Re: [PATCH v2] locking/mutex: Prevent lock starvation when spinning is enabled

[Waiman Long <waiman.long@hpe.com>]

On 08/10/2016 02:44 PM, Jason Low wrote:
> Imre reported an issue where threads are getting starved when trying
> to acquire a mutex. Threads acquiring a mutex can get arbitrarily delayed
> sleeping on a mutex because other threads can continually steal the lock
> in the fastpath and/or through optimistic spinning.
>
> Waiman has developed patches that allow waiters to return to optimistic
> spinning, thus reducing the probability that starvation occurs. However,
> Imre still sees this starvation problem in the workloads when optimistic
> spinning is disabled.
>
> This patch adds an additional boolean to the mutex that gets used in
> the CONFIG_SMP&&  !CONFIG_MUTEX_SPIN_ON_OWNER cases. The flag signifies
> whether or not other threads need to yield to a waiter and gets set
> when a waiter spends too much time waiting for the mutex. The threshold
> is currently set to 16 wakeups, and once the wakeup threshold is exceeded,
> other threads must yield to the top waiter. The flag gets cleared
> immediately after the top waiter acquires the mutex.
>
> This prevents waiters from getting starved without sacrificing much
> much performance, as lock stealing is still allowed and only
> temporarily disabled when it is detected that a waiter has been waiting
> for too long.
>
> Reported-by: Imre Deak<imre.deak@intel.com>
> Signed-off-by: Jason Low<jason.low2@hpe.com>
> ---
> v1->v2:
> - Addressed Waiman's suggestions of needing the yield_to_waiter
>    flag only in the CONFIG_SMP case.
>
> - Make sure to only clear the flag if the thread is the top waiter.
>
> - Refactor code to clear flag into an inline function.
>
> - Rename 'loops' variable name to 'wakeups'.
>
>   include/linux/mutex.h  |  2 ++
>   kernel/locking/mutex.c | 83 +++++++++++++++++++++++++++++++++++++++++++-------
>   2 files changed, 74 insertions(+), 11 deletions(-)
>
> diff --git a/include/linux/mutex.h b/include/linux/mutex.h
> index 2cb7531..5643a233 100644
> --- a/include/linux/mutex.h
> +++ b/include/linux/mutex.h
> @@ -57,6 +57,8 @@ struct mutex {
>   #endif
>   #ifdef CONFIG_MUTEX_SPIN_ON_OWNER
>   	struct optimistic_spin_queue osq; /* Spinner MCS lock */
> +#elif defined(CONFIG_SMP)
> +	bool yield_to_waiter; /* Prevent starvation when spinning disabled */
>   #endif
>   #ifdef CONFIG_DEBUG_MUTEXES
>   	void			*magic;
> diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
> index a70b90d..faf31a0 100644
> --- a/kernel/locking/mutex.c
> +++ b/kernel/locking/mutex.c
> @@ -55,6 +55,8 @@ __mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key)
>   	mutex_clear_owner(lock);
>   #ifdef CONFIG_MUTEX_SPIN_ON_OWNER
>   	osq_lock_init(&lock->osq);
> +#elif defined(CONFIG_SMP)
> +	lock->yield_to_waiter = false;
>   #endif
>
>   	debug_mutex_init(lock, name, key);
> @@ -71,6 +73,9 @@ EXPORT_SYMBOL(__mutex_init);
>    */
>   __visible void __sched __mutex_lock_slowpath(atomic_t *lock_count);
>
> +
> +static inline bool need_yield_to_waiter(struct mutex *lock);
> +
>   /**
>    * mutex_lock - acquire the mutex
>    * @lock: the mutex to be acquired
> @@ -99,7 +104,10 @@ void __sched mutex_lock(struct mutex *lock)
>   	 * The locking fastpath is the 1->0 transition from
>   	 * 'unlocked' into 'locked' state.
>   	 */
> -	__mutex_fastpath_lock(&lock->count, __mutex_lock_slowpath);
> +	if (!need_yield_to_waiter(lock))
> +		__mutex_fastpath_lock(&lock->count, __mutex_lock_slowpath);
> +	else
> +		__mutex_lock_slowpath(&lock->count);
>   	mutex_set_owner(lock);
>   }
>
> @@ -398,12 +406,51 @@ done:
>
>   	return false;
>   }
> +
> +static inline void do_yield_to_waiter(struct mutex *lock, int *wakeups)
> +{
> +	return;
> +}
> +
> +static inline void clear_yield_to_waiter(struct mutex *lock)
> +{
> +	return;
> +}
> +
> +static inline bool need_yield_to_waiter(struct mutex *lock)
> +{
> +	return false;
> +}
> +
>   #else
>   static bool mutex_optimistic_spin(struct mutex *lock,
>   				  struct ww_acquire_ctx *ww_ctx, const bool use_ww_ctx)
>   {
>   	return false;
>   }
> +
> +#define MUTEX_WAKEUP_THRESHOLD 16
> +
> +static inline void do_yield_to_waiter(struct mutex *lock, int *wakeups)
> +{
> +	*wakeups += 1;
> +
> +	if (*wakeups<  MUTEX_WAKEUP_THRESHOLD)
> +		return;
> +
> +	if (lock->yield_to_waiter != true)
> +		lock->yield_to_waiter = true;
> +}
> +
> +static inline void clear_yield_to_waiter(struct mutex *lock)
> +{
> +	lock->yield_to_waiter = false;
> +}
> +
> +static inline bool need_yield_to_waiter(struct mutex *lock)
> +{
> +	return lock->yield_to_waiter;
> +}
>   #endif
>
>   _

The *yield* helper functions should be in a separate conditional 
compilation block as the declaration of yield_to_waiter may not match 
the helper functions with certain combination of config variables.

Something like

#if !defined(CONFIG_MUTEX_SPIN_ON_OWNER) && defined(CONFIG_SMP)
...
#else
...
#endif

Cheers,
Longman