Merge tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost

Pull virtio updates from Michael Tsirkin:
 "vhost,virtio and vdpa features, fixes, and cleanups:

   - mac vlan filter and stats support in mlx5 vdpa

   - irq hardening in virtio

   - performance improvements in virtio crypto

   - polling i/o support in virtio blk

   - ASID support in vhost

   - fixes, cleanups all over the place"

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost: (64 commits)
  vdpa: ifcvf: set pci driver data in probe
  vdpa/mlx5: Add RX MAC VLAN filter support
  vdpa/mlx5: Remove flow counter from steering
  vhost: rename vhost_work_dev_flush
  vhost-test: drop flush after vhost_dev_cleanup
  vhost-scsi: drop flush after vhost_dev_cleanup
  vhost_vsock: simplify vhost_vsock_flush()
  vhost_test: remove vhost_test_flush_vq()
  vhost_net: get rid of vhost_net_flush_vq() and extra flush calls
  vhost: flush dev once during vhost_dev_stop
  vhost: get rid of vhost_poll_flush() wrapper
  vhost-vdpa: return -EFAULT on copy_to_user() failure
  vdpasim: Off by one in vdpasim_set_group_asid()
  virtio: Directly use ida_alloc()/free()
  virtio: use WARN_ON() to warning illegal status value
  virtio: harden vring IRQ
  virtio: allow to unbreak virtqueue
  virtio-ccw: implement synchronize_cbs()
  virtio-mmio: implement synchronize_cbs()
  virtio-pci: implement synchronize_cbs()
  ...

1 files changed, 201 insertions, 19 deletions

diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index d624cc8eddc3..6fc7850c2b0a 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -37,6 +37,10 @@ MODULE_PARM_DESC(num_request_queues,
 		 "0 for no limit. "
 		 "Values > nr_cpu_ids truncated to nr_cpu_ids.");
 
+static unsigned int poll_queues;
+module_param(poll_queues, uint, 0644);
+MODULE_PARM_DESC(poll_queues, "The number of dedicated virtqueues for polling I/O");
+
 static int major;
 static DEFINE_IDA(vd_index_ida);
 
@@ -74,6 +78,7 @@ struct virtio_blk {
 
 	/* num of vqs */
 	int num_vqs;
+	int io_queues[HCTX_MAX_TYPES];
 	struct virtio_blk_vq *vqs;
 };
 
@@ -96,8 +101,7 @@ static inline blk_status_t virtblk_result(struct virtblk_req *vbr)
 	}
 }
 
-static int virtblk_add_req(struct virtqueue *vq, struct virtblk_req *vbr,
-		struct scatterlist *data_sg, bool have_data)
+static int virtblk_add_req(struct virtqueue *vq, struct virtblk_req *vbr)
 {
 	struct scatterlist hdr, status, *sgs[3];
 	unsigned int num_out = 0, num_in = 0;
@@ -105,11 +109,11 @@ static int virtblk_add_req(struct virtqueue *vq, struct virtblk_req *vbr,
 	sg_init_one(&hdr, &vbr->out_hdr, sizeof(vbr->out_hdr));
 	sgs[num_out++] = &hdr;
 
-	if (have_data) {
+	if (vbr->sg_table.nents) {
 		if (vbr->out_hdr.type & cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_OUT))
-			sgs[num_out++] = data_sg;
+			sgs[num_out++] = vbr->sg_table.sgl;
 		else
-			sgs[num_out + num_in++] = data_sg;
+			sgs[num_out + num_in++] = vbr->sg_table.sgl;
 	}
 
 	sg_init_one(&status, &vbr->status, sizeof(vbr->status));
@@ -299,6 +303,28 @@ static void virtio_commit_rqs(struct blk_mq_hw_ctx *hctx)
 		virtqueue_notify(vq->vq);
 }
 
+static blk_status_t virtblk_prep_rq(struct blk_mq_hw_ctx *hctx,
+					struct virtio_blk *vblk,
+					struct request *req,
+					struct virtblk_req *vbr)
+{
+	blk_status_t status;
+
+	status = virtblk_setup_cmd(vblk->vdev, req, vbr);
+	if (unlikely(status))
+		return status;
+
+	blk_mq_start_request(req);
+
+	vbr->sg_table.nents = virtblk_map_data(hctx, req, vbr);
+	if (unlikely(vbr->sg_table.nents < 0)) {
+		virtblk_cleanup_cmd(req);
+		return BLK_STS_RESOURCE;
+	}
+
+	return BLK_STS_OK;
+}
+
 static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
 			   const struct blk_mq_queue_data *bd)
 {
@@ -306,26 +332,17 @@ static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
 	struct request *req = bd->rq;
 	struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
 	unsigned long flags;
-	int num;
 	int qid = hctx->queue_num;
 	bool notify = false;
 	blk_status_t status;
 	int err;
 
-	status = virtblk_setup_cmd(vblk->vdev, req, vbr);
+	status = virtblk_prep_rq(hctx, vblk, req, vbr);
 	if (unlikely(status))
 		return status;
 
-	blk_mq_start_request(req);
-
-	num = virtblk_map_data(hctx, req, vbr);
-	if (unlikely(num < 0)) {
-		virtblk_cleanup_cmd(req);
-		return BLK_STS_RESOURCE;
-	}
-
 	spin_lock_irqsave(&vblk->vqs[qid].lock, flags);
-	err = virtblk_add_req(vblk->vqs[qid].vq, vbr, vbr->sg_table.sgl, num);
+	err = virtblk_add_req(vblk->vqs[qid].vq, vbr);
 	if (err) {
 		virtqueue_kick(vblk->vqs[qid].vq);
 		/* Don't stop the queue if -ENOMEM: we may have failed to
@@ -355,6 +372,75 @@ static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
 	return BLK_STS_OK;
 }
 
+static bool virtblk_prep_rq_batch(struct request *req)
+{
+	struct virtio_blk *vblk = req->mq_hctx->queue->queuedata;
+	struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
+
+	req->mq_hctx->tags->rqs[req->tag] = req;
+
+	return virtblk_prep_rq(req->mq_hctx, vblk, req, vbr) == BLK_STS_OK;
+}
+
+static bool virtblk_add_req_batch(struct virtio_blk_vq *vq,
+					struct request **rqlist,
+					struct request **requeue_list)
+{
+	unsigned long flags;
+	int err;
+	bool kick;
+
+	spin_lock_irqsave(&vq->lock, flags);
+
+	while (!rq_list_empty(*rqlist)) {
+		struct request *req = rq_list_pop(rqlist);
+		struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
+
+		err = virtblk_add_req(vq->vq, vbr);
+		if (err) {
+			virtblk_unmap_data(req, vbr);
+			virtblk_cleanup_cmd(req);
+			rq_list_add(requeue_list, req);
+		}
+	}
+
+	kick = virtqueue_kick_prepare(vq->vq);
+	spin_unlock_irqrestore(&vq->lock, flags);
+
+	return kick;
+}
+
+static void virtio_queue_rqs(struct request **rqlist)
+{
+	struct request *req, *next, *prev = NULL;
+	struct request *requeue_list = NULL;
+
+	rq_list_for_each_safe(rqlist, req, next) {
+		struct virtio_blk_vq *vq = req->mq_hctx->driver_data;
+		bool kick;
+
+		if (!virtblk_prep_rq_batch(req)) {
+			rq_list_move(rqlist, &requeue_list, req, prev);
+			req = prev;
+			if (!req)
+				continue;
+		}
+
+		if (!next || req->mq_hctx != next->mq_hctx) {
+			req->rq_next = NULL;
+			kick = virtblk_add_req_batch(vq, rqlist, &requeue_list);
+			if (kick)
+				virtqueue_notify(vq->vq);
+
+			*rqlist = next;
+			prev = NULL;
+		} else
+			prev = req;
+	}
+
+	*rqlist = requeue_list;
+}
+
 /* return id (s/n) string for *disk to *id_str
  */
 static int virtblk_get_id(struct gendisk *disk, char *id_str)
@@ -512,6 +598,7 @@ static int init_vq(struct virtio_blk *vblk)
 	const char **names;
 	struct virtqueue **vqs;
 	unsigned short num_vqs;
+	unsigned int num_poll_vqs;
 	struct virtio_device *vdev = vblk->vdev;
 	struct irq_affinity desc = { 0, };
 
@@ -520,6 +607,7 @@ static int init_vq(struct virtio_blk *vblk)
 				   &num_vqs);
 	if (err)
 		num_vqs = 1;
+
 	if (!err && !num_vqs) {
 		dev_err(&vdev->dev, "MQ advertised but zero queues reported\n");
 		return -EINVAL;
@@ -529,6 +617,17 @@ static int init_vq(struct virtio_blk *vblk)
 			min_not_zero(num_request_queues, nr_cpu_ids),
 			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_array(num_vqs, sizeof(*vblk->vqs), GFP_KERNEL);
 	if (!vblk->vqs)
 		return -ENOMEM;
@@ -541,12 +640,18 @@ static int init_vq(struct virtio_blk *vblk)
 		goto out;
 	}
 
-	for (i = 0; i < num_vqs; i++) {
+	for (i = 0; i < num_vqs - num_poll_vqs; i++) {
 		callbacks[i] = virtblk_done;
 		snprintf(vblk->vqs[i].name, VQ_NAME_LEN, "req.%d", i);
 		names[i] = vblk->vqs[i].name;
 	}
 
+	for (; i < num_vqs; i++) {
+		callbacks[i] = NULL;
+		snprintf(vblk->vqs[i].name, VQ_NAME_LEN, "req_poll.%d", i);
+		names[i] = vblk->vqs[i].name;
+	}
+
 	/* Discover virtqueues and write information to configuration.  */
 	err = virtio_find_vqs(vdev, num_vqs, vqs, callbacks, names, &desc);
 	if (err)
@@ -692,16 +797,90 @@ static const struct attribute_group *virtblk_attr_groups[] = {
 static int virtblk_map_queues(struct blk_mq_tag_set *set)
 {
 	struct virtio_blk *vblk = set->driver_data;
+	int i, qoff;
+
+	for (i = 0, qoff = 0; i < set->nr_maps; i++) {
+		struct blk_mq_queue_map *map = &set->map[i];
+
+		map->nr_queues = vblk->io_queues[i];
+		map->queue_offset = qoff;
+		qoff += map->nr_queues;
+
+		if (map->nr_queues == 0)
+			continue;
+
+		/*
+		 * Regular queues have interrupts and hence CPU affinity is
+		 * defined by the core virtio code, but polling queues have
+		 * no interrupts so we let the block layer assign CPU affinity.
+		 */
+		if (i == HCTX_TYPE_POLL)
+			blk_mq_map_queues(&set->map[i]);
+		else
+			blk_mq_virtio_map_queues(&set->map[i], vblk->vdev, 0);
+	}
+
+	return 0;
+}
+
+static void virtblk_complete_batch(struct io_comp_batch *iob)
+{
+	struct request *req;
+
+	rq_list_for_each(&iob->req_list, req) {
+		virtblk_unmap_data(req, blk_mq_rq_to_pdu(req));
+		virtblk_cleanup_cmd(req);
+	}
+	blk_mq_end_request_batch(iob);
+}
+
+static int virtblk_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)
+{
+	struct virtio_blk *vblk = hctx->queue->queuedata;
+	struct virtio_blk_vq *vq = hctx->driver_data;
+	struct virtblk_req *vbr;
+	unsigned long flags;
+	unsigned int len;
+	int found = 0;
 
-	return blk_mq_virtio_map_queues(&set->map[HCTX_TYPE_DEFAULT],
-					vblk->vdev, 0);
+	spin_lock_irqsave(&vq->lock, flags);
+
+	while ((vbr = virtqueue_get_buf(vq->vq, &len)) != NULL) {
+		struct request *req = blk_mq_rq_from_pdu(vbr);
+
+		found++;
+		if (!blk_mq_add_to_batch(req, iob, vbr->status,
+						virtblk_complete_batch))
+			blk_mq_complete_request(req);
+	}
+
+	if (found)
+		blk_mq_start_stopped_hw_queues(vblk->disk->queue, true);
+
+	spin_unlock_irqrestore(&vq->lock, flags);
+
+	return found;
+}
+
+static int virtblk_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
+			  unsigned int hctx_idx)
+{
+	struct virtio_blk *vblk = data;
+	struct virtio_blk_vq *vq = &vblk->vqs[hctx_idx];
+
+	WARN_ON(vblk->tag_set.tags[hctx_idx] != hctx->tags);
+	hctx->driver_data = vq;
+	return 0;
 }
 
 static const struct blk_mq_ops virtio_mq_ops = {
 	.queue_rq	= virtio_queue_rq,
+	.queue_rqs	= virtio_queue_rqs,
 	.commit_rqs	= virtio_commit_rqs,
+	.init_hctx	= virtblk_init_hctx,
 	.complete	= virtblk_request_done,
 	.map_queues	= virtblk_map_queues,
+	.poll		= virtblk_poll,
 };
 
 static unsigned int virtblk_queue_depth;
@@ -778,6 +957,9 @@ static int virtblk_probe(struct virtio_device *vdev)
 		sizeof(struct scatterlist) * VIRTIO_BLK_INLINE_SG_CNT;
 	vblk->tag_set.driver_data = vblk;
 	vblk->tag_set.nr_hw_queues = vblk->num_vqs;
+	vblk->tag_set.nr_maps = 1;
+	if (vblk->io_queues[HCTX_TYPE_POLL])
+		vblk->tag_set.nr_maps = 3;
 
 	err = blk_mq_alloc_tag_set(&vblk->tag_set);
 	if (err)