From patchwork Thu May 7 13:00:41 2015 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Ouyang Changchun X-Patchwork-Id: 4644 Return-Path: X-Original-To: patchwork@dpdk.org Delivered-To: patchwork@dpdk.org Received: from [92.243.14.124] (localhost [IPv6:::1]) by dpdk.org (Postfix) with ESMTP id 3611B5937; Thu, 7 May 2015 15:01:19 +0200 (CEST) Received: from mga14.intel.com (mga14.intel.com [192.55.52.115]) by dpdk.org (Postfix) with ESMTP id CA9E45697 for ; Thu, 7 May 2015 15:01:16 +0200 (CEST) Received: from orsmga002.jf.intel.com ([10.7.209.21]) by fmsmga103.fm.intel.com with ESMTP; 07 May 2015 06:01:03 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.13,384,1427785200"; d="scan'208";a="725300229" Received: from shvmail01.sh.intel.com ([10.239.29.42]) by orsmga002.jf.intel.com with ESMTP; 07 May 2015 06:01:02 -0700 Received: from shecgisg004.sh.intel.com (shecgisg004.sh.intel.com [10.239.29.89]) by shvmail01.sh.intel.com with ESMTP id t47D109B004521; Thu, 7 May 2015 21:01:00 +0800 Received: from shecgisg004.sh.intel.com (localhost [127.0.0.1]) by shecgisg004.sh.intel.com (8.13.6/8.13.6/SuSE Linux 0.8) with ESMTP id t47D0uDT027981; Thu, 7 May 2015 21:00:58 +0800 Received: (from couyang@localhost) by shecgisg004.sh.intel.com (8.13.6/8.13.6/Submit) id t47D0u2h027977; Thu, 7 May 2015 21:00:56 +0800 From: Ouyang Changchun To: dev@dpdk.org Date: Thu, 7 May 2015 21:00:41 +0800 Message-Id: <1431003645-27889-3-git-send-email-changchun.ouyang@intel.com> X-Mailer: git-send-email 1.7.12.2 In-Reply-To: <1431003645-27889-1-git-send-email-changchun.ouyang@intel.com> References: <1431003645-27889-1-git-send-email-changchun.ouyang@intel.com> Subject: [dpdk-dev] [RFC PATCH 2/6] lib_vhost: Support multiple queues in virtio dev X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: patches and discussions about DPDK List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" Each virtio device could have multiple queues, say 2 or 4, at most 8. Enabling this feature allows virtio device/port on guest has the ability to use different vCPU to receive/transmit packets from/to each queue. In multiple queues mode, virtio device readiness means all queues of this virtio device are ready, cleanup/destroy a virtio device also requires clearing all queues belong to it. Signed-off-by: Changchun Ouyang --- lib/librte_vhost/rte_virtio_net.h | 15 +++- lib/librte_vhost/vhost_rxtx.c | 32 +++---- lib/librte_vhost/vhost_user/virtio-net-user.c | 41 ++++----- lib/librte_vhost/virtio-net.c | 117 +++++++++++++++++--------- 4 files changed, 131 insertions(+), 74 deletions(-) diff --git a/lib/librte_vhost/rte_virtio_net.h b/lib/librte_vhost/rte_virtio_net.h index 2fc1c44..5fb6006 100644 --- a/lib/librte_vhost/rte_virtio_net.h +++ b/lib/librte_vhost/rte_virtio_net.h @@ -58,6 +58,10 @@ /* Backend value set by guest. */ #define VIRTIO_DEV_STOPPED -1 +/** + * Maximum number of virtqueues per device. + */ +#define VIRTIO_MAX_VIRTQUEUES 8 /* Enum for virtqueue management. */ enum {VIRTIO_RXQ, VIRTIO_TXQ, VIRTIO_QNUM}; @@ -95,13 +99,14 @@ struct vhost_virtqueue { * Device structure contains all configuration information relating to the device. */ struct virtio_net { - struct vhost_virtqueue *virtqueue[VIRTIO_QNUM]; /**< Contains all virtqueue information. */ struct virtio_memory *mem; /**< QEMU memory and memory region information. */ + struct vhost_virtqueue *virtqueue[VIRTIO_QNUM * VIRTIO_MAX_VIRTQUEUES]; /**< Contains all virtqueue information. */ uint64_t features; /**< Negotiated feature set. */ uint64_t device_fh; /**< device identifier. */ uint32_t flags; /**< Device flags. Only used to check if device is running on data core. */ #define IF_NAME_SZ (PATH_MAX > IFNAMSIZ ? PATH_MAX : IFNAMSIZ) char ifname[IF_NAME_SZ]; /**< Name of the tap device or socket path. */ + uint32_t num_virt_queues; void *priv; /**< private context */ } __rte_cache_aligned; @@ -215,4 +220,12 @@ uint16_t rte_vhost_enqueue_burst(struct virtio_net *dev, uint16_t queue_id, uint16_t rte_vhost_dequeue_burst(struct virtio_net *dev, uint16_t queue_id, struct rte_mempool *mbuf_pool, struct rte_mbuf **pkts, uint16_t count); +/** + * This function get the queue number of one vhost device. + * @param q_number + * queue number one vhost device. + * @return + * 0 if success, -1 if q_number exceed the max. + */ +int rte_vhost_q_num_get(uint32_t q_number); #endif /* _VIRTIO_NET_H_ */ diff --git a/lib/librte_vhost/vhost_rxtx.c b/lib/librte_vhost/vhost_rxtx.c index 535c7a1..d8dd5ec 100644 --- a/lib/librte_vhost/vhost_rxtx.c +++ b/lib/librte_vhost/vhost_rxtx.c @@ -67,12 +67,12 @@ virtio_dev_rx(struct virtio_net *dev, uint16_t queue_id, uint8_t success = 0; LOG_DEBUG(VHOST_DATA, "(%"PRIu64") virtio_dev_rx()\n", dev->device_fh); - if (unlikely(queue_id != VIRTIO_RXQ)) { - LOG_DEBUG(VHOST_DATA, "mq isn't supported in this version.\n"); - return 0; + if (unlikely(queue_id >= VIRTIO_QNUM * dev->num_virt_queues)) { + LOG_DEBUG(VHOST_DATA, "queue id: %d invalid.\n", queue_id); + return -1; } - vq = dev->virtqueue[VIRTIO_RXQ]; + vq = dev->virtqueue[queue_id]; count = (count > MAX_PKT_BURST) ? MAX_PKT_BURST : count; /* @@ -185,8 +185,9 @@ virtio_dev_rx(struct virtio_net *dev, uint16_t queue_id, } static inline uint32_t __attribute__((always_inline)) -copy_from_mbuf_to_vring(struct virtio_net *dev, uint16_t res_base_idx, - uint16_t res_end_idx, struct rte_mbuf *pkt) +copy_from_mbuf_to_vring(struct virtio_net *dev, uint16_t queue_id, + uint16_t res_base_idx, uint16_t res_end_idx, + struct rte_mbuf *pkt) { uint32_t vec_idx = 0; uint32_t entry_success = 0; @@ -214,9 +215,9 @@ copy_from_mbuf_to_vring(struct virtio_net *dev, uint16_t res_base_idx, * Convert from gpa to vva * (guest physical addr -> vhost virtual addr) */ - vq = dev->virtqueue[VIRTIO_RXQ]; vb_addr = gpa_to_vva(dev, vq->buf_vec[vec_idx].buf_addr); + vq = dev->virtqueue[queue_id]; vb_hdr_addr = vb_addr; /* Prefetch buffer address. */ @@ -404,11 +405,12 @@ virtio_dev_merge_rx(struct virtio_net *dev, uint16_t queue_id, LOG_DEBUG(VHOST_DATA, "(%"PRIu64") virtio_dev_merge_rx()\n", dev->device_fh); - if (unlikely(queue_id != VIRTIO_RXQ)) { - LOG_DEBUG(VHOST_DATA, "mq isn't supported in this version.\n"); + if (unlikely(queue_id >= VIRTIO_QNUM * dev->num_virt_queues)) { + LOG_DEBUG(VHOST_DATA, "queue id: %d invalid.\n", queue_id); + return -1; } - vq = dev->virtqueue[VIRTIO_RXQ]; + vq = dev->virtqueue[queue_id]; count = RTE_MIN((uint32_t)MAX_PKT_BURST, count); if (count == 0) @@ -490,7 +492,7 @@ virtio_dev_merge_rx(struct virtio_net *dev, uint16_t queue_id, res_end_idx = res_cur_idx; - entry_success = copy_from_mbuf_to_vring(dev, res_base_idx, + entry_success = copy_from_mbuf_to_vring(dev, queue_id, res_base_idx, res_end_idx, pkts[pkt_idx]); rte_compiler_barrier(); @@ -537,12 +539,12 @@ rte_vhost_dequeue_burst(struct virtio_net *dev, uint16_t queue_id, uint16_t free_entries, entry_success = 0; uint16_t avail_idx; - if (unlikely(queue_id != VIRTIO_TXQ)) { - LOG_DEBUG(VHOST_DATA, "mq isn't supported in this version.\n"); - return 0; + if (unlikely(queue_id >= VIRTIO_QNUM * dev->num_virt_queues)) { + LOG_DEBUG(VHOST_DATA, "queue id:%d invalid.\n", queue_id); + return -1; } - vq = dev->virtqueue[VIRTIO_TXQ]; + vq = dev->virtqueue[queue_id]; avail_idx = *((volatile uint16_t *)&vq->avail->idx); /* If there are no available buffers then return. */ diff --git a/lib/librte_vhost/vhost_user/virtio-net-user.c b/lib/librte_vhost/vhost_user/virtio-net-user.c index 465d3ef..031712c 100644 --- a/lib/librte_vhost/vhost_user/virtio-net-user.c +++ b/lib/librte_vhost/vhost_user/virtio-net-user.c @@ -209,22 +209,29 @@ static int virtio_is_ready(struct virtio_net *dev) { struct vhost_virtqueue *rvq, *tvq; + uint32_t q_idx; /* mq support in future.*/ - rvq = dev->virtqueue[VIRTIO_RXQ]; - tvq = dev->virtqueue[VIRTIO_TXQ]; - if (rvq && tvq && rvq->desc && tvq->desc && - (rvq->kickfd != (eventfd_t)-1) && - (rvq->callfd != (eventfd_t)-1) && - (tvq->kickfd != (eventfd_t)-1) && - (tvq->callfd != (eventfd_t)-1)) { - RTE_LOG(INFO, VHOST_CONFIG, - "virtio is now ready for processing.\n"); - return 1; + for (q_idx = 0; q_idx < dev->num_virt_queues; q_idx++) { + uint32_t virt_rx_q_idx = q_idx * VIRTIO_QNUM + VIRTIO_RXQ; + uint32_t virt_tx_q_idx = q_idx * VIRTIO_QNUM + VIRTIO_TXQ; + + rvq = dev->virtqueue[virt_rx_q_idx]; + tvq = dev->virtqueue[virt_tx_q_idx]; + if ((rvq == NULL) || (tvq == NULL) || + (rvq->desc == NULL) || (tvq->desc == NULL) || + (rvq->kickfd == (eventfd_t)-1) || + (rvq->callfd == (eventfd_t)-1) || + (tvq->kickfd == (eventfd_t)-1) || + (tvq->callfd == (eventfd_t)-1)) { + RTE_LOG(INFO, VHOST_CONFIG, + "virtio isn't ready for processing.\n"); + return 0; + } } RTE_LOG(INFO, VHOST_CONFIG, - "virtio isn't ready for processing.\n"); - return 0; + "virtio is now ready for processing.\n"); + return 1; } void @@ -290,13 +297,9 @@ user_get_vring_base(struct vhost_device_ctx ctx, * sent and only sent in vhost_vring_stop. * TODO: cleanup the vring, it isn't usable since here. */ - if (((int)dev->virtqueue[VIRTIO_RXQ]->kickfd) >= 0) { - close(dev->virtqueue[VIRTIO_RXQ]->kickfd); - dev->virtqueue[VIRTIO_RXQ]->kickfd = (eventfd_t)-1; - } - if (((int)dev->virtqueue[VIRTIO_TXQ]->kickfd) >= 0) { - close(dev->virtqueue[VIRTIO_TXQ]->kickfd); - dev->virtqueue[VIRTIO_TXQ]->kickfd = (eventfd_t)-1; + if (((int)dev->virtqueue[state->index]->kickfd) >= 0) { + close(dev->virtqueue[state->index]->kickfd); + dev->virtqueue[state->index]->kickfd = (eventfd_t)-1; } return 0; diff --git a/lib/librte_vhost/virtio-net.c b/lib/librte_vhost/virtio-net.c index 4672e67..55b7440 100644 --- a/lib/librte_vhost/virtio-net.c +++ b/lib/librte_vhost/virtio-net.c @@ -66,9 +66,11 @@ static struct virtio_net_config_ll *ll_root; /* Features supported by this lib. */ #define VHOST_SUPPORTED_FEATURES ((1ULL << VIRTIO_NET_F_MRG_RXBUF) | \ (1ULL << VIRTIO_NET_F_CTRL_VQ) | \ - (1ULL << VIRTIO_NET_F_CTRL_RX)) + (1ULL << VIRTIO_NET_F_CTRL_RX) | \ + (1ULL << VIRTIO_NET_F_MQ)) static uint64_t VHOST_FEATURES = VHOST_SUPPORTED_FEATURES; +static uint32_t q_num = 1; /* * Converts QEMU virtual address to Vhost virtual address. This function is @@ -177,6 +179,8 @@ add_config_ll_entry(struct virtio_net_config_ll *new_ll_dev) static void cleanup_device(struct virtio_net *dev) { + uint32_t q_idx; + /* Unmap QEMU memory file if mapped. */ if (dev->mem) { munmap((void *)(uintptr_t)dev->mem->mapped_address, @@ -185,14 +189,18 @@ cleanup_device(struct virtio_net *dev) } /* Close any event notifiers opened by device. */ - if ((int)dev->virtqueue[VIRTIO_RXQ]->callfd >= 0) - close((int)dev->virtqueue[VIRTIO_RXQ]->callfd); - if ((int)dev->virtqueue[VIRTIO_RXQ]->kickfd >= 0) - close((int)dev->virtqueue[VIRTIO_RXQ]->kickfd); - if ((int)dev->virtqueue[VIRTIO_TXQ]->callfd >= 0) - close((int)dev->virtqueue[VIRTIO_TXQ]->callfd); - if ((int)dev->virtqueue[VIRTIO_TXQ]->kickfd >= 0) - close((int)dev->virtqueue[VIRTIO_TXQ]->kickfd); + for (q_idx = 0; q_idx < dev->num_virt_queues; q_idx++) { + uint32_t virt_rx_q_idx = q_idx * VIRTIO_QNUM + VIRTIO_RXQ; + uint32_t virt_tx_q_idx = q_idx * VIRTIO_QNUM + VIRTIO_TXQ; + if ((int)dev->virtqueue[virt_rx_q_idx]->callfd >= 0) + close((int)dev->virtqueue[virt_rx_q_idx]->callfd); + if ((int)dev->virtqueue[virt_rx_q_idx]->kickfd >= 0) + close((int)dev->virtqueue[virt_rx_q_idx]->kickfd); + if ((int)dev->virtqueue[virt_tx_q_idx]->callfd >= 0) + close((int)dev->virtqueue[virt_tx_q_idx]->callfd); + if ((int)dev->virtqueue[virt_tx_q_idx]->kickfd >= 0) + close((int)dev->virtqueue[virt_tx_q_idx]->kickfd); + } } /* @@ -201,7 +209,10 @@ cleanup_device(struct virtio_net *dev) static void free_device(struct virtio_net_config_ll *ll_dev) { - /* Free any malloc'd memory */ + /* + * Free any malloc'd memory, just need free once even in multi Q case + * as they are malloc'd once. + */ free(ll_dev->dev.virtqueue[VIRTIO_RXQ]); free(ll_dev->dev.virtqueue[VIRTIO_TXQ]); free(ll_dev); @@ -243,6 +254,7 @@ static void init_device(struct virtio_net *dev) { uint64_t vq_offset; + uint32_t q_idx; /* * Virtqueues have already been malloced so @@ -253,17 +265,24 @@ init_device(struct virtio_net *dev) /* Set everything to 0. */ memset((void *)(uintptr_t)((uint64_t)(uintptr_t)dev + vq_offset), 0, (sizeof(struct virtio_net) - (size_t)vq_offset)); - memset(dev->virtqueue[VIRTIO_RXQ], 0, sizeof(struct vhost_virtqueue)); - memset(dev->virtqueue[VIRTIO_TXQ], 0, sizeof(struct vhost_virtqueue)); - dev->virtqueue[VIRTIO_RXQ]->kickfd = (eventfd_t)-1; - dev->virtqueue[VIRTIO_RXQ]->callfd = (eventfd_t)-1; - dev->virtqueue[VIRTIO_TXQ]->kickfd = (eventfd_t)-1; - dev->virtqueue[VIRTIO_TXQ]->callfd = (eventfd_t)-1; + dev->num_virt_queues = q_num; + + for (q_idx = 0; q_idx < dev->num_virt_queues; q_idx++) { + uint32_t virt_rx_q_idx = q_idx * VIRTIO_QNUM + VIRTIO_RXQ; + uint32_t virt_tx_q_idx = q_idx * VIRTIO_QNUM + VIRTIO_TXQ; + memset(dev->virtqueue[virt_rx_q_idx], 0, sizeof(struct vhost_virtqueue)); + memset(dev->virtqueue[virt_tx_q_idx], 0, sizeof(struct vhost_virtqueue)); - /* Backends are set to -1 indicating an inactive device. */ - dev->virtqueue[VIRTIO_RXQ]->backend = VIRTIO_DEV_STOPPED; - dev->virtqueue[VIRTIO_TXQ]->backend = VIRTIO_DEV_STOPPED; + dev->virtqueue[virt_rx_q_idx]->kickfd = (eventfd_t)-1; + dev->virtqueue[virt_rx_q_idx]->callfd = (eventfd_t)-1; + dev->virtqueue[virt_tx_q_idx]->kickfd = (eventfd_t)-1; + dev->virtqueue[virt_tx_q_idx]->callfd = (eventfd_t)-1; + + /* Backends are set to -1 indicating an inactive device. */ + dev->virtqueue[virt_rx_q_idx]->backend = VIRTIO_DEV_STOPPED; + dev->virtqueue[virt_tx_q_idx]->backend = VIRTIO_DEV_STOPPED; + } } /* @@ -276,6 +295,7 @@ new_device(struct vhost_device_ctx ctx) { struct virtio_net_config_ll *new_ll_dev; struct vhost_virtqueue *virtqueue_rx, *virtqueue_tx; + uint32_t q_idx; /* Setup device and virtqueues. */ new_ll_dev = malloc(sizeof(struct virtio_net_config_ll)); @@ -286,7 +306,7 @@ new_device(struct vhost_device_ctx ctx) return -1; } - virtqueue_rx = malloc(sizeof(struct vhost_virtqueue)); + virtqueue_rx = malloc(sizeof(struct vhost_virtqueue) * q_num); if (virtqueue_rx == NULL) { free(new_ll_dev); RTE_LOG(ERR, VHOST_CONFIG, @@ -295,7 +315,7 @@ new_device(struct vhost_device_ctx ctx) return -1; } - virtqueue_tx = malloc(sizeof(struct vhost_virtqueue)); + virtqueue_tx = malloc(sizeof(struct vhost_virtqueue) * q_num); if (virtqueue_tx == NULL) { free(virtqueue_rx); free(new_ll_dev); @@ -305,8 +325,13 @@ new_device(struct vhost_device_ctx ctx) return -1; } - new_ll_dev->dev.virtqueue[VIRTIO_RXQ] = virtqueue_rx; - new_ll_dev->dev.virtqueue[VIRTIO_TXQ] = virtqueue_tx; + memset(new_ll_dev->dev.virtqueue, 0, sizeof(new_ll_dev->dev.virtqueue)); + for (q_idx = 0; q_idx < q_num; q_idx++) { + uint32_t virt_rx_q_idx = q_idx * VIRTIO_QNUM + VIRTIO_RXQ; + uint32_t virt_tx_q_idx = q_idx * VIRTIO_QNUM + VIRTIO_TXQ; + new_ll_dev->dev.virtqueue[virt_rx_q_idx] = virtqueue_rx + q_idx; + new_ll_dev->dev.virtqueue[virt_tx_q_idx] = virtqueue_tx + q_idx; + } /* Initialise device and virtqueues. */ init_device(&new_ll_dev->dev); @@ -429,6 +454,7 @@ static int set_features(struct vhost_device_ctx ctx, uint64_t *pu) { struct virtio_net *dev; + uint32_t q_idx; dev = get_device(ctx); if (dev == NULL) @@ -440,22 +466,26 @@ set_features(struct vhost_device_ctx ctx, uint64_t *pu) dev->features = *pu; /* Set the vhost_hlen depending on if VIRTIO_NET_F_MRG_RXBUF is set. */ - if (dev->features & (1 << VIRTIO_NET_F_MRG_RXBUF)) { - LOG_DEBUG(VHOST_CONFIG, - "(%"PRIu64") Mergeable RX buffers enabled\n", - dev->device_fh); - dev->virtqueue[VIRTIO_RXQ]->vhost_hlen = - sizeof(struct virtio_net_hdr_mrg_rxbuf); - dev->virtqueue[VIRTIO_TXQ]->vhost_hlen = - sizeof(struct virtio_net_hdr_mrg_rxbuf); - } else { - LOG_DEBUG(VHOST_CONFIG, - "(%"PRIu64") Mergeable RX buffers disabled\n", - dev->device_fh); - dev->virtqueue[VIRTIO_RXQ]->vhost_hlen = - sizeof(struct virtio_net_hdr); - dev->virtqueue[VIRTIO_TXQ]->vhost_hlen = - sizeof(struct virtio_net_hdr); + for (q_idx = 0; q_idx < dev->num_virt_queues; q_idx++) { + uint32_t virt_rx_q_idx = q_idx * VIRTIO_QNUM + VIRTIO_RXQ; + uint32_t virt_tx_q_idx = q_idx * VIRTIO_QNUM + VIRTIO_TXQ; + if (dev->features & (1 << VIRTIO_NET_F_MRG_RXBUF)) { + LOG_DEBUG(VHOST_CONFIG, + "(%"PRIu64") Mergeable RX buffers enabled\n", + dev->device_fh); + dev->virtqueue[virt_rx_q_idx]->vhost_hlen = + sizeof(struct virtio_net_hdr_mrg_rxbuf); + dev->virtqueue[virt_tx_q_idx]->vhost_hlen = + sizeof(struct virtio_net_hdr_mrg_rxbuf); + } else { + LOG_DEBUG(VHOST_CONFIG, + "(%"PRIu64") Mergeable RX buffers disabled\n", + dev->device_fh); + dev->virtqueue[virt_rx_q_idx]->vhost_hlen = + sizeof(struct virtio_net_hdr); + dev->virtqueue[virt_tx_q_idx]->vhost_hlen = + sizeof(struct virtio_net_hdr); + } } return 0; } @@ -736,6 +766,15 @@ int rte_vhost_feature_enable(uint64_t feature_mask) return -1; } +int rte_vhost_q_num_get(uint32_t q_number) +{ + if (q_number > VIRTIO_MAX_VIRTQUEUES) + return -1; + + q_num = q_number; + return 0; +} + /* * Register ops so that we can add/remove device to data core. */