X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=lib%2Flibrte_vhost%2Fvhost_user.c;h=6039a8fdb9cb9eaa6a47f232a631204e58d1617c;hb=35a7fe80c29446eab49ffd7e81a4f610fd1f98ce;hp=9a7b8b3088d5849f4c6be72e21582ce5aa4154d6;hpb=c47edd040a6a409de6bc86a31f44e86e5fa55b19;p=dpdk.git diff --git a/lib/librte_vhost/vhost_user.c b/lib/librte_vhost/vhost_user.c index 9a7b8b3088..6039a8fdb9 100644 --- a/lib/librte_vhost/vhost_user.c +++ b/lib/librte_vhost/vhost_user.c @@ -191,7 +191,7 @@ vhost_backend_cleanup(struct virtio_net *dev) dev->mem = NULL; } - free(dev->guest_pages); + rte_free(dev->guest_pages); dev->guest_pages = NULL; if (dev->log_addr) { @@ -206,7 +206,7 @@ vhost_backend_cleanup(struct virtio_net *dev) dev->inflight_info->addr = NULL; } - if (dev->inflight_info->fd > 0) { + if (dev->inflight_info->fd >= 0) { close(dev->inflight_info->fd); dev->inflight_info->fd = -1; } @@ -228,6 +228,20 @@ vhost_backend_cleanup(struct virtio_net *dev) dev->postcopy_listening = 0; } +static void +vhost_user_notify_queue_state(struct virtio_net *dev, uint16_t index, + int enable) +{ + struct rte_vdpa_device *vdpa_dev = dev->vdpa_dev; + + 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, + index, enable); +} + /* * This function just returns success at the moment unless * the device hasn't been initialised. @@ -315,7 +329,6 @@ vhost_user_set_features(struct virtio_net **pdev, struct VhostUserMsg *msg, uint64_t features = msg->payload.u64; uint64_t vhost_features = 0; struct rte_vdpa_device *vdpa_dev; - int did = -1; if (validate_msg_fds(msg, 0) != 0) return RTE_VHOST_MSG_RESULT_ERR; @@ -384,8 +397,7 @@ vhost_user_set_features(struct virtio_net **pdev, struct VhostUserMsg *msg, } } - did = dev->vdpa_dev_id; - vdpa_dev = rte_vdpa_get_device(did); + vdpa_dev = dev->vdpa_dev; if (vdpa_dev && vdpa_dev->ops->set_features) vdpa_dev->ops->set_features(dev->vid); @@ -656,13 +668,11 @@ 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, + vhost_user_iotlb_rd_lock(vq); + vva = vhost_iova_to_vva(dev, vq, ra, size, VHOST_ACCESS_RW); - if (req_size != *size) - vhost_user_iotlb_miss(dev, (ra + *size), - VHOST_ACCESS_RW); + vhost_user_iotlb_rd_unlock(vq); return vva; } @@ -670,37 +680,16 @@ 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) +log_addr_to_gpa(struct virtio_net *dev, struct vhost_virtqueue *vq) { - 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; + uint64_t log_gpa; - gpa = hva_to_gpa(dev, hva, exp_size); - if (!gpa) { - VHOST_LOG_CONFIG(ERR, - "VQ: Failed to find GPA for log_addr: 0x%" PRIx64 " hva: 0x%" PRIx64 "\n", - log_addr, hva); - return 0; - } - return gpa; + vhost_user_iotlb_rd_lock(vq); + log_gpa = translate_log_addr(dev, vq, vq->ring_addrs.log_guest_addr); + vhost_user_iotlb_rd_unlock(vq); - } else - return log_addr; + return log_gpa; } static struct virtio_net * @@ -712,7 +701,7 @@ translate_ring_addresses(struct virtio_net *dev, int vq_index) if (addr->flags & (1 << VHOST_VRING_F_LOG)) { vq->log_guest_addr = - translate_log_addr(dev, vq, addr->log_guest_addr); + log_addr_to_gpa(dev, vq); if (vq->log_guest_addr == 0) { VHOST_LOG_CONFIG(DEBUG, "(%d) failed to map log_guest_addr.\n", @@ -926,11 +915,12 @@ add_one_guest_page(struct virtio_net *dev, uint64_t guest_phys_addr, 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) { + dev->guest_pages = rte_realloc(dev->guest_pages, + dev->max_guest_pages * sizeof(*page), + RTE_CACHE_LINE_SIZE); + if (dev->guest_pages == NULL) { VHOST_LOG_CONFIG(ERR, "cannot realloc guest_pages\n"); - free(old_pages); + rte_free(old_pages); return -1; } } @@ -987,6 +977,12 @@ add_guest_pages(struct virtio_net *dev, struct rte_vhost_mem_region *reg, reg_size -= size; } + /* sort guest page array if over binary search threshold */ + if (dev->nr_guest_pages >= VHOST_BINARY_SEARCH_THRESH) { + qsort((void *)dev->guest_pages, dev->nr_guest_pages, + sizeof(struct guest_page), guest_page_addrcmp); + } + return 0; } @@ -1074,6 +1070,13 @@ vhost_user_set_mem_table(struct virtio_net **pdev, struct VhostUserMsg *msg, } if (dev->mem) { + if (dev->flags & VIRTIO_DEV_VDPA_CONFIGURED) { + struct rte_vdpa_device *vdpa_dev = dev->vdpa_dev; + + if (vdpa_dev && vdpa_dev->ops->dev_close) + vdpa_dev->ops->dev_close(dev->vid); + dev->flags &= ~VIRTIO_DEV_VDPA_CONFIGURED; + } free_mem_region(dev); rte_free(dev->mem); dev->mem = NULL; @@ -1085,10 +1088,12 @@ vhost_user_set_mem_table(struct virtio_net **pdev, struct VhostUserMsg *msg, vhost_user_iotlb_flush_all(dev->virtqueue[i]); dev->nr_guest_pages = 0; - if (!dev->guest_pages) { + if (dev->guest_pages == NULL) { dev->max_guest_pages = 8; - dev->guest_pages = malloc(dev->max_guest_pages * - sizeof(struct guest_page)); + dev->guest_pages = rte_zmalloc(NULL, + dev->max_guest_pages * + sizeof(struct guest_page), + RTE_CACHE_LINE_SIZE); if (dev->guest_pages == NULL) { VHOST_LOG_CONFIG(ERR, "(%d) failed to allocate memory " @@ -1320,27 +1325,31 @@ vq_is_ready(struct virtio_net *dev, struct vhost_virtqueue *vq) return rings_ok && vq->kickfd != VIRTIO_UNINITIALIZED_EVENTFD && - vq->callfd != VIRTIO_UNINITIALIZED_EVENTFD; + vq->callfd != VIRTIO_UNINITIALIZED_EVENTFD && + vq->enabled; } +#define VIRTIO_DEV_NUM_VQS_TO_BE_READY 2u + static int virtio_is_ready(struct virtio_net *dev) { struct vhost_virtqueue *vq; uint32_t i; - if (dev->nr_vring == 0) + if (dev->nr_vring < VIRTIO_DEV_NUM_VQS_TO_BE_READY) return 0; - for (i = 0; i < dev->nr_vring; i++) { + for (i = 0; i < VIRTIO_DEV_NUM_VQS_TO_BE_READY; i++) { vq = dev->virtqueue[i]; if (!vq_is_ready(dev, vq)) return 0; } - VHOST_LOG_CONFIG(INFO, - "virtio is now ready for processing.\n"); + if (!(dev->flags & VIRTIO_DEV_RUNNING)) + VHOST_LOG_CONFIG(INFO, + "virtio is now ready for processing.\n"); return 1; } @@ -1431,6 +1440,7 @@ vhost_user_get_inflight_fd(struct virtio_net **pdev, "failed to alloc dev inflight area\n"); return RTE_VHOST_MSG_RESULT_ERR; } + dev->inflight_info->fd = -1; } num_queues = msg->payload.inflight.num_queues; @@ -1456,6 +1466,16 @@ vhost_user_get_inflight_fd(struct virtio_net **pdev, } memset(addr, 0, mmap_size); + 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; + } + dev->inflight_info->addr = addr; dev->inflight_info->size = msg->payload.inflight.mmap_size = mmap_size; dev->inflight_info->fd = msg->fds[0] = fd; @@ -1538,10 +1558,13 @@ vhost_user_set_inflight_fd(struct virtio_net **pdev, VhostUserMsg *msg, "failed to alloc dev inflight area\n"); return RTE_VHOST_MSG_RESULT_ERR; } + dev->inflight_info->fd = -1; } - if (dev->inflight_info->addr) + if (dev->inflight_info->addr) { munmap(dev->inflight_info->addr, dev->inflight_info->size); + dev->inflight_info->addr = NULL; + } addr = mmap(0, mmap_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, mmap_offset); @@ -1550,8 +1573,10 @@ vhost_user_set_inflight_fd(struct virtio_net **pdev, VhostUserMsg *msg, return RTE_VHOST_MSG_RESULT_ERR; } - if (dev->inflight_info->fd) + if (dev->inflight_info->fd >= 0) { close(dev->inflight_info->fd); + dev->inflight_info->fd = -1; + } dev->inflight_info->fd = fd; dev->inflight_info->addr = addr; @@ -1594,6 +1619,12 @@ vhost_user_set_vring_call(struct virtio_net **pdev, struct VhostUserMsg *msg, "vring call idx:%d file:%d\n", file.index, file.fd); vq = dev->virtqueue[file.index]; + + if (vq->ready) { + vhost_user_notify_queue_state(dev, file.index, 0); + vq->ready = 0; + } + if (vq->callfd >= 0) close(vq->callfd); @@ -1852,6 +1883,11 @@ vhost_user_set_vring_kick(struct virtio_net **pdev, struct VhostUserMsg *msg, dev->vid, file.index, 1); } + if (vq->ready) { + vhost_user_notify_queue_state(dev, file.index, 0); + vq->ready = 0; + } + if (vq->kickfd >= 0) close(vq->kickfd); vq->kickfd = file.fd; @@ -1968,8 +2004,6 @@ vhost_user_set_vring_enable(struct virtio_net **pdev, struct virtio_net *dev = *pdev; int enable = (int)msg->payload.state.num; int index = (int)msg->payload.state.index; - struct rte_vdpa_device *vdpa_dev; - int did = -1; if (validate_msg_fds(msg, 0) != 0) return RTE_VHOST_MSG_RESULT_ERR; @@ -1978,15 +2012,6 @@ vhost_user_set_vring_enable(struct virtio_net **pdev, "set queue enable: %d to qp idx: %d\n", 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, - index, enable); - /* On disable, rings have to be stopped being processed. */ if (!enable && dev->dequeue_zero_copy) drain_zmbuf_list(dev->virtqueue[index]); @@ -2010,15 +2035,6 @@ vhost_user_get_protocol_features(struct virtio_net **pdev, 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 - * 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); msg->fd_num = 0; @@ -2082,10 +2098,10 @@ vhost_user_set_log_base(struct virtio_net **pdev, 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) { + /* Check for mmap size and offset overflow. */ + if (off >= -size) { VHOST_LOG_CONFIG(ERR, - "log offset %#"PRIx64" exceeds log size %#"PRIx64"\n", + "log offset %#"PRIx64" and log size %#"PRIx64" overflow\n", off, size); return RTE_VHOST_MSG_RESULT_ERR; } @@ -2154,7 +2170,6 @@ vhost_user_send_rarp(struct virtio_net **pdev, struct VhostUserMsg *msg, struct virtio_net *dev = *pdev; uint8_t *mac = (uint8_t *)&msg->payload.u64; struct rte_vdpa_device *vdpa_dev; - int did = -1; if (validate_msg_fds(msg, 0) != 0) return RTE_VHOST_MSG_RESULT_ERR; @@ -2168,13 +2183,11 @@ vhost_user_send_rarp(struct virtio_net **pdev, struct VhostUserMsg *msg, * Set the flag to inject a RARP broadcast packet at * rte_vhost_dequeue_burst(). * - * rte_smp_wmb() is for making sure the mac is copied - * before the flag is set. + * __ATOMIC_RELEASE ordering is for making sure the mac is + * copied before the flag is set. */ - rte_smp_wmb(); - rte_atomic16_set(&dev->broadcast_rarp, 1); - did = dev->vdpa_dev_id; - vdpa_dev = rte_vdpa_get_device(did); + __atomic_store_n(&dev->broadcast_rarp, 1, __ATOMIC_RELEASE); + vdpa_dev = dev->vdpa_dev; if (vdpa_dev && vdpa_dev->ops->migration_done) vdpa_dev->ops->migration_done(dev->vid); @@ -2251,6 +2264,13 @@ is_vring_iotlb_split(struct vhost_virtqueue *vq, struct vhost_iotlb_msg *imsg) if (ra->used_user_addr < end && (ra->used_user_addr + len) > start) return 1; + if (ra->flags & (1 << VHOST_VRING_F_LOG)) { + len = sizeof(uint64_t); + if (ra->log_guest_addr < end && + (ra->log_guest_addr + len) > start) + return 1; + } + return 0; } @@ -2276,6 +2296,13 @@ is_vring_iotlb_packed(struct vhost_virtqueue *vq, struct vhost_iotlb_msg *imsg) if (ra->used_user_addr < end && (ra->used_user_addr + len) > start) return 1; + if (ra->flags & (1 << VHOST_VRING_F_LOG)) { + len = sizeof(uint64_t); + if (ra->log_guest_addr < end && + (ra->log_guest_addr + len) > start) + return 1; + } + return 0; } @@ -2535,7 +2562,7 @@ static int vhost_user_check_and_alloc_queue_pair(struct virtio_net *dev, struct VhostUserMsg *msg) { - uint16_t vring_idx; + uint32_t vring_idx; switch (msg->request.master) { case VHOST_USER_SET_VRING_KICK: @@ -2607,11 +2634,11 @@ 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; bool handled; int request; + uint32_t i; dev = get_device(vid); if (dev == NULL) @@ -2684,8 +2711,10 @@ vhost_user_msg_handler(int vid, int fd) case VHOST_USER_SEND_RARP: case VHOST_USER_NET_SET_MTU: case VHOST_USER_SET_SLAVE_REQ_FD: - vhost_user_lock_all_queue_pairs(dev); - unlock_required = 1; + if (!(dev->flags & VIRTIO_DEV_VDPA_CONFIGURED)) { + vhost_user_lock_all_queue_pairs(dev); + unlock_required = 1; + } break; default: break; @@ -2785,6 +2814,17 @@ skip_to_post_handle: return -1; } + for (i = 0; i < dev->nr_vring; i++) { + struct vhost_virtqueue *vq = dev->virtqueue[i]; + bool cur_ready = vq_is_ready(dev, vq); + + if (cur_ready != (vq && vq->ready)) { + vhost_user_notify_queue_state(dev, i, cur_ready); + vq->ready = cur_ready; + } + } + + if (!(dev->flags & VIRTIO_DEV_RUNNING) && virtio_is_ready(dev)) { dev->flags |= VIRTIO_DEV_READY; @@ -2799,11 +2839,9 @@ skip_to_post_handle: } } - did = dev->vdpa_dev_id; - vdpa_dev = rte_vdpa_get_device(did); + vdpa_dev = dev->vdpa_dev; if (vdpa_dev && virtio_is_ready(dev) && - !(dev->flags & VIRTIO_DEV_VDPA_CONFIGURED) && - msg.request.master == VHOST_USER_SET_VRING_CALL) { + !(dev->flags & VIRTIO_DEV_VDPA_CONFIGURED)) { if (vdpa_dev->ops->dev_conf) vdpa_dev->ops->dev_conf(dev->vid); dev->flags |= VIRTIO_DEV_VDPA_CONFIGURED; @@ -2821,11 +2859,19 @@ static int process_slave_message_reply(struct virtio_net *dev, if ((msg->flags & VHOST_USER_NEED_REPLY) == 0) return 0; - if (read_vhost_message(dev->slave_req_fd, &msg_reply) < 0) { + ret = read_vhost_message(dev->slave_req_fd, &msg_reply); + if (ret <= 0) { + if (ret < 0) + VHOST_LOG_CONFIG(ERR, + "vhost read slave message reply failed\n"); + else + VHOST_LOG_CONFIG(INFO, + "vhost peer closed\n"); ret = -1; goto out; } + ret = 0; if (msg_reply.request.slave != msg->request.slave) { VHOST_LOG_CONFIG(ERR, "Received unexpected msg type (%u), expected %u\n", @@ -2937,21 +2983,21 @@ static int vhost_user_slave_set_vring_host_notifier(struct virtio_net *dev, return process_slave_message_reply(dev, &msg); } -int rte_vhost_host_notifier_ctrl(int vid, bool enable) +int rte_vhost_host_notifier_ctrl(int vid, uint16_t qid, bool enable) { struct virtio_net *dev; struct rte_vdpa_device *vdpa_dev; - int vfio_device_fd, did, ret = 0; + int vfio_device_fd, ret = 0; uint64_t offset, size; - unsigned int i; + unsigned int i, q_start, q_last; dev = get_device(vid); if (!dev) return -ENODEV; - did = dev->vdpa_dev_id; - if (did < 0) - return -EINVAL; + vdpa_dev = dev->vdpa_dev; + if (vdpa_dev == NULL) + return -ENODEV; if (!(dev->features & (1ULL << VIRTIO_F_VERSION_1)) || !(dev->features & (1ULL << VHOST_USER_F_PROTOCOL_FEATURES)) || @@ -2963,9 +3009,15 @@ int rte_vhost_host_notifier_ctrl(int vid, bool enable) (1ULL << VHOST_USER_PROTOCOL_F_HOST_NOTIFIER))) return -ENOTSUP; - vdpa_dev = rte_vdpa_get_device(did); - if (!vdpa_dev) - return -ENODEV; + if (qid == RTE_VHOST_QUEUE_ALL) { + q_start = 0; + q_last = dev->nr_vring - 1; + } else { + if (qid >= dev->nr_vring) + return -EINVAL; + q_start = qid; + q_last = qid; + } RTE_FUNC_PTR_OR_ERR_RET(vdpa_dev->ops->get_vfio_device_fd, -ENOTSUP); RTE_FUNC_PTR_OR_ERR_RET(vdpa_dev->ops->get_notify_area, -ENOTSUP); @@ -2975,7 +3027,7 @@ int rte_vhost_host_notifier_ctrl(int vid, bool enable) return -ENOTSUP; if (enable) { - for (i = 0; i < dev->nr_vring; i++) { + for (i = q_start; i <= q_last; i++) { if (vdpa_dev->ops->get_notify_area(vid, i, &offset, &size) < 0) { ret = -ENOTSUP; @@ -2990,7 +3042,7 @@ int rte_vhost_host_notifier_ctrl(int vid, bool enable) } } else { disable: - for (i = 0; i < dev->nr_vring; i++) { + for (i = q_start; i <= q_last; i++) { vhost_user_slave_set_vring_host_notifier(dev, i, -1, 0, 0); }