perf/aux: Allow using AUX data in perf samples

AUX data can be used to annotate perf events such as performance counters
or tracepoints/breakpoints by including it in sample records when
PERF_SAMPLE_AUX flag is set. Such samples would be instrumental in debugging
and profiling by providing, for example, a history of instruction flow
leading up to the event's overflow.

The implementation makes use of grouping an AUX event with all the events
that wish to take samples of the AUX data, such that the former is the
group leader. The samplees should also specify the desired size of the AUX
sample via attr.aux_sample_size.

AUX capable PMUs need to explicitly add support for sampling, because it
relies on a new callback to take a snapshot of the buffer without touching
the event states.

Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: adrian.hunter@intel.com
Cc: mathieu.poirier@linaro.org
Link: https://lkml.kernel.org/r/20191025140835.53665-2-alexander.shishkin@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 19 insertions, 0 deletions

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 011dcbdbccc2..34c7c6910026 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -249,6 +249,8 @@ struct perf_event;
 #define PERF_PMU_CAP_NO_EXCLUDE			0x80
 #define PERF_PMU_CAP_AUX_OUTPUT			0x100
 
+struct perf_output_handle;
+
 /**
  * struct pmu - generic performance monitoring unit
  */
@@ -433,6 +435,19 @@ struct pmu {
 	void (*free_aux)		(void *aux); /* optional */
 
 	/*
+	 * Take a snapshot of the AUX buffer without touching the event
+	 * state, so that preempting ->start()/->stop() callbacks does
+	 * not interfere with their logic. Called in PMI context.
+	 *
+	 * Returns the size of AUX data copied to the output handle.
+	 *
+	 * Optional.
+	 */
+	long (*snapshot_aux)		(struct perf_event *event,
+					 struct perf_output_handle *handle,
+					 unsigned long size);
+
+	/*
 	 * Validate address range filters: make sure the HW supports the
 	 * requested configuration and number of filters; return 0 if the
 	 * supplied filters are valid, -errno otherwise.
@@ -973,6 +988,7 @@ struct perf_sample_data {
 		u32	reserved;
 	}				cpu_entry;
 	struct perf_callchain_entry	*callchain;
+	u64				aux_size;
 
 	/*
 	 * regs_user may point to task_pt_regs or to regs_user_copy, depending
@@ -1362,6 +1378,9 @@ extern unsigned int perf_output_copy(struct perf_output_handle *handle,
 			     const void *buf, unsigned int len);
 extern unsigned int perf_output_skip(struct perf_output_handle *handle,
 				     unsigned int len);
+extern long perf_output_copy_aux(struct perf_output_handle *aux_handle,
+				 struct perf_output_handle *handle,
+				 unsigned long from, unsigned long to);
 extern int perf_swevent_get_recursion_context(void);
 extern void perf_swevent_put_recursion_context(int rctx);
 extern u64 perf_swevent_set_period(struct perf_event *event);