Skip to content
GitLab
  1. Nov 21, 2009
    • Masami Hiramatsu's avatar
      x86: insn decoder test checks objdump version · 6f5f6726
      Masami Hiramatsu authored 
      

Check objdump version before using it for insn decoder build test,
because some older objdump can't decode AVX code correctly.

Signed-off-by: default avatarMasami Hiramatsu <mhiramat@redhat.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Randy Dunlap <rdunlap@xenotime.net>
Cc: Jim Keniston <jkenisto@us.ibm.com>
LKML-Reference: <20091120171314.6715.30390.stgit@dhcp-100-2-132.bos.redhat.com>
Signed-off-by: default avatarH. Peter Anvin <hpa@zytor.com>
      6f5f6726
    • Masami Hiramatsu's avatar
      x86: Fix insn decoder test typos · 80509e27
      Masami Hiramatsu authored 
      

Fix postest_verbose to posttest_verbose, and add posttest_64bit option
for CONFIG_64BIT != y, since old command just passed '-' instead
of '-n' when CONFIG_64BIT is not set.

Signed-off-by: default avatarMasami Hiramatsu <mhiramat@redhat.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Randy Dunlap <rdunlap@xenotime.net>
Cc: Jim Keniston <jkenisto@us.ibm.com>
LKML-Reference: <20091120171307.6715.66099.stgit@dhcp-100-2-132.bos.redhat.com>
Signed-off-by: default avatarH. Peter Anvin <hpa@zytor.com>
      80509e27
  3. Nov 17, 2009
  5. Nov 16, 2009
    • Peter Zijlstra's avatar
      perf_event: Optimize perf_output_lock() · 559fdc3c
      Peter Zijlstra authored 
      

The purpose of perf_output_{un,}lock() is to:

 1) avoid publishing incomplete data
    [ possible when publishing a head that is ahead of an entry
      that is still being written ]

 2) guarantee fwd progress
    [ a simple refcount on pending writers doesn't need to drop to
      0, making it so would end up implementing something like forced
      quiecent states of RCU ]

To satisfy the above without undue complexity it serializes
between CPUs, this means that a pending writer can only be the
same cpu in a nested context, and since (under normal operation)
a cpu always makes progress we're good -- if the head is only
published when the bottom  most writer completes.

Now we don't need to disable IRQs in order to serialize between
CPUs, disabling preemption ought to be sufficient, esp since we
already deal with nesting due to NMIs.

This avoids potentially expensive (and needless) local IRQ
disable/enable ops.

Signed-off-by: default avatarPeter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <1258373161.26714.254.camel@laptop>
Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      559fdc3c
  7. Nov 15, 2009
    • Lucas De Marchi's avatar
      perf stat: Do not print ratio when task-clock event is not counted · 7255fe2a
      Lucas De Marchi authored 
      

The ratio between the number of events and the time elapsed makes
sense only if task-clock event is counted. Otherwise it will be
simply a (confusing)

	#      0.000 M/sec

This patch outputs the ratio only if task-clock event is counted.
Some test examples of before and after:

Before:

 [lucas@skywalker linux.trees.git]$ sudo perf stat -e branch-misses -a -- sleep 1

	 Performance counter stats for 'sleep 1':

		1367818  branch-misses            #      0.000 M/sec

	    1.001494325  seconds time elapsed

After (without task-clock):

 [lucas@skywalker perf]$ sudo ./perf stat -e branch-misses -a -- sleep 1

	 Performance counter stats for 'sleep 1':

		1135044  branch-misses

	    1.001370775  seconds time elapsed

After (with task-clock):

 [lucas@skywalker perf]$ sudo ./perf stat -e branch-misses -e task-clock -a -- sleep 1

	 Performance counter stats for 'sleep 1':

		1070111  branch-misses            #      0.534 M/sec
	    2002.730893  task-clock-msecs         #      1.999 CPUs

	    1.001640292  seconds time elapsed

Signed-off-by: default avatarLucas De Marchi <lucas.de.marchi@gmail.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
LKML-Reference: <20091115140507.GB21561@skywalker.lan>
Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      7255fe2a
    • Hitoshi Mitake's avatar
      perf tools: Add new perf_atoll() function to parse string representing size in bytes · d2fb8b41
      Hitoshi Mitake authored 
      

This patch modifies util/string.[ch] to add new function:
perf_atoll() to parse string representing size in bytes.

This function parses (\d+)(b|B|kb|KB|mb|MB|gb|GB) (e.g. "256MB")
and returns its numeric value. (e.g. 268435456)

Signed-off-by: default avatarHitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <1258285013-4759-1-git-send-email-mitake@dcl.info.waseda.ac.jp>
Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      d2fb8b41
    • Ingo Molnar's avatar
      Merge branches 'perf/powerpc' and 'perf/bench' into perf/core · 0ffa798d
      Ingo Molnar authored 
      

Merge reason: Both 'perf bench' and the pending PowerPC changes
              are now ready for the next merge window.

Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      0ffa798d
    • Ingo Molnar's avatar
      Merge commit 'v2.6.32-rc7' into perf/core · 39dc78b6
      Ingo Molnar authored 
      

Merge reason: pick up perf fixlets

Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      39dc78b6
  9. Nov 14, 2009
  11. Nov 13, 2009
  13. Nov 12, 2009