diff options
Diffstat (limited to 'lib/librte_vhost/vhost_user.c')
| -rw-r--r-- | lib/librte_vhost/vhost_user.c | 246 |
1 files changed, 217 insertions, 29 deletions
diff --git a/lib/librte_vhost/vhost_user.c b/lib/librte_vhost/vhost_user.c index 2d008fb0..947290fc 100644 --- a/lib/librte_vhost/vhost_user.c +++ b/lib/librte_vhost/vhost_user.c @@ -1,5 +1,22 @@ /* SPDX-License-Identifier: BSD-3-Clause - * Copyright(c) 2010-2016 Intel Corporation + * Copyright(c) 2010-2018 Intel Corporation + */ + +/* Security model + * -------------- + * The vhost-user protocol connection is an external interface, so it must be + * robust against invalid inputs. + * + * This is important because the vhost-user master is only one step removed + * from the guest. Malicious guests that have escaped will then launch further + * attacks from the vhost-user master. + * + * Even in deployments where guests are trusted, a bug in the vhost-user master + * can still cause invalid messages to be sent. Such messages must not + * compromise the stability of the DPDK application by causing crashes, memory + * corruption, or other problematic behavior. + * + * Do not assume received VhostUserMsg fields contain sensible values! */ #include <stdint.h> @@ -50,6 +67,8 @@ static const char *vhost_message_str[VHOST_USER_MAX] = { [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", + [VHOST_USER_CRYPTO_CREATE_SESS] = "VHOST_USER_CRYPTO_CREATE_SESS", + [VHOST_USER_CRYPTO_CLOSE_SESS] = "VHOST_USER_CRYPTO_CLOSE_SESS", }; static uint64_t @@ -116,7 +135,14 @@ vhost_user_set_owner(void) static int vhost_user_reset_owner(struct virtio_net *dev) { + struct rte_vdpa_device *vdpa_dev; + int did = -1; + if (dev->flags & VIRTIO_DEV_RUNNING) { + did = dev->vdpa_dev_id; + vdpa_dev = rte_vdpa_get_device(did); + if (vdpa_dev && vdpa_dev->ops->dev_close) + vdpa_dev->ops->dev_close(dev->vid); dev->flags &= ~VIRTIO_DEV_RUNNING; dev->notify_ops->destroy_device(dev->vid); } @@ -139,12 +165,26 @@ vhost_user_get_features(struct virtio_net *dev) } /* + * The queue number that we support are requested. + */ +static uint32_t +vhost_user_get_queue_num(struct virtio_net *dev) +{ + uint32_t queue_num = 0; + + rte_vhost_driver_get_queue_num(dev->ifname, &queue_num); + return queue_num; +} + +/* * We receive the negotiated features supported by us and the virtio device. */ static int vhost_user_set_features(struct virtio_net *dev, uint64_t features) { uint64_t vhost_features = 0; + struct rte_vdpa_device *vdpa_dev; + int did = -1; rte_vhost_driver_get_features(dev->ifname, &vhost_features); if (features & ~vhost_features) { @@ -181,7 +221,7 @@ vhost_user_set_features(struct virtio_net *dev, uint64_t features) } else { dev->vhost_hlen = sizeof(struct virtio_net_hdr); } - LOG_DEBUG(VHOST_CONFIG, + VHOST_LOG_DEBUG(VHOST_CONFIG, "(%d) mergeable RX buffers %s, virtio 1 %s\n", dev->vid, (dev->features & (1 << VIRTIO_NET_F_MRG_RXBUF)) ? "on" : "off", @@ -207,6 +247,11 @@ vhost_user_set_features(struct virtio_net *dev, uint64_t features) } } + did = dev->vdpa_dev_id; + vdpa_dev = rte_vdpa_get_device(did); + if (vdpa_dev && vdpa_dev->ops->set_features) + vdpa_dev->ops->set_features(dev->vid); + return 0; } @@ -221,6 +266,17 @@ vhost_user_set_vring_num(struct virtio_net *dev, vq->size = msg->payload.state.num; + /* VIRTIO 1.0, 2.4 Virtqueues says: + * + * Queue Size value is always a power of 2. The maximum Queue Size + * value is 32768. + */ + if ((vq->size & (vq->size - 1)) || vq->size > 32768) { + RTE_LOG(ERR, VHOST_CONFIG, + "invalid virtqueue size %u\n", vq->size); + return -1; + } + if (dev->dequeue_zero_copy) { vq->nr_zmbuf = 0; vq->last_zmbuf_idx = 0; @@ -474,13 +530,13 @@ translate_ring_addresses(struct virtio_net *dev, int vq_index) vq->log_guest_addr = addr->log_guest_addr; - LOG_DEBUG(VHOST_CONFIG, "(%d) mapped address desc: %p\n", + VHOST_LOG_DEBUG(VHOST_CONFIG, "(%d) mapped address desc: %p\n", dev->vid, vq->desc); - LOG_DEBUG(VHOST_CONFIG, "(%d) mapped address avail: %p\n", + VHOST_LOG_DEBUG(VHOST_CONFIG, "(%d) mapped address avail: %p\n", dev->vid, vq->avail); - LOG_DEBUG(VHOST_CONFIG, "(%d) mapped address used: %p\n", + VHOST_LOG_DEBUG(VHOST_CONFIG, "(%d) mapped address used: %p\n", dev->vid, vq->used); - LOG_DEBUG(VHOST_CONFIG, "(%d) log_guest_addr: %" PRIx64 "\n", + VHOST_LOG_DEBUG(VHOST_CONFIG, "(%d) log_guest_addr: %" PRIx64 "\n", dev->vid, vq->log_guest_addr); return dev; @@ -513,7 +569,7 @@ vhost_user_set_vring_addr(struct virtio_net **pdev, VhostUserMsg *msg) if (vq->enabled && (dev->features & (1ULL << VHOST_USER_F_PROTOCOL_FEATURES))) { - dev = translate_ring_addresses(dev, msg->payload.state.index); + dev = translate_ring_addresses(dev, msg->payload.addr.index); if (!dev) return -1; @@ -538,7 +594,7 @@ vhost_user_set_vring_base(struct virtio_net *dev, return 0; } -static void +static int add_one_guest_page(struct virtio_net *dev, uint64_t guest_phys_addr, uint64_t host_phys_addr, uint64_t size) { @@ -548,6 +604,10 @@ add_one_guest_page(struct virtio_net *dev, uint64_t guest_phys_addr, dev->max_guest_pages *= 2; 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"); + return -1; + } } if (dev->nr_guest_pages > 0) { @@ -556,7 +616,7 @@ add_one_guest_page(struct virtio_net *dev, uint64_t guest_phys_addr, if (host_phys_addr == last_page->host_phys_addr + last_page->size) { last_page->size += size; - return; + return 0; } } @@ -564,9 +624,11 @@ add_one_guest_page(struct virtio_net *dev, uint64_t guest_phys_addr, page->guest_phys_addr = guest_phys_addr; page->host_phys_addr = host_phys_addr; page->size = size; + + return 0; } -static void +static int add_guest_pages(struct virtio_net *dev, struct rte_vhost_mem_region *reg, uint64_t page_size) { @@ -580,7 +642,9 @@ add_guest_pages(struct virtio_net *dev, struct rte_vhost_mem_region *reg, 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); + if (add_one_guest_page(dev, guest_phys_addr, host_phys_addr, size) < 0) + return -1; + host_user_addr += size; guest_phys_addr += size; reg_size -= size; @@ -589,12 +653,16 @@ add_guest_pages(struct virtio_net *dev, struct rte_vhost_mem_region *reg, 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); + if (add_one_guest_page(dev, guest_phys_addr, host_phys_addr, + size) < 0) + return -1; host_user_addr += size; guest_phys_addr += size; reg_size -= size; } + + return 0; } #ifdef RTE_LIBRTE_VHOST_DEBUG @@ -648,8 +716,9 @@ vhost_memory_changed(struct VhostUserMemory *new, } static int -vhost_user_set_mem_table(struct virtio_net *dev, struct VhostUserMsg *pmsg) +vhost_user_set_mem_table(struct virtio_net **pdev, struct VhostUserMsg *pmsg) { + struct virtio_net *dev = *pdev; struct VhostUserMemory memory = pmsg->payload.memory; struct rte_vhost_mem_region *reg; void *mmap_addr; @@ -657,8 +726,15 @@ vhost_user_set_mem_table(struct virtio_net *dev, struct VhostUserMsg *pmsg) uint64_t mmap_offset; uint64_t alignment; uint32_t i; + int populate; int fd; + if (memory.nregions > VHOST_MEMORY_MAX_NREGIONS) { + RTE_LOG(ERR, VHOST_CONFIG, + "too many memory regions (%u)\n", memory.nregions); + return -1; + } + if (dev->mem && !vhost_memory_changed(&memory, dev->mem)) { RTE_LOG(INFO, VHOST_CONFIG, "(%d) memory regions not changed\n", dev->vid); @@ -709,7 +785,17 @@ vhost_user_set_mem_table(struct virtio_net *dev, struct VhostUserMsg *pmsg) reg->fd = fd; mmap_offset = memory.regions[i].mmap_offset; - mmap_size = reg->size + mmap_offset; + + /* Check for memory_size + mmap_offset overflow */ + if (mmap_offset >= -reg->size) { + RTE_LOG(ERR, VHOST_CONFIG, + "mmap_offset (%#"PRIx64") and memory_size " + "(%#"PRIx64") overflow\n", + mmap_offset, reg->size); + goto err_mmap; + } + + mmap_size = reg->size + mmap_offset; /* mmap() without flag of MAP_ANONYMOUS, should be called * with length argument aligned with hugepagesz at older @@ -727,8 +813,9 @@ vhost_user_set_mem_table(struct virtio_net *dev, struct VhostUserMsg *pmsg) } mmap_size = RTE_ALIGN_CEIL(mmap_size, alignment); + populate = (dev->dequeue_zero_copy) ? MAP_POPULATE : 0; mmap_addr = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE, - MAP_SHARED | MAP_POPULATE, fd, 0); + MAP_SHARED | populate, fd, 0); if (mmap_addr == MAP_FAILED) { RTE_LOG(ERR, VHOST_CONFIG, @@ -742,7 +829,12 @@ vhost_user_set_mem_table(struct virtio_net *dev, struct VhostUserMsg *pmsg) mmap_offset; if (dev->dequeue_zero_copy) - add_guest_pages(dev, reg, alignment); + if (add_guest_pages(dev, reg, alignment) < 0) { + RTE_LOG(ERR, VHOST_CONFIG, + "adding guest pages to region %u failed.\n", + i); + goto err_mmap; + } RTE_LOG(INFO, VHOST_CONFIG, "guest memory region %u, size: 0x%" PRIx64 "\n" @@ -763,6 +855,25 @@ vhost_user_set_mem_table(struct virtio_net *dev, struct VhostUserMsg *pmsg) mmap_offset); } + for (i = 0; i < dev->nr_vring; i++) { + struct vhost_virtqueue *vq = dev->virtqueue[i]; + + if (vq->desc || vq->avail || vq->used) { + /* + * If the memory table got updated, the ring addresses + * need to be translated again as virtual addresses have + * changed. + */ + vring_invalidate(dev, vq); + + dev = translate_ring_addresses(dev, i); + if (!dev) + return -1; + + *pdev = dev; + } + } + dump_guest_pages(dev); return 0; @@ -885,17 +996,24 @@ vhost_user_get_vring_base(struct virtio_net *dev, VhostUserMsg *msg) { struct vhost_virtqueue *vq = dev->virtqueue[msg->payload.state.index]; + struct rte_vdpa_device *vdpa_dev; + int did = -1; /* We have to stop the queue (virtio) if it is running. */ if (dev->flags & VIRTIO_DEV_RUNNING) { + did = dev->vdpa_dev_id; + vdpa_dev = rte_vdpa_get_device(did); + if (vdpa_dev && vdpa_dev->ops->dev_close) + vdpa_dev->ops->dev_close(dev->vid); dev->flags &= ~VIRTIO_DEV_RUNNING; dev->notify_ops->destroy_device(dev->vid); } dev->flags &= ~VIRTIO_DEV_READY; + dev->flags &= ~VIRTIO_DEV_VDPA_CONFIGURED; - /* Here we are safe to get the last used index */ - msg->payload.state.num = vq->last_used_idx; + /* Here we are safe to get the last avail index */ + msg->payload.state.num = vq->last_avail_idx; RTE_LOG(INFO, VHOST_CONFIG, "vring base idx:%d file:%d\n", msg->payload.state.index, @@ -910,6 +1028,11 @@ vhost_user_get_vring_base(struct virtio_net *dev, vq->kickfd = VIRTIO_UNINITIALIZED_EVENTFD; + if (vq->callfd >= 0) + close(vq->callfd); + + vq->callfd = VIRTIO_UNINITIALIZED_EVENTFD; + if (dev->dequeue_zero_copy) free_zmbufs(vq); rte_free(vq->shadow_used_ring); @@ -930,16 +1053,24 @@ vhost_user_set_vring_enable(struct virtio_net *dev, VhostUserMsg *msg) { int enable = (int)msg->payload.state.num; + int index = (int)msg->payload.state.index; + struct rte_vdpa_device *vdpa_dev; + int did = -1; RTE_LOG(INFO, VHOST_CONFIG, "set queue enable: %d to qp idx: %d\n", - enable, msg->payload.state.index); + enable, index); + + did = dev->vdpa_dev_id; + vdpa_dev = rte_vdpa_get_device(did); + if (vdpa_dev && vdpa_dev->ops->set_vring_state) + vdpa_dev->ops->set_vring_state(dev->vid, index, enable); if (dev->notify_ops->vring_state_changed) dev->notify_ops->vring_state_changed(dev->vid, - msg->payload.state.index, enable); + index, enable); - dev->virtqueue[msg->payload.state.index]->enabled = enable; + dev->virtqueue[index]->enabled = enable; return 0; } @@ -948,9 +1079,10 @@ static void vhost_user_get_protocol_features(struct virtio_net *dev, struct VhostUserMsg *msg) { - uint64_t features, protocol_features = VHOST_USER_PROTOCOL_FEATURES; + uint64_t features, protocol_features; rte_vhost_driver_get_features(dev->ifname, &features); + rte_vhost_driver_get_protocol_features(dev->ifname, &protocol_features); /* * REPLY_ACK protocol feature is only mandatory for now @@ -996,6 +1128,15 @@ vhost_user_set_log_base(struct virtio_net *dev, struct VhostUserMsg *msg) size = msg->payload.log.mmap_size; off = msg->payload.log.mmap_offset; + + /* Don't allow mmap_offset to point outside the mmap region */ + if (off > size) { + RTE_LOG(ERR, VHOST_CONFIG, + "log offset %#"PRIx64" exceeds log size %#"PRIx64"\n", + off, size); + return -1; + } + RTE_LOG(INFO, VHOST_CONFIG, "log mmap size: %"PRId64", offset: %"PRId64"\n", size, off); @@ -1004,7 +1145,7 @@ vhost_user_set_log_base(struct virtio_net *dev, struct VhostUserMsg *msg) * mmap from 0 to workaround a hugepage mmap bug: mmap will * fail when offset is not page size aligned. */ - addr = mmap(0, size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); + addr = mmap(0, size + off, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); close(fd); if (addr == MAP_FAILED) { RTE_LOG(ERR, VHOST_CONFIG, "mmap log base failed!\n"); @@ -1037,6 +1178,8 @@ static int vhost_user_send_rarp(struct virtio_net *dev, struct VhostUserMsg *msg) { uint8_t *mac = (uint8_t *)&msg->payload.u64; + struct rte_vdpa_device *vdpa_dev; + int did = -1; RTE_LOG(DEBUG, VHOST_CONFIG, ":: mac: %02x:%02x:%02x:%02x:%02x:%02x\n", @@ -1052,6 +1195,10 @@ vhost_user_send_rarp(struct virtio_net *dev, struct VhostUserMsg *msg) */ rte_smp_wmb(); rte_atomic16_set(&dev->broadcast_rarp, 1); + did = dev->vdpa_dev_id; + vdpa_dev = rte_vdpa_get_device(did); + if (vdpa_dev && vdpa_dev->ops->migration_done) + vdpa_dev->ops->migration_done(dev->vid); return 0; } @@ -1214,13 +1361,13 @@ read_vhost_message(int sockfd, struct VhostUserMsg *msg) } static int -send_vhost_message(int sockfd, struct VhostUserMsg *msg) +send_vhost_message(int sockfd, struct VhostUserMsg *msg, int *fds, int fd_num) { if (!msg) return 0; return send_fd_message(sockfd, (char *)msg, - VHOST_USER_HDR_SIZE + msg->size, NULL, 0); + VHOST_USER_HDR_SIZE + msg->size, fds, fd_num); } static int @@ -1234,7 +1381,7 @@ 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); + return send_vhost_message(sockfd, msg, NULL, 0); } /* @@ -1314,8 +1461,11 @@ vhost_user_msg_handler(int vid, int fd) { struct virtio_net *dev; struct VhostUserMsg msg; + struct rte_vdpa_device *vdpa_dev; + int did = -1; int ret; int unlock_required = 0; + uint32_t skip_master = 0; dev = get_device(vid); if (dev == NULL) @@ -1393,6 +1543,21 @@ vhost_user_msg_handler(int vid, int fd) } + if (dev->extern_ops.pre_msg_handle) { + uint32_t need_reply; + + ret = (*dev->extern_ops.pre_msg_handle)(dev->vid, + (void *)&msg, &need_reply, &skip_master); + if (ret < 0) + goto skip_to_reply; + + if (need_reply) + send_vhost_reply(fd, &msg); + + if (skip_master) + goto skip_to_post_handle; + } + switch (msg.request.master) { case VHOST_USER_GET_FEATURES: msg.payload.u64 = vhost_user_get_features(dev); @@ -1421,7 +1586,7 @@ vhost_user_msg_handler(int vid, int fd) break; case VHOST_USER_SET_MEM_TABLE: - ret = vhost_user_set_mem_table(dev, &msg); + ret = vhost_user_set_mem_table(&dev, &msg); break; case VHOST_USER_SET_LOG_BASE: @@ -1466,7 +1631,7 @@ vhost_user_msg_handler(int vid, int fd) break; case VHOST_USER_GET_QUEUE_NUM: - msg.payload.u64 = VHOST_MAX_QUEUE_PAIRS; + msg.payload.u64 = (uint64_t)vhost_user_get_queue_num(dev); msg.size = sizeof(msg.payload.u64); send_vhost_reply(fd, &msg); break; @@ -1493,9 +1658,22 @@ vhost_user_msg_handler(int vid, int fd) default: ret = -1; break; + } + +skip_to_post_handle: + if (dev->extern_ops.post_msg_handle) { + uint32_t need_reply; + ret = (*dev->extern_ops.post_msg_handle)( + dev->vid, (void *)&msg, &need_reply); + if (ret < 0) + goto skip_to_reply; + + if (need_reply) + send_vhost_reply(fd, &msg); } +skip_to_reply: if (unlock_required) vhost_user_unlock_all_queue_pairs(dev); @@ -1519,6 +1697,16 @@ vhost_user_msg_handler(int vid, int fd) } } + did = dev->vdpa_dev_id; + 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) { + if (vdpa_dev->ops->dev_conf) + vdpa_dev->ops->dev_conf(dev->vid); + dev->flags |= VIRTIO_DEV_VDPA_CONFIGURED; + } + return 0; } @@ -1537,7 +1725,7 @@ vhost_user_iotlb_miss(struct virtio_net *dev, uint64_t iova, uint8_t perm) }, }; - ret = send_vhost_message(dev->slave_req_fd, &msg); + ret = send_vhost_message(dev->slave_req_fd, &msg, NULL, 0); if (ret < 0) { RTE_LOG(ERR, VHOST_CONFIG, "Failed to send IOTLB miss message (%d)\n", |