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

Pull virtio updates from Michael Tsirkin:
 "Mostly fixes all over the place, a couple of cleanups"

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost: (32 commits)
  virtio_blk: Fix signedness bug in virtblk_prep_rq()
  vdpa_sim_net: should not drop the multicast/broadcast packet
  vdpasim: fix memory leak when freeing IOTLBs
  vdpa: conditionally fill max max queue pair for stats
  vdpa/vp_vdpa: fix kfree a wrong pointer in vp_vdpa_remove
  vduse: Validate vq_num in vduse_validate_config()
  tools/virtio: remove smp_read_barrier_depends()
  tools/virtio: remove stray characters
  vhost_vdpa: fix the crash in unmap a large memory
  virtio: Implementing attribute show with sysfs_emit
  virtio-crypto: fix memory leak in virtio_crypto_alg_skcipher_close_session()
  tools/virtio: Variable type completion
  vdpa_sim: fix vringh initialization in vdpasim_queue_ready()
  virtio_blk: use UINT_MAX instead of -1U
  vhost-vdpa: fix an iotlb memory leak
  vhost: fix range used in translate_desc()
  vringh: fix range used in iotlb_translate()
  vhost/vsock: Fix error handling in vhost_vsock_init()
  vdpa_sim: fix possible memory leak in vdpasim_net_init() and vdpasim_blk_init()
  tools: Delete the unneeded semicolon after curly braces
  ...

drivers/block/virtio_blk.c

@@ -315,22 +315,35 @@ static void virtio_commit_rqs(struct blk_mq_hw_ctx *hctx)
 		virtqueue_notify(vq->vq);
 }
 
+static blk_status_t virtblk_fail_to_queue(struct request *req, int rc)
+{
+	virtblk_cleanup_cmd(req);
+	switch (rc) {
+	case -ENOSPC:
+		return BLK_STS_DEV_RESOURCE;
+	case -ENOMEM:
+		return BLK_STS_RESOURCE;
+	default:
+		return BLK_STS_IOERR;
+	}
+}
+
 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;
+	int num;
 
 	status = virtblk_setup_cmd(vblk->vdev, req, vbr);
 	if (unlikely(status))
 		return status;
 
-	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;
-	}
+	num = virtblk_map_data(hctx, req, vbr);
+	if (unlikely(num < 0))
+		return virtblk_fail_to_queue(req, -ENOMEM);
+	vbr->sg_table.nents = num;
 
 	blk_mq_start_request(req);
 
@@ -364,15 +377,7 @@ static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
 			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;
-		case -ENOMEM:
-			return BLK_STS_RESOURCE;
-		default:
-			return BLK_STS_IOERR;
-		}
+		return virtblk_fail_to_queue(req, err);
 	}
 
 	if (bd->last && virtqueue_kick_prepare(vblk->vqs[qid].vq))
@@ -991,7 +996,7 @@ static int virtblk_probe(struct virtio_device *vdev)
 	blk_queue_max_segments(q, sg_elems);
 
 	/* No real sector limit. */
-	blk_queue_max_hw_sectors(q, -1U);
+	blk_queue_max_hw_sectors(q, UINT_MAX);
 
 	max_size = virtio_max_dma_size(vdev);
 

drivers/crypto/virtio/virtio_crypto_skcipher_algs.c

@@ -239,7 +239,8 @@ static int virtio_crypto_alg_skcipher_close_session(
 		pr_err("virtio_crypto: Close session failed status: %u, session_id: 0x%llx\n",
 			ctrl_status->status, destroy_session->session_id);
 
-		return -EINVAL;
+		err = -EINVAL;
+		goto out;
 	}
 
 	err = 0;

drivers/vdpa/mlx5/core/mlx5_vdpa.h

@@ -116,8 +116,9 @@ int mlx5_vdpa_create_mkey(struct mlx5_vdpa_dev *mvdev, u32 *mkey, u32 *in,
 			  int inlen);
 int mlx5_vdpa_destroy_mkey(struct mlx5_vdpa_dev *mvdev, u32 mkey);
 int mlx5_vdpa_handle_set_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb,
-			     bool *change_map);
-int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb);
+			     bool *change_map, unsigned int asid);
+int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb,
+			unsigned int asid);
 void mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev);
 
 #define mlx5_vdpa_warn(__dev, format, ...)                                                         \

drivers/vdpa/mlx5/core/mr.c

@@ -311,7 +311,6 @@ static int add_direct_chain(struct mlx5_vdpa_dev *mvdev, u64 start, u64 size, u8
 	u64 st;
 	u64 sz;
 	int err;
-	int i = 0;
 
 	st = start;
 	while (size) {
@@ -336,7 +335,6 @@ static int add_direct_chain(struct mlx5_vdpa_dev *mvdev, u64 start, u64 size, u8
 		mr->num_directs++;
 		mr->num_klms++;
 		st += sz;
-		i++;
 	}
 	list_splice_tail(&tmp, &mr->head);
 	return 0;
@@ -511,7 +509,8 @@ void mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev)
 	mutex_unlock(&mr->mkey_mtx);
 }
 
-static int _mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb)
+static int _mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev,
+				struct vhost_iotlb *iotlb, unsigned int asid)
 {
 	struct mlx5_vdpa_mr *mr = &mvdev->mr;
 	int err;
@@ -519,42 +518,49 @@ static int _mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb
 	if (mr->initialized)
 		return 0;
 
-	if (iotlb)
-		err = create_user_mr(mvdev, iotlb);
-	else
-		err = create_dma_mr(mvdev, mr);
+	if (mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP] == asid) {
+		if (iotlb)
+			err = create_user_mr(mvdev, iotlb);
+		else
+			err = create_dma_mr(mvdev, mr);
 
-	if (err)
-		return err;
+		if (err)
+			return err;
+	}
 
-	err = dup_iotlb(mvdev, iotlb);
-	if (err)
-		goto out_err;
+	if (mvdev->group2asid[MLX5_VDPA_CVQ_GROUP] == asid) {
+		err = dup_iotlb(mvdev, iotlb);
+		if (err)
+			goto out_err;
+	}
 
 	mr->initialized = true;
 	return 0;
 
 out_err:
-	if (iotlb)
-		destroy_user_mr(mvdev, mr);
-	else
-		destroy_dma_mr(mvdev, mr);
+	if (mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP] == asid) {
+		if (iotlb)
+			destroy_user_mr(mvdev, mr);
+		else
+			destroy_dma_mr(mvdev, mr);
+	}
 
 	return err;
 }
 
-int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb)
+int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb,
+			unsigned int asid)
 {
 	int err;
 
 	mutex_lock(&mvdev->mr.mkey_mtx);
-	err = _mlx5_vdpa_create_mr(mvdev, iotlb);
+	err = _mlx5_vdpa_create_mr(mvdev, iotlb, asid);
 	mutex_unlock(&mvdev->mr.mkey_mtx);
 	return err;
 }
 
 int mlx5_vdpa_handle_set_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb,
-			     bool *change_map)
+			     bool *change_map, unsigned int asid)
 {
 	struct mlx5_vdpa_mr *mr = &mvdev->mr;
 	int err = 0;
@@ -566,7 +572,7 @@ int mlx5_vdpa_handle_set_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *io
 		*change_map = true;
 	}
 	if (!*change_map)
-		err = _mlx5_vdpa_create_mr(mvdev, iotlb);
+		err = _mlx5_vdpa_create_mr(mvdev, iotlb, asid);
 	mutex_unlock(&mr->mkey_mtx);
 
 	return err;

drivers/vdpa/mlx5/net/mlx5_vnet.c

@@ -1468,11 +1468,13 @@ static int mlx5_vdpa_add_mac_vlan_rules(struct mlx5_vdpa_net *ndev, u8 *mac,
 	dmac_v = MLX5_ADDR_OF(fte_match_param, headers_v, outer_headers.dmac_47_16);
 	eth_broadcast_addr(dmac_c);
 	ether_addr_copy(dmac_v, mac);
-	MLX5_SET(fte_match_set_lyr_2_4, headers_c, cvlan_tag, 1);
+	if (ndev->mvdev.actual_features & BIT_ULL(VIRTIO_NET_F_CTRL_VLAN)) {
+		MLX5_SET(fte_match_set_lyr_2_4, headers_c, cvlan_tag, 1);
+		MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, first_vid);
+	}
 	if (tagged) {
 		MLX5_SET(fte_match_set_lyr_2_4, headers_v, cvlan_tag, 1);
-		MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, first_vid);
-		MLX5_SET(fte_match_set_lyr_2_4, headers_c, first_vid, vid);
+		MLX5_SET(fte_match_set_lyr_2_4, headers_v, first_vid, vid);
 	}
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 	dest.type = MLX5_FLOW_DESTINATION_TYPE_TIR;
@@ -1684,7 +1686,7 @@ static virtio_net_ctrl_ack handle_ctrl_mac(struct mlx5_vdpa_dev *mvdev, u8 cmd)
 
 		/* Need recreate the flow table entry, so that the packet could forward back
 		 */
-		mac_vlan_del(ndev, ndev->config.mac, 0, false);
+		mac_vlan_del(ndev, mac_back, 0, false);
 
 		if (mac_vlan_add(ndev, ndev->config.mac, 0, false)) {
 			mlx5_vdpa_warn(mvdev, "failed to insert forward rules, try to restore\n");
@@ -1821,6 +1823,9 @@ static virtio_net_ctrl_ack handle_ctrl_vlan(struct mlx5_vdpa_dev *mvdev, u8 cmd)
 	size_t read;
 	u16 id;
 
+	if (!(ndev->mvdev.actual_features & BIT_ULL(VIRTIO_NET_F_CTRL_VLAN)))
+		return status;
+
 	switch (cmd) {
 	case VIRTIO_NET_CTRL_VLAN_ADD:
 		read = vringh_iov_pull_iotlb(&cvq->vring, &cvq->riov, &vlan, sizeof(vlan));
@@ -2389,7 +2394,8 @@ static void restore_channels_info(struct mlx5_vdpa_net *ndev)
 	}
 }
 
-static int mlx5_vdpa_change_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb)
+static int mlx5_vdpa_change_map(struct mlx5_vdpa_dev *mvdev,
+				struct vhost_iotlb *iotlb, unsigned int asid)
 {
 	struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
 	int err;
@@ -2401,7 +2407,7 @@ static int mlx5_vdpa_change_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb
 
 	teardown_driver(ndev);
 	mlx5_vdpa_destroy_mr(mvdev);
-	err = mlx5_vdpa_create_mr(mvdev, iotlb);
+	err = mlx5_vdpa_create_mr(mvdev, iotlb, asid);
 	if (err)
 		goto err_mr;
 
@@ -2582,7 +2588,7 @@ static int mlx5_vdpa_reset(struct vdpa_device *vdev)
 	++mvdev->generation;
 
 	if (MLX5_CAP_GEN(mvdev->mdev, umem_uid_0)) {
-		if (mlx5_vdpa_create_mr(mvdev, NULL))
+		if (mlx5_vdpa_create_mr(mvdev, NULL, 0))
 			mlx5_vdpa_warn(mvdev, "create MR failed\n");
 	}
 	up_write(&ndev->reslock);
@@ -2618,41 +2624,20 @@ static u32 mlx5_vdpa_get_generation(struct vdpa_device *vdev)
 	return mvdev->generation;
 }
 
-static int set_map_control(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb)
-{
-	u64 start = 0ULL, last = 0ULL - 1;
-	struct vhost_iotlb_map *map;
-	int err = 0;
-
-	spin_lock(&mvdev->cvq.iommu_lock);
-	vhost_iotlb_reset(mvdev->cvq.iotlb);
-
-	for (map = vhost_iotlb_itree_first(iotlb, start, last); map;
-	     map = vhost_iotlb_itree_next(map, start, last)) {
-		err = vhost_iotlb_add_range(mvdev->cvq.iotlb, map->start,
-					    map->last, map->addr, map->perm);
-		if (err)
-			goto out;
-	}
-
-out:
-	spin_unlock(&mvdev->cvq.iommu_lock);
-	return err;
-}
-
-static int set_map_data(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb)
+static int set_map_data(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb,
+			unsigned int asid)
 {
 	bool change_map;
 	int err;
 
-	err = mlx5_vdpa_handle_set_map(mvdev, iotlb, &change_map);
+	err = mlx5_vdpa_handle_set_map(mvdev, iotlb, &change_map, asid);
 	if (err) {
 		mlx5_vdpa_warn(mvdev, "set map failed(%d)\n", err);
 		return err;
 	}
 
 	if (change_map)
-		err = mlx5_vdpa_change_map(mvdev, iotlb);
+		err = mlx5_vdpa_change_map(mvdev, iotlb, asid);
 
 	return err;
 }
@@ -2665,16 +2650,7 @@ static int mlx5_vdpa_set_map(struct vdpa_device *vdev, unsigned int asid,
 	int err = -EINVAL;
 
 	down_write(&ndev->reslock);
-	if (mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP] == asid) {
-		err = set_map_data(mvdev, iotlb);
-		if (err)
-			goto out;
-	}
-
-	if (mvdev->group2asid[MLX5_VDPA_CVQ_GROUP] == asid)
-		err = set_map_control(mvdev, iotlb);
-
-out:
+	err = set_map_data(mvdev, iotlb, asid);
 	up_write(&ndev->reslock);
 	return err;
 }
@@ -2840,8 +2816,8 @@ static int mlx5_vdpa_suspend(struct vdpa_device *vdev)
 	int i;
 
 	down_write(&ndev->reslock);
-	mlx5_notifier_unregister(mvdev->mdev, &ndev->nb);
 	ndev->nb_registered = false;
+	mlx5_notifier_unregister(mvdev->mdev, &ndev->nb);
 	flush_workqueue(ndev->mvdev.wq);
 	for (i = 0; i < ndev->cur_num_vqs; i++) {
 		mvq = &ndev->vqs[i];
@@ -3019,7 +2995,7 @@ static void update_carrier(struct work_struct *work)
 	else
 		ndev->config.status &= cpu_to_mlx5vdpa16(mvdev, ~VIRTIO_NET_S_LINK_UP);
 
-	if (ndev->config_cb.callback)
+	if (ndev->nb_registered && ndev->config_cb.callback)
 		ndev->config_cb.callback(ndev->config_cb.private);
 
 	kfree(wqent);
@@ -3036,21 +3012,13 @@ static int event_handler(struct notifier_block *nb, unsigned long event, void *p
 		switch (eqe->sub_type) {
 		case MLX5_PORT_CHANGE_SUBTYPE_DOWN:
 		case MLX5_PORT_CHANGE_SUBTYPE_ACTIVE:
-			down_read(&ndev->reslock);
-			if (!ndev->nb_registered) {
-				up_read(&ndev->reslock);
-				return NOTIFY_DONE;
-			}
 			wqent = kzalloc(sizeof(*wqent), GFP_ATOMIC);
-			if (!wqent) {
-				up_read(&ndev->reslock);
+			if (!wqent)
 				return NOTIFY_DONE;
-			}
 
 			wqent->mvdev = &ndev->mvdev;
 			INIT_WORK(&wqent->work, update_carrier);
 			queue_work(ndev->mvdev.wq, &wqent->work);
-			up_read(&ndev->reslock);
 			ret = NOTIFY_OK;
 			break;
 		default:
@@ -3185,7 +3153,7 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name,
 		goto err_mpfs;
 
 	if (MLX5_CAP_GEN(mvdev->mdev, umem_uid_0)) {
-		err = mlx5_vdpa_create_mr(mvdev, NULL);
+		err = mlx5_vdpa_create_mr(mvdev, NULL, 0);
 		if (err)
 			goto err_res;
 	}
@@ -3237,8 +3205,8 @@ static void mlx5_vdpa_dev_del(struct vdpa_mgmt_dev *v_mdev, struct vdpa_device *
 	struct workqueue_struct *wq;
 
 	if (ndev->nb_registered) {
-		mlx5_notifier_unregister(mvdev->mdev, &ndev->nb);
 		ndev->nb_registered = false;
+		mlx5_notifier_unregister(mvdev->mdev, &ndev->nb);
 	}
 	wq = mvdev->wq;
 	mvdev->wq = NULL;

drivers/vdpa/vdpa.c

@@ -855,7 +855,7 @@ static int vdpa_dev_net_config_fill(struct vdpa_device *vdev, struct sk_buff *ms
 
 	features_device = vdev->config->get_device_features(vdev);
 
-	if (nla_put_u64_64bit(msg, VDPA_ATTR_VDPA_DEV_SUPPORTED_FEATURES, features_device,
+	if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_FEATURES, features_device,
 			      VDPA_ATTR_PAD))
 		return -EMSGSIZE;
 
@@ -935,7 +935,6 @@ static int vdpa_fill_stats_rec(struct vdpa_device *vdev, struct sk_buff *msg,
 {
 	struct virtio_net_config config = {};
 	u64 features;
-	u16 max_vqp;
 	u8 status;
 	int err;
 
@@ -946,15 +945,15 @@ static int vdpa_fill_stats_rec(struct vdpa_device *vdev, struct sk_buff *msg,
 	}
 	vdpa_get_config_unlocked(vdev, 0, &config, sizeof(config));
 
-	max_vqp = __virtio16_to_cpu(true, config.max_virtqueue_pairs);
-	if (nla_put_u16(msg, VDPA_ATTR_DEV_NET_CFG_MAX_VQP, max_vqp))
-		return -EMSGSIZE;
-
 	features = vdev->config->get_driver_features(vdev);
 	if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_NEGOTIATED_FEATURES,
 			      features, VDPA_ATTR_PAD))
 		return -EMSGSIZE;
 
+	err = vdpa_dev_net_mq_config_fill(msg, features, &config);
+	if (err)
+		return err;
+
 	if (nla_put_u32(msg, VDPA_ATTR_DEV_QUEUE_INDEX, index))
 		return -EMSGSIZE;
 

drivers/vdpa/vdpa_sim/vdpa_sim.c

@@ -67,8 +67,7 @@ static void vdpasim_queue_ready(struct vdpasim *vdpasim, unsigned int idx)
 {
 	struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx];
 
-	vringh_init_iotlb(&vq->vring, vdpasim->dev_attr.supported_features,
-			  VDPASIM_QUEUE_MAX, false,
+	vringh_init_iotlb(&vq->vring, vdpasim->features, vq->num, false,
 			  (struct vring_desc *)(uintptr_t)vq->desc_addr,
 			  (struct vring_avail *)
 			  (uintptr_t)vq->driver_addr,
@@ -690,7 +689,9 @@ static void vdpasim_free(struct vdpa_device *vdpa)
 	}
 
 	kvfree(vdpasim->buffer);
-	vhost_iotlb_free(vdpasim->iommu);
+	for (i = 0; i < vdpasim->dev_attr.nas; i++)
+		vhost_iotlb_reset(&vdpasim->iommu[i]);
+	kfree(vdpasim->iommu);
 	kfree(vdpasim->vqs);
 	kfree(vdpasim->config);
 }

drivers/vdpa/vdpa_sim/vdpa_sim_blk.c

@@ -427,8 +427,10 @@ static int __init vdpasim_blk_init(void)
 	int ret;
 
 	ret = device_register(&vdpasim_blk_mgmtdev);
-	if (ret)
+	if (ret) {
+		put_device(&vdpasim_blk_mgmtdev);
 		return ret;
+	}
 
 	ret = vdpa_mgmtdev_register(&mgmt_dev);
 	if (ret)

drivers/vdpa/vdpa_sim/vdpa_sim_net.c

@@ -62,6 +62,9 @@ static bool receive_filter(struct vdpasim *vdpasim, size_t len)
 	if (len < ETH_ALEN + hdr_len)
 		return false;
 
+	if (is_broadcast_ether_addr(vdpasim->buffer + hdr_len) ||
+	    is_multicast_ether_addr(vdpasim->buffer + hdr_len))
+		return true;
 	if (!strncmp(vdpasim->buffer + hdr_len, vio_config->mac, ETH_ALEN))
 		return true;
 
@@ -305,8 +308,10 @@ static int __init vdpasim_net_init(void)
 	int ret;
 
 	ret = device_register(&vdpasim_net_mgmtdev);
-	if (ret)
+	if (ret) {
+		put_device(&vdpasim_net_mgmtdev);
 		return ret;
+	}
 
 	ret = vdpa_mgmtdev_register(&mgmt_dev);
 	if (ret)

drivers/vdpa/vdpa_user/vduse_dev.c

@@ -1440,6 +1440,9 @@ static bool vduse_validate_config(struct vduse_dev_config *config)
 	if (config->config_size > PAGE_SIZE)
 		return false;
 
+	if (config->vq_num > 0xffff)
+		return false;
+
 	if (!device_is_allowed(config->device_id))
 		return false;
 

drivers/vdpa/virtio_pci/vp_vdpa.c

@@ -647,7 +647,7 @@ static void vp_vdpa_remove(struct pci_dev *pdev)
 	mdev = vp_vdpa_mgtdev->mdev;
 	vp_modern_remove(mdev);
 	vdpa_mgmtdev_unregister(&vp_vdpa_mgtdev->mgtdev);
-	kfree(&vp_vdpa_mgtdev->mgtdev.id_table);
+	kfree(vp_vdpa_mgtdev->mgtdev.id_table);
 	kfree(mdev);
 	kfree(vp_vdpa_mgtdev);
 }

drivers/vhost/vdpa.c

@@ -65,6 +65,10 @@ static DEFINE_IDA(vhost_vdpa_ida);
 
 static dev_t vhost_vdpa_major;
 
+static void vhost_vdpa_iotlb_unmap(struct vhost_vdpa *v,
+				   struct vhost_iotlb *iotlb, u64 start,
+				   u64 last, u32 asid);
+
 static inline u32 iotlb_to_asid(struct vhost_iotlb *iotlb)
 {
 	struct vhost_vdpa_as *as = container_of(iotlb, struct
@@ -135,7 +139,7 @@ static int vhost_vdpa_remove_as(struct vhost_vdpa *v, u32 asid)
 		return -EINVAL;
 
 	hlist_del(&as->hash_link);
-	vhost_iotlb_reset(&as->iotlb);
+	vhost_vdpa_iotlb_unmap(v, &as->iotlb, 0ULL, 0ULL - 1, asid);
 	kfree(as);
 
 	return 0;
@@ -683,10 +687,20 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep,
 	mutex_unlock(&d->mutex);
 	return r;
 }
+static void vhost_vdpa_general_unmap(struct vhost_vdpa *v,
+				     struct vhost_iotlb_map *map, u32 asid)
+{
+	struct vdpa_device *vdpa = v->vdpa;
+	const struct vdpa_config_ops *ops = vdpa->config;
+	if (ops->dma_map) {
+		ops->dma_unmap(vdpa, asid, map->start, map->size);
+	} else if (ops->set_map == NULL) {
+		iommu_unmap(v->domain, map->start, map->size);
+	}
+}
 
-static void vhost_vdpa_pa_unmap(struct vhost_vdpa *v,
-				struct vhost_iotlb *iotlb,
-				u64 start, u64 last)
+static void vhost_vdpa_pa_unmap(struct vhost_vdpa *v, struct vhost_iotlb *iotlb,
+				u64 start, u64 last, u32 asid)
 {
 	struct vhost_dev *dev = &v->vdev;
 	struct vhost_iotlb_map *map;
@@ -703,13 +717,13 @@ static void vhost_vdpa_pa_unmap(struct vhost_vdpa *v,
 			unpin_user_page(page);
 		}
 		atomic64_sub(PFN_DOWN(map->size), &dev->mm->pinned_vm);
+		vhost_vdpa_general_unmap(v, map, asid);
 		vhost_iotlb_map_free(iotlb, map);
 	}
 }
 
-static void vhost_vdpa_va_unmap(struct vhost_vdpa *v,
-				struct vhost_iotlb *iotlb,
-				u64 start, u64 last)
+static void vhost_vdpa_va_unmap(struct vhost_vdpa *v, struct vhost_iotlb *iotlb,
+				u64 start, u64 last, u32 asid)
 {
 	struct vhost_iotlb_map *map;
 	struct vdpa_map_file *map_file;
@@ -718,20 +732,21 @@ static void vhost_vdpa_va_unmap(struct vhost_vdpa *v,
 		map_file = (struct vdpa_map_file *)map->opaque;
 		fput(map_file->file);
 		kfree(map_file);
+		vhost_vdpa_general_unmap(v, map, asid);
 		vhost_iotlb_map_free(iotlb, map);
 	}
 }
 
 static void vhost_vdpa_iotlb_unmap(struct vhost_vdpa *v,
-				   struct vhost_iotlb *iotlb,
-				   u64 start, u64 last)
+				   struct vhost_iotlb *iotlb, u64 start,
+				   u64 last, u32 asid)
 {
 	struct vdpa_device *vdpa = v->vdpa;
 
 	if (vdpa->use_va)
-		return vhost_vdpa_va_unmap(v, iotlb, start, last);
+		return vhost_vdpa_va_unmap(v, iotlb, start, last, asid);
 
-	return vhost_vdpa_pa_unmap(v, iotlb, start, last);
+	return vhost_vdpa_pa_unmap(v, iotlb, start, last, asid);
 }
 
 static int perm_to_iommu_flags(u32 perm)
@@ -798,17 +813,12 @@ static void vhost_vdpa_unmap(struct vhost_vdpa *v,
 	const struct vdpa_config_ops *ops = vdpa->config;
 	u32 asid = iotlb_to_asid(iotlb);
 
-	vhost_vdpa_iotlb_unmap(v, iotlb, iova, iova + size - 1);
+	vhost_vdpa_iotlb_unmap(v, iotlb, iova, iova + size - 1, asid);
 
-	if (ops->dma_map) {
-		ops->dma_unmap(vdpa, asid, iova, size);
-	} else if (ops->set_map) {
+	if (ops->set_map) {
 		if (!v->in_batch)
 			ops->set_map(vdpa, asid, iotlb);
-	} else {
-		iommu_unmap(v->domain, iova, size);
 	}
-
 	/* If we are in the middle of batch processing, delay the free
 	 * of AS until BATCH_END.
 	 */
@@ -1162,14 +1172,14 @@ static void vhost_vdpa_cleanup(struct vhost_vdpa *v)
 	struct vhost_vdpa_as *as;
 	u32 asid;
 
-	vhost_dev_cleanup(&v->vdev);
-	kfree(v->vdev.vqs);
-
 	for (asid = 0; asid < v->vdpa->nas; asid++) {
 		as = asid_to_as(v, asid);
 		if (as)
 			vhost_vdpa_remove_as(v, asid);
 	}
+
+	vhost_dev_cleanup(&v->vdev);
+	kfree(v->vdev.vqs);
 }
 
 static int vhost_vdpa_open(struct inode *inode, struct file *filep)

drivers/vhost/vhost.c

@@ -2053,7 +2053,7 @@ static int translate_desc(struct vhost_virtqueue *vq, u64 addr, u32 len,
 	struct vhost_dev *dev = vq->dev;
 	struct vhost_iotlb *umem = dev->iotlb ? dev->iotlb : dev->umem;
 	struct iovec *_iov;
-	u64 s = 0;
+	u64 s = 0, last = addr + len - 1;
 	int ret = 0;
 
 	while ((u64)len > s) {
@@ -2063,7 +2063,7 @@ static int translate_desc(struct vhost_virtqueue *vq, u64 addr, u32 len,
 			break;
 		}
 
-		map = vhost_iotlb_itree_first(umem, addr, addr + len - 1);
+		map = vhost_iotlb_itree_first(umem, addr, last);
 		if (map == NULL || map->start > addr) {
 			if (umem != dev->iotlb) {
 				ret = -EFAULT;

drivers/vhost/vringh.c

@@ -1102,7 +1102,7 @@ static int iotlb_translate(const struct vringh *vrh,
 	struct vhost_iotlb_map *map;
 	struct vhost_iotlb *iotlb = vrh->iotlb;
 	int ret = 0;
-	u64 s = 0;
+	u64 s = 0, last = addr + len - 1;
 
 	spin_lock(vrh->iotlb_lock);
 
@@ -1114,8 +1114,7 @@ static int iotlb_translate(const struct vringh *vrh,
 			break;
 		}
 
-		map = vhost_iotlb_itree_first(iotlb, addr,
-					      addr + len - 1);
+		map = vhost_iotlb_itree_first(iotlb, addr, last);
 		if (!map || map->start > addr) {
 			ret = -EINVAL;
 			break;

drivers/vhost/vsock.c

@@ -959,7 +959,14 @@ static int __init vhost_vsock_init(void)
 				  VSOCK_TRANSPORT_F_H2G);
 	if (ret < 0)
 		return ret;
-	return misc_register(&vhost_vsock_misc);
+
+	ret = misc_register(&vhost_vsock_misc);
+	if (ret) {
+		vsock_core_unregister(&vhost_transport.transport);
+		return ret;
+	}
+
+	return 0;
 };
 
 static void __exit vhost_vsock_exit(void)

drivers/virtio/virtio.c

@@ -15,7 +15,7 @@ static ssize_t device_show(struct device *_d,
 			   struct device_attribute *attr, char *buf)
 {
 	struct virtio_device *dev = dev_to_virtio(_d);
-	return sprintf(buf, "0x%04x\n", dev->id.device);
+	return sysfs_emit(buf, "0x%04x\n", dev->id.device);
 }
 static DEVICE_ATTR_RO(device);
 
@@ -23,7 +23,7 @@ static ssize_t vendor_show(struct device *_d,
 			   struct device_attribute *attr, char *buf)
 {
 	struct virtio_device *dev = dev_to_virtio(_d);
-	return sprintf(buf, "0x%04x\n", dev->id.vendor);
+	return sysfs_emit(buf, "0x%04x\n", dev->id.vendor);
 }
 static DEVICE_ATTR_RO(vendor);
 
@@ -31,7 +31,7 @@ static ssize_t status_show(struct device *_d,
 			   struct device_attribute *attr, char *buf)
 {
 	struct virtio_device *dev = dev_to_virtio(_d);
-	return sprintf(buf, "0x%08x\n", dev->config->get_status(dev));
+	return sysfs_emit(buf, "0x%08x\n", dev->config->get_status(dev));
 }
 static DEVICE_ATTR_RO(status);
 
@@ -39,7 +39,7 @@ static ssize_t modalias_show(struct device *_d,
 			     struct device_attribute *attr, char *buf)
 {
 	struct virtio_device *dev = dev_to_virtio(_d);
-	return sprintf(buf, "virtio:d%08Xv%08X\n",
+	return sysfs_emit(buf, "virtio:d%08Xv%08X\n",
 		       dev->id.device, dev->id.vendor);
 }
 static DEVICE_ATTR_RO(modalias);
@@ -54,9 +54,9 @@ static ssize_t features_show(struct device *_d,
 	/* We actually represent this as a bitstring, as it could be
 	 * arbitrary length in future. */
 	for (i = 0; i < sizeof(dev->features)*8; i++)
-		len += sprintf(buf+len, "%c",
+		len += sysfs_emit_at(buf, len, "%c",
 			       __virtio_test_bit(dev, i) ? '1' : '0');
-	len += sprintf(buf+len, "\n");
+	len += sysfs_emit_at(buf, len, "\n");
 	return len;
 }
 static DEVICE_ATTR_RO(features);

drivers/virtio/virtio_pci_modern.c

@@ -303,14 +303,14 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 	int err;
 
 	if (index >= vp_modern_get_num_queues(mdev))
-		return ERR_PTR(-ENOENT);
+		return ERR_PTR(-EINVAL);
 
 	/* Check if queue is either not available or already active. */
 	num = vp_modern_get_queue_size(mdev, index);
 	if (!num || vp_modern_get_queue_enable(mdev, index))
 		return ERR_PTR(-ENOENT);
 
-	if (num & (num - 1)) {
+	if (!is_power_of_2(num)) {
 		dev_warn(&vp_dev->pci_dev->dev, "bad queue size %u", num);
 		return ERR_PTR(-EINVAL);
 	}

drivers/virtio/virtio_ring.c

@@ -1052,7 +1052,7 @@ static int vring_alloc_queue_split(struct vring_virtqueue_split *vring_split,
 	dma_addr_t dma_addr;
 
 	/* We assume num is a power of 2. */
-	if (num & (num - 1)) {
+	if (!is_power_of_2(num)) {
 		dev_warn(&vdev->dev, "Bad virtqueue length %u\n", num);
 		return -EINVAL;
 	}

include/uapi/linux/vdpa.h

@@ -53,11 +53,9 @@ enum vdpa_attr {
 	VDPA_ATTR_DEV_VENDOR_ATTR_NAME,		/* string */
 	VDPA_ATTR_DEV_VENDOR_ATTR_VALUE,        /* u64 */
 
+	/* virtio features that are provisioned to the vDPA device */
 	VDPA_ATTR_DEV_FEATURES,                 /* u64 */
 
-	/* virtio features that are supported by the vDPA device */
-	VDPA_ATTR_VDPA_DEV_SUPPORTED_FEATURES,	/* u64 */
-
 	/* new attributes must be added above here */
 	VDPA_ATTR_MAX,
 };

tools/virtio/ringtest/main.h

@@ -140,25 +140,19 @@ static inline void busy_wait(void)
 #define smp_wmb() smp_release()
 #endif
 
-#ifdef __alpha__
-#define smp_read_barrier_depends() smp_acquire()
-#else
-#define smp_read_barrier_depends() do {} while(0)
-#endif
-
 static __always_inline
 void __read_once_size(const volatile void *p, void *res, int size)
 {
-        switch (size) {                                                 \
-        case 1: *(unsigned char *)res = *(volatile unsigned char *)p; break;              \
-        case 2: *(unsigned short *)res = *(volatile unsigned short *)p; break;            \
-        case 4: *(unsigned int *)res = *(volatile unsigned int *)p; break;            \
-        case 8: *(unsigned long long *)res = *(volatile unsigned long long *)p; break;            \
-        default:                                                        \
-                barrier();                                              \
-                __builtin_memcpy((void *)res, (const void *)p, size);   \
-                barrier();                                              \
-        }                                                               \
+	switch (size) {
+	case 1: *(unsigned char *)res = *(volatile unsigned char *)p; break;
+	case 2: *(unsigned short *)res = *(volatile unsigned short *)p; break;
+	case 4: *(unsigned int *)res = *(volatile unsigned int *)p; break;
+	case 8: *(unsigned long long *)res = *(volatile unsigned long long *)p; break;
+	default:
+		barrier();
+		__builtin_memcpy((void *)res, (const void *)p, size);
+		barrier();
+	}
 }
 
 static __always_inline void __write_once_size(volatile void *p, void *res, int size)
@@ -175,13 +169,22 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
 	}
 }
 
+#ifdef __alpha__
 #define READ_ONCE(x) \
 ({									\
 	union { typeof(x) __val; char __c[1]; } __u;			\
 	__read_once_size(&(x), __u.__c, sizeof(x));		\
-	smp_read_barrier_depends(); /* Enforce dependency ordering from x */ \
+	smp_mb(); /* Enforce dependency ordering from x */		\
+	__u.__val;							\
+})
+#else
+#define READ_ONCE(x)							\
+({									\
+	union { typeof(x) __val; char __c[1]; } __u;			\
+	__read_once_size(&(x), __u.__c, sizeof(x));			\
 	__u.__val;							\
 })
+#endif
 
 #define WRITE_ONCE(x, val) \
 ({							\

tools/virtio/virtio-trace/trace-agent-ctl.c

@@ -75,7 +75,7 @@ static int wait_order(int ctl_fd)
 
 		if (ret)
 			break;
-	};
+	}
 
 	return ret;
 

tools/virtio/virtio_test.c

@@ -173,7 +173,7 @@ static void run_test(struct vdev_info *dev, struct vq_info *vq,
 	long started = 0, completed = 0, next_reset = reset_n;
 	long completed_before, started_before;
 	int r, test = 1;
-	unsigned len;
+	unsigned int len;
 	long long spurious = 0;
 	const bool random_batch = batch == RANDOM_BATCH;
 

tools/virtio/vringh_test.c

@@ -308,6 +308,7 @@ static int parallel_test(u64 features,
 
 		gvdev.vdev.features = features;
 		INIT_LIST_HEAD(&gvdev.vdev.vqs);
+		spin_lock_init(&gvdev.vdev.vqs_list_lock);
 		gvdev.to_host_fd = to_host[1];
 		gvdev.notifies = 0;
 
@@ -455,6 +456,7 @@ int main(int argc, char *argv[])
 	getrange = getrange_iov;
 	vdev.features = 0;
 	INIT_LIST_HEAD(&vdev.vqs);
+	spin_lock_init(&vdev.vqs_list_lock);
 
 	while (argv[1]) {
 		if (strcmp(argv[1], "--indirect") == 0)