perf: Support overwrite mode for the AUX area (2023a0d2) · Commits · 戴 / test

This adds support for overwrite mode in the AUX area, which means "keep collecting data till you're stopped", turning AUX area into a circular buffer, where new data overwrites old data. It does not depend on data buffer's overwrite mode, so that it doesn't lose sideband data that is instrumental for processing AUX data. Overwrite mode is enabled at mapping AUX area read only. Even though aux_tail in the buffer's user page might be user writable, it will be ignored in this mode. A PERF_RECORD_AUX with PERF_AUX_FLAG_OVERWRITE set is written to the perf data stream every time an event writes new data to the AUX area. The pmu driver might not be able to infer the exact beginning of the new data in each snapshot, some drivers will only provide the tail, which is aux_offset + aux_size in the AUX record. Consumer has to be able to tell the new data from the old one, for example, by means of time stamps if such are provided in the trace. Consumer is also responsible for disabling any events that might write to the AUX area (thus potentially racing with the consumer) before collecting the data. Signed-off-by:

Alexander Shishkin <alexander.shishkin@linux.intel.com> Signed-off-by:

Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Kaixu Xia <kaixu.xia@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Robert Richter <rric@kernel.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: acme@infradead.org Cc: adrian.hunter@intel.com Cc: kan.liang@intel.com Cc: markus.t.metzger@intel.com Cc: mathieu.poirier@linaro.org Link: http://lkml.kernel.org/r/1421237903-181015-9-git-send-email-alexander.shishkin@linux.intel.com Signed-off-by:

Ingo Molnar <mingo@kernel.org>

include/uapi/linux/perf_event.h

+1 −0

Original line number	Diff line number	Diff line
		@@ -803,6 +803,7 @@ enum perf_callchain_context {
		* PERF_RECORD_AUX::flags bits
		*/
		#define PERF_AUX_FLAG_TRUNCATED 0x01 /* record was truncated to fit */
		#define PERF_AUX_FLAG_OVERWRITE 0x02 /* snapshot from overwrite mode */

		#define PERF_FLAG_FD_NO_GROUP (1UL << 0)
		#define PERF_FLAG_FD_OUTPUT (1UL << 1)

kernel/events/internal.h

+1 −0

Original line number	Diff line number	Diff line
		@@ -40,6 +40,7 @@ struct ring_buffer {
		local_t aux_nest;
		unsigned long aux_pgoff;
		int aux_nr_pages;
		int aux_overwrite;
		atomic_t aux_mmap_count;
		unsigned long aux_mmap_locked;
		void (free_aux)(void );

kernel/events/ring_buffer.c

+33 −15

Original line number	Diff line number	Diff line
		@@ -283,15 +283,21 @@ void perf_aux_output_begin(struct perf_output_handle handle,
		goto err_put;

		aux_head = local_read(&rb->aux_head);
		aux_tail = ACCESS_ONCE(rb->user_page->aux_tail);

		handle->rb = rb;
		handle->event = event;
		handle->head = aux_head;
		handle->size = 0;

		/*
		* In overwrite mode, AUX data stores do not depend on aux_tail,
		* therefore (A) control dependency barrier does not exist. The
		* (B) <-> (C) ordering is still observed by the pmu driver.
		*/
		if (!rb->aux_overwrite) {
		aux_tail = ACCESS_ONCE(rb->user_page->aux_tail);
		if (aux_head - aux_tail < perf_aux_size(rb))
		handle->size = CIRC_SPACE(aux_head, aux_tail, perf_aux_size(rb));
		else
		handle->size = 0;

		/*
		* handle->size computation depends on aux_tail load; this forms a
		@@ -304,6 +310,7 @@ void perf_aux_output_begin(struct perf_output_handle handle,
		local_set(&rb->aux_nest, 0);
		goto err_put;
		}
		}

		return handle->rb->aux_priv;

		@@ -327,13 +334,22 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size,
		bool truncated)
		{
		struct ring_buffer *rb = handle->rb;
		unsigned long aux_head = local_read(&rb->aux_head);
		unsigned long aux_head;
		u64 flags = 0;

		if (truncated)
		flags \|= PERF_AUX_FLAG_TRUNCATED;

		/* in overwrite mode, driver provides aux_head via handle */
		if (rb->aux_overwrite) {
		flags \|= PERF_AUX_FLAG_OVERWRITE;

		aux_head = handle->head;
		local_set(&rb->aux_head, aux_head);
		} else {
		aux_head = local_read(&rb->aux_head);
		local_add(size, &rb->aux_head);
		}

		if (size \|\| flags) {
		/*
		@@ -480,6 +496,8 @@ int rb_alloc_aux(struct ring_buffer rb, struct perf_event event,
		*/
		atomic_set(&rb->aux_refcount, 1);

		rb->aux_overwrite = overwrite;

		out:
		if (!ret)
		rb->aux_pgoff = pgoff;

Admin message