Re: br_read_lock SMP race fix

From: David S. Miller (davem@redhat.com)
Date: Thu Jul 27 2000 - 19:55:26 EDT

  • Next message: Johan Kullstam: "Re: RLIM_INFINITY inconsistency between archs"

       Date: Wed, 26 Jul 2000 17:00:40 +0200 (CEST)
       From: Andrea Arcangeli <andrea@suse.de>

       I don't see why we need any ordering in the fallback path.

    Here is one reason. Without the memory barrier nothing guarentees the
    store of the counter decrement will leave the local cpu store buffer
    in finite time (and thus be visible to the writer). If an ordering is
    imposed between the counter decrement store and the spin loop loads,
    the store is propagated in finite time thus allowing the writer to
    proceed in finite time.

    Later,
    David S. Miller
    davem@redhat.com

    -
    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/



    This archive was generated by hypermail 2b29 : Thu Jul 27 2000 - 20:13:42 EDT