Re: [PATCH v2] ipc/msg: Implement lockless pipelined wakeups

[Peter Zijlstra <peterz@infradead.org>]

On Tue, Nov 03, 2015 at 04:03:29PM +0100, Sebastian Andrzej Siewior wrote:
> @@ -932,58 +924,26 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, int msgfl
>  		rcu_read_lock();
>  
>  		/* Lockless receive, part 2:

This is a broken comment style, please fix that while you're there
anyway.

Also, the comment above ("Lockless receive, part 1:") is broken
too, not only in style, but it refers to rcu_read_unlock() as disabling
preemption, and avoiding preemption, which is false.

> +		 * The work in pipelined_send() and expunge_all():
> +		 * - Set pointer to message
> +		 * - Queue the receiver task for later wakeup
> +		 * - Wake up the process after the lock is dropped.
>  		 *
> +		 * Should the process wake up before this wakeup (due to a
> +		 * signal) it will either see the message and continue ...
>  		 */
>  
> +		msg = msr_d.r_msg;

Since this is a lockless read, it should very much be READ_ONCE(), esp.
since you killed the volatile on its type.