summaryrefslogtreecommitdiff
path: root/arch/powerpc
diff options
context:
space:
mode:
authorsukadev@linux.vnet.ibm.com <sukadev@linux.vnet.ibm.com>2013-01-24 17:25:23 +0400
committerBenjamin Herrenschmidt <benh@kernel.crashing.org>2013-01-29 04:35:07 +0400
commitf53d168c025f27d64417a56bf129dbb39d2e1189 (patch)
tree094e0912b1fa861bc7eca5958ded86b437fa9164 /arch/powerpc
parent94c95cfbfe784eca5f4b96955e41bda1318605bc (diff)
downloadlinux-f53d168c025f27d64417a56bf129dbb39d2e1189.tar.xz
perf/Power: PERF_EVENT_IOC_ENABLE does not reenable event
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> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Diffstat (limited to 'arch/powerpc')
-rw-r--r--arch/powerpc/perf/core-book3s.c8
1 files changed, 8 insertions, 0 deletions
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 89bd59365c07..069f92b31992 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,