Re: [PATCH next v2 2/5] locking/osq_lock: Optimise the vcpu_is_preempted() check.

[Waiman Long <longman@redhat.com>]

On 12/31/23 16:52, David Laight wrote:
> The vcpu_is_preempted() test stops osq_lock() spinning if a virtual
> cpu is no longer running.
>
> Although patched out for bare-metal the code still needs the cpu number.
> Reading this from 'prev->cpu' is a pretty much guaranteed have a cache miss
> when osq_unlock() is waking up the next cpu.
>
> Instead save 'prev->cpu' in 'node->prev_cpu' and use that value instead.
> Update in the osq_lock() 'unqueue' path when 'node->prev' is changed.
>
> This is simpler than checking for 'node->prev' changing and caching
> 'prev->cpu'.
>
> Signed-off-by: David Laight <david.laight@aculab.com>
> ---
>   kernel/locking/osq_lock.c | 16 +++++++---------
>   1 file changed, 7 insertions(+), 9 deletions(-)
>
> diff --git a/kernel/locking/osq_lock.c b/kernel/locking/osq_lock.c
> index e0bc74d85a76..eb8a6dfdb79d 100644
> --- a/kernel/locking/osq_lock.c
> +++ b/kernel/locking/osq_lock.c
> @@ -14,8 +14,9 @@
>   
>   struct optimistic_spin_node {
>   	struct optimistic_spin_node *next, *prev;
> -	int locked; /* 1 if lock acquired */
> -	int cpu; /* encoded CPU # + 1 value */
> +	int locked;    /* 1 if lock acquired */
> +	int cpu;       /* encoded CPU # + 1 value */
> +	int prev_cpu;  /* encoded CPU # + 1 value */
>   };
>   
>   static DEFINE_PER_CPU_SHARED_ALIGNED(struct optimistic_spin_node, osq_node);
> @@ -29,11 +30,6 @@ static inline int encode_cpu(int cpu_nr)
>   	return cpu_nr + 1;
>   }
>   
> -static inline int node_cpu(struct optimistic_spin_node *node)
> -{
> -	return node->cpu - 1;
> -}
> -
>   static inline struct optimistic_spin_node *decode_cpu(int encoded_cpu_val)
>   {
>   	int cpu_nr = encoded_cpu_val - 1;
> @@ -110,9 +106,10 @@ bool osq_lock(struct optimistic_spin_queue *lock)
>   	if (old == OSQ_UNLOCKED_VAL)
>   		return true;
>   
> -	node->locked = 0;
> +	node->prev_cpu = old;
>   	prev = decode_cpu(old);
>   	node->prev = prev;
> +	node->locked = 0;
>   
>   	/*
>   	 * osq_lock()			unqueue
> @@ -144,7 +141,7 @@ bool osq_lock(struct optimistic_spin_queue *lock)
>   	 * polling, be careful.
>   	 */
>   	if (smp_cond_load_relaxed(&node->locked, VAL || need_resched() ||
> -				  vcpu_is_preempted(node_cpu(node->prev))))
> +				  vcpu_is_preempted(READ_ONCE(node->prev_cpu) - 1)))
>   		return true;
>   
>   	/* unqueue */
> @@ -201,6 +198,7 @@ bool osq_lock(struct optimistic_spin_queue *lock)
>   	 * it will wait in Step-A.
>   	 */
>   
> +	WRITE_ONCE(next->prev_cpu, prev->cpu);
>   	WRITE_ONCE(next->prev, prev);
>   	WRITE_ONCE(prev->next, next);
>   

Reviewed-by: Waiman Long <longman@redhat.com>

Reviewed-by: Waiman Long <longman@redhat.com>