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

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

  vdpa/mlx5:
   - VHOST_BACKEND_F_ENABLE_AFTER_DRIVER_OK
   - new maintainer

  vdpa:
   - support for vq descriptor mappings
   - decouple reset of iotlb mapping from device reset

  and fixes, cleanups all over the place"

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost: (34 commits)
  vdpa_sim: implement .reset_map support
  vdpa/mlx5: implement .reset_map driver op
  vhost-vdpa: clean iotlb map during reset for older userspace
  vdpa: introduce .compat_reset operation callback
  vhost-vdpa: introduce IOTLB_PERSIST backend feature bit
  vhost-vdpa: reset vendor specific mapping to initial state in .release
  vdpa: introduce .reset_map operation callback
  virtio_pci: add check for common cfg size
  virtio-blk: fix implicit overflow on virtio_max_dma_size
  virtio_pci: add build offset check for the new common cfg items
  virtio: add definition of VIRTIO_F_NOTIF_CONFIG_DATA feature bit
  vduse: make vduse_class constant
  vhost-scsi: Spelling s/preceeding/preceding/g
  virtio: kdoc for struct virtio_pci_modern_device
  vdpa: Update sysfs ABI documentation
  MAINTAINERS: Add myself as mlx5_vdpa driver
  virtio-balloon: correct the comment of virtballoon_migratepage()
  mlx5_vdpa: offer VHOST_BACKEND_F_ENABLE_AFTER_DRIVER_OK
  vdpa/mlx5: Update cvq iotlb mapping on ASID change
  vdpa/mlx5: Make iotlb helper functions more generic
  ...

22 files changed, 544 insertions, 184 deletions

diff --git a/Documentation/ABI/testing/sysfs-bus-vdpa b/Documentation/ABI/testing/sysfs-bus-vdpa
index 28a6111202ba..4da53878bff6 100644
--- a/Documentation/ABI/testing/sysfs-bus-vdpa
+++ b/Documentation/ABI/testing/sysfs-bus-vdpa
@@ -1,4 +1,4 @@
-What:		/sys/bus/vdpa/driver_autoprobe
+What:		/sys/bus/vdpa/drivers_autoprobe
 Date:		March 2020
 Contact:	virtualization@lists.linux-foundation.org
 Description:
@@ -17,7 +17,7 @@ Description:
 		Writing a device name to this file will cause the kernel binds
 		devices to a compatible driver.
 
-		This can be useful when /sys/bus/vdpa/driver_autoprobe is
+		This can be useful when /sys/bus/vdpa/drivers_autoprobe is
 		disabled.
 
 What:		/sys/bus/vdpa/drivers/.../bind
diff --git a/MAINTAINERS b/MAINTAINERS
index 2cc111933d98..cdc42c5eda24 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -13790,6 +13790,12 @@ F:	drivers/infiniband/hw/mlx5/
 F:	include/linux/mlx5/
 F:	include/uapi/rdma/mlx5-abi.h
 
+MELLANOX MLX5 VDPA DRIVER
+M:	Dragos Tatulea <dtatulea@nvidia.com>
+L:	virtualization@lists.linux-foundation.org
+S:	Supported
+F:	drivers/vdpa/mlx5/
+
 MELLANOX MLXCPLD I2C AND MUX DRIVER
 M:	Vadim Pasternak <vadimp@nvidia.com>
 M:	Michael Shych <michaelsh@nvidia.com>
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 4689ac2e0c0e..d53d6aa8ee69 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -1311,6 +1311,7 @@ static int virtblk_probe(struct virtio_device *vdev)
 	u16 min_io_size;
 	u8 physical_block_exp, alignment_offset;
 	unsigned int queue_depth;
+	size_t max_dma_size;
 
 	if (!vdev->config->get) {
 		dev_err(&vdev->dev, "%s failure: config access disabled\n",
@@ -1409,7 +1410,8 @@ static int virtblk_probe(struct virtio_device *vdev)
 	/* No real sector limit. */
 	blk_queue_max_hw_sectors(q, UINT_MAX);
 
-	max_size = virtio_max_dma_size(vdev);
+	max_dma_size = virtio_max_dma_size(vdev);
+	max_size = max_dma_size > U32_MAX ? U32_MAX : max_dma_size;
 
 	/* Host can optionally specify maximum segment size and number of
 	 * segments. */
diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa.h b/drivers/vdpa/mlx5/core/mlx5_vdpa.h
index ca56242972b3..84547d998bcf 100644
--- a/drivers/vdpa/mlx5/core/mlx5_vdpa.h
+++ b/drivers/vdpa/mlx5/core/mlx5_vdpa.h
@@ -31,11 +31,9 @@ struct mlx5_vdpa_mr {
 	struct list_head head;
 	unsigned long num_directs;
 	unsigned long num_klms;
-	/* state of dvq mr */
-	bool initialized;
 
-	/* serialize mkey creation and destruction */
-	struct mutex mkey_mtx;
+	struct vhost_iotlb *iotlb;
+
 	bool user_mr;
 };
 
@@ -74,11 +72,12 @@ struct mlx5_vdpa_wq_ent {
 enum {
 	MLX5_VDPA_DATAVQ_GROUP,
 	MLX5_VDPA_CVQ_GROUP,
+	MLX5_VDPA_DATAVQ_DESC_GROUP,
 	MLX5_VDPA_NUMVQ_GROUPS
 };
 
 enum {
-	MLX5_VDPA_NUM_AS = MLX5_VDPA_NUMVQ_GROUPS
+	MLX5_VDPA_NUM_AS = 2
 };
 
 struct mlx5_vdpa_dev {
@@ -93,7 +92,9 @@ struct mlx5_vdpa_dev {
 	u16 max_idx;
 	u32 generation;
 
-	struct mlx5_vdpa_mr mr;
+	struct mlx5_vdpa_mr *mr[MLX5_VDPA_NUM_AS];
+	/* serialize mr access */
+	struct mutex mr_mtx;
 	struct mlx5_control_vq cvq;
 	struct workqueue_struct *wq;
 	unsigned int group2asid[MLX5_VDPA_NUMVQ_GROUPS];
@@ -114,12 +115,19 @@ void mlx5_vdpa_free_resources(struct mlx5_vdpa_dev *mvdev);
 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, 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);
-void mlx5_vdpa_destroy_mr_asid(struct mlx5_vdpa_dev *mvdev, unsigned int asid);
+struct mlx5_vdpa_mr *mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev,
+					 struct vhost_iotlb *iotlb);
+void mlx5_vdpa_destroy_mr_resources(struct mlx5_vdpa_dev *mvdev);
+void mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev,
+			  struct mlx5_vdpa_mr *mr);
+void mlx5_vdpa_update_mr(struct mlx5_vdpa_dev *mvdev,
+			 struct mlx5_vdpa_mr *mr,
+			 unsigned int asid);
+int mlx5_vdpa_update_cvq_iotlb(struct mlx5_vdpa_dev *mvdev,
+				struct vhost_iotlb *iotlb,
+				unsigned int asid);
+int mlx5_vdpa_create_dma_mr(struct mlx5_vdpa_dev *mvdev);
+int mlx5_vdpa_reset_mr(struct mlx5_vdpa_dev *mvdev, unsigned int asid);
 
 #define mlx5_vdpa_warn(__dev, format, ...)                                                         \
 	dev_warn((__dev)->mdev->device, "%s:%d:(pid %d) warning: " format, __func__, __LINE__,     \
diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c
index 5a1971fcd87b..2197c46e563a 100644
--- a/drivers/vdpa/mlx5/core/mr.c
+++ b/drivers/vdpa/mlx5/core/mr.c
@@ -301,10 +301,13 @@ static void unmap_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct
 	sg_free_table(&mr->sg_head);
 }
 
-static int add_direct_chain(struct mlx5_vdpa_dev *mvdev, u64 start, u64 size, u8 perm,
+static int add_direct_chain(struct mlx5_vdpa_dev *mvdev,
+			    struct mlx5_vdpa_mr *mr,
+			    u64 start,
+			    u64 size,
+			    u8 perm,
 			    struct vhost_iotlb *iotlb)
 {
-	struct mlx5_vdpa_mr *mr = &mvdev->mr;
 	struct mlx5_vdpa_direct_mr *dmr;
 	struct mlx5_vdpa_direct_mr *n;
 	LIST_HEAD(tmp);
@@ -354,9 +357,10 @@ err_alloc:
  * indirect memory key that provides access to the enitre address space given
  * by iotlb.
  */
-static int create_user_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb)
+static int create_user_mr(struct mlx5_vdpa_dev *mvdev,
+			  struct mlx5_vdpa_mr *mr,
+			  struct vhost_iotlb *iotlb)
 {
-	struct mlx5_vdpa_mr *mr = &mvdev->mr;
 	struct mlx5_vdpa_direct_mr *dmr;
 	struct mlx5_vdpa_direct_mr *n;
 	struct vhost_iotlb_map *map;
@@ -384,7 +388,7 @@ static int create_user_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb
 								       LOG_MAX_KLM_SIZE);
 					mr->num_klms += nnuls;
 				}
-				err = add_direct_chain(mvdev, ps, pe - ps, pperm, iotlb);
+				err = add_direct_chain(mvdev, mr, ps, pe - ps, pperm, iotlb);
 				if (err)
 					goto err_chain;
 			}
@@ -393,7 +397,7 @@ static int create_user_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb
 			pperm = map->perm;
 		}
 	}
-	err = add_direct_chain(mvdev, ps, pe - ps, pperm, iotlb);
+	err = add_direct_chain(mvdev, mr, ps, pe - ps, pperm, iotlb);
 	if (err)
 		goto err_chain;
 
@@ -450,20 +454,23 @@ static void destroy_dma_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_mr *mr)
 	mlx5_vdpa_destroy_mkey(mvdev, mr->mkey);
 }
 
-static int dup_iotlb(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *src)
+static int dup_iotlb(struct vhost_iotlb *dst, struct vhost_iotlb *src)
 {
 	struct vhost_iotlb_map *map;
 	u64 start = 0, last = ULLONG_MAX;
 	int err;
 
+	if (dst == src)
+		return -EINVAL;
+
 	if (!src) {
-		err = vhost_iotlb_add_range(mvdev->cvq.iotlb, start, last, start, VHOST_ACCESS_RW);
+		err = vhost_iotlb_add_range(dst, start, last, start, VHOST_ACCESS_RW);
 		return err;
 	}
 
 	for (map = vhost_iotlb_itree_first(src, start, last); map;
 		map = vhost_iotlb_itree_next(map, start, last)) {
-		err = vhost_iotlb_add_range(mvdev->cvq.iotlb, map->start, map->last,
+		err = vhost_iotlb_add_range(dst, map->start, map->last,
 					    map->addr, map->perm);
 		if (err)
 			return err;
@@ -471,9 +478,9 @@ static int dup_iotlb(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *src)
 	return 0;
 }
 
-static void prune_iotlb(struct mlx5_vdpa_dev *mvdev)
+static void prune_iotlb(struct vhost_iotlb *iotlb)
 {
-	vhost_iotlb_del_range(mvdev->cvq.iotlb, 0, ULLONG_MAX);
+	vhost_iotlb_del_range(iotlb, 0, ULLONG_MAX);
 }
 
 static void destroy_user_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_mr *mr)
@@ -489,133 +496,169 @@ static void destroy_user_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_mr *mr
 	}
 }
 
-static void _mlx5_vdpa_destroy_cvq_mr(struct mlx5_vdpa_dev *mvdev, unsigned int asid)
+static void _mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_mr *mr)
 {
-	if (mvdev->group2asid[MLX5_VDPA_CVQ_GROUP] != asid)
-		return;
+	if (mr->user_mr)
+		destroy_user_mr(mvdev, mr);
+	else
+		destroy_dma_mr(mvdev, mr);
 
-	prune_iotlb(mvdev);
+	vhost_iotlb_free(mr->iotlb);
 }
 
-static void _mlx5_vdpa_destroy_dvq_mr(struct mlx5_vdpa_dev *mvdev, unsigned int asid)
+void mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev,
+			  struct mlx5_vdpa_mr *mr)
 {
-	struct mlx5_vdpa_mr *mr = &mvdev->mr;
-
-	if (mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP] != asid)
+	if (!mr)
 		return;
 
-	if (!mr->initialized)
-		return;
+	mutex_lock(&mvdev->mr_mtx);
 
-	if (mr->user_mr)
-		destroy_user_mr(mvdev, mr);
-	else
-		destroy_dma_mr(mvdev, mr);
+	_mlx5_vdpa_destroy_mr(mvdev, mr);
+
+	for (int i = 0; i < MLX5_VDPA_NUM_AS; i++) {
+		if (mvdev->mr[i] == mr)
+			mvdev->mr[i] = NULL;
+	}
 
-	mr->initialized = false;
+	mutex_unlock(&mvdev->mr_mtx);
+
+	kfree(mr);
 }
 
-void mlx5_vdpa_destroy_mr_asid(struct mlx5_vdpa_dev *mvdev, unsigned int asid)
+void mlx5_vdpa_update_mr(struct mlx5_vdpa_dev *mvdev,
+			 struct mlx5_vdpa_mr *new_mr,
+			 unsigned int asid)
 {
-	struct mlx5_vdpa_mr *mr = &mvdev->mr;
+	struct mlx5_vdpa_mr *old_mr = mvdev->mr[asid];
 
-	mutex_lock(&mr->mkey_mtx);
+	mutex_lock(&mvdev->mr_mtx);
 
-	_mlx5_vdpa_destroy_dvq_mr(mvdev, asid);
-	_mlx5_vdpa_destroy_cvq_mr(mvdev, asid);
+	mvdev->mr[asid] = new_mr;
+	if (old_mr) {
+		_mlx5_vdpa_destroy_mr(mvdev, old_mr);
+		kfree(old_mr);
+	}
 
-	mutex_unlock(&mr->mkey_mtx);
-}
+	mutex_unlock(&mvdev->mr_mtx);
 
-void mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev)
-{
-	mlx5_vdpa_destroy_mr_asid(mvdev, mvdev->group2asid[MLX5_VDPA_CVQ_GROUP]);
-	mlx5_vdpa_destroy_mr_asid(mvdev, mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP]);
 }
 
-static int _mlx5_vdpa_create_cvq_mr(struct mlx5_vdpa_dev *mvdev,
-				    struct vhost_iotlb *iotlb,
-				    unsigned int asid)
+void mlx5_vdpa_destroy_mr_resources(struct mlx5_vdpa_dev *mvdev)
 {
-	if (mvdev->group2asid[MLX5_VDPA_CVQ_GROUP] != asid)
-		return 0;
+	for (int i = 0; i < MLX5_VDPA_NUM_AS; i++)
+		mlx5_vdpa_destroy_mr(mvdev, mvdev->mr[i]);
 
-	return dup_iotlb(mvdev, iotlb);
+	prune_iotlb(mvdev->cvq.iotlb);
 }
 
-static int _mlx5_vdpa_create_dvq_mr(struct mlx5_vdpa_dev *mvdev,
-				    struct vhost_iotlb *iotlb,
-				    unsigned int asid)
+static int _mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev,
+				struct mlx5_vdpa_mr *mr,
+				struct vhost_iotlb *iotlb)
 {
-	struct mlx5_vdpa_mr *mr = &mvdev->mr;
 	int err;
 
-	if (mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP] != asid)
-		return 0;
-
-	if (mr->initialized)
-		return 0;
-
 	if (iotlb)
-		err = create_user_mr(mvdev, iotlb);
+		err = create_user_mr(mvdev, mr, iotlb);
 	else
 		err = create_dma_mr(mvdev, mr);
 
 	if (err)
 		return err;
 
-	mr->initialized = true;
+	mr->iotlb = vhost_iotlb_alloc(0, 0);
+	if (!mr->iotlb) {
+		err = -ENOMEM;
+		goto err_mr;
+	}
+
+	err = dup_iotlb(mr->iotlb, iotlb);
+	if (err)
+		goto err_iotlb;
 
 	return 0;
+
+err_iotlb:
+	vhost_iotlb_free(mr->iotlb);
+
+err_mr:
+	if (iotlb)
+		destroy_user_mr(mvdev, mr);
+	else
+		destroy_dma_mr(mvdev, mr);
+
+	return err;
 }
 
-static int _mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev,
-				struct vhost_iotlb *iotlb, unsigned int asid)
+struct mlx5_vdpa_mr *mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev,
+					 struct vhost_iotlb *iotlb)
 {
+	struct mlx5_vdpa_mr *mr;
 	int err;
 
-	err = _mlx5_vdpa_create_dvq_mr(mvdev, iotlb, asid);
-	if (err)
-		return err;
+	mr = kzalloc(sizeof(*mr), GFP_KERNEL);
+	if (!mr)
+		return ERR_PTR(-ENOMEM);
+
+	mutex_lock(&mvdev->mr_mtx);
+	err = _mlx5_vdpa_create_mr(mvdev, mr, iotlb);
+	mutex_unlock(&mvdev->mr_mtx);
 
-	err = _mlx5_vdpa_create_cvq_mr(mvdev, iotlb, asid);
 	if (err)
 		goto out_err;
 
-	return 0;
+	return mr;
 
 out_err:
-	_mlx5_vdpa_destroy_dvq_mr(mvdev, asid);
-
-	return err;
+	kfree(mr);
+	return ERR_PTR(err);
 }
 
-int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb,
-			unsigned int asid)
+int mlx5_vdpa_update_cvq_iotlb(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, asid);
-	mutex_unlock(&mvdev->mr.mkey_mtx);
+	if (mvdev->group2asid[MLX5_VDPA_CVQ_GROUP] != asid)
+		return 0;
+
+	spin_lock(&mvdev->cvq.iommu_lock);
+
+	prune_iotlb(mvdev->cvq.iotlb);
+	err = dup_iotlb(mvdev->cvq.iotlb, iotlb);
+
+	spin_unlock(&mvdev->cvq.iommu_lock);
+
 	return err;
 }
 
-int mlx5_vdpa_handle_set_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb,
-			     bool *change_map, unsigned int asid)
+int mlx5_vdpa_create_dma_mr(struct mlx5_vdpa_dev *mvdev)
 {
-	struct mlx5_vdpa_mr *mr = &mvdev->mr;
-	int err = 0;
+	struct mlx5_vdpa_mr *mr;
+
+	mr = mlx5_vdpa_create_mr(mvdev, NULL);
+	if (IS_ERR(mr))
+		return PTR_ERR(mr);
 
-	*change_map = false;
-	mutex_lock(&mr->mkey_mtx);
-	if (mr->initialized) {
-		mlx5_vdpa_info(mvdev, "memory map update\n");
-		*change_map = true;
+	mlx5_vdpa_update_mr(mvdev, mr, 0);
+
+	return mlx5_vdpa_update_cvq_iotlb(mvdev, NULL, 0);
+}
+
+int mlx5_vdpa_reset_mr(struct mlx5_vdpa_dev *mvdev, unsigned int asid)
+{
+	if (asid >= MLX5_VDPA_NUM_AS)
+		return -EINVAL;
+
+	mlx5_vdpa_destroy_mr(mvdev, mvdev->mr[asid]);
+
+	if (asid == 0 && MLX5_CAP_GEN(mvdev->mdev, umem_uid_0)) {
+		if (mlx5_vdpa_create_dma_mr(mvdev))
+			mlx5_vdpa_warn(mvdev, "create DMA MR failed\n");
+	} else {
+		mlx5_vdpa_update_cvq_iotlb(mvdev, NULL, asid);
 	}
-	if (!*change_map)
-		err = _mlx5_vdpa_create_mr(mvdev, iotlb, asid);
-	mutex_unlock(&mr->mkey_mtx);
 
-	return err;
+	return 0;
 }
diff --git a/drivers/vdpa/mlx5/core/resources.c b/drivers/vdpa/mlx5/core/resources.c
index d5a59c9035fb..5c5a41b64bfc 100644
--- a/drivers/vdpa/mlx5/core/resources.c
+++ b/drivers/vdpa/mlx5/core/resources.c
@@ -256,7 +256,7 @@ int mlx5_vdpa_alloc_resources(struct mlx5_vdpa_dev *mvdev)
 		mlx5_vdpa_warn(mvdev, "resources already allocated\n");
 		return -EINVAL;
 	}
-	mutex_init(&mvdev->mr.mkey_mtx);
+	mutex_init(&mvdev->mr_mtx);
 	res->uar = mlx5_get_uars_page(mdev);
 	if (IS_ERR(res->uar)) {
 		err = PTR_ERR(res->uar);
@@ -301,7 +301,7 @@ err_pd:
 err_uctx:
 	mlx5_put_uars_page(mdev, res->uar);
 err_uars:
-	mutex_destroy(&mvdev->mr.mkey_mtx);
+	mutex_destroy(&mvdev->mr_mtx);
 	return err;
 }
 
@@ -318,6 +318,6 @@ void mlx5_vdpa_free_resources(struct mlx5_vdpa_dev *mvdev)
 	dealloc_pd(mvdev, res->pdn, res->uid);
 	destroy_uctx(mvdev, res->uid);
 	mlx5_put_uars_page(mvdev->mdev, res->uar);
-	mutex_destroy(&mvdev->mr.mkey_mtx);
+	mutex_destroy(&mvdev->mr_mtx);
 	res->valid = false;
 }
diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index 946488b8989f..12ac3397f39b 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -7,6 +7,7 @@
 #include <uapi/linux/virtio_net.h>
 #include <uapi/linux/virtio_ids.h>
 #include <uapi/linux/vdpa.h>
+#include <uapi/linux/vhost_types.h>
 #include <linux/virtio_config.h>
 #include <linux/auxiliary_bus.h>
 #include <linux/mlx5/cq.h>
@@ -861,6 +862,9 @@ static int create_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtque
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_virtio_net_q_in);
 	u32 out[MLX5_ST_SZ_DW(create_virtio_net_q_out)] = {};
+	struct mlx5_vdpa_dev *mvdev = &ndev->mvdev;
+	struct mlx5_vdpa_mr *vq_mr;
+	struct mlx5_vdpa_mr *vq_desc_mr;
 	void *obj_context;
 	u16 mlx_features;
 	void *cmd_hdr;
@@ -913,7 +917,14 @@ static int create_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtque
 	MLX5_SET64(virtio_q, vq_ctx, desc_addr, mvq->desc_addr);
 	MLX5_SET64(virtio_q, vq_ctx, used_addr, mvq->device_addr);
 	MLX5_SET64(virtio_q, vq_ctx, available_addr, mvq->driver_addr);
-	MLX5_SET(virtio_q, vq_ctx, virtio_q_mkey, ndev->mvdev.mr.mkey);
+	vq_mr = mvdev->mr[mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP]];
+	if (vq_mr)
+		MLX5_SET(virtio_q, vq_ctx, virtio_q_mkey, vq_mr->mkey);
+
+	vq_desc_mr = mvdev->mr[mvdev->group2asid[MLX5_VDPA_DATAVQ_DESC_GROUP]];
+	if (vq_desc_mr && MLX5_CAP_DEV_VDPA_EMULATION(mvdev->mdev, desc_group_mkey_supported))
+		MLX5_SET(virtio_q, vq_ctx, desc_group_mkey, vq_desc_mr->mkey);
+
 	MLX5_SET(virtio_q, vq_ctx, umem_1_id, mvq->umem1.id);
 	MLX5_SET(virtio_q, vq_ctx, umem_1_size, mvq->umem1.size);
 	MLX5_SET(virtio_q, vq_ctx, umem_2_id, mvq->umem2.id);
@@ -2301,6 +2312,16 @@ static u32 mlx5_vdpa_get_vq_group(struct vdpa_device *vdev, u16 idx)
 	return MLX5_VDPA_DATAVQ_GROUP;
 }
 
+static u32 mlx5_vdpa_get_vq_desc_group(struct vdpa_device *vdev, u16 idx)
+{
+	struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
+
+	if (is_ctrl_vq_idx(mvdev, idx))
+		return MLX5_VDPA_CVQ_GROUP;
+
+	return MLX5_VDPA_DATAVQ_DESC_GROUP;
+}
+
 static u64 mlx_to_vritio_features(u16 dev_features)
 {
 	u64 result = 0;
@@ -2539,6 +2560,11 @@ static void unregister_link_notifier(struct mlx5_vdpa_net *ndev)
 		flush_workqueue(ndev->mvdev.wq);
 }
 
+static u64 mlx5_vdpa_get_backend_features(const struct vdpa_device *vdpa)
+{
+	return BIT_ULL(VHOST_BACKEND_F_ENABLE_AFTER_DRIVER_OK);
+}
+
 static int mlx5_vdpa_set_driver_features(struct vdpa_device *vdev, u64 features)
 {
 	struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
@@ -2673,7 +2699,8 @@ 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, unsigned int asid)
+				struct mlx5_vdpa_mr *new_mr,
+				unsigned int asid)
 {
 	struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
 	int err;
@@ -2681,28 +2708,21 @@ static int mlx5_vdpa_change_map(struct mlx5_vdpa_dev *mvdev,
 	suspend_vqs(ndev);
 	err = save_channels_info(ndev);
 	if (err)
-		goto err_mr;
+		return err;
 
 	teardown_driver(ndev);
-	mlx5_vdpa_destroy_mr_asid(mvdev, asid);
-	err = mlx5_vdpa_create_mr(mvdev, iotlb, asid);
-	if (err)
-		goto err_mr;
+
+	mlx5_vdpa_update_mr(mvdev, new_mr, asid);
 
 	if (!(mvdev->status & VIRTIO_CONFIG_S_DRIVER_OK) || mvdev->suspended)
-		goto err_mr;
+		return 0;
 
 	restore_channels_info(ndev);
 	err = setup_driver(mvdev);
 	if (err)
-		goto err_setup;
+		return err;
 
 	return 0;
-
-err_setup:
-	mlx5_vdpa_destroy_mr_asid(mvdev, asid);
-err_mr:
-	return err;
 }
 
 /* reslock must be held for this function */
@@ -2841,7 +2861,7 @@ static void mlx5_vdpa_set_status(struct vdpa_device *vdev, u8 status)
 err_driver:
 	unregister_link_notifier(ndev);
 err_setup:
-	mlx5_vdpa_destroy_mr(&ndev->mvdev);
+	mlx5_vdpa_destroy_mr_resources(&ndev->mvdev);
 	ndev->mvdev.status |= VIRTIO_CONFIG_S_FAILED;
 err_clear:
 	up_write(&ndev->reslock);
@@ -2856,7 +2876,7 @@ static void init_group_to_asid_map(struct mlx5_vdpa_dev *mvdev)
 		mvdev->group2asid[i] = 0;
 }
 
-static int mlx5_vdpa_reset(struct vdpa_device *vdev)
+static int mlx5_vdpa_compat_reset(struct vdpa_device *vdev, u32 flags)
 {
 	struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
 	struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
@@ -2868,7 +2888,8 @@ static int mlx5_vdpa_reset(struct vdpa_device *vdev)
 	unregister_link_notifier(ndev);
 	teardown_driver(ndev);
 	clear_vqs_ready(ndev);
-	mlx5_vdpa_destroy_mr(&ndev->mvdev);
+	if (flags & VDPA_RESET_F_CLEAN_MAP)
+		mlx5_vdpa_destroy_mr_resources(&ndev->mvdev);
 	ndev->mvdev.status = 0;
 	ndev->mvdev.suspended = false;
 	ndev->cur_num_vqs = 0;
@@ -2879,8 +2900,9 @@ static int mlx5_vdpa_reset(struct vdpa_device *vdev)
 	init_group_to_asid_map(mvdev);
 	++mvdev->generation;
 
-	if (MLX5_CAP_GEN(mvdev->mdev, umem_uid_0)) {
-		if (mlx5_vdpa_create_mr(mvdev, NULL, 0))
+	if ((flags & VDPA_RESET_F_CLEAN_MAP) &&
+	    MLX5_CAP_GEN(mvdev->mdev, umem_uid_0)) {
+		if (mlx5_vdpa_create_dma_mr(mvdev))
 			mlx5_vdpa_warn(mvdev, "create MR failed\n");
 	}
 	up_write(&ndev->reslock);
@@ -2888,6 +2910,11 @@ static int mlx5_vdpa_reset(struct vdpa_device *vdev)
 	return 0;
 }
 
+static int mlx5_vdpa_reset(struct vdpa_device *vdev)
+{
+	return mlx5_vdpa_compat_reset(vdev, 0);
+}
+
 static size_t mlx5_vdpa_get_config_size(struct vdpa_device *vdev)
 {
 	return sizeof(struct virtio_net_config);
@@ -2919,18 +2946,38 @@ static u32 mlx5_vdpa_get_generation(struct vdpa_device *vdev)
 static int set_map_data(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb,
 			unsigned int asid)
 {
-	bool change_map;
+	struct mlx5_vdpa_mr *new_mr;
 	int err;
 
-	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 (asid >= MLX5_VDPA_NUM_AS)
+		return -EINVAL;
+
+	if (vhost_iotlb_itree_first(iotlb, 0, U64_MAX)) {
+		new_mr = mlx5_vdpa_create_mr(mvdev, iotlb);
+		if (IS_ERR(new_mr)) {
+			err = PTR_ERR(new_mr);
+			mlx5_vdpa_warn(mvdev, "create map failed(%d)\n", err);
+			return err;
+		}
+	} else {
+		/* Empty iotlbs don't have an mr but will clear the previous mr. */
+		new_mr = NULL;
+	}
+
+	if (!mvdev->mr[asid]) {
+		mlx5_vdpa_update_mr(mvdev, new_mr, asid);
+	} else {
+		err = mlx5_vdpa_change_map(mvdev, new_mr, asid);
+		if (err) {
+			mlx5_vdpa_warn(mvdev, "change map failed(%d)\n", err);
+			goto out_err;
+		}
 	}
 
-	if (change_map)
-		err = mlx5_vdpa_change_map(mvdev, iotlb, asid);
+	return mlx5_vdpa_update_cvq_iotlb(mvdev, iotlb, asid);
 
+out_err:
+	mlx5_vdpa_destroy_mr(mvdev, new_mr);
 	return err;
 }
 
@@ -2947,6 +2994,18 @@ static int mlx5_vdpa_set_map(struct vdpa_device *vdev, unsigned int asid,
 	return err;
 }
 
+static int mlx5_vdpa_reset_map(struct vdpa_device *vdev, unsigned int asid)
+{
+	struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
+	struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
+	int err;
+
+	down_write(&ndev->reslock);
+	err = mlx5_vdpa_reset_mr(mvdev, asid);
+	up_write(&ndev->reslock);
+	return err;
+}
+
 static struct device *mlx5_get_vq_dma_dev(struct vdpa_device *vdev, u16 idx)
 {
 	struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
@@ -2985,7 +3044,7 @@ static void mlx5_vdpa_free(struct vdpa_device *vdev)
 	ndev = to_mlx5_vdpa_ndev(mvdev);
 
 	free_resources(ndev);
-	mlx5_vdpa_destroy_mr(mvdev);
+	mlx5_vdpa_destroy_mr_resources(mvdev);
 	if (!is_zero_ether_addr(ndev->config.mac)) {
 		pfmdev = pci_get_drvdata(pci_physfn(mvdev->mdev->pdev));
 		mlx5_mpfs_del_mac(pfmdev, ndev->config.mac);
@@ -3169,12 +3228,19 @@ static int mlx5_set_group_asid(struct vdpa_device *vdev, u32 group,
 			       unsigned int asid)
 {
 	struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
+	int err = 0;
 
 	if (group >= MLX5_VDPA_NUMVQ_GROUPS)
 		return -EINVAL;
 
 	mvdev->group2asid[group] = asid;
-	return 0;
+
+	mutex_lock(&mvdev->mr_mtx);
+	if (group == MLX5_VDPA_CVQ_GROUP && mvdev->mr[asid])
+		err = mlx5_vdpa_update_cvq_iotlb(mvdev, mvdev->mr[asid]->iotlb, asid);
+	mutex_unlock(&mvdev->mr_mtx);
+
+	return err;
 }
 
 static const struct vdpa_config_ops mlx5_vdpa_ops = {
@@ -3191,7 +3257,9 @@ static const struct vdpa_config_ops mlx5_vdpa_ops = {
 	.get_vq_irq = mlx5_get_vq_irq,
 	.get_vq_align = mlx5_vdpa_get_vq_align,
 	.get_vq_group = mlx5_vdpa_get_vq_group,
+	.get_vq_desc_group = mlx5_vdpa_get_vq_desc_group, /* Op disabled if not supported. */
 	.get_device_features = mlx5_vdpa_get_device_features,
+	.get_backend_features = mlx5_vdpa_get_backend_features,
 	.set_driver_features = mlx5_vdpa_set_driver_features,
 	.get_driver_features = mlx5_vdpa_get_driver_features,
 	.set_config_cb = mlx5_vdpa_set_config_cb,
@@ -3201,11 +3269,13 @@ static const struct vdpa_config_ops mlx5_vdpa_ops = {
 	.get_status = mlx5_vdpa_get_status,
 	.set_status = mlx5_vdpa_set_status,
 	.reset = mlx5_vdpa_reset,
+	.compat_reset = mlx5_vdpa_compat_reset,
 	.get_config_size = mlx5_vdpa_get_config_size,
 	.get_config = mlx5_vdpa_get_config,
 	.set_config = mlx5_vdpa_set_config,
 	.get_generation = mlx5_vdpa_get_generation,
 	.set_map = mlx5_vdpa_set_map,
+	.reset_map = mlx5_vdpa_reset_map,
 	.set_group_asid = mlx5_set_group_asid,
 	.get_vq_dma_dev = mlx5_get_vq_dma_dev,
 	.free = mlx5_vdpa_free,
@@ -3289,6 +3359,7 @@ struct mlx5_vdpa_mgmtdev {
 	struct vdpa_mgmt_dev mgtdev;
 	struct mlx5_adev *madev;
 	struct mlx5_vdpa_net *ndev;
+	struct vdpa_config_ops vdpa_ops;
 };
 
 static int config_func_mtu(struct mlx5_core_dev *mdev, u16 mtu)
@@ -3402,7 +3473,7 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name,
 		max_vqs = 2;
 	}
 
-	ndev = vdpa_alloc_device(struct mlx5_vdpa_net, mvdev.vdev, mdev->device, &mlx5_vdpa_ops,
+	ndev = vdpa_alloc_device(struct mlx5_vdpa_net, mvdev.vdev, mdev->device, &mgtdev->vdpa_ops,
 				 MLX5_VDPA_NUMVQ_GROUPS, MLX5_VDPA_NUM_AS, name, false);
 	if (IS_ERR(ndev))
 		return PTR_ERR(ndev);
@@ -3485,7 +3556,7 @@ 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, 0);
+		err = mlx5_vdpa_create_dma_mr(mvdev);
 		if (err)
 			goto err_res;
 	}
@@ -3515,7 +3586,7 @@ err_reg:
 err_res2:
 	free_resources(ndev);
 err_mr:
-	mlx5_vdpa_destroy_mr(mvdev);
+	mlx5_vdpa_destroy_mr_resources(mvdev);
 err_res:
 	mlx5_vdpa_free_resources(&ndev->mvdev);
 err_mpfs:
@@ -3575,6 +3646,10 @@ static int mlx5v_probe(struct auxiliary_device *adev,
 		MLX5_CAP_DEV_VDPA_EMULATION(mdev, max_num_virtio_queues) + 1;
 	mgtdev->mgtdev.supported_features = get_supported_features(mdev);
 	mgtdev->madev = madev;
+	mgtdev->vdpa_ops = mlx5_vdpa_ops;
+
+	if (!MLX5_CAP_DEV_VDPA_EMULATION(mdev, desc_group_mkey_supported))
+		mgtdev->vdpa_ops.get_vq_desc_group = NULL;
 
 	err = vdpa_mgmtdev_register(&mgtdev->mgtdev);
 	if (err)
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c
index 76d41058add9..be2925d0d283 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c
@@ -139,7 +139,7 @@ static void vdpasim_vq_reset(struct vdpasim *vdpasim,
 	vq->vring.notify = NULL;
 }
 
-static void vdpasim_do_reset(struct vdpasim *vdpasim)
+static void vdpasim_do_reset(struct vdpasim *vdpasim, u32 flags)
 {
 	int i;
 
@@ -151,11 +151,13 @@ static void vdpasim_do_reset(struct vdpasim *vdpasim)
 				 &vdpasim->iommu_lock);
 	}
 
-	for (i = 0; i < vdpasim->dev_attr.nas; i++) {
-		vhost_iotlb_reset(&vdpasim->iommu[i]);
-		vhost_iotlb_add_range(&vdpasim->iommu[i], 0, ULONG_MAX,
-				      0, VHOST_MAP_RW);
-		vdpasim->iommu_pt[i] = true;
+	if (flags & VDPA_RESET_F_CLEAN_MAP) {
+		for (i = 0; i < vdpasim->dev_attr.nas; i++) {
+			vhost_iotlb_reset(&vdpasim->iommu[i]);
+			vhost_iotlb_add_range(&vdpasim->iommu[i], 0, ULONG_MAX,
+					      0, VHOST_MAP_RW);
+			vdpasim->iommu_pt[i] = true;
+		}
 	}
 
 	vdpasim->running = true;
@@ -259,8 +261,12 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr,
 	if (!vdpasim->iommu_pt)
 		goto err_iommu;
 
-	for (i = 0; i