Messages in this thread | | | Date | Fri, 26 Nov 1999 02:51:47 +0100 (CET) | From | Andrea Arcangeli <> | Subject | Re: [patch] smp-2.3.30-A1, mb(), wmb(), rmb() |
| |
On Fri, 26 Nov 1999, Ingo Molnar wrote:
>On Thu, 25 Nov 1999, Andrea Arcangeli wrote: > >> Your "addl $0, (%%esp)" make no sense to me. > >It's basically a dummy store, which prevents previous reads executing >after the write has been executed. [It's guaranteed to be a store and it >will never be optimized away by the CPU as a no-op.]
Yes but you put it in rmb() and rmb() should prevent also following reads to be moved before the barrier.
Andrea
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
| |