blk-iocost: use spin_lock_irqsave in adjust_inuse_and_calc_cost

adjust_inuse_and_calc_cost() use spin_lock_irq() and IRQ will be enabled
when unlock. DEADLOCK might happen if we have held other locks and disabled
IRQ before invoking it.

Fix it by using spin_lock_irqsave() instead, which can keep IRQ state
consistent with before when unlock.

  ================================
  WARNING: inconsistent lock state
  5.10.0-02758-g8e5f91fd772f #26 Not tainted
  --------------------------------
  inconsistent {IN-HARDIRQ-W} -> {HARDIRQ-ON-W} usage.
  kworker/2:3/388 [HC0[0]:SC0[0]:HE0:SE1] takes:
  ffff888118c00c28 (&bfqd->lock){?.-.}-{2:2}, at: spin_lock_irq
  ffff888118c00c28 (&bfqd->lock){?.-.}-{2:2}, at: bfq_bio_merge+0x141/0x390
  {IN-HARDIRQ-W} state was registered at:
    __lock_acquire+0x3d7/0x1070
    lock_acquire+0x197/0x4a0
    __raw_spin_lock_irqsave
    _raw_spin_lock_irqsave+0x3b/0x60
    bfq_idle_slice_timer_body
    bfq_idle_slice_timer+0x53/0x1d0
    __run_hrtimer+0x477/0xa70
    __hrtimer_run_queues+0x1c6/0x2d0
    hrtimer_interrupt+0x302/0x9e0
    local_apic_timer_interrupt
    __sysvec_apic_timer_interrupt+0xfd/0x420
    run_sysvec_on_irqstack_cond
    sysvec_apic_timer_interrupt+0x46/0xa0
    asm_sysvec_apic_timer_interrupt+0x12/0x20
  irq event stamp: 837522
  hardirqs last  enabled at (837521): [<ffffffff84b9419d>] __raw_spin_unlock_irqrestore
  hardirqs last  enabled at (837521): [<ffffffff84b9419d>] _raw_spin_unlock_irqrestore+0x3d/0x40
  hardirqs last disabled at (837522): [<ffffffff84b93fa3>] __raw_spin_lock_irq
  hardirqs last disabled at (837522): [<ffffffff84b93fa3>] _raw_spin_lock_irq+0x43/0x50
  softirqs last  enabled at (835852): [<ffffffff84e00558>] __do_softirq+0x558/0x8ec
  softirqs last disabled at (835845): [<ffffffff84c010ff>] asm_call_irq_on_stack+0xf/0x20

  other info that might help us debug this:
   Possible unsafe locking scenario:

         CPU0
         ----
    lock(&bfqd->lock);
    <Interrupt>
      lock(&bfqd->lock);

   *** DEADLOCK ***

  3 locks held by kworker/2:3/388:
   #0: ffff888107af0f38 ((wq_completion)kthrotld){+.+.}-{0:0}, at: process_one_work+0x742/0x13f0
   #1: ffff8881176bfdd8 ((work_completion)(&td->dispatch_work)){+.+.}-{0:0}, at: process_one_work+0x777/0x13f0
   #2: ffff888118c00c28 (&bfqd->lock){?.-.}-{2:2}, at: spin_lock_irq
   #2: ffff888118c00c28 (&bfqd->lock){?.-.}-{2:2}, at: bfq_bio_merge+0x141/0x390

  stack backtrace:
  CPU: 2 PID: 388 Comm: kworker/2:3 Not tainted 5.10.0-02758-g8e5f91fd772f #26
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014
  Workqueue: kthrotld blk_throtl_dispatch_work_fn
  Call Trace:
   __dump_stack lib/dump_stack.c:77 [inline]
   dump_stack+0x107/0x167
   print_usage_bug
   valid_state
   mark_lock_irq.cold+0x32/0x3a
   mark_lock+0x693/0xbc0
   mark_held_locks+0x9e/0xe0
   __trace_hardirqs_on_caller
   lockdep_hardirqs_on_prepare.part.0+0x151/0x360
   trace_hardirqs_on+0x5b/0x180
   __raw_spin_unlock_irq
   _raw_spin_unlock_irq+0x24/0x40
   spin_unlock_irq
   adjust_inuse_and_calc_cost+0x4fb/0x970
   ioc_rqos_merge+0x277/0x740
   __rq_qos_merge+0x62/0xb0
   rq_qos_merge
   bio_attempt_back_merge+0x12c/0x4a0
   blk_mq_sched_try_merge+0x1b6/0x4d0
   bfq_bio_merge+0x24a/0x390
   __blk_mq_sched_bio_merge+0xa6/0x460
   blk_mq_sched_bio_merge
   blk_mq_submit_bio+0x2e7/0x1ee0
   __submit_bio_noacct_mq+0x175/0x3b0
   submit_bio_noacct+0x1fb/0x270
   blk_throtl_dispatch_work_fn+0x1ef/0x2b0
   process_one_work+0x83e/0x13f0
   process_scheduled_works
   worker_thread+0x7e3/0xd80
   kthread+0x353/0x470
   ret_from_fork+0x1f/0x30

Fixes: b0853ab4a2 ("blk-iocost: revamp in-period donation snapbacks")
Signed-off-by: Li Nan <linan122@huawei.com>
Acked-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Yu Kuai <yukuai3@huawei.com>
Link: https://lore.kernel.org/r/20230527091904.3001833-1-linan666@huaweicloud.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This commit is contained in:
Li Nan 2023-05-27 17:19:04 +08:00 committed by Jens Axboe
parent 2577f53f42
commit 8d21155467

View File

@ -2455,6 +2455,7 @@ static u64 adjust_inuse_and_calc_cost(struct ioc_gq *iocg, u64 vtime,
u32 hwi, adj_step; u32 hwi, adj_step;
s64 margin; s64 margin;
u64 cost, new_inuse; u64 cost, new_inuse;
unsigned long flags;
current_hweight(iocg, NULL, &hwi); current_hweight(iocg, NULL, &hwi);
old_hwi = hwi; old_hwi = hwi;
@ -2473,11 +2474,11 @@ static u64 adjust_inuse_and_calc_cost(struct ioc_gq *iocg, u64 vtime,
iocg->inuse == iocg->active) iocg->inuse == iocg->active)
return cost; return cost;
spin_lock_irq(&ioc->lock); spin_lock_irqsave(&ioc->lock, flags);
/* we own inuse only when @iocg is in the normal active state */ /* we own inuse only when @iocg is in the normal active state */
if (iocg->abs_vdebt || list_empty(&iocg->active_list)) { if (iocg->abs_vdebt || list_empty(&iocg->active_list)) {
spin_unlock_irq(&ioc->lock); spin_unlock_irqrestore(&ioc->lock, flags);
return cost; return cost;
} }
@ -2498,7 +2499,7 @@ static u64 adjust_inuse_and_calc_cost(struct ioc_gq *iocg, u64 vtime,
} while (time_after64(vtime + cost, now->vnow) && } while (time_after64(vtime + cost, now->vnow) &&
iocg->inuse != iocg->active); iocg->inuse != iocg->active);
spin_unlock_irq(&ioc->lock); spin_unlock_irqrestore(&ioc->lock, flags);
TRACE_IOCG_PATH(inuse_adjust, iocg, now, TRACE_IOCG_PATH(inuse_adjust, iocg, now,
old_inuse, iocg->inuse, old_hwi, hwi); old_inuse, iocg->inuse, old_hwi, hwi);