[009/151] perf_event: Initialize data.period in perf_swevent_hrtimer()

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

------------------

From: Xiao Guangrong <xiaoguangrong@xxxxxxxxxxxxxx>

commit 59d069eb5ae9b033ed1c124c92e1532c4a958991 upstream.

In current code in perf_swevent_hrtimer(), data.period is not
initialized, The result is obvious wrong:

 # ./perf record -f -e cpu-clock make
 # ./perf report
 # Samples: 1740
 #
 # Overhead   Command                                   ......
 # ........  ........  ..........................................
 #
   1025422183050275328.00%        sh  libc-2.9.90.so ...
   1025422183050275328.00%      perl  libperl.so     ...
   1025422168240043264.00%      perl  [kernel]       ...
   1025422030011210752.00%      perl  [kernel]       ...

Signed-off-by: Xiao Guangrong <xiaoguangrong@xxxxxxxxxxxxxx>
Acked-by: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Frederic Weisbecker <fweisbec@xxxxxxxxx>
LKML-Reference: <4B14E220.2050107@xxxxxxxxxxxxxx>
Signed-off-by: Ingo Molnar <mingo@xxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxx>

---
 kernel/perf_event.c |    1 +
 1 file changed, 1 insertion(+)

--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -3949,6 +3949,7 @@ static enum hrtimer_restart perf_swevent
 	event->pmu->read(event);
 
 	data.addr = 0;
+	data.period = event->hw.last_period;
 	regs = get_irq_regs();
 	/*
 	 * In case we exclude kernel IPs or are somehow not in interrupt


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/