X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=lib%2Flibrte_vhost%2Fvhost_user.c;h=61ef699aced4b6c1e8369707d5e4bfc1346cef96;hb=f974ca7a2995b59b881d68b2e422c6e59f6b7069;hp=c1c5f35ff8ef6fbe90bf7db6481410891ca7cfe8;hpb=c00bb88d35fe975ede0ea35bdf4f765a2cece7e8;p=dpdk.git

diff --git a/lib/librte_vhost/vhost_user.c b/lib/librte_vhost/vhost_user.c
index c1c5f35ff8..61ef699ace 100644
--- a/lib/librte_vhost/vhost_user.c
+++ b/lib/librte_vhost/vhost_user.c
@@ -24,13 +24,23 @@
 #include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
+#include <fcntl.h>
+#include <sys/ioctl.h>
 #include <sys/mman.h>
 #include <sys/types.h>
 #include <sys/stat.h>
+#include <sys/syscall.h>
 #include <assert.h>
 #ifdef RTE_LIBRTE_VHOST_NUMA
 #include <numaif.h>
 #endif
+#ifdef RTE_LIBRTE_VHOST_POSTCOPY
+#include <linux/userfaultfd.h>
+#endif
+#ifdef F_ADD_SEALS /* if file sealing is supported, so is memfd */
+#include <linux/memfd.h>
+#define MEMFD_SUPPORTED
+#endif
 
 #include <rte_common.h>
 #include <rte_malloc.h>
@@ -43,6 +53,9 @@
 #define VIRTIO_MIN_MTU 68
 #define VIRTIO_MAX_MTU 65535
 
+#define INFLIGHT_ALIGNMENT	64
+#define INFLIGHT_VERSION	0x1
+
 static const char *vhost_message_str[VHOST_USER_MAX] = {
 	[VHOST_USER_NONE] = "VHOST_USER_NONE",
 	[VHOST_USER_GET_FEATURES] = "VHOST_USER_GET_FEATURES",
@@ -69,8 +82,16 @@ static const char *vhost_message_str[VHOST_USER_MAX] = {
 	[VHOST_USER_IOTLB_MSG]  = "VHOST_USER_IOTLB_MSG",
 	[VHOST_USER_CRYPTO_CREATE_SESS] = "VHOST_USER_CRYPTO_CREATE_SESS",
 	[VHOST_USER_CRYPTO_CLOSE_SESS] = "VHOST_USER_CRYPTO_CLOSE_SESS",
+	[VHOST_USER_POSTCOPY_ADVISE]  = "VHOST_USER_POSTCOPY_ADVISE",
+	[VHOST_USER_POSTCOPY_LISTEN]  = "VHOST_USER_POSTCOPY_LISTEN",
+	[VHOST_USER_POSTCOPY_END]  = "VHOST_USER_POSTCOPY_END",
+	[VHOST_USER_GET_INFLIGHT_FD] = "VHOST_USER_GET_INFLIGHT_FD",
+	[VHOST_USER_SET_INFLIGHT_FD] = "VHOST_USER_SET_INFLIGHT_FD",
 };
 
+static int send_vhost_reply(int sockfd, struct VhostUserMsg *msg);
+static int read_vhost_message(int sockfd, struct VhostUserMsg *msg);
+
 static uint64_t
 get_blk_size(int fd)
 {
@@ -81,15 +102,47 @@ get_blk_size(int fd)
 	return ret == -1 ? (uint64_t)-1 : (uint64_t)stat.st_blksize;
 }
 
+/*
+ * Reclaim all the outstanding zmbufs for a virtqueue.
+ */
+static void
+drain_zmbuf_list(struct vhost_virtqueue *vq)
+{
+	struct zcopy_mbuf *zmbuf, *next;
+
+	for (zmbuf = TAILQ_FIRST(&vq->zmbuf_list);
+	     zmbuf != NULL; zmbuf = next) {
+		next = TAILQ_NEXT(zmbuf, next);
+
+		while (!mbuf_is_consumed(zmbuf->mbuf))
+			usleep(1000);
+
+		TAILQ_REMOVE(&vq->zmbuf_list, zmbuf, next);
+		restore_mbuf(zmbuf->mbuf);
+		rte_pktmbuf_free(zmbuf->mbuf);
+		put_zmbuf(zmbuf);
+		vq->nr_zmbuf -= 1;
+	}
+}
+
 static void
 free_mem_region(struct virtio_net *dev)
 {
 	uint32_t i;
 	struct rte_vhost_mem_region *reg;
+	struct vhost_virtqueue *vq;
 
 	if (!dev || !dev->mem)
 		return;
 
+	if (dev->dequeue_zero_copy) {
+		for (i = 0; i < dev->nr_vring; i++) {
+			vq = dev->virtqueue[i];
+			if (vq)
+				drain_zmbuf_list(vq);
+		}
+	}
+
 	for (i = 0; i < dev->mem->nregions; i++) {
 		reg = &dev->mem->regions[i];
 		if (reg->host_user_addr) {
@@ -116,10 +169,33 @@ vhost_backend_cleanup(struct virtio_net *dev)
 		dev->log_addr = 0;
 	}
 
+	if (dev->inflight_info) {
+		if (dev->inflight_info->addr) {
+			munmap(dev->inflight_info->addr,
+			       dev->inflight_info->size);
+			dev->inflight_info->addr = NULL;
+		}
+
+		if (dev->inflight_info->fd > 0) {
+			close(dev->inflight_info->fd);
+			dev->inflight_info->fd = -1;
+		}
+
+		free(dev->inflight_info);
+		dev->inflight_info = NULL;
+	}
+
 	if (dev->slave_req_fd >= 0) {
 		close(dev->slave_req_fd);
 		dev->slave_req_fd = -1;
 	}
+
+	if (dev->postcopy_ufd >= 0) {
+		close(dev->postcopy_ufd);
+		dev->postcopy_ufd = -1;
+	}
+
+	dev->postcopy_listening = 0;
 }
 
 /*
@@ -128,28 +204,31 @@ vhost_backend_cleanup(struct virtio_net *dev)
  */
 static int
 vhost_user_set_owner(struct virtio_net **pdev __rte_unused,
-		struct VhostUserMsg *msg __rte_unused)
+			struct VhostUserMsg *msg __rte_unused,
+			int main_fd __rte_unused)
 {
-	return VH_RESULT_OK;
+	return RTE_VHOST_MSG_RESULT_OK;
 }
 
 static int
 vhost_user_reset_owner(struct virtio_net **pdev,
-		struct VhostUserMsg *msg __rte_unused)
+			struct VhostUserMsg *msg __rte_unused,
+			int main_fd __rte_unused)
 {
 	struct virtio_net *dev = *pdev;
 	vhost_destroy_device_notify(dev);
 
 	cleanup_device(dev, 0);
 	reset_device(dev);
-	return VH_RESULT_OK;
+	return RTE_VHOST_MSG_RESULT_OK;
 }
 
 /*
  * The features that we support are requested.
  */
 static int
-vhost_user_get_features(struct virtio_net **pdev, struct VhostUserMsg *msg)
+vhost_user_get_features(struct virtio_net **pdev, struct VhostUserMsg *msg,
+			int main_fd __rte_unused)
 {
 	struct virtio_net *dev = *pdev;
 	uint64_t features = 0;
@@ -158,15 +237,17 @@ vhost_user_get_features(struct virtio_net **pdev, struct VhostUserMsg *msg)
 
 	msg->payload.u64 = features;
 	msg->size = sizeof(msg->payload.u64);
+	msg->fd_num = 0;
 
-	return VH_RESULT_REPLY;
+	return RTE_VHOST_MSG_RESULT_REPLY;
 }
 
 /*
  * The queue number that we support are requested.
  */
 static int
-vhost_user_get_queue_num(struct virtio_net **pdev, struct VhostUserMsg *msg)
+vhost_user_get_queue_num(struct virtio_net **pdev, struct VhostUserMsg *msg,
+			int main_fd __rte_unused)
 {
 	struct virtio_net *dev = *pdev;
 	uint32_t queue_num = 0;
@@ -175,15 +256,17 @@ vhost_user_get_queue_num(struct virtio_net **pdev, struct VhostUserMsg *msg)
 
 	msg->payload.u64 = (uint64_t)queue_num;
 	msg->size = sizeof(msg->payload.u64);
+	msg->fd_num = 0;
 
-	return VH_RESULT_REPLY;
+	return RTE_VHOST_MSG_RESULT_REPLY;
 }
 
 /*
  * We receive the negotiated features supported by us and the virtio device.
  */
 static int
-vhost_user_set_features(struct virtio_net **pdev, struct VhostUserMsg *msg)
+vhost_user_set_features(struct virtio_net **pdev, struct VhostUserMsg *msg,
+			int main_fd __rte_unused)
 {
 	struct virtio_net *dev = *pdev;
 	uint64_t features = msg->payload.u64;
@@ -196,12 +279,12 @@ vhost_user_set_features(struct virtio_net **pdev, struct VhostUserMsg *msg)
 		RTE_LOG(ERR, VHOST_CONFIG,
 			"(%d) received invalid negotiated features.\n",
 			dev->vid);
-		return VH_RESULT_ERR;
+		return RTE_VHOST_MSG_RESULT_ERR;
 	}
 
 	if (dev->flags & VIRTIO_DEV_RUNNING) {
 		if (dev->features == features)
-			return VH_RESULT_OK;
+			return RTE_VHOST_MSG_RESULT_OK;
 
 		/*
 		 * Error out if master tries to change features while device is
@@ -212,7 +295,7 @@ vhost_user_set_features(struct virtio_net **pdev, struct VhostUserMsg *msg)
 			RTE_LOG(ERR, VHOST_CONFIG,
 				"(%d) features changed while device is running.\n",
 				dev->vid);
-			return VH_RESULT_ERR;
+			return RTE_VHOST_MSG_RESULT_ERR;
 		}
 
 		if (dev->notify_ops->features_changed)
@@ -226,6 +309,8 @@ vhost_user_set_features(struct virtio_net **pdev, struct VhostUserMsg *msg)
 	} else {
 		dev->vhost_hlen = sizeof(struct virtio_net_hdr);
 	}
+	RTE_LOG(INFO, VHOST_CONFIG,
+		"negotiated Virtio features: 0x%" PRIx64 "\n", dev->features);
 	VHOST_LOG_DEBUG(VHOST_CONFIG,
 		"(%d) mergeable RX buffers %s, virtio 1 %s\n",
 		dev->vid,
@@ -248,6 +333,7 @@ vhost_user_set_features(struct virtio_net **pdev, struct VhostUserMsg *msg)
 
 			dev->virtqueue[dev->nr_vring] = NULL;
 			cleanup_vq(vq, 1);
+			cleanup_vq_inflight(dev, vq);
 			free_vq(dev, vq);
 		}
 	}
@@ -257,7 +343,7 @@ vhost_user_set_features(struct virtio_net **pdev, struct VhostUserMsg *msg)
 	if (vdpa_dev && vdpa_dev->ops->set_features)
 		vdpa_dev->ops->set_features(dev->vid);
 
-	return VH_RESULT_OK;
+	return RTE_VHOST_MSG_RESULT_OK;
 }
 
 /*
@@ -265,7 +351,8 @@ vhost_user_set_features(struct virtio_net **pdev, struct VhostUserMsg *msg)
  */
 static int
 vhost_user_set_vring_num(struct virtio_net **pdev,
-			 struct VhostUserMsg *msg)
+			struct VhostUserMsg *msg,
+			int main_fd __rte_unused)
 {
 	struct virtio_net *dev = *pdev;
 	struct vhost_virtqueue *vq = dev->virtqueue[msg->payload.state.index];
@@ -280,7 +367,7 @@ vhost_user_set_vring_num(struct virtio_net **pdev,
 	if ((vq->size & (vq->size - 1)) || vq->size > 32768) {
 		RTE_LOG(ERR, VHOST_CONFIG,
 			"invalid virtqueue size %u\n", vq->size);
-		return VH_RESULT_ERR;
+		return RTE_VHOST_MSG_RESULT_ERR;
 	}
 
 	if (dev->dequeue_zero_copy) {
@@ -306,7 +393,7 @@ vhost_user_set_vring_num(struct virtio_net **pdev,
 		if (!vq->shadow_used_packed) {
 			RTE_LOG(ERR, VHOST_CONFIG,
 					"failed to allocate memory for shadow used ring.\n");
-			return VH_RESULT_ERR;
+			return RTE_VHOST_MSG_RESULT_ERR;
 		}
 
 	} else {
@@ -316,7 +403,7 @@ vhost_user_set_vring_num(struct virtio_net **pdev,
 		if (!vq->shadow_used_split) {
 			RTE_LOG(ERR, VHOST_CONFIG,
 					"failed to allocate memory for shadow used ring.\n");
-			return VH_RESULT_ERR;
+			return RTE_VHOST_MSG_RESULT_ERR;
 		}
 	}
 
@@ -326,10 +413,10 @@ vhost_user_set_vring_num(struct virtio_net **pdev,
 	if (!vq->batch_copy_elems) {
 		RTE_LOG(ERR, VHOST_CONFIG,
 			"failed to allocate memory for batching copy.\n");
-		return VH_RESULT_ERR;
+		return RTE_VHOST_MSG_RESULT_ERR;
 	}
 
-	return VH_RESULT_OK;
+	return RTE_VHOST_MSG_RESULT_OK;
 }
 
 /*
@@ -349,6 +436,9 @@ numa_realloc(struct virtio_net *dev, int index)
 	struct batch_copy_elem *new_batch_copy_elems;
 	int ret;
 
+	if (dev->flags & VIRTIO_DEV_RUNNING)
+		return dev;
+
 	old_dev = dev;
 	vq = old_vq = dev->virtqueue[index];
 
@@ -462,6 +552,9 @@ qva_to_vva(struct virtio_net *dev, uint64_t qva, uint64_t *len)
 	struct rte_vhost_mem_region *r;
 	uint32_t i;
 
+	if (unlikely(!dev || !dev->mem))
+		goto out_error;
+
 	/* Find the region where the address lives. */
 	for (i = 0; i < dev->mem->nregions; i++) {
 		r = &dev->mem->regions[i];
@@ -476,6 +569,7 @@ qva_to_vva(struct virtio_net *dev, uint64_t qva, uint64_t *len)
 			       r->host_user_addr;
 		}
 	}
+out_error:
 	*len = 0;
 
 	return 0;
@@ -493,11 +587,13 @@ ring_addr_to_vva(struct virtio_net *dev, struct vhost_virtqueue *vq,
 {
 	if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM)) {
 		uint64_t vva;
+		uint64_t req_size = *size;
 
 		vva = vhost_user_iotlb_cache_find(vq, ra,
 					size, VHOST_ACCESS_RW);
-		if (!vva)
-			vhost_user_iotlb_miss(dev, ra, VHOST_ACCESS_RW);
+		if (req_size != *size)
+			vhost_user_iotlb_miss(dev, (ra + *size),
+					      VHOST_ACCESS_RW);
 
 		return vva;
 	}
@@ -505,12 +601,45 @@ ring_addr_to_vva(struct virtio_net *dev, struct vhost_virtqueue *vq,
 	return qva_to_vva(dev, ra, size);
 }
 
+/*
+ * Converts vring log address to GPA
+ * If IOMMU is enabled, the log address is IOVA
+ * If IOMMU not enabled, the log address is already GPA
+ */
+static uint64_t
+translate_log_addr(struct virtio_net *dev, struct vhost_virtqueue *vq,
+		uint64_t log_addr)
+{
+	if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM)) {
+		const uint64_t exp_size = sizeof(struct vring_used) +
+			sizeof(struct vring_used_elem) * vq->size;
+		uint64_t hva, gpa;
+		uint64_t size = exp_size;
+
+		hva = vhost_iova_to_vva(dev, vq, log_addr,
+					&size, VHOST_ACCESS_RW);
+		if (size != exp_size)
+			return 0;
+
+		gpa = hva_to_gpa(dev, hva, exp_size);
+		if (!gpa) {
+			RTE_LOG(ERR, VHOST_CONFIG,
+				"VQ: Failed to find GPA for log_addr: 0x%" PRIx64 " hva: 0x%" PRIx64 "\n",
+				log_addr, hva);
+			return 0;
+		}
+		return gpa;
+
+	} else
+		return log_addr;
+}
+
 static struct virtio_net *
 translate_ring_addresses(struct virtio_net *dev, int vq_index)
 {
 	struct vhost_virtqueue *vq = dev->virtqueue[vq_index];
 	struct vhost_vring_addr *addr = &vq->ring_addrs;
-	uint64_t len;
+	uint64_t len, expected_len;
 
 	if (vq_is_packed(dev)) {
 		len = sizeof(struct vring_packed_desc) * vq->size;
@@ -554,6 +683,7 @@ translate_ring_addresses(struct virtio_net *dev, int vq_index)
 			return dev;
 		}
 
+		vq->access_ok = 1;
 		return dev;
 	}
 
@@ -576,11 +706,12 @@ translate_ring_addresses(struct virtio_net *dev, int vq_index)
 	addr = &vq->ring_addrs;
 
 	len = sizeof(struct vring_avail) + sizeof(uint16_t) * vq->size;
+	if (dev->features & (1ULL << VIRTIO_RING_F_EVENT_IDX))
+		len += sizeof(uint16_t);
+	expected_len = len;
 	vq->avail = (struct vring_avail *)(uintptr_t)ring_addr_to_vva(dev,
 			vq, addr->avail_user_addr, &len);
-	if (vq->avail == 0 ||
-			len != sizeof(struct vring_avail) +
-			sizeof(uint16_t) * vq->size) {
+	if (vq->avail == 0 || len != expected_len) {
 		RTE_LOG(DEBUG, VHOST_CONFIG,
 			"(%d) failed to map avail ring.\n",
 			dev->vid);
@@ -589,10 +720,12 @@ translate_ring_addresses(struct virtio_net *dev, int vq_index)
 
 	len = sizeof(struct vring_used) +
 		sizeof(struct vring_used_elem) * vq->size;
+	if (dev->features & (1ULL << VIRTIO_RING_F_EVENT_IDX))
+		len += sizeof(uint16_t);
+	expected_len = len;
 	vq->used = (struct vring_used *)(uintptr_t)ring_addr_to_vva(dev,
 			vq, addr->used_user_addr, &len);
-	if (vq->used == 0 || len != sizeof(struct vring_used) +
-			sizeof(struct vring_used_elem) * vq->size) {
+	if (vq->used == 0 || len != expected_len) {
 		RTE_LOG(DEBUG, VHOST_CONFIG,
 			"(%d) failed to map used ring.\n",
 			dev->vid);
@@ -608,7 +741,15 @@ translate_ring_addresses(struct virtio_net *dev, int vq_index)
 		vq->last_avail_idx = vq->used->idx;
 	}
 
-	vq->log_guest_addr = addr->log_guest_addr;
+	vq->log_guest_addr =
+		translate_log_addr(dev, vq, addr->log_guest_addr);
+	if (vq->log_guest_addr == 0) {
+		RTE_LOG(DEBUG, VHOST_CONFIG,
+			"(%d) failed to map log_guest_addr .\n",
+			dev->vid);
+		return dev;
+	}
+	vq->access_ok = 1;
 
 	VHOST_LOG_DEBUG(VHOST_CONFIG, "(%d) mapped address desc: %p\n",
 			dev->vid, vq->desc);
@@ -627,18 +768,22 @@ translate_ring_addresses(struct virtio_net *dev, int vq_index)
  * This function then converts these to our address space.
  */
 static int
-vhost_user_set_vring_addr(struct virtio_net **pdev, struct VhostUserMsg *msg)
+vhost_user_set_vring_addr(struct virtio_net **pdev, struct VhostUserMsg *msg,
+			int main_fd __rte_unused)
 {
 	struct virtio_net *dev = *pdev;
 	struct vhost_virtqueue *vq;
 	struct vhost_vring_addr *addr = &msg->payload.addr;
+	bool access_ok;
 
 	if (dev->mem == NULL)
-		return VH_RESULT_ERR;
+		return RTE_VHOST_MSG_RESULT_ERR;
 
 	/* addr->index refers to the queue index. The txq 1, rxq is 0. */
 	vq = dev->virtqueue[msg->payload.addr.index];
 
+	access_ok = vq->access_ok;
+
 	/*
 	 * Rings addresses should not be interpreted as long as the ring is not
 	 * started and enabled
@@ -647,16 +792,17 @@ vhost_user_set_vring_addr(struct virtio_net **pdev, struct VhostUserMsg *msg)
 
 	vring_invalidate(dev, vq);
 
-	if (vq->enabled && (dev->features &
-				(1ULL << VHOST_USER_F_PROTOCOL_FEATURES))) {
+	if ((vq->enabled && (dev->features &
+				(1ULL << VHOST_USER_F_PROTOCOL_FEATURES))) ||
+			access_ok) {
 		dev = translate_ring_addresses(dev, msg->payload.addr.index);
 		if (!dev)
-			return VH_RESULT_ERR;
+			return RTE_VHOST_MSG_RESULT_ERR;
 
 		*pdev = dev;
 	}
 
-	return VH_RESULT_OK;
+	return RTE_VHOST_MSG_RESULT_OK;
 }
 
 /*
@@ -664,15 +810,33 @@ vhost_user_set_vring_addr(struct virtio_net **pdev, struct VhostUserMsg *msg)
  */
 static int
 vhost_user_set_vring_base(struct virtio_net **pdev,
-			  struct VhostUserMsg *msg)
+			struct VhostUserMsg *msg,
+			int main_fd __rte_unused)
 {
 	struct virtio_net *dev = *pdev;
-	dev->virtqueue[msg->payload.state.index]->last_used_idx  =
-			msg->payload.state.num;
-	dev->virtqueue[msg->payload.state.index]->last_avail_idx =
-			msg->payload.state.num;
+	struct vhost_virtqueue *vq = dev->virtqueue[msg->payload.state.index];
+	uint64_t val = msg->payload.state.num;
 
-	return VH_RESULT_OK;
+	if (vq_is_packed(dev)) {
+		/*
+		 * Bit[0:14]: avail index
+		 * Bit[15]: avail wrap counter
+		 */
+		vq->last_avail_idx = val & 0x7fff;
+		vq->avail_wrap_counter = !!(val & (0x1 << 15));
+		/*
+		 * Set used index to same value as available one, as
+		 * their values should be the same since ring processing
+		 * was stopped at get time.
+		 */
+		vq->last_used_idx = vq->last_avail_idx;
+		vq->used_wrap_counter = vq->avail_wrap_counter;
+	} else {
+		vq->last_used_idx = msg->payload.state.num;
+		vq->last_avail_idx = msg->payload.state.num;
+	}
+
+	return RTE_VHOST_MSG_RESULT_OK;
 }
 
 static int
@@ -680,13 +844,16 @@ add_one_guest_page(struct virtio_net *dev, uint64_t guest_phys_addr,
 		   uint64_t host_phys_addr, uint64_t size)
 {
 	struct guest_page *page, *last_page;
+	struct guest_page *old_pages;
 
 	if (dev->nr_guest_pages == dev->max_guest_pages) {
 		dev->max_guest_pages *= 2;
+		old_pages = dev->guest_pages;
 		dev->guest_pages = realloc(dev->guest_pages,
 					dev->max_guest_pages * sizeof(*page));
 		if (!dev->guest_pages) {
 			RTE_LOG(ERR, VHOST_CONFIG, "cannot realloc guest_pages\n");
+			free(old_pages);
 			return -1;
 		}
 	}
@@ -797,10 +964,11 @@ vhost_memory_changed(struct VhostUserMemory *new,
 }
 
 static int
-vhost_user_set_mem_table(struct virtio_net **pdev, struct VhostUserMsg *msg)
+vhost_user_set_mem_table(struct virtio_net **pdev, struct VhostUserMsg *msg,
+			int main_fd)
 {
 	struct virtio_net *dev = *pdev;
-	struct VhostUserMemory memory = msg->payload.memory;
+	struct VhostUserMemory *memory = &msg->payload.memory;
 	struct rte_vhost_mem_region *reg;
 	void *mmap_addr;
 	uint64_t mmap_size;
@@ -810,20 +978,20 @@ vhost_user_set_mem_table(struct virtio_net **pdev, struct VhostUserMsg *msg)
 	int populate;
 	int fd;
 
-	if (memory.nregions > VHOST_MEMORY_MAX_NREGIONS) {
+	if (memory->nregions > VHOST_MEMORY_MAX_NREGIONS) {
 		RTE_LOG(ERR, VHOST_CONFIG,
-			"too many memory regions (%u)\n", memory.nregions);
-		return VH_RESULT_ERR;
+			"too many memory regions (%u)\n", memory->nregions);
+		return RTE_VHOST_MSG_RESULT_ERR;
 	}
 
-	if (dev->mem && !vhost_memory_changed(&memory, dev->mem)) {
+	if (dev->mem && !vhost_memory_changed(memory, dev->mem)) {
 		RTE_LOG(INFO, VHOST_CONFIG,
 			"(%d) memory regions not changed\n", dev->vid);
 
-		for (i = 0; i < memory.nregions; i++)
+		for (i = 0; i < memory->nregions; i++)
 			close(msg->fds[i]);
 
-		return VH_RESULT_OK;
+		return RTE_VHOST_MSG_RESULT_OK;
 	}
 
 	if (dev->mem) {
@@ -847,30 +1015,30 @@ vhost_user_set_mem_table(struct virtio_net **pdev, struct VhostUserMsg *msg)
 				"(%d) failed to allocate memory "
 				"for dev->guest_pages\n",
 				dev->vid);
-			return VH_RESULT_ERR;
+			return RTE_VHOST_MSG_RESULT_ERR;
 		}
 	}
 
 	dev->mem = rte_zmalloc("vhost-mem-table", sizeof(struct rte_vhost_memory) +
-		sizeof(struct rte_vhost_mem_region) * memory.nregions, 0);
+		sizeof(struct rte_vhost_mem_region) * memory->nregions, 0);
 	if (dev->mem == NULL) {
 		RTE_LOG(ERR, VHOST_CONFIG,
 			"(%d) failed to allocate memory for dev->mem\n",
 			dev->vid);
-		return VH_RESULT_ERR;
+		return RTE_VHOST_MSG_RESULT_ERR;
 	}
-	dev->mem->nregions = memory.nregions;
+	dev->mem->nregions = memory->nregions;
 
-	for (i = 0; i < memory.nregions; i++) {
+	for (i = 0; i < memory->nregions; i++) {
 		fd  = msg->fds[i];
 		reg = &dev->mem->regions[i];
 
-		reg->guest_phys_addr = memory.regions[i].guest_phys_addr;
-		reg->guest_user_addr = memory.regions[i].userspace_addr;
-		reg->size            = memory.regions[i].memory_size;
+		reg->guest_phys_addr = memory->regions[i].guest_phys_addr;
+		reg->guest_user_addr = memory->regions[i].userspace_addr;
+		reg->size            = memory->regions[i].memory_size;
 		reg->fd              = fd;
 
-		mmap_offset = memory.regions[i].mmap_offset;
+		mmap_offset = memory->regions[i].mmap_offset;
 
 		/* Check for memory_size + mmap_offset overflow */
 		if (mmap_offset >= -reg->size) {
@@ -939,6 +1107,70 @@ vhost_user_set_mem_table(struct virtio_net **pdev, struct VhostUserMsg *msg)
 			mmap_size,
 			alignment,
 			mmap_offset);
+
+		if (dev->postcopy_listening) {
+			/*
+			 * We haven't a better way right now than sharing
+			 * DPDK's virtual address with Qemu, so that Qemu can
+			 * retrieve the region offset when handling userfaults.
+			 */
+			memory->regions[i].userspace_addr =
+				reg->host_user_addr;
+		}
+	}
+	if (dev->postcopy_listening) {
+		/* Send the addresses back to qemu */
+		msg->fd_num = 0;
+		send_vhost_reply(main_fd, msg);
+
+		/* Wait for qemu to acknolwedge it's got the addresses
+		 * we've got to wait before we're allowed to generate faults.
+		 */
+		VhostUserMsg ack_msg;
+		if (read_vhost_message(main_fd, &ack_msg) <= 0) {
+			RTE_LOG(ERR, VHOST_CONFIG,
+				"Failed to read qemu ack on postcopy set-mem-table\n");
+			goto err_mmap;
+		}
+		if (ack_msg.request.master != VHOST_USER_SET_MEM_TABLE) {
+			RTE_LOG(ERR, VHOST_CONFIG,
+				"Bad qemu ack on postcopy set-mem-table (%d)\n",
+				ack_msg.request.master);
+			goto err_mmap;
+		}
+
+		/* Now userfault register and we can use the memory */
+		for (i = 0; i < memory->nregions; i++) {
+#ifdef RTE_LIBRTE_VHOST_POSTCOPY
+			reg = &dev->mem->regions[i];
+			struct uffdio_register reg_struct;
+
+			/*
+			 * Let's register all the mmap'ed area to ensure
+			 * alignment on page boundary.
+			 */
+			reg_struct.range.start =
+				(uint64_t)(uintptr_t)reg->mmap_addr;
+			reg_struct.range.len = reg->mmap_size;
+			reg_struct.mode = UFFDIO_REGISTER_MODE_MISSING;
+
+			if (ioctl(dev->postcopy_ufd, UFFDIO_REGISTER,
+						&reg_struct)) {
+				RTE_LOG(ERR, VHOST_CONFIG,
+					"Failed to register ufd for region %d: (ufd = %d) %s\n",
+					i, dev->postcopy_ufd,
+					strerror(errno));
+				goto err_mmap;
+			}
+			RTE_LOG(INFO, VHOST_CONFIG,
+				"\t userfaultfd registered for range : %llx - %llx\n",
+				reg_struct.range.start,
+				reg_struct.range.start +
+				reg_struct.range.len - 1);
+#else
+			goto err_mmap;
+#endif
+		}
 	}
 
 	for (i = 0; i < dev->nr_vring; i++) {
@@ -964,13 +1196,13 @@ vhost_user_set_mem_table(struct virtio_net **pdev, struct VhostUserMsg *msg)
 
 	dump_guest_pages(dev);
 
-	return VH_RESULT_OK;
+	return RTE_VHOST_MSG_RESULT_OK;
 
 err_mmap:
 	free_mem_region(dev);
 	rte_free(dev->mem);
 	dev->mem = NULL;
-	return VH_RESULT_ERR;
+	return RTE_VHOST_MSG_RESULT_ERR;
 }
 
 static bool
@@ -1012,8 +1244,237 @@ virtio_is_ready(struct virtio_net *dev)
 	return 1;
 }
 
+static void *
+inflight_mem_alloc(const char *name, size_t size, int *fd)
+{
+	void *ptr;
+	int mfd = -1;
+	char fname[20] = "/tmp/memfd-XXXXXX";
+
+	*fd = -1;
+#ifdef MEMFD_SUPPORTED
+	mfd = memfd_create(name, MFD_CLOEXEC);
+#else
+	RTE_SET_USED(name);
+#endif
+	if (mfd == -1) {
+		mfd = mkstemp(fname);
+		if (mfd == -1) {
+			RTE_LOG(ERR, VHOST_CONFIG,
+				"failed to get inflight buffer fd\n");
+			return NULL;
+		}
+
+		unlink(fname);
+	}
+
+	if (ftruncate(mfd, size) == -1) {
+		RTE_LOG(ERR, VHOST_CONFIG,
+			"failed to alloc inflight buffer\n");
+		close(mfd);
+		return NULL;
+	}
+
+	ptr = mmap(0, size, PROT_READ | PROT_WRITE, MAP_SHARED, mfd, 0);
+	if (ptr == MAP_FAILED) {
+		RTE_LOG(ERR, VHOST_CONFIG,
+			"failed to mmap inflight buffer\n");
+		close(mfd);
+		return NULL;
+	}
+
+	*fd = mfd;
+	return ptr;
+}
+
+static uint32_t
+get_pervq_shm_size_split(uint16_t queue_size)
+{
+	return RTE_ALIGN_MUL_CEIL(sizeof(struct rte_vhost_inflight_desc_split) *
+				  queue_size + sizeof(uint64_t) +
+				  sizeof(uint16_t) * 4, INFLIGHT_ALIGNMENT);
+}
+
+static uint32_t
+get_pervq_shm_size_packed(uint16_t queue_size)
+{
+	return RTE_ALIGN_MUL_CEIL(sizeof(struct rte_vhost_inflight_desc_packed)
+				  * queue_size + sizeof(uint64_t) +
+				  sizeof(uint16_t) * 6 + sizeof(uint8_t) * 9,
+				  INFLIGHT_ALIGNMENT);
+}
+
+static int
+vhost_user_get_inflight_fd(struct virtio_net **pdev,
+			   VhostUserMsg *msg,
+			   int main_fd __rte_unused)
+{
+	struct rte_vhost_inflight_info_packed *inflight_packed;
+	uint64_t pervq_inflight_size, mmap_size;
+	uint16_t num_queues, queue_size;
+	struct virtio_net *dev = *pdev;
+	int fd, i, j;
+	void *addr;
+
+	if (msg->size != sizeof(msg->payload.inflight)) {
+		RTE_LOG(ERR, VHOST_CONFIG,
+			"invalid get_inflight_fd message size is %d\n",
+			msg->size);
+		return RTE_VHOST_MSG_RESULT_ERR;
+	}
+
+	if (dev->inflight_info == NULL) {
+		dev->inflight_info = calloc(1,
+					    sizeof(struct inflight_mem_info));
+		if (!dev->inflight_info) {
+			RTE_LOG(ERR, VHOST_CONFIG,
+				"failed to alloc dev inflight area\n");
+			return RTE_VHOST_MSG_RESULT_ERR;
+		}
+	}
+
+	num_queues = msg->payload.inflight.num_queues;
+	queue_size = msg->payload.inflight.queue_size;
+
+	RTE_LOG(INFO, VHOST_CONFIG, "get_inflight_fd num_queues: %u\n",
+		msg->payload.inflight.num_queues);
+	RTE_LOG(INFO, VHOST_CONFIG, "get_inflight_fd queue_size: %u\n",
+		msg->payload.inflight.queue_size);
+
+	if (vq_is_packed(dev))
+		pervq_inflight_size = get_pervq_shm_size_packed(queue_size);
+	else
+		pervq_inflight_size = get_pervq_shm_size_split(queue_size);
+
+	mmap_size = num_queues * pervq_inflight_size;
+	addr = inflight_mem_alloc("vhost-inflight", mmap_size, &fd);
+	if (!addr) {
+		RTE_LOG(ERR, VHOST_CONFIG,
+			"failed to alloc vhost inflight area\n");
+			msg->payload.inflight.mmap_size = 0;
+		return RTE_VHOST_MSG_RESULT_ERR;
+	}
+	memset(addr, 0, mmap_size);
+
+	dev->inflight_info->addr = addr;
+	dev->inflight_info->size = msg->payload.inflight.mmap_size = mmap_size;
+	dev->inflight_info->fd = msg->fds[0] = fd;
+	msg->payload.inflight.mmap_offset = 0;
+	msg->fd_num = 1;
+
+	if (vq_is_packed(dev)) {
+		for (i = 0; i < num_queues; i++) {
+			inflight_packed =
+				(struct rte_vhost_inflight_info_packed *)addr;
+			inflight_packed->used_wrap_counter = 1;
+			inflight_packed->old_used_wrap_counter = 1;
+			for (j = 0; j < queue_size; j++)
+				inflight_packed->desc[j].next = j + 1;
+			addr = (void *)((char *)addr + pervq_inflight_size);
+		}
+	}
+
+	RTE_LOG(INFO, VHOST_CONFIG,
+		"send inflight mmap_size: %"PRIu64"\n",
+		msg->payload.inflight.mmap_size);
+	RTE_LOG(INFO, VHOST_CONFIG,
+		"send inflight mmap_offset: %"PRIu64"\n",
+		msg->payload.inflight.mmap_offset);
+	RTE_LOG(INFO, VHOST_CONFIG,
+		"send inflight fd: %d\n", msg->fds[0]);
+
+	return RTE_VHOST_MSG_RESULT_REPLY;
+}
+
+static int
+vhost_user_set_inflight_fd(struct virtio_net **pdev, VhostUserMsg *msg,
+			   int main_fd __rte_unused)
+{
+	uint64_t mmap_size, mmap_offset;
+	uint16_t num_queues, queue_size;
+	struct virtio_net *dev = *pdev;
+	uint32_t pervq_inflight_size;
+	struct vhost_virtqueue *vq;
+	void *addr;
+	int fd, i;
+
+	fd = msg->fds[0];
+	if (msg->size != sizeof(msg->payload.inflight) || fd < 0) {
+		RTE_LOG(ERR, VHOST_CONFIG,
+			"invalid set_inflight_fd message size is %d,fd is %d\n",
+			msg->size, fd);
+		return RTE_VHOST_MSG_RESULT_ERR;
+	}
+
+	mmap_size = msg->payload.inflight.mmap_size;
+	mmap_offset = msg->payload.inflight.mmap_offset;
+	num_queues = msg->payload.inflight.num_queues;
+	queue_size = msg->payload.inflight.queue_size;
+
+	if (vq_is_packed(dev))
+		pervq_inflight_size = get_pervq_shm_size_packed(queue_size);
+	else
+		pervq_inflight_size = get_pervq_shm_size_split(queue_size);
+
+	RTE_LOG(INFO, VHOST_CONFIG,
+		"set_inflight_fd mmap_size: %"PRIu64"\n", mmap_size);
+	RTE_LOG(INFO, VHOST_CONFIG,
+		"set_inflight_fd mmap_offset: %"PRIu64"\n", mmap_offset);
+	RTE_LOG(INFO, VHOST_CONFIG,
+		"set_inflight_fd num_queues: %u\n", num_queues);
+	RTE_LOG(INFO, VHOST_CONFIG,
+		"set_inflight_fd queue_size: %u\n", queue_size);
+	RTE_LOG(INFO, VHOST_CONFIG,
+		"set_inflight_fd fd: %d\n", fd);
+	RTE_LOG(INFO, VHOST_CONFIG,
+		"set_inflight_fd pervq_inflight_size: %d\n",
+		pervq_inflight_size);
+
+	if (!dev->inflight_info) {
+		dev->inflight_info = calloc(1,
+					    sizeof(struct inflight_mem_info));
+		if (dev->inflight_info == NULL) {
+			RTE_LOG(ERR, VHOST_CONFIG,
+				"failed to alloc dev inflight area\n");
+			return RTE_VHOST_MSG_RESULT_ERR;
+		}
+	}
+
+	if (dev->inflight_info->addr)
+		munmap(dev->inflight_info->addr, dev->inflight_info->size);
+
+	addr = mmap(0, mmap_size, PROT_READ | PROT_WRITE, MAP_SHARED,
+		    fd, mmap_offset);
+	if (addr == MAP_FAILED) {
+		RTE_LOG(ERR, VHOST_CONFIG, "failed to mmap share memory.\n");
+		return RTE_VHOST_MSG_RESULT_ERR;
+	}
+
+	if (dev->inflight_info->fd)
+		close(dev->inflight_info->fd);
+
+	dev->inflight_info->fd = fd;
+	dev->inflight_info->addr = addr;
+	dev->inflight_info->size = mmap_size;
+
+	for (i = 0; i < num_queues; i++) {
+		vq = dev->virtqueue[i];
+		if (vq_is_packed(dev)) {
+			vq->inflight_packed = addr;
+			vq->inflight_packed->desc_num = queue_size;
+		} else {
+			vq->inflight_split = addr;
+			vq->inflight_split->desc_num = queue_size;
+		}
+		addr = (void *)((char *)addr + pervq_inflight_size);
+	}
+
+	return RTE_VHOST_MSG_RESULT_OK;
+}
+
 static int
-vhost_user_set_vring_call(struct virtio_net **pdev, struct VhostUserMsg *msg)
+vhost_user_set_vring_call(struct virtio_net **pdev, struct VhostUserMsg *msg,
+			int main_fd __rte_unused)
 {
 	struct virtio_net *dev = *pdev;
 	struct vhost_vring_file file;
@@ -1033,21 +1494,208 @@ vhost_user_set_vring_call(struct virtio_net **pdev, struct VhostUserMsg *msg)
 
 	vq->callfd = file.fd;
 
-	return VH_RESULT_OK;
+	return RTE_VHOST_MSG_RESULT_OK;
 }
 
 static int vhost_user_set_vring_err(struct virtio_net **pdev __rte_unused,
-			struct VhostUserMsg *msg)
+			struct VhostUserMsg *msg,
+			int main_fd __rte_unused)
 {
 	if (!(msg->payload.u64 & VHOST_USER_VRING_NOFD_MASK))
 		close(msg->fds[0]);
 	RTE_LOG(INFO, VHOST_CONFIG, "not implemented\n");
 
-	return VH_RESULT_OK;
+	return RTE_VHOST_MSG_RESULT_OK;
+}
+
+static int
+resubmit_desc_compare(const void *a, const void *b)
+{
+	const struct rte_vhost_resubmit_desc *desc0 = a;
+	const struct rte_vhost_resubmit_desc *desc1 = b;
+
+	if (desc1->counter > desc0->counter)
+		return 1;
+
+	return -1;
+}
+
+static int
+vhost_check_queue_inflights_split(struct virtio_net *dev,
+				  struct vhost_virtqueue *vq)
+{
+	uint16_t i;
+	uint16_t resubmit_num = 0, last_io, num;
+	struct vring_used *used = vq->used;
+	struct rte_vhost_resubmit_info *resubmit;
+	struct rte_vhost_inflight_info_split *inflight_split;
+
+	if (!(dev->protocol_features &
+	    (1ULL << VHOST_USER_PROTOCOL_F_INFLIGHT_SHMFD)))
+		return RTE_VHOST_MSG_RESULT_OK;
+
+	if ((!vq->inflight_split))
+		return RTE_VHOST_MSG_RESULT_ERR;
+
+	if (!vq->inflight_split->version) {
+		vq->inflight_split->version = INFLIGHT_VERSION;
+		return RTE_VHOST_MSG_RESULT_OK;
+	}
+
+	if (vq->resubmit_inflight)
+		return RTE_VHOST_MSG_RESULT_OK;
+
+	inflight_split = vq->inflight_split;
+	vq->global_counter = 0;
+	last_io = inflight_split->last_inflight_io;
+
+	if (inflight_split->used_idx != used->idx) {
+		inflight_split->desc[last_io].inflight = 0;
+		rte_smp_mb();
+		inflight_split->used_idx = used->idx;
+	}
+
+	for (i = 0; i < inflight_split->desc_num; i++) {
+		if (inflight_split->desc[i].inflight == 1)
+			resubmit_num++;
+	}
+
+	vq->last_avail_idx += resubmit_num;
+
+	if (resubmit_num) {
+		resubmit  = calloc(1, sizeof(struct rte_vhost_resubmit_info));
+		if (!resubmit) {
+			RTE_LOG(ERR, VHOST_CONFIG,
+				"failed to allocate memory for resubmit info.\n");
+			return RTE_VHOST_MSG_RESULT_ERR;
+		}
+
+		resubmit->resubmit_list = calloc(resubmit_num,
+			sizeof(struct rte_vhost_resubmit_desc));
+		if (!resubmit->resubmit_list) {
+			RTE_LOG(ERR, VHOST_CONFIG,
+				"failed to allocate memory for inflight desc.\n");
+			free(resubmit);
+			return RTE_VHOST_MSG_RESULT_ERR;
+		}
+
+		num = 0;
+		for (i = 0; i < vq->inflight_split->desc_num; i++) {
+			if (vq->inflight_split->desc[i].inflight == 1) {
+				resubmit->resubmit_list[num].index = i;
+				resubmit->resubmit_list[num].counter =
+					inflight_split->desc[i].counter;
+				num++;
+			}
+		}
+		resubmit->resubmit_num = num;
+
+		if (resubmit->resubmit_num > 1)
+			qsort(resubmit->resubmit_list, resubmit->resubmit_num,
+			      sizeof(struct rte_vhost_resubmit_desc),
+			      resubmit_desc_compare);
+
+		vq->global_counter = resubmit->resubmit_list[0].counter + 1;
+		vq->resubmit_inflight = resubmit;
+	}
+
+	return RTE_VHOST_MSG_RESULT_OK;
+}
+
+static int
+vhost_check_queue_inflights_packed(struct virtio_net *dev,
+				   struct vhost_virtqueue *vq)
+{
+	uint16_t i;
+	uint16_t resubmit_num = 0, old_used_idx, num;
+	struct rte_vhost_resubmit_info *resubmit;
+	struct rte_vhost_inflight_info_packed *inflight_packed;
+
+	if (!(dev->protocol_features &
+	    (1ULL << VHOST_USER_PROTOCOL_F_INFLIGHT_SHMFD)))
+		return RTE_VHOST_MSG_RESULT_OK;
+
+	if ((!vq->inflight_packed))
+		return RTE_VHOST_MSG_RESULT_ERR;
+
+	if (!vq->inflight_packed->version) {
+		vq->inflight_packed->version = INFLIGHT_VERSION;
+		return RTE_VHOST_MSG_RESULT_OK;
+	}
+
+	if (vq->resubmit_inflight)
+		return RTE_VHOST_MSG_RESULT_OK;
+
+	inflight_packed = vq->inflight_packed;
+	vq->global_counter = 0;
+	old_used_idx = inflight_packed->old_used_idx;
+
+	if (inflight_packed->used_idx != old_used_idx) {
+		if (inflight_packed->desc[old_used_idx].inflight == 0) {
+			inflight_packed->old_used_idx =
+				inflight_packed->used_idx;
+			inflight_packed->old_used_wrap_counter =
+				inflight_packed->used_wrap_counter;
+			inflight_packed->old_free_head =
+				inflight_packed->free_head;
+		} else {
+			inflight_packed->used_idx =
+				inflight_packed->old_used_idx;
+			inflight_packed->used_wrap_counter =
+				inflight_packed->old_used_wrap_counter;
+			inflight_packed->free_head =
+				inflight_packed->old_free_head;
+		}
+	}
+
+	for (i = 0; i < inflight_packed->desc_num; i++) {
+		if (inflight_packed->desc[i].inflight == 1)
+			resubmit_num++;
+	}
+
+	if (resubmit_num) {
+		resubmit = calloc(1, sizeof(struct rte_vhost_resubmit_info));
+		if (resubmit == NULL) {
+			RTE_LOG(ERR, VHOST_CONFIG,
+				"failed to allocate memory for resubmit info.\n");
+			return RTE_VHOST_MSG_RESULT_ERR;
+		}
+
+		resubmit->resubmit_list = calloc(resubmit_num,
+			sizeof(struct rte_vhost_resubmit_desc));
+		if (resubmit->resubmit_list == NULL) {
+			RTE_LOG(ERR, VHOST_CONFIG,
+				"failed to allocate memory for resubmit desc.\n");
+			free(resubmit);
+			return RTE_VHOST_MSG_RESULT_ERR;
+		}
+
+		num = 0;
+		for (i = 0; i < inflight_packed->desc_num; i++) {
+			if (vq->inflight_packed->desc[i].inflight == 1) {
+				resubmit->resubmit_list[num].index = i;
+				resubmit->resubmit_list[num].counter =
+					inflight_packed->desc[i].counter;
+				num++;
+			}
+		}
+		resubmit->resubmit_num = num;
+
+		if (resubmit->resubmit_num > 1)
+			qsort(resubmit->resubmit_list, resubmit->resubmit_num,
+			      sizeof(struct rte_vhost_resubmit_desc),
+			      resubmit_desc_compare);
+
+		vq->global_counter = resubmit->resubmit_list[0].counter + 1;
+		vq->resubmit_inflight = resubmit;
+	}
+
+	return RTE_VHOST_MSG_RESULT_OK;
 }
 
 static int
-vhost_user_set_vring_kick(struct virtio_net **pdev, struct VhostUserMsg *msg)
+vhost_user_set_vring_kick(struct virtio_net **pdev, struct VhostUserMsg *msg,
+			int main_fd __rte_unused)
 {
 	struct virtio_net *dev = *pdev;
 	struct vhost_vring_file file;
@@ -1064,7 +1712,7 @@ vhost_user_set_vring_kick(struct virtio_net **pdev, struct VhostUserMsg *msg)
 	/* Interpret ring addresses only when ring is started. */
 	dev = translate_ring_addresses(dev, file.index);
 	if (!dev)
-		return VH_RESULT_ERR;
+		return RTE_VHOST_MSG_RESULT_ERR;
 
 	*pdev = dev;
 
@@ -1075,28 +1723,38 @@ vhost_user_set_vring_kick(struct virtio_net **pdev, struct VhostUserMsg *msg)
 	 * the ring starts already enabled. Otherwise, it is enabled via
 	 * the SET_VRING_ENABLE message.
 	 */
-	if (!(dev->features & (1ULL << VHOST_USER_F_PROTOCOL_FEATURES)))
+	if (!(dev->features & (1ULL << VHOST_USER_F_PROTOCOL_FEATURES))) {
 		vq->enabled = 1;
+		if (dev->notify_ops->vring_state_changed)
+			dev->notify_ops->vring_state_changed(
+				dev->vid, file.index, 1);
+	}
 
 	if (vq->kickfd >= 0)
 		close(vq->kickfd);
 	vq->kickfd = file.fd;
 
-	return VH_RESULT_OK;
+	if (vq_is_packed(dev)) {
+		if (vhost_check_queue_inflights_packed(dev, vq)) {
+			RTE_LOG(ERR, VHOST_CONFIG,
+				"failed to inflights for vq: %d\n", file.index);
+			return RTE_VHOST_MSG_RESULT_ERR;
+		}
+	} else {
+		if (vhost_check_queue_inflights_split(dev, vq)) {
+			RTE_LOG(ERR, VHOST_CONFIG,
+				"failed to inflights for vq: %d\n", file.index);
+			return RTE_VHOST_MSG_RESULT_ERR;
+		}
+	}
+
+	return RTE_VHOST_MSG_RESULT_OK;
 }
 
 static void
 free_zmbufs(struct vhost_virtqueue *vq)
 {
-	struct zcopy_mbuf *zmbuf, *next;
-
-	for (zmbuf = TAILQ_FIRST(&vq->zmbuf_list);
-	     zmbuf != NULL; zmbuf = next) {
-		next = TAILQ_NEXT(zmbuf, next);
-
-		rte_pktmbuf_free(zmbuf->mbuf);
-		TAILQ_REMOVE(&vq->zmbuf_list, zmbuf, next);
-	}
+	drain_zmbuf_list(vq);
 
 	rte_free(vq->zmbufs);
 }
@@ -1106,10 +1764,12 @@ free_zmbufs(struct vhost_virtqueue *vq)
  */
 static int
 vhost_user_get_vring_base(struct virtio_net **pdev,
-			  struct VhostUserMsg *msg)
+			struct VhostUserMsg *msg,
+			int main_fd __rte_unused)
 {
 	struct virtio_net *dev = *pdev;
 	struct vhost_virtqueue *vq = dev->virtqueue[msg->payload.state.index];
+	uint64_t val;
 
 	/* We have to stop the queue (virtio) if it is running. */
 	vhost_destroy_device_notify(dev);
@@ -1117,8 +1777,18 @@ vhost_user_get_vring_base(struct virtio_net **pdev,
 	dev->flags &= ~VIRTIO_DEV_READY;
 	dev->flags &= ~VIRTIO_DEV_VDPA_CONFIGURED;
 
-	/* Here we are safe to get the last avail index */
-	msg->payload.state.num = vq->last_avail_idx;
+	/* Here we are safe to get the indexes */
+	if (vq_is_packed(dev)) {
+		/*
+		 * Bit[0:14]: avail index
+		 * Bit[15]: avail wrap counter
+		 */
+		val = vq->last_avail_idx & 0x7fff;
+		val |= vq->avail_wrap_counter << 15;
+		msg->payload.state.num = val;
+	} else {
+		msg->payload.state.num = vq->last_avail_idx;
+	}
 
 	RTE_LOG(INFO, VHOST_CONFIG,
 		"vring base idx:%d file:%d\n", msg->payload.state.index,
@@ -1138,6 +1808,8 @@ vhost_user_get_vring_base(struct virtio_net **pdev,
 
 	vq->callfd = VIRTIO_UNINITIALIZED_EVENTFD;
 
+	vq->signalled_used_valid = false;
+
 	if (dev->dequeue_zero_copy)
 		free_zmbufs(vq);
 	if (vq_is_packed(dev)) {
@@ -1152,8 +1824,11 @@ vhost_user_get_vring_base(struct virtio_net **pdev,
 	vq->batch_copy_elems = NULL;
 
 	msg->size = sizeof(msg->payload.state);
+	msg->fd_num = 0;
+
+	vring_invalidate(dev, vq);
 
-	return VH_RESULT_REPLY;
+	return RTE_VHOST_MSG_RESULT_REPLY;
 }
 
 /*
@@ -1162,7 +1837,8 @@ vhost_user_get_vring_base(struct virtio_net **pdev,
  */
 static int
 vhost_user_set_vring_enable(struct virtio_net **pdev,
-			    struct VhostUserMsg *msg)
+			struct VhostUserMsg *msg,
+			int main_fd __rte_unused)
 {
 	struct virtio_net *dev = *pdev;
 	int enable = (int)msg->payload.state.num;
@@ -1183,14 +1859,19 @@ vhost_user_set_vring_enable(struct virtio_net **pdev,
 		dev->notify_ops->vring_state_changed(dev->vid,
 				index, enable);
 
+	/* On disable, rings have to be stopped being processed. */
+	if (!enable && dev->dequeue_zero_copy)
+		drain_zmbuf_list(dev->virtqueue[index]);
+
 	dev->virtqueue[index]->enabled = enable;
 
-	return VH_RESULT_OK;
+	return RTE_VHOST_MSG_RESULT_OK;
 }
 
 static int
 vhost_user_get_protocol_features(struct virtio_net **pdev,
-				 struct VhostUserMsg *msg)
+			struct VhostUserMsg *msg,
+			int main_fd __rte_unused)
 {
 	struct virtio_net *dev = *pdev;
 	uint64_t features, protocol_features;
@@ -1209,30 +1890,40 @@ vhost_user_get_protocol_features(struct virtio_net **pdev,
 
 	msg->payload.u64 = protocol_features;
 	msg->size = sizeof(msg->payload.u64);
+	msg->fd_num = 0;
 
-	return VH_RESULT_REPLY;
+	return RTE_VHOST_MSG_RESULT_REPLY;
 }
 
 static int
 vhost_user_set_protocol_features(struct virtio_net **pdev,
-				 struct VhostUserMsg *msg)
+			struct VhostUserMsg *msg,
+			int main_fd __rte_unused)
 {
 	struct virtio_net *dev = *pdev;
 	uint64_t protocol_features = msg->payload.u64;
-	if (protocol_features & ~VHOST_USER_PROTOCOL_FEATURES) {
+	uint64_t slave_protocol_features = 0;
+
+	rte_vhost_driver_get_protocol_features(dev->ifname,
+			&slave_protocol_features);
+	if (protocol_features & ~slave_protocol_features) {
 		RTE_LOG(ERR, VHOST_CONFIG,
 			"(%d) received invalid protocol features.\n",
 			dev->vid);
-		return VH_RESULT_ERR;
+		return RTE_VHOST_MSG_RESULT_ERR;
 	}
 
 	dev->protocol_features = protocol_features;
+	RTE_LOG(INFO, VHOST_CONFIG,
+		"negotiated Vhost-user protocol features: 0x%" PRIx64 "\n",
+		dev->protocol_features);
 
-	return VH_RESULT_OK;
+	return RTE_VHOST_MSG_RESULT_OK;
 }
 
 static int
-vhost_user_set_log_base(struct virtio_net **pdev, struct VhostUserMsg *msg)
+vhost_user_set_log_base(struct virtio_net **pdev, struct VhostUserMsg *msg,
+			int main_fd __rte_unused)
 {
 	struct virtio_net *dev = *pdev;
 	int fd = msg->fds[0];
@@ -1241,14 +1932,14 @@ vhost_user_set_log_base(struct virtio_net **pdev, struct VhostUserMsg *msg)
 
 	if (fd < 0) {
 		RTE_LOG(ERR, VHOST_CONFIG, "invalid log fd: %d\n", fd);
-		return VH_RESULT_ERR;
+		return RTE_VHOST_MSG_RESULT_ERR;
 	}
 
 	if (msg->size != sizeof(VhostUserLog)) {
 		RTE_LOG(ERR, VHOST_CONFIG,
 			"invalid log base msg size: %"PRId32" != %d\n",
 			msg->size, (int)sizeof(VhostUserLog));
-		return VH_RESULT_ERR;
+		return RTE_VHOST_MSG_RESULT_ERR;
 	}
 
 	size = msg->payload.log.mmap_size;
@@ -1259,7 +1950,7 @@ vhost_user_set_log_base(struct virtio_net **pdev, struct VhostUserMsg *msg)
 		RTE_LOG(ERR, VHOST_CONFIG,
 			"log offset %#"PRIx64" exceeds log size %#"PRIx64"\n",
 			off, size);
-		return VH_RESULT_ERR;
+		return RTE_VHOST_MSG_RESULT_ERR;
 	}
 
 	RTE_LOG(INFO, VHOST_CONFIG,
@@ -1274,7 +1965,7 @@ vhost_user_set_log_base(struct virtio_net **pdev, struct VhostUserMsg *msg)
 	close(fd);
 	if (addr == MAP_FAILED) {
 		RTE_LOG(ERR, VHOST_CONFIG, "mmap log base failed!\n");
-		return VH_RESULT_ERR;
+		return RTE_VHOST_MSG_RESULT_ERR;
 	}
 
 	/*
@@ -1293,17 +1984,19 @@ vhost_user_set_log_base(struct virtio_net **pdev, struct VhostUserMsg *msg)
 	 * any payload in the reply.
 	 */
 	msg->size = 0;
+	msg->fd_num = 0;
 
-	return VH_RESULT_REPLY;
+	return RTE_VHOST_MSG_RESULT_REPLY;
 }
 
 static int vhost_user_set_log_fd(struct virtio_net **pdev __rte_unused,
-			struct VhostUserMsg *msg)
+			struct VhostUserMsg *msg,
+			int main_fd __rte_unused)
 {
 	close(msg->fds[0]);
 	RTE_LOG(INFO, VHOST_CONFIG, "not implemented.\n");
 
-	return VH_RESULT_OK;
+	return RTE_VHOST_MSG_RESULT_OK;
 }
 
 /*
@@ -1315,7 +2008,8 @@ static int vhost_user_set_log_fd(struct virtio_net **pdev __rte_unused,
  * a flag 'broadcast_rarp' to let rte_vhost_dequeue_burst() inject it.
  */
 static int
-vhost_user_send_rarp(struct virtio_net **pdev, struct VhostUserMsg *msg)
+vhost_user_send_rarp(struct virtio_net **pdev, struct VhostUserMsg *msg,
+			int main_fd __rte_unused)
 {
 	struct virtio_net *dev = *pdev;
 	uint8_t *mac = (uint8_t *)&msg->payload.u64;
@@ -1341,11 +2035,12 @@ vhost_user_send_rarp(struct virtio_net **pdev, struct VhostUserMsg *msg)
 	if (vdpa_dev && vdpa_dev->ops->migration_done)
 		vdpa_dev->ops->migration_done(dev->vid);
 
-	return VH_RESULT_OK;
+	return RTE_VHOST_MSG_RESULT_OK;
 }
 
 static int
-vhost_user_net_set_mtu(struct virtio_net **pdev, struct VhostUserMsg *msg)
+vhost_user_net_set_mtu(struct virtio_net **pdev, struct VhostUserMsg *msg,
+			int main_fd __rte_unused)
 {
 	struct virtio_net *dev = *pdev;
 	if (msg->payload.u64 < VIRTIO_MIN_MTU ||
@@ -1353,16 +2048,17 @@ vhost_user_net_set_mtu(struct virtio_net **pdev, struct VhostUserMsg *msg)
 		RTE_LOG(ERR, VHOST_CONFIG, "Invalid MTU size (%"PRIu64")\n",
 				msg->payload.u64);
 
-		return VH_RESULT_ERR;
+		return RTE_VHOST_MSG_RESULT_ERR;
 	}
 
 	dev->mtu = msg->payload.u64;
 
-	return VH_RESULT_OK;
+	return RTE_VHOST_MSG_RESULT_OK;
 }
 
 static int
-vhost_user_set_req_fd(struct virtio_net **pdev, struct VhostUserMsg *msg)
+vhost_user_set_req_fd(struct virtio_net **pdev, struct VhostUserMsg *msg,
+			int main_fd __rte_unused)
 {
 	struct virtio_net *dev = *pdev;
 	int fd = msg->fds[0];
@@ -1371,65 +2067,81 @@ vhost_user_set_req_fd(struct virtio_net **pdev, struct VhostUserMsg *msg)
 		RTE_LOG(ERR, VHOST_CONFIG,
 				"Invalid file descriptor for slave channel (%d)\n",
 				fd);
-		return VH_RESULT_ERR;
+		return RTE_VHOST_MSG_RESULT_ERR;
 	}
 
+	if (dev->slave_req_fd >= 0)
+		close(dev->slave_req_fd);
+
 	dev->slave_req_fd = fd;
 
-	return VH_RESULT_OK;
+	return RTE_VHOST_MSG_RESULT_OK;
 }
 
 static int
-is_vring_iotlb_update(struct vhost_virtqueue *vq, struct vhost_iotlb_msg *imsg)
+is_vring_iotlb_split(struct vhost_virtqueue *vq, struct vhost_iotlb_msg *imsg)
 {
 	struct vhost_vring_addr *ra;
-	uint64_t start, end;
+	uint64_t start, end, len;
 
 	start = imsg->iova;
 	end = start + imsg->size;
 
 	ra = &vq->ring_addrs;
-	if (ra->desc_user_addr >= start && ra->desc_user_addr < end)
+	len = sizeof(struct vring_desc) * vq->size;
+	if (ra->desc_user_addr < end && (ra->desc_user_addr + len) > start)
 		return 1;
-	if (ra->avail_user_addr >= start && ra->avail_user_addr < end)
+
+	len = sizeof(struct vring_avail) + sizeof(uint16_t) * vq->size;
+	if (ra->avail_user_addr < end && (ra->avail_user_addr + len) > start)
 		return 1;
-	if (ra->used_user_addr >= start && ra->used_user_addr < end)
+
+	len = sizeof(struct vring_used) +
+	       sizeof(struct vring_used_elem) * vq->size;
+	if (ra->used_user_addr < end && (ra->used_user_addr + len) > start)
 		return 1;
 
 	return 0;
 }
 
 static int
-is_vring_iotlb_invalidate(struct vhost_virtqueue *vq,
-				struct vhost_iotlb_msg *imsg)
+is_vring_iotlb_packed(struct vhost_virtqueue *vq, struct vhost_iotlb_msg *imsg)
 {
-	uint64_t istart, iend, vstart, vend;
+	struct vhost_vring_addr *ra;
+	uint64_t start, end, len;
 
-	istart = imsg->iova;
-	iend = istart + imsg->size - 1;
+	start = imsg->iova;
+	end = start + imsg->size;
 
-	vstart = (uintptr_t)vq->desc;
-	vend = vstart + sizeof(struct vring_desc) * vq->size - 1;
-	if (vstart <= iend && istart <= vend)
+	ra = &vq->ring_addrs;
+	len = sizeof(struct vring_packed_desc) * vq->size;
+	if (ra->desc_user_addr < end && (ra->desc_user_addr + len) > start)
 		return 1;
 
-	vstart = (uintptr_t)vq->avail;
-	vend = vstart + sizeof(struct vring_avail);
-	vend += sizeof(uint16_t) * vq->size - 1;
-	if (vstart <= iend && istart <= vend)
+	len = sizeof(struct vring_packed_desc_event);
+	if (ra->avail_user_addr < end && (ra->avail_user_addr + len) > start)
 		return 1;
 
-	vstart = (uintptr_t)vq->used;
-	vend = vstart + sizeof(struct vring_used);
-	vend += sizeof(struct vring_used_elem) * vq->size - 1;
-	if (vstart <= iend && istart <= vend)
+	len = sizeof(struct vring_packed_desc_event);
+	if (ra->used_user_addr < end && (ra->used_user_addr + len) > start)
 		return 1;
 
 	return 0;
 }
 
+static int is_vring_iotlb(struct virtio_net *dev,
+			  struct vhost_virtqueue *vq,
+			  struct vhost_iotlb_msg *imsg)
+{
+	if (vq_is_packed(dev))
+		return is_vring_iotlb_packed(vq, imsg);
+	else
+		return is_vring_iotlb_split(vq, imsg);
+}
+
 static int
-vhost_user_iotlb_msg(struct virtio_net **pdev, struct VhostUserMsg *msg)
+vhost_user_iotlb_msg(struct virtio_net **pdev, struct VhostUserMsg *msg,
+			int main_fd __rte_unused)
 {
 	struct virtio_net *dev = *pdev;
 	struct vhost_iotlb_msg *imsg = &msg->payload.iotlb;
@@ -1441,7 +2153,7 @@ vhost_user_iotlb_msg(struct virtio_net **pdev, struct VhostUserMsg *msg)
 		len = imsg->size;
 		vva = qva_to_vva(dev, imsg->uaddr, &len);
 		if (!vva)
-			return VH_RESULT_ERR;
+			return RTE_VHOST_MSG_RESULT_ERR;
 
 		for (i = 0; i < dev->nr_vring; i++) {
 			struct vhost_virtqueue *vq = dev->virtqueue[i];
@@ -1449,7 +2161,7 @@ vhost_user_iotlb_msg(struct virtio_net **pdev, struct VhostUserMsg *msg)
 			vhost_user_iotlb_cache_insert(vq, imsg->iova, vva,
 					len, imsg->perm);
 
-			if (is_vring_iotlb_update(vq, imsg))
+			if (is_vring_iotlb(dev, vq, imsg))
 				*pdev = dev = translate_ring_addresses(dev, i);
 		}
 		break;
@@ -1460,21 +2172,95 @@ vhost_user_iotlb_msg(struct virtio_net **pdev, struct VhostUserMsg *msg)
 			vhost_user_iotlb_cache_remove(vq, imsg->iova,
 					imsg->size);
 
-			if (is_vring_iotlb_invalidate(vq, imsg))
+			if (is_vring_iotlb(dev, vq, imsg))
 				vring_invalidate(dev, vq);
 		}
 		break;
 	default:
 		RTE_LOG(ERR, VHOST_CONFIG, "Invalid IOTLB message type (%d)\n",
 				imsg->type);
-		return VH_RESULT_ERR;
+		return RTE_VHOST_MSG_RESULT_ERR;
+	}
+
+	return RTE_VHOST_MSG_RESULT_OK;
+}
+
+static int
+vhost_user_set_postcopy_advise(struct virtio_net **pdev,
+			struct VhostUserMsg *msg,
+			int main_fd __rte_unused)
+{
+	struct virtio_net *dev = *pdev;
+#ifdef RTE_LIBRTE_VHOST_POSTCOPY
+	struct uffdio_api api_struct;
+
+	dev->postcopy_ufd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK);
+
+	if (dev->postcopy_ufd == -1) {
+		RTE_LOG(ERR, VHOST_CONFIG, "Userfaultfd not available: %s\n",
+			strerror(errno));
+		return RTE_VHOST_MSG_RESULT_ERR;
+	}
+	api_struct.api = UFFD_API;
+	api_struct.features = 0;
+	if (ioctl(dev->postcopy_ufd, UFFDIO_API, &api_struct)) {
+		RTE_LOG(ERR, VHOST_CONFIG, "UFFDIO_API ioctl failure: %s\n",
+			strerror(errno));
+		close(dev->postcopy_ufd);
+		dev->postcopy_ufd = -1;
+		return RTE_VHOST_MSG_RESULT_ERR;
 	}
+	msg->fds[0] = dev->postcopy_ufd;
+	msg->fd_num = 1;
 
-	return VH_RESULT_OK;
+	return RTE_VHOST_MSG_RESULT_REPLY;
+#else
+	dev->postcopy_ufd = -1;
+	msg->fd_num = 0;
+
+	return RTE_VHOST_MSG_RESULT_ERR;
+#endif
+}
+
+static int
+vhost_user_set_postcopy_listen(struct virtio_net **pdev,
+			struct VhostUserMsg *msg __rte_unused,
+			int main_fd __rte_unused)
+{
+	struct virtio_net *dev = *pdev;
+
+	if (dev->mem && dev->mem->nregions) {
+		RTE_LOG(ERR, VHOST_CONFIG,
+			"Regions already registered at postcopy-listen\n");
+		return RTE_VHOST_MSG_RESULT_ERR;
+	}
+	dev->postcopy_listening = 1;
+
+	return RTE_VHOST_MSG_RESULT_OK;
+}
+
+static int
+vhost_user_postcopy_end(struct virtio_net **pdev, struct VhostUserMsg *msg,
+			int main_fd __rte_unused)
+{
+	struct virtio_net *dev = *pdev;
+
+	dev->postcopy_listening = 0;
+	if (dev->postcopy_ufd >= 0) {
+		close(dev->postcopy_ufd);
+		dev->postcopy_ufd = -1;
+	}
+
+	msg->payload.u64 = 0;
+	msg->size = sizeof(msg->payload.u64);
+	msg->fd_num = 0;
+
+	return RTE_VHOST_MSG_RESULT_REPLY;
 }
 
 typedef int (*vhost_message_handler_t)(struct virtio_net **pdev,
-					struct VhostUserMsg *msg);
+					struct VhostUserMsg *msg,
+					int main_fd);
 static vhost_message_handler_t vhost_message_handlers[VHOST_USER_MAX] = {
 	[VHOST_USER_NONE] = NULL,
 	[VHOST_USER_GET_FEATURES] = vhost_user_get_features,
@@ -1499,9 +2285,13 @@ static vhost_message_handler_t vhost_message_handlers[VHOST_USER_MAX] = {
 	[VHOST_USER_NET_SET_MTU] = vhost_user_net_set_mtu,
 	[VHOST_USER_SET_SLAVE_REQ_FD] = vhost_user_set_req_fd,
 	[VHOST_USER_IOTLB_MSG] = vhost_user_iotlb_msg,
+	[VHOST_USER_POSTCOPY_ADVISE] = vhost_user_set_postcopy_advise,
+	[VHOST_USER_POSTCOPY_LISTEN] = vhost_user_set_postcopy_listen,
+	[VHOST_USER_POSTCOPY_END] = vhost_user_postcopy_end,
+	[VHOST_USER_GET_INFLIGHT_FD] = vhost_user_get_inflight_fd,
+	[VHOST_USER_SET_INFLIGHT_FD] = vhost_user_set_inflight_fd,
 };
 
-
 /* return bytes# of read on success or negative val on failure. */
 static int
 read_vhost_message(int sockfd, struct VhostUserMsg *msg)
@@ -1513,7 +2303,7 @@ read_vhost_message(int sockfd, struct VhostUserMsg *msg)
 	if (ret <= 0)
 		return ret;
 
-	if (msg && msg->size) {
+	if (msg->size) {
 		if (msg->size > sizeof(msg->payload)) {
 			RTE_LOG(ERR, VHOST_CONFIG,
 				"invalid msg size: %d\n", msg->size);
@@ -1533,13 +2323,13 @@ read_vhost_message(int sockfd, struct VhostUserMsg *msg)
 }
 
 static int
-send_vhost_message(int sockfd, struct VhostUserMsg *msg, int *fds, int fd_num)
+send_vhost_message(int sockfd, struct VhostUserMsg *msg)
 {
 	if (!msg)
 		return 0;
 
 	return send_fd_message(sockfd, (char *)msg,
-		VHOST_USER_HDR_SIZE + msg->size, fds, fd_num);
+		VHOST_USER_HDR_SIZE + msg->size, msg->fds, msg->fd_num);
 }
 
 static int
@@ -1553,19 +2343,18 @@ send_vhost_reply(int sockfd, struct VhostUserMsg *msg)
 	msg->flags |= VHOST_USER_VERSION;
 	msg->flags |= VHOST_USER_REPLY_MASK;
 
-	return send_vhost_message(sockfd, msg, NULL, 0);
+	return send_vhost_message(sockfd, msg);
 }
 
 static int
-send_vhost_slave_message(struct virtio_net *dev, struct VhostUserMsg *msg,
-			 int *fds, int fd_num)
+send_vhost_slave_message(struct virtio_net *dev, struct VhostUserMsg *msg)
 {
 	int ret;
 
 	if (msg->flags & VHOST_USER_NEED_REPLY)
 		rte_spinlock_lock(&dev->slave_req_lock);
 
-	ret = send_vhost_message(dev->slave_req_fd, msg, fds, fd_num);
+	ret = send_vhost_message(dev->slave_req_fd, msg);
 	if (ret < 0 && (msg->flags & VHOST_USER_NEED_REPLY))
 		rte_spinlock_unlock(&dev->slave_req_lock);
 
@@ -1654,7 +2443,7 @@ vhost_user_msg_handler(int vid, int fd)
 	int did = -1;
 	int ret;
 	int unlock_required = 0;
-	uint32_t skip_master = 0;
+	bool handled;
 	int request;
 
 	dev = get_device(vid);
@@ -1672,27 +2461,30 @@ vhost_user_msg_handler(int vid, int fd)
 	}
 
 	ret = read_vhost_message(fd, &msg);
-	if (ret <= 0 || msg.request.master >= VHOST_USER_MAX) {
+	if (ret <= 0) {
 		if (ret < 0)
 			RTE_LOG(ERR, VHOST_CONFIG,
 				"vhost read message failed\n");
-		else if (ret == 0)
+		else
 			RTE_LOG(INFO, VHOST_CONFIG,
 				"vhost peer closed\n");
-		else
-			RTE_LOG(ERR, VHOST_CONFIG,
-				"vhost read incorrect message\n");
 
 		return -1;
 	}
 
 	ret = 0;
-	if (msg.request.master != VHOST_USER_IOTLB_MSG)
-		RTE_LOG(INFO, VHOST_CONFIG, "read message %s\n",
-			vhost_message_str[msg.request.master]);
-	else
-		RTE_LOG(DEBUG, VHOST_CONFIG, "read message %s\n",
-			vhost_message_str[msg.request.master]);
+	request = msg.request.master;
+	if (request > VHOST_USER_NONE && request < VHOST_USER_MAX &&
+			vhost_message_str[request]) {
+		if (request != VHOST_USER_IOTLB_MSG)
+			RTE_LOG(INFO, VHOST_CONFIG, "read message %s\n",
+				vhost_message_str[request]);
+		else
+			RTE_LOG(DEBUG, VHOST_CONFIG, "read message %s\n",
+				vhost_message_str[request]);
+	} else {
+		RTE_LOG(DEBUG, VHOST_CONFIG, "External request %d\n", request);
+	}
 
 	ret = vhost_user_check_and_alloc_queue_pair(dev, &msg);
 	if (ret < 0) {
@@ -1708,7 +2500,7 @@ vhost_user_msg_handler(int vid, int fd)
 	 * inactive, so it is safe. Otherwise taking the access_lock
 	 * would cause a dead lock.
 	 */
-	switch (msg.request.master) {
+	switch (request) {
 	case VHOST_USER_SET_FEATURES:
 	case VHOST_USER_SET_PROTOCOL_FEATURES:
 	case VHOST_USER_SET_OWNER:
@@ -1733,72 +2525,93 @@ vhost_user_msg_handler(int vid, int fd)
 
 	}
 
+	handled = false;
 	if (dev->extern_ops.pre_msg_handle) {
 		ret = (*dev->extern_ops.pre_msg_handle)(dev->vid,
-				(void *)&msg, &skip_master);
-		if (ret == VH_RESULT_ERR)
-			goto skip_to_reply;
-		else if (ret == VH_RESULT_REPLY)
+				(void *)&msg);
+		switch (ret) {
+		case RTE_VHOST_MSG_RESULT_REPLY:
 			send_vhost_reply(fd, &msg);
-
-		if (skip_master)
+			/* Fall-through */
+		case RTE_VHOST_MSG_RESULT_ERR:
+		case RTE_VHOST_MSG_RESULT_OK:
+			handled = true;
 			goto skip_to_post_handle;
+		case RTE_VHOST_MSG_RESULT_NOT_HANDLED:
+		default:
+			break;
+		}
 	}
 
-	request = msg.request.master;
 	if (request > VHOST_USER_NONE && request < VHOST_USER_MAX) {
 		if (!vhost_message_handlers[request])
 			goto skip_to_post_handle;
-		ret = vhost_message_handlers[request](&dev, &msg);
+		ret = vhost_message_handlers[request](&dev, &msg, fd);
 
 		switch (ret) {
-		case VH_RESULT_ERR:
+		case RTE_VHOST_MSG_RESULT_ERR:
 			RTE_LOG(ERR, VHOST_CONFIG,
 				"Processing %s failed.\n",
 				vhost_message_str[request]);
+			handled = true;
 			break;
-		case VH_RESULT_OK:
+		case RTE_VHOST_MSG_RESULT_OK:
 			RTE_LOG(DEBUG, VHOST_CONFIG,
 				"Processing %s succeeded.\n",
 				vhost_message_str[request]);
+			handled = true;
 			break;
-		case VH_RESULT_REPLY:
+		case RTE_VHOST_MSG_RESULT_REPLY:
 			RTE_LOG(DEBUG, VHOST_CONFIG,
 				"Processing %s succeeded and needs reply.\n",
 				vhost_message_str[request]);
 			send_vhost_reply(fd, &msg);
+			handled = true;
+			break;
+		default:
 			break;
 		}
-	} else {
-		RTE_LOG(ERR, VHOST_CONFIG,
-			"Requested invalid message type %d.\n", request);
-		ret = VH_RESULT_ERR;
 	}
 
 skip_to_post_handle:
-	if (ret != VH_RESULT_ERR && dev->extern_ops.post_msg_handle) {
-		ret = (*dev->extern_ops.post_msg_handle)(
-				dev->vid, (void *)&msg);
-		if (ret == VH_RESULT_ERR)
-			goto skip_to_reply;
-		else if (ret == VH_RESULT_REPLY)
+	if (ret != RTE_VHOST_MSG_RESULT_ERR &&
+			dev->extern_ops.post_msg_handle) {
+		ret = (*dev->extern_ops.post_msg_handle)(dev->vid,
+				(void *)&msg);
+		switch (ret) {
+		case RTE_VHOST_MSG_RESULT_REPLY:
 			send_vhost_reply(fd, &msg);
+			/* Fall-through */
+		case RTE_VHOST_MSG_RESULT_ERR:
+		case RTE_VHOST_MSG_RESULT_OK:
+			handled = true;
+		case RTE_VHOST_MSG_RESULT_NOT_HANDLED:
+		default:
+			break;
+		}
 	}
 
-skip_to_reply:
 	if (unlock_required)
 		vhost_user_unlock_all_queue_pairs(dev);
 
+	/* If message was not handled at this stage, treat it as an error */
+	if (!handled) {
+		RTE_LOG(ERR, VHOST_CONFIG,
+			"vhost message (req: %d) was not handled.\n", request);
+		ret = RTE_VHOST_MSG_RESULT_ERR;
+	}
+
 	/*
 	 * If the request required a reply that was already sent,
 	 * this optional reply-ack won't be sent as the
 	 * VHOST_USER_NEED_REPLY was cleared in send_vhost_reply().
 	 */
 	if (msg.flags & VHOST_USER_NEED_REPLY) {
-		msg.payload.u64 = ret == VH_RESULT_ERR;
+		msg.payload.u64 = ret == RTE_VHOST_MSG_RESULT_ERR;
 		msg.size = sizeof(msg.payload.u64);
+		msg.fd_num = 0;
 		send_vhost_reply(fd, &msg);
-	} else if (ret == VH_RESULT_ERR) {
+	} else if (ret == RTE_VHOST_MSG_RESULT_ERR) {
 		RTE_LOG(ERR, VHOST_CONFIG,
 			"vhost message handling failed.\n");
 		return -1;
@@ -1822,15 +2635,10 @@ skip_to_reply:
 	vdpa_dev = rte_vdpa_get_device(did);
 	if (vdpa_dev && virtio_is_ready(dev) &&
 			!(dev->flags & VIRTIO_DEV_VDPA_CONFIGURED) &&
-			msg.request.master == VHOST_USER_SET_VRING_ENABLE) {
+			msg.request.master == VHOST_USER_SET_VRING_CALL) {
 		if (vdpa_dev->ops->dev_conf)
 			vdpa_dev->ops->dev_conf(dev->vid);
 		dev->flags |= VIRTIO_DEV_VDPA_CONFIGURED;
-		if (vhost_user_host_notifier_ctrl(dev->vid, true) != 0) {
-			RTE_LOG(INFO, VHOST_CONFIG,
-				"(%d) software relay is used for vDPA, performance may be low.\n",
-				dev->vid);
-		}
 	}
 
 	return 0;
@@ -1880,7 +2688,7 @@ vhost_user_iotlb_miss(struct virtio_net *dev, uint64_t iova, uint8_t perm)
 		},
 	};
 
-	ret = send_vhost_message(dev->slave_req_fd, &msg, NULL, 0);
+	ret = send_vhost_message(dev->slave_req_fd, &msg);
 	if (ret < 0) {
 		RTE_LOG(ERR, VHOST_CONFIG,
 				"Failed to send IOTLB miss message (%d)\n",
@@ -1896,8 +2704,6 @@ static int vhost_user_slave_set_vring_host_notifier(struct virtio_net *dev,
 						    uint64_t offset,
 						    uint64_t size)
 {
-	int *fdp = NULL;
-	size_t fd_num = 0;
 	int ret;
 	struct VhostUserMsg msg = {
 		.request.slave = VHOST_USER_SLAVE_VRING_HOST_NOTIFIER_MSG,
@@ -1913,11 +2719,11 @@ static int vhost_user_slave_set_vring_host_notifier(struct virtio_net *dev,
 	if (fd < 0)
 		msg.payload.area.u64 |= VHOST_USER_VRING_NOFD_MASK;
 	else {
-		fdp = &fd;
-		fd_num = 1;
+		msg.fds[0] = fd;
+		msg.fd_num = 1;
 	}
 
-	ret = send_vhost_slave_message(dev, &msg, fdp, fd_num);
+	ret = send_vhost_slave_message(dev, &msg);
 	if (ret < 0) {
 		RTE_LOG(ERR, VHOST_CONFIG,
 			"Failed to set host notifier (%d)\n", ret);
@@ -1927,7 +2733,7 @@ static int vhost_user_slave_set_vring_host_notifier(struct virtio_net *dev,
 	return process_slave_message_reply(dev, &msg);
 }
 
-int vhost_user_host_notifier_ctrl(int vid, bool enable)
+int rte_vhost_host_notifier_ctrl(int vid, bool enable)
 {
 	struct virtio_net *dev;
 	struct rte_vdpa_device *vdpa_dev;