[PATCH 5.9 18/75] ring-buffer: Set the right timestamp in the slow path of __rb_reserve_next()

From: Greg Kroah-Hartman
Date: Thu Dec 10 2020 - 11:48:07 EST


From: Andrea Righi <andrea.righi@xxxxxxxxxxxxx>

commit 8785f51a17083eee7c37606079c6447afc6ba102 upstream.

In the slow path of __rb_reserve_next() a nested event(s) can happen
between evaluating the timestamp delta of the current event and updating
write_stamp via local_cmpxchg(); in this case the delta is not valid
anymore and it should be set to 0 (same timestamp as the interrupting
event), since the event that we are currently processing is not the last
event in the buffer.

Link: https://lkml.kernel.org/r/X8IVJcp1gRE+FJCJ@xps-13-7390

Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Masami Hiramatsu <mhiramat@xxxxxxxxxx>
Cc: stable@xxxxxxxxxxxxxxx
Link: https://lwn.net/Articles/831207
Fixes: a389d86f7fd0 ("ring-buffer: Have nested events still record running time stamp")
Signed-off-by: Andrea Righi <andrea.righi@xxxxxxxxxxxxx>
Signed-off-by: Steven Rostedt (VMware) <rostedt@xxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>

---
kernel/trace/ring_buffer.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)

--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -3287,11 +3287,11 @@ __rb_reserve_next(struct ring_buffer_per
ts = rb_time_stamp(cpu_buffer->buffer);
barrier();
/*E*/ if (write == (local_read(&tail_page->write) & RB_WRITE_MASK) &&
- info->after < ts) {
+ info->after < ts &&
+ rb_time_cmpxchg(&cpu_buffer->write_stamp,
+ info->after, ts)) {
/* Nothing came after this event between C and E */
info->delta = ts - info->after;
- (void)rb_time_cmpxchg(&cpu_buffer->write_stamp,
- info->after, ts);
info->ts = ts;
} else {
/*