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

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

   - Hardening work by Jason

   - vdpa driver for Alibaba ENI

   - Performance tweaks for virtio blk

   - virtio rng rework using an internal buffer

   - mac/mtu programming for mlx5 vdpa

   - Misc fixes, cleanups"

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost: (45 commits)
  vdpa/mlx5: Forward only packets with allowed MAC address
  vdpa/mlx5: Support configuration of MAC
  vdpa/mlx5: Fix clearing of VIRTIO_NET_F_MAC feature bit
  vdpa_sim_net: Enable user to set mac address and mtu
  vdpa: Enable user to set mac and mtu of vdpa device
  vdpa: Use kernel coding style for structure comments
  vdpa: Introduce query of device config layout
  vdpa: Introduce and use vdpa device get, set config helpers
  virtio-scsi: don't let virtio core to validate used buffer length
  virtio-blk: don't let virtio core to validate used length
  virtio-net: don't let virtio core to validate used length
  virtio_ring: validate used buffer length
  virtio_blk: correct types for status handling
  virtio_blk: allow 0 as num_request_queues
  i2c: virtio: Add support for zero-length requests
  virtio-blk: fixup coccinelle warnings
  virtio_ring: fix typos in vring_desc_extra
  virtio-pci: harden INTX interrupts
  virtio_pci: harden MSI-X interrupts
  virtio_config: introduce a new .enable_cbs method
  ...

1 files changed, 119 insertions, 59 deletions

diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index fc4fc951dba7..97bf051a50ce 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -24,6 +24,19 @@
 /* The maximum number of sg elements that fit into a virtqueue */
 #define VIRTIO_BLK_MAX_SG_ELEMS 32768
 
+#ifdef CONFIG_ARCH_NO_SG_CHAIN
+#define VIRTIO_BLK_INLINE_SG_CNT	0
+#else
+#define VIRTIO_BLK_INLINE_SG_CNT	2
+#endif
+
+static unsigned int num_request_queues;
+module_param(num_request_queues, uint, 0644);
+MODULE_PARM_DESC(num_request_queues,
+		 "Limit the number of request queues to use for blk device. "
+		 "0 for no limit. "
+		 "Values > nr_cpu_ids truncated to nr_cpu_ids.");
+
 static int major;
 static DEFINE_IDA(vd_index_ida);
 
@@ -77,6 +90,7 @@ struct virtio_blk {
 struct virtblk_req {
 	struct virtio_blk_outhdr out_hdr;
 	u8 status;
+	struct sg_table sg_table;
 	struct scatterlist sg[];
 };
 
@@ -162,12 +176,93 @@ static int virtblk_setup_discard_write_zeroes(struct request *req, bool unmap)
 	return 0;
 }
 
-static inline void virtblk_request_done(struct request *req)
+static void virtblk_unmap_data(struct request *req, struct virtblk_req *vbr)
 {
-	struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
+	if (blk_rq_nr_phys_segments(req))
+		sg_free_table_chained(&vbr->sg_table,
+				      VIRTIO_BLK_INLINE_SG_CNT);
+}
+
+static int virtblk_map_data(struct blk_mq_hw_ctx *hctx, struct request *req,
+		struct virtblk_req *vbr)
+{
+	int err;
+
+	if (!blk_rq_nr_phys_segments(req))
+		return 0;
+
+	vbr->sg_table.sgl = vbr->sg;
+	err = sg_alloc_table_chained(&vbr->sg_table,
+				     blk_rq_nr_phys_segments(req),
+				     vbr->sg_table.sgl,
+				     VIRTIO_BLK_INLINE_SG_CNT);
+	if (unlikely(err))
+		return -ENOMEM;
 
+	return blk_rq_map_sg(hctx->queue, req, vbr->sg_table.sgl);
+}
+
+static void virtblk_cleanup_cmd(struct request *req)
+{
 	if (req->rq_flags & RQF_SPECIAL_PAYLOAD)
 		kfree(bvec_virt(&req->special_vec));
+}
+
+static blk_status_t virtblk_setup_cmd(struct virtio_device *vdev,
+				      struct request *req,
+				      struct virtblk_req *vbr)
+{
+	bool unmap = false;
+	u32 type;
+
+	vbr->out_hdr.sector = 0;
+
+	switch (req_op(req)) {
+	case REQ_OP_READ:
+		type = VIRTIO_BLK_T_IN;
+		vbr->out_hdr.sector = cpu_to_virtio64(vdev,
+						      blk_rq_pos(req));
+		break;
+	case REQ_OP_WRITE:
+		type = VIRTIO_BLK_T_OUT;
+		vbr->out_hdr.sector = cpu_to_virtio64(vdev,
+						      blk_rq_pos(req));
+		break;
+	case REQ_OP_FLUSH:
+		type = VIRTIO_BLK_T_FLUSH;
+		break;
+	case REQ_OP_DISCARD:
+		type = VIRTIO_BLK_T_DISCARD;
+		break;
+	case REQ_OP_WRITE_ZEROES:
+		type = VIRTIO_BLK_T_WRITE_ZEROES;
+		unmap = !(req->cmd_flags & REQ_NOUNMAP);
+		break;
+	case REQ_OP_DRV_IN:
+		type = VIRTIO_BLK_T_GET_ID;
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return BLK_STS_IOERR;
+	}
+
+	vbr->out_hdr.type = cpu_to_virtio32(vdev, type);
+	vbr->out_hdr.ioprio = cpu_to_virtio32(vdev, req_get_ioprio(req));
+
+	if (type == VIRTIO_BLK_T_DISCARD || type == VIRTIO_BLK_T_WRITE_ZEROES) {
+		if (virtblk_setup_discard_write_zeroes(req, unmap))
+			return BLK_STS_RESOURCE;
+	}
+
+	return 0;
+}
+
+static inline void virtblk_request_done(struct request *req)
+{
+	struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
+
+	virtblk_unmap_data(req, vbr);
+	virtblk_cleanup_cmd(req);
 	blk_mq_end_request(req, virtblk_result(vbr));
 }
 
@@ -223,59 +318,26 @@ static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
 	unsigned long flags;
 	unsigned int num;
 	int qid = hctx->queue_num;
-	int err;
 	bool notify = false;
-	bool unmap = false;
-	u32 type;
+	blk_status_t status;
+	int err;
 
 	BUG_ON(req->nr_phys_segments + 2 > vblk->sg_elems);
 
-	switch (req_op(req)) {
-	case REQ_OP_READ:
-	case REQ_OP_WRITE:
-		type = 0;
-		break;
-	case REQ_OP_FLUSH:
-		type = VIRTIO_BLK_T_FLUSH;
-		break;
-	case REQ_OP_DISCARD:
-		type = VIRTIO_BLK_T_DISCARD;
-		break;
-	case REQ_OP_WRITE_ZEROES:
-		type = VIRTIO_BLK_T_WRITE_ZEROES;
-		unmap = !(req->cmd_flags & REQ_NOUNMAP);
-		break;
-	case REQ_OP_DRV_IN:
-		type = VIRTIO_BLK_T_GET_ID;
-		break;
-	default:
-		WARN_ON_ONCE(1);
-		return BLK_STS_IOERR;
-	}
-
-	vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, type);
-	vbr->out_hdr.sector = type ?
-		0 : cpu_to_virtio64(vblk->vdev, blk_rq_pos(req));
-	vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(req));
+	status = virtblk_setup_cmd(vblk->vdev, req, vbr);
+	if (unlikely(status))
+		return status;
 
 	blk_mq_start_request(req);
 
-	if (type == VIRTIO_BLK_T_DISCARD || type == VIRTIO_BLK_T_WRITE_ZEROES) {
-		err = virtblk_setup_discard_write_zeroes(req, unmap);
-		if (err)
-			return BLK_STS_RESOURCE;
-	}
-
-	num = blk_rq_map_sg(hctx->queue, req, vbr->sg);
-	if (num) {
-		if (rq_data_dir(req) == WRITE)
-			vbr->out_hdr.type |= cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_OUT);
-		else
-			vbr->out_hdr.type |= cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_IN);
+	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, num);
+	err = virtblk_add_req(vblk->vqs[qid].vq, vbr, vbr->sg_table.sgl, num);
 	if (err) {
 		virtqueue_kick(vblk->vqs[qid].vq);
 		/* Don't stop the queue if -ENOMEM: we may have failed to
@@ -284,6 +346,8 @@ static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
 		if (err == -ENOSPC)
 			blk_mq_stop_hw_queue(hctx);
 		spin_unlock_irqrestore(&vblk->vqs[qid].lock, flags);
+		virtblk_unmap_data(req, vbr);
+		virtblk_cleanup_cmd(req);
 		switch (err) {
 		case -ENOSPC:
 			return BLK_STS_DEV_RESOURCE;
@@ -497,8 +561,14 @@ 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;
+	}
 
-	num_vqs = min_t(unsigned int, nr_cpu_ids, num_vqs);
+	num_vqs = min_t(unsigned int,
+			min_not_zero(num_request_queues, nr_cpu_ids),
+			num_vqs);
 
 	vblk->vqs = kmalloc_array(num_vqs, sizeof(*vblk->vqs), GFP_KERNEL);
 	if (!vblk->vqs)
@@ -624,7 +694,7 @@ cache_type_show(struct device *dev, struct device_attribute *attr, char *buf)
 	u8 writeback = virtblk_get_cache_mode(vblk->vdev);
 
 	BUG_ON(writeback >= ARRAY_SIZE(virtblk_cache_types));
-	return snprintf(buf, 40, "%s\n", virtblk_cache_types[writeback]);
+	return sysfs_emit(buf, "%s\n", virtblk_cache_types[writeback]);
 }
 
 static DEVICE_ATTR_RW(cache_type);
@@ -660,16 +730,6 @@ static const struct attribute_group *virtblk_attr_groups[] = {
 	NULL,
 };
 
-static int virtblk_init_request(struct blk_mq_tag_set *set, struct request *rq,
-		unsigned int hctx_idx, unsigned int numa_node)
-{
-	struct virtio_blk *vblk = set->driver_data;
-	struct virtblk_req *vbr = blk_mq_rq_to_pdu(rq);
-
-	sg_init_table(vbr->sg, vblk->sg_elems);
-	return 0;
-}
-
 static int virtblk_map_queues(struct blk_mq_tag_set *set)
 {
 	struct virtio_blk *vblk = set->driver_data;
@@ -682,7 +742,6 @@ static const struct blk_mq_ops virtio_mq_ops = {
 	.queue_rq	= virtio_queue_rq,
 	.commit_rqs	= virtio_commit_rqs,
 	.complete	= virtblk_request_done,
-	.init_request	= virtblk_init_request,
 	.map_queues	= virtblk_map_queues,
 };
 
@@ -762,7 +821,7 @@ static int virtblk_probe(struct virtio_device *vdev)
 	vblk->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
 	vblk->tag_set.cmd_size =
 		sizeof(struct virtblk_req) +
-		sizeof(struct scatterlist) * sg_elems;
+		sizeof(struct scatterlist) * VIRTIO_BLK_INLINE_SG_CNT;
 	vblk->tag_set.driver_data = vblk;
 	vblk->tag_set.nr_hw_queues = vblk->num_vqs;
 
@@ -990,6 +1049,7 @@ static struct virtio_driver virtio_blk = {
 	.feature_table_size		= ARRAY_SIZE(features),
 	.feature_table_legacy		= features_legacy,
 	.feature_table_size_legacy	= ARRAY_SIZE(features_legacy),
+	.suppress_used_validation	= true,
 	.driver.name			= KBUILD_MODNAME,
 	.driver.owner			= THIS_MODULE,
 	.id_table			= id_table,