From 39e6dd73502f64e2ae3236b304e160ae30de9384 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 14 Aug 2009 15:26:32 -0300
Subject: [PATCH 1/6] perf record: Fix typo in pid_synthesize_comm_event
We were using 'fd' locally, but there was a global 'fd' too, so
when converting from open to fopen the test made against fd
should be made against 'fp', but since we have that global
it didnt get discovered ...
Reported-by: Ulrich Drepper <drepper@redhat.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
LKML-Reference: <20090814182632.GF3490@ghostprotocols.net>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
tools/perf/builtin-record.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 3d051b9cf25f..89a5ddcd1ded 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -219,7 +219,7 @@ static pid_t pid_synthesize_comm_event(pid_t pid, int full)
snprintf(filename, sizeof(filename), "/proc/%d/status", pid);
fp = fopen(filename, "r");
- if (fd == NULL) {
+ if (fp == NULL) {
/*
* We raced with a task exiting - just return:
*/
From 2932cffc89e9a1476b28a59896fa4f81e0d4f131 Mon Sep 17 00:00:00 2001
From: "Carlos R. Mafra" <crmafra@gmail.com>
Date: Mon, 17 Aug 2009 00:36:21 +0200
Subject: [PATCH 2/6] perf: Rename perf-examples.txt to examples.txt
Rename it to examples.txt to avoid the perf-*.txt pattern in
the Makefile, otherwise 'make doc' fails because
perf-examples.txt is not formatted to be a man page:
ERROR: perf-examples.txt: line 1: manpage document title is mandatory
Signed-off-by: Carlos R. Mafra <crmafra@gmail.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
tools/perf/Documentation/{perf-examples.txt => examples.txt} | 0
1 file changed, 0 insertions(+), 0 deletions(-)
rename tools/perf/Documentation/{perf-examples.txt => examples.txt} (100%)
diff --git a/tools/perf/Documentation/perf-examples.txt b/tools/perf/Documentation/examples.txt
similarity index 100%
rename from tools/perf/Documentation/perf-examples.txt
rename to tools/perf/Documentation/examples.txt
From e1ac3614ff606ae03677f47459113f98a19af63c Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Fri, 14 Aug 2009 15:39:10 +1000
Subject: [PATCH 3/6] perf_counter: Check task on counter read IPI
In general, code in perf_counter.c that is called through an
IPI checks, for per-task counters, that the counter's task is
still the current task. This is to handle the race condition
where the cpu switches from the task we want to another task in
the interval between sending the IPI and the IPI arriving and
being handled on the target CPU.
For some reason, __perf_counter_read is missing this check, yet
there is no reason why the race condition can't occur. This
adds a check that the current task is the one we want. If it
isn't, we just return. In that case the counter->count value
should be up to date, since it will have been updated when the
counter was scheduled out, which must have happened since the
IPI was sent.
I don't have an example of an actual failure due to this race,
but it seems obvious that it could occur and we need to guard
against it.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <19076.63614.277861.368125@drongo.ozlabs.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
kernel/perf_counter.c | 11 +++++++++++
1 file changed, 11 insertions(+)
diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c
index 534e20d14d63..b8fe7397b902 100644
--- a/kernel/perf_counter.c
+++ b/kernel/perf_counter.c
@@ -1503,10 +1503,21 @@ static void perf_counter_enable_on_exec(struct task_struct *task)
*/
static void __perf_counter_read(void *info)
{
+ struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
struct perf_counter *counter = info;
struct perf_counter_context *ctx = counter->ctx;
unsigned long flags;
+ /*
+ * If this is a task context, we need to check whether it is
+ * the current task context of this cpu. If not it has been
+ * scheduled out before the smp call arrived. In that case
+ * counter->count would have been updated to a recent sample
+ * when the counter was scheduled out.
+ */
+ if (ctx->task && cpuctx->task_ctx != ctx)
+ return;
+
local_irq_save(flags);
if (ctx->is_active)
update_context_time(ctx);
From f738eb1b63edf664da1b4ac76895d988749b2f07 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@elte.hu>
Date: Tue, 18 Aug 2009 11:32:24 +0200
Subject: [PATCH 4/6] perf_counter: Fix the PARISC build
PARISC does not build:
/home/mingo/tip/kernel/perf_counter.c: In function 'perf_counter_index':
/home/mingo/tip/kernel/perf_counter.c:2016: error: 'PERF_COUNTER_INDEX_OFFSET' undeclared (first use in this function)
/home/mingo/tip/kernel/perf_counter.c:2016: error: (Each undeclared identifier is reported only once
/home/mingo/tip/kernel/perf_counter.c:2016: error: for each function it appears in.)
As PERF_COUNTER_INDEX_OFFSET is not defined.
Now, we could define it in the architecture - but lets also provide
a core default of 0 (which happens to be what all but one
architecture uses at the moment).
Architectures that need a different index offset should set this
value in their asm/perf_counter.h files.
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Helge Deller <deller@gmx.de>
Cc: linux-parisc@vger.kernel.org
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
kernel/perf_counter.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c
index b8fe7397b902..36f65e2b8b57 100644
--- a/kernel/perf_counter.c
+++ b/kernel/perf_counter.c
@@ -2019,6 +2019,10 @@ int perf_counter_task_disable(void)
return 0;
}
+#ifndef PERF_COUNTER_INDEX_OFFSET
+# define PERF_COUNTER_INDEX_OFFSET 0
+#endif
+
static int perf_counter_index(struct perf_counter *counter)
{
if (counter->state != PERF_COUNTER_STATE_ACTIVE)
From 15f3fa4e7f608c5ce19187b3b4a953222fdfa751 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@elte.hu>
Date: Tue, 18 Aug 2009 13:52:28 +0200
Subject: [PATCH 5/6] perf annotate: Fix segmentation fault
Linus reported this perf annotate segfault:
[torvalds@nehalem git]$ perf annotate unmap_vmas
Segmentation fault
#0 map__clone (self=<value optimized out>) at builtin-annotate.c:236
#1 thread__fork (self=<value optimized out>) at builtin-annotate.c:372
The bug here was that builtin-annotate.c was a copy of
builtin-report.c and a threading related fix to builtin-report.c
didnt get propagated to builtin-annotate.c ...
Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
tools/perf/builtin-annotate.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 1dba568e1941..343e7b14bf01 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -980,6 +980,13 @@ process_fork_event(event_t *event, unsigned long offset, unsigned long head)
(void *)(long)(event->header.size),
event->fork.pid, event->fork.ppid);
+ /*
+ * A thread clone will have the same PID for both
+ * parent and child.
+ */
+ if (thread == parent)
+ return 0;
+
if (!thread || !parent || thread__fork(thread, parent)) {
dprintf("problem processing PERF_EVENT_FORK, skipping event.\n");
return -1;
From b395cd8a74b4a8d943dd4b5585e676f62f7350b3 Mon Sep 17 00:00:00 2001
From: Kyle McMartin <kyle@redhat.com>
Date: Tue, 18 Aug 2009 12:41:25 -0400
Subject: [PATCH 6/6] perf tools: Make 'make html' work
pushd tools/perf/Documentation
make html
popd
is failing for me...
ASCIIDOC perf-annotate.html
ERROR: unsafe: include file: /etc/asciidoc/./stylesheets/xhtml11.css
ERROR: unsafe: include file:
/etc/asciidoc/./stylesheets/xhtml11-manpage.css
ERROR: unsafe: include file:
/etc/asciidoc/./stylesheets/xhtml11-quirks.css
make: *** [perf-annotate.html] Error 1
Apparently asciidoc "unsafe" is the default mode of operation
in practice.
https://bugzilla.redhat.com/show_bug.cgi?id=506953
Works tidily now.
Signed-off-by: Kyle McMartin <kyle@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <20090818164125.GM25206@bombadil.infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
tools/perf/Documentation/Makefile | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile
index 5457192e1b41..bdd3b7ecad0a 100644
--- a/tools/perf/Documentation/Makefile
+++ b/tools/perf/Documentation/Makefile
@@ -35,7 +35,7 @@ man7dir=$(mandir)/man7
# DESTDIR=
ASCIIDOC=asciidoc
-ASCIIDOC_EXTRA =
+ASCIIDOC_EXTRA = --unsafe
MANPAGE_XSL = manpage-normal.xsl
XMLTO_EXTRA =
INSTALL?=install