[PATCH] CFQ: use irq safe locking in cfq_cic_link()
authorJens Axboe <jens.axboe@oracle.com>
Mon, 30 Oct 2006 18:07:48 +0000 (19:07 +0100)
committerLinus Torvalds <torvalds@g5.osdl.org>
Mon, 30 Oct 2006 18:21:58 +0000 (10:21 -0800)
commit0261d6886eb5822867a5310dc1e4479b940a1942
treee1abc43a23dce3a2250eed8732e68fd6e8a92053
parent209ad53bc19667a128d9c51beba873a5c62bff6e
[PATCH] CFQ: use irq safe locking in cfq_cic_link()

If cfq_set_request() is called for a new process AND a non-fs io
request (so that __GFP_WAIT may not be set), cfq_cic_link() may
use spin_lock_irq() and spin_unlock_irq() with interrupts already
disabled.

Fix is to always use irq safe locking in cfq_cic_link()

Acked-By: Arjan van de Ven <arjan@linux.intel.com>
Acked-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
block/cfq-iosched.c