From patchwork Wed Mar 27 09:00:27 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Xiaolong Ye X-Patchwork-Id: 51768 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 06CE65A6A; Wed, 27 Mar 2019 10:05:28 +0100 (CET) Received: from mga06.intel.com (mga06.intel.com [134.134.136.31]) by dpdk.org (Postfix) with ESMTP id 4C1925681 for ; Wed, 27 Mar 2019 10:05:13 +0100 (CET) X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from orsmga006.jf.intel.com ([10.7.209.51]) by orsmga104.jf.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 27 Mar 2019 02:05:13 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.60,276,1549958400"; d="scan'208";a="130554302" Received: from yexl-server.sh.intel.com ([10.67.110.206]) by orsmga006.jf.intel.com with ESMTP; 27 Mar 2019 02:05:10 -0700 From: Xiaolong Ye To: dev@dpdk.org, David Marchand , Andrew Rybchenko Cc: Qi Zhang , Karlsson Magnus , Topel Bjorn , Maxime Coquelin , Stephen Hemminger , Ferruh Yigit , Luca Boccassi , Bruce Richardson , Ananyev Konstantin , Xiaolong Ye Date: Wed, 27 Mar 2019 17:00:27 +0800 Message-Id: <20190327090027.72170-6-xiaolong.ye@intel.com> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20190327090027.72170-1-xiaolong.ye@intel.com> References: <20190301080947.91086-1-xiaolong.ye@intel.com> <20190327090027.72170-1-xiaolong.ye@intel.com> Subject: [dpdk-dev] [PATCH v7 5/5] 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 | 130 ++++++++++++++++++++-------- 1 file changed, 96 insertions(+), 34 deletions(-) diff --git a/drivers/net/af_xdp/rte_eth_af_xdp.c b/drivers/net/af_xdp/rte_eth_af_xdp.c index a1fda9212..c6ade4c94 100644 --- a/drivers/net/af_xdp/rte_eth_af_xdp.c +++ b/drivers/net/af_xdp/rte_eth_af_xdp.c @@ -67,6 +67,7 @@ struct xsk_umem_info { struct xsk_umem *umem; struct rte_mempool *mb_pool; void *buffer; + uint8_t zc; }; struct rx_stats { @@ -85,6 +86,7 @@ struct pkt_rx_queue { struct pkt_tx_queue *pair; uint16_t queue_idx; + uint8_t zc; }; struct tx_stats { @@ -202,7 +204,9 @@ eth_af_xdp_rx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts) if (xsk_prod_nb_free(fq, free_thresh) >= free_thresh) (void)reserve_fill_queue(umem, ETH_AF_XDP_RX_BATCH_SIZE); - if (unlikely(rte_pktmbuf_alloc_bulk(rxq->mb_pool, mbufs, rcvd) != 0)) + if (!rxq->zc && + unlikely(rte_pktmbuf_alloc_bulk(rxq->mb_pool, + mbufs, rcvd) != 0)) return 0; for (i = 0; i < rcvd; i++) { @@ -216,13 +220,23 @@ eth_af_xdp_rx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts) len = desc->len; pkt = xsk_umem__get_data(rxq->umem->buffer, addr); - rte_memcpy(rte_pktmbuf_mtod(mbufs[i], void *), pkt, len); - rte_pktmbuf_pkt_len(mbufs[i]) = len; - rte_pktmbuf_data_len(mbufs[i]) = len; - rx_bytes += len; - bufs[count++] = mbufs[i]; - - rte_pktmbuf_free(addr_to_mbuf(umem, addr)); + if (rxq->zc) { + struct rte_mbuf *mbuf; + mbuf = addr_to_mbuf(rxq->umem, addr); + rte_pktmbuf_pkt_len(mbuf) = len; + rte_pktmbuf_data_len(mbuf) = len; + rx_bytes += len; + bufs[count++] = mbuf; + } else { + rte_memcpy(rte_pktmbuf_mtod(mbufs[i], void *), + pkt, len); + rte_pktmbuf_pkt_len(mbufs[i]) = len; + rte_pktmbuf_data_len(mbufs[i]) = len; + rx_bytes += len; + bufs[count++] = mbufs[i]; + + rte_pktmbuf_free(addr_to_mbuf(umem, addr)); + } } xsk_ring_cons__release(rx, rcvd); @@ -295,22 +309,29 @@ 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 (unlikely(mbuf_to_tx == NULL)) { - 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); - rte_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 (unlikely(mbuf_to_tx == NULL)) { + 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); @@ -488,7 +509,7 @@ 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 = { @@ -505,16 +526,23 @@ static struct xsk_umem_info *xdp_umem_configure(void) return NULL; } - umem->mb_pool = rte_pktmbuf_pool_create_with_flags("af_xdp_mempool", - ETH_AF_XDP_NUM_BUFFERS, - 250, 0, - ETH_AF_XDP_FRAME_SIZE - - ETH_AF_XDP_MBUF_OVERHEAD, - MEMPOOL_F_NO_SPREAD | MEMPOOL_CHUNK_F_PAGE_ALIGN, - SOCKET_ID_ANY); - if (umem->mb_pool == NULL || umem->mb_pool->nb_mem_chunks != 1) { - AF_XDP_LOG(ERR, "Failed to create mempool\n"); - goto err; + if (!mb_pool) { + umem->mb_pool = rte_pktmbuf_pool_create_with_flags("af_xdp_mempool", + ETH_AF_XDP_NUM_BUFFERS, + 250, 0, + ETH_AF_XDP_FRAME_SIZE - + ETH_AF_XDP_MBUF_OVERHEAD, + MEMPOOL_F_NO_SPREAD | MEMPOOL_CHUNK_F_PAGE_ALIGN, + SOCKET_ID_ANY); + + if (umem->mb_pool == NULL || + umem->mb_pool->nb_mem_chunks != 1) { + AF_XDP_LOG(ERR, "Failed to create mempool\n"); + goto err; + } + } else { + umem->mb_pool = mb_pool; + umem->zc = 1; } base_addr = (void *)get_base_addr(umem->mb_pool); @@ -536,16 +564,43 @@ 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 == NULL) return -ENOMEM; @@ -622,7 +677,7 @@ 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)) { AF_XDP_LOG(ERR, "Failed to configure xdp socket\n"); ret = -EINVAL; goto err; @@ -630,6 +685,13 @@ 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) + AF_XDP_LOG(INFO, + "zero copy enabled on rx queue %d\n", rx_queue_id); + dev->data->rx_queues[rx_queue_id] = rxq; return 0;