[PATCH v6 12/12] nvdimm: virtio_pmem: drain requests in freeze

[Li Chen]

virtio_pmem_freeze() currently deletes virtqueues and resets the device
without waking threads waiting for a virtqueue descriptor or a host
completion.

Mark the request virtqueue broken before reset. This makes new submissions
fail fast and lets -ENOSPC waiters leave the wait list. Reset the device
before draining used and unused request tokens, then delete the virtqueues.
This wakes waiters with -EIO. It also keeps the detach call on a quiesced
device.

Clear req_vq after del_vqs(), and make drain tolerate a NULL queue, so
remove after freeze does not dereference a stale virtqueue pointer.

Signed-off-by: Li Chen <me@linux.beauty>
---
Changes in v6:
- Clear req_vq after del_vqs() and make drain tolerate a NULL queue.
Changes in v5:
- Reset the device before draining used and unused request tokens.
- Use the split broken-marking and post-reset drain helpers.
v2->v3:
- No change.
v3->v4:
- Rebased onto v7.1-rc7 and renumbered after the flush error patches.

 drivers/nvdimm/nd_virtio.c   |  3 +++
 drivers/nvdimm/virtio_pmem.c | 36 +++++++++++++++++++++++++++++++-----
 2 files changed, 34 insertions(+), 5 deletions(-)

diff --git a/drivers/nvdimm/nd_virtio.c b/drivers/nvdimm/nd_virtio.c
index fb9391ebc46e7..ce4032dc07628 100644
--- a/drivers/nvdimm/nd_virtio.c
+++ b/drivers/nvdimm/nd_virtio.c
@@ -93,6 +93,9 @@ void virtio_pmem_drain(struct virtio_pmem *vpmem)
 	struct virtio_pmem_request *req;
 	unsigned int len;
 
+	if (!vpmem->req_vq)
+		return;
+
 	while ((req = virtqueue_get_buf(vpmem->req_vq, &len)) != NULL) {
 		virtio_pmem_clear_inflight(vpmem, req);
 		virtio_pmem_complete_err(req);
diff --git a/drivers/nvdimm/virtio_pmem.c b/drivers/nvdimm/virtio_pmem.c
index b272e9279ef23..fef792f725db2 100644
--- a/drivers/nvdimm/virtio_pmem.c
+++ b/drivers/nvdimm/virtio_pmem.c
@@ -17,11 +17,16 @@ static struct virtio_device_id id_table[] = {
  /* Initialize virt queue */
 static int init_vq(struct virtio_pmem *vpmem)
 {
+	int err;
+
 	/* single vq */
 	vpmem->req_vq = virtio_find_single_vq(vpmem->vdev,
 					virtio_pmem_host_ack, "flush_queue");
-	if (IS_ERR(vpmem->req_vq))
-		return PTR_ERR(vpmem->req_vq);
+	if (IS_ERR(vpmem->req_vq)) {
+		err = PTR_ERR(vpmem->req_vq);
+		vpmem->req_vq = NULL;
+		return err;
+	}
 
 	spin_lock_init(&vpmem->pmem_lock);
 	INIT_LIST_HEAD(&vpmem->req_list);
@@ -31,6 +36,15 @@ static int init_vq(struct virtio_pmem *vpmem)
 	return 0;
 };
 
+static void virtio_pmem_del_vqs(struct virtio_pmem *vpmem)
+{
+	if (!vpmem->req_vq)
+		return;
+
+	vpmem->vdev->config->del_vqs(vpmem->vdev);
+	vpmem->req_vq = NULL;
+}
+
 static int virtio_pmem_validate(struct virtio_device *vdev)
 {
 	struct virtio_shm_region shm_reg;
@@ -132,7 +146,7 @@ static int virtio_pmem_probe(struct virtio_device *vdev)
 	virtio_reset_device(vdev);
 	nvdimm_bus_unregister(vpmem->nvdimm_bus);
 out_vq:
-	vdev->config->del_vqs(vdev);
+	virtio_pmem_del_vqs(vpmem);
 out_err:
 	return err;
 }
@@ -154,14 +168,26 @@ static void virtio_pmem_remove(struct virtio_device *vdev)
 	spin_unlock_irqrestore(&vpmem->pmem_lock, flags);
 
 	nvdimm_bus_unregister(nvdimm_bus);
-	vdev->config->del_vqs(vdev);
+	virtio_pmem_del_vqs(vpmem);
 }
 
 static int virtio_pmem_freeze(struct virtio_device *vdev)
 {
-	vdev->config->del_vqs(vdev);
+	struct virtio_pmem *vpmem = vdev->priv;
+	unsigned long flags;
+
+	spin_lock_irqsave(&vpmem->pmem_lock, flags);
+	virtio_pmem_mark_broken(vpmem);
+	spin_unlock_irqrestore(&vpmem->pmem_lock, flags);
+
 	virtio_reset_device(vdev);
 
+	spin_lock_irqsave(&vpmem->pmem_lock, flags);
+	virtio_pmem_drain(vpmem);
+	spin_unlock_irqrestore(&vpmem->pmem_lock, flags);
+
+	virtio_pmem_del_vqs(vpmem);
+
 	return 0;
 }
 
-- 
2.52.0