linux-kernel - [GIT PULL] virtio

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [day] [month] [year] [list]

Message-ID: <20140527144437.GA31504@kernel.dk>
Date:	Tue, 27 May 2014 08:44:37 -0600
From:	Jens Axboe <axboe@...com>
To:	<torvalds@...ux-foundation.org>
CC:	<linux-kernel@...r.kernel.org>, <sakari.ailus@....fi>,
	<rusty@...tcorp.com.au>
Subject: [GIT PULL] virtio_blk fix for 3.15

Hi,

There's a start/stop queue race in virtio_blk, which causes stalls and
erratic behaviour for some. I've had this queued up for 3.16 for a
while, but I think we should push it into the current series as well. So
I cherry picked the commit and added a stable marker as well, so it can
propagate down.

Please pull!

  git://git.kernel.dk/linux-block.git for-linus

  virtio_blk: fix race between start and stop queue (2014-05-27 08:41:10 -0600)

----------------------------------------------------------------
Ming Lei (1):
      virtio_blk: fix race between start and stop queue

 drivers/block/virtio_blk.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)


diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 6d8a87f252de..cb9b1f8326c3 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -144,11 +144,11 @@ static void virtblk_done(struct virtqueue *vq)
 		if (unlikely(virtqueue_is_broken(vq)))
 			break;
 	} while (!virtqueue_enable_cb(vq));
-	spin_unlock_irqrestore(&vblk->vq_lock, flags);
 
 	/* In case queue is stopped waiting for more buffers. */
 	if (req_done)
 		blk_mq_start_stopped_hw_queues(vblk->disk->queue);
+	spin_unlock_irqrestore(&vblk->vq_lock, flags);
 }
 
 static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req)
@@ -202,8 +202,8 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req)
 	err = __virtblk_add_req(vblk->vq, vbr, vbr->sg, num);
 	if (err) {
 		virtqueue_kick(vblk->vq);
-		spin_unlock_irqrestore(&vblk->vq_lock, flags);
 		blk_mq_stop_hw_queue(hctx);
+		spin_unlock_irqrestore(&vblk->vq_lock, flags);
 		/* Out of mem doesn't actually happen, since we fall back
 		 * to direct descriptors */
 		if (err == -ENOMEM || err == -ENOSPC)

-- 
Jens Axboe

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/