Re: [PATCH 1/6] net/rds: Avoid queuing superfluous send and recv work

[Jakub Kicinski <kuba@kernel.org>]

On Wed, 2 Apr 2025 01:34:40 +0000 Allison Henderson wrote:
> I had a look at the example, how about we move the barriers from
> rds_clear_queued_send_work_bit into rds_cond_queue_send_work?  Then
> we have something like this:
> 
> static inline void rds_cond_queue_send_work(struct rds_conn_path *cp,
> unsigned long delay) {
> 	/* Ensure prior clear_bit operations for RDS_SEND_WORK_QUEUED are observed  */ smp_mb__before_atomic();
> 
>         if (!test_and_set_bit(RDS_SEND_WORK_QUEUED, &cp->cp_flags))
>                 queue_delayed_work(rds_wq, &cp->cp_send_w, delay);
> 
> 	/* Ensure the RDS_SEND_WORK_QUEUED bit is observed before proceeding */ smp_mb__after_atomic();
> }
> 
> I think that's more like whats in the example, and in line with what
> this patch is trying to do.  Let me know what you think.

Sorry, this still feels like a cargo cult to me.
Let's get a clear explanation of what the barriers order 
or just skip the patch.