Re: [PATCH] locking/semaphore: Use wake_q to wake up processes outside lock critical section

[Waiman Long]

On 1/18/22 10:32, Waiman Long wrote:
> The following lockdep splat was observed:
>
> [ 9776.459819] ======================================================
> [ 9776.459820] WARNING: possible circular locking dependency detected
> [ 9776.459821] 5.14.0-0.rc4.35.el9.x86_64+debug #1 Not tainted
> [ 9776.459823] ------------------------------------------------------
> [ 9776.459824] stress-ng/117708 is trying to acquire lock:
> [ 9776.459825] ffffffff892d41d8 ((console_sem).lock){-...}-{2:2}, at: down_trylock+0x13/0x70
>
> [ 9776.459831] but task is already holding lock:
> [ 9776.459832] ffff888e005f6d18 (&rq->__lock){-.-.}-{2:2}, at: raw_spin_rq_lock_nested+0x27/0x130
>
> [ 9776.459837] which lock already depends on the new lock.
>        :
> [ 9776.459857] -> #1 (&p->pi_lock){-.-.}-{2:2}:
> [ 9776.459860]        __lock_acquire+0xb72/0x1870
> [ 9776.459861]        lock_acquire+0x1ca/0x570
> [ 9776.459862]        _raw_spin_lock_irqsave+0x40/0x90
> [ 9776.459863]        try_to_wake_up+0x9d/0x1210
> [ 9776.459864]        up+0x7a/0xb0
> [ 9776.459864]        __up_console_sem+0x33/0x70
> [ 9776.459865]        console_unlock+0x3a1/0x5f0
> [ 9776.459866]        vprintk_emit+0x23b/0x2b0
> [ 9776.459867]        devkmsg_emit.constprop.0+0xab/0xdc
> [ 9776.459868]        devkmsg_write.cold+0x4e/0x78
> [ 9776.459869]        do_iter_readv_writev+0x343/0x690
> [ 9776.459870]        do_iter_write+0x123/0x340
> [ 9776.459871]        vfs_writev+0x19d/0x520
> [ 9776.459871]        do_writev+0x110/0x290
> [ 9776.459872]        do_syscall_64+0x3b/0x90
> [ 9776.459873]        entry_SYSCALL_64_after_hwframe+0x44/0xae
>        :
> [ 9776.459905] Chain exists of:
> [ 9776.459906]   (console_sem).lock --> &p->pi_lock --> &rq->__lock
>
> [ 9776.459911]  Possible unsafe locking scenario:
>
> [ 9776.459913]        CPU0                    CPU1
> [ 9776.459914]        ----                    ----
> [ 9776.459914]   lock(&rq->__lock);
> [ 9776.459917]                                lock(&p->pi_lock);
> [ 9776.459919]                                lock(&rq->__lock);
> [ 9776.459921]   lock((console_sem).lock);
>
> [ 9776.459923]  *** DEADLOCK ***
>
> The problematic locking sequence ((console_sem).lock --> &p->pi_lock)
> was caused by the fact the semaphore up() function is calling
> wake_up_process() while holding the semaphore raw spinlock.
>
> By moving the wake_up_processs() call out of the raw spinlock critical
> section using wake_q, it will break the problematic locking sequence as
> well as reducing raw spinlock hold time which will be good for
> PREEMPT_RT.
>
> Signed-off-by: Waiman Long <longman@xxxxxxxxxx>
> ---
>   kernel/locking/semaphore.c | 13 +++++++++----
>   1 file changed, 9 insertions(+), 4 deletions(-)
>
> diff --git a/kernel/locking/semaphore.c b/kernel/locking/semaphore.c
> index 9ee381e4d2a4..a26c915430ba 100644
> --- a/kernel/locking/semaphore.c
> +++ b/kernel/locking/semaphore.c
> @@ -29,6 +29,7 @@
>   #include <linux/export.h>
>   #include <linux/sched.h>
>   #include <linux/sched/debug.h>
> +#include <linux/sched/wake_q.h>
>   #include <linux/semaphore.h>
>   #include <linux/spinlock.h>
>   #include <linux/ftrace.h>
> @@ -37,7 +38,7 @@ static noinline void __down(struct semaphore *sem);
>   static noinline int __down_interruptible(struct semaphore *sem);
>   static noinline int __down_killable(struct semaphore *sem);
>   static noinline int __down_timeout(struct semaphore *sem, long timeout);
> -static noinline void __up(struct semaphore *sem);
> +static noinline void __up(struct semaphore *sem, struct wake_q_head *wake_q);
>   
>   /**
>    * down - acquire the semaphore
> @@ -182,13 +183,16 @@ EXPORT_SYMBOL(down_timeout);
>   void up(struct semaphore *sem)
>   {
>   	unsigned long flags;
> +	DEFINE_WAKE_Q(wake_q);
>   
>   	raw_spin_lock_irqsave(&sem->lock, flags);
>   	if (likely(list_empty(&sem->wait_list)))
>   		sem->count++;
>   	else
> -		__up(sem);
> +		__up(sem, &wake_q);
>   	raw_spin_unlock_irqrestore(&sem->lock, flags);
> +	if (!wake_q_empty(&wake_q))
> +		wake_up_q(&wake_q);
>   }
>   EXPORT_SYMBOL(up);
>   
> @@ -256,11 +260,12 @@ static noinline int __sched __down_timeout(struct semaphore *sem, long timeout)
>   	return __down_common(sem, TASK_UNINTERRUPTIBLE, timeout);
>   }
>   
> -static noinline void __sched __up(struct semaphore *sem)
> +static noinline void __sched __up(struct semaphore *sem,
> +				  struct wake_q_head *wake_q)
>   {
>   	struct semaphore_waiter *waiter = list_first_entry(&sem->wait_list,
>   						struct semaphore_waiter, list);
>   	list_del(&waiter->list);
>   	waiter->up = true;
> -	wake_up_process(waiter->task);
> +	wake_q_add(wake_q, waiter->task);
>   }

Peter, is this patch good enough to be merged?

Regards,
Longman