[PATCH] virtio_blk: freeze the virtqueue layout at probe time

[Yunye Zhao <yunye.zhao@linux.alibaba.com>]

init_vq() reads the writable num_request_queues and poll_queues module
parameters both at probe and when recreating virtqueues after suspend
or reset. However, virtio-blk does not update the blk-mq hardware queue
count or queue maps on restore.

Increasing poll_queues can therefore remove the completion callback
from a virtqueue still used for interrupt-driven I/O, leaving requests
uncompleted. Reducing the effective request queue count through
num_request_queues can instead leave existing hardware contexts
indexing beyond the reallocated vblk->vqs array.

Determine the virtqueue count and the split between interrupt-driven
and polling queues once at probe, and reuse this layout when
recreating the virtqueues. Changes to these module parameters then
affect only subsequently probed devices.

Fixes: 0989c41bed96 ("virtio-blk: add num_request_queues module parameter")
Signed-off-by: Yunye Zhao <yunye.zhao@linux.alibaba.com>
---
The functional fix was previously tested with QEMU 8.2.2 on
7be4bc52fd9e (v7.3-2415), covering:

- PCI FLR after changing poll_queues from 0 to 1 or num_request_queues
  from 0 to 1 on a device with four request queues.
- Normal and polled I/O across FLR with poll_queues=1 at probe,
  including a subsequent change of poll_queues to 0.
- Device suspend/resume with pm_test=devices and state=freeze (not a
  full s2idle cycle), plus full S3 and S4 suspend/resume cycles.

 drivers/block/virtio_blk.c | 71 +++++++++++++++++++++++++++-----------------
 1 file changed, 43 insertions(+), 28 deletions(-)

diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index c8bfbf8435ac..0df89f381047 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -958,42 +958,54 @@ static void virtblk_config_changed(struct virtio_device *vdev)
 	queue_work(virtblk_wq, &vblk->config_work);
 }
 
+/* Keep the queue layout unchanged for the lifetime of the tag set. */
+static int virtblk_init_queue_layout(struct virtio_blk *vblk)
+{
+	struct virtio_device *vdev = vblk->vdev;
+	unsigned short num_vqs;
+	unsigned short num_poll_vqs;
+	int err;
+
+	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_MQ,
+				   struct virtio_blk_config, num_queues,
+				   &num_vqs);
+	if (err)
+		num_vqs = 1;
+
+	if (!err && !num_vqs) {
+		dev_err(&vdev->dev, "MQ advertised but zero queues reported\n");
+		return -EINVAL;
+	}
+
+	num_vqs = blk_mq_num_possible_queues(
+			min_not_zero(num_request_queues, num_vqs));
+
+	num_poll_vqs = min_t(unsigned int, poll_queues, num_vqs - 1);
+
+	vblk->num_vqs = num_vqs;
+	vblk->io_queues[HCTX_TYPE_DEFAULT] = num_vqs - num_poll_vqs;
+	vblk->io_queues[HCTX_TYPE_READ] = 0;
+	vblk->io_queues[HCTX_TYPE_POLL] = num_poll_vqs;
+
+	dev_info(&vdev->dev, "%d/%d/%d default/read/poll queues\n",
+				vblk->io_queues[HCTX_TYPE_DEFAULT],
+				vblk->io_queues[HCTX_TYPE_READ],
+				vblk->io_queues[HCTX_TYPE_POLL]);
+
+	return 0;
+}
+
 static int init_vq(struct virtio_blk *vblk)
 {
 	int err;
 	unsigned short i;
 	struct virtqueue_info *vqs_info;
 	struct virtqueue **vqs;
-	unsigned short num_vqs;
-	unsigned short num_poll_vqs;
+	unsigned short num_vqs = vblk->num_vqs;
+	unsigned short num_poll_vqs = vblk->io_queues[HCTX_TYPE_POLL];
 	struct virtio_device *vdev = vblk->vdev;
 	struct irq_affinity desc = { 0, };
 
-	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_MQ,
-				   struct virtio_blk_config, num_queues,
-				   &num_vqs);
-	if (err)
-		num_vqs = 1;
-
-	if (!err && !num_vqs) {
-		dev_err(&vdev->dev, "MQ advertised but zero queues reported\n");
-		return -EINVAL;
-	}
-
-	num_vqs = blk_mq_num_possible_queues(
-			min_not_zero(num_request_queues, num_vqs));
-
-	num_poll_vqs = min_t(unsigned int, poll_queues, num_vqs - 1);
-
-	vblk->io_queues[HCTX_TYPE_DEFAULT] = num_vqs - num_poll_vqs;
-	vblk->io_queues[HCTX_TYPE_READ] = 0;
-	vblk->io_queues[HCTX_TYPE_POLL] = num_poll_vqs;
-
-	dev_info(&vdev->dev, "%d/%d/%d default/read/poll queues\n",
-				vblk->io_queues[HCTX_TYPE_DEFAULT],
-				vblk->io_queues[HCTX_TYPE_READ],
-				vblk->io_queues[HCTX_TYPE_POLL]);
-
 	vblk->vqs = kmalloc_objs(*vblk->vqs, num_vqs);
 	if (!vblk->vqs)
 		return -ENOMEM;
@@ -1025,7 +1037,6 @@ static int init_vq(struct virtio_blk *vblk)
 		spin_lock_init(&vblk->vqs[i].lock);
 		vblk->vqs[i].vq = vqs[i];
 	}
-	vblk->num_vqs = num_vqs;
 
 out:
 	kfree(vqs);
@@ -1470,6 +1481,10 @@ static int virtblk_probe(struct virtio_device *vdev)
 
 	INIT_WORK(&vblk->config_work, virtblk_config_changed_work);
 
+	err = virtblk_init_queue_layout(vblk);
+	if (err)
+		goto out_free_vblk;
+
 	err = init_vq(vblk);
 	if (err)
 		goto out_free_vblk;

base-commit: 7be4bc52fd9e0e55dc9a2e0232b89427d2c4b614
-- 
2.19.1.6.gb485710b