[lkml]   [2010]   [Sep]   [26]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
    Patch in this message
    SubjectRe: fs hang in 2.6.27.y | Fwd: [Bug 15658] New: [PATCH] x86 constant_test_bit() prone to misoptimization with gcc-4.4
    On Thu, Sep 23, 2010 at 04:50:22PM -0700, Andrew Morton wrote:
    > Working around a gcc-4.4 bug is a good thing, and the patch cleans the
    > code up anyway - is there a reason for casting away the `volatile const'?

    It turned out that I translated the original assumption of _gcc_
    fault (from our bugzilla) when the latter conclusion was that it
    was correctly optimizing the code given that addr wasn't marked
    as volatile. My fault, sorry; fixed the commit comment this time.

    > I changed the patch cosmetics a bit, see below.
    > We don't have a Signed-off-by: for this patch - it would be
    > good to have one, please. We should at least have yours, as
    > you sent the patch.

    The simplicity of adding that somewhat went over my head --
    please find attached the corrected original patch against HEAD
    with Signed-off-by: for both of us. led@ didn't change cosmetics
    -- thanks for providing it anyways.

    > Also, we prefer to have real names in kernel commits.
    > Does "Led" refer to Alexander Chumachenko?

    (just in case) Yes.

    ---- WBR, Michael Shigorin <>
    ------ Linux.Kiev
    From 70e6a20b3720e522633f4b791f2f35e817d7ced3 Mon Sep 17 00:00:00 2001
    From: Led <>
    Date: Thu, 1 Apr 2010 15:34:52 +0300
    Subject: [PATCH] x86: avoid 'constant_test_bit()' misoptimization due to cast to non-volatile

    While debugging bit_spin_lock() hang, it was tracked down to gcc-4.4
    misoptimization of non-inlined constant_test_bit() due to non-volatile
    addr when 'const volatile unsigned long *addr' cast to 'unsigned long *'
    with subsequent unconditional jump to pause (and not to the test) leading
    to hang.

    Compiling with gcc-4.3 or disabling CONFIG_OPTIMIZE_INLINING yields inlined
    constant_test_bit() and correct jump, thus working around the kernel bug.

    Other arches than asm-x86 may implement this slightly differently;
    2.6.29 mitigates the misoptimization by changing the function prototype
    (commit c4295fbb6048d85f0b41c5ced5cbf63f6811c46c) but probably fixing the issue
    itself is better.

    Signed-off-by: Alexander Chumachenko <>
    Signed-off-by: Michael Shigorin <>

    arch/x86/include/asm/bitops.h | 2 +-
    1 files changed, 1 insertions(+), 1 deletions(-)

    diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
    index 545776e..bafd80d 100644
    --- a/arch/x86/include/asm/bitops.h
    +++ b/arch/x86/include/asm/bitops.h
    @@ -309,7 +309,7 @@ static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
    static __always_inline int constant_test_bit(unsigned int nr, const volatile unsigned long *addr)
    return ((1UL << (nr % BITS_PER_LONG)) &
    - (((unsigned long *)addr)[nr / BITS_PER_LONG])) != 0;
    + (addr[nr / BITS_PER_LONG])) != 0;

    static inline int variable_test_bit(int nr, volatile const unsigned long *addr)
    [unhandled content-type:application/pgp-signature]
     \ /
      Last update: 2010-09-27 20:09    [W:0.045 / U:2.936 seconds]
    ©2003-2017 Jasper Spaans. hosted at Digital OceanAdvertise on this site