perf: Add wakeup watermark control to the AUX area

When AUX area gets a certain amount of new data, we want to wake up
userspace to collect it. This adds a new control to specify how much
data will cause a wakeup. This is then passed down to pmu drivers via
output handle's "wakeup" field, so that the driver can find the nearest
point where it can generate an interrupt.

We repurpose __reserved_2 in the event attribute for this, even though
it was never checked to be zero before, aux_watermark will only matter
for new AUX-aware code, so the old code should still be fine.

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/1421237903-181015-10-git-send-email-alexander.shishkin@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

include/uapi/linux/perf_event.h

@@ -261,6 +261,7 @@ enum perf_event_read_format {
 #define PERF_ATTR_SIZE_VER3	96	/* add: sample_regs_user */
 					/* add: sample_stack_user */
 #define PERF_ATTR_SIZE_VER4	104	/* add: sample_regs_intr */
+#define PERF_ATTR_SIZE_VER5	112	/* add: aux_watermark */
 
 /*
  * Hardware event_id to monitor via a performance monitoring event:
@@ -366,6 +367,12 @@ struct perf_event_attr {
 	 * See asm/perf_regs.h for details.
 	 */
 	__u64	sample_regs_intr;
+
+	/*
+	 * Wakeup watermark for AUX area
+	 */
+	__u32	aux_watermark;
+	__u32	__reserved_2;	/* align to __u64 */
 };
 
 #define perf_flags(attr)	(*(&(attr)->read_format + 1))

kernel/events/core.c

@@ -4677,7 +4677,8 @@ accounting:
 		perf_event_init_userpage(event);
 		perf_event_update_userpage(event);
 	} else {
-		ret = rb_alloc_aux(rb, event, vma->vm_pgoff, nr_pages, flags);
+		ret = rb_alloc_aux(rb, event, vma->vm_pgoff, nr_pages,
+				   event->attr.aux_watermark, flags);
 		if (!ret)
 			rb->aux_mmap_locked = extra;
 	}

kernel/events/internal.h

@@ -27,6 +27,7 @@ struct ring_buffer {
 	local_t				lost;		/* nr records lost   */
 
 	long				watermark;	/* wakeup watermark  */
+	long				aux_watermark;
 	/* poll crap */
 	spinlock_t			event_lock;
 	struct list_head		event_list;
@@ -38,6 +39,7 @@ struct ring_buffer {
 	/* AUX area */
 	local_t				aux_head;
 	local_t				aux_nest;
+	local_t				aux_wakeup;
 	unsigned long			aux_pgoff;
 	int				aux_nr_pages;
 	int				aux_overwrite;
@@ -57,7 +59,7 @@ extern struct ring_buffer *
 rb_alloc(int nr_pages, long watermark, int cpu, int flags);
 extern void perf_event_wakeup(struct perf_event *event);
 extern int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event,
-			pgoff_t pgoff, int nr_pages, int flags);
+			pgoff_t pgoff, int nr_pages, long watermark, int flags);
 extern void rb_free_aux(struct ring_buffer *rb);
 extern struct ring_buffer *ring_buffer_get(struct perf_event *event);
 extern void ring_buffer_put(struct ring_buffer *rb);

kernel/events/ring_buffer.c

@@ -296,6 +296,7 @@ void *perf_aux_output_begin(struct perf_output_handle *handle,
 	 */
 	if (!rb->aux_overwrite) {
 		aux_tail = ACCESS_ONCE(rb->user_page->aux_tail);
+		handle->wakeup = local_read(&rb->aux_wakeup) + rb->aux_watermark;
 		if (aux_head - aux_tail < perf_aux_size(rb))
 			handle->size = CIRC_SPACE(aux_head, aux_tail, perf_aux_size(rb));
 
@@ -359,9 +360,12 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size,
 		perf_event_aux_event(handle->event, aux_head, size, flags);
 	}
 
-	rb->user_page->aux_head = local_read(&rb->aux_head);
+	aux_head = rb->user_page->aux_head = local_read(&rb->aux_head);
 
-	perf_output_wakeup(handle);
+	if (aux_head - local_read(&rb->aux_wakeup) >= rb->aux_watermark) {
+		perf_output_wakeup(handle);
+		local_add(rb->aux_watermark, &rb->aux_wakeup);
+	}
 	handle->event = NULL;
 
 	local_set(&rb->aux_nest, 0);
@@ -383,6 +387,14 @@ int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size)
 
 	local_add(size, &rb->aux_head);
 
+	aux_head = rb->user_page->aux_head = local_read(&rb->aux_head);
+	if (aux_head - local_read(&rb->aux_wakeup) >= rb->aux_watermark) {
+		perf_output_wakeup(handle);
+		local_add(rb->aux_watermark, &rb->aux_wakeup);
+		handle->wakeup = local_read(&rb->aux_wakeup) +
+				 rb->aux_watermark;
+	}
+
 	handle->head = aux_head;
 	handle->size -= size;
 
@@ -433,7 +445,7 @@ static void rb_free_aux_page(struct ring_buffer *rb, int idx)
 }
 
 int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event,
-		 pgoff_t pgoff, int nr_pages, int flags)
+		 pgoff_t pgoff, int nr_pages, long watermark, int flags)
 {
 	bool overwrite = !(flags & RING_BUFFER_WRITABLE);
 	int node = (event->cpu == -1) ? -1 : cpu_to_node(event->cpu);
@@ -497,6 +509,10 @@ int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event,
 	atomic_set(&rb->aux_refcount, 1);
 
 	rb->aux_overwrite = overwrite;
+	rb->aux_watermark = watermark;
+
+	if (!rb->aux_watermark && !rb->aux_overwrite)
+		rb->aux_watermark = nr_pages << (PAGE_SHIFT - 1);
 
 out:
 	if (!ret)