diff options
Diffstat (limited to 'net/ipv4')
-rw-r--r-- | net/ipv4/ip_gre.c | 5 | ||||
-rw-r--r-- | net/ipv4/ip_output.c | 3 | ||||
-rw-r--r-- | net/ipv4/ip_tunnel.c | 8 | ||||
-rw-r--r-- | net/ipv4/ip_vti.c | 1 | ||||
-rw-r--r-- | net/ipv4/netfilter/ipt_CLUSTERIP.c | 15 | ||||
-rw-r--r-- | net/ipv4/netfilter/nf_socket_ipv4.c | 6 | ||||
-rw-r--r-- | net/ipv4/ping.c | 7 | ||||
-rw-r--r-- | net/ipv4/route.c | 144 | ||||
-rw-r--r-- | net/ipv4/tcp.c | 3 | ||||
-rw-r--r-- | net/ipv4/tcp_bbr.c | 4 | ||||
-rw-r--r-- | net/ipv4/tcp_illinois.c | 2 | ||||
-rw-r--r-- | net/ipv4/tcp_output.c | 7 | ||||
-rw-r--r-- | net/ipv4/udp.c | 11 | ||||
-rw-r--r-- | net/ipv4/xfrm4_policy.c | 1 |
14 files changed, 119 insertions, 98 deletions
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 23e6d5532b5c..2459e9cc22a6 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -951,9 +951,6 @@ static void __gre_tunnel_init(struct net_device *dev) t_hlen = tunnel->hlen + sizeof(struct iphdr); - dev->needed_headroom = LL_MAX_HEADER + t_hlen + 4; - dev->mtu = ETH_DATA_LEN - t_hlen - 4; - dev->features |= GRE_FEATURES; dev->hw_features |= GRE_FEATURES; @@ -1253,8 +1250,6 @@ static int erspan_tunnel_init(struct net_device *dev) sizeof(struct erspanhdr); t_hlen = tunnel->hlen + sizeof(struct iphdr); - dev->needed_headroom = LL_MAX_HEADER + t_hlen + 4; - dev->mtu = ETH_DATA_LEN - t_hlen - 4; dev->features |= GRE_FEATURES; dev->hw_features |= GRE_FEATURES; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index e8e675be60ec..63d5d66e040a 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1040,7 +1040,8 @@ alloc_new_skb: if (copy > length) copy = length; - if (!(rt->dst.dev->features&NETIF_F_SG)) { + if (!(rt->dst.dev->features&NETIF_F_SG) && + skb_tailroom(skb) >= copy) { unsigned int off; off = skb->len; diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index a2fcc20774a6..4784f3f36b7e 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -1103,8 +1103,14 @@ int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[], eth_hw_addr_random(dev); mtu = ip_tunnel_bind_dev(dev); - if (!tb[IFLA_MTU]) + if (tb[IFLA_MTU]) { + unsigned int max = 0xfff8 - dev->hard_header_len - nt->hlen; + + dev->mtu = clamp(dev->mtu, (unsigned int)ETH_MIN_MTU, + (unsigned int)(max - sizeof(struct iphdr))); + } else { dev->mtu = mtu; + } ip_tunnel_add(itn, nt); out: diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index c9cd891f69c2..00d4371d4573 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -396,7 +396,6 @@ static int vti_tunnel_init(struct net_device *dev) memcpy(dev->dev_addr, &iph->saddr, 4); memcpy(dev->broadcast, &iph->daddr, 4); - dev->hard_header_len = LL_MAX_HEADER + sizeof(struct iphdr); dev->mtu = ETH_DATA_LEN; dev->flags = IFF_NOARP; dev->addr_len = 4; diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index c07e9db95ccc..cc7c9d67ac19 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -228,7 +228,6 @@ clusterip_config_init(struct net *net, const struct ipt_clusterip_tgt_info *i, c->hash_mode = i->hash_mode; c->hash_initval = i->hash_initval; refcount_set(&c->refcount, 1); - refcount_set(&c->entries, 1); spin_lock_bh(&cn->lock); if (__clusterip_config_find(net, ip)) { @@ -259,8 +258,10 @@ clusterip_config_init(struct net *net, const struct ipt_clusterip_tgt_info *i, c->notifier.notifier_call = clusterip_netdev_event; err = register_netdevice_notifier(&c->notifier); - if (!err) + if (!err) { + refcount_set(&c->entries, 1); return c; + } #ifdef CONFIG_PROC_FS proc_remove(c->pde); @@ -269,7 +270,7 @@ err: spin_lock_bh(&cn->lock); list_del_rcu(&c->list); spin_unlock_bh(&cn->lock); - kfree(c); + clusterip_config_put(c); return ERR_PTR(err); } @@ -492,12 +493,15 @@ static int clusterip_tg_check(const struct xt_tgchk_param *par) return PTR_ERR(config); } } - cipinfo->config = config; ret = nf_ct_netns_get(par->net, par->family); - if (ret < 0) + if (ret < 0) { pr_info("cannot load conntrack support for proto=%u\n", par->family); + clusterip_config_entry_put(par->net, config); + clusterip_config_put(config); + return ret; + } if (!par->net->xt.clusterip_deprecated_warning) { pr_info("ipt_CLUSTERIP is deprecated and it will removed soon, " @@ -505,6 +509,7 @@ static int clusterip_tg_check(const struct xt_tgchk_param *par) par->net->xt.clusterip_deprecated_warning = true; } + cipinfo->config = config; return ret; } diff --git a/net/ipv4/netfilter/nf_socket_ipv4.c b/net/ipv4/netfilter/nf_socket_ipv4.c index e9293bdebba0..4824b1e183a1 100644 --- a/net/ipv4/netfilter/nf_socket_ipv4.c +++ b/net/ipv4/netfilter/nf_socket_ipv4.c @@ -108,10 +108,12 @@ struct sock *nf_sk_lookup_slow_v4(struct net *net, const struct sk_buff *skb, int doff = 0; if (iph->protocol == IPPROTO_UDP || iph->protocol == IPPROTO_TCP) { - struct udphdr _hdr, *hp; + struct tcphdr _hdr; + struct udphdr *hp; hp = skb_header_pointer(skb, ip_hdrlen(skb), - sizeof(_hdr), &_hdr); + iph->protocol == IPPROTO_UDP ? + sizeof(*hp) : sizeof(_hdr), &_hdr); if (hp == NULL) return NULL; diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index b8f0db54b197..16226d49263d 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -775,8 +775,10 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ipc.addr = faddr = daddr; if (ipc.opt && ipc.opt->opt.srr) { - if (!daddr) - return -EINVAL; + if (!daddr) { + err = -EINVAL; + goto out_free; + } faddr = ipc.opt->opt.faddr; } tos = get_rttos(&ipc, inet); @@ -842,6 +844,7 @@ back_from_confirm: out: ip_rt_put(rt); +out_free: if (free) kfree(ipc.opt); if (!err) { diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 5ea559f8c456..7afa8d2463d8 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -639,6 +639,7 @@ static inline u32 fnhe_hashfun(__be32 daddr) static void fill_route_from_fnhe(struct rtable *rt, struct fib_nh_exception *fnhe) { rt->rt_pmtu = fnhe->fnhe_pmtu; + rt->rt_mtu_locked = fnhe->fnhe_mtu_locked; rt->dst.expires = fnhe->fnhe_expires; if (fnhe->fnhe_gw) { @@ -649,7 +650,7 @@ static void fill_route_from_fnhe(struct rtable *rt, struct fib_nh_exception *fnh } static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, - u32 pmtu, unsigned long expires) + u32 pmtu, bool lock, unsigned long expires) { struct fnhe_hash_bucket *hash; struct fib_nh_exception *fnhe; @@ -686,8 +687,10 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, fnhe->fnhe_genid = genid; if (gw) fnhe->fnhe_gw = gw; - if (pmtu) + if (pmtu) { fnhe->fnhe_pmtu = pmtu; + fnhe->fnhe_mtu_locked = lock; + } fnhe->fnhe_expires = max(1UL, expires); /* Update all cached dsts too */ rt = rcu_dereference(fnhe->fnhe_rth_input); @@ -711,7 +714,8 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, fnhe->fnhe_daddr = daddr; fnhe->fnhe_gw = gw; fnhe->fnhe_pmtu = pmtu; - fnhe->fnhe_expires = expires; + fnhe->fnhe_mtu_locked = lock; + fnhe->fnhe_expires = max(1UL, expires); /* Exception created; mark the cached routes for the nexthop * stale, so anyone caching it rechecks if this exception @@ -792,7 +796,8 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow struct fib_nh *nh = &FIB_RES_NH(res); update_or_create_fnhe(nh, fl4->daddr, new_gw, - 0, jiffies + ip_rt_gc_timeout); + 0, false, + jiffies + ip_rt_gc_timeout); } if (kill_route) rt->dst.obsolete = DST_OBSOLETE_KILL; @@ -1005,15 +1010,18 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) { struct dst_entry *dst = &rt->dst; struct fib_result res; + bool lock = false; - if (dst_metric_locked(dst, RTAX_MTU)) + if (ip_mtu_locked(dst)) return; if (ipv4_mtu(dst) < mtu) return; - if (mtu < ip_rt_min_pmtu) + if (mtu < ip_rt_min_pmtu) { + lock = true; mtu = ip_rt_min_pmtu; + } if (rt->rt_pmtu == mtu && time_before(jiffies, dst->expires - ip_rt_mtu_expires / 2)) @@ -1023,7 +1031,7 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) if (fib_lookup(dev_net(dst->dev), fl4, &res, 0) == 0) { struct fib_nh *nh = &FIB_RES_NH(res); - update_or_create_fnhe(nh, fl4->daddr, 0, mtu, + update_or_create_fnhe(nh, fl4->daddr, 0, mtu, lock, jiffies + ip_rt_mtu_expires); } rcu_read_unlock(); @@ -1276,7 +1284,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst) mtu = READ_ONCE(dst->dev->mtu); - if (unlikely(dst_metric_locked(dst, RTAX_MTU))) { + if (unlikely(ip_mtu_locked(dst))) { if (rt->rt_uses_gateway && mtu > 576) mtu = 576; } @@ -1286,6 +1294,36 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst) return mtu - lwtunnel_headroom(dst->lwtstate, mtu); } +static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr) +{ + struct fnhe_hash_bucket *hash; + struct fib_nh_exception *fnhe, __rcu **fnhe_p; + u32 hval = fnhe_hashfun(daddr); + + spin_lock_bh(&fnhe_lock); + + hash = rcu_dereference_protected(nh->nh_exceptions, + lockdep_is_held(&fnhe_lock)); + hash += hval; + + fnhe_p = &hash->chain; + fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock)); + while (fnhe) { + if (fnhe->fnhe_daddr == daddr) { + rcu_assign_pointer(*fnhe_p, rcu_dereference_protected( + fnhe->fnhe_next, lockdep_is_held(&fnhe_lock))); + fnhe_flush_routes(fnhe); + kfree_rcu(fnhe, rcu); + break; + } + fnhe_p = &fnhe->fnhe_next; + fnhe = rcu_dereference_protected(fnhe->fnhe_next, + lockdep_is_held(&fnhe_lock)); + } + + spin_unlock_bh(&fnhe_lock); +} + static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr) { struct fnhe_hash_bucket *hash = rcu_dereference(nh->nh_exceptions); @@ -1299,8 +1337,14 @@ static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr) for (fnhe = rcu_dereference(hash[hval].chain); fnhe; fnhe = rcu_dereference(fnhe->fnhe_next)) { - if (fnhe->fnhe_daddr == daddr) + if (fnhe->fnhe_daddr == daddr) { + if (fnhe->fnhe_expires && + time_after(jiffies, fnhe->fnhe_expires)) { + ip_del_fnhe(nh, daddr); + break; + } return fnhe; + } } return NULL; } @@ -1512,6 +1556,7 @@ struct rtable *rt_dst_alloc(struct net_device *dev, rt->rt_is_input = 0; rt->rt_iif = 0; rt->rt_pmtu = 0; + rt->rt_mtu_locked = 0; rt->rt_gateway = 0; rt->rt_uses_gateway = 0; rt->rt_table_id = 0; @@ -1620,36 +1665,6 @@ static void ip_handle_martian_source(struct net_device *dev, #endif } -static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr) -{ - struct fnhe_hash_bucket *hash; - struct fib_nh_exception *fnhe, __rcu **fnhe_p; - u32 hval = fnhe_hashfun(daddr); - - spin_lock_bh(&fnhe_lock); - - hash = rcu_dereference_protected(nh->nh_exceptions, - lockdep_is_held(&fnhe_lock)); - hash += hval; - - fnhe_p = &hash->chain; - fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock)); - while (fnhe) { - if (fnhe->fnhe_daddr == daddr) { - rcu_assign_pointer(*fnhe_p, rcu_dereference_protected( - fnhe->fnhe_next, lockdep_is_held(&fnhe_lock))); - fnhe_flush_routes(fnhe); - kfree_rcu(fnhe, rcu); - break; - } - fnhe_p = &fnhe->fnhe_next; - fnhe = rcu_dereference_protected(fnhe->fnhe_next, - lockdep_is_held(&fnhe_lock)); - } - - spin_unlock_bh(&fnhe_lock); -} - static void set_lwt_redirect(struct rtable *rth) { if (lwtunnel_output_redirect(rth->dst.lwtstate)) { @@ -1716,20 +1731,10 @@ static int __mkroute_input(struct sk_buff *skb, fnhe = find_exception(&FIB_RES_NH(*res), daddr); if (do_cache) { - if (fnhe) { + if (fnhe) rth = rcu_dereference(fnhe->fnhe_rth_input); - if (rth && rth->dst.expires && - time_after(jiffies, rth->dst.expires)) { - ip_del_fnhe(&FIB_RES_NH(*res), daddr); - fnhe = NULL; - } else { - goto rt_cache; - } - } - - rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input); - -rt_cache: + else + rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input); if (rt_cache_valid(rth)) { skb_dst_set_noref(skb, &rth->dst); goto out; @@ -2206,39 +2211,31 @@ static struct rtable *__mkroute_output(const struct fib_result *res, * the loopback interface and the IP_PKTINFO ipi_ifindex will * be set to the loopback interface as well. */ - fi = NULL; + do_cache = false; } fnhe = NULL; do_cache &= fi != NULL; - if (do_cache) { + if (fi) { struct rtable __rcu **prth; struct fib_nh *nh = &FIB_RES_NH(*res); fnhe = find_exception(nh, fl4->daddr); + if (!do_cache) + goto add; if (fnhe) { prth = &fnhe->fnhe_rth_output; - rth = rcu_dereference(*prth); - if (rth && rth->dst.expires && - time_after(jiffies, rth->dst.expires)) { - ip_del_fnhe(nh, fl4->daddr); - fnhe = NULL; - } else { - goto rt_cache; + } else { + if (unlikely(fl4->flowi4_flags & + FLOWI_FLAG_KNOWN_NH && + !(nh->nh_gw && + nh->nh_scope == RT_SCOPE_LINK))) { + do_cache = false; + goto add; } + prth = raw_cpu_ptr(nh->nh_pcpu_rth_output); } - - if (unlikely(fl4->flowi4_flags & - FLOWI_FLAG_KNOWN_NH && - !(nh->nh_gw && - nh->nh_scope == RT_SCOPE_LINK))) { - do_cache = false; - goto add; - } - prth = raw_cpu_ptr(nh->nh_pcpu_rth_output); rth = rcu_dereference(*prth); - -rt_cache: if (rt_cache_valid(rth) && dst_hold_safe(&rth->dst)) return rth; } @@ -2538,6 +2535,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or rt->rt_is_input = ort->rt_is_input; rt->rt_iif = ort->rt_iif; rt->rt_pmtu = ort->rt_pmtu; + rt->rt_mtu_locked = ort->rt_mtu_locked; rt->rt_genid = rt_genid_ipv4(net); rt->rt_flags = ort->rt_flags; @@ -2640,6 +2638,8 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, u32 table_id, memcpy(metrics, dst_metrics_ptr(&rt->dst), sizeof(metrics)); if (rt->rt_pmtu && expires) metrics[RTAX_MTU - 1] = rt->rt_pmtu; + if (rt->rt_mtu_locked && expires) + metrics[RTAX_LOCK - 1] |= BIT(RTAX_MTU); if (rtnetlink_put_metrics(skb, metrics) < 0) goto nla_put_failure; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index b694fbf44a35..e3ece12f0250 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1194,7 +1194,8 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) uarg->zerocopy = 0; } - if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect)) { + if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect) && + !tp->repair) { err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size); if (err == -EINPROGRESS && copied_syn > 0) goto out; diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 25c5a0b60cfc..9a0b952dd09b 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -802,7 +802,9 @@ static void bbr_update_min_rtt(struct sock *sk, const struct rate_sample *rs) } } } - bbr->idle_restart = 0; + /* Restart after idle ends only once we process a new S/ACK for data */ + if (rs->delivered > 0) + bbr->idle_restart = 0; } static void bbr_update_model(struct sock *sk, const struct rate_sample *rs) diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c index 7c843578f233..faddf4f9a707 100644 --- a/net/ipv4/tcp_illinois.c +++ b/net/ipv4/tcp_illinois.c @@ -6,7 +6,7 @@ * The algorithm is described in: * "TCP-Illinois: A Loss and Delay-Based Congestion Control Algorithm * for High-Speed Networks" - * http://www.ifp.illinois.edu/~srikant/Papers/liubassri06perf.pdf + * http://tamerbasar.csl.illinois.edu/LiuBasarSrikantPerfEvalArtJun2008.pdf * * Implemented from description in paper and ns-2 simulation. * Copyright (C) 2007 Stephen Hemminger <shemminger@linux-foundation.org> diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 83d11cd2eb65..abae5196cd3a 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2814,8 +2814,10 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) return -EBUSY; if (before(TCP_SKB_CB(skb)->seq, tp->snd_una)) { - if (before(TCP_SKB_CB(skb)->end_seq, tp->snd_una)) - BUG(); + if (unlikely(before(TCP_SKB_CB(skb)->end_seq, tp->snd_una))) { + WARN_ON_ONCE(1); + return -EINVAL; + } if (tcp_trim_head(sk, skb, tp->snd_una - TCP_SKB_CB(skb)->seq)) return -ENOMEM; } @@ -3312,6 +3314,7 @@ static void tcp_connect_init(struct sock *sk) sock_reset_flag(sk, SOCK_DONE); tp->snd_wnd = 0; tcp_init_wl(tp, 0); + tcp_write_queue_purge(sk); tp->snd_una = tp->write_seq; tp->snd_sml = tp->write_seq; tp->snd_up = tp->write_seq; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index c79fa6f6b758..b0ad62bd38f7 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -413,9 +413,9 @@ static int compute_score(struct sock *sk, struct net *net, bool dev_match = (sk->sk_bound_dev_if == dif || sk->sk_bound_dev_if == sdif); - if (exact_dif && !dev_match) + if (!dev_match) return -1; - if (sk->sk_bound_dev_if && dev_match) + if (sk->sk_bound_dev_if) score += 4; } @@ -978,8 +978,10 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) sock_tx_timestamp(sk, ipc.sockc.tsflags, &ipc.tx_flags); if (ipc.opt && ipc.opt->opt.srr) { - if (!daddr) - return -EINVAL; + if (!daddr) { + err = -EINVAL; + goto out_free; + } faddr = ipc.opt->opt.faddr; connected = 0; } @@ -1087,6 +1089,7 @@ do_append_data: out: ip_rt_put(rt); +out_free: if (free) kfree(ipc.opt); if (!err) diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 05017e2c849c..4b586e7d5637 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -100,6 +100,7 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, xdst->u.rt.rt_gateway = rt->rt_gateway; xdst->u.rt.rt_uses_gateway = rt->rt_uses_gateway; xdst->u.rt.rt_pmtu = rt->rt_pmtu; + xdst->u.rt.rt_mtu_locked = rt->rt_mtu_locked; xdst->u.rt.rt_table_id = rt->rt_table_id; INIT_LIST_HEAD(&xdst->u.rt.rt_uncached); |