[[PATCH v6 08/10] Define PERF_PMU_TXN_READ interface

Sukadev Bhattiprolu sukadev at linux.vnet.ibm.com
Fri Sep 4 13:07:51 AEST 2015


Define a new PERF_PMU_TXN_READ interface to read a group of counters
at once.

        pmu->start_txn()                // Initialize before first event

        for each event in group
                pmu->read(event);       // Queue each event to be read

        rc = pmu->commit_txn()          // Read/update all queued counters

Note that we use this interface with all PMUs.  PMUs that implement this
interface use the ->read() operation to _queue_ the counters to be read
and use ->commit_txn() to actually read all the queued counters at once.

PMUs that don't implement PERF_PMU_TXN_READ ignore ->start_txn() and
->commit_txn() and continue to read counters one at a time.

Thanks to input from Peter Zijlstra.

Signed-off-by: Sukadev Bhattiprolu <sukadev at linux.vnet.ibm.com>
---
Changelog[v4]
        - [Peter Zijlstra] Add lockdep_assert_held() in perf_event_read_group().
          Make sure the entire transaction happens on the same CPU.
---
 include/linux/perf_event.h |    1 +
 kernel/events/core.c       |   24 +++++++++++++++++++-----
 2 files changed, 20 insertions(+), 5 deletions(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 4e8d780..b3435e7 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -169,6 +169,7 @@ struct perf_event;
 #define PERF_EVENT_TXN 0x1
 
 #define PERF_PMU_TXN_ADD  0x1		/* txn to add/schedule event on PMU */
+#define PERF_PMU_TXN_READ 0x2		/* txn to read event group from PMU */
 
 /**
  * pmu::capabilities flags
diff --git a/kernel/events/core.c b/kernel/events/core.c
index acdd8b5..9335bce 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3199,6 +3199,7 @@ static void __perf_event_read(void *info)
 	struct perf_event *sub, *event = data->event;
 	struct perf_event_context *ctx = event->ctx;
 	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
+	struct pmu *pmu = event->pmu;
 
 	/*
 	 * If this is a task context, we need to check whether it is
@@ -3217,18 +3218,31 @@ static void __perf_event_read(void *info)
 	}
 
 	update_event_times(event);
-	if (event->state == PERF_EVENT_STATE_ACTIVE)
-		event->pmu->read(event);
+	if (event->state != PERF_EVENT_STATE_ACTIVE)
+		goto unlock;
 
-	if (!data->group)
+	if (!data->group) {
+		pmu->read(event);
+		data->ret = 0;
 		goto unlock;
+	}
+
+	pmu->start_txn(pmu, PERF_PMU_TXN_READ);
+
+	pmu->read(event);
 
 	list_for_each_entry(sub, &event->sibling_list, group_entry) {
 		update_event_times(sub);
-		if (sub->state == PERF_EVENT_STATE_ACTIVE)
+		if (sub->state == PERF_EVENT_STATE_ACTIVE) {
+			/*
+			 * Use sibling's PMU rather than @event's since
+			 * sibling could be on different (eg: software) PMU.
+			 */
 			sub->pmu->read(sub);
+		}
 	}
-	data->ret = 0;
+
+	data->ret = pmu->commit_txn(pmu);
 
 unlock:
 	raw_spin_unlock(&ctx->lock);
-- 
1.7.9.5



More information about the Linuxppc-dev mailing list