dm io: Support IO priority

[ Upstream commit 6e5f0f6383b4896c7e9b943d84b136149d0f45e9 ]

Some IO will dispatch from kworker with different io_context settings
than the submitting task, we may need t

dm io: Support IO priority

[ Upstream commit 6e5f0f6383b4896c7e9b943d84b136149d0f45e9 ]

Some IO will dispatch from kworker with different io_context settings
than the submitting task, we may need to specify a priority to avoid
losing priority.

Add IO priority parameter to dm_io() and update all callers.

Co-developed-by: Yibin Ding <yibin.ding@unisoc.com>
Signed-off-by: Yibin Ding <yibin.ding@unisoc.com>
Signed-off-by: Hongyu Jin <hongyu.jin@unisoc.com>
Reviewed-by: Eric Biggers <ebiggers@google.com>
Reviewed-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
Stable-dep-of: b4d78cfeb304 ("dm-integrity: align the outgoing bio in integrity_recheck")
Signed-off-by: Sasha Levin <sashal@kernel.org>

show more ...

dm: remove unnecessary (void*) conversions

Pointer variables of void * type do not require type cast.

Signed-off-by: Yu Zhe <yuzhe@nfschina.com>
Signed-off-by: Mike Snitzer <snitzer@kernel.org>

dm: fix use of sizeof() macro

Signed-off-by: Heinz Mauelshagen <heinzm@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@kernel.org>

dm: avoid using symbolic permissions

Signed-off-by: Heinz Mauelshagen <heinzm@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@kernel.org>

dm: add missing empty lines

Signed-off-by: Heinz Mauelshagen <heinzm@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@kernel.org>

dm: avoid spaces before function arguments or in favour of tabs

Signed-off-by: Heinz Mauelshagen <heinzm@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@kernel.org>

dm: correct block comments format.

Signed-off-by: Heinz Mauelshagen <heinzm@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@kernel.org>

dm: change "unsigned" to "unsigned int"

Signed-off-by: Heinz Mauelshagen <heinzm@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@kernel.org>

dm: use fsleep() instead of msleep() for deterministic sleep duration

Signed-off-by: Heinz Mauelshagen <heinzm@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@kernel.org>

dm: add missing SPDX-License-Indentifiers

'GPL-2.0-only' is used instead of 'GPL-2.0' because SPDX has
deprecated its use.

Suggested-by: John Wiele <jwiele@redhat.com>
Signed-off-by: Heinz Mauelsha

dm: add missing SPDX-License-Indentifiers

'GPL-2.0-only' is used instead of 'GPL-2.0' because SPDX has
deprecated its use.

Suggested-by: John Wiele <jwiele@redhat.com>
Signed-off-by: Heinz Mauelshagen <heinzm@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@kernel.org>

show more ...

dm kcopyd: use __GFP_HIGHMEM when allocating pages

dm-kcopyd doesn't access the allocated pages directly, it only passes
them to dm-io which adds them to a bio list - thus, we can allocate
the pages

dm kcopyd: use __GFP_HIGHMEM when allocating pages

dm-kcopyd doesn't access the allocated pages directly, it only passes
them to dm-io which adds them to a bio list - thus, we can allocate
the pages from high memory. This will reduce pressure on the low
memory when there are a large number of kcopyd jobs in progress.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@kernel.org>

show more ...

dm/core: Rename kcopyd_job.rw into kcopyd.op

The member name 'rw' suggests that this member either has the value 'READ'
or 'WRITE' and no other values. Since that member also can have the value
REQ_

dm/core: Rename kcopyd_job.rw into kcopyd.op

The member name 'rw' suggests that this member either has the value 'READ'
or 'WRITE' and no other values. Since that member also can have the value
REQ_OP_WRITE_ZEROES, rename 'rw' into 'op'. This patch does not change any
functionality since REQ_OP_READ = READ = 0 and REQ_OP_WRITE = WRITE = 1.

Cc: Alasdair Kergon <agk@redhat.com>
Cc: Mike Snitzer <snitzer@kernel.org>
Cc: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20220714180729.1065367-23-bvanassche@acm.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>

show more ...

dm/core: Reduce the size of struct dm_io_request

Combine the bi_op and bi_op_flags into the bi_opf member. Use the new
blk_opf_t type to improve static type checking. This patch does not
change any

dm/core: Reduce the size of struct dm_io_request

Combine the bi_op and bi_op_flags into the bi_opf member. Use the new
blk_opf_t type to improve static type checking. This patch does not
change any functionality.

Cc: Alasdair Kergon <agk@redhat.com>
Cc: Mike Snitzer <snitzer@kernel.org>
Cc: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20220714180729.1065367-22-bvanassche@acm.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>

show more ...

dm writecache: have ssd writeback wait if the kcopyd workqueue is busy

Make dm-writecache wait if the kcopyd workqueue is busy (as will
happen if waiting for page allocation or inside submit_bio).

dm writecache: have ssd writeback wait if the kcopyd workqueue is busy

Make dm-writecache wait if the kcopyd workqueue is busy (as will
happen if waiting for page allocation or inside submit_bio).

This change improves performance of "mkfs.ext2" by approximately 20%
on one testbed.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

show more ...

dm kcopyd: avoid spin_lock_irqsave from process context

The functions "pop", "push_head", "do_work" can only be called from
process context. Therefore, replace spin_lock_irq{save,restore} with
spin_

dm kcopyd: avoid spin_lock_irqsave from process context

The functions "pop", "push_head", "do_work" can only be called from
process context. Therefore, replace spin_lock_irq{save,restore} with
spin_{lock,unlock}_irq.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

show more ...

dm kcopyd: avoid useless atomic operations

The functions set_bit and clear_bit are atomic. We don't need
atomicity when making flags for dm-kcopyd. So, change them to direct
manipulation of the flag

dm kcopyd: avoid useless atomic operations

The functions set_bit and clear_bit are atomic. We don't need
atomicity when making flags for dm-kcopyd. So, change them to direct
manipulation of the flags.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

show more ...

dm kcopyd: always complete failed jobs

This patch fixes a problem in dm-kcopyd that may leave jobs in
complete queue indefinitely in the event of backing storage failure.

This behavior has been obs

dm kcopyd: always complete failed jobs

This patch fixes a problem in dm-kcopyd that may leave jobs in
complete queue indefinitely in the event of backing storage failure.

This behavior has been observed while running 100% write file fio
workload against an XFS volume created on top of a dm-zoned target
device. If the underlying storage of dm-zoned goes to offline state
under I/O, kcopyd sometimes never issues the end copy callback and
dm-zoned reclaim work hangs indefinitely waiting for that completion.

This behavior was traced down to the error handling code in
process_jobs() function that places the failed job to complete_jobs
queue, but doesn't wake up the job handler. In case of backing device
failure, all outstanding jobs may end up going to complete_jobs queue
via this code path and then stay there forever because there are no
more successful I/O jobs to wake up the job handler.

This patch adds a wake() call to always wake up kcopyd job wait queue
for all I/O jobs that fail before dm_io() gets called for that job.

The patch also sets the write error status in all sub jobs that are
failed because their master job has failed.

Fixes: b73c67c2cbb00 ("dm kcopyd: add sequential write feature")
Cc: stable@vger.kernel.org
Signed-off-by: Dmitry Fomichev <dmitry.fomichev@wdc.com>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

show more ...

dm kcopyd: Increase default sub-job size to 512KB

Currently, kcopyd has a sub-job size of 64KB and a maximum number of 8
sub-jobs. As a result, for any kcopyd job, we have a maximum of 512KB of
I/O

dm kcopyd: Increase default sub-job size to 512KB

Currently, kcopyd has a sub-job size of 64KB and a maximum number of 8
sub-jobs. As a result, for any kcopyd job, we have a maximum of 512KB of
I/O in flight.

This upper limit to the amount of in-flight I/O under-utilizes fast
devices and results in decreased throughput, e.g., when writing to a
snapshotted thin LV with I/O size less than the pool's block size (so
COW is performed using kcopyd).

Increase kcopyd's default sub-job size to 512KB, so we have a maximum of
4MB of I/O in flight for each kcopyd job. This results in an up to 96%
improvement of bandwidth when writing to a snapshotted thin LV, with I/O
sizes less than the pool's block size.

Also, add dm_mod.kcopyd_subjob_size_kb module parameter to allow users
to fine tune the sub-job size of kcopyd. The default value of this
parameter is 512KB and the maximum allowed value is 1024KB.

We evaluate the performance impact of the change by running the
snap_breaking_throughput benchmark, from the device mapper test suite
[1].

The benchmark:

1. Creates a 1G thin LV
2. Provisions the thin LV
3. Takes a snapshot of the thin LV
4. Writes to the thin LV with:

dd if=/dev/zero of=/dev/vg/thin_lv oflag=direct bs=<I/O size>

Running this benchmark with various thin pool block sizes and dd I/O
sizes (all combinations triggering the use of kcopyd) we get the
following results:

+-----------------+-------------+------------------+-----------------+
| Pool block size | dd I/O size | BW before (MB/s) | BW after (MB/s) |
+-----------------+-------------+------------------+-----------------+
| 1 MB | 256 KB | 242 | 280 |
| 1 MB | 512 KB | 238 | 295 |
| | | | |
| 2 MB | 256 KB | 238 | 354 |
| 2 MB | 512 KB | 241 | 380 |
| 2 MB | 1 MB | 245 | 394 |
| | | | |
| 4 MB | 256 KB | 248 | 412 |
| 4 MB | 512 KB | 234 | 432 |
| 4 MB | 1 MB | 251 | 474 |
| 4 MB | 2 MB | 257 | 504 |
| | | | |
| 8 MB | 256 KB | 239 | 420 |
| 8 MB | 512 KB | 256 | 431 |
| 8 MB | 1 MB | 264 | 467 |
| 8 MB | 2 MB | 264 | 502 |
| 8 MB | 4 MB | 281 | 537 |
+-----------------+-------------+------------------+-----------------+

[1] https://github.com/jthornber/device-mapper-test-suite

Signed-off-by: Nikos Tsironis <ntsironis@arrikto.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

show more ...

dm kcopyd: Fix bug causing workqueue stalls

When using kcopyd to run callbacks through dm_kcopyd_do_callback() or
submitting copy jobs with a source size of 0, the jobs are pushed
directly to the co

dm kcopyd: Fix bug causing workqueue stalls

When using kcopyd to run callbacks through dm_kcopyd_do_callback() or
submitting copy jobs with a source size of 0, the jobs are pushed
directly to the complete_jobs list, which could be under processing by
the kcopyd thread. As a result, the kcopyd thread can continue running
completed jobs indefinitely, without releasing the CPU, as long as
someone keeps submitting new completed jobs through the aforementioned
paths. Processing of work items, queued for execution on the same CPU as
the currently running kcopyd thread, is thus stalled for excessive
amounts of time, hurting performance.

Running the following test, from the device mapper test suite [1],

dmtest run --suite snapshot -n parallel_io_to_many_snaps_N

, with 8 active snapshots, we get, in dmesg, messages like the
following:

[68899.948523] BUG: workqueue lockup - pool cpus=0 node=0 flags=0x0 nice=0 stuck for 95s!
[68899.949282] Showing busy workqueues and worker pools:
[68899.949288] workqueue events: flags=0x0
[68899.949295] pwq 0: cpus=0 node=0 flags=0x0 nice=0 active=2/256
[68899.949306] pending: vmstat_shepherd, cache_reap
[68899.949331] workqueue mm_percpu_wq: flags=0x8
[68899.949337] pwq 0: cpus=0 node=0 flags=0x0 nice=0 active=1/256
[68899.949345] pending: vmstat_update
[68899.949387] workqueue dm_bufio_cache: flags=0x8
[68899.949392] pwq 4: cpus=2 node=0 flags=0x0 nice=0 active=1/256
[68899.949400] pending: work_fn [dm_bufio]
[68899.949423] workqueue kcopyd: flags=0x8
[68899.949429] pwq 0: cpus=0 node=0 flags=0x0 nice=0 active=1/256
[68899.949437] pending: do_work [dm_mod]
[68899.949452] workqueue kcopyd: flags=0x8
[68899.949458] pwq 0: cpus=0 node=0 flags=0x0 nice=0 active=2/256
[68899.949466] in-flight: 13:do_work [dm_mod]
[68899.949474] pending: do_work [dm_mod]
[68899.949487] workqueue kcopyd: flags=0x8
[68899.949493] pwq 0: cpus=0 node=0 flags=0x0 nice=0 active=1/256
[68899.949501] pending: do_work [dm_mod]
[68899.949515] workqueue kcopyd: flags=0x8
[68899.949521] pwq 0: cpus=0 node=0 flags=0x0 nice=0 active=1/256
[68899.949529] pending: do_work [dm_mod]
[68899.949541] workqueue kcopyd: flags=0x8
[68899.949547] pwq 0: cpus=0 node=0 flags=0x0 nice=0 active=1/256
[68899.949555] pending: do_work [dm_mod]
[68899.949568] pool 0: cpus=0 node=0 flags=0x0 nice=0 hung=95s workers=4 idle: 27130 27223 1084

Fix this by splitting the complete_jobs list into two parts: A user
facing part, named callback_jobs, and one used internally by kcopyd,
retaining the name complete_jobs. dm_kcopyd_do_callback() and
dispatch_job() now push their jobs to the callback_jobs list, which is
spliced to the complete_jobs list once, every time the kcopyd thread
wakes up. This prevents kcopyd from hogging the CPU indefinitely and
causing workqueue stalls.

Re-running the aforementioned test:

* Workqueue stalls are eliminated
* The maximum writing time among all targets is reduced from 09m37.10s
to 06m04.85s and the total run time of the test is reduced from
10m43.591s to 7m19.199s

[1] https://github.com/jthornber/device-mapper-test-suite

Signed-off-by: Nikos Tsironis <ntsironis@arrikto.com>
Signed-off-by: Ilias Tsitsimpis <iliastsi@arrikto.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

show more ...

dm kcopyd: avoid softlockup in run_complete_job

It was reported that softlockups occur when using dm-snapshot ontop of
slow (rbd) storage. E.g.:

[ 4047.990647] watchdog: BUG: soft lockup - CPU#10

dm kcopyd: avoid softlockup in run_complete_job

It was reported that softlockups occur when using dm-snapshot ontop of
slow (rbd) storage. E.g.:

[ 4047.990647] watchdog: BUG: soft lockup - CPU#10 stuck for 22s! [kworker/10:23:26177]
...
[ 4048.034151] Workqueue: kcopyd do_work [dm_mod]
[ 4048.034156] RIP: 0010:copy_callback+0x41/0x160 [dm_snapshot]
...
[ 4048.034190] Call Trace:
[ 4048.034196] ? __chunk_is_tracked+0x70/0x70 [dm_snapshot]
[ 4048.034200] run_complete_job+0x5f/0xb0 [dm_mod]
[ 4048.034205] process_jobs+0x91/0x220 [dm_mod]
[ 4048.034210] ? kcopyd_put_pages+0x40/0x40 [dm_mod]
[ 4048.034214] do_work+0x46/0xa0 [dm_mod]
[ 4048.034219] process_one_work+0x171/0x370
[ 4048.034221] worker_thread+0x1fc/0x3f0
[ 4048.034224] kthread+0xf8/0x130
[ 4048.034226] ? max_active_store+0x80/0x80
[ 4048.034227] ? kthread_bind+0x10/0x10
[ 4048.034231] ret_from_fork+0x35/0x40
[ 4048.034233] Kernel panic - not syncing: softlockup: hung tasks

Fix this by calling cond_resched() after run_complete_job()'s callout to
the dm_kcopyd_notify_fn (which is dm-snap.c:copy_callback in the above
trace).

Signed-off-by: John Pittman <jpittman@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

show more ...

dm kcopyd: return void from dm_kcopyd_copy()

dm_kcopyd_copy() only ever returns 0 so there is no need for callers to
account for possible failure. Same goes for dm_kcopyd_zero().

Signed-off-by: Mi

dm kcopyd: return void from dm_kcopyd_copy()

dm_kcopyd_copy() only ever returns 0 so there is no need for callers to
account for possible failure. Same goes for dm_kcopyd_zero().

Signed-off-by: Mike Snitzer <snitzer@redhat.com>

show more ...

dm: adjust structure members to improve alignment

Eliminate most holes in DM data structures that were modified by
commit 6f1c819c21 ("dm: convert to bioset_init()/mempool_init()").
Also prevent str

dm: adjust structure members to improve alignment

Eliminate most holes in DM data structures that were modified by
commit 6f1c819c21 ("dm: convert to bioset_init()/mempool_init()").
Also prevent structure members from unnecessarily spanning cache
lines.

Signed-off-by: Mike Snitzer <snitzer@redhat.com>

show more ...

dm: Use kzalloc for all structs with embedded biosets/mempools

mempool_init()/bioset_init() require that the mempools/biosets be zeroed
first; they probably should not _require_ this, but not alloca

dm: Use kzalloc for all structs with embedded biosets/mempools

mempool_init()/bioset_init() require that the mempools/biosets be zeroed
first; they probably should not _require_ this, but not allocating those
structs with kzalloc is a fairly nonsensical thing to do (calling
mempool_exit()/bioset_exit() on an uninitialized mempool/bioset is legal
and safe, but only works if said memory was zeroed.)

Acked-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

show more ...

dm: convert to bioset_init()/mempool_init()

Convert dm to embedded bio sets.

Acked-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Je

dm: convert to bioset_init()/mempool_init()

Convert dm to embedded bio sets.

Acked-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

show more ...

dm: backfill missing calls to mutex_destroy()

Signed-off-by: Mike Snitzer <snitzer@redhat.com>