From 04dd17822334871b23ea2862f7798fb0e0007777 Mon Sep 17 00:00:00 2001 From: hc <hc@nodka.com> Date: Sat, 11 May 2024 08:53:19 +0000 Subject: [PATCH] change otg to host mode --- kernel/net/ipv4/ip_tunnel.c | 166 +++++++++++++++++++++++++++++++++---------------------- 1 files changed, 100 insertions(+), 66 deletions(-) diff --git a/kernel/net/ipv4/ip_tunnel.c b/kernel/net/ipv4/ip_tunnel.c index 30e93b4..99f70b9 100644 --- a/kernel/net/ipv4/ip_tunnel.c +++ b/kernel/net/ipv4/ip_tunnel.c @@ -1,19 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2013 Nicira, Inc. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of version 2 of the GNU General Public - * License as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -308,7 +295,7 @@ ip_tunnel_init_flow(&fl4, iph->protocol, iph->daddr, iph->saddr, tunnel->parms.o_key, RT_TOS(iph->tos), tunnel->parms.link, - tunnel->fwmark); + tunnel->fwmark, 0); rt = ip_route_output_key(tunnel->net, &fl4); if (!IS_ERR(rt)) { @@ -376,7 +363,6 @@ const struct tnl_ptk_info *tpi, struct metadata_dst *tun_dst, bool log_ecn_error) { - struct pcpu_sw_netstats *tstats; const struct iphdr *iph = ip_hdr(skb); int err; @@ -404,7 +390,7 @@ tunnel->i_seqno = ntohl(tpi->seq) + 1; } - skb_reset_network_header(skb); + skb_set_network_header(skb, (tunnel->dev->type == ARPHRD_ETHER) ? ETH_HLEN : 0); err = IP_ECN_decapsulate(iph, skb); if (unlikely(err)) { @@ -418,12 +404,7 @@ } } - tstats = this_cpu_ptr(tunnel->dev->tstats); - u64_stats_update_begin(&tstats->syncp); - tstats->rx_packets++; - tstats->rx_bytes += skb->len; - u64_stats_update_end(&tstats->syncp); - + dev_sw_netstats_rx_add(tunnel->dev, skb->len); skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(tunnel->dev))); if (tunnel->dev->type == ARPHRD_ETHER) { @@ -502,41 +483,47 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, struct rtable *rt, __be16 df, - const struct iphdr *inner_iph) + const struct iphdr *inner_iph, + int tunnel_hlen, __be32 dst, bool md) { struct ip_tunnel *tunnel = netdev_priv(dev); int pkt_size; int mtu; - pkt_size = skb->len - tunnel->hlen; + tunnel_hlen = md ? tunnel_hlen : tunnel->hlen; + pkt_size = skb->len - tunnel_hlen; pkt_size -= dev->type == ARPHRD_ETHER ? dev->hard_header_len : 0; if (df) { - mtu = dst_mtu(&rt->dst) - (sizeof(struct iphdr) + tunnel->hlen); + mtu = dst_mtu(&rt->dst) - (sizeof(struct iphdr) + tunnel_hlen); mtu -= dev->type == ARPHRD_ETHER ? dev->hard_header_len : 0; } else { - mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; + mtu = skb_valid_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; } - skb_dst_update_pmtu_no_confirm(skb, mtu); + if (skb_valid_dst(skb)) + skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->protocol == htons(ETH_P_IP)) { if (!skb_is_gso(skb) && (inner_iph->frag_off & htons(IP_DF)) && mtu < pkt_size) { - memset(IPCB(skb), 0, sizeof(*IPCB(skb))); - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); + icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); return -E2BIG; } } #if IS_ENABLED(CONFIG_IPV6) else if (skb->protocol == htons(ETH_P_IPV6)) { - struct rt6_info *rt6 = (struct rt6_info *)skb_dst(skb); + struct rt6_info *rt6; + __be32 daddr; + + rt6 = skb_valid_dst(skb) ? (struct rt6_info *)skb_dst(skb) : + NULL; + daddr = md ? dst : tunnel->parms.iph.daddr; if (rt6 && mtu < dst_mtu(skb_dst(skb)) && mtu >= IPV6_MIN_MTU) { - if ((tunnel->parms.iph.daddr && - !ipv4_is_multicast(tunnel->parms.iph.daddr)) || + if ((daddr && !ipv4_is_multicast(daddr)) || rt6->rt6i_dst.plen == 128) { rt6->rt6i_flags |= RTF_MODIFIED; dst_metric_set(skb_dst(skb), RTAX_MTU, mtu); @@ -545,7 +532,7 @@ if (!skb_is_gso(skb) && mtu >= IPV6_MIN_MTU && mtu < pkt_size) { - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); return -E2BIG; } } @@ -553,17 +540,19 @@ return 0; } -void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, u8 proto) +void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, + u8 proto, int tunnel_hlen) { struct ip_tunnel *tunnel = netdev_priv(dev); u32 headroom = sizeof(struct iphdr); struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; const struct iphdr *inner_iph; - struct rtable *rt; + struct rtable *rt = NULL; struct flowi4 fl4; __be16 df = 0; u8 tos, ttl; + bool use_cache; tun_info = skb_tunnel_info(skb); if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) || @@ -581,19 +570,37 @@ } ip_tunnel_init_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src, tunnel_id_to_key32(key->tun_id), RT_TOS(tos), - 0, skb->mark); + 0, skb->mark, skb_get_hash(skb)); if (tunnel->encap.type != TUNNEL_ENCAP_NONE) goto tx_error; - rt = ip_route_output_key(tunnel->net, &fl4); - if (IS_ERR(rt)) { - dev->stats.tx_carrier_errors++; - goto tx_error; + + use_cache = ip_tunnel_dst_cache_usable(skb, tun_info); + if (use_cache) + rt = dst_cache_get_ip4(&tun_info->dst_cache, &fl4.saddr); + if (!rt) { + rt = ip_route_output_key(tunnel->net, &fl4); + if (IS_ERR(rt)) { + dev->stats.tx_carrier_errors++; + goto tx_error; + } + if (use_cache) + dst_cache_set_ip4(&tun_info->dst_cache, &rt->dst, + fl4.saddr); } if (rt->dst.dev == dev) { ip_rt_put(rt); dev->stats.collisions++; goto tx_error; } + + if (key->tun_flags & TUNNEL_DONT_FRAGMENT) + df = htons(IP_DF); + if (tnl_update_pmtu(dev, skb, rt, df, inner_iph, tunnel_hlen, + key->u.ipv4.dst, true)) { + ip_rt_put(rt); + goto tx_error; + } + tos = ip_tunnel_ecn_encap(tos, inner_iph, skb); ttl = key->ttl; if (ttl == 0) { @@ -604,15 +611,12 @@ else ttl = ip4_dst_hoplimit(&rt->dst); } - if (key->tun_flags & TUNNEL_DONT_FRAGMENT) - df = htons(IP_DF); - else if (skb->protocol == htons(ETH_P_IP)) - df = inner_iph->frag_off & htons(IP_DF); - headroom += LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len; - if (headroom > dev->needed_headroom) - dev->needed_headroom = headroom; - if (skb_cow_head(skb, dev->needed_headroom)) { + headroom += LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len; + if (headroom > READ_ONCE(dev->needed_headroom)) + WRITE_ONCE(dev->needed_headroom, headroom); + + if (skb_cow_head(skb, READ_ONCE(dev->needed_headroom))) { ip_rt_put(rt); goto tx_dropped; } @@ -633,14 +637,17 @@ const struct iphdr *tnl_params, u8 protocol) { struct ip_tunnel *tunnel = netdev_priv(dev); + struct ip_tunnel_info *tun_info = NULL; const struct iphdr *inner_iph; - struct flowi4 fl4; - u8 tos, ttl; - __be16 df; - struct rtable *rt; /* Route to the other host */ unsigned int max_headroom; /* The extra header space needed */ - __be32 dst; + struct rtable *rt = NULL; /* Route to the other host */ + bool use_cache = false; + struct flowi4 fl4; + bool md = false; bool connected; + u8 tos, ttl; + __be32 dst; + __be16 df; inner_iph = (const struct iphdr *)skb_inner_network_header(skb); connected = (tunnel->parms.iph.daddr != 0); @@ -650,7 +657,6 @@ dst = tnl_params->daddr; if (dst == 0) { /* NBMA tunnel */ - struct ip_tunnel_info *tun_info; if (!skb_dst(skb)) { dev->stats.tx_fifo_errors++; @@ -660,8 +666,11 @@ tun_info = skb_tunnel_info(skb); if (tun_info && (tun_info->mode & IP_TUNNEL_INFO_TX) && ip_tunnel_info_af(tun_info) == AF_INET && - tun_info->key.u.ipv4.dst) + tun_info->key.u.ipv4.dst) { dst = tun_info->key.u.ipv4.dst; + md = true; + connected = true; + } else if (skb->protocol == htons(ETH_P_IP)) { rt = skb_rtable(skb); dst = rt_nexthop(rt, inner_iph->daddr); @@ -700,7 +709,8 @@ else goto tx_error; - connected = false; + if (!md) + connected = false; } tos = tnl_params->tos; @@ -717,13 +727,20 @@ ip_tunnel_init_flow(&fl4, protocol, dst, tnl_params->saddr, tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link, - tunnel->fwmark); + tunnel->fwmark, skb_get_hash(skb)); if (ip_tunnel_encap(skb, tunnel, &protocol, &fl4) < 0) goto tx_error; - rt = connected ? dst_cache_get_ip4(&tunnel->dst_cache, &fl4.saddr) : - NULL; + if (connected && md) { + use_cache = ip_tunnel_dst_cache_usable(skb, tun_info); + if (use_cache) + rt = dst_cache_get_ip4(&tun_info->dst_cache, + &fl4.saddr); + } else { + rt = connected ? dst_cache_get_ip4(&tunnel->dst_cache, + &fl4.saddr) : NULL; + } if (!rt) { rt = ip_route_output_key(tunnel->net, &fl4); @@ -732,7 +749,10 @@ dev->stats.tx_carrier_errors++; goto tx_error; } - if (connected) + if (use_cache) + dst_cache_set_ip4(&tun_info->dst_cache, &rt->dst, + fl4.saddr); + else if (!md && connected) dst_cache_set_ip4(&tunnel->dst_cache, &rt->dst, fl4.saddr); } @@ -747,7 +767,7 @@ if (skb->protocol == htons(ETH_P_IP) && !tunnel->ignore_df) df |= (inner_iph->frag_off & htons(IP_DF)); - if (tnl_update_pmtu(dev, skb, rt, df, inner_iph)) { + if (tnl_update_pmtu(dev, skb, rt, df, inner_iph, 0, 0, false)) { ip_rt_put(rt); goto tx_error; } @@ -777,10 +797,10 @@ max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr) + rt->dst.header_len + ip_encap_hlen(&tunnel->encap); - if (max_headroom > dev->needed_headroom) - dev->needed_headroom = max_headroom; + if (max_headroom > READ_ONCE(dev->needed_headroom)) + WRITE_ONCE(dev->needed_headroom, max_headroom); - if (skb_cow_head(skb, dev->needed_headroom)) { + if (skb_cow_head(skb, READ_ONCE(dev->needed_headroom))) { ip_rt_put(rt); dev->stats.tx_dropped++; kfree_skb(skb); @@ -836,7 +856,7 @@ netdev_state_change(dev); } -int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) +int ip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) { int err = 0; struct ip_tunnel *t = netdev_priv(dev); @@ -936,6 +956,20 @@ done: return err; } +EXPORT_SYMBOL_GPL(ip_tunnel_ctl); + +int ip_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +{ + struct ip_tunnel_parm p; + int err; + + if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) + return -EFAULT; + err = dev->netdev_ops->ndo_tunnel_ctl(dev, &p, cmd); + if (!err && copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) + return -EFAULT; + return err; +} EXPORT_SYMBOL_GPL(ip_tunnel_ioctl); int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict) -- Gitblit v1.6.2