Define a new PERF_PMU_TXN_READ interface to read a group of counters
at once. Note that we use this interface with all PMUs.
PMUs that implement this interface will queue the counters to be read
in ->read() and read them all at once in ->commit_txn().
PMUs that don't implement PERF_PMU_TXN_READ will continue to read one
counter at a time and ignore the ->start_txn() and ->commit_txn().
Thanks to input from Peter Zijlstra.
Signed-off-by: Sukadev Bhattiprolu <suka...@linux.vnet.ibm.com>
---
include/linux/perf_event.h | 1 +
kernel/events/core.c | 33 +++++++++++++++++++++++++++++++--
2 files changed, 32 insertions(+), 2 deletions(-)
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index e684c6b..3e46a07 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -244,6 +244,7 @@ struct pmu {
* Optional.
*/
#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 */
void (*start_txn) (struct pmu *pmu, int flags);
/*
* If ->start_txn() disabled the ->add() schedulability test
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1ac99d1..a001582 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3644,6 +3644,33 @@ static void orphans_remove_work(struct work_struct *work)
put_ctx(ctx);
}
+/*
+ * Use the transaction interface to read the group of events in @leader.
+ * PMUs like the 24x7 counters in Power, can use this to queue the events
+ * in the ->read() operation and perform the actual read in ->commit_txn.
+ *
+ * Other PMUs can ignore the ->start_txn and ->commit_txn and read each
+ * PMU directly in the ->read() operation.
+ */
+static int perf_event_read_txn(struct perf_event *leader)
+{
+ int ret;
+ struct perf_event *sub;
+ struct pmu *pmu;
+
+ pmu = leader->pmu;
+
+ pmu->start_txn(pmu, PERF_PMU_TXN_READ);
+
+ perf_event_read(leader);
+ list_for_each_entry(sub, &leader->sibling_list, group_entry)
+ perf_event_read(sub);
+
+ ret = pmu->commit_txn(pmu, PERF_PMU_TXN_READ);
+
+ return ret;
+}
+
u64 perf_event_compute_values(struct perf_event *event, u64 *enabled,
u64 *running)
{
@@ -3685,7 +3712,10 @@ static int perf_event_read_group(struct perf_event
*event,
lockdep_assert_held(&ctx->mutex);
- perf_event_read(leader);
+ ret = perf_event_read_txn(leader);
+ if (ret)
+ return ret;
+
count = perf_event_compute_values(leader, &enabled, &running);
values[n++] = 1 + leader->nr_siblings;
@@ -3707,7 +3737,6 @@ static int perf_event_read_group(struct perf_event *event,
list_for_each_entry(sub, &leader->sibling_list, group_entry) {
n = 0;
- perf_event_read(sub);
values[n++] = perf_event_compute_values(sub, &enabled,
&running);
if (read_format & PERF_FORMAT_ID)
values[n++] = primary_event_id(sub);
--
1.7.9.5
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
