X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;ds=inline;f=lib%2Flibrte_vhost%2Fvhost_user.c;h=2a9fa7c6cae0616042ab8f6334c9e22a06311fac;hb=5a5793a5ffa2231ae759de824fb8bfc970e5d4f7;hp=555d09ad9ef347accee520b014cfa77d146bea32;hpb=11d5253a3e93a38be14da65328dd19960fd8cb14;p=dpdk.git diff --git a/lib/librte_vhost/vhost_user.c b/lib/librte_vhost/vhost_user.c index 555d09ad9e..2a9fa7c6ca 100644 --- a/lib/librte_vhost/vhost_user.c +++ b/lib/librte_vhost/vhost_user.c @@ -37,6 +37,10 @@ #ifdef RTE_LIBRTE_VHOST_POSTCOPY #include #endif +#ifdef F_ADD_SEALS /* if file sealing is supported, so is memfd */ +#include +#define MEMFD_SUPPORTED +#endif #include #include @@ -49,6 +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", @@ -78,6 +85,8 @@ static const char *vhost_message_str[VHOST_USER_MAX] = { [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); @@ -160,6 +169,22 @@ 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; @@ -284,6 +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, @@ -306,6 +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); } } @@ -408,6 +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]; @@ -556,11 +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; } @@ -568,6 +601,39 @@ 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) { @@ -617,6 +683,7 @@ translate_ring_addresses(struct virtio_net *dev, int vq_index) return dev; } + vq->access_ok = 1; return dev; } @@ -674,7 +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); @@ -699,6 +774,7 @@ vhost_user_set_vring_addr(struct virtio_net **pdev, struct VhostUserMsg *msg, 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 RTE_VHOST_MSG_RESULT_ERR; @@ -706,6 +782,8 @@ vhost_user_set_vring_addr(struct virtio_net **pdev, struct VhostUserMsg *msg, /* 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 @@ -714,8 +792,9 @@ 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 RTE_VHOST_MSG_RESULT_ERR; @@ -1084,10 +1163,11 @@ vhost_user_set_mem_table(struct virtio_net **pdev, struct VhostUserMsg *msg, 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); + "\t userfaultfd registered for range : " + "%" PRIx64 " - %" PRIx64 "\n", + (uint64_t)reg_struct.range.start, + (uint64_t)reg_struct.range.start + + (uint64_t)reg_struct.range.len - 1); #else goto err_mmap; #endif @@ -1165,6 +1245,234 @@ 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, int main_fd __rte_unused) @@ -1201,6 +1509,191 @@ static int vhost_user_set_vring_err(struct virtio_net **pdev __rte_unused, 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, int main_fd __rte_unused) @@ -1231,13 +1724,31 @@ 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; + 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; } @@ -1298,6 +1809,8 @@ 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)) { @@ -1314,6 +1827,8 @@ vhost_user_get_vring_base(struct virtio_net **pdev, msg->size = sizeof(msg->payload.state); msg->fd_num = 0; + vring_invalidate(dev, vq); + return RTE_VHOST_MSG_RESULT_REPLY; } @@ -1400,6 +1915,9 @@ vhost_user_set_protocol_features(struct virtio_net **pdev, } dev->protocol_features = protocol_features; + RTE_LOG(INFO, VHOST_CONFIG, + "negotiated Vhost-user protocol features: 0x%" PRIx64 "\n", + dev->protocol_features); return RTE_VHOST_MSG_RESULT_OK; } @@ -1553,60 +2071,75 @@ vhost_user_set_req_fd(struct virtio_net **pdev, struct VhostUserMsg *msg, return RTE_VHOST_MSG_RESULT_ERR; } + if (dev->slave_req_fd >= 0) + close(dev->slave_req_fd); + dev->slave_req_fd = fd; 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, int main_fd __rte_unused) @@ -1629,7 +2162,7 @@ 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; @@ -1640,7 +2173,7 @@ 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; @@ -1756,9 +2289,10 @@ static vhost_message_handler_t vhost_message_handlers[VHOST_USER_MAX] = { [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) @@ -1910,7 +2444,7 @@ 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); @@ -1928,27 +2462,30 @@ 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) { @@ -1964,7 +2501,7 @@ 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: @@ -1989,19 +2526,24 @@ 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 == RTE_VHOST_MSG_RESULT_ERR) - goto skip_to_reply; - else if (ret == RTE_VHOST_MSG_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; @@ -2012,40 +2554,54 @@ vhost_user_msg_handler(int vid, int fd) RTE_LOG(ERR, VHOST_CONFIG, "Processing %s failed.\n", vhost_message_str[request]); + handled = true; break; case RTE_VHOST_MSG_RESULT_OK: RTE_LOG(DEBUG, VHOST_CONFIG, "Processing %s succeeded.\n", vhost_message_str[request]); + handled = true; break; 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 = RTE_VHOST_MSG_RESULT_ERR; } skip_to_post_handle: if (ret != RTE_VHOST_MSG_RESULT_ERR && dev->extern_ops.post_msg_handle) { - ret = (*dev->extern_ops.post_msg_handle)( - dev->vid, (void *)&msg); - if (ret == RTE_VHOST_MSG_RESULT_ERR) - goto skip_to_reply; - else if (ret == RTE_VHOST_MSG_RESULT_REPLY) + 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