Skip to content

L
linux
Switch branch/tag
  1. 01 Aug, 2010 2 commits
  3. 29 Jul, 2010 1 commit
    • H. Peter Anvin's avatar
      x86, asm: Merge cmpxchg_486_u64() and cmpxchg8b_emu() · a378d933
      H. Peter Anvin authored 
      We have two functions for doing exactly the same thing -- emulating
cmpxchg8b on 486 and older hardware -- with different calling
conventions, and yet doing the same thing.  Drop the C version and use
the assembly version, via alternatives, for both the local and
non-local versions of cmpxchg8b.
Signed-off-by: default avatarH. Peter Anvin <hpa@linux.intel.com>
LKML-Reference: <AANLkTikAmaDPji-TVDarmG1yD=fwbffcsmEU=YEuP+8r@mail.gmail.com>
      a378d933
  5. 28 Jul, 2010 5 commits
    • H. Peter Anvin's avatar
      x86, asm: Move cmpxchg emulation code to arch/x86/lib · 90c8f92f
      H. Peter Anvin authored 
      Move cmpxchg emulation code from arch/x86/kernel/cpu (which is
otherwise CPU identification) to arch/x86/lib, where other emulation
code lives already.
Signed-off-by: default avatarH. Peter Anvin <hpa@linux.intel.com>
LKML-Reference: <AANLkTikAmaDPji-TVDarmG1yD=fwbffcsmEU=YEuP+8r@mail.gmail.com>
      90c8f92f
    • H. Peter Anvin's avatar
      x86, asm: Clean up and simplify <asm/cmpxchg.h> · 4532b305
      H. Peter Anvin authored 
      Remove the __xg() hack to create a memory barrier near xchg and
cmpxchg; it has been there since 1.3.11 but should not be necessary
with "asm volatile" and a "memory" clobber, neither of which were
there in the original implementation.

However, we *should* make this a volatile reference.
Signed-off-by: default avatarH. Peter Anvin <hpa@linux.intel.com>
LKML-Reference: <AANLkTikAmaDPji-TVDarmG1yD=fwbffcsmEU=YEuP+8r@mail.gmail.com>
      4532b305
    • H. Peter Anvin's avatar
      x86, asm: Clean up and simplify set_64bit() · 69309a05
      H. Peter Anvin authored 
      Clean up and simplify set_64bit().  This code is quite old (1.3.11)
and contains a fair bit of auxilliary machinery that current versions
of gcc handle just fine automatically.  Worse, the auxilliary
machinery can actually cause an unnecessary spill to memory.

Furthermore, the loading of the old value inside the loop in the
32-bit case is unnecessary: if the value doesn't match, the CMPXCHG8B
instruction will already have loaded the "new previous" value for us.

Clean up the comment, too, and remove page references to obsolete
versions of the Intel SDM.
Signed-off-by: default avatarH. Peter Anvin <hpa@zytor.com>
LKML-Reference: <tip-*@vger.kernel.org>
      69309a05
    • H. Peter Anvin's avatar
      Merge remote branch 'origin/x86/urgent' into x86/asm · d3608b56
      H. Peter Anvin authored
      d3608b56
    • H. Peter Anvin's avatar
      x86: Add memory modify constraints to xchg() and cmpxchg() · 113fc5a6
      H. Peter Anvin authored 
      xchg() and cmpxchg() modify their memory operands, not merely read
them.  For some versions of gcc the "memory" clobber has apparently
dealt with the situation, but not for all.
Originally-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: default avatarH. Peter Anvin <hpa@zytor.com>
Cc: Glauber Costa <glommer@redhat.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Peter Palfrader <peter@palfrader.org>
Cc: Greg KH <gregkh@suse.de>
Cc: Alan Cox <alan@lxorguk.ukuu.org.uk>
Cc: Zachary Amsden <zamsden@redhat.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: <stable@kernel.org>
LKML-Reference: <4C4F7277.8050306@zytor.com>
      113fc5a6
  7. 27 Jul, 2010 10 commits
  9. 26 Jul, 2010 22 commits
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7