From patchwork Fri Mar 1 08:09:46 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Xiaolong Ye X-Patchwork-Id: 50708 X-Patchwork-Delegate: ferruh.yigit@amd.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 5F89F4C9F; Fri, 1 Mar 2019 09:12:51 +0100 (CET) Received: from mga11.intel.com (mga11.intel.com [192.55.52.93]) by dpdk.org (Postfix) with ESMTP id AFE182BF4 for ; Fri, 1 Mar 2019 09:12:48 +0100 (CET) X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from fmsmga002.fm.intel.com ([10.253.24.26]) by fmsmga102.fm.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 01 Mar 2019 00:12:48 -0800 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.58,426,1544515200"; d="scan'208";a="147594764" Received: from yexl-server.sh.intel.com ([10.67.110.206]) by fmsmga002.fm.intel.com with ESMTP; 01 Mar 2019 00:12:47 -0800 From: Xiaolong Ye To: dev@dpdk.org Cc: Qi Zhang , Xiaolong Ye Date: Fri, 1 Mar 2019 16:09:46 +0800 Message-Id: <20190301080947.91086-6-xiaolong.ye@intel.com> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20190301080947.91086-1-xiaolong.ye@intel.com> References: <20190301080947.91086-1-xiaolong.ye@intel.com> Subject: [dpdk-dev] [PATCH v1 5/6] net/af_xdp: enable zero copy 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" Try to check if external mempool (from rx_queue_setup) is fit for af_xdp, if it is, it will be registered to af_xdp socket directly and there will be no packet data copy on Rx and Tx. Signed-off-by: Xiaolong Ye --- drivers/net/af_xdp/rte_eth_af_xdp.c | 126 ++++++++++++++++++++-------- 1 file changed, 91 insertions(+), 35 deletions(-) diff --git a/drivers/net/af_xdp/rte_eth_af_xdp.c b/drivers/net/af_xdp/rte_eth_af_xdp.c index e8270360c..bfb93f50d 100644 --- a/drivers/net/af_xdp/rte_eth_af_xdp.c +++ b/drivers/net/af_xdp/rte_eth_af_xdp.c @@ -60,6 +60,7 @@ struct xsk_umem_info { struct xsk_umem *umem; struct rte_mempool *mb_pool; void *buffer; + uint8_t zc; }; struct pkt_rx_queue { @@ -74,6 +75,7 @@ struct pkt_rx_queue { struct pkt_tx_queue *pair; uint16_t queue_idx; + uint8_t zc; }; struct pkt_tx_queue { @@ -187,17 +189,24 @@ eth_af_xdp_rx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts) uint32_t len = xsk_ring_cons__rx_desc(rx, idx_rx++)->len; char *pkt = xsk_umem__get_data(rxq->umem->buffer, addr); - mbuf = rte_pktmbuf_alloc(rxq->mb_pool); - if (mbuf) { - memcpy(rte_pktmbuf_mtod(mbuf, void*), pkt, len); + if (rxq->zc) { + mbuf = addr_to_mbuf(rxq->umem, addr); rte_pktmbuf_pkt_len(mbuf) = rte_pktmbuf_data_len(mbuf) = len; - rx_bytes += len; bufs[count++] = mbuf; } else { - dropped++; + mbuf = rte_pktmbuf_alloc(rxq->mb_pool); + if (mbuf) { + memcpy(rte_pktmbuf_mtod(mbuf, void*), pkt, len); + rte_pktmbuf_pkt_len(mbuf) = + rte_pktmbuf_data_len(mbuf) = len; + rx_bytes += len; + bufs[count++] = mbuf; + } else { + dropped++; + } + rte_pktmbuf_free(addr_to_mbuf(umem, addr)); } - rte_pktmbuf_free(addr_to_mbuf(umem, addr)); } xsk_ring_cons__release(rx, rcvd); @@ -278,22 +287,29 @@ eth_af_xdp_tx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts) - ETH_AF_XDP_DATA_HEADROOM; desc = xsk_ring_prod__tx_desc(&txq->tx, idx_tx + i); mbuf = bufs[i]; - if (mbuf->pkt_len <= buf_len) { - mbuf_to_tx = rte_pktmbuf_alloc(umem->mb_pool); - if (!mbuf_to_tx) { - rte_pktmbuf_free(mbuf); - continue; - } - desc->addr = mbuf_to_addr(umem, mbuf_to_tx); + if (txq->pair->zc && mbuf->pool == umem->mb_pool) { + desc->addr = mbuf_to_addr(umem, mbuf); desc->len = mbuf->pkt_len; - pkt = xsk_umem__get_data(umem->buffer, - desc->addr); - memcpy(pkt, rte_pktmbuf_mtod(mbuf, void *), - desc->len); valid++; tx_bytes += mbuf->pkt_len; + } else { + if (mbuf->pkt_len <= buf_len) { + mbuf_to_tx = rte_pktmbuf_alloc(umem->mb_pool); + if (!mbuf_to_tx) { + rte_pktmbuf_free(mbuf); + continue; + } + desc->addr = mbuf_to_addr(umem, mbuf_to_tx); + desc->len = mbuf->pkt_len; + pkt = xsk_umem__get_data(umem->buffer, + desc->addr); + memcpy(pkt, rte_pktmbuf_mtod(mbuf, void *), + desc->len); + valid++; + tx_bytes += mbuf->pkt_len; + } + rte_pktmbuf_free(mbuf); } - rte_pktmbuf_free(mbuf); } xsk_ring_prod__submit(&txq->tx, nb_pkts); @@ -471,7 +487,7 @@ static inline uint64_t get_len(struct rte_mempool *mp) return (uint64_t)(memhdr->len); } -static struct xsk_umem_info *xdp_umem_configure(void) +static struct xsk_umem_info *xdp_umem_configure(struct rte_mempool *mb_pool) { struct xsk_umem_info *umem; struct xsk_umem_config usr_config = { @@ -489,20 +505,26 @@ static struct xsk_umem_info *xdp_umem_configure(void) return NULL; } - snprintf(pool_name, 0x100, "af_xdp_ring"); - umem->mb_pool = rte_pktmbuf_pool_create_with_flags(pool_name, - ETH_AF_XDP_NUM_BUFFERS, - 250, 0, - ETH_AF_XDP_FRAME_SIZE - - ETH_AF_XDP_MBUF_OVERHEAD, - MEMPOOL_F_NO_SPREAD | MEMPOOL_F_PAGE_ALIGN, - SOCKET_ID_ANY); - - if (!umem->mb_pool || umem->mb_pool->nb_mem_chunks != 1) { - RTE_LOG(ERR, PMD, - "Failed to create rte_mempool\n"); - goto err; + if (!mb_pool) { + snprintf(pool_name, 0x100, "af_xdp_ring"); + umem->mb_pool = rte_pktmbuf_pool_create_with_flags(pool_name, + ETH_AF_XDP_NUM_BUFFERS, + 250, 0, + ETH_AF_XDP_FRAME_SIZE - + ETH_AF_XDP_MBUF_OVERHEAD, + MEMPOOL_F_NO_SPREAD | MEMPOOL_F_PAGE_ALIGN, + SOCKET_ID_ANY); + + if (!umem->mb_pool || umem->mb_pool->nb_mem_chunks != 1) { + RTE_LOG(ERR, PMD, + "Failed to create rte_mempool\n"); + goto err; + } + } else { + umem->mb_pool = mb_pool; + umem->zc = 1; } + base_addr = (void *)get_base_addr(umem->mb_pool); ret = xsk_umem__create(&umem->umem, base_addr, @@ -523,16 +545,43 @@ static struct xsk_umem_info *xdp_umem_configure(void) return NULL; } +static uint8_t +check_mempool_zc(struct rte_mempool *mp) +{ + RTE_ASSERT(mp); + + /* must continues */ + if (mp->nb_mem_chunks > 1) + return 0; + + /* check header size */ + if (mp->header_size != RTE_CACHE_LINE_SIZE) + return 0; + + /* check base address */ + if ((uint64_t)get_base_addr(mp) % getpagesize() != 0) + return 0; + + /* check chunk size */ + if ((mp->elt_size + mp->header_size + mp->trailer_size) % + ETH_AF_XDP_FRAME_SIZE != 0) + return 0; + + return 1; +} + static int xsk_configure(struct pmd_internals *internals, struct pkt_rx_queue *rxq, - int ring_size) + int ring_size, struct rte_mempool *mb_pool) { struct xsk_socket_config cfg; struct pkt_tx_queue *txq = rxq->pair; + struct rte_mempool *mp; int ret = 0; int reserve_size; - rxq->umem = xdp_umem_configure(); + mp = check_mempool_zc(mb_pool) ? mb_pool : NULL; + rxq->umem = xdp_umem_configure(mp); if (!rxq->umem) { ret = -ENOMEM; goto err; @@ -633,7 +682,7 @@ eth_rx_queue_setup(struct rte_eth_dev *dev, rxq->mb_pool = mb_pool; - if (xsk_configure(internals, rxq, nb_rx_desc)) { + if (xsk_configure(internals, rxq, nb_rx_desc, mb_pool)) { RTE_LOG(ERR, PMD, "Failed to configure xdp socket\n"); ret = -EINVAL; @@ -642,6 +691,13 @@ eth_rx_queue_setup(struct rte_eth_dev *dev, internals->umem = rxq->umem; + if (mb_pool == internals->umem->mb_pool) + rxq->zc = internals->umem->zc; + + if (rxq->zc) + RTE_LOG(INFO, PMD, + "zero copy enabled on rx queue %d\n", rx_queue_id); + dev->data->rx_queues[rx_queue_id] = rxq; return 0;