From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932828AbdDGJ6r (ORCPT ); Fri, 7 Apr 2017 05:58:47 -0400 Received: from mx0b-001b2d01.pphosted.com ([148.163.158.5]:60865 "EHLO mx0a-001b2d01.pphosted.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1751738AbdDGJ6i (ORCPT ); Fri, 7 Apr 2017 05:58:38 -0400 From: Sivakumar Krishnasamy To: netdev@vger.kernel.org Cc: tlfalcon@linux.vnet.ibm.com, benh@kernel.crashing.org, paulus@samba.org, mpe@ellerman.id.au, linuxppc-dev@lists.ozlabs.org, linux-kernel@vger.kernel.org, brking@linux.vnet.ibm.com, seroyer@linux.vnet.ibm.com, Sivakumar Krishnasamy Subject: [PATCH] ibmveth: Support to enable LSO/CSO for Trunk VEA. Date: Fri, 7 Apr 2017 05:57:59 -0400 X-Mailer: git-send-email 2.7.4 X-TM-AS-GCONF: 00 x-cbid: 17040709-0040-0000-0000-0000030B0D27 X-IBM-SpamModules-Scores: X-IBM-SpamModules-Versions: BY=3.00006892; HX=3.00000240; KW=3.00000007; PH=3.00000004; SC=3.00000208; SDB=6.00844211; UDB=6.00416113; IPR=6.00622509; BA=6.00005274; NDR=6.00000001; ZLA=6.00000005; ZF=6.00000009; ZB=6.00000000; ZP=6.00000000; ZH=6.00000000; ZU=6.00000002; MB=3.00014947; XFM=3.00000013; UTC=2017-04-07 09:58:35 X-IBM-AV-DETECTION: SAVI=unused REMOTE=unused XFE=unused x-cbparentid: 17040709-0041-0000-0000-000006FF1188 Message-Id: <1491559079-10855-1-git-send-email-ksiva@linux.vnet.ibm.com> X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10432:,, definitions=2017-04-07_09:,, signatures=0 X-Proofpoint-Spam-Details: rule=outbound_notspam policy=outbound score=0 spamscore=0 suspectscore=1 malwarescore=0 phishscore=0 adultscore=0 bulkscore=0 classifier=spam adjust=0 reason=mlx scancount=1 engine=8.0.1-1702020001 definitions=main-1704070086 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Enable largesend and checksum offload for ibmveth configured in trunk mode. Added support to SKB frag_list in TX path by skb_linearize'ing such SKBs. Signed-off-by: Sivakumar Krishnasamy --- drivers/net/ethernet/ibm/ibmveth.c | 102 ++++++++++++++++++++++++++++++------- drivers/net/ethernet/ibm/ibmveth.h | 1 + 2 files changed, 85 insertions(+), 18 deletions(-) diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index 72ab7b6..e1e238d 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -46,6 +46,8 @@ #include #include #include +#include +#include #include "ibmveth.h" @@ -808,8 +810,7 @@ static int ibmveth_set_csum_offload(struct net_device *dev, u32 data) ret = h_illan_attributes(adapter->vdev->unit_address, 0, 0, &ret_attr); - if (ret == H_SUCCESS && !(ret_attr & IBMVETH_ILLAN_ACTIVE_TRUNK) && - !(ret_attr & IBMVETH_ILLAN_TRUNK_PRI_MASK) && + if (ret == H_SUCCESS && (ret_attr & IBMVETH_ILLAN_PADDED_PKT_CSUM)) { ret4 = h_illan_attributes(adapter->vdev->unit_address, clr_attr, set_attr, &ret_attr); @@ -1040,6 +1041,15 @@ static netdev_tx_t ibmveth_start_xmit(struct sk_buff *skb, dma_addr_t dma_addr; unsigned long mss = 0; + /* veth doesn't handle frag_list, so linearize the skb. + * When GRO is enabled SKB's can have frag_list. + */ + if (adapter->is_active_trunk && + skb_has_frag_list(skb) && __skb_linearize(skb)) { + netdev->stats.tx_dropped++; + goto out; + } + /* * veth handles a maximum of 6 segments including the header, so * we have to linearize the skb if there are more than this. @@ -1064,9 +1074,6 @@ static netdev_tx_t ibmveth_start_xmit(struct sk_buff *skb, desc_flags = IBMVETH_BUF_VALID; - if (skb_is_gso(skb) && adapter->fw_large_send_support) - desc_flags |= IBMVETH_BUF_LRG_SND; - if (skb->ip_summed == CHECKSUM_PARTIAL) { unsigned char *buf = skb_transport_header(skb) + skb->csum_offset; @@ -1076,6 +1083,9 @@ static netdev_tx_t ibmveth_start_xmit(struct sk_buff *skb, /* Need to zero out the checksum */ buf[0] = 0; buf[1] = 0; + + if (skb_is_gso(skb) && adapter->fw_large_send_support) + desc_flags |= IBMVETH_BUF_LRG_SND; } retry_bounce: @@ -1128,7 +1138,7 @@ retry_bounce: descs[i+1].fields.address = dma_addr; } - if (skb_is_gso(skb)) { + if (skb->ip_summed == CHECKSUM_PARTIAL && skb_is_gso(skb)) { if (adapter->fw_large_send_support) { mss = (unsigned long)skb_shinfo(skb)->gso_size; adapter->tx_large_packets++; @@ -1232,6 +1242,66 @@ static void ibmveth_rx_mss_helper(struct sk_buff *skb, u16 mss, int lrg_pkt) } } +static void ibmveth_rx_csum_helper(struct sk_buff *skb, + struct ibmveth_adapter *adapter) +{ + struct iphdr *iph = NULL; + struct ipv6hdr *iph6 = NULL; + __be16 skb_proto = 0; + u16 iphlen = 0; + u16 iph_proto = 0; + u16 tcphdrlen = 0; + + skb_proto = be16_to_cpu(skb->protocol); + + if (skb_proto == ETH_P_IP) { + iph = (struct iphdr *)skb->data; + + /* If the IP checksum is not offloaded and if the packet + * is large send, the checksum must be rebuilt. + */ + if (iph->check == 0xffff) { + iph->check = 0; + iph->check = ip_fast_csum((unsigned char *)iph, + iph->ihl); + } + + iphlen = iph->ihl * 4; + iph_proto = iph->protocol; + } else if (skb_proto == ETH_P_IPV6) { + iph6 = (struct ipv6hdr *)skb->data; + iphlen = sizeof(struct ipv6hdr); + iph_proto = iph6->nexthdr; + } + + /* In OVS environment, when a flow is not cached, specifically for a + * new TCP connection, the first (SYN) packet information is passed up + * the user space for finding a flow. During this process, OVS computes + * checksum on the packet when CHECKSUM_PARTIAL flag is set. + * Given that we zeroed out TCP checksum field in transmit path as we + * set "no checksum bit", OVS computed checksum will be incorrect w/o + * TCP pseudo checksum in the packet. + * So, re-compute TCP pseudo header checksum. + */ + if (iph_proto == IPPROTO_TCP && adapter->is_active_trunk) { + struct tcphdr *tcph = (struct tcphdr *)(skb->data + iphlen); + + tcphdrlen = skb->len - iphlen; + + if (skb_proto == ETH_P_IP) + tcph->check = ~csum_tcpudp_magic(iph->saddr, + iph->daddr, tcphdrlen, iph_proto, 0); + else if (skb_proto == ETH_P_IPV6) + tcph->check = ~csum_ipv6_magic(&iph6->saddr, + &iph6->daddr, tcphdrlen, iph_proto, 0); + + /* Setup SKB fields for checksum offload */ + skb_partial_csum_set(skb, iphlen, + offsetof(struct tcphdr, check)); + skb_reset_network_header(skb); + } +} + static int ibmveth_poll(struct napi_struct *napi, int budget) { struct ibmveth_adapter *adapter = @@ -1239,7 +1309,6 @@ static int ibmveth_poll(struct napi_struct *napi, int budget) struct net_device *netdev = adapter->netdev; int frames_processed = 0; unsigned long lpar_rc; - struct iphdr *iph; u16 mss = 0; restart_poll: @@ -1297,17 +1366,7 @@ restart_poll: if (csum_good) { skb->ip_summed = CHECKSUM_UNNECESSARY; - if (be16_to_cpu(skb->protocol) == ETH_P_IP) { - iph = (struct iphdr *)skb->data; - - /* If the IP checksum is not offloaded and if the packet - * is large send, the checksum must be rebuilt. - */ - if (iph->check == 0xffff) { - iph->check = 0; - iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); - } - } + ibmveth_rx_csum_helper(skb, adapter); } if (length > netdev->mtu + ETH_HLEN) { @@ -1626,6 +1685,13 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id) netdev->hw_features |= NETIF_F_TSO; } + adapter->is_active_trunk = false; + if (ret == H_SUCCESS && (ret_attr & IBMVETH_ILLAN_ACTIVE_TRUNK)) { + adapter->is_active_trunk = true; + netdev->hw_features |= NETIF_F_FRAGLIST; + netdev->features |= NETIF_F_FRAGLIST; + } + netdev->min_mtu = IBMVETH_MIN_MTU; netdev->max_mtu = ETH_MAX_MTU; diff --git a/drivers/net/ethernet/ibm/ibmveth.h b/drivers/net/ethernet/ibm/ibmveth.h index 7acda04..de6e381 100644 --- a/drivers/net/ethernet/ibm/ibmveth.h +++ b/drivers/net/ethernet/ibm/ibmveth.h @@ -157,6 +157,7 @@ struct ibmveth_adapter { int pool_config; int rx_csum; int large_send; + bool is_active_trunk; void *bounce_buffer; dma_addr_t bounce_buffer_dma; -- 2.7.4