| Age | Commit message (Collapse) | Author |
|---|
|
Fold nvme_init_ms into nvme_configure_metadata after splitting up
a little helper to deal with the extended LBA formats.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
|
|
Move reading the Identify Namespace Data Structure, NVM Command Set out
of configure_metadata into the caller. This allows doing the identify
call outside the frozen I/O queues, and prepares for using data from
the Identify data structure for other purposes.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
|
|
Split the logic to query the Identify Namespace Data Structure, NVM
Command Set into a separate helper.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
|
|
nvme_update_ns_info_generic and nvme_update_ns_info_block share a
fair amount of logic related to not fully supported namespace
formats and updating the multipath information. Move this logic
into the common caller.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
|
|
nvme_set_queue_limits is used on the admin queue and all gendisks
including hidden ones that don't support block I/O. The write cache
setting on the other hand only makes sense for block I/O. Move the
blk_queue_write_cache call to nvme_update_ns_info_block instead.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
|
|
Move setting up the integrity profile and setting the disk capacity out
of nvme_update_disk_info to get nvme_update_disk_info into a shape where
it just sets queue_limits eventually.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
|
|
Currently nvme_update_ns_info_block calls nvme_update_disk_info both for
the namespace attached disk, and the multipath one (if it exists). This
is very different from how other stacking drivers work, and leads to
a lot of complexity.
Switch to setting the disk capacity and initializing the integrity
profile, and let blk_stack_limits which already is called just below
deal with updating the other limits.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
|
|
Move uneregistering the existing integrity profile into the helper
dealing with all the other integrity / metadata setup.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
|
|
Handle the no metadata support case in nvme_init_integrity as well to
simplify the calling convention and prepare for future changes in the
area.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
|
|
max_integrity_segments is just a hardware limit and doesn't need to be
in nvme_init_integrity with the PI setup.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
|
|
Handle setting the zone size / chunk_sectors and max_append_sectors
limits together with the other ZNS limits, and just open code the
call to blk_revalidate_zones in the current place.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Keith Busch <kbusch@kernel.org>
|
|
Move the handling of the NVME_QUIRK_DEALLOCATE_ZEROES quirk out of
nvme_config_discard so that it is combined with the normal write_zeroes
limit handling.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
|
|
All transports set a max_hw_sectors value in the nvme_ctrl, so make
the code using it unconditional and clean it up using a little helper.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Reviewed-by: John Garry <john.g.garry@oracle.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/sudeep.holla/linux into soc/dt
Arm Vexpress update for v6.9
Just a single update to add stdout-path in the device tree chosen node
so that the system console can be routed to this serial/uart port.
* tag 'vexpress-update-6.9' of git://git.kernel.org/pub/scm/linux/kernel/git/sudeep.holla/linux:
ARM: dts: vexpress: Set stdout-path to serial0 in the chosen node
Link: https://lore.kernel.org/r/20240223033307.117906-1-sudeep.holla@arm.com
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
|
|
The last 4 MiB of RAM on those devices is likely used by trustzone
firmware, and is unusable under Linux. Change the device tree memory
node accordingly.
The proprietary bootloader (S-BOOT) passes these memory ranges through
ATAG_MEM; this change allows us to have the correct memory ranges
without relying on ATAG_MEM.
Tested-by: Henrik Grimler <henrik@grimler.se> # i9300, i9305
Signed-off-by: Artur Weber <aweber.kernel@gmail.com>
Link: https://lore.kernel.org/r/20240217-exynos4-memsize-fix-v1-1-7858e9c5f844@gmail.com
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
|
|
https://git.kernel.org/pub/scm/linux/kernel/git/ti/linux into soc/dt
Keystone2 device tree updates for v6.9
Cosmetic cleanups:
* Replace http urls with https.
* tag 'ti-keystone-dt-for-v6.9' of https://git.kernel.org/pub/scm/linux/kernel/git/ti/linux:
ARM: dts: keystone: Replace http urls with https
Link: https://lore.kernel.org/r/20240304133843.e6rm5va6w4oavgoy@posted
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/mmind/linux-rockchip into soc/defconfig
Enablement of the hdmi phy-driver used on rk3588.
* tag 'v6.9-rockchip-config64-1' of git://git.kernel.org/pub/scm/linux/kernel/git/mmind/linux-rockchip:
arm64: defconfig: Enable Rockchip HDMI/eDP Combo PHY
Link: https://lore.kernel.org/r/14841602.uLZWGnKmhe@phil
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
|
|
https://git.kernel.org/pub/scm/linux/kernel/git/ti/linux into soc/defconfig
TI K2/K3 defconfig updates for v6.9
- Enable Wave5 encoder/decoder driver present on multiple K3 SoCs
- Enable K2 boards via multi_v7_defconfig to move away from keystone
specific defconfig.
* tag 'ti-k3-config-for-v6.9' of https://git.kernel.org/pub/scm/linux/kernel/git/ti/linux:
arm64: defconfig: Enable Wave5 Video Encoder/Decoder
ARM: multi_v7_defconfig: Add more TI Keystone support
Link: https://lore.kernel.org/r/a555943a-45d0-4e8e-ad25-682638cfcff7@ti.com
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
|
|
Enable STMicroelectronics accelerometer and gyro drivers for the Samsung
P4note device family in exynos and multi_v7 defconfigs.
Signed-off-by: Martin Jücker <martin.juecker@gmail.com>
Link: https://lore.kernel.org/r/20231221230258.56272-2-martin.juecker@gmail.com
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20240227080755.34170-2-krzysztof.kozlowski@linaro.org
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/shawnguo/linux into soc/defconfig
i.MX defconfig for 6.9:
- Enable VF610 GPIO driver for both arm64 and i.MX ARM defconfig.
- Enable i.MX8MP LDB bridge and i.MX8QXP support drivers in arm64
defconfig.
* tag 'imx-defconfig-6.9' of git://git.kernel.org/pub/scm/linux/kernel/git/shawnguo/linux:
arm64: defconfig: enable i.MX8MP ldb bridge
arm64: defconfig: enable the vf610 gpio driver
ARM: imx_v6_v7_defconfig: enable the vf610 gpio driver
arm64: defconfig: Enable i.MX8QXP device drivers
Link: https://lore.kernel.org/r/20240226034147.233993-5-shawnguo2@yeah.net
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
|
|
https://git.kernel.org/pub/scm/linux/kernel/git/qcom/linux into soc/defconfig
Qualcomm ARM64 defconfig updates for v6.9
Enable the Qualcomm PBS driver to resolve the dependency from the Light
Pulse Generator (LED-driver) on modern Qualcomm platforms. Enable the
X1E multimedia clock controllers, to provide clocks for the various
multimedia blocks. Enable Global clock controller and interconnect
drivers for the QDU1000/QRU1000 platforms.
Enable the audio drivers and the Goodi Berlin touchscreen driver, used
on SM8650 QRD.
Enable the MAX20411 regulator driver drive the GPU rail on SA8295P.
Lastly mark the Qualcomm interconnect providers that feeds UART
instances as builtin, to ensure the console exists when userspace is
launched.
* tag 'qcom-arm64-defconfig-for-6.9' of https://git.kernel.org/pub/scm/linux/kernel/git/qcom/linux:
arm64: defconfig: Enable QCOM PBS
arm64: deconfig: enable Goodix Berlin SPI touchscreen driver as module
arm64: defconfig: Enable X1E80100 multimedia clock controllers configs
arm64: defconfig: Enable GCC and interconnect for QDU1000/QRU1000
arm64: defconfig: enable WCD939x USBSS driver as module
arm64: defconfig: enable audio drivers for SM8650 QRD board
arm64: defconfig: Enable Qualcomm interconnect providers
arm64: defconfig: Enable MAX20411 regulator driver
Link: https://lore.kernel.org/r/20240225032456.481112-1-andersson@kernel.org
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
|
|
ext4 filesystem can mount ext2, so drop CONFIG_EXT2_FS to make builds a
bit faster. Drop also redundant CONFIG_EXT3_FS, because it just
selectes EXT4_FS.
Suggested-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20240221155033.44160-1-krzysztof.kozlowski@linaro.org
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
|
|
https://git.kernel.org/pub/scm/linux/kernel/git/krzk/linux-mem-ctrl into soc/drivers
Memory controller drivers for v6.9, part two
1. Renesas RPC-IF: add bindings for R-Car V4M.
2. Tegra MC: correct and extend support for Tegra234 memory controller.
3. STM32: add support for Flexible Memory Controller on MP25 SoC.
4. NXP WEIM bindings: convert to DT schema.
* tag 'memory-controller-drv-6.9-2' of https://git.kernel.org/pub/scm/linux/kernel/git/krzk/linux-mem-ctrl:
memory: stm32-fmc2-ebi: keep power domain on
memory: stm32-fmc2-ebi: add MP25 RIF support
memory: stm32-fmc2-ebi: add MP25 support
memory: stm32-fmc2-ebi: check regmap_read return value
dt-bindings: memory-controller: st,stm32: add MP25 support
dt-bindings: bus: imx-weim: convert to YAML
memory: tegra: Fix indentation
memory: tegra: Add BPMP and ICC info for DLA clients
memory: tegra: Correct DLA client names
dt-bindings: memory: renesas,rpc-if: Document R-Car V4M support
Link: https://lore.kernel.org/r/20240229124600.405016-1-krzysztof.kozlowski@linaro.org
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/tmlind/linux-omap into soc/drivers
Driver change for ti-sysc
Just one change to constify struct device_type.
* tag 'omap-for-v6.9/ti-sysc-signed' of git://git.kernel.org/pub/scm/linux/kernel/git/tmlind/linux-omap:
bus: ti-sysc: constify the struct device_type usage
Link: https://lore.kernel.org/r/pull-1709194472-263643@atomide.com
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
|
|
https://git.kernel.org/pub/scm/linux/kernel/git/krzk/linux into soc/drivers
Samsung SoC driver changes for v6.9, part two
1. Extend Exynos PMU (Power Management Unit) driver being also the
syscon to main system controller registers block, to support Google
GS101. The Google GS101 has PMU registers protected and writing is
available only via SMC. The Exynos PMU will register its own custom
regmap for such case of mixed MMIO+SMC.
2. Rework Samsung watchdog driver to get the regmap to PMU block not
via syscon API, but from the Exynos PMU driver. This is necessary
for the watchdog driver to work on Google GS101.
* tag 'samsung-drivers-6.9-2' of https://git.kernel.org/pub/scm/linux/kernel/git/krzk/linux:
watchdog: s3c2410_wdt: use exynos_get_pmu_regmap_by_phandle() for PMU regs
soc: samsung: exynos-pmu: Add regmap support for SoCs that protect PMU regs
MAINTAINERS: samsung: gs101: match patches touching Google Tensor SoC
Link: https://lore.kernel.org/r/20240227080755.34170-1-krzysztof.kozlowski@linaro.org
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
|
|
https://git.kernel.org/pub/scm/linux/kernel/git/qcom/linux into soc/drivers
Qualcomm driver updates for v6.9
This introduces the Qualcomm Programmable Boot Sequencer (PBS) driver.
The Qualcomm SMEM no longer acquires the hwspinlock during the "get"
operation, to improve the system behavior during the recovery of a
remoteproc that crashed with the hwspinlock held.
The Qualcomm Always On Subsystem (AOSS) message protocol driver gains
tracepoints, printf annotation, and a debugfs interface is introduced
for tweaking system properties during development and debugging.
The Qualcomm socinfo driver gains data for SM8475, QCM8550 and
QCS8550 platforms, and the PM2250 is renamed to PM4125.
Support for controlling the voltage regulator in SPM/SAW2 is introduced.
The gfx.lvl power-domain is dropped for SA8540P, as this resource was
incorrectly inherited from SC8280XP.
Additionally some code cleanup improvements is introduced across APR,
LLCC, SMP2P and SPM.
* tag 'qcom-drivers-for-6.9' of https://git.kernel.org/pub/scm/linux/kernel/git/qcom/linux: (23 commits)
dt-bindings: soc: qcom: qcom,saw2: add msm8226 l2 compatible
soc: qcom: spm: add support for voltage regulator
soc: qcom: spm: remove driver-internal structures from the driver API
dt-bindings: soc: qcom: qcom,saw2: define optional regulator node
dt-bindings: soc: qcom: qcom,saw2: add missing compatible strings
dt-bindings: soc: qcom: merge qcom,saw2.txt into qcom,spm.yaml
soc: qcom: llcc: Check return value on Broadcast_OR reg read
soc: qcom: socinfo: Add Soc IDs for SM8475 family
dt-bindings: arm: qcom,ids: Add IDs for SM8475 family
soc: qcom: apr: make aprbus const
dt-bindings: soc: qcom: qcom,pmic-glink: document X1E80100 compatible
soc: qcom: add QCOM PBS driver
dt-bindings: soc: qcom: Add qcom,pbs bindings
pmdomain: qcom: rpmhpd: Drop SA8540P gfx.lvl
soc: qcom: socinfo: rename PM2250 to PM4125
soc: qcom: aoss: Add tracepoints in qmp_send()
soc: qcom: socinfo: add SoC Info support for QCM8550 and QCS8550 platform
dt-bindings: arm: qcom,ids: add SoC ID for QCM8550 and QCS8550
soc: qcom: aoss: Add debugfs interface for sending messages
soc: qcom: smem: remove hwspinlock from item get routine
...
Link: https://lore.kernel.org/r/20240225030612.480241-1-andersson@kernel.org
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
|
|
https://git.kernel.org/pub/scm/linux/kernel/git/sunxi/linux into soc/drivers
- make sunxi_rsb_bus constant
* tag 'sunxi-drivers-for-6.9-1' of https://git.kernel.org/pub/scm/linux/kernel/git/sunxi/linux:
bus: sunxi-rsb: make sunxi_rsb_bus const
Link: https://lore.kernel.org/r/20240223205734.GA9027@jernej-laptop
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/tegra/linux into soc/drivers
firmware: tegra: Changes for v6.9-rc1
Contains a fix that makes sure we don't unnecessarily call kfree().
* tag 'tegra-for-6.9-firmware' of git://git.kernel.org/pub/scm/linux/kernel/git/tegra/linux:
firmware: tegra: bpmp: Return directly after a failed kzalloc() in get_filename()
Link: https://lore.kernel.org/r/20240223174849.1509465-2-thierry.reding@gmail.com
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/tegra/linux into soc/drivers
soc/tegra: Changes for v6.9-rc1
This set of changes adds ACPI support for the APBMISC driver and cleans
up a few things like dependencies and unused code.
* tag 'tegra-for-6.9-soc' of git://git.kernel.org/pub/scm/linux/kernel/git/tegra/linux:
soc/tegra: pmc: Add SD wake event for Tegra234
soc/tegra: pmc: Update scratch as an optional aperture
soc/tegra: pmc: Update address mapping sequence for PMC apertures
bus: tegra-aconnect: Update dependency to ARCH_TEGRA
soc/tegra: Fix build failure on Tegra241
soc/tegra: fuse: Fix crash in tegra_fuse_readl()
soc/tegra: fuse: Define tegra194_soc_attr_group for Tegra241
soc/tegra: fuse: Add support for Tegra241
soc/tegra: fuse: Add ACPI support for Tegra194 and Tegra234
soc/tegra: fuse: Add function to print SKU info
soc/tegra: fuse: Add function to add lookups
soc/tegra: fuse: Add tegra_acpi_init_apbmisc()
soc/tegra: fuse: Refactor resource mapping
soc/tegra: fuse: Use dev_err_probe for probe failures
mm/util: Introduce kmemdup_array()
soc/tegra: pmc: Remove some old and deprecated functions and constants
Link: https://lore.kernel.org/r/20240223174849.1509465-1-thierry.reding@gmail.com
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
|
|
The helpers btrfs_del_delalloc_inode() and __btrfs_del_delalloc_inode()
don't follow the pattern when the "__" helper does a special case and
are in fact reversed regarding the naming. We can merge them into one as
there's only one place that needs to be open coded.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
|
|
Replace the two parameters bdev and name by one that can be used to get
them both.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
|
|
Other errors in flush_reservations() are handled and also in the caller.
Ignoring commit might make some sense as it's called right after join so
it's to poke the whole commit machinery to free space.
However for consistency return the error. The caller
btrfs_quota_disable() would try to start the transaction which would
in turn fail too so there's no effective change.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
|
|
Use the KMEM_CACHE() macro instead of kmem_cache_create() to simplify
the creation of SLAB caches when the default values are used.
Signed-off-by: Kunwu Chan <chentao@kylinos.cn>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
|
|
Use the KMEM_CACHE() macro instead of kmem_cache_create() to simplify
the creation of SLAB caches related to delayed refs when the default
values are used.
Signed-off-by: Kunwu Chan <chentao@kylinos.cn>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
|
|
Use the KMEM_CACHE() macro instead of kmem_cache_create() to simplify
the creation of SLAB caches when the default values are used.
Signed-off-by: Kunwu Chan <chentao@kylinos.cn>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
|
|
Use the KMEM_CACHE() macro instead of kmem_cache_create() to simplify
the creation of SLAB caches when the default values are used.
Signed-off-by: Kunwu Chan <chentao@kylinos.cn>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
|
|
Use the KMEM_CACHE() macro instead of kmem_cache_create() to simplify
the creation of SLAB caches when the default values are used.
Signed-off-by: Kunwu Chan <chentao@kylinos.cn>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
|
|
Use the KMEM_CACHE() macro instead of kmem_cache_create() to simplify
the creation of SLAB caches when the default values are used.
Signed-off-by: Kunwu Chan <chentao@kylinos.cn>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
|
|
The helpers are doing an initialization or release work, none of which
is performance critical that it would require a static inline, so move
them to the .c file.
Signed-off-by: David Sterba <dsterba@suse.com>
|
|
The helper is really trivial, reading a cache size can be done directly.
Signed-off-by: David Sterba <dsterba@suse.com>
|
|
The helpers are doing an initialization or release work, none of which
is performance critical that it would require a static inline, so move
them to the .c file.
Signed-off-by: David Sterba <dsterba@suse.com>
|
|
Using static inline in a .c file should be justified, e.g. when
functions are on a hot path but none of the affected functions seem to
be. As it's all in one compilation unit let the compiler decide.
Signed-off-by: David Sterba <dsterba@suse.com>
|
|
This is a simple initializer and not on any hot path, it does not need
to be static inline.
Signed-off-by: David Sterba <dsterba@suse.com>
|
|
There are many helpers doing simple things but not simple enough to
justify the static inline. None of them seems to be on a hot path so
move them to .c.
Signed-off-by: David Sterba <dsterba@suse.com>
|
|
The helper is trivial, we can inline it. It's safe to remove the 'if' as
the iterator is always valid when used, the potential NULL was never
checked anyway.
Signed-off-by: David Sterba <dsterba@suse.com>
|
|
The helper is trivial and used only once, open code it. It's safe to
remove the 'if', the pointer is validated in build_backref_tree().
Signed-off-by: David Sterba <dsterba@suse.com>
|
|
The from/to CPU/disk helpers for balance args are used only in volumes,
no need to define them in accessors.h.
Signed-off-by: David Sterba <dsterba@suse.com>
|
|
We disable offloading checksum to workqueues and do it synchronously when
the checksum algorithm is fast. However, as reported in the link below,
RAID0 with multiple devices may suffer from the sync checksum, because
"fast checksum" is still not fast enough to catch up with RAID0 writing.
We don't have an effective way to determine whether to offload or not,
for now add a sysfs knob so this can be debugged. This is intentionally
under CONFIG_BTRFS_DEBUG so ti's not exposed to users as it may be
removed in the future agin.
Introduce fs_devices->offload_csum_mode, so that a btrfs developer can
change the behavior by writing to /sys/fs/btrfs/<uuid>/offload_csum. The
default is "auto" which is the same as the previous behavior. Or, you
can set "on" or "off" (or "y" or "n" whatever kstrtobool() accepts) to
always/never offload checksum.
More benchmark need to be collected with this knob to implement a proper
criteria to enable/disable checksum offloading.
Link: https://lore.kernel.org/linux-btrfs/20230731152223.4EFB.409509F4@e16-tech.com/
Link: https://lore.kernel.org/linux-btrfs/p3vo3g7pqn664mhmdhlotu5dzcna6vjtcoc2hb2lsgo2fwct7k@xzaxclba5tae/
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
|
|
[BUG]
I have got at least two crash report for RAID6 syndrome generation, no
matter if it's AVX2 or SSE2, they all seems to have a similar
calltrace with corrupted RAX:
BUG: kernel NULL pointer dereference, address: 0000000000000000
#PF: supervisor read access in kernel mode
#PF: error_code(0x0000) - not-present page
PGD 0 P4D 0
Oops: 0000 [#1] PREEMPT SMP PTI
Workqueue: btrfs-rmw rmw_rbio_work [btrfs]
RIP: 0010:raid6_sse21_gen_syndrome+0x9e/0x130 [raid6_pq]
RAX: 0000000000000000 RBX: 0000000000001000 RCX: ffffa0ff4cfa3248
RDX: 0000000000000000 RSI: ffffa0f74cfa3238 RDI: 0000000000000000
Call Trace:
<TASK>
rmw_rbio+0x5c8/0xa80 [btrfs]
process_one_work+0x1c7/0x3d0
worker_thread+0x4d/0x380
kthread+0xf3/0x120
ret_from_fork+0x2c/0x50
</TASK>
[CAUSE]
The cause is not known. Recently I also hit this in AVX512 path, and
that's even in v5.15 backport, which doesn't have any of my RAID56
rework.
Furthermore according to the registers:
RAX: 0000000000000000 RBX: 0000000000001000 RCX: ffffa0ff4cfa3248
The RAX register is showing the number of stripes (including PQ), which
is not correct (0). But the remaining two registers are all sane.
- RBX is the sectorsize
For x86_64 it should always be 4K and matches the output.
- RCX is the pointers array
Which is from rbio->finish_pointers, and it looks like a sane
kernel address.
[WORKAROUND]
For now, I can only add extra debug ASSERT()s before we call raid6
gen_syndrome() helper and hopes to catch the problem.
The debug requires both CONFIG_BTRFS_DEBUG and CONFIG_BTRFS_ASSERT
enabled.
My current guess is some use-after-free, but every report is only having
corrupted RAX but seemingly valid pointers doesn't make much sense.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
|
|
At btrfs_free_tree_block(), we are always initializing a delayed reference
to drop the given extent buffer but we only use if it does not belong to a
log root tree. So we are doing unnecessary work here and increasing the
duration of a critical section as this is normally called while holding a
lock on the parent tree block (if any) and while holding a log transaction
open.
So initialize the delayed reference only if the extent buffer is not from
a log tree, avoiding unnecessary work and making the code also a bit
easier to follow.
Reviewed-by: Naohiro Aota <naohiro.aota@wdc.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
|
