lkml.org 
[lkml]   [2009]   [May]   [8]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Date
From
Subject[tip:perfcounters/core] perf_counter: add PERF_RECORD_CONFIG
Commit-ID:  a85f61abe11a46553c4562e74edb27ebc782aeb7
Gitweb: http://git.kernel.org/tip/a85f61abe11a46553c4562e74edb27ebc782aeb7
Author: Peter Zijlstra <a.p.zijlstra@chello.nl>
AuthorDate: Fri, 8 May 2009 18:52:23 +0200
Committer: Ingo Molnar <mingo@elte.hu>
CommitDate: Fri, 8 May 2009 20:36:58 +0200

perf_counter: add PERF_RECORD_CONFIG

Much like CONFIG_RECORD_GROUP records the hw_event.config to
identify the values, allow to record this for all counters.

[ Impact: extend perfcounter output record format ]

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
LKML-Reference: <20090508170028.923228280@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>


---
include/linux/perf_counter.h | 2 ++
kernel/perf_counter.c | 8 ++++++++
2 files changed, 10 insertions(+), 0 deletions(-)

diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h
index 88f863e..0e6303d 100644
--- a/include/linux/perf_counter.h
+++ b/include/linux/perf_counter.h
@@ -104,6 +104,7 @@ enum perf_counter_record_format {
PERF_RECORD_ADDR = 1U << 3,
PERF_RECORD_GROUP = 1U << 4,
PERF_RECORD_CALLCHAIN = 1U << 5,
+ PERF_RECORD_CONFIG = 1U << 6,
};

/*
@@ -258,6 +259,7 @@ enum perf_event_type {
* { u32 pid, tid; } && PERF_RECORD_TID
* { u64 time; } && PERF_RECORD_TIME
* { u64 addr; } && PERF_RECORD_ADDR
+ * { u64 config; } && PERF_RECORD_CONFIG
*
* { u64 nr;
* { u64 event, val; } cnt[nr]; } && PERF_RECORD_GROUP
diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c
index f4883f1..c615f52 100644
--- a/kernel/perf_counter.c
+++ b/kernel/perf_counter.c
@@ -1994,6 +1994,11 @@ static void perf_counter_output(struct perf_counter *counter,
header.size += sizeof(u64);
}

+ if (record_type & PERF_RECORD_CONFIG) {
+ header.type |= PERF_RECORD_CONFIG;
+ header.size += sizeof(u64);
+ }
+
if (record_type & PERF_RECORD_GROUP) {
header.type |= PERF_RECORD_GROUP;
header.size += sizeof(u64) +
@@ -2029,6 +2034,9 @@ static void perf_counter_output(struct perf_counter *counter,
if (record_type & PERF_RECORD_ADDR)
perf_output_put(&handle, addr);

+ if (record_type & PERF_RECORD_CONFIG)
+ perf_output_put(&handle, counter->hw_event.config);
+
/*
* XXX PERF_RECORD_GROUP vs inherited counters seems difficult.
*/

\
 
 \ /
  Last update: 2009-05-08 20:45    [W:0.146 / U:0.368 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site