Patchwork [v2] perf/Power: PERF_EVENT_IOC_ENABLE does not reenable event

login
register
mail settings
Submitter sukadev@linux.vnet.ibm.com
Date Jan. 24, 2013, 11:25 p.m.
Message ID <20130124232523.GA12162@us.ibm.com>
Download mbox | patch
Permalink /patch/215509/
State Accepted, archived
Commit f53d168c025f27d64417a56bf129dbb39d2e1189
Headers show

Comments

sukadev@linux.vnet.ibm.com - Jan. 24, 2013, 11:25 p.m.
perf/Power: PERF_EVENT_IOC_ENABLE does not reenable event

If we disable a perf event because we exceeded the specified ->event_limit,
power_pmu_stop() sets the PERF_HES_STOPPED flag on the event.

If the application then re-enables the event using PERF_EVENT_IOC_ENABLE
ioctl, we don't ever clear this STOPPED flag. Consequently, the user space
is never notified of the event.

Following message has more background and test case.

    http://lists.eecs.utk.edu/pipermail/ptools-perfapi/2012-October/002528.html

Used the following test cases to verify that this patch works on latest PAPI.

	$ papi.git/src/ctests/nonthread PAPI_TOT_CYC@5000000

	$ papi.git/src/ctests/overflow_single_event

Changelog[v2]:
	- [Paul Mackerras] Also clear PERF_HES_UPTODATE flag since we are
	  restarting the event; cleanup comments and patch description.

Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
---
 arch/powerpc/perf/core-book3s.c |    8 ++++++++
 1 files changed, 8 insertions(+), 0 deletions(-)

Patch

diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index aa2465e..4b1e584 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -880,8 +880,16 @@  static int power_pmu_add(struct perf_event *event, int ef_flags)
 	cpuhw->events[n0] = event->hw.config;
 	cpuhw->flags[n0] = event->hw.event_base;
 
+	/*
+	 * This event may have been disabled/stopped in record_and_restart()
+	 * because we exceeded the ->event_limit. If re-starting the event,
+	 * clear the ->hw.state (STOPPED and UPTODATE flags), so the user
+	 * notification is re-enabled.
+	 */
 	if (!(ef_flags & PERF_EF_START))
 		event->hw.state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
+	else
+		event->hw.state = 0;
 
 	/*
 	 * If group events scheduling transaction was started,