BUG/MEDIUM: thread: mask stopping_threads with threads_enabled when checking it

When soft-stopping, there's a comparison between stopping_threads and
threads_enabled to make sure all threads are stopped, but this is not
correct and is racy since the threads_enabled bit is removed when a
thread is stopped but not its stopping_threads bit. The consequence is
that depending on timing, when stopping, if the first stopping thread
is fast enough to remove its bit from threads_enabled, the other threads
will see that stopping_threads doesn't match threads_enabled anymore and
will wait forever. As such the mask must be applied to stopping_threads
during the test. This issue was introduced in recent commit ef422ced9
("MEDIUM: thread: make stopping_threads per-group and add stopping_tgroups"),
no backport is needed.
This commit is contained in:
Willy Tarreau 2022-07-06 10:13:05 +02:00
parent 4c3d3d2a68
commit f34a3fa33d

View File

@ -2840,7 +2840,8 @@ void run_poll_loop()
(_HA_ATOMIC_LOAD(&stopping_tgroup_mask) & all_tgroups_mask) == all_tgroups_mask) { (_HA_ATOMIC_LOAD(&stopping_tgroup_mask) & all_tgroups_mask) == all_tgroups_mask) {
/* check that all threads are aware of the stopping status */ /* check that all threads are aware of the stopping status */
for (i = 0; i < global.nbtgroups; i++) for (i = 0; i < global.nbtgroups; i++)
if (_HA_ATOMIC_LOAD(&ha_tgroup_ctx[i].stopping_threads) != ha_tgroup_info[i].threads_enabled) if ((_HA_ATOMIC_LOAD(&ha_tgroup_ctx[i].stopping_threads) & ha_tgroup_info[i].threads_enabled) !=
ha_tgroup_info[i].threads_enabled)
break; break;
#ifdef USE_THREAD #ifdef USE_THREAD
if (i == global.nbtgroups) { if (i == global.nbtgroups) {