diff options
Diffstat (limited to 'net/ipv6')
-rw-r--r-- | net/ipv6/addrconf.c | 12 | ||||
-rw-r--r-- | net/ipv6/icmp.c | 6 | ||||
-rw-r--r-- | net/ipv6/ila.c | 4 | ||||
-rw-r--r-- | net/ipv6/inet6_hashtables.c | 2 | ||||
-rw-r--r-- | net/ipv6/ip6_fib.c | 1 | ||||
-rw-r--r-- | net/ipv6/ip6_output.c | 31 | ||||
-rw-r--r-- | net/ipv6/ip6_vti.c | 2 | ||||
-rw-r--r-- | net/ipv6/ip6mr.c | 2 | ||||
-rw-r--r-- | net/ipv6/mcast.c | 4 | ||||
-rw-r--r-- | net/ipv6/mip6.c | 16 | ||||
-rw-r--r-- | net/ipv6/ndisc.c | 29 | ||||
-rw-r--r-- | net/ipv6/netfilter/ip6t_SYNPROXY.c | 2 | ||||
-rw-r--r-- | net/ipv6/netfilter/nf_conntrack_reasm.c | 4 | ||||
-rw-r--r-- | net/ipv6/netfilter/nf_defrag_ipv6_hooks.c | 3 | ||||
-rw-r--r-- | net/ipv6/netfilter/nf_dup_ipv6.c | 2 | ||||
-rw-r--r-- | net/ipv6/netfilter/nf_reject_ipv6.c | 2 | ||||
-rw-r--r-- | net/ipv6/output_core.c | 22 | ||||
-rw-r--r-- | net/ipv6/raw.c | 2 | ||||
-rw-r--r-- | net/ipv6/route.c | 73 | ||||
-rw-r--r-- | net/ipv6/syncookies.c | 6 | ||||
-rw-r--r-- | net/ipv6/tcp_ipv6.c | 9 | ||||
-rw-r--r-- | net/ipv6/udp.c | 11 | ||||
-rw-r--r-- | net/ipv6/xfrm6_output.c | 17 | ||||
-rw-r--r-- | net/ipv6/xfrm6_policy.c | 1 |
24 files changed, 157 insertions, 106 deletions
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index c8380f1876f1..f0326aae7a02 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -81,6 +81,7 @@ #include <net/ip.h> #include <net/netlink.h> #include <net/pkt_sched.h> +#include <net/l3mdev.h> #include <linux/if_tunnel.h> #include <linux/rtnetlink.h> #include <linux/netconf.h> @@ -2146,7 +2147,7 @@ addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev, unsigned long expires, u32 flags) { struct fib6_config cfg = { - .fc_table = RT6_TABLE_PREFIX, + .fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_PREFIX, .fc_metric = IP6_RT_PRIO_ADDRCONF, .fc_ifindex = dev->ifindex, .fc_expires = expires, @@ -2179,8 +2180,9 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, struct fib6_node *fn; struct rt6_info *rt = NULL; struct fib6_table *table; + u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_PREFIX; - table = fib6_get_table(dev_net(dev), RT6_TABLE_PREFIX); + table = fib6_get_table(dev_net(dev), tb_id); if (!table) return NULL; @@ -2211,7 +2213,7 @@ out: static void addrconf_add_mroute(struct net_device *dev) { struct fib6_config cfg = { - .fc_table = RT6_TABLE_LOCAL, + .fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_LOCAL, .fc_metric = IP6_RT_PRIO_ADDRCONF, .fc_ifindex = dev->ifindex, .fc_dst_len = 8, @@ -3029,6 +3031,10 @@ static void addrconf_addr_gen(struct inet6_dev *idev, bool prefix_route) { struct in6_addr addr; + /* no link local addresses on L3 master devices */ + if (netif_is_l3_master(idev->dev)) + return; + ipv6_addr_set(&addr, htonl(0xFE800000), 0, 0, 0); if (idev->addr_gen_mode == IN6_ADDR_GEN_MODE_STABLE_PRIVACY) { diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 6c2b2132c8d3..efb1c00f2270 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -68,6 +68,7 @@ #include <net/xfrm.h> #include <net/inet_common.h> #include <net/dsfield.h> +#include <net/l3mdev.h> #include <asm/uaccess.h> @@ -496,6 +497,9 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) else if (!fl6.flowi6_oif) fl6.flowi6_oif = np->ucast_oif; + if (!fl6.flowi6_oif) + fl6.flowi6_oif = l3mdev_master_ifindex(skb->dev); + dst = icmpv6_route_lookup(net, skb, sk, &fl6); if (IS_ERR(dst)) goto out; @@ -575,7 +579,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb) fl6.daddr = ipv6_hdr(skb)->saddr; if (saddr) fl6.saddr = *saddr; - fl6.flowi6_oif = skb->dev->ifindex; + fl6.flowi6_oif = l3mdev_fib_oif(skb->dev); fl6.fl6_icmp_type = ICMPV6_ECHO_REPLY; fl6.flowi6_mark = mark; security_skb_classify_flow(skb, flowi6_to_flowi(&fl6)); diff --git a/net/ipv6/ila.c b/net/ipv6/ila.c index 678d2df4b8d9..1a6852e1ac69 100644 --- a/net/ipv6/ila.c +++ b/net/ipv6/ila.c @@ -91,7 +91,7 @@ static void update_ipv6_locator(struct sk_buff *skb, struct ila_params *p) *(__be64 *)&ip6h->daddr = p->locator; } -static int ila_output(struct sock *sk, struct sk_buff *skb) +static int ila_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); @@ -100,7 +100,7 @@ static int ila_output(struct sock *sk, struct sk_buff *skb) update_ipv6_locator(skb, ila_params_lwtunnel(dst->lwtstate)); - return dst->lwtstate->orig_output(sk, skb); + return dst->lwtstate->orig_output(net, sk, skb); drop: kfree_skb(skb); diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 6ac8dad0138a..21ace5a2bf7c 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -114,6 +114,8 @@ static inline int compute_score(struct sock *sk, struct net *net, return -1; score++; } + if (sk->sk_incoming_cpu == raw_smp_processor_id()) + score++; } return score; } diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 7d2e0023c72d..09fddf70cca4 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -264,6 +264,7 @@ struct fib6_table *fib6_get_table(struct net *net, u32 id) return NULL; } +EXPORT_SYMBOL_GPL(fib6_get_table); static void __net_init fib6_tables_init(struct net *net) { diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index a598fe2c0849..23f97c4783bb 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -55,12 +55,12 @@ #include <net/xfrm.h> #include <net/checksum.h> #include <linux/mroute6.h> +#include <net/l3mdev.h> -static int ip6_finish_output2(struct sock *sk, struct sk_buff *skb) +static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct net_device *dev = dst->dev; - struct net *net = dev_net(dev); struct neighbour *neigh; struct in6_addr *nexthop; int ret; @@ -126,16 +126,15 @@ static int ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *s if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) || dst_allfrag(skb_dst(skb)) || (IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size)) - return ip6_fragment(sk, skb, ip6_finish_output2); + return ip6_fragment(net, sk, skb, ip6_finish_output2); else - return ip6_finish_output2(sk, skb); + return ip6_finish_output2(net, sk, skb); } -int ip6_output(struct sock *sk, struct sk_buff *skb) +int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb_dst(skb)->dev; struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); - struct net *net = dev_net(dev); if (unlikely(idev->cnf.disable_ipv6)) { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); @@ -234,7 +233,7 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, */ return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, (struct sock *)sk, skb, NULL, dst->dev, - dst_output_okfn); + dst_output); } skb->dev = dst->dev; @@ -334,7 +333,7 @@ static inline int ip6_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { skb_sender_cpu_clear(skb); - return dst_output(sk, skb); + return dst_output(net, sk, skb); } static unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst) @@ -554,8 +553,8 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from) skb_copy_secmark(to, from); } -int ip6_fragment(struct sock *sk, struct sk_buff *skb, - int (*output)(struct sock *, struct sk_buff *)) +int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, + int (*output)(struct net *, struct sock *, struct sk_buff *)) { struct sk_buff *frag; struct rt6_info *rt = (struct rt6_info *)skb_dst(skb); @@ -568,7 +567,6 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb, __be32 frag_id; int ptr, offset = 0, err = 0; u8 *prevhdr, nexthdr = 0; - struct net *net = dev_net(skb_dst(skb)->dev); hlen = ip6_find_1stfragopt(skb, &prevhdr); nexthdr = *prevhdr; @@ -688,7 +686,7 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb, ip6_copy_metadata(frag, skb); } - err = output(sk, skb); + err = output(net, sk, skb); if (!err) IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), IPSTATS_MIB_FRAGCREATES); @@ -816,7 +814,7 @@ slow_path: /* * Put this fragment into the sending queue. */ - err = output(sk, frag); + err = output(net, sk, frag); if (err) goto fail; @@ -888,7 +886,8 @@ static struct dst_entry *ip6_sk_dst_check(struct sock *sk, #ifdef CONFIG_IPV6_SUBTREES ip6_rt_check(&rt->rt6i_src, &fl6->saddr, np->saddr_cache) || #endif - (fl6->flowi6_oif && fl6->flowi6_oif != dst->dev->ifindex)) { + (!(fl6->flowi6_flags & FLOWI_FLAG_SKIP_NH_OIF) && + (fl6->flowi6_oif && fl6->flowi6_oif != dst->dev->ifindex))) { dst_release(dst); dst = NULL; } @@ -1040,7 +1039,7 @@ struct dst_entry *ip6_dst_lookup_flow(const struct sock *sk, struct flowi6 *fl6, if (final_dst) fl6->daddr = *final_dst; if (!fl6->flowi6_oif) - fl6->flowi6_oif = dst->dev->ifindex; + fl6->flowi6_oif = l3mdev_fib_oif(dst->dev); return xfrm_lookup_route(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0); } @@ -1694,7 +1693,7 @@ int ip6_send_skb(struct sk_buff *skb) struct rt6_info *rt = (struct rt6_info *)skb_dst(skb); int err; - err = ip6_local_out(skb); + err = ip6_local_out(net, skb->sk, skb); if (err) { if (err > 0) err = net_xmit_errno(err); diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index f96f1c19b4a8..0a8610b33d79 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -482,7 +482,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) return -EMSGSIZE; } - err = dst_output(skb->sk, skb); + err = dst_output(t->net, skb->sk, skb); if (net_xmit_eval(err) == 0) { struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 5e5d16e7ce85..ad19136086dd 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1991,7 +1991,7 @@ static inline int ip6mr_forward2_finish(struct net *net, struct sock *sk, struct IPSTATS_MIB_OUTFORWDATAGRAMS); IP6_ADD_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUTOCTETS, skb->len); - return dst_output(sk, skb); + return dst_output(net, sk, skb); } /* diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index a8bf57ca74d3..124338a39e29 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1646,7 +1646,7 @@ static void mld_sendpack(struct sk_buff *skb) err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, net->ipv6.igmp_sk, skb, NULL, skb->dev, - dst_output_okfn); + dst_output); out: if (!err) { ICMP6MSGOUT_INC_STATS(net, idev, ICMPV6_MLD2_REPORT); @@ -2010,7 +2010,7 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) skb_dst_set(skb, dst); err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb->dev, - dst_output_okfn); + dst_output); out: if (!err) { ICMP6MSGOUT_INC_STATS(net, idev, type); diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c index b9779d441b12..60c79a08e14a 100644 --- a/net/ipv6/mip6.c +++ b/net/ipv6/mip6.c @@ -118,7 +118,7 @@ static int mip6_mh_filter(struct sock *sk, struct sk_buff *skb) struct mip6_report_rate_limiter { spinlock_t lock; - struct timeval stamp; + ktime_t stamp; int iif; struct in6_addr src; struct in6_addr dst; @@ -184,20 +184,18 @@ static int mip6_destopt_output(struct xfrm_state *x, struct sk_buff *skb) return 0; } -static inline int mip6_report_rl_allow(struct timeval *stamp, +static inline int mip6_report_rl_allow(ktime_t stamp, const struct in6_addr *dst, const struct in6_addr *src, int iif) { int allow = 0; spin_lock_bh(&mip6_report_rl.lock); - if (mip6_report_rl.stamp.tv_sec != stamp->tv_sec || - mip6_report_rl.stamp.tv_usec != stamp->tv_usec || + if (!ktime_equal(mip6_report_rl.stamp, stamp) || mip6_report_rl.iif != iif || !ipv6_addr_equal(&mip6_report_rl.src, src) || !ipv6_addr_equal(&mip6_report_rl.dst, dst)) { - mip6_report_rl.stamp.tv_sec = stamp->tv_sec; - mip6_report_rl.stamp.tv_usec = stamp->tv_usec; + mip6_report_rl.stamp = stamp; mip6_report_rl.iif = iif; mip6_report_rl.src = *src; mip6_report_rl.dst = *dst; @@ -216,7 +214,7 @@ static int mip6_destopt_reject(struct xfrm_state *x, struct sk_buff *skb, struct ipv6_destopt_hao *hao = NULL; struct xfrm_selector sel; int offset; - struct timeval stamp; + ktime_t stamp; int err = 0; if (unlikely(fl6->flowi6_proto == IPPROTO_MH && @@ -230,9 +228,9 @@ static int mip6_destopt_reject(struct xfrm_state *x, struct sk_buff *skb, (skb_network_header(skb) + offset); } - skb_get_timestamp(skb, &stamp); + stamp = skb_get_ktime(skb); - if (!mip6_report_rl_allow(&stamp, &ipv6_hdr(skb)->daddr, + if (!mip6_report_rl_allow(stamp, &ipv6_hdr(skb)->daddr, hao ? &hao->addr : &ipv6_hdr(skb)->saddr, opt->iif)) goto out; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 7089c305245c..3e0f855e1bea 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -67,6 +67,7 @@ #include <net/flow.h> #include <net/ip6_checksum.h> #include <net/inet_common.h> +#include <net/l3mdev.h> #include <linux/proc_fs.h> #include <linux/netfilter.h> @@ -147,6 +148,7 @@ struct neigh_table nd_tbl = { .gc_thresh2 = 512, .gc_thresh3 = 1024, }; +EXPORT_SYMBOL_GPL(nd_tbl); static void ndisc_fill_addr_option(struct sk_buff *skb, int type, void *data) { @@ -441,8 +443,11 @@ static void ndisc_send_skb(struct sk_buff *skb, if (!dst) { struct flowi6 fl6; + int oif = l3mdev_fib_oif(skb->dev); - icmpv6_flow_init(sk, &fl6, type, saddr, daddr, skb->dev->ifindex); + icmpv6_flow_init(sk, &fl6, type, saddr, daddr, oif); + if (oif != skb->dev->ifindex) + fl6.flowi6_flags |= FLOWI_FLAG_L3MDEV_SRC; dst = icmp6_dst_alloc(skb->dev, &fl6); if (IS_ERR(dst)) { kfree_skb(skb); @@ -465,7 +470,7 @@ static void ndisc_send_skb(struct sk_buff *skb, err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, dst->dev, - dst_output_okfn); + dst_output); if (!err) { ICMP6MSGOUT_INC_STATS(net, idev, type); ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); @@ -766,7 +771,7 @@ static void ndisc_recv_ns(struct sk_buff *skb) ifp = ipv6_get_ifaddr(dev_net(dev), &msg->target, dev, 1); if (ifp) { - +have_ifp: if (ifp->flags & (IFA_F_TENTATIVE|IFA_F_OPTIMISTIC)) { if (dad) { /* @@ -792,6 +797,18 @@ static void ndisc_recv_ns(struct sk_buff *skb) } else { struct net *net = dev_net(dev); + /* perhaps an address on the master device */ + if (netif_is_l3_slave(dev)) { + struct net_device *mdev; + + mdev = netdev_master_upper_dev_get_rcu(dev); + if (mdev) { + ifp = ipv6_get_ifaddr(net, &msg->target, mdev, 1); + if (ifp) + goto have_ifp; + } + } + idev = in6_dev_get(dev); if (!idev) { /* XXX: count this drop? */ @@ -1483,6 +1500,7 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) struct flowi6 fl6; int rd_len; u8 ha_buf[MAX_ADDR_LEN], *ha = NULL; + int oif = l3mdev_fib_oif(dev); bool ret; if (ipv6_get_lladdr(dev, &saddr_buf, IFA_F_TENTATIVE)) { @@ -1499,7 +1517,10 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) } icmpv6_flow_init(sk, &fl6, NDISC_REDIRECT, - &saddr_buf, &ipv6_hdr(skb)->saddr, dev->ifindex); + &saddr_buf, &ipv6_hdr(skb)->saddr, oif); + + if (oif != skb->dev->ifindex) + fl6.flowi6_flags |= FLOWI_FLAG_L3MDEV_SRC; dst = ip6_route_output(net, NULL, &fl6); if (dst->error) { diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c index 3426d9df1be7..3deed5860a42 100644 --- a/net/ipv6/netfilter/ip6t_SYNPROXY.c +++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c @@ -76,7 +76,7 @@ synproxy_send_tcp(const struct synproxy_net *snet, nf_conntrack_get(nfct); } - ip6_local_out(nskb); + ip6_local_out(net, nskb->sk, nskb); return; free_nskb: diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index deab0a1608d6..056f5d4a852a 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -563,12 +563,10 @@ find_prev_fhdr(struct sk_buff *skb, u8 *prevhdrp, int *prevhoff, int *fhoff) return 0; } -struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user) +struct sk_buff *nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) { struct sk_buff *clone; struct net_device *dev = skb->dev; - struct net *net = skb_dst(skb) ? dev_net(skb_dst(skb)->dev) - : dev_net(skb->dev); struct frag_hdr *fhdr; struct frag_queue *fq; struct ipv6hdr *hdr; diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c index b6ddca746109..4fdbed5ebfb6 100644 --- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c +++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c @@ -63,7 +63,8 @@ static unsigned int ipv6_defrag(void *priv, return NF_ACCEPT; #endif - reasm = nf_ct_frag6_gather(skb, nf_ct6_defrag_user(state->hook, skb)); + reasm = nf_ct_frag6_gather(state->net, skb, + nf_ct6_defrag_user(state->hook, skb)); /* queued */ if (reasm == NULL) return NF_STOLEN; diff --git a/net/ipv6/netfilter/nf_dup_ipv6.c b/net/ipv6/netfilter/nf_dup_ipv6.c index ee0d9a5b16c3..6989c70ae29f 100644 --- a/net/ipv6/netfilter/nf_dup_ipv6.c +++ b/net/ipv6/netfilter/nf_dup_ipv6.c @@ -68,7 +68,7 @@ void nf_dup_ipv6(struct net *net, struct sk_buff *skb, unsigned int hooknum, } if (nf_dup_ipv6_route(net, skb, gw, oif)) { __this_cpu_write(nf_skb_duplicated, true); - ip6_local_out(skb); + ip6_local_out(net, skb->sk, skb); __this_cpu_write(nf_skb_duplicated, false); } else { kfree_skb(skb); diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c index 5629db84c047..e0f922b777e3 100644 --- a/net/ipv6/netfilter/nf_reject_ipv6.c +++ b/net/ipv6/netfilter/nf_reject_ipv6.c @@ -206,7 +206,7 @@ void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook) dev_queue_xmit(nskb); } else #endif - ip6_local_out(nskb); + ip6_local_out(net, nskb->sk, nskb); } EXPORT_SYMBOL_GPL(nf_send_reset6); diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index e77102c4f804..462f2a76b5c2 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -138,9 +138,8 @@ int ip6_dst_hoplimit(struct dst_entry *dst) EXPORT_SYMBOL(ip6_dst_hoplimit); #endif -static int __ip6_local_out_sk(struct sock *sk, struct sk_buff *skb) +int __ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { - struct net *net = dev_net(skb_dst(skb)->dev); int len; len = skb->len - sizeof(struct ipv6hdr); @@ -151,29 +150,18 @@ static int __ip6_local_out_sk(struct sock *sk, struct sk_buff *skb) return nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb_dst(skb)->dev, - dst_output_okfn); -} - -int __ip6_local_out(struct sk_buff *skb) -{ - return __ip6_local_out_sk(skb->sk, skb); + dst_output); } EXPORT_SYMBOL_GPL(__ip6_local_out); -int ip6_local_out_sk(struct sock *sk, struct sk_buff *skb) +int ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { int err; - err = __ip6_local_out_sk(sk, skb); + err = __ip6_local_out(net, sk, skb); if (likely(err == 1)) - err = dst_output(sk, skb); + err = dst_output(net, sk, skb); return err; } -EXPORT_SYMBOL_GPL(ip6_local_out_sk); - -int ip6_local_out(struct sk_buff *skb) -{ - return ip6_local_out_sk(skb->sk, skb); -} EXPORT_SYMBOL_GPL(ip6_local_out); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index fec0151522a2..dc65ec198f7c 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -655,7 +655,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len); err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, - NULL, rt->dst.dev, dst_output_okfn); + NULL, rt->dst.dev, dst_output); if (err > 0) err = net_xmit_errno(err); if (err) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index d3d946773a3e..5fc1149fe91d 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -61,6 +61,7 @@ #include <net/nexthop.h> #include <net/lwtunnel.h> #include <net/ip_tunnels.h> +#include <net/l3mdev.h> #include <asm/uaccess.h> @@ -86,9 +87,9 @@ static void ip6_dst_ifdown(struct dst_entry *, static int ip6_dst_gc(struct dst_ops *ops); static int ip6_pkt_discard(struct sk_buff *skb); -static int ip6_pkt_discard_out(struct sock *sk, struct sk_buff *skb); +static int ip6_pkt_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb); static int ip6_pkt_prohibit(struct sk_buff *skb); -static int ip6_pkt_prohibit_out(struct sock *sk, struct sk_buff *skb); +static int ip6_pkt_prohibit_out(struct net *net, struct sock *sk, struct sk_buff *skb); static void ip6_link_failure(struct sk_buff *skb); static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu); @@ -308,7 +309,7 @@ static const struct rt6_info ip6_blk_hole_entry_template = { .obsolete = DST_OBSOLETE_FORCE_CHK, .error = -EINVAL, .input = dst_discard, - .output = dst_discard_sk, + .output = dst_discard_out, }, .rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP), .rt6i_protocol = RTPROT_KERNEL, @@ -1044,6 +1045,9 @@ static struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); saved_fn = fn; + if (fl6->flowi6_flags & FLOWI_FLAG_SKIP_NH_OIF) + oif = 0; + redo_rt6_select: rt = rt6_select(fn, oif, strict); if (rt->rt6i_nsiblings) @@ -1141,7 +1145,7 @@ void ip6_route_input(struct sk_buff *skb) int flags = RT6_LOOKUP_F_HAS_SADDR; struct ip_tunnel_info *tun_info; struct flowi6 fl6 = { - .flowi6_iif = skb->dev->ifindex, + .flowi6_iif = l3mdev_fib_oif(skb->dev), .daddr = iph->daddr, .saddr = iph->saddr, .flowlabel = ip6_flowinfo(iph), @@ -1165,8 +1169,13 @@ static struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk, struct flowi6 *fl6) { + struct dst_entry *dst; int flags = 0; + dst = l3mdev_rt6_dst_by_oif(net, fl6); + if (dst) + return dst; + fl6->flowi6_iif = LOOPBACK_IFINDEX; if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl6->daddr) || @@ -1195,7 +1204,7 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori new->__use = 1; new->input = dst_discard; - new->output = dst_discard_sk; + new->output = dst_discard_out; if (dst_metrics_read_only(&ort->dst)) new->_metrics = ort->dst._metrics; @@ -1724,21 +1733,21 @@ static int ip6_convert_metrics(struct mx6_config *mxc, return -EINVAL; } -int ip6_route_info_create(struct fib6_config *cfg, struct rt6_info **rt_ret) +static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg) { - int err; struct net *net = cfg->fc_nlinfo.nl_net; struct rt6_info *rt = NULL; struct net_device *dev = NULL; struct inet6_dev *idev = NULL; struct fib6_table *table; int addr_type; + int err = -EINVAL; if (cfg->fc_dst_len > 128 || cfg->fc_src_len > 128) - return -EINVAL; + goto out; #ifndef CONFIG_IPV6_SUBTREES if (cfg->fc_src_len) - return -EINVAL; + goto out; #endif if (cfg->fc_ifindex) { err = -ENODEV; @@ -1853,7 +1862,7 @@ int ip6_route_info_create(struct fib6_config *cfg, struct rt6_info **rt_ret) switch (cfg->fc_type) { case RTN_BLACKHOLE: rt->dst.error = -EINVAL; - rt->dst.output = dst_discard_sk; + rt->dst.output = dst_discard_out; rt->dst.input = dst_discard; break; case RTN_PROHIBIT: @@ -1958,9 +1967,7 @@ install_route: cfg->fc_nlinfo.nl_net = dev_net(dev); - *rt_ret = rt; - - return 0; + return rt; out: if (dev) dev_put(dev); @@ -1969,20 +1976,21 @@ out: if (rt) dst_free(&rt->dst); - *rt_ret = NULL; - - return err; + return ERR_PTR(err); } int ip6_route_add(struct fib6_config *cfg) { struct mx6_config mxc = { .mx = NULL, }; - struct rt6_info *rt = NULL; + struct rt6_info *rt; int err; - err = ip6_route_info_create(cfg, &rt); - if (err) + rt = ip6_route_info_create(cfg); + if (IS_ERR(rt)) { + err = PTR_ERR(rt); + rt = NULL; goto out; + } err = ip6_convert_metrics(&mxc, cfg); if (err) @@ -2264,7 +2272,6 @@ static struct rt6_info *rt6_add_route_info(struct net *net, unsigned int pref) { struct fib6_config cfg = { - .fc_table = RT6_TABLE_INFO, .fc_metric = IP6_RT_PRIO_USER, .fc_ifindex = ifindex, .fc_dst_len = prefixlen, @@ -2275,6 +2282,7 @@ static struct rt6_info *rt6_add_route_info(struct net *net, .fc_nlinfo.nl_net = net, }; + cfg.fc_table = l3mdev_fib_table_by_index(net, ifindex) ? : RT6_TABLE_INFO; cfg.fc_dst = *prefix; cfg.fc_gateway = *gwaddr; @@ -2315,7 +2323,7 @@ struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr, unsigned int pref) { struct fib6_config cfg = { - .fc_table = RT6_TABLE_DFLT, + .fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_DFLT, .fc_metric = IP6_RT_PRIO_USER, .fc_ifindex = dev->ifindex, .fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT | @@ -2362,7 +2370,8 @@ static void rtmsg_to_fib6_config(struct net *net, { memset(cfg, 0, sizeof(*cfg)); - cfg->fc_table = RT6_TABLE_MAIN; + cfg->fc_table = l3mdev_fib_table_by_index(net, rtmsg->rtmsg_ifindex) ? + : RT6_TABLE_MAIN; cfg->fc_ifindex = rtmsg->rtmsg_ifindex; cfg->fc_metric = rtmsg->rtmsg_metric; cfg->fc_expires = rtmsg->rtmsg_info; @@ -2446,7 +2455,7 @@ static int ip6_pkt_discard(struct sk_buff *skb) return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_INNOROUTES); } -static int ip6_pkt_discard_out(struct sock *sk, struct sk_buff *skb) +static int ip6_pkt_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb) { skb->dev = skb_dst(skb)->dev; return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_OUTNOROUTES); @@ -2457,7 +2466,7 @@ static int ip6_pkt_prohibit(struct sk_buff *skb) return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_INNOROUTES); } -static int ip6_pkt_prohibit_out(struct sock *sk, struct sk_buff *skb) +static int ip6_pkt_prohibit_out(struct net *net, struct sock *sk, struct sk_buff *skb) { skb->dev = skb_dst(skb)->dev; return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_OUTNOROUTES); @@ -2471,6 +2480,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, const struct in6_addr *addr, bool anycast) { + u32 tb_id; struct net *net = dev_net(idev->dev); struct rt6_info *rt = ip6_dst_alloc(net, net->loopback_dev, DST_NOCOUNT); @@ -2493,7 +2503,8 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, rt->rt6i_gateway = *addr; rt->rt6i_dst.addr = *addr; rt->rt6i_dst.plen = 128; - rt->rt6i_table = fib6_get_table(net, RT6_TABLE_LOCAL); + tb_id = l3mdev_fib_table(idev->dev) ? : RT6_TABLE_LOCAL; + rt->rt6i_table = fib6_get_table(net, tb_id); rt->dst.flags |= DST_NOCACHE; atomic_set(&rt->dst.__refcnt, 1); @@ -2871,9 +2882,12 @@ static int ip6_route_multipath_add(struct fib6_config *cfg) r_cfg.fc_encap_type = nla_get_u16(nla); } - err = ip6_route_info_create(&r_cfg, &rt); - if (err) + rt = ip6_route_info_create(&r_cfg); + if (IS_ERR(rt)) { + err = PTR_ERR(rt); + rt = NULL; goto cleanup; + } err = ip6_route_info_append(&rt6_nh_list, rt, &r_cfg); if (err) { @@ -3252,6 +3266,11 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh) } else { fl6.flowi6_oif = oif; + if (netif_index_is_l3_master(net, oif)) { + fl6.flowi6_flags = FLOWI_FLAG_L3MDEV_SRC | + FLOWI_FLAG_SKIP_NH_OIF; + } + rt = (struct rt6_info *)ip6_route_output(net, NULL, &fl6); } diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 7606eba83e7b..bb8f2fa1c7fb 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -170,7 +170,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) goto out; ret = NULL; - req = inet_reqsk_alloc(&tcp6_request_sock_ops, sk); + req = inet_reqsk_alloc(&tcp6_request_sock_ops, sk, false); if (!req) goto out; @@ -235,9 +235,9 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) goto out_free; } - req->window_clamp = tp->window_clamp ? :dst_metric(dst, RTAX_WINDOW); + req->rsk_window_clamp = tp->window_clamp ? :dst_metric(dst, RTAX_WINDOW); tcp_select_initial_window(tcp_full_space(sk), req->mss, - &req->rcv_wnd, &req->window_clamp, + &req->rsk_rcv_wnd, &req->rsk_window_clamp, ireq->wscale_ok, &rcv_wscale, dst_metric(dst, RTAX_INITRWND)); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 33334f0c217d..acb06f86f372 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -931,7 +931,7 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, */ tcp_v6_send_ack(sk, skb, (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt, - tcp_rsk(req)->rcv_nxt, req->rcv_wnd, + tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd, tcp_time_stamp, req->ts_recent, sk->sk_bound_dev_if, tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr), 0, 0); @@ -1363,6 +1363,7 @@ static int tcp_v6_rcv(struct sk_buff *skb) th = tcp_hdr(skb); hdr = ipv6_hdr(skb); +lookup: sk = __inet6_lookup_skb(&tcp_hashinfo, skb, th->source, th->dest, inet6_iif(skb)); if (!sk) @@ -1382,8 +1383,12 @@ process: reqsk_put(req); goto discard_it; } - if (sk->sk_state == TCP_LISTEN) + if (likely(sk->sk_state == TCP_LISTEN)) { nsk = tcp_check_req(sk, skb, req, false); + } else { + inet_csk_reqsk_queue_drop_and_put(sk, req); + goto lookup; + } if (!nsk) { reqsk_put(req); goto discard_it; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 0aba654f5b91..01bcb49619ee 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -182,10 +182,12 @@ static inline int compute_score(struct sock *sk, struct net *net, score++; } + if (sk->sk_incoming_cpu == raw_smp_processor_id()) + score++; + return score; } -#define SCORE2_MAX (1 + 1 + 1) static inline int compute_score2(struct sock *sk, struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, @@ -223,6 +225,9 @@ static inline int compute_score2(struct sock *sk, struct net *net, score++; } + if (sk->sk_incoming_cpu == raw_smp_processor_id()) + score++; + return score; } @@ -251,8 +256,7 @@ begin: hash = udp6_ehashfn(net, daddr, hnum, saddr, sport); matches = 1; - } else if (score == SCORE2_MAX) - goto exact_match; + } } else if (score == badness && reuseport) { matches++; if (reciprocal_scale(hash, matches) == 0) @@ -269,7 +273,6 @@ begin: goto begin; if (result) { -exact_match: if (unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2))) result = NULL; else if (unlikely(compute_score2(result, net, saddr, sport, diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 0c3e9ffcf231..9db067a11b52 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -131,6 +131,13 @@ int xfrm6_output_finish(struct sock *sk, struct sk_buff *skb) return xfrm_output(sk, skb); } +static int __xfrm6_output_finish(struct net *net, struct sock *sk, struct sk_buff *skb) +{ + struct xfrm_state *x = skb_dst(skb)->xfrm; + + return x->outer_mode->afinfo->output_finish(sk, skb); +} + static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); @@ -140,7 +147,7 @@ static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb) #ifdef CONFIG_NETFILTER if (!x) { IP6CB(skb)->flags |= IP6SKB_REROUTED; - return dst_output(sk, skb); + return dst_output(net, sk, skb); } #endif @@ -160,16 +167,14 @@ static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb) if (x->props.mode == XFRM_MODE_TUNNEL && ((skb->len > mtu && !skb_is_gso(skb)) || dst_allfrag(skb_dst(skb)))) { - return ip6_fragment(sk, skb, - x->outer_mode->afinfo->output_finish); + return ip6_fragment(net, sk, skb, + __xfrm6_output_finish); } return x->outer_mode->afinfo->output_finish(sk, skb); } -int xfrm6_output(struct sock *sk, struct sk_buff *skb) +int xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb) { - struct net *net = dev_net(skb_dst(skb)->dev); - return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, net, sk, skb, NULL, skb_dst(skb)->dev, __xfrm6_output, diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 69cee4e0d728..08c9c93f3527 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -37,6 +37,7 @@ static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos, int oif, memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_oif = oif; + fl6.flowi6_flags = FLOWI_FLAG_SKIP_NH_OIF; memcpy(&fl6.daddr, daddr, sizeof(fl6.daddr)); if (saddr) memcpy(&fl6.saddr, saddr, sizeof(fl6.saddr)); |