Re: [PATCH] workqueue: avoid re-entry of pwq->pool->lock through __queue_work

[Kassey Li]

On 7/28/2022 12:51 AM, Lai Jiangshan wrote:
> On Wed, Jul 27, 2022 at 7:04 PM Kassey Li <quic_yingangl@xxxxxxxxxxx> wrote:
> > [0:swapper/4]BUG: spinlock recursion on CPU#4, swapper/4/0
> > [0:swapper/4]lock: 0xffffff8000c0f400, .magic: dead4ead, .owner:
> > swapper/4/0, .owner_cpu: 4
> > [0:swapper/4]CPU: 4 PID: 0 Comm: swapper/4 Tainted: G S
> > [0:swapper/4]Call trace:
> > [0:swapper/4] dump_backtrace.cfi_jt+0x0/0x8
> > [0:swapper/4] show_stack+0x1c/0x2c
> > [0:swapper/4] dump_stack_lvl+0xd8/0x16c
> > [0:swapper/4] spin_dump+0x104/0x278
> > [0:swapper/4] do_raw_spin_lock+0xec/0x15c
> > [0:swapper/4] _raw_spin_lock+0x28/0x3c
> > [0:swapper/4] __queue_work+0x1fc/0x618
> > [0:swapper/4] queue_work_on+0x64/0x134
> > [0:swapper/4] memlat_hrtimer_handler+0x28/0x3c [memlat]
> > [0:swapper/4] __run_hrtimer+0xe8/0x448
> > [0:swapper/4] hrtimer_interrupt+0x184/0x40c
> > [0:swapper/4] arch_timer_handler_virt+0x5c/0x98
> > [0:swapper/4] handle_percpu_devid_irq+0xd8/0x3e0
> > [0:swapper/4] __handle_domain_irq+0xd0/0x19c
> > [0:swapper/4] gic_handle_irq+0x6c/0x134
> > [0:swapper/4] el1_irq+0xe4/0x1c0
>
> It seems it is an unexpected IRQ.
   thanks for your suggest, we will focus on the api usage of spin_lock 
where possible broken the irq enable/disable.
   currently, abandon this change.
> > [0:swapper/4] _raw_spin_unlock_irqrestore+0x2c/0x60
> > [0:swapper/4] try_to_wake_up.llvm.14610847381734009831+0x334/0x888
> > [0:swapper/4] wake_up_process+0x1c/0x2c
> > [0:swapper/4] __queue_work+0x3e8/0x618
> > [0:swapper/4] delayed_work_timer_fn+0x24/0x34
>
> delayed_work_timer_fn() should have been invoked with IRQ disabled
> since it is TIMER_IRQSAFE.
>
> Could you add some code to check if it is the case if possible, please?
  the timer flags = 0x15200004, which means TIMER_IRQSAFE is set.
  #define TIMER_IRQSAFE 0x00200000

> > [0:swapper/4] call_timer_fn+0x58/0x268
> > [0:swapper/4] expire_timers+0xe0/0x1c4
>
> Or could you do a "disass expire_timers+0xe0" in GDB?


   0xffffffc01025bf44 <+200>:   tbz     w8, #5, 0xffffffc01025bee4 
<expire_timers+104>
   0xffffffc01025bf48 <+204>:   bl      0xffffffc0118093bc 
<_raw_spin_unlock>
   0xffffffc01025bf4c <+208>:   mov     x0, x23
   0xffffffc01025bf50 <+212>:   mov     x1, x24
   0xffffffc01025bf54 <+216>:   mov     x2, x21
   0xffffffc01025bf58 <+220>:   bl      0xffffffc01025c040 <call_timer_fn>
   0xffffffc01025bf5c <+224>:   mov     x0, x20 //expire_timers+0xe0
--Type <RET> for more, q to quit, c to continue without paging--
   0xffffffc01025bf60 <+228>:   bl      0xffffffc011809230 <_raw_spin_lock>
   0xffffffc01025bf64 <+232>:   b       0xffffffc01025bf00 
<expire_timers+132>

> > [0:swapper/4] __run_timers+0x16c/0x1c4
> > [0:swapper/4] run_timer_softirq+0x34/0x60
> > [0:swapper/4] efi_header_end+0x198/0x59c
> > [0:swapper/4] __irq_exit_rcu+0xdc/0xf0
> > [0:swapper/4] irq_exit+0x14/0x50
> > [0:swapper/4] __handle_domain_irq+0xd4/0x19c
> > [0:swapper/4] gic_handle_irq+0x6c/0x134
> > [0:swapper/4] el1_irq+0xe4/0x1c0
> > [0:swapper/4] cpuidle_enter_state+0x1b4/0x5dc
> > [0:swapper/4] cpuidle_enter+0x3c/0x58
> > [0:swapper/4] do_idle.llvm.6296834828977863291+0x1f4/0x2e8
> > [0:swapper/4] cpu_startup_entry+0x28/0x2c
> > [0:swapper/4] secondary_start_kernel+0x1c8/0x230
> >
> > Signed-off-by: Kassey Li <quic_yingangl@xxxxxxxxxxx>
> > ---
> >   kernel/workqueue.c | 8 ++++----
> >   1 file changed, 4 insertions(+), 4 deletions(-)
> >
> > diff --git a/kernel/workqueue.c b/kernel/workqueue.c
> > index 1ea50f6be843..f23491f373b1 100644
> > --- a/kernel/workqueue.c
> > +++ b/kernel/workqueue.c
> > @@ -1468,10 +1468,10 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
> >                  } else {
> >                          /* meh... not running there, queue here */
> >                          raw_spin_unlock(&last_pool->lock);
> > -                       raw_spin_lock(&pwq->pool->lock);
> > +                       raw_spin_lock_irq(&pwq->pool->lock);
> >                  }
> >          } else {
> > -               raw_spin_lock(&pwq->pool->lock);
> > +               raw_spin_lock_irq(&pwq->pool->lock);
> >          }
> >
> >          /*
> > @@ -1484,7 +1484,7 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
> >           */
> >          if (unlikely(!pwq->refcnt)) {
> >                  if (wq->flags & WQ_UNBOUND) {
> > -                       raw_spin_unlock(&pwq->pool->lock);
> > +                       raw_spin_unlock_irq(&pwq->pool->lock);
>
> The patch is hardly correct, __queue_work() is called with irq-disabled,
> this code will enable IRQ imbalanced.
>
> >                          cpu_relax();
> >                          goto retry;
> >                  }
> > @@ -1517,7 +1517,7 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
> >          insert_work(pwq, work, worklist, work_flags);
> >
> >   out:
> > -       raw_spin_unlock(&pwq->pool->lock);
> > +       raw_spin_unlock_irq(&pwq->pool->lock);
> >          rcu_read_unlock();
> >   }
> >
> > --
> > 2.17.1