RepoMirrors/haproxy
1
0
Fork 0
mirror of http://git.haproxy.org/git/haproxy.git/ synced 2024-12-17 00:44:33 +00:00
Code Issues Packages Projects Releases Wiki Activity

BUG/MEDIUM: thread: Fix a deadlock if an isolated thread is marked as harmless

Browse Source 
If an isolated thread is marked as harmless, it will loop forever in
thread_harmless_till_end() waiting no threads are isolated anymore. It never
happens because the current thread is isolated. To fix the bug, we exclude
the current thread for the test. We now wait for all other threads to leave
the rendez-vous point.

This bug only seems to occurr if HAProxy is compiled with DEBUG_UAF, when
pool_gc() is called. pool_gc() isolates the current thread, while
pool_free_area() set the thread as harmless when munmap is called.

This patch must be backported as far as 2.0.
This commit is contained in:
Christopher Faulet 2021-03-25 14:11:36 +01:00
parent 65bf600cc3
commit a9a9e9aac9
1 changed files with 5 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
src/thread.c
View File

@ -48,13 +48,15 @@ struct lock_stat lock_stats[LOCK_LABELS];
#endif
/* Marks the thread as harmless until the last thread using the rendez-vous
* point quits. Given that we can wait for a long time, sched_yield() is used
* when available to offer the CPU resources to competing threads if needed.
* point quits, excluding the current one. Thus an isolated thread may be safely
* marked as harmless. Given that we can wait for a long time, sched_yield() is
* used when available to offer the CPU resources to competing threads if
* needed.
*/
void thread_harmless_till_end()
{
_HA_ATOMIC_OR(&threads_harmless_mask, tid_bit);
while (threads_want_rdv_mask & all_threads_mask) {
while (threads_want_rdv_mask & ~tid_bit) {
ha_thread_relax();
}
}