The quilt patch titled
Subject: mm: optimize the redundant loop of mm_update_owner_next()
has been removed from the -mm tree. Its filename was
mm-optimize-the-redundant-loop-of-mm_update_owner_next.patch
This patch was dropped because it was merged into the mm-hotfixes-stable branch
of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
------------------------------------------------------
From: Jinliang Zheng <alexjlzheng@xxxxxxxxxxx>
Subject: mm: optimize the redundant loop of mm_update_owner_next()
Date: Thu, 20 Jun 2024 20:21:24 +0800
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/20240620122123.3877432-1-alexjlzheng@xxxxxxxxxxx
Signed-off-by: Jinliang Zheng <alexjlzheng@xxxxxxxxxxx>
Acked-by: Michal Hocko <mhocko@xxxxxxxx>
Cc: Christian Brauner <brauner@xxxxxxxxxx>
Cc: Jens Axboe <axboe@xxxxxxxxx>
Cc: Mateusz Guzik <mjguzik@xxxxxxxxx>
Cc: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
Cc: Oleg Nesterov <oleg@xxxxxxxxxx>
Cc: Tycho Andersen <tandersen@xxxxxxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
kernel/exit.c | 2 ++
1 file changed, 2 insertions(+)
--- a/kernel/exit.c~mm-optimize-the-redundant-loop-of-mm_update_owner_next
+++ a/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) {
_
Patches currently in -mm which might be from alexjlzheng@xxxxxxxxxxx are
