From patchwork Wed Oct 9 13:38:40 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Marvin Liu X-Patchwork-Id: 60738 X-Patchwork-Delegate: maxime.coquelin@redhat.com Return-Path: X-Original-To: patchwork@dpdk.org Delivered-To: patchwork@dpdk.org Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id 1973A1C139; Wed, 9 Oct 2019 07:59:38 +0200 (CEST) Received: from mga12.intel.com (mga12.intel.com [192.55.52.136]) by dpdk.org (Postfix) with ESMTP id 4CD441C0C1 for ; Wed, 9 Oct 2019 07:59:32 +0200 (CEST) X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from fmsmga002.fm.intel.com ([10.253.24.26]) by fmsmga106.fm.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 08 Oct 2019 22:59:33 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.67,273,1566889200"; d="scan'208";a="223473389" Received: from npg-dpdk-virtual-marvin-dev.sh.intel.com ([10.67.119.142]) by fmsmga002.fm.intel.com with ESMTP; 08 Oct 2019 22:59:30 -0700 From: Marvin Liu To: maxime.coquelin@redhat.com, tiwei.bie@intel.com, zhihong.wang@intel.com, stephen@networkplumber.org, gavin.hu@arm.com Cc: dev@dpdk.org, Marvin Liu Date: Wed, 9 Oct 2019 21:38:40 +0800 Message-Id: <20191009133849.69002-6-yong.liu@intel.com> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20191009133849.69002-1-yong.liu@intel.com> References: <20190925171329.63734-1-yong.liu@intel.com> <20191009133849.69002-1-yong.liu@intel.com> Subject: [dpdk-dev] [PATCH v4 05/14] vhost: add batch dequeue function X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" Add batch dequeue function like enqueue function for packed ring, batch dequeue function will not support chained descritpors, single packet dequeue function will handle it. Signed-off-by: Marvin Liu diff --git a/lib/librte_vhost/vhost.h b/lib/librte_vhost/vhost.h index e241436c7..e50e137ca 100644 --- a/lib/librte_vhost/vhost.h +++ b/lib/librte_vhost/vhost.h @@ -61,6 +61,8 @@ #define UNROLL_PRAGMA(param) do {} while (0); #endif +#define PACKED_SINGLE_DEQUEUE_FLAG (VRING_DESC_F_NEXT | VRING_DESC_F_INDIRECT) + /** * Structure contains buffer address, length and descriptor index * from vring to do scatter RX. diff --git a/lib/librte_vhost/virtio_net.c b/lib/librte_vhost/virtio_net.c index 17aabe8eb..2ff7329b2 100644 --- a/lib/librte_vhost/virtio_net.c +++ b/lib/librte_vhost/virtio_net.c @@ -1571,6 +1571,119 @@ virtio_dev_tx_split(struct virtio_net *dev, struct vhost_virtqueue *vq, return i; } +static __rte_always_inline int +vhost_dequeue_batch_packed(struct virtio_net *dev, struct vhost_virtqueue *vq, + struct rte_mempool *mbuf_pool, struct rte_mbuf **pkts, + uint16_t avail_idx, uintptr_t *desc_addrs, uint16_t *ids) +{ + bool wrap_counter = vq->avail_wrap_counter; + struct vring_packed_desc *descs = vq->desc_packed; + uint64_t lens[PACKED_BATCH_SIZE]; + uint64_t buf_lens[PACKED_BATCH_SIZE]; + uint32_t buf_offset = dev->vhost_hlen; + uint16_t i; + + if (unlikely(avail_idx & PACKED_BATCH_MASK)) + return -1; + if (unlikely((avail_idx + PACKED_BATCH_SIZE) > vq->size)) + return -1; + + UNROLL_PRAGMA(UNROLL_PRAGMA_PARAM) + for (i = 0; i < PACKED_BATCH_SIZE; i++) { + if (unlikely(!desc_is_avail(&descs[avail_idx + i], + wrap_counter))) + return -1; + if (unlikely(descs[avail_idx + i].flags & + PACKED_SINGLE_DEQUEUE_FLAG)) + return -1; + } + + rte_smp_rmb(); + + UNROLL_PRAGMA(UNROLL_PRAGMA_PARAM) + for (i = 0; i < PACKED_BATCH_SIZE; i++) + lens[i] = descs[avail_idx + i].len; + + UNROLL_PRAGMA(UNROLL_PRAGMA_PARAM) + for (i = 0; i < PACKED_BATCH_SIZE; i++) { + desc_addrs[i] = vhost_iova_to_vva(dev, vq, + descs[avail_idx + i].addr, + &lens[i], VHOST_ACCESS_RW); + } + + UNROLL_PRAGMA(UNROLL_PRAGMA_PARAM) + for (i = 0; i < PACKED_BATCH_SIZE; i++) { + if (unlikely((lens[i] != descs[avail_idx + i].len))) + return -1; + } + + if (rte_pktmbuf_alloc_bulk(mbuf_pool, pkts, PACKED_BATCH_SIZE)) + return -1; + + UNROLL_PRAGMA(UNROLL_PRAGMA_PARAM) + for (i = 0; i < PACKED_BATCH_SIZE; i++) + buf_lens[i] = pkts[i]->buf_len - pkts[i]->data_off; + + UNROLL_PRAGMA(UNROLL_PRAGMA_PARAM) + for (i = 0; i < PACKED_BATCH_SIZE; i++) { + if (unlikely(buf_lens[i] < (lens[i] - buf_offset))) + goto free_buf; + } + + UNROLL_PRAGMA(UNROLL_PRAGMA_PARAM) + for (i = 0; i < PACKED_BATCH_SIZE; i++) { + pkts[i]->pkt_len = descs[avail_idx + i].len - buf_offset; + pkts[i]->data_len = pkts[i]->pkt_len; + ids[i] = descs[avail_idx + i].id; + } + + return 0; +free_buf: + for (i = 0; i < PACKED_BATCH_SIZE; i++) + rte_pktmbuf_free(pkts[i]); + + return -1; +} + +static __rte_unused int +virtio_dev_tx_batch_packed(struct virtio_net *dev, struct vhost_virtqueue *vq, + struct rte_mempool *mbuf_pool, struct rte_mbuf **pkts) +{ + uint16_t avail_idx = vq->last_avail_idx; + uint32_t buf_offset = dev->vhost_hlen; + uintptr_t desc_addrs[PACKED_BATCH_SIZE]; + uint16_t ids[PACKED_BATCH_SIZE]; + struct virtio_net_hdr *hdr; + uint16_t i; + + if (vhost_dequeue_batch_packed(dev, vq, mbuf_pool, pkts, avail_idx, + desc_addrs, ids)) + return -1; + + UNROLL_PRAGMA(UNROLL_PRAGMA_PARAM) + for (i = 0; i < PACKED_BATCH_SIZE; i++) { + rte_prefetch0((void *)(uintptr_t)desc_addrs[i]); + rte_memcpy(rte_pktmbuf_mtod_offset(pkts[i], void *, 0), + (void *)(uintptr_t)(desc_addrs[i] + buf_offset), + pkts[i]->pkt_len); + } + + if (virtio_net_with_host_offload(dev)) { + UNROLL_PRAGMA(UNROLL_PRAGMA_PARAM) + for (i = 0; i < PACKED_BATCH_SIZE; i++) { + hdr = (struct virtio_net_hdr *)(desc_addrs[i]); + vhost_dequeue_offload(hdr, pkts[i]); + } + } + + vq->last_avail_idx += PACKED_BATCH_SIZE; + if (vq->last_avail_idx >= vq->size) { + vq->last_avail_idx -= vq->size; + vq->avail_wrap_counter ^= 1; + } + return 0; +} + static __rte_always_inline int vhost_dequeue_single_packed(struct virtio_net *dev, struct vhost_virtqueue *vq, struct rte_mempool *mbuf_pool, struct rte_mbuf **pkts, uint16_t *buf_id,