From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mga11.intel.com (mga11.intel.com [192.55.52.93]) by dpdk.org (Postfix) with ESMTP id AA3859A92 for ; Mon, 1 Jun 2015 10:25:58 +0200 (CEST) Received: from orsmga001.jf.intel.com ([10.7.209.18]) by fmsmga102.fm.intel.com with ESMTP; 01 Jun 2015 01:25:59 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.13,531,1427785200"; d="scan'208";a="703170432" Received: from shvmail01.sh.intel.com ([10.239.29.42]) by orsmga001.jf.intel.com with ESMTP; 01 Jun 2015 01:25:57 -0700 Received: from shecgisg004.sh.intel.com (shecgisg004.sh.intel.com [10.239.29.89]) by shvmail01.sh.intel.com with ESMTP id t518PtjW003777; Mon, 1 Jun 2015 16:25:55 +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 t518ProF031685; Mon, 1 Jun 2015 16:25:55 +0800 Received: (from couyang@localhost) by shecgisg004.sh.intel.com (8.13.6/8.13.6/Submit) id t518PrUR031681; Mon, 1 Jun 2015 16:25:53 +0800 From: Ouyang Changchun To: dev@dpdk.org Date: Mon, 1 Jun 2015 16:25:46 +0800 Message-Id: <1433147149-31645-2-git-send-email-changchun.ouyang@intel.com> X-Mailer: git-send-email 1.7.12.2 In-Reply-To: <1433147149-31645-1-git-send-email-changchun.ouyang@intel.com> References: <1432826207-8428-1-git-send-email-changchun.ouyang@intel.com> <1433147149-31645-1-git-send-email-changchun.ouyang@intel.com> Subject: [dpdk-dev] [PATCH v3 1/4] lib_vhost: Fix enqueue/dequeue can't handle chained vring descriptors 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: Mon, 01 Jun 2015 08:25:59 -0000 Vring enqueue need consider the 2 cases: 1. use separate descriptors to contain virtio header and actual data, e.g. the first descriptor is for virtio header, and then followed by descriptors for actual data. 2. virtio header and some data are put together in one descriptor, e.g. the first descriptor contain both virtio header and part of actual data, and then followed by more descriptors for rest of packet data, current DPDK based virtio-net pmd implementation is this case; So does vring dequeue, it should not assume vring descriptor is chained or not chained, it should use desc->flags to check whether it is chained or not. this patch also fixes TX corrupt issue in fedora 21 which uses one single vring descriptor(header and data are in one descriptor) for virtio tx process on default. Changes in v3 - support scattered mbuf, check the mbuf has 'next' pointer or not and copy all segments to vring buffer. Changes in v2 - drop the uncompleted packet - refine code logic Signed-off-by: Changchun Ouyang --- lib/librte_vhost/vhost_rxtx.c | 88 ++++++++++++++++++++++++++++++++++--------- 1 file changed, 71 insertions(+), 17 deletions(-) diff --git a/lib/librte_vhost/vhost_rxtx.c b/lib/librte_vhost/vhost_rxtx.c index 4809d32..5fe1b6c 100644 --- a/lib/librte_vhost/vhost_rxtx.c +++ b/lib/librte_vhost/vhost_rxtx.c @@ -46,7 +46,8 @@ * This function adds buffers to the virtio devices RX virtqueue. Buffers can * be received from the physical port or from another virtio device. A packet * count is returned to indicate the number of packets that are succesfully - * added to the RX queue. This function works when mergeable is disabled. + * added to the RX queue. This function works when the mbuf is scattered, but + * it doesn't support the mergeable feature. */ static inline uint32_t __attribute__((always_inline)) virtio_dev_rx(struct virtio_net *dev, uint16_t queue_id, @@ -59,7 +60,7 @@ virtio_dev_rx(struct virtio_net *dev, uint16_t queue_id, struct virtio_net_hdr_mrg_rxbuf virtio_hdr = {{0, 0, 0, 0, 0, 0}, 0}; uint64_t buff_addr = 0; uint64_t buff_hdr_addr = 0; - uint32_t head[MAX_PKT_BURST], packet_len = 0; + uint32_t head[MAX_PKT_BURST]; uint32_t head_idx, packet_success = 0; uint16_t avail_idx, res_cur_idx; uint16_t res_base_idx, res_end_idx; @@ -113,6 +114,10 @@ virtio_dev_rx(struct virtio_net *dev, uint16_t queue_id, rte_prefetch0(&vq->desc[head[packet_success]]); while (res_cur_idx != res_end_idx) { + uint32_t offset = 0, vb_offset = 0; + uint32_t pkt_len, len_to_cpy, data_len, total_copied = 0; + uint8_t hdr = 0, uncompleted_pkt = 0; + /* Get descriptor from available ring */ desc = &vq->desc[head[packet_success]]; @@ -125,7 +130,6 @@ virtio_dev_rx(struct virtio_net *dev, uint16_t queue_id, /* Copy virtio_hdr to packet and increment buffer address */ buff_hdr_addr = buff_addr; - packet_len = rte_pktmbuf_data_len(buff) + vq->vhost_hlen; /* * If the descriptors are chained the header and data are @@ -136,28 +140,73 @@ virtio_dev_rx(struct virtio_net *dev, uint16_t queue_id, desc = &vq->desc[desc->next]; /* Buffer address translation. */ buff_addr = gpa_to_vva(dev, desc->addr); - desc->len = rte_pktmbuf_data_len(buff); } else { - buff_addr += vq->vhost_hlen; - desc->len = packet_len; + vb_offset += vq->vhost_hlen; + hdr = 1; } + pkt_len = rte_pktmbuf_pkt_len(buff); + data_len = rte_pktmbuf_data_len(buff); + len_to_cpy = RTE_MIN(data_len, + hdr ? desc->len - vq->vhost_hlen : desc->len); + while (len_to_cpy > 0) { + /* Copy mbuf data to buffer */ + rte_memcpy((void *)(uintptr_t)(buff_addr + vb_offset), + (const void *)(rte_pktmbuf_mtod(buff, const char *) + offset), + len_to_cpy); + PRINT_PACKET(dev, (uintptr_t)(buff_addr + vb_offset), + len_to_cpy, 0); + + offset += len_to_cpy; + vb_offset += len_to_cpy; + total_copied += len_to_cpy; + + /* The whole packet completes */ + if (total_copied == pkt_len) + break; + + /* The current segment completes */ + if (offset == data_len) { + buff = buff->next; + if (buff != NULL) { + offset = 0; + data_len = rte_pktmbuf_data_len(buff); + } + } + + /* The current vring descriptor done */ + if (vb_offset == desc->len) { + if (desc->flags & VRING_DESC_F_NEXT) { + desc = &vq->desc[desc->next]; + buff_addr = gpa_to_vva(dev, desc->addr); + vb_offset = 0; + } else { + /* Room in vring buffer is not enough */ + uncompleted_pkt = 1; + break; + } + } + len_to_cpy = RTE_MIN(data_len - offset, desc->len - vb_offset); + }; + /* Update used ring with desc information */ vq->used->ring[res_cur_idx & (vq->size - 1)].id = head[packet_success]; - vq->used->ring[res_cur_idx & (vq->size - 1)].len = packet_len; - /* Copy mbuf data to buffer */ - /* FIXME for sg mbuf and the case that desc couldn't hold the mbuf data */ - rte_memcpy((void *)(uintptr_t)buff_addr, - rte_pktmbuf_mtod(buff, const void *), - rte_pktmbuf_data_len(buff)); - PRINT_PACKET(dev, (uintptr_t)buff_addr, - rte_pktmbuf_data_len(buff), 0); + /* Drop the packet if it is uncompleted */ + if (unlikely(uncompleted_pkt == 1)) + vq->used->ring[res_cur_idx & (vq->size - 1)].len = + vq->vhost_hlen; + else + vq->used->ring[res_cur_idx & (vq->size - 1)].len = + pkt_len + vq->vhost_hlen; res_cur_idx++; packet_success++; + if (unlikely(uncompleted_pkt == 1)) + continue; + rte_memcpy((void *)(uintptr_t)buff_hdr_addr, (const void *)&virtio_hdr, vq->vhost_hlen); @@ -589,7 +638,14 @@ rte_vhost_dequeue_burst(struct virtio_net *dev, uint16_t queue_id, desc = &vq->desc[head[entry_success]]; /* Discard first buffer as it is the virtio header */ - desc = &vq->desc[desc->next]; + if (desc->flags & VRING_DESC_F_NEXT) { + desc = &vq->desc[desc->next]; + vb_offset = 0; + vb_avail = desc->len; + } else { + vb_offset = vq->vhost_hlen; + vb_avail = desc->len - vb_offset; + } /* Buffer address translation. */ vb_addr = gpa_to_vva(dev, desc->addr); @@ -608,8 +664,6 @@ rte_vhost_dequeue_burst(struct virtio_net *dev, uint16_t queue_id, vq->used->ring[used_idx].id = head[entry_success]; vq->used->ring[used_idx].len = 0; - vb_offset = 0; - vb_avail = desc->len; /* Allocate an mbuf and populate the structure. */ m = rte_pktmbuf_alloc(mbuf_pool); if (unlikely(m == NULL)) { -- 1.8.4.2