task_work: add a scheduling point in task_work_run()

f341861f · Eric Dumazet <[email protected]> · 2012-08-21 15:05:14 +02:00

It seems commit 4a9d4b024a31 ("switch fput to task_work_add") re-
introduced the problem addressed in 944be0b22472 ("close_files(): add
scheduling point")

If a server process with a lot of files (say 2 million tcp sockets) is
killed, we can spend a lot of time in task_work_run() and trigger a soft
lockup.

Signed-off-by: Eric Dumazet <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

Commit: f341861fb0b701139849f8a85c2d3cdff466e8e8
Parents: ec5da7f8

Changes

1 files changed · +1 −0

File	Status	Add	Del	Content
kernel/task_work.c	modified	+1	−0	View file

kernel/task_work.c

View file

diff --git a/kernel/task_work.c b/kernel/task_work.c
index 91d4e17..d320d44 100644
--- a/kernel/task_work.c
+++ b/kernel/task_work.c
@@ -75,6 +75,7 @@ void task_work_run(void)
 			p = q->next;
 			q->func(q);
 			q = p;
+			cond_resched();
 		}
 	}
 }