kernel/linux
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ synced 2026-10-20 19:23:40 +00:00
Code Issues Releases Packages Activity
linux/block
History
Li Lingfeng 9b8ec0ea24 block: Fix lockdep warning in blk_mq_mark_tag_wait 
[ Upstream commit b313a8c835 ]

Lockdep reported a warning in Linux version 6.6:

[  414.344659] ================================
[  414.345155] WARNING: inconsistent lock state
[  414.345658] 6.6.0-07439-gba2303cacfda #6 Not tainted
[  414.346221] --------------------------------
[  414.346712] inconsistent {IN-SOFTIRQ-W} -> {SOFTIRQ-ON-W} usage.
[  414.347545] kworker/u10:3/1152 [HC0[0]:SC0[0]:HE0:SE1] takes:
[  414.349245] ffff88810edd1098 (&sbq->ws[i].wait){+.?.}-{2:2}, at: blk_mq_dispatch_rq_list+0x131c/0x1ee0
[  414.351204] {IN-SOFTIRQ-W} state was registered at:
[  414.351751]   lock_acquire+0x18d/0x460
[  414.352218]   _raw_spin_lock_irqsave+0x39/0x60
[  414.352769]   __wake_up_common_lock+0x22/0x60
[  414.353289]   sbitmap_queue_wake_up+0x375/0x4f0
[  414.353829]   sbitmap_queue_clear+0xdd/0x270
[  414.354338]   blk_mq_put_tag+0xdf/0x170
[  414.354807]   __blk_mq_free_request+0x381/0x4d0
[  414.355335]   blk_mq_free_request+0x28b/0x3e0
[  414.355847]   __blk_mq_end_request+0x242/0xc30
[  414.356367]   scsi_end_request+0x2c1/0x830
[  414.345155] WARNING: inconsistent lock state
[  414.345658] 6.6.0-07439-gba2303cacfda #6 Not tainted
[  414.346221] --------------------------------
[  414.346712] inconsistent {IN-SOFTIRQ-W} -> {SOFTIRQ-ON-W} usage.
[  414.347545] kworker/u10:3/1152 [HC0[0]:SC0[0]:HE0:SE1] takes:
[  414.349245] ffff88810edd1098 (&sbq->ws[i].wait){+.?.}-{2:2}, at: blk_mq_dispatch_rq_list+0x131c/0x1ee0
[  414.351204] {IN-SOFTIRQ-W} state was registered at:
[  414.351751]   lock_acquire+0x18d/0x460
[  414.352218]   _raw_spin_lock_irqsave+0x39/0x60
[  414.352769]   __wake_up_common_lock+0x22/0x60
[  414.353289]   sbitmap_queue_wake_up+0x375/0x4f0
[  414.353829]   sbitmap_queue_clear+0xdd/0x270
[  414.354338]   blk_mq_put_tag+0xdf/0x170
[  414.354807]   __blk_mq_free_request+0x381/0x4d0
[  414.355335]   blk_mq_free_request+0x28b/0x3e0
[  414.355847]   __blk_mq_end_request+0x242/0xc30
[  414.356367]   scsi_end_request+0x2c1/0x830
[  414.356863]   scsi_io_completion+0x177/0x1610
[  414.357379]   scsi_complete+0x12f/0x260
[  414.357856]   blk_complete_reqs+0xba/0xf0
[  414.358338]   __do_softirq+0x1b0/0x7a2
[  414.358796]   irq_exit_rcu+0x14b/0x1a0
[  414.359262]   sysvec_call_function_single+0xaf/0xc0
[  414.359828]   asm_sysvec_call_function_single+0x1a/0x20
[  414.360426]   default_idle+0x1e/0x30
[  414.360873]   default_idle_call+0x9b/0x1f0
[  414.361390]   do_idle+0x2d2/0x3e0
[  414.361819]   cpu_startup_entry+0x55/0x60
[  414.362314]   start_secondary+0x235/0x2b0
[  414.362809]   secondary_startup_64_no_verify+0x18f/0x19b
[  414.363413] irq event stamp: 428794
[  414.363825] hardirqs last  enabled at (428793): [<ffffffff816bfd1c>] ktime_get+0x1dc/0x200
[  414.364694] hardirqs last disabled at (428794): [<ffffffff85470177>] _raw_spin_lock_irq+0x47/0x50
[  414.365629] softirqs last  enabled at (428444): [<ffffffff85474780>] __do_softirq+0x540/0x7a2
[  414.366522] softirqs last disabled at (428419): [<ffffffff813f65ab>] irq_exit_rcu+0x14b/0x1a0
[  414.367425]
               other info that might help us debug this:
[  414.368194]  Possible unsafe locking scenario:
[  414.368900]        CPU0
[  414.369225]        ----
[  414.369548]   lock(&sbq->ws[i].wait);
[  414.370000]   <Interrupt>
[  414.370342]     lock(&sbq->ws[i].wait);
[  414.370802]
                *** DEADLOCK ***
[  414.371569] 5 locks held by kworker/u10:3/1152:
[  414.372088]  #0: ffff88810130e938 ((wq_completion)writeback){+.+.}-{0:0}, at: process_scheduled_works+0x357/0x13f0
[  414.373180]  #1: ffff88810201fdb8 ((work_completion)(&(&wb->dwork)->work)){+.+.}-{0:0}, at: process_scheduled_works+0x3a3/0x13f0
[  414.374384]  #2: ffffffff86ffbdc0 (rcu_read_lock){....}-{1:2}, at: blk_mq_run_hw_queue+0x637/0xa00
[  414.375342]  #3: ffff88810edd1098 (&sbq->ws[i].wait){+.?.}-{2:2}, at: blk_mq_dispatch_rq_list+0x131c/0x1ee0
[  414.376377]  #4: ffff888106205a08 (&hctx->dispatch_wait_lock){+.-.}-{2:2}, at: blk_mq_dispatch_rq_list+0x1337/0x1ee0
[  414.378607]
               stack backtrace:
[  414.379177] CPU: 0 PID: 1152 Comm: kworker/u10:3 Not tainted 6.6.0-07439-gba2303cacfda #6
[  414.380032] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014
[  414.381177] Workqueue: writeback wb_workfn (flush-253:0)
[  414.381805] Call Trace:
[  414.382136]  <TASK>
[  414.382429]  dump_stack_lvl+0x91/0xf0
[  414.382884]  mark_lock_irq+0xb3b/0x1260
[  414.383367]  ? __pfx_mark_lock_irq+0x10/0x10
[  414.383889]  ? stack_trace_save+0x8e/0xc0
[  414.384373]  ? __pfx_stack_trace_save+0x10/0x10
[  414.384903]  ? graph_lock+0xcf/0x410
[  414.385350]  ? save_trace+0x3d/0xc70
[  414.385808]  mark_lock.part.20+0x56d/0xa90
[  414.386317]  mark_held_locks+0xb0/0x110
[  414.386791]  ? __pfx_do_raw_spin_lock+0x10/0x10
[  414.387320]  lockdep_hardirqs_on_prepare+0x297/0x3f0
[  414.387901]  ? _raw_spin_unlock_irq+0x28/0x50
[  414.388422]  trace_hardirqs_on+0x58/0x100
[  414.388917]  _raw_spin_unlock_irq+0x28/0x50
[  414.389422]  __blk_mq_tag_busy+0x1d6/0x2a0
[  414.389920]  __blk_mq_get_driver_tag+0x761/0x9f0
[  414.390899]  blk_mq_dispatch_rq_list+0x1780/0x1ee0
[  414.391473]  ? __pfx_blk_mq_dispatch_rq_list+0x10/0x10
[  414.392070]  ? sbitmap_get+0x2b8/0x450
[  414.392533]  ? __blk_mq_get_driver_tag+0x210/0x9f0
[  414.393095]  __blk_mq_sched_dispatch_requests+0xd99/0x1690
[  414.393730]  ? elv_attempt_insert_merge+0x1b1/0x420
[  414.394302]  ? __pfx___blk_mq_sched_dispatch_requests+0x10/0x10
[  414.394970]  ? lock_acquire+0x18d/0x460
[  414.395456]  ? blk_mq_run_hw_queue+0x637/0xa00
[  414.395986]  ? __pfx_lock_acquire+0x10/0x10
[  414.396499]  blk_mq_sched_dispatch_requests+0x109/0x190
[  414.397100]  blk_mq_run_hw_queue+0x66e/0xa00
[  414.397616]  blk_mq_flush_plug_list.part.17+0x614/0x2030
[  414.398244]  ? __pfx_blk_mq_flush_plug_list.part.17+0x10/0x10
[  414.398897]  ? writeback_sb_inodes+0x241/0xcc0
[  414.399429]  blk_mq_flush_plug_list+0x65/0x80
[  414.399957]  __blk_flush_plug+0x2f1/0x530
[  414.400458]  ? __pfx___blk_flush_plug+0x10/0x10
[  414.400999]  blk_finish_plug+0x59/0xa0
[  414.401467]  wb_writeback+0x7cc/0x920
[  414.401935]  ? __pfx_wb_writeback+0x10/0x10
[  414.402442]  ? mark_held_locks+0xb0/0x110
[  414.402931]  ? __pfx_do_raw_spin_lock+0x10/0x10
[  414.403462]  ? lockdep_hardirqs_on_prepare+0x297/0x3f0
[  414.404062]  wb_workfn+0x2b3/0xcf0
[  414.404500]  ? __pfx_wb_workfn+0x10/0x10
[  414.404989]  process_scheduled_works+0x432/0x13f0
[  414.405546]  ? __pfx_process_scheduled_works+0x10/0x10
[  414.406139]  ? do_raw_spin_lock+0x101/0x2a0
[  414.406641]  ? assign_work+0x19b/0x240
[  414.407106]  ? lock_is_held_type+0x9d/0x110
[  414.407604]  worker_thread+0x6f2/0x1160
[  414.408075]  ? __kthread_parkme+0x62/0x210
[  414.408572]  ? lockdep_hardirqs_on_prepare+0x297/0x3f0
[  414.409168]  ? __kthread_parkme+0x13c/0x210
[  414.409678]  ? __pfx_worker_thread+0x10/0x10
[  414.410191]  kthread+0x33c/0x440
[  414.410602]  ? __pfx_kthread+0x10/0x10
[  414.411068]  ret_from_fork+0x4d/0x80
[  414.411526]  ? __pfx_kthread+0x10/0x10
[  414.411993]  ret_from_fork_asm+0x1b/0x30
[  414.412489]  </TASK>

When interrupt is turned on while a lock holding by spin_lock_irq it
throws a warning because of potential deadlock.

blk_mq_prep_dispatch_rq
 blk_mq_get_driver_tag
  __blk_mq_get_driver_tag
   __blk_mq_alloc_driver_tag
    blk_mq_tag_busy -> tag is already busy
    // failed to get driver tag
 blk_mq_mark_tag_wait
  spin_lock_irq(&wq->lock) -> lock A (&sbq->ws[i].wait)
  __add_wait_queue(wq, wait) -> wait queue active
  blk_mq_get_driver_tag
  __blk_mq_tag_busy
-> 1) tag must be idle, which means there can't be inflight IO
   spin_lock_irq(&tags->lock) -> lock B (hctx->tags)
   spin_unlock_irq(&tags->lock) -> unlock B, turn on interrupt accidentally
-> 2) context must be preempt by IO interrupt to trigger deadlock.

As shown above, the deadlock is not possible in theory, but the warning
still need to be fixed.

Fix it by using spin_lock_irqsave to get lockB instead of spin_lock_irq.

Fixes: 4f1731df60 ("blk-mq: fix potential io hang by wrong 'wake_batch'")
Signed-off-by: Li Lingfeng <lilingfeng3@huawei.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Yu Kuai <yukuai3@huawei.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20240815024736.2040971-1-lilingfeng@huaweicloud.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Sasha Levin <sashal@kernel.org>
History 2024-08-29 17:30:33 +02:00
..
partitions block: Move checking GENHD_FL_NO_PART to bdev_add_partition() 2024-01-31 16:17:11 -08:00
badblocks.c block/badblocks: Remove redundant assignments 2022-04-23 07:15:26 -06:00
bdev.c block: update the stable_writes flag in bdev_add 2024-01-10 17:10:32 +01:00
bfq-cgroup.c block, bfq: fix uaf for bfqq in bic_set_bfqq() 2023-02-09 11:28:06 +01:00
bfq-iosched.c block, bfq: Fix division by zero error on zero wsum 2023-05-24 17:32:38 +01:00
bfq-iosched.h block, bfq: remove unused variable for bfq_queue 2022-10-20 05:46:49 -07:00
bfq-wf2q.c block, bfq: remove useless parameter for bfq_add/del_bfqq_busy() 2022-08-22 10:07:56 -06:00
bio-integrity.c block: initialize integrity buffer to zero before writing it to media 2024-08-03 08:48:53 +02:00
bio.c block: Fix page refcounts for unaligned buffers in __bio_release_pages() 2024-04-03 15:19:46 +02:00
blk-cgroup-fc-appid.c cgroup: Homogenize cgroup_get_from_id() return value 2022-08-26 10:57:41 -10:00
blk-cgroup-rwstat.c blk-cgroup: Fix the recursive blkg rwstat 2021-03-05 11:32:15 -07:00
blk-cgroup-rwstat.h block: Use the new blk_opf_t type 2022-07-14 12:14:30 -06:00
blk-cgroup.c blk-cgroup: bypass blkcg_deactivate_policy after destroying 2023-12-20 17:00:21 +01:00
blk-cgroup.h blk-cgroup: pass a gendisk to blkcg_init_queue and blkcg_exit_queue 2022-09-26 19:09:31 -06:00
blk-core.c block: support to account io_ticks precisely 2024-06-12 11:03:07 +02:00
blk-crypto-fallback.c blk-crypto: dynamically allocate fallback profile 2023-08-23 17:52:39 +02:00
blk-crypto-internal.h blk-mq: release crypto keyslot before reporting I/O complete 2023-05-11 23:03:00 +09:00
blk-crypto-profile.c blk-crypto: use dynamic lock class for blk_crypto_profile::lock 2023-07-23 13:49:21 +02:00
blk-crypto-sysfs.c blk-crypto: show crypto capabilities in sysfs 2022-02-28 06:40:23 -07:00
blk-crypto.c blk-crypto: make blk_crypto_evict_key() more robust 2023-05-11 23:03:01 +09:00
blk-flush.c block: change request end_io handler to pass back a return value 2022-09-30 07:49:09 -06:00
blk-ia-ranges.c block: simplify disk_set_independent_access_ranges 2022-06-29 08:36:46 -06:00
blk-integrity.c blk-crypto: remove blk_crypto_unregister() 2021-11-29 06:38:51 -07:00
blk-ioc.c block: fix default IO priority handling again 2022-06-27 06:29:12 -06:00
blk-iocost.c blk-iocost: avoid out of bounds shift 2024-05-17 11:56:07 +02:00
blk-iolatency.c blk-cgroup: pass a gendisk to blkcg_schedule_throttle 2022-09-26 19:17:28 -06:00
blk-ioprio.c blk-ioprio: pass a gendisk to blk_ioprio_init and blk_ioprio_exit 2022-09-26 19:09:31 -06:00
blk-ioprio.h blk-ioprio: pass a gendisk to blk_ioprio_init and blk_ioprio_exit 2022-09-26 19:09:31 -06:00
blk-lib.c blk-lib: fix blkdev_issue_secure_erase 2022-09-15 00:25:17 -06:00
blk-map.c block: Fix WARNING in _copy_from_iter 2024-03-01 13:26:25 +01:00
blk-merge.c block: support to account io_ticks precisely 2024-06-12 11:03:07 +02:00
blk-mq-cpumap.c block: Change the return type of blk_mq_map_queues() into void 2022-08-22 10:07:53 -06:00
blk-mq-debugfs-zoned.c block: move zone related fields to struct gendisk 2022-07-06 06:46:26 -06:00
blk-mq-debugfs.c blk-mq: fix potential io hang by wrong 'wake_batch' 2023-07-19 16:20:55 +02:00
blk-mq-debugfs.h block: remove per-disk debugfs files in blk_unregister_queue 2022-06-17 07:31:05 -06:00
blk-mq-pci.c block: Change the return type of blk_mq_map_queues() into void 2022-08-22 10:07:53 -06:00
blk-mq-rdma.c block: Change the return type of blk_mq_map_queues() into void 2022-08-22 10:07:53 -06:00
blk-mq-sched.c blk-mq: correct stale comment of .get_budget 2023-03-10 09:32:44 +01:00
blk-mq-sched.h block: move blk_mq_sched_assign_ioc to blk-ioc.c 2021-11-29 06:41:29 -07:00
blk-mq-sysfs.c blk-mq: fix possible memleak when register 'hctx' failed 2022-12-31 13:33:03 +01:00
blk-mq-tag.c block: Fix lockdep warning in blk_mq_mark_tag_wait 2024-08-29 17:30:33 +02:00
blk-mq-tag.h blk-mq: blk_mq_tag_busy is no need to return a value 2022-06-27 06:29:12 -06:00
blk-mq-virtio.c block: Change the return type of blk_mq_map_queues() into void 2022-08-22 10:07:53 -06:00
blk-mq.c block: Call .limit_depth() after .hctx has been set 2024-08-14 13:53:02 +02:00
blk-mq.h blk-mq: fix potential io hang by wrong 'wake_batch' 2023-07-19 16:20:55 +02:00
blk-pm.c scsi: block: pm: Always set request queue runtime active in blk_post_runtime_resume() 2021-12-22 23:38:29 -05:00
blk-pm.h block: Remove unused blk_pm_*() function definitions 2021-02-22 06:33:48 -07:00
blk-rq-qos.c block/rq_qos: Use atomic_try_cmpxchg in atomic_inc_below 2022-07-12 14:38:52 -06:00
blk-rq-qos.h block/blk-rq-qos: delete useless enmu RQ_QOS_IOPRIO 2022-09-21 19:50:53 -06:00
blk-settings.c block: Clear zone limits for a non-zoned stacked queue 2024-04-03 15:19:27 +02:00
blk-stat.c block: prevent division by zero in blk_rq_stat_sum() 2024-04-13 13:05:12 +02:00
blk-stat.h block: make queue stat accounting a reference 2021-12-14 17:23:05 -07:00
blk-sysfs.c block: fix use-after-free of q->q_usage_counter 2023-10-10 22:00:37 +02:00
blk-throttle.c blk-throttle: fix lockdep warning of "cgroup_mutex or RCU read lock required!" 2023-12-20 17:00:21 +01:00
blk-throttle.h blk-throttle: pass a gendisk to blk_throtl_cancel_bios 2022-09-26 19:17:28 -06:00
blk-timeout.c block: blk-timeout: delete duplicated word 2020-07-31 16:29:47 -06:00
blk-wbt.c blk-wbt: fix that 'rwb->wc' is always set to 1 in wbt_init() 2022-10-09 07:48:16 -06:00
blk-wbt.h blk-wbt: remove wbt_track stub 2022-03-31 12:58:38 -06:00
blk-zoned.c block: adapt blk_mq_plug() to not plug for writes that require a zone lock 2022-09-29 07:45:47 -06:00
blk.h block: support to account io_ticks precisely 2024-06-12 11:03:07 +02:00
bounce.c block: change the blk_queue_bounce calling convention 2022-08-02 17:22:54 -06:00
bsg-lib.c blk-mq: Drop blk_mq_ops.timeout 'reserved' arg 2022-07-06 06:33:53 -06:00
bsg.c scsi: core: bsg: Remove usage of the deprecated ida_simple_xxx() API 2022-06-21 21:22:51 -04:00
disk-events.c block: increment diskseq on all media change events 2023-07-19 16:21:47 +02:00
elevator.c blk-mq: use quiesced elevator switch when reinitializing queues 2022-09-27 09:58:56 -06:00
elevator.h block: Use the new blk_opf_t type 2022-07-14 12:14:30 -06:00
fops.c block: Don't invalidate pagecache for invalid falloc modes 2024-01-10 17:10:20 +01:00
genhd.c block: support to account io_ticks precisely 2024-06-12 11:03:07 +02:00
holder.c block: remove WARN_ON() from bd_link_disk_holder 2022-06-23 07:48:05 -06:00
ioctl.c block/ioctl: prefer different overflow check 2024-06-27 13:46:15 +02:00
ioprio.c block: Fix handling of tasks without ioprio in ioprio_get(2) 2022-06-27 06:29:12 -06:00
Kconfig block: remove "select BLK_RQ_IO_DATA_LEN" from BLK_CGROUP_IOCOST dependency 2022-06-29 08:35:57 -06:00
Kconfig.iosched block: only build the icq tracking code when needed 2021-12-16 10:59:02 -07:00
kyber-iosched.c block/kyber: Use the new blk_opf_t type 2022-07-14 12:14:30 -06:00
Makefile blk-cgroup: move blkcg_{get,set}_fc_appid out of line 2022-05-02 14:06:20 -06:00
mq-deadline.c block/mq-deadline: Fix the tag reservation code 2024-08-14 13:53:02 +02:00
opal_proto.h block: sed-opal: handle empty atoms when parsing response 2024-03-26 18:20:26 -04:00
sed-opal.c block: sed-opal: handle empty atoms when parsing response 2024-03-26 18:20:26 -04:00
t10-pi.c block: add pi for extended integrity 2022-03-07 12:48:35 -07:00