Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Sender: Namhyung Kim <namhyung@gmail.com>
From:   Namhyung Kim <namhyung@kernel.org>
To:     Arnaldo Carvalho de Melo <acme@kernel.org>,
        Jiri Olsa <jolsa@redhat.com>,
        Peter Zijlstra <peterz@infradead.org>
Cc:     Ingo Molnar <mingo@kernel.org>,
        Mark Rutland <mark.rutland@arm.com>,
        Alexander Shishkin <alexander.shishkin@linux.intel.com>,
        LKML <linux-kernel@vger.kernel.org>,
        Stephane Eranian <eranian@google.com>,
        Andi Kleen <ak@linux.intel.com>,
        Ian Rogers <irogers@google.com>,
        Alexey Alexandrov <aalexand@google.com>
Subject: [PATCH] perf/core: Emit PERF_RECORD_LOST for pinned events
Date:   Mon, 18 Jan 2021 12:43:23 +0900
Message-Id: <20210118034323.427029-1-namhyung@kernel.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

As of now we silently ignore pinned events when it's failed to be
scheduled and make it error state not try to schedule it again.
That means we won't get any samples for the event.

But there's no way for users to notice and respond to it.  Let's
emit a lost event with a new misc bit to indicate this situation.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 include/uapi/linux/perf_event.h |  2 ++
 kernel/events/core.c            | 36 +++++++++++++++++++++++++++++++++
 2 files changed, 38 insertions(+)

diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index b15e3447cd9f..3c0e115dd8b7 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -679,11 +679,13 @@ struct perf_event_mmap_page {
  *   PERF_RECORD_MISC_COMM_EXEC  - PERF_RECORD_COMM event
  *   PERF_RECORD_MISC_FORK_EXEC  - PERF_RECORD_FORK event (perf internal)
  *   PERF_RECORD_MISC_SWITCH_OUT - PERF_RECORD_SWITCH* events
+ *   PERF_RECORD_MISC_LOST_PINNED- PERF_RECORD_LOST event
  */
 #define PERF_RECORD_MISC_MMAP_DATA		(1 << 13)
 #define PERF_RECORD_MISC_COMM_EXEC		(1 << 13)
 #define PERF_RECORD_MISC_FORK_EXEC		(1 << 13)
 #define PERF_RECORD_MISC_SWITCH_OUT		(1 << 13)
+#define PERF_RECORD_MISC_LOST_PINNED		(1 << 13)
 /*
  * These PERF_RECORD_MISC_* flags below are safely reused
  * for the following events:
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 55d18791a72d..523927575434 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3654,6 +3654,8 @@ static noinline int visit_groups_merge(struct perf_cpu_context *cpuctx,
 	return 0;
 }
 
+static void perf_log_lost_event(struct perf_event *event);
+
 static int merge_sched_in(struct perf_event *event, void *data)
 {
 	struct perf_event_context *ctx = event->ctx;
@@ -3675,6 +3677,7 @@ static int merge_sched_in(struct perf_event *event, void *data)
 		if (event->attr.pinned) {
 			perf_cgroup_event_disable(event, ctx);
 			perf_event_set_state(event, PERF_EVENT_STATE_ERROR);
+			perf_log_lost_event(event);
 		}
 
 		*can_add_hw = 0;
@@ -8414,6 +8417,39 @@ void perf_event_aux_event(struct perf_event *event, unsigned long head,
 	perf_output_end(&handle);
 }
 
+/*
+ * failed/errored events logging
+ */
+static void perf_log_lost_event(struct perf_event *event)
+{
+	struct perf_output_handle handle;
+	struct perf_sample_data sample;
+	int ret;
+	struct {
+		struct perf_event_header header;
+		u64			 id;
+		u64			 lost;
+	} lost_event = {
+		.header = {
+			.type = PERF_RECORD_LOST,
+			.misc = PERF_RECORD_MISC_LOST_PINNED,
+			.size = sizeof(lost_event),
+		},
+		.id		= event->id,
+	};
+
+	perf_event_header__init_id(&lost_event.header, &sample, event);
+
+	ret = perf_output_begin(&handle, &sample, event,
+				lost_event.header.size);
+	if (ret)
+		return;
+
+	perf_output_put(&handle, lost_event);
+	perf_event__output_id_sample(event, &handle, &sample);
+	perf_output_end(&handle);
+}
+
 /*
  * Lost/dropped samples logging
  */
-- 
2.30.0.284.gd98b1dd5eaa7-goog