diff options
author | Pablo Neira Ayuso <pablo@netfilter.org> | 2015-10-17 12:11:08 (GMT) |
---|---|---|
committer | Pablo Neira Ayuso <pablo@netfilter.org> | 2015-10-17 12:28:03 (GMT) |
commit | f0a0a978b66fea782a52b0a7075b3fa9ab27ad0a (patch) | |
tree | 52ecc0eafbac697c6afaa542efe324984484120c /net/ipv4 | |
parent | c8d71d08aa23679f56e7072358383442c6ede352 (diff) | |
parent | 4be3158abe1e02d24f82b34101e41d662fae2185 (diff) | |
download | linux-f0a0a978b66fea782a52b0a7075b3fa9ab27ad0a.tar.xz |
Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
This merge resolves conflicts with 75aec9df3a78 ("bridge: Remove
br_nf_push_frag_xmit_sk") as part of Eric Biederman's effort to improve
netns support in the network stack that reached upstream via David's
net-next tree.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Conflicts:
net/bridge/br_netfilter_hooks.c
Diffstat (limited to 'net/ipv4')
-rw-r--r-- | net/ipv4/fib_semantics.c | 161 | ||||
-rw-r--r-- | net/ipv4/icmp.c | 19 | ||||
-rw-r--r-- | net/ipv4/igmp.c | 4 | ||||
-rw-r--r-- | net/ipv4/inet_connection_sock.c | 87 | ||||
-rw-r--r-- | net/ipv4/inet_hashtables.c | 6 | ||||
-rw-r--r-- | net/ipv4/ip_forward.c | 2 | ||||
-rw-r--r-- | net/ipv4/ip_fragment.c | 7 | ||||
-rw-r--r-- | net/ipv4/ip_input.c | 10 | ||||
-rw-r--r-- | net/ipv4/ip_output.c | 86 | ||||
-rw-r--r-- | net/ipv4/ip_tunnel_core.c | 6 | ||||
-rw-r--r-- | net/ipv4/ip_vti.c | 2 | ||||
-rw-r--r-- | net/ipv4/ipmr.c | 2 | ||||
-rw-r--r-- | net/ipv4/netfilter/ipt_SYNPROXY.c | 2 | ||||
-rw-r--r-- | net/ipv4/netfilter/nf_defrag_ipv4.c | 7 | ||||
-rw-r--r-- | net/ipv4/netfilter/nf_dup_ipv4.c | 2 | ||||
-rw-r--r-- | net/ipv4/netfilter/nf_reject_ipv4.c | 2 | ||||
-rw-r--r-- | net/ipv4/raw.c | 10 | ||||
-rw-r--r-- | net/ipv4/route.c | 81 | ||||
-rw-r--r-- | net/ipv4/syncookies.c | 7 | ||||
-rw-r--r-- | net/ipv4/tcp.c | 24 | ||||
-rw-r--r-- | net/ipv4/tcp_fastopen.c | 26 | ||||
-rw-r--r-- | net/ipv4/tcp_input.c | 16 | ||||
-rw-r--r-- | net/ipv4/tcp_ipv4.c | 13 | ||||
-rw-r--r-- | net/ipv4/tcp_minisocks.c | 19 | ||||
-rw-r--r-- | net/ipv4/tcp_output.c | 2 | ||||
-rw-r--r-- | net/ipv4/tcp_timer.c | 6 | ||||
-rw-r--r-- | net/ipv4/udp.c | 28 | ||||
-rw-r--r-- | net/ipv4/xfrm4_output.c | 6 |
28 files changed, 382 insertions, 261 deletions
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 064bd3c..42778d9 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -57,8 +57,7 @@ static unsigned int fib_info_cnt; static struct hlist_head fib_info_devhash[DEVINDEX_HASHSIZE]; #ifdef CONFIG_IP_ROUTE_MULTIPATH - -static DEFINE_SPINLOCK(fib_multipath_lock); +u32 fib_multipath_secret __read_mostly; #define for_nexthops(fi) { \ int nhsel; const struct fib_nh *nh; \ @@ -532,7 +531,67 @@ errout: return ret; } -#endif +static void fib_rebalance(struct fib_info *fi) +{ + int total; + int w; + struct in_device *in_dev; + + if (fi->fib_nhs < 2) + return; + + total = 0; + for_nexthops(fi) { + if (nh->nh_flags & RTNH_F_DEAD) + continue; + + in_dev = __in_dev_get_rtnl(nh->nh_dev); + + if (in_dev && + IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) && + nh->nh_flags & RTNH_F_LINKDOWN) + continue; + + total += nh->nh_weight; + } endfor_nexthops(fi); + + w = 0; + change_nexthops(fi) { + int upper_bound; + + in_dev = __in_dev_get_rtnl(nexthop_nh->nh_dev); + + if (nexthop_nh->nh_flags & RTNH_F_DEAD) { + upper_bound = -1; + } else if (in_dev && + IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) && + nexthop_nh->nh_flags & RTNH_F_LINKDOWN) { + upper_bound = -1; + } else { + w += nexthop_nh->nh_weight; + upper_bound = DIV_ROUND_CLOSEST_ULL((u64)w << 31, + total) - 1; + } + + atomic_set(&nexthop_nh->nh_upper_bound, upper_bound); + } endfor_nexthops(fi); + + net_get_random_once(&fib_multipath_secret, + sizeof(fib_multipath_secret)); +} + +static inline void fib_add_weight(struct fib_info *fi, + const struct fib_nh *nh) +{ + fi->fib_weight += nh->nh_weight; +} + +#else /* CONFIG_IP_ROUTE_MULTIPATH */ + +#define fib_rebalance(fi) do { } while (0) +#define fib_add_weight(fi, nh) do { } while (0) + +#endif /* CONFIG_IP_ROUTE_MULTIPATH */ static int fib_encap_match(struct net *net, u16 encap_type, struct nlattr *encap, @@ -1094,8 +1153,11 @@ struct fib_info *fib_create_info(struct fib_config *cfg) change_nexthops(fi) { fib_info_update_nh_saddr(net, nexthop_nh); + fib_add_weight(fi, nexthop_nh); } endfor_nexthops(fi) + fib_rebalance(fi); + link_it: ofi = fib_find_info(fi); if (ofi) { @@ -1317,12 +1379,6 @@ int fib_sync_down_dev(struct net_device *dev, unsigned long event) nexthop_nh->nh_flags |= RTNH_F_LINKDOWN; break; } -#ifdef CONFIG_IP_ROUTE_MULTIPATH - spin_lock_bh(&fib_multipath_lock); - fi->fib_power -= nexthop_nh->nh_power; - nexthop_nh->nh_power = 0; - spin_unlock_bh(&fib_multipath_lock); -#endif dead++; } #ifdef CONFIG_IP_ROUTE_MULTIPATH @@ -1345,6 +1401,8 @@ int fib_sync_down_dev(struct net_device *dev, unsigned long event) } ret++; } + + fib_rebalance(fi); } return ret; @@ -1467,20 +1525,15 @@ int fib_sync_up(struct net_device *dev, unsigned int nh_flags) !__in_dev_get_rtnl(dev)) continue; alive++; -#ifdef CONFIG_IP_ROUTE_MULTIPATH - spin_lock_bh(&fib_multipath_lock); - nexthop_nh->nh_power = 0; nexthop_nh->nh_flags &= ~nh_flags; - spin_unlock_bh(&fib_multipath_lock); -#else - nexthop_nh->nh_flags &= ~nh_flags; -#endif } endfor_nexthops(fi) if (alive > 0) { fi->fib_flags &= ~nh_flags; ret++; } + + fib_rebalance(fi); } return ret; @@ -1488,62 +1541,40 @@ int fib_sync_up(struct net_device *dev, unsigned int nh_flags) #ifdef CONFIG_IP_ROUTE_MULTIPATH -/* - * The algorithm is suboptimal, but it provides really - * fair weighted route distribution. - */ -void fib_select_multipath(struct fib_result *res) +void fib_select_multipath(struct fib_result *res, int hash) { struct fib_info *fi = res->fi; - struct in_device *in_dev; - int w; - - spin_lock_bh(&fib_multipath_lock); - if (fi->fib_power <= 0) { - int power = 0; - change_nexthops(fi) { - in_dev = __in_dev_get_rcu(nexthop_nh->nh_dev); - if (nexthop_nh->nh_flags & RTNH_F_DEAD) - continue; - if (in_dev && - IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) && - nexthop_nh->nh_flags & RTNH_F_LINKDOWN) - continue; - power += nexthop_nh->nh_weight; - nexthop_nh->nh_power = nexthop_nh->nh_weight; - } endfor_nexthops(fi); - fi->fib_power = power; - if (power <= 0) { - spin_unlock_bh(&fib_multipath_lock); - /* Race condition: route has just become dead. */ - res->nh_sel = 0; - return; - } - } - - /* w should be random number [0..fi->fib_power-1], - * it is pretty bad approximation. - */ - - w = jiffies % fi->fib_power; + for_nexthops(fi) { + if (hash > atomic_read(&nh->nh_upper_bound)) + continue; - change_nexthops(fi) { - if (!(nexthop_nh->nh_flags & RTNH_F_DEAD) && - nexthop_nh->nh_power) { - w -= nexthop_nh->nh_power; - if (w <= 0) { - nexthop_nh->nh_power--; - fi->fib_power--; - res->nh_sel = nhsel; - spin_unlock_bh(&fib_multipath_lock); - return; - } - } + res->nh_sel = nhsel; + return; } endfor_nexthops(fi); /* Race condition: route has just become dead. */ res->nh_sel = 0; - spin_unlock_bh(&fib_multipath_lock); } #endif + +void fib_select_path(struct net *net, struct fib_result *res, + struct flowi4 *fl4, int mp_hash) +{ +#ifdef CONFIG_IP_ROUTE_MULTIPATH + if (res->fi->fib_nhs > 1 && fl4->flowi4_oif == 0) { + if (mp_hash < 0) + mp_hash = fib_multipath_hash(fl4->saddr, fl4->daddr); + fib_select_multipath(res, mp_hash); + } + else +#endif + if (!res->prefixlen && + res->table->tb_num_default > 1 && + res->type == RTN_UNICAST && !fl4->flowi4_oif) + fib_select_default(fl4, res); + + if (!fl4->saddr) + fl4->saddr = FIB_RES_PREFSRC(net, *res); +} +EXPORT_SYMBOL_GPL(fib_select_path); diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 6b96dee..36e2697 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -440,6 +440,22 @@ out_unlock: icmp_xmit_unlock(sk); } +#ifdef CONFIG_IP_ROUTE_MULTIPATH + +/* Source and destination is swapped. See ip_multipath_icmp_hash */ +static int icmp_multipath_hash_skb(const struct sk_buff *skb) +{ + const struct iphdr *iph = ip_hdr(skb); + + return fib_multipath_hash(iph->daddr, iph->saddr); +} + +#else + +#define icmp_multipath_hash_skb(skb) (-1) + +#endif + static struct rtable *icmp_route_lookup(struct net *net, struct flowi4 *fl4, struct sk_buff *skb_in, @@ -464,7 +480,8 @@ static struct rtable *icmp_route_lookup(struct net *net, fl4->flowi4_oif = l3mdev_master_ifindex(skb_in->dev); security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4)); - rt = __ip_route_output_key(net, fl4); + rt = __ip_route_output_key_hash(net, fl4, + icmp_multipath_hash_skb(skb_in)); if (IS_ERR(rt)) return rt; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index de6d4c8..64aaf35 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -397,7 +397,7 @@ static int igmpv3_sendpack(struct sk_buff *skb) pig->csum = ip_compute_csum(igmp_hdr(skb), igmplen); - return ip_local_out(skb); + return ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb); } static int grec_size(struct ip_mc_list *pmc, int type, int gdel, int sdel) @@ -739,7 +739,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, ih->group = group; ih->csum = ip_compute_csum((void *)ih, sizeof(struct igmphdr)); - return ip_local_out(skb); + return ip_local_out(net, skb->sk, skb); } static void igmp_gq_timer_expire(unsigned long data) diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 89eedfb..8430bc8 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -546,6 +546,13 @@ void inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req) } EXPORT_SYMBOL(inet_csk_reqsk_queue_drop); +void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req) +{ + inet_csk_reqsk_queue_drop(sk, req); + reqsk_put(req); +} +EXPORT_SYMBOL(inet_csk_reqsk_queue_drop_and_put); + static void reqsk_timer_handler(unsigned long data) { struct request_sock *req = (struct request_sock *)data; @@ -579,7 +586,7 @@ static void reqsk_timer_handler(unsigned long data) * ones are about to clog our table. */ qlen = reqsk_queue_len(queue); - if ((qlen << 1) > sk_listener->sk_max_ack_backlog) { + if ((qlen << 1) > max(8U, sk_listener->sk_max_ack_backlog)) { int young = reqsk_queue_len_young(queue) << 1; while (thresh > 2) { @@ -608,8 +615,7 @@ static void reqsk_timer_handler(unsigned long data) return; } drop: - inet_csk_reqsk_queue_drop(sk_listener, req); - reqsk_put(req); + inet_csk_reqsk_queue_drop_and_put(sk_listener, req); } static void reqsk_queue_hash_req(struct request_sock *req, @@ -727,14 +733,14 @@ void inet_csk_prepare_forced_close(struct sock *sk) } EXPORT_SYMBOL(inet_csk_prepare_forced_close); -int inet_csk_listen_start(struct sock *sk, const int nr_table_entries) +int inet_csk_listen_start(struct sock *sk, int backlog) { struct inet_connection_sock *icsk = inet_csk(sk); struct inet_sock *inet = inet_sk(sk); reqsk_queue_alloc(&icsk->icsk_accept_queue); - sk->sk_max_ack_backlog = 0; + sk->sk_max_ack_backlog = backlog; sk->sk_ack_backlog = 0; inet_csk_delack_init(sk); @@ -758,6 +764,53 @@ int inet_csk_listen_start(struct sock *sk, const int nr_table_entries) } EXPORT_SYMBOL_GPL(inet_csk_listen_start); +static void inet_child_forget(struct sock *sk, struct request_sock *req, + struct sock *child) +{ + sk->sk_prot->disconnect(child, O_NONBLOCK); + + sock_orphan(child); + + percpu_counter_inc(sk->sk_prot->orphan_count); + + if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(req)->tfo_listener) { + BUG_ON(tcp_sk(child)->fastopen_rsk != req); + BUG_ON(sk != req->rsk_listener); + + /* Paranoid, to prevent race condition if + * an inbound pkt destined for child is + * blocked by sock lock in tcp_v4_rcv(). + * Also to satisfy an assertion in + * tcp_v4_destroy_sock(). + */ + tcp_sk(child)->fastopen_rsk = NULL; + } + inet_csk_destroy_sock(child); + reqsk_put(req); +} + +void inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req, + struct sock *child) +{ + struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; + + spin_lock(&queue->rskq_lock); + if (unlikely(sk->sk_state != TCP_LISTEN)) { + inet_child_forget(sk, req, child); + } else { + req->sk = child; + req->dl_next = NULL; + if (queue->rskq_accept_head == NULL) + queue->rskq_accept_head = req; + else + queue->rskq_accept_tail->dl_next = req; + queue->rskq_accept_tail = req; + sk_acceptq_added(sk); + } + spin_unlock(&queue->rskq_lock); +} +EXPORT_SYMBOL(inet_csk_reqsk_queue_add); + /* * This routine closes sockets which have been at least partially * opened, but not yet accepted. @@ -784,31 +837,11 @@ void inet_csk_listen_stop(struct sock *sk) WARN_ON(sock_owned_by_user(child)); sock_hold(child); - sk->sk_prot->disconnect(child, O_NONBLOCK); - - sock_orphan(child); - - percpu_counter_inc(sk->sk_prot->orphan_count); - - if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(req)->tfo_listener) { - BUG_ON(tcp_sk(child)->fastopen_rsk != req); - BUG_ON(sk != req->rsk_listener); - - /* Paranoid, to prevent race condition if - * an inbound pkt destined for child is - * blocked by sock lock in tcp_v4_rcv(). - * Also to satisfy an assertion in - * tcp_v4_destroy_sock(). - */ - tcp_sk(child)->fastopen_rsk = NULL; - } - inet_csk_destroy_sock(child); - + inet_child_forget(sk, req, child); bh_unlock_sock(child); local_bh_enable(); sock_put(child); - reqsk_put(req); cond_resched(); } if (queue->fastopenq.rskq_rst_head) { @@ -823,7 +856,7 @@ void inet_csk_listen_stop(struct sock *sk) req = next; } } - WARN_ON(sk->sk_ack_backlog); + WARN_ON_ONCE(sk->sk_ack_backlog); } EXPORT_SYMBOL_GPL(inet_csk_listen_stop); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index bed8886..958728a 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -137,6 +137,10 @@ int __inet_inherit_port(const struct sock *sk, struct sock *child) spin_lock(&head->lock); tb = inet_csk(sk)->icsk_bind_hash; + if (unlikely(!tb)) { + spin_unlock(&head->lock); + return -ENOENT; + } if (tb->port != port) { /* NOTE: using tproxy and redirecting skbs to a proxy * on a different listener port breaks the assumption @@ -185,6 +189,8 @@ static inline int compute_score(struct sock *sk, struct net *net, return -1; score += 4; } + if (sk->sk_incoming_cpu == raw_smp_processor_id()) + score++; } return score; } diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index d66cfb3..da0d7ce 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -72,7 +72,7 @@ static int ip_forward_finish(struct net *net, struct sock *sk, struct sk_buff *s ip_forward_options(skb); skb_sender_cpu_clear(skb); - return dst_output(sk, skb); + return dst_output(net, sk, skb); } int ip_forward(struct sk_buff *skb) diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 9772b78..5482745 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -654,11 +654,10 @@ out_fail: } /* Process an incoming IP datagram fragment. */ -int ip_defrag(struct sk_buff *skb, u32 user) +int ip_defrag(struct net *net, struct sk_buff *skb, u32 user) { struct net_device *dev = skb->dev ? : skb_dst(skb)->dev; int vif = l3mdev_master_ifindex_rcu(dev); - struct net *net = dev_net(dev); struct ipq *qp; IP_INC_STATS_BH(net, IPSTATS_MIB_REASMREQDS); @@ -683,7 +682,7 @@ int ip_defrag(struct sk_buff *skb, u32 user) } EXPORT_SYMBOL(ip_defrag); -struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user) +struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user) { struct iphdr iph; int netoff; @@ -712,7 +711,7 @@ struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user) if (pskb_trim_rcsum(skb, netoff + len)) return skb; memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); - if (ip_defrag(skb, user)) + if (ip_defrag(net, skb, user)) return NULL; skb_clear_hash(skb); } diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 7cc9f7b..b1209b6 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -157,6 +157,7 @@ bool ip_call_ra_chain(struct sk_buff *skb) u8 protocol = ip_hdr(skb)->protocol; struct sock *last = NULL; struct net_device *dev = skb->dev; + struct net *net = dev_net(dev); for (ra = rcu_dereference(ip_ra_chain); ra; ra = rcu_dereference(ra->next)) { struct sock *sk = ra->sk; @@ -167,9 +168,9 @@ bool ip_call_ra_chain(struct sk_buff *skb) if (sk && inet_sk(sk)->inet_num == protocol && (!sk->sk_bound_dev_if || sk->sk_bound_dev_if == dev->ifindex) && - net_eq(sock_net(sk), dev_net(dev))) { + net_eq(sock_net(sk), net)) { if (ip_is_fragment(ip_hdr(skb))) { - if (ip_defrag(skb, IP_DEFRAG_CALL_RA_CHAIN)) + if (ip_defrag(net, skb, IP_DEFRAG_CALL_RA_CHAIN)) return true; } if (last) { @@ -246,14 +247,15 @@ int ip_local_deliver(struct sk_buff *skb) /* * Reassemble IP fragments. */ + struct net *net = dev_net(skb->dev); if (ip_is_fragment(ip_hdr(skb))) { - if (ip_defrag(skb, IP_DEFRAG_LOCAL_DELIVER)) + if (ip_defrag(net, skb, IP_DEFRAG_LOCAL_DELIVER)) return 0; } return NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_IN, - dev_net(skb->dev), NULL, skb, skb->dev, NULL, + net, NULL, skb, skb->dev, NULL, ip_local_deliver_finish); } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index aff6766..67404e1 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -83,9 +83,10 @@ int sysctl_ip_default_ttl __read_mostly = IPDEFTTL; EXPORT_SYMBOL(sysctl_ip_default_ttl); -static int ip_fragment(struct sock *sk, struct sk_buff *skb, - unsigned int mtu, - int (*output)(struct sock *, struct sk_buff *)); +static int +ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, + unsigned int mtu, + int (*output)(struct net *, struct sock *, struct sk_buff *)); /* Generate a checksum for an outgoing IP datagram. */ void ip_send_check(struct iphdr *iph) @@ -95,34 +96,28 @@ void ip_send_check(struct iphdr *iph) } EXPORT_SYMBOL(ip_send_check); -static int __ip_local_out_sk(struct sock *sk, struct sk_buff *skb) +int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { - struct net *net = dev_net(skb_dst(skb)->dev); struct iphdr *iph = ip_hdr(skb); iph->tot_len = htons(skb->len); ip_send_check(iph); return nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb_dst(skb)->dev, - dst_output_okfn); -} - -int __ip_local_out(struct sk_buff *skb) -{ - return __ip_local_out_sk(skb->sk, skb); + dst_output); } -int ip_local_out_sk(struct sock *sk, struct sk_buff *skb) +int ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { int err; - err = __ip_local_out(skb); + err = __ip_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(ip_local_out_sk); +EXPORT_SYMBOL_GPL(ip_local_out); static inline int ip_select_ttl(struct inet_sock *inet, struct dst_entry *dst) { @@ -142,6 +137,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, { struct inet_sock *inet = inet_sk(sk); struct rtable *rt = skb_rtable(skb); + struct net *net = sock_net(sk); struct iphdr *iph; /* Build the IP header. */ @@ -160,7 +156,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, iph->id = 0; } else { iph->frag_off = 0; - __ip_select_ident(sock_net(sk), iph, 1); + __ip_select_ident(net, iph, 1); } if (opt && opt->opt.optlen) { @@ -172,16 +168,15 @@ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, skb->mark = sk->sk_mark; /* Send it out. */ - return ip_local_out(skb); + return ip_local_out(net, skb->sk, skb); } EXPORT_SYMBOL_GPL(ip_build_and_send_pkt); -static int ip_finish_output2(struct sock *sk, struct sk_buff *skb) +static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct rtable *rt = (struct rtable *)dst; struct net_device *dev = dst->dev; - struct net *net = dev_net(dev); unsigned int hh_len = LL_RESERVED_SPACE(dev); struct neighbour *neigh; u32 nexthop; @@ -225,8 +220,8 @@ static int ip_finish_output2(struct sock *sk, struct sk_buff *skb) return -EINVAL; } -static int ip_finish_output_gso(struct sock *sk, struct sk_buff *skb, - unsigned int mtu) +static int ip_finish_output_gso(struct net *net, struct sock *sk, + struct sk_buff *skb, unsigned int mtu) { netdev_features_t features; struct sk_buff *segs; @@ -235,7 +230,7 @@ static int ip_finish_output_gso(struct sock *sk, struct sk_buff *skb, /* common case: locally created skb or seglen is <= mtu */ if (((IPCB(skb)->flags & IPSKB_FORWARDED) == 0) || skb_gso_network_seglen(skb) <= mtu) - return ip_finish_output2(sk, skb); + return ip_finish_output2(net, sk, skb); /* Slowpath - GSO segment length is exceeding the dst MTU. * @@ -258,7 +253,7 @@ static int ip_finish_output_gso(struct sock *sk, struct sk_buff *skb, int err; segs->next = NULL; - err = ip_fragment(sk, segs, mtu, ip_finish_output2); + err = ip_fragment(net, sk, segs, mtu, ip_finish_output2); if (err && ret == 0) ret = err; @@ -276,24 +271,23 @@ static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *sk /* Policy lookup after SNAT yielded a new policy */ if (skb_dst(skb)->xfrm) { IPCB(skb)->flags |= IPSKB_REROUTED; - return dst_output(sk, skb); + return dst_output(net, sk, skb); } #endif mtu = ip_skb_dst_mtu(skb); if (skb_is_gso(skb)) - return ip_finish_output_gso(sk, skb, mtu); + return ip_finish_output_gso(net, sk, skb, mtu); if (skb->len > mtu || (IPCB(skb)->flags & IPSKB_FRAG_PMTU)) - return ip_fragment(sk, skb, mtu, ip_finish_output2); + return ip_fragment(net, sk, skb, mtu, ip_finish_output2); - return ip_finish_output2(sk, skb); + return ip_finish_output2(net, sk, skb); } -int ip_mc_output(struct sock *sk, struct sk_buff *skb) +int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct rtable *rt = skb_rtable(skb); struct net_device *dev = rt->dst.dev; - struct net *net = dev_net(dev); /* * If the indicated interface is up and running, send the packet. @@ -352,10 +346,9 @@ int ip_mc_output(struct sock *sk, struct sk_buff *skb) !(IPCB(skb)->flags & IPSKB_REROUTED)); } -int ip_output(struct sock *sk, struct sk_buff *skb) +int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb_dst(skb)->dev; - struct net *net = dev_net(dev); IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len); @@ -386,6 +379,7 @@ static void ip_copy_addrs(struct iphdr *iph, const struct flowi4 *fl4) int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl) { struct inet_sock *inet = inet_sk(sk); + struct net *net = sock_net(sk); struct ip_options_rcu *inet_opt; struct flowi4 *fl4; struct rtable *rt; @@ -416,7 +410,7 @@ int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl) * keep trying until route appears or the connection times * itself out. */ - rt = ip_route_output_ports(sock_net(sk), fl4, sk, + rt = ip_route_output_ports(net, fl4, sk, daddr, inet->inet_saddr, inet->inet_dport, inet->inet_sport, @@ -453,20 +447,20 @@ packet_routed: ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt, 0); } - ip_select_ident_segs(sock_net(sk), skb, sk, + ip_select_ident_segs(net, skb, sk, skb_shinfo(skb)->gso_segs ?: 1); /* TODO : should we use skb->sk here instead of sk ? */ skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; - res = ip_local_out(skb); + res = ip_local_out(net, sk, skb); rcu_read_unlock(); return res; no_route: rcu_read_unlock(); - IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES); + IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); kfree_skb(skb); return -EHOSTUNREACH; } @@ -495,20 +489,18 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) skb_copy_secmark(to, from); } -static int ip_fragment(struct sock *sk, struct sk_buff *skb, +static int ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int mtu, - int (*output)(struct sock *, struct sk_buff *)) + int (*output)(struct net *, struct sock *, struct sk_buff *)) { struct iphdr *iph = ip_hdr(skb); if ((iph->frag_off & htons(IP_DF)) == 0) - return ip_do_fragment(sk, skb, output); + return ip_do_fragment(net, sk, skb, output); if (unlikely(!skb->ignore_df || (IPCB(skb)->frag_max_size && IPCB(skb)->frag_max_size > mtu))) { - struct net *net = dev_net(skb_rtable(skb)->dst.dev); - IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS); icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); @@ -516,7 +508,7 @@ static int ip_fragment(struct sock *sk, struct sk_buff *skb, return -EMSGSIZE; } - return ip_do_fragment(sk, skb, output); + return ip_do_fragment(net, sk, skb, output); } /* @@ -526,8 +518,8 @@ static int ip_fragment(struct sock *sk, struct sk_buff *skb, * single device frame, and queue such a frame for sending. */ -int ip_do_fragment(struct sock *sk, struct sk_buff *skb, - int (*output)(struct sock *, struct sk_buff *)) +int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, + int (*output)(struct net *, struct sock *, struct sk_buff *)) { struct iphdr *iph; int ptr; @@ -537,11 +529,9 @@ int ip_do_fragment(struct sock *sk, struct sk_buff *skb, int offset; __be16 not_last_frag; struct rtable *rt = skb_rtable(skb); - struct net *net; int err = 0; dev = rt->dst.dev; - net = dev_net(dev); /* * Point into the IP datagram header. @@ -631,7 +621,7 @@ int ip_do_fragment(struct sock *sk, struct sk_buff *skb, ip_send_check(iph); } - err = output(sk, skb); + err = output(net, sk, skb); if (!err) IP_INC_STATS(net, IPSTATS_MIB_FRAGCREATES); @@ -771,7 +761,7 @@ slow_path: ip_send_check(iph); - err = output(sk, skb2); + err = output(net, sk, skb2); if (err) goto fail; @@ -1444,7 +1434,7 @@ int ip_send_skb(struct net *net, struct sk_buff *skb) { int err; - err = ip_local_out(skb); + err = ip_local_out(net, skb->sk, skb); if (err) { if (err > 0) err = net_xmit_errno(err); diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 84dce6a..6cb9009 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -53,6 +53,7 @@ int iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, __u8 tos, __u8 ttl, __be16 df, bool xnet) { int pkt_len = skb->len - skb_inner_network_offset(skb); + struct net *net = dev_net(rt->dst.dev); struct iphdr *iph; int err; @@ -76,10 +77,9 @@ int iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, iph->daddr = dst; iph->saddr = src; iph->ttl = ttl; - __ip_select_ident(dev_net(rt->dst.dev), iph, - skb_shinfo(skb)->gso_segs ?: 1); + __ip_select_ident(net, iph, skb_shinfo(skb)->gso_segs ?: 1); - err = ip_local_out_sk(sk, skb); + err = ip_local_out(net, sk, skb); if (unlikely(net_xmit_eval(err))) pkt_len = 0; return pkt_len; diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 3b87ec5..4d8f0b6 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -197,7 +197,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, skb_dst_set(skb, dst); skb->dev = skb_dst(skb)->dev; - err = dst_output(skb->sk, skb); + err = dst_output(tunnel->net, skb->sk, skb); if (net_xmit_eval(err) == 0) err = skb->len; iptunnel_xmit_stats(err, &dev->stats, dev->tstats); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index cfcb996..fc42525 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1689,7 +1689,7 @@ static inline int ipmr_forward_finish(struct net *net, struct sock *sk, if (unlikely(opt->optlen)) ip_forward_options(skb); - return dst_output(sk, skb); + return dst_output(net, sk, skb); } /* diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c index a105836..5fdc556 100644 --- a/net/ipv4/netfilter/ipt_SYNPROXY.c +++ b/net/ipv4/netfilter/ipt_SYNPROXY.c @@ -63,7 +63,7 @@ synproxy_send_tcp(const struct synproxy_net *snet, nf_conntrack_get(nfct); } - ip_local_out(nskb); + ip_local_out(net, nskb->sk, nskb); return; free_nskb: diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c index 9df3f93..0e5591c 100644 --- a/net/ipv4/netfilter/nf_defrag_ipv4.c +++ b/net/ipv4/netfilter/nf_defrag_ipv4.c @@ -22,14 +22,15 @@ #endif #include <net/netfilter/nf_conntrack_zones.h> -static int nf_ct_ipv4_gather_frags(struct sk_buff *skb, u_int32_t user) +static int nf_ct_ipv4_gather_frags(struct net *net, struct sk_buff *skb, + u_int32_t user) { int err; skb_orphan(skb); local_bh_disable(); - err = ip_defrag(skb, user); + err = ip_defrag(net, skb, user); local_bh_enable(); if (!err) { @@ -85,7 +86,7 @@ static unsigned int ipv4_conntrack_defrag(void *priv, enum ip_defrag_users user = nf_ct_defrag_user(state->hook, skb); - if (nf_ct_ipv4_gather_frags(skb, user)) + if (nf_ct_ipv4_gather_frags(state->net, skb, user)) return NF_STOLEN; } return NF_ACCEPT; diff --git a/net/ipv4/netfilter/nf_dup_ipv4.c b/net/ipv4/netfilter/nf_dup_ipv4.c index ce2a59e..ceb1873 100644 --- a/net/ipv4/netfilter/nf_dup_ipv4.c +++ b/net/ipv4/netfilter/nf_dup_ipv4.c @@ -92,7 +92,7 @@ void nf_dup_ipv4(struct net *net, struct sk_buff *skb, unsigned int hooknum, if (nf_dup_ipv4_route(net, skb, gw, oif)) { __this_cpu_write(nf_skb_duplicated, true); - ip_local_out(skb); + ip_local_out(net, skb->sk, skb); __this_cpu_write(nf_skb_duplicated, false); } else { kfree_skb(skb); diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c index 2f5e925..c747b2d 100644 --- a/net/ipv4/netfilter/nf_reject_ipv4.c +++ b/net/ipv4/netfilter/nf_reject_ipv4.c @@ -157,7 +157,7 @@ void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook) dev_queue_xmit(nskb); } else #endif - ip_local_out(nskb); + ip_local_out(net, nskb->sk, nskb); return; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 28ef8a9..8c0d0bd 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -413,7 +413,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, err = NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk, skb, NULL, rt->dst.dev, - dst_output_okfn); + dst_output); if (err > 0) err = net_xmit_errno(err); if (err) @@ -484,6 +484,7 @@ static int raw_getfrag(void *from, char *to, int offset, int len, int odd, static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct inet_sock *inet = inet_sk(sk); + struct net *net = sock_net(sk); struct ipcm_cookie ipc; struct rtable *rt = NULL; struct flowi4 fl4; @@ -543,7 +544,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ipc.oif = sk->sk_bound_dev_if; if (msg->msg_controllen) { - err = ip_cmsg_send(sock_net(sk), msg, &ipc, false); + err = ip_cmsg_send(net, msg, &ipc, false); if (err) goto out; if (ipc.opt) @@ -598,6 +599,9 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) (inet->hdrincl ? FLOWI_FLAG_KNOWN_NH : 0), daddr, saddr, 0, 0); + if (!saddr && ipc.oif) + l3mdev_get_saddr(net, ipc.oif, &fl4); + if (!inet->hdrincl) { rfv.msg = msg; rfv.hlen = 0; @@ -608,7 +612,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) } security_sk_classify_flow(sk, flowi4_to_flowi(&fl4)); - rt = ip_route_output_flow(sock_net(sk), &fl4, sk); + rt = ip_route_output_flow(net, &fl4, sk); if (IS_ERR(rt)) { err = PTR_ERR(rt); rt = NULL; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 76ca4e7..85f184e 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1152,7 +1152,7 @@ static void ipv4_link_failure(struct sk_buff *skb) dst_set_expires(&rt->dst, 0); } -static int ip_rt_bug(struct sock *sk, struct sk_buff *skb) +static int ip_rt_bug(struct net *net, struct sock *sk, struct sk_buff *skb) { pr_debug("%s: %pI4 -> %pI4, %s\n", __func__, &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, @@ -1651,6 +1651,48 @@ out: return err; } +#ifdef CONFIG_IP_ROUTE_MULTIPATH + +/* To make ICMP packets follow the right flow, the multipath hash is + * calculated from the inner IP addresses in reverse order. + */ +static int ip_multipath_icmp_hash(struct sk_buff *skb) +{ + const struct iphdr *outer_iph = ip_hdr(skb); + struct icmphdr _icmph; + const struct icmphdr *icmph; + struct iphdr _inner_iph; + const struct iphdr *inner_iph; + + if (unlikely((outer_iph->frag_off & htons(IP_OFFSET)) != 0)) + goto standard_hash; + + icmph = skb_header_pointer(skb, outer_iph->ihl * 4, sizeof(_icmph), + &_icmph); + if (!icmph) + goto standard_hash; + + if (icmph->type != ICMP_DEST_UNREACH && + icmph->type != ICMP_REDIRECT && + icmph->type != ICMP_TIME_EXCEEDED && + icmph->type != ICMP_PARAMETERPROB) { + goto standard_hash; + } + + inner_iph = skb_header_pointer(skb, + outer_iph->ihl * 4 + sizeof(_icmph), + sizeof(_inner_iph), &_inner_iph); + if (!inner_iph) + goto standard_hash; + + return fib_multipath_hash(inner_iph->daddr, inner_iph->saddr); + +standard_hash: + return fib_multipath_hash(outer_iph->saddr, outer_iph->daddr); +} + +#endif /* CONFIG_IP_ROUTE_MULTIPATH */ + static int ip_mkroute_input(struct sk_buff *skb, struct fib_result *res, const struct flowi4 *fl4, @@ -1658,8 +1700,15 @@ static int ip_mkroute_input(struct sk_buff *skb, __be32 daddr, __be32 saddr, u32 tos) { #ifdef CONFIG_IP_ROUTE_MULTIPATH - if (res->fi && res->fi->fib_nhs > 1) - fib_select_multipath(res); + if (res->fi && res->fi->fib_nhs > 1) { + int h; + + if (unlikely(ip_hdr(skb)->protocol == IPPROTO_ICMP)) + h = ip_multipath_icmp_hash(skb); + else + h = fib_multipath_hash(saddr, daddr); + fib_select_multipath(res, h); + } #endif /* create a routing cache entry */ @@ -2026,7 +2075,8 @@ add: * Major route resolver routine. */ -struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) +struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, + int mp_hash) { struct net_device *dev_out = NULL; __u8 tos = RT_FL_TOS(fl4); @@ -2146,7 +2196,8 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) if (err) { res.fi = NULL; res.table = NULL; - if (fl4->flowi4_oif) { + if (fl4->flowi4_oif && + !netif_index_is_l3_master(net, fl4->flowi4_oif)) { /* Apparently, routing tables are wrong. Assume, that the destination is on link. @@ -2188,18 +2239,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) goto make_route; } -#ifdef CONFIG_IP_ROUTE_MULTIPATH - if (res.fi->fib_nhs > 1 && fl4->flowi4_oif == 0) - fib_select_multipath(&res); - else -#endif - if (!res.prefixlen && - res.table->tb_num_default > 1 && - res.type == RTN_UNICAST && !fl4->flowi4_oif) - fib_select_default(fl4, &res); - - if (!fl4->saddr) - fl4->saddr = FIB_RES_PREFSRC(net, res); + fib_select_path(net, &res, fl4, mp_hash); dev_out = FIB_RES_DEV(res); fl4->flowi4_oif = dev_out->ifindex; @@ -2212,7 +2252,7 @@ out: rcu_read_unlock(); return rth; } -EXPORT_SYMBOL_GPL(__ip_route_output_key); +EXPORT_SYMBOL_GPL(__ip_route_output_key_hash); static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 cookie) { @@ -2264,7 +2304,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or new->__use = 1; new->input = dst_discard; - new->output = dst_discard_sk; + new->output = dst_discard_out; new->dev = ort->dst.dev; if (new->dev) @@ -2468,6 +2508,9 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh) fl4.flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0; fl4.flowi4_mark = mark; + if (netif_index_is_l3_master(net, fl4.flowi4_oif)) + fl4.flowi4_flags = FLOWI_FLAG_L3MDEV_SRC | FLOWI_FLAG_SKIP_NH_OIF; + if (iif) { struct net_device *dev; diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 729ceb5..4c0892b 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -225,6 +225,7 @@ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb, child = icsk->icsk_af_ops->syn_recv_sock(sk, skb, req, dst); if (child) { atomic_set(&req->rsk_refcnt, 1); + sock_rps_save_rxhash(child, skb); inet_csk_reqsk_queue_add(sk, req, child); } else { reqsk_free(req); @@ -326,7 +327,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) goto out; ret = NULL; - req = inet_reqsk_alloc(&tcp_request_sock_ops, sk); /* for safety */ + req = inet_reqsk_alloc(&tcp_request_sock_ops, sk, false); /* for safety */ if (!req) goto out; @@ -381,10 +382,10 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) } /* Try to redo what tcp_v4_send_synack did. */ - req->window_clamp = tp->window_clamp ? :dst_metric(&rt->dst, RTAX_WINDOW); + req->rsk_window_clamp = tp->window_clamp ? :dst_metric(&rt->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(&rt->dst, RTAX_INITRWND)); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 3c96fa8..ac1bdbb 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -900,7 +900,8 @@ static ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, */ if (((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) && !tcp_passive_fastopen(sk)) { - if ((err = sk_stream_wait_connect(sk, &timeo)) != 0) + err = sk_stream_wait_connect(sk, &timeo); + if (err != 0) goto out_err; } @@ -967,7 +968,8 @@ new_segment: copied += copy; offset += copy; - if (!(size -= copy)) { + size -= copy; + if (!size) { tcp_tx_timestamp(sk, skb); goto out; } @@ -988,7 +990,8 @@ wait_for_memory: tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH, size_goal); - if ((err = sk_stream_wait_memory(sk, &timeo)) != 0) + err = sk_stream_wait_memory(sk, &timeo); + if (err != 0) goto do_error; mss_now = tcp_send_mss(sk, &size_goal, flags); @@ -1111,7 +1114,8 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) */ if (((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) && !tcp_passive_fastopen(sk)) { - if ((err = sk_stream_wait_connect(sk, &timeo)) != 0) + err = sk_stream_wait_connect(sk, &timeo); + if (err != 0) goto do_error; } @@ -1267,7 +1271,8 @@ wait_for_memory: tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH, size_goal); - if ((err = sk_stream_wait_memory(sk, &timeo)) != 0) + err = sk_stream_wait_memory(sk, &timeo); + if (err != 0) goto do_error; mss_now = tcp_send_mss(sk, &size_goal, flags); @@ -1767,7 +1772,8 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, /* __ Restore normal policy in scheduler __ */ - if ((chunk = len - tp->ucopy.len) != 0) { + chunk = len - tp->ucopy.len; + if (chunk != 0) { NET_ADD_STATS_USER(sock_net(sk), LINUX_MIB_TCPDIRECTCOPYFROMBACKLOG, chunk); len -= chunk; copied += chunk; @@ -1778,7 +1784,8 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, do_prequeue: tcp_prequeue_process(sk); - if ((chunk = len - tp->ucopy.len) != 0) { + chunk = len - tp->ucopy.len; + if (chunk != 0) { NET_ADD_STATS_USER(sock_net(sk), LINUX_MIB_TCPDIRECTCOPYFROMPREQUEUE, chunk); len -= chunk; copied += chunk; @@ -2230,7 +2237,8 @@ int tcp_disconnect(struct sock *sk, int flags) sk->sk_shutdown = 0; sock_reset_flag(sk, SOCK_DONE); tp->srtt_us = 0; - if ((tp->write_seq += tp->max_window + 2) == 0) + tp->write_seq += tp->max_window + 2; + if (tp->write_seq == 0) tp->write_seq = 1; icsk->icsk_backoff = 0; tp->snd_cwnd = 2; diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 410ac48..93396bf 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -168,8 +168,6 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk, TCP_TIMEOUT_INIT, TCP_RTO_MAX); atomic_set(&req->rsk_refcnt, 2); - /* Add the child socket directly into the accept queue */ - inet_csk_reqsk_queue_add(sk, req, child); /* Now finish processing the fastopen child socket. */ inet_csk(child)->icsk_af_ops->rebuild_header(child); @@ -178,12 +176,10 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk, tcp_init_metrics(child); tcp_init_buffer_space(child); - /* Queue the data carried in the SYN packet. We need to first - * bump skb's refcnt because the caller will attempt to free it. - * Note that IPv6 might also have used skb_get() trick - * in tcp_v6_conn_request() to keep this SYN around (treq->pktopts) - * So we need to eventually get a clone of the packet, - * before inserting it in sk_receive_queue. + /* Queue the data carried in the SYN packet. + * We used to play tricky games with skb_get(). + * With lockless listener, it is a dead end. + * Do not think about it. * * XXX (TFO) - we honor a zero-payload TFO request for now, * (any reason not to?) but no need to queue the skb since @@ -191,12 +187,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk, */ end_seq = TCP_SKB_CB(skb)->end_seq; if (end_seq != TCP_SKB_CB(skb)->seq + 1) { - struct sk_buff *skb2; - - if (unlikely(skb_shared(skb))) - skb2 = skb_clone(skb, GFP_ATOMIC); - else - skb2 = skb_get(skb); + struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (likely(skb2)) { skb_dst_drop(skb2); @@ -214,12 +205,9 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk, } } tcp_rsk(req)->rcv_nxt = tp->rcv_nxt = end_seq; - sk->sk_data_ready(sk); - bh_unlock_sock(child); - /* Note: sock_put(child) will be done by tcp_conn_request() - * after SYNACK packet is sent. + /* tcp_conn_request() is sending the SYNACK, + * and queues the child into listener accept queue. */ - WARN_ON(!req->sk); return child; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 2710875..3b35c3f 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6022,7 +6022,7 @@ static void tcp_openreq_init(struct request_sock *req, { struct inet_request_sock *ireq = inet_rsk(req); - req->rcv_wnd = 0; /* So that tcp_send_synack() knows! */ + req->rsk_rcv_wnd = 0; /* So that tcp_send_synack() knows! */ req->cookie_ts = 0; tcp_rsk(req)->rcv_isn = TCP_SKB_CB(skb)->seq; tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; @@ -6042,9 +6042,11 @@ static void tcp_openreq_init(struct request_sock *req, } struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops, - struct sock *sk_listener) + struct sock *sk_listener, + bool attach_listener) { - struct request_sock *req = reqsk_alloc(ops, sk_listener); + struct request_sock *req = reqsk_alloc(ops, sk_listener, + attach_listener); if (req) { struct inet_request_sock *ireq = inet_rsk(req); @@ -6143,7 +6145,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, goto drop; } - req = inet_reqsk_alloc(rsk_ops, sk); + req = inet_reqsk_alloc(rsk_ops, sk, !want_cookie); if (!req) goto drop; @@ -6229,12 +6231,16 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, tcp_rsk(req)->txhash = net_tx_rndhash(); tcp_openreq_init_rwin(req, sk, dst); if (!want_cookie) { - fastopen_sk = tcp_try_fastopen(sk, skb, req, &foc, dst); tcp_reqsk_record_syn(sk, req, skb); + fastopen_sk = tcp_try_fastopen(sk, skb, req, &foc, dst); } if (fastopen_sk) { af_ops->send_synack(fastopen_sk, dst, &fl, req, skb_get_queue_mapping(skb), &foc, false); + /* Add the child socket directly into the accept queue */ + inet_csk_reqsk_queue_add(sk, req, fastopen_sk); + sk->sk_data_ready(sk); + bh_unlock_sock(fastopen_sk); sock_put(fastopen_sk); } else { tcp_rsk(req)->tfo_listener = false; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 3431074..9c68cf3 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -324,7 +324,6 @@ void tcp_req_err(struct sock *sk, u32 seq) if (seq != tcp_rsk(req)->snt_isn) { NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); - reqsk_put(req); } else { /* * Still in SYN_RECV, just remove it silently. @@ -332,9 +331,10 @@ void tcp_req_err(struct sock *sk, u32 seq) * created socket, and POSIX does not want network * errors returned from accept(). */ - NET_INC_STATS_BH(net, LINUX_MIB_LISTENDROPS); inet_csk_reqsk_queue_drop(req->rsk_listener, req); + NET_INC_STATS_BH(net, LINUX_MIB_LISTENDROPS); } + reqsk_put(req); } EXPORT_SYMBOL(tcp_req_err); @@ -803,7 +803,7 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, */ tcp_v4_send_ack(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, 0, @@ -1572,6 +1572,7 @@ int tcp_v4_rcv(struct sk_buff *skb) TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph); TCP_SKB_CB(skb)->sacked = 0; +lookup: sk = __inet_lookup_skb(&tcp_hashinfo, skb, th->source, th->dest); if (!sk) goto no_tcp_socket; @@ -1587,8 +1588,12 @@ process: sk = req->rsk_listener; if (tcp_v4_inbound_md5_hash(sk, skb)) goto discard_and_relse; - 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/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 9adf1e2..41828bd 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -381,18 +381,18 @@ void tcp_openreq_init_rwin(struct request_sock *req, window_clamp = READ_ONCE(tp->window_clamp); /* Set this up on the first call only */ - req->window_clamp = window_clamp ? : dst_metric(dst, RTAX_WINDOW); + req->rsk_window_clamp = window_clamp ? : dst_metric(dst, RTAX_WINDOW); /* limit the window selection if the user enforce a smaller rx buffer */ if (sk_listener->sk_userlocks & SOCK_RCVBUF_LOCK && - (req->window_clamp > full_space || req->window_clamp == 0)) - req->window_clamp = full_space; + (req->rsk_window_clamp > full_space || req->rsk_window_clamp == 0)) + req->rsk_window_clamp = full_space; /* tcp_full_space because it is guaranteed to be the first packet */ tcp_select_initial_window(full_space, mss - (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0), - &req->rcv_wnd, - &req->window_clamp, + &req->rsk_rcv_wnd, + &req->rsk_window_clamp, ireq->wscale_ok, &rcv_wscale, dst_metric(dst, RTAX_INITRWND)); @@ -512,9 +512,9 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, if (sysctl_tcp_fack) tcp_enable_fack(newtp); } - newtp->window_clamp = req->window_clamp; - newtp->rcv_ssthresh = req->rcv_wnd; - newtp->rcv_wnd = req->rcv_wnd; + newtp->window_clamp = req->rsk_window_clamp; + newtp->rcv_ssthresh = req->rsk_rcv_wnd; + newtp->rcv_wnd = req->rsk_rcv_wnd; newtp->rx_opt.wscale_ok = ireq->wscale_ok; if (newtp->rx_opt.wscale_ok) { newtp->rx_opt.snd_wscale = ireq->snd_wscale; @@ -707,7 +707,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, /* RFC793: "first check sequence number". */ if (paws_reject || !tcp_in_window(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq, - tcp_rsk(req)->rcv_nxt, tcp_rsk(req)->rcv_nxt + req->rcv_wnd)) { + tcp_rsk(req)->rcv_nxt, tcp_rsk(req)->rcv_nxt + req->rsk_rcv_wnd)) { /* Out of window: send ACK and drop. */ if (!(flg & TCP_FLAG_RST)) req->rsk_ops->send_ack(sk, skb, req); @@ -768,6 +768,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, if (!child) goto listen_overflow; + sock_rps_save_rxhash(child, skb); tcp_synack_rtt_meas(child, req); inet_csk_reqsk_queue_drop(sk, req); inet_csk_reqsk_queue_add(sk, req, child); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 55ed3266..6e79fcb 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3023,7 +3023,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, th->ack_seq = htonl(tcp_rsk(req)->rcv_nxt); /* RFC1323: The window in SYN & SYN/ACK segments is never scaled. */ - th->window = htons(min(req->rcv_wnd, 65535U)); + th->window = htons(min(req->rsk_rcv_wnd, 65535U)); tcp_options_write((__be32 *)(th + 1), NULL, &opts); th->doff = (tcp_header_size >> 2); TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_OUTSEGS); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 7149ebc..c9c716a 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -83,7 +83,7 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset) } /* Calculate maximal number or retries on an orphaned socket. */ -static int tcp_orphan_retries(struct sock *sk, int alive) +static int tcp_orphan_retries(struct sock *sk, bool alive) { int retries = sysctl_tcp_orphan_retries; /* May be zero. */ @@ -184,7 +184,7 @@ static int tcp_write_timeout(struct sock *sk) retry_until = sysctl_tcp_retries2; if (sock_flag(sk, SOCK_DEAD)) { - const int alive = icsk->icsk_rto < TCP_RTO_MAX; + const bool alive = icsk->icsk_rto < TCP_RTO_MAX; retry_until = tcp_orphan_retries(sk, alive); do_reset = alive || @@ -298,7 +298,7 @@ static void tcp_probe_timer(struct sock *sk) max_probes = sysctl_tcp_retries2; if (sock_flag(sk, SOCK_DEAD)) { - const int alive = inet_csk_rto_backoff(icsk, TCP_RTO_MAX) < TCP_RTO_MAX; + const bool alive = inet_csk_rto_backoff(icsk, TCP_RTO_MAX) < TCP_RTO_MAX; max_probes = tcp_orphan_retries(sk, alive); if (!alive && icsk->icsk_backoff >= max_probes) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 156ba75..24ec14f9 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -375,7 +375,8 @@ static inline int compute_score(struct sock *sk, struct net *net, return -1; score += 4; } - + if (sk->sk_incoming_cpu == raw_smp_processor_id()) + score++; return score; } @@ -419,6 +420,9 @@ static inline int compute_score2(struct sock *sk, struct net *net, score += 4; } + if (sk->sk_incoming_cpu == raw_smp_processor_id()) + score++; + return score; } @@ -1017,30 +1021,14 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) fl4 = &fl4_stack; - /* unconnected socket. If output device is enslaved to a VRF - * device lookup source address from VRF table. This mimics - * behavior of ip_route_connect{_init}. - */ - if (netif_index_is_l3_master(net, ipc.oif)) { - flowi4_init_output(fl4, ipc.oif, sk->sk_mark, tos, - RT_SCOPE_UNIVERSE, sk->sk_protocol, - (flow_flags | FLOWI_FLAG_VRFSRC | - FLOWI_FLAG_SKIP_NH_OIF), - faddr, saddr, dport, - inet->inet_sport); - - rt = ip_route_output_flow(net, fl4, sk); - if (!IS_ERR(rt)) { - saddr = fl4->saddr; - ip_rt_put(rt); - } - } - flowi4_init_output(fl4, ipc.oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE, sk->sk_protocol, flow_flags, faddr, saddr, dport, inet->inet_sport); + if (!saddr && ipc.oif) + l3mdev_get_saddr(net, ipc.oif, fl4); + security_sk_classify_flow(sk, flowi4_to_flowi(fl4)); rt = ip_route_output_flow(net, fl4, sk); if (IS_ERR(rt)) { diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index cd6be73..9f298d0 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -87,17 +87,15 @@ static int __xfrm4_output(struct net *net, struct sock *sk, struct sk_buff *skb) #ifdef CONFIG_NETFILTER if (!x) { IPCB(skb)->flags |= IPSKB_REROUTED; - return dst_output(sk, skb); + return dst_output(net, sk, skb); } #endif return x->outer_mode->afinfo->output_finish(sk, skb); } -int xfrm4_output(struct sock *sk, struct sk_buff *skb) +int xfrm4_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_IPV4, NF_INET_POST_ROUTING, net, sk, skb, NULL, skb_dst(skb)->dev, __xfrm4_output, |