diff options
| author | Jinliang Zheng <[email protected]> | 2024-06-20 20:21:24 +0800 |
|---|---|---|
| committer | Andrew Morton <[email protected]> | 2024-07-03 12:29:24 -0700 |
| commit | cf3f9a593dab87a032d2b6a6fb205e7f3de4f0a1 (patch) | |
| tree | 179b27d1f6bb993000e5745f1d413d8ee2f600f4 | |
| parent | 22a40d14b572deb80c0648557f4bd502d7e83826 (diff) | |
mm: optimize the redundant loop of mm_update_owner_next()
When mm_update_owner_next() is racing with swapoff (try_to_unuse()) or
/proc or ptrace or page migration (get_task_mm()), it is impossible to
find an appropriate task_struct in the loop whose mm_struct is the same as
the target mm_struct.
If the above race condition is combined with the stress-ng-zombie and
stress-ng-dup tests, such a long loop can easily cause a Hard Lockup in
write_lock_irq() for tasklist_lock.
Recognize this situation in advance and exit early.
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Jinliang Zheng <[email protected]>
Acked-by: Michal Hocko <[email protected]>
Cc: Christian Brauner <[email protected]>
Cc: Jens Axboe <[email protected]>
Cc: Mateusz Guzik <[email protected]>
Cc: Matthew Wilcox (Oracle) <[email protected]>
Cc: Oleg Nesterov <[email protected]>
Cc: Tycho Andersen <[email protected]>
Cc: <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
| -rw-r--r-- | kernel/exit.c | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/kernel/exit.c b/kernel/exit.c index f95a2c1338a8..81fcee45d630 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -484,6 +484,8 @@ retry: * Search through everything else, we should not get here often. */ for_each_process(g) { + if (atomic_read(&mm->mm_users) <= 1) + break; if (g->flags & PF_KTHREAD) continue; for_each_thread(g, c) { |