[PATCH] task_work: add a scheduling point in task_work_run()

From: Eric Dumazet <eric.dumazet@gmail.com>
To: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Mimi Zohar <zohar@linux.vnet.ibm.com>,
	Oleg Nesterov <oleg@redhat.com>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	". James Morris" <jmorris@namei.org>,
	linux-security-module@vger.kernel.org,
	linux-kernel <linux-kernel@vger.kernel.org>,
	David Howells <dhowells@redhat.com>
Subject: [PATCH] task_work: add a scheduling point in task_work_run()
Date: Tue, 21 Aug 2012 15:05:14 +0200	[thread overview]
Message-ID: <1345554314.5158.490.camel@edumazet-glaptop> (raw)
In-Reply-To: <1341240603.2086.1.camel@falcor>

From: Eric Dumazet <edumazet@google.com>

It seems commit 4a9d4b02 (switch fput to task_work_add) reintroduced
the problem addressed in commit 944be0b2 (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 <edumazet@google.com>
---
 kernel/task_work.c |    1 +
 1 file changed, 1 insertion(+)

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();
 		}
 	}
 }


