From patchwork Mon Dec 7 16:32:30 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "lorenzo@kernel.org" X-Patchwork-Id: 11956335 X-Patchwork-Delegate: bpf@iogearbox.net Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-17.0 required=3.0 tests=BAYES_00,INCLUDES_CR_TRAILER, INCLUDES_PATCH,MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS,USER_AGENT_GIT autolearn=unavailable autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 1C46CC197BF for ; Mon, 7 Dec 2020 16:33:52 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id CA411239A4 for ; Mon, 7 Dec 2020 16:33:51 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1726866AbgLGQdk (ORCPT ); Mon, 7 Dec 2020 11:33:40 -0500 Received: from mail.kernel.org ([198.145.29.99]:60604 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1726249AbgLGQdj (ORCPT ); Mon, 7 Dec 2020 11:33:39 -0500 From: Lorenzo Bianconi Authentication-Results: mail.kernel.org; dkim=permerror (bad message/signature format) To: bpf@vger.kernel.org, netdev@vger.kernel.org Cc: davem@davemloft.net, kuba@kernel.org, ast@kernel.org, daniel@iogearbox.net, shayagr@amazon.com, sameehj@amazon.com, john.fastabend@gmail.com, dsahern@kernel.org, brouer@redhat.com, echaudro@redhat.com, lorenzo.bianconi@redhat.com, jasowang@redhat.com Subject: [PATCH v5 bpf-next 01/14] xdp: introduce mb in xdp_buff/xdp_frame Date: Mon, 7 Dec 2020 17:32:30 +0100 Message-Id: <7e7dbe0c739640b053c930d3cd22ab7588d6aa3c.1607349924.git.lorenzo@kernel.org> X-Mailer: git-send-email 2.28.0 In-Reply-To: References: MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: bpf@vger.kernel.org X-Patchwork-Delegate: bpf@iogearbox.net Introduce multi-buffer bit (mb) in xdp_frame/xdp_buffer data structure in order to specify if this is a linear buffer (mb = 0) or a multi-buffer frame (mb = 1). In the latter case the shared_info area at the end of the first buffer is been properly initialized to link together subsequent buffers. Signed-off-by: Lorenzo Bianconi --- include/net/xdp.h | 8 ++++++-- net/core/xdp.c | 1 + 2 files changed, 7 insertions(+), 2 deletions(-) diff --git a/include/net/xdp.h b/include/net/xdp.h index 700ad5db7f5d..70559720ff44 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -73,7 +73,8 @@ struct xdp_buff { void *data_hard_start; struct xdp_rxq_info *rxq; struct xdp_txq_info *txq; - u32 frame_sz; /* frame size to deduce data_hard_end/reserved tailroom*/ + u32 frame_sz:31; /* frame size to deduce data_hard_end/reserved tailroom*/ + u32 mb:1; /* xdp non-linear buffer */ }; /* Reserve memory area at end-of data area. @@ -97,7 +98,8 @@ struct xdp_frame { u16 len; u16 headroom; u32 metasize:8; - u32 frame_sz:24; + u32 frame_sz:23; + u32 mb:1; /* xdp non-linear frame */ /* Lifetime of xdp_rxq_info is limited to NAPI/enqueue time, * while mem info is valid on remote CPU. */ @@ -154,6 +156,7 @@ void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp) xdp->data_end = frame->data + frame->len; xdp->data_meta = frame->data - frame->metasize; xdp->frame_sz = frame->frame_sz; + xdp->mb = frame->mb; } static inline @@ -180,6 +183,7 @@ int xdp_update_frame_from_buff(struct xdp_buff *xdp, xdp_frame->headroom = headroom - sizeof(*xdp_frame); xdp_frame->metasize = metasize; xdp_frame->frame_sz = xdp->frame_sz; + xdp_frame->mb = xdp->mb; return 0; } diff --git a/net/core/xdp.c b/net/core/xdp.c index 17ffd33c6b18..79dd45234e4d 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -509,6 +509,7 @@ struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp) xdpf->headroom = 0; xdpf->metasize = metasize; xdpf->frame_sz = PAGE_SIZE; + xdpf->mb = xdp->mb; xdpf->mem.type = MEM_TYPE_PAGE_ORDER0; xsk_buff_free(xdp); From patchwork Mon Dec 7 16:32:31 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "lorenzo@kernel.org" X-Patchwork-Id: 11956337 X-Patchwork-Delegate: bpf@iogearbox.net Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-17.0 required=3.0 tests=BAYES_00,INCLUDES_CR_TRAILER, INCLUDES_PATCH,MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS,USER_AGENT_GIT autolearn=unavailable autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 5B530C1B0E3 for ; Mon, 7 Dec 2020 16:33:52 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 34FF523998 for ; Mon, 7 Dec 2020 16:33:52 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1727050AbgLGQdp (ORCPT ); Mon, 7 Dec 2020 11:33:45 -0500 Received: from mail.kernel.org ([198.145.29.99]:60656 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1726249AbgLGQdo (ORCPT ); Mon, 7 Dec 2020 11:33:44 -0500 From: Lorenzo Bianconi Authentication-Results: mail.kernel.org; dkim=permerror (bad message/signature format) To: bpf@vger.kernel.org, netdev@vger.kernel.org Cc: davem@davemloft.net, kuba@kernel.org, ast@kernel.org, daniel@iogearbox.net, shayagr@amazon.com, sameehj@amazon.com, john.fastabend@gmail.com, dsahern@kernel.org, brouer@redhat.com, echaudro@redhat.com, lorenzo.bianconi@redhat.com, jasowang@redhat.com Subject: [PATCH v5 bpf-next 02/14] xdp: initialize xdp_buff mb bit to 0 in all XDP drivers Date: Mon, 7 Dec 2020 17:32:31 +0100 Message-Id: <693d48b46dd5172763952acd94358cc5d02dcda3.1607349924.git.lorenzo@kernel.org> X-Mailer: git-send-email 2.28.0 In-Reply-To: References: MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: bpf@vger.kernel.org X-Patchwork-Delegate: bpf@iogearbox.net Initialize multi-buffer bit (mb) to 0 in all XDP-capable drivers. This is a preliminary patch to enable xdp multi-buffer support. Signed-off-by: Lorenzo Bianconi --- drivers/net/ethernet/amazon/ena/ena_netdev.c | 1 + drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c | 1 + drivers/net/ethernet/cavium/thunder/nicvf_main.c | 1 + drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 1 + drivers/net/ethernet/intel/i40e/i40e_txrx.c | 1 + drivers/net/ethernet/intel/ice/ice_txrx.c | 1 + drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 1 + drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 1 + drivers/net/ethernet/marvell/mvneta.c | 1 + drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 1 + drivers/net/ethernet/mellanox/mlx4/en_rx.c | 1 + drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 1 + drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 1 + drivers/net/ethernet/qlogic/qede/qede_fp.c | 1 + drivers/net/ethernet/sfc/rx.c | 1 + drivers/net/ethernet/socionext/netsec.c | 1 + drivers/net/ethernet/ti/cpsw.c | 1 + drivers/net/ethernet/ti/cpsw_new.c | 1 + drivers/net/hyperv/netvsc_bpf.c | 1 + drivers/net/tun.c | 2 ++ drivers/net/veth.c | 1 + drivers/net/virtio_net.c | 2 ++ drivers/net/xen-netfront.c | 1 + net/core/dev.c | 1 + 24 files changed, 26 insertions(+) diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index 0e98f45c2b22..abe826395e2f 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -1569,6 +1569,7 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi, res_budget = budget; xdp.rxq = &rx_ring->xdp_rxq; xdp.frame_sz = ENA_PAGE_SIZE; + xdp.mb = 0; do { xdp_verdict = XDP_PASS; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c index fcc262064766..344644b6dd4d 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c @@ -139,6 +139,7 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons, xdp.data_end = *data_ptr + *len; xdp.rxq = &rxr->xdp_rxq; xdp.frame_sz = PAGE_SIZE; /* BNXT_RX_PAGE_MODE(bp) when XDP enabled */ + xdp.mb = 0; orig_data = xdp.data; rcu_read_lock(); diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index f3b7b443f964..4e790a50d14c 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -553,6 +553,7 @@ static inline bool nicvf_xdp_rx(struct nicvf *nic, struct bpf_prog *prog, xdp.data_end = xdp.data + len; xdp.rxq = &rq->xdp_rxq; xdp.frame_sz = RCV_FRAG_LEN + XDP_PACKET_HEADROOM; + xdp.mb = 0; orig_data = xdp.data; rcu_read_lock(); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index 91cff93dbdae..fe70be3ca399 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -366,6 +366,7 @@ static u32 dpaa2_eth_run_xdp(struct dpaa2_eth_priv *priv, xdp.frame_sz = DPAA2_ETH_RX_BUF_RAW_SIZE - (dpaa2_fd_get_offset(fd) - XDP_PACKET_HEADROOM); + xdp.mb = 0; xdp_act = bpf_prog_run_xdp(xdp_prog, &xdp); diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 9f73cd7aee09..1c8acebfde3d 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -2343,6 +2343,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) xdp.frame_sz = i40e_rx_frame_truesize(rx_ring, 0); #endif xdp.rxq = &rx_ring->xdp_rxq; + xdp.mb = 0; while (likely(total_rx_packets < (unsigned int)budget)) { struct i40e_rx_buffer *rx_buffer; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 77d5eae6b4c2..0f8a996e298b 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -1089,6 +1089,7 @@ int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget) #if (PAGE_SIZE < 8192) xdp.frame_sz = ice_rx_frame_truesize(rx_ring, 0); #endif + xdp.mb = 0; /* start the loop to process Rx packets bounded by 'budget' */ while (likely(total_rx_pkts < (unsigned int)budget)) { diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 50e6b8b6ba7b..2e028b306677 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -2298,6 +2298,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, #if (PAGE_SIZE < 8192) xdp.frame_sz = ixgbe_rx_frame_truesize(rx_ring, 0); #endif + xdp.mb = 0; while (likely(total_rx_packets < budget)) { union ixgbe_adv_rx_desc *rx_desc; diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 4061cd7db5dd..037bfb2aadac 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -1129,6 +1129,7 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector, struct xdp_buff xdp; xdp.rxq = &rx_ring->xdp_rxq; + xdp.mb = 0; /* Frame size depend on rx_ring setup when PAGE_SIZE=4K */ #if (PAGE_SIZE < 8192) diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 563ceac3060f..1e5b5c69685a 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -2366,6 +2366,7 @@ static int mvneta_rx_swbm(struct napi_struct *napi, xdp_buf.data_hard_start = NULL; xdp_buf.frame_sz = PAGE_SIZE; xdp_buf.rxq = &rxq->xdp_rxq; + xdp_buf.mb = 0; sinfo.nr_frags = 0; diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index afdd22827223..32b48de36841 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -3566,6 +3566,7 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi, xdp.data = data + MVPP2_MH_SIZE + MVPP2_SKB_HEADROOM; xdp.data_end = xdp.data + rx_bytes; xdp.frame_sz = PAGE_SIZE; + xdp.mb = 0; if (bm_pool->pkt_size == MVPP2_BM_SHORT_PKT_SIZE) xdp.rxq = &rxq->xdp_rxq_short; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 7954c1daf2b6..547ff84bb71a 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -684,6 +684,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud xdp_prog = rcu_dereference(ring->xdp_prog); xdp.rxq = &ring->xdp_rxq; xdp.frame_sz = priv->frag_info[0].frag_stride; + xdp.mb = 0; doorbell_pending = false; /* We assume a 1:1 mapping between CQEs and Rx descriptors, so Rx diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 6628a0197b4e..50fd12ba3a0f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -1133,6 +1133,7 @@ static void mlx5e_fill_xdp_buff(struct mlx5e_rq *rq, void *va, u16 headroom, xdp->data_end = xdp->data + len; xdp->rxq = &rq->xdp_rxq; xdp->frame_sz = rq->buff.frame0_sz; + xdp->mb = 0; } static struct sk_buff * diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index b4acf2f41e84..4e762bbf283c 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -1824,6 +1824,7 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget) true_bufsz = xdp_prog ? PAGE_SIZE : dp->fl_bufsz; xdp.frame_sz = PAGE_SIZE - NFP_NET_RX_BUF_HEADROOM; xdp.rxq = &rx_ring->xdp_rxq; + xdp.mb = 0; tx_ring = r_vec->xdp_ring; while (pkts_polled < budget) { diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c index a2494bf85007..14a54094ca08 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_fp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c @@ -1096,6 +1096,7 @@ static bool qede_rx_xdp(struct qede_dev *edev, xdp.data_end = xdp.data + *len; xdp.rxq = &rxq->xdp_rxq; xdp.frame_sz = rxq->rx_buf_seg_size; /* PAGE_SIZE when XDP enabled */ + xdp.mb = 0; /* Queues always have a full reset currently, so for the time * being until there's atomic program replace just mark read diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c index aaa112877561..286feb510c21 100644 --- a/drivers/net/ethernet/sfc/rx.c +++ b/drivers/net/ethernet/sfc/rx.c @@ -301,6 +301,7 @@ static bool efx_do_xdp(struct efx_nic *efx, struct efx_channel *channel, xdp.data_end = xdp.data + rx_buf->len; xdp.rxq = &rx_queue->xdp_rxq_info; xdp.frame_sz = efx->rx_page_buf_step; + xdp.mb = 0; xdp_act = bpf_prog_run_xdp(xdp_prog, &xdp); rcu_read_unlock(); diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c index 19d20a6d0d44..8853db2575f0 100644 --- a/drivers/net/ethernet/socionext/netsec.c +++ b/drivers/net/ethernet/socionext/netsec.c @@ -958,6 +958,7 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget) xdp.rxq = &dring->xdp_rxq; xdp.frame_sz = PAGE_SIZE; + xdp.mb = 0; rcu_read_lock(); xdp_prog = READ_ONCE(priv->xdp_prog); diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index b0f00b4edd94..6e3fa1994bd5 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -407,6 +407,7 @@ static void cpsw_rx_handler(void *token, int len, int status) xdp.data_hard_start = pa; xdp.rxq = &priv->xdp_rxq[ch]; xdp.frame_sz = PAGE_SIZE; + xdp.mb = 0; port = priv->emac_port + cpsw->data.dual_emac; ret = cpsw_run_xdp(priv, ch, &xdp, page, port); diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c index 2f5e0ad23ad7..a13535fefbeb 100644 --- a/drivers/net/ethernet/ti/cpsw_new.c +++ b/drivers/net/ethernet/ti/cpsw_new.c @@ -350,6 +350,7 @@ static void cpsw_rx_handler(void *token, int len, int status) xdp.data_hard_start = pa; xdp.rxq = &priv->xdp_rxq[ch]; xdp.frame_sz = PAGE_SIZE; + xdp.mb = 0; ret = cpsw_run_xdp(priv, ch, &xdp, page, priv->emac_port); if (ret != CPSW_XDP_PASS) diff --git a/drivers/net/hyperv/netvsc_bpf.c b/drivers/net/hyperv/netvsc_bpf.c index 440486d9c999..a4bafc64997f 100644 --- a/drivers/net/hyperv/netvsc_bpf.c +++ b/drivers/net/hyperv/netvsc_bpf.c @@ -50,6 +50,7 @@ u32 netvsc_run_xdp(struct net_device *ndev, struct netvsc_channel *nvchan, xdp->data_end = xdp->data + len; xdp->rxq = &nvchan->xdp_rxq; xdp->frame_sz = PAGE_SIZE; + xdp->mb = 0; memcpy(xdp->data, data, len); diff --git a/drivers/net/tun.c b/drivers/net/tun.c index fbed05ae7b0f..8c100f4b2001 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1605,6 +1605,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun, xdp.data_end = xdp.data + len; xdp.rxq = &tfile->xdp_rxq; xdp.frame_sz = buflen; + xdp.mb = 0; act = bpf_prog_run_xdp(xdp_prog, &xdp); if (act == XDP_REDIRECT || act == XDP_TX) { @@ -2347,6 +2348,7 @@ static int tun_xdp_one(struct tun_struct *tun, xdp_set_data_meta_invalid(xdp); xdp->rxq = &tfile->xdp_rxq; xdp->frame_sz = buflen; + xdp->mb = 0; act = bpf_prog_run_xdp(xdp_prog, xdp); err = tun_xdp_act(tun, xdp_prog, xdp, act); diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 02bfcdf50a7a..52e050228a42 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -719,6 +719,7 @@ static struct sk_buff *veth_xdp_rcv_skb(struct veth_rq *rq, /* SKB "head" area always have tailroom for skb_shared_info */ xdp.frame_sz = (void *)skb_end_pointer(skb) - xdp.data_hard_start; xdp.frame_sz += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + xdp.mb = 0; orig_data = xdp.data; orig_data_end = xdp.data_end; diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 052975ea0af4..4c15e30d7ef1 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -695,6 +695,7 @@ static struct sk_buff *receive_small(struct net_device *dev, xdp.data_meta = xdp.data; xdp.rxq = &rq->xdp_rxq; xdp.frame_sz = buflen; + xdp.mb = 0; orig_data = xdp.data; act = bpf_prog_run_xdp(xdp_prog, &xdp); stats->xdp_packets++; @@ -865,6 +866,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, xdp.data_meta = xdp.data; xdp.rxq = &rq->xdp_rxq; xdp.frame_sz = frame_sz - vi->hdr_len; + xdp.mb = 0; act = bpf_prog_run_xdp(xdp_prog, &xdp); stats->xdp_packets++; diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index b01848ef4649..34a254eab58b 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -870,6 +870,7 @@ static u32 xennet_run_xdp(struct netfront_queue *queue, struct page *pdata, xdp->data_end = xdp->data + len; xdp->rxq = &queue->xdp_rxq; xdp->frame_sz = XEN_PAGE_SIZE - XDP_PACKET_HEADROOM; + xdp->mb = 0; act = bpf_prog_run_xdp(prog, xdp); switch (act) { diff --git a/net/core/dev.c b/net/core/dev.c index ce8fea2e2788..7f0b2b25860a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4633,6 +4633,7 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, /* SKB "head" area always have tailroom for skb_shared_info */ xdp->frame_sz = (void *)skb_end_pointer(skb) - xdp->data_hard_start; xdp->frame_sz += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + xdp->mb = 0; orig_data_end = xdp->data_end; orig_data = xdp->data; From patchwork Mon Dec 7 16:32:32 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "lorenzo@kernel.org" X-Patchwork-Id: 11956339 X-Patchwork-Delegate: bpf@iogearbox.net Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-17.0 required=3.0 tests=BAYES_00,INCLUDES_CR_TRAILER, INCLUDES_PATCH,MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS,USER_AGENT_GIT autolearn=unavailable autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 9184DC2BB40 for ; Mon, 7 Dec 2020 16:33:52 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 65FD82395B for ; Mon, 7 Dec 2020 16:33:52 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1727225AbgLGQdr (ORCPT ); Mon, 7 Dec 2020 11:33:47 -0500 Received: from mail.kernel.org ([198.145.29.99]:60684 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1726249AbgLGQdr (ORCPT ); Mon, 7 Dec 2020 11:33:47 -0500 From: Lorenzo Bianconi Authentication-Results: mail.kernel.org; dkim=permerror (bad message/signature format) To: bpf@vger.kernel.org, netdev@vger.kernel.org Cc: davem@davemloft.net, kuba@kernel.org, ast@kernel.org, daniel@iogearbox.net, shayagr@amazon.com, sameehj@amazon.com, john.fastabend@gmail.com, dsahern@kernel.org, brouer@redhat.com, echaudro@redhat.com, lorenzo.bianconi@redhat.com, jasowang@redhat.com Subject: [PATCH v5 bpf-next 03/14] xdp: add xdp_shared_info data structure Date: Mon, 7 Dec 2020 17:32:32 +0100 Message-Id: <21d27f233e37b66c9ad4073dd09df5c2904112a4.1607349924.git.lorenzo@kernel.org> X-Mailer: git-send-email 2.28.0 In-Reply-To: References: MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: bpf@vger.kernel.org X-Patchwork-Delegate: bpf@iogearbox.net Introduce xdp_shared_info data structure to contain info about "non-linear" xdp frame. xdp_shared_info will alias skb_shared_info allowing to keep most of the frags in the same cache-line. Introduce some xdp_shared_info helpers aligned to skb_frag* ones Signed-off-by: Lorenzo Bianconi --- drivers/net/ethernet/marvell/mvneta.c | 62 +++++++++++++++------------ include/net/xdp.h | 52 ++++++++++++++++++++-- 2 files changed, 82 insertions(+), 32 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 1e5b5c69685a..d635463609ad 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -2033,14 +2033,17 @@ int mvneta_rx_refill_queue(struct mvneta_port *pp, struct mvneta_rx_queue *rxq) static void mvneta_xdp_put_buff(struct mvneta_port *pp, struct mvneta_rx_queue *rxq, - struct xdp_buff *xdp, struct skb_shared_info *sinfo, + struct xdp_buff *xdp, struct xdp_shared_info *xdp_sinfo, int sync_len) { int i; - for (i = 0; i < sinfo->nr_frags; i++) + for (i = 0; i < xdp_sinfo->nr_frags; i++) { + skb_frag_t *frag = &xdp_sinfo->frags[i]; + page_pool_put_full_page(rxq->page_pool, - skb_frag_page(&sinfo->frags[i]), true); + xdp_get_frag_page(frag), true); + } page_pool_put_page(rxq->page_pool, virt_to_head_page(xdp->data), sync_len, true); } @@ -2179,7 +2182,7 @@ mvneta_run_xdp(struct mvneta_port *pp, struct mvneta_rx_queue *rxq, struct bpf_prog *prog, struct xdp_buff *xdp, u32 frame_sz, struct mvneta_stats *stats) { - struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); + struct xdp_shared_info *xdp_sinfo = xdp_get_shared_info_from_buff(xdp); unsigned int len, data_len, sync; u32 ret, act; @@ -2200,7 +2203,7 @@ mvneta_run_xdp(struct mvneta_port *pp, struct mvneta_rx_queue *rxq, err = xdp_do_redirect(pp->dev, xdp, prog); if (unlikely(err)) { - mvneta_xdp_put_buff(pp, rxq, xdp, sinfo, sync); + mvneta_xdp_put_buff(pp, rxq, xdp, xdp_sinfo, sync); ret = MVNETA_XDP_DROPPED; } else { ret = MVNETA_XDP_REDIR; @@ -2211,7 +2214,7 @@ mvneta_run_xdp(struct mvneta_port *pp, struct mvneta_rx_queue *rxq, case XDP_TX: ret = mvneta_xdp_xmit_back(pp, xdp); if (ret != MVNETA_XDP_TX) - mvneta_xdp_put_buff(pp, rxq, xdp, sinfo, sync); + mvneta_xdp_put_buff(pp, rxq, xdp, xdp_sinfo, sync); break; default: bpf_warn_invalid_xdp_action(act); @@ -2220,7 +2223,7 @@ mvneta_run_xdp(struct mvneta_port *pp, struct mvneta_rx_queue *rxq, trace_xdp_exception(pp->dev, prog, act); fallthrough; case XDP_DROP: - mvneta_xdp_put_buff(pp, rxq, xdp, sinfo, sync); + mvneta_xdp_put_buff(pp, rxq, xdp, xdp_sinfo, sync); ret = MVNETA_XDP_DROPPED; stats->xdp_drop++; break; @@ -2241,9 +2244,9 @@ mvneta_swbm_rx_frame(struct mvneta_port *pp, { unsigned char *data = page_address(page); int data_len = -MVNETA_MH_SIZE, len; + struct xdp_shared_info *xdp_sinfo; struct net_device *dev = pp->dev; enum dma_data_direction dma_dir; - struct skb_shared_info *sinfo; if (*size > MVNETA_MAX_RX_BUF_SIZE) { len = MVNETA_MAX_RX_BUF_SIZE; @@ -2269,8 +2272,8 @@ mvneta_swbm_rx_frame(struct mvneta_port *pp, xdp->data_end = xdp->data + data_len; xdp_set_data_meta_invalid(xdp); - sinfo = xdp_get_shared_info_from_buff(xdp); - sinfo->nr_frags = 0; + xdp_sinfo = xdp_get_shared_info_from_buff(xdp); + xdp_sinfo->nr_frags = 0; } static void @@ -2278,7 +2281,7 @@ mvneta_swbm_add_rx_fragment(struct mvneta_port *pp, struct mvneta_rx_desc *rx_desc, struct mvneta_rx_queue *rxq, struct xdp_buff *xdp, int *size, - struct skb_shared_info *xdp_sinfo, + struct xdp_shared_info *xdp_sinfo, struct page *page) { struct net_device *dev = pp->dev; @@ -2301,13 +2304,13 @@ mvneta_swbm_add_rx_fragment(struct mvneta_port *pp, if (data_len > 0 && xdp_sinfo->nr_frags < MAX_SKB_FRAGS) { skb_frag_t *frag = &xdp_sinfo->frags[xdp_sinfo->nr_frags++]; - skb_frag_off_set(frag, pp->rx_offset_correction); - skb_frag_size_set(frag, data_len); - __skb_frag_set_page(frag, page); + xdp_set_frag_offset(frag, pp->rx_offset_correction); + xdp_set_frag_size(frag, data_len); + xdp_set_frag_page(frag, page); /* last fragment */ if (len == *size) { - struct skb_shared_info *sinfo; + struct xdp_shared_info *sinfo; sinfo = xdp_get_shared_info_from_buff(xdp); sinfo->nr_frags = xdp_sinfo->nr_frags; @@ -2324,10 +2327,13 @@ static struct sk_buff * mvneta_swbm_build_skb(struct mvneta_port *pp, struct mvneta_rx_queue *rxq, struct xdp_buff *xdp, u32 desc_status) { - struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); - int i, num_frags = sinfo->nr_frags; + struct xdp_shared_info *xdp_sinfo = xdp_get_shared_info_from_buff(xdp); + int i, num_frags = xdp_sinfo->nr_frags; + skb_frag_t frag_list[MAX_SKB_FRAGS]; struct sk_buff *skb; + memcpy(frag_list, xdp_sinfo->frags, sizeof(skb_frag_t) * num_frags); + skb = build_skb(xdp->data_hard_start, PAGE_SIZE); if (!skb) return ERR_PTR(-ENOMEM); @@ -2339,12 +2345,12 @@ mvneta_swbm_build_skb(struct mvneta_port *pp, struct mvneta_rx_queue *rxq, mvneta_rx_csum(pp, desc_status, skb); for (i = 0; i < num_frags; i++) { - skb_frag_t *frag = &sinfo->frags[i]; + struct page *page = xdp_get_frag_page(&frag_list[i]); skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, - skb_frag_page(frag), skb_frag_off(frag), - skb_frag_size(frag), PAGE_SIZE); - page_pool_release_page(rxq->page_pool, skb_frag_page(frag)); + page, xdp_get_frag_offset(&frag_list[i]), + xdp_get_frag_size(&frag_list[i]), PAGE_SIZE); + page_pool_release_page(rxq->page_pool, page); } return skb; @@ -2357,7 +2363,7 @@ static int mvneta_rx_swbm(struct napi_struct *napi, { int rx_proc = 0, rx_todo, refill, size = 0; struct net_device *dev = pp->dev; - struct skb_shared_info sinfo; + struct xdp_shared_info xdp_sinfo; struct mvneta_stats ps = {}; struct bpf_prog *xdp_prog; u32 desc_status, frame_sz; @@ -2368,7 +2374,7 @@ static int mvneta_rx_swbm(struct napi_struct *napi, xdp_buf.rxq = &rxq->xdp_rxq; xdp_buf.mb = 0; - sinfo.nr_frags = 0; + xdp_sinfo.nr_frags = 0; /* Get number of received packets */ rx_todo = mvneta_rxq_busy_desc_num_get(pp, rxq); @@ -2412,7 +2418,7 @@ static int mvneta_rx_swbm(struct napi_struct *napi, } mvneta_swbm_add_rx_fragment(pp, rx_desc, rxq, &xdp_buf, - &size, &sinfo, page); + &size, &xdp_sinfo, page); } /* Middle or Last descriptor */ if (!(rx_status & MVNETA_RXD_LAST_DESC)) @@ -2420,7 +2426,7 @@ static int mvneta_rx_swbm(struct napi_struct *napi, continue; if (size) { - mvneta_xdp_put_buff(pp, rxq, &xdp_buf, &sinfo, -1); + mvneta_xdp_put_buff(pp, rxq, &xdp_buf, &xdp_sinfo, -1); goto next; } @@ -2432,7 +2438,7 @@ static int mvneta_rx_swbm(struct napi_struct *napi, if (IS_ERR(skb)) { struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats); - mvneta_xdp_put_buff(pp, rxq, &xdp_buf, &sinfo, -1); + mvneta_xdp_put_buff(pp, rxq, &xdp_buf, &xdp_sinfo, -1); u64_stats_update_begin(&stats->syncp); stats->es.skb_alloc_error++; @@ -2449,12 +2455,12 @@ static int mvneta_rx_swbm(struct napi_struct *napi, napi_gro_receive(napi, skb); next: xdp_buf.data_hard_start = NULL; - sinfo.nr_frags = 0; + xdp_sinfo.nr_frags = 0; } rcu_read_unlock(); if (xdp_buf.data_hard_start) - mvneta_xdp_put_buff(pp, rxq, &xdp_buf, &sinfo, -1); + mvneta_xdp_put_buff(pp, rxq, &xdp_buf, &xdp_sinfo, -1); if (ps.xdp_redirect) xdp_do_flush_map(); diff --git a/include/net/xdp.h b/include/net/xdp.h index 70559720ff44..614f66d35ee8 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -87,10 +87,54 @@ struct xdp_buff { ((xdp)->data_hard_start + (xdp)->frame_sz - \ SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) -static inline struct skb_shared_info * +struct xdp_shared_info { + u16 nr_frags; + u16 data_length; /* paged area length */ + skb_frag_t frags[MAX_SKB_FRAGS]; +}; + +static inline struct xdp_shared_info * xdp_get_shared_info_from_buff(struct xdp_buff *xdp) { - return (struct skb_shared_info *)xdp_data_hard_end(xdp); + BUILD_BUG_ON(sizeof(struct xdp_shared_info) > + sizeof(struct skb_shared_info)); + return (struct xdp_shared_info *)xdp_data_hard_end(xdp); +} + +static inline struct page *xdp_get_frag_page(const skb_frag_t *frag) +{ + return frag->bv_page; +} + +static inline unsigned int xdp_get_frag_offset(const skb_frag_t *frag) +{ + return frag->bv_offset; +} + +static inline unsigned int xdp_get_frag_size(const skb_frag_t *frag) +{ + return frag->bv_len; +} + +static inline void *xdp_get_frag_address(const skb_frag_t *frag) +{ + return page_address(xdp_get_frag_page(frag)) + + xdp_get_frag_offset(frag); +} + +static inline void xdp_set_frag_page(skb_frag_t *frag, struct page *page) +{ + frag->bv_page = page; +} + +static inline void xdp_set_frag_offset(skb_frag_t *frag, u32 offset) +{ + frag->bv_offset = offset; +} + +static inline void xdp_set_frag_size(skb_frag_t *frag, u32 size) +{ + frag->bv_len = size; } struct xdp_frame { @@ -120,12 +164,12 @@ static __always_inline void xdp_frame_bulk_init(struct xdp_frame_bulk *bq) bq->xa = NULL; } -static inline struct skb_shared_info * +static inline struct xdp_shared_info * xdp_get_shared_info_from_frame(struct xdp_frame *frame) { void *data_hard_start = frame->data - frame->headroom - sizeof(*frame); - return (struct skb_shared_info *)(data_hard_start + frame->frame_sz - + return (struct xdp_shared_info *)(data_hard_start + frame->frame_sz - SKB_DATA_ALIGN(sizeof(struct skb_shared_info))); } From patchwork Mon Dec 7 16:32:33 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "lorenzo@kernel.org" X-Patchwork-Id: 11956341 X-Patchwork-Delegate: bpf@iogearbox.net Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-17.0 required=3.0 tests=BAYES_00,INCLUDES_CR_TRAILER, INCLUDES_PATCH,MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS,USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id AAB74C2BBCD for ; Mon, 7 Dec 2020 16:33:52 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 8586C238E8 for ; Mon, 7 Dec 2020 16:33:52 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1727288AbgLGQdv (ORCPT ); Mon, 7 Dec 2020 11:33:51 -0500 Received: from mail.kernel.org ([198.145.29.99]:60740 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1726249AbgLGQdu (ORCPT ); Mon, 7 Dec 2020 11:33:50 -0500 From: Lorenzo Bianconi Authentication-Results: mail.kernel.org; dkim=permerror (bad message/signature format) To: bpf@vger.kernel.org, netdev@vger.kernel.org Cc: davem@davemloft.net, kuba@kernel.org, ast@kernel.org, daniel@iogearbox.net, shayagr@amazon.com, sameehj@amazon.com, john.fastabend@gmail.com, dsahern@kernel.org, brouer@redhat.com, echaudro@redhat.com, lorenzo.bianconi@redhat.com, jasowang@redhat.com Subject: [PATCH v5 bpf-next 04/14] net: mvneta: update mb bit before passing the xdp buffer to eBPF layer Date: Mon, 7 Dec 2020 17:32:33 +0100 Message-Id: <12c23f8c86236b2c12f6a15cbb1f4f8dccc2f0b5.1607349924.git.lorenzo@kernel.org> X-Mailer: git-send-email 2.28.0 In-Reply-To: References: MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: bpf@vger.kernel.org X-Patchwork-Delegate: bpf@iogearbox.net Update multi-buffer bit (mb) in xdp_buff to notify XDP/eBPF layer and XDP remote drivers if this is a "non-linear" XDP buffer. Access xdp_shared_info only if xdp_buff mb is set. Signed-off-by: Lorenzo Bianconi --- drivers/net/ethernet/marvell/mvneta.c | 24 ++++++++++++++++++------ 1 file changed, 18 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index d635463609ad..bac1ae7014eb 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -2038,12 +2038,16 @@ mvneta_xdp_put_buff(struct mvneta_port *pp, struct mvneta_rx_queue *rxq, { int i; + if (likely(!xdp->mb)) + goto out; + for (i = 0; i < xdp_sinfo->nr_frags; i++) { skb_frag_t *frag = &xdp_sinfo->frags[i]; page_pool_put_full_page(rxq->page_pool, xdp_get_frag_page(frag), true); } +out: page_pool_put_page(rxq->page_pool, virt_to_head_page(xdp->data), sync_len, true); } @@ -2244,7 +2248,6 @@ mvneta_swbm_rx_frame(struct mvneta_port *pp, { unsigned char *data = page_address(page); int data_len = -MVNETA_MH_SIZE, len; - struct xdp_shared_info *xdp_sinfo; struct net_device *dev = pp->dev; enum dma_data_direction dma_dir; @@ -2271,9 +2274,6 @@ mvneta_swbm_rx_frame(struct mvneta_port *pp, xdp->data = data + pp->rx_offset_correction + MVNETA_MH_SIZE; xdp->data_end = xdp->data + data_len; xdp_set_data_meta_invalid(xdp); - - xdp_sinfo = xdp_get_shared_info_from_buff(xdp); - xdp_sinfo->nr_frags = 0; } static void @@ -2308,12 +2308,18 @@ mvneta_swbm_add_rx_fragment(struct mvneta_port *pp, xdp_set_frag_size(frag, data_len); xdp_set_frag_page(frag, page); + if (!xdp->mb) { + xdp_sinfo->data_length = *size; + xdp->mb = 1; + } /* last fragment */ if (len == *size) { struct xdp_shared_info *sinfo; sinfo = xdp_get_shared_info_from_buff(xdp); sinfo->nr_frags = xdp_sinfo->nr_frags; + sinfo->data_length = xdp_sinfo->data_length; + memcpy(sinfo->frags, xdp_sinfo->frags, sinfo->nr_frags * sizeof(skb_frag_t)); } @@ -2328,11 +2334,13 @@ mvneta_swbm_build_skb(struct mvneta_port *pp, struct mvneta_rx_queue *rxq, struct xdp_buff *xdp, u32 desc_status) { struct xdp_shared_info *xdp_sinfo = xdp_get_shared_info_from_buff(xdp); - int i, num_frags = xdp_sinfo->nr_frags; + int i, num_frags = xdp->mb ? xdp_sinfo->nr_frags : 0; skb_frag_t frag_list[MAX_SKB_FRAGS]; struct sk_buff *skb; - memcpy(frag_list, xdp_sinfo->frags, sizeof(skb_frag_t) * num_frags); + if (unlikely(xdp->mb)) + memcpy(frag_list, xdp_sinfo->frags, + sizeof(skb_frag_t) * num_frags); skb = build_skb(xdp->data_hard_start, PAGE_SIZE); if (!skb) @@ -2344,6 +2352,9 @@ mvneta_swbm_build_skb(struct mvneta_port *pp, struct mvneta_rx_queue *rxq, skb_put(skb, xdp->data_end - xdp->data); mvneta_rx_csum(pp, desc_status, skb); + if (likely(!xdp->mb)) + return skb; + for (i = 0; i < num_frags; i++) { struct page *page = xdp_get_frag_page(&frag_list[i]); @@ -2407,6 +2418,7 @@ static int mvneta_rx_swbm(struct napi_struct *napi, frame_sz = size - ETH_FCS_LEN; desc_status = rx_status; + xdp_buf.mb = 0; mvneta_swbm_rx_frame(pp, rx_desc, rxq, &xdp_buf, &size, page); } else { From patchwork Mon Dec 7 16:32:34 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "lorenzo@kernel.org" X-Patchwork-Id: 11956347 X-Patchwork-Delegate: bpf@iogearbox.net Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-17.0 required=3.0 tests=BAYES_00,INCLUDES_CR_TRAILER, INCLUDES_PATCH,MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS,USER_AGENT_GIT autolearn=unavailable autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id AE7A5C47435 for ; Mon, 7 Dec 2020 16:34:30 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 88D99238EA for ; Mon, 7 Dec 2020 16:34:30 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1727444AbgLGQeQ (ORCPT ); Mon, 7 Dec 2020 11:34:16 -0500 Received: from mail.kernel.org ([198.145.29.99]:32810 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1726718AbgLGQeQ (ORCPT ); Mon, 7 Dec 2020 11:34:16 -0500 From: Lorenzo Bianconi Authentication-Results: mail.kernel.org; dkim=permerror (bad message/signature format) To: bpf@vger.kernel.org, netdev@vger.kernel.org Cc: davem@davemloft.net, kuba@kernel.org, ast@kernel.org, daniel@iogearbox.net, shayagr@amazon.com, sameehj@amazon.com, john.fastabend@gmail.com, dsahern@kernel.org, brouer@redhat.com, echaudro@redhat.com, lorenzo.bianconi@redhat.com, jasowang@redhat.com Subject: [PATCH v5 bpf-next 05/14] xdp: add multi-buff support to xdp_return_{buff/frame} Date: Mon, 7 Dec 2020 17:32:34 +0100 Message-Id: <662d5db543dba3b933ed604c5cf7944d0df65c38.1607349924.git.lorenzo@kernel.org> X-Mailer: git-send-email 2.28.0 In-Reply-To: References: MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: bpf@vger.kernel.org X-Patchwork-Delegate: bpf@iogearbox.net Take into account if the received xdp_buff/xdp_frame is non-linear recycling/returning the frame memory to the allocator or into xdp_frame_bulk. Introduce xdp_return_num_frags_from_buff to return a given number of fragments from a xdp multi-buff starting from the tail. Signed-off-by: Lorenzo Bianconi --- include/net/xdp.h | 19 ++++++++++-- net/core/xdp.c | 76 ++++++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 92 insertions(+), 3 deletions(-) diff --git a/include/net/xdp.h b/include/net/xdp.h index 614f66d35ee8..d0e90d729023 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -258,6 +258,7 @@ void xdp_return_buff(struct xdp_buff *xdp); void xdp_flush_frame_bulk(struct xdp_frame_bulk *bq); void xdp_return_frame_bulk(struct xdp_frame *xdpf, struct xdp_frame_bulk *bq); +void xdp_return_num_frags_from_buff(struct xdp_buff *xdp, u16 num_frags); /* When sending xdp_frame into the network stack, then there is no * return point callback, which is needed to release e.g. DMA-mapping @@ -268,10 +269,24 @@ void __xdp_release_frame(void *data, struct xdp_mem_info *mem); static inline void xdp_release_frame(struct xdp_frame *xdpf) { struct xdp_mem_info *mem = &xdpf->mem; + struct xdp_shared_info *xdp_sinfo; + int i; /* Curr only page_pool needs this */ - if (mem->type == MEM_TYPE_PAGE_POOL) - __xdp_release_frame(xdpf->data, mem); + if (mem->type != MEM_TYPE_PAGE_POOL) + return; + + if (likely(!xdpf->mb)) + goto out; + + xdp_sinfo = xdp_get_shared_info_from_frame(xdpf); + for (i = 0; i < xdp_sinfo->nr_frags; i++) { + struct page *page = xdp_get_frag_page(&xdp_sinfo->frags[i]); + + __xdp_release_frame(page_address(page), mem); + } +out: + __xdp_release_frame(xdpf->data, mem); } int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, diff --git a/net/core/xdp.c b/net/core/xdp.c index 79dd45234e4d..6c8e743ad03a 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -371,12 +371,38 @@ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct) void xdp_return_frame(struct xdp_frame *xdpf) { + struct xdp_shared_info *xdp_sinfo; + int i; + + if (likely(!xdpf->mb)) + goto out; + + xdp_sinfo = xdp_get_shared_info_from_frame(xdpf); + for (i = 0; i < xdp_sinfo->nr_frags; i++) { + struct page *page = xdp_get_frag_page(&xdp_sinfo->frags[i]); + + __xdp_return(page_address(page), &xdpf->mem, false); + } +out: __xdp_return(xdpf->data, &xdpf->mem, false); } EXPORT_SYMBOL_GPL(xdp_return_frame); void xdp_return_frame_rx_napi(struct xdp_frame *xdpf) { + struct xdp_shared_info *xdp_sinfo; + int i; + + if (likely(!xdpf->mb)) + goto out; + + xdp_sinfo = xdp_get_shared_info_from_frame(xdpf); + for (i = 0; i < xdp_sinfo->nr_frags; i++) { + struct page *page = xdp_get_frag_page(&xdp_sinfo->frags[i]); + + __xdp_return(page_address(page), &xdpf->mem, true); + } +out: __xdp_return(xdpf->data, &xdpf->mem, true); } EXPORT_SYMBOL_GPL(xdp_return_frame_rx_napi); @@ -412,7 +438,7 @@ void xdp_return_frame_bulk(struct xdp_frame *xdpf, struct xdp_mem_allocator *xa; if (mem->type != MEM_TYPE_PAGE_POOL) { - __xdp_return(xdpf->data, &xdpf->mem, false); + xdp_return_frame(xdpf); return; } @@ -431,15 +457,63 @@ void xdp_return_frame_bulk(struct xdp_frame *xdpf, bq->xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params); } + if (unlikely(xdpf->mb)) { + struct xdp_shared_info *xdp_sinfo; + int i; + + xdp_sinfo = xdp_get_shared_info_from_frame(xdpf); + for (i = 0; i < xdp_sinfo->nr_frags; i++) { + skb_frag_t *frag = &xdp_sinfo->frags[i]; + + bq->q[bq->count++] = xdp_get_frag_address(frag); + if (bq->count == XDP_BULK_QUEUE_SIZE) + xdp_flush_frame_bulk(bq); + } + } bq->q[bq->count++] = xdpf->data; } EXPORT_SYMBOL_GPL(xdp_return_frame_bulk); void xdp_return_buff(struct xdp_buff *xdp) { + struct xdp_shared_info *xdp_sinfo; + int i; + + if (likely(!xdp->mb)) + goto out; + + xdp_sinfo = xdp_get_shared_info_from_buff(xdp); + for (i = 0; i < xdp_sinfo->nr_frags; i++) { + struct page *page = xdp_get_frag_page(&xdp_sinfo->frags[i]); + + __xdp_return(page_address(page), &xdp->rxq->mem, true); + } +out: __xdp_return(xdp->data, &xdp->rxq->mem, true); } +void xdp_return_num_frags_from_buff(struct xdp_buff *xdp, u16 num_frags) +{ + struct xdp_shared_info *xdp_sinfo; + int i; + + if (unlikely(!xdp->mb)) + return; + + xdp_sinfo = xdp_get_shared_info_from_buff(xdp); + num_frags = min_t(u16, num_frags, xdp_sinfo->nr_frags); + for (i = 1; i <= num_frags; i++) { + skb_frag_t *frag = &xdp_sinfo->frags[xdp_sinfo->nr_frags - i]; + struct page *page = xdp_get_frag_page(frag); + + xdp_sinfo->data_length -= xdp_get_frag_size(frag); + __xdp_return(page_address(page), &xdp->rxq->mem, false); + } + xdp_sinfo->nr_frags -= num_frags; + xdp->mb = !!xdp_sinfo->nr_frags; +} +EXPORT_SYMBOL_GPL(xdp_return_num_frags_from_buff); + /* Only called for MEM_TYPE_PAGE_POOL see xdp.h */ void __xdp_release_frame(void *data, struct xdp_mem_info *mem) { From patchwork Mon Dec 7 16:32:35 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "lorenzo@kernel.org" X-Patchwork-Id: 11956343 X-Patchwork-Delegate: bpf@iogearbox.net Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-14.2 required=3.0 tests=BAYES_00,INCLUDES_CR_TRAILER, INCLUDES_PATCH,MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS, UNWANTED_LANGUAGE_BODY,USER_AGENT_GIT autolearn=unavailable autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 62D2BC433FE for ; Mon, 7 Dec 2020 16:34:30 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 37EAD238EA for ; Mon, 7 Dec 2020 16:34:30 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1727434AbgLGQeQ (ORCPT ); Mon, 7 Dec 2020 11:34:16 -0500 Received: from mail.kernel.org ([198.145.29.99]:32812 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1727132AbgLGQeQ (ORCPT ); Mon, 7 Dec 2020 11:34:16 -0500 From: Lorenzo Bianconi Authentication-Results: mail.kernel.org; dkim=permerror (bad message/signature format) To: bpf@vger.kernel.org, netdev@vger.kernel.org Cc: davem@davemloft.net, kuba@kernel.org, ast@kernel.org, daniel@iogearbox.net, shayagr@amazon.com, sameehj@amazon.com, john.fastabend@gmail.com, dsahern@kernel.org, brouer@redhat.com, echaudro@redhat.com, lorenzo.bianconi@redhat.com, jasowang@redhat.com Subject: [PATCH v5 bpf-next 06/14] net: mvneta: add multi buffer support to XDP_TX Date: Mon, 7 Dec 2020 17:32:35 +0100 Message-Id: X-Mailer: git-send-email 2.28.0 In-Reply-To: References: MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: bpf@vger.kernel.org X-Patchwork-Delegate: bpf@iogearbox.net Introduce the capability to map non-linear xdp buffer running mvneta_xdp_submit_frame() for XDP_TX and XDP_REDIRECT Signed-off-by: Lorenzo Bianconi --- drivers/net/ethernet/marvell/mvneta.c | 94 ++++++++++++++++----------- 1 file changed, 56 insertions(+), 38 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index bac1ae7014eb..dc1f1f25fce0 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -1857,8 +1857,8 @@ static void mvneta_txq_bufs_free(struct mvneta_port *pp, bytes_compl += buf->skb->len; pkts_compl++; dev_kfree_skb_any(buf->skb); - } else if (buf->type == MVNETA_TYPE_XDP_TX || - buf->type == MVNETA_TYPE_XDP_NDO) { + } else if ((buf->type == MVNETA_TYPE_XDP_TX || + buf->type == MVNETA_TYPE_XDP_NDO) && buf->xdpf) { if (napi && buf->type == MVNETA_TYPE_XDP_TX) xdp_return_frame_rx_napi(buf->xdpf); else @@ -2054,45 +2054,64 @@ mvneta_xdp_put_buff(struct mvneta_port *pp, struct mvneta_rx_queue *rxq, static int mvneta_xdp_submit_frame(struct mvneta_port *pp, struct mvneta_tx_queue *txq, - struct xdp_frame *xdpf, bool dma_map) + struct xdp_frame *xdpf, int *nxmit_byte, bool dma_map) { - struct mvneta_tx_desc *tx_desc; - struct mvneta_tx_buf *buf; - dma_addr_t dma_addr; + struct xdp_shared_info *xdp_sinfo = xdp_get_shared_info_from_frame(xdpf); + int i, num_frames = xdpf->mb ? xdp_sinfo->nr_frags + 1 : 1; + struct mvneta_tx_desc *tx_desc = NULL; + struct page *page; - if (txq->count >= txq->tx_stop_threshold) + if (txq->count + num_frames >= txq->size) return MVNETA_XDP_DROPPED; - tx_desc = mvneta_txq_next_desc_get(txq); + for (i = 0; i < num_frames; i++) { + struct mvneta_tx_buf *buf = &txq->buf[txq->txq_put_index]; + skb_frag_t *frag = i ? &xdp_sinfo->frags[i - 1] : NULL; + int len = frag ? xdp_get_frag_size(frag) : xdpf->len; + dma_addr_t dma_addr; - buf = &txq->buf[txq->txq_put_index]; - if (dma_map) { - /* ndo_xdp_xmit */ - dma_addr = dma_map_single(pp->dev->dev.parent, xdpf->data, - xdpf->len, DMA_TO_DEVICE); - if (dma_mapping_error(pp->dev->dev.parent, dma_addr)) { - mvneta_txq_desc_put(txq); - return MVNETA_XDP_DROPPED; + tx_desc = mvneta_txq_next_desc_get(txq); + if (dma_map) { + /* ndo_xdp_xmit */ + void *data; + + data = frag ? xdp_get_frag_address(frag) : xdpf->data; + dma_addr = dma_map_single(pp->dev->dev.parent, data, + len, DMA_TO_DEVICE); + if (dma_mapping_error(pp->dev->dev.parent, dma_addr)) { + for (; i >= 0; i--) + mvneta_txq_desc_put(txq); + return MVNETA_XDP_DROPPED; + } + buf->type = MVNETA_TYPE_XDP_NDO; + } else { + page = frag ? xdp_get_frag_page(frag) + : virt_to_page(xdpf->data); + dma_addr = page_pool_get_dma_addr(page); + if (frag) + dma_addr += xdp_get_frag_offset(frag); + else + dma_addr += sizeof(*xdpf) + xdpf->headroom; + dma_sync_single_for_device(pp->dev->dev.parent, + dma_addr, len, + DMA_BIDIRECTIONAL); + buf->type = MVNETA_TYPE_XDP_TX; } - buf->type = MVNETA_TYPE_XDP_NDO; - } else { - struct page *page = virt_to_page(xdpf->data); + buf->xdpf = i ? NULL : xdpf; + + tx_desc->command = !i ? MVNETA_TXD_F_DESC : 0; + tx_desc->buf_phys_addr = dma_addr; + tx_desc->data_size = len; + *nxmit_byte += len; - dma_addr = page_pool_get_dma_addr(page) + - sizeof(*xdpf) + xdpf->headroom; - dma_sync_single_for_device(pp->dev->dev.parent, dma_addr, - xdpf->len, DMA_BIDIRECTIONAL); - buf->type = MVNETA_TYPE_XDP_TX; + mvneta_txq_inc_put(txq); } - buf->xdpf = xdpf; - tx_desc->command = MVNETA_TXD_FLZ_DESC; - tx_desc->buf_phys_addr = dma_addr; - tx_desc->data_size = xdpf->len; + /*last descriptor */ + tx_desc->command |= MVNETA_TXD_L_DESC | MVNETA_TXD_Z_PAD; - mvneta_txq_inc_put(txq); - txq->pending++; - txq->count++; + txq->pending += num_frames; + txq->count += num_frames; return MVNETA_XDP_TX; } @@ -2103,8 +2122,8 @@ mvneta_xdp_xmit_back(struct mvneta_port *pp, struct xdp_buff *xdp) struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats); struct mvneta_tx_queue *txq; struct netdev_queue *nq; + int cpu, nxmit_byte = 0; struct xdp_frame *xdpf; - int cpu; u32 ret; xdpf = xdp_convert_buff_to_frame(xdp); @@ -2116,10 +2135,10 @@ mvneta_xdp_xmit_back(struct mvneta_port *pp, struct xdp_buff *xdp) nq = netdev_get_tx_queue(pp->dev, txq->id); __netif_tx_lock(nq, cpu); - ret = mvneta_xdp_submit_frame(pp, txq, xdpf, false); + ret = mvneta_xdp_submit_frame(pp, txq, xdpf, &nxmit_byte, false); if (ret == MVNETA_XDP_TX) { u64_stats_update_begin(&stats->syncp); - stats->es.ps.tx_bytes += xdpf->len; + stats->es.ps.tx_bytes += nxmit_byte; stats->es.ps.tx_packets++; stats->es.ps.xdp_tx++; u64_stats_update_end(&stats->syncp); @@ -2158,10 +2177,9 @@ mvneta_xdp_xmit(struct net_device *dev, int num_frame, __netif_tx_lock(nq, cpu); for (i = 0; i < num_frame; i++) { - ret = mvneta_xdp_submit_frame(pp, txq, frames[i], true); - if (ret == MVNETA_XDP_TX) { - nxmit_byte += frames[i]->len; - } else { + ret = mvneta_xdp_submit_frame(pp, txq, frames[i], &nxmit_byte, + true); + if (ret != MVNETA_XDP_TX) { xdp_return_frame_rx_napi(frames[i]); nxmit--; } From patchwork Mon Dec 7 16:32:36 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "lorenzo@kernel.org" X-Patchwork-Id: 11956351 X-Patchwork-Delegate: bpf@iogearbox.net Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-17.0 required=3.0 tests=BAYES_00,INCLUDES_CR_TRAILER, INCLUDES_PATCH,MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS,USER_AGENT_GIT autolearn=unavailable autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 0BEDEC47434 for ; Mon, 7 Dec 2020 16:34:31 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id E5E9C238EA for ; Mon, 7 Dec 2020 16:34:30 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1727495AbgLGQeV (ORCPT ); Mon, 7 Dec 2020 11:34:21 -0500 Received: from mail.kernel.org ([198.145.29.99]:32886 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1726718AbgLGQeU (ORCPT ); Mon, 7 Dec 2020 11:34:20 -0500 From: Lorenzo Bianconi Authentication-Results: mail.kernel.org; dkim=permerror (bad message/signature format) To: bpf@vger.kernel.org, netdev@vger.kernel.org Cc: davem@davemloft.net, kuba@kernel.org, ast@kernel.org, daniel@iogearbox.net, shayagr@amazon.com, sameehj@amazon.com, john.fastabend@gmail.com, dsahern@kernel.org, brouer@redhat.com, echaudro@redhat.com, lorenzo.bianconi@redhat.com, jasowang@redhat.com Subject: [PATCH v5 bpf-next 07/14] bpf: move user_size out of bpf_test_init Date: Mon, 7 Dec 2020 17:32:36 +0100 Message-Id: <6f92d87e554a92db2cddb444004d5f9b102011ff.1607349924.git.lorenzo@kernel.org> X-Mailer: git-send-email 2.28.0 In-Reply-To: References: MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: bpf@vger.kernel.org X-Patchwork-Delegate: bpf@iogearbox.net Rely on data_size_in in bpf_test_init routine signature. This is a preliminary patch to introduce xdp multi-buff selftest Signed-off-by: Lorenzo Bianconi --- net/bpf/test_run.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index c1c30a9f76f3..bd291f5f539c 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -171,11 +171,10 @@ __diag_pop(); ALLOW_ERROR_INJECTION(bpf_modify_return_test, ERRNO); -static void *bpf_test_init(const union bpf_attr *kattr, u32 size, - u32 headroom, u32 tailroom) +static void *bpf_test_init(const union bpf_attr *kattr, u32 user_size, + u32 size, u32 headroom, u32 tailroom) { void __user *data_in = u64_to_user_ptr(kattr->test.data_in); - u32 user_size = kattr->test.data_size_in; void *data; if (size < ETH_HLEN || size > PAGE_SIZE - headroom - tailroom) @@ -495,7 +494,8 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, if (kattr->test.flags || kattr->test.cpu) return -EINVAL; - data = bpf_test_init(kattr, size, NET_SKB_PAD + NET_IP_ALIGN, + data = bpf_test_init(kattr, kattr->test.data_size_in, + size, NET_SKB_PAD + NET_IP_ALIGN, SKB_DATA_ALIGN(sizeof(struct skb_shared_info))); if (IS_ERR(data)) return PTR_ERR(data); @@ -632,7 +632,8 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, /* XDP have extra tailroom as (most) drivers use full page */ max_data_sz = 4096 - headroom - tailroom; - data = bpf_test_init(kattr, max_data_sz, headroom, tailroom); + data = bpf_test_init(kattr, kattr->test.data_size_in, + max_data_sz, headroom, tailroom); if (IS_ERR(data)) return PTR_ERR(data); @@ -698,7 +699,7 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, if (size < ETH_HLEN) return -EINVAL; - data = bpf_test_init(kattr, size, 0, 0); + data = bpf_test_init(kattr, kattr->test.data_size_in, size, 0, 0); if (IS_ERR(data)) return PTR_ERR(data); From patchwork Mon Dec 7 16:32:37 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "lorenzo@kernel.org" X-Patchwork-Id: 11956345 X-Patchwork-Delegate: bpf@iogearbox.net Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-17.0 required=3.0 tests=BAYES_00,INCLUDES_CR_TRAILER, INCLUDES_PATCH,MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS,USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id BAFB5C1B0D9 for ; Mon, 7 Dec 2020 16:34:30 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id A2B8F238E7 for ; Mon, 7 Dec 2020 16:34:30 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1727472AbgLGQeU (ORCPT ); Mon, 7 Dec 2020 11:34:20 -0500 Received: from mail.kernel.org ([198.145.29.99]:32888 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1726840AbgLGQeU (ORCPT ); Mon, 7 Dec 2020 11:34:20 -0500 From: Lorenzo Bianconi Authentication-Results: mail.kernel.org; dkim=permerror (bad message/signature format) To: bpf@vger.kernel.org, netdev@vger.kernel.org Cc: davem@davemloft.net, kuba@kernel.org, ast@kernel.org, daniel@iogearbox.net, shayagr@amazon.com, sameehj@amazon.com, john.fastabend@gmail.com, dsahern@kernel.org, brouer@redhat.com, echaudro@redhat.com, lorenzo.bianconi@redhat.com, jasowang@redhat.com Subject: [PATCH v5 bpf-next 08/14] bpf: introduce multibuff support to bpf_prog_test_run_xdp() Date: Mon, 7 Dec 2020 17:32:37 +0100 Message-Id: <309f21434ee15dbe66dc129bdcb947b203de4378.1607349924.git.lorenzo@kernel.org> X-Mailer: git-send-email 2.28.0 In-Reply-To: References: MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: bpf@vger.kernel.org X-Patchwork-Delegate: bpf@iogearbox.net Introduce the capability to allocate a xdp multi-buff in bpf_prog_test_run_xdp routine. This is a preliminary patch to introduce the selftests for new xdp multi-buff ebpf helpers Signed-off-by: Lorenzo Bianconi --- net/bpf/test_run.c | 52 +++++++++++++++++++++++++++++++++++++++------- 1 file changed, 44 insertions(+), 8 deletions(-) diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index bd291f5f539c..e4b7b749184d 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -617,23 +617,22 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, { u32 tailroom = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); u32 headroom = XDP_PACKET_HEADROOM; - u32 size = kattr->test.data_size_in; + struct xdp_shared_info *xdp_sinfo; u32 repeat = kattr->test.repeat; struct netdev_rx_queue *rxqueue; struct xdp_buff xdp = {}; + u32 max_data_sz, size; u32 retval, duration; - u32 max_data_sz; + int i, ret; void *data; - int ret; if (kattr->test.ctx_in || kattr->test.ctx_out) return -EINVAL; - /* XDP have extra tailroom as (most) drivers use full page */ max_data_sz = 4096 - headroom - tailroom; + size = min_t(u32, kattr->test.data_size_in, max_data_sz); - data = bpf_test_init(kattr, kattr->test.data_size_in, - max_data_sz, headroom, tailroom); + data = bpf_test_init(kattr, size, max_data_sz, headroom, tailroom); if (IS_ERR(data)) return PTR_ERR(data); @@ -643,18 +642,55 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, xdp.data_end = xdp.data + size; xdp.frame_sz = headroom + max_data_sz + tailroom; + xdp_sinfo = xdp_get_shared_info_from_buff(&xdp); + if (unlikely(kattr->test.data_size_in > size)) { + void __user *data_in = u64_to_user_ptr(kattr->test.data_in); + + while (size < kattr->test.data_size_in) { + struct page *page; + skb_frag_t *frag; + int data_len; + + page = alloc_page(GFP_KERNEL); + if (!page) { + ret = -ENOMEM; + goto out; + } + + frag = &xdp_sinfo->frags[xdp_sinfo->nr_frags++]; + xdp_set_frag_page(frag, page); + + data_len = min_t(int, kattr->test.data_size_in - size, + PAGE_SIZE); + xdp_set_frag_size(frag, data_len); + + if (copy_from_user(page_address(page), data_in + size, + data_len)) { + ret = -EFAULT; + goto out; + } + xdp_sinfo->data_length += data_len; + size += data_len; + } + xdp.mb = 1; + } + rxqueue = __netif_get_rx_queue(current->nsproxy->net_ns->loopback_dev, 0); xdp.rxq = &rxqueue->xdp_rxq; bpf_prog_change_xdp(NULL, prog); ret = bpf_test_run(prog, &xdp, repeat, &retval, &duration, true); if (ret) goto out; - if (xdp.data != data + headroom || xdp.data_end != xdp.data + size) - size = xdp.data_end - xdp.data; + + size = xdp.data_end - xdp.data + xdp_sinfo->data_length; ret = bpf_test_finish(kattr, uattr, xdp.data, size, retval, duration); + out: bpf_prog_change_xdp(prog, NULL); + for (i = 0; i < xdp_sinfo->nr_frags; i++) + __free_page(xdp_get_frag_page(&xdp_sinfo->frags[i])); kfree(data); + return ret; } From patchwork Mon Dec 7 16:32:38 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "lorenzo@kernel.org" X-Patchwork-Id: 11956353 X-Patchwork-Delegate: bpf@iogearbox.net Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-17.0 required=3.0 tests=BAYES_00,INCLUDES_CR_TRAILER, INCLUDES_PATCH,MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS,USER_AGENT_GIT autolearn=unavailable autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 774A0C2BBCA for ; Mon, 7 Dec 2020 16:34:31 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 50B01238E7 for ; Mon, 7 Dec 2020 16:34:31 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1726718AbgLGQe0 (ORCPT ); Mon, 7 Dec 2020 11:34:26 -0500 Received: from mail.kernel.org ([198.145.29.99]:33016 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1727017AbgLGQeZ (ORCPT ); Mon, 7 Dec 2020 11:34:25 -0500 From: Lorenzo Bianconi Authentication-Results: mail.kernel.org; dkim=permerror (bad message/signature format) To: bpf@vger.kernel.org, netdev@vger.kernel.org Cc: davem@davemloft.net, kuba@kernel.org, ast@kernel.org, daniel@iogearbox.net, shayagr@amazon.com, sameehj@amazon.com, john.fastabend@gmail.com, dsahern@kernel.org, brouer@redhat.com, echaudro@redhat.com, lorenzo.bianconi@redhat.com, jasowang@redhat.com Subject: [PATCH v5 bpf-next 09/14] bpf: test_run: add xdp_shared_info pointer in bpf_test_finish signature Date: Mon, 7 Dec 2020 17:32:38 +0100 Message-Id: X-Mailer: git-send-email 2.28.0 In-Reply-To: References: MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: bpf@vger.kernel.org X-Patchwork-Delegate: bpf@iogearbox.net introduce xdp_shared_info pointer in bpf_test_finish signature in order to copy back paged data from a xdp multi-buff frame to userspace buffer Signed-off-by: Lorenzo Bianconi --- net/bpf/test_run.c | 46 +++++++++++++++++++++++++++++++++++++++------- 1 file changed, 39 insertions(+), 7 deletions(-) diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index e4b7b749184d..32cda04ac7fb 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -81,7 +81,8 @@ static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, static int bpf_test_finish(const union bpf_attr *kattr, union bpf_attr __user *uattr, const void *data, - u32 size, u32 retval, u32 duration) + struct xdp_shared_info *xdp_sinfo, u32 size, + u32 retval, u32 duration) { void __user *data_out = u64_to_user_ptr(kattr->test.data_out); int err = -EFAULT; @@ -96,8 +97,37 @@ static int bpf_test_finish(const union bpf_attr *kattr, err = -ENOSPC; } - if (data_out && copy_to_user(data_out, data, copy_size)) - goto out; + if (data_out) { + int len = xdp_sinfo ? copy_size - xdp_sinfo->data_length + : copy_size; + + if (copy_to_user(data_out, data, len)) + goto out; + + if (xdp_sinfo) { + int i, offset = len, data_len; + + for (i = 0; i < xdp_sinfo->nr_frags; i++) { + skb_frag_t *frag = &xdp_sinfo->frags[i]; + + if (offset >= copy_size) { + err = -ENOSPC; + break; + } + + data_len = min_t(int, copy_size - offset, + xdp_get_frag_size(frag)); + + if (copy_to_user(data_out + offset, + xdp_get_frag_address(frag), + data_len)) + goto out; + + offset += data_len; + } + } + } + if (copy_to_user(&uattr->test.data_size_out, &size, sizeof(size))) goto out; if (copy_to_user(&uattr->test.retval, &retval, sizeof(retval))) @@ -598,7 +628,8 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, /* bpf program can never convert linear skb to non-linear */ if (WARN_ON_ONCE(skb_is_nonlinear(skb))) size = skb_headlen(skb); - ret = bpf_test_finish(kattr, uattr, skb->data, size, retval, duration); + ret = bpf_test_finish(kattr, uattr, skb->data, NULL, size, retval, + duration); if (!ret) ret = bpf_ctx_finish(kattr, uattr, ctx, sizeof(struct __sk_buff)); @@ -683,7 +714,8 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, goto out; size = xdp.data_end - xdp.data + xdp_sinfo->data_length; - ret = bpf_test_finish(kattr, uattr, xdp.data, size, retval, duration); + ret = bpf_test_finish(kattr, uattr, xdp.data, xdp_sinfo, size, retval, + duration); out: bpf_prog_change_xdp(prog, NULL); @@ -794,8 +826,8 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, do_div(time_spent, repeat); duration = time_spent > U32_MAX ? U32_MAX : (u32)time_spent; - ret = bpf_test_finish(kattr, uattr, &flow_keys, sizeof(flow_keys), - retval, duration); + ret = bpf_test_finish(kattr, uattr, &flow_keys, NULL, + sizeof(flow_keys), retval, duration); if (!ret) ret = bpf_ctx_finish(kattr, uattr, user_ctx, sizeof(struct bpf_flow_keys)); From patchwork Mon Dec 7 16:32:39 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "lorenzo@kernel.org" X-Patchwork-Id: 11956349 X-Patchwork-Delegate: bpf@iogearbox.net Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-17.0 required=3.0 tests=BAYES_00,INCLUDES_CR_TRAILER, INCLUDES_PATCH,MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS,USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 3513AC1B0E3 for ; Mon, 7 Dec 2020 16:34:31 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 09E6F238E7 for ; Mon, 7 Dec 2020 16:34:31 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1727518AbgLGQeZ (ORCPT ); Mon, 7 Dec 2020 11:34:25 -0500 Received: from mail.kernel.org ([198.145.29.99]:33018 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1726718AbgLGQeZ (ORCPT ); Mon, 7 Dec 2020 11:34:25 -0500 From: Lorenzo Bianconi Authentication-Results: mail.kernel.org; dkim=permerror (bad message/signature format) To: bpf@vger.kernel.org, netdev@vger.kernel.org Cc: davem@davemloft.net, kuba@kernel.org, ast@kernel.org, daniel@iogearbox.net, shayagr@amazon.com, sameehj@amazon.com, john.fastabend@gmail.com, dsahern@kernel.org, brouer@redhat.com, echaudro@redhat.com, lorenzo.bianconi@redhat.com, jasowang@redhat.com Subject: [PATCH v5 bpf-next 10/14] net: mvneta: enable jumbo frames for XDP Date: Mon, 7 Dec 2020 17:32:39 +0100 Message-Id: <1005050acd8d9990e84a397da8d7b4e85524a5ec.1607349924.git.lorenzo@kernel.org> X-Mailer: git-send-email 2.28.0 In-Reply-To: References: MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: bpf@vger.kernel.org X-Patchwork-Delegate: bpf@iogearbox.net Enable the capability to receive jumbo frames even if the interface is running in XDP mode Signed-off-by: Lorenzo Bianconi --- drivers/net/ethernet/marvell/mvneta.c | 10 ---------- 1 file changed, 10 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index dc1f1f25fce0..853bea9fcb14 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -3766,11 +3766,6 @@ static int mvneta_change_mtu(struct net_device *dev, int mtu) mtu = ALIGN(MVNETA_RX_PKT_SIZE(mtu), 8); } - if (pp->xdp_prog && mtu > MVNETA_MAX_RX_BUF_SIZE) { - netdev_info(dev, "Illegal MTU value %d for XDP mode\n", mtu); - return -EINVAL; - } - dev->mtu = mtu; if (!netif_running(dev)) { @@ -4468,11 +4463,6 @@ static int mvneta_xdp_setup(struct net_device *dev, struct bpf_prog *prog, struct mvneta_port *pp = netdev_priv(dev); struct bpf_prog *old_prog; - if (prog && dev->mtu > MVNETA_MAX_RX_BUF_SIZE) { - NL_SET_ERR_MSG_MOD(extack, "Jumbo frames not supported on XDP"); - return -EOPNOTSUPP; - } - if (pp->bm_priv) { NL_SET_ERR_MSG_MOD(extack, "Hardware Buffer Management not supported on XDP"); From patchwork Mon Dec 7 16:32:40 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "lorenzo@kernel.org" X-Patchwork-Id: 11956361 X-Patchwork-Delegate: bpf@iogearbox.net Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-17.0 required=3.0 tests=BAYES_00,INCLUDES_CR_TRAILER, INCLUDES_PATCH,MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS,USER_AGENT_GIT autolearn=unavailable autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id F40D7C3527A for ; Mon, 7 Dec 2020 16:35:55 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id E00D4238E8 for ; Mon, 7 Dec 2020 16:35:55 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1727620AbgLGQe2 (ORCPT ); Mon, 7 Dec 2020 11:34:28 -0500 Received: from mail.kernel.org ([198.145.29.99]:33134 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1727571AbgLGQe2 (ORCPT ); Mon, 7 Dec 2020 11:34:28 -0500 From: Lorenzo Bianconi Authentication-Results: mail.kernel.org; dkim=permerror (bad message/signature format) To: bpf@vger.kernel.org, netdev@vger.kernel.org Cc: davem@davemloft.net, kuba@kernel.org, ast@kernel.org, daniel@iogearbox.net, shayagr@amazon.com, sameehj@amazon.com, john.fastabend@gmail.com, dsahern@kernel.org, brouer@redhat.com, echaudro@redhat.com, lorenzo.bianconi@redhat.com, jasowang@redhat.com Subject: [PATCH v5 bpf-next 11/14] bpf: cpumap: introduce xdp multi-buff support Date: Mon, 7 Dec 2020 17:32:40 +0100 Message-Id: X-Mailer: git-send-email 2.28.0 In-Reply-To: References: MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: bpf@vger.kernel.org X-Patchwork-Delegate: bpf@iogearbox.net Introduce __xdp_build_skb_from_frame and xdp_build_skb_from_frame utility routines to build the skb from xdp_frame. Add xdp multi-buff support to cpumap Signed-off-by: Lorenzo Bianconi --- include/net/xdp.h | 5 ++++ kernel/bpf/cpumap.c | 45 +--------------------------- net/core/xdp.c | 73 +++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 79 insertions(+), 44 deletions(-) diff --git a/include/net/xdp.h b/include/net/xdp.h index d0e90d729023..76cfee6a40f7 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -191,6 +191,11 @@ void xdp_warn(const char *msg, const char *func, const int line); #define XDP_WARN(msg) xdp_warn(msg, __func__, __LINE__) struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp); +struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf, + struct sk_buff *skb, + struct net_device *dev); +struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf, + struct net_device *dev); static inline void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp) diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index 747313698178..49113880b82a 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -141,49 +141,6 @@ static void cpu_map_kthread_stop(struct work_struct *work) kthread_stop(rcpu->kthread); } -static struct sk_buff *cpu_map_build_skb(struct xdp_frame *xdpf, - struct sk_buff *skb) -{ - unsigned int hard_start_headroom; - unsigned int frame_size; - void *pkt_data_start; - - /* Part of headroom was reserved to xdpf */ - hard_start_headroom = sizeof(struct xdp_frame) + xdpf->headroom; - - /* Memory size backing xdp_frame data already have reserved - * room for build_skb to place skb_shared_info in tailroom. - */ - frame_size = xdpf->frame_sz; - - pkt_data_start = xdpf->data - hard_start_headroom; - skb = build_skb_around(skb, pkt_data_start, frame_size); - if (unlikely(!skb)) - return NULL; - - skb_reserve(skb, hard_start_headroom); - __skb_put(skb, xdpf->len); - if (xdpf->metasize) - skb_metadata_set(skb, xdpf->metasize); - - /* Essential SKB info: protocol and skb->dev */ - skb->protocol = eth_type_trans(skb, xdpf->dev_rx); - - /* Optional SKB info, currently missing: - * - HW checksum info (skb->ip_summed) - * - HW RX hash (skb_set_hash) - * - RX ring dev queue index (skb_record_rx_queue) - */ - - /* Until page_pool get SKB return path, release DMA here */ - xdp_release_frame(xdpf); - - /* Allow SKB to reuse area used by xdp_frame */ - xdp_scrub_frame(xdpf); - - return skb; -} - static void __cpu_map_ring_cleanup(struct ptr_ring *ring) { /* The tear-down procedure should have made sure that queue is @@ -350,7 +307,7 @@ static int cpu_map_kthread_run(void *data) struct sk_buff *skb = skbs[i]; int ret; - skb = cpu_map_build_skb(xdpf, skb); + skb = __xdp_build_skb_from_frame(xdpf, skb, xdpf->dev_rx); if (!skb) { xdp_return_frame(xdpf); continue; diff --git a/net/core/xdp.c b/net/core/xdp.c index 6c8e743ad03a..55f3e9c69427 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -597,3 +597,76 @@ void xdp_warn(const char *msg, const char *func, const int line) WARN(1, "XDP_WARN: %s(line:%d): %s\n", func, line, msg); }; EXPORT_SYMBOL_GPL(xdp_warn); + +struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf, + struct sk_buff *skb, + struct net_device *dev) +{ + unsigned int headroom = sizeof(*xdpf) + xdpf->headroom; + void *hard_start = xdpf->data - headroom; + skb_frag_t frag_list[MAX_SKB_FRAGS]; + struct xdp_shared_info *xdp_sinfo; + int i, num_frags = 0; + + xdp_sinfo = xdp_get_shared_info_from_frame(xdpf); + if (unlikely(xdpf->mb)) { + num_frags = xdp_sinfo->nr_frags; + memcpy(frag_list, xdp_sinfo->frags, + sizeof(skb_frag_t) * num_frags); + } + + skb = build_skb_around(skb, hard_start, xdpf->frame_sz); + if (unlikely(!skb)) + return NULL; + + skb_reserve(skb, headroom); + __skb_put(skb, xdpf->len); + if (xdpf->metasize) + skb_metadata_set(skb, xdpf->metasize); + + if (likely(!num_frags)) + goto out; + + for (i = 0; i < num_frags; i++) { + struct page *page = xdp_get_frag_page(&frag_list[i]); + + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, + page, xdp_get_frag_offset(&frag_list[i]), + xdp_get_frag_size(&frag_list[i]), + xdpf->frame_sz); + } + +out: + /* Essential SKB info: protocol and skb->dev */ + skb->protocol = eth_type_trans(skb, dev); + + /* Optional SKB info, currently missing: + * - HW checksum info (skb->ip_summed) + * - HW RX hash (skb_set_hash) + * - RX ring dev queue index (skb_record_rx_queue) + */ + + /* Until page_pool get SKB return path, release DMA here */ + xdp_release_frame(xdpf); + + /* Allow SKB to reuse area used by xdp_frame */ + xdp_scrub_frame(xdpf); + + return skb; +} +EXPORT_SYMBOL_GPL(__xdp_build_skb_from_frame); + +struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf, + struct net_device *dev) +{ + struct sk_buff *skb; + + skb = kmem_cache_alloc(skbuff_head_cache, GFP_ATOMIC); + if (unlikely(!skb)) + return NULL; + + memset(skb, 0, offsetof(struct sk_buff, tail)); + + return __xdp_build_skb_from_frame(xdpf, skb, dev); +} +EXPORT_SYMBOL_GPL(xdp_build_skb_from_frame); From patchwork Mon Dec 7 16:32:41 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "lorenzo@kernel.org" X-Patchwork-Id: 11956355 X-Patchwork-Delegate: bpf@iogearbox.net Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-17.0 required=3.0 tests=BAYES_00,INCLUDES_CR_TRAILER, INCLUDES_PATCH,MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS,USER_AGENT_GIT autolearn=unavailable autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 6398EC4361B for ; Mon, 7 Dec 2020 16:34:59 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 33CA7238E5 for ; Mon, 7 Dec 2020 16:34:59 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1727623AbgLGQe2 (ORCPT ); Mon, 7 Dec 2020 11:34:28 -0500 Received: from mail.kernel.org ([198.145.29.99]:33136 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1727017AbgLGQe1 (ORCPT ); Mon, 7 Dec 2020 11:34:27 -0500 From: Lorenzo Bianconi Authentication-Results: mail.kernel.org; dkim=permerror (bad message/signature format) To: bpf@vger.kernel.org, netdev@vger.kernel.org Cc: davem@davemloft.net, kuba@kernel.org, ast@kernel.org, daniel@iogearbox.net, shayagr@amazon.com, sameehj@amazon.com, john.fastabend@gmail.com, dsahern@kernel.org, brouer@redhat.com, echaudro@redhat.com, lorenzo.bianconi@redhat.com, jasowang@redhat.com Subject: [PATCH v5 bpf-next 12/14] bpf: add multi-buff support to the bpf_xdp_adjust_tail() API Date: Mon, 7 Dec 2020 17:32:41 +0100 Message-Id: <45d9ac7cd5895fa7af1ff54472257662ba25b877.1607349924.git.lorenzo@kernel.org> X-Mailer: git-send-email 2.28.0 In-Reply-To: References: MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: bpf@vger.kernel.org X-Patchwork-Delegate: bpf@iogearbox.net From: Eelco Chaudron This change adds support for tail growing and shrinking for XDP multi-buff. Signed-off-by: Eelco Chaudron Signed-off-by: Lorenzo Bianconi --- include/net/xdp.h | 5 ++++ net/core/filter.c | 63 +++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 68 insertions(+) diff --git a/include/net/xdp.h b/include/net/xdp.h index 76cfee6a40f7..09078ab6644c 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -137,6 +137,11 @@ static inline void xdp_set_frag_size(skb_frag_t *frag, u32 size) frag->bv_len = size; } +static inline unsigned int xdp_get_frag_tailroom(const skb_frag_t *frag) +{ + return PAGE_SIZE - xdp_get_frag_size(frag) - xdp_get_frag_offset(frag); +} + struct xdp_frame { void *data; u16 len; diff --git a/net/core/filter.c b/net/core/filter.c index 77001a35768f..4c4882d4d92c 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3860,11 +3860,74 @@ static const struct bpf_func_proto bpf_xdp_adjust_head_proto = { .arg2_type = ARG_ANYTHING, }; +static int bpf_xdp_mb_adjust_tail(struct xdp_buff *xdp, int offset) +{ + struct xdp_shared_info *xdp_sinfo = xdp_get_shared_info_from_buff(xdp); + + if (unlikely(xdp_sinfo->nr_frags == 0)) + return -EINVAL; + + if (offset >= 0) { + skb_frag_t *frag = &xdp_sinfo->frags[xdp_sinfo->nr_frags - 1]; + int size; + + if (unlikely(offset > xdp_get_frag_tailroom(frag))) + return -EINVAL; + + size = xdp_get_frag_size(frag); + memset(xdp_get_frag_address(frag) + size, 0, offset); + xdp_set_frag_size(frag, size + offset); + xdp_sinfo->data_length += offset; + } else { + int i, frags_to_free = 0; + + offset = abs(offset); + + if (unlikely(offset > ((int)(xdp->data_end - xdp->data) + + xdp_sinfo->data_length - + ETH_HLEN))) + return -EINVAL; + + for (i = xdp_sinfo->nr_frags - 1; i >= 0 && offset > 0; i--) { + skb_frag_t *frag = &xdp_sinfo->frags[i]; + int size = xdp_get_frag_size(frag); + int shrink = min_t(int, offset, size); + + offset -= shrink; + if (likely(size - shrink > 0)) { + /* When updating the final fragment we have + * to adjust the data_length in line. + */ + xdp_sinfo->data_length -= shrink; + xdp_set_frag_size(frag, size - shrink); + break; + } + + /* When we free the fragments, + * xdp_return_frags_from_buff() will take care + * of updating the xdp share info data_length. + */ + frags_to_free++; + } + + if (unlikely(frags_to_free)) + xdp_return_num_frags_from_buff(xdp, frags_to_free); + + if (unlikely(offset > 0)) + xdp->data_end -= offset; + } + + return 0; +} + BPF_CALL_2(bpf_xdp_adjust_tail, struct xdp_buff *, xdp, int, offset) { void *data_hard_end = xdp_data_hard_end(xdp); /* use xdp->frame_sz */ void *data_end = xdp->data_end + offset; + if (unlikely(xdp->mb)) + return bpf_xdp_mb_adjust_tail(xdp, offset); + /* Notice that xdp_data_hard_end have reserved some tailroom */ if (unlikely(data_end > data_hard_end)) return -EINVAL; From patchwork Mon Dec 7 16:32:42 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "lorenzo@kernel.org" X-Patchwork-Id: 11956359 X-Patchwork-Delegate: bpf@iogearbox.net Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-17.0 required=3.0 tests=BAYES_00,INCLUDES_CR_TRAILER, INCLUDES_PATCH,MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS,USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 9D8C9C4361B for ; Mon, 7 Dec 2020 16:35:55 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 7E9CC238E7 for ; Mon, 7 Dec 2020 16:35:55 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1727981AbgLGQfd (ORCPT ); Mon, 7 Dec 2020 11:35:33 -0500 Received: from mail.kernel.org ([198.145.29.99]:33484 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1727611AbgLGQeb (ORCPT ); Mon, 7 Dec 2020 11:34:31 -0500 From: Lorenzo Bianconi Authentication-Results: mail.kernel.org; dkim=permerror (bad message/signature format) To: bpf@vger.kernel.org, netdev@vger.kernel.org Cc: davem@davemloft.net, kuba@kernel.org, ast@kernel.org, daniel@iogearbox.net, shayagr@amazon.com, sameehj@amazon.com, john.fastabend@gmail.com, dsahern@kernel.org, brouer@redhat.com, echaudro@redhat.com, lorenzo.bianconi@redhat.com, jasowang@redhat.com Subject: [PATCH v5 bpf-next 13/14] bpf: add new frame_length field to the XDP ctx Date: Mon, 7 Dec 2020 17:32:42 +0100 Message-Id: <0547d6f752e325f56a8e5f6466b50e81ff29d65f.1607349924.git.lorenzo@kernel.org> X-Mailer: git-send-email 2.28.0 In-Reply-To: References: MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: bpf@vger.kernel.org X-Patchwork-Delegate: bpf@iogearbox.net From: Eelco Chaudron This patch adds a new field to the XDP context called frame_length, which will hold the full length of the packet, including fragments if existing. eBPF programs can determine if fragments are present using something like: if (ctx->data_end - ctx->data < ctx->frame_length) { /* Fragements exists. /* } Signed-off-by: Eelco Chaudron Signed-off-by: Lorenzo Bianconi --- include/net/xdp.h | 22 +++++++++ include/uapi/linux/bpf.h | 1 + kernel/bpf/verifier.c | 2 +- net/core/filter.c | 83 ++++++++++++++++++++++++++++++++++ tools/include/uapi/linux/bpf.h | 1 + 5 files changed, 108 insertions(+), 1 deletion(-) diff --git a/include/net/xdp.h b/include/net/xdp.h index 09078ab6644c..e54d733c90ed 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -73,8 +73,30 @@ struct xdp_buff { void *data_hard_start; struct xdp_rxq_info *rxq; struct xdp_txq_info *txq; + /* If any of the bitfield lengths for frame_sz or mb below change, + * make sure the defines here are also updated! + */ +#ifdef __BIG_ENDIAN_BITFIELD +#define MB_SHIFT 0 +#define MB_MASK 0x00000001 +#define FRAME_SZ_SHIFT 1 +#define FRAME_SZ_MASK 0xfffffffe +#else +#define MB_SHIFT 31 +#define MB_MASK 0x80000000 +#define FRAME_SZ_SHIFT 0 +#define FRAME_SZ_MASK 0x7fffffff +#endif +#define FRAME_SZ_OFFSET() offsetof(struct xdp_buff, __u32_bit_fields_offset) +#define MB_OFFSET() offsetof(struct xdp_buff, __u32_bit_fields_offset) + /* private: */ + u32 __u32_bit_fields_offset[0]; + /* public: */ u32 frame_sz:31; /* frame size to deduce data_hard_end/reserved tailroom*/ u32 mb:1; /* xdp non-linear buffer */ + + /* Temporary registers to make conditional access/stores possible. */ + u64 tmp_reg[2]; }; /* Reserve memory area at end-of data area. diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 30b477a26482..62c50ab28ea9 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4380,6 +4380,7 @@ struct xdp_md { __u32 rx_queue_index; /* rxq->queue_index */ __u32 egress_ifindex; /* txq->dev->ifindex */ + __u32 frame_length; }; /* DEVMAP map-value layout diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 93def76cf32b..c50caea29fa2 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -10526,7 +10526,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) const struct bpf_verifier_ops *ops = env->ops; int i, cnt, size, ctx_field_size, delta = 0; const int insn_cnt = env->prog->len; - struct bpf_insn insn_buf[16], *insn; + struct bpf_insn insn_buf[32], *insn; u32 target_size, size_default, off; struct bpf_prog *new_prog; enum bpf_access_type type; diff --git a/net/core/filter.c b/net/core/filter.c index 4c4882d4d92c..278640db9e0a 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -8908,6 +8908,7 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { + int ctx_reg, dst_reg, scratch_reg; struct bpf_insn *insn = insn_buf; switch (si->off) { @@ -8954,6 +8955,88 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type, *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct net_device, ifindex)); break; + case offsetof(struct xdp_md, frame_length): + /* Need tmp storage for src_reg in case src_reg == dst_reg, + * and a scratch reg */ + scratch_reg = BPF_REG_9; + dst_reg = si->dst_reg; + + if (dst_reg == scratch_reg) + scratch_reg--; + + ctx_reg = (si->src_reg == si->dst_reg) ? scratch_reg - 1 : si->src_reg; + while (dst_reg == ctx_reg || scratch_reg == ctx_reg) + ctx_reg--; + + /* Save scratch registers */ + if (ctx_reg != si->src_reg) { + *insn++ = BPF_STX_MEM(BPF_DW, si->src_reg, ctx_reg, + offsetof(struct xdp_buff, + tmp_reg[1])); + + *insn++ = BPF_MOV64_REG(ctx_reg, si->src_reg); + } + + *insn++ = BPF_STX_MEM(BPF_DW, ctx_reg, scratch_reg, + offsetof(struct xdp_buff, tmp_reg[0])); + + /* What does this code do? + * dst_reg = 0 + * + * if (!ctx_reg->mb) + * goto no_mb: + * + * dst_reg = (struct xdp_shared_info *)xdp_data_hard_end(xdp) + * dst_reg = dst_reg->data_length + * + * NOTE: xdp_data_hard_end() is xdp->hard_start + + * xdp->frame_sz - sizeof(shared_info) + * + * no_mb: + * dst_reg += ctx_reg->data_end - ctx_reg->data + */ + *insn++ = BPF_MOV64_IMM(dst_reg, 0); + + *insn++ = BPF_LDX_MEM(BPF_W, scratch_reg, ctx_reg, MB_OFFSET()); + *insn++ = BPF_ALU32_IMM(BPF_AND, scratch_reg, MB_MASK); + *insn++ = BPF_JMP_IMM(BPF_JEQ, scratch_reg, 0, 7); /*goto no_mb; */ + + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, + data_hard_start), + dst_reg, ctx_reg, + offsetof(struct xdp_buff, data_hard_start)); + *insn++ = BPF_LDX_MEM(BPF_W, scratch_reg, ctx_reg, + FRAME_SZ_OFFSET()); + *insn++ = BPF_ALU32_IMM(BPF_AND, scratch_reg, FRAME_SZ_MASK); + *insn++ = BPF_ALU32_IMM(BPF_RSH, scratch_reg, FRAME_SZ_SHIFT); + *insn++ = BPF_ALU64_REG(BPF_ADD, dst_reg, scratch_reg); + *insn++ = BPF_ALU64_IMM(BPF_SUB, dst_reg, + SKB_DATA_ALIGN(sizeof(struct skb_shared_info))); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_shared_info, + data_length), + dst_reg, dst_reg, + offsetof(struct xdp_shared_info, + data_length)); + + /* no_mb: */ + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, data_end), + scratch_reg, ctx_reg, + offsetof(struct xdp_buff, data_end)); + *insn++ = BPF_ALU64_REG(BPF_ADD, dst_reg, scratch_reg); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, data), + scratch_reg, ctx_reg, + offsetof(struct xdp_buff, data)); + *insn++ = BPF_ALU64_REG(BPF_SUB, dst_reg, scratch_reg); + + /* Restore scratch registers */ + *insn++ = BPF_LDX_MEM(BPF_DW, scratch_reg, ctx_reg, + offsetof(struct xdp_buff, tmp_reg[0])); + + if (ctx_reg != si->src_reg) + *insn++ = BPF_LDX_MEM(BPF_DW, ctx_reg, ctx_reg, + offsetof(struct xdp_buff, + tmp_reg[1])); + break; } return insn - insn_buf; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 30b477a26482..62c50ab28ea9 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4380,6 +4380,7 @@ struct xdp_md { __u32 rx_queue_index; /* rxq->queue_index */ __u32 egress_ifindex; /* txq->dev->ifindex */ + __u32 frame_length; }; /* DEVMAP map-value layout From patchwork Mon Dec 7 16:32:43 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "lorenzo@kernel.org" X-Patchwork-Id: 11956357 X-Patchwork-Delegate: bpf@iogearbox.net Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-17.0 required=3.0 tests=BAYES_00,INCLUDES_CR_TRAILER, INCLUDES_PATCH,MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS,USER_AGENT_GIT autolearn=unavailable autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 6E829C1B087 for ; Mon, 7 Dec 2020 16:35:53 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 3B6EB238E7 for ; Mon, 7 Dec 2020 16:35:53 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1727735AbgLGQef (ORCPT ); Mon, 7 Dec 2020 11:34:35 -0500 Received: from mail.kernel.org ([198.145.29.99]:33960 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1727128AbgLGQee (ORCPT ); Mon, 7 Dec 2020 11:34:34 -0500 From: Lorenzo Bianconi Authentication-Results: mail.kernel.org; dkim=permerror (bad message/signature format) To: bpf@vger.kernel.org, netdev@vger.kernel.org Cc: davem@davemloft.net, kuba@kernel.org, ast@kernel.org, daniel@iogearbox.net, shayagr@amazon.com, sameehj@amazon.com, john.fastabend@gmail.com, dsahern@kernel.org, brouer@redhat.com, echaudro@redhat.com, lorenzo.bianconi@redhat.com, jasowang@redhat.com Subject: [PATCH v5 bpf-next 14/14] bpf: update xdp_adjust_tail selftest to include multi-buffer Date: Mon, 7 Dec 2020 17:32:43 +0100 Message-Id: <6804eb7af70902fda5180b2f7494b2a671f96486.1607349924.git.lorenzo@kernel.org> X-Mailer: git-send-email 2.28.0 In-Reply-To: References: MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: bpf@vger.kernel.org X-Patchwork-Delegate: bpf@iogearbox.net From: Eelco Chaudron This change adds test cases for the multi-buffer scenarios when shrinking and growing. Signed-off-by: Eelco Chaudron Signed-off-by: Lorenzo Bianconi --- .../bpf/prog_tests/xdp_adjust_tail.c | 105 ++++++++++++++++++ .../bpf/progs/test_xdp_adjust_tail_grow.c | 16 +-- .../bpf/progs/test_xdp_adjust_tail_shrink.c | 32 +++++- 3 files changed, 142 insertions(+), 11 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c index d5c98f2cb12f..b936beaba797 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c @@ -130,6 +130,107 @@ void test_xdp_adjust_tail_grow2(void) bpf_object__close(obj); } +void test_xdp_adjust_mb_tail_shrink(void) +{ + const char *file = "./test_xdp_adjust_tail_shrink.o"; + __u32 duration, retval, size, exp_size; + struct bpf_object *obj; + static char buf[9000]; + int err, prog_fd; + + /* For the individual test cases, the first byte in the packet + * indicates which test will be run. + */ + + err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); + if (CHECK_FAIL(err)) + return; + + /* Test case removing 10 bytes from last frag, NOT freeing it */ + buf[0] = 0; + exp_size = sizeof(buf) - 10; + err = bpf_prog_test_run(prog_fd, 1, buf, sizeof(buf), + buf, &size, &retval, &duration); + + CHECK(err || retval != XDP_TX || size != exp_size, + "9k-10b", "err %d errno %d retval %d[%d] size %d[%u]\n", + err, errno, retval, XDP_TX, size, exp_size); + + /* Test case removing one of two pages, assuming 4K pages */ + buf[0] = 1; + exp_size = sizeof(buf) - 4100; + err = bpf_prog_test_run(prog_fd, 1, buf, sizeof(buf), + buf, &size, &retval, &duration); + + CHECK(err || retval != XDP_TX || size != exp_size, + "9k-1p", "err %d errno %d retval %d[%d] size %d[%u]\n", + err, errno, retval, XDP_TX, size, exp_size); + + /* Test case removing two pages resulting in a non mb xdp_buff */ + buf[0] = 2; + exp_size = sizeof(buf) - 8200; + err = bpf_prog_test_run(prog_fd, 1, buf, sizeof(buf), + buf, &size, &retval, &duration); + + CHECK(err || retval != XDP_TX || size != exp_size, + "9k-2p", "err %d errno %d retval %d[%d] size %d[%u]\n", + err, errno, retval, XDP_TX, size, exp_size); + + bpf_object__close(obj); +} + +void test_xdp_adjust_mb_tail_grow(void) +{ + const char *file = "./test_xdp_adjust_tail_grow.o"; + __u32 duration, retval, size, exp_size; + static char buf[16384]; + struct bpf_object *obj; + int err, i, prog_fd; + + err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); + if (CHECK_FAIL(err)) + return; + + /* Test case add 10 bytes to last frag */ + memset(buf, 1, sizeof(buf)); + size = 9000; + exp_size = size + 10; + err = bpf_prog_test_run(prog_fd, 1, buf, size, + buf, &size, &retval, &duration); + + CHECK(err || retval != XDP_TX || size != exp_size, + "9k+10b", "err %d retval %d[%d] size %d[%u]\n", + err, retval, XDP_TX, size, exp_size); + + for (i = 0; i < 9000; i++) + CHECK(buf[i] != 1, "9k+10b-old", + "Old data not all ok, offset %i is failing [%u]!\n", + i, buf[i]); + + for (i = 9000; i < 9010; i++) + CHECK(buf[i] != 0, "9k+10b-new", + "New data not all ok, offset %i is failing [%u]!\n", + i, buf[i]); + + for (i = 9010; i < sizeof(buf); i++) + CHECK(buf[i] != 1, "9k+10b-untouched", + "Unused data not all ok, offset %i is failing [%u]!\n", + i, buf[i]); + + /* Test a too large grow */ + memset(buf, 1, sizeof(buf)); + size = 9001; + exp_size = size; + err = bpf_prog_test_run(prog_fd, 1, buf, size, + buf, &size, &retval, &duration); + + CHECK(err || retval != XDP_DROP || size != exp_size, + "9k+10b", "err %d retval %d[%d] size %d[%u]\n", + err, retval, XDP_TX, size, exp_size); + + bpf_object__close(obj); +} + void test_xdp_adjust_tail(void) { if (test__start_subtest("xdp_adjust_tail_shrink")) @@ -138,4 +239,8 @@ void test_xdp_adjust_tail(void) test_xdp_adjust_tail_grow(); if (test__start_subtest("xdp_adjust_tail_grow2")) test_xdp_adjust_tail_grow2(); + if (test__start_subtest("xdp_adjust_mb_tail_shrink")) + test_xdp_adjust_mb_tail_shrink(); + if (test__start_subtest("xdp_adjust_mb_tail_grow")) + test_xdp_adjust_mb_tail_grow(); } diff --git a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c index 3d66599eee2e..25ac7108a53f 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c @@ -7,20 +7,22 @@ int _xdp_adjust_tail_grow(struct xdp_md *xdp) { void *data_end = (void *)(long)xdp->data_end; void *data = (void *)(long)xdp->data; - unsigned int data_len; int offset = 0; /* Data length determine test case */ - data_len = data_end - data; - if (data_len == 54) { /* sizeof(pkt_v4) */ + if (xdp->frame_length == 54) { /* sizeof(pkt_v4) */ offset = 4096; /* test too large offset */ - } else if (data_len == 74) { /* sizeof(pkt_v6) */ + } else if (xdp->frame_length == 74) { /* sizeof(pkt_v6) */ offset = 40; - } else if (data_len == 64) { + } else if (xdp->frame_length == 64) { offset = 128; - } else if (data_len == 128) { - offset = 4096 - 256 - 320 - data_len; /* Max tail grow 3520 */ + } else if (xdp->frame_length == 128) { + offset = 4096 - 256 - 320 - xdp->frame_length; /* Max tail grow 3520 */ + } else if (xdp->frame_length == 9000) { + offset = 10; + } else if (xdp->frame_length == 9001) { + offset = 4096; } else { return XDP_ABORTED; /* No matching test */ } diff --git a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c index 22065a9cfb25..689450414d29 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c @@ -14,14 +14,38 @@ int _version SEC("version") = 1; SEC("xdp_adjust_tail_shrink") int _xdp_adjust_tail_shrink(struct xdp_md *xdp) { - void *data_end = (void *)(long)xdp->data_end; - void *data = (void *)(long)xdp->data; + __u8 *data_end = (void *)(long)xdp->data_end; + __u8 *data = (void *)(long)xdp->data; int offset = 0; - if (data_end - data == 54) /* sizeof(pkt_v4) */ + switch (xdp->frame_length) { + case 54: + /* sizeof(pkt_v4) */ offset = 256; /* shrink too much */ - else + break; + case 9000: + /* Multi-buffer test cases */ + if (data + 1 > data_end) + return XDP_DROP; + + switch (data[0]) { + case 0: + offset = 10; + break; + case 1: + offset = 4100; + break; + case 2: + offset = 8200; + break; + default: + return XDP_DROP; + } + break; + default: offset = 20; + break; + } if (bpf_xdp_adjust_tail(xdp, 0 - offset)) return XDP_DROP; return XDP_TX;