perf/ring_buffer: Introduce new ioctl options to pause and resume the ring-buffer

Add new ioctl() to pause/resume ring-buffer output.

In some situations we want to read from the ring-buffer only when we
ensure nothing can write to the ring-buffer during reading. Without
this patch we have to turn off all events attached to this ring-buffer
to achieve this.

This patch is a prerequisite to enable overwrite support for the
perf ring-buffer support. Following commits will introduce new methods
support reading from overwrite ring buffer. Before reading, caller
must ensure the ring buffer is frozen, or the reading is unreliable.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: <pi3orama@163.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: Zefan Li <lizefan@huawei.com>
Link: http://lkml.kernel.org/r/1459147292-239310-2-git-send-email-wangnan0@huawei.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

4 files changed, 34 insertions, 1 deletions

diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 1afe9623c1a7..a3c19034d5f8 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -401,6 +401,7 @@ struct perf_event_attr {
 #define PERF_EVENT_IOC_SET_FILTER	_IOW('$', 6, char *)
 #define PERF_EVENT_IOC_ID		_IOR('$', 7, __u64 *)
 #define PERF_EVENT_IOC_SET_BPF		_IOW('$', 8, __u32)
+#define PERF_EVENT_IOC_PAUSE_OUTPUT	_IOW('$', 9, __u32)
 
 enum perf_event_ioc_flags {
 	PERF_IOC_FLAG_GROUP		= 1U << 0,
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 243df4b62870..51386e84293e 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4379,6 +4379,19 @@ static long _perf_ioctl(struct perf_event *event, unsigned int cmd, unsigned lon
 	case PERF_EVENT_IOC_SET_BPF:
 		return perf_event_set_bpf_prog(event, arg);
 
+	case PERF_EVENT_IOC_PAUSE_OUTPUT: {
+		struct ring_buffer *rb;
+
+		rcu_read_lock();
+		rb = rcu_dereference(event->rb);
+		if (!rb || !rb->nr_pages) {
+			rcu_read_unlock();
+			return -EINVAL;
+		}
+		rb_toggle_paused(rb, !!arg);
+		rcu_read_unlock();
+		return 0;
+	}
 	default:
 		return -ENOTTY;
 	}
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index 2b229fdcfc09..2d67327d9ad9 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -17,6 +17,7 @@ struct ring_buffer {
 #endif
 	int				nr_pages;	/* nr of data pages  */
 	int				overwrite;	/* can overwrite itself */
+	int				paused;		/* can write into ring buffer */
 
 	atomic_t			poll;		/* POLL_ for wakeups */
 
@@ -64,6 +65,14 @@ static inline void rb_free_rcu(struct rcu_head *rcu_head)
 	rb_free(rb);
 }
 
+static inline void rb_toggle_paused(struct ring_buffer *rb, bool pause)
+{
+	if (!pause && rb->nr_pages)
+		rb->paused = 0;
+	else
+		rb->paused = 1;
+}
+
 extern struct ring_buffer *
 rb_alloc(int nr_pages, long watermark, int cpu, int flags);
 extern void perf_event_wakeup(struct perf_event *event);
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 0ed4555309bd..72d8127bb8fd 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -125,8 +125,11 @@ int perf_output_begin(struct perf_output_handle *handle,
 	if (unlikely(!rb))
 		goto out;
 
-	if (unlikely(!rb->nr_pages))
+	if (unlikely(rb->paused)) {
+		if (rb->nr_pages)
+			local_inc(&rb->lost);
 		goto out;
+	}
 
 	handle->rb    = rb;
 	handle->event = event;
@@ -241,6 +244,13 @@ ring_buffer_init(struct ring_buffer *rb, long watermark, int flags)
 
 	INIT_LIST_HEAD(&rb->event_list);
 	spin_lock_init(&rb->event_lock);
+
+	/*
+	 * perf_output_begin() only checks rb->paused, therefore
+	 * rb->paused must be true if we have no pages for output.
+	 */
+	if (!rb->nr_pages)
+		rb->paused = 1;
 }
 
 /*