AcoSail/kernel_optimize_test
8
0
Fork 0
forked from luck/tmp_suning_uos_patched
Code Pull Requests Activity

perf: Always wake the parent event

Browse Source 
[ Upstream commit 961c39121759ad09a89598ec4ccdd34ae0468a19 ]

When using per-process mode and event inheritance is set to true,
forked processes will create a new perf events via inherit_event() ->
perf_event_alloc(). But these events will not have ring buffers
assigned to them. Any call to wakeup will be dropped if it's called on
an event with no ring buffer assigned because that's the object that
holds the wakeup list.

If the child event is disabled due to a call to
perf_aux_output_begin() or perf_aux_output_end(), the wakeup is
dropped leaving userspace hanging forever on the poll.

Normally the event is explicitly re-enabled by userspace after it
wakes up to read the aux data, but in this case it does not get woken
up so the event remains disabled.

This can be reproduced when using Arm SPE and 'stress' which forks once
before running the workload. By looking at the list of aux buffers read,
it's apparent that they stop after the fork:

  perf record -e arm_spe// -vvv -- stress -c 1

With this patch applied they continue to be printed. This behaviour
doesn't happen when using systemwide or per-cpu mode.

Reported-by: Ruben Ayrapetyan <Ruben.Ayrapetyan@arm.com>
Signed-off-by: James Clark <james.clark@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20211206113840.130802-2-james.clark@arm.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
This commit is contained in:
James Clark 2021-12-06 11:38:40 +00:00 committed by Greg Kroah-Hartman
parent a117e986e9
commit d0774cf730
1 changed files with 10 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
kernel/events/core.c
View File

@ -5877,6 +5877,8 @@ static void ring_buffer_attach(struct perf_event *event,
struct perf_buffer *old_rb = NULL; struct perf_buffer *old_rb = NULL;
unsigned long flags; unsigned long flags;
WARN_ON_ONCE(event->parent);
if (event->rb) { if (event->rb) {
/* /*
* Should be impossible, we set this when removing * Should be impossible, we set this when removing
@ -5934,6 +5936,9 @@ static void ring_buffer_wakeup(struct perf_event *event)
{ {
struct perf_buffer *rb; struct perf_buffer *rb;
if (event->parent)
event = event->parent;
rcu_read_lock(); rcu_read_lock();
rb = rcu_dereference(event->rb); rb = rcu_dereference(event->rb);
if (rb) { if (rb) {
@ -5947,6 +5952,9 @@ struct perf_buffer *ring_buffer_get(struct perf_event *event)
{ {
struct perf_buffer *rb; struct perf_buffer *rb;
if (event->parent)
event = event->parent;
rcu_read_lock(); rcu_read_lock();
rb = rcu_dereference(event->rb); rb = rcu_dereference(event->rb);
if (rb) { if (rb) {
@ -6618,7 +6626,7 @@ static unsigned long perf_prepare_sample_aux(struct perf_event *event,
if (WARN_ON_ONCE(READ_ONCE(sampler->oncpu) != smp_processor_id())) if (WARN_ON_ONCE(READ_ONCE(sampler->oncpu) != smp_processor_id()))
goto out; goto out;
rb = ring_buffer_get(sampler->parent ? sampler->parent : sampler); rb = ring_buffer_get(sampler);
if (!rb) if (!rb)
goto out; goto out;
@ -6684,7 +6692,7 @@ static void perf_aux_sample_output(struct perf_event *event,
if (WARN_ON_ONCE(!sampler || !data->aux_size)) if (WARN_ON_ONCE(!sampler || !data->aux_size))
return; return;
rb = ring_buffer_get(sampler->parent ? sampler->parent : sampler); rb = ring_buffer_get(sampler);
if (!rb) if (!rb)
return; return;