Skip to content

L
linux

xiphi1978 / linux

通知 2
Star 0
Fork 0
L
linux

体验新版 GitCode，发现更多精彩内容 >>

切换分支/标签
  1. 11 5月, 2008 4 次提交
    • L
      BKL: revert back to the old spinlock implementation · 8e3e076c
      由 Linus Torvalds 提交于 
      The generic semaphore rewrite had a huge performance regression on AIM7
(and potentially other BKL-heavy benchmarks) because the generic
semaphores had been rewritten to be simple to understand and fair.  The
latter, in particular, turns a semaphore-based BKL implementation into a
mess of scheduling.

The attempt to fix the performance regression failed miserably (see the
previous commit 00b41ec2 'Revert
"semaphore: fix"'), and so for now the simple and sane approach is to
instead just go back to the old spinlock-based BKL implementation that
never had any issues like this.

This patch also has the advantage of being reported to fix the
regression completely according to Yanmin Zhang, unlike the semaphore
hack which still left a couple percentage point regression.

As a spinlock, the BKL obviously has the potential to be a latency
issue, but it's not really any different from any other spinlock in that
respect.  We do want to get rid of the BKL asap, but that has been the
plan for several years.

These days, the biggest users are in the tty layer (open/release in
particular) and Alan holds out some hope:

  "tty release is probably a few months away from getting cured - I'm
   afraid it will almost certainly be the very last user of the BKL in
   tty to get fixed as it depends on everything else being sanely locked."

so while we're not there yet, we do have a plan of action.
Tested-by: NYanmin Zhang <yanmin_zhang@linux.intel.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Matthew Wilcox <matthew@wil.cx>
Cc: Alexander Viro <viro@ftp.linux.org.uk>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      8e3e076c
    • L
      Revert "semaphore: fix" · 00b41ec2
      由 Linus Torvalds 提交于 
      This reverts commit bf726eab, as it has
been reported to cause a regression with processes stuck in __down(),
apparently because some missing wakeup.

Quoth Sven Wegener:
 "I'm currently investigating a regression that has showed up with my
  last git pull yesterday.  Bisecting the commits showed bf726e
  "semaphore: fix" to be the culprit, reverting it fixed the issue.

  Symptoms: During heavy filesystem usage (e.g.  a kernel compile) I get
  several compiler processes in uninterruptible sleep, blocking all i/o
  on the filesystem.  System is an Intel Core 2 Quad running a 64bit
  kernel and userspace.  Filesystem is xfs on top of lvm.  See below for
  the output of sysrq-w."

See

	http://lkml.org/lkml/2008/5/10/45

for full report.

In the meantime, we can just fix the BKL performance regression by
reverting back to the good old BKL spinlock implementation instead,
since any sleeping lock will generally perform badly, especially if it
tries to be fair.
Reported-by: NSven Wegener <sven.wegener@stealer.net>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      00b41ec2
    • L
      Make <asm-x86/spinlock.h> use ACCESS_ONCE() · 39f004ba
      由 Linus Torvalds 提交于 
      ..instead of cooking up its own uglier local version of it.
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      39f004ba
    • L
      Move ACCESS_ONCE() to <linux/compiler.h> · 9c3cdc1f
      由 Linus Torvalds 提交于 
      It actually makes much more sense there, and we do tend to need it for
non-RCU usage too.  Moving it to <linux/compiler.h> will allow some
other cases that have open-coded the same logic to use the same helper
function that RCU has used.
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      9c3cdc1f
  3. 10 5月, 2008 1 次提交
    • L
      Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/cooloney/blackfin-2.6 · 3ed43c74
      由 Linus Torvalds 提交于 
      * 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/cooloney/blackfin-2.6: (21 commits)
  Blackfin Serial Driver: abstract away DLAB differences into header
  Blackfin Serial Driver: macro away the IER differences between processors
  [Blackfin] arch: remove useless IRQ_SW_INT defines
  [Blackfin] arch: protect linux/usb/musb.h include until the driver gets mainlined
  [Blackfin] arch: protect linux/usb/isp1362.h include until the driver gets mainlined
  [Blackfin] arch: add EBIU supporting for BF54x EZKIT SMSC LAN911x/LAN921x families embedded ethernet driver
  [Blackfin] arch: Set spi flash partition on bf527 as like bf548.
  [Blackfin] arch: fix bug - Remove module will not free L1 memory used
  [Blackfin] arch: fix wrong header name in comment
  [Blackfin] arch: Fix BUG - spi flash on bf527 ezkit would fail at mount
  [Blackfin] arch: add twi_lcd and twi_keypad i2c board info to bf527-ezkit
  [Blackfin] arch: Add physmap partition for BF527-EZkit
  [Blackfin] arch: fix gdb testing regression
  [Blackfin] arch: disable single stepping when delivering a signal
  [Blackfin] arch: Delete unused (copied from m68k) entries in asm-offsets.c.
  [Blackfin] arch: In the double fault handler, set up the PT_RETI slot
  [Blackfin] arch: Support for CPU_FREQ and NOHZ
  [Blackfin] arch: Functional power management support: Add CPU and platform voltage scaling support
  [Blackfin] arch: fix bug -  breaking the atomic sections code.
  [Blackfin] arch: Equalize include files: Add VR_CTL masks
  ...
      3ed43c74
  5. 09 5月, 2008 35 次提交