@@ -602,6 +602,8 @@ struct perf_sample_data {
* Transaction flags for abort events:
*/
u64 txn;
+ /* Raw monotonic timestamp, for userspace time correlation */
+ u64 clock_raw_monotonic;
};
static inline void perf_sample_data_init(struct perf_sample_data *data,
@@ -137,8 +137,9 @@ enum perf_event_sample_format {
PERF_SAMPLE_DATA_SRC = 1U << 15,
PERF_SAMPLE_IDENTIFIER = 1U << 16,
PERF_SAMPLE_TRANSACTION = 1U << 17,
+ PERF_SAMPLE_CLOCK_RAW_MONOTONIC = 1U << 18,
- PERF_SAMPLE_MAX = 1U << 18, /* non-ABI */
+ PERF_SAMPLE_MAX = 1U << 19, /* non-ABI */
};
/*
@@ -686,6 +687,7 @@ enum perf_event_type {
* { u64 weight; } && PERF_SAMPLE_WEIGHT
* { u64 data_src; } && PERF_SAMPLE_DATA_SRC
* { u64 transaction; } && PERF_SAMPLE_TRANSACTION
+ * { u64 clock_raw_monotonic; } && PERF_SAMPLE_CLOCK_RAW_MONOTONIC
* };
*/
PERF_RECORD_SAMPLE = 9,
@@ -1216,6 +1216,9 @@ static void perf_event__header_size(struct perf_event *event)
if (sample_type & PERF_SAMPLE_TRANSACTION)
size += sizeof(data->txn);
+ if (sample_type & PERF_SAMPLE_CLOCK_RAW_MONOTONIC)
+ size += sizeof(data->clock_raw_monotonic);
+
event->header_size = size;
}
@@ -4456,6 +4459,12 @@ static void __perf_event_header__init_id(struct perf_event_header *header,
data->cpu_entry.cpu = raw_smp_processor_id();
data->cpu_entry.reserved = 0;
}
+
+ if (sample_type & PERF_SAMPLE_CLOCK_RAW_MONOTONIC) {
+ struct timespec now;
+ getrawmonotonic(&now);
+ data->clock_raw_monotonic = timespec_to_ns(&now);
+ }
}
void perf_event_header__init_id(struct perf_event_header *header,
@@ -4714,6 +4723,9 @@ void perf_output_sample(struct perf_output_handle *handle,
if (sample_type & PERF_SAMPLE_TRANSACTION)
perf_output_put(handle, data->txn);
+ if (sample_type & PERF_SAMPLE_CLOCK_RAW_MONOTONIC)
+ perf_output_put(handle, data->clock_raw_monotonic);
+
if (!event->attr.watermark) {
int wakeup_events = event->attr.wakeup_events;
This patch adds an option to sample raw monotonic clock value with any perf event, with the the aim of allowing time correlation between data coming from perf and additional performance-related information generated in userspace. In order to correlate timestamps in perf data stream with events happening in userspace (be it JITed debug symbols or hwmon-originating environment data), user requests a more or less periodic event (sched_switch trace event of a hrtimer-based cpu-clock being the most obvious examples) with PERF_SAMPLE_TIME *and* PERF_SAMPLE_CLOCK_RAW_MONOTONIC and stamps user-originating data with values obtained from clock_gettime(CLOCK_MONOTONIC_RAW). Then, during analysis, one looks at the perf events immediately preceding and following (in terms of the clock_raw_monotonic sample) the userspace event and does simple linear approximation to get the equivalent perf time. perf event user event -----O--------------+-------------O------> t_mono : | : : V : -----O----------------------------O------> t_perf Signed-off-by: Pawel Moll <pawel.moll@arm.com> --- include/linux/perf_event.h | 2 ++ include/uapi/linux/perf_event.h | 4 +++- kernel/events/core.c | 12 ++++++++++++ 3 files changed, 17 insertions(+), 1 deletion(-)