diff options
876 files changed, 12629 insertions, 7095 deletions
@@ -191,6 +191,10 @@ Gao Xiang <xiang@kernel.org> <gaoxiang25@huawei.com> Gao Xiang <xiang@kernel.org> <hsiangkao@aol.com> Gao Xiang <xiang@kernel.org> <hsiangkao@linux.alibaba.com> Gao Xiang <xiang@kernel.org> <hsiangkao@redhat.com> +Geliang Tang <geliang.tang@linux.dev> <geliang.tang@suse.com> +Geliang Tang <geliang.tang@linux.dev> <geliangtang@xiaomi.com> +Geliang Tang <geliang.tang@linux.dev> <geliangtang@gmail.com> +Geliang Tang <geliang.tang@linux.dev> <geliangtang@163.com> Georgi Djakov <djakov@kernel.org> <georgi.djakov@linaro.org> Gerald Schaefer <gerald.schaefer@linux.ibm.com> <geraldsc@de.ibm.com> Gerald Schaefer <gerald.schaefer@linux.ibm.com> <gerald.schaefer@de.ibm.com> @@ -266,6 +270,9 @@ Jens Osterkamp <Jens.Osterkamp@de.ibm.com> Jernej Skrabec <jernej.skrabec@gmail.com> <jernej.skrabec@siol.net> Jessica Zhang <quic_jesszhan@quicinc.com> <jesszhan@codeaurora.org> Jilai Wang <quic_jilaiw@quicinc.com> <jilaiw@codeaurora.org> +Jiri Kosina <jikos@kernel.org> <jikos@jikos.cz> +Jiri Kosina <jikos@kernel.org> <jkosina@suse.cz> +Jiri Kosina <jikos@kernel.org> <jkosina@suse.com> Jiri Pirko <jiri@resnulli.us> <jiri@nvidia.com> Jiri Pirko <jiri@resnulli.us> <jiri@mellanox.com> Jiri Pirko <jiri@resnulli.us> <jpirko@redhat.com> @@ -370,7 +377,7 @@ Martin Kepplinger <martink@posteo.de> <martin.kepplinger@ginzinger.com> Martin Kepplinger <martink@posteo.de> <martin.kepplinger@puri.sm> Martin Kepplinger <martink@posteo.de> <martin.kepplinger@theobroma-systems.com> Martyna Szapar-Mudlaw <martyna.szapar-mudlaw@linux.intel.com> <martyna.szapar-mudlaw@intel.com> -Mathieu Othacehe <m.othacehe@gmail.com> +Mathieu Othacehe <m.othacehe@gmail.com> <othacehe@gnu.org> Mat Martineau <martineau@kernel.org> <mathew.j.martineau@linux.intel.com> Mat Martineau <martineau@kernel.org> <mathewm@codeaurora.org> Matthew Wilcox <willy@infradead.org> <matthew.r.wilcox@intel.com> @@ -429,6 +436,7 @@ Muna Sinada <quic_msinada@quicinc.com> <msinada@codeaurora.org> Murali Nalajala <quic_mnalajal@quicinc.com> <mnalajal@codeaurora.org> Mythri P K <mythripk@ti.com> Nadia Yvette Chambers <nyc@holomorphy.com> William Lee Irwin III <wli@holomorphy.com> +Naoya Horiguchi <naoya.horiguchi@nec.com> <n-horiguchi@ah.jp.nec.com> Nathan Chancellor <nathan@kernel.org> <natechancellor@gmail.com> Neeraj Upadhyay <quic_neeraju@quicinc.com> <neeraju@codeaurora.org> Neil Armstrong <neil.armstrong@linaro.org> <narmstrong@baylibre.com> @@ -630,4 +638,5 @@ Wolfram Sang <wsa@kernel.org> <w.sang@pengutronix.de> Wolfram Sang <wsa@kernel.org> <wsa@the-dreams.de> Yakir Yang <kuankuan.y@gmail.com> <ykk@rock-chips.com> Yusuke Goda <goda.yusuke@renesas.com> +Zack Rusin <zack.rusin@broadcom.com> <zackr@vmware.com> Zhu Yanjun <zyjzyj2000@gmail.com> <yanjunz@nvidia.com> @@ -1855,6 +1855,10 @@ D: Fedora kernel maintenance (2003-2014). D: 'Trinity' and similar fuzz testing work. D: Misc/Other. +N: Tom Joseph +E: tjoseph@cadence.com +D: Cadence PCIe driver + N: Martin Josfsson E: gandalf@wlug.westbo.se P: 1024D/F6B6D3B1 7610 7CED 5C34 4AA6 DBA2 8BE1 5A6D AF95 F6B6 D3B1 @@ -2126,6 +2130,10 @@ S: 2213 La Terrace Circle S: San Jose, CA 95123 S: USA +N: Mike Kravetz +E: mike.kravetz@oracle.com +D: Maintenance and development of the hugetlb subsystem + N: Andreas S. Krebs E: akrebs@altavista.net D: CYPRESS CY82C693 chipset IDE, Digital's PC-Alpha 164SX boards diff --git a/Documentation/arch/x86/cpuinfo.rst b/Documentation/arch/x86/cpuinfo.rst index 08246e8ac835..8895784d4784 100644 --- a/Documentation/arch/x86/cpuinfo.rst +++ b/Documentation/arch/x86/cpuinfo.rst @@ -7,27 +7,74 @@ x86 Feature Flags Introduction ============ -On x86, flags appearing in /proc/cpuinfo have an X86_FEATURE definition -in arch/x86/include/asm/cpufeatures.h. If the kernel cares about a feature -or KVM want to expose the feature to a KVM guest, it can and should have -an X86_FEATURE_* defined. These flags represent hardware features as -well as software features. - -If users want to know if a feature is available on a given system, they -try to find the flag in /proc/cpuinfo. If a given flag is present, it -means that the kernel supports it and is currently making it available. -If such flag represents a hardware feature, it also means that the -hardware supports it. - -If the expected flag does not appear in /proc/cpuinfo, things are murkier. -Users need to find out the reason why the flag is missing and find the way -how to enable it, which is not always easy. There are several factors that -can explain missing flags: the expected feature failed to enable, the feature -is missing in hardware, platform firmware did not enable it, the feature is -disabled at build or run time, an old kernel is in use, or the kernel does -not support the feature and thus has not enabled it. In general, /proc/cpuinfo -shows features which the kernel supports. For a full list of CPUID flags -which the CPU supports, use tools/arch/x86/kcpuid. +The list of feature flags in /proc/cpuinfo is not complete and +represents an ill-fated attempt from long time ago to put feature flags +in an easy to find place for userspace. + +However, the amount of feature flags is growing by the CPU generation, +leading to unparseable and unwieldy /proc/cpuinfo. + +What is more, those feature flags do not even need to be in that file +because userspace doesn't care about them - glibc et al already use +CPUID to find out what the target machine supports and what not. + +And even if it doesn't show a particular feature flag - although the CPU +still does have support for the respective hardware functionality and +said CPU supports CPUID faulting - userspace can simply probe for the +feature and figure out if it is supported or not, regardless of whether +it is being advertised somewhere. + +Furthermore, those flag strings become an ABI the moment they appear +there and maintaining them forever when nothing even uses them is a lot +of wasted effort. + +So, the current use of /proc/cpuinfo is to show features which the +kernel has *enabled* and *supports*. As in: the CPUID feature flag is +there, there's an additional setup which the kernel has done while +booting and the functionality is ready to use. A perfect example for +that is "user_shstk" where additional code enablement is present in the +kernel to support shadow stack for user programs. + +So, if users want to know if a feature is available on a given system, +they try to find the flag in /proc/cpuinfo. If a given flag is present, +it means that + +* the kernel knows about the feature enough to have an X86_FEATURE bit + +* the kernel supports it and is currently making it available either to + userspace or some other part of the kernel + +* if the flag represents a hardware feature the hardware supports it. + +The absence of a flag in /proc/cpuinfo by itself means almost nothing to +an end user. + +On the one hand, a feature like "vaes" might be fully available to user +applications on a kernel that has not defined X86_FEATURE_VAES and thus +there is no "vaes" in /proc/cpuinfo. + +On the other hand, a new kernel running on non-VAES hardware would also +have no "vaes" in /proc/cpuinfo. There's no way for an application or +user to tell the difference. + +The end result is that the flags field in /proc/cpuinfo is marginally +useful for kernel debugging, but not really for anything else. +Applications should instead use things like the glibc facilities for +querying CPU support. Users should rely on tools like +tools/arch/x86/kcpuid and cpuid(1). + +Regarding implementation, flags appearing in /proc/cpuinfo have an +X86_FEATURE definition in arch/x86/include/asm/cpufeatures.h. These flags +represent hardware features as well as software features. + +If the kernel cares about a feature or KVM want to expose the feature to +a KVM guest, it should only then expose it to the guest when the guest +needs to parse /proc/cpuinfo. Which, as mentioned above, is highly +unlikely. KVM can synthesize the CPUID bit and the KVM guest can simply +query CPUID and figure out what the hypervisor supports and what not. As +already stated, /proc/cpuinfo is not a dumping ground for useless +feature flags. + How are feature flags created? ============================== diff --git a/Documentation/devicetree/bindings/display/panel/panel-simple-dsi.yaml b/Documentation/devicetree/bindings/display/panel/panel-simple-dsi.yaml index 73674baea75d..f9160d7bac3c 100644 --- a/Documentation/devicetree/bindings/display/panel/panel-simple-dsi.yaml +++ b/Documentation/devicetree/bindings/display/panel/panel-simple-dsi.yaml @@ -42,6 +42,8 @@ properties: - lg,acx467akm-7 # LG Corporation 7" WXGA TFT LCD panel - lg,ld070wx3-sl01 + # LG Corporation 5" HD TFT LCD panel + - lg,lh500wx1-sd03 # One Stop Displays OSD101T2587-53TS 10.1" 1920x1200 panel - osddisplays,osd101t2587-53ts # Panasonic 10" WUXGA TFT LCD panel diff --git a/Documentation/devicetree/bindings/display/panel/panel-simple.yaml b/Documentation/devicetree/bindings/display/panel/panel-simple.yaml index 3ec9ee95045f..11422af3477e 100644 --- a/Documentation/devicetree/bindings/display/panel/panel-simple.yaml +++ b/Documentation/devicetree/bindings/display/panel/panel-simple.yaml @@ -208,8 +208,6 @@ properties: - lemaker,bl035-rgb-002 # LG 7" (800x480 pixels) TFT LCD panel - lg,lb070wv8 - # LG Corporation 5" HD TFT LCD panel - - lg,lh500wx1-sd03 # LG LP079QX1-SP0V 7.9" (1536x2048 pixels) TFT LCD panel - lg,lp079qx1-sp0v # LG 9.7" (2048x1536 pixels) TFT LCD panel diff --git a/Documentation/devicetree/bindings/nvmem/mxs-ocotp.yaml b/Documentation/devicetree/bindings/nvmem/mxs-ocotp.yaml index f43186f98607..d9287be89877 100644 --- a/Documentation/devicetree/bindings/nvmem/mxs-ocotp.yaml +++ b/Documentation/devicetree/bindings/nvmem/mxs-ocotp.yaml @@ -15,9 +15,11 @@ allOf: properties: compatible: - enum: - - fsl,imx23-ocotp - - fsl,imx28-ocotp + items: + - enum: + - fsl,imx23-ocotp + - fsl,imx28-ocotp + - const: fsl,ocotp reg: maxItems: 1 @@ -35,7 +37,7 @@ unevaluatedProperties: false examples: - | ocotp: efuse@8002c000 { - compatible = "fsl,imx28-ocotp"; + compatible = "fsl,imx28-ocotp", "fsl,ocotp"; #address-cells = <1>; #size-cells = <1>; reg = <0x8002c000 0x2000>; diff --git a/Documentation/filesystems/fuse-io.rst b/Documentation/filesystems/fuse-io.rst index 255a368fe534..6464de4266ad 100644 --- a/Documentation/filesystems/fuse-io.rst +++ b/Documentation/filesystems/fuse-io.rst @@ -15,7 +15,8 @@ The direct-io mode can be selected with the FOPEN_DIRECT_IO flag in the FUSE_OPEN reply. In direct-io mode the page cache is completely bypassed for reads and writes. -No read-ahead takes place. Shared mmap is disabled. +No read-ahead takes place. Shared mmap is disabled by default. To allow shared +mmap, the FUSE_DIRECT_IO_ALLOW_MMAP flag may be enabled in the FUSE_INIT reply. In cached mode reads may be satisfied from the page cache, and data may be read-ahead by the kernel to fill the cache. The cache is always kept consistent diff --git a/Documentation/filesystems/porting.rst b/Documentation/filesystems/porting.rst index 878e72b2f8b7..ced3a6761329 100644 --- a/Documentation/filesystems/porting.rst +++ b/Documentation/filesystems/porting.rst @@ -1061,3 +1061,15 @@ export_operations ->encode_fh() no longer has a default implementation to encode FILEID_INO32_GEN* file handles. Filesystems that used the default implementation may use the generic helper generic_encode_ino32_fh() explicitly. + +--- + +**recommended** + +Block device freezing and thawing have been moved to holder operations. + +Before this change, get_active_super() would only be able to find the +superblock of the main block device, i.e., the one stored in sb->s_bdev. Block +device freezing now works for any block device owned by a given superblock, not +just the main block device. The get_active_super() helper and bd_fsfreeze_sb +pointer are gone. diff --git a/Documentation/i2c/i2c-address-translators.rst b/Documentation/i2c/i2c-address-translators.rst index b22ce9f41ecf..6845c114e472 100644 --- a/Documentation/i2c/i2c-address-translators.rst +++ b/Documentation/i2c/i2c-address-translators.rst @@ -71,7 +71,7 @@ Transaction: - Physical I2C transaction on bus A, slave address 0x20 - ATR chip detects transaction on address 0x20, finds it in table, propagates transaction on bus B with address translated to 0x10, - keeps clock streched on bus A waiting for reply + keeps clock stretched on bus A waiting for reply - Slave X chip (on bus B) detects transaction at its own physical address 0x10 and replies normally - ATR chip stops clock stretching and forwards reply on bus A, diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index 4dfe0d9a57bb..7afff42612e9 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -2511,7 +2511,7 @@ temp_valid_lft - INTEGER temp_prefered_lft - INTEGER Preferred lifetime (in seconds) for temporary addresses. If temp_prefered_lft is less than the minimum required lifetime (typically - 5 seconds), the preferred lifetime is the minimum required. If + 5 seconds), temporary addresses will not be created. If temp_prefered_lft is greater than temp_valid_lft, the preferred lifetime is temp_valid_lft. diff --git a/MAINTAINERS b/MAINTAINERS index e2c6187a3ac8..550d98cf14c6 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4127,7 +4127,6 @@ M: Franky Lin <franky.lin@broadcom.com> M: Hante Meuleman <hante.meuleman@broadcom.com> L: linux-wireless@vger.kernel.org L: brcm80211-dev-list.pdl@broadcom.com -L: SHA-cyfmac-dev-list@infineon.com S: Supported F: drivers/net/wireless/broadcom/brcm80211/ @@ -6050,10 +6049,8 @@ M: Mikulas Patocka <mpatocka@redhat.com> M: dm-devel@lists.linux.dev L: dm-devel@lists.linux.dev S: Maintained -W: http://sources.redhat.com/dm Q: http://patchwork.kernel.org/project/dm-devel/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm.git -T: quilt http://people.redhat.com/agk/patches/linux/editing/ F: Documentation/admin-guide/device-mapper/ F: drivers/md/Kconfig F: drivers/md/Makefile @@ -6904,8 +6901,8 @@ T: git git://anongit.freedesktop.org/drm/drm-misc F: drivers/gpu/drm/vboxvideo/ DRM DRIVER FOR VMWARE VIRTUAL GPU -M: Zack Rusin <zackr@vmware.com> -R: VMware Graphics Reviewers <linux-graphics-maintainer@vmware.com> +M: Zack Rusin <zack.rusin@broadcom.com> +R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com> L: dri-devel@lists.freedesktop.org S: Supported T: git git://anongit.freedesktop.org/drm/drm-misc @@ -8106,6 +8103,7 @@ F: include/trace/events/fs_dax.h FILESYSTEMS (VFS and infrastructure) M: Alexander Viro <viro@zeniv.linux.org.uk> M: Christian Brauner <brauner@kernel.org> +R: Jan Kara <jack@suse.cz> L: linux-fsdevel@vger.kernel.org S: Maintained F: fs/* @@ -8126,6 +8124,16 @@ F: fs/exportfs/ F: fs/fhandle.c F: include/linux/exportfs.h +FILESYSTEMS [IDMAPPED MOUNTS] +M: Christian Brauner <brauner@kernel.org> +M: Seth Forshee <sforshee@kernel.org> +L: linux-fsdevel@vger.kernel.org +S: Maintained +F: Documentation/filesystems/idmappings.rst +F: fs/mnt_idmapping.c +F: include/linux/mnt_idmapping.* +F: tools/testing/selftests/mount_setattr/ + FILESYSTEMS [IOMAP] M: Christian Brauner <brauner@kernel.org> R: Darrick J. Wong <djwong@kernel.org> @@ -8135,6 +8143,15 @@ S: Supported F: fs/iomap/ F: include/linux/iomap.h +FILESYSTEMS [STACKABLE] +M: Miklos Szeredi <miklos@szeredi.hu> +M: Amir Goldstein <amir73il@gmail.com> +L: linux-fsdevel@vger.kernel.org +L: linux-unionfs@vger.kernel.org +S: Maintained +F: fs/backing-file.c +F: include/linux/backing-file.h + FINTEK F75375S HARDWARE MONITOR AND FAN CONTROLLER DRIVER M: Riku Voipio <riku.voipio@iki.fi> L: linux-hwmon@vger.kernel.org @@ -9002,12 +9019,9 @@ K: (devm_)?gpio_regmap_(un)?register GPIO SUBSYSTEM M: Linus Walleij <linus.walleij@linaro.org> M: Bartosz Golaszewski <brgl@bgdev.pl> -R: Andy Shevchenko <andy@kernel.org> L: linux-gpio@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/brgl/linux.git -F: Documentation/ABI/obsolete/sysfs-gpio -F: Documentation/ABI/testing/gpio-cdev F: Documentation/admin-guide/gpio/ F: Documentation/devicetree/bindings/gpio/ F: Documentation/driver-api/gpio/ @@ -9016,6 +9030,16 @@ F: include/dt-bindings/gpio/ F: include/linux/gpio.h F: include/linux/gpio/ F: include/linux/of_gpio.h + +GPIO UAPI +M: Bartosz Golaszewski <brgl@bgdev.pl> +R: Kent Gibson <warthog618@gmail.com> +L: linux-gpio@vger.kernel.org +S: Maintained +T: git git://git.kernel.org/pub/scm/linux/kernel/git/brgl/linux.git +F: Documentation/ABI/obsolete/sysfs-gpio +F: Documentation/ABI/testing/gpio-cdev +F: drivers/gpio/gpiolib-cdev.c F: include/uapi/linux/gpio.h F: tools/gpio/ @@ -9526,6 +9550,7 @@ F: drivers/bus/hisi_lpc.c HISILICON NETWORK SUBSYSTEM 3 DRIVER (HNS3) M: Yisen Zhuang <yisen.zhuang@huawei.com> M: Salil Mehta <salil.mehta@huawei.com> +M: Jijie Shao <shaojijie@huawei.com> L: netdev@vger.kernel.org S: Maintained W: http://www.hisilicon.com @@ -9762,7 +9787,6 @@ F: Documentation/networking/device_drivers/ethernet/huawei/hinic.rst F: drivers/net/ethernet/huawei/hinic/ HUGETLB SUBSYSTEM -M: Mike Kravetz <mike.kravetz@oracle.com> M: Muchun Song <muchun.song@linux.dev> L: linux-mm@kvack.org S: Maintained @@ -9786,8 +9810,8 @@ T: git git://linuxtv.org/media_tree.git F: drivers/media/platform/st/sti/hva HWPOISON MEMORY FAILURE HANDLING -M: Naoya Horiguchi <naoya.horiguchi@nec.com> -R: Miaohe Lin <linmiaohe@huawei.com> +M: Miaohe Lin <linmiaohe@huawei.com> +R: Naoya Horiguchi <naoya.horiguchi@nec.com> L: linux-mm@kvack.org S: Maintained F: mm/hwpoison-inject.c @@ -10198,16 +10222,6 @@ S: Maintained W: https://github.com/o2genum/ideapad-slidebar F: drivers/input/misc/ideapad_slidebar.c -IDMAPPED MOUNTS -M: Christian Brauner <brauner@kernel.org> -M: Seth Forshee <sforshee@kernel.org> -L: linux-fsdevel@vger.kernel.org -S: Maintained -T: git git://git.kernel.org/pub/scm/linux/kernel/git/vfs/idmapping.git -F: Documentation/filesystems/idmappings.rst -F: include/linux/mnt_idmapping.* -F: tools/testing/selftests/mount_setattr/ - IDT VersaClock 5 CLOCK DRIVER M: Luca Ceresoli <luca@lucaceresoli.net> S: Maintained @@ -10640,6 +10654,7 @@ F: drivers/gpio/gpio-pch.c F: drivers/gpio/gpio-sch.c F: drivers/gpio/gpio-sodaville.c F: drivers/gpio/gpio-tangier.c +F: drivers/gpio/gpio-tangier.h INTEL GVT-g DRIVERS (Intel GPU Virtualization) M: Zhenyu Wang <zhenyuw@linux.intel.com> @@ -11470,6 +11485,7 @@ F: scripts/*vmlinux* F: scripts/Kbuild* F: scripts/Makefile* F: scripts/basic/ +F: scripts/clang-tools/ F: scripts/dummy-tools/ F: scripts/mk* F: scripts/mod/ @@ -12189,6 +12205,8 @@ LINUX FOR POWERPC (32-BIT AND 64-BIT) M: Michael Ellerman <mpe@ellerman.id.au> R: Nicholas Piggin <npiggin@gmail.com> R: Christophe Leroy <christophe.leroy@csgroup.eu> +R: Aneesh Kumar K.V <aneesh.kumar@kernel.org> +R: Naveen N. Rao <naveen.n.rao@linux.ibm.com> L: linuxppc-dev@lists.ozlabs.org S: Supported W: https://github.com/linuxppc/wiki/wiki @@ -12814,7 +12832,7 @@ S: Maintained F: drivers/net/ethernet/marvell/mvneta.* MARVELL MVPP2 ETHERNET DRIVER -M: Marcin Wojtas <mw@semihalf.com> +M: Marcin Wojtas <marcin.s.wojtas@gmail.com> M: Russell King <linux@armlinux.org.uk> L: netdev@vger.kernel.org S: Maintained @@ -15077,6 +15095,7 @@ K: \bmdo_ NETWORKING [MPTCP] M: Matthieu Baerts <matttbe@kernel.org> M: Mat Martineau <martineau@kernel.org> +R: Geliang Tang <geliang.tang@linux.dev> L: netdev@vger.kernel.org L: mptcp@lists.linux.dev S: Maintained @@ -15424,7 +15443,7 @@ F: Documentation/devicetree/bindings/net/bluetooth/nxp,88w8987-bt.yaml F: drivers/bluetooth/btnxpuart.c NXP C45 TJA11XX PHY DRIVER -M: Radu Pirea <radu-nicolae.pirea@oss.nxp.com> +M: Andrei Botila <andrei.botila@oss.nxp.com> L: netdev@vger.kernel.org S: Maintained F: drivers/net/phy/nxp-c45-tja11xx.c @@ -16448,11 +16467,10 @@ F: Documentation/devicetree/bindings/pci/pci-armada8k.txt F: drivers/pci/controller/dwc/pcie-armada8k.c PCI DRIVER FOR CADENCE PCIE IP -M: Tom Joseph <tjoseph@cadence.com> L: linux-pci@vger.kernel.org -S: Maintained +S: Orphan F: Documentation/devicetree/bindings/pci/cdns,* -F: drivers/pci/controller/cadence/ +F: drivers/pci/controller/cadence/*cadence* PCI DRIVER FOR FREESCALE LAYERSCAPE M: Minghuan Lian <minghuan.Lian@nxp.com> @@ -19564,7 +19582,6 @@ S: Maintained F: drivers/misc/sgi-xp/ SHARED MEMORY COMMUNICATIONS (SMC) SOCKETS -M: Karsten Graul <kgraul@linux.ibm.com> M: Wenjia Zhang <wenjia@linux.ibm.com> M: Jan Karcher <jaka@linux.ibm.com> R: D. Wythe <alibuda@linux.alibaba.com> @@ -23207,9 +23224,8 @@ F: drivers/misc/vmw_vmci/ F: include/linux/vmw_vmci* VMWARE VMMOUSE SUBDRIVER -M: Zack Rusin <zackr@vmware.com> -R: VMware Graphics Reviewers <linux-graphics-maintainer@vmware.com> -R: VMware PV-Drivers Reviewers <pv-drivers@vmware.com> +M: Zack Rusin <zack.rusin@broadcom.com> +R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com> L: linux-input@vger.kernel.org S: Supported F: drivers/input/mouse/vmmouse.c @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 7 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = NAME = Hurr durr I'ma ninja sloth # *DOCUMENTATION* diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl index 18c842ca6c32..186e785f5b56 100644 --- a/arch/alpha/kernel/syscalls/syscall.tbl +++ b/arch/alpha/kernel/syscalls/syscall.tbl @@ -496,3 +496,5 @@ 564 common futex_wake sys_futex_wake 565 common futex_wait sys_futex_wait 566 common futex_requeue sys_futex_requeue +567 common statmount sys_statmount +568 common listmount sys_listmount diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 3162db540ee9..1b0483c51cc1 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -49,7 +49,6 @@ config ARC select OF select OF_EARLY_FLATTREE select PCI_SYSCALL if PCI - select PERF_USE_VMALLOC if ARC_CACHE_VIPT_ALIASING select HAVE_ARCH_JUMP_LABEL if ISA_ARCV2 && !CPU_ENDIAN_BE32 select TRACE_IRQFLAGS_SUPPORT @@ -232,10 +231,6 @@ config ARC_CACHE_PAGES Note that Global I/D ENABLE + Per Page DISABLE works but corollary Global DISABLE + Per Page ENABLE won't work -config ARC_CACHE_VIPT_ALIASING - bool "Support VIPT Aliasing D$" - depends on ARC_HAS_DCACHE && ISA_ARCOMPACT - endif #ARC_CACHE config ARC_HAS_ICCM diff --git a/arch/arc/include/asm/cacheflush.h b/arch/arc/include/asm/cacheflush.h index bd5b1a9a0544..563af3e75f01 100644 --- a/arch/arc/include/asm/cacheflush.h +++ b/arch/arc/include/asm/cacheflush.h @@ -44,31 +44,10 @@ void dma_cache_wback(phys_addr_t start, unsigned long sz); #define flush_cache_dup_mm(mm) /* called on fork (VIVT only) */ -#ifndef CONFIG_ARC_CACHE_VIPT_ALIASING - #define flush_cache_mm(mm) /* called on munmap/exit */ #define flush_cache_range(mm, u_vstart, u_vend) #define flush_cache_page(vma, u_vaddr, pfn) /* PF handling/COW-break */ -#else /* VIPT aliasing dcache */ - -/* To clear out stale userspace mappings */ -void flush_cache_mm(struct mm_struct *mm); -void flush_cache_range(struct vm_area_struct *vma, - unsigned long start,unsigned long end); -void flush_cache_page(struct vm_area_struct *vma, - unsigned long user_addr, unsigned long page); - -/* - * To make sure that userspace mapping is flushed to memory before - * get_user_pages() uses a kernel mapping to access the page - */ -#define ARCH_HAS_FLUSH_ANON_PAGE -void flush_anon_page(struct vm_area_struct *vma, - struct page *page, unsigned long u_vaddr); - -#endif /* CONFIG_ARC_CACHE_VIPT_ALIASING */ - /* * A new pagecache page has PG_arch_1 clear - thus dcache dirty by default * This works around some PIO based drivers which don't call flush_dcache_page @@ -76,28 +55,6 @@ void flush_anon_page(struct vm_area_struct *vma, */ #define PG_dc_clean PG_arch_1 -#define CACHE_COLORS_NUM 4 -#define CACHE_COLORS_MSK (CACHE_COLORS_NUM - 1) -#define CACHE_COLOR(addr) (((unsigned long)(addr) >> (PAGE_SHIFT)) & CACHE_COLORS_MSK) - -/* - * Simple wrapper over config option - * Bootup code ensures that hardware matches kernel configuration - */ -static inline int cache_is_vipt_aliasing(void) -{ - return IS_ENABLED(CONFIG_ARC_CACHE_VIPT_ALIASING); -} - -/* - * checks if two addresses (after page aligning) index into same cache set - */ -#define addr_not_cache_congruent(addr1, addr2) \ -({ \ - cache_is_vipt_aliasing() ? \ - (CACHE_COLOR(addr1) != CACHE_COLOR(addr2)) : 0; \ -}) - #define copy_to_user_page(vma, page, vaddr, dst, src, len) \ do { \ memcpy(dst, src, len); \ diff --git a/arch/arc/include/asm/entry-arcv2.h b/arch/arc/include/asm/entry-arcv2.h index 4d13320e0c1b..3802a2daaf86 100644 --- a/arch/arc/include/asm/entry-arcv2.h +++ b/arch/arc/include/asm/entry-arcv2.h @@ -291,4 +291,36 @@ /* M = 8-1 N = 8 */ .endm +.macro SAVE_ABI_CALLEE_REGS + push r13 + push r14 + push r15 + push r16 + push r17 + push r18 + push r19 + push r20 + push r21 + push r22 + push r23 + push r24 + push r25 +.endm + +.macro RESTORE_ABI_CALLEE_REGS + pop r25 + pop r24 + pop r23 + pop r22 + pop r21 + pop r20 + pop r19 + pop r18 + pop r17 + pop r16 + pop r15 + pop r14 + pop r13 +.endm + #endif diff --git a/arch/arc/include/asm/entry-compact.h b/arch/arc/include/asm/entry-compact.h index a0e760eb35a8..92c3e9f13252 100644 --- a/arch/arc/include/asm/entry-compact.h +++ b/arch/arc/include/asm/entry-compact.h @@ -33,6 +33,91 @@ #include <asm/irqflags-compact.h> #include <asm/thread_info.h> /* For THREAD_SIZE */ +/* Note on the LD/ST addr modes with addr reg wback + * + * LD.a same as LD.aw + * + * LD.a reg1, [reg2, x] => Pre Incr + * Eff Addr for load = [reg2 + x] + * + * LD.ab reg1, [reg2, x] => Post Incr + * Eff Addr for load = [reg2] + */ + +.macro PUSHAX aux + lr r9, [\aux] + push r9 +.endm + +.macro POPAX aux + pop r9 + sr r9, [\aux] +.endm + +.macro SAVE_R0_TO_R12 + push r0 + push r1 + push r2 + push r3 + push r4 + push r5 + push r6 + push r7 + push r8 + push r9 + push r10 + push r11 + push r12 +.endm + +.macro RESTORE_R12_TO_R0 + pop r12 + pop r11 + pop r10 + pop r9 + pop r8 + pop r7 + pop r6 + pop r5 + pop r4 + pop r3 + pop r2 + pop r1 + pop r0 +.endm + +.macro SAVE_ABI_CALLEE_REGS + push r13 + push r14 + push r15 + push r16 + push r17 + push r18 + push r19 + push r20 + push r21 + push r22 + push r23 + push r24 + push r25 +.endm + +.macro RESTORE_ABI_CALLEE_REGS + pop r25 + pop r24 + pop r23 + pop r22 + pop r21 + pop r20 + pop r19 + pop r18 + pop r17 + pop r16 + pop r15 + pop r14 + pop r13 +.endm + /*-------------------------------------------------------------- * Switch to Kernel Mode stack if SP points to User Mode stack * @@ -235,7 +320,7 @@ SWITCH_TO_KERNEL_STK - PUSH 0x003\LVL\()abcd /* Dummy ECR */ + st.a 0x003\LVL\()abcd, [sp, -4] /* Dummy ECR */ sub sp, sp, 8 /* skip orig_r0 (not needed) skip pt_regs->sp, already saved above */ diff --git a/arch/arc/include/asm/entry.h b/arch/arc/include/asm/entry.h index 49c2e090cb5c..cf1ba376e992 100644 --- a/arch/arc/include/asm/entry.h +++ b/arch/arc/include/asm/entry.h @@ -21,114 +21,12 @@ #include <asm/entry-arcv2.h> #endif -/* Note on the LD/ST addr modes with addr reg wback - * - * LD.a same as LD.aw - * - * LD.a reg1, [reg2, x] => Pre Incr - * Eff Addr for load = [reg2 + x] - * - * LD.ab reg1, [reg2, x] => Post Incr - * Eff Addr for load = [reg2] - */ - -.macro PUSH reg - st.a \reg, [sp, -4] -.endm - -.macro PUSHAX aux - lr r9, [\aux] - PUSH r9 -.endm - -.macro POP reg - ld.ab \reg, [sp, 4] -.endm - -.macro POPAX aux - POP r9 - sr r9, [\aux] -.endm - -/*-------------------------------------------------------------- - * Helpers to save/restore Scratch Regs: - * used by Interrupt/Exception Prologue/Epilogue - *-------------------------------------------------------------*/ -.macro SAVE_R0_TO_R12 - PUSH r0 - PUSH r1 - PUSH r2 - PUSH r3 - PUSH r4 - PUSH r5 - PUSH r6 - PUSH r7 - PUSH r8 - PUSH r9 - PUSH r10 - PUSH r11 - PUSH r12 -.endm - -.macro RESTORE_R12_TO_R0 - POP r12 - POP r11 - POP r10 - POP r9 - POP r8 - POP r7 - POP r6 - POP r5 - POP r4 - POP r3 - POP r2 - POP r1 - POP r0 - -.endm - -/*-------------------------------------------------------------- - * Helpers to save/restore callee-saved regs: - * used by several macros below - *-------------------------------------------------------------*/ -.macro SAVE_R13_TO_R25 - PUSH r13 - PUSH r14 - PUSH r15 - PUSH r16 - PUSH r17 - PUSH r18 - PUSH r19 - PUSH r20 - PUSH r21 - PUSH r22 - PUSH r23 - PUSH r24 - PUSH r25 -.endm - -.macro RESTORE_R25_TO_R13 - POP r25 - POP r24 - POP r23 - POP r22 - POP r21 - POP r20 - POP r19 - POP r18 - POP r17 - POP r16 - POP r15 - POP r14 - POP r13 -.endm - /* * save user mode callee regs as struct callee_regs * - needed by fork/do_signal/unaligned-access-emulation. */ .macro SAVE_CALLEE_SAVED_USER - SAVE_R13_TO_R25 + SAVE_ABI_CALLEE_REGS .endm /* @@ -136,18 +34,18 @@ * - could have been changed by ptrace tracer or unaligned-access fixup */ .macro RESTORE_CALLEE_SAVED_USER - RESTORE_R25_TO_R13 + RESTORE_ABI_CALLEE_REGS .endm /* * save/restore kernel mode callee regs at the time of context switch */ .macro SAVE_CALLEE_SAVED_KERNEL - SAVE_R13_TO_R25 + SAVE_ABI_CALLEE_REGS .endm .macro RESTORE_CALLEE_SAVED_KERNEL - RESTORE_R25_TO_R13 + RESTORE_ABI_CALLEE_REGS .endm /*-------------------------------------------------------------- diff --git a/arch/arc/include/asm/hugepage.h b/arch/arc/include/asm/hugepage.h index ef8d4166370c..8a2441670a8f 100644 --- a/arch/arc/include/asm/hugepage.h +++ b/arch/arc/include/asm/hugepage.h @@ -10,6 +10,13 @@ #include <linux/types.h> #include <asm-generic/pgtable-nopmd.h> +/* + * Hugetlb definitions. + */ +#define HPAGE_SHIFT PMD_SHIFT +#define HPAGE_SIZE (_AC(1, UL) << HPAGE_SHIFT) +#define HPAGE_MASK (~(HPAGE_SIZE - 1)) + static inline pte_t pmd_pte(pmd_t pmd) { return __pte(pmd_val(pmd)); diff --git a/arch/arc/include/asm/ptrace.h b/arch/arc/include/asm/ptrace.h index 4a2b30fb5a98..00b9318e551e 100644 --- a/arch/arc/include/asm/ptrace.h +++ b/arch/arc/include/asm/ptrace.h @@ -54,6 +54,10 @@ struct pt_regs { ecr_reg ecr; }; +struct callee_regs { + unsigned long r25, r24, r23, r22, r21, r20, r19, r18, r17, r16, r15, r14, r13; +}; + #define MAX_REG_OFFSET offsetof(struct pt_regs, ecr) #else @@ -92,16 +96,14 @@ struct pt_regs { unsigned long status32; }; -#define MAX_REG_OFFSET offsetof(struct pt_regs, status32) - -#endif - -/* Callee saved registers - need to be saved only when you are scheduled out */ - struct callee_regs { unsigned long r25, r24, r23, r22, r21, r20, r19, r18, r17, r16, r15, r14, r13; }; +#define MAX_REG_OFFSET offsetof(struct pt_regs, status32) + +#endif + #define instruction_pointer(regs) ((regs)->ret) #define profile_pc(regs) instruction_pointer(regs) diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index 4dcf8589b708..d08a5092c2b4 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -153,7 +153,7 @@ static int arcv2_mumbojumbo(int c, struct cpuinfo_arc *info, char *buf, int len) { int n = 0; #ifdef CONFIG_ISA_ARCV2 - const char *release, *cpu_nm, *isa_nm = "ARCv2"; + const char *release = "", *cpu_nm = "HS38", *isa_nm = "ARCv2"; int dual_issue = 0, dual_enb = 0, mpy_opt, present; int bpu_full, bpu_cache, bpu_pred, bpu_ret_stk; char mpy_nm[16], lpb_nm[32]; @@ -172,8 +172,6 @@ static int arcv2_mumbojumbo(int c, struct cpuinfo_arc *info, char *buf, int len) * releases only update it. */ - cpu_nm = "HS38"; - if (info->arcver > 0x50 && info->arcver <= 0x53) { release = arc_hs_rel[info->arcver - 0x51].str; } else { diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c index 0b3bb529d246..8f6f4a542964 100644 --- a/arch/arc/kernel/signal.c +++ b/arch/arc/kernel/signal.c @@ -62,7 +62,7 @@ struct rt_sigframe { unsigned int sigret_magic; }; -static int save_arcv2_regs(struct sigcontext *mctx, struct pt_regs *regs) +static int save_arcv2_regs(struct sigcontext __user *mctx, struct pt_regs *regs) { int err = 0; #ifndef CONFIG_ISA_ARCOMPACT @@ -75,12 +75,12 @@ static int save_arcv2_regs(struct sigcontext *mctx, struct pt_regs *regs) #else v2abi.r58 = v2abi.r59 = 0; #endif - err = __copy_to_user(&mctx->v2abi, &v2abi, sizeof(v2abi)); + err = __copy_to_user(&mctx->v2abi, (void const *)&v2abi, sizeof(v2abi)); #endif return err; } -static int restore_arcv2_regs(struct sigcontext *mctx, struct pt_regs *regs) +static int restore_arcv2_regs(struct sigcontext __user *mctx, struct pt_regs *regs) { int err = 0; #ifndef CONFIG_ISA_ARCOMPACT diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c index f7e05c146637..9106ceac323c 100644 --- a/arch/arc/mm/cache.c +++ b/arch/arc/mm/cache.c @@ -145,10 +145,9 @@ dc_chk: p_dc->sz_k = 1 << (dbcr.sz - 1); n += scnprintf(buf + n, len - n, - "D-Cache\t\t: %uK, %dway/set, %uB Line, %s%s%s\n", + "D-Cache\t\t: %uK, %dway/set, %uB Line, %s%s\n", p_dc->sz_k, assoc, p_dc->line_len, vipt ? "VIPT" : "PIPT", - p_dc->colors > 1 ? " aliasing" : "", IS_USED_CFG(CONFIG_ARC_HAS_DCACHE)); slc_chk: @@ -703,51 +702,10 @@ static inline void arc_slc_enable(void) * Exported APIs */ -/* - * Handle cache congruency of kernel and userspace mappings of page when kernel - * writes-to/reads-from - * - * The idea is to defer flushing of kernel mapping after a WRITE, possible if: - * -dcache is NOT aliasing, hence any U/K-mappings of page are congruent - * -U-mapping doesn't exist yet for page (finalised in update_mmu_cache) - * -In SMP, if hardware caches are coherent - * - * There's a corollary case, where kernel READs from a userspace mapped page. - * If the U-mapping is not congruent to K-mapping, former needs flushing. - */ void flush_dcache_folio(struct folio *folio) { - struct address_space *mapping; - - if (!cache_is_vipt_aliasing()) { - clear_bit(PG_dc_clean, &folio->flags); - return; - } - - /* don't handle anon pages here */ - mapping = folio_flush_mapping(folio); - if (!mapping) - return; - - /* - * pagecache page, file not yet mapped to userspace - * Make a note that K-mapping is dirty - */ - if (!mapping_mapped(mapping)) { - clear_bit(PG_dc_clean, &folio->flags); - } else if (folio_mapped(folio)) { - /* kernel reading from page with U-mapping */ - phys_addr_t paddr = (unsigned long)folio_address(folio); - unsigned long vaddr = folio_pos(folio); - - /* - * vaddr is not actually the virtual address, but is - * congruent to every user mapping. - */ - if (addr_not_cache_congruent(paddr, vaddr)) - __flush_dcache_pages(paddr, vaddr, - folio_nr_pages(folio)); - } + clear_bit(PG_dc_clean, &folio->flags); + return; } EXPORT_SYMBOL(flush_dcache_folio); @@ -921,44 +879,6 @@ noinline void flush_cache_all(void) } -#ifdef CONFIG_ARC_CACHE_VIPT_ALIASING - -void flush_cache_mm(struct mm_struct *mm) -{ - flush_cache_all(); -} - -void flush_cache_page(struct vm_area_struct *vma, unsigned long u_vaddr, - unsigned long pfn) -{ - phys_addr_t paddr = pfn << PAGE_SHIFT; - - u_vaddr &= PAGE_MASK; - - __flush_dcache_pages(paddr, u_vaddr, 1); - - if (vma->vm_flags & VM_EXEC) - __inv_icache_pages(paddr, u_vaddr, 1); -} - -void flush_cache_range(struct vm_area_struct *vma, unsigned long start, - unsigned long end) -{ - flush_cache_all(); -} - -void flush_anon_page(struct vm_area_struct *vma, struct page *page, - unsigned long u_vaddr) -{ - /* TBD: do we really need to clear the kernel mapping */ - __flush_dcache_pages((phys_addr_t)page_address(page), u_vaddr, 1); - __flush_dcache_pages((phys_addr_t)page_address(page), - (phys_addr_t)page_address(page), 1); - -} - -#endif - void copy_user_highpage(struct page *to, struct page *from, unsigned long u_vaddr, struct vm_area_struct *vma) { @@ -966,46 +886,11 @@ void copy_user_highpage(struct page *to, struct page *from, struct folio *dst = page_folio(to); void *kfrom = kmap_atomic(from); void *kto = kmap_atomic(to); - int clean_src_k_mappings = 0; - - /* - * If SRC page was already mapped in userspace AND it's U-mapping is - * not congruent with K-mapping, sync former to physical page so that - * K-mapping in memcpy below, sees the right data - * - * Note that while @u_vaddr refers to DST page's userspace vaddr, it is - * equally valid for SRC page as well - * - * For !VIPT cache, all of this gets compiled out as - * addr_not_cache_congruent() is 0 - */ - if (page_mapcount(from) && addr_not_cache_congruent(kfrom, u_vaddr)) { - __flush_dcache_pages((unsigned long)kfrom, u_vaddr, 1); - clean_src_k_mappings = 1; - } copy_page(kto, kfrom); - /* - * Mark DST page K-mapping as dirty for a later finalization by - * update_mmu_cache(). Although the finalization could have been done - * here as well (given that both vaddr/paddr are available). - * But update_mmu_cache() already has code to do that for other - * non copied user pages (e.g. read faults which wire in pagecache page - * directly). - */ clear_bit(PG_dc_clean, &dst->flags); - - /* - * if SRC was already usermapped and non-congruent to kernel mapping - * sync the kernel mapping back to physical page - */ - if (clean_src_k_mappings) { - __flush_dcache_pages((unsigned long)kfrom, - (unsigned long)kfrom, 1); - } else { - clear_bit(PG_dc_clean, &src->flags); - } + clear_bit(PG_dc_clean, &src->flags); kunmap_atomic(kto); kunmap_atomic(kfrom); @@ -1140,17 +1025,8 @@ static noinline void __init arc_cache_init_master(void) dc->line_len, L1_CACHE_BYTES); /* check for D-Cache aliasing on ARCompact: ARCv2 has PIPT */ - if (is_isa_arcompact()) { - int handled = IS_ENABLED(CONFIG_ARC_CACHE_VIPT_ALIASING); - - if (dc->colors > 1) { - if (!handled) - panic("Enable CONFIG_ARC_CACHE_VIPT_ALIASING\n"); - if (CACHE_COLORS_NUM != dc->colors) - panic("CACHE_COLORS_NUM not optimized for config\n"); - } else if (handled && dc->colors == 1) { - panic("Disable CONFIG_ARC_CACHE_VIPT_ALIASING\n"); - } + if (is_isa_arcompact() && dc->colors > 1) { + panic("Aliasing VIPT cache not supported\n"); } } diff --git a/arch/arc/mm/mmap.c b/arch/arc/mm/mmap.c index fce5fa2b4f52..3c1c7ae73292 100644 --- a/arch/arc/mm/mmap.c +++ b/arch/arc/mm/mmap.c @@ -14,10 +14,6 @@ #include <asm/cacheflush.h> -#define COLOUR_ALIGN(addr, pgoff) \ - ((((addr) + SHMLBA - 1) & ~(SHMLBA - 1)) + \ - (((pgoff) << PAGE_SHIFT) & (SHMLBA - 1))) - /* * Ensure that shared mappings are correctly aligned to * avoid aliasing issues with VIPT caches. @@ -31,21 +27,13 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; - int do_align = 0; - int aliasing = cache_is_vipt_aliasing(); struct vm_unmapped_area_info info; /* - * We only need to do colour alignment if D cache aliases. - */ - if (aliasing) - do_align = filp || (flags & MAP_SHARED); - - /* * We enforce the MAP_FIXED case. */ if (flags & MAP_FIXED) { - if (aliasing && flags & MAP_SHARED && + if (flags & MAP_SHARED && (addr - (pgoff << PAGE_SHIFT)) & (SHMLBA - 1)) return -EINVAL; return addr; @@ -55,10 +43,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, return -ENOMEM; if (addr) { - if (do_align) - addr = COLOUR_ALIGN(addr, pgoff); - else - addr = PAGE_ALIGN(addr); + addr = PAGE_ALIGN(addr); vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && @@ -70,7 +55,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, info.length = len; info.low_limit = mm->mmap_base; info.high_limit = TASK_SIZE; - info.align_mask = do_align ? (PAGE_MASK & (SHMLBA - 1)) : 0; + info.align_mask = 0; info.align_offset = pgoff << PAGE_SHIFT; return vm_unmapped_area(&info); } diff --git a/arch/arc/mm/tlb.c b/arch/arc/mm/tlb.c index e536b2dcd4b0..ad702b49aeb3 100644 --- a/arch/arc/mm/tlb.c +++ b/arch/arc/mm/tlb.c @@ -478,21 +478,15 @@ void update_mmu_cache_range(struct vm_fault *vmf, struct vm_area_struct *vma, create_tlb(vma, vaddr, ptep); - if (page == ZERO_PAGE(0)) { + if (page == ZERO_PAGE(0)) return; - } /* - * Exec page : Independent of aliasing/page-color considerations, - * since icache doesn't snoop dcache on ARC, any dirty - * K-mapping of a code page needs to be wback+inv so that - * icache fetch by userspace sees code correctly. - * !EXEC page: If K-mapping is NOT congruent to U-mapping, flush it - * so userspace sees the right data. - * (Avoids the flush for Non-exec + congruent mapping case) + * For executable pages, since icache doesn't snoop dcache, any + * dirty K-mapping of a code page needs to be wback+inv so that + * icache fetch by userspace sees code correctly. */ - if ((vma->vm_flags & VM_EXEC) || - addr_not_cache_congruent(paddr, vaddr)) { + if (vma->vm_flags & VM_EXEC) { struct folio *folio = page_folio(page); int dirty = !test_and_set_bit(PG_dc_clean, &folio->flags); if (dirty) { diff --git a/arch/arm/boot/dts/ti/omap/am33xx.dtsi b/arch/arm/boot/dts/ti/omap/am33xx.dtsi index 1a2cd5baf402..5b9e01a8aa5d 100644 --- a/arch/arm/boot/dts/ti/omap/am33xx.dtsi +++ b/arch/arm/boot/dts/ti/omap/am33xx.dtsi @@ -359,6 +359,7 @@ <SYSC_IDLE_NO>, <SYSC_IDLE_SMART>, <SYSC_IDLE_SMART_WKUP>; + ti,sysc-delay-us = <2>; clocks = <&l3s_clkctrl AM3_L3S_USB_OTG_HS_CLKCTRL 0>; clock-names = "fck"; #address-cells = <1>; diff --git a/arch/arm/boot/dts/ti/omap/dra7.dtsi b/arch/arm/boot/dts/ti/omap/dra7.dtsi index 3f3e52e3b375..6509c742fb58 100644 --- a/arch/arm/boot/dts/ti/omap/dra7.dtsi +++ b/arch/arm/boot/dts/ti/omap/dra7.dtsi @@ -147,7 +147,7 @@ l3-noc@44000000 { compatible = "ti,dra7-l3-noc"; - reg = <0x44000000 0x1000>, + reg = <0x44000000 0x1000000>, <0x45000000 0x1000>; interrupts-extended = <&crossbar_mpu GIC_SPI 4 IRQ_TYPE_LEVEL_HIGH>, <&wakeupgen GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>; diff --git a/arch/arm/mach-omap2/id.c b/arch/arm/mach-omap2/id.c index 98999aa8cc0c..7f387706368a 100644 --- a/arch/arm/mach-omap2/id.c +++ b/arch/arm/mach-omap2/id.c @@ -793,11 +793,16 @@ void __init omap_soc_device_init(void) soc_dev_attr->machine = soc_name; soc_dev_attr->family = omap_get_family(); + if (!soc_dev_attr->family) { + kfree(soc_dev_attr); + return; + } soc_dev_attr->revision = soc_rev; soc_dev_attr->custom_attr_group = omap_soc_groups[0]; soc_dev = soc_device_register(soc_dev_attr); if (IS_ERR(soc_dev)) { + kfree(soc_dev_attr->family); kfree(soc_dev_attr); return; } diff --git a/arch/arm/mach-sunxi/mc_smp.c b/arch/arm/mach-sunxi/mc_smp.c index cb63921232a6..277f6aa8e6c2 100644 --- a/arch/arm/mach-sunxi/mc_smp.c +++ b/arch/arm/mach-sunxi/mc_smp.c @@ -803,16 +803,16 @@ static int __init sunxi_mc_smp_init(void) for (i = 0; i < ARRAY_SIZE(sunxi_mc_smp_data); i++) { ret = of_property_match_string(node, "enable-method", sunxi_mc_smp_data[i].enable_method); - if (!ret) + if (ret >= 0) break; } - is_a83t = sunxi_mc_smp_data[i].is_a83t; - of_node_put(node); - if (ret) + if (ret < 0) return -ENODEV; + is_a83t = sunxi_mc_smp_data[i].is_a83t; + if (!sunxi_mc_smp_cpu_table_init()) return -EINVAL; diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl index 584f9528c996..d6a324dbff2e 100644 --- a/arch/arm/tools/syscall.tbl +++ b/arch/arm/tools/syscall.tbl @@ -470,3 +470,5 @@ 454 common futex_wake sys_futex_wake 455 common futex_wait sys_futex_wait 456 common futex_requeue sys_futex_requeue +457 common statmount sys_statmount +458 common listmount sys_listmount diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h616-orangepi-zero.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-h616-orangepi-zero.dtsi index 15290e6892fc..fc7315b94406 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h616-orangepi-zero.dtsi +++ b/arch/arm64/boot/dts/allwinner/sun50i-h616-orangepi-zero.dtsi @@ -68,10 +68,7 @@ &emac0 { pinctrl-names = "default"; pinctrl-0 = <&ext_rgmii_pins>; - phy-mode = "rgmii"; phy-handle = <&ext_rgmii_phy>; - allwinner,rx-delay-ps = <3100>; - allwinner,tx-delay-ps = <700>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h616-orangepi-zero2.dts b/arch/arm64/boot/dts/allwinner/sun50i-h616-orangepi-zero2.dts index d83852e72f06..b5d713926a34 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h616-orangepi-zero2.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h616-orangepi-zero2.dts @@ -13,6 +13,9 @@ }; &emac0 { + allwinner,rx-delay-ps = <3100>; + allwinner,tx-delay-ps = <700>; + phy-mode = "rgmii"; phy-supply = <®_dcdce>; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h618-orangepi-zero3.dts b/arch/arm64/boot/dts/allwinner/sun50i-h618-orangepi-zero3.dts index 00fe28caac93..b3b1b8692125 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h618-orangepi-zero3.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h618-orangepi-zero3.dts @@ -13,6 +13,8 @@ }; &emac0 { + allwinner,tx-delay-ps = <700>; + phy-mode = "rgmii-rxid"; phy-supply = <®_dldo1>; }; diff --git a/arch/arm64/boot/dts/mediatek/mt8395-genio-1200-evk.dts b/arch/arm64/boot/dts/mediatek/mt8395-genio-1200-evk.dts index 70b465f7c6a7..00ac59a873e8 100644 --- a/arch/arm64/boot/dts/mediatek/mt8395-genio-1200-evk.dts +++ b/arch/arm64/boot/dts/mediatek/mt8395-genio-1200-evk.dts @@ -238,6 +238,7 @@ mt6360: pmic@34 { compatible = "mediatek,mt6360"; reg = <0x34>; + interrupt-parent = <&pio>; interrupts = <128 IRQ_TYPE_EDGE_FALLING>; interrupt-names = "IRQB"; interrupt-controller; diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index b19a8aee684c..79ce70fbb751 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -834,6 +834,12 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) pte = set_pte_bit(pte, __pgprot(PTE_DIRTY)); pte_val(pte) = (pte_val(pte) & ~mask) | (pgprot_val(newprot) & mask); + /* + * If we end up clearing hw dirtiness for a sw-dirty PTE, set hardware + * dirtiness again. + */ + if (pte_sw_dirty(pte)) + pte = pte_mkdirty(pte); return pte; } diff --git a/arch/arm64/include/asm/syscall_wrapper.h b/arch/arm64/include/asm/syscall_wrapper.h index d977713ec0ba..abb57bc54305 100644 --- a/arch/arm64/include/asm/syscall_wrapper.h +++ b/arch/arm64/include/asm/syscall_wrapper.h @@ -44,9 +44,6 @@ return sys_ni_syscall(); \ } -#define COMPAT_SYS_NI(name) \ - SYSCALL_ALIAS(__arm64_compat_sys_##name, sys_ni_posix_timers); - #endif /* CONFIG_COMPAT */ #define __SYSCALL_DEFINEx(x, name, ...) \ @@ -81,6 +78,5 @@ } asmlinkage long __arm64_sys_ni_syscall(const struct pt_regs *__unused); -#define SYS_NI(name) SYSCALL_ALIAS(__arm64_sys_##name, sys_ni_posix_timers); #endif /* __ASM_SYSCALL_WRAPPER_H */ diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index 9f7c1bf99526..8a191423c316 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -919,6 +919,10 @@ __SYSCALL(__NR_futex_wake, sys_futex_wake) __SYSCALL(__NR_futex_wait, sys_futex_wait) #define __NR_futex_requeue 456 __SYSCALL(__NR_futex_requeue, sys_futex_requeue) +#define __NR_statmount 457 +__SYSCALL(__NR_statmount, sys_statmount) +#define __NR_listmount 458 +__SYSCALL(__NR_listmount, sys_listmount) /* * Please add new compat syscalls above this comment and update diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index e5f75f1f1085..4796104c4471 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -410,7 +410,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_cache); kvm_timer_vcpu_terminate(vcpu); kvm_pmu_vcpu_destroy(vcpu); - + kvm_vgic_vcpu_destroy(vcpu); kvm_arm_vcpu_destroy(vcpu); } diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index c8c3cb812783..e949e1d0fd9f 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -368,7 +368,7 @@ static void kvm_vgic_dist_destroy(struct kvm *kvm) vgic_v4_teardown(kvm); } -void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) +static void __kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; @@ -379,29 +379,39 @@ void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) vgic_flush_pending_lpis(vcpu); INIT_LIST_HEAD(&vgic_cpu->ap_list_head); - vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF; + if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) { + vgic_unregister_redist_iodev(vcpu); + vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF; + } } -static void __kvm_vgic_destroy(struct kvm *kvm) +void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + + mutex_lock(&kvm->slots_lock); + __kvm_vgic_vcpu_destroy(vcpu); + mutex_unlock(&kvm->slots_lock); +} + +void kvm_vgic_destroy(struct kvm *kvm) { struct kvm_vcpu *vcpu; unsigned long i; - lockdep_assert_held(&kvm->arch.config_lock); + mutex_lock(&kvm->slots_lock); vgic_debug_destroy(kvm); kvm_for_each_vcpu(i, vcpu, kvm) - kvm_vgic_vcpu_destroy(vcpu); + __kvm_vgic_vcpu_destroy(vcpu); + + mutex_lock(&kvm->arch.config_lock); kvm_vgic_dist_destroy(kvm); -} -void kvm_vgic_destroy(struct kvm *kvm) -{ - mutex_lock(&kvm->arch.config_lock); - __kvm_vgic_destroy(kvm); mutex_unlock(&kvm->arch.config_lock); + mutex_unlock(&kvm->slots_lock); } /** @@ -469,25 +479,26 @@ int kvm_vgic_map_resources(struct kvm *kvm) type = VGIC_V3; } - if (ret) { - __kvm_vgic_destroy(kvm); + if (ret) goto out; - } + dist->ready = true; dist_base = dist->vgic_dist_base; mutex_unlock(&kvm->arch.config_lock); ret = vgic_register_dist_iodev(kvm, dist_base, type); - if (ret) { + if (ret) kvm_err("Unable to register VGIC dist MMIO regions\n"); - kvm_vgic_destroy(kvm); - } - mutex_unlock(&kvm->slots_lock); - return ret; + goto out_slots; out: mutex_unlock(&kvm->arch.config_lock); +out_slots: mutex_unlock(&kvm->slots_lock); + + if (ret) + kvm_vgic_destroy(kvm); + return ret; } diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c index 89117ba2528a..a764b0ab8bf9 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c +++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c @@ -820,7 +820,7 @@ out_unlock: return ret; } -static void vgic_unregister_redist_iodev(struct kvm_vcpu *vcpu) +void vgic_unregister_redist_iodev(struct kvm_vcpu *vcpu) { struct vgic_io_device *rd_dev = &vcpu->arch.vgic_cpu.rd_iodev; @@ -833,6 +833,8 @@ static int vgic_register_all_redist_iodevs(struct kvm *kvm) unsigned long c; int ret = 0; + lockdep_assert_held(&kvm->slots_lock); + kvm_for_each_vcpu(c, vcpu, kvm) { ret = vgic_register_redist_iodev(vcpu); if (ret) diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h index 0ab09b0d4440..8d134569d0a1 100644 --- a/arch/arm64/kvm/vgic/vgic.h +++ b/arch/arm64/kvm/vgic/vgic.h @@ -241,6 +241,7 @@ int vgic_v3_lpi_sync_pending_status(struct kvm *kvm, struct vgic_irq *irq); int vgic_v3_save_pending_tables(struct kvm *kvm); int vgic_v3_set_redist_base(struct kvm *kvm, u32 index, u64 addr, u32 count); int vgic_register_redist_iodev(struct kvm_vcpu *vcpu); +void vgic_unregister_redist_iodev(struct kvm_vcpu *vcpu); bool vgic_v3_check_base(struct kvm *kvm); void vgic_v3_load(struct kvm_vcpu *vcpu); diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 460d799e1296..55f6455a8284 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -607,6 +607,8 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr, goto done; } count_vm_vma_lock_event(VMA_LOCK_RETRY); + if (fault & VM_FAULT_MAJOR) + mm_flags |= FAULT_FLAG_TRIED; /* Quick path to respond to signals */ if (fault_signal_pending(fault, regs)) { diff --git a/arch/loongarch/include/asm/efi.h b/arch/loongarch/include/asm/efi.h index 091897d40b03..91d81f9730ab 100644 --- a/arch/loongarch/include/asm/efi.h +++ b/arch/loongarch/include/asm/efi.h @@ -32,6 +32,6 @@ static inline unsigned long efi_get_kimg_min_align(void) #define EFI_KIMG_PREFERRED_ADDRESS PHYSADDR(VMLINUX_LOAD_ADDRESS) -unsigned long kernel_entry_address(void); +unsigned long kernel_entry_address(unsigned long kernel_addr); #endif /* _ASM_LOONGARCH_EFI_H */ diff --git a/arch/loongarch/kernel/Makefile b/arch/loongarch/kernel/Makefile index 4fcc168f0732..3c808c680370 100644 --- a/arch/loongarch/kernel/Makefile +++ b/arch/loongarch/kernel/Makefile @@ -57,7 +57,7 @@ obj-$(CONFIG_MAGIC_SYSRQ) += sysrq.o obj-$(CONFIG_RELOCATABLE) += relocate.o -obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o +obj-$(CONFIG_KEXEC_CORE) += machine_kexec.o relocate_kernel.o obj-$(CONFIG_CRASH_DUMP) += crash_dump.o obj-$(CONFIG_UNWINDER_GUESS) += unwind_guess.o diff --git a/arch/m68k/include/asm/kexec.h b/arch/m68k/include/asm/kexec.h index f5a8b2defa4b..3b0b64f0a353 100644 --- a/arch/m68k/include/asm/kexec.h +++ b/arch/m68k/include/asm/kexec.h @@ -2,7 +2,7 @@ #ifndef _ASM_M68K_KEXEC_H #define _ASM_M68K_KEXEC_H -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE /* Maximum physical address we can use pages from */ #define KEXEC_SOURCE_MEMORY_LIMIT (-1UL) @@ -25,6 +25,6 @@ static inline void crash_setup_regs(struct pt_regs *newregs, #endif /* __ASSEMBLY__ */ -#endif /* CONFIG_KEXEC */ +#endif /* CONFIG_KEXEC_CORE */ #endif /* _ASM_M68K_KEXEC_H */ diff --git a/arch/m68k/kernel/Makefile b/arch/m68k/kernel/Makefile index 01fb69a5095f..f335bf3268a1 100644 --- a/arch/m68k/kernel/Makefile +++ b/arch/m68k/kernel/Makefile @@ -25,7 +25,7 @@ obj-$(CONFIG_PCI) += pcibios.o obj-$(CONFIG_M68K_NONCOHERENT_DMA) += dma.o -obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o +obj-$(CONFIG_KEXEC_CORE) += machine_kexec.o relocate_kernel.o obj-$(CONFIG_BOOTINFO_PROC) += bootinfo_proc.o obj-$(CONFIG_UBOOT) += uboot.o diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl index 7a4b780e82cb..37db1a810b67 100644 --- a/arch/m68k/kernel/syscalls/syscall.tbl +++ b/arch/m68k/kernel/syscalls/syscall.tbl @@ -456,3 +456,5 @@ 454 common futex_wake sys_futex_wake 455 common futex_wait sys_futex_wait 456 common futex_requeue sys_futex_requeue +457 common statmount sys_statmount +458 common listmount sys_listmount diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl index 5b6a0b02b7de..07fff5ad1c9c 100644 --- a/arch/microblaze/kernel/syscalls/syscall.tbl +++ b/arch/microblaze/kernel/syscalls/syscall.tbl @@ -462,3 +462,5 @@ 454 common futex_wake sys_futex_wake 455 common futex_wait sys_futex_wait 456 common futex_requeue sys_futex_requeue +457 common statmount sys_statmount +458 common listmount sys_listmount diff --git a/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi b/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi index f878f47e4501..ee3e2153dd13 100644 --- a/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi +++ b/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi @@ -130,8 +130,7 @@ compatible = "pci0014,7a03.0", "pci0014,7a03", "pciclass0c0320", - "pciclass0c03", - "loongson, pci-gmac"; + "pciclass0c03"; reg = <0x1800 0x0 0x0 0x0 0x0>; interrupts = <12 IRQ_TYPE_LEVEL_LOW>, diff --git a/arch/mips/boot/dts/loongson/ls7a-pch.dtsi b/arch/mips/boot/dts/loongson/ls7a-pch.dtsi index 7c69e8245c2f..cce9428afc41 100644 --- a/arch/mips/boot/dts/loongson/ls7a-pch.dtsi +++ b/arch/mips/boot/dts/loongson/ls7a-pch.dtsi @@ -193,8 +193,7 @@ compatible = "pci0014,7a03.0", "pci0014,7a03", "pciclass020000", - "pciclass0200", - "loongson, pci-gmac"; + "pciclass0200"; reg = <0x1800 0x0 0x0 0x0 0x0>; interrupts = <12 IRQ_TYPE_LEVEL_HIGH>, diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c index 33c09688210f..08ea2cde1eb5 100644 --- a/arch/mips/cavium-octeon/smp.c +++ b/arch/mips/cavium-octeon/smp.c @@ -422,7 +422,7 @@ static const struct plat_smp_ops octeon_smp_ops = { .cpu_disable = octeon_cpu_disable, .cpu_die = octeon_cpu_die, #endif -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE .kexec_nonboot_cpu = kexec_nonboot_cpu_jump, #endif }; @@ -502,7 +502,7 @@ static const struct plat_smp_ops octeon_78xx_smp_ops = { .cpu_disable = octeon_cpu_disable, .cpu_die = octeon_cpu_die, #endif -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE .kexec_nonboot_cpu = kexec_nonboot_cpu_jump, #endif }; diff --git a/arch/mips/include/asm/kexec.h b/arch/mips/include/asm/kexec.h index d6d5fa5cc31d..69e579e41e66 100644 --- a/arch/mips/include/asm/kexec.h +++ b/arch/mips/include/asm/kexec.h @@ -31,7 +31,7 @@ static inline void crash_setup_regs(struct pt_regs *newregs, prepare_frametrace(newregs); } -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE struct kimage; extern unsigned long kexec_args[4]; extern int (*_machine_kexec_prepare)(struct kimage *); diff --git a/arch/mips/include/asm/smp-ops.h b/arch/mips/include/asm/smp-ops.h index 5719ff49eff1..0c59e168f800 100644 --- a/arch/mips/include/asm/smp-ops.h +++ b/arch/mips/include/asm/smp-ops.h @@ -35,7 +35,7 @@ struct plat_smp_ops { void (*cpu_die)(unsigned int cpu); void (*cleanup_dead_cpu)(unsigned cpu); #endif -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE void (*kexec_nonboot_cpu)(void); #endif }; diff --git a/arch/mips/include/asm/smp.h b/arch/mips/include/asm/smp.h index a40d8c0e4b87..901bc61fa7ae 100644 --- a/arch/mips/include/asm/smp.h +++ b/arch/mips/include/asm/smp.h @@ -93,7 +93,7 @@ static inline void __cpu_die(unsigned int cpu) extern void __noreturn play_dead(void); #endif -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE static inline void kexec_nonboot_cpu(void) { extern const struct plat_smp_ops *mp_ops; /* private */ diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile index 853a43ee4b44..ecf3278a32f7 100644 --- a/arch/mips/kernel/Makefile +++ b/arch/mips/kernel/Makefile @@ -90,7 +90,7 @@ obj-$(CONFIG_GPIO_TXX9) += gpio_txx9.o obj-$(CONFIG_RELOCATABLE) += relocate.o -obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o crash.o +obj-$(CONFIG_KEXEC_CORE) += machine_kexec.o relocate_kernel.o crash.o obj-$(CONFIG_CRASH_DUMP) += crash_dump.o obj-$(CONFIG_EARLY_PRINTK) += early_printk.o obj-$(CONFIG_EARLY_PRINTK_8250) += early_printk_8250.o diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c index c074ecce3fbf..b3dbf9ecb0d6 100644 --- a/arch/mips/kernel/smp-bmips.c +++ b/arch/mips/kernel/smp-bmips.c @@ -434,7 +434,7 @@ const struct plat_smp_ops bmips43xx_smp_ops = { .cpu_disable = bmips_cpu_disable, .cpu_die = bmips_cpu_die, #endif -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE .kexec_nonboot_cpu = kexec_nonboot_cpu_jump, #endif }; @@ -451,7 +451,7 @@ const struct plat_smp_ops bmips5000_smp_ops = { .cpu_disable = bmips_cpu_disable, .cpu_die = bmips_cpu_die, #endif -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE .kexec_nonboot_cpu = kexec_nonboot_cpu_jump, #endif }; diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c index dd55d59b88db..f6c37d407f36 100644 --- a/arch/mips/kernel/smp-cps.c +++ b/arch/mips/kernel/smp-cps.c @@ -392,7 +392,7 @@ static void cps_smp_finish(void) local_irq_enable(); } -#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_KEXEC) +#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_KEXEC_CORE) enum cpu_death { CPU_DEATH_HALT, @@ -429,7 +429,7 @@ static void cps_shutdown_this_cpu(enum cpu_death death) } } -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE static void cps_kexec_nonboot_cpu(void) { @@ -439,9 +439,9 @@ static void cps_kexec_nonboot_cpu(void) cps_shutdown_this_cpu(CPU_DEATH_POWER); } -#endif /* CONFIG_KEXEC */ +#endif /* CONFIG_KEXEC_CORE */ -#endif /* CONFIG_HOTPLUG_CPU || CONFIG_KEXEC */ +#endif /* CONFIG_HOTPLUG_CPU || CONFIG_KEXEC_CORE */ #ifdef CONFIG_HOTPLUG_CPU @@ -610,7 +610,7 @@ static const struct plat_smp_ops cps_smp_ops = { .cpu_die = cps_cpu_die, .cleanup_dead_cpu = cps_cleanup_dead_cpu, #endif -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE .kexec_nonboot_cpu = cps_kexec_nonboot_cpu, #endif }; diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl index a842b41c8e06..134ea054b1c7 100644 --- a/arch/mips/kernel/syscalls/syscall_n32.tbl +++ b/arch/mips/kernel/syscalls/syscall_n32.tbl @@ -395,3 +395,5 @@ 454 n32 futex_wake sys_futex_wake 455 n32 futex_wait sys_futex_wait 456 n32 futex_requeue sys_futex_requeue +457 n32 statmount sys_statmount +458 n32 listmount sys_listmount diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl index 116ff501bf92..959a21664703 100644 --- a/arch/mips/kernel/syscalls/syscall_n64.tbl +++ b/arch/mips/kernel/syscalls/syscall_n64.tbl @@ -371,3 +371,5 @@ 454 n64 futex_wake sys_futex_wake 455 n64 futex_wait sys_futex_wait 456 n64 futex_requeue sys_futex_requeue +457 n64 statmount sys_statmount +458 n64 listmount sys_listmount diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index 525cc54bc63b..e55bc1d4bf0f 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -444,3 +444,5 @@ 454 o32 futex_wake sys_futex_wake 455 o32 futex_wait sys_futex_wait 456 o32 futex_requeue sys_futex_requeue +457 o32 statmount sys_statmount +458 o32 listmount sys_listmount diff --git a/arch/mips/loongson64/reset.c b/arch/mips/loongson64/reset.c index e420800043b0..e01c8d4a805a 100644 --- a/arch/mips/loongson64/reset.c +++ b/arch/mips/loongson64/reset.c @@ -53,7 +53,7 @@ static void loongson_halt(void) } } -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE /* 0X80000000~0X80200000 is safe */ #define MAX_ARGS 64 @@ -158,7 +158,7 @@ static int __init mips_reboot_setup(void) _machine_halt = loongson_halt; pm_power_off = loongson_poweroff; -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE kexec_argv = kmalloc(KEXEC_ARGV_SIZE, GFP_KERNEL); if (WARN_ON(!kexec_argv)) return -ENOMEM; diff --git a/arch/mips/loongson64/smp.c b/arch/mips/loongson64/smp.c index e015a26a40f7..498bdc1bb0ed 100644 --- a/arch/mips/loongson64/smp.c +++ b/arch/mips/loongson64/smp.c @@ -864,7 +864,7 @@ const struct plat_smp_ops loongson3_smp_ops = { .cpu_disable = loongson3_cpu_disable, .cpu_die = loongson3_cpu_die, #endif -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE .kexec_nonboot_cpu = kexec_nonboot_cpu_jump, #endif }; diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl index a47798fed54e..9c84470c31c7 100644 --- a/arch/parisc/kernel/syscalls/syscall.tbl +++ b/arch/parisc/kernel/syscalls/syscall.tbl @@ -455,3 +455,5 @@ 454 common futex_wake sys_futex_wake 455 common futex_wait sys_futex_wait 456 common futex_requeue sys_futex_requeue +457 common statmount sys_statmount +458 common listmount sys_listmount diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 6f105ee4f3cf..1f11a62809f2 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -608,10 +608,10 @@ config ARCH_SUPPORTS_KEXEC def_bool PPC_BOOK3S || PPC_E500 || (44x && !SMP) config ARCH_SUPPORTS_KEXEC_FILE - def_bool PPC64 && CRYPTO=y && CRYPTO_SHA256=y + def_bool PPC64 config ARCH_SUPPORTS_KEXEC_PURGATORY - def_bool KEXEC_FILE + def_bool y config ARCH_SELECTS_KEXEC_FILE def_bool y diff --git a/arch/powerpc/configs/skiroot_defconfig b/arch/powerpc/configs/skiroot_defconfig index 8d3eacb50d56..9d44e6630908 100644 --- a/arch/powerpc/configs/skiroot_defconfig +++ b/arch/powerpc/configs/skiroot_defconfig @@ -301,7 +301,6 @@ CONFIG_WQ_WATCHDOG=y CONFIG_DEBUG_SG=y CONFIG_DEBUG_NOTIFIERS=y CONFIG_BUG_ON_DATA_CORRUPTION=y -CONFIG_DEBUG_CREDENTIALS=y # CONFIG_FTRACE is not set CONFIG_XMON=y # CONFIG_RUNTIME_TESTING_MENU is not set diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index 7fab411378f2..6988ecbc316e 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -543,3 +543,5 @@ 454 common futex_wake sys_futex_wake 455 common futex_wait sys_futex_wait 456 common futex_requeue sys_futex_requeue +457 common statmount sys_statmount +458 common listmount sys_listmount diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 9e49ede2bc1c..53335ae21a40 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -497,6 +497,8 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address, goto done; } count_vm_vma_lock_event(VMA_LOCK_RETRY); + if (fault & VM_FAULT_MAJOR) + flags |= FAULT_FLAG_TRIED; if (fault_signal_pending(fault, regs)) return user_mode(regs) ? 0 : SIGBUS; diff --git a/arch/powerpc/platforms/pseries/vas.c b/arch/powerpc/platforms/pseries/vas.c index b1f25bac280b..71d52a670d95 100644 --- a/arch/powerpc/platforms/pseries/vas.c +++ b/arch/powerpc/platforms/pseries/vas.c @@ -385,11 +385,15 @@ static struct vas_window *vas_allocate_window(int vas_id, u64 flags, * same fault IRQ is not freed by the OS before. */ mutex_lock(&vas_pseries_mutex); - if (migration_in_progress) + if (migration_in_progress) { rc = -EBUSY; - else + } else { rc = allocate_setup_window(txwin, (u64 *)&domain[0], cop_feat_caps->win_type); + if (!rc) + caps->nr_open_wins_progress++; + } + mutex_unlock(&vas_pseries_mutex); if (rc) goto out; @@ -404,8 +408,17 @@ static struct vas_window *vas_allocate_window(int vas_id, u64 flags, goto out_free; txwin->win_type = cop_feat_caps->win_type; - mutex_lock(&vas_pseries_mutex); + /* + * The migration SUSPEND thread sets migration_in_progress and + * closes all open windows from the list. But the window is + * added to the list after open and modify HCALLs. So possible + * that migration_in_progress is set before modify HCALL which + * may cause some windows are still open when the hypervisor + * initiates the migration. + * So checks the migration_in_progress flag again and close all + * open windows. + * * Possible to lose the acquired credit with DLPAR core * removal after the window is opened. So if there are any * closed windows (means with lost credits), do not give new @@ -413,9 +426,11 @@ static struct vas_window *vas_allocate_window(int vas_id, u64 flags, * after the existing windows are reopened when credits are * available. */ - if (!caps->nr_close_wins) { + mutex_lock(&vas_pseries_mutex); + if (!caps->nr_close_wins && !migration_in_progress) { list_add(&txwin->win_list, &caps->list); caps->nr_open_windows++; + caps->nr_open_wins_progress--; mutex_unlock(&vas_pseries_mutex); vas_user_win_add_mm_context(&txwin->vas_win.task_ref); return &txwin->vas_win; @@ -433,6 +448,12 @@ out_free: */ free_irq_setup(txwin); h_deallocate_vas_window(txwin->vas_win.winid); + /* + * Hold mutex and reduce nr_open_wins_progress counter. + */ + mutex_lock(&vas_pseries_mutex); + caps->nr_open_wins_progress--; + mutex_unlock(&vas_pseries_mutex); out: atomic_dec(&cop_feat_caps->nr_used_credits); kfree(txwin); @@ -937,14 +958,14 @@ int vas_migration_handler(int action) struct vas_caps *vcaps; int i, rc = 0; + pr_info("VAS migration event %d\n", action); + /* * NX-GZIP is not enabled. Nothing to do for migration. */ if (!copypaste_feat) return rc; - mutex_lock(&vas_pseries_mutex); - if (action == VAS_SUSPEND) migration_in_progress = true; else @@ -990,12 +1011,27 @@ int vas_migration_handler(int action) switch (action) { case VAS_SUSPEND: + mutex_lock(&vas_pseries_mutex); rc = reconfig_close_windows(vcaps, vcaps->nr_open_windows, true); + /* + * Windows are included in the list after successful + * open. So wait for closing these in-progress open + * windows in vas_allocate_window() which will be + * done if the migration_in_progress is set. + */ + while (vcaps->nr_open_wins_progress) { + mutex_unlock(&vas_pseries_mutex); + msleep(10); + mutex_lock(&vas_pseries_mutex); + } + mutex_unlock(&vas_pseries_mutex); break; case VAS_RESUME: + mutex_lock(&vas_pseries_mutex); atomic_set(&caps->nr_total_credits, new_nr_creds); rc = reconfig_open_windows(vcaps, new_nr_creds, true); + mutex_unlock(&vas_pseries_mutex); break; default: /* should not happen */ @@ -1011,8 +1047,9 @@ int vas_migration_handler(int action) goto out; } + pr_info("VAS migration event (%d) successful\n", action); + out: - mutex_unlock(&vas_pseries_mutex); return rc; } diff --git a/arch/powerpc/platforms/pseries/vas.h b/arch/powerpc/platforms/pseries/vas.h index 7115043ec488..45567cd13178 100644 --- a/arch/powerpc/platforms/pseries/vas.h +++ b/arch/powerpc/platforms/pseries/vas.h @@ -91,6 +91,8 @@ struct vas_cop_feat_caps { struct vas_caps { struct vas_cop_feat_caps caps; struct list_head list; /* List of open windows */ + int nr_open_wins_progress; /* Number of open windows in */ + /* progress. Used in migration */ int nr_close_wins; /* closed windows in the hypervisor for DLPAR */ int nr_open_windows; /* Number of successful open windows */ u8 feat; /* Feature type */ diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 95a2a06acc6a..cd4c9a204d08 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -685,7 +685,7 @@ config RISCV_BOOT_SPINWAIT If unsure what to do here, say N. config ARCH_SUPPORTS_KEXEC - def_bool MMU + def_bool y config ARCH_SELECTS_KEXEC def_bool y @@ -693,7 +693,7 @@ config ARCH_SELECTS_KEXEC select HOTPLUG_CPU if SMP config ARCH_SUPPORTS_KEXEC_FILE - def_bool 64BIT && MMU + def_bool 64BIT config ARCH_SELECTS_KEXEC_FILE def_bool y @@ -702,9 +702,7 @@ config ARCH_SELECTS_KEXEC_FILE select KEXEC_ELF config ARCH_SUPPORTS_KEXEC_PURGATORY - def_bool KEXEC_FILE - depends on CRYPTO=y - depends on CRYPTO_SHA256=y + def_bool ARCH_SUPPORTS_KEXEC_FILE config ARCH_SUPPORTS_CRASH_DUMP def_bool y diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 294044429e8e..ab00235b018f 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -899,7 +899,7 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte) #define PAGE_KERNEL __pgprot(0) #define swapper_pg_dir NULL #define TASK_SIZE 0xffffffffUL -#define VMALLOC_START 0 +#define VMALLOC_START _AC(0, UL) #define VMALLOC_END TASK_SIZE #endif /* !CONFIG_MMU */ diff --git a/arch/riscv/include/asm/syscall_wrapper.h b/arch/riscv/include/asm/syscall_wrapper.h index 1d7942c8a6cb..eeec04b7dae6 100644 --- a/arch/riscv/include/asm/syscall_wrapper.h +++ b/arch/riscv/include/asm/syscall_wrapper.h @@ -46,9 +46,6 @@ asmlinkage long __riscv_sys_ni_syscall(const struct pt_regs *); return sys_ni_syscall(); \ } -#define COMPAT_SYS_NI(name) \ - SYSCALL_ALIAS(__riscv_compat_sys_##name, sys_ni_posix_timers); - #endif /* CONFIG_COMPAT */ #define __SYSCALL_DEFINEx(x, name, ...) \ @@ -82,6 +79,4 @@ asmlinkage long __riscv_sys_ni_syscall(const struct pt_regs *); return sys_ni_syscall(); \ } -#define SYS_NI(name) SYSCALL_ALIAS(__riscv_sys_##name, sys_ni_posix_timers); - #endif /* __ASM_SYSCALL_WRAPPER_H */ diff --git a/arch/riscv/kernel/crash_core.c b/arch/riscv/kernel/crash_core.c index 55f1d7856b54..8706736fd4e2 100644 --- a/arch/riscv/kernel/crash_core.c +++ b/arch/riscv/kernel/crash_core.c @@ -5,18 +5,20 @@ void arch_crash_save_vmcoreinfo(void) { - VMCOREINFO_NUMBER(VA_BITS); VMCOREINFO_NUMBER(phys_ram_base); vmcoreinfo_append_str("NUMBER(PAGE_OFFSET)=0x%lx\n", PAGE_OFFSET); vmcoreinfo_append_str("NUMBER(VMALLOC_START)=0x%lx\n", VMALLOC_START); vmcoreinfo_append_str("NUMBER(VMALLOC_END)=0x%lx\n", VMALLOC_END); +#ifdef CONFIG_MMU + VMCOREINFO_NUMBER(VA_BITS); vmcoreinfo_append_str("NUMBER(VMEMMAP_START)=0x%lx\n", VMEMMAP_START); vmcoreinfo_append_str("NUMBER(VMEMMAP_END)=0x%lx\n", VMEMMAP_END); #ifdef CONFIG_64BIT vmcoreinfo_append_str("NUMBER(MODULES_VADDR)=0x%lx\n", MODULES_VADDR); vmcoreinfo_append_str("NUMBER(MODULES_END)=0x%lx\n", MODULES_END); #endif +#endif vmcoreinfo_append_str("NUMBER(KERNEL_LINK_ADDR)=0x%lx\n", KERNEL_LINK_ADDR); vmcoreinfo_append_str("NUMBER(va_kernel_pa_offset)=0x%lx\n", kernel_map.va_kernel_pa_offset); diff --git a/arch/riscv/kvm/aia_imsic.c b/arch/riscv/kvm/aia_imsic.c index 6cf23b8adb71..e808723a85f1 100644 --- a/arch/riscv/kvm/aia_imsic.c +++ b/arch/riscv/kvm/aia_imsic.c @@ -55,6 +55,7 @@ struct imsic { /* IMSIC SW-file */ struct imsic_mrif *swfile; phys_addr_t swfile_pa; + spinlock_t swfile_extirq_lock; }; #define imsic_vs_csr_read(__c) \ @@ -613,12 +614,23 @@ static void imsic_swfile_extirq_update(struct kvm_vcpu *vcpu) { struct imsic *imsic = vcpu->arch.aia_context.imsic_state; struct imsic_mrif *mrif = imsic->swfile; + unsigned long flags; + + /* + * The critical section is necessary during external interrupt + * updates to avoid the risk of losing interrupts due to potential + * interruptions between reading topei and updating pending status. + */ + + spin_lock_irqsave(&imsic->swfile_extirq_lock, flags); if (imsic_mrif_atomic_read(mrif, &mrif->eidelivery) && imsic_mrif_topei(mrif, imsic->nr_eix, imsic->nr_msis)) kvm_riscv_vcpu_set_interrupt(vcpu, IRQ_VS_EXT); else kvm_riscv_vcpu_unset_interrupt(vcpu, IRQ_VS_EXT); + + spin_unlock_irqrestore(&imsic->swfile_extirq_lock, flags); } static void imsic_swfile_read(struct kvm_vcpu *vcpu, bool clear, @@ -1039,6 +1051,7 @@ int kvm_riscv_vcpu_aia_imsic_init(struct kvm_vcpu *vcpu) } imsic->swfile = page_to_virt(swfile_page); imsic->swfile_pa = page_to_phys(swfile_page); + spin_lock_init(&imsic->swfile_extirq_lock); /* Setup IO device */ kvm_iodevice_init(&imsic->iodev, &imsic_iodoev_ops); diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index 90d4ba36d1d0..081339ddf47e 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -304,6 +304,8 @@ void handle_page_fault(struct pt_regs *regs) goto done; } count_vm_vma_lock_event(VMA_LOCK_RETRY); + if (fault & VM_FAULT_MAJOR) + flags |= FAULT_FLAG_TRIED; if (fault_signal_pending(fault, regs)) { if (!user_mode(regs)) diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 3bec98d20283..d5d8f99d1f25 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -254,13 +254,13 @@ config ARCH_SUPPORTS_KEXEC def_bool y config ARCH_SUPPORTS_KEXEC_FILE - def_bool CRYPTO && CRYPTO_SHA256 && CRYPTO_SHA256_S390 + def_bool y config ARCH_SUPPORTS_KEXEC_SIG def_bool MODULE_SIG_FORMAT config ARCH_SUPPORTS_KEXEC_PURGATORY - def_bool KEXEC_FILE + def_bool y config ARCH_SUPPORTS_CRASH_DUMP def_bool y diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 438cd92e6080..6de44ede4e14 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -44,8 +44,7 @@ CONFIG_KEXEC_FILE=y CONFIG_KEXEC_SIG=y CONFIG_CRASH_DUMP=y CONFIG_LIVEPATCH=y -CONFIG_MARCH_ZEC12=y -CONFIG_TUNE_ZEC12=y +CONFIG_MARCH_Z13=y CONFIG_NR_CPUS=512 CONFIG_NUMA=y CONFIG_HZ_100=y @@ -76,7 +75,6 @@ CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODULE_UNLOAD_TAINT_TRACKING=y CONFIG_MODVERSIONS=y CONFIG_MODULE_SRCVERSION_ALL=y -CONFIG_MODULE_SIG_SHA256=y CONFIG_BLK_DEV_THROTTLING=y CONFIG_BLK_WBT=y CONFIG_BLK_CGROUP_IOLATENCY=y @@ -93,6 +91,7 @@ CONFIG_UNIXWARE_DISKLABEL=y CONFIG_IOSCHED_BFQ=y CONFIG_BINFMT_MISC=m CONFIG_ZSWAP=y +CONFIG_ZSWAP_ZPOOL_DEFAULT_ZBUD=y CONFIG_ZSMALLOC_STAT=y CONFIG_SLUB_STATS=y # CONFIG_COMPAT_BRK is not set @@ -619,6 +618,9 @@ CONFIG_BTRFS_FS_POSIX_ACL=y CONFIG_BTRFS_DEBUG=y CONFIG_BTRFS_ASSERT=y CONFIG_NILFS2_FS=m +CONFIG_BCACHEFS_FS=y +CONFIG_BCACHEFS_QUOTA=y +CONFIG_BCACHEFS_POSIX_ACL=y CONFIG_FS_DAX=y CONFIG_EXPORTFS_BLOCK_OPS=y CONFIG_FS_ENCRYPTION=y @@ -691,7 +693,6 @@ CONFIG_PERSISTENT_KEYRINGS=y CONFIG_ENCRYPTED_KEYS=m CONFIG_KEY_NOTIFICATIONS=y CONFIG_SECURITY=y -CONFIG_SECURITY_NETWORK=y CONFIG_HARDENED_USERCOPY=y CONFIG_FORTIFY_SOURCE=y CONFIG_SECURITY_SELINUX=y @@ -834,7 +835,6 @@ CONFIG_DEBUG_IRQFLAGS=y CONFIG_DEBUG_LIST=y CONFIG_DEBUG_SG=y CONFIG_DEBUG_NOTIFIERS=y -CONFIG_DEBUG_CREDENTIALS=y CONFIG_RCU_TORTURE_TEST=m CONFIG_RCU_REF_SCALE_TEST=m CONFIG_RCU_CPU_STALL_TIMEOUT=300 diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 1b8150e50f6a..bcae47da6b7c 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -42,8 +42,7 @@ CONFIG_KEXEC_FILE=y CONFIG_KEXEC_SIG=y CONFIG_CRASH_DUMP=y CONFIG_LIVEPATCH=y -CONFIG_MARCH_ZEC12=y -CONFIG_TUNE_ZEC12=y +CONFIG_MARCH_Z13=y CONFIG_NR_CPUS=512 CONFIG_NUMA=y CONFIG_HZ_100=y @@ -71,7 +70,6 @@ CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODULE_UNLOAD_TAINT_TRACKING=y CONFIG_MODVERSIONS=y CONFIG_MODULE_SRCVERSION_ALL=y -CONFIG_MODULE_SIG_SHA256=y CONFIG_BLK_DEV_THROTTLING=y CONFIG_BLK_WBT=y CONFIG_BLK_CGROUP_IOLATENCY=y @@ -88,6 +86,7 @@ CONFIG_UNIXWARE_DISKLABEL=y CONFIG_IOSCHED_BFQ=y CONFIG_BINFMT_MISC=m CONFIG_ZSWAP=y +CONFIG_ZSWAP_ZPOOL_DEFAULT_ZBUD=y CONFIG_ZSMALLOC_STAT=y # CONFIG_COMPAT_BRK is not set CONFIG_MEMORY_HOTPLUG=y @@ -605,6 +604,9 @@ CONFIG_OCFS2_FS=m CONFIG_BTRFS_FS=y CONFIG_BTRFS_FS_POSIX_ACL=y CONFIG_NILFS2_FS=m +CONFIG_BCACHEFS_FS=m +CONFIG_BCACHEFS_QUOTA=y +CONFIG_BCACHEFS_POSIX_ACL=y CONFIG_FS_DAX=y CONFIG_EXPORTFS_BLOCK_OPS=y CONFIG_FS_ENCRYPTION=y @@ -677,7 +679,6 @@ CONFIG_PERSISTENT_KEYRINGS=y CONFIG_ENCRYPTED_KEYS=m CONFIG_KEY_NOTIFICATIONS=y CONFIG_SECURITY=y -CONFIG_SECURITY_NETWORK=y CONFIG_SECURITY_SELINUX=y CONFIG_SECURITY_SELINUX_BOOTPARAM=y CONFIG_SECURITY_LOCKDOWN_LSM=y diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index b831083b4edd..47028450eee1 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -9,8 +9,7 @@ CONFIG_BPF_SYSCALL=y CONFIG_BLK_DEV_INITRD=y CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_CRASH_DUMP=y -CONFIG_MARCH_ZEC12=y -CONFIG_TUNE_ZEC12=y +CONFIG_MARCH_Z13=y # CONFIG_COMPAT is not set CONFIG_NR_CPUS=2 CONFIG_HZ_100=y diff --git a/arch/s390/include/asm/fpu/api.h b/arch/s390/include/asm/fpu/api.h index b714ed0ef688..9acf48e53a87 100644 --- a/arch/s390/include/asm/fpu/api.h +++ b/arch/s390/include/asm/fpu/api.h @@ -79,7 +79,7 @@ static inline int test_fp_ctl(u32 fpc) #define KERNEL_VXR_HIGH (KERNEL_VXR_V16V23|KERNEL_VXR_V24V31) #define KERNEL_VXR (KERNEL_VXR_LOW|KERNEL_VXR_HIGH) -#define KERNEL_FPR (KERNEL_FPC|KERNEL_VXR_V0V7) +#define KERNEL_FPR (KERNEL_FPC|KERNEL_VXR_LOW) struct kernel_fpu; diff --git a/arch/s390/include/asm/syscall_wrapper.h b/arch/s390/include/asm/syscall_wrapper.h index 9286430fe729..35c1d1b860d8 100644 --- a/arch/s390/include/asm/syscall_wrapper.h +++ b/arch/s390/include/asm/syscall_wrapper.h @@ -63,10 +63,6 @@ cond_syscall(__s390x_sys_##name); \ cond_syscall(__s390_sys_##name) -#define SYS_NI(name) \ - SYSCALL_ALIAS(__s390x_sys_##name, sys_ni_posix_timers); \ - SYSCALL_ALIAS(__s390_sys_##name, sys_ni_posix_timers) - #define COMPAT_SYSCALL_DEFINEx(x, name, ...) \ long __s390_compat_sys##name(struct pt_regs *regs); \ ALLOW_ERROR_INJECTION(__s390_compat_sys##name, ERRNO); \ @@ -85,15 +81,11 @@ /* * As some compat syscalls may not be implemented, we need to expand - * COND_SYSCALL_COMPAT in kernel/sys_ni.c and COMPAT_SYS_NI in - * kernel/time/posix-stubs.c to cover this case as well. + * COND_SYSCALL_COMPAT in kernel/sys_ni.c to cover this case as well. */ #define COND_SYSCALL_COMPAT(name) \ cond_syscall(__s390_compat_sys_##name) -#define COMPAT_SYS_NI(name) \ - SYSCALL_ALIAS(__s390_compat_sys_##name, sys_ni_posix_timers) - #define __S390_SYS_STUBx(x, name, ...) \ long __s390_sys##name(struct pt_regs *regs); \ ALLOW_ERROR_INJECTION(__s390_sys##name, ERRNO); \ @@ -124,9 +116,6 @@ #define COND_SYSCALL(name) \ cond_syscall(__s390x_sys_##name) -#define SYS_NI(name) \ - SYSCALL_ALIAS(__s390x_sys_##name, sys_ni_posix_timers) - #define __S390_SYS_STUBx(x, fullname, name, ...) #endif /* CONFIG_COMPAT */ diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index 86fec9b080f6..5f5cd20ebb34 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -459,3 +459,5 @@ 454 common futex_wake sys_futex_wake sys_futex_wake 455 common futex_wait sys_futex_wait sys_futex_wait 456 common futex_requeue sys_futex_requeue sys_futex_requeue +457 common statmount sys_statmount sys_statmount +458 common listmount sys_listmount sys_listmount diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 249aefcf7c4e..ab4098886e56 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -337,6 +337,9 @@ static void do_exception(struct pt_regs *regs, int access) return; } count_vm_vma_lock_event(VMA_LOCK_RETRY); + if (fault & VM_FAULT_MAJOR) + flags |= FAULT_FLAG_TRIED; + /* Quick path to respond to signals */ if (fault_signal_pending(fault, regs)) { if (!user_mode(regs)) diff --git a/arch/sh/include/asm/kexec.h b/arch/sh/include/asm/kexec.h index 927d80ba2332..76631714673c 100644 --- a/arch/sh/include/asm/kexec.h +++ b/arch/sh/include/asm/kexec.h @@ -28,7 +28,7 @@ /* The native architecture */ #define KEXEC_ARCH KEXEC_ARCH_SH -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE /* arch/sh/kernel/machine_kexec.c */ void reserve_crashkernel(void); @@ -67,6 +67,6 @@ static inline void crash_setup_regs(struct pt_regs *newregs, } #else static inline void reserve_crashkernel(void) { } -#endif /* CONFIG_KEXEC */ +#endif /* CONFIG_KEXEC_CORE */ #endif /* __ASM_SH_KEXEC_H */ diff --git a/arch/sh/kernel/Makefile b/arch/sh/kernel/Makefile index 69cd9ac4b2ab..2d7e70537de0 100644 --- a/arch/sh/kernel/Makefile +++ b/arch/sh/kernel/Makefile @@ -33,7 +33,7 @@ obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_SH_STANDARD_BIOS) += sh_bios.o obj-$(CONFIG_KGDB) += kgdb.o obj-$(CONFIG_MODULES) += sh_ksyms_32.o module.o -obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o +obj-$(CONFIG_KEXEC_CORE) += machine_kexec.o relocate_kernel.o obj-$(CONFIG_CRASH_DUMP) += crash_dump.o obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-$(CONFIG_IO_TRAPPED) += io_trapped.o diff --git a/arch/sh/kernel/reboot.c b/arch/sh/kernel/reboot.c index e8eeedc9b182..1de006b1c339 100644 --- a/arch/sh/kernel/reboot.c +++ b/arch/sh/kernel/reboot.c @@ -63,7 +63,7 @@ struct machine_ops machine_ops = { .shutdown = native_machine_shutdown, .restart = native_machine_restart, .halt = native_machine_halt, -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE .crash_shutdown = native_machine_crash_shutdown, #endif }; @@ -88,7 +88,7 @@ void machine_halt(void) machine_ops.halt(); } -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE void machine_crash_shutdown(struct pt_regs *regs) { machine_ops.crash_shutdown(regs); diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c index 3d80515298d2..d3175f09b3aa 100644 --- a/arch/sh/kernel/setup.c +++ b/arch/sh/kernel/setup.c @@ -220,7 +220,7 @@ void __init __add_active_range(unsigned int nid, unsigned long start_pfn, request_resource(res, &code_resource); request_resource(res, &data_resource); request_resource(res, &bss_resource); -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE request_resource(res, &crashk_res); #endif diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl index 363fae0fe9bf..3103ebd2e4cb 100644 --- a/arch/sh/kernel/syscalls/syscall.tbl +++ b/arch/sh/kernel/syscalls/syscall.tbl @@ -459,3 +459,5 @@ 454 common futex_wake sys_futex_wake 455 common futex_wait sys_futex_wait 456 common futex_requeue sys_futex_requeue +457 common statmount sys_statmount +458 common listmount sys_listmount diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl index 7bcaa3d5ea44..ba147d7ad19a 100644 --- a/arch/sparc/kernel/syscalls/syscall.tbl +++ b/arch/sparc/kernel/syscalls/syscall.tbl @@ -502,3 +502,5 @@ 454 common futex_wake sys_futex_wake 455 common futex_wait sys_futex_wait 456 common futex_requeue sys_futex_requeue +457 common statmount sys_statmount +458 common listmount sys_listmount diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 3762f41bb092..1566748f16c4 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2072,7 +2072,7 @@ config ARCH_SUPPORTS_KEXEC def_bool y config ARCH_SUPPORTS_KEXEC_FILE - def_bool X86_64 && CRYPTO && CRYPTO_SHA256 + def_bool X86_64 config ARCH_SELECTS_KEXEC_FILE def_bool y @@ -2080,7 +2080,7 @@ config ARCH_SELECTS_KEXEC_FILE select HAVE_IMA_KEXEC if IMA config ARCH_SUPPORTS_KEXEC_PURGATORY - def_bool KEXEC_FILE + def_bool y config ARCH_SUPPORTS_KEXEC_SIG def_bool y diff --git a/arch/x86/boot/compressed/acpi.c b/arch/x86/boot/compressed/acpi.c index 55c98fdd67d2..18d15d1ce87d 100644 --- a/arch/x86/boot/compressed/acpi.c +++ b/arch/x86/boot/compressed/acpi.c @@ -178,7 +178,7 @@ static unsigned long get_cmdline_acpi_rsdp(void) { unsigned long addr = 0; -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE char val[MAX_ADDR_LEN] = { }; int ret; diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index c8fac5205803..56e6c2f3ee9c 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -461,3 +461,5 @@ 454 i386 futex_wake sys_futex_wake 455 i386 futex_wait sys_futex_wait 456 i386 futex_requeue sys_futex_requeue +457 i386 statmount sys_statmount +458 i386 listmount sys_listmount diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index 8cb8bf68721c..3a22eef585c2 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -378,6 +378,8 @@ 454 common futex_wake sys_futex_wake 455 common futex_wait sys_futex_wait 456 common futex_requeue sys_futex_requeue +457 common statmount sys_statmount +458 common listmount sys_listmount # # Due to a historical design error, certain syscalls are numbered differently diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index ce1c777227b4..0f2786d4e405 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -4051,12 +4051,17 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr, void *data) u64 pebs_mask = cpuc->pebs_enabled & x86_pmu.pebs_capable; int global_ctrl, pebs_enable; + /* + * In addition to obeying exclude_guest/exclude_host, remove bits being + * used for PEBS when running a guest, because PEBS writes to virtual + * addresses (not physical addresses). + */ *nr = 0; global_ctrl = (*nr)++; arr[global_ctrl] = (struct perf_guest_switch_msr){ .msr = MSR_CORE_PERF_GLOBAL_CTRL, .host = intel_ctrl & ~cpuc->intel_ctrl_guest_mask, - .guest = intel_ctrl & (~cpuc->intel_ctrl_host_mask | ~pebs_mask), + .guest = intel_ctrl & ~cpuc->intel_ctrl_host_mask & ~pebs_mask, }; if (!x86_pmu.pebs) diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 65f79092c9d9..fcd20c6dc7f9 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -10,6 +10,9 @@ #define ALT_FLAG_NOT (1 << 0) #define ALT_NOT(feature) ((ALT_FLAG_NOT << ALT_FLAGS_SHIFT) | (feature)) +#define ALT_FLAG_DIRECT_CALL (1 << 1) +#define ALT_DIRECT_CALL(feature) ((ALT_FLAG_DIRECT_CALL << ALT_FLAGS_SHIFT) | (feature)) +#define ALT_CALL_ALWAYS ALT_DIRECT_CALL(X86_FEATURE_ALWAYS) #ifndef __ASSEMBLY__ @@ -86,6 +89,8 @@ struct alt_instr { u8 replacementlen; /* length of new instruction */ } __packed; +extern struct alt_instr __alt_instructions[], __alt_instructions_end[]; + /* * Debug flag that can be tested to see whether alternative * instructions were patched in already: @@ -101,11 +106,10 @@ extern void apply_fineibt(s32 *start_retpoline, s32 *end_retpoine, s32 *start_cfi, s32 *end_cfi); struct module; -struct paravirt_patch_site; struct callthunk_sites { s32 *call_start, *call_end; - struct paravirt_patch_site *pv_start, *pv_end; + struct alt_instr *alt_start, *alt_end; }; #ifdef CONFIG_CALL_THUNKS @@ -150,6 +154,8 @@ static inline int alternatives_text_reserved(void *start, void *end) } #endif /* CONFIG_SMP */ +#define ALT_CALL_INSTR "call BUG_func" + #define b_replacement(num) "664"#num #define e_replacement(num) "665"#num @@ -330,6 +336,22 @@ static inline int alternatives_text_reserved(void *start, void *end) */ #define ASM_NO_INPUT_CLOBBER(clbr...) "i" (0) : clbr +/* Macro for creating assembler functions avoiding any C magic. */ +#define DEFINE_ASM_FUNC(func, instr, sec) \ + asm (".pushsection " #sec ", \"ax\"\n" \ + ".global " #func "\n\t" \ + ".type " #func ", @function\n\t" \ + ASM_FUNC_ALIGN "\n" \ + #func ":\n\t" \ + ASM_ENDBR \ + instr "\n\t" \ + ASM_RET \ + ".size " #func ", . - " #func "\n\t" \ + ".popsection") + +void BUG_func(void); +void nop_func(void); + #else /* __ASSEMBLY__ */ #ifdef CONFIG_SMP @@ -370,6 +392,10 @@ static inline int alternatives_text_reserved(void *start, void *end) .byte \alt_len .endm +.macro ALT_CALL_INSTR + call BUG_func +.endm + /* * Define an alternative between two instructions. If @feature is * present, early code in apply_alternatives() replaces @oldinstr with diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index a0234dfd1031..1e16bd5ac781 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -150,7 +150,7 @@ do { \ ((x)->e_machine == EM_X86_64) #define compat_elf_check_arch(x) \ - ((elf_check_arch_ia32(x) && ia32_enabled()) || \ + ((elf_check_arch_ia32(x) && ia32_enabled_verbose()) || \ (IS_ENABLED(CONFIG_X86_X32_ABI) && (x)->e_machine == EM_X86_64)) static inline void elf_common_init(struct thread_struct *t, diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h index 9805629479d9..c7ef6ea2fa99 100644 --- a/arch/x86/include/asm/ia32.h +++ b/arch/x86/include/asm/ia32.h @@ -2,7 +2,6 @@ #ifndef _ASM_X86_IA32_H #define _ASM_X86_IA32_H - #ifdef CONFIG_IA32_EMULATION #include <linux/compat.h> @@ -91,4 +90,14 @@ static inline void ia32_disable(void) {} #endif +static inline bool ia32_enabled_verbose(void) +{ + bool enabled = ia32_enabled(); + + if (IS_ENABLED(CONFIG_IA32_EMULATION) && !enabled) + pr_notice_once("32-bit emulation disabled. You can reenable with ia32_emulation=on\n"); + + return enabled; +} + #endif /* _ASM_X86_IA32_H */ diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 6c8ff12140ae..8bcf7584e7dd 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -142,8 +142,7 @@ static inline void write_cr0(unsigned long x) static __always_inline unsigned long read_cr2(void) { return PVOP_ALT_CALLEE0(unsigned long, mmu.read_cr2, - "mov %%cr2, %%rax;", - ALT_NOT(X86_FEATURE_XENPV)); + "mov %%cr2, %%rax;", ALT_NOT_XEN); } static __always_inline void write_cr2(unsigned long x) @@ -154,13 +153,12 @@ static __always_inline void write_cr2(unsigned long x) static inline unsigned long __read_cr3(void) { return PVOP_ALT_CALL0(unsigned long, mmu.read_cr3, - "mov %%cr3, %%rax;", ALT_NOT(X86_FEATURE_XENPV)); + "mov %%cr3, %%rax;", ALT_NOT_XEN); } static inline void write_cr3(unsigned long x) { - PVOP_ALT_VCALL1(mmu.write_cr3, x, - "mov %%rdi, %%cr3", ALT_NOT(X86_FEATURE_XENPV)); + PVOP_ALT_VCALL1(mmu.write_cr3, x, "mov %%rdi, %%cr3", ALT_NOT_XEN); } static inline void __write_cr4(unsigned long x) @@ -182,7 +180,7 @@ extern noinstr void pv_native_wbinvd(void); static __always_inline void wbinvd(void) { - PVOP_ALT_VCALL0(cpu.wbinvd, "wbinvd", ALT_NOT(X86_FEATURE_XENPV)); + PVOP_ALT_VCALL0(cpu.wbinvd, "wbinvd", ALT_NOT_XEN); } static inline u64 paravirt_read_msr(unsigned msr) @@ -390,27 +388,25 @@ static inline void paravirt_release_p4d(unsigned long pfn) static inline pte_t __pte(pteval_t val) { return (pte_t) { PVOP_ALT_CALLEE1(pteval_t, mmu.make_pte, val, - "mov %%rdi, %%rax", - ALT_NOT(X86_FEATURE_XENPV)) }; + "mov %%rdi, %%rax", ALT_NOT_XEN) }; } static inline pteval_t pte_val(pte_t pte) { return PVOP_ALT_CALLEE1(pteval_t, mmu.pte_val, pte.pte, - "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV)); + "mov %%rdi, %%rax", ALT_NOT_XEN); } static inline pgd_t __pgd(pgdval_t val) { return (pgd_t) { PVOP_ALT_CALLEE1(pgdval_t, mmu.make_pgd, val, - "mov %%rdi, %%rax", - ALT_NOT(X86_FEATURE_XENPV)) }; + "mov %%rdi, %%rax", ALT_NOT_XEN) }; } static inline pgdval_t pgd_val(pgd_t pgd) { return PVOP_ALT_CALLEE1(pgdval_t, mmu.pgd_val, pgd.pgd, - "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV)); + "mov %%rdi, %%rax", ALT_NOT_XEN); } #define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION @@ -444,14 +440,13 @@ static inline void set_pmd(pmd_t *pmdp, pmd_t pmd) static inline pmd_t __pmd(pmdval_t val) { return (pmd_t) { PVOP_ALT_CALLEE1(pmdval_t, mmu.make_pmd, val, - "mov %%rdi, %%rax", - ALT_NOT(X86_FEATURE_XENPV)) }; + "mov %%rdi, %%rax", ALT_NOT_XEN) }; } static inline pmdval_t pmd_val(pmd_t pmd) { return PVOP_ALT_CALLEE1(pmdval_t, mmu.pmd_val, pmd.pmd, - "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV)); + "mov %%rdi, %%rax", ALT_NOT_XEN); } static inline void set_pud(pud_t *pudp, pud_t pud) @@ -464,7 +459,7 @@ static inline pud_t __pud(pudval_t val) pudval_t ret; ret = PVOP_ALT_CALLEE1(pudval_t, mmu.make_pud, val, - "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV)); + "mov %%rdi, %%rax", ALT_NOT_XEN); return (pud_t) { ret }; } @@ -472,7 +467,7 @@ static inline pud_t __pud(pudval_t val) static inline pudval_t pud_val(pud_t pud) { return PVOP_ALT_CALLEE1(pudval_t, mmu.pud_val, pud.pud, - "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV)); + "mov %%rdi, %%rax", ALT_NOT_XEN); } static inline void pud_clear(pud_t *pudp) @@ -492,8 +487,7 @@ static inline void set_p4d(p4d_t *p4dp, p4d_t p4d) static inline p4d_t __p4d(p4dval_t val) { p4dval_t ret = PVOP_ALT_CALLEE1(p4dval_t, mmu.make_p4d, val, - "mov %%rdi, %%rax", - ALT_NOT(X86_FEATURE_XENPV)); + "mov %%rdi, %%rax", ALT_NOT_XEN); return (p4d_t) { ret }; } @@ -501,7 +495,7 @@ static inline p4d_t __p4d(p4dval_t val) static inline p4dval_t p4d_val(p4d_t p4d) { return PVOP_ALT_CALLEE1(p4dval_t, mmu.p4d_val, p4d.p4d, - "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV)); + "mov %%rdi, %%rax", ALT_NOT_XEN); } static inline void __set_pgd(pgd_t *pgdp, pgd_t pgd) @@ -687,17 +681,17 @@ bool __raw_callee_save___native_vcpu_is_preempted(long cpu); static __always_inline unsigned long arch_local_save_flags(void) { return PVOP_ALT_CALLEE0(unsigned long, irq.save_fl, "pushf; pop %%rax;", - ALT_NOT(X86_FEATURE_XENPV)); + ALT_NOT_XEN); } static __always_inline void arch_local_irq_disable(void) { - PVOP_ALT_VCALLEE0(irq.irq_disable, "cli;", ALT_NOT(X86_FEATURE_XENPV)); + PVOP_ALT_VCALLEE0(irq.irq_disable, "cli;", ALT_NOT_XEN); } static __always_inline void arch_local_irq_enable(void) { - PVOP_ALT_VCALLEE0(irq.irq_enable, "sti;", ALT_NOT(X86_FEATURE_XENPV)); + PVOP_ALT_VCALLEE0(irq.irq_enable, "sti;", ALT_NOT_XEN); } static __always_inline unsigned long arch_local_irq_save(void) @@ -726,52 +720,25 @@ static __always_inline unsigned long arch_local_irq_save(void) #undef PVOP_VCALL4 #undef PVOP_CALL4 -#define DEFINE_PARAVIRT_ASM(func, instr, sec) \ - asm (".pushsection " #sec ", \"ax\"\n" \ - ".global " #func "\n\t" \ - ".type " #func ", @function\n\t" \ - ASM_FUNC_ALIGN "\n" \ - #func ":\n\t" \ - ASM_ENDBR \ - instr "\n\t" \ - ASM_RET \ - ".size " #func ", . - " #func "\n\t" \ - ".popsection") - extern void default_banner(void); void native_pv_lock_init(void) __init; #else /* __ASSEMBLY__ */ -#define _PVSITE(ptype, ops, word, algn) \ -771:; \ - ops; \ -772:; \ - .pushsection .parainstructions,"a"; \ - .align algn; \ - word 771b; \ - .byte ptype; \ - .byte 772b-771b; \ - _ASM_ALIGN; \ - .popsection - - #ifdef CONFIG_X86_64 #ifdef CONFIG_PARAVIRT_XXL +#ifdef CONFIG_DEBUG_ENTRY -#define PARA_PATCH(off) ((off) / 8) -#define PARA_SITE(ptype, ops) _PVSITE(ptype, ops, .quad, 8) #define PARA_INDIRECT(addr) *addr(%rip) -#ifdef CONFIG_DEBUG_ENTRY .macro PARA_IRQ_save_fl - PARA_SITE(PARA_PATCH(PV_IRQ_save_fl), - ANNOTATE_RETPOLINE_SAFE; - call PARA_INDIRECT(pv_ops+PV_IRQ_save_fl);) + ANNOTATE_RETPOLINE_SAFE; + call PARA_INDIRECT(pv_ops+PV_IRQ_save_fl); .endm -#define SAVE_FLAGS ALTERNATIVE "PARA_IRQ_save_fl;", "pushf; pop %rax;", \ - ALT_NOT(X86_FEATURE_XENPV) +#define SAVE_FLAGS ALTERNATIVE_2 "PARA_IRQ_save_fl;", \ + "ALT_CALL_INSTR;", ALT_CALL_ALWAYS, \ + "pushf; pop %rax;", ALT_NOT_XEN #endif #endif /* CONFIG_PARAVIRT_XXL */ #endif /* CONFIG_X86_64 */ diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 772d03487520..d8e85d2cf8d5 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -2,15 +2,6 @@ #ifndef _ASM_X86_PARAVIRT_TYPES_H #define _ASM_X86_PARAVIRT_TYPES_H -#ifndef __ASSEMBLY__ -/* These all sit in the .parainstructions section to tell us what to patch. */ -struct paravirt_patch_site { - u8 *instr; /* original instructions */ - u8 type; /* type of this instruction */ - u8 len; /* length of original instruction */ -}; -#endif - #ifdef CONFIG_PARAVIRT #ifndef __ASSEMBLY__ @@ -250,43 +241,11 @@ struct paravirt_patch_template { extern struct pv_info pv_info; extern struct paravirt_patch_template pv_ops; -#define PARAVIRT_PATCH(x) \ - (offsetof(struct paravirt_patch_template, x) / sizeof(void *)) - -#define paravirt_type(op) \ - [paravirt_typenum] "i" (PARAVIRT_PATCH(op)), \ - [paravirt_opptr] "m" (pv_ops.op) -/* - * Generate some code, and mark it as patchable by the - * apply_paravirt() alternate instruction patcher. - */ -#define _paravirt_alt(insn_string, type) \ - "771:\n\t" insn_string "\n" "772:\n" \ - ".pushsection .parainstructions,\"a\"\n" \ - _ASM_ALIGN "\n" \ - _ASM_PTR " 771b\n" \ - " .byte " type "\n" \ - " .byte 772b-771b\n" \ - _ASM_ALIGN "\n" \ - ".popsection\n" - -/* Generate patchable code, with the default asm parameters. */ -#define paravirt_alt(insn_string) \ - _paravirt_alt(insn_string, "%c[paravirt_typenum]") - -/* Simple instruction patching code. */ -#define NATIVE_LABEL(a,x,b) "\n\t.globl " a #x "_" #b "\n" a #x "_" #b ":\n\t" - -unsigned int paravirt_patch(u8 type, void *insn_buff, unsigned long addr, unsigned int len); +#define paravirt_ptr(op) [paravirt_opptr] "m" (pv_ops.op) int paravirt_disable_iospace(void); -/* - * This generates an indirect call based on the operation type number. - * The type number, computed in PARAVIRT_PATCH, is derived from the - * offset into the paravirt_patch_template structure, and can therefore be - * freely converted back into a structure offset. - */ +/* This generates an indirect call based on the operation type number. */ #define PARAVIRT_CALL \ ANNOTATE_RETPOLINE_SAFE \ "call *%[paravirt_opptr];" @@ -319,12 +278,6 @@ int paravirt_disable_iospace(void); * However, x86_64 also has to clobber all caller saved registers, which * unfortunately, are quite a bit (r8 - r11) * - * The call instruction itself is marked by placing its start address - * and size into the .parainstructions section, so that - * apply_paravirt() in arch/i386/kernel/alternative.c can do the - * appropriate patching under the control of the backend pv_init_ops - * implementation. - * * Unfortunately there's no way to get gcc to generate the args setup * for the call, and then allow the call itself to be generated by an * inline asm. Because of this, we must do the complete arg setup and @@ -423,14 +376,27 @@ int paravirt_disable_iospace(void); __mask & __eax; \ }) - +/* + * Use alternative patching for paravirt calls: + * - For replacing an indirect call with a direct one, use the "normal" + * ALTERNATIVE() macro with the indirect call as the initial code sequence, + * which will be replaced with the related direct call by using the + * ALT_FLAG_DIRECT_CALL special case and the "always on" feature. + * - In case the replacement is either a direct call or a short code sequence + * depending on a feature bit, the ALTERNATIVE_2() macro is being used. + * The indirect call is the initial code sequence again, while the special + * code sequence is selected with the specified feature bit. In case the + * feature is not active, the direct call is used as above via the + * ALT_FLAG_DIRECT_CALL special case and the "always on" feature. + */ #define ____PVOP_CALL(ret, op, call_clbr, extra_clbr, ...) \ ({ \ PVOP_CALL_ARGS; \ PVOP_TEST_NULL(op); \ - asm volatile(paravirt_alt(PARAVIRT_CALL) \ + asm volatile(ALTERNATIVE(PARAVIRT_CALL, ALT_CALL_INSTR, \ + ALT_CALL_ALWAYS) \ : call_clbr, ASM_CALL_CONSTRAINT \ - : paravirt_type(op), \ + : paravirt_ptr(op), \ ##__VA_ARGS__ \ : "memory", "cc" extra_clbr); \ ret; \ @@ -441,10 +407,11 @@ int paravirt_disable_iospace(void); ({ \ PVOP_CALL_ARGS; \ PVOP_TEST_NULL(op); \ - asm volatile(ALTERNATIVE(paravirt_alt(PARAVIRT_CALL), \ - alt, cond) \ + asm volatile(ALTERNATIVE_2(PARAVIRT_CALL, \ + ALT_CALL_INSTR, ALT_CALL_ALWAYS, \ + alt, cond) \ : call_clbr, ASM_CALL_CONSTRAINT \ - : paravirt_type(op), \ + : paravirt_ptr(op), \ ##__VA_ARGS__ \ : "memory", "cc" extra_clbr); \ ret; \ @@ -542,8 +509,6 @@ int paravirt_disable_iospace(void); __PVOP_VCALL(op, PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2), \ PVOP_CALL_ARG3(arg3), PVOP_CALL_ARG4(arg4)) -void _paravirt_nop(void); -void paravirt_BUG(void); unsigned long paravirt_ret0(void); #ifdef CONFIG_PARAVIRT_XXL u64 _paravirt_ident_64(u64); @@ -553,11 +518,11 @@ void pv_native_irq_enable(void); unsigned long pv_native_read_cr2(void); #endif -#define paravirt_nop ((void *)_paravirt_nop) - -extern struct paravirt_patch_site __parainstructions[], - __parainstructions_end[]; +#define paravirt_nop ((void *)nop_func) #endif /* __ASSEMBLY__ */ + +#define ALT_NOT_XEN ALT_NOT(X86_FEATURE_XENPV) + #endif /* CONFIG_PARAVIRT */ #endif /* _ASM_X86_PARAVIRT_TYPES_H */ diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h index 85b6e3609cb9..ef9697f20129 100644 --- a/arch/x86/include/asm/qspinlock_paravirt.h +++ b/arch/x86/include/asm/qspinlock_paravirt.h @@ -56,8 +56,8 @@ __PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock_slowpath, ".spinlock.text"); "pop %rdx\n\t" \ FRAME_END -DEFINE_PARAVIRT_ASM(__raw_callee_save___pv_queued_spin_unlock, - PV_UNLOCK_ASM, .spinlock.text); +DEFINE_ASM_FUNC(__raw_callee_save___pv_queued_spin_unlock, + PV_UNLOCK_ASM, .spinlock.text); #else /* CONFIG_64BIT */ diff --git a/arch/x86/include/asm/syscall_wrapper.h b/arch/x86/include/asm/syscall_wrapper.h index fd2669b1cb2d..21f9407be5d3 100644 --- a/arch/x86/include/asm/syscall_wrapper.h +++ b/arch/x86/include/asm/syscall_wrapper.h @@ -86,9 +86,6 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); return sys_ni_syscall(); \ } -#define __SYS_NI(abi, name) \ - SYSCALL_ALIAS(__##abi##_##name, sys_ni_posix_timers); - #ifdef CONFIG_X86_64 #define __X64_SYS_STUB0(name) \ __SYS_STUB0(x64, sys_##name) @@ -100,13 +97,10 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); #define __X64_COND_SYSCALL(name) \ __COND_SYSCALL(x64, sys_##name) -#define __X64_SYS_NI(name) \ - __SYS_NI(x64, sys_##name) #else /* CONFIG_X86_64 */ #define __X64_SYS_STUB0(name) #define __X64_SYS_STUBx(x, name, ...) #define __X64_COND_SYSCALL(name) -#define __X64_SYS_NI(name) #endif /* CONFIG_X86_64 */ #if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) @@ -120,13 +114,10 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); #define __IA32_COND_SYSCALL(name) \ __COND_SYSCALL(ia32, sys_##name) -#define __IA32_SYS_NI(name) \ - __SYS_NI(ia32, sys_##name) #else /* CONFIG_X86_32 || CONFIG_IA32_EMULATION */ #define __IA32_SYS_STUB0(name) #define __IA32_SYS_STUBx(x, name, ...) #define __IA32_COND_SYSCALL(name) -#define __IA32_SYS_NI(name) #endif /* CONFIG_X86_32 || CONFIG_IA32_EMULATION */ #ifdef CONFIG_IA32_EMULATION @@ -135,8 +126,7 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); * additional wrappers (aptly named __ia32_sys_xyzzy) which decode the * ia32 regs in the proper order for shared or "common" syscalls. As some * syscalls may not be implemented, we need to expand COND_SYSCALL in - * kernel/sys_ni.c and SYS_NI in kernel/time/posix-stubs.c to cover this - * case as well. + * kernel/sys_ni.c to cover this case as well. */ #define __IA32_COMPAT_SYS_STUB0(name) \ __SYS_STUB0(ia32, compat_sys_##name) @@ -148,14 +138,10 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); #define __IA32_COMPAT_COND_SYSCALL(name) \ __COND_SYSCALL(ia32, compat_sys_##name) -#define __IA32_COMPAT_SYS_NI(name) \ - __SYS_NI(ia32, compat_sys_##name) - #else /* CONFIG_IA32_EMULATION */ #define __IA32_COMPAT_SYS_STUB0(name) #define __IA32_COMPAT_SYS_STUBx(x, name, ...) #define __IA32_COMPAT_COND_SYSCALL(name) -#define __IA32_COMPAT_SYS_NI(name) #endif /* CONFIG_IA32_EMULATION */ @@ -175,13 +161,10 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); #define __X32_COMPAT_COND_SYSCALL(name) \ __COND_SYSCALL(x64, compat_sys_##name) -#define __X32_COMPAT_SYS_NI(name) \ - __SYS_NI(x64, compat_sys_##name) #else /* CONFIG_X86_X32_ABI */ #define __X32_COMPAT_SYS_STUB0(name) #define __X32_COMPAT_SYS_STUBx(x, name, ...) #define __X32_COMPAT_COND_SYSCALL(name) -#define __X32_COMPAT_SYS_NI(name) #endif /* CONFIG_X86_X32_ABI */ @@ -212,17 +195,12 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); /* * As some compat syscalls may not be implemented, we need to expand - * COND_SYSCALL_COMPAT in kernel/sys_ni.c and COMPAT_SYS_NI in - * kernel/time/posix-stubs.c to cover this case as well. + * COND_SYSCALL_COMPAT in kernel/sys_ni.c to cover this case as well. */ #define COND_SYSCALL_COMPAT(name) \ __IA32_COMPAT_COND_SYSCALL(name) \ __X32_COMPAT_COND_SYSCALL(name) -#define COMPAT_SYS_NI(name) \ - __IA32_COMPAT_SYS_NI(name) \ - __X32_COMPAT_SYS_NI(name) - #endif /* CONFIG_COMPAT */ #define __SYSCALL_DEFINEx(x, name, ...) \ @@ -243,8 +221,8 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); * As the generic SYSCALL_DEFINE0() macro does not decode any parameters for * obvious reasons, and passing struct pt_regs *regs to it in %rdi does not * hurt, we only need to re-define it here to keep the naming congruent to - * SYSCALL_DEFINEx() -- which is essential for the COND_SYSCALL() and SYS_NI() - * macros to work correctly. + * SYSCALL_DEFINEx() -- which is essential for the COND_SYSCALL() macro + * to work correctly. */ #define SYSCALL_DEFINE0(sname) \ SYSCALL_METADATA(_##sname, 0); \ @@ -257,10 +235,6 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); __X64_COND_SYSCALL(name) \ __IA32_COND_SYSCALL(name) -#define SYS_NI(name) \ - __X64_SYS_NI(name) \ - __IA32_SYS_NI(name) - /* * For VSYSCALLS, we need to declare these three syscalls with the new diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h index 29832c338cdc..0b70653a98c1 100644 --- a/arch/x86/include/asm/text-patching.h +++ b/arch/x86/include/asm/text-patching.h @@ -6,18 +6,6 @@ #include <linux/stddef.h> #include <asm/ptrace.h> -struct paravirt_patch_site; -#ifdef CONFIG_PARAVIRT -void apply_paravirt(struct paravirt_patch_site *start, - struct paravirt_patch_site *end); -#else -static inline void apply_paravirt(struct paravirt_patch_site *start, - struct paravirt_patch_site *end) -{} -#define __parainstructions NULL -#define __parainstructions_end NULL -#endif - /* * Currently, the max observed size in the kernel code is * JUMP_LABEL_NOP_SIZE/RELATIVEJUMP_SIZE, which are 5. diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 1a0dd80d81ac..85a3ce2a3666 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -293,6 +293,7 @@ acpi_parse_lapic(union acpi_subtable_headers * header, const unsigned long end) processor->processor_id, /* ACPI ID */ processor->lapic_flags & ACPI_MADT_ENABLED); + has_lapic_cpus = true; return 0; } @@ -1134,7 +1135,6 @@ static int __init acpi_parse_madt_lapic_entries(void) if (!count) { count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC, acpi_parse_lapic, MAX_LOCAL_APIC); - has_lapic_cpus = count > 0; x2count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_X2APIC, acpi_parse_x2apic, MAX_LOCAL_APIC); } diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 73be3931e4f0..95e21596e2f9 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -160,7 +160,6 @@ extern s32 __retpoline_sites[], __retpoline_sites_end[]; extern s32 __return_sites[], __return_sites_end[]; extern s32 __cfi_sites[], __cfi_sites_end[]; extern s32 __ibt_endbr_seal[], __ibt_endbr_seal_end[]; -extern struct alt_instr __alt_instructions[], __alt_instructions_end[]; extern s32 __smp_locks[], __smp_locks_end[]; void text_poke_early(void *addr, const void *opcode, size_t len); @@ -255,6 +254,16 @@ static void __init_or_module noinline optimize_nops(u8 *instr, size_t len) } } +static void __init_or_module noinline optimize_nops_inplace(u8 *instr, size_t len) +{ + unsigned long flags; + + local_irq_save(flags); + optimize_nops(instr, len); + sync_core(); + local_irq_restore(flags); +} + /* * In this context, "source" is where the instructions are placed in the * section .altinstr_replacement, for example during kernel build by the @@ -385,6 +394,63 @@ apply_relocation(u8 *buf, size_t len, u8 *dest, u8 *src, size_t src_len) } } +/* Low-level backend functions usable from alternative code replacements. */ +DEFINE_ASM_FUNC(nop_func, "", .entry.text); +EXPORT_SYMBOL_GPL(nop_func); + +noinstr void BUG_func(void) +{ + BUG(); +} +EXPORT_SYMBOL_GPL(BUG_func); + +#define CALL_RIP_REL_OPCODE 0xff +#define CALL_RIP_REL_MODRM 0x15 + +/* + * Rewrite the "call BUG_func" replacement to point to the target of the + * indirect pv_ops call "call *disp(%ip)". + */ +static int alt_replace_call(u8 *instr, u8 *insn_buff, struct alt_instr *a) +{ + void *target, *bug = &BUG_func; + s32 disp; + + if (a->replacementlen != 5 || insn_buff[0] != CALL_INSN_OPCODE) { + pr_err("ALT_FLAG_DIRECT_CALL set for a non-call replacement instruction\n"); + BUG(); + } + + if (a->instrlen != 6 || + instr[0] != CALL_RIP_REL_OPCODE || + instr[1] != CALL_RIP_REL_MODRM) { + pr_err("ALT_FLAG_DIRECT_CALL set for unrecognized indirect call\n"); + BUG(); + } + + /* Skip CALL_RIP_REL_OPCODE and CALL_RIP_REL_MODRM */ + disp = *(s32 *)(instr + 2); +#ifdef CONFIG_X86_64 + /* ff 15 00 00 00 00 call *0x0(%rip) */ + /* target address is stored at "next instruction + disp". */ + target = *(void **)(instr + a->instrlen + disp); +#else + /* ff 15 00 00 00 00 call *0x0 */ + /* target address is stored at disp. */ + target = *(void **)disp; +#endif + if (!target) + target = bug; + + /* (BUG_func - .) + (target - BUG_func) := target - . */ + *(s32 *)(insn_buff + 1) += target - bug; + + if (target == &nop_func) + return 0; + + return 5; +} + /* * Replace instructions with better alternatives for this CPU type. This runs * before SMP is initialized to avoid SMP problems with self modifying code. @@ -438,20 +504,25 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start, * patch if feature is *NOT* present. */ if (!boot_cpu_has(a->cpuid) == !(a->flags & ALT_FLAG_NOT)) { - optimize_nops(instr, a->instrlen); + optimize_nops_inplace(instr, a->instrlen); continue; } - DPRINTK(ALT, "feat: %s%d*32+%d, old: (%pS (%px) len: %d), repl: (%px, len: %d)", - (a->flags & ALT_FLAG_NOT) ? "!" : "", + DPRINTK(ALT, "feat: %d*32+%d, old: (%pS (%px) len: %d), repl: (%px, len: %d) flags: 0x%x", a->cpuid >> 5, a->cpuid & 0x1f, instr, instr, a->instrlen, - replacement, a->replacementlen); + replacement, a->replacementlen, a->flags); memcpy(insn_buff, replacement, a->replacementlen); insn_buff_sz = a->replacementlen; + if (a->flags & ALT_FLAG_DIRECT_CALL) { + insn_buff_sz = alt_replace_call(instr, insn_buff, a); + if (insn_buff_sz < 0) + continue; + } + for (; insn_buff_sz < a->instrlen; insn_buff_sz++) insn_buff[insn_buff_sz] = 0x90; @@ -1411,46 +1482,6 @@ int alternatives_text_reserved(void *start, void *end) } #endif /* CONFIG_SMP */ -#ifdef CONFIG_PARAVIRT - -/* Use this to add nops to a buffer, then text_poke the whole buffer. */ -static void __init_or_module add_nops(void *insns, unsigned int len) -{ - while (len > 0) { - unsigned int noplen = len; - if (noplen > ASM_NOP_MAX) - noplen = ASM_NOP_MAX; - memcpy(insns, x86_nops[noplen], noplen); - insns += noplen; - len -= noplen; - } -} - -void __init_or_module apply_paravirt(struct paravirt_patch_site *start, - struct paravirt_patch_site *end) -{ - struct paravirt_patch_site *p; - char insn_buff[MAX_PATCH_LEN]; - - for (p = start; p < end; p++) { - unsigned int used; - - BUG_ON(p->len > MAX_PATCH_LEN); - /* prep the buffer with the original instructions */ - memcpy(insn_buff, p->instr, p->len); - used = paravirt_patch(p->type, insn_buff, (unsigned long)p->instr, p->len); - - BUG_ON(used > p->len); - - /* Pad the rest with nops */ - add_nops(insn_buff + used, p->len - used); - text_poke_early(p->instr, insn_buff, p->len); - } -} -extern struct paravirt_patch_site __start_parainstructions[], - __stop_parainstructions[]; -#endif /* CONFIG_PARAVIRT */ - /* * Self-test for the INT3 based CALL emulation code. * @@ -1586,28 +1617,11 @@ void __init alternative_instructions(void) */ /* - * Paravirt patching and alternative patching can be combined to - * replace a function call with a short direct code sequence (e.g. - * by setting a constant return value instead of doing that in an - * external function). - * In order to make this work the following sequence is required: - * 1. set (artificial) features depending on used paravirt - * functions which can later influence alternative patching - * 2. apply paravirt patching (generally replacing an indirect - * function call with a direct one) - * 3. apply alternative patching (e.g. replacing a direct function - * call with a custom code sequence) - * Doing paravirt patching after alternative patching would clobber - * the optimization of the custom code with a function call again. + * Make sure to set (artificial) features depending on used paravirt + * functions which can later influence alternative patching. */ paravirt_set_cap(); - /* - * First patch paravirt functions, such that we overwrite the indirect - * call with the direct call. - */ - apply_paravirt(__parainstructions, __parainstructions_end); - __apply_fineibt(__retpoline_sites, __retpoline_sites_end, __cfi_sites, __cfi_sites_end, true); @@ -1618,10 +1632,6 @@ void __init alternative_instructions(void) apply_retpolines(__retpoline_sites, __retpoline_sites_end); apply_returns(__return_sites, __return_sites_end); - /* - * Then patch alternatives, such that those paravirt calls that are in - * alternatives can be overwritten by their immediate fragments. - */ apply_alternatives(__alt_instructions, __alt_instructions_end); /* @@ -1685,8 +1695,8 @@ void __init_or_module text_poke_early(void *addr, const void *opcode, } else { local_irq_save(flags); memcpy(addr, opcode, len); - local_irq_restore(flags); sync_core(); + local_irq_restore(flags); /* * Could also do a CLFLUSH here to speed up CPU recovery; but diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c index e9ad518a5003..64ad2ddea121 100644 --- a/arch/x86/kernel/callthunks.c +++ b/arch/x86/kernel/callthunks.c @@ -233,14 +233,13 @@ patch_call_sites(s32 *start, s32 *end, const struct core_text *ct) } static __init_or_module void -patch_paravirt_call_sites(struct paravirt_patch_site *start, - struct paravirt_patch_site *end, - const struct core_text *ct) +patch_alt_call_sites(struct alt_instr *start, struct alt_instr *end, + const struct core_text *ct) { - struct paravirt_patch_site *p; + struct alt_instr *a; - for (p = start; p < end; p++) - patch_call(p->instr, ct); + for (a = start; a < end; a++) + patch_call((void *)&a->instr_offset + a->instr_offset, ct); } static __init_or_module void @@ -248,7 +247,7 @@ callthunks_setup(struct callthunk_sites *cs, const struct core_text *ct) { prdbg("Patching call sites %s\n", ct->name); patch_call_sites(cs->call_start, cs->call_end, ct); - patch_paravirt_call_sites(cs->pv_start, cs->pv_end, ct); + patch_alt_call_sites(cs->alt_start, cs->alt_end, ct); prdbg("Patching call sites done%s\n", ct->name); } @@ -257,8 +256,8 @@ void __init callthunks_patch_builtin_calls(void) struct callthunk_sites cs = { .call_start = __call_sites, .call_end = __call_sites_end, - .pv_start = __parainstructions, - .pv_end = __parainstructions_end + .alt_start = __alt_instructions, + .alt_end = __alt_instructions_end }; if (!cpu_feature_enabled(X86_FEATURE_CALL_DEPTH)) diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 070426b9895f..857e608af641 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -370,14 +370,14 @@ static __init struct microcode_intel *get_microcode_blob(struct ucode_cpu_info * { struct cpio_data cp; + intel_collect_cpu_info(&uci->cpu_sig); + if (!load_builtin_intel_microcode(&cp)) cp = find_microcode_in_initrd(ucode_path); if (!(cp.data && cp.size)) return NULL; - intel_collect_cpu_info(&uci->cpu_sig); - return scan_microcode(cp.data, cp.size, uci, save); } @@ -410,13 +410,13 @@ void __init load_ucode_intel_bsp(struct early_load_data *ed) { struct ucode_cpu_info uci; - ed->old_rev = intel_get_microcode_revision(); - uci.mc = get_microcode_blob(&uci, false); - if (uci.mc && apply_microcode_early(&uci) == UCODE_UPDATED) - ucode_patch_va = UCODE_BSP_LOADED; + ed->old_rev = uci.cpu_sig.rev; - ed->new_rev = uci.cpu_sig.rev; + if (uci.mc && apply_microcode_early(&uci) == UCODE_UPDATED) { + ucode_patch_va = UCODE_BSP_LOADED; + ed->new_rev = uci.cpu_sig.rev; + } } void load_ucode_intel_ap(void) @@ -457,12 +457,6 @@ static enum ucode_state apply_microcode_late(int cpu) if (ret != UCODE_UPDATED && ret != UCODE_OK) return ret; - if (!cpu && uci->cpu_sig.rev != cur_rev) { - pr_info("Updated to revision 0x%x, date = %04x-%02x-%02x\n", - uci->cpu_sig.rev, mc->hdr.date & 0xffff, mc->hdr.date >> 24, - (mc->hdr.date >> 16) & 0xff); - } - cpu_data(cpu).microcode = uci->cpu_sig.rev; if (!cpu) boot_cpu_data.microcode = uci->cpu_sig.rev; diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index d1dc39af6771..f479e5e793a2 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -268,6 +268,22 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) testl $X2APIC_ENABLE, %eax jnz .Lread_apicid_msr +#ifdef CONFIG_X86_X2APIC + /* + * If system is in X2APIC mode then MMIO base might not be + * mapped causing the MMIO read below to fault. Faults can't + * be handled at that point. + */ + cmpl $0, x2apic_mode(%rip) + jz .Lread_apicid_mmio + + /* Force the AP into X2APIC mode. */ + orl $X2APIC_ENABLE, %eax + wrmsr + jmp .Lread_apicid_msr +#endif + +.Lread_apicid_mmio: /* Read the APIC ID from the fix-mapped MMIO space. */ movq apic_mmio_base(%rip), %rcx addq $APIC_ID, %rcx diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index e8babebad7b8..a0ce46c0a2d8 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -576,7 +576,8 @@ static void kprobe_emulate_call_indirect(struct kprobe *p, struct pt_regs *regs) { unsigned long offs = addrmode_regoffs[p->ainsn.indirect.reg]; - int3_emulate_call(regs, regs_get_register(regs, offs)); + int3_emulate_push(regs, regs->ip - INT3_INSN_SIZE + p->ainsn.size); + int3_emulate_jmp(regs, regs_get_register(regs, offs)); } NOKPROBE_SYMBOL(kprobe_emulate_call_indirect); diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 0ddb3bd0f1aa..c461c1a4b6af 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -803,8 +803,8 @@ extern bool __raw_callee_save___kvm_vcpu_is_preempted(long); "cmpb $0, " __stringify(KVM_STEAL_TIME_preempted) "+steal_time(%rax)\n\t" \ "setne %al\n\t" -DEFINE_PARAVIRT_ASM(__raw_callee_save___kvm_vcpu_is_preempted, - PV_VCPU_PREEMPTED_ASM, .text); +DEFINE_ASM_FUNC(__raw_callee_save___kvm_vcpu_is_preempted, + PV_VCPU_PREEMPTED_ASM, .text); #endif static void __init kvm_guest_init(void) diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index 5f71a0cf4399..e18914c0e38a 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -276,7 +276,7 @@ int module_finalize(const Elf_Ehdr *hdr, struct module *me) { const Elf_Shdr *s, *alt = NULL, *locks = NULL, - *para = NULL, *orc = NULL, *orc_ip = NULL, + *orc = NULL, *orc_ip = NULL, *retpolines = NULL, *returns = NULL, *ibt_endbr = NULL, *calls = NULL, *cfi = NULL; char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; @@ -286,8 +286,6 @@ int module_finalize(const Elf_Ehdr *hdr, alt = s; if (!strcmp(".smp_locks", secstrings + s->sh_name)) locks = s; - if (!strcmp(".parainstructions", secstrings + s->sh_name)) - para = s; if (!strcmp(".orc_unwind", secstrings + s->sh_name)) orc = s; if (!strcmp(".orc_unwind_ip", secstrings + s->sh_name)) @@ -304,14 +302,6 @@ int module_finalize(const Elf_Ehdr *hdr, ibt_endbr = s; } - /* - * See alternative_instructions() for the ordering rules between the - * various patching types. - */ - if (para) { - void *pseg = (void *)para->sh_addr; - apply_paravirt(pseg, pseg + para->sh_size); - } if (retpolines || cfi) { void *rseg = NULL, *cseg = NULL; unsigned int rsize = 0, csize = 0; @@ -341,7 +331,7 @@ int module_finalize(const Elf_Ehdr *hdr, void *aseg = (void *)alt->sh_addr; apply_alternatives(aseg, aseg + alt->sh_size); } - if (calls || para) { + if (calls || alt) { struct callthunk_sites cs = {}; if (calls) { @@ -349,9 +339,9 @@ int module_finalize(const Elf_Ehdr *hdr, cs.call_end = (void *)calls->sh_addr + calls->sh_size; } - if (para) { - cs.pv_start = (void *)para->sh_addr; - cs.pv_end = (void *)para->sh_addr + para->sh_size; + if (alt) { + cs.alt_start = (void *)alt->sh_addr; + cs.alt_end = (void *)alt->sh_addr + alt->sh_size; } callthunks_patch_module_calls(&cs, me); diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 97f1436c1a20..5358d43886ad 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -34,14 +34,8 @@ #include <asm/io_bitmap.h> #include <asm/gsseg.h> -/* - * nop stub, which must not clobber anything *including the stack* to - * avoid confusing the entry prologues. - */ -DEFINE_PARAVIRT_ASM(_paravirt_nop, "", .entry.text); - /* stub always returning 0. */ -DEFINE_PARAVIRT_ASM(paravirt_ret0, "xor %eax,%eax", .entry.text); +DEFINE_ASM_FUNC(paravirt_ret0, "xor %eax,%eax", .entry.text); void __init default_banner(void) { @@ -49,26 +43,12 @@ void __init default_banner(void) pv_info.name); } -/* Undefined instruction for dealing with missing ops pointers. */ -noinstr void paravirt_BUG(void) -{ - BUG(); -} - -static unsigned paravirt_patch_call(void *insn_buff, const void *target, - unsigned long addr, unsigned len) -{ - __text_gen_insn(insn_buff, CALL_INSN_OPCODE, - (void *)addr, target, CALL_INSN_SIZE); - return CALL_INSN_SIZE; -} - #ifdef CONFIG_PARAVIRT_XXL -DEFINE_PARAVIRT_ASM(_paravirt_ident_64, "mov %rdi, %rax", .text); -DEFINE_PARAVIRT_ASM(pv_native_save_fl, "pushf; pop %rax", .noinstr.text); -DEFINE_PARAVIRT_ASM(pv_native_irq_disable, "cli", .noinstr.text); -DEFINE_PARAVIRT_ASM(pv_native_irq_enable, "sti", .noinstr.text); -DEFINE_PARAVIRT_ASM(pv_native_read_cr2, "mov %cr2, %rax", .noinstr.text); +DEFINE_ASM_FUNC(_paravirt_ident_64, "mov %rdi, %rax", .text); +DEFINE_ASM_FUNC(pv_native_save_fl, "pushf; pop %rax", .noinstr.text); +DEFINE_ASM_FUNC(pv_native_irq_disable, "cli", .noinstr.text); +DEFINE_ASM_FUNC(pv_native_irq_enable, "sti", .noinstr.text); +DEFINE_ASM_FUNC(pv_native_read_cr2, "mov %cr2, %rax", .noinstr.text); #endif DEFINE_STATIC_KEY_TRUE(virt_spin_lock_key); @@ -85,28 +65,6 @@ static void native_tlb_remove_table(struct mmu_gather *tlb, void *table) tlb_remove_page(tlb, table); } -unsigned int paravirt_patch(u8 type, void *insn_buff, unsigned long addr, - unsigned int len) -{ - /* - * Neat trick to map patch type back to the call within the - * corresponding structure. - */ - void *opfunc = *((void **)&pv_ops + type); - unsigned ret; - - if (opfunc == NULL) - /* If there's no function, patch it with paravirt_BUG() */ - ret = paravirt_patch_call(insn_buff, paravirt_BUG, addr, len); - else if (opfunc == _paravirt_nop) - ret = 0; - else - /* Otherwise call the function. */ - ret = paravirt_patch_call(insn_buff, opfunc, addr, len); - - return ret; -} - struct static_key paravirt_steal_enabled; struct static_key paravirt_steal_rq_enabled; diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 54a5596adaa6..a349dbfc6d5a 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -267,19 +267,6 @@ SECTIONS } #endif - /* - * start address and size of operations which during runtime - * can be patched with virtualization friendly instructions or - * baremetal native ones. Think page table operations. - * Details in paravirt_types.h - */ - . = ALIGN(8); - .parainstructions : AT(ADDR(.parainstructions) - LOAD_OFFSET) { - __parainstructions = .; - *(.parainstructions) - __parainstructions_end = .; - } - #ifdef CONFIG_RETPOLINE /* * List of instructions that call/jmp/jcc to retpoline thunks diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 238afd7335e4..4943f6b2bbee 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -2388,7 +2388,7 @@ static u16 kvm_hvcall_signal_event(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *h if (!eventfd) return HV_STATUS_INVALID_PORT_ID; - eventfd_signal(eventfd, 1); + eventfd_signal(eventfd); return HV_STATUS_SUCCESS; } diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 4900c078045a..6ee925d66648 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2972,6 +2972,25 @@ static void sev_es_vcpu_after_set_cpuid(struct vcpu_svm *svm) set_msr_interception(vcpu, svm->msrpm, MSR_TSC_AUX, v_tsc_aux, v_tsc_aux); } + + /* + * For SEV-ES, accesses to MSR_IA32_XSS should not be intercepted if + * the host/guest supports its use. + * + * guest_can_use() checks a number of requirements on the host/guest to + * ensure that MSR_IA32_XSS is available, but it might report true even + * if X86_FEATURE_XSAVES isn't configured in the guest to ensure host + * MSR_IA32_XSS is always properly restored. For SEV-ES, it is better + * to further check that the guest CPUID actually supports + * X86_FEATURE_XSAVES so that accesses to MSR_IA32_XSS by misbehaved + * guests will still get intercepted and caught in the normal + * kvm_emulate_rdmsr()/kvm_emulated_wrmsr() paths. + */ + if (guest_can_use(vcpu, X86_FEATURE_XSAVES) && + guest_cpuid_has(vcpu, X86_FEATURE_XSAVES)) + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_XSS, 1, 1); + else + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_XSS, 0, 0); } void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index f3bb30b40876..a8bd4e909a1e 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -103,6 +103,7 @@ static const struct svm_direct_access_msrs { { .index = MSR_IA32_LASTBRANCHTOIP, .always = false }, { .index = MSR_IA32_LASTINTFROMIP, .always = false }, { .index = MSR_IA32_LASTINTTOIP, .always = false }, + { .index = MSR_IA32_XSS, .always = false }, { .index = MSR_EFER, .always = false }, { .index = MSR_IA32_CR_PAT, .always = false }, { .index = MSR_AMD64_SEV_ES_GHCB, .always = true }, diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index be67ab7fdd10..c409f934c377 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -30,7 +30,7 @@ #define IOPM_SIZE PAGE_SIZE * 3 #define MSRPM_SIZE PAGE_SIZE * 2 -#define MAX_DIRECT_ACCESS_MSRS 46 +#define MAX_DIRECT_ACCESS_MSRS 47 #define MSRPM_OFFSETS 32 extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; extern bool npt_enabled; diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index e53fad915a62..523bb6df5ac9 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -2088,7 +2088,7 @@ static bool kvm_xen_hcall_evtchn_send(struct kvm_vcpu *vcpu, u64 param, u64 *r) if (ret < 0 && ret != -ENOTCONN) return false; } else { - eventfd_signal(evtchnfd->deliver.eventfd.ctx, 1); + eventfd_signal(evtchnfd->deliver.eventfd.ctx); } *r = 0; diff --git a/arch/x86/lib/csum-partial_64.c b/arch/x86/lib/csum-partial_64.c index cea25ca8b8cf..c9dae65ac01b 100644 --- a/arch/x86/lib/csum-partial_64.c +++ b/arch/x86/lib/csum-partial_64.c @@ -11,26 +11,23 @@ #include <asm/checksum.h> #include <asm/word-at-a-time.h> -static inline unsigned short from32to16(unsigned a) +static inline __wsum csum_finalize_sum(u64 temp64) { - unsigned short b = a >> 16; - asm("addw %w2,%w0\n\t" - "adcw $0,%w0\n" - : "=r" (b) - : "0" (b), "r" (a)); - return b; + return (__force __wsum)((temp64 + ror64(temp64, 32)) >> 32); } -static inline __wsum csum_tail(u64 temp64, int odd) +static inline unsigned long update_csum_40b(unsigned long sum, const unsigned long m[5]) { - unsigned int result; - - result = add32_with_carry(temp64 >> 32, temp64 & 0xffffffff); - if (unlikely(odd)) { - result = from32to16(result); - result = ((result >> 8) & 0xff) | ((result & 0xff) << 8); - } - return (__force __wsum)result; + asm("addq %1,%0\n\t" + "adcq %2,%0\n\t" + "adcq %3,%0\n\t" + "adcq %4,%0\n\t" + "adcq %5,%0\n\t" + "adcq $0,%0" + :"+r" (sum) + :"m" (m[0]), "m" (m[1]), "m" (m[2]), + "m" (m[3]), "m" (m[4])); + return sum; } /* @@ -47,64 +44,32 @@ static inline __wsum csum_tail(u64 temp64, int odd) __wsum csum_partial(const void *buff, int len, __wsum sum) { u64 temp64 = (__force u64)sum; - unsigned odd; - odd = 1 & (unsigned long) buff; - if (unlikely(odd)) { - if (unlikely(len == 0)) - return sum; - temp64 = ror32((__force u32)sum, 8); - temp64 += (*(unsigned char *)buff << 8); - len--; - buff++; + /* Do two 40-byte chunks in parallel to get better ILP */ + if (likely(len >= 80)) { + u64 temp64_2 = 0; + do { + temp64 = update_csum_40b(temp64, buff); + temp64_2 = update_csum_40b(temp64_2, buff + 40); + buff += 80; + len -= 80; + } while (len >= 80); + + asm("addq %1,%0\n\t" + "adcq $0,%0" + :"+r" (temp64): "r" (temp64_2)); } /* - * len == 40 is the hot case due to IPv6 headers, but annotating it likely() - * has noticeable negative affect on codegen for all other cases with - * minimal performance benefit here. + * len == 40 is the hot case due to IPv6 headers, so return + * early for that exact case without checking the tail bytes. */ - if (len == 40) { - asm("addq 0*8(%[src]),%[res]\n\t" - "adcq 1*8(%[src]),%[res]\n\t" - "adcq 2*8(%[src]),%[res]\n\t" - "adcq 3*8(%[src]),%[res]\n\t" - "adcq 4*8(%[src]),%[res]\n\t" - "adcq $0,%[res]" - : [res] "+r"(temp64) - : [src] "r"(buff), "m"(*(const char(*)[40])buff)); - return csum_tail(temp64, odd); - } - if (unlikely(len >= 64)) { - /* - * Extra accumulators for better ILP in the loop. - */ - u64 tmp_accum, tmp_carries; - - asm("xorl %k[tmp_accum],%k[tmp_accum]\n\t" - "xorl %k[tmp_carries],%k[tmp_carries]\n\t" - "subl $64, %[len]\n\t" - "1:\n\t" - "addq 0*8(%[src]),%[res]\n\t" - "adcq 1*8(%[src]),%[res]\n\t" - "adcq 2*8(%[src]),%[res]\n\t" - "adcq 3*8(%[src]),%[res]\n\t" - "adcl $0,%k[tmp_carries]\n\t" - "addq 4*8(%[src]),%[tmp_accum]\n\t" - "adcq 5*8(%[src]),%[tmp_accum]\n\t" - "adcq 6*8(%[src]),%[tmp_accum]\n\t" - "adcq 7*8(%[src]),%[tmp_accum]\n\t" - "adcl $0,%k[tmp_carries]\n\t" - "addq $64, %[src]\n\t" - "subl $64, %[len]\n\t" - "jge 1b\n\t" - "addq %[tmp_accum],%[res]\n\t" - "adcq %[tmp_carries],%[res]\n\t" - "adcq $0,%[res]" - : [tmp_accum] "=&r"(tmp_accum), - [tmp_carries] "=&r"(tmp_carries), [res] "+r"(temp64), - [len] "+r"(len), [src] "+r"(buff) - : "m"(*(const char *)buff)); + if (len >= 40) { + temp64 = update_csum_40b(temp64, buff); + len -= 40; + if (!len) + return csum_finalize_sum(temp64); + buff += 40; } if (len & 32) { @@ -143,7 +108,7 @@ __wsum csum_partial(const void *buff, int len, __wsum sum) : [res] "+r"(temp64) : [trail] "r"(trail)); } - return csum_tail(temp64, odd); + return csum_finalize_sum(temp64); } EXPORT_SYMBOL(csum_partial); diff --git a/arch/x86/lib/misc.c b/arch/x86/lib/misc.c index 92cd8ecc3a2c..40b81c338ae5 100644 --- a/arch/x86/lib/misc.c +++ b/arch/x86/lib/misc.c @@ -8,7 +8,7 @@ */ int num_digits(int val) { - int m = 10; + long long m = 10; int d = 1; if (val < 0) { diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index ab778eac1952..679b09cfe241 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -1370,6 +1370,8 @@ void do_user_addr_fault(struct pt_regs *regs, goto done; } count_vm_vma_lock_event(VMA_LOCK_RETRY); + if (fault & VM_FAULT_MAJOR) + flags |= FAULT_FLAG_TRIED; /* Quick path to respond to signals */ if (fault_signal_pending(fault, regs)) { diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c index d30949e25ebd..a3bae2b24626 100644 --- a/arch/x86/tools/relocs.c +++ b/arch/x86/tools/relocs.c @@ -66,7 +66,7 @@ static const char * const sym_regex_kernel[S_NSYMTYPES] = { [S_REL] = "^(__init_(begin|end)|" "__x86_cpu_dev_(start|end)|" - "(__parainstructions|__alt_instructions)(_end)?|" + "__alt_instructions(_end)?|" "(__iommu_table|__apicdrivers|__smp_locks)(_end)?|" "__(start|end)_pci_.*|" #if CONFIG_FW_LOADER diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig index 9b1ec5d8c99c..a65fc2ae15b4 100644 --- a/arch/x86/xen/Kconfig +++ b/arch/x86/xen/Kconfig @@ -9,6 +9,7 @@ config XEN select PARAVIRT_CLOCK select X86_HV_CALLBACK_VECTOR depends on X86_64 || (X86_32 && X86_PAE) + depends on X86_64 || (X86_GENERIC || MPENTIUM4 || MCORE2 || MATOM || MK8) depends on X86_LOCAL_APIC && X86_TSC help This is the Linux Xen port. Enabling this will allow the diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c index 6092fea7d651..39982f955cfe 100644 --- a/arch/x86/xen/irq.c +++ b/arch/x86/xen/irq.c @@ -45,7 +45,7 @@ static const typeof(pv_ops) xen_irq_ops __initconst = { /* Initial interrupt flag handling only called while interrupts off. */ .save_fl = __PV_IS_CALLEE_SAVE(paravirt_ret0), .irq_disable = __PV_IS_CALLEE_SAVE(paravirt_nop), - .irq_enable = __PV_IS_CALLEE_SAVE(paravirt_BUG), + .irq_enable = __PV_IS_CALLEE_SAVE(BUG_func), .safe_halt = xen_safe_halt, .halt = xen_halt, diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl index 06eefa9c1458..497b5d32f457 100644 --- a/arch/xtensa/kernel/syscalls/syscall.tbl +++ b/arch/xtensa/kernel/syscalls/syscall.tbl @@ -427,3 +427,5 @@ 454 common futex_wake sys_futex_wake 455 common futex_wait sys_futex_wait 456 common futex_requeue sys_futex_requeue +457 common statmount sys_statmount +458 common listmount sys_listmount diff --git a/block/Kconfig b/block/Kconfig index 55ae2286a4de..1de4682d48cc 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -78,6 +78,26 @@ config BLK_DEV_INTEGRITY_T10 select CRC_T10DIF select CRC64_ROCKSOFT +config BLK_DEV_WRITE_MOUNTED + bool "Allow writing to mounted block devices" + default y + help + When a block device is mounted, writing to its buffer cache is very + likely going to cause filesystem corruption. It is also rather easy to + crash the kernel in this way since the filesystem has no practical way + of detecting these writes to buffer cache and verifying its metadata + integrity. However there are some setups that need this capability + like running fsck on read-only mounted root device, modifying some + features on mounted ext4 filesystem, and similar. If you say N, the + kernel will prevent processes from writing to block devices that are + mounted by filesystems which provides some more protection from runaway + privileged processes and generally makes it much harder to crash + filesystem drivers. Note however that this does not prevent + underlying device(s) from being modified by other means, e.g. by + directly submitting SCSI commands or through access to lower layers of + storage stack. If in doubt, say Y. The configuration can be overridden + with the bdev_allow_write_mounted boot option. + config BLK_DEV_ZONED bool "Zoned block device support" select MQ_IOSCHED_DEADLINE diff --git a/block/badblocks.c b/block/badblocks.c index fc92d4e18aa3..db4ec8b9b2a8 100644 --- a/block/badblocks.c +++ b/block/badblocks.c @@ -1312,12 +1312,14 @@ re_check: prev = prev_badblocks(bb, &bad, hint); /* start after all badblocks */ - if ((prev + 1) >= bb->count && !overlap_front(bb, prev, &bad)) { + if ((prev >= 0) && + ((prev + 1) >= bb->count) && !overlap_front(bb, prev, &bad)) { len = sectors; goto update_sectors; } - if (overlap_front(bb, prev, &bad)) { + /* Overlapped with front badblocks record */ + if ((prev >= 0) && overlap_front(bb, prev, &bad)) { if (BB_ACK(p[prev])) acked_badblocks++; else diff --git a/block/bdev.c b/block/bdev.c index 750aec178b6a..e9f1b12bd75c 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -30,6 +30,9 @@ #include "../fs/internal.h" #include "blk.h" +/* Should we allow writing to mounted block devices? */ +static bool bdev_allow_write_mounted = IS_ENABLED(CONFIG_BLK_DEV_WRITE_MOUNTED); + struct bdev_inode { struct block_device bdev; struct inode vfs_inode; @@ -207,85 +210,88 @@ int sync_blockdev_range(struct block_device *bdev, loff_t lstart, loff_t lend) EXPORT_SYMBOL(sync_blockdev_range); /** - * freeze_bdev - lock a filesystem and force it into a consistent state + * bdev_freeze - lock a filesystem and force it into a consistent state * @bdev: blockdevice to lock * * If a superblock is found on this device, we take the s_umount semaphore * on it to make sure nobody unmounts until the snapshot creation is done. * The reference counter (bd_fsfreeze_count) guarantees that only the last * unfreeze process can unfreeze the frozen filesystem actually when multiple - * freeze requests arrive simultaneously. It counts up in freeze_bdev() and - * count down in thaw_bdev(). When it becomes 0, thaw_bdev() will unfreeze + * freeze requests arrive simultaneously. It counts up in bdev_freeze() and + * count down in bdev_thaw(). When it becomes 0, thaw_bdev() will unfreeze * actually. + * + * Return: On success zero is returned, negative error code on failure. */ -int freeze_bdev(struct block_device *bdev) +int bdev_freeze(struct block_device *bdev) { - struct super_block *sb; int error = 0; mutex_lock(&bdev->bd_fsfreeze_mutex); - if (++bdev->bd_fsfreeze_count > 1) - goto done; - - sb = get_active_super(bdev); - if (!sb) - goto sync; - if (sb->s_op->freeze_super) - error = sb->s_op->freeze_super(sb, FREEZE_HOLDER_USERSPACE); - else - error = freeze_super(sb, FREEZE_HOLDER_USERSPACE); - deactivate_super(sb); - if (error) { - bdev->bd_fsfreeze_count--; - goto done; + if (atomic_inc_return(&bdev->bd_fsfreeze_count) > 1) { + mutex_unlock(&bdev->bd_fsfreeze_mutex); + return 0; } - bdev->bd_fsfreeze_sb = sb; -sync: - sync_blockdev(bdev); -done: + mutex_lock(&bdev->bd_holder_lock); + if (bdev->bd_holder_ops && bdev->bd_holder_ops->freeze) { + error = bdev->bd_holder_ops->freeze(bdev); + lockdep_assert_not_held(&bdev->bd_holder_lock); + } else { + mutex_unlock(&bdev->bd_holder_lock); + error = sync_blockdev(bdev); + } + + if (error) + atomic_dec(&bdev->bd_fsfreeze_count); + mutex_unlock(&bdev->bd_fsfreeze_mutex); return error; } -EXPORT_SYMBOL(freeze_bdev); +EXPORT_SYMBOL(bdev_freeze); /** - * thaw_bdev - unlock filesystem + * bdev_thaw - unlock filesystem * @bdev: blockdevice to unlock * - * Unlocks the filesystem and marks it writeable again after freeze_bdev(). + * Unlocks the filesystem and marks it writeable again after bdev_freeze(). + * + * Return: On success zero is returned, negative error code on failure. */ -int thaw_bdev(struct block_device *bdev) +int bdev_thaw(struct block_device *bdev) { - struct super_block *sb; - int error = -EINVAL; + int error = -EINVAL, nr_freeze; mutex_lock(&bdev->bd_fsfreeze_mutex); - if (!bdev->bd_fsfreeze_count) + + /* + * If this returns < 0 it means that @bd_fsfreeze_count was + * already 0 and no decrement was performed. + */ + nr_freeze = atomic_dec_if_positive(&bdev->bd_fsfreeze_count); + if (nr_freeze < 0) goto out; error = 0; - if (--bdev->bd_fsfreeze_count > 0) + if (nr_freeze > 0) goto out; - sb = bdev->bd_fsfreeze_sb; - if (!sb) - goto out; + mutex_lock(&bdev->bd_holder_lock); + if (bdev->bd_holder_ops && bdev->bd_holder_ops->thaw) { + error = bdev->bd_holder_ops->thaw(bdev); + lockdep_assert_not_held(&bdev->bd_holder_lock); + } else { + mutex_unlock(&bdev->bd_holder_lock); + } - if (sb->s_op->thaw_super) - error = sb->s_op->thaw_super(sb, FREEZE_HOLDER_USERSPACE); - else - error = thaw_super(sb, FREEZE_HOLDER_USERSPACE); if (error) - bdev->bd_fsfreeze_count++; - else - bdev->bd_fsfreeze_sb = NULL; + atomic_inc(&bdev->bd_fsfreeze_count); out: mutex_unlock(&bdev->bd_fsfreeze_mutex); return error; } -EXPORT_SYMBOL(thaw_bdev); +EXPORT_SYMBOL(bdev_thaw); /* * pseudo-fs @@ -729,9 +735,60 @@ void blkdev_put_no_open(struct block_device *bdev) { put_device(&bdev->bd_device); } - + +static bool bdev_writes_blocked(struct block_device *bdev) +{ + return bdev->bd_writers == -1; +} + +static void bdev_block_writes(struct block_device *bdev) +{ + bdev->bd_writers = -1; +} + +static void bdev_unblock_writes(struct block_device *bdev) +{ + bdev->bd_writers = 0; +} + +static bool bdev_may_open(struct block_device *bdev, blk_mode_t mode) +{ + if (bdev_allow_write_mounted) + return true; + /* Writes blocked? */ + if (mode & BLK_OPEN_WRITE && bdev_writes_blocked(bdev)) + return false; + if (mode & BLK_OPEN_RESTRICT_WRITES && bdev->bd_writers > 0) + return false; + return true; +} + +static void bdev_claim_write_access(struct block_device *bdev, blk_mode_t mode) +{ + if (bdev_allow_write_mounted) + return; + + /* Claim exclusive or shared write access. */ + if (mode & BLK_OPEN_RESTRICT_WRITES) + bdev_block_writes(bdev); + else if (mode & BLK_OPEN_WRITE) + bdev->bd_writers++; +} + +static void bdev_yield_write_access(struct block_device *bdev, blk_mode_t mode) +{ + if (bdev_allow_write_mounted) + return; + + /* Yield exclusive or shared write access. */ + if (mode & BLK_OPEN_RESTRICT_WRITES) + bdev_unblock_writes(bdev); + else if (mode & BLK_OPEN_WRITE) + bdev->bd_writers--; +} + /** - * blkdev_get_by_dev - open a block device by device number + * bdev_open_by_dev - open a block device by device number * @dev: device number of block device to open * @mode: open mode (BLK_OPEN_*) * @holder: exclusive holder identifier @@ -743,32 +800,46 @@ void blkdev_put_no_open(struct block_device *bdev) * * Use this interface ONLY if you really do not have anything better - i.e. when * you are behind a truly sucky interface and all you are given is a device - * number. Everything else should use blkdev_get_by_path(). + * number. Everything else should use bdev_open_by_path(). * * CONTEXT: * Might sleep. * * RETURNS: - * Reference to the block_device on success, ERR_PTR(-errno) on failure. + * Handle with a reference to the block_device on success, ERR_PTR(-errno) on + * failure. */ -struct block_device *blkdev_get_by_dev(dev_t dev, blk_mode_t mode, void *holder, - const struct blk_holder_ops *hops) +struct bdev_handle *bdev_open_by_dev(dev_t dev, blk_mode_t mode, void *holder, + const struct blk_holder_ops *hops) { - bool unblock_events = true; + struct bdev_handle *handle = kmalloc(sizeof(struct bdev_handle), + GFP_KERNEL); struct block_device *bdev; + bool unblock_events = true; struct gendisk *disk; int ret; + if (!handle) + return ERR_PTR(-ENOMEM); + ret = devcgroup_check_permission(DEVCG_DEV_BLOCK, MAJOR(dev), MINOR(dev), ((mode & BLK_OPEN_READ) ? DEVCG_ACC_READ : 0) | ((mode & BLK_OPEN_WRITE) ? DEVCG_ACC_WRITE : 0)); if (ret) - return ERR_PTR(ret); + goto free_handle; + + /* Blocking writes requires exclusive opener */ + if (mode & BLK_OPEN_RESTRICT_WRITES && !holder) { + ret = -EINVAL; + goto free_handle; + } bdev = blkdev_get_no_open(dev); - if (!bdev) - return ERR_PTR(-ENXIO); + if (!bdev) { + ret = -ENXIO; + goto free_handle; + } disk = bdev->bd_disk; if (holder) { @@ -791,12 +862,16 @@ struct block_device *blkdev_get_by_dev(dev_t dev, blk_mode_t mode, void *holder, goto abort_claiming; if (!try_module_get(disk->fops->owner)) goto abort_claiming; + ret = -EBUSY; + if (!bdev_may_open(bdev, mode)) + goto abort_claiming; if (bdev_is_partition(bdev)) ret = blkdev_get_part(bdev, mode); else ret = blkdev_get_whole(bdev, mode); if (ret) goto put_module; + bdev_claim_write_access(bdev, mode); if (holder) { bd_finish_claiming(bdev, holder, hops); @@ -817,7 +892,10 @@ struct block_device *blkdev_get_by_dev(dev_t dev, blk_mode_t mode, void *holder, if (unblock_events) disk_unblock_events(disk); - return bdev; + handle->bdev = bdev; + handle->holder = holder; + handle->mode = mode; + return handle; put_module: module_put(disk->fops->owner); abort_claiming: @@ -827,34 +905,14 @@ abort_claiming: disk_unblock_events(disk); put_blkdev: blkdev_put_no_open(bdev); +free_handle: + kfree(handle); return ERR_PTR(ret); } -EXPORT_SYMBOL(blkdev_get_by_dev); - -struct bdev_handle *bdev_open_by_dev(dev_t dev, blk_mode_t mode, void *holder, - const struct blk_holder_ops *hops) -{ - struct bdev_handle *handle = kmalloc(sizeof(*handle), GFP_KERNEL); - struct block_device *bdev; - - if (!handle) - return ERR_PTR(-ENOMEM); - bdev = blkdev_get_by_dev(dev, mode, holder, hops); - if (IS_ERR(bdev)) { - kfree(handle); - return ERR_CAST(bdev); - } - handle->bdev = bdev; - handle->holder = holder; - if (holder) - mode |= BLK_OPEN_EXCL; - handle->mode = mode; - return handle; -} EXPORT_SYMBOL(bdev_open_by_dev); /** - * blkdev_get_by_path - open a block device by name + * bdev_open_by_path - open a block device by name * @path: path to the block device to open * @mode: open mode (BLK_OPEN_*) * @holder: exclusive holder identifier @@ -868,29 +926,9 @@ EXPORT_SYMBOL(bdev_open_by_dev); * Might sleep. * * RETURNS: - * Reference to the block_device on success, ERR_PTR(-errno) on failure. + * Handle with a reference to the block_device on success, ERR_PTR(-errno) on + * failure. */ -struct block_device *blkdev_get_by_path(const char *path, blk_mode_t mode, - void *holder, const struct blk_holder_ops *hops) -{ - struct block_device *bdev; - dev_t dev; - int error; - - error = lookup_bdev(path, &dev); - if (error) - return ERR_PTR(error); - - bdev = blkdev_get_by_dev(dev, mode, holder, hops); - if (!IS_ERR(bdev) && (mode & BLK_OPEN_WRITE) && bdev_read_only(bdev)) { - blkdev_put(bdev, holder); - return ERR_PTR(-EACCES); - } - - return bdev; -} -EXPORT_SYMBOL(blkdev_get_by_path); - struct bdev_handle *bdev_open_by_path(const char *path, blk_mode_t mode, void *holder, const struct blk_holder_ops *hops) { @@ -913,8 +951,9 @@ struct bdev_handle *bdev_open_by_path(const char *path, blk_mode_t mode, } EXPORT_SYMBOL(bdev_open_by_path); -void blkdev_put(struct block_device *bdev, void *holder) +void bdev_release(struct bdev_handle *handle) { + struct block_device *bdev = handle->bdev; struct gendisk *disk = bdev->bd_disk; /* @@ -928,8 +967,10 @@ void blkdev_put(struct block_device *bdev, void *holder) sync_blockdev(bdev); mutex_lock(&disk->open_mutex); - if (holder) - bd_end_claim(bdev, holder); + bdev_yield_write_access(bdev, handle->mode); + + if (handle->holder) + bd_end_claim(bdev, handle->holder); /* * Trigger event checking and tell drivers to flush MEDIA_CHANGE @@ -946,12 +987,6 @@ void blkdev_put(struct block_device *bdev, void *holder) module_put(disk->fops->owner); blkdev_put_no_open(bdev); -} -EXPORT_SYMBOL(blkdev_put); - -void bdev_release(struct bdev_handle *handle) -{ - blkdev_put(handle->bdev, handle->holder); kfree(handle); } EXPORT_SYMBOL(bdev_release); @@ -1102,3 +1137,12 @@ void bdev_statx_dioalign(struct inode *inode, struct kstat *stat) blkdev_put_no_open(bdev); } + +static int __init setup_bdev_allow_write_mounted(char *str) +{ + if (kstrtobool(str, &bdev_allow_write_mounted)) + pr_warn("Invalid option string for bdev_allow_write_mounted:" + " '%s'\n", str); + return 1; +} +__setup("bdev_allow_write_mounted=", setup_bdev_allow_write_mounted); diff --git a/drivers/accel/habanalabs/common/device.c b/drivers/accel/habanalabs/common/device.c index 9711e8fc979d..3a89644f087c 100644 --- a/drivers/accel/habanalabs/common/device.c +++ b/drivers/accel/habanalabs/common/device.c @@ -2044,7 +2044,7 @@ static void hl_notifier_event_send(struct hl_notifier_event *notifier_event, u64 notifier_event->events_mask |= event_mask; if (notifier_event->eventfd) - eventfd_signal(notifier_event->eventfd, 1); + eventfd_signal(notifier_event->eventfd); mutex_unlock(¬ifier_event->lock); } diff --git a/drivers/accel/ivpu/ivpu_hw_37xx.c b/drivers/accel/ivpu/ivpu_hw_37xx.c index 4ccf1994b97a..d530384f8d60 100644 --- a/drivers/accel/ivpu/ivpu_hw_37xx.c +++ b/drivers/accel/ivpu/ivpu_hw_37xx.c @@ -53,10 +53,12 @@ #define ICB_0_1_IRQ_MASK ((((u64)ICB_1_IRQ_MASK) << 32) | ICB_0_IRQ_MASK) -#define BUTTRESS_IRQ_MASK ((REG_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, FREQ_CHANGE)) | \ - (REG_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, ATS_ERR)) | \ +#define BUTTRESS_IRQ_MASK ((REG_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, ATS_ERR)) | \ (REG_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, UFI_ERR))) +#define BUTTRESS_ALL_IRQ_MASK (BUTTRESS_IRQ_MASK | \ + (REG_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, FREQ_CHANGE))) + #define BUTTRESS_IRQ_ENABLE_MASK ((u32)~BUTTRESS_IRQ_MASK) #define BUTTRESS_IRQ_DISABLE_MASK ((u32)-1) @@ -74,8 +76,12 @@ static void ivpu_hw_wa_init(struct ivpu_device *vdev) vdev->wa.clear_runtime_mem = false; vdev->wa.d3hot_after_power_off = true; - if (ivpu_device_id(vdev) == PCI_DEVICE_ID_MTL && ivpu_revision(vdev) < 4) + REGB_WR32(VPU_37XX_BUTTRESS_INTERRUPT_STAT, BUTTRESS_ALL_IRQ_MASK); + if (REGB_RD32(VPU_37XX_BUTTRESS_INTERRUPT_STAT) == BUTTRESS_ALL_IRQ_MASK) { + /* Writing 1s does not clear the interrupt status register */ vdev->wa.interrupt_clear_with_0 = true; + REGB_WR32(VPU_37XX_BUTTRESS_INTERRUPT_STAT, 0x0); + } IVPU_PRINT_WA(punit_disabled); IVPU_PRINT_WA(clear_runtime_mem); diff --git a/drivers/accel/qaic/mhi_controller.c b/drivers/accel/qaic/mhi_controller.c index 5036e58e7235..1405623b03e4 100644 --- a/drivers/accel/qaic/mhi_controller.c +++ b/drivers/accel/qaic/mhi_controller.c @@ -404,8 +404,21 @@ static struct mhi_controller_config aic100_config = { static int mhi_read_reg(struct mhi_controller *mhi_cntrl, void __iomem *addr, u32 *out) { - u32 tmp = readl_relaxed(addr); + u32 tmp; + /* + * SOC_HW_VERSION quirk + * The SOC_HW_VERSION register (offset 0x224) is not reliable and + * may contain uninitialized values, including 0xFFFFFFFF. This could + * cause a false positive link down error. Instead, intercept any + * reads and provide the correct value of the register. + */ + if (addr - mhi_cntrl->regs == 0x224) { + *out = 0x60110200; + return 0; + } + + tmp = readl_relaxed(addr); if (tmp == U32_MAX) return -EIO; diff --git a/drivers/accel/qaic/qaic_data.c b/drivers/accel/qaic/qaic_data.c index 4a8e43a7a6a4..d42f002bc0cf 100644 --- a/drivers/accel/qaic/qaic_data.c +++ b/drivers/accel/qaic/qaic_data.c @@ -777,7 +777,6 @@ struct drm_gem_object *qaic_gem_prime_import(struct drm_device *dev, struct dma_ struct dma_buf_attachment *attach; struct drm_gem_object *obj; struct qaic_bo *bo; - size_t size; int ret; bo = qaic_alloc_init_bo(); @@ -795,13 +794,12 @@ struct drm_gem_object *qaic_gem_prime_import(struct drm_device *dev, struct dma_ goto attach_fail; } - size = PAGE_ALIGN(attach->dmabuf->size); - if (size == 0) { + if (!attach->dmabuf->size) { ret = -EINVAL; goto size_align_fail; } - drm_gem_private_object_init(dev, obj, size); + drm_gem_private_object_init(dev, obj, attach->dmabuf->size); /* * skipping dma_buf_map_attachment() as we do not know the direction * just yet. Once the direction is known in the subsequent IOCTL to diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 92128aae2d06..7658103ba760 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -1921,7 +1921,7 @@ static void binder_deferred_fd_close(int fd) if (!twcb) return; init_task_work(&twcb->twork, binder_do_fd_close); - twcb->file = close_fd_get_file(fd); + twcb->file = file_close_fd(fd); if (twcb->file) { // pin it until binder_do_fd_close(); see comments there get_file(twcb->file); diff --git a/drivers/atm/solos-pci.c b/drivers/atm/solos-pci.c index 94fbc3abe60e..d3c30a28c410 100644 --- a/drivers/atm/solos-pci.c +++ b/drivers/atm/solos-pci.c @@ -449,9 +449,9 @@ static ssize_t console_show(struct device *dev, struct device_attribute *attr, struct sk_buff *skb; unsigned int len; - spin_lock(&card->cli_queue_lock); + spin_lock_bh(&card->cli_queue_lock); skb = skb_dequeue(&card->cli_queue[SOLOS_CHAN(atmdev)]); - spin_unlock(&card->cli_queue_lock); + spin_unlock_bh(&card->cli_queue_lock); if(skb == NULL) return sprintf(buf, "No data.\n"); @@ -956,14 +956,14 @@ static void pclose(struct atm_vcc *vcc) struct pkt_hdr *header; /* Remove any yet-to-be-transmitted packets from the pending queue */ - spin_lock(&card->tx_queue_lock); + spin_lock_bh(&card->tx_queue_lock); skb_queue_walk_safe(&card->tx_queue[port], skb, tmpskb) { if (SKB_CB(skb)->vcc == vcc) { skb_unlink(skb, &card->tx_queue[port]); solos_pop(vcc, skb); } } - spin_unlock(&card->tx_queue_lock); + spin_unlock_bh(&card->tx_queue_lock); skb = alloc_skb(sizeof(*header), GFP_KERNEL); if (!skb) { diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 9f2d412fc560..8a8cd4fc9238 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -245,9 +245,7 @@ static int lo_write_bvec(struct file *file, struct bio_vec *bvec, loff_t *ppos) iov_iter_bvec(&i, ITER_SOURCE, bvec, 1, bvec->bv_len); - file_start_write(file); bw = vfs_iter_write(file, &i, ppos, 0); - file_end_write(file); if (likely(bw == bvec->bv_len)) return 0; diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 83600b45e12a..3eaf02ebeebe 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -893,12 +893,9 @@ static int ublk_map_io(const struct ublk_queue *ubq, const struct request *req, */ if (ublk_need_map_req(req)) { struct iov_iter iter; - struct iovec iov; const int dir = ITER_DEST; - import_single_range(dir, u64_to_user_ptr(io->addr), rq_bytes, - &iov, &iter); - + import_ubuf(dir, u64_to_user_ptr(io->addr), rq_bytes, &iter); return ublk_copy_user_pages(req, 0, &iter, dir); } return rq_bytes; @@ -915,13 +912,11 @@ static int ublk_unmap_io(const struct ublk_queue *ubq, if (ublk_need_unmap_req(req)) { struct iov_iter iter; - struct iovec iov; const int dir = ITER_SOURCE; WARN_ON_ONCE(io->res > rq_bytes); - import_single_range(dir, u64_to_user_ptr(io->addr), io->res, - &iov, &iter); + import_ubuf(dir, u64_to_user_ptr(io->addr), io->res, &iter); return ublk_copy_user_pages(req, 0, &iter, dir); } return rq_bytes; diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index d53d6aa8ee69..47556d8ccc32 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -1019,12 +1019,12 @@ static void virtblk_config_changed(struct virtio_device *vdev) static int init_vq(struct virtio_blk *vblk) { int err; - int i; + unsigned short i; vq_callback_t **callbacks; const char **names; struct virtqueue **vqs; unsigned short num_vqs; - unsigned int num_poll_vqs; + unsigned short num_poll_vqs; struct virtio_device *vdev = vblk->vdev; struct irq_affinity desc = { 0, }; @@ -1068,13 +1068,13 @@ static int init_vq(struct virtio_blk *vblk) for (i = 0; i < num_vqs - num_poll_vqs; i++) { callbacks[i] = virtblk_done; - snprintf(vblk->vqs[i].name, VQ_NAME_LEN, "req.%d", i); + snprintf(vblk->vqs[i].name, VQ_NAME_LEN, "req.%u", i); names[i] = vblk->vqs[i].name; } for (; i < num_vqs; i++) { callbacks[i] = NULL; - snprintf(vblk->vqs[i].name, VQ_NAME_LEN, "req_poll.%d", i); + snprintf(vblk->vqs[i].name, VQ_NAME_LEN, "req_poll.%u", i); names[i] = vblk->vqs[i].name; } diff --git a/drivers/bluetooth/hci_vhci.c b/drivers/bluetooth/hci_vhci.c index f3892e9ce800..572d68d52965 100644 --- a/drivers/bluetooth/hci_vhci.c +++ b/drivers/bluetooth/hci_vhci.c @@ -11,6 +11,7 @@ #include <linux/module.h> #include <asm/unaligned.h> +#include <linux/atomic.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/slab.h> @@ -44,6 +45,7 @@ struct vhci_data { bool wakeup; __u16 msft_opcode; bool aosp_capable; + atomic_t initialized; }; static int vhci_open_dev(struct hci_dev *hdev) @@ -75,11 +77,10 @@ static int vhci_send_frame(struct hci_dev *hdev, struct sk_buff *skb) memcpy(skb_push(skb, 1), &hci_skb_pkt_type(skb), 1); - mutex_lock(&data->open_mutex); skb_queue_tail(&data->readq, skb); - mutex_unlock(&data->open_mutex); - wake_up_interruptible(&data->read_wait); + if (atomic_read(&data->initialized)) + wake_up_interruptible(&data->read_wait); return 0; } @@ -464,7 +465,8 @@ static int __vhci_create_device(struct vhci_data *data, __u8 opcode) skb_put_u8(skb, 0xff); skb_put_u8(skb, opcode); put_unaligned_le16(hdev->id, skb_put(skb, 2)); - skb_queue_tail(&data->readq, skb); + skb_queue_head(&data->readq, skb); + atomic_inc(&data->initialized); wake_up_interruptible(&data->read_wait); return 0; diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index d57bc066dce6..9ed9239b1228 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -2158,13 +2158,23 @@ static int sysc_reset(struct sysc *ddata) sysc_val = sysc_read_sysconfig(ddata); sysc_val |= sysc_mask; sysc_write(ddata, sysc_offset, sysc_val); - /* Flush posted write */ + + /* + * Some devices need a delay before reading registers + * after reset. Presumably a srst_udelay is not needed + * for devices that use a rstctrl register reset. + */ + if (ddata->cfg.srst_udelay) + fsleep(ddata->cfg.srst_udelay); + + /* + * Flush posted write. For devices needing srst_udelay + * this should trigger an interconnect error if the + * srst_udelay value is needed but not configured. + */ sysc_val = sysc_read_sysconfig(ddata); } - if (ddata->cfg.srst_udelay) - fsleep(ddata->cfg.srst_udelay); - if (ddata->post_reset_quirk) ddata->post_reset_quirk(ddata); diff --git a/drivers/char/random.c b/drivers/char/random.c index 4a9c79391dee..456be28ba67c 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1364,7 +1364,6 @@ static void __cold try_to_generate_entropy(void) SYSCALL_DEFINE3(getrandom, char __user *, ubuf, size_t, len, unsigned int, flags) { struct iov_iter iter; - struct iovec iov; int ret; if (flags & ~(GRND_NONBLOCK | GRND_RANDOM | GRND_INSECURE)) @@ -1385,7 +1384,7 @@ SYSCALL_DEFINE3(getrandom, char __user *, ubuf, size_t, len, unsigned int, flags return ret; } - ret = import_single_range(ITER_DEST, ubuf, len, &iov, &iter); + ret = import_ubuf(ITER_DEST, ubuf, len, &iter); if (unlikely(ret)) return ret; return get_random_bytes_user(&iter); @@ -1491,7 +1490,6 @@ static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg) return 0; case RNDADDENTROPY: { struct iov_iter iter; - struct iovec iov; ssize_t ret; int len; @@ -1503,7 +1501,7 @@ static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg) return -EINVAL; if (get_user(len, p++)) return -EFAULT; - ret = import_single_range(ITER_SOURCE, p, len, &iov, &iter); + ret = import_ubuf(ITER_SOURCE, p, len, &iter); if (unlikely(ret)) return ret; ret = write_pool_user(&iter); diff --git a/drivers/clk/qcom/Kconfig b/drivers/clk/qcom/Kconfig index ad1acd9b7426..dbc3950c5960 100644 --- a/drivers/clk/qcom/Kconfig +++ b/drivers/clk/qcom/Kconfig @@ -767,6 +767,7 @@ config SM_CAMCC_8450 config SM_CAMCC_8550 tristate "SM8550 Camera Clock Controller" + depends on ARM64 || COMPILE_TEST select SM_GCC_8550 help Support for the camera clock controller on SM8550 devices. diff --git a/drivers/clk/rockchip/clk-rk3128.c b/drivers/clk/rockchip/clk-rk3128.c index aa53797dbfc1..75071e0cd321 100644 --- a/drivers/clk/rockchip/clk-rk3128.c +++ b/drivers/clk/rockchip/clk-rk3128.c @@ -138,7 +138,7 @@ PNAME(mux_pll_src_5plls_p) = { "cpll", "gpll", "gpll_div2", "gpll_div3", "usb480 PNAME(mux_pll_src_4plls_p) = { "cpll", "gpll", "gpll_div2", "usb480m" }; PNAME(mux_pll_src_3plls_p) = { "cpll", "gpll", "gpll_div2" }; -PNAME(mux_aclk_peri_src_p) = { "gpll_peri", "cpll_peri", "gpll_div2_peri", "gpll_div3_peri" }; +PNAME(mux_clk_peri_src_p) = { "gpll", "cpll", "gpll_div2", "gpll_div3" }; PNAME(mux_mmc_src_p) = { "cpll", "gpll", "gpll_div2", "xin24m" }; PNAME(mux_clk_cif_out_src_p) = { "clk_cif_src", "xin24m" }; PNAME(mux_sclk_vop_src_p) = { "cpll", "gpll", "gpll_div2", "gpll_div3" }; @@ -275,23 +275,17 @@ static struct rockchip_clk_branch common_clk_branches[] __initdata = { RK2928_CLKGATE_CON(0), 11, GFLAGS), /* PD_PERI */ - GATE(0, "gpll_peri", "gpll", CLK_IGNORE_UNUSED, + COMPOSITE(0, "clk_peri_src", mux_clk_peri_src_p, 0, + RK2928_CLKSEL_CON(10), 14, 2, MFLAGS, 0, 5, DFLAGS, RK2928_CLKGATE_CON(2), 0, GFLAGS), - GATE(0, "cpll_peri", "cpll", CLK_IGNORE_UNUSED, - RK2928_CLKGATE_CON(2), 0, GFLAGS), - GATE(0, "gpll_div2_peri", "gpll_div2", CLK_IGNORE_UNUSED, - RK2928_CLKGATE_CON(2), 0, GFLAGS), - GATE(0, "gpll_div3_peri", "gpll_div3", CLK_IGNORE_UNUSED, - RK2928_CLKGATE_CON(2), 0, GFLAGS), - COMPOSITE_NOGATE(0, "aclk_peri_src", mux_aclk_peri_src_p, 0, - RK2928_CLKSEL_CON(10), 14, 2, MFLAGS, 0, 5, DFLAGS), - COMPOSITE_NOMUX(PCLK_PERI, "pclk_peri", "aclk_peri_src", 0, + + COMPOSITE_NOMUX(PCLK_PERI, "pclk_peri", "clk_peri_src", 0, RK2928_CLKSEL_CON(10), 12, 2, DFLAGS | CLK_DIVIDER_POWER_OF_TWO, RK2928_CLKGATE_CON(2), 3, GFLAGS), - COMPOSITE_NOMUX(HCLK_PERI, "hclk_peri", "aclk_peri_src", 0, + COMPOSITE_NOMUX(HCLK_PERI, "hclk_peri", "clk_peri_src", 0, RK2928_CLKSEL_CON(10), 8, 2, DFLAGS | CLK_DIVIDER_POWER_OF_TWO, RK2928_CLKGATE_CON(2), 2, GFLAGS), - GATE(ACLK_PERI, "aclk_peri", "aclk_peri_src", 0, + GATE(ACLK_PERI, "aclk_peri", "clk_peri_src", 0, RK2928_CLKGATE_CON(2), 1, GFLAGS), GATE(SCLK_TIMER0, "sclk_timer0", "xin24m", 0, @@ -316,7 +310,7 @@ static struct rockchip_clk_branch common_clk_branches[] __initdata = { GATE(SCLK_MIPI_24M, "clk_mipi_24m", "xin24m", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(2), 15, GFLAGS), - COMPOSITE(SCLK_SDMMC, "sclk_sdmmc0", mux_mmc_src_p, 0, + COMPOSITE(SCLK_SDMMC, "sclk_sdmmc", mux_mmc_src_p, 0, RK2928_CLKSEL_CON(11), 6, 2, MFLAGS, 0, 6, DFLAGS, RK2928_CLKGATE_CON(2), 11, GFLAGS), @@ -490,7 +484,7 @@ static struct rockchip_clk_branch common_clk_branches[] __initdata = { GATE(HCLK_I2S_2CH, "hclk_i2s_2ch", "hclk_peri", 0, RK2928_CLKGATE_CON(7), 2, GFLAGS), GATE(0, "hclk_usb_peri", "hclk_peri", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(9), 13, GFLAGS), GATE(HCLK_HOST2, "hclk_host2", "hclk_peri", 0, RK2928_CLKGATE_CON(7), 3, GFLAGS), - GATE(HCLK_OTG, "hclk_otg", "hclk_peri", 0, RK2928_CLKGATE_CON(3), 13, GFLAGS), + GATE(HCLK_OTG, "hclk_otg", "hclk_peri", 0, RK2928_CLKGATE_CON(5), 13, GFLAGS), GATE(0, "hclk_peri_ahb", "hclk_peri", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(9), 14, GFLAGS), GATE(HCLK_SPDIF, "hclk_spdif", "hclk_peri", 0, RK2928_CLKGATE_CON(10), 9, GFLAGS), GATE(HCLK_TSP, "hclk_tsp", "hclk_peri", 0, RK2928_CLKGATE_CON(10), 12, GFLAGS), diff --git a/drivers/clk/rockchip/clk-rk3568.c b/drivers/clk/rockchip/clk-rk3568.c index 16dabe2b9c47..db713e1526cd 100644 --- a/drivers/clk/rockchip/clk-rk3568.c +++ b/drivers/clk/rockchip/clk-rk3568.c @@ -72,6 +72,7 @@ static struct rockchip_pll_rate_table rk3568_pll_rates[] = { RK3036_PLL_RATE(408000000, 1, 68, 2, 2, 1, 0), RK3036_PLL_RATE(312000000, 1, 78, 6, 1, 1, 0), RK3036_PLL_RATE(297000000, 2, 99, 4, 1, 1, 0), + RK3036_PLL_RATE(292500000, 1, 195, 4, 4, 1, 0), RK3036_PLL_RATE(241500000, 2, 161, 4, 2, 1, 0), RK3036_PLL_RATE(216000000, 1, 72, 4, 2, 1, 0), RK3036_PLL_RATE(200000000, 1, 100, 3, 4, 1, 0), diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c index 44b19e696176..3d5e6d705fc6 100644 --- a/drivers/connector/cn_proc.c +++ b/drivers/connector/cn_proc.c @@ -108,8 +108,9 @@ static inline void send_msg(struct cn_msg *msg) filter_data[1] = 0; } - cn_netlink_send_mult(msg, msg->len, 0, CN_IDX_PROC, GFP_NOWAIT, - cn_filter, (void *)filter_data); + if (cn_netlink_send_mult(msg, msg->len, 0, CN_IDX_PROC, GFP_NOWAIT, + cn_filter, (void *)filter_data) == -ESRCH) + atomic_set(&proc_event_num_listeners, 0); local_unlock(&local_event.lock); } diff --git a/drivers/cxl/core/hdm.c b/drivers/cxl/core/hdm.c index 1cc9be85ba4c..7d97790b893d 100644 --- a/drivers/cxl/core/hdm.c +++ b/drivers/cxl/core/hdm.c @@ -363,10 +363,9 @@ resource_size_t cxl_dpa_resource_start(struct cxl_endpoint_decoder *cxled) { resource_size_t base = -1; - down_read(&cxl_dpa_rwsem); + lockdep_assert_held(&cxl_dpa_rwsem); if (cxled->dpa_res) base = cxled->dpa_res->start; - up_read(&cxl_dpa_rwsem); return base; } @@ -839,6 +838,8 @@ static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld, cxld->target_type = CXL_DECODER_HOSTONLYMEM; else cxld->target_type = CXL_DECODER_DEVMEM; + + guard(rwsem_write)(&cxl_region_rwsem); if (cxld->id != cxl_num_decoders_committed(port)) { dev_warn(&port->dev, "decoder%d.%d: Committed out of order\n", diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c index fc5c2b414793..2f43d368ba07 100644 --- a/drivers/cxl/core/memdev.c +++ b/drivers/cxl/core/memdev.c @@ -227,10 +227,16 @@ int cxl_trigger_poison_list(struct cxl_memdev *cxlmd) if (!port || !is_cxl_endpoint(port)) return -EINVAL; - rc = down_read_interruptible(&cxl_dpa_rwsem); + rc = down_read_interruptible(&cxl_region_rwsem); if (rc) return rc; + rc = down_read_interruptible(&cxl_dpa_rwsem); + if (rc) { + up_read(&cxl_region_rwsem); + return rc; + } + if (cxl_num_decoders_committed(port) == 0) { /* No regions mapped to this memdev */ rc = cxl_get_poison_by_memdev(cxlmd); @@ -239,6 +245,7 @@ int cxl_trigger_poison_list(struct cxl_memdev *cxlmd) rc = cxl_get_poison_by_endpoint(port); } up_read(&cxl_dpa_rwsem); + up_read(&cxl_region_rwsem); return rc; } @@ -324,10 +331,16 @@ int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa) if (!IS_ENABLED(CONFIG_DEBUG_FS)) return 0; - rc = down_read_interruptible(&cxl_dpa_rwsem); + rc = down_read_interruptible(&cxl_region_rwsem); if (rc) return rc; + rc = down_read_interruptible(&cxl_dpa_rwsem); + if (rc) { + up_read(&cxl_region_rwsem); + return rc; + } + rc = cxl_validate_poison_dpa(cxlmd, dpa); if (rc) goto out; @@ -355,6 +368,7 @@ int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa) trace_cxl_poison(cxlmd, cxlr, &record, 0, 0, CXL_POISON_TRACE_INJECT); out: up_read(&cxl_dpa_rwsem); + up_read(&cxl_region_rwsem); return rc; } @@ -372,10 +386,16 @@ int cxl_clear_poison(struct cxl_memdev *cxlmd, u64 dpa) if (!IS_ENABLED(CONFIG_DEBUG_FS)) return 0; - rc = down_read_interruptible(&cxl_dpa_rwsem); + rc = down_read_interruptible(&cxl_region_rwsem); if (rc) return rc; + rc = down_read_interruptible(&cxl_dpa_rwsem); + if (rc) { + up_read(&cxl_region_rwsem); + return rc; + } + rc = cxl_validate_poison_dpa(cxlmd, dpa); if (rc) goto out; @@ -412,6 +432,7 @@ int cxl_clear_poison(struct cxl_memdev *cxlmd, u64 dpa) trace_cxl_poison(cxlmd, cxlr, &record, 0, 0, CXL_POISON_TRACE_CLEAR); out: up_read(&cxl_dpa_rwsem); + up_read(&cxl_region_rwsem); return rc; } diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c index eff20e83d0a6..37e1652afbc7 100644 --- a/drivers/cxl/core/pci.c +++ b/drivers/cxl/core/pci.c @@ -620,7 +620,7 @@ void read_cdat_data(struct cxl_port *port) struct pci_dev *pdev = NULL; struct cxl_memdev *cxlmd; size_t cdat_length; - void *cdat_table; + void *cdat_table, *cdat_buf; int rc; if (is_cxl_memdev(uport)) { @@ -651,16 +651,15 @@ void read_cdat_data(struct cxl_port *port) return; } - cdat_table = devm_kzalloc(dev, cdat_length + sizeof(__le32), - GFP_KERNEL); - if (!cdat_table) + cdat_buf = devm_kzalloc(dev, cdat_length + sizeof(__le32), GFP_KERNEL); + if (!cdat_buf) return; - rc = cxl_cdat_read_table(dev, cdat_doe, cdat_table, &cdat_length); + rc = cxl_cdat_read_table(dev, cdat_doe, cdat_buf, &cdat_length); if (rc) goto err; - cdat_table = cdat_table + sizeof(__le32); + cdat_table = cdat_buf + sizeof(__le32); if (cdat_checksum(cdat_table, cdat_length)) goto err; @@ -670,7 +669,7 @@ void read_cdat_data(struct cxl_port *port) err: /* Don't leave table data allocated on error */ - devm_kfree(dev, cdat_table); + devm_kfree(dev, cdat_buf); dev_err(dev, "Failed to read/validate CDAT.\n"); } EXPORT_SYMBOL_NS_GPL(read_cdat_data, CXL); diff --git a/drivers/cxl/core/pmu.c b/drivers/cxl/core/pmu.c index 7684c843e5a5..5d8e06b0ba6e 100644 --- a/drivers/cxl/core/pmu.c +++ b/drivers/cxl/core/pmu.c @@ -23,7 +23,7 @@ const struct device_type cxl_pmu_type = { static void remove_dev(void *dev) { - device_del(dev); + device_unregister(dev); } int devm_cxl_pmu_add(struct device *parent, struct cxl_pmu_regs *regs, diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c index 38441634e4c6..b7c93bb18f6e 100644 --- a/drivers/cxl/core/port.c +++ b/drivers/cxl/core/port.c @@ -226,9 +226,9 @@ static ssize_t dpa_resource_show(struct device *dev, struct device_attribute *at char *buf) { struct cxl_endpoint_decoder *cxled = to_cxl_endpoint_decoder(dev); - u64 base = cxl_dpa_resource_start(cxled); - return sysfs_emit(buf, "%#llx\n", base); + guard(rwsem_read)(&cxl_dpa_rwsem); + return sysfs_emit(buf, "%#llx\n", (u64)cxl_dpa_resource_start(cxled)); } static DEVICE_ATTR_RO(dpa_resource); diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c index 56e575c79bb4..3e817a6f94c6 100644 --- a/drivers/cxl/core/region.c +++ b/drivers/cxl/core/region.c @@ -2467,10 +2467,6 @@ int cxl_get_poison_by_endpoint(struct cxl_port *port) struct cxl_poison_context ctx; int rc = 0; - rc = down_read_interruptible(&cxl_region_rwsem); - if (rc) - return rc; - ctx = (struct cxl_poison_context) { .port = port }; @@ -2480,7 +2476,6 @@ int cxl_get_poison_by_endpoint(struct cxl_port *port) rc = cxl_get_poison_unmapped(to_cxl_memdev(port->uport_dev), &ctx); - up_read(&cxl_region_rwsem); return rc; } diff --git a/drivers/dma/fsl-edma-common.c b/drivers/dma/fsl-edma-common.c index 6a3abe5b1790..b53f46245c37 100644 --- a/drivers/dma/fsl-edma-common.c +++ b/drivers/dma/fsl-edma-common.c @@ -828,6 +828,7 @@ void fsl_edma_free_chan_resources(struct dma_chan *chan) dma_pool_destroy(fsl_chan->tcd_pool); fsl_chan->tcd_pool = NULL; fsl_chan->is_sw = false; + fsl_chan->srcid = 0; } void fsl_edma_cleanup_vchan(struct dma_device *dmadev) diff --git a/drivers/dma/fsl-edma-main.c b/drivers/dma/fsl-edma-main.c index 4635e16d7705..238a69bd0d6f 100644 --- a/drivers/dma/fsl-edma-main.c +++ b/drivers/dma/fsl-edma-main.c @@ -396,9 +396,8 @@ static int fsl_edma3_attach_pd(struct platform_device *pdev, struct fsl_edma_eng link = device_link_add(dev, pd_chan, DL_FLAG_STATELESS | DL_FLAG_PM_RUNTIME | DL_FLAG_RPM_ACTIVE); - if (IS_ERR(link)) { - dev_err(dev, "Failed to add device_link to %d: %ld\n", i, - PTR_ERR(link)); + if (!link) { + dev_err(dev, "Failed to add device_link to %d\n", i); return -EINVAL; } @@ -631,6 +630,8 @@ static int fsl_edma_suspend_late(struct device *dev) for (i = 0; i < fsl_edma->n_chans; i++) { fsl_chan = &fsl_edma->chans[i]; + if (fsl_edma->chan_masked & BIT(i)) + continue; spin_lock_irqsave(&fsl_chan->vchan.lock, flags); /* Make sure chan is idle or will force disable. */ if (unlikely(!fsl_chan->idle)) { @@ -655,13 +656,16 @@ static int fsl_edma_resume_early(struct device *dev) for (i = 0; i < fsl_edma->n_chans; i++) { fsl_chan = &fsl_edma->chans[i]; + if (fsl_edma->chan_masked & BIT(i)) + continue; fsl_chan->pm_state = RUNNING; edma_write_tcdreg(fsl_chan, 0, csr); if (fsl_chan->slave_id != 0) fsl_edma_chan_mux(fsl_chan, fsl_chan->slave_id, true); } - edma_writel(fsl_edma, EDMA_CR_ERGA | EDMA_CR_ERCA, regs->cr); + if (!(fsl_edma->drvdata->flags & FSL_EDMA_DRV_SPLIT_REG)) + edma_writel(fsl_edma, EDMA_CR_ERGA | EDMA_CR_ERCA, regs->cr); return 0; } diff --git a/drivers/dma/idxd/registers.h b/drivers/dma/idxd/registers.h index 7b54a3939ea1..315c004f58e4 100644 --- a/drivers/dma/idxd/registers.h +++ b/drivers/dma/idxd/registers.h @@ -440,12 +440,14 @@ union wqcfg { /* * This macro calculates the offset into the GRPCFG register * idxd - struct idxd * - * n - wq id - * ofs - the index of the 32b dword for the config register + * n - group id + * ofs - the index of the 64b qword for the config register * - * The WQCFG register block is divided into groups per each wq. The n index - * allows us to move to the register group that's for that particular wq. - * Each register is 32bits. The ofs gives us the number of register to access. + * The GRPCFG register block is divided into three sub-registers, which + * are GRPWQCFG, GRPENGCFG and GRPFLGCFG. The n index allows us to move + * to the register block that contains the three sub-registers. + * Each register block is 64bits. And the ofs gives us the offset + * within the GRPWQCFG register to access. */ #define GRPWQCFG_OFFSET(idxd_dev, n, ofs) ((idxd_dev)->grpcfg_offset +\ (n) * GRPCFG_SIZE + sizeof(u64) * (ofs)) diff --git a/drivers/dma/idxd/submit.c b/drivers/dma/idxd/submit.c index c01db23e3333..3f922518e3a5 100644 --- a/drivers/dma/idxd/submit.c +++ b/drivers/dma/idxd/submit.c @@ -183,13 +183,6 @@ int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc) portal = idxd_wq_portal_addr(wq); /* - * The wmb() flushes writes to coherent DMA data before - * possibly triggering a DMA read. The wmb() is necessary - * even on UP because the recipient is a device. - */ - wmb(); - - /* * Pending the descriptor to the lockless list for the irq_entry * that we designated the descriptor to. */ @@ -199,6 +192,13 @@ int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc) llist_add(&desc->llnode, &ie->pending_llist); } + /* + * The wmb() flushes writes to coherent DMA data before + * possibly triggering a DMA read. The wmb() is necessary + * even on UP because the recipient is a device. + */ + wmb(); + if (wq_dedicated(wq)) { iosubmit_cmds512(portal, desc->hw, 1); } else { diff --git a/drivers/dma/stm32-dma.c b/drivers/dma/stm32-dma.c index 72d83cd9ed6b..90857d08a1a7 100644 --- a/drivers/dma/stm32-dma.c +++ b/drivers/dma/stm32-dma.c @@ -1246,8 +1246,8 @@ static struct dma_async_tx_descriptor *stm32_dma_prep_dma_memcpy( enum dma_slave_buswidth max_width; struct stm32_dma_desc *desc; size_t xfer_count, offset; - u32 num_sgs, best_burst, dma_burst, threshold; - int i; + u32 num_sgs, best_burst, threshold; + int dma_burst, i; num_sgs = DIV_ROUND_UP(len, STM32_DMA_ALIGNED_MAX_DATA_ITEMS); desc = kzalloc(struct_size(desc, sg_req, num_sgs), GFP_NOWAIT); @@ -1266,6 +1266,10 @@ static struct dma_async_tx_descriptor *stm32_dma_prep_dma_memcpy( best_burst = stm32_dma_get_best_burst(len, STM32_DMA_MAX_BURST, threshold, max_width); dma_burst = stm32_dma_get_burst(chan, best_burst); + if (dma_burst < 0) { + kfree(desc); + return NULL; + } stm32_dma_clear_reg(&desc->sg_req[i].chan_reg); desc->sg_req[i].chan_reg.dma_scr = diff --git a/drivers/dma/ti/k3-psil-am62.c b/drivers/dma/ti/k3-psil-am62.c index 2b6fd6e37c61..1272b1541f61 100644 --- a/drivers/dma/ti/k3-psil-am62.c +++ b/drivers/dma/ti/k3-psil-am62.c @@ -74,7 +74,9 @@ static struct psil_ep am62_src_ep_map[] = { PSIL_SAUL(0x7505, 21, 35, 8, 36, 0), PSIL_SAUL(0x7506, 22, 43, 8, 43, 0), PSIL_SAUL(0x7507, 23, 43, 8, 44, 0), - /* PDMA_MAIN0 - SPI0-3 */ + /* PDMA_MAIN0 - SPI0-2 */ + PSIL_PDMA_XY_PKT(0x4300), + PSIL_PDMA_XY_PKT(0x4301), PSIL_PDMA_XY_PKT(0x4302), PSIL_PDMA_XY_PKT(0x4303), PSIL_PDMA_XY_PKT(0x4304), @@ -85,8 +87,6 @@ static struct psil_ep am62_src_ep_map[] = { PSIL_PDMA_XY_PKT(0x4309), PSIL_PDMA_XY_PKT(0x430a), PSIL_PDMA_XY_PKT(0x430b), - PSIL_PDMA_XY_PKT(0x430c), - PSIL_PDMA_XY_PKT(0x430d), /* PDMA_MAIN1 - UART0-6 */ PSIL_PDMA_XY_PKT(0x4400), PSIL_PDMA_XY_PKT(0x4401), @@ -141,7 +141,9 @@ static struct psil_ep am62_dst_ep_map[] = { /* SAUL */ PSIL_SAUL(0xf500, 27, 83, 8, 83, 1), PSIL_SAUL(0xf501, 28, 91, 8, 91, 1), - /* PDMA_MAIN0 - SPI0-3 */ + /* PDMA_MAIN0 - SPI0-2 */ + PSIL_PDMA_XY_PKT(0xc300), + PSIL_PDMA_XY_PKT(0xc301), PSIL_PDMA_XY_PKT(0xc302), PSIL_PDMA_XY_PKT(0xc303), PSIL_PDMA_XY_PKT(0xc304), @@ -152,8 +154,6 @@ static struct psil_ep am62_dst_ep_map[] = { PSIL_PDMA_XY_PKT(0xc309), PSIL_PDMA_XY_PKT(0xc30a), PSIL_PDMA_XY_PKT(0xc30b), - PSIL_PDMA_XY_PKT(0xc30c), - PSIL_PDMA_XY_PKT(0xc30d), /* PDMA_MAIN1 - UART0-6 */ PSIL_PDMA_XY_PKT(0xc400), PSIL_PDMA_XY_PKT(0xc401), diff --git a/drivers/dma/ti/k3-psil-am62a.c b/drivers/dma/ti/k3-psil-am62a.c index ca9d71f91422..4cf9123b0e93 100644 --- a/drivers/dma/ti/k3-psil-am62a.c +++ b/drivers/dma/ti/k3-psil-am62a.c @@ -84,7 +84,9 @@ static struct psil_ep am62a_src_ep_map[] = { PSIL_SAUL(0x7505, 21, 35, 8, 36, 0), PSIL_SAUL(0x7506, 22, 43, 8, 43, 0), PSIL_SAUL(0x7507, 23, 43, 8, 44, 0), - /* PDMA_MAIN0 - SPI0-3 */ + /* PDMA_MAIN0 - SPI0-2 */ + PSIL_PDMA_XY_PKT(0x4300), + PSIL_PDMA_XY_PKT(0x4301), PSIL_PDMA_XY_PKT(0x4302), PSIL_PDMA_XY_PKT(0x4303), PSIL_PDMA_XY_PKT(0x4304), @@ -95,8 +97,6 @@ static struct psil_ep am62a_src_ep_map[] = { PSIL_PDMA_XY_PKT(0x4309), PSIL_PDMA_XY_PKT(0x430a), PSIL_PDMA_XY_PKT(0x430b), - PSIL_PDMA_XY_PKT(0x430c), - PSIL_PDMA_XY_PKT(0x430d), /* PDMA_MAIN1 - UART0-6 */ PSIL_PDMA_XY_PKT(0x4400), PSIL_PDMA_XY_PKT(0x4401), @@ -151,7 +151,9 @@ static struct psil_ep am62a_dst_ep_map[] = { /* SAUL */ PSIL_SAUL(0xf500, 27, 83, 8, 83, 1), PSIL_SAUL(0xf501, 28, 91, 8, 91, 1), - /* PDMA_MAIN0 - SPI0-3 */ + /* PDMA_MAIN0 - SPI0-2 */ + PSIL_PDMA_XY_PKT(0xc300), + PSIL_PDMA_XY_PKT(0xc301), PSIL_PDMA_XY_PKT(0xc302), PSIL_PDMA_XY_PKT(0xc303), PSIL_PDMA_XY_PKT(0xc304), @@ -162,8 +164,6 @@ static struct psil_ep am62a_dst_ep_map[] = { PSIL_PDMA_XY_PKT(0xc309), PSIL_PDMA_XY_PKT(0xc30a), PSIL_PDMA_XY_PKT(0xc30b), - PSIL_PDMA_XY_PKT(0xc30c), - PSIL_PDMA_XY_PKT(0xc30d), /* PDMA_MAIN1 - UART0-6 */ PSIL_PDMA_XY_PKT(0xc400), PSIL_PDMA_XY_PKT(0xc401), diff --git a/drivers/dpll/dpll_netlink.c b/drivers/dpll/dpll_netlink.c index 442a0ebeb953..ce7cf736f020 100644 --- a/drivers/dpll/dpll_netlink.c +++ b/drivers/dpll/dpll_netlink.c @@ -925,7 +925,6 @@ dpll_pin_parent_pin_set(struct dpll_pin *pin, struct nlattr *parent_nest, struct netlink_ext_ack *extack) { struct nlattr *tb[DPLL_A_PIN_MAX + 1]; - enum dpll_pin_state state; u32 ppin_idx; int ret; @@ -936,10 +935,14 @@ dpll_pin_parent_pin_set(struct dpll_pin *pin, struct nlattr *parent_nest, return -EINVAL; } ppin_idx = nla_get_u32(tb[DPLL_A_PIN_PARENT_ID]); - state = nla_get_u32(tb[DPLL_A_PIN_STATE]); - ret = dpll_pin_on_pin_state_set(pin, ppin_idx, state, extack); - if (ret) - return ret; + + if (tb[DPLL_A_PIN_STATE]) { + enum dpll_pin_state state = nla_get_u32(tb[DPLL_A_PIN_STATE]); + + ret = dpll_pin_on_pin_state_set(pin, ppin_idx, state, extack); + if (ret) + return ret; + } return 0; } diff --git a/drivers/edac/altera_edac.c b/drivers/edac/altera_edac.c index 8b31cd54bdb6..ae17ce4d9722 100644 --- a/drivers/edac/altera_edac.c +++ b/drivers/edac/altera_edac.c @@ -22,6 +22,7 @@ #include <linux/of_platform.h> #include <linux/panic_notifier.h> #include <linux/platform_device.h> +#include <linux/property.h> #include <linux/regmap.h> #include <linux/types.h> #include <linux/uaccess.h> @@ -279,7 +280,6 @@ release: static int altr_sdram_probe(struct platform_device *pdev) { - const struct of_device_id *id; struct edac_mc_layer layers[2]; struct mem_ctl_info *mci; struct altr_sdram_mc_data *drvdata; @@ -290,10 +290,6 @@ static int altr_sdram_probe(struct platform_device *pdev) int irq, irq2, res = 0; unsigned long mem_size, irqflags = 0; - id = of_match_device(altr_sdram_ctrl_of_match, &pdev->dev); - if (!id) - return -ENODEV; - /* Grab the register range from the sdr controller in device tree */ mc_vbase = syscon_regmap_lookup_by_phandle(pdev->dev.of_node, "altr,sdr-syscon"); @@ -304,8 +300,7 @@ static int altr_sdram_probe(struct platform_device *pdev) } /* Check specific dependencies for the module */ - priv = of_match_node(altr_sdram_ctrl_of_match, - pdev->dev.of_node)->data; + priv = device_get_match_data(&pdev->dev); /* Validate the SDRAM controller has ECC enabled */ if (regmap_read(mc_vbase, priv->ecc_ctrl_offset, &read_reg) || @@ -459,15 +454,13 @@ free: return res; } -static int altr_sdram_remove(struct platform_device *pdev) +static void altr_sdram_remove(struct platform_device *pdev) { struct mem_ctl_info *mci = platform_get_drvdata(pdev); edac_mc_del_mc(&pdev->dev); edac_mc_free(mci); platform_set_drvdata(pdev, NULL); - - return 0; } /* @@ -489,7 +482,7 @@ static const struct dev_pm_ops altr_sdram_pm_ops = { static struct platform_driver altr_sdram_edac_driver = { .probe = altr_sdram_probe, - .remove = altr_sdram_remove, + .remove_new = altr_sdram_remove, .driver = { .name = "altr_sdram_edac", #ifdef CONFIG_PM @@ -812,7 +805,7 @@ fail: return res; } -static int altr_edac_device_remove(struct platform_device *pdev) +static void altr_edac_device_remove(struct platform_device *pdev) { struct edac_device_ctl_info *dci = platform_get_drvdata(pdev); struct altr_edac_device_dev *drvdata = dci->pvt_info; @@ -820,13 +813,11 @@ static int altr_edac_device_remove(struct platform_device *pdev) debugfs_remove_recursive(drvdata->debugfs_dir); edac_device_del_device(&pdev->dev); edac_device_free_ctl_info(dci); - - return 0; } static struct platform_driver altr_edac_device_driver = { .probe = altr_edac_device_probe, - .remove = altr_edac_device_remove, + .remove_new = altr_edac_device_remove, .driver = { .name = "altr_edac_device", .of_match_table = altr_edac_device_of_match, diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index 9b6642d00871..537b9987a431 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -996,15 +996,23 @@ static struct local_node_map { #define LNTM_NODE_COUNT GENMASK(27, 16) #define LNTM_BASE_NODE_ID GENMASK(11, 0) -static int gpu_get_node_map(void) +static int gpu_get_node_map(struct amd64_pvt *pvt) { struct pci_dev *pdev; int ret; u32 tmp; /* - * Node ID 0 is reserved for CPUs. - * Therefore, a non-zero Node ID means we've already cached the values. + * Mapping of nodes from hardware-provided AMD Node ID to a + * Linux logical one is applicable for MI200 models. Therefore, + * return early for other heterogeneous systems. + */ + if (pvt->F3->device != PCI_DEVICE_ID_AMD_MI200_DF_F3) + return 0; + + /* + * Node ID 0 is reserved for CPUs. Therefore, a non-zero Node ID + * means the values have been already cached. */ if (gpu_node_map.base_node_id) return 0; @@ -3851,7 +3859,7 @@ static void gpu_init_csrows(struct mem_ctl_info *mci) dimm->nr_pages = gpu_get_csrow_nr_pages(pvt, umc, cs); dimm->edac_mode = EDAC_SECDED; - dimm->mtype = MEM_HBM2; + dimm->mtype = pvt->dram_type; dimm->dtype = DEV_X16; dimm->grain = 64; } @@ -3880,7 +3888,7 @@ static bool gpu_ecc_enabled(struct amd64_pvt *pvt) return true; } -static inline u32 gpu_get_umc_base(u8 umc, u8 channel) +static inline u32 gpu_get_umc_base(struct amd64_pvt *pvt, u8 umc, u8 channel) { /* * On CPUs, there is one channel per UMC, so UMC numbering equals @@ -3893,13 +3901,16 @@ static inline u32 gpu_get_umc_base(u8 umc, u8 channel) * On GPU nodes channels are selected in 3rd nibble * HBM chX[3:0]= [Y ]5X[3:0]000; * HBM chX[7:4]= [Y+1]5X[3:0]000 + * + * On MI300 APU nodes, same as GPU nodes but channels are selected + * in the base address of 0x90000 */ umc *= 2; if (channel >= 4) umc++; - return 0x50000 + (umc << 20) + ((channel % 4) << 12); + return pvt->gpu_umc_base + (umc << 20) + ((channel % 4) << 12); } static void gpu_read_mc_regs(struct amd64_pvt *pvt) @@ -3910,7 +3921,7 @@ static void gpu_read_mc_regs(struct amd64_pvt *pvt) /* Read registers from each UMC */ for_each_umc(i) { - umc_base = gpu_get_umc_base(i, 0); + umc_base = gpu_get_umc_base(pvt, i, 0); umc = &pvt->umc[i]; amd_smn_read(nid, umc_base + UMCCH_UMC_CFG, &umc->umc_cfg); @@ -3927,7 +3938,7 @@ static void gpu_read_base_mask(struct amd64_pvt *pvt) for_each_umc(umc) { for_each_chip_select(cs, umc, pvt) { - base_reg = gpu_get_umc_base(umc, cs) + UMCCH_BASE_ADDR; + base_reg = gpu_get_umc_base(pvt, umc, cs) + UMCCH_BASE_ADDR; base = &pvt->csels[umc].csbases[cs]; if (!amd_smn_read(pvt->mc_node_id, base_reg, base)) { @@ -3935,7 +3946,7 @@ static void gpu_read_base_mask(struct amd64_pvt *pvt) umc, cs, *base, base_reg); } - mask_reg = gpu_get_umc_base(umc, cs) + UMCCH_ADDR_MASK; + mask_reg = gpu_get_umc_base(pvt, umc, cs) + UMCCH_ADDR_MASK; mask = &pvt->csels[umc].csmasks[cs]; if (!amd_smn_read(pvt->mc_node_id, mask_reg, mask)) { @@ -3960,7 +3971,7 @@ static int gpu_hw_info_get(struct amd64_pvt *pvt) { int ret; - ret = gpu_get_node_map(); + ret = gpu_get_node_map(pvt); if (ret) return ret; @@ -4125,6 +4136,8 @@ static int per_family_init(struct amd64_pvt *pvt) if (pvt->F3->device == PCI_DEVICE_ID_AMD_MI200_DF_F3) { pvt->ctl_name = "MI200"; pvt->max_mcs = 4; + pvt->dram_type = MEM_HBM2; + pvt->gpu_umc_base = 0x50000; pvt->ops = &gpu_ops; } else { pvt->ctl_name = "F19h_M30h"; @@ -4142,6 +4155,13 @@ static int per_family_init(struct amd64_pvt *pvt) pvt->ctl_name = "F19h_M70h"; pvt->flags.zn_regs_v2 = 1; break; + case 0x90 ... 0x9f: + pvt->ctl_name = "F19h_M90h"; + pvt->max_mcs = 4; + pvt->dram_type = MEM_HBM3; + pvt->gpu_umc_base = 0x90000; + pvt->ops = &gpu_ops; + break; case 0xa0 ... 0xaf: pvt->ctl_name = "F19h_MA0h"; pvt->max_mcs = 12; @@ -4180,23 +4200,33 @@ static const struct attribute_group *amd64_edac_attr_groups[] = { NULL }; +/* + * For heterogeneous and APU models EDAC CHIP_SELECT and CHANNEL layers + * should be swapped to fit into the layers. + */ +static unsigned int get_layer_size(struct amd64_pvt *pvt, u8 layer) +{ + bool is_gpu = (pvt->ops == &gpu_ops); + + if (!layer) + return is_gpu ? pvt->max_mcs + : pvt->csels[0].b_cnt; + else + return is_gpu ? pvt->csels[0].b_cnt + : pvt->max_mcs; +} + static int init_one_instance(struct amd64_pvt *pvt) { struct mem_ctl_info *mci = NULL; struct edac_mc_layer layers[2]; int ret = -ENOMEM; - /* - * For Heterogeneous family EDAC CHIP_SELECT and CHANNEL layers should - * be swapped to fit into the layers. - */ layers[0].type = EDAC_MC_LAYER_CHIP_SELECT; - layers[0].size = (pvt->F3->device == PCI_DEVICE_ID_AMD_MI200_DF_F3) ? - pvt->max_mcs : pvt->csels[0].b_cnt; + layers[0].size = get_layer_size(pvt, 0); layers[0].is_virt_csrow = true; layers[1].type = EDAC_MC_LAYER_CHANNEL; - layers[1].size = (pvt->F3->device == PCI_DEVICE_ID_AMD_MI200_DF_F3) ? - pvt->csels[0].b_cnt : pvt->max_mcs; + layers[1].size = get_layer_size(pvt, 1); layers[1].is_virt_csrow = false; mci = edac_mc_alloc(pvt->mc_node_id, ARRAY_SIZE(layers), layers, 0); diff --git a/drivers/edac/amd64_edac.h b/drivers/edac/amd64_edac.h index 5a4e4a59682b..1665f7932bac 100644 --- a/drivers/edac/amd64_edac.h +++ b/drivers/edac/amd64_edac.h @@ -362,6 +362,7 @@ struct amd64_pvt { u32 dct_sel_lo; /* DRAM Controller Select Low */ u32 dct_sel_hi; /* DRAM Controller Select High */ u32 online_spare; /* On-Line spare Reg */ + u32 gpu_umc_base; /* Base address used for channel selection on GPUs */ /* x4, x8, or x16 syndromes in use */ u8 ecc_sym_sz; diff --git a/drivers/edac/armada_xp_edac.c b/drivers/edac/armada_xp_edac.c index c4bd2fb9c46b..25517c99b3ea 100644 --- a/drivers/edac/armada_xp_edac.c +++ b/drivers/edac/armada_xp_edac.c @@ -5,7 +5,9 @@ #include <linux/kernel.h> #include <linux/edac.h> -#include <linux/of_platform.h> +#include <linux/of.h> +#include <linux/of_device.h> +#include <linux/platform_device.h> #include <asm/hardware/cache-l2x0.h> #include <asm/hardware/cache-aurora-l2.h> @@ -351,20 +353,18 @@ static int axp_mc_probe(struct platform_device *pdev) return 0; } -static int axp_mc_remove(struct platform_device *pdev) +static void axp_mc_remove(struct platform_device *pdev) { struct mem_ctl_info *mci = platform_get_drvdata(pdev); edac_mc_del_mc(&pdev->dev); edac_mc_free(mci); platform_set_drvdata(pdev, NULL); - - return 0; } static struct platform_driver axp_mc_driver = { .probe = axp_mc_probe, - .remove = axp_mc_remove, + .remove_new = axp_mc_remove, .driver = { .name = "armada_xp_mc_edac", .of_match_table = of_match_ptr(axp_mc_of_match), @@ -564,7 +564,7 @@ static int aurora_l2_probe(struct platform_device *pdev) return 0; } -static int aurora_l2_remove(struct platform_device *pdev) +static void aurora_l2_remove(struct platform_device *pdev) { struct edac_device_ctl_info *dci = platform_get_drvdata(pdev); #ifdef CONFIG_EDAC_DEBUG @@ -575,13 +575,11 @@ static int aurora_l2_remove(struct platform_device *pdev) edac_device_del_device(&pdev->dev); edac_device_free_ctl_info(dci); platform_set_drvdata(pdev, NULL); - - return 0; } static struct platform_driver aurora_l2_driver = { .probe = aurora_l2_probe, - .remove = aurora_l2_remove, + .remove_new = aurora_l2_remove, .driver = { .name = "aurora_l2_edac", .of_match_table = of_match_ptr(aurora_l2_of_match), diff --git a/drivers/edac/aspeed_edac.c b/drivers/edac/aspeed_edac.c index 6bd5f8815919..157a480eb761 100644 --- a/drivers/edac/aspeed_edac.c +++ b/drivers/edac/aspeed_edac.c @@ -357,7 +357,7 @@ probe_exit02: } -static int aspeed_remove(struct platform_device *pdev) +static void aspeed_remove(struct platform_device *pdev) { struct mem_ctl_info *mci; @@ -369,8 +369,6 @@ static int aspeed_remove(struct platform_device *pdev) mci = edac_mc_del_mc(&pdev->dev); if (mci) edac_mc_free(mci); - - return 0; } @@ -389,7 +387,7 @@ static struct platform_driver aspeed_driver = { .of_match_table = aspeed_of_match }, .probe = aspeed_probe, - .remove = aspeed_remove + .remove_new = aspeed_remove }; module_platform_driver(aspeed_driver); diff --git a/drivers/edac/bluefield_edac.c b/drivers/edac/bluefield_edac.c index e4736eb37bfb..5b3164560648 100644 --- a/drivers/edac/bluefield_edac.c +++ b/drivers/edac/bluefield_edac.c @@ -323,14 +323,12 @@ err: } -static int bluefield_edac_mc_remove(struct platform_device *pdev) +static void bluefield_edac_mc_remove(struct platform_device *pdev) { struct mem_ctl_info *mci = platform_get_drvdata(pdev); edac_mc_del_mc(&pdev->dev); edac_mc_free(mci); - - return 0; } static const struct acpi_device_id bluefield_mc_acpi_ids[] = { @@ -346,7 +344,7 @@ static struct platform_driver bluefield_edac_mc_driver = { .acpi_match_table = bluefield_mc_acpi_ids, }, .probe = bluefield_edac_mc_probe, - .remove = bluefield_edac_mc_remove, + .remove_new = bluefield_edac_mc_remove, }; module_platform_driver(bluefield_edac_mc_driver); diff --git a/drivers/edac/cell_edac.c b/drivers/edac/cell_edac.c index bc1f3416400e..2000f66fbf5c 100644 --- a/drivers/edac/cell_edac.c +++ b/drivers/edac/cell_edac.c @@ -234,12 +234,11 @@ static int cell_edac_probe(struct platform_device *pdev) return 0; } -static int cell_edac_remove(struct platform_device *pdev) +static void cell_edac_remove(struct platform_device *pdev) { struct mem_ctl_info *mci = edac_mc_del_mc(&pdev->dev); if (mci) edac_mc_free(mci); - return 0; } static struct platform_driver cell_edac_driver = { @@ -247,7 +246,7 @@ static struct platform_driver cell_edac_driver = { .name = "cbe-mic", }, .probe = cell_edac_probe, - .remove = cell_edac_remove, + .remove_new = cell_edac_remove, }; static int __init cell_edac_init(void) diff --git a/drivers/edac/cpc925_edac.c b/drivers/edac/cpc925_edac.c index 9797e6d60dde..5075dc7526e3 100644 --- a/drivers/edac/cpc925_edac.c +++ b/drivers/edac/cpc925_edac.c @@ -1010,7 +1010,7 @@ out: return res; } -static int cpc925_remove(struct platform_device *pdev) +static void cpc925_remove(struct platform_device *pdev) { struct mem_ctl_info *mci = platform_get_drvdata(pdev); @@ -1023,13 +1023,11 @@ static int cpc925_remove(struct platform_device *pdev) edac_mc_del_mc(&pdev->dev); edac_mc_free(mci); - - return 0; } static struct platform_driver cpc925_edac_driver = { .probe = cpc925_probe, - .remove = cpc925_remove, + .remove_new = cpc925_remove, .driver = { .name = "cpc925_edac", } diff --git a/drivers/edac/dmc520_edac.c b/drivers/edac/dmc520_edac.c index 1fa5ca57e9ec..4e30b989a1a4 100644 --- a/drivers/edac/dmc520_edac.c +++ b/drivers/edac/dmc520_edac.c @@ -602,7 +602,7 @@ err: return ret; } -static int dmc520_edac_remove(struct platform_device *pdev) +static void dmc520_edac_remove(struct platform_device *pdev) { u32 reg_val, idx, irq_mask_all = 0; struct mem_ctl_info *mci; @@ -626,8 +626,6 @@ static int dmc520_edac_remove(struct platform_device *pdev) edac_mc_del_mc(&pdev->dev); edac_mc_free(mci); - - return 0; } static const struct of_device_id dmc520_edac_driver_id[] = { @@ -644,7 +642,7 @@ static struct platform_driver dmc520_edac_driver = { }, .probe = dmc520_edac_probe, - .remove = dmc520_edac_remove + .remove_new = dmc520_edac_remove }; module_platform_driver(dmc520_edac_driver); diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c index 6faeb2ab3960..d6eed727b0cd 100644 --- a/drivers/edac/edac_mc.c +++ b/drivers/edac/edac_mc.c @@ -166,6 +166,7 @@ const char * const edac_mem_types[] = { [MEM_NVDIMM] = "Non-volatile-RAM", [MEM_WIO2] = "Wide-IO-2", [MEM_HBM2] = "High-bandwidth-memory-Gen2", + [MEM_HBM3] = "High-bandwidth-memory-Gen3", }; EXPORT_SYMBOL_GPL(edac_mem_types); diff --git a/drivers/edac/edac_pci_sysfs.c b/drivers/edac/edac_pci_sysfs.c index 287cc51dbc86..901d4cd3ca38 100644 --- a/drivers/edac/edac_pci_sysfs.c +++ b/drivers/edac/edac_pci_sysfs.c @@ -521,7 +521,7 @@ static void edac_pci_dev_parity_clear(struct pci_dev *dev) /* read the device TYPE, looking for bridges */ pci_read_config_byte(dev, PCI_HEADER_TYPE, &header_type); - if ((header_type & 0x7F) == PCI_HEADER_TYPE_BRIDGE) + if ((header_type & PCI_HEADER_TYPE_MASK) == PCI_HEADER_TYPE_BRIDGE) get_pci_parity_status(dev, 1); } @@ -583,7 +583,7 @@ static void edac_pci_dev_parity_test(struct pci_dev *dev) edac_dbg(4, "PCI HEADER TYPE= 0x%02x %s\n", header_type, dev_name(&dev->dev)); - if ((header_type & 0x7F) == PCI_HEADER_TYPE_BRIDGE) { + if ((header_type & PCI_HEADER_TYPE_MASK) == PCI_HEADER_TYPE_BRIDGE) { /* On bridges, need to examine secondary status register */ status = get_pci_parity_status(dev, 1); diff --git a/drivers/edac/fsl_ddr_edac.c b/drivers/edac/fsl_ddr_edac.c index b81757555a8a..d148d262d0d4 100644 --- a/drivers/edac/fsl_ddr_edac.c +++ b/drivers/edac/fsl_ddr_edac.c @@ -612,7 +612,7 @@ err: return res; } -int fsl_mc_err_remove(struct platform_device *op) +void fsl_mc_err_remove(struct platform_device *op) { struct mem_ctl_info *mci = dev_get_drvdata(&op->dev); struct fsl_mc_pdata *pdata = mci->pvt_info; @@ -629,5 +629,4 @@ int fsl_mc_err_remove(struct platform_device *op) edac_mc_del_mc(&op->dev); edac_mc_free(mci); - return 0; } diff --git a/drivers/edac/fsl_ddr_edac.h b/drivers/edac/fsl_ddr_edac.h index 332439d7b2d9..c0994a2a003c 100644 --- a/drivers/edac/fsl_ddr_edac.h +++ b/drivers/edac/fsl_ddr_edac.h @@ -72,5 +72,5 @@ struct fsl_mc_pdata { int irq; }; int fsl_mc_err_probe(struct platform_device *op); -int fsl_mc_err_remove(struct platform_device *op); +void fsl_mc_err_remove(struct platform_device *op); #endif diff --git a/drivers/edac/highbank_l2_edac.c b/drivers/edac/highbank_l2_edac.c index 140d4431bd0d..5646c049a934 100644 --- a/drivers/edac/highbank_l2_edac.c +++ b/drivers/edac/highbank_l2_edac.c @@ -118,18 +118,17 @@ err: return res; } -static int highbank_l2_err_remove(struct platform_device *pdev) +static void highbank_l2_err_remove(struct platform_device *pdev) { struct edac_device_ctl_info *dci = platform_get_drvdata(pdev); edac_device_del_device(&pdev->dev); edac_device_free_ctl_info(dci); - return 0; } static struct platform_driver highbank_l2_edac_driver = { .probe = highbank_l2_err_probe, - .remove = highbank_l2_err_remove, + .remove_new = highbank_l2_err_remove, .driver = { .name = "hb_l2_edac", .of_match_table = hb_l2_err_of_match, diff --git a/drivers/edac/highbank_mc_edac.c b/drivers/edac/highbank_mc_edac.c index a0c04a7f95e9..1c5b888ab11d 100644 --- a/drivers/edac/highbank_mc_edac.c +++ b/drivers/edac/highbank_mc_edac.c @@ -251,18 +251,17 @@ free: return res; } -static int highbank_mc_remove(struct platform_device *pdev) +static void highbank_mc_remove(struct platform_device *pdev) { struct mem_ctl_info *mci = platform_get_drvdata(pdev); edac_mc_del_mc(&pdev->dev); edac_mc_free(mci); - return 0; } static struct platform_driver highbank_mc_edac_driver = { .probe = highbank_mc_probe, - .remove = highbank_mc_remove, + .remove_new = highbank_mc_remove, .driver = { .name = "hb_mc_edac", .of_match_table = hb_ddr_ctrl_of_match, diff --git a/drivers/edac/i7core_edac.c b/drivers/edac/i7core_edac.c index 23d25724bae4..91e0a88ef904 100644 --- a/drivers/edac/i7core_edac.c +++ b/drivers/edac/i7core_edac.c @@ -376,7 +376,7 @@ static const struct pci_id_table pci_dev_table[] = { PCI_ID_TABLE_ENTRY(pci_dev_descr_i7core_nehalem), PCI_ID_TABLE_ENTRY(pci_dev_descr_lynnfield), PCI_ID_TABLE_ENTRY(pci_dev_descr_i7core_westmere), - {0,} /* 0 terminated list. */ + { NULL, } }; /* @@ -385,7 +385,7 @@ static const struct pci_id_table pci_dev_table[] = { static const struct pci_device_id i7core_pci_tbl[] = { {PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_X58_HUB_MGMT)}, {PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_LYNNFIELD_QPI_LINK0)}, - {0,} /* 0 terminated list. */ + { 0, } }; /**************************************************************************** diff --git a/drivers/edac/igen6_edac.c b/drivers/edac/igen6_edac.c index 1a18693294db..2b0ecdeba5cd 100644 --- a/drivers/edac/igen6_edac.c +++ b/drivers/edac/igen6_edac.c @@ -58,6 +58,7 @@ /* Capability register E */ #define CAPID_E_OFFSET 0xf0 #define CAPID_E_IBECC BIT(12) +#define CAPID_E_IBECC_BIT18 BIT(18) /* Error Status */ #define ERRSTS_OFFSET 0xc8 @@ -80,6 +81,7 @@ #define ECC_ERROR_LOG_UE BIT_ULL(63) #define ECC_ERROR_LOG_ADDR_SHIFT 5 #define ECC_ERROR_LOG_ADDR(v) GET_BITFIELD(v, 5, 38) +#define ECC_ERROR_LOG_ADDR45(v) GET_BITFIELD(v, 5, 45) #define ECC_ERROR_LOG_SYND(v) GET_BITFIELD(v, 46, 61) /* Host MMIO base address */ @@ -133,6 +135,8 @@ static struct res_config { u32 ibecc_base; u32 ibecc_error_log_offset; bool (*ibecc_available)(struct pci_dev *pdev); + /* Extract error address logged in IBECC */ + u64 (*err_addr)(u64 ecclog); /* Convert error address logged in IBECC to system physical address */ u64 (*err_addr_to_sys_addr)(u64 eaddr, int mc); /* Convert error address logged in IBECC to integrated memory controller address */ @@ -222,6 +226,67 @@ static struct work_struct ecclog_work; #define DID_ADL_SKU3 0x4621 #define DID_ADL_SKU4 0x4641 +/* Compute die IDs for Alder Lake-N with IBECC */ +#define DID_ADL_N_SKU1 0x4614 +#define DID_ADL_N_SKU2 0x4617 +#define DID_ADL_N_SKU3 0x461b +#define DID_ADL_N_SKU4 0x461c +#define DID_ADL_N_SKU5 0x4673 +#define DID_ADL_N_SKU6 0x4674 +#define DID_ADL_N_SKU7 0x4675 +#define DID_ADL_N_SKU8 0x4677 +#define DID_ADL_N_SKU9 0x4678 +#define DID_ADL_N_SKU10 0x4679 +#define DID_ADL_N_SKU11 0x467c + +/* Compute die IDs for Raptor Lake-P with IBECC */ +#define DID_RPL_P_SKU1 0xa706 +#define DID_RPL_P_SKU2 0xa707 +#define DID_RPL_P_SKU3 0xa708 +#define DID_RPL_P_SKU4 0xa716 +#define DID_RPL_P_SKU5 0xa718 + +/* Compute die IDs for Meteor Lake-PS with IBECC */ +#define DID_MTL_PS_SKU1 0x7d21 +#define DID_MTL_PS_SKU2 0x7d22 +#define DID_MTL_PS_SKU3 0x7d23 +#define DID_MTL_PS_SKU4 0x7d24 + +/* Compute die IDs for Meteor Lake-P with IBECC */ +#define DID_MTL_P_SKU1 0x7d01 +#define DID_MTL_P_SKU2 0x7d02 +#define DID_MTL_P_SKU3 0x7d14 + +static int get_mchbar(struct pci_dev *pdev, u64 *mchbar) +{ + union { + u64 v; + struct { + u32 v_lo; + u32 v_hi; + }; + } u; + + if (pci_read_config_dword(pdev, MCHBAR_OFFSET, &u.v_lo)) { + igen6_printk(KERN_ERR, "Failed to read lower MCHBAR\n"); + return -ENODEV; + } + + if (pci_read_config_dword(pdev, MCHBAR_OFFSET + 4, &u.v_hi)) { + igen6_printk(KERN_ERR, "Failed to read upper MCHBAR\n"); + return -ENODEV; + } + + if (!(u.v & MCHBAR_EN)) { + igen6_printk(KERN_ERR, "MCHBAR is disabled\n"); + return -ENODEV; + } + + *mchbar = MCHBAR_BASE(u.v); + + return 0; +} + static bool ehl_ibecc_available(struct pci_dev *pdev) { u32 v; @@ -272,6 +337,39 @@ static bool tgl_ibecc_available(struct pci_dev *pdev) return !(CAPID_E_IBECC & v); } +static bool mtl_p_ibecc_available(struct pci_dev *pdev) +{ + u32 v; + + if (pci_read_config_dword(pdev, CAPID_E_OFFSET, &v)) + return false; + + return !(CAPID_E_IBECC_BIT18 & v); +} + +static bool mtl_ps_ibecc_available(struct pci_dev *pdev) +{ +#define MCHBAR_MEMSS_IBECCDIS 0x13c00 + void __iomem *window; + u64 mchbar; + u32 val; + + if (get_mchbar(pdev, &mchbar)) + return false; + + window = ioremap(mchbar, MCHBAR_SIZE * 2); + if (!window) { + igen6_printk(KERN_ERR, "Failed to ioremap 0x%llx\n", mchbar); + return false; + } + + val = readl(window + MCHBAR_MEMSS_IBECCDIS); + iounmap(window); + + /* Bit6: 1 - IBECC is disabled, 0 - IBECC isn't disabled */ + return !GET_BITFIELD(val, 6, 6); +} + static u64 mem_addr_to_sys_addr(u64 maddr) { if (maddr < igen6_tolud) @@ -358,6 +456,11 @@ static u64 adl_err_addr_to_imc_addr(u64 eaddr, int mc) return imc_addr; } +static u64 rpl_p_err_addr(u64 ecclog) +{ + return ECC_ERROR_LOG_ADDR45(ecclog); +} + static struct res_config ehl_cfg = { .num_imc = 1, .imc_base = 0x5000, @@ -403,6 +506,51 @@ static struct res_config adl_cfg = { .err_addr_to_imc_addr = adl_err_addr_to_imc_addr, }; +static struct res_config adl_n_cfg = { + .machine_check = true, + .num_imc = 1, + .imc_base = 0xd800, + .ibecc_base = 0xd400, + .ibecc_error_log_offset = 0x68, + .ibecc_available = tgl_ibecc_available, + .err_addr_to_sys_addr = adl_err_addr_to_sys_addr, + .err_addr_to_imc_addr = adl_err_addr_to_imc_addr, +}; + +static struct res_config rpl_p_cfg = { + .machine_check = true, + .num_imc = 2, + .imc_base = 0xd800, + .ibecc_base = 0xd400, + .ibecc_error_log_offset = 0x68, + .ibecc_available = tgl_ibecc_available, + .err_addr = rpl_p_err_addr, + .err_addr_to_sys_addr = adl_err_addr_to_sys_addr, + .err_addr_to_imc_addr = adl_err_addr_to_imc_addr, +}; + +static struct res_config mtl_ps_cfg = { + .machine_check = true, + .num_imc = 2, + .imc_base = 0xd800, + .ibecc_base = 0xd400, + .ibecc_error_log_offset = 0x170, + .ibecc_available = mtl_ps_ibecc_available, + .err_addr_to_sys_addr = adl_err_addr_to_sys_addr, + .err_addr_to_imc_addr = adl_err_addr_to_imc_addr, +}; + +static struct res_config mtl_p_cfg = { + .machine_check = true, + .num_imc = 2, + .imc_base = 0xd800, + .ibecc_base = 0xd400, + .ibecc_error_log_offset = 0x170, + .ibecc_available = mtl_p_ibecc_available, + .err_addr_to_sys_addr = adl_err_addr_to_sys_addr, + .err_addr_to_imc_addr = adl_err_addr_to_imc_addr, +}; + static const struct pci_device_id igen6_pci_tbl[] = { { PCI_VDEVICE(INTEL, DID_EHL_SKU5), (kernel_ulong_t)&ehl_cfg }, { PCI_VDEVICE(INTEL, DID_EHL_SKU6), (kernel_ulong_t)&ehl_cfg }, @@ -424,6 +572,29 @@ static const struct pci_device_id igen6_pci_tbl[] = { { PCI_VDEVICE(INTEL, DID_ADL_SKU2), (kernel_ulong_t)&adl_cfg }, { PCI_VDEVICE(INTEL, DID_ADL_SKU3), (kernel_ulong_t)&adl_cfg }, { PCI_VDEVICE(INTEL, DID_ADL_SKU4), (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU1), (kernel_ulong_t)&adl_n_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU2), (kernel_ulong_t)&adl_n_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU3), (kernel_ulong_t)&adl_n_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU4), (kernel_ulong_t)&adl_n_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU5), (kernel_ulong_t)&adl_n_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU6), (kernel_ulong_t)&adl_n_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU7), (kernel_ulong_t)&adl_n_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU8), (kernel_ulong_t)&adl_n_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU9), (kernel_ulong_t)&adl_n_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU10), (kernel_ulong_t)&adl_n_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU11), (kernel_ulong_t)&adl_n_cfg }, + { PCI_VDEVICE(INTEL, DID_RPL_P_SKU1), (kernel_ulong_t)&rpl_p_cfg }, + { PCI_VDEVICE(INTEL, DID_RPL_P_SKU2), (kernel_ulong_t)&rpl_p_cfg }, + { PCI_VDEVICE(INTEL, DID_RPL_P_SKU3), (kernel_ulong_t)&rpl_p_cfg }, + { PCI_VDEVICE(INTEL, DID_RPL_P_SKU4), (kernel_ulong_t)&rpl_p_cfg }, + { PCI_VDEVICE(INTEL, DID_RPL_P_SKU5), (kernel_ulong_t)&rpl_p_cfg }, + { PCI_VDEVICE(INTEL, DID_MTL_PS_SKU1), (kernel_ulong_t)&mtl_ps_cfg }, + { PCI_VDEVICE(INTEL, DID_MTL_PS_SKU2), (kernel_ulong_t)&mtl_ps_cfg }, + { PCI_VDEVICE(INTEL, DID_MTL_PS_SKU3), (kernel_ulong_t)&mtl_ps_cfg }, + { PCI_VDEVICE(INTEL, DID_MTL_PS_SKU4), (kernel_ulong_t)&mtl_ps_cfg }, + { PCI_VDEVICE(INTEL, DID_MTL_P_SKU1), (kernel_ulong_t)&mtl_p_cfg }, + { PCI_VDEVICE(INTEL, DID_MTL_P_SKU2), (kernel_ulong_t)&mtl_p_cfg }, + { PCI_VDEVICE(INTEL, DID_MTL_P_SKU3), (kernel_ulong_t)&mtl_p_cfg }, { }, }; MODULE_DEVICE_TABLE(pci, igen6_pci_tbl); @@ -679,8 +850,11 @@ static void ecclog_work_cb(struct work_struct *work) llist_for_each_entry_safe(node, tmp, head, llnode) { memset(&res, 0, sizeof(res)); - eaddr = ECC_ERROR_LOG_ADDR(node->ecclog) << - ECC_ERROR_LOG_ADDR_SHIFT; + if (res_cfg->err_addr) + eaddr = res_cfg->err_addr(node->ecclog); + else + eaddr = ECC_ERROR_LOG_ADDR(node->ecclog) << + ECC_ERROR_LOG_ADDR_SHIFT; res.mc = node->mc; res.sys_addr = res_cfg->err_addr_to_sys_addr(eaddr, res.mc); res.imc_addr = res_cfg->err_addr_to_imc_addr(eaddr, res.mc); @@ -969,22 +1143,8 @@ static int igen6_pci_setup(struct pci_dev *pdev, u64 *mchbar) igen6_tom = u.v & GENMASK_ULL(38, 20); - if (pci_read_config_dword(pdev, MCHBAR_OFFSET, &u.v_lo)) { - igen6_printk(KERN_ERR, "Failed to read lower MCHBAR\n"); + if (get_mchbar(pdev, mchbar)) goto fail; - } - - if (pci_read_config_dword(pdev, MCHBAR_OFFSET + 4, &u.v_hi)) { - igen6_printk(KERN_ERR, "Failed to read upper MCHBAR\n"); - goto fail; - } - - if (!(u.v & MCHBAR_EN)) { - igen6_printk(KERN_ERR, "MCHBAR is disabled\n"); - goto fail; - } - - *mchbar = MCHBAR_BASE(u.v); #ifdef CONFIG_EDAC_DEBUG if (pci_read_config_dword(pdev, TOUUD_OFFSET, &u.v_lo)) diff --git a/drivers/edac/layerscape_edac.c b/drivers/edac/layerscape_edac.c index 7c5e2b3c0daa..d2f895033280 100644 --- a/drivers/edac/layerscape_edac.c +++ b/drivers/edac/layerscape_edac.c @@ -27,7 +27,7 @@ MODULE_DEVICE_TABLE(of, fsl_ddr_mc_err_of_match); static struct platform_driver fsl_ddr_mc_err_driver = { .probe = fsl_mc_err_probe, - .remove = fsl_mc_err_remove, + .remove_new = fsl_mc_err_remove, .driver = { .name = "fsl_ddr_mc_err", .of_match_table = fsl_ddr_mc_err_of_match, diff --git a/drivers/edac/mpc85xx_edac.c b/drivers/edac/mpc85xx_edac.c index 2b5703e5066e..c1bc53f4e184 100644 --- a/drivers/edac/mpc85xx_edac.c +++ b/drivers/edac/mpc85xx_edac.c @@ -300,7 +300,7 @@ err: return res; } -static int mpc85xx_pci_err_remove(struct platform_device *op) +static void mpc85xx_pci_err_remove(struct platform_device *op) { struct edac_pci_ctl_info *pci = dev_get_drvdata(&op->dev); struct mpc85xx_pci_pdata *pdata = pci->pvt_info; @@ -312,8 +312,6 @@ static int mpc85xx_pci_err_remove(struct platform_device *op) edac_pci_del_device(&op->dev); edac_pci_free_ctl_info(pci); - - return 0; } static const struct platform_device_id mpc85xx_pci_err_match[] = { @@ -325,7 +323,7 @@ static const struct platform_device_id mpc85xx_pci_err_match[] = { static struct platform_driver mpc85xx_pci_err_driver = { .probe = mpc85xx_pci_err_probe, - .remove = mpc85xx_pci_err_remove, + .remove_new = mpc85xx_pci_err_remove, .id_table = mpc85xx_pci_err_match, .driver = { .name = "mpc85xx_pci_err", @@ -591,7 +589,7 @@ err: return res; } -static int mpc85xx_l2_err_remove(struct platform_device *op) +static void mpc85xx_l2_err_remove(struct platform_device *op) { struct edac_device_ctl_info *edac_dev = dev_get_drvdata(&op->dev); struct mpc85xx_l2_pdata *pdata = edac_dev->pvt_info; @@ -606,7 +604,6 @@ static int mpc85xx_l2_err_remove(struct platform_device *op) out_be32(pdata->l2_vbase + MPC85XX_L2_ERRDIS, orig_l2_err_disable); edac_device_del_device(&op->dev); edac_device_free_ctl_info(edac_dev); - return 0; } static const struct of_device_id mpc85xx_l2_err_of_match[] = { @@ -630,7 +627,7 @@ MODULE_DEVICE_TABLE(of, mpc85xx_l2_err_of_match); static struct platform_driver mpc85xx_l2_err_driver = { .probe = mpc85xx_l2_err_probe, - .remove = mpc85xx_l2_err_remove, + .remove_new = mpc85xx_l2_err_remove, .driver = { .name = "mpc85xx_l2_err", .of_match_table = mpc85xx_l2_err_of_match, @@ -659,7 +656,7 @@ MODULE_DEVICE_TABLE(of, mpc85xx_mc_err_of_match); static struct platform_driver mpc85xx_mc_err_driver = { .probe = fsl_mc_err_probe, - .remove = fsl_mc_err_remove, + .remove_new = fsl_mc_err_remove, .driver = { .name = "mpc85xx_mc_err", .of_match_table = mpc85xx_mc_err_of_match, diff --git a/drivers/edac/npcm_edac.c b/drivers/edac/npcm_edac.c index 6d15c1550263..2e2133b784e9 100644 --- a/drivers/edac/npcm_edac.c +++ b/drivers/edac/npcm_edac.c @@ -410,7 +410,7 @@ free_edac_mc: return rc; } -static int edac_remove(struct platform_device *pdev) +static void edac_remove(struct platform_device *pdev) { struct mem_ctl_info *mci = platform_get_drvdata(pdev); struct priv_data *priv = mci->pvt_info; @@ -426,8 +426,6 @@ static int edac_remove(struct platform_device *pdev) regmap_write(npcm_regmap, pdata->ctl_int_mask_master, pdata->int_mask_master_global_mask); regmap_update_bits(npcm_regmap, pdata->ctl_ecc_en, pdata->ecc_en_mask, 0); - - return 0; } static const struct npcm_platform_data npcm750_edac = { @@ -533,7 +531,7 @@ static struct platform_driver npcm_edac_driver = { .of_match_table = npcm_edac_of_match, }, .probe = edac_probe, - .remove = edac_remove, + .remove_new = edac_remove, }; module_platform_driver(npcm_edac_driver); diff --git a/drivers/edac/octeon_edac-l2c.c b/drivers/edac/octeon_edac-l2c.c index c33059e9b0be..4015eb9af6fe 100644 --- a/drivers/edac/octeon_edac-l2c.c +++ b/drivers/edac/octeon_edac-l2c.c @@ -184,19 +184,17 @@ err: return -ENXIO; } -static int octeon_l2c_remove(struct platform_device *pdev) +static void octeon_l2c_remove(struct platform_device *pdev) { struct edac_device_ctl_info *l2c = platform_get_drvdata(pdev); edac_device_del_device(&pdev->dev); edac_device_free_ctl_info(l2c); - - return 0; } static struct platform_driver octeon_l2c_driver = { .probe = octeon_l2c_probe, - .remove = octeon_l2c_remove, + .remove_new = octeon_l2c_remove, .driver = { .name = "octeon_l2c_edac", } diff --git a/drivers/edac/octeon_edac-lmc.c b/drivers/edac/octeon_edac-lmc.c index aeb222ca3ed1..18615cbcd9ea 100644 --- a/drivers/edac/octeon_edac-lmc.c +++ b/drivers/edac/octeon_edac-lmc.c @@ -302,18 +302,17 @@ static int octeon_lmc_edac_probe(struct platform_device *pdev) return 0; } -static int octeon_lmc_edac_remove(struct platform_device *pdev) +static void octeon_lmc_edac_remove(struct platform_device *pdev) { struct mem_ctl_info *mci = platform_get_drvdata(pdev); edac_mc_del_mc(&pdev->dev); edac_mc_free(mci); - return 0; } static struct platform_driver octeon_lmc_edac_driver = { .probe = octeon_lmc_edac_probe, - .remove = octeon_lmc_edac_remove, + .remove_new = octeon_lmc_edac_remove, .driver = { .name = "octeon_lmc_edac", } diff --git a/drivers/edac/octeon_edac-pc.c b/drivers/edac/octeon_edac-pc.c index 754eced59c32..ea8a8e337b1e 100644 --- a/drivers/edac/octeon_edac-pc.c +++ b/drivers/edac/octeon_edac-pc.c @@ -119,19 +119,18 @@ err: return -ENXIO; } -static int co_cache_error_remove(struct platform_device *pdev) +static void co_cache_error_remove(struct platform_device *pdev) { struct co_cache_error *p = platform_get_drvdata(pdev); unregister_co_cache_error_notifier(&p->notifier); edac_device_del_device(&pdev->dev); edac_device_free_ctl_info(p->ed); - return 0; } static struct platform_driver co_cache_error_driver = { .probe = co_cache_error_probe, - .remove = co_cache_error_remove, + .remove_new = co_cache_error_remove, .driver = { .name = "octeon_pc_edac", } diff --git a/drivers/edac/octeon_edac-pci.c b/drivers/edac/octeon_edac-pci.c index 28b238eecefc..108ad9493cfb 100644 --- a/drivers/edac/octeon_edac-pci.c +++ b/drivers/edac/octeon_edac-pci.c @@ -87,19 +87,17 @@ err: return res; } -static int octeon_pci_remove(struct platform_device *pdev) +static void octeon_pci_remove(struct platform_device *pdev) { struct edac_pci_ctl_info *pci = platform_get_drvdata(pdev); edac_pci_del_device(&pdev->dev); edac_pci_free_ctl_info(pci); - - return 0; } static struct platform_driver octeon_pci_driver = { .probe = octeon_pci_probe, - .remove = octeon_pci_remove, + .remove_new = octeon_pci_remove, .driver = { .name = "octeon_pci_edac", } diff --git a/drivers/edac/pnd2_edac.c b/drivers/edac/pnd2_edac.c index 2b306f2cc605..2afcd148fcf8 100644 --- a/drivers/edac/pnd2_edac.c +++ b/drivers/edac/pnd2_edac.c @@ -16,18 +16,20 @@ * rank, bank, row and column using the appropriate "dunit_ops" functions/parameters. */ -#include <linux/module.h> +#include <linux/bitmap.h> +#include <linux/delay.h> +#include <linux/edac.h> #include <linux/init.h> +#include <linux/math64.h> +#include <linux/mmzone.h> +#include <linux/mod_devicetable.h> +#include <linux/module.h> #include <linux/pci.h> #include <linux/pci_ids.h> +#include <linux/sizes.h> #include <linux/slab.h> -#include <linux/delay.h> -#include <linux/edac.h> -#include <linux/mmzone.h> #include <linux/smp.h> -#include <linux/bitmap.h> -#include <linux/math64.h> -#include <linux/mod_devicetable.h> + #include <linux/platform_data/x86/p2sb.h> #include <asm/cpu_device_id.h> @@ -109,7 +111,6 @@ static struct mem_ctl_info *pnd2_mci; #define MOT_CHAN_INTLV_BIT_1SLC_2CH 12 #define MOT_CHAN_INTLV_BIT_2SLC_2CH 13 #define SELECTOR_DISABLED (-1) -#define _4GB (1ul << 32) #define PMI_ADDRESS_WIDTH 31 #define PND_MAX_PHYS_BIT 39 @@ -183,7 +184,7 @@ static int _apl_rd_reg(int port, int off, int op, u32 *data) } P2SB_READ(dword, P2SB_DATA_OFF, data); - ret = (status >> 1) & 0x3; + ret = (status >> 1) & GENMASK(1, 0); out: /* Hide the P2SB device, if it was hidden before */ if (hidden) @@ -307,7 +308,7 @@ static bool two_channels; /* Both PMI channels in one slice enabled */ static u8 sym_chan_mask; static u8 asym_chan_mask; -static u8 chan_mask; +static unsigned long chan_mask; static int slice_selector = -1; static int chan_selector = -1; @@ -329,7 +330,7 @@ static void mk_region_mask(char *name, struct region *rp, u64 base, u64 mask) return; } if (mask != GENMASK_ULL(PND_MAX_PHYS_BIT, __ffs(mask))) { - pr_info(FW_BUG "MOT mask not power of two\n"); + pr_info(FW_BUG "MOT mask is invalid\n"); return; } if (base & ~mask) { @@ -587,7 +588,7 @@ static int get_registers(void) /* Get a contiguous memory address (remove the MMIO gap) */ static u64 remove_mmio_gap(u64 sys) { - return (sys < _4GB) ? sys : sys - (_4GB - top_lm); + return (sys < SZ_4G) ? sys : sys - (SZ_4G - top_lm); } /* Squeeze out one address bit, shift upper part down to fill gap */ @@ -598,7 +599,7 @@ static void remove_addr_bit(u64 *addr, int bitidx) if (bitidx == -1) return; - mask = (1ull << bitidx) - 1; + mask = BIT_ULL(bitidx) - 1; *addr = ((*addr >> 1) & ~mask) | (*addr & mask); } @@ -642,8 +643,8 @@ static int sys2pmi(const u64 addr, u32 *pmiidx, u64 *pmiaddr, char *msg) int sym_chan_shift = sym_channels >> 1; /* Give up if address is out of range, or in MMIO gap */ - if (addr >= (1ul << PND_MAX_PHYS_BIT) || - (addr >= top_lm && addr < _4GB) || addr >= top_hm) { + if (addr >= BIT(PND_MAX_PHYS_BIT) || + (addr >= top_lm && addr < SZ_4G) || addr >= top_hm) { snprintf(msg, PND2_MSG_SIZE, "Error address 0x%llx is not DRAM", addr); return -EINVAL; } @@ -727,10 +728,10 @@ static int sys2pmi(const u64 addr, u32 *pmiidx, u64 *pmiaddr, char *msg) } /* Translate PMI address to memory (rank, row, bank, column) */ -#define C(n) (0x10 | (n)) /* column */ -#define B(n) (0x20 | (n)) /* bank */ -#define R(n) (0x40 | (n)) /* row */ -#define RS (0x80) /* rank */ +#define C(n) (BIT(4) | (n)) /* column */ +#define B(n) (BIT(5) | (n)) /* bank */ +#define R(n) (BIT(6) | (n)) /* row */ +#define RS (BIT(7)) /* rank */ /* addrdec values */ #define AMAP_1KB 0 @@ -1064,9 +1065,9 @@ static int apl_check_ecc_active(void) int i, ret = 0; /* Check dramtype and ECC mode for each present DIMM */ - for (i = 0; i < APL_NUM_CHANNELS; i++) - if (chan_mask & BIT(i)) - ret += check_channel(i); + for_each_set_bit(i, &chan_mask, APL_NUM_CHANNELS) + ret += check_channel(i); + return ret ? -EINVAL : 0; } @@ -1205,10 +1206,7 @@ static void apl_get_dimm_config(struct mem_ctl_info *mci) u64 capacity; int i, g; - for (i = 0; i < APL_NUM_CHANNELS; i++) { - if (!(chan_mask & BIT(i))) - continue; - + for_each_set_bit(i, &chan_mask, APL_NUM_CHANNELS) { dimm = edac_get_dimm(mci, i, 0, 0); if (!dimm) { edac_dbg(0, "No allocated DIMM for channel %d\n", i); @@ -1228,8 +1226,7 @@ static void apl_get_dimm_config(struct mem_ctl_info *mci) } pvt->dimm_geom[i] = g; - capacity = (d->rken0 + d->rken1) * 8 * (1ul << dimms[g].rowbits) * - (1ul << dimms[g].colbits); + capacity = (d->rken0 + d->rken1) * 8 * BIT(dimms[g].rowbits + dimms[g].colbits); edac_dbg(0, "Channel %d: %lld MByte DIMM\n", i, capacity >> (20 - 3)); dimm->nr_pages = MiB_TO_PAGES(capacity >> (20 - 3)); dimm->grain = 32; @@ -1295,7 +1292,7 @@ static void dnv_get_dimm_config(struct mem_ctl_info *mci) continue; } - capacity = ranks_of_dimm[j] * banks * (1ul << rowbits) * (1ul << colbits); + capacity = ranks_of_dimm[j] * banks * BIT(rowbits + colbits); edac_dbg(0, "Channel %d DIMM %d: %lld MByte DIMM\n", i, j, capacity >> (20 - 3)); dimm->nr_pages = MiB_TO_PAGES(capacity >> (20 - 3)); dimm->grain = 32; diff --git a/drivers/edac/ppc4xx_edac.c b/drivers/edac/ppc4xx_edac.c index 046969b4e82e..1eea3341a916 100644 --- a/drivers/edac/ppc4xx_edac.c +++ b/drivers/edac/ppc4xx_edac.c @@ -1329,8 +1329,7 @@ static int ppc4xx_edac_probe(struct platform_device *op) * * Unconditionally returns 0. */ -static int -ppc4xx_edac_remove(struct platform_device *op) +static void ppc4xx_edac_remove(struct platform_device *op) { struct mem_ctl_info *mci = dev_get_drvdata(&op->dev); struct ppc4xx_edac_pdata *pdata = mci->pvt_info; @@ -1344,8 +1343,6 @@ ppc4xx_edac_remove(struct platform_device *op) edac_mc_del_mc(mci->pdev); edac_mc_free(mci); - - return 0; } /** @@ -1379,7 +1376,7 @@ ppc4xx_edac_opstate_init(void) static struct platform_driver ppc4xx_edac_driver = { .probe = ppc4xx_edac_probe, - .remove = ppc4xx_edac_remove, + .remove_new = ppc4xx_edac_remove, .driver = { .name = PPC4XX_EDAC_MODULE_NAME, .of_match_table = ppc4xx_edac_match, diff --git a/drivers/edac/qcom_edac.c b/drivers/edac/qcom_edac.c index b2db545c6810..5539917c01dd 100644 --- a/drivers/edac/qcom_edac.c +++ b/drivers/edac/qcom_edac.c @@ -390,14 +390,12 @@ irq_done: return rc; } -static int qcom_llcc_edac_remove(struct platform_device *pdev) +static void qcom_llcc_edac_remove(struct platform_device *pdev) { struct edac_device_ctl_info *edev_ctl = dev_get_drvdata(&pdev->dev); edac_device_del_device(edev_ctl->dev); edac_device_free_ctl_info(edev_ctl); - - return 0; } static const struct platform_device_id qcom_llcc_edac_id_table[] = { @@ -408,7 +406,7 @@ MODULE_DEVICE_TABLE(platform, qcom_llcc_edac_id_table); static struct platform_driver qcom_llcc_edac_driver = { .probe = qcom_llcc_edac_probe, - .remove = qcom_llcc_edac_remove, + .remove_new = qcom_llcc_edac_remove, .driver = { .name = "qcom_llcc_edac", }, diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c index 0c779a0326b6..26cca5a9322d 100644 --- a/drivers/edac/sb_edac.c +++ b/drivers/edac/sb_edac.c @@ -439,7 +439,7 @@ static const struct pci_id_descr pci_dev_descr_sbridge[] = { static const struct pci_id_table pci_dev_descr_sbridge_table[] = { PCI_ID_TABLE_ENTRY(pci_dev_descr_sbridge, ARRAY_SIZE(pci_dev_descr_sbridge), 1, SANDY_BRIDGE), - {0,} /* 0 terminated list. */ + { NULL, } }; /* This changes depending if 1HA or 2HA: @@ -505,7 +505,7 @@ static const struct pci_id_descr pci_dev_descr_ibridge[] = { static const struct pci_id_table pci_dev_descr_ibridge_table[] = { PCI_ID_TABLE_ENTRY(pci_dev_descr_ibridge, 12, 2, IVY_BRIDGE), - {0,} /* 0 terminated list. */ + { NULL, } }; /* Haswell support */ @@ -576,7 +576,7 @@ static const struct pci_id_descr pci_dev_descr_haswell[] = { static const struct pci_id_table pci_dev_descr_haswell_table[] = { PCI_ID_TABLE_ENTRY(pci_dev_descr_haswell, 13, 2, HASWELL), - {0,} /* 0 terminated list. */ + { NULL, } }; /* Knight's Landing Support */ @@ -620,7 +620,7 @@ static const struct pci_id_descr pci_dev_descr_knl[] = { static const struct pci_id_table pci_dev_descr_knl_table[] = { PCI_ID_TABLE_ENTRY(pci_dev_descr_knl, ARRAY_SIZE(pci_dev_descr_knl), 1, KNIGHTS_LANDING), - {0,} + { NULL, } }; /* @@ -686,7 +686,7 @@ static const struct pci_id_descr pci_dev_descr_broadwell[] = { static const struct pci_id_table pci_dev_descr_broadwell_table[] = { PCI_ID_TABLE_ENTRY(pci_dev_descr_broadwell, 10, 2, BROADWELL), - {0,} /* 0 terminated list. */ + { NULL, } }; diff --git a/drivers/edac/skx_common.c b/drivers/edac/skx_common.c index ce3e0069e028..9c5b6f8bd8bd 100644 --- a/drivers/edac/skx_common.c +++ b/drivers/edac/skx_common.c @@ -648,6 +648,10 @@ int skx_mce_check_error(struct notifier_block *nb, unsigned long val, memset(&res, 0, sizeof(res)); res.mce = mce; res.addr = mce->addr & MCI_ADDR_PHYSADDR; + if (!pfn_to_online_page(res.addr >> PAGE_SHIFT)) { + pr_err("Invalid address 0x%llx in IA32_MC%d_ADDR\n", mce->addr, mce->bank); + return NOTIFY_DONE; + } /* Try driver decoder first */ if (!(driver_decode && driver_decode(&res))) { diff --git a/drivers/edac/synopsys_edac.c b/drivers/edac/synopsys_edac.c index c4fc64cbecd0..709babce43ba 100644 --- a/drivers/edac/synopsys_edac.c +++ b/drivers/edac/synopsys_edac.c @@ -1410,7 +1410,7 @@ free_edac_mc: * * Return: Unconditionally 0 */ -static int mc_remove(struct platform_device *pdev) +static void mc_remove(struct platform_device *pdev) { struct mem_ctl_info *mci = platform_get_drvdata(pdev); struct synps_edac_priv *priv = mci->pvt_info; @@ -1425,8 +1425,6 @@ static int mc_remove(struct platform_device *pdev) edac_mc_del_mc(&pdev->dev); edac_mc_free(mci); - - return 0; } static struct platform_driver synps_edac_mc_driver = { @@ -1435,7 +1433,7 @@ static struct platform_driver synps_edac_mc_driver = { .of_match_table = synps_edac_match, }, .probe = mc_probe, - .remove = mc_remove, + .remove_new = mc_remove, }; module_platform_driver(synps_edac_mc_driver); diff --git a/drivers/edac/thunderx_edac.c b/drivers/edac/thunderx_edac.c index b9c5772da959..90d46e5c4ff0 100644 --- a/drivers/edac/thunderx_edac.c +++ b/drivers/edac/thunderx_edac.c @@ -1133,7 +1133,7 @@ static irqreturn_t thunderx_ocx_com_threaded_isr(int irq, void *irq_id) decode_register(other, OCX_OTHER_SIZE, ocx_com_errors, ctx->reg_com_int); - strncat(msg, other, OCX_MESSAGE_SIZE); + strlcat(msg, other, OCX_MESSAGE_SIZE); for (lane = 0; lane < OCX_RX_LANES; lane++) if (ctx->reg_com_int & BIT(lane)) { @@ -1142,12 +1142,12 @@ static irqreturn_t thunderx_ocx_com_threaded_isr(int irq, void *irq_id) lane, ctx->reg_lane_int[lane], lane, ctx->reg_lane_stat11[lane]); - strncat(msg, other, OCX_MESSAGE_SIZE); + strlcat(msg, other, OCX_MESSAGE_SIZE); decode_register(other, OCX_OTHER_SIZE, ocx_lane_errors, ctx->reg_lane_int[lane]); - strncat(msg, other, OCX_MESSAGE_SIZE); + strlcat(msg, other, OCX_MESSAGE_SIZE); } if (ctx->reg_com_int & OCX_COM_INT_CE) @@ -1217,7 +1217,7 @@ static irqreturn_t thunderx_ocx_lnk_threaded_isr(int irq, void *irq_id) decode_register(other, OCX_OTHER_SIZE, ocx_com_link_errors, ctx->reg_com_link_int); - strncat(msg, other, OCX_MESSAGE_SIZE); + strlcat(msg, other, OCX_MESSAGE_SIZE); if (ctx->reg_com_link_int & OCX_COM_LINK_INT_UE) edac_device_handle_ue(ocx->edac_dev, 0, 0, msg); @@ -1896,7 +1896,7 @@ static irqreturn_t thunderx_l2c_threaded_isr(int irq, void *irq_id) decode_register(other, L2C_OTHER_SIZE, l2_errors, ctx->reg_int); - strncat(msg, other, L2C_MESSAGE_SIZE); + strlcat(msg, other, L2C_MESSAGE_SIZE); if (ctx->reg_int & mask_ue) edac_device_handle_ue(l2c->edac_dev, 0, 0, msg); diff --git a/drivers/edac/ti_edac.c b/drivers/edac/ti_edac.c index 6971ded598de..29723c9592f7 100644 --- a/drivers/edac/ti_edac.c +++ b/drivers/edac/ti_edac.c @@ -312,19 +312,17 @@ err: return ret; } -static int ti_edac_remove(struct platform_device *pdev) +static void ti_edac_remove(struct platform_device *pdev) { struct mem_ctl_info *mci = platform_get_drvdata(pdev); edac_mc_del_mc(&pdev->dev); edac_mc_free(mci); - - return 0; } static struct platform_driver ti_edac_driver = { .probe = ti_edac_probe, - .remove = ti_edac_remove, + .remove_new = ti_edac_remove, .driver = { .name = EDAC_MOD_NAME, .of_match_table = ti_edac_of_match, diff --git a/drivers/edac/versal_edac.c b/drivers/edac/versal_edac.c index 87e730dfefa0..8625de20fc71 100644 --- a/drivers/edac/versal_edac.c +++ b/drivers/edac/versal_edac.c @@ -966,10 +966,10 @@ static int mc_probe(struct platform_device *pdev) edac_mc_id = emif_get_id(pdev->dev.of_node); regval = readl(ddrmc_baseaddr + XDDR_REG_CONFIG0_OFFSET); - num_chans = FIELD_PREP(XDDR_REG_CONFIG0_NUM_CHANS_MASK, regval); + num_chans = FIELD_GET(XDDR_REG_CONFIG0_NUM_CHANS_MASK, regval); num_chans++; - num_csrows = FIELD_PREP(XDDR_REG_CONFIG0_NUM_RANKS_MASK, regval); + num_csrows = FIELD_GET(XDDR_REG_CONFIG0_NUM_RANKS_MASK, regval); num_csrows *= 2; if (!num_csrows) num_csrows = 1; diff --git a/drivers/edac/xgene_edac.c b/drivers/edac/xgene_edac.c index c52b9dd9154c..1b50f8160013 100644 --- a/drivers/edac/xgene_edac.c +++ b/drivers/edac/xgene_edac.c @@ -1960,7 +1960,7 @@ out_err: return rc; } -static int xgene_edac_remove(struct platform_device *pdev) +static void xgene_edac_remove(struct platform_device *pdev) { struct xgene_edac *edac = dev_get_drvdata(&pdev->dev); struct xgene_edac_mc_ctx *mcu; @@ -1981,8 +1981,6 @@ static int xgene_edac_remove(struct platform_device *pdev) list_for_each_entry_safe(node, temp_node, &edac->socs, next) xgene_edac_soc_remove(node); - - return 0; } static const struct of_device_id xgene_edac_of_match[] = { @@ -1993,7 +1991,7 @@ MODULE_DEVICE_TABLE(of, xgene_edac_of_match); static struct platform_driver xgene_edac_driver = { .probe = xgene_edac_probe, - .remove = xgene_edac_remove, + .remove_new = xgene_edac_remove, .driver = { .name = "xgene-edac", .of_match_table = xgene_edac_of_match, diff --git a/drivers/edac/zynqmp_edac.c b/drivers/edac/zynqmp_edac.c index ac7d1e0b324c..2d9a5cfd8931 100644 --- a/drivers/edac/zynqmp_edac.c +++ b/drivers/edac/zynqmp_edac.c @@ -426,7 +426,7 @@ free_dev_ctl: return ret; } -static int edac_remove(struct platform_device *pdev) +static void edac_remove(struct platform_device *pdev) { struct edac_device_ctl_info *dci = platform_get_drvdata(pdev); struct edac_priv *priv = dci->pvt_info; @@ -440,8 +440,6 @@ static int edac_remove(struct platform_device *pdev) edac_device_del_device(&pdev->dev); edac_device_free_ctl_info(dci); - - return 0; } static const struct of_device_id zynqmp_ocm_edac_match[] = { @@ -457,7 +455,7 @@ static struct platform_driver zynqmp_ocm_edac_driver = { .of_match_table = zynqmp_ocm_edac_match, }, .probe = edac_probe, - .remove = edac_remove, + .remove_new = edac_remove, }; module_platform_driver(zynqmp_ocm_edac_driver); diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c index 7e88fd489741..9db9290c3269 100644 --- a/drivers/firewire/ohci.c +++ b/drivers/firewire/ohci.c @@ -279,6 +279,51 @@ static char ohci_driver_name[] = KBUILD_MODNAME; #define QUIRK_TI_SLLZ059 0x20 #define QUIRK_IR_WAKE 0x40 +// On PCI Express Root Complex in any type of AMD Ryzen machine, VIA VT6306/6307/6308 with Asmedia +// ASM1083/1085 brings an inconvenience that the read accesses to 'Isochronous Cycle Timer' register +// (at offset 0xf0 in PCI I/O space) often causes unexpected system reboot. The mechanism is not +// clear, since the read access to the other registers is enough safe; e.g. 'Node ID' register, +// while it is probable due to detection of any type of PCIe error. +#define QUIRK_REBOOT_BY_CYCLE_TIMER_READ 0x80000000 + +#if IS_ENABLED(CONFIG_X86) + +static bool has_reboot_by_cycle_timer_read_quirk(const struct fw_ohci *ohci) +{ + return !!(ohci->quirks & QUIRK_REBOOT_BY_CYCLE_TIMER_READ); +} + +#define PCI_DEVICE_ID_ASMEDIA_ASM108X 0x1080 + +static bool detect_vt630x_with_asm1083_on_amd_ryzen_machine(const struct pci_dev *pdev) +{ + const struct pci_dev *pcie_to_pci_bridge; + + // Detect any type of AMD Ryzen machine. + if (!static_cpu_has(X86_FEATURE_ZEN)) + return false; + + // Detect VIA VT6306/6307/6308. + if (pdev->vendor != PCI_VENDOR_ID_VIA) + return false; + if (pdev->device != PCI_DEVICE_ID_VIA_VT630X) + return false; + + // Detect Asmedia ASM1083/1085. + pcie_to_pci_bridge = pdev->bus->self; + if (pcie_to_pci_bridge->vendor != PCI_VENDOR_ID_ASMEDIA) + return false; + if (pcie_to_pci_bridge->device != PCI_DEVICE_ID_ASMEDIA_ASM108X) + return false; + + return true; +} + +#else +#define has_reboot_by_cycle_timer_read_quirk(ohci) false +#define detect_vt630x_with_asm1083_on_amd_ryzen_machine(pdev) false +#endif + /* In case of multiple matches in ohci_quirks[], only the first one is used. */ static const struct { unsigned short vendor, device, revision, flags; @@ -1724,6 +1769,9 @@ static u32 get_cycle_time(struct fw_ohci *ohci) s32 diff01, diff12; int i; + if (has_reboot_by_cycle_timer_read_quirk(ohci)) + return 0; + c2 = reg_read(ohci, OHCI1394_IsochronousCycleTimer); if (ohci->quirks & QUIRK_CYCLE_TIMER) { @@ -3630,6 +3678,9 @@ static int pci_probe(struct pci_dev *dev, if (param_quirks) ohci->quirks = param_quirks; + if (detect_vt630x_with_asm1083_on_amd_ryzen_machine(dev)) + ohci->quirks |= QUIRK_REBOOT_BY_CYCLE_TIMER_READ; + /* * Because dma_alloc_coherent() allocates at least one page, * we save space by using a common buffer for the AR request/ diff --git a/drivers/firmware/efi/libstub/loongarch-stub.c b/drivers/firmware/efi/libstub/loongarch-stub.c index 72c71ae201f0..d6ec5d4b8dbe 100644 --- a/drivers/firmware/efi/libstub/loongarch-stub.c +++ b/drivers/firmware/efi/libstub/loongarch-stub.c @@ -35,9 +35,9 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, return status; } -unsigned long kernel_entry_address(void) +unsigned long kernel_entry_address(unsigned long kernel_addr) { unsigned long base = (unsigned long)&kernel_offset - kernel_offset; - return (unsigned long)&kernel_entry - base + VMLINUX_LOAD_ADDRESS; + return (unsigned long)&kernel_entry - base + kernel_addr; } diff --git a/drivers/firmware/efi/libstub/loongarch.c b/drivers/firmware/efi/libstub/loongarch.c index 807cba2693fc..0e0aa6cda73f 100644 --- a/drivers/firmware/efi/libstub/loongarch.c +++ b/drivers/firmware/efi/libstub/loongarch.c @@ -37,9 +37,9 @@ static efi_status_t exit_boot_func(struct efi_boot_memmap *map, void *priv) return EFI_SUCCESS; } -unsigned long __weak kernel_entry_address(void) +unsigned long __weak kernel_entry_address(unsigned long kernel_addr) { - return *(unsigned long *)(PHYSADDR(VMLINUX_LOAD_ADDRESS) + 8); + return *(unsigned long *)(kernel_addr + 8) - VMLINUX_LOAD_ADDRESS + kernel_addr; } efi_status_t efi_boot_kernel(void *handle, efi_loaded_image_t *image, @@ -73,7 +73,7 @@ efi_status_t efi_boot_kernel(void *handle, efi_loaded_image_t *image, csr_write64(CSR_DMW0_INIT, LOONGARCH_CSR_DMWIN0); csr_write64(CSR_DMW1_INIT, LOONGARCH_CSR_DMWIN1); - real_kernel_entry = (void *)kernel_entry_address(); + real_kernel_entry = (void *)kernel_entry_address(kernel_addr); real_kernel_entry(true, (unsigned long)cmdline_ptr, (unsigned long)efi_system_table); diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c index 1bfdae34df39..0d510c9a06a4 100644 --- a/drivers/firmware/efi/libstub/x86-stub.c +++ b/drivers/firmware/efi/libstub/x86-stub.c @@ -307,17 +307,20 @@ static void setup_unaccepted_memory(void) efi_err("Memory acceptance protocol failed\n"); } +static efi_char16_t *efistub_fw_vendor(void) +{ + unsigned long vendor = efi_table_attr(efi_system_table, fw_vendor); + + return (efi_char16_t *)vendor; +} + static const efi_char16_t apple[] = L"Apple"; static void setup_quirks(struct boot_params *boot_params) { - efi_char16_t *fw_vendor = (efi_char16_t *)(unsigned long) - efi_table_attr(efi_system_table, fw_vendor); - - if (!memcmp(fw_vendor, apple, sizeof(apple))) { - if (IS_ENABLED(CONFIG_APPLE_PROPERTIES)) - retrieve_apple_device_properties(boot_params); - } + if (IS_ENABLED(CONFIG_APPLE_PROPERTIES) && + !memcmp(efistub_fw_vendor(), apple, sizeof(apple))) + retrieve_apple_device_properties(boot_params); } /* @@ -765,11 +768,27 @@ static efi_status_t efi_decompress_kernel(unsigned long *kernel_entry) if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && !efi_nokaslr) { u64 range = KERNEL_IMAGE_SIZE - LOAD_PHYSICAL_ADDR - kernel_total_size; + static const efi_char16_t ami[] = L"American Megatrends"; efi_get_seed(seed, sizeof(seed)); virt_addr += (range * seed[1]) >> 32; virt_addr &= ~(CONFIG_PHYSICAL_ALIGN - 1); + + /* + * Older Dell systems with AMI UEFI firmware v2.0 may hang + * while decompressing the kernel if physical address + * randomization is enabled. + * + * https://bugzilla.kernel.org/show_bug.cgi?id=218173 + */ + if (efi_system_table->hdr.revision <= EFI_2_00_SYSTEM_TABLE_REVISION && + !memcmp(efistub_fw_vendor(), ami, sizeof(ami))) { + efi_debug("AMI firmware v2.0 or older detected - disabling physical KASLR\n"); + seed[0] = 0; + } + + boot_params_ptr->hdr.loadflags |= KASLR_FLAG; } status = efi_random_alloc(alloc_size, CONFIG_PHYSICAL_ALIGN, &addr, diff --git a/drivers/fpga/dfl.c b/drivers/fpga/dfl.c index dd7a783d53b5..e73f88050f08 100644 --- a/drivers/fpga/dfl.c +++ b/drivers/fpga/dfl.c @@ -1872,7 +1872,7 @@ static irqreturn_t dfl_irq_handler(int irq, void *arg) { struct eventfd_ctx *trigger = arg; - eventfd_signal(trigger, 1); + eventfd_signal(trigger); return IRQ_HANDLED; } diff --git a/drivers/gpio/gpio-dwapb.c b/drivers/gpio/gpio-dwapb.c index 4a4f61bf6c58..8c59332429c2 100644 --- a/drivers/gpio/gpio-dwapb.c +++ b/drivers/gpio/gpio-dwapb.c @@ -282,13 +282,15 @@ static void dwapb_irq_enable(struct irq_data *d) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); struct dwapb_gpio *gpio = to_dwapb_gpio(gc); + irq_hw_number_t hwirq = irqd_to_hwirq(d); unsigned long flags; u32 val; raw_spin_lock_irqsave(&gc->bgpio_lock, flags); - val = dwapb_read(gpio, GPIO_INTEN); - val |= BIT(irqd_to_hwirq(d)); + val = dwapb_read(gpio, GPIO_INTEN) | BIT(hwirq); dwapb_write(gpio, GPIO_INTEN, val); + val = dwapb_read(gpio, GPIO_INTMASK) & ~BIT(hwirq); + dwapb_write(gpio, GPIO_INTMASK, val); raw_spin_unlock_irqrestore(&gc->bgpio_lock, flags); } @@ -296,12 +298,14 @@ static void dwapb_irq_disable(struct irq_data *d) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); struct dwapb_gpio *gpio = to_dwapb_gpio(gc); + irq_hw_number_t hwirq = irqd_to_hwirq(d); unsigned long flags; u32 val; raw_spin_lock_irqsave(&gc->bgpio_lock, flags); - val = dwapb_read(gpio, GPIO_INTEN); - val &= ~BIT(irqd_to_hwirq(d)); + val = dwapb_read(gpio, GPIO_INTMASK) | BIT(hwirq); + dwapb_write(gpio, GPIO_INTMASK, val); + val = dwapb_read(gpio, GPIO_INTEN) & ~BIT(hwirq); dwapb_write(gpio, GPIO_INTEN, val); raw_spin_unlock_irqrestore(&gc->bgpio_lock, flags); } diff --git a/drivers/gpio/gpiolib-cdev.c b/drivers/gpio/gpiolib-cdev.c index 02ffda6c1e51..f713d1ef7746 100644 --- a/drivers/gpio/gpiolib-cdev.c +++ b/drivers/gpio/gpiolib-cdev.c @@ -2481,10 +2481,7 @@ static int lineinfo_unwatch(struct gpio_chardev_data *cdev, void __user *ip) return 0; } -/* - * gpio_ioctl() - ioctl handler for the GPIO chardev - */ -static long gpio_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +static long gpio_ioctl_unlocked(struct file *file, unsigned int cmd, unsigned long arg) { struct gpio_chardev_data *cdev = file->private_data; struct gpio_device *gdev = cdev->gdev; @@ -2521,6 +2518,17 @@ static long gpio_ioctl(struct file *file, unsigned int cmd, unsigned long arg) } } +/* + * gpio_ioctl() - ioctl handler for the GPIO chardev + */ +static long gpio_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + struct gpio_chardev_data *cdev = file->private_data; + + return call_ioctl_locked(file, cmd, arg, cdev->gdev, + gpio_ioctl_unlocked); +} + #ifdef CONFIG_COMPAT static long gpio_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 1f64d8cbb14d..93cf73d6fa11 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -2188,15 +2188,8 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev) adev->firmware.gpu_info_fw = NULL; - if (adev->mman.discovery_bin) { - /* - * FIXME: The bounding box is still needed by Navi12, so - * temporarily read it from gpu_info firmware. Should be dropped - * when DAL no longer needs it. - */ - if (adev->asic_type != CHIP_NAVI12) - return 0; - } + if (adev->mman.discovery_bin) + return 0; switch (adev->asic_type) { default: @@ -4516,8 +4509,6 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon) amdgpu_ras_suspend(adev); - amdgpu_ttm_set_buffer_funcs_status(adev, false); - amdgpu_device_ip_suspend_phase1(adev); if (!adev->in_s0ix) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index d79b4ca1ecfc..5ad03f2afdb4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -1343,6 +1343,8 @@ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo) abo = ttm_to_amdgpu_bo(bo); + WARN_ON(abo->vm_bo); + if (abo->kfd_bo) amdgpu_amdkfd_release_notify(abo); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index d1b8afd105c9..5baefb548a29 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -285,6 +285,7 @@ static void amdgpu_vm_bo_reset_state_machine(struct amdgpu_vm *vm) list_for_each_entry_safe(vm_bo, tmp, &vm->idle, vm_status) { struct amdgpu_bo *bo = vm_bo->bo; + vm_bo->moved = true; if (!bo || bo->tbo.type != ttm_bo_type_kernel) list_move(&vm_bo->vm_status, &vm_bo->vm->moved); else if (bo->parent) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c index a2287bb25223..a160265ddc07 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c @@ -642,13 +642,14 @@ static void amdgpu_vm_pt_free(struct amdgpu_vm_bo_base *entry) if (!entry->bo) return; + + entry->bo->vm_bo = NULL; shadow = amdgpu_bo_shadowed(entry->bo); if (shadow) { ttm_bo_set_bulk_move(&shadow->tbo, NULL); amdgpu_bo_unref(&shadow); } ttm_bo_set_bulk_move(&entry->bo->tbo, NULL); - entry->bo->vm_bo = NULL; spin_lock(&entry->vm->status_lock); list_del(&entry->vm_status); diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c index 9df011323d4b..6ede85b28cc8 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c @@ -155,13 +155,6 @@ static int jpeg_v4_0_5_hw_init(void *handle) struct amdgpu_ring *ring = adev->jpeg.inst->ring_dec; int r; - adev->nbio.funcs->vcn_doorbell_range(adev, ring->use_doorbell, - (adev->doorbell_index.vcn.vcn_ring0_1 << 1), 0); - - WREG32_SOC15(VCN, 0, regVCN_JPEG_DB_CTRL, - ring->doorbell_index << VCN_JPEG_DB_CTRL__OFFSET__SHIFT | - VCN_JPEG_DB_CTRL__EN_MASK); - r = amdgpu_ring_test_helper(ring); if (r) return r; @@ -336,6 +329,14 @@ static int jpeg_v4_0_5_start(struct amdgpu_device *adev) if (adev->pm.dpm_enabled) amdgpu_dpm_enable_jpeg(adev, true); + /* doorbell programming is done for every playback */ + adev->nbio.funcs->vcn_doorbell_range(adev, ring->use_doorbell, + (adev->doorbell_index.vcn.vcn_ring0_1 << 1), 0); + + WREG32_SOC15(VCN, 0, regVCN_JPEG_DB_CTRL, + ring->doorbell_index << VCN_JPEG_DB_CTRL__OFFSET__SHIFT | + VCN_JPEG_DB_CTRL__EN_MASK); + /* disable power gating */ r = jpeg_v4_0_5_disable_static_power_gating(adev); if (r) diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c index 45377a175250..8d5d86675a7f 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c @@ -813,12 +813,12 @@ static int sdma_v2_4_early_init(void *handle) struct amdgpu_device *adev = (struct amdgpu_device *)handle; int r; + adev->sdma.num_instances = SDMA_MAX_INSTANCE; + r = sdma_v2_4_init_microcode(adev); if (r) return r; - adev->sdma.num_instances = SDMA_MAX_INSTANCE; - sdma_v2_4_set_ring_funcs(adev); sdma_v2_4_set_buffer_funcs(adev); sdma_v2_4_set_vm_pte_funcs(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c index 83c240f741b5..0058f3f7cf6e 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c @@ -1643,6 +1643,32 @@ static void sdma_v5_2_get_clockgating_state(void *handle, u64 *flags) *flags |= AMD_CG_SUPPORT_SDMA_LS; } +static void sdma_v5_2_ring_begin_use(struct amdgpu_ring *ring) +{ + struct amdgpu_device *adev = ring->adev; + + /* SDMA 5.2.3 (RMB) FW doesn't seem to properly + * disallow GFXOFF in some cases leading to + * hangs in SDMA. Disallow GFXOFF while SDMA is active. + * We can probably just limit this to 5.2.3, + * but it shouldn't hurt for other parts since + * this GFXOFF will be disallowed anyway when SDMA is + * active, this just makes it explicit. + */ + amdgpu_gfx_off_ctrl(adev, false); +} + +static void sdma_v5_2_ring_end_use(struct amdgpu_ring *ring) +{ + struct amdgpu_device *adev = ring->adev; + + /* SDMA 5.2.3 (RMB) FW doesn't seem to properly + * disallow GFXOFF in some cases leading to + * hangs in SDMA. Allow GFXOFF when SDMA is complete. + */ + amdgpu_gfx_off_ctrl(adev, true); +} + const struct amd_ip_funcs sdma_v5_2_ip_funcs = { .name = "sdma_v5_2", .early_init = sdma_v5_2_early_init, @@ -1690,6 +1716,8 @@ static const struct amdgpu_ring_funcs sdma_v5_2_ring_funcs = { .test_ib = sdma_v5_2_ring_test_ib, .insert_nop = sdma_v5_2_ring_insert_nop, .pad_ib = sdma_v5_2_ring_pad_ib, + .begin_use = sdma_v5_2_ring_begin_use, + .end_use = sdma_v5_2_ring_end_use, .emit_wreg = sdma_v5_2_ring_emit_wreg, .emit_reg_wait = sdma_v5_2_ring_emit_reg_wait, .emit_reg_write_reg_wait = sdma_v5_2_ring_emit_reg_write_reg_wait, diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index f2f3c338fd94..a15bfb5223e8 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -1653,18 +1653,24 @@ static int svm_range_validate_and_map(struct mm_struct *mm, if (test_bit(gpuidx, prange->bitmap_access)) bitmap_set(ctx->bitmap, gpuidx, 1); } + + /* + * If prange is already mapped or with always mapped flag, + * update mapping on GPUs with ACCESS attribute + */ + if (bitmap_empty(ctx->bitmap, MAX_GPU_INSTANCE)) { + if (prange->mapped_to_gpu || + prange->flags & KFD_IOCTL_SVM_FLAG_GPU_ALWAYS_MAPPED) + bitmap_copy(ctx->bitmap, prange->bitmap_access, MAX_GPU_INSTANCE); + } } else { bitmap_or(ctx->bitmap, prange->bitmap_access, prange->bitmap_aip, MAX_GPU_INSTANCE); } if (bitmap_empty(ctx->bitmap, MAX_GPU_INSTANCE)) { - bitmap_copy(ctx->bitmap, prange->bitmap_access, MAX_GPU_INSTANCE); - if (!prange->mapped_to_gpu || - bitmap_empty(ctx->bitmap, MAX_GPU_INSTANCE)) { - r = 0; - goto free_ctx; - } + r = 0; + goto free_ctx; } if (prange->actual_loc && !prange->ttm_res) { diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index b452796fc6d3..4e82ee4d74ac 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -5182,6 +5182,9 @@ static void fill_dc_dirty_rects(struct drm_plane *plane, if (plane->type == DRM_PLANE_TYPE_CURSOR) return; + if (new_plane_state->rotation != DRM_MODE_ROTATE_0) + goto ffu; + num_clips = drm_plane_get_damage_clips_count(new_plane_state); clips = drm_plane_get_damage_clips(new_plane_state); @@ -6167,8 +6170,9 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector, if (stream->signal == SIGNAL_TYPE_HDMI_TYPE_A) mod_build_hf_vsif_infopacket(stream, &stream->vsp_infopacket); - - if (stream->link->psr_settings.psr_feature_enabled || stream->link->replay_settings.replay_feature_enabled) { + else if (stream->signal == SIGNAL_TYPE_DISPLAY_PORT || + stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST || + stream->signal == SIGNAL_TYPE_EDP) { // // should decide stream support vsc sdp colorimetry capability // before building vsc info packet @@ -6184,8 +6188,9 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector, if (stream->out_transfer_func->tf == TRANSFER_FUNCTION_GAMMA22) tf = TRANSFER_FUNC_GAMMA_22; mod_build_vsc_infopacket(stream, &stream->vsc_infopacket, stream->output_color_space, tf); - aconnector->psr_skip_count = AMDGPU_DM_PSR_ENTRY_DELAY; + if (stream->link->psr_settings.psr_feature_enabled) + aconnector->psr_skip_count = AMDGPU_DM_PSR_ENTRY_DELAY; } finish: dc_sink_release(sink); @@ -6911,8 +6916,7 @@ static int dm_encoder_helper_atomic_check(struct drm_encoder *encoder, if (IS_ERR(mst_state)) return PTR_ERR(mst_state); - if (!mst_state->pbn_div) - mst_state->pbn_div = dm_mst_get_pbn_divider(aconnector->mst_root->dc_link); + mst_state->pbn_div = dm_mst_get_pbn_divider(aconnector->mst_root->dc_link); if (!state->duplicated) { int max_bpc = conn_state->max_requested_bpc; diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c index 6a96810a477e..2d1f5efa9091 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c +++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c @@ -1014,13 +1014,20 @@ static enum bp_result get_ss_info_v4_5( DC_LOG_BIOS("AS_SIGNAL_TYPE_HDMI ss_percentage: %d\n", ss_info->spread_spectrum_percentage); break; case AS_SIGNAL_TYPE_DISPLAY_PORT: - ss_info->spread_spectrum_percentage = + if (bp->base.integrated_info) { + DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", bp->base.integrated_info->gpuclk_ss_percentage); + ss_info->spread_spectrum_percentage = + bp->base.integrated_info->gpuclk_ss_percentage; + ss_info->type.CENTER_MODE = + bp->base.integrated_info->gpuclk_ss_type; + } else { + ss_info->spread_spectrum_percentage = disp_cntl_tbl->dp_ss_percentage; - ss_info->spread_spectrum_range = + ss_info->spread_spectrum_range = disp_cntl_tbl->dp_ss_rate_10hz * 10; - if (disp_cntl_tbl->dp_ss_mode & ATOM_SS_CENTRE_SPREAD_MODE) - ss_info->type.CENTER_MODE = true; - + if (disp_cntl_tbl->dp_ss_mode & ATOM_SS_CENTRE_SPREAD_MODE) + ss_info->type.CENTER_MODE = true; + } DC_LOG_BIOS("AS_SIGNAL_TYPE_DISPLAY_PORT ss_percentage: %d\n", ss_info->spread_spectrum_percentage); break; case AS_SIGNAL_TYPE_GPU_PLL: @@ -2386,13 +2393,7 @@ static enum bp_result get_vram_info_v30( return BP_RESULT_BADBIOSTABLE; info->num_chans = info_v30->channel_num; - /* As suggested by VBIOS we should always use - * dram_channel_width_bytes = 2 when using VRAM - * table version 3.0. This is because the channel_width - * param in the VRAM info table is changed in 7000 series and - * no longer represents the memory channel width. - */ - info->dram_channel_width_bytes = 2; + info->dram_channel_width_bytes = (1 << info_v30->channel_width) / 8; return result; } @@ -2820,6 +2821,8 @@ static enum bp_result get_integrated_info_v2_2( info->ma_channel_number = info_v2_2->umachannelnumber; info->dp_ss_control = le16_to_cpu(info_v2_2->reserved1); + info->gpuclk_ss_percentage = info_v2_2->gpuclk_ss_percentage; + info->gpuclk_ss_type = info_v2_2->gpuclk_ss_type; for (i = 0; i < NUMBER_OF_UCHAR_FOR_GUID; ++i) { info->ext_disp_conn_info.gu_id[i] = diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 76b47f178127..5c1185206645 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -5095,18 +5095,28 @@ void dc_mclk_switch_using_fw_based_vblank_stretch_shut_down(struct dc *dc) */ bool dc_is_dmub_outbox_supported(struct dc *dc) { - /* DCN31 B0 USB4 DPIA needs dmub notifications for interrupts */ - if (dc->ctx->asic_id.chip_family == FAMILY_YELLOW_CARP && - dc->ctx->asic_id.hw_internal_rev == YELLOW_CARP_B0 && - !dc->debug.dpia_debug.bits.disable_dpia) - return true; + switch (dc->ctx->asic_id.chip_family) { - if (dc->ctx->asic_id.chip_family == AMDGPU_FAMILY_GC_11_0_1 && - !dc->debug.dpia_debug.bits.disable_dpia) - return true; + case FAMILY_YELLOW_CARP: + /* DCN31 B0 USB4 DPIA needs dmub notifications for interrupts */ + if (dc->ctx->asic_id.hw_internal_rev == YELLOW_CARP_B0 && + !dc->debug.dpia_debug.bits.disable_dpia) + return true; + break; + + case AMDGPU_FAMILY_GC_11_0_1: + case AMDGPU_FAMILY_GC_11_5_0: + if (!dc->debug.dpia_debug.bits.disable_dpia) + return true; + break; + + default: + break; + } /* dmub aux needs dmub notifications to be enabled */ return dc->debug.enable_dmub_aux_for_legacy_ddc; + } /** diff --git a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h index 9649934ea186..e2a3aa8812df 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h @@ -465,6 +465,7 @@ struct dc_cursor_mi_param { struct fixed31_32 v_scale_ratio; enum dc_rotation_angle rotation; bool mirror; + struct dc_stream_state *stream; }; /* IPP related types */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c index 139cf31d2e45..89c3bf0fe0c9 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c @@ -1077,8 +1077,16 @@ void hubp2_cursor_set_position( if (src_y_offset < 0) src_y_offset = 0; /* Save necessary cursor info x, y position. w, h is saved in attribute func. */ - hubp->cur_rect.x = src_x_offset + param->viewport.x; - hubp->cur_rect.y = src_y_offset + param->viewport.y; + if (param->stream->link->psr_settings.psr_version >= DC_PSR_VERSION_SU_1 && + param->rotation != ROTATION_ANGLE_0) { + hubp->cur_rect.x = 0; + hubp->cur_rect.y = 0; + hubp->cur_rect.w = param->stream->timing.h_addressable; + hubp->cur_rect.h = param->stream->timing.v_addressable; + } else { + hubp->cur_rect.x = src_x_offset + param->viewport.x; + hubp->cur_rect.y = src_y_offset + param->viewport.y; + } } void hubp2_clk_cntl(struct hubp *hubp, bool enable) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c index ec77b2b41ba3..d2271e308fa0 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c @@ -440,7 +440,115 @@ struct _vcs_dpi_soc_bounding_box_st dcn2_0_nv14_soc = { .use_urgent_burst_bw = 0 }; -struct _vcs_dpi_soc_bounding_box_st dcn2_0_nv12_soc = { 0 }; +struct _vcs_dpi_soc_bounding_box_st dcn2_0_nv12_soc = { + .clock_limits = { + { + .state = 0, + .dcfclk_mhz = 560.0, + .fabricclk_mhz = 560.0, + .dispclk_mhz = 513.0, + .dppclk_mhz = 513.0, + .phyclk_mhz = 540.0, + .socclk_mhz = 560.0, + .dscclk_mhz = 171.0, + .dram_speed_mts = 1069.0, + }, + { + .state = 1, + .dcfclk_mhz = 694.0, + .fabricclk_mhz = 694.0, + .dispclk_mhz = 642.0, + .dppclk_mhz = 642.0, + .phyclk_mhz = 600.0, + .socclk_mhz = 694.0, + .dscclk_mhz = 214.0, + .dram_speed_mts = 1324.0, + }, + { + .state = 2, + .dcfclk_mhz = 875.0, + .fabricclk_mhz = 875.0, + .dispclk_mhz = 734.0, + .dppclk_mhz = 734.0, + .phyclk_mhz = 810.0, + .socclk_mhz = 875.0, + .dscclk_mhz = 245.0, + .dram_speed_mts = 1670.0, + }, + { + .state = 3, + .dcfclk_mhz = 1000.0, + .fabricclk_mhz = 1000.0, + .dispclk_mhz = 1100.0, + .dppclk_mhz = 1100.0, + .phyclk_mhz = 810.0, + .socclk_mhz = 1000.0, + .dscclk_mhz = 367.0, + .dram_speed_mts = 2000.0, + }, + { + .state = 4, + .dcfclk_mhz = 1200.0, + .fabricclk_mhz = 1200.0, + .dispclk_mhz = 1284.0, + .dppclk_mhz = 1284.0, + .phyclk_mhz = 810.0, + .socclk_mhz = 1200.0, + .dscclk_mhz = 428.0, + .dram_speed_mts = 2000.0, + }, + { + .state = 5, + .dcfclk_mhz = 1200.0, + .fabricclk_mhz = 1200.0, + .dispclk_mhz = 1284.0, + .dppclk_mhz = 1284.0, + .phyclk_mhz = 810.0, + .socclk_mhz = 1200.0, + .dscclk_mhz = 428.0, + .dram_speed_mts = 2000.0, + }, + }, + + .num_states = 5, + .sr_exit_time_us = 1.9, + .sr_enter_plus_exit_time_us = 4.4, + .urgent_latency_us = 3.0, + .urgent_latency_pixel_data_only_us = 4.0, + .urgent_latency_pixel_mixed_with_vm_data_us = 4.0, + .urgent_latency_vm_data_only_us = 4.0, + .urgent_out_of_order_return_per_channel_pixel_only_bytes = 4096, + .urgent_out_of_order_return_per_channel_pixel_and_vm_bytes = 4096, + .urgent_out_of_order_return_per_channel_vm_only_bytes = 4096, + .pct_ideal_dram_sdp_bw_after_urgent_pixel_only = 40.0, + .pct_ideal_dram_sdp_bw_after_urgent_pixel_and_vm = 40.0, + .pct_ideal_dram_sdp_bw_after_urgent_vm_only = 40.0, + .max_avg_sdp_bw_use_normal_percent = 40.0, + .max_avg_dram_bw_use_normal_percent = 40.0, + .writeback_latency_us = 12.0, + .ideal_dram_bw_after_urgent_percent = 40.0, + .max_request_size_bytes = 256, + .dram_channel_width_bytes = 16, + .fabric_datapath_to_dcn_data_return_bytes = 64, + .dcn_downspread_percent = 0.5, + .downspread_percent = 0.5, + .dram_page_open_time_ns = 50.0, + .dram_rw_turnaround_time_ns = 17.5, + .dram_return_buffer_per_channel_bytes = 8192, + .round_trip_ping_latency_dcfclk_cycles = 131, + .urgent_out_of_order_return_per_channel_bytes = 4096, + .channel_interleave_bytes = 256, + .num_banks = 8, + .num_chans = 16, + .vmm_page_size_bytes = 4096, + .dram_clock_change_latency_us = 45.0, + .writeback_dram_clock_change_latency_us = 23.0, + .return_bus_width_bytes = 64, + .dispclk_dppclk_vco_speed_mhz = 3850, + .xfc_bus_transport_time_us = 20, + .xfc_xbuf_latency_tolerance_us = 50, + .use_urgent_burst_bw = 0, +}; struct _vcs_dpi_ip_params_st dcn2_1_ip = { .odm_capable = 1, diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c index 39cf1ae3a3e1..f154a3eb1d1a 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c @@ -124,7 +124,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_5_soc = { .phyclk_mhz = 600.0, .phyclk_d18_mhz = 667.0, .dscclk_mhz = 186.0, - .dtbclk_mhz = 625.0, + .dtbclk_mhz = 600.0, }, { .state = 1, @@ -133,7 +133,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_5_soc = { .phyclk_mhz = 810.0, .phyclk_d18_mhz = 667.0, .dscclk_mhz = 209.0, - .dtbclk_mhz = 625.0, + .dtbclk_mhz = 600.0, }, { .state = 2, @@ -142,7 +142,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_5_soc = { .phyclk_mhz = 810.0, .phyclk_d18_mhz = 667.0, .dscclk_mhz = 209.0, - .dtbclk_mhz = 625.0, + .dtbclk_mhz = 600.0, }, { .state = 3, @@ -151,7 +151,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_5_soc = { .phyclk_mhz = 810.0, .phyclk_d18_mhz = 667.0, .dscclk_mhz = 371.0, - .dtbclk_mhz = 625.0, + .dtbclk_mhz = 600.0, }, { .state = 4, @@ -160,7 +160,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_5_soc = { .phyclk_mhz = 810.0, .phyclk_d18_mhz = 667.0, .dscclk_mhz = 417.0, - .dtbclk_mhz = 625.0, + .dtbclk_mhz = 600.0, }, }, .num_states = 5, @@ -348,6 +348,8 @@ void dcn35_update_bw_bounding_box_fpu(struct dc *dc, clock_limits[i].socclk_mhz; dc->dml2_options.bbox_overrides.clks_table.clk_entries[i].memclk_mhz = clk_table->entries[i].memclk_mhz * clk_table->entries[i].wck_ratio; + dc->dml2_options.bbox_overrides.clks_table.clk_entries[i].dtbclk_mhz = + clock_limits[i].dtbclk_mhz; dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_dcfclk_levels = clk_table->num_entries; dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_fclk_levels = @@ -360,6 +362,8 @@ void dcn35_update_bw_bounding_box_fpu(struct dc *dc, clk_table->num_entries; dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_memclk_levels = clk_table->num_entries; + dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_dtbclk_levels = + clk_table->num_entries; } } diff --git a/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c b/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c index 4d1336e5afc2..b95bf27f2fe2 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c @@ -5420,7 +5420,7 @@ static void CalculateOutputLink( *OutBpp = TruncToValidBPP((1 - Downspreading / 100) * 13500, OutputLinkDPLanes, HTotal, HActive, PixelClockBackEnd, ForcedOutputLinkBPP, LinkDSCEnable, Output, OutputFormat, DSCInputBitPerComponent, NumberOfDSCSlices, (dml_uint_t)AudioSampleRate, AudioSampleLayout, ODMModeNoDSC, ODMModeDSC, RequiredSlots); - if (OutBpp == 0 && PHYCLKD32PerState < 20000 / 32 && DSCEnable == dml_dsc_enable_if_necessary && ForcedOutputLinkBPP == 0) { + if (*OutBpp == 0 && PHYCLKD32PerState < 20000 / 32 && DSCEnable == dml_dsc_enable_if_necessary && ForcedOutputLinkBPP == 0) { *RequiresDSC = true; LinkDSCEnable = true; *OutBpp = TruncToValidBPP((1 - Downspreading / 100) * 13500, OutputLinkDPLanes, HTotal, HActive, PixelClockBackEnd, ForcedOutputLinkBPP, LinkDSCEnable, Output, @@ -6329,7 +6329,7 @@ static void dml_prefetch_check(struct display_mode_lib_st *mode_lib) mode_lib->ms.NoOfDPPThisState, mode_lib->ms.dpte_group_bytes, s->HostVMInefficiencyFactor, - mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024, + mode_lib->ms.soc.hostvm_min_page_size_kbytes, mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels); s->NextMaxVStartup = s->MaxVStartupAllPlanes[j]; @@ -6542,7 +6542,7 @@ static void dml_prefetch_check(struct display_mode_lib_st *mode_lib) mode_lib->ms.cache_display_cfg.plane.HostVMEnable, mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels, mode_lib->ms.cache_display_cfg.plane.GPUVMEnable, - mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024, + mode_lib->ms.soc.hostvm_min_page_size_kbytes, mode_lib->ms.PDEAndMetaPTEBytesPerFrame[j][k], mode_lib->ms.MetaRowBytes[j][k], mode_lib->ms.DPTEBytesPerRow[j][k], @@ -7687,7 +7687,7 @@ dml_bool_t dml_core_mode_support(struct display_mode_lib_st *mode_lib) CalculateVMRowAndSwath_params->HostVMMaxNonCachedPageTableLevels = mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels; CalculateVMRowAndSwath_params->GPUVMMaxPageTableLevels = mode_lib->ms.cache_display_cfg.plane.GPUVMMaxPageTableLevels; CalculateVMRowAndSwath_params->GPUVMMinPageSizeKBytes = mode_lib->ms.cache_display_cfg.plane.GPUVMMinPageSizeKBytes; - CalculateVMRowAndSwath_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024; + CalculateVMRowAndSwath_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes; CalculateVMRowAndSwath_params->PTEBufferModeOverrideEn = mode_lib->ms.cache_display_cfg.plane.PTEBufferModeOverrideEn; CalculateVMRowAndSwath_params->PTEBufferModeOverrideVal = mode_lib->ms.cache_display_cfg.plane.PTEBufferMode; CalculateVMRowAndSwath_params->PTEBufferSizeNotExceeded = mode_lib->ms.PTEBufferSizeNotExceededPerState; @@ -7957,7 +7957,7 @@ dml_bool_t dml_core_mode_support(struct display_mode_lib_st *mode_lib) UseMinimumDCFCLK_params->GPUVMMaxPageTableLevels = mode_lib->ms.cache_display_cfg.plane.GPUVMMaxPageTableLevels; UseMinimumDCFCLK_params->HostVMEnable = mode_lib->ms.cache_display_cfg.plane.HostVMEnable; UseMinimumDCFCLK_params->NumberOfActiveSurfaces = mode_lib->ms.num_active_planes; - UseMinimumDCFCLK_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024; + UseMinimumDCFCLK_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes; UseMinimumDCFCLK_params->HostVMMaxNonCachedPageTableLevels = mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels; UseMinimumDCFCLK_params->DynamicMetadataVMEnabled = mode_lib->ms.ip.dynamic_metadata_vm_enabled; UseMinimumDCFCLK_params->ImmediateFlipRequirement = s->ImmediateFlipRequiredFinal; @@ -8699,7 +8699,7 @@ void dml_core_mode_programming(struct display_mode_lib_st *mode_lib, const struc CalculateVMRowAndSwath_params->HostVMMaxNonCachedPageTableLevels = mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels; CalculateVMRowAndSwath_params->GPUVMMaxPageTableLevels = mode_lib->ms.cache_display_cfg.plane.GPUVMMaxPageTableLevels; CalculateVMRowAndSwath_params->GPUVMMinPageSizeKBytes = mode_lib->ms.cache_display_cfg.plane.GPUVMMinPageSizeKBytes; - CalculateVMRowAndSwath_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024; + CalculateVMRowAndSwath_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes; CalculateVMRowAndSwath_params->PTEBufferModeOverrideEn = mode_lib->ms.cache_display_cfg.plane.PTEBufferModeOverrideEn; CalculateVMRowAndSwath_params->PTEBufferModeOverrideVal = mode_lib->ms.cache_display_cfg.plane.PTEBufferMode; CalculateVMRowAndSwath_params->PTEBufferSizeNotExceeded = s->dummy_boolean_array[0]; @@ -8805,7 +8805,7 @@ void dml_core_mode_programming(struct display_mode_lib_st *mode_lib, const struc mode_lib->ms.cache_display_cfg.hw.DPPPerSurface, locals->dpte_group_bytes, s->HostVMInefficiencyFactor, - mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024, + mode_lib->ms.soc.hostvm_min_page_size_kbytes, mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels); locals->TCalc = 24.0 / locals->DCFCLKDeepSleep; @@ -8995,7 +8995,7 @@ void dml_core_mode_programming(struct display_mode_lib_st *mode_lib, const struc CalculatePrefetchSchedule_params->GPUVMEnable = mode_lib->ms.cache_display_cfg.plane.GPUVMEnable; CalculatePrefetchSchedule_params->HostVMEnable = mode_lib->ms.cache_display_cfg.plane.HostVMEnable; CalculatePrefetchSchedule_params->HostVMMaxNonCachedPageTableLevels = mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels; - CalculatePrefetchSchedule_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024; + CalculatePrefetchSchedule_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes; CalculatePrefetchSchedule_params->DynamicMetadataEnable = mode_lib->ms.cache_display_cfg.plane.DynamicMetadataEnable[k]; CalculatePrefetchSchedule_params->DynamicMetadataVMEnabled = mode_lib->ms.ip.dynamic_metadata_vm_enabled; CalculatePrefetchSchedule_params->DynamicMetadataLinesBeforeActiveRequired = mode_lib->ms.cache_display_cfg.plane.DynamicMetadataLinesBeforeActiveRequired[k]; @@ -9240,7 +9240,7 @@ void dml_core_mode_programming(struct display_mode_lib_st *mode_lib, const struc mode_lib->ms.cache_display_cfg.plane.HostVMEnable, mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels, mode_lib->ms.cache_display_cfg.plane.GPUVMEnable, - mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024, + mode_lib->ms.soc.hostvm_min_page_size_kbytes, locals->PDEAndMetaPTEBytesFrame[k], locals->MetaRowByte[k], locals->PixelPTEBytesPerRow[k], diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c index fa8fe5bf7e57..db06a5b749b4 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c @@ -423,8 +423,9 @@ void dml2_init_soc_states(struct dml2_context *dml2, const struct dc *in_dc, } for (i = 0; i < dml2->config.bbox_overrides.clks_table.num_entries_per_clk.num_dtbclk_levels; i++) { - p->in_states->state_array[i].dtbclk_mhz = - dml2->config.bbox_overrides.clks_table.clk_entries[i].dtbclk_mhz; + if (dml2->config.bbox_overrides.clks_table.clk_entries[i].dtbclk_mhz > 0) + p->in_states->state_array[i].dtbclk_mhz = + dml2->config.bbox_overrides.clks_table.clk_entries[i].dtbclk_mhz; } for (i = 0; i < dml2->config.bbox_overrides.clks_table.num_entries_per_clk.num_dispclk_levels; i++) { diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c index 2b8b8366538e..cdb903116eb7 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c @@ -3417,7 +3417,8 @@ void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx) .h_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.horz, .v_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.vert, .rotation = pipe_ctx->plane_state->rotation, - .mirror = pipe_ctx->plane_state->horizontal_mirror + .mirror = pipe_ctx->plane_state->horizontal_mirror, + .stream = pipe_ctx->stream, }; bool pipe_split_on = false; bool odm_combine_on = (pipe_ctx->next_odm_pipe != NULL) || diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c index 5f7f474ef51c..c1a9b746c43f 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c @@ -960,6 +960,12 @@ void dcn32_init_hw(struct dc *dc) dc->caps.dmub_caps.subvp_psr = dc->ctx->dmub_srv->dmub->feature_caps.subvp_psr_support; dc->caps.dmub_caps.gecc_enable = dc->ctx->dmub_srv->dmub->feature_caps.gecc_enable; dc->caps.dmub_caps.mclk_sw = dc->ctx->dmub_srv->dmub->feature_caps.fw_assisted_mclk_switch; + + if (dc->ctx->dmub_srv->dmub->fw_version < + DMUB_FW_VERSION(7, 0, 35)) { + dc->debug.force_disable_subvp = true; + dc->debug.disable_fpo_optimizations = true; + } } } diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c index 996e4ee99023..e5cfaaef70b3 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c @@ -287,8 +287,8 @@ bool set_default_brightness_aux(struct dc_link *link) if (link && link->dpcd_sink_ext_caps.bits.oled == 1) { if (!read_default_bl_aux(link, &default_backlight)) default_backlight = 150000; - // if > 5000, it might be wrong readback - if (default_backlight > 5000000) + // if < 1 nits or > 5000, it might be wrong readback + if (default_backlight < 1000 || default_backlight > 5000000) default_backlight = 150000; return edp_set_backlight_level_nits(link, true, diff --git a/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h b/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h index bc96d0211360..813463ffe15c 100644 --- a/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h +++ b/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h @@ -417,6 +417,8 @@ struct integrated_info { /* V2.1 */ struct edp_info edp1_info; struct edp_info edp2_info; + uint32_t gpuclk_ss_percentage; + uint32_t gpuclk_ss_type; }; /* diff --git a/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c b/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c index 84f9b412a4f1..738ee763f24a 100644 --- a/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c +++ b/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c @@ -147,12 +147,15 @@ void mod_build_vsc_infopacket(const struct dc_stream_state *stream, } /* VSC packet set to 4 for PSR-SU, or 2 for PSR1 */ - if (stream->link->psr_settings.psr_version == DC_PSR_VERSION_SU_1) - vsc_packet_revision = vsc_packet_rev4; - else if (stream->link->replay_settings.config.replay_supported) + if (stream->link->psr_settings.psr_feature_enabled) { + if (stream->link->psr_settings.psr_version == DC_PSR_VERSION_SU_1) + vsc_packet_revision = vsc_packet_rev4; + else if (stream->link->psr_settings.psr_version == DC_PSR_VERSION_1) + vsc_packet_revision = vsc_packet_rev2; + } + + if (stream->link->replay_settings.config.replay_supported) vsc_packet_revision = vsc_packet_rev4; - else if (stream->link->psr_settings.psr_version == DC_PSR_VERSION_1) - vsc_packet_revision = vsc_packet_rev2; /* Update to revision 5 for extended colorimetry support */ if (stream->use_vsc_sdp_for_colorimetry) diff --git a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c index a522a7c02911..1675314a3ff2 100644 --- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c +++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c @@ -839,6 +839,8 @@ bool is_psr_su_specific_panel(struct dc_link *link) ((dpcd_caps->sink_dev_id_str[1] == 0x08 && dpcd_caps->sink_dev_id_str[0] == 0x08) || (dpcd_caps->sink_dev_id_str[1] == 0x08 && dpcd_caps->sink_dev_id_str[0] == 0x07))) isPSRSUSupported = false; + else if (dpcd_caps->sink_dev_id_str[1] == 0x08 && dpcd_caps->sink_dev_id_str[0] == 0x03) + isPSRSUSupported = false; else if (dpcd_caps->psr_info.force_psrsu_cap == 0x1) isPSRSUSupported = true; } diff --git a/drivers/gpu/drm/amd/include/kgd_pp_interface.h b/drivers/gpu/drm/amd/include/kgd_pp_interface.h index 1c5049e894e3..c2ccf3724e37 100644 --- a/drivers/gpu/drm/amd/include/kgd_pp_interface.h +++ b/drivers/gpu/drm/amd/include/kgd_pp_interface.h @@ -318,6 +318,7 @@ enum pp_xgmi_plpd_mode { #define MAX_GFX_CLKS 8 #define MAX_CLKS 4 #define NUM_VCN 4 +#define NUM_JPEG_ENG 32 struct seq_file; enum amd_pp_clock_type; @@ -774,6 +775,85 @@ struct gpu_metrics_v1_4 { uint16_t padding; }; +struct gpu_metrics_v1_5 { + struct metrics_table_header common_header; + + /* Temperature (Celsius) */ + uint16_t temperature_hotspot; + uint16_t temperature_mem; + uint16_t temperature_vrsoc; + + /* Power (Watts) */ + uint16_t curr_socket_power; + + /* Utilization (%) */ + uint16_t average_gfx_activity; + uint16_t average_umc_activity; // memory controller + uint16_t vcn_activity[NUM_VCN]; + uint16_t jpeg_activity[NUM_JPEG_ENG]; + + /* Energy (15.259uJ (2^-16) units) */ + uint64_t energy_accumulator; + + /* Driver attached timestamp (in ns) */ + uint64_t system_clock_counter; + + /* Throttle status */ + uint32_t throttle_status; + + /* Clock Lock Status. Each bit corresponds to clock instance */ + uint32_t gfxclk_lock_status; + + /* Link width (number of lanes) and speed (in 0.1 GT/s) */ + uint16_t pcie_link_width; + uint16_t pcie_link_speed; + + /* XGMI bus width and bitrate (in Gbps) */ + uint16_t xgmi_link_width; + uint16_t xgmi_link_speed; + + /* Utilization Accumulated (%) */ + uint32_t gfx_activity_acc; + uint32_t mem_activity_acc; + + /*PCIE accumulated bandwidth (GB/sec) */ + uint64_t pcie_bandwidth_acc; + + /*PCIE instantaneous bandwidth (GB/sec) */ + uint64_t pcie_bandwidth_inst; + + /* PCIE L0 to recovery state transition accumulated count */ + uint64_t pcie_l0_to_recov_count_acc; + + /* PCIE replay accumulated count */ + uint64_t pcie_replay_count_acc; + + /* PCIE replay rollover accumulated count */ + uint64_t pcie_replay_rover_count_acc; + + /* PCIE NAK sent accumulated count */ + uint32_t pcie_nak_sent_count_acc; + + /* PCIE NAK received accumulated count */ + uint32_t pcie_nak_rcvd_count_acc; + + /* XGMI accumulated data transfer size(KiloBytes) */ + uint64_t xgmi_read_data_acc[NUM_XGMI_LINKS]; + uint64_t xgmi_write_data_acc[NUM_XGMI_LINKS]; + + /* PMFW attached timestamp (10ns resolution) */ + uint64_t firmware_timestamp; + + /* Current clocks (Mhz) */ + uint16_t current_gfxclk[MAX_GFX_CLKS]; + uint16_t current_socclk[MAX_CLKS]; + uint16_t current_vclk0[MAX_CLKS]; + uint16_t current_dclk0[MAX_CLKS]; + uint16_t current_uclk; + + uint16_t padding; +}; + /* * gpu_metrics_v2_0 is not recommended as it's not naturally aligned. * Use gpu_metrics_v2_1 or later instead. diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c index ca2ece24e1e0..20c53eefd680 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c @@ -2128,7 +2128,9 @@ static int default_attr_update(struct amdgpu_device *adev, struct amdgpu_device_ if (amdgpu_dpm_is_overdrive_supported(adev)) *states = ATTR_STATE_SUPPORTED; } else if (DEVICE_ATTR_IS(mem_busy_percent)) { - if (adev->flags & AMD_IS_APU || gc_ver == IP_VERSION(9, 0, 1)) + if ((adev->flags & AMD_IS_APU && + gc_ver != IP_VERSION(9, 4, 3)) || + gc_ver == IP_VERSION(9, 0, 1)) *states = ATTR_STATE_UNSUPPORTED; } else if (DEVICE_ATTR_IS(pcie_bw)) { /* PCIe Perf counters won't work on APU nodes */ @@ -2198,10 +2200,10 @@ static int default_attr_update(struct amdgpu_device *adev, struct amdgpu_device_ } else if (DEVICE_ATTR_IS(xgmi_plpd_policy)) { if (amdgpu_dpm_get_xgmi_plpd_mode(adev, NULL) == XGMI_PLPD_NONE) *states = ATTR_STATE_UNSUPPORTED; - } else if (DEVICE_ATTR_IS(pp_dpm_mclk_od)) { + } else if (DEVICE_ATTR_IS(pp_mclk_od)) { if (amdgpu_dpm_get_mclk_od(adev) == -EOPNOTSUPP) *states = ATTR_STATE_UNSUPPORTED; - } else if (DEVICE_ATTR_IS(pp_dpm_sclk_od)) { + } else if (DEVICE_ATTR_IS(pp_sclk_od)) { if (amdgpu_dpm_get_sclk_od(adev) == -EOPNOTSUPP) *states = ATTR_STATE_UNSUPPORTED; } else if (DEVICE_ATTR_IS(apu_thermal_cap)) { diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h index fef2d290f3f2..7b812b9994d7 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h @@ -123,7 +123,7 @@ typedef enum { VOLTAGE_GUARDBAND_COUNT } GFX_GUARDBAND_e; -#define SMU_METRICS_TABLE_VERSION 0x9 +#define SMU_METRICS_TABLE_VERSION 0xB typedef struct __attribute__((packed, aligned(4))) { uint32_t AccumulationCounter; @@ -219,7 +219,103 @@ typedef struct __attribute__((packed, aligned(4))) { uint32_t PCIenReplayARolloverCountAcc; // The Pcie counter itself is accumulated uint32_t PCIeNAKSentCountAcc; // The Pcie counter itself is accumulated uint32_t PCIeNAKReceivedCountAcc; // The Pcie counter itself is accumulated -} MetricsTable_t; + + // VCN/JPEG ACTIVITY + uint32_t VcnBusy[4]; + uint32_t JpegBusy[32]; +} MetricsTableX_t; + +typedef struct __attribute__((packed, aligned(4))) { + uint32_t AccumulationCounter; + + //TEMPERATURE + uint32_t MaxSocketTemperature; + uint32_t MaxVrTemperature; + uint32_t MaxHbmTemperature; + uint64_t MaxSocketTemperatureAcc; + uint64_t MaxVrTemperatureAcc; + uint64_t MaxHbmTemperatureAcc; + + //POWER + uint32_t SocketPowerLimit; + uint32_t MaxSocketPowerLimit; + uint32_t SocketPower; + + //ENERGY + uint64_t Timestamp; + uint64_t SocketEnergyAcc; + uint64_t CcdEnergyAcc; + uint64_t XcdEnergyAcc; + uint64_t AidEnergyAcc; + uint64_t HbmEnergyAcc; + + //FREQUENCY + uint32_t CclkFrequencyLimit; + uint32_t GfxclkFrequencyLimit; + uint32_t FclkFrequency; + uint32_t UclkFrequency; + uint32_t SocclkFrequency[4]; + uint32_t VclkFrequency[4]; + uint32_t DclkFrequency[4]; + uint32_t LclkFrequency[4]; + uint64_t GfxclkFrequencyAcc[8]; + uint64_t CclkFrequencyAcc[96]; + + //FREQUENCY RANGE + uint32_t MaxCclkFrequency; + uint32_t MinCclkFrequency; + uint32_t MaxGfxclkFrequency; + uint32_t MinGfxclkFrequency; + uint32_t FclkFrequencyTable[4]; + uint32_t UclkFrequencyTable[4]; + uint32_t SocclkFrequencyTable[4]; + uint32_t VclkFrequencyTable[4]; + uint32_t DclkFrequencyTable[4]; + uint32_t LclkFrequencyTable[4]; + uint32_t MaxLclkDpmRange; + uint32_t MinLclkDpmRange; + + //XGMI + uint32_t XgmiWidth; + uint32_t XgmiBitrate; + uint64_t XgmiReadBandwidthAcc[8]; + uint64_t XgmiWriteBandwidthAcc[8]; + + //ACTIVITY + uint32_t SocketC0Residency; + uint32_t SocketGfxBusy; + uint32_t DramBandwidthUtilization; + uint64_t SocketC0ResidencyAcc; + uint64_t SocketGfxBusyAcc; + uint64_t DramBandwidthAcc; + uint32_t MaxDramBandwidth; + uint64_t DramBandwidthUtilizationAcc; + uint64_t PcieBandwidthAcc[4]; + + //THROTTLERS + uint32_t ProchotResidencyAcc; + uint32_t PptResidencyAcc; + uint32_t SocketThmResidencyAcc; + uint32_t VrThmResidencyAcc; + uint32_t HbmThmResidencyAcc; + uint32_t GfxLockXCDMak; + + // New Items at end to maintain driver compatibility + uint32_t GfxclkFrequency[8]; + + //PSNs + uint64_t PublicSerialNumber_AID[4]; + uint64_t PublicSerialNumber_XCD[8]; + uint64_t PublicSerialNumber_CCD[12]; + + //XGMI Data tranfser size + uint64_t XgmiReadDataSizeAcc[8];//in KByte + uint64_t XgmiWriteDataSizeAcc[8];//in KByte + + // VCN/JPEG ACTIVITY + uint32_t VcnBusy[4]; + uint32_t JpegBusy[32]; +} MetricsTableA_t; #define SMU_VF_METRICS_TABLE_VERSION 0x3 diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c index 900a2d9e6d85..b64e07b75937 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c @@ -245,6 +245,8 @@ struct PPTable_t { #define SMUQ10_TO_UINT(x) ((x) >> 10) #define SMUQ10_FRAC(x) ((x) & 0x3ff) #define SMUQ10_ROUND(x) ((SMUQ10_TO_UINT(x)) + ((SMUQ10_FRAC(x)) >= 0x200)) +#define GET_METRIC_FIELD(field) ((adev->flags & AMD_IS_APU) ?\ + (metrics_a->field) : (metrics_x->field)) struct smu_v13_0_6_dpm_map { enum smu_clk_type clk_type; @@ -327,7 +329,8 @@ static int smu_v13_0_6_tables_init(struct smu_context *smu) SMU_TABLE_INIT(tables, SMU_TABLE_PMSTATUSLOG, SMU13_TOOL_SIZE, PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM); - SMU_TABLE_INIT(tables, SMU_TABLE_SMU_METRICS, sizeof(MetricsTable_t), + SMU_TABLE_INIT(tables, SMU_TABLE_SMU_METRICS, + max(sizeof(MetricsTableX_t), sizeof(MetricsTableA_t)), PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM | AMDGPU_GEM_DOMAIN_GTT); @@ -335,12 +338,13 @@ static int smu_v13_0_6_tables_init(struct smu_context *smu) PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM | AMDGPU_GEM_DOMAIN_GTT); - smu_table->metrics_table = kzalloc(sizeof(MetricsTable_t), GFP_KERNEL); + smu_table->metrics_table = kzalloc(max(sizeof(MetricsTableX_t), + sizeof(MetricsTableA_t)), GFP_KERNEL); if (!smu_table->metrics_table) return -ENOMEM; smu_table->metrics_time = 0; - smu_table->gpu_metrics_table_size = sizeof(struct gpu_metrics_v1_4); + smu_table->gpu_metrics_table_size = sizeof(struct gpu_metrics_v1_5); smu_table->gpu_metrics_table = kzalloc(smu_table->gpu_metrics_table_size, GFP_KERNEL); if (!smu_table->gpu_metrics_table) { @@ -431,9 +435,11 @@ static int smu_v13_0_6_get_metrics_table(struct smu_context *smu, static int smu_v13_0_6_setup_driver_pptable(struct smu_context *smu) { struct smu_table_context *smu_table = &smu->smu_table; - MetricsTable_t *metrics = (MetricsTable_t *)smu_table->metrics_table; + MetricsTableX_t *metrics_x = (MetricsTableX_t *)smu_table->metrics_table; + MetricsTableA_t *metrics_a = (MetricsTableA_t *)smu_table->metrics_table; struct PPTable_t *pptable = (struct PPTable_t *)smu_table->driver_pptable; + struct amdgpu_device *adev = smu->adev; int ret, i, retry = 100; /* Store one-time values in driver PPTable */ @@ -444,7 +450,7 @@ static int smu_v13_0_6_setup_driver_pptable(struct smu_context *smu) return ret; /* Ensure that metrics have been updated */ - if (metrics->AccumulationCounter) + if (GET_METRIC_FIELD(AccumulationCounter)) break; usleep_range(1000, 1100); @@ -454,29 +460,29 @@ static int smu_v13_0_6_setup_driver_pptable(struct smu_context *smu) return -ETIME; pptable->MaxSocketPowerLimit = - SMUQ10_ROUND(metrics->MaxSocketPowerLimit); + SMUQ10_ROUND(GET_METRIC_FIELD(MaxSocketPowerLimit)); pptable->MaxGfxclkFrequency = - SMUQ10_ROUND(metrics->MaxGfxclkFrequency); + SMUQ10_ROUND(GET_METRIC_FIELD(MaxGfxclkFrequency)); pptable->MinGfxclkFrequency = - SMUQ10_ROUND(metrics->MinGfxclkFrequency); + SMUQ10_ROUND(GET_METRIC_FIELD(MinGfxclkFrequency)); for (i = 0; i < 4; ++i) { pptable->FclkFrequencyTable[i] = - SMUQ10_ROUND(metrics->FclkFrequencyTable[i]); + SMUQ10_ROUND(GET_METRIC_FIELD(FclkFrequencyTable)[i]); pptable->UclkFrequencyTable[i] = - SMUQ10_ROUND(metrics->UclkFrequencyTable[i]); + SMUQ10_ROUND(GET_METRIC_FIELD(UclkFrequencyTable)[i]); pptable->SocclkFrequencyTable[i] = SMUQ10_ROUND( - metrics->SocclkFrequencyTable[i]); + GET_METRIC_FIELD(SocclkFrequencyTable)[i]); pptable->VclkFrequencyTable[i] = - SMUQ10_ROUND(metrics->VclkFrequencyTable[i]); + SMUQ10_ROUND(GET_METRIC_FIELD(VclkFrequencyTable)[i]); pptable->DclkFrequencyTable[i] = - SMUQ10_ROUND(metrics->DclkFrequencyTable[i]); + SMUQ10_ROUND(GET_METRIC_FIELD(DclkFrequencyTable)[i]); pptable->LclkFrequencyTable[i] = - SMUQ10_ROUND(metrics->LclkFrequencyTable[i]); + SMUQ10_ROUND(GET_METRIC_FIELD(LclkFrequencyTable)[i]); } /* use AID0 serial number by default */ - pptable->PublicSerialNumber_AID = metrics->PublicSerialNumber_AID[0]; + pptable->PublicSerialNumber_AID = GET_METRIC_FIELD(PublicSerialNumber_AID)[0]; pptable->Init = true; } @@ -778,7 +784,8 @@ static int smu_v13_0_6_get_smu_metrics_data(struct smu_context *smu, uint32_t *value) { struct smu_table_context *smu_table = &smu->smu_table; - MetricsTable_t *metrics = (MetricsTable_t *)smu_table->metrics_table; + MetricsTableX_t *metrics_x = (MetricsTableX_t *)smu_table->metrics_table; + MetricsTableA_t *metrics_a = (MetricsTableA_t *)smu_table->metrics_table; struct amdgpu_device *adev = smu->adev; int ret = 0; int xcc_id; @@ -793,50 +800,50 @@ static int smu_v13_0_6_get_smu_metrics_data(struct smu_context *smu, case METRICS_AVERAGE_GFXCLK: if (smu->smc_fw_version >= 0x552F00) { xcc_id = GET_INST(GC, 0); - *value = SMUQ10_ROUND(metrics->GfxclkFrequency[xcc_id]); + *value = SMUQ10_ROUND(GET_METRIC_FIELD(GfxclkFrequency)[xcc_id]); } else { *value = 0; } break; case METRICS_CURR_SOCCLK: case METRICS_AVERAGE_SOCCLK: - *value = SMUQ10_ROUND(metrics->SocclkFrequency[0]); + *value = SMUQ10_ROUND(GET_METRIC_FIELD(SocclkFrequency)[0]); break; case METRICS_CURR_UCLK: case METRICS_AVERAGE_UCLK: - *value = SMUQ10_ROUND(metrics->UclkFrequency); + *value = SMUQ10_ROUND(GET_METRIC_FIELD(UclkFrequency)); break; case METRICS_CURR_VCLK: - *value = SMUQ10_ROUND(metrics->VclkFrequency[0]); + *value = SMUQ10_ROUND(GET_METRIC_FIELD(VclkFrequency)[0]); break; case METRICS_CURR_DCLK: - *value = SMUQ10_ROUND(metrics->DclkFrequency[0]); + *value = SMUQ10_ROUND(GET_METRIC_FIELD(DclkFrequency)[0]); break; case METRICS_CURR_FCLK: - *value = SMUQ10_ROUND(metrics->FclkFrequency); + *value = SMUQ10_ROUND(GET_METRIC_FIELD(FclkFrequency)); break; case METRICS_AVERAGE_GFXACTIVITY: - *value = SMUQ10_ROUND(metrics->SocketGfxBusy); + *value = SMUQ10_ROUND(GET_METRIC_FIELD(SocketGfxBusy)); break; case METRICS_AVERAGE_MEMACTIVITY: - *value = SMUQ10_ROUND(metrics->DramBandwidthUtilization); + *value = SMUQ10_ROUND(GET_METRIC_FIELD(DramBandwidthUtilization)); break; case METRICS_CURR_SOCKETPOWER: - *value = SMUQ10_ROUND(metrics->SocketPower) << 8; + *value = SMUQ10_ROUND(GET_METRIC_FIELD(SocketPower)) << 8; break; case METRICS_TEMPERATURE_HOTSPOT: - *value = SMUQ10_ROUND(metrics->MaxSocketTemperature) * + *value = SMUQ10_ROUND(GET_METRIC_FIELD(MaxSocketTemperature)) * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; break; case METRICS_TEMPERATURE_MEM: - *value = SMUQ10_ROUND(metrics->MaxHbmTemperature) * + *value = SMUQ10_ROUND(GET_METRIC_FIELD(MaxHbmTemperature)) * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; break; /* This is the max of all VRs and not just SOC VR. * No need to define another data type for the same. */ case METRICS_TEMPERATURE_VRSOC: - *value = SMUQ10_ROUND(metrics->MaxVrTemperature) * + *value = SMUQ10_ROUND(GET_METRIC_FIELD(MaxVrTemperature)) * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; break; default: @@ -2022,67 +2029,70 @@ static int smu_v13_0_6_get_current_pcie_link_speed(struct smu_context *smu) static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table) { struct smu_table_context *smu_table = &smu->smu_table; - struct gpu_metrics_v1_4 *gpu_metrics = - (struct gpu_metrics_v1_4 *)smu_table->gpu_metrics_table; + struct gpu_metrics_v1_5 *gpu_metrics = + (struct gpu_metrics_v1_5 *)smu_table->gpu_metrics_table; struct amdgpu_device *adev = smu->adev; - int ret = 0, xcc_id, inst, i; - MetricsTable_t *metrics; + int ret = 0, xcc_id, inst, i, j; + MetricsTableX_t *metrics_x; + MetricsTableA_t *metrics_a; u16 link_width_level; - metrics = kzalloc(sizeof(MetricsTable_t), GFP_KERNEL); - ret = smu_v13_0_6_get_metrics_table(smu, metrics, true); + metrics_x = kzalloc(max(sizeof(MetricsTableX_t), sizeof(MetricsTableA_t)), GFP_KERNEL); + ret = smu_v13_0_6_get_metrics_table(smu, metrics_x, true); if (ret) { - kfree(metrics); + kfree(metrics_x); return ret; } - smu_cmn_init_soft_gpu_metrics(gpu_metrics, 1, 4); + metrics_a = (MetricsTableA_t *)metrics_x; + + smu_cmn_init_soft_gpu_metrics(gpu_metrics, 1, 5); gpu_metrics->temperature_hotspot = - SMUQ10_ROUND(metrics->MaxSocketTemperature); + SMUQ10_ROUND(GET_METRIC_FIELD(MaxSocketTemperature)); /* Individual HBM stack temperature is not reported */ gpu_metrics->temperature_mem = - SMUQ10_ROUND(metrics->MaxHbmTemperature); + SMUQ10_ROUND(GET_METRIC_FIELD(MaxHbmTemperature)); /* Reports max temperature of all voltage rails */ gpu_metrics->temperature_vrsoc = - SMUQ10_ROUND(metrics->MaxVrTemperature); + SMUQ10_ROUND(GET_METRIC_FIELD(MaxVrTemperature)); gpu_metrics->average_gfx_activity = - SMUQ10_ROUND(metrics->SocketGfxBusy); + SMUQ10_ROUND(GET_METRIC_FIELD(SocketGfxBusy)); gpu_metrics->average_umc_activity = - SMUQ10_ROUND(metrics->DramBandwidthUtilization); + SMUQ10_ROUND(GET_METRIC_FIELD(DramBandwidthUtilization)); gpu_metrics->curr_socket_power = - SMUQ10_ROUND(metrics->SocketPower); + SMUQ10_ROUND(GET_METRIC_FIELD(SocketPower)); /* Energy counter reported in 15.259uJ (2^-16) units */ - gpu_metrics->energy_accumulator = metrics->SocketEnergyAcc; + gpu_metrics->energy_accumulator = GET_METRIC_FIELD(SocketEnergyAcc); for (i = 0; i < MAX_GFX_CLKS; i++) { xcc_id = GET_INST(GC, i); if (xcc_id >= 0) gpu_metrics->current_gfxclk[i] = - SMUQ10_ROUND(metrics->GfxclkFrequency[xcc_id]); + SMUQ10_ROUND(GET_METRIC_FIELD(GfxclkFrequency)[xcc_id]); if (i < MAX_CLKS) { gpu_metrics->current_socclk[i] = - SMUQ10_ROUND(metrics->SocclkFrequency[i]); + SMUQ10_ROUND(GET_METRIC_FIELD(SocclkFrequency)[i]); inst = GET_INST(VCN, i); if (inst >= 0) { gpu_metrics->current_vclk0[i] = - SMUQ10_ROUND(metrics->VclkFrequency[inst]); + SMUQ10_ROUND(GET_METRIC_FIELD(VclkFrequency)[inst]); gpu_metrics->current_dclk0[i] = - SMUQ10_ROUND(metrics->DclkFrequency[inst]); + SMUQ10_ROUND(GET_METRIC_FIELD(DclkFrequency)[inst]); } } } - gpu_metrics->current_uclk = SMUQ10_ROUND(metrics->UclkFrequency); + gpu_metrics->current_uclk = SMUQ10_ROUND(GET_METRIC_FIELD(UclkFrequency)); /* Throttle status is not reported through metrics now */ gpu_metrics->throttle_status = 0; /* Clock Lock Status. Each bit corresponds to each GFXCLK instance */ - gpu_metrics->gfxclk_lock_status = metrics->GfxLockXCDMak >> GET_INST(GC, 0); + gpu_metrics->gfxclk_lock_status = GET_METRIC_FIELD(GfxLockXCDMak) >> GET_INST(GC, 0); if (!(adev->flags & AMD_IS_APU)) { link_width_level = smu_v13_0_6_get_current_pcie_link_width_level(smu); @@ -2094,38 +2104,57 @@ static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table gpu_metrics->pcie_link_speed = smu_v13_0_6_get_current_pcie_link_speed(smu); gpu_metrics->pcie_bandwidth_acc = - SMUQ10_ROUND(metrics->PcieBandwidthAcc[0]); + SMUQ10_ROUND(metrics_x->PcieBandwidthAcc[0]); gpu_metrics->pcie_bandwidth_inst = - SMUQ10_ROUND(metrics->PcieBandwidth[0]); + SMUQ10_ROUND(metrics_x->PcieBandwidth[0]); gpu_metrics->pcie_l0_to_recov_count_acc = - metrics->PCIeL0ToRecoveryCountAcc; + metrics_x->PCIeL0ToRecoveryCountAcc; gpu_metrics->pcie_replay_count_acc = - metrics->PCIenReplayAAcc; + metrics_x->PCIenReplayAAcc; gpu_metrics->pcie_replay_rover_count_acc = - metrics->PCIenReplayARolloverCountAcc; + metrics_x->PCIenReplayARolloverCountAcc; + gpu_metrics->pcie_nak_sent_count_acc = + metrics_x->PCIeNAKSentCountAcc; + gpu_metrics->pcie_nak_rcvd_count_acc = + metrics_x->PCIeNAKReceivedCountAcc; } gpu_metrics->system_clock_counter = ktime_get_boottime_ns(); gpu_metrics->gfx_activity_acc = - SMUQ10_ROUND(metrics->SocketGfxBusyAcc); + SMUQ10_ROUND(GET_METRIC_FIELD(SocketGfxBusyAcc)); gpu_metrics->mem_activity_acc = - SMUQ10_ROUND(metrics->DramBandwidthUtilizationAcc); + SMUQ10_ROUND(GET_METRIC_FIELD(DramBandwidthUtilizationAcc)); for (i = 0; i < NUM_XGMI_LINKS; i++) { gpu_metrics->xgmi_read_data_acc[i] = - SMUQ10_ROUND(metrics->XgmiReadDataSizeAcc[i]); + SMUQ10_ROUND(GET_METRIC_FIELD(XgmiReadDataSizeAcc)[i]); gpu_metrics->xgmi_write_data_acc[i] = - SMUQ10_ROUND(metrics->XgmiWriteDataSizeAcc[i]); + SMUQ10_ROUND(GET_METRIC_FIELD(XgmiWriteDataSizeAcc)[i]); + } + + for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) { + inst = GET_INST(JPEG, i); + for (j = 0; j < adev->jpeg.num_jpeg_rings; ++j) { + gpu_metrics->jpeg_activity[(i * adev->jpeg.num_jpeg_rings) + j] = + SMUQ10_ROUND(GET_METRIC_FIELD(JpegBusy) + [(inst * adev->jpeg.num_jpeg_rings) + j]); + } + } + + for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + inst = GET_INST(VCN, i); + gpu_metrics->vcn_activity[i] = + SMUQ10_ROUND(GET_METRIC_FIELD(VcnBusy)[inst]); } - gpu_metrics->xgmi_link_width = SMUQ10_ROUND(metrics->XgmiWidth); - gpu_metrics->xgmi_link_speed = SMUQ10_ROUND(metrics->XgmiBitrate); + gpu_metrics->xgmi_link_width = SMUQ10_ROUND(GET_METRIC_FIELD(XgmiWidth)); + gpu_metrics->xgmi_link_speed = SMUQ10_ROUND(GET_METRIC_FIELD(XgmiBitrate)); - gpu_metrics->firmware_timestamp = metrics->Timestamp; + gpu_metrics->firmware_timestamp = GET_METRIC_FIELD(Timestamp); *table = (void *)gpu_metrics; - kfree(metrics); + kfree(metrics_x); return sizeof(*gpu_metrics); } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c index 001a5cf09657..00cd615bbcdc 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c @@ -989,6 +989,9 @@ void smu_cmn_init_soft_gpu_metrics(void *table, uint8_t frev, uint8_t crev) case METRICS_VERSION(1, 4): structure_size = sizeof(struct gpu_metrics_v1_4); break; + case METRICS_VERSION(1, 5): + structure_size = sizeof(struct gpu_metrics_v1_5); + break; case METRICS_VERSION(2, 0): structure_size = sizeof(struct gpu_metrics_v2_0); break; diff --git a/drivers/gpu/drm/bridge/parade-ps8640.c b/drivers/gpu/drm/bridge/parade-ps8640.c index 8161b1a1a4b1..541e4f5afc4c 100644 --- a/drivers/gpu/drm/bridge/parade-ps8640.c +++ b/drivers/gpu/drm/bridge/parade-ps8640.c @@ -210,7 +210,7 @@ static ssize_t ps8640_aux_transfer_msg(struct drm_dp_aux *aux, struct ps8640 *ps_bridge = aux_to_ps8640(aux); struct regmap *map = ps_bridge->regmap[PAGE0_DP_CNTL]; struct device *dev = &ps_bridge->page[PAGE0_DP_CNTL]->dev; - unsigned int len = msg->size; + size_t len = msg->size; unsigned int data; unsigned int base; int ret; @@ -330,11 +330,12 @@ static ssize_t ps8640_aux_transfer_msg(struct drm_dp_aux *aux, return ret; } - buf[i] = data; + if (i < msg->size) + buf[i] = data; } } - return len; + return min(len, msg->size); } static ssize_t ps8640_aux_transfer(struct drm_dp_aux *aux, diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c index c45c07840f64..b5464199b633 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c @@ -527,6 +527,7 @@ static ssize_t ti_sn_aux_transfer(struct drm_dp_aux *aux, u32 request_val = AUX_CMD_REQ(msg->request); u8 *buf = msg->buffer; unsigned int len = msg->size; + unsigned int short_len; unsigned int val; int ret; u8 addr_len[SN_AUX_LENGTH_REG + 1 - SN_AUX_ADDR_19_16_REG]; @@ -600,7 +601,8 @@ static ssize_t ti_sn_aux_transfer(struct drm_dp_aux *aux, } if (val & AUX_IRQ_STATUS_AUX_SHORT) { - ret = regmap_read(pdata->regmap, SN_AUX_LENGTH_REG, &len); + ret = regmap_read(pdata->regmap, SN_AUX_LENGTH_REG, &short_len); + len = min(len, short_len); if (ret) goto exit; } else if (val & AUX_IRQ_STATUS_NAT_I2C_FAIL) { diff --git a/drivers/gpu/drm/drm_auth.c b/drivers/gpu/drm/drm_auth.c index 2ed2585ded37..6899b3dc1f12 100644 --- a/drivers/gpu/drm/drm_auth.c +++ b/drivers/gpu/drm/drm_auth.c @@ -236,7 +236,7 @@ static int drm_master_check_perm(struct drm_device *dev, struct drm_file *file_priv) { if (file_priv->was_master && - rcu_access_pointer(file_priv->pid) == task_pid(current)) + rcu_access_pointer(file_priv->pid) == task_tgid(current)) return 0; if (!capable(CAP_SYS_ADMIN)) diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c index df9bf3c9206e..cb90e70d85e8 100644 --- a/drivers/gpu/drm/drm_crtc.c +++ b/drivers/gpu/drm/drm_crtc.c @@ -715,8 +715,7 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data, struct drm_mode_set set; uint32_t __user *set_connectors_ptr; struct drm_modeset_acquire_ctx ctx; - int ret; - int i; + int ret, i, num_connectors = 0; if (!drm_core_check_feature(dev, DRIVER_MODESET)) return -EOPNOTSUPP; @@ -871,6 +870,7 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data, connector->name); connector_set[i] = connector; + num_connectors++; } } @@ -879,7 +879,7 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data, set.y = crtc_req->y; set.mode = mode; set.connectors = connector_set; - set.num_connectors = crtc_req->count_connectors; + set.num_connectors = num_connectors; set.fb = fb; if (drm_drv_uses_atomic_modeset(dev)) @@ -892,7 +892,7 @@ out: drm_framebuffer_put(fb); if (connector_set) { - for (i = 0; i < crtc_req->count_connectors; i++) { + for (i = 0; i < num_connectors; i++) { if (connector_set[i]) drm_connector_put(connector_set[i]); } diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index 39db08f803ea..3b4065099872 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -2309,7 +2309,8 @@ int drm_edid_override_connector_update(struct drm_connector *connector) override = drm_edid_override_get(connector); if (override) { - num_modes = drm_edid_connector_update(connector, override); + if (drm_edid_connector_update(connector, override) == 0) + num_modes = drm_edid_connector_add_modes(connector); drm_edid_free(override); diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c index 01da6789d044..b9cc62982196 100644 --- a/drivers/gpu/drm/drm_syncobj.c +++ b/drivers/gpu/drm/drm_syncobj.c @@ -1365,7 +1365,7 @@ static void syncobj_eventfd_entry_fence_func(struct dma_fence *fence, struct syncobj_eventfd_entry *entry = container_of(cb, struct syncobj_eventfd_entry, fence_cb); - eventfd_signal(entry->ev_fd_ctx, 1); + eventfd_signal(entry->ev_fd_ctx); syncobj_eventfd_entry_free(entry); } @@ -1388,13 +1388,13 @@ syncobj_eventfd_entry_func(struct drm_syncobj *syncobj, entry->fence = fence; if (entry->flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE) { - eventfd_signal(entry->ev_fd_ctx, 1); + eventfd_signal(entry->ev_fd_ctx); syncobj_eventfd_entry_free(entry); } else { ret = dma_fence_add_callback(fence, &entry->fence_cb, syncobj_eventfd_entry_fence_func); if (ret == -ENOENT) { - eventfd_signal(entry->ev_fd_ctx, 1); + eventfd_signal(entry->ev_fd_ctx); syncobj_eventfd_entry_free(entry); } } diff --git a/drivers/gpu/drm/i915/display/intel_cx0_phy.c b/drivers/gpu/drm/i915/display/intel_cx0_phy.c index d414f6b7f993..ccf225afeb2a 100644 --- a/drivers/gpu/drm/i915/display/intel_cx0_phy.c +++ b/drivers/gpu/drm/i915/display/intel_cx0_phy.c @@ -2465,7 +2465,8 @@ static void intel_program_port_clock_ctl(struct intel_encoder *encoder, val |= XELPDP_FORWARD_CLOCK_UNGATE; - if (is_hdmi_frl(crtc_state->port_clock)) + if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI) && + is_hdmi_frl(crtc_state->port_clock)) val |= XELPDP_DDI_CLOCK_SELECT(XELPDP_DDI_CLOCK_SELECT_DIV18CLK); else val |= XELPDP_DDI_CLOCK_SELECT(XELPDP_DDI_CLOCK_SELECT_MAXPCLK); diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 63ba4d54a715..df582ff81b45 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -3747,8 +3747,8 @@ static bool hsw_get_pipe_config(struct intel_crtc *crtc, if (!active) goto out; - intel_dsc_get_config(pipe_config); intel_bigjoiner_get_config(pipe_config); + intel_dsc_get_config(pipe_config); if (!transcoder_is_dsi(pipe_config->cpu_transcoder) || DISPLAY_VER(dev_priv) >= 11) @@ -6033,6 +6033,17 @@ static int intel_async_flip_check_uapi(struct intel_atomic_state *state, return -EINVAL; } + /* + * FIXME: Bigjoiner+async flip is busted currently. + * Remove this check once the issues are fixed. + */ + if (new_crtc_state->bigjoiner_pipes) { + drm_dbg_kms(&i915->drm, + "[CRTC:%d:%s] async flip disallowed with bigjoiner\n", + crtc->base.base.id, crtc->base.name); + return -EINVAL; + } + for_each_oldnew_intel_plane_in_state(state, plane, old_plane_state, new_plane_state, i) { if (plane->pipe != crtc->pipe) diff --git a/drivers/gpu/drm/i915/display/intel_dmc.c b/drivers/gpu/drm/i915/display/intel_dmc.c index 63e080e07023..073b85b57679 100644 --- a/drivers/gpu/drm/i915/display/intel_dmc.c +++ b/drivers/gpu/drm/i915/display/intel_dmc.c @@ -389,7 +389,7 @@ disable_all_flip_queue_events(struct drm_i915_private *i915) enum intel_dmc_id dmc_id; /* TODO: check if the following applies to all D13+ platforms. */ - if (!IS_DG2(i915) && !IS_TIGERLAKE(i915)) + if (!IS_TIGERLAKE(i915)) return; for_each_dmc_id(dmc_id) { @@ -493,6 +493,45 @@ void intel_dmc_disable_pipe(struct drm_i915_private *i915, enum pipe pipe) intel_de_rmw(i915, PIPEDMC_CONTROL(pipe), PIPEDMC_ENABLE, 0); } +static bool is_dmc_evt_ctl_reg(struct drm_i915_private *i915, + enum intel_dmc_id dmc_id, i915_reg_t reg) +{ + u32 offset = i915_mmio_reg_offset(reg); + u32 start = i915_mmio_reg_offset(DMC_EVT_CTL(i915, dmc_id, 0)); + u32 end = i915_mmio_reg_offset(DMC_EVT_CTL(i915, dmc_id, DMC_EVENT_HANDLER_COUNT_GEN12)); + + return offset >= start && offset < end; +} + +static bool disable_dmc_evt(struct drm_i915_private *i915, + enum intel_dmc_id dmc_id, + i915_reg_t reg, u32 data) +{ + if (!is_dmc_evt_ctl_reg(i915, dmc_id, reg)) + return false; + + /* keep all pipe DMC events disabled by default */ + if (dmc_id != DMC_FW_MAIN) + return true; + + return false; +} + +static u32 dmc_mmiodata(struct drm_i915_private *i915, + struct intel_dmc *dmc, + enum intel_dmc_id dmc_id, int i) +{ + if (disable_dmc_evt(i915, dmc_id, + dmc->dmc_info[dmc_id].mmioaddr[i], + dmc->dmc_info[dmc_id].mmiodata[i])) + return REG_FIELD_PREP(DMC_EVT_CTL_TYPE_MASK, + DMC_EVT_CTL_TYPE_EDGE_0_1) | + REG_FIELD_PREP(DMC_EVT_CTL_EVENT_ID_MASK, + DMC_EVT_CTL_EVENT_ID_FALSE); + else + return dmc->dmc_info[dmc_id].mmiodata[i]; +} + /** * intel_dmc_load_program() - write the firmware from memory to register. * @i915: i915 drm device. @@ -532,7 +571,7 @@ void intel_dmc_load_program(struct drm_i915_private *i915) for_each_dmc_id(dmc_id) { for (i = 0; i < dmc->dmc_info[dmc_id].mmio_count; i++) { intel_de_write(i915, dmc->dmc_info[dmc_id].mmioaddr[i], - dmc->dmc_info[dmc_id].mmiodata[i]); + dmc_mmiodata(i915, dmc, dmc_id, i)); } } diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index b21bcd40f111..62ce92772367 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -4496,7 +4496,7 @@ static void intel_dp_process_phy_request(struct intel_dp *intel_dp, intel_dp->train_set, crtc_state->lane_count); drm_dp_set_phy_test_pattern(&intel_dp->aux, data, - link_status[DP_DPCD_REV]); + intel_dp->dpcd[DP_DPCD_REV]); } static u8 intel_dp_autotest_phy_pattern(struct intel_dp *intel_dp) diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c index dbc1b66c8ee4..1abfafbbfa75 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c +++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c @@ -650,19 +650,30 @@ intel_dp_update_link_bw_set(struct intel_dp *intel_dp, const struct intel_crtc_state *crtc_state, u8 link_bw, u8 rate_select) { - u8 link_config[2]; + u8 lane_count = crtc_state->lane_count; - /* Write the link configuration data */ - link_config[0] = link_bw; - link_config[1] = crtc_state->lane_count; if (crtc_state->enhanced_framing) - link_config[1] |= DP_LANE_COUNT_ENHANCED_FRAME_EN; - drm_dp_dpcd_write(&intel_dp->aux, DP_LINK_BW_SET, link_config, 2); + lane_count |= DP_LANE_COUNT_ENHANCED_FRAME_EN; + + if (link_bw) { + /* DP and eDP v1.3 and earlier link bw set method. */ + u8 link_config[] = { link_bw, lane_count }; - /* eDP 1.4 rate select method. */ - if (!link_bw) - drm_dp_dpcd_write(&intel_dp->aux, DP_LINK_RATE_SET, - &rate_select, 1); + drm_dp_dpcd_write(&intel_dp->aux, DP_LINK_BW_SET, link_config, + ARRAY_SIZE(link_config)); + } else { + /* + * eDP v1.4 and later link rate set method. + * + * eDP v1.4x sinks shall ignore DP_LINK_RATE_SET if + * DP_LINK_BW_SET is set. Avoid writing DP_LINK_BW_SET. + * + * eDP v1.5 sinks allow choosing either, and the last choice + * shall be active. + */ + drm_dp_dpcd_writeb(&intel_dp->aux, DP_LANE_COUNT_SET, lane_count); + drm_dp_dpcd_writeb(&intel_dp->aux, DP_LINK_RATE_SET, rate_select); + } } /* diff --git a/drivers/gpu/drm/i915/display/intel_fb.c b/drivers/gpu/drm/i915/display/intel_fb.c index 19b35ece31f1..646f367a13f5 100644 --- a/drivers/gpu/drm/i915/display/intel_fb.c +++ b/drivers/gpu/drm/i915/display/intel_fb.c @@ -1374,7 +1374,8 @@ plane_view_scanout_stride(const struct intel_framebuffer *fb, int color_plane, struct drm_i915_private *i915 = to_i915(fb->base.dev); unsigned int stride_tiles; - if (IS_ALDERLAKE_P(i915) || DISPLAY_VER(i915) >= 14) + if ((IS_ALDERLAKE_P(i915) || DISPLAY_VER(i915) >= 14) && + src_stride_tiles < dst_stride_tiles) stride_tiles = src_stride_tiles; else stride_tiles = dst_stride_tiles; @@ -1501,8 +1502,20 @@ static u32 calc_plane_remap_info(const struct intel_framebuffer *fb, int color_p size += remap_info->size; } else { - unsigned int dst_stride = plane_view_dst_stride_tiles(fb, color_plane, - remap_info->width); + unsigned int dst_stride; + + /* + * The hardware automagically calculates the CCS AUX surface + * stride from the main surface stride so can't really remap a + * smaller subset (unless we'd remap in whole AUX page units). + */ + if (intel_fb_needs_pot_stride_remap(fb) && + intel_fb_is_ccs_modifier(fb->base.modifier)) + dst_stride = remap_info->src_stride; + else + dst_stride = remap_info->width; + + dst_stride = plane_view_dst_stride_tiles(fb, color_plane, dst_stride); assign_chk_ovf(i915, remap_info->dst_stride, dst_stride); color_plane_info->mapping_stride = dst_stride * diff --git a/drivers/gpu/drm/i915/display/skl_scaler.c b/drivers/gpu/drm/i915/display/skl_scaler.c index 1e7c97243fcf..8a934bada624 100644 --- a/drivers/gpu/drm/i915/display/skl_scaler.c +++ b/drivers/gpu/drm/i915/display/skl_scaler.c @@ -504,7 +504,6 @@ int intel_atomic_setup_scalers(struct drm_i915_private *dev_priv, { struct drm_plane *plane = NULL; struct intel_plane *intel_plane; - struct intel_plane_state *plane_state = NULL; struct intel_crtc_scaler_state *scaler_state = &crtc_state->scaler_state; struct drm_atomic_state *drm_state = crtc_state->uapi.state; @@ -536,6 +535,7 @@ int intel_atomic_setup_scalers(struct drm_i915_private *dev_priv, /* walkthrough scaler_users bits and start assigning scalers */ for (i = 0; i < sizeof(scaler_state->scaler_users) * 8; i++) { + struct intel_plane_state *plane_state = NULL; int *scaler_id; const char *name; int idx, ret; diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c index d5ed904f355d..6801f8b95c53 100644 --- a/drivers/gpu/drm/i915/gt/intel_reset.c +++ b/drivers/gpu/drm/i915/gt/intel_reset.c @@ -1293,7 +1293,7 @@ int __intel_engine_reset_bh(struct intel_engine_cs *engine, const char *msg) if (msg) drm_notice(&engine->i915->drm, "Resetting %s for %s\n", engine->name, msg); - atomic_inc(&engine->i915->gpu_error.reset_engine_count[engine->uabi_class]); + i915_increase_reset_engine_count(&engine->i915->gpu_error, engine); ret = intel_gt_reset_engine(engine); if (ret) { diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index d37698bd6b91..17df71117cc7 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -5001,7 +5001,8 @@ static void capture_error_state(struct intel_guc *guc, if (match) { intel_engine_set_hung_context(e, ce); engine_mask |= e->mask; - atomic_inc(&i915->gpu_error.reset_engine_count[e->uabi_class]); + i915_increase_reset_engine_count(&i915->gpu_error, + e); } } @@ -5013,7 +5014,7 @@ static void capture_error_state(struct intel_guc *guc, } else { intel_engine_set_hung_context(ce->engine, ce); engine_mask = ce->engine->mask; - atomic_inc(&i915->gpu_error.reset_engine_count[ce->engine->uabi_class]); + i915_increase_reset_engine_count(&i915->gpu_error, ce->engine); } with_intel_runtime_pm(&i915->runtime_pm, wakeref) diff --git a/drivers/gpu/drm/i915/gvt/interrupt.c b/drivers/gpu/drm/i915/gvt/interrupt.c index de3f5903d1a7..c8e7dfc9f791 100644 --- a/drivers/gpu/drm/i915/gvt/interrupt.c +++ b/drivers/gpu/drm/i915/gvt/interrupt.c @@ -422,7 +422,7 @@ static void init_irq_map(struct intel_gvt_irq *irq) #define MSI_CAP_DATA(offset) (offset + 8) #define MSI_CAP_EN 0x1 -static int inject_virtual_interrupt(struct intel_vgpu *vgpu) +static void inject_virtual_interrupt(struct intel_vgpu *vgpu) { unsigned long offset = vgpu->gvt->device_info.msi_cap_offset; u16 control, data; @@ -434,10 +434,10 @@ static int inject_virtual_interrupt(struct intel_vgpu *vgpu) /* Do not generate MSI if MSIEN is disabled */ if (!(control & MSI_CAP_EN)) - return 0; + return; if (WARN(control & GENMASK(15, 1), "only support one MSI format\n")) - return -EINVAL; + return; trace_inject_msi(vgpu->id, addr, data); @@ -451,10 +451,9 @@ static int inject_virtual_interrupt(struct intel_vgpu *vgpu) * returned and don't inject interrupt into guest. */ if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status)) - return -ESRCH; - if (vgpu->msi_trigger && eventfd_signal(vgpu->msi_trigger, 1) != 1) - return -EFAULT; - return 0; + return; + if (vgpu->msi_trigger) + eventfd_signal(vgpu->msi_trigger); } static void propagate_event(struct intel_gvt_irq *irq, diff --git a/drivers/gpu/drm/i915/i915_gpu_error.h b/drivers/gpu/drm/i915/i915_gpu_error.h index 9f5971f5e980..48f6c00402c4 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.h +++ b/drivers/gpu/drm/i915/i915_gpu_error.h @@ -16,6 +16,7 @@ #include "display/intel_display_device.h" #include "gt/intel_engine.h" +#include "gt/intel_engine_types.h" #include "gt/intel_gt_types.h" #include "gt/uc/intel_uc_fw.h" @@ -232,7 +233,7 @@ struct i915_gpu_error { atomic_t reset_count; /** Number of times an engine has been reset */ - atomic_t reset_engine_count[I915_NUM_ENGINES]; + atomic_t reset_engine_count[MAX_ENGINE_CLASS]; }; struct drm_i915_error_state_buf { @@ -255,7 +256,14 @@ static inline u32 i915_reset_count(struct i915_gpu_error *error) static inline u32 i915_reset_engine_count(struct i915_gpu_error *error, const struct intel_engine_cs *engine) { - return atomic_read(&error->reset_engine_count[engine->uabi_class]); + return atomic_read(&error->reset_engine_count[engine->class]); +} + +static inline void +i915_increase_reset_engine_count(struct i915_gpu_error *error, + const struct intel_engine_cs *engine) +{ + atomic_inc(&error->reset_engine_count[engine->class]); } #define CORE_DUMP_FLAG_NONE 0x0 diff --git a/drivers/gpu/drm/i915/i915_hwmon.c b/drivers/gpu/drm/i915/i915_hwmon.c index 975da8e7f2a9..8c3f443c8347 100644 --- a/drivers/gpu/drm/i915/i915_hwmon.c +++ b/drivers/gpu/drm/i915/i915_hwmon.c @@ -175,7 +175,7 @@ hwm_power1_max_interval_show(struct device *dev, struct device_attribute *attr, * tau4 = (4 | x) << y * but add 2 when doing the final right shift to account for units */ - tau4 = ((1 << x_w) | x) << y; + tau4 = (u64)((1 << x_w) | x) << y; /* val in hwmon interface units (millisec) */ out = mul_u64_u32_shr(tau4, SF_TIME, hwmon->scl_shift_time + x_w); @@ -211,7 +211,7 @@ hwm_power1_max_interval_store(struct device *dev, r = FIELD_PREP(PKG_MAX_WIN, PKG_MAX_WIN_DEFAULT); x = REG_FIELD_GET(PKG_MAX_WIN_X, r); y = REG_FIELD_GET(PKG_MAX_WIN_Y, r); - tau4 = ((1 << x_w) | x) << y; + tau4 = (u64)((1 << x_w) | x) << y; max_win = mul_u64_u32_shr(tau4, SF_TIME, hwmon->scl_shift_time + x_w); if (val > max_win) diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 7b1c8de2f9cb..2d695818f006 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -772,10 +772,6 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream, * The reason field includes flags identifying what * triggered this specific report (mostly timer * triggered or e.g. due to a context switch). - * - * In MMIO triggered reports, some platforms do not set the - * reason bit in this field and it is valid to have a reason - * field of zero. */ reason = oa_report_reason(stream, report); ctx_id = oa_context_id(stream, report32); @@ -787,8 +783,41 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream, * * Note: that we don't clear the valid_ctx_bit so userspace can * understand that the ID has been squashed by the kernel. + * + * Update: + * + * On XEHP platforms the behavior of context id valid bit has + * changed compared to prior platforms. To describe this, we + * define a few terms: + * + * context-switch-report: This is a report with the reason type + * being context-switch. It is generated when a context switches + * out. + * + * context-valid-bit: A bit that is set in the report ID field + * to indicate that a valid context has been loaded. + * + * gpu-idle: A condition characterized by a + * context-switch-report with context-valid-bit set to 0. + * + * On prior platforms, context-id-valid bit is set to 0 only + * when GPU goes idle. In all other reports, it is set to 1. + * + * On XEHP platforms, context-valid-bit is set to 1 in a context + * switch report if a new context switched in. For all other + * reports it is set to 0. + * + * This change in behavior causes an issue with MMIO triggered + * reports. MMIO triggered reports have the markers in the + * context ID field and the context-valid-bit is 0. The logic + * below to squash the context ID would render the report + * useless since the user will not be able to find it in the OA + * buffer. Since MMIO triggered reports exist only on XEHP, + * we should avoid squashing these for XEHP platforms. */ - if (oa_report_ctx_invalid(stream, report)) { + + if (oa_report_ctx_invalid(stream, report) && + GRAPHICS_VER_FULL(stream->engine->i915) < IP_VER(12, 50)) { ctx_id = INVALID_CTX_ID; oa_context_id_squash(stream, report32); } diff --git a/drivers/gpu/drm/i915/selftests/igt_live_test.c b/drivers/gpu/drm/i915/selftests/igt_live_test.c index 4ddc6d902752..7d41874a49c5 100644 --- a/drivers/gpu/drm/i915/selftests/igt_live_test.c +++ b/drivers/gpu/drm/i915/selftests/igt_live_test.c @@ -37,8 +37,9 @@ int igt_live_test_begin(struct igt_live_test *t, } for_each_engine(engine, gt, id) - t->reset_engine[id] = - i915_reset_engine_count(&i915->gpu_error, engine); + t->reset_engine[i][id] = + i915_reset_engine_count(&i915->gpu_error, + engine); } t->reset_global = i915_reset_count(&i915->gpu_error); @@ -66,14 +67,14 @@ int igt_live_test_end(struct igt_live_test *t) for_each_gt(gt, i915, i) { for_each_engine(engine, gt, id) { - if (t->reset_engine[id] == + if (t->reset_engine[i][id] == i915_reset_engine_count(&i915->gpu_error, engine)) continue; gt_err(gt, "%s(%s): engine '%s' was reset %d times!\n", t->func, t->name, engine->name, i915_reset_engine_count(&i915->gpu_error, engine) - - t->reset_engine[id]); + t->reset_engine[i][id]); return -EIO; } } diff --git a/drivers/gpu/drm/i915/selftests/igt_live_test.h b/drivers/gpu/drm/i915/selftests/igt_live_test.h index 36ed42736c52..83e3ad430922 100644 --- a/drivers/gpu/drm/i915/selftests/igt_live_test.h +++ b/drivers/gpu/drm/i915/selftests/igt_live_test.h @@ -7,6 +7,7 @@ #ifndef IGT_LIVE_TEST_H #define IGT_LIVE_TEST_H +#include "gt/intel_gt_defines.h" /* for I915_MAX_GT */ #include "gt/intel_engine.h" /* for I915_NUM_ENGINES */ struct drm_i915_private; @@ -17,7 +18,7 @@ struct igt_live_test { const char *name; unsigned int reset_global; - unsigned int reset_engine[I915_NUM_ENGINES]; + unsigned int reset_engine[I915_MAX_GT][I915_NUM_ENGINES]; }; /* diff --git a/drivers/gpu/drm/mediatek/mtk_disp_gamma.c b/drivers/gpu/drm/mediatek/mtk_disp_gamma.c index f81dc34c9c3e..c1bc8b00d938 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_gamma.c +++ b/drivers/gpu/drm/mediatek/mtk_disp_gamma.c @@ -203,7 +203,7 @@ void mtk_gamma_set(struct device *dev, struct drm_crtc_state *state) /* Disable RELAY mode to pass the processed image */ cfg_val &= ~GAMMA_RELAY_MODE; - cfg_val = readl(gamma->regs + DISP_GAMMA_CFG); + writel(cfg_val, gamma->regs + DISP_GAMMA_CFG); } void mtk_gamma_config(struct device *dev, unsigned int w, diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c index c277b9fae950..db43f9dff912 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c @@ -788,6 +788,7 @@ static void mtk_drm_crtc_atomic_begin(struct drm_crtc *crtc, crtc); struct mtk_crtc_state *mtk_crtc_state = to_mtk_crtc_state(crtc_state); struct mtk_drm_crtc *mtk_crtc = to_mtk_crtc(crtc); + unsigned long flags; if (mtk_crtc->event && mtk_crtc_state->base.event) DRM_ERROR("new event while there is still a pending event\n"); @@ -795,7 +796,11 @@ static void mtk_drm_crtc_atomic_begin(struct drm_crtc *crtc, if (mtk_crtc_state->base.event) { mtk_crtc_state->base.event->pipe = drm_crtc_index(crtc); WARN_ON(drm_crtc_vblank_get(crtc) != 0); + + spin_lock_irqsave(&crtc->dev->event_lock, flags); mtk_crtc->event = mtk_crtc_state->base.event; + spin_unlock_irqrestore(&crtc->dev->event_lock, flags); + mtk_crtc_state->base.event = NULL; } } @@ -921,7 +926,14 @@ static int mtk_drm_crtc_init_comp_planes(struct drm_device *drm_dev, struct device *mtk_drm_crtc_dma_dev_get(struct drm_crtc *crtc) { - struct mtk_drm_crtc *mtk_crtc = to_mtk_crtc(crtc); + struct mtk_drm_crtc *mtk_crtc = NULL; + + if (!crtc) + return NULL; + + mtk_crtc = to_mtk_crtc(crtc); + if (!mtk_crtc) + return NULL; return mtk_crtc->dma_dev; } diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c index 2dfaa613276a..2b0c35cacbc6 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c @@ -443,6 +443,7 @@ static int mtk_drm_kms_init(struct drm_device *drm) struct mtk_drm_private *private = drm->dev_private; struct mtk_drm_private *priv_n; struct device *dma_dev = NULL; + struct drm_crtc *crtc; int ret, i, j; if (drm_firmware_drivers_only()) @@ -519,7 +520,9 @@ static int mtk_drm_kms_init(struct drm_device *drm) } /* Use OVL device for all DMA memory allocations */ - dma_dev = mtk_drm_crtc_dma_dev_get(drm_crtc_from_index(drm, 0)); + crtc = drm_crtc_from_index(drm, 0); + if (crtc) + dma_dev = mtk_drm_crtc_dma_dev_get(crtc); if (!dma_dev) { ret = -ENODEV; dev_err(drm->dev, "Need at least one OVL device\n"); diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.h b/drivers/gpu/drm/mgag200/mgag200_drv.h index 57c7edcab602..765e49fd8911 100644 --- a/drivers/gpu/drm/mgag200/mgag200_drv.h +++ b/drivers/gpu/drm/mgag200/mgag200_drv.h @@ -392,6 +392,11 @@ void mgag200_primary_plane_helper_atomic_disable(struct drm_plane *plane, .destroy = drm_plane_cleanup, \ DRM_GEM_SHADOW_PLANE_FUNCS +void mgag200_crtc_set_gamma_linear(struct mga_device *mdev, const struct drm_format_info *format); +void mgag200_crtc_set_gamma(struct mga_device *mdev, + const struct drm_format_info *format, + struct drm_color_lut *lut); + enum drm_mode_status mgag200_crtc_helper_mode_valid(struct drm_crtc *crtc, const struct drm_display_mode *mode); int mgag200_crtc_helper_atomic_check(struct drm_crtc *crtc, struct drm_atomic_state *new_state); diff --git a/drivers/gpu/drm/mgag200/mgag200_g200er.c b/drivers/gpu/drm/mgag200/mgag200_g200er.c index bce267e0f7de..8d4538b71047 100644 --- a/drivers/gpu/drm/mgag200/mgag200_g200er.c +++ b/drivers/gpu/drm/mgag200/mgag200_g200er.c @@ -202,6 +202,11 @@ static void mgag200_g200er_crtc_helper_atomic_enable(struct drm_crtc *crtc, mgag200_g200er_reset_tagfifo(mdev); + if (crtc_state->gamma_lut) + mgag200_crtc_set_gamma(mdev, format, crtc_state->gamma_lut->data); + else + mgag200_crtc_set_gamma_linear(mdev, format); + mgag200_enable_display(mdev); if (funcs->enable_vidrst) diff --git a/drivers/gpu/drm/mgag200/mgag200_g200ev.c b/drivers/gpu/drm/mgag200/mgag200_g200ev.c index ac957f42abe1..56e6f986bff3 100644 --- a/drivers/gpu/drm/mgag200/mgag200_g200ev.c +++ b/drivers/gpu/drm/mgag200/mgag200_g200ev.c @@ -203,6 +203,11 @@ static void mgag200_g200ev_crtc_helper_atomic_enable(struct drm_crtc *crtc, mgag200_g200ev_set_hiprilvl(mdev); + if (crtc_state->gamma_lut) + mgag200_crtc_set_gamma(mdev, format, crtc_state->gamma_lut->data); + else + mgag200_crtc_set_gamma_linear(mdev, format); + mgag200_enable_display(mdev); if (funcs->enable_vidrst) diff --git a/drivers/gpu/drm/mgag200/mgag200_g200se.c b/drivers/gpu/drm/mgag200/mgag200_g200se.c index bd6e573c9a1a..ff2b3c6622e7 100644 --- a/drivers/gpu/drm/mgag200/mgag200_g200se.c +++ b/drivers/gpu/drm/mgag200/mgag200_g200se.c @@ -334,6 +334,11 @@ static void mgag200_g200se_crtc_helper_atomic_enable(struct drm_crtc *crtc, mgag200_g200se_set_hiprilvl(mdev, adjusted_mode, format); + if (crtc_state->gamma_lut) + mgag200_crtc_set_gamma(mdev, format, crtc_state->gamma_lut->data); + else + mgag200_crtc_set_gamma_linear(mdev, format); + mgag200_enable_display(mdev); if (funcs->enable_vidrst) diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c index af3ce5a6a636..0f0d59938c3a 100644 --- a/drivers/gpu/drm/mgag200/mgag200_mode.c +++ b/drivers/gpu/drm/mgag200/mgag200_mode.c @@ -28,8 +28,8 @@ * This file contains setup code for the CRTC. */ -static void mgag200_crtc_set_gamma_linear(struct mga_device *mdev, - const struct drm_format_info *format) +void mgag200_crtc_set_gamma_linear(struct mga_device *mdev, + const struct drm_format_info *format) { int i; @@ -65,9 +65,9 @@ static void mgag200_crtc_set_gamma_linear(struct mga_device *mdev, } } -static void mgag200_crtc_set_gamma(struct mga_device *mdev, - const struct drm_format_info *format, - struct drm_color_lut *lut) +void mgag200_crtc_set_gamma(struct mga_device *mdev, + const struct drm_format_info *format, + struct drm_color_lut *lut) { int i; diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h index 2fa0445d8928..d1437c08645f 100644 --- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h +++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h @@ -187,7 +187,7 @@ struct nvkm_gsp { void (*rpc_done)(struct nvkm_gsp *gsp, void *repv); void *(*rm_ctrl_get)(struct nvkm_gsp_object *, u32 cmd, u32 argc); - void *(*rm_ctrl_push)(struct nvkm_gsp_object *, void *argv, u32 repc); + int (*rm_ctrl_push)(struct nvkm_gsp_object *, void **argv, u32 repc); void (*rm_ctrl_done)(struct nvkm_gsp_object *, void *repv); void *(*rm_alloc_get)(struct nvkm_gsp_object *, u32 oclass, u32 argc); @@ -265,7 +265,7 @@ nvkm_gsp_rm_ctrl_get(struct nvkm_gsp_object *object, u32 cmd, u32 argc) return object->client->gsp->rm->rm_ctrl_get(object, cmd, argc); } -static inline void * +static inline int nvkm_gsp_rm_ctrl_push(struct nvkm_gsp_object *object, void *argv, u32 repc) { return object->client->gsp->rm->rm_ctrl_push(object, argv, repc); @@ -275,21 +275,24 @@ static inline void * nvkm_gsp_rm_ctrl_rd(struct nvkm_gsp_object *object, u32 cmd, u32 repc) { void *argv = nvkm_gsp_rm_ctrl_get(object, cmd, repc); + int ret; if (IS_ERR(argv)) return argv; - return nvkm_gsp_rm_ctrl_push(object, argv, repc); + ret = nvkm_gsp_rm_ctrl_push(object, &argv, repc); + if (ret) + return ERR_PTR(ret); + return argv; } static inline int nvkm_gsp_rm_ctrl_wr(struct nvkm_gsp_object *object, void *argv) { - void *repv = nvkm_gsp_rm_ctrl_push(object, argv, 0); - - if (IS_ERR(repv)) - return PTR_ERR(repv); + int ret = nvkm_gsp_rm_ctrl_push(object, &argv, 0); + if (ret) + return ret; return 0; } diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c index ca762ea55413..5057d976fa57 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.c +++ b/drivers/gpu/drm/nouveau/nouveau_fence.c @@ -62,7 +62,7 @@ nouveau_fence_signal(struct nouveau_fence *fence) if (test_bit(DMA_FENCE_FLAG_USER_BITS, &fence->base.flags)) { struct nouveau_fence_chan *fctx = nouveau_fctx(fence); - if (!--fctx->notify_ref) + if (atomic_dec_and_test(&fctx->notify_ref)) drop = 1; } @@ -103,6 +103,7 @@ nouveau_fence_context_kill(struct nouveau_fence_chan *fctx, int error) void nouveau_fence_context_del(struct nouveau_fence_chan *fctx) { + cancel_work_sync(&fctx->allow_block_work); nouveau_fence_context_kill(fctx, 0); nvif_event_dtor(&fctx->event); fctx->dead = 1; @@ -167,6 +168,18 @@ nouveau_fence_wait_uevent_handler(struct nvif_event *event, void *repv, u32 repc return ret; } +static void +nouveau_fence_work_allow_block(struct work_struct *work) +{ + struct nouveau_fence_chan *fctx = container_of(work, struct nouveau_fence_chan, + allow_block_work); + + if (atomic_read(&fctx->notify_ref) == 0) + nvif_event_block(&fctx->event); + else + nvif_event_allow(&fctx->event); +} + void nouveau_fence_context_new(struct nouveau_channel *chan, struct nouveau_fence_chan *fctx) { @@ -178,6 +191,7 @@ nouveau_fence_context_new(struct nouveau_channel *chan, struct nouveau_fence_cha } args; int ret; + INIT_WORK(&fctx->allow_block_work, nouveau_fence_work_allow_block); INIT_LIST_HEAD(&fctx->flip); INIT_LIST_HEAD(&fctx->pending); spin_lock_init(&fctx->lock); @@ -521,15 +535,19 @@ static bool nouveau_fence_enable_signaling(struct dma_fence *f) struct nouveau_fence *fence = from_fence(f); struct nouveau_fence_chan *fctx = nouveau_fctx(fence); bool ret; + bool do_work; - if (!fctx->notify_ref++) - nvif_event_allow(&fctx->event); + if (atomic_inc_return(&fctx->notify_ref) == 0) + do_work = true; ret = nouveau_fence_no_signaling(f); if (ret) set_bit(DMA_FENCE_FLAG_USER_BITS, &fence->base.flags); - else if (!--fctx->notify_ref) - nvif_event_block(&fctx->event); + else if (atomic_dec_and_test(&fctx->notify_ref)) + do_work = true; + + if (do_work) + schedule_work(&fctx->allow_block_work); return ret; } diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.h b/drivers/gpu/drm/nouveau/nouveau_fence.h index 64d33ae7f356..28f5cf013b89 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.h +++ b/drivers/gpu/drm/nouveau/nouveau_fence.h @@ -3,6 +3,7 @@ #define __NOUVEAU_FENCE_H__ #include <linux/dma-fence.h> +#include <linux/workqueue.h> #include <nvif/event.h> struct nouveau_drm; @@ -45,7 +46,9 @@ struct nouveau_fence_chan { char name[32]; struct nvif_event event; - int notify_ref, dead, killed; + struct work_struct allow_block_work; + atomic_t notify_ref; + int dead, killed; }; struct nouveau_fence_priv { diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/base.c index 457ec5db794d..b24eb1e560bc 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/base.c @@ -209,7 +209,7 @@ nvkm_disp_dtor(struct nvkm_engine *engine) nvkm_head_del(&head); } - if (disp->func->dtor) + if (disp->func && disp->func->dtor) disp->func->dtor(disp); return data; @@ -243,8 +243,10 @@ nvkm_disp_new_(const struct nvkm_disp_func *func, struct nvkm_device *device, spin_lock_init(&disp->client.lock); ret = nvkm_engine_ctor(&nvkm_disp, device, type, inst, true, &disp->engine); - if (ret) + if (ret) { + disp->func = NULL; return ret; + } if (func->super) { disp->super.wq = create_singlethread_workqueue("nvkm-disp"); diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/r535.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/r535.c index 298035070b3a..6a0a4d3b8902 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/r535.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/r535.c @@ -282,7 +282,7 @@ r535_sor_bl_get(struct nvkm_ior *sor) { struct nvkm_disp *disp = sor->disp; NV0073_CTRL_SPECIFIC_BACKLIGHT_BRIGHTNESS_PARAMS *ctrl; - int lvl; + int ret, lvl; ctrl = nvkm_gsp_rm_ctrl_get(&disp->rm.objcom, NV0073_CTRL_CMD_SPECIFIC_GET_BACKLIGHT_BRIGHTNESS, @@ -292,9 +292,11 @@ r535_sor_bl_get(struct nvkm_ior *sor) ctrl->displayId = BIT(sor->asy.outp->index); - ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl)); - if (IS_ERR(ctrl)) - return PTR_ERR(ctrl); + ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl)); + if (ret) { + nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); + return ret; + } lvl = ctrl->brightness; nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); @@ -649,9 +651,11 @@ r535_conn_new(struct nvkm_disp *disp, u32 id) ctrl->subDeviceInstance = 0; ctrl->displayId = BIT(id); - ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl)); - if (IS_ERR(ctrl)) - return (void *)ctrl; + ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl)); + if (ret) { + nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); + return ERR_PTR(ret); + } list_for_each_entry(conn, &disp->conns, head) { if (conn->index == ctrl->data[0].index) { @@ -686,7 +690,7 @@ r535_outp_acquire(struct nvkm_outp *outp, bool hda) struct nvkm_disp *disp = outp->disp; struct nvkm_ior *ior; NV0073_CTRL_DFP_ASSIGN_SOR_PARAMS *ctrl; - int or; + int ret, or; ctrl = nvkm_gsp_rm_ctrl_get(&disp->rm.objcom, NV0073_CTRL_CMD_DFP_ASSIGN_SOR, sizeof(*ctrl)); @@ -699,9 +703,11 @@ r535_outp_acquire(struct nvkm_outp *outp, bool hda) if (hda) ctrl->flags |= NVDEF(NV0073_CTRL, DFP_ASSIGN_SOR_FLAGS, AUDIO, OPTIMAL); - ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl)); - if (IS_ERR(ctrl)) - return PTR_ERR(ctrl); + ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl)); + if (ret) { + nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); + return ret; + } for (or = 0; or < ARRAY_SIZE(ctrl->sorAssignListWithTag); or++) { if (ctrl->sorAssignListWithTag[or].displayMask & BIT(outp->index)) { @@ -727,6 +733,7 @@ static int r535_disp_head_displayid(struct nvkm_disp *disp, int head, u32 *displayid) { NV0073_CTRL_SYSTEM_GET_ACTIVE_PARAMS *ctrl; + int ret; ctrl = nvkm_gsp_rm_ctrl_get(&disp->rm.objcom, NV0073_CTRL_CMD_SYSTEM_GET_ACTIVE, sizeof(*ctrl)); @@ -736,9 +743,11 @@ r535_disp_head_displayid(struct nvkm_disp *disp, int head, u32 *displayid) ctrl->subDeviceInstance = 0; ctrl->head = head; - ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl)); - if (IS_ERR(ctrl)) - return PTR_ERR(ctrl); + ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl)); + if (ret) { + nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); + return ret; + } *displayid = ctrl->displayId; nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); @@ -772,9 +781,11 @@ r535_outp_inherit(struct nvkm_outp *outp) ctrl->subDeviceInstance = 0; ctrl->displayId = displayid; - ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl)); - if (IS_ERR(ctrl)) + ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl)); + if (ret) { + nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); return NULL; + } id = ctrl->index; proto = ctrl->protocol; @@ -825,6 +836,7 @@ r535_outp_dfp_get_info(struct nvkm_outp *outp) { NV0073_CTRL_DFP_GET_INFO_PARAMS *ctrl; struct nvkm_disp *disp = outp->disp; + int ret; ctrl = nvkm_gsp_rm_ctrl_get(&disp->rm.objcom, NV0073_CTRL_CMD_DFP_GET_INFO, sizeof(*ctrl)); if (IS_ERR(ctrl)) @@ -832,9 +844,11 @@ r535_outp_dfp_get_info(struct nvkm_outp *outp) ctrl->displayId = BIT(outp->index); - ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl)); - if (IS_ERR(ctrl)) - return PTR_ERR(ctrl); + ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl)); + if (ret) { + nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); + return ret; + } nvkm_debug(&disp->engine.subdev, "DFP %08x: flags:%08x flags2:%08x\n", ctrl->displayId, ctrl->flags, ctrl->flags2); @@ -858,9 +872,11 @@ r535_outp_detect(struct nvkm_outp *outp) ctrl->subDeviceInstance = 0; ctrl->displayMask = BIT(outp->index); - ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl)); - if (IS_ERR(ctrl)) - return PTR_ERR(ctrl); + ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl)); + if (ret) { + nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); + return ret; + } if (ctrl->displayMask & BIT(outp->index)) { ret = r535_outp_dfp_get_info(outp); @@ -895,6 +911,7 @@ r535_dp_mst_id_get(struct nvkm_outp *outp, u32 *pid) { NV0073_CTRL_CMD_DP_TOPOLOGY_ALLOCATE_DISPLAYID_PARAMS *ctrl; struct nvkm_disp *disp = outp->disp; + int ret; ctrl = nvkm_gsp_rm_ctrl_get(&disp->rm.objcom, NV0073_CTRL_CMD_DP_TOPOLOGY_ALLOCATE_DISPLAYID, @@ -904,9 +921,11 @@ r535_dp_mst_id_get(struct nvkm_outp *outp, u32 *pid) ctrl->subDeviceInstance = 0; ctrl->displayId = BIT(outp->index); - ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl)); - if (IS_ERR(ctrl)) - return PTR_ERR(ctrl); + ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl)); + if (ret) { + nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); + return ret; + } *pid = ctrl->displayIdAssigned; nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); @@ -938,38 +957,60 @@ r535_dp_train_target(struct nvkm_outp *outp, u8 target, bool mst, u8 link_nr, u8 { struct nvkm_disp *disp = outp->disp; NV0073_CTRL_DP_CTRL_PARAMS *ctrl; - int ret; - - ctrl = nvkm_gsp_rm_ctrl_get(&disp->rm.objcom, NV0073_CTRL_CMD_DP_CTRL, sizeof(*ctrl)); - if (IS_ERR(ctrl)) - return PTR_ERR(ctrl); + int ret, retries; + u32 cmd, data; - ctrl->subDeviceInstance = 0; - ctrl->displayId = BIT(outp->index); - ctrl->cmd = NVDEF(NV0073_CTRL, DP_CMD, SET_LANE_COUNT, TRUE) | - NVDEF(NV0073_CTRL, DP_CMD, SET_LINK_BW, TRUE) | - NVDEF(NV0073_CTRL, DP_CMD, TRAIN_PHY_REPEATER, YES); - ctrl->data = NVVAL(NV0073_CTRL, DP_DATA, SET_LANE_COUNT, link_nr) | - NVVAL(NV0073_CTRL, DP_DATA, SET_LINK_BW, link_bw) | - NVVAL(NV0073_CTRL, DP_DATA, TARGET, target); + cmd = NVDEF(NV0073_CTRL, DP_CMD, SET_LANE_COUNT, TRUE) | + NVDEF(NV0073_CTRL, DP_CMD, SET_LINK_BW, TRUE) | + NVDEF(NV0073_CTRL, DP_CMD, TRAIN_PHY_REPEATER, YES); + data = NVVAL(NV0073_CTRL, DP_DATA, SET_LANE_COUNT, link_nr) | + NVVAL(NV0073_CTRL, DP_DATA, SET_LINK_BW, link_bw) | + NVVAL(NV0073_CTRL, DP_DATA, TARGET, target); if (mst) - ctrl->cmd |= NVDEF(NV0073_CTRL, DP_CMD, SET_FORMAT_MODE, MULTI_STREAM); + cmd |= NVDEF(NV0073_CTRL, DP_CMD, SET_FORMAT_MODE, MULTI_STREAM); if (outp->dp.dpcd[DPCD_RC02] & DPCD_RC02_ENHANCED_FRAME_CAP) - ctrl->cmd |= NVDEF(NV0073_CTRL, DP_CMD, SET_ENHANCED_FRAMING, TRUE); + cmd |= NVDEF(NV0073_CTRL, DP_CMD, SET_ENHANCED_FRAMING, TRUE); if (target == 0 && (outp->dp.dpcd[DPCD_RC02] & 0x20) && !(outp->dp.dpcd[DPCD_RC03] & DPCD_RC03_TPS4_SUPPORTED)) - ctrl->cmd |= NVDEF(NV0073_CTRL, DP_CMD, POST_LT_ADJ_REQ_GRANTED, YES); + cmd |= NVDEF(NV0073_CTRL, DP_CMD, POST_LT_ADJ_REQ_GRANTED, YES); - ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl)); - if (IS_ERR(ctrl)) - return PTR_ERR(ctrl); + /* We should retry up to 3 times, but only if GSP asks politely */ + for (retries = 0; retries < 3; ++retries) { + ctrl = nvkm_gsp_rm_ctrl_get(&disp->rm.objcom, NV0073_CTRL_CMD_DP_CTRL, + sizeof(*ctrl)); + if (IS_ERR(ctrl)) + return PTR_ERR(ctrl); + + ctrl->subDeviceInstance = 0; + ctrl->displayId = BIT(outp->index); + ctrl->retryTimeMs = 0; + ctrl->cmd = cmd; + ctrl->data = data; + + ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl)); + if (ret == -EAGAIN && ctrl->retryTimeMs) { + /* + * Device (likely an eDP panel) isn't ready yet, wait for the time specified + * by GSP before retrying again + */ + nvkm_debug(&disp->engine.subdev, + "Waiting %dms for GSP LT panel delay before retrying\n", + ctrl->retryTimeMs); + msleep(ctrl->retryTimeMs); + nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); + } else { + /* GSP didn't say to retry, or we were successful */ + if (ctrl->err) + ret = -EIO; + nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); + break; + } + } - ret = ctrl->err ? -EIO : 0; - nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); return ret; } @@ -1036,9 +1077,11 @@ r535_dp_aux_xfer(struct nvkm_outp *outp, u8 type, u32 addr, u8 *data, u8 *psize) ctrl->size = !ctrl->bAddrOnly ? (size - 1) : 0; memcpy(ctrl->data, data, size); - ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl)); - if (IS_ERR(ctrl)) + ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl)); + if (ret) { + nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); return PTR_ERR(ctrl); + } memcpy(data, ctrl->data, size); *psize = ctrl->size; @@ -1111,10 +1154,13 @@ r535_tmds_edid_get(struct nvkm_outp *outp, u8 *data, u16 *psize) ctrl->subDeviceInstance = 0; ctrl->displayId = BIT(outp->index); - ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl)); - if (IS_ERR(ctrl)) - return PTR_ERR(ctrl); + ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl)); + if (ret) { + nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); + return ret; + } + ret = -E2BIG; if (ctrl->bufferSize <= *psize) { memcpy(data, ctrl->edidBuffer, ctrl->bufferSize); *psize = ctrl->bufferSize; @@ -1153,9 +1199,11 @@ r535_outp_new(struct nvkm_disp *disp, u32 id) ctrl->subDeviceInstance = 0; ctrl->displayId = BIT(id); - ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl)); - if (IS_ERR(ctrl)) - return PTR_ERR(ctrl); + ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl)); + if (ret) { + nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); + return ret; + } switch (ctrl->type) { case NV0073_CTRL_SPECIFIC_OR_TYPE_NONE: @@ -1229,9 +1277,11 @@ r535_outp_new(struct nvkm_disp *disp, u32 id) ctrl->sorIndex = ~0; - ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl)); - if (IS_ERR(ctrl)) - return PTR_ERR(ctrl); + ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl)); + if (ret) { + nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); + return ret; + } switch (NVVAL_GET(ctrl->maxLinkRate, NV0073_CTRL_CMD, DP_GET_CAPS, MAX_LINK_RATE)) { case NV0073_CTRL_CMD_DP_GET_CAPS_MAX_LINK_RATE_1_62: @@ -1465,8 +1515,6 @@ r535_disp_oneinit(struct nvkm_disp *disp) bool nvhg = acpi_check_dsm(handle, &NVHG_DSM_GUID, NVHG_DSM_REV, 1ULL << 0x00000014); - printk(KERN_ERR "bl: nbci:%d nvhg:%d\n", nbci, nvhg); - if (nbci || nvhg) { union acpi_object argv4 = { .buffer.type = ACPI_TYPE_BUFFER, @@ -1479,9 +1527,6 @@ r535_disp_oneinit(struct nvkm_disp *disp) if (!obj) { acpi_handle_info(handle, "failed to evaluate _DSM\n"); } else { - printk(KERN_ERR "bl: obj type %d\n", obj->type); - printk(KERN_ERR "bl: obj len %d\n", obj->package.count); - for (int i = 0; i < obj->package.count; i++) { union acpi_object *elt = &obj->package.elements[i]; u32 size; @@ -1491,12 +1536,10 @@ r535_disp_oneinit(struct nvkm_disp *disp) else size = 4; - printk(KERN_ERR "elt %03d: type %d size %d\n", i, elt->type, size); memcpy(&ctrl->backLightData[ctrl->backLightDataSize], &elt->integer.value, size); ctrl->backLightDataSize += size; } - printk(KERN_ERR "bl: data size %d\n", ctrl->backLightDataSize); ctrl->status = 0; ACPI_FREE(obj); } diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/uoutp.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/uoutp.c index e4279f1772a1..377d0e0cef84 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/uoutp.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/uoutp.c @@ -385,7 +385,7 @@ nvkm_uoutp_mthd_inherit(struct nvkm_outp *outp, void *argv, u32 argc) /* Ensure an ior is hooked up to this outp already */ ior = outp->func->inherit(outp); - if (!ior) + if (!ior || !ior->arm.head) return -ENODEV; /* With iors, there will be a separate output path for each type of connector - and all of diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/r535.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/r535.c index d088e636edc3..b903785056b5 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/r535.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/r535.c @@ -242,6 +242,7 @@ r535_chan_id_put(struct nvkm_chan *chan) nvkm_memory_unref(&userd->mem); nvkm_chid_put(runl->chid, userd->chid, &chan->cgrp->lock); list_del(&userd->head); + kfree(userd); } break; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c index 44fb86841c05..9ee58e2a0eb2 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c @@ -70,6 +70,20 @@ struct r535_gsp_msg { #define GSP_MSG_HDR_SIZE offsetof(struct r535_gsp_msg, data) +static int +r535_rpc_status_to_errno(uint32_t rpc_status) +{ + switch (rpc_status) { + case 0x55: /* NV_ERR_NOT_READY */ + case 0x66: /* NV_ERR_TIMEOUT_RETRY */ + return -EAGAIN; + case 0x51: /* NV_ERR_NO_MEMORY */ + return -ENOMEM; + default: + return -EINVAL; + } +} + static void * r535_gsp_msgq_wait(struct nvkm_gsp *gsp, u32 repc, u32 *prepc, int *ptime) { @@ -298,7 +312,8 @@ retry: struct nvkm_gsp_msgq_ntfy *ntfy = &gsp->msgq.ntfy[i]; if (ntfy->fn == msg->function) { - ntfy->func(ntfy->priv, ntfy->fn, msg->data, msg->length - sizeof(*msg)); + if (ntfy->func) + ntfy->func(ntfy->priv, ntfy->fn, msg->data, msg->length - sizeof(*msg)); break; } } @@ -583,14 +598,14 @@ r535_gsp_rpc_rm_alloc_push(struct nvkm_gsp_object *object, void *argv, u32 repc) return rpc; if (rpc->status) { - nvkm_error(&gsp->subdev, "RM_ALLOC: 0x%x\n", rpc->status); - ret = ERR_PTR(-EINVAL); + ret = ERR_PTR(r535_rpc_status_to_errno(rpc->status)); + if (PTR_ERR(ret) != -EAGAIN) + nvkm_error(&gsp->subdev, "RM_ALLOC: 0x%x\n", rpc->status); } else { ret = repc ? rpc->params : NULL; } - if (IS_ERR_OR_NULL(ret)) - nvkm_gsp_rpc_done(gsp, rpc); + nvkm_gsp_rpc_done(gsp, rpc); return ret; } @@ -623,29 +638,34 @@ r535_gsp_rpc_rm_ctrl_done(struct nvkm_gsp_object *object, void *repv) { rpc_gsp_rm_control_v03_00 *rpc = container_of(repv, typeof(*rpc), params); + if (!repv) + return; nvkm_gsp_rpc_done(object->client->gsp, rpc); } -static void * -r535_gsp_rpc_rm_ctrl_push(struct nvkm_gsp_object *object, void *argv, u32 repc) +static int +r535_gsp_rpc_rm_ctrl_push(struct nvkm_gsp_object *object, void **argv, u32 repc) { - rpc_gsp_rm_control_v03_00 *rpc = container_of(argv, typeof(*rpc), params); + rpc_gsp_rm_control_v03_00 *rpc = container_of((*argv), typeof(*rpc), params); struct nvkm_gsp *gsp = object->client->gsp; - void *ret; + int ret = 0; rpc = nvkm_gsp_rpc_push(gsp, rpc, true, repc); - if (IS_ERR_OR_NULL(rpc)) - return rpc; + if (IS_ERR_OR_NULL(rpc)) { + *argv = NULL; + return PTR_ERR(rpc); + } if (rpc->status) { - nvkm_error(&gsp->subdev, "cli:0x%08x obj:0x%08x ctrl cmd:0x%08x failed: 0x%08x\n", - object->client->object.handle, object->handle, rpc->cmd, rpc->status); - ret = ERR_PTR(-EINVAL); - } else { - ret = repc ? rpc->params : NULL; + ret = r535_rpc_status_to_errno(rpc->status); + if (ret != -EAGAIN) + nvkm_error(&gsp->subdev, "cli:0x%08x obj:0x%08x ctrl cmd:0x%08x failed: 0x%08x\n", + object->client->object.handle, object->handle, rpc->cmd, rpc->status); } - if (IS_ERR_OR_NULL(ret)) + if (repc) + *argv = rpc->params; + else nvkm_gsp_rpc_done(gsp, rpc); return ret; @@ -843,9 +863,11 @@ r535_gsp_intr_get_table(struct nvkm_gsp *gsp) if (IS_ERR(ctrl)) return PTR_ERR(ctrl); - ctrl = nvkm_gsp_rm_ctrl_push(&gsp->internal.device.subdevice, ctrl, sizeof(*ctrl)); - if (WARN_ON(IS_ERR(ctrl))) - return PTR_ERR(ctrl); + ret = nvkm_gsp_rm_ctrl_push(&gsp->internal.device.subdevice, &ctrl, sizeof(*ctrl)); + if (WARN_ON(ret)) { + nvkm_gsp_rm_ctrl_done(&gsp->internal.device.subdevice, ctrl); + return ret; + } for (unsigned i = 0; i < ctrl->tableLen; i++) { enum nvkm_subdev_type type; @@ -1099,16 +1121,12 @@ r535_gsp_acpi_caps(acpi_handle handle, CAPS_METHOD_DATA *caps) if (!obj) return; - printk(KERN_ERR "nvop: obj type %d\n", obj->type); - printk(KERN_ERR "nvop: obj len %d\n", obj->buffer.length); - if (WARN_ON(obj->type != ACPI_TYPE_BUFFER) || WARN_ON(obj->buffer.length != 4)) return; caps->status = 0; caps->optimusCaps = *(u32 *)obj->buffer.pointer; - printk(KERN_ERR "nvop: caps %08x\n", caps->optimusCaps); ACPI_FREE(obj); @@ -1135,9 +1153,6 @@ r535_gsp_acpi_jt(acpi_handle handle, JT_METHOD_DATA *jt) if (!obj) return; - printk(KERN_ERR "jt: obj type %d\n", obj->type); - printk(KERN_ERR "jt: obj len %d\n", obj->buffer.length); - if (WARN_ON(obj->type != ACPI_TYPE_BUFFER) || WARN_ON(obj->buffer.length != 4)) return; @@ -1146,7 +1161,6 @@ r535_gsp_acpi_jt(acpi_handle handle, JT_METHOD_DATA *jt) jt->jtCaps = *(u32 *)obj->buffer.pointer; jt->jtRevId = (jt->jtCaps & 0xfff00000) >> 20; jt->bSBIOSCaps = 0; - printk(KERN_ERR "jt: caps %08x rev:%04x\n", jt->jtCaps, jt->jtRevId); ACPI_FREE(obj); @@ -1157,6 +1171,8 @@ static void r535_gsp_acpi_mux_id(acpi_handle handle, u32 id, MUX_METHOD_DATA_ELEMENT *mode, MUX_METHOD_DATA_ELEMENT *part) { + union acpi_object mux_arg = { ACPI_TYPE_INTEGER }; + struct acpi_object_list input = { 1, &mux_arg }; acpi_handle iter = NULL, handle_mux = NULL; acpi_status status; unsigned long long value; @@ -1179,14 +1195,18 @@ r535_gsp_acpi_mux_id(acpi_handle handle, u32 id, MUX_METHOD_DATA_ELEMENT *mode, if (!handle_mux) return; - status = acpi_evaluate_integer(handle_mux, "MXDM", NULL, &value); + /* I -think- 0 means "acquire" according to nvidia's driver source */ + input.pointer->integer.type = ACPI_TYPE_INTEGER; + input.pointer->integer.value = 0; + + status = acpi_evaluate_integer(handle_mux, "MXDM", &input, &value); if (ACPI_SUCCESS(status)) { mode->acpiId = id; mode->mode = value; mode->status = 0; } - status = acpi_evaluate_integer(handle_mux, "MXDS", NULL, &value); + status = acpi_evaluate_integer(handle_mux, "MXDS", &input, &value); if (ACPI_SUCCESS(status)) { part->acpiId = id; part->mode = value; @@ -1232,8 +1252,8 @@ r535_gsp_acpi_dod(acpi_handle handle, DOD_METHOD_DATA *dod) dod->acpiIdListLen += sizeof(dod->acpiIdList[0]); } - printk(KERN_ERR "_DOD: ok! len:%d\n", dod->acpiIdListLen); dod->status = 0; + kfree(output.pointer); } #endif @@ -2186,7 +2206,9 @@ r535_gsp_oneinit(struct nvkm_gsp *gsp) r535_gsp_msg_ntfy_add(gsp, NV_VGPU_MSG_EVENT_MMU_FAULT_QUEUED, r535_gsp_msg_mmu_fault_queued, gsp); r535_gsp_msg_ntfy_add(gsp, NV_VGPU_MSG_EVENT_OS_ERROR_LOG, r535_gsp_msg_os_error_log, gsp); - + r535_gsp_msg_ntfy_add(gsp, NV_VGPU_MSG_EVENT_PERF_BRIDGELESS_INFO_UPDATE, NULL, NULL); + r535_gsp_msg_ntfy_add(gsp, NV_VGPU_MSG_EVENT_UCODE_LIBOS_PRINT, NULL, NULL); + r535_gsp_msg_ntfy_add(gsp, NV_VGPU_MSG_EVENT_GSP_SEND_USER_SHARED_DATA, NULL, NULL); ret = r535_gsp_rm_boot_ctor(gsp); if (ret) return ret; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/gk20a.c b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/gk20a.c index 1b811d6972a1..201022ae9214 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/gk20a.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/gk20a.c @@ -49,14 +49,14 @@ #include <subdev/mmu.h> struct gk20a_instobj { - struct nvkm_memory memory; + struct nvkm_instobj base; struct nvkm_mm_node *mn; struct gk20a_instmem *imem; /* CPU mapping */ u32 *vaddr; }; -#define gk20a_instobj(p) container_of((p), struct gk20a_instobj, memory) +#define gk20a_instobj(p) container_of((p), struct gk20a_instobj, base.memory) /* * Used for objects allocated using the DMA API @@ -148,7 +148,7 @@ gk20a_instobj_iommu_recycle_vaddr(struct gk20a_instobj_iommu *obj) list_del(&obj->vaddr_node); vunmap(obj->base.vaddr); obj->base.vaddr = NULL; - imem->vaddr_use -= nvkm_memory_size(&obj->base.memory); + imem->vaddr_use -= nvkm_memory_size(&obj->base.base.memory); nvkm_debug(&imem->base.subdev, "vaddr used: %x/%x\n", imem->vaddr_use, imem->vaddr_max); } @@ -283,7 +283,7 @@ gk20a_instobj_map(struct nvkm_memory *memory, u64 offset, struct nvkm_vmm *vmm, { struct gk20a_instobj *node = gk20a_instobj(memory); struct nvkm_vmm_map map = { - .memory = &node->memory, + .memory = &node->base.memory, .offset = offset, .mem = node->mn, }; @@ -391,8 +391,8 @@ gk20a_instobj_ctor_dma(struct gk20a_instmem *imem, u32 npages, u32 align, return -ENOMEM; *_node = &node->base; - nvkm_memory_ctor(&gk20a_instobj_func_dma, &node->base.memory); - node->base.memory.ptrs = &gk20a_instobj_ptrs; + nvkm_memory_ctor(&gk20a_instobj_func_dma, &node->base.base.memory); + node->base.base.memory.ptrs = &gk20a_instobj_ptrs; node->base.vaddr = dma_alloc_attrs(dev, npages << PAGE_SHIFT, &node->handle, GFP_KERNEL, @@ -438,8 +438,8 @@ gk20a_instobj_ctor_iommu(struct gk20a_instmem *imem, u32 npages, u32 align, *_node = &node->base; node->dma_addrs = (void *)(node->pages + npages); - nvkm_memory_ctor(&gk20a_instobj_func_iommu, &node->base.memory); - node->base.memory.ptrs = &gk20a_instobj_ptrs; + nvkm_memory_ctor(&gk20a_instobj_func_iommu, &node->base.base.memory); + node->base.base.memory.ptrs = &gk20a_instobj_ptrs; /* Allocate backing memory */ for (i = 0; i < npages; i++) { @@ -533,7 +533,7 @@ gk20a_instobj_new(struct nvkm_instmem *base, u32 size, u32 align, bool zero, else ret = gk20a_instobj_ctor_dma(imem, size >> PAGE_SHIFT, align, &node); - *pmemory = node ? &node->memory : NULL; + *pmemory = node ? &node->base.memory : NULL; if (ret) return ret; diff --git a/drivers/gpu/drm/panel/panel-leadtek-ltk050h3146w.c b/drivers/gpu/drm/panel/panel-leadtek-ltk050h3146w.c index 6e3670508e3a..30919c872ac8 100644 --- a/drivers/gpu/drm/panel/panel-leadtek-ltk050h3146w.c +++ b/drivers/gpu/drm/panel/panel-leadtek-ltk050h3146w.c @@ -326,7 +326,7 @@ static const struct drm_display_mode ltk050h3148w_mode = { static const struct ltk050h3146w_desc ltk050h3148w_data = { .mode = <k050h3148w_mode, .init = ltk050h3148w_init_sequence, - .mode_flags = MIPI_DSI_MODE_VIDEO_SYNC_PULSE, + .mode_flags = MIPI_DSI_MODE_VIDEO_SYNC_PULSE | MIPI_DSI_MODE_VIDEO_BURST, }; static int ltk050h3146w_init_sequence(struct ltk050h3146w *ctx) diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c index d9e9829b2200..b9c7c0ed7bcc 100644 --- a/drivers/hid/hid-apple.c +++ b/drivers/hid/hid-apple.c @@ -347,6 +347,8 @@ static const struct apple_non_apple_keyboard non_apple_keyboards[] = { { "Hailuck" }, { "Jamesdonkey" }, { "A3R" }, + { "hfd.cn" }, + { "WKB603" }, }; static bool apple_is_non_apple_keyboard(struct hid_device *hdev) diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index c6e4e0d1f214..72046039d1be 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -740,6 +740,7 @@ #define USB_VENDOR_ID_LABTEC 0x1020 #define USB_DEVICE_ID_LABTEC_WIRELESS_KEYBOARD 0x0006 +#define USB_DEVICE_ID_LABTEC_ODDOR_HANDBRAKE 0x8888 #define USB_VENDOR_ID_LAVIEW 0x22D4 #define USB_DEVICE_ID_GLORIOUS_MODEL_I 0x1503 diff --git a/drivers/hid/hid-lenovo.c b/drivers/hid/hid-lenovo.c index 7c1b33be9d13..149a3c74346b 100644 --- a/drivers/hid/hid-lenovo.c +++ b/drivers/hid/hid-lenovo.c @@ -692,7 +692,8 @@ static int lenovo_event_cptkbd(struct hid_device *hdev, * so set middlebutton_state to 3 * to never apply workaround anymore */ - if (cptkbd_data->middlebutton_state == 1 && + if (hdev->product == USB_DEVICE_ID_LENOVO_CUSBKBD && + cptkbd_data->middlebutton_state == 1 && usage->type == EV_REL && (usage->code == REL_X || usage->code == REL_Y)) { cptkbd_data->middlebutton_state = 3; diff --git a/drivers/hid/hid-nintendo.c b/drivers/hid/hid-nintendo.c index 138f154fecef..997c3a1adaca 100644 --- a/drivers/hid/hid-nintendo.c +++ b/drivers/hid/hid-nintendo.c @@ -325,28 +325,28 @@ struct joycon_imu_cal { * All the controller's button values are stored in a u32. * They can be accessed with bitwise ANDs. */ -static const u32 JC_BTN_Y = BIT(0); -static const u32 JC_BTN_X = BIT(1); -static const u32 JC_BTN_B = BIT(2); -static const u32 JC_BTN_A = BIT(3); -static const u32 JC_BTN_SR_R = BIT(4); -static const u32 JC_BTN_SL_R = BIT(5); -static const u32 JC_BTN_R = BIT(6); -static const u32 JC_BTN_ZR = BIT(7); -static const u32 JC_BTN_MINUS = BIT(8); -static const u32 JC_BTN_PLUS = BIT(9); -static const u32 JC_BTN_RSTICK = BIT(10); -static const u32 JC_BTN_LSTICK = BIT(11); -static const u32 JC_BTN_HOME = BIT(12); -static const u32 JC_BTN_CAP = BIT(13); /* capture button */ -static const u32 JC_BTN_DOWN = BIT(16); -static const u32 JC_BTN_UP = BIT(17); -static const u32 JC_BTN_RIGHT = BIT(18); -static const u32 JC_BTN_LEFT = BIT(19); -static const u32 JC_BTN_SR_L = BIT(20); -static const u32 JC_BTN_SL_L = BIT(21); -static const u32 JC_BTN_L = BIT(22); -static const u32 JC_BTN_ZL = BIT(23); +#define JC_BTN_Y BIT(0) +#define JC_BTN_X BIT(1) +#define JC_BTN_B BIT(2) +#define JC_BTN_A BIT(3) +#define JC_BTN_SR_R BIT(4) +#define JC_BTN_SL_R BIT(5) +#define JC_BTN_R BIT(6) +#define JC_BTN_ZR BIT(7) +#define JC_BTN_MINUS BIT(8) +#define JC_BTN_PLUS BIT(9) +#define JC_BTN_RSTICK BIT(10) +#define JC_BTN_LSTICK BIT(11) +#define JC_BTN_HOME BIT(12) +#define JC_BTN_CAP BIT(13) /* capture button */ +#define JC_BTN_DOWN BIT(16) +#define JC_BTN_UP BIT(17) +#define JC_BTN_RIGHT BIT(18) +#define JC_BTN_LEFT BIT(19) +#define JC_BTN_SR_L BIT(20) +#define JC_BTN_SL_L BIT(21) +#define JC_BTN_L BIT(22) +#define JC_BTN_ZL BIT(23) enum joycon_msg_type { JOYCON_MSG_TYPE_NONE, @@ -927,14 +927,27 @@ static int joycon_request_calibration(struct joycon_ctlr *ctlr) */ static void joycon_calc_imu_cal_divisors(struct joycon_ctlr *ctlr) { - int i; + int i, divz = 0; for (i = 0; i < 3; i++) { ctlr->imu_cal_accel_divisor[i] = ctlr->accel_cal.scale[i] - ctlr->accel_cal.offset[i]; ctlr->imu_cal_gyro_divisor[i] = ctlr->gyro_cal.scale[i] - ctlr->gyro_cal.offset[i]; + + if (ctlr->imu_cal_accel_divisor[i] == 0) { + ctlr->imu_cal_accel_divisor[i] = 1; + divz++; + } + + if (ctlr->imu_cal_gyro_divisor[i] == 0) { + ctlr->imu_cal_gyro_divisor[i] = 1; + divz++; + } } + + if (divz) + hid_warn(ctlr->hdev, "inaccurate IMU divisors (%d)\n", divz); } static const s16 DFLT_ACCEL_OFFSET /*= 0*/; @@ -1163,16 +1176,16 @@ static void joycon_parse_imu_report(struct joycon_ctlr *ctlr, JC_IMU_SAMPLES_PER_DELTA_AVG) { ctlr->imu_avg_delta_ms = ctlr->imu_delta_samples_sum / ctlr->imu_delta_samples_count; - /* don't ever want divide by zero shenanigans */ - if (ctlr->imu_avg_delta_ms == 0) { - ctlr->imu_avg_delta_ms = 1; - hid_warn(ctlr->hdev, - "calculated avg imu delta of 0\n"); - } ctlr->imu_delta_samples_count = 0; ctlr->imu_delta_samples_sum = 0; } + /* don't ever want divide by zero shenanigans */ + if (ctlr->imu_avg_delta_ms == 0) { + ctlr->imu_avg_delta_ms = 1; + hid_warn(ctlr->hdev, "calculated avg imu delta of 0\n"); + } + /* useful for debugging IMU sample rate */ hid_dbg(ctlr->hdev, "imu_report: ms=%u last_ms=%u delta=%u avg_delta=%u\n", diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index ea472923fab0..e0bbf0c6345d 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -121,6 +121,7 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_M406XE), HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X_V2), HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_PENSKETCH_T609A), HID_QUIRK_MULTI_INPUT }, + { HID_USB_DEVICE(USB_VENDOR_ID_LABTEC, USB_DEVICE_ID_LABTEC_ODDOR_HANDBRAKE), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_OPTICAL_USB_MOUSE_600E), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_608D), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_6019), HID_QUIRK_ALWAYS_POLL }, diff --git a/drivers/hid/i2c-hid/i2c-hid-acpi.c b/drivers/hid/i2c-hid/i2c-hid-acpi.c index ac918a9ea8d3..1b49243adb16 100644 --- a/drivers/hid/i2c-hid/i2c-hid-acpi.c +++ b/drivers/hid/i2c-hid/i2c-hid-acpi.c @@ -40,6 +40,11 @@ static const struct acpi_device_id i2c_hid_acpi_blacklist[] = { * ICN8505 controller, has a _CID of PNP0C50 but is not HID compatible. */ { "CHPN0001" }, + /* + * The IDEA5002 ACPI device causes high interrupt usage and spurious + * wakeups from suspend. + */ + { "IDEA5002" }, { } }; diff --git a/drivers/i2c/busses/i2c-aspeed.c b/drivers/i2c/busses/i2c-aspeed.c index 28e2a5fc4528..5511fd46a65e 100644 --- a/drivers/i2c/busses/i2c-aspeed.c +++ b/drivers/i2c/busses/i2c-aspeed.c @@ -249,18 +249,46 @@ static u32 aspeed_i2c_slave_irq(struct aspeed_i2c_bus *bus, u32 irq_status) if (!slave) return 0; - command = readl(bus->base + ASPEED_I2C_CMD_REG); + /* + * Handle stop conditions early, prior to SLAVE_MATCH. Some masters may drive + * transfers with low enough latency between the nak/stop phase of the current + * command and the start/address phase of the following command that the + * interrupts are coalesced by the time we process them. + */ + if (irq_status & ASPEED_I2CD_INTR_NORMAL_STOP) { + irq_handled |= ASPEED_I2CD_INTR_NORMAL_STOP; + bus->slave_state = ASPEED_I2C_SLAVE_STOP; + } + + if (irq_status & ASPEED_I2CD_INTR_TX_NAK && + bus->slave_state == ASPEED_I2C_SLAVE_READ_PROCESSED) { + irq_handled |= ASPEED_I2CD_INTR_TX_NAK; + bus->slave_state = ASPEED_I2C_SLAVE_STOP; + } + + /* Propagate any stop conditions to the slave implementation. */ + if (bus->slave_state == ASPEED_I2C_SLAVE_STOP) { + i2c_slave_event(slave, I2C_SLAVE_STOP, &value); + bus->slave_state = ASPEED_I2C_SLAVE_INACTIVE; + } - /* Slave was requested, restart state machine. */ + /* + * Now that we've dealt with any potentially coalesced stop conditions, + * address any start conditions. + */ if (irq_status & ASPEED_I2CD_INTR_SLAVE_MATCH) { irq_handled |= ASPEED_I2CD_INTR_SLAVE_MATCH; bus->slave_state = ASPEED_I2C_SLAVE_START; } - /* Slave is not currently active, irq was for someone else. */ + /* + * If the slave has been stopped and not started then slave interrupt + * handling is complete. + */ if (bus->slave_state == ASPEED_I2C_SLAVE_INACTIVE) return irq_handled; + command = readl(bus->base + ASPEED_I2C_CMD_REG); dev_dbg(bus->dev, "slave irq status 0x%08x, cmd 0x%08x\n", irq_status, command); @@ -279,17 +307,6 @@ static u32 aspeed_i2c_slave_irq(struct aspeed_i2c_bus *bus, u32 irq_status) irq_handled |= ASPEED_I2CD_INTR_RX_DONE; } - /* Slave was asked to stop. */ - if (irq_status & ASPEED_I2CD_INTR_NORMAL_STOP) { - irq_handled |= ASPEED_I2CD_INTR_NORMAL_STOP; - bus->slave_state = ASPEED_I2C_SLAVE_STOP; - } - if (irq_status & ASPEED_I2CD_INTR_TX_NAK && - bus->slave_state == ASPEED_I2C_SLAVE_READ_PROCESSED) { - irq_handled |= ASPEED_I2CD_INTR_TX_NAK; - bus->slave_state = ASPEED_I2C_SLAVE_STOP; - } - switch (bus->slave_state) { case ASPEED_I2C_SLAVE_READ_REQUESTED: if (unlikely(irq_status & ASPEED_I2CD_INTR_TX_ACK)) @@ -324,8 +341,7 @@ static u32 aspeed_i2c_slave_irq(struct aspeed_i2c_bus *bus, u32 irq_status) i2c_slave_event(slave, I2C_SLAVE_WRITE_RECEIVED, &value); break; case ASPEED_I2C_SLAVE_STOP: - i2c_slave_event(slave, I2C_SLAVE_STOP, &value); - bus->slave_state = ASPEED_I2C_SLAVE_INACTIVE; + /* Stop event handling is done early. Unreachable. */ break; case ASPEED_I2C_SLAVE_START: /* Slave was just started. Waiting for the next event. */; diff --git a/drivers/i2c/busses/i2c-qcom-geni.c b/drivers/i2c/busses/i2c-qcom-geni.c index 6d829ed2f868..0d2e7171e3a6 100644 --- a/drivers/i2c/busses/i2c-qcom-geni.c +++ b/drivers/i2c/busses/i2c-qcom-geni.c @@ -858,6 +858,7 @@ static int geni_i2c_probe(struct platform_device *pdev) ret = geni_se_resources_on(&gi2c->se); if (ret) { dev_err(dev, "Error turning on resources %d\n", ret); + clk_disable_unprepare(gi2c->core_clk); return ret; } proto = geni_se_read_proto(&gi2c->se); @@ -877,8 +878,11 @@ static int geni_i2c_probe(struct platform_device *pdev) /* FIFO is disabled, so we can only use GPI DMA */ gi2c->gpi_mode = true; ret = setup_gpi_dma(gi2c); - if (ret) + if (ret) { + geni_se_resources_off(&gi2c->se); + clk_disable_unprepare(gi2c->core_clk); return dev_err_probe(dev, ret, "Failed to setup GPI DMA mode\n"); + } dev_dbg(dev, "Using GPI DMA mode for I2C\n"); } else { @@ -891,6 +895,8 @@ static int geni_i2c_probe(struct platform_device *pdev) if (!tx_depth) { dev_err(dev, "Invalid TX FIFO depth\n"); + geni_se_resources_off(&gi2c->se); + clk_disable_unprepare(gi2c->core_clk); return -EINVAL; } diff --git a/drivers/i2c/busses/i2c-rk3x.c b/drivers/i2c/busses/i2c-rk3x.c index a044ca0c35a1..4362db7c5789 100644 --- a/drivers/i2c/busses/i2c-rk3x.c +++ b/drivers/i2c/busses/i2c-rk3x.c @@ -178,6 +178,7 @@ struct rk3x_i2c_soc_data { * @clk: function clk for rk3399 or function & Bus clks for others * @pclk: Bus clk for rk3399 * @clk_rate_nb: i2c clk rate change notify + * @irq: irq number * @t: I2C known timing information * @lock: spinlock for the i2c bus * @wait: the waitqueue to wait for i2c transfer @@ -200,6 +201,7 @@ struct rk3x_i2c { struct clk *clk; struct clk *pclk; struct notifier_block clk_rate_nb; + int irq; /* Settings */ struct i2c_timings t; @@ -1087,13 +1089,18 @@ static int rk3x_i2c_xfer_common(struct i2c_adapter *adap, spin_unlock_irqrestore(&i2c->lock, flags); - rk3x_i2c_start(i2c); - if (!polling) { + rk3x_i2c_start(i2c); + timeout = wait_event_timeout(i2c->wait, !i2c->busy, msecs_to_jiffies(WAIT_TIMEOUT)); } else { + disable_irq(i2c->irq); + rk3x_i2c_start(i2c); + timeout = rk3x_i2c_wait_xfer_poll(i2c); + + enable_irq(i2c->irq); } spin_lock_irqsave(&i2c->lock, flags); @@ -1310,6 +1317,8 @@ static int rk3x_i2c_probe(struct platform_device *pdev) return ret; } + i2c->irq = irq; + platform_set_drvdata(pdev, i2c); if (i2c->soc_data->calc_timings == rk3x_i2c_v0_calc_timings) { diff --git a/drivers/i2c/i2c-core.h b/drivers/i2c/i2c-core.h index 05b8b8dfa9bd..36587f38dff3 100644 --- a/drivers/i2c/i2c-core.h +++ b/drivers/i2c/i2c-core.h @@ -3,6 +3,7 @@ * i2c-core.h - interfaces internal to the I2C framework */ +#include <linux/kconfig.h> #include <linux/rwsem.h> struct i2c_devinfo { @@ -29,7 +30,8 @@ int i2c_dev_irq_from_resources(const struct resource *resources, */ static inline bool i2c_in_atomic_xfer_mode(void) { - return system_state > SYSTEM_RUNNING && !preemptible(); + return system_state > SYSTEM_RUNNING && + (IS_ENABLED(CONFIG_PREEMPT_COUNT) ? !preemptible() : irqs_disabled()); } static inline int __i2c_lock_bus_helper(struct i2c_adapter *adap) diff --git a/drivers/iio/accel/kionix-kx022a.c b/drivers/iio/accel/kionix-kx022a.c index 60864be3a667..53d59a04ae15 100644 --- a/drivers/iio/accel/kionix-kx022a.c +++ b/drivers/iio/accel/kionix-kx022a.c @@ -393,17 +393,17 @@ static const unsigned int kx022a_odrs[] = { * (range / 2^bits) * g = (range / 2^bits) * 9.80665 m/s^2 * => KX022A uses 16 bit (HiRes mode - assume the low 8 bits are zeroed * in low-power mode(?) ) - * => +/-2G => 4 / 2^16 * 9,80665 * 10^6 (to scale to micro) - * => +/-2G - 598.550415 - * +/-4G - 1197.10083 - * +/-8G - 2394.20166 - * +/-16G - 4788.40332 + * => +/-2G => 4 / 2^16 * 9,80665 + * => +/-2G - 0.000598550415 + * +/-4G - 0.00119710083 + * +/-8G - 0.00239420166 + * +/-16G - 0.00478840332 */ static const int kx022a_scale_table[][2] = { - { 598, 550415 }, - { 1197, 100830 }, - { 2394, 201660 }, - { 4788, 403320 }, + { 0, 598550 }, + { 0, 1197101 }, + { 0, 2394202 }, + { 0, 4788403 }, }; static int kx022a_read_avail(struct iio_dev *indio_dev, @@ -422,7 +422,7 @@ static int kx022a_read_avail(struct iio_dev *indio_dev, *vals = (const int *)kx022a_scale_table; *length = ARRAY_SIZE(kx022a_scale_table) * ARRAY_SIZE(kx022a_scale_table[0]); - *type = IIO_VAL_INT_PLUS_MICRO; + *type = IIO_VAL_INT_PLUS_NANO; return IIO_AVAIL_LIST; default: return -EINVAL; @@ -485,6 +485,20 @@ static int kx022a_turn_on_unlock(struct kx022a_data *data) return ret; } +static int kx022a_write_raw_get_fmt(struct iio_dev *idev, + struct iio_chan_spec const *chan, + long mask) +{ + switch (mask) { + case IIO_CHAN_INFO_SCALE: + return IIO_VAL_INT_PLUS_NANO; + case IIO_CHAN_INFO_SAMP_FREQ: + return IIO_VAL_INT_PLUS_MICRO; + default: + return -EINVAL; + } +} + static int kx022a_write_raw(struct iio_dev *idev, struct iio_chan_spec const *chan, int val, int val2, long mask) @@ -629,7 +643,7 @@ static int kx022a_read_raw(struct iio_dev *idev, kx022a_reg2scale(regval, val, val2); - return IIO_VAL_INT_PLUS_MICRO; + return IIO_VAL_INT_PLUS_NANO; } return -EINVAL; @@ -856,6 +870,7 @@ static int kx022a_fifo_flush(struct iio_dev *idev, unsigned int samples) static const struct iio_info kx022a_info = { .read_raw = &kx022a_read_raw, .write_raw = &kx022a_write_raw, + .write_raw_get_fmt = &kx022a_write_raw_get_fmt, .read_avail = &kx022a_read_avail, .validate_trigger = iio_validate_own_trigger, diff --git a/drivers/iio/adc/imx93_adc.c b/drivers/iio/adc/imx93_adc.c index 9bb1e4ba1aee..4ccf4819f1f1 100644 --- a/drivers/iio/adc/imx93_adc.c +++ b/drivers/iio/adc/imx93_adc.c @@ -93,6 +93,10 @@ static const struct iio_chan_spec imx93_adc_iio_channels[] = { IMX93_ADC_CHAN(1), IMX93_ADC_CHAN(2), IMX93_ADC_CHAN(3), + IMX93_ADC_CHAN(4), + IMX93_ADC_CHAN(5), + IMX93_ADC_CHAN(6), + IMX93_ADC_CHAN(7), }; static void imx93_adc_power_down(struct imx93_adc *adc) diff --git a/drivers/iio/adc/mcp3564.c b/drivers/iio/adc/mcp3564.c index e3f1de5fcc5a..311b613b6057 100644 --- a/drivers/iio/adc/mcp3564.c +++ b/drivers/iio/adc/mcp3564.c @@ -918,7 +918,7 @@ static int mcp3564_write_raw(struct iio_dev *indio_dev, mutex_unlock(&adc->lock); return ret; case IIO_CHAN_INFO_CALIBBIAS: - if (val < mcp3564_calib_bias[0] && val > mcp3564_calib_bias[2]) + if (val < mcp3564_calib_bias[0] || val > mcp3564_calib_bias[2]) return -EINVAL; mutex_lock(&adc->lock); @@ -928,7 +928,7 @@ static int mcp3564_write_raw(struct iio_dev *indio_dev, mutex_unlock(&adc->lock); return ret; case IIO_CHAN_INFO_CALIBSCALE: - if (val < mcp3564_calib_scale[0] && val > mcp3564_calib_scale[2]) + if (val < mcp3564_calib_scale[0] || val > mcp3564_calib_scale[2]) return -EINVAL; if (adc->calib_scale == val) @@ -1122,7 +1122,7 @@ static int mcp3564_config(struct iio_dev *indio_dev) enum mcp3564_ids ids; int ret = 0; unsigned int tmp = 0x01; - bool err = true; + bool err = false; /* * The address is set on a per-device basis by fuses in the factory, @@ -1509,5 +1509,5 @@ static struct spi_driver mcp3564_driver = { module_spi_driver(mcp3564_driver); MODULE_AUTHOR("Marius Cristea <marius.cristea@microchip.com>"); -MODULE_DESCRIPTION("Microchip MCP346x/MCP346xR and MCP356x/MCP346xR ADCs"); +MODULE_DESCRIPTION("Microchip MCP346x/MCP346xR and MCP356x/MCP356xR ADCs"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/iio/adc/meson_saradc.c b/drivers/iio/adc/meson_saradc.c index 950ff13e6dde..13b473d8c6c7 100644 --- a/drivers/iio/adc/meson_saradc.c +++ b/drivers/iio/adc/meson_saradc.c @@ -1241,6 +1241,20 @@ static const struct meson_sar_adc_param meson_sar_adc_gxl_param = { .cmv_select = 1, }; +static const struct meson_sar_adc_param meson_sar_adc_axg_param = { + .has_bl30_integration = true, + .clock_rate = 1200000, + .bandgap_reg = MESON_SAR_ADC_REG11, + .regmap_config = &meson_sar_adc_regmap_config_gxbb, + .resolution = 12, + .disable_ring_counter = 1, + .has_reg11 = true, + .vref_volatge = 1, + .has_vref_select = true, + .vref_select = VREF_VDDA, + .cmv_select = 1, +}; + static const struct meson_sar_adc_param meson_sar_adc_g12a_param = { .has_bl30_integration = false, .clock_rate = 1200000, @@ -1285,7 +1299,7 @@ static const struct meson_sar_adc_data meson_sar_adc_gxm_data = { }; static const struct meson_sar_adc_data meson_sar_adc_axg_data = { - .param = &meson_sar_adc_gxl_param, + .param = &meson_sar_adc_axg_param, .name = "meson-axg-saradc", }; diff --git a/drivers/iio/adc/ti_am335x_adc.c b/drivers/iio/adc/ti_am335x_adc.c index c755e8cd5220..95fa857e8aad 100644 --- a/drivers/iio/adc/ti_am335x_adc.c +++ b/drivers/iio/adc/ti_am335x_adc.c @@ -670,8 +670,10 @@ static int tiadc_probe(struct platform_device *pdev) platform_set_drvdata(pdev, indio_dev); err = tiadc_request_dma(pdev, adc_dev); - if (err && err == -EPROBE_DEFER) + if (err && err != -ENODEV) { + dev_err_probe(&pdev->dev, err, "DMA request failed\n"); goto err_dma; + } return 0; diff --git a/drivers/iio/buffer/industrialio-triggered-buffer.c b/drivers/iio/buffer/industrialio-triggered-buffer.c index c7671b1f5ead..c06515987e7a 100644 --- a/drivers/iio/buffer/industrialio-triggered-buffer.c +++ b/drivers/iio/buffer/industrialio-triggered-buffer.c @@ -46,6 +46,16 @@ int iio_triggered_buffer_setup_ext(struct iio_dev *indio_dev, struct iio_buffer *buffer; int ret; + /* + * iio_triggered_buffer_cleanup() assumes that the buffer allocated here + * is assigned to indio_dev->buffer but this is only the case if this + * function is the first caller to iio_device_attach_buffer(). If + * indio_dev->buffer is already set then we can't proceed otherwise the + * cleanup function will try to free a buffer that was not allocated here. + */ + if (indio_dev->buffer) + return -EADDRINUSE; + buffer = iio_kfifo_allocate(); if (!buffer) { ret = -ENOMEM; diff --git a/drivers/iio/common/ms_sensors/ms_sensors_i2c.c b/drivers/iio/common/ms_sensors/ms_sensors_i2c.c index 6633b35a94e6..9c9bc77003c7 100644 --- a/drivers/iio/common/ms_sensors/ms_sensors_i2c.c +++ b/drivers/iio/common/ms_sensors/ms_sensors_i2c.c @@ -15,8 +15,8 @@ /* Conversion times in us */ static const u16 ms_sensors_ht_t_conversion_time[] = { 50000, 25000, 13000, 7000 }; -static const u16 ms_sensors_ht_h_conversion_time[] = { 16000, 3000, - 5000, 8000 }; +static const u16 ms_sensors_ht_h_conversion_time[] = { 16000, 5000, + 3000, 8000 }; static const u16 ms_sensors_tp_conversion_time[] = { 500, 1100, 2100, 4100, 8220, 16440 }; diff --git a/drivers/iio/imu/adis16475.c b/drivers/iio/imu/adis16475.c index b7cbe1565aee..64be656f0b80 100644 --- a/drivers/iio/imu/adis16475.c +++ b/drivers/iio/imu/adis16475.c @@ -70,8 +70,8 @@ #define ADIS16475_MAX_SCAN_DATA 20 /* spi max speed in brust mode */ #define ADIS16475_BURST_MAX_SPEED 1000000 -#define ADIS16475_LSB_DEC_MASK BIT(0) -#define ADIS16475_LSB_FIR_MASK BIT(1) +#define ADIS16475_LSB_DEC_MASK 0 +#define ADIS16475_LSB_FIR_MASK 1 #define ADIS16500_BURST_DATA_SEL_0_CHN_MASK GENMASK(5, 0) #define ADIS16500_BURST_DATA_SEL_1_CHN_MASK GENMASK(12, 7) @@ -1406,50 +1406,6 @@ static int adis16475_config_irq_pin(struct adis16475 *st) return 0; } -static const struct of_device_id adis16475_of_match[] = { - { .compatible = "adi,adis16470", - .data = &adis16475_chip_info[ADIS16470] }, - { .compatible = "adi,adis16475-1", - .data = &adis16475_chip_info[ADIS16475_1] }, - { .compatible = "adi,adis16475-2", - .data = &adis16475_chip_info[ADIS16475_2] }, - { .compatible = "adi,adis16475-3", - .data = &adis16475_chip_info[ADIS16475_3] }, - { .compatible = "adi,adis16477-1", - .data = &adis16475_chip_info[ADIS16477_1] }, - { .compatible = "adi,adis16477-2", - .data = &adis16475_chip_info[ADIS16477_2] }, - { .compatible = "adi,adis16477-3", - .data = &adis16475_chip_info[ADIS16477_3] }, - { .compatible = "adi,adis16465-1", - .data = &adis16475_chip_info[ADIS16465_1] }, - { .compatible = "adi,adis16465-2", - .data = &adis16475_chip_info[ADIS16465_2] }, - { .compatible = "adi,adis16465-3", - .data = &adis16475_chip_info[ADIS16465_3] }, - { .compatible = "adi,adis16467-1", - .data = &adis16475_chip_info[ADIS16467_1] }, - { .compatible = "adi,adis16467-2", - .data = &adis16475_chip_info[ADIS16467_2] }, - { .compatible = "adi,adis16467-3", - .data = &adis16475_chip_info[ADIS16467_3] }, - { .compatible = "adi,adis16500", - .data = &adis16475_chip_info[ADIS16500] }, - { .compatible = "adi,adis16505-1", - .data = &adis16475_chip_info[ADIS16505_1] }, - { .compatible = "adi,adis16505-2", - .data = &adis16475_chip_info[ADIS16505_2] }, - { .compatible = "adi,adis16505-3", - .data = &adis16475_chip_info[ADIS16505_3] }, - { .compatible = "adi,adis16507-1", - .data = &adis16475_chip_info[ADIS16507_1] }, - { .compatible = "adi,adis16507-2", - .data = &adis16475_chip_info[ADIS16507_2] }, - { .compatible = "adi,adis16507-3", - .data = &adis16475_chip_info[ADIS16507_3] }, - { }, -}; -MODULE_DEVICE_TABLE(of, adis16475_of_match); static int adis16475_probe(struct spi_device *spi) { @@ -1463,7 +1419,7 @@ static int adis16475_probe(struct spi_device *spi) st = iio_priv(indio_dev); - st->info = device_get_match_data(&spi->dev); + st->info = spi_get_device_match_data(spi); if (!st->info) return -EINVAL; @@ -1503,12 +1459,83 @@ static int adis16475_probe(struct spi_device *spi) return 0; } +static const struct of_device_id adis16475_of_match[] = { + { .compatible = "adi,adis16470", + .data = &adis16475_chip_info[ADIS16470] }, + { .compatible = "adi,adis16475-1", + .data = &adis16475_chip_info[ADIS16475_1] }, + { .compatible = "adi,adis16475-2", + .data = &adis16475_chip_info[ADIS16475_2] }, + { .compatible = "adi,adis16475-3", + .data = &adis16475_chip_info[ADIS16475_3] }, + { .compatible = "adi,adis16477-1", + .data = &adis16475_chip_info[ADIS16477_1] }, + { .compatible = "adi,adis16477-2", + .data = &adis16475_chip_info[ADIS16477_2] }, + { .compatible = "adi,adis16477-3", + .data = &adis16475_chip_info[ADIS16477_3] }, + { .compatible = "adi,adis16465-1", + .data = &adis16475_chip_info[ADIS16465_1] }, + { .compatible = "adi,adis16465-2", + .data = &adis16475_chip_info[ADIS16465_2] }, + { .compatible = "adi,adis16465-3", + .data = &adis16475_chip_info[ADIS16465_3] }, + { .compatible = "adi,adis16467-1", + .data = &adis16475_chip_info[ADIS16467_1] }, + { .compatible = "adi,adis16467-2", + .data = &adis16475_chip_info[ADIS16467_2] }, + { .compatible = "adi,adis16467-3", + .data = &adis16475_chip_info[ADIS16467_3] }, + { .compatible = "adi,adis16500", + .data = &adis16475_chip_info[ADIS16500] }, + { .compatible = "adi,adis16505-1", + .data = &adis16475_chip_info[ADIS16505_1] }, + { .compatible = "adi,adis16505-2", + .data = &adis16475_chip_info[ADIS16505_2] }, + { .compatible = "adi,adis16505-3", + .data = &adis16475_chip_info[ADIS16505_3] }, + { .compatible = "adi,adis16507-1", + .data = &adis16475_chip_info[ADIS16507_1] }, + { .compatible = "adi,adis16507-2", + .data = &adis16475_chip_info[ADIS16507_2] }, + { .compatible = "adi,adis16507-3", + .data = &adis16475_chip_info[ADIS16507_3] }, + { }, +}; +MODULE_DEVICE_TABLE(of, adis16475_of_match); + +static const struct spi_device_id adis16475_ids[] = { + { "adis16470", (kernel_ulong_t)&adis16475_chip_info[ADIS16470] }, + { "adis16475-1", (kernel_ulong_t)&adis16475_chip_info[ADIS16475_1] }, + { "adis16475-2", (kernel_ulong_t)&adis16475_chip_info[ADIS16475_2] }, + { "adis16475-3", (kernel_ulong_t)&adis16475_chip_info[ADIS16475_3] }, + { "adis16477-1", (kernel_ulong_t)&adis16475_chip_info[ADIS16477_1] }, + { "adis16477-2", (kernel_ulong_t)&adis16475_chip_info[ADIS16477_2] }, + { "adis16477-3", (kernel_ulong_t)&adis16475_chip_info[ADIS16477_3] }, + { "adis16465-1", (kernel_ulong_t)&adis16475_chip_info[ADIS16465_1] }, + { "adis16465-2", (kernel_ulong_t)&adis16475_chip_info[ADIS16465_2] }, + { "adis16465-3", (kernel_ulong_t)&adis16475_chip_info[ADIS16465_3] }, + { "adis16467-1", (kernel_ulong_t)&adis16475_chip_info[ADIS16467_1] }, + { "adis16467-2", (kernel_ulong_t)&adis16475_chip_info[ADIS16467_2] }, + { "adis16467-3", (kernel_ulong_t)&adis16475_chip_info[ADIS16467_3] }, + { "adis16500", (kernel_ulong_t)&adis16475_chip_info[ADIS16500] }, + { "adis16505-1", (kernel_ulong_t)&adis16475_chip_info[ADIS16505_1] }, + { "adis16505-2", (kernel_ulong_t)&adis16475_chip_info[ADIS16505_2] }, + { "adis16505-3", (kernel_ulong_t)&adis16475_chip_info[ADIS16505_3] }, + { "adis16507-1", (kernel_ulong_t)&adis16475_chip_info[ADIS16507_1] }, + { "adis16507-2", (kernel_ulong_t)&adis16475_chip_info[ADIS16507_2] }, + { "adis16507-3", (kernel_ulong_t)&adis16475_chip_info[ADIS16507_3] }, + { } +}; +MODULE_DEVICE_TABLE(spi, adis16475_ids); + static struct spi_driver adis16475_driver = { .driver = { .name = "adis16475", .of_match_table = adis16475_of_match, }, .probe = adis16475_probe, + .id_table = adis16475_ids, }; module_spi_driver(adis16475_driver); diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c index 3fbeef1a7018..6b034dccc3b1 100644 --- a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c +++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c @@ -750,13 +750,13 @@ inv_mpu6050_read_raw(struct iio_dev *indio_dev, ret = inv_mpu6050_sensor_show(st, st->reg->gyro_offset, chan->channel2, val); mutex_unlock(&st->lock); - return IIO_VAL_INT; + return ret; case IIO_ACCEL: mutex_lock(&st->lock); ret = inv_mpu6050_sensor_show(st, st->reg->accl_offset, chan->channel2, val); mutex_unlock(&st->lock); - return IIO_VAL_INT; + return ret; default: return -EINVAL; diff --git a/drivers/iio/light/hid-sensor-als.c b/drivers/iio/light/hid-sensor-als.c index f17304b54468..5cd27f04b45e 100644 --- a/drivers/iio/light/hid-sensor-als.c +++ b/drivers/iio/light/hid-sensor-als.c @@ -14,11 +14,8 @@ #include "../common/hid-sensors/hid-sensor-trigger.h" enum { - CHANNEL_SCAN_INDEX_INTENSITY, - CHANNEL_SCAN_INDEX_ILLUM, - CHANNEL_SCAN_INDEX_COLOR_TEMP, - CHANNEL_SCAN_INDEX_CHROMATICITY_X, - CHANNEL_SCAN_INDEX_CHROMATICITY_Y, + CHANNEL_SCAN_INDEX_INTENSITY = 0, + CHANNEL_SCAN_INDEX_ILLUM = 1, CHANNEL_SCAN_INDEX_MAX }; @@ -68,40 +65,6 @@ static const struct iio_chan_spec als_channels[] = { BIT(IIO_CHAN_INFO_HYSTERESIS_RELATIVE), .scan_index = CHANNEL_SCAN_INDEX_ILLUM, }, - { - .type = IIO_COLORTEMP, - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_OFFSET) | - BIT(IIO_CHAN_INFO_SCALE) | - BIT(IIO_CHAN_INFO_SAMP_FREQ) | - BIT(IIO_CHAN_INFO_HYSTERESIS) | - BIT(IIO_CHAN_INFO_HYSTERESIS_RELATIVE), - .scan_index = CHANNEL_SCAN_INDEX_COLOR_TEMP, - }, - { - .type = IIO_CHROMATICITY, - .modified = 1, - .channel2 = IIO_MOD_X, - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_OFFSET) | - BIT(IIO_CHAN_INFO_SCALE) | - BIT(IIO_CHAN_INFO_SAMP_FREQ) | - BIT(IIO_CHAN_INFO_HYSTERESIS) | - BIT(IIO_CHAN_INFO_HYSTERESIS_RELATIVE), - .scan_index = CHANNEL_SCAN_INDEX_CHROMATICITY_X, - }, - { - .type = IIO_CHROMATICITY, - .modified = 1, - .channel2 = IIO_MOD_Y, - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_OFFSET) | - BIT(IIO_CHAN_INFO_SCALE) | - BIT(IIO_CHAN_INFO_SAMP_FREQ) | - BIT(IIO_CHAN_INFO_HYSTERESIS) | - BIT(IIO_CHAN_INFO_HYSTERESIS_RELATIVE), - .scan_index = CHANNEL_SCAN_INDEX_CHROMATICITY_Y, - }, IIO_CHAN_SOFT_TIMESTAMP(CHANNEL_SCAN_INDEX_TIMESTAMP) }; @@ -140,21 +103,6 @@ static int als_read_raw(struct iio_dev *indio_dev, min = als_state->als[chan->scan_index].logical_minimum; address = HID_USAGE_SENSOR_LIGHT_ILLUM; break; - case CHANNEL_SCAN_INDEX_COLOR_TEMP: - report_id = als_state->als[chan->scan_index].report_id; - min = als_state->als[chan->scan_index].logical_minimum; - address = HID_USAGE_SENSOR_LIGHT_COLOR_TEMPERATURE; - break; - case CHANNEL_SCAN_INDEX_CHROMATICITY_X: - report_id = als_state->als[chan->scan_index].report_id; - min = als_state->als[chan->scan_index].logical_minimum; - address = HID_USAGE_SENSOR_LIGHT_CHROMATICITY_X; - break; - case CHANNEL_SCAN_INDEX_CHROMATICITY_Y: - report_id = als_state->als[chan->scan_index].report_id; - min = als_state->als[chan->scan_index].logical_minimum; - address = HID_USAGE_SENSOR_LIGHT_CHROMATICITY_Y; - break; default: report_id = -1; break; @@ -275,18 +223,6 @@ static int als_capture_sample(struct hid_sensor_hub_device *hsdev, als_state->scan.illum[CHANNEL_SCAN_INDEX_ILLUM] = sample_data; ret = 0; break; - case HID_USAGE_SENSOR_LIGHT_COLOR_TEMPERATURE: - als_state->scan.illum[CHANNEL_SCAN_INDEX_COLOR_TEMP] = sample_data; - ret = 0; - break; - case HID_USAGE_SENSOR_LIGHT_CHROMATICITY_X: - als_state->scan.illum[CHANNEL_SCAN_INDEX_CHROMATICITY_X] = sample_data; - ret = 0; - break; - case HID_USAGE_SENSOR_LIGHT_CHROMATICITY_Y: - als_state->scan.illum[CHANNEL_SCAN_INDEX_CHROMATICITY_Y] = sample_data; - ret = 0; - break; case HID_USAGE_SENSOR_TIME_TIMESTAMP: als_state->timestamp = hid_sensor_convert_timestamp(&als_state->common_attributes, *(s64 *)raw_data); @@ -322,38 +258,6 @@ static int als_parse_report(struct platform_device *pdev, st->als[i].report_id); } - ret = sensor_hub_input_get_attribute_info(hsdev, HID_INPUT_REPORT, - usage_id, - HID_USAGE_SENSOR_LIGHT_COLOR_TEMPERATURE, - &st->als[CHANNEL_SCAN_INDEX_COLOR_TEMP]); - if (ret < 0) - return ret; - als_adjust_channel_bit_mask(channels, CHANNEL_SCAN_INDEX_COLOR_TEMP, - st->als[CHANNEL_SCAN_INDEX_COLOR_TEMP].size); - - dev_dbg(&pdev->dev, "als %x:%x\n", - st->als[CHANNEL_SCAN_INDEX_COLOR_TEMP].index, - st->als[CHANNEL_SCAN_INDEX_COLOR_TEMP].report_id); - - for (i = 0; i < 2; i++) { - int next_scan_index = CHANNEL_SCAN_INDEX_CHROMATICITY_X + i; - - ret = sensor_hub_input_get_attribute_info(hsdev, - HID_INPUT_REPORT, usage_id, - HID_USAGE_SENSOR_LIGHT_CHROMATICITY_X + i, - &st->als[next_scan_index]); - if (ret < 0) - return ret; - - als_adjust_channel_bit_mask(channels, - CHANNEL_SCAN_INDEX_CHROMATICITY_X + i, - st->als[next_scan_index].size); - - dev_dbg(&pdev->dev, "als %x:%x\n", - st->als[next_scan_index].index, - st->als[next_scan_index].report_id); - } - st->scale_precision = hid_sensor_format_scale(usage_id, &st->als[CHANNEL_SCAN_INDEX_INTENSITY], &st->scale_pre_decml, &st->scale_post_decml); diff --git a/drivers/iio/magnetometer/tmag5273.c b/drivers/iio/magnetometer/tmag5273.c index c5e5c4ad681e..e8c4ca142d21 100644 --- a/drivers/iio/magnetometer/tmag5273.c +++ b/drivers/iio/magnetometer/tmag5273.c @@ -356,7 +356,7 @@ static int tmag5273_read_raw(struct iio_dev *indio_dev, case IIO_CHAN_INFO_OFFSET: switch (chan->type) { case IIO_TEMP: - *val = -266314; + *val = -16005; return IIO_VAL_INT; default: return -EINVAL; diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c index 8ba53edf2311..869369cb5b5f 100644 --- a/drivers/infiniband/hw/mlx5/devx.c +++ b/drivers/infiniband/hw/mlx5/devx.c @@ -2498,7 +2498,7 @@ static void dispatch_event_fd(struct list_head *fd_list, list_for_each_entry_rcu(item, fd_list, xa_list) { if (item->eventfd) - eventfd_signal(item->eventfd, 1); + eventfd_signal(item->eventfd); else deliver_event(item, data); } diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index f5c21565bb3c..e2c1848182de 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -286,6 +286,7 @@ static const struct xpad_device { { 0x146b, 0x0604, "Bigben Interactive DAIJA Arcade Stick", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 }, { 0x1532, 0x0a00, "Razer Atrox Arcade Stick", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOXONE }, { 0x1532, 0x0a03, "Razer Wildcat", 0, XTYPE_XBOXONE }, + { 0x1532, 0x0a29, "Razer Wolverine V2", 0, XTYPE_XBOXONE }, { 0x15e4, 0x3f00, "Power A Mini Pro Elite", 0, XTYPE_XBOX360 }, { 0x15e4, 0x3f0a, "Xbox Airflo wired controller", 0, XTYPE_XBOX360 }, { 0x15e4, 0x3f10, "Batarang Xbox 360 controller", 0, XTYPE_XBOX360 }, diff --git a/drivers/input/keyboard/atkbd.c b/drivers/input/keyboard/atkbd.c index c92e544c792d..786f00f6b7fd 100644 --- a/drivers/input/keyboard/atkbd.c +++ b/drivers/input/keyboard/atkbd.c @@ -765,6 +765,44 @@ static void atkbd_deactivate(struct atkbd *atkbd) ps2dev->serio->phys); } +#ifdef CONFIG_X86 +static bool atkbd_is_portable_device(void) +{ + static const char * const chassis_types[] = { + "8", /* Portable */ + "9", /* Laptop */ + "10", /* Notebook */ + "14", /* Sub-Notebook */ + "31", /* Convertible */ + "32", /* Detachable */ + }; + int i; + + for (i = 0; i < ARRAY_SIZE(chassis_types); i++) + if (dmi_match(DMI_CHASSIS_TYPE, chassis_types[i])) + return true; + + return false; +} + +/* + * On many modern laptops ATKBD_CMD_GETID may cause problems, on these laptops + * the controller is always in translated mode. In this mode mice/touchpads will + * not work. So in this case simply assume a keyboard is connected to avoid + * confusing some laptop keyboards. + * + * Skipping ATKBD_CMD_GETID ends up using a fake keyboard id. Using a fake id is + * ok in translated mode, only atkbd_select_set() checks atkbd->id and in + * translated mode that is a no-op. + */ +static bool atkbd_skip_getid(struct atkbd *atkbd) +{ + return atkbd->translated && atkbd_is_portable_device(); +} +#else +static inline bool atkbd_skip_getid(struct atkbd *atkbd) { return false; } +#endif + /* * atkbd_probe() probes for an AT keyboard on a serio port. */ @@ -794,12 +832,12 @@ static int atkbd_probe(struct atkbd *atkbd) */ param[0] = param[1] = 0xa5; /* initialize with invalid values */ - if (ps2_command(ps2dev, param, ATKBD_CMD_GETID)) { + if (atkbd_skip_getid(atkbd) || ps2_command(ps2dev, param, ATKBD_CMD_GETID)) { /* - * If the get ID command failed, we check if we can at least set the LEDs on - * the keyboard. This should work on every keyboard out there. It also turns - * the LEDs off, which we want anyway. + * If the get ID command was skipped or failed, we check if we can at least set + * the LEDs on the keyboard. This should work on every keyboard out there. + * It also turns the LEDs off, which we want anyway. */ param[0] = 0; if (ps2_command(ps2dev, param, ATKBD_CMD_SETLEDS)) diff --git a/drivers/input/keyboard/ipaq-micro-keys.c b/drivers/input/keyboard/ipaq-micro-keys.c index 7b509bce2b33..1d71dd79ffd2 100644 --- a/drivers/input/keyboard/ipaq-micro-keys.c +++ b/drivers/input/keyboard/ipaq-micro-keys.c @@ -105,6 +105,9 @@ static int micro_key_probe(struct platform_device *pdev) keys->codes = devm_kmemdup(&pdev->dev, micro_keycodes, keys->input->keycodesize * keys->input->keycodemax, GFP_KERNEL); + if (!keys->codes) + return -ENOMEM; + keys->input->keycode = keys->codes; __set_bit(EV_KEY, keys->input->evbit); diff --git a/drivers/input/misc/soc_button_array.c b/drivers/input/misc/soc_button_array.c index 08bcee3d6bcc..f6d060377d18 100644 --- a/drivers/input/misc/soc_button_array.c +++ b/drivers/input/misc/soc_button_array.c @@ -299,6 +299,11 @@ static int soc_button_parse_btn_desc(struct device *dev, info->name = "power"; info->event_code = KEY_POWER; info->wakeup = true; + } else if (upage == 0x01 && usage == 0xc6) { + info->name = "airplane mode switch"; + info->event_type = EV_SW; + info->event_code = SW_RFKILL_ALL; + info->active_low = false; } else if (upage == 0x01 && usage == 0xca) { info->name = "rotation lock switch"; info->event_type = EV_SW; diff --git a/drivers/input/mouse/amimouse.c b/drivers/input/mouse/amimouse.c index a50e50354832..cda0c3ff5a28 100644 --- a/drivers/input/mouse/amimouse.c +++ b/drivers/input/mouse/amimouse.c @@ -125,16 +125,15 @@ static int __init amimouse_probe(struct platform_device *pdev) return 0; } -static int __exit amimouse_remove(struct platform_device *pdev) +static void __exit amimouse_remove(struct platform_device *pdev) { struct input_dev *dev = platform_get_drvdata(pdev); input_unregister_device(dev); - return 0; } static struct platform_driver amimouse_driver = { - .remove = __exit_p(amimouse_remove), + .remove_new = __exit_p(amimouse_remove), .driver = { .name = "amiga-mouse", }, diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c index 22d16d80efb9..7a303a9d6bf7 100644 --- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -183,6 +183,7 @@ static const char * const smbus_pnp_ids[] = { "LEN009b", /* T580 */ "LEN0402", /* X1 Extreme Gen 2 / P1 Gen 2 */ "LEN040f", /* P1 Gen 3 */ + "LEN0411", /* L14 Gen 1 */ "LEN200f", /* T450s */ "LEN2044", /* L470 */ "LEN2054", /* E480 */ diff --git a/drivers/input/serio/i8042-acpipnpio.h b/drivers/input/serio/i8042-acpipnpio.h index 9c39553d30fa..b585b1dab870 100644 --- a/drivers/input/serio/i8042-acpipnpio.h +++ b/drivers/input/serio/i8042-acpipnpio.h @@ -361,6 +361,14 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = { .driver_data = (void *)(SERIO_QUIRK_DRITEK) }, { + /* Acer TravelMate P459-G2-M */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate P459-G2-M"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) + }, + { /* Amoi M636/A737 */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Amoi Electronics CO.,LTD."), diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c index dfab160ca529..50bac2d79d9b 100644 --- a/drivers/interconnect/core.c +++ b/drivers/interconnect/core.c @@ -395,6 +395,9 @@ struct icc_node_data *of_icc_get_from_provider(struct of_phandle_args *spec) } mutex_unlock(&icc_lock); + if (!node) + return ERR_PTR(-EINVAL); + if (IS_ERR(node)) return ERR_CAST(node); diff --git a/drivers/interconnect/qcom/icc-rpm.c b/drivers/interconnect/qcom/icc-rpm.c index 628e651c555c..dbacb2a7af50 100644 --- a/drivers/interconnect/qcom/icc-rpm.c +++ b/drivers/interconnect/qcom/icc-rpm.c @@ -307,7 +307,7 @@ static u64 qcom_icc_calc_rate(struct qcom_icc_provider *qp, struct qcom_icc_node if (qn->ib_coeff) { agg_peak_rate = qn->max_peak[ctx] * 100; - agg_peak_rate = div_u64(qn->max_peak[ctx], qn->ib_coeff); + agg_peak_rate = div_u64(agg_peak_rate, qn->ib_coeff); } else { agg_peak_rate = qn->max_peak[ctx]; } diff --git a/drivers/interconnect/qcom/sm8250.c b/drivers/interconnect/qcom/sm8250.c index 83aeb3eedc19..02d40eea0d69 100644 --- a/drivers/interconnect/qcom/sm8250.c +++ b/drivers/interconnect/qcom/sm8250.c @@ -1995,6 +1995,7 @@ static struct platform_driver qnoc_driver = { .driver = { .name = "qnoc-sm8250", .of_match_table = qnoc_of_match, + .sync_state = icc_sync_state, }, }; module_platform_driver(qnoc_driver); diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index 2a8b081bce7d..3ff87cb4dc49 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -660,6 +660,7 @@ config DM_ZONED config DM_AUDIT bool "DM audit events" + depends on BLK_DEV_DM depends on AUDIT help Generate audit events for device-mapper. diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index e85c688fd91e..c5f03aab4552 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -1755,11 +1755,12 @@ static void integrity_metadata(struct work_struct *w) sectors_to_process = dio->range.n_sectors; __bio_for_each_segment(bv, bio, iter, dio->bio_details.bi_iter) { + struct bio_vec bv_copy = bv; unsigned int pos; char *mem, *checksums_ptr; again: - mem = bvec_kmap_local(&bv); + mem = bvec_kmap_local(&bv_copy); pos = 0; checksums_ptr = checksums; do { @@ -1768,7 +1769,7 @@ again: sectors_to_process -= ic->sectors_per_block; pos += ic->sectors_per_block << SECTOR_SHIFT; sector += ic->sectors_per_block; - } while (pos < bv.bv_len && sectors_to_process && checksums != checksums_onstack); + } while (pos < bv_copy.bv_len && sectors_to_process && checksums != checksums_onstack); kunmap_local(mem); r = dm_integrity_rw_tag(ic, checksums, &dio->metadata_block, &dio->metadata_offset, @@ -1793,9 +1794,9 @@ again: if (!sectors_to_process) break; - if (unlikely(pos < bv.bv_len)) { - bv.bv_offset += pos; - bv.bv_len -= pos; + if (unlikely(pos < bv_copy.bv_len)) { + bv_copy.bv_offset += pos; + bv_copy.bv_len -= pos; goto again; } } diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 91ebdcc6e9a8..eb009d6bb03a 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -3317,6 +3317,9 @@ static void raid_dtr(struct dm_target *ti) mddev_lock_nointr(&rs->md); md_stop(&rs->md); mddev_unlock(&rs->md); + + if (work_pending(&rs->md.event_work)) + flush_work(&rs->md.event_work); raid_set_free(rs); } diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 23c32cd1f1d8..8dcabf84d866 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -2675,7 +2675,7 @@ static int lock_fs(struct mapped_device *md) WARN_ON(test_bit(DMF_FROZEN, &md->flags)); - r = freeze_bdev(md->disk->part0); + r = bdev_freeze(md->disk->part0); if (!r) set_bit(DMF_FROZEN, &md->flags); return r; @@ -2685,7 +2685,7 @@ static void unlock_fs(struct mapped_device *md) { if (!test_bit(DMF_FROZEN, &md->flags)) return; - thaw_bdev(md->disk->part0); + bdev_thaw(md->disk->part0); clear_bit(DMF_FROZEN, &md->flags); } diff --git a/drivers/md/md.c b/drivers/md/md.c index b066abbffd10..9bdd57324c37 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -82,6 +82,14 @@ static struct module *md_cluster_mod; static DECLARE_WAIT_QUEUE_HEAD(resync_wait); static struct workqueue_struct *md_wq; + +/* + * This workqueue is used for sync_work to register new sync_thread, and for + * del_work to remove rdev, and for event_work that is only set by dm-raid. + * + * Noted that sync_work will grab reconfig_mutex, hence never flush this + * workqueue whith reconfig_mutex grabbed. + */ static struct workqueue_struct *md_misc_wq; struct workqueue_struct *md_bitmap_wq; @@ -6330,9 +6338,6 @@ static void __md_stop(struct mddev *mddev) struct md_personality *pers = mddev->pers; md_bitmap_destroy(mddev); mddev_detach(mddev); - /* Ensure ->event_work is done */ - if (mddev->event_work.func) - flush_workqueue(md_misc_wq); spin_lock(&mddev->lock); mddev->pers = NULL; spin_unlock(&mddev->lock); diff --git a/drivers/misc/ocxl/file.c b/drivers/misc/ocxl/file.c index ac69b7f361f5..7eb74711ac96 100644 --- a/drivers/misc/ocxl/file.c +++ b/drivers/misc/ocxl/file.c @@ -184,7 +184,7 @@ static irqreturn_t irq_handler(void *private) { struct eventfd_ctx *ev_ctx = private; - eventfd_signal(ev_ctx, 1); + eventfd_signal(ev_ctx); return IRQ_HANDLED; } diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index f9a5cffa64b1..134c36edb6cf 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -851,9 +851,10 @@ static const struct block_device_operations mmc_bdops = { static int mmc_blk_part_switch_pre(struct mmc_card *card, unsigned int part_type) { + const unsigned int mask = EXT_CSD_PART_CONFIG_ACC_RPMB; int ret = 0; - if (part_type == EXT_CSD_PART_CONFIG_ACC_RPMB) { + if ((part_type & mask) == mask) { if (card->ext_csd.cmdq_en) { ret = mmc_cmdq_disable(card); if (ret) @@ -868,9 +869,10 @@ static int mmc_blk_part_switch_pre(struct mmc_card *card, static int mmc_blk_part_switch_post(struct mmc_card *card, unsigned int part_type) { + const unsigned int mask = EXT_CSD_PART_CONFIG_ACC_RPMB; int ret = 0; - if (part_type == EXT_CSD_PART_CONFIG_ACC_RPMB) { + if ((part_type & mask) == mask) { mmc_retune_unpause(card->host); if (card->reenable_cmdq && !card->ext_csd.cmdq_en) ret = mmc_cmdq_enable(card); @@ -3145,4 +3147,3 @@ module_exit(mmc_blk_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Multimedia Card (MMC) block device driver"); - diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c index 096093f7be00..2f51db4df1a8 100644 --- a/drivers/mmc/core/host.c +++ b/drivers/mmc/core/host.c @@ -692,6 +692,7 @@ EXPORT_SYMBOL(mmc_remove_host); */ void mmc_free_host(struct mmc_host *host) { + cancel_delayed_work_sync(&host->detect); mmc_pwrseq_free(host); put_device(&host->class_dev); } diff --git a/drivers/mmc/host/meson-mx-sdhc-mmc.c b/drivers/mmc/host/meson-mx-sdhc-mmc.c index 528ec8166e7c..1ed9731e77ef 100644 --- a/drivers/mmc/host/meson-mx-sdhc-mmc.c +++ b/drivers/mmc/host/meson-mx-sdhc-mmc.c @@ -269,7 +269,7 @@ static int meson_mx_sdhc_enable_clks(struct mmc_host *mmc) static int meson_mx_sdhc_set_clk(struct mmc_host *mmc, struct mmc_ios *ios) { struct meson_mx_sdhc_host *host = mmc_priv(mmc); - u32 rx_clk_phase; + u32 val, rx_clk_phase; int ret; meson_mx_sdhc_disable_clks(mmc); @@ -290,27 +290,11 @@ static int meson_mx_sdhc_set_clk(struct mmc_host *mmc, struct mmc_ios *ios) mmc->actual_clock = clk_get_rate(host->sd_clk); /* - * according to Amlogic the following latching points are - * selected with empirical values, there is no (known) formula - * to calculate these. + * Phase 90 should work in most cases. For data transmission, + * meson_mx_sdhc_execute_tuning() will find a accurate value */ - if (mmc->actual_clock > 100000000) { - rx_clk_phase = 1; - } else if (mmc->actual_clock > 45000000) { - if (ios->signal_voltage == MMC_SIGNAL_VOLTAGE_330) - rx_clk_phase = 15; - else - rx_clk_phase = 11; - } else if (mmc->actual_clock >= 25000000) { - rx_clk_phase = 15; - } else if (mmc->actual_clock > 5000000) { - rx_clk_phase = 23; - } else if (mmc->actual_clock > 1000000) { - rx_clk_phase = 55; - } else { - rx_clk_phase = 1061; - } - + regmap_read(host->regmap, MESON_SDHC_CLKC, &val); + rx_clk_phase = FIELD_GET(MESON_SDHC_CLKC_CLK_DIV, val) / 4; regmap_update_bits(host->regmap, MESON_SDHC_CLK2, MESON_SDHC_CLK2_RX_CLK_PHASE, FIELD_PREP(MESON_SDHC_CLK2_RX_CLK_PHASE, diff --git a/drivers/mmc/host/sdhci-sprd.c b/drivers/mmc/host/sdhci-sprd.c index 6b8a57e2d20f..bed57a1c64b5 100644 --- a/drivers/mmc/host/sdhci-sprd.c +++ b/drivers/mmc/host/sdhci-sprd.c @@ -239,15 +239,19 @@ static inline void _sdhci_sprd_set_clock(struct sdhci_host *host, div = ((div & 0x300) >> 2) | ((div & 0xFF) << 8); sdhci_enable_clk(host, div); + val = sdhci_readl(host, SDHCI_SPRD_REG_32_BUSY_POSI); + mask = SDHCI_SPRD_BIT_OUTR_CLK_AUTO_EN | SDHCI_SPRD_BIT_INNR_CLK_AUTO_EN; /* Enable CLK_AUTO when the clock is greater than 400K. */ if (clk > 400000) { - val = sdhci_readl(host, SDHCI_SPRD_REG_32_BUSY_POSI); - mask = SDHCI_SPRD_BIT_OUTR_CLK_AUTO_EN | - SDHCI_SPRD_BIT_INNR_CLK_AUTO_EN; if (mask != (val & mask)) { val |= mask; sdhci_writel(host, val, SDHCI_SPRD_REG_32_BUSY_POSI); } + } else { + if (val & mask) { + val &= ~mask; + sdhci_writel(host, val, SDHCI_SPRD_REG_32_BUSY_POSI); + } } } diff --git a/drivers/net/ethernet/amazon/ena/ena_eth_com.c b/drivers/net/ethernet/amazon/ena/ena_eth_com.c index 3d6f0a466a9e..f9f886289b97 100644 --- a/drivers/net/ethernet/amazon/ena/ena_eth_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_eth_com.c @@ -328,9 +328,6 @@ static int ena_com_create_and_store_tx_meta_desc(struct ena_com_io_sq *io_sq, * compare it to the stored version, just create the meta */ if (io_sq->disable_meta_caching) { - if (unlikely(!ena_tx_ctx->meta_valid)) - return -EINVAL; - *have_meta = true; return ena_com_create_meta(io_sq, ena_meta); } diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index b5bca4814830..c44c44e26ddf 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -74,6 +74,8 @@ static void ena_unmap_tx_buff(struct ena_ring *tx_ring, struct ena_tx_buffer *tx_info); static int ena_create_io_tx_queues_in_range(struct ena_adapter *adapter, int first_index, int count); +static void ena_free_all_io_tx_resources_in_range(struct ena_adapter *adapter, + int first_index, int count); /* Increase a stat by cnt while holding syncp seqlock on 32bit machines */ static void ena_increase_stat(u64 *statp, u64 cnt, @@ -457,23 +459,22 @@ static void ena_init_all_xdp_queues(struct ena_adapter *adapter) static int ena_setup_and_create_all_xdp_queues(struct ena_adapter *adapter) { + u32 xdp_first_ring = adapter->xdp_first_ring; + u32 xdp_num_queues = adapter->xdp_num_queues; int rc = 0; - rc = ena_setup_tx_resources_in_range(adapter, adapter->xdp_first_ring, - adapter->xdp_num_queues); + rc = ena_setup_tx_resources_in_range(adapter, xdp_first_ring, xdp_num_queues); if (rc) goto setup_err; - rc = ena_create_io_tx_queues_in_range(adapter, - adapter->xdp_first_ring, - adapter->xdp_num_queues); + rc = ena_create_io_tx_queues_in_range(adapter, xdp_first_ring, xdp_num_queues); if (rc) goto create_err; return 0; create_err: - ena_free_all_io_tx_resources(adapter); + ena_free_all_io_tx_resources_in_range(adapter, xdp_first_ring, xdp_num_queues); setup_err: return rc; } @@ -1492,11 +1493,6 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring, if (unlikely(!skb)) return NULL; - /* sync this buffer for CPU use */ - dma_sync_single_for_cpu(rx_ring->dev, - dma_unmap_addr(&rx_info->ena_buf, paddr) + pkt_offset, - len, - DMA_FROM_DEVICE); skb_copy_to_linear_data(skb, buf_addr + buf_offset, len); dma_sync_single_for_device(rx_ring->dev, dma_unmap_addr(&rx_info->ena_buf, paddr) + pkt_offset, @@ -1515,17 +1511,10 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring, buf_len = SKB_DATA_ALIGN(len + buf_offset + tailroom); - pre_reuse_paddr = dma_unmap_addr(&rx_info->ena_buf, paddr); - /* If XDP isn't loaded try to reuse part of the RX buffer */ reuse_rx_buf_page = !is_xdp_loaded && ena_try_rx_buf_page_reuse(rx_info, buf_len, len, pkt_offset); - dma_sync_single_for_cpu(rx_ring->dev, - pre_reuse_paddr + pkt_offset, - len, - DMA_FROM_DEVICE); - if (!reuse_rx_buf_page) ena_unmap_rx_buff_attrs(rx_ring, rx_info, DMA_ATTR_SKIP_CPU_SYNC); @@ -1671,20 +1660,23 @@ static void ena_set_rx_hash(struct ena_ring *rx_ring, } } -static int ena_xdp_handle_buff(struct ena_ring *rx_ring, struct xdp_buff *xdp) +static int ena_xdp_handle_buff(struct ena_ring *rx_ring, struct xdp_buff *xdp, u16 num_descs) { struct ena_rx_buffer *rx_info; int ret; + /* XDP multi-buffer packets not supported */ + if (unlikely(num_descs > 1)) { + netdev_err_once(rx_ring->adapter->netdev, + "xdp: dropped unsupported multi-buffer packets\n"); + ena_increase_stat(&rx_ring->rx_stats.xdp_drop, 1, &rx_ring->syncp); + return ENA_XDP_DROP; + } + rx_info = &rx_ring->rx_buffer_info[rx_ring->ena_bufs[0].req_id]; xdp_prepare_buff(xdp, page_address(rx_info->page), rx_info->buf_offset, rx_ring->ena_bufs[0].len, false); - /* If for some reason we received a bigger packet than - * we expect, then we simply drop it - */ - if (unlikely(rx_ring->ena_bufs[0].len > ENA_XDP_MAX_MTU)) - return ENA_XDP_DROP; ret = ena_xdp_execute(rx_ring, xdp); @@ -1719,6 +1711,7 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi, int xdp_flags = 0; int total_len = 0; int xdp_verdict; + u8 pkt_offset; int rc = 0; int i; @@ -1745,15 +1738,21 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi, /* First descriptor might have an offset set by the device */ rx_info = &rx_ring->rx_buffer_info[rx_ring->ena_bufs[0].req_id]; - rx_info->buf_offset += ena_rx_ctx.pkt_offset; + pkt_offset = ena_rx_ctx.pkt_offset; + rx_info->buf_offset += pkt_offset; netif_dbg(rx_ring->adapter, rx_status, rx_ring->netdev, "rx_poll: q %d got packet from ena. descs #: %d l3 proto %d l4 proto %d hash: %x\n", rx_ring->qid, ena_rx_ctx.descs, ena_rx_ctx.l3_proto, ena_rx_ctx.l4_proto, ena_rx_ctx.hash); + dma_sync_single_for_cpu(rx_ring->dev, + dma_unmap_addr(&rx_info->ena_buf, paddr) + pkt_offset, + rx_ring->ena_bufs[0].len, + DMA_FROM_DEVICE); + if (ena_xdp_present_ring(rx_ring)) - xdp_verdict = ena_xdp_handle_buff(rx_ring, &xdp); + xdp_verdict = ena_xdp_handle_buff(rx_ring, &xdp, ena_rx_ctx.descs); /* allocate skb and fill it */ if (xdp_verdict == ENA_XDP_PASS) @@ -1777,7 +1776,7 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi, if (xdp_verdict & ENA_XDP_FORWARDED) { ena_unmap_rx_buff_attrs(rx_ring, &rx_ring->rx_buffer_info[req_id], - 0); + DMA_ATTR_SKIP_CPU_SYNC); rx_ring->rx_buffer_info[req_id].page = NULL; } } diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index 694daeaf3e61..e1885c1eb100 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -938,11 +938,14 @@ void aq_ring_free(struct aq_ring_s *self) return; kfree(self->buff_ring); + self->buff_ring = NULL; - if (self->dx_ring) + if (self->dx_ring) { dma_free_coherent(aq_nic_get_dev(self->aq_nic), self->size * self->dx_size, self->dx_ring, self->dx_ring_pa); + self->dx_ring = NULL; + } } unsigned int aq_ring_fill_stats_data(struct aq_ring_s *self, u64 *data) diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c index 5935be190b9e..5f2a6fcba967 100644 --- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c +++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c @@ -866,10 +866,13 @@ static int atl1e_setup_ring_resources(struct atl1e_adapter *adapter) netdev_err(adapter->netdev, "offset(%d) > ring size(%d) !!\n", offset, adapter->ring_size); err = -1; - goto failed; + goto free_buffer; } return 0; +free_buffer: + kfree(tx_ring->tx_buffer); + tx_ring->tx_buffer = NULL; failed: if (adapter->ring_vir_addr != NULL) { dma_free_coherent(&pdev->dev, adapter->ring_size, diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index d0359b569afe..e1f1e646cf48 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -1748,16 +1748,32 @@ static void bnxt_tpa_agg(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, static void bnxt_deliver_skb(struct bnxt *bp, struct bnxt_napi *bnapi, struct sk_buff *skb) { + skb_mark_for_recycle(skb); + if (skb->dev != bp->dev) { /* this packet belongs to a vf-rep */ bnxt_vf_rep_rx(bp, skb); return; } skb_record_rx_queue(skb, bnapi->index); - skb_mark_for_recycle(skb); napi_gro_receive(&bnapi->napi, skb); } +static bool bnxt_rx_ts_valid(struct bnxt *bp, u32 flags, + struct rx_cmp_ext *rxcmp1, u32 *cmpl_ts) +{ + u32 ts = le32_to_cpu(rxcmp1->rx_cmp_timestamp); + + if (BNXT_PTP_RX_TS_VALID(flags)) + goto ts_valid; + if (!bp->ptp_all_rx_tstamp || !ts || !BNXT_ALL_RX_TS_VALID(flags)) + return false; + +ts_valid: + *cmpl_ts = ts; + return true; +} + /* returns the following: * 1 - 1 packet successfully received * 0 - successful TPA_START, packet not completed yet @@ -1783,6 +1799,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, struct sk_buff *skb; struct xdp_buff xdp; u32 flags, misc; + u32 cmpl_ts; void *data; int rc = 0; @@ -2005,10 +2022,8 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, } } - if (unlikely((flags & RX_CMP_FLAGS_ITYPES_MASK) == - RX_CMP_FLAGS_ITYPE_PTP_W_TS) || bp->ptp_all_rx_tstamp) { + if (bnxt_rx_ts_valid(bp, flags, rxcmp1, &cmpl_ts)) { if (bp->flags & BNXT_FLAG_CHIP_P5) { - u32 cmpl_ts = le32_to_cpu(rxcmp1->rx_cmp_timestamp); u64 ns, ts; if (!bnxt_get_rx_ts_p5(bp, &ts, cmpl_ts)) { @@ -10731,10 +10746,8 @@ static void __bnxt_close_nic(struct bnxt *bp, bool irq_re_init, bnxt_free_mem(bp, irq_re_init); } -int bnxt_close_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) +void bnxt_close_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) { - int rc = 0; - if (test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) { /* If we get here, it means firmware reset is in progress * while we are trying to close. We can safely proceed with @@ -10749,15 +10762,18 @@ int bnxt_close_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) #ifdef CONFIG_BNXT_SRIOV if (bp->sriov_cfg) { + int rc; + rc = wait_event_interruptible_timeout(bp->sriov_cfg_wait, !bp->sriov_cfg, BNXT_SRIOV_CFG_WAIT_TMO); - if (rc) - netdev_warn(bp->dev, "timeout waiting for SRIOV config operation to complete!\n"); + if (!rc) + netdev_warn(bp->dev, "timeout waiting for SRIOV config operation to complete, proceeding to close!\n"); + else if (rc < 0) + netdev_warn(bp->dev, "SRIOV config operation interrupted, proceeding to close!\n"); } #endif __bnxt_close_nic(bp, irq_re_init, link_re_init); - return rc; } static int bnxt_close(struct net_device *dev) @@ -12077,6 +12093,8 @@ static void bnxt_sp_task(struct work_struct *work) bnxt_cfg_ntp_filters(bp); if (test_and_clear_bit(BNXT_HWRM_EXEC_FWD_REQ_SP_EVENT, &bp->sp_event)) bnxt_hwrm_exec_fwd_req(bp); + if (test_and_clear_bit(BNXT_HWRM_PF_UNLOAD_SP_EVENT, &bp->sp_event)) + netdev_info(bp->dev, "Receive PF driver unload event!\n"); if (test_and_clear_bit(BNXT_PERIODIC_STATS_SP_EVENT, &bp->sp_event)) { bnxt_hwrm_port_qstats(bp, 0); bnxt_hwrm_port_qstats_ext(bp, 0); @@ -13077,8 +13095,6 @@ static void bnxt_cfg_ntp_filters(struct bnxt *bp) } } } - if (test_and_clear_bit(BNXT_HWRM_PF_UNLOAD_SP_EVENT, &bp->sp_event)) - netdev_info(bp->dev, "Receive PF driver unload event!\n"); } #else @@ -13940,6 +13956,8 @@ static int bnxt_resume(struct device *device) if (rc) goto resume_exit; + bnxt_clear_reservations(bp, true); + if (bnxt_hwrm_func_drv_rgtr(bp, NULL, 0, false)) { rc = -ENODEV; goto resume_exit; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index e702dbc3e6b1..a7d7b09ea162 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -161,7 +161,7 @@ struct rx_cmp { #define RX_CMP_FLAGS_ERROR (1 << 6) #define RX_CMP_FLAGS_PLACEMENT (7 << 7) #define RX_CMP_FLAGS_RSS_VALID (1 << 10) - #define RX_CMP_FLAGS_UNUSED (1 << 11) + #define RX_CMP_FLAGS_PKT_METADATA_PRESENT (1 << 11) #define RX_CMP_FLAGS_ITYPES_SHIFT 12 #define RX_CMP_FLAGS_ITYPES_MASK 0xf000 #define RX_CMP_FLAGS_ITYPE_UNKNOWN (0 << 12) @@ -188,6 +188,12 @@ struct rx_cmp { __le32 rx_cmp_rss_hash; }; +#define BNXT_PTP_RX_TS_VALID(flags) \ + (((flags) & RX_CMP_FLAGS_ITYPES_MASK) == RX_CMP_FLAGS_ITYPE_PTP_W_TS) + +#define BNXT_ALL_RX_TS_VALID(flags) \ + !((flags) & RX_CMP_FLAGS_PKT_METADATA_PRESENT) + #define RX_CMP_HASH_VALID(rxcmp) \ ((rxcmp)->rx_cmp_len_flags_type & cpu_to_le32(RX_CMP_FLAGS_RSS_VALID)) @@ -2375,7 +2381,7 @@ int bnxt_open_nic(struct bnxt *, bool, bool); int bnxt_half_open_nic(struct bnxt *bp); void bnxt_half_close_nic(struct bnxt *bp); void bnxt_reenable_sriov(struct bnxt *bp); -int bnxt_close_nic(struct bnxt *, bool, bool); +void bnxt_close_nic(struct bnxt *, bool, bool); void bnxt_get_ring_err_stats(struct bnxt *bp, struct bnxt_total_ring_err_stats *stats); int bnxt_dbg_hwrm_rd_reg(struct bnxt *bp, u32 reg_off, u16 num_words, diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c index f302dac56599..89809f1b129c 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c @@ -449,15 +449,8 @@ static int bnxt_dl_reload_down(struct devlink *dl, bool netns_change, return -ENODEV; } bnxt_ulp_stop(bp); - if (netif_running(bp->dev)) { - rc = bnxt_close_nic(bp, true, true); - if (rc) { - NL_SET_ERR_MSG_MOD(extack, "Failed to close"); - dev_close(bp->dev); - rtnl_unlock(); - break; - } - } + if (netif_running(bp->dev)) + bnxt_close_nic(bp, true, true); bnxt_vf_reps_free(bp); rc = bnxt_hwrm_func_drv_unrgtr(bp); if (rc) { diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index f3f384773ac0..5f67a7f94e7d 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -165,9 +165,8 @@ static int bnxt_set_coalesce(struct net_device *dev, reset_coalesce: if (test_bit(BNXT_STATE_OPEN, &bp->state)) { if (update_stats) { - rc = bnxt_close_nic(bp, true, false); - if (!rc) - rc = bnxt_open_nic(bp, true, false); + bnxt_close_nic(bp, true, false); + rc = bnxt_open_nic(bp, true, false); } else { rc = bnxt_hwrm_set_coal(bp); } @@ -972,12 +971,7 @@ static int bnxt_set_channels(struct net_device *dev, * before PF unload */ } - rc = bnxt_close_nic(bp, true, false); - if (rc) { - netdev_err(bp->dev, "Set channel failure rc :%x\n", - rc); - return rc; - } + bnxt_close_nic(bp, true, false); } if (sh) { @@ -4042,12 +4036,7 @@ static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest, bnxt_run_fw_tests(bp, test_mask, &test_results); } else { bnxt_ulp_stop(bp); - rc = bnxt_close_nic(bp, true, false); - if (rc) { - etest->flags |= ETH_TEST_FL_FAILED; - bnxt_ulp_start(bp, rc); - return; - } + bnxt_close_nic(bp, true, false); bnxt_run_fw_tests(bp, test_mask, &test_results); buf[BNXT_MACLPBK_TEST_IDX] = 1; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c index f3886710e778..6e3da3362bd6 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c @@ -521,9 +521,8 @@ static int bnxt_hwrm_ptp_cfg(struct bnxt *bp) if (netif_running(bp->dev)) { if (ptp->rx_filter == HWTSTAMP_FILTER_ALL) { - rc = bnxt_close_nic(bp, false, false); - if (!rc) - rc = bnxt_open_nic(bp, false, false); + bnxt_close_nic(bp, false, false); + rc = bnxt_open_nic(bp, false, false); } else { bnxt_ptp_cfg_tstamp_filters(bp); } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c index 96f5ca778c67..8cb9a99154aa 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c @@ -59,7 +59,6 @@ struct bnxt_sw_tx_bd *bnxt_xmit_bd(struct bnxt *bp, for (i = 0; i < num_frags ; i++) { skb_frag_t *frag = &sinfo->frags[i]; struct bnxt_sw_tx_bd *frag_tx_buf; - struct pci_dev *pdev = bp->pdev; dma_addr_t frag_mapping; int frag_len; @@ -73,16 +72,10 @@ struct bnxt_sw_tx_bd *bnxt_xmit_bd(struct bnxt *bp, txbd = &txr->tx_desc_ring[TX_RING(prod)][TX_IDX(prod)]; frag_len = skb_frag_size(frag); - frag_mapping = skb_frag_dma_map(&pdev->dev, frag, 0, - frag_len, DMA_TO_DEVICE); - - if (unlikely(dma_mapping_error(&pdev->dev, frag_mapping))) - return NULL; - - dma_unmap_addr_set(frag_tx_buf, mapping, frag_mapping); - flags = frag_len << TX_BD_LEN_SHIFT; txbd->tx_bd_len_flags_type = cpu_to_le32(flags); + frag_mapping = page_pool_get_dma_addr(skb_frag_page(frag)) + + skb_frag_off(frag); txbd->tx_bd_haddr = cpu_to_le64(frag_mapping); len = frag_len; diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 9282403d1bf6..2d7ae71287b1 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -2132,8 +2132,10 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev) /* Note: if we ever change from DMA_TX_APPEND_CRC below we * will need to restore software padding of "runt" packets */ + len_stat |= DMA_TX_APPEND_CRC; + if (!i) { - len_stat |= DMA_TX_APPEND_CRC | DMA_SOP; + len_stat |= DMA_SOP; if (skb->ip_summed == CHECKSUM_PARTIAL) len_stat |= DMA_TX_DO_CSUM; } diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c index 4798fb7fe35d..b6a534a3e0b1 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c @@ -139,7 +139,8 @@ int dpaa2_switch_acl_entry_add(struct dpaa2_switch_filter_block *filter_block, err = dpsw_acl_add_entry(ethsw->mc_io, 0, ethsw->dpsw_handle, filter_block->acl_id, acl_entry_cfg); - dma_unmap_single(dev, acl_entry_cfg->key_iova, sizeof(cmd_buff), + dma_unmap_single(dev, acl_entry_cfg->key_iova, + DPAA2_ETHSW_PORT_ACL_CMD_BUF_SIZE, DMA_TO_DEVICE); if (err) { dev_err(dev, "dpsw_acl_add_entry() failed %d\n", err); @@ -181,8 +182,8 @@ dpaa2_switch_acl_entry_remove(struct dpaa2_switch_filter_block *block, err = dpsw_acl_remove_entry(ethsw->mc_io, 0, ethsw->dpsw_handle, block->acl_id, acl_entry_cfg); - dma_unmap_single(dev, acl_entry_cfg->key_iova, sizeof(cmd_buff), - DMA_TO_DEVICE); + dma_unmap_single(dev, acl_entry_cfg->key_iova, + DPAA2_ETHSW_PORT_ACL_CMD_BUF_SIZE, DMA_TO_DEVICE); if (err) { dev_err(dev, "dpsw_acl_remove_entry() failed %d\n", err); kfree(cmd_buff); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c index 97d3151076d5..e01a246124ac 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c @@ -1998,9 +1998,6 @@ static int dpaa2_switch_port_attr_set_event(struct net_device *netdev, return notifier_from_errno(err); } -static struct notifier_block dpaa2_switch_port_switchdev_nb; -static struct notifier_block dpaa2_switch_port_switchdev_blocking_nb; - static int dpaa2_switch_port_bridge_join(struct net_device *netdev, struct net_device *upper_dev, struct netlink_ext_ack *extack) @@ -2043,9 +2040,7 @@ static int dpaa2_switch_port_bridge_join(struct net_device *netdev, goto err_egress_flood; err = switchdev_bridge_port_offload(netdev, netdev, NULL, - &dpaa2_switch_port_switchdev_nb, - &dpaa2_switch_port_switchdev_blocking_nb, - false, extack); + NULL, NULL, false, extack); if (err) goto err_switchdev_offload; @@ -2079,9 +2074,7 @@ static int dpaa2_switch_port_restore_rxvlan(struct net_device *vdev, int vid, vo static void dpaa2_switch_port_pre_bridge_leave(struct net_device *netdev) { - switchdev_bridge_port_unoffload(netdev, NULL, - &dpaa2_switch_port_switchdev_nb, - &dpaa2_switch_port_switchdev_blocking_nb); + switchdev_bridge_port_unoffload(netdev, NULL, NULL, NULL); } static int dpaa2_switch_port_bridge_leave(struct net_device *netdev) diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index c3b7694a7485..e08c7b572497 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -3731,31 +3731,26 @@ static int fec_set_features(struct net_device *netdev, return 0; } -static u16 fec_enet_get_raw_vlan_tci(struct sk_buff *skb) -{ - struct vlan_ethhdr *vhdr; - unsigned short vlan_TCI = 0; - - if (skb->protocol == htons(ETH_P_ALL)) { - vhdr = (struct vlan_ethhdr *)(skb->data); - vlan_TCI = ntohs(vhdr->h_vlan_TCI); - } - - return vlan_TCI; -} - static u16 fec_enet_select_queue(struct net_device *ndev, struct sk_buff *skb, struct net_device *sb_dev) { struct fec_enet_private *fep = netdev_priv(ndev); - u16 vlan_tag; + u16 vlan_tag = 0; if (!(fep->quirks & FEC_QUIRK_HAS_AVB)) return netdev_pick_tx(ndev, skb, NULL); - vlan_tag = fec_enet_get_raw_vlan_tci(skb); - if (!vlan_tag) + /* VLAN is present in the payload.*/ + if (eth_type_vlan(skb->protocol)) { + struct vlan_ethhdr *vhdr = skb_vlan_eth_hdr(skb); + + vlan_tag = ntohs(vhdr->h_vlan_TCI); + /* VLAN is present in the skb but not yet pushed in the payload.*/ + } else if (skb_vlan_tag_present(skb)) { + vlan_tag = skb->vlan_tci; + } else { return vlan_tag; + } return fec_enet_vlan_pri_to_queue[vlan_tag >> 13]; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 1ab8dbe2d880..d5519af34657 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -107,12 +107,18 @@ static struct workqueue_struct *i40e_wq; static void netdev_hw_addr_refcnt(struct i40e_mac_filter *f, struct net_device *netdev, int delta) { + struct netdev_hw_addr_list *ha_list; struct netdev_hw_addr *ha; if (!f || !netdev) return; - netdev_for_each_mc_addr(ha, netdev) { + if (is_unicast_ether_addr(f->macaddr) || is_link_local_ether_addr(f->macaddr)) + ha_list = &netdev->uc; + else + ha_list = &netdev->mc; + + netdev_hw_addr_list_for_each(ha, ha_list) { if (ether_addr_equal(ha->addr, f->macaddr)) { ha->refcount += delta; if (ha->refcount <= 0) @@ -16512,6 +16518,9 @@ static void i40e_pci_error_reset_done(struct pci_dev *pdev) return; i40e_reset_and_rebuild(pf, false, false); +#ifdef CONFIG_PCI_IOV + i40e_restore_all_vfs_msi_state(pdev); +#endif /* CONFIG_PCI_IOV */ } /** diff --git a/drivers/net/ethernet/intel/i40e/i40e_register.h b/drivers/net/ethernet/intel/i40e/i40e_register.h index f408fcf23ce8..f6671ac79735 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_register.h +++ b/drivers/net/ethernet/intel/i40e/i40e_register.h @@ -207,7 +207,7 @@ #define I40E_GLGEN_MSCA_OPCODE_SHIFT 26 #define I40E_GLGEN_MSCA_OPCODE_MASK(_i) I40E_MASK(_i, I40E_GLGEN_MSCA_OPCODE_SHIFT) #define I40E_GLGEN_MSCA_STCODE_SHIFT 28 -#define I40E_GLGEN_MSCA_STCODE_MASK I40E_MASK(0x1, I40E_GLGEN_MSCA_STCODE_SHIFT) +#define I40E_GLGEN_MSCA_STCODE_MASK(_i) I40E_MASK(_i, I40E_GLGEN_MSCA_STCODE_SHIFT) #define I40E_GLGEN_MSCA_MDICMD_SHIFT 30 #define I40E_GLGEN_MSCA_MDICMD_MASK I40E_MASK(0x1, I40E_GLGEN_MSCA_MDICMD_SHIFT) #define I40E_GLGEN_MSCA_MDIINPROGEN_SHIFT 31 diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h index aff6dc6afbe2..f95bc2a4a838 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_type.h +++ b/drivers/net/ethernet/intel/i40e/i40e_type.h @@ -37,11 +37,11 @@ typedef void (*I40E_ADMINQ_CALLBACK)(struct i40e_hw *, struct i40e_aq_desc *); #define I40E_QTX_CTL_VM_QUEUE 0x1 #define I40E_QTX_CTL_PF_QUEUE 0x2 -#define I40E_MDIO_CLAUSE22_STCODE_MASK I40E_GLGEN_MSCA_STCODE_MASK +#define I40E_MDIO_CLAUSE22_STCODE_MASK I40E_GLGEN_MSCA_STCODE_MASK(1) #define I40E_MDIO_CLAUSE22_OPCODE_WRITE_MASK I40E_GLGEN_MSCA_OPCODE_MASK(1) #define I40E_MDIO_CLAUSE22_OPCODE_READ_MASK I40E_GLGEN_MSCA_OPCODE_MASK(2) -#define I40E_MDIO_CLAUSE45_STCODE_MASK I40E_GLGEN_MSCA_STCODE_MASK +#define I40E_MDIO_CLAUSE45_STCODE_MASK I40E_GLGEN_MSCA_STCODE_MASK(0) #define I40E_MDIO_CLAUSE45_OPCODE_ADDRESS_MASK I40E_GLGEN_MSCA_OPCODE_MASK(0) #define I40E_MDIO_CLAUSE45_OPCODE_WRITE_MASK I40E_GLGEN_MSCA_OPCODE_MASK(1) #define I40E_MDIO_CLAUSE45_OPCODE_READ_MASK I40E_GLGEN_MSCA_OPCODE_MASK(3) diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 3f99eb198245..de5ec4e6bedf 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -154,6 +154,32 @@ void i40e_vc_notify_reset(struct i40e_pf *pf) (u8 *)&pfe, sizeof(struct virtchnl_pf_event)); } +#ifdef CONFIG_PCI_IOV +void i40e_restore_all_vfs_msi_state(struct pci_dev *pdev) +{ + u16 vf_id; + u16 pos; + + /* Continue only if this is a PF */ + if (!pdev->is_physfn) + return; + + if (!pci_num_vf(pdev)) + return; + + pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_SRIOV); + if (pos) { + struct pci_dev *vf_dev = NULL; + + pci_read_config_word(pdev, pos + PCI_SRIOV_VF_DID, &vf_id); + while ((vf_dev = pci_get_device(pdev->vendor, vf_id, vf_dev))) { + if (vf_dev->is_virtfn && vf_dev->physfn == pdev) + pci_restore_msi_state(vf_dev); + } + } +} +#endif /* CONFIG_PCI_IOV */ + /** * i40e_vc_notify_vf_reset * @vf: pointer to the VF structure @@ -3521,16 +3547,16 @@ static int i40e_validate_cloud_filter(struct i40e_vf *vf, bool found = false; int bkt; - if (!tc_filter->action) { + if (tc_filter->action != VIRTCHNL_ACTION_TC_REDIRECT) { dev_info(&pf->pdev->dev, - "VF %d: Currently ADq doesn't support Drop Action\n", - vf->vf_id); + "VF %d: ADQ doesn't support this action (%d)\n", + vf->vf_id, tc_filter->action); goto err; } /* action_meta is TC number here to which the filter is applied */ if (!tc_filter->action_meta || - tc_filter->action_meta > I40E_MAX_VF_VSI) { + tc_filter->action_meta > vf->num_tc) { dev_info(&pf->pdev->dev, "VF %d: Invalid TC number %u\n", vf->vf_id, tc_filter->action_meta); goto err; diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h index 2ee0f8a23248..5fd607c0de0a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h @@ -137,6 +137,9 @@ int i40e_ndo_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool enable); void i40e_vc_notify_link_state(struct i40e_pf *pf); void i40e_vc_notify_reset(struct i40e_pf *pf); +#ifdef CONFIG_PCI_IOV +void i40e_restore_all_vfs_msi_state(struct pci_dev *pdev); +#endif /* CONFIG_PCI_IOV */ int i40e_get_vf_stats(struct net_device *netdev, int vf_id, struct ifla_vf_stats *vf_stats); diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index e7ab89dc883a..63b45c61cc4a 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -292,6 +292,7 @@ struct iavf_adapter { #define IAVF_FLAG_QUEUES_DISABLED BIT(17) #define IAVF_FLAG_SETUP_NETDEV_FEATURES BIT(18) #define IAVF_FLAG_REINIT_MSIX_NEEDED BIT(20) +#define IAVF_FLAG_FDIR_ENABLED BIT(21) /* duplicates for common code */ #define IAVF_FLAG_DCB_ENABLED 0 /* flags for admin queue service task */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index 19cbfe554689..dc499fe7734e 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -1061,7 +1061,7 @@ iavf_get_ethtool_fdir_entry(struct iavf_adapter *adapter, struct iavf_fdir_fltr *rule = NULL; int ret = 0; - if (!FDIR_FLTR_SUPPORT(adapter)) + if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED)) return -EOPNOTSUPP; spin_lock_bh(&adapter->fdir_fltr_lock); @@ -1203,7 +1203,7 @@ iavf_get_fdir_fltr_ids(struct iavf_adapter *adapter, struct ethtool_rxnfc *cmd, unsigned int cnt = 0; int val = 0; - if (!FDIR_FLTR_SUPPORT(adapter)) + if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED)) return -EOPNOTSUPP; cmd->data = IAVF_MAX_FDIR_FILTERS; @@ -1395,7 +1395,7 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx int count = 50; int err; - if (!FDIR_FLTR_SUPPORT(adapter)) + if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED)) return -EOPNOTSUPP; if (fsp->flow_type & FLOW_MAC_EXT) @@ -1436,12 +1436,16 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx spin_lock_bh(&adapter->fdir_fltr_lock); iavf_fdir_list_add_fltr(adapter, fltr); adapter->fdir_active_fltr++; - fltr->state = IAVF_FDIR_FLTR_ADD_REQUEST; - adapter->aq_required |= IAVF_FLAG_AQ_ADD_FDIR_FILTER; + if (adapter->link_up) { + fltr->state = IAVF_FDIR_FLTR_ADD_REQUEST; + adapter->aq_required |= IAVF_FLAG_AQ_ADD_FDIR_FILTER; + } else { + fltr->state = IAVF_FDIR_FLTR_INACTIVE; + } spin_unlock_bh(&adapter->fdir_fltr_lock); - mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0); - + if (adapter->link_up) + mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0); ret: if (err && fltr) kfree(fltr); @@ -1463,7 +1467,7 @@ static int iavf_del_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx struct iavf_fdir_fltr *fltr = NULL; int err = 0; - if (!FDIR_FLTR_SUPPORT(adapter)) + if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED)) return -EOPNOTSUPP; spin_lock_bh(&adapter->fdir_fltr_lock); @@ -1472,6 +1476,11 @@ static int iavf_del_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx if (fltr->state == IAVF_FDIR_FLTR_ACTIVE) { fltr->state = IAVF_FDIR_FLTR_DEL_REQUEST; adapter->aq_required |= IAVF_FLAG_AQ_DEL_FDIR_FILTER; + } else if (fltr->state == IAVF_FDIR_FLTR_INACTIVE) { + list_del(&fltr->list); + kfree(fltr); + adapter->fdir_active_fltr--; + fltr = NULL; } else { err = -EBUSY; } @@ -1780,7 +1789,7 @@ static int iavf_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, ret = 0; break; case ETHTOOL_GRXCLSRLCNT: - if (!FDIR_FLTR_SUPPORT(adapter)) + if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED)) break; spin_lock_bh(&adapter->fdir_fltr_lock); cmd->rule_cnt = adapter->fdir_active_fltr; diff --git a/drivers/net/ethernet/intel/iavf/iavf_fdir.h b/drivers/net/ethernet/intel/iavf/iavf_fdir.h index 9eb9f73f6adf..d31bd923ba8c 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_fdir.h +++ b/drivers/net/ethernet/intel/iavf/iavf_fdir.h @@ -6,12 +6,25 @@ struct iavf_adapter; -/* State of Flow Director filter */ +/* State of Flow Director filter + * + * *_REQUEST states are used to mark filter to be sent to PF driver to perform + * an action (either add or delete filter). *_PENDING states are an indication + * that request was sent to PF and the driver is waiting for response. + * + * Both DELETE and DISABLE states are being used to delete a filter in PF. + * The difference is that after a successful response filter in DEL_PENDING + * state is being deleted from VF driver as well and filter in DIS_PENDING state + * is being changed to INACTIVE state. + */ enum iavf_fdir_fltr_state_t { IAVF_FDIR_FLTR_ADD_REQUEST, /* User requests to add filter */ IAVF_FDIR_FLTR_ADD_PENDING, /* Filter pending add by the PF */ IAVF_FDIR_FLTR_DEL_REQUEST, /* User requests to delete filter */ IAVF_FDIR_FLTR_DEL_PENDING, /* Filter pending delete by the PF */ + IAVF_FDIR_FLTR_DIS_REQUEST, /* Filter scheduled to be disabled */ + IAVF_FDIR_FLTR_DIS_PENDING, /* Filter pending disable by the PF */ + IAVF_FDIR_FLTR_INACTIVE, /* Filter inactive on link down */ IAVF_FDIR_FLTR_ACTIVE, /* Filter is active */ }; diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index c862ebcd2e39..e8d5b889addc 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -277,27 +277,6 @@ void iavf_free_virt_mem(struct iavf_hw *hw, struct iavf_virt_mem *mem) } /** - * iavf_lock_timeout - try to lock mutex but give up after timeout - * @lock: mutex that should be locked - * @msecs: timeout in msecs - * - * Returns 0 on success, negative on failure - **/ -static int iavf_lock_timeout(struct mutex *lock, unsigned int msecs) -{ - unsigned int wait, delay = 10; - - for (wait = 0; wait < msecs; wait += delay) { - if (mutex_trylock(lock)) - return 0; - - msleep(delay); - } - - return -1; -} - -/** * iavf_schedule_reset - Set the flags and schedule a reset event * @adapter: board private structure * @flags: IAVF_FLAG_RESET_PENDING or IAVF_FLAG_RESET_NEEDED @@ -1353,18 +1332,20 @@ static void iavf_clear_cloud_filters(struct iavf_adapter *adapter) **/ static void iavf_clear_fdir_filters(struct iavf_adapter *adapter) { - struct iavf_fdir_fltr *fdir, *fdirtmp; + struct iavf_fdir_fltr *fdir; /* remove all Flow Director filters */ spin_lock_bh(&adapter->fdir_fltr_lock); - list_for_each_entry_safe(fdir, fdirtmp, &adapter->fdir_list_head, - list) { + list_for_each_entry(fdir, &adapter->fdir_list_head, list) { if (fdir->state == IAVF_FDIR_FLTR_ADD_REQUEST) { - list_del(&fdir->list); - kfree(fdir); - adapter->fdir_active_fltr--; - } else { - fdir->state = IAVF_FDIR_FLTR_DEL_REQUEST; + /* Cancel a request, keep filter as inactive */ + fdir->state = IAVF_FDIR_FLTR_INACTIVE; + } else if (fdir->state == IAVF_FDIR_FLTR_ADD_PENDING || + fdir->state == IAVF_FDIR_FLTR_ACTIVE) { + /* Disable filters which are active or have a pending + * request to PF to be added + */ + fdir->state = IAVF_FDIR_FLTR_DIS_REQUEST; } } spin_unlock_bh(&adapter->fdir_fltr_lock); @@ -4113,6 +4094,33 @@ static int iavf_setup_tc(struct net_device *netdev, enum tc_setup_type type, } /** + * iavf_restore_fdir_filters + * @adapter: board private structure + * + * Restore existing FDIR filters when VF netdev comes back up. + **/ +static void iavf_restore_fdir_filters(struct iavf_adapter *adapter) +{ + struct iavf_fdir_fltr *f; + + spin_lock_bh(&adapter->fdir_fltr_lock); + list_for_each_entry(f, &adapter->fdir_list_head, list) { + if (f->state == IAVF_FDIR_FLTR_DIS_REQUEST) { + /* Cancel a request, keep filter as active */ + f->state = IAVF_FDIR_FLTR_ACTIVE; + } else if (f->state == IAVF_FDIR_FLTR_DIS_PENDING || + f->state == IAVF_FDIR_FLTR_INACTIVE) { + /* Add filters which are inactive or have a pending + * request to PF to be deleted + */ + f->state = IAVF_FDIR_FLTR_ADD_REQUEST; + adapter->aq_required |= IAVF_FLAG_AQ_ADD_FDIR_FILTER; + } + } + spin_unlock_bh(&adapter->fdir_fltr_lock); +} + +/** * iavf_open - Called when a network interface is made active * @netdev: network interface device structure * @@ -4179,8 +4187,9 @@ static int iavf_open(struct net_device *netdev) spin_unlock_bh(&adapter->mac_vlan_list_lock); - /* Restore VLAN filters that were removed with IFF_DOWN */ + /* Restore filters that were removed with IFF_DOWN */ iavf_restore_filters(adapter); + iavf_restore_fdir_filters(adapter); iavf_configure(adapter); @@ -4311,6 +4320,49 @@ static int iavf_change_mtu(struct net_device *netdev, int new_mtu) return ret; } +/** + * iavf_disable_fdir - disable Flow Director and clear existing filters + * @adapter: board private structure + **/ +static void iavf_disable_fdir(struct iavf_adapter *adapter) +{ + struct iavf_fdir_fltr *fdir, *fdirtmp; + bool del_filters = false; + + adapter->flags &= ~IAVF_FLAG_FDIR_ENABLED; + + /* remove all Flow Director filters */ + spin_lock_bh(&adapter->fdir_fltr_lock); + list_for_each_entry_safe(fdir, fdirtmp, &adapter->fdir_list_head, + list) { + if (fdir->state == IAVF_FDIR_FLTR_ADD_REQUEST || + fdir->state == IAVF_FDIR_FLTR_INACTIVE) { + /* Delete filters not registered in PF */ + list_del(&fdir->list); + kfree(fdir); + adapter->fdir_active_fltr--; + } else if (fdir->state == IAVF_FDIR_FLTR_ADD_PENDING || + fdir->state == IAVF_FDIR_FLTR_DIS_REQUEST || + fdir->state == IAVF_FDIR_FLTR_ACTIVE) { + /* Filters registered in PF, schedule their deletion */ + fdir->state = IAVF_FDIR_FLTR_DEL_REQUEST; + del_filters = true; + } else if (fdir->state == IAVF_FDIR_FLTR_DIS_PENDING) { + /* Request to delete filter already sent to PF, change + * state to DEL_PENDING to delete filter after PF's + * response, not set as INACTIVE + */ + fdir->state = IAVF_FDIR_FLTR_DEL_PENDING; + } + } + spin_unlock_bh(&adapter->fdir_fltr_lock); + + if (del_filters) { + adapter->aq_required |= IAVF_FLAG_AQ_DEL_FDIR_FILTER; + mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0); + } +} + #define NETIF_VLAN_OFFLOAD_FEATURES (NETIF_F_HW_VLAN_CTAG_RX | \ NETIF_F_HW_VLAN_CTAG_TX | \ NETIF_F_HW_VLAN_STAG_RX | \ @@ -4336,6 +4388,13 @@ static int iavf_set_features(struct net_device *netdev, ((netdev->features & NETIF_F_RXFCS) ^ (features & NETIF_F_RXFCS))) iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED); + if ((netdev->features & NETIF_F_NTUPLE) ^ (features & NETIF_F_NTUPLE)) { + if (features & NETIF_F_NTUPLE) + adapter->flags |= IAVF_FLAG_FDIR_ENABLED; + else + iavf_disable_fdir(adapter); + } + return 0; } @@ -4685,6 +4744,9 @@ static netdev_features_t iavf_fix_features(struct net_device *netdev, features = iavf_fix_netdev_vlan_features(adapter, features); + if (!FDIR_FLTR_SUPPORT(adapter)) + features &= ~NETIF_F_NTUPLE; + return iavf_fix_strip_features(adapter, features); } @@ -4802,6 +4864,12 @@ int iavf_process_config(struct iavf_adapter *adapter) if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN) netdev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; + if (FDIR_FLTR_SUPPORT(adapter)) { + netdev->hw_features |= NETIF_F_NTUPLE; + netdev->features |= NETIF_F_NTUPLE; + adapter->flags |= IAVF_FLAG_FDIR_ENABLED; + } + netdev->priv_flags |= IFF_UNICAST_FLT; /* Do not turn on offloads when they are requested to be turned off. @@ -4826,34 +4894,6 @@ int iavf_process_config(struct iavf_adapter *adapter) } /** - * iavf_shutdown - Shutdown the device in preparation for a reboot - * @pdev: pci device structure - **/ -static void iavf_shutdown(struct pci_dev *pdev) -{ - struct iavf_adapter *adapter = iavf_pdev_to_adapter(pdev); - struct net_device *netdev = adapter->netdev; - - netif_device_detach(netdev); - - if (netif_running(netdev)) - iavf_close(netdev); - - if (iavf_lock_timeout(&adapter->crit_lock, 5000)) - dev_warn(&adapter->pdev->dev, "%s: failed to acquire crit_lock\n", __func__); - /* Prevent the watchdog from running. */ - iavf_change_state(adapter, __IAVF_REMOVE); - adapter->aq_required = 0; - mutex_unlock(&adapter->crit_lock); - -#ifdef CONFIG_PM - pci_save_state(pdev); - -#endif - pci_disable_device(pdev); -} - -/** * iavf_probe - Device Initialization Routine * @pdev: PCI device information struct * @ent: entry in iavf_pci_tbl @@ -5063,16 +5103,21 @@ static int __maybe_unused iavf_resume(struct device *dev_d) **/ static void iavf_remove(struct pci_dev *pdev) { - struct iavf_adapter *adapter = iavf_pdev_to_adapter(pdev); struct iavf_fdir_fltr *fdir, *fdirtmp; struct iavf_vlan_filter *vlf, *vlftmp; struct iavf_cloud_filter *cf, *cftmp; struct iavf_adv_rss *rss, *rsstmp; struct iavf_mac_filter *f, *ftmp; + struct iavf_adapter *adapter; struct net_device *netdev; struct iavf_hw *hw; - netdev = adapter->netdev; + /* Don't proceed with remove if netdev is already freed */ + netdev = pci_get_drvdata(pdev); + if (!netdev) + return; + + adapter = iavf_pdev_to_adapter(pdev); hw = &adapter->hw; if (test_and_set_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section)) @@ -5184,11 +5229,25 @@ static void iavf_remove(struct pci_dev *pdev) destroy_workqueue(adapter->wq); + pci_set_drvdata(pdev, NULL); + free_netdev(netdev); pci_disable_device(pdev); } +/** + * iavf_shutdown - Shutdown the device in preparation for a reboot + * @pdev: pci device structure + **/ +static void iavf_shutdown(struct pci_dev *pdev) +{ + iavf_remove(pdev); + + if (system_state == SYSTEM_POWER_OFF) + pci_set_power_state(pdev, PCI_D3hot); +} + static SIMPLE_DEV_PM_OPS(iavf_pm_ops, iavf_suspend, iavf_resume); static struct pci_driver iavf_driver = { diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 64c4443dbef9..2d9366be0ec5 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -1735,8 +1735,8 @@ void iavf_add_fdir_filter(struct iavf_adapter *adapter) **/ void iavf_del_fdir_filter(struct iavf_adapter *adapter) { + struct virtchnl_fdir_del f = {}; struct iavf_fdir_fltr *fdir; - struct virtchnl_fdir_del f; bool process_fltr = false; int len; @@ -1753,11 +1753,16 @@ void iavf_del_fdir_filter(struct iavf_adapter *adapter) list_for_each_entry(fdir, &adapter->fdir_list_head, list) { if (fdir->state == IAVF_FDIR_FLTR_DEL_REQUEST) { process_fltr = true; - memset(&f, 0, len); f.vsi_id = fdir->vc_add_msg.vsi_id; f.flow_id = fdir->flow_id; fdir->state = IAVF_FDIR_FLTR_DEL_PENDING; break; + } else if (fdir->state == IAVF_FDIR_FLTR_DIS_REQUEST) { + process_fltr = true; + f.vsi_id = fdir->vc_add_msg.vsi_id; + f.flow_id = fdir->flow_id; + fdir->state = IAVF_FDIR_FLTR_DIS_PENDING; + break; } } spin_unlock_bh(&adapter->fdir_fltr_lock); @@ -1902,6 +1907,48 @@ static void iavf_netdev_features_vlan_strip_set(struct net_device *netdev, } /** + * iavf_activate_fdir_filters - Reactivate all FDIR filters after a reset + * @adapter: private adapter structure + * + * Called after a reset to re-add all FDIR filters and delete some of them + * if they were pending to be deleted. + */ +static void iavf_activate_fdir_filters(struct iavf_adapter *adapter) +{ + struct iavf_fdir_fltr *f, *ftmp; + bool add_filters = false; + + spin_lock_bh(&adapter->fdir_fltr_lock); + list_for_each_entry_safe(f, ftmp, &adapter->fdir_list_head, list) { + if (f->state == IAVF_FDIR_FLTR_ADD_REQUEST || + f->state == IAVF_FDIR_FLTR_ADD_PENDING || + f->state == IAVF_FDIR_FLTR_ACTIVE) { + /* All filters and requests have been removed in PF, + * restore them + */ + f->state = IAVF_FDIR_FLTR_ADD_REQUEST; + add_filters = true; + } else if (f->state == IAVF_FDIR_FLTR_DIS_REQUEST || + f->state == IAVF_FDIR_FLTR_DIS_PENDING) { + /* Link down state, leave filters as inactive */ + f->state = IAVF_FDIR_FLTR_INACTIVE; + } else if (f->state == IAVF_FDIR_FLTR_DEL_REQUEST || + f->state == IAVF_FDIR_FLTR_DEL_PENDING) { + /* Delete filters that were pending to be deleted, the + * list on PF is already cleared after a reset + */ + list_del(&f->list); + kfree(f); + adapter->fdir_active_fltr--; + } + } + spin_unlock_bh(&adapter->fdir_fltr_lock); + + if (add_filters) + adapter->aq_required |= IAVF_FLAG_AQ_ADD_FDIR_FILTER; +} + +/** * iavf_virtchnl_completion * @adapter: adapter structure * @v_opcode: opcode sent by PF @@ -2078,7 +2125,8 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, spin_lock_bh(&adapter->fdir_fltr_lock); list_for_each_entry(fdir, &adapter->fdir_list_head, list) { - if (fdir->state == IAVF_FDIR_FLTR_DEL_PENDING) { + if (fdir->state == IAVF_FDIR_FLTR_DEL_PENDING || + fdir->state == IAVF_FDIR_FLTR_DIS_PENDING) { fdir->state = IAVF_FDIR_FLTR_ACTIVE; dev_info(&adapter->pdev->dev, "Failed to del Flow Director filter, error %s\n", iavf_stat_str(&adapter->hw, @@ -2214,6 +2262,8 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, spin_unlock_bh(&adapter->mac_vlan_list_lock); + iavf_activate_fdir_filters(adapter); + iavf_parse_vf_resource_msg(adapter); /* negotiated VIRTCHNL_VF_OFFLOAD_VLAN_V2, so wait for the @@ -2390,7 +2440,9 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, list_for_each_entry_safe(fdir, fdir_tmp, &adapter->fdir_list_head, list) { if (fdir->state == IAVF_FDIR_FLTR_DEL_PENDING) { - if (del_fltr->status == VIRTCHNL_FDIR_SUCCESS) { + if (del_fltr->status == VIRTCHNL_FDIR_SUCCESS || + del_fltr->status == + VIRTCHNL_FDIR_FAILURE_RULE_NONEXIST) { dev_info(&adapter->pdev->dev, "Flow Director filter with location %u is deleted\n", fdir->loc); list_del(&fdir->list); @@ -2402,6 +2454,17 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, del_fltr->status); iavf_print_fdir_fltr(adapter, fdir); } + } else if (fdir->state == IAVF_FDIR_FLTR_DIS_PENDING) { + if (del_fltr->status == VIRTCHNL_FDIR_SUCCESS || + del_fltr->status == + VIRTCHNL_FDIR_FAILURE_RULE_NONEXIST) { + fdir->state = IAVF_FDIR_FLTR_INACTIVE; + } else { + fdir->state = IAVF_FDIR_FLTR_ACTIVE; + dev_info(&adapter->pdev->dev, "Failed to disable Flow Director filter with status: %d\n", + del_fltr->status); + iavf_print_fdir_fltr(adapter, fdir); + } } } spin_unlock_bh(&adapter->fdir_fltr_lock); diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index d7fdb7ba7268..fbd5d92182d3 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -1359,8 +1359,9 @@ struct ice_aqc_get_link_status_data { u8 lp_flowcontrol; #define ICE_AQ_LINK_LP_PAUSE_ADV BIT(0) #define ICE_AQ_LINK_LP_ASM_DIR_ADV BIT(1) + u8 reserved5[5]; #define ICE_AQC_LS_DATA_SIZE_V2 \ - offsetofend(struct ice_aqc_get_link_status_data, lp_flowcontrol) + offsetofend(struct ice_aqc_get_link_status_data, reserved5) } __packed; /* Set event mask command (direct 0x0613) */ diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 9a6c25f98632..edac34c796ce 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -5332,7 +5332,6 @@ ice_aq_get_cgu_dpll_status(struct ice_hw *hw, u8 dpll_num, u8 *ref_state, u8 *eec_mode) { struct ice_aqc_get_cgu_dpll_status *cmd; - const s64 nsec_per_psec = 1000LL; struct ice_aq_desc desc; int status; @@ -5348,8 +5347,7 @@ ice_aq_get_cgu_dpll_status(struct ice_hw *hw, u8 dpll_num, u8 *ref_state, *phase_offset = le32_to_cpu(cmd->phase_offset_h); *phase_offset <<= 32; *phase_offset += le32_to_cpu(cmd->phase_offset_l); - *phase_offset = div64_s64(sign_extend64(*phase_offset, 47), - nsec_per_psec); + *phase_offset = sign_extend64(*phase_offset, 47); *eec_mode = cmd->eec_mode; } diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index a34083567e6f..bde9bc74f928 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -1850,14 +1850,14 @@ ice_phy_type_to_ethtool(struct net_device *netdev, linkmode_zero(ks->link_modes.supported); linkmode_zero(ks->link_modes.advertising); - for (i = 0; i < BITS_PER_TYPE(u64); i++) { + for (i = 0; i < ARRAY_SIZE(phy_type_low_lkup); i++) { if (phy_types_low & BIT_ULL(i)) ice_linkmode_set_bit(&phy_type_low_lkup[i], ks, req_speeds, advert_phy_type_lo, i); } - for (i = 0; i < BITS_PER_TYPE(u64); i++) { + for (i = 0; i < ARRAY_SIZE(phy_type_high_lkup); i++) { if (phy_types_high & BIT_ULL(i)) ice_linkmode_set_bit(&phy_type_high_lkup[i], ks, req_speeds, advert_phy_type_hi, diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c index 280994ee5933..b47cd43ae871 100644 --- a/drivers/net/ethernet/intel/ice/ice_lag.c +++ b/drivers/net/ethernet/intel/ice/ice_lag.c @@ -1981,6 +1981,8 @@ int ice_init_lag(struct ice_pf *pf) int n, err; ice_lag_init_feature_support_flag(pf); + if (!ice_is_feature_supported(pf, ICE_F_SRIOV_LAG)) + return 0; pf->lag = kzalloc(sizeof(*lag), GFP_KERNEL); if (!pf->lag) diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 4b1e56396293..1bad6e17f9be 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -2371,6 +2371,9 @@ static int ice_vsi_cfg_tc_lan(struct ice_pf *pf, struct ice_vsi *vsi) } else { max_txqs[i] = vsi->alloc_txq; } + + if (vsi->type == ICE_VSI_PF) + max_txqs[i] += vsi->num_xdp_txq; } dev_dbg(dev, "vsi->tc_cfg.ena_tc = %d\n", vsi->tc_cfg.ena_tc); @@ -2620,10 +2623,6 @@ void ice_vsi_decfg(struct ice_vsi *vsi) if (vsi->type == ICE_VSI_VF && vsi->agg_node && vsi->agg_node->valid) vsi->agg_node->num_vsis--; - if (vsi->agg_node) { - vsi->agg_node->valid = false; - vsi->agg_node->agg_id = 0; - } } /** diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index fb9c93f37e84..adfdea1e2805 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -2146,7 +2146,7 @@ static int ice_configure_phy(struct ice_vsi *vsi) /* Ensure we have media as we cannot configure a medialess port */ if (!(phy->link_info.link_info & ICE_AQ_MEDIA_AVAILABLE)) - return -EPERM; + return -ENOMEDIUM; ice_print_topo_conflict(vsi); @@ -9187,8 +9187,14 @@ int ice_stop(struct net_device *netdev) int link_err = ice_force_phys_link_state(vsi, false); if (link_err) { - netdev_err(vsi->netdev, "Failed to set physical link down, VSI %d error %d\n", - vsi->vsi_num, link_err); + if (link_err == -ENOMEDIUM) + netdev_info(vsi->netdev, "Skipping link reconfig - no media attached, VSI %d\n", + vsi->vsi_num); + else + netdev_err(vsi->netdev, "Failed to set physical link down, VSI %d error %d\n", + vsi->vsi_num, link_err); + + ice_vsi_close(vsi); return -EIO; } } diff --git a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c index 81288a17da2a..20c4b3a64710 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c @@ -1044,7 +1044,6 @@ static int idpf_rx_singleq_clean(struct idpf_queue *rx_q, int budget) } idpf_rx_sync_for_cpu(rx_buf, fields.size); - skb = rx_q->skb; if (skb) idpf_rx_add_frag(rx_buf, skb, fields.size); else diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c index 1f728a9004d9..9e942e5baf39 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c @@ -396,7 +396,7 @@ static void idpf_rx_desc_rel(struct idpf_queue *rxq, bool bufq, s32 q_model) if (!rxq) return; - if (!bufq && idpf_is_queue_model_split(q_model) && rxq->skb) { + if (rxq->skb) { dev_kfree_skb_any(rxq->skb); rxq->skb = NULL; } diff --git a/drivers/net/ethernet/intel/idpf/virtchnl2.h b/drivers/net/ethernet/intel/idpf/virtchnl2.h index 07e72c72d156..8dc837889723 100644 --- a/drivers/net/ethernet/intel/idpf/virtchnl2.h +++ b/drivers/net/ethernet/intel/idpf/virtchnl2.h @@ -1104,9 +1104,9 @@ struct virtchnl2_rss_key { __le32 vport_id; __le16 key_len; u8 pad; - __DECLARE_FLEX_ARRAY(u8, key_flex); -}; -VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_rss_key); + u8 key_flex[]; +} __packed; +VIRTCHNL2_CHECK_STRUCT_LEN(7, virtchnl2_rss_key); /** * struct virtchnl2_queue_chunk - chunk of contiguous queues diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index f48f82d5e274..85cc16396506 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -568,6 +568,7 @@ struct igc_nfc_filter { u16 etype; __be16 vlan_etype; u16 vlan_tci; + u16 vlan_tci_mask; u8 src_addr[ETH_ALEN]; u8 dst_addr[ETH_ALEN]; u8 user_data[8]; diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c index 785eaa8e0ba8..859b2636f3d9 100644 --- a/drivers/net/ethernet/intel/igc/igc_ethtool.c +++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c @@ -958,6 +958,7 @@ static int igc_ethtool_set_coalesce(struct net_device *netdev, } #define ETHER_TYPE_FULL_MASK ((__force __be16)~0) +#define VLAN_TCI_FULL_MASK ((__force __be16)~0) static int igc_ethtool_get_nfc_rule(struct igc_adapter *adapter, struct ethtool_rxnfc *cmd) { @@ -980,10 +981,16 @@ static int igc_ethtool_get_nfc_rule(struct igc_adapter *adapter, fsp->m_u.ether_spec.h_proto = ETHER_TYPE_FULL_MASK; } + if (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_ETYPE) { + fsp->flow_type |= FLOW_EXT; + fsp->h_ext.vlan_etype = rule->filter.vlan_etype; + fsp->m_ext.vlan_etype = ETHER_TYPE_FULL_MASK; + } + if (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_TCI) { fsp->flow_type |= FLOW_EXT; fsp->h_ext.vlan_tci = htons(rule->filter.vlan_tci); - fsp->m_ext.vlan_tci = htons(VLAN_PRIO_MASK); + fsp->m_ext.vlan_tci = htons(rule->filter.vlan_tci_mask); } if (rule->filter.match_flags & IGC_FILTER_FLAG_DST_MAC_ADDR) { @@ -1218,6 +1225,7 @@ static void igc_ethtool_init_nfc_rule(struct igc_nfc_rule *rule, if ((fsp->flow_type & FLOW_EXT) && fsp->m_ext.vlan_tci) { rule->filter.vlan_tci = ntohs(fsp->h_ext.vlan_tci); + rule->filter.vlan_tci_mask = ntohs(fsp->m_ext.vlan_tci); rule->filter.match_flags |= IGC_FILTER_FLAG_VLAN_TCI; } @@ -1255,11 +1263,19 @@ static void igc_ethtool_init_nfc_rule(struct igc_nfc_rule *rule, memcpy(rule->filter.user_mask, fsp->m_ext.data, sizeof(fsp->m_ext.data)); } - /* When multiple filter options or user data or vlan etype is set, use a - * flex filter. + /* The i225/i226 has various different filters. Flex filters provide a + * way to match up to the first 128 bytes of a packet. Use them for: + * a) For specific user data + * b) For VLAN EtherType + * c) For full TCI match + * d) Or in case multiple filter criteria are set + * + * Otherwise, use the simple MAC, VLAN PRIO or EtherType filters. */ if ((rule->filter.match_flags & IGC_FILTER_FLAG_USER_DATA) || (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_ETYPE) || + ((rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_TCI) && + rule->filter.vlan_tci_mask == ntohs(VLAN_TCI_FULL_MASK)) || (rule->filter.match_flags & (rule->filter.match_flags - 1))) rule->flex = true; else @@ -1329,6 +1345,26 @@ static int igc_ethtool_add_nfc_rule(struct igc_adapter *adapter, return -EINVAL; } + /* There are two ways to match the VLAN TCI: + * 1. Match on PCP field and use vlan prio filter for it + * 2. Match on complete TCI field and use flex filter for it + */ + if ((fsp->flow_type & FLOW_EXT) && + fsp->m_ext.vlan_tci && + fsp->m_ext.vlan_tci != htons(VLAN_PRIO_MASK) && + fsp->m_ext.vlan_tci != VLAN_TCI_FULL_MASK) { + netdev_dbg(netdev, "VLAN mask not supported\n"); + return -EOPNOTSUPP; + } + + /* VLAN EtherType can only be matched by full mask. */ + if ((fsp->flow_type & FLOW_EXT) && + fsp->m_ext.vlan_etype && + fsp->m_ext.vlan_etype != ETHER_TYPE_FULL_MASK) { + netdev_dbg(netdev, "VLAN EtherType mask not supported\n"); + return -EOPNOTSUPP; + } + if (fsp->location >= IGC_MAX_RXNFC_RULES) { netdev_dbg(netdev, "Invalid location\n"); return -EINVAL; diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.c b/drivers/net/ethernet/intel/igc/igc_tsn.c index a9c08321aca9..22cefb1eeedf 100644 --- a/drivers/net/ethernet/intel/igc/igc_tsn.c +++ b/drivers/net/ethernet/intel/igc/igc_tsn.c @@ -227,7 +227,7 @@ static int igc_tsn_enable_offload(struct igc_adapter *adapter) wr32(IGC_TQAVCC(i), tqavcc); wr32(IGC_TQAVHC(i), - 0x80000000 + ring->hicredit * 0x7735); + 0x80000000 + ring->hicredit * 0x7736); } else { /* Disable any CBS for the queue */ txqctl &= ~(IGC_TXQCTL_QAV_SEL_MASK); diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c index 552970c7dec0..a9bdf3283a85 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c @@ -1193,6 +1193,13 @@ int octep_device_setup(struct octep_device *oct) if (ret) return ret; + INIT_WORK(&oct->tx_timeout_task, octep_tx_timeout_task); + INIT_WORK(&oct->ctrl_mbox_task, octep_ctrl_mbox_task); + INIT_DELAYED_WORK(&oct->intr_poll_task, octep_intr_poll_task); + oct->poll_non_ioq_intr = true; + queue_delayed_work(octep_wq, &oct->intr_poll_task, + msecs_to_jiffies(OCTEP_INTR_POLL_TIME_MSECS)); + atomic_set(&oct->hb_miss_cnt, 0); INIT_DELAYED_WORK(&oct->hb_task, octep_hb_timeout_task); @@ -1258,7 +1265,8 @@ static bool get_fw_ready_status(struct pci_dev *pdev) pci_read_config_byte(pdev, (pos + 8), &status); dev_info(&pdev->dev, "Firmware ready status = %u\n", status); - return status; +#define FW_STATUS_READY 1ULL + return status == FW_STATUS_READY; } return false; } @@ -1325,21 +1333,18 @@ static int octep_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_octep_config; } - octep_ctrl_net_get_info(octep_dev, OCTEP_CTRL_NET_INVALID_VFID, - &octep_dev->conf->fw_info); + err = octep_ctrl_net_get_info(octep_dev, OCTEP_CTRL_NET_INVALID_VFID, + &octep_dev->conf->fw_info); + if (err) { + dev_err(&pdev->dev, "Failed to get firmware info\n"); + goto register_dev_err; + } dev_info(&octep_dev->pdev->dev, "Heartbeat interval %u msecs Heartbeat miss count %u\n", octep_dev->conf->fw_info.hb_interval, octep_dev->conf->fw_info.hb_miss_count); queue_delayed_work(octep_wq, &octep_dev->hb_task, msecs_to_jiffies(octep_dev->conf->fw_info.hb_interval)); - INIT_WORK(&octep_dev->tx_timeout_task, octep_tx_timeout_task); - INIT_WORK(&octep_dev->ctrl_mbox_task, octep_ctrl_mbox_task); - INIT_DELAYED_WORK(&octep_dev->intr_poll_task, octep_intr_poll_task); - octep_dev->poll_non_ioq_intr = true; - queue_delayed_work(octep_wq, &octep_dev->intr_poll_task, - msecs_to_jiffies(OCTEP_INTR_POLL_TIME_MSECS)); - netdev->netdev_ops = &octep_netdev_ops; octep_set_ethtool_ops(netdev); netif_carrier_off(netdev); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/npc.h b/drivers/net/ethernet/marvell/octeontx2/af/npc.h index ab3e39eef2eb..8c0732c9a7ee 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/npc.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/npc.h @@ -528,7 +528,7 @@ struct npc_lt_def { u8 ltype_mask; u8 ltype_match; u8 lid; -}; +} __packed; struct npc_lt_def_ipsec { u8 ltype_mask; @@ -536,7 +536,7 @@ struct npc_lt_def_ipsec { u8 lid; u8 spi_offset; u8 spi_nz; -}; +} __packed; struct npc_lt_def_apad { u8 ltype_mask; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c index af21e2030cff..4728ba34b0e3 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c @@ -373,6 +373,11 @@ void rpm_lmac_pause_frm_config(void *rpmd, int lmac_id, bool enable) cfg |= RPMX_MTI_MAC100X_COMMAND_CONFIG_TX_P_DISABLE; rpm_write(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG, cfg); + /* Disable forward pause to driver */ + cfg = rpm_read(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG); + cfg &= ~RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_FWD; + rpm_write(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG, cfg); + /* Enable channel mask for all LMACS */ if (is_dev_rpm2(rpm)) rpm_write(rpm, lmac_id, RPM2_CMR_CHAN_MSK_OR, 0xffff); @@ -616,12 +621,10 @@ int rpm_lmac_pfc_config(void *rpmd, int lmac_id, u8 tx_pause, u8 rx_pause, u16 p if (rx_pause) { cfg &= ~(RPMX_MTI_MAC100X_COMMAND_CONFIG_RX_P_DISABLE | - RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE | - RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_FWD); + RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE); } else { cfg |= (RPMX_MTI_MAC100X_COMMAND_CONFIG_RX_P_DISABLE | - RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE | - RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_FWD); + RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE); } if (tx_pause) { diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index cce2806aaa50..8802961b8889 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -905,6 +905,7 @@ u32 rvu_cgx_get_fifolen(struct rvu *rvu); void *rvu_first_cgx_pdata(struct rvu *rvu); int cgxlmac_to_pf(struct rvu *rvu, int cgx_id, int lmac_id); int rvu_cgx_config_tx(void *cgxd, int lmac_id, bool enable); +int rvu_cgx_tx_enable(struct rvu *rvu, u16 pcifunc, bool enable); int rvu_cgx_prio_flow_ctrl_cfg(struct rvu *rvu, u16 pcifunc, u8 tx_pause, u8 rx_pause, u16 pfc_en); int rvu_cgx_cfg_pause_frm(struct rvu *rvu, u16 pcifunc, u8 tx_pause, u8 rx_pause); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c index 15a319684ed3..38acdc7a73bb 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c @@ -465,6 +465,23 @@ int rvu_cgx_config_rxtx(struct rvu *rvu, u16 pcifunc, bool start) return mac_ops->mac_rx_tx_enable(cgxd, lmac_id, start); } +int rvu_cgx_tx_enable(struct rvu *rvu, u16 pcifunc, bool enable) +{ + int pf = rvu_get_pf(pcifunc); + struct mac_ops *mac_ops; + u8 cgx_id, lmac_id; + void *cgxd; + + if (!is_cgx_config_permitted(rvu, pcifunc)) + return LMAC_AF_ERR_PERM_DENIED; + + rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id); + cgxd = rvu_cgx_pdata(cgx_id, rvu); + mac_ops = get_mac_ops(cgxd); + + return mac_ops->mac_tx_enable(cgxd, lmac_id, enable); +} + int rvu_cgx_config_tx(void *cgxd, int lmac_id, bool enable) { struct mac_ops *mac_ops; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c index 62780d8b4f9a..21b5d71c1e37 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c @@ -538,7 +538,7 @@ static int rvu_nix_register_reporters(struct rvu_devlink *rvu_dl) rvu_dl->devlink_wq = create_workqueue("rvu_devlink_wq"); if (!rvu_dl->devlink_wq) - goto err; + return -ENOMEM; INIT_WORK(&rvu_reporters->intr_work, rvu_nix_intr_work); INIT_WORK(&rvu_reporters->gen_work, rvu_nix_gen_work); @@ -546,9 +546,6 @@ static int rvu_nix_register_reporters(struct rvu_devlink *rvu_dl) INIT_WORK(&rvu_reporters->ras_work, rvu_nix_ras_work); return 0; -err: - rvu_nix_health_reporters_destroy(rvu_dl); - return -ENOMEM; } static int rvu_nix_health_reporters_create(struct rvu_devlink *rvu_dl) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index 4227ebb4a758..58744313f0eb 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -4143,90 +4143,18 @@ static void nix_find_link_frs(struct rvu *rvu, req->minlen = minlen; } -static int -nix_config_link_credits(struct rvu *rvu, int blkaddr, int link, - u16 pcifunc, u64 tx_credits) -{ - struct rvu_hwinfo *hw = rvu->hw; - int pf = rvu_get_pf(pcifunc); - u8 cgx_id = 0, lmac_id = 0; - unsigned long poll_tmo; - bool restore_tx_en = 0; - struct nix_hw *nix_hw; - u64 cfg, sw_xoff = 0; - u32 schq = 0; - u32 credits; - int rc; - - nix_hw = get_nix_hw(rvu->hw, blkaddr); - if (!nix_hw) - return NIX_AF_ERR_INVALID_NIXBLK; - - if (tx_credits == nix_hw->tx_credits[link]) - return 0; - - /* Enable cgx tx if disabled for credits to be back */ - if (is_pf_cgxmapped(rvu, pf)) { - rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id); - restore_tx_en = !rvu_cgx_config_tx(rvu_cgx_pdata(cgx_id, rvu), - lmac_id, true); - } - - mutex_lock(&rvu->rsrc_lock); - /* Disable new traffic to link */ - if (hw->cap.nix_shaping) { - schq = nix_get_tx_link(rvu, pcifunc); - sw_xoff = rvu_read64(rvu, blkaddr, NIX_AF_TL1X_SW_XOFF(schq)); - rvu_write64(rvu, blkaddr, - NIX_AF_TL1X_SW_XOFF(schq), BIT_ULL(0)); - } - - rc = NIX_AF_ERR_LINK_CREDITS; - poll_tmo = jiffies + usecs_to_jiffies(200000); - /* Wait for credits to return */ - do { - if (time_after(jiffies, poll_tmo)) - goto exit; - usleep_range(100, 200); - - cfg = rvu_read64(rvu, blkaddr, - NIX_AF_TX_LINKX_NORM_CREDIT(link)); - credits = (cfg >> 12) & 0xFFFFFULL; - } while (credits != nix_hw->tx_credits[link]); - - cfg &= ~(0xFFFFFULL << 12); - cfg |= (tx_credits << 12); - rvu_write64(rvu, blkaddr, NIX_AF_TX_LINKX_NORM_CREDIT(link), cfg); - rc = 0; - - nix_hw->tx_credits[link] = tx_credits; - -exit: - /* Enable traffic back */ - if (hw->cap.nix_shaping && !sw_xoff) - rvu_write64(rvu, blkaddr, NIX_AF_TL1X_SW_XOFF(schq), 0); - - /* Restore state of cgx tx */ - if (restore_tx_en) - rvu_cgx_config_tx(rvu_cgx_pdata(cgx_id, rvu), lmac_id, false); - - mutex_unlock(&rvu->rsrc_lock); - return rc; -} - int rvu_mbox_handler_nix_set_hw_frs(struct rvu *rvu, struct nix_frs_cfg *req, struct msg_rsp *rsp) { struct rvu_hwinfo *hw = rvu->hw; u16 pcifunc = req->hdr.pcifunc; int pf = rvu_get_pf(pcifunc); - int blkaddr, schq, link = -1; - struct nix_txsch *txsch; - u64 cfg, lmac_fifo_len; + int blkaddr, link = -1; struct nix_hw *nix_hw; struct rvu_pfvf *pfvf; u8 cgx = 0, lmac = 0; u16 max_mtu; + u64 cfg; blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc); if (blkaddr < 0) @@ -4247,25 +4175,6 @@ int rvu_mbox_handler_nix_set_hw_frs(struct rvu *rvu, struct nix_frs_cfg *req, if (req->update_minlen && req->minlen < NIC_HW_MIN_FRS) return NIX_AF_ERR_FRS_INVALID; - /* Check if requester wants to update SMQ's */ - if (!req->update_smq) - goto rx_frscfg; - - /* Update min/maxlen in each of the SMQ attached to this PF/VF */ - txsch = &nix_hw->txsch[NIX_TXSCH_LVL_SMQ]; - mutex_lock(&rvu->rsrc_lock); - for (schq = 0; schq < txsch->schq.max; schq++) { - if (TXSCH_MAP_FUNC(txsch->pfvf_map[schq]) != pcifunc) - continue; - cfg = rvu_read64(rvu, blkaddr, NIX_AF_SMQX_CFG(schq)); - cfg = (cfg & ~(0xFFFFULL << 8)) | ((u64)req->maxlen << 8); - if (req->update_minlen) - cfg = (cfg & ~0x7FULL) | ((u64)req->minlen & 0x7F); - rvu_write64(rvu, blkaddr, NIX_AF_SMQX_CFG(schq), cfg); - } - mutex_unlock(&rvu->rsrc_lock); - -rx_frscfg: /* Check if config is for SDP link */ if (req->sdp_link) { if (!hw->sdp_links) @@ -4288,7 +4197,6 @@ rx_frscfg: if (link < 0) return NIX_AF_ERR_RX_LINK_INVALID; - linkcfg: nix_find_link_frs(rvu, req, pcifunc); @@ -4298,19 +4206,7 @@ linkcfg: cfg = (cfg & ~0xFFFFULL) | req->minlen; rvu_write64(rvu, blkaddr, NIX_AF_RX_LINKX_CFG(link), cfg); - if (req->sdp_link || pf == 0) - return 0; - - /* Update transmit credits for CGX links */ - lmac_fifo_len = rvu_cgx_get_lmac_fifolen(rvu, cgx, lmac); - if (!lmac_fifo_len) { - dev_err(rvu->dev, - "%s: Failed to get CGX/RPM%d:LMAC%d FIFO size\n", - __func__, cgx, lmac); - return 0; - } - return nix_config_link_credits(rvu, blkaddr, link, pcifunc, - (lmac_fifo_len - req->maxlen) / 16); + return 0; } int rvu_mbox_handler_nix_set_rx_cfg(struct rvu *rvu, struct nix_rx_cfg *req, @@ -4841,7 +4737,13 @@ int rvu_mbox_handler_nix_lf_stop_rx(struct rvu *rvu, struct msg_req *req, pfvf = rvu_get_pfvf(rvu, pcifunc); clear_bit(NIXLF_INITIALIZED, &pfvf->flags); - return rvu_cgx_start_stop_io(rvu, pcifunc, false); + err = rvu_cgx_start_stop_io(rvu, pcifunc, false); + if (err) + return err; + + rvu_cgx_tx_enable(rvu, pcifunc, true); + + return 0; } #define RX_SA_BASE GENMASK_ULL(52, 7) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index f65805860c8d..0bcf3e559280 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -671,6 +671,7 @@ void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc, int blkaddr, ucast_idx, index; struct nix_rx_action action = { 0 }; u64 relaxed_mask; + u8 flow_key_alg; if (!hw->cap.nix_rx_multicast && is_cgx_vf(rvu, pcifunc)) return; @@ -701,6 +702,8 @@ void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc, action.op = NIX_RX_ACTIONOP_UCAST; } + flow_key_alg = action.flow_key_alg; + /* RX_ACTION set to MCAST for CGX PF's */ if (hw->cap.nix_rx_multicast && pfvf->use_mce_list && is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc))) { @@ -740,7 +743,7 @@ void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc, req.vf = pcifunc; req.index = action.index; req.match_id = action.match_id; - req.flow_key_alg = action.flow_key_alg; + req.flow_key_alg = flow_key_alg; rvu_mbox_handler_npc_install_flow(rvu, &req, &rsp); } @@ -854,6 +857,7 @@ void rvu_npc_install_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf, u8 mac_addr[ETH_ALEN] = { 0 }; struct nix_rx_action action = { 0 }; struct rvu_pfvf *pfvf; + u8 flow_key_alg; u16 vf_func; /* Only CGX PF/VF can add allmulticast entry */ @@ -888,6 +892,7 @@ void rvu_npc_install_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf, *(u64 *)&action = npc_get_mcam_action(rvu, mcam, blkaddr, ucast_idx); + flow_key_alg = action.flow_key_alg; if (action.op != NIX_RX_ACTIONOP_RSS) { *(u64 *)&action = 0; action.op = NIX_RX_ACTIONOP_UCAST; @@ -924,7 +929,7 @@ void rvu_npc_install_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf, req.vf = pcifunc | vf_func; req.index = action.index; req.match_id = action.match_id; - req.flow_key_alg = action.flow_key_alg; + req.flow_key_alg = flow_key_alg; rvu_mbox_handler_npc_install_flow(rvu, &req, &rsp); } @@ -990,11 +995,38 @@ static void npc_update_vf_flow_entry(struct rvu *rvu, struct npc_mcam *mcam, mutex_unlock(&mcam->lock); } +static void npc_update_rx_action_with_alg_idx(struct rvu *rvu, struct nix_rx_action action, + struct rvu_pfvf *pfvf, int mcam_index, int blkaddr, + int alg_idx) + +{ + struct npc_mcam *mcam = &rvu->hw->mcam; + struct rvu_hwinfo *hw = rvu->hw; + int bank, op_rss; + + if (!is_mcam_entry_enabled(rvu, mcam, blkaddr, mcam_index)) + return; + + op_rss = (!hw->cap.nix_rx_multicast || !pfvf->use_mce_list); + + bank = npc_get_bank(mcam, mcam_index); + mcam_index &= (mcam->banksize - 1); + + /* If Rx action is MCAST update only RSS algorithm index */ + if (!op_rss) { + *(u64 *)&action = rvu_read64(rvu, blkaddr, + NPC_AF_MCAMEX_BANKX_ACTION(mcam_index, bank)); + + action.flow_key_alg = alg_idx; + } + rvu_write64(rvu, blkaddr, + NPC_AF_MCAMEX_BANKX_ACTION(mcam_index, bank), *(u64 *)&action); +} + void rvu_npc_update_flowkey_alg_idx(struct rvu *rvu, u16 pcifunc, int nixlf, int group, int alg_idx, int mcam_index) { struct npc_mcam *mcam = &rvu->hw->mcam; - struct rvu_hwinfo *hw = rvu->hw; struct nix_rx_action action; int blkaddr, index, bank; struct rvu_pfvf *pfvf; @@ -1050,15 +1082,16 @@ void rvu_npc_update_flowkey_alg_idx(struct rvu *rvu, u16 pcifunc, int nixlf, /* If PF's promiscuous entry is enabled, * Set RSS action for that entry as well */ - if ((!hw->cap.nix_rx_multicast || !pfvf->use_mce_list) && - is_mcam_entry_enabled(rvu, mcam, blkaddr, index)) { - bank = npc_get_bank(mcam, index); - index &= (mcam->banksize - 1); + npc_update_rx_action_with_alg_idx(rvu, action, pfvf, index, blkaddr, + alg_idx); - rvu_write64(rvu, blkaddr, - NPC_AF_MCAMEX_BANKX_ACTION(index, bank), - *(u64 *)&action); - } + index = npc_get_nixlf_mcam_index(mcam, pcifunc, + nixlf, NIXLF_ALLMULTI_ENTRY); + /* If PF's allmulti entry is enabled, + * Set RSS action for that entry as well + */ + npc_update_rx_action_with_alg_idx(rvu, action, pfvf, index, blkaddr, + alg_idx); } void npc_enadis_default_mce_entry(struct rvu *rvu, u16 pcifunc, diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c index bfddbff7bcdf..28fb643d2917 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c @@ -399,9 +399,10 @@ static int otx2_dcbnl_ieee_getpfc(struct net_device *dev, struct ieee_pfc *pfc) static int otx2_dcbnl_ieee_setpfc(struct net_device *dev, struct ieee_pfc *pfc) { struct otx2_nic *pfvf = netdev_priv(dev); + u8 old_pfc_en; int err; - /* Save PFC configuration to interface */ + old_pfc_en = pfvf->pfc_en; pfvf->pfc_en = pfc->pfc_en; if (pfvf->hw.tx_queues >= NIX_PF_PFC_PRIO_MAX) @@ -411,13 +412,17 @@ static int otx2_dcbnl_ieee_setpfc(struct net_device *dev, struct ieee_pfc *pfc) * supported by the tx queue configuration */ err = otx2_check_pfc_config(pfvf); - if (err) + if (err) { + pfvf->pfc_en = old_pfc_en; return err; + } process_pfc: err = otx2_config_priority_flow_ctrl(pfvf); - if (err) + if (err) { + pfvf->pfc_en = old_pfc_en; return err; + } /* Request Per channel Bpids */ if (pfc->pfc_en) @@ -425,6 +430,12 @@ process_pfc: err = otx2_pfc_txschq_update(pfvf); if (err) { + if (pfc->pfc_en) + otx2_nix_config_bp(pfvf, false); + + otx2_pfc_txschq_stop(pfvf); + pfvf->pfc_en = old_pfc_en; + otx2_config_priority_flow_ctrl(pfvf); dev_err(pfvf->dev, "%s failed to update TX schedulers\n", __func__); return err; } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index 0c17ebdda148..a57455aebff6 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -1650,6 +1650,21 @@ static void otx2_free_hw_resources(struct otx2_nic *pf) mutex_unlock(&mbox->lock); } +static bool otx2_promisc_use_mce_list(struct otx2_nic *pfvf) +{ + int vf; + + /* The AF driver will determine whether to allow the VF netdev or not */ + if (is_otx2_vf(pfvf->pcifunc)) + return true; + + /* check if there are any trusted VFs associated with the PF netdev */ + for (vf = 0; vf < pci_num_vf(pfvf->pdev); vf++) + if (pfvf->vf_configs[vf].trusted) + return true; + return false; +} + static void otx2_do_set_rx_mode(struct otx2_nic *pf) { struct net_device *netdev = pf->netdev; @@ -1682,7 +1697,8 @@ static void otx2_do_set_rx_mode(struct otx2_nic *pf) if (netdev->flags & (IFF_ALLMULTI | IFF_MULTICAST)) req->mode |= NIX_RX_MODE_ALLMULTI; - req->mode |= NIX_RX_MODE_USE_MCE; + if (otx2_promisc_use_mce_list(pf)) + req->mode |= NIX_RX_MODE_USE_MCE; otx2_sync_mbox_msg(&pf->mbox); mutex_unlock(&pf->mbox.lock); @@ -2691,11 +2707,14 @@ static int otx2_ndo_set_vf_trust(struct net_device *netdev, int vf, pf->vf_configs[vf].trusted = enable; rc = otx2_set_vf_permissions(pf, vf, OTX2_TRUSTED_VF); - if (rc) + if (rc) { pf->vf_configs[vf].trusted = !enable; - else + } else { netdev_info(pf->netdev, "VF %d is %strusted\n", vf, enable ? "" : "not "); + otx2_set_rx_mode(netdev); + } + return rc; } diff --git a/drivers/net/ethernet/mediatek/mtk_wed_wo.c b/drivers/net/ethernet/mediatek/mtk_wed_wo.c index 3bd51a3d6650..ae44ad5f8ce8 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed_wo.c +++ b/drivers/net/ethernet/mediatek/mtk_wed_wo.c @@ -291,6 +291,9 @@ mtk_wed_wo_queue_tx_clean(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q) for (i = 0; i < q->n_desc; i++) { struct mtk_wed_wo_queue_entry *entry = &q->entry[i]; + if (!entry->buf) + continue; + dma_unmap_single(wo->hw->dev, entry->addr, entry->len, DMA_TO_DEVICE); skb_free_frag(entry->buf); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index f8f0a712c943..a7b1f9686c09 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -156,15 +156,18 @@ static u8 alloc_token(struct mlx5_cmd *cmd) return token; } -static int cmd_alloc_index(struct mlx5_cmd *cmd) +static int cmd_alloc_index(struct mlx5_cmd *cmd, struct mlx5_cmd_work_ent *ent) { unsigned long flags; int ret; spin_lock_irqsave(&cmd->alloc_lock, flags); ret = find_first_bit(&cmd->vars.bitmask, cmd->vars.max_reg_cmds); - if (ret < cmd->vars.max_reg_cmds) + if (ret < cmd->vars.max_reg_cmds) { clear_bit(ret, &cmd->vars.bitmask); + ent->idx = ret; + cmd->ent_arr[ent->idx] = ent; + } spin_unlock_irqrestore(&cmd->alloc_lock, flags); return ret < cmd->vars.max_reg_cmds ? ret : -ENOMEM; @@ -979,7 +982,7 @@ static void cmd_work_handler(struct work_struct *work) sem = ent->page_queue ? &cmd->vars.pages_sem : &cmd->vars.sem; down(sem); if (!ent->page_queue) { - alloc_ret = cmd_alloc_index(cmd); + alloc_ret = cmd_alloc_index(cmd, ent); if (alloc_ret < 0) { mlx5_core_err_rl(dev, "failed to allocate command entry\n"); if (ent->callback) { @@ -994,15 +997,14 @@ static void cmd_work_handler(struct work_struct *work) up(sem); return; } - ent->idx = alloc_ret; } else { ent->idx = cmd->vars.max_reg_cmds; spin_lock_irqsave(&cmd->alloc_lock, flags); clear_bit(ent->idx, &cmd->vars.bitmask); + cmd->ent_arr[ent->idx] = ent; spin_unlock_irqrestore(&cmd->alloc_lock, flags); } - cmd->ent_arr[ent->idx] = ent; lay = get_inst(cmd, ent->idx); ent->lay = lay; memset(lay, 0, sizeof(*lay)); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c index 76d27d2ee40c..080e7eab52c7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -718,7 +718,7 @@ static void mlx5_fw_tracer_handle_traces(struct work_struct *work) while (block_timestamp > tracer->last_timestamp) { /* Check block override if it's not the first block */ - if (!tracer->last_timestamp) { + if (tracer->last_timestamp) { u64 *ts_event; /* To avoid block override be the HW in case of buffer * wraparound, the time stamp of the previous block diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index b2a5da9739d2..729a11b5fb25 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -826,6 +826,7 @@ enum { MLX5E_STATE_DESTROYING, MLX5E_STATE_XDP_TX_ENABLED, MLX5E_STATE_XDP_ACTIVE, + MLX5E_STATE_CHANNELS_ACTIVE, }; struct mlx5e_modify_sq_param { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c b/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c index be83ad9db82a..e1283531e0b8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c @@ -154,6 +154,7 @@ static int fs_udp_create_groups(struct mlx5e_flow_table *ft, enum fs_udp_type ty in = kvzalloc(inlen, GFP_KERNEL); if (!in || !ft->g) { kfree(ft->g); + ft->g = NULL; kvfree(in); return -ENOMEM; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c index f63402c48028..1b418095b79a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c @@ -197,7 +197,7 @@ parse_mirred_encap(struct mlx5e_tc_act_parse_state *parse_state, } esw_attr->dests[esw_attr->out_count].flags |= MLX5_ESW_DEST_ENCAP; esw_attr->out_count++; - /* attr->dests[].rep is resolved when we handle encap */ + /* attr->dests[].vport is resolved when we handle encap */ return 0; } @@ -270,7 +270,8 @@ parse_mirred(struct mlx5e_tc_act_parse_state *parse_state, out_priv = netdev_priv(out_dev); rpriv = out_priv->ppriv; - esw_attr->dests[esw_attr->out_count].rep = rpriv->rep; + esw_attr->dests[esw_attr->out_count].vport_valid = true; + esw_attr->dests[esw_attr->out_count].vport = rpriv->rep->vport; esw_attr->dests[esw_attr->out_count].mdev = out_priv->mdev; esw_attr->out_count++; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c index 4e923a2874ae..86bf007fd05b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c @@ -83,6 +83,9 @@ mlx5e_tc_post_act_offload(struct mlx5e_post_act *post_act, struct mlx5_flow_spec *spec; int err; + if (IS_ERR(post_act)) + return PTR_ERR(post_act); + spec = kvzalloc(sizeof(*spec), GFP_KERNEL); if (!spec) return -ENOMEM; @@ -111,6 +114,9 @@ mlx5e_tc_post_act_add(struct mlx5e_post_act *post_act, struct mlx5_flow_attr *po struct mlx5e_post_act_handle *handle; int err; + if (IS_ERR(post_act)) + return ERR_CAST(post_act); + handle = kzalloc(sizeof(*handle), GFP_KERNEL); if (!handle) return ERR_PTR(-ENOMEM); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c index 668da5c70e63..8dfb57f712b0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -300,6 +300,10 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv, if (err) goto destroy_neigh_entry; + e->encap_size = ipv4_encap_size; + e->encap_header = encap_header; + encap_header = NULL; + if (!(nud_state & NUD_VALID)) { neigh_event_send(attr.n, NULL); /* the encap entry will be made valid on neigh update event @@ -310,8 +314,8 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv, memset(&reformat_params, 0, sizeof(reformat_params)); reformat_params.type = e->reformat_type; - reformat_params.size = ipv4_encap_size; - reformat_params.data = encap_header; + reformat_params.size = e->encap_size; + reformat_params.data = e->encap_header; e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, &reformat_params, MLX5_FLOW_NAMESPACE_FDB); if (IS_ERR(e->pkt_reformat)) { @@ -319,8 +323,6 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv, goto destroy_neigh_entry; } - e->encap_size = ipv4_encap_size; - e->encap_header = encap_header; e->flags |= MLX5_ENCAP_ENTRY_VALID; mlx5e_rep_queue_neigh_stats_work(netdev_priv(attr.out_dev)); mlx5e_route_lookup_ipv4_put(&attr); @@ -403,18 +405,23 @@ int mlx5e_tc_tun_update_header_ipv4(struct mlx5e_priv *priv, if (err) goto free_encap; + e->encap_size = ipv4_encap_size; + kfree(e->encap_header); + e->encap_header = encap_header; + encap_header = NULL; + if (!(nud_state & NUD_VALID)) { neigh_event_send(attr.n, NULL); /* the encap entry will be made valid on neigh update event * and not used before that. */ - goto free_encap; + goto release_neigh; } memset(&reformat_params, 0, sizeof(reformat_params)); reformat_params.type = e->reformat_type; - reformat_params.size = ipv4_encap_size; - reformat_params.data = encap_header; + reformat_params.size = e->encap_size; + reformat_params.data = e->encap_header; e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, &reformat_params, MLX5_FLOW_NAMESPACE_FDB); if (IS_ERR(e->pkt_reformat)) { @@ -422,10 +429,6 @@ int mlx5e_tc_tun_update_header_ipv4(struct mlx5e_priv *priv, goto free_encap; } - e->encap_size = ipv4_encap_size; - kfree(e->encap_header); - e->encap_header = encap_header; - e->flags |= MLX5_ENCAP_ENTRY_VALID; mlx5e_rep_queue_neigh_stats_work(netdev_priv(attr.out_dev)); mlx5e_route_lookup_ipv4_put(&attr); @@ -567,6 +570,10 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, if (err) goto destroy_neigh_entry; + e->encap_size = ipv6_encap_size; + e->encap_header = encap_header; + encap_header = NULL; + if (!(nud_state & NUD_VALID)) { neigh_event_send(attr.n, NULL); /* the encap entry will be made valid on neigh update event @@ -577,8 +584,8 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, memset(&reformat_params, 0, sizeof(reformat_params)); reformat_params.type = e->reformat_type; - reformat_params.size = ipv6_encap_size; - reformat_params.data = encap_header; + reformat_params.size = e->encap_size; + reformat_params.data = e->encap_header; e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, &reformat_params, MLX5_FLOW_NAMESPACE_FDB); if (IS_ERR(e->pkt_reformat)) { @@ -586,8 +593,6 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, goto destroy_neigh_entry; } - e->encap_size = ipv6_encap_size; - e->encap_header = encap_header; e->flags |= MLX5_ENCAP_ENTRY_VALID; mlx5e_rep_queue_neigh_stats_work(netdev_priv(attr.out_dev)); mlx5e_route_lookup_ipv6_put(&attr); @@ -669,18 +674,23 @@ int mlx5e_tc_tun_update_header_ipv6(struct mlx5e_priv *priv, if (err) goto free_encap; + e->encap_size = ipv6_encap_size; + kfree(e->encap_header); + e->encap_header = encap_header; + encap_header = NULL; + if (!(nud_state & NUD_VALID)) { neigh_event_send(attr.n, NULL); /* the encap entry will be made valid on neigh update event * and not used before that. */ - goto free_encap; + goto release_neigh; } memset(&reformat_params, 0, sizeof(reformat_params)); reformat_params.type = e->reformat_type; - reformat_params.size = ipv6_encap_size; - reformat_params.data = encap_header; + reformat_params.size = e->encap_size; + reformat_params.data = e->encap_header; e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, &reformat_params, MLX5_FLOW_NAMESPACE_FDB); if (IS_ERR(e->pkt_reformat)) { @@ -688,10 +698,6 @@ int mlx5e_tc_tun_update_header_ipv6(struct mlx5e_priv *priv, goto free_encap; } - e->encap_size = ipv6_encap_size; - kfree(e->encap_header); - e->encap_header = encap_header; - e->flags |= MLX5_ENCAP_ENTRY_VALID; mlx5e_rep_queue_neigh_stats_work(netdev_priv(attr.out_dev)); mlx5e_route_lookup_ipv6_put(&attr); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c index b10e40e1a9c1..f1d1e1542e81 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c @@ -1064,7 +1064,8 @@ int mlx5e_tc_tun_encap_dests_set(struct mlx5e_priv *priv, out_priv = netdev_priv(encap_dev); rpriv = out_priv->ppriv; - esw_attr->dests[out_index].rep = rpriv->rep; + esw_attr->dests[out_index].vport_valid = true; + esw_attr->dests[out_index].vport = rpriv->rep->vport; esw_attr->dests[out_index].mdev = out_priv->mdev; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index 7decc81ed33a..13c7ed1bb37e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -493,6 +493,7 @@ mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd, dma_addr_t dma_addr = xdptxd->dma_addr; u32 dma_len = xdptxd->len; u16 ds_cnt, inline_hdr_sz; + unsigned int frags_size; u8 num_wqebbs = 1; int num_frags = 0; bool inline_ok; @@ -503,8 +504,9 @@ mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd, inline_ok = sq->min_inline_mode == MLX5_INLINE_MODE_NONE || dma_len >= MLX5E_XDP_MIN_INLINE; + frags_size = xdptxd->has_frags ? xdptxdf->sinfo->xdp_frags_size : 0; - if (unlikely(!inline_ok || sq->hw_mtu < dma_len)) { + if (unlikely(!inline_ok || sq->hw_mtu < dma_len + frags_size)) { stats->err++; return false; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c index 655496598c68..161c5190c236 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c @@ -121,7 +121,14 @@ static bool mlx5e_ipsec_update_esn_state(struct mlx5e_ipsec_sa_entry *sa_entry) if (x->xso.type == XFRM_DEV_OFFLOAD_CRYPTO) esn_msb = xfrm_replay_seqhi(x, htonl(seq_bottom)); - sa_entry->esn_state.esn = esn; + if (sa_entry->esn_state.esn_msb) + sa_entry->esn_state.esn = esn; + else + /* According to RFC4303, section "3.3.3. Sequence Number Generation", + * the first packet sent using a given SA will contain a sequence + * number of 1. + */ + sa_entry->esn_state.esn = max_t(u32, esn, 1); sa_entry->esn_state.esn_msb = esn_msb; if (unlikely(overlap && seq_bottom < MLX5E_IPSEC_ESN_SCOPE_MID)) { @@ -335,6 +342,27 @@ void mlx5e_ipsec_build_accel_xfrm_attrs(struct mlx5e_ipsec_sa_entry *sa_entry, attrs->replay_esn.esn = sa_entry->esn_state.esn; attrs->replay_esn.esn_msb = sa_entry->esn_state.esn_msb; attrs->replay_esn.overlap = sa_entry->esn_state.overlap; + switch (x->replay_esn->replay_window) { + case 32: + attrs->replay_esn.replay_window = + MLX5_IPSEC_ASO_REPLAY_WIN_32BIT; + break; + case 64: + attrs->replay_esn.replay_window = + MLX5_IPSEC_ASO_REPLAY_WIN_64BIT; + break; + case 128: + attrs->replay_esn.replay_window = + MLX5_IPSEC_ASO_REPLAY_WIN_128BIT; + break; + case 256: + attrs->replay_esn.replay_window = + MLX5_IPSEC_ASO_REPLAY_WIN_256BIT; + break; + default: + WARN_ON(true); + return; + } } attrs->dir = x->xso.dir; @@ -907,9 +935,11 @@ void mlx5e_ipsec_cleanup(struct mlx5e_priv *priv) return; mlx5e_accel_ipsec_fs_cleanup(ipsec); - if (mlx5_ipsec_device_caps(priv->mdev) & MLX5_IPSEC_CAP_TUNNEL) + if (ipsec->netevent_nb.notifier_call) { unregister_netevent_notifier(&ipsec->netevent_nb); - if (mlx5_ipsec_device_caps(priv->mdev) & MLX5_IPSEC_CAP_PACKET_OFFLOAD) + ipsec->netevent_nb.notifier_call = NULL; + } + if (ipsec->aso) mlx5e_ipsec_aso_cleanup(ipsec); destroy_workqueue(ipsec->wq); kfree(ipsec); @@ -1018,6 +1048,12 @@ static int mlx5e_xfrm_validate_policy(struct mlx5_core_dev *mdev, } } + if (x->xdo.type == XFRM_DEV_OFFLOAD_PACKET && + !(mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_PACKET_OFFLOAD)) { + NL_SET_ERR_MSG_MOD(extack, "Packet offload is not supported"); + return -EINVAL; + } + return 0; } @@ -1113,14 +1149,6 @@ static const struct xfrmdev_ops mlx5e_ipsec_xfrmdev_ops = { .xdo_dev_state_free = mlx5e_xfrm_free_state, .xdo_dev_offload_ok = mlx5e_ipsec_offload_ok, .xdo_dev_state_advance_esn = mlx5e_xfrm_advance_esn_state, -}; - -static const struct xfrmdev_ops mlx5e_ipsec_packet_xfrmdev_ops = { - .xdo_dev_state_add = mlx5e_xfrm_add_state, - .xdo_dev_state_delete = mlx5e_xfrm_del_state, - .xdo_dev_state_free = mlx5e_xfrm_free_state, - .xdo_dev_offload_ok = mlx5e_ipsec_offload_ok, - .xdo_dev_state_advance_esn = mlx5e_xfrm_advance_esn_state, .xdo_dev_state_update_curlft = mlx5e_xfrm_update_curlft, .xdo_dev_policy_add = mlx5e_xfrm_add_policy, @@ -1138,11 +1166,7 @@ void mlx5e_ipsec_build_netdev(struct mlx5e_priv *priv) mlx5_core_info(mdev, "mlx5e: IPSec ESP acceleration enabled\n"); - if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_PACKET_OFFLOAD) - netdev->xfrmdev_ops = &mlx5e_ipsec_packet_xfrmdev_ops; - else - netdev->xfrmdev_ops = &mlx5e_ipsec_xfrmdev_ops; - + netdev->xfrmdev_ops = &mlx5e_ipsec_xfrmdev_ops; netdev->features |= NETIF_F_HW_ESP; netdev->hw_enc_features |= NETIF_F_HW_ESP; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h index 8f4a37bceaf4..adaea3493193 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h @@ -189,11 +189,19 @@ struct mlx5e_ipsec_ft { u32 refcnt; }; +struct mlx5e_ipsec_drop { + struct mlx5_flow_handle *rule; + struct mlx5_fc *fc; +}; + struct mlx5e_ipsec_rule { struct mlx5_flow_handle *rule; struct mlx5_modify_hdr *modify_hdr; struct mlx5_pkt_reformat *pkt_reformat; struct mlx5_fc *fc; + struct mlx5e_ipsec_drop replay; + struct mlx5e_ipsec_drop auth; + struct mlx5e_ipsec_drop trailer; }; struct mlx5e_ipsec_miss { @@ -201,19 +209,6 @@ struct mlx5e_ipsec_miss { struct mlx5_flow_handle *rule; }; -struct mlx5e_ipsec_rx { - struct mlx5e_ipsec_ft ft; - struct mlx5e_ipsec_miss pol; - struct mlx5e_ipsec_miss sa; - struct mlx5e_ipsec_rule status; - struct mlx5e_ipsec_miss status_drop; - struct mlx5_fc *status_drop_cnt; - struct mlx5e_ipsec_fc *fc; - struct mlx5_fs_chains *chains; - u8 allow_tunnel_mode : 1; - struct xarray ipsec_obj_id_map; -}; - struct mlx5e_ipsec_tx_create_attr { int prio; int pol_level; @@ -248,6 +243,7 @@ struct mlx5e_ipsec { struct mlx5_ipsec_fs *roce; u8 is_uplink_rep: 1; struct mlx5e_ipsec_mpv_work mpv_work; + struct xarray ipsec_obj_id_map; }; struct mlx5e_ipsec_esn_state { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c index f41c976dc33f..41a2543a52cd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c @@ -32,6 +32,22 @@ struct mlx5e_ipsec_tx { u8 allow_tunnel_mode : 1; }; +struct mlx5e_ipsec_status_checks { + struct mlx5_flow_group *drop_all_group; + struct mlx5e_ipsec_drop all; +}; + +struct mlx5e_ipsec_rx { + struct mlx5e_ipsec_ft ft; + struct mlx5e_ipsec_miss pol; + struct mlx5e_ipsec_miss sa; + struct mlx5e_ipsec_rule status; + struct mlx5e_ipsec_status_checks status_drops; + struct mlx5e_ipsec_fc *fc; + struct mlx5_fs_chains *chains; + u8 allow_tunnel_mode : 1; +}; + /* IPsec RX flow steering */ static enum mlx5_traffic_types family2tt(u32 family) { @@ -128,14 +144,37 @@ static struct mlx5_flow_table *ipsec_ft_create(struct mlx5_flow_namespace *ns, return mlx5_create_auto_grouped_flow_table(ns, &ft_attr); } -static int ipsec_status_rule(struct mlx5_core_dev *mdev, - struct mlx5e_ipsec_rx *rx, - struct mlx5_flow_destination *dest) +static void ipsec_rx_status_drop_destroy(struct mlx5e_ipsec *ipsec, + struct mlx5e_ipsec_rx *rx) +{ + mlx5_del_flow_rules(rx->status_drops.all.rule); + mlx5_fc_destroy(ipsec->mdev, rx->status_drops.all.fc); + mlx5_destroy_flow_group(rx->status_drops.drop_all_group); +} + +static void ipsec_rx_status_pass_destroy(struct mlx5e_ipsec *ipsec, + struct mlx5e_ipsec_rx *rx) { - u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {}; + mlx5_del_flow_rules(rx->status.rule); + + if (rx != ipsec->rx_esw) + return; + +#ifdef CONFIG_MLX5_ESWITCH + mlx5_chains_put_table(esw_chains(ipsec->mdev->priv.eswitch), 0, 1, 0); +#endif +} + +static int rx_add_rule_drop_auth_trailer(struct mlx5e_ipsec_sa_entry *sa_entry, + struct mlx5e_ipsec_rx *rx) +{ + struct mlx5e_ipsec *ipsec = sa_entry->ipsec; + struct mlx5_flow_table *ft = rx->ft.status; + struct mlx5_core_dev *mdev = ipsec->mdev; + struct mlx5_flow_destination dest = {}; struct mlx5_flow_act flow_act = {}; - struct mlx5_modify_hdr *modify_hdr; - struct mlx5_flow_handle *fte; + struct mlx5_flow_handle *rule; + struct mlx5_fc *flow_counter; struct mlx5_flow_spec *spec; int err; @@ -143,48 +182,273 @@ static int ipsec_status_rule(struct mlx5_core_dev *mdev, if (!spec) return -ENOMEM; - /* Action to copy 7 bit ipsec_syndrome to regB[24:30] */ - MLX5_SET(copy_action_in, action, action_type, MLX5_ACTION_TYPE_COPY); - MLX5_SET(copy_action_in, action, src_field, MLX5_ACTION_IN_FIELD_IPSEC_SYNDROME); - MLX5_SET(copy_action_in, action, src_offset, 0); - MLX5_SET(copy_action_in, action, length, 7); - MLX5_SET(copy_action_in, action, dst_field, MLX5_ACTION_IN_FIELD_METADATA_REG_B); - MLX5_SET(copy_action_in, action, dst_offset, 24); + flow_counter = mlx5_fc_create(mdev, true); + if (IS_ERR(flow_counter)) { + err = PTR_ERR(flow_counter); + mlx5_core_err(mdev, + "Failed to add ipsec rx status drop rule counter, err=%d\n", err); + goto err_cnt; + } + sa_entry->ipsec_rule.auth.fc = flow_counter; - modify_hdr = mlx5_modify_header_alloc(mdev, MLX5_FLOW_NAMESPACE_KERNEL, - 1, action); + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT; + flow_act.flags = FLOW_ACT_NO_APPEND; + dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; + dest.counter_id = mlx5_fc_id(flow_counter); + if (rx == ipsec->rx_esw) + spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK; - if (IS_ERR(modify_hdr)) { - err = PTR_ERR(modify_hdr); + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.ipsec_syndrome); + MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.ipsec_syndrome, 1); + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.metadata_reg_c_2); + MLX5_SET(fte_match_param, spec->match_value, + misc_parameters_2.metadata_reg_c_2, + sa_entry->ipsec_obj_id | BIT(31)); + spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2; + rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1); + if (IS_ERR(rule)) { + err = PTR_ERR(rule); mlx5_core_err(mdev, - "fail to alloc ipsec copy modify_header_id err=%d\n", err); - goto out_spec; + "Failed to add ipsec rx status drop rule, err=%d\n", err); + goto err_rule; } + sa_entry->ipsec_rule.auth.rule = rule; - /* create fte */ - flow_act.action = MLX5_FLOW_CONTEXT_ACTION_MOD_HDR | - MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | + flow_counter = mlx5_fc_create(mdev, true); + if (IS_ERR(flow_counter)) { + err = PTR_ERR(flow_counter); + mlx5_core_err(mdev, + "Failed to add ipsec rx status drop rule counter, err=%d\n", err); + goto err_cnt_2; + } + sa_entry->ipsec_rule.trailer.fc = flow_counter; + + dest.counter_id = mlx5_fc_id(flow_counter); + MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.ipsec_syndrome, 2); + rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1); + if (IS_ERR(rule)) { + err = PTR_ERR(rule); + mlx5_core_err(mdev, + "Failed to add ipsec rx status drop rule, err=%d\n", err); + goto err_rule_2; + } + sa_entry->ipsec_rule.trailer.rule = rule; + + kvfree(spec); + return 0; + +err_rule_2: + mlx5_fc_destroy(mdev, sa_entry->ipsec_rule.trailer.fc); +err_cnt_2: + mlx5_del_flow_rules(sa_entry->ipsec_rule.auth.rule); +err_rule: + mlx5_fc_destroy(mdev, sa_entry->ipsec_rule.auth.fc); +err_cnt: + kvfree(spec); + return err; +} + +static int rx_add_rule_drop_replay(struct mlx5e_ipsec_sa_entry *sa_entry, struct mlx5e_ipsec_rx *rx) +{ + struct mlx5e_ipsec *ipsec = sa_entry->ipsec; + struct mlx5_flow_table *ft = rx->ft.status; + struct mlx5_core_dev *mdev = ipsec->mdev; + struct mlx5_flow_destination dest = {}; + struct mlx5_flow_act flow_act = {}; + struct mlx5_flow_handle *rule; + struct mlx5_fc *flow_counter; + struct mlx5_flow_spec *spec; + int err; + + spec = kvzalloc(sizeof(*spec), GFP_KERNEL); + if (!spec) + return -ENOMEM; + + flow_counter = mlx5_fc_create(mdev, true); + if (IS_ERR(flow_counter)) { + err = PTR_ERR(flow_counter); + mlx5_core_err(mdev, + "Failed to add ipsec rx status drop rule counter, err=%d\n", err); + goto err_cnt; + } + + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT; + flow_act.flags = FLOW_ACT_NO_APPEND; + dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; + dest.counter_id = mlx5_fc_id(flow_counter); + if (rx == ipsec->rx_esw) + spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK; + + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.metadata_reg_c_4); + MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.metadata_reg_c_4, 1); + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.metadata_reg_c_2); + MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.metadata_reg_c_2, + sa_entry->ipsec_obj_id | BIT(31)); + spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2; + rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1); + if (IS_ERR(rule)) { + err = PTR_ERR(rule); + mlx5_core_err(mdev, + "Failed to add ipsec rx status drop rule, err=%d\n", err); + goto err_rule; + } + + sa_entry->ipsec_rule.replay.rule = rule; + sa_entry->ipsec_rule.replay.fc = flow_counter; + + kvfree(spec); + return 0; + +err_rule: + mlx5_fc_destroy(mdev, flow_counter); +err_cnt: + kvfree(spec); + return err; +} + +static int ipsec_rx_status_drop_all_create(struct mlx5e_ipsec *ipsec, + struct mlx5e_ipsec_rx *rx) +{ + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + struct mlx5_flow_table *ft = rx->ft.status; + struct mlx5_core_dev *mdev = ipsec->mdev; + struct mlx5_flow_destination dest = {}; + struct mlx5_flow_act flow_act = {}; + struct mlx5_flow_handle *rule; + struct mlx5_fc *flow_counter; + struct mlx5_flow_spec *spec; + struct mlx5_flow_group *g; + u32 *flow_group_in; + int err = 0; + + flow_group_in = kvzalloc(inlen, GFP_KERNEL); + spec = kvzalloc(sizeof(*spec), GFP_KERNEL); + if (!flow_group_in || !spec) { + err = -ENOMEM; + goto err_out; + } + + MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ft->max_fte - 1); + MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, ft->max_fte - 1); + g = mlx5_create_flow_group(ft, flow_group_in); + if (IS_ERR(g)) { + err = PTR_ERR(g); + mlx5_core_err(mdev, + "Failed to add ipsec rx status drop flow group, err=%d\n", err); + goto err_out; + } + + flow_counter = mlx5_fc_create(mdev, false); + if (IS_ERR(flow_counter)) { + err = PTR_ERR(flow_counter); + mlx5_core_err(mdev, + "Failed to add ipsec rx status drop rule counter, err=%d\n", err); + goto err_cnt; + } + + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT; + dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; + dest.counter_id = mlx5_fc_id(flow_counter); + if (rx == ipsec->rx_esw) + spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK; + rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1); + if (IS_ERR(rule)) { + err = PTR_ERR(rule); + mlx5_core_err(mdev, + "Failed to add ipsec rx status drop rule, err=%d\n", err); + goto err_rule; + } + + rx->status_drops.drop_all_group = g; + rx->status_drops.all.rule = rule; + rx->status_drops.all.fc = flow_counter; + + kvfree(flow_group_in); + kvfree(spec); + return 0; + +err_rule: + mlx5_fc_destroy(mdev, flow_counter); +err_cnt: + mlx5_destroy_flow_group(g); +err_out: + kvfree(flow_group_in); + kvfree(spec); + return err; +} + +static int ipsec_rx_status_pass_create(struct mlx5e_ipsec *ipsec, + struct mlx5e_ipsec_rx *rx, + struct mlx5_flow_destination *dest) +{ + struct mlx5_flow_act flow_act = {}; + struct mlx5_flow_handle *rule; + struct mlx5_flow_spec *spec; + int err; + + spec = kvzalloc(sizeof(*spec), GFP_KERNEL); + if (!spec) + return -ENOMEM; + + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, + misc_parameters_2.ipsec_syndrome); + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, + misc_parameters_2.metadata_reg_c_4); + MLX5_SET(fte_match_param, spec->match_value, + misc_parameters_2.ipsec_syndrome, 0); + MLX5_SET(fte_match_param, spec->match_value, + misc_parameters_2.metadata_reg_c_4, 0); + if (rx == ipsec->rx_esw) + spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK; + spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2; + flow_act.flags = FLOW_ACT_NO_APPEND; + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_COUNT; - flow_act.modify_hdr = modify_hdr; - fte = mlx5_add_flow_rules(rx->ft.status, spec, &flow_act, dest, 2); - if (IS_ERR(fte)) { - err = PTR_ERR(fte); - mlx5_core_err(mdev, "fail to add ipsec rx err copy rule err=%d\n", err); - goto out; + rule = mlx5_add_flow_rules(rx->ft.status, spec, &flow_act, dest, 2); + if (IS_ERR(rule)) { + err = PTR_ERR(rule); + mlx5_core_warn(ipsec->mdev, + "Failed to add ipsec rx status pass rule, err=%d\n", err); + goto err_rule; } + rx->status.rule = rule; kvfree(spec); - rx->status.rule = fte; - rx->status.modify_hdr = modify_hdr; return 0; -out: - mlx5_modify_header_dealloc(mdev, modify_hdr); -out_spec: +err_rule: kvfree(spec); return err; } +static void mlx5_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec, + struct mlx5e_ipsec_rx *rx) +{ + ipsec_rx_status_pass_destroy(ipsec, rx); + ipsec_rx_status_drop_destroy(ipsec, rx); +} + +static int mlx5_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec, + struct mlx5e_ipsec_rx *rx, + struct mlx5_flow_destination *dest) +{ + int err; + + err = ipsec_rx_status_drop_all_create(ipsec, rx); + if (err) + return err; + + err = ipsec_rx_status_pass_create(ipsec, rx, dest); + if (err) + goto err_pass_create; + + return 0; + +err_pass_create: + ipsec_rx_status_drop_destroy(ipsec, rx); + return err; +} + static int ipsec_miss_create(struct mlx5_core_dev *mdev, struct mlx5_flow_table *ft, struct mlx5e_ipsec_miss *miss, @@ -333,12 +597,7 @@ static void rx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec, mlx5_destroy_flow_table(rx->ft.sa); if (rx->allow_tunnel_mode) mlx5_eswitch_unblock_encap(mdev); - if (rx == ipsec->rx_esw) { - mlx5_esw_ipsec_rx_status_destroy(ipsec, rx); - } else { - mlx5_del_flow_rules(rx->status.rule); - mlx5_modify_header_dealloc(mdev, rx->status.modify_hdr); - } + mlx5_ipsec_rx_status_destroy(ipsec, rx); mlx5_destroy_flow_table(rx->ft.status); mlx5_ipsec_fs_roce_rx_destroy(ipsec->roce, family, mdev); @@ -419,7 +678,7 @@ static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec, if (err) return err; - ft = ipsec_ft_create(attr.ns, attr.status_level, attr.prio, 1, 0); + ft = ipsec_ft_create(attr.ns, attr.status_level, attr.prio, 3, 0); if (IS_ERR(ft)) { err = PTR_ERR(ft); goto err_fs_ft_status; @@ -428,10 +687,7 @@ static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec, dest[1].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; dest[1].counter_id = mlx5_fc_id(rx->fc->cnt); - if (rx == ipsec->rx_esw) - err = mlx5_esw_ipsec_rx_status_create(ipsec, rx, dest); - else - err = ipsec_status_rule(mdev, rx, dest); + err = mlx5_ipsec_rx_status_create(ipsec, rx, dest); if (err) goto err_add; @@ -956,13 +1212,22 @@ static void setup_fte_esp(struct mlx5_flow_spec *spec) MLX5_SET(fte_match_param, spec->match_value, outer_headers.ip_protocol, IPPROTO_ESP); } -static void setup_fte_spi(struct mlx5_flow_spec *spec, u32 spi) +static void setup_fte_spi(struct mlx5_flow_spec *spec, u32 spi, bool encap) { /* SPI number */ spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS; - MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters.outer_esp_spi); - MLX5_SET(fte_match_param, spec->match_value, misc_parameters.outer_esp_spi, spi); + if (encap) { + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, + misc_parameters.inner_esp_spi); + MLX5_SET(fte_match_param, spec->match_value, + misc_parameters.inner_esp_spi, spi); + } else { + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, + misc_parameters.outer_esp_spi); + MLX5_SET(fte_match_param, spec->match_value, + misc_parameters.outer_esp_spi, spi); + } } static void setup_fte_no_frags(struct mlx5_flow_spec *spec) @@ -1052,29 +1317,48 @@ static int setup_modify_header(struct mlx5e_ipsec *ipsec, int type, u32 val, u8 struct mlx5_flow_act *flow_act) { enum mlx5_flow_namespace_type ns_type = ipsec_fs_get_ns(ipsec, type, dir); - u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {}; + u8 action[3][MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {}; struct mlx5_core_dev *mdev = ipsec->mdev; struct mlx5_modify_hdr *modify_hdr; + u8 num_of_actions = 1; - MLX5_SET(set_action_in, action, action_type, MLX5_ACTION_TYPE_SET); + MLX5_SET(set_action_in, action[0], action_type, MLX5_ACTION_TYPE_SET); switch (dir) { case XFRM_DEV_OFFLOAD_IN: - MLX5_SET(set_action_in, action, field, + MLX5_SET(set_action_in, action[0], field, MLX5_ACTION_IN_FIELD_METADATA_REG_B); + + num_of_actions++; + MLX5_SET(set_action_in, action[1], action_type, MLX5_ACTION_TYPE_SET); + MLX5_SET(set_action_in, action[1], field, MLX5_ACTION_IN_FIELD_METADATA_REG_C_2); + MLX5_SET(set_action_in, action[1], data, val); + MLX5_SET(set_action_in, action[1], offset, 0); + MLX5_SET(set_action_in, action[1], length, 32); + + if (type == XFRM_DEV_OFFLOAD_CRYPTO) { + num_of_actions++; + MLX5_SET(set_action_in, action[2], action_type, + MLX5_ACTION_TYPE_SET); + MLX5_SET(set_action_in, action[2], field, + MLX5_ACTION_IN_FIELD_METADATA_REG_C_4); + MLX5_SET(set_action_in, action[2], data, 0); + MLX5_SET(set_action_in, action[2], offset, 0); + MLX5_SET(set_action_in, action[2], length, 32); + } break; case XFRM_DEV_OFFLOAD_OUT: - MLX5_SET(set_action_in, action, field, + MLX5_SET(set_action_in, action[0], field, MLX5_ACTION_IN_FIELD_METADATA_REG_C_4); break; default: return -EINVAL; } - MLX5_SET(set_action_in, action, data, val); - MLX5_SET(set_action_in, action, offset, 0); - MLX5_SET(set_action_in, action, length, 32); + MLX5_SET(set_action_in, action[0], data, val); + MLX5_SET(set_action_in, action[0], offset, 0); + MLX5_SET(set_action_in, action[0], length, 32); - modify_hdr = mlx5_modify_header_alloc(mdev, ns_type, 1, action); + modify_hdr = mlx5_modify_header_alloc(mdev, ns_type, num_of_actions, action); if (IS_ERR(modify_hdr)) { mlx5_core_err(mdev, "Failed to allocate modify_header %ld\n", PTR_ERR(modify_hdr)); @@ -1321,8 +1605,9 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry) else setup_fte_addr6(spec, attrs->saddr.a6, attrs->daddr.a6); - setup_fte_spi(spec, attrs->spi); - setup_fte_esp(spec); + setup_fte_spi(spec, attrs->spi, attrs->encap); + if (!attrs->encap) + setup_fte_esp(spec); setup_fte_no_frags(spec); setup_fte_upper_proto_match(spec, &attrs->upspec); @@ -1372,6 +1657,15 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry) mlx5_core_err(mdev, "fail to add RX ipsec rule err=%d\n", err); goto err_add_flow; } + if (attrs->type == XFRM_DEV_OFFLOAD_PACKET) + err = rx_add_rule_drop_replay(sa_entry, rx); + if (err) + goto err_add_replay; + + err = rx_add_rule_drop_auth_trailer(sa_entry, rx); + if (err) + goto err_drop_reason; + kvfree(spec); sa_entry->ipsec_rule.rule = rule; @@ -1380,6 +1674,13 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry) sa_entry->ipsec_rule.pkt_reformat = flow_act.pkt_reformat; return 0; +err_drop_reason: + if (sa_entry->ipsec_rule.replay.rule) { + mlx5_del_flow_rules(sa_entry->ipsec_rule.replay.rule); + mlx5_fc_destroy(mdev, sa_entry->ipsec_rule.replay.fc); + } +err_add_replay: + mlx5_del_flow_rules(rule); err_add_flow: mlx5_fc_destroy(mdev, counter); err_add_cnt: @@ -1428,7 +1729,7 @@ static int tx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry) switch (attrs->type) { case XFRM_DEV_OFFLOAD_CRYPTO: - setup_fte_spi(spec, attrs->spi); + setup_fte_spi(spec, attrs->spi, false); setup_fte_esp(spec); setup_fte_reg_a(spec); break; @@ -1809,8 +2110,11 @@ static int mlx5e_ipsec_block_tc_offload(struct mlx5_core_dev *mdev) struct mlx5_eswitch *esw = mdev->priv.eswitch; int err = 0; - if (esw) - down_write(&esw->mode_lock); + if (esw) { + err = mlx5_esw_lock(esw); + if (err) + return err; + } if (mdev->num_block_ipsec) { err = -EBUSY; @@ -1821,7 +2125,7 @@ static int mlx5e_ipsec_block_tc_offload(struct mlx5_core_dev *mdev) unlock: if (esw) - up_write(&esw->mode_lock); + mlx5_esw_unlock(esw); return err; } @@ -1838,7 +2142,7 @@ static int mlx5e_ipsec_block_tc_offload(struct mlx5_core_dev *mdev) static void mlx5e_ipsec_unblock_tc_offload(struct mlx5_core_dev *mdev) { - mdev->num_block_tc++; + mdev->num_block_tc--; } int mlx5e_accel_ipsec_fs_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry) @@ -1887,6 +2191,17 @@ void mlx5e_accel_ipsec_fs_del_rule(struct mlx5e_ipsec_sa_entry *sa_entry) if (ipsec_rule->modify_hdr) mlx5_modify_header_dealloc(mdev, ipsec_rule->modify_hdr); + + mlx5_del_flow_rules(ipsec_rule->trailer.rule); + mlx5_fc_destroy(mdev, ipsec_rule->trailer.fc); + + mlx5_del_flow_rules(ipsec_rule->auth.rule); + mlx5_fc_destroy(mdev, ipsec_rule->auth.fc); + + if (ipsec_rule->replay.rule) { + mlx5_del_flow_rules(ipsec_rule->replay.rule); + mlx5_fc_destroy(mdev, ipsec_rule->replay.fc); + } mlx5_esw_ipsec_rx_id_mapping_remove(sa_entry); rx_ft_put(sa_entry->ipsec, sa_entry->attrs.family, sa_entry->attrs.type); } @@ -1957,7 +2272,7 @@ void mlx5e_accel_ipsec_fs_cleanup(struct mlx5e_ipsec *ipsec) kfree(ipsec->rx_ipv6); if (ipsec->is_uplink_rep) { - xa_destroy(&ipsec->rx_esw->ipsec_obj_id_map); + xa_destroy(&ipsec->ipsec_obj_id_map); mutex_destroy(&ipsec->tx_esw->ft.mutex); WARN_ON(ipsec->tx_esw->ft.refcnt); @@ -2020,7 +2335,7 @@ int mlx5e_accel_ipsec_fs_init(struct mlx5e_ipsec *ipsec, mutex_init(&ipsec->tx_esw->ft.mutex); mutex_init(&ipsec->rx_esw->ft.mutex); ipsec->tx_esw->ns = ns_esw; - xa_init_flags(&ipsec->rx_esw->ipsec_obj_id_map, XA_FLAGS_ALLOC1); + xa_init_flags(&ipsec->ipsec_obj_id_map, XA_FLAGS_ALLOC1); } else if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_ROCE) { ipsec->roce = mlx5_ipsec_fs_roce_init(mdev, devcom); } else { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c index a91f772dc981..6e00afe4671b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c @@ -6,6 +6,8 @@ #include "ipsec.h" #include "lib/crypto.h" #include "lib/ipsec_fs_roce.h" +#include "fs_core.h" +#include "eswitch.h" enum { MLX5_IPSEC_ASO_REMOVE_FLOW_PKT_CNT_OFFSET, @@ -38,7 +40,10 @@ u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev) MLX5_CAP_ETH(mdev, insert_trailer) && MLX5_CAP_ETH(mdev, swp)) caps |= MLX5_IPSEC_CAP_CRYPTO; - if (MLX5_CAP_IPSEC(mdev, ipsec_full_offload)) { + if (MLX5_CAP_IPSEC(mdev, ipsec_full_offload) && + (mdev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_DMFS || + (mdev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_SMFS && + is_mdev_legacy_mode(mdev)))) { if (MLX5_CAP_FLOWTABLE_NIC_TX(mdev, reformat_add_esp_trasport) && MLX5_CAP_FLOWTABLE_NIC_RX(mdev, @@ -95,7 +100,7 @@ static void mlx5e_ipsec_packet_setup(void *obj, u32 pdn, if (attrs->dir == XFRM_DEV_OFFLOAD_IN) { MLX5_SET(ipsec_aso, aso_ctx, window_sz, - attrs->replay_esn.replay_window / 64); + attrs->replay_esn.replay_window); MLX5_SET(ipsec_aso, aso_ctx, mode, MLX5_IPSEC_ASO_REPLAY_PROTECTION); } @@ -559,6 +564,7 @@ void mlx5e_ipsec_aso_cleanup(struct mlx5e_ipsec *ipsec) dma_unmap_single(pdev, aso->dma_addr, sizeof(aso->ctx), DMA_BIDIRECTIONAL); kfree(aso); + ipsec->aso = NULL; } static void mlx5e_ipsec_aso_copy(struct mlx5_wqe_aso_ctrl_seg *ctrl, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 792a0ea544cd..c7c1b667b105 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -49,7 +49,7 @@ void mlx5e_ethtool_get_drvinfo(struct mlx5e_priv *priv, count = snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), "%d.%d.%04d (%.16s)", fw_rev_maj(mdev), fw_rev_min(mdev), fw_rev_sub(mdev), mdev->board_id); - if (count == sizeof(drvinfo->fw_version)) + if (count >= sizeof(drvinfo->fw_version)) snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), "%d.%d.%04d", fw_rev_maj(mdev), fw_rev_min(mdev), fw_rev_sub(mdev)); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index ea58c6917433..0c87ddb8a7a2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -2731,6 +2731,7 @@ void mlx5e_close_channels(struct mlx5e_channels *chs) { int i; + ASSERT_RTNL(); if (chs->ptp) { mlx5e_ptp_close(chs->ptp); chs->ptp = NULL; @@ -3012,17 +3013,29 @@ void mlx5e_activate_priv_channels(struct mlx5e_priv *priv) if (mlx5e_is_vport_rep(priv)) mlx5e_rep_activate_channels(priv); + set_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state); + mlx5e_wait_channels_min_rx_wqes(&priv->channels); if (priv->rx_res) mlx5e_rx_res_channels_activate(priv->rx_res, &priv->channels); } +static void mlx5e_cancel_tx_timeout_work(struct mlx5e_priv *priv) +{ + WARN_ON_ONCE(test_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state)); + if (current_work() != &priv->tx_timeout_work) + cancel_work_sync(&priv->tx_timeout_work); +} + void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv) { if (priv->rx_res) mlx5e_rx_res_channels_deactivate(priv->rx_res); + clear_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state); + mlx5e_cancel_tx_timeout_work(priv); + if (mlx5e_is_vport_rep(priv)) mlx5e_rep_deactivate_channels(priv); @@ -4801,8 +4814,17 @@ static void mlx5e_tx_timeout_work(struct work_struct *work) struct net_device *netdev = priv->netdev; int i; - rtnl_lock(); - mutex_lock(&priv->state_lock); + /* Take rtnl_lock to ensure no change in netdev->real_num_tx_queues + * through this flow. However, channel closing flows have to wait for + * this work to finish while holding rtnl lock too. So either get the + * lock or find that channels are being closed for other reason and + * this work is not relevant anymore. + */ + while (!rtnl_trylock()) { + if (!test_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state)) + return; + msleep(20); + } if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) goto unlock; @@ -4821,7 +4843,6 @@ static void mlx5e_tx_timeout_work(struct work_struct *work) } unlock: - mutex_unlock(&priv->state_lock); rtnl_unlock(); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 3ab682bbcf86..e92d4f83592e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -78,7 +78,7 @@ static void mlx5e_rep_get_drvinfo(struct net_device *dev, count = snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), "%d.%d.%04d (%.16s)", fw_rev_maj(mdev), fw_rev_min(mdev), fw_rev_sub(mdev), mdev->board_id); - if (count == sizeof(drvinfo->fw_version)) + if (count >= sizeof(drvinfo->fw_version)) snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), "%d.%d.%04d", fw_rev_maj(mdev), fw_rev_min(mdev), fw_rev_sub(mdev)); @@ -1497,7 +1497,7 @@ mlx5e_vport_vf_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) dl_port = mlx5_esw_offloads_devlink_port(dev->priv.eswitch, rpriv->rep->vport); - if (dl_port) { + if (!IS_ERR(dl_port)) { SET_NETDEV_DEVLINK_PORT(netdev, dl_port); mlx5e_rep_vnic_reporter_create(priv, dl_port); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 7ca9e5b86778..96af9e2ab1d8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -444,6 +444,9 @@ mlx5e_tc_add_flow_meter(struct mlx5e_priv *priv, struct mlx5e_flow_meter_handle *meter; enum mlx5e_post_meter_type type; + if (IS_ERR(post_act)) + return PTR_ERR(post_act); + meter = mlx5e_tc_meter_replace(priv->mdev, &attr->meter_attr.params); if (IS_ERR(meter)) { mlx5_core_err(priv->mdev, "Failed to get flow meter\n"); @@ -3739,6 +3742,20 @@ out_free: } static int +set_branch_dest_ft(struct mlx5e_priv *priv, struct mlx5_flow_attr *attr) +{ + struct mlx5e_post_act *post_act = get_post_action(priv); + + if (IS_ERR(post_act)) + return PTR_ERR(post_act); + + attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + attr->dest_ft = mlx5e_tc_post_act_get_ft(post_act); + + return 0; +} + +static int alloc_branch_attr(struct mlx5e_tc_flow *flow, struct mlx5e_tc_act_branch_ctrl *cond, struct mlx5_flow_attr **cond_attr, @@ -3761,8 +3778,9 @@ alloc_branch_attr(struct mlx5e_tc_flow *flow, break; case FLOW_ACTION_ACCEPT: case FLOW_ACTION_PIPE: - attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; - attr->dest_ft = mlx5e_tc_post_act_get_ft(get_post_action(flow->priv)); + err = set_branch_dest_ft(flow->priv, attr); + if (err) + goto out_err; break; case FLOW_ACTION_JUMP: if (*jump_count) { @@ -3771,8 +3789,9 @@ alloc_branch_attr(struct mlx5e_tc_flow *flow, goto out_err; } *jump_count = cond->extval; - attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; - attr->dest_ft = mlx5e_tc_post_act_get_ft(get_post_action(flow->priv)); + err = set_branch_dest_ft(flow->priv, attr); + if (err) + goto out_err; break; default: err = -EOPNOTSUPP; @@ -5719,8 +5738,10 @@ int mlx5e_tc_action_miss_mapping_get(struct mlx5e_priv *priv, struct mlx5_flow_a esw = priv->mdev->priv.eswitch; attr->act_id_restore_rule = esw_add_restore_rule(esw, *act_miss_mapping); - if (IS_ERR(attr->act_id_restore_rule)) + if (IS_ERR(attr->act_id_restore_rule)) { + err = PTR_ERR(attr->act_id_restore_rule); goto err_rule; + } return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c index 095f31f380fa..190f10aba170 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c @@ -21,158 +21,6 @@ enum { MLX5_ESW_IPSEC_TX_ESP_FT_CNT_LEVEL, }; -static void esw_ipsec_rx_status_drop_destroy(struct mlx5e_ipsec *ipsec, - struct mlx5e_ipsec_rx *rx) -{ - mlx5_del_flow_rules(rx->status_drop.rule); - mlx5_destroy_flow_group(rx->status_drop.group); - mlx5_fc_destroy(ipsec->mdev, rx->status_drop_cnt); -} - -static void esw_ipsec_rx_status_pass_destroy(struct mlx5e_ipsec *ipsec, - struct mlx5e_ipsec_rx *rx) -{ - mlx5_del_flow_rules(rx->status.rule); - mlx5_chains_put_table(esw_chains(ipsec->mdev->priv.eswitch), 0, 1, 0); -} - -static int esw_ipsec_rx_status_drop_create(struct mlx5e_ipsec *ipsec, - struct mlx5e_ipsec_rx *rx) -{ - int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); - struct mlx5_flow_table *ft = rx->ft.status; - struct mlx5_core_dev *mdev = ipsec->mdev; - struct mlx5_flow_destination dest = {}; - struct mlx5_flow_act flow_act = {}; - struct mlx5_flow_handle *rule; - struct mlx5_fc *flow_counter; - struct mlx5_flow_spec *spec; - struct mlx5_flow_group *g; - u32 *flow_group_in; - int err = 0; - - flow_group_in = kvzalloc(inlen, GFP_KERNEL); - spec = kvzalloc(sizeof(*spec), GFP_KERNEL); - if (!flow_group_in || !spec) { - err = -ENOMEM; - goto err_out; - } - - MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ft->max_fte - 1); - MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, ft->max_fte - 1); - g = mlx5_create_flow_group(ft, flow_group_in); - if (IS_ERR(g)) { - err = PTR_ERR(g); - mlx5_core_err(mdev, - "Failed to add ipsec rx status drop flow group, err=%d\n", err); - goto err_out; - } - - flow_counter = mlx5_fc_create(mdev, false); - if (IS_ERR(flow_counter)) { - err = PTR_ERR(flow_counter); - mlx5_core_err(mdev, - "Failed to add ipsec rx status drop rule counter, err=%d\n", err); - goto err_cnt; - } - - flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT; - dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; - dest.counter_id = mlx5_fc_id(flow_counter); - spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK; - rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1); - if (IS_ERR(rule)) { - err = PTR_ERR(rule); - mlx5_core_err(mdev, - "Failed to add ipsec rx status drop rule, err=%d\n", err); - goto err_rule; - } - - rx->status_drop.group = g; - rx->status_drop.rule = rule; - rx->status_drop_cnt = flow_counter; - - kvfree(flow_group_in); - kvfree(spec); - return 0; - -err_rule: - mlx5_fc_destroy(mdev, flow_counter); -err_cnt: - mlx5_destroy_flow_group(g); -err_out: - kvfree(flow_group_in); - kvfree(spec); - return err; -} - -static int esw_ipsec_rx_status_pass_create(struct mlx5e_ipsec *ipsec, - struct mlx5e_ipsec_rx *rx, - struct mlx5_flow_destination *dest) -{ - struct mlx5_flow_act flow_act = {}; - struct mlx5_flow_handle *rule; - struct mlx5_flow_spec *spec; - int err; - - spec = kvzalloc(sizeof(*spec), GFP_KERNEL); - if (!spec) - return -ENOMEM; - - MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, - misc_parameters_2.ipsec_syndrome); - MLX5_SET(fte_match_param, spec->match_value, - misc_parameters_2.ipsec_syndrome, 0); - spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK; - spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2; - flow_act.flags = FLOW_ACT_NO_APPEND; - flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | - MLX5_FLOW_CONTEXT_ACTION_COUNT; - rule = mlx5_add_flow_rules(rx->ft.status, spec, &flow_act, dest, 2); - if (IS_ERR(rule)) { - err = PTR_ERR(rule); - mlx5_core_warn(ipsec->mdev, - "Failed to add ipsec rx status pass rule, err=%d\n", err); - goto err_rule; - } - - rx->status.rule = rule; - kvfree(spec); - return 0; - -err_rule: - kvfree(spec); - return err; -} - -void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec, - struct mlx5e_ipsec_rx *rx) -{ - esw_ipsec_rx_status_pass_destroy(ipsec, rx); - esw_ipsec_rx_status_drop_destroy(ipsec, rx); -} - -int mlx5_esw_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec, - struct mlx5e_ipsec_rx *rx, - struct mlx5_flow_destination *dest) -{ - int err; - - err = esw_ipsec_rx_status_drop_create(ipsec, rx); - if (err) - return err; - - err = esw_ipsec_rx_status_pass_create(ipsec, rx, dest); - if (err) - goto err_pass_create; - - return 0; - -err_pass_create: - esw_ipsec_rx_status_drop_destroy(ipsec, rx); - return err; -} - void mlx5_esw_ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_rx_create_attr *attr) { @@ -202,7 +50,7 @@ int mlx5_esw_ipsec_rx_setup_modify_header(struct mlx5e_ipsec_sa_entry *sa_entry, u32 mapped_id; int err; - err = xa_alloc_bh(&ipsec->rx_esw->ipsec_obj_id_map, &mapped_id, + err = xa_alloc_bh(&ipsec->ipsec_obj_id_map, &mapped_id, xa_mk_value(sa_entry->ipsec_obj_id), XA_LIMIT(1, ESW_IPSEC_RX_MAPPED_ID_MASK), 0); if (err) @@ -233,7 +81,7 @@ int mlx5_esw_ipsec_rx_setup_modify_header(struct mlx5e_ipsec_sa_entry *sa_entry, return 0; err_header_alloc: - xa_erase_bh(&ipsec->rx_esw->ipsec_obj_id_map, mapped_id); + xa_erase_bh(&ipsec->ipsec_obj_id_map, mapped_id); return err; } @@ -242,7 +90,7 @@ void mlx5_esw_ipsec_rx_id_mapping_remove(struct mlx5e_ipsec_sa_entry *sa_entry) struct mlx5e_ipsec *ipsec = sa_entry->ipsec; if (sa_entry->rx_mapped_id) - xa_erase_bh(&ipsec->rx_esw->ipsec_obj_id_map, + xa_erase_bh(&ipsec->ipsec_obj_id_map, sa_entry->rx_mapped_id); } @@ -252,7 +100,7 @@ int mlx5_esw_ipsec_rx_ipsec_obj_id_search(struct mlx5e_priv *priv, u32 id, struct mlx5e_ipsec *ipsec = priv->ipsec; void *val; - val = xa_load(&ipsec->rx_esw->ipsec_obj_id_map, id); + val = xa_load(&ipsec->ipsec_obj_id_map, id); if (!val) return -ENOENT; @@ -304,7 +152,7 @@ void mlx5_esw_ipsec_restore_dest_uplink(struct mlx5_core_dev *mdev) xa_for_each(&esw->offloads.vport_reps, i, rep) { rpriv = rep->rep_data[REP_ETH].priv; - if (!rpriv || !rpriv->netdev) + if (!rpriv || !rpriv->netdev || !atomic_read(&rpriv->tc_ht.nelems)) continue; rhashtable_walk_enter(&rpriv->tc_ht, &iter); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h index 0c90f7a8b0d3..ac9c65b89166 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h @@ -8,11 +8,6 @@ struct mlx5e_ipsec; struct mlx5e_ipsec_sa_entry; #ifdef CONFIG_MLX5_ESWITCH -void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec, - struct mlx5e_ipsec_rx *rx); -int mlx5_esw_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec, - struct mlx5e_ipsec_rx *rx, - struct mlx5_flow_destination *dest); void mlx5_esw_ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_rx_create_attr *attr); int mlx5_esw_ipsec_rx_status_pass_dest_get(struct mlx5e_ipsec *ipsec, @@ -26,16 +21,6 @@ void mlx5_esw_ipsec_tx_create_attr_set(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx_create_attr *attr); void mlx5_esw_ipsec_restore_dest_uplink(struct mlx5_core_dev *mdev); #else -static inline void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec, - struct mlx5e_ipsec_rx *rx) {} - -static inline int mlx5_esw_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec, - struct mlx5e_ipsec_rx *rx, - struct mlx5_flow_destination *dest) -{ - return -EINVAL; -} - static inline void mlx5_esw_ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_rx_create_attr *attr) {} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 8d0b915a3121..3047d7015c52 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1463,7 +1463,7 @@ int mlx5_eswitch_enable_locked(struct mlx5_eswitch *esw, int num_vfs) { int err; - lockdep_assert_held(&esw->mode_lock); + devl_assert_locked(priv_to_devlink(esw->dev)); if (!MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ft_support)) { esw_warn(esw->dev, "FDB is not supported, aborting ...\n"); @@ -1531,7 +1531,6 @@ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs) if (toggle_lag) mlx5_lag_disable_change(esw->dev); - down_write(&esw->mode_lock); if (!mlx5_esw_is_fdb_created(esw)) { ret = mlx5_eswitch_enable_locked(esw, num_vfs); } else { @@ -1554,8 +1553,6 @@ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs) } } - up_write(&esw->mode_lock); - if (toggle_lag) mlx5_lag_enable_change(esw->dev); @@ -1569,12 +1566,11 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw, bool clear_vf) return; devl_assert_locked(priv_to_devlink(esw->dev)); - down_write(&esw->mode_lock); /* If driver is unloaded, this function is called twice by remove_one() * and mlx5_unload(). Prevent the second call. */ if (!esw->esw_funcs.num_vfs && !esw->esw_funcs.num_ec_vfs && !clear_vf) - goto unlock; + return; esw_info(esw->dev, "Unload vfs: mode(%s), nvfs(%d), necvfs(%d), active vports(%d)\n", esw->mode == MLX5_ESWITCH_LEGACY ? "LEGACY" : "OFFLOADS", @@ -1603,9 +1599,6 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw, bool clear_vf) esw->esw_funcs.num_vfs = 0; else esw->esw_funcs.num_ec_vfs = 0; - -unlock: - up_write(&esw->mode_lock); } /* Free resources for corresponding eswitch mode. It is called by devlink @@ -1647,10 +1640,8 @@ void mlx5_eswitch_disable(struct mlx5_eswitch *esw) devl_assert_locked(priv_to_devlink(esw->dev)); mlx5_lag_disable_change(esw->dev); - down_write(&esw->mode_lock); mlx5_eswitch_disable_locked(esw); esw->mode = MLX5_ESWITCH_LEGACY; - up_write(&esw->mode_lock); mlx5_lag_enable_change(esw->dev); } @@ -2254,8 +2245,13 @@ bool mlx5_esw_hold(struct mlx5_core_dev *mdev) if (!mlx5_esw_allowed(esw)) return true; - if (down_read_trylock(&esw->mode_lock) != 0) + if (down_read_trylock(&esw->mode_lock) != 0) { + if (esw->eswitch_operation_in_progress) { + up_read(&esw->mode_lock); + return false; + } return true; + } return false; } @@ -2312,7 +2308,8 @@ int mlx5_esw_try_lock(struct mlx5_eswitch *esw) if (down_write_trylock(&esw->mode_lock) == 0) return -EINVAL; - if (atomic64_read(&esw->user_count) > 0) { + if (esw->eswitch_operation_in_progress || + atomic64_read(&esw->user_count) > 0) { up_write(&esw->mode_lock); return -EBUSY; } @@ -2320,6 +2317,18 @@ int mlx5_esw_try_lock(struct mlx5_eswitch *esw) return esw->mode; } +int mlx5_esw_lock(struct mlx5_eswitch *esw) +{ + down_write(&esw->mode_lock); + + if (esw->eswitch_operation_in_progress) { + up_write(&esw->mode_lock); + return -EBUSY; + } + + return 0; +} + /** * mlx5_esw_unlock() - Release write lock on esw mode lock * @esw: eswitch device. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 37ab66e7b403..b4eb17141edf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -383,6 +383,7 @@ struct mlx5_eswitch { struct xarray paired; struct mlx5_devcom_comp_dev *devcom; u16 enabled_ipsec_vf_count; + bool eswitch_operation_in_progress; }; void esw_offloads_disable(struct mlx5_eswitch *esw); @@ -525,7 +526,8 @@ struct mlx5_esw_flow_attr { u8 total_vlan; struct { u32 flags; - struct mlx5_eswitch_rep *rep; + bool vport_valid; + u16 vport; struct mlx5_pkt_reformat *pkt_reformat; struct mlx5_core_dev *mdev; struct mlx5_termtbl_handle *termtbl; @@ -827,6 +829,7 @@ void mlx5_esw_release(struct mlx5_core_dev *dev); void mlx5_esw_get(struct mlx5_core_dev *dev); void mlx5_esw_put(struct mlx5_core_dev *dev); int mlx5_esw_try_lock(struct mlx5_eswitch *esw); +int mlx5_esw_lock(struct mlx5_eswitch *esw); void mlx5_esw_unlock(struct mlx5_eswitch *esw); void esw_vport_change_handle_locked(struct mlx5_vport *vport); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 88236e75fd90..b0455134c98e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -287,10 +287,9 @@ static void esw_put_dest_tables_loop(struct mlx5_eswitch *esw, struct mlx5_flow_ for (i = from; i < to; i++) if (esw_attr->dests[i].flags & MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE) mlx5_chains_put_table(chains, 0, 1, 0); - else if (mlx5_esw_indir_table_needed(esw, attr, esw_attr->dests[i].rep->vport, + else if (mlx5_esw_indir_table_needed(esw, attr, esw_attr->dests[i].vport, esw_attr->dests[i].mdev)) - mlx5_esw_indir_table_put(esw, esw_attr->dests[i].rep->vport, - false); + mlx5_esw_indir_table_put(esw, esw_attr->dests[i].vport, false); } static bool @@ -358,8 +357,8 @@ esw_is_indir_table(struct mlx5_eswitch *esw, struct mlx5_flow_attr *attr) * this criteria. */ for (i = esw_attr->split_count; i < esw_attr->out_count; i++) { - if (esw_attr->dests[i].rep && - mlx5_esw_indir_table_needed(esw, attr, esw_attr->dests[i].rep->vport, + if (esw_attr->dests[i].vport_valid && + mlx5_esw_indir_table_needed(esw, attr, esw_attr->dests[i].vport, esw_attr->dests[i].mdev)) { result = true; } else { @@ -388,7 +387,7 @@ esw_setup_indir_table(struct mlx5_flow_destination *dest, dest[*i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; dest[*i].ft = mlx5_esw_indir_table_get(esw, attr, - esw_attr->dests[j].rep->vport, false); + esw_attr->dests[j].vport, false); if (IS_ERR(dest[*i].ft)) { err = PTR_ERR(dest[*i].ft); goto err_indir_tbl_get; @@ -432,11 +431,11 @@ static bool esw_setup_uplink_fwd_ipsec_needed(struct mlx5_eswitch *esw, int attr_idx) { if (esw->offloads.ft_ipsec_tx_pol && - esw_attr->dests[attr_idx].rep && - esw_attr->dests[attr_idx].rep->vport == MLX5_VPORT_UPLINK && + esw_attr->dests[attr_idx].vport_valid && + esw_attr->dests[attr_idx].vport == MLX5_VPORT_UPLINK && /* To be aligned with software, encryption is needed only for tunnel device */ (esw_attr->dests[attr_idx].flags & MLX5_ESW_DEST_ENCAP_VALID) && - esw_attr->dests[attr_idx].rep != esw_attr->in_rep && + esw_attr->dests[attr_idx].vport != esw_attr->in_rep->vport && esw_same_vhca_id(esw_attr->dests[attr_idx].mdev, esw->dev)) return true; @@ -469,7 +468,7 @@ esw_setup_dest_fwd_vport(struct mlx5_flow_destination *dest, struct mlx5_flow_ac int attr_idx, int dest_idx, bool pkt_reformat) { dest[dest_idx].type = MLX5_FLOW_DESTINATION_TYPE_VPORT; - dest[dest_idx].vport.num = esw_attr->dests[attr_idx].rep->vport; + dest[dest_idx].vport.num = esw_attr->dests[attr_idx].vport; if (MLX5_CAP_ESW(esw->dev, merged_eswitch)) { dest[dest_idx].vport.vhca_id = MLX5_CAP_GEN(esw_attr->dests[attr_idx].mdev, vhca_id); @@ -1177,9 +1176,9 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw, struct mlx5_flow_handle *flow; struct mlx5_flow_spec *spec; struct mlx5_vport *vport; + int err, pfindex; unsigned long i; void *misc; - int err; if (!MLX5_VPORT_MANAGER(esw->dev) && !mlx5_core_is_ecpf_esw_manager(esw->dev)) return 0; @@ -1255,7 +1254,15 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw, flows[vport->index] = flow; } } - esw->fdb_table.offloads.peer_miss_rules[mlx5_get_dev_index(peer_dev)] = flows; + + pfindex = mlx5_get_dev_index(peer_dev); + if (pfindex >= MLX5_MAX_PORTS) { + esw_warn(esw->dev, "Peer dev index(%d) is over the max num defined(%d)\n", + pfindex, MLX5_MAX_PORTS); + err = -EINVAL; + goto add_ec_vf_flow_err; + } + esw->fdb_table.offloads.peer_miss_rules[pfindex] = flows; kvfree(spec); return 0; @@ -3653,14 +3660,18 @@ static int esw_inline_mode_to_devlink(u8 mlx5_mode, u8 *mode) static bool esw_offloads_devlink_ns_eq_netdev_ns(struct devlink *devlink) { + struct mlx5_core_dev *dev = devlink_priv(devlink); struct net *devl_net, *netdev_net; - struct mlx5_eswitch *esw; - - esw = mlx5_devlink_eswitch_nocheck_get(devlink); - netdev_net = dev_net(esw->dev->mlx5e_res.uplink_netdev); - devl_net = devlink_net(devlink); + bool ret = false; - return net_eq(devl_net, netdev_net); + mutex_lock(&dev->mlx5e_res.uplink_netdev_lock); + if (dev->mlx5e_res.uplink_netdev) { + netdev_net = dev_net(dev->mlx5e_res.uplink_netdev); + devl_net = devlink_net(devlink); + ret = net_eq(devl_net, netdev_net); + } + mutex_unlock(&dev->mlx5e_res.uplink_netdev_lock); + return ret; } int mlx5_eswitch_block_mode(struct mlx5_core_dev *dev) @@ -3733,13 +3744,16 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode, goto unlock; } + esw->eswitch_operation_in_progress = true; + up_write(&esw->mode_lock); + mlx5_eswitch_disable_locked(esw); if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV) { if (mlx5_devlink_trap_get_num_active(esw->dev)) { NL_SET_ERR_MSG_MOD(extack, "Can't change mode while devlink traps are active"); err = -EOPNOTSUPP; - goto unlock; + goto skip; } err = esw_offloads_start(esw, extack); } else if (mode == DEVLINK_ESWITCH_MODE_LEGACY) { @@ -3749,6 +3763,9 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode, err = -EINVAL; } +skip: + down_write(&esw->mode_lock); + esw->eswitch_operation_in_progress = false; unlock: mlx5_esw_unlock(esw); enable_lag: @@ -3759,16 +3776,12 @@ enable_lag: int mlx5_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode) { struct mlx5_eswitch *esw; - int err; esw = mlx5_devlink_eswitch_get(devlink); if (IS_ERR(esw)) return PTR_ERR(esw); - down_read(&esw->mode_lock); - err = esw_mode_to_devlink(esw->mode, mode); - up_read(&esw->mode_lock); - return err; + return esw_mode_to_devlink(esw->mode, mode); } static int mlx5_esw_vports_inline_set(struct mlx5_eswitch *esw, u8 mlx5_mode, @@ -3862,11 +3875,15 @@ int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode, if (err) goto out; + esw->eswitch_operation_in_progress = true; + up_write(&esw->mode_lock); + err = mlx5_esw_vports_inline_set(esw, mlx5_mode, extack); - if (err) - goto out; + if (!err) + esw->offloads.inline_mode = mlx5_mode; - esw->offloads.inline_mode = mlx5_mode; + down_write(&esw->mode_lock); + esw->eswitch_operation_in_progress = false; up_write(&esw->mode_lock); return 0; @@ -3878,16 +3895,12 @@ out: int mlx5_devlink_eswitch_inline_mode_get(struct devlink *devlink, u8 *mode) { struct mlx5_eswitch *esw; - int err; esw = mlx5_devlink_eswitch_get(devlink); if (IS_ERR(esw)) return PTR_ERR(esw); - down_read(&esw->mode_lock); - err = esw_inline_mode_to_devlink(esw->offloads.inline_mode, mode); - up_read(&esw->mode_lock); - return err; + return esw_inline_mode_to_devlink(esw->offloads.inline_mode, mode); } bool mlx5_eswitch_block_encap(struct mlx5_core_dev *dev) @@ -3969,6 +3982,9 @@ int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink, goto unlock; } + esw->eswitch_operation_in_progress = true; + up_write(&esw->mode_lock); + esw_destroy_offloads_fdb_tables(esw); esw->offloads.encap = encap; @@ -3982,6 +3998,9 @@ int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink, (void)esw_create_offloads_fdb_tables(esw); } + down_write(&esw->mode_lock); + esw->eswitch_operation_in_progress = false; + unlock: up_write(&esw->mode_lock); return err; @@ -3996,9 +4015,7 @@ int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink, if (IS_ERR(esw)) return PTR_ERR(esw); - down_read(&esw->mode_lock); *encap = esw->offloads.encap; - up_read(&esw->mode_lock); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c index edd910258314..40bdc677f051 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c @@ -233,8 +233,8 @@ mlx5_eswitch_termtbl_required(struct mlx5_eswitch *esw, /* hairpin */ for (i = esw_attr->split_count; i < esw_attr->out_count; i++) - if (!esw_attr->dest_int_port && esw_attr->dests[i].rep && - esw_attr->dests[i].rep->vport == MLX5_VPORT_UPLINK) + if (!esw_attr->dest_int_port && esw_attr->dests[i].vport_valid && + esw_attr->dests[i].vport == MLX5_VPORT_UPLINK) return true; return false; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c index b568988e92e3..c4e19d627da2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c @@ -325,6 +325,29 @@ static void mlx5_fw_live_patch_event(struct work_struct *work) mlx5_core_err(dev, "Failed to reload FW tracer\n"); } +#if IS_ENABLED(CONFIG_HOTPLUG_PCI_PCIE) +static int mlx5_check_hotplug_interrupt(struct mlx5_core_dev *dev) +{ + struct pci_dev *bridge = dev->pdev->bus->self; + u16 reg16; + int err; + + if (!bridge) + return -EOPNOTSUPP; + + err = pcie_capability_read_word(bridge, PCI_EXP_SLTCTL, ®16); + if (err) + return err; + + if ((reg16 & PCI_EXP_SLTCTL_HPIE) && (reg16 & PCI_EXP_SLTCTL_DLLSCE)) { + mlx5_core_warn(dev, "FW reset is not supported as HotPlug is enabled\n"); + return -EOPNOTSUPP; + } + + return 0; +} +#endif + static int mlx5_check_dev_ids(struct mlx5_core_dev *dev, u16 dev_id) { struct pci_bus *bridge_bus = dev->pdev->bus; @@ -357,6 +380,12 @@ static bool mlx5_is_reset_now_capable(struct mlx5_core_dev *dev) return false; } +#if IS_ENABLED(CONFIG_HOTPLUG_PCI_PCIE) + err = mlx5_check_hotplug_interrupt(dev); + if (err) + return false; +#endif + err = pci_read_config_word(dev->pdev, PCI_DEVICE_ID, &dev_id); if (err) return false; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index 5a31fb47ffa5..21753f327868 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -277,7 +277,7 @@ int mlx5_query_nic_vport_mac_list(struct mlx5_core_dev *dev, req_list_size = max_list_size; } - out_sz = MLX5_ST_SZ_BYTES(query_nic_vport_context_in) + + out_sz = MLX5_ST_SZ_BYTES(query_nic_vport_context_out) + req_list_size * MLX5_ST_SZ_BYTES(mac_address_layout); out = kvzalloc(out_sz, GFP_KERNEL); diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c index 0d5a41a2ae01..227d01cace3f 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c @@ -267,6 +267,13 @@ static bool mlxbf_gige_rx_packet(struct mlxbf_gige *priv, int *rx_pkts) priv->stats.rx_truncate_errors++; } + /* Read receive consumer index before replenish so that this routine + * returns accurate return value even if packet is received into + * just-replenished buffer prior to exiting this routine. + */ + rx_ci = readq(priv->base + MLXBF_GIGE_RX_CQE_PACKET_CI); + rx_ci_rem = rx_ci % priv->rx_q_entries; + /* Let hardware know we've replenished one buffer */ rx_pi++; @@ -279,8 +286,6 @@ static bool mlxbf_gige_rx_packet(struct mlxbf_gige *priv, int *rx_pkts) rx_pi_rem = rx_pi % priv->rx_q_entries; if (rx_pi_rem == 0) priv->valid_polarity ^= 1; - rx_ci = readq(priv->base + MLXBF_GIGE_RX_CQE_PACKET_CI); - rx_ci_rem = rx_ci % priv->rx_q_entries; if (skb) netif_receive_skb(skb); diff --git a/drivers/net/ethernet/micrel/ks8851.h b/drivers/net/ethernet/micrel/ks8851.h index fecd43754cea..e5ec0a363aff 100644 --- a/drivers/net/ethernet/micrel/ks8851.h +++ b/drivers/net/ethernet/micrel/ks8851.h @@ -350,6 +350,8 @@ union ks8851_tx_hdr { * @rxd: Space for receiving SPI data, in DMA-able space. * @txd: Space for transmitting SPI data, in DMA-able space. * @msg_enable: The message flags controlling driver output (see ethtool). + * @tx_space: Free space in the hardware TX buffer (cached copy of KS_TXMIR). + * @queued_len: Space required in hardware TX buffer for queued packets in txq. * @fid: Incrementing frame id tag. * @rc_ier: Cached copy of KS_IER. * @rc_ccr: Cached copy of KS_CCR. @@ -399,6 +401,7 @@ struct ks8851_net { struct work_struct rxctrl_work; struct sk_buff_head txq; + unsigned int queued_len; struct eeprom_93cx6 eeprom; struct regulator *vdd_reg; diff --git a/drivers/net/ethernet/micrel/ks8851_common.c b/drivers/net/ethernet/micrel/ks8851_common.c index cfbc900d4aeb..0bf13b38b8f5 100644 --- a/drivers/net/ethernet/micrel/ks8851_common.c +++ b/drivers/net/ethernet/micrel/ks8851_common.c @@ -362,16 +362,18 @@ static irqreturn_t ks8851_irq(int irq, void *_ks) handled |= IRQ_RXPSI; if (status & IRQ_TXI) { - handled |= IRQ_TXI; + unsigned short tx_space = ks8851_rdreg16(ks, KS_TXMIR); - /* no lock here, tx queue should have been stopped */ + netif_dbg(ks, intr, ks->netdev, + "%s: txspace %d\n", __func__, tx_space); - /* update our idea of how much tx space is available to the - * system */ - ks->tx_space = ks8851_rdreg16(ks, KS_TXMIR); + spin_lock(&ks->statelock); + ks->tx_space = tx_space; + if (netif_queue_stopped(ks->netdev)) + netif_wake_queue(ks->netdev); + spin_unlock(&ks->statelock); - netif_dbg(ks, intr, ks->netdev, - "%s: txspace %d\n", __func__, ks->tx_space); + handled |= IRQ_TXI; } if (status & IRQ_RXI) @@ -414,9 +416,6 @@ static irqreturn_t ks8851_irq(int irq, void *_ks) if (status & IRQ_LCI) mii_check_link(&ks->mii); - if (status & IRQ_TXI) - netif_wake_queue(ks->netdev); - return IRQ_HANDLED; } @@ -500,6 +499,7 @@ static int ks8851_net_open(struct net_device *dev) ks8851_wrreg16(ks, KS_ISR, ks->rc_ier); ks8851_wrreg16(ks, KS_IER, ks->rc_ier); + ks->queued_len = 0; netif_start_queue(ks->netdev); netif_dbg(ks, ifup, ks->netdev, "network device up\n"); diff --git a/drivers/net/ethernet/micrel/ks8851_spi.c b/drivers/net/ethernet/micrel/ks8851_spi.c index 70bc7253454f..88e26c120b48 100644 --- a/drivers/net/ethernet/micrel/ks8851_spi.c +++ b/drivers/net/ethernet/micrel/ks8851_spi.c @@ -287,6 +287,18 @@ static void ks8851_wrfifo_spi(struct ks8851_net *ks, struct sk_buff *txp, } /** + * calc_txlen - calculate size of message to send packet + * @len: Length of data + * + * Returns the size of the TXFIFO message needed to send + * this packet. + */ +static unsigned int calc_txlen(unsigned int len) +{ + return ALIGN(len + 4, 4); +} + +/** * ks8851_rx_skb_spi - receive skbuff * @ks: The device state * @skb: The skbuff @@ -305,7 +317,9 @@ static void ks8851_rx_skb_spi(struct ks8851_net *ks, struct sk_buff *skb) */ static void ks8851_tx_work(struct work_struct *work) { + unsigned int dequeued_len = 0; struct ks8851_net_spi *kss; + unsigned short tx_space; struct ks8851_net *ks; unsigned long flags; struct sk_buff *txb; @@ -322,6 +336,8 @@ static void ks8851_tx_work(struct work_struct *work) last = skb_queue_empty(&ks->txq); if (txb) { + dequeued_len += calc_txlen(txb->len); + ks8851_wrreg16_spi(ks, KS_RXQCR, ks->rc_rxqcr | RXQCR_SDA); ks8851_wrfifo_spi(ks, txb, last); @@ -332,6 +348,13 @@ static void ks8851_tx_work(struct work_struct *work) } } + tx_space = ks8851_rdreg16_spi(ks, KS_TXMIR); + + spin_lock(&ks->statelock); + ks->queued_len -= dequeued_len; + ks->tx_space = tx_space; + spin_unlock(&ks->statelock); + ks8851_unlock_spi(ks, &flags); } @@ -347,18 +370,6 @@ static void ks8851_flush_tx_work_spi(struct ks8851_net *ks) } /** - * calc_txlen - calculate size of message to send packet - * @len: Length of data - * - * Returns the size of the TXFIFO message needed to send - * this packet. - */ -static unsigned int calc_txlen(unsigned int len) -{ - return ALIGN(len + 4, 4); -} - -/** * ks8851_start_xmit_spi - transmit packet using SPI * @skb: The buffer to transmit * @dev: The device used to transmit the packet. @@ -386,16 +397,17 @@ static netdev_tx_t ks8851_start_xmit_spi(struct sk_buff *skb, spin_lock(&ks->statelock); - if (needed > ks->tx_space) { + if (ks->queued_len + needed > ks->tx_space) { netif_stop_queue(dev); ret = NETDEV_TX_BUSY; } else { - ks->tx_space -= needed; + ks->queued_len += needed; skb_queue_tail(&ks->txq, skb); } spin_unlock(&ks->statelock); - schedule_work(&kss->tx_work); + if (ret == NETDEV_TX_OK) + schedule_work(&kss->tx_work); return ret; } diff --git a/drivers/net/ethernet/microsoft/Kconfig b/drivers/net/ethernet/microsoft/Kconfig index 090e6b983243..01eb7445ead9 100644 --- a/drivers/net/ethernet/microsoft/Kconfig +++ b/drivers/net/ethernet/microsoft/Kconfig @@ -20,6 +20,7 @@ config MICROSOFT_MANA depends on PCI_MSI && X86_64 depends on PCI_HYPERV select AUXILIARY_BUS + select PAGE_POOL help This driver supports Microsoft Azure Network Adapter (MANA). So far, the driver is only supported on X86_64. diff --git a/drivers/net/ethernet/mscc/ocelot_stats.c b/drivers/net/ethernet/mscc/ocelot_stats.c index 5c55197c7327..c018783757fb 100644 --- a/drivers/net/ethernet/mscc/ocelot_stats.c +++ b/drivers/net/ethernet/mscc/ocelot_stats.c @@ -582,10 +582,10 @@ static void ocelot_port_rmon_stats_cb(struct ocelot *ocelot, int port, void *pri rmon_stats->hist_tx[0] = s[OCELOT_STAT_TX_64]; rmon_stats->hist_tx[1] = s[OCELOT_STAT_TX_65_127]; rmon_stats->hist_tx[2] = s[OCELOT_STAT_TX_128_255]; - rmon_stats->hist_tx[3] = s[OCELOT_STAT_TX_128_255]; - rmon_stats->hist_tx[4] = s[OCELOT_STAT_TX_256_511]; - rmon_stats->hist_tx[5] = s[OCELOT_STAT_TX_512_1023]; - rmon_stats->hist_tx[6] = s[OCELOT_STAT_TX_1024_1526]; + rmon_stats->hist_tx[3] = s[OCELOT_STAT_TX_256_511]; + rmon_stats->hist_tx[4] = s[OCELOT_STAT_TX_512_1023]; + rmon_stats->hist_tx[5] = s[OCELOT_STAT_TX_1024_1526]; + rmon_stats->hist_tx[6] = s[OCELOT_STAT_TX_1527_MAX]; } static void ocelot_port_pmac_rmon_stats_cb(struct ocelot *ocelot, int port, @@ -610,10 +610,10 @@ static void ocelot_port_pmac_rmon_stats_cb(struct ocelot *ocelot, int port, rmon_stats->hist_tx[0] = s[OCELOT_STAT_TX_PMAC_64]; rmon_stats->hist_tx[1] = s[OCELOT_STAT_TX_PMAC_65_127]; rmon_stats->hist_tx[2] = s[OCELOT_STAT_TX_PMAC_128_255]; - rmon_stats->hist_tx[3] = s[OCELOT_STAT_TX_PMAC_128_255]; - rmon_stats->hist_tx[4] = s[OCELOT_STAT_TX_PMAC_256_511]; - rmon_stats->hist_tx[5] = s[OCELOT_STAT_TX_PMAC_512_1023]; - rmon_stats->hist_tx[6] = s[OCELOT_STAT_TX_PMAC_1024_1526]; + rmon_stats->hist_tx[3] = s[OCELOT_STAT_TX_PMAC_256_511]; + rmon_stats->hist_tx[4] = s[OCELOT_STAT_TX_PMAC_512_1023]; + rmon_stats->hist_tx[5] = s[OCELOT_STAT_TX_PMAC_1024_1526]; + rmon_stats->hist_tx[6] = s[OCELOT_STAT_TX_PMAC_1527_MAX]; } void ocelot_port_get_rmon_stats(struct ocelot *ocelot, int port, diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c index 65e20693c549..33f4f58ee51c 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c +++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c @@ -933,6 +933,7 @@ static void qed_ilt_shadow_free(struct qed_hwfn *p_hwfn) p_dma->virt_addr = NULL; } kfree(p_mngr->ilt_shadow); + p_mngr->ilt_shadow = NULL; } static int qed_ilt_blk_alloc(struct qed_hwfn *p_hwfn, diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c index 0d57ffcedf0c..fc78bc959ded 100644 --- a/drivers/net/ethernet/qlogic/qla3xxx.c +++ b/drivers/net/ethernet/qlogic/qla3xxx.c @@ -2591,6 +2591,7 @@ static int ql_alloc_buffer_queues(struct ql3_adapter *qdev) if (qdev->lrg_buf_q_alloc_virt_addr == NULL) { netdev_err(qdev->ndev, "lBufQ failed\n"); + kfree(qdev->lrg_buf); return -ENOMEM; } qdev->lrg_buf_q_virt_addr = qdev->lrg_buf_q_alloc_virt_addr; @@ -2615,6 +2616,7 @@ static int ql_alloc_buffer_queues(struct ql3_adapter *qdev) qdev->lrg_buf_q_alloc_size, qdev->lrg_buf_q_alloc_virt_addr, qdev->lrg_buf_q_alloc_phy_addr); + kfree(qdev->lrg_buf); return -ENOMEM; } diff --git a/drivers/net/ethernet/qualcomm/qca_debug.c b/drivers/net/ethernet/qualcomm/qca_debug.c index 6f2fa2a42770..1822f2ad8f0d 100644 --- a/drivers/net/ethernet/qualcomm/qca_debug.c +++ b/drivers/net/ethernet/qualcomm/qca_debug.c @@ -30,6 +30,8 @@ #define QCASPI_MAX_REGS 0x20 +#define QCASPI_RX_MAX_FRAMES 4 + static const u16 qcaspi_spi_regs[] = { SPI_REG_BFR_SIZE, SPI_REG_WRBUF_SPC_AVA, @@ -252,9 +254,9 @@ qcaspi_get_ringparam(struct net_device *dev, struct ethtool_ringparam *ring, { struct qcaspi *qca = netdev_priv(dev); - ring->rx_max_pending = 4; + ring->rx_max_pending = QCASPI_RX_MAX_FRAMES; ring->tx_max_pending = TX_RING_MAX_LEN; - ring->rx_pending = 4; + ring->rx_pending = QCASPI_RX_MAX_FRAMES; ring->tx_pending = qca->txr.count; } @@ -263,22 +265,21 @@ qcaspi_set_ringparam(struct net_device *dev, struct ethtool_ringparam *ring, struct kernel_ethtool_ringparam *kernel_ring, struct netlink_ext_ack *extack) { - const struct net_device_ops *ops = dev->netdev_ops; struct qcaspi *qca = netdev_priv(dev); - if ((ring->rx_pending) || + if (ring->rx_pending != QCASPI_RX_MAX_FRAMES || (ring->rx_mini_pending) || (ring->rx_jumbo_pending)) return -EINVAL; - if (netif_running(dev)) - ops->ndo_stop(dev); + if (qca->spi_thread) + kthread_park(qca->spi_thread); qca->txr.count = max_t(u32, ring->tx_pending, TX_RING_MIN_LEN); qca->txr.count = min_t(u16, qca->txr.count, TX_RING_MAX_LEN); - if (netif_running(dev)) - ops->ndo_open(dev); + if (qca->spi_thread) + kthread_unpark(qca->spi_thread); return 0; } diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c index bec723028e96..5f3c11fb3fa2 100644 --- a/drivers/net/ethernet/qualcomm/qca_spi.c +++ b/drivers/net/ethernet/qualcomm/qca_spi.c @@ -580,6 +580,18 @@ qcaspi_spi_thread(void *data) netdev_info(qca->net_dev, "SPI thread created\n"); while (!kthread_should_stop()) { set_current_state(TASK_INTERRUPTIBLE); + if (kthread_should_park()) { + netif_tx_disable(qca->net_dev); + netif_carrier_off(qca->net_dev); + qcaspi_flush_tx_ring(qca); + kthread_parkme(); + if (qca->sync == QCASPI_SYNC_READY) { + netif_carrier_on(qca->net_dev); + netif_wake_queue(qca->net_dev); + } + continue; + } + if ((qca->intr_req == qca->intr_svc) && !qca->txr.skb[qca->txr.head]) schedule(); @@ -608,11 +620,17 @@ qcaspi_spi_thread(void *data) if (intr_cause & SPI_INT_CPU_ON) { qcaspi_qca7k_sync(qca, QCASPI_EVENT_CPUON); + /* Frame decoding in progress */ + if (qca->frm_handle.state != qca->frm_handle.init) + qca->net_dev->stats.rx_dropped++; + + qcafrm_fsm_init_spi(&qca->frm_handle); + qca->stats.device_reset++; + /* not synced. */ if (qca->sync != QCASPI_SYNC_READY) continue; - qca->stats.device_reset++; netif_wake_queue(qca->net_dev); netif_carrier_on(qca->net_dev); } diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index bb787a52bc75..81fd31f6fac4 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -1211,7 +1211,7 @@ static void rtl8168ep_driver_start(struct rtl8169_private *tp) { r8168ep_ocp_write(tp, 0x01, 0x180, OOB_CMD_DRIVER_START); r8168ep_ocp_write(tp, 0x01, 0x30, r8168ep_ocp_read(tp, 0x30) | 0x01); - rtl_loop_wait_high(tp, &rtl_ep_ocp_read_cond, 10000, 10); + rtl_loop_wait_high(tp, &rtl_ep_ocp_read_cond, 10000, 30); } static void rtl8168_driver_start(struct rtl8169_private *tp) diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 664eda4b5a11..8649b3e90edb 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -66,16 +66,27 @@ int ravb_wait(struct net_device *ndev, enum ravb_reg reg, u32 mask, u32 value) return -ETIMEDOUT; } -static int ravb_config(struct net_device *ndev) +static int ravb_set_opmode(struct net_device *ndev, u32 opmode) { + u32 csr_ops = 1U << (opmode & CCC_OPC); + u32 ccc_mask = CCC_OPC; int error; - /* Set config mode */ - ravb_modify(ndev, CCC, CCC_OPC, CCC_OPC_CONFIG); - /* Check if the operating mode is changed to the config mode */ - error = ravb_wait(ndev, CSR, CSR_OPS, CSR_OPS_CONFIG); - if (error) - netdev_err(ndev, "failed to switch device to config mode\n"); + /* If gPTP active in config mode is supported it needs to be configured + * along with CSEL and operating mode in the same access. This is a + * hardware limitation. + */ + if (opmode & CCC_GAC) + ccc_mask |= CCC_GAC | CCC_CSEL; + + /* Set operating mode */ + ravb_modify(ndev, CCC, ccc_mask, opmode); + /* Check if the operating mode is changed to the requested one */ + error = ravb_wait(ndev, CSR, CSR_OPS, csr_ops); + if (error) { + netdev_err(ndev, "failed to switch device to requested mode (%u)\n", + opmode & CCC_OPC); + } return error; } @@ -673,7 +684,7 @@ static int ravb_dmac_init(struct net_device *ndev) int error; /* Set CONFIG mode */ - error = ravb_config(ndev); + error = ravb_set_opmode(ndev, CCC_OPC_CONFIG); if (error) return error; @@ -682,9 +693,7 @@ static int ravb_dmac_init(struct net_device *ndev) return error; /* Setting the control will start the AVB-DMAC process. */ - ravb_modify(ndev, CCC, CCC_OPC, CCC_OPC_OPERATION); - - return 0; + return ravb_set_opmode(ndev, CCC_OPC_OPERATION); } static void ravb_get_tx_tstamp(struct net_device *ndev) @@ -1046,7 +1055,7 @@ static int ravb_stop_dma(struct net_device *ndev) return error; /* Stop AVB-DMAC process */ - return ravb_config(ndev); + return ravb_set_opmode(ndev, CCC_OPC_CONFIG); } /* E-MAC interrupt handler */ @@ -2560,21 +2569,25 @@ static int ravb_set_gti(struct net_device *ndev) return 0; } -static void ravb_set_config_mode(struct net_device *ndev) +static int ravb_set_config_mode(struct net_device *ndev) { struct ravb_private *priv = netdev_priv(ndev); const struct ravb_hw_info *info = priv->info; + int error; if (info->gptp) { - ravb_modify(ndev, CCC, CCC_OPC, CCC_OPC_CONFIG); + error = ravb_set_opmode(ndev, CCC_OPC_CONFIG); + if (error) + return error; /* Set CSEL value */ ravb_modify(ndev, CCC, CCC_CSEL, CCC_CSEL_HPB); } else if (info->ccc_gac) { - ravb_modify(ndev, CCC, CCC_OPC, CCC_OPC_CONFIG | - CCC_GAC | CCC_CSEL_HPB); + error = ravb_set_opmode(ndev, CCC_OPC_CONFIG | CCC_GAC | CCC_CSEL_HPB); } else { - ravb_modify(ndev, CCC, CCC_OPC, CCC_OPC_CONFIG); + error = ravb_set_opmode(ndev, CCC_OPC_CONFIG); } + + return error; } /* Set tx and rx clock internal delay modes */ @@ -2794,7 +2807,9 @@ static int ravb_probe(struct platform_device *pdev) ndev->ethtool_ops = &ravb_ethtool_ops; /* Set AVB config mode */ - ravb_set_config_mode(ndev); + error = ravb_set_config_mode(ndev); + if (error) + goto out_disable_gptp_clk; if (info->gptp || info->ccc_gac) { /* Set GTI value */ @@ -2917,8 +2932,7 @@ static void ravb_remove(struct platform_device *pdev) dma_free_coherent(ndev->dev.parent, priv->desc_bat_size, priv->desc_bat, priv->desc_bat_dma); - /* Set reset mode */ - ravb_write(ndev, CCC_OPC_RESET, CCC); + ravb_set_opmode(ndev, CCC_OPC_RESET); clk_disable_unprepare(priv->gptp_clk); clk_disable_unprepare(priv->refclk); @@ -3000,8 +3014,11 @@ static int __maybe_unused ravb_resume(struct device *dev) int ret = 0; /* If WoL is enabled set reset mode to rearm the WoL logic */ - if (priv->wol_enabled) - ravb_write(ndev, CCC_OPC_RESET, CCC); + if (priv->wol_enabled) { + ret = ravb_set_opmode(ndev, CCC_OPC_RESET); + if (ret) + return ret; + } /* All register have been reset to default values. * Restore all registers which where setup at probe time and @@ -3009,7 +3026,9 @@ static int __maybe_unused ravb_resume(struct device *dev) */ /* Set AVB config mode */ - ravb_set_config_mode(ndev); + ret = ravb_set_config_mode(ndev); + if (ret) + return ret; if (info->gptp || info->ccc_gac) { /* Set GTI value */ diff --git a/drivers/net/ethernet/sfc/rx_common.c b/drivers/net/ethernet/sfc/rx_common.c index d2f35ee15eff..fac227d372db 100644 --- a/drivers/net/ethernet/sfc/rx_common.c +++ b/drivers/net/ethernet/sfc/rx_common.c @@ -823,8 +823,10 @@ int efx_probe_filters(struct efx_nic *efx) } if (!success) { - efx_for_each_channel(channel, efx) + efx_for_each_channel(channel, efx) { kfree(channel->rps_flow_id); + channel->rps_flow_id = NULL; + } efx->type->filter_table_remove(efx); rc = -ENOMEM; goto out_unlock; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c index 2cd6fce5c993..9e40c28d453a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c @@ -59,26 +59,19 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id return -ENODEV; } - if (!of_device_is_compatible(np, "loongson, pci-gmac")) { - pr_info("dwmac_loongson_pci: Incompatible OF node\n"); - return -ENODEV; - } - plat = devm_kzalloc(&pdev->dev, sizeof(*plat), GFP_KERNEL); if (!plat) return -ENOMEM; + plat->mdio_bus_data = devm_kzalloc(&pdev->dev, + sizeof(*plat->mdio_bus_data), + GFP_KERNEL); + if (!plat->mdio_bus_data) + return -ENOMEM; + plat->mdio_node = of_get_child_by_name(np, "mdio"); if (plat->mdio_node) { dev_info(&pdev->dev, "Found MDIO subnode\n"); - - plat->mdio_bus_data = devm_kzalloc(&pdev->dev, - sizeof(*plat->mdio_bus_data), - GFP_KERNEL); - if (!plat->mdio_bus_data) { - ret = -ENOMEM; - goto err_put_node; - } plat->mdio_bus_data->needs_reset = true; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c index d3bf42d0fceb..31631e3f89d0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c @@ -34,6 +34,7 @@ #define RGMII_CONFIG_LOOPBACK_EN BIT(2) #define RGMII_CONFIG_PROG_SWAP BIT(1) #define RGMII_CONFIG_DDR_MODE BIT(0) +#define RGMII_CONFIG_SGMII_CLK_DVDR GENMASK(18, 10) /* SDCC_HC_REG_DLL_CONFIG fields */ #define SDCC_DLL_CONFIG_DLL_RST BIT(30) @@ -78,6 +79,8 @@ #define ETHQOS_MAC_CTRL_SPEED_MODE BIT(14) #define ETHQOS_MAC_CTRL_PORT_SEL BIT(15) +#define SGMII_10M_RX_CLK_DVDR 0x31 + struct ethqos_emac_por { unsigned int offset; unsigned int value; @@ -598,6 +601,9 @@ static int ethqos_configure_rgmii(struct qcom_ethqos *ethqos) return 0; } +/* On interface toggle MAC registers gets reset. + * Configure MAC block for SGMII on ethernet phy link up + */ static int ethqos_configure_sgmii(struct qcom_ethqos *ethqos) { int val; @@ -617,6 +623,10 @@ static int ethqos_configure_sgmii(struct qcom_ethqos *ethqos) case SPEED_10: val |= ETHQOS_MAC_CTRL_PORT_SEL; val &= ~ETHQOS_MAC_CTRL_SPEED_MODE; + rgmii_updatel(ethqos, RGMII_CONFIG_SGMII_CLK_DVDR, + FIELD_PREP(RGMII_CONFIG_SGMII_CLK_DVDR, + SGMII_10M_RX_CLK_DVDR), + RGMII_IO_MACRO_CONFIG); break; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c index 540f6a4ec0b8..f05bd757dfe5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c @@ -237,7 +237,7 @@ static void timestamp_interrupt(struct stmmac_priv *priv) */ ts_status = readl(priv->ioaddr + GMAC_TIMESTAMP_STATUS); - if (priv->plat->flags & STMMAC_FLAG_EXT_SNAPSHOT_EN) + if (!(priv->plat->flags & STMMAC_FLAG_EXT_SNAPSHOT_EN)) return; num_snapshot = (ts_status & GMAC_TIMESTAMP_ATSNS_MASK) >> diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c index fa9e7e7040b9..0542cfd1817e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c @@ -591,7 +591,11 @@ int stmmac_mdio_register(struct net_device *ndev) new_bus->parent = priv->device; err = of_mdiobus_register(new_bus, mdio_node); - if (err != 0) { + if (err == -ENODEV) { + err = 0; + dev_info(dev, "MDIO bus is disabled\n"); + goto bus_register_fail; + } else if (err) { dev_err_probe(dev, err, "Cannot register the MDIO bus\n"); goto bus_register_fail; } diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_lib.c index a5a50b5a8816..347d3cec02a3 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_lib.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.c @@ -160,60 +160,6 @@ static __le32 wx_test_staterr(union wx_rx_desc *rx_desc, return rx_desc->wb.upper.status_error & cpu_to_le32(stat_err_bits); } -static bool wx_can_reuse_rx_page(struct wx_rx_buffer *rx_buffer, - int rx_buffer_pgcnt) -{ - unsigned int pagecnt_bias = rx_buffer->pagecnt_bias; - struct page *page = rx_buffer->page; - - /* avoid re-using remote and pfmemalloc pages */ - if (!dev_page_is_reusable(page)) - return false; - -#if (PAGE_SIZE < 8192) - /* if we are only owner of page we can reuse it */ - if (unlikely((rx_buffer_pgcnt - pagecnt_bias) > 1)) - return false; -#endif - - /* If we have drained the page fragment pool we need to update - * the pagecnt_bias and page count so that we fully restock the - * number of references the driver holds. - */ - if (unlikely(pagecnt_bias == 1)) { - page_ref_add(page, USHRT_MAX - 1); - rx_buffer->pagecnt_bias = USHRT_MAX; - } - - return true; -} - -/** - * wx_reuse_rx_page - page flip buffer and store it back on the ring - * @rx_ring: rx descriptor ring to store buffers on - * @old_buff: donor buffer to have page reused - * - * Synchronizes page for reuse by the adapter - **/ -static void wx_reuse_rx_page(struct wx_ring *rx_ring, - struct wx_rx_buffer *old_buff) -{ - u16 nta = rx_ring->next_to_alloc; - struct wx_rx_buffer *new_buff; - - new_buff = &rx_ring->rx_buffer_info[nta]; - - /* update, and store next to alloc */ - nta++; - rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0; - - /* transfer page from old buffer to new buffer */ - new_buff->page = old_buff->page; - new_buff->page_dma = old_buff->page_dma; - new_buff->page_offset = old_buff->page_offset; - new_buff->pagecnt_bias = old_buff->pagecnt_bias; -} - static void wx_dma_sync_frag(struct wx_ring *rx_ring, struct wx_rx_buffer *rx_buffer) { @@ -270,8 +216,6 @@ static struct wx_rx_buffer *wx_get_rx_buffer(struct wx_ring *rx_ring, size, DMA_FROM_DEVICE); skip_sync: - rx_buffer->pagecnt_bias--; - return rx_buffer; } @@ -280,19 +224,9 @@ static void wx_put_rx_buffer(struct wx_ring *rx_ring, struct sk_buff *skb, int rx_buffer_pgcnt) { - if (wx_can_reuse_rx_page(rx_buffer, rx_buffer_pgcnt)) { - /* hand second half of page back to the ring */ - wx_reuse_rx_page(rx_ring, rx_buffer); - } else { - if (!IS_ERR(skb) && WX_CB(skb)->dma == rx_buffer->dma) - /* the page has been released from the ring */ - WX_CB(skb)->page_released = true; - else - page_pool_put_full_page(rx_ring->page_pool, rx_buffer->page, false); - - __page_frag_cache_drain(rx_buffer->page, - rx_buffer->pagecnt_bias); - } + if (!IS_ERR(skb) && WX_CB(skb)->dma == rx_buffer->dma) + /* the page has been released from the ring */ + WX_CB(skb)->page_released = true; /* clear contents of rx_buffer */ rx_buffer->page = NULL; @@ -335,11 +269,12 @@ static struct sk_buff *wx_build_skb(struct wx_ring *rx_ring, if (size <= WX_RXBUFFER_256) { memcpy(__skb_put(skb, size), page_addr, ALIGN(size, sizeof(long))); - rx_buffer->pagecnt_bias++; - + page_pool_put_full_page(rx_ring->page_pool, rx_buffer->page, true); return skb; } + skb_mark_for_recycle(skb); + if (!wx_test_staterr(rx_desc, WX_RXD_STAT_EOP)) WX_CB(skb)->dma = rx_buffer->dma; @@ -382,8 +317,6 @@ static bool wx_alloc_mapped_page(struct wx_ring *rx_ring, bi->page_dma = dma; bi->page = page; bi->page_offset = 0; - page_ref_add(page, USHRT_MAX - 1); - bi->pagecnt_bias = USHRT_MAX; return true; } @@ -723,7 +656,6 @@ static int wx_clean_rx_irq(struct wx_q_vector *q_vector, /* exit if we failed to retrieve a buffer */ if (!skb) { rx_ring->rx_stats.alloc_rx_buff_failed++; - rx_buffer->pagecnt_bias++; break; } @@ -2248,8 +2180,6 @@ static void wx_clean_rx_ring(struct wx_ring *rx_ring) /* free resources associated with mapping */ page_pool_put_full_page(rx_ring->page_pool, rx_buffer->page, false); - __page_frag_cache_drain(rx_buffer->page, - rx_buffer->pagecnt_bias); i++; rx_buffer++; diff --git a/drivers/net/ethernet/wangxun/libwx/wx_type.h b/drivers/net/ethernet/wangxun/libwx/wx_type.h index 165e82de772e..83f9bb7b3c22 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_type.h +++ b/drivers/net/ethernet/wangxun/libwx/wx_type.h @@ -787,7 +787,6 @@ struct wx_rx_buffer { dma_addr_t page_dma; struct page *page; unsigned int page_offset; - u16 pagecnt_bias; }; struct wx_queue_stats { diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 2ce74593d6e4..a42df2c1bd04 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1548,7 +1548,8 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, goto error; phy_resume(phydev); - phy_led_triggers_register(phydev); + if (!phydev->is_on_sfp_module) + phy_led_triggers_register(phydev); /** * If the external phy used by current mac interface is managed by @@ -1817,7 +1818,8 @@ void phy_detach(struct phy_device *phydev) } phydev->phylink = NULL; - phy_led_triggers_unregister(phydev); + if (!phydev->is_on_sfp_module) + phy_led_triggers_unregister(phydev); if (phydev->mdio.dev.driver) module_put(phydev->mdio.dev.driver->owner); diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 508d9a392ab1..f575f225d417 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -281,8 +281,10 @@ static int __team_options_register(struct team *team, return 0; inst_rollback: - for (i--; i >= 0; i--) + for (i--; i >= 0; i--) { __team_option_inst_del_option(team, dst_opts[i]); + list_del(&dst_opts[i]->list); + } i = option_count; alloc_rollback: diff --git a/drivers/net/usb/ax88172a.c b/drivers/net/usb/ax88172a.c index 3777c7e2e6fc..e47bb125048d 100644 --- a/drivers/net/usb/ax88172a.c +++ b/drivers/net/usb/ax88172a.c @@ -161,7 +161,9 @@ static int ax88172a_bind(struct usbnet *dev, struct usb_interface *intf) u8 buf[ETH_ALEN]; struct ax88172a_private *priv; - usbnet_get_endpoints(dev, intf); + ret = usbnet_get_endpoints(dev, intf); + if (ret) + return ret; priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (!priv) diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index 4ea0e155bb0d..5a1bf42ce156 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -173,6 +173,7 @@ struct ax88179_data { u8 in_pm; u32 wol_supported; u32 wolopts; + u8 disconnecting; }; struct ax88179_int_data { @@ -208,6 +209,7 @@ static int __ax88179_read_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index, { int ret; int (*fn)(struct usbnet *, u8, u8, u16, u16, void *, u16); + struct ax88179_data *ax179_data = dev->driver_priv; BUG_ON(!dev); @@ -219,7 +221,7 @@ static int __ax88179_read_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index, ret = fn(dev, cmd, USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE, value, index, data, size); - if (unlikely(ret < 0)) + if (unlikely((ret < 0) && !(ret == -ENODEV && ax179_data->disconnecting))) netdev_warn(dev->net, "Failed to read reg index 0x%04x: %d\n", index, ret); @@ -231,6 +233,7 @@ static int __ax88179_write_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index, { int ret; int (*fn)(struct usbnet *, u8, u8, u16, u16, const void *, u16); + struct ax88179_data *ax179_data = dev->driver_priv; BUG_ON(!dev); @@ -242,7 +245,7 @@ static int __ax88179_write_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index, ret = fn(dev, cmd, USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE, value, index, data, size); - if (unlikely(ret < 0)) + if (unlikely((ret < 0) && !(ret == -ENODEV && ax179_data->disconnecting))) netdev_warn(dev->net, "Failed to write reg index 0x%04x: %d\n", index, ret); @@ -492,6 +495,20 @@ static int ax88179_resume(struct usb_interface *intf) return usbnet_resume(intf); } +static void ax88179_disconnect(struct usb_interface *intf) +{ + struct usbnet *dev = usb_get_intfdata(intf); + struct ax88179_data *ax179_data; + + if (!dev) + return; + + ax179_data = dev->driver_priv; + ax179_data->disconnecting = 1; + + usbnet_disconnect(intf); +} + static void ax88179_get_wol(struct net_device *net, struct ethtool_wolinfo *wolinfo) { @@ -1906,7 +1923,7 @@ static struct usb_driver ax88179_178a_driver = { .suspend = ax88179_suspend, .resume = ax88179_resume, .reset_resume = ax88179_resume, - .disconnect = usbnet_disconnect, + .disconnect = ax88179_disconnect, .supports_autosuspend = 1, .disable_hub_initiated_lpm = 1, }; diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index d16f592c2061..51b1868d2f22 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -334,7 +334,6 @@ struct virtio_net_common_hdr { }; }; -static void virtnet_rq_free_unused_buf(struct virtqueue *vq, void *buf); static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf); static bool is_xdp_frame(void *ptr) @@ -408,6 +407,17 @@ static struct page *get_a_page(struct receive_queue *rq, gfp_t gfp_mask) return p; } +static void virtnet_rq_free_buf(struct virtnet_info *vi, + struct receive_queue *rq, void *buf) +{ + if (vi->mergeable_rx_bufs) + put_page(virt_to_head_page(buf)); + else if (vi->big_packets) + give_pages(rq, buf); + else + put_page(virt_to_head_page(buf)); +} + static void enable_delayed_refill(struct virtnet_info *vi) { spin_lock_bh(&vi->refill_lock); @@ -634,17 +644,6 @@ static void *virtnet_rq_get_buf(struct receive_queue *rq, u32 *len, void **ctx) return buf; } -static void *virtnet_rq_detach_unused_buf(struct receive_queue *rq) -{ - void *buf; - - buf = virtqueue_detach_unused_buf(rq->vq); - if (buf && rq->do_dma) - virtnet_rq_unmap(rq, buf, 0); - - return buf; -} - static void virtnet_rq_init_one_sg(struct receive_queue *rq, void *buf, u32 len) { struct virtnet_rq_dma *dma; @@ -744,6 +743,20 @@ static void virtnet_rq_set_premapped(struct virtnet_info *vi) } } +static void virtnet_rq_unmap_free_buf(struct virtqueue *vq, void *buf) +{ + struct virtnet_info *vi = vq->vdev->priv; + struct receive_queue *rq; + int i = vq2rxq(vq); + + rq = &vi->rq[i]; + + if (rq->do_dma) + virtnet_rq_unmap(rq, buf, 0); + + virtnet_rq_free_buf(vi, rq, buf); +} + static void free_old_xmit_skbs(struct send_queue *sq, bool in_napi) { unsigned int len; @@ -1764,7 +1777,7 @@ static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq, if (unlikely(len < vi->hdr_len + ETH_HLEN)) { pr_debug("%s: short packet %i\n", dev->name, len); DEV_STATS_INC(dev, rx_length_errors); - virtnet_rq_free_unused_buf(rq->vq, buf); + virtnet_rq_free_buf(vi, rq, buf); return; } @@ -2392,7 +2405,7 @@ static int virtnet_rx_resize(struct virtnet_info *vi, if (running) napi_disable(&rq->napi); - err = virtqueue_resize(rq->vq, ring_num, virtnet_rq_free_unused_buf); + err = virtqueue_resize(rq->vq, ring_num, virtnet_rq_unmap_free_buf); if (err) netdev_err(vi->dev, "resize rx fail: rx queue index: %d err: %d\n", qindex, err); @@ -4031,19 +4044,6 @@ static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf) xdp_return_frame(ptr_to_xdp(buf)); } -static void virtnet_rq_free_unused_buf(struct virtqueue *vq, void *buf) -{ - struct virtnet_info *vi = vq->vdev->priv; - int i = vq2rxq(vq); - - if (vi->mergeable_rx_bufs) - put_page(virt_to_head_page(buf)); - else if (vi->big_packets) - give_pages(&vi->rq[i], buf); - else - put_page(virt_to_head_page(buf)); -} - static void free_unused_bufs(struct virtnet_info *vi) { void *buf; @@ -4057,10 +4057,10 @@ static void free_unused_bufs(struct virtnet_info *vi) } for (i = 0; i < vi->max_queue_pairs; i++) { - struct receive_queue *rq = &vi->rq[i]; + struct virtqueue *vq = vi->rq[i].vq; - while ((buf = virtnet_rq_detach_unused_buf(rq)) != NULL) - virtnet_rq_free_unused_buf(rq->vq, buf); + while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) + virtnet_rq_unmap_free_buf(vq, buf); cond_resched(); } } diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h index 56def20374f3..7805a42948af 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h +++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h @@ -770,7 +770,7 @@ static inline void iwl_enable_rfkill_int(struct iwl_trans *trans) } } -void iwl_pcie_handle_rfkill_irq(struct iwl_trans *trans); +void iwl_pcie_handle_rfkill_irq(struct iwl_trans *trans, bool from_irq); static inline bool iwl_is_rfkill_set(struct iwl_trans *trans) { @@ -817,7 +817,7 @@ static inline bool iwl_pcie_dbg_on(struct iwl_trans *trans) return (trans->dbg.dest_tlv || iwl_trans_dbg_ini_valid(trans)); } -void iwl_trans_pcie_rf_kill(struct iwl_trans *trans, bool state); +void iwl_trans_pcie_rf_kill(struct iwl_trans *trans, bool state, bool from_irq); void iwl_trans_pcie_dump_regs(struct iwl_trans *trans); #ifdef CONFIG_IWLWIFI_DEBUGFS diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c index 146bc7bd14fb..07931c2db494 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c @@ -1385,7 +1385,7 @@ static void iwl_pcie_rx_handle_rb(struct iwl_trans *trans, * if it is true then one of the handlers took the page. */ - if (reclaim) { + if (reclaim && txq) { u16 sequence = le16_to_cpu(pkt->hdr.sequence); int index = SEQ_TO_INDEX(sequence); int cmd_index = iwl_txq_get_cmd_index(txq, index); @@ -1783,7 +1783,7 @@ static u32 iwl_pcie_int_cause_ict(struct iwl_trans *trans) return inta; } -void iwl_pcie_handle_rfkill_irq(struct iwl_trans *trans) +void iwl_pcie_handle_rfkill_irq(struct iwl_trans *trans, bool from_irq) { struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); struct isr_statistics *isr_stats = &trans_pcie->isr_stats; @@ -1807,7 +1807,7 @@ void iwl_pcie_handle_rfkill_irq(struct iwl_trans *trans) isr_stats->rfkill++; if (prev != report) - iwl_trans_pcie_rf_kill(trans, report); + iwl_trans_pcie_rf_kill(trans, report, from_irq); mutex_unlock(&trans_pcie->mutex); if (hw_rfkill) { @@ -1947,7 +1947,7 @@ irqreturn_t iwl_pcie_irq_handler(int irq, void *dev_id) /* HW RF KILL switch toggled */ if (inta & CSR_INT_BIT_RF_KILL) { - iwl_pcie_handle_rfkill_irq(trans); + iwl_pcie_handle_rfkill_irq(trans, true); handled |= CSR_INT_BIT_RF_KILL; } @@ -2370,7 +2370,7 @@ irqreturn_t iwl_pcie_irq_msix_handler(int irq, void *dev_id) /* HW RF KILL switch toggled */ if (inta_hw & MSIX_HW_INT_CAUSES_REG_RF_KILL) - iwl_pcie_handle_rfkill_irq(trans); + iwl_pcie_handle_rfkill_irq(trans, true); if (inta_hw & MSIX_HW_INT_CAUSES_REG_HW_ERR) { IWL_ERR(trans, diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c index a468e5efeecd..d10208075ae5 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c @@ -1082,7 +1082,7 @@ bool iwl_pcie_check_hw_rf_kill(struct iwl_trans *trans) report = test_bit(STATUS_RFKILL_OPMODE, &trans->status); if (prev != report) - iwl_trans_pcie_rf_kill(trans, report); + iwl_trans_pcie_rf_kill(trans, report, false); return hw_rfkill; } @@ -1237,7 +1237,7 @@ static void iwl_pcie_init_msix(struct iwl_trans_pcie *trans_pcie) trans_pcie->hw_mask = trans_pcie->hw_init_mask; } -static void _iwl_trans_pcie_stop_device(struct iwl_trans *trans) +static void _iwl_trans_pcie_stop_device(struct iwl_trans *trans, bool from_irq) { struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); @@ -1264,7 +1264,8 @@ static void _iwl_trans_pcie_stop_device(struct iwl_trans *trans) if (test_and_clear_bit(STATUS_DEVICE_ENABLED, &trans->status)) { IWL_DEBUG_INFO(trans, "DEVICE_ENABLED bit was set and is now cleared\n"); - iwl_pcie_synchronize_irqs(trans); + if (!from_irq) + iwl_pcie_synchronize_irqs(trans); iwl_pcie_rx_napi_sync(trans); iwl_pcie_tx_stop(trans); iwl_pcie_rx_stop(trans); @@ -1454,7 +1455,7 @@ void iwl_trans_pcie_handle_stop_rfkill(struct iwl_trans *trans, clear_bit(STATUS_RFKILL_OPMODE, &trans->status); } if (hw_rfkill != was_in_rfkill) - iwl_trans_pcie_rf_kill(trans, hw_rfkill); + iwl_trans_pcie_rf_kill(trans, hw_rfkill, false); } static void iwl_trans_pcie_stop_device(struct iwl_trans *trans) @@ -1469,12 +1470,12 @@ static void iwl_trans_pcie_stop_device(struct iwl_trans *trans) mutex_lock(&trans_pcie->mutex); trans_pcie->opmode_down = true; was_in_rfkill = test_bit(STATUS_RFKILL_OPMODE, &trans->status); - _iwl_trans_pcie_stop_device(trans); + _iwl_trans_pcie_stop_device(trans, false); iwl_trans_pcie_handle_stop_rfkill(trans, was_in_rfkill); mutex_unlock(&trans_pcie->mutex); } -void iwl_trans_pcie_rf_kill(struct iwl_trans *trans, bool state) +void iwl_trans_pcie_rf_kill(struct iwl_trans *trans, bool state, bool from_irq) { struct iwl_trans_pcie __maybe_unused *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); @@ -1487,7 +1488,7 @@ void iwl_trans_pcie_rf_kill(struct iwl_trans *trans, bool state) if (trans->trans_cfg->gen2) _iwl_trans_pcie_gen2_stop_device(trans); else - _iwl_trans_pcie_stop_device(trans); + _iwl_trans_pcie_stop_device(trans, from_irq); } } @@ -2887,7 +2888,7 @@ static ssize_t iwl_dbgfs_rfkill_write(struct file *file, IWL_WARN(trans, "changing debug rfkill %d->%d\n", trans_pcie->debug_rfkill, new_value); trans_pcie->debug_rfkill = new_value; - iwl_pcie_handle_rfkill_irq(trans); + iwl_pcie_handle_rfkill_irq(trans, false); return count; } @@ -3106,7 +3107,7 @@ static u32 iwl_trans_pcie_dump_rbs(struct iwl_trans *trans, struct iwl_rxq *rxq = &trans_pcie->rxq[0]; u32 i, r, j, rb_len = 0; - spin_lock(&rxq->lock); + spin_lock_bh(&rxq->lock); r = iwl_get_closed_rb_stts(trans, rxq); @@ -3130,7 +3131,7 @@ static u32 iwl_trans_pcie_dump_rbs(struct iwl_trans *trans, *data = iwl_fw_error_next_data(*data); } - spin_unlock(&rxq->lock); + spin_unlock_bh(&rxq->lock); return rb_len; } diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c index 511fe7e6e744..68ad915203aa 100644 --- a/drivers/net/wireless/mediatek/mt76/dma.c +++ b/drivers/net/wireless/mediatek/mt76/dma.c @@ -783,7 +783,7 @@ mt76_dma_rx_reset(struct mt76_dev *dev, enum mt76_rxq_id qid) static void mt76_add_fragment(struct mt76_dev *dev, struct mt76_queue *q, void *data, - int len, bool more, u32 info) + int len, bool more, u32 info, bool allow_direct) { struct sk_buff *skb = q->rx_head; struct skb_shared_info *shinfo = skb_shinfo(skb); @@ -795,7 +795,7 @@ mt76_add_fragment(struct mt76_dev *dev, struct mt76_queue *q, void *data, skb_add_rx_frag(skb, nr_frags, page, offset, len, q->buf_size); } else { - mt76_put_page_pool_buf(data, true); + mt76_put_page_pool_buf(data, allow_direct); } if (more) @@ -815,6 +815,7 @@ mt76_dma_rx_process(struct mt76_dev *dev, struct mt76_queue *q, int budget) struct sk_buff *skb; unsigned char *data; bool check_ddone = false; + bool allow_direct = !mt76_queue_is_wed_rx(q); bool more; if (IS_ENABLED(CONFIG_NET_MEDIATEK_SOC_WED) && @@ -855,7 +856,8 @@ mt76_dma_rx_process(struct mt76_dev *dev, struct mt76_queue *q, int budget) } if (q->rx_head) { - mt76_add_fragment(dev, q, data, len, more, info); + mt76_add_fragment(dev, q, data, len, more, info, + allow_direct); continue; } @@ -884,7 +886,7 @@ mt76_dma_rx_process(struct mt76_dev *dev, struct mt76_queue *q, int budget) continue; free_frag: - mt76_put_page_pool_buf(data, true); + mt76_put_page_pool_buf(data, allow_direct); } mt76_dma_rx_fill(dev, q, true); diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 8ebdfd623e0f..60f14019f981 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -4137,6 +4137,8 @@ static void nvme_fw_act_work(struct work_struct *work) struct nvme_ctrl, fw_act_work); unsigned long fw_act_timeout; + nvme_auth_stop(ctrl); + if (ctrl->mtfa) fw_act_timeout = jiffies + msecs_to_jiffies(ctrl->mtfa * 100); @@ -4192,7 +4194,6 @@ static bool nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result) * firmware activation. */ if (nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING)) { - nvme_auth_stop(ctrl); requeue = false; queue_work(nvme_wq, &ctrl->fw_act_work); } diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index fb22976a36a8..1d51925ea67f 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -2548,24 +2548,17 @@ nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg) * the controller. Abort any ios on the association and let the * create_association error path resolve things. */ - enum nvme_ctrl_state state; - unsigned long flags; - - spin_lock_irqsave(&ctrl->lock, flags); - state = ctrl->ctrl.state; - if (state == NVME_CTRL_CONNECTING) { - set_bit(ASSOC_FAILED, &ctrl->flags); - spin_unlock_irqrestore(&ctrl->lock, flags); + if (ctrl->ctrl.state == NVME_CTRL_CONNECTING) { __nvme_fc_abort_outstanding_ios(ctrl, true); + set_bit(ASSOC_FAILED, &ctrl->flags); dev_warn(ctrl->ctrl.device, "NVME-FC{%d}: transport error during (re)connect\n", ctrl->cnum); return; } - spin_unlock_irqrestore(&ctrl->lock, flags); /* Otherwise, only proceed if in LIVE state - e.g. on first error */ - if (state != NVME_CTRL_LIVE) + if (ctrl->ctrl.state != NVME_CTRL_LIVE) return; dev_warn(ctrl->ctrl.device, @@ -3180,16 +3173,12 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) else ret = nvme_fc_recreate_io_queues(ctrl); } - - spin_lock_irqsave(&ctrl->lock, flags); if (!ret && test_bit(ASSOC_FAILED, &ctrl->flags)) ret = -EIO; - if (ret) { - spin_unlock_irqrestore(&ctrl->lock, flags); + if (ret) goto out_term_aen_ops; - } + changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE); - spin_unlock_irqrestore(&ctrl->lock, flags); ctrl->ctrl.nr_reconnects = 0; diff --git a/drivers/nvmem/brcm_nvram.c b/drivers/nvmem/brcm_nvram.c index 9737104f3b76..5cdf339cfbec 100644 --- a/drivers/nvmem/brcm_nvram.c +++ b/drivers/nvmem/brcm_nvram.c @@ -17,9 +17,23 @@ #define NVRAM_MAGIC "FLSH" +/** + * struct brcm_nvram - driver state internal struct + * + * @dev: NVMEM device pointer + * @nvmem_size: Size of the whole space available for NVRAM + * @data: NVRAM data copy stored to avoid poking underlaying flash controller + * @data_len: NVRAM data size + * @padding_byte: Padding value used to fill remaining space + * @cells: Array of discovered NVMEM cells + * @ncells: Number of elements in cells + */ struct brcm_nvram { struct device *dev; - void __iomem *base; + size_t nvmem_size; + uint8_t *data; + size_t data_len; + uint8_t padding_byte; struct nvmem_cell_info *cells; int ncells; }; @@ -36,10 +50,47 @@ static int brcm_nvram_read(void *context, unsigned int offset, void *val, size_t bytes) { struct brcm_nvram *priv = context; - u8 *dst = val; + size_t to_copy; + + if (offset + bytes > priv->data_len) + to_copy = max_t(ssize_t, (ssize_t)priv->data_len - offset, 0); + else + to_copy = bytes; + + memcpy(val, priv->data + offset, to_copy); + + memset((uint8_t *)val + to_copy, priv->padding_byte, bytes - to_copy); + + return 0; +} + +static int brcm_nvram_copy_data(struct brcm_nvram *priv, struct platform_device *pdev) +{ + struct resource *res; + void __iomem *base; + + base = devm_platform_get_and_ioremap_resource(pdev, 0, &res); + if (IS_ERR(base)) + return PTR_ERR(base); + + priv->nvmem_size = resource_size(res); + + priv->padding_byte = readb(base + priv->nvmem_size - 1); + for (priv->data_len = priv->nvmem_size; + priv->data_len; + priv->data_len--) { + if (readb(base + priv->data_len - 1) != priv->padding_byte) + break; + } + WARN(priv->data_len > SZ_128K, "Unexpected (big) NVRAM size: %zu B\n", priv->data_len); + + priv->data = devm_kzalloc(priv->dev, priv->data_len, GFP_KERNEL); + if (!priv->data) + return -ENOMEM; + + memcpy_fromio(priv->data, base, priv->data_len); - while (bytes--) - *dst++ = readb(priv->base + offset++); + bcm47xx_nvram_init_from_iomem(base, priv->data_len); return 0; } @@ -67,8 +118,13 @@ static int brcm_nvram_add_cells(struct brcm_nvram *priv, uint8_t *data, size_t len) { struct device *dev = priv->dev; - char *var, *value, *eq; + char *var, *value; + uint8_t tmp; int idx; + int err = 0; + + tmp = priv->data[len - 1]; + priv->data[len - 1] = '\0'; priv->ncells = 0; for (var = data + sizeof(struct brcm_nvram_header); @@ -78,67 +134,68 @@ static int brcm_nvram_add_cells(struct brcm_nvram *priv, uint8_t *data, } priv->cells = devm_kcalloc(dev, priv->ncells, sizeof(*priv->cells), GFP_KERNEL); - if (!priv->cells) - return -ENOMEM; + if (!priv->cells) { + err = -ENOMEM; + goto out; + } for (var = data + sizeof(struct brcm_nvram_header), idx = 0; var < (char *)data + len && *var; var = value + strlen(value) + 1, idx++) { + char *eq, *name; + eq = strchr(var, '='); if (!eq) break; *eq = '\0'; + name = devm_kstrdup(dev, var, GFP_KERNEL); + *eq = '='; + if (!name) { + err = -ENOMEM; + goto out; + } value = eq + 1; - priv->cells[idx].name = devm_kstrdup(dev, var, GFP_KERNEL); - if (!priv->cells[idx].name) - return -ENOMEM; + priv->cells[idx].name = name; priv->cells[idx].offset = value - (char *)data; priv->cells[idx].bytes = strlen(value); priv->cells[idx].np = of_get_child_by_name(dev->of_node, priv->cells[idx].name); - if (!strcmp(var, "et0macaddr") || - !strcmp(var, "et1macaddr") || - !strcmp(var, "et2macaddr")) { + if (!strcmp(name, "et0macaddr") || + !strcmp(name, "et1macaddr") || + !strcmp(name, "et2macaddr")) { priv->cells[idx].raw_len = strlen(value); priv->cells[idx].bytes = ETH_ALEN; priv->cells[idx].read_post_process = brcm_nvram_read_post_process_macaddr; } } - return 0; +out: + priv->data[len - 1] = tmp; + return err; } static int brcm_nvram_parse(struct brcm_nvram *priv) { + struct brcm_nvram_header *header = (struct brcm_nvram_header *)priv->data; struct device *dev = priv->dev; - struct brcm_nvram_header header; - uint8_t *data; size_t len; int err; - memcpy_fromio(&header, priv->base, sizeof(header)); - - if (memcmp(header.magic, NVRAM_MAGIC, 4)) { + if (memcmp(header->magic, NVRAM_MAGIC, 4)) { dev_err(dev, "Invalid NVRAM magic\n"); return -EINVAL; } - len = le32_to_cpu(header.len); - - data = kzalloc(len, GFP_KERNEL); - if (!data) - return -ENOMEM; - - memcpy_fromio(data, priv->base, len); - data[len - 1] = '\0'; - - err = brcm_nvram_add_cells(priv, data, len); - if (err) { - dev_err(dev, "Failed to add cells: %d\n", err); - return err; + len = le32_to_cpu(header->len); + if (len > priv->nvmem_size) { + dev_err(dev, "NVRAM length (%zd) exceeds mapped size (%zd)\n", len, + priv->nvmem_size); + return -EINVAL; } - kfree(data); + err = brcm_nvram_add_cells(priv, priv->data, len); + if (err) + dev_err(dev, "Failed to add cells: %d\n", err); return 0; } @@ -150,7 +207,6 @@ static int brcm_nvram_probe(struct platform_device *pdev) .reg_read = brcm_nvram_read, }; struct device *dev = &pdev->dev; - struct resource *res; struct brcm_nvram *priv; int err; @@ -159,21 +215,19 @@ static int brcm_nvram_probe(struct platform_device *pdev) return -ENOMEM; priv->dev = dev; - priv->base = devm_platform_get_and_ioremap_resource(pdev, 0, &res); - if (IS_ERR(priv->base)) - return PTR_ERR(priv->base); + err = brcm_nvram_copy_data(priv, pdev); + if (err) + return err; err = brcm_nvram_parse(priv); if (err) return err; - bcm47xx_nvram_init_from_iomem(priv->base, resource_size(res)); - config.dev = dev; config.cells = priv->cells; config.ncells = priv->ncells; config.priv = priv; - config.size = resource_size(res); + config.size = priv->nvmem_size; return PTR_ERR_OR_ZERO(devm_nvmem_register(dev, &config)); } diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c index 6902e97719d1..11c80555d975 100644 --- a/drivers/pci/controller/dwc/pcie-qcom.c +++ b/drivers/pci/controller/dwc/pcie-qcom.c @@ -968,9 +968,12 @@ static int qcom_pcie_post_init_2_7_0(struct qcom_pcie *pcie) static int qcom_pcie_enable_aspm(struct pci_dev *pdev, void *userdata) { - /* Downstream devices need to be in D0 state before enabling PCI PM substates */ + /* + * Downstream devices need to be in D0 state before enabling PCI PM + * substates. + */ pci_set_power_state(pdev, PCI_D0); - pci_enable_link_state(pdev, PCIE_LINK_STATE_ALL); + pci_enable_link_state_locked(pdev, PCIE_LINK_STATE_ALL); return 0; } diff --git a/drivers/pci/controller/pci-loongson.c b/drivers/pci/controller/pci-loongson.c index d45e7b8dc530..8b34ccff073a 100644 --- a/drivers/pci/controller/pci-loongson.c +++ b/drivers/pci/controller/pci-loongson.c @@ -80,13 +80,49 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, DEV_LS7A_LPC, system_bus_quirk); +/* + * Some Loongson PCIe ports have hardware limitations on their Maximum Read + * Request Size. They can't handle anything larger than this. Sane + * firmware will set proper MRRS at boot, so we only need no_inc_mrrs for + * bridges. However, some MIPS Loongson firmware doesn't set MRRS properly, + * so we have to enforce maximum safe MRRS, which is 256 bytes. + */ +#ifdef CONFIG_MIPS +static void loongson_set_min_mrrs_quirk(struct pci_dev *pdev) +{ + struct pci_bus *bus = pdev->bus; + struct pci_dev *bridge; + static const struct pci_device_id bridge_devids[] = { + { PCI_VDEVICE(LOONGSON, DEV_LS2K_PCIE_PORT0) }, + { PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT0) }, + { PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT1) }, + { PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT2) }, + { PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT3) }, + { PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT4) }, + { PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT5) }, + { PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT6) }, + { 0, }, + }; + + /* look for the matching bridge */ + while (!pci_is_root_bus(bus)) { + bridge = bus->self; + bus = bus->parent; + + if (pci_match_id(bridge_devids, bridge)) { + if (pcie_get_readrq(pdev) > 256) { + pci_info(pdev, "limiting MRRS to 256\n"); + pcie_set_readrq(pdev, 256); + } + break; + } + } +} +DECLARE_PCI_FIXUP_ENABLE(PCI_ANY_ID, PCI_ANY_ID, loongson_set_min_mrrs_quirk); +#endif + static void loongson_mrrs_quirk(struct pci_dev *pdev) { - /* - * Some Loongson PCIe ports have h/w limitations of maximum read - * request size. They can't handle anything larger than this. So - * force this limit on any devices attached under these ports. - */ struct pci_host_bridge *bridge = pci_find_host_bridge(pdev->bus); bridge->no_inc_mrrs = 1; diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c index 94ba61fe1c44..0452cbc362ee 100644 --- a/drivers/pci/controller/vmd.c +++ b/drivers/pci/controller/vmd.c @@ -751,7 +751,7 @@ static int vmd_pm_enable_quirk(struct pci_dev *pdev, void *userdata) if (!(features & VMD_FEAT_BIOS_PM_QUIRK)) return 0; - pci_enable_link_state(pdev, PCIE_LINK_STATE_ALL); + pci_enable_link_state_locked(pdev, PCIE_LINK_STATE_ALL); pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_LTR); if (!pos) diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c index 601129772b2d..5b1f271c6034 100644 --- a/drivers/pci/hotplug/acpiphp_glue.c +++ b/drivers/pci/hotplug/acpiphp_glue.c @@ -512,15 +512,12 @@ static void enable_slot(struct acpiphp_slot *slot, bool bridge) if (pass && dev->subordinate) { check_hotplug_bridge(slot, dev); pcibios_resource_survey_bus(dev->subordinate); - if (pci_is_root_bus(bus)) - __pci_bus_size_bridges(dev->subordinate, &add_list); + __pci_bus_size_bridges(dev->subordinate, + &add_list); } } } - if (pci_is_root_bus(bus)) - __pci_bus_assign_resources(bus, &add_list, NULL); - else - pci_assign_unassigned_bridge_resources(bus->self); + __pci_bus_assign_resources(bus, &add_list, NULL); } acpiphp_sanitize_bus(bus); diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 55bc3576a985..bdbf8a94b4d0 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1335,6 +1335,9 @@ static int pci_set_full_power_state(struct pci_dev *dev) pci_restore_bars(dev); } + if (dev->bus->self) + pcie_aspm_pm_state_change(dev->bus->self); + return 0; } @@ -1429,6 +1432,9 @@ static int pci_set_low_power_state(struct pci_dev *dev, pci_power_t state) pci_power_name(dev->current_state), pci_power_name(state)); + if (dev->bus->self) + pcie_aspm_pm_state_change(dev->bus->self); + return 0; } diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 5ecbcf041179..f43873049d52 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -569,10 +569,12 @@ int pcie_retrain_link(struct pci_dev *pdev, bool use_lt); #ifdef CONFIG_PCIEASPM void pcie_aspm_init_link_state(struct pci_dev *pdev); void pcie_aspm_exit_link_state(struct pci_dev *pdev); +void pcie_aspm_pm_state_change(struct pci_dev *pdev); void pcie_aspm_powersave_config_link(struct pci_dev *pdev); #else static inline void pcie_aspm_init_link_state(struct pci_dev *pdev) { } static inline void pcie_aspm_exit_link_state(struct pci_dev *pdev) { } +static inline void pcie_aspm_pm_state_change(struct pci_dev *pdev) { } static inline void pcie_aspm_powersave_config_link(struct pci_dev *pdev) { } #endif diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index 50b04ae5c394..060f4b3c8698 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -1008,6 +1008,25 @@ void pcie_aspm_exit_link_state(struct pci_dev *pdev) up_read(&pci_bus_sem); } +/* @pdev: the root port or switch downstream port */ +void pcie_aspm_pm_state_change(struct pci_dev *pdev) +{ + struct pcie_link_state *link = pdev->link_state; + + if (aspm_disabled || !link) + return; + /* + * Devices changed PM state, we should recheck if latency + * meets all functions' requirement + */ + down_read(&pci_bus_sem); + mutex_lock(&aspm_lock); + pcie_update_aspm_capable(link->root); + pcie_config_aspm_path(link); + mutex_unlock(&aspm_lock); + up_read(&pci_bus_sem); +} + void pcie_aspm_powersave_config_link(struct pci_dev *pdev) { struct pcie_link_state *link = pdev->link_state; @@ -1041,7 +1060,7 @@ static struct pcie_link_state *pcie_aspm_get_link(struct pci_dev *pdev) return bridge->link_state; } -static int __pci_disable_link_state(struct pci_dev *pdev, int state, bool sem) +static int __pci_disable_link_state(struct pci_dev *pdev, int state, bool locked) { struct pcie_link_state *link = pcie_aspm_get_link(pdev); @@ -1060,7 +1079,7 @@ static int __pci_disable_link_state(struct pci_dev *pdev, int state, bool sem) return -EPERM; } - if (sem) + if (!locked) down_read(&pci_bus_sem); mutex_lock(&aspm_lock); if (state & PCIE_LINK_STATE_L0S) @@ -1082,7 +1101,7 @@ static int __pci_disable_link_state(struct pci_dev *pdev, int state, bool sem) link->clkpm_disable = 1; pcie_set_clkpm(link, policy_to_clkpm_state(link)); mutex_unlock(&aspm_lock); - if (sem) + if (!locked) up_read(&pci_bus_sem); return 0; @@ -1090,7 +1109,9 @@ static int __pci_disable_link_state(struct pci_dev *pdev, int state, bool sem) int pci_disable_link_state_locked(struct pci_dev *pdev, int state) { - return __pci_disable_link_state(pdev, state, false); + lockdep_assert_held_read(&pci_bus_sem); + + return __pci_disable_link_state(pdev, state, true); } EXPORT_SYMBOL(pci_disable_link_state_locked); @@ -1105,21 +1126,11 @@ EXPORT_SYMBOL(pci_disable_link_state_locked); */ int pci_disable_link_state(struct pci_dev *pdev, int state) { - return __pci_disable_link_state(pdev, state, true); + return __pci_disable_link_state(pdev, state, false); } EXPORT_SYMBOL(pci_disable_link_state); -/** - * pci_enable_link_state - Clear and set the default device link state so that - * the link may be allowed to enter the specified states. Note that if the - * BIOS didn't grant ASPM control to the OS, this does nothing because we can't - * touch the LNKCTL register. Also note that this does not enable states - * disabled by pci_disable_link_state(). Return 0 or a negative errno. - * - * @pdev: PCI device - * @state: Mask of ASPM link states to enable - */ -int pci_enable_link_state(struct pci_dev *pdev, int state) +static int __pci_enable_link_state(struct pci_dev *pdev, int state, bool locked) { struct pcie_link_state *link = pcie_aspm_get_link(pdev); @@ -1136,7 +1147,8 @@ int pci_enable_link_state(struct pci_dev *pdev, int state) return -EPERM; } - down_read(&pci_bus_sem); + if (!locked) + down_read(&pci_bus_sem); mutex_lock(&aspm_lock); link->aspm_default = 0; if (state & PCIE_LINK_STATE_L0S) @@ -1157,12 +1169,48 @@ int pci_enable_link_state(struct pci_dev *pdev, int state) link->clkpm_default = (state & PCIE_LINK_STATE_CLKPM) ? 1 : 0; pcie_set_clkpm(link, policy_to_clkpm_state(link)); mutex_unlock(&aspm_lock); - up_read(&pci_bus_sem); + if (!locked) + up_read(&pci_bus_sem); return 0; } + +/** + * pci_enable_link_state - Clear and set the default device link state so that + * the link may be allowed to enter the specified states. Note that if the + * BIOS didn't grant ASPM control to the OS, this does nothing because we can't + * touch the LNKCTL register. Also note that this does not enable states + * disabled by pci_disable_link_state(). Return 0 or a negative errno. + * + * @pdev: PCI device + * @state: Mask of ASPM link states to enable + */ +int pci_enable_link_state(struct pci_dev *pdev, int state) +{ + return __pci_enable_link_state(pdev, state, false); +} EXPORT_SYMBOL(pci_enable_link_state); +/** + * pci_enable_link_state_locked - Clear and set the default device link state + * so that the link may be allowed to enter the specified states. Note that if + * the BIOS didn't grant ASPM control to the OS, this does nothing because we + * can't touch the LNKCTL register. Also note that this does not enable states + * disabled by pci_disable_link_state(). Return 0 or a negative errno. + * + * @pdev: PCI device + * @state: Mask of ASPM link states to enable + * + * Context: Caller holds pci_bus_sem read lock. + */ +int pci_enable_link_state_locked(struct pci_dev *pdev, int state) +{ + lockdep_assert_held_read(&pci_bus_sem); + + return __pci_enable_link_state(pdev, state, true); +} +EXPORT_SYMBOL(pci_enable_link_state_locked); + static int pcie_aspm_set_policy(const char *val, const struct kernel_param *kp) { diff --git a/drivers/perf/arm-cmn.c b/drivers/perf/arm-cmn.c index 014010d03588..847b0dc41293 100644 --- a/drivers/perf/arm-cmn.c +++ b/drivers/perf/arm-cmn.c @@ -1816,7 +1816,7 @@ static int arm_cmn_event_add(struct perf_event *event, int flags) idx = 0; while (cmn->dtc[j].counters[idx]) if (++idx == CMN_DT_NUM_COUNTERS) - goto free_dtms; + return -ENOSPC; } hw->dtc_idx[j] = idx; } diff --git a/drivers/phy/mediatek/phy-mtk-mipi-dsi-mt8183.c b/drivers/phy/mediatek/phy-mtk-mipi-dsi-mt8183.c index f021ec5a70e5..553725e1269c 100644 --- a/drivers/phy/mediatek/phy-mtk-mipi-dsi-mt8183.c +++ b/drivers/phy/mediatek/phy-mtk-mipi-dsi-mt8183.c @@ -100,7 +100,7 @@ static void mtk_mipi_tx_pll_disable(struct clk_hw *hw) static long mtk_mipi_tx_pll_round_rate(struct clk_hw *hw, unsigned long rate, unsigned long *prate) { - return clamp_val(rate, 50000000, 1600000000); + return clamp_val(rate, 125000000, 1600000000); } static const struct clk_ops mtk_mipi_tx_pll_ops = { diff --git a/drivers/phy/sunplus/phy-sunplus-usb2.c b/drivers/phy/sunplus/phy-sunplus-usb2.c index 0efe74ac9c6a..637a5fbae6d9 100644 --- a/drivers/phy/sunplus/phy-sunplus-usb2.c +++ b/drivers/phy/sunplus/phy-sunplus-usb2.c @@ -275,7 +275,7 @@ static int sp_usb_phy_probe(struct platform_device *pdev) phy = devm_phy_create(&pdev->dev, NULL, &sp_uphy_ops); if (IS_ERR(phy)) { - ret = -PTR_ERR(phy); + ret = PTR_ERR(phy); return ret; } diff --git a/drivers/phy/ti/phy-gmii-sel.c b/drivers/phy/ti/phy-gmii-sel.c index 555b323f45da..bc847d3879f7 100644 --- a/drivers/phy/ti/phy-gmii-sel.c +++ b/drivers/phy/ti/phy-gmii-sel.c @@ -64,6 +64,7 @@ struct phy_gmii_sel_priv { u32 num_ports; u32 reg_offset; u32 qsgmii_main_ports; + bool no_offset; }; static int phy_gmii_sel_mode(struct phy *phy, enum phy_mode mode, int submode) @@ -402,7 +403,8 @@ static int phy_gmii_sel_init_ports(struct phy_gmii_sel_priv *priv) priv->num_ports = size / sizeof(u32); if (!priv->num_ports) return -EINVAL; - priv->reg_offset = __be32_to_cpu(*offset); + if (!priv->no_offset) + priv->reg_offset = __be32_to_cpu(*offset); } if_phys = devm_kcalloc(dev, priv->num_ports, @@ -471,6 +473,7 @@ static int phy_gmii_sel_probe(struct platform_device *pdev) dev_err(dev, "Failed to get syscon %d\n", ret); return ret; } + priv->no_offset = true; } ret = phy_gmii_sel_init_ports(priv); diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index fb58acb843d9..03ecb3d1aaf6 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -923,6 +923,15 @@ static int amd_gpio_suspend(struct device *dev) raw_spin_lock_irqsave(&gpio_dev->lock, flags); gpio_dev->saved_regs[i] = readl(gpio_dev->base + pin * 4) & ~PIN_IRQ_PENDING; + + /* mask any interrupts not intended to be a wake source */ + if (!(gpio_dev->saved_regs[i] & WAKE_SOURCE)) { + writel(gpio_dev->saved_regs[i] & ~BIT(INTERRUPT_MASK_OFF), + gpio_dev->base + pin * 4); + pm_pr_dbg("Disabling GPIO #%d interrupt for suspend.\n", + pin); + } + raw_spin_unlock_irqrestore(&gpio_dev->lock, flags); } diff --git a/drivers/pinctrl/pinctrl-amd.h b/drivers/pinctrl/pinctrl-amd.h index 34c5c3e71fb2..cf59089f2776 100644 --- a/drivers/pinctrl/pinctrl-amd.h +++ b/drivers/pinctrl/pinctrl-amd.h @@ -80,6 +80,11 @@ #define FUNCTION_MASK GENMASK(1, 0) #define FUNCTION_INVALID GENMASK(7, 0) +#define WAKE_SOURCE (BIT(WAKE_CNTRL_OFF_S0I3) | \ + BIT(WAKE_CNTRL_OFF_S3) | \ + BIT(WAKE_CNTRL_OFF_S4) | \ + BIT(WAKECNTRL_Z_OFF)) + struct amd_function { const char *name; const char * const groups[NSELECTS]; diff --git a/drivers/pinctrl/pinctrl-at91-pio4.c b/drivers/pinctrl/pinctrl-at91-pio4.c index 383309e533c3..a27c01fcbb47 100644 --- a/drivers/pinctrl/pinctrl-at91-pio4.c +++ b/drivers/pinctrl/pinctrl-at91-pio4.c @@ -1068,6 +1068,13 @@ static const struct of_device_id atmel_pctrl_of_match[] = { } }; +/* + * This lock class allows to tell lockdep that parent IRQ and children IRQ do + * not share the same class so it does not raise false positive + */ +static struct lock_class_key atmel_lock_key; +static struct lock_class_key atmel_request_key; + static int atmel_pinctrl_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -1214,6 +1221,7 @@ static int atmel_pinctrl_probe(struct platform_device *pdev) irq_set_chip_and_handler(irq, &atmel_gpio_irq_chip, handle_simple_irq); irq_set_chip_data(irq, atmel_pioctrl); + irq_set_lockdep_class(irq, &atmel_lock_key, &atmel_request_key); dev_dbg(dev, "atmel gpio irq domain: hwirq: %d, linux irq: %d\n", i, irq); diff --git a/drivers/pinctrl/pinctrl-cy8c95x0.c b/drivers/pinctrl/pinctrl-cy8c95x0.c index 4ccfa99ed93a..fe9545c630a2 100644 --- a/drivers/pinctrl/pinctrl-cy8c95x0.c +++ b/drivers/pinctrl/pinctrl-cy8c95x0.c @@ -308,6 +308,9 @@ static const char * const cy8c95x0_groups[] = { "gp77", }; +static int cy8c95x0_pinmux_direction(struct cy8c95x0_pinctrl *chip, + unsigned int pin, bool input); + static inline u8 cypress_get_port(struct cy8c95x0_pinctrl *chip, unsigned int pin) { /* Account for GPORT2 which only has 4 bits */ @@ -712,6 +715,8 @@ static int cy8c95x0_gpio_get_pincfg(struct cy8c95x0_pinctrl *chip, ret = regmap_read(chip->regmap, reg, ®_val); if (reg_val & bit) arg = 1; + if (param == PIN_CONFIG_OUTPUT_ENABLE) + arg = !arg; *config = pinconf_to_config_packed(param, (u16)arg); out: @@ -727,6 +732,7 @@ static int cy8c95x0_gpio_set_pincfg(struct cy8c95x0_pinctrl *chip, u8 port = cypress_get_port(chip, off); u8 bit = cypress_get_pin_mask(chip, off); unsigned long param = pinconf_to_config_param(config); + unsigned long arg = pinconf_to_config_argument(config); unsigned int reg; int ret; @@ -765,6 +771,12 @@ static int cy8c95x0_gpio_set_pincfg(struct cy8c95x0_pinctrl *chip, case PIN_CONFIG_MODE_PWM: reg = CY8C95X0_PWMSEL; break; + case PIN_CONFIG_OUTPUT_ENABLE: + ret = cy8c95x0_pinmux_direction(chip, off, !arg); + goto out; + case PIN_CONFIG_INPUT_ENABLE: + ret = cy8c95x0_pinmux_direction(chip, off, arg); + goto out; default: ret = -ENOTSUPP; goto out; @@ -822,7 +834,7 @@ static int cy8c95x0_setup_gpiochip(struct cy8c95x0_pinctrl *chip) gc->get_direction = cy8c95x0_gpio_get_direction; gc->get_multiple = cy8c95x0_gpio_get_multiple; gc->set_multiple = cy8c95x0_gpio_set_multiple; - gc->set_config = gpiochip_generic_config, + gc->set_config = gpiochip_generic_config; gc->can_sleep = true; gc->add_pin_ranges = cy8c95x0_add_pin_ranges; diff --git a/drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c b/drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c index ea70b8c61679..b29b0ab9892b 100644 --- a/drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c +++ b/drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c @@ -492,7 +492,7 @@ static int starfive_dt_node_to_map(struct pinctrl_dev *pctldev, nmaps = 0; ngroups = 0; - for_each_child_of_node(np, child) { + for_each_available_child_of_node(np, child) { int npinmux = of_property_count_u32_elems(child, "pinmux"); int npins = of_property_count_u32_elems(child, "pins"); @@ -527,7 +527,7 @@ static int starfive_dt_node_to_map(struct pinctrl_dev *pctldev, nmaps = 0; ngroups = 0; mutex_lock(&sfp->mutex); - for_each_child_of_node(np, child) { + for_each_available_child_of_node(np, child) { int npins; int i; diff --git a/drivers/pinctrl/starfive/pinctrl-starfive-jh7110.c b/drivers/pinctrl/starfive/pinctrl-starfive-jh7110.c index 9d71e8c13310..6de11a405734 100644 --- a/drivers/pinctrl/starfive/pinctrl-starfive-jh7110.c +++ b/drivers/pinctrl/starfive/pinctrl-starfive-jh7110.c @@ -135,7 +135,7 @@ static int jh7110_dt_node_to_map(struct pinctrl_dev *pctldev, int ret; ngroups = 0; - for_each_child_of_node(np, child) + for_each_available_child_of_node(np, child) ngroups += 1; nmaps = 2 * ngroups; @@ -150,7 +150,7 @@ static int jh7110_dt_node_to_map(struct pinctrl_dev *pctldev, nmaps = 0; ngroups = 0; mutex_lock(&sfp->mutex); - for_each_child_of_node(np, child) { + for_each_available_child_of_node(np, child) { int npins = of_property_count_u32_elems(child, "pinmux"); int *pins; u32 *pinmux; diff --git a/drivers/platform/x86/amd/pmc/pmc-quirks.c b/drivers/platform/x86/amd/pmc/pmc-quirks.c index 6bbffb081053..b456370166b6 100644 --- a/drivers/platform/x86/amd/pmc/pmc-quirks.c +++ b/drivers/platform/x86/amd/pmc/pmc-quirks.c @@ -16,12 +16,17 @@ struct quirk_entry { u32 s2idle_bug_mmio; + bool spurious_8042; }; static struct quirk_entry quirk_s2idle_bug = { .s2idle_bug_mmio = 0xfed80380, }; +static struct quirk_entry quirk_spurious_8042 = { + .spurious_8042 = true, +}; + static const struct dmi_system_id fwbug_list[] = { { .ident = "L14 Gen2 AMD", @@ -193,6 +198,16 @@ static const struct dmi_system_id fwbug_list[] = { DMI_MATCH(DMI_PRODUCT_NAME, "HP Laptop 15s-eq2xxx"), } }, + /* https://community.frame.work/t/tracking-framework-amd-ryzen-7040-series-lid-wakeup-behavior-feedback/39128 */ + { + .ident = "Framework Laptop 13 (Phoenix)", + .driver_data = &quirk_spurious_8042, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Framework"), + DMI_MATCH(DMI_PRODUCT_NAME, "Laptop 13 (AMD Ryzen 7040Series)"), + DMI_MATCH(DMI_BIOS_VERSION, "03.03"), + } + }, {} }; @@ -235,6 +250,9 @@ void amd_pmc_quirks_init(struct amd_pmc_dev *dev) { const struct dmi_system_id *dmi_id; + if (dev->cpu_id == AMD_CPU_ID_CZN) + dev->disable_8042_wakeup = true; + dmi_id = dmi_first_match(fwbug_list); if (!dmi_id) return; @@ -242,4 +260,6 @@ void amd_pmc_quirks_init(struct amd_pmc_dev *dev) if (dev->quirks->s2idle_bug_mmio) pr_info("Using s2idle quirk to avoid %s platform firmware bug\n", dmi_id->ident); + if (dev->quirks->spurious_8042) + dev->disable_8042_wakeup = true; } diff --git a/drivers/platform/x86/amd/pmc/pmc.c b/drivers/platform/x86/amd/pmc/pmc.c index c3104714b480..864c8cc2f8a3 100644 --- a/drivers/platform/x86/amd/pmc/pmc.c +++ b/drivers/platform/x86/amd/pmc/pmc.c @@ -91,16 +91,6 @@ #define SMU_MSG_LOG_RESET 0x07 #define SMU_MSG_LOG_DUMP_DATA 0x08 #define SMU_MSG_GET_SUP_CONSTRAINTS 0x09 -/* List of supported CPU ids */ -#define AMD_CPU_ID_RV 0x15D0 -#define AMD_CPU_ID_RN 0x1630 -#define AMD_CPU_ID_PCO AMD_CPU_ID_RV -#define AMD_CPU_ID_CZN AMD_CPU_ID_RN -#define AMD_CPU_ID_YC 0x14B5 -#define AMD_CPU_ID_CB 0x14D8 -#define AMD_CPU_ID_PS 0x14E8 -#define AMD_CPU_ID_SP 0x14A4 -#define PCI_DEVICE_ID_AMD_1AH_M20H_ROOT 0x1507 #define PMC_MSG_DELAY_MIN_US 50 #define RESPONSE_REGISTER_LOOP_MAX 20000 @@ -766,19 +756,22 @@ static int amd_pmc_get_os_hint(struct amd_pmc_dev *dev) return -EINVAL; } -static int amd_pmc_czn_wa_irq1(struct amd_pmc_dev *pdev) +static int amd_pmc_wa_irq1(struct amd_pmc_dev *pdev) { struct device *d; int rc; - if (!pdev->major) { - rc = amd_pmc_get_smu_version(pdev); - if (rc) - return rc; - } + /* cezanne platform firmware has a fix in 64.66.0 */ + if (pdev->cpu_id == AMD_CPU_ID_CZN) { + if (!pdev->major) { + rc = amd_pmc_get_smu_version(pdev); + if (rc) + return rc; + } - if (pdev->major > 64 || (pdev->major == 64 && pdev->minor > 65)) - return 0; + if (pdev->major > 64 || (pdev->major == 64 && pdev->minor > 65)) + return 0; + } d = bus_find_device_by_name(&serio_bus, NULL, "serio0"); if (!d) @@ -937,8 +930,8 @@ static int amd_pmc_suspend_handler(struct device *dev) { struct amd_pmc_dev *pdev = dev_get_drvdata(dev); - if (pdev->cpu_id == AMD_CPU_ID_CZN && !disable_workarounds) { - int rc = amd_pmc_czn_wa_irq1(pdev); + if (pdev->disable_8042_wakeup && !disable_workarounds) { + int rc = amd_pmc_wa_irq1(pdev); if (rc) { dev_err(pdev->dev, "failed to adjust keyboard wakeup: %d\n", rc); diff --git a/drivers/platform/x86/amd/pmc/pmc.h b/drivers/platform/x86/amd/pmc/pmc.h index c27bd6a5642f..b4794f118739 100644 --- a/drivers/platform/x86/amd/pmc/pmc.h +++ b/drivers/platform/x86/amd/pmc/pmc.h @@ -36,9 +36,21 @@ struct amd_pmc_dev { struct mutex lock; /* generic mutex lock */ struct dentry *dbgfs_dir; struct quirk_entry *quirks; + bool disable_8042_wakeup; }; void amd_pmc_process_restore_quirks(struct amd_pmc_dev *dev); void amd_pmc_quirks_init(struct amd_pmc_dev *dev); +/* List of supported CPU ids */ +#define AMD_CPU_ID_RV 0x15D0 +#define AMD_CPU_ID_RN 0x1630 +#define AMD_CPU_ID_PCO AMD_CPU_ID_RV +#define AMD_CPU_ID_CZN AMD_CPU_ID_RN +#define AMD_CPU_ID_YC 0x14B5 +#define AMD_CPU_ID_CB 0x14D8 +#define AMD_CPU_ID_PS 0x14E8 +#define AMD_CPU_ID_SP 0x14A4 +#define PCI_DEVICE_ID_AMD_1AH_M20H_ROOT 0x1507 + #endif /* PMC_H */ diff --git a/drivers/platform/x86/intel/pmc/adl.c b/drivers/platform/x86/intel/pmc/adl.c index 5006008e01be..606f7678bcb0 100644 --- a/drivers/platform/x86/intel/pmc/adl.c +++ b/drivers/platform/x86/intel/pmc/adl.c @@ -314,16 +314,13 @@ int adl_core_init(struct pmc_dev *pmcdev) struct pmc *pmc = pmcdev->pmcs[PMC_IDX_MAIN]; int ret; + pmcdev->suspend = cnl_suspend; + pmcdev->resume = cnl_resume; + pmc->map = &adl_reg_map; ret = get_primary_reg_base(pmc); if (ret) return ret; - /* Due to a hardware limitation, the GBE LTR blocks PC10 - * when a cable is attached. Tell the PMC to ignore it. - */ - dev_dbg(&pmcdev->pdev->dev, "ignoring GBE LTR\n"); - pmc_core_send_ltr_ignore(pmcdev, 3); - return 0; } diff --git a/drivers/platform/x86/intel/pmc/cnp.c b/drivers/platform/x86/intel/pmc/cnp.c index 420aaa1d7c76..98b36651201a 100644 --- a/drivers/platform/x86/intel/pmc/cnp.c +++ b/drivers/platform/x86/intel/pmc/cnp.c @@ -204,21 +204,35 @@ const struct pmc_reg_map cnp_reg_map = { .etr3_offset = ETR3_OFFSET, }; +void cnl_suspend(struct pmc_dev *pmcdev) +{ + /* + * Due to a hardware limitation, the GBE LTR blocks PC10 + * when a cable is attached. To unblock PC10 during suspend, + * tell the PMC to ignore it. + */ + pmc_core_send_ltr_ignore(pmcdev, 3, 1); +} + +int cnl_resume(struct pmc_dev *pmcdev) +{ + pmc_core_send_ltr_ignore(pmcdev, 3, 0); + + return pmc_core_resume_common(pmcdev); +} + int cnp_core_init(struct pmc_dev *pmcdev) { struct pmc *pmc = pmcdev->pmcs[PMC_IDX_MAIN]; int ret; + pmcdev->suspend = cnl_suspend; + pmcdev->resume = cnl_resume; + pmc->map = &cnp_reg_map; ret = get_primary_reg_base(pmc); if (ret) return ret; - /* Due to a hardware limitation, the GBE LTR blocks PC10 - * when a cable is attached. Tell the PMC to ignore it. - */ - dev_dbg(&pmcdev->pdev->dev, "ignoring GBE LTR\n"); - pmc_core_send_ltr_ignore(pmcdev, 3); - return 0; } diff --git a/drivers/platform/x86/intel/pmc/core.c b/drivers/platform/x86/intel/pmc/core.c index 84c175b9721a..022afb97d531 100644 --- a/drivers/platform/x86/intel/pmc/core.c +++ b/drivers/platform/x86/intel/pmc/core.c @@ -460,7 +460,7 @@ out_unlock: } DEFINE_SHOW_ATTRIBUTE(pmc_core_pll); -int pmc_core_send_ltr_ignore(struct pmc_dev *pmcdev, u32 value) +int pmc_core_send_ltr_ignore(struct pmc_dev *pmcdev, u32 value, int ignore) { struct pmc *pmc; const struct pmc_reg_map *map; @@ -472,7 +472,7 @@ int pmc_core_send_ltr_ignore(struct pmc_dev *pmcdev, u32 value) * is based on the contiguous indexes from ltr_show output. * pmc index and ltr index needs to be calculated from it. */ - for (pmc_index = 0; pmc_index < ARRAY_SIZE(pmcdev->pmcs) && ltr_index > 0; pmc_index++) { + for (pmc_index = 0; pmc_index < ARRAY_SIZE(pmcdev->pmcs) && ltr_index >= 0; pmc_index++) { pmc = pmcdev->pmcs[pmc_index]; if (!pmc) @@ -498,7 +498,10 @@ int pmc_core_send_ltr_ignore(struct pmc_dev *pmcdev, u32 value) mutex_lock(&pmcdev->lock); reg = pmc_core_reg_read(pmc, map->ltr_ignore_offset); - reg |= BIT(ltr_index); + if (ignore) + reg |= BIT(ltr_index); + else + reg &= ~BIT(ltr_index); pmc_core_reg_write(pmc, map->ltr_ignore_offset, reg); mutex_unlock(&pmcdev->lock); @@ -521,7 +524,7 @@ static ssize_t pmc_core_ltr_ignore_write(struct file *file, if (err) return err; - err = pmc_core_send_ltr_ignore(pmcdev, value); + err = pmc_core_send_ltr_ignore(pmcdev, value, 1); return err == 0 ? count : err; } @@ -1279,6 +1282,9 @@ static __maybe_unused int pmc_core_suspend(struct device *dev) struct pmc_dev *pmcdev = dev_get_drvdata(dev); struct pmc *pmc = pmcdev->pmcs[PMC_IDX_MAIN]; + if (pmcdev->suspend) + pmcdev->suspend(pmcdev); + /* Check if the syspend will actually use S0ix */ if (pm_suspend_via_firmware()) return 0; diff --git a/drivers/platform/x86/intel/pmc/core.h b/drivers/platform/x86/intel/pmc/core.h index 0729f593c6a7..b66dacbfb94b 100644 --- a/drivers/platform/x86/intel/pmc/core.h +++ b/drivers/platform/x86/intel/pmc/core.h @@ -363,6 +363,7 @@ struct pmc { * @s0ix_counter: S0ix residency (step adjusted) * @num_lpm_modes: Count of enabled modes * @lpm_en_modes: Array of enabled modes from lowest to highest priority + * @suspend: Function to perform platform specific suspend * @resume: Function to perform platform specific resume * * pmc_dev contains info about power management controller device. @@ -379,6 +380,7 @@ struct pmc_dev { u64 s0ix_counter; int num_lpm_modes; int lpm_en_modes[LPM_MAX_NUM_MODES]; + void (*suspend)(struct pmc_dev *pmcdev); int (*resume)(struct pmc_dev *pmcdev); bool has_die_c6; @@ -486,7 +488,7 @@ extern const struct pmc_bit_map *mtl_ioem_lpm_maps[]; extern const struct pmc_reg_map mtl_ioem_reg_map; extern void pmc_core_get_tgl_lpm_reqs(struct platform_device *pdev); -extern int pmc_core_send_ltr_ignore(struct pmc_dev *pmcdev, u32 value); +int pmc_core_send_ltr_ignore(struct pmc_dev *pmcdev, u32 value, int ignore); int pmc_core_resume_common(struct pmc_dev *pmcdev); int get_primary_reg_base(struct pmc *pmc); @@ -500,6 +502,9 @@ int tgl_core_init(struct pmc_dev *pmcdev); int adl_core_init(struct pmc_dev *pmcdev); int mtl_core_init(struct pmc_dev *pmcdev); +void cnl_suspend(struct pmc_dev *pmcdev); +int cnl_resume(struct pmc_dev *pmcdev); + #define pmc_for_each_mode(i, mode, pmcdev) \ for (i = 0, mode = pmcdev->lpm_en_modes[i]; \ i < pmcdev->num_lpm_modes; \ diff --git a/drivers/platform/x86/intel/pmc/mtl.c b/drivers/platform/x86/intel/pmc/mtl.c index 2204bc666980..504e3e273c32 100644 --- a/drivers/platform/x86/intel/pmc/mtl.c +++ b/drivers/platform/x86/intel/pmc/mtl.c @@ -979,6 +979,8 @@ static void mtl_d3_fixup(void) static int mtl_resume(struct pmc_dev *pmcdev) { mtl_d3_fixup(); + pmc_core_send_ltr_ignore(pmcdev, 3, 0); + return pmc_core_resume_common(pmcdev); } @@ -989,6 +991,7 @@ int mtl_core_init(struct pmc_dev *pmcdev) mtl_d3_fixup(); + pmcdev->suspend = cnl_suspend; pmcdev->resume = mtl_resume; pmcdev->regmap_list = mtl_pmc_info_list; @@ -1002,11 +1005,5 @@ int mtl_core_init(struct pmc_dev *pmcdev) return ret; } - /* Due to a hardware limitation, the GBE LTR blocks PC10 - * when a cable is attached. Tell the PMC to ignore it. - */ - dev_dbg(&pmcdev->pdev->dev, "ignoring GBE LTR\n"); - pmc_core_send_ltr_ignore(pmcdev, 3); - return 0; } diff --git a/drivers/platform/x86/intel/pmc/tgl.c b/drivers/platform/x86/intel/pmc/tgl.c index 2449940102db..e88d3d00c853 100644 --- a/drivers/platform/x86/intel/pmc/tgl.c +++ b/drivers/platform/x86/intel/pmc/tgl.c @@ -259,16 +259,15 @@ int tgl_core_init(struct pmc_dev *pmcdev) int ret; pmc->map = &tgl_reg_map; + + pmcdev->suspend = cnl_suspend; + pmcdev->resume = cnl_resume; + ret = get_primary_reg_base(pmc); if (ret) return ret; pmc_core_get_tgl_lpm_reqs(pmcdev->pdev); - /* Due to a hardware limitation, the GBE LTR blocks PC10 - * when a cable is attached. Tell the PMC to ignore it. - */ - dev_dbg(&pmcdev->pdev->dev, "ignoring GBE LTR\n"); - pmc_core_send_ltr_ignore(pmcdev, 3); return 0; } diff --git a/drivers/platform/x86/intel/vbtn.c b/drivers/platform/x86/intel/vbtn.c index 6fa1735ad7a4..210b0a81b7ec 100644 --- a/drivers/platform/x86/intel/vbtn.c +++ b/drivers/platform/x86/intel/vbtn.c @@ -73,10 +73,10 @@ struct intel_vbtn_priv { bool wakeup_mode; }; -static void detect_tablet_mode(struct platform_device *device) +static void detect_tablet_mode(struct device *dev) { - struct intel_vbtn_priv *priv = dev_get_drvdata(&device->dev); - acpi_handle handle = ACPI_HANDLE(&device->dev); + struct intel_vbtn_priv *priv = dev_get_drvdata(dev); + acpi_handle handle = ACPI_HANDLE(dev); unsigned long long vgbs; acpi_status status; int m; @@ -89,6 +89,8 @@ static void detect_tablet_mode(struct platform_device *device) input_report_switch(priv->switches_dev, SW_TABLET_MODE, m); m = (vgbs & VGBS_DOCK_MODE_FLAG) ? 1 : 0; input_report_switch(priv->switches_dev, SW_DOCK, m); + + input_sync(priv->switches_dev); } /* @@ -134,7 +136,7 @@ static int intel_vbtn_input_setup(struct platform_device *device) priv->switches_dev->id.bustype = BUS_HOST; if (priv->has_switches) { - detect_tablet_mode(device); + detect_tablet_mode(&device->dev); ret = input_register_device(priv->switches_dev); if (ret) @@ -198,6 +200,9 @@ static void notify_handler(acpi_handle handle, u32 event, void *context) autorelease = val && (!ke_rel || ke_rel->type == KE_IGNORE); sparse_keymap_report_event(input_dev, event, val, autorelease); + + /* Some devices need this to report further events */ + acpi_evaluate_object(handle, "VBDL", NULL, NULL); } /* @@ -352,7 +357,13 @@ static void intel_vbtn_pm_complete(struct device *dev) static int intel_vbtn_pm_resume(struct device *dev) { + struct intel_vbtn_priv *priv = dev_get_drvdata(dev); + intel_vbtn_pm_complete(dev); + + if (priv->has_switches) + detect_tablet_mode(dev); + return 0; } diff --git a/drivers/platform/x86/intel_ips.c b/drivers/platform/x86/intel_ips.c index 4dfdbfca6841..c66808601fdd 100644 --- a/drivers/platform/x86/intel_ips.c +++ b/drivers/platform/x86/intel_ips.c @@ -590,6 +590,8 @@ static void ips_disable_gpu_turbo(struct ips_driver *ips) * @ips: IPS driver struct * * Check whether the MCP is over its thermal or power budget. + * + * Returns: %true if the temp or power has exceeded its maximum, else %false */ static bool mcp_exceeded(struct ips_driver *ips) { @@ -619,6 +621,8 @@ static bool mcp_exceeded(struct ips_driver *ips) * @cpu: CPU number to check * * Check a given CPU's average temp or power is over its limit. + * + * Returns: %true if the temp or power has exceeded its maximum, else %false */ static bool cpu_exceeded(struct ips_driver *ips, int cpu) { @@ -645,6 +649,8 @@ static bool cpu_exceeded(struct ips_driver *ips, int cpu) * @ips: IPS driver struct * * Check the MCH temp & power against their maximums. + * + * Returns: %true if the temp or power has exceeded its maximum, else %false */ static bool mch_exceeded(struct ips_driver *ips) { @@ -742,12 +748,13 @@ static void update_turbo_limits(struct ips_driver *ips) * - down (at TDP limit) * - adjust both CPU and GPU down if possible * - cpu+ gpu+ cpu+gpu- cpu-gpu+ cpu-gpu- -cpu < gpu < cpu+gpu+ cpu+ gpu+ nothing -cpu < gpu >= cpu+gpu-(mcp<) cpu+gpu-(mcp<) gpu- gpu- -cpu >= gpu < cpu-gpu+(mcp<) cpu- cpu-gpu+(mcp<) cpu- -cpu >= gpu >= cpu-gpu- cpu-gpu- cpu-gpu- cpu-gpu- + * |cpu+ gpu+ cpu+gpu- cpu-gpu+ cpu-gpu- + * cpu < gpu < |cpu+gpu+ cpu+ gpu+ nothing + * cpu < gpu >= |cpu+gpu-(mcp<) cpu+gpu-(mcp<) gpu- gpu- + * cpu >= gpu < |cpu-gpu+(mcp<) cpu- cpu-gpu+(mcp<) cpu- + * cpu >= gpu >=|cpu-gpu- cpu-gpu- cpu-gpu- cpu-gpu- * + * Returns: %0 */ static int ips_adjust(void *data) { @@ -935,11 +942,13 @@ static void monitor_timeout(struct timer_list *t) * @data: ips driver structure * * This is the main function for the IPS driver. It monitors power and - * tempurature in the MCP and adjusts CPU and GPU power clams accordingly. + * temperature in the MCP and adjusts CPU and GPU power clamps accordingly. * - * We keep a 5s moving average of power consumption and tempurature. Using + * We keep a 5s moving average of power consumption and temperature. Using * that data, along with CPU vs GPU preference, we adjust the power clamps * up or down. + * + * Returns: %0 on success or -errno on error */ static int ips_monitor(void *data) { @@ -1146,6 +1155,8 @@ static void dump_thermal_info(struct ips_driver *ips) * Handle temperature limit trigger events, generally by lowering the clamps. * If we're at a critical limit, we clamp back to the lowest possible value * to prevent emergency shutdown. + * + * Returns: IRQ_NONE or IRQ_HANDLED */ static irqreturn_t ips_irq_handler(int irq, void *arg) { @@ -1293,9 +1304,12 @@ static void ips_debugfs_init(struct ips_driver *ips) /** * ips_detect_cpu - detect whether CPU supports IPS + * @ips: IPS driver struct * * Walk our list and see if we're on a supported CPU. If we find one, * return the limits for it. + * + * Returns: the &ips_mcp_limits struct that matches the boot CPU or %NULL */ static struct ips_mcp_limits *ips_detect_cpu(struct ips_driver *ips) { @@ -1352,6 +1366,8 @@ static struct ips_mcp_limits *ips_detect_cpu(struct ips_driver *ips) * monitor and control graphics turbo mode. If we can find them, we can * enable graphics turbo, otherwise we must disable it to avoid exceeding * thermal and power limits in the MCP. + * + * Returns: %true if the required symbols are found, else %false */ static bool ips_get_i915_syms(struct ips_driver *ips) { diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index d0b5fd4137bc..c4895e9bc714 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -512,10 +512,10 @@ struct tpacpi_quirk { * Iterates over a quirks list until one is found that matches the * ThinkPad's vendor, BIOS and EC model. * - * Returns 0 if nothing matches, otherwise returns the quirks field of + * Returns: %0 if nothing matches, otherwise returns the quirks field of * the matching &struct tpacpi_quirk entry. * - * The match criteria is: vendor, ec and bios much match. + * The match criteria is: vendor, ec and bios must match. */ static unsigned long __init tpacpi_check_quirks( const struct tpacpi_quirk *qlist, @@ -7948,8 +7948,19 @@ static struct ibm_struct volume_driver_data = { * TPACPI_FAN_WR_TPEC is also available and should be used to * command the fan. The X31/X40/X41 seems to have 8 fan levels, * but the ACPI tables just mention level 7. + * + * TPACPI_FAN_RD_TPEC_NS: + * This mode is used for a few ThinkPads (L13 Yoga Gen2, X13 Yoga Gen2 etc.) + * that are using non-standard EC locations for reporting fan speeds. + * Currently these platforms only provide fan rpm reporting. + * */ +#define FAN_RPM_CAL_CONST 491520 /* FAN RPM calculation offset for some non-standard ECFW */ + +#define FAN_NS_CTRL_STATUS BIT(2) /* Bit which determines control is enabled or not */ +#define FAN_NS_CTRL BIT(4) /* Bit which determines control is by host or EC */ + enum { /* Fan control constants */ fan_status_offset = 0x2f, /* EC register 0x2f */ fan_rpm_offset = 0x84, /* EC register 0x84: LSB, 0x85 MSB (RPM) @@ -7957,6 +7968,11 @@ enum { /* Fan control constants */ fan_select_offset = 0x31, /* EC register 0x31 (Firmware 7M) bit 0 selects which fan is active */ + fan_status_offset_ns = 0x93, /* Special status/control offset for non-standard EC Fan1 */ + fan2_status_offset_ns = 0x96, /* Special status/control offset for non-standard EC Fan2 */ + fan_rpm_status_ns = 0x95, /* Special offset for Fan1 RPM status for non-standard EC */ + fan2_rpm_status_ns = 0x98, /* Special offset for Fan2 RPM status for non-standard EC */ + TP_EC_FAN_FULLSPEED = 0x40, /* EC fan mode: full speed */ TP_EC_FAN_AUTO = 0x80, /* EC fan mode: auto fan control */ @@ -7967,6 +7983,7 @@ enum fan_status_access_mode { TPACPI_FAN_NONE = 0, /* No fan status or control */ TPACPI_FAN_RD_ACPI_GFAN, /* Use ACPI GFAN */ TPACPI_FAN_RD_TPEC, /* Use ACPI EC regs 0x2f, 0x84-0x85 */ + TPACPI_FAN_RD_TPEC_NS, /* Use non-standard ACPI EC regs (eg: L13 Yoga gen2 etc.) */ }; enum fan_control_access_mode { @@ -7994,6 +8011,8 @@ static u8 fan_control_desired_level; static u8 fan_control_resume_level; static int fan_watchdog_maxinterval; +static bool fan_with_ns_addr; + static struct mutex fan_mutex; static void fan_watchdog_fire(struct work_struct *ignored); @@ -8123,6 +8142,15 @@ static int fan_get_status(u8 *status) } break; + case TPACPI_FAN_RD_TPEC_NS: + /* Default mode is AUTO which means controlled by EC */ + if (!acpi_ec_read(fan_status_offset_ns, &s)) + return -EIO; + + if (status) + *status = s; + + break; default: return -ENXIO; @@ -8139,7 +8167,8 @@ static int fan_get_status_safe(u8 *status) if (mutex_lock_killable(&fan_mutex)) return -ERESTARTSYS; rc = fan_get_status(&s); - if (!rc) + /* NS EC doesn't have register with level settings */ + if (!rc && !fan_with_ns_addr) fan_update_desired_level(s); mutex_unlock(&fan_mutex); @@ -8166,7 +8195,13 @@ static int fan_get_speed(unsigned int *speed) if (likely(speed)) *speed = (hi << 8) | lo; + break; + case TPACPI_FAN_RD_TPEC_NS: + if (!acpi_ec_read(fan_rpm_status_ns, &lo)) + return -EIO; + if (speed) + *speed = lo ? FAN_RPM_CAL_CONST / lo : 0; break; default: @@ -8178,7 +8213,7 @@ static int fan_get_speed(unsigned int *speed) static int fan2_get_speed(unsigned int *speed) { - u8 hi, lo; + u8 hi, lo, status; bool rc; switch (fan_status_access_mode) { @@ -8194,7 +8229,21 @@ static int fan2_get_speed(unsigned int *speed) if (likely(speed)) *speed = (hi << 8) | lo; + break; + case TPACPI_FAN_RD_TPEC_NS: + rc = !acpi_ec_read(fan2_status_offset_ns, &status); + if (rc) + return -EIO; + if (!(status & FAN_NS_CTRL_STATUS)) { + pr_info("secondary fan control not supported\n"); + return -EIO; + } + rc = !acpi_ec_read(fan2_rpm_status_ns, &lo); + if (rc) + return -EIO; + if (speed) + *speed = lo ? FAN_RPM_CAL_CONST / lo : 0; break; default: @@ -8697,6 +8746,7 @@ static const struct attribute_group fan_driver_attr_group = { #define TPACPI_FAN_2FAN 0x0002 /* EC 0x31 bit 0 selects fan2 */ #define TPACPI_FAN_2CTL 0x0004 /* selects fan2 control */ #define TPACPI_FAN_NOFAN 0x0008 /* no fan available */ +#define TPACPI_FAN_NS 0x0010 /* For EC with non-Standard register addresses */ static const struct tpacpi_quirk fan_quirk_table[] __initconst = { TPACPI_QEC_IBM('1', 'Y', TPACPI_FAN_Q1), @@ -8715,6 +8765,8 @@ static const struct tpacpi_quirk fan_quirk_table[] __initconst = { TPACPI_Q_LNV3('N', '2', 'O', TPACPI_FAN_2CTL), /* P1 / X1 Extreme (2nd gen) */ TPACPI_Q_LNV3('N', '3', '0', TPACPI_FAN_2CTL), /* P15 (1st gen) / P15v (1st gen) */ TPACPI_Q_LNV3('N', '3', '7', TPACPI_FAN_2CTL), /* T15g (2nd gen) */ + TPACPI_Q_LNV3('R', '1', 'F', TPACPI_FAN_NS), /* L13 Yoga Gen 2 */ + TPACPI_Q_LNV3('N', '2', 'U', TPACPI_FAN_NS), /* X13 Yoga Gen 2*/ TPACPI_Q_LNV3('N', '1', 'O', TPACPI_FAN_NOFAN), /* X1 Tablet (2nd gen) */ }; @@ -8749,18 +8801,27 @@ static int __init fan_init(struct ibm_init_struct *iibm) return -ENODEV; } + if (quirks & TPACPI_FAN_NS) { + pr_info("ECFW with non-standard fan reg control found\n"); + fan_with_ns_addr = 1; + /* Fan ctrl support from host is undefined for now */ + tp_features.fan_ctrl_status_undef = 1; + } + if (gfan_handle) { /* 570, 600e/x, 770e, 770x */ fan_status_access_mode = TPACPI_FAN_RD_ACPI_GFAN; } else { /* all other ThinkPads: note that even old-style * ThinkPad ECs supports the fan control register */ - if (likely(acpi_ec_read(fan_status_offset, - &fan_control_initial_status))) { + if (fan_with_ns_addr || + likely(acpi_ec_read(fan_status_offset, &fan_control_initial_status))) { int res; unsigned int speed; - fan_status_access_mode = TPACPI_FAN_RD_TPEC; + fan_status_access_mode = fan_with_ns_addr ? + TPACPI_FAN_RD_TPEC_NS : TPACPI_FAN_RD_TPEC; + if (quirks & TPACPI_FAN_Q1) fan_quirk1_setup(); /* Try and probe the 2nd fan */ @@ -8769,7 +8830,8 @@ static int __init fan_init(struct ibm_init_struct *iibm) if (res >= 0 && speed != FAN_NOT_PRESENT) { /* It responded - so let's assume it's there */ tp_features.second_fan = 1; - tp_features.second_fan_ctl = 1; + /* fan control not currently available for ns ECFW */ + tp_features.second_fan_ctl = !fan_with_ns_addr; pr_info("secondary fan control detected & enabled\n"); } else { /* Fan not auto-detected */ @@ -8944,6 +9006,7 @@ static int fan_read(struct seq_file *m) str_enabled_disabled(status), status); break; + case TPACPI_FAN_RD_TPEC_NS: case TPACPI_FAN_RD_TPEC: /* all except 570, 600e/x, 770e, 770x */ rc = fan_get_status_safe(&status); @@ -8958,13 +9021,22 @@ static int fan_read(struct seq_file *m) seq_printf(m, "speed:\t\t%d\n", speed); - if (status & TP_EC_FAN_FULLSPEED) - /* Disengaged mode takes precedence */ - seq_printf(m, "level:\t\tdisengaged\n"); - else if (status & TP_EC_FAN_AUTO) - seq_printf(m, "level:\t\tauto\n"); - else - seq_printf(m, "level:\t\t%d\n", status); + if (fan_status_access_mode == TPACPI_FAN_RD_TPEC_NS) { + /* + * No full speed bit in NS EC + * EC Auto mode is set by default. + * No other levels settings available + */ + seq_printf(m, "level:\t\t%s\n", status & FAN_NS_CTRL ? "unknown" : "auto"); + } else { + if (status & TP_EC_FAN_FULLSPEED) + /* Disengaged mode takes precedence */ + seq_printf(m, "level:\t\tdisengaged\n"); + else if (status & TP_EC_FAN_AUTO) + seq_printf(m, "level:\t\tauto\n"); + else + seq_printf(m, "level:\t\t%d\n", status); + } break; case TPACPI_FAN_NONE: @@ -9303,7 +9375,7 @@ static struct tpacpi_battery_driver_data battery_info; /* ACPI helpers/functions/probes */ -/** +/* * This evaluates a ACPI method call specific to the battery * ACPI extension. The specifics are that an error is marked * in the 32rd bit of the response, so we just check that here. diff --git a/drivers/ptp/ptp_ocp.c b/drivers/ptp/ptp_ocp.c index 4021d3d325f9..e7defce8cf48 100644 --- a/drivers/ptp/ptp_ocp.c +++ b/drivers/ptp/ptp_ocp.c @@ -4492,7 +4492,7 @@ ptp_ocp_remove(struct pci_dev *pdev) cancel_delayed_work_sync(&bp->sync_work); for (i = 0; i < OCP_SMA_NUM; i++) { if (bp->sma[i].dpll_pin) { - dpll_pin_unregister(bp->dpll, bp->sma[i].dpll_pin, &dpll_pins_ops, bp); + dpll_pin_unregister(bp->dpll, bp->sma[i].dpll_pin, &dpll_pins_ops, &bp->sma[i]); dpll_pin_put(bp->sma[i].dpll_pin); } } diff --git a/drivers/reset/core.c b/drivers/reset/core.c index 7ece6a8e9858..4d5a78d3c085 100644 --- a/drivers/reset/core.c +++ b/drivers/reset/core.c @@ -807,6 +807,9 @@ static void __reset_control_put_internal(struct reset_control *rstc) { lockdep_assert_held(&reset_list_mutex); + if (IS_ERR_OR_NULL(rstc)) + return; + kref_put(&rstc->refcnt, __reset_control_release); } @@ -1017,11 +1020,8 @@ EXPORT_SYMBOL_GPL(reset_control_put); void reset_control_bulk_put(int num_rstcs, struct reset_control_bulk_data *rstcs) { mutex_lock(&reset_list_mutex); - while (num_rstcs--) { - if (IS_ERR_OR_NULL(rstcs[num_rstcs].rstc)) - continue; + while (num_rstcs--) __reset_control_put_internal(rstcs[num_rstcs].rstc); - } mutex_unlock(&reset_list_mutex); } EXPORT_SYMBOL_GPL(reset_control_bulk_put); diff --git a/drivers/reset/hisilicon/hi6220_reset.c b/drivers/reset/hisilicon/hi6220_reset.c index 8d1fce18ded7..5c3267acd2b1 100644 --- a/drivers/reset/hisilicon/hi6220_reset.c +++ b/drivers/reset/hisilicon/hi6220_reset.c @@ -163,7 +163,7 @@ static int hi6220_reset_probe(struct platform_device *pdev) if (!data) return -ENOMEM; - type = (enum hi6220_reset_ctrl_type)of_device_get_match_data(dev); + type = (uintptr_t)of_device_get_match_data(dev); regmap = syscon_node_to_regmap(np); if (IS_ERR(regmap)) { diff --git a/drivers/s390/block/scm_blk.c b/drivers/s390/block/scm_blk.c index 3a9cc8a4a230..ade95e91b3c8 100644 --- a/drivers/s390/block/scm_blk.c +++ b/drivers/s390/block/scm_blk.c @@ -17,6 +17,7 @@ #include <linux/blk-mq.h> #include <linux/slab.h> #include <linux/list.h> +#include <linux/io.h> #include <asm/eadm.h> #include "scm_blk.h" @@ -130,7 +131,7 @@ static void scm_request_done(struct scm_request *scmrq) for (i = 0; i < nr_requests_per_io && scmrq->request[i]; i++) { msb = &scmrq->aob->msb[i]; - aidaw = msb->data_addr; + aidaw = (u64)phys_to_virt(msb->data_addr); if ((msb->flags & MSB_FLAG_IDA) && aidaw && IS_ALIGNED(aidaw, PAGE_SIZE)) @@ -195,12 +196,12 @@ static int scm_request_prepare(struct scm_request *scmrq) msb->scm_addr = scmdev->address + ((u64) blk_rq_pos(req) << 9); msb->oc = (rq_data_dir(req) == READ) ? MSB_OC_READ : MSB_OC_WRITE; msb->flags |= MSB_FLAG_IDA; - msb->data_addr = (u64) aidaw; + msb->data_addr = (u64)virt_to_phys(aidaw); rq_for_each_segment(bv, req, iter) { WARN_ON(bv.bv_offset); msb->blk_count += bv.bv_len >> 12; - aidaw->data_addr = (u64) page_address(bv.bv_page); + aidaw->data_addr = virt_to_phys(page_address(bv.bv_page)); aidaw++; } diff --git a/drivers/s390/cio/vfio_ccw_chp.c b/drivers/s390/cio/vfio_ccw_chp.c index d3f3a611f95b..38c176cf6295 100644 --- a/drivers/s390/cio/vfio_ccw_chp.c +++ b/drivers/s390/cio/vfio_ccw_chp.c @@ -115,7 +115,7 @@ static ssize_t vfio_ccw_crw_region_read(struct vfio_ccw_private *private, /* Notify the guest if more CRWs are on our queue */ if (!list_empty(&private->crw) && private->crw_trigger) - eventfd_signal(private->crw_trigger, 1); + eventfd_signal(private->crw_trigger); return ret; } diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c index 43601816ea4e..bfb35cfce1ef 100644 --- a/drivers/s390/cio/vfio_ccw_drv.c +++ b/drivers/s390/cio/vfio_ccw_drv.c @@ -112,7 +112,7 @@ void vfio_ccw_sch_io_todo(struct work_struct *work) private->state = VFIO_CCW_STATE_IDLE; if (private->io_trigger) - eventfd_signal(private->io_trigger, 1); + eventfd_signal(private->io_trigger); } void vfio_ccw_crw_todo(struct work_struct *work) @@ -122,7 +122,7 @@ void vfio_ccw_crw_todo(struct work_struct *work) private = container_of(work, struct vfio_ccw_private, crw_work); if (!list_empty(&private->crw) && private->crw_trigger) - eventfd_signal(private->crw_trigger, 1); + eventfd_signal(private->crw_trigger); } /* diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c index cba4971618ff..ea532a8a4a0c 100644 --- a/drivers/s390/cio/vfio_ccw_ops.c +++ b/drivers/s390/cio/vfio_ccw_ops.c @@ -421,7 +421,7 @@ static int vfio_ccw_mdev_set_irqs(struct vfio_ccw_private *private, case VFIO_IRQ_SET_DATA_NONE: { if (*ctx) - eventfd_signal(*ctx, 1); + eventfd_signal(*ctx); return 0; } case VFIO_IRQ_SET_DATA_BOOL: @@ -432,7 +432,7 @@ static int vfio_ccw_mdev_set_irqs(struct vfio_ccw_private *private, return -EFAULT; if (trigger && *ctx) - eventfd_signal(*ctx, 1); + eventfd_signal(*ctx); return 0; } case VFIO_IRQ_SET_DATA_EVENTFD: @@ -612,7 +612,7 @@ static void vfio_ccw_mdev_request(struct vfio_device *vdev, unsigned int count) "Relaying device request to user (#%u)\n", count); - eventfd_signal(private->req_trigger, 1); + eventfd_signal(private->req_trigger); } else if (count == 0) { dev_notice(dev, "No device request channel registered, blocked until released by user\n"); diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c index 4db538a55192..542b5be73a6a 100644 --- a/drivers/s390/crypto/vfio_ap_ops.c +++ b/drivers/s390/crypto/vfio_ap_ops.c @@ -1794,7 +1794,7 @@ static void vfio_ap_mdev_request(struct vfio_device *vdev, unsigned int count) "Relaying device request to user (#%u)\n", count); - eventfd_signal(matrix_mdev->req_trigger, 1); + eventfd_signal(matrix_mdev->req_trigger); } else if (count == 0) { dev_notice(dev, "No device request registered, blocked until released by user\n"); diff --git a/drivers/scsi/aacraid/aacraid.h b/drivers/scsi/aacraid/aacraid.h index 73b6ac0c01f5..7d5a155073c6 100644 --- a/drivers/scsi/aacraid/aacraid.h +++ b/drivers/scsi/aacraid/aacraid.h @@ -1678,7 +1678,6 @@ struct aac_dev u32 handle_pci_error; bool init_reset; u8 soft_reset_support; - u8 use_map_queue; }; #define aac_adapter_interrupt(dev) \ diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c index 013a9a334972..25cee03d7f97 100644 --- a/drivers/scsi/aacraid/commsup.c +++ b/drivers/scsi/aacraid/commsup.c @@ -223,12 +223,8 @@ int aac_fib_setup(struct aac_dev * dev) struct fib *aac_fib_alloc_tag(struct aac_dev *dev, struct scsi_cmnd *scmd) { struct fib *fibptr; - u32 blk_tag; - int i; - blk_tag = blk_mq_unique_tag(scsi_cmd_to_rq(scmd)); - i = blk_mq_unique_tag_to_tag(blk_tag); - fibptr = &dev->fibs[i]; + fibptr = &dev->fibs[scsi_cmd_to_rq(scmd)->tag]; /* * Null out fields that depend on being zero at the start of * each I/O diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c index c4a36c0be527..68f4dbcfff49 100644 --- a/drivers/scsi/aacraid/linit.c +++ b/drivers/scsi/aacraid/linit.c @@ -19,7 +19,6 @@ #include <linux/compat.h> #include <linux/blkdev.h> -#include <linux/blk-mq-pci.h> #include <linux/completion.h> #include <linux/init.h> #include <linux/interrupt.h> @@ -505,15 +504,6 @@ common_config: return 0; } -static void aac_map_queues(struct Scsi_Host *shost) -{ - struct aac_dev *aac = (struct aac_dev *)shost->hostdata; - - blk_mq_pci_map_queues(&shost->tag_set.map[HCTX_TYPE_DEFAULT], - aac->pdev, 0); - aac->use_map_queue = true; -} - /** * aac_change_queue_depth - alter queue depths * @sdev: SCSI device we are considering @@ -1498,7 +1488,6 @@ static const struct scsi_host_template aac_driver_template = { .bios_param = aac_biosparm, .shost_groups = aac_host_groups, .slave_configure = aac_slave_configure, - .map_queues = aac_map_queues, .change_queue_depth = aac_change_queue_depth, .sdev_groups = aac_dev_groups, .eh_abort_handler = aac_eh_abort, @@ -1786,8 +1775,6 @@ static int aac_probe_one(struct pci_dev *pdev, const struct pci_device_id *id) shost->max_lun = AAC_MAX_LUN; pci_set_drvdata(pdev, shost); - shost->nr_hw_queues = aac->max_msix; - shost->host_tagset = 1; error = scsi_add_host(shost, &pdev->dev); if (error) @@ -1919,7 +1906,6 @@ static void aac_remove_one(struct pci_dev *pdev) struct aac_dev *aac = (struct aac_dev *)shost->hostdata; aac_cancel_rescan_worker(aac); - aac->use_map_queue = false; scsi_remove_host(shost); __aac_shutdown(aac); diff --git a/drivers/scsi/aacraid/src.c b/drivers/scsi/aacraid/src.c index 61949f374188..11ef58204e96 100644 --- a/drivers/scsi/aacraid/src.c +++ b/drivers/scsi/aacraid/src.c @@ -493,10 +493,6 @@ static int aac_src_deliver_message(struct fib *fib) #endif u16 vector_no; - struct scsi_cmnd *scmd; - u32 blk_tag; - struct Scsi_Host *shost = dev->scsi_host_ptr; - struct blk_mq_queue_map *qmap; atomic_inc(&q->numpending); @@ -509,25 +505,8 @@ static int aac_src_deliver_message(struct fib *fib) if ((dev->comm_interface == AAC_COMM_MESSAGE_TYPE3) && dev->sa_firmware) vector_no = aac_get_vector(dev); - else { - if (!fib->vector_no || !fib->callback_data) { - if (shost && dev->use_map_queue) { - qmap = &shost->tag_set.map[HCTX_TYPE_DEFAULT]; - vector_no = qmap->mq_map[raw_smp_processor_id()]; - } - /* - * We hardcode the vector_no for - * reserved commands as a valid shost is - * absent during the init - */ - else - vector_no = 0; - } else { - scmd = (struct scsi_cmnd *)fib->callback_data; - blk_tag = blk_mq_unique_tag(scsi_cmd_to_rq(scmd)); - vector_no = blk_mq_unique_tag_to_hwq(blk_tag); - } - } + else + vector_no = fib->vector_no; if (native_hba) { if (fib->flags & FIB_CONTEXT_FLAG_NATIVE_HBA_TMF) { diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c index 05ddbb9bb7d8..451a58e0fd96 100644 --- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c +++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c @@ -429,7 +429,6 @@ static int bnx2fc_rcv(struct sk_buff *skb, struct net_device *dev, struct fcoe_ctlr *ctlr; struct fcoe_rcv_info *fr; struct fcoe_percpu_s *bg; - struct sk_buff *tmp_skb; interface = container_of(ptype, struct bnx2fc_interface, fcoe_packet_type); @@ -441,11 +440,9 @@ static int bnx2fc_rcv(struct sk_buff *skb, struct net_device *dev, goto err; } - tmp_skb = skb_share_check(skb, GFP_ATOMIC); - if (!tmp_skb) - goto err; - - skb = tmp_skb; + skb = skb_share_check(skb, GFP_ATOMIC); + if (!skb) + return -1; if (unlikely(eth_hdr(skb)->h_proto != htons(ETH_P_FCOE))) { printk(KERN_ERR PFX "bnx2fc_rcv: Wrong FC type frame\n"); diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index c67cdcdc3ba8..1223d34c04da 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -1152,6 +1152,7 @@ retry: scsi_log_send(scmd); scmd->submitter = SUBMITTED_BY_SCSI_ERROR_HANDLER; + scmd->flags |= SCMD_LAST; /* * Lock sdev->state_mutex to avoid that scsi_device_quiesce() can @@ -2459,6 +2460,7 @@ scsi_ioctl_reset(struct scsi_device *dev, int __user *arg) scsi_init_command(dev, scmd); scmd->submitter = SUBMITTED_BY_SCSI_RESET_IOCTL; + scmd->flags |= SCMD_LAST; memset(&scmd->sdb, 0, sizeof(scmd->sdb)); scmd->cmd_len = 0; diff --git a/drivers/soundwire/intel_ace2x.c b/drivers/soundwire/intel_ace2x.c index 82672fcbc2aa..8280baa3254b 100644 --- a/drivers/soundwire/intel_ace2x.c +++ b/drivers/soundwire/intel_ace2x.c @@ -23,8 +23,9 @@ static void intel_shim_vs_init(struct sdw_intel *sdw) { void __iomem *shim_vs = sdw->link_res->shim_vs; - u16 act = 0; + u16 act; + act = intel_readw(shim_vs, SDW_SHIM2_INTEL_VS_ACTMCTL); u16p_replace_bits(&act, 0x1, SDW_SHIM2_INTEL_VS_ACTMCTL_DOAIS); act |= SDW_SHIM2_INTEL_VS_ACTMCTL_DACTQE; act |= SDW_SHIM2_INTEL_VS_ACTMCTL_DODS; diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c index 69719b335bcb..f048b3d55b2e 100644 --- a/drivers/soundwire/stream.c +++ b/drivers/soundwire/stream.c @@ -742,14 +742,15 @@ error_1: * sdw_ml_sync_bank_switch: Multilink register bank switch * * @bus: SDW bus instance + * @multi_link: whether this is a multi-link stream with hardware-based sync * * Caller function should free the buffers on error */ -static int sdw_ml_sync_bank_switch(struct sdw_bus *bus) +static int sdw_ml_sync_bank_switch(struct sdw_bus *bus, bool multi_link) { unsigned long time_left; - if (!bus->multi_link) + if (!multi_link) return 0; /* Wait for completion of transfer */ @@ -847,7 +848,7 @@ static int do_bank_switch(struct sdw_stream_runtime *stream) bus->bank_switch_timeout = DEFAULT_BANK_SWITCH_TIMEOUT; /* Check if bank switch was successful */ - ret = sdw_ml_sync_bank_switch(bus); + ret = sdw_ml_sync_bank_switch(bus, multi_link); if (ret < 0) { dev_err(bus->dev, "multi link bank switch failed: %d\n", ret); diff --git a/drivers/spi/spi-atmel.c b/drivers/spi/spi-atmel.c index 6aa8adbe4170..bad34998454a 100644 --- a/drivers/spi/spi-atmel.c +++ b/drivers/spi/spi-atmel.c @@ -22,6 +22,7 @@ #include <linux/gpio/consumer.h> #include <linux/pinctrl/consumer.h> #include <linux/pm_runtime.h> +#include <linux/iopoll.h> #include <trace/events/spi.h> /* SPI register offsets */ @@ -233,9 +234,6 @@ */ #define DMA_MIN_BYTES 16 -#define SPI_DMA_MIN_TIMEOUT (msecs_to_jiffies(1000)) -#define SPI_DMA_TIMEOUT_PER_10K (msecs_to_jiffies(4)) - #define AUTOSUSPEND_TIMEOUT 2000 struct atmel_spi_caps { @@ -279,6 +277,7 @@ struct atmel_spi { bool keep_cs; u32 fifo_size; + bool last_polarity; u8 native_cs_free; u8 native_cs_for_gpio; }; @@ -292,6 +291,22 @@ struct atmel_spi_device { #define INVALID_DMA_ADDRESS 0xffffffff /* + * This frequency can be anything supported by the controller, but to avoid + * unnecessary delay, the highest possible frequency is chosen. + * + * This frequency is the highest possible which is not interfering with other + * chip select registers (see Note for Serial Clock Bit Rate configuration in + * Atmel-11121F-ATARM-SAMA5D3-Series-Datasheet_02-Feb-16, page 1283) + */ +#define DUMMY_MSG_FREQUENCY 0x02 +/* + * 8 bits is the minimum data the controller is capable of sending. + * + * This message can be anything as it should not be treated by any SPI device. + */ +#define DUMMY_MSG 0xAA + +/* * Version 2 of the SPI controller has * - CR.LASTXFER * - SPI_MR.DIV32 may become FDIV or must-be-zero (here: always zero) @@ -305,6 +320,43 @@ static bool atmel_spi_is_v2(struct atmel_spi *as) } /* + * Send a dummy message. + * + * This is sometimes needed when using a CS GPIO to force clock transition when + * switching between devices with different polarities. + */ +static void atmel_spi_send_dummy(struct atmel_spi *as, struct spi_device *spi, int chip_select) +{ + u32 status; + u32 csr; + + /* + * Set a clock frequency to allow sending message on SPI bus. + * The frequency here can be anything, but is needed for + * the controller to send the data. + */ + csr = spi_readl(as, CSR0 + 4 * chip_select); + csr = SPI_BFINS(SCBR, DUMMY_MSG_FREQUENCY, csr); + spi_writel(as, CSR0 + 4 * chip_select, csr); + + /* + * Read all data coming from SPI bus, needed to be able to send + * the message. + */ + spi_readl(as, RDR); + while (spi_readl(as, SR) & SPI_BIT(RDRF)) { + spi_readl(as, RDR); + cpu_relax(); + } + + spi_writel(as, TDR, DUMMY_MSG); + + readl_poll_timeout_atomic(as->regs + SPI_SR, status, + (status & SPI_BIT(TXEMPTY)), 1, 1000); +} + + +/* * Earlier SPI controllers (e.g. on at91rm9200) have a design bug whereby * they assume that spi slave device state will not change on deselect, so * that automagic deselection is OK. ("NPCSx rises if no data is to be @@ -320,11 +372,17 @@ static bool atmel_spi_is_v2(struct atmel_spi *as) * Master on Chip Select 0.") No workaround exists for that ... so for * nCS0 on that chip, we (a) don't use the GPIO, (b) can't support CS_HIGH, * and (c) will trigger that first erratum in some cases. + * + * When changing the clock polarity, the SPI controller waits for the next + * transmission to enforce the default clock state. This may be an issue when + * using a GPIO as Chip Select: the clock level is applied only when the first + * packet is sent, once the CS has already been asserted. The workaround is to + * avoid this by sending a first (dummy) message before toggling the CS state. */ - static void cs_activate(struct atmel_spi *as, struct spi_device *spi) { struct atmel_spi_device *asd = spi->controller_state; + bool new_polarity; int chip_select; u32 mr; @@ -353,6 +411,25 @@ static void cs_activate(struct atmel_spi *as, struct spi_device *spi) } mr = spi_readl(as, MR); + + /* + * Ensures the clock polarity is valid before we actually + * assert the CS to avoid spurious clock edges to be + * processed by the spi devices. + */ + if (spi_get_csgpiod(spi, 0)) { + new_polarity = (asd->csr & SPI_BIT(CPOL)) != 0; + if (new_polarity != as->last_polarity) { + /* + * Need to disable the GPIO before sending the dummy + * message because it is already set by the spi core. + */ + gpiod_set_value_cansleep(spi_get_csgpiod(spi, 0), 0); + atmel_spi_send_dummy(as, spi, chip_select); + as->last_polarity = new_polarity; + gpiod_set_value_cansleep(spi_get_csgpiod(spi, 0), 1); + } + } } else { u32 cpol = (spi->mode & SPI_CPOL) ? SPI_BIT(CPOL) : 0; int i; @@ -1336,12 +1413,10 @@ static int atmel_spi_one_transfer(struct spi_controller *host, } dma_timeout = msecs_to_jiffies(spi_controller_xfer_timeout(host, xfer)); - ret_timeout = wait_for_completion_interruptible_timeout(&as->xfer_completion, - dma_timeout); - if (ret_timeout <= 0) { - dev_err(&spi->dev, "spi transfer %s\n", - !ret_timeout ? "timeout" : "canceled"); - as->done_status = ret_timeout < 0 ? ret_timeout : -EIO; + ret_timeout = wait_for_completion_timeout(&as->xfer_completion, dma_timeout); + if (!ret_timeout) { + dev_err(&spi->dev, "spi transfer timeout\n"); + as->done_status = -EIO; } if (as->done_status) diff --git a/drivers/spi/spi-cadence.c b/drivers/spi/spi-cadence.c index 1f2f8c717df6..a50eb4db79de 100644 --- a/drivers/spi/spi-cadence.c +++ b/drivers/spi/spi-cadence.c @@ -451,7 +451,6 @@ static int cdns_transfer_one(struct spi_controller *ctlr, udelay(10); cdns_spi_process_fifo(xspi, xspi->tx_fifo_depth, 0); - spi_transfer_delay_exec(transfer); cdns_spi_write(xspi, CDNS_SPI_IER, CDNS_SPI_IXR_DEFAULT); return transfer->len; diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c index 498e35c8db2c..272bc871a848 100644 --- a/drivers/spi/spi-imx.c +++ b/drivers/spi/spi-imx.c @@ -659,11 +659,18 @@ static int mx51_ecspi_prepare_transfer(struct spi_imx_data *spi_imx, ctrl |= (spi_imx->target_burst * 8 - 1) << MX51_ECSPI_CTRL_BL_OFFSET; else { - if (spi_imx->count >= 512) - ctrl |= 0xFFF << MX51_ECSPI_CTRL_BL_OFFSET; - else - ctrl |= (spi_imx->count * spi_imx->bits_per_word - 1) + if (spi_imx->usedma) { + ctrl |= (spi_imx->bits_per_word * + spi_imx_bytes_per_word(spi_imx->bits_per_word) - 1) << MX51_ECSPI_CTRL_BL_OFFSET; + } else { + if (spi_imx->count >= MX51_ECSPI_CTRL_MAX_BURST) + ctrl |= (MX51_ECSPI_CTRL_MAX_BURST - 1) + << MX51_ECSPI_CTRL_BL_OFFSET; + else + ctrl |= (spi_imx->count * spi_imx->bits_per_word - 1) + << MX51_ECSPI_CTRL_BL_OFFSET; + } } /* set clock speed */ diff --git a/drivers/thunderbolt/debugfs.c b/drivers/thunderbolt/debugfs.c index c9ddd49138d8..e324cd899719 100644 --- a/drivers/thunderbolt/debugfs.c +++ b/drivers/thunderbolt/debugfs.c @@ -959,7 +959,7 @@ static void margining_port_remove(struct tb_port *port) snprintf(dir_name, sizeof(dir_name), "port%d", port->port); parent = debugfs_lookup(dir_name, port->sw->debugfs_dir); if (parent) - debugfs_remove_recursive(debugfs_lookup("margining", parent)); + debugfs_lookup_and_remove("margining", parent); kfree(port->usb4->margining); port->usb4->margining = NULL; diff --git a/drivers/thunderbolt/usb4.c b/drivers/thunderbolt/usb4.c index 4277733d0021..f8f0d24ff6e4 100644 --- a/drivers/thunderbolt/usb4.c +++ b/drivers/thunderbolt/usb4.c @@ -2311,13 +2311,13 @@ int usb4_usb3_port_release_bandwidth(struct tb_port *port, int *upstream_bw, goto err_request; /* - * Always keep 1000 Mb/s to make sure xHCI has at least some + * Always keep 900 Mb/s to make sure xHCI has at least some * bandwidth available for isochronous traffic. */ - if (consumed_up < 1000) - consumed_up = 1000; - if (consumed_down < 1000) - consumed_down = 1000; + if (consumed_up < 900) + consumed_up = 900; + if (consumed_down < 900) + consumed_down = 900; ret = usb4_usb3_port_write_allocated_bandwidth(port, consumed_up, consumed_down); diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index bce0d2a9a7f3..16d76325039a 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -2274,9 +2274,10 @@ void ufshcd_send_command(struct ufs_hba *hba, unsigned int task_tag, if (is_mcq_enabled(hba)) { int utrd_size = sizeof(struct utp_transfer_req_desc); struct utp_transfer_req_desc *src = lrbp->utr_descriptor_ptr; - struct utp_transfer_req_desc *dest = hwq->sqe_base_addr + hwq->sq_tail_slot; + struct utp_transfer_req_desc *dest; spin_lock(&hwq->sq_lock); + dest = hwq->sqe_base_addr + hwq->sq_tail_slot; memcpy(dest, src, utrd_size); ufshcd_inc_sq_tail(hwq); spin_unlock(&hwq->sq_lock); diff --git a/drivers/ufs/host/ufs-qcom.c b/drivers/ufs/host/ufs-qcom.c index 96cb8b5b4e66..17e24270477d 100644 --- a/drivers/ufs/host/ufs-qcom.c +++ b/drivers/ufs/host/ufs-qcom.c @@ -1516,9 +1516,11 @@ static int ufs_qcom_clk_scale_notify(struct ufs_hba *hba, err = ufs_qcom_clk_scale_up_pre_change(hba); else err = ufs_qcom_clk_scale_down_pre_change(hba); - if (err) - ufshcd_uic_hibern8_exit(hba); + if (err) { + ufshcd_uic_hibern8_exit(hba); + return err; + } } else { if (scale_up) err = ufs_qcom_clk_scale_up_post_change(hba); diff --git a/drivers/ufs/host/ufshcd-pltfrm.c b/drivers/ufs/host/ufshcd-pltfrm.c index da2558e274b4..db9d9365ff55 100644 --- a/drivers/ufs/host/ufshcd-pltfrm.c +++ b/drivers/ufs/host/ufshcd-pltfrm.c @@ -8,6 +8,7 @@ * Vinayak Holikatti <h.vinayak@samsung.com> */ +#include <linux/clk.h> #include <linux/module.h> #include <linux/platform_device.h> #include <linux/pm_opp.h> @@ -213,6 +214,55 @@ static void ufshcd_init_lanes_per_dir(struct ufs_hba *hba) } } +/** + * ufshcd_parse_clock_min_max_freq - Parse MIN and MAX clocks freq + * @hba: per adapter instance + * + * This function parses MIN and MAX frequencies of all clocks required + * by the host drivers. + * + * Returns 0 for success and non-zero for failure + */ +static int ufshcd_parse_clock_min_max_freq(struct ufs_hba *hba) +{ + struct list_head *head = &hba->clk_list_head; + struct ufs_clk_info *clki; + struct dev_pm_opp *opp; + unsigned long freq; + u8 idx = 0; + + list_for_each_entry(clki, head, list) { + if (!clki->name) + continue; + + clki->clk = devm_clk_get(hba->dev, clki->name); + if (IS_ERR(clki->clk)) + continue; + + /* Find Max Freq */ + freq = ULONG_MAX; + opp = dev_pm_opp_find_freq_floor_indexed(hba->dev, &freq, idx); + if (IS_ERR(opp)) { + dev_err(hba->dev, "Failed to find OPP for MAX frequency\n"); + return PTR_ERR(opp); + } + clki->max_freq = dev_pm_opp_get_freq_indexed(opp, idx); + dev_pm_opp_put(opp); + + /* Find Min Freq */ + freq = 0; + opp = dev_pm_opp_find_freq_ceil_indexed(hba->dev, &freq, idx); + if (IS_ERR(opp)) { + dev_err(hba->dev, "Failed to find OPP for MIN frequency\n"); + return PTR_ERR(opp); + } + clki->min_freq = dev_pm_opp_get_freq_indexed(opp, idx++); + dev_pm_opp_put(opp); + } + + return 0; +} + static int ufshcd_parse_operating_points(struct ufs_hba *hba) { struct device *dev = hba->dev; @@ -279,6 +329,10 @@ static int ufshcd_parse_operating_points(struct ufs_hba *hba) return ret; } + ret = ufshcd_parse_clock_min_max_freq(hba); + if (ret) + return ret; + hba->use_pm_opp = true; return 0; diff --git a/drivers/usb/fotg210/fotg210-hcd.c b/drivers/usb/fotg210/fotg210-hcd.c index 929106c16b29..7bf810a0c98a 100644 --- a/drivers/usb/fotg210/fotg210-hcd.c +++ b/drivers/usb/fotg210/fotg210-hcd.c @@ -428,8 +428,6 @@ static void qh_lines(struct fotg210_hcd *fotg210, struct fotg210_qh *qh, temp = size; size -= temp; next += temp; - if (temp == size) - goto done; } temp = snprintf(next, size, "\n"); @@ -439,7 +437,6 @@ static void qh_lines(struct fotg210_hcd *fotg210, struct fotg210_qh *qh, size -= temp; next += temp; -done: *sizep = size; *nextp = next; } diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index efe3e3b85769..fdd0fc7b8f25 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -831,7 +831,7 @@ static void ffs_user_copy_worker(struct work_struct *work) io_data->kiocb->ki_complete(io_data->kiocb, ret); if (io_data->ffs->ffs_eventfd && !kiocb_has_eventfd) - eventfd_signal(io_data->ffs->ffs_eventfd, 1); + eventfd_signal(io_data->ffs->ffs_eventfd); if (io_data->read) kfree(io_data->to_free); @@ -2738,7 +2738,7 @@ static void __ffs_event_add(struct ffs_data *ffs, ffs->ev.types[ffs->ev.count++] = type; wake_up_locked(&ffs->ev.waitq); if (ffs->ffs_eventfd) - eventfd_signal(ffs->ffs_eventfd, 1); + eventfd_signal(ffs->ffs_eventfd); } static void ffs_event_add(struct ffs_data *ffs, diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index 1bf23611be12..13a56783830d 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -1033,9 +1033,9 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(FTDI_VID, ACTISENSE_USG_PID) }, { USB_DEVICE(FTDI_VID, ACTISENSE_NGT_PID) }, { USB_DEVICE(FTDI_VID, ACTISENSE_NGW_PID) }, - { USB_DEVICE(FTDI_VID, ACTISENSE_D9AC_PID) }, - { USB_DEVICE(FTDI_VID, ACTISENSE_D9AD_PID) }, - { USB_DEVICE(FTDI_VID, ACTISENSE_D9AE_PID) }, + { USB_DEVICE(FTDI_VID, ACTISENSE_UID_PID) }, + { USB_DEVICE(FTDI_VID, ACTISENSE_USA_PID) }, + { USB_DEVICE(FTDI_VID, ACTISENSE_NGX_PID) }, { USB_DEVICE(FTDI_VID, ACTISENSE_D9AF_PID) }, { USB_DEVICE(FTDI_VID, CHETCO_SEAGAUGE_PID) }, { USB_DEVICE(FTDI_VID, CHETCO_SEASWITCH_PID) }, diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h index e2099445db70..21a2b5a25fc0 100644 --- a/drivers/usb/serial/ftdi_sio_ids.h +++ b/drivers/usb/serial/ftdi_sio_ids.h @@ -1568,9 +1568,9 @@ #define ACTISENSE_USG_PID 0xD9A9 /* USG USB Serial Adapter */ #define ACTISENSE_NGT_PID 0xD9AA /* NGT NMEA2000 Interface */ #define ACTISENSE_NGW_PID 0xD9AB /* NGW NMEA2000 Gateway */ -#define ACTISENSE_D9AC_PID 0xD9AC /* Actisense Reserved */ -#define ACTISENSE_D9AD_PID 0xD9AD /* Actisense Reserved */ -#define ACTISENSE_D9AE_PID 0xD9AE /* Actisense Reserved */ +#define ACTISENSE_UID_PID 0xD9AC /* USB Isolating Device */ +#define ACTISENSE_USA_PID 0xD9AD /* USB to Serial Adapter */ +#define ACTISENSE_NGX_PID 0xD9AE /* NGX NMEA2000 Gateway */ #define ACTISENSE_D9AF_PID 0xD9AF /* Actisense Reserved */ #define CHETCO_SEAGAUGE_PID 0xA548 /* SeaGauge USB Adapter */ #define CHETCO_SEASWITCH_PID 0xA549 /* SeaSwitch USB Adapter */ diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 4dffcfefd62d..72390dbf0769 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -272,6 +272,7 @@ static void option_instat_callback(struct urb *urb); #define QUECTEL_PRODUCT_RM500Q 0x0800 #define QUECTEL_PRODUCT_RM520N 0x0801 #define QUECTEL_PRODUCT_EC200U 0x0901 +#define QUECTEL_PRODUCT_EG912Y 0x6001 #define QUECTEL_PRODUCT_EC200S_CN 0x6002 #define QUECTEL_PRODUCT_EC200A 0x6005 #define QUECTEL_PRODUCT_EM061K_LWW 0x6008 @@ -1232,6 +1233,7 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, 0x0700, 0xff), /* BG95 */ .driver_info = RSVD(3) | ZLP }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500Q, 0xff, 0xff, 0x30) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500Q, 0xff, 0, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500Q, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500Q, 0xff, 0xff, 0x10), .driver_info = ZLP }, @@ -1244,6 +1246,7 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200U, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200S_CN, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200T, 0xff, 0, 0) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EG912Y, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500K, 0xff, 0x00, 0x00) }, { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6001) }, @@ -2242,6 +2245,8 @@ static const struct usb_device_id option_ids[] = { .driver_info = RSVD(0) | RSVD(1) | RSVD(6) }, { USB_DEVICE(0x0489, 0xe0b5), /* Foxconn T77W968 ESIM */ .driver_info = RSVD(0) | RSVD(1) | RSVD(6) }, + { USB_DEVICE_INTERFACE_CLASS(0x0489, 0xe0da, 0xff), /* Foxconn T99W265 MBIM variant */ + .driver_info = RSVD(3) | RSVD(5) }, { USB_DEVICE_INTERFACE_CLASS(0x0489, 0xe0db, 0xff), /* Foxconn T99W265 MBIM */ .driver_info = RSVD(3) }, { USB_DEVICE_INTERFACE_CLASS(0x0489, 0xe0ee, 0xff), /* Foxconn T99W368 MBIM */ diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h index 20dcbccb290b..fd68204374f2 100644 --- a/drivers/usb/storage/unusual_devs.h +++ b/drivers/usb/storage/unusual_devs.h @@ -1306,6 +1306,17 @@ UNUSUAL_DEV( 0x090c, 0x6000, 0x0100, 0x0100, US_FL_INITIAL_READ10 ), /* + * Patch by Tasos Sahanidis <tasos@tasossah.com> + * This flash drive always shows up with write protect enabled + * during the first mode sense. + */ +UNUSUAL_DEV(0x0951, 0x1697, 0x0100, 0x0100, + "Kingston", + "DT Ultimate G3", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_NO_WP_DETECT), + +/* * This Pentax still camera is not conformant * to the USB storage specification: - * - It does not like the INQUIRY command. So we must handle this command diff --git a/drivers/usb/typec/ucsi/ucsi_glink.c b/drivers/usb/typec/ucsi/ucsi_glink.c index db6e248f8208..4853141cd10c 100644 --- a/drivers/usb/typec/ucsi/ucsi_glink.c +++ b/drivers/usb/typec/ucsi/ucsi_glink.c @@ -228,7 +228,7 @@ static void pmic_glink_ucsi_notify(struct work_struct *work) con_num = UCSI_CCI_CONNECTOR(cci); if (con_num) { - if (con_num < PMIC_GLINK_MAX_PORTS && + if (con_num <= PMIC_GLINK_MAX_PORTS && ucsi->port_orientation[con_num - 1]) { int orientation = gpiod_get_value(ucsi->port_orientation[con_num - 1]); diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c index 0ddd4b8abecb..1d24da79c399 100644 --- a/drivers/vdpa/vdpa_user/vduse_dev.c +++ b/drivers/vdpa/vdpa_user/vduse_dev.c @@ -493,7 +493,7 @@ static void vduse_vq_kick(struct vduse_virtqueue *vq) goto unlock; if (vq->kickfd) - eventfd_signal(vq->kickfd, 1); + eventfd_signal(vq->kickfd); else vq->kicked = true; unlock: @@ -911,7 +911,7 @@ static int vduse_kickfd_setup(struct vduse_dev *dev, eventfd_ctx_put(vq->kickfd); vq->kickfd = ctx; if (vq->ready && vq->kicked && vq->kickfd) { - eventfd_signal(vq->kickfd, 1); + eventfd_signal(vq->kickfd); vq->kicked = false; } spin_unlock(&vq->kick_lock); @@ -960,7 +960,7 @@ static bool vduse_vq_signal_irqfd(struct vduse_virtqueue *vq) spin_lock_irq(&vq->irq_lock); if (vq->ready && vq->cb.trigger) { - eventfd_signal(vq->cb.trigger, 1); + eventfd_signal(vq->cb.trigger); signal = true; } spin_unlock_irq(&vq->irq_lock); @@ -1157,7 +1157,7 @@ static long vduse_dev_ioctl(struct file *file, unsigned int cmd, fput(f); break; } - ret = receive_fd(f, perm_to_file_flags(entry.perm)); + ret = receive_fd(f, NULL, perm_to_file_flags(entry.perm)); fput(f); break; } diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c b/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c index c51229fccbd6..d62fbfff20b8 100644 --- a/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c +++ b/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c @@ -54,7 +54,7 @@ static irqreturn_t vfio_fsl_mc_irq_handler(int irq_num, void *arg) { struct vfio_fsl_mc_irq *mc_irq = (struct vfio_fsl_mc_irq *)arg; - eventfd_signal(mc_irq->trigger, 1); + eventfd_signal(mc_irq->trigger); return IRQ_HANDLED; } diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index 1929103ee59a..1cbc990d42e0 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -443,7 +443,7 @@ static int vfio_pci_core_runtime_resume(struct device *dev) */ down_write(&vdev->memory_lock); if (vdev->pm_wake_eventfd_ctx) { - eventfd_signal(vdev->pm_wake_eventfd_ctx, 1); + eventfd_signal(vdev->pm_wake_eventfd_ctx); __vfio_pci_runtime_pm_exit(vdev); } up_write(&vdev->memory_lock); @@ -1883,7 +1883,7 @@ void vfio_pci_core_request(struct vfio_device *core_vdev, unsigned int count) pci_notice_ratelimited(pdev, "Relaying device request to user (#%u)\n", count); - eventfd_signal(vdev->req_trigger, 1); + eventfd_signal(vdev->req_trigger); } else if (count == 0) { pci_warn(pdev, "No device request channel registered, blocked until released by user\n"); @@ -2302,7 +2302,7 @@ pci_ers_result_t vfio_pci_core_aer_err_detected(struct pci_dev *pdev, mutex_lock(&vdev->igate); if (vdev->err_trigger) - eventfd_signal(vdev->err_trigger, 1); + eventfd_signal(vdev->err_trigger); mutex_unlock(&vdev->igate); diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c index cbb4bcbfbf83..237beac83809 100644 --- a/drivers/vfio/pci/vfio_pci_intrs.c +++ b/drivers/vfio/pci/vfio_pci_intrs.c @@ -94,7 +94,7 @@ static void vfio_send_intx_eventfd(void *opaque, void *unused) ctx = vfio_irq_ctx_get(vdev, 0); if (WARN_ON_ONCE(!ctx)) return; - eventfd_signal(ctx->trigger, 1); + eventfd_signal(ctx->trigger); } } @@ -342,7 +342,7 @@ static irqreturn_t vfio_msihandler(int irq, void *arg) { struct eventfd_ctx *trigger = arg; - eventfd_signal(trigger, 1); + eventfd_signal(trigger); return IRQ_HANDLED; } @@ -689,11 +689,11 @@ static int vfio_pci_set_msi_trigger(struct vfio_pci_core_device *vdev, if (!ctx) continue; if (flags & VFIO_IRQ_SET_DATA_NONE) { - eventfd_signal(ctx->trigger, 1); + eventfd_signal(ctx->trigger); } else if (flags & VFIO_IRQ_SET_DATA_BOOL) { uint8_t *bools = data; if (bools[i - start]) - eventfd_signal(ctx->trigger, 1); + eventfd_signal(ctx->trigger); } } return 0; @@ -707,7 +707,7 @@ static int vfio_pci_set_ctx_trigger_single(struct eventfd_ctx **ctx, if (flags & VFIO_IRQ_SET_DATA_NONE) { if (*ctx) { if (count) { - eventfd_signal(*ctx, 1); + eventfd_signal(*ctx); } else { eventfd_ctx_put(*ctx); *ctx = NULL; @@ -722,7 +722,7 @@ static int vfio_pci_set_ctx_trigger_single(struct eventfd_ctx **ctx, trigger = *(uint8_t *)data; if (trigger && *ctx) - eventfd_signal(*ctx, 1); + eventfd_signal(*ctx); return 0; } else if (flags & VFIO_IRQ_SET_DATA_EVENTFD) { diff --git a/drivers/vfio/platform/vfio_platform_irq.c b/drivers/vfio/platform/vfio_platform_irq.c index 665197caed89..61a1bfb68ac7 100644 --- a/drivers/vfio/platform/vfio_platform_irq.c +++ b/drivers/vfio/platform/vfio_platform_irq.c @@ -155,7 +155,7 @@ static irqreturn_t vfio_automasked_irq_handler(int irq, void *dev_id) spin_unlock_irqrestore(&irq_ctx->lock, flags); if (ret == IRQ_HANDLED) - eventfd_signal(irq_ctx->trigger, 1); + eventfd_signal(irq_ctx->trigger); return ret; } @@ -164,7 +164,7 @@ static irqreturn_t vfio_irq_handler(int irq, void *dev_id) { struct vfio_platform_irq *irq_ctx = dev_id; - eventfd_signal(irq_ctx->trigger, 1); + eventfd_signal(irq_ctx->trigger); return IRQ_HANDLED; } diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index da7ec77cdaff..173beda74b38 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -178,7 +178,7 @@ static irqreturn_t vhost_vdpa_virtqueue_cb(void *private) struct eventfd_ctx *call_ctx = vq->call_ctx.ctx; if (call_ctx) - eventfd_signal(call_ctx, 1); + eventfd_signal(call_ctx); return IRQ_HANDLED; } @@ -189,7 +189,7 @@ static irqreturn_t vhost_vdpa_config_cb(void *private) struct eventfd_ctx *config_ctx = v->config_ctx; if (config_ctx) - eventfd_signal(config_ctx, 1); + eventfd_signal(config_ctx); return IRQ_HANDLED; } diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index e0c181ad17e3..045f666b4f12 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -2248,7 +2248,7 @@ int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log, len -= l; if (!len) { if (vq->log_ctx) - eventfd_signal(vq->log_ctx, 1); + eventfd_signal(vq->log_ctx); return 0; } } @@ -2271,7 +2271,7 @@ static int vhost_update_used_flags(struct vhost_virtqueue *vq) log_used(vq, (used - (void __user *)vq->used), sizeof vq->used->flags); if (vq->log_ctx) - eventfd_signal(vq->log_ctx, 1); + eventfd_signal(vq->log_ctx); } return 0; } @@ -2289,7 +2289,7 @@ static int vhost_update_avail_event(struct vhost_virtqueue *vq) log_used(vq, (used - (void __user *)vq->used), sizeof *vhost_avail_event(vq)); if (vq->log_ctx) - eventfd_signal(vq->log_ctx, 1); + eventfd_signal(vq->log_ctx); } return 0; } @@ -2715,7 +2715,7 @@ int vhost_add_used_n(struct vhost_virtqueue *vq, struct vring_used_elem *heads, log_used(vq, offsetof(struct vring_used, idx), sizeof vq->used->idx); if (vq->log_ctx) - eventfd_signal(vq->log_ctx, 1); + eventfd_signal(vq->log_ctx); } return r; } @@ -2763,7 +2763,7 @@ void vhost_signal(struct vhost_dev *dev, struct vhost_virtqueue *vq) { /* Signal the Guest tell them we used something up. */ if (vq->call_ctx.ctx && vhost_notify(dev, vq)) - eventfd_signal(vq->call_ctx.ctx, 1); + eventfd_signal(vq->call_ctx.ctx); } EXPORT_SYMBOL_GPL(vhost_signal); diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index f60d5f7bef94..9e942fcda5c3 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -249,7 +249,7 @@ void vhost_iotlb_map_free(struct vhost_iotlb *iotlb, #define vq_err(vq, fmt, ...) do { \ pr_debug(pr_fmt(fmt), ##__VA_ARGS__); \ if ((vq)->error_ctx) \ - eventfd_signal((vq)->error_ctx, 1);\ + eventfd_signal((vq)->error_ctx);\ } while (0) enum { diff --git a/drivers/virt/acrn/ioeventfd.c b/drivers/virt/acrn/ioeventfd.c index ac4037e9f947..4e845c6ca0b5 100644 --- a/drivers/virt/acrn/ioeventfd.c +++ b/drivers/virt/acrn/ioeventfd.c @@ -223,7 +223,7 @@ static int acrn_ioeventfd_handler(struct acrn_ioreq_client *client, mutex_lock(&client->vm->ioeventfds_lock); p = hsm_ioeventfd_match(client->vm, addr, val, size, req->type); if (p) - eventfd_signal(p->eventfd, 1); + eventfd_signal(p->eventfd); mutex_unlock(&client->vm->ioeventfds_lock); return 0; diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 51d8f3299c10..49299b1f9ec7 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -3219,8 +3219,7 @@ void virtqueue_dma_sync_single_range_for_cpu(struct virtqueue *_vq, if (!vq->use_dma_api) return; - dma_sync_single_range_for_cpu(dev, addr, offset, size, - DMA_BIDIRECTIONAL); + dma_sync_single_range_for_cpu(dev, addr, offset, size, dir); } EXPORT_SYMBOL_GPL(virtqueue_dma_sync_single_range_for_cpu); @@ -3246,8 +3245,7 @@ void virtqueue_dma_sync_single_range_for_device(struct virtqueue *_vq, if (!vq->use_dma_api) return; - dma_sync_single_range_for_device(dev, addr, offset, size, - DMA_BIDIRECTIONAL); + dma_sync_single_range_for_device(dev, addr, offset, size, dir); } EXPORT_SYMBOL_GPL(virtqueue_dma_sync_single_range_for_device); diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c index 0eb337a8ec0f..35b6e306026a 100644 --- a/drivers/xen/privcmd.c +++ b/drivers/xen/privcmd.c @@ -1147,7 +1147,7 @@ static irqreturn_t ioeventfd_interrupt(int irq, void *dev_id) if (ioreq->addr == kioeventfd->addr + VIRTIO_MMIO_QUEUE_NOTIFY && ioreq->size == kioeventfd->addr_len && (ioreq->data & QUEUE_NOTIFY_VQ_MASK) == kioeventfd->vq) { - eventfd_signal(kioeventfd->eventfd, 1); + eventfd_signal(kioeventfd->eventfd); state = STATE_IORESP_READY; break; } diff --git a/fs/Kconfig b/fs/Kconfig index 42837617a55b..231c7703793a 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -18,6 +18,10 @@ config VALIDATE_FS_PARSER config FS_IOMAP bool +# Stackable filesystems +config FS_STACK + bool + config BUFFER_HEAD bool diff --git a/fs/Makefile b/fs/Makefile index 75522f88e763..a6962c588962 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -39,6 +39,7 @@ obj-$(CONFIG_COMPAT_BINFMT_ELF) += compat_binfmt_elf.o obj-$(CONFIG_BINFMT_ELF_FDPIC) += binfmt_elf_fdpic.o obj-$(CONFIG_BINFMT_FLAT) += binfmt_flat.o +obj-$(CONFIG_FS_STACK) += backing-file.o obj-$(CONFIG_FS_MBCACHE) += mbcache.o obj-$(CONFIG_FS_POSIX_ACL) += posix_acl.o obj-$(CONFIG_NFS_COMMON) += nfs_common/ diff --git a/fs/afs/cell.c b/fs/afs/cell.c index 988c2ac7cece..926cb1188eba 100644 --- a/fs/afs/cell.c +++ b/fs/afs/cell.c @@ -409,10 +409,12 @@ static int afs_update_cell(struct afs_cell *cell) if (ret == -ENOMEM) goto out_wake; - ret = -ENOMEM; vllist = afs_alloc_vlserver_list(0); - if (!vllist) + if (!vllist) { + if (ret >= 0) + ret = -ENOMEM; goto out_wake; + } switch (ret) { case -ENODATA: diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c index 1fa8cf23bd36..1f656005018e 100644 --- a/fs/afs/dynroot.c +++ b/fs/afs/dynroot.c @@ -114,6 +114,7 @@ static int afs_probe_cell_name(struct dentry *dentry) struct afs_net *net = afs_d2net(dentry); const char *name = dentry->d_name.name; size_t len = dentry->d_name.len; + char *result = NULL; int ret; /* Names prefixed with a dot are R/W mounts. */ @@ -131,9 +132,22 @@ static int afs_probe_cell_name(struct dentry *dentry) } ret = dns_query(net->net, "afsdb", name, len, "srv=1", - NULL, NULL, false); - if (ret == -ENODATA || ret == -ENOKEY) + &result, NULL, false); + if (ret == -ENODATA || ret == -ENOKEY || ret == 0) ret = -ENOENT; + if (ret > 0 && ret >= sizeof(struct dns_server_list_v1_header)) { + struct dns_server_list_v1_header *v1 = (void *)result; + + if (v1->hdr.zero == 0 && + v1->hdr.content == DNS_PAYLOAD_IS_SERVER_LIST && + v1->hdr.version == 1 && + (v1->status != DNS_LOOKUP_GOOD && + v1->status != DNS_LOOKUP_GOOD_WITH_BAD)) + return -ENOENT; + + } + + kfree(result); return ret; } @@ -252,20 +266,9 @@ static int afs_dynroot_d_revalidate(struct dentry *dentry, unsigned int flags) return 1; } -/* - * Allow the VFS to enquire as to whether a dentry should be unhashed (mustn't - * sleep) - * - called from dput() when d_count is going to 0. - * - return 1 to request dentry be unhashed, 0 otherwise - */ -static int afs_dynroot_d_delete(const struct dentry *dentry) -{ - return d_really_is_positive(dentry); -} - const struct dentry_operations afs_dynroot_dentry_operations = { .d_revalidate = afs_dynroot_d_revalidate, - .d_delete = afs_dynroot_d_delete, + .d_delete = always_delete_dentry, .d_release = afs_d_release, .d_automount = afs_d_automount, }; diff --git a/fs/afs/internal.h b/fs/afs/internal.h index a812952be1c9..7385d62c8cf5 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -586,6 +586,7 @@ struct afs_volume { #define AFS_VOLUME_OFFLINE 4 /* - T if volume offline notice given */ #define AFS_VOLUME_BUSY 5 /* - T if volume busy notice given */ #define AFS_VOLUME_MAYBE_NO_IBULK 6 /* - T if some servers don't have InlineBulkStatus */ +#define AFS_VOLUME_RM_TREE 7 /* - Set if volume removed from cell->volumes */ #ifdef CONFIG_AFS_FSCACHE struct fscache_volume *cache; /* Caching cookie */ #endif @@ -1513,6 +1514,7 @@ extern struct afs_vlserver_list *afs_extract_vlserver_list(struct afs_cell *, extern struct afs_volume *afs_create_volume(struct afs_fs_context *); extern int afs_activate_volume(struct afs_volume *); extern void afs_deactivate_volume(struct afs_volume *); +bool afs_try_get_volume(struct afs_volume *volume, enum afs_volume_trace reason); extern struct afs_volume *afs_get_volume(struct afs_volume *, enum afs_volume_trace); extern void afs_put_volume(struct afs_net *, struct afs_volume *, enum afs_volume_trace); extern int afs_check_volume_status(struct afs_volume *, struct afs_operation *); diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index ed1644e7683f..d642d06a453b 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -424,7 +424,7 @@ error_kill_call: if (call->async) { if (cancel_work_sync(&call->async_work)) afs_put_call(call); - afs_put_call(call); + afs_set_call_complete(call, ret, 0); } ac->error = ret; diff --git a/fs/afs/volume.c b/fs/afs/volume.c index 29d483c80281..115c081a8e2c 100644 --- a/fs/afs/volume.c +++ b/fs/afs/volume.c @@ -32,8 +32,13 @@ static struct afs_volume *afs_insert_volume_into_cell(struct afs_cell *cell, } else if (p->vid > volume->vid) { pp = &(*pp)->rb_right; } else { - volume = afs_get_volume(p, afs_volume_trace_get_cell_insert); - goto found; + if (afs_try_get_volume(p, afs_volume_trace_get_cell_insert)) { + volume = p; + goto found; + } + + set_bit(AFS_VOLUME_RM_TREE, &volume->flags); + rb_replace_node_rcu(&p->cell_node, &volume->cell_node, &cell->volumes); } } @@ -56,7 +61,8 @@ static void afs_remove_volume_from_cell(struct afs_volume *volume) afs_volume_trace_remove); write_seqlock(&cell->volume_lock); hlist_del_rcu(&volume->proc_link); - rb_erase(&volume->cell_node, &cell->volumes); + if (!test_and_set_bit(AFS_VOLUME_RM_TREE, &volume->flags)) + rb_erase(&volume->cell_node, &cell->volumes); write_sequnlock(&cell->volume_lock); } } @@ -232,6 +238,20 @@ static void afs_destroy_volume(struct afs_net *net, struct afs_volume *volume) } /* + * Try to get a reference on a volume record. + */ +bool afs_try_get_volume(struct afs_volume *volume, enum afs_volume_trace reason) +{ + int r; + + if (__refcount_inc_not_zero(&volume->ref, &r)) { + trace_afs_volume(volume->vid, r + 1, reason); + return true; + } + return false; +} + +/* * Get a reference on a volume record. */ struct afs_volume *afs_get_volume(struct afs_volume *volume, @@ -266,7 +266,7 @@ static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages) return ERR_CAST(inode); inode->i_mapping->a_ops = &aio_ctx_aops; - inode->i_mapping->private_data = ctx; + inode->i_mapping->i_private_data = ctx; inode->i_size = PAGE_SIZE * nr_pages; file = alloc_file_pseudo(inode, aio_mnt, "[aio]", @@ -316,10 +316,10 @@ static void put_aio_ring_file(struct kioctx *ctx) /* Prevent further access to the kioctx from migratepages */ i_mapping = aio_ring_file->f_mapping; - spin_lock(&i_mapping->private_lock); - i_mapping->private_data = NULL; + spin_lock(&i_mapping->i_private_lock); + i_mapping->i_private_data = NULL; ctx->aio_ring_file = NULL; - spin_unlock(&i_mapping->private_lock); + spin_unlock(&i_mapping->i_private_lock); fput(aio_ring_file); } @@ -422,9 +422,9 @@ static int aio_migrate_folio(struct address_space *mapping, struct folio *dst, rc = 0; - /* mapping->private_lock here protects against the kioctx teardown. */ - spin_lock(&mapping->private_lock); - ctx = mapping->private_data; + /* mapping->i_private_lock here protects against the kioctx teardown. */ + spin_lock(&mapping->i_private_lock); + ctx = mapping->i_private_data; if (!ctx) { rc = -EINVAL; goto out; @@ -476,7 +476,7 @@ static int aio_migrate_folio(struct address_space *mapping, struct folio *dst, out_unlock: mutex_unlock(&ctx->ring_lock); out: - spin_unlock(&mapping->private_lock); + spin_unlock(&mapping->i_private_lock); return rc; } #else @@ -1106,6 +1106,11 @@ static inline void iocb_destroy(struct aio_kiocb *iocb) kmem_cache_free(kiocb_cachep, iocb); } +struct aio_waiter { + struct wait_queue_entry w; + size_t min_nr; +}; + /* aio_complete * Called when the io request on the given iocb is complete. */ @@ -1114,7 +1119,7 @@ static void aio_complete(struct aio_kiocb *iocb) struct kioctx *ctx = iocb->ki_ctx; struct aio_ring *ring; struct io_event *ev_page, *event; - unsigned tail, pos, head; + unsigned tail, pos, head, avail; unsigned long flags; /* @@ -1156,6 +1161,10 @@ static void aio_complete(struct aio_kiocb *iocb) ctx->completed_events++; if (ctx->completed_events > 1) refill_reqs_available(ctx, head, tail); + + avail = tail > head + ? tail - head + : tail + ctx->nr_events - head; spin_unlock_irqrestore(&ctx->completion_lock, flags); pr_debug("added to ring %p at [%u]\n", iocb, tail); @@ -1166,7 +1175,7 @@ static void aio_complete(struct aio_kiocb *iocb) * from IRQ context. */ if (iocb->ki_eventfd) - eventfd_signal(iocb->ki_eventfd, 1); + eventfd_signal(iocb->ki_eventfd); /* * We have to order our ring_info tail store above and test @@ -1176,8 +1185,18 @@ static void aio_complete(struct aio_kiocb *iocb) */ smp_mb(); - if (waitqueue_active(&ctx->wait)) - wake_up(&ctx->wait); + if (waitqueue_active(&ctx->wait)) { + struct aio_waiter *curr, *next; + unsigned long flags; + + spin_lock_irqsave(&ctx->wait.lock, flags); + list_for_each_entry_safe(curr, next, &ctx->wait.head, w.entry) + if (avail >= curr->min_nr) { + list_del_init_careful(&curr->w.entry); + wake_up_process(curr->w.private); + } + spin_unlock_irqrestore(&ctx->wait.lock, flags); + } } static inline void iocb_put(struct aio_kiocb *iocb) @@ -1290,7 +1309,9 @@ static long read_events(struct kioctx *ctx, long min_nr, long nr, struct io_event __user *event, ktime_t until) { - long ret = 0; + struct hrtimer_sleeper t; + struct aio_waiter w; + long ret = 0, ret2 = 0; /* * Note that aio_read_events() is being called as the conditional - i.e. @@ -1306,12 +1327,38 @@ static long read_events(struct kioctx *ctx, long min_nr, long nr, * the ringbuffer empty. So in practice we should be ok, but it's * something to be aware of when touching this code. */ - if (until == 0) - aio_read_events(ctx, min_nr, nr, event, &ret); - else - wait_event_interruptible_hrtimeout(ctx->wait, - aio_read_events(ctx, min_nr, nr, event, &ret), - until); + aio_read_events(ctx, min_nr, nr, event, &ret); + if (until == 0 || ret < 0 || ret >= min_nr) + return ret; + + hrtimer_init_sleeper_on_stack(&t, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + if (until != KTIME_MAX) { + hrtimer_set_expires_range_ns(&t.timer, until, current->timer_slack_ns); + hrtimer_sleeper_start_expires(&t, HRTIMER_MODE_REL); + } + + init_wait(&w.w); + + while (1) { + unsigned long nr_got = ret; + + w.min_nr = min_nr - ret; + + ret2 = prepare_to_wait_event(&ctx->wait, &w.w, TASK_INTERRUPTIBLE); + if (!ret2 && !t.task) + ret2 = -ETIME; + + if (aio_read_events(ctx, min_nr, nr, event, &ret) || ret2) + break; + + if (nr_got == ret) + schedule(); + } + + finish_wait(&ctx->wait, &w.w); + hrtimer_cancel(&t.timer); + destroy_hrtimer_on_stack(&t.timer); + return ret; } @@ -1498,7 +1545,7 @@ static ssize_t aio_setup_rw(int rw, const struct iocb *iocb, size_t len = iocb->aio_nbytes; if (!vectored) { - ssize_t ret = import_single_range(rw, buf, len, *iovec, iter); + ssize_t ret = import_ubuf(rw, buf, len, iter); *iovec = NULL; return ret; } diff --git a/fs/attr.c b/fs/attr.c index bdf5deb06ea9..5a13f0c8495f 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -157,7 +157,7 @@ static bool chgrp_ok(struct mnt_idmap *idmap, * the vfsmount must be passed through @idmap. This function will then * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be - * performed on the raw inode simply passs @nop_mnt_idmap. + * performed on the raw inode simply pass @nop_mnt_idmap. * * Should be called as the first thing in ->setattr implementations, * possibly after taking additional locks. diff --git a/fs/backing-file.c b/fs/backing-file.c new file mode 100644 index 000000000000..a681f38d84d8 --- /dev/null +++ b/fs/backing-file.c @@ -0,0 +1,336 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Common helpers for stackable filesystems and backing files. + * + * Forked from fs/overlayfs/file.c. + * + * Copyright (C) 2017 Red Hat, Inc. + * Copyright (C) 2023 CTERA Networks. + */ + +#include <linux/fs.h> +#include <linux/backing-file.h> +#include <linux/splice.h> +#include <linux/mm.h> + +#include "internal.h" + +/** + * backing_file_open - open a backing file for kernel internal use + * @user_path: path that the user reuqested to open + * @flags: open flags + * @real_path: path of the backing file + * @cred: credentials for open + * + * Open a backing file for a stackable filesystem (e.g., overlayfs). + * @user_path may be on the stackable filesystem and @real_path on the + * underlying filesystem. In this case, we want to be able to return the + * @user_path of the stackable filesystem. This is done by embedding the + * returned file into a container structure that also stores the stacked + * file's path, which can be retrieved using backing_file_user_path(). + */ +struct file *backing_file_open(const struct path *user_path, int flags, + const struct path *real_path, + const struct cred *cred) +{ + struct file *f; + int error; + + f = alloc_empty_backing_file(flags, cred); + if (IS_ERR(f)) + return f; + + path_get(user_path); + *backing_file_user_path(f) = *user_path; + error = vfs_open(real_path, f); + if (error) { + fput(f); + f = ERR_PTR(error); + } + + return f; +} +EXPORT_SYMBOL_GPL(backing_file_open); + +struct backing_aio { + struct kiocb iocb; + refcount_t ref; + struct kiocb *orig_iocb; + /* used for aio completion */ + void (*end_write)(struct file *); + struct work_struct work; + long res; +}; + +static struct kmem_cache *backing_aio_cachep; + +#define BACKING_IOCB_MASK \ + (IOCB_NOWAIT | IOCB_HIPRI | IOCB_DSYNC | IOCB_SYNC | IOCB_APPEND) + +static rwf_t iocb_to_rw_flags(int flags) +{ + return (__force rwf_t)(flags & BACKING_IOCB_MASK); +} + +static void backing_aio_put(struct backing_aio *aio) +{ + if (refcount_dec_and_test(&aio->ref)) { + fput(aio->iocb.ki_filp); + kmem_cache_free(backing_aio_cachep, aio); + } +} + +static void backing_aio_cleanup(struct backing_aio *aio, long res) +{ + struct kiocb *iocb = &aio->iocb; + struct kiocb *orig_iocb = aio->orig_iocb; + + if (aio->end_write) + aio->end_write(orig_iocb->ki_filp); + + orig_iocb->ki_pos = iocb->ki_pos; + backing_aio_put(aio); +} + +static void backing_aio_rw_complete(struct kiocb *iocb, long res) +{ + struct backing_aio *aio = container_of(iocb, struct backing_aio, iocb); + struct kiocb *orig_iocb = aio->orig_iocb; + + if (iocb->ki_flags & IOCB_WRITE) + kiocb_end_write(iocb); + + backing_aio_cleanup(aio, res); + orig_iocb->ki_complete(orig_iocb, res); +} + +static void backing_aio_complete_work(struct work_struct *work) +{ + struct backing_aio *aio = container_of(work, struct backing_aio, work); + + backing_aio_rw_complete(&aio->iocb, aio->res); +} + +static void backing_aio_queue_completion(struct kiocb *iocb, long res) +{ + struct backing_aio *aio = container_of(iocb, struct backing_aio, iocb); + + /* + * Punt to a work queue to serialize updates of mtime/size. + */ + aio->res = res; + INIT_WORK(&aio->work, backing_aio_complete_work); + queue_work(file_inode(aio->orig_iocb->ki_filp)->i_sb->s_dio_done_wq, + &aio->work); +} + +static int backing_aio_init_wq(struct kiocb *iocb) +{ + struct super_block *sb = file_inode(iocb->ki_filp)->i_sb; + + if (sb->s_dio_done_wq) + return 0; + + return sb_init_dio_done_wq(sb); +} + + +ssize_t backing_file_read_iter(struct file *file, struct iov_iter *iter, + struct kiocb *iocb, int flags, + struct backing_file_ctx *ctx) +{ + struct backing_aio *aio = NULL; + const struct cred *old_cred; + ssize_t ret; + + if (WARN_ON_ONCE(!(file->f_mode & FMODE_BACKING))) + return -EIO; + + if (!iov_iter_count(iter)) + return 0; + + if (iocb->ki_flags & IOCB_DIRECT && + !(file->f_mode & FMODE_CAN_ODIRECT)) + return -EINVAL; + + old_cred = override_creds(ctx->cred); + if (is_sync_kiocb(iocb)) { + rwf_t rwf = iocb_to_rw_flags(flags); + + ret = vfs_iter_read(file, iter, &iocb->ki_pos, rwf); + } else { + ret = -ENOMEM; + aio = kmem_cache_zalloc(backing_aio_cachep, GFP_KERNEL); + if (!aio) + goto out; + + aio->orig_iocb = iocb; + kiocb_clone(&aio->iocb, iocb, get_file(file)); + aio->iocb.ki_complete = backing_aio_rw_complete; + refcount_set(&aio->ref, 2); + ret = vfs_iocb_iter_read(file, &aio->iocb, iter); + backing_aio_put(aio); + if (ret != -EIOCBQUEUED) + backing_aio_cleanup(aio, ret); + } +out: + revert_creds(old_cred); + + if (ctx->accessed) + ctx->accessed(ctx->user_file); + + return ret; +} +EXPORT_SYMBOL_GPL(backing_file_read_iter); + +ssize_t backing_file_write_iter(struct file *file, struct iov_iter *iter, + struct kiocb *iocb, int flags, + struct backing_file_ctx *ctx) +{ + const struct cred *old_cred; + ssize_t ret; + + if (WARN_ON_ONCE(!(file->f_mode & FMODE_BACKING))) + return -EIO; + + if (!iov_iter_count(iter)) + return 0; + + ret = file_remove_privs(ctx->user_file); + if (ret) + return ret; + + if (iocb->ki_flags & IOCB_DIRECT && + !(file->f_mode & FMODE_CAN_ODIRECT)) + return -EINVAL; + + /* + * Stacked filesystems don't support deferred completions, don't copy + * this property in case it is set by the issuer. + */ + flags &= ~IOCB_DIO_CALLER_COMP; + + old_cred = override_creds(ctx->cred); + if (is_sync_kiocb(iocb)) { + rwf_t rwf = iocb_to_rw_flags(flags); + + ret = vfs_iter_write(file, iter, &iocb->ki_pos, rwf); + if (ctx->end_write) + ctx->end_write(ctx->user_file); + } else { + struct backing_aio *aio; + + ret = backing_aio_init_wq(iocb); + if (ret) + goto out; + + ret = -ENOMEM; + aio = kmem_cache_zalloc(backing_aio_cachep, GFP_KERNEL); + if (!aio) + goto out; + + aio->orig_iocb = iocb; + aio->end_write = ctx->end_write; + kiocb_clone(&aio->iocb, iocb, get_file(file)); + aio->iocb.ki_flags = flags; + aio->iocb.ki_complete = backing_aio_queue_completion; + refcount_set(&aio->ref, 2); + ret = vfs_iocb_iter_write(file, &aio->iocb, iter); + backing_aio_put(aio); + if (ret != -EIOCBQUEUED) + backing_aio_cleanup(aio, ret); + } +out: + revert_creds(old_cred); + + return ret; +} +EXPORT_SYMBOL_GPL(backing_file_write_iter); + +ssize_t backing_file_splice_read(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, + unsigned int flags, + struct backing_file_ctx *ctx) +{ + const struct cred *old_cred; + ssize_t ret; + + if (WARN_ON_ONCE(!(in->f_mode & FMODE_BACKING))) + return -EIO; + + old_cred = override_creds(ctx->cred); + ret = vfs_splice_read(in, ppos, pipe, len, flags); + revert_creds(old_cred); + + if (ctx->accessed) + ctx->accessed(ctx->user_file); + + return ret; +} +EXPORT_SYMBOL_GPL(backing_file_splice_read); + +ssize_t backing_file_splice_write(struct pipe_inode_info *pipe, + struct file *out, loff_t *ppos, size_t len, + unsigned int flags, + struct backing_file_ctx *ctx) +{ + const struct cred *old_cred; + ssize_t ret; + + if (WARN_ON_ONCE(!(out->f_mode & FMODE_BACKING))) + return -EIO; + + ret = file_remove_privs(ctx->user_file); + if (ret) + return ret; + + old_cred = override_creds(ctx->cred); + file_start_write(out); + ret = iter_file_splice_write(pipe, out, ppos, len, flags); + file_end_write(out); + revert_creds(old_cred); + + if (ctx->end_write) + ctx->end_write(ctx->user_file); + + return ret; +} +EXPORT_SYMBOL_GPL(backing_file_splice_write); + +int backing_file_mmap(struct file *file, struct vm_area_struct *vma, + struct backing_file_ctx *ctx) +{ + const struct cred *old_cred; + int ret; + + if (WARN_ON_ONCE(!(file->f_mode & FMODE_BACKING)) || + WARN_ON_ONCE(ctx->user_file != vma->vm_file)) + return -EIO; + + if (!file->f_op->mmap) + return -ENODEV; + + vma_set_file(vma, file); + + old_cred = override_creds(ctx->cred); + ret = call_mmap(vma->vm_file, vma); + revert_creds(old_cred); + + if (ctx->accessed) + ctx->accessed(ctx->user_file); + + return ret; +} +EXPORT_SYMBOL_GPL(backing_file_mmap); + +static int __init backing_aio_init(void) +{ + backing_aio_cachep = kmem_cache_create("backing_aio", + sizeof(struct backing_aio), + 0, SLAB_HWCACHE_ALIGN, NULL); + if (!backing_aio_cachep) + return -ENOMEM; + + return 0; +} +fs_initcall(backing_aio_init); diff --git a/fs/bcachefs/Makefile b/fs/bcachefs/Makefile index 45b64f89258c..b81268418174 100644 --- a/fs/bcachefs/Makefile +++ b/fs/bcachefs/Makefile @@ -28,6 +28,7 @@ bcachefs-y := \ clock.o \ compress.o \ counters.o \ + darray.o \ debug.o \ dirent.o \ disk_groups.o \ @@ -70,6 +71,7 @@ bcachefs-y := \ reflink.o \ replicas.o \ sb-clean.o \ + sb-downgrade.o \ sb-errors.o \ sb-members.o \ siphash.o \ diff --git a/fs/bcachefs/acl.c b/fs/bcachefs/acl.c index f3809897f00a..3640f417cce1 100644 --- a/fs/bcachefs/acl.c +++ b/fs/bcachefs/acl.c @@ -366,7 +366,8 @@ retry: bch2_trans_begin(trans); acl = _acl; - ret = bch2_inode_peek(trans, &inode_iter, &inode_u, inode_inum(inode), + ret = bch2_subvol_is_ro_trans(trans, inode->ei_subvol) ?: + bch2_inode_peek(trans, &inode_iter, &inode_u, inode_inum(inode), BTREE_ITER_INTENT); if (ret) goto btree_err; diff --git a/fs/bcachefs/alloc_foreground.c b/fs/bcachefs/alloc_foreground.c index 1ba0eeb7552a..0e6157982607 100644 --- a/fs/bcachefs/alloc_foreground.c +++ b/fs/bcachefs/alloc_foreground.c @@ -1374,8 +1374,17 @@ retry: goto alloc_done; /* Don't retry from all devices if we're out of open buckets: */ - if (bch2_err_matches(ret, BCH_ERR_open_buckets_empty)) - goto allocate_blocking; + if (bch2_err_matches(ret, BCH_ERR_open_buckets_empty)) { + int ret = open_bucket_add_buckets(trans, &ptrs, wp, devs_have, + target, erasure_code, + nr_replicas, &nr_effective, + &have_cache, watermark, + flags, cl); + if (!ret || + bch2_err_matches(ret, BCH_ERR_transaction_restart) || + bch2_err_matches(ret, BCH_ERR_open_buckets_empty)) + goto alloc_done; + } /* * Only try to allocate cache (durability = 0 devices) from the @@ -1389,7 +1398,6 @@ retry: &have_cache, watermark, flags, cl); } else { -allocate_blocking: ret = open_bucket_add_buckets(trans, &ptrs, wp, devs_have, target, erasure_code, nr_replicas, &nr_effective, diff --git a/fs/bcachefs/bcachefs.h b/fs/bcachefs/bcachefs.h index dfa22f9d9a1d..b62737fdf5ab 100644 --- a/fs/bcachefs/bcachefs.h +++ b/fs/bcachefs/bcachefs.h @@ -737,6 +737,7 @@ struct bch_fs { unsigned nsec_per_time_unit; u64 features; u64 compat; + unsigned long errors_silent[BITS_TO_LONGS(BCH_SB_ERR_MAX)]; } sb; diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h index 1ab1f08d763b..fe78e87603fc 100644 --- a/fs/bcachefs/bcachefs_format.h +++ b/fs/bcachefs/bcachefs_format.h @@ -1207,19 +1207,21 @@ struct bch_sb_field { }; #define BCH_SB_FIELDS() \ - x(journal, 0) \ - x(members_v1, 1) \ - x(crypt, 2) \ - x(replicas_v0, 3) \ - x(quota, 4) \ - x(disk_groups, 5) \ - x(clean, 6) \ - x(replicas, 7) \ - x(journal_seq_blacklist, 8) \ - x(journal_v2, 9) \ - x(counters, 10) \ - x(members_v2, 11) \ - x(errors, 12) + x(journal, 0) \ + x(members_v1, 1) \ + x(crypt, 2) \ + x(replicas_v0, 3) \ + x(quota, 4) \ + x(disk_groups, 5) \ + x(clean, 6) \ + x(replicas, 7) \ + x(journal_seq_blacklist, 8) \ + x(journal_v2, 9) \ + x(counters, 10) \ + x(members_v2, 11) \ + x(errors, 12) \ + x(ext, 13) \ + x(downgrade, 14) enum bch_sb_field_type { #define x(f, nr) BCH_SB_FIELD_##f = nr, @@ -1631,6 +1633,24 @@ struct bch_sb_field_errors { LE64_BITMASK(BCH_SB_ERROR_ENTRY_ID, struct bch_sb_field_error_entry, v, 0, 16); LE64_BITMASK(BCH_SB_ERROR_ENTRY_NR, struct bch_sb_field_error_entry, v, 16, 64); +struct bch_sb_field_ext { + struct bch_sb_field field; + __le64 recovery_passes_required[2]; + __le64 errors_silent[8]; +}; + +struct bch_sb_field_downgrade_entry { + __le16 version; + __le64 recovery_passes[2]; + __le16 nr_errors; + __le16 errors[] __counted_by(nr_errors); +} __packed __aligned(2); + +struct bch_sb_field_downgrade { + struct bch_sb_field field; + struct bch_sb_field_downgrade_entry entries[]; +}; + /* Superblock: */ /* @@ -1644,6 +1664,11 @@ LE64_BITMASK(BCH_SB_ERROR_ENTRY_NR, struct bch_sb_field_error_entry, v, 16, 64); #define RECOVERY_PASS_ALL_FSCK (1ULL << 63) +/* + * field 1: version name + * field 2: BCH_VERSION(major, minor) + * field 3: recovery passess required on upgrade + */ #define BCH_METADATA_VERSIONS() \ x(bkey_renumber, BCH_VERSION(0, 10), \ RECOVERY_PASS_ALL_FSCK) \ diff --git a/fs/bcachefs/btree_cache.c b/fs/bcachefs/btree_cache.c index 47e7770d0583..79495cd7a794 100644 --- a/fs/bcachefs/btree_cache.c +++ b/fs/bcachefs/btree_cache.c @@ -9,6 +9,7 @@ #include "debug.h" #include "errcode.h" #include "error.h" +#include "journal.h" #include "trace.h" #include <linux/prefetch.h> @@ -424,14 +425,11 @@ void bch2_fs_btree_cache_exit(struct bch_fs *c) BUG_ON(btree_node_read_in_flight(b) || btree_node_write_in_flight(b)); - if (btree_node_dirty(b)) - bch2_btree_complete_write(c, b, btree_current_write(b)); - clear_btree_node_dirty_acct(c, b); - btree_node_data_free(c, b); } - BUG_ON(atomic_read(&c->btree_cache.dirty)); + BUG_ON(!bch2_journal_error(&c->journal) && + atomic_read(&c->btree_cache.dirty)); list_splice(&bc->freed_pcpu, &bc->freed_nonpcpu); diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c index 57c20390e10e..5a720f0cd5a6 100644 --- a/fs/bcachefs/btree_io.c +++ b/fs/bcachefs/btree_io.c @@ -1704,8 +1704,8 @@ int bch2_btree_root_read(struct bch_fs *c, enum btree_id id, return bch2_trans_run(c, __bch2_btree_root_read(trans, id, k, level)); } -void bch2_btree_complete_write(struct bch_fs *c, struct btree *b, - struct btree_write *w) +static void bch2_btree_complete_write(struct bch_fs *c, struct btree *b, + struct btree_write *w) { unsigned long old, new, v = READ_ONCE(b->will_make_reachable); diff --git a/fs/bcachefs/btree_io.h b/fs/bcachefs/btree_io.h index 7e03dd76fb38..e0d7fa5b1dfb 100644 --- a/fs/bcachefs/btree_io.h +++ b/fs/bcachefs/btree_io.h @@ -134,9 +134,6 @@ void bch2_btree_node_read(struct bch_fs *, struct btree *, bool); int bch2_btree_root_read(struct bch_fs *, enum btree_id, const struct bkey_i *, unsigned); -void bch2_btree_complete_write(struct bch_fs *, struct btree *, - struct btree_write *); - bool bch2_btree_post_write_cleanup(struct bch_fs *, struct btree *); enum btree_write_flags { diff --git a/fs/bcachefs/btree_iter.c b/fs/bcachefs/btree_iter.c index 8e0fe65f6101..da594e006769 100644 --- a/fs/bcachefs/btree_iter.c +++ b/fs/bcachefs/btree_iter.c @@ -2085,18 +2085,16 @@ struct bkey_s_c bch2_btree_iter_peek_upto(struct btree_iter *iter, struct bpos e goto out_no_locked; /* - * iter->pos should be mononotically increasing, and always be - * equal to the key we just returned - except extents can - * straddle iter->pos: + * We need to check against @end before FILTER_SNAPSHOTS because + * if we get to a different inode that requested we might be + * seeing keys for a different snapshot tree that will all be + * filtered out. + * + * But we can't do the full check here, because bkey_start_pos() + * isn't monotonically increasing before FILTER_SNAPSHOTS, and + * that's what we check against in extents mode: */ - if (!(iter->flags & BTREE_ITER_IS_EXTENTS)) - iter_pos = k.k->p; - else - iter_pos = bkey_max(iter->pos, bkey_start_pos(k.k)); - - if (unlikely(!(iter->flags & BTREE_ITER_IS_EXTENTS) - ? bkey_gt(iter_pos, end) - : bkey_ge(iter_pos, end))) + if (k.k->p.inode > end.inode) goto end; if (iter->update_path && @@ -2155,6 +2153,21 @@ struct bkey_s_c bch2_btree_iter_peek_upto(struct btree_iter *iter, struct bpos e continue; } + /* + * iter->pos should be mononotically increasing, and always be + * equal to the key we just returned - except extents can + * straddle iter->pos: + */ + if (!(iter->flags & BTREE_ITER_IS_EXTENTS)) + iter_pos = k.k->p; + else + iter_pos = bkey_max(iter->pos, bkey_start_pos(k.k)); + + if (unlikely(!(iter->flags & BTREE_ITER_IS_EXTENTS) + ? bkey_gt(iter_pos, end) + : bkey_ge(iter_pos, end))) + goto end; + break; } @@ -3214,10 +3227,9 @@ void bch2_fs_btree_iter_exit(struct bch_fs *c) mempool_exit(&c->btree_trans_pool); } -int bch2_fs_btree_iter_init(struct bch_fs *c) +void bch2_fs_btree_iter_init_early(struct bch_fs *c) { struct btree_transaction_stats *s; - int ret; for (s = c->btree_transaction_stats; s < c->btree_transaction_stats + ARRAY_SIZE(c->btree_transaction_stats); @@ -3228,6 +3240,11 @@ int bch2_fs_btree_iter_init(struct bch_fs *c) INIT_LIST_HEAD(&c->btree_trans_list); seqmutex_init(&c->btree_trans_lock); +} + +int bch2_fs_btree_iter_init(struct bch_fs *c) +{ + int ret; c->btree_trans_bufs = alloc_percpu(struct btree_trans_buf); if (!c->btree_trans_bufs) diff --git a/fs/bcachefs/btree_iter.h b/fs/bcachefs/btree_iter.h index 85e7cb52f6b6..eaffced4c132 100644 --- a/fs/bcachefs/btree_iter.h +++ b/fs/bcachefs/btree_iter.h @@ -938,6 +938,7 @@ unsigned bch2_trans_get_fn_idx(const char *); void bch2_btree_trans_to_text(struct printbuf *, struct btree_trans *); void bch2_fs_btree_iter_exit(struct bch_fs *); +void bch2_fs_btree_iter_init_early(struct bch_fs *); int bch2_fs_btree_iter_init(struct bch_fs *); #endif /* _BCACHEFS_BTREE_ITER_H */ diff --git a/fs/bcachefs/btree_key_cache.c b/fs/bcachefs/btree_key_cache.c index 37fbf22de8fc..1b7a5668df7c 100644 --- a/fs/bcachefs/btree_key_cache.c +++ b/fs/bcachefs/btree_key_cache.c @@ -992,8 +992,6 @@ void bch2_fs_btree_key_cache_exit(struct btree_key_cache *bc) list_for_each_entry_safe(ck, n, &items, list) { cond_resched(); - bch2_journal_pin_drop(&c->journal, &ck->journal); - list_del(&ck->list); kfree(ck->k); six_lock_exit(&ck->c.lock); diff --git a/fs/bcachefs/btree_update.c b/fs/bcachefs/btree_update.c index 324767c0ddcc..2fd3c8cc6f51 100644 --- a/fs/bcachefs/btree_update.c +++ b/fs/bcachefs/btree_update.c @@ -186,8 +186,11 @@ int bch2_trans_update_extent_overwrite(struct btree_trans *trans, enum btree_id btree_id = iter->btree_id; struct bkey_i *update; struct bpos new_start = bkey_start_pos(new.k); - bool front_split = bkey_lt(bkey_start_pos(old.k), new_start); - bool back_split = bkey_gt(old.k->p, new.k->p); + unsigned front_split = bkey_lt(bkey_start_pos(old.k), new_start); + unsigned back_split = bkey_gt(old.k->p, new.k->p); + unsigned middle_split = (front_split || back_split) && + old.k->p.snapshot != new.k->p.snapshot; + unsigned nr_splits = front_split + back_split + middle_split; int ret = 0, compressed_sectors; /* @@ -195,10 +198,9 @@ int bch2_trans_update_extent_overwrite(struct btree_trans *trans, * so that __bch2_trans_commit() can increase our disk * reservation: */ - if (((front_split && back_split) || - ((front_split || back_split) && old.k->p.snapshot != new.k->p.snapshot)) && + if (nr_splits > 1 && (compressed_sectors = bch2_bkey_sectors_compressed(old))) - trans->extra_journal_res += compressed_sectors; + trans->extra_journal_res += compressed_sectors * (nr_splits - 1); if (front_split) { update = bch2_bkey_make_mut_noupdate(trans, old); @@ -216,8 +218,7 @@ int bch2_trans_update_extent_overwrite(struct btree_trans *trans, } /* If we're overwriting in a different snapshot - middle split: */ - if (old.k->p.snapshot != new.k->p.snapshot && - (front_split || back_split)) { + if (middle_split) { update = bch2_bkey_make_mut_noupdate(trans, old); if ((ret = PTR_ERR_OR_ZERO(update))) return ret; @@ -554,6 +555,19 @@ int __must_check bch2_trans_update_seq(struct btree_trans *trans, u64 seq, BTREE_UPDATE_PREJOURNAL); } +static noinline int bch2_btree_insert_clone_trans(struct btree_trans *trans, + enum btree_id btree, + struct bkey_i *k) +{ + struct bkey_i *n = bch2_trans_kmalloc(trans, bkey_bytes(&k->k)); + int ret = PTR_ERR_OR_ZERO(n); + if (ret) + return ret; + + bkey_copy(n, k); + return bch2_btree_insert_trans(trans, btree, n, 0); +} + int __must_check bch2_trans_update_buffered(struct btree_trans *trans, enum btree_id btree, struct bkey_i *k) @@ -564,6 +578,9 @@ int __must_check bch2_trans_update_buffered(struct btree_trans *trans, EBUG_ON(trans->nr_wb_updates > trans->wb_updates_size); EBUG_ON(k->k.u64s > BTREE_WRITE_BUFERED_U64s_MAX); + if (unlikely(trans->journal_replay_not_finished)) + return bch2_btree_insert_clone_trans(trans, btree, k); + trans_for_each_wb_update(trans, i) { if (i->btree == btree && bpos_eq(i->k.k.p, k->k.p)) { bkey_copy(&i->k, k); diff --git a/fs/bcachefs/btree_update_interior.c b/fs/bcachefs/btree_update_interior.c index 6697417273aa..239fcc3c7c99 100644 --- a/fs/bcachefs/btree_update_interior.c +++ b/fs/bcachefs/btree_update_interior.c @@ -99,7 +99,7 @@ static void btree_node_interior_verify(struct bch_fs *c, struct btree *b) /* Calculate ideal packed bkey format for new btree nodes: */ -void __bch2_btree_calc_format(struct bkey_format_state *s, struct btree *b) +static void __bch2_btree_calc_format(struct bkey_format_state *s, struct btree *b) { struct bkey_packed *k; struct bset_tree *t; @@ -125,21 +125,20 @@ static struct bkey_format bch2_btree_calc_format(struct btree *b) return bch2_bkey_format_done(&s); } -static size_t btree_node_u64s_with_format(struct btree *b, +static size_t btree_node_u64s_with_format(struct btree_nr_keys nr, + struct bkey_format *old_f, struct bkey_format *new_f) { - struct bkey_format *old_f = &b->format; - /* stupid integer promotion rules */ ssize_t delta = (((int) new_f->key_u64s - old_f->key_u64s) * - (int) b->nr.packed_keys) + + (int) nr.packed_keys) + (((int) new_f->key_u64s - BKEY_U64s) * - (int) b->nr.unpacked_keys); + (int) nr.unpacked_keys); - BUG_ON(delta + b->nr.live_u64s < 0); + BUG_ON(delta + nr.live_u64s < 0); - return b->nr.live_u64s + delta; + return nr.live_u64s + delta; } /** @@ -147,16 +146,18 @@ static size_t btree_node_u64s_with_format(struct btree *b, * * @c: filesystem handle * @b: btree node to rewrite + * @nr: number of keys for new node (i.e. b->nr) * @new_f: bkey format to translate keys to * * Returns: true if all re-packed keys will be able to fit in a new node. * * Assumes all keys will successfully pack with the new format. */ -bool bch2_btree_node_format_fits(struct bch_fs *c, struct btree *b, +static bool bch2_btree_node_format_fits(struct bch_fs *c, struct btree *b, + struct btree_nr_keys nr, struct bkey_format *new_f) { - size_t u64s = btree_node_u64s_with_format(b, new_f); + size_t u64s = btree_node_u64s_with_format(nr, &b->format, new_f); return __vstruct_bytes(struct btree_node, u64s) < btree_bytes(c); } @@ -391,7 +392,7 @@ static struct btree *bch2_btree_node_alloc_replacement(struct btree_update *as, * The keys might expand with the new format - if they wouldn't fit in * the btree node anymore, use the old format for now: */ - if (!bch2_btree_node_format_fits(as->c, b, &format)) + if (!bch2_btree_node_format_fits(as->c, b, b->nr, &format)) format = b->format; SET_BTREE_NODE_SEQ(n->data, BTREE_NODE_SEQ(b->data) + 1); @@ -1056,6 +1057,17 @@ bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path, flags &= ~BCH_WATERMARK_MASK; flags |= watermark; + if (!(flags & BTREE_INSERT_JOURNAL_RECLAIM) && + watermark < c->journal.watermark) { + struct journal_res res = { 0 }; + + ret = drop_locks_do(trans, + bch2_journal_res_get(&c->journal, &res, 1, + watermark|JOURNAL_RES_GET_CHECK)); + if (ret) + return ERR_PTR(ret); + } + while (1) { nr_nodes[!!update_level] += 1 + split; update_level++; @@ -1334,8 +1346,11 @@ static void __btree_split_node(struct btree_update *as, struct bkey_packed *out[2]; struct bkey uk; unsigned u64s, n1_u64s = (b->nr.live_u64s * 3) / 5; + struct { unsigned nr_keys, val_u64s; } nr_keys[2]; int i; + memset(&nr_keys, 0, sizeof(nr_keys)); + for (i = 0; i < 2; i++) { BUG_ON(n[i]->nsets != 1); @@ -1357,6 +1372,9 @@ static void __btree_split_node(struct btree_update *as, if (!i) n1_pos = uk.p; bch2_bkey_format_add_key(&format[i], &uk); + + nr_keys[i].nr_keys++; + nr_keys[i].val_u64s += bkeyp_val_u64s(&b->format, k); } btree_set_min(n[0], b->data->min_key); @@ -1369,6 +1387,12 @@ static void __btree_split_node(struct btree_update *as, bch2_bkey_format_add_pos(&format[i], n[i]->data->max_key); n[i]->data->format = bch2_bkey_format_done(&format[i]); + + unsigned u64s = nr_keys[i].nr_keys * n[i]->data->format.key_u64s + + nr_keys[i].val_u64s; + if (__vstruct_bytes(struct btree_node, u64s) > btree_bytes(as->c)) + n[i]->data->format = b->format; + btree_node_set_format(n[i], n[i]->data->format); } @@ -1811,8 +1835,8 @@ int __bch2_foreground_maybe_merge(struct btree_trans *trans, bch2_bkey_format_add_pos(&new_s, next->data->max_key); new_f = bch2_bkey_format_done(&new_s); - sib_u64s = btree_node_u64s_with_format(b, &new_f) + - btree_node_u64s_with_format(m, &new_f); + sib_u64s = btree_node_u64s_with_format(b->nr, &b->format, &new_f) + + btree_node_u64s_with_format(m->nr, &m->format, &new_f); if (sib_u64s > BTREE_FOREGROUND_MERGE_HYSTERESIS(c)) { sib_u64s -= BTREE_FOREGROUND_MERGE_HYSTERESIS(c); diff --git a/fs/bcachefs/btree_update_interior.h b/fs/bcachefs/btree_update_interior.h index 031076e75fa1..a6668992a272 100644 --- a/fs/bcachefs/btree_update_interior.h +++ b/fs/bcachefs/btree_update_interior.h @@ -6,10 +6,6 @@ #include "btree_locking.h" #include "btree_update.h" -void __bch2_btree_calc_format(struct bkey_format_state *, struct btree *); -bool bch2_btree_node_format_fits(struct bch_fs *c, struct btree *, - struct bkey_format *); - #define BTREE_UPDATE_NODES_MAX ((BTREE_MAX_DEPTH - 2) * 2 + GC_MERGE_NODES) #define BTREE_UPDATE_JOURNAL_RES (BTREE_UPDATE_NODES_MAX * (BKEY_BTREE_PTR_U64s_MAX + 1)) diff --git a/fs/bcachefs/darray.c b/fs/bcachefs/darray.c new file mode 100644 index 000000000000..ac35b8b705ae --- /dev/null +++ b/fs/bcachefs/darray.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/log2.h> +#include <linux/slab.h> +#include "darray.h" + +int __bch2_darray_resize(darray_char *d, size_t element_size, size_t new_size, gfp_t gfp) +{ + if (new_size > d->size) { + new_size = roundup_pow_of_two(new_size); + + void *data = kvmalloc_array(new_size, element_size, gfp); + if (!data) + return -ENOMEM; + + memcpy(data, d->data, d->size * element_size); + if (d->data != d->preallocated) + kvfree(d->data); + d->data = data; + d->size = new_size; + } + + return 0; +} diff --git a/fs/bcachefs/darray.h b/fs/bcachefs/darray.h index 87b4b2d1ec76..e367c625f057 100644 --- a/fs/bcachefs/darray.h +++ b/fs/bcachefs/darray.h @@ -8,39 +8,48 @@ * Inspired by CCAN's darray */ -#include "util.h" #include <linux/slab.h> -#define DARRAY(type) \ +#define DARRAY_PREALLOCATED(_type, _nr) \ struct { \ size_t nr, size; \ - type *data; \ + _type *data; \ + _type preallocated[_nr]; \ } -typedef DARRAY(void) darray_void; +#define DARRAY(_type) DARRAY_PREALLOCATED(_type, 0) -static inline int __darray_make_room(darray_void *d, size_t t_size, size_t more, gfp_t gfp) +typedef DARRAY(char) darray_char; + +int __bch2_darray_resize(darray_char *, size_t, size_t, gfp_t); + +static inline int __darray_resize(darray_char *d, size_t element_size, + size_t new_size, gfp_t gfp) { - if (d->nr + more > d->size) { - size_t new_size = roundup_pow_of_two(d->nr + more); - void *data = krealloc_array(d->data, new_size, t_size, gfp); + return unlikely(new_size > d->size) + ? __bch2_darray_resize(d, element_size, new_size, gfp) + : 0; +} - if (!data) - return -ENOMEM; +#define darray_resize_gfp(_d, _new_size, _gfp) \ + unlikely(__darray_resize((darray_char *) (_d), sizeof((_d)->data[0]), (_new_size), _gfp)) - d->data = data; - d->size = new_size; - } +#define darray_resize(_d, _new_size) \ + darray_resize_gfp(_d, _new_size, GFP_KERNEL) - return 0; +static inline int __darray_make_room(darray_char *d, size_t t_size, size_t more, gfp_t gfp) +{ + return __darray_resize(d, t_size, d->nr + more, gfp); } #define darray_make_room_gfp(_d, _more, _gfp) \ - __darray_make_room((darray_void *) (_d), sizeof((_d)->data[0]), (_more), _gfp) + __darray_make_room((darray_char *) (_d), sizeof((_d)->data[0]), (_more), _gfp) #define darray_make_room(_d, _more) \ darray_make_room_gfp(_d, _more, GFP_KERNEL) +#define darray_room(_d) ((_d).size - (_d).nr) + #define darray_top(_d) ((_d).data[(_d).nr]) #define darray_push_gfp(_d, _item, _gfp) \ @@ -80,13 +89,16 @@ static inline int __darray_make_room(darray_void *d, size_t t_size, size_t more, #define darray_init(_d) \ do { \ - (_d)->data = NULL; \ - (_d)->nr = (_d)->size = 0; \ + (_d)->nr = 0; \ + (_d)->size = ARRAY_SIZE((_d)->preallocated); \ + (_d)->data = (_d)->size ? (_d)->preallocated : NULL; \ } while (0) #define darray_exit(_d) \ do { \ - kfree((_d)->data); \ + if (!ARRAY_SIZE((_d)->preallocated) || \ + (_d)->data != (_d)->preallocated) \ + kvfree((_d)->data); \ darray_init(_d); \ } while (0) diff --git a/fs/bcachefs/data_update.c b/fs/bcachefs/data_update.c index 71aa5e59787b..37d6ecae8c30 100644 --- a/fs/bcachefs/data_update.c +++ b/fs/bcachefs/data_update.c @@ -471,7 +471,7 @@ int bch2_extent_drop_ptrs(struct btree_trans *trans, * we aren't using the extent overwrite path to delete, we're * just using the normal key deletion path: */ - if (bkey_deleted(&n->k)) + if (bkey_deleted(&n->k) && !(iter->flags & BTREE_ITER_IS_EXTENTS)) n->k.size = 0; return bch2_trans_relock(trans) ?: @@ -560,7 +560,8 @@ int bch2_data_update_init(struct btree_trans *trans, move_ctxt_wait_event(ctxt, (locked = bch2_bucket_nocow_trylock(&c->nocow_locks, PTR_BUCKET_POS(c, &p.ptr), 0)) || - !atomic_read(&ctxt->read_sectors)); + (!atomic_read(&ctxt->read_sectors) && + !atomic_read(&ctxt->write_sectors))); if (!locked) bch2_bucket_nocow_lock(&c->nocow_locks, @@ -586,12 +587,13 @@ int bch2_data_update_init(struct btree_trans *trans, * Increasing replication is an explicit operation triggered by * rereplicate, currently, so that users don't get an unexpected -ENOSPC */ - if (durability_have >= io_opts.data_replicas) { + if (!(m->data_opts.write_flags & BCH_WRITE_CACHED) && + durability_have >= io_opts.data_replicas) { m->data_opts.kill_ptrs |= m->data_opts.rewrite_ptrs; m->data_opts.rewrite_ptrs = 0; /* if iter == NULL, it's just a promote */ if (iter) - ret = bch2_extent_drop_ptrs(trans, iter, k, data_opts); + ret = bch2_extent_drop_ptrs(trans, iter, k, m->data_opts); goto done; } diff --git a/fs/bcachefs/dirent.c b/fs/bcachefs/dirent.c index 1a0f2d571569..2bfff0da7000 100644 --- a/fs/bcachefs/dirent.c +++ b/fs/bcachefs/dirent.c @@ -485,20 +485,15 @@ retry: return ret; } -int bch2_empty_dir_trans(struct btree_trans *trans, subvol_inum dir) +int bch2_empty_dir_snapshot(struct btree_trans *trans, u64 dir, u32 snapshot) { struct btree_iter iter; struct bkey_s_c k; - u32 snapshot; int ret; - ret = bch2_subvolume_get_snapshot(trans, dir.subvol, &snapshot); - if (ret) - return ret; - for_each_btree_key_upto_norestart(trans, iter, BTREE_ID_dirents, - SPOS(dir.inum, 0, snapshot), - POS(dir.inum, U64_MAX), 0, k, ret) + SPOS(dir, 0, snapshot), + POS(dir, U64_MAX), 0, k, ret) if (k.k->type == KEY_TYPE_dirent) { ret = -ENOTEMPTY; break; @@ -508,6 +503,14 @@ int bch2_empty_dir_trans(struct btree_trans *trans, subvol_inum dir) return ret; } +int bch2_empty_dir_trans(struct btree_trans *trans, subvol_inum dir) +{ + u32 snapshot; + + return bch2_subvolume_get_snapshot(trans, dir.subvol, &snapshot) ?: + bch2_empty_dir_snapshot(trans, dir.inum, snapshot); +} + int bch2_readdir(struct bch_fs *c, subvol_inum inum, struct dir_context *ctx) { struct btree_trans *trans = bch2_trans_get(c); diff --git a/fs/bcachefs/dirent.h b/fs/bcachefs/dirent.h index cd262bf4d9c5..1e3431990abd 100644 --- a/fs/bcachefs/dirent.h +++ b/fs/bcachefs/dirent.h @@ -64,6 +64,7 @@ u64 bch2_dirent_lookup(struct bch_fs *, subvol_inum, const struct bch_hash_info *, const struct qstr *, subvol_inum *); +int bch2_empty_dir_snapshot(struct btree_trans *, u64, u32); int bch2_empty_dir_trans(struct btree_trans *, subvol_inum); int bch2_readdir(struct bch_fs *, subvol_inum, struct dir_context *); diff --git a/fs/bcachefs/errcode.h b/fs/bcachefs/errcode.h index ae7910bf2228..9ce29681eec9 100644 --- a/fs/bcachefs/errcode.h +++ b/fs/bcachefs/errcode.h @@ -95,6 +95,7 @@ x(ENOSPC, ENOSPC_sb_members) \ x(ENOSPC, ENOSPC_sb_members_v2) \ x(ENOSPC, ENOSPC_sb_crypt) \ + x(ENOSPC, ENOSPC_sb_downgrade) \ x(ENOSPC, ENOSPC_btree_slot) \ x(ENOSPC, ENOSPC_snapshot_tree) \ x(ENOENT, ENOENT_bkey_type_mismatch) \ @@ -218,6 +219,8 @@ x(BCH_ERR_invalid_sb, invalid_sb_quota) \ x(BCH_ERR_invalid_sb, invalid_sb_errors) \ x(BCH_ERR_invalid_sb, invalid_sb_opt_compression) \ + x(BCH_ERR_invalid_sb, invalid_sb_ext) \ + x(BCH_ERR_invalid_sb, invalid_sb_downgrade) \ x(BCH_ERR_invalid, invalid_bkey) \ x(BCH_ERR_operation_blocked, nocow_lock_blocked) \ x(EIO, btree_node_read_err) \ diff --git a/fs/bcachefs/error.c b/fs/bcachefs/error.c index 7b28d37922fd..25cf78a7b946 100644 --- a/fs/bcachefs/error.c +++ b/fs/bcachefs/error.c @@ -152,6 +152,9 @@ int bch2_fsck_err(struct bch_fs *c, struct printbuf buf = PRINTBUF, *out = &buf; int ret = -BCH_ERR_fsck_ignore; + if (test_bit(err, c->sb.errors_silent)) + return -BCH_ERR_fsck_fix; + bch2_sb_error_count(c, err); va_start(args, fmt); diff --git a/fs/bcachefs/error.h b/fs/bcachefs/error.h index d167d65986e0..fec17d1353d1 100644 --- a/fs/bcachefs/error.h +++ b/fs/bcachefs/error.h @@ -157,6 +157,7 @@ void bch2_flush_fsck_errs(struct bch_fs *); #define fsck_err_on(cond, c, _err_type, ...) \ __fsck_err_on(cond, c, FSCK_CAN_FIX|FSCK_CAN_IGNORE, _err_type, __VA_ARGS__) +__printf(4, 0) static inline void bch2_bkey_fsck_err(struct bch_fs *c, struct printbuf *err_msg, enum bch_sb_error_id err_type, @@ -167,7 +168,6 @@ static inline void bch2_bkey_fsck_err(struct bch_fs *c, va_start(args, fmt); prt_vprintf(err_msg, fmt, args); va_end(args); - } #define bkey_fsck_err(c, _err_msg, _err_type, ...) \ diff --git a/fs/bcachefs/extents.c b/fs/bcachefs/extents.c index f6c92df55270..9d8afcb5979a 100644 --- a/fs/bcachefs/extents.c +++ b/fs/bcachefs/extents.c @@ -1294,7 +1294,8 @@ unsigned bch2_bkey_ptrs_need_rebalance(struct bch_fs *c, struct bkey_s_c k, unsigned i = 0; bkey_for_each_ptr_decode(k.k, ptrs, p, entry) { - if (p.crc.compression_type == BCH_COMPRESSION_TYPE_incompressible) { + if (p.crc.compression_type == BCH_COMPRESSION_TYPE_incompressible || + p.ptr.unwritten) { rewrite_ptrs = 0; goto incompressible; } diff --git a/fs/bcachefs/fs-io-direct.c b/fs/bcachefs/fs-io-direct.c index 9a479e4de6b3..84e20c3ada6c 100644 --- a/fs/bcachefs/fs-io-direct.c +++ b/fs/bcachefs/fs-io-direct.c @@ -216,11 +216,11 @@ struct dio_write { struct address_space *mapping; struct bch_inode_info *inode; struct mm_struct *mm; + const struct iovec *iov; unsigned loop:1, extending:1, sync:1, - flush:1, - free_iov:1; + flush:1; struct quota_res quota_res; u64 written; @@ -312,12 +312,10 @@ static noinline int bch2_dio_write_copy_iov(struct dio_write *dio) return -1; if (dio->iter.nr_segs > ARRAY_SIZE(dio->inline_vecs)) { - iov = kmalloc_array(dio->iter.nr_segs, sizeof(*iov), + dio->iov = iov = kmalloc_array(dio->iter.nr_segs, sizeof(*iov), GFP_KERNEL); if (unlikely(!iov)) return -ENOMEM; - - dio->free_iov = true; } memcpy(iov, dio->iter.__iov, dio->iter.nr_segs * sizeof(*iov)); @@ -381,8 +379,7 @@ static __always_inline long bch2_dio_write_done(struct dio_write *dio) bch2_pagecache_block_put(inode); - if (dio->free_iov) - kfree(dio->iter.__iov); + kfree(dio->iov); ret = dio->op.error ?: ((long) dio->written << 9); bio_put(&dio->op.wbio.bio); @@ -626,11 +623,11 @@ ssize_t bch2_direct_write(struct kiocb *req, struct iov_iter *iter) dio->mapping = mapping; dio->inode = inode; dio->mm = current->mm; + dio->iov = NULL; dio->loop = false; dio->extending = extending; dio->sync = is_sync_kiocb(req) || extending; dio->flush = iocb_is_dsync(req) && !c->opts.journal_flush_disabled; - dio->free_iov = false; dio->quota_res.sectors = 0; dio->written = 0; dio->iter = *iter; diff --git a/fs/bcachefs/fs-ioctl.c b/fs/bcachefs/fs-ioctl.c index 5a39bcb597a3..94e5a567fa44 100644 --- a/fs/bcachefs/fs-ioctl.c +++ b/fs/bcachefs/fs-ioctl.c @@ -100,7 +100,8 @@ static int bch2_ioc_setflags(struct bch_fs *c, } mutex_lock(&inode->ei_update_lock); - ret = bch2_write_inode(c, inode, bch2_inode_flags_set, &s, + ret = bch2_subvol_is_ro(c, inode->ei_subvol) ?: + bch2_write_inode(c, inode, bch2_inode_flags_set, &s, ATTR_CTIME); mutex_unlock(&inode->ei_update_lock); @@ -183,13 +184,10 @@ static int bch2_ioc_fssetxattr(struct bch_fs *c, } mutex_lock(&inode->ei_update_lock); - ret = bch2_set_projid(c, inode, fa.fsx_projid); - if (ret) - goto err_unlock; - - ret = bch2_write_inode(c, inode, fssetxattr_inode_update_fn, &s, + ret = bch2_subvol_is_ro(c, inode->ei_subvol) ?: + bch2_set_projid(c, inode, fa.fsx_projid) ?: + bch2_write_inode(c, inode, fssetxattr_inode_update_fn, &s, ATTR_CTIME); -err_unlock: mutex_unlock(&inode->ei_update_lock); err: inode_unlock(&inode->v); @@ -291,14 +289,14 @@ static int bch2_ioc_goingdown(struct bch_fs *c, u32 __user *arg) switch (flags) { case FSOP_GOING_FLAGS_DEFAULT: - ret = freeze_bdev(c->vfs_sb->s_bdev); + ret = bdev_freeze(c->vfs_sb->s_bdev); if (ret) goto err; bch2_journal_flush(&c->journal); c->vfs_sb->s_flags |= SB_RDONLY; bch2_fs_emergency_read_only(c); - thaw_bdev(c->vfs_sb->s_bdev); + bdev_thaw(c->vfs_sb->s_bdev); break; case FSOP_GOING_FLAGS_LOGFLUSH: @@ -413,7 +411,7 @@ retry: if ((arg.flags & BCH_SUBVOL_SNAPSHOT_CREATE) && !arg.src_ptr) - snapshot_src.subvol = to_bch_ei(dir)->ei_inode.bi_subvol; + snapshot_src.subvol = inode_inum(to_bch_ei(dir)).subvol; inode = __bch2_create(file_mnt_idmap(filp), to_bch_ei(dir), dst_dentry, arg.mode|S_IFDIR, diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c index 4d51be813509..49da8db1d9e9 100644 --- a/fs/bcachefs/fs.c +++ b/fs/bcachefs/fs.c @@ -258,7 +258,8 @@ __bch2_create(struct mnt_idmap *idmap, retry: bch2_trans_begin(trans); - ret = bch2_create_trans(trans, + ret = bch2_subvol_is_ro_trans(trans, dir->ei_subvol) ?: + bch2_create_trans(trans, inode_inum(dir), &dir_u, &inode_u, !(flags & BCH_CREATE_TMPFILE) ? &dentry->d_name : NULL, @@ -430,7 +431,9 @@ static int bch2_link(struct dentry *old_dentry, struct inode *vdir, lockdep_assert_held(&inode->v.i_rwsem); - ret = __bch2_link(c, inode, dir, dentry); + ret = bch2_subvol_is_ro(c, dir->ei_subvol) ?: + bch2_subvol_is_ro(c, inode->ei_subvol) ?: + __bch2_link(c, inode, dir, dentry); if (unlikely(ret)) return ret; @@ -481,7 +484,11 @@ err: static int bch2_unlink(struct inode *vdir, struct dentry *dentry) { - return __bch2_unlink(vdir, dentry, false); + struct bch_inode_info *dir= to_bch_ei(vdir); + struct bch_fs *c = dir->v.i_sb->s_fs_info; + + return bch2_subvol_is_ro(c, dir->ei_subvol) ?: + __bch2_unlink(vdir, dentry, false); } static int bch2_symlink(struct mnt_idmap *idmap, @@ -562,6 +569,11 @@ static int bch2_rename2(struct mnt_idmap *idmap, src_inode, dst_inode); + ret = bch2_subvol_is_ro_trans(trans, src_dir->ei_subvol) ?: + bch2_subvol_is_ro_trans(trans, dst_dir->ei_subvol); + if (ret) + goto err; + if (inode_attr_changing(dst_dir, src_inode, Inode_opt_project)) { ret = bch2_fs_quota_transfer(c, src_inode, dst_dir->ei_qid, @@ -783,11 +795,13 @@ static int bch2_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr) { struct bch_inode_info *inode = to_bch_ei(dentry->d_inode); + struct bch_fs *c = inode->v.i_sb->s_fs_info; int ret; lockdep_assert_held(&inode->v.i_rwsem); - ret = setattr_prepare(idmap, dentry, iattr); + ret = bch2_subvol_is_ro(c, inode->ei_subvol) ?: + setattr_prepare(idmap, dentry, iattr); if (ret) return ret; @@ -1010,12 +1024,26 @@ static int bch2_vfs_readdir(struct file *file, struct dir_context *ctx) return bch2_err_class(ret); } +static int bch2_open(struct inode *vinode, struct file *file) +{ + if (file->f_flags & (O_WRONLY|O_RDWR)) { + struct bch_inode_info *inode = to_bch_ei(vinode); + struct bch_fs *c = inode->v.i_sb->s_fs_info; + + int ret = bch2_subvol_is_ro(c, inode->ei_subvol); + if (ret) + return ret; + } + + return generic_file_open(vinode, file); +} + static const struct file_operations bch_file_operations = { + .open = bch2_open, .llseek = bch2_llseek, .read_iter = bch2_read_iter, .write_iter = bch2_write_iter, .mmap = bch2_mmap, - .open = generic_file_open, .fsync = bch2_fsync, .splice_read = filemap_splice_read, .splice_write = iter_file_splice_write, @@ -1143,24 +1171,33 @@ static int bch2_encode_fh(struct inode *vinode, u32 *fh, int *len, { struct bch_inode_info *inode = to_bch_ei(vinode); struct bch_inode_info *dir = to_bch_ei(vdir); - - if (*len < sizeof(struct bcachefs_fid_with_parent) / sizeof(u32)) - return FILEID_INVALID; + int min_len; if (!S_ISDIR(inode->v.i_mode) && dir) { struct bcachefs_fid_with_parent *fid = (void *) fh; + min_len = sizeof(*fid) / sizeof(u32); + if (*len < min_len) { + *len = min_len; + return FILEID_INVALID; + } + fid->fid = bch2_inode_to_fid(inode); fid->dir = bch2_inode_to_fid(dir); - *len = sizeof(*fid) / sizeof(u32); + *len = min_len; return FILEID_BCACHEFS_WITH_PARENT; } else { struct bcachefs_fid *fid = (void *) fh; + min_len = sizeof(*fid) / sizeof(u32); + if (*len < min_len) { + *len = min_len; + return FILEID_INVALID; + } *fid = bch2_inode_to_fid(inode); - *len = sizeof(*fid) / sizeof(u32); + *len = min_len; return FILEID_BCACHEFS_WITHOUT_PARENT; } } @@ -1733,6 +1770,9 @@ static int bch2_unfreeze(struct super_block *sb) struct bch_fs *c = sb->s_fs_info; int ret; + if (test_bit(BCH_FS_EMERGENCY_RO, &c->flags)) + return 0; + down_write(&c->state_lock); ret = bch2_fs_read_write(c); up_write(&c->state_lock); diff --git a/fs/bcachefs/inode.c b/fs/bcachefs/inode.c index c7849b0753e7..9309cfeecd8d 100644 --- a/fs/bcachefs/inode.c +++ b/fs/bcachefs/inode.c @@ -7,6 +7,7 @@ #include "btree_update.h" #include "buckets.h" #include "compress.h" +#include "dirent.h" #include "error.h" #include "extents.h" #include "extent_update.h" @@ -1093,11 +1094,15 @@ static int may_delete_deleted_inode(struct btree_trans *trans, if (ret) goto out; - if (fsck_err_on(S_ISDIR(inode.bi_mode), c, - deleted_inode_is_dir, - "directory %llu:%u in deleted_inodes btree", - pos.offset, pos.snapshot)) - goto delete; + if (S_ISDIR(inode.bi_mode)) { + ret = bch2_empty_dir_snapshot(trans, pos.offset, pos.snapshot); + if (fsck_err_on(ret == -ENOTEMPTY, c, deleted_inode_is_dir, + "non empty directory %llu:%u in deleted_inodes btree", + pos.offset, pos.snapshot)) + goto delete; + if (ret) + goto out; + } if (fsck_err_on(!(inode.bi_flags & BCH_INODE_unlinked), c, deleted_inode_not_unlinked, diff --git a/fs/bcachefs/io_write.c b/fs/bcachefs/io_write.c index 8ede46b1e354..8c8cb1541ac9 100644 --- a/fs/bcachefs/io_write.c +++ b/fs/bcachefs/io_write.c @@ -1216,6 +1216,12 @@ static CLOSURE_CALLBACK(bch2_nocow_write_done) bch2_write_done(cl); } +struct bucket_to_lock { + struct bpos b; + unsigned gen; + struct nocow_lock_bucket *l; +}; + static void bch2_nocow_write(struct bch_write_op *op) { struct bch_fs *c = op->c; @@ -1224,18 +1230,16 @@ static void bch2_nocow_write(struct bch_write_op *op) struct bkey_s_c k; struct bkey_ptrs_c ptrs; const struct bch_extent_ptr *ptr; - struct { - struct bpos b; - unsigned gen; - struct nocow_lock_bucket *l; - } buckets[BCH_REPLICAS_MAX]; - unsigned nr_buckets = 0; + DARRAY_PREALLOCATED(struct bucket_to_lock, 3) buckets; + struct bucket_to_lock *i; u32 snapshot; - int ret, i; + struct bucket_to_lock *stale_at; + int ret; if (op->flags & BCH_WRITE_MOVE) return; + darray_init(&buckets); trans = bch2_trans_get(c); retry: bch2_trans_begin(trans); @@ -1250,7 +1254,7 @@ retry: while (1) { struct bio *bio = &op->wbio.bio; - nr_buckets = 0; + buckets.nr = 0; k = bch2_btree_iter_peek_slot(&iter); ret = bkey_err(k); @@ -1263,26 +1267,26 @@ retry: break; if (bch2_keylist_realloc(&op->insert_keys, - op->inline_keys, - ARRAY_SIZE(op->inline_keys), - k.k->u64s)) + op->inline_keys, + ARRAY_SIZE(op->inline_keys), + k.k->u64s)) break; /* Get iorefs before dropping btree locks: */ ptrs = bch2_bkey_ptrs_c(k); bkey_for_each_ptr(ptrs, ptr) { - buckets[nr_buckets].b = PTR_BUCKET_POS(c, ptr); - buckets[nr_buckets].gen = ptr->gen; - buckets[nr_buckets].l = - bucket_nocow_lock(&c->nocow_locks, - bucket_to_u64(buckets[nr_buckets].b)); - - prefetch(buckets[nr_buckets].l); + struct bpos b = PTR_BUCKET_POS(c, ptr); + struct nocow_lock_bucket *l = + bucket_nocow_lock(&c->nocow_locks, bucket_to_u64(b)); + prefetch(l); if (unlikely(!bch2_dev_get_ioref(bch_dev_bkey_exists(c, ptr->dev), WRITE))) goto err_get_ioref; - nr_buckets++; + /* XXX allocating memory with btree locks held - rare */ + darray_push_gfp(&buckets, ((struct bucket_to_lock) { + .b = b, .gen = ptr->gen, .l = l, + }), GFP_KERNEL|__GFP_NOFAIL); if (ptr->unwritten) op->flags |= BCH_WRITE_CONVERT_UNWRITTEN; @@ -1296,21 +1300,21 @@ retry: if (op->flags & BCH_WRITE_CONVERT_UNWRITTEN) bch2_cut_back(POS(op->pos.inode, op->pos.offset + bio_sectors(bio)), op->insert_keys.top); - for (i = 0; i < nr_buckets; i++) { - struct bch_dev *ca = bch_dev_bkey_exists(c, buckets[i].b.inode); - struct nocow_lock_bucket *l = buckets[i].l; - bool stale; + darray_for_each(buckets, i) { + struct bch_dev *ca = bch_dev_bkey_exists(c, i->b.inode); - __bch2_bucket_nocow_lock(&c->nocow_locks, l, - bucket_to_u64(buckets[i].b), + __bch2_bucket_nocow_lock(&c->nocow_locks, i->l, + bucket_to_u64(i->b), BUCKET_NOCOW_LOCK_UPDATE); rcu_read_lock(); - stale = gen_after(*bucket_gen(ca, buckets[i].b.offset), buckets[i].gen); + bool stale = gen_after(*bucket_gen(ca, i->b.offset), i->gen); rcu_read_unlock(); - if (unlikely(stale)) + if (unlikely(stale)) { + stale_at = i; goto err_bucket_stale; + } } bio = &op->wbio.bio; @@ -1346,15 +1350,14 @@ err: if (ret) { bch_err_inum_offset_ratelimited(c, - op->pos.inode, - op->pos.offset << 9, - "%s: btree lookup error %s", - __func__, bch2_err_str(ret)); + op->pos.inode, op->pos.offset << 9, + "%s: btree lookup error %s", __func__, bch2_err_str(ret)); op->error = ret; op->flags |= BCH_WRITE_DONE; } bch2_trans_put(trans); + darray_exit(&buckets); /* fallback to cow write path? */ if (!(op->flags & BCH_WRITE_DONE)) { @@ -1374,24 +1377,21 @@ err: } return; err_get_ioref: - for (i = 0; i < nr_buckets; i++) - percpu_ref_put(&bch_dev_bkey_exists(c, buckets[i].b.inode)->io_ref); + darray_for_each(buckets, i) + percpu_ref_put(&bch_dev_bkey_exists(c, i->b.inode)->io_ref); /* Fall back to COW path: */ goto out; err_bucket_stale: - while (i >= 0) { - bch2_bucket_nocow_unlock(&c->nocow_locks, - buckets[i].b, - BUCKET_NOCOW_LOCK_UPDATE); - --i; + darray_for_each(buckets, i) { + bch2_bucket_nocow_unlock(&c->nocow_locks, i->b, BUCKET_NOCOW_LOCK_UPDATE); + if (i == stale_at) + break; } - for (i = 0; i < nr_buckets; i++) - percpu_ref_put(&bch_dev_bkey_exists(c, buckets[i].b.inode)->io_ref); /* We can retry this: */ ret = -BCH_ERR_transaction_restart; - goto out; + goto err_get_ioref; } static void __bch2_write(struct bch_write_op *op) diff --git a/fs/bcachefs/journal.c b/fs/bcachefs/journal.c index 489b34046e78..8cf238be6213 100644 --- a/fs/bcachefs/journal.c +++ b/fs/bcachefs/journal.c @@ -249,7 +249,7 @@ static bool journal_entry_want_write(struct journal *j) return ret; } -static bool journal_entry_close(struct journal *j) +bool bch2_journal_entry_close(struct journal *j) { bool ret; @@ -383,7 +383,7 @@ static bool journal_quiesced(struct journal *j) bool ret = atomic64_read(&j->seq) == j->seq_ondisk; if (!ret) - journal_entry_close(j); + bch2_journal_entry_close(j); return ret; } @@ -436,7 +436,7 @@ retry: /* * Recheck after taking the lock, so we don't race with another thread - * that just did journal_entry_open() and call journal_entry_close() + * that just did journal_entry_open() and call bch2_journal_entry_close() * unnecessarily */ if (journal_res_get_fast(j, res, flags)) { @@ -1041,7 +1041,7 @@ void bch2_fs_journal_stop(struct journal *j) bch2_journal_reclaim_stop(j); bch2_journal_flush_all_pins(j); - wait_event(j->wait, journal_entry_close(j)); + wait_event(j->wait, bch2_journal_entry_close(j)); /* * Always write a new journal entry, to make sure the clock hands are up diff --git a/fs/bcachefs/journal.h b/fs/bcachefs/journal.h index 4c513fca5ef2..2f768e11aec9 100644 --- a/fs/bcachefs/journal.h +++ b/fs/bcachefs/journal.h @@ -266,6 +266,7 @@ static inline union journal_res_state journal_state_buf_put(struct journal *j, u return s; } +bool bch2_journal_entry_close(struct journal *); void bch2_journal_buf_put_final(struct journal *, u64, bool); static inline void __bch2_journal_buf_put(struct journal *j, unsigned idx, u64 seq) diff --git a/fs/bcachefs/journal_io.c b/fs/bcachefs/journal_io.c index 0f17fc5f8d68..3eb6c3f62a81 100644 --- a/fs/bcachefs/journal_io.c +++ b/fs/bcachefs/journal_io.c @@ -408,8 +408,10 @@ static int journal_entry_btree_root_validate(struct bch_fs *c, return 0; } - return journal_validate_key(c, jset, entry, 1, entry->btree_id, k, - version, big_endian, flags); + ret = journal_validate_key(c, jset, entry, 1, entry->btree_id, k, + version, big_endian, flags); + if (ret == FSCK_DELETED_KEY) + ret = 0; fsck_err: return ret; } @@ -1599,6 +1601,7 @@ static CLOSURE_CALLBACK(journal_write_done) } while ((v = atomic64_cmpxchg(&j->reservations.counter, old.v, new.v)) != old.v); + bch2_journal_reclaim_fast(j); bch2_journal_space_available(j); closure_wake_up(&w->wait); diff --git a/fs/bcachefs/journal_reclaim.c b/fs/bcachefs/journal_reclaim.c index e63c6eda86af..ec712104addb 100644 --- a/fs/bcachefs/journal_reclaim.c +++ b/fs/bcachefs/journal_reclaim.c @@ -776,6 +776,9 @@ static int journal_flush_done(struct journal *j, u64 seq_to_flush, (1U << JOURNAL_PIN_btree), 0, 0, 0)) *did_work = true; + if (seq_to_flush > journal_cur_seq(j)) + bch2_journal_entry_close(j); + spin_lock(&j->lock); /* * If journal replay hasn't completed, the unreplayed journal entries diff --git a/fs/bcachefs/printbuf.c b/fs/bcachefs/printbuf.c index 5e653eb81d54..accf246c3233 100644 --- a/fs/bcachefs/printbuf.c +++ b/fs/bcachefs/printbuf.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: LGPL-2.1+ /* Copyright (C) 2022 Kent Overstreet */ +#include <linux/bitmap.h> #include <linux/err.h> #include <linux/export.h> #include <linux/kernel.h> @@ -423,3 +424,24 @@ void bch2_prt_bitflags(struct printbuf *out, flags ^= BIT_ULL(bit); } } + +void bch2_prt_bitflags_vector(struct printbuf *out, + const char * const list[], + unsigned long *v, unsigned nr) +{ + bool first = true; + unsigned i; + + for (i = 0; i < nr; i++) + if (!list[i]) { + nr = i - 1; + break; + } + + for_each_set_bit(i, v, nr) { + if (!first) + bch2_prt_printf(out, ","); + first = false; + bch2_prt_printf(out, "%s", list[i]); + } +} diff --git a/fs/bcachefs/printbuf.h b/fs/bcachefs/printbuf.h index 2191423d9f22..9a4a56c40937 100644 --- a/fs/bcachefs/printbuf.h +++ b/fs/bcachefs/printbuf.h @@ -124,6 +124,8 @@ void bch2_prt_units_u64(struct printbuf *, u64); void bch2_prt_units_s64(struct printbuf *, s64); void bch2_prt_string_option(struct printbuf *, const char * const[], size_t); void bch2_prt_bitflags(struct printbuf *, const char * const[], u64); +void bch2_prt_bitflags_vector(struct printbuf *, const char * const[], + unsigned long *, unsigned); /* Initializer for a heap allocated printbuf: */ #define PRINTBUF ((struct printbuf) { .heap_allocated = true }) diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c index 770ced1c6285..5cf7d0532002 100644 --- a/fs/bcachefs/recovery.c +++ b/fs/bcachefs/recovery.c @@ -27,6 +27,7 @@ #include "recovery.h" #include "replicas.h" #include "sb-clean.h" +#include "sb-downgrade.h" #include "snapshot.h" #include "subvolume.h" #include "super-io.h" @@ -144,7 +145,7 @@ static int bch2_journal_replay(struct bch_fs *c) u64 start_seq = c->journal_replay_seq_start; u64 end_seq = c->journal_replay_seq_start; size_t i; - int ret; + int ret = 0; move_gap(keys->d, keys->nr, keys->size, keys->gap, keys->nr); keys->gap = keys->nr; @@ -481,7 +482,7 @@ static int bch2_fs_upgrade_for_subvolumes(struct bch_fs *c) } const char * const bch2_recovery_passes[] = { -#define x(_fn, _when) #_fn, +#define x(_fn, ...) #_fn, BCH_RECOVERY_PASSES() #undef x NULL @@ -504,18 +505,47 @@ struct recovery_pass_fn { }; static struct recovery_pass_fn recovery_pass_fns[] = { -#define x(_fn, _when) { .fn = bch2_##_fn, .when = _when }, +#define x(_fn, _id, _when) { .fn = bch2_##_fn, .when = _when }, BCH_RECOVERY_PASSES() #undef x }; -static void check_version_upgrade(struct bch_fs *c) +u64 bch2_recovery_passes_to_stable(u64 v) +{ + static const u8 map[] = { +#define x(n, id, ...) [BCH_RECOVERY_PASS_##n] = BCH_RECOVERY_PASS_STABLE_##n, + BCH_RECOVERY_PASSES() +#undef x + }; + + u64 ret = 0; + for (unsigned i = 0; i < ARRAY_SIZE(map); i++) + if (v & BIT_ULL(i)) + ret |= BIT_ULL(map[i]); + return ret; +} + +u64 bch2_recovery_passes_from_stable(u64 v) +{ + static const u8 map[] = { +#define x(n, id, ...) [BCH_RECOVERY_PASS_STABLE_##n] = BCH_RECOVERY_PASS_##n, + BCH_RECOVERY_PASSES() +#undef x + }; + + u64 ret = 0; + for (unsigned i = 0; i < ARRAY_SIZE(map); i++) + if (v & BIT_ULL(i)) + ret |= BIT_ULL(map[i]); + return ret; +} + +static bool check_version_upgrade(struct bch_fs *c) { unsigned latest_compatible = bch2_latest_compatible_version(c->sb.version); unsigned latest_version = bcachefs_metadata_version_current; unsigned old_version = c->sb.version_upgrade_complete ?: c->sb.version; unsigned new_version = 0; - u64 recovery_passes; if (old_version < bcachefs_metadata_required_upgrade_below) { if (c->opts.version_upgrade == BCH_VERSION_UPGRADE_incompatible || @@ -559,7 +589,7 @@ static void check_version_upgrade(struct bch_fs *c) bch2_version_to_text(&buf, new_version); prt_newline(&buf); - recovery_passes = bch2_upgrade_recovery_passes(c, old_version, new_version); + u64 recovery_passes = bch2_upgrade_recovery_passes(c, old_version, new_version); if (recovery_passes) { if ((recovery_passes & RECOVERY_PASS_ALL_FSCK) == RECOVERY_PASS_ALL_FSCK) prt_str(&buf, "fsck required"); @@ -574,12 +604,13 @@ static void check_version_upgrade(struct bch_fs *c) bch_info(c, "%s", buf.buf); - mutex_lock(&c->sb_lock); bch2_sb_upgrade(c, new_version); - mutex_unlock(&c->sb_lock); printbuf_exit(&buf); + return true; } + + return false; } u64 bch2_fsck_recovery_passes(void) @@ -654,7 +685,6 @@ int bch2_fs_recovery(struct bch_fs *c) struct bch_sb_field_clean *clean = NULL; struct jset *last_journal_entry = NULL; u64 last_seq = 0, blacklist_seq, journal_seq; - bool write_sb = false; int ret = 0; if (c->sb.clean) { @@ -682,15 +712,73 @@ int bch2_fs_recovery(struct bch_fs *c) goto err; } - if (c->opts.fsck || !(c->opts.nochanges && c->opts.norecovery)) - check_version_upgrade(c); - if (c->opts.fsck && c->opts.norecovery) { bch_err(c, "cannot select both norecovery and fsck"); ret = -EINVAL; goto err; } + if (!(c->opts.nochanges && c->opts.norecovery)) { + mutex_lock(&c->sb_lock); + bool write_sb = false; + + struct bch_sb_field_ext *ext = + bch2_sb_field_get_minsize(&c->disk_sb, ext, sizeof(*ext) / sizeof(u64)); + if (!ext) { + ret = -BCH_ERR_ENOSPC_sb; + mutex_unlock(&c->sb_lock); + goto err; + } + + if (BCH_SB_HAS_TOPOLOGY_ERRORS(c->disk_sb.sb)) { + ext->recovery_passes_required[0] |= + cpu_to_le64(bch2_recovery_passes_to_stable(BIT_ULL(BCH_RECOVERY_PASS_check_topology))); + write_sb = true; + } + + u64 sb_passes = bch2_recovery_passes_from_stable(le64_to_cpu(ext->recovery_passes_required[0])); + if (sb_passes) { + struct printbuf buf = PRINTBUF; + prt_str(&buf, "superblock requires following recovery passes to be run:\n "); + prt_bitflags(&buf, bch2_recovery_passes, sb_passes); + bch_info(c, "%s", buf.buf); + printbuf_exit(&buf); + } + + if (bch2_check_version_downgrade(c)) { + struct printbuf buf = PRINTBUF; + + prt_str(&buf, "Version downgrade required:\n"); + + __le64 passes = ext->recovery_passes_required[0]; + bch2_sb_set_downgrade(c, + BCH_VERSION_MINOR(bcachefs_metadata_version_current), + BCH_VERSION_MINOR(c->sb.version)); + passes = ext->recovery_passes_required[0] & ~passes; + if (passes) { + prt_str(&buf, " running recovery passes: "); + prt_bitflags(&buf, bch2_recovery_passes, + bch2_recovery_passes_from_stable(le64_to_cpu(passes))); + } + + bch_info(c, "%s", buf.buf); + printbuf_exit(&buf); + write_sb = true; + } + + if (check_version_upgrade(c)) + write_sb = true; + + if (write_sb) + bch2_write_super(c); + + c->recovery_passes_explicit |= bch2_recovery_passes_from_stable(le64_to_cpu(ext->recovery_passes_required[0])); + mutex_unlock(&c->sb_lock); + } + + if (c->opts.fsck && IS_ENABLED(CONFIG_BCACHEFS_DEBUG)) + c->recovery_passes_explicit |= BIT_ULL(BCH_RECOVERY_PASS_check_topology); + ret = bch2_blacklist_table_initialize(c); if (ret) { bch_err(c, "error initializing blacklist table"); @@ -827,11 +915,6 @@ use_clean: if (ret) goto err; - if (c->opts.fsck && - (IS_ENABLED(CONFIG_BCACHEFS_DEBUG) || - BCH_SB_HAS_TOPOLOGY_ERRORS(c->disk_sb.sb))) - c->recovery_passes_explicit |= BIT_ULL(BCH_RECOVERY_PASS_check_topology); - ret = bch2_run_recovery_passes(c); if (ret) goto err; @@ -868,16 +951,30 @@ use_clean: } mutex_lock(&c->sb_lock); - if (BCH_SB_VERSION_UPGRADE_COMPLETE(c->disk_sb.sb) != c->sb.version) { - SET_BCH_SB_VERSION_UPGRADE_COMPLETE(c->disk_sb.sb, c->sb.version); + bool write_sb = false; + + if (BCH_SB_VERSION_UPGRADE_COMPLETE(c->disk_sb.sb) != le16_to_cpu(c->disk_sb.sb->version)) { + SET_BCH_SB_VERSION_UPGRADE_COMPLETE(c->disk_sb.sb, le16_to_cpu(c->disk_sb.sb->version)); write_sb = true; } - if (!test_bit(BCH_FS_ERROR, &c->flags)) { + if (!test_bit(BCH_FS_ERROR, &c->flags) && + !(c->disk_sb.sb->compat[0] & cpu_to_le64(1ULL << BCH_COMPAT_alloc_info))) { c->disk_sb.sb->compat[0] |= cpu_to_le64(1ULL << BCH_COMPAT_alloc_info); write_sb = true; } + if (!test_bit(BCH_FS_ERROR, &c->flags)) { + struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext); + if (ext && + (!bch2_is_zero(ext->recovery_passes_required, sizeof(ext->recovery_passes_required)) || + !bch2_is_zero(ext->errors_silent, sizeof(ext->errors_silent)))) { + memset(ext->recovery_passes_required, 0, sizeof(ext->recovery_passes_required)); + memset(ext->errors_silent, 0, sizeof(ext->errors_silent)); + write_sb = true; + } + } + if (c->opts.fsck && !test_bit(BCH_FS_ERROR, &c->flags) && !test_bit(BCH_FS_ERRORS_NOT_FIXED, &c->flags)) { @@ -947,7 +1044,7 @@ int bch2_fs_initialize(struct bch_fs *c) c->disk_sb.sb->compat[0] |= cpu_to_le64(1ULL << BCH_COMPAT_extents_above_btree_updates_done); c->disk_sb.sb->compat[0] |= cpu_to_le64(1ULL << BCH_COMPAT_bformat_overflow_done); - bch2_sb_maybe_downgrade(c); + bch2_check_version_downgrade(c); if (c->opts.version_upgrade != BCH_VERSION_UPGRADE_none) { bch2_sb_upgrade(c, bcachefs_metadata_version_current); diff --git a/fs/bcachefs/recovery.h b/fs/bcachefs/recovery.h index 852d30567da9..3a554b0751d0 100644 --- a/fs/bcachefs/recovery.h +++ b/fs/bcachefs/recovery.h @@ -4,12 +4,18 @@ extern const char * const bch2_recovery_passes[]; +u64 bch2_recovery_passes_to_stable(u64 v); +u64 bch2_recovery_passes_from_stable(u64 v); + /* * For when we need to rewind recovery passes and run a pass we skipped: */ static inline int bch2_run_explicit_recovery_pass(struct bch_fs *c, enum bch_recovery_pass pass) { + if (c->recovery_passes_explicit & BIT_ULL(pass)) + return 0; + bch_info(c, "running explicit recovery pass %s (%u), currently at %s (%u)", bch2_recovery_passes[pass], pass, bch2_recovery_passes[c->curr_recovery_pass], c->curr_recovery_pass); diff --git a/fs/bcachefs/recovery_types.h b/fs/bcachefs/recovery_types.h index 515e3d62c2ac..d37c6fd30e38 100644 --- a/fs/bcachefs/recovery_types.h +++ b/fs/bcachefs/recovery_types.h @@ -7,45 +7,57 @@ #define PASS_UNCLEAN BIT(2) #define PASS_ALWAYS BIT(3) -#define BCH_RECOVERY_PASSES() \ - x(alloc_read, PASS_ALWAYS) \ - x(stripes_read, PASS_ALWAYS) \ - x(initialize_subvolumes, 0) \ - x(snapshots_read, PASS_ALWAYS) \ - x(check_topology, 0) \ - x(check_allocations, PASS_FSCK) \ - x(trans_mark_dev_sbs, PASS_ALWAYS|PASS_SILENT) \ - x(fs_journal_alloc, PASS_ALWAYS|PASS_SILENT) \ - x(set_may_go_rw, PASS_ALWAYS|PASS_SILENT) \ - x(journal_replay, PASS_ALWAYS) \ - x(check_alloc_info, PASS_FSCK) \ - x(check_lrus, PASS_FSCK) \ - x(check_btree_backpointers, PASS_FSCK) \ - x(check_backpointers_to_extents,PASS_FSCK) \ - x(check_extents_to_backpointers,PASS_FSCK) \ - x(check_alloc_to_lru_refs, PASS_FSCK) \ - x(fs_freespace_init, PASS_ALWAYS|PASS_SILENT) \ - x(bucket_gens_init, 0) \ - x(check_snapshot_trees, PASS_FSCK) \ - x(check_snapshots, PASS_FSCK) \ - x(check_subvols, PASS_FSCK) \ - x(delete_dead_snapshots, PASS_FSCK) \ - x(fs_upgrade_for_subvolumes, 0) \ - x(resume_logged_ops, PASS_ALWAYS) \ - x(check_inodes, PASS_FSCK) \ - x(check_extents, PASS_FSCK) \ - x(check_indirect_extents, PASS_FSCK) \ - x(check_dirents, PASS_FSCK) \ - x(check_xattrs, PASS_FSCK) \ - x(check_root, PASS_FSCK) \ - x(check_directory_structure, PASS_FSCK) \ - x(check_nlinks, PASS_FSCK) \ - x(delete_dead_inodes, PASS_FSCK|PASS_UNCLEAN) \ - x(fix_reflink_p, 0) \ - x(set_fs_needs_rebalance, 0) \ +/* + * Passes may be reordered, but the second field is a persistent identifier and + * must never change: + */ +#define BCH_RECOVERY_PASSES() \ + x(alloc_read, 0, PASS_ALWAYS) \ + x(stripes_read, 1, PASS_ALWAYS) \ + x(initialize_subvolumes, 2, 0) \ + x(snapshots_read, 3, PASS_ALWAYS) \ + x(check_topology, 4, 0) \ + x(check_allocations, 5, PASS_FSCK) \ + x(trans_mark_dev_sbs, 6, PASS_ALWAYS|PASS_SILENT) \ + x(fs_journal_alloc, 7, PASS_ALWAYS|PASS_SILENT) \ + x(set_may_go_rw, 8, PASS_ALWAYS|PASS_SILENT) \ + x(journal_replay, 9, PASS_ALWAYS) \ + x(check_alloc_info, 10, PASS_FSCK) \ + x(check_lrus, 11, PASS_FSCK) \ + x(check_btree_backpointers, 12, PASS_FSCK) \ + x(check_backpointers_to_extents, 13, PASS_FSCK) \ + x(check_extents_to_backpointers, 14, PASS_FSCK) \ + x(check_alloc_to_lru_refs, 15, PASS_FSCK) \ + x(fs_freespace_init, 16, PASS_ALWAYS|PASS_SILENT) \ + x(bucket_gens_init, 17, 0) \ + x(check_snapshot_trees, 18, PASS_FSCK) \ + x(check_snapshots, 19, PASS_FSCK) \ + x(check_subvols, 20, PASS_FSCK) \ + x(delete_dead_snapshots, 21, PASS_FSCK) \ + x(fs_upgrade_for_subvolumes, 22, 0) \ + x(resume_logged_ops, 23, PASS_ALWAYS) \ + x(check_inodes, 24, PASS_FSCK) \ + x(check_extents, 25, PASS_FSCK) \ + x(check_indirect_extents, 26, PASS_FSCK) \ + x(check_dirents, 27, PASS_FSCK) \ + x(check_xattrs, 28, PASS_FSCK) \ + x(check_root, 29, PASS_FSCK) \ + x(check_directory_structure, 30, PASS_FSCK) \ + x(check_nlinks, 31, PASS_FSCK) \ + x(delete_dead_inodes, 32, PASS_FSCK|PASS_UNCLEAN) \ + x(fix_reflink_p, 33, 0) \ + x(set_fs_needs_rebalance, 34, 0) \ +/* We normally enumerate recovery passes in the order we run them: */ enum bch_recovery_pass { -#define x(n, when) BCH_RECOVERY_PASS_##n, +#define x(n, id, when) BCH_RECOVERY_PASS_##n, + BCH_RECOVERY_PASSES() +#undef x +}; + +/* But we also need stable identifiers that can be used in the superblock */ +enum bch_recovery_pass_stable { +#define x(n, id, when) BCH_RECOVERY_PASS_STABLE_##n = id, BCH_RECOVERY_PASSES() #undef x }; diff --git a/fs/bcachefs/reflink.c b/fs/bcachefs/reflink.c index 6e1bfe9feb59..37d16e04e671 100644 --- a/fs/bcachefs/reflink.c +++ b/fs/bcachefs/reflink.c @@ -121,6 +121,14 @@ int bch2_trans_mark_reflink_v(struct btree_trans *trans, { check_indirect_extent_deleting(new, &flags); + if (old.k->type == KEY_TYPE_reflink_v && + new->k.type == KEY_TYPE_reflink_v && + old.k->u64s == new->k.u64s && + !memcmp(bkey_s_c_to_reflink_v(old).v->start, + bkey_i_to_reflink_v(new)->v.start, + bkey_val_bytes(&new->k) - 8)) + return 0; + return bch2_trans_mark_extent(trans, btree_id, level, old, new, flags); } diff --git a/fs/bcachefs/sb-clean.c b/fs/bcachefs/sb-clean.c index e151ada1c8bd..c76ad8ea5e4a 100644 --- a/fs/bcachefs/sb-clean.c +++ b/fs/bcachefs/sb-clean.c @@ -332,8 +332,6 @@ int bch2_fs_mark_dirty(struct bch_fs *c) mutex_lock(&c->sb_lock); SET_BCH_SB_CLEAN(c->disk_sb.sb, false); - - bch2_sb_maybe_downgrade(c); c->disk_sb.sb->features[0] |= cpu_to_le64(BCH_SB_FEATURES_ALWAYS); ret = bch2_write_super(c); diff --git a/fs/bcachefs/sb-downgrade.c b/fs/bcachefs/sb-downgrade.c new file mode 100644 index 000000000000..4919237bbe73 --- /dev/null +++ b/fs/bcachefs/sb-downgrade.c @@ -0,0 +1,188 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Superblock section that contains a list of recovery passes to run when + * downgrading past a given version + */ + +#include "bcachefs.h" +#include "darray.h" +#include "recovery.h" +#include "sb-downgrade.h" +#include "sb-errors.h" +#include "super-io.h" + +/* + * Downgrade table: + * When dowgrading past certain versions, we need to run certain recovery passes + * and fix certain errors: + * + * x(version, recovery_passes, errors...) + */ + +#define DOWNGRADE_TABLE() + +struct downgrade_entry { + u64 recovery_passes; + u16 version; + u16 nr_errors; + const u16 *errors; +}; + +#define x(ver, passes, ...) static const u16 ver_##errors[] = { __VA_ARGS__ }; +DOWNGRADE_TABLE() +#undef x + +static const struct downgrade_entry downgrade_table[] = { +#define x(ver, passes, ...) { \ + .recovery_passes = passes, \ + .version = bcachefs_metadata_version_##ver,\ + .nr_errors = ARRAY_SIZE(ver_##errors), \ + .errors = ver_##errors, \ +}, +DOWNGRADE_TABLE() +#undef x +}; + +static inline const struct bch_sb_field_downgrade_entry * +downgrade_entry_next_c(const struct bch_sb_field_downgrade_entry *e) +{ + return (void *) &e->errors[le16_to_cpu(e->nr_errors)]; +} + +#define for_each_downgrade_entry(_d, _i) \ + for (const struct bch_sb_field_downgrade_entry *_i = (_d)->entries; \ + (void *) _i < vstruct_end(&(_d)->field) && \ + (void *) &_i->errors[0] < vstruct_end(&(_d)->field); \ + _i = downgrade_entry_next_c(_i)) + +static int bch2_sb_downgrade_validate(struct bch_sb *sb, struct bch_sb_field *f, + struct printbuf *err) +{ + struct bch_sb_field_downgrade *e = field_to_type(f, downgrade); + + for_each_downgrade_entry(e, i) { + if (BCH_VERSION_MAJOR(le16_to_cpu(i->version)) != + BCH_VERSION_MAJOR(le16_to_cpu(sb->version))) { + prt_printf(err, "downgrade entry with mismatched major version (%u != %u)", + BCH_VERSION_MAJOR(le16_to_cpu(i->version)), + BCH_VERSION_MAJOR(le16_to_cpu(sb->version))); + return -BCH_ERR_invalid_sb_downgrade; + } + } + + return 0; +} + +static void bch2_sb_downgrade_to_text(struct printbuf *out, struct bch_sb *sb, + struct bch_sb_field *f) +{ + struct bch_sb_field_downgrade *e = field_to_type(f, downgrade); + + if (out->nr_tabstops <= 1) + printbuf_tabstop_push(out, 16); + + for_each_downgrade_entry(e, i) { + prt_str(out, "version:"); + prt_tab(out); + bch2_version_to_text(out, le16_to_cpu(i->version)); + prt_newline(out); + + prt_str(out, "recovery passes:"); + prt_tab(out); + prt_bitflags(out, bch2_recovery_passes, + bch2_recovery_passes_from_stable(le64_to_cpu(i->recovery_passes[0]))); + prt_newline(out); + + prt_str(out, "errors:"); + prt_tab(out); + bool first = true; + for (unsigned j = 0; j < le16_to_cpu(i->nr_errors); j++) { + if (!first) + prt_char(out, ','); + first = false; + unsigned e = le16_to_cpu(i->errors[j]); + prt_str(out, e < BCH_SB_ERR_MAX ? bch2_sb_error_strs[e] : "(unknown)"); + } + prt_newline(out); + } +} + +const struct bch_sb_field_ops bch_sb_field_ops_downgrade = { + .validate = bch2_sb_downgrade_validate, + .to_text = bch2_sb_downgrade_to_text, +}; + +int bch2_sb_downgrade_update(struct bch_fs *c) +{ + darray_char table = {}; + int ret = 0; + + for (const struct downgrade_entry *src = downgrade_table; + src < downgrade_table + ARRAY_SIZE(downgrade_table); + src++) { + if (BCH_VERSION_MAJOR(src->version) != BCH_VERSION_MAJOR(le16_to_cpu(c->disk_sb.sb->version))) + continue; + + struct bch_sb_field_downgrade_entry *dst; + unsigned bytes = sizeof(*dst) + sizeof(dst->errors[0]) * src->nr_errors; + + ret = darray_make_room(&table, bytes); + if (ret) + goto out; + + dst = (void *) &darray_top(table); + dst->version = cpu_to_le16(src->version); + dst->recovery_passes[0] = cpu_to_le64(src->recovery_passes); + dst->recovery_passes[1] = 0; + dst->nr_errors = cpu_to_le16(src->nr_errors); + for (unsigned i = 0; i < src->nr_errors; i++) + dst->errors[i] = cpu_to_le16(src->errors[i]); + + table.nr += bytes; + } + + struct bch_sb_field_downgrade *d = bch2_sb_field_get(c->disk_sb.sb, downgrade); + + unsigned sb_u64s = DIV_ROUND_UP(sizeof(*d) + table.nr, sizeof(u64)); + + if (d && le32_to_cpu(d->field.u64s) > sb_u64s) + goto out; + + d = bch2_sb_field_resize(&c->disk_sb, downgrade, sb_u64s); + if (!d) { + ret = -BCH_ERR_ENOSPC_sb_downgrade; + goto out; + } + + memcpy(d->entries, table.data, table.nr); + memset_u64s_tail(d->entries, 0, table.nr); +out: + darray_exit(&table); + return ret; +} + +void bch2_sb_set_downgrade(struct bch_fs *c, unsigned new_minor, unsigned old_minor) +{ + struct bch_sb_field_downgrade *d = bch2_sb_field_get(c->disk_sb.sb, downgrade); + if (!d) + return; + + struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext); + + for_each_downgrade_entry(d, i) { + unsigned minor = BCH_VERSION_MINOR(le16_to_cpu(i->version)); + if (new_minor < minor && minor <= old_minor) { + ext->recovery_passes_required[0] |= i->recovery_passes[0]; + ext->recovery_passes_required[1] |= i->recovery_passes[1]; + + for (unsigned j = 0; j < le16_to_cpu(i->nr_errors); j++) { + unsigned e = le16_to_cpu(i->errors[j]); + if (e < BCH_SB_ERR_MAX) + __set_bit(e, c->sb.errors_silent); + if (e < sizeof(ext->errors_silent) * 8) + ext->errors_silent[e / 64] |= cpu_to_le64(BIT_ULL(e % 64)); + } + } + } +} diff --git a/fs/bcachefs/sb-downgrade.h b/fs/bcachefs/sb-downgrade.h new file mode 100644 index 000000000000..bc48fd2ca70e --- /dev/null +++ b/fs/bcachefs/sb-downgrade.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _BCACHEFS_SB_DOWNGRADE_H +#define _BCACHEFS_SB_DOWNGRADE_H + +extern const struct bch_sb_field_ops bch_sb_field_ops_downgrade; + +int bch2_sb_downgrade_update(struct bch_fs *); +void bch2_sb_set_downgrade(struct bch_fs *, unsigned, unsigned); + +#endif /* _BCACHEFS_SB_DOWNGRADE_H */ diff --git a/fs/bcachefs/sb-errors.c b/fs/bcachefs/sb-errors.c index f0930ab7f036..5f5bcae391fb 100644 --- a/fs/bcachefs/sb-errors.c +++ b/fs/bcachefs/sb-errors.c @@ -4,7 +4,7 @@ #include "sb-errors.h" #include "super-io.h" -static const char * const bch2_sb_error_strs[] = { +const char * const bch2_sb_error_strs[] = { #define x(t, n, ...) [n] = #t, BCH_SB_ERRS() NULL @@ -20,9 +20,7 @@ static void bch2_sb_error_id_to_text(struct printbuf *out, enum bch_sb_error_id static inline unsigned bch2_sb_field_errors_nr_entries(struct bch_sb_field_errors *e) { - return e - ? (bch2_sb_field_bytes(&e->field) - sizeof(*e)) / sizeof(e->entries[0]) - : 0; + return bch2_sb_field_nr_entries(e); } static inline unsigned bch2_sb_field_errors_u64s(unsigned nr) diff --git a/fs/bcachefs/sb-errors.h b/fs/bcachefs/sb-errors.h index 5a09a53966be..8889001e7db4 100644 --- a/fs/bcachefs/sb-errors.h +++ b/fs/bcachefs/sb-errors.h @@ -4,258 +4,7 @@ #include "sb-errors_types.h" -#define BCH_SB_ERRS() \ - x(clean_but_journal_not_empty, 0) \ - x(dirty_but_no_journal_entries, 1) \ - x(dirty_but_no_journal_entries_post_drop_nonflushes, 2) \ - x(sb_clean_journal_seq_mismatch, 3) \ - x(sb_clean_btree_root_mismatch, 4) \ - x(sb_clean_missing, 5) \ - x(jset_unsupported_version, 6) \ - x(jset_unknown_csum, 7) \ - x(jset_last_seq_newer_than_seq, 8) \ - x(jset_past_bucket_end, 9) \ - x(jset_seq_blacklisted, 10) \ - x(journal_entries_missing, 11) \ - x(journal_entry_replicas_not_marked, 12) \ - x(journal_entry_past_jset_end, 13) \ - x(journal_entry_replicas_data_mismatch, 14) \ - x(journal_entry_bkey_u64s_0, 15) \ - x(journal_entry_bkey_past_end, 16) \ - x(journal_entry_bkey_bad_format, 17) \ - x(journal_entry_bkey_invalid, 18) \ - x(journal_entry_btree_root_bad_size, 19) \ - x(journal_entry_blacklist_bad_size, 20) \ - x(journal_entry_blacklist_v2_bad_size, 21) \ - x(journal_entry_blacklist_v2_start_past_end, 22) \ - x(journal_entry_usage_bad_size, 23) \ - x(journal_entry_data_usage_bad_size, 24) \ - x(journal_entry_clock_bad_size, 25) \ - x(journal_entry_clock_bad_rw, 26) \ - x(journal_entry_dev_usage_bad_size, 27) \ - x(journal_entry_dev_usage_bad_dev, 28) \ - x(journal_entry_dev_usage_bad_pad, 29) \ - x(btree_node_unreadable, 30) \ - x(btree_node_fault_injected, 31) \ - x(btree_node_bad_magic, 32) \ - x(btree_node_bad_seq, 33) \ - x(btree_node_unsupported_version, 34) \ - x(btree_node_bset_older_than_sb_min, 35) \ - x(btree_node_bset_newer_than_sb, 36) \ - x(btree_node_data_missing, 37) \ - x(btree_node_bset_after_end, 38) \ - x(btree_node_replicas_sectors_written_mismatch, 39) \ - x(btree_node_replicas_data_mismatch, 40) \ - x(bset_unknown_csum, 41) \ - x(bset_bad_csum, 42) \ - x(bset_past_end_of_btree_node, 43) \ - x(bset_wrong_sector_offset, 44) \ - x(bset_empty, 45) \ - x(bset_bad_seq, 46) \ - x(bset_blacklisted_journal_seq, 47) \ - x(first_bset_blacklisted_journal_seq, 48) \ - x(btree_node_bad_btree, 49) \ - x(btree_node_bad_level, 50) \ - x(btree_node_bad_min_key, 51) \ - x(btree_node_bad_max_key, 52) \ - x(btree_node_bad_format, 53) \ - x(btree_node_bkey_past_bset_end, 54) \ - x(btree_node_bkey_bad_format, 55) \ - x(btree_node_bad_bkey, 56) \ - x(btree_node_bkey_out_of_order, 57) \ - x(btree_root_bkey_invalid, 58) \ - x(btree_root_read_error, 59) \ - x(btree_root_bad_min_key, 50) \ - x(btree_root_bad_max_key, 61) \ - x(btree_node_read_error, 62) \ - x(btree_node_topology_bad_min_key, 63) \ - x(btree_node_topology_bad_max_key, 64) \ - x(btree_node_topology_overwritten_by_prev_node, 65) \ - x(btree_node_topology_overwritten_by_next_node, 66) \ - x(btree_node_topology_interior_node_empty, 67) \ - x(fs_usage_hidden_wrong, 68) \ - x(fs_usage_btree_wrong, 69) \ - x(fs_usage_data_wrong, 70) \ - x(fs_usage_cached_wrong, 71) \ - x(fs_usage_reserved_wrong, 72) \ - x(fs_usage_persistent_reserved_wrong, 73) \ - x(fs_usage_nr_inodes_wrong, 74) \ - x(fs_usage_replicas_wrong, 75) \ - x(dev_usage_buckets_wrong, 76) \ - x(dev_usage_sectors_wrong, 77) \ - x(dev_usage_fragmented_wrong, 78) \ - x(dev_usage_buckets_ec_wrong, 79) \ - x(bkey_version_in_future, 80) \ - x(bkey_u64s_too_small, 81) \ - x(bkey_invalid_type_for_btree, 82) \ - x(bkey_extent_size_zero, 83) \ - x(bkey_extent_size_greater_than_offset, 84) \ - x(bkey_size_nonzero, 85) \ - x(bkey_snapshot_nonzero, 86) \ - x(bkey_snapshot_zero, 87) \ - x(bkey_at_pos_max, 88) \ - x(bkey_before_start_of_btree_node, 89) \ - x(bkey_after_end_of_btree_node, 90) \ - x(bkey_val_size_nonzero, 91) \ - x(bkey_val_size_too_small, 92) \ - x(alloc_v1_val_size_bad, 93) \ - x(alloc_v2_unpack_error, 94) \ - x(alloc_v3_unpack_error, 95) \ - x(alloc_v4_val_size_bad, 96) \ - x(alloc_v4_backpointers_start_bad, 97) \ - x(alloc_key_data_type_bad, 98) \ - x(alloc_key_empty_but_have_data, 99) \ - x(alloc_key_dirty_sectors_0, 100) \ - x(alloc_key_data_type_inconsistency, 101) \ - x(alloc_key_to_missing_dev_bucket, 102) \ - x(alloc_key_cached_inconsistency, 103) \ - x(alloc_key_cached_but_read_time_zero, 104) \ - x(alloc_key_to_missing_lru_entry, 105) \ - x(alloc_key_data_type_wrong, 106) \ - x(alloc_key_gen_wrong, 107) \ - x(alloc_key_dirty_sectors_wrong, 108) \ - x(alloc_key_cached_sectors_wrong, 109) \ - x(alloc_key_stripe_wrong, 110) \ - x(alloc_key_stripe_redundancy_wrong, 111) \ - x(bucket_sector_count_overflow, 112) \ - x(bucket_metadata_type_mismatch, 113) \ - x(need_discard_key_wrong, 114) \ - x(freespace_key_wrong, 115) \ - x(freespace_hole_missing, 116) \ - x(bucket_gens_val_size_bad, 117) \ - x(bucket_gens_key_wrong, 118) \ - x(bucket_gens_hole_wrong, 119) \ - x(bucket_gens_to_invalid_dev, 120) \ - x(bucket_gens_to_invalid_buckets, 121) \ - x(bucket_gens_nonzero_for_invalid_buckets, 122) \ - x(need_discard_freespace_key_to_invalid_dev_bucket, 123) \ - x(need_discard_freespace_key_bad, 124) \ - x(backpointer_pos_wrong, 125) \ - x(backpointer_to_missing_device, 126) \ - x(backpointer_to_missing_alloc, 127) \ - x(backpointer_to_missing_ptr, 128) \ - x(lru_entry_at_time_0, 129) \ - x(lru_entry_to_invalid_bucket, 130) \ - x(lru_entry_bad, 131) \ - x(btree_ptr_val_too_big, 132) \ - x(btree_ptr_v2_val_too_big, 133) \ - x(btree_ptr_has_non_ptr, 134) \ - x(extent_ptrs_invalid_entry, 135) \ - x(extent_ptrs_no_ptrs, 136) \ - x(extent_ptrs_too_many_ptrs, 137) \ - x(extent_ptrs_redundant_crc, 138) \ - x(extent_ptrs_redundant_stripe, 139) \ - x(extent_ptrs_unwritten, 140) \ - x(extent_ptrs_written_and_unwritten, 141) \ - x(ptr_to_invalid_device, 142) \ - x(ptr_to_duplicate_device, 143) \ - x(ptr_after_last_bucket, 144) \ - x(ptr_before_first_bucket, 145) \ - x(ptr_spans_multiple_buckets, 146) \ - x(ptr_to_missing_backpointer, 147) \ - x(ptr_to_missing_alloc_key, 148) \ - x(ptr_to_missing_replicas_entry, 149) \ - x(ptr_to_missing_stripe, 150) \ - x(ptr_to_incorrect_stripe, 151) \ - x(ptr_gen_newer_than_bucket_gen, 152) \ - x(ptr_too_stale, 153) \ - x(stale_dirty_ptr, 154) \ - x(ptr_bucket_data_type_mismatch, 155) \ - x(ptr_cached_and_erasure_coded, 156) \ - x(ptr_crc_uncompressed_size_too_small, 157) \ - x(ptr_crc_csum_type_unknown, 158) \ - x(ptr_crc_compression_type_unknown, 159) \ - x(ptr_crc_redundant, 160) \ - x(ptr_crc_uncompressed_size_too_big, 161) \ - x(ptr_crc_nonce_mismatch, 162) \ - x(ptr_stripe_redundant, 163) \ - x(reservation_key_nr_replicas_invalid, 164) \ - x(reflink_v_refcount_wrong, 165) \ - x(reflink_p_to_missing_reflink_v, 166) \ - x(stripe_pos_bad, 167) \ - x(stripe_val_size_bad, 168) \ - x(stripe_sector_count_wrong, 169) \ - x(snapshot_tree_pos_bad, 170) \ - x(snapshot_tree_to_missing_snapshot, 171) \ - x(snapshot_tree_to_missing_subvol, 172) \ - x(snapshot_tree_to_wrong_subvol, 173) \ - x(snapshot_tree_to_snapshot_subvol, 174) \ - x(snapshot_pos_bad, 175) \ - x(snapshot_parent_bad, 176) \ - x(snapshot_children_not_normalized, 177) \ - x(snapshot_child_duplicate, 178) \ - x(snapshot_child_bad, 179) \ - x(snapshot_skiplist_not_normalized, 180) \ - x(snapshot_skiplist_bad, 181) \ - x(snapshot_should_not_have_subvol, 182) \ - x(snapshot_to_bad_snapshot_tree, 183) \ - x(snapshot_bad_depth, 184) \ - x(snapshot_bad_skiplist, 185) \ - x(subvol_pos_bad, 186) \ - x(subvol_not_master_and_not_snapshot, 187) \ - x(subvol_to_missing_root, 188) \ - x(subvol_root_wrong_bi_subvol, 189) \ - x(bkey_in_missing_snapshot, 190) \ - x(inode_pos_inode_nonzero, 191) \ - x(inode_pos_blockdev_range, 192) \ - x(inode_unpack_error, 193) \ - x(inode_str_hash_invalid, 194) \ - x(inode_v3_fields_start_bad, 195) \ - x(inode_snapshot_mismatch, 196) \ - x(inode_unlinked_but_clean, 197) \ - x(inode_unlinked_but_nlink_nonzero, 198) \ - x(inode_checksum_type_invalid, 199) \ - x(inode_compression_type_invalid, 200) \ - x(inode_subvol_root_but_not_dir, 201) \ - x(inode_i_size_dirty_but_clean, 202) \ - x(inode_i_sectors_dirty_but_clean, 203) \ - x(inode_i_sectors_wrong, 204) \ - x(inode_dir_wrong_nlink, 205) \ - x(inode_dir_multiple_links, 206) \ - x(inode_multiple_links_but_nlink_0, 207) \ - x(inode_wrong_backpointer, 208) \ - x(inode_wrong_nlink, 209) \ - x(inode_unreachable, 210) \ - x(deleted_inode_but_clean, 211) \ - x(deleted_inode_missing, 212) \ - x(deleted_inode_is_dir, 213) \ - x(deleted_inode_not_unlinked, 214) \ - x(extent_overlapping, 215) \ - x(extent_in_missing_inode, 216) \ - x(extent_in_non_reg_inode, 217) \ - x(extent_past_end_of_inode, 218) \ - x(dirent_empty_name, 219) \ - x(dirent_val_too_big, 220) \ - x(dirent_name_too_long, 221) \ - x(dirent_name_embedded_nul, 222) \ - x(dirent_name_dot_or_dotdot, 223) \ - x(dirent_name_has_slash, 224) \ - x(dirent_d_type_wrong, 225) \ - x(dirent_d_parent_subvol_wrong, 226) \ - x(dirent_in_missing_dir_inode, 227) \ - x(dirent_in_non_dir_inode, 228) \ - x(dirent_to_missing_inode, 229) \ - x(dirent_to_missing_subvol, 230) \ - x(dirent_to_itself, 231) \ - x(quota_type_invalid, 232) \ - x(xattr_val_size_too_small, 233) \ - x(xattr_val_size_too_big, 234) \ - x(xattr_invalid_type, 235) \ - x(xattr_name_invalid_chars, 236) \ - x(xattr_in_missing_inode, 237) \ - x(root_subvol_missing, 238) \ - x(root_dir_missing, 239) \ - x(root_inode_not_dir, 240) \ - x(dir_loop, 241) \ - x(hash_table_key_duplicate, 242) \ - x(hash_table_key_wrong_offset, 243) - -enum bch_sb_error_id { -#define x(t, n) BCH_FSCK_ERR_##t = n, - BCH_SB_ERRS() -#undef x - BCH_SB_ERR_MAX -}; +extern const char * const bch2_sb_error_strs[]; extern const struct bch_sb_field_ops bch_sb_field_ops_errors; diff --git a/fs/bcachefs/sb-errors_types.h b/fs/bcachefs/sb-errors_types.h index b1c099843a39..3504c2d09c29 100644 --- a/fs/bcachefs/sb-errors_types.h +++ b/fs/bcachefs/sb-errors_types.h @@ -4,6 +4,259 @@ #include "darray.h" +#define BCH_SB_ERRS() \ + x(clean_but_journal_not_empty, 0) \ + x(dirty_but_no_journal_entries, 1) \ + x(dirty_but_no_journal_entries_post_drop_nonflushes, 2) \ + x(sb_clean_journal_seq_mismatch, 3) \ + x(sb_clean_btree_root_mismatch, 4) \ + x(sb_clean_missing, 5) \ + x(jset_unsupported_version, 6) \ + x(jset_unknown_csum, 7) \ + x(jset_last_seq_newer_than_seq, 8) \ + x(jset_past_bucket_end, 9) \ + x(jset_seq_blacklisted, 10) \ + x(journal_entries_missing, 11) \ + x(journal_entry_replicas_not_marked, 12) \ + x(journal_entry_past_jset_end, 13) \ + x(journal_entry_replicas_data_mismatch, 14) \ + x(journal_entry_bkey_u64s_0, 15) \ + x(journal_entry_bkey_past_end, 16) \ + x(journal_entry_bkey_bad_format, 17) \ + x(journal_entry_bkey_invalid, 18) \ + x(journal_entry_btree_root_bad_size, 19) \ + x(journal_entry_blacklist_bad_size, 20) \ + x(journal_entry_blacklist_v2_bad_size, 21) \ + x(journal_entry_blacklist_v2_start_past_end, 22) \ + x(journal_entry_usage_bad_size, 23) \ + x(journal_entry_data_usage_bad_size, 24) \ + x(journal_entry_clock_bad_size, 25) \ + x(journal_entry_clock_bad_rw, 26) \ + x(journal_entry_dev_usage_bad_size, 27) \ + x(journal_entry_dev_usage_bad_dev, 28) \ + x(journal_entry_dev_usage_bad_pad, 29) \ + x(btree_node_unreadable, 30) \ + x(btree_node_fault_injected, 31) \ + x(btree_node_bad_magic, 32) \ + x(btree_node_bad_seq, 33) \ + x(btree_node_unsupported_version, 34) \ + x(btree_node_bset_older_than_sb_min, 35) \ + x(btree_node_bset_newer_than_sb, 36) \ + x(btree_node_data_missing, 37) \ + x(btree_node_bset_after_end, 38) \ + x(btree_node_replicas_sectors_written_mismatch, 39) \ + x(btree_node_replicas_data_mismatch, 40) \ + x(bset_unknown_csum, 41) \ + x(bset_bad_csum, 42) \ + x(bset_past_end_of_btree_node, 43) \ + x(bset_wrong_sector_offset, 44) \ + x(bset_empty, 45) \ + x(bset_bad_seq, 46) \ + x(bset_blacklisted_journal_seq, 47) \ + x(first_bset_blacklisted_journal_seq, 48) \ + x(btree_node_bad_btree, 49) \ + x(btree_node_bad_level, 50) \ + x(btree_node_bad_min_key, 51) \ + x(btree_node_bad_max_key, 52) \ + x(btree_node_bad_format, 53) \ + x(btree_node_bkey_past_bset_end, 54) \ + x(btree_node_bkey_bad_format, 55) \ + x(btree_node_bad_bkey, 56) \ + x(btree_node_bkey_out_of_order, 57) \ + x(btree_root_bkey_invalid, 58) \ + x(btree_root_read_error, 59) \ + x(btree_root_bad_min_key, 60) \ + x(btree_root_bad_max_key, 61) \ + x(btree_node_read_error, 62) \ + x(btree_node_topology_bad_min_key, 63) \ + x(btree_node_topology_bad_max_key, 64) \ + x(btree_node_topology_overwritten_by_prev_node, 65) \ + x(btree_node_topology_overwritten_by_next_node, 66) \ + x(btree_node_topology_interior_node_empty, 67) \ + x(fs_usage_hidden_wrong, 68) \ + x(fs_usage_btree_wrong, 69) \ + x(fs_usage_data_wrong, 70) \ + x(fs_usage_cached_wrong, 71) \ + x(fs_usage_reserved_wrong, 72) \ + x(fs_usage_persistent_reserved_wrong, 73) \ + x(fs_usage_nr_inodes_wrong, 74) \ + x(fs_usage_replicas_wrong, 75) \ + x(dev_usage_buckets_wrong, 76) \ + x(dev_usage_sectors_wrong, 77) \ + x(dev_usage_fragmented_wrong, 78) \ + x(dev_usage_buckets_ec_wrong, 79) \ + x(bkey_version_in_future, 80) \ + x(bkey_u64s_too_small, 81) \ + x(bkey_invalid_type_for_btree, 82) \ + x(bkey_extent_size_zero, 83) \ + x(bkey_extent_size_greater_than_offset, 84) \ + x(bkey_size_nonzero, 85) \ + x(bkey_snapshot_nonzero, 86) \ + x(bkey_snapshot_zero, 87) \ + x(bkey_at_pos_max, 88) \ + x(bkey_before_start_of_btree_node, 89) \ + x(bkey_after_end_of_btree_node, 90) \ + x(bkey_val_size_nonzero, 91) \ + x(bkey_val_size_too_small, 92) \ + x(alloc_v1_val_size_bad, 93) \ + x(alloc_v2_unpack_error, 94) \ + x(alloc_v3_unpack_error, 95) \ + x(alloc_v4_val_size_bad, 96) \ + x(alloc_v4_backpointers_start_bad, 97) \ + x(alloc_key_data_type_bad, 98) \ + x(alloc_key_empty_but_have_data, 99) \ + x(alloc_key_dirty_sectors_0, 100) \ + x(alloc_key_data_type_inconsistency, 101) \ + x(alloc_key_to_missing_dev_bucket, 102) \ + x(alloc_key_cached_inconsistency, 103) \ + x(alloc_key_cached_but_read_time_zero, 104) \ + x(alloc_key_to_missing_lru_entry, 105) \ + x(alloc_key_data_type_wrong, 106) \ + x(alloc_key_gen_wrong, 107) \ + x(alloc_key_dirty_sectors_wrong, 108) \ + x(alloc_key_cached_sectors_wrong, 109) \ + x(alloc_key_stripe_wrong, 110) \ + x(alloc_key_stripe_redundancy_wrong, 111) \ + x(bucket_sector_count_overflow, 112) \ + x(bucket_metadata_type_mismatch, 113) \ + x(need_discard_key_wrong, 114) \ + x(freespace_key_wrong, 115) \ + x(freespace_hole_missing, 116) \ + x(bucket_gens_val_size_bad, 117) \ + x(bucket_gens_key_wrong, 118) \ + x(bucket_gens_hole_wrong, 119) \ + x(bucket_gens_to_invalid_dev, 120) \ + x(bucket_gens_to_invalid_buckets, 121) \ + x(bucket_gens_nonzero_for_invalid_buckets, 122) \ + x(need_discard_freespace_key_to_invalid_dev_bucket, 123) \ + x(need_discard_freespace_key_bad, 124) \ + x(backpointer_pos_wrong, 125) \ + x(backpointer_to_missing_device, 126) \ + x(backpointer_to_missing_alloc, 127) \ + x(backpointer_to_missing_ptr, 128) \ + x(lru_entry_at_time_0, 129) \ + x(lru_entry_to_invalid_bucket, 130) \ + x(lru_entry_bad, 131) \ + x(btree_ptr_val_too_big, 132) \ + x(btree_ptr_v2_val_too_big, 133) \ + x(btree_ptr_has_non_ptr, 134) \ + x(extent_ptrs_invalid_entry, 135) \ + x(extent_ptrs_no_ptrs, 136) \ + x(extent_ptrs_too_many_ptrs, 137) \ + x(extent_ptrs_redundant_crc, 138) \ + x(extent_ptrs_redundant_stripe, 139) \ + x(extent_ptrs_unwritten, 140) \ + x(extent_ptrs_written_and_unwritten, 141) \ + x(ptr_to_invalid_device, 142) \ + x(ptr_to_duplicate_device, 143) \ + x(ptr_after_last_bucket, 144) \ + x(ptr_before_first_bucket, 145) \ + x(ptr_spans_multiple_buckets, 146) \ + x(ptr_to_missing_backpointer, 147) \ + x(ptr_to_missing_alloc_key, 148) \ + x(ptr_to_missing_replicas_entry, 149) \ + x(ptr_to_missing_stripe, 150) \ + x(ptr_to_incorrect_stripe, 151) \ + x(ptr_gen_newer_than_bucket_gen, 152) \ + x(ptr_too_stale, 153) \ + x(stale_dirty_ptr, 154) \ + x(ptr_bucket_data_type_mismatch, 155) \ + x(ptr_cached_and_erasure_coded, 156) \ + x(ptr_crc_uncompressed_size_too_small, 157) \ + x(ptr_crc_csum_type_unknown, 158) \ + x(ptr_crc_compression_type_unknown, 159) \ + x(ptr_crc_redundant, 160) \ + x(ptr_crc_uncompressed_size_too_big, 161) \ + x(ptr_crc_nonce_mismatch, 162) \ + x(ptr_stripe_redundant, 163) \ + x(reservation_key_nr_replicas_invalid, 164) \ + x(reflink_v_refcount_wrong, 165) \ + x(reflink_p_to_missing_reflink_v, 166) \ + x(stripe_pos_bad, 167) \ + x(stripe_val_size_bad, 168) \ + x(stripe_sector_count_wrong, 169) \ + x(snapshot_tree_pos_bad, 170) \ + x(snapshot_tree_to_missing_snapshot, 171) \ + x(snapshot_tree_to_missing_subvol, 172) \ + x(snapshot_tree_to_wrong_subvol, 173) \ + x(snapshot_tree_to_snapshot_subvol, 174) \ + x(snapshot_pos_bad, 175) \ + x(snapshot_parent_bad, 176) \ + x(snapshot_children_not_normalized, 177) \ + x(snapshot_child_duplicate, 178) \ + x(snapshot_child_bad, 179) \ + x(snapshot_skiplist_not_normalized, 180) \ + x(snapshot_skiplist_bad, 181) \ + x(snapshot_should_not_have_subvol, 182) \ + x(snapshot_to_bad_snapshot_tree, 183) \ + x(snapshot_bad_depth, 184) \ + x(snapshot_bad_skiplist, 185) \ + x(subvol_pos_bad, 186) \ + x(subvol_not_master_and_not_snapshot, 187) \ + x(subvol_to_missing_root, 188) \ + x(subvol_root_wrong_bi_subvol, 189) \ + x(bkey_in_missing_snapshot, 190) \ + x(inode_pos_inode_nonzero, 191) \ + x(inode_pos_blockdev_range, 192) \ + x(inode_unpack_error, 193) \ + x(inode_str_hash_invalid, 194) \ + x(inode_v3_fields_start_bad, 195) \ + x(inode_snapshot_mismatch, 196) \ + x(inode_unlinked_but_clean, 197) \ + x(inode_unlinked_but_nlink_nonzero, 198) \ + x(inode_checksum_type_invalid, 199) \ + x(inode_compression_type_invalid, 200) \ + x(inode_subvol_root_but_not_dir, 201) \ + x(inode_i_size_dirty_but_clean, 202) \ + x(inode_i_sectors_dirty_but_clean, 203) \ + x(inode_i_sectors_wrong, 204) \ + x(inode_dir_wrong_nlink, 205) \ + x(inode_dir_multiple_links, 206) \ + x(inode_multiple_links_but_nlink_0, 207) \ + x(inode_wrong_backpointer, 208) \ + x(inode_wrong_nlink, 209) \ + x(inode_unreachable, 210) \ + x(deleted_inode_but_clean, 211) \ + x(deleted_inode_missing, 212) \ + x(deleted_inode_is_dir, 213) \ + x(deleted_inode_not_unlinked, 214) \ + x(extent_overlapping, 215) \ + x(extent_in_missing_inode, 216) \ + x(extent_in_non_reg_inode, 217) \ + x(extent_past_end_of_inode, 218) \ + x(dirent_empty_name, 219) \ + x(dirent_val_too_big, 220) \ + x(dirent_name_too_long, 221) \ + x(dirent_name_embedded_nul, 222) \ + x(dirent_name_dot_or_dotdot, 223) \ + x(dirent_name_has_slash, 224) \ + x(dirent_d_type_wrong, 225) \ + x(dirent_d_parent_subvol_wrong, 226) \ + x(dirent_in_missing_dir_inode, 227) \ + x(dirent_in_non_dir_inode, 228) \ + x(dirent_to_missing_inode, 229) \ + x(dirent_to_missing_subvol, 230) \ + x(dirent_to_itself, 231) \ + x(quota_type_invalid, 232) \ + x(xattr_val_size_too_small, 233) \ + x(xattr_val_size_too_big, 234) \ + x(xattr_invalid_type, 235) \ + x(xattr_name_invalid_chars, 236) \ + x(xattr_in_missing_inode, 237) \ + x(root_subvol_missing, 238) \ + x(root_dir_missing, 239) \ + x(root_inode_not_dir, 240) \ + x(dir_loop, 241) \ + x(hash_table_key_duplicate, 242) \ + x(hash_table_key_wrong_offset, 243) + +enum bch_sb_error_id { +#define x(t, n) BCH_FSCK_ERR_##t = n, + BCH_SB_ERRS() +#undef x + BCH_SB_ERR_MAX +}; + struct bch_sb_error_entry_cpu { u64 id:16, nr:48; diff --git a/fs/bcachefs/subvolume.c b/fs/bcachefs/subvolume.c index fccd25aa3242..22b34a8e4d6e 100644 --- a/fs/bcachefs/subvolume.c +++ b/fs/bcachefs/subvolume.c @@ -146,6 +146,24 @@ int bch2_subvolume_get(struct btree_trans *trans, unsigned subvol, return bch2_subvolume_get_inlined(trans, subvol, inconsistent_if_not_found, iter_flags, s); } +int bch2_subvol_is_ro_trans(struct btree_trans *trans, u32 subvol) +{ + struct bch_subvolume s; + int ret = bch2_subvolume_get_inlined(trans, subvol, true, 0, &s); + if (ret) + return ret; + + if (BCH_SUBVOLUME_RO(&s)) + return -EROFS; + return 0; +} + +int bch2_subvol_is_ro(struct bch_fs *c, u32 subvol) +{ + return bch2_trans_do(c, NULL, NULL, 0, + bch2_subvol_is_ro_trans(trans, subvol)); +} + int bch2_snapshot_get_subvol(struct btree_trans *trans, u32 snapshot, struct bch_subvolume *subvol) { diff --git a/fs/bcachefs/subvolume.h b/fs/bcachefs/subvolume.h index a1003d30ab0a..a6f56f66e27c 100644 --- a/fs/bcachefs/subvolume.h +++ b/fs/bcachefs/subvolume.h @@ -23,6 +23,9 @@ int bch2_subvolume_get(struct btree_trans *, unsigned, bool, int, struct bch_subvolume *); int bch2_subvolume_get_snapshot(struct btree_trans *, u32, u32 *); +int bch2_subvol_is_ro_trans(struct btree_trans *, u32); +int bch2_subvol_is_ro(struct bch_fs *, u32); + int bch2_delete_dead_snapshots(struct bch_fs *); void bch2_delete_dead_snapshots_async(struct bch_fs *); diff --git a/fs/bcachefs/super-io.c b/fs/bcachefs/super-io.c index f3e12f7979d5..78013deda9df 100644 --- a/fs/bcachefs/super-io.c +++ b/fs/bcachefs/super-io.c @@ -13,6 +13,7 @@ #include "replicas.h" #include "quota.h" #include "sb-clean.h" +#include "sb-downgrade.h" #include "sb-errors.h" #include "sb-members.h" #include "super-io.h" @@ -163,8 +164,8 @@ void bch2_sb_field_delete(struct bch_sb_handle *sb, void bch2_free_super(struct bch_sb_handle *sb) { kfree(sb->bio); - if (!IS_ERR_OR_NULL(sb->bdev)) - blkdev_put(sb->bdev, sb->holder); + if (!IS_ERR_OR_NULL(sb->bdev_handle)) + bdev_release(sb->bdev_handle); kfree(sb->holder); kfree(sb->sb_name); @@ -264,6 +265,17 @@ struct bch_sb_field *bch2_sb_field_resize_id(struct bch_sb_handle *sb, return f; } +struct bch_sb_field *bch2_sb_field_get_minsize_id(struct bch_sb_handle *sb, + enum bch_sb_field_type type, + unsigned u64s) +{ + struct bch_sb_field *f = bch2_sb_field_get_id(sb->sb, type); + + if (!f || le32_to_cpu(f->u64s) < u64s) + f = bch2_sb_field_resize_id(sb, type, u64s); + return f; +} + /* Superblock validate: */ static int validate_sb_layout(struct bch_sb_layout *layout, struct printbuf *out) @@ -484,6 +496,21 @@ static int bch2_sb_validate(struct bch_sb_handle *disk_sb, struct printbuf *out, /* device open: */ +static unsigned long le_ulong_to_cpu(unsigned long v) +{ + return sizeof(unsigned long) == 8 + ? le64_to_cpu(v) + : le32_to_cpu(v); +} + +static void le_bitvector_to_cpu(unsigned long *dst, unsigned long *src, unsigned nr) +{ + BUG_ON(nr & (BITS_PER_TYPE(long) - 1)); + + for (unsigned i = 0; i < BITS_TO_LONGS(nr); i++) + dst[i] = le_ulong_to_cpu(src[i]); +} + static void bch2_sb_update(struct bch_fs *c) { struct bch_sb *src = c->disk_sb.sb; @@ -512,8 +539,15 @@ static void bch2_sb_update(struct bch_fs *c) c->sb.features = le64_to_cpu(src->features[0]); c->sb.compat = le64_to_cpu(src->compat[0]); + memset(c->sb.errors_silent, 0, sizeof(c->sb.errors_silent)); + + struct bch_sb_field_ext *ext = bch2_sb_field_get(src, ext); + if (ext) + le_bitvector_to_cpu(c->sb.errors_silent, (void *) ext->errors_silent, + sizeof(c->sb.errors_silent) * 8); + for_each_member_device(ca, c, i) { - struct bch_member m = bch2_sb_member_get(src, i); + struct bch_member m = bch2_sb_member_get(src, ca->dev_idx); ca->mi = bch2_mi_to_cpu(&m); } } @@ -691,21 +725,22 @@ retry: if (!opt_get(*opts, nochanges)) sb->mode |= BLK_OPEN_WRITE; - sb->bdev = blkdev_get_by_path(path, sb->mode, sb->holder, &bch2_sb_handle_bdev_ops); - if (IS_ERR(sb->bdev) && - PTR_ERR(sb->bdev) == -EACCES && + sb->bdev_handle = bdev_open_by_path(path, sb->mode, sb->holder, &bch2_sb_handle_bdev_ops); + if (IS_ERR(sb->bdev_handle) && + PTR_ERR(sb->bdev_handle) == -EACCES && opt_get(*opts, read_only)) { sb->mode &= ~BLK_OPEN_WRITE; - sb->bdev = blkdev_get_by_path(path, sb->mode, sb->holder, &bch2_sb_handle_bdev_ops); - if (!IS_ERR(sb->bdev)) + sb->bdev_handle = bdev_open_by_path(path, sb->mode, sb->holder, &bch2_sb_handle_bdev_ops); + if (!IS_ERR(sb->bdev_handle)) opt_set(*opts, nochanges, true); } - if (IS_ERR(sb->bdev)) { - ret = PTR_ERR(sb->bdev); + if (IS_ERR(sb->bdev_handle)) { + ret = PTR_ERR(sb->bdev_handle); goto out; } + sb->bdev = sb->bdev_handle->bdev; ret = bch2_sb_realloc(sb, 0); if (ret) { @@ -906,6 +941,7 @@ int bch2_write_super(struct bch_fs *c) bch2_sb_members_from_cpu(c); bch2_sb_members_cpy_v2_v1(&c->disk_sb); bch2_sb_errors_from_cpu(c); + bch2_sb_downgrade_update(c); for_each_online_member(ca, c, i) bch2_sb_from_fs(c, ca); @@ -1029,8 +1065,10 @@ void __bch2_check_set_feature(struct bch_fs *c, unsigned feat) } /* Downgrade if superblock is at a higher version than currently supported: */ -void bch2_sb_maybe_downgrade(struct bch_fs *c) +bool bch2_check_version_downgrade(struct bch_fs *c) { + bool ret = bcachefs_metadata_version_current < c->sb.version; + lockdep_assert_held(&c->sb_lock); /* @@ -1044,16 +1082,61 @@ void bch2_sb_maybe_downgrade(struct bch_fs *c) if (c->sb.version_min > bcachefs_metadata_version_current) c->disk_sb.sb->version_min = cpu_to_le16(bcachefs_metadata_version_current); c->disk_sb.sb->compat[0] &= cpu_to_le64((1ULL << BCH_COMPAT_NR) - 1); + return ret; } void bch2_sb_upgrade(struct bch_fs *c, unsigned new_version) { lockdep_assert_held(&c->sb_lock); + if (BCH_VERSION_MAJOR(new_version) > + BCH_VERSION_MAJOR(le16_to_cpu(c->disk_sb.sb->version))) + bch2_sb_field_resize(&c->disk_sb, downgrade, 0); + c->disk_sb.sb->version = cpu_to_le16(new_version); c->disk_sb.sb->features[0] |= cpu_to_le64(BCH_SB_FEATURES_ALL); } +static int bch2_sb_ext_validate(struct bch_sb *sb, struct bch_sb_field *f, + struct printbuf *err) +{ + if (vstruct_bytes(f) < 88) { + prt_printf(err, "field too small (%zu < %u)", vstruct_bytes(f), 88); + return -BCH_ERR_invalid_sb_ext; + } + + return 0; +} + +static void bch2_sb_ext_to_text(struct printbuf *out, struct bch_sb *sb, + struct bch_sb_field *f) +{ + struct bch_sb_field_ext *e = field_to_type(f, ext); + + prt_printf(out, "Recovery passes required:"); + prt_tab(out); + prt_bitflags(out, bch2_recovery_passes, + bch2_recovery_passes_from_stable(le64_to_cpu(e->recovery_passes_required[0]))); + prt_newline(out); + + unsigned long *errors_silent = kmalloc(sizeof(e->errors_silent), GFP_KERNEL); + if (errors_silent) { + le_bitvector_to_cpu(errors_silent, (void *) e->errors_silent, sizeof(e->errors_silent) * 8); + + prt_printf(out, "Errors to silently fix:"); + prt_tab(out); + prt_bitflags_vector(out, bch2_sb_error_strs, errors_silent, sizeof(e->errors_silent) * 8); + prt_newline(out); + + kfree(errors_silent); + } +} + +static const struct bch_sb_field_ops bch_sb_field_ops_ext = { + .validate = bch2_sb_ext_validate, + .to_text = bch2_sb_ext_to_text, +}; + static const struct bch_sb_field_ops *bch2_sb_field_ops[] = { #define x(f, nr) \ [BCH_SB_FIELD_##f] = &bch_sb_field_ops_##f, diff --git a/fs/bcachefs/super-io.h b/fs/bcachefs/super-io.h index f5abd102bff7..e41e5de531a0 100644 --- a/fs/bcachefs/super-io.h +++ b/fs/bcachefs/super-io.h @@ -40,6 +40,16 @@ struct bch_sb_field *bch2_sb_field_resize_id(struct bch_sb_handle *, #define bch2_sb_field_resize(_sb, _name, _u64s) \ field_to_type(bch2_sb_field_resize_id(_sb, BCH_SB_FIELD_##_name, _u64s), _name) +struct bch_sb_field *bch2_sb_field_get_minsize_id(struct bch_sb_handle *, + enum bch_sb_field_type, unsigned); +#define bch2_sb_field_get_minsize(_sb, _name, _u64s) \ + field_to_type(bch2_sb_field_get_minsize_id(_sb, BCH_SB_FIELD_##_name, _u64s), _name) + +#define bch2_sb_field_nr_entries(_f) \ + (_f ? ((bch2_sb_field_bytes(&_f->field) - sizeof(*_f)) / \ + sizeof(_f->entries[0])) \ + : 0) + void bch2_sb_field_delete(struct bch_sb_handle *, enum bch_sb_field_type); extern const char * const bch2_sb_fields[]; @@ -83,7 +93,7 @@ static inline void bch2_check_set_feature(struct bch_fs *c, unsigned feat) __bch2_check_set_feature(c, feat); } -void bch2_sb_maybe_downgrade(struct bch_fs *); +bool bch2_check_version_downgrade(struct bch_fs *); void bch2_sb_upgrade(struct bch_fs *, unsigned); void bch2_sb_field_to_text(struct printbuf *, struct bch_sb *, diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c index f63474c5c5a2..818ec467a06b 100644 --- a/fs/bcachefs/super.c +++ b/fs/bcachefs/super.c @@ -72,6 +72,12 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Kent Overstreet <kent.overstreet@gmail.com>"); MODULE_DESCRIPTION("bcachefs filesystem"); +MODULE_SOFTDEP("pre: crc32c"); +MODULE_SOFTDEP("pre: crc64"); +MODULE_SOFTDEP("pre: sha256"); +MODULE_SOFTDEP("pre: chacha20"); +MODULE_SOFTDEP("pre: poly1305"); +MODULE_SOFTDEP("pre: xxhash"); #define KTYPE(type) \ static const struct attribute_group type ## _group = { \ @@ -714,6 +720,7 @@ static struct bch_fs *bch2_fs_alloc(struct bch_sb *sb, struct bch_opts opts) bch2_fs_copygc_init(c); bch2_fs_btree_key_cache_init_early(&c->btree_key_cache); + bch2_fs_btree_iter_init_early(c); bch2_fs_btree_interior_update_init_early(c); bch2_fs_allocator_background_init(c); bch2_fs_allocator_foreground_init(c); diff --git a/fs/bcachefs/super_types.h b/fs/bcachefs/super_types.h index 9c1fd4ca2b10..b2119686e2e1 100644 --- a/fs/bcachefs/super_types.h +++ b/fs/bcachefs/super_types.h @@ -4,6 +4,7 @@ struct bch_sb_handle { struct bch_sb *sb; + struct bdev_handle *bdev_handle; struct block_device *bdev; char *sb_name; struct bio *bio; diff --git a/fs/bcachefs/sysfs.c b/fs/bcachefs/sysfs.c index ab743115f169..f3cb7115b530 100644 --- a/fs/bcachefs/sysfs.c +++ b/fs/bcachefs/sysfs.c @@ -276,8 +276,8 @@ static int bch2_compression_stats_to_text(struct printbuf *out, struct bch_fs *c if (!btree_type_has_ptrs(id)) continue; - for_each_btree_key(trans, iter, id, POS_MIN, - BTREE_ITER_ALL_SNAPSHOTS, k, ret) { + ret = for_each_btree_key2(trans, iter, id, POS_MIN, + BTREE_ITER_ALL_SNAPSHOTS, k, ({ struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); const union bch_extent_entry *entry; struct extent_ptr_decoded p; @@ -309,8 +309,8 @@ static int bch2_compression_stats_to_text(struct printbuf *out, struct bch_fs *c nr_uncompressed_extents++; else if (compressed) nr_compressed_extents++; - } - bch2_trans_iter_exit(trans, &iter); + 0; + })); } bch2_trans_put(trans); diff --git a/fs/bcachefs/util.h b/fs/bcachefs/util.h index 2984b57b2958..b701f7fe0784 100644 --- a/fs/bcachefs/util.h +++ b/fs/bcachefs/util.h @@ -243,6 +243,7 @@ do { \ #define prt_units_s64(...) bch2_prt_units_s64(__VA_ARGS__) #define prt_string_option(...) bch2_prt_string_option(__VA_ARGS__) #define prt_bitflags(...) bch2_prt_bitflags(__VA_ARGS__) +#define prt_bitflags_vector(...) bch2_prt_bitflags_vector(__VA_ARGS__) void bch2_pr_time_units(struct printbuf *, u64); void bch2_prt_datetime(struct printbuf *, time64_t); diff --git a/fs/bcachefs/xattr.c b/fs/bcachefs/xattr.c index 79d982674c18..5a1858fb9879 100644 --- a/fs/bcachefs/xattr.c +++ b/fs/bcachefs/xattr.c @@ -176,7 +176,8 @@ int bch2_xattr_set(struct btree_trans *trans, subvol_inum inum, struct btree_iter inode_iter = { NULL }; int ret; - ret = bch2_inode_peek(trans, &inode_iter, inode_u, inum, BTREE_ITER_INTENT); + ret = bch2_subvol_is_ro_trans(trans, inum.subvol) ?: + bch2_inode_peek(trans, &inode_iter, inode_u, inum, BTREE_ITER_INTENT); if (ret) return ret; diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c index 51453d4928fa..2833e8ef4c09 100644 --- a/fs/btrfs/delalloc-space.c +++ b/fs/btrfs/delalloc-space.c @@ -199,7 +199,7 @@ void btrfs_free_reserved_data_space(struct btrfs_inode *inode, start = round_down(start, fs_info->sectorsize); btrfs_free_reserved_data_space_noquota(fs_info, len); - btrfs_qgroup_free_data(inode, reserved, start, len); + btrfs_qgroup_free_data(inode, reserved, start, len, NULL); } /* diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index bbcc3df77646..62cb97f7c94f 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -4799,6 +4799,32 @@ void btrfs_cleanup_dirty_bgs(struct btrfs_transaction *cur_trans, } } +static void btrfs_free_all_qgroup_pertrans(struct btrfs_fs_info *fs_info) +{ + struct btrfs_root *gang[8]; + int i; + int ret; + + spin_lock(&fs_info->fs_roots_radix_lock); + while (1) { + ret = radix_tree_gang_lookup_tag(&fs_info->fs_roots_radix, + (void **)gang, 0, + ARRAY_SIZE(gang), + BTRFS_ROOT_TRANS_TAG); + if (ret == 0) + break; + for (i = 0; i < ret; i++) { + struct btrfs_root *root = gang[i]; + + btrfs_qgroup_free_meta_all_pertrans(root); + radix_tree_tag_clear(&fs_info->fs_roots_radix, + (unsigned long)root->root_key.objectid, + BTRFS_ROOT_TRANS_TAG); + } + } + spin_unlock(&fs_info->fs_roots_radix_lock); +} + void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans, struct btrfs_fs_info *fs_info) { @@ -4827,6 +4853,8 @@ void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans, EXTENT_DIRTY); btrfs_destroy_pinned_extent(fs_info, &cur_trans->pinned_extents); + btrfs_free_all_qgroup_pertrans(fs_info); + cur_trans->state =TRANS_STATE_COMPLETED; wake_up(&cur_trans->commit_wait); } diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 0455935ff558..01423670bc8a 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -1547,6 +1547,23 @@ out: return ret; } +static void free_head_ref_squota_rsv(struct btrfs_fs_info *fs_info, + struct btrfs_delayed_ref_head *href) +{ + u64 root = href->owning_root; + + /* + * Don't check must_insert_reserved, as this is called from contexts + * where it has already been unset. + */ + if (btrfs_qgroup_mode(fs_info) != BTRFS_QGROUP_MODE_SIMPLE || + !href->is_data || !is_fstree(root)) + return; + + btrfs_qgroup_free_refroot(fs_info, root, href->reserved_bytes, + BTRFS_QGROUP_RSV_DATA); +} + static int run_delayed_data_ref(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_head *href, struct btrfs_delayed_ref_node *node, @@ -1569,7 +1586,6 @@ static int run_delayed_data_ref(struct btrfs_trans_handle *trans, struct btrfs_squota_delta delta = { .root = href->owning_root, .num_bytes = node->num_bytes, - .rsv_bytes = href->reserved_bytes, .is_data = true, .is_inc = true, .generation = trans->transid, @@ -1586,11 +1602,9 @@ static int run_delayed_data_ref(struct btrfs_trans_handle *trans, flags, ref->objectid, ref->offset, &key, node->ref_mod, href->owning_root); + free_head_ref_squota_rsv(trans->fs_info, href); if (!ret) ret = btrfs_record_squota_delta(trans->fs_info, &delta); - else - btrfs_qgroup_free_refroot(trans->fs_info, delta.root, - delta.rsv_bytes, BTRFS_QGROUP_RSV_DATA); } else if (node->action == BTRFS_ADD_DELAYED_REF) { ret = __btrfs_inc_extent_ref(trans, node, parent, ref->root, ref->objectid, ref->offset, @@ -1742,7 +1756,6 @@ static int run_delayed_tree_ref(struct btrfs_trans_handle *trans, struct btrfs_squota_delta delta = { .root = href->owning_root, .num_bytes = fs_info->nodesize, - .rsv_bytes = 0, .is_data = false, .is_inc = true, .generation = trans->transid, @@ -1774,8 +1787,10 @@ static int run_one_delayed_ref(struct btrfs_trans_handle *trans, int ret = 0; if (TRANS_ABORTED(trans)) { - if (insert_reserved) + if (insert_reserved) { btrfs_pin_extent(trans, node->bytenr, node->num_bytes, 1); + free_head_ref_squota_rsv(trans->fs_info, href); + } return 0; } @@ -1871,6 +1886,8 @@ u64 btrfs_cleanup_ref_head_accounting(struct btrfs_fs_info *fs_info, struct btrfs_delayed_ref_root *delayed_refs, struct btrfs_delayed_ref_head *head) { + u64 ret = 0; + /* * We had csum deletions accounted for in our delayed refs rsv, we need * to drop the csum leaves for this update from our delayed_refs_rsv. @@ -1885,14 +1902,13 @@ u64 btrfs_cleanup_ref_head_accounting(struct btrfs_fs_info *fs_info, btrfs_delayed_refs_rsv_release(fs_info, 0, nr_csums); - return btrfs_calc_delayed_ref_csum_bytes(fs_info, nr_csums); + ret = btrfs_calc_delayed_ref_csum_bytes(fs_info, nr_csums); } - if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE && - head->must_insert_reserved && head->is_data) - btrfs_qgroup_free_refroot(fs_info, head->owning_root, - head->reserved_bytes, BTRFS_QGROUP_RSV_DATA); + /* must_insert_reserved can be set only if we didn't run the head ref. */ + if (head->must_insert_reserved) + free_head_ref_squota_rsv(fs_info, head); - return 0; + return ret; } static int cleanup_ref_head(struct btrfs_trans_handle *trans, @@ -2033,6 +2049,12 @@ static int btrfs_run_delayed_refs_for_head(struct btrfs_trans_handle *trans, * spin lock. */ must_insert_reserved = locked_ref->must_insert_reserved; + /* + * Unsetting this on the head ref relinquishes ownership of + * the rsv_bytes, so it is critical that every possible code + * path from here forward frees all reserves including qgroup + * reserve. + */ locked_ref->must_insert_reserved = false; extent_op = locked_ref->extent_op; @@ -3292,7 +3314,6 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_squota_delta delta = { .root = delayed_ref_root, .num_bytes = num_bytes, - .rsv_bytes = 0, .is_data = is_data, .is_inc = false, .generation = btrfs_extent_generation(leaf, ei), @@ -4937,7 +4958,6 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans, .root = root_objectid, .num_bytes = ins->offset, .generation = trans->transid, - .rsv_bytes = 0, .is_data = true, .is_inc = true, }; diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index e6230a6ffa98..b6ff6f320198 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -875,7 +875,7 @@ static int attach_extent_buffer_page(struct extent_buffer *eb, * will not race with any other ebs. */ if (page->mapping) - lockdep_assert_held(&page->mapping->private_lock); + lockdep_assert_held(&page->mapping->i_private_lock); if (fs_info->nodesize >= PAGE_SIZE) { if (!PagePrivate(page)) @@ -1741,16 +1741,16 @@ static int submit_eb_subpage(struct page *page, struct writeback_control *wbc) * Take private lock to ensure the subpage won't be detached * in the meantime. */ - spin_lock(&page->mapping->private_lock); + spin_lock(&page->mapping->i_private_lock); if (!PagePrivate(page)) { - spin_unlock(&page->mapping->private_lock); + spin_unlock(&page->mapping->i_private_lock); break; } spin_lock_irqsave(&subpage->lock, flags); if (!test_bit(bit_start + fs_info->subpage_info->dirty_offset, subpage->bitmaps)) { spin_unlock_irqrestore(&subpage->lock, flags); - spin_unlock(&page->mapping->private_lock); + spin_unlock(&page->mapping->i_private_lock); bit_start++; continue; } @@ -1764,7 +1764,7 @@ static int submit_eb_subpage(struct page *page, struct writeback_control *wbc) */ eb = find_extent_buffer_nolock(fs_info, start); spin_unlock_irqrestore(&subpage->lock, flags); - spin_unlock(&page->mapping->private_lock); + spin_unlock(&page->mapping->i_private_lock); /* * The eb has already reached 0 refs thus find_extent_buffer() @@ -1816,9 +1816,9 @@ static int submit_eb_page(struct page *page, struct btrfs_eb_write_context *ctx) if (btrfs_sb(page->mapping->host->i_sb)->nodesize < PAGE_SIZE) return submit_eb_subpage(page, wbc); - spin_lock(&mapping->private_lock); + spin_lock(&mapping->i_private_lock); if (!PagePrivate(page)) { - spin_unlock(&mapping->private_lock); + spin_unlock(&mapping->i_private_lock); return 0; } @@ -1829,16 +1829,16 @@ static int submit_eb_page(struct page *page, struct btrfs_eb_write_context *ctx) * crashing the machine for something we can survive anyway. */ if (WARN_ON(!eb)) { - spin_unlock(&mapping->private_lock); + spin_unlock(&mapping->i_private_lock); return 0; } if (eb == ctx->eb) { - spin_unlock(&mapping->private_lock); + spin_unlock(&mapping->i_private_lock); return 0; } ret = atomic_inc_not_zero(&eb->refs); - spin_unlock(&mapping->private_lock); + spin_unlock(&mapping->i_private_lock); if (!ret) return 0; @@ -2302,7 +2302,8 @@ static int try_release_extent_state(struct extent_io_tree *tree, ret = 0; } else { u32 clear_bits = ~(EXTENT_LOCKED | EXTENT_NODATASUM | - EXTENT_DELALLOC_NEW | EXTENT_CTLBITS); + EXTENT_DELALLOC_NEW | EXTENT_CTLBITS | + EXTENT_QGROUP_RESERVED); /* * At this point we can safely clear everything except the @@ -3061,7 +3062,7 @@ static bool page_range_has_eb(struct btrfs_fs_info *fs_info, struct page *page) { struct btrfs_subpage *subpage; - lockdep_assert_held(&page->mapping->private_lock); + lockdep_assert_held(&page->mapping->i_private_lock); if (PagePrivate(page)) { subpage = (struct btrfs_subpage *)page->private; @@ -3084,14 +3085,14 @@ static void detach_extent_buffer_page(struct extent_buffer *eb, struct page *pag /* * For mapped eb, we're going to change the page private, which should - * be done under the private_lock. + * be done under the i_private_lock. */ if (mapped) - spin_lock(&page->mapping->private_lock); + spin_lock(&page->mapping->i_private_lock); if (!PagePrivate(page)) { if (mapped) - spin_unlock(&page->mapping->private_lock); + spin_unlock(&page->mapping->i_private_lock); return; } @@ -3115,7 +3116,7 @@ static void detach_extent_buffer_page(struct extent_buffer *eb, struct page *pag detach_page_private(page); } if (mapped) - spin_unlock(&page->mapping->private_lock); + spin_unlock(&page->mapping->i_private_lock); return; } @@ -3138,7 +3139,7 @@ static void detach_extent_buffer_page(struct extent_buffer *eb, struct page *pag if (!page_range_has_eb(fs_info, page)) btrfs_detach_subpage(fs_info, page); - spin_unlock(&page->mapping->private_lock); + spin_unlock(&page->mapping->i_private_lock); } /* Release all pages attached to the extent buffer */ @@ -3519,7 +3520,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, /* * Preallocate page->private for subpage case, so that we won't - * allocate memory with private_lock nor page lock hold. + * allocate memory with i_private_lock nor page lock hold. * * The memory will be freed by attach_extent_buffer_page() or freed * manually if we exit earlier. @@ -3540,10 +3541,10 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, goto free_eb; } - spin_lock(&mapping->private_lock); + spin_lock(&mapping->i_private_lock); exists = grab_extent_buffer(fs_info, p); if (exists) { - spin_unlock(&mapping->private_lock); + spin_unlock(&mapping->i_private_lock); unlock_page(p); put_page(p); mark_extent_buffer_accessed(exists, p); @@ -3563,7 +3564,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, * Thus needs no special handling in error path. */ btrfs_page_inc_eb_refs(fs_info, p); - spin_unlock(&mapping->private_lock); + spin_unlock(&mapping->i_private_lock); WARN_ON(btrfs_page_test_dirty(fs_info, p, eb->start, eb->len)); eb->pages[i] = p; @@ -4568,12 +4569,12 @@ static int try_release_subpage_extent_buffer(struct page *page) * Finally to check if we have cleared page private, as if we have * released all ebs in the page, the page private should be cleared now. */ - spin_lock(&page->mapping->private_lock); + spin_lock(&page->mapping->i_private_lock); if (!PagePrivate(page)) ret = 1; else ret = 0; - spin_unlock(&page->mapping->private_lock); + spin_unlock(&page->mapping->i_private_lock); return ret; } @@ -4589,9 +4590,9 @@ int try_release_extent_buffer(struct page *page) * We need to make sure nobody is changing page->private, as we rely on * page->private as the pointer to extent buffer. */ - spin_lock(&page->mapping->private_lock); + spin_lock(&page->mapping->i_private_lock); if (!PagePrivate(page)) { - spin_unlock(&page->mapping->private_lock); + spin_unlock(&page->mapping->i_private_lock); return 1; } @@ -4606,10 +4607,10 @@ int try_release_extent_buffer(struct page *page) spin_lock(&eb->refs_lock); if (atomic_read(&eb->refs) != 1 || extent_buffer_under_io(eb)) { spin_unlock(&eb->refs_lock); - spin_unlock(&page->mapping->private_lock); + spin_unlock(&page->mapping->i_private_lock); return 0; } - spin_unlock(&page->mapping->private_lock); + spin_unlock(&page->mapping->i_private_lock); /* * If tree ref isn't set then we know the ref on this eb is a real ref, diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index f47731c45bb5..32611a4edd6b 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -3192,7 +3192,7 @@ static long btrfs_fallocate(struct file *file, int mode, qgroup_reserved -= range->len; } else if (qgroup_reserved > 0) { btrfs_qgroup_free_data(BTRFS_I(inode), data_reserved, - range->start, range->len); + range->start, range->len, NULL); qgroup_reserved -= range->len; } list_del(&range->list); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 9f5a9894f88f..fb3c3f43c3fa 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -688,7 +688,7 @@ out: * And at reserve time, it's always aligned to page size, so * just free one page here. */ - btrfs_qgroup_free_data(inode, NULL, 0, PAGE_SIZE); + btrfs_qgroup_free_data(inode, NULL, 0, PAGE_SIZE, NULL); btrfs_free_path(path); btrfs_end_transaction(trans); return ret; @@ -5132,7 +5132,7 @@ static void evict_inode_truncate_pages(struct inode *inode) */ if (state_flags & EXTENT_DELALLOC) btrfs_qgroup_free_data(BTRFS_I(inode), NULL, start, - end - start + 1); + end - start + 1, NULL); clear_extent_bit(io_tree, start, end, EXTENT_CLEAR_ALL_BITS | EXTENT_DO_ACCOUNTING, @@ -8059,7 +8059,7 @@ next: * reserved data space. * Since the IO will never happen for this page. */ - btrfs_qgroup_free_data(inode, NULL, cur, range_end + 1 - cur); + btrfs_qgroup_free_data(inode, NULL, cur, range_end + 1 - cur, NULL); if (!inode_evicting) { clear_extent_bit(tree, cur, range_end, EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_UPTODATE | @@ -9491,7 +9491,7 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent( struct btrfs_path *path; u64 start = ins->objectid; u64 len = ins->offset; - int qgroup_released; + u64 qgroup_released = 0; int ret; memset(&stack_fi, 0, sizeof(stack_fi)); @@ -9504,9 +9504,9 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent( btrfs_set_stack_file_extent_compression(&stack_fi, BTRFS_COMPRESS_NONE); /* Encryption and other encoding is reserved and all 0 */ - qgroup_released = btrfs_qgroup_release_data(inode, file_offset, len); - if (qgroup_released < 0) - return ERR_PTR(qgroup_released); + ret = btrfs_qgroup_release_data(inode, file_offset, len, &qgroup_released); + if (ret < 0) + return ERR_PTR(ret); if (trans) { ret = insert_reserved_file_extent(trans, inode, @@ -10401,7 +10401,7 @@ out_delalloc_release: btrfs_delalloc_release_metadata(inode, disk_num_bytes, ret < 0); out_qgroup_free_data: if (ret < 0) - btrfs_qgroup_free_data(inode, data_reserved, start, num_bytes); + btrfs_qgroup_free_data(inode, data_reserved, start, num_bytes, NULL); out_free_data_space: /* * If btrfs_reserve_extent() succeeded, then we already decremented diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 4e50b62db2a8..41b479861b3c 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1290,6 +1290,15 @@ static noinline int __btrfs_ioctl_snap_create(struct file *file, * are limited to own subvolumes only */ ret = -EPERM; + } else if (btrfs_ino(BTRFS_I(src_inode)) != BTRFS_FIRST_FREE_OBJECTID) { + /* + * Snapshots must be made with the src_inode referring + * to the subvolume inode, otherwise the permission + * checking above is useless because we may have + * permission on a lower directory but not the subvol + * itself. + */ + ret = -EINVAL; } else { ret = btrfs_mksnapshot(&file->f_path, idmap, name, namelen, @@ -4524,29 +4533,29 @@ static int btrfs_ioctl_encoded_write(struct file *file, void __user *argp, bool if (ret < 0) goto out_acct; - file_start_write(file); - if (iov_iter_count(&iter) == 0) { ret = 0; - goto out_end_write; + goto out_iov; } pos = args.offset; ret = rw_verify_area(WRITE, file, &pos, args.len); if (ret < 0) - goto out_end_write; + goto out_iov; init_sync_kiocb(&kiocb, file); ret = kiocb_set_rw_flags(&kiocb, 0); if (ret) - goto out_end_write; + goto out_iov; kiocb.ki_pos = pos; + file_start_write(file); + ret = btrfs_do_write_iter(&kiocb, &iter, &args); if (ret > 0) fsnotify_modify(file); -out_end_write: file_end_write(file); +out_iov: kfree(iov); out_acct: if (ret > 0) diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 574e8a55e24a..a82e1417c4d2 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -152,11 +152,12 @@ static struct btrfs_ordered_extent *alloc_ordered_extent( { struct btrfs_ordered_extent *entry; int ret; + u64 qgroup_rsv = 0; if (flags & ((1 << BTRFS_ORDERED_NOCOW) | (1 << BTRFS_ORDERED_PREALLOC))) { /* For nocow write, we can release the qgroup rsv right now */ - ret = btrfs_qgroup_free_data(inode, NULL, file_offset, num_bytes); + ret = btrfs_qgroup_free_data(inode, NULL, file_offset, num_bytes, &qgroup_rsv); if (ret < 0) return ERR_PTR(ret); } else { @@ -164,7 +165,7 @@ static struct btrfs_ordered_extent *alloc_ordered_extent( * The ordered extent has reserved qgroup space, release now * and pass the reserved number for qgroup_record to free. */ - ret = btrfs_qgroup_release_data(inode, file_offset, num_bytes); + ret = btrfs_qgroup_release_data(inode, file_offset, num_bytes, &qgroup_rsv); if (ret < 0) return ERR_PTR(ret); } @@ -182,7 +183,7 @@ static struct btrfs_ordered_extent *alloc_ordered_extent( entry->inode = igrab(&inode->vfs_inode); entry->compress_type = compress_type; entry->truncated_len = (u64)-1; - entry->qgroup_rsv = ret; + entry->qgroup_rsv = qgroup_rsv; entry->flags = flags; refcount_set(&entry->refs, 1); init_waitqueue_head(&entry->wait); @@ -599,7 +600,9 @@ void btrfs_remove_ordered_extent(struct btrfs_inode *btrfs_inode, release = entry->disk_num_bytes; else release = entry->num_bytes; - btrfs_delalloc_release_metadata(btrfs_inode, release, false); + btrfs_delalloc_release_metadata(btrfs_inode, release, + test_bit(BTRFS_ORDERED_IOERR, + &entry->flags)); } percpu_counter_add_batch(&fs_info->ordered_bytes, -entry->num_bytes, diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index ce446d9d7f23..e46774e8f49f 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -4057,13 +4057,14 @@ int btrfs_qgroup_reserve_data(struct btrfs_inode *inode, /* Free ranges specified by @reserved, normally in error path */ static int qgroup_free_reserved_data(struct btrfs_inode *inode, - struct extent_changeset *reserved, u64 start, u64 len) + struct extent_changeset *reserved, + u64 start, u64 len, u64 *freed_ret) { struct btrfs_root *root = inode->root; struct ulist_node *unode; struct ulist_iterator uiter; struct extent_changeset changeset; - int freed = 0; + u64 freed = 0; int ret; extent_changeset_init(&changeset); @@ -4104,7 +4105,9 @@ static int qgroup_free_reserved_data(struct btrfs_inode *inode, } btrfs_qgroup_free_refroot(root->fs_info, root->root_key.objectid, freed, BTRFS_QGROUP_RSV_DATA); - ret = freed; + if (freed_ret) + *freed_ret = freed; + ret = 0; out: extent_changeset_release(&changeset); return ret; @@ -4112,7 +4115,7 @@ out: static int __btrfs_qgroup_release_data(struct btrfs_inode *inode, struct extent_changeset *reserved, u64 start, u64 len, - int free) + u64 *released, int free) { struct extent_changeset changeset; int trace_op = QGROUP_RELEASE; @@ -4128,7 +4131,7 @@ static int __btrfs_qgroup_release_data(struct btrfs_inode *inode, /* In release case, we shouldn't have @reserved */ WARN_ON(!free && reserved); if (free && reserved) - return qgroup_free_reserved_data(inode, reserved, start, len); + return qgroup_free_reserved_data(inode, reserved, start, len, released); extent_changeset_init(&changeset); ret = clear_record_extent_bits(&inode->io_tree, start, start + len -1, EXTENT_QGROUP_RESERVED, &changeset); @@ -4143,7 +4146,8 @@ static int __btrfs_qgroup_release_data(struct btrfs_inode *inode, btrfs_qgroup_free_refroot(inode->root->fs_info, inode->root->root_key.objectid, changeset.bytes_changed, BTRFS_QGROUP_RSV_DATA); - ret = changeset.bytes_changed; + if (released) + *released = changeset.bytes_changed; out: extent_changeset_release(&changeset); return ret; @@ -4162,9 +4166,10 @@ out: * NOTE: This function may sleep for memory allocation. */ int btrfs_qgroup_free_data(struct btrfs_inode *inode, - struct extent_changeset *reserved, u64 start, u64 len) + struct extent_changeset *reserved, + u64 start, u64 len, u64 *freed) { - return __btrfs_qgroup_release_data(inode, reserved, start, len, 1); + return __btrfs_qgroup_release_data(inode, reserved, start, len, freed, 1); } /* @@ -4182,9 +4187,9 @@ int btrfs_qgroup_free_data(struct btrfs_inode *inode, * * NOTE: This function may sleep for memory allocation. */ -int btrfs_qgroup_release_data(struct btrfs_inode *inode, u64 start, u64 len) +int btrfs_qgroup_release_data(struct btrfs_inode *inode, u64 start, u64 len, u64 *released) { - return __btrfs_qgroup_release_data(inode, NULL, start, len, 0); + return __btrfs_qgroup_release_data(inode, NULL, start, len, released, 0); } static void add_root_meta_rsv(struct btrfs_root *root, int num_bytes, @@ -4332,8 +4337,9 @@ static void qgroup_convert_meta(struct btrfs_fs_info *fs_info, u64 ref_root, qgroup_rsv_release(fs_info, qgroup, num_bytes, BTRFS_QGROUP_RSV_META_PREALLOC); - qgroup_rsv_add(fs_info, qgroup, num_bytes, - BTRFS_QGROUP_RSV_META_PERTRANS); + if (!sb_rdonly(fs_info->sb)) + qgroup_rsv_add(fs_info, qgroup, num_bytes, + BTRFS_QGROUP_RSV_META_PERTRANS); list_for_each_entry(glist, &qgroup->groups, next_group) qgroup_iterator_add(&qgroup_list, glist->group); @@ -4655,6 +4661,17 @@ void btrfs_qgroup_destroy_extent_records(struct btrfs_transaction *trans) *root = RB_ROOT; } +void btrfs_free_squota_rsv(struct btrfs_fs_info *fs_info, u64 root, u64 rsv_bytes) +{ + if (btrfs_qgroup_mode(fs_info) != BTRFS_QGROUP_MODE_SIMPLE) + return; + + if (!is_fstree(root)) + return; + + btrfs_qgroup_free_refroot(fs_info, root, rsv_bytes, BTRFS_QGROUP_RSV_DATA); +} + int btrfs_record_squota_delta(struct btrfs_fs_info *fs_info, struct btrfs_squota_delta *delta) { @@ -4699,8 +4716,5 @@ int btrfs_record_squota_delta(struct btrfs_fs_info *fs_info, out: spin_unlock(&fs_info->qgroup_lock); - if (!ret && delta->rsv_bytes) - btrfs_qgroup_free_refroot(fs_info, root, delta->rsv_bytes, - BTRFS_QGROUP_RSV_DATA); return ret; } diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h index 855a4f978761..be18c862e64e 100644 --- a/fs/btrfs/qgroup.h +++ b/fs/btrfs/qgroup.h @@ -274,8 +274,6 @@ struct btrfs_squota_delta { u64 root; /* The number of bytes in the extent being counted. */ u64 num_bytes; - /* The number of bytes reserved for this extent. */ - u64 rsv_bytes; /* The generation the extent was created in. */ u64 generation; /* Whether we are using or freeing the extent. */ @@ -358,10 +356,10 @@ int btrfs_verify_qgroup_counts(struct btrfs_fs_info *fs_info, u64 qgroupid, /* New io_tree based accurate qgroup reserve API */ int btrfs_qgroup_reserve_data(struct btrfs_inode *inode, struct extent_changeset **reserved, u64 start, u64 len); -int btrfs_qgroup_release_data(struct btrfs_inode *inode, u64 start, u64 len); +int btrfs_qgroup_release_data(struct btrfs_inode *inode, u64 start, u64 len, u64 *released); int btrfs_qgroup_free_data(struct btrfs_inode *inode, struct extent_changeset *reserved, u64 start, - u64 len); + u64 len, u64 *freed); int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes, enum btrfs_qgroup_rsv_type type, bool enforce); int __btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes, @@ -422,6 +420,7 @@ int btrfs_qgroup_trace_subtree_after_cow(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *eb); void btrfs_qgroup_destroy_extent_records(struct btrfs_transaction *trans); bool btrfs_check_quota_leak(struct btrfs_fs_info *fs_info); +void btrfs_free_squota_rsv(struct btrfs_fs_info *fs_info, u64 root, u64 rsv_bytes); int btrfs_record_squota_delta(struct btrfs_fs_info *fs_info, struct btrfs_squota_delta *delta); diff --git a/fs/btrfs/subpage.c b/fs/btrfs/subpage.c index 1b999c6e4193..2347cf15278b 100644 --- a/fs/btrfs/subpage.c +++ b/fs/btrfs/subpage.c @@ -200,7 +200,7 @@ void btrfs_page_inc_eb_refs(const struct btrfs_fs_info *fs_info, return; ASSERT(PagePrivate(page) && page->mapping); - lockdep_assert_held(&page->mapping->private_lock); + lockdep_assert_held(&page->mapping->i_private_lock); subpage = (struct btrfs_subpage *)page->private; atomic_inc(&subpage->eb_refs); @@ -215,7 +215,7 @@ void btrfs_page_dec_eb_refs(const struct btrfs_fs_info *fs_info, return; ASSERT(PagePrivate(page) && page->mapping); - lockdep_assert_held(&page->mapping->private_lock); + lockdep_assert_held(&page->mapping->i_private_lock); subpage = (struct btrfs_subpage *)page->private; ASSERT(atomic_read(&subpage->eb_refs)); diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index ef256b944c72..2a3a5bf102dc 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1406,6 +1406,8 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type, return ERR_PTR(error); } + /* No support for restricting writes to btrfs devices yet... */ + mode &= ~BLK_OPEN_RESTRICT_WRITES; /* * Setup a dummy root and fs_info for test/set super. This is because * we don't actually fill this stuff out until open_ctree, but we need diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index bfc0eb5e3b7c..5b3333ceef04 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -37,8 +37,6 @@ static struct kmem_cache *btrfs_trans_handle_cachep; -#define BTRFS_ROOT_TRANS_TAG 0 - /* * Transaction states and transitions * diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 18c4f6e83b78..2bf8bbdfd0b3 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -12,6 +12,9 @@ #include "ctree.h" #include "misc.h" +/* Radix-tree tag for roots that are part of the trasaction. */ +#define BTRFS_ROOT_TRANS_TAG 0 + enum btrfs_trans_state { TRANS_STATE_RUNNING, TRANS_STATE_COMMIT_PREP, diff --git a/fs/buffer.c b/fs/buffer.c index 967f34b70aa8..5ffc44ab4854 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -180,11 +180,11 @@ EXPORT_SYMBOL(end_buffer_write_sync); * Various filesystems appear to want __find_get_block to be non-blocking. * But it's the page lock which protects the buffers. To get around this, * we get exclusion from try_to_free_buffers with the blockdev mapping's - * private_lock. + * i_private_lock. * - * Hack idea: for the blockdev mapping, private_lock contention + * Hack idea: for the blockdev mapping, i_private_lock contention * may be quite high. This code could TryLock the page, and if that - * succeeds, there is no need to take private_lock. + * succeeds, there is no need to take i_private_lock. */ static struct buffer_head * __find_get_block_slow(struct block_device *bdev, sector_t block) @@ -204,7 +204,7 @@ __find_get_block_slow(struct block_device *bdev, sector_t block) if (IS_ERR(folio)) goto out; - spin_lock(&bd_mapping->private_lock); + spin_lock(&bd_mapping->i_private_lock); head = folio_buffers(folio); if (!head) goto out_unlock; @@ -236,7 +236,7 @@ __find_get_block_slow(struct block_device *bdev, sector_t block) 1 << bd_inode->i_blkbits); } out_unlock: - spin_unlock(&bd_mapping->private_lock); + spin_unlock(&bd_mapping->i_private_lock); folio_put(folio); out: return ret; @@ -467,25 +467,25 @@ EXPORT_SYMBOL(mark_buffer_async_write); * * The functions mark_buffer_inode_dirty(), fsync_inode_buffers(), * inode_has_buffers() and invalidate_inode_buffers() are provided for the - * management of a list of dependent buffers at ->i_mapping->private_list. + * management of a list of dependent buffers at ->i_mapping->i_private_list. * * Locking is a little subtle: try_to_free_buffers() will remove buffers * from their controlling inode's queue when they are being freed. But * try_to_free_buffers() will be operating against the *blockdev* mapping * at the time, not against the S_ISREG file which depends on those buffers. - * So the locking for private_list is via the private_lock in the address_space + * So the locking for i_private_list is via the i_private_lock in the address_space * which backs the buffers. Which is different from the address_space * against which the buffers are listed. So for a particular address_space, - * mapping->private_lock does *not* protect mapping->private_list! In fact, - * mapping->private_list will always be protected by the backing blockdev's - * ->private_lock. + * mapping->i_private_lock does *not* protect mapping->i_private_list! In fact, + * mapping->i_private_list will always be protected by the backing blockdev's + * ->i_private_lock. * * Which introduces a requirement: all buffers on an address_space's - * ->private_list must be from the same address_space: the blockdev's. + * ->i_private_list must be from the same address_space: the blockdev's. * - * address_spaces which do not place buffers at ->private_list via these - * utility functions are free to use private_lock and private_list for - * whatever they want. The only requirement is that list_empty(private_list) + * address_spaces which do not place buffers at ->i_private_list via these + * utility functions are free to use i_private_lock and i_private_list for + * whatever they want. The only requirement is that list_empty(i_private_list) * be true at clear_inode() time. * * FIXME: clear_inode should not call invalidate_inode_buffers(). The @@ -508,7 +508,7 @@ EXPORT_SYMBOL(mark_buffer_async_write); */ /* - * The buffer's backing address_space's private_lock must be held + * The buffer's backing address_space's i_private_lock must be held */ static void __remove_assoc_queue(struct buffer_head *bh) { @@ -519,7 +519,7 @@ static void __remove_assoc_queue(struct buffer_head *bh) int inode_has_buffers(struct inode *inode) { - return !list_empty(&inode->i_data.private_list); + return !list_empty(&inode->i_data.i_private_list); } /* @@ -561,7 +561,7 @@ repeat: * sync_mapping_buffers - write out & wait upon a mapping's "associated" buffers * @mapping: the mapping which wants those buffers written * - * Starts I/O against the buffers at mapping->private_list, and waits upon + * Starts I/O against the buffers at mapping->i_private_list, and waits upon * that I/O. * * Basically, this is a convenience function for fsync(). @@ -570,13 +570,13 @@ repeat: */ int sync_mapping_buffers(struct address_space *mapping) { - struct address_space *buffer_mapping = mapping->private_data; + struct address_space *buffer_mapping = mapping->i_private_data; - if (buffer_mapping == NULL || list_empty(&mapping->private_list)) + if (buffer_mapping == NULL || list_empty(&mapping->i_private_list)) return 0; - return fsync_buffers_list(&buffer_mapping->private_lock, - &mapping->private_list); + return fsync_buffers_list(&buffer_mapping->i_private_lock, + &mapping->i_private_list); } EXPORT_SYMBOL(sync_mapping_buffers); @@ -673,17 +673,17 @@ void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode) struct address_space *buffer_mapping = bh->b_folio->mapping; mark_buffer_dirty(bh); - if (!mapping->private_data) { - mapping->private_data = buffer_mapping; + if (!mapping->i_private_data) { + mapping->i_private_data = buffer_mapping; } else { - BUG_ON(mapping->private_data != buffer_mapping); + BUG_ON(mapping->i_private_data != buffer_mapping); } if (!bh->b_assoc_map) { - spin_lock(&buffer_mapping->private_lock); + spin_lock(&buffer_mapping->i_private_lock); list_move_tail(&bh->b_assoc_buffers, - &mapping->private_list); + &mapping->i_private_list); bh->b_assoc_map = mapping; - spin_unlock(&buffer_mapping->private_lock); + spin_unlock(&buffer_mapping->i_private_lock); } } EXPORT_SYMBOL(mark_buffer_dirty_inode); @@ -706,7 +706,7 @@ EXPORT_SYMBOL(mark_buffer_dirty_inode); * bit, see a bunch of clean buffers and we'd end up with dirty buffers/clean * page on the dirty page list. * - * We use private_lock to lock against try_to_free_buffers while using the + * We use i_private_lock to lock against try_to_free_buffers while using the * page's buffer list. Also use this to protect against clean buffers being * added to the page after it was set dirty. * @@ -718,7 +718,7 @@ bool block_dirty_folio(struct address_space *mapping, struct folio *folio) struct buffer_head *head; bool newly_dirty; - spin_lock(&mapping->private_lock); + spin_lock(&mapping->i_private_lock); head = folio_buffers(folio); if (head) { struct buffer_head *bh = head; @@ -734,7 +734,7 @@ bool block_dirty_folio(struct address_space *mapping, struct folio *folio) */ folio_memcg_lock(folio); newly_dirty = !folio_test_set_dirty(folio); - spin_unlock(&mapping->private_lock); + spin_unlock(&mapping->i_private_lock); if (newly_dirty) __folio_mark_dirty(folio, mapping, 1); @@ -827,7 +827,7 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list) smp_mb(); if (buffer_dirty(bh)) { list_add(&bh->b_assoc_buffers, - &mapping->private_list); + &mapping->i_private_list); bh->b_assoc_map = mapping; } spin_unlock(lock); @@ -851,7 +851,7 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list) * probably unmounting the fs, but that doesn't mean we have already * done a sync(). Just drop the buffers from the inode list. * - * NOTE: we take the inode's blockdev's mapping's private_lock. Which + * NOTE: we take the inode's blockdev's mapping's i_private_lock. Which * assumes that all the buffers are against the blockdev. Not true * for reiserfs. */ @@ -859,13 +859,13 @@ void invalidate_inode_buffers(struct inode *inode) { if (inode_has_buffers(inode)) { struct address_space *mapping = &inode->i_data; - struct list_head *list = &mapping->private_list; - struct address_space *buffer_mapping = mapping->private_data; + struct list_head *list = &mapping->i_private_list; + struct address_space *buffer_mapping = mapping->i_private_data; - spin_lock(&buffer_mapping->private_lock); + spin_lock(&buffer_mapping->i_private_lock); while (!list_empty(list)) __remove_assoc_queue(BH_ENTRY(list->next)); - spin_unlock(&buffer_mapping->private_lock); + spin_unlock(&buffer_mapping->i_private_lock); } } EXPORT_SYMBOL(invalidate_inode_buffers); @@ -882,10 +882,10 @@ int remove_inode_buffers(struct inode *inode) if (inode_has_buffers(inode)) { struct address_space *mapping = &inode->i_data; - struct list_head *list = &mapping->private_list; - struct address_space *buffer_mapping = mapping->private_data; + struct list_head *list = &mapping->i_private_list; + struct address_space *buffer_mapping = mapping->i_private_data; - spin_lock(&buffer_mapping->private_lock); + spin_lock(&buffer_mapping->i_private_lock); while (!list_empty(list)) { struct buffer_head *bh = BH_ENTRY(list->next); if (buffer_dirty(bh)) { @@ -894,7 +894,7 @@ int remove_inode_buffers(struct inode *inode) } __remove_assoc_queue(bh); } - spin_unlock(&buffer_mapping->private_lock); + spin_unlock(&buffer_mapping->i_private_lock); } return ret; } @@ -1064,11 +1064,11 @@ grow_dev_page(struct block_device *bdev, sector_t block, * lock to be atomic wrt __find_get_block(), which does not * run under the folio lock. */ - spin_lock(&inode->i_mapping->private_lock); + spin_lock(&inode->i_mapping->i_private_lock); link_dev_buffers(folio, bh); end_block = folio_init_buffers(folio, bdev, (sector_t)index << sizebits, size); - spin_unlock(&inode->i_mapping->private_lock); + spin_unlock(&inode->i_mapping->i_private_lock); done: ret = (block < end_block) ? 1 : -ENXIO; failed: @@ -1168,7 +1168,7 @@ __getblk_slow(struct block_device *bdev, sector_t block, * and then attach the address_space's inode to its superblock's dirty * inode list. * - * mark_buffer_dirty() is atomic. It takes bh->b_folio->mapping->private_lock, + * mark_buffer_dirty() is atomic. It takes bh->b_folio->mapping->i_private_lock, * i_pages lock and mapping->host->i_lock. */ void mark_buffer_dirty(struct buffer_head *bh) @@ -1246,10 +1246,10 @@ void __bforget(struct buffer_head *bh) if (bh->b_assoc_map) { struct address_space *buffer_mapping = bh->b_folio->mapping; - spin_lock(&buffer_mapping->private_lock); + spin_lock(&buffer_mapping->i_private_lock); list_del_init(&bh->b_assoc_buffers); bh->b_assoc_map = NULL; - spin_unlock(&buffer_mapping->private_lock); + spin_unlock(&buffer_mapping->i_private_lock); } __brelse(bh); } @@ -1638,7 +1638,7 @@ EXPORT_SYMBOL(block_invalidate_folio); /* * We attach and possibly dirty the buffers atomically wrt - * block_dirty_folio() via private_lock. try_to_free_buffers + * block_dirty_folio() via i_private_lock. try_to_free_buffers * is already excluded via the folio lock. */ struct buffer_head *create_empty_buffers(struct folio *folio, @@ -1656,7 +1656,7 @@ struct buffer_head *create_empty_buffers(struct folio *folio, } while (bh); tail->b_this_page = head; - spin_lock(&folio->mapping->private_lock); + spin_lock(&folio->mapping->i_private_lock); if (folio_test_uptodate(folio) || folio_test_dirty(folio)) { bh = head; do { @@ -1668,7 +1668,7 @@ struct buffer_head *create_empty_buffers(struct folio *folio, } while (bh != head); } folio_attach_private(folio, head); - spin_unlock(&folio->mapping->private_lock); + spin_unlock(&folio->mapping->i_private_lock); return head; } @@ -1715,7 +1715,7 @@ void clean_bdev_aliases(struct block_device *bdev, sector_t block, sector_t len) if (!folio_buffers(folio)) continue; /* - * We use folio lock instead of bd_mapping->private_lock + * We use folio lock instead of bd_mapping->i_private_lock * to pin buffers here since we can afford to sleep and * it scales better than a global spinlock lock. */ @@ -2883,7 +2883,7 @@ EXPORT_SYMBOL(sync_dirty_buffer); * are unused, and releases them if so. * * Exclusion against try_to_free_buffers may be obtained by either - * locking the folio or by holding its mapping's private_lock. + * locking the folio or by holding its mapping's i_private_lock. * * If the folio is dirty but all the buffers are clean then we need to * be sure to mark the folio clean as well. This is because the folio @@ -2894,7 +2894,7 @@ EXPORT_SYMBOL(sync_dirty_buffer); * The same applies to regular filesystem folios: if all the buffers are * clean then we set the folio clean and proceed. To do that, we require * total exclusion from block_dirty_folio(). That is obtained with - * private_lock. + * i_private_lock. * * try_to_free_buffers() is non-blocking. */ @@ -2946,7 +2946,7 @@ bool try_to_free_buffers(struct folio *folio) goto out; } - spin_lock(&mapping->private_lock); + spin_lock(&mapping->i_private_lock); ret = drop_buffers(folio, &buffers_to_free); /* @@ -2959,13 +2959,13 @@ bool try_to_free_buffers(struct folio *folio) * the folio's buffers clean. We discover that here and clean * the folio also. * - * private_lock must be held over this entire operation in order + * i_private_lock must be held over this entire operation in order * to synchronise against block_dirty_folio and prevent the * dirty bit from being lost. */ if (ret) folio_cancel_dirty(folio); - spin_unlock(&mapping->private_lock); + spin_unlock(&mapping->i_private_lock); out: if (buffers_to_free) { struct buffer_head *bh = buffers_to_free; diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c index aa4efcabb5e3..3f24905f4066 100644 --- a/fs/cachefiles/daemon.c +++ b/fs/cachefiles/daemon.c @@ -77,6 +77,7 @@ static const struct cachefiles_daemon_cmd cachefiles_daemon_cmds[] = { { "tag", cachefiles_daemon_tag }, #ifdef CONFIG_CACHEFILES_ONDEMAND { "copen", cachefiles_ondemand_copen }, + { "restore", cachefiles_ondemand_restore }, #endif { "", NULL } }; @@ -355,14 +356,24 @@ static __poll_t cachefiles_daemon_poll(struct file *file, struct poll_table_struct *poll) { struct cachefiles_cache *cache = file->private_data; + XA_STATE(xas, &cache->reqs, 0); + struct cachefiles_req *req; __poll_t mask; poll_wait(file, &cache->daemon_pollwq, poll); mask = 0; if (cachefiles_in_ondemand_mode(cache)) { - if (!xa_empty(&cache->reqs)) - mask |= EPOLLIN; + if (!xa_empty(&cache->reqs)) { + rcu_read_lock(); + xas_for_each_marked(&xas, req, ULONG_MAX, CACHEFILES_REQ_NEW) { + if (!cachefiles_ondemand_is_reopening_read(req)) { + mask |= EPOLLIN; + break; + } + } + rcu_read_unlock(); + } } else { if (test_bit(CACHEFILES_STATE_CHANGED, &cache->flags)) mask |= EPOLLIN; diff --git a/fs/cachefiles/interface.c b/fs/cachefiles/interface.c index 40052bdb3365..35ba2117a6f6 100644 --- a/fs/cachefiles/interface.c +++ b/fs/cachefiles/interface.c @@ -31,6 +31,11 @@ struct cachefiles_object *cachefiles_alloc_object(struct fscache_cookie *cookie) if (!object) return NULL; + if (cachefiles_ondemand_init_obj_info(object, volume)) { + kmem_cache_free(cachefiles_object_jar, object); + return NULL; + } + refcount_set(&object->ref, 1); spin_lock_init(&object->lock); @@ -88,7 +93,7 @@ void cachefiles_put_object(struct cachefiles_object *object, ASSERTCMP(object->file, ==, NULL); kfree(object->d_name); - + cachefiles_ondemand_deinit_obj_info(object); cache = object->volume->cache->cache; fscache_put_cookie(object->cookie, fscache_cookie_put_object); object->cookie = NULL; diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h index 2ad58c465208..4a87c9d714a9 100644 --- a/fs/cachefiles/internal.h +++ b/fs/cachefiles/internal.h @@ -44,6 +44,19 @@ struct cachefiles_volume { struct dentry *fanout[256]; /* Fanout subdirs */ }; +enum cachefiles_object_state { + CACHEFILES_ONDEMAND_OBJSTATE_CLOSE, /* Anonymous fd closed by daemon or initial state */ + CACHEFILES_ONDEMAND_OBJSTATE_OPEN, /* Anonymous fd associated with object is available */ + CACHEFILES_ONDEMAND_OBJSTATE_REOPENING, /* Object that was closed and is being reopened. */ +}; + +struct cachefiles_ondemand_info { + struct work_struct ondemand_work; + int ondemand_id; + enum cachefiles_object_state state; + struct cachefiles_object *object; +}; + /* * Backing file state. */ @@ -61,7 +74,7 @@ struct cachefiles_object { unsigned long flags; #define CACHEFILES_OBJECT_USING_TMPFILE 0 /* Have an unlinked tmpfile */ #ifdef CONFIG_CACHEFILES_ONDEMAND - int ondemand_id; + struct cachefiles_ondemand_info *ondemand; #endif }; @@ -290,12 +303,42 @@ extern ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache, extern int cachefiles_ondemand_copen(struct cachefiles_cache *cache, char *args); +extern int cachefiles_ondemand_restore(struct cachefiles_cache *cache, + char *args); + extern int cachefiles_ondemand_init_object(struct cachefiles_object *object); extern void cachefiles_ondemand_clean_object(struct cachefiles_object *object); extern int cachefiles_ondemand_read(struct cachefiles_object *object, loff_t pos, size_t len); +extern int cachefiles_ondemand_init_obj_info(struct cachefiles_object *obj, + struct cachefiles_volume *volume); +extern void cachefiles_ondemand_deinit_obj_info(struct cachefiles_object *obj); + +#define CACHEFILES_OBJECT_STATE_FUNCS(_state, _STATE) \ +static inline bool \ +cachefiles_ondemand_object_is_##_state(const struct cachefiles_object *object) \ +{ \ + return object->ondemand->state == CACHEFILES_ONDEMAND_OBJSTATE_##_STATE; \ +} \ + \ +static inline void \ +cachefiles_ondemand_set_object_##_state(struct cachefiles_object *object) \ +{ \ + object->ondemand->state = CACHEFILES_ONDEMAND_OBJSTATE_##_STATE; \ +} + +CACHEFILES_OBJECT_STATE_FUNCS(open, OPEN); +CACHEFILES_OBJECT_STATE_FUNCS(close, CLOSE); +CACHEFILES_OBJECT_STATE_FUNCS(reopening, REOPENING); + +static inline bool cachefiles_ondemand_is_reopening_read(struct cachefiles_req *req) +{ + return cachefiles_ondemand_object_is_reopening(req->object) && + req->msg.opcode == CACHEFILES_OP_READ; +} + #else static inline ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache, char __user *_buffer, size_t buflen) @@ -317,6 +360,20 @@ static inline int cachefiles_ondemand_read(struct cachefiles_object *object, { return -EOPNOTSUPP; } + +static inline int cachefiles_ondemand_init_obj_info(struct cachefiles_object *obj, + struct cachefiles_volume *volume) +{ + return 0; +} +static inline void cachefiles_ondemand_deinit_obj_info(struct cachefiles_object *obj) +{ +} + +static inline bool cachefiles_ondemand_is_reopening_read(struct cachefiles_req *req) +{ + return false; +} #endif /* diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c index 009d23cd435b..5857241c5918 100644 --- a/fs/cachefiles/io.c +++ b/fs/cachefiles/io.c @@ -259,7 +259,8 @@ static void cachefiles_write_complete(struct kiocb *iocb, long ret) _enter("%ld", ret); - kiocb_end_write(iocb); + if (ki->was_async) + kiocb_end_write(iocb); if (ret < 0) trace_cachefiles_io_error(object, inode, ret, @@ -319,8 +320,6 @@ int __cachefiles_write(struct cachefiles_object *object, ki->iocb.ki_complete = cachefiles_write_complete; atomic_long_add(ki->b_writing, &cache->b_writing); - kiocb_start_write(&ki->iocb); - get_file(ki->iocb.ki_filp); cachefiles_grab_object(object, cachefiles_obj_get_ioreq); diff --git a/fs/cachefiles/ondemand.c b/fs/cachefiles/ondemand.c index 0254ed39f68c..b8fbbb1961bb 100644 --- a/fs/cachefiles/ondemand.c +++ b/fs/cachefiles/ondemand.c @@ -9,21 +9,19 @@ static int cachefiles_ondemand_fd_release(struct inode *inode, { struct cachefiles_object *object = file->private_data; struct cachefiles_cache *cache = object->volume->cache; - int object_id = object->ondemand_id; + struct cachefiles_ondemand_info *info = object->ondemand; + int object_id = info->ondemand_id; struct cachefiles_req *req; XA_STATE(xas, &cache->reqs, 0); xa_lock(&cache->reqs); - object->ondemand_id = CACHEFILES_ONDEMAND_ID_CLOSED; + info->ondemand_id = CACHEFILES_ONDEMAND_ID_CLOSED; + cachefiles_ondemand_set_object_close(object); - /* - * Flush all pending READ requests since their completion depends on - * anon_fd. - */ - xas_for_each(&xas, req, ULONG_MAX) { + /* Only flush CACHEFILES_REQ_NEW marked req to avoid race with daemon_read */ + xas_for_each_marked(&xas, req, ULONG_MAX, CACHEFILES_REQ_NEW) { if (req->msg.object_id == object_id && - req->msg.opcode == CACHEFILES_OP_READ) { - req->error = -EIO; + req->msg.opcode == CACHEFILES_OP_CLOSE) { complete(&req->done); xas_store(&xas, NULL); } @@ -176,11 +174,37 @@ int cachefiles_ondemand_copen(struct cachefiles_cache *cache, char *args) set_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags); trace_cachefiles_ondemand_copen(req->object, id, size); + cachefiles_ondemand_set_object_open(req->object); + wake_up_all(&cache->daemon_pollwq); + out: complete(&req->done); return ret; } +int cachefiles_ondemand_restore(struct cachefiles_cache *cache, char *args) +{ + struct cachefiles_req *req; + + XA_STATE(xas, &cache->reqs, 0); + + if (!test_bit(CACHEFILES_ONDEMAND_MODE, &cache->flags)) + return -EOPNOTSUPP; + + /* + * Reset the requests to CACHEFILES_REQ_NEW state, so that the + * requests have been processed halfway before the crash of the + * user daemon could be reprocessed after the recovery. + */ + xas_lock(&xas); + xas_for_each(&xas, req, ULONG_MAX) + xas_set_mark(&xas, CACHEFILES_REQ_NEW); + xas_unlock(&xas); + + wake_up_all(&cache->daemon_pollwq); + return 0; +} + static int cachefiles_ondemand_get_fd(struct cachefiles_req *req) { struct cachefiles_object *object; @@ -218,8 +242,7 @@ static int cachefiles_ondemand_get_fd(struct cachefiles_req *req) load = (void *)req->msg.data; load->fd = fd; - req->msg.object_id = object_id; - object->ondemand_id = object_id; + object->ondemand->ondemand_id = object_id; cachefiles_get_unbind_pincount(cache); trace_cachefiles_ondemand_open(object, &req->msg, load); @@ -234,6 +257,43 @@ err: return ret; } +static void ondemand_object_worker(struct work_struct *work) +{ + struct cachefiles_ondemand_info *info = + container_of(work, struct cachefiles_ondemand_info, ondemand_work); + + cachefiles_ondemand_init_object(info->object); +} + +/* + * If there are any inflight or subsequent READ requests on the + * closed object, reopen it. + * Skip read requests whose related object is reopening. + */ +static struct cachefiles_req *cachefiles_ondemand_select_req(struct xa_state *xas, + unsigned long xa_max) +{ + struct cachefiles_req *req; + struct cachefiles_object *object; + struct cachefiles_ondemand_info *info; + + xas_for_each_marked(xas, req, xa_max, CACHEFILES_REQ_NEW) { + if (req->msg.opcode != CACHEFILES_OP_READ) + return req; + object = req->object; + info = object->ondemand; + if (cachefiles_ondemand_object_is_close(object)) { + cachefiles_ondemand_set_object_reopening(object); + queue_work(fscache_wq, &info->ondemand_work); + continue; + } + if (cachefiles_ondemand_object_is_reopening(object)) + continue; + return req; + } + return NULL; +} + ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache, char __user *_buffer, size_t buflen) { @@ -244,16 +304,16 @@ ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache, int ret = 0; XA_STATE(xas, &cache->reqs, cache->req_id_next); + xa_lock(&cache->reqs); /* * Cyclically search for a request that has not ever been processed, * to prevent requests from being processed repeatedly, and make * request distribution fair. */ - xa_lock(&cache->reqs); - req = xas_find_marked(&xas, UINT_MAX, CACHEFILES_REQ_NEW); + req = cachefiles_ondemand_select_req(&xas, ULONG_MAX); if (!req && cache->req_id_next > 0) { xas_set(&xas, 0); - req = xas_find_marked(&xas, cache->req_id_next - 1, CACHEFILES_REQ_NEW); + req = cachefiles_ondemand_select_req(&xas, cache->req_id_next - 1); } if (!req) { xa_unlock(&cache->reqs); @@ -273,14 +333,18 @@ ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache, xa_unlock(&cache->reqs); id = xas.xa_index; - msg->msg_id = id; if (msg->opcode == CACHEFILES_OP_OPEN) { ret = cachefiles_ondemand_get_fd(req); - if (ret) + if (ret) { + cachefiles_ondemand_set_object_close(req->object); goto error; + } } + msg->msg_id = id; + msg->object_id = req->object->ondemand->ondemand_id; + if (copy_to_user(_buffer, msg, n) != 0) { ret = -EFAULT; goto err_put_fd; @@ -313,19 +377,23 @@ static int cachefiles_ondemand_send_req(struct cachefiles_object *object, void *private) { struct cachefiles_cache *cache = object->volume->cache; - struct cachefiles_req *req; + struct cachefiles_req *req = NULL; XA_STATE(xas, &cache->reqs, 0); int ret; if (!test_bit(CACHEFILES_ONDEMAND_MODE, &cache->flags)) return 0; - if (test_bit(CACHEFILES_DEAD, &cache->flags)) - return -EIO; + if (test_bit(CACHEFILES_DEAD, &cache->flags)) { + ret = -EIO; + goto out; + } req = kzalloc(sizeof(*req) + data_len, GFP_KERNEL); - if (!req) - return -ENOMEM; + if (!req) { + ret = -ENOMEM; + goto out; + } req->object = object; init_completion(&req->done); @@ -363,8 +431,9 @@ static int cachefiles_ondemand_send_req(struct cachefiles_object *object, /* coupled with the barrier in cachefiles_flush_reqs() */ smp_mb(); - if (opcode != CACHEFILES_OP_OPEN && object->ondemand_id <= 0) { - WARN_ON_ONCE(object->ondemand_id == 0); + if (opcode == CACHEFILES_OP_CLOSE && + !cachefiles_ondemand_object_is_open(object)) { + WARN_ON_ONCE(object->ondemand->ondemand_id == 0); xas_unlock(&xas); ret = -EIO; goto out; @@ -387,7 +456,15 @@ static int cachefiles_ondemand_send_req(struct cachefiles_object *object, wake_up_all(&cache->daemon_pollwq); wait_for_completion(&req->done); ret = req->error; + kfree(req); + return ret; out: + /* Reset the object to close state in error handling path. + * If error occurs after creating the anonymous fd, + * cachefiles_ondemand_fd_release() will set object to close. + */ + if (opcode == CACHEFILES_OP_OPEN) + cachefiles_ondemand_set_object_close(object); kfree(req); return ret; } @@ -430,18 +507,10 @@ static int cachefiles_ondemand_init_close_req(struct cachefiles_req *req, void *private) { struct cachefiles_object *object = req->object; - int object_id = object->ondemand_id; - /* - * It's possible that object id is still 0 if the cookie looking up - * phase failed before OPEN request has ever been sent. Also avoid - * sending CLOSE request for CACHEFILES_ONDEMAND_ID_CLOSED, which means - * anon_fd has already been closed. - */ - if (object_id <= 0) + if (!cachefiles_ondemand_object_is_open(object)) return -ENOENT; - req->msg.object_id = object_id; trace_cachefiles_ondemand_close(object, &req->msg); return 0; } @@ -457,16 +526,7 @@ static int cachefiles_ondemand_init_read_req(struct cachefiles_req *req, struct cachefiles_object *object = req->object; struct cachefiles_read *load = (void *)req->msg.data; struct cachefiles_read_ctx *read_ctx = private; - int object_id = object->ondemand_id; - - /* Stop enqueuing requests when daemon has closed anon_fd. */ - if (object_id <= 0) { - WARN_ON_ONCE(object_id == 0); - pr_info_once("READ: anonymous fd closed prematurely.\n"); - return -EIO; - } - req->msg.object_id = object_id; load->off = read_ctx->off; load->len = read_ctx->len; trace_cachefiles_ondemand_read(object, &req->msg, load); @@ -485,7 +545,7 @@ int cachefiles_ondemand_init_object(struct cachefiles_object *object) * creating a new tmpfile as the cache file. Reuse the previously * allocated object ID if any. */ - if (object->ondemand_id > 0) + if (cachefiles_ondemand_object_is_open(object)) return 0; volume_key_size = volume->key[0] + 1; @@ -503,6 +563,28 @@ void cachefiles_ondemand_clean_object(struct cachefiles_object *object) cachefiles_ondemand_init_close_req, NULL); } +int cachefiles_ondemand_init_obj_info(struct cachefiles_object *object, + struct cachefiles_volume *volume) +{ + if (!cachefiles_in_ondemand_mode(volume->cache)) + return 0; + + object->ondemand = kzalloc(sizeof(struct cachefiles_ondemand_info), + GFP_KERNEL); + if (!object->ondemand) + return -ENOMEM; + + object->ondemand->object = object; + INIT_WORK(&object->ondemand->ondemand_work, ondemand_object_worker); + return 0; +} + +void cachefiles_ondemand_deinit_obj_info(struct cachefiles_object *object) +{ + kfree(object->ondemand); + object->ondemand = NULL; +} + int cachefiles_ondemand_read(struct cachefiles_object *object, loff_t pos, size_t len) { diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 3b5aae29e944..d380d9dad0e0 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -12,6 +12,7 @@ #include <linux/falloc.h> #include <linux/iversion.h> #include <linux/ktime.h> +#include <linux/splice.h> #include "super.h" #include "mds_client.h" @@ -3010,8 +3011,8 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off, * {read,write}_iter, which will get caps again. */ put_rd_wr_caps(src_ci, src_got, dst_ci, dst_got); - ret = do_splice_direct(src_file, &src_off, dst_file, - &dst_off, src_objlen, flags); + ret = splice_file_range(src_file, &src_off, dst_file, &dst_off, + src_objlen); /* Abort on short copies or on error */ if (ret < (long)src_objlen) { doutc(cl, "Failed partial copy (%zd)\n", ret); @@ -3065,8 +3066,8 @@ out_caps: */ if (len && (len < src_ci->i_layout.object_size)) { doutc(cl, "Final partial copy of %zu bytes\n", len); - bytes = do_splice_direct(src_file, &src_off, dst_file, - &dst_off, len, flags); + bytes = splice_file_range(src_file, &src_off, dst_file, + &dst_off, len); if (bytes > 0) ret += bytes; else @@ -3089,8 +3090,8 @@ static ssize_t ceph_copy_file_range(struct file *src_file, loff_t src_off, len, flags); if (ret == -EOPNOTSUPP || ret == -EXDEV) - ret = generic_copy_file_range(src_file, src_off, dst_file, - dst_off, len, flags); + ret = splice_copy_file_range(src_file, src_off, dst_file, + dst_off, len); return ret; } diff --git a/fs/coda/file.c b/fs/coda/file.c index 16acc58311ea..148856a582a9 100644 --- a/fs/coda/file.c +++ b/fs/coda/file.c @@ -79,14 +79,12 @@ coda_file_write_iter(struct kiocb *iocb, struct iov_iter *to) if (ret) goto finish_write; - file_start_write(host_file); inode_lock(coda_inode); ret = vfs_iter_write(cfi->cfi_container, to, &iocb->ki_pos, 0); coda_inode->i_size = file_inode(host_file)->i_size; coda_inode->i_blocks = (coda_inode->i_size + 511) >> 9; inode_set_mtime_to_ts(coda_inode, inode_set_ctime_current(coda_inode)); inode_unlock(coda_inode); - file_end_write(host_file); finish_write: venus_access_intent(coda_inode->i_sb, coda_i2f(coda_inode), @@ -1128,7 +1128,7 @@ static int dax_iomap_copy_around(loff_t pos, uint64_t length, size_t align_size, /* zero the edges if srcmap is a HOLE or IOMAP_UNWRITTEN */ bool zero_edge = srcmap->flags & IOMAP_F_SHARED || srcmap->type == IOMAP_UNWRITTEN; - void *saddr = 0; + void *saddr = NULL; int ret = 0; if (!zero_edge) { diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index 5063434be0fc..6d7c1a49581f 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -104,12 +104,14 @@ int debugfs_file_get(struct dentry *dentry) ~DEBUGFS_FSDATA_IS_REAL_FOPS_BIT); refcount_set(&fsd->active_users, 1); init_completion(&fsd->active_users_drained); + INIT_LIST_HEAD(&fsd->cancellations); + mutex_init(&fsd->cancellations_mtx); + if (cmpxchg(&dentry->d_fsdata, d_fsd, fsd) != d_fsd) { + mutex_destroy(&fsd->cancellations_mtx); kfree(fsd); fsd = READ_ONCE(dentry->d_fsdata); } - INIT_LIST_HEAD(&fsd->cancellations); - mutex_init(&fsd->cancellations_mtx); } /* diff --git a/fs/direct-io.c b/fs/direct-io.c index 20533266ade6..60456263a338 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -1114,7 +1114,7 @@ ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, loff_t offset = iocb->ki_pos; const loff_t end = offset + count; struct dio *dio; - struct dio_submit sdio = { 0, }; + struct dio_submit sdio = { NULL, }; struct buffer_head map_bh = { 0, }; struct blk_plug plug; unsigned long align = offset | iov_iter_alignment(iter); diff --git a/fs/eventfd.c b/fs/eventfd.c index 33a918f9566c..ad8186d47ba7 100644 --- a/fs/eventfd.c +++ b/fs/eventfd.c @@ -43,7 +43,17 @@ struct eventfd_ctx { int id; }; -__u64 eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, __poll_t mask) +/** + * eventfd_signal_mask - Increment the event counter + * @ctx: [in] Pointer to the eventfd context. + * @mask: [in] poll mask + * + * This function is supposed to be called by the kernel in paths that do not + * allow sleeping. In this function we allow the counter to reach the ULLONG_MAX + * value, and we signal this as overflow condition by returning a EPOLLERR + * to poll(2). + */ +void eventfd_signal_mask(struct eventfd_ctx *ctx, __poll_t mask) { unsigned long flags; @@ -56,45 +66,23 @@ __u64 eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, __poll_t mask) * safe context. */ if (WARN_ON_ONCE(current->in_eventfd)) - return 0; + return; spin_lock_irqsave(&ctx->wqh.lock, flags); current->in_eventfd = 1; - if (ULLONG_MAX - ctx->count < n) - n = ULLONG_MAX - ctx->count; - ctx->count += n; + if (ctx->count < ULLONG_MAX) + ctx->count++; if (waitqueue_active(&ctx->wqh)) wake_up_locked_poll(&ctx->wqh, EPOLLIN | mask); current->in_eventfd = 0; spin_unlock_irqrestore(&ctx->wqh.lock, flags); - - return n; -} - -/** - * eventfd_signal - Adds @n to the eventfd counter. - * @ctx: [in] Pointer to the eventfd context. - * @n: [in] Value of the counter to be added to the eventfd internal counter. - * The value cannot be negative. - * - * This function is supposed to be called by the kernel in paths that do not - * allow sleeping. In this function we allow the counter to reach the ULLONG_MAX - * value, and we signal this as overflow condition by returning a EPOLLERR - * to poll(2). - * - * Returns the amount by which the counter was incremented. This will be less - * than @n if the counter has overflowed. - */ -__u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n) -{ - return eventfd_signal_mask(ctx, n, 0); } -EXPORT_SYMBOL_GPL(eventfd_signal); +EXPORT_SYMBOL_GPL(eventfd_signal_mask); static void eventfd_free_ctx(struct eventfd_ctx *ctx) { if (ctx->id >= 0) - ida_simple_remove(&eventfd_ida, ctx->id); + ida_free(&eventfd_ida, ctx->id); kfree(ctx); } @@ -407,7 +395,7 @@ static int do_eventfd(unsigned int count, int flags) init_waitqueue_head(&ctx->wqh); ctx->count = count; ctx->flags = flags; - ctx->id = ida_simple_get(&eventfd_ida, 0, 0, GFP_KERNEL); + ctx->id = ida_alloc(&eventfd_ida, GFP_KERNEL); flags &= EFD_SHARED_FCNTL_FLAGS; flags |= O_RDWR; diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 0166bb9ca160..6aa15dafc677 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -349,9 +349,10 @@ static void ext4_inode_extension_cleanup(struct inode *inode, ssize_t count) return; } /* - * If i_disksize got extended due to writeback of delalloc blocks while - * the DIO was running we could fail to cleanup the orphan list in - * ext4_handle_inode_extension(). Do it now. + * If i_disksize got extended either due to writeback of delalloc + * blocks or extending truncate while the DIO was running we could fail + * to cleanup the orphan list in ext4_handle_inode_extension(). Do it + * now. */ if (!list_empty(&EXT4_I(inode)->i_orphan) && inode->i_nlink) { handle_t *handle = ext4_journal_start(inode, EXT4_HT_INODE, 2); @@ -386,10 +387,11 @@ static int ext4_dio_write_end_io(struct kiocb *iocb, ssize_t size, * blocks. But the code in ext4_iomap_alloc() is careful to use * zeroed/unwritten extents if this is possible; thus we won't leave * uninitialized blocks in a file even if we didn't succeed in writing - * as much as we intended. + * as much as we intended. Also we can race with truncate or write + * expanding the file so we have to be a bit careful here. */ - WARN_ON_ONCE(i_size_read(inode) < READ_ONCE(EXT4_I(inode)->i_disksize)); - if (pos + size <= READ_ONCE(EXT4_I(inode)->i_disksize)) + if (pos + size <= READ_ONCE(EXT4_I(inode)->i_disksize) && + pos + size <= i_size_read(inode)) return size; return ext4_handle_inode_extension(inode, pos, size); } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 61277f7f8722..0558c8c986d4 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1261,7 +1261,7 @@ static int write_end_fn(handle_t *handle, struct inode *inode, * We need to pick up the new inode size which generic_commit_write gave us * `file' can be NULL - eg, when called from page_symlink(). * - * ext4 never places buffers on inode->i_mapping->private_list. metadata + * ext4 never places buffers on inode->i_mapping->i_private_list. metadata * buffers are managed internally. */ static int ext4_write_end(struct file *file, @@ -3213,7 +3213,7 @@ static bool ext4_inode_datasync_dirty(struct inode *inode) } /* Any metadata buffers to write? */ - if (!list_empty(&inode->i_mapping->private_list)) + if (!list_empty(&inode->i_mapping->i_private_list)) return true; return inode->i_state & I_DIRTY_DATASYNC; } diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 4f931f80cb34..aa6be510eb8f 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -819,11 +819,11 @@ int ext4_force_shutdown(struct super_block *sb, u32 flags) switch (flags) { case EXT4_GOING_FLAGS_DEFAULT: - ret = freeze_bdev(sb->s_bdev); + ret = bdev_freeze(sb->s_bdev); if (ret) return ret; set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags); - thaw_bdev(sb->s_bdev); + bdev_thaw(sb->s_bdev); break; case EXT4_GOING_FLAGS_LOGFLUSH: set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags); diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 454d5612641e..d72b5e3c92ec 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -4478,6 +4478,10 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac, start = max(start, rounddown(ac->ac_o_ex.fe_logical, (ext4_lblk_t)EXT4_BLOCKS_PER_GROUP(ac->ac_sb))); + /* avoid unnecessary preallocation that may trigger assertions */ + if (start + size > EXT_MAX_BLOCKS) + size = EXT_MAX_BLOCKS - start; + /* don't cover already allocated blocks in selected range */ if (ar->pleft && start <= ar->lleft) { size -= ar->lleft + 1 - start; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index c5fcf377ab1f..0980845c8b8f 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -5864,11 +5864,9 @@ static struct bdev_handle *ext4_get_journal_blkdev(struct super_block *sb, struct ext4_super_block *es; int errno; - /* see get_tree_bdev why this is needed and safe */ - up_write(&sb->s_umount); - bdev_handle = bdev_open_by_dev(j_dev, BLK_OPEN_READ | BLK_OPEN_WRITE, - sb, &fs_holder_ops); - down_write(&sb->s_umount); + bdev_handle = bdev_open_by_dev(j_dev, + BLK_OPEN_READ | BLK_OPEN_WRITE | BLK_OPEN_RESTRICT_WRITES, + sb, &fs_holder_ops); if (IS_ERR(bdev_handle)) { ext4_msg(sb, KERN_ERR, "failed to open journal device unknown-block(%u,%u) %ld", diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index e50363583f01..4580dfefd5e9 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -2239,11 +2239,11 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg) switch (in) { case F2FS_GOING_DOWN_FULLSYNC: - ret = freeze_bdev(sb->s_bdev); + ret = bdev_freeze(sb->s_bdev); if (ret) goto out; f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_SHUTDOWN); - thaw_bdev(sb->s_bdev); + bdev_thaw(sb->s_bdev); break; case F2FS_GOING_DOWN_METASYNC: /* do checkpoint only */ diff --git a/fs/file.c b/fs/file.c index 5fb0b146e79e..3b683b9101d8 100644 --- a/fs/file.c +++ b/fs/file.c @@ -629,19 +629,23 @@ void fd_install(unsigned int fd, struct file *file) EXPORT_SYMBOL(fd_install); /** - * pick_file - return file associatd with fd + * file_close_fd_locked - return file associated with fd * @files: file struct to retrieve file from * @fd: file descriptor to retrieve file for * + * Doesn't take a separate reference count. + * * Context: files_lock must be held. * * Returns: The file associated with @fd (NULL if @fd is not open) */ -static struct file *pick_file(struct files_struct *files, unsigned fd) +struct file *file_close_fd_locked(struct files_struct *files, unsigned fd) { struct fdtable *fdt = files_fdtable(files); struct file *file; + lockdep_assert_held(&files->file_lock); + if (fd >= fdt->max_fds) return NULL; @@ -660,7 +664,7 @@ int close_fd(unsigned fd) struct file *file; spin_lock(&files->file_lock); - file = pick_file(files, fd); + file = file_close_fd_locked(files, fd); spin_unlock(&files->file_lock); if (!file) return -EBADF; @@ -707,7 +711,7 @@ static inline void __range_close(struct files_struct *files, unsigned int fd, max_fd = min(max_fd, n); for (; fd <= max_fd; fd++) { - file = pick_file(files, fd); + file = file_close_fd_locked(files, fd); if (file) { spin_unlock(&files->file_lock); filp_close(file, files); @@ -795,26 +799,21 @@ int __close_range(unsigned fd, unsigned max_fd, unsigned int flags) return 0; } -/* - * See close_fd_get_file() below, this variant assumes current->files->file_lock - * is held. - */ -struct file *__close_fd_get_file(unsigned int fd) -{ - return pick_file(current->files, fd); -} - -/* - * variant of close_fd that gets a ref on the file for later fput. - * The caller must ensure that filp_close() called on the file. +/** + * file_close_fd - return file associated with fd + * @fd: file descriptor to retrieve file for + * + * Doesn't take a separate reference count. + * + * Returns: The file associated with @fd (NULL if @fd is not open) */ -struct file *close_fd_get_file(unsigned int fd) +struct file *file_close_fd(unsigned int fd) { struct files_struct *files = current->files; struct file *file; spin_lock(&files->file_lock); - file = pick_file(files, fd); + file = file_close_fd_locked(files, fd); spin_unlock(&files->file_lock); return file; @@ -959,31 +958,45 @@ static inline struct file *__fget_files_rcu(struct files_struct *files, struct file *file; struct fdtable *fdt = rcu_dereference_raw(files->fdt); struct file __rcu **fdentry; + unsigned long nospec_mask; - if (unlikely(fd >= fdt->max_fds)) - return NULL; - - fdentry = fdt->fd + array_index_nospec(fd, fdt->max_fds); + /* Mask is a 0 for invalid fd's, ~0 for valid ones */ + nospec_mask = array_index_mask_nospec(fd, fdt->max_fds); /* - * Ok, we have a file pointer. However, because we do - * this all locklessly under RCU, we may be racing with - * that file being closed. - * - * Such a race can take two forms: - * - * (a) the file ref already went down to zero and the - * file hasn't been reused yet or the file count - * isn't zero but the file has already been reused. + * fdentry points to the 'fd' offset, or fdt->fd[0]. + * Loading from fdt->fd[0] is always safe, because the + * array always exists. */ - file = __get_file_rcu(fdentry); + fdentry = fdt->fd + (fd & nospec_mask); + + /* Do the load, then mask any invalid result */ + file = rcu_dereference_raw(*fdentry); + file = (void *)(nospec_mask & (unsigned long)file); if (unlikely(!file)) return NULL; - if (unlikely(IS_ERR(file))) + /* + * Ok, we have a file pointer that was valid at + * some point, but it might have become stale since. + * + * We need to confirm it by incrementing the refcount + * and then check the lookup again. + * + * atomic_long_inc_not_zero() gives us a full memory + * barrier. We only really need an 'acquire' one to + * protect the loads below, but we don't have that. + */ + if (unlikely(!atomic_long_inc_not_zero(&file->f_count))) continue; /* + * Such a race can take two forms: + * + * (a) the file ref already went down to zero and the + * file hasn't been reused yet or the file count + * isn't zero but the file has already been reused. + * * (b) the file table entry has changed under us. * Note that we don't need to re-check the 'fdt->fd' * pointer having changed, because it always goes @@ -991,7 +1004,8 @@ static inline struct file *__fget_files_rcu(struct files_struct *files, * * If so, we need to put our ref and try again. */ - if (unlikely(rcu_dereference_raw(files->fdt) != fdt)) { + if (unlikely(file != rcu_dereference_raw(*fdentry)) || + unlikely(rcu_dereference_raw(files->fdt) != fdt)) { fput(file); continue; } @@ -1128,13 +1142,13 @@ static unsigned long __fget_light(unsigned int fd, fmode_t mask) * atomic_read_acquire() pairs with atomic_dec_and_test() in * put_files_struct(). */ - if (atomic_read_acquire(&files->count) == 1) { + if (likely(atomic_read_acquire(&files->count) == 1)) { file = files_lookup_fd_raw(files, fd); if (!file || unlikely(file->f_mode & mask)) return 0; return (unsigned long)file; } else { - file = __fget(fd, mask); + file = __fget_files(files, fd, mask); if (!file) return 0; return FDPUT_FPUT | (unsigned long)file; @@ -1282,7 +1296,7 @@ out_unlock: } /** - * __receive_fd() - Install received file into file descriptor table + * receive_fd() - Install received file into file descriptor table * @file: struct file that was received from another process * @ufd: __user pointer to write new fd number to * @o_flags: the O_* flags to apply to the new fd entry @@ -1296,7 +1310,7 @@ out_unlock: * * Returns newly install fd or -ve on error. */ -int __receive_fd(struct file *file, int __user *ufd, unsigned int o_flags) +int receive_fd(struct file *file, int __user *ufd, unsigned int o_flags) { int new_fd; int error; @@ -1321,6 +1335,7 @@ int __receive_fd(struct file *file, int __user *ufd, unsigned int o_flags) __receive_sock(file); return new_fd; } +EXPORT_SYMBOL_GPL(receive_fd); int receive_fd_replace(int new_fd, struct file *file, unsigned int o_flags) { @@ -1336,12 +1351,6 @@ int receive_fd_replace(int new_fd, struct file *file, unsigned int o_flags) return new_fd; } -int receive_fd(struct file *file, unsigned int o_flags) -{ - return __receive_fd(file, NULL, o_flags); -} -EXPORT_SYMBOL_GPL(receive_fd); - static int ksys_dup3(unsigned int oldfd, unsigned int newfd, int flags) { int err = -EBADF; diff --git a/fs/file_table.c b/fs/file_table.c index de4a2915bfd4..3ba764d73fc9 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -75,18 +75,6 @@ static inline void file_free(struct file *f) } } -void release_empty_file(struct file *f) -{ - WARN_ON_ONCE(f->f_mode & (FMODE_BACKING | FMODE_OPENED)); - if (atomic_long_dec_and_test(&f->f_count)) { - security_file_free(f); - put_cred(f->f_cred); - if (likely(!(f->f_mode & FMODE_NOACCOUNT))) - percpu_counter_dec(&nr_files); - kmem_cache_free(filp_cachep, f); - } -} - /* * Return the total number of open files in the system */ @@ -419,7 +407,7 @@ static void delayed_fput(struct work_struct *unused) static void ____fput(struct callback_head *work) { - __fput(container_of(work, struct file, f_rcuhead)); + __fput(container_of(work, struct file, f_task_work)); } /* @@ -445,9 +433,13 @@ void fput(struct file *file) if (atomic_long_dec_and_test(&file->f_count)) { struct task_struct *task = current; + if (unlikely(!(file->f_mode & (FMODE_BACKING | FMODE_OPENED)))) { + file_free(file); + return; + } if (likely(!in_interrupt() && !(task->flags & PF_KTHREAD))) { - init_task_work(&file->f_rcuhead, ____fput); - if (!task_work_add(task, &file->f_rcuhead, TWA_RESUME)) + init_task_work(&file->f_task_work, ____fput); + if (!task_work_add(task, &file->f_task_work, TWA_RESUME)) return; /* * After this task has run exit_task_work(), diff --git a/fs/fuse/dax.c b/fs/fuse/dax.c index 23904a6a9a96..12ef91d170bb 100644 --- a/fs/fuse/dax.c +++ b/fs/fuse/dax.c @@ -1222,6 +1222,7 @@ void fuse_dax_conn_free(struct fuse_conn *fc) if (fc->dax) { fuse_free_dax_mem_ranges(&fc->dax->free_ranges); kfree(fc->dax); + fc->dax = NULL; } } diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 1cdb6327511e..148a71b8b4d0 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -19,6 +19,7 @@ #include <linux/uio.h> #include <linux/fs.h> #include <linux/filelock.h> +#include <linux/splice.h> static int fuse_send_open(struct fuse_mount *fm, u64 nodeid, unsigned int open_flags, int opcode, @@ -1448,7 +1449,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter, if (!ia) return -ENOMEM; - if (fopen_direct_io && fc->direct_io_relax) { + if (fopen_direct_io && fc->direct_io_allow_mmap) { res = filemap_write_and_wait_range(mapping, pos, pos + count - 1); if (res) { fuse_io_free(ia); @@ -1574,6 +1575,7 @@ static ssize_t fuse_direct_write_iter(struct kiocb *iocb, struct iov_iter *from) ssize_t res; bool exclusive_lock = !(ff->open_flags & FOPEN_PARALLEL_DIRECT_WRITES) || + get_fuse_conn(inode)->direct_io_allow_mmap || iocb->ki_flags & IOCB_APPEND || fuse_direct_write_extending_i_size(iocb, from); @@ -1581,6 +1583,7 @@ static ssize_t fuse_direct_write_iter(struct kiocb *iocb, struct iov_iter *from) * Take exclusive lock if * - Parallel direct writes are disabled - a user space decision * - Parallel direct writes are enabled and i_size is being extended. + * - Shared mmap on direct_io file is supported (FUSE_DIRECT_IO_ALLOW_MMAP). * This might not be needed at all, but needs further investigation. */ if (exclusive_lock) @@ -2466,9 +2469,9 @@ static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma) if (ff->open_flags & FOPEN_DIRECT_IO) { /* Can't provide the coherency needed for MAP_SHARED - * if FUSE_DIRECT_IO_RELAX isn't set. + * if FUSE_DIRECT_IO_ALLOW_MMAP isn't set. */ - if ((vma->vm_flags & VM_MAYSHARE) && !fc->direct_io_relax) + if ((vma->vm_flags & VM_MAYSHARE) && !fc->direct_io_allow_mmap) return -ENODEV; invalidate_inode_pages2(file->f_mapping); @@ -3193,8 +3196,8 @@ static ssize_t fuse_copy_file_range(struct file *src_file, loff_t src_off, len, flags); if (ret == -EOPNOTSUPP || ret == -EXDEV) - ret = generic_copy_file_range(src_file, src_off, dst_file, - dst_off, len, flags); + ret = splice_copy_file_range(src_file, src_off, dst_file, + dst_off, len); return ret; } diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 6e6e721f421b..1df83eebda92 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -63,6 +63,19 @@ struct fuse_forget_link { struct fuse_forget_link *next; }; +/* Submount lookup tracking */ +struct fuse_submount_lookup { + /** Refcount */ + refcount_t count; + + /** Unique ID, which identifies the inode between userspace + * and kernel */ + u64 nodeid; + + /** The request used for sending the FORGET message */ + struct fuse_forget_link *forget; +}; + /** FUSE inode */ struct fuse_inode { /** Inode data */ @@ -158,6 +171,8 @@ struct fuse_inode { */ struct fuse_inode_dax *dax; #endif + /** Submount specific lookup tracking */ + struct fuse_submount_lookup *submount_lookup; }; /** FUSE inode state bits */ @@ -797,8 +812,8 @@ struct fuse_conn { /* Is tmpfile not implemented by fs? */ unsigned int no_tmpfile:1; - /* relax restrictions in FOPEN_DIRECT_IO mode */ - unsigned int direct_io_relax:1; + /* Relax restrictions to allow shared mmap in FOPEN_DIRECT_IO mode */ + unsigned int direct_io_allow_mmap:1; /* Is statx not implemented by fs? */ unsigned int no_statx:1; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 74d4f09d5827..2a6d44f91729 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -68,6 +68,24 @@ struct fuse_forget_link *fuse_alloc_forget(void) return kzalloc(sizeof(struct fuse_forget_link), GFP_KERNEL_ACCOUNT); } +static struct fuse_submount_lookup *fuse_alloc_submount_lookup(void) +{ + struct fuse_submount_lookup *sl; + + sl = kzalloc(sizeof(struct fuse_submount_lookup), GFP_KERNEL_ACCOUNT); + if (!sl) + return NULL; + sl->forget = fuse_alloc_forget(); + if (!sl->forget) + goto out_free; + + return sl; + +out_free: + kfree(sl); + return NULL; +} + static struct inode *fuse_alloc_inode(struct super_block *sb) { struct fuse_inode *fi; @@ -83,6 +101,7 @@ static struct inode *fuse_alloc_inode(struct super_block *sb) fi->attr_version = 0; fi->orig_ino = 0; fi->state = 0; + fi->submount_lookup = NULL; mutex_init(&fi->mutex); spin_lock_init(&fi->lock); fi->forget = fuse_alloc_forget(); @@ -113,6 +132,17 @@ static void fuse_free_inode(struct inode *inode) kmem_cache_free(fuse_inode_cachep, fi); } +static void fuse_cleanup_submount_lookup(struct fuse_conn *fc, + struct fuse_submount_lookup *sl) +{ + if (!refcount_dec_and_test(&sl->count)) + return; + + fuse_queue_forget(fc, sl->forget, sl->nodeid, 1); + sl->forget = NULL; + kfree(sl); +} + static void fuse_evict_inode(struct inode *inode) { struct fuse_inode *fi = get_fuse_inode(inode); @@ -132,6 +162,11 @@ static void fuse_evict_inode(struct inode *inode) fi->nlookup); fi->forget = NULL; } + + if (fi->submount_lookup) { + fuse_cleanup_submount_lookup(fc, fi->submount_lookup); + fi->submount_lookup = NULL; + } } if (S_ISREG(inode->i_mode) && !fuse_is_bad(inode)) { WARN_ON(!list_empty(&fi->write_files)); @@ -330,6 +365,13 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr, fuse_dax_dontcache(inode, attr->flags); } +static void fuse_init_submount_lookup(struct fuse_submount_lookup *sl, + u64 nodeid) +{ + sl->nodeid = nodeid; + refcount_set(&sl->count, 1); +} + static void fuse_init_inode(struct inode *inode, struct fuse_attr *attr, struct fuse_conn *fc) { @@ -392,12 +434,22 @@ struct inode *fuse_iget(struct super_block *sb, u64 nodeid, */ if (fc->auto_submounts && (attr->flags & FUSE_ATTR_SUBMOUNT) && S_ISDIR(attr->mode)) { + struct fuse_inode *fi; + inode = new_inode(sb); if (!inode) return NULL; fuse_init_inode(inode, attr, fc); - get_fuse_inode(inode)->nodeid = nodeid; + fi = get_fuse_inode(inode); + fi->nodeid = nodeid; + fi->submount_lookup = fuse_alloc_submount_lookup(); + if (!fi->submount_lookup) { + iput(inode); + return NULL; + } + /* Sets nlookup = 1 on fi->submount_lookup->nlookup */ + fuse_init_submount_lookup(fi->submount_lookup, nodeid); inode->i_flags |= S_AUTOMOUNT; goto done; } @@ -420,11 +472,11 @@ retry: iput(inode); goto retry; } -done: fi = get_fuse_inode(inode); spin_lock(&fi->lock); fi->nlookup++; spin_unlock(&fi->lock); +done: fuse_change_attributes(inode, attr, NULL, attr_valid, attr_version); return inode; @@ -1230,8 +1282,8 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args, fc->init_security = 1; if (flags & FUSE_CREATE_SUPP_GROUP) fc->create_supp_group = 1; - if (flags & FUSE_DIRECT_IO_RELAX) - fc->direct_io_relax = 1; + if (flags & FUSE_DIRECT_IO_ALLOW_MMAP) + fc->direct_io_allow_mmap = 1; } else { ra_pages = fc->max_read / PAGE_SIZE; fc->no_lock = 1; @@ -1278,7 +1330,7 @@ void fuse_send_init(struct fuse_mount *fm) FUSE_NO_OPENDIR_SUPPORT | FUSE_EXPLICIT_INVAL_DATA | FUSE_HANDLE_KILLPRIV_V2 | FUSE_SETXATTR_EXT | FUSE_INIT_EXT | FUSE_SECURITY_CTX | FUSE_CREATE_SUPP_GROUP | - FUSE_HAS_EXPIRE_ONLY | FUSE_DIRECT_IO_RELAX; + FUSE_HAS_EXPIRE_ONLY | FUSE_DIRECT_IO_ALLOW_MMAP; #ifdef CONFIG_FUSE_DAX if (fm->fc->dax) flags |= FUSE_MAP_ALIGNMENT; @@ -1465,6 +1517,8 @@ static int fuse_fill_super_submount(struct super_block *sb, struct super_block *parent_sb = parent_fi->inode.i_sb; struct fuse_attr root_attr; struct inode *root; + struct fuse_submount_lookup *sl; + struct fuse_inode *fi; fuse_sb_defaults(sb); fm->sb = sb; @@ -1487,12 +1541,27 @@ static int fuse_fill_super_submount(struct super_block *sb, * its nlookup should not be incremented. fuse_iget() does * that, though, so undo it here. */ - get_fuse_inode(root)->nlookup--; + fi = get_fuse_inode(root); + fi->nlookup--; + sb->s_d_op = &fuse_dentry_operations; sb->s_root = d_make_root(root); if (!sb->s_root) return -ENOMEM; + /* + * Grab the parent's submount_lookup pointer and take a + * reference on the shared nlookup from the parent. This is to + * prevent the last forget for this nodeid from getting + * triggered until all users have finished with it. + */ + sl = parent_fi->submount_lookup; + WARN_ON(!sl); + if (sl) { + refcount_inc(&sl->count); + fi->submount_lookup = sl; + } + return 0; } diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index d6bf1f8c25dc..d8b619ed2f1e 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -1213,7 +1213,7 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number, mapping->host = s->s_bdev->bd_inode; mapping->flags = 0; mapping_set_gfp_mask(mapping, GFP_NOFS); - mapping->private_data = NULL; + mapping->i_private_data = NULL; mapping->writeback_index = 0; } diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index b108c5d26839..00ce89bdf32c 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -117,7 +117,7 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb) mapping->host = sb->s_bdev->bd_inode; mapping->flags = 0; mapping_set_gfp_mask(mapping, GFP_NOFS); - mapping->private_data = NULL; + mapping->i_private_data = NULL; mapping->writeback_index = 0; spin_lock_init(&sdp->sd_log_lock); diff --git a/fs/hfsplus/wrapper.c b/fs/hfsplus/wrapper.c index 0b791adf02e5..b0cb70400996 100644 --- a/fs/hfsplus/wrapper.c +++ b/fs/hfsplus/wrapper.c @@ -30,8 +30,7 @@ struct hfsplus_wd { * @sector: block to read or write, for blocks of HFSPLUS_SECTOR_SIZE bytes * @buf: buffer for I/O * @data: output pointer for location of requested data - * @op: direction of I/O - * @op_flags: request op flags + * @opf: request op flags * * The unit of I/O is hfsplus_min_io_size(sb), which may be bigger than * HFSPLUS_SECTOR_SIZE, and @buf must be sized accordingly. On reads @@ -43,6 +42,8 @@ struct hfsplus_wd { * that starts at the rounded-down address. As long as the data was * read using hfsplus_submit_bio() and the same buffer is used things * will work correctly. + * + * Returns: %0 on success else -errno code */ int hfsplus_submit_bio(struct super_block *sb, sector_t sector, void *buf, void **data, blk_opf_t opf) diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index f757d4f7ad98..05609ab15cbc 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -686,7 +686,7 @@ static void hugetlbfs_evict_inode(struct inode *inode) * at inode creation time. If this is a device special inode, * i_mapping may not point to the original address space. */ - resv_map = (struct resv_map *)(&inode->i_data)->private_data; + resv_map = (struct resv_map *)(&inode->i_data)->i_private_data; /* Only regular and link inodes have associated reserve maps */ if (resv_map) resv_map_release(&resv_map->refs); @@ -1000,7 +1000,7 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, &hugetlbfs_i_mmap_rwsem_key); inode->i_mapping->a_ops = &hugetlbfs_aops; simple_inode_init_ts(inode); - inode->i_mapping->private_data = resv_map; + inode->i_mapping->i_private_data = resv_map; info->seals = F_SEAL_SEAL; switch (mode & S_IFMT) { default: diff --git a/fs/inode.c b/fs/inode.c index f238d987dec9..6cdb017f45c6 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -209,7 +209,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode) atomic_set(&mapping->nr_thps, 0); #endif mapping_set_gfp_mask(mapping, GFP_HIGHUSER_MOVABLE); - mapping->private_data = NULL; + mapping->i_private_data = NULL; mapping->writeback_index = 0; init_rwsem(&mapping->invalidate_lock); lockdep_set_class_and_name(&mapping->invalidate_lock, @@ -398,8 +398,8 @@ static void __address_space_init_once(struct address_space *mapping) { xa_init_flags(&mapping->i_pages, XA_FLAGS_LOCK_IRQ | XA_FLAGS_ACCOUNT); init_rwsem(&mapping->i_mmap_rwsem); - INIT_LIST_HEAD(&mapping->private_list); - spin_lock_init(&mapping->private_lock); + INIT_LIST_HEAD(&mapping->i_private_list); + spin_lock_init(&mapping->i_private_lock); mapping->i_mmap = RB_ROOT_CACHED; } @@ -620,7 +620,7 @@ void clear_inode(struct inode *inode) * nor even WARN_ON(!mapping_empty). */ xa_unlock_irq(&inode->i_data.i_pages); - BUG_ON(!list_empty(&inode->i_data.private_list)); + BUG_ON(!list_empty(&inode->i_data.i_private_list)); BUG_ON(!(inode->i_state & I_FREEING)); BUG_ON(inode->i_state & I_CLEAR); BUG_ON(!list_empty(&inode->i_wb_list)); @@ -1836,37 +1836,37 @@ EXPORT_SYMBOL(bmap); * earlier than or equal to either the ctime or mtime, * or if at least a day has passed since the last atime update. */ -static int relatime_need_update(struct vfsmount *mnt, struct inode *inode, +static bool relatime_need_update(struct vfsmount *mnt, struct inode *inode, struct timespec64 now) { struct timespec64 atime, mtime, ctime; if (!(mnt->mnt_flags & MNT_RELATIME)) - return 1; + return true; /* * Is mtime younger than or equal to atime? If yes, update atime: */ atime = inode_get_atime(inode); mtime = inode_get_mtime(inode); if (timespec64_compare(&mtime, &atime) >= 0) - return 1; + return true; /* * Is ctime younger than or equal to atime? If yes, update atime: */ ctime = inode_get_ctime(inode); if (timespec64_compare(&ctime, &atime) >= 0) - return 1; + return true; /* * Is the previous atime value older than a day? If yes, * update atime: */ if ((long)(now.tv_sec - atime.tv_sec) >= 24*60*60) - return 1; + return true; /* * Good, we can skip the atime update: */ - return 0; + return false; } /** @@ -2404,7 +2404,7 @@ EXPORT_SYMBOL(inode_init_owner); * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the - * raw inode simply passs @nop_mnt_idmap. + * raw inode simply pass @nop_mnt_idmap. */ bool inode_owner_or_capable(struct mnt_idmap *idmap, const struct inode *inode) diff --git a/fs/internal.h b/fs/internal.h index 58e43341aebf..bf2ee2e0d45d 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -83,6 +83,8 @@ int path_mount(const char *dev_name, struct path *path, const char *type_page, unsigned long flags, void *data_page); int path_umount(struct path *path, int flags); +int show_path(struct seq_file *m, struct dentry *root); + /* * fs_struct.c */ @@ -94,7 +96,6 @@ extern void chroot_fs_refs(const struct path *, const struct path *); struct file *alloc_empty_file(int flags, const struct cred *cred); struct file *alloc_empty_file_noaccount(int flags, const struct cred *cred); struct file *alloc_empty_backing_file(int flags, const struct cred *cred); -void release_empty_file(struct file *f); static inline void file_put_write_access(struct file *file) { @@ -180,7 +181,7 @@ extern struct file *do_file_open_root(const struct path *, const char *, const struct open_flags *); extern struct open_how build_open_how(int flags, umode_t mode); extern int build_open_flags(const struct open_how *how, struct open_flags *op); -extern struct file *__close_fd_get_file(unsigned int fd); +struct file *file_close_fd_locked(struct files_struct *files, unsigned fd); long do_sys_ftruncate(unsigned int fd, loff_t length, int small); int chmod_common(const struct path *path, umode_t mode); @@ -243,10 +244,10 @@ int do_statx(int dfd, struct filename *filename, unsigned int flags, /* * fs/splice.c: */ -long splice_file_to_pipe(struct file *in, - struct pipe_inode_info *opipe, - loff_t *offset, - size_t len, unsigned int flags); +ssize_t splice_file_to_pipe(struct file *in, + struct pipe_inode_info *opipe, + loff_t *offset, + size_t len, unsigned int flags); /* * fs/xattr.c: diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 8d6f934c3d95..5e122586e06e 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -119,7 +119,7 @@ static int journal_submit_commit_record(journal_t *journal, struct commit_header *tmp; struct buffer_head *bh; struct timespec64 now; - blk_opf_t write_flags = REQ_OP_WRITE | REQ_SYNC; + blk_opf_t write_flags = REQ_OP_WRITE | JBD2_JOURNAL_REQ_FLAGS; *cbh = NULL; @@ -270,6 +270,7 @@ static int journal_finish_inode_data_buffers(journal_t *journal, if (!ret) ret = err; } + cond_resched(); spin_lock(&journal->j_list_lock); jinode->i_flags &= ~JI_COMMIT_RUNNING; smp_mb(); @@ -395,8 +396,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) */ jbd2_journal_update_sb_log_tail(journal, journal->j_tail_sequence, - journal->j_tail, - REQ_SYNC); + journal->j_tail, 0); mutex_unlock(&journal->j_checkpoint_mutex); } else { jbd2_debug(3, "superblock not updated\n"); @@ -715,6 +715,7 @@ start_journal_io: for (i = 0; i < bufs; i++) { struct buffer_head *bh = wbuf[i]; + /* * Compute checksum. */ @@ -727,7 +728,8 @@ start_journal_io: clear_buffer_dirty(bh); set_buffer_uptodate(bh); bh->b_end_io = journal_end_buffer_io_sync; - submit_bh(REQ_OP_WRITE | REQ_SYNC, bh); + submit_bh(REQ_OP_WRITE | JBD2_JOURNAL_REQ_FLAGS, + bh); } cond_resched(); diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index ed53188472f9..206cb53ef2b0 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1100,8 +1100,7 @@ int __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block) * space and if we lose sb update during power failure we'd replay * old transaction with possibly newly overwritten data. */ - ret = jbd2_journal_update_sb_log_tail(journal, tid, block, - REQ_SYNC | REQ_FUA); + ret = jbd2_journal_update_sb_log_tail(journal, tid, block, REQ_FUA); if (ret) goto out; @@ -1775,8 +1774,7 @@ static int journal_reset(journal_t *journal) */ jbd2_journal_update_sb_log_tail(journal, journal->j_tail_sequence, - journal->j_tail, - REQ_SYNC | REQ_FUA); + journal->j_tail, REQ_FUA); mutex_unlock(&journal->j_checkpoint_mutex); } return jbd2_journal_start_thread(journal); @@ -1798,9 +1796,16 @@ static int jbd2_write_superblock(journal_t *journal, blk_opf_t write_flags) return -EIO; } - trace_jbd2_write_superblock(journal, write_flags); + /* + * Always set high priority flags to exempt from block layer's + * QOS policies, e.g. writeback throttle. + */ + write_flags |= JBD2_JOURNAL_REQ_FLAGS; if (!(journal->j_flags & JBD2_BARRIER)) write_flags &= ~(REQ_FUA | REQ_PREFLUSH); + + trace_jbd2_write_superblock(journal, write_flags); + if (buffer_write_io_error(bh)) { /* * Oh, dear. A previous attempt to write the journal @@ -2050,7 +2055,7 @@ void jbd2_journal_update_sb_errno(journal_t *journal) jbd2_debug(1, "JBD2: updating superblock error (errno %d)\n", errcode); sb->s_errno = cpu_to_be32(errcode); - jbd2_write_superblock(journal, REQ_SYNC | REQ_FUA); + jbd2_write_superblock(journal, REQ_FUA); } EXPORT_SYMBOL(jbd2_journal_update_sb_errno); @@ -2171,8 +2176,7 @@ int jbd2_journal_destroy(journal_t *journal) ++journal->j_transaction_sequence; write_unlock(&journal->j_state_lock); - jbd2_mark_journal_empty(journal, - REQ_SYNC | REQ_PREFLUSH | REQ_FUA); + jbd2_mark_journal_empty(journal, REQ_PREFLUSH | REQ_FUA); mutex_unlock(&journal->j_checkpoint_mutex); } else err = -EIO; @@ -2473,7 +2477,7 @@ int jbd2_journal_flush(journal_t *journal, unsigned int flags) * the magic code for a fully-recovered superblock. Any future * commits of data to the journal will restore the current * s_start value. */ - jbd2_mark_journal_empty(journal, REQ_SYNC | REQ_FUA); + jbd2_mark_journal_empty(journal, REQ_FUA); if (flags) err = __jbd2_journal_erase(journal, flags); @@ -2519,7 +2523,7 @@ int jbd2_journal_wipe(journal_t *journal, int write) if (write) { /* Lock to make assertions happy... */ mutex_lock_io(&journal->j_checkpoint_mutex); - jbd2_mark_journal_empty(journal, REQ_SYNC | REQ_FUA); + jbd2_mark_journal_empty(journal, REQ_FUA); mutex_unlock(&journal->j_checkpoint_mutex); } diff --git a/fs/mnt_idmapping.c b/fs/mnt_idmapping.c index 57d1dedf3f8f..64c5205e2b5e 100644 --- a/fs/mnt_idmapping.c +++ b/fs/mnt_idmapping.c @@ -9,8 +9,16 @@ #include "internal.h" +/* + * Outside of this file vfs{g,u}id_t are always created from k{g,u}id_t, + * never from raw values. These are just internal helpers. + */ +#define VFSUIDT_INIT_RAW(val) (vfsuid_t){ val } +#define VFSGIDT_INIT_RAW(val) (vfsgid_t){ val } + struct mnt_idmap { - struct user_namespace *owner; + struct uid_gid_map uid_map; + struct uid_gid_map gid_map; refcount_t count; }; @@ -20,25 +28,11 @@ struct mnt_idmap { * mapped to {g,u}id 1, [...], {g,u}id 1000 to {g,u}id 1000, [...]. */ struct mnt_idmap nop_mnt_idmap = { - .owner = &init_user_ns, .count = REFCOUNT_INIT(1), }; EXPORT_SYMBOL_GPL(nop_mnt_idmap); /** - * check_fsmapping - check whether an mount idmapping is allowed - * @idmap: idmap of the relevent mount - * @sb: super block of the filesystem - * - * Return: true if @idmap is allowed, false if not. - */ -bool check_fsmapping(const struct mnt_idmap *idmap, - const struct super_block *sb) -{ - return idmap->owner != sb->s_user_ns; -} - -/** * initial_idmapping - check whether this is the initial mapping * @ns: idmapping to check * @@ -53,26 +47,6 @@ static inline bool initial_idmapping(const struct user_namespace *ns) } /** - * no_idmapping - check whether we can skip remapping a kuid/gid - * @mnt_userns: the mount's idmapping - * @fs_userns: the filesystem's idmapping - * - * This function can be used to check whether a remapping between two - * idmappings is required. - * An idmapped mount is a mount that has an idmapping attached to it that - * is different from the filsystem's idmapping and the initial idmapping. - * If the initial mapping is used or the idmapping of the mount and the - * filesystem are identical no remapping is required. - * - * Return: true if remapping can be skipped, false if not. - */ -static inline bool no_idmapping(const struct user_namespace *mnt_userns, - const struct user_namespace *fs_userns) -{ - return initial_idmapping(mnt_userns) || mnt_userns == fs_userns; -} - -/** * make_vfsuid - map a filesystem kuid according to an idmapping * @idmap: the mount's idmapping * @fs_userns: the filesystem's idmapping @@ -81,8 +55,8 @@ static inline bool no_idmapping(const struct user_namespace *mnt_userns, * Take a @kuid and remap it from @fs_userns into @idmap. Use this * function when preparing a @kuid to be reported to userspace. * - * If no_idmapping() determines that this is not an idmapped mount we can - * simply return @kuid unchanged. + * If initial_idmapping() determines that this is not an idmapped mount + * we can simply return @kuid unchanged. * If initial_idmapping() tells us that the filesystem is not mounted with an * idmapping we know the value of @kuid won't change when calling * from_kuid() so we can simply retrieve the value via __kuid_val() @@ -94,13 +68,12 @@ static inline bool no_idmapping(const struct user_namespace *mnt_userns, */ vfsuid_t make_vfsuid(struct mnt_idmap *idmap, - struct user_namespace *fs_userns, - kuid_t kuid) + struct user_namespace *fs_userns, + kuid_t kuid) { uid_t uid; - struct user_namespace *mnt_userns = idmap->owner; - if (no_idmapping(mnt_userns, fs_userns)) + if (idmap == &nop_mnt_idmap) return VFSUIDT_INIT(kuid); if (initial_idmapping(fs_userns)) uid = __kuid_val(kuid); @@ -108,7 +81,7 @@ vfsuid_t make_vfsuid(struct mnt_idmap *idmap, uid = from_kuid(fs_userns, kuid); if (uid == (uid_t)-1) return INVALID_VFSUID; - return VFSUIDT_INIT(make_kuid(mnt_userns, uid)); + return VFSUIDT_INIT_RAW(map_id_down(&idmap->uid_map, uid)); } EXPORT_SYMBOL_GPL(make_vfsuid); @@ -121,8 +94,8 @@ EXPORT_SYMBOL_GPL(make_vfsuid); * Take a @kgid and remap it from @fs_userns into @idmap. Use this * function when preparing a @kgid to be reported to userspace. * - * If no_idmapping() determines that this is not an idmapped mount we can - * simply return @kgid unchanged. + * If initial_idmapping() determines that this is not an idmapped mount + * we can simply return @kgid unchanged. * If initial_idmapping() tells us that the filesystem is not mounted with an * idmapping we know the value of @kgid won't change when calling * from_kgid() so we can simply retrieve the value via __kgid_val() @@ -136,9 +109,8 @@ vfsgid_t make_vfsgid(struct mnt_idmap *idmap, struct user_namespace *fs_userns, kgid_t kgid) { gid_t gid; - struct user_namespace *mnt_userns = idmap->owner; - if (no_idmapping(mnt_userns, fs_userns)) + if (idmap == &nop_mnt_idmap) return VFSGIDT_INIT(kgid); if (initial_idmapping(fs_userns)) gid = __kgid_val(kgid); @@ -146,7 +118,7 @@ vfsgid_t make_vfsgid(struct mnt_idmap *idmap, gid = from_kgid(fs_userns, kgid); if (gid == (gid_t)-1) return INVALID_VFSGID; - return VFSGIDT_INIT(make_kgid(mnt_userns, gid)); + return VFSGIDT_INIT_RAW(map_id_down(&idmap->gid_map, gid)); } EXPORT_SYMBOL_GPL(make_vfsgid); @@ -165,11 +137,10 @@ kuid_t from_vfsuid(struct mnt_idmap *idmap, struct user_namespace *fs_userns, vfsuid_t vfsuid) { uid_t uid; - struct user_namespace *mnt_userns = idmap->owner; - if (no_idmapping(mnt_userns, fs_userns)) + if (idmap == &nop_mnt_idmap) return AS_KUIDT(vfsuid); - uid = from_kuid(mnt_userns, AS_KUIDT(vfsuid)); + uid = map_id_up(&idmap->uid_map, __vfsuid_val(vfsuid)); if (uid == (uid_t)-1) return INVALID_UID; if (initial_idmapping(fs_userns)) @@ -193,11 +164,10 @@ kgid_t from_vfsgid(struct mnt_idmap *idmap, struct user_namespace *fs_userns, vfsgid_t vfsgid) { gid_t gid; - struct user_namespace *mnt_userns = idmap->owner; - if (no_idmapping(mnt_userns, fs_userns)) + if (idmap == &nop_mnt_idmap) return AS_KGIDT(vfsgid); - gid = from_kgid(mnt_userns, AS_KGIDT(vfsgid)); + gid = map_id_up(&idmap->gid_map, __vfsgid_val(vfsgid)); if (gid == (gid_t)-1) return INVALID_GID; if (initial_idmapping(fs_userns)) @@ -228,16 +198,91 @@ int vfsgid_in_group_p(vfsgid_t vfsgid) #endif EXPORT_SYMBOL_GPL(vfsgid_in_group_p); +static int copy_mnt_idmap(struct uid_gid_map *map_from, + struct uid_gid_map *map_to) +{ + struct uid_gid_extent *forward, *reverse; + u32 nr_extents = READ_ONCE(map_from->nr_extents); + /* Pairs with smp_wmb() when writing the idmapping. */ + smp_rmb(); + + /* + * Don't blindly copy @map_to into @map_from if nr_extents is + * smaller or equal to UID_GID_MAP_MAX_BASE_EXTENTS. Since we + * read @nr_extents someone could have written an idmapping and + * then we might end up with inconsistent data. So just don't do + * anything at all. + */ + if (nr_extents == 0) + return 0; + + /* + * Here we know that nr_extents is greater than zero which means + * a map has been written. Since idmappings can't be changed + * once they have been written we know that we can safely copy + * from @map_to into @map_from. + */ + + if (nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) { + *map_to = *map_from; + return 0; + } + + forward = kmemdup(map_from->forward, + nr_extents * sizeof(struct uid_gid_extent), + GFP_KERNEL_ACCOUNT); + if (!forward) + return -ENOMEM; + + reverse = kmemdup(map_from->reverse, + nr_extents * sizeof(struct uid_gid_extent), + GFP_KERNEL_ACCOUNT); + if (!reverse) { + kfree(forward); + return -ENOMEM; + } + + /* + * The idmapping isn't exposed anywhere so we don't need to care + * about ordering between extent pointers and @nr_extents + * initialization. + */ + map_to->forward = forward; + map_to->reverse = reverse; + map_to->nr_extents = nr_extents; + return 0; +} + +static void free_mnt_idmap(struct mnt_idmap *idmap) +{ + if (idmap->uid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) { + kfree(idmap->uid_map.forward); + kfree(idmap->uid_map.reverse); + } + if (idmap->gid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) { + kfree(idmap->gid_map.forward); + kfree(idmap->gid_map.reverse); + } + kfree(idmap); +} + struct mnt_idmap *alloc_mnt_idmap(struct user_namespace *mnt_userns) { struct mnt_idmap *idmap; + int ret; idmap = kzalloc(sizeof(struct mnt_idmap), GFP_KERNEL_ACCOUNT); if (!idmap) return ERR_PTR(-ENOMEM); - idmap->owner = get_user_ns(mnt_userns); refcount_set(&idmap->count, 1); + ret = copy_mnt_idmap(&mnt_userns->uid_map, &idmap->uid_map); + if (!ret) + ret = copy_mnt_idmap(&mnt_userns->gid_map, &idmap->gid_map); + if (ret) { + free_mnt_idmap(idmap); + idmap = ERR_PTR(ret); + } return idmap; } @@ -267,9 +312,7 @@ EXPORT_SYMBOL_GPL(mnt_idmap_get); */ void mnt_idmap_put(struct mnt_idmap *idmap) { - if (idmap != &nop_mnt_idmap && refcount_dec_and_test(&idmap->count)) { - put_user_ns(idmap->owner); - kfree(idmap); - } + if (idmap != &nop_mnt_idmap && refcount_dec_and_test(&idmap->count)) + free_mnt_idmap(idmap); } EXPORT_SYMBOL_GPL(mnt_idmap_put); diff --git a/fs/mount.h b/fs/mount.h index 130c07c2f8d2..4a42fc68f4cc 100644 --- a/fs/mount.h +++ b/fs/mount.h @@ -8,19 +8,13 @@ struct mnt_namespace { struct ns_common ns; struct mount * root; - /* - * Traversal and modification of .list is protected by either - * - taking namespace_sem for write, OR - * - taking namespace_sem for read AND taking .ns_lock. - */ - struct list_head list; - spinlock_t ns_lock; + struct rb_root mounts; /* Protected by namespace_sem */ struct user_namespace *user_ns; struct ucounts *ucounts; u64 seq; /* Sequence number to prevent loops */ wait_queue_head_t poll; u64 event; - unsigned int mounts; /* # of mounts in the namespace */ + unsigned int nr_mounts; /* # of mounts in the namespace */ unsigned int pending_mounts; } __randomize_layout; @@ -55,7 +49,10 @@ struct mount { struct list_head mnt_child; /* and going through their mnt_child */ struct list_head mnt_instance; /* mount instance on sb->s_mounts */ const char *mnt_devname; /* Name of device e.g. /dev/dsk/hda1 */ - struct list_head mnt_list; + union { + struct rb_node mnt_node; /* Under ns->mounts */ + struct list_head mnt_list; + }; struct list_head mnt_expire; /* link in fs-specific expiry list */ struct list_head mnt_share; /* circular list of shared mounts */ struct list_head mnt_slave_list;/* list of slave mounts */ @@ -72,7 +69,8 @@ struct mount { struct fsnotify_mark_connector __rcu *mnt_fsnotify_marks; __u32 mnt_fsnotify_mask; #endif - int mnt_id; /* mount identifier */ + int mnt_id; /* mount identifier, reused */ + u64 mnt_id_unique; /* mount ID unique until reboot */ int mnt_group_id; /* peer group identifier */ int mnt_expiry_mark; /* true if marked for expiry */ struct hlist_head mnt_pins; @@ -127,7 +125,6 @@ struct proc_mounts { struct mnt_namespace *ns; struct path root; int (*show)(struct seq_file *, struct vfsmount *); - struct mount cursor; }; extern const struct seq_operations mounts_op; @@ -146,4 +143,12 @@ static inline bool is_anon_ns(struct mnt_namespace *ns) return ns->seq == 0; } +static inline void move_from_ns(struct mount *mnt, struct list_head *dt_list) +{ + WARN_ON(!(mnt->mnt.mnt_flags & MNT_ONRB)); + mnt->mnt.mnt_flags &= ~MNT_ONRB; + rb_erase(&mnt->mnt_node, &mnt->mnt_ns->mounts); + list_add_tail(&mnt->mnt_list, dt_list); +} + extern void mnt_cursor_del(struct mnt_namespace *ns, struct mount *cursor); diff --git a/fs/namei.c b/fs/namei.c index 71c13b2990b4..faae721e4d63 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -289,7 +289,7 @@ EXPORT_SYMBOL(putname); * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the - * raw inode simply passs @nop_mnt_idmap. + * raw inode simply pass @nop_mnt_idmap. */ static int check_acl(struct mnt_idmap *idmap, struct inode *inode, int mask) @@ -334,7 +334,7 @@ static int check_acl(struct mnt_idmap *idmap, * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the - * raw inode simply passs @nop_mnt_idmap. + * raw inode simply pass @nop_mnt_idmap. */ static int acl_permission_check(struct mnt_idmap *idmap, struct inode *inode, int mask) @@ -395,7 +395,7 @@ static int acl_permission_check(struct mnt_idmap *idmap, * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the - * raw inode simply passs @nop_mnt_idmap. + * raw inode simply pass @nop_mnt_idmap. */ int generic_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) @@ -2467,7 +2467,7 @@ static int handle_lookup_down(struct nameidata *nd) return PTR_ERR(step_into(nd, WALK_NOFOLLOW, nd->path.dentry)); } -/* Returns 0 and nd will be valid on success; Retuns error, otherwise. */ +/* Returns 0 and nd will be valid on success; Returns error, otherwise. */ static int path_lookupat(struct nameidata *nd, unsigned flags, struct path *path) { const char *s = path_init(nd, flags); @@ -2522,7 +2522,7 @@ int filename_lookup(int dfd, struct filename *name, unsigned flags, return retval; } -/* Returns 0 and nd will be valid on success; Retuns error, otherwise. */ +/* Returns 0 and nd will be valid on success; Returns error, otherwise. */ static int path_parentat(struct nameidata *nd, unsigned flags, struct path *parent) { @@ -3158,7 +3158,7 @@ static inline umode_t vfs_prepare_mode(struct mnt_idmap *idmap, * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the - * raw inode simply passs @nop_mnt_idmap. + * raw inode simply pass @nop_mnt_idmap. */ int vfs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool want_excl) @@ -3646,7 +3646,7 @@ static int do_open(struct nameidata *nd, * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the - * raw inode simply passs @nop_mnt_idmap. + * raw inode simply pass @nop_mnt_idmap. */ static int vfs_tmpfile(struct mnt_idmap *idmap, const struct path *parentpath, @@ -3785,10 +3785,7 @@ static struct file *path_openat(struct nameidata *nd, WARN_ON(1); error = -EINVAL; } - if (unlikely(file->f_mode & FMODE_OPENED)) - fput(file); - else - release_empty_file(file); + fput(file); if (error == -EOPENSTALE) { if (flags & LOOKUP_RCU) error = -ECHILD; @@ -3954,7 +3951,7 @@ EXPORT_SYMBOL(user_path_create); * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the - * raw inode simply passs @nop_mnt_idmap. + * raw inode simply pass @nop_mnt_idmap. */ int vfs_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) @@ -4080,7 +4077,7 @@ SYSCALL_DEFINE3(mknod, const char __user *, filename, umode_t, mode, unsigned, d * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the - * raw inode simply passs @nop_mnt_idmap. + * raw inode simply pass @nop_mnt_idmap. */ int vfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) @@ -4161,7 +4158,7 @@ SYSCALL_DEFINE2(mkdir, const char __user *, pathname, umode_t, mode) * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the - * raw inode simply passs @nop_mnt_idmap. + * raw inode simply pass @nop_mnt_idmap. */ int vfs_rmdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry) @@ -4290,7 +4287,7 @@ SYSCALL_DEFINE1(rmdir, const char __user *, pathname) * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the - * raw inode simply passs @nop_mnt_idmap. + * raw inode simply pass @nop_mnt_idmap. */ int vfs_unlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, struct inode **delegated_inode) @@ -4443,7 +4440,7 @@ SYSCALL_DEFINE1(unlink, const char __user *, pathname) * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the - * raw inode simply passs @nop_mnt_idmap. + * raw inode simply pass @nop_mnt_idmap. */ int vfs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *oldname) @@ -4535,7 +4532,7 @@ SYSCALL_DEFINE2(symlink, const char __user *, oldname, const char __user *, newn * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the - * raw inode simply passs @nop_mnt_idmap. + * raw inode simply pass @nop_mnt_idmap. */ int vfs_link(struct dentry *old_dentry, struct mnt_idmap *idmap, struct inode *dir, struct dentry *new_dentry, diff --git a/fs/namespace.c b/fs/namespace.c index fbf0e596fcd3..3beda4bb59af 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -32,6 +32,7 @@ #include <linux/fs_context.h> #include <linux/shmem_fs.h> #include <linux/mnt_idmapping.h> +#include <linux/nospec.h> #include "pnode.h" #include "internal.h" @@ -68,6 +69,9 @@ static u64 event; static DEFINE_IDA(mnt_id_ida); static DEFINE_IDA(mnt_group_ida); +/* Don't allow confusion with old 32bit mount ID */ +static atomic64_t mnt_id_ctr = ATOMIC64_INIT(1ULL << 32); + static struct hlist_head *mount_hashtable __ro_after_init; static struct hlist_head *mountpoint_hashtable __ro_after_init; static struct kmem_cache *mnt_cache __ro_after_init; @@ -131,6 +135,7 @@ static int mnt_alloc_id(struct mount *mnt) if (res < 0) return res; mnt->mnt_id = res; + mnt->mnt_id_unique = atomic64_inc_return(&mnt_id_ctr); return 0; } @@ -730,21 +735,6 @@ struct vfsmount *lookup_mnt(const struct path *path) return m; } -static inline void lock_ns_list(struct mnt_namespace *ns) -{ - spin_lock(&ns->ns_lock); -} - -static inline void unlock_ns_list(struct mnt_namespace *ns) -{ - spin_unlock(&ns->ns_lock); -} - -static inline bool mnt_is_cursor(struct mount *mnt) -{ - return mnt->mnt.mnt_flags & MNT_CURSOR; -} - /* * __is_local_mountpoint - Test to see if dentry is a mountpoint in the * current mount namespace. @@ -763,19 +753,15 @@ static inline bool mnt_is_cursor(struct mount *mnt) bool __is_local_mountpoint(struct dentry *dentry) { struct mnt_namespace *ns = current->nsproxy->mnt_ns; - struct mount *mnt; + struct mount *mnt, *n; bool is_covered = false; down_read(&namespace_sem); - lock_ns_list(ns); - list_for_each_entry(mnt, &ns->list, mnt_list) { - if (mnt_is_cursor(mnt)) - continue; + rbtree_postorder_for_each_entry_safe(mnt, n, &ns->mounts, mnt_node) { is_covered = (mnt->mnt_mountpoint == dentry); if (is_covered) break; } - unlock_ns_list(ns); up_read(&namespace_sem); return is_covered; @@ -1022,6 +1008,30 @@ void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, struct m mnt_add_count(old_parent, -1); } +static inline struct mount *node_to_mount(struct rb_node *node) +{ + return node ? rb_entry(node, struct mount, mnt_node) : NULL; +} + +static void mnt_add_to_ns(struct mnt_namespace *ns, struct mount *mnt) +{ + struct rb_node **link = &ns->mounts.rb_node; + struct rb_node *parent = NULL; + + WARN_ON(mnt->mnt.mnt_flags & MNT_ONRB); + mnt->mnt_ns = ns; + while (*link) { + parent = *link; + if (mnt->mnt_id_unique < node_to_mount(parent)->mnt_id_unique) + link = &parent->rb_left; + else + link = &parent->rb_right; + } + rb_link_node(&mnt->mnt_node, parent, link); + rb_insert_color(&mnt->mnt_node, &ns->mounts); + mnt->mnt.mnt_flags |= MNT_ONRB; +} + /* * vfsmount lock must be held for write */ @@ -1035,12 +1045,13 @@ static void commit_tree(struct mount *mnt) BUG_ON(parent == mnt); list_add_tail(&head, &mnt->mnt_list); - list_for_each_entry(m, &head, mnt_list) - m->mnt_ns = n; + while (!list_empty(&head)) { + m = list_first_entry(&head, typeof(*m), mnt_list); + list_del(&m->mnt_list); - list_splice(&head, n->list.prev); - - n->mounts += n->pending_mounts; + mnt_add_to_ns(n, m); + } + n->nr_mounts += n->pending_mounts; n->pending_mounts = 0; __attach_mnt(mnt, parent); @@ -1188,7 +1199,7 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root, } mnt->mnt.mnt_flags = old->mnt.mnt_flags; - mnt->mnt.mnt_flags &= ~(MNT_WRITE_HOLD|MNT_MARKED|MNT_INTERNAL); + mnt->mnt.mnt_flags &= ~(MNT_WRITE_HOLD|MNT_MARKED|MNT_INTERNAL|MNT_ONRB); atomic_inc(&sb->s_active); mnt->mnt.mnt_idmap = mnt_idmap_get(mnt_idmap(&old->mnt)); @@ -1413,65 +1424,57 @@ struct vfsmount *mnt_clone_internal(const struct path *path) return &p->mnt; } -#ifdef CONFIG_PROC_FS -static struct mount *mnt_list_next(struct mnt_namespace *ns, - struct list_head *p) +/* + * Returns the mount which either has the specified mnt_id, or has the next + * smallest id afer the specified one. + */ +static struct mount *mnt_find_id_at(struct mnt_namespace *ns, u64 mnt_id) { - struct mount *mnt, *ret = NULL; + struct rb_node *node = ns->mounts.rb_node; + struct mount *ret = NULL; - lock_ns_list(ns); - list_for_each_continue(p, &ns->list) { - mnt = list_entry(p, typeof(*mnt), mnt_list); - if (!mnt_is_cursor(mnt)) { - ret = mnt; - break; + while (node) { + struct mount *m = node_to_mount(node); + + if (mnt_id <= m->mnt_id_unique) { + ret = node_to_mount(node); + if (mnt_id == m->mnt_id_unique) + break; + node = node->rb_left; + } else { + node = node->rb_right; } } - unlock_ns_list(ns); - return ret; } +#ifdef CONFIG_PROC_FS + /* iterator; we want it to have access to namespace_sem, thus here... */ static void *m_start(struct seq_file *m, loff_t *pos) { struct proc_mounts *p = m->private; - struct list_head *prev; down_read(&namespace_sem); - if (!*pos) { - prev = &p->ns->list; - } else { - prev = &p->cursor.mnt_list; - /* Read after we'd reached the end? */ - if (list_empty(prev)) - return NULL; - } - - return mnt_list_next(p->ns, prev); + return mnt_find_id_at(p->ns, *pos); } static void *m_next(struct seq_file *m, void *v, loff_t *pos) { - struct proc_mounts *p = m->private; - struct mount *mnt = v; + struct mount *next = NULL, *mnt = v; + struct rb_node *node = rb_next(&mnt->mnt_node); ++*pos; - return mnt_list_next(p->ns, &mnt->mnt_list); + if (node) { + next = node_to_mount(node); + *pos = next->mnt_id_unique; + } + return next; } static void m_stop(struct seq_file *m, void *v) { - struct proc_mounts *p = m->private; - struct mount *mnt = v; - - lock_ns_list(p->ns); - if (mnt) - list_move_tail(&p->cursor.mnt_list, &mnt->mnt_list); - else - list_del_init(&p->cursor.mnt_list); - unlock_ns_list(p->ns); up_read(&namespace_sem); } @@ -1489,14 +1492,6 @@ const struct seq_operations mounts_op = { .show = m_show, }; -void mnt_cursor_del(struct mnt_namespace *ns, struct mount *cursor) -{ - down_read(&namespace_sem); - lock_ns_list(ns); - list_del(&cursor->mnt_list); - unlock_ns_list(ns); - up_read(&namespace_sem); -} #endif /* CONFIG_PROC_FS */ /** @@ -1638,7 +1633,10 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how) /* Gather the mounts to umount */ for (p = mnt; p; p = next_mnt(p, mnt)) { p->mnt.mnt_flags |= MNT_UMOUNT; - list_move(&p->mnt_list, &tmp_list); + if (p->mnt.mnt_flags & MNT_ONRB) + move_from_ns(p, &tmp_list); + else + list_move(&p->mnt_list, &tmp_list); } /* Hide the mounts from mnt_mounts */ @@ -1658,7 +1656,7 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how) list_del_init(&p->mnt_list); ns = p->mnt_ns; if (ns) { - ns->mounts--; + ns->nr_mounts--; __touch_mnt_namespace(ns); } p->mnt_ns = NULL; @@ -1784,14 +1782,16 @@ static int do_umount(struct mount *mnt, int flags) event++; if (flags & MNT_DETACH) { - if (!list_empty(&mnt->mnt_list)) + if (mnt->mnt.mnt_flags & MNT_ONRB || + !list_empty(&mnt->mnt_list)) umount_tree(mnt, UMOUNT_PROPAGATE); retval = 0; } else { shrink_submounts(mnt); retval = -EBUSY; if (!propagate_mount_busy(mnt, 2)) { - if (!list_empty(&mnt->mnt_list)) + if (mnt->mnt.mnt_flags & MNT_ONRB || + !list_empty(&mnt->mnt_list)) umount_tree(mnt, UMOUNT_PROPAGATE|UMOUNT_SYNC); retval = 0; } @@ -2209,9 +2209,9 @@ int count_mounts(struct mnt_namespace *ns, struct mount *mnt) unsigned int mounts = 0; struct mount *p; - if (ns->mounts >= max) + if (ns->nr_mounts >= max) return -ENOSPC; - max -= ns->mounts; + max -= ns->nr_mounts; if (ns->pending_mounts >= max) return -ENOSPC; max -= ns->pending_mounts; @@ -2355,8 +2355,12 @@ static int attach_recursive_mnt(struct mount *source_mnt, touch_mnt_namespace(source_mnt->mnt_ns); } else { if (source_mnt->mnt_ns) { + LIST_HEAD(head); + /* move from anon - the caller will destroy */ - list_del_init(&source_mnt->mnt_ns->list); + for (p = source_mnt; p; p = next_mnt(p, source_mnt)) + move_from_ns(p, &head); + list_del_init(&head); } if (beneath) mnt_set_mountpoint_beneath(source_mnt, top_mnt, smp); @@ -2667,11 +2671,10 @@ static struct file *open_detached_copy(struct path *path, bool recursive) lock_mount_hash(); for (p = mnt; p; p = next_mnt(p, mnt)) { - p->mnt_ns = ns; - ns->mounts++; + mnt_add_to_ns(ns, p); + ns->nr_mounts++; } ns->root = mnt; - list_add_tail(&ns->list, &mnt->mnt_list); mntget(&mnt->mnt); unlock_mount_hash(); namespace_unlock(); @@ -3026,6 +3029,7 @@ static inline bool path_overmounted(const struct path *path) * can_move_mount_beneath - check that we can mount beneath the top mount * @from: mount to mount beneath * @to: mount under which to mount + * @mp: mountpoint of @to * * - Make sure that @to->dentry is actually the root of a mount under * which we can mount another mount. @@ -3734,9 +3738,8 @@ static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns, bool a if (!anon) new_ns->seq = atomic64_add_return(1, &mnt_ns_seq); refcount_set(&new_ns->ns.count, 1); - INIT_LIST_HEAD(&new_ns->list); + new_ns->mounts = RB_ROOT; init_waitqueue_head(&new_ns->poll); - spin_lock_init(&new_ns->ns_lock); new_ns->user_ns = get_user_ns(user_ns); new_ns->ucounts = ucounts; return new_ns; @@ -3783,7 +3786,6 @@ struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns, unlock_mount_hash(); } new_ns->root = new; - list_add_tail(&new_ns->list, &new->mnt_list); /* * Second pass: switch the tsk->fs->* elements and mark new vfsmounts @@ -3793,8 +3795,8 @@ struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns, p = old; q = new; while (p) { - q->mnt_ns = new_ns; - new_ns->mounts++; + mnt_add_to_ns(new_ns, q); + new_ns->nr_mounts++; if (new_fs) { if (&p->mnt == new_fs->root.mnt) { new_fs->root.mnt = mntget(&q->mnt); @@ -3836,10 +3838,9 @@ struct dentry *mount_subtree(struct vfsmount *m, const char *name) mntput(m); return ERR_CAST(ns); } - mnt->mnt_ns = ns; ns->root = mnt; - ns->mounts++; - list_add(&mnt->mnt_list, &ns->list); + ns->nr_mounts++; + mnt_add_to_ns(ns, mnt); err = vfs_path_lookup(m->mnt_root, m, name, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &path); @@ -4017,10 +4018,9 @@ SYSCALL_DEFINE3(fsmount, int, fs_fd, unsigned int, flags, goto err_path; } mnt = real_mount(newmount.mnt); - mnt->mnt_ns = ns; ns->root = mnt; - ns->mounts = 1; - list_add(&mnt->mnt_list, &ns->list); + ns->nr_mounts = 1; + mnt_add_to_ns(ns, mnt); mntget(newmount.mnt); /* Attach to an apparent O_PATH fd with a note that we need to unmount @@ -4288,7 +4288,7 @@ static int can_idmap_mount(const struct mount_kattr *kattr, struct mount *mnt) * Creating an idmapped mount with the filesystem wide idmapping * doesn't make sense so block that. We don't allow mushy semantics. */ - if (!check_fsmapping(kattr->mnt_idmap, m->mnt_sb)) + if (kattr->mnt_userns == m->mnt_sb->s_user_ns) return -EINVAL; /* @@ -4676,6 +4676,438 @@ SYSCALL_DEFINE5(mount_setattr, int, dfd, const char __user *, path, return err; } +int show_path(struct seq_file *m, struct dentry *root) +{ + if (root->d_sb->s_op->show_path) + return root->d_sb->s_op->show_path(m, root); + + seq_dentry(m, root, " \t\n\\"); + return 0; +} + +static struct vfsmount *lookup_mnt_in_ns(u64 id, struct mnt_namespace *ns) +{ + struct mount *mnt = mnt_find_id_at(ns, id); + + if (!mnt || mnt->mnt_id_unique != id) + return NULL; + + return &mnt->mnt; +} + +struct kstatmount { + struct statmount __user *buf; + size_t bufsize; + struct vfsmount *mnt; + u64 mask; + struct path root; + struct statmount sm; + struct seq_file seq; +}; + +static u64 mnt_to_attr_flags(struct vfsmount *mnt) +{ + unsigned int mnt_flags = READ_ONCE(mnt->mnt_flags); + u64 attr_flags = 0; + + if (mnt_flags & MNT_READONLY) + attr_flags |= MOUNT_ATTR_RDONLY; + if (mnt_flags & MNT_NOSUID) + attr_flags |= MOUNT_ATTR_NOSUID; + if (mnt_flags & MNT_NODEV) + attr_flags |= MOUNT_ATTR_NODEV; + if (mnt_flags & MNT_NOEXEC) + attr_flags |= MOUNT_ATTR_NOEXEC; + if (mnt_flags & MNT_NODIRATIME) + attr_flags |= MOUNT_ATTR_NODIRATIME; + if (mnt_flags & MNT_NOSYMFOLLOW) + attr_flags |= MOUNT_ATTR_NOSYMFOLLOW; + + if (mnt_flags & MNT_NOATIME) + attr_flags |= MOUNT_ATTR_NOATIME; + else if (mnt_flags & MNT_RELATIME) + attr_flags |= MOUNT_ATTR_RELATIME; + else + attr_flags |= MOUNT_ATTR_STRICTATIME; + + if (is_idmapped_mnt(mnt)) + attr_flags |= MOUNT_ATTR_IDMAP; + + return attr_flags; +} + +static u64 mnt_to_propagation_flags(struct mount *m) +{ + u64 propagation = 0; + + if (IS_MNT_SHARED(m)) + propagation |= MS_SHARED; + if (IS_MNT_SLAVE(m)) + propagation |= MS_SLAVE; + if (IS_MNT_UNBINDABLE(m)) + propagation |= MS_UNBINDABLE; + if (!propagation) + propagation |= MS_PRIVATE; + + return propagation; +} + +static void statmount_sb_basic(struct kstatmount *s) +{ + struct super_block *sb = s->mnt->mnt_sb; + + s->sm.mask |= STATMOUNT_SB_BASIC; + s->sm.sb_dev_major = MAJOR(sb->s_dev); + s->sm.sb_dev_minor = MINOR(sb->s_dev); + s->sm.sb_magic = sb->s_magic; + s->sm.sb_flags = sb->s_flags & (SB_RDONLY|SB_SYNCHRONOUS|SB_DIRSYNC|SB_LAZYTIME); +} + +static void statmount_mnt_basic(struct kstatmount *s) +{ + struct mount *m = real_mount(s->mnt); + + s->sm.mask |= STATMOUNT_MNT_BASIC; + s->sm.mnt_id = m->mnt_id_unique; + s->sm.mnt_parent_id = m->mnt_parent->mnt_id_unique; + s->sm.mnt_id_old = m->mnt_id; + s->sm.mnt_parent_id_old = m->mnt_parent->mnt_id; + s->sm.mnt_attr = mnt_to_attr_flags(&m->mnt); + s->sm.mnt_propagation = mnt_to_propagation_flags(m); + s->sm.mnt_peer_group = IS_MNT_SHARED(m) ? m->mnt_group_id : 0; + s->sm.mnt_master = IS_MNT_SLAVE(m) ? m->mnt_master->mnt_group_id : 0; +} + +static void statmount_propagate_from(struct kstatmount *s) +{ + struct mount *m = real_mount(s->mnt); + + s->sm.mask |= STATMOUNT_PROPAGATE_FROM; + if (IS_MNT_SLAVE(m)) + s->sm.propagate_from = get_dominating_id(m, ¤t->fs->root); +} + +static int statmount_mnt_root(struct kstatmount *s, struct seq_file *seq) +{ + int ret; + size_t start = seq->count; + + ret = show_path(seq, s->mnt->mnt_root); + if (ret) + return ret; + + if (unlikely(seq_has_overflowed(seq))) + return -EAGAIN; + + /* + * Unescape the result. It would be better if supplied string was not + * escaped in the first place, but that's a pretty invasive change. + */ + seq->buf[seq->count] = '\0'; + seq->count = start; + seq_commit(seq, string_unescape_inplace(seq->buf + start, UNESCAPE_OCTAL)); + return 0; +} + +static int statmount_mnt_point(struct kstatmount *s, struct seq_file *seq) +{ + struct vfsmount *mnt = s->mnt; + struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt }; + int err; + + err = seq_path_root(seq, &mnt_path, &s->root, ""); + return err == SEQ_SKIP ? 0 : err; +} + +static int statmount_fs_type(struct kstatmount *s, struct seq_file *seq) +{ + struct super_block *sb = s->mnt->mnt_sb; + + seq_puts(seq, sb->s_type->name); + return 0; +} + +static int statmount_string(struct kstatmount *s, u64 flag) +{ + int ret; + size_t kbufsize; + struct seq_file *seq = &s->seq; + struct statmount *sm = &s->sm; + + switch (flag) { + case STATMOUNT_FS_TYPE: + sm->fs_type = seq->count; + ret = statmount_fs_type(s, seq); + break; + case STATMOUNT_MNT_ROOT: + sm->mnt_root = seq->count; + ret = statmount_mnt_root(s, seq); + break; + case STATMOUNT_MNT_POINT: + sm->mnt_point = seq->count; + ret = statmount_mnt_point(s, seq); + break; + default: + WARN_ON_ONCE(true); + return -EINVAL; + } + + if (unlikely(check_add_overflow(sizeof(*sm), seq->count, &kbufsize))) + return -EOVERFLOW; + if (kbufsize >= s->bufsize) + return -EOVERFLOW; + + /* signal a retry */ + if (unlikely(seq_has_overflowed(seq))) + return -EAGAIN; + + if (ret) + return ret; + + seq->buf[seq->count++] = '\0'; + sm->mask |= flag; + return 0; +} + +static int copy_statmount_to_user(struct kstatmount *s) +{ + struct statmount *sm = &s->sm; + struct seq_file *seq = &s->seq; + char __user *str = ((char __user *)s->buf) + sizeof(*sm); + size_t copysize = min_t(size_t, s->bufsize, sizeof(*sm)); + + if (seq->count && copy_to_user(str, seq->buf, seq->count)) + return -EFAULT; + + /* Return the number of bytes copied to the buffer */ + sm->size = copysize + seq->count; + if (copy_to_user(s->buf, sm, copysize)) + return -EFAULT; + + return 0; +} + +static int do_statmount(struct kstatmount *s) +{ + struct mount *m = real_mount(s->mnt); + int err; + + /* + * Don't trigger audit denials. We just want to determine what + * mounts to show users. + */ + if (!is_path_reachable(m, m->mnt.mnt_root, &s->root) && + !ns_capable_noaudit(&init_user_ns, CAP_SYS_ADMIN)) + return -EPERM; + + err = security_sb_statfs(s->mnt->mnt_root); + if (err) + return err; + + if (s->mask & STATMOUNT_SB_BASIC) + statmount_sb_basic(s); + + if (s->mask & STATMOUNT_MNT_BASIC) + statmount_mnt_basic(s); + + if (s->mask & STATMOUNT_PROPAGATE_FROM) + statmount_propagate_from(s); + + if (s->mask & STATMOUNT_FS_TYPE) + err = statmount_string(s, STATMOUNT_FS_TYPE); + + if (!err && s->mask & STATMOUNT_MNT_ROOT) + err = statmount_string(s, STATMOUNT_MNT_ROOT); + + if (!err && s->mask & STATMOUNT_MNT_POINT) + err = statmount_string(s, STATMOUNT_MNT_POINT); + + if (err) + return err; + + return 0; +} + +static inline bool retry_statmount(const long ret, size_t *seq_size) +{ + if (likely(ret != -EAGAIN)) + return false; + if (unlikely(check_mul_overflow(*seq_size, 2, seq_size))) + return false; + if (unlikely(*seq_size > MAX_RW_COUNT)) + return false; + return true; +} + +static int prepare_kstatmount(struct kstatmount *ks, struct mnt_id_req *kreq, + struct statmount __user *buf, size_t bufsize, + size_t seq_size) +{ + if (!access_ok(buf, bufsize)) + return -EFAULT; + + memset(ks, 0, sizeof(*ks)); + ks->mask = kreq->param; + ks->buf = buf; + ks->bufsize = bufsize; + ks->seq.size = seq_size; + ks->seq.buf = kvmalloc(seq_size, GFP_KERNEL_ACCOUNT); + if (!ks->seq.buf) + return -ENOMEM; + return 0; +} + +static int copy_mnt_id_req(const struct mnt_id_req __user *req, + struct mnt_id_req *kreq) +{ + int ret; + size_t usize; + + BUILD_BUG_ON(sizeof(struct mnt_id_req) != MNT_ID_REQ_SIZE_VER0); + + ret = get_user(usize, &req->size); + if (ret) + return -EFAULT; + if (unlikely(usize > PAGE_SIZE)) + return -E2BIG; + if (unlikely(usize < MNT_ID_REQ_SIZE_VER0)) + return -EINVAL; + memset(kreq, 0, sizeof(*kreq)); + ret = copy_struct_from_user(kreq, sizeof(*kreq), req, usize); + if (ret) + return ret; + if (kreq->spare != 0) + return -EINVAL; + return 0; +} + +SYSCALL_DEFINE4(statmount, const struct mnt_id_req __user *, req, + struct statmount __user *, buf, size_t, bufsize, + unsigned int, flags) +{ + struct vfsmount *mnt; + struct mnt_id_req kreq; + struct kstatmount ks; + /* We currently support retrieval of 3 strings. */ + size_t seq_size = 3 * PATH_MAX; + int ret; + + if (flags) + return -EINVAL; + + ret = copy_mnt_id_req(req, &kreq); + if (ret) + return ret; + +retry: + ret = prepare_kstatmount(&ks, &kreq, buf, bufsize, seq_size); + if (ret) + return ret; + + down_read(&namespace_sem); + mnt = lookup_mnt_in_ns(kreq.mnt_id, current->nsproxy->mnt_ns); + if (!mnt) { + up_read(&namespace_sem); + kvfree(ks.seq.buf); + return -ENOENT; + } + + ks.mnt = mnt; + get_fs_root(current->fs, &ks.root); + ret = do_statmount(&ks); + path_put(&ks.root); + up_read(&namespace_sem); + + if (!ret) + ret = copy_statmount_to_user(&ks); + kvfree(ks.seq.buf); + if (retry_statmount(ret, &seq_size)) + goto retry; + return ret; +} + +static struct mount *listmnt_next(struct mount *curr) +{ + return node_to_mount(rb_next(&curr->mnt_node)); +} + +static ssize_t do_listmount(struct mount *first, struct path *orig, u64 mnt_id, + u64 __user *buf, size_t bufsize, + const struct path *root) +{ + struct mount *r; + ssize_t ctr; + int err; + + /* + * Don't trigger audit denials. We just want to determine what + * mounts to show users. + */ + if (!is_path_reachable(real_mount(orig->mnt), orig->dentry, root) && + !ns_capable_noaudit(&init_user_ns, CAP_SYS_ADMIN)) + return -EPERM; + + err = security_sb_statfs(orig->dentry); + if (err) + return err; + + for (ctr = 0, r = first; r && ctr < bufsize; r = listmnt_next(r)) { + if (r->mnt_id_unique == mnt_id) + continue; + if (!is_path_reachable(r, r->mnt.mnt_root, orig)) + continue; + ctr = array_index_nospec(ctr, bufsize); + if (put_user(r->mnt_id_unique, buf + ctr)) + return -EFAULT; + if (check_add_overflow(ctr, 1, &ctr)) + return -ERANGE; + } + return ctr; +} + +SYSCALL_DEFINE4(listmount, const struct mnt_id_req __user *, req, + u64 __user *, buf, size_t, bufsize, unsigned int, flags) +{ + struct mnt_namespace *ns = current->nsproxy->mnt_ns; + struct mnt_id_req kreq; + struct mount *first; + struct path root, orig; + u64 mnt_id, last_mnt_id; + ssize_t ret; + + if (flags) + return -EINVAL; + + ret = copy_mnt_id_req(req, &kreq); + if (ret) + return ret; + mnt_id = kreq.mnt_id; + last_mnt_id = kreq.param; + + down_read(&namespace_sem); + get_fs_root(current->fs, &root); + if (mnt_id == LSMT_ROOT) { + orig = root; + } else { + ret = -ENOENT; + orig.mnt = lookup_mnt_in_ns(mnt_id, ns); + if (!orig.mnt) + goto err; + orig.dentry = orig.mnt->mnt_root; + } + if (!last_mnt_id) + first = node_to_mount(rb_first(&ns->mounts)); + else + first = mnt_find_id_at(ns, last_mnt_id + 1); + + ret = do_listmount(first, &orig, mnt_id, buf, bufsize, &root); +err: + path_put(&root); + up_read(&namespace_sem); + return ret; +} + + static void __init init_mount_tree(void) { struct vfsmount *mnt; @@ -4691,10 +5123,9 @@ static void __init init_mount_tree(void) if (IS_ERR(ns)) panic("Can't allocate initial namespace"); m = real_mount(mnt); - m->mnt_ns = ns; ns->root = m; - ns->mounts = 1; - list_add(&m->mnt_list, &ns->list); + ns->nr_mounts = 1; + mnt_add_to_ns(ns, m); init_task.nsproxy->mnt_ns = ns; get_mnt_ns(ns); @@ -4821,18 +5252,14 @@ static bool mnt_already_visible(struct mnt_namespace *ns, int *new_mnt_flags) { int new_flags = *new_mnt_flags; - struct mount *mnt; + struct mount *mnt, *n; bool visible = false; down_read(&namespace_sem); - lock_ns_list(ns); - list_for_each_entry(mnt, &ns->list, mnt_list) { + rbtree_postorder_for_each_entry_safe(mnt, n, &ns->mounts, mnt_node) { struct mount *child; int mnt_flags; - if (mnt_is_cursor(mnt)) - continue; - if (mnt->mnt.mnt_sb->s_type != sb->s_type) continue; @@ -4880,7 +5307,6 @@ static bool mnt_already_visible(struct mnt_namespace *ns, next: ; } found: - unlock_ns_list(ns); up_read(&namespace_sem); return visible; } diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index 02788c3c85e5..e238abc78a13 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -10,6 +10,7 @@ #include <linux/mount.h> #include <linux/nfs_fs.h> #include <linux/nfs_ssc.h> +#include <linux/splice.h> #include "delegation.h" #include "internal.h" #include "iostat.h" @@ -195,8 +196,8 @@ static ssize_t nfs4_copy_file_range(struct file *file_in, loff_t pos_in, ret = __nfs4_copy_file_range(file_in, pos_in, file_out, pos_out, count, flags); if (ret == -EOPNOTSUPP || ret == -EXDEV) - ret = generic_copy_file_range(file_in, pos_in, file_out, - pos_out, count, flags); + ret = splice_copy_file_range(file_in, pos_in, file_out, + pos_out, count); return ret; } diff --git a/fs/nfs/write.c b/fs/nfs/write.c index b664caea8b4e..7248705faef4 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -192,13 +192,13 @@ static struct nfs_page *nfs_folio_find_private_request(struct folio *folio) if (!folio_test_private(folio)) return NULL; - spin_lock(&mapping->private_lock); + spin_lock(&mapping->i_private_lock); req = nfs_folio_private_request(folio); if (req) { WARN_ON_ONCE(req->wb_head != req); kref_get(&req->wb_kref); } - spin_unlock(&mapping->private_lock); + spin_unlock(&mapping->i_private_lock); return req; } @@ -769,13 +769,13 @@ static void nfs_inode_add_request(struct nfs_page *req) * Swap-space should not get truncated. Hence no need to plug the race * with invalidate/truncate. */ - spin_lock(&mapping->private_lock); + spin_lock(&mapping->i_private_lock); if (likely(!folio_test_swapcache(folio))) { set_bit(PG_MAPPED, &req->wb_flags); folio_set_private(folio); folio->private = req; } - spin_unlock(&mapping->private_lock); + spin_unlock(&mapping->i_private_lock); atomic_long_inc(&nfsi->nrequests); /* this a head request for a page group - mark it as having an * extra reference so sub groups can follow suit. @@ -796,13 +796,13 @@ static void nfs_inode_remove_request(struct nfs_page *req) struct folio *folio = nfs_page_to_folio(req->wb_head); struct address_space *mapping = folio_file_mapping(folio); - spin_lock(&mapping->private_lock); + spin_lock(&mapping->i_private_lock); if (likely(folio && !folio_test_swapcache(folio))) { folio->private = NULL; folio_clear_private(folio); clear_bit(PG_MAPPED, &req->wb_head->wb_flags); } - spin_unlock(&mapping->private_lock); + spin_unlock(&mapping->i_private_lock); } if (test_and_clear_bit(PG_INODE_REF, &req->wb_flags)) { diff --git a/fs/nfsd/auth.c b/fs/nfsd/auth.c index fdf2aad73470..e6beaaf4f170 100644 --- a/fs/nfsd/auth.c +++ b/fs/nfsd/auth.c @@ -26,8 +26,6 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp) int i; int flags = nfsexp_flags(rqstp, exp); - validate_process_creds(); - /* discard any old override before preparing the new set */ revert_creds(get_cred(current_real_cred())); new = prepare_creds(); @@ -81,10 +79,8 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp) else new->cap_effective = cap_raise_nfsd_set(new->cap_effective, new->cap_permitted); - validate_process_creds(); put_cred(override_creds(new)); put_cred(new); - validate_process_creds(); return 0; oom: diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 92bc109dabe6..4039ffcf90ba 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -84,21 +84,7 @@ static void encode_uint32(struct xdr_stream *xdr, u32 n) static void encode_bitmap4(struct xdr_stream *xdr, const __u32 *bitmap, size_t len) { - xdr_stream_encode_uint32_array(xdr, bitmap, len); -} - -static int decode_cb_fattr4(struct xdr_stream *xdr, uint32_t *bitmap, - struct nfs4_cb_fattr *fattr) -{ - fattr->ncf_cb_change = 0; - fattr->ncf_cb_fsize = 0; - if (bitmap[0] & FATTR4_WORD0_CHANGE) - if (xdr_stream_decode_u64(xdr, &fattr->ncf_cb_change) < 0) - return -NFSERR_BAD_XDR; - if (bitmap[0] & FATTR4_WORD0_SIZE) - if (xdr_stream_decode_u64(xdr, &fattr->ncf_cb_fsize) < 0) - return -NFSERR_BAD_XDR; - return 0; + WARN_ON_ONCE(xdr_stream_encode_uint32_array(xdr, bitmap, len) < 0); } /* @@ -372,30 +358,6 @@ encode_cb_recallany4args(struct xdr_stream *xdr, } /* - * CB_GETATTR4args - * struct CB_GETATTR4args { - * nfs_fh4 fh; - * bitmap4 attr_request; - * }; - * - * The size and change attributes are the only one - * guaranteed to be serviced by the client. - */ -static void -encode_cb_getattr4args(struct xdr_stream *xdr, struct nfs4_cb_compound_hdr *hdr, - struct nfs4_cb_fattr *fattr) -{ - struct nfs4_delegation *dp = - container_of(fattr, struct nfs4_delegation, dl_cb_fattr); - struct knfsd_fh *fh = &dp->dl_stid.sc_file->fi_fhandle; - - encode_nfs_cb_opnum4(xdr, OP_CB_GETATTR); - encode_nfs_fh4(xdr, fh); - encode_bitmap4(xdr, fattr->ncf_cb_bmap, ARRAY_SIZE(fattr->ncf_cb_bmap)); - hdr->nops++; -} - -/* * CB_SEQUENCE4args * * struct CB_SEQUENCE4args { @@ -531,26 +493,6 @@ static void nfs4_xdr_enc_cb_null(struct rpc_rqst *req, struct xdr_stream *xdr, } /* - * 20.1. Operation 3: CB_GETATTR - Get Attributes - */ -static void nfs4_xdr_enc_cb_getattr(struct rpc_rqst *req, - struct xdr_stream *xdr, const void *data) -{ - const struct nfsd4_callback *cb = data; - struct nfs4_cb_fattr *ncf = - container_of(cb, struct nfs4_cb_fattr, ncf_getattr); - struct nfs4_cb_compound_hdr hdr = { - .ident = cb->cb_clp->cl_cb_ident, - .minorversion = cb->cb_clp->cl_minorversion, - }; - - encode_cb_compound4args(xdr, &hdr); - encode_cb_sequence4args(xdr, cb, &hdr); - encode_cb_getattr4args(xdr, &hdr, ncf); - encode_cb_nops(&hdr); -} - -/* * 20.2. Operation 4: CB_RECALL - Recall a Delegation */ static void nfs4_xdr_enc_cb_recall(struct rpc_rqst *req, struct xdr_stream *xdr, @@ -606,42 +548,6 @@ static int nfs4_xdr_dec_cb_null(struct rpc_rqst *req, struct xdr_stream *xdr, } /* - * 20.1. Operation 3: CB_GETATTR - Get Attributes - */ -static int nfs4_xdr_dec_cb_getattr(struct rpc_rqst *rqstp, - struct xdr_stream *xdr, - void *data) -{ - struct nfsd4_callback *cb = data; - struct nfs4_cb_compound_hdr hdr; - int status; - u32 bitmap[3] = {0}; - u32 attrlen; - struct nfs4_cb_fattr *ncf = - container_of(cb, struct nfs4_cb_fattr, ncf_getattr); - - status = decode_cb_compound4res(xdr, &hdr); - if (unlikely(status)) - return status; - - status = decode_cb_sequence4res(xdr, cb); - if (unlikely(status || cb->cb_seq_status)) - return status; - - status = decode_cb_op_status(xdr, OP_CB_GETATTR, &cb->cb_status); - if (status) - return status; - if (xdr_stream_decode_uint32_array(xdr, bitmap, 3) < 0) - return -NFSERR_BAD_XDR; - if (xdr_stream_decode_u32(xdr, &attrlen) < 0) - return -NFSERR_BAD_XDR; - if (attrlen > (sizeof(ncf->ncf_cb_change) + sizeof(ncf->ncf_cb_fsize))) - return -NFSERR_BAD_XDR; - status = decode_cb_fattr4(xdr, bitmap, ncf); - return status; -} - -/* * 20.2. Operation 4: CB_RECALL - Recall a Delegation */ static int nfs4_xdr_dec_cb_recall(struct rpc_rqst *rqstp, @@ -949,7 +855,6 @@ static const struct rpc_procinfo nfs4_cb_procedures[] = { PROC(CB_NOTIFY_LOCK, COMPOUND, cb_notify_lock, cb_notify_lock), PROC(CB_OFFLOAD, COMPOUND, cb_offload, cb_offload), PROC(CB_RECALL_ANY, COMPOUND, cb_recall_any, cb_recall_any), - PROC(CB_GETATTR, COMPOUND, cb_getattr, cb_getattr), }; static unsigned int nfs4_cb_counts[ARRAY_SIZE(nfs4_cb_procedures)]; diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 40415929e2ae..3edbfa0233e6 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -127,7 +127,6 @@ static void free_session(struct nfsd4_session *); static const struct nfsd4_callback_ops nfsd4_cb_recall_ops; static const struct nfsd4_callback_ops nfsd4_cb_notify_lock_ops; -static const struct nfsd4_callback_ops nfsd4_cb_getattr_ops; static struct workqueue_struct *laundry_wq; @@ -1190,10 +1189,6 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp, dp->dl_recalled = false; nfsd4_init_cb(&dp->dl_recall, dp->dl_stid.sc_client, &nfsd4_cb_recall_ops, NFSPROC4_CLNT_CB_RECALL); - nfsd4_init_cb(&dp->dl_cb_fattr.ncf_getattr, dp->dl_stid.sc_client, - &nfsd4_cb_getattr_ops, NFSPROC4_CLNT_CB_GETATTR); - dp->dl_cb_fattr.ncf_file_modified = false; - dp->dl_cb_fattr.ncf_cb_bmap[0] = FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE; get_nfs4_file(fp); dp->dl_stid.sc_file = fp; return dp; @@ -2901,56 +2896,11 @@ nfsd4_cb_recall_any_release(struct nfsd4_callback *cb) spin_unlock(&nn->client_lock); } -static int -nfsd4_cb_getattr_done(struct nfsd4_callback *cb, struct rpc_task *task) -{ - struct nfs4_cb_fattr *ncf = - container_of(cb, struct nfs4_cb_fattr, ncf_getattr); - - ncf->ncf_cb_status = task->tk_status; - switch (task->tk_status) { - case -NFS4ERR_DELAY: - rpc_delay(task, 2 * HZ); - return 0; - default: - return 1; - } -} - -static void -nfsd4_cb_getattr_release(struct nfsd4_callback *cb) -{ - struct nfs4_cb_fattr *ncf = - container_of(cb, struct nfs4_cb_fattr, ncf_getattr); - struct nfs4_delegation *dp = - container_of(ncf, struct nfs4_delegation, dl_cb_fattr); - - nfs4_put_stid(&dp->dl_stid); - clear_bit(CB_GETATTR_BUSY, &ncf->ncf_cb_flags); - wake_up_bit(&ncf->ncf_cb_flags, CB_GETATTR_BUSY); -} - static const struct nfsd4_callback_ops nfsd4_cb_recall_any_ops = { .done = nfsd4_cb_recall_any_done, .release = nfsd4_cb_recall_any_release, }; -static const struct nfsd4_callback_ops nfsd4_cb_getattr_ops = { - .done = nfsd4_cb_getattr_done, - .release = nfsd4_cb_getattr_release, -}; - -void nfs4_cb_getattr(struct nfs4_cb_fattr *ncf) -{ - struct nfs4_delegation *dp = - container_of(ncf, struct nfs4_delegation, dl_cb_fattr); - - if (test_and_set_bit(CB_GETATTR_BUSY, &ncf->ncf_cb_flags)) - return; - refcount_inc(&dp->dl_stid.sc_count); - nfsd4_run_cb(&ncf->ncf_getattr); -} - static struct nfs4_client *create_client(struct xdr_netobj name, struct svc_rqst *rqstp, nfs4_verifier *verf) { @@ -5685,8 +5635,6 @@ nfs4_open_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, struct svc_fh *parent = NULL; int cb_up; int status = 0; - struct kstat stat; - struct path path; cb_up = nfsd4_cb_channel_good(oo->oo_owner.so_client); open->op_recall = false; @@ -5724,18 +5672,6 @@ nfs4_open_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE) { open->op_delegate_type = NFS4_OPEN_DELEGATE_WRITE; trace_nfsd_deleg_write(&dp->dl_stid.sc_stateid); - path.mnt = currentfh->fh_export->ex_path.mnt; - path.dentry = currentfh->fh_dentry; - if (vfs_getattr(&path, &stat, - (STATX_SIZE | STATX_CTIME | STATX_CHANGE_COOKIE), - AT_STATX_SYNC_AS_STAT)) { - nfs4_put_stid(&dp->dl_stid); - destroy_delegation(dp); - goto out_no_deleg; - } - dp->dl_cb_fattr.ncf_cur_fsize = stat.size; - dp->dl_cb_fattr.ncf_initial_cinfo = - nfsd4_change_attribute(&stat, d_inode(currentfh->fh_dentry)); } else { open->op_delegate_type = NFS4_OPEN_DELEGATE_READ; trace_nfsd_deleg_read(&dp->dl_stid.sc_stateid); @@ -8492,8 +8428,6 @@ nfsd4_get_writestateid(struct nfsd4_compound_state *cstate, * nfsd4_deleg_getattr_conflict - Recall if GETATTR causes conflict * @rqstp: RPC transaction context * @inode: file to be checked for a conflict - * @modified: return true if file was modified - * @size: new size of file if modified is true * * This function is called when there is a conflict between a write * delegation and a change/size GETATTR from another client. The server @@ -8502,23 +8436,21 @@ nfsd4_get_writestateid(struct nfsd4_compound_state *cstate, * delegation before replying to the GETATTR. See RFC 8881 section * 18.7.4. * + * The current implementation does not support CB_GETATTR yet. However + * this can avoid recalling the delegation could be added in follow up + * work. + * * Returns 0 if there is no conflict; otherwise an nfs_stat * code is returned. */ __be32 -nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct inode *inode, - bool *modified, u64 *size) +nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct inode *inode) { + __be32 status; struct file_lock_context *ctx; - struct nfs4_delegation *dp; - struct nfs4_cb_fattr *ncf; struct file_lock *fl; - struct iattr attrs; - __be32 status; - - might_sleep(); + struct nfs4_delegation *dp; - *modified = false; ctx = locks_inode_context(inode); if (!ctx) return 0; @@ -8545,34 +8477,10 @@ nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct inode *inode, break_lease: spin_unlock(&ctx->flc_lock); nfsd_stats_wdeleg_getattr_inc(); - - dp = fl->fl_owner; - ncf = &dp->dl_cb_fattr; - nfs4_cb_getattr(&dp->dl_cb_fattr); - wait_on_bit(&ncf->ncf_cb_flags, CB_GETATTR_BUSY, TASK_INTERRUPTIBLE); - if (ncf->ncf_cb_status) { - status = nfserrno(nfsd_open_break_lease(inode, NFSD_MAY_READ)); - if (status != nfserr_jukebox || - !nfsd_wait_for_delegreturn(rqstp, inode)) - return status; - } - if (!ncf->ncf_file_modified && - (ncf->ncf_initial_cinfo != ncf->ncf_cb_change || - ncf->ncf_cur_fsize != ncf->ncf_cb_fsize)) - ncf->ncf_file_modified = true; - if (ncf->ncf_file_modified) { - /* - * The server would not update the file's metadata - * with the client's modified size. - */ - attrs.ia_mtime = attrs.ia_ctime = current_time(inode); - attrs.ia_valid = ATTR_MTIME | ATTR_CTIME; - setattr_copy(&nop_mnt_idmap, inode, &attrs); - mark_inode_dirty(inode); - ncf->ncf_cur_fsize = ncf->ncf_cb_fsize; - *size = ncf->ncf_cur_fsize; - *modified = true; - } + status = nfserrno(nfsd_open_break_lease(inode, NFSD_MAY_READ)); + if (status != nfserr_jukebox || + !nfsd_wait_for_delegreturn(rqstp, inode)) + return status; return 0; } break; diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index ec4ed6206df1..b499fe9caa32 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -3505,9 +3505,7 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, u32 attrmask[3]; unsigned long mask[2]; } u; - bool file_modified; unsigned long bit; - u64 size = 0; WARN_ON_ONCE(bmval[1] & NFSD_WRITEONLY_ATTRS_WORD1); WARN_ON_ONCE(!nfsd_attrs_supported(minorversion, bmval)); @@ -3534,8 +3532,7 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, } args.size = 0; if (u.attrmask[0] & (FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE)) { - status = nfsd4_deleg_getattr_conflict(rqstp, d_inode(dentry), - &file_modified, &size); + status = nfsd4_deleg_getattr_conflict(rqstp, d_inode(dentry)); if (status) goto out; } @@ -3545,7 +3542,7 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, AT_STATX_SYNC_AS_STAT); if (err) goto out_nfserr; - args.size = file_modified ? size : args.stat.size; + args.size = args.stat.size; if (!(args.stat.result_mask & STATX_BTIME)) /* underlying FS does not offer btime so we can't share it */ diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 3e15b72f421d..87fed75808ff 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -693,6 +693,7 @@ static ssize_t __write_ports_addfd(char *buf, struct net *net, const struct cred char *mesg = buf; int fd, err; struct nfsd_net *nn = net_generic(net, nfsd_net_id); + struct svc_serv *serv; err = get_int(&mesg, &fd); if (err != 0 || fd < 0) @@ -703,13 +704,15 @@ static ssize_t __write_ports_addfd(char *buf, struct net *net, const struct cred if (err != 0) return err; - err = svc_addsock(nn->nfsd_serv, net, fd, buf, SIMPLE_TRANSACTION_LIMIT, cred); + serv = nn->nfsd_serv; + err = svc_addsock(serv, net, fd, buf, SIMPLE_TRANSACTION_LIMIT, cred); - if (err >= 0 && - !nn->nfsd_serv->sv_nrthreads && !xchg(&nn->keep_active, 1)) - svc_get(nn->nfsd_serv); + if (err < 0 && !serv->sv_nrthreads && !nn->keep_active) + nfsd_last_thread(net); + else if (err >= 0 && !serv->sv_nrthreads && !xchg(&nn->keep_active, 1)) + svc_get(serv); - nfsd_put(net); + svc_put(serv); return err; } @@ -723,6 +726,7 @@ static ssize_t __write_ports_addxprt(char *buf, struct net *net, const struct cr struct svc_xprt *xprt; int port, err; struct nfsd_net *nn = net_generic(net, nfsd_net_id); + struct svc_serv *serv; if (sscanf(buf, "%15s %5u", transport, &port) != 2) return -EINVAL; @@ -735,29 +739,33 @@ static ssize_t __write_ports_addxprt(char *buf, struct net *net, const struct cr if (err != 0) return err; - err = svc_xprt_create(nn->nfsd_serv, transport, net, + serv = nn->nfsd_serv; + err = svc_xprt_create(serv, transport, net, PF_INET, port, SVC_SOCK_ANONYMOUS, cred); if (err < 0) goto out_err; - err = svc_xprt_create(nn->nfsd_serv, transport, net, + err = svc_xprt_create(serv, transport, net, PF_INET6, port, SVC_SOCK_ANONYMOUS, cred); if (err < 0 && err != -EAFNOSUPPORT) goto out_close; - if (!nn->nfsd_serv->sv_nrthreads && !xchg(&nn->keep_active, 1)) - svc_get(nn->nfsd_serv); + if (!serv->sv_nrthreads && !xchg(&nn->keep_active, 1)) + svc_get(serv); - nfsd_put(net); + svc_put(serv); return 0; out_close: - xprt = svc_find_xprt(nn->nfsd_serv, transport, net, PF_INET, port); + xprt = svc_find_xprt(serv, transport, net, PF_INET, port); if (xprt != NULL) { svc_xprt_close(xprt); svc_xprt_put(xprt); } out_err: - nfsd_put(net); + if (!serv->sv_nrthreads && !nn->keep_active) + nfsd_last_thread(net); + + svc_put(serv); return err; } @@ -1510,11 +1518,10 @@ int nfsd_nl_rpc_status_get_start(struct netlink_callback *cb) int ret = -ENODEV; mutex_lock(&nfsd_mutex); - if (nn->nfsd_serv) { - svc_get(nn->nfsd_serv); + if (nn->nfsd_serv) ret = 0; - } - mutex_unlock(&nfsd_mutex); + else + mutex_unlock(&nfsd_mutex); return ret; } @@ -1686,8 +1693,6 @@ out: */ int nfsd_nl_rpc_status_get_done(struct netlink_callback *cb) { - mutex_lock(&nfsd_mutex); - nfsd_put(sock_net(cb->skb->sk)); mutex_unlock(&nfsd_mutex); return 0; diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index f5ff42f41ee7..9ed0e08d16c2 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -113,13 +113,6 @@ int nfsd_pool_stats_open(struct inode *, struct file *); int nfsd_pool_stats_release(struct inode *, struct file *); void nfsd_shutdown_threads(struct net *net); -static inline void nfsd_put(struct net *net) -{ - struct nfsd_net *nn = net_generic(net, nfsd_net_id); - - svc_put(nn->nfsd_serv); -} - bool i_am_nfsd(void); struct nfsdfs_client { @@ -155,6 +148,7 @@ int nfsd_vers(struct nfsd_net *nn, int vers, enum vers_op change); int nfsd_minorversion(struct nfsd_net *nn, u32 minorversion, enum vers_op change); void nfsd_reset_versions(struct nfsd_net *nn); int nfsd_create_serv(struct net *net); +void nfsd_last_thread(struct net *net); extern int nfsd_max_blksize; diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index fe61d9bbcc1f..7a2bc8e82a63 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -542,7 +542,7 @@ static struct notifier_block nfsd_inet6addr_notifier = { /* Only used under nfsd_mutex, so this atomic may be overkill: */ static atomic_t nfsd_notifier_refcount = ATOMIC_INIT(0); -static void nfsd_last_thread(struct net *net) +void nfsd_last_thread(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct svc_serv *serv = nn->nfsd_serv; @@ -955,7 +955,6 @@ nfsd(void *vrqstp) rqstp->rq_server->sv_maxconn = nn->max_connections; svc_recv(rqstp); - validate_process_creds(); } atomic_dec(&nfsdstats.th_cnt); diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index f96eaa8e9413..41bdc913fa71 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -117,24 +117,6 @@ struct nfs4_cpntf_state { time64_t cpntf_time; /* last time stateid used */ }; -struct nfs4_cb_fattr { - struct nfsd4_callback ncf_getattr; - u32 ncf_cb_status; - u32 ncf_cb_bmap[1]; - - /* from CB_GETATTR reply */ - u64 ncf_cb_change; - u64 ncf_cb_fsize; - - unsigned long ncf_cb_flags; - bool ncf_file_modified; - u64 ncf_initial_cinfo; - u64 ncf_cur_fsize; -}; - -/* bits for ncf_cb_flags */ -#define CB_GETATTR_BUSY 0 - /* * Represents a delegation stateid. The nfs4_client holds references to these * and they are put when it is being destroyed or when the delegation is @@ -168,9 +150,6 @@ struct nfs4_delegation { int dl_retries; struct nfsd4_callback dl_recall; bool dl_recalled; - - /* for CB_GETATTR */ - struct nfs4_cb_fattr dl_cb_fattr; }; #define cb_to_delegation(cb) \ @@ -661,7 +640,6 @@ enum nfsd4_cb_op { NFSPROC4_CLNT_CB_SEQUENCE, NFSPROC4_CLNT_CB_NOTIFY_LOCK, NFSPROC4_CLNT_CB_RECALL_ANY, - NFSPROC4_CLNT_CB_GETATTR, }; /* Returns true iff a is later than b: */ @@ -754,6 +732,5 @@ static inline bool try_to_expire_client(struct nfs4_client *clp) } extern __be32 nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, - struct inode *inode, bool *file_modified, u64 *size); -extern void nfs4_cb_getattr(struct nfs4_cb_fattr *ncf); + struct inode *inode); #endif /* NFSD4_STATE_H */ diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index fbbea7498f02..707ef21f275b 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -901,7 +901,6 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int host_err; bool retried = false; - validate_process_creds(); /* * If we get here, then the client has already done an "open", * and (hopefully) checked permission - so allow OWNER_OVERRIDE @@ -926,7 +925,6 @@ retry: } err = nfserrno(host_err); } - validate_process_creds(); return err; } @@ -943,12 +941,7 @@ int nfsd_open_verified(struct svc_rqst *rqstp, struct svc_fh *fhp, int may_flags, struct file **filp) { - int err; - - validate_process_creds(); - err = __nfsd_open(rqstp, fhp, S_IFREG, may_flags, filp); - validate_process_creds(); - return err; + return __nfsd_open(rqstp, fhp, S_IFREG, may_flags, filp); } /* @@ -1046,7 +1039,10 @@ __be32 nfsd_splice_read(struct svc_rqst *rqstp, struct svc_fh *fhp, ssize_t host_err; trace_nfsd_read_splice(rqstp, fhp, offset, *count); - host_err = splice_direct_to_actor(file, &sd, nfsd_direct_splice_actor); + host_err = rw_verify_area(READ, file, &offset, *count); + if (!host_err) + host_err = splice_direct_to_actor(file, &sd, + nfsd_direct_splice_actor); return nfsd_finish_read(rqstp, fhp, file, offset, count, eof, host_err); } @@ -1183,9 +1179,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf, since = READ_ONCE(file->f_wb_err); if (verf) nfsd_copy_write_verifier(verf, nn); - file_start_write(file); host_err = vfs_iter_write(file, &iter, &pos, flags); - file_end_write(file); if (host_err < 0) { commit_reset_write_verifier(nn, rqstp, host_err); goto out_nfserr; diff --git a/fs/nfsd/xdr4cb.h b/fs/nfsd/xdr4cb.h index e8b00309c449..0d39af1b00a0 100644 --- a/fs/nfsd/xdr4cb.h +++ b/fs/nfsd/xdr4cb.h @@ -54,21 +54,3 @@ #define NFS4_dec_cb_recall_any_sz (cb_compound_dec_hdr_sz + \ cb_sequence_dec_sz + \ op_dec_sz) - -/* - * 1: CB_GETATTR opcode (32-bit) - * N: file_handle - * 1: number of entry in attribute array (32-bit) - * 1: entry 0 in attribute array (32-bit) - */ -#define NFS4_enc_cb_getattr_sz (cb_compound_enc_hdr_sz + \ - cb_sequence_enc_sz + \ - 1 + enc_nfs4_fh_sz + 1 + 1) -/* - * 4: fattr_bitmap_maxsz - * 1: attribute array len - * 2: change attr (64-bit) - * 2: size (64-bit) - */ -#define NFS4_dec_cb_getattr_sz (cb_compound_dec_hdr_sz + \ - cb_sequence_dec_sz + 4 + 1 + 2 + 2 + op_dec_sz) diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index f861f3a0bf5c..2ead36dfa2a3 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -214,7 +214,7 @@ static bool nilfs_dirty_folio(struct address_space *mapping, /* * The page may not be locked, eg if called from try_to_unmap_one() */ - spin_lock(&mapping->private_lock); + spin_lock(&mapping->i_private_lock); head = folio_buffers(folio); if (head) { struct buffer_head *bh = head; @@ -230,7 +230,7 @@ static bool nilfs_dirty_folio(struct address_space *mapping, } else if (ret) { nr_dirty = 1 << (folio_shift(folio) - inode->i_blkbits); } - spin_unlock(&mapping->private_lock); + spin_unlock(&mapping->i_private_lock); if (nr_dirty) nilfs_set_file_dirty(inode, nr_dirty); diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index a5d1fa4e7552..df8674173b22 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -1314,15 +1314,7 @@ nilfs_mount(struct file_system_type *fs_type, int flags, return ERR_CAST(s); if (!s->s_root) { - /* - * We drop s_umount here because we need to open the bdev and - * bdev->open_mutex ranks above s_umount (blkdev_put() -> - * __invalidate_device()). It is safe because we have active sb - * reference and SB_BORN is not set yet. - */ - up_write(&s->s_umount); err = setup_bdev_super(s, flags, NULL); - down_write(&s->s_umount); if (!err) err = nilfs_fill_super(s, data, flags & SB_SILENT ? 1 : 0); diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c index 71e31e789b29..548f3b51aa5f 100644 --- a/fs/ntfs/aops.c +++ b/fs/ntfs/aops.c @@ -1690,7 +1690,7 @@ const struct address_space_operations ntfs_mst_aops = { * * If the page does not have buffers, we create them and set them uptodate. * The page may not be locked which is why we need to handle the buffers under - * the mapping->private_lock. Once the buffers are marked dirty we no longer + * the mapping->i_private_lock. Once the buffers are marked dirty we no longer * need the lock since try_to_free_buffers() does not free dirty buffers. */ void mark_ntfs_record_dirty(struct page *page, const unsigned int ofs) { @@ -1702,11 +1702,11 @@ void mark_ntfs_record_dirty(struct page *page, const unsigned int ofs) { BUG_ON(!PageUptodate(page)); end = ofs + ni->itype.index.block_size; bh_size = VFS_I(ni)->i_sb->s_blocksize; - spin_lock(&mapping->private_lock); + spin_lock(&mapping->i_private_lock); if (unlikely(!page_has_buffers(page))) { - spin_unlock(&mapping->private_lock); + spin_unlock(&mapping->i_private_lock); bh = head = alloc_page_buffers(page, bh_size, true); - spin_lock(&mapping->private_lock); + spin_lock(&mapping->i_private_lock); if (likely(!page_has_buffers(page))) { struct buffer_head *tail; @@ -1730,7 +1730,7 @@ void mark_ntfs_record_dirty(struct page *page, const unsigned int ofs) { break; set_buffer_dirty(bh); } while ((bh = bh->b_this_page) != head); - spin_unlock(&mapping->private_lock); + spin_unlock(&mapping->i_private_lock); filemap_dirty_folio(mapping, page_folio(page)); if (unlikely(buffers_to_free)) { do { diff --git a/fs/ntfs/dir.c b/fs/ntfs/dir.c index 4596c90e7b7c..629723a8d712 100644 --- a/fs/ntfs/dir.c +++ b/fs/ntfs/dir.c @@ -1462,7 +1462,8 @@ static int ntfs_dir_open(struct inode *vi, struct file *filp) /** * ntfs_dir_fsync - sync a directory to disk * @filp: directory to be synced - * @dentry: dentry describing the directory to sync + * @start: offset in bytes of the beginning of data range to sync + * @end: offset in bytes of the end of data range (inclusive) * @datasync: if non-zero only flush user data and not metadata * * Data integrity sync of a directory to disk. Used for fsync, fdatasync, and diff --git a/fs/open.c b/fs/open.c index 02dc608d40d8..a84d21e55c39 100644 --- a/fs/open.c +++ b/fs/open.c @@ -304,6 +304,10 @@ int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len) if (ret) return ret; + ret = fsnotify_file_area_perm(file, MAY_WRITE, &offset, len); + if (ret) + return ret; + if (S_ISFIFO(inode->i_mode)) return -ESPIPE; @@ -442,7 +446,8 @@ static const struct cred *access_override_creds(void) * 'get_current_cred()' function), that will clear the * non_rcu field, because now that other user may be * expecting RCU freeing. But normal thread-synchronous - * cred accesses will keep things non-RCY. + * cred accesses will keep things non-racy to avoid RCU + * freeing. */ override_cred->non_rcu = 1; @@ -1088,8 +1093,6 @@ struct file *dentry_open(const struct path *path, int flags, int error; struct file *f; - validate_creds(cred); - /* We must always pass in a valid mount pointer. */ BUG_ON(!path->mnt); @@ -1128,7 +1131,6 @@ struct file *dentry_create(const struct path *path, int flags, umode_t mode, struct file *f; int error; - validate_creds(cred); f = alloc_empty_file(flags, cred); if (IS_ERR(f)) return f; @@ -1180,44 +1182,6 @@ struct file *kernel_file_open(const struct path *path, int flags, } EXPORT_SYMBOL_GPL(kernel_file_open); -/** - * backing_file_open - open a backing file for kernel internal use - * @user_path: path that the user reuqested to open - * @flags: open flags - * @real_path: path of the backing file - * @cred: credentials for open - * - * Open a backing file for a stackable filesystem (e.g., overlayfs). - * @user_path may be on the stackable filesystem and @real_path on the - * underlying filesystem. In this case, we want to be able to return the - * @user_path of the stackable filesystem. This is done by embedding the - * returned file into a container structure that also stores the stacked - * file's path, which can be retrieved using backing_file_user_path(). - */ -struct file *backing_file_open(const struct path *user_path, int flags, - const struct path *real_path, - const struct cred *cred) -{ - struct file *f; - int error; - - f = alloc_empty_backing_file(flags, cred); - if (IS_ERR(f)) - return f; - - path_get(user_path); - *backing_file_user_path(f) = *user_path; - f->f_path = *real_path; - error = do_dentry_open(f, d_inode(real_path->dentry), NULL); - if (error) { - fput(f); - f = ERR_PTR(error); - } - - return f; -} -EXPORT_SYMBOL_GPL(backing_file_open); - #define WILL_CREATE(flags) (flags & (O_CREAT | __O_TMPFILE)) #define O_PATH_FLAGS (O_DIRECTORY | O_NOFOLLOW | O_PATH | O_CLOEXEC) @@ -1577,7 +1541,7 @@ SYSCALL_DEFINE1(close, unsigned int, fd) int retval; struct file *file; - file = close_fd_get_file(fd); + file = file_close_fd(fd); if (!file) return -EBADF; diff --git a/fs/overlayfs/Kconfig b/fs/overlayfs/Kconfig index fec5020c3495..2ac67e04a6fb 100644 --- a/fs/overlayfs/Kconfig +++ b/fs/overlayfs/Kconfig @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only config OVERLAY_FS tristate "Overlay filesystem support" + select FS_STACK select EXPORTFS help An overlay filesystem combines two filesystems - an 'upper' filesystem diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 4382881b0709..45cadc3aed85 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -230,6 +230,19 @@ static int ovl_copy_fileattr(struct inode *inode, const struct path *old, return ovl_real_fileattr_set(new, &newfa); } +static int ovl_verify_area(loff_t pos, loff_t pos2, loff_t len, loff_t totlen) +{ + loff_t tmp; + + if (WARN_ON_ONCE(pos != pos2)) + return -EIO; + if (WARN_ON_ONCE(pos < 0 || len < 0 || totlen < 0)) + return -EIO; + if (WARN_ON_ONCE(check_add_overflow(pos, len, &tmp))) + return -EIO; + return 0; +} + static int ovl_copy_up_file(struct ovl_fs *ofs, struct dentry *dentry, struct file *new_file, loff_t len) { @@ -244,13 +257,20 @@ static int ovl_copy_up_file(struct ovl_fs *ofs, struct dentry *dentry, int error = 0; ovl_path_lowerdata(dentry, &datapath); - if (WARN_ON(datapath.dentry == NULL)) + if (WARN_ON_ONCE(datapath.dentry == NULL) || + WARN_ON_ONCE(len < 0)) return -EIO; old_file = ovl_path_open(&datapath, O_LARGEFILE | O_RDONLY); if (IS_ERR(old_file)) return PTR_ERR(old_file); + error = rw_verify_area(READ, old_file, &old_pos, len); + if (!error) + error = rw_verify_area(WRITE, new_file, &new_pos, len); + if (error) + goto out_fput; + /* Try to use clone_file_range to clone up within the same fs */ ovl_start_write(dentry); cloned = do_clone_file_range(old_file, 0, new_file, 0, len, 0); @@ -265,7 +285,7 @@ static int ovl_copy_up_file(struct ovl_fs *ofs, struct dentry *dentry, while (len) { size_t this_len = OVL_COPY_UP_CHUNK_SIZE; - long bytes; + ssize_t bytes; if (len < this_len) this_len = len; @@ -309,11 +329,13 @@ static int ovl_copy_up_file(struct ovl_fs *ofs, struct dentry *dentry, } } - ovl_start_write(dentry); + error = ovl_verify_area(old_pos, new_pos, this_len, len); + if (error) + break; + bytes = do_splice_direct(old_file, &old_pos, new_file, &new_pos, this_len, SPLICE_F_MOVE); - ovl_end_write(dentry); if (bytes <= 0) { error = bytes; break; @@ -753,15 +775,16 @@ static int ovl_copy_up_workdir(struct ovl_copy_up_ctx *c) path.dentry = temp; err = ovl_copy_up_data(c, &path); /* - * We cannot hold lock_rename() throughout this helper, because or + * We cannot hold lock_rename() throughout this helper, because of * lock ordering with sb_writers, which shouldn't be held when calling * ovl_copy_up_data(), so lock workdir and destdir and make sure that * temp wasn't moved before copy up completion or cleanup. - * If temp was moved, abort without the cleanup. */ ovl_start_write(c->dentry); if (lock_rename(c->workdir, c->destdir) != NULL || temp->d_parent != c->workdir) { + /* temp or workdir moved underneath us? abort without cleanup */ + dput(temp); err = -EIO; goto unlock; } else if (err) { diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index 131621daeb13..05536964d37f 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -9,25 +9,11 @@ #include <linux/xattr.h> #include <linux/uio.h> #include <linux/uaccess.h> -#include <linux/splice.h> #include <linux/security.h> -#include <linux/mm.h> #include <linux/fs.h> +#include <linux/backing-file.h> #include "overlayfs.h" -#include "../internal.h" /* for sb_init_dio_done_wq */ - -struct ovl_aio_req { - struct kiocb iocb; - refcount_t ref; - struct kiocb *orig_iocb; - /* used for aio completion */ - struct work_struct work; - long res; -}; - -static struct kmem_cache *ovl_aio_request_cachep; - static char ovl_whatisit(struct inode *inode, struct inode *realinode) { if (realinode != ovl_inode_upper(inode)) @@ -274,83 +260,16 @@ static void ovl_file_accessed(struct file *file) touch_atime(&file->f_path); } -#define OVL_IOCB_MASK \ - (IOCB_NOWAIT | IOCB_HIPRI | IOCB_DSYNC | IOCB_SYNC | IOCB_APPEND) - -static rwf_t iocb_to_rw_flags(int flags) -{ - return (__force rwf_t)(flags & OVL_IOCB_MASK); -} - -static inline void ovl_aio_put(struct ovl_aio_req *aio_req) -{ - if (refcount_dec_and_test(&aio_req->ref)) { - fput(aio_req->iocb.ki_filp); - kmem_cache_free(ovl_aio_request_cachep, aio_req); - } -} - -static void ovl_aio_cleanup_handler(struct ovl_aio_req *aio_req) -{ - struct kiocb *iocb = &aio_req->iocb; - struct kiocb *orig_iocb = aio_req->orig_iocb; - - if (iocb->ki_flags & IOCB_WRITE) { - kiocb_end_write(iocb); - ovl_file_modified(orig_iocb->ki_filp); - } - - orig_iocb->ki_pos = iocb->ki_pos; - ovl_aio_put(aio_req); -} - -static void ovl_aio_rw_complete(struct kiocb *iocb, long res) -{ - struct ovl_aio_req *aio_req = container_of(iocb, - struct ovl_aio_req, iocb); - struct kiocb *orig_iocb = aio_req->orig_iocb; - - ovl_aio_cleanup_handler(aio_req); - orig_iocb->ki_complete(orig_iocb, res); -} - -static void ovl_aio_complete_work(struct work_struct *work) -{ - struct ovl_aio_req *aio_req = container_of(work, - struct ovl_aio_req, work); - - ovl_aio_rw_complete(&aio_req->iocb, aio_req->res); -} - -static void ovl_aio_queue_completion(struct kiocb *iocb, long res) -{ - struct ovl_aio_req *aio_req = container_of(iocb, - struct ovl_aio_req, iocb); - struct kiocb *orig_iocb = aio_req->orig_iocb; - - /* - * Punt to a work queue to serialize updates of mtime/size. - */ - aio_req->res = res; - INIT_WORK(&aio_req->work, ovl_aio_complete_work); - queue_work(file_inode(orig_iocb->ki_filp)->i_sb->s_dio_done_wq, - &aio_req->work); -} - -static int ovl_init_aio_done_wq(struct super_block *sb) -{ - if (sb->s_dio_done_wq) - return 0; - - return sb_init_dio_done_wq(sb); -} - static ssize_t ovl_read_iter(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct fd real; - const struct cred *old_cred; ssize_t ret; + struct backing_file_ctx ctx = { + .cred = ovl_creds(file_inode(file)->i_sb), + .user_file = file, + .accessed = ovl_file_accessed, + }; if (!iov_iter_count(iter)) return 0; @@ -359,37 +278,8 @@ static ssize_t ovl_read_iter(struct kiocb *iocb, struct iov_iter *iter) if (ret) return ret; - ret = -EINVAL; - if (iocb->ki_flags & IOCB_DIRECT && - !(real.file->f_mode & FMODE_CAN_ODIRECT)) - goto out_fdput; - - old_cred = ovl_override_creds(file_inode(file)->i_sb); - if (is_sync_kiocb(iocb)) { - rwf_t rwf = iocb_to_rw_flags(iocb->ki_flags); - - ret = vfs_iter_read(real.file, iter, &iocb->ki_pos, rwf); - } else { - struct ovl_aio_req *aio_req; - - ret = -ENOMEM; - aio_req = kmem_cache_zalloc(ovl_aio_request_cachep, GFP_KERNEL); - if (!aio_req) - goto out; - - aio_req->orig_iocb = iocb; - kiocb_clone(&aio_req->iocb, iocb, get_file(real.file)); - aio_req->iocb.ki_complete = ovl_aio_rw_complete; - refcount_set(&aio_req->ref, 2); - ret = vfs_iocb_iter_read(real.file, &aio_req->iocb, iter); - ovl_aio_put(aio_req); - if (ret != -EIOCBQUEUED) - ovl_aio_cleanup_handler(aio_req); - } -out: - revert_creds(old_cred); - ovl_file_accessed(file); -out_fdput: + ret = backing_file_read_iter(real.file, iter, iocb, iocb->ki_flags, + &ctx); fdput(real); return ret; @@ -400,9 +290,13 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter) struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); struct fd real; - const struct cred *old_cred; ssize_t ret; int ifl = iocb->ki_flags; + struct backing_file_ctx ctx = { + .cred = ovl_creds(inode->i_sb), + .user_file = file, + .end_write = ovl_file_modified, + }; if (!iov_iter_count(iter)) return 0; @@ -410,19 +304,11 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter) inode_lock(inode); /* Update mode */ ovl_copyattr(inode); - ret = file_remove_privs(file); - if (ret) - goto out_unlock; ret = ovl_real_fdget(file, &real); if (ret) goto out_unlock; - ret = -EINVAL; - if (iocb->ki_flags & IOCB_DIRECT && - !(real.file->f_mode & FMODE_CAN_ODIRECT)) - goto out_fdput; - if (!ovl_should_sync(OVL_FS(inode->i_sb))) ifl &= ~(IOCB_DSYNC | IOCB_SYNC); @@ -431,42 +317,7 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter) * this property in case it is set by the issuer. */ ifl &= ~IOCB_DIO_CALLER_COMP; - - old_cred = ovl_override_creds(file_inode(file)->i_sb); - if (is_sync_kiocb(iocb)) { - rwf_t rwf = iocb_to_rw_flags(ifl); - - file_start_write(real.file); - ret = vfs_iter_write(real.file, iter, &iocb->ki_pos, rwf); - file_end_write(real.file); - /* Update size */ - ovl_file_modified(file); - } else { - struct ovl_aio_req *aio_req; - - ret = ovl_init_aio_done_wq(inode->i_sb); - if (ret) - goto out; - - ret = -ENOMEM; - aio_req = kmem_cache_zalloc(ovl_aio_request_cachep, GFP_KERNEL); - if (!aio_req) - goto out; - - aio_req->orig_iocb = iocb; - kiocb_clone(&aio_req->iocb, iocb, get_file(real.file)); - aio_req->iocb.ki_flags = ifl; - aio_req->iocb.ki_complete = ovl_aio_queue_completion; - refcount_set(&aio_req->ref, 2); - kiocb_start_write(&aio_req->iocb); - ret = vfs_iocb_iter_write(real.file, &aio_req->iocb, iter); - ovl_aio_put(aio_req); - if (ret != -EIOCBQUEUED) - ovl_aio_cleanup_handler(aio_req); - } -out: - revert_creds(old_cred); -out_fdput: + ret = backing_file_write_iter(real.file, iter, iocb, ifl, &ctx); fdput(real); out_unlock: @@ -479,20 +330,21 @@ static ssize_t ovl_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { - const struct cred *old_cred; struct fd real; ssize_t ret; + struct backing_file_ctx ctx = { + .cred = ovl_creds(file_inode(in)->i_sb), + .user_file = in, + .accessed = ovl_file_accessed, + }; ret = ovl_real_fdget(in, &real); if (ret) return ret; - old_cred = ovl_override_creds(file_inode(in)->i_sb); - ret = vfs_splice_read(real.file, ppos, pipe, len, flags); - revert_creds(old_cred); - ovl_file_accessed(in); - + ret = backing_file_splice_read(real.file, ppos, pipe, len, flags, &ctx); fdput(real); + return ret; } @@ -508,30 +360,23 @@ static ssize_t ovl_splice_write(struct pipe_inode_info *pipe, struct file *out, loff_t *ppos, size_t len, unsigned int flags) { struct fd real; - const struct cred *old_cred; struct inode *inode = file_inode(out); ssize_t ret; + struct backing_file_ctx ctx = { + .cred = ovl_creds(inode->i_sb), + .user_file = out, + .end_write = ovl_file_modified, + }; inode_lock(inode); /* Update mode */ ovl_copyattr(inode); - ret = file_remove_privs(out); - if (ret) - goto out_unlock; ret = ovl_real_fdget(out, &real); if (ret) goto out_unlock; - old_cred = ovl_override_creds(inode->i_sb); - file_start_write(real.file); - - ret = iter_file_splice_write(pipe, real.file, ppos, len, flags); - - file_end_write(real.file); - /* Update size */ - ovl_file_modified(out); - revert_creds(old_cred); + ret = backing_file_splice_write(pipe, real.file, ppos, len, flags, &ctx); fdput(real); out_unlock: @@ -569,23 +414,13 @@ static int ovl_fsync(struct file *file, loff_t start, loff_t end, int datasync) static int ovl_mmap(struct file *file, struct vm_area_struct *vma) { struct file *realfile = file->private_data; - const struct cred *old_cred; - int ret; - - if (!realfile->f_op->mmap) - return -ENODEV; + struct backing_file_ctx ctx = { + .cred = ovl_creds(file_inode(file)->i_sb), + .user_file = file, + .accessed = ovl_file_accessed, + }; - if (WARN_ON(file != vma->vm_file)) - return -EIO; - - vma_set_file(vma, realfile); - - old_cred = ovl_override_creds(file_inode(file)->i_sb); - ret = call_mmap(vma->vm_file, vma); - revert_creds(old_cred); - ovl_file_accessed(file); - - return ret; + return backing_file_mmap(realfile, vma, &ctx); } static long ovl_fallocate(struct file *file, int mode, loff_t offset, loff_t len) @@ -778,19 +613,3 @@ const struct file_operations ovl_file_operations = { .copy_file_range = ovl_copy_file_range, .remap_file_range = ovl_remap_file_range, }; - -int __init ovl_aio_request_cache_init(void) -{ - ovl_aio_request_cachep = kmem_cache_create("ovl_aio_req", - sizeof(struct ovl_aio_req), - 0, SLAB_HWCACHE_ALIGN, NULL); - if (!ovl_aio_request_cachep) - return -ENOMEM; - - return 0; -} - -void ovl_aio_request_cache_destroy(void) -{ - kmem_cache_destroy(ovl_aio_request_cachep); -} diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index 05c3dd597fa8..5ba11eb43767 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -425,6 +425,12 @@ int ovl_want_write(struct dentry *dentry); void ovl_drop_write(struct dentry *dentry); struct dentry *ovl_workdir(struct dentry *dentry); const struct cred *ovl_override_creds(struct super_block *sb); + +static inline const struct cred *ovl_creds(struct super_block *sb) +{ + return OVL_FS(sb)->creator_cred; +} + int ovl_can_decode_fh(struct super_block *sb); struct dentry *ovl_indexdir(struct super_block *sb); bool ovl_index_all(struct super_block *sb); @@ -837,8 +843,6 @@ struct dentry *ovl_create_temp(struct ovl_fs *ofs, struct dentry *workdir, /* file.c */ extern const struct file_operations ovl_file_operations; -int __init ovl_aio_request_cache_init(void); -void ovl_aio_request_cache_destroy(void); int ovl_real_fileattr_get(const struct path *realpath, struct fileattr *fa); int ovl_real_fileattr_set(const struct path *realpath, struct fileattr *fa); int ovl_fileattr_get(struct dentry *dentry, struct fileattr *fa); diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index a0967bb25003..bcd4c314a7eb 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -1501,14 +1501,10 @@ static int __init ovl_init(void) if (ovl_inode_cachep == NULL) return -ENOMEM; - err = ovl_aio_request_cache_init(); - if (!err) { - err = register_filesystem(&ovl_fs_type); - if (!err) - return 0; + err = register_filesystem(&ovl_fs_type); + if (!err) + return 0; - ovl_aio_request_cache_destroy(); - } kmem_cache_destroy(ovl_inode_cachep); return err; @@ -1524,7 +1520,6 @@ static void __exit ovl_exit(void) */ rcu_barrier(); kmem_cache_destroy(ovl_inode_cachep); - ovl_aio_request_cache_destroy(); } module_init(ovl_init); diff --git a/fs/pipe.c b/fs/pipe.c index 804a7d789452..8d9286a1f2e8 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -446,6 +446,18 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) bool was_empty = false; bool wake_next_writer = false; + /* + * Reject writing to watch queue pipes before the point where we lock + * the pipe. + * Otherwise, lockdep would be unhappy if the caller already has another + * pipe locked. + * If we had to support locking a normal pipe and a notification pipe at + * the same time, we could set up lockdep annotations for that, but + * since we don't actually need that, it's simpler to just bail here. + */ + if (pipe_has_watch_queue(pipe)) + return -EXDEV; + /* Null write succeeds. */ if (unlikely(total_len == 0)) return 0; @@ -458,11 +470,6 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) goto out; } - if (pipe_has_watch_queue(pipe)) { - ret = -EXDEV; - goto out; - } - /* * If it wasn't empty we try to merge new data into * the last buffer. @@ -1317,6 +1324,11 @@ int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots) pipe->tail = tail; pipe->head = head; + if (!pipe_has_watch_queue(pipe)) { + pipe->max_usage = nr_slots; + pipe->nr_accounted = nr_slots; + } + spin_unlock_irq(&pipe->rd_wait.lock); /* This might have made more room for writers */ @@ -1368,8 +1380,6 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned int arg) if (ret < 0) goto out_revert_acct; - pipe->max_usage = nr_slots; - pipe->nr_accounted = nr_slots; return pipe->max_usage * PAGE_SIZE; out_revert_acct: diff --git a/fs/pnode.c b/fs/pnode.c index e4d0340393d5..a799e0315cc9 100644 --- a/fs/pnode.c +++ b/fs/pnode.c @@ -468,7 +468,7 @@ static void umount_one(struct mount *mnt, struct list_head *to_umount) mnt->mnt.mnt_flags |= MNT_UMOUNT; list_del_init(&mnt->mnt_child); list_del_init(&mnt->mnt_umounting); - list_move_tail(&mnt->mnt_list, to_umount); + move_from_ns(mnt, to_umount); } /* diff --git a/fs/posix_acl.c b/fs/posix_acl.c index a05fe94970ce..e1af20893ebe 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -600,7 +600,7 @@ EXPORT_SYMBOL(__posix_acl_chmod); * the vfsmount must be passed through @idmap. This function will then * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be - * performed on the raw inode simply passs @nop_mnt_idmap. + * performed on the raw inode simply pass @nop_mnt_idmap. */ int posix_acl_chmod(struct mnt_idmap *idmap, struct dentry *dentry, @@ -700,7 +700,7 @@ EXPORT_SYMBOL_GPL(posix_acl_create); * the vfsmount must be passed through @idmap. This function will then * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be - * performed on the raw inode simply passs @nop_mnt_idmap. + * performed on the raw inode simply pass @nop_mnt_idmap. * * Called from set_acl inode operations. */ diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 435b61054b5b..1801e409a061 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -273,7 +273,8 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma) const char *name = NULL; if (file) { - struct inode *inode = file_inode(vma->vm_file); + const struct inode *inode = file_user_inode(vma->vm_file); + dev = inode->i_sb->s_dev; ino = inode->i_ino; pgoff = ((loff_t)vma->vm_pgoff) << PAGE_SHIFT; diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c index 250eb5bf7b52..0a808951b7d3 100644 --- a/fs/proc_namespace.c +++ b/fs/proc_namespace.c @@ -142,13 +142,9 @@ static int show_mountinfo(struct seq_file *m, struct vfsmount *mnt) seq_printf(m, "%i %i %u:%u ", r->mnt_id, r->mnt_parent->mnt_id, MAJOR(sb->s_dev), MINOR(sb->s_dev)); - if (sb->s_op->show_path) { - err = sb->s_op->show_path(m, mnt->mnt_root); - if (err) - goto out; - } else { - seq_dentry(m, mnt->mnt_root, " \t\n\\"); - } + err = show_path(m, mnt->mnt_root); + if (err) + goto out; seq_putc(m, ' '); /* mountpoints outside of chroot jail will give SEQ_SKIP on this */ @@ -283,8 +279,6 @@ static int mounts_open_common(struct inode *inode, struct file *file, p->ns = ns; p->root = root; p->show = show; - INIT_LIST_HEAD(&p->cursor.mnt_list); - p->cursor.mnt.mnt_flags = MNT_CURSOR; return 0; @@ -301,7 +295,6 @@ static int mounts_release(struct inode *inode, struct file *file) struct seq_file *m = file->private_data; struct proc_mounts *p = m->private; path_put(&p->root); - mnt_cursor_del(p->ns, &p->cursor); put_mnt_ns(p->ns); return seq_release_private(inode, file); } diff --git a/fs/read_write.c b/fs/read_write.c index 4771701c896b..d4c036e82b6c 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -354,6 +354,9 @@ out_putf: int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t count) { + int mask = read_write == READ ? MAY_READ : MAY_WRITE; + int ret; + if (unlikely((ssize_t) count < 0)) return -EINVAL; @@ -371,8 +374,11 @@ int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t } } - return security_file_permission(file, - read_write == READ ? MAY_READ : MAY_WRITE); + ret = security_file_permission(file, mask); + if (ret) + return ret; + + return fsnotify_file_area_perm(file, mask, ppos, count); } EXPORT_SYMBOL(rw_verify_area); @@ -773,12 +779,14 @@ static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter, return ret; } -static ssize_t do_iter_read(struct file *file, struct iov_iter *iter, - loff_t *pos, rwf_t flags) +ssize_t vfs_iocb_iter_read(struct file *file, struct kiocb *iocb, + struct iov_iter *iter) { size_t tot_len; ssize_t ret = 0; + if (!file->f_op->read_iter) + return -EINVAL; if (!(file->f_mode & FMODE_READ)) return -EBADF; if (!(file->f_mode & FMODE_CAN_READ)) @@ -787,22 +795,20 @@ static ssize_t do_iter_read(struct file *file, struct iov_iter *iter, tot_len = iov_iter_count(iter); if (!tot_len) goto out; - ret = rw_verify_area(READ, file, pos, tot_len); + ret = rw_verify_area(READ, file, &iocb->ki_pos, tot_len); if (ret < 0) return ret; - if (file->f_op->read_iter) - ret = do_iter_readv_writev(file, iter, pos, READ, flags); - else - ret = do_loop_readv_writev(file, iter, pos, READ, flags); + ret = call_read_iter(file, iocb, iter); out: if (ret >= 0) fsnotify_access(file); return ret; } +EXPORT_SYMBOL(vfs_iocb_iter_read); -ssize_t vfs_iocb_iter_read(struct file *file, struct kiocb *iocb, - struct iov_iter *iter) +ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos, + rwf_t flags) { size_t tot_len; ssize_t ret = 0; @@ -817,33 +823,30 @@ ssize_t vfs_iocb_iter_read(struct file *file, struct kiocb *iocb, tot_len = iov_iter_count(iter); if (!tot_len) goto out; - ret = rw_verify_area(READ, file, &iocb->ki_pos, tot_len); + ret = rw_verify_area(READ, file, ppos, tot_len); if (ret < 0) return ret; - ret = call_read_iter(file, iocb, iter); + ret = do_iter_readv_writev(file, iter, ppos, READ, flags); out: if (ret >= 0) fsnotify_access(file); return ret; } -EXPORT_SYMBOL(vfs_iocb_iter_read); - -ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos, - rwf_t flags) -{ - if (!file->f_op->read_iter) - return -EINVAL; - return do_iter_read(file, iter, ppos, flags); -} EXPORT_SYMBOL(vfs_iter_read); -static ssize_t do_iter_write(struct file *file, struct iov_iter *iter, - loff_t *pos, rwf_t flags) +/* + * Caller is responsible for calling kiocb_end_write() on completion + * if async iocb was queued. + */ +ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb, + struct iov_iter *iter) { size_t tot_len; ssize_t ret = 0; + if (!file->f_op->write_iter) + return -EINVAL; if (!(file->f_mode & FMODE_WRITE)) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) @@ -852,88 +855,127 @@ static ssize_t do_iter_write(struct file *file, struct iov_iter *iter, tot_len = iov_iter_count(iter); if (!tot_len) return 0; - ret = rw_verify_area(WRITE, file, pos, tot_len); + ret = rw_verify_area(WRITE, file, &iocb->ki_pos, tot_len); if (ret < 0) return ret; - if (file->f_op->write_iter) - ret = do_iter_readv_writev(file, iter, pos, WRITE, flags); - else - ret = do_loop_readv_writev(file, iter, pos, WRITE, flags); + kiocb_start_write(iocb); + ret = call_write_iter(file, iocb, iter); + if (ret != -EIOCBQUEUED) + kiocb_end_write(iocb); if (ret > 0) fsnotify_modify(file); + return ret; } +EXPORT_SYMBOL(vfs_iocb_iter_write); -ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb, - struct iov_iter *iter) +ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos, + rwf_t flags) { size_t tot_len; - ssize_t ret = 0; + ssize_t ret; - if (!file->f_op->write_iter) - return -EINVAL; if (!(file->f_mode & FMODE_WRITE)) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; + if (!file->f_op->write_iter) + return -EINVAL; tot_len = iov_iter_count(iter); if (!tot_len) return 0; - ret = rw_verify_area(WRITE, file, &iocb->ki_pos, tot_len); + + ret = rw_verify_area(WRITE, file, ppos, tot_len); if (ret < 0) return ret; - ret = call_write_iter(file, iocb, iter); + file_start_write(file); + ret = do_iter_readv_writev(file, iter, ppos, WRITE, flags); if (ret > 0) fsnotify_modify(file); + file_end_write(file); return ret; } -EXPORT_SYMBOL(vfs_iocb_iter_write); - -ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos, - rwf_t flags) -{ - if (!file->f_op->write_iter) - return -EINVAL; - return do_iter_write(file, iter, ppos, flags); -} EXPORT_SYMBOL(vfs_iter_write); static ssize_t vfs_readv(struct file *file, const struct iovec __user *vec, - unsigned long vlen, loff_t *pos, rwf_t flags) + unsigned long vlen, loff_t *pos, rwf_t flags) { struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; struct iov_iter iter; - ssize_t ret; + size_t tot_len; + ssize_t ret = 0; - ret = import_iovec(ITER_DEST, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter); - if (ret >= 0) { - ret = do_iter_read(file, &iter, pos, flags); - kfree(iov); - } + if (!(file->f_mode & FMODE_READ)) + return -EBADF; + if (!(file->f_mode & FMODE_CAN_READ)) + return -EINVAL; + + ret = import_iovec(ITER_DEST, vec, vlen, ARRAY_SIZE(iovstack), &iov, + &iter); + if (ret < 0) + return ret; + + tot_len = iov_iter_count(&iter); + if (!tot_len) + goto out; + ret = rw_verify_area(READ, file, pos, tot_len); + if (ret < 0) + goto out; + + if (file->f_op->read_iter) + ret = do_iter_readv_writev(file, &iter, pos, READ, flags); + else + ret = do_loop_readv_writev(file, &iter, pos, READ, flags); +out: + if (ret >= 0) + fsnotify_access(file); + kfree(iov); return ret; } static ssize_t vfs_writev(struct file *file, const struct iovec __user *vec, - unsigned long vlen, loff_t *pos, rwf_t flags) + unsigned long vlen, loff_t *pos, rwf_t flags) { struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; struct iov_iter iter; - ssize_t ret; + size_t tot_len; + ssize_t ret = 0; - ret = import_iovec(ITER_SOURCE, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter); - if (ret >= 0) { - file_start_write(file); - ret = do_iter_write(file, &iter, pos, flags); - file_end_write(file); - kfree(iov); - } + if (!(file->f_mode & FMODE_WRITE)) + return -EBADF; + if (!(file->f_mode & FMODE_CAN_WRITE)) + return -EINVAL; + + ret = import_iovec(ITER_SOURCE, vec, vlen, ARRAY_SIZE(iovstack), &iov, + &iter); + if (ret < 0) + return ret; + + tot_len = iov_iter_count(&iter); + if (!tot_len) + goto out; + + ret = rw_verify_area(WRITE, file, pos, tot_len); + if (ret < 0) + goto out; + + file_start_write(file); + if (file->f_op->write_iter) + ret = do_iter_readv_writev(file, &iter, pos, WRITE, flags); + else + ret = do_loop_readv_writev(file, &iter, pos, WRITE, flags); + if (ret > 0) + fsnotify_modify(file); + file_end_write(file); +out: + kfree(iov); return ret; } @@ -1178,7 +1220,7 @@ COMPAT_SYSCALL_DEFINE6(pwritev2, compat_ulong_t, fd, #endif /* CONFIG_COMPAT */ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, - size_t count, loff_t max) + size_t count, loff_t max) { struct fd in, out; struct inode *in_inode, *out_inode; @@ -1250,10 +1292,8 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, retval = rw_verify_area(WRITE, out.file, &out_pos, count); if (retval < 0) goto fput_out; - file_start_write(out.file); retval = do_splice_direct(in.file, &pos, out.file, &out_pos, count, fl); - file_end_write(out.file); } else { if (out.file->f_flags & O_NONBLOCK) fl |= SPLICE_F_NONBLOCK; @@ -1362,38 +1402,6 @@ COMPAT_SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd, } #endif -/** - * generic_copy_file_range - copy data between two files - * @file_in: file structure to read from - * @pos_in: file offset to read from - * @file_out: file structure to write data to - * @pos_out: file offset to write data to - * @len: amount of data to copy - * @flags: copy flags - * - * This is a generic filesystem helper to copy data from one file to another. - * It has no constraints on the source or destination file owners - the files - * can belong to different superblocks and different filesystem types. Short - * copies are allowed. - * - * This should be called from the @file_out filesystem, as per the - * ->copy_file_range() method. - * - * Returns the number of bytes copied or a negative error indicating the - * failure. - */ - -ssize_t generic_copy_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - size_t len, unsigned int flags) -{ - lockdep_assert(sb_write_started(file_inode(file_out)->i_sb)); - - return do_splice_direct(file_in, &pos_in, file_out, &pos_out, - len > MAX_RW_COUNT ? MAX_RW_COUNT : len, 0); -} -EXPORT_SYMBOL(generic_copy_file_range); - /* * Performs necessary checks before doing a file copy * @@ -1478,6 +1486,7 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, { ssize_t ret; bool splice = flags & COPY_FILE_SPLICE; + bool samesb = file_inode(file_in)->i_sb == file_inode(file_out)->i_sb; if (flags & ~COPY_FILE_SPLICE) return -EINVAL; @@ -1509,19 +1518,24 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, ret = file_out->f_op->copy_file_range(file_in, pos_in, file_out, pos_out, len, flags); - goto done; - } - - if (!splice && file_in->f_op->remap_file_range && - file_inode(file_in)->i_sb == file_inode(file_out)->i_sb) { + } else if (!splice && file_in->f_op->remap_file_range && samesb) { ret = file_in->f_op->remap_file_range(file_in, pos_in, file_out, pos_out, min_t(loff_t, MAX_RW_COUNT, len), REMAP_FILE_CAN_SHORTEN); - if (ret > 0) - goto done; + /* fallback to splice */ + if (ret <= 0) + splice = true; + } else if (samesb) { + /* Fallback to splice for same sb copy for backward compat */ + splice = true; } + file_end_write(file_out); + + if (!splice) + goto done; + /* * We can get here for same sb copy of filesystems that do not implement * ->copy_file_range() in case filesystem does not support clone or in @@ -1533,11 +1547,16 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, * and which filesystems do not, that will allow userspace tools to * make consistent desicions w.r.t using copy_file_range(). * - * We also get here if caller (e.g. nfsd) requested COPY_FILE_SPLICE. + * We also get here if caller (e.g. nfsd) requested COPY_FILE_SPLICE + * for server-side-copy between any two sb. + * + * In any case, we call do_splice_direct() and not splice_file_range(), + * without file_start_write() held, to avoid possible deadlocks related + * to splicing from input file, while file_start_write() is held on + * the output file on a different sb. */ - ret = generic_copy_file_range(file_in, pos_in, file_out, pos_out, len, - flags); - + ret = do_splice_direct(file_in, &pos_in, file_out, &pos_out, + min_t(size_t, len, MAX_RW_COUNT), 0); done: if (ret > 0) { fsnotify_access(file_in); @@ -1549,8 +1568,6 @@ done: inc_syscr(current); inc_syscw(current); - file_end_write(file_out); - return ret; } EXPORT_SYMBOL(vfs_copy_file_range); diff --git a/fs/readdir.c b/fs/readdir.c index c8c46e294431..278bc0254732 100644 --- a/fs/readdir.c +++ b/fs/readdir.c @@ -96,6 +96,10 @@ int iterate_dir(struct file *file, struct dir_context *ctx) if (res) goto out; + res = fsnotify_file_perm(file, MAY_READ); + if (res) + goto out; + res = down_read_killable(&inode->i_rwsem); if (res) goto out; diff --git a/fs/reiserfs/stree.c b/fs/reiserfs/stree.c index 2138ee7d271d..5faf702f8d15 100644 --- a/fs/reiserfs/stree.c +++ b/fs/reiserfs/stree.c @@ -1407,7 +1407,7 @@ void reiserfs_delete_solid_item(struct reiserfs_transaction_handle *th, INITIALIZE_PATH(path); int item_len = 0; int tb_init = 0; - struct cpu_key cpu_key; + struct cpu_key cpu_key = {}; int retval; int quota_cut_bytes = 0; diff --git a/fs/remap_range.c b/fs/remap_range.c index 87ae4f0dc3aa..f8c1120b8311 100644 --- a/fs/remap_range.c +++ b/fs/remap_range.c @@ -102,7 +102,9 @@ static int generic_remap_checks(struct file *file_in, loff_t pos_in, static int remap_verify_area(struct file *file, loff_t pos, loff_t len, bool write) { + int mask = write ? MAY_WRITE : MAY_READ; loff_t tmp; + int ret; if (unlikely(pos < 0 || len < 0)) return -EINVAL; @@ -110,7 +112,11 @@ static int remap_verify_area(struct file *file, loff_t pos, loff_t len, if (unlikely(check_add_overflow(pos, len, &tmp))) return -EINVAL; - return security_file_permission(file, write ? MAY_WRITE : MAY_READ); + ret = security_file_permission(file, mask); + if (ret) + return ret; + + return fsnotify_file_area_perm(file, mask, &pos, len); } /* @@ -385,14 +391,6 @@ loff_t do_clone_file_range(struct file *file_in, loff_t pos_in, if (!file_in->f_op->remap_file_range) return -EOPNOTSUPP; - ret = remap_verify_area(file_in, pos_in, len, false); - if (ret) - return ret; - - ret = remap_verify_area(file_out, pos_out, len, true); - if (ret) - return ret; - ret = file_in->f_op->remap_file_range(file_in, pos_in, file_out, pos_out, len, remap_flags); if (ret < 0) @@ -410,6 +408,14 @@ loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in, { loff_t ret; + ret = remap_verify_area(file_in, pos_in, len, false); + if (ret) + return ret; + + ret = remap_verify_area(file_out, pos_out, len, true); + if (ret) + return ret; + file_start_write(file_out); ret = do_clone_file_range(file_in, pos_in, file_out, pos_out, len, remap_flags); @@ -420,7 +426,7 @@ loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in, EXPORT_SYMBOL(vfs_clone_file_range); /* Check whether we are allowed to dedupe the destination file */ -static bool allow_file_dedupe(struct file *file) +static bool may_dedupe_file(struct file *file) { struct mnt_idmap *idmap = file_mnt_idmap(file); struct inode *inode = file_inode(file); @@ -445,24 +451,29 @@ loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, WARN_ON_ONCE(remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_CAN_SHORTEN)); - ret = mnt_want_write_file(dst_file); - if (ret) - return ret; - /* * This is redundant if called from vfs_dedupe_file_range(), but other * callers need it and it's not performance sesitive... */ ret = remap_verify_area(src_file, src_pos, len, false); if (ret) - goto out_drop_write; + return ret; ret = remap_verify_area(dst_file, dst_pos, len, true); if (ret) - goto out_drop_write; + return ret; + + /* + * This needs to be called after remap_verify_area() because of + * sb_start_write() and before may_dedupe_file() because the mount's + * MAY_WRITE need to be checked with mnt_get_write_access_file() held. + */ + ret = mnt_want_write_file(dst_file); + if (ret) + return ret; ret = -EPERM; - if (!allow_file_dedupe(dst_file)) + if (!may_dedupe_file(dst_file)) goto out_drop_write; ret = -EXDEV; diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c index 59f6b8e32cc9..d64a306a414b 100644 --- a/fs/smb/client/cached_dir.c +++ b/fs/smb/client/cached_dir.c @@ -291,16 +291,23 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, oparms.fid->mid = le64_to_cpu(o_rsp->hdr.MessageId); #endif /* CIFS_DEBUG2 */ - rc = -EINVAL; + if (o_rsp->OplockLevel != SMB2_OPLOCK_LEVEL_LEASE) { spin_unlock(&cfids->cfid_list_lock); + rc = -EINVAL; + goto oshr_free; + } + + rc = smb2_parse_contexts(server, rsp_iov, + &oparms.fid->epoch, + oparms.fid->lease_key, + &oplock, NULL, NULL); + if (rc) { + spin_unlock(&cfids->cfid_list_lock); goto oshr_free; } - smb2_parse_contexts(server, o_rsp, - &oparms.fid->epoch, - oparms.fid->lease_key, &oplock, - NULL, NULL); + rc = -EINVAL; if (!(oplock & SMB2_LEASE_READ_CACHING_HE)) { spin_unlock(&cfids->cfid_list_lock); goto oshr_free; diff --git a/fs/smb/client/cifs_debug.c b/fs/smb/client/cifs_debug.c index 5596c9f30ccb..60027f5aebe8 100644 --- a/fs/smb/client/cifs_debug.c +++ b/fs/smb/client/cifs_debug.c @@ -40,11 +40,13 @@ void cifs_dump_detail(void *buf, struct TCP_Server_Info *server) #ifdef CONFIG_CIFS_DEBUG2 struct smb_hdr *smb = buf; - cifs_dbg(VFS, "Cmd: %d Err: 0x%x Flags: 0x%x Flgs2: 0x%x Mid: %d Pid: %d\n", - smb->Command, smb->Status.CifsError, - smb->Flags, smb->Flags2, smb->Mid, smb->Pid); - cifs_dbg(VFS, "smb buf %p len %u\n", smb, - server->ops->calc_smb_size(smb)); + cifs_dbg(VFS, "Cmd: %d Err: 0x%x Flags: 0x%x Flgs2: 0x%x Mid: %d Pid: %d Wct: %d\n", + smb->Command, smb->Status.CifsError, smb->Flags, + smb->Flags2, smb->Mid, smb->Pid, smb->WordCount); + if (!server->ops->check_message(buf, server->total_read, server)) { + cifs_dbg(VFS, "smb buf %p len %u\n", smb, + server->ops->calc_smb_size(smb)); + } #endif /* CONFIG_CIFS_DEBUG2 */ } diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index 2131638f26d0..99b0ade833aa 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -25,6 +25,7 @@ #include <linux/freezer.h> #include <linux/namei.h> #include <linux/random.h> +#include <linux/splice.h> #include <linux/uuid.h> #include <linux/xattr.h> #include <uapi/linux/magic.h> @@ -1506,8 +1507,8 @@ static ssize_t cifs_copy_file_range(struct file *src_file, loff_t off, free_xid(xid); if (rc == -EOPNOTSUPP || rc == -EXDEV) - rc = generic_copy_file_range(src_file, off, dst_file, - destoff, len, flags); + rc = splice_copy_file_range(src_file, off, dst_file, + destoff, len); return rc; } diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 7558167f603c..5e32c79f03a7 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -532,7 +532,8 @@ struct smb_version_operations { struct mid_q_entry **, char **, int *); enum securityEnum (*select_sectype)(struct TCP_Server_Info *, enum securityEnum); - int (*next_header)(char *); + int (*next_header)(struct TCP_Server_Info *server, char *buf, + unsigned int *noff); /* ioctl passthrough for query_info */ int (*ioctl_query_info)(const unsigned int xid, struct cifs_tcon *tcon, @@ -993,7 +994,6 @@ release_iface(struct kref *ref) struct cifs_server_iface *iface = container_of(ref, struct cifs_server_iface, refcount); - list_del_init(&iface->iface_head); kfree(iface); } diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index 9dc6dc2754c2..dc9b95ca71e6 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -216,22 +216,29 @@ cifs_mark_tcp_ses_conns_for_reconnect(struct TCP_Server_Info *server, /* If server is a channel, select the primary channel */ pserver = SERVER_IS_CHAN(server) ? server->primary_server : server; + /* + * if the server has been marked for termination, there is a + * chance that the remaining channels all need reconnect. To be + * on the safer side, mark the session and trees for reconnect + * for this scenario. This might cause a few redundant session + * setup and tree connect requests, but it is better than not doing + * a tree connect when needed, and all following requests failing + */ + if (server->terminate) { + mark_smb_session = true; + server = pserver; + } spin_lock(&cifs_tcp_ses_lock); list_for_each_entry_safe(ses, nses, &pserver->smb_ses_list, smb_ses_list) { - /* - * if channel has been marked for termination, nothing to do - * for the channel. in fact, we cannot find the channel for the - * server. So safe to exit here - */ - if (server->terminate) - break; - /* check if iface is still active */ - if (!cifs_chan_is_iface_active(ses, server)) + spin_lock(&ses->chan_lock); + if (!cifs_chan_is_iface_active(ses, server)) { + spin_unlock(&ses->chan_lock); cifs_chan_update_iface(ses, server); + spin_lock(&ses->chan_lock); + } - spin_lock(&ses->chan_lock); if (!mark_smb_session && cifs_chan_needs_reconnect(ses, server)) { spin_unlock(&ses->chan_lock); continue; @@ -1201,7 +1208,12 @@ next_pdu: server->total_read += length; if (server->ops->next_header) { - next_offset = server->ops->next_header(buf); + if (server->ops->next_header(server, buf, &next_offset)) { + cifs_dbg(VFS, "%s: malformed response (next_offset=%u)\n", + __func__, next_offset); + cifs_reconnect(server, true); + continue; + } if (next_offset) server->pdu_size = next_offset; } diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index cf17e3dd703e..32a8525415d9 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -4671,7 +4671,7 @@ static int cifs_readpage_worker(struct file *file, struct page *page, /* we do not want atime to be less than mtime, it broke some apps */ atime = inode_set_atime_to_ts(inode, current_time(inode)); mtime = inode_get_mtime(inode); - if (timespec64_compare(&atime, &mtime)) + if (timespec64_compare(&atime, &mtime) < 0) inode_set_atime_to_ts(inode, inode_get_mtime(inode)); if (PAGE_SIZE > rc) diff --git a/fs/smb/client/misc.c b/fs/smb/client/misc.c index 35b176457bbe..c2137ea3c253 100644 --- a/fs/smb/client/misc.c +++ b/fs/smb/client/misc.c @@ -363,6 +363,10 @@ checkSMB(char *buf, unsigned int total_read, struct TCP_Server_Info *server) cifs_dbg(VFS, "Length less than smb header size\n"); } return -EIO; + } else if (total_read < sizeof(*smb) + 2 * smb->WordCount) { + cifs_dbg(VFS, "%s: can't read BCC due to invalid WordCount(%u)\n", + __func__, smb->WordCount); + return -EIO; } /* otherwise, there is enough to get to the BCC */ diff --git a/fs/smb/client/sess.c b/fs/smb/client/sess.c index 816e01c5589b..2d3b332a79a1 100644 --- a/fs/smb/client/sess.c +++ b/fs/smb/client/sess.c @@ -439,7 +439,7 @@ cifs_chan_update_iface(struct cifs_ses *ses, struct TCP_Server_Info *server) cifs_dbg(FYI, "unable to find a suitable iface\n"); } - if (!chan_index && !iface) { + if (!iface) { cifs_dbg(FYI, "unable to get the interface matching: %pIS\n", &ss); spin_unlock(&ses->iface_lock); @@ -447,7 +447,7 @@ cifs_chan_update_iface(struct cifs_ses *ses, struct TCP_Server_Info *server) } /* now drop the ref to the current iface */ - if (old_iface && iface) { + if (old_iface) { cifs_dbg(FYI, "replacing iface: %pIS with %pIS\n", &old_iface->sockaddr, &iface->sockaddr); @@ -460,44 +460,32 @@ cifs_chan_update_iface(struct cifs_ses *ses, struct TCP_Server_Info *server) kref_put(&old_iface->refcount, release_iface); } else if (old_iface) { - cifs_dbg(FYI, "releasing ref to iface: %pIS\n", + /* if a new candidate is not found, keep things as is */ + cifs_dbg(FYI, "could not replace iface: %pIS\n", &old_iface->sockaddr); - - old_iface->num_channels--; - if (old_iface->weight_fulfilled) - old_iface->weight_fulfilled--; - - kref_put(&old_iface->refcount, release_iface); } else if (!chan_index) { /* special case: update interface for primary channel */ - cifs_dbg(FYI, "referencing primary channel iface: %pIS\n", - &iface->sockaddr); - iface->num_channels++; - iface->weight_fulfilled++; - } else { - WARN_ON(!iface); - cifs_dbg(FYI, "adding new iface: %pIS\n", &iface->sockaddr); + if (iface) { + cifs_dbg(FYI, "referencing primary channel iface: %pIS\n", + &iface->sockaddr); + iface->num_channels++; + iface->weight_fulfilled++; + } } spin_unlock(&ses->iface_lock); - spin_lock(&ses->chan_lock); - chan_index = cifs_ses_get_chan_index(ses, server); - if (chan_index == CIFS_INVAL_CHAN_INDEX) { + if (iface) { + spin_lock(&ses->chan_lock); + chan_index = cifs_ses_get_chan_index(ses, server); + if (chan_index == CIFS_INVAL_CHAN_INDEX) { + spin_unlock(&ses->chan_lock); + return 0; + } + + ses->chans[chan_index].iface = iface; spin_unlock(&ses->chan_lock); - return 0; } - ses->chans[chan_index].iface = iface; - - /* No iface is found. if secondary chan, drop connection */ - if (!iface && SERVER_IS_CHAN(server)) - ses->chans[chan_index].server = NULL; - - spin_unlock(&ses->chan_lock); - - if (!iface && SERVER_IS_CHAN(server)) - cifs_put_tcp_session(server, false); - return rc; } diff --git a/fs/smb/client/smb2misc.c b/fs/smb/client/smb2misc.c index 32dfa0f7a78c..82b84a4941dd 100644 --- a/fs/smb/client/smb2misc.c +++ b/fs/smb/client/smb2misc.c @@ -173,6 +173,21 @@ smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *server) } mid = le64_to_cpu(shdr->MessageId); + if (check_smb2_hdr(shdr, mid)) + return 1; + + if (shdr->StructureSize != SMB2_HEADER_STRUCTURE_SIZE) { + cifs_dbg(VFS, "Invalid structure size %u\n", + le16_to_cpu(shdr->StructureSize)); + return 1; + } + + command = le16_to_cpu(shdr->Command); + if (command >= NUMBER_OF_SMB2_COMMANDS) { + cifs_dbg(VFS, "Invalid SMB2 command %d\n", command); + return 1; + } + if (len < pdu_size) { if ((len >= hdr_size) && (shdr->Status != 0)) { @@ -193,21 +208,6 @@ smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *server) return 1; } - if (check_smb2_hdr(shdr, mid)) - return 1; - - if (shdr->StructureSize != SMB2_HEADER_STRUCTURE_SIZE) { - cifs_dbg(VFS, "Invalid structure size %u\n", - le16_to_cpu(shdr->StructureSize)); - return 1; - } - - command = le16_to_cpu(shdr->Command); - if (command >= NUMBER_OF_SMB2_COMMANDS) { - cifs_dbg(VFS, "Invalid SMB2 command %d\n", command); - return 1; - } - if (smb2_rsp_struct_sizes[command] != pdu->StructureSize2) { if (command != SMB2_OPLOCK_BREAK_HE && (shdr->Status == 0 || pdu->StructureSize2 != SMB2_ERROR_STRUCTURE_SIZE2_LE)) { @@ -313,6 +313,9 @@ static const bool has_smb2_data_area[NUMBER_OF_SMB2_COMMANDS] = { char * smb2_get_data_area_len(int *off, int *len, struct smb2_hdr *shdr) { + const int max_off = 4096; + const int max_len = 128 * 1024; + *off = 0; *len = 0; @@ -384,29 +387,20 @@ smb2_get_data_area_len(int *off, int *len, struct smb2_hdr *shdr) * Invalid length or offset probably means data area is invalid, but * we have little choice but to ignore the data area in this case. */ - if (*off > 4096) { - cifs_dbg(VFS, "offset %d too large, data area ignored\n", *off); - *len = 0; + if (unlikely(*off < 0 || *off > max_off || + *len < 0 || *len > max_len)) { + cifs_dbg(VFS, "%s: invalid data area (off=%d len=%d)\n", + __func__, *off, *len); *off = 0; - } else if (*off < 0) { - cifs_dbg(VFS, "negative offset %d to data invalid ignore data area\n", - *off); - *off = 0; - *len = 0; - } else if (*len < 0) { - cifs_dbg(VFS, "negative data length %d invalid, data area ignored\n", - *len); *len = 0; - } else if (*len > 128 * 1024) { - cifs_dbg(VFS, "data area larger than 128K: %d\n", *len); + } else if (*off == 0) { *len = 0; } /* return pointer to beginning of data area, ie offset from SMB start */ - if ((*off != 0) && (*len != 0)) + if (*off > 0 && *len > 0) return (char *)shdr + *off; - else - return NULL; + return NULL; } /* diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index fcfb6566b899..14bc745de199 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -403,8 +403,10 @@ smb2_dump_detail(void *buf, struct TCP_Server_Info *server) cifs_server_dbg(VFS, "Cmd: %d Err: 0x%x Flags: 0x%x Mid: %llu Pid: %d\n", shdr->Command, shdr->Status, shdr->Flags, shdr->MessageId, shdr->Id.SyncId.ProcessId); - cifs_server_dbg(VFS, "smb buf %p len %u\n", buf, - server->ops->calc_smb_size(buf)); + if (!server->ops->check_message(buf, server->total_read, server)) { + cifs_server_dbg(VFS, "smb buf %p len %u\n", buf, + server->ops->calc_smb_size(buf)); + } #endif } @@ -593,16 +595,12 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf, } /* - * Go through iface_list and do kref_put to remove - * any unused ifaces. ifaces in use will be removed - * when the last user calls a kref_put on it + * Go through iface_list and mark them as inactive */ list_for_each_entry_safe(iface, niface, &ses->iface_list, - iface_head) { + iface_head) iface->is_active = 0; - kref_put(&iface->refcount, release_iface); - ses->iface_count--; - } + spin_unlock(&ses->iface_lock); /* @@ -676,10 +674,7 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf, iface_head) { ret = iface_cmp(iface, &tmp_iface); if (!ret) { - /* just get a ref so that it doesn't get picked/freed */ iface->is_active = 1; - kref_get(&iface->refcount); - ses->iface_count++; spin_unlock(&ses->iface_lock); goto next_iface; } else if (ret < 0) { @@ -746,6 +741,20 @@ next_iface: } out: + /* + * Go through the list again and put the inactive entries + */ + spin_lock(&ses->iface_lock); + list_for_each_entry_safe(iface, niface, &ses->iface_list, + iface_head) { + if (!iface->is_active) { + list_del(&iface->iface_head); + kref_put(&iface->refcount, release_iface); + ses->iface_count--; + } + } + spin_unlock(&ses->iface_lock); + return rc; } @@ -782,9 +791,14 @@ SMB3_request_interfaces(const unsigned int xid, struct cifs_tcon *tcon, bool in_ goto out; /* check if iface is still active */ + spin_lock(&ses->chan_lock); pserver = ses->chans[0].server; - if (pserver && !cifs_chan_is_iface_active(ses, pserver)) + if (pserver && !cifs_chan_is_iface_active(ses, pserver)) { + spin_unlock(&ses->chan_lock); cifs_chan_update_iface(ses, pserver); + spin_lock(&ses->chan_lock); + } + spin_unlock(&ses->chan_lock); out: kfree(out_buf); @@ -3003,7 +3017,7 @@ static int smb2_query_reparse_point(const unsigned int xid, struct kvec *rsp_iov; struct smb2_ioctl_rsp *ioctl_rsp; struct reparse_data_buffer *reparse_buf; - u32 plen; + u32 off, count, len; cifs_dbg(FYI, "%s: path: %s\n", __func__, full_path); @@ -3084,16 +3098,22 @@ static int smb2_query_reparse_point(const unsigned int xid, */ if (rc == 0) { /* See MS-FSCC 2.3.23 */ + off = le32_to_cpu(ioctl_rsp->OutputOffset); + count = le32_to_cpu(ioctl_rsp->OutputCount); + if (check_add_overflow(off, count, &len) || + len > rsp_iov[1].iov_len) { + cifs_tcon_dbg(VFS, "%s: invalid ioctl: off=%d count=%d\n", + __func__, off, count); + rc = -EIO; + goto query_rp_exit; + } - reparse_buf = (struct reparse_data_buffer *) - ((char *)ioctl_rsp + - le32_to_cpu(ioctl_rsp->OutputOffset)); - plen = le32_to_cpu(ioctl_rsp->OutputCount); - - if (plen + le32_to_cpu(ioctl_rsp->OutputOffset) > - rsp_iov[1].iov_len) { - cifs_tcon_dbg(FYI, "srv returned invalid ioctl len: %d\n", - plen); + reparse_buf = (void *)((u8 *)ioctl_rsp + off); + len = sizeof(*reparse_buf); + if (count < len || + count < le16_to_cpu(reparse_buf->ReparseDataLength) + len) { + cifs_tcon_dbg(VFS, "%s: invalid ioctl: off=%d count=%d\n", + __func__, off, count); rc = -EIO; goto query_rp_exit; } @@ -4943,6 +4963,7 @@ receive_encrypted_standard(struct TCP_Server_Info *server, struct smb2_hdr *shdr; unsigned int pdu_length = server->pdu_size; unsigned int buf_size; + unsigned int next_cmd; struct mid_q_entry *mid_entry; int next_is_large; char *next_buffer = NULL; @@ -4971,14 +4992,15 @@ receive_encrypted_standard(struct TCP_Server_Info *server, next_is_large = server->large_buf; one_more: shdr = (struct smb2_hdr *)buf; - if (shdr->NextCommand) { + next_cmd = le32_to_cpu(shdr->NextCommand); + if (next_cmd) { + if (WARN_ON_ONCE(next_cmd > pdu_length)) + return -1; if (next_is_large) next_buffer = (char *)cifs_buf_get(); else next_buffer = (char *)cifs_small_buf_get(); - memcpy(next_buffer, - buf + le32_to_cpu(shdr->NextCommand), - pdu_length - le32_to_cpu(shdr->NextCommand)); + memcpy(next_buffer, buf + next_cmd, pdu_length - next_cmd); } mid_entry = smb2_find_mid(server, buf); @@ -5002,8 +5024,8 @@ one_more: else ret = cifs_handle_standard(server, mid_entry); - if (ret == 0 && shdr->NextCommand) { - pdu_length -= le32_to_cpu(shdr->NextCommand); + if (ret == 0 && next_cmd) { + pdu_length -= next_cmd; server->large_buf = next_is_large; if (next_is_large) server->bigbuf = buf = next_buffer; @@ -5066,17 +5088,22 @@ smb3_handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid) NULL, 0, false); } -static int -smb2_next_header(char *buf) +static int smb2_next_header(struct TCP_Server_Info *server, char *buf, + unsigned int *noff) { struct smb2_hdr *hdr = (struct smb2_hdr *)buf; struct smb2_transform_hdr *t_hdr = (struct smb2_transform_hdr *)buf; - if (hdr->ProtocolId == SMB2_TRANSFORM_PROTO_NUM) - return sizeof(struct smb2_transform_hdr) + - le32_to_cpu(t_hdr->OriginalMessageSize); - - return le32_to_cpu(hdr->NextCommand); + if (hdr->ProtocolId == SMB2_TRANSFORM_PROTO_NUM) { + *noff = le32_to_cpu(t_hdr->OriginalMessageSize); + if (unlikely(check_add_overflow(*noff, sizeof(*t_hdr), noff))) + return -EINVAL; + } else { + *noff = le32_to_cpu(hdr->NextCommand); + } + if (unlikely(*noff && *noff < MID_HEADER_SIZE(server))) + return -EINVAL; + return 0; } int cifs_sfu_make_node(unsigned int xid, struct inode *inode, diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 20634fc6d4f0..4f971c1061f0 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -411,8 +411,7 @@ skip_sess_setup: } if (smb2_command != SMB2_INTERNAL_CMD) - if (mod_delayed_work(cifsiod_wq, &server->reconnect, 0)) - cifs_put_tcp_session(server, false); + mod_delayed_work(cifsiod_wq, &server->reconnect, 0); atomic_inc(&tconInfoReconnectCount); out: @@ -471,10 +470,15 @@ static int __smb2_plain_req_init(__le16 smb2_command, struct cifs_tcon *tcon, void **request_buf, unsigned int *total_len) { /* BB eventually switch this to SMB2 specific small buf size */ - if (smb2_command == SMB2_SET_INFO) + switch (smb2_command) { + case SMB2_SET_INFO: + case SMB2_QUERY_INFO: *request_buf = cifs_buf_get(); - else + break; + default: *request_buf = cifs_small_buf_get(); + break; + } if (*request_buf == NULL) { /* BB should we add a retry in here if not a writepage? */ return -ENOMEM; @@ -2236,17 +2240,18 @@ parse_posix_ctxt(struct create_context *cc, struct smb2_file_all_info *info, posix->nlink, posix->mode, posix->reparse_tag); } -void -smb2_parse_contexts(struct TCP_Server_Info *server, - struct smb2_create_rsp *rsp, - unsigned int *epoch, char *lease_key, __u8 *oplock, - struct smb2_file_all_info *buf, - struct create_posix_rsp *posix) +int smb2_parse_contexts(struct TCP_Server_Info *server, + struct kvec *rsp_iov, + unsigned int *epoch, + char *lease_key, __u8 *oplock, + struct smb2_file_all_info *buf, + struct create_posix_rsp *posix) { - char *data_offset; + struct smb2_create_rsp *rsp = rsp_iov->iov_base; struct create_context *cc; - unsigned int next; - unsigned int remaining; + size_t rem, off, len; + size_t doff, dlen; + size_t noff, nlen; char *name; static const char smb3_create_tag_posix[] = { 0x93, 0xAD, 0x25, 0x50, 0x9C, @@ -2255,45 +2260,63 @@ smb2_parse_contexts(struct TCP_Server_Info *server, }; *oplock = 0; - data_offset = (char *)rsp + le32_to_cpu(rsp->CreateContextsOffset); - remaining = le32_to_cpu(rsp->CreateContextsLength); - cc = (struct create_context *)data_offset; + + off = le32_to_cpu(rsp->CreateContextsOffset); + rem = le32_to_cpu(rsp->CreateContextsLength); + if (check_add_overflow(off, rem, &len) || len > rsp_iov->iov_len) + return -EINVAL; + cc = (struct create_context *)((u8 *)rsp + off); /* Initialize inode number to 0 in case no valid data in qfid context */ if (buf) buf->IndexNumber = 0; - while (remaining >= sizeof(struct create_context)) { - name = le16_to_cpu(cc->NameOffset) + (char *)cc; - if (le16_to_cpu(cc->NameLength) == 4 && - strncmp(name, SMB2_CREATE_REQUEST_LEASE, 4) == 0) - *oplock = server->ops->parse_lease_buf(cc, epoch, - lease_key); - else if (buf && (le16_to_cpu(cc->NameLength) == 4) && - strncmp(name, SMB2_CREATE_QUERY_ON_DISK_ID, 4) == 0) - parse_query_id_ctxt(cc, buf); - else if ((le16_to_cpu(cc->NameLength) == 16)) { - if (posix && - memcmp(name, smb3_create_tag_posix, 16) == 0) + while (rem >= sizeof(*cc)) { + doff = le16_to_cpu(cc->DataOffset); + dlen = le32_to_cpu(cc->DataLength); + if (check_add_overflow(doff, dlen, &len) || len > rem) + return -EINVAL; + + noff = le16_to_cpu(cc->NameOffset); + nlen = le16_to_cpu(cc->NameLength); + if (noff + nlen >= doff) + return -EINVAL; + + name = (char *)cc + noff; + switch (nlen) { + case 4: + if (!strncmp(name, SMB2_CREATE_REQUEST_LEASE, 4)) { + *oplock = server->ops->parse_lease_buf(cc, epoch, + lease_key); + } else if (buf && + !strncmp(name, SMB2_CREATE_QUERY_ON_DISK_ID, 4)) { + parse_query_id_ctxt(cc, buf); + } + break; + case 16: + if (posix && !memcmp(name, smb3_create_tag_posix, 16)) parse_posix_ctxt(cc, buf, posix); + break; + default: + cifs_dbg(FYI, "%s: unhandled context (nlen=%zu dlen=%zu)\n", + __func__, nlen, dlen); + if (IS_ENABLED(CONFIG_CIFS_DEBUG2)) + cifs_dump_mem("context data: ", cc, dlen); + break; } - /* else { - cifs_dbg(FYI, "Context not matched with len %d\n", - le16_to_cpu(cc->NameLength)); - cifs_dump_mem("Cctxt name: ", name, 4); - } */ - - next = le32_to_cpu(cc->Next); - if (!next) + + off = le32_to_cpu(cc->Next); + if (!off) break; - remaining -= next; - cc = (struct create_context *)((char *)cc + next); + if (check_sub_overflow(rem, off, &rem)) + return -EINVAL; + cc = (struct create_context *)((u8 *)cc + off); } if (rsp->OplockLevel != SMB2_OPLOCK_LEVEL_LEASE) *oplock = rsp->OplockLevel; - return; + return 0; } static int @@ -3124,8 +3147,8 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, } - smb2_parse_contexts(server, rsp, &oparms->fid->epoch, - oparms->fid->lease_key, oplock, buf, posix); + rc = smb2_parse_contexts(server, &rsp_iov, &oparms->fid->epoch, + oparms->fid->lease_key, oplock, buf, posix); creat_exit: SMB2_open_free(&rqst); free_rsp_buf(resp_buftype, rsp); @@ -3568,8 +3591,13 @@ SMB2_query_info_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server, struct smb2_query_info_req *req; struct kvec *iov = rqst->rq_iov; unsigned int total_len; + size_t len; int rc; + if (unlikely(check_add_overflow(input_len, sizeof(*req), &len) || + len > CIFSMaxBufSize)) + return -EINVAL; + rc = smb2_plain_req_init(SMB2_QUERY_INFO, tcon, server, (void **) &req, &total_len); if (rc) @@ -3591,7 +3619,7 @@ SMB2_query_info_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server, iov[0].iov_base = (char *)req; /* 1 for Buffer */ - iov[0].iov_len = total_len - 1 + input_len; + iov[0].iov_len = len; return 0; } @@ -3599,7 +3627,7 @@ void SMB2_query_info_free(struct smb_rqst *rqst) { if (rqst && rqst->rq_iov) - cifs_small_buf_release(rqst->rq_iov[0].iov_base); /* request */ + cifs_buf_release(rqst->rq_iov[0].iov_base); /* request */ } static int @@ -5474,6 +5502,11 @@ build_qfs_info_req(struct kvec *iov, struct cifs_tcon *tcon, return 0; } +static inline void free_qfs_info_req(struct kvec *iov) +{ + cifs_buf_release(iov->iov_base); +} + int SMB311_posix_qfs_info(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, struct kstatfs *fsdata) @@ -5505,7 +5538,7 @@ SMB311_posix_qfs_info(const unsigned int xid, struct cifs_tcon *tcon, rc = cifs_send_recv(xid, ses, server, &rqst, &resp_buftype, flags, &rsp_iov); - cifs_small_buf_release(iov.iov_base); + free_qfs_info_req(&iov); if (rc) { cifs_stats_fail_inc(tcon, SMB2_QUERY_INFO_HE); goto posix_qfsinf_exit; @@ -5556,7 +5589,7 @@ SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon, rc = cifs_send_recv(xid, ses, server, &rqst, &resp_buftype, flags, &rsp_iov); - cifs_small_buf_release(iov.iov_base); + free_qfs_info_req(&iov); if (rc) { cifs_stats_fail_inc(tcon, SMB2_QUERY_INFO_HE); goto qfsinf_exit; @@ -5623,7 +5656,7 @@ SMB2_QFS_attr(const unsigned int xid, struct cifs_tcon *tcon, rc = cifs_send_recv(xid, ses, server, &rqst, &resp_buftype, flags, &rsp_iov); - cifs_small_buf_release(iov.iov_base); + free_qfs_info_req(&iov); if (rc) { cifs_stats_fail_inc(tcon, SMB2_QUERY_INFO_HE); goto qfsattr_exit; diff --git a/fs/smb/client/smb2proto.h b/fs/smb/client/smb2proto.h index 46eff9ec302a..0e371f7e2854 100644 --- a/fs/smb/client/smb2proto.h +++ b/fs/smb/client/smb2proto.h @@ -251,11 +251,13 @@ extern int smb3_validate_negotiate(const unsigned int, struct cifs_tcon *); extern enum securityEnum smb2_select_sectype(struct TCP_Server_Info *, enum securityEnum); -extern void smb2_parse_contexts(struct TCP_Server_Info *server, - struct smb2_create_rsp *rsp, - unsigned int *epoch, char *lease_key, - __u8 *oplock, struct smb2_file_all_info *buf, - struct create_posix_rsp *posix); +int smb2_parse_contexts(struct TCP_Server_Info *server, + struct kvec *rsp_iov, + unsigned int *epoch, + char *lease_key, __u8 *oplock, + struct smb2_file_all_info *buf, + struct create_posix_rsp *posix); + extern int smb3_encryption_required(const struct cifs_tcon *tcon); extern int smb2_validate_iov(unsigned int offset, unsigned int buffer_length, struct kvec *iov, unsigned int min_buf_size); diff --git a/fs/smb/common/smb2pdu.h b/fs/smb/common/smb2pdu.h index 9fbaaa387dcc..57f2343164a3 100644 --- a/fs/smb/common/smb2pdu.h +++ b/fs/smb/common/smb2pdu.h @@ -1145,7 +1145,7 @@ struct smb2_server_client_notification { #define SMB2_CREATE_SD_BUFFER "SecD" /* security descriptor */ #define SMB2_CREATE_DURABLE_HANDLE_REQUEST "DHnQ" #define SMB2_CREATE_DURABLE_HANDLE_RECONNECT "DHnC" -#define SMB2_CREATE_ALLOCATION_SIZE "AISi" +#define SMB2_CREATE_ALLOCATION_SIZE "AlSi" #define SMB2_CREATE_QUERY_MAXIMAL_ACCESS_REQUEST "MxAc" #define SMB2_CREATE_TIMEWARP_REQUEST "TWrp" #define SMB2_CREATE_QUERY_ON_DISK_ID "QFid" @@ -1253,6 +1253,7 @@ struct create_mxac_rsp { #define SMB2_LEASE_WRITE_CACHING_LE cpu_to_le32(0x04) #define SMB2_LEASE_FLAG_BREAK_IN_PROGRESS_LE cpu_to_le32(0x02) +#define SMB2_LEASE_FLAG_PARENT_LEASE_KEY_SET_LE cpu_to_le32(0x04) #define SMB2_LEASE_KEY_SIZE 16 diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index 50c68beb71d6..562b180459a1 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -102,9 +102,10 @@ static int alloc_lease(struct oplock_info *opinfo, struct lease_ctx_info *lctx) lease->new_state = 0; lease->flags = lctx->flags; lease->duration = lctx->duration; + lease->is_dir = lctx->is_dir; memcpy(lease->parent_lease_key, lctx->parent_lease_key, SMB2_LEASE_KEY_SIZE); lease->version = lctx->version; - lease->epoch = 0; + lease->epoch = le16_to_cpu(lctx->epoch); INIT_LIST_HEAD(&opinfo->lease_entry); opinfo->o_lease = lease; @@ -395,8 +396,8 @@ void close_id_del_oplock(struct ksmbd_file *fp) { struct oplock_info *opinfo; - if (S_ISDIR(file_inode(fp->filp)->i_mode)) - return; + if (fp->reserve_lease_break) + smb_lazy_parent_lease_break_close(fp); opinfo = opinfo_get(fp); if (!opinfo) @@ -543,12 +544,13 @@ static struct oplock_info *same_client_has_lease(struct ksmbd_inode *ci, /* upgrading lease */ if ((atomic_read(&ci->op_count) + atomic_read(&ci->sop_count)) == 1) { - if (lease->state == - (lctx->req_state & lease->state)) { + if (lease->state != SMB2_LEASE_NONE_LE && + lease->state == (lctx->req_state & lease->state)) { lease->state |= lctx->req_state; if (lctx->req_state & SMB2_LEASE_WRITE_CACHING_LE) lease_read_to_write(opinfo); + } } else if ((atomic_read(&ci->op_count) + atomic_read(&ci->sop_count)) > 1) { @@ -900,7 +902,8 @@ static int oplock_break(struct oplock_info *brk_opinfo, int req_op_level) lease->new_state = SMB2_LEASE_READ_CACHING_LE; } else { - if (lease->state & SMB2_LEASE_HANDLE_CACHING_LE) + if (lease->state & SMB2_LEASE_HANDLE_CACHING_LE && + !lease->is_dir) lease->new_state = SMB2_LEASE_READ_CACHING_LE; else @@ -1032,6 +1035,7 @@ static void copy_lease(struct oplock_info *op1, struct oplock_info *op2) SMB2_LEASE_KEY_SIZE); lease2->duration = lease1->duration; lease2->flags = lease1->flags; + lease2->epoch = lease1->epoch++; } static int add_lease_global_list(struct oplock_info *opinfo) @@ -1081,6 +1085,89 @@ static void set_oplock_level(struct oplock_info *opinfo, int level, } } +void smb_send_parent_lease_break_noti(struct ksmbd_file *fp, + struct lease_ctx_info *lctx) +{ + struct oplock_info *opinfo; + struct ksmbd_inode *p_ci = NULL; + + if (lctx->version != 2) + return; + + p_ci = ksmbd_inode_lookup_lock(fp->filp->f_path.dentry->d_parent); + if (!p_ci) + return; + + read_lock(&p_ci->m_lock); + list_for_each_entry(opinfo, &p_ci->m_op_list, op_entry) { + if (!opinfo->is_lease) + continue; + + if (opinfo->o_lease->state != SMB2_OPLOCK_LEVEL_NONE && + (!(lctx->flags & SMB2_LEASE_FLAG_PARENT_LEASE_KEY_SET_LE) || + !compare_guid_key(opinfo, fp->conn->ClientGUID, + lctx->parent_lease_key))) { + if (!atomic_inc_not_zero(&opinfo->refcount)) + continue; + + atomic_inc(&opinfo->conn->r_count); + if (ksmbd_conn_releasing(opinfo->conn)) { + atomic_dec(&opinfo->conn->r_count); + continue; + } + + read_unlock(&p_ci->m_lock); + oplock_break(opinfo, SMB2_OPLOCK_LEVEL_NONE); + opinfo_conn_put(opinfo); + read_lock(&p_ci->m_lock); + } + } + read_unlock(&p_ci->m_lock); + + ksmbd_inode_put(p_ci); +} + +void smb_lazy_parent_lease_break_close(struct ksmbd_file *fp) +{ + struct oplock_info *opinfo; + struct ksmbd_inode *p_ci = NULL; + + rcu_read_lock(); + opinfo = rcu_dereference(fp->f_opinfo); + rcu_read_unlock(); + + if (!opinfo->is_lease || opinfo->o_lease->version != 2) + return; + + p_ci = ksmbd_inode_lookup_lock(fp->filp->f_path.dentry->d_parent); + if (!p_ci) + return; + + read_lock(&p_ci->m_lock); + list_for_each_entry(opinfo, &p_ci->m_op_list, op_entry) { + if (!opinfo->is_lease) + continue; + + if (opinfo->o_lease->state != SMB2_OPLOCK_LEVEL_NONE) { + if (!atomic_inc_not_zero(&opinfo->refcount)) + continue; + + atomic_inc(&opinfo->conn->r_count); + if (ksmbd_conn_releasing(opinfo->conn)) { + atomic_dec(&opinfo->conn->r_count); + continue; + } + read_unlock(&p_ci->m_lock); + oplock_break(opinfo, SMB2_OPLOCK_LEVEL_NONE); + opinfo_conn_put(opinfo); + read_lock(&p_ci->m_lock); + } + } + read_unlock(&p_ci->m_lock); + + ksmbd_inode_put(p_ci); +} + /** * smb_grant_oplock() - handle oplock/lease request on file open * @work: smb work @@ -1104,10 +1191,6 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid, bool prev_op_has_lease; __le32 prev_op_state = 0; - /* not support directory lease */ - if (S_ISDIR(file_inode(fp->filp)->i_mode)) - return 0; - opinfo = alloc_opinfo(work, pid, tid); if (!opinfo) return -ENOMEM; @@ -1364,6 +1447,7 @@ void create_lease_buf(u8 *rbuf, struct lease *lease) memcpy(buf->lcontext.LeaseKey, lease->lease_key, SMB2_LEASE_KEY_SIZE); buf->lcontext.LeaseFlags = lease->flags; + buf->lcontext.Epoch = cpu_to_le16(++lease->epoch); buf->lcontext.LeaseState = lease->state; memcpy(buf->lcontext.ParentLeaseKey, lease->parent_lease_key, SMB2_LEASE_KEY_SIZE); @@ -1400,10 +1484,11 @@ void create_lease_buf(u8 *rbuf, struct lease *lease) /** * parse_lease_state() - parse lease context containted in file open request * @open_req: buffer containing smb2 file open(create) request + * @is_dir: whether leasing file is directory * * Return: oplock state, -ENOENT if create lease context not found */ -struct lease_ctx_info *parse_lease_state(void *open_req) +struct lease_ctx_info *parse_lease_state(void *open_req, bool is_dir) { struct create_context *cc; struct smb2_create_req *req = (struct smb2_create_req *)open_req; @@ -1421,8 +1506,14 @@ struct lease_ctx_info *parse_lease_state(void *open_req) struct create_lease_v2 *lc = (struct create_lease_v2 *)cc; memcpy(lreq->lease_key, lc->lcontext.LeaseKey, SMB2_LEASE_KEY_SIZE); - lreq->req_state = lc->lcontext.LeaseState; + if (is_dir) { + lreq->req_state = lc->lcontext.LeaseState & + ~SMB2_LEASE_WRITE_CACHING_LE; + lreq->is_dir = true; + } else + lreq->req_state = lc->lcontext.LeaseState; lreq->flags = lc->lcontext.LeaseFlags; + lreq->epoch = lc->lcontext.Epoch; lreq->duration = lc->lcontext.LeaseDuration; memcpy(lreq->parent_lease_key, lc->lcontext.ParentLeaseKey, SMB2_LEASE_KEY_SIZE); diff --git a/fs/smb/server/oplock.h b/fs/smb/server/oplock.h index 4b0fe6da7694..5b93ea9196c0 100644 --- a/fs/smb/server/oplock.h +++ b/fs/smb/server/oplock.h @@ -34,7 +34,9 @@ struct lease_ctx_info { __le32 flags; __le64 duration; __u8 parent_lease_key[SMB2_LEASE_KEY_SIZE]; + __le16 epoch; int version; + bool is_dir; }; struct lease_table { @@ -53,6 +55,7 @@ struct lease { __u8 parent_lease_key[SMB2_LEASE_KEY_SIZE]; int version; unsigned short epoch; + bool is_dir; struct lease_table *l_lb; }; @@ -108,7 +111,7 @@ void opinfo_put(struct oplock_info *opinfo); /* Lease related functions */ void create_lease_buf(u8 *rbuf, struct lease *lease); -struct lease_ctx_info *parse_lease_state(void *open_req); +struct lease_ctx_info *parse_lease_state(void *open_req, bool is_dir); __u8 smb2_map_lease_to_oplock(__le32 lease_state); int lease_read_to_write(struct oplock_info *opinfo); @@ -124,4 +127,7 @@ struct oplock_info *lookup_lease_in_table(struct ksmbd_conn *conn, int find_same_lease_key(struct ksmbd_session *sess, struct ksmbd_inode *ci, struct lease_ctx_info *lctx); void destroy_lease_table(struct ksmbd_conn *conn); +void smb_send_parent_lease_break_noti(struct ksmbd_file *fp, + struct lease_ctx_info *lctx); +void smb_lazy_parent_lease_break_close(struct ksmbd_file *fp); #endif /* __KSMBD_OPLOCK_H */ diff --git a/fs/smb/server/smb2misc.c b/fs/smb/server/smb2misc.c index 23bd3d1209df..03dded29a980 100644 --- a/fs/smb/server/smb2misc.c +++ b/fs/smb/server/smb2misc.c @@ -106,16 +106,25 @@ static int smb2_get_data_area_len(unsigned int *off, unsigned int *len, break; case SMB2_CREATE: { + unsigned short int name_off = + le16_to_cpu(((struct smb2_create_req *)hdr)->NameOffset); + unsigned short int name_len = + le16_to_cpu(((struct smb2_create_req *)hdr)->NameLength); + if (((struct smb2_create_req *)hdr)->CreateContextsLength) { *off = le32_to_cpu(((struct smb2_create_req *) hdr)->CreateContextsOffset); *len = le32_to_cpu(((struct smb2_create_req *) hdr)->CreateContextsLength); - break; + if (!name_len) + break; + + if (name_off + name_len < (u64)*off + *len) + break; } - *off = le16_to_cpu(((struct smb2_create_req *)hdr)->NameOffset); - *len = le16_to_cpu(((struct smb2_create_req *)hdr)->NameLength); + *off = name_off; + *len = name_len; break; } case SMB2_QUERY_INFO: diff --git a/fs/smb/server/smb2ops.c b/fs/smb/server/smb2ops.c index aed7704a0672..27a9dce3e03a 100644 --- a/fs/smb/server/smb2ops.c +++ b/fs/smb/server/smb2ops.c @@ -221,7 +221,8 @@ void init_smb3_0_server(struct ksmbd_conn *conn) conn->signing_algorithm = SIGNING_ALG_AES_CMAC_LE; if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_LEASES) - conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING; + conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING | + SMB2_GLOBAL_CAP_DIRECTORY_LEASING; if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION && conn->cli_cap & SMB2_GLOBAL_CAP_ENCRYPTION) @@ -245,7 +246,8 @@ void init_smb3_02_server(struct ksmbd_conn *conn) conn->signing_algorithm = SIGNING_ALG_AES_CMAC_LE; if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_LEASES) - conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING; + conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING | + SMB2_GLOBAL_CAP_DIRECTORY_LEASING; if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION || (!(server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION_OFF) && @@ -270,7 +272,8 @@ int init_smb3_11_server(struct ksmbd_conn *conn) conn->signing_algorithm = SIGNING_ALG_AES_CMAC_LE; if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_LEASES) - conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING; + conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING | + SMB2_GLOBAL_CAP_DIRECTORY_LEASING; if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION || (!(server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION_OFF) && diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index d369b98a6e10..652ab429bf2e 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -2516,7 +2516,7 @@ static void smb2_new_xattrs(struct ksmbd_tree_connect *tcon, const struct path * da.flags = XATTR_DOSINFO_ATTRIB | XATTR_DOSINFO_CREATE_TIME | XATTR_DOSINFO_ITIME; - rc = ksmbd_vfs_set_dos_attrib_xattr(mnt_idmap(path->mnt), path, &da, false); + rc = ksmbd_vfs_set_dos_attrib_xattr(mnt_idmap(path->mnt), path, &da, true); if (rc) ksmbd_debug(SMB, "failed to store file attribute into xattr\n"); } @@ -2732,10 +2732,6 @@ int smb2_open(struct ksmbd_work *work) } } - req_op_level = req->RequestedOplockLevel; - if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE) - lc = parse_lease_state(req); - if (le32_to_cpu(req->ImpersonationLevel) > le32_to_cpu(IL_DELEGATE)) { pr_err("Invalid impersonationlevel : 0x%x\n", le32_to_cpu(req->ImpersonationLevel)); @@ -3189,23 +3185,6 @@ int smb2_open(struct ksmbd_work *work) goto err_out; } - rc = ksmbd_vfs_getattr(&path, &stat); - if (rc) - goto err_out; - - if (stat.result_mask & STATX_BTIME) - fp->create_time = ksmbd_UnixTimeToNT(stat.btime); - else - fp->create_time = ksmbd_UnixTimeToNT(stat.ctime); - if (req->FileAttributes || fp->f_ci->m_fattr == 0) - fp->f_ci->m_fattr = - cpu_to_le32(smb2_get_dos_mode(&stat, le32_to_cpu(req->FileAttributes))); - - if (!created) - smb2_update_xattrs(tcon, &path, fp); - else - smb2_new_xattrs(tcon, &path, fp); - if (file_present || created) ksmbd_vfs_kern_path_unlock(&parent_path, &path); @@ -3215,6 +3194,10 @@ int smb2_open(struct ksmbd_work *work) need_truncate = 1; } + req_op_level = req->RequestedOplockLevel; + if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE) + lc = parse_lease_state(req, S_ISDIR(file_inode(filp)->i_mode)); + share_ret = ksmbd_smb_check_shared_mode(fp->filp, fp); if (!test_share_config_flag(work->tcon->share_conf, KSMBD_SHARE_FLAG_OPLOCKS) || (req_op_level == SMB2_OPLOCK_LEVEL_LEASE && @@ -3225,6 +3208,13 @@ int smb2_open(struct ksmbd_work *work) } } else { if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE) { + /* + * Compare parent lease using parent key. If there is no + * a lease that has same parent key, Send lease break + * notification. + */ + smb_send_parent_lease_break_noti(fp, lc); + req_op_level = smb2_map_lease_to_oplock(lc->req_state); ksmbd_debug(SMB, "lease req for(%s) req oplock state 0x%x, lease state 0x%x\n", @@ -3295,6 +3285,23 @@ int smb2_open(struct ksmbd_work *work) } } + rc = ksmbd_vfs_getattr(&path, &stat); + if (rc) + goto err_out1; + + if (stat.result_mask & STATX_BTIME) + fp->create_time = ksmbd_UnixTimeToNT(stat.btime); + else + fp->create_time = ksmbd_UnixTimeToNT(stat.ctime); + if (req->FileAttributes || fp->f_ci->m_fattr == 0) + fp->f_ci->m_fattr = + cpu_to_le32(smb2_get_dos_mode(&stat, le32_to_cpu(req->FileAttributes))); + + if (!created) + smb2_update_xattrs(tcon, &path, fp); + else + smb2_new_xattrs(tcon, &path, fp); + memcpy(fp->client_guid, conn->ClientGUID, SMB2_CLIENT_GUID_SIZE); rsp->StructureSize = cpu_to_le16(89); @@ -7080,6 +7087,7 @@ skip: smb2_remove_blocked_lock, argv); if (rc) { + kfree(argv); err = -ENOMEM; goto out; } @@ -8211,6 +8219,11 @@ static void smb21_lease_break_ack(struct ksmbd_work *work) le32_to_cpu(req->LeaseState)); } + if (ret < 0) { + rsp->hdr.Status = err; + goto err_out; + } + lease_state = lease->state; opinfo->op_state = OPLOCK_STATE_NONE; wake_up_interruptible_all(&opinfo->oplock_q); @@ -8218,11 +8231,6 @@ static void smb21_lease_break_ack(struct ksmbd_work *work) wake_up_interruptible_all(&opinfo->oplock_brk); opinfo_put(opinfo); - if (ret < 0) { - rsp->hdr.Status = err; - goto err_out; - } - rsp->StructureSize = cpu_to_le16(36); rsp->Reserved = 0; rsp->Flags = 0; diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c index 9091dcd7a310..4277750a6da1 100644 --- a/fs/smb/server/vfs.c +++ b/fs/smb/server/vfs.c @@ -517,6 +517,9 @@ int ksmbd_vfs_write(struct ksmbd_work *work, struct ksmbd_file *fp, } } + /* Reserve lease break for parent dir at closing time */ + fp->reserve_lease_break = true; + /* Do we need to break any of a levelII oplock? */ smb_break_all_levII_oplock(work, fp, 1); diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c index ddf233994ddb..4e82ff627d12 100644 --- a/fs/smb/server/vfs_cache.c +++ b/fs/smb/server/vfs_cache.c @@ -87,6 +87,17 @@ static struct ksmbd_inode *ksmbd_inode_lookup(struct ksmbd_file *fp) return __ksmbd_inode_lookup(fp->filp->f_path.dentry); } +struct ksmbd_inode *ksmbd_inode_lookup_lock(struct dentry *d) +{ + struct ksmbd_inode *ci; + + read_lock(&inode_hash_lock); + ci = __ksmbd_inode_lookup(d); + read_unlock(&inode_hash_lock); + + return ci; +} + int ksmbd_query_inode_status(struct dentry *dentry) { struct ksmbd_inode *ci; @@ -199,7 +210,7 @@ static void ksmbd_inode_free(struct ksmbd_inode *ci) kfree(ci); } -static void ksmbd_inode_put(struct ksmbd_inode *ci) +void ksmbd_inode_put(struct ksmbd_inode *ci) { if (atomic_dec_and_test(&ci->m_count)) ksmbd_inode_free(ci); diff --git a/fs/smb/server/vfs_cache.h b/fs/smb/server/vfs_cache.h index 8325cf4527c4..a528f0cc775a 100644 --- a/fs/smb/server/vfs_cache.h +++ b/fs/smb/server/vfs_cache.h @@ -105,6 +105,7 @@ struct ksmbd_file { struct ksmbd_readdir_data readdir_data; int dot_dotdot[2]; unsigned int f_state; + bool reserve_lease_break; }; static inline void set_ctx_actor(struct dir_context *ctx, @@ -138,6 +139,8 @@ struct ksmbd_file *ksmbd_lookup_foreign_fd(struct ksmbd_work *work, u64 id); struct ksmbd_file *ksmbd_lookup_fd_slow(struct ksmbd_work *work, u64 id, u64 pid); void ksmbd_fd_put(struct ksmbd_work *work, struct ksmbd_file *fp); +struct ksmbd_inode *ksmbd_inode_lookup_lock(struct dentry *d); +void ksmbd_inode_put(struct ksmbd_inode *ci); struct ksmbd_file *ksmbd_lookup_durable_fd(unsigned long long id); struct ksmbd_file *ksmbd_lookup_fd_cguid(char *cguid); struct ksmbd_file *ksmbd_lookup_fd_inode(struct dentry *dentry); diff --git a/fs/splice.c b/fs/splice.c index d983d375ff11..218e24b1ac40 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -201,7 +201,8 @@ ssize_t splice_to_pipe(struct pipe_inode_info *pipe, unsigned int tail = pipe->tail; unsigned int head = pipe->head; unsigned int mask = pipe->ring_size - 1; - int ret = 0, page_nr = 0; + ssize_t ret = 0; + int page_nr = 0; if (!spd_pages) return 0; @@ -673,10 +674,13 @@ iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out, .u.file = out, }; int nbufs = pipe->max_usage; - struct bio_vec *array = kcalloc(nbufs, sizeof(struct bio_vec), - GFP_KERNEL); + struct bio_vec *array; ssize_t ret; + if (!out->f_op->write_iter) + return -EINVAL; + + array = kcalloc(nbufs, sizeof(struct bio_vec), GFP_KERNEL); if (unlikely(!array)) return -ENOMEM; @@ -684,6 +688,7 @@ iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out, splice_from_pipe_begin(&sd); while (sd.total_len) { + struct kiocb kiocb; struct iov_iter from; unsigned int head, tail, mask; size_t left; @@ -733,7 +738,10 @@ iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out, } iov_iter_bvec(&from, ITER_SOURCE, array, n, sd.total_len - left); - ret = vfs_iter_write(out, &from, &sd.pos, 0); + init_sync_kiocb(&kiocb, out); + kiocb.ki_pos = sd.pos; + ret = call_write_iter(out, &kiocb, &from); + sd.pos = kiocb.ki_pos; if (ret <= 0) break; @@ -925,8 +933,8 @@ static int warn_unsupported(struct file *file, const char *op) /* * Attempt to initiate a splice from pipe to file. */ -static long do_splice_from(struct pipe_inode_info *pipe, struct file *out, - loff_t *ppos, size_t len, unsigned int flags) +static ssize_t do_splice_from(struct pipe_inode_info *pipe, struct file *out, + loff_t *ppos, size_t len, unsigned int flags) { if (unlikely(!out->f_op->splice_write)) return warn_unsupported(out, "write"); @@ -944,27 +952,15 @@ static void do_splice_eof(struct splice_desc *sd) sd->splice_eof(sd); } -/** - * vfs_splice_read - Read data from a file and splice it into a pipe - * @in: File to splice from - * @ppos: Input file offset - * @pipe: Pipe to splice to - * @len: Number of bytes to splice - * @flags: Splice modifier flags (SPLICE_F_*) - * - * Splice the requested amount of data from the input file to the pipe. This - * is synchronous as the caller must hold the pipe lock across the entire - * operation. - * - * If successful, it returns the amount of data spliced, 0 if it hit the EOF or - * a hole and a negative error code otherwise. +/* + * Callers already called rw_verify_area() on the entire range. + * No need to call it for sub ranges. */ -long vfs_splice_read(struct file *in, loff_t *ppos, - struct pipe_inode_info *pipe, size_t len, - unsigned int flags) +static ssize_t do_splice_read(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, + unsigned int flags) { unsigned int p_space; - int ret; if (unlikely(!(in->f_mode & FMODE_READ))) return -EBADF; @@ -975,10 +971,6 @@ long vfs_splice_read(struct file *in, loff_t *ppos, p_space = pipe->max_usage - pipe_occupancy(pipe->head, pipe->tail); len = min_t(size_t, len, p_space << PAGE_SHIFT); - ret = rw_verify_area(READ, in, ppos, len); - if (unlikely(ret < 0)) - return ret; - if (unlikely(len > MAX_RW_COUNT)) len = MAX_RW_COUNT; @@ -992,6 +984,34 @@ long vfs_splice_read(struct file *in, loff_t *ppos, return copy_splice_read(in, ppos, pipe, len, flags); return in->f_op->splice_read(in, ppos, pipe, len, flags); } + +/** + * vfs_splice_read - Read data from a file and splice it into a pipe + * @in: File to splice from + * @ppos: Input file offset + * @pipe: Pipe to splice to + * @len: Number of bytes to splice + * @flags: Splice modifier flags (SPLICE_F_*) + * + * Splice the requested amount of data from the input file to the pipe. This + * is synchronous as the caller must hold the pipe lock across the entire + * operation. + * + * If successful, it returns the amount of data spliced, 0 if it hit the EOF or + * a hole and a negative error code otherwise. + */ +ssize_t vfs_splice_read(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, + unsigned int flags) +{ + ssize_t ret; + + ret = rw_verify_area(READ, in, ppos, len); + if (unlikely(ret < 0)) + return ret; + + return do_splice_read(in, ppos, pipe, len, flags); +} EXPORT_SYMBOL_GPL(vfs_splice_read); /** @@ -1011,7 +1031,7 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd, splice_direct_actor *actor) { struct pipe_inode_info *pipe; - long ret, bytes; + ssize_t ret, bytes; size_t len; int i, flags, more; @@ -1066,7 +1086,7 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd, size_t read_len; loff_t pos = sd->pos, prev_pos = pos; - ret = vfs_splice_read(in, &pos, pipe, len, flags); + ret = do_splice_read(in, &pos, pipe, len, flags); if (unlikely(ret <= 0)) goto read_failure; @@ -1138,9 +1158,20 @@ static int direct_splice_actor(struct pipe_inode_info *pipe, struct splice_desc *sd) { struct file *file = sd->u.file; + long ret; + + file_start_write(file); + ret = do_splice_from(pipe, file, sd->opos, sd->total_len, sd->flags); + file_end_write(file); + return ret; +} + +static int splice_file_range_actor(struct pipe_inode_info *pipe, + struct splice_desc *sd) +{ + struct file *file = sd->u.file; - return do_splice_from(pipe, file, sd->opos, sd->total_len, - sd->flags); + return do_splice_from(pipe, file, sd->opos, sd->total_len, sd->flags); } static void direct_file_splice_eof(struct splice_desc *sd) @@ -1151,24 +1182,10 @@ static void direct_file_splice_eof(struct splice_desc *sd) file->f_op->splice_eof(file); } -/** - * do_splice_direct - splices data directly between two files - * @in: file to splice from - * @ppos: input file offset - * @out: file to splice to - * @opos: output file offset - * @len: number of bytes to splice - * @flags: splice modifier flags - * - * Description: - * For use by do_sendfile(). splice can easily emulate sendfile, but - * doing it in the application would incur an extra system call - * (splice in + splice out, as compared to just sendfile()). So this helper - * can splice directly through a process-private pipe. - * - */ -long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, - loff_t *opos, size_t len, unsigned int flags) +static ssize_t do_splice_direct_actor(struct file *in, loff_t *ppos, + struct file *out, loff_t *opos, + size_t len, unsigned int flags, + splice_direct_actor *actor) { struct splice_desc sd = { .len = len, @@ -1179,7 +1196,7 @@ long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, .splice_eof = direct_file_splice_eof, .opos = opos, }; - long ret; + ssize_t ret; if (unlikely(!(out->f_mode & FMODE_WRITE))) return -EBADF; @@ -1187,18 +1204,63 @@ long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, if (unlikely(out->f_flags & O_APPEND)) return -EINVAL; - ret = rw_verify_area(WRITE, out, opos, len); - if (unlikely(ret < 0)) - return ret; - - ret = splice_direct_to_actor(in, &sd, direct_splice_actor); + ret = splice_direct_to_actor(in, &sd, actor); if (ret > 0) *ppos = sd.pos; return ret; } +/** + * do_splice_direct - splices data directly between two files + * @in: file to splice from + * @ppos: input file offset + * @out: file to splice to + * @opos: output file offset + * @len: number of bytes to splice + * @flags: splice modifier flags + * + * Description: + * For use by do_sendfile(). splice can easily emulate sendfile, but + * doing it in the application would incur an extra system call + * (splice in + splice out, as compared to just sendfile()). So this helper + * can splice directly through a process-private pipe. + * + * Callers already called rw_verify_area() on the entire range. + */ +ssize_t do_splice_direct(struct file *in, loff_t *ppos, struct file *out, + loff_t *opos, size_t len, unsigned int flags) +{ + return do_splice_direct_actor(in, ppos, out, opos, len, flags, + direct_splice_actor); +} EXPORT_SYMBOL(do_splice_direct); +/** + * splice_file_range - splices data between two files for copy_file_range() + * @in: file to splice from + * @ppos: input file offset + * @out: file to splice to + * @opos: output file offset + * @len: number of bytes to splice + * + * Description: + * For use by ->copy_file_range() methods. + * Like do_splice_direct(), but vfs_copy_file_range() already holds + * start_file_write() on @out file. + * + * Callers already called rw_verify_area() on the entire range. + */ +ssize_t splice_file_range(struct file *in, loff_t *ppos, struct file *out, + loff_t *opos, size_t len) +{ + lockdep_assert(file_write_started(out)); + + return do_splice_direct_actor(in, ppos, out, opos, + min_t(size_t, len, MAX_RW_COUNT), + 0, splice_file_range_actor); +} +EXPORT_SYMBOL(splice_file_range); + static int wait_for_space(struct pipe_inode_info *pipe, unsigned flags) { for (;;) { @@ -1220,17 +1282,17 @@ static int splice_pipe_to_pipe(struct pipe_inode_info *ipipe, struct pipe_inode_info *opipe, size_t len, unsigned int flags); -long splice_file_to_pipe(struct file *in, - struct pipe_inode_info *opipe, - loff_t *offset, - size_t len, unsigned int flags) +ssize_t splice_file_to_pipe(struct file *in, + struct pipe_inode_info *opipe, + loff_t *offset, + size_t len, unsigned int flags) { - long ret; + ssize_t ret; pipe_lock(opipe); ret = wait_for_space(opipe, flags); if (!ret) - ret = vfs_splice_read(in, offset, opipe, len, flags); + ret = do_splice_read(in, offset, opipe, len, flags); pipe_unlock(opipe); if (ret > 0) wakeup_pipe_readers(opipe); @@ -1240,13 +1302,13 @@ long splice_file_to_pipe(struct file *in, /* * Determine where to splice to/from. */ -long do_splice(struct file *in, loff_t *off_in, struct file *out, - loff_t *off_out, size_t len, unsigned int flags) +ssize_t do_splice(struct file *in, loff_t *off_in, struct file *out, + loff_t *off_out, size_t len, unsigned int flags) { struct pipe_inode_info *ipipe; struct pipe_inode_info *opipe; loff_t offset; - long ret; + ssize_t ret; if (unlikely(!(in->f_mode & FMODE_READ) || !(out->f_mode & FMODE_WRITE))) @@ -1307,6 +1369,10 @@ long do_splice(struct file *in, loff_t *off_in, struct file *out, offset = in->f_pos; } + ret = rw_verify_area(READ, in, &offset, len); + if (unlikely(ret < 0)) + return ret; + if (out->f_flags & O_NONBLOCK) flags |= SPLICE_F_NONBLOCK; @@ -1333,14 +1399,14 @@ long do_splice(struct file *in, loff_t *off_in, struct file *out, return ret; } -static long __do_splice(struct file *in, loff_t __user *off_in, - struct file *out, loff_t __user *off_out, - size_t len, unsigned int flags) +static ssize_t __do_splice(struct file *in, loff_t __user *off_in, + struct file *out, loff_t __user *off_out, + size_t len, unsigned int flags) { struct pipe_inode_info *ipipe; struct pipe_inode_info *opipe; loff_t offset, *__off_in = NULL, *__off_out = NULL; - long ret; + ssize_t ret; ipipe = get_pipe_info(in, true); opipe = get_pipe_info(out, true); @@ -1379,16 +1445,16 @@ static long __do_splice(struct file *in, loff_t __user *off_in, return ret; } -static int iter_to_pipe(struct iov_iter *from, - struct pipe_inode_info *pipe, - unsigned flags) +static ssize_t iter_to_pipe(struct iov_iter *from, + struct pipe_inode_info *pipe, + unsigned int flags) { struct pipe_buffer buf = { .ops = &user_page_pipe_buf_ops, .flags = flags }; size_t total = 0; - int ret = 0; + ssize_t ret = 0; while (iov_iter_count(from)) { struct page *pages[16]; @@ -1437,8 +1503,8 @@ static int pipe_to_user(struct pipe_inode_info *pipe, struct pipe_buffer *buf, * For lack of a better implementation, implement vmsplice() to userspace * as a simple copy of the pipes pages to the user iov. */ -static long vmsplice_to_user(struct file *file, struct iov_iter *iter, - unsigned int flags) +static ssize_t vmsplice_to_user(struct file *file, struct iov_iter *iter, + unsigned int flags) { struct pipe_inode_info *pipe = get_pipe_info(file, true); struct splice_desc sd = { @@ -1446,7 +1512,7 @@ static long vmsplice_to_user(struct file *file, struct iov_iter *iter, .flags = flags, .u.data = iter }; - long ret = 0; + ssize_t ret = 0; if (!pipe) return -EBADF; @@ -1470,11 +1536,11 @@ static long vmsplice_to_user(struct file *file, struct iov_iter *iter, * as splice-from-memory, where the regular splice is splice-from-file (or * to file). In both cases the output is a pipe, naturally. */ -static long vmsplice_to_pipe(struct file *file, struct iov_iter *iter, - unsigned int flags) +static ssize_t vmsplice_to_pipe(struct file *file, struct iov_iter *iter, + unsigned int flags) { struct pipe_inode_info *pipe; - long ret = 0; + ssize_t ret = 0; unsigned buf_flag = 0; if (flags & SPLICE_F_GIFT) @@ -1570,7 +1636,7 @@ SYSCALL_DEFINE6(splice, int, fd_in, loff_t __user *, off_in, size_t, len, unsigned int, flags) { struct fd in, out; - long error; + ssize_t error; if (unlikely(!len)) return 0; @@ -1584,7 +1650,7 @@ SYSCALL_DEFINE6(splice, int, fd_in, loff_t __user *, off_in, out = fdget(fd_out); if (out.file) { error = __do_splice(in.file, off_in, out.file, off_out, - len, flags); + len, flags); fdput(out); } fdput(in); @@ -1807,15 +1873,15 @@ retry: /* * Link contents of ipipe to opipe. */ -static int link_pipe(struct pipe_inode_info *ipipe, - struct pipe_inode_info *opipe, - size_t len, unsigned int flags) +static ssize_t link_pipe(struct pipe_inode_info *ipipe, + struct pipe_inode_info *opipe, + size_t len, unsigned int flags) { struct pipe_buffer *ibuf, *obuf; unsigned int i_head, o_head; unsigned int i_tail, o_tail; unsigned int i_mask, o_mask; - int ret = 0; + ssize_t ret = 0; /* * Potential ABBA deadlock, work around it by ordering lock @@ -1898,11 +1964,12 @@ static int link_pipe(struct pipe_inode_info *ipipe, * The 'flags' used are the SPLICE_F_* variants, currently the only * applicable one is SPLICE_F_NONBLOCK. */ -long do_tee(struct file *in, struct file *out, size_t len, unsigned int flags) +ssize_t do_tee(struct file *in, struct file *out, size_t len, + unsigned int flags) { struct pipe_inode_info *ipipe = get_pipe_info(in, true); struct pipe_inode_info *opipe = get_pipe_info(out, true); - int ret = -EINVAL; + ssize_t ret = -EINVAL; if (unlikely(!(in->f_mode & FMODE_READ) || !(out->f_mode & FMODE_WRITE))) @@ -1939,7 +2006,7 @@ long do_tee(struct file *in, struct file *out, size_t len, unsigned int flags) SYSCALL_DEFINE4(tee, int, fdin, int, fdout, size_t, len, unsigned int, flags) { struct fd in, out; - int error; + ssize_t error; if (unlikely(flags & ~SPLICE_F_ALL)) return -EINVAL; diff --git a/fs/stat.c b/fs/stat.c index f721d26ec3f7..77cdc69eb422 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -41,7 +41,7 @@ * the vfsmount must be passed through @idmap. This function will then * take care to map the inode according to @idmap before filling in the * uid and gid filds. On non-idmapped mounts or if permission checking is to be - * performed on the raw inode simply passs @nop_mnt_idmap. + * performed on the raw inode simply pass @nop_mnt_idmap. */ void generic_fillattr(struct mnt_idmap *idmap, u32 request_mask, struct inode *inode, struct kstat *stat) @@ -247,8 +247,13 @@ retry: error = vfs_getattr(&path, stat, request_mask, flags); - stat->mnt_id = real_mount(path.mnt)->mnt_id; - stat->result_mask |= STATX_MNT_ID; + if (request_mask & STATX_MNT_ID_UNIQUE) { + stat->mnt_id = real_mount(path.mnt)->mnt_id_unique; + stat->result_mask |= STATX_MNT_ID_UNIQUE; + } else { + stat->mnt_id = real_mount(path.mnt)->mnt_id; + stat->result_mask |= STATX_MNT_ID; + } if (path.mnt->mnt_root == path.dentry) stat->attributes |= STATX_ATTR_MOUNT_ROOT; diff --git a/fs/super.c b/fs/super.c index 076392396e72..e35936000408 100644 --- a/fs/super.c +++ b/fs/super.c @@ -81,16 +81,13 @@ static inline void super_unlock_shared(struct super_block *sb) super_unlock(sb, false); } -static inline bool wait_born(struct super_block *sb) +static bool super_flags(const struct super_block *sb, unsigned int flags) { - unsigned int flags; - /* * Pairs with smp_store_release() in super_wake() and ensures - * that we see SB_BORN or SB_DYING after we're woken. + * that we see @flags after we're woken. */ - flags = smp_load_acquire(&sb->s_flags); - return flags & (SB_BORN | SB_DYING); + return smp_load_acquire(&sb->s_flags) & flags; } /** @@ -105,15 +102,21 @@ static inline bool wait_born(struct super_block *sb) * * The caller must have acquired a temporary reference on @sb->s_count. * - * Return: This returns true if SB_BORN was set, false if SB_DYING was - * set. The function acquires s_umount and returns with it held. + * Return: The function returns true if SB_BORN was set and with + * s_umount held. The function returns false if SB_DYING was + * set and without s_umount held. */ static __must_check bool super_lock(struct super_block *sb, bool excl) { - lockdep_assert_not_held(&sb->s_umount); -relock: + /* wait until the superblock is ready or dying */ + wait_var_event(&sb->s_flags, super_flags(sb, SB_BORN | SB_DYING)); + + /* Don't pointlessly acquire s_umount. */ + if (super_flags(sb, SB_DYING)) + return false; + __super_lock(sb, excl); /* @@ -121,32 +124,22 @@ relock: * @sb->s_root is NULL and @sb->s_active is 0. No one needs to * grab a reference to this. Tell them so. */ - if (sb->s_flags & SB_DYING) + if (sb->s_flags & SB_DYING) { + super_unlock(sb, excl); return false; + } - /* Has called ->get_tree() successfully. */ - if (sb->s_flags & SB_BORN) - return true; - - super_unlock(sb, excl); - - /* wait until the superblock is ready or dying */ - wait_var_event(&sb->s_flags, wait_born(sb)); - - /* - * Neither SB_BORN nor SB_DYING are ever unset so we never loop. - * Just reacquire @sb->s_umount for the caller. - */ - goto relock; + WARN_ON_ONCE(!(sb->s_flags & SB_BORN)); + return true; } -/* wait and acquire read-side of @sb->s_umount */ +/* wait and try to acquire read-side of @sb->s_umount */ static inline bool super_lock_shared(struct super_block *sb) { return super_lock(sb, false); } -/* wait and acquire write-side of @sb->s_umount */ +/* wait and try to acquire write-side of @sb->s_umount */ static inline bool super_lock_excl(struct super_block *sb) { return super_lock(sb, true); @@ -323,7 +316,7 @@ static void destroy_unused_super(struct super_block *s) static struct super_block *alloc_super(struct file_system_type *type, int flags, struct user_namespace *user_ns) { - struct super_block *s = kzalloc(sizeof(struct super_block), GFP_USER); + struct super_block *s = kzalloc(sizeof(struct super_block), GFP_KERNEL); static const struct super_operations default_op; int i; @@ -521,48 +514,7 @@ void deactivate_super(struct super_block *s) EXPORT_SYMBOL(deactivate_super); /** - * grab_super - acquire an active reference - * @s: reference we are trying to make active - * - * Tries to acquire an active reference. grab_super() is used when we - * had just found a superblock in super_blocks or fs_type->fs_supers - * and want to turn it into a full-blown active reference. grab_super() - * is called with sb_lock held and drops it. Returns 1 in case of - * success, 0 if we had failed (superblock contents was already dead or - * dying when grab_super() had been called). Note that this is only - * called for superblocks not in rundown mode (== ones still on ->fs_supers - * of their type), so increment of ->s_count is OK here. - */ -static int grab_super(struct super_block *s) __releases(sb_lock) -{ - bool born; - - s->s_count++; - spin_unlock(&sb_lock); - born = super_lock_excl(s); - if (born && atomic_inc_not_zero(&s->s_active)) { - put_super(s); - return 1; - } - super_unlock_excl(s); - put_super(s); - return 0; -} - -static inline bool wait_dead(struct super_block *sb) -{ - unsigned int flags; - - /* - * Pairs with memory barrier in super_wake() and ensures - * that we see SB_DEAD after we're woken. - */ - flags = smp_load_acquire(&sb->s_flags); - return flags & SB_DEAD; -} - -/** - * grab_super_dead - acquire an active reference to a superblock + * grab_super - acquire an active reference to a superblock * @sb: superblock to acquire * * Acquire a temporary reference on a superblock and try to trade it for @@ -573,17 +525,21 @@ static inline bool wait_dead(struct super_block *sb) * Return: This returns true if an active reference could be acquired, * false if not. */ -static bool grab_super_dead(struct super_block *sb) +static bool grab_super(struct super_block *sb) { + bool locked; sb->s_count++; - if (grab_super(sb)) { - put_super(sb); - lockdep_assert_held(&sb->s_umount); - return true; + spin_unlock(&sb_lock); + locked = super_lock_excl(sb); + if (locked) { + if (atomic_inc_not_zero(&sb->s_active)) { + put_super(sb); + return true; + } + super_unlock_excl(sb); } - wait_var_event(&sb->s_flags, wait_dead(sb)); - lockdep_assert_not_held(&sb->s_umount); + wait_var_event(&sb->s_flags, super_flags(sb, SB_DEAD)); put_super(sb); return false; } @@ -834,7 +790,7 @@ share_extant_sb: warnfc(fc, "reusing existing filesystem in another namespace not allowed"); return ERR_PTR(-EBUSY); } - if (!grab_super_dead(old)) + if (!grab_super(old)) goto retry; destroy_unused_super(s); return old; @@ -878,7 +834,7 @@ retry: destroy_unused_super(s); return ERR_PTR(-EBUSY); } - if (!grab_super_dead(old)) + if (!grab_super(old)) goto retry; destroy_unused_super(s); return old; @@ -930,8 +886,7 @@ static void __iterate_supers(void (*f)(struct super_block *)) spin_lock(&sb_lock); list_for_each_entry(sb, &super_blocks, s_list) { - /* Pairs with memory marrier in super_wake(). */ - if (smp_load_acquire(&sb->s_flags) & SB_DYING) + if (super_flags(sb, SB_DYING)) continue; sb->s_count++; spin_unlock(&sb_lock); @@ -961,15 +916,17 @@ void iterate_supers(void (*f)(struct super_block *, void *), void *arg) spin_lock(&sb_lock); list_for_each_entry(sb, &super_blocks, s_list) { - bool born; + bool locked; sb->s_count++; spin_unlock(&sb_lock); - born = super_lock_shared(sb); - if (born && sb->s_root) - f(sb, arg); - super_unlock_shared(sb); + locked = super_lock_shared(sb); + if (locked) { + if (sb->s_root) + f(sb, arg); + super_unlock_shared(sb); + } spin_lock(&sb_lock); if (p) @@ -997,15 +954,17 @@ void iterate_supers_type(struct file_system_type *type, spin_lock(&sb_lock); hlist_for_each_entry(sb, &type->fs_supers, s_instances) { - bool born; + bool locked; sb->s_count++; spin_unlock(&sb_lock); - born = super_lock_shared(sb); - if (born && sb->s_root) - f(sb, arg); - super_unlock_shared(sb); + locked = super_lock_shared(sb); + if (locked) { + if (sb->s_root) + f(sb, arg); + super_unlock_shared(sb); + } spin_lock(&sb_lock); if (p) @@ -1019,34 +978,6 @@ void iterate_supers_type(struct file_system_type *type, EXPORT_SYMBOL(iterate_supers_type); -/** - * get_active_super - get an active reference to the superblock of a device - * @bdev: device to get the superblock for - * - * Scans the superblock list and finds the superblock of the file system - * mounted on the device given. Returns the superblock with an active - * reference or %NULL if none was found. - */ -struct super_block *get_active_super(struct block_device *bdev) -{ - struct super_block *sb; - - if (!bdev) - return NULL; - - spin_lock(&sb_lock); - list_for_each_entry(sb, &super_blocks, s_list) { - if (sb->s_bdev == bdev) { - if (!grab_super(sb)) - return NULL; - super_unlock_excl(sb); - return sb; - } - } - spin_unlock(&sb_lock); - return NULL; -} - struct super_block *user_get_super(dev_t dev, bool excl) { struct super_block *sb; @@ -1054,15 +985,17 @@ struct super_block *user_get_super(dev_t dev, bool excl) spin_lock(&sb_lock); list_for_each_entry(sb, &super_blocks, s_list) { if (sb->s_dev == dev) { - bool born; + bool locked; sb->s_count++; spin_unlock(&sb_lock); /* still alive? */ - born = super_lock(sb, excl); - if (born && sb->s_root) - return sb; - super_unlock(sb, excl); + locked = super_lock(sb, excl); + if (locked) { + if (sb->s_root) + return sb; + super_unlock(sb, excl); + } /* nope, got unmounted */ spin_lock(&sb_lock); __put_super(sb); @@ -1173,9 +1106,9 @@ cancel_readonly: static void do_emergency_remount_callback(struct super_block *sb) { - bool born = super_lock_excl(sb); + bool locked = super_lock_excl(sb); - if (born && sb->s_root && sb->s_bdev && !sb_rdonly(sb)) { + if (locked && sb->s_root && sb->s_bdev && !sb_rdonly(sb)) { struct fs_context *fc; fc = fs_context_for_reconfigure(sb->s_root, @@ -1186,7 +1119,8 @@ static void do_emergency_remount_callback(struct super_block *sb) put_fs_context(fc); } } - super_unlock_excl(sb); + if (locked) + super_unlock_excl(sb); } static void do_emergency_remount(struct work_struct *work) @@ -1209,16 +1143,17 @@ void emergency_remount(void) static void do_thaw_all_callback(struct super_block *sb) { - bool born = super_lock_excl(sb); + bool locked = super_lock_excl(sb); - if (born && sb->s_root) { + if (locked && sb->s_root) { if (IS_ENABLED(CONFIG_BLOCK)) - while (sb->s_bdev && !thaw_bdev(sb->s_bdev)) + while (sb->s_bdev && !bdev_thaw(sb->s_bdev)) pr_warn("Emergency Thaw on %pg\n", sb->s_bdev); thaw_super_locked(sb, FREEZE_HOLDER_USERSPACE); - } else { - super_unlock_excl(sb); + return; } + if (locked) + super_unlock_excl(sb); } static void do_thaw_all(struct work_struct *work) @@ -1428,11 +1363,11 @@ EXPORT_SYMBOL(sget_dev); * * The function must be called with bdev->bd_holder_lock and releases it. */ -static struct super_block *bdev_super_lock_shared(struct block_device *bdev) +static struct super_block *bdev_super_lock(struct block_device *bdev, bool excl) __releases(&bdev->bd_holder_lock) { struct super_block *sb = bdev->bd_holder; - bool born; + bool locked; lockdep_assert_held(&bdev->bd_holder_lock); lockdep_assert_not_held(&sb->s_umount); @@ -1442,19 +1377,25 @@ static struct super_block *bdev_super_lock_shared(struct block_device *bdev) spin_lock(&sb_lock); sb->s_count++; spin_unlock(&sb_lock); + mutex_unlock(&bdev->bd_holder_lock); - born = super_lock_shared(sb); - if (!born || !sb->s_root || !(sb->s_flags & SB_ACTIVE)) { - super_unlock_shared(sb); - put_super(sb); - return NULL; - } + locked = super_lock(sb, excl); + /* - * The superblock is active and we hold s_umount, we can drop our - * temporary reference now. - */ + * If the superblock wasn't already SB_DYING then we hold + * s_umount and can safely drop our temporary reference. + */ put_super(sb); + + if (!locked) + return NULL; + + if (!sb->s_root || !(sb->s_flags & SB_ACTIVE)) { + super_unlock(sb, excl); + return NULL; + } + return sb; } @@ -1462,7 +1403,7 @@ static void fs_bdev_mark_dead(struct block_device *bdev, bool surprise) { struct super_block *sb; - sb = bdev_super_lock_shared(bdev); + sb = bdev_super_lock(bdev, false); if (!sb) return; @@ -1480,16 +1421,110 @@ static void fs_bdev_sync(struct block_device *bdev) { struct super_block *sb; - sb = bdev_super_lock_shared(bdev); + sb = bdev_super_lock(bdev, false); if (!sb) return; + sync_filesystem(sb); super_unlock_shared(sb); } +static struct super_block *get_bdev_super(struct block_device *bdev) +{ + bool active = false; + struct super_block *sb; + + sb = bdev_super_lock(bdev, true); + if (sb) { + active = atomic_inc_not_zero(&sb->s_active); + super_unlock_excl(sb); + } + if (!active) + return NULL; + return sb; +} + +/** + * fs_bdev_freeze - freeze owning filesystem of block device + * @bdev: block device + * + * Freeze the filesystem that owns this block device if it is still + * active. + * + * A filesystem that owns multiple block devices may be frozen from each + * block device and won't be unfrozen until all block devices are + * unfrozen. Each block device can only freeze the filesystem once as we + * nest freezes for block devices in the block layer. + * + * Return: If the freeze was successful zero is returned. If the freeze + * failed a negative error code is returned. + */ +static int fs_bdev_freeze(struct block_device *bdev) +{ + struct super_block *sb; + int error = 0; + + lockdep_assert_held(&bdev->bd_fsfreeze_mutex); + + sb = get_bdev_super(bdev); + if (!sb) + return -EINVAL; + + if (sb->s_op->freeze_super) + error = sb->s_op->freeze_super(sb, + FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE); + else + error = freeze_super(sb, + FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE); + if (!error) + error = sync_blockdev(bdev); + deactivate_super(sb); + return error; +} + +/** + * fs_bdev_thaw - thaw owning filesystem of block device + * @bdev: block device + * + * Thaw the filesystem that owns this block device. + * + * A filesystem that owns multiple block devices may be frozen from each + * block device and won't be unfrozen until all block devices are + * unfrozen. Each block device can only freeze the filesystem once as we + * nest freezes for block devices in the block layer. + * + * Return: If the thaw was successful zero is returned. If the thaw + * failed a negative error code is returned. If this function + * returns zero it doesn't mean that the filesystem is unfrozen + * as it may have been frozen multiple times (kernel may hold a + * freeze or might be frozen from other block devices). + */ +static int fs_bdev_thaw(struct block_device *bdev) +{ + struct super_block *sb; + int error; + + lockdep_assert_held(&bdev->bd_fsfreeze_mutex); + + sb = get_bdev_super(bdev); + if (WARN_ON_ONCE(!sb)) + return -EINVAL; + + if (sb->s_op->thaw_super) + error = sb->s_op->thaw_super(sb, + FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE); + else + error = thaw_super(sb, + FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE); + deactivate_super(sb); + return error; +} + const struct blk_holder_ops fs_holder_ops = { .mark_dead = fs_bdev_mark_dead, .sync = fs_bdev_sync, + .freeze = fs_bdev_freeze, + .thaw = fs_bdev_thaw, }; EXPORT_SYMBOL_GPL(fs_holder_ops); @@ -1519,15 +1554,10 @@ int setup_bdev_super(struct super_block *sb, int sb_flags, } /* - * Until SB_BORN flag is set, there can be no active superblock - * references and thus no filesystem freezing. get_active_super() will - * just loop waiting for SB_BORN so even freeze_bdev() cannot proceed. - * - * It is enough to check bdev was not frozen before we set s_bdev. + * It is enough to check bdev was not frozen before we set + * s_bdev as freezing will wait until SB_BORN is set. */ - mutex_lock(&bdev->bd_fsfreeze_mutex); - if (bdev->bd_fsfreeze_count > 0) { - mutex_unlock(&bdev->bd_fsfreeze_mutex); + if (atomic_read(&bdev->bd_fsfreeze_count) > 0) { if (fc) warnf(fc, "%pg: Can't mount, blockdev is frozen", bdev); bdev_release(bdev_handle); @@ -1540,7 +1570,6 @@ int setup_bdev_super(struct super_block *sb, int sb_flags, if (bdev_stable_writes(bdev)) sb->s_iflags |= SB_I_STABLE_WRITES; spin_unlock(&sb_lock); - mutex_unlock(&bdev->bd_fsfreeze_mutex); snprintf(sb->s_id, sizeof(sb->s_id), "%pg", bdev); shrinker_debugfs_rename(sb->s_shrink, "sb-%s:%s", sb->s_type->name, @@ -1585,15 +1614,7 @@ int get_tree_bdev(struct fs_context *fc, return -EBUSY; } } else { - /* - * We drop s_umount here because we need to open the bdev and - * bdev->open_mutex ranks above s_umount (blkdev_put() -> - * bdev_mark_dead()). It is safe because we have active sb - * reference and SB_BORN is not set yet. - */ - super_unlock_excl(s); error = setup_bdev_super(s, fc->sb_flags, fc); - __super_lock_excl(s); if (!error) error = fill_super(s, fc); if (error) { @@ -1637,15 +1658,7 @@ struct dentry *mount_bdev(struct file_system_type *fs_type, return ERR_PTR(-EBUSY); } } else { - /* - * We drop s_umount here because we need to open the bdev and - * bdev->open_mutex ranks above s_umount (blkdev_put() -> - * bdev_mark_dead()). It is safe because we have active sb - * reference and SB_BORN is not set yet. - */ - super_unlock_excl(s); error = setup_bdev_super(s, flags, NULL); - __super_lock_excl(s); if (!error) error = fill_super(s, data, flags & SB_SILENT ? 1 : 0); if (error) { @@ -1914,6 +1927,47 @@ static int wait_for_partially_frozen(struct super_block *sb) return ret; } +#define FREEZE_HOLDERS (FREEZE_HOLDER_KERNEL | FREEZE_HOLDER_USERSPACE) +#define FREEZE_FLAGS (FREEZE_HOLDERS | FREEZE_MAY_NEST) + +static inline int freeze_inc(struct super_block *sb, enum freeze_holder who) +{ + WARN_ON_ONCE((who & ~FREEZE_FLAGS)); + WARN_ON_ONCE(hweight32(who & FREEZE_HOLDERS) > 1); + + if (who & FREEZE_HOLDER_KERNEL) + ++sb->s_writers.freeze_kcount; + if (who & FREEZE_HOLDER_USERSPACE) + ++sb->s_writers.freeze_ucount; + return sb->s_writers.freeze_kcount + sb->s_writers.freeze_ucount; +} + +static inline int freeze_dec(struct super_block *sb, enum freeze_holder who) +{ + WARN_ON_ONCE((who & ~FREEZE_FLAGS)); + WARN_ON_ONCE(hweight32(who & FREEZE_HOLDERS) > 1); + + if ((who & FREEZE_HOLDER_KERNEL) && sb->s_writers.freeze_kcount) + --sb->s_writers.freeze_kcount; + if ((who & FREEZE_HOLDER_USERSPACE) && sb->s_writers.freeze_ucount) + --sb->s_writers.freeze_ucount; + return sb->s_writers.freeze_kcount + sb->s_writers.freeze_ucount; +} + +static inline bool may_freeze(struct super_block *sb, enum freeze_holder who) +{ + WARN_ON_ONCE((who & ~FREEZE_FLAGS)); + WARN_ON_ONCE(hweight32(who & FREEZE_HOLDERS) > 1); + + if (who & FREEZE_HOLDER_KERNEL) + return (who & FREEZE_MAY_NEST) || + sb->s_writers.freeze_kcount == 0; + if (who & FREEZE_HOLDER_USERSPACE) + return (who & FREEZE_MAY_NEST) || + sb->s_writers.freeze_ucount == 0; + return false; +} + /** * freeze_super - lock the filesystem and force it into a consistent state * @sb: the super to lock @@ -1926,6 +1980,7 @@ static int wait_for_partially_frozen(struct super_block *sb) * @who should be: * * %FREEZE_HOLDER_USERSPACE if userspace wants to freeze the fs; * * %FREEZE_HOLDER_KERNEL if the kernel wants to freeze the fs. + * * %FREEZE_MAY_NEST whether nesting freeze and thaw requests is allowed. * * The @who argument distinguishes between the kernel and userspace trying to * freeze the filesystem. Although there cannot be multiple kernel freezes or @@ -1933,6 +1988,13 @@ static int wait_for_partially_frozen(struct super_block *sb) * userspace can both hold a filesystem frozen. The filesystem remains frozen * until there are no kernel or userspace freezes in effect. * + * A filesystem may hold multiple devices and thus a filesystems may be + * frozen through the block layer via multiple block devices. In this + * case the request is marked as being allowed to nest by passing + * FREEZE_MAY_NEST. The filesystem remains frozen until all block + * devices are unfrozen. If multiple freezes are attempted without + * FREEZE_MAY_NEST -EBUSY will be returned. + * * During this function, sb->s_writers.frozen goes through these values: * * SB_UNFROZEN: File system is normal, all writes progress as usual. @@ -1957,31 +2019,29 @@ static int wait_for_partially_frozen(struct super_block *sb) * mostly auxiliary for filesystems to verify they do not modify frozen fs. * * sb->s_writers.frozen is protected by sb->s_umount. + * + * Return: If the freeze was successful zero is returned. If the freeze + * failed a negative error code is returned. */ int freeze_super(struct super_block *sb, enum freeze_holder who) { int ret; + if (!super_lock_excl(sb)) { + WARN_ON_ONCE("Dying superblock while freezing!"); + return -EINVAL; + } atomic_inc(&sb->s_active); - if (!super_lock_excl(sb)) - WARN(1, "Dying superblock while freezing!"); retry: if (sb->s_writers.frozen == SB_FREEZE_COMPLETE) { - if (sb->s_writers.freeze_holders & who) { - deactivate_locked_super(sb); - return -EBUSY; - } - - WARN_ON(sb->s_writers.freeze_holders == 0); - - /* - * Someone else already holds this type of freeze; share the - * freeze and assign the active ref to the freeze. - */ - sb->s_writers.freeze_holders |= who; - super_unlock_excl(sb); - return 0; + if (may_freeze(sb, who)) + ret = !!WARN_ON_ONCE(freeze_inc(sb, who) == 1); + else + ret = -EBUSY; + /* All freezers share a single active reference. */ + deactivate_locked_super(sb); + return ret; } if (sb->s_writers.frozen != SB_UNFROZEN) { @@ -1994,14 +2054,9 @@ retry: goto retry; } - if (!(sb->s_flags & SB_BORN)) { - super_unlock_excl(sb); - return 0; /* sic - it's "nothing to do" */ - } - if (sb_rdonly(sb)) { /* Nothing to do really... */ - sb->s_writers.freeze_holders |= who; + WARN_ON_ONCE(freeze_inc(sb, who) > 1); sb->s_writers.frozen = SB_FREEZE_COMPLETE; wake_up_var(&sb->s_writers.frozen); super_unlock_excl(sb); @@ -2012,8 +2067,7 @@ retry: /* Release s_umount to preserve sb_start_write -> s_umount ordering */ super_unlock_excl(sb); sb_wait_write(sb, SB_FREEZE_WRITE); - if (!super_lock_excl(sb)) - WARN(1, "Dying superblock while freezing!"); + __super_lock_excl(sb); /* Now we go and block page faults... */ sb->s_writers.frozen = SB_FREEZE_PAGEFAULT; @@ -2049,7 +2103,7 @@ retry: * For debugging purposes so that fs can warn if it sees write activity * when frozen is set to SB_FREEZE_COMPLETE, and for thaw_super(). */ - sb->s_writers.freeze_holders |= who; + WARN_ON_ONCE(freeze_inc(sb, who) > 1); sb->s_writers.frozen = SB_FREEZE_COMPLETE; wake_up_var(&sb->s_writers.frozen); lockdep_sb_freeze_release(sb); @@ -2066,34 +2120,22 @@ EXPORT_SYMBOL(freeze_super); */ static int thaw_super_locked(struct super_block *sb, enum freeze_holder who) { - int error; + int error = -EINVAL; - if (sb->s_writers.frozen == SB_FREEZE_COMPLETE) { - if (!(sb->s_writers.freeze_holders & who)) { - super_unlock_excl(sb); - return -EINVAL; - } + if (sb->s_writers.frozen != SB_FREEZE_COMPLETE) + goto out_unlock; - /* - * Freeze is shared with someone else. Release our hold and - * drop the active ref that freeze_super assigned to the - * freezer. - */ - if (sb->s_writers.freeze_holders & ~who) { - sb->s_writers.freeze_holders &= ~who; - deactivate_locked_super(sb); - return 0; - } - } else { - super_unlock_excl(sb); - return -EINVAL; - } + /* + * All freezers share a single active reference. + * So just unlock in case there are any left. + */ + if (freeze_dec(sb, who)) + goto out_unlock; if (sb_rdonly(sb)) { - sb->s_writers.freeze_holders &= ~who; sb->s_writers.frozen = SB_UNFROZEN; wake_up_var(&sb->s_writers.frozen); - goto out; + goto out_deactivate; } lockdep_sb_freeze_acquire(sb); @@ -2101,20 +2143,23 @@ static int thaw_super_locked(struct super_block *sb, enum freeze_holder who) if (sb->s_op->unfreeze_fs) { error = sb->s_op->unfreeze_fs(sb); if (error) { - printk(KERN_ERR "VFS:Filesystem thaw failed\n"); + pr_err("VFS: Filesystem thaw failed\n"); + freeze_inc(sb, who); lockdep_sb_freeze_release(sb); - super_unlock_excl(sb); - return error; + goto out_unlock; } } - sb->s_writers.freeze_holders &= ~who; sb->s_writers.frozen = SB_UNFROZEN; wake_up_var(&sb->s_writers.frozen); sb_freeze_unlock(sb, SB_FREEZE_FS); -out: +out_deactivate: deactivate_locked_super(sb); return 0; + +out_unlock: + super_unlock_excl(sb); + return error; } /** @@ -2128,11 +2173,18 @@ out: * @who should be: * * %FREEZE_HOLDER_USERSPACE if userspace wants to thaw the fs; * * %FREEZE_HOLDER_KERNEL if the kernel wants to thaw the fs. + * * %FREEZE_MAY_NEST whether nesting freeze and thaw requests is allowed + * + * A filesystem may hold multiple devices and thus a filesystems may + * have been frozen through the block layer via multiple block devices. + * The filesystem remains frozen until all block devices are unfrozen. */ int thaw_super(struct super_block *sb, enum freeze_holder who) { - if (!super_lock_excl(sb)) - WARN(1, "Dying superblock while thawing!"); + if (!super_lock_excl(sb)) { + WARN_ON_ONCE("Dying superblock while thawing!"); + return -EINVAL; + } return thaw_super_locked(sb, who); } EXPORT_SYMBOL(thaw_super); diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c index 0b90869fd805..f0677ea0ec24 100644 --- a/fs/tracefs/event_inode.c +++ b/fs/tracefs/event_inode.c @@ -113,7 +113,14 @@ static int eventfs_set_attr(struct mnt_idmap *idmap, struct dentry *dentry, * determined by the parent directory. */ if (dentry->d_inode->i_mode & S_IFDIR) { - update_attr(&ei->attr, iattr); + /* + * The events directory dentry is never freed, unless its + * part of an instance that is deleted. It's attr is the + * default for its child files and directories. + * Do not update it. It's not used for its own mode or ownership + */ + if (!ei->is_events) + update_attr(&ei->attr, iattr); } else { name = dentry->d_name.name; @@ -148,17 +155,49 @@ static const struct file_operations eventfs_file_operations = { .release = eventfs_release, }; -static void update_inode_attr(struct inode *inode, struct eventfs_attr *attr, umode_t mode) +/* Return the evenfs_inode of the "events" directory */ +static struct eventfs_inode *eventfs_find_events(struct dentry *dentry) +{ + struct eventfs_inode *ei; + + mutex_lock(&eventfs_mutex); + do { + /* The parent always has an ei, except for events itself */ + ei = dentry->d_parent->d_fsdata; + + /* + * If the ei is being freed, the ownership of the children + * doesn't matter. + */ + if (ei->is_freed) { + ei = NULL; + break; + } + + dentry = ei->dentry; + } while (!ei->is_events); + mutex_unlock(&eventfs_mutex); + + return ei; +} + +static void update_inode_attr(struct dentry *dentry, struct inode *inode, + struct eventfs_attr *attr, umode_t mode) { - if (!attr) { - inode->i_mode = mode; + struct eventfs_inode *events_ei = eventfs_find_events(dentry); + + if (!events_ei) + return; + + inode->i_mode = mode; + inode->i_uid = events_ei->attr.uid; + inode->i_gid = events_ei->attr.gid; + + if (!attr) return; - } if (attr->mode & EVENTFS_SAVE_MODE) inode->i_mode = attr->mode & EVENTFS_MODE_MASK; - else - inode->i_mode = mode; if (attr->mode & EVENTFS_SAVE_UID) inode->i_uid = attr->uid; @@ -167,6 +206,44 @@ static void update_inode_attr(struct inode *inode, struct eventfs_attr *attr, um inode->i_gid = attr->gid; } +static void update_gid(struct eventfs_inode *ei, kgid_t gid, int level) +{ + struct eventfs_inode *ei_child; + + /* at most we have events/system/event */ + if (WARN_ON_ONCE(level > 3)) + return; + + ei->attr.gid = gid; + + if (ei->entry_attrs) { + for (int i = 0; i < ei->nr_entries; i++) { + ei->entry_attrs[i].gid = gid; + } + } + + /* + * Only eventfs_inode with dentries are updated, make sure + * all eventfs_inodes are updated. If one of the children + * do not have a dentry, this function must traverse it. + */ + list_for_each_entry_srcu(ei_child, &ei->children, list, + srcu_read_lock_held(&eventfs_srcu)) { + if (!ei_child->dentry) + update_gid(ei_child, gid, level + 1); + } +} + +void eventfs_update_gid(struct dentry *dentry, kgid_t gid) +{ + struct eventfs_inode *ei = dentry->d_fsdata; + int idx; + + idx = srcu_read_lock(&eventfs_srcu); + update_gid(ei, gid, 0); + srcu_read_unlock(&eventfs_srcu, idx); +} + /** * create_file - create a file in the tracefs filesystem * @name: the name of the file to create. @@ -206,7 +283,7 @@ static struct dentry *create_file(const char *name, umode_t mode, return eventfs_failed_creating(dentry); /* If the user updated the directory's attributes, use them */ - update_inode_attr(inode, attr, mode); + update_inode_attr(dentry, inode, attr, mode); inode->i_op = &eventfs_file_inode_operations; inode->i_fop = fop; @@ -242,7 +319,8 @@ static struct dentry *create_dir(struct eventfs_inode *ei, struct dentry *parent return eventfs_failed_creating(dentry); /* If the user updated the directory's attributes, use them */ - update_inode_attr(inode, &ei->attr, S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO); + update_inode_attr(dentry, inode, &ei->attr, + S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO); inode->i_op = &eventfs_root_dir_inode_operations; inode->i_fop = &eventfs_file_operations; @@ -546,6 +624,8 @@ static struct dentry *eventfs_root_lookup(struct inode *dir, if (strcmp(ei_child->name, name) != 0) continue; ret = simple_lookup(dir, dentry, flags); + if (IS_ERR(ret)) + goto out; create_dir_dentry(ei, ei_child, ei_dentry, true); created = true; break; @@ -568,6 +648,8 @@ static struct dentry *eventfs_root_lookup(struct inode *dir, if (r <= 0) continue; ret = simple_lookup(dir, dentry, flags); + if (IS_ERR(ret)) + goto out; create_file_dentry(ei, i, ei_dentry, name, mode, cdata, fops, true); break; @@ -850,6 +932,8 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry struct eventfs_inode *ei; struct tracefs_inode *ti; struct inode *inode; + kuid_t uid; + kgid_t gid; if (security_locked_down(LOCKDOWN_TRACEFS)) return NULL; @@ -874,11 +958,20 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry ei->dentry = dentry; ei->entries = entries; ei->nr_entries = size; + ei->is_events = 1; ei->data = data; ei->name = kstrdup_const(name, GFP_KERNEL); if (!ei->name) goto fail; + /* Save the ownership of this directory */ + uid = d_inode(dentry->d_parent)->i_uid; + gid = d_inode(dentry->d_parent)->i_gid; + + /* This is used as the default ownership of the files and directories */ + ei->attr.uid = uid; + ei->attr.gid = gid; + INIT_LIST_HEAD(&ei->children); INIT_LIST_HEAD(&ei->list); @@ -887,6 +980,8 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry ti->private = ei; inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO; + inode->i_uid = uid; + inode->i_gid = gid; inode->i_op = &eventfs_root_dir_inode_operations; inode->i_fop = &eventfs_file_operations; diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index ae648deed019..bc86ffdb103b 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -210,14 +210,24 @@ repeat: next = this_parent->d_subdirs.next; resume: while (next != &this_parent->d_subdirs) { + struct tracefs_inode *ti; struct list_head *tmp = next; struct dentry *dentry = list_entry(tmp, struct dentry, d_child); next = tmp->next; + /* Note, getdents() can add a cursor dentry with no inode */ + if (!dentry->d_inode) + continue; + spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); change_gid(dentry, gid); + /* If this is the events directory, update that too */ + ti = get_tracefs(dentry->d_inode); + if (ti && (ti->flags & TRACEFS_EVENT_INODE)) + eventfs_update_gid(dentry, gid); + if (!list_empty(&dentry->d_subdirs)) { spin_unlock(&this_parent->d_lock); spin_release(&dentry->d_lock.dep_map, _RET_IP_); diff --git a/fs/tracefs/internal.h b/fs/tracefs/internal.h index ccee18ca66c7..42bdeb471a07 100644 --- a/fs/tracefs/internal.h +++ b/fs/tracefs/internal.h @@ -62,7 +62,8 @@ struct eventfs_inode { struct rcu_head rcu; }; unsigned int is_freed:1; - unsigned int nr_entries:31; + unsigned int is_events:1; + unsigned int nr_entries:30; }; static inline struct tracefs_inode *get_tracefs(const struct inode *inode) @@ -77,6 +78,7 @@ struct inode *tracefs_get_inode(struct super_block *sb); struct dentry *eventfs_start_creating(const char *name, struct dentry *parent); struct dentry *eventfs_failed_creating(struct dentry *dentry); struct dentry *eventfs_end_creating(struct dentry *dentry); +void eventfs_update_gid(struct dentry *dentry, kgid_t gid); void eventfs_set_ei_status_free(struct tracefs_inode *ti, struct dentry *dentry); #endif /* _TRACEFS_INTERNAL_H */ diff --git a/fs/ufs/util.c b/fs/ufs/util.c index 13ba34e6d64f..2acf191eb89e 100644 --- a/fs/ufs/util.c +++ b/fs/ufs/util.c @@ -245,7 +245,7 @@ struct folio *ufs_get_locked_folio(struct address_space *mapping, { struct inode *inode = mapping->host; struct folio *folio = filemap_lock_folio(mapping, index); - if (!folio) { + if (IS_ERR(folio)) { folio = read_mapping_folio(mapping, index, NULL); if (IS_ERR(folio)) { diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index 7cb75cb6b8e9..57076a25f17d 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -482,9 +482,9 @@ xfs_fs_goingdown( { switch (inflags) { case XFS_FSOP_GOING_FLAGS_DEFAULT: { - if (!freeze_bdev(mp->m_super->s_bdev)) { + if (!bdev_freeze(mp->m_super->s_bdev)) { xfs_force_shutdown(mp, SHUTDOWN_FORCE_UMOUNT); - thaw_bdev(mp->m_super->s_bdev); + bdev_thaw(mp->m_super->s_bdev); } break; } diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 764304595e8b..07857d967ee8 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -366,8 +366,9 @@ xfs_blkdev_get( { int error = 0; - *handlep = bdev_open_by_path(name, BLK_OPEN_READ | BLK_OPEN_WRITE, - mp->m_super, &fs_holder_ops); + *handlep = bdev_open_by_path(name, + BLK_OPEN_READ | BLK_OPEN_WRITE | BLK_OPEN_RESTRICT_WRITES, + mp->m_super, &fs_holder_ops); if (IS_ERR(*handlep)) { error = PTR_ERR(*handlep); *handlep = NULL; @@ -439,18 +440,12 @@ xfs_open_devices( int error; /* - * blkdev_put() can't be called under s_umount, see the comment - * in get_tree_bdev() for more details - */ - up_write(&sb->s_umount); - - /* * Open real time and log devices - order is important. */ if (mp->m_logname) { error = xfs_blkdev_get(mp, mp->m_logname, &logdev_handle); if (error) - goto out_relock; + return error; } if (mp->m_rtname) { @@ -493,10 +488,7 @@ xfs_open_devices( bdev_release(logdev_handle); } - error = 0; -out_relock: - down_write(&sb->s_umount); - return error; + return 0; out_free_rtdev_targ: if (mp->m_rtdev_targp) @@ -509,7 +501,7 @@ out_relock: out_close_logdev: if (logdev_handle) bdev_release(logdev_handle); - goto out_relock; + return error; } /* @@ -759,10 +751,6 @@ static void xfs_mount_free( struct xfs_mount *mp) { - /* - * Free the buftargs here because blkdev_put needs to be called outside - * of sb->s_umount, which is held around the call to ->put_super. - */ if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp) xfs_free_buftarg(mp->m_logdev_targp); if (mp->m_rtdev_targp) diff --git a/include/asm-generic/unaligned.h b/include/asm-generic/unaligned.h index 699650f81970..a84c64e5f11e 100644 --- a/include/asm-generic/unaligned.h +++ b/include/asm-generic/unaligned.h @@ -104,9 +104,9 @@ static inline u32 get_unaligned_le24(const void *p) static inline void __put_unaligned_be24(const u32 val, u8 *p) { - *p++ = val >> 16; - *p++ = val >> 8; - *p++ = val; + *p++ = (val >> 16) & 0xff; + *p++ = (val >> 8) & 0xff; + *p++ = val & 0xff; } static inline void put_unaligned_be24(const u32 val, void *p) @@ -116,9 +116,9 @@ static inline void put_unaligned_be24(const u32 val, void *p) static inline void __put_unaligned_le24(const u32 val, u8 *p) { - *p++ = val; - *p++ = val >> 8; - *p++ = val >> 16; + *p++ = val & 0xff; + *p++ = (val >> 8) & 0xff; + *p++ = (val >> 16) & 0xff; } static inline void put_unaligned_le24(const u32 val, void *p) @@ -128,12 +128,12 @@ static inline void put_unaligned_le24(const u32 val, void *p) static inline void __put_unaligned_be48(const u64 val, u8 *p) { - *p++ = val >> 40; - *p++ = val >> 32; - *p++ = val >> 24; - *p++ = val >> 16; - *p++ = val >> 8; - *p++ = val; + *p++ = (val >> 40) & 0xff; + *p++ = (val >> 32) & 0xff; + *p++ = (val >> 24) & 0xff; + *p++ = (val >> 16) & 0xff; + *p++ = (val >> 8) & 0xff; + *p++ = val & 0xff; } static inline void put_unaligned_be48(const u64 val, void *p) diff --git a/include/linux/backing-file.h b/include/linux/backing-file.h new file mode 100644 index 000000000000..3f1fe1774f1b --- /dev/null +++ b/include/linux/backing-file.h @@ -0,0 +1,42 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Common helpers for stackable filesystems and backing files. + * + * Copyright (C) 2023 CTERA Networks. + */ + +#ifndef _LINUX_BACKING_FILE_H +#define _LINUX_BACKING_FILE_H + +#include <linux/file.h> +#include <linux/uio.h> +#include <linux/fs.h> + +struct backing_file_ctx { + const struct cred *cred; + struct file *user_file; + void (*accessed)(struct file *); + void (*end_write)(struct file *); +}; + +struct file *backing_file_open(const struct path *user_path, int flags, + const struct path *real_path, + const struct cred *cred); +ssize_t backing_file_read_iter(struct file *file, struct iov_iter *iter, + struct kiocb *iocb, int flags, + struct backing_file_ctx *ctx); +ssize_t backing_file_write_iter(struct file *file, struct iov_iter *iter, + struct kiocb *iocb, int flags, + struct backing_file_ctx *ctx); +ssize_t backing_file_splice_read(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, + unsigned int flags, + struct backing_file_ctx *ctx); +ssize_t backing_file_splice_write(struct pipe_inode_info *pipe, + struct file *out, loff_t *ppos, size_t len, + unsigned int flags, + struct backing_file_ctx *ctx); +int backing_file_mmap(struct file *file, struct vm_area_struct *vma, + struct backing_file_ctx *ctx); + +#endif /* _LINUX_BACKING_FILE_H */ diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index b29ebd53417d..7c2316c91cbd 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -57,20 +57,18 @@ struct block_device { void * bd_holder; const struct blk_holder_ops *bd_holder_ops; struct mutex bd_holder_lock; - /* The counter of freeze processes */ - int bd_fsfreeze_count; int bd_holders; struct kobject *bd_holder_dir; - /* Mutex for freeze */ - struct mutex bd_fsfreeze_mutex; - struct super_block *bd_fsfreeze_sb; + atomic_t bd_fsfreeze_count; /* number of freeze requests */ + struct mutex bd_fsfreeze_mutex; /* serialize freeze/thaw */ struct partition_meta_info *bd_meta_info; #ifdef CONFIG_FAIL_MAKE_REQUEST bool bd_make_it_fail; #endif bool bd_ro_warned; + int bd_writers; /* * keep this out-of-line as it's both big and not needed in the fast * path diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 51fa7ffdee83..c30a98e08423 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -124,6 +124,8 @@ typedef unsigned int __bitwise blk_mode_t; #define BLK_OPEN_NDELAY ((__force blk_mode_t)(1 << 3)) /* open for "writes" only for ioctls (specialy hack for floppy.c) */ #define BLK_OPEN_WRITE_IOCTL ((__force blk_mode_t)(1 << 4)) +/* open is exclusive wrt all other BLK_OPEN_WRITE opens to the device */ +#define BLK_OPEN_RESTRICT_WRITES ((__force blk_mode_t)(1 << 5)) struct gendisk { /* @@ -538,7 +540,7 @@ struct request_queue { #define QUEUE_FLAG_ADD_RANDOM 10 /* Contributes to random pool */ #define QUEUE_FLAG_SYNCHRONOUS 11 /* always completes in submit context */ #define QUEUE_FLAG_SAME_FORCE 12 /* force complete on same CPU */ -#define QUEUE_FLAG_HW_WC 18 /* Write back caching supported */ +#define QUEUE_FLAG_HW_WC 13 /* Write back caching supported */ #define QUEUE_FLAG_INIT_DONE 14 /* queue is initialized */ #define QUEUE_FLAG_STABLE_WRITES 15 /* don't modify blks until WB is done */ #define QUEUE_FLAG_POLL 16 /* IO polling enabled if set */ @@ -1468,8 +1470,23 @@ struct blk_holder_ops { * Sync the file system mounted on the block device. */ void (*sync)(struct block_device *bdev); + + /* + * Freeze the file system mounted on the block device. + */ + int (*freeze)(struct block_device *bdev); + + /* + * Thaw the file system mounted on the block device. + */ + int (*thaw)(struct block_device *bdev); }; +/* + * For filesystems using @fs_holder_ops, the @holder argument passed to + * helpers used to open and claim block devices via + * bd_prepare_to_claim() must point to a superblock. + */ extern const struct blk_holder_ops fs_holder_ops; /* @@ -1477,7 +1494,8 @@ extern const struct blk_holder_ops fs_holder_ops; * as stored in sb->s_flags. */ #define sb_open_mode(flags) \ - (BLK_OPEN_READ | (((flags) & SB_RDONLY) ? 0 : BLK_OPEN_WRITE)) + (BLK_OPEN_READ | BLK_OPEN_RESTRICT_WRITES | \ + (((flags) & SB_RDONLY) ? 0 : BLK_OPEN_WRITE)) struct bdev_handle { struct block_device *bdev; @@ -1485,10 +1503,6 @@ struct bdev_handle { blk_mode_t mode; }; -struct block_device *blkdev_get_by_dev(dev_t dev, blk_mode_t mode, void *holder, - const struct blk_holder_ops *hops); -struct block_device *blkdev_get_by_path(const char *path, blk_mode_t mode, - void *holder, const struct blk_holder_ops *hops); struct bdev_handle *bdev_open_by_dev(dev_t dev, blk_mode_t mode, void *holder, const struct blk_holder_ops *hops); struct bdev_handle *bdev_open_by_path(const char *path, blk_mode_t mode, @@ -1496,7 +1510,6 @@ struct bdev_handle *bdev_open_by_path(const char *path, blk_mode_t mode, int bd_prepare_to_claim(struct block_device *bdev, void *holder, const struct blk_holder_ops *hops); void bd_abort_claiming(struct block_device *bdev, void *holder); -void blkdev_put(struct block_device *bdev, void *holder); void bdev_release(struct bdev_handle *handle); /* just for blk-cgroup, don't use elsewhere */ @@ -1541,8 +1554,8 @@ static inline int early_lookup_bdev(const char *pathname, dev_t *dev) } #endif /* CONFIG_BLOCK */ -int freeze_bdev(struct block_device *bdev); -int thaw_bdev(struct block_device *bdev); +int bdev_freeze(struct block_device *bdev); +int bdev_thaw(struct block_device *bdev); struct io_comp_batch { struct request *req_list; diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index fc0d6f32c687..94baced5a1ad 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -142,9 +142,13 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_ITER, iter) #ifdef CONFIG_NET BPF_LINK_TYPE(BPF_LINK_TYPE_NETNS, netns) BPF_LINK_TYPE(BPF_LINK_TYPE_XDP, xdp) +BPF_LINK_TYPE(BPF_LINK_TYPE_NETFILTER, netfilter) +BPF_LINK_TYPE(BPF_LINK_TYPE_TCX, tcx) +BPF_LINK_TYPE(BPF_LINK_TYPE_NETKIT, netkit) #endif #ifdef CONFIG_PERF_EVENTS BPF_LINK_TYPE(BPF_LINK_TYPE_PERF_EVENT, perf) #endif BPF_LINK_TYPE(BPF_LINK_TYPE_KPROBE_MULTI, kprobe_multi) BPF_LINK_TYPE(BPF_LINK_TYPE_STRUCT_OPS, struct_ops) +BPF_LINK_TYPE(BPF_LINK_TYPE_UPROBE_MULTI, uprobe_multi) diff --git a/include/linux/cred.h b/include/linux/cred.h index af8d353a4b86..2976f534a7a3 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -109,14 +109,7 @@ static inline int groups_search(const struct group_info *group_info, kgid_t grp) * same context as task->real_cred. */ struct cred { - atomic_t usage; -#ifdef CONFIG_DEBUG_CREDENTIALS - atomic_t subscribers; /* number of processes subscribed */ - void *put_addr; - unsigned magic; -#define CRED_MAGIC 0x43736564 -#define CRED_MAGIC_DEAD 0x44656144 -#endif + atomic_long_t usage; kuid_t uid; /* real UID of the task */ kgid_t gid; /* real GID of the task */ kuid_t suid; /* saved UID of the task */ @@ -172,46 +165,6 @@ extern int cred_fscmp(const struct cred *, const struct cred *); extern void __init cred_init(void); extern int set_cred_ucounts(struct cred *); -/* - * check for validity of credentials - */ -#ifdef CONFIG_DEBUG_CREDENTIALS -extern void __noreturn __invalid_creds(const struct cred *, const char *, unsigned); -extern void __validate_process_creds(struct task_struct *, - const char *, unsigned); - -extern bool creds_are_invalid(const struct cred *cred); - -static inline void __validate_creds(const struct cred *cred, - const char *file, unsigned line) -{ - if (unlikely(creds_are_invalid(cred))) - __invalid_creds(cred, file, line); -} - -#define validate_creds(cred) \ -do { \ - __validate_creds((cred), __FILE__, __LINE__); \ -} while(0) - -#define validate_process_creds() \ -do { \ - __validate_process_creds(current, __FILE__, __LINE__); \ -} while(0) - -extern void validate_creds_for_do_exit(struct task_struct *); -#else -static inline void validate_creds(const struct cred *cred) -{ -} -static inline void validate_creds_for_do_exit(struct task_struct *tsk) -{ -} -static inline void validate_process_creds(void) -{ -} -#endif - static inline bool cap_ambient_invariant_ok(const struct cred *cred) { return cap_issubset(cred->cap_ambient, @@ -229,7 +182,7 @@ static inline bool cap_ambient_invariant_ok(const struct cred *cred) */ static inline struct cred *get_new_cred_many(struct cred *cred, int nr) { - atomic_add(nr, &cred->usage); + atomic_long_add(nr, &cred->usage); return cred; } @@ -264,7 +217,6 @@ static inline const struct cred *get_cred_many(const struct cred *cred, int nr) struct cred *nonconst_cred = (struct cred *) cred; if (!cred) return cred; - validate_creds(cred); nonconst_cred->non_rcu = 0; return get_new_cred_many(nonconst_cred, nr); } @@ -288,9 +240,8 @@ static inline const struct cred *get_cred_rcu(const struct cred *cred) struct cred *nonconst_cred = (struct cred *) cred; if (!cred) return NULL; - if (!atomic_inc_not_zero(&nonconst_cred->usage)) + if (!atomic_long_inc_not_zero(&nonconst_cred->usage)) return NULL; - validate_creds(cred); nonconst_cred->non_rcu = 0; return cred; } @@ -312,8 +263,7 @@ static inline void put_cred_many(const struct cred *_cred, int nr) struct cred *cred = (struct cred *) _cred; if (cred) { - validate_creds(cred); - if (atomic_sub_and_test(nr, &cred->usage)) + if (atomic_long_sub_and_test(nr, &cred->usage)) __put_cred(cred); } } diff --git a/include/linux/damon.h b/include/linux/damon.h index ab2f17d9926b..e00ddf1ed39c 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -559,6 +559,8 @@ struct damon_ctx { * update */ unsigned long next_ops_update_sis; + /* for waiting until the execution of the kdamond_fn is started */ + struct completion kdamond_started; /* public: */ struct task_struct *kdamond; diff --git a/include/linux/device.h b/include/linux/device.h index d7a72a8749ea..6c83294395ac 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1007,6 +1007,8 @@ static inline void device_unlock(struct device *dev) mutex_unlock(&dev->mutex); } +DEFINE_GUARD(device, struct device *, device_lock(_T), device_unlock(_T)) + static inline void device_lock_assert(struct device *dev) { lockdep_assert_held(&dev->mutex); diff --git a/include/linux/edac.h b/include/linux/edac.h index fa4bda2a70f6..1174beb94ab6 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -187,6 +187,7 @@ static inline char *mc_event_error_type(const unsigned int err_type) * @MEM_NVDIMM: Non-volatile RAM * @MEM_WIO2: Wide I/O 2. * @MEM_HBM2: High bandwidth Memory Gen 2. + * @MEM_HBM3: High bandwidth Memory Gen 3. */ enum mem_type { MEM_EMPTY = 0, @@ -218,6 +219,7 @@ enum mem_type { MEM_NVDIMM, MEM_WIO2, MEM_HBM2, + MEM_HBM3, }; #define MEM_FLAG_EMPTY BIT(MEM_EMPTY) @@ -248,6 +250,7 @@ enum mem_type { #define MEM_FLAG_NVDIMM BIT(MEM_NVDIMM) #define MEM_FLAG_WIO2 BIT(MEM_WIO2) #define MEM_FLAG_HBM2 BIT(MEM_HBM2) +#define MEM_FLAG_HBM3 BIT(MEM_HBM3) /** * enum edac_type - Error Detection and Correction capabilities and mode diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h index b9d83652c097..e32bee4345fb 100644 --- a/include/linux/eventfd.h +++ b/include/linux/eventfd.h @@ -35,8 +35,7 @@ void eventfd_ctx_put(struct eventfd_ctx *ctx); struct file *eventfd_fget(int fd); struct eventfd_ctx *eventfd_ctx_fdget(int fd); struct eventfd_ctx *eventfd_ctx_fileget(struct file *file); -__u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n); -__u64 eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, __poll_t mask); +void eventfd_signal_mask(struct eventfd_ctx *ctx, __poll_t mask); int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *wait, __u64 *cnt); void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt); @@ -58,15 +57,8 @@ static inline struct eventfd_ctx *eventfd_ctx_fdget(int fd) return ERR_PTR(-ENOSYS); } -static inline int eventfd_signal(struct eventfd_ctx *ctx, __u64 n) +static inline void eventfd_signal_mask(struct eventfd_ctx *ctx, __poll_t mask) { - return -ENOSYS; -} - -static inline int eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, - unsigned mask) -{ - return -ENOSYS; } static inline void eventfd_ctx_put(struct eventfd_ctx *ctx) @@ -92,5 +84,10 @@ static inline void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt) #endif +static inline void eventfd_signal(struct eventfd_ctx *ctx) +{ + eventfd_signal_mask(ctx, 0); +} + #endif /* _LINUX_EVENTFD_H */ diff --git a/include/linux/export-internal.h b/include/linux/export-internal.h index 69501e0ec239..d445705ac13c 100644 --- a/include/linux/export-internal.h +++ b/include/linux/export-internal.h @@ -16,10 +16,13 @@ * and eliminates the need for absolute relocations that require runtime * processing on relocatable kernels. */ +#define __KSYM_ALIGN ".balign 4" #define __KSYM_REF(sym) ".long " #sym "- ." #elif defined(CONFIG_64BIT) +#define __KSYM_ALIGN ".balign 8" #define __KSYM_REF(sym) ".quad " #sym #else +#define __KSYM_ALIGN ".balign 4" #define __KSYM_REF(sym) ".long " #sym #endif @@ -42,7 +45,7 @@ " .asciz \"" ns "\"" "\n" \ " .previous" "\n" \ " .section \"___ksymtab" sec "+" #name "\", \"a\"" "\n" \ - " .balign 4" "\n" \ + __KSYM_ALIGN "\n" \ "__ksymtab_" #name ":" "\n" \ __KSYM_REF(sym) "\n" \ __KSYM_REF(__kstrtab_ ##name) "\n" \ @@ -61,6 +64,7 @@ #define SYMBOL_CRC(sym, crc, sec) \ asm(".section \"___kcrctab" sec "+" #sym "\",\"a\"" "\n" \ + ".balign 4" "\n" \ "__crc_" #sym ":" "\n" \ ".long " #crc "\n" \ ".previous" "\n") diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h index bc4c3287a65e..78c8326d74ae 100644 --- a/include/linux/fdtable.h +++ b/include/linux/fdtable.h @@ -83,12 +83,17 @@ struct dentry; static inline struct file *files_lookup_fd_raw(struct files_struct *files, unsigned int fd) { struct fdtable *fdt = rcu_dereference_raw(files->fdt); - - if (fd < fdt->max_fds) { - fd = array_index_nospec(fd, fdt->max_fds); - return rcu_dereference_raw(fdt->fd[fd]); - } - return NULL; + unsigned long mask = array_index_mask_nospec(fd, fdt->max_fds); + struct file *needs_masking; + + /* + * 'mask' is zero for an out-of-bounds fd, all ones for ok. + * 'fd&mask' is 'fd' for ok, or 0 for out of bounds. + * + * Accessing fdt->fd[0] is ok, but needs masking of the result. + */ + needs_masking = rcu_dereference_raw(fdt->fd[fd&mask]); + return (struct file *)(mask & (unsigned long)needs_masking); } static inline struct file *files_lookup_fd_locked(struct files_struct *files, unsigned int fd) @@ -114,7 +119,7 @@ int iterate_fd(struct files_struct *, unsigned, extern int close_fd(unsigned int fd); extern int __close_range(unsigned int fd, unsigned int max_fd, unsigned int flags); -extern struct file *close_fd_get_file(unsigned int fd); +extern struct file *file_close_fd(unsigned int fd); extern int unshare_fd(unsigned long unshare_flags, unsigned int max_fds, struct files_struct **new_fdp); diff --git a/include/linux/file.h b/include/linux/file.h index 6e9099d29343..6834a29338c4 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -96,18 +96,8 @@ DEFINE_CLASS(get_unused_fd, int, if (_T >= 0) put_unused_fd(_T), extern void fd_install(unsigned int fd, struct file *file); -extern int __receive_fd(struct file *file, int __user *ufd, - unsigned int o_flags); +int receive_fd(struct file *file, int __user *ufd, unsigned int o_flags); -extern int receive_fd(struct file *file, unsigned int o_flags); - -static inline int receive_fd_user(struct file *file, int __user *ufd, - unsigned int o_flags) -{ - if (ufd == NULL) - return -EFAULT; - return __receive_fd(file, ufd, o_flags); -} int receive_fd_replace(int new_fd, struct file *file, unsigned int o_flags); extern void flush_delayed_fput(void); diff --git a/include/linux/fs.h b/include/linux/fs.h index 98b7a7a8c42e..cdbf43a8ea88 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -463,9 +463,9 @@ extern const struct address_space_operations empty_aops; * @a_ops: Methods. * @flags: Error bits and flags (AS_*). * @wb_err: The most recent error which has occurred. - * @private_lock: For use by the owner of the address_space. - * @private_list: For use by the owner of the address_space. - * @private_data: For use by the owner of the address_space. + * @i_private_lock: For use by the owner of the address_space. + * @i_private_list: For use by the owner of the address_space. + * @i_private_data: For use by the owner of the address_space. */ struct address_space { struct inode *host; @@ -484,9 +484,9 @@ struct address_space { unsigned long flags; struct rw_semaphore i_mmap_rwsem; errseq_t wb_err; - spinlock_t private_lock; - struct list_head private_list; - void *private_data; + spinlock_t i_private_lock; + struct list_head i_private_list; + void * i_private_data; } __attribute__((aligned(sizeof(long)))) __randomize_layout; /* * On most architectures that alignment is already the case; but @@ -991,8 +991,10 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index) */ struct file { union { + /* fput() uses task work when closing and freeing file (default). */ + struct callback_head f_task_work; + /* fput() must use workqueue (most kernel threads). */ struct llist_node f_llist; - struct rcu_head f_rcuhead; unsigned int f_iocb_flags; }; @@ -1185,7 +1187,8 @@ enum { struct sb_writers { unsigned short frozen; /* Is sb frozen? */ - unsigned short freeze_holders; /* Who froze fs? */ + int freeze_kcount; /* How many kernel freeze requests? */ + int freeze_ucount; /* How many userspace freeze requests? */ struct percpu_rw_semaphore rw_sem[SB_FREEZE_LEVELS]; }; @@ -1645,9 +1648,70 @@ static inline bool __sb_start_write_trylock(struct super_block *sb, int level) #define __sb_writers_release(sb, lev) \ percpu_rwsem_release(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_) +/** + * __sb_write_started - check if sb freeze level is held + * @sb: the super we write to + * @level: the freeze level + * + * * > 0 - sb freeze level is held + * * 0 - sb freeze level is not held + * * < 0 - !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN + */ +static inline int __sb_write_started(const struct super_block *sb, int level) +{ + return lockdep_is_held_type(sb->s_writers.rw_sem + level - 1, 1); +} + +/** + * sb_write_started - check if SB_FREEZE_WRITE is held + * @sb: the super we write to + * + * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. + */ static inline bool sb_write_started(const struct super_block *sb) { - return lockdep_is_held_type(sb->s_writers.rw_sem + SB_FREEZE_WRITE - 1, 1); + return __sb_write_started(sb, SB_FREEZE_WRITE); +} + +/** + * sb_write_not_started - check if SB_FREEZE_WRITE is not held + * @sb: the super we write to + * + * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. + */ +static inline bool sb_write_not_started(const struct super_block *sb) +{ + return __sb_write_started(sb, SB_FREEZE_WRITE) <= 0; +} + +/** + * file_write_started - check if SB_FREEZE_WRITE is held + * @file: the file we write to + * + * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. + * May be false positive with !S_ISREG, because file_start_write() has + * no effect on !S_ISREG. + */ +static inline bool file_write_started(const struct file *file) +{ + if (!S_ISREG(file_inode(file)->i_mode)) + return true; + return sb_write_started(file_inode(file)->i_sb); +} + +/** + * file_write_not_started - check if SB_FREEZE_WRITE is not held + * @file: the file we write to + * + * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. + * May be false positive with !S_ISREG, because file_start_write() has + * no effect on !S_ISREG. + */ +static inline bool file_write_not_started(const struct file *file) +{ + if (!S_ISREG(file_inode(file)->i_mode)) + return true; + return sb_write_not_started(file_inode(file)->i_sb); } /** @@ -2029,9 +2093,6 @@ extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); -extern ssize_t generic_copy_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - size_t len, unsigned int flags); int __generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *len, unsigned int remap_flags, @@ -2051,9 +2112,24 @@ extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, struct file *dst_file, loff_t dst_pos, loff_t len, unsigned int remap_flags); +/** + * enum freeze_holder - holder of the freeze + * @FREEZE_HOLDER_KERNEL: kernel wants to freeze or thaw filesystem + * @FREEZE_HOLDER_USERSPACE: userspace wants to freeze or thaw filesystem + * @FREEZE_MAY_NEST: whether nesting freeze and thaw requests is allowed + * + * Indicate who the owner of the freeze or thaw request is and whether + * the freeze needs to be exclusive or can nest. + * Without @FREEZE_MAY_NEST, multiple freeze and thaw requests from the + * same holder aren't allowed. It is however allowed to hold a single + * @FREEZE_HOLDER_USERSPACE and a single @FREEZE_HOLDER_KERNEL freeze at + * the same time. This is relied upon by some filesystems during online + * repair or similar. + */ enum freeze_holder { FREEZE_HOLDER_KERNEL = (1U << 0), FREEZE_HOLDER_USERSPACE = (1U << 1), + FREEZE_MAY_NEST = (1U << 2), }; struct super_operations { @@ -2517,26 +2593,31 @@ struct file *dentry_open(const struct path *path, int flags, const struct cred *creds); struct file *dentry_create(const struct path *path, int flags, umode_t mode, const struct cred *cred); -struct file *backing_file_open(const struct path *user_path, int flags, - const struct path *real_path, - const struct cred *cred); struct path *backing_file_user_path(struct file *f); /* - * file_user_path - get the path to display for memory mapped file - * * When mmapping a file on a stackable filesystem (e.g., overlayfs), the file * stored in ->vm_file is a backing file whose f_inode is on the underlying - * filesystem. When the mapped file path is displayed to user (e.g. via - * /proc/<pid>/maps), this helper should be used to get the path to display - * to the user, which is the path of the fd that user has requested to map. + * filesystem. When the mapped file path and inode number are displayed to + * user (e.g. via /proc/<pid>/maps), these helpers should be used to get the + * path and inode number to display to the user, which is the path of the fd + * that user has requested to map and the inode number that would be returned + * by fstat() on that same fd. */ +/* Get the path to display in /proc/<pid>/maps */ static inline const struct path *file_user_path(struct file *f) { if (unlikely(f->f_mode & FMODE_BACKING)) return backing_file_user_path(f); return &f->f_path; } +/* Get the inode whose inode number to display in /proc/<pid>/maps */ +static inline const struct inode *file_user_inode(struct file *f) +{ + if (unlikely(f->f_mode & FMODE_BACKING)) + return d_inode(backing_file_user_path(f)->dentry); + return file_inode(f); +} static inline struct file *file_clone_open(struct file *file) { @@ -2991,8 +3072,6 @@ ssize_t copy_splice_read(struct file *in, loff_t *ppos, size_t len, unsigned int flags); extern ssize_t iter_file_splice_write(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); -extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, - loff_t *opos, size_t len, unsigned int flags); extern void @@ -3121,7 +3200,6 @@ extern int vfs_readlink(struct dentry *, char __user *, int); extern struct file_system_type *get_filesystem(struct file_system_type *fs); extern void put_filesystem(struct file_system_type *fs); extern struct file_system_type *get_fs_type(const char *name); -extern struct super_block *get_active_super(struct block_device *bdev); extern void drop_super(struct super_block *sb); extern void drop_super_exclusive(struct super_block *sb); extern void iterate_supers(void (*)(struct super_block *, void *), void *); diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index bcb6609b54b3..11e6434b8e71 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -100,29 +100,49 @@ static inline int fsnotify_file(struct file *file, __u32 mask) return fsnotify_parent(path->dentry, mask, path, FSNOTIFY_EVENT_PATH); } -/* Simple call site for access decisions */ -static inline int fsnotify_perm(struct file *file, int mask) +/* + * fsnotify_file_area_perm - permission hook before access to file range + */ +static inline int fsnotify_file_area_perm(struct file *file, int perm_mask, + const loff_t *ppos, size_t count) { - int ret; - __u32 fsnotify_mask = 0; + __u32 fsnotify_mask = FS_ACCESS_PERM; + + /* + * filesystem may be modified in the context of permission events + * (e.g. by HSM filling a file on access), so sb freeze protection + * must not be held. + */ + lockdep_assert_once(file_write_not_started(file)); - if (!(mask & (MAY_READ | MAY_OPEN))) + if (!(perm_mask & MAY_READ)) return 0; - if (mask & MAY_OPEN) { - fsnotify_mask = FS_OPEN_PERM; + return fsnotify_file(file, fsnotify_mask); +} + +/* + * fsnotify_file_perm - permission hook before file access + */ +static inline int fsnotify_file_perm(struct file *file, int perm_mask) +{ + return fsnotify_file_area_perm(file, perm_mask, NULL, 0); +} - if (file->f_flags & __FMODE_EXEC) { - ret = fsnotify_file(file, FS_OPEN_EXEC_PERM); +/* + * fsnotify_open_perm - permission hook before file open + */ +static inline int fsnotify_open_perm(struct file *file) +{ + int ret; - if (ret) - return ret; - } - } else if (mask & MAY_READ) { - fsnotify_mask = FS_ACCESS_PERM; + if (file->f_flags & __FMODE_EXEC) { + ret = fsnotify_file(file, FS_OPEN_EXEC_PERM); + if (ret) + return ret; } - return fsnotify_file(file, fsnotify_mask); + return fsnotify_file(file, FS_OPEN_PERM); } /* diff --git a/include/linux/hid-sensor-ids.h b/include/linux/hid-sensor-ids.h index 6730ee900ee1..13b1e65fbdcc 100644 --- a/include/linux/hid-sensor-ids.h +++ b/include/linux/hid-sensor-ids.h @@ -21,10 +21,6 @@ #define HID_USAGE_SENSOR_ALS 0x200041 #define HID_USAGE_SENSOR_DATA_LIGHT 0x2004d0 #define HID_USAGE_SENSOR_LIGHT_ILLUM 0x2004d1 -#define HID_USAGE_SENSOR_LIGHT_COLOR_TEMPERATURE 0x2004d2 -#define HID_USAGE_SENSOR_LIGHT_CHROMATICITY 0x2004d3 -#define HID_USAGE_SENSOR_LIGHT_CHROMATICITY_X 0x2004d4 -#define HID_USAGE_SENSOR_LIGHT_CHROMATICITY_Y 0x2004d5 /* PROX (200011) */ #define HID_USAGE_SENSOR_PROX 0x200011 diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index c2ac9e9e7ee9..2b5e500bf093 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -4447,7 +4447,8 @@ ieee80211_is_protected_dual_of_public_action(struct sk_buff *skb) action != WLAN_PUB_ACTION_LOC_TRACK_NOTI && action != WLAN_PUB_ACTION_FTM_REQUEST && action != WLAN_PUB_ACTION_FTM_RESPONSE && - action != WLAN_PUB_ACTION_FILS_DISCOVERY; + action != WLAN_PUB_ACTION_FILS_DISCOVERY && + action != WLAN_PUB_ACTION_VENDOR_SPECIFIC; } /** diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 805bb635cdf5..239a4f68801b 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -434,6 +434,7 @@ enum { /* keep async read/write and isreg together and in order */ REQ_F_SUPPORT_NOWAIT_BIT, REQ_F_ISREG_BIT, + REQ_F_POLL_NO_LAZY_BIT, /* not a real bit, just to check we're not overflowing the space */ __REQ_F_LAST_BIT, @@ -501,6 +502,8 @@ enum { REQ_F_CLEAR_POLLIN = BIT(REQ_F_CLEAR_POLLIN_BIT), /* hashed into ->cancel_hash_locked, protected by ->uring_lock */ REQ_F_HASH_LOCKED = BIT(REQ_F_HASH_LOCKED_BIT), + /* don't use lazy poll wake for this request */ + REQ_F_POLL_NO_LAZY = BIT(REQ_F_POLL_NO_LAZY_BIT), }; typedef void (*io_req_tw_func_t)(struct io_kiocb *req, struct io_tw_state *ts); diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 6dcbb4eb80fb..beb30719ee16 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1374,6 +1374,9 @@ JBD2_FEATURE_INCOMPAT_FUNCS(csum2, CSUM_V2) JBD2_FEATURE_INCOMPAT_FUNCS(csum3, CSUM_V3) JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit, FAST_COMMIT) +/* Journal high priority write IO operation flags */ +#define JBD2_JOURNAL_REQ_FLAGS (REQ_META | REQ_SYNC | REQ_IDLE) + /* * Journal flag definitions */ diff --git a/include/linux/key-type.h b/include/linux/key-type.h index 7d985a1dfe4a..5caf3ce82373 100644 --- a/include/linux/key-type.h +++ b/include/linux/key-type.h @@ -73,6 +73,7 @@ struct key_type { unsigned int flags; #define KEY_TYPE_NET_DOMAIN 0x00000001 /* Keys of this type have a net namespace domain */ +#define KEY_TYPE_INSTANT_REAP 0x00000002 /* Keys of this type don't have a delay after expiring */ /* vet a description */ int (*vet_description)(const char *description); diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 6f3631425f38..3f7b664d625b 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -621,7 +621,7 @@ struct mlx5_ifc_fte_match_set_misc_bits { u8 reserved_at_140[0x8]; u8 bth_dst_qp[0x18]; - u8 reserved_at_160[0x20]; + u8 inner_esp_spi[0x20]; u8 outer_esp_spi[0x20]; u8 reserved_at_1a0[0x60]; }; @@ -12001,6 +12001,13 @@ enum { MLX5_IPSEC_ASO_INC_SN = 0x2, }; +enum { + MLX5_IPSEC_ASO_REPLAY_WIN_32BIT = 0x0, + MLX5_IPSEC_ASO_REPLAY_WIN_64BIT = 0x1, + MLX5_IPSEC_ASO_REPLAY_WIN_128BIT = 0x2, + MLX5_IPSEC_ASO_REPLAY_WIN_256BIT = 0x3, +}; + struct mlx5_ifc_ipsec_aso_bits { u8 valid[0x1]; u8 reserved_at_201[0x1]; diff --git a/include/linux/mm.h b/include/linux/mm.h index 418d26608ece..da5219b48d52 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -886,8 +886,8 @@ static inline bool vma_is_anonymous(struct vm_area_struct *vma) */ static inline bool vma_is_initial_heap(const struct vm_area_struct *vma) { - return vma->vm_start <= vma->vm_mm->brk && - vma->vm_end >= vma->vm_mm->start_brk; + return vma->vm_start < vma->vm_mm->brk && + vma->vm_end > vma->vm_mm->start_brk; } /* @@ -901,8 +901,8 @@ static inline bool vma_is_initial_stack(const struct vm_area_struct *vma) * its "stack". It's not even well-defined for programs written * languages like Go. */ - return vma->vm_start <= vma->vm_mm->start_stack && - vma->vm_end >= vma->vm_mm->start_stack; + return vma->vm_start <= vma->vm_mm->start_stack && + vma->vm_end >= vma->vm_mm->start_stack; } static inline bool vma_is_temporary_stack(struct vm_area_struct *vma) diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 9ae7def16cb2..f4fe593c1400 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -232,22 +232,27 @@ static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, if (folio_test_unevictable(folio) || !lrugen->enabled) return false; /* - * There are three common cases for this page: - * 1. If it's hot, e.g., freshly faulted in or previously hot and - * migrated, add it to the youngest generation. - * 2. If it's cold but can't be evicted immediately, i.e., an anon page - * not in swapcache or a dirty page pending writeback, add it to the - * second oldest generation. - * 3. Everything else (clean, cold) is added to the oldest generation. + * There are four common cases for this page: + * 1. If it's hot, i.e., freshly faulted in, add it to the youngest + * generation, and it's protected over the rest below. + * 2. If it can't be evicted immediately, i.e., a dirty page pending + * writeback, add it to the second youngest generation. + * 3. If it should be evicted first, e.g., cold and clean from + * folio_rotate_reclaimable(), add it to the oldest generation. + * 4. Everything else falls between 2 & 3 above and is added to the + * second oldest generation if it's considered inactive, or the + * oldest generation otherwise. See lru_gen_is_active(). */ if (folio_test_active(folio)) seq = lrugen->max_seq; else if ((type == LRU_GEN_ANON && !folio_test_swapcache(folio)) || (folio_test_reclaim(folio) && (folio_test_dirty(folio) || folio_test_writeback(folio)))) - seq = lrugen->min_seq[type] + 1; - else + seq = lrugen->max_seq - 1; + else if (reclaiming || lrugen->min_seq[type] + MIN_NR_GENS >= lrugen->max_seq) seq = lrugen->min_seq[type]; + else + seq = lrugen->min_seq[type] + 1; gen = lru_gen_from_seq(seq); flags = (gen + 1UL) << LRU_GEN_PGOFF; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 3c25226beeed..9db36e197712 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -505,33 +505,37 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw); * the old generation, is incremented when all its bins become empty. * * There are four operations: - * 1. MEMCG_LRU_HEAD, which moves an memcg to the head of a random bin in its + * 1. MEMCG_LRU_HEAD, which moves a memcg to the head of a random bin in its * current generation (old or young) and updates its "seg" to "head"; - * 2. MEMCG_LRU_TAIL, which moves an memcg to the tail of a random bin in its + * 2. MEMCG_LRU_TAIL, which moves a memcg to the tail of a random bin in its * current generation (old or young) and updates its "seg" to "tail"; - * 3. MEMCG_LRU_OLD, which moves an memcg to the head of a random bin in the old + * 3. MEMCG_LRU_OLD, which moves a memcg to the head of a random bin in the old * generation, updates its "gen" to "old" and resets its "seg" to "default"; - * 4. MEMCG_LRU_YOUNG, which moves an memcg to the tail of a random bin in the + * 4. MEMCG_LRU_YOUNG, which moves a memcg to the tail of a random bin in the * young generation, updates its "gen" to "young" and resets its "seg" to * "default". * * The events that trigger the above operations are: * 1. Exceeding the soft limit, which triggers MEMCG_LRU_HEAD; - * 2. The first attempt to reclaim an memcg below low, which triggers + * 2. The first attempt to reclaim a memcg below low, which triggers * MEMCG_LRU_TAIL; - * 3. The first attempt to reclaim an memcg below reclaimable size threshold, - * which triggers MEMCG_LRU_TAIL; - * 4. The second attempt to reclaim an memcg below reclaimable size threshold, - * which triggers MEMCG_LRU_YOUNG; - * 5. Attempting to reclaim an memcg below min, which triggers MEMCG_LRU_YOUNG; + * 3. The first attempt to reclaim a memcg offlined or below reclaimable size + * threshold, which triggers MEMCG_LRU_TAIL; + * 4. The second attempt to reclaim a memcg offlined or below reclaimable size + * threshold, which triggers MEMCG_LRU_YOUNG; + * 5. Attempting to reclaim a memcg below min, which triggers MEMCG_LRU_YOUNG; * 6. Finishing the aging on the eviction path, which triggers MEMCG_LRU_YOUNG; - * 7. Offlining an memcg, which triggers MEMCG_LRU_OLD. + * 7. Offlining a memcg, which triggers MEMCG_LRU_OLD. * - * Note that memcg LRU only applies to global reclaim, and the round-robin - * incrementing of their max_seq counters ensures the eventual fairness to all - * eligible memcgs. For memcg reclaim, it still relies on mem_cgroup_iter(). + * Notes: + * 1. Memcg LRU only applies to global reclaim, and the round-robin incrementing + * of their max_seq counters ensures the eventual fairness to all eligible + * memcgs. For memcg reclaim, it still relies on mem_cgroup_iter(). + * 2. There are only two valid generations: old (seq) and young (seq+1). + * MEMCG_NR_GENS is set to three so that when reading the generation counter + * locklessly, a stale value (seq-1) does not wraparound to young. */ -#define MEMCG_NR_GENS 2 +#define MEMCG_NR_GENS 3 #define MEMCG_NR_BINS 8 struct lru_gen_memcg { diff --git a/include/linux/mnt_idmapping.h b/include/linux/mnt_idmapping.h index b8da2db4ecd2..cd4d5c8781f5 100644 --- a/include/linux/mnt_idmapping.h +++ b/include/linux/mnt_idmapping.h @@ -244,7 +244,4 @@ static inline kgid_t mapped_fsgid(struct mnt_idmap *idmap, return from_vfsgid(idmap, fs_userns, VFSGIDT_INIT(current_fsgid())); } -bool check_fsmapping(const struct mnt_idmap *idmap, - const struct super_block *sb); - #endif /* _LINUX_MNT_IDMAPPING_H */ diff --git a/include/linux/mount.h b/include/linux/mount.h index ac3dd2876197..c34c18b4e8f3 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -50,8 +50,7 @@ struct path; #define MNT_ATIME_MASK (MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME ) #define MNT_INTERNAL_FLAGS (MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL | \ - MNT_DOOMED | MNT_SYNC_UMOUNT | MNT_MARKED | \ - MNT_CURSOR) + MNT_DOOMED | MNT_SYNC_UMOUNT | MNT_MARKED | MNT_ONRB) #define MNT_INTERNAL 0x4000 @@ -65,7 +64,7 @@ struct path; #define MNT_SYNC_UMOUNT 0x2000000 #define MNT_MARKED 0x4000000 #define MNT_UMOUNT 0x8000000 -#define MNT_CURSOR 0x10000000 +#define MNT_ONRB 0x10000000 struct vfsmount { struct dentry *mnt_root; /* root of the mounted tree */ diff --git a/include/linux/osq_lock.h b/include/linux/osq_lock.h index 5581dbd3bd34..ea8fb31379e3 100644 --- a/include/linux/osq_lock.h +++ b/include/linux/osq_lock.h @@ -6,11 +6,6 @@ * An MCS like lock especially tailored for optimistic spinning for sleeping * lock implementations (mutex, rwsem, etc). */ -struct optimistic_spin_node { - struct optimistic_spin_node *next, *prev; - int locked; /* 1 if lock acquired */ - int cpu; /* encoded CPU # + 1 value */ -}; struct optimistic_spin_queue { /* diff --git a/include/linux/pci.h b/include/linux/pci.h index 60ca768bc867..dea043bc1e38 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1829,6 +1829,7 @@ extern bool pcie_ports_native; int pci_disable_link_state(struct pci_dev *pdev, int state); int pci_disable_link_state_locked(struct pci_dev *pdev, int state); int pci_enable_link_state(struct pci_dev *pdev, int state); +int pci_enable_link_state_locked(struct pci_dev *pdev, int state); void pcie_no_aspm(void); bool pcie_aspm_support_enabled(void); bool pcie_aspm_enabled(struct pci_dev *pdev); @@ -1839,6 +1840,8 @@ static inline int pci_disable_link_state_locked(struct pci_dev *pdev, int state) { return 0; } static inline int pci_enable_link_state(struct pci_dev *pdev, int state) { return 0; } +static inline int pci_enable_link_state_locked(struct pci_dev *pdev, int state) +{ return 0; } static inline void pcie_no_aspm(void) { } static inline bool pcie_aspm_support_enabled(void) { return false; } static inline bool pcie_aspm_enabled(struct pci_dev *pdev) { return false; } diff --git a/include/linux/phy.h b/include/linux/phy.h index 3cc52826f18e..bd285950972c 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -568,7 +568,6 @@ struct macsec_ops; * - Bits [31:24] are reserved for defining generic * PHY driver behavior. * @irq: IRQ number of the PHY's interrupt (-1 if none) - * @phy_timer: The timer for handling the state machine * @phylink: Pointer to phylink instance for this PHY * @sfp_bus_attached: Flag indicating whether the SFP bus has been attached * @sfp_bus: SFP bus attached to this PHY's fiber port diff --git a/include/linux/splice.h b/include/linux/splice.h index 6c461573434d..9dec4861d09f 100644 --- a/include/linux/splice.h +++ b/include/linux/splice.h @@ -68,28 +68,37 @@ typedef int (splice_actor)(struct pipe_inode_info *, struct pipe_buffer *, typedef int (splice_direct_actor)(struct pipe_inode_info *, struct splice_desc *); -extern ssize_t splice_from_pipe(struct pipe_inode_info *, struct file *, - loff_t *, size_t, unsigned int, - splice_actor *); -extern ssize_t __splice_from_pipe(struct pipe_inode_info *, - struct splice_desc *, splice_actor *); -extern ssize_t splice_to_pipe(struct pipe_inode_info *, - struct splice_pipe_desc *); -extern ssize_t add_to_pipe(struct pipe_inode_info *, - struct pipe_buffer *); -long vfs_splice_read(struct file *in, loff_t *ppos, - struct pipe_inode_info *pipe, size_t len, - unsigned int flags); -extern ssize_t splice_direct_to_actor(struct file *, struct splice_desc *, - splice_direct_actor *); -extern long do_splice(struct file *in, loff_t *off_in, - struct file *out, loff_t *off_out, - size_t len, unsigned int flags); +ssize_t splice_from_pipe(struct pipe_inode_info *pipe, struct file *out, + loff_t *ppos, size_t len, unsigned int flags, + splice_actor *actor); +ssize_t __splice_from_pipe(struct pipe_inode_info *pipe, + struct splice_desc *sd, splice_actor *actor); +ssize_t splice_to_pipe(struct pipe_inode_info *pipe, + struct splice_pipe_desc *spd); +ssize_t add_to_pipe(struct pipe_inode_info *pipe, struct pipe_buffer *buf); +ssize_t vfs_splice_read(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, + unsigned int flags); +ssize_t splice_direct_to_actor(struct file *file, struct splice_desc *sd, + splice_direct_actor *actor); +ssize_t do_splice(struct file *in, loff_t *off_in, struct file *out, + loff_t *off_out, size_t len, unsigned int flags); +ssize_t do_splice_direct(struct file *in, loff_t *ppos, struct file *out, + loff_t *opos, size_t len, unsigned int flags); +ssize_t splice_file_range(struct file *in, loff_t *ppos, struct file *out, + loff_t *opos, size_t len); -extern long do_tee(struct file *in, struct file *out, size_t len, - unsigned int flags); -extern ssize_t splice_to_socket(struct pipe_inode_info *pipe, struct file *out, - loff_t *ppos, size_t len, unsigned int flags); +static inline long splice_copy_file_range(struct file *in, loff_t pos_in, + struct file *out, loff_t pos_out, + size_t len) +{ + return splice_file_range(in, &pos_in, out, &pos_out, len); +} + +ssize_t do_tee(struct file *in, struct file *out, size_t len, + unsigned int flags); +ssize_t splice_to_socket(struct pipe_inode_info *pipe, struct file *out, + loff_t *ppos, size_t len, unsigned int flags); /* * for dynamic pipe sizing diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index fd9d12de7e92..2d6d3e76e3f7 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -74,6 +74,8 @@ struct landlock_ruleset_attr; enum landlock_rule_type; struct cachestat_range; struct cachestat; +struct statmount; +struct mnt_id_req; #include <linux/types.h> #include <linux/aio_abi.h> @@ -407,6 +409,12 @@ asmlinkage long sys_statfs64(const char __user *path, size_t sz, asmlinkage long sys_fstatfs(unsigned int fd, struct statfs __user *buf); asmlinkage long sys_fstatfs64(unsigned int fd, size_t sz, struct statfs64 __user *buf); +asmlinkage long sys_statmount(const struct mnt_id_req __user *req, + struct statmount __user *buf, size_t bufsize, + unsigned int flags); +asmlinkage long sys_listmount(const struct mnt_id_req __user *req, + u64 __user *buf, size_t bufsize, + unsigned int flags); asmlinkage long sys_truncate(const char __user *path, long length); asmlinkage long sys_ftruncate(unsigned int fd, unsigned long length); #if BITS_PER_LONG == 32 diff --git a/include/linux/uidgid.h b/include/linux/uidgid.h index b0542cd11aeb..415a7ca2b882 100644 --- a/include/linux/uidgid.h +++ b/include/linux/uidgid.h @@ -17,6 +17,7 @@ struct user_namespace; extern struct user_namespace init_user_ns; +struct uid_gid_map; typedef struct { uid_t val; @@ -138,6 +139,9 @@ static inline bool kgid_has_mapping(struct user_namespace *ns, kgid_t gid) return from_kgid(ns, gid) != (gid_t) -1; } +u32 map_id_down(struct uid_gid_map *map, u32 id); +u32 map_id_up(struct uid_gid_map *map, u32 id); + #else static inline kuid_t make_kuid(struct user_namespace *from, uid_t uid) @@ -186,6 +190,15 @@ static inline bool kgid_has_mapping(struct user_namespace *ns, kgid_t gid) return gid_valid(gid); } +static inline u32 map_id_down(struct uid_gid_map *map, u32 id) +{ + return id; +} + +static inline u32 map_id_up(struct uid_gid_map *map, u32 id) +{ + return id; +} #endif /* CONFIG_USER_NS */ #endif /* _LINUX_UIDGID_H */ diff --git a/include/linux/uio.h b/include/linux/uio.h index b6214cbf2a43..bea9c89922d9 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -347,8 +347,6 @@ ssize_t import_iovec(int type, const struct iovec __user *uvec, ssize_t __import_iovec(int type, const struct iovec __user *uvec, unsigned nr_segs, unsigned fast_segs, struct iovec **iovp, struct iov_iter *i, bool compat); -int import_single_range(int type, void __user *buf, size_t len, - struct iovec *iov, struct iov_iter *i); int import_ubuf(int type, void __user *buf, size_t len, struct iov_iter *i); static inline void iov_iter_ubuf(struct iov_iter *i, unsigned int direction, diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 083387c00f0c..6d0a14f7019d 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -193,7 +193,6 @@ void inode_io_list_del(struct inode *inode); /* writeback.h requires fs.h; it, too, is not included from here. */ static inline void wait_on_inode(struct inode *inode) { - might_sleep(); wait_on_bit(&inode->i_state, __I_NEW, TASK_UNINTERRUPTIBLE); } diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 82da55101b5a..61ebe723ee4d 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -31,17 +31,22 @@ struct prefix_info { __u8 length; __u8 prefix_len; + union __packed { + __u8 flags; + struct __packed { #if defined(__BIG_ENDIAN_BITFIELD) - __u8 onlink : 1, + __u8 onlink : 1, autoconf : 1, reserved : 6; #elif defined(__LITTLE_ENDIAN_BITFIELD) - __u8 reserved : 6, + __u8 reserved : 6, autoconf : 1, onlink : 1; #else #error "Please fix <asm/byteorder.h>" #endif + }; + }; __be32 valid; __be32 prefered; __be32 reserved2; @@ -49,6 +54,9 @@ struct prefix_info { struct in6_addr prefix; }; +/* rfc4861 4.6.2: IPv6 PIO is 32 bytes in size */ +static_assert(sizeof(struct prefix_info) == 32); + #include <linux/ipv6.h> #include <linux/netdevice.h> #include <net/if_inet6.h> diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 20988623c5cc..a3a1ea2696a8 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -189,6 +189,7 @@ struct blocked_key { struct smp_csrk { bdaddr_t bdaddr; u8 bdaddr_type; + u8 link_type; u8 type; u8 val[16]; }; @@ -198,6 +199,7 @@ struct smp_ltk { struct rcu_head rcu; bdaddr_t bdaddr; u8 bdaddr_type; + u8 link_type; u8 authenticated; u8 type; u8 enc_size; @@ -212,6 +214,7 @@ struct smp_irk { bdaddr_t rpa; bdaddr_t bdaddr; u8 addr_type; + u8 link_type; u8 val[16]; }; @@ -219,6 +222,8 @@ struct link_key { struct list_head list; struct rcu_head rcu; bdaddr_t bdaddr; + u8 bdaddr_type; + u8 link_type; u8 type; u8 val[HCI_LINK_KEY_SIZE]; u8 pin_len; @@ -1227,11 +1232,11 @@ static inline struct hci_conn *hci_conn_hash_lookup_cis(struct hci_dev *hdev, continue; /* Match CIG ID if set */ - if (cig != BT_ISO_QOS_CIG_UNSET && cig != c->iso_qos.ucast.cig) + if (cig != c->iso_qos.ucast.cig) continue; /* Match CIS ID if set */ - if (id != BT_ISO_QOS_CIS_UNSET && id != c->iso_qos.ucast.cis) + if (id != c->iso_qos.ucast.cis) continue; /* Match destination address if set */ diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index 3e454c4d7ba6..f07642264c1e 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -22,10 +22,6 @@ #define IF_RS_SENT 0x10 #define IF_READY 0x80000000 -/* prefix flags */ -#define IF_PREFIX_ONLINK 0x01 -#define IF_PREFIX_AUTOCONF 0x02 - enum { INET6_IFADDR_STATE_PREDAD, INET6_IFADDR_STATE_DAD, diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 1ba9f4ddf2f6..9ba6413fd2e3 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -179,9 +179,6 @@ struct fib6_info { refcount_t fib6_ref; unsigned long expires; - - struct hlist_node gc_link; - struct dst_metrics *fib6_metrics; #define fib6_pmtu fib6_metrics->metrics[RTAX_MTU-1] @@ -250,6 +247,19 @@ static inline bool fib6_requires_src(const struct fib6_info *rt) return rt->fib6_src.plen > 0; } +static inline void fib6_clean_expires(struct fib6_info *f6i) +{ + f6i->fib6_flags &= ~RTF_EXPIRES; + f6i->expires = 0; +} + +static inline void fib6_set_expires(struct fib6_info *f6i, + unsigned long expires) +{ + f6i->expires = expires; + f6i->fib6_flags |= RTF_EXPIRES; +} + static inline bool fib6_check_expired(const struct fib6_info *f6i) { if (f6i->fib6_flags & RTF_EXPIRES) @@ -257,11 +267,6 @@ static inline bool fib6_check_expired(const struct fib6_info *f6i) return false; } -static inline bool fib6_has_expires(const struct fib6_info *f6i) -{ - return f6i->fib6_flags & RTF_EXPIRES; -} - /* Function to safely get fn->fn_sernum for passed in rt * and store result in passed in cookie. * Return true if we can get cookie safely @@ -383,7 +388,6 @@ struct fib6_table { struct inet_peer_base tb6_peers; unsigned int flags; unsigned int fib_seq; - struct hlist_head tb6_gc_hlist; /* GC candidates */ #define RT6_TABLE_HAS_DFLT_ROUTER BIT(0) }; @@ -500,48 +504,6 @@ void fib6_gc_cleanup(void); int fib6_init(void); -/* fib6_info must be locked by the caller, and fib6_info->fib6_table can be - * NULL. - */ -static inline void fib6_set_expires_locked(struct fib6_info *f6i, - unsigned long expires) -{ - struct fib6_table *tb6; - - tb6 = f6i->fib6_table; - f6i->expires = expires; - if (tb6 && !fib6_has_expires(f6i)) - hlist_add_head(&f6i->gc_link, &tb6->tb6_gc_hlist); - f6i->fib6_flags |= RTF_EXPIRES; -} - -/* fib6_info must be locked by the caller, and fib6_info->fib6_table can be - * NULL. If fib6_table is NULL, the fib6_info will no be inserted into the - * list of GC candidates until it is inserted into a table. - */ -static inline void fib6_set_expires(struct fib6_info *f6i, - unsigned long expires) -{ - spin_lock_bh(&f6i->fib6_table->tb6_lock); - fib6_set_expires_locked(f6i, expires); - spin_unlock_bh(&f6i->fib6_table->tb6_lock); -} - -static inline void fib6_clean_expires_locked(struct fib6_info *f6i) -{ - if (fib6_has_expires(f6i)) - hlist_del_init(&f6i->gc_link); - f6i->fib6_flags &= ~RTF_EXPIRES; - f6i->expires = 0; -} - -static inline void fib6_clean_expires(struct fib6_info *f6i) -{ - spin_lock_bh(&f6i->fib6_table->tb6_lock); - fib6_clean_expires_locked(f6i); - spin_unlock_bh(&f6i->fib6_table->tb6_lock); -} - struct ipv6_route_iter { struct seq_net_private p; struct fib6_walker w; diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index fe1507c1db82..692d5955911c 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -62,6 +62,8 @@ struct nf_flowtable_type { enum flow_offload_tuple_dir dir, struct nf_flow_rule *flow_rule); void (*free)(struct nf_flowtable *ft); + void (*get)(struct nf_flowtable *ft); + void (*put)(struct nf_flowtable *ft); nf_hookfn *hook; struct module *owner; }; @@ -240,6 +242,11 @@ nf_flow_table_offload_add_cb(struct nf_flowtable *flow_table, } list_add_tail(&block_cb->list, &block->cb_list); + up_write(&flow_table->flow_block_lock); + + if (flow_table->type->get) + flow_table->type->get(flow_table); + return 0; unlock: up_write(&flow_table->flow_block_lock); @@ -262,6 +269,9 @@ nf_flow_table_offload_del_cb(struct nf_flowtable *flow_table, WARN_ON(true); } up_write(&flow_table->flow_block_lock); + + if (flow_table->type->put) + flow_table->type->put(flow_table); } void flow_offload_route_init(struct flow_offload *flow, diff --git a/include/net/netfilter/nf_tables_ipv4.h b/include/net/netfilter/nf_tables_ipv4.h index 947973623dc7..60a7d0ce3080 100644 --- a/include/net/netfilter/nf_tables_ipv4.h +++ b/include/net/netfilter/nf_tables_ipv4.h @@ -30,7 +30,7 @@ static inline int __nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt) return -1; len = iph_totlen(pkt->skb, iph); - thoff = iph->ihl * 4; + thoff = skb_network_offset(pkt->skb) + (iph->ihl * 4); if (pkt->skb->len < len) return -1; else if (len < thoff) diff --git a/include/net/scm.h b/include/net/scm.h index e8c76b4be2fe..cf68acec4d70 100644 --- a/include/net/scm.h +++ b/include/net/scm.h @@ -5,6 +5,7 @@ #include <linux/limits.h> #include <linux/net.h> #include <linux/cred.h> +#include <linux/file.h> #include <linux/security.h> #include <linux/pid.h> #include <linux/nsproxy.h> @@ -208,5 +209,13 @@ static inline void scm_recv_unix(struct socket *sock, struct msghdr *msg, scm_destroy_cred(scm); } +static inline int scm_recv_one_fd(struct file *f, int __user *ufd, + unsigned int flags) +{ + if (!ufd) + return -EFAULT; + return receive_fd(f, ufd, flags); +} + #endif /* __LINUX_NET_SCM_H */ diff --git a/include/net/sock.h b/include/net/sock.h index 1d6931caf0c3..0201136b0b9c 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2799,6 +2799,11 @@ static inline bool sk_is_tcp(const struct sock *sk) return sk->sk_type == SOCK_STREAM && sk->sk_protocol == IPPROTO_TCP; } +static inline bool sk_is_stream_unix(const struct sock *sk) +{ + return sk->sk_family == AF_UNIX && sk->sk_type == SOCK_STREAM; +} + /** * sk_eat_skb - Release a skb if it is no longer needed * @sk: socket to eat this skb from diff --git a/include/net/tcp.h b/include/net/tcp.h index 144ba48bb07b..87f0e6c2e1f2 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1788,8 +1788,6 @@ struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk, const struct sock *addr_sk); #ifdef CONFIG_TCP_MD5SIG -#include <linux/jump_label.h> -extern struct static_key_false_deferred tcp_md5_needed; struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, int l3index, const union tcp_md5_addr *addr, int family, bool any_l3index); diff --git a/include/net/tcp_ao.h b/include/net/tcp_ao.h index 647781080613..b04afced4cc9 100644 --- a/include/net/tcp_ao.h +++ b/include/net/tcp_ao.h @@ -127,12 +127,35 @@ struct tcp_ao_info { struct rcu_head rcu; }; +#ifdef CONFIG_TCP_MD5SIG +#include <linux/jump_label.h> +extern struct static_key_false_deferred tcp_md5_needed; +#define static_branch_tcp_md5() static_branch_unlikely(&tcp_md5_needed.key) +#else +#define static_branch_tcp_md5() false +#endif +#ifdef CONFIG_TCP_AO +/* TCP-AO structures and functions */ +#include <linux/jump_label.h> +extern struct static_key_false_deferred tcp_ao_needed; +#define static_branch_tcp_ao() static_branch_unlikely(&tcp_ao_needed.key) +#else +#define static_branch_tcp_ao() false +#endif + +static inline bool tcp_hash_should_produce_warnings(void) +{ + return static_branch_tcp_md5() || static_branch_tcp_ao(); +} + #define tcp_hash_fail(msg, family, skb, fmt, ...) \ do { \ const struct tcphdr *th = tcp_hdr(skb); \ char hdr_flags[6]; \ char *f = hdr_flags; \ \ + if (!tcp_hash_should_produce_warnings()) \ + break; \ if (th->fin) \ *f++ = 'F'; \ if (th->syn) \ @@ -159,9 +182,6 @@ do { \ #ifdef CONFIG_TCP_AO /* TCP-AO structures and functions */ -#include <linux/jump_label.h> -extern struct static_key_false_deferred tcp_ao_needed; - struct tcp4_ao_context { __be32 saddr; __be32 daddr; diff --git a/include/trace/events/9p.h b/include/trace/events/9p.h index 4dfa6d7f83ba..cd104a1343e2 100644 --- a/include/trace/events/9p.h +++ b/include/trace/events/9p.h @@ -178,18 +178,21 @@ TRACE_EVENT(9p_protocol_dump, __field( void *, clnt ) __field( __u8, type ) __field( __u16, tag ) - __array( unsigned char, line, P9_PROTO_DUMP_SZ ) + __dynamic_array(unsigned char, line, + min_t(size_t, pdu->capacity, P9_PROTO_DUMP_SZ)) ), TP_fast_assign( __entry->clnt = clnt; __entry->type = pdu->id; __entry->tag = pdu->tag; - memcpy(__entry->line, pdu->sdata, P9_PROTO_DUMP_SZ); + memcpy(__get_dynamic_array(line), pdu->sdata, + __get_dynamic_array_len(line)); ), - TP_printk("clnt %lu %s(tag = %d)\n%.3x: %16ph\n%.3x: %16ph\n", + TP_printk("clnt %lu %s(tag = %d)\n%*ph\n", (unsigned long)__entry->clnt, show_9p_op(__entry->type), - __entry->tag, 0, __entry->line, 16, __entry->line + 16) + __entry->tag, __get_dynamic_array_len(line), + __get_dynamic_array(line)) ); diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index 756b013fb832..b67b18e71fbd 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -829,8 +829,14 @@ __SYSCALL(__NR_futex_wait, sys_futex_wait) #define __NR_futex_requeue 456 __SYSCALL(__NR_futex_requeue, sys_futex_requeue) +#define __NR_statmount 457 +__SYSCALL(__NR_statmount, sys_statmount) + +#define __NR_listmount 458 +__SYSCALL(__NR_listmount, sys_listmount) + #undef __NR_syscalls -#define __NR_syscalls 457 +#define __NR_syscalls 459 /* * 32 bit systems traditionally used different diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index db92a7202b34..e7418d15fe39 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -209,7 +209,7 @@ * - add FUSE_HAS_EXPIRE_ONLY * * 7.39 - * - add FUSE_DIRECT_IO_RELAX + * - add FUSE_DIRECT_IO_ALLOW_MMAP * - add FUSE_STATX and related structures */ @@ -409,8 +409,7 @@ struct fuse_file_lock { * FUSE_CREATE_SUPP_GROUP: add supplementary group info to create, mkdir, * symlink and mknod (single group that matches parent) * FUSE_HAS_EXPIRE_ONLY: kernel supports expiry-only entry invalidation - * FUSE_DIRECT_IO_RELAX: relax restrictions in FOPEN_DIRECT_IO mode, for now - * allow shared mmap + * FUSE_DIRECT_IO_ALLOW_MMAP: allow shared mmap in FOPEN_DIRECT_IO mode. */ #define FUSE_ASYNC_READ (1 << 0) #define FUSE_POSIX_LOCKS (1 << 1) @@ -449,7 +448,10 @@ struct fuse_file_lock { #define FUSE_HAS_INODE_DAX (1ULL << 33) #define FUSE_CREATE_SUPP_GROUP (1ULL << 34) #define FUSE_HAS_EXPIRE_ONLY (1ULL << 35) -#define FUSE_DIRECT_IO_RELAX (1ULL << 36) +#define FUSE_DIRECT_IO_ALLOW_MMAP (1ULL << 36) + +/* Obsolete alias for FUSE_DIRECT_IO_ALLOW_MMAP */ +#define FUSE_DIRECT_IO_RELAX FUSE_DIRECT_IO_ALLOW_MMAP /** * CUSE INIT request/reply flags diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h index bb242fdcfe6b..ad5478dbad00 100644 --- a/include/uapi/linux/mount.h +++ b/include/uapi/linux/mount.h @@ -138,4 +138,74 @@ struct mount_attr { /* List of all mount_attr versions. */ #define MOUNT_ATTR_SIZE_VER0 32 /* sizeof first published struct */ + +/* + * Structure for getting mount/superblock/filesystem info with statmount(2). + * + * The interface is similar to statx(2): individual fields or groups can be + * selected with the @mask argument of statmount(). Kernel will set the @mask + * field according to the supported fields. + * + * If string fields are selected, then the caller needs to pass a buffer that + * has space after the fixed part of the structure. Nul terminated strings are + * copied there and offsets relative to @str are stored in the relevant fields. + * If the buffer is too small, then EOVERFLOW is returned. The actually used + * size is returned in @size. + */ +struct statmount { + __u32 size; /* Total size, including strings */ + __u32 __spare1; + __u64 mask; /* What results were written */ + __u32 sb_dev_major; /* Device ID */ + __u32 sb_dev_minor; + __u64 sb_magic; /* ..._SUPER_MAGIC */ + __u32 sb_flags; /* SB_{RDONLY,SYNCHRONOUS,DIRSYNC,LAZYTIME} */ + __u32 fs_type; /* [str] Filesystem type */ + __u64 mnt_id; /* Unique ID of mount */ + __u64 mnt_parent_id; /* Unique ID of parent (for root == mnt_id) */ + __u32 mnt_id_old; /* Reused IDs used in proc/.../mountinfo */ + __u32 mnt_parent_id_old; + __u64 mnt_attr; /* MOUNT_ATTR_... */ + __u64 mnt_propagation; /* MS_{SHARED,SLAVE,PRIVATE,UNBINDABLE} */ + __u64 mnt_peer_group; /* ID of shared peer group */ + __u64 mnt_master; /* Mount receives propagation from this ID */ + __u64 propagate_from; /* Propagation from in current namespace */ + __u32 mnt_root; /* [str] Root of mount relative to root of fs */ + __u32 mnt_point; /* [str] Mountpoint relative to current root */ + __u64 __spare2[50]; + char str[]; /* Variable size part containing strings */ +}; + +/* + * Structure for passing mount ID and miscellaneous parameters to statmount(2) + * and listmount(2). + * + * For statmount(2) @param represents the request mask. + * For listmount(2) @param represents the last listed mount id (or zero). + */ +struct mnt_id_req { + __u32 size; + __u32 spare; + __u64 mnt_id; + __u64 param; +}; + +/* List of all mnt_id_req versions. */ +#define MNT_ID_REQ_SIZE_VER0 24 /* sizeof first published struct */ + +/* + * @mask bits for statmount(2) + */ +#define STATMOUNT_SB_BASIC 0x00000001U /* Want/got sb_... */ +#define STATMOUNT_MNT_BASIC 0x00000002U /* Want/got mnt_... */ +#define STATMOUNT_PROPAGATE_FROM 0x00000004U /* Want/got propagate_from */ +#define STATMOUNT_MNT_ROOT 0x00000008U /* Want/got mnt_root */ +#define STATMOUNT_MNT_POINT 0x00000010U /* Want/got mnt_point */ +#define STATMOUNT_FS_TYPE 0x00000020U /* Want/got fs_type */ + +/* + * Special @mnt_id values that can be passed to listmount + */ +#define LSMT_ROOT 0xffffffffffffffff /* root mount */ + #endif /* _UAPI_LINUX_MOUNT_H */ diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h index 7cab2c65d3d7..2f2ee82d5517 100644 --- a/include/uapi/linux/stat.h +++ b/include/uapi/linux/stat.h @@ -154,6 +154,7 @@ struct statx { #define STATX_BTIME 0x00000800U /* Want/got stx_btime */ #define STATX_MNT_ID 0x00001000U /* Got stx_mnt_id */ #define STATX_DIOALIGN 0x00002000U /* Want/got direct I/O alignment info */ +#define STATX_MNT_ID_UNIQUE 0x00004000U /* Want/got extended stx_mount_id */ #define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */ diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 9626a363f121..9839016f82ea 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -561,7 +561,7 @@ static void io_eventfd_ops(struct rcu_head *rcu) int ops = atomic_xchg(&ev_fd->ops, 0); if (ops & BIT(IO_EVENTFD_OP_SIGNAL_BIT)) - eventfd_signal_mask(ev_fd->cq_ev_fd, 1, EPOLL_URING_WAKE); + eventfd_signal_mask(ev_fd->cq_ev_fd, EPOLL_URING_WAKE); /* IO_EVENTFD_OP_FREE_BIT may not be set here depending on callback * ordering in a race but if references are 0 we know we have to free @@ -597,7 +597,7 @@ static void io_eventfd_signal(struct io_ring_ctx *ctx) goto out; if (likely(eventfd_signal_allowed())) { - eventfd_signal_mask(ev_fd->cq_ev_fd, 1, EPOLL_URING_WAKE); + eventfd_signal_mask(ev_fd->cq_ev_fd, EPOLL_URING_WAKE); } else { atomic_inc(&ev_fd->refs); if (!atomic_fetch_or(BIT(IO_EVENTFD_OP_SIGNAL_BIT), &ev_fd->ops)) diff --git a/io_uring/openclose.c b/io_uring/openclose.c index fb73adb89067..74fc22461f48 100644 --- a/io_uring/openclose.c +++ b/io_uring/openclose.c @@ -241,7 +241,7 @@ int io_close(struct io_kiocb *req, unsigned int issue_flags) return -EAGAIN; } - file = __close_fd_get_file(close->fd); + file = file_close_fd_locked(files, close->fd); spin_unlock(&files->file_lock); if (!file) goto err; diff --git a/io_uring/poll.c b/io_uring/poll.c index d38d05edb4fa..d59b74a99d4e 100644 --- a/io_uring/poll.c +++ b/io_uring/poll.c @@ -366,11 +366,16 @@ void io_poll_task_func(struct io_kiocb *req, struct io_tw_state *ts) static void __io_poll_execute(struct io_kiocb *req, int mask) { + unsigned flags = 0; + io_req_set_res(req, mask, 0); req->io_task_work.func = io_poll_task_func; trace_io_uring_task_add(req, mask); - __io_req_task_work_add(req, IOU_F_TWQ_LAZY_WAKE); + + if (!(req->flags & REQ_F_POLL_NO_LAZY)) + flags = IOU_F_TWQ_LAZY_WAKE; + __io_req_task_work_add(req, flags); } static inline void io_poll_execute(struct io_kiocb *req, int res) @@ -526,10 +531,19 @@ static void __io_queue_proc(struct io_poll *poll, struct io_poll_table *pt, poll->head = head; poll->wait.private = (void *) wqe_private; - if (poll->events & EPOLLEXCLUSIVE) + if (poll->events & EPOLLEXCLUSIVE) { + /* + * Exclusive waits may only wake a limited amount of entries + * rather than all of them, this may interfere with lazy + * wake if someone does wait(events > 1). Ensure we don't do + * lazy wake for those, as we need to process each one as they + * come in. + */ + req->flags |= REQ_F_POLL_NO_LAZY; add_wait_queue_exclusive(head, &poll->wait); - else + } else { add_wait_queue(head, &poll->wait); + } } static void io_poll_queue_proc(struct file *file, struct wait_queue_head *head, diff --git a/io_uring/splice.c b/io_uring/splice.c index 7c4469e9540e..3b659cd23e9d 100644 --- a/io_uring/splice.c +++ b/io_uring/splice.c @@ -51,7 +51,7 @@ int io_tee(struct io_kiocb *req, unsigned int issue_flags) struct file *out = sp->file_out; unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED; struct file *in; - long ret = 0; + ssize_t ret = 0; WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK); @@ -92,7 +92,7 @@ int io_splice(struct io_kiocb *req, unsigned int issue_flags) unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED; loff_t *poff_in, *poff_out; struct file *in; - long ret = 0; + ssize_t ret = 0; WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK); diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c index acbc2924ecd2..7d3ef62e620a 100644 --- a/io_uring/uring_cmd.c +++ b/io_uring/uring_cmd.c @@ -7,7 +7,7 @@ #include <linux/nospec.h> #include <uapi/linux/io_uring.h> -#include <uapi/asm-generic/ioctls.h> +#include <asm/ioctls.h> #include "io_uring.h" #include "rsrc.h" diff --git a/kernel/Kconfig.kexec b/kernel/Kconfig.kexec index 1cc3b1c595d7..946dffa048b7 100644 --- a/kernel/Kconfig.kexec +++ b/kernel/Kconfig.kexec @@ -36,6 +36,8 @@ config KEXEC config KEXEC_FILE bool "Enable kexec file based system call" depends on ARCH_SUPPORTS_KEXEC_FILE + select CRYPTO + select CRYPTO_SHA256 select KEXEC_CORE help This is new version of kexec system call. This system call is @@ -94,7 +96,6 @@ config KEXEC_JUMP config CRASH_DUMP bool "kernel crash dumps" depends on ARCH_SUPPORTS_CRASH_DUMP - depends on ARCH_SUPPORTS_KEXEC select CRASH_CORE select KEXEC_CORE help diff --git a/kernel/crash_core.c b/kernel/crash_core.c index efe87d501c8c..d4313b53837e 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -199,7 +199,7 @@ static __initdata char *suffix_tbl[] = { * It returns 0 on success and -EINVAL on failure. */ static int __init parse_crashkernel_suffix(char *cmdline, - unsigned long long *crash_size, + unsigned long long *crash_size, const char *suffix) { char *cur = cmdline; @@ -268,9 +268,9 @@ static int __init __parse_crashkernel(char *cmdline, unsigned long long *crash_base, const char *suffix) { - char *first_colon, *first_space; - char *ck_cmdline; - char *name = "crashkernel="; + char *first_colon, *first_space; + char *ck_cmdline; + char *name = "crashkernel="; BUG_ON(!crash_size || !crash_base); *crash_size = 0; @@ -440,7 +440,7 @@ retry: return; } - if ((crash_base > CRASH_ADDR_LOW_MAX) && + if ((crash_base >= CRASH_ADDR_LOW_MAX) && crash_low_size && reserve_crashkernel_low(crash_low_size)) { memblock_phys_free(crash_base, crash_size); return; diff --git a/kernel/cred.c b/kernel/cred.c index 3c714cb31660..c033a201c808 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -43,10 +43,6 @@ static struct group_info init_groups = { .usage = REFCOUNT_INIT(2) }; */ struct cred init_cred = { .usage = ATOMIC_INIT(4), -#ifdef CONFIG_DEBUG_CREDENTIALS - .subscribers = ATOMIC_INIT(2), - .magic = CRED_MAGIC, -#endif .uid = GLOBAL_ROOT_UID, .gid = GLOBAL_ROOT_GID, .suid = GLOBAL_ROOT_UID, @@ -66,31 +62,6 @@ struct cred init_cred = { .ucounts = &init_ucounts, }; -static inline void set_cred_subscribers(struct cred *cred, int n) -{ -#ifdef CONFIG_DEBUG_CREDENTIALS - atomic_set(&cred->subscribers, n); -#endif -} - -static inline int read_cred_subscribers(const struct cred *cred) -{ -#ifdef CONFIG_DEBUG_CREDENTIALS - return atomic_read(&cred->subscribers); -#else - return 0; -#endif -} - -static inline void alter_cred_subscribers(const struct cred *_cred, int n) -{ -#ifdef CONFIG_DEBUG_CREDENTIALS - struct cred *cred = (struct cred *) _cred; - - atomic_add(n, &cred->subscribers); -#endif -} - /* * The RCU callback to actually dispose of a set of credentials */ @@ -100,20 +71,9 @@ static void put_cred_rcu(struct rcu_head *rcu) kdebug("put_cred_rcu(%p)", cred); -#ifdef CONFIG_DEBUG_CREDENTIALS - if (cred->magic != CRED_MAGIC_DEAD || - atomic_read(&cred->usage) != 0 || - read_cred_subscribers(cred) != 0) - panic("CRED: put_cred_rcu() sees %p with" - " mag %x, put %p, usage %d, subscr %d\n", - cred, cred->magic, cred->put_addr, - atomic_read(&cred->usage), - read_cred_subscribers(cred)); -#else - if (atomic_read(&cred->usage) != 0) - panic("CRED: put_cred_rcu() sees %p with usage %d\n", - cred, atomic_read(&cred->usage)); -#endif + if (atomic_long_read(&cred->usage) != 0) + panic("CRED: put_cred_rcu() sees %p with usage %ld\n", + cred, atomic_long_read(&cred->usage)); security_cred_free(cred); key_put(cred->session_keyring); @@ -137,16 +97,10 @@ static void put_cred_rcu(struct rcu_head *rcu) */ void __put_cred(struct cred *cred) { - kdebug("__put_cred(%p{%d,%d})", cred, - atomic_read(&cred->usage), - read_cred_subscribers(cred)); - - BUG_ON(atomic_read(&cred->usage) != 0); -#ifdef CONFIG_DEBUG_CREDENTIALS - BUG_ON(read_cred_subscribers(cred) != 0); - cred->magic = CRED_MAGIC_DEAD; - cred->put_addr = __builtin_return_address(0); -#endif + kdebug("__put_cred(%p{%ld})", cred, + atomic_long_read(&cred->usage)); + + BUG_ON(atomic_long_read(&cred->usage) != 0); BUG_ON(cred == current->cred); BUG_ON(cred == current->real_cred); @@ -164,9 +118,8 @@ void exit_creds(struct task_struct *tsk) { struct cred *real_cred, *cred; - kdebug("exit_creds(%u,%p,%p,{%d,%d})", tsk->pid, tsk->real_cred, tsk->cred, - atomic_read(&tsk->cred->usage), - read_cred_subscribers(tsk->cred)); + kdebug("exit_creds(%u,%p,%p,{%ld})", tsk->pid, tsk->real_cred, tsk->cred, + atomic_long_read(&tsk->cred->usage)); real_cred = (struct cred *) tsk->real_cred; tsk->real_cred = NULL; @@ -174,15 +127,10 @@ void exit_creds(struct task_struct *tsk) cred = (struct cred *) tsk->cred; tsk->cred = NULL; - validate_creds(cred); if (real_cred == cred) { - alter_cred_subscribers(cred, -2); put_cred_many(cred, 2); } else { - validate_creds(real_cred); - alter_cred_subscribers(real_cred, -1); put_cred(real_cred); - alter_cred_subscribers(cred, -1); put_cred(cred); } @@ -230,10 +178,7 @@ struct cred *cred_alloc_blank(void) if (!new) return NULL; - atomic_set(&new->usage, 1); -#ifdef CONFIG_DEBUG_CREDENTIALS - new->magic = CRED_MAGIC; -#endif + atomic_long_set(&new->usage, 1); if (security_cred_alloc_blank(new, GFP_KERNEL_ACCOUNT) < 0) goto error; @@ -264,8 +209,6 @@ struct cred *prepare_creds(void) const struct cred *old; struct cred *new; - validate_process_creds(); - new = kmem_cache_alloc(cred_jar, GFP_KERNEL); if (!new) return NULL; @@ -276,8 +219,7 @@ struct cred *prepare_creds(void) memcpy(new, old, sizeof(struct cred)); new->non_rcu = 0; - atomic_set(&new->usage, 1); - set_cred_subscribers(new, 0); + atomic_long_set(&new->usage, 1); get_group_info(new->group_info); get_uid(new->user); get_user_ns(new->user_ns); @@ -300,7 +242,6 @@ struct cred *prepare_creds(void) if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0) goto error; - validate_creds(new); return new; error: @@ -362,10 +303,8 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags) clone_flags & CLONE_THREAD ) { p->real_cred = get_cred_many(p->cred, 2); - alter_cred_subscribers(p->cred, 2); - kdebug("share_creds(%p{%d,%d})", - p->cred, atomic_read(&p->cred->usage), - read_cred_subscribers(p->cred)); + kdebug("share_creds(%p{%ld})", + p->cred, atomic_long_read(&p->cred->usage)); inc_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1); return 0; } @@ -404,8 +343,6 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags) p->cred = p->real_cred = get_cred(new); inc_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1); - alter_cred_subscribers(new, 2); - validate_creds(new); return 0; error_put: @@ -457,17 +394,11 @@ int commit_creds(struct cred *new) struct task_struct *task = current; const struct cred *old = task->real_cred; - kdebug("commit_creds(%p{%d,%d})", new, - atomic_read(&new->usage), - read_cred_subscribers(new)); + kdebug("commit_creds(%p{%ld})", new, + atomic_long_read(&new->usage)); BUG_ON(task->cred != old); -#ifdef CONFIG_DEBUG_CREDENTIALS - BUG_ON(read_cred_subscribers(old) < 2); - validate_creds(old); - validate_creds(new); -#endif - BUG_ON(atomic_read(&new->usage) < 1); + BUG_ON(atomic_long_read(&new->usage) < 1); get_cred(new); /* we will require a ref for the subj creds too */ @@ -502,14 +433,12 @@ int commit_creds(struct cred *new) * RLIMIT_NPROC limits on user->processes have already been checked * in set_user(). */ - alter_cred_subscribers(new, 2); if (new->user != old->user || new->user_ns != old->user_ns) inc_rlimit_ucounts(new->ucounts, UCOUNT_RLIMIT_NPROC, 1); rcu_assign_pointer(task->real_cred, new); rcu_assign_pointer(task->cred, new); if (new->user != old->user || new->user_ns != old->user_ns) dec_rlimit_ucounts(old->ucounts, UCOUNT_RLIMIT_NPROC, 1); - alter_cred_subscribers(old, -2); /* send notifications */ if (!uid_eq(new->uid, old->uid) || @@ -539,14 +468,10 @@ EXPORT_SYMBOL(commit_creds); */ void abort_creds(struct cred *new) { - kdebug("abort_creds(%p{%d,%d})", new, - atomic_read(&new->usage), - read_cred_subscribers(new)); + kdebug("abort_creds(%p{%ld})", new, + atomic_long_read(&new->usage)); -#ifdef CONFIG_DEBUG_CREDENTIALS - BUG_ON(read_cred_subscribers(new) != 0); -#endif - BUG_ON(atomic_read(&new->usage) < 1); + BUG_ON(atomic_long_read(&new->usage) < 1); put_cred(new); } EXPORT_SYMBOL(abort_creds); @@ -562,12 +487,8 @@ const struct cred *override_creds(const struct cred *new) { const struct cred *old = current->cred; - kdebug("override_creds(%p{%d,%d})", new, - atomic_read(&new->usage), - read_cred_subscribers(new)); - - validate_creds(old); - validate_creds(new); + kdebug("override_creds(%p{%ld})", new, + atomic_long_read(&new->usage)); /* * NOTE! This uses 'get_new_cred()' rather than 'get_cred()'. @@ -576,18 +497,12 @@ const struct cred *override_creds(const struct cred *new) * we are only installing the cred into the thread-synchronous * '->cred' pointer, not the '->real_cred' pointer that is * visible to other threads under RCU. - * - * Also note that we did validate_creds() manually, not depending - * on the validation in 'get_cred()'. */ get_new_cred((struct cred *)new); - alter_cred_subscribers(new, 1); rcu_assign_pointer(current->cred, new); - alter_cred_subscribers(old, -1); - kdebug("override_creds() = %p{%d,%d}", old, - atomic_read(&old->usage), - read_cred_subscribers(old)); + kdebug("override_creds() = %p{%ld}", old, + atomic_long_read(&old->usage)); return old; } EXPORT_SYMBOL(override_creds); @@ -603,15 +518,10 @@ void revert_creds(const struct cred *old) { const struct cred *override = current->cred; - kdebug("revert_creds(%p{%d,%d})", old, - atomic_read(&old->usage), - read_cred_subscribers(old)); + kdebug("revert_creds(%p{%ld})", old, + atomic_long_read(&old->usage)); - validate_creds(old); - validate_creds(override); - alter_cred_subscribers(old, 1); rcu_assign_pointer(current->cred, old); - alter_cred_subscribers(override, -1); put_cred(override); } EXPORT_SYMBOL(revert_creds); @@ -731,12 +641,10 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon) kdebug("prepare_kernel_cred() alloc %p", new); old = get_task_cred(daemon); - validate_creds(old); *new = *old; new->non_rcu = 0; - atomic_set(&new->usage, 1); - set_cred_subscribers(new, 0); + atomic_long_set(&new->usage, 1); get_uid(new->user); get_user_ns(new->user_ns); get_group_info(new->group_info); @@ -760,7 +668,6 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon) goto error; put_cred(old); - validate_creds(new); return new; error: @@ -825,109 +732,3 @@ int set_create_files_as(struct cred *new, struct inode *inode) return security_kernel_create_files_as(new, inode); } EXPORT_SYMBOL(set_create_files_as); - -#ifdef CONFIG_DEBUG_CREDENTIALS - -bool creds_are_invalid(const struct cred *cred) -{ - if (cred->magic != CRED_MAGIC) - return true; - return false; -} -EXPORT_SYMBOL(creds_are_invalid); - -/* - * dump invalid credentials - */ -static void dump_invalid_creds(const struct cred *cred, const char *label, - const struct task_struct *tsk) -{ - pr_err("%s credentials: %p %s%s%s\n", - label, cred, - cred == &init_cred ? "[init]" : "", - cred == tsk->real_cred ? "[real]" : "", - cred == tsk->cred ? "[eff]" : ""); - pr_err("->magic=%x, put_addr=%p\n", - cred->magic, cred->put_addr); - pr_err("->usage=%d, subscr=%d\n", - atomic_read(&cred->usage), - read_cred_subscribers(cred)); - pr_err("->*uid = { %d,%d,%d,%d }\n", - from_kuid_munged(&init_user_ns, cred->uid), - from_kuid_munged(&init_user_ns, cred->euid), - from_kuid_munged(&init_user_ns, cred->suid), - from_kuid_munged(&init_user_ns, cred->fsuid)); - pr_err("->*gid = { %d,%d,%d,%d }\n", - from_kgid_munged(&init_user_ns, cred->gid), - from_kgid_munged(&init_user_ns, cred->egid), - from_kgid_munged(&init_user_ns, cred->sgid), - from_kgid_munged(&init_user_ns, cred->fsgid)); -#ifdef CONFIG_SECURITY - pr_err("->security is %p\n", cred->security); - if ((unsigned long) cred->security >= PAGE_SIZE && - (((unsigned long) cred->security & 0xffffff00) != - (POISON_FREE << 24 | POISON_FREE << 16 | POISON_FREE << 8))) - pr_err("->security {%x, %x}\n", - ((u32*)cred->security)[0], - ((u32*)cred->security)[1]); -#endif -} - -/* - * report use of invalid credentials - */ -void __noreturn __invalid_creds(const struct cred *cred, const char *file, unsigned line) -{ - pr_err("Invalid credentials\n"); - pr_err("At %s:%u\n", file, line); - dump_invalid_creds(cred, "Specified", current); - BUG(); -} -EXPORT_SYMBOL(__invalid_creds); - -/* - * check the credentials on a process - */ -void __validate_process_creds(struct task_struct *tsk, - const char *file, unsigned line) -{ - if (tsk->cred == tsk->real_cred) { - if (unlikely(read_cred_subscribers(tsk->cred) < 2 || - creds_are_invalid(tsk->cred))) - goto invalid_creds; - } else { - if (unlikely(read_cred_subscribers(tsk->real_cred) < 1 || - read_cred_subscribers(tsk->cred) < 1 || - creds_are_invalid(tsk->real_cred) || - creds_are_invalid(tsk->cred))) - goto invalid_creds; - } - return; - -invalid_creds: - pr_err("Invalid process credentials\n"); - pr_err("At %s:%u\n", file, line); - - dump_invalid_creds(tsk->real_cred, "Real", tsk); - if (tsk->cred != tsk->real_cred) - dump_invalid_creds(tsk->cred, "Effective", tsk); - else - pr_err("Effective creds == Real creds\n"); - BUG(); -} -EXPORT_SYMBOL(__validate_process_creds); - -/* - * check creds for do_exit() - */ -void validate_creds_for_do_exit(struct task_struct *tsk) -{ - kdebug("validate_creds_for_do_exit(%p,%p{%d,%d})", - tsk->real_cred, tsk->cred, - atomic_read(&tsk->cred->usage), - read_cred_subscribers(tsk->cred)); - - __validate_process_creds(tsk, __FILE__, __LINE__); -} - -#endif /* CONFIG_DEBUG_CREDENTIALS */ diff --git a/kernel/events/core.c b/kernel/events/core.c index c9d123e13b57..9efd0d7775e7 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1947,6 +1947,16 @@ static bool perf_event_validate_size(struct perf_event *event) group_leader->nr_siblings + 1) > 16*1024) return false; + /* + * When creating a new group leader, group_leader->ctx is initialized + * after the size has been validated, but we cannot safely use + * for_each_sibling_event() until group_leader->ctx is set. A new group + * leader cannot have any siblings yet, so we can safely skip checking + * the non-existent siblings. + */ + if (event == group_leader) + return true; + for_each_sibling_event(sibling, group_leader) { if (__perf_event_read_size(sibling->attr.read_format, group_leader->nr_siblings + 1) > 16*1024) diff --git a/kernel/exit.c b/kernel/exit.c index ee9f43bed49a..aedc0832c9f4 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -824,8 +824,6 @@ void __noreturn do_exit(long code) ptrace_event(PTRACE_EVENT_EXIT, code); user_events_exit(tsk); - validate_creds_for_do_exit(tsk); - io_uring_files_cancel(); exit_signals(tsk); /* sets PF_EXITING */ @@ -909,7 +907,6 @@ void __noreturn do_exit(long code) if (tsk->task_frag.page) put_page(tsk->task_frag.page); - validate_creds_for_do_exit(tsk); exit_task_stack_account(tsk); check_stack_usage(); diff --git a/kernel/locking/osq_lock.c b/kernel/locking/osq_lock.c index d5610ad52b92..75a6f6133866 100644 --- a/kernel/locking/osq_lock.c +++ b/kernel/locking/osq_lock.c @@ -11,6 +11,13 @@ * called from interrupt context and we have preemption disabled while * spinning. */ + +struct optimistic_spin_node { + struct optimistic_spin_node *next, *prev; + int locked; /* 1 if lock acquired */ + int cpu; /* encoded CPU # + 1 value */ +}; + static DEFINE_PER_CPU_SHARED_ALIGNED(struct optimistic_spin_node, osq_node); /* @@ -37,32 +44,28 @@ static inline struct optimistic_spin_node *decode_cpu(int encoded_cpu_val) /* * Get a stable @node->next pointer, either for unlock() or unqueue() purposes. * Can return NULL in case we were the last queued and we updated @lock instead. + * + * If osq_lock() is being cancelled there must be a previous node + * and 'old_cpu' is its CPU #. + * For osq_unlock() there is never a previous node and old_cpu is + * set to OSQ_UNLOCKED_VAL. */ static inline struct optimistic_spin_node * osq_wait_next(struct optimistic_spin_queue *lock, struct optimistic_spin_node *node, - struct optimistic_spin_node *prev) + int old_cpu) { - struct optimistic_spin_node *next = NULL; int curr = encode_cpu(smp_processor_id()); - int old; - - /* - * If there is a prev node in queue, then the 'old' value will be - * the prev node's CPU #, else it's set to OSQ_UNLOCKED_VAL since if - * we're currently last in queue, then the queue will then become empty. - */ - old = prev ? prev->cpu : OSQ_UNLOCKED_VAL; for (;;) { if (atomic_read(&lock->tail) == curr && - atomic_cmpxchg_acquire(&lock->tail, curr, old) == curr) { + atomic_cmpxchg_acquire(&lock->tail, curr, old_cpu) == curr) { /* * We were the last queued, we moved @lock back. @prev * will now observe @lock and will complete its * unlock()/unqueue(). */ - break; + return NULL; } /* @@ -76,15 +79,15 @@ osq_wait_next(struct optimistic_spin_queue *lock, * wait for a new @node->next from its Step-C. */ if (node->next) { + struct optimistic_spin_node *next; + next = xchg(&node->next, NULL); if (next) - break; + return next; } cpu_relax(); } - - return next; } bool osq_lock(struct optimistic_spin_queue *lock) @@ -186,7 +189,7 @@ bool osq_lock(struct optimistic_spin_queue *lock) * back to @prev. */ - next = osq_wait_next(lock, node, prev); + next = osq_wait_next(lock, node, prev->cpu); if (!next) return false; @@ -226,7 +229,7 @@ void osq_unlock(struct optimistic_spin_queue *lock) return; } - next = osq_wait_next(lock, node, NULL); + next = osq_wait_next(lock, node, OSQ_UNLOCKED_VAL); if (next) WRITE_ONCE(next->locked, 1); } diff --git a/kernel/pid.c b/kernel/pid.c index 6500ef956f2f..b52b10865454 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -700,7 +700,7 @@ static int pidfd_getfd(struct pid *pid, int fd) if (IS_ERR(file)) return PTR_ERR(file); - ret = receive_fd(file, O_CLOEXEC); + ret = receive_fd(file, NULL, O_CLOEXEC); fput(file); return ret; diff --git a/kernel/resource.c b/kernel/resource.c index 866ef3663a0b..91be1bc50b60 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -1844,8 +1844,8 @@ get_free_mem_region(struct device *dev, struct resource *base, write_lock(&resource_lock); for (addr = gfr_start(base, size, align, flags); - gfr_continue(base, addr, size, flags); - addr = gfr_next(addr, size, flags)) { + gfr_continue(base, addr, align, flags); + addr = gfr_next(addr, align, flags)) { if (__region_intersects(base, addr, size, 0, IORES_DESC_NONE) != REGION_DISJOINT) continue; diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 255999ba9190..aca7b437882e 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -1072,7 +1072,7 @@ static void seccomp_handle_addfd(struct seccomp_kaddfd *addfd, struct seccomp_kn */ list_del_init(&addfd->list); if (!addfd->setfd) - fd = receive_fd(addfd->file, addfd->flags); + fd = receive_fd(addfd->file, NULL, addfd->flags); else fd = receive_fd_replace(addfd->fd, addfd->file, addfd->flags); addfd->ret = fd; diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index e1a6e3c675c0..9a846439b36a 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -201,6 +201,20 @@ COND_SYSCALL(recvmmsg_time32); COND_SYSCALL_COMPAT(recvmmsg_time32); COND_SYSCALL_COMPAT(recvmmsg_time64); +/* Posix timer syscalls may be configured out */ +COND_SYSCALL(timer_create); +COND_SYSCALL(timer_gettime); +COND_SYSCALL(timer_getoverrun); +COND_SYSCALL(timer_settime); +COND_SYSCALL(timer_delete); +COND_SYSCALL(clock_adjtime); +COND_SYSCALL(getitimer); +COND_SYSCALL(setitimer); +COND_SYSCALL(alarm); +COND_SYSCALL_COMPAT(timer_create); +COND_SYSCALL_COMPAT(getitimer); +COND_SYSCALL_COMPAT(setitimer); + /* * Architecture specific syscalls: see further below */ diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c index 828aeecbd1e8..9b6fcb8d85e7 100644 --- a/kernel/time/posix-stubs.c +++ b/kernel/time/posix-stubs.c @@ -17,40 +17,6 @@ #include <linux/time_namespace.h> #include <linux/compat.h> -#ifdef CONFIG_ARCH_HAS_SYSCALL_WRAPPER -/* Architectures may override SYS_NI and COMPAT_SYS_NI */ -#include <asm/syscall_wrapper.h> -#endif - -asmlinkage long sys_ni_posix_timers(void) -{ - pr_err_once("process %d (%s) attempted a POSIX timer syscall " - "while CONFIG_POSIX_TIMERS is not set\n", - current->pid, current->comm); - return -ENOSYS; -} - -#ifndef SYS_NI -#define SYS_NI(name) SYSCALL_ALIAS(sys_##name, sys_ni_posix_timers) -#endif - -#ifndef COMPAT_SYS_NI -#define COMPAT_SYS_NI(name) SYSCALL_ALIAS(compat_sys_##name, sys_ni_posix_timers) -#endif - -SYS_NI(timer_create); -SYS_NI(timer_gettime); -SYS_NI(timer_getoverrun); -SYS_NI(timer_settime); -SYS_NI(timer_delete); -SYS_NI(clock_adjtime); -SYS_NI(getitimer); -SYS_NI(setitimer); -SYS_NI(clock_adjtime32); -#ifdef __ARCH_WANT_SYS_ALARM -SYS_NI(alarm); -#endif - /* * We preserve minimal support for CLOCK_REALTIME and CLOCK_MONOTONIC * as it is easy to remain compatible with little code. CLOCK_BOOTTIME @@ -158,18 +124,7 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags, which_clock); } -#ifdef CONFIG_COMPAT -COMPAT_SYS_NI(timer_create); -#endif - -#if defined(CONFIG_COMPAT) || defined(CONFIG_ALPHA) -COMPAT_SYS_NI(getitimer); -COMPAT_SYS_NI(setitimer); -#endif - #ifdef CONFIG_COMPAT_32BIT_TIME -SYS_NI(timer_settime32); -SYS_NI(timer_gettime32); SYSCALL_DEFINE2(clock_settime32, const clockid_t, which_clock, struct old_timespec32 __user *, tp) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 8de8bec5f366..b01ae7d36021 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1183,18 +1183,19 @@ static void __add_hash_entry(struct ftrace_hash *hash, hash->count++; } -static int add_hash_entry(struct ftrace_hash *hash, unsigned long ip) +static struct ftrace_func_entry * +add_hash_entry(struct ftrace_hash *hash, unsigned long ip) { struct ftrace_func_entry *entry; entry = kmalloc(sizeof(*entry), GFP_KERNEL); if (!entry) - return -ENOMEM; + return NULL; entry->ip = ip; __add_hash_entry(hash, entry); - return 0; + return entry; } static void @@ -1349,7 +1350,6 @@ alloc_and_copy_ftrace_hash(int size_bits, struct ftrace_hash *hash) struct ftrace_func_entry *entry; struct ftrace_hash *new_hash; int size; - int ret; int i; new_hash = alloc_ftrace_hash(size_bits); @@ -1366,8 +1366,7 @@ alloc_and_copy_ftrace_hash(int size_bits, struct ftrace_hash *hash) size = 1 << hash->size_bits; for (i = 0; i < size; i++) { hlist_for_each_entry(entry, &hash->buckets[i], hlist) { - ret = add_hash_entry(new_hash, entry->ip); - if (ret < 0) + if (add_hash_entry(new_hash, entry->ip) == NULL) goto free_hash; } } @@ -2536,7 +2535,7 @@ ftrace_find_unique_ops(struct dyn_ftrace *rec) #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS /* Protected by rcu_tasks for reading, and direct_mutex for writing */ -static struct ftrace_hash *direct_functions = EMPTY_HASH; +static struct ftrace_hash __rcu *direct_functions = EMPTY_HASH; static DEFINE_MUTEX(direct_mutex); int ftrace_direct_func_count; @@ -2555,39 +2554,6 @@ unsigned long ftrace_find_rec_direct(unsigned long ip) return entry->direct; } -static struct ftrace_func_entry* -ftrace_add_rec_direct(unsigned long ip, unsigned long addr, - struct ftrace_hash **free_hash) -{ - struct ftrace_func_entry *entry; - - if (ftrace_hash_empty(direct_functions) || - direct_functions->count > 2 * (1 << direct_functions->size_bits)) { - struct ftrace_hash *new_hash; - int size = ftrace_hash_empty(direct_functions) ? 0 : - direct_functions->count + 1; - - if (size < 32) - size = 32; - - new_hash = dup_hash(direct_functions, size); - if (!new_hash) - return NULL; - - *free_hash = direct_functions; - direct_functions = new_hash; - } - - entry = kmalloc(sizeof(*entry), GFP_KERNEL); - if (!entry) - return NULL; - - entry->ip = ip; - entry->direct = addr; - __add_hash_entry(direct_functions, entry); - return entry; -} - static void call_direct_funcs(unsigned long ip, unsigned long pip, struct ftrace_ops *ops, struct ftrace_regs *fregs) { @@ -4223,8 +4189,8 @@ enter_record(struct ftrace_hash *hash, struct dyn_ftrace *rec, int clear_filter) /* Do nothing if it exists */ if (entry) return 0; - - ret = add_hash_entry(hash, rec->ip); + if (add_hash_entry(hash, rec->ip) == NULL) + ret = -ENOMEM; } return ret; } @@ -5266,7 +5232,8 @@ __ftrace_match_addr(struct ftrace_hash *hash, unsigned long ip, int remove) return 0; } - return add_hash_entry(hash, ip); + entry = add_hash_entry(hash, ip); + return entry ? 0 : -ENOMEM; } static int @@ -5410,7 +5377,7 @@ static void remove_direct_functions_hash(struct ftrace_hash *hash, unsigned long */ int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr) { - struct ftrace_hash *hash, *free_hash = NULL; + struct ftrace_hash *hash, *new_hash = NULL, *free_hash = NULL; struct ftrace_func_entry *entry, *new; int err = -EBUSY, size, i; @@ -5436,17 +5403,44 @@ int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr) } } - /* ... and insert them to direct_functions hash. */ err = -ENOMEM; + + /* Make a copy hash to place the new and the old entries in */ + size = hash->count + direct_functions->count; + if (size > 32) + size = 32; + new_hash = alloc_ftrace_hash(fls(size)); + if (!new_hash) + goto out_unlock; + + /* Now copy over the existing direct entries */ + size = 1 << direct_functions->size_bits; + for (i = 0; i < size; i++) { + hlist_for_each_entry(entry, &direct_functions->buckets[i], hlist) { + new = add_hash_entry(new_hash, entry->ip); + if (!new) + goto out_unlock; + new->direct = entry->direct; + } + } + + /* ... and add the new entries */ + size = 1 << hash->size_bits; for (i = 0; i < size; i++) { hlist_for_each_entry(entry, &hash->buckets[i], hlist) { - new = ftrace_add_rec_direct(entry->ip, addr, &free_hash); + new = add_hash_entry(new_hash, entry->ip); if (!new) - goto out_remove; + goto out_unlock; + /* Update both the copy and the hash entry */ + new->direct = addr; entry->direct = addr; } } + free_hash = direct_functions; + rcu_assign_pointer(direct_functions, new_hash); + new_hash = NULL; + ops->func = call_direct_funcs; ops->flags = MULTI_FLAGS; ops->trampoline = FTRACE_REGS_ADDR; @@ -5454,17 +5448,17 @@ int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr) err = register_ftrace_function_nolock(ops); - out_remove: - if (err) - remove_direct_functions_hash(hash, addr); - out_unlock: mutex_unlock(&direct_mutex); - if (free_hash) { + if (free_hash && free_hash != EMPTY_HASH) { synchronize_rcu_tasks(); free_ftrace_hash(free_hash); } + + if (new_hash) + free_ftrace_hash(new_hash); + return err; } EXPORT_SYMBOL_GPL(register_ftrace_direct); @@ -6309,7 +6303,7 @@ ftrace_graph_set_hash(struct ftrace_hash *hash, char *buffer) if (entry) continue; - if (add_hash_entry(hash, rec->ip) < 0) + if (add_hash_entry(hash, rec->ip) == NULL) goto out; } else { if (entry) { diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 8d2a4f00eca9..9286f88fcd32 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -644,8 +644,8 @@ static inline bool __rb_time_read(rb_time_t *t, u64 *ret, unsigned long *cnt) *cnt = rb_time_cnt(top); - /* If top and msb counts don't match, this interrupted a write */ - if (*cnt != rb_time_cnt(msb)) + /* If top, msb or bottom counts don't match, this interrupted a write */ + if (*cnt != rb_time_cnt(msb) || *cnt != rb_time_cnt(bottom)) return false; /* The shift to msb will lose its cnt bits */ @@ -700,44 +700,6 @@ rb_time_read_cmpxchg(local_t *l, unsigned long expect, unsigned long set) return local_try_cmpxchg(l, &expect, set); } -static bool rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set) -{ - unsigned long cnt, top, bottom, msb; - unsigned long cnt2, top2, bottom2, msb2; - u64 val; - - /* The cmpxchg always fails if it interrupted an update */ - if (!__rb_time_read(t, &val, &cnt2)) - return false; - - if (val != expect) - return false; - - cnt = local_read(&t->cnt); - if ((cnt & 3) != cnt2) - return false; - - cnt2 = cnt + 1; - - rb_time_split(val, &top, &bottom, &msb); - top = rb_time_val_cnt(top, cnt); - bottom = rb_time_val_cnt(bottom, cnt); - - rb_time_split(set, &top2, &bottom2, &msb2); - top2 = rb_time_val_cnt(top2, cnt2); - bottom2 = rb_time_val_cnt(bottom2, cnt2); - - if (!rb_time_read_cmpxchg(&t->cnt, cnt, cnt2)) - return false; - if (!rb_time_read_cmpxchg(&t->msb, msb, msb2)) - return false; - if (!rb_time_read_cmpxchg(&t->top, top, top2)) - return false; - if (!rb_time_read_cmpxchg(&t->bottom, bottom, bottom2)) - return false; - return true; -} - #else /* 64 bits */ /* local64_t always succeeds */ @@ -751,11 +713,6 @@ static void rb_time_set(rb_time_t *t, u64 val) { local64_set(&t->time, val); } - -static bool rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set) -{ - return local64_try_cmpxchg(&t->time, &expect, set); -} #endif /* @@ -924,9 +881,14 @@ static __always_inline bool full_hit(struct trace_buffer *buffer, int cpu, int f if (!nr_pages || !full) return true; - dirty = ring_buffer_nr_dirty_pages(buffer, cpu); + /* + * Add one as dirty will never equal nr_pages, as the sub-buffer + * that the writer is on is not counted as dirty. + * This is needed if "buffer_percent" is set to 100. + */ + dirty = ring_buffer_nr_dirty_pages(buffer, cpu) + 1; - return (dirty * 100) > (full * nr_pages); + return (dirty * 100) >= (full * nr_pages); } /* @@ -987,7 +949,8 @@ void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu) /* make sure the waiters see the new index */ smp_wmb(); - rb_wake_up_waiters(&rbwork->work); + /* This can be called in any context */ + irq_work_queue(&rbwork->work); } /** @@ -1787,6 +1750,8 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer) free_buffer_page(bpage); } + free_page((unsigned long)cpu_buffer->free_page); + kfree(cpu_buffer); } @@ -2407,7 +2372,7 @@ rb_iter_head_event(struct ring_buffer_iter *iter) */ barrier(); - if ((iter->head + length) > commit || length > BUF_MAX_DATA_SIZE) + if ((iter->head + length) > commit || length > BUF_PAGE_SIZE) /* Writer corrupted the read? */ goto reset; @@ -2981,25 +2946,6 @@ static unsigned rb_calculate_event_length(unsigned length) return length; } -static u64 rb_time_delta(struct ring_buffer_event *event) -{ - switch (event->type_len) { - case RINGBUF_TYPE_PADDING: - return 0; - - case RINGBUF_TYPE_TIME_EXTEND: - return rb_event_time_stamp(event); - - case RINGBUF_TYPE_TIME_STAMP: - return 0; - - case RINGBUF_TYPE_DATA: - return event->time_delta; - default: - return 0; - } -} - static inline bool rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer, struct ring_buffer_event *event) @@ -3007,8 +2953,6 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer, unsigned long new_index, old_index; struct buffer_page *bpage; unsigned long addr; - u64 write_stamp; - u64 delta; new_index = rb_event_index(event); old_index = new_index + rb_event_ts_length(event); @@ -3017,14 +2961,10 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer, bpage = READ_ONCE(cpu_buffer->tail_page); - delta = rb_time_delta(event); - - if (!rb_time_read(&cpu_buffer->write_stamp, &write_stamp)) - return false; - - /* Make sure the write stamp is read before testing the location */ - barrier(); - + /* + * Make sure the tail_page is still the same and + * the next write location is the end of this event + */ if (bpage->page == (void *)addr && rb_page_write(bpage) == old_index) { unsigned long write_mask = local_read(&bpage->write) & ~RB_WRITE_MASK; @@ -3035,20 +2975,20 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer, * to make sure that the next event adds an absolute * value and does not rely on the saved write stamp, which * is now going to be bogus. + * + * By setting the before_stamp to zero, the next event + * is not going to use the write_stamp and will instead + * create an absolute timestamp. This means there's no + * reason to update the wirte_stamp! */ rb_time_set(&cpu_buffer->before_stamp, 0); - /* Something came in, can't discard */ - if (!rb_time_cmpxchg(&cpu_buffer->write_stamp, - write_stamp, write_stamp - delta)) - return false; - /* * If an event were to come in now, it would see that the * write_stamp and the before_stamp are different, and assume * that this event just added itself before updating * the write stamp. The interrupting event will fix the - * write stamp for us, and use the before stamp as its delta. + * write stamp for us, and use an absolute timestamp. */ /* @@ -3485,7 +3425,7 @@ static void check_buffer(struct ring_buffer_per_cpu *cpu_buffer, return; /* - * If this interrupted another event, + * If this interrupted another event, */ if (atomic_inc_return(this_cpu_ptr(&checking)) != 1) goto out; @@ -3579,7 +3519,10 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, * absolute timestamp. * Don't bother if this is the start of a new page (w == 0). */ - if (unlikely(!a_ok || !b_ok || (info->before != info->after && w))) { + if (!w) { + /* Use the sub-buffer timestamp */ + info->delta = 0; + } else if (unlikely(!a_ok || !b_ok || info->before != info->after)) { info->add_timestamp |= RB_ADD_STAMP_FORCE | RB_ADD_STAMP_EXTEND; info->length += RB_LEN_TIME_EXTEND; } else { @@ -3602,26 +3545,19 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, /* See if we shot pass the end of this buffer page */ if (unlikely(write > BUF_PAGE_SIZE)) { - /* before and after may now different, fix it up*/ - b_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before); - a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after); - if (a_ok && b_ok && info->before != info->after) - (void)rb_time_cmpxchg(&cpu_buffer->before_stamp, - info->before, info->after); - if (a_ok && b_ok) - check_buffer(cpu_buffer, info, CHECK_FULL_PAGE); + check_buffer(cpu_buffer, info, CHECK_FULL_PAGE); return rb_move_tail(cpu_buffer, tail, info); } if (likely(tail == w)) { - u64 save_before; - bool s_ok; - /* Nothing interrupted us between A and C */ /*D*/ rb_time_set(&cpu_buffer->write_stamp, info->ts); - barrier(); - /*E*/ s_ok = rb_time_read(&cpu_buffer->before_stamp, &save_before); - RB_WARN_ON(cpu_buffer, !s_ok); + /* + * If something came in between C and D, the write stamp + * may now not be in sync. But that's fine as the before_stamp + * will be different and then next event will just be forced + * to use an absolute timestamp. + */ if (likely(!(info->add_timestamp & (RB_ADD_STAMP_FORCE | RB_ADD_STAMP_ABSOLUTE)))) /* This did not interrupt any time update */ @@ -3629,41 +3565,40 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, else /* Just use full timestamp for interrupting event */ info->delta = info->ts; - barrier(); check_buffer(cpu_buffer, info, tail); - if (unlikely(info->ts != save_before)) { - /* SLOW PATH - Interrupted between C and E */ - - a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after); - RB_WARN_ON(cpu_buffer, !a_ok); - - /* Write stamp must only go forward */ - if (save_before > info->after) { - /* - * We do not care about the result, only that - * it gets updated atomically. - */ - (void)rb_time_cmpxchg(&cpu_buffer->write_stamp, - info->after, save_before); - } - } } else { u64 ts; /* SLOW PATH - Interrupted between A and C */ - a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after); - /* Was interrupted before here, write_stamp must be valid */ + + /* Save the old before_stamp */ + a_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before); RB_WARN_ON(cpu_buffer, !a_ok); + + /* + * Read a new timestamp and update the before_stamp to make + * the next event after this one force using an absolute + * timestamp. This is in case an interrupt were to come in + * between E and F. + */ ts = rb_time_stamp(cpu_buffer->buffer); + rb_time_set(&cpu_buffer->before_stamp, ts); + barrier(); - /*E*/ if (write == (local_read(&tail_page->write) & RB_WRITE_MASK) && - info->after < ts && - rb_time_cmpxchg(&cpu_buffer->write_stamp, - info->after, ts)) { - /* Nothing came after this event between C and E */ + /*E*/ a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after); + /* Was interrupted before here, write_stamp must be valid */ + RB_WARN_ON(cpu_buffer, !a_ok); + barrier(); + /*F*/ if (write == (local_read(&tail_page->write) & RB_WRITE_MASK) && + info->after == info->before && info->after < ts) { + /* + * Nothing came after this event between C and F, it is + * safe to use info->after for the delta as it + * matched info->before and is still valid. + */ info->delta = ts - info->after; } else { /* - * Interrupted between C and E: + * Interrupted between C and F: * Lost the previous events time stamp. Just set the * delta to zero, and this will be the same time as * the event this event interrupted. And the events that @@ -3714,6 +3649,12 @@ rb_reserve_next_event(struct trace_buffer *buffer, int nr_loops = 0; int add_ts_default; + /* ring buffer does cmpxchg, make sure it is safe in NMI context */ + if (!IS_ENABLED(CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG) && + (unlikely(in_nmi()))) { + return NULL; + } + rb_start_commit(cpu_buffer); /* The commit page can not change after this */ @@ -3737,6 +3678,8 @@ rb_reserve_next_event(struct trace_buffer *buffer, if (ring_buffer_time_stamp_abs(cpu_buffer->buffer)) { add_ts_default = RB_ADD_STAMP_ABSOLUTE; info.length += RB_LEN_TIME_EXTEND; + if (info.length > BUF_MAX_DATA_SIZE) + goto out_fail; } else { add_ts_default = RB_ADD_STAMP_NONE; } @@ -5118,7 +5061,8 @@ ring_buffer_read_prepare(struct trace_buffer *buffer, int cpu, gfp_t flags) if (!iter) return NULL; - iter->event = kmalloc(BUF_MAX_DATA_SIZE, flags); + /* Holds the entire event: data and meta data */ + iter->event = kmalloc(BUF_PAGE_SIZE, flags); if (!iter->event) { kfree(iter); return NULL; diff --git a/kernel/trace/synth_event_gen_test.c b/kernel/trace/synth_event_gen_test.c index 8dfe85499d4a..354c2117be43 100644 --- a/kernel/trace/synth_event_gen_test.c +++ b/kernel/trace/synth_event_gen_test.c @@ -477,6 +477,17 @@ static int __init synth_event_gen_test_init(void) ret = test_trace_synth_event(); WARN_ON(ret); + + /* Disable when done */ + trace_array_set_clr_event(gen_synth_test->tr, + "synthetic", + "gen_synth_test", false); + trace_array_set_clr_event(empty_synth_test->tr, + "synthetic", + "empty_synth_test", false); + trace_array_set_clr_event(create_synth_test->tr, + "synthetic", + "create_synth_test", false); out: return ret; } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index fbcd3bafb93e..a0defe156b57 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1894,6 +1894,9 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu, __update_max_tr(tr, tsk, cpu); arch_spin_unlock(&tr->max_lock); + + /* Any waiters on the old snapshot buffer need to wake up */ + ring_buffer_wake_waiters(tr->array_buffer.buffer, RING_BUFFER_ALL_CPUS); } /** @@ -1945,12 +1948,23 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) static int wait_on_pipe(struct trace_iterator *iter, int full) { + int ret; + /* Iterators are static, they should be filled or empty */ if (trace_buffer_iter(iter, iter->cpu_file)) return 0; - return ring_buffer_wait(iter->array_buffer->buffer, iter->cpu_file, - full); + ret = ring_buffer_wait(iter->array_buffer->buffer, iter->cpu_file, full); + +#ifdef CONFIG_TRACER_MAX_TRACE + /* + * Make sure this is still the snapshot buffer, as if a snapshot were + * to happen, this would now be the main buffer. + */ + if (iter->snapshot) + iter->array_buffer = &iter->tr->max_buffer; +#endif + return ret; } #ifdef CONFIG_FTRACE_STARTUP_TEST @@ -4722,7 +4736,11 @@ static int s_show(struct seq_file *m, void *v) iter->leftover = ret; } else { - print_trace_line(iter); + ret = print_trace_line(iter); + if (ret == TRACE_TYPE_PARTIAL_LINE) { + iter->seq.full = 0; + trace_seq_puts(&iter->seq, "[LINE TOO BIG]\n"); + } ret = trace_print_seq(m, &iter->seq); /* * If we overflow the seq_file buffer, then it will @@ -4964,6 +4982,12 @@ int tracing_release_file_tr(struct inode *inode, struct file *filp) return 0; } +int tracing_single_release_file_tr(struct inode *inode, struct file *filp) +{ + tracing_release_file_tr(inode, filp); + return single_release(inode, filp); +} + static int tracing_mark_open(struct inode *inode, struct file *filp) { stream_open(inode, filp); @@ -6344,7 +6368,7 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr, if (!tr->array_buffer.buffer) return 0; - /* Do not allow tracing while resizng ring buffer */ + /* Do not allow tracing while resizing ring buffer */ tracing_stop_tr(tr); ret = ring_buffer_resize(tr->array_buffer.buffer, size, cpu); @@ -6352,7 +6376,7 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr, goto out_start; #ifdef CONFIG_TRACER_MAX_TRACE - if (!tr->current_trace->use_max_tr) + if (!tr->allocated_snapshot) goto out; ret = ring_buffer_resize(tr->max_buffer.buffer, size, cpu); @@ -8507,7 +8531,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, wait_index = READ_ONCE(iter->wait_index); - ret = wait_on_pipe(iter, iter->tr->buffer_percent); + ret = wait_on_pipe(iter, iter->snapshot ? 0 : iter->tr->buffer_percent); if (ret) goto out; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index b7f4ea25a194..0489e72c8169 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -617,6 +617,7 @@ int tracing_open_generic(struct inode *inode, struct file *filp); int tracing_open_generic_tr(struct inode *inode, struct file *filp); int tracing_open_file_tr(struct inode *inode, struct file *filp); int tracing_release_file_tr(struct inode *inode, struct file *filp); +int tracing_single_release_file_tr(struct inode *inode, struct file *filp); bool tracing_is_disabled(void); bool tracer_tracing_is_on(struct trace_array *tr); void tracer_tracing_on(struct trace_array *tr); diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 1abc07fba1b9..5ecf3c8bde20 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -5623,10 +5623,12 @@ static int event_hist_open(struct inode *inode, struct file *file) { int ret; - ret = security_locked_down(LOCKDOWN_TRACEFS); + ret = tracing_open_file_tr(inode, file); if (ret) return ret; + /* Clear private_data to avoid warning in single_open() */ + file->private_data = NULL; return single_open(file, hist_show, file); } @@ -5634,7 +5636,7 @@ const struct file_operations event_hist_fops = { .open = event_hist_open, .read = seq_read, .llseek = seq_lseek, - .release = single_release, + .release = tracing_single_release_file_tr, }; #ifdef CONFIG_HIST_TRIGGERS_DEBUG @@ -5900,10 +5902,12 @@ static int event_hist_debug_open(struct inode *inode, struct file *file) { int ret; - ret = security_locked_down(LOCKDOWN_TRACEFS); + ret = tracing_open_file_tr(inode, file); if (ret) return ret; + /* Clear private_data to avoid warning in single_open() */ + file->private_data = NULL; return single_open(file, hist_debug_show, file); } @@ -5911,7 +5915,7 @@ const struct file_operations event_hist_debug_fops = { .open = event_hist_debug_open, .read = seq_read, .llseek = seq_lseek, - .release = single_release, + .release = tracing_single_release_file_tr, }; #endif diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c index 846e02c0fb59..e7af286af4f1 100644 --- a/kernel/trace/trace_events_synth.c +++ b/kernel/trace/trace_events_synth.c @@ -1137,7 +1137,7 @@ EXPORT_SYMBOL_GPL(synth_event_add_fields); * @cmd: A pointer to the dynevent_cmd struct representing the new event * @name: The name of the synthetic event * @mod: The module creating the event, NULL if not created from a module - * @args: Variable number of arg (pairs), one pair for each field + * @...: Variable number of arg (pairs), one pair for each field * * NOTE: Users normally won't want to call this function directly, but * rather use the synth_event_gen_cmd_start() wrapper, which @@ -1695,7 +1695,7 @@ __synth_event_trace_end(struct synth_event_trace_state *trace_state) * synth_event_trace - Trace a synthetic event * @file: The trace_event_file representing the synthetic event * @n_vals: The number of values in vals - * @args: Variable number of args containing the event values + * @...: Variable number of args containing the event values * * Trace a synthetic event using the values passed in the variable * argument list. diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index 9365ce407426..e76f5e1efdf2 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -2177,14 +2177,12 @@ static int user_events_open(struct inode *node, struct file *file) static ssize_t user_events_write(struct file *file, const char __user *ubuf, size_t count, loff_t *ppos) { - struct iovec iov; struct iov_iter i; if (unlikely(*ppos != 0)) return -EFAULT; - if (unlikely(import_single_range(ITER_SOURCE, (char __user *)ubuf, - count, &iov, &i))) + if (unlikely(import_ubuf(ITER_SOURCE, (char __user *)ubuf, count, &i))) return -EFAULT; return user_events_write_core(file, &i); diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index d8b302d01083..3e7fa44dc2b2 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -1587,11 +1587,12 @@ static enum print_line_t trace_print_print(struct trace_iterator *iter, { struct print_entry *field; struct trace_seq *s = &iter->seq; + int max = iter->ent_size - offsetof(struct print_entry, buf); trace_assign_type(field, iter->ent); seq_print_ip_sym(s, field->ip, flags); - trace_seq_printf(s, ": %s", field->buf); + trace_seq_printf(s, ": %.*s", max, field->buf); return trace_handle_return(s); } @@ -1600,10 +1601,11 @@ static enum print_line_t trace_print_raw(struct trace_iterator *iter, int flags, struct trace_event *event) { struct print_entry *field; + int max = iter->ent_size - offsetof(struct print_entry, buf); trace_assign_type(field, iter->ent); - trace_seq_printf(&iter->seq, "# %lx %s", field->ip, field->buf); + trace_seq_printf(&iter->seq, "# %lx %.*s", field->ip, max, field->buf); return trace_handle_return(&iter->seq); } diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index eabe8bcc7042..ce4d99df5f0e 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -231,7 +231,7 @@ void __put_user_ns(struct user_namespace *ns) } EXPORT_SYMBOL(__put_user_ns); -/** +/* * struct idmap_key - holds the information necessary to find an idmapping in a * sorted idmap array. It is passed to cmp_map_id() as first argument. */ @@ -241,7 +241,7 @@ struct idmap_key { u32 count; /* == 0 unless used with map_id_range_down() */ }; -/** +/* * cmp_map_id - Function to be passed to bsearch() to find the requested * idmapping. Expects struct idmap_key to be passed via @k. */ @@ -271,7 +271,7 @@ static int cmp_map_id(const void *k, const void *e) return 1; } -/** +/* * map_id_range_down_max - Find idmap via binary search in ordered idmap array. * Can only be called if number of mappings exceeds UID_GID_MAP_MAX_BASE_EXTENTS. */ @@ -288,7 +288,7 @@ map_id_range_down_max(unsigned extents, struct uid_gid_map *map, u32 id, u32 cou sizeof(struct uid_gid_extent), cmp_map_id); } -/** +/* * map_id_range_down_base - Find idmap via binary search in static extent array. * Can only be called if number of mappings is equal or less than * UID_GID_MAP_MAX_BASE_EXTENTS. @@ -332,12 +332,12 @@ static u32 map_id_range_down(struct uid_gid_map *map, u32 id, u32 count) return id; } -static u32 map_id_down(struct uid_gid_map *map, u32 id) +u32 map_id_down(struct uid_gid_map *map, u32 id) { return map_id_range_down(map, id, 1); } -/** +/* * map_id_up_base - Find idmap via binary search in static extent array. * Can only be called if number of mappings is equal or less than * UID_GID_MAP_MAX_BASE_EXTENTS. @@ -358,7 +358,7 @@ map_id_up_base(unsigned extents, struct uid_gid_map *map, u32 id) return NULL; } -/** +/* * map_id_up_max - Find idmap via binary search in ordered idmap array. * Can only be called if number of mappings exceeds UID_GID_MAP_MAX_BASE_EXTENTS. */ @@ -375,7 +375,7 @@ map_id_up_max(unsigned extents, struct uid_gid_map *map, u32 id) sizeof(struct uid_gid_extent), cmp_map_id); } -static u32 map_id_up(struct uid_gid_map *map, u32 id) +u32 map_id_up(struct uid_gid_map *map, u32 id) { struct uid_gid_extent *extent; unsigned extents = map->nr_extents; @@ -770,7 +770,7 @@ static bool mappings_overlap(struct uid_gid_map *new_map, return false; } -/** +/* * insert_extent - Safely insert a new idmap extent into struct uid_gid_map. * Takes care to allocate a 4K block of memory if the number of mappings exceeds * UID_GID_MAP_MAX_BASE_EXTENTS. @@ -839,7 +839,7 @@ static int cmp_extents_reverse(const void *a, const void *b) return 0; } -/** +/* * sort_idmaps - Sorts an array of idmap entries. * Can only be called if number of mappings exceeds UID_GID_MAP_MAX_BASE_EXTENTS. */ diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c index 778b4056700f..03b90d7d2175 100644 --- a/kernel/watch_queue.c +++ b/kernel/watch_queue.c @@ -270,7 +270,7 @@ long watch_queue_set_size(struct pipe_inode_info *pipe, unsigned int nr_notes) goto error; ret = -ENOMEM; - pages = kcalloc(sizeof(struct page *), nr_pages, GFP_KERNEL); + pages = kcalloc(nr_pages, sizeof(struct page *), GFP_KERNEL); if (!pages) goto error; diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index cc7d53d9dc01..4405f81248fb 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1739,21 +1739,6 @@ config DEBUG_MAPLE_TREE endmenu -config DEBUG_CREDENTIALS - bool "Debug credential management" - depends on DEBUG_KERNEL - help - Enable this to turn on some debug checking for credential - management. The additional code keeps track of the number of - pointers from task_structs to any given cred struct, and checks to - see that this number never exceeds the usage count of the cred - struct. - - Furthermore, if SELinux is enabled, this also checks that the - security pointer in the cred struct is never seen to be invalid. - - If unsure, say N. - source "kernel/rcu/Kconfig.debug" config DEBUG_WQ_FORCE_RR_CPU diff --git a/lib/idr.c b/lib/idr.c index 13f2758c2377..da36054c3ca0 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -508,7 +508,7 @@ void ida_free(struct ida *ida, unsigned int id) goto delete; xas_store(&xas, xa_mk_value(v)); } else { - if (!test_bit(bit, bitmap->bitmap)) + if (!bitmap || !test_bit(bit, bitmap->bitmap)) goto err; __clear_bit(bit, bitmap->bitmap); xas_set_mark(&xas, XA_FREE_MARK); diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 8ff6824a1005..e0aa6b440ca5 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -1369,19 +1369,6 @@ ssize_t import_iovec(int type, const struct iovec __user *uvec, } EXPORT_SYMBOL(import_iovec); -int import_single_range(int rw, void __user *buf, size_t len, - struct iovec *iov, struct iov_iter *i) -{ - if (len > MAX_RW_COUNT) - len = MAX_RW_COUNT; - if (unlikely(!access_ok(buf, len))) - return -EFAULT; - - iov_iter_ubuf(i, rw, buf, len); - return 0; -} -EXPORT_SYMBOL(import_single_range); - int import_ubuf(int rw, void __user *buf, size_t len, struct iov_iter *i) { if (len > MAX_RW_COUNT) diff --git a/lib/maple_tree.c b/lib/maple_tree.c index bb24d84a4922..684689457d77 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -5501,6 +5501,17 @@ int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp) mas_wr_end_piv(&wr_mas); node_size = mas_wr_new_end(&wr_mas); + + /* Slot store, does not require additional nodes */ + if (node_size == wr_mas.node_end) { + /* reuse node */ + if (!mt_in_rcu(mas->tree)) + return 0; + /* shifting boundary */ + if (wr_mas.offset_end - mas->offset == 1) + return 0; + } + if (node_size >= mt_slots[wr_mas.type]) { /* Split, worst case for now. */ request = 1 + mas_mt_height(mas) * 2; diff --git a/lib/test_ida.c b/lib/test_ida.c index b06880625961..55105baa19da 100644 --- a/lib/test_ida.c +++ b/lib/test_ida.c @@ -150,6 +150,45 @@ static void ida_check_conv(struct ida *ida) IDA_BUG_ON(ida, !ida_is_empty(ida)); } +/* + * Check various situations where we attempt to free an ID we don't own. + */ +static void ida_check_bad_free(struct ida *ida) +{ + unsigned long i; + + printk("vvv Ignore \"not allocated\" warnings\n"); + /* IDA is empty; all of these will fail */ + ida_free(ida, 0); + for (i = 0; i < 31; i++) + ida_free(ida, 1 << i); + + /* IDA contains a single value entry */ + IDA_BUG_ON(ida, ida_alloc_min(ida, 3, GFP_KERNEL) != 3); + ida_free(ida, 0); + for (i = 0; i < 31; i++) + ida_free(ida, 1 << i); + + /* IDA contains a single bitmap */ + IDA_BUG_ON(ida, ida_alloc_min(ida, 1023, GFP_KERNEL) != 1023); + ida_free(ida, 0); + for (i = 0; i < 31; i++) + ida_free(ida, 1 << i); + + /* IDA contains a tree */ + IDA_BUG_ON(ida, ida_alloc_min(ida, (1 << 20) - 1, GFP_KERNEL) != (1 << 20) - 1); + ida_free(ida, 0); + for (i = 0; i < 31; i++) + ida_free(ida, 1 << i); + printk("^^^ \"not allocated\" warnings over\n"); + + ida_free(ida, 3); + ida_free(ida, 1023); + ida_free(ida, (1 << 20) - 1); + + IDA_BUG_ON(ida, !ida_is_empty(ida)); +} + static DEFINE_IDA(ida); static int ida_checks(void) @@ -162,6 +201,7 @@ static int ida_checks(void) ida_check_leaf(&ida, 1024 * 64); ida_check_max(&ida); ida_check_conv(&ida); + ida_check_bad_free(&ida); printk("IDA: %u of %u tests passed\n", tests_passed, tests_run); return (tests_run != tests_passed) ? 0 : -EINVAL; diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 3e3733a7084f..552738f14275 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -2111,15 +2111,20 @@ char *fwnode_full_name_string(struct fwnode_handle *fwnode, char *buf, /* Loop starting from the root node to the current node. */ for (depth = fwnode_count_parents(fwnode); depth >= 0; depth--) { - struct fwnode_handle *__fwnode = - fwnode_get_nth_parent(fwnode, depth); + /* + * Only get a reference for other nodes (i.e. parent nodes). + * fwnode refcount may be 0 here. + */ + struct fwnode_handle *__fwnode = depth ? + fwnode_get_nth_parent(fwnode, depth) : fwnode; buf = string(buf, end, fwnode_get_name_prefix(__fwnode), default_str_spec); buf = string(buf, end, fwnode_get_name(__fwnode), default_str_spec); - fwnode_handle_put(__fwnode); + if (depth) + fwnode_handle_put(__fwnode); } return buf; diff --git a/mm/damon/core.c b/mm/damon/core.c index ce1562783e7e..3a05e71509b9 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -445,6 +445,8 @@ struct damon_ctx *damon_new_ctx(void) if (!ctx) return NULL; + init_completion(&ctx->kdamond_started); + ctx->attrs.sample_interval = 5 * 1000; ctx->attrs.aggr_interval = 100 * 1000; ctx->attrs.ops_update_interval = 60 * 1000 * 1000; @@ -668,11 +670,14 @@ static int __damon_start(struct damon_ctx *ctx) mutex_lock(&ctx->kdamond_lock); if (!ctx->kdamond) { err = 0; + reinit_completion(&ctx->kdamond_started); ctx->kdamond = kthread_run(kdamond_fn, ctx, "kdamond.%d", nr_running_ctxs); if (IS_ERR(ctx->kdamond)) { err = PTR_ERR(ctx->kdamond); ctx->kdamond = NULL; + } else { + wait_for_completion(&ctx->kdamond_started); } } mutex_unlock(&ctx->kdamond_lock); @@ -1433,6 +1438,7 @@ static int kdamond_fn(void *data) pr_debug("kdamond (%d) starts\n", current->pid); + complete(&ctx->kdamond_started); kdamond_init_intervals_sis(ctx); if (ctx->ops.init) diff --git a/mm/filemap.c b/mm/filemap.c index f1c8c278310f..ad5b4aa049a3 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2608,6 +2608,15 @@ ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter, end_offset = min_t(loff_t, isize, iocb->ki_pos + iter->count); /* + * Pairs with a barrier in + * block_write_end()->mark_buffer_dirty() or other page + * dirtying routines like iomap_write_end() to ensure + * changes to page contents are visible before we see + * increased inode size. + */ + smp_rmb(); + + /* * Once we start copying data, we don't want to be touching any * cachelines that might be contended: */ diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 4f542444a91f..86ee29b5c39c 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2823,7 +2823,7 @@ void folio_undo_large_rmappable(struct folio *folio) spin_lock_irqsave(&ds_queue->split_queue_lock, flags); if (!list_empty(&folio->_deferred_list)) { ds_queue->split_queue_len--; - list_del(&folio->_deferred_list); + list_del_init(&folio->_deferred_list); } spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 6feb3e0630d1..c466551e2fd9 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1141,7 +1141,7 @@ static inline struct resv_map *inode_resv_map(struct inode *inode) * The VERY common case is inode->mapping == &inode->i_data but, * this may not be true for device special inodes. */ - return (struct resv_map *)(&inode->i_data)->private_data; + return (struct resv_map *)(&inode->i_data)->i_private_data; } static struct resv_map *vma_resv_map(struct vm_area_struct *vma) diff --git a/mm/kasan/kasan_test.c b/mm/kasan/kasan_test.c index 8281eb42464b..34515a106ca5 100644 --- a/mm/kasan/kasan_test.c +++ b/mm/kasan/kasan_test.c @@ -493,14 +493,17 @@ static void kmalloc_oob_memset_2(struct kunit *test) { char *ptr; size_t size = 128 - KASAN_GRANULE_SIZE; + size_t memset_size = 2; KASAN_TEST_NEEDS_CHECKED_MEMINTRINSICS(test); ptr = kmalloc(size, GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr); + OPTIMIZER_HIDE_VAR(ptr); OPTIMIZER_HIDE_VAR(size); - KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 1, 0, 2)); + OPTIMIZER_HIDE_VAR(memset_size); + KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 1, 0, memset_size)); kfree(ptr); } @@ -508,14 +511,17 @@ static void kmalloc_oob_memset_4(struct kunit *test) { char *ptr; size_t size = 128 - KASAN_GRANULE_SIZE; + size_t memset_size = 4; KASAN_TEST_NEEDS_CHECKED_MEMINTRINSICS(test); ptr = kmalloc(size, GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr); + OPTIMIZER_HIDE_VAR(ptr); OPTIMIZER_HIDE_VAR(size); - KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 3, 0, 4)); + OPTIMIZER_HIDE_VAR(memset_size); + KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 3, 0, memset_size)); kfree(ptr); } @@ -523,14 +529,17 @@ static void kmalloc_oob_memset_8(struct kunit *test) { char *ptr; size_t size = 128 - KASAN_GRANULE_SIZE; + size_t memset_size = 8; KASAN_TEST_NEEDS_CHECKED_MEMINTRINSICS(test); ptr = kmalloc(size, GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr); + OPTIMIZER_HIDE_VAR(ptr); OPTIMIZER_HIDE_VAR(size); - KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 7, 0, 8)); + OPTIMIZER_HIDE_VAR(memset_size); + KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 7, 0, memset_size)); kfree(ptr); } @@ -538,14 +547,17 @@ static void kmalloc_oob_memset_16(struct kunit *test) { char *ptr; size_t size = 128 - KASAN_GRANULE_SIZE; + size_t memset_size = 16; KASAN_TEST_NEEDS_CHECKED_MEMINTRINSICS(test); ptr = kmalloc(size, GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr); + OPTIMIZER_HIDE_VAR(ptr); OPTIMIZER_HIDE_VAR(size); - KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 15, 0, 16)); + OPTIMIZER_HIDE_VAR(memset_size); + KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 15, 0, memset_size)); kfree(ptr); } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index b226090fd906..73692cd8c142 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4379,7 +4379,7 @@ static void __mem_cgroup_threshold(struct mem_cgroup *memcg, bool swap) * only one element of the array here. */ for (; i >= 0 && unlikely(t->entries[i].threshold > usage); i--) - eventfd_signal(t->entries[i].eventfd, 1); + eventfd_signal(t->entries[i].eventfd); /* i = current_threshold + 1 */ i++; @@ -4391,7 +4391,7 @@ static void __mem_cgroup_threshold(struct mem_cgroup *memcg, bool swap) * only one element of the array here. */ for (; i < t->size && unlikely(t->entries[i].threshold <= usage); i++) - eventfd_signal(t->entries[i].eventfd, 1); + eventfd_signal(t->entries[i].eventfd); /* Update current_threshold */ t->current_threshold = i - 1; @@ -4431,7 +4431,7 @@ static int mem_cgroup_oom_notify_cb(struct mem_cgroup *memcg) spin_lock(&memcg_oom_lock); list_for_each_entry(ev, &memcg->oom_notify, list) - eventfd_signal(ev->eventfd, 1); + eventfd_signal(ev->eventfd); spin_unlock(&memcg_oom_lock); return 0; @@ -4650,7 +4650,7 @@ static int mem_cgroup_oom_register_event(struct mem_cgroup *memcg, /* already in OOM ? */ if (memcg->under_oom) - eventfd_signal(eventfd, 1); + eventfd_signal(eventfd); spin_unlock(&memcg_oom_lock); return 0; @@ -4942,7 +4942,7 @@ static void memcg_event_remove(struct work_struct *work) event->unregister_event(memcg, event->eventfd); /* Notify userspace the event is going away. */ - eventfd_signal(event->eventfd, 1); + eventfd_signal(event->eventfd); eventfd_ctx_put(event->eventfd); kfree(event); @@ -7543,6 +7543,17 @@ void mem_cgroup_migrate(struct folio *old, struct folio *new) /* Transfer the charge and the css ref */ commit_charge(new, memcg); + /* + * If the old folio is a large folio and is in the split queue, it needs + * to be removed from the split queue now, in case getting an incorrect + * split queue in destroy_large_folio() after the memcg of the old folio + * is cleared. + * + * In addition, the old folio is about to be freed after migration, so + * removing from the split queue a bit earlier seems reasonable. + */ + if (folio_test_large(old) && folio_test_large_rmappable(old)) + folio_undo_large_rmappable(old); old->memcg_data = 0; } diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 660c21859118..455093f73a70 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -595,10 +595,9 @@ struct task_struct *task_early_kill(struct task_struct *tsk, int force_early) /* * Collect processes when the error hit an anonymous page. */ -static void collect_procs_anon(struct page *page, struct list_head *to_kill, - int force_early) +static void collect_procs_anon(struct folio *folio, struct page *page, + struct list_head *to_kill, int force_early) { - struct folio *folio = page_folio(page); struct vm_area_struct *vma; struct task_struct *tsk; struct anon_vma *av; @@ -633,12 +632,12 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill, /* * Collect processes when the error hit a file mapped page. */ -static void collect_procs_file(struct page *page, struct list_head *to_kill, - int force_early) +static void collect_procs_file(struct folio *folio, struct page *page, + struct list_head *to_kill, int force_early) { struct vm_area_struct *vma; struct task_struct *tsk; - struct address_space *mapping = page->mapping; + struct address_space *mapping = folio->mapping; pgoff_t pgoff; i_mmap_lock_read(mapping); @@ -704,17 +703,17 @@ static void collect_procs_fsdax(struct page *page, /* * Collect the processes who have the corrupted page mapped to kill. */ -static void collect_procs(struct page *page, struct list_head *tokill, - int force_early) +static void collect_procs(struct folio *folio, struct page *page, + struct list_head *tokill, int force_early) { - if (!page->mapping) + if (!folio->mapping) return; if (unlikely(PageKsm(page))) collect_procs_ksm(page, tokill, force_early); else if (PageAnon(page)) - collect_procs_anon(page, tokill, force_early); + collect_procs_anon(folio, page, tokill, force_early); else - collect_procs_file(page, tokill, force_early); + collect_procs_file(folio, page, tokill, force_early); } struct hwpoison_walk { @@ -1571,7 +1570,7 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, * This check implies we don't kill processes if their pages * are in the swap cache early. Those are always late kills. */ - if (!page_mapped(hpage)) + if (!page_mapped(p)) return true; if (PageSwapCache(p)) { @@ -1602,7 +1601,7 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, * mapped in dirty form. This has to be done before try_to_unmap, * because ttu takes the rmap data structures down. */ - collect_procs(hpage, &tokill, flags & MF_ACTION_REQUIRED); + collect_procs(folio, p, &tokill, flags & MF_ACTION_REQUIRED); if (PageHuge(hpage) && !PageAnon(hpage)) { /* @@ -1622,10 +1621,10 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, try_to_unmap(folio, ttu); } - unmap_success = !page_mapped(hpage); + unmap_success = !page_mapped(p); if (!unmap_success) pr_err("%#lx: failed to unmap page (mapcount=%d)\n", - pfn, page_mapcount(hpage)); + pfn, page_mapcount(p)); /* * try_to_unmap() might put mlocked page in lru cache, so call @@ -1705,7 +1704,7 @@ static void unmap_and_kill(struct list_head *to_kill, unsigned long pfn, * mapping being torn down is communicated in siginfo, see * kill_proc() */ - loff_t start = (index << PAGE_SHIFT) & ~(size - 1); + loff_t start = ((loff_t)index << PAGE_SHIFT) & ~(size - 1); unmap_mapping_range(mapping, start, size, 0); } @@ -1772,7 +1771,7 @@ static int mf_generic_kill_procs(unsigned long long pfn, int flags, * SIGBUS (i.e. MF_MUST_KILL) */ flags |= MF_ACTION_REQUIRED | MF_MUST_KILL; - collect_procs(&folio->page, &to_kill, true); + collect_procs(folio, &folio->page, &to_kill, true); unmap_and_kill(&to_kill, pfn, folio->mapping, folio->index, flags); unlock: diff --git a/mm/memory.c b/mm/memory.c index 5c757fba8858..6e0712d06cd4 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3624,8 +3624,8 @@ EXPORT_SYMBOL_GPL(unmap_mapping_pages); void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows) { - pgoff_t hba = holebegin >> PAGE_SHIFT; - pgoff_t hlen = (holelen + PAGE_SIZE - 1) >> PAGE_SHIFT; + pgoff_t hba = (pgoff_t)(holebegin) >> PAGE_SHIFT; + pgoff_t hlen = ((pgoff_t)(holelen) + PAGE_SIZE - 1) >> PAGE_SHIFT; /* Check for overflow. */ if (sizeof(holelen) > sizeof(hlen)) { diff --git a/mm/migrate.c b/mm/migrate.c index 35a88334bb3c..36c011a36b71 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -405,6 +405,7 @@ int folio_migrate_mapping(struct address_space *mapping, int dirty; int expected_count = folio_expected_refs(mapping, folio) + extra_count; long nr = folio_nr_pages(folio); + long entries, i; if (!mapping) { /* Anonymous page without mapping */ @@ -442,8 +443,10 @@ int folio_migrate_mapping(struct address_space *mapping, folio_set_swapcache(newfolio); newfolio->private = folio_get_private(folio); } + entries = nr; } else { VM_BUG_ON_FOLIO(folio_test_swapcache(folio), folio); + entries = 1; } /* Move dirty while page refs frozen and newpage not yet exposed */ @@ -453,7 +456,11 @@ int folio_migrate_mapping(struct address_space *mapping, folio_set_dirty(newfolio); } - xas_store(&xas, newfolio); + /* Swap cache still stores N entries instead of a high-order entry */ + for (i = 0; i < entries; i++) { + xas_store(&xas, newfolio); + xas_next(&xas); + } /* * Drop cache reference from old page by unfreezing @@ -746,7 +753,7 @@ static int __buffer_migrate_folio(struct address_space *mapping, recheck_buffers: busy = false; - spin_lock(&mapping->private_lock); + spin_lock(&mapping->i_private_lock); bh = head; do { if (atomic_read(&bh->b_count)) { @@ -760,7 +767,7 @@ recheck_buffers: rc = -EAGAIN; goto unlock_buffers; } - spin_unlock(&mapping->private_lock); + spin_unlock(&mapping->i_private_lock); invalidate_bh_lrus(); invalidated = true; goto recheck_buffers; @@ -787,7 +794,7 @@ recheck_buffers: rc = MIGRATEPAGE_SUCCESS; unlock_buffers: if (check_refs) - spin_unlock(&mapping->private_lock); + spin_unlock(&mapping->i_private_lock); bh = head; do { unlock_buffer(bh); diff --git a/mm/mmap.c b/mm/mmap.c index 1971bfffcc03..aa82eec17489 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1829,6 +1829,9 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, */ pgoff = 0; get_area = shmem_get_unmapped_area; + } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { + /* Ensures that larger anonymous mappings are THP aligned. */ + get_area = thp_get_unmapped_area; } addr = get_area(file, addr, len, pgoff, flags); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index ee2fd6a6af40..05e5c425b3ff 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -692,7 +692,6 @@ static int __bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ra if (min_ratio > 100 * BDI_RATIO_SCALE) return -EINVAL; - min_ratio *= BDI_RATIO_SCALE; spin_lock_bh(&bdi_lock); if (min_ratio > bdi->max_ratio) { @@ -729,7 +728,8 @@ static int __bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ra ret = -EINVAL; } else { bdi->max_ratio = max_ratio; - bdi->max_prop_frac = (FPROP_FRAC_BASE * max_ratio) / 100; + bdi->max_prop_frac = (FPROP_FRAC_BASE * max_ratio) / + (100 * BDI_RATIO_SCALE); } spin_unlock_bh(&bdi_lock); diff --git a/mm/shmem.c b/mm/shmem.c index 91e2620148b2..0d1ce70bce38 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1080,7 +1080,24 @@ whole_folios: } VM_BUG_ON_FOLIO(folio_test_writeback(folio), folio); - truncate_inode_folio(mapping, folio); + + if (!folio_test_large(folio)) { + truncate_inode_folio(mapping, folio); + } else if (truncate_inode_partial_folio(folio, lstart, lend)) { + /* + * If we split a page, reset the loop so + * that we pick up the new sub pages. + * Otherwise the THP was entirely + * dropped or the target range was + * zeroed, so just continue the loop as + * is. + */ + if (!folio_test_large(folio)) { + folio_unlock(folio); + index = start; + break; + } + } } folio_unlock(folio); } diff --git a/mm/shrinker.c b/mm/shrinker.c index dd91eab43ed3..dc5d2a6fcfc4 100644 --- a/mm/shrinker.c +++ b/mm/shrinker.c @@ -126,7 +126,7 @@ static int expand_one_shrinker_info(struct mem_cgroup *memcg, int new_size, if (new_nr_max <= old->map_nr_max) continue; - new = kvmalloc_node(sizeof(*new) + new_size, GFP_KERNEL, nid); + new = kvzalloc_node(sizeof(*new) + new_size, GFP_KERNEL, nid); if (!new) return -ENOMEM; diff --git a/mm/vmpressure.c b/mm/vmpressure.c index 22c6689d9302..bd5183dfd879 100644 --- a/mm/vmpressure.c +++ b/mm/vmpressure.c @@ -169,7 +169,7 @@ static bool vmpressure_event(struct vmpressure *vmpr, continue; if (level < ev->level) continue; - eventfd_signal(ev->efd, 1); + eventfd_signal(ev->efd); ret = true; } mutex_unlock(&vmpr->events_lock); diff --git a/mm/vmscan.c b/mm/vmscan.c index 506f8220c5fe..bba207f41b14 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -3955,6 +3955,7 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) int young = 0; pte_t *pte = pvmw->pte; unsigned long addr = pvmw->address; + struct vm_area_struct *vma = pvmw->vma; struct folio *folio = pfn_folio(pvmw->pfn); bool can_swap = !folio_is_file_lru(folio); struct mem_cgroup *memcg = folio_memcg(folio); @@ -3969,11 +3970,15 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) if (spin_is_contended(pvmw->ptl)) return; + /* exclude special VMAs containing anon pages from COW */ + if (vma->vm_flags & VM_SPECIAL) + return; + /* avoid taking the LRU lock under the PTL when possible */ walk = current->reclaim_state ? current->reclaim_state->mm_walk : NULL; - start = max(addr & PMD_MASK, pvmw->vma->vm_start); - end = min(addr | ~PMD_MASK, pvmw->vma->vm_end - 1) + 1; + start = max(addr & PMD_MASK, vma->vm_start); + end = min(addr | ~PMD_MASK, vma->vm_end - 1) + 1; if (end - start > MIN_LRU_BATCH * PAGE_SIZE) { if (addr - start < MIN_LRU_BATCH * PAGE_SIZE / 2) @@ -3998,7 +4003,7 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) unsigned long pfn; pte_t ptent = ptep_get(pte + i); - pfn = get_pte_pfn(ptent, pvmw->vma, addr); + pfn = get_pte_pfn(ptent, vma, addr); if (pfn == -1) continue; @@ -4009,7 +4014,7 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) if (!folio) continue; - if (!ptep_test_and_clear_young(pvmw->vma, addr, pte + i)) + if (!ptep_test_and_clear_young(vma, addr, pte + i)) VM_WARN_ON_ONCE(true); young++; @@ -4089,6 +4094,9 @@ static void lru_gen_rotate_memcg(struct lruvec *lruvec, int op) else VM_WARN_ON_ONCE(true); + WRITE_ONCE(lruvec->lrugen.seg, seg); + WRITE_ONCE(lruvec->lrugen.gen, new); + hlist_nulls_del_rcu(&lruvec->lrugen.list); if (op == MEMCG_LRU_HEAD || op == MEMCG_LRU_OLD) @@ -4099,9 +4107,6 @@ static void lru_gen_rotate_memcg(struct lruvec *lruvec, int op) pgdat->memcg_lru.nr_memcgs[old]--; pgdat->memcg_lru.nr_memcgs[new]++; - lruvec->lrugen.gen = new; - WRITE_ONCE(lruvec->lrugen.seg, seg); - if (!pgdat->memcg_lru.nr_memcgs[old] && old == get_memcg_gen(pgdat->memcg_lru.seq)) WRITE_ONCE(pgdat->memcg_lru.seq, pgdat->memcg_lru.seq + 1); @@ -4124,11 +4129,11 @@ void lru_gen_online_memcg(struct mem_cgroup *memcg) gen = get_memcg_gen(pgdat->memcg_lru.seq); + lruvec->lrugen.gen = gen; + hlist_nulls_add_tail_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[gen][bin]); pgdat->memcg_lru.nr_memcgs[gen]++; - lruvec->lrugen.gen = gen; - spin_unlock_irq(&pgdat->memcg_lru.lock); } } @@ -4232,7 +4237,7 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_c } /* protected */ - if (tier > tier_idx) { + if (tier > tier_idx || refs == BIT(LRU_REFS_WIDTH)) { int hist = lru_hist_from_seq(lrugen->min_seq[type]); gen = folio_inc_gen(lruvec, folio, false); @@ -4598,7 +4603,12 @@ static bool should_run_aging(struct lruvec *lruvec, unsigned long max_seq, } /* try to scrape all its memory if this memcg was deleted */ - *nr_to_scan = mem_cgroup_online(memcg) ? (total >> sc->priority) : total; + if (!mem_cgroup_online(memcg)) { + *nr_to_scan = total; + return false; + } + + *nr_to_scan = total >> sc->priority; /* * The aging tries to be lazy to reduce the overhead, while the eviction @@ -4635,7 +4645,7 @@ static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, bool DEFINE_MAX_SEQ(lruvec); if (mem_cgroup_below_min(sc->target_mem_cgroup, memcg)) - return 0; + return -1; if (!should_run_aging(lruvec, max_seq, sc, can_swap, &nr_to_scan)) return nr_to_scan; @@ -4648,20 +4658,41 @@ static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, bool return try_to_inc_max_seq(lruvec, max_seq, sc, can_swap, false) ? -1 : 0; } -static unsigned long get_nr_to_reclaim(struct scan_control *sc) +static bool should_abort_scan(struct lruvec *lruvec, struct scan_control *sc) { + int i; + enum zone_watermarks mark; + /* don't abort memcg reclaim to ensure fairness */ if (!root_reclaim(sc)) - return -1; + return false; + + if (sc->nr_reclaimed >= max(sc->nr_to_reclaim, compact_gap(sc->order))) + return true; + + /* check the order to exclude compaction-induced reclaim */ + if (!current_is_kswapd() || sc->order) + return false; + + mark = sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING ? + WMARK_PROMO : WMARK_HIGH; - return max(sc->nr_to_reclaim, compact_gap(sc->order)); + for (i = 0; i <= sc->reclaim_idx; i++) { + struct zone *zone = lruvec_pgdat(lruvec)->node_zones + i; + unsigned long size = wmark_pages(zone, mark) + MIN_LRU_BATCH; + + if (managed_zone(zone) && !zone_watermark_ok(zone, 0, size, sc->reclaim_idx, 0)) + return false; + } + + /* kswapd should abort if all eligible zones are safe */ + return true; } static bool try_to_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) { long nr_to_scan; unsigned long scanned = 0; - unsigned long nr_to_reclaim = get_nr_to_reclaim(sc); int swappiness = get_swappiness(lruvec, sc); /* clean file folios are more likely to exist */ @@ -4683,13 +4714,13 @@ static bool try_to_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) if (scanned >= nr_to_scan) break; - if (sc->nr_reclaimed >= nr_to_reclaim) + if (should_abort_scan(lruvec, sc)) break; cond_resched(); } - /* whether try_to_inc_max_seq() was successful */ + /* whether this lruvec should be rotated */ return nr_to_scan < 0; } @@ -4698,14 +4729,9 @@ static int shrink_one(struct lruvec *lruvec, struct scan_control *sc) bool success; unsigned long scanned = sc->nr_scanned; unsigned long reclaimed = sc->nr_reclaimed; - int seg = lru_gen_memcg_seg(lruvec); struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct pglist_data *pgdat = lruvec_pgdat(lruvec); - /* see the comment on MEMCG_NR_GENS */ - if (!lruvec_is_sizable(lruvec, sc)) - return seg != MEMCG_LRU_TAIL ? MEMCG_LRU_TAIL : MEMCG_LRU_YOUNG; - mem_cgroup_calculate_protection(NULL, memcg); if (mem_cgroup_below_min(NULL, memcg)) @@ -4713,7 +4739,7 @@ static int shrink_one(struct lruvec *lruvec, struct scan_control *sc) if (mem_cgroup_below_low(NULL, memcg)) { /* see the comment on MEMCG_NR_GENS */ - if (seg != MEMCG_LRU_TAIL) + if (lru_gen_memcg_seg(lruvec) != MEMCG_LRU_TAIL) return MEMCG_LRU_TAIL; memcg_memory_event(memcg, MEMCG_LOW); @@ -4729,7 +4755,15 @@ static int shrink_one(struct lruvec *lruvec, struct scan_control *sc) flush_reclaim_state(sc); - return success ? MEMCG_LRU_YOUNG : 0; + if (success && mem_cgroup_online(memcg)) + return MEMCG_LRU_YOUNG; + + if (!success && lruvec_is_sizable(lruvec, sc)) + return 0; + + /* one retry if offlined or too small */ + return lru_gen_memcg_seg(lruvec) != MEMCG_LRU_TAIL ? + MEMCG_LRU_TAIL : MEMCG_LRU_YOUNG; } #ifdef CONFIG_MEMCG @@ -4743,14 +4777,13 @@ static void shrink_many(struct pglist_data *pgdat, struct scan_control *sc) struct lruvec *lruvec; struct lru_gen_folio *lrugen; struct mem_cgroup *memcg; - const struct hlist_nulls_node *pos; - unsigned long nr_to_reclaim = get_nr_to_reclaim(sc); + struct hlist_nulls_node *pos; + gen = get_memcg_gen(READ_ONCE(pgdat->memcg_lru.seq)); bin = first_bin = get_random_u32_below(MEMCG_NR_BINS); restart: op = 0; memcg = NULL; - gen = get_memcg_gen(READ_ONCE(pgdat->memcg_lru.seq)); rcu_read_lock(); @@ -4761,6 +4794,10 @@ restart: } mem_cgroup_put(memcg); + memcg = NULL; + + if (gen != READ_ONCE(lrugen->gen)) + continue; lruvec = container_of(lrugen, struct lruvec, lrugen); memcg = lruvec_memcg(lruvec); @@ -4777,7 +4814,7 @@ restart: rcu_read_lock(); - if (sc->nr_reclaimed >= nr_to_reclaim) + if (should_abort_scan(lruvec, sc)) break; } @@ -4788,7 +4825,7 @@ restart: mem_cgroup_put(memcg); - if (sc->nr_reclaimed >= nr_to_reclaim) + if (!is_a_nulls(pos)) return; /* restart if raced with lru_gen_rotate_memcg() */ @@ -4845,16 +4882,14 @@ static void set_initial_priority(struct pglist_data *pgdat, struct scan_control if (sc->priority != DEF_PRIORITY || sc->nr_to_reclaim < MIN_LRU_BATCH) return; /* - * Determine the initial priority based on ((total / MEMCG_NR_GENS) >> - * priority) * reclaimed_to_scanned_ratio = nr_to_reclaim, where the - * estimated reclaimed_to_scanned_ratio = inactive / total. + * Determine the initial priority based on + * (total >> priority) * reclaimed_to_scanned_ratio = nr_to_reclaim, + * where reclaimed_to_scanned_ratio = inactive / total. */ reclaimable = node_page_state(pgdat, NR_INACTIVE_FILE); if (get_swappiness(lruvec, sc)) reclaimable += node_page_state(pgdat, NR_INACTIVE_ANON); - reclaimable /= MEMCG_NR_GENS; - /* round down reclaimable and round up sc->nr_to_reclaim */ priority = fls_long(reclaimable) - 1 - fls_long(sc->nr_to_reclaim - 1); diff --git a/mm/workingset.c b/mm/workingset.c index b192e44a0e7c..33baad203277 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -313,10 +313,10 @@ static void lru_gen_refault(struct folio *folio, void *shadow) * 1. For pages accessed through page tables, hotter pages pushed out * hot pages which refaulted immediately. * 2. For pages accessed multiple times through file descriptors, - * numbers of accesses might have been out of the range. + * they would have been protected by sort_folio(). */ - if (lru_gen_in_fault() || refs == BIT(LRU_REFS_WIDTH)) { - folio_set_workingset(folio); + if (lru_gen_in_fault() || refs >= BIT(LRU_REFS_WIDTH) - 1) { + set_mask_bits(&folio->flags, 0, LRU_REFS_MASK | BIT(PG_workingset)); mod_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + type, delta); } unlock: diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index 0beb44f2fe1f..f00158234505 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -407,6 +407,8 @@ int vlan_vids_add_by_dev(struct net_device *dev, return 0; list_for_each_entry(vid_info, &vlan_info->vid_list, list) { + if (!vlan_hw_filter_capable(by_dev, vid_info->proto)) + continue; err = vlan_vid_add(dev, vid_info->proto, vid_info->vid); if (err) goto unwind; @@ -417,6 +419,8 @@ unwind: list_for_each_entry_continue_reverse(vid_info, &vlan_info->vid_list, list) { + if (!vlan_hw_filter_capable(by_dev, vid_info->proto)) + continue; vlan_vid_del(dev, vid_info->proto, vid_info->vid); } @@ -436,8 +440,11 @@ void vlan_vids_del_by_dev(struct net_device *dev, if (!vlan_info) return; - list_for_each_entry(vid_info, &vlan_info->vid_list, list) + list_for_each_entry(vid_info, &vlan_info->vid_list, list) { + if (!vlan_hw_filter_capable(by_dev, vid_info->proto)) + continue; vlan_vid_del(dev, vid_info->proto, vid_info->vid); + } } EXPORT_SYMBOL(vlan_vids_del_by_dev); diff --git a/net/9p/protocol.c b/net/9p/protocol.c index 4e3a2a1ffcb3..0e6603b1ec90 100644 --- a/net/9p/protocol.c +++ b/net/9p/protocol.c @@ -394,6 +394,8 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt, uint16_t *nwname = va_arg(ap, uint16_t *); char ***wnames = va_arg(ap, char ***); + *wnames = NULL; + errcode = p9pdu_readf(pdu, proto_version, "w", nwname); if (!errcode) { @@ -403,6 +405,8 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt, GFP_NOFS); if (!*wnames) errcode = -ENOMEM; + else + (*wnames)[0] = NULL; } if (!errcode) { @@ -414,8 +418,10 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt, proto_version, "s", &(*wnames)[i]); - if (errcode) + if (errcode) { + (*wnames)[i] = NULL; break; + } } } @@ -423,11 +429,14 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt, if (*wnames) { int i; - for (i = 0; i < *nwname; i++) + for (i = 0; i < *nwname; i++) { + if (!(*wnames)[i]) + break; kfree((*wnames)[i]); + } + kfree(*wnames); + *wnames = NULL; } - kfree(*wnames); - *wnames = NULL; } } break; diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index 9ba04a69ec2a..a852ec093fa8 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -1775,15 +1775,14 @@ static int atalk_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) break; } case TIOCINQ: { - /* - * These two are safe on a single CPU system as only - * user tasks fiddle here - */ - struct sk_buff *skb = skb_peek(&sk->sk_receive_queue); + struct sk_buff *skb; long amount = 0; + spin_lock_irq(&sk->sk_receive_queue.lock); + skb = skb_peek(&sk->sk_receive_queue); if (skb) amount = skb->len - sizeof(struct ddpehdr); + spin_unlock_irq(&sk->sk_receive_queue.lock); rc = put_user(amount, (int __user *)argp); break; } diff --git a/net/atm/ioctl.c b/net/atm/ioctl.c index 838ebf0cabbf..f81f8d56f5c0 100644 --- a/net/atm/ioctl.c +++ b/net/atm/ioctl.c @@ -73,14 +73,17 @@ static int do_vcc_ioctl(struct socket *sock, unsigned int cmd, case SIOCINQ: { struct sk_buff *skb; + int amount; if (sock->state != SS_CONNECTED) { error = -EINVAL; goto done; } + spin_lock_irq(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); - error = put_user(skb ? skb->len : 0, - (int __user *)argp) ? -EFAULT : 0; + amount = skb ? skb->len : 0; + spin_unlock_irq(&sk->sk_receive_queue.lock); + error = put_user(amount, (int __user *)argp) ? -EFAULT : 0; goto done; } case ATM_SETSC: diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 336a76165454..b93464ac3517 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -309,11 +309,14 @@ int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, if (flags & MSG_OOB) return -EOPNOTSUPP; + lock_sock(sk); + skb = skb_recv_datagram(sk, flags, &err); if (!skb) { if (sk->sk_shutdown & RCV_SHUTDOWN) - return 0; + err = 0; + release_sock(sk); return err; } @@ -343,6 +346,8 @@ int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, skb_free_datagram(sk, skb); + release_sock(sk); + if (flags & MSG_TRUNC) copied = skblen; diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 0849e0dafa95..ebf17b51072f 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -516,6 +516,9 @@ static u8 hci_cc_read_class_of_dev(struct hci_dev *hdev, void *data, { struct hci_rp_read_class_of_dev *rp = data; + if (WARN_ON(!hdev)) + return HCI_ERROR_UNSPECIFIED; + bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) @@ -747,9 +750,23 @@ static u8 hci_cc_read_enc_key_size(struct hci_dev *hdev, void *data, } else { conn->enc_key_size = rp->key_size; status = 0; + + if (conn->enc_key_size < hdev->min_enc_key_size) { + /* As slave role, the conn->state has been set to + * BT_CONNECTED and l2cap conn req might not be received + * yet, at this moment the l2cap layer almost does + * nothing with the non-zero status. + * So we also clear encrypt related bits, and then the + * handler of l2cap conn req will get the right secure + * state at a later time. + */ + status = HCI_ERROR_AUTH_FAILURE; + clear_bit(HCI_CONN_ENCRYPT, &conn->flags); + clear_bit(HCI_CONN_AES_CCM, &conn->flags); + } } - hci_encrypt_cfm(conn, 0); + hci_encrypt_cfm(conn, status); done: hci_dev_unlock(hdev); @@ -820,8 +837,6 @@ static u8 hci_cc_write_auth_payload_timeout(struct hci_dev *hdev, void *data, if (!rp->status) conn->auth_payload_timeout = get_unaligned_le16(sent + 2); - hci_encrypt_cfm(conn, 0); - unlock: hci_dev_unlock(hdev); @@ -2304,7 +2319,8 @@ static void hci_cs_inquiry(struct hci_dev *hdev, __u8 status) return; } - set_bit(HCI_INQUIRY, &hdev->flags); + if (hci_sent_cmd_data(hdev, HCI_OP_INQUIRY)) + set_bit(HCI_INQUIRY, &hdev->flags); } static void hci_cs_create_conn(struct hci_dev *hdev, __u8 status) @@ -3683,12 +3699,8 @@ static void hci_encrypt_change_evt(struct hci_dev *hdev, void *data, cp.handle = cpu_to_le16(conn->handle); cp.timeout = cpu_to_le16(hdev->auth_payload_timeout); if (hci_send_cmd(conn->hdev, HCI_OP_WRITE_AUTH_PAYLOAD_TO, - sizeof(cp), &cp)) { + sizeof(cp), &cp)) bt_dev_err(hdev, "write auth payload timeout failed"); - goto notify; - } - - goto unlock; } notify: diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 17ca13e8c044..baeebee41cd9 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -6492,6 +6492,14 @@ drop: kfree_skb(skb); } +static inline void l2cap_sig_send_rej(struct l2cap_conn *conn, u16 ident) +{ + struct l2cap_cmd_rej_unk rej; + + rej.reason = cpu_to_le16(L2CAP_REJ_NOT_UNDERSTOOD); + l2cap_send_cmd(conn, ident, L2CAP_COMMAND_REJ, sizeof(rej), &rej); +} + static inline void l2cap_sig_channel(struct l2cap_conn *conn, struct sk_buff *skb) { @@ -6517,23 +6525,24 @@ static inline void l2cap_sig_channel(struct l2cap_conn *conn, if (len > skb->len || !cmd->ident) { BT_DBG("corrupted command"); + l2cap_sig_send_rej(conn, cmd->ident); break; } err = l2cap_bredr_sig_cmd(conn, cmd, len, skb->data); if (err) { - struct l2cap_cmd_rej_unk rej; - BT_ERR("Wrong link type (%d)", err); - - rej.reason = cpu_to_le16(L2CAP_REJ_NOT_UNDERSTOOD); - l2cap_send_cmd(conn, cmd->ident, L2CAP_COMMAND_REJ, - sizeof(rej), &rej); + l2cap_sig_send_rej(conn, cmd->ident); } skb_pull(skb, len); } + if (skb->len > 0) { + BT_DBG("corrupted command"); + l2cap_sig_send_rej(conn, 0); + } + drop: kfree_skb(skb); } diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index ba2e00646e8e..9dd815b6603f 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -2897,7 +2897,8 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data, for (i = 0; i < key_count; i++) { struct mgmt_link_key_info *key = &cp->keys[i]; - if (key->addr.type != BDADDR_BREDR || key->type > 0x08) + /* Considering SMP over BREDR/LE, there is no need to check addr_type */ + if (key->type > 0x08) return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_LINK_KEYS, MGMT_STATUS_INVALID_PARAMS); @@ -7130,6 +7131,7 @@ static int load_irks(struct sock *sk, struct hci_dev *hdev, void *cp_data, for (i = 0; i < irk_count; i++) { struct mgmt_irk_info *irk = &cp->irks[i]; + u8 addr_type = le_addr_type(irk->addr.type); if (hci_is_blocked_key(hdev, HCI_BLOCKED_KEY_TYPE_IRK, @@ -7139,8 +7141,12 @@ static int load_irks(struct sock *sk, struct hci_dev *hdev, void *cp_data, continue; } + /* When using SMP over BR/EDR, the addr type should be set to BREDR */ + if (irk->addr.type == BDADDR_BREDR) + addr_type = BDADDR_BREDR; + hci_add_irk(hdev, &irk->addr.bdaddr, - le_addr_type(irk->addr.type), irk->val, + addr_type, irk->val, BDADDR_ANY); } @@ -7221,6 +7227,7 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev, for (i = 0; i < key_count; i++) { struct mgmt_ltk_info *key = &cp->keys[i]; u8 type, authenticated; + u8 addr_type = le_addr_type(key->addr.type); if (hci_is_blocked_key(hdev, HCI_BLOCKED_KEY_TYPE_LTK, @@ -7255,8 +7262,12 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev, continue; } + /* When using SMP over BR/EDR, the addr type should be set to BREDR */ + if (key->addr.type == BDADDR_BREDR) + addr_type = BDADDR_BREDR; + hci_add_ltk(hdev, &key->addr.bdaddr, - le_addr_type(key->addr.type), type, authenticated, + addr_type, type, authenticated, key->val, key->enc_size, key->ediv, key->rand); } @@ -9523,7 +9534,7 @@ void mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key, ev.store_hint = persistent; bacpy(&ev.key.addr.bdaddr, &key->bdaddr); - ev.key.addr.type = BDADDR_BREDR; + ev.key.addr.type = link_to_bdaddr(key->link_type, key->bdaddr_type); ev.key.type = key->type; memcpy(ev.key.val, key->val, HCI_LINK_KEY_SIZE); ev.key.pin_len = key->pin_len; @@ -9574,7 +9585,7 @@ void mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, bool persistent) ev.store_hint = persistent; bacpy(&ev.key.addr.bdaddr, &key->bdaddr); - ev.key.addr.type = link_to_bdaddr(LE_LINK, key->bdaddr_type); + ev.key.addr.type = link_to_bdaddr(key->link_type, key->bdaddr_type); ev.key.type = mgmt_ltk_type(key); ev.key.enc_size = key->enc_size; ev.key.ediv = key->ediv; @@ -9603,7 +9614,7 @@ void mgmt_new_irk(struct hci_dev *hdev, struct smp_irk *irk, bool persistent) bacpy(&ev.rpa, &irk->rpa); bacpy(&ev.irk.addr.bdaddr, &irk->bdaddr); - ev.irk.addr.type = link_to_bdaddr(LE_LINK, irk->addr_type); + ev.irk.addr.type = link_to_bdaddr(irk->link_type, irk->addr_type); memcpy(ev.irk.val, irk->val, sizeof(irk->val)); mgmt_event(MGMT_EV_NEW_IRK, hdev, &ev, sizeof(ev), NULL); @@ -9632,7 +9643,7 @@ void mgmt_new_csrk(struct hci_dev *hdev, struct smp_csrk *csrk, ev.store_hint = persistent; bacpy(&ev.key.addr.bdaddr, &csrk->bdaddr); - ev.key.addr.type = link_to_bdaddr(LE_LINK, csrk->bdaddr_type); + ev.key.addr.type = link_to_bdaddr(csrk->link_type, csrk->bdaddr_type); ev.key.type = csrk->type; memcpy(ev.key.val, csrk->val, sizeof(csrk->val)); diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 5f2f97de295e..1e7ea3a4b7ef 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -1059,6 +1059,7 @@ static void smp_notify_keys(struct l2cap_conn *conn) } if (smp->remote_irk) { + smp->remote_irk->link_type = hcon->type; mgmt_new_irk(hdev, smp->remote_irk, persistent); /* Now that user space can be considered to know the @@ -1078,24 +1079,28 @@ static void smp_notify_keys(struct l2cap_conn *conn) } if (smp->csrk) { + smp->csrk->link_type = hcon->type; smp->csrk->bdaddr_type = hcon->dst_type; bacpy(&smp->csrk->bdaddr, &hcon->dst); mgmt_new_csrk(hdev, smp->csrk, persistent); } if (smp->responder_csrk) { + smp->responder_csrk->link_type = hcon->type; smp->responder_csrk->bdaddr_type = hcon->dst_type; bacpy(&smp->responder_csrk->bdaddr, &hcon->dst); mgmt_new_csrk(hdev, smp->responder_csrk, persistent); } if (smp->ltk) { + smp->ltk->link_type = hcon->type; smp->ltk->bdaddr_type = hcon->dst_type; bacpy(&smp->ltk->bdaddr, &hcon->dst); mgmt_new_ltk(hdev, smp->ltk, persistent); } if (smp->responder_ltk) { + smp->responder_ltk->link_type = hcon->type; smp->responder_ltk->bdaddr_type = hcon->dst_type; bacpy(&smp->responder_ltk->bdaddr, &hcon->dst); mgmt_new_ltk(hdev, smp->responder_ltk, persistent); @@ -1115,6 +1120,8 @@ static void smp_notify_keys(struct l2cap_conn *conn) key = hci_add_link_key(hdev, smp->conn->hcon, &hcon->dst, smp->link_key, type, 0, &persistent); if (key) { + key->link_type = hcon->type; + key->bdaddr_type = hcon->dst_type; mgmt_new_link_key(hdev, key, persistent); /* Don't keep debug keys around if the relevant diff --git a/net/compat.c b/net/compat.c index 6564720f32b7..485db8ee9b28 100644 --- a/net/compat.c +++ b/net/compat.c @@ -297,7 +297,7 @@ void scm_detach_fds_compat(struct msghdr *msg, struct scm_cookie *scm) int err = 0, i; for (i = 0; i < fdmax; i++) { - err = receive_fd_user(scm->fp->fp[i], cmsg_data + i, o_flags); + err = scm_recv_one_fd(scm->fp->fp[i], cmsg_data + i, o_flags); if (err < 0) break; } diff --git a/net/core/dev.c b/net/core/dev.c index c879246be48d..ad20bebe153f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3472,6 +3472,9 @@ static netdev_features_t gso_features_check(const struct sk_buff *skb, if (gso_segs > READ_ONCE(dev->gso_max_segs)) return features & ~NETIF_F_GSO_MASK; + if (unlikely(skb->len >= READ_ONCE(dev->gso_max_size))) + return features & ~NETIF_F_GSO_MASK; + if (!skb_shinfo(skb)->gso_type) { skb_warn_bad_offload(skb); return features & ~NETIF_F_GSO_MASK; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index df81c1f0a570..552719c3bbc3 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -253,9 +253,11 @@ static int neigh_forced_gc(struct neigh_table *tbl) { int max_clean = atomic_read(&tbl->gc_entries) - READ_ONCE(tbl->gc_thresh2); + u64 tmax = ktime_get_ns() + NSEC_PER_MSEC; unsigned long tref = jiffies - 5 * HZ; struct neighbour *n, *tmp; int shrunk = 0; + int loop = 0; NEIGH_CACHE_STAT_INC(tbl, forced_gc_runs); @@ -278,11 +280,16 @@ static int neigh_forced_gc(struct neigh_table *tbl) shrunk++; if (shrunk >= max_clean) break; + if (++loop == 16) { + if (ktime_get_ns() > tmax) + goto unlock; + loop = 0; + } } } WRITE_ONCE(tbl->last_flush, jiffies); - +unlock: write_unlock_bh(&tbl->lock); return shrunk; diff --git a/net/core/scm.c b/net/core/scm.c index 7dc47c17d863..db3f7cd519c2 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -325,7 +325,7 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm) } for (i = 0; i < fdmax; i++) { - err = receive_fd_user(scm->fp->fp[i], cmsg_data + i, o_flags); + err = scm_recv_one_fd(scm->fp->fp[i], cmsg_data + i, o_flags); if (err < 0) break; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index b157efea5dea..94cc40a6f797 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4522,8 +4522,9 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb, /* GSO partial only requires that we trim off any excess that * doesn't fit into an MSS sized block, so take care of that * now. + * Cap len to not accidentally hit GSO_BY_FRAGS. */ - partial_segs = len / mss; + partial_segs = min(len, GSO_BY_FRAGS - 1) / mss; if (partial_segs > 1) mss *= partial_segs; else @@ -4824,7 +4825,9 @@ static __always_inline unsigned int skb_ext_total_length(void) static void skb_extensions_init(void) { BUILD_BUG_ON(SKB_EXT_NUM >= 8); +#if !IS_ENABLED(CONFIG_KCOV_INSTRUMENT_ALL) BUILD_BUG_ON(skb_ext_total_length() > 255); +#endif skbuff_ext_cache = kmem_cache_create("skbuff_ext_cache", SKB_EXT_ALIGN_VALUE * skb_ext_total_length(), diff --git a/net/core/sock.c b/net/core/sock.c index fef349dd72fa..d02534c77413 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1711,9 +1711,16 @@ int sk_getsockopt(struct sock *sk, int level, int optname, break; case SO_TIMESTAMPING_OLD: + case SO_TIMESTAMPING_NEW: lv = sizeof(v.timestamping); - v.timestamping.flags = READ_ONCE(sk->sk_tsflags); - v.timestamping.bind_phc = READ_ONCE(sk->sk_bind_phc); + /* For the later-added case SO_TIMESTAMPING_NEW: Be strict about only + * returning the flags when they were set through the same option. + * Don't change the beviour for the old case SO_TIMESTAMPING_OLD. + */ + if (optname == SO_TIMESTAMPING_OLD || sock_flag(sk, SOCK_TSTAMP_NEW)) { + v.timestamping.flags = READ_ONCE(sk->sk_tsflags); + v.timestamping.bind_phc = READ_ONCE(sk->sk_bind_phc); + } break; case SO_RCVTIMEO_OLD: @@ -2806,6 +2813,7 @@ int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg, sockc->mark = *(u32 *)CMSG_DATA(cmsg); break; case SO_TIMESTAMPING_OLD: + case SO_TIMESTAMPING_NEW: if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32))) return -EINVAL; diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 4292c2ed1828..27d733c0f65e 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -536,6 +536,8 @@ static bool sock_map_sk_state_allowed(const struct sock *sk) { if (sk_is_tcp(sk)) return (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_LISTEN); + if (sk_is_stream_unix(sk)) + return (1 << sk->sk_state) & TCPF_ESTABLISHED; return true; } diff --git a/net/core/stream.c b/net/core/stream.c index 96fbcb9bbb30..b16dfa568a2d 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -79,7 +79,7 @@ int sk_stream_wait_connect(struct sock *sk, long *timeo_p) remove_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending--; } while (!done); - return 0; + return done < 0 ? done : 0; } EXPORT_SYMBOL(sk_stream_wait_connect); diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c index 01e54b46ae0b..f18ca02aa95a 100644 --- a/net/dns_resolver/dns_key.c +++ b/net/dns_resolver/dns_key.c @@ -91,7 +91,6 @@ const struct cred *dns_resolver_cache; static int dns_resolver_preparse(struct key_preparsed_payload *prep) { - const struct dns_payload_header *bin; struct user_key_payload *upayload; unsigned long derrno; int ret; @@ -102,26 +101,34 @@ dns_resolver_preparse(struct key_preparsed_payload *prep) return -EINVAL; if (data[0] == 0) { + const struct dns_server_list_v1_header *v1; + /* It may be a server list. */ - if (datalen <= sizeof(*bin)) + if (datalen <= sizeof(*v1)) return -EINVAL; - bin = (const struct dns_payload_header *)data; - kenter("[%u,%u],%u", bin->content, bin->version, datalen); - if (bin->content != DNS_PAYLOAD_IS_SERVER_LIST) { + v1 = (const struct dns_server_list_v1_header *)data; + kenter("[%u,%u],%u", v1->hdr.content, v1->hdr.version, datalen); + if (v1->hdr.content != DNS_PAYLOAD_IS_SERVER_LIST) { pr_warn_ratelimited( "dns_resolver: Unsupported content type (%u)\n", - bin->content); + v1->hdr.content); return -EINVAL; } - if (bin->version != 1) { + if (v1->hdr.version != 1) { pr_warn_ratelimited( "dns_resolver: Unsupported server list version (%u)\n", - bin->version); + v1->hdr.version); return -EINVAL; } + if ((v1->status != DNS_LOOKUP_GOOD && + v1->status != DNS_LOOKUP_GOOD_WITH_BAD)) { + if (prep->expiry == TIME64_MAX) + prep->expiry = ktime_get_real_seconds() + 1; + } + result_len = datalen; goto store_result; } @@ -314,7 +321,7 @@ static long dns_resolver_read(const struct key *key, struct key_type key_type_dns_resolver = { .name = "dns_resolver", - .flags = KEY_TYPE_NET_DOMAIN, + .flags = KEY_TYPE_NET_DOMAIN | KEY_TYPE_INSTANT_REAP, .preparse = dns_resolver_preparse, .free_preparse = dns_resolver_free_preparse, .instantiate = generic_key_instantiate, diff --git a/net/ife/ife.c b/net/ife/ife.c index 13bbf8cb6a39..be05b690b9ef 100644 --- a/net/ife/ife.c +++ b/net/ife/ife.c @@ -82,6 +82,7 @@ void *ife_decode(struct sk_buff *skb, u16 *metalen) if (unlikely(!pskb_may_pull(skb, total_pull))) return NULL; + ifehdr = (struct ifeheadr *)(skb->data + skb->dev->hard_header_len); skb_set_mac_header(skb, total_pull); __skb_pull(skb, total_pull); *metalen = ifehdrln - IFE_METAHDRLEN; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index ff6838ca2e58..fce5668a6a3d 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1849,7 +1849,6 @@ static int receive_fallback_to_copy(struct sock *sk, { unsigned long copy_address = (unsigned long)zc->copybuf_address; struct msghdr msg = {}; - struct iovec iov; int err; zc->length = 0; @@ -1858,8 +1857,8 @@ static int receive_fallback_to_copy(struct sock *sk, if (copy_address != zc->copybuf_address) return -EINVAL; - err = import_single_range(ITER_DEST, (void __user *)copy_address, - inq, &iov, &msg.msg_iter); + err = import_ubuf(ITER_DEST, (void __user *)copy_address, inq, + &msg.msg_iter); if (err) return err; @@ -1886,14 +1885,13 @@ static int tcp_copy_straggler_data(struct tcp_zerocopy_receive *zc, { unsigned long copy_address = (unsigned long)zc->copybuf_address; struct msghdr msg = {}; - struct iovec iov; int err; if (copy_address != zc->copybuf_address) return -EINVAL; - err = import_single_range(ITER_DEST, (void __user *)copy_address, - copylen, &iov, &msg.msg_iter); + err = import_ubuf(ITER_DEST, (void __user *)copy_address, copylen, + &msg.msg_iter); if (err) return err; err = skb_copy_datagram_msg(skb, *offset, &msg, copylen); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 90de838a2745..701cb87043f2 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4368,6 +4368,23 @@ EXPORT_SYMBOL(tcp_do_parse_auth_options); * up to bandwidth of 18Gigabit/sec. 8) ] */ +/* Estimates max number of increments of remote peer TSval in + * a replay window (based on our current RTO estimation). + */ +static u32 tcp_tsval_replay(const struct sock *sk) +{ + /* If we use usec TS resolution, + * then expect the remote peer to use the same resolution. + */ + if (tcp_sk(sk)->tcp_usec_ts) + return inet_csk(sk)->icsk_rto * (USEC_PER_SEC / HZ); + + /* RFC 7323 recommends a TSval clock between 1ms and 1sec. + * We know that some OS (including old linux) can use 1200 Hz. + */ + return inet_csk(sk)->icsk_rto * 1200 / HZ; +} + static int tcp_disordered_ack(const struct sock *sk, const struct sk_buff *skb) { const struct tcp_sock *tp = tcp_sk(sk); @@ -4375,7 +4392,7 @@ static int tcp_disordered_ack(const struct sock *sk, const struct sk_buff *skb) u32 seq = TCP_SKB_CB(skb)->seq; u32 ack = TCP_SKB_CB(skb)->ack_seq; - return (/* 1. Pure ACK with correct sequence number. */ + return /* 1. Pure ACK with correct sequence number. */ (th->ack && seq == TCP_SKB_CB(skb)->end_seq && seq == tp->rcv_nxt) && /* 2. ... and duplicate ACK. */ @@ -4385,7 +4402,8 @@ static int tcp_disordered_ack(const struct sock *sk, const struct sk_buff *skb) !tcp_may_update_window(tp, ack, seq, ntohs(th->window) << tp->rx_opt.snd_wscale) && /* 4. ... and sits in replay window. */ - (s32)(tp->rx_opt.ts_recent - tp->rx_opt.rcv_tsval) <= (inet_csk(sk)->icsk_rto * 1024) / HZ); + (s32)(tp->rx_opt.ts_recent - tp->rx_opt.rcv_tsval) <= + tcp_tsval_replay(sk); } static inline bool tcp_paws_discard(const struct sock *sk, diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index f5ef15e1d9ac..e3167ad96567 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3293,7 +3293,13 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) if (skb_still_in_host_queue(sk, skb)) return -EBUSY; +start: if (before(TCP_SKB_CB(skb)->seq, tp->snd_una)) { + if (unlikely(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) { + TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_SYN; + TCP_SKB_CB(skb)->seq++; + goto start; + } if (unlikely(before(TCP_SKB_CB(skb)->end_seq, tp->snd_una))) { WARN_ON_ONCE(1); return -EINVAL; diff --git a/net/ipv4/tcp_sigpool.c b/net/ipv4/tcp_sigpool.c index 55b310a722c7..8512cb09ebc0 100644 --- a/net/ipv4/tcp_sigpool.c +++ b/net/ipv4/tcp_sigpool.c @@ -162,9 +162,8 @@ int tcp_sigpool_alloc_ahash(const char *alg, size_t scratch_size) if (strcmp(cpool[i].alg, alg)) continue; - if (kref_read(&cpool[i].kref) > 0) - kref_get(&cpool[i].kref); - else + /* pairs with tcp_sigpool_release() */ + if (!kref_get_unless_zero(&cpool[i].kref)) kref_init(&cpool[i].kref); ret = i; goto out; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 3aaea56b5166..733ace18806c 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1407,23 +1407,15 @@ retry: write_unlock_bh(&idev->lock); - /* From RFC 4941: - * - * A temporary address is created only if this calculated Preferred - * Lifetime is greater than REGEN_ADVANCE time units. In - * particular, an implementation must not create a temporary address - * with a zero Preferred Lifetime. - * - * Clamp the preferred lifetime to a minimum of regen_advance, unless - * that would exceed valid_lft. - * + /* A temporary address is created only if this calculated Preferred + * Lifetime is greater than REGEN_ADVANCE time units. In particular, + * an implementation must not create a temporary address with a zero + * Preferred Lifetime. * Use age calculation as in addrconf_verify to avoid unnecessary * temporary addresses being generated. */ age = (now - tmp_tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ; - if (cfg.preferred_lft <= regen_advance + age) - cfg.preferred_lft = regen_advance + age + 1; - if (cfg.preferred_lft > cfg.valid_lft) { + if (cfg.preferred_lft <= regen_advance + age) { in6_ifa_put(ifp); in6_dev_put(idev); ret = -1; @@ -6149,11 +6141,7 @@ static int inet6_fill_prefix(struct sk_buff *skb, struct inet6_dev *idev, pmsg->prefix_len = pinfo->prefix_len; pmsg->prefix_type = pinfo->type; pmsg->prefix_pad3 = 0; - pmsg->prefix_flags = 0; - if (pinfo->onlink) - pmsg->prefix_flags |= IF_PREFIX_ONLINK; - if (pinfo->autoconf) - pmsg->prefix_flags |= IF_PREFIX_AUTOCONF; + pmsg->prefix_flags = pinfo->flags; if (nla_put(skb, PREFIX_ADDRESS, sizeof(pinfo->prefix), &pinfo->prefix)) goto nla_put_failure; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 7772f42ff2b9..4fc2cae0d116 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -160,8 +160,6 @@ struct fib6_info *fib6_info_alloc(gfp_t gfp_flags, bool with_fib6_nh) INIT_LIST_HEAD(&f6i->fib6_siblings); refcount_set(&f6i->fib6_ref, 1); - INIT_HLIST_NODE(&f6i->gc_link); - return f6i; } @@ -248,7 +246,6 @@ static struct fib6_table *fib6_alloc_table(struct net *net, u32 id) net->ipv6.fib6_null_entry); table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; inet_peer_base_init(&table->tb6_peers); - INIT_HLIST_HEAD(&table->tb6_gc_hlist); } return table; @@ -1060,8 +1057,6 @@ static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn, lockdep_is_held(&table->tb6_lock)); } } - - fib6_clean_expires_locked(rt); } /* @@ -1123,10 +1118,9 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, if (!(iter->fib6_flags & RTF_EXPIRES)) return -EEXIST; if (!(rt->fib6_flags & RTF_EXPIRES)) - fib6_clean_expires_locked(iter); + fib6_clean_expires(iter); else - fib6_set_expires_locked(iter, - rt->expires); + fib6_set_expires(iter, rt->expires); if (rt->fib6_pmtu) fib6_metric_set(iter, RTAX_MTU, @@ -1485,10 +1479,6 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt, if (rt->nh) list_add(&rt->nh_list, &rt->nh->f6i_list); __fib6_update_sernum_upto_root(rt, fib6_new_sernum(info->nl_net)); - - if (fib6_has_expires(rt)) - hlist_add_head(&rt->gc_link, &table->tb6_gc_hlist); - fib6_start_gc(info->nl_net, rt); } @@ -2291,8 +2281,9 @@ static void fib6_flush_trees(struct net *net) * Garbage collection */ -static int fib6_age(struct fib6_info *rt, struct fib6_gc_args *gc_args) +static int fib6_age(struct fib6_info *rt, void *arg) { + struct fib6_gc_args *gc_args = arg; unsigned long now = jiffies; /* @@ -2300,7 +2291,7 @@ static int fib6_age(struct fib6_info *rt, struct fib6_gc_args *gc_args) * Routes are expired even if they are in use. */ - if (fib6_has_expires(rt) && rt->expires) { + if (rt->fib6_flags & RTF_EXPIRES && rt->expires) { if (time_after(now, rt->expires)) { RT6_TRACE("expiring %p\n", rt); return -1; @@ -2317,40 +2308,6 @@ static int fib6_age(struct fib6_info *rt, struct fib6_gc_args *gc_args) return 0; } -static void fib6_gc_table(struct net *net, - struct fib6_table *tb6, - struct fib6_gc_args *gc_args) -{ - struct fib6_info *rt; - struct hlist_node *n; - struct nl_info info = { - .nl_net = net, - .skip_notify = false, - }; - - hlist_for_each_entry_safe(rt, n, &tb6->tb6_gc_hlist, gc_link) - if (fib6_age(rt, gc_args) == -1) - fib6_del(rt, &info); -} - -static void fib6_gc_all(struct net *net, struct fib6_gc_args *gc_args) -{ - struct fib6_table *table; - struct hlist_head *head; - unsigned int h; - - rcu_read_lock(); - for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { - head = &net->ipv6.fib_table_hash[h]; - hlist_for_each_entry_rcu(table, head, tb6_hlist) { - spin_lock_bh(&table->tb6_lock); - fib6_gc_table(net, table, gc_args); - spin_unlock_bh(&table->tb6_lock); - } - } - rcu_read_unlock(); -} - void fib6_run_gc(unsigned long expires, struct net *net, bool force) { struct fib6_gc_args gc_args; @@ -2366,7 +2323,7 @@ void fib6_run_gc(unsigned long expires, struct net *net, bool force) net->ipv6.sysctl.ip6_rt_gc_interval; gc_args.more = 0; - fib6_gc_all(net, &gc_args); + fib6_clean_all(net, fib6_age, &gc_args); now = jiffies; net->ipv6.ip6_rt_last_gc = now; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index b132feae3393..ea1dec8448fc 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3763,10 +3763,10 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg, rt->dst_nocount = true; if (cfg->fc_flags & RTF_EXPIRES) - fib6_set_expires_locked(rt, jiffies + - clock_t_to_jiffies(cfg->fc_expires)); + fib6_set_expires(rt, jiffies + + clock_t_to_jiffies(cfg->fc_expires)); else - fib6_clean_expires_locked(rt); + fib6_clean_expires(rt); if (cfg->fc_protocol == RTPROT_UNSPEC) cfg->fc_protocol = RTPROT_BOOT; diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 606b1b2e4123..eb1d3ef84353 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1788,10 +1788,10 @@ static int sta_link_apply_parameters(struct ieee80211_local *local, lockdep_is_held(&local->hw.wiphy->mtx)); /* - * If there are no changes, then accept a link that doesn't exist, + * If there are no changes, then accept a link that exist, * unless it's a new link. */ - if (params->link_id < 0 && !new_link && + if (params->link_id >= 0 && !new_link && !params->link_mac && !params->txpwr_set && !params->supported_rates_len && !params->ht_capa && !params->vht_capa && diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c index 80aeb25f1b68..dce5606ed66d 100644 --- a/net/mac80211/debugfs_netdev.c +++ b/net/mac80211/debugfs_netdev.c @@ -1043,9 +1043,12 @@ void ieee80211_debugfs_recreate_netdev(struct ieee80211_sub_if_data *sdata, { ieee80211_debugfs_remove_netdev(sdata); ieee80211_debugfs_add_netdev(sdata, mld_vif); - drv_vif_add_debugfs(sdata->local, sdata); - if (!mld_vif) - ieee80211_link_debugfs_drv_add(&sdata->deflink); + + if (sdata->flags & IEEE80211_SDATA_IN_DRIVER) { + drv_vif_add_debugfs(sdata->local, sdata); + if (!mld_vif) + ieee80211_link_debugfs_drv_add(&sdata->deflink); + } } void ieee80211_link_debugfs_add(struct ieee80211_link_data *link) diff --git a/net/mac80211/driver-ops.c b/net/mac80211/driver-ops.c index 7938ec87ef25..3b7f70073fc3 100644 --- a/net/mac80211/driver-ops.c +++ b/net/mac80211/driver-ops.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only /* * Copyright 2015 Intel Deutschland GmbH - * Copyright (C) 2022 Intel Corporation + * Copyright (C) 2022-2023 Intel Corporation */ #include <net/mac80211.h> #include "ieee80211_i.h" @@ -75,9 +75,9 @@ int drv_add_interface(struct ieee80211_local *local, if (ret) return ret; - sdata->flags |= IEEE80211_SDATA_IN_DRIVER; + if (!(sdata->flags & IEEE80211_SDATA_IN_DRIVER)) { + sdata->flags |= IEEE80211_SDATA_IN_DRIVER; - if (!local->in_reconfig) { drv_vif_add_debugfs(local, sdata); /* initially vif is not MLD */ ieee80211_link_debugfs_drv_add(&sdata->deflink); @@ -113,9 +113,13 @@ void drv_remove_interface(struct ieee80211_local *local, if (!check_sdata_in_driver(sdata)) return; + sdata->flags &= ~IEEE80211_SDATA_IN_DRIVER; + + /* Remove driver debugfs entries */ + ieee80211_debugfs_recreate_netdev(sdata, sdata->vif.valid_links); + trace_drv_remove_interface(local, sdata); local->ops->remove_interface(&local->hw, &sdata->vif); - sdata->flags &= ~IEEE80211_SDATA_IN_DRIVER; trace_drv_return_void(local); } @@ -534,7 +538,7 @@ int drv_change_vif_links(struct ieee80211_local *local, if (ret) return ret; - if (!local->in_reconfig) { + if (!local->in_reconfig && !local->resuming) { for_each_set_bit(link_id, &links_to_add, IEEE80211_MLD_MAX_NUM_LINKS) { link = rcu_access_pointer(sdata->link[link_id]); @@ -589,6 +593,10 @@ int drv_change_sta_links(struct ieee80211_local *local, if (ret) return ret; + /* during reconfig don't add it to debugfs again */ + if (local->in_reconfig || local->resuming) + return 0; + for_each_set_bit(link_id, &links_to_add, IEEE80211_MLD_MAX_NUM_LINKS) { link_sta = rcu_dereference_protected(info->link[link_id], lockdep_is_held(&local->hw.wiphy->mtx)); diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c index dbabeefe4515..28bf794f67f8 100644 --- a/net/mac80211/mesh_plink.c +++ b/net/mac80211/mesh_plink.c @@ -1068,8 +1068,8 @@ mesh_plink_get_event(struct ieee80211_sub_if_data *sdata, case WLAN_SP_MESH_PEERING_OPEN: if (!matches_local) event = OPN_RJCT; - if (!mesh_plink_free_count(sdata) || - (sta->mesh->plid && sta->mesh->plid != plid)) + else if (!mesh_plink_free_count(sdata) || + (sta->mesh->plid && sta->mesh->plid != plid)) event = OPN_IGNR; else event = OPN_ACPT; @@ -1077,9 +1077,9 @@ mesh_plink_get_event(struct ieee80211_sub_if_data *sdata, case WLAN_SP_MESH_PEERING_CONFIRM: if (!matches_local) event = CNF_RJCT; - if (!mesh_plink_free_count(sdata) || - sta->mesh->llid != llid || - (sta->mesh->plid && sta->mesh->plid != plid)) + else if (!mesh_plink_free_count(sdata) || + sta->mesh->llid != llid || + (sta->mesh->plid && sta->mesh->plid != plid)) event = CNF_IGNR; else event = CNF_ACPT; @@ -1247,6 +1247,8 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, return; } elems = ieee802_11_parse_elems(baseaddr, len - baselen, true, NULL); - mesh_process_plink_frame(sdata, mgmt, elems, rx_status); - kfree(elems); + if (elems) { + mesh_process_plink_frame(sdata, mgmt, elems, rx_status); + kfree(elems); + } } diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 887b496f2b81..c8998cf01b7a 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -5782,7 +5782,7 @@ static void ieee80211_ml_reconfiguration(struct ieee80211_sub_if_data *sdata, { const struct ieee80211_multi_link_elem *ml; const struct element *sub; - size_t ml_len; + ssize_t ml_len; unsigned long removed_links = 0; u16 link_removal_timeout[IEEE80211_MLD_MAX_NUM_LINKS] = {}; u8 link_id; @@ -5798,6 +5798,8 @@ static void ieee80211_ml_reconfiguration(struct ieee80211_sub_if_data *sdata, elems->scratch + elems->scratch_len - elems->scratch_pos, WLAN_EID_FRAGMENT); + if (ml_len < 0) + return; elems->ml_reconf = (const void *)elems->scratch_pos; elems->ml_reconf_len = ml_len; diff --git a/net/mptcp/crypto_test.c b/net/mptcp/crypto_test.c index 017248dea038..220414e5c850 100644 --- a/net/mptcp/crypto_test.c +++ b/net/mptcp/crypto_test.c @@ -70,3 +70,4 @@ static struct kunit_suite mptcp_crypto_suite = { kunit_test_suite(mptcp_crypto_suite); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("KUnit tests for MPTCP Crypto"); diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index bc81ea53a049..5cd5c3f535a8 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -3402,12 +3402,12 @@ static void mptcp_release_cb(struct sock *sk) if (__test_and_clear_bit(MPTCP_CLEAN_UNA, &msk->cb_flags)) __mptcp_clean_una_wakeup(sk); if (unlikely(msk->cb_flags)) { - /* be sure to set the current sk state before taking actions + /* be sure to sync the msk state before taking actions * depending on sk_state (MPTCP_ERROR_REPORT) * On sk release avoid actions depending on the first subflow */ - if (__test_and_clear_bit(MPTCP_CONNECTED, &msk->cb_flags) && msk->first) - __mptcp_set_connected(sk); + if (__test_and_clear_bit(MPTCP_SYNC_STATE, &msk->cb_flags) && msk->first) + __mptcp_sync_state(sk, msk->pending_state); if (__test_and_clear_bit(MPTCP_ERROR_REPORT, &msk->cb_flags)) __mptcp_error_report(sk); if (__test_and_clear_bit(MPTCP_SYNC_SNDBUF, &msk->cb_flags)) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index fe6f2d399ee8..aa1a93fe40ff 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -124,7 +124,7 @@ #define MPTCP_ERROR_REPORT 3 #define MPTCP_RETRANSMIT 4 #define MPTCP_FLUSH_JOIN_LIST 5 -#define MPTCP_CONNECTED 6 +#define MPTCP_SYNC_STATE 6 #define MPTCP_SYNC_SNDBUF 7 struct mptcp_skb_cb { @@ -296,6 +296,9 @@ struct mptcp_sock { bool use_64bit_ack; /* Set when we received a 64-bit DSN */ bool csum_enabled; bool allow_infinite_fallback; + u8 pending_state; /* A subflow asked to set this sk_state, + * protected by the msk data lock + */ u8 mpc_endpoint_id; u8 recvmsg_inq:1, cork:1, @@ -728,7 +731,7 @@ void mptcp_get_options(const struct sk_buff *skb, struct mptcp_options_received *mp_opt); void mptcp_finish_connect(struct sock *sk); -void __mptcp_set_connected(struct sock *sk); +void __mptcp_sync_state(struct sock *sk, int state); void mptcp_reset_tout_timer(struct mptcp_sock *msk, unsigned long fail_tout); static inline void mptcp_stop_tout_timer(struct sock *sk) @@ -1115,7 +1118,7 @@ static inline bool subflow_simultaneous_connect(struct sock *sk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); - return sk->sk_state == TCP_ESTABLISHED && + return (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_FIN_WAIT1) && is_active_ssk(subflow) && !subflow->conn_finished; } diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index a4f3c27f0309..852b3f4af000 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -419,22 +419,28 @@ static bool subflow_use_different_dport(struct mptcp_sock *msk, const struct soc return inet_sk(sk)->inet_dport != inet_sk((struct sock *)msk)->inet_dport; } -void __mptcp_set_connected(struct sock *sk) +void __mptcp_sync_state(struct sock *sk, int state) { - __mptcp_propagate_sndbuf(sk, mptcp_sk(sk)->first); + struct mptcp_sock *msk = mptcp_sk(sk); + + __mptcp_propagate_sndbuf(sk, msk->first); if (sk->sk_state == TCP_SYN_SENT) { - inet_sk_state_store(sk, TCP_ESTABLISHED); + inet_sk_state_store(sk, state); sk->sk_state_change(sk); } } -static void mptcp_set_connected(struct sock *sk) +static void mptcp_propagate_state(struct sock *sk, struct sock *ssk) { + struct mptcp_sock *msk = mptcp_sk(sk); + mptcp_data_lock(sk); - if (!sock_owned_by_user(sk)) - __mptcp_set_connected(sk); - else - __set_bit(MPTCP_CONNECTED, &mptcp_sk(sk)->cb_flags); + if (!sock_owned_by_user(sk)) { + __mptcp_sync_state(sk, ssk->sk_state); + } else { + msk->pending_state = ssk->sk_state; + __set_bit(MPTCP_SYNC_STATE, &msk->cb_flags); + } mptcp_data_unlock(sk); } @@ -496,7 +502,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) subflow_set_remote_key(msk, subflow, &mp_opt); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVEACK); mptcp_finish_connect(sk); - mptcp_set_connected(parent); + mptcp_propagate_state(parent, sk); } else if (subflow->request_join) { u8 hmac[SHA256_DIGEST_SIZE]; @@ -540,7 +546,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) } else if (mptcp_check_fallback(sk)) { fallback: mptcp_rcv_space_init(msk, sk); - mptcp_set_connected(parent); + mptcp_propagate_state(parent, sk); } return; @@ -1740,7 +1746,7 @@ static void subflow_state_change(struct sock *sk) mptcp_rcv_space_init(msk, sk); pr_fallback(msk); subflow->conn_finished = 1; - mptcp_set_connected(parent); + mptcp_propagate_state(parent, sk); } /* as recvmsg() does not acquire the subflow socket for ssk selection @@ -1976,6 +1982,17 @@ static void tcp_release_cb_override(struct sock *ssk) tcp_release_cb(ssk); } +static int tcp_abort_override(struct sock *ssk, int err) +{ + /* closing a listener subflow requires a great deal of care. + * keep it simple and just prevent such operation + */ + if (inet_sk_state_load(ssk) == TCP_LISTEN) + return -EINVAL; + + return tcp_abort(ssk, err); +} + static struct tcp_ulp_ops subflow_ulp_ops __read_mostly = { .name = "mptcp", .owner = THIS_MODULE, @@ -2020,6 +2037,7 @@ void __init mptcp_subflow_init(void) tcp_prot_override = tcp_prot; tcp_prot_override.release_cb = tcp_release_cb_override; + tcp_prot_override.diag_destroy = tcp_abort_override; #if IS_ENABLED(CONFIG_MPTCP_IPV6) /* In struct mptcp_subflow_request_sock, we assume the TCP request sock @@ -2055,6 +2073,7 @@ void __init mptcp_subflow_init(void) tcpv6_prot_override = tcpv6_prot; tcpv6_prot_override.release_cb = tcp_release_cb_override; + tcpv6_prot_override.diag_destroy = tcp_abort_override; #endif mptcp_diag_subflow_init(&subflow_ulp_ops); diff --git a/net/mptcp/token_test.c b/net/mptcp/token_test.c index 0758865ab658..bfff53e668da 100644 --- a/net/mptcp/token_test.c +++ b/net/mptcp/token_test.c @@ -143,3 +143,4 @@ static struct kunit_suite mptcp_token_suite = { kunit_test_suite(mptcp_token_suite); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("KUnit tests for MPTCP Token"); diff --git a/net/netfilter/nf_nat_ovs.c b/net/netfilter/nf_nat_ovs.c index 551abd2da614..0f9a559f6207 100644 --- a/net/netfilter/nf_nat_ovs.c +++ b/net/netfilter/nf_nat_ovs.c @@ -75,9 +75,10 @@ static int nf_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct, } err = nf_nat_packet(ct, ctinfo, hooknum, skb); +out: if (err == NF_ACCEPT) *action |= BIT(maniptype); -out: + return err; } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index c5c17c6e80ed..be04af433988 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -9887,7 +9887,7 @@ static void nft_set_commit_update(struct list_head *set_update_list) list_for_each_entry_safe(set, next, set_update_list, pending_update) { list_del_init(&set->pending_update); - if (!set->ops->commit) + if (!set->ops->commit || set->dead) continue; set->ops->commit(set); diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index 8b536d7ef6c2..c3e635364701 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -158,7 +158,7 @@ static bool nft_payload_fast_eval(const struct nft_expr *expr, else { if (!(pkt->flags & NFT_PKTINFO_L4PROTO)) return false; - ptr = skb_network_header(skb) + nft_thoff(pkt); + ptr = skb->data + nft_thoff(pkt); } ptr += priv->offset; diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index fccb3cf7749c..6475c7abc1fe 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -78,7 +78,7 @@ static int nft_immediate_init(const struct nft_ctx *ctx, case NFT_GOTO: err = nf_tables_bind_chain(ctx, chain); if (err < 0) - return err; + goto err1; break; default: break; diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c index 1dac28136e6a..18be13fb9b75 100644 --- a/net/nfc/llcp_core.c +++ b/net/nfc/llcp_core.c @@ -145,6 +145,13 @@ static void nfc_llcp_socket_release(struct nfc_llcp_local *local, bool device, static struct nfc_llcp_local *nfc_llcp_local_get(struct nfc_llcp_local *local) { + /* Since using nfc_llcp_local may result in usage of nfc_dev, whenever + * we hold a reference to local, we also need to hold a reference to + * the device to avoid UAF. + */ + if (!nfc_get_device(local->dev->idx)) + return NULL; + kref_get(&local->ref); return local; @@ -177,10 +184,18 @@ static void local_release(struct kref *ref) int nfc_llcp_local_put(struct nfc_llcp_local *local) { + struct nfc_dev *dev; + int ret; + if (local == NULL) return 0; - return kref_put(&local->ref, local_release); + dev = local->dev; + + ret = kref_put(&local->ref, local_release); + nfc_put_device(dev); + + return ret; } static struct nfc_llcp_sock *nfc_llcp_sock_get(struct nfc_llcp_local *local, @@ -959,8 +974,17 @@ static void nfc_llcp_recv_connect(struct nfc_llcp_local *local, } new_sock = nfc_llcp_sock(new_sk); - new_sock->dev = local->dev; + new_sock->local = nfc_llcp_local_get(local); + if (!new_sock->local) { + reason = LLCP_DM_REJ; + sock_put(&new_sock->sk); + release_sock(&sock->sk); + sock_put(&sock->sk); + goto fail; + } + + new_sock->dev = local->dev; new_sock->rw = sock->rw; new_sock->miux = sock->miux; new_sock->nfc_protocol = sock->nfc_protocol; @@ -1597,7 +1621,16 @@ int nfc_llcp_register_device(struct nfc_dev *ndev) if (local == NULL) return -ENOMEM; - local->dev = ndev; + /* As we are going to initialize local's refcount, we need to get the + * nfc_dev to avoid UAF, otherwise there is no point in continuing. + * See nfc_llcp_local_get(). + */ + local->dev = nfc_get_device(ndev->idx); + if (!local->dev) { + kfree(local); + return -ENODEV; + } + INIT_LIST_HEAD(&local->list); kref_init(&local->ref); mutex_init(&local->sdp_lock); diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c index 645677f84dba..819157bbb5a2 100644 --- a/net/nfc/llcp_sock.c +++ b/net/nfc/llcp_sock.c @@ -796,6 +796,11 @@ static int llcp_sock_sendmsg(struct socket *sock, struct msghdr *msg, } if (sk->sk_type == SOCK_DGRAM) { + if (sk->sk_state != LLCP_BOUND) { + release_sock(sk); + return -ENOTCONN; + } + DECLARE_SOCKADDR(struct sockaddr_nfc_llcp *, addr, msg->msg_name); diff --git a/net/qrtr/ns.c b/net/qrtr/ns.c index b1db0b519179..abb0c70ffc8b 100644 --- a/net/qrtr/ns.c +++ b/net/qrtr/ns.c @@ -512,7 +512,9 @@ static int ctrl_cmd_del_server(struct sockaddr_qrtr *from, if (!node) return -ENOENT; - return server_del(node, port, true); + server_del(node, port, true); + + return 0; } static int ctrl_cmd_new_lookup(struct sockaddr_qrtr *from, diff --git a/net/rfkill/rfkill-gpio.c b/net/rfkill/rfkill-gpio.c index 5a81505fba9a..4e32d659524e 100644 --- a/net/rfkill/rfkill-gpio.c +++ b/net/rfkill/rfkill-gpio.c @@ -126,6 +126,14 @@ static int rfkill_gpio_probe(struct platform_device *pdev) return -EINVAL; } + ret = gpiod_direction_output(rfkill->reset_gpio, true); + if (ret) + return ret; + + ret = gpiod_direction_output(rfkill->shutdown_gpio, true); + if (ret) + return ret; + rfkill->rfkill_dev = rfkill_alloc(rfkill->name, &pdev->dev, rfkill->type, &rfkill_gpio_ops, rfkill); diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 0cc5a4e19900..ef81d019b20f 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -182,21 +182,47 @@ void rose_kill_by_neigh(struct rose_neigh *neigh) */ static void rose_kill_by_device(struct net_device *dev) { - struct sock *s; + struct sock *sk, *array[16]; + struct rose_sock *rose; + bool rescan; + int i, cnt; +start: + rescan = false; + cnt = 0; spin_lock_bh(&rose_list_lock); - sk_for_each(s, &rose_list) { - struct rose_sock *rose = rose_sk(s); + sk_for_each(sk, &rose_list) { + rose = rose_sk(sk); + if (rose->device == dev) { + if (cnt == ARRAY_SIZE(array)) { + rescan = true; + break; + } + sock_hold(sk); + array[cnt++] = sk; + } + } + spin_unlock_bh(&rose_list_lock); + for (i = 0; i < cnt; i++) { + sk = array[cnt]; + rose = rose_sk(sk); + lock_sock(sk); + spin_lock_bh(&rose_list_lock); if (rose->device == dev) { - rose_disconnect(s, ENETUNREACH, ROSE_OUT_OF_ORDER, 0); + rose_disconnect(sk, ENETUNREACH, ROSE_OUT_OF_ORDER, 0); if (rose->neighbour) rose->neighbour->use--; netdev_put(rose->device, &rose->dev_tracker); rose->device = NULL; } + spin_unlock_bh(&rose_list_lock); + release_sock(sk); + sock_put(sk); + cond_resched(); } - spin_unlock_bh(&rose_list_lock); + if (rescan) + goto start; } /* @@ -656,7 +682,10 @@ static int rose_release(struct socket *sock) break; } + spin_lock_bh(&rose_list_lock); netdev_put(rose->device, &rose->dev_tracker); + rose->device = NULL; + spin_unlock_bh(&rose_list_lock); sock->sk = NULL; release_sock(sk); sock_put(sk); @@ -1315,9 +1344,11 @@ static int rose_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) case TIOCINQ: { struct sk_buff *skb; long amount = 0L; - /* These two are safe on a single CPU system as only user tasks fiddle here */ + + spin_lock_irq(&sk->sk_receive_queue.lock); if ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) amount = skb->len; + spin_unlock_irq(&sk->sk_receive_queue.lock); return put_user(amount, (unsigned int __user *) argp); } diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index b3f4a503ee2b..f69c47945175 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -286,9 +286,31 @@ static bool tcf_ct_flow_is_outdated(const struct flow_offload *flow) !test_bit(NF_FLOW_HW_ESTABLISHED, &flow->flags); } +static void tcf_ct_flow_table_get_ref(struct tcf_ct_flow_table *ct_ft); + +static void tcf_ct_nf_get(struct nf_flowtable *ft) +{ + struct tcf_ct_flow_table *ct_ft = + container_of(ft, struct tcf_ct_flow_table, nf_ft); + + tcf_ct_flow_table_get_ref(ct_ft); +} + +static void tcf_ct_flow_table_put(struct tcf_ct_flow_table *ct_ft); + +static void tcf_ct_nf_put(struct nf_flowtable *ft) +{ + struct tcf_ct_flow_table *ct_ft = + container_of(ft, struct tcf_ct_flow_table, nf_ft); + + tcf_ct_flow_table_put(ct_ft); +} + static struct nf_flowtable_type flowtable_ct = { .gc = tcf_ct_flow_is_outdated, .action = tcf_ct_flow_table_fill_actions, + .get = tcf_ct_nf_get, + .put = tcf_ct_nf_put, .owner = THIS_MODULE, }; @@ -337,9 +359,13 @@ err_alloc: return err; } +static void tcf_ct_flow_table_get_ref(struct tcf_ct_flow_table *ct_ft) +{ + refcount_inc(&ct_ft->ref); +} + static void tcf_ct_flow_table_cleanup_work(struct work_struct *work) { - struct flow_block_cb *block_cb, *tmp_cb; struct tcf_ct_flow_table *ct_ft; struct flow_block *block; @@ -347,13 +373,9 @@ static void tcf_ct_flow_table_cleanup_work(struct work_struct *work) rwork); nf_flow_table_free(&ct_ft->nf_ft); - /* Remove any remaining callbacks before cleanup */ block = &ct_ft->nf_ft.flow_block; down_write(&ct_ft->nf_ft.flow_block_lock); - list_for_each_entry_safe(block_cb, tmp_cb, &block->cb_list, list) { - list_del(&block_cb->list); - flow_block_cb_free(block_cb); - } + WARN_ON(!list_empty(&block->cb_list)); up_write(&ct_ft->nf_ft.flow_block_lock); kfree(ct_ft); diff --git a/net/sched/em_text.c b/net/sched/em_text.c index 6f3c1fb2fb44..f176afb70559 100644 --- a/net/sched/em_text.c +++ b/net/sched/em_text.c @@ -97,8 +97,10 @@ retry: static void em_text_destroy(struct tcf_ematch *m) { - if (EM_TEXT_PRIV(m) && EM_TEXT_PRIV(m)->config) + if (EM_TEXT_PRIV(m) && EM_TEXT_PRIV(m)->config) { textsearch_destroy(EM_TEXT_PRIV(m)->config); + kfree(EM_TEXT_PRIV(m)); + } } static int em_text_dump(struct sk_buff *skb, struct tcf_ematch *m) diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c index a584613aca12..5cc376834c57 100644 --- a/net/smc/smc_diag.c +++ b/net/smc/smc_diag.c @@ -153,8 +153,7 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb, .lnk[0].link_id = link->link_id, }; - memcpy(linfo.lnk[0].ibname, - smc->conn.lgr->lnk[0].smcibdev->ibdev->name, + memcpy(linfo.lnk[0].ibname, link->smcibdev->ibdev->name, sizeof(link->smcibdev->ibdev->name)); smc_gid_be16_convert(linfo.lnk[0].gid, link->gid); smc_gid_be16_convert(linfo.lnk[0].peer_gid, link->peer_gid); diff --git a/net/socket.c b/net/socket.c index 3379c64217a4..ed3df2f749bf 100644 --- a/net/socket.c +++ b/net/socket.c @@ -757,6 +757,7 @@ int sock_sendmsg(struct socket *sock, struct msghdr *msg) { struct sockaddr_storage *save_addr = (struct sockaddr_storage *)msg->msg_name; struct sockaddr_storage address; + int save_len = msg->msg_namelen; int ret; if (msg->msg_name) { @@ -766,6 +767,7 @@ int sock_sendmsg(struct socket *sock, struct msghdr *msg) ret = __sock_sendmsg(sock, msg); msg->msg_name = save_addr; + msg->msg_namelen = save_len; return ret; } @@ -2161,10 +2163,9 @@ int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags, struct sockaddr_storage address; int err; struct msghdr msg; - struct iovec iov; int fput_needed; - err = import_single_range(ITER_SOURCE, buff, len, &iov, &msg.msg_iter); + err = import_ubuf(ITER_SOURCE, buff, len, &msg.msg_iter); if (unlikely(err)) return err; sock = sockfd_lookup_light(fd, &err, &fput_needed); @@ -2226,11 +2227,10 @@ int __sys_recvfrom(int fd, void __user *ubuf, size_t size, unsigned int flags, .msg_name = addr ? (struct sockaddr *)&address : NULL, }; struct socket *sock; - struct iovec iov; int err, err2; int fput_needed; - err = import_single_range(ITER_DEST, ubuf, size, &iov, &msg.msg_iter); + err = import_ubuf(ITER_DEST, ubuf, size, &msg.msg_iter); if (unlikely(err)) return err; sock = sockfd_lookup_light(fd, &err, &fput_needed); diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index 7bfe7d9a32aa..04534ea537c8 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -40,9 +40,6 @@ static unsigned long number_cred_unused; static struct cred machine_cred = { .usage = ATOMIC_INIT(1), -#ifdef CONFIG_DEBUG_CREDENTIALS - .magic = CRED_MAGIC, -#endif }; /* diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index fee83d1024bc..1b71055fc391 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -654,9 +654,8 @@ static bool svc_alloc_arg(struct svc_rqst *rqstp) } for (filled = 0; filled < pages; filled = ret) { - ret = alloc_pages_bulk_array_node(GFP_KERNEL, - rqstp->rq_pool->sp_id, - pages, rqstp->rq_pages); + ret = alloc_pages_bulk_array(GFP_KERNEL, pages, + rqstp->rq_pages); if (ret > filled) /* Made progress, don't sleep yet */ continue; diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index c8e162c9d1df..6df246b53260 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -843,7 +843,7 @@ static s64 virtio_transport_has_space(struct vsock_sock *vsk) struct virtio_vsock_sock *vvs = vsk->trans; s64 bytes; - bytes = vvs->peer_buf_alloc - (vvs->tx_cnt - vvs->peer_fwd_cnt); + bytes = (s64)vvs->peer_buf_alloc - (vvs->tx_cnt - vvs->peer_fwd_cnt); if (bytes < 0) bytes = 0; diff --git a/net/wireless/certs/wens.hex b/net/wireless/certs/wens.hex new file mode 100644 index 000000000000..0d50369bede9 --- /dev/null +++ b/net/wireless/certs/wens.hex @@ -0,0 +1,87 @@ +/* Chen-Yu Tsai's regdb certificate */ +0x30, 0x82, 0x02, 0xa7, 0x30, 0x82, 0x01, 0x8f, +0x02, 0x14, 0x61, 0xc0, 0x38, 0x65, 0x1a, 0xab, +0xdc, 0xf9, 0x4b, 0xd0, 0xac, 0x7f, 0xf0, 0x6c, +0x72, 0x48, 0xdb, 0x18, 0xc6, 0x00, 0x30, 0x0d, +0x06, 0x09, 0x2a, 0x86, 0x48, 0x86, 0xf7, 0x0d, +0x01, 0x01, 0x0b, 0x05, 0x00, 0x30, 0x0f, 0x31, +0x0d, 0x30, 0x0b, 0x06, 0x03, 0x55, 0x04, 0x03, +0x0c, 0x04, 0x77, 0x65, 0x6e, 0x73, 0x30, 0x20, +0x17, 0x0d, 0x32, 0x33, 0x31, 0x32, 0x30, 0x31, +0x30, 0x37, 0x34, 0x31, 0x31, 0x34, 0x5a, 0x18, +0x0f, 0x32, 0x31, 0x32, 0x33, 0x31, 0x31, 0x30, +0x37, 0x30, 0x37, 0x34, 0x31, 0x31, 0x34, 0x5a, +0x30, 0x0f, 0x31, 0x0d, 0x30, 0x0b, 0x06, 0x03, +0x55, 0x04, 0x03, 0x0c, 0x04, 0x77, 0x65, 0x6e, +0x73, 0x30, 0x82, 0x01, 0x22, 0x30, 0x0d, 0x06, +0x09, 0x2a, 0x86, 0x48, 0x86, 0xf7, 0x0d, 0x01, +0x01, 0x01, 0x05, 0x00, 0x03, 0x82, 0x01, 0x0f, +0x00, 0x30, 0x82, 0x01, 0x0a, 0x02, 0x82, 0x01, +0x01, 0x00, 0xa9, 0x7a, 0x2c, 0x78, 0x4d, 0xa7, +0x19, 0x2d, 0x32, 0x52, 0xa0, 0x2e, 0x6c, 0xef, +0x88, 0x7f, 0x15, 0xc5, 0xb6, 0x69, 0x54, 0x16, +0x43, 0x14, 0x79, 0x53, 0xb7, 0xae, 0x88, 0xfe, +0xc0, 0xb7, 0x5d, 0x47, 0x8e, 0x1a, 0xe1, 0xef, +0xb3, 0x90, 0x86, 0xda, 0xd3, 0x64, 0x81, 0x1f, +0xce, 0x5d, 0x9e, 0x4b, 0x6e, 0x58, 0x02, 0x3e, +0xb2, 0x6f, 0x5e, 0x42, 0x47, 0x41, 0xf4, 0x2c, +0xb8, 0xa8, 0xd4, 0xaa, 0xc0, 0x0e, 0xe6, 0x48, +0xf0, 0xa8, 0xce, 0xcb, 0x08, 0xae, 0x37, 0xaf, +0xf6, 0x40, 0x39, 0xcb, 0x55, 0x6f, 0x5b, 0x4f, +0x85, 0x34, 0xe6, 0x69, 0x10, 0x50, 0x72, 0x5e, +0x4e, 0x9d, 0x4c, 0xba, 0x38, 0x36, 0x0d, 0xce, +0x73, 0x38, 0xd7, 0x27, 0x02, 0x2a, 0x79, 0x03, +0xe1, 0xac, 0xcf, 0xb0, 0x27, 0x85, 0x86, 0x93, +0x17, 0xab, 0xec, 0x42, 0x77, 0x37, 0x65, 0x8a, +0x44, 0xcb, 0xd6, 0x42, 0x93, 0x92, 0x13, 0xe3, +0x39, 0x45, 0xc5, 0x6e, 0x00, 0x4a, 0x7f, 0xcb, +0x42, 0x17, 0x2b, 0x25, 0x8c, 0xb8, 0x17, 0x3b, +0x15, 0x36, 0x59, 0xde, 0x42, 0xce, 0x21, 0xe6, +0xb6, 0xc7, 0x6e, 0x5e, 0x26, 0x1f, 0xf7, 0x8a, +0x57, 0x9e, 0xa5, 0x96, 0x72, 0xb7, 0x02, 0x32, +0xeb, 0x07, 0x2b, 0x73, 0xe2, 0x4f, 0x66, 0x58, +0x9a, 0xeb, 0x0f, 0x07, 0xb6, 0xab, 0x50, 0x8b, +0xc3, 0x8f, 0x17, 0xfa, 0x0a, 0x99, 0xc2, 0x16, +0x25, 0xbf, 0x2d, 0x6b, 0x1a, 0xaa, 0xe6, 0x3e, +0x5f, 0xeb, 0x6d, 0x9b, 0x5d, 0x4d, 0x42, 0x83, +0x2d, 0x39, 0xb8, 0xc9, 0xac, 0xdb, 0x3a, 0x91, +0x50, 0xdf, 0xbb, 0xb1, 0x76, 0x6d, 0x15, 0x73, +0xfd, 0xc6, 0xe6, 0x6b, 0x71, 0x9e, 0x67, 0x36, +0x22, 0x83, 0x79, 0xb1, 0xd6, 0xb8, 0x84, 0x52, +0xaf, 0x96, 0x5b, 0xc3, 0x63, 0x02, 0x4e, 0x78, +0x70, 0x57, 0x02, 0x03, 0x01, 0x00, 0x01, 0x30, +0x0d, 0x06, 0x09, 0x2a, 0x86, 0x48, 0x86, 0xf7, +0x0d, 0x01, 0x01, 0x0b, 0x05, 0x00, 0x03, 0x82, +0x01, 0x01, 0x00, 0x24, 0x28, 0xee, 0x22, 0x74, +0x7f, 0x7c, 0xfa, 0x6c, 0x1f, 0xb3, 0x18, 0xd1, +0xc2, 0x3d, 0x7d, 0x29, 0x42, 0x88, 0xad, 0x82, +0xa5, 0xb1, 0x8a, 0x05, 0xd0, 0xec, 0x5c, 0x91, +0x20, 0xf6, 0x82, 0xfd, 0xd5, 0x67, 0x60, 0x5f, +0x31, 0xf5, 0xbd, 0x88, 0x91, 0x70, 0xbd, 0xb8, +0xb9, 0x8c, 0x88, 0xfe, 0x53, 0xc9, 0x54, 0x9b, +0x43, 0xc4, 0x7a, 0x43, 0x74, 0x6b, 0xdd, 0xb0, +0xb1, 0x3b, 0x33, 0x45, 0x46, 0x78, 0xa3, 0x1c, +0xef, 0x54, 0x68, 0xf7, 0x85, 0x9c, 0xe4, 0x51, +0x6f, 0x06, 0xaf, 0x81, 0xdb, 0x2a, 0x7b, 0x7b, +0x6f, 0xa8, 0x9c, 0x67, 0xd8, 0xcb, 0xc9, 0x91, +0x40, 0x00, 0xae, 0xd9, 0xa1, 0x9f, 0xdd, 0xa6, +0x43, 0x0e, 0x28, 0x7b, 0xaa, 0x1b, 0xe9, 0x84, +0xdb, 0x76, 0x64, 0x42, 0x70, 0xc9, 0xc0, 0xeb, +0xae, 0x84, 0x11, 0x16, 0x68, 0x4e, 0x84, 0x9e, +0x7e, 0x92, 0x36, 0xee, 0x1c, 0x3b, 0x08, 0x63, +0xeb, 0x79, 0x84, 0x15, 0x08, 0x9d, 0xaf, 0xc8, +0x9a, 0xc7, 0x34, 0xd3, 0x94, 0x4b, 0xd1, 0x28, +0x97, 0xbe, 0xd1, 0x45, 0x75, 0xdc, 0x35, 0x62, +0xac, 0x1d, 0x1f, 0xb7, 0xb7, 0x15, 0x87, 0xc8, +0x98, 0xc0, 0x24, 0x31, 0x56, 0x8d, 0xed, 0xdb, +0x06, 0xc6, 0x46, 0xbf, 0x4b, 0x6d, 0xa6, 0xd5, +0xab, 0xcc, 0x60, 0xfc, 0xe5, 0x37, 0xb6, 0x53, +0x7d, 0x58, 0x95, 0xa9, 0x56, 0xc7, 0xf7, 0xee, +0xc3, 0xa0, 0x76, 0xf7, 0x65, 0x4d, 0x53, 0xfa, +0xff, 0x5f, 0x76, 0x33, 0x5a, 0x08, 0xfa, 0x86, +0x92, 0x5a, 0x13, 0xfa, 0x1a, 0xfc, 0xf2, 0x1b, +0x8c, 0x7f, 0x42, 0x6d, 0xb7, 0x7e, 0xb7, 0xb4, +0xf0, 0xc7, 0x83, 0xbb, 0xa2, 0x81, 0x03, 0x2d, +0xd4, 0x2a, 0x63, 0x3f, 0xf7, 0x31, 0x2e, 0x40, +0x33, 0x5c, 0x46, 0xbc, 0x9b, 0xc1, 0x05, 0xa5, +0x45, 0x4e, 0xc3, diff --git a/samples/vfio-mdev/mtty.c b/samples/vfio-mdev/mtty.c index 69ba0281f9e0..2284b3751240 100644 --- a/samples/vfio-mdev/mtty.c +++ b/samples/vfio-mdev/mtty.c @@ -234,10 +234,10 @@ static void mtty_trigger_interrupt(struct mdev_state *mdev_state) if (is_msi(mdev_state)) { if (mdev_state->msi_evtfd) - eventfd_signal(mdev_state->msi_evtfd, 1); + eventfd_signal(mdev_state->msi_evtfd); } else if (is_intx(mdev_state)) { if (mdev_state->intx_evtfd && !mdev_state->intx_mask) { - eventfd_signal(mdev_state->intx_evtfd, 1); + eventfd_signal(mdev_state->intx_evtfd); mdev_state->intx_mask = true; } } diff --git a/scripts/Makefile.vdsoinst b/scripts/Makefile.vdsoinst index 1022d9fdd976..c477d17b0aa5 100644 --- a/scripts/Makefile.vdsoinst +++ b/scripts/Makefile.vdsoinst @@ -22,7 +22,7 @@ $$(dest): $$(src) FORCE # Some architectures create .build-id symlinks ifneq ($(filter arm sparc x86, $(SRCARCH)),) -link := $(install-dir)/.build-id/$$(shell $(READELF) -n $$(src) | sed -n 's@^.*Build ID: \(..\)\(.*\)@\1/\2@p') +link := $(install-dir)/.build-id/$$(shell $(READELF) -n $$(src) | sed -n 's@^.*Build ID: \(..\)\(.*\)@\1/\2@p').debug __default: $$(link) $$(link): $$(dest) FORCE diff --git a/scripts/clang-tools/gen_compile_commands.py b/scripts/clang-tools/gen_compile_commands.py index 180952fb91c1..5dea4479240b 100755 --- a/scripts/clang-tools/gen_compile_commands.py +++ b/scripts/clang-tools/gen_compile_commands.py @@ -64,7 +64,7 @@ def parse_arguments(): args = parser.parse_args() return (args.log_level, - os.path.abspath(args.directory), + os.path.realpath(args.directory), args.output, args.ar, args.paths if len(args.paths) > 0 else [args.directory]) @@ -172,8 +172,8 @@ def process_line(root_directory, command_prefix, file_path): # by Make, so this code replaces the escaped version with '#'. prefix = command_prefix.replace('\#', '#').replace('$(pound)', '#') - # Use os.path.abspath() to normalize the path resolving '.' and '..' . - abs_path = os.path.abspath(os.path.join(root_directory, file_path)) + # Return the canonical path, eliminating any symbolic links encountered in the path. + abs_path = os.path.realpath(os.path.join(root_directory, file_path)) if not os.path.exists(abs_path): raise ValueError('File %s not found' % abs_path) return { diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl index 16d8ac6005b6..ee1aed7e090c 100755 --- a/scripts/get_maintainer.pl +++ b/scripts/get_maintainer.pl @@ -20,6 +20,7 @@ use Getopt::Long qw(:config no_auto_abbrev); use Cwd; use File::Find; use File::Spec::Functions; +use open qw(:std :encoding(UTF-8)); my $cur_path = fastgetcwd() . '/'; my $lk_path = "./"; @@ -445,7 +446,7 @@ sub maintainers_in_file { my $text = do { local($/) ; <$f> }; close($f); - my @poss_addr = $text =~ m$[A-Za-zÀ-ÿ\"\' \,\.\+-]*\s*[\,]*\s*[\(\<\{]{0,1}[A-Za-z0-9_\.\+-]+\@[A-Za-z0-9\.-]+\.[A-Za-z0-9]+[\)\>\}]{0,1}$g; + my @poss_addr = $text =~ m$[\p{L}\"\' \,\.\+-]*\s*[\,]*\s*[\(\<\{]{0,1}[A-Za-z0-9_\.\+-]+\@[A-Za-z0-9\.-]+\.[A-Za-z0-9]+[\)\>\}]{0,1}$g; push(@file_emails, clean_file_emails(@poss_addr)); } } @@ -1152,6 +1153,17 @@ sub top_of_kernel_tree { return 0; } +sub escape_name { + my ($name) = @_; + + if ($name =~ /[^\w \-]/ai) { ##has "must quote" chars + $name =~ s/(?<!\\)"/\\"/g; ##escape quotes + $name = "\"$name\""; + } + + return $name; +} + sub parse_email { my ($formatted_email) = @_; @@ -1169,13 +1181,9 @@ sub parse_email { $name =~ s/^\s+|\s+$//g; $name =~ s/^\"|\"$//g; + $name = escape_name($name); $address =~ s/^\s+|\s+$//g; - if ($name =~ /[^\w \-]/i) { ##has "must quote" chars - $name =~ s/(?<!\\)"/\\"/g; ##escape quotes - $name = "\"$name\""; - } - return ($name, $address); } @@ -1186,13 +1194,9 @@ sub format_email { $name =~ s/^\s+|\s+$//g; $name =~ s/^\"|\"$//g; + $name = escape_name($name); $address =~ s/^\s+|\s+$//g; - if ($name =~ /[^\w \-]/i) { ##has "must quote" chars - $name =~ s/(?<!\\)"/\\"/g; ##escape quotes - $name = "\"$name\""; - } - if ($usename) { if ("$name" eq "") { $formatted_email = "$address"; @@ -2458,17 +2462,23 @@ sub clean_file_emails { foreach my $email (@file_emails) { $email =~ s/[\(\<\{]{0,1}([A-Za-z0-9_\.\+-]+\@[A-Za-z0-9\.-]+)[\)\>\}]{0,1}/\<$1\>/g; my ($name, $address) = parse_email($email); - if ($name eq '"[,\.]"') { - $name = ""; - } - my @nw = split(/[^A-Za-zÀ-ÿ\'\,\.\+-]/, $name); + # Strip quotes for easier processing, format_email will add them back + $name =~ s/^"(.*)"$/$1/; + + # Split into name-like parts and remove stray punctuation particles + my @nw = split(/[^\p{L}\'\,\.\+-]/, $name); + @nw = grep(!/^[\'\,\.\+-]$/, @nw); + + # Make a best effort to extract the name, and only the name, by taking + # only the last two names, or in the case of obvious initials, the last + # three names. if (@nw > 2) { my $first = $nw[@nw - 3]; my $middle = $nw[@nw - 2]; my $last = $nw[@nw - 1]; - if (((length($first) == 1 && $first =~ m/[A-Za-z]/) || + if (((length($first) == 1 && $first =~ m/\p{L}/) || (length($first) == 2 && substr($first, -1) eq ".")) || (length($middle) == 1 || (length($middle) == 2 && substr($middle, -1) eq "."))) { @@ -2476,18 +2486,16 @@ sub clean_file_emails { } else { $name = "$middle $last"; } + } else { + $name = "@nw"; } if (substr($name, -1) =~ /[,\.]/) { $name = substr($name, 0, length($name) - 1); - } elsif (substr($name, -2) =~ /[,\.]"/) { - $name = substr($name, 0, length($name) - 2) . '"'; } if (substr($name, 0, 1) =~ /[,\.]/) { $name = substr($name, 1, length($name) - 1); - } elsif (substr($name, 0, 2) =~ /"[,\.]/) { - $name = '"' . substr($name, 2, length($name) - 2); } my $fmt_email = format_email($name, $address, $email_usename); diff --git a/scripts/sign-file.c b/scripts/sign-file.c index 598ef5465f82..3edb156ae52c 100644 --- a/scripts/sign-file.c +++ b/scripts/sign-file.c @@ -322,7 +322,7 @@ int main(int argc, char **argv) CMS_NOSMIMECAP | use_keyid | use_signed_attrs), "CMS_add1_signer"); - ERR(CMS_final(cms, bm, NULL, CMS_NOCERTS | CMS_BINARY) < 0, + ERR(CMS_final(cms, bm, NULL, CMS_NOCERTS | CMS_BINARY) != 1, "CMS_final"); #else @@ -341,10 +341,10 @@ int main(int argc, char **argv) b = BIO_new_file(sig_file_name, "wb"); ERR(!b, "%s", sig_file_name); #ifndef USE_PKCS7 - ERR(i2d_CMS_bio_stream(b, cms, NULL, 0) < 0, + ERR(i2d_CMS_bio_stream(b, cms, NULL, 0) != 1, "%s", sig_file_name); #else - ERR(i2d_PKCS7_bio(b, pkcs7) < 0, + ERR(i2d_PKCS7_bio(b, pkcs7) != 1, "%s", sig_file_name); #endif BIO_free(b); @@ -374,9 +374,9 @@ int main(int argc, char **argv) if (!raw_sig) { #ifndef USE_PKCS7 - ERR(i2d_CMS_bio_stream(bd, cms, NULL, 0) < 0, "%s", dest_name); + ERR(i2d_CMS_bio_stream(bd, cms, NULL, 0) != 1, "%s", dest_name); #else - ERR(i2d_PKCS7_bio(bd, pkcs7) < 0, "%s", dest_name); + ERR(i2d_PKCS7_bio(bd, pkcs7) != 1, "%s", dest_name); #endif } else { BIO *b; @@ -396,7 +396,7 @@ int main(int argc, char **argv) ERR(BIO_write(bd, &sig_info, sizeof(sig_info)) < 0, "%s", dest_name); ERR(BIO_write(bd, magic_number, sizeof(magic_number) - 1) < 0, "%s", dest_name); - ERR(BIO_free(bd) < 0, "%s", dest_name); + ERR(BIO_free(bd) != 1, "%s", dest_name); /* Finally, if we're signing in place, replace the original. */ if (replace_orig) diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c index 38650e52ef57..2d9f2a4b4519 100644 --- a/security/apparmor/apparmorfs.c +++ b/security/apparmor/apparmorfs.c @@ -2373,6 +2373,7 @@ static struct aa_sfs_entry aa_sfs_entry_policy[] = { static struct aa_sfs_entry aa_sfs_entry_mount[] = { AA_SFS_FILE_STRING("mask", "mount umount pivot_root"), + AA_SFS_FILE_STRING("move_mount", "detached"), { } }; diff --git a/security/apparmor/mount.c b/security/apparmor/mount.c index fb30204c761a..49fe8da6fea4 100644 --- a/security/apparmor/mount.c +++ b/security/apparmor/mount.c @@ -499,6 +499,10 @@ int aa_move_mount(const struct cred *subj_cred, error = -ENOMEM; if (!to_buffer || !from_buffer) goto out; + + if (!our_mnt(from_path->mnt)) + /* moving a mount detached from the namespace */ + from_path = NULL; error = fn_for_each_confined(label, profile, match_mnt(subj_cred, profile, to_path, to_buffer, from_path, from_buffer, diff --git a/security/keys/gc.c b/security/keys/gc.c index 3c90807476eb..eaddaceda14e 100644 --- a/security/keys/gc.c +++ b/security/keys/gc.c @@ -67,6 +67,19 @@ void key_schedule_gc(time64_t gc_at) } /* + * Set the expiration time on a key. + */ +void key_set_expiry(struct key *key, time64_t expiry) +{ + key->expiry = expiry; + if (expiry != TIME64_MAX) { + if (!(key->type->flags & KEY_TYPE_INSTANT_REAP)) + expiry += key_gc_delay; + key_schedule_gc(expiry); + } +} + +/* * Schedule a dead links collection run. */ void key_schedule_gc_links(void) @@ -176,7 +189,6 @@ static void key_garbage_collector(struct work_struct *work) static u8 gc_state; /* Internal persistent state */ #define KEY_GC_REAP_AGAIN 0x01 /* - Need another cycle */ #define KEY_GC_REAPING_LINKS 0x02 /* - We need to reap links */ -#define KEY_GC_SET_TIMER 0x04 /* - We need to restart the timer */ #define KEY_GC_REAPING_DEAD_1 0x10 /* - We need to mark dead keys */ #define KEY_GC_REAPING_DEAD_2 0x20 /* - We need to reap dead key links */ #define KEY_GC_REAPING_DEAD_3 0x40 /* - We need to reap dead keys */ @@ -184,21 +196,17 @@ static void key_garbage_collector(struct work_struct *work) struct rb_node *cursor; struct key *key; - time64_t new_timer, limit; + time64_t new_timer, limit, expiry; kenter("[%lx,%x]", key_gc_flags, gc_state); limit = ktime_get_real_seconds(); - if (limit > key_gc_delay) - limit -= key_gc_delay; - else - limit = key_gc_delay; /* Work out what we're going to be doing in this pass */ gc_state &= KEY_GC_REAPING_DEAD_1 | KEY_GC_REAPING_DEAD_2; gc_state <<= 1; if (test_and_clear_bit(KEY_GC_KEY_EXPIRED, &key_gc_flags)) - gc_state |= KEY_GC_REAPING_LINKS | KEY_GC_SET_TIMER; + gc_state |= KEY_GC_REAPING_LINKS; if (test_and_clear_bit(KEY_GC_REAP_KEYTYPE, &key_gc_flags)) gc_state |= KEY_GC_REAPING_DEAD_1; @@ -233,8 +241,11 @@ continue_scanning: } } - if (gc_state & KEY_GC_SET_TIMER) { - if (key->expiry > limit && key->expiry < new_timer) { + expiry = key->expiry; + if (expiry != TIME64_MAX) { + if (!(key->type->flags & KEY_TYPE_INSTANT_REAP)) + expiry += key_gc_delay; + if (expiry > limit && expiry < new_timer) { kdebug("will expire %x in %lld", key_serial(key), key->expiry - limit); new_timer = key->expiry; @@ -276,7 +287,7 @@ maybe_resched: */ kdebug("pass complete"); - if (gc_state & KEY_GC_SET_TIMER && new_timer != (time64_t)TIME64_MAX) { + if (new_timer != TIME64_MAX) { new_timer += key_gc_delay; key_schedule_gc(new_timer); } diff --git a/security/keys/internal.h b/security/keys/internal.h index 471cf36dedc0..2cffa6dc8255 100644 --- a/security/keys/internal.h +++ b/security/keys/internal.h @@ -167,6 +167,7 @@ extern unsigned key_gc_delay; extern void keyring_gc(struct key *keyring, time64_t limit); extern void keyring_restriction_gc(struct key *keyring, struct key_type *dead_type); +void key_set_expiry(struct key *key, time64_t expiry); extern void key_schedule_gc(time64_t gc_at); extern void key_schedule_gc_links(void); extern void key_gc_keytype(struct key_type *ktype); @@ -215,10 +216,18 @@ extern struct key *key_get_instantiation_authkey(key_serial_t target_id); */ static inline bool key_is_dead(const struct key *key, time64_t limit) { + time64_t expiry = key->expiry; + + if (expiry != TIME64_MAX) { + if (!(key->type->flags & KEY_TYPE_INSTANT_REAP)) + expiry += key_gc_delay; + if (expiry <= limit) + return true; + } + return key->flags & ((1 << KEY_FLAG_DEAD) | (1 << KEY_FLAG_INVALIDATED)) || - (key->expiry > 0 && key->expiry <= limit) || key->domain_tag->removed; } diff --git a/security/keys/key.c b/security/keys/key.c index 0260a1902922..5b10641debd5 100644 --- a/security/keys/key.c +++ b/security/keys/key.c @@ -294,6 +294,7 @@ struct key *key_alloc(struct key_type *type, const char *desc, key->uid = uid; key->gid = gid; key->perm = perm; + key->expiry = TIME64_MAX; key->restrict_link = restrict_link; key->last_used_at = ktime_get_real_seconds(); @@ -463,10 +464,7 @@ static int __key_instantiate_and_link(struct key *key, if (authkey) key_invalidate(authkey); - if (prep->expiry != TIME64_MAX) { - key->expiry = prep->expiry; - key_schedule_gc(prep->expiry + key_gc_delay); - } + key_set_expiry(key, prep->expiry); } } @@ -606,8 +604,7 @@ int key_reject_and_link(struct key *key, atomic_inc(&key->user->nikeys); mark_key_instantiated(key, -error); notify_key(key, NOTIFY_KEY_INSTANTIATED, -error); - key->expiry = ktime_get_real_seconds() + timeout; - key_schedule_gc(key->expiry + key_gc_delay); + key_set_expiry(key, ktime_get_real_seconds() + timeout); if (test_and_clear_bit(KEY_FLAG_USER_CONSTRUCT, &key->flags)) awaken = 1; @@ -723,16 +720,14 @@ found_kernel_type: void key_set_timeout(struct key *key, unsigned timeout) { - time64_t expiry = 0; + time64_t expiry = TIME64_MAX; /* make the changes with the locks held to prevent races */ down_write(&key->sem); if (timeout > 0) expiry = ktime_get_real_seconds() + timeout; - - key->expiry = expiry; - key_schedule_gc(key->expiry + key_gc_delay); + key_set_expiry(key, expiry); up_write(&key->sem); } diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c index 19be69fa4d05..10ba439968f7 100644 --- a/security/keys/keyctl.c +++ b/security/keys/keyctl.c @@ -1252,12 +1252,11 @@ long keyctl_instantiate_key(key_serial_t id, key_serial_t ringid) { if (_payload && plen) { - struct iovec iov; struct iov_iter from; int ret; - ret = import_single_range(ITER_SOURCE, (void __user *)_payload, plen, - &iov, &from); + ret = import_ubuf(ITER_SOURCE, (void __user *)_payload, plen, + &from); if (unlikely(ret)) return ret; diff --git a/security/keys/proc.c b/security/keys/proc.c index d0cde6685627..4f4e2c1824f1 100644 --- a/security/keys/proc.c +++ b/security/keys/proc.c @@ -198,7 +198,7 @@ static int proc_keys_show(struct seq_file *m, void *v) /* come up with a suitable timeout value */ expiry = READ_ONCE(key->expiry); - if (expiry == 0) { + if (expiry == TIME64_MAX) { memcpy(xbuf, "perm", 5); } else if (now >= expiry) { memcpy(xbuf, "expd", 5); diff --git a/security/security.c b/security/security.c index dcb3e7014f9b..2a7fc7881cbc 100644 --- a/security/security.c +++ b/security/security.c @@ -2580,13 +2580,7 @@ int security_kernfs_init_security(struct kernfs_node *kn_dir, */ int security_file_permission(struct file *file, int mask) { - int ret; - - ret = call_int_hook(file_permission, 0, file, mask); - if (ret) - return ret; - - return fsnotify_perm(file, mask); + return call_int_hook(file_permission, 0, file, mask); } /** @@ -2837,7 +2831,7 @@ int security_file_open(struct file *file) if (ret) return ret; - return fsnotify_perm(file, MAY_OPEN); + return fsnotify_open_perm(file); } /** diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index feda711c6b7b..340b2bbbb2dd 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -1660,8 +1660,6 @@ static int inode_has_perm(const struct cred *cred, struct inode_security_struct *isec; u32 sid; - validate_creds(cred); - if (unlikely(IS_PRIVATE(inode))) return 0; @@ -3056,8 +3054,6 @@ static int selinux_inode_follow_link(struct dentry *dentry, struct inode *inode, struct inode_security_struct *isec; u32 sid; - validate_creds(cred); - ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = dentry; sid = cred_sid(cred); @@ -3101,8 +3097,6 @@ static int selinux_inode_permission(struct inode *inode, int mask) if (!mask) return 0; - validate_creds(cred); - if (unlikely(IS_PRIVATE(inode))) return 0; diff --git a/sound/pci/hda/cs35l41_hda.c b/sound/pci/hda/cs35l41_hda.c index cbd7d8badf91..92ca2b3b6c92 100644 --- a/sound/pci/hda/cs35l41_hda.c +++ b/sound/pci/hda/cs35l41_hda.c @@ -1826,6 +1826,7 @@ err: if (cs35l41_safe_reset(cs35l41->regmap, cs35l41->hw_cfg.bst_type)) gpiod_set_value_cansleep(cs35l41->reset_gpio, 0); gpiod_put(cs35l41->reset_gpio); + gpiod_put(cs35l41->cs_gpio); acpi_dev_put(cs35l41->dacpi); kfree(cs35l41->acpi_subsystem_id); @@ -1853,6 +1854,7 @@ void cs35l41_hda_remove(struct device *dev) if (cs35l41_safe_reset(cs35l41->regmap, cs35l41->hw_cfg.bst_type)) gpiod_set_value_cansleep(cs35l41->reset_gpio, 0); gpiod_put(cs35l41->reset_gpio); + gpiod_put(cs35l41->cs_gpio); kfree(cs35l41->acpi_subsystem_id); } EXPORT_SYMBOL_NS_GPL(cs35l41_hda_remove, SND_HDA_SCODEC_CS35L41); diff --git a/sound/pci/hda/cs35l41_hda.h b/sound/pci/hda/cs35l41_hda.h index ce3f2bb6ffd0..3d925d677213 100644 --- a/sound/pci/hda/cs35l41_hda.h +++ b/sound/pci/hda/cs35l41_hda.h @@ -35,8 +35,8 @@ struct cs35l41_amp_efi_data { } __packed; enum cs35l41_hda_spk_pos { - CS35l41_LEFT, - CS35l41_RIGHT, + CS35L41_LEFT, + CS35L41_RIGHT, }; enum cs35l41_hda_gpio_function { @@ -50,6 +50,7 @@ struct cs35l41_hda { struct device *dev; struct regmap *regmap; struct gpio_desc *reset_gpio; + struct gpio_desc *cs_gpio; struct cs35l41_hw_cfg hw_cfg; struct hda_codec *codec; diff --git a/sound/pci/hda/cs35l41_hda_property.c b/sound/pci/hda/cs35l41_hda_property.c index c83328971728..c1afb721b4c6 100644 --- a/sound/pci/hda/cs35l41_hda_property.c +++ b/sound/pci/hda/cs35l41_hda_property.c @@ -6,9 +6,301 @@ // // Author: Stefan Binding <sbinding@opensource.cirrus.com> +#include <linux/acpi.h> #include <linux/gpio/consumer.h> #include <linux/string.h> #include "cs35l41_hda_property.h" +#include <linux/spi/spi.h> + +#define MAX_AMPS 4 + +struct cs35l41_config { + const char *ssid; + enum { + SPI, + I2C + } bus; + int num_amps; + enum { + INTERNAL, + EXTERNAL + } boost_type; + u8 channel[MAX_AMPS]; + int reset_gpio_index; /* -1 if no reset gpio */ + int spkid_gpio_index; /* -1 if no spkid gpio */ + int cs_gpio_index; /* -1 if no cs gpio, or cs-gpios already exists, max num amps == 2 */ + int boost_ind_nanohenry; /* Required if boost_type == Internal */ + int boost_peak_milliamp; /* Required if boost_type == Internal */ + int boost_cap_microfarad; /* Required if boost_type == Internal */ +}; + +static const struct cs35l41_config cs35l41_config_table[] = { +/* + * Device 103C89C6 does have _DSD, however it is setup to use the wrong boost type. + * We can override the _DSD to correct the boost type here. + * Since this laptop has valid ACPI, we do not need to handle cs-gpios, since that already exists + * in the ACPI. The Reset GPIO is also valid, so we can use the Reset defined in _DSD. + */ + { "103C89C6", SPI, 2, INTERNAL, { CS35L41_RIGHT, CS35L41_LEFT, 0, 0 }, -1, -1, -1, 1000, 4500, 24 }, + { "104312AF", SPI, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 }, + { "10431433", I2C, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 }, + { "10431463", I2C, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 }, + { "10431473", SPI, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, -1, 0, 1000, 4500, 24 }, + { "10431483", SPI, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, -1, 0, 1000, 4500, 24 }, + { "10431493", SPI, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 }, + { "104314D3", SPI, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 }, + { "104314E3", I2C, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 }, + { "10431503", I2C, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 }, + { "10431533", I2C, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 }, + { "10431573", SPI, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 }, + { "10431663", SPI, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, -1, 0, 1000, 4500, 24 }, + { "104316D3", SPI, 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 0, 0, 0 }, + { "104316F3", SPI, 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 0, 0, 0 }, + { "104317F3", I2C, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 }, + { "10431863", SPI, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 }, + { "104318D3", I2C, 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 0, 0, 0 }, + { "10431C9F", SPI, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 }, + { "10431CAF", SPI, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 }, + { "10431CCF", SPI, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 }, + { "10431CDF", SPI, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 }, + { "10431CEF", SPI, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 }, + { "10431D1F", I2C, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 }, + { "10431DA2", SPI, 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 0, 0, 0 }, + { "10431E02", SPI, 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 0, 0, 0 }, + { "10431EE2", I2C, 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, -1, -1, 0, 0, 0 }, + { "10431F12", I2C, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 }, + { "10431F1F", SPI, 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, -1, 0, 0, 0, 0 }, + { "10431F62", SPI, 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 0, 0, 0 }, + {} +}; + +static int cs35l41_add_gpios(struct cs35l41_hda *cs35l41, struct device *physdev, int reset_gpio, + int spkid_gpio, int cs_gpio_index, int num_amps) +{ + struct acpi_gpio_mapping *gpio_mapping = NULL; + struct acpi_gpio_params *reset_gpio_params = NULL; + struct acpi_gpio_params *spkid_gpio_params = NULL; + struct acpi_gpio_params *cs_gpio_params = NULL; + unsigned int num_entries = 0; + unsigned int reset_index, spkid_index, csgpio_index; + int i; + + /* + * GPIO Mapping only needs to be done once, since it would be available for subsequent amps + */ + if (cs35l41->dacpi->driver_gpios) + return 0; + + if (reset_gpio >= 0) { + reset_index = num_entries; + num_entries++; + } + + if (spkid_gpio >= 0) { + spkid_index = num_entries; + num_entries++; + } + + if ((cs_gpio_index >= 0) && (num_amps == 2)) { + csgpio_index = num_entries; + num_entries++; + } + + if (!num_entries) + return 0; + + /* must include termination entry */ + num_entries++; + + gpio_mapping = devm_kcalloc(physdev, num_entries, sizeof(struct acpi_gpio_mapping), + GFP_KERNEL); + + if (!gpio_mapping) + goto err; + + if (reset_gpio >= 0) { + gpio_mapping[reset_index].name = "reset-gpios"; + reset_gpio_params = devm_kcalloc(physdev, num_amps, sizeof(struct acpi_gpio_params), + GFP_KERNEL); + if (!reset_gpio_params) + goto err; + + for (i = 0; i < num_amps; i++) + reset_gpio_params[i].crs_entry_index = reset_gpio; + + gpio_mapping[reset_index].data = reset_gpio_params; + gpio_mapping[reset_index].size = num_amps; + } + + if (spkid_gpio >= 0) { + gpio_mapping[spkid_index].name = "spk-id-gpios"; + spkid_gpio_params = devm_kcalloc(physdev, num_amps, sizeof(struct acpi_gpio_params), + GFP_KERNEL); + if (!spkid_gpio_params) + goto err; + + for (i = 0; i < num_amps; i++) + spkid_gpio_params[i].crs_entry_index = spkid_gpio; + + gpio_mapping[spkid_index].data = spkid_gpio_params; + gpio_mapping[spkid_index].size = num_amps; + } + + if ((cs_gpio_index >= 0) && (num_amps == 2)) { + gpio_mapping[csgpio_index].name = "cs-gpios"; + /* only one GPIO CS is supported without using _DSD, obtained using index 0 */ + cs_gpio_params = devm_kzalloc(physdev, sizeof(struct acpi_gpio_params), GFP_KERNEL); + if (!cs_gpio_params) + goto err; + + cs_gpio_params->crs_entry_index = cs_gpio_index; + + gpio_mapping[csgpio_index].data = cs_gpio_params; + gpio_mapping[csgpio_index].size = 1; + } + + return devm_acpi_dev_add_driver_gpios(physdev, gpio_mapping); +err: + devm_kfree(physdev, gpio_mapping); + devm_kfree(physdev, reset_gpio_params); + devm_kfree(physdev, spkid_gpio_params); + devm_kfree(physdev, cs_gpio_params); + return -ENOMEM; +} + +static int generic_dsd_config(struct cs35l41_hda *cs35l41, struct device *physdev, int id, + const char *hid) +{ + struct cs35l41_hw_cfg *hw_cfg = &cs35l41->hw_cfg; + const struct cs35l41_config *cfg; + struct gpio_desc *cs_gpiod; + struct spi_device *spi; + bool dsd_found; + int ret; + + for (cfg = cs35l41_config_table; cfg->ssid; cfg++) { + if (!strcasecmp(cfg->ssid, cs35l41->acpi_subsystem_id)) + break; + } + + if (!cfg->ssid) + return -ENOENT; + + if (!cs35l41->dacpi || cs35l41->dacpi != ACPI_COMPANION(physdev)) { + dev_err(cs35l41->dev, "ACPI Device does not match, cannot override _DSD.\n"); + return -ENODEV; + } + + dev_info(cs35l41->dev, "Adding DSD properties for %s\n", cs35l41->acpi_subsystem_id); + + dsd_found = acpi_dev_has_props(cs35l41->dacpi); + + if (!dsd_found) { + ret = cs35l41_add_gpios(cs35l41, physdev, cfg->reset_gpio_index, + cfg->spkid_gpio_index, cfg->cs_gpio_index, + cfg->num_amps); + if (ret) { + dev_err(cs35l41->dev, "Error adding GPIO mapping: %d\n", ret); + return ret; + } + } else if (cfg->reset_gpio_index >= 0 || cfg->spkid_gpio_index >= 0) { + dev_warn(cs35l41->dev, "Cannot add Reset/Speaker ID/SPI CS GPIO Mapping, " + "_DSD already exists.\n"); + } + + if (cfg->bus == SPI) { + cs35l41->index = id; + + /* + * Manually set the Chip Select for the second amp <cs_gpio_index> in the node. + * This is only supported for systems with 2 amps, since we cannot expand the + * default number of chip selects without using cs-gpios + * The CS GPIO must be set high prior to communicating with the first amp (which + * uses a native chip select), to ensure the second amp does not clash with the + * first. + */ + if (IS_ENABLED(CONFIG_SPI) && cfg->cs_gpio_index >= 0) { + spi = to_spi_device(cs35l41->dev); + + if (cfg->num_amps != 2) { + dev_warn(cs35l41->dev, + "Cannot update SPI CS, Number of Amps (%d) != 2\n", + cfg->num_amps); + } else if (dsd_found) { + dev_warn(cs35l41->dev, + "Cannot update SPI CS, _DSD already exists.\n"); + } else { + /* + * This is obtained using driver_gpios, since only one GPIO for CS + * exists, this can be obtained using index 0. + */ + cs_gpiod = gpiod_get_index(physdev, "cs", 0, GPIOD_OUT_LOW); + if (IS_ERR(cs_gpiod)) { + dev_err(cs35l41->dev, + "Unable to get Chip Select GPIO descriptor\n"); + return PTR_ERR(cs_gpiod); + } + if (id == 1) { + spi_set_csgpiod(spi, 0, cs_gpiod); + cs35l41->cs_gpio = cs_gpiod; + } else { + gpiod_set_value_cansleep(cs_gpiod, true); + gpiod_put(cs_gpiod); + } + spi_setup(spi); + } + } + } else { + if (cfg->num_amps > 2) + /* + * i2c addresses for 3/4 amps are used in order: 0x40, 0x41, 0x42, 0x43, + * subtracting 0x40 would give zero-based index + */ + cs35l41->index = id - 0x40; + else + /* i2c addr 0x40 for first amp (always), 0x41/0x42 for 2nd amp */ + cs35l41->index = id == 0x40 ? 0 : 1; + } + + if (cfg->num_amps == 3) + /* 3 amps means a center channel, so no duplicate channels */ + cs35l41->channel_index = 0; + else + /* + * if 4 amps, there are duplicate channels, so they need different indexes + * if 2 amps, no duplicate channels, channel_index would be 0 + */ + cs35l41->channel_index = cs35l41->index / 2; + + cs35l41->reset_gpio = fwnode_gpiod_get_index(acpi_fwnode_handle(cs35l41->dacpi), "reset", + cs35l41->index, GPIOD_OUT_LOW, + "cs35l41-reset"); + cs35l41->speaker_id = cs35l41_get_speaker_id(physdev, cs35l41->index, cfg->num_amps, -1); + + hw_cfg->spk_pos = cfg->channel[cs35l41->index]; + + if (cfg->boost_type == INTERNAL) { + hw_cfg->bst_type = CS35L41_INT_BOOST; + hw_cfg->bst_ind = cfg->boost_ind_nanohenry; + hw_cfg->bst_ipk = cfg->boost_peak_milliamp; + hw_cfg->bst_cap = cfg->boost_cap_microfarad; + hw_cfg->gpio1.func = CS35L41_NOT_USED; + hw_cfg->gpio1.valid = true; + } else { + hw_cfg->bst_type = CS35L41_EXT_BOOST; + hw_cfg->bst_ind = -1; + hw_cfg->bst_ipk = -1; + hw_cfg->bst_cap = -1; + hw_cfg->gpio1.func = CS35l41_VSPK_SWITCH; + hw_cfg->gpio1.valid = true; + } + + hw_cfg->gpio2.func = CS35L41_INTERRUPT; + hw_cfg->gpio2.valid = true; + hw_cfg->valid = true; + + return 0; +} /* * Device CLSA010(0/1) doesn't have _DSD so a gpiod_get by the label reset won't work. @@ -43,44 +335,6 @@ static int lenovo_legion_no_acpi(struct cs35l41_hda *cs35l41, struct device *phy return 0; } -/* - * Device 103C89C6 does have _DSD, however it is setup to use the wrong boost type. - * We can override the _DSD to correct the boost type here. - * Since this laptop has valid ACPI, we do not need to handle cs-gpios, since that already exists - * in the ACPI. - */ -static int hp_vision_acpi_fix(struct cs35l41_hda *cs35l41, struct device *physdev, int id, - const char *hid) -{ - struct cs35l41_hw_cfg *hw_cfg = &cs35l41->hw_cfg; - - dev_info(cs35l41->dev, "Adding DSD properties for %s\n", cs35l41->acpi_subsystem_id); - - cs35l41->index = id; - cs35l41->channel_index = 0; - - /* - * This system has _DSD, it just contains an error, so we can still get the reset using - * the "reset" label. - */ - cs35l41->reset_gpio = fwnode_gpiod_get_index(acpi_fwnode_handle(cs35l41->dacpi), "reset", - cs35l41->index, GPIOD_OUT_LOW, - "cs35l41-reset"); - cs35l41->speaker_id = -ENOENT; - hw_cfg->spk_pos = cs35l41->index ? 0 : 1; // right:left - hw_cfg->gpio1.func = CS35L41_NOT_USED; - hw_cfg->gpio1.valid = true; - hw_cfg->gpio2.func = CS35L41_INTERRUPT; - hw_cfg->gpio2.valid = true; - hw_cfg->bst_type = CS35L41_INT_BOOST; - hw_cfg->bst_ind = 1000; - hw_cfg->bst_ipk = 4500; - hw_cfg->bst_cap = 24; - hw_cfg->valid = true; - - return 0; -} - struct cs35l41_prop_model { const char *hid; const char *ssid; @@ -91,7 +345,36 @@ struct cs35l41_prop_model { static const struct cs35l41_prop_model cs35l41_prop_model_table[] = { { "CLSA0100", NULL, lenovo_legion_no_acpi }, { "CLSA0101", NULL, lenovo_legion_no_acpi }, - { "CSC3551", "103C89C6", hp_vision_acpi_fix }, + { "CSC3551", "103C89C6", generic_dsd_config }, + { "CSC3551", "104312AF", generic_dsd_config }, + { "CSC3551", "10431433", generic_dsd_config }, + { "CSC3551", "10431463", generic_dsd_config }, + { "CSC3551", "10431473", generic_dsd_config }, + { "CSC3551", "10431483", generic_dsd_config }, + { "CSC3551", "10431493", generic_dsd_config }, + { "CSC3551", "104314D3", generic_dsd_config }, + { "CSC3551", "104314E3", generic_dsd_config }, + { "CSC3551", "10431503", generic_dsd_config }, + { "CSC3551", "10431533", generic_dsd_config }, + { "CSC3551", "10431573", generic_dsd_config }, + { "CSC3551", "10431663", generic_dsd_config }, + { "CSC3551", "104316D3", generic_dsd_config }, + { "CSC3551", "104316F3", generic_dsd_config }, + { "CSC3551", "104317F3", generic_dsd_config }, + { "CSC3551", "10431863", generic_dsd_config }, + { "CSC3551", "104318D3", generic_dsd_config }, + { "CSC3551", "10431C9F", generic_dsd_config }, + { "CSC3551", "10431CAF", generic_dsd_config }, + { "CSC3551", "10431CCF", generic_dsd_config }, + { "CSC3551", "10431CDF", generic_dsd_config }, + { "CSC3551", "10431CEF", generic_dsd_config }, + { "CSC3551", "10431D1F", generic_dsd_config }, + { "CSC3551", "10431DA2", generic_dsd_config }, + { "CSC3551", "10431E02", generic_dsd_config }, + { "CSC3551", "10431EE2", generic_dsd_config }, + { "CSC3551", "10431F12", generic_dsd_config }, + { "CSC3551", "10431F1F", generic_dsd_config }, + { "CSC3551", "10431F62", generic_dsd_config }, {} }; @@ -104,7 +387,7 @@ int cs35l41_add_dsd_properties(struct cs35l41_hda *cs35l41, struct device *physd if (!strcmp(model->hid, hid) && (!model->ssid || (cs35l41->acpi_subsystem_id && - !strcmp(model->ssid, cs35l41->acpi_subsystem_id)))) + !strcasecmp(model->ssid, cs35l41->acpi_subsystem_id)))) return model->add_prop(cs35l41, physdev, id, hid); } diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 1cde2a69bdb4..78cee53fee02 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -1993,7 +1993,10 @@ static const struct snd_pci_quirk force_connect_list[] = { SND_PCI_QUIRK(0x103c, 0x871a, "HP", 1), SND_PCI_QUIRK(0x103c, 0x8711, "HP", 1), SND_PCI_QUIRK(0x103c, 0x8715, "HP", 1), + SND_PCI_QUIRK(0x1043, 0x86ae, "ASUS", 1), /* Z170 PRO */ + SND_PCI_QUIRK(0x1043, 0x86c7, "ASUS", 1), /* Z170M PLUS */ SND_PCI_QUIRK(0x1462, 0xec94, "MS-7C94", 1), + SND_PCI_QUIRK(0x8086, 0x2060, "Intel NUC5CPYB", 1), SND_PCI_QUIRK(0x8086, 0x2081, "Intel NUC 10", 1), {} }; diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 0377912e9264..70b17b08d4ff 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9795,9 +9795,11 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x83b9, "HP Spectre x360", ALC269_FIXUP_HP_MUTE_LED_MIC3), SND_PCI_QUIRK(0x103c, 0x841c, "HP Pavilion 15-CK0xx", ALC269_FIXUP_HP_MUTE_LED_MIC3), SND_PCI_QUIRK(0x103c, 0x8497, "HP Envy x360", ALC269_FIXUP_HP_MUTE_LED_MIC3), + SND_PCI_QUIRK(0x103c, 0x84ae, "HP 15-db0403ng", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x84da, "HP OMEN dc0019-ur", ALC295_FIXUP_HP_OMEN), SND_PCI_QUIRK(0x103c, 0x84e7, "HP Pavilion 15", ALC269_FIXUP_HP_MUTE_LED_MIC3), SND_PCI_QUIRK(0x103c, 0x8519, "HP Spectre x360 15-df0xxx", ALC285_FIXUP_HP_SPECTRE_X360), + SND_PCI_QUIRK(0x103c, 0x8537, "HP ProBook 440 G6", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x860f, "HP ZBook 15 G6", ALC285_FIXUP_HP_GPIO_AMP_INIT), SND_PCI_QUIRK(0x103c, 0x861f, "HP Elite Dragonfly G1", ALC285_FIXUP_HP_GPIO_AMP_INIT), SND_PCI_QUIRK(0x103c, 0x869d, "HP", ALC236_FIXUP_HP_MUTE_LED), @@ -9880,6 +9882,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x89c6, "Zbook Fury 17 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x89ca, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x89d3, "HP EliteBook 645 G9 (MB 89D2)", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8a0f, "HP Pavilion 14-ec1xxx", ALC287_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8a20, "HP Laptop 15s-fq5xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x8a25, "HP Victus 16-d1xxx (MB 8A25)", ALC245_FIXUP_HP_MUTE_LED_COEFBIT), SND_PCI_QUIRK(0x103c, 0x8a78, "HP Dev One", ALC285_FIXUP_HP_LIMIT_INT_MIC_BOOST), @@ -9924,6 +9927,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8c70, "HP EliteBook 835 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c71, "HP EliteBook 845 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c72, "HP EliteBook 865 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8c96, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8ca4, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ca7, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8cf5, "HP ZBook Studio 16", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED), @@ -9947,21 +9951,28 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1313, "Asus K42JZ", ALC269VB_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x13b0, "ASUS Z550SA", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x1427, "Asus Zenbook UX31E", ALC269VB_FIXUP_ASUS_ZENBOOK), - SND_PCI_QUIRK(0x1043, 0x1433, "ASUS GX650P", ALC285_FIXUP_ASUS_I2C_HEADSET_MIC), - SND_PCI_QUIRK(0x1043, 0x1463, "Asus GA402X", ALC285_FIXUP_ASUS_I2C_HEADSET_MIC), - SND_PCI_QUIRK(0x1043, 0x1473, "ASUS GU604V", ALC285_FIXUP_ASUS_HEADSET_MIC), - SND_PCI_QUIRK(0x1043, 0x1483, "ASUS GU603V", ALC285_FIXUP_ASUS_HEADSET_MIC), - SND_PCI_QUIRK(0x1043, 0x1493, "ASUS GV601V", ALC285_FIXUP_ASUS_HEADSET_MIC), + SND_PCI_QUIRK(0x1043, 0x1433, "ASUS GX650PY/PZ/PV/PU/PYV/PZV/PIV/PVV", ALC285_FIXUP_ASUS_I2C_HEADSET_MIC), + SND_PCI_QUIRK(0x1043, 0x1463, "Asus GA402X/GA402N", ALC285_FIXUP_ASUS_I2C_HEADSET_MIC), + SND_PCI_QUIRK(0x1043, 0x1473, "ASUS GU604VI/VC/VE/VG/VJ/VQ/VU/VV/VY/VZ", ALC285_FIXUP_ASUS_HEADSET_MIC), + SND_PCI_QUIRK(0x1043, 0x1483, "ASUS GU603VQ/VU/VV/VJ/VI", ALC285_FIXUP_ASUS_HEADSET_MIC), + SND_PCI_QUIRK(0x1043, 0x1493, "ASUS GV601VV/VU/VJ/VQ/VI", ALC285_FIXUP_ASUS_HEADSET_MIC), + SND_PCI_QUIRK(0x1043, 0x14d3, "ASUS G614JY/JZ/JG", ALC245_FIXUP_CS35L41_SPI_2), + SND_PCI_QUIRK(0x1043, 0x14e3, "ASUS G513PI/PU/PV", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x1043, 0x1503, "ASUS G733PY/PZ/PZV/PYV", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x1043, 0x1517, "Asus Zenbook UX31A", ALC269VB_FIXUP_ASUS_ZENBOOK_UX31A), - SND_PCI_QUIRK(0x1043, 0x1573, "ASUS GZ301V", ALC285_FIXUP_ASUS_HEADSET_MIC), + SND_PCI_QUIRK(0x1043, 0x1533, "ASUS GV302XA/XJ/XQ/XU/XV/XI", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x1043, 0x1573, "ASUS GZ301VV/VQ/VU/VJ/VA/VC/VE/VVC/VQC/VUC/VJC/VEC/VCC", ALC285_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1662, "ASUS GV301QH", ALC294_FIXUP_ASUS_DUAL_SPK), - SND_PCI_QUIRK(0x1043, 0x1663, "ASUS GU603ZV", ALC285_FIXUP_ASUS_HEADSET_MIC), + SND_PCI_QUIRK(0x1043, 0x1663, "ASUS GU603ZI/ZJ/ZQ/ZU/ZV", ALC285_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1683, "ASUS UM3402YAR", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x1043, 0x16b2, "ASUS GU603", ALC289_FIXUP_ASUS_GA401), + SND_PCI_QUIRK(0x1043, 0x16d3, "ASUS UX5304VA", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x16e3, "ASUS UX50", ALC269_FIXUP_STEREO_DMIC), + SND_PCI_QUIRK(0x1043, 0x16f3, "ASUS UX7602VI/BZ", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x1740, "ASUS UX430UA", ALC295_FIXUP_ASUS_DACS), SND_PCI_QUIRK(0x1043, 0x17d1, "ASUS UX431FL", ALC294_FIXUP_ASUS_DUAL_SPK), - SND_PCI_QUIRK(0x1043, 0x17f3, "ROG Ally RC71L_RC71L", ALC294_FIXUP_ASUS_ALLY), + SND_PCI_QUIRK(0x1043, 0x17f3, "ROG Ally NR2301L/X", ALC294_FIXUP_ASUS_ALLY), + SND_PCI_QUIRK(0x1043, 0x1863, "ASUS UX6404VI/VV", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x1881, "ASUS Zephyrus S/M", ALC294_FIXUP_ASUS_GX502_PINS), SND_PCI_QUIRK(0x1043, 0x18b1, "Asus MJ401TA", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x18d3, "ASUS UM3504DA", ALC294_FIXUP_CS35L41_I2C_2), @@ -9986,23 +9997,30 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1c43, "ASUS UX8406MA", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x1c62, "ASUS GU603", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x1c92, "ASUS ROG Strix G15", ALC285_FIXUP_ASUS_G533Z_PINS), - SND_PCI_QUIRK(0x1043, 0x1c9f, "ASUS G614JI", ALC285_FIXUP_ASUS_HEADSET_MIC), - SND_PCI_QUIRK(0x1043, 0x1caf, "ASUS G634JYR/JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS), + SND_PCI_QUIRK(0x1043, 0x1c9f, "ASUS G614JU/JV/JI", ALC285_FIXUP_ASUS_HEADSET_MIC), + SND_PCI_QUIRK(0x1043, 0x1caf, "ASUS G634JY/JZ/JI/JG", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS), SND_PCI_QUIRK(0x1043, 0x1ccd, "ASUS X555UB", ALC256_FIXUP_ASUS_MIC), - SND_PCI_QUIRK(0x1043, 0x1d1f, "ASUS ROG Strix G17 2023 (G713PV)", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x1043, 0x1ccf, "ASUS G814JU/JV/JI", ALC245_FIXUP_CS35L41_SPI_2), + SND_PCI_QUIRK(0x1043, 0x1cdf, "ASUS G814JY/JZ/JG", ALC245_FIXUP_CS35L41_SPI_2), + SND_PCI_QUIRK(0x1043, 0x1cef, "ASUS G834JY/JZ/JI/JG", ALC285_FIXUP_ASUS_HEADSET_MIC), + SND_PCI_QUIRK(0x1043, 0x1d1f, "ASUS G713PI/PU/PV/PVN", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x1043, 0x1d42, "ASUS Zephyrus G14 2022", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x1d4e, "ASUS TM420", ALC256_FIXUP_ASUS_HPE), + SND_PCI_QUIRK(0x1043, 0x1da2, "ASUS UP6502ZA/ZD", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x1e02, "ASUS UX3402ZA", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x16a3, "ASUS UX3402VA", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x1f62, "ASUS UX7602ZM", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x1e11, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA502), - SND_PCI_QUIRK(0x1043, 0x1e12, "ASUS UM3402", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x1043, 0x1e12, "ASUS UM6702RA/RC", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x1043, 0x1e51, "ASUS Zephyrus M15", ALC294_FIXUP_ASUS_GU502_PINS), SND_PCI_QUIRK(0x1043, 0x1e5e, "ASUS ROG Strix G513", ALC294_FIXUP_ASUS_G513_PINS), SND_PCI_QUIRK(0x1043, 0x1e8e, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA401), + SND_PCI_QUIRK(0x1043, 0x1ee2, "ASUS UM3402", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x1043, 0x1c52, "ASUS Zephyrus G15 2022", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x1f11, "ASUS Zephyrus G14", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x1f12, "ASUS UM5302", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x1043, 0x1f1f, "ASUS H7604JI/JV/J3D", ALC245_FIXUP_CS35L41_SPI_2), + SND_PCI_QUIRK(0x1043, 0x1f62, "ASUS UX7602ZM", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x1f92, "ASUS ROG Flow X16", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x3030, "ASUS ZN270IE", ALC256_FIXUP_ASUS_AIO_GPIO2), SND_PCI_QUIRK(0x1043, 0x3a20, "ASUS G614JZR", ALC245_FIXUP_CS35L41_SPI_2), diff --git a/sound/pci/hda/tas2781_hda_i2c.c b/sound/pci/hda/tas2781_hda_i2c.c index fb802802939e..dfe281b57aa6 100644 --- a/sound/pci/hda/tas2781_hda_i2c.c +++ b/sound/pci/hda/tas2781_hda_i2c.c @@ -65,6 +65,15 @@ enum calib_data { CALIB_MAX }; +struct tas2781_hda { + struct device *dev; + struct tasdevice_priv *priv; + struct snd_kcontrol *dsp_prog_ctl; + struct snd_kcontrol *dsp_conf_ctl; + struct snd_kcontrol *prof_ctl; + struct snd_kcontrol *snd_ctls[3]; +}; + static int tas2781_get_i2c_res(struct acpi_resource *ares, void *data) { struct tasdevice_priv *tas_priv = data; @@ -125,26 +134,26 @@ err: static void tas2781_hda_playback_hook(struct device *dev, int action) { - struct tasdevice_priv *tas_priv = dev_get_drvdata(dev); + struct tas2781_hda *tas_hda = dev_get_drvdata(dev); - dev_dbg(tas_priv->dev, "%s: action = %d\n", __func__, action); + dev_dbg(tas_hda->dev, "%s: action = %d\n", __func__, action); switch (action) { case HDA_GEN_PCM_ACT_OPEN: pm_runtime_get_sync(dev); - mutex_lock(&tas_priv->codec_lock); - tasdevice_tuning_switch(tas_priv, 0); - mutex_unlock(&tas_priv->codec_lock); + mutex_lock(&tas_hda->priv->codec_lock); + tasdevice_tuning_switch(tas_hda->priv, 0); + mutex_unlock(&tas_hda->priv->codec_lock); break; case HDA_GEN_PCM_ACT_CLOSE: - mutex_lock(&tas_priv->codec_lock); - tasdevice_tuning_switch(tas_priv, 1); - mutex_unlock(&tas_priv->codec_lock); + mutex_lock(&tas_hda->priv->codec_lock); + tasdevice_tuning_switch(tas_hda->priv, 1); + mutex_unlock(&tas_hda->priv->codec_lock); pm_runtime_mark_last_busy(dev); pm_runtime_put_autosuspend(dev); break; default: - dev_dbg(tas_priv->dev, "Playback action not supported: %d\n", + dev_dbg(tas_hda->dev, "Playback action not supported: %d\n", action); break; } @@ -421,9 +430,9 @@ static void tas2781_apply_calib(struct tasdevice_priv *tas_priv) } } -/* Update the calibrate data, including speaker impedance, f0, etc, into algo. +/* Update the calibration data, including speaker impedance, f0, etc, into algo. * Calibrate data is done by manufacturer in the factory. These data are used - * by Algo for calucating the speaker temperature, speaker membrance excursion + * by Algo for calculating the speaker temperature, speaker membrane excursion * and f0 in real time during playback. */ static int tas2781_save_calibration(struct tasdevice_priv *tas_priv) @@ -455,9 +464,9 @@ static int tas2781_save_calibration(struct tasdevice_priv *tas_priv) status = efi.get_variable(efi_name, &efi_guid, &attr, &tas_priv->cali_data.total_sz, tas_priv->cali_data.data); - if (status != EFI_SUCCESS) - return -EINVAL; } + if (status != EFI_SUCCESS) + return -EINVAL; tmp_val = (unsigned int *)tas_priv->cali_data.data; @@ -477,9 +486,28 @@ static int tas2781_save_calibration(struct tasdevice_priv *tas_priv) return 0; } +static void tas2781_hda_remove_controls(struct tas2781_hda *tas_hda) +{ + struct hda_codec *codec = tas_hda->priv->codec; + + if (tas_hda->dsp_prog_ctl) + snd_ctl_remove(codec->card, tas_hda->dsp_prog_ctl); + + if (tas_hda->dsp_conf_ctl) + snd_ctl_remove(codec->card, tas_hda->dsp_conf_ctl); + + for (int i = ARRAY_SIZE(tas_hda->snd_ctls) - 1; i >= 0; i--) + if (tas_hda->snd_ctls[i]) + snd_ctl_remove(codec->card, tas_hda->snd_ctls[i]); + + if (tas_hda->prof_ctl) + snd_ctl_remove(codec->card, tas_hda->prof_ctl); +} + static void tasdev_fw_ready(const struct firmware *fmw, void *context) { struct tasdevice_priv *tas_priv = context; + struct tas2781_hda *tas_hda = dev_get_drvdata(tas_priv->dev); struct hda_codec *codec = tas_priv->codec; int i, ret; @@ -490,8 +518,8 @@ static void tasdev_fw_ready(const struct firmware *fmw, void *context) if (ret) goto out; - ret = snd_ctl_add(codec->card, - snd_ctl_new1(&tas2781_prof_ctrl, tas_priv)); + tas_hda->prof_ctl = snd_ctl_new1(&tas2781_prof_ctrl, tas_priv); + ret = snd_ctl_add(codec->card, tas_hda->prof_ctl); if (ret) { dev_err(tas_priv->dev, "Failed to add KControl %s = %d\n", @@ -500,8 +528,9 @@ static void tasdev_fw_ready(const struct firmware *fmw, void *context) } for (i = 0; i < ARRAY_SIZE(tas2781_snd_controls); i++) { - ret = snd_ctl_add(codec->card, - snd_ctl_new1(&tas2781_snd_controls[i], tas_priv)); + tas_hda->snd_ctls[i] = snd_ctl_new1(&tas2781_snd_controls[i], + tas_priv); + ret = snd_ctl_add(codec->card, tas_hda->snd_ctls[i]); if (ret) { dev_err(tas_priv->dev, "Failed to add KControl %s = %d\n", @@ -523,8 +552,9 @@ static void tasdev_fw_ready(const struct firmware *fmw, void *context) goto out; } - ret = snd_ctl_add(codec->card, - snd_ctl_new1(&tas2781_dsp_prog_ctrl, tas_priv)); + tas_hda->dsp_prog_ctl = snd_ctl_new1(&tas2781_dsp_prog_ctrl, + tas_priv); + ret = snd_ctl_add(codec->card, tas_hda->dsp_prog_ctl); if (ret) { dev_err(tas_priv->dev, "Failed to add KControl %s = %d\n", @@ -532,8 +562,9 @@ static void tasdev_fw_ready(const struct firmware *fmw, void *context) goto out; } - ret = snd_ctl_add(codec->card, - snd_ctl_new1(&tas2781_dsp_conf_ctrl, tas_priv)); + tas_hda->dsp_conf_ctl = snd_ctl_new1(&tas2781_dsp_conf_ctrl, + tas_priv); + ret = snd_ctl_add(codec->card, tas_hda->dsp_conf_ctl); if (ret) { dev_err(tas_priv->dev, "Failed to add KControl %s = %d\n", @@ -543,6 +574,10 @@ static void tasdev_fw_ready(const struct firmware *fmw, void *context) tas_priv->fw_state = TASDEVICE_DSP_FW_ALL_OK; tasdevice_prmg_load(tas_priv, 0); + if (tas_priv->fmw->nr_programs > 0) + tas_priv->cur_prog = 0; + if (tas_priv->fmw->nr_configurations > 0) + tas_priv->cur_conf = 0; /* If calibrated data occurs error, dsp will still works with default * calibrated data inside algo. @@ -550,32 +585,27 @@ static void tasdev_fw_ready(const struct firmware *fmw, void *context) tas2781_save_calibration(tas_priv); out: - if (tas_priv->fw_state == TASDEVICE_DSP_FW_FAIL) { - /*If DSP FW fail, kcontrol won't be created */ - tasdevice_config_info_remove(tas_priv); - tasdevice_dsp_remove(tas_priv); - } - mutex_unlock(&tas_priv->codec_lock); + mutex_unlock(&tas_hda->priv->codec_lock); if (fmw) release_firmware(fmw); - pm_runtime_mark_last_busy(tas_priv->dev); - pm_runtime_put_autosuspend(tas_priv->dev); + pm_runtime_mark_last_busy(tas_hda->dev); + pm_runtime_put_autosuspend(tas_hda->dev); } static int tas2781_hda_bind(struct device *dev, struct device *master, void *master_data) { - struct tasdevice_priv *tas_priv = dev_get_drvdata(dev); + struct tas2781_hda *tas_hda = dev_get_drvdata(dev); struct hda_component *comps = master_data; struct hda_codec *codec; unsigned int subid; int ret; - if (!comps || tas_priv->index < 0 || - tas_priv->index >= HDA_MAX_COMPONENTS) + if (!comps || tas_hda->priv->index < 0 || + tas_hda->priv->index >= HDA_MAX_COMPONENTS) return -EINVAL; - comps = &comps[tas_priv->index]; + comps = &comps[tas_hda->priv->index]; if (comps->dev) return -EBUSY; @@ -584,10 +614,10 @@ static int tas2781_hda_bind(struct device *dev, struct device *master, switch (subid) { case 0x17aa: - tas_priv->catlog_id = LENOVO; + tas_hda->priv->catlog_id = LENOVO; break; default: - tas_priv->catlog_id = OTHERS; + tas_hda->priv->catlog_id = OTHERS; break; } @@ -597,7 +627,7 @@ static int tas2781_hda_bind(struct device *dev, struct device *master, strscpy(comps->name, dev_name(dev), sizeof(comps->name)); - ret = tascodec_init(tas_priv, codec, tasdev_fw_ready); + ret = tascodec_init(tas_hda->priv, codec, tasdev_fw_ready); if (!ret) comps->playback_hook = tas2781_hda_playback_hook; @@ -610,16 +640,22 @@ static int tas2781_hda_bind(struct device *dev, struct device *master, static void tas2781_hda_unbind(struct device *dev, struct device *master, void *master_data) { - struct tasdevice_priv *tas_priv = dev_get_drvdata(dev); + struct tas2781_hda *tas_hda = dev_get_drvdata(dev); struct hda_component *comps = master_data; + comps = &comps[tas_hda->priv->index]; - if (comps[tas_priv->index].dev == dev) - memset(&comps[tas_priv->index], 0, sizeof(*comps)); + if (comps->dev == dev) { + comps->dev = NULL; + memset(comps->name, 0, sizeof(comps->name)); + comps->playback_hook = NULL; + } - tasdevice_config_info_remove(tas_priv); - tasdevice_dsp_remove(tas_priv); + tas2781_hda_remove_controls(tas_hda); - tas_priv->fw_state = TASDEVICE_DSP_FW_PENDING; + tasdevice_config_info_remove(tas_hda->priv); + tasdevice_dsp_remove(tas_hda->priv); + + tas_hda->priv->fw_state = TASDEVICE_DSP_FW_PENDING; } static const struct component_ops tas2781_hda_comp_ops = { @@ -629,21 +665,21 @@ static const struct component_ops tas2781_hda_comp_ops = { static void tas2781_hda_remove(struct device *dev) { - struct tasdevice_priv *tas_priv = dev_get_drvdata(dev); + struct tas2781_hda *tas_hda = dev_get_drvdata(dev); - pm_runtime_get_sync(tas_priv->dev); - pm_runtime_disable(tas_priv->dev); + pm_runtime_get_sync(tas_hda->dev); + pm_runtime_disable(tas_hda->dev); - component_del(tas_priv->dev, &tas2781_hda_comp_ops); + component_del(tas_hda->dev, &tas2781_hda_comp_ops); - pm_runtime_put_noidle(tas_priv->dev); + pm_runtime_put_noidle(tas_hda->dev); - tasdevice_remove(tas_priv); + tasdevice_remove(tas_hda->priv); } static int tas2781_hda_i2c_probe(struct i2c_client *clt) { - struct tasdevice_priv *tas_priv; + struct tas2781_hda *tas_hda; const char *device_name; int ret; @@ -652,37 +688,44 @@ static int tas2781_hda_i2c_probe(struct i2c_client *clt) else return -ENODEV; - tas_priv = tasdevice_kzalloc(clt); - if (!tas_priv) + tas_hda = devm_kzalloc(&clt->dev, sizeof(*tas_hda), GFP_KERNEL); + if (!tas_hda) + return -ENOMEM; + + dev_set_drvdata(&clt->dev, tas_hda); + tas_hda->dev = &clt->dev; + + tas_hda->priv = tasdevice_kzalloc(clt); + if (!tas_hda->priv) return -ENOMEM; - tas_priv->irq_info.irq = clt->irq; - ret = tas2781_read_acpi(tas_priv, device_name); + tas_hda->priv->irq_info.irq = clt->irq; + ret = tas2781_read_acpi(tas_hda->priv, device_name); if (ret) - return dev_err_probe(tas_priv->dev, ret, + return dev_err_probe(tas_hda->dev, ret, "Platform not supported\n"); - ret = tasdevice_init(tas_priv); + ret = tasdevice_init(tas_hda->priv); if (ret) goto err; - pm_runtime_set_autosuspend_delay(tas_priv->dev, 3000); - pm_runtime_use_autosuspend(tas_priv->dev); - pm_runtime_mark_last_busy(tas_priv->dev); - pm_runtime_set_active(tas_priv->dev); - pm_runtime_get_noresume(tas_priv->dev); - pm_runtime_enable(tas_priv->dev); + pm_runtime_set_autosuspend_delay(tas_hda->dev, 3000); + pm_runtime_use_autosuspend(tas_hda->dev); + pm_runtime_mark_last_busy(tas_hda->dev); + pm_runtime_set_active(tas_hda->dev); + pm_runtime_get_noresume(tas_hda->dev); + pm_runtime_enable(tas_hda->dev); - pm_runtime_put_autosuspend(tas_priv->dev); + pm_runtime_put_autosuspend(tas_hda->dev); - ret = component_add(tas_priv->dev, &tas2781_hda_comp_ops); + tas2781_reset(tas_hda->priv); + + ret = component_add(tas_hda->dev, &tas2781_hda_comp_ops); if (ret) { - dev_err(tas_priv->dev, "Register component failed: %d\n", ret); - pm_runtime_disable(tas_priv->dev); - goto err; + dev_err(tas_hda->dev, "Register component failed: %d\n", ret); + pm_runtime_disable(tas_hda->dev); } - tas2781_reset(tas_priv); err: if (ret) tas2781_hda_remove(&clt->dev); @@ -696,81 +739,65 @@ static void tas2781_hda_i2c_remove(struct i2c_client *clt) static int tas2781_runtime_suspend(struct device *dev) { - struct tasdevice_priv *tas_priv = dev_get_drvdata(dev); + struct tas2781_hda *tas_hda = dev_get_drvdata(dev); int i; - dev_dbg(tas_priv->dev, "Runtime Suspend\n"); + dev_dbg(tas_hda->dev, "Runtime Suspend\n"); - mutex_lock(&tas_priv->codec_lock); + mutex_lock(&tas_hda->priv->codec_lock); - if (tas_priv->playback_started) { - tasdevice_tuning_switch(tas_priv, 1); - tas_priv->playback_started = false; + if (tas_hda->priv->playback_started) { + tasdevice_tuning_switch(tas_hda->priv, 1); + tas_hda->priv->playback_started = false; } - for (i = 0; i < tas_priv->ndev; i++) { - tas_priv->tasdevice[i].cur_book = -1; - tas_priv->tasdevice[i].cur_prog = -1; - tas_priv->tasdevice[i].cur_conf = -1; + for (i = 0; i < tas_hda->priv->ndev; i++) { + tas_hda->priv->tasdevice[i].cur_book = -1; + tas_hda->priv->tasdevice[i].cur_prog = -1; + tas_hda->priv->tasdevice[i].cur_conf = -1; } - regcache_cache_only(tas_priv->regmap, true); - regcache_mark_dirty(tas_priv->regmap); - - mutex_unlock(&tas_priv->codec_lock); + mutex_unlock(&tas_hda->priv->codec_lock); return 0; } static int tas2781_runtime_resume(struct device *dev) { - struct tasdevice_priv *tas_priv = dev_get_drvdata(dev); + struct tas2781_hda *tas_hda = dev_get_drvdata(dev); unsigned long calib_data_sz = - tas_priv->ndev * TASDEVICE_SPEAKER_CALIBRATION_SIZE; - int ret; + tas_hda->priv->ndev * TASDEVICE_SPEAKER_CALIBRATION_SIZE; - dev_dbg(tas_priv->dev, "Runtime Resume\n"); + dev_dbg(tas_hda->dev, "Runtime Resume\n"); - mutex_lock(&tas_priv->codec_lock); + mutex_lock(&tas_hda->priv->codec_lock); - regcache_cache_only(tas_priv->regmap, false); - ret = regcache_sync(tas_priv->regmap); - if (ret) { - dev_err(tas_priv->dev, - "Failed to restore register cache: %d\n", ret); - goto out; - } - - tasdevice_prmg_load(tas_priv, tas_priv->cur_prog); + tasdevice_prmg_load(tas_hda->priv, tas_hda->priv->cur_prog); /* If calibrated data occurs error, dsp will still works with default * calibrated data inside algo. */ - if (tas_priv->cali_data.total_sz > calib_data_sz) - tas2781_apply_calib(tas_priv); + if (tas_hda->priv->cali_data.total_sz > calib_data_sz) + tas2781_apply_calib(tas_hda->priv); -out: - mutex_unlock(&tas_priv->codec_lock); + mutex_unlock(&tas_hda->priv->codec_lock); - return ret; + return 0; } static int tas2781_system_suspend(struct device *dev) { - struct tasdevice_priv *tas_priv = dev_get_drvdata(dev); + struct tas2781_hda *tas_hda = dev_get_drvdata(dev); int ret; - dev_dbg(tas_priv->dev, "System Suspend\n"); + dev_dbg(tas_hda->priv->dev, "System Suspend\n"); ret = pm_runtime_force_suspend(dev); if (ret) return ret; /* Shutdown chip before system suspend */ - regcache_cache_only(tas_priv->regmap, false); - tasdevice_tuning_switch(tas_priv, 1); - regcache_cache_only(tas_priv->regmap, true); - regcache_mark_dirty(tas_priv->regmap); + tasdevice_tuning_switch(tas_hda->priv, 1); /* * Reset GPIO may be shared, so cannot reset here. @@ -781,33 +808,33 @@ static int tas2781_system_suspend(struct device *dev) static int tas2781_system_resume(struct device *dev) { - struct tasdevice_priv *tas_priv = dev_get_drvdata(dev); + struct tas2781_hda *tas_hda = dev_get_drvdata(dev); unsigned long calib_data_sz = - tas_priv->ndev * TASDEVICE_SPEAKER_CALIBRATION_SIZE; + tas_hda->priv->ndev * TASDEVICE_SPEAKER_CALIBRATION_SIZE; int i, ret; - dev_dbg(tas_priv->dev, "System Resume\n"); + dev_info(tas_hda->priv->dev, "System Resume\n"); ret = pm_runtime_force_resume(dev); if (ret) return ret; - mutex_lock(&tas_priv->codec_lock); + mutex_lock(&tas_hda->priv->codec_lock); - for (i = 0; i < tas_priv->ndev; i++) { - tas_priv->tasdevice[i].cur_book = -1; - tas_priv->tasdevice[i].cur_prog = -1; - tas_priv->tasdevice[i].cur_conf = -1; + for (i = 0; i < tas_hda->priv->ndev; i++) { + tas_hda->priv->tasdevice[i].cur_book = -1; + tas_hda->priv->tasdevice[i].cur_prog = -1; + tas_hda->priv->tasdevice[i].cur_conf = -1; } - tas2781_reset(tas_priv); - tasdevice_prmg_load(tas_priv, tas_priv->cur_prog); + tas2781_reset(tas_hda->priv); + tasdevice_prmg_load(tas_hda->priv, tas_hda->priv->cur_prog); /* If calibrated data occurs error, dsp will still work with default * calibrated data inside algo. */ - if (tas_priv->cali_data.total_sz > calib_data_sz) - tas2781_apply_calib(tas_priv); - mutex_unlock(&tas_priv->codec_lock); + if (tas_hda->priv->cali_data.total_sz > calib_data_sz) + tas2781_apply_calib(tas_hda->priv); + mutex_unlock(&tas_hda->priv->codec_lock); return 0; } diff --git a/sound/soc/codecs/cs35l45-i2c.c b/sound/soc/codecs/cs35l45-i2c.c index 77e0f8750f37..bc2af1ed0fe9 100644 --- a/sound/soc/codecs/cs35l45-i2c.c +++ b/sound/soc/codecs/cs35l45-i2c.c @@ -62,7 +62,7 @@ static struct i2c_driver cs35l45_i2c_driver = { .driver = { .name = "cs35l45", .of_match_table = cs35l45_of_match, - .pm = &cs35l45_pm_ops, + .pm = pm_ptr(&cs35l45_pm_ops), }, .id_table = cs35l45_id_i2c, .probe = cs35l45_i2c_probe, diff --git a/sound/soc/codecs/cs35l45-spi.c b/sound/soc/codecs/cs35l45-spi.c index 5efb77530cc3..39e203a5f060 100644 --- a/sound/soc/codecs/cs35l45-spi.c +++ b/sound/soc/codecs/cs35l45-spi.c @@ -64,7 +64,7 @@ static struct spi_driver cs35l45_spi_driver = { .driver = { .name = "cs35l45", .of_match_table = cs35l45_of_match, - .pm = &cs35l45_pm_ops, + .pm = pm_ptr(&cs35l45_pm_ops), }, .id_table = cs35l45_id_spi, .probe = cs35l45_spi_probe, diff --git a/sound/soc/codecs/cs35l45.c b/sound/soc/codecs/cs35l45.c index b68853e42fd1..44c221745c3b 100644 --- a/sound/soc/codecs/cs35l45.c +++ b/sound/soc/codecs/cs35l45.c @@ -947,6 +947,8 @@ static int cs35l45_enter_hibernate(struct cs35l45_private *cs35l45) cs35l45_setup_hibernate(cs35l45); + regmap_set_bits(cs35l45->regmap, CS35L45_IRQ1_MASK_2, CS35L45_DSP_VIRT2_MBOX_MASK); + // Don't wait for ACK since bus activity would wake the device regmap_write(cs35l45->regmap, CS35L45_DSP_VIRT1_MBOX_1, CSPL_MBOX_CMD_HIBERNATE); @@ -967,6 +969,8 @@ static int cs35l45_exit_hibernate(struct cs35l45_private *cs35l45) CSPL_MBOX_CMD_OUT_OF_HIBERNATE); if (!ret) { dev_dbg(cs35l45->dev, "Wake success at cycle: %d\n", j); + regmap_clear_bits(cs35l45->regmap, CS35L45_IRQ1_MASK_2, + CS35L45_DSP_VIRT2_MBOX_MASK); return 0; } usleep_range(100, 200); @@ -982,7 +986,7 @@ static int cs35l45_exit_hibernate(struct cs35l45_private *cs35l45) return -ETIMEDOUT; } -static int __maybe_unused cs35l45_runtime_suspend(struct device *dev) +static int cs35l45_runtime_suspend(struct device *dev) { struct cs35l45_private *cs35l45 = dev_get_drvdata(dev); @@ -999,7 +1003,7 @@ static int __maybe_unused cs35l45_runtime_suspend(struct device *dev) return 0; } -static int __maybe_unused cs35l45_runtime_resume(struct device *dev) +static int cs35l45_runtime_resume(struct device *dev) { struct cs35l45_private *cs35l45 = dev_get_drvdata(dev); int ret; @@ -1026,6 +1030,46 @@ static int __maybe_unused cs35l45_runtime_resume(struct device *dev) return ret; } +static int cs35l45_sys_suspend(struct device *dev) +{ + struct cs35l45_private *cs35l45 = dev_get_drvdata(dev); + + dev_dbg(cs35l45->dev, "System suspend, disabling IRQ\n"); + disable_irq(cs35l45->irq); + + return 0; +} + +static int cs35l45_sys_suspend_noirq(struct device *dev) +{ + struct cs35l45_private *cs35l45 = dev_get_drvdata(dev); + + dev_dbg(cs35l45->dev, "Late system suspend, reenabling IRQ\n"); + enable_irq(cs35l45->irq); + + return 0; +} + +static int cs35l45_sys_resume_noirq(struct device *dev) +{ + struct cs35l45_private *cs35l45 = dev_get_drvdata(dev); + + dev_dbg(cs35l45->dev, "Early system resume, disabling IRQ\n"); + disable_irq(cs35l45->irq); + + return 0; +} + +static int cs35l45_sys_resume(struct device *dev) +{ + struct cs35l45_private *cs35l45 = dev_get_drvdata(dev); + + dev_dbg(cs35l45->dev, "System resume, reenabling IRQ\n"); + enable_irq(cs35l45->irq); + + return 0; +} + static int cs35l45_apply_property_config(struct cs35l45_private *cs35l45) { struct device_node *node = cs35l45->dev->of_node; @@ -1466,10 +1510,12 @@ void cs35l45_remove(struct cs35l45_private *cs35l45) } EXPORT_SYMBOL_NS_GPL(cs35l45_remove, SND_SOC_CS35L45); -const struct dev_pm_ops cs35l45_pm_ops = { - SET_RUNTIME_PM_OPS(cs35l45_runtime_suspend, cs35l45_runtime_resume, NULL) +EXPORT_GPL_DEV_PM_OPS(cs35l45_pm_ops) = { + RUNTIME_PM_OPS(cs35l45_runtime_suspend, cs35l45_runtime_resume, NULL) + + SYSTEM_SLEEP_PM_OPS(cs35l45_sys_suspend, cs35l45_sys_resume) + NOIRQ_SYSTEM_SLEEP_PM_OPS(cs35l45_sys_suspend_noirq, cs35l45_sys_resume_noirq) }; -EXPORT_SYMBOL_NS_GPL(cs35l45_pm_ops, SND_SOC_CS35L45); MODULE_DESCRIPTION("ASoC CS35L45 driver"); MODULE_AUTHOR("James Schulman, Cirrus Logic Inc, <james.schulman@cirrus.com>"); diff --git a/sound/soc/codecs/cs42l43-jack.c b/sound/soc/codecs/cs42l43-jack.c index 73454de068cf..54a3ea606443 100644 --- a/sound/soc/codecs/cs42l43-jack.c +++ b/sound/soc/codecs/cs42l43-jack.c @@ -237,7 +237,7 @@ error: return ret; } -static void cs42l43_start_hs_bias(struct cs42l43_codec *priv, bool force_high) +static void cs42l43_start_hs_bias(struct cs42l43_codec *priv, bool type_detect) { struct cs42l43 *cs42l43 = priv->core; unsigned int val = 0x3 << CS42L43_HSBIAS_MODE_SHIFT; @@ -247,16 +247,17 @@ static void cs42l43_start_hs_bias(struct cs42l43_codec *priv, bool force_high) regmap_update_bits(cs42l43->regmap, CS42L43_HS2, CS42L43_HS_CLAMP_DISABLE_MASK, CS42L43_HS_CLAMP_DISABLE_MASK); - if (!force_high && priv->bias_low) - val = 0x2 << CS42L43_HSBIAS_MODE_SHIFT; - - if (priv->bias_sense_ua) { - regmap_update_bits(cs42l43->regmap, - CS42L43_HS_BIAS_SENSE_AND_CLAMP_AUTOCONTROL, - CS42L43_HSBIAS_SENSE_EN_MASK | - CS42L43_AUTO_HSBIAS_CLAMP_EN_MASK, - CS42L43_HSBIAS_SENSE_EN_MASK | - CS42L43_AUTO_HSBIAS_CLAMP_EN_MASK); + if (!type_detect) { + if (priv->bias_low) + val = 0x2 << CS42L43_HSBIAS_MODE_SHIFT; + + if (priv->bias_sense_ua) + regmap_update_bits(cs42l43->regmap, + CS42L43_HS_BIAS_SENSE_AND_CLAMP_AUTOCONTROL, + CS42L43_HSBIAS_SENSE_EN_MASK | + CS42L43_AUTO_HSBIAS_CLAMP_EN_MASK, + CS42L43_HSBIAS_SENSE_EN_MASK | + CS42L43_AUTO_HSBIAS_CLAMP_EN_MASK); } regmap_update_bits(cs42l43->regmap, CS42L43_MIC_DETECT_CONTROL_1, diff --git a/sound/soc/codecs/hdmi-codec.c b/sound/soc/codecs/hdmi-codec.c index 20da1eaa4f1c..0938671700c6 100644 --- a/sound/soc/codecs/hdmi-codec.c +++ b/sound/soc/codecs/hdmi-codec.c @@ -850,8 +850,9 @@ static int hdmi_dai_probe(struct snd_soc_dai *dai) static void hdmi_codec_jack_report(struct hdmi_codec_priv *hcp, unsigned int jack_status) { - if (hcp->jack && jack_status != hcp->jack_status) { - snd_soc_jack_report(hcp->jack, jack_status, SND_JACK_LINEOUT); + if (jack_status != hcp->jack_status) { + if (hcp->jack) + snd_soc_jack_report(hcp->jack, jack_status, SND_JACK_LINEOUT); hcp->jack_status = jack_status; } } @@ -880,6 +881,13 @@ static int hdmi_codec_set_jack(struct snd_soc_component *component, if (hcp->hcd.ops->hook_plugged_cb) { hcp->jack = jack; + + /* + * Report the initial jack status which may have been provided + * by the parent hdmi driver while the hpd hook was registered. + */ + snd_soc_jack_report(jack, hcp->jack_status, SND_JACK_LINEOUT); + return 0; } diff --git a/sound/soc/codecs/tas2781-comlib.c b/sound/soc/codecs/tas2781-comlib.c index ffb26e4a7e2f..00e35169ae49 100644 --- a/sound/soc/codecs/tas2781-comlib.c +++ b/sound/soc/codecs/tas2781-comlib.c @@ -39,7 +39,7 @@ static const struct regmap_range_cfg tasdevice_ranges[] = { static const struct regmap_config tasdevice_regmap = { .reg_bits = 8, .val_bits = 8, - .cache_type = REGCACHE_RBTREE, + .cache_type = REGCACHE_NONE, .ranges = tasdevice_ranges, .num_ranges = ARRAY_SIZE(tasdevice_ranges), .max_register = 256 * 128, @@ -316,8 +316,6 @@ int tasdevice_init(struct tasdevice_priv *tas_priv) tas_priv->tasdevice[i].cur_conf = -1; } - dev_set_drvdata(tas_priv->dev, tas_priv); - mutex_init(&tas_priv->codec_lock); out: diff --git a/sound/soc/codecs/tas2781-fmwlib.c b/sound/soc/codecs/tas2781-fmwlib.c index 4efe95b60aaa..5c09e441a936 100644 --- a/sound/soc/codecs/tas2781-fmwlib.c +++ b/sound/soc/codecs/tas2781-fmwlib.c @@ -2189,11 +2189,11 @@ int tasdevice_select_tuningprm_cfg(void *context, int prm_no, goto out; } - conf = &(tas_fmw->configs[cfg_no]); for (i = 0, prog_status = 0; i < tas_priv->ndev; i++) { if (cfg_info[rca_conf_no]->active_dev & (1 << i)) { - if (tas_priv->tasdevice[i].cur_prog != prm_no - || tas_priv->force_fwload_status) { + if (prm_no >= 0 + && (tas_priv->tasdevice[i].cur_prog != prm_no + || tas_priv->force_fwload_status)) { tas_priv->tasdevice[i].cur_conf = -1; tas_priv->tasdevice[i].is_loading = true; prog_status++; @@ -2228,7 +2228,8 @@ int tasdevice_select_tuningprm_cfg(void *context, int prm_no, } for (i = 0, status = 0; i < tas_priv->ndev; i++) { - if (tas_priv->tasdevice[i].cur_conf != cfg_no + if (cfg_no >= 0 + && tas_priv->tasdevice[i].cur_conf != cfg_no && (cfg_info[rca_conf_no]->active_dev & (1 << i)) && (tas_priv->tasdevice[i].is_loaderr == false)) { status++; @@ -2238,6 +2239,7 @@ int tasdevice_select_tuningprm_cfg(void *context, int prm_no, } if (status) { + conf = &(tas_fmw->configs[cfg_no]); status = 0; tasdevice_load_data(tas_priv, &(conf->dev_data)); for (i = 0; i < tas_priv->ndev; i++) { @@ -2281,7 +2283,7 @@ int tasdevice_prmg_load(void *context, int prm_no) } for (i = 0, prog_status = 0; i < tas_priv->ndev; i++) { - if (tas_priv->tasdevice[i].cur_prog != prm_no) { + if (prm_no >= 0 && tas_priv->tasdevice[i].cur_prog != prm_no) { tas_priv->tasdevice[i].cur_conf = -1; tas_priv->tasdevice[i].is_loading = true; prog_status++; @@ -2326,7 +2328,7 @@ int tasdevice_prmg_calibdata_load(void *context, int prm_no) } for (i = 0, prog_status = 0; i < tas_priv->ndev; i++) { - if (tas_priv->tasdevice[i].cur_prog != prm_no) { + if (prm_no >= 0 && tas_priv->tasdevice[i].cur_prog != prm_no) { tas_priv->tasdevice[i].cur_conf = -1; tas_priv->tasdevice[i].is_loading = true; prog_status++; diff --git a/sound/soc/codecs/tas2781-i2c.c b/sound/soc/codecs/tas2781-i2c.c index 55cd5e3c23a5..917b1c15f71d 100644 --- a/sound/soc/codecs/tas2781-i2c.c +++ b/sound/soc/codecs/tas2781-i2c.c @@ -689,6 +689,8 @@ static int tasdevice_i2c_probe(struct i2c_client *i2c) if (!tas_priv) return -ENOMEM; + dev_set_drvdata(&i2c->dev, tas_priv); + if (ACPI_HANDLE(&i2c->dev)) { acpi_id = acpi_match_device(i2c->dev.driver->acpi_match_table, &i2c->dev); diff --git a/sound/soc/fsl/fsl_rpmsg.c b/sound/soc/fsl/fsl_rpmsg.c index 5c5c04ce9db7..00852f174a69 100644 --- a/sound/soc/fsl/fsl_rpmsg.c +++ b/sound/soc/fsl/fsl_rpmsg.c @@ -238,7 +238,7 @@ static int fsl_rpmsg_probe(struct platform_device *pdev) ret = devm_snd_soc_register_component(&pdev->dev, &fsl_component, &fsl_rpmsg_dai, 1); if (ret) - return ret; + goto err_pm_disable; rpmsg->card_pdev = platform_device_register_data(&pdev->dev, "imx-audio-rpmsg", @@ -248,16 +248,22 @@ static int fsl_rpmsg_probe(struct platform_device *pdev) if (IS_ERR(rpmsg->card_pdev)) { dev_err(&pdev->dev, "failed to register rpmsg card\n"); ret = PTR_ERR(rpmsg->card_pdev); - return ret; + goto err_pm_disable; } return 0; + +err_pm_disable: + pm_runtime_disable(&pdev->dev); + return ret; } static void fsl_rpmsg_remove(struct platform_device *pdev) { struct fsl_rpmsg *rpmsg = platform_get_drvdata(pdev); + pm_runtime_disable(&pdev->dev); + if (rpmsg->card_pdev) platform_device_unregister(rpmsg->card_pdev); } diff --git a/sound/soc/fsl/fsl_sai.c b/sound/soc/fsl/fsl_sai.c index 32bbe5056a63..546bd4e333b5 100644 --- a/sound/soc/fsl/fsl_sai.c +++ b/sound/soc/fsl/fsl_sai.c @@ -714,6 +714,9 @@ static int fsl_sai_hw_free(struct snd_pcm_substream *substream, bool tx = substream->stream == SNDRV_PCM_STREAM_PLAYBACK; unsigned int ofs = sai->soc_data->reg_offset; + /* Clear xMR to avoid channel swap with mclk_with_tere enabled case */ + regmap_write(sai->regmap, FSL_SAI_xMR(tx), 0); + regmap_update_bits(sai->regmap, FSL_SAI_xCR3(tx, ofs), FSL_SAI_CR3_TRCE_MASK, 0); diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c index ed14d9e4aa53..42466b4b1ca4 100644 --- a/sound/soc/intel/boards/bytcr_rt5640.c +++ b/sound/soc/intel/boards/bytcr_rt5640.c @@ -83,6 +83,7 @@ enum { #define BYT_RT5640_HSMIC2_ON_IN1 BIT(27) #define BYT_RT5640_JD_HP_ELITEP_1000G2 BIT(28) #define BYT_RT5640_USE_AMCR0F28 BIT(29) +#define BYT_RT5640_SWAPPED_SPEAKERS BIT(30) #define BYTCR_INPUT_DEFAULTS \ (BYT_RT5640_IN3_MAP | \ @@ -157,6 +158,8 @@ static void log_quirks(struct device *dev) dev_info(dev, "quirk MONO_SPEAKER enabled\n"); if (byt_rt5640_quirk & BYT_RT5640_NO_SPEAKERS) dev_info(dev, "quirk NO_SPEAKERS enabled\n"); + if (byt_rt5640_quirk & BYT_RT5640_SWAPPED_SPEAKERS) + dev_info(dev, "quirk SWAPPED_SPEAKERS enabled\n"); if (byt_rt5640_quirk & BYT_RT5640_LINEOUT) dev_info(dev, "quirk LINEOUT enabled\n"); if (byt_rt5640_quirk & BYT_RT5640_LINEOUT_AS_HP2) @@ -894,6 +897,19 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = { BYT_RT5640_SSP0_AIF1 | BYT_RT5640_MCLK_EN), }, + { + /* Medion Lifetab S10346 */ + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"), + DMI_MATCH(DMI_BOARD_NAME, "Aptio CRB"), + /* Above strings are much too generic, also match on BIOS date */ + DMI_MATCH(DMI_BIOS_DATE, "10/22/2015"), + }, + .driver_data = (void *)(BYTCR_INPUT_DEFAULTS | + BYT_RT5640_SWAPPED_SPEAKERS | + BYT_RT5640_SSP0_AIF1 | + BYT_RT5640_MCLK_EN), + }, { /* Mele PCG03 Mini PC */ .matches = { DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "Mini PC"), @@ -1619,11 +1635,11 @@ static int snd_byt_rt5640_mc_probe(struct platform_device *pdev) const char *platform_name; struct acpi_device *adev; struct device *codec_dev; + const char *cfg_spk; bool sof_parent; int ret_val = 0; int dai_index = 0; - int i, cfg_spk; - int aif; + int i, aif; is_bytcr = false; priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); @@ -1783,13 +1799,16 @@ static int snd_byt_rt5640_mc_probe(struct platform_device *pdev) } if (byt_rt5640_quirk & BYT_RT5640_NO_SPEAKERS) { - cfg_spk = 0; + cfg_spk = "0"; spk_type = "none"; } else if (byt_rt5640_quirk & BYT_RT5640_MONO_SPEAKER) { - cfg_spk = 1; + cfg_spk = "1"; spk_type = "mono"; + } else if (byt_rt5640_quirk & BYT_RT5640_SWAPPED_SPEAKERS) { + cfg_spk = "swapped"; + spk_type = "swapped"; } else { - cfg_spk = 2; + cfg_spk = "2"; spk_type = "stereo"; } @@ -1804,7 +1823,7 @@ static int snd_byt_rt5640_mc_probe(struct platform_device *pdev) headset2_string = " cfg-hs2:in1"; snprintf(byt_rt5640_components, sizeof(byt_rt5640_components), - "cfg-spk:%d cfg-mic:%s aif:%d%s%s", cfg_spk, + "cfg-spk:%s cfg-mic:%s aif:%d%s%s", cfg_spk, map_name[BYT_RT5640_MAP(byt_rt5640_quirk)], aif, lineout_string, headset2_string); byt_rt5640_card.components = byt_rt5640_components; diff --git a/sound/soc/intel/common/soc-acpi-intel-mtl-match.c b/sound/soc/intel/common/soc-acpi-intel-mtl-match.c index 301b8142d554..9008b6768205 100644 --- a/sound/soc/intel/common/soc-acpi-intel-mtl-match.c +++ b/sound/soc/intel/common/soc-acpi-intel-mtl-match.c @@ -306,13 +306,13 @@ static const struct snd_soc_acpi_adr_device cs35l56_1_adr[] = { .adr = 0x00013701FA355601ull, .num_endpoints = 1, .endpoints = &spk_r_endpoint, - .name_prefix = "cs35l56-8" + .name_prefix = "AMP8" }, { .adr = 0x00013601FA355601ull, .num_endpoints = 1, .endpoints = &spk_3_endpoint, - .name_prefix = "cs35l56-7" + .name_prefix = "AMP7" } }; @@ -321,13 +321,13 @@ static const struct snd_soc_acpi_adr_device cs35l56_2_adr[] = { .adr = 0x00023301FA355601ull, .num_endpoints = 1, .endpoints = &spk_l_endpoint, - .name_prefix = "cs35l56-1" + .name_prefix = "AMP1" }, { .adr = 0x00023201FA355601ull, .num_endpoints = 1, .endpoints = &spk_2_endpoint, - .name_prefix = "cs35l56-2" + .name_prefix = "AMP2" } }; diff --git a/sound/soc/mediatek/mt8186/mt8186-dai-adda.c b/sound/soc/mediatek/mt8186/mt8186-dai-adda.c index 85ae3f76d951..ad6d4b5cf697 100644 --- a/sound/soc/mediatek/mt8186/mt8186-dai-adda.c +++ b/sound/soc/mediatek/mt8186/mt8186-dai-adda.c @@ -499,7 +499,7 @@ static const struct snd_soc_dapm_widget mtk_dai_adda_widgets[] = { SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMD), SND_SOC_DAPM_SUPPLY_S("AUD_PAD_TOP", SUPPLY_SEQ_ADDA_AUD_PAD_TOP, - 0, 0, 0, + AFE_AUD_PAD_TOP, RG_RX_FIFO_ON_SFT, 0, mtk_adda_pad_top_event, SND_SOC_DAPM_PRE_PMU), SND_SOC_DAPM_SUPPLY_S("ADDA_MTKAIF_CFG", SUPPLY_SEQ_ADDA_MTKAIF_CFG, diff --git a/sound/soc/meson/g12a-toacodec.c b/sound/soc/meson/g12a-toacodec.c index 6c4503766fdc..531bb8707a3e 100644 --- a/sound/soc/meson/g12a-toacodec.c +++ b/sound/soc/meson/g12a-toacodec.c @@ -71,6 +71,9 @@ static int g12a_toacodec_mux_put_enum(struct snd_kcontrol *kcontrol, struct soc_enum *e = (struct soc_enum *)kcontrol->private_value; unsigned int mux, reg; + if (ucontrol->value.enumerated.item[0] >= e->items) + return -EINVAL; + mux = snd_soc_enum_item_to_val(e, ucontrol->value.enumerated.item[0]); regmap_field_read(priv->field_dat_sel, ®); @@ -101,7 +104,7 @@ static int g12a_toacodec_mux_put_enum(struct snd_kcontrol *kcontrol, snd_soc_dapm_mux_update_power(dapm, kcontrol, mux, e, NULL); - return 0; + return 1; } static SOC_ENUM_SINGLE_DECL(g12a_toacodec_mux_enum, TOACODEC_CTRL0, diff --git a/sound/soc/meson/g12a-tohdmitx.c b/sound/soc/meson/g12a-tohdmitx.c index f7ef9aa1eed8..b92434125fac 100644 --- a/sound/soc/meson/g12a-tohdmitx.c +++ b/sound/soc/meson/g12a-tohdmitx.c @@ -45,6 +45,9 @@ static int g12a_tohdmitx_i2s_mux_put_enum(struct snd_kcontrol *kcontrol, struct soc_enum *e = (struct soc_enum *)kcontrol->private_value; unsigned int mux, changed; + if (ucontrol->value.enumerated.item[0] >= e->items) + return -EINVAL; + mux = snd_soc_enum_item_to_val(e, ucontrol->value.enumerated.item[0]); changed = snd_soc_component_test_bits(component, e->reg, CTRL0_I2S_DAT_SEL, @@ -93,6 +96,9 @@ static int g12a_tohdmitx_spdif_mux_put_enum(struct snd_kcontrol *kcontrol, struct soc_enum *e = (struct soc_enum *)kcontrol->private_value; unsigned int mux, changed; + if (ucontrol->value.enumerated.item[0] >= e->items) + return -EINVAL; + mux = snd_soc_enum_item_to_val(e, ucontrol->value.enumerated.item[0]); changed = snd_soc_component_test_bits(component, TOHDMITX_CTRL0, CTRL0_SPDIF_SEL, @@ -112,7 +118,7 @@ static int g12a_tohdmitx_spdif_mux_put_enum(struct snd_kcontrol *kcontrol, snd_soc_dapm_mux_update_power(dapm, kcontrol, mux, e, NULL); - return 0; + return 1; } static SOC_ENUM_SINGLE_DECL(g12a_tohdmitx_spdif_mux_enum, TOHDMITX_CTRL0, diff --git a/sound/soc/sof/intel/hda-codec.c b/sound/soc/sof/intel/hda-codec.c index 28ecbebb4b84..9f84b0d287a5 100644 --- a/sound/soc/sof/intel/hda-codec.c +++ b/sound/soc/sof/intel/hda-codec.c @@ -54,8 +54,16 @@ static int request_codec_module(struct hda_codec *codec) static int hda_codec_load_module(struct hda_codec *codec) { - int ret = request_codec_module(codec); + int ret; + + ret = snd_hdac_device_register(&codec->core); + if (ret) { + dev_err(&codec->core.dev, "failed to register hdac device\n"); + put_device(&codec->core.dev); + return ret; + } + ret = request_codec_module(codec); if (ret <= 0) { codec->probe_id = HDA_CODEC_ID_GENERIC; ret = request_codec_module(codec); @@ -116,7 +124,6 @@ EXPORT_SYMBOL_NS_GPL(hda_codec_jack_check, SND_SOC_SOF_HDA_AUDIO_CODEC); static struct hda_codec *hda_codec_device_init(struct hdac_bus *bus, int addr, int type) { struct hda_codec *codec; - int ret; codec = snd_hda_codec_device_init(to_hda_bus(bus), addr, "ehdaudio%dD%d", bus->idx, addr); if (IS_ERR(codec)) { @@ -126,13 +133,6 @@ static struct hda_codec *hda_codec_device_init(struct hdac_bus *bus, int addr, i codec->core.type = type; - ret = snd_hdac_device_register(&codec->core); - if (ret) { - dev_err(bus->dev, "failed to register hdac device\n"); - put_device(&codec->core.dev); - return ERR_PTR(ret); - } - return codec; } diff --git a/sound/soc/sof/mediatek/mt8186/mt8186.c b/sound/soc/sof/mediatek/mt8186/mt8186.c index e0d88e7aa8ca..b69fa788b16f 100644 --- a/sound/soc/sof/mediatek/mt8186/mt8186.c +++ b/sound/soc/sof/mediatek/mt8186/mt8186.c @@ -597,9 +597,6 @@ static struct snd_sof_dsp_ops sof_mt8186_ops = { static struct snd_sof_of_mach sof_mt8186_machs[] = { { - .compatible = "google,steelix", - .sof_tplg_filename = "sof-mt8186-google-steelix.tplg" - }, { .compatible = "mediatek,mt8186", .sof_tplg_filename = "sof-mt8186.tplg", }, diff --git a/sound/usb/mixer_scarlett2.c b/sound/usb/mixer_scarlett2.c index f7c57a2c3028..33a3d1161885 100644 --- a/sound/usb/mixer_scarlett2.c +++ b/sound/usb/mixer_scarlett2.c @@ -1966,7 +1966,7 @@ static int scarlett2_usb_get_meter_levels(struct usb_mixer_interface *mixer, __le16 num_meters; __le32 magic; } __packed req; - u32 resp[SCARLETT2_MAX_METERS]; + __le32 resp[SCARLETT2_MAX_METERS]; int i, err; req.pad = 0; @@ -1979,7 +1979,7 @@ static int scarlett2_usb_get_meter_levels(struct usb_mixer_interface *mixer, /* copy, convert to u16 */ for (i = 0; i < num_meters; i++) - levels[i] = resp[i]; + levels[i] = le32_to_cpu(resp[i]); return 0; } diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index ab2b938502eb..07cc6a201579 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1387,7 +1387,7 @@ free_buf: static int snd_usb_motu_m_series_boot_quirk(struct usb_device *dev) { - msleep(2000); + msleep(4000); return 0; } @@ -1630,7 +1630,7 @@ int snd_usb_apply_boot_quirk_once(struct usb_device *dev, unsigned int id) { switch (id) { - case USB_ID(0x07fd, 0x0008): /* MOTU M Series */ + case USB_ID(0x07fd, 0x0008): /* MOTU M Series, 1st hardware version */ return snd_usb_motu_m_series_boot_quirk(dev); } diff --git a/tools/objtool/noreturns.h b/tools/objtool/noreturns.h index 649ebdef9c3f..1685d7ea6a9f 100644 --- a/tools/objtool/noreturns.h +++ b/tools/objtool/noreturns.h @@ -6,7 +6,6 @@ * * Yes, this is unfortunate. A better solution is in the works. */ -NORETURN(__invalid_creds) NORETURN(__kunit_abort) NORETURN(__module_put_and_kthread_exit) NORETURN(__reiserfs_panic) diff --git a/tools/testing/cxl/Kbuild b/tools/testing/cxl/Kbuild index 90f3c9802ffb..95dc58b94178 100644 --- a/tools/testing/cxl/Kbuild +++ b/tools/testing/cxl/Kbuild @@ -62,5 +62,6 @@ cxl_core-$(CONFIG_TRACING) += $(CXL_CORE_SRC)/trace.o cxl_core-$(CONFIG_CXL_REGION) += $(CXL_CORE_SRC)/region.o cxl_core-y += config_check.o cxl_core-y += cxl_core_test.o +cxl_core-y += cxl_core_exports.o obj-m += test/ diff --git a/tools/testing/cxl/cxl_core_exports.c b/tools/testing/cxl/cxl_core_exports.c new file mode 100644 index 000000000000..077e6883921d --- /dev/null +++ b/tools/testing/cxl/cxl_core_exports.c @@ -0,0 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2022 Intel Corporation. All rights reserved. */ + +#include "cxl.h" + +/* Exporting of cxl_core symbols that are only used by cxl_test */ +EXPORT_SYMBOL_NS_GPL(cxl_num_decoders_committed, CXL); diff --git a/tools/testing/cxl/test/cxl.c b/tools/testing/cxl/test/cxl.c index b88546299902..f4e517a0c774 100644 --- a/tools/testing/cxl/test/cxl.c +++ b/tools/testing/cxl/test/cxl.c @@ -669,10 +669,11 @@ static int mock_decoder_commit(struct cxl_decoder *cxld) return 0; dev_dbg(&port->dev, "%s commit\n", dev_name(&cxld->dev)); - if (port->commit_end + 1 != id) { + if (cxl_num_decoders_committed(port) != id) { dev_dbg(&port->dev, "%s: out of order commit, expected decoder%d.%d\n", - dev_name(&cxld->dev), port->id, port->commit_end + 1); + dev_name(&cxld->dev), port->id, + cxl_num_decoders_committed(port)); return -EBUSY; } diff --git a/tools/testing/radix-tree/maple.c b/tools/testing/radix-tree/maple.c index e5da1cad70ba..76a8990bb14e 100644 --- a/tools/testing/radix-tree/maple.c +++ b/tools/testing/radix-tree/maple.c @@ -35538,7 +35538,7 @@ static noinline void __init check_prealloc(struct maple_tree *mt) MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); - MT_BUG_ON(mt, allocated != 1); + MT_BUG_ON(mt, allocated != 0); mas_store_prealloc(&mas, ptr); MT_BUG_ON(mt, mas_allocated(&mas) != 0); diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 3b2061d1c1a5..8dc3de8beb98 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -26,6 +26,8 @@ TARGETS += filesystems TARGETS += filesystems/binderfs TARGETS += filesystems/epoll TARGETS += filesystems/fat +TARGETS += filesystems/overlayfs +TARGETS += filesystems/statmount TARGETS += firmware TARGETS += fpu TARGETS += ftrace @@ -155,12 +157,10 @@ ifneq ($(KBUILD_OUTPUT),) abs_objtree := $(realpath $(abs_objtree)) BUILD := $(abs_objtree)/kselftest KHDR_INCLUDES := -isystem ${abs_objtree}/usr/include - KHDR_DIR := ${abs_objtree}/usr/include else BUILD := $(CURDIR) abs_srctree := $(shell cd $(top_srcdir) && pwd) KHDR_INCLUDES := -isystem ${abs_srctree}/usr/include - KHDR_DIR := ${abs_srctree}/usr/include DEFAULT_INSTALL_HDR_PATH := 1 endif @@ -174,7 +174,7 @@ export KHDR_INCLUDES # all isn't the first target in the file. .DEFAULT_GOAL := all -all: kernel_header_files +all: @ret=1; \ for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ @@ -185,23 +185,6 @@ all: kernel_header_files ret=$$((ret * $$?)); \ done; exit $$ret; -kernel_header_files: - @ls $(KHDR_DIR)/linux/*.h >/dev/null 2>/dev/null; \ - if [ $$? -ne 0 ]; then \ - RED='\033[1;31m'; \ - NOCOLOR='\033[0m'; \ - echo; \ - echo -e "$${RED}error$${NOCOLOR}: missing kernel header files."; \ - echo "Please run this and try again:"; \ - echo; \ - echo " cd $(top_srcdir)"; \ - echo " make headers"; \ - echo; \ - exit 1; \ - fi - -.PHONY: kernel_header_files - run_tests: all @for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ diff --git a/tools/testing/selftests/alsa/mixer-test.c b/tools/testing/selftests/alsa/mixer-test.c index 21e482b23f50..23df154fcdd7 100644 --- a/tools/testing/selftests/alsa/mixer-test.c +++ b/tools/testing/selftests/alsa/mixer-test.c @@ -138,7 +138,7 @@ static void find_controls(void) err = snd_ctl_elem_info(card_data->handle, ctl_data->info); if (err < 0) { - ksft_print_msg("%s getting info for %d\n", + ksft_print_msg("%s getting info for %s\n", snd_strerror(err), ctl_data->name); } diff --git a/tools/testing/selftests/bpf/config.x86_64 b/tools/testing/selftests/bpf/config.x86_64 index 2e70a6048278..49a29dbc1910 100644 --- a/tools/testing/selftests/bpf/config.x86_64 +++ b/tools/testing/selftests/bpf/config.x86_64 @@ -50,7 +50,6 @@ CONFIG_CRYPTO_SEQIV=y CONFIG_CRYPTO_XXHASH=y CONFIG_DCB=y CONFIG_DEBUG_ATOMIC_SLEEP=y -CONFIG_DEBUG_CREDENTIALS=y CONFIG_DEBUG_INFO_BTF=y CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y CONFIG_DEBUG_MEMORY_INIT=y diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index f75f84d0b3d7..7c2241fae19a 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -524,6 +524,37 @@ out: test_sockmap_pass_prog__destroy(pass); } +static void test_sockmap_unconnected_unix(void) +{ + int err, map, stream = 0, dgram = 0, zero = 0; + struct test_sockmap_pass_prog *skel; + + skel = test_sockmap_pass_prog__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + return; + + map = bpf_map__fd(skel->maps.sock_map_rx); + + stream = xsocket(AF_UNIX, SOCK_STREAM, 0); + if (stream < 0) + return; + + dgram = xsocket(AF_UNIX, SOCK_DGRAM, 0); + if (dgram < 0) { + close(stream); + return; + } + + err = bpf_map_update_elem(map, &zero, &stream, BPF_ANY); + ASSERT_ERR(err, "bpf_map_update_elem(stream)"); + + err = bpf_map_update_elem(map, &zero, &dgram, BPF_ANY); + ASSERT_OK(err, "bpf_map_update_elem(dgram)"); + + close(stream); + close(dgram); +} + void test_sockmap_basic(void) { if (test__start_subtest("sockmap create_update_free")) @@ -566,4 +597,7 @@ void test_sockmap_basic(void) test_sockmap_skb_verdict_fionread(false); if (test__start_subtest("sockmap skb_verdict msg_f_peek")) test_sockmap_skb_verdict_peek(); + + if (test__start_subtest("sockmap unconnected af_unix")) + test_sockmap_unconnected_unix(); } diff --git a/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh b/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh index 4917dbb35a44..5667febee328 100755 --- a/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh @@ -30,16 +30,16 @@ ip netns exec server ip addr add ${server_ip4}/24 dev eth0 ip netns exec client ip link add dev bond0 down type bond mode 1 \ miimon 100 all_slaves_active 1 -ip netns exec client ip link set dev eth0 down master bond0 +ip netns exec client ip link set dev eth0 master bond0 ip netns exec client ip link set dev bond0 up ip netns exec client ip addr add ${client_ip4}/24 dev bond0 ip netns exec client ping -c 5 $server_ip4 >/dev/null -ip netns exec client ip link set dev eth0 down nomaster +ip netns exec client ip link set dev eth0 nomaster ip netns exec client ip link set dev bond0 down ip netns exec client ip link set dev bond0 type bond mode 0 \ arp_interval 1000 arp_ip_target "+${server_ip4}" -ip netns exec client ip link set dev eth0 down master bond0 +ip netns exec client ip link set dev eth0 master bond0 ip netns exec client ip link set dev bond0 up ip netns exec client ping -c 5 $server_ip4 >/dev/null diff --git a/tools/testing/selftests/filesystems/overlayfs/.gitignore b/tools/testing/selftests/filesystems/overlayfs/.gitignore new file mode 100644 index 000000000000..52ae618fdd98 --- /dev/null +++ b/tools/testing/selftests/filesystems/overlayfs/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +dev_in_maps diff --git a/tools/testing/selftests/filesystems/overlayfs/Makefile b/tools/testing/selftests/filesystems/overlayfs/Makefile new file mode 100644 index 000000000000..56b2b48a765b --- /dev/null +++ b/tools/testing/selftests/filesystems/overlayfs/Makefile @@ -0,0 +1,7 @@ +# SPDX-License-Identifier: GPL-2.0 + +TEST_GEN_PROGS := dev_in_maps + +CFLAGS := -Wall -Werror + +include ../../lib.mk diff --git a/tools/testing/selftests/filesystems/overlayfs/dev_in_maps.c b/tools/testing/selftests/filesystems/overlayfs/dev_in_maps.c new file mode 100644 index 000000000000..e19ab0e85709 --- /dev/null +++ b/tools/testing/selftests/filesystems/overlayfs/dev_in_maps.c @@ -0,0 +1,182 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE + +#include <inttypes.h> +#include <unistd.h> +#include <stdio.h> + +#include <linux/unistd.h> +#include <linux/types.h> +#include <linux/mount.h> +#include <sys/syscall.h> +#include <sys/stat.h> +#include <sys/mount.h> +#include <sys/mman.h> +#include <sched.h> +#include <fcntl.h> + +#include "../../kselftest.h" +#include "log.h" + +static int sys_fsopen(const char *fsname, unsigned int flags) +{ + return syscall(__NR_fsopen, fsname, flags); +} + +static int sys_fsconfig(int fd, unsigned int cmd, const char *key, const char *value, int aux) +{ + return syscall(__NR_fsconfig, fd, cmd, key, value, aux); +} + +static int sys_fsmount(int fd, unsigned int flags, unsigned int attr_flags) +{ + return syscall(__NR_fsmount, fd, flags, attr_flags); +} + +static int sys_move_mount(int from_dfd, const char *from_pathname, + int to_dfd, const char *to_pathname, + unsigned int flags) +{ + return syscall(__NR_move_mount, from_dfd, from_pathname, to_dfd, to_pathname, flags); +} + +static long get_file_dev_and_inode(void *addr, struct statx *stx) +{ + char buf[4096]; + FILE *mapf; + + mapf = fopen("/proc/self/maps", "r"); + if (mapf == NULL) + return pr_perror("fopen(/proc/self/maps)"); + + while (fgets(buf, sizeof(buf), mapf)) { + unsigned long start, end; + uint32_t maj, min; + __u64 ino; + + if (sscanf(buf, "%lx-%lx %*s %*s %x:%x %llu", + &start, &end, &maj, &min, &ino) != 5) + return pr_perror("unable to parse: %s", buf); + if (start == (unsigned long)addr) { + stx->stx_dev_major = maj; + stx->stx_dev_minor = min; + stx->stx_ino = ino; + return 0; + } + } + + return pr_err("unable to find the mapping"); +} + +static int ovl_mount(void) +{ + int tmpfs, fsfd, ovl; + + fsfd = sys_fsopen("tmpfs", 0); + if (fsfd == -1) + return pr_perror("fsopen(tmpfs)"); + + if (sys_fsconfig(fsfd, FSCONFIG_CMD_CREATE, NULL, NULL, 0) == -1) + return pr_perror("FSCONFIG_CMD_CREATE"); + + tmpfs = sys_fsmount(fsfd, 0, 0); + if (tmpfs == -1) + return pr_perror("fsmount"); + + close(fsfd); + + /* overlayfs can't be constructed on top of a detached mount. */ + if (sys_move_mount(tmpfs, "", AT_FDCWD, "/tmp", MOVE_MOUNT_F_EMPTY_PATH)) + return pr_perror("move_mount"); + close(tmpfs); + + if (mkdir("/tmp/w", 0755) == -1 || + mkdir("/tmp/u", 0755) == -1 || + mkdir("/tmp/l", 0755) == -1) + return pr_perror("mkdir"); + + fsfd = sys_fsopen("overlay", 0); + if (fsfd == -1) + return pr_perror("fsopen(overlay)"); + if (sys_fsconfig(fsfd, FSCONFIG_SET_STRING, "source", "test", 0) == -1 || + sys_fsconfig(fsfd, FSCONFIG_SET_STRING, "lowerdir", "/tmp/l", 0) == -1 || + sys_fsconfig(fsfd, FSCONFIG_SET_STRING, "upperdir", "/tmp/u", 0) == -1 || + sys_fsconfig(fsfd, FSCONFIG_SET_STRING, "workdir", "/tmp/w", 0) == -1) + return pr_perror("fsconfig"); + if (sys_fsconfig(fsfd, FSCONFIG_CMD_CREATE, NULL, NULL, 0) == -1) + return pr_perror("fsconfig"); + ovl = sys_fsmount(fsfd, 0, 0); + if (ovl == -1) + return pr_perror("fsmount"); + + return ovl; +} + +/* + * Check that the file device and inode shown in /proc/pid/maps match values + * returned by stat(2). + */ +static int test(void) +{ + struct statx stx, mstx; + int ovl, fd; + void *addr; + + ovl = ovl_mount(); + if (ovl == -1) + return -1; + + fd = openat(ovl, "test", O_RDWR | O_CREAT, 0644); + if (fd == -1) + return pr_perror("openat"); + + addr = mmap(NULL, 4096, PROT_READ | PROT_WRITE, MAP_FILE | MAP_SHARED, fd, 0); + if (addr == MAP_FAILED) + return pr_perror("mmap"); + + if (get_file_dev_and_inode(addr, &mstx)) + return -1; + if (statx(fd, "", AT_EMPTY_PATH | AT_STATX_SYNC_AS_STAT, STATX_INO, &stx)) + return pr_perror("statx"); + + if (stx.stx_dev_major != mstx.stx_dev_major || + stx.stx_dev_minor != mstx.stx_dev_minor || + stx.stx_ino != mstx.stx_ino) + return pr_fail("unmatched dev:ino %x:%x:%llx (expected %x:%x:%llx)\n", + mstx.stx_dev_major, mstx.stx_dev_minor, mstx.stx_ino, + stx.stx_dev_major, stx.stx_dev_minor, stx.stx_ino); + + ksft_test_result_pass("devices are matched\n"); + return 0; +} + +int main(int argc, char **argv) +{ + int fsfd; + + fsfd = sys_fsopen("overlay", 0); + if (fsfd == -1) { + ksft_test_result_skip("unable to create overlay mount\n"); + return 1; + } + close(fsfd); + + /* Create a new mount namespace to not care about cleaning test mounts. */ + if (unshare(CLONE_NEWNS) == -1) { + ksft_test_result_skip("unable to create a new mount namespace\n"); + return 1; + } + + if (mount(NULL, "/", NULL, MS_SLAVE | MS_REC, NULL) == -1) { + pr_perror("mount"); + return 1; + } + + ksft_set_plan(1); + + if (test()) + return 1; + + ksft_exit_pass(); + return 0; +} diff --git a/tools/testing/selftests/filesystems/overlayfs/log.h b/tools/testing/selftests/filesystems/overlayfs/log.h new file mode 100644 index 000000000000..db64df2a8483 --- /dev/null +++ b/tools/testing/selftests/filesystems/overlayfs/log.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __SELFTEST_TIMENS_LOG_H__ +#define __SELFTEST_TIMENS_LOG_H__ + +#define pr_msg(fmt, lvl, ...) \ + ksft_print_msg("[%s] (%s:%d)\t" fmt "\n", \ + lvl, __FILE__, __LINE__, ##__VA_ARGS__) + +#define pr_p(func, fmt, ...) func(fmt ": %m", ##__VA_ARGS__) + +#define pr_err(fmt, ...) \ + ({ \ + ksft_test_result_error(fmt "\n", ##__VA_ARGS__); \ + -1; \ + }) + +#define pr_fail(fmt, ...) \ + ({ \ + ksft_test_result_fail(fmt, ##__VA_ARGS__); \ + -1; \ + }) + +#define pr_perror(fmt, ...) pr_p(pr_err, fmt, ##__VA_ARGS__) + +#endif diff --git a/tools/testing/selftests/filesystems/statmount/.gitignore b/tools/testing/selftests/filesystems/statmount/.gitignore new file mode 100644 index 000000000000..82a4846cbc4b --- /dev/null +++ b/tools/testing/selftests/filesystems/statmount/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +/*_test diff --git a/tools/testing/selftests/filesystems/statmount/Makefile b/tools/testing/selftests/filesystems/statmount/Makefile new file mode 100644 index 000000000000..07a0d5b545ca --- /dev/null +++ b/tools/testing/selftests/filesystems/statmount/Makefile @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0-or-later + +CFLAGS += -Wall -O2 -g $(KHDR_INCLUDES) +TEST_GEN_PROGS := statmount_test + +include ../../lib.mk diff --git a/tools/testing/selftests/filesystems/statmount/statmount_test.c b/tools/testing/selftests/filesystems/statmount/statmount_test.c new file mode 100644 index 000000000000..3eafd7da58e2 --- /dev/null +++ b/tools/testing/selftests/filesystems/statmount/statmount_test.c @@ -0,0 +1,612 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#define _GNU_SOURCE + +#include <assert.h> +#include <stdint.h> +#include <sched.h> +#include <fcntl.h> +#include <sys/param.h> +#include <sys/mount.h> +#include <sys/stat.h> +#include <sys/statfs.h> +#include <linux/mount.h> +#include <linux/stat.h> +#include <asm/unistd.h> + +#include "../../kselftest.h" + +static const char *const known_fs[] = { + "9p", "adfs", "affs", "afs", "aio", "anon_inodefs", "apparmorfs", + "autofs", "bcachefs", "bdev", "befs", "bfs", "binder", "binfmt_misc", + "bpf", "btrfs", "btrfs_test_fs", "ceph", "cgroup", "cgroup2", "cifs", + "coda", "configfs", "cpuset", "cramfs", "cxl", "dax", "debugfs", + "devpts", "devtmpfs", "dmabuf", "drm", "ecryptfs", "efivarfs", "efs", + "erofs", "exfat", "ext2", "ext3", "ext4", "f2fs", "functionfs", + "fuse", "fuseblk", "fusectl", "gadgetfs", "gfs2", "gfs2meta", "hfs", + "hfsplus", "hostfs", "hpfs", "hugetlbfs", "ibmasmfs", "iomem", + "ipathfs", "iso9660", "jffs2", "jfs", "minix", "mqueue", "msdos", + "nfs", "nfs4", "nfsd", "nilfs2", "nsfs", "ntfs", "ntfs3", "ocfs2", + "ocfs2_dlmfs", "ocxlflash", "omfs", "openpromfs", "overlay", "pipefs", + "proc", "pstore", "pvfs2", "qnx4", "qnx6", "ramfs", "reiserfs", + "resctrl", "romfs", "rootfs", "rpc_pipefs", "s390_hypfs", "secretmem", + "securityfs", "selinuxfs", "smackfs", "smb3", "sockfs", "spufs", + "squashfs", "sysfs", "sysv", "tmpfs", "tracefs", "ubifs", "udf", + "ufs", "v7", "vboxsf", "vfat", "virtiofs", "vxfs", "xenfs", "xfs", + "zonefs", NULL }; + +static int statmount(uint64_t mnt_id, uint64_t mask, struct statmount *buf, + size_t bufsize, unsigned int flags) +{ + struct mnt_id_req req = { + .size = MNT_ID_REQ_SIZE_VER0, + .mnt_id = mnt_id, + .param = mask, + }; + + return syscall(__NR_statmount, &req, buf, bufsize, flags); +} + +static struct statmount *statmount_alloc(uint64_t mnt_id, uint64_t mask, unsigned int flags) +{ + size_t bufsize = 1 << 15; + struct statmount *buf = NULL, *tmp = alloca(bufsize); + int tofree = 0; + int ret; + + for (;;) { + ret = statmount(mnt_id, mask, tmp, bufsize, flags); + if (ret != -1) + break; + if (tofree) + free(tmp); + if (errno != EOVERFLOW) + return NULL; + bufsize <<= 1; + tofree = 1; + tmp = malloc(bufsize); + if (!tmp) + return NULL; + } + buf = malloc(tmp->size); + if (buf) + memcpy(buf, tmp, tmp->size); + if (tofree) + free(tmp); + + return buf; +} + +static void write_file(const char *path, const char *val) +{ + int fd = open(path, O_WRONLY); + size_t len = strlen(val); + int ret; + + if (fd == -1) + ksft_exit_fail_msg("opening %s for write: %s\n", path, strerror(errno)); + + ret = write(fd, val, len); + if (ret == -1) + ksft_exit_fail_msg("writing to %s: %s\n", path, strerror(errno)); + if (ret != len) + ksft_exit_fail_msg("short write to %s\n", path); + + ret = close(fd); + if (ret == -1) + ksft_exit_fail_msg("closing %s\n", path); +} + +static uint64_t get_mnt_id(const char *name, const char *path, uint64_t mask) +{ + struct statx sx; + int ret; + + ret = statx(AT_FDCWD, path, 0, mask, &sx); + if (ret == -1) + ksft_exit_fail_msg("retrieving %s mount ID for %s: %s\n", + mask & STATX_MNT_ID_UNIQUE ? "unique" : "old", + name, strerror(errno)); + if (!(sx.stx_mask & mask)) + ksft_exit_fail_msg("no %s mount ID available for %s\n", + mask & STATX_MNT_ID_UNIQUE ? "unique" : "old", + name); + + return sx.stx_mnt_id; +} + + +static char root_mntpoint[] = "/tmp/statmount_test_root.XXXXXX"; +static int orig_root; +static uint64_t root_id, parent_id; +static uint32_t old_root_id, old_parent_id; + + +static void cleanup_namespace(void) +{ + fchdir(orig_root); + chroot("."); + umount2(root_mntpoint, MNT_DETACH); + rmdir(root_mntpoint); +} + +static void setup_namespace(void) +{ + int ret; + char buf[32]; + uid_t uid = getuid(); + gid_t gid = getgid(); + + ret = unshare(CLONE_NEWNS|CLONE_NEWUSER); + if (ret == -1) + ksft_exit_fail_msg("unsharing mountns and userns: %s\n", + strerror(errno)); + + sprintf(buf, "0 %d 1", uid); + write_file("/proc/self/uid_map", buf); + write_file("/proc/self/setgroups", "deny"); + sprintf(buf, "0 %d 1", gid); + write_file("/proc/self/gid_map", buf); + + ret = mount("", "/", NULL, MS_REC|MS_PRIVATE, NULL); + if (ret == -1) + ksft_exit_fail_msg("making mount tree private: %s\n", + strerror(errno)); + + if (!mkdtemp(root_mntpoint)) + ksft_exit_fail_msg("creating temporary directory %s: %s\n", + root_mntpoint, strerror(errno)); + + old_parent_id = get_mnt_id("parent", root_mntpoint, STATX_MNT_ID); + parent_id = get_mnt_id("parent", root_mntpoint, STATX_MNT_ID_UNIQUE); + + orig_root = open("/", O_PATH); + if (orig_root == -1) + ksft_exit_fail_msg("opening root directory: %s", + strerror(errno)); + + atexit(cleanup_namespace); + + ret = mount(root_mntpoint, root_mntpoint, NULL, MS_BIND, NULL); + if (ret == -1) + ksft_exit_fail_msg("mounting temp root %s: %s\n", + root_mntpoint, strerror(errno)); + + ret = chroot(root_mntpoint); + if (ret == -1) + ksft_exit_fail_msg("chroot to temp root %s: %s\n", + root_mntpoint, strerror(errno)); + + ret = chdir("/"); + if (ret == -1) + ksft_exit_fail_msg("chdir to root: %s\n", strerror(errno)); + + old_root_id = get_mnt_id("root", "/", STATX_MNT_ID); + root_id = get_mnt_id("root", "/", STATX_MNT_ID_UNIQUE); +} + +static int setup_mount_tree(int log2_num) +{ + int ret, i; + + ret = mount("", "/", NULL, MS_REC|MS_SHARED, NULL); + if (ret == -1) { + ksft_test_result_fail("making mount tree shared: %s\n", + strerror(errno)); + return -1; + } + + for (i = 0; i < log2_num; i++) { + ret = mount("/", "/", NULL, MS_BIND, NULL); + if (ret == -1) { + ksft_test_result_fail("mounting submount %s: %s\n", + root_mntpoint, strerror(errno)); + return -1; + } + } + return 0; +} + +static ssize_t listmount(uint64_t mnt_id, uint64_t last_mnt_id, + uint64_t list[], size_t num, unsigned int flags) +{ + struct mnt_id_req req = { + .size = MNT_ID_REQ_SIZE_VER0, + .mnt_id = mnt_id, + .param = last_mnt_id, + }; + + return syscall(__NR_listmount, &req, list, num, flags); +} + +static void test_listmount_empty_root(void) +{ + ssize_t res; + const unsigned int size = 32; + uint64_t list[size]; + + res = listmount(LSMT_ROOT, 0, list, size, 0); + if (res == -1) { + ksft_test_result_fail("listmount: %s\n", strerror(errno)); + return; + } + if (res != 1) { + ksft_test_result_fail("listmount result is %zi != 1\n", res); + return; + } + + if (list[0] != root_id) { + ksft_test_result_fail("listmount ID doesn't match 0x%llx != 0x%llx\n", + (unsigned long long) list[0], + (unsigned long long) root_id); + return; + } + + ksft_test_result_pass("listmount empty root\n"); +} + +static void test_statmount_zero_mask(void) +{ + struct statmount sm; + int ret; + + ret = statmount(root_id, 0, &sm, sizeof(sm), 0); + if (ret == -1) { + ksft_test_result_fail("statmount zero mask: %s\n", + strerror(errno)); + return; + } + if (sm.size != sizeof(sm)) { + ksft_test_result_fail("unexpected size: %u != %u\n", + sm.size, (uint32_t) sizeof(sm)); + return; + } + if (sm.mask != 0) { + ksft_test_result_fail("unexpected mask: 0x%llx != 0x0\n", + (unsigned long long) sm.mask); + return; + } + + ksft_test_result_pass("statmount zero mask\n"); +} + +static void test_statmount_mnt_basic(void) +{ + struct statmount sm; + int ret; + uint64_t mask = STATMOUNT_MNT_BASIC; + + ret = statmount(root_id, mask, &sm, sizeof(sm), 0); + if (ret == -1) { + ksft_test_result_fail("statmount mnt basic: %s\n", + strerror(errno)); + return; + } + if (sm.size != sizeof(sm)) { + ksft_test_result_fail("unexpected size: %u != %u\n", + sm.size, (uint32_t) sizeof(sm)); + return; + } + if (sm.mask != mask) { + ksft_test_result_skip("statmount mnt basic unavailable\n"); + return; + } + + if (sm.mnt_id != root_id) { + ksft_test_result_fail("unexpected root ID: 0x%llx != 0x%llx\n", + (unsigned long long) sm.mnt_id, + (unsigned long long) root_id); + return; + } + + if (sm.mnt_id_old != old_root_id) { + ksft_test_result_fail("unexpected old root ID: %u != %u\n", + sm.mnt_id_old, old_root_id); + return; + } + + if (sm.mnt_parent_id != parent_id) { + ksft_test_result_fail("unexpected parent ID: 0x%llx != 0x%llx\n", + (unsigned long long) sm.mnt_parent_id, + (unsigned long long) parent_id); + return; + } + + if (sm.mnt_parent_id_old != old_parent_id) { + ksft_test_result_fail("unexpected old parent ID: %u != %u\n", + sm.mnt_parent_id_old, old_parent_id); + return; + } + + if (sm.mnt_propagation != MS_PRIVATE) { + ksft_test_result_fail("unexpected propagation: 0x%llx\n", + (unsigned long long) sm.mnt_propagation); + return; + } + + ksft_test_result_pass("statmount mnt basic\n"); +} + + +static void test_statmount_sb_basic(void) +{ + struct statmount sm; + int ret; + uint64_t mask = STATMOUNT_SB_BASIC; + struct statx sx; + struct statfs sf; + + ret = statmount(root_id, mask, &sm, sizeof(sm), 0); + if (ret == -1) { + ksft_test_result_fail("statmount sb basic: %s\n", + strerror(errno)); + return; + } + if (sm.size != sizeof(sm)) { + ksft_test_result_fail("unexpected size: %u != %u\n", + sm.size, (uint32_t) sizeof(sm)); + return; + } + if (sm.mask != mask) { + ksft_test_result_skip("statmount sb basic unavailable\n"); + return; + } + + ret = statx(AT_FDCWD, "/", 0, 0, &sx); + if (ret == -1) { + ksft_test_result_fail("stat root failed: %s\n", + strerror(errno)); + return; + } + + if (sm.sb_dev_major != sx.stx_dev_major || + sm.sb_dev_minor != sx.stx_dev_minor) { + ksft_test_result_fail("unexpected sb dev %u:%u != %u:%u\n", + sm.sb_dev_major, sm.sb_dev_minor, + sx.stx_dev_major, sx.stx_dev_minor); + return; + } + + ret = statfs("/", &sf); + if (ret == -1) { + ksft_test_result_fail("statfs root failed: %s\n", + strerror(errno)); + return; + } + + if (sm.sb_magic != sf.f_type) { + ksft_test_result_fail("unexpected sb magic: 0x%llx != 0x%lx\n", + (unsigned long long) sm.sb_magic, + sf.f_type); + return; + } + + ksft_test_result_pass("statmount sb basic\n"); +} + +static void test_statmount_mnt_point(void) +{ + struct statmount *sm; + + sm = statmount_alloc(root_id, STATMOUNT_MNT_POINT, 0); + if (!sm) { + ksft_test_result_fail("statmount mount point: %s\n", + strerror(errno)); + return; + } + + if (strcmp(sm->str + sm->mnt_point, "/") != 0) { + ksft_test_result_fail("unexpected mount point: '%s' != '/'\n", + sm->str + sm->mnt_point); + goto out; + } + ksft_test_result_pass("statmount mount point\n"); +out: + free(sm); +} + +static void test_statmount_mnt_root(void) +{ + struct statmount *sm; + const char *mnt_root, *last_dir, *last_root; + + last_dir = strrchr(root_mntpoint, '/'); + assert(last_dir); + last_dir++; + + sm = statmount_alloc(root_id, STATMOUNT_MNT_ROOT, 0); + if (!sm) { + ksft_test_result_fail("statmount mount root: %s\n", + strerror(errno)); + return; + } + mnt_root = sm->str + sm->mnt_root; + last_root = strrchr(mnt_root, '/'); + if (last_root) + last_root++; + else + last_root = mnt_root; + + if (strcmp(last_dir, last_root) != 0) { + ksft_test_result_fail("unexpected mount root last component: '%s' != '%s'\n", + last_root, last_dir); + goto out; + } + ksft_test_result_pass("statmount mount root\n"); +out: + free(sm); +} + +static void test_statmount_fs_type(void) +{ + struct statmount *sm; + const char *fs_type; + const char *const *s; + + sm = statmount_alloc(root_id, STATMOUNT_FS_TYPE, 0); + if (!sm) { + ksft_test_result_fail("statmount fs type: %s\n", + strerror(errno)); + return; + } + fs_type = sm->str + sm->fs_type; + for (s = known_fs; s != NULL; s++) { + if (strcmp(fs_type, *s) == 0) + break; + } + if (!s) + ksft_print_msg("unknown filesystem type: %s\n", fs_type); + + ksft_test_result_pass("statmount fs type\n"); + free(sm); +} + +static void test_statmount_string(uint64_t mask, size_t off, const char *name) +{ + struct statmount *sm; + size_t len, shortsize, exactsize; + uint32_t start, i; + int ret; + + sm = statmount_alloc(root_id, mask, 0); + if (!sm) { + ksft_test_result_fail("statmount %s: %s\n", name, + strerror(errno)); + goto out; + } + if (sm->size < sizeof(*sm)) { + ksft_test_result_fail("unexpected size: %u < %u\n", + sm->size, (uint32_t) sizeof(*sm)); + goto out; + } + if (sm->mask != mask) { + ksft_test_result_skip("statmount %s unavailable\n", name); + goto out; + } + len = sm->size - sizeof(*sm); + start = ((uint32_t *) sm)[off]; + + for (i = start;; i++) { + if (i >= len) { + ksft_test_result_fail("string out of bounds\n"); + goto out; + } + if (!sm->str[i]) + break; + } + exactsize = sm->size; + shortsize = sizeof(*sm) + i; + + ret = statmount(root_id, mask, sm, exactsize, 0); + if (ret == -1) { + ksft_test_result_fail("statmount exact size: %s\n", + strerror(errno)); + goto out; + } + errno = 0; + ret = statmount(root_id, mask, sm, shortsize, 0); + if (ret != -1 || errno != EOVERFLOW) { + ksft_test_result_fail("should have failed with EOVERFLOW: %s\n", + strerror(errno)); + goto out; + } + + ksft_test_result_pass("statmount string %s\n", name); +out: + free(sm); +} + +static void test_listmount_tree(void) +{ + ssize_t res; + const unsigned int log2_num = 4; + const unsigned int step = 3; + const unsigned int size = (1 << log2_num) + step + 1; + size_t num, expect = 1 << log2_num; + uint64_t list[size]; + uint64_t list2[size]; + size_t i; + + + res = setup_mount_tree(log2_num); + if (res == -1) + return; + + num = res = listmount(LSMT_ROOT, 0, list, size, 0); + if (res == -1) { + ksft_test_result_fail("listmount: %s\n", strerror(errno)); + return; + } + if (num != expect) { + ksft_test_result_fail("listmount result is %zi != %zi\n", + res, expect); + return; + } + + for (i = 0; i < size - step;) { + res = listmount(LSMT_ROOT, i ? list2[i - 1] : 0, list2 + i, step, 0); + if (res == -1) + ksft_test_result_fail("short listmount: %s\n", + strerror(errno)); + i += res; + if (res < step) + break; + } + if (i != num) { + ksft_test_result_fail("different number of entries: %zu != %zu\n", + i, num); + return; + } + for (i = 0; i < num; i++) { + if (list2[i] != list[i]) { + ksft_test_result_fail("different value for entry %zu: 0x%llx != 0x%llx\n", + i, + (unsigned long long) list2[i], + (unsigned long long) list[i]); + } + } + + ksft_test_result_pass("listmount tree\n"); +} + +#define str_off(memb) (offsetof(struct statmount, memb) / sizeof(uint32_t)) + +int main(void) +{ + int ret; + uint64_t all_mask = STATMOUNT_SB_BASIC | STATMOUNT_MNT_BASIC | + STATMOUNT_PROPAGATE_FROM | STATMOUNT_MNT_ROOT | + STATMOUNT_MNT_POINT | STATMOUNT_FS_TYPE; + + ksft_print_header(); + + ret = statmount(0, 0, NULL, 0, 0); + assert(ret == -1); + if (errno == ENOSYS) + ksft_exit_skip("statmount() syscall not supported\n"); + + setup_namespace(); + + ksft_set_plan(14); + test_listmount_empty_root(); + test_statmount_zero_mask(); + test_statmount_mnt_basic(); + test_statmount_sb_basic(); + test_statmount_mnt_root(); + test_statmount_mnt_point(); + test_statmount_fs_type(); + test_statmount_string(STATMOUNT_MNT_ROOT, str_off(mnt_root), "mount root"); + test_statmount_string(STATMOUNT_MNT_POINT, str_off(mnt_point), "mount point"); + test_statmount_string(STATMOUNT_FS_TYPE, str_off(fs_type), "fs type"); + test_statmount_string(all_mask, str_off(mnt_root), "mount root & all"); + test_statmount_string(all_mask, str_off(mnt_point), "mount point & all"); + test_statmount_string(all_mask, str_off(fs_type), "fs type & all"); + + test_listmount_tree(); + + + if (ksft_get_fail_cnt() + ksft_get_error_cnt() > 0) + ksft_exit_fail(); + else + ksft_exit_pass(); +} diff --git a/tools/testing/selftests/hid/config.common b/tools/testing/selftests/hid/config.common index 0617275d93cc..0f456dbab62f 100644 --- a/tools/testing/selftests/hid/config.common +++ b/tools/testing/selftests/hid/config.common @@ -46,7 +46,6 @@ CONFIG_CRYPTO_SEQIV=y CONFIG_CRYPTO_XXHASH=y CONFIG_DCB=y CONFIG_DEBUG_ATOMIC_SLEEP=y -CONFIG_DEBUG_CREDENTIALS=y CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y CONFIG_DEBUG_MEMORY_INIT=y CONFIG_DEFAULT_FQ_CODEL=y diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 963435959a92..3e0c36b8ddd5 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -17,16 +17,6 @@ else ARCH_DIR := $(ARCH) endif -ifeq ($(ARCH),arm64) -tools_dir := $(top_srcdir)/tools -arm64_tools_dir := $(tools_dir)/arch/arm64/tools/ -GEN_HDRS := $(top_srcdir)/tools/arch/arm64/include/generated/ -CFLAGS += -I$(GEN_HDRS) - -$(GEN_HDRS): $(wildcard $(arm64_tools_dir)/*) - $(MAKE) -C $(arm64_tools_dir) O=$(tools_dir) -endif - LIBKVM += lib/assert.c LIBKVM += lib/elf.c LIBKVM += lib/guest_modes.c @@ -234,6 +224,22 @@ CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \ ifeq ($(ARCH),s390) CFLAGS += -march=z10 endif +ifeq ($(ARCH),arm64) +tools_dir := $(top_srcdir)/tools +arm64_tools_dir := $(tools_dir)/arch/arm64/tools/ + +ifneq ($(abs_objdir),) +arm64_hdr_outdir := $(abs_objdir)/tools/ +else +arm64_hdr_outdir := $(tools_dir)/ +endif + +GEN_HDRS := $(arm64_hdr_outdir)arch/arm64/include/generated/ +CFLAGS += -I$(GEN_HDRS) + +$(GEN_HDRS): $(wildcard $(arm64_tools_dir)/*) + $(MAKE) -C $(arm64_tools_dir) OUTPUT=$(arm64_hdr_outdir) +endif no-pie-option := $(call try-run, echo 'int main(void) { return 0; }' | \ $(CC) -Werror $(CFLAGS) -no-pie -x c - -o "$$TMP", -no-pie) diff --git a/tools/testing/selftests/kvm/get-reg-list.c b/tools/testing/selftests/kvm/get-reg-list.c index be7bf5224434..8274ef04301f 100644 --- a/tools/testing/selftests/kvm/get-reg-list.c +++ b/tools/testing/selftests/kvm/get-reg-list.c @@ -71,11 +71,12 @@ static const char *config_name(struct vcpu_reg_list *c) for_each_sublist(c, s) { if (!strcmp(s->name, "base")) continue; - strcat(c->name + len, s->name); - len += strlen(s->name) + 1; - c->name[len - 1] = '+'; + if (len) + c->name[len++] = '+'; + strcpy(c->name + len, s->name); + len += strlen(s->name); } - c->name[len - 1] = '\0'; + c->name[len] = '\0'; return c->name; } diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c index 6bedaea95395..25de4b8bc347 100644 --- a/tools/testing/selftests/kvm/riscv/get-reg-list.c +++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c @@ -458,8 +458,9 @@ void print_reg(const char *prefix, __u64 id) reg_size = "KVM_REG_SIZE_U128"; break; default: - printf("\tKVM_REG_RISCV | (%lld << KVM_REG_SIZE_SHIFT) | 0x%llx /* UNKNOWN */,", - (id & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT, id & REG_MASK); + printf("\tKVM_REG_RISCV | (%lld << KVM_REG_SIZE_SHIFT) | 0x%llx /* UNKNOWN */,\n", + (id & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT, id & ~REG_MASK); + return; } switch (id & KVM_REG_RISCV_TYPE_MASK) { @@ -496,8 +497,9 @@ void print_reg(const char *prefix, __u64 id) reg_size, sbi_ext_id_to_str(prefix, id)); break; default: - printf("\tKVM_REG_RISCV | %s | 0x%llx /* UNKNOWN */,", - reg_size, id & REG_MASK); + printf("\tKVM_REG_RISCV | %s | 0x%llx /* UNKNOWN */,\n", + reg_size, id & ~REG_MASK); + return; } } diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index 118e0964bda9..aa646e0661f3 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -44,26 +44,10 @@ endif selfdir = $(realpath $(dir $(filter %/lib.mk,$(MAKEFILE_LIST)))) top_srcdir = $(selfdir)/../../.. -ifeq ("$(origin O)", "command line") - KBUILD_OUTPUT := $(O) +ifeq ($(KHDR_INCLUDES),) +KHDR_INCLUDES := -isystem $(top_srcdir)/usr/include endif -ifneq ($(KBUILD_OUTPUT),) - # Make's built-in functions such as $(abspath ...), $(realpath ...) cannot - # expand a shell special character '~'. We use a somewhat tedious way here. - abs_objtree := $(shell cd $(top_srcdir) && mkdir -p $(KBUILD_OUTPUT) && cd $(KBUILD_OUTPUT) && pwd) - $(if $(abs_objtree),, \ - $(error failed to create output directory "$(KBUILD_OUTPUT)")) - # $(realpath ...) resolves symlinks - abs_objtree := $(realpath $(abs_objtree)) - KHDR_DIR := ${abs_objtree}/usr/include -else - abs_srctree := $(shell cd $(top_srcdir) && pwd) - KHDR_DIR := ${abs_srctree}/usr/include -endif - -KHDR_INCLUDES := -isystem $(KHDR_DIR) - # The following are built by lib.mk common compile rules. # TEST_CUSTOM_PROGS should be used by tests that require # custom build rule and prevent common build rule use. @@ -74,25 +58,7 @@ TEST_GEN_PROGS := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS)) TEST_GEN_PROGS_EXTENDED := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS_EXTENDED)) TEST_GEN_FILES := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_FILES)) -all: kernel_header_files $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) \ - $(TEST_GEN_FILES) - -kernel_header_files: - @ls $(KHDR_DIR)/linux/*.h >/dev/null 2>/dev/null; \ - if [ $$? -ne 0 ]; then \ - RED='\033[1;31m'; \ - NOCOLOR='\033[0m'; \ - echo; \ - echo -e "$${RED}error$${NOCOLOR}: missing kernel header files."; \ - echo "Please run this and try again:"; \ - echo; \ - echo " cd $(top_srcdir)"; \ - echo " make headers"; \ - echo; \ - exit 1; \ - fi - -.PHONY: kernel_header_files +all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) define RUN_TESTS BASE_DIR="$(selfdir)"; \ diff --git a/tools/testing/selftests/mm/cow.c b/tools/testing/selftests/mm/cow.c index 7324ce5363c0..6f2f83990441 100644 --- a/tools/testing/selftests/mm/cow.c +++ b/tools/testing/selftests/mm/cow.c @@ -1680,6 +1680,8 @@ int main(int argc, char **argv) { int err; + ksft_print_header(); + pagesize = getpagesize(); thpsize = read_pmd_pagesize(); if (thpsize) @@ -1689,7 +1691,6 @@ int main(int argc, char **argv) ARRAY_SIZE(hugetlbsizes)); detect_huge_zeropage(); - ksft_print_header(); ksft_set_plan(ARRAY_SIZE(anon_test_cases) * tests_per_anon_test_case() + ARRAY_SIZE(anon_thp_test_cases) * tests_per_anon_thp_test_case() + ARRAY_SIZE(non_anon_test_cases) * tests_per_non_anon_test_case()); diff --git a/tools/testing/selftests/mm/memfd_secret.c b/tools/testing/selftests/mm/memfd_secret.c index 957b9e18c729..9b298f6a04b3 100644 --- a/tools/testing/selftests/mm/memfd_secret.c +++ b/tools/testing/selftests/mm/memfd_secret.c @@ -62,6 +62,9 @@ static void test_mlock_limit(int fd) char *mem; len = mlock_limit_cur; + if (len % page_size != 0) + len = (len/page_size) * page_size; + mem = mmap(NULL, len, prot, mode, fd, 0); if (mem == MAP_FAILED) { fail("unable to mmap secret memory\n"); diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 5b2aca4c5f10..9e5bf59a20bf 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -91,6 +91,7 @@ TEST_PROGS += test_bridge_neigh_suppress.sh TEST_PROGS += test_vxlan_nolocalbypass.sh TEST_PROGS += test_bridge_backup_port.sh TEST_PROGS += fdb_flush.sh +TEST_PROGS += vlan_hw_filter.sh TEST_FILES := settings diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 3c94f2f194d6..24a57b3ae215 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -2776,7 +2776,7 @@ backup_tests() fi if reset "mpc backup" && - continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then + continue_if mptcp_lib_kallsyms_doesnt_have "T mptcp_subflow_send_ack$"; then pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,backup speed=slow \ run_tests $ns1 $ns2 10.0.1.1 @@ -2785,7 +2785,7 @@ backup_tests() fi if reset "mpc backup both sides" && - continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then + continue_if mptcp_lib_kallsyms_doesnt_have "T mptcp_subflow_send_ack$"; then pm_nl_add_endpoint $ns1 10.0.1.1 flags subflow,backup pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,backup speed=slow \ @@ -2795,7 +2795,7 @@ backup_tests() fi if reset "mpc switch to backup" && - continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then + continue_if mptcp_lib_kallsyms_doesnt_have "T mptcp_subflow_send_ack$"; then pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow sflags=backup speed=slow \ run_tests $ns1 $ns2 10.0.1.1 @@ -2804,7 +2804,7 @@ backup_tests() fi if reset "mpc switch to backup both sides" && - continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then + continue_if mptcp_lib_kallsyms_doesnt_have "T mptcp_subflow_send_ack$"; then pm_nl_add_endpoint $ns1 10.0.1.1 flags subflow pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow sflags=backup speed=slow \ diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index 38be9706c45f..26827ea4e3e5 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -297,7 +297,7 @@ kci_test_addrlft() done sleep 5 - run_cmd_grep "10.23.11." ip addr show dev "$devdummy" + run_cmd_grep_fail "10.23.11." ip addr show dev "$devdummy" if [ $? -eq 0 ]; then check_err 1 end_test "FAIL: preferred_lft addresses remaining" diff --git a/tools/testing/selftests/net/vlan_hw_filter.sh b/tools/testing/selftests/net/vlan_hw_filter.sh new file mode 100755 index 000000000000..7bc804ffaf7c --- /dev/null +++ b/tools/testing/selftests/net/vlan_hw_filter.sh @@ -0,0 +1,29 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 + +readonly NETNS="ns-$(mktemp -u XXXXXX)" + +ret=0 + +cleanup() { + ip netns del $NETNS +} + +trap cleanup EXIT + +fail() { + echo "ERROR: ${1:-unexpected return code} (ret: $_)" >&2 + ret=1 +} + +ip netns add ${NETNS} +ip netns exec ${NETNS} ip link add bond0 type bond mode 0 +ip netns exec ${NETNS} ip link add bond_slave_1 type veth peer veth2 +ip netns exec ${NETNS} ip link set bond_slave_1 master bond0 +ip netns exec ${NETNS} ethtool -K bond0 rx-vlan-filter off +ip netns exec ${NETNS} ip link add link bond_slave_1 name bond_slave_1.0 type vlan id 0 +ip netns exec ${NETNS} ip link add link bond0 name bond0.0 type vlan id 0 +ip netns exec ${NETNS} ip link set bond_slave_1 nomaster +ip netns exec ${NETNS} ip link del veth2 || fail "Please check vlan HW filter function" + +exit $ret diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index 89912a17f5d5..c0e230f4c3e9 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -61,7 +61,7 @@ static void irqfd_resampler_notify(struct kvm_kernel_irqfd_resampler *resampler) list_for_each_entry_srcu(irqfd, &resampler->list, resampler_link, srcu_read_lock_held(&resampler->kvm->irq_srcu)) - eventfd_signal(irqfd->resamplefd, 1); + eventfd_signal(irqfd->resamplefd); } /* @@ -786,7 +786,7 @@ ioeventfd_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this, gpa_t addr, if (!ioeventfd_in_range(p, addr, len, val)) return -EOPNOTSUPP; - eventfd_signal(p->eventfd, 1); + eventfd_signal(p->eventfd); return 0; } diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 3b1b9e8dd70c..7db96875ac46 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -5540,7 +5540,6 @@ int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, return r < 0 ? r : 0; } -/* Caller must hold slots_lock. */ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, int len, struct kvm_io_device *dev) { @@ -5548,6 +5547,8 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, struct kvm_io_bus *new_bus, *bus; struct kvm_io_range range; + lockdep_assert_held(&kvm->slots_lock); + bus = kvm_get_bus(kvm, bus_idx); if (!bus) return -ENOMEM; |