md: using GFP_NOIO to allocate bio for flush request

commit b5e1b8cee7ad58a15d2fa79bcd7946acb592602d upstream.

A flush request is usually issued in transaction commit code path, so
using GFP_KERNEL to allocate memory for flush request bio falls into
the classic deadlock issue.

This is suitable for any -stable kernel to which it applies as it
avoids a possible deadlock.

Signed-off-by: Shaohua Li <shli@fusionio.com>
Signed-off-by: NeilBrown <neilb@suse.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 363aaf40500ef46f4622efdf5014d5ea81f6f65c..1ae432764b93ef391db661c9a35dbbca72740282 100644 (file)
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -452,7 +452,7 @@ static void submit_flushes(struct work_struct *ws)
                        atomic_inc(&rdev->nr_pending);
                        atomic_inc(&rdev->nr_pending);
                        rcu_read_unlock();
-                       bi = bio_alloc_mddev(GFP_KERNEL, 0, mddev);
+                       bi = bio_alloc_mddev(GFP_NOIO, 0, mddev);
                        bi->bi_end_io = md_end_flush;
                        bi->bi_private = rdev;
                        bi->bi_bdev = rdev->bdev;