lkml.org 
[lkml]   [2012]   [Apr]   [14]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
    /
    From
    Date
    SubjectRe: [PATCH RFC 0/7] rcu: v2 Inlinable preemptible rcu_read_lock() and rcu_read_unlock()
    On Sat, Apr 14, 2012 at 9:19 AM, Paul E. McKenney
    <paulmck@linux.vnet.ibm.com> wrote:
    >
    > It also compiles this:
    >
    >        void rcu_read_unlock_code(void)
    >        {
    >                rcu_read_unlock();
    >        }
    >
    > to this:
    >
    >        000000e0 <rcu_read_unlock_code>:
    >          e0:   64 a1 00 00 00 00       mov    %fs:0x0,%eax
    >          e6:   83 f8 01                cmp    $0x1,%eax
    >          e9:   74 0d                   je     f8 <rcu_read_unlock_code+0x18>
    >          eb:   64 ff 0d 00 00 00 00    decl   %fs:0x0
    >          f2:   c3                      ret
    >          f3:   90                      nop
    >          f4:   8d 74 26 00             lea    0x0(%esi,%eiz,1),%esi
    >          f8:   64 c7 05 00 00 00 00    movl   $0x80000000,%fs:0x0
    >          ff:   00 00 00 80
    >         103:   64 a1 00 00 00 00       mov    %fs:0x0,%eax
    >         109:   85 c0                   test   %eax,%eax
    >         10b:   75 0c                   jne    119 <rcu_read_unlock_code+0x39>
    >         10d:   64 c7 05 00 00 00 00    movl   $0x0,%fs:0x0
    >         114:   00 00 00 00
    >         118:   c3                      ret
    >         119:   8d b4 26 00 00 00 00    lea    0x0(%esi,%eiz,1),%esi
    >         120:   e8 fc ff ff ff          call   121 <rcu_read_unlock_code+0x41>
    >         125:   eb e6                   jmp    10d <rcu_read_unlock_code+0x2d>
    >
    > It is therefore not at all clear to me that the final patch in this
    > series is worthwhile.

    Yeah, the read-unlock does not seem to be worth inlining as-is. As
    mentioned earlier, it tends to be the rcu_read_lock() that we really
    want to inline anyway (not just because it's small, but also because
    the call clobbers registers, and that has other bad interaction).

    Linus
    --
    To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
    the body of a message to majordomo@vger.kernel.org
    More majordomo info at http://vger.kernel.org/majordomo-info.html
    Please read the FAQ at http://www.tux.org/lkml/

    \
     
     \ /
      Last update: 2012-04-14 18:31    [W:2.738 / U:0.076 seconds]
    ©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site