X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=lib%2Flibrte_vhost%2Fvhost_user.c;h=f4c7ce462f0ba6198a7bb8d24ab1fa059391748e;hb=7da018731c565e11215e0924985e39ae24179916;hp=ada0a6367b28331fe1c23bc3ad4391fc471832de;hpb=de854fd95d5fb2037793b44f469241b1af5700f9;p=dpdk.git

diff --git a/lib/librte_vhost/vhost_user.c b/lib/librte_vhost/vhost_user.c
index ada0a6367b..f4c7ce462f 100644
--- a/lib/librte_vhost/vhost_user.c
+++ b/lib/librte_vhost/vhost_user.c
@@ -48,9 +48,13 @@
 #include <rte_malloc.h>
 #include <rte_log.h>
 
+#include "iotlb.h"
 #include "vhost.h"
 #include "vhost_user.h"
 
+#define VIRTIO_MIN_MTU 68
+#define VIRTIO_MAX_MTU 65535
+
 static const char *vhost_message_str[VHOST_USER_MAX] = {
 	[VHOST_USER_NONE] = "VHOST_USER_NONE",
 	[VHOST_USER_GET_FEATURES] = "VHOST_USER_GET_FEATURES",
@@ -72,20 +76,11 @@ static const char *vhost_message_str[VHOST_USER_MAX] = {
 	[VHOST_USER_GET_QUEUE_NUM]  = "VHOST_USER_GET_QUEUE_NUM",
 	[VHOST_USER_SET_VRING_ENABLE]  = "VHOST_USER_SET_VRING_ENABLE",
 	[VHOST_USER_SEND_RARP]  = "VHOST_USER_SEND_RARP",
+	[VHOST_USER_NET_SET_MTU]  = "VHOST_USER_NET_SET_MTU",
+	[VHOST_USER_SET_SLAVE_REQ_FD]  = "VHOST_USER_SET_SLAVE_REQ_FD",
+	[VHOST_USER_IOTLB_MSG]  = "VHOST_USER_IOTLB_MSG",
 };
 
-struct orig_region_map {
-	int fd;
-	uint64_t mapped_address;
-	uint64_t mapped_size;
-	uint64_t blksz;
-};
-
-#define orig_region(ptr, nregions) \
-	((struct orig_region_map *)RTE_PTR_ADD((ptr), \
-		sizeof(struct virtio_memory) + \
-		sizeof(struct virtio_memory_regions) * (nregions)))
-
 static uint64_t
 get_blk_size(int fd)
 {
@@ -99,18 +94,17 @@ get_blk_size(int fd)
 static void
 free_mem_region(struct virtio_net *dev)
 {
-	struct orig_region_map *region;
-	unsigned int idx;
+	uint32_t i;
+	struct rte_vhost_mem_region *reg;
 
 	if (!dev || !dev->mem)
 		return;
 
-	region = orig_region(dev->mem, dev->mem->nregions);
-	for (idx = 0; idx < dev->mem->nregions; idx++) {
-		if (region[idx].mapped_address) {
-			munmap((void *)(uintptr_t)region[idx].mapped_address,
-					region[idx].mapped_size);
-			close(region[idx].fd);
+	for (i = 0; i < dev->mem->nregions; i++) {
+		reg = &dev->mem->regions[i];
+		if (reg->host_user_addr) {
+			munmap(reg->mmap_addr, reg->mmap_size);
+			close(reg->fd);
 		}
 	}
 }
@@ -120,13 +114,22 @@ vhost_backend_cleanup(struct virtio_net *dev)
 {
 	if (dev->mem) {
 		free_mem_region(dev);
-		free(dev->mem);
+		rte_free(dev->mem);
 		dev->mem = NULL;
 	}
+
+	free(dev->guest_pages);
+	dev->guest_pages = NULL;
+
 	if (dev->log_addr) {
 		munmap((void *)(uintptr_t)dev->log_addr, dev->log_size);
 		dev->log_addr = 0;
 	}
+
+	if (dev->slave_req_fd >= 0) {
+		close(dev->slave_req_fd);
+		dev->slave_req_fd = -1;
+	}
 }
 
 /*
@@ -134,29 +137,17 @@ vhost_backend_cleanup(struct virtio_net *dev)
  * the device hasn't been initialised.
  */
 static int
-vhost_set_owner(int vid)
+vhost_user_set_owner(void)
 {
-	struct virtio_net *dev;
-
-	dev = get_device(vid);
-	if (dev == NULL)
-		return -1;
-
 	return 0;
 }
 
 static int
-vhost_reset_owner(int vid)
+vhost_user_reset_owner(struct virtio_net *dev)
 {
-	struct virtio_net *dev;
-
-	dev = get_device(vid);
-	if (dev == NULL)
-		return -1;
-
 	if (dev->flags & VIRTIO_DEV_RUNNING) {
 		dev->flags &= ~VIRTIO_DEV_RUNNING;
-		notify_ops->destroy_device(vid);
+		dev->notify_ops->destroy_device(dev->vid);
 	}
 
 	cleanup_device(dev, 0);
@@ -167,35 +158,37 @@ vhost_reset_owner(int vid)
 /*
  * The features that we support are requested.
  */
-static int
-vhost_get_features(int vid, uint64_t *pu)
+static uint64_t
+vhost_user_get_features(struct virtio_net *dev)
 {
-	struct virtio_net *dev;
-
-	dev = get_device(vid);
-	if (dev == NULL)
-		return -1;
+	uint64_t features = 0;
 
-	/* Send our supported features. */
-	*pu = VHOST_FEATURES;
-	return 0;
+	rte_vhost_driver_get_features(dev->ifname, &features);
+	return features;
 }
 
 /*
  * We receive the negotiated features supported by us and the virtio device.
  */
 static int
-vhost_set_features(int vid, uint64_t *pu)
+vhost_user_set_features(struct virtio_net *dev, uint64_t features)
 {
-	struct virtio_net *dev;
+	uint64_t vhost_features = 0;
 
-	dev = get_device(vid);
-	if (dev == NULL)
-		return -1;
-	if (*pu & ~VHOST_FEATURES)
+	rte_vhost_driver_get_features(dev->ifname, &vhost_features);
+	if (features & ~vhost_features) {
+		RTE_LOG(ERR, VHOST_CONFIG,
+			"(%d) received invalid negotiated features.\n",
+			dev->vid);
 		return -1;
+	}
 
-	dev->features = *pu;
+	if ((dev->flags & VIRTIO_DEV_RUNNING) && dev->features != features) {
+		if (dev->notify_ops->features_changed)
+			dev->notify_ops->features_changed(dev->vid, features);
+	}
+
+	dev->features = features;
 	if (dev->features &
 		((1 << VIRTIO_NET_F_MRG_RXBUF) | (1ULL << VIRTIO_F_VERSION_1))) {
 		dev->vhost_hlen = sizeof(struct virtio_net_hdr_mrg_rxbuf);
@@ -215,16 +208,44 @@ vhost_set_features(int vid, uint64_t *pu)
  * The virtio device sends us the size of the descriptor ring.
  */
 static int
-vhost_set_vring_num(int vid, struct vhost_vring_state *state)
+vhost_user_set_vring_num(struct virtio_net *dev,
+			 VhostUserMsg *msg)
 {
-	struct virtio_net *dev;
+	struct vhost_virtqueue *vq = dev->virtqueue[msg->payload.state.index];
+
+	vq->size = msg->payload.state.num;
+
+	if (dev->dequeue_zero_copy) {
+		vq->nr_zmbuf = 0;
+		vq->last_zmbuf_idx = 0;
+		vq->zmbuf_size = vq->size;
+		vq->zmbufs = rte_zmalloc(NULL, vq->zmbuf_size *
+					 sizeof(struct zcopy_mbuf), 0);
+		if (vq->zmbufs == NULL) {
+			RTE_LOG(WARNING, VHOST_CONFIG,
+				"failed to allocate mem for zero copy; "
+				"zero copy is force disabled\n");
+			dev->dequeue_zero_copy = 0;
+		}
+	}
 
-	dev = get_device(vid);
-	if (dev == NULL)
+	vq->shadow_used_ring = rte_malloc(NULL,
+				vq->size * sizeof(struct vring_used_elem),
+				RTE_CACHE_LINE_SIZE);
+	if (!vq->shadow_used_ring) {
+		RTE_LOG(ERR, VHOST_CONFIG,
+			"failed to allocate memory for shadow used ring.\n");
 		return -1;
+	}
 
-	/* State->index refers to the queue index. The txq is 1, rxq is 0. */
-	dev->virtqueue[state->index]->size = state->num;
+	vq->batch_copy_elems = rte_malloc(NULL,
+				vq->size * sizeof(struct batch_copy_elem),
+				RTE_CACHE_LINE_SIZE);
+	if (!vq->batch_copy_elems) {
+		RTE_LOG(ERR, VHOST_CONFIG,
+			"failed to allocate memory for batching copy.\n");
+		return -1;
+	}
 
 	return 0;
 }
@@ -242,13 +263,6 @@ numa_realloc(struct virtio_net *dev, int index)
 	struct vhost_virtqueue *old_vq, *vq;
 	int ret;
 
-	/*
-	 * vq is allocated on pairs, we should try to do realloc
-	 * on first queue of one queue pair only.
-	 */
-	if (index % VIRTIO_QNUM != 0)
-		return dev;
-
 	old_dev = dev;
 	vq = old_vq = dev->virtqueue[index];
 
@@ -266,12 +280,11 @@ numa_realloc(struct virtio_net *dev, int index)
 	if (oldnode != newnode) {
 		RTE_LOG(INFO, VHOST_CONFIG,
 			"reallocate vq from %d to %d node\n", oldnode, newnode);
-		vq = rte_malloc_socket(NULL, sizeof(*vq) * VIRTIO_QNUM, 0,
-				       newnode);
+		vq = rte_malloc_socket(NULL, sizeof(*vq), 0, newnode);
 		if (!vq)
 			return dev;
 
-		memcpy(vq, old_vq, sizeof(*vq) * VIRTIO_QNUM);
+		memcpy(vq, old_vq, sizeof(*vq));
 		rte_free(old_vq);
 	}
 
@@ -299,9 +312,11 @@ numa_realloc(struct virtio_net *dev, int index)
 
 out:
 	dev->virtqueue[index] = vq;
-	dev->virtqueue[index + 1] = vq + 1;
 	vhost_devices[dev->vid] = dev;
 
+	if (old_vq != vq)
+		vhost_user_iotlb_init(dev, index);
+
 	return dev;
 }
 #else
@@ -312,78 +327,90 @@ numa_realloc(struct virtio_net *dev, int index __rte_unused)
 }
 #endif
 
-/*
- * Converts QEMU virtual address to Vhost virtual address. This function is
- * used to convert the ring addresses to our address space.
- */
+/* Converts QEMU virtual address to Vhost virtual address. */
 static uint64_t
-qva_to_vva(struct virtio_net *dev, uint64_t qemu_va)
+qva_to_vva(struct virtio_net *dev, uint64_t qva)
 {
-	struct virtio_memory_regions *region;
-	uint64_t vhost_va = 0;
-	uint32_t regionidx = 0;
+	struct rte_vhost_mem_region *reg;
+	uint32_t i;
 
 	/* Find the region where the address lives. */
-	for (regionidx = 0; regionidx < dev->mem->nregions; regionidx++) {
-		region = &dev->mem->regions[regionidx];
-		if ((qemu_va >= region->userspace_address) &&
-			(qemu_va <= region->userspace_address +
-			region->memory_size)) {
-			vhost_va = qemu_va + region->guest_phys_address +
-				region->address_offset -
-				region->userspace_address;
-			break;
+	for (i = 0; i < dev->mem->nregions; i++) {
+		reg = &dev->mem->regions[i];
+
+		if (qva >= reg->guest_user_addr &&
+		    qva <  reg->guest_user_addr + reg->size) {
+			return qva - reg->guest_user_addr +
+			       reg->host_user_addr;
 		}
 	}
-	return vhost_va;
+
+	return 0;
 }
 
+
 /*
- * The virtio device sends us the desc, used and avail ring addresses.
- * This function then converts these to our address space.
+ * Converts ring address to Vhost virtual address.
+ * If IOMMU is enabled, the ring address is a guest IO virtual address,
+ * else it is a QEMU virtual address.
  */
-static int
-vhost_set_vring_addr(int vid, struct vhost_vring_addr *addr)
+static uint64_t
+ring_addr_to_vva(struct virtio_net *dev, struct vhost_virtqueue *vq,
+		uint64_t ra, uint64_t size)
 {
-	struct virtio_net *dev;
-	struct vhost_virtqueue *vq;
+	if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM)) {
+		uint64_t vva;
 
-	dev = get_device(vid);
-	if ((dev == NULL) || (dev->mem == NULL))
-		return -1;
+		vva = vhost_user_iotlb_cache_find(vq, ra,
+					&size, VHOST_ACCESS_RW);
+		if (!vva)
+			vhost_user_iotlb_miss(dev, ra, VHOST_ACCESS_RW);
 
-	/* addr->index refers to the queue index. The txq 1, rxq is 0. */
-	vq = dev->virtqueue[addr->index];
+		return vva;
+	}
+
+	return qva_to_vva(dev, ra);
+}
+
+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;
 
 	/* The addresses are converted from QEMU virtual to Vhost virtual. */
-	vq->desc = (struct vring_desc *)(uintptr_t)qva_to_vva(dev,
-			addr->desc_user_addr);
+	if (vq->desc && vq->avail && vq->used)
+		return dev;
+
+	vq->desc = (struct vring_desc *)(uintptr_t)ring_addr_to_vva(dev,
+			vq, addr->desc_user_addr, sizeof(struct vring_desc));
 	if (vq->desc == 0) {
-		RTE_LOG(ERR, VHOST_CONFIG,
+		RTE_LOG(DEBUG, VHOST_CONFIG,
 			"(%d) failed to find desc ring address.\n",
 			dev->vid);
-		return -1;
+		return dev;
 	}
 
-	dev = numa_realloc(dev, addr->index);
-	vq = dev->virtqueue[addr->index];
+	dev = numa_realloc(dev, vq_index);
+	vq = dev->virtqueue[vq_index];
+	addr = &vq->ring_addrs;
 
-	vq->avail = (struct vring_avail *)(uintptr_t)qva_to_vva(dev,
-			addr->avail_user_addr);
+	vq->avail = (struct vring_avail *)(uintptr_t)ring_addr_to_vva(dev,
+			vq, addr->avail_user_addr, sizeof(struct vring_avail));
 	if (vq->avail == 0) {
-		RTE_LOG(ERR, VHOST_CONFIG,
+		RTE_LOG(DEBUG, VHOST_CONFIG,
 			"(%d) failed to find avail ring address.\n",
 			dev->vid);
-		return -1;
+		return dev;
 	}
 
-	vq->used = (struct vring_used *)(uintptr_t)qva_to_vva(dev,
-			addr->used_user_addr);
+	vq->used = (struct vring_used *)(uintptr_t)ring_addr_to_vva(dev,
+			vq, addr->used_user_addr, sizeof(struct vring_used));
 	if (vq->used == 0) {
-		RTE_LOG(ERR, VHOST_CONFIG,
+		RTE_LOG(DEBUG, VHOST_CONFIG,
 			"(%d) failed to find used ring address.\n",
 			dev->vid);
-		return -1;
+		return dev;
 	}
 
 	if (vq->last_used_idx != vq->used->idx) {
@@ -391,7 +418,8 @@ vhost_set_vring_addr(int vid, struct vhost_vring_addr *addr)
 			"last_used_idx (%u) and vq->used->idx (%u) mismatches; "
 			"some packets maybe resent for Tx and dropped for Rx\n",
 			vq->last_used_idx, vq->used->idx);
-		vq->last_used_idx     = vq->used->idx;
+		vq->last_used_idx  = vq->used->idx;
+		vq->last_avail_idx = vq->used->idx;
 	}
 
 	vq->log_guest_addr = addr->log_guest_addr;
@@ -405,59 +433,180 @@ vhost_set_vring_addr(int vid, struct vhost_vring_addr *addr)
 	LOG_DEBUG(VHOST_CONFIG, "(%d) log_guest_addr: %" PRIx64 "\n",
 			dev->vid, vq->log_guest_addr);
 
-	return 0;
+	return dev;
 }
 
 /*
- * The virtio device sends us the available ring last used index.
+ * The virtio device sends us the desc, used and avail ring addresses.
+ * This function then converts these to our address space.
  */
 static int
-vhost_set_vring_base(int vid, struct vhost_vring_state *state)
+vhost_user_set_vring_addr(struct virtio_net **pdev, VhostUserMsg *msg)
 {
-	struct virtio_net *dev;
+	struct vhost_virtqueue *vq;
+	struct vhost_vring_addr *addr = &msg->payload.addr;
+	struct virtio_net *dev = *pdev;
 
-	dev = get_device(vid);
-	if (dev == NULL)
+	if (dev->mem == NULL)
 		return -1;
 
-	/* State->index refers to the queue index. The txq is 1, rxq is 0. */
-	dev->virtqueue[state->index]->last_used_idx = state->num;
+	/* addr->index refers to the queue index. The txq 1, rxq is 0. */
+	vq = dev->virtqueue[msg->payload.addr.index];
+
+	/*
+	 * Rings addresses should not be interpreted as long as the ring is not
+	 * started and enabled
+	 */
+	memcpy(&vq->ring_addrs, addr, sizeof(*addr));
+
+	vring_invalidate(dev, vq);
+
+	if (vq->enabled && (dev->features &
+				(1ULL << VHOST_USER_F_PROTOCOL_FEATURES))) {
+		dev = translate_ring_addresses(dev, msg->payload.state.index);
+		if (!dev)
+			return -1;
+
+		*pdev = dev;
+	}
 
 	return 0;
 }
 
+/*
+ * The virtio device sends us the available ring last used index.
+ */
 static int
-user_set_mem_table(int vid, struct VhostUserMsg *pmsg)
+vhost_user_set_vring_base(struct virtio_net *dev,
+			  VhostUserMsg *msg)
 {
-	struct VhostUserMemory memory = pmsg->payload.memory;
-	struct virtio_memory_regions *pregion;
-	uint64_t mapped_address, mapped_size;
-	struct virtio_net *dev;
-	unsigned int idx = 0;
-	struct orig_region_map *pregion_orig;
-	uint64_t alignment;
+	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;
 
-	/* unmap old memory regions one by one*/
-	dev = get_device(vid);
-	if (dev == NULL)
-		return -1;
+	return 0;
+}
 
-	/* Remove from the data plane. */
-	if (dev->flags & VIRTIO_DEV_RUNNING) {
-		dev->flags &= ~VIRTIO_DEV_RUNNING;
-		notify_ops->destroy_device(vid);
+static void
+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;
+
+	if (dev->nr_guest_pages == dev->max_guest_pages) {
+		dev->max_guest_pages *= 2;
+		dev->guest_pages = realloc(dev->guest_pages,
+					dev->max_guest_pages * sizeof(*page));
+	}
+
+	if (dev->nr_guest_pages > 0) {
+		last_page = &dev->guest_pages[dev->nr_guest_pages - 1];
+		/* merge if the two pages are continuous */
+		if (host_phys_addr == last_page->host_phys_addr +
+				      last_page->size) {
+			last_page->size += size;
+			return;
+		}
+	}
+
+	page = &dev->guest_pages[dev->nr_guest_pages++];
+	page->guest_phys_addr = guest_phys_addr;
+	page->host_phys_addr  = host_phys_addr;
+	page->size = size;
+}
+
+static void
+add_guest_pages(struct virtio_net *dev, struct rte_vhost_mem_region *reg,
+		uint64_t page_size)
+{
+	uint64_t reg_size = reg->size;
+	uint64_t host_user_addr  = reg->host_user_addr;
+	uint64_t guest_phys_addr = reg->guest_phys_addr;
+	uint64_t host_phys_addr;
+	uint64_t size;
+
+	host_phys_addr = rte_mem_virt2iova((void *)(uintptr_t)host_user_addr);
+	size = page_size - (guest_phys_addr & (page_size - 1));
+	size = RTE_MIN(size, reg_size);
+
+	add_one_guest_page(dev, guest_phys_addr, host_phys_addr, size);
+	host_user_addr  += size;
+	guest_phys_addr += size;
+	reg_size -= size;
+
+	while (reg_size > 0) {
+		size = RTE_MIN(reg_size, page_size);
+		host_phys_addr = rte_mem_virt2iova((void *)(uintptr_t)
+						  host_user_addr);
+		add_one_guest_page(dev, guest_phys_addr, host_phys_addr, size);
+
+		host_user_addr  += size;
+		guest_phys_addr += size;
+		reg_size -= size;
+	}
+}
+
+#ifdef RTE_LIBRTE_VHOST_DEBUG
+/* TODO: enable it only in debug mode? */
+static void
+dump_guest_pages(struct virtio_net *dev)
+{
+	uint32_t i;
+	struct guest_page *page;
+
+	for (i = 0; i < dev->nr_guest_pages; i++) {
+		page = &dev->guest_pages[i];
+
+		RTE_LOG(INFO, VHOST_CONFIG,
+			"guest physical page region %u\n"
+			"\t guest_phys_addr: %" PRIx64 "\n"
+			"\t host_phys_addr : %" PRIx64 "\n"
+			"\t size           : %" PRIx64 "\n",
+			i,
+			page->guest_phys_addr,
+			page->host_phys_addr,
+			page->size);
 	}
+}
+#else
+#define dump_guest_pages(dev)
+#endif
+
+static int
+vhost_user_set_mem_table(struct virtio_net *dev, struct VhostUserMsg *pmsg)
+{
+	struct VhostUserMemory memory = pmsg->payload.memory;
+	struct rte_vhost_mem_region *reg;
+	void *mmap_addr;
+	uint64_t mmap_size;
+	uint64_t mmap_offset;
+	uint64_t alignment;
+	uint32_t i;
+	int fd;
 
 	if (dev->mem) {
 		free_mem_region(dev);
-		free(dev->mem);
+		rte_free(dev->mem);
 		dev->mem = NULL;
 	}
 
-	dev->mem = calloc(1,
-		sizeof(struct virtio_memory) +
-		sizeof(struct virtio_memory_regions) * memory.nregions +
-		sizeof(struct orig_region_map) * memory.nregions);
+	dev->nr_guest_pages = 0;
+	if (!dev->guest_pages) {
+		dev->max_guest_pages = 8;
+		dev->guest_pages = malloc(dev->max_guest_pages *
+						sizeof(struct guest_page));
+		if (dev->guest_pages == NULL) {
+			RTE_LOG(ERR, VHOST_CONFIG,
+				"(%d) failed to allocate memory "
+				"for dev->guest_pages\n",
+				dev->vid);
+			return -1;
+		}
+	}
+
+	dev->mem = rte_zmalloc("vhost-mem-table", sizeof(struct rte_vhost_memory) +
+		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",
@@ -466,22 +615,17 @@ user_set_mem_table(int vid, struct VhostUserMsg *pmsg)
 	}
 	dev->mem->nregions = memory.nregions;
 
-	pregion_orig = orig_region(dev->mem, memory.nregions);
-	for (idx = 0; idx < memory.nregions; idx++) {
-		pregion = &dev->mem->regions[idx];
-		pregion->guest_phys_address =
-			memory.regions[idx].guest_phys_addr;
-		pregion->guest_phys_address_end =
-			memory.regions[idx].guest_phys_addr +
-			memory.regions[idx].memory_size;
-		pregion->memory_size =
-			memory.regions[idx].memory_size;
-		pregion->userspace_address =
-			memory.regions[idx].userspace_addr;
-
-		/* This is ugly */
-		mapped_size = memory.regions[idx].memory_size +
-			memory.regions[idx].mmap_offset;
+	for (i = 0; i < memory.nregions; i++) {
+		fd  = pmsg->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->fd              = fd;
+
+		mmap_offset = memory.regions[i].mmap_offset;
+		mmap_size   = reg->size + mmap_offset;
 
 		/* mmap() without flag of MAP_ANONYMOUS, should be called
 		 * with length argument aligned with hugepagesz at older
@@ -491,67 +635,57 @@ user_set_mem_table(int vid, struct VhostUserMsg *pmsg)
 		 * to avoid failure, make sure in caller to keep length
 		 * aligned.
 		 */
-		alignment = get_blk_size(pmsg->fds[idx]);
+		alignment = get_blk_size(fd);
 		if (alignment == (uint64_t)-1) {
 			RTE_LOG(ERR, VHOST_CONFIG,
 				"couldn't get hugepage size through fstat\n");
 			goto err_mmap;
 		}
-		mapped_size = RTE_ALIGN_CEIL(mapped_size, alignment);
-
-		mapped_address = (uint64_t)(uintptr_t)mmap(NULL,
-			mapped_size,
-			PROT_READ | PROT_WRITE, MAP_SHARED,
-			pmsg->fds[idx],
-			0);
+		mmap_size = RTE_ALIGN_CEIL(mmap_size, alignment);
 
-		RTE_LOG(INFO, VHOST_CONFIG,
-			"mapped region %d fd:%d to:%p sz:0x%"PRIx64" "
-			"off:0x%"PRIx64" align:0x%"PRIx64"\n",
-			idx, pmsg->fds[idx], (void *)(uintptr_t)mapped_address,
-			mapped_size, memory.regions[idx].mmap_offset,
-			alignment);
+		mmap_addr = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE,
+				 MAP_SHARED | MAP_POPULATE, fd, 0);
 
-		if (mapped_address == (uint64_t)(uintptr_t)MAP_FAILED) {
+		if (mmap_addr == MAP_FAILED) {
 			RTE_LOG(ERR, VHOST_CONFIG,
-				"mmap qemu guest failed.\n");
+				"mmap region %u failed.\n", i);
 			goto err_mmap;
 		}
 
-		pregion_orig[idx].mapped_address = mapped_address;
-		pregion_orig[idx].mapped_size = mapped_size;
-		pregion_orig[idx].blksz = alignment;
-		pregion_orig[idx].fd = pmsg->fds[idx];
-
-		mapped_address +=  memory.regions[idx].mmap_offset;
-
-		pregion->address_offset = mapped_address -
-			pregion->guest_phys_address;
+		reg->mmap_addr = mmap_addr;
+		reg->mmap_size = mmap_size;
+		reg->host_user_addr = (uint64_t)(uintptr_t)mmap_addr +
+				      mmap_offset;
 
-		if (memory.regions[idx].guest_phys_addr == 0) {
-			dev->mem->base_address =
-				memory.regions[idx].userspace_addr;
-			dev->mem->mapped_address =
-				pregion->address_offset;
-		}
+		if (dev->dequeue_zero_copy)
+			add_guest_pages(dev, reg, alignment);
 
-		LOG_DEBUG(VHOST_CONFIG,
-			"REGION: %u GPA: %p QEMU VA: %p SIZE (%"PRIu64")\n",
-			idx,
-			(void *)(uintptr_t)pregion->guest_phys_address,
-			(void *)(uintptr_t)pregion->userspace_address,
-			 pregion->memory_size);
+		RTE_LOG(INFO, VHOST_CONFIG,
+			"guest memory region %u, size: 0x%" PRIx64 "\n"
+			"\t guest physical addr: 0x%" PRIx64 "\n"
+			"\t guest virtual  addr: 0x%" PRIx64 "\n"
+			"\t host  virtual  addr: 0x%" PRIx64 "\n"
+			"\t mmap addr : 0x%" PRIx64 "\n"
+			"\t mmap size : 0x%" PRIx64 "\n"
+			"\t mmap align: 0x%" PRIx64 "\n"
+			"\t mmap off  : 0x%" PRIx64 "\n",
+			i, reg->size,
+			reg->guest_phys_addr,
+			reg->guest_user_addr,
+			reg->host_user_addr,
+			(uint64_t)(uintptr_t)mmap_addr,
+			mmap_size,
+			alignment,
+			mmap_offset);
 	}
 
+	dump_guest_pages(dev);
+
 	return 0;
 
 err_mmap:
-	while (idx--) {
-		munmap((void *)(uintptr_t)pregion_orig[idx].mapped_address,
-				pregion_orig[idx].mapped_size);
-		close(pregion_orig[idx].fd);
-	}
-	free(dev->mem);
+	free_mem_region(dev);
+	rte_free(dev->mem);
 	dev->mem = NULL;
 	return -1;
 }
@@ -559,7 +693,7 @@ err_mmap:
 static int
 vq_is_ready(struct vhost_virtqueue *vq)
 {
-	return vq && vq->desc   &&
+	return vq && vq->desc && vq->avail && vq->used &&
 	       vq->kickfd != VIRTIO_UNINITIALIZED_EVENTFD &&
 	       vq->callfd != VIRTIO_UNINITIALIZED_EVENTFD;
 }
@@ -567,18 +701,17 @@ vq_is_ready(struct vhost_virtqueue *vq)
 static int
 virtio_is_ready(struct virtio_net *dev)
 {
-	struct vhost_virtqueue *rvq, *tvq;
+	struct vhost_virtqueue *vq;
 	uint32_t i;
 
-	for (i = 0; i < dev->virt_qp_nb; i++) {
-		rvq = dev->virtqueue[i * VIRTIO_QNUM + VIRTIO_RXQ];
-		tvq = dev->virtqueue[i * VIRTIO_QNUM + VIRTIO_TXQ];
+	if (dev->nr_vring == 0)
+		return 0;
+
+	for (i = 0; i < dev->nr_vring; i++) {
+		vq = dev->virtqueue[i];
 
-		if (!vq_is_ready(rvq) || !vq_is_ready(tvq)) {
-			RTE_LOG(INFO, VHOST_CONFIG,
-				"virtio is not ready for processing.\n");
+		if (!vq_is_ready(vq))
 			return 0;
-		}
 	}
 
 	RTE_LOG(INFO, VHOST_CONFIG,
@@ -587,15 +720,10 @@ virtio_is_ready(struct virtio_net *dev)
 }
 
 static void
-user_set_vring_call(int vid, struct VhostUserMsg *pmsg)
+vhost_user_set_vring_call(struct virtio_net *dev, struct VhostUserMsg *pmsg)
 {
 	struct vhost_vring_file file;
-	struct virtio_net *dev = get_device(vid);
 	struct vhost_virtqueue *vq;
-	uint32_t cur_qp_idx;
-
-	if (!dev)
-		return;
 
 	file.index = pmsg->payload.u64 & VHOST_USER_VRING_IDX_MASK;
 	if (pmsg->payload.u64 & VHOST_USER_VRING_NOFD_MASK)
@@ -605,38 +733,19 @@ user_set_vring_call(int vid, struct VhostUserMsg *pmsg)
 	RTE_LOG(INFO, VHOST_CONFIG,
 		"vring call idx:%d file:%d\n", file.index, file.fd);
 
-	/*
-	 * FIXME: VHOST_SET_VRING_CALL is the first per-vring message
-	 * we get, so we do vring queue pair allocation here.
-	 */
-	cur_qp_idx = file.index / VIRTIO_QNUM;
-	if (cur_qp_idx + 1 > dev->virt_qp_nb) {
-		if (alloc_vring_queue_pair(dev, cur_qp_idx) < 0)
-			return;
-	}
-
 	vq = dev->virtqueue[file.index];
-	assert(vq != NULL);
-
 	if (vq->callfd >= 0)
 		close(vq->callfd);
 
 	vq->callfd = file.fd;
 }
 
-/*
- *  In vhost-user, when we receive kick message, will test whether virtio
- *  device is ready for packet processing.
- */
 static void
-user_set_vring_kick(int vid, struct VhostUserMsg *pmsg)
+vhost_user_set_vring_kick(struct virtio_net **pdev, struct VhostUserMsg *pmsg)
 {
 	struct vhost_vring_file file;
-	struct virtio_net *dev = get_device(vid);
 	struct vhost_virtqueue *vq;
-
-	if (!dev)
-		return;
+	struct virtio_net *dev = *pdev;
 
 	file.index = pmsg->payload.u64 & VHOST_USER_VRING_IDX_MASK;
 	if (pmsg->payload.u64 & VHOST_USER_VRING_NOFD_MASK)
@@ -646,47 +755,84 @@ user_set_vring_kick(int vid, struct VhostUserMsg *pmsg)
 	RTE_LOG(INFO, VHOST_CONFIG,
 		"vring kick idx:%d file:%d\n", file.index, file.fd);
 
+	/* Interpret ring addresses only when ring is started. */
+	dev = translate_ring_addresses(dev, file.index);
+	if (!dev)
+		return;
+
+	*pdev = dev;
+
 	vq = dev->virtqueue[file.index];
+
+	/*
+	 * When VHOST_USER_F_PROTOCOL_FEATURES is not negotiated,
+	 * the ring starts already enabled. Otherwise, it is enabled via
+	 * the SET_VRING_ENABLE message.
+	 */
+	if (!(dev->features & (1ULL << VHOST_USER_F_PROTOCOL_FEATURES)))
+		vq->enabled = 1;
+
 	if (vq->kickfd >= 0)
 		close(vq->kickfd);
 	vq->kickfd = file.fd;
+}
+
+static void
+free_zmbufs(struct vhost_virtqueue *vq)
+{
+	struct zcopy_mbuf *zmbuf, *next;
 
-	if (virtio_is_ready(dev) && !(dev->flags & VIRTIO_DEV_RUNNING)) {
-		if (notify_ops->new_device(vid) == 0)
-			dev->flags |= VIRTIO_DEV_RUNNING;
+	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);
 	}
+
+	rte_free(vq->zmbufs);
 }
 
 /*
  * when virtio is stopped, qemu will send us the GET_VRING_BASE message.
  */
 static int
-user_get_vring_base(int vid, struct vhost_vring_state *state)
+vhost_user_get_vring_base(struct virtio_net *dev,
+			  VhostUserMsg *msg)
 {
-	struct virtio_net *dev = get_device(vid);
+	struct vhost_virtqueue *vq = dev->virtqueue[msg->payload.state.index];
 
-	if (dev == NULL)
-		return -1;
 	/* We have to stop the queue (virtio) if it is running. */
 	if (dev->flags & VIRTIO_DEV_RUNNING) {
 		dev->flags &= ~VIRTIO_DEV_RUNNING;
-		notify_ops->destroy_device(vid);
+		dev->notify_ops->destroy_device(dev->vid);
 	}
 
+	dev->flags &= ~VIRTIO_DEV_READY;
+
 	/* Here we are safe to get the last used index */
-	state->num = dev->virtqueue[state->index]->last_used_idx;
+	msg->payload.state.num = vq->last_used_idx;
 
 	RTE_LOG(INFO, VHOST_CONFIG,
-		"vring base idx:%d file:%d\n", state->index, state->num);
+		"vring base idx:%d file:%d\n", msg->payload.state.index,
+		msg->payload.state.num);
 	/*
 	 * Based on current qemu vhost-user implementation, this message is
 	 * sent and only sent in vhost_vring_stop.
 	 * TODO: cleanup the vring, it isn't usable since here.
 	 */
-	if (dev->virtqueue[state->index]->kickfd >= 0)
-		close(dev->virtqueue[state->index]->kickfd);
+	if (vq->kickfd >= 0)
+		close(vq->kickfd);
+
+	vq->kickfd = VIRTIO_UNINITIALIZED_EVENTFD;
+
+	if (dev->dequeue_zero_copy)
+		free_zmbufs(vq);
+	rte_free(vq->shadow_used_ring);
+	vq->shadow_used_ring = NULL;
 
-	dev->virtqueue[state->index]->kickfd = VIRTIO_UNINITIALIZED_EVENTFD;
+	rte_free(vq->batch_copy_elems);
+	vq->batch_copy_elems = NULL;
 
 	return 0;
 }
@@ -696,51 +842,62 @@ user_get_vring_base(int vid, struct vhost_vring_state *state)
  * enable the virtio queue pair.
  */
 static int
-user_set_vring_enable(int vid, struct vhost_vring_state *state)
+vhost_user_set_vring_enable(struct virtio_net *dev,
+			    VhostUserMsg *msg)
 {
-	struct virtio_net *dev;
-	int enable = (int)state->num;
-
-	dev = get_device(vid);
-	if (dev == NULL)
-		return -1;
+	int enable = (int)msg->payload.state.num;
 
 	RTE_LOG(INFO, VHOST_CONFIG,
 		"set queue enable: %d to qp idx: %d\n",
-		enable, state->index);
+		enable, msg->payload.state.index);
 
-	if (notify_ops->vring_state_changed)
-		notify_ops->vring_state_changed(vid, state->index, enable);
+	if (dev->notify_ops->vring_state_changed)
+		dev->notify_ops->vring_state_changed(dev->vid,
+				msg->payload.state.index, enable);
 
-	dev->virtqueue[state->index]->enabled = enable;
+	dev->virtqueue[msg->payload.state.index]->enabled = enable;
 
 	return 0;
 }
 
 static void
-user_set_protocol_features(int vid, uint64_t protocol_features)
+vhost_user_get_protocol_features(struct virtio_net *dev,
+				 struct VhostUserMsg *msg)
 {
-	struct virtio_net *dev;
+	uint64_t features, protocol_features = VHOST_USER_PROTOCOL_FEATURES;
 
-	dev = get_device(vid);
-	if (dev == NULL || protocol_features & ~VHOST_USER_PROTOCOL_FEATURES)
+	rte_vhost_driver_get_features(dev->ifname, &features);
+
+	/*
+	 * REPLY_ACK protocol feature is only mandatory for now
+	 * for IOMMU feature. If IOMMU is explicitly disabled by the
+	 * application, disable also REPLY_ACK feature for older buggy
+	 * Qemu versions (from v2.7.0 to v2.9.0).
+	 */
+	if (!(features & (1ULL << VIRTIO_F_IOMMU_PLATFORM)))
+		protocol_features &= ~(1ULL << VHOST_USER_PROTOCOL_F_REPLY_ACK);
+
+	msg->payload.u64 = protocol_features;
+	msg->size = sizeof(msg->payload.u64);
+}
+
+static void
+vhost_user_set_protocol_features(struct virtio_net *dev,
+				 uint64_t protocol_features)
+{
+	if (protocol_features & ~VHOST_USER_PROTOCOL_FEATURES)
 		return;
 
 	dev->protocol_features = protocol_features;
 }
 
 static int
-user_set_log_base(int vid, struct VhostUserMsg *msg)
+vhost_user_set_log_base(struct virtio_net *dev, struct VhostUserMsg *msg)
 {
-	struct virtio_net *dev;
 	int fd = msg->fds[0];
 	uint64_t size, off;
 	void *addr;
 
-	dev = get_device(vid);
-	if (!dev)
-		return -1;
-
 	if (fd < 0) {
 		RTE_LOG(ERR, VHOST_CONFIG, "invalid log fd: %d\n", fd);
 		return -1;
@@ -793,15 +950,10 @@ user_set_log_base(int vid, struct VhostUserMsg *msg)
  * a flag 'broadcast_rarp' to let rte_vhost_dequeue_burst() inject it.
  */
 static int
-user_send_rarp(int vid, struct VhostUserMsg *msg)
+vhost_user_send_rarp(struct virtio_net *dev, struct VhostUserMsg *msg)
 {
-	struct virtio_net *dev;
 	uint8_t *mac = (uint8_t *)&msg->payload.u64;
 
-	dev = get_device(vid);
-	if (!dev)
-		return -1;
-
 	RTE_LOG(DEBUG, VHOST_CONFIG,
 		":: mac: %02x:%02x:%02x:%02x:%02x:%02x\n",
 		mac[0], mac[1], mac[2], mac[3], mac[4], mac[5]);
@@ -820,6 +972,132 @@ user_send_rarp(int vid, struct VhostUserMsg *msg)
 	return 0;
 }
 
+static int
+vhost_user_net_set_mtu(struct virtio_net *dev, struct VhostUserMsg *msg)
+{
+	if (msg->payload.u64 < VIRTIO_MIN_MTU ||
+			msg->payload.u64 > VIRTIO_MAX_MTU) {
+		RTE_LOG(ERR, VHOST_CONFIG, "Invalid MTU size (%"PRIu64")\n",
+				msg->payload.u64);
+
+		return -1;
+	}
+
+	dev->mtu = msg->payload.u64;
+
+	return 0;
+}
+
+static int
+vhost_user_set_req_fd(struct virtio_net *dev, struct VhostUserMsg *msg)
+{
+	int fd = msg->fds[0];
+
+	if (fd < 0) {
+		RTE_LOG(ERR, VHOST_CONFIG,
+				"Invalid file descriptor for slave channel (%d)\n",
+				fd);
+		return -1;
+	}
+
+	dev->slave_req_fd = fd;
+
+	return 0;
+}
+
+static int
+is_vring_iotlb_update(struct vhost_virtqueue *vq, struct vhost_iotlb_msg *imsg)
+{
+	struct vhost_vring_addr *ra;
+	uint64_t start, end;
+
+	start = imsg->iova;
+	end = start + imsg->size;
+
+	ra = &vq->ring_addrs;
+	if (ra->desc_user_addr >= start && ra->desc_user_addr < end)
+		return 1;
+	if (ra->avail_user_addr >= start && ra->avail_user_addr < end)
+		return 1;
+	if (ra->used_user_addr >= start && ra->used_user_addr < end)
+		return 1;
+
+	return 0;
+}
+
+static int
+is_vring_iotlb_invalidate(struct vhost_virtqueue *vq,
+				struct vhost_iotlb_msg *imsg)
+{
+	uint64_t istart, iend, vstart, vend;
+
+	istart = imsg->iova;
+	iend = istart + imsg->size - 1;
+
+	vstart = (uintptr_t)vq->desc;
+	vend = vstart + sizeof(struct vring_desc) * vq->size - 1;
+	if (vstart <= iend && istart <= vend)
+		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)
+		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)
+		return 1;
+
+	return 0;
+}
+
+static int
+vhost_user_iotlb_msg(struct virtio_net **pdev, struct VhostUserMsg *msg)
+{
+	struct virtio_net *dev = *pdev;
+	struct vhost_iotlb_msg *imsg = &msg->payload.iotlb;
+	uint16_t i;
+	uint64_t vva;
+
+	switch (imsg->type) {
+	case VHOST_IOTLB_UPDATE:
+		vva = qva_to_vva(dev, imsg->uaddr);
+		if (!vva)
+			return -1;
+
+		for (i = 0; i < dev->nr_vring; i++) {
+			struct vhost_virtqueue *vq = dev->virtqueue[i];
+
+			vhost_user_iotlb_cache_insert(vq, imsg->iova, vva,
+					imsg->size, imsg->perm);
+
+			if (is_vring_iotlb_update(vq, imsg))
+				*pdev = dev = translate_ring_addresses(dev, i);
+		}
+		break;
+	case VHOST_IOTLB_INVALIDATE:
+		for (i = 0; i < dev->nr_vring; i++) {
+			struct vhost_virtqueue *vq = dev->virtqueue[i];
+
+			vhost_user_iotlb_cache_remove(vq, imsg->iova,
+					imsg->size);
+
+			if (is_vring_iotlb_invalidate(vq, imsg))
+				vring_invalidate(dev, vq);
+		}
+		break;
+	default:
+		RTE_LOG(ERR, VHOST_CONFIG, "Invalid IOTLB message type (%d)\n",
+				imsg->type);
+		return -1;
+	}
+
+	return 0;
+}
+
 /* return bytes# of read on success or negative val on failure. */
 static int
 read_vhost_message(int sockfd, struct VhostUserMsg *msg)
@@ -853,30 +1131,88 @@ read_vhost_message(int sockfd, struct VhostUserMsg *msg)
 static int
 send_vhost_message(int sockfd, struct VhostUserMsg *msg)
 {
-	int ret;
+	if (!msg)
+		return 0;
 
+	return send_fd_message(sockfd, (char *)msg,
+		VHOST_USER_HDR_SIZE + msg->size, NULL, 0);
+}
+
+static int
+send_vhost_reply(int sockfd, struct VhostUserMsg *msg)
+{
 	if (!msg)
 		return 0;
 
 	msg->flags &= ~VHOST_USER_VERSION_MASK;
+	msg->flags &= ~VHOST_USER_NEED_REPLY;
 	msg->flags |= VHOST_USER_VERSION;
 	msg->flags |= VHOST_USER_REPLY_MASK;
 
-	ret = send_fd_message(sockfd, (char *)msg,
-		VHOST_USER_HDR_SIZE + msg->size, NULL, 0);
+	return send_vhost_message(sockfd, msg);
+}
 
-	return ret;
+/*
+ * Allocate a queue pair if it hasn't been allocated yet
+ */
+static int
+vhost_user_check_and_alloc_queue_pair(struct virtio_net *dev, VhostUserMsg *msg)
+{
+	uint16_t vring_idx;
+
+	switch (msg->request.master) {
+	case VHOST_USER_SET_VRING_KICK:
+	case VHOST_USER_SET_VRING_CALL:
+	case VHOST_USER_SET_VRING_ERR:
+		vring_idx = msg->payload.u64 & VHOST_USER_VRING_IDX_MASK;
+		break;
+	case VHOST_USER_SET_VRING_NUM:
+	case VHOST_USER_SET_VRING_BASE:
+	case VHOST_USER_SET_VRING_ENABLE:
+		vring_idx = msg->payload.state.index;
+		break;
+	case VHOST_USER_SET_VRING_ADDR:
+		vring_idx = msg->payload.addr.index;
+		break;
+	default:
+		return 0;
+	}
+
+	if (vring_idx >= VHOST_MAX_VRING) {
+		RTE_LOG(ERR, VHOST_CONFIG,
+			"invalid vring index: %u\n", vring_idx);
+		return -1;
+	}
+
+	if (dev->virtqueue[vring_idx])
+		return 0;
+
+	return alloc_vring_queue(dev, vring_idx);
 }
 
 int
 vhost_user_msg_handler(int vid, int fd)
 {
+	struct virtio_net *dev;
 	struct VhostUserMsg msg;
-	uint64_t features = 0;
 	int ret;
 
+	dev = get_device(vid);
+	if (dev == NULL)
+		return -1;
+
+	if (!dev->notify_ops) {
+		dev->notify_ops = vhost_driver_callback_get(dev->ifname);
+		if (!dev->notify_ops) {
+			RTE_LOG(ERR, VHOST_CONFIG,
+				"failed to get callback ops for driver %s\n",
+				dev->ifname);
+			return -1;
+		}
+	}
+
 	ret = read_vhost_message(fd, &msg);
-	if (ret <= 0 || msg.request >= VHOST_USER_MAX) {
+	if (ret <= 0 || msg.request.master >= VHOST_USER_MAX) {
 		if (ret < 0)
 			RTE_LOG(ERR, VHOST_CONFIG,
 				"vhost read message failed\n");
@@ -890,46 +1226,56 @@ vhost_user_msg_handler(int vid, int fd)
 		return -1;
 	}
 
-	RTE_LOG(INFO, VHOST_CONFIG, "read message %s\n",
-		vhost_message_str[msg.request]);
-	switch (msg.request) {
+	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]);
+
+	ret = vhost_user_check_and_alloc_queue_pair(dev, &msg);
+	if (ret < 0) {
+		RTE_LOG(ERR, VHOST_CONFIG,
+			"failed to alloc queue\n");
+		return -1;
+	}
+
+	switch (msg.request.master) {
 	case VHOST_USER_GET_FEATURES:
-		ret = vhost_get_features(vid, &features);
-		msg.payload.u64 = features;
+		msg.payload.u64 = vhost_user_get_features(dev);
 		msg.size = sizeof(msg.payload.u64);
-		send_vhost_message(fd, &msg);
+		send_vhost_reply(fd, &msg);
 		break;
 	case VHOST_USER_SET_FEATURES:
-		features = msg.payload.u64;
-		vhost_set_features(vid, &features);
+		vhost_user_set_features(dev, msg.payload.u64);
 		break;
 
 	case VHOST_USER_GET_PROTOCOL_FEATURES:
-		msg.payload.u64 = VHOST_USER_PROTOCOL_FEATURES;
-		msg.size = sizeof(msg.payload.u64);
-		send_vhost_message(fd, &msg);
+		vhost_user_get_protocol_features(dev, &msg);
+		send_vhost_reply(fd, &msg);
 		break;
 	case VHOST_USER_SET_PROTOCOL_FEATURES:
-		user_set_protocol_features(vid, msg.payload.u64);
+		vhost_user_set_protocol_features(dev, msg.payload.u64);
 		break;
 
 	case VHOST_USER_SET_OWNER:
-		vhost_set_owner(vid);
+		vhost_user_set_owner();
 		break;
 	case VHOST_USER_RESET_OWNER:
-		vhost_reset_owner(vid);
+		vhost_user_reset_owner(dev);
 		break;
 
 	case VHOST_USER_SET_MEM_TABLE:
-		user_set_mem_table(vid, &msg);
+		ret = vhost_user_set_mem_table(dev, &msg);
 		break;
 
 	case VHOST_USER_SET_LOG_BASE:
-		user_set_log_base(vid, &msg);
+		vhost_user_set_log_base(dev, &msg);
 
 		/* it needs a reply */
 		msg.size = sizeof(msg.payload.u64);
-		send_vhost_message(fd, &msg);
+		send_vhost_reply(fd, &msg);
 		break;
 	case VHOST_USER_SET_LOG_FD:
 		close(msg.fds[0]);
@@ -937,26 +1283,26 @@ vhost_user_msg_handler(int vid, int fd)
 		break;
 
 	case VHOST_USER_SET_VRING_NUM:
-		vhost_set_vring_num(vid, &msg.payload.state);
+		vhost_user_set_vring_num(dev, &msg);
 		break;
 	case VHOST_USER_SET_VRING_ADDR:
-		vhost_set_vring_addr(vid, &msg.payload.addr);
+		vhost_user_set_vring_addr(&dev, &msg);
 		break;
 	case VHOST_USER_SET_VRING_BASE:
-		vhost_set_vring_base(vid, &msg.payload.state);
+		vhost_user_set_vring_base(dev, &msg);
 		break;
 
 	case VHOST_USER_GET_VRING_BASE:
-		ret = user_get_vring_base(vid, &msg.payload.state);
+		vhost_user_get_vring_base(dev, &msg);
 		msg.size = sizeof(msg.payload.state);
-		send_vhost_message(fd, &msg);
+		send_vhost_reply(fd, &msg);
 		break;
 
 	case VHOST_USER_SET_VRING_KICK:
-		user_set_vring_kick(vid, &msg);
+		vhost_user_set_vring_kick(&dev, &msg);
 		break;
 	case VHOST_USER_SET_VRING_CALL:
-		user_set_vring_call(vid, &msg);
+		vhost_user_set_vring_call(dev, &msg);
 		break;
 
 	case VHOST_USER_SET_VRING_ERR:
@@ -968,20 +1314,79 @@ vhost_user_msg_handler(int vid, int fd)
 	case VHOST_USER_GET_QUEUE_NUM:
 		msg.payload.u64 = VHOST_MAX_QUEUE_PAIRS;
 		msg.size = sizeof(msg.payload.u64);
-		send_vhost_message(fd, &msg);
+		send_vhost_reply(fd, &msg);
 		break;
 
 	case VHOST_USER_SET_VRING_ENABLE:
-		user_set_vring_enable(vid, &msg.payload.state);
+		vhost_user_set_vring_enable(dev, &msg);
 		break;
 	case VHOST_USER_SEND_RARP:
-		user_send_rarp(vid, &msg);
+		vhost_user_send_rarp(dev, &msg);
+		break;
+
+	case VHOST_USER_NET_SET_MTU:
+		ret = vhost_user_net_set_mtu(dev, &msg);
+		break;
+
+	case VHOST_USER_SET_SLAVE_REQ_FD:
+		ret = vhost_user_set_req_fd(dev, &msg);
+		break;
+
+	case VHOST_USER_IOTLB_MSG:
+		ret = vhost_user_iotlb_msg(&dev, &msg);
 		break;
 
 	default:
+		ret = -1;
 		break;
 
 	}
 
+	if (msg.flags & VHOST_USER_NEED_REPLY) {
+		msg.payload.u64 = !!ret;
+		msg.size = sizeof(msg.payload.u64);
+		send_vhost_reply(fd, &msg);
+	}
+
+	if (!(dev->flags & VIRTIO_DEV_RUNNING) && virtio_is_ready(dev)) {
+		dev->flags |= VIRTIO_DEV_READY;
+
+		if (!(dev->flags & VIRTIO_DEV_RUNNING)) {
+			if (dev->dequeue_zero_copy) {
+				RTE_LOG(INFO, VHOST_CONFIG,
+						"dequeue zero copy is enabled\n");
+			}
+
+			if (dev->notify_ops->new_device(dev->vid) == 0)
+				dev->flags |= VIRTIO_DEV_RUNNING;
+		}
+	}
+
+	return 0;
+}
+
+int
+vhost_user_iotlb_miss(struct virtio_net *dev, uint64_t iova, uint8_t perm)
+{
+	int ret;
+	struct VhostUserMsg msg = {
+		.request.slave = VHOST_USER_SLAVE_IOTLB_MSG,
+		.flags = VHOST_USER_VERSION,
+		.size = sizeof(msg.payload.iotlb),
+		.payload.iotlb = {
+			.iova = iova,
+			.perm = perm,
+			.type = VHOST_IOTLB_MISS,
+		},
+	};
+
+	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",
+				ret);
+		return ret;
+	}
+
 	return 0;
 }