Re: [PATCH tip/core/rcu 01/21] doc: READ_ONCE() now implies smp_barrier_depends()

[David Howells]

Paul E. McKenney <paulmck@xxxxxxxxxxxxxxxxxx> wrote:

> -	Q = READ_ONCE(P); smp_read_barrier_depends(); D = READ_ONCE(*Q);
> +	Q = READ_ONCE(P); D = READ_ONCE(*Q);
>  
>       the CPU will issue the following memory operations:
>  
>  	Q = LOAD P, D = LOAD *Q

The CPU may now issue two barriers in addition to the loads, so should we show
this?  E.g.:

	Q = LOAD P, BARRIER, D = LOAD *Q, BARRIER

David