Re: [PATCH v5 02/19] locking/mutex: Removes wakeups from under mutex::wait_lock

[Waiman Long <longman@redhat.com>]

On 8/19/23 02:08, John Stultz wrote:
> In preparation to nest mutex::wait_lock under rq::lock we need to remove
> wakeups from under it.
>
> Cc: Joel Fernandes <joelaf@google.com>
> Cc: Qais Yousef <qyousef@google.com>
> Cc: Ingo Molnar <mingo@redhat.com>
> Cc: Peter Zijlstra <peterz@infradead.org>
> Cc: Juri Lelli <juri.lelli@redhat.com>
> Cc: Vincent Guittot <vincent.guittot@linaro.org>
> Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
> Cc: Valentin Schneider <vschneid@redhat.com>
> Cc: Steven Rostedt <rostedt@goodmis.org>
> Cc: Ben Segall <bsegall@google.com>
> Cc: Zimuzo Ezeozue <zezeozue@google.com>
> Cc: Youssef Esmat <youssefesmat@google.com>
> Cc: Mel Gorman <mgorman@suse.de>
> Cc: Daniel Bristot de Oliveira <bristot@redhat.com>
> Cc: Will Deacon <will@kernel.org>
> Cc: Waiman Long <longman@redhat.com>
> Cc: Boqun Feng <boqun.feng@gmail.com>
> Cc: "Paul E . McKenney" <paulmck@kernel.org>
> Cc: kernel-team@android.com
> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
> [Heavily changed after 55f036ca7e74 ("locking: WW mutex cleanup") and
> 08295b3b5bee ("locking: Implement an algorithm choice for Wound-Wait
> mutexes")]
> Signed-off-by: Juri Lelli <juri.lelli@redhat.com>
> [jstultz: rebased to mainline, added extra wake_up_q & init
>   to avoid hangs, similar to Connor's rework of this patch]
> Signed-off-by: John Stultz <jstultz@google.com>
> ---
> v5:
> * Reverted back to an earlier version of this patch to undo
>    the change that kept the wake_q in the ctx structure, as
>    that broke the rule that the wake_q must always be on the
>    stack, as its not safe for concurrency.
> ---
>   kernel/locking/mutex.c    | 15 ++++++++++++---
>   kernel/locking/ww_mutex.h | 29 ++++++++++++++++++-----------
>   2 files changed, 30 insertions(+), 14 deletions(-)
>
> diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
> index d973fe6041bf..118b6412845c 100644
> --- a/kernel/locking/mutex.c
> +++ b/kernel/locking/mutex.c
> @@ -570,6 +570,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
>   		    struct lockdep_map *nest_lock, unsigned long ip,
>   		    struct ww_acquire_ctx *ww_ctx, const bool use_ww_ctx)
>   {
> +	DEFINE_WAKE_Q(wake_q);
>   	struct mutex_waiter waiter;
>   	struct ww_mutex *ww;
>   	int ret;
> @@ -620,7 +621,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
>   	 */
>   	if (__mutex_trylock(lock)) {
>   		if (ww_ctx)
> -			__ww_mutex_check_waiters(lock, ww_ctx);
> +			__ww_mutex_check_waiters(lock, ww_ctx, &wake_q);
>   
>   		goto skip_wait;
>   	}
> @@ -640,7 +641,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
>   		 * Add in stamp order, waking up waiters that must kill
>   		 * themselves.
>   		 */
> -		ret = __ww_mutex_add_waiter(&waiter, lock, ww_ctx);
> +		ret = __ww_mutex_add_waiter(&waiter, lock, ww_ctx, &wake_q);
>   		if (ret)
>   			goto err_early_kill;
>   	}
> @@ -676,6 +677,10 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
>   		}
>   
>   		raw_spin_unlock(&lock->wait_lock);
> +		/* Make sure we do wakeups before calling schedule */
> +		wake_up_q(&wake_q);
> +		wake_q_init(&wake_q);
> +

The wake_q may have task to wake up only in the case of ww_mutex which 
is a minority in the kernel. IOW, wake_up_q() which is a function call 
will do nothing in most cases. From an optimization point of view, it is 
better to do a "!wake_q_empty(&wake_q)" check before calling wake_up_q().


>   		schedule_preempt_disabled();
>   
>   		first = __mutex_waiter_is_first(lock, &waiter);
> @@ -709,7 +714,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
>   		 */
>   		if (!ww_ctx->is_wait_die &&
>   		    !__mutex_waiter_is_first(lock, &waiter))
> -			__ww_mutex_check_waiters(lock, ww_ctx);
> +			__ww_mutex_check_waiters(lock, ww_ctx, &wake_q);
>   	}
>   
>   	__mutex_remove_waiter(lock, &waiter);
> @@ -725,6 +730,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
>   		ww_mutex_lock_acquired(ww, ww_ctx);
>   
>   	raw_spin_unlock(&lock->wait_lock);
> +	wake_up_q(&wake_q);
>   	preempt_enable();
>   	return 0;
>   
> @@ -736,6 +742,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
>   	raw_spin_unlock(&lock->wait_lock);
>   	debug_mutex_free_waiter(&waiter);
>   	mutex_release(&lock->dep_map, ip);
> +	wake_up_q(&wake_q);
>   	preempt_enable();
>   	return ret;
>   }
> @@ -946,9 +953,11 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne
>   	if (owner & MUTEX_FLAG_HANDOFF)
>   		__mutex_handoff(lock, next);
>   
> +	preempt_disable();
>   	raw_spin_unlock(&lock->wait_lock);
>   
>   	wake_up_q(&wake_q);
> +	preempt_enable();
>   }

I think it looks better to put the preempt_disable() right before 
raw_spin_lock() for proper nesting.

Cheers,
Longman