[PATCH] virtio_blk: Fix device surprise removal

[Parav Pandit <parav@nvidia.com>]

When the PCI device is surprise removed, requests won't complete from
the device. These IOs are never completed and disk deletion hangs
indefinitely.

Fix it by aborting the IOs which the device will never complete
when the VQ is broken.

With this fix now fio completes swiftly.
An alternative of IO timeout has been considered, however
when the driver knows about unresponsive block device, swiftly clearing
them enables users and upper layers to react quickly.

Verified with multiple device unplug cycles with pending IOs in virtio
used ring and some pending with device.

In future instead of VQ broken, a more elegant method can be used. At the
moment the patch is kept to its minimal changes given its urgency to fix
broken kernels.

Fixes: 43bb40c5b926 ("virtio_pci: Support surprise removal of virtio pci device")
Cc: stable@vger.kernel.org
Reported-by: lirongqing@baidu.com
Closes: https://lore.kernel.org/virtualization/c45dd68698cd47238c55fb73ca9b4741@baidu.com/
Co-developed-by: Chaitanya Kulkarni <kch@nvidia.com>
Signed-off-by: Chaitanya Kulkarni <kch@nvidia.com>
Signed-off-by: Parav Pandit <parav@nvidia.com>
---
 drivers/block/virtio_blk.c | 54 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 54 insertions(+)

diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 2bf14a0e2815..59b49899b229 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -1562,10 +1562,64 @@ static int virtblk_probe(struct virtio_device *vdev)
 	return err;
 }
 
+static bool virtblk_cancel_request(struct request *rq, void *data)
+{
+	struct virtblk_req *vbr = blk_mq_rq_to_pdu(rq);
+
+	vbr->in_hdr.status = VIRTIO_BLK_S_IOERR;
+	if (blk_mq_request_started(rq) && !blk_mq_request_completed(rq))
+		blk_mq_complete_request(rq);
+
+	return true;
+}
+
+static void virtblk_cleanup_reqs(struct virtio_blk *vblk)
+{
+	struct virtio_blk_vq *blk_vq;
+	struct request_queue *q;
+	struct virtqueue *vq;
+	unsigned long flags;
+	int i;
+
+	vq = vblk->vqs[0].vq;
+	if (!virtqueue_is_broken(vq))
+		return;
+
+	q = vblk->disk->queue;
+	/* Block upper layer to not get any new requests */
+	blk_mq_quiesce_queue(q);
+
+	for (i = 0; i < vblk->num_vqs; i++) {
+		blk_vq = &vblk->vqs[i];
+
+		/* Synchronize with any ongoing virtblk_poll() which may be
+		 * completing the requests to uppper layer which has already
+		 * crossed the broken vq check.
+		 */
+		spin_lock_irqsave(&blk_vq->lock, flags);
+		spin_unlock_irqrestore(&blk_vq->lock, flags);
+	}
+
+	blk_sync_queue(q);
+
+	/* Complete remaining pending requests with error */
+	blk_mq_tagset_busy_iter(&vblk->tag_set, virtblk_cancel_request, vblk);
+	blk_mq_tagset_wait_completed_request(&vblk->tag_set);
+
+	/*
+	 * Unblock any pending dispatch I/Os before we destroy device. From
+	 * del_gendisk() -> __blk_mark_disk_dead(disk) will set GD_DEAD flag,
+	 * that will make sure any new I/O from bio_queue_enter() to fail.
+	 */
+	blk_mq_unquiesce_queue(q);
+}
+
 static void virtblk_remove(struct virtio_device *vdev)
 {
 	struct virtio_blk *vblk = vdev->priv;
 
+	virtblk_cleanup_reqs(vblk);
+
 	/* Make sure no work handler is accessing the device. */
 	flush_work(&vblk->config_work);
 
-- 
2.34.1