Re: [PATCH] call_rcu: stop using mb_set/mb_read

[Richard Henderson <richard.henderson@linaro.org>]

On 4/30/23 12:25, Paolo Bonzini wrote:
> Use a store-release when enqueuing a new call_rcu, and a load-acquire
> when dequeuing; and read the tail after checking that node->next is
> consistent, which is the standard message passing pattern and it is
> clearer than mb_read/mb_set.
> 
> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
> ---
>   util/rcu.c | 38 +++++++++++++++++++++++++++-----------
>   1 file changed, 27 insertions(+), 11 deletions(-)
> 
> diff --git a/util/rcu.c b/util/rcu.c
> index e5b6e52be6f8..867607cd5a1e 100644
> --- a/util/rcu.c
> +++ b/util/rcu.c
> @@ -189,8 +189,22 @@ static void enqueue(struct rcu_head *node)
>       struct rcu_head **old_tail;
>   
>       node->next = NULL;
> +
> +    /*
> +     * Make this node the tail of the list.  The node will be
> +     * used by further enqueue operations, but it will not
> +     * be dequeued yet...
> +     */
>       old_tail = qatomic_xchg(&tail, &node->next);
> -    qatomic_mb_set(old_tail, node);
> +
> +    /*
> +     * ... until it is pointed to from another item in the list.
> +     * In the meanwhile, try_dequeue() will find a NULL next pointer

Either "In the meantime" or "Meanwhile" (noun vs adverb).
E.g. "Meanwhile, at Try Dequeue's volcano lair..."  :-)


> +    /* If the head node has NULL in its next pointer, the value is
> +     * wrong and we need to wait until its enqueuer finishes the update.
> +     */

/*
  *
  */

I know surrounding code is different, but slowly it will all be edited.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>


r~