Add vduse live migration features

new file mode 100644
index 000000000000..3d238e09c8f8
@@ -0,0 +1,85 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _LINUX_STDDEF_H
+#define _LINUX_STDDEF_H
+
+#ifdef __KERNEL__
+#include <linux/compiler_types.h>
+#endif
+
+#ifndef __always_inline
+#define __always_inline inline
+#endif
+
+/* Not all C++ standards support type declarations inside an anonymous union */
+#ifndef __cplusplus
+#define __struct_group_tag(TAG)		TAG
+#else
+#define __struct_group_tag(TAG)
+#endif
+
+/**
+ * __struct_group() - Create a mirrored named and anonyomous struct
+ *
+ * @TAG: The tag name for the named sub-struct (usually empty)
+ * @NAME: The identifier name of the mirrored sub-struct
+ * @ATTRS: Any struct attributes (usually empty)
+ * @MEMBERS: The member declarations for the mirrored structs
+ *
+ * Used to create an anonymous union of two structs with identical layout
+ * and size: one anonymous and one named. The former's members can be used
+ * normally without sub-struct naming, and the latter can be used to
+ * reason about the start, end, and size of the group of struct members.
+ * The named struct can also be explicitly tagged for layer reuse (C only),
+ * as well as both having struct attributes appended.
+ */
+#define __struct_group(TAG, NAME, ATTRS, MEMBERS...) \
+	union { \
+		struct { MEMBERS } ATTRS; \
+		struct __struct_group_tag(TAG) { MEMBERS } ATTRS NAME; \
+	} ATTRS
+
+#ifdef __cplusplus
+/* sizeof(struct{}) is 1 in C++, not 0, can't use C version of the macro. */
+#define __DECLARE_FLEX_ARRAY(T, member)	\
+	T member[0]
+#else
+/**
+ * __DECLARE_FLEX_ARRAY() - Declare a flexible array usable in a union
+ *
+ * @TYPE: The type of each flexible array element
+ * @NAME: The name of the flexible array member
+ *
+ * In order to have a flexible array member in a union or alone in a
+ * struct, it needs to be wrapped in an anonymous struct with at least 1
+ * named member, but that member can be empty.
+ */
+#define __DECLARE_FLEX_ARRAY(TYPE, NAME)	\
+	struct { \
+		struct { } __empty_ ## NAME; \
+		TYPE NAME[]; \
+	}
+#endif
+
+#ifndef __counted_by
+#define __counted_by(m)
+#endif
+
+#ifndef __counted_by_le
+#define __counted_by_le(m)
+#endif
+
+#ifndef __counted_by_be
+#define __counted_by_be(m)
+#endif
+
+#ifndef __counted_by_ptr
+#define __counted_by_ptr(m)
+#endif
+
+#ifdef __KERNEL__
+#define __kernel_nonstring	__nonstring
+#else
+#define __kernel_nonstring
+#endif
+
+#endif /* _LINUX_STDDEF_H */

216 lines not on this page · raw message

149 lines not on this page · raw message

index f2c275a7d77e..e5e69d11cb65 100644
@@ -11,6 +11,16 @@
 #include "iotlb.h"
 #include "vhost.h"
 
+struct iotlb {
+	rte_rwlock_t			pending_lock;
+	struct vhost_iotlb_entry	*pool;
+	TAILQ_HEAD(, vhost_iotlb_entry)	list;
+	TAILQ_HEAD(, vhost_iotlb_entry)	pending_list;
+	int				cache_nr;
+	rte_spinlock_t			free_lock;
+	SLIST_HEAD(, vhost_iotlb_entry)	free_list;
+};
+
 struct vhost_iotlb_entry {
 	TAILQ_ENTRY(vhost_iotlb_entry) next;
 	SLIST_ENTRY(vhost_iotlb_entry) next_free;

@@ -85,78 +95,78 @@ vhost_user_iotlb_clear_dump(struct virtio_net *dev, struct vhost_iotlb_entry *no
 }
 
 static struct vhost_iotlb_entry *
-vhost_user_iotlb_pool_get(struct virtio_net *dev)
+vhost_user_iotlb_pool_get(struct virtio_net *dev, int asid)
 {
 	struct vhost_iotlb_entry *node;
 
-	rte_spinlock_lock(&dev->iotlb_free_lock);
-	node = SLIST_FIRST(&dev->iotlb_free_list);
+	rte_spinlock_lock(&dev->iotlb[asid]->free_lock);
+	node = SLIST_FIRST(&dev->iotlb[asid]->free_list);
 	if (node != NULL)
-		SLIST_REMOVE_HEAD(&dev->iotlb_free_list, next_free);
-	rte_spinlock_unlock(&dev->iotlb_free_lock);
+		SLIST_REMOVE_HEAD(&dev->iotlb[asid]->free_list, next_free);
+	rte_spinlock_unlock(&dev->iotlb[asid]->free_lock);
 	return node;
 }
 
 static void
-vhost_user_iotlb_pool_put(struct virtio_net *dev, struct vhost_iotlb_entry *node)
+vhost_user_iotlb_pool_put(struct virtio_net *dev, int asid, struct vhost_iotlb_entry *node)
 {
-	rte_spinlock_lock(&dev->iotlb_free_lock);
-	SLIST_INSERT_HEAD(&dev->iotlb_free_list, node, next_free);
-	rte_spinlock_unlock(&dev->iotlb_free_lock);
+	rte_spinlock_lock(&dev->iotlb[asid]->free_lock);
+	SLIST_INSERT_HEAD(&dev->iotlb[asid]->free_list, node, next_free);
+	rte_spinlock_unlock(&dev->iotlb[asid]->free_lock);
 }
 
 static void
-vhost_user_iotlb_cache_random_evict(struct virtio_net *dev);
+vhost_user_iotlb_cache_random_evict(struct virtio_net *dev, int asid);
 
 static void
-vhost_user_iotlb_pending_remove_all(struct virtio_net *dev)
+vhost_user_iotlb_pending_remove_all(struct virtio_net *dev, int asid)
 {
 	struct vhost_iotlb_entry *node, *temp_node;
 
-	rte_rwlock_write_lock(&dev->iotlb_pending_lock);
+	rte_rwlock_write_lock(&dev->iotlb[asid]->pending_lock);
 
-	RTE_TAILQ_FOREACH_SAFE(node, &dev->iotlb_pending_list, next, temp_node) {
-		TAILQ_REMOVE(&dev->iotlb_pending_list, node, next);
-		vhost_user_iotlb_pool_put(dev, node);
+	RTE_TAILQ_FOREACH_SAFE(node, &dev->iotlb[asid]->pending_list, next, temp_node) {
+		TAILQ_REMOVE(&dev->iotlb[asid]->pending_list, node, next);
+		vhost_user_iotlb_pool_put(dev, asid, node);
 	}
 
-	rte_rwlock_write_unlock(&dev->iotlb_pending_lock);
+	rte_rwlock_write_unlock(&dev->iotlb[asid]->pending_lock);
 }
 
 bool
-vhost_user_iotlb_pending_miss(struct virtio_net *dev, uint64_t iova, uint8_t perm)
+vhost_user_iotlb_pending_miss(struct virtio_net *dev, int asid, uint64_t iova, uint8_t perm)
 {
 	struct vhost_iotlb_entry *node;
 	bool found = false;
 
-	rte_rwlock_read_lock(&dev->iotlb_pending_lock);
+	rte_rwlock_read_lock(&dev->iotlb[asid]->pending_lock);
 
-	TAILQ_FOREACH(node, &dev->iotlb_pending_list, next) {
+	TAILQ_FOREACH(node, &dev->iotlb[asid]->pending_list, next) {
 		if ((node->iova == iova) && (node->perm == perm)) {
 			found = true;
 			break;
 		}
 	}
 
-	rte_rwlock_read_unlock(&dev->iotlb_pending_lock);
+	rte_rwlock_read_unlock(&dev->iotlb[asid]->pending_lock);
 
 	return found;
 }
 
 void
-vhost_user_iotlb_pending_insert(struct virtio_net *dev, uint64_t iova, uint8_t perm)
+vhost_user_iotlb_pending_insert(struct virtio_net *dev, int asid, uint64_t iova, uint8_t perm)
 {
 	struct vhost_iotlb_entry *node;
 
-	node = vhost_user_iotlb_pool_get(dev);
+	node = vhost_user_iotlb_pool_get(dev, asid);
 	if (node == NULL) {
 		VHOST_CONFIG_LOG(dev->ifname, DEBUG,
 			"IOTLB pool empty, clear entries for pending insertion");
-		if (!TAILQ_EMPTY(&dev->iotlb_pending_list))
-			vhost_user_iotlb_pending_remove_all(dev);
+		if (!TAILQ_EMPTY(&dev->iotlb[asid]->pending_list))
+			vhost_user_iotlb_pending_remove_all(dev, asid);
 		else
-			vhost_user_iotlb_cache_random_evict(dev);
-		node = vhost_user_iotlb_pool_get(dev);
+			vhost_user_iotlb_cache_random_evict(dev, asid);
+		node = vhost_user_iotlb_pool_get(dev, asid);
 		if (node == NULL) {
 			VHOST_CONFIG_LOG(dev->ifname, ERR,
 				"IOTLB pool still empty, pending insertion failure");

@@ -167,21 +177,22 @@ vhost_user_iotlb_pending_insert(struct virtio_net *dev, uint64_t iova, uint8_t p
 	node->iova = iova;
 	node->perm = perm;
 
-	rte_rwlock_write_lock(&dev->iotlb_pending_lock);
+	rte_rwlock_write_lock(&dev->iotlb[asid]->pending_lock);
 
-	TAILQ_INSERT_TAIL(&dev->iotlb_pending_list, node, next);
+	TAILQ_INSERT_TAIL(&dev->iotlb[asid]->pending_list, node, next);
 
-	rte_rwlock_write_unlock(&dev->iotlb_pending_lock);
+	rte_rwlock_write_unlock(&dev->iotlb[asid]->pending_lock);
 }
 
 void
-vhost_user_iotlb_pending_remove(struct virtio_net *dev, uint64_t iova, uint64_t size, uint8_t perm)
+vhost_user_iotlb_pending_remove(struct virtio_net *dev, int asid,
+				uint64_t iova, uint64_t size, uint8_t perm)
 {
 	struct vhost_iotlb_entry *node, *temp_node;
 
-	rte_rwlock_write_lock(&dev->iotlb_pending_lock);
+	rte_rwlock_write_lock(&dev->iotlb[asid]->pending_lock);
 
-	RTE_TAILQ_FOREACH_SAFE(node, &dev->iotlb_pending_list, next,
+	RTE_TAILQ_FOREACH_SAFE(node, &dev->iotlb[asid]->pending_list, next,
 				temp_node) {
 		if (node->iova < iova)
 			continue;

@@ -189,53 +200,53 @@ vhost_user_iotlb_pending_remove(struct virtio_net *dev, uint64_t iova, uint64_t
 			continue;
 		if ((node->perm & perm) != node->perm)
 			continue;
-		TAILQ_REMOVE(&dev->iotlb_pending_list, node, next);
-		vhost_user_iotlb_pool_put(dev, node);
+		TAILQ_REMOVE(&dev->iotlb[asid]->pending_list, node, next);
+		vhost_user_iotlb_pool_put(dev, asid, node);
 	}
 
-	rte_rwlock_write_unlock(&dev->iotlb_pending_lock);
+	rte_rwlock_write_unlock(&dev->iotlb[asid]->pending_lock);
 }
 
 static void
-vhost_user_iotlb_cache_remove_all(struct virtio_net *dev)
+vhost_user_iotlb_cache_remove_all(struct virtio_net *dev, int asid)
 {
 	struct vhost_iotlb_entry *node, *temp_node;
 
 	vhost_user_iotlb_wr_lock_all(dev);
 
-	RTE_TAILQ_FOREACH_SAFE(node, &dev->iotlb_list, next, temp_node) {
+	RTE_TAILQ_FOREACH_SAFE(node, &dev->iotlb[asid]->list, next, temp_node) {
 		vhost_user_iotlb_clear_dump(dev, node, NULL, NULL);
 
-		TAILQ_REMOVE(&dev->iotlb_list, node, next);
+		TAILQ_REMOVE(&dev->iotlb[asid]->list, node, next);
 		vhost_user_iotlb_remove_notify(dev, node);
-		vhost_user_iotlb_pool_put(dev, node);
+		vhost_user_iotlb_pool_put(dev, asid, node);
 	}
 
-	dev->iotlb_cache_nr = 0;
+	dev->iotlb[asid]->cache_nr = 0;
 
 	vhost_user_iotlb_wr_unlock_all(dev);
 }
 
 static void
-vhost_user_iotlb_cache_random_evict(struct virtio_net *dev)
+vhost_user_iotlb_cache_random_evict(struct virtio_net *dev, int asid)
 {
 	struct vhost_iotlb_entry *node, *temp_node, *prev_node = NULL;
 	int entry_idx;
 
 	vhost_user_iotlb_wr_lock_all(dev);
 
-	entry_idx = rte_rand() % dev->iotlb_cache_nr;
+	entry_idx = rte_rand() % dev->iotlb[asid]->cache_nr;
 
-	RTE_TAILQ_FOREACH_SAFE(node, &dev->iotlb_list, next, temp_node) {
+	RTE_TAILQ_FOREACH_SAFE(node, &dev->iotlb[asid]->list, next, temp_node) {
 		if (!entry_idx) {
 			struct vhost_iotlb_entry *next_node = RTE_TAILQ_NEXT(node, next);
 
 			vhost_user_iotlb_clear_dump(dev, node, prev_node, next_node);
 
-			TAILQ_REMOVE(&dev->iotlb_list, node, next);
+			TAILQ_REMOVE(&dev->iotlb[asid]->list, node, next);
 			vhost_user_iotlb_remove_notify(dev, node);
-			vhost_user_iotlb_pool_put(dev, node);
-			dev->iotlb_cache_nr--;
+			vhost_user_iotlb_pool_put(dev, asid, node);
+			dev->iotlb[asid]->cache_nr--;
 			break;
 		}
 		prev_node = node;

@@ -246,20 +257,20 @@ vhost_user_iotlb_cache_random_evict(struct virtio_net *dev)
 }
 
 void
-vhost_user_iotlb_cache_insert(struct virtio_net *dev, uint64_t iova, uint64_t uaddr,
+vhost_user_iotlb_cache_insert(struct virtio_net *dev, int asid, uint64_t iova, uint64_t uaddr,
 				uint64_t uoffset, uint64_t size, uint64_t page_size, uint8_t perm)
 {
 	struct vhost_iotlb_entry *node, *new_node;
 
-	new_node = vhost_user_iotlb_pool_get(dev);
+	new_node = vhost_user_iotlb_pool_get(dev, asid);
 	if (new_node == NULL) {
 		VHOST_CONFIG_LOG(dev->ifname, DEBUG,
 			"IOTLB pool empty, clear entries for cache insertion");
-		if (!TAILQ_EMPTY(&dev->iotlb_list))
-			vhost_user_iotlb_cache_random_evict(dev);
+		if (!TAILQ_EMPTY(&dev->iotlb[asid]->list))
+			vhost_user_iotlb_cache_random_evict(dev, asid);
 		else
-			vhost_user_iotlb_pending_remove_all(dev);
-		new_node = vhost_user_iotlb_pool_get(dev);
+			vhost_user_iotlb_pending_remove_all(dev, asid);
+		new_node = vhost_user_iotlb_pool_get(dev, asid);
 		if (new_node == NULL) {
 			VHOST_CONFIG_LOG(dev->ifname, ERR,
 				"IOTLB pool still empty, cache insertion failed");

@@ -276,36 +287,36 @@ vhost_user_iotlb_cache_insert(struct virtio_net *dev, uint64_t iova, uint64_t ua
 
 	vhost_user_iotlb_wr_lock_all(dev);
 
-	TAILQ_FOREACH(node, &dev->iotlb_list, next) {
+	TAILQ_FOREACH(node, &dev->iotlb[asid]->list, next) {
 		/*
 		 * Entries must be invalidated before being updated.
 		 * So if iova already in list, assume identical.
 		 */
 		if (node->iova == new_node->iova) {
-			vhost_user_iotlb_pool_put(dev, new_node);
+			vhost_user_iotlb_pool_put(dev, asid, new_node);
 			goto unlock;
 		} else if (node->iova > new_node->iova) {
 			vhost_user_iotlb_set_dump(dev, new_node);
 
 			TAILQ_INSERT_BEFORE(node, new_node, next);
-			dev->iotlb_cache_nr++;
+			dev->iotlb[asid]->cache_nr++;
 			goto unlock;
 		}
 	}
 
 	vhost_user_iotlb_set_dump(dev, new_node);
 
-	TAILQ_INSERT_TAIL(&dev->iotlb_list, new_node, next);
-	dev->iotlb_cache_nr++;
+	TAILQ_INSERT_TAIL(&dev->iotlb[asid]->list, new_node, next);
+	dev->iotlb[asid]->cache_nr++;
 
 unlock:
-	vhost_user_iotlb_pending_remove(dev, iova, size, perm);
+	vhost_user_iotlb_pending_remove(dev, asid, iova, size, perm);
 
 	vhost_user_iotlb_wr_unlock_all(dev);
 }
 
 void
-vhost_user_iotlb_cache_remove(struct virtio_net *dev, uint64_t iova, uint64_t size)
+vhost_user_iotlb_cache_remove(struct virtio_net *dev, int asid, uint64_t iova, uint64_t size)
 {
 	struct vhost_iotlb_entry *node, *temp_node, *prev_node = NULL;
 

@@ -314,7 +325,7 @@ vhost_user_iotlb_cache_remove(struct virtio_net *dev, uint64_t iova, uint64_t si
 
 	vhost_user_iotlb_wr_lock_all(dev);
 
-	RTE_TAILQ_FOREACH_SAFE(node, &dev->iotlb_list, next, temp_node) {
+	RTE_TAILQ_FOREACH_SAFE(node, &dev->iotlb[asid]->list, next, temp_node) {
 		/* Sorted list */
 		if (unlikely(iova + size < node->iova))
 			break;

@@ -324,10 +335,10 @@ vhost_user_iotlb_cache_remove(struct virtio_net *dev, uint64_t iova, uint64_t si
 
 			vhost_user_iotlb_clear_dump(dev, node, prev_node, next_node);
 
-			TAILQ_REMOVE(&dev->iotlb_list, node, next);
+			TAILQ_REMOVE(&dev->iotlb[asid]->list, node, next);
 			vhost_user_iotlb_remove_notify(dev, node);
-			vhost_user_iotlb_pool_put(dev, node);
-			dev->iotlb_cache_nr--;
+			vhost_user_iotlb_pool_put(dev, asid, node);
+			dev->iotlb[asid]->cache_nr--;
 		} else {
 			prev_node = node;
 		}

@@ -337,7 +348,8 @@ vhost_user_iotlb_cache_remove(struct virtio_net *dev, uint64_t iova, uint64_t si
 }
 
 uint64_t
-vhost_user_iotlb_cache_find(struct virtio_net *dev, uint64_t iova, uint64_t *size, uint8_t perm)
+vhost_user_iotlb_cache_find(struct virtio_net *dev, int asid,
+			    uint64_t iova, uint64_t *size, uint8_t perm)
 {
 	struct vhost_iotlb_entry *node;
 	uint64_t offset, vva = 0, mapped = 0;

@@ -345,7 +357,7 @@ vhost_user_iotlb_cache_find(struct virtio_net *dev, uint64_t iova, uint64_t *siz
 	if (unlikely(!*size))
 		goto out;
 
-	TAILQ_FOREACH(node, &dev->iotlb_list, next) {
+	TAILQ_FOREACH(node, &dev->iotlb[asid]->list, next) {
 		/* List sorted by iova */
 		if (unlikely(iova < node->iova))
 			break;

@@ -378,25 +390,28 @@ vhost_user_iotlb_cache_find(struct virtio_net *dev, uint64_t iova, uint64_t *siz
 }
 
 void
-vhost_user_iotlb_flush_all(struct virtio_net *dev)
+vhost_user_iotlb_flush_all(struct virtio_net *dev, int asid)
 {
-	vhost_user_iotlb_cache_remove_all(dev);
-	vhost_user_iotlb_pending_remove_all(dev);
+	vhost_user_iotlb_cache_remove_all(dev, asid);
+	vhost_user_iotlb_pending_remove_all(dev, asid);
 }
 
-int
-vhost_user_iotlb_init(struct virtio_net *dev)
+static int
+vhost_user_iotlb_init_one(struct virtio_net *dev, int asid)
 {
 	unsigned int i;
 	int socket = 0;
 
-	if (dev->iotlb_pool) {
-		/*
-		 * The cache has already been initialized,
-		 * just drop all cached and pending entries.
-		 */
-		vhost_user_iotlb_flush_all(dev);
-		rte_free(dev->iotlb_pool);
+	if (dev->iotlb[asid] != NULL) {
+		if (dev->iotlb[asid]->pool != NULL) {
+			/*
+			 * The cache has already been initialized,
+			 * just drop all cached and pending entries.
+			 */
+			vhost_user_iotlb_flush_all(dev, asid);
+			rte_free(dev->iotlb[asid]->pool);
+		}
+		rte_free(dev->iotlb[asid]);
 	}
 
 #ifdef RTE_LIBRTE_VHOST_NUMA

@@ -404,31 +419,73 @@ vhost_user_iotlb_init(struct virtio_net *dev)
 		socket = 0;
 #endif
 
-	rte_spinlock_init(&dev->iotlb_free_lock);
-	rte_rwlock_init(&dev->iotlb_pending_lock);
+	dev->iotlb[asid] = rte_malloc_socket("iotlb", sizeof(struct iotlb), 0, socket);
+	if (!dev->iotlb[asid]) {
+		VHOST_CONFIG_LOG(dev->ifname, ERR, "Failed to allocate IOTLB");
+		return -1;
+	}
+
+	rte_spinlock_init(&dev->iotlb[asid]->free_lock);
+	rte_rwlock_init(&dev->iotlb[asid]->pending_lock);
 
-	SLIST_INIT(&dev->iotlb_free_list);
-	TAILQ_INIT(&dev->iotlb_list);
-	TAILQ_INIT(&dev->iotlb_pending_list);
+	SLIST_INIT(&dev->iotlb[asid]->free_list);
+	TAILQ_INIT(&dev->iotlb[asid]->list);
+	TAILQ_INIT(&dev->iotlb[asid]->pending_list);
 
 	if (dev->flags & VIRTIO_DEV_SUPPORT_IOMMU) {
-		dev->iotlb_pool = rte_calloc_socket("iotlb", IOTLB_CACHE_SIZE,
+		dev->iotlb[asid]->pool = rte_calloc_socket("iotlb_pool", IOTLB_CACHE_SIZE,
 			sizeof(struct vhost_iotlb_entry), 0, socket);
-		if (!dev->iotlb_pool) {
+		if (!dev->iotlb[asid]->pool) {
 			VHOST_CONFIG_LOG(dev->ifname, ERR, "Failed to create IOTLB cache pool");
-			return -1;
+			goto free_iotlb;
 		}
 		for (i = 0; i < IOTLB_CACHE_SIZE; i++)
-			vhost_user_iotlb_pool_put(dev, &dev->iotlb_pool[i]);
+			vhost_user_iotlb_pool_put(dev, asid, &dev->iotlb[asid]->pool[i]);
 	}
 
-	dev->iotlb_cache_nr = 0;
+	dev->iotlb[asid]->cache_nr = 0;
+
+	return 0;
+
+free_iotlb:
+	rte_free(dev->iotlb[asid]);
+	dev->iotlb[asid] = NULL;
+	return -1;
+}
+
+int
+vhost_user_iotlb_init(struct virtio_net *dev)
+{
+	int i;
+
+	for (i = 0; i < IOTLB_MAX_ASID; i++)
+		if (vhost_user_iotlb_init_one(dev, i) < 0)
+			goto fail;
 
 	return 0;
+fail:
+	while (i--) {
+		rte_free(dev->iotlb[i]->pool);
+		dev->iotlb[i]->pool = NULL;
+		rte_free(dev->iotlb[i]);
+		dev->iotlb[i] = NULL;
+	}
+
+	return -1;
 }
 
 void
 vhost_user_iotlb_destroy(struct virtio_net *dev)
 {
-	rte_free(dev->iotlb_pool);
+	int i;
+
+	for (i = 0; i < IOTLB_MAX_ASID; i++) {
+		if (dev->iotlb[i]) {
+			rte_free(dev->iotlb[i]->pool);
+			dev->iotlb[i]->pool = NULL;
+
+			rte_free(dev->iotlb[i]);
+			dev->iotlb[i] = NULL;
+		}
+	}
 }

index 72232b0dcf08..52963d6c4de0 100644
@@ -57,16 +57,16 @@ vhost_user_iotlb_wr_unlock_all(struct virtio_net *dev)
 		rte_rwlock_write_unlock(&dev->virtqueue[i]->iotlb_lock);
 }
 
-void vhost_user_iotlb_cache_insert(struct virtio_net *dev, uint64_t iova, uint64_t uaddr,
+void vhost_user_iotlb_cache_insert(struct virtio_net *dev, int asid, uint64_t iova, uint64_t uaddr,
 		uint64_t uoffset, uint64_t size, uint64_t page_size, uint8_t perm);
-void vhost_user_iotlb_cache_remove(struct virtio_net *dev, uint64_t iova, uint64_t size);
-uint64_t vhost_user_iotlb_cache_find(struct virtio_net *dev, uint64_t iova,
+void vhost_user_iotlb_cache_remove(struct virtio_net *dev, int asid, uint64_t iova, uint64_t size);
+uint64_t vhost_user_iotlb_cache_find(struct virtio_net *dev, int asid, uint64_t iova,
 					uint64_t *size, uint8_t perm);
-bool vhost_user_iotlb_pending_miss(struct virtio_net *dev, uint64_t iova, uint8_t perm);
-void vhost_user_iotlb_pending_insert(struct virtio_net *dev, uint64_t iova, uint8_t perm);
-void vhost_user_iotlb_pending_remove(struct virtio_net *dev, uint64_t iova,
+bool vhost_user_iotlb_pending_miss(struct virtio_net *dev, int asid, uint64_t iova, uint8_t perm);
+void vhost_user_iotlb_pending_insert(struct virtio_net *dev, int asid, uint64_t iova, uint8_t perm);
+void vhost_user_iotlb_pending_remove(struct virtio_net *dev, int asid, uint64_t iova,
 						uint64_t size, uint8_t perm);
-void vhost_user_iotlb_flush_all(struct virtio_net *dev);
+void vhost_user_iotlb_flush_all(struct virtio_net *dev, int asid);
 int vhost_user_iotlb_init(struct virtio_net *dev);
 void vhost_user_iotlb_destroy(struct virtio_net *dev);
 

index f8a4a8edcbf2..3c72bafcf511 100644
@@ -57,7 +57,7 @@ vduse_iotlb_remove_notify(uint64_t addr, uint64_t offset, uint64_t size)
 }
 
 static int
-vduse_iotlb_miss(struct virtio_net *dev, uint64_t iova, uint8_t perm __rte_unused)
+vduse_iotlb_miss(struct virtio_net *dev, int asid, uint64_t iova, uint8_t perm __rte_unused)
 {
 	struct vduse_iotlb_entry entry;
 	uint64_t size, page_size;

@@ -102,7 +102,7 @@ vduse_iotlb_miss(struct virtio_net *dev, uint64_t iova, uint8_t perm __rte_unuse
 	}
 	page_size = (uint64_t)stat.st_blksize;
 
-	vhost_user_iotlb_cache_insert(dev, entry.start, (uint64_t)(uintptr_t)mmap_addr,
+	vhost_user_iotlb_cache_insert(dev, asid, entry.start, (uint64_t)(uintptr_t)mmap_addr,
 		entry.offset, size, page_size, entry.perm);
 
 	ret = 0;

@@ -398,7 +398,8 @@ vduse_device_stop(struct virtio_net *dev)
 	for (i = 0; i < dev->nr_vring; i++)
 		vduse_vring_cleanup(dev, i);
 
-	vhost_user_iotlb_flush_all(dev);
+	for (i = 0; i < IOTLB_MAX_ASID; i++)
+		vhost_user_iotlb_flush_all(dev, i);
 }
 
 static void

@@ -445,7 +446,7 @@ vduse_events_handler(int fd, void *arg, int *close __rte_unused)
 	case VDUSE_UPDATE_IOTLB:
 		VHOST_CONFIG_LOG(dev->ifname, INFO, "\tIOVA range: %" PRIx64 " - %" PRIx64,
 				(uint64_t)req.iova.start, (uint64_t)req.iova.last);
-		vhost_user_iotlb_cache_remove(dev, req.iova.start,
+		vhost_user_iotlb_cache_remove(dev, 0, req.iova.start,
 				req.iova.last - req.iova.start + 1);
 		resp.result = VDUSE_REQ_RESULT_OK;
 		break;

index fde8acb00cde..8bfdbee894b5 100644
@@ -62,9 +62,9 @@ static const struct vhost_vq_stats_name_off vhost_vq_stat_strings[] = {
 #define VHOST_NB_VQ_STATS RTE_DIM(vhost_vq_stat_strings)
 
 static int
-vhost_iotlb_miss(struct virtio_net *dev, uint64_t iova, uint8_t perm)
+vhost_iotlb_miss(struct virtio_net *dev, int asid, uint64_t iova, uint8_t perm)
 {
-	return dev->backend_ops->iotlb_miss(dev, iova, perm);
+	return dev->backend_ops->iotlb_miss(dev, asid, iova, perm);
 }
 
 uint64_t

@@ -78,7 +78,7 @@ __vhost_iova_to_vva(struct virtio_net *dev, struct vhost_virtqueue *vq,
 
 	tmp_size = *size;
 
-	vva = vhost_user_iotlb_cache_find(dev, iova, &tmp_size, perm);
+	vva = vhost_user_iotlb_cache_find(dev, vq->asid, iova, &tmp_size, perm);
 	if (tmp_size == *size) {
 		if (dev->flags & VIRTIO_DEV_STATS_ENABLED)
 			vq->stats.iotlb_hits++;

@@ -90,7 +90,7 @@ __vhost_iova_to_vva(struct virtio_net *dev, struct vhost_virtqueue *vq,
 
 	iova += tmp_size;
 
-	if (!vhost_user_iotlb_pending_miss(dev, iova, perm)) {
+	if (!vhost_user_iotlb_pending_miss(dev, vq->asid, iova, perm)) {
 		/*
 		 * iotlb_lock is read-locked for a full burst,
 		 * but it only protects the iotlb cache.

@@ -100,12 +100,12 @@ __vhost_iova_to_vva(struct virtio_net *dev, struct vhost_virtqueue *vq,
 		 */
 		vhost_user_iotlb_rd_unlock(vq);
 
-		vhost_user_iotlb_pending_insert(dev, iova, perm);
-		if (vhost_iotlb_miss(dev, iova, perm)) {
+		vhost_user_iotlb_pending_insert(dev, vq->asid, iova, perm);
+		if (vhost_iotlb_miss(dev, vq->asid, iova, perm)) {
 			VHOST_DATA_LOG(dev->ifname, ERR,
 				"IOTLB miss req failed for IOVA 0x%" PRIx64,
 				iova);
-			vhost_user_iotlb_pending_remove(dev, iova, 1, perm);
+			vhost_user_iotlb_pending_remove(dev, vq->asid, iova, 1, perm);
 		}
 
 		vhost_user_iotlb_rd_lock(vq);

@@ -113,7 +113,7 @@ __vhost_iova_to_vva(struct virtio_net *dev, struct vhost_virtqueue *vq,
 
 	tmp_size = *size;
 	/* Retry in case of VDUSE, as it is synchronous */
-	vva = vhost_user_iotlb_cache_find(dev, iova, &tmp_size, perm);
+	vva = vhost_user_iotlb_cache_find(dev, vq->asid, iova, &tmp_size, perm);
 	if (tmp_size == *size)
 		return vva;
 

index bb4708aed5ed..e0441adb6193 100644
@@ -85,7 +85,7 @@ struct vhost_virtqueue;
 
 typedef void (*vhost_iotlb_remove_notify)(uint64_t addr, uint64_t off, uint64_t size);
 
-typedef int (*vhost_iotlb_miss_cb)(struct virtio_net *dev, uint64_t iova, uint8_t perm);
+typedef int (*vhost_iotlb_miss_cb)(struct virtio_net *dev, int asid, uint64_t iova, uint8_t perm);
 
 typedef int (*vhost_vring_inject_irq_cb)(struct virtio_net *dev, struct vhost_virtqueue *vq);
 /**

@@ -326,6 +326,7 @@ struct __rte_cache_aligned vhost_virtqueue {
 	uint16_t		batch_copy_nb_elems;
 	struct batch_copy_elem	*batch_copy_elems;
 	int			numa_node;
+	int			asid;
 	bool			used_wrap_counter;
 	bool			avail_wrap_counter;
 

@@ -483,6 +484,8 @@ struct inflight_mem_info {
 	uint64_t	size;
 };
 
+#define IOTLB_MAX_ASID 2
+
 /**
  * Device structure contains all configuration information relating
  * to the device.

@@ -504,13 +507,7 @@ struct __rte_cache_aligned virtio_net {
 	int			linearbuf;
 	struct vhost_virtqueue	*virtqueue[VHOST_MAX_VRING];
 
-	rte_rwlock_t	iotlb_pending_lock;
-	struct vhost_iotlb_entry *iotlb_pool;
-	TAILQ_HEAD(, vhost_iotlb_entry) iotlb_list;
-	TAILQ_HEAD(, vhost_iotlb_entry) iotlb_pending_list;
-	int				iotlb_cache_nr;
-	rte_spinlock_t	iotlb_free_lock;
-	SLIST_HEAD(, vhost_iotlb_entry) iotlb_free_list;
+	struct iotlb		*iotlb[IOTLB_MAX_ASID];
 
 	struct inflight_mem_info *inflight_info;
 #define IF_NAME_SZ (PATH_MAX > IFNAMSIZ ? PATH_MAX : IFNAMSIZ)

index 020c993b2991..e623651fc01e 100644
@@ -1530,7 +1530,8 @@ vhost_user_set_mem_table(struct virtio_net **pdev,
 
 		/* Flush IOTLB cache as previous HVAs are now invalid */
 		if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
-			vhost_user_iotlb_flush_all(dev);
+			for (i = 0; i < IOTLB_MAX_ASID; i++)
+				vhost_user_iotlb_flush_all(dev, i);
 
 		free_all_mem_regions(dev);
 		rte_free(dev->mem);

@@ -1830,7 +1831,7 @@ vhost_user_rem_mem_reg(struct virtio_net **pdev,
 			if (dev->async_copy && rte_vfio_is_enabled("vfio"))
 				async_dma_map_region(dev, current_region, false);
 			if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
-				vhost_user_iotlb_cache_remove(dev,
+				vhost_user_iotlb_cache_remove(dev, 0,
 					current_region->guest_phys_addr,
 					current_region->size);
 			remove_guest_pages(dev, current_region);

@@ -2581,7 +2582,7 @@ vhost_user_get_vring_base(struct virtio_net **pdev,
 	ctx->msg.size = sizeof(ctx->msg.payload.state);
 	ctx->fd_num = 0;
 
-	vhost_user_iotlb_flush_all(dev);
+	vhost_user_iotlb_flush_all(dev, vq->asid);
 
 	rte_rwlock_write_lock(&vq->access_lock);
 	vring_invalidate(dev, vq);

@@ -3030,7 +3031,7 @@ vhost_user_iotlb_msg(struct virtio_net **pdev,
 
 		pg_sz = hua_to_alignment(dev->mem, (void *)(uintptr_t)vva);
 
-		vhost_user_iotlb_cache_insert(dev, imsg->iova, vva, 0, len, pg_sz, imsg->perm);
+		vhost_user_iotlb_cache_insert(dev, 0, imsg->iova, vva, 0, len, pg_sz, imsg->perm);
 
 		for (i = 0; i < dev->nr_vring; i++) {
 			struct vhost_virtqueue *vq = dev->virtqueue[i];

@@ -3047,7 +3048,7 @@ vhost_user_iotlb_msg(struct virtio_net **pdev,
 		}
 		break;
 	case VHOST_IOTLB_INVALIDATE:
-		vhost_user_iotlb_cache_remove(dev, imsg->iova, imsg->size);
+		vhost_user_iotlb_cache_remove(dev, 0, imsg->iova, imsg->size);
 
 		for (i = 0; i < dev->nr_vring; i++) {
 			struct vhost_virtqueue *vq = dev->virtqueue[i];

@@ -3640,7 +3641,7 @@ vhost_user_msg_handler(int vid, int fd)
 }
 
 static int
-vhost_user_iotlb_miss(struct virtio_net *dev, uint64_t iova, uint8_t perm)
+vhost_user_iotlb_miss(struct virtio_net *dev, int asid __rte_unused, uint64_t iova, uint8_t perm)
 {
 	int ret;
 	struct vhu_msg_context ctx = {

index 3c72bafcf511..ceef207ad2df 100644
@@ -25,7 +25,7 @@
 #include "vhost.h"
 #include "virtio_net_ctrl.h"
 
-#define VHOST_VDUSE_API_VERSION 0
+#define VHOST_VDUSE_API_VERSION 0ULL
 #define VDUSE_CTRL_PATH "/dev/vduse/control"
 
 struct vduse {

@@ -680,7 +680,7 @@ vduse_device_create(const char *path, bool compliant_ol_flags, bool extbuf, bool
 	uint32_t i, max_queue_pairs, total_queues;
 	struct virtio_net *dev;
 	struct virtio_net_config vnet_config = {{ 0 }};
-	uint64_t ver = VHOST_VDUSE_API_VERSION;
+	uint64_t ver;
 	uint64_t features;
 	const char *name = path + strlen("/dev/vduse/");
 	bool reconnect = false;

@@ -700,6 +700,15 @@ vduse_device_create(const char *path, bool compliant_ol_flags, bool extbuf, bool
 		return -1;
 	}
 
+	if (ioctl(control_fd, VDUSE_GET_API_VERSION, &ver)) {
+		VHOST_CONFIG_LOG(name, ERR, "Failed to get API version: %s", strerror(errno));
+		ret = -1;
+		goto out_ctrl_close;
+	}
+
+	ver = RTE_MIN(ver, VHOST_VDUSE_API_VERSION);
+	VHOST_CONFIG_LOG(name, INFO, "Using VDUSE API version %" PRIu64 "", ver);
+
 	if (ioctl(control_fd, VDUSE_SET_API_VERSION, &ver)) {
 		VHOST_CONFIG_LOG(name, ERR, "Failed to set API version: %" PRIu64 ": %s",
 				ver, strerror(errno));

@@ -800,6 +809,7 @@ vduse_device_create(const char *path, bool compliant_ol_flags, bool extbuf, bool
 	strlcpy(dev->ifname, path, sizeof(dev->ifname));
 	dev->vduse_ctrl_fd = control_fd;
 	dev->vduse_dev_fd = dev_fd;
+	dev->vduse_api_ver = ver;
 
 	ret = vduse_reconnect_log_map(dev, !reconnect);
 	if (ret < 0)

index e0441adb6193..36d65bc2c162 100644
@@ -532,6 +532,7 @@ struct __rte_cache_aligned virtio_net {
 	int			postcopy_listening;
 	int			vduse_ctrl_fd;
 	int			vduse_dev_fd;
+	uint64_t		vduse_api_ver;
 
 	struct vhost_virtqueue	*cvq;
 

index ceef207ad2df..8c031168bf77 100644
@@ -38,12 +38,24 @@ static const char * const vduse_reqs_str[] = {
 	"VDUSE_GET_VQ_STATE",
 	"VDUSE_SET_STATUS",
 	"VDUSE_UPDATE_IOTLB",
+	"VDUSE_SET_VQ_GROUP_ASID",
 };
 
 #define vduse_req_id_to_str(id) \
 	(id < RTE_DIM(vduse_reqs_str) ? \
 	vduse_reqs_str[id] : "Unknown")
 
+static uint64_t vduse_vq_to_group(struct virtio_net *dev, struct vhost_virtqueue *vq)
+{
+	if (dev->vduse_api_ver < 1)
+		return 0;
+
+	if (vq == dev->cvq)
+		return 1;
+
+	return 0;
+}
+
 static int
 vduse_inject_irq(struct virtio_net *dev, struct vhost_virtqueue *vq)
 {

@@ -271,6 +283,7 @@ vduse_vring_cleanup(struct virtio_net *dev, unsigned int index)
 	vq->size = 0;
 	vq->last_used_idx = 0;
 	vq->last_avail_idx = 0;
+	vq->asid = 0;
 }
 
 /*

@@ -410,6 +423,7 @@ vduse_events_handler(int fd, void *arg, int *close __rte_unused)
 	struct vduse_dev_response resp;
 	struct vhost_virtqueue *vq;
 	uint8_t old_status = dev->status;
+	uint32_t i;
 	int ret;
 
 	memset(&resp, 0, sizeof(resp));

@@ -450,6 +464,34 @@ vduse_events_handler(int fd, void *arg, int *close __rte_unused)
 				req.iova.last - req.iova.start + 1);
 		resp.result = VDUSE_REQ_RESULT_OK;
 		break;
+	case VDUSE_SET_VQ_GROUP_ASID:
+		if (dev->vduse_api_ver < 1) {
+			resp.result = VDUSE_REQ_RESULT_FAILED;
+			break;
+		}
+
+		if (req.vq_group_asid.asid >= RTE_DIM(dev->iotlb)) {
+			VHOST_CONFIG_LOG(dev->ifname, ERR,
+				"Invalid ASID %u for group %u",
+				req.vq_group_asid.asid, req.vq_group_asid.group);
+			resp.result = VDUSE_REQ_RESULT_FAILED;
+			break;
+		}
+
+		VHOST_CONFIG_LOG(dev->ifname, INFO, "\tAssigning ASID %d to group %d",
+				req.vq_group_asid.asid, req.vq_group_asid.group);
+
+		for (i = 0; i < dev->nr_vring; i++) {
+			vq = dev->virtqueue[i];
+
+			if (vduse_vq_to_group(dev, vq) == req.vq_group_asid.group) {
+				vq->asid = req.vq_group_asid.asid;
+				VHOST_CONFIG_LOG(dev->ifname, INFO, "\t\tVQ %d gets ASID %d",
+						i, req.vq_group_asid.asid);
+			}
+		}
+		resp.result = VDUSE_REQ_RESULT_OK;
+		break;
 	default:
 		resp.result = VDUSE_REQ_RESULT_FAILED;
 		break;

@@ -760,6 +802,10 @@ vduse_device_create(const char *path, bool compliant_ol_flags, bool extbuf, bool
 		dev_config->features = features;
 		dev_config->vq_num = total_queues;
 		dev_config->vq_align = rte_mem_page_size();
+		if (ver >= 1) {
+			dev_config->ngroups = 2;
+			dev_config->nas = 2;
+		}
 		dev_config->config_size = sizeof(struct virtio_net_config);
 		memcpy(dev_config->config, &vnet_config, sizeof(vnet_config));
 

@@ -848,11 +894,15 @@ vduse_device_create(const char *path, bool compliant_ol_flags, bool extbuf, bool
 		vq = dev->virtqueue[i];
 		vq->reconnect_log = &dev->reconnect_log->vring[i];
 
+		if (i == max_queue_pairs * 2)
+			dev->cvq = vq;
+
 		if (reconnect)
 			continue;
 
 		vq_cfg.index = i;
 		vq_cfg.max_size = 1024;
+		vq_cfg.group = vduse_vq_to_group(dev, vq);
 
 		ret = ioctl(dev->vduse_dev_fd, VDUSE_VQ_SETUP, &vq_cfg);
 		if (ret) {

@@ -861,8 +911,6 @@ vduse_device_create(const char *path, bool compliant_ol_flags, bool extbuf, bool
 		}
 	}
 
-	dev->cvq = dev->virtqueue[max_queue_pairs * 2];
-
 	ret = fdset_add(vduse.fdset, dev->vduse_dev_fd, vduse_events_handler, NULL, dev);
 	if (ret) {
 		VHOST_CONFIG_LOG(name, ERR, "Failed to add fd %d to vduse fdset",

index 8c031168bf77..2d3d8a536773 100644
@@ -71,7 +71,7 @@ vduse_iotlb_remove_notify(uint64_t addr, uint64_t offset, uint64_t size)
 static int
 vduse_iotlb_miss(struct virtio_net *dev, int asid, uint64_t iova, uint8_t perm __rte_unused)
 {
-	struct vduse_iotlb_entry entry;
+	struct vduse_iotlb_entry_v2 entry = {};
 	uint64_t size, page_size;
 	struct stat stat;
 	void *mmap_addr;

@@ -79,8 +79,13 @@ vduse_iotlb_miss(struct virtio_net *dev, int asid, uint64_t iova, uint8_t perm _
 
 	entry.start = iova;
 	entry.last = iova + 1;
+	entry.asid = asid;
 
-	ret = ioctl(dev->vduse_dev_fd, VDUSE_IOTLB_GET_FD, &entry);
+	if (dev->vduse_api_ver < 1) {
+		ret = ioctl(dev->vduse_dev_fd, VDUSE_IOTLB_GET_FD, &entry);
+	} else {
+		ret = ioctl(dev->vduse_dev_fd, VDUSE_IOTLB_GET_FD2, &entry);
+	}
 	if (ret < 0) {
 		VHOST_CONFIG_LOG(dev->ifname, ERR, "Failed to get IOTLB entry for 0x%" PRIx64,
 				iova);

@@ -90,6 +95,7 @@ vduse_iotlb_miss(struct virtio_net *dev, int asid, uint64_t iova, uint8_t perm _
 	fd = ret;
 
 	VHOST_CONFIG_LOG(dev->ifname, DEBUG, "New IOTLB entry:");
+	VHOST_CONFIG_LOG(dev->ifname, DEBUG, "\tASID: %d", entry.asid);
 	VHOST_CONFIG_LOG(dev->ifname, DEBUG, "\tIOVA: %" PRIx64 " - %" PRIx64,
 			(uint64_t)entry.start, (uint64_t)entry.last);
 	VHOST_CONFIG_LOG(dev->ifname, DEBUG, "\toffset: %" PRIx64, (uint64_t)entry.offset);

@@ -458,10 +464,31 @@ vduse_events_handler(int fd, void *arg, int *close __rte_unused)
 		resp.result = VDUSE_REQ_RESULT_OK;
 		break;
 	case VDUSE_UPDATE_IOTLB:
-		VHOST_CONFIG_LOG(dev->ifname, INFO, "\tIOVA range: %" PRIx64 " - %" PRIx64,
-				(uint64_t)req.iova.start, (uint64_t)req.iova.last);
-		vhost_user_iotlb_cache_remove(dev, 0, req.iova.start,
-				req.iova.last - req.iova.start + 1);
+		{
+			uint64_t start, last;
+			uint32_t asid;
+
+			if (dev->vduse_api_ver < 1) {
+				start = req.iova.start;
+				last = req.iova.last;
+				asid = 0;
+			} else {
+				start = req.iova_v2.start;
+				last = req.iova_v2.last;
+				asid = req.iova_v2.asid;
+			}
+
+			if (asid >= RTE_DIM(dev->iotlb)) {
+				VHOST_CONFIG_LOG(dev->ifname, ERR,
+					"Invalid ASID %u in IOTLB update", asid);
+				resp.result = VDUSE_REQ_RESULT_FAILED;
+				break;
+			}
+
+			VHOST_CONFIG_LOG(dev->ifname, INFO, "\t(ASID %d) IOVA range: %" PRIx64 " - %" PRIx64,
+				asid, start, last);
+			vhost_user_iotlb_cache_remove(dev, asid, start, last - start + 1);
+		}
 		resp.result = VDUSE_REQ_RESULT_OK;
 		break;
 	case VDUSE_SET_VQ_GROUP_ASID:

index 2d3d8a536773..4950a5da01dd 100644
@@ -25,7 +25,7 @@
 #include "vhost.h"
 #include "virtio_net_ctrl.h"
 
-#define VHOST_VDUSE_API_VERSION 0ULL
+#define VHOST_VDUSE_API_VERSION 1ULL
 #define VDUSE_CTRL_PATH "/dev/vduse/control"
 
 struct vduse {

index 4950a5da01dd..b51776cf3ff4 100644
@@ -820,6 +820,7 @@ vduse_device_create(const char *path, bool compliant_ol_flags, bool extbuf, bool
 			goto out_ctrl_close;
 		}
 
+		vnet_config.status = VIRTIO_NET_S_LINK_UP;
 		vnet_config.max_virtqueue_pairs = max_queue_pairs;
 		memset(dev_config, 0, sizeof(struct vduse_dev_config));
 

index b2515bb9df76..d697f85be5cc 100644
@@ -7,7 +7,8 @@
 
 #include "vhost.h"
 
-#define VDUSE_NET_SUPPORTED_FEATURES VIRTIO_NET_SUPPORTED_FEATURES
+#define VDUSE_NET_SUPPORTED_FEATURES (VIRTIO_NET_SUPPORTED_FEATURES | \
+		(1ULL << VIRTIO_NET_F_STATUS))
 
 int vduse_device_create(const char *path, bool compliant_ol_flags, bool extbuf, bool linearbuf);
 int vduse_device_destroy(const char *path);

index b51776cf3ff4..bcbd9fcd6d52 100644
@@ -39,12 +39,15 @@ static const char * const vduse_reqs_str[] = {
 	"VDUSE_SET_STATUS",
 	"VDUSE_UPDATE_IOTLB",
 	"VDUSE_SET_VQ_GROUP_ASID",
+	"VDUSE_SET_VQ_READY",
 };
 
 #define vduse_req_id_to_str(id) \
 	(id < RTE_DIM(vduse_reqs_str) ? \
 	vduse_reqs_str[id] : "Unknown")
 
+static const uint64_t supported_vduse_features = RTE_BIT64(VDUSE_F_QUEUE_READY);
+
 static uint64_t vduse_vq_to_group(struct virtio_net *dev, struct vhost_virtqueue *vq)
 {
 	if (dev->vduse_api_ver < 1)

@@ -519,6 +522,51 @@ vduse_events_handler(int fd, void *arg, int *close __rte_unused)
 		}
 		resp.result = VDUSE_REQ_RESULT_OK;
 		break;
+	case VDUSE_SET_VQ_READY:
+		if (!(dev->status & VIRTIO_DEVICE_STATUS_DRIVER_OK)) {
+			/*
+			 * dev->notify_ops is NULL if !S_DRIVER_OK,
+			 * vduse_device_start will check the queue readiness.
+			 */
+			resp.result = VDUSE_REQ_RESULT_OK;
+			break;
+		}
+		if (!(dev->vduse_features & RTE_BIT64(VDUSE_F_QUEUE_READY))) {
+			VHOST_CONFIG_LOG(dev->ifname, ERR,
+				"Unexpected ready message with no ready feature acked");
+			resp.result = VDUSE_REQ_RESULT_FAILED;
+			break;
+		}
+
+		i = req.vq_ready.num;
+		if (i >= dev->nr_vring) {
+			VHOST_CONFIG_LOG(dev->ifname, ERR,
+					"Invalid virtqueue index: %u", i);
+			resp.result = VDUSE_REQ_RESULT_FAILED;
+			break;
+		}
+
+		vq = dev->virtqueue[i];
+		if (dev->notify_ops == NULL || dev->notify_ops->vring_state_changed == NULL) {
+			VHOST_CONFIG_LOG(dev->ifname, ERR,
+					 "No ops->vring_state_changed");
+			resp.result = VDUSE_REQ_RESULT_FAILED;
+			break;
+		}
+
+		ret = dev->notify_ops->vring_state_changed(dev->vid, i,
+				req.vq_ready.ready);
+		VHOST_CONFIG_LOG(dev->ifname, INFO,
+				"\t\t VQ %d gets ready %d ok %d", i,
+				req.vq_ready.ready, ret);
+		if (ret != 0) {
+			resp.result = VDUSE_REQ_RESULT_FAILED;
+			break;
+		}
+
+		vq->enabled = req.vq_ready.ready;
+		resp.result = VDUSE_REQ_RESULT_OK;
+		break;
 	default:
 		resp.result = VDUSE_REQ_RESULT_FAILED;
 		break;

@@ -536,7 +584,8 @@ vduse_events_handler(int fd, void *arg, int *close __rte_unused)
 	if ((old_status ^ dev->status) & VIRTIO_DEVICE_STATUS_DRIVER_OK) {
 		if (dev->status & VIRTIO_DEVICE_STATUS_DRIVER_OK) {
 			/* Poll virtqueues ready states before starting device */
-			ret = vduse_wait_for_virtqueues_ready(dev);
+			ret = dev->vduse_features & RTE_BIT64(VDUSE_F_QUEUE_READY) ? 0
+				: vduse_wait_for_virtqueues_ready(dev);
 			if (ret < 0) {
 				VHOST_CONFIG_LOG(dev->ifname, ERR,
 					"Failed to wait for virtqueues ready, aborting device start");

@@ -742,6 +791,26 @@ vduse_reconnect_start_device(struct virtio_net *dev)
 	return ret;
 }
 
+/* If some error occurs just continue as if the kernel exposed no features */
+static uint64_t
+vduse_device_get_vduse_features(int control_fd, const char *log_name)
+{
+	uint64_t vduse_kernel_features;
+	int ret;
+
+	ret = ioctl(control_fd, VDUSE_GET_FEATURES, &vduse_kernel_features);
+	if (ret < 0) {
+		VHOST_CONFIG_LOG(log_name, INFO,
+			"Failed to get kernel VDUSE features, assuming not supported: %d(%s)",
+			errno, strerror(errno));
+		return 0;
+	}
+
+	VHOST_CONFIG_LOG(log_name, DEBUG, "Setting vhost kernel features: %"PRIx64,
+			vduse_kernel_features & supported_vduse_features);
+	return vduse_kernel_features & supported_vduse_features;
+}
+
 int
 vduse_device_create(const char *path, bool compliant_ol_flags, bool extbuf, bool linearbuf)
 {

@@ -750,7 +819,7 @@ vduse_device_create(const char *path, bool compliant_ol_flags, bool extbuf, bool
 	struct virtio_net *dev;
 	struct virtio_net_config vnet_config = {{ 0 }};
 	uint64_t ver;
-	uint64_t features;
+	uint64_t features, vduse_features = 0;
 	const char *name = path + strlen("/dev/vduse/");
 	bool reconnect = false;
 

@@ -834,6 +903,18 @@ vduse_device_create(const char *path, bool compliant_ol_flags, bool extbuf, bool
 			dev_config->ngroups = 2;
 			dev_config->nas = 2;
 		}
+
+		vduse_features = vduse_device_get_vduse_features(control_fd, name);
+		if (vduse_features) {
+			ret = ioctl(control_fd, VDUSE_SET_FEATURES, &vduse_features);
+			if (ret < 0) {
+				VHOST_CONFIG_LOG(name, ERR, "Failed to set VDUSE features: %s",
+						strerror(errno));
+				free(dev_config);
+				goto out_ctrl_close;
+			}
+		}
+
 		dev_config->config_size = sizeof(struct virtio_net_config);
 		memcpy(dev_config->config, &vnet_config, sizeof(vnet_config));
 

@@ -884,6 +965,7 @@ vduse_device_create(const char *path, bool compliant_ol_flags, bool extbuf, bool
 	dev->vduse_ctrl_fd = control_fd;
 	dev->vduse_dev_fd = dev_fd;
 	dev->vduse_api_ver = ver;
+	dev->vduse_features = vduse_features;
 
 	ret = vduse_reconnect_log_map(dev, !reconnect);
 	if (ret < 0)

index 36d65bc2c162..369ccf399146 100644
@@ -533,6 +533,7 @@ struct __rte_cache_aligned virtio_net {
 	int			vduse_ctrl_fd;
 	int			vduse_dev_fd;
 	uint64_t		vduse_api_ver;
+	uint64_t		vduse_features;
 
 	struct vhost_virtqueue	*cvq;
 

index bcbd9fcd6d52..cdff4df84a84 100644
@@ -46,7 +46,8 @@ static const char * const vduse_reqs_str[] = {
 	(id < RTE_DIM(vduse_reqs_str) ? \
 	vduse_reqs_str[id] : "Unknown")
 
-static const uint64_t supported_vduse_features = RTE_BIT64(VDUSE_F_QUEUE_READY);
+static const uint64_t supported_vduse_features =
+	RTE_BIT64(VDUSE_F_QUEUE_READY) | RTE_BIT64(VDUSE_F_SUSPEND);
 
 static uint64_t vduse_vq_to_group(struct virtio_net *dev, struct vhost_virtqueue *vq)
 {

@@ -416,6 +417,7 @@ vduse_device_stop(struct virtio_net *dev)
 	vhost_destroy_device_notify(dev);
 
 	dev->flags &= ~VIRTIO_DEV_READY;
+	dev->vduse_suspended = false;
 
 	for (i = 0; i < dev->nr_vring; i++)
 		vduse_vring_cleanup(dev, i);

@@ -537,6 +539,12 @@ vduse_events_handler(int fd, void *arg, int *close __rte_unused)
 			resp.result = VDUSE_REQ_RESULT_FAILED;
 			break;
 		}
+		if (dev->vduse_suspended) {
+			VHOST_CONFIG_LOG(dev->ifname, ERR,
+				"SET_VQ_READY received on suspended device");
+			resp.result = VDUSE_REQ_RESULT_FAILED;
+			break;
+		}
 
 		i = req.vq_ready.num;
 		if (i >= dev->nr_vring) {

@@ -567,11 +575,43 @@ vduse_events_handler(int fd, void *arg, int *close __rte_unused)
 		vq->enabled = req.vq_ready.ready;
 		resp.result = VDUSE_REQ_RESULT_OK;
 		break;
+	case VDUSE_SUSPEND:
+		if (!(dev->vduse_features & RTE_BIT64(VDUSE_F_SUSPEND))) {
+			VHOST_CONFIG_LOG(dev->ifname, ERR,
+				"Unnegotiated suspend message");
+			resp.result = VDUSE_REQ_RESULT_FAILED;
+			break;
+		}
+		if (!(dev->status & VIRTIO_DEVICE_STATUS_DRIVER_OK)) {
+			VHOST_CONFIG_LOG(dev->ifname, ERR,
+				"Unexpected suspend message with no DRIVER_OK");
+			resp.result = VDUSE_REQ_RESULT_FAILED;
+			break;
+		}
+		for (i = 0; dev->notify_ops != NULL &&
+			    dev->notify_ops->vring_state_changed != NULL &&
+			    i < dev->nr_vring; i++) {
+			if (dev->virtqueue[i] == dev->cvq)
+				continue;
+
+			ret = dev->notify_ops->vring_state_changed(dev->vid, i, false);
+			if (ret) {
+				VHOST_CONFIG_LOG(dev->ifname, ERR,
+					"Failed to disable VQ %u for suspend", i);
+				resp.result = VDUSE_REQ_RESULT_FAILED;
+				goto out;
+			}
+		}
+		dev->vduse_suspended = true;
+		resp.result = VDUSE_REQ_RESULT_OK;
+		break;
+
 	default:
 		resp.result = VDUSE_REQ_RESULT_FAILED;
 		break;
 	}
 
+out:
 	resp.request_id = req.request_id;
 
 	ret = write(dev->vduse_dev_fd, &resp, sizeof(resp));

index 369ccf399146..d77e2003d4bd 100644
@@ -534,6 +534,7 @@ struct __rte_cache_aligned virtio_net {
 	int			vduse_dev_fd;
 	uint64_t		vduse_api_ver;
 	uint64_t		vduse_features;
+	bool			vduse_suspended;
 
 	struct vhost_virtqueue	*cvq;