From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mga09.intel.com (mga09.intel.com [134.134.136.24]) by dpdk.org (Postfix) with ESMTP id 09CE71FE for ; Sat, 12 Jul 2014 04:24:00 +0200 (CEST) Received: from orsmga001.jf.intel.com ([10.7.209.18]) by orsmga102.jf.intel.com with ESMTP; 11 Jul 2014 19:18:56 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.01,647,1400050800"; d="scan'208";a="542293892" Received: from shvmail01.sh.intel.com ([10.239.29.42]) by orsmga001.jf.intel.com with ESMTP; 11 Jul 2014 19:24:29 -0700 Received: from shecgisg004.sh.intel.com (shecgisg004.sh.intel.com [10.239.29.89]) by shvmail01.sh.intel.com with ESMTP id s6C2ORMY012214; Sat, 12 Jul 2014 10:24:27 +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 s6C2OONc008349; Sat, 12 Jul 2014 10:24:26 +0800 Received: (from couyang@localhost) by shecgisg004.sh.intel.com (8.13.6/8.13.6/Submit) id s6C2OOdf008345; Sat, 12 Jul 2014 10:24:24 +0800 From: Ouyang Changchun To: dev@dpdk.org Date: Sat, 12 Jul 2014 10:24:22 +0800 Message-Id: <1405131862-8248-1-git-send-email-changchun.ouyang@intel.com> X-Mailer: git-send-email 1.7.0.7 Subject: [dpdk-dev] [PATCH] virtio: Support mergeable buffer in virtio PMD. 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: , X-List-Received-Date: Sat, 12 Jul 2014 02:24:02 -0000 This patch supports mergeable buffer feature in DPDK based virtio PMD, which can receive jumbo frame with larger size, like 3K, 4K or even 9K. Signed-off-by: Ouyang Changchun --- lib/librte_pmd_virtio/virtio_ethdev.c | 20 ++-- lib/librte_pmd_virtio/virtio_ethdev.h | 3 + lib/librte_pmd_virtio/virtio_rxtx.c | 172 ++++++++++++++++++++++++++++++---- lib/librte_pmd_virtio/virtqueue.h | 35 ++++--- 4 files changed, 193 insertions(+), 37 deletions(-) diff --git a/lib/librte_pmd_virtio/virtio_ethdev.c b/lib/librte_pmd_virtio/virtio_ethdev.c index d4730f9..57f32f3 100644 --- a/lib/librte_pmd_virtio/virtio_ethdev.c +++ b/lib/librte_pmd_virtio/virtio_ethdev.c @@ -340,7 +340,7 @@ int virtio_dev_queue_setup(struct rte_eth_dev *dev, snprintf(vq_name, sizeof(vq_name), "port%d_tvq%d_hdrzone", dev->data->port_id, queue_idx); vq->virtio_net_hdr_mz = rte_memzone_reserve_aligned(vq_name, - vq_size * sizeof(struct virtio_net_hdr), + vq_size * hw->vtnet_hdr_size, socket_id, 0, CACHE_LINE_SIZE); if (vq->virtio_net_hdr_mz == NULL) { rte_free(vq); @@ -349,7 +349,7 @@ int virtio_dev_queue_setup(struct rte_eth_dev *dev, vq->virtio_net_hdr_mem = (void *)(uintptr_t)vq->virtio_net_hdr_mz->phys_addr; memset(vq->virtio_net_hdr_mz->addr, 0, - vq_size * sizeof(struct virtio_net_hdr)); + vq_size * hw->vtnet_hdr_size); } else if (queue_type == VTNET_CQ) { /* Allocate a page for control vq command, data and status */ snprintf(vq_name, sizeof(vq_name), "port%d_cvq_hdrzone", @@ -526,9 +526,6 @@ virtio_negotiate_features(struct virtio_hw *hw) mask |= VIRTIO_NET_F_GUEST_TSO4 | VIRTIO_NET_F_GUEST_TSO6 | VIRTIO_NET_F_GUEST_ECN; mask |= VTNET_LRO_FEATURES; - /* rx_mbuf should not be in multiple merged segments */ - mask |= VIRTIO_NET_F_MRG_RXBUF; - /* not negotiating INDIRECT descriptor table support */ mask |= VIRTIO_RING_F_INDIRECT_DESC; @@ -677,7 +674,6 @@ eth_virtio_dev_init(__rte_unused struct eth_driver *eth_drv, } eth_dev->dev_ops = &virtio_eth_dev_ops; - eth_dev->rx_pkt_burst = &virtio_recv_pkts; eth_dev->tx_pkt_burst = &virtio_xmit_pkts; if (rte_eal_process_type() == RTE_PROC_SECONDARY) @@ -733,10 +729,13 @@ eth_virtio_dev_init(__rte_unused struct eth_driver *eth_drv, virtio_negotiate_features(hw); /* Setting up rx_header size for the device */ - if (vtpci_with_feature(hw, VIRTIO_NET_F_MRG_RXBUF)) + if (vtpci_with_feature(hw, VIRTIO_NET_F_MRG_RXBUF)) { + eth_dev->rx_pkt_burst = &virtio_recv_mergeable_pkts; hw->vtnet_hdr_size = sizeof(struct virtio_net_hdr_mrg_rxbuf); - else + } else { + eth_dev->rx_pkt_burst = &virtio_recv_pkts; hw->vtnet_hdr_size = sizeof(struct virtio_net_hdr); + } /* Allocate memory for storing MAC addresses */ eth_dev->data->mac_addrs = rte_zmalloc("virtio", ETHER_ADDR_LEN, 0); @@ -932,7 +931,7 @@ static void virtio_dev_free_mbufs(struct rte_eth_dev *dev) while ((buf = (struct rte_mbuf *)virtqueue_detatch_unused( dev->data->rx_queues[i])) != NULL) { - rte_pktmbuf_free_seg(buf); + rte_pktmbuf_free(buf); mbuf_num++; } @@ -951,7 +950,8 @@ static void virtio_dev_free_mbufs(struct rte_eth_dev *dev) mbuf_num = 0; while ((buf = (struct rte_mbuf *)virtqueue_detatch_unused( dev->data->tx_queues[i])) != NULL) { - rte_pktmbuf_free_seg(buf); + rte_pktmbuf_free(buf); + mbuf_num++; } diff --git a/lib/librte_pmd_virtio/virtio_ethdev.h b/lib/librte_pmd_virtio/virtio_ethdev.h index 858e644..d2e1eed 100644 --- a/lib/librte_pmd_virtio/virtio_ethdev.h +++ b/lib/librte_pmd_virtio/virtio_ethdev.h @@ -104,6 +104,9 @@ int virtio_dev_tx_queue_setup(struct rte_eth_dev *dev, uint16_t tx_queue_id, uint16_t virtio_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t nb_pkts); +uint16_t virtio_recv_mergeable_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, + uint16_t nb_pkts); + uint16_t virtio_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pkts); diff --git a/lib/librte_pmd_virtio/virtio_rxtx.c b/lib/librte_pmd_virtio/virtio_rxtx.c index 6f02a61..671c2d3 100644 --- a/lib/librte_pmd_virtio/virtio_rxtx.c +++ b/lib/librte_pmd_virtio/virtio_rxtx.c @@ -127,7 +127,7 @@ virtio_dev_vring_start(struct rte_eth_dev *dev, struct virtqueue *vq, int queue_ error = virtqueue_enqueue_recv_refill(vq, m); if (error) { - rte_pktmbuf_free_seg(m); + rte_pktmbuf_free(m); break; } nbufs++; @@ -259,7 +259,7 @@ virtio_discard_rxbuf(struct virtqueue *vq, struct rte_mbuf *m) error = virtqueue_enqueue_recv_refill(vq, m); if (unlikely(error)) { RTE_LOG(ERR, PMD, "cannot requeue discarded mbuf"); - rte_pktmbuf_free_seg(m); + rte_pktmbuf_free(m); } } @@ -307,19 +307,18 @@ virtio_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t nb_pkts) rxm->pkt.in_port = rxvq->port_id; rxm->pkt.data = (char *)rxm->buf_addr + RTE_PKTMBUF_HEADROOM; + rxm->pkt.nb_segs = 1; rxm->pkt.next = NULL; - rxm->pkt.pkt_len = (uint32_t)(len[i] - - sizeof(struct virtio_net_hdr)); - rxm->pkt.data_len = (uint16_t)(len[i] - - sizeof(struct virtio_net_hdr)); + rxm->pkt.pkt_len = (uint32_t)(len[i] - hw->vtnet_hdr_size); + rxm->pkt.data_len = (uint16_t)(len[i] - hw->vtnet_hdr_size); VIRTIO_DUMP_PACKET(rxm, rxm->pkt.data_len); rx_pkts[nb_rx++] = rxm; - hw->eth_stats.ibytes += len[i] - sizeof(struct virtio_net_hdr); - hw->eth_stats.q_ibytes[rxvq->queue_id] += len[i] - - sizeof(struct virtio_net_hdr); + hw->eth_stats.ibytes += rx_pkts[nb_rx - 1]->pkt.pkt_len; + hw->eth_stats.q_ibytes[rxvq->queue_id] += + rx_pkts[nb_rx - 1]->pkt.pkt_len; } hw->eth_stats.ipackets += nb_rx; @@ -335,11 +334,149 @@ virtio_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t nb_pkts) } error = virtqueue_enqueue_recv_refill(rxvq, new_mbuf); if (unlikely(error)) { - rte_pktmbuf_free_seg(new_mbuf); + rte_pktmbuf_free(new_mbuf); break; } nb_enqueued++; } + + if (likely(nb_enqueued)) { + if (unlikely(virtqueue_kick_prepare(rxvq))) { + virtqueue_notify(rxvq); + PMD_RX_LOG(DEBUG, "Notified\n"); + } + } + + vq_update_avail_idx(rxvq); + + return nb_rx; +} + +uint16_t +virtio_recv_mergeable_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t nb_pkts) +{ + struct virtqueue *rxvq = rx_queue; + struct virtio_hw *hw = rxvq->hw; + struct rte_mbuf *rxm, *new_mbuf; + uint16_t nb_used, num, nb_rx = 0; + uint32_t len[VIRTIO_MBUF_BURST_SZ]; + struct rte_mbuf *rcv_pkts[VIRTIO_MBUF_BURST_SZ]; + struct rte_mbuf *prev; + int error; + uint32_t i = 0, nb_enqueued = 0; + uint32_t seg_num = 0; + uint16_t extra_idx = 0; + + nb_used = VIRTQUEUE_NUSED(rxvq); + + rmb(); + + if (nb_used == 0) + return 0; + + while (i < nb_used) { + struct virtio_net_hdr_mrg_rxbuf * header; + char *head_ptr; + + if (nb_rx >= nb_pkts) + break; + + num = virtqueue_dequeue_burst_rx(rxvq, rcv_pkts, len, 1); + i += num; + + PMD_RX_LOG(DEBUG, "used:%d dequeue:%d\n", nb_used, num); + PMD_RX_LOG(DEBUG, "packet len:%d\n", len[i]); + + rxm = rcv_pkts[0]; + extra_idx = 0; + + if (unlikely(len[0] + < (uint32_t)hw->vtnet_hdr_size + ETHER_HDR_LEN)) { + PMD_RX_LOG(ERR, "Packet drop\n"); + nb_enqueued++; + virtio_discard_rxbuf(rxvq, rxm); + hw->eth_stats.ierrors++; + continue; + } + + head_ptr = (char *)rxm->pkt.data; + head_ptr -= hw->vtnet_hdr_size; + header = (struct virtio_net_hdr_mrg_rxbuf *)head_ptr; + seg_num = header->num_buffers; + + if (seg_num == 0) + seg_num = 1; + + rxm->pkt.data = (char *)rxm->buf_addr + RTE_PKTMBUF_HEADROOM; + rxm->pkt.nb_segs = seg_num; + rxm->pkt.next = NULL; + rxm->pkt.pkt_len = (uint32_t)(len[0] - hw->vtnet_hdr_size); + rxm->pkt.data_len = (uint16_t)(len[0] - hw->vtnet_hdr_size); + + rxm->pkt.in_port = rxvq->port_id; + rx_pkts[nb_rx] = rxm; + + prev = rxm; + + VIRTIO_DUMP_PACKET(rxm, rxm->pkt.data_len); + + /* + * Get extra segments for current uncompleted packet. + */ + if (VIRTQUEUE_NUSED(rxvq) >= seg_num - 1) { + uint32_t rx_num = virtqueue_dequeue_burst_rx(rxvq, + rcv_pkts, len, seg_num - 1); + i += rx_num; + } else { + PMD_RX_LOG(ERR, "No enough segments for packet.\n"); + break; + } + + while (extra_idx < seg_num - 1) { + rxm = rcv_pkts[extra_idx]; + + rxm->pkt.data = + (char *)rxm->buf_addr + RTE_PKTMBUF_HEADROOM; + rxm->pkt.next = NULL; + rxm->pkt.pkt_len = (uint32_t)(len[extra_idx]); + rxm->pkt.data_len = (uint16_t)(len[extra_idx]); + + if (prev) + prev->pkt.next = rxm; + + prev = rxm; + rx_pkts[nb_rx]->pkt.pkt_len += rxm->pkt.pkt_len; + + extra_idx++; + + VIRTIO_DUMP_PACKET(rxm, rxm->pkt.data_len); + }; + + hw->eth_stats.ibytes += rx_pkts[nb_rx]->pkt.pkt_len; + hw->eth_stats.q_ibytes[rxvq->queue_id] += + rx_pkts[nb_rx]->pkt.pkt_len; + nb_rx++; + } + + hw->eth_stats.ipackets += nb_rx; + hw->eth_stats.q_ipackets[rxvq->queue_id] += nb_rx; + + /* Allocate new mbuf for the used descriptor */ + error = ENOSPC; + while (likely(!virtqueue_full(rxvq))) { + new_mbuf = rte_rxmbuf_alloc(rxvq->mpool); + if (unlikely(new_mbuf == NULL)) { + hw->eth_stats.rx_nombuf++; + break; + } + error = virtqueue_enqueue_recv_refill(rxvq, new_mbuf); + if (unlikely(error)) { + rte_pktmbuf_free(new_mbuf); + break; + } + nb_enqueued++; + } + if (likely(nb_enqueued)) { if (unlikely(virtqueue_kick_prepare(rxvq))) { virtqueue_notify(rxvq); @@ -375,12 +512,15 @@ virtio_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pkts) num = (uint16_t)(likely(nb_used < VIRTIO_MBUF_BURST_SZ) ? nb_used : VIRTIO_MBUF_BURST_SZ); while (nb_tx < nb_pkts) { - if (virtqueue_full(txvq) && num) { - virtqueue_dequeue_pkt_tx(txvq); - num--; + int need = tx_pkts[nb_tx]->pkt.nb_segs - txvq->vq_free_cnt; + if ((need > 0) && (num > 0)) { + do { + virtqueue_dequeue_pkt_tx(txvq); + num--; + } while (num > 0); } - if (!virtqueue_full(txvq)) { + if (tx_pkts[nb_tx]->pkt.nb_segs <= txvq->vq_free_cnt) { txm = tx_pkts[nb_tx]; /* Enqueue Packet buffers */ error = virtqueue_enqueue_xmit(txvq, txm); @@ -394,9 +534,9 @@ virtio_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pkts) break; } nb_tx++; - hw->eth_stats.obytes += txm->pkt.data_len; + hw->eth_stats.obytes += txm->pkt.pkt_len; hw->eth_stats.q_obytes[txvq->queue_id] - += txm->pkt.data_len; + += txm->pkt.pkt_len; } else { PMD_TX_LOG(ERR, "No free tx descriptors to transmit\n"); break; diff --git a/lib/librte_pmd_virtio/virtqueue.h b/lib/librte_pmd_virtio/virtqueue.h index a63723d..0ac294a 100644 --- a/lib/librte_pmd_virtio/virtqueue.h +++ b/lib/librte_pmd_virtio/virtqueue.h @@ -297,12 +297,14 @@ static inline int __attribute__((always_inline)) virtqueue_enqueue_recv_refill(struct virtqueue *vq, struct rte_mbuf *cookie) { struct vq_desc_extra *dxp; + struct virtio_hw *hw = vq->hw; struct vring_desc *start_dp; uint16_t needed = 1; uint16_t head_idx, idx; if (unlikely(vq->vq_free_cnt == 0)) return -ENOSPC; + if (unlikely(vq->vq_free_cnt < needed)) return -EMSGSIZE; @@ -316,9 +318,11 @@ virtqueue_enqueue_recv_refill(struct virtqueue *vq, struct rte_mbuf *cookie) dxp->ndescs = needed; start_dp = vq->vq_ring.desc; - start_dp[idx].addr = - (uint64_t) (cookie->buf_physaddr + RTE_PKTMBUF_HEADROOM - sizeof(struct virtio_net_hdr)); - start_dp[idx].len = cookie->buf_len - RTE_PKTMBUF_HEADROOM + sizeof(struct virtio_net_hdr); + start_dp[idx].addr = + (uint64_t)(cookie->buf_physaddr + RTE_PKTMBUF_HEADROOM + - hw->vtnet_hdr_size); + start_dp[idx].len = + cookie->buf_len - RTE_PKTMBUF_HEADROOM + hw->vtnet_hdr_size; start_dp[idx].flags = VRING_DESC_F_WRITE; idx = start_dp[idx].next; vq->vq_desc_head_idx = idx; @@ -335,8 +339,10 @@ virtqueue_enqueue_xmit(struct virtqueue *txvq, struct rte_mbuf *cookie) { struct vq_desc_extra *dxp; struct vring_desc *start_dp; - uint16_t needed = 2; + uint16_t seg_num = cookie->pkt.nb_segs; + uint16_t needed = 1 + seg_num; uint16_t head_idx, idx; + uint16_t head_size = txvq->hw->vtnet_hdr_size; if (unlikely(txvq->vq_free_cnt == 0)) return -ENOSPC; @@ -349,18 +355,25 @@ virtqueue_enqueue_xmit(struct virtqueue *txvq, struct rte_mbuf *cookie) idx = head_idx; dxp = &txvq->vq_descx[idx]; if (dxp->cookie != NULL) - rte_pktmbuf_free_seg(dxp->cookie); + rte_pktmbuf_free(dxp->cookie); dxp->cookie = (void *)cookie; dxp->ndescs = needed; start_dp = txvq->vq_ring.desc; - start_dp[idx].addr = (uint64_t)(uintptr_t)txvq->virtio_net_hdr_mem + idx * sizeof(struct virtio_net_hdr); - start_dp[idx].len = sizeof(struct virtio_net_hdr); + start_dp[idx].addr = + (uint64_t)(uintptr_t)txvq->virtio_net_hdr_mem + idx * head_size; + start_dp[idx].len = (uint32_t)head_size; start_dp[idx].flags = VRING_DESC_F_NEXT; - idx = start_dp[idx].next; - start_dp[idx].addr = RTE_MBUF_DATA_DMA_ADDR(cookie); - start_dp[idx].len = cookie->pkt.data_len; - start_dp[idx].flags = 0; + + for (; ((seg_num > 0) && (cookie != NULL)); seg_num--) { + idx = start_dp[idx].next; + start_dp[idx].addr = RTE_MBUF_DATA_DMA_ADDR(cookie); + start_dp[idx].len = cookie->pkt.data_len; + start_dp[idx].flags = VRING_DESC_F_NEXT; + cookie = cookie->pkt.next; + } + + start_dp[idx].flags &= ~VRING_DESC_F_NEXT; idx = start_dp[idx].next; txvq->vq_desc_head_idx = idx; if (txvq->vq_desc_head_idx == VQ_RING_DESC_CHAIN_END) -- 1.8.4.2