In raid10_run() if raid10_set_queue_limits() succeed, the return value
is set to zero, and if following procedures failed raid10_run() will
return zero while mddev->private is still NULL, causing null ptr
dereference in raid10_size().
Fix the problem by only overwrite the return value if
raid10_set_queue_limits() failed.
Fixes: 3d8466ba68 ("md/raid10: use the atomic queue limit update APIs")
Cc: stable@vger.kernel.org
Reported-and-tested-by: ValdikSS <iam@valdikss.org.ru>
Closes: https://lore.kernel.org/all/0dd96820-fe52-4841-bc58-dbf14d6bfcc8@valdikss.org.ru/
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20241009014914.1682037-1-yukuai1@huaweicloud.com
Signed-off-by: Song Liu <song@kernel.org>
And move the condition "if (mddev->bitmap)" into md_bitmap_resize() as
well, on the one hand make code cleaner, on the other hand try not to
access bitmap directly.
Since we are here, also change the parameter 'init' from int to bool.
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Link: https://lore.kernel.org/r/20240826074452.1490072-35-yukuai1@huaweicloud.com
Signed-off-by: Song Liu <song@kernel.org>
Add a parameter 'bool sync' to distinguish them, and
md_bitmap_unplug_async() won't be exported anymore, hence
bitmap_operations only need one op to cover them.
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Link: https://lore.kernel.org/r/20240826074452.1490072-32-yukuai1@huaweicloud.com
Signed-off-by: Song Liu <song@kernel.org>
So that the implementation won't be exposed, and it'll be possible
to invent a new bitmap by replacing bitmap_operations.
Also change the parameter from bitmap to mddev, to avoid access
bitmap outside md-bitmap.c as much as possible.
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Link: https://lore.kernel.org/r/20240826074452.1490072-30-yukuai1@huaweicloud.com
Signed-off-by: Song Liu <song@kernel.org>
So that the implementation won't be exposed, and it'll be possible
to invent a new bitmap by replacing bitmap_operations.
Also change the parameter from bitmap to mddev, to avoid access
bitmap outside md-bitmap.c as much as possible.
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Link: https://lore.kernel.org/r/20240826074452.1490072-29-yukuai1@huaweicloud.com
Signed-off-by: Song Liu <song@kernel.org>
So that the implementation won't be exposed, and it'll be possible
to invent a new bitmap by replacing bitmap_operations.
Also change the parameter from bitmap to mddev, to avoid access
bitmap outside md-bitmap.c as much as possible.
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Link: https://lore.kernel.org/r/20240826074452.1490072-28-yukuai1@huaweicloud.com
Signed-off-by: Song Liu <song@kernel.org>
For internal callers, aborted are always set to false, while for
external callers, aborted are always set to true.
Hence there is no need to always pass in true for exported api.
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Link: https://lore.kernel.org/r/20240826074452.1490072-27-yukuai1@huaweicloud.com
Signed-off-by: Song Liu <song@kernel.org>
So that the implementation won't be exposed, and it'll be possible
to invent a new bitmap by replacing bitmap_operations.
Also change the parameter from bitmap to mddev, to avoid access
bitmap outside md-bitmap.c as much as possible.
Also fix lots of code style.
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Link: https://lore.kernel.org/r/20240826074452.1490072-26-yukuai1@huaweicloud.com
Signed-off-by: Song Liu <song@kernel.org>
So that the implementation won't be exposed, and it'll be possible
to invent a new bitmap by replacing bitmap_operations.
Also change the parameter from bitmap to mddev, to avoid access
bitmap outside md-bitmap.c as much as possible. And change the type
of 'success' and 'behind' from int to bool.
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Link: https://lore.kernel.org/r/20240826074452.1490072-25-yukuai1@huaweicloud.com
Signed-off-by: Song Liu <song@kernel.org>
So that the implementation won't be exposed, and it'll be possible
to invent a new bitmap by replacing bitmap_operations.
Also change the parameter from bitmap to mddev, to avoid access
bitmap outside md-bitmap.c as much as possible. And change the type
of 'behind' from int to bool.
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Link: https://lore.kernel.org/r/20240826074452.1490072-24-yukuai1@huaweicloud.com
Signed-off-by: Song Liu <song@kernel.org>
The md driver wants to enforce a number of flags for all devices, even
when not inheriting them from the underlying devices. To make sure these
flags survive the queue_limits_set calls that md uses to update the
queue limits without deriving them form the previous limits add a new
md_init_stacking_limits helper that calls blk_set_stacking_limits and sets
these flags.
Fixes: 1122c0c1cc ("block: move cache control settings out of queue->flags")
Reported-by: kernel test robot <oliver.sang@intel.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Link: https://lore.kernel.org/r/20240626142637.300624-2-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Pull in block limits branch, which exists as a shared branch for both
the block and SCSI tree.
* for-6.11/block-limits: (26 commits)
block: move integrity information into queue_limits
block: invert the BLK_INTEGRITY_{GENERATE,VERIFY} flags
block: bypass the STABLE_WRITES flag for protection information
block: don't require stable pages for non-PI metadata
block: use kstrtoul in flag_store
block: factor out flag_{store,show} helper for integrity
block: remove the blk_flush_integrity call in blk_integrity_unregister
block: remove the blk_integrity_profile structure
dm-integrity: use the nop integrity profile
md/raid1: don't free conf on raid0_run failure
md/raid0: don't free conf on raid0_run failure
block: initialize integrity buffer to zero before writing it to media
block: add special APIs for run-time disabling of discard and friends
block: remove unused queue limits API
sr: convert to the atomic queue limits API
sd: convert to the atomic queue limits API
sd: cleanup zoned queue limits initialization
sd: factor out a sd_discard_mode helper
sd: simplify the disable case in sd_config_discard
sd: add a sd_disable_write_same helper
...
Move the integrity information into the queue limits so that it can be
set atomically with other queue limits, and that the sysfs changes to
the read_verify and write_generate flags are properly synchronized.
This also allows to provide a more useful helper to stack the integrity
fields, although it still is separate from the main stacking function
as not all stackable devices want to inherit the integrity settings.
Even with that it greatly simplifies the code in md and dm.
Note that the integrity field is moved as-is into the queue limits.
While there are good arguments for removing the separate blk_integrity
structure, this would cause a lot of churn and might better be done at a
later time if desired. However the integrity field in the queue_limits
structure is now unconditional so that various ifdefs can be avoided or
replaced with IS_ENABLED(). Given that tiny size of it that seems like
a worthwhile trade off.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Link: https://lore.kernel.org/r/20240613084839.1044015-13-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
For different sync_action, sync_thread will use different max_sectors,
see details in md_sync_max_sectors(), currently both md_do_sync() and
pers->sync_request() in eatch iteration have to get the same
max_sectors. Hence pass in max_sectors for pers->sync_request() to
prevent redundant code.
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20240611132251.1967786-12-yukuai1@huaweicloud.com
Commit cc27b0c78c ("md: fix deadlock between mddev_suspend() and
md_write_start()") aborted md_write_start() with false when mddev is
suspended, which fixed a deadlock if calling mddev_suspend() with
holding reconfig_mutex(). Since mddev_suspend() now includes
lockdep_assert_not_held(), it no longer holds the reconfig_mutex. This
makes previous abort unnecessary. Now, remove unnecessary abort and
change function return value to void.
Signed-off-by: Li Nan <linan122@huawei.com>
Reviewed-by: Yu Kuai <yukuai3@huawei.com>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20240525185257.3896201-2-linan666@huaweicloud.com
Just use the request_queue from the gendisk pointer in the relatively
few places that sill need it.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed--by: Song Liu <song@kernel.org>
Tested-by: Song Liu <song@kernel.org>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20240303140150.5435-11-hch@lst.de
Build the queue limits outside the queue and apply them using
queue_limits_set. To make the code more obvious also split the queue
limits handling into separate helpers.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed--by: Song Liu <song@kernel.org>
Tested-by: Song Liu <song@kernel.org>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20240303140150.5435-9-hch@lst.de
Add a helper to check for a DM-mapped MD device instead of using
the obfuscated ->gendisk or ->queue NULL checks.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed--by: Song Liu <song@kernel.org>
Tested-by: Song Liu <song@kernel.org>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20240303140150.5435-4-hch@lst.de
Add a small wrapper around blk_add_trace_msg that hides some argument
dereferences and the check for a DM-mapped MD device.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed--by: Song Liu <song@kernel.org>
Tested-by: Song Liu <song@kernel.org>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20240303140150.5435-3-hch@lst.de
Add a helper to trace bio remapping that hides some argument
dereferences and the check for a DM-mapped MD device.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed--by: Song Liu <song@kernel.org>
Tested-by: Song Liu <song@kernel.org>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20240303140150.5435-2-hch@lst.de
If resync is in progress, read_balance() should find the first usable
disk, otherwise, data could be inconsistent after resync is done. raid1
and raid10 implement the same checking, hence factor out the checking
to make code cleaner.
Noted that raid1 is using 'mddev->recovery_cp', which is updated after
all resync IO is done, while raid10 is using 'conf->next_resync', which
is inaccurate because raid10 update it before submitting resync IO.
Fortunately, raid10 read IO can't concurrent with resync IO, hence there
is no problem. And this patch also switch raid10 to use
'mddev->recovery_cp'.
Co-developed-by: Paul Luse <paul.e.luse@linux.intel.com>
Signed-off-by: Paul Luse <paul.e.luse@linux.intel.com>
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Reviewed-by: Xiao Ni <xni@redhat.com>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20240229095714.926789-7-yukuai1@huaweicloud.com
The current api is_badblock() must pass in 'first_bad' and
'bad_sectors', however, many caller just want to know if there are
badblocks or not, and these caller must define two local variable that
will never be used.
Add a new helper rdev_has_badblock() that will only return if there are
badblocks or not, remove unnecessary local variables and replace
is_badblock() with the new helper in many places.
There are no functional changes, and the new helper will also be used
later to refactor read_balance().
Co-developed-by: Paul Luse <paul.e.luse@linux.intel.com>
Signed-off-by: Paul Luse <paul.e.luse@linux.intel.com>
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Reviewed-by: Xiao Ni <xni@redhat.com>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20240229095714.926789-2-yukuai1@huaweicloud.com
Currently, if reshape is interrupted, then reassemble the array will
register sync_thread directly from pers->run(), in this case
'MD_RECOVERY_RUNNING' is set directly, however, there is no guarantee
that md_do_sync() will be executed, hence stop_sync_thread() will hang
because 'MD_RECOVERY_RUNNING' can't be cleared.
Last patch make sure that md_do_sync() will set MD_RECOVERY_DONE,
however, following hang can still be triggered by dm-raid test
shell/lvconvert-raid-reshape.sh occasionally:
[root@fedora ~]# cat /proc/1982/stack
[<0>] stop_sync_thread+0x1ab/0x270 [md_mod]
[<0>] md_frozen_sync_thread+0x5c/0xa0 [md_mod]
[<0>] raid_presuspend+0x1e/0x70 [dm_raid]
[<0>] dm_table_presuspend_targets+0x40/0xb0 [dm_mod]
[<0>] __dm_destroy+0x2a5/0x310 [dm_mod]
[<0>] dm_destroy+0x16/0x30 [dm_mod]
[<0>] dev_remove+0x165/0x290 [dm_mod]
[<0>] ctl_ioctl+0x4bb/0x7b0 [dm_mod]
[<0>] dm_ctl_ioctl+0x11/0x20 [dm_mod]
[<0>] vfs_ioctl+0x21/0x60
[<0>] __x64_sys_ioctl+0xb9/0xe0
[<0>] do_syscall_64+0xc6/0x230
[<0>] entry_SYSCALL_64_after_hwframe+0x6c/0x74
Meanwhile mddev->recovery is:
MD_RECOVERY_RUNNING |
MD_RECOVERY_INTR |
MD_RECOVERY_RESHAPE |
MD_RECOVERY_FROZEN
Fix this problem by remove the code to register sync_thread directly
from raid10 and raid5. And let md_check_recovery() to register
sync_thread.
Fixes: f67055780c ("[PATCH] md: Checkpoint and allow restart of raid5 reshape")
Fixes: f52f5c71f3 ("md: fix stopping sync thread")
Cc: stable@vger.kernel.org # v6.7+
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20240201092559.910982-5-yukuai1@huaweicloud.com
Move check_decay_read_errors() to raid1-10.c and factor out a helper
exceed_read_errors() to check if read_errors exceeds the limit, so that
raid1 can also use it. There are no functional changes.
Signed-off-by: Li Nan <linan122@huawei.com>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20231215023852.3478228-2-linan666@huaweicloud.com
Because it's safe to accees rdev from conf:
- If any spinlock is held, because synchronize_rcu() from
md_kick_rdev_from_array() will prevent 'rdev' to be freed until
spinlock is released;
- If 'reconfig_lock' is held, because rdev can't be added or removed from
array;
- If there is normal IO inflight, because mddev_suspend() will prevent
rdev to be added or removed from array;
- If there is sync IO inflight, because 'MD_RECOVERY_RUNNING' is
checked in remove_and_add_spares().
And these will cover all the scenarios in raid10.
This patch also cleanup the code to handle the case that replacement
replace rdev while IO is still inflight.
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20231125081604.3939938-3-yukuai1@huaweicloud.com
rcu is not used correctly here, because synchronize_rcu() is called
before replacing old value, for example:
remove_and_add_spares // other path
synchronize_rcu
// called before replacing old value
set_bit(RemoveSynchronized)
rcu_read_lock()
rdev = conf->mirros[].rdev
pers->hot_remove_disk
conf->mirros[].rdev = NULL;
if (!test_bit(RemoveSynchronized))
synchronize_rcu
/*
* won't be called, and won't wait
* for concurrent readers to be done.
*/
// access rdev after remove_and_add_spares()
rcu_read_unlock()
Fortunately, there is a separate rcu protection to prevent such rdev
to be freed:
md_kick_rdev_from_array //other path
rcu_read_lock()
rdev = conf->mirros[].rdev
list_del_rcu(&rdev->same_set)
rcu_read_unlock()
/*
* rdev can be removed from conf, but
* rdev won't be freed.
*/
synchronize_rcu()
free rdev
Hence remove this useless flag and prepare to remove rcu protection to
access rdev from 'conf'.
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20231125081604.3939938-2-yukuai1@huaweicloud.com
Currently 'writes_pending' is initialized in pers->run for raid1/5/10,
and it's freed while deleing mddev, instead of pers->free. pers->run can
be called multiple times before mddev is deleted, and a helper
mddev_init_writes_pending() is used to prevent 'writes_pending' to be
initialized multiple times, this usage is safe but a litter weird.
On the other hand, 'writes_pending' is only initialized for raid1/5/10,
however, it's used in common layer, for example:
array_state_store
set_in_sync
if (!mddev->in_sync) -> in_sync is used for all levels
// access writes_pending
There might be some implicit dependency that I don't recognized to make
sure 'writes_pending' can only be accessed for raid1/5/10, but there are
no comments about that.
By the way, it make sense to initialize 'writes_pending' in common layer
because there are already three levels use it.
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20230825030956.1527023-3-yukuai1@huaweicloud.com
Commit ba9d9f1a707f ("Revert "md: unlock mddev before reap sync_thread in
action_store"") removed the scenario of calling md_unregister_thread()
without holding mddev->reconfig_mutex, so add a lock holding check before
acquiring mddev->sync_thread by passing mdev to md_unregister_thread().
Signed-off-by: Li Lingfeng <lilingfeng3@huawei.com>
Reviewed-by: Yu Kuai <yukuai3@huawei.com>
Link: https://lore.kernel.org/r/20230803071711.2546560-1-lilingfeng@huaweicloud.com
Signed-off-by: Song Liu <song@kernel.org>
After commit b39f35ebe8 ("md: don't quiesce in mddev_suspend()"),
'conf->barrier' will be leaked in the case that raid10 takeover raid0:
level_store
pers->takeover -> raid10_takeover
raid10_takeover_raid0
WRITE_ONCE(conf->barrier, 1)
mddev_suspend
// still raid0
mddev->pers = pers
// switch to raid10
mddev_resume
// resume without suspend
After the above commit, mddev_resume() will not decrease 'conf->barrier'
that is set in raid10_takeover_raid0().
Fix this problem by not setting 'conf->barrier' in raid10_takeover_raid0().
By the way, this problem is found while I'm trying to make
mddev_suspend/resume() to be independent from raid personalities. raid10
is the only personality to use reference count in the quiesce() callback
and this problem is only related to raid10.
Fixes: b39f35ebe8 ("md: don't quiesce in mddev_suspend()")
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Link: https://lore.kernel.org/r/20230731022800.1424902-1-yukuai1@huaweicloud.com
Signed-off-by: Song Liu <song@kernel.org>
Commit 2ae6aaf769 ("md/raid10: fix io loss while replacement replace
rdev") reads replacement first to prevent io loss. However, there are same
issue in wait_blocked_dev() and raid10_handle_discard(), too. Fix it by
using dereference_rdev_and_rrdev() to get devices.
Fixes: d30588b273 ("md/raid10: improve raid10 discard request")
Fixes: f2e7e269a7 ("md/raid10: pull the code that wait for blocked dev into one function")
Signed-off-by: Li Nan <linan122@huawei.com>
Link: https://lore.kernel.org/r/20230701080529.2684932-4-linan666@huaweicloud.com
Signed-off-by: Song Liu <song@kernel.org>
Factor out a helper to get 'rdev' and 'replacement' from config->mirrors.
Just to make code cleaner and prepare to fix the bug of io loss while
'replacement' replace 'rdev'.
There is no functional change.
Signed-off-by: Li Nan <linan122@huawei.com>
Link: https://lore.kernel.org/r/20230701080529.2684932-3-linan666@huaweicloud.com
Signed-off-by: Song Liu <song@kernel.org>
After commit 4ca40c2ce0 ("md/raid10: Allow replacement device to be
replace old drive."), 'rdev' and 'replacement' could appear to be
identical. There are already checks for that in wait_blocked_dev() and
raid10_write_request(). Add check for raid10_handle_discard() now.
Signed-off-by: Li Nan <linan122@huawei.com>
Link: https://lore.kernel.org/r/20230701080529.2684932-2-linan666@huaweicloud.com
Signed-off-by: Song Liu <song@kernel.org>
In fix_read_error(), 'success' will be checked immediately after assigning
it, if it is set to 1 then the loop will break. Checking it again in
condition of loop is redundant. Clean it up.
Signed-off-by: Li Nan <linan122@huawei.com>
Reviewed-by: Yu Kuai <yukuai3@huawei.com>
Link: https://lore.kernel.org/r/20230623173236.2513554-3-linan666@huaweicloud.com
Signed-off-by: Song Liu <song@kernel.org>
We dereference r10_bio->read_slot too many times in fix_read_error().
Optimize it by using a variable to store read_slot.
Signed-off-by: Li Nan <linan122@huawei.com>
Reviewed-by: Yu Kuai <yukuai3@huawei.com>
Link: https://lore.kernel.org/r/20230623173236.2513554-2-linan666@huaweicloud.com
Signed-off-by: Song Liu <song@kernel.org>
Make sure that 'active_io' will represent inflight io instead of io that
is dispatching, and io accounting from all levels will be consistent.
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Reviewed-by: Xiao Ni <xni@redhat.com>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20230621165110.1498313-6-yukuai1@huaweicloud.com
Commit 0c0be98bbe ("md/raid10: prevent unnecessary calls to wake_up()
in fast path") missed one place, for example, with:
fio -direct=1 -rw=write/randwrite -iodepth=1 ...
Plug and unplug are called for each io, then wake_up() from raid10_unplug()
will cause lock contention as well.
Avoid this contention by using wake_up_barrier() instead of wake_up(),
where spin_lock is not held if waitqueue is empty.
Fio test script:
[global]
name=random reads and writes
ioengine=libaio
direct=1
readwrite=randrw
rwmixread=70
iodepth=64
buffered=0
filename=/dev/md0
size=1G
runtime=30
time_based
randrepeat=0
norandommap
refill_buffers
ramp_time=10
bs=4k
numjobs=400
group_reporting=1
[job1]
Test result with ramdisk raid10(By Ali):
Before this patch With this patch
READ IOPS=2033k IOPS=3642k
WRITE IOPS=871k IOPS=1561K
By the way, in this scenario, blk_plug_cb() will be allocated and freed
for each io, this seems need to be optimized as well.
Reported-and-tested-by: Ali Gholami Rudi <aligrudi@gmail.com>
Closes: https://lore.kernel.org/all/20231606122233@laper.mirepesht/
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20230621105728.1268542-1-yukuai1@huaweicloud.com
/sys/block/[device]/queue/iostats is used to control whether to count io
stat. Write 0 to it will clear queue_flags QUEUE_FLAG_IO_STAT which means
iostats is disabled. If we disable iostats and later endable it, the io
issued during this period will be counted incorrectly, inflight will be
decreased to -1.
//T1 set iostats
echo 0 > /sys/block/md0/queue/iostats
clear QUEUE_FLAG_IO_STAT
//T2 issue io
if (QUEUE_FLAG_IO_STAT) -> false
bio_start_io_acct
inflight++
echo 1 > /sys/block/md0/queue/iostats
set QUEUE_FLAG_IO_STAT
//T3 io end
if (QUEUE_FLAG_IO_STAT) -> true
bio_end_io_acct
inflight-- -> -1
Also, if iostats is enabled while issuing io but disabled while io end,
inflight will never be decreased.
Fix it by checking start_time when io end. If start_time is not 0, call
bio_end_io_acct().
Fixes: 528bc2cf2f ("md/raid10: enable io accounting")
Signed-off-by: Li Nan <linan122@huawei.com>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20230609094320.2397604-1-linan666@huaweicloud.com
bio can be added to plug infinitely, and following writeback test can
trigger huge amount of plugged bio:
Test script:
modprobe brd rd_nr=4 rd_size=10485760
mdadm -CR /dev/md0 -l10 -n4 /dev/ram[0123] --assume-clean --bitmap=internal
echo 0 > /proc/sys/vm/dirty_background_ratio
fio -filename=/dev/md0 -ioengine=libaio -rw=write -bs=4k -numjobs=1 -iodepth=128 -name=test
Test result:
Monitor /sys/block/md0/inflight will found that inflight keep increasing
until fio finish writing, after running for about 2 minutes:
[root@fedora ~]# cat /sys/block/md0/inflight
0 4474191
Fix the problem by limiting the number of plugged bio based on the number
of copies for original bio.
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20230529131106.2123367-8-yukuai1@huaweicloud.com
current->bio_list will be set under submit_bio() context, in this case
bitmap io will be added to the list and wait for current io submission to
finish, while current io submission must wait for bitmap io to be done.
commit 874807a831 ("md/raid1{,0}: fix deadlock in bitmap_unplug.") fix
the deadlock by handling plugged bio by daemon thread.
On the one hand, the deadlock won't exist after commit a214b949d8
("blk-mq: only flush requests from the plug in blk_mq_submit_bio"). On
the other hand, current solution makes it impossible to flush plugged bio
in raid1/10_make_request(), because this will cause that all the writes
will goto daemon thread.
In order to limit the number of plugged bio, commit 874807a831
("md/raid1{,0}: fix deadlock in bitmap_unplug.") is reverted, and the
deadlock is fixed by handling bitmap io asynchronously.
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20230529131106.2123367-7-yukuai1@huaweicloud.com
There are multiple places to do the same thing, factor out a helper to
prevent redundant code, and the helper will be used in following patch
as well.
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20230529131106.2123367-4-yukuai1@huaweicloud.com
Currently, there is no limit for raid1/raid10 plugged bio. While flushing
writes, raid1 has cond_resched() while raid10 doesn't, and too many
writes can cause soft lockup.
Follow up soft lockup can be triggered easily with writeback test for
raid10 with ramdisks:
watchdog: BUG: soft lockup - CPU#10 stuck for 27s! [md0_raid10:1293]
Call Trace:
<TASK>
call_rcu+0x16/0x20
put_object+0x41/0x80
__delete_object+0x50/0x90
delete_object_full+0x2b/0x40
kmemleak_free+0x46/0xa0
slab_free_freelist_hook.constprop.0+0xed/0x1a0
kmem_cache_free+0xfd/0x300
mempool_free_slab+0x1f/0x30
mempool_free+0x3a/0x100
bio_free+0x59/0x80
bio_put+0xcf/0x2c0
free_r10bio+0xbf/0xf0
raid_end_bio_io+0x78/0xb0
one_write_done+0x8a/0xa0
raid10_end_write_request+0x1b4/0x430
bio_endio+0x175/0x320
brd_submit_bio+0x3b9/0x9b7 [brd]
__submit_bio+0x69/0xe0
submit_bio_noacct_nocheck+0x1e6/0x5a0
submit_bio_noacct+0x38c/0x7e0
flush_pending_writes+0xf0/0x240
raid10d+0xac/0x1ed0
Fix the problem by adding cond_resched() to raid10 like what raid1 did.
Note that unlimited plugged bio still need to be optimized, for example,
in the case of lots of dirty pages writeback, this will take lots of
memory and io will spend a long time in plug, hence io latency is bad.
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20230529131106.2123367-2-yukuai1@huaweicloud.com
When removing a disk with replacement, the replacement will be used to
replace rdev. During this process, there is a brief window in which both
rdev and replacement are read as NULL in raid10_write_request(). This
will result in io not being submitted but it should be.
//remove //write
raid10_remove_disk raid10_write_request
mirror->rdev = NULL
read rdev -> NULL
mirror->rdev = mirror->replacement
mirror->replacement = NULL
read replacement -> NULL
Fix it by reading replacement first and rdev later, meanwhile, use smp_mb()
to prevent memory reordering.
Fixes: 475b0321a4 ("md/raid10: writes should get directed to replacement as well as original.")
Signed-off-by: Li Nan <linan122@huawei.com>
Reviewed-by: Yu Kuai <yukuai3@huawei.com>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20230602091839.743798-3-linan666@huaweicloud.com
In raid10_sync_request(), if data cannot be read from any disk for
recovery, it will go to 'giveup' and let 'chunks_skipped' + 1. After
multiple 'giveup', when 'chunks_skipped >= geo.raid_disks', it will
return 'max_sector', indicating that the recovery has been completed.
However, the recovery is just aborted and the data remains inconsistent.
Fix it by setting mirror->recovery_disabled, which will prevent the spare
disk from being added to this mirror. The same issue also exists during
resync, it will be fixed afterwards.
Signed-off-by: Li Nan <linan122@huawei.com>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20230602091839.743798-2-linan666@huaweicloud.com
When add a new disk to raid10, it will traverse conf->mirror from start
and find one of the following mirror to add:
1. mirror->rdev is set to WantReplacement and it have no replacement,
set new disk to mirror->replacement.
2. no mirror->rdev, set new disk to mirror->rdev.
There is a array as below (sda is set to WantReplacement):
Number Major Minor RaidDevice State
0 8 0 0 active sync set-A /dev/sda
- 0 0 1 removed
2 8 32 2 active sync set-A /dev/sdc
3 8 48 3 active sync set-B /dev/sdd
Use 'mdadm --add' to add a new disk to this array, the new disk will
become sda's replacement instead of add to removed position, which is
confusing for users. Meanwhile, after new disk recovery success, sda
will be set to Faulty.
Prioritize adding disk to 'removed' mirror is a better choice. In the
above scenario, the behavior is the same as before, except sda will not
be deleted. Before other disks are added, continued use sda is more
reliable.
Signed-off-by: Li Nan <linan122@huawei.com>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20230527092007.3008856-1-linan666@huaweicloud.com
'need_recover' and 'mrdev' are equivalent in raid10_sync_request(), and
inc mrdev->nr_pending is unreasonable if don't need recovery. Replace
'need_recover' with 'mrdev', and only inc nr_pending when needed.
Signed-off-by: Li Nan <linan122@huawei.com>
Reviewed-by: Yu Kuai <yukuai3@huawei.com>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20230527072218.2365857-3-linan666@huaweicloud.com
There are two check of 'mreplace' in raid10_sync_request(). In the first
check, 'need_replace' will be set and 'mreplace' will be used later if
no-Faulty 'mreplace' exists, In the second check, 'mreplace' will be
set to NULL if it is Faulty, but 'need_replace' will not be changed
accordingly. null-ptr-deref occurs if Faulty is set between two check.
Fix it by merging two checks into one. And replace 'need_replace' with
'mreplace' because their values are always the same.
Fixes: ee37d7314a ("md/raid10: Fix raid10 replace hang when new added disk faulty")
Signed-off-by: Li Nan <linan122@huawei.com>
Reviewed-by: Yu Kuai <yukuai3@huawei.com>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20230527072218.2365857-2-linan666@huaweicloud.com
