@@ -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,
@@ -4341,6 +4341,19 @@ 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) {
+ rcu_read_unlock();
+ return -EINVAL;
+ }
+ rb_toggle_paused(rb, !!arg);
+ rcu_read_unlock();
+ return 0;
+ }
default:
return -ENOTTY;
}
@@ -18,6 +18,7 @@ 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 */
@@ -65,6 +66,16 @@ 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);
@@ -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;
@@ -244,6 +247,8 @@ ring_buffer_init(struct ring_buffer *rb, long watermark, int flags)
INIT_LIST_HEAD(&rb->event_list);
spin_lock_init(&rb->event_lock);
init_irq_work(&rb->irq_work, rb_irq_work);
+
+ rb->paused = rb->nr_pages ? 0 : 1;
}
static void ring_buffer_put_async(struct ring_buffer *rb)
Add new ioctl() to pause/resume ring-buffer output. In some situations we want to read from 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 for supporting overwrite ring buffer. 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> Cc: He Kuang <hekuang@huawei.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com --- include/uapi/linux/perf_event.h | 1 + kernel/events/core.c | 13 +++++++++++++ kernel/events/internal.h | 11 +++++++++++ kernel/events/ring_buffer.c | 7 ++++++- 4 files changed, 31 insertions(+), 1 deletion(-) -- 1.8.3.4