In perf_event_attr a new bit 'write_backward' is appended to indicate
this event should write ring buffer from its end to beginning.
In perf_output_begin(), prepare ring buffer according this bit.
This patch introduces small overhead into perf_output_begin():
an extra memory read and a conditional branch. Further patch can remove
this overhead by using custom output handler.
Signed-off-by: Wang Nan <wangn...@huawei.com>
Cc: He Kuang <heku...@huawei.com>
Cc: Alexei Starovoitov <a...@kernel.org>
Cc: Arnaldo Carvalho de Melo <a...@redhat.com>
Cc: Brendan Gregg <brendan.d.gr...@gmail.com>
Cc: Ingo Molnar <mi...@redhat.com>
Cc: Jiri Olsa <jo...@kernel.org>
Cc: Masami Hiramatsu <masami.hiramatsu...@hitachi.com>
Cc: Namhyung Kim <namhy...@kernel.org>
Cc: Peter Zijlstra <pet...@infradead.org>
Cc: Zefan Li <lize...@huawei.com>
Cc: pi3or...@163.com
---
include/linux/perf_event.h | 5 +++++
include/uapi/linux/perf_event.h | 3 ++-
kernel/events/core.c | 7 +++++++
kernel/events/ring_buffer.c | 2 ++
4 files changed, 16 insertions(+), 1 deletion(-)
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index a9d8cab..88e2b47 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1031,6 +1031,11 @@ static inline bool has_aux(struct perf_event *event)
return event->pmu->setup_aux;
}
+static inline bool is_write_backward(struct perf_event *event)
+{
+ return !!event->attr.write_backward;
+}
+
extern int perf_output_begin(struct perf_output_handle *handle,
struct perf_event *event, unsigned int size);
extern void perf_output_end(struct perf_output_handle *handle);
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index a3c1903..43fc8d2 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -340,7 +340,8 @@ struct perf_event_attr {
comm_exec : 1, /* flag comm events that
are due to an exec */
use_clockid : 1, /* use @clockid for time
fields */
context_switch : 1, /* context switch data */
- __reserved_1 : 37;
+ write_backward : 1, /* Write ring buffer from
end to beginning */
+ __reserved_1 : 36;
union {
__u32 wakeup_events; /* wakeup every n events */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index ed94c91..513b556 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -8196,6 +8196,13 @@ perf_event_set_output(struct perf_event *event, struct
perf_event *output_event)
goto out;
/*
+ * Either writing ring buffer from beginning or from end.
+ * Mixing is not allowed.
+ */
+ if (is_write_backward(output_event) != is_write_backward(event))
+ goto out;
+
+ /*
* If both events generate aux data, they must be on the same PMU
*/
if (has_aux(event) && has_aux(output_event) &&
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 37c11c6..80b1fa7 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -233,6 +233,8 @@ out:
int perf_output_begin(struct perf_output_handle *handle,
struct perf_event *event, unsigned int size)
{
+ if (unlikely(is_write_backward(event)))
+ return __perf_output_begin(handle, event, size, true);
return __perf_output_begin(handle, event, size, false);
}
--
1.8.3.4
