diff options
Diffstat (limited to 'net/ipv4')
-rw-r--r-- | net/ipv4/Makefile | 2 | ||||
-rw-r--r-- | net/ipv4/af_inet.c | 4 | ||||
-rw-r--r-- | net/ipv4/devinet.c | 39 | ||||
-rw-r--r-- | net/ipv4/fib_frontend.c | 3 | ||||
-rw-r--r-- | net/ipv4/fib_semantics.c | 42 | ||||
-rw-r--r-- | net/ipv4/fib_trie.c | 68 | ||||
-rw-r--r-- | net/ipv4/igmp.c | 7 | ||||
-rw-r--r-- | net/ipv4/inet_connection_sock.c | 7 | ||||
-rw-r--r-- | net/ipv4/ip_input.c | 2 | ||||
-rw-r--r-- | net/ipv4/ip_output.c | 10 | ||||
-rw-r--r-- | net/ipv4/ipmr.c | 2 | ||||
-rw-r--r-- | net/ipv4/netfilter/ipt_rpfilter.c | 2 | ||||
-rw-r--r-- | net/ipv4/netfilter/nf_nat_sip.c | 9 | ||||
-rw-r--r-- | net/ipv4/route.c | 205 | ||||
-rw-r--r-- | net/ipv4/sysctl_net_ipv4.c | 15 | ||||
-rw-r--r-- | net/ipv4/tcp.c | 9 | ||||
-rw-r--r-- | net/ipv4/tcp_cong.c | 3 | ||||
-rw-r--r-- | net/ipv4/tcp_input.c | 38 | ||||
-rw-r--r-- | net/ipv4/tcp_ipv4.c | 54 | ||||
-rw-r--r-- | net/ipv4/tcp_metrics.c | 12 | ||||
-rw-r--r-- | net/ipv4/tcp_minisocks.c | 2 | ||||
-rw-r--r-- | net/ipv4/tcp_output.c | 49 | ||||
-rw-r--r-- | net/ipv4/tcp_timer.c | 6 | ||||
-rw-r--r-- | net/ipv4/udp.c | 2 | ||||
-rw-r--r-- | net/ipv4/xfrm4_policy.c | 1 |
25 files changed, 371 insertions, 222 deletions
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index ae2ccf2890e4..15ca63ec604e 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -49,7 +49,7 @@ obj-$(CONFIG_TCP_CONG_SCALABLE) += tcp_scalable.o obj-$(CONFIG_TCP_CONG_LP) += tcp_lp.o obj-$(CONFIG_TCP_CONG_YEAH) += tcp_yeah.o obj-$(CONFIG_TCP_CONG_ILLINOIS) += tcp_illinois.o -obj-$(CONFIG_CGROUP_MEM_RES_CTLR_KMEM) += tcp_memcontrol.o +obj-$(CONFIG_MEMCG_KMEM) += tcp_memcontrol.o obj-$(CONFIG_NETLABEL) += cipso_ipv4.o obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \ diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index fe4582ca969a..6681ccf5c3ee 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1364,7 +1364,7 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head, if (*(u8 *)iph != 0x45) goto out_unlock; - if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl))) + if (unlikely(ip_fast_csum((u8 *)iph, 5))) goto out_unlock; id = ntohl(*(__be32 *)&iph->id); @@ -1380,7 +1380,6 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head, iph2 = ip_hdr(p); if ((iph->protocol ^ iph2->protocol) | - (iph->tos ^ iph2->tos) | ((__force u32)iph->saddr ^ (__force u32)iph2->saddr) | ((__force u32)iph->daddr ^ (__force u32)iph2->daddr)) { NAPI_GRO_CB(p)->same_flow = 0; @@ -1390,6 +1389,7 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head, /* All fields must match except length and checksum. */ NAPI_GRO_CB(p)->flush |= (iph->ttl ^ iph2->ttl) | + (iph->tos ^ iph2->tos) | ((u16)(ntohs(iph2->id) + NAPI_GRO_CB(p)->count) ^ id); NAPI_GRO_CB(p)->flush |= flush; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 44bf82e3aef7..adf273f8ad2e 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -94,25 +94,22 @@ static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = { [IFA_LABEL] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, }; -/* inet_addr_hash's shifting is dependent upon this IN4_ADDR_HSIZE - * value. So if you change this define, make appropriate changes to - * inet_addr_hash as well. - */ -#define IN4_ADDR_HSIZE 256 +#define IN4_ADDR_HSIZE_SHIFT 8 +#define IN4_ADDR_HSIZE (1U << IN4_ADDR_HSIZE_SHIFT) + static struct hlist_head inet_addr_lst[IN4_ADDR_HSIZE]; static DEFINE_SPINLOCK(inet_addr_hash_lock); -static inline unsigned int inet_addr_hash(struct net *net, __be32 addr) +static u32 inet_addr_hash(struct net *net, __be32 addr) { - u32 val = (__force u32) addr ^ hash_ptr(net, 8); + u32 val = (__force u32) addr ^ net_hash_mix(net); - return ((val ^ (val >> 8) ^ (val >> 16) ^ (val >> 24)) & - (IN4_ADDR_HSIZE - 1)); + return hash_32(val, IN4_ADDR_HSIZE_SHIFT); } static void inet_hash_insert(struct net *net, struct in_ifaddr *ifa) { - unsigned int hash = inet_addr_hash(net, ifa->ifa_local); + u32 hash = inet_addr_hash(net, ifa->ifa_local); spin_lock(&inet_addr_hash_lock); hlist_add_head_rcu(&ifa->hash, &inet_addr_lst[hash]); @@ -136,18 +133,18 @@ static void inet_hash_remove(struct in_ifaddr *ifa) */ struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref) { - unsigned int hash = inet_addr_hash(net, addr); + u32 hash = inet_addr_hash(net, addr); struct net_device *result = NULL; struct in_ifaddr *ifa; struct hlist_node *node; rcu_read_lock(); hlist_for_each_entry_rcu(ifa, node, &inet_addr_lst[hash], hash) { - struct net_device *dev = ifa->ifa_dev->dev; - - if (!net_eq(dev_net(dev), net)) - continue; if (ifa->ifa_local == addr) { + struct net_device *dev = ifa->ifa_dev->dev; + + if (!net_eq(dev_net(dev), net)) + continue; result = dev; break; } @@ -182,10 +179,10 @@ static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, static void devinet_sysctl_register(struct in_device *idev); static void devinet_sysctl_unregister(struct in_device *idev); #else -static inline void devinet_sysctl_register(struct in_device *idev) +static void devinet_sysctl_register(struct in_device *idev) { } -static inline void devinet_sysctl_unregister(struct in_device *idev) +static void devinet_sysctl_unregister(struct in_device *idev) { } #endif @@ -205,7 +202,7 @@ static void inet_rcu_free_ifa(struct rcu_head *head) kfree(ifa); } -static inline void inet_free_ifa(struct in_ifaddr *ifa) +static void inet_free_ifa(struct in_ifaddr *ifa) { call_rcu(&ifa->rcu_head, inet_rcu_free_ifa); } @@ -659,7 +656,7 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg * Determine a default network mask, based on the IP address. */ -static inline int inet_abc_len(__be32 addr) +static int inet_abc_len(__be32 addr) { int rc = -1; /* Something else, probably a multicast. */ @@ -1124,7 +1121,7 @@ skip: } } -static inline bool inetdev_valid_mtu(unsigned int mtu) +static bool inetdev_valid_mtu(unsigned int mtu) { return mtu >= 68; } @@ -1239,7 +1236,7 @@ static struct notifier_block ip_netdev_notifier = { .notifier_call = inetdev_event, }; -static inline size_t inet_nlmsg_size(void) +static size_t inet_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct ifaddrmsg)) + nla_total_size(4) /* IFA_ADDRESS */ diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 8732cc7920ed..7f073a38c87d 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -218,7 +218,7 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb) scope = RT_SCOPE_UNIVERSE; if (!ipv4_is_zeronet(ip_hdr(skb)->saddr)) { fl4.flowi4_oif = 0; - fl4.flowi4_iif = net->loopback_dev->ifindex; + fl4.flowi4_iif = LOOPBACK_IFINDEX; fl4.daddr = ip_hdr(skb)->saddr; fl4.saddr = 0; fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos); @@ -1046,6 +1046,7 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo if (event == NETDEV_UNREGISTER) { fib_disable_ip(dev, 2, -1); + rt_flush_dev(dev); return NOTIFY_DONE; } diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index da0cc2e6b250..da80dc14cc76 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -140,6 +140,21 @@ const struct fib_prop fib_props[RTN_MAX + 1] = { }, }; +static void rt_fibinfo_free(struct rtable __rcu **rtp) +{ + struct rtable *rt = rcu_dereference_protected(*rtp, 1); + + if (!rt) + return; + + /* Not even needed : RCU_INIT_POINTER(*rtp, NULL); + * because we waited an RCU grace period before calling + * free_fib_info_rcu() + */ + + dst_free(&rt->dst); +} + static void free_nh_exceptions(struct fib_nh *nh) { struct fnhe_hash_bucket *hash = nh->nh_exceptions; @@ -153,6 +168,9 @@ static void free_nh_exceptions(struct fib_nh *nh) struct fib_nh_exception *next; next = rcu_dereference_protected(fnhe->fnhe_next, 1); + + rt_fibinfo_free(&fnhe->fnhe_rth); + kfree(fnhe); fnhe = next; @@ -161,6 +179,23 @@ static void free_nh_exceptions(struct fib_nh *nh) kfree(hash); } +static void rt_fibinfo_free_cpus(struct rtable __rcu * __percpu *rtp) +{ + int cpu; + + if (!rtp) + return; + + for_each_possible_cpu(cpu) { + struct rtable *rt; + + rt = rcu_dereference_protected(*per_cpu_ptr(rtp, cpu), 1); + if (rt) + dst_free(&rt->dst); + } + free_percpu(rtp); +} + /* Release a nexthop info record */ static void free_fib_info_rcu(struct rcu_head *head) { @@ -171,10 +206,8 @@ static void free_fib_info_rcu(struct rcu_head *head) dev_put(nexthop_nh->nh_dev); if (nexthop_nh->nh_exceptions) free_nh_exceptions(nexthop_nh); - if (nexthop_nh->nh_rth_output) - dst_free(&nexthop_nh->nh_rth_output->dst); - if (nexthop_nh->nh_rth_input) - dst_free(&nexthop_nh->nh_rth_input->dst); + rt_fibinfo_free_cpus(nexthop_nh->nh_pcpu_rth_output); + rt_fibinfo_free(&nexthop_nh->nh_rth_input); } endfor_nexthops(fi); release_net(fi->fib_net); @@ -804,6 +837,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg) fi->fib_nhs = nhs; change_nexthops(fi) { nexthop_nh->nh_parent = fi; + nexthop_nh->nh_pcpu_rth_output = alloc_percpu(struct rtable __rcu *); } endfor_nexthops(fi) if (cfg->fc_mx) { diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 18cbc15b20d5..3c820dae235e 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -159,7 +159,6 @@ struct trie { #endif }; -static void put_child(struct trie *t, struct tnode *tn, int i, struct rt_trie_node *n); static void tnode_put_child_reorg(struct tnode *tn, int i, struct rt_trie_node *n, int wasfull); static struct rt_trie_node *resize(struct trie *t, struct tnode *tn); @@ -368,7 +367,7 @@ static void __leaf_free_rcu(struct rcu_head *head) static inline void free_leaf(struct leaf *l) { - call_rcu_bh(&l->rcu, __leaf_free_rcu); + call_rcu(&l->rcu, __leaf_free_rcu); } static inline void free_leaf_info(struct leaf_info *leaf) @@ -473,7 +472,7 @@ static struct tnode *tnode_new(t_key key, int pos, int bits) } pr_debug("AT %p s=%zu %zu\n", tn, sizeof(struct tnode), - sizeof(struct rt_trie_node) << bits); + sizeof(struct rt_trie_node *) << bits); return tn; } @@ -490,7 +489,7 @@ static inline int tnode_full(const struct tnode *tn, const struct rt_trie_node * return ((struct tnode *) n)->pos == tn->pos + tn->bits; } -static inline void put_child(struct trie *t, struct tnode *tn, int i, +static inline void put_child(struct tnode *tn, int i, struct rt_trie_node *n) { tnode_put_child_reorg(tn, i, n, -1); @@ -754,8 +753,8 @@ static struct tnode *inflate(struct trie *t, struct tnode *tn) goto nomem; } - put_child(t, tn, 2*i, (struct rt_trie_node *) left); - put_child(t, tn, 2*i+1, (struct rt_trie_node *) right); + put_child(tn, 2*i, (struct rt_trie_node *) left); + put_child(tn, 2*i+1, (struct rt_trie_node *) right); } } @@ -776,9 +775,9 @@ static struct tnode *inflate(struct trie *t, struct tnode *tn) if (tkey_extract_bits(node->key, oldtnode->pos + oldtnode->bits, 1) == 0) - put_child(t, tn, 2*i, node); + put_child(tn, 2*i, node); else - put_child(t, tn, 2*i+1, node); + put_child(tn, 2*i+1, node); continue; } @@ -786,8 +785,8 @@ static struct tnode *inflate(struct trie *t, struct tnode *tn) inode = (struct tnode *) node; if (inode->bits == 1) { - put_child(t, tn, 2*i, rtnl_dereference(inode->child[0])); - put_child(t, tn, 2*i+1, rtnl_dereference(inode->child[1])); + put_child(tn, 2*i, rtnl_dereference(inode->child[0])); + put_child(tn, 2*i+1, rtnl_dereference(inode->child[1])); tnode_free_safe(inode); continue; @@ -817,22 +816,22 @@ static struct tnode *inflate(struct trie *t, struct tnode *tn) */ left = (struct tnode *) tnode_get_child(tn, 2*i); - put_child(t, tn, 2*i, NULL); + put_child(tn, 2*i, NULL); BUG_ON(!left); right = (struct tnode *) tnode_get_child(tn, 2*i+1); - put_child(t, tn, 2*i+1, NULL); + put_child(tn, 2*i+1, NULL); BUG_ON(!right); size = tnode_child_length(left); for (j = 0; j < size; j++) { - put_child(t, left, j, rtnl_dereference(inode->child[j])); - put_child(t, right, j, rtnl_dereference(inode->child[j + size])); + put_child(left, j, rtnl_dereference(inode->child[j])); + put_child(right, j, rtnl_dereference(inode->child[j + size])); } - put_child(t, tn, 2*i, resize(t, left)); - put_child(t, tn, 2*i+1, resize(t, right)); + put_child(tn, 2*i, resize(t, left)); + put_child(tn, 2*i+1, resize(t, right)); tnode_free_safe(inode); } @@ -877,7 +876,7 @@ static struct tnode *halve(struct trie *t, struct tnode *tn) if (!newn) goto nomem; - put_child(t, tn, i/2, (struct rt_trie_node *)newn); + put_child(tn, i/2, (struct rt_trie_node *)newn); } } @@ -892,21 +891,21 @@ static struct tnode *halve(struct trie *t, struct tnode *tn) if (left == NULL) { if (right == NULL) /* Both are empty */ continue; - put_child(t, tn, i/2, right); + put_child(tn, i/2, right); continue; } if (right == NULL) { - put_child(t, tn, i/2, left); + put_child(tn, i/2, left); continue; } /* Two nonempty children */ newBinNode = (struct tnode *) tnode_get_child(tn, i/2); - put_child(t, tn, i/2, NULL); - put_child(t, newBinNode, 0, left); - put_child(t, newBinNode, 1, right); - put_child(t, tn, i/2, resize(t, newBinNode)); + put_child(tn, i/2, NULL); + put_child(newBinNode, 0, left); + put_child(newBinNode, 1, right); + put_child(tn, i/2, resize(t, newBinNode)); } tnode_free_safe(oldtnode); return tn; @@ -1125,7 +1124,7 @@ static struct list_head *fib_insert_node(struct trie *t, u32 key, int plen) node_set_parent((struct rt_trie_node *)l, tp); cindex = tkey_extract_bits(key, tp->pos, tp->bits); - put_child(t, tp, cindex, (struct rt_trie_node *)l); + put_child(tp, cindex, (struct rt_trie_node *)l); } else { /* Case 3: n is a LEAF or a TNODE and the key doesn't match. */ /* @@ -1155,12 +1154,12 @@ static struct list_head *fib_insert_node(struct trie *t, u32 key, int plen) node_set_parent((struct rt_trie_node *)tn, tp); missbit = tkey_extract_bits(key, newpos, 1); - put_child(t, tn, missbit, (struct rt_trie_node *)l); - put_child(t, tn, 1-missbit, n); + put_child(tn, missbit, (struct rt_trie_node *)l); + put_child(tn, 1-missbit, n); if (tp) { cindex = tkey_extract_bits(key, tp->pos, tp->bits); - put_child(t, tp, cindex, (struct rt_trie_node *)tn); + put_child(tp, cindex, (struct rt_trie_node *)tn); } else { rcu_assign_pointer(t->trie, (struct rt_trie_node *)tn); tp = tn; @@ -1551,7 +1550,8 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp, * state.directly. */ if (pref_mismatch) { - int mp = KEYLENGTH - fls(pref_mismatch); + /* fls(x) = __fls(x) + 1 */ + int mp = KEYLENGTH - __fls(pref_mismatch) - 1; if (tkey_extract_bits(cn->key, mp, cn->pos - mp) != 0) goto backtrace; @@ -1619,7 +1619,7 @@ static void trie_leaf_remove(struct trie *t, struct leaf *l) if (tp) { t_key cindex = tkey_extract_bits(l->key, tp->pos, tp->bits); - put_child(t, tp, cindex, NULL); + put_child(tp, cindex, NULL); trie_rebalance(t, tp); } else RCU_INIT_POINTER(t->trie, NULL); @@ -1656,7 +1656,12 @@ int fib_table_delete(struct fib_table *tb, struct fib_config *cfg) if (!l) return -ESRCH; - fa_head = get_fa_head(l, plen); + li = find_leaf_info(l, plen); + + if (!li) + return -ESRCH; + + fa_head = &li->falh; fa = fib_find_alias(fa_head, tos, 0); if (!fa) @@ -1692,9 +1697,6 @@ int fib_table_delete(struct fib_table *tb, struct fib_config *cfg) rtmsg_fib(RTM_DELROUTE, htonl(key), fa, plen, tb->tb_id, &cfg->fc_nlinfo, 0); - l = fib_find_node(t, key); - li = find_leaf_info(l, plen); - list_del_rcu(&fa->fa_list); if (!plen) diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 6699f23e6f55..0b5580c69f2d 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -2435,6 +2435,8 @@ static int igmp_mc_seq_show(struct seq_file *seq, void *v) struct ip_mc_list *im = (struct ip_mc_list *)v; struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); char *querier; + long delta; + #ifdef CONFIG_IP_MULTICAST querier = IGMP_V1_SEEN(state->in_dev) ? "V1" : IGMP_V2_SEEN(state->in_dev) ? "V2" : @@ -2448,11 +2450,12 @@ static int igmp_mc_seq_show(struct seq_file *seq, void *v) state->dev->ifindex, state->dev->name, state->in_dev->mc_count, querier); } + delta = im->timer.expires - jiffies; seq_printf(seq, "\t\t\t\t%08X %5d %d:%08lX\t\t%d\n", im->multiaddr, im->users, - im->tm_running, im->tm_running ? - jiffies_to_clock_t(im->timer.expires-jiffies) : 0, + im->tm_running, + im->tm_running ? jiffies_delta_to_clock_t(delta) : 0, im->reporter); } return 0; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index db0cf17c00f7..7f75f21d7b83 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -404,12 +404,15 @@ struct dst_entry *inet_csk_route_child_sock(struct sock *sk, { const struct inet_request_sock *ireq = inet_rsk(req); struct inet_sock *newinet = inet_sk(newsk); - struct ip_options_rcu *opt = ireq->opt; + struct ip_options_rcu *opt; struct net *net = sock_net(sk); struct flowi4 *fl4; struct rtable *rt; fl4 = &newinet->cork.fl.u.ip4; + + rcu_read_lock(); + opt = rcu_dereference(newinet->inet_opt); flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark, RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, sk->sk_protocol, inet_sk_flowi_flags(sk), @@ -421,11 +424,13 @@ struct dst_entry *inet_csk_route_child_sock(struct sock *sk, goto no_route; if (opt && opt->opt.is_strictroute && rt->rt_gateway) goto route_err; + rcu_read_unlock(); return &rt->dst; route_err: ip_rt_put(rt); no_route: + rcu_read_unlock(); IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES); return NULL; } diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 981ff1eef28c..f1395a6fb35f 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -325,14 +325,12 @@ static int ip_rcv_finish(struct sk_buff *skb) const struct net_protocol *ipprot; int protocol = iph->protocol; - rcu_read_lock(); ipprot = rcu_dereference(inet_protos[protocol]); if (ipprot && ipprot->early_demux) { ipprot->early_demux(skb); /* must reload iph, skb->head might have changed */ iph = ip_hdr(skb); } - rcu_read_unlock(); } /* diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index ba39a52d18c1..c196d749daf2 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -197,7 +197,7 @@ static inline int ip_finish_output2(struct sk_buff *skb) neigh = __ipv4_neigh_lookup_noref(dev, nexthop); if (unlikely(!neigh)) neigh = __neigh_create(&arp_tbl, &nexthop, dev, false); - if (neigh) { + if (!IS_ERR(neigh)) { int res = dst_neigh_output(dst, neigh, skb); rcu_read_unlock_bh(); @@ -1338,10 +1338,10 @@ struct sk_buff *__ip_make_skb(struct sock *sk, iph->ihl = 5; iph->tos = inet->tos; iph->frag_off = df; - ip_select_ident(iph, &rt->dst, sk); iph->ttl = ttl; iph->protocol = sk->sk_protocol; ip_copy_addrs(iph, fl4); + ip_select_ident(iph, &rt->dst, sk); if (opt) { iph->ihl += opt->optlen>>2; @@ -1366,9 +1366,8 @@ out: return skb; } -int ip_send_skb(struct sk_buff *skb) +int ip_send_skb(struct net *net, struct sk_buff *skb) { - struct net *net = sock_net(skb->sk); int err; err = ip_local_out(skb); @@ -1391,7 +1390,7 @@ int ip_push_pending_frames(struct sock *sk, struct flowi4 *fl4) return 0; /* Netfilter gets whole the not fragmented skb. */ - return ip_send_skb(skb); + return ip_send_skb(sock_net(sk), skb); } /* @@ -1536,6 +1535,7 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr, arg->csumoffset) = csum_fold(csum_add(nskb->csum, arg->csum)); nskb->ip_summed = CHECKSUM_NONE; + skb_orphan(nskb); skb_set_queue_mapping(nskb, skb_get_queue_mapping(skb)); ip_push_pending_frames(sk, &fl4); } diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 8eec8f4a0536..3a57570c8ee5 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1798,7 +1798,7 @@ static struct mr_table *ipmr_rt_fib_lookup(struct net *net, struct sk_buff *skb) .flowi4_oif = (rt_is_output_route(rt) ? skb->dev->ifindex : 0), .flowi4_iif = (rt_is_output_route(rt) ? - net->loopback_dev->ifindex : + LOOPBACK_IFINDEX : skb->dev->ifindex), .flowi4_mark = skb->mark, }; diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c index 31371be8174b..c30130062cd6 100644 --- a/net/ipv4/netfilter/ipt_rpfilter.c +++ b/net/ipv4/netfilter/ipt_rpfilter.c @@ -85,7 +85,7 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) return ipv4_is_local_multicast(iph->daddr) ^ invert; flow.flowi4_iif = 0; } else { - flow.flowi4_iif = dev_net(par->in)->loopback_dev->ifindex; + flow.flowi4_iif = LOOPBACK_IFINDEX; } flow.daddr = iph->saddr; diff --git a/net/ipv4/netfilter/nf_nat_sip.c b/net/ipv4/netfilter/nf_nat_sip.c index ea4a23813d26..4ad9cf173992 100644 --- a/net/ipv4/netfilter/nf_nat_sip.c +++ b/net/ipv4/netfilter/nf_nat_sip.c @@ -148,7 +148,7 @@ static unsigned int ip_nat_sip(struct sk_buff *skb, unsigned int dataoff, if (ct_sip_parse_header_uri(ct, *dptr, NULL, *datalen, hdr, NULL, &matchoff, &matchlen, &addr, &port) > 0) { - unsigned int matchend, poff, plen, buflen, n; + unsigned int olen, matchend, poff, plen, buflen, n; char buffer[sizeof("nnn.nnn.nnn.nnn:nnnnn")]; /* We're only interested in headers related to this @@ -163,17 +163,18 @@ static unsigned int ip_nat_sip(struct sk_buff *skb, unsigned int dataoff, goto next; } + olen = *datalen; if (!map_addr(skb, dataoff, dptr, datalen, matchoff, matchlen, &addr, port)) return NF_DROP; - matchend = matchoff + matchlen; + matchend = matchoff + matchlen + *datalen - olen; /* The maddr= parameter (RFC 2361) specifies where to send * the reply. */ if (ct_sip_parse_address_param(ct, *dptr, matchend, *datalen, "maddr=", &poff, &plen, - &addr) > 0 && + &addr, true) > 0 && addr.ip == ct->tuplehash[dir].tuple.src.u3.ip && addr.ip != ct->tuplehash[!dir].tuple.dst.u3.ip) { buflen = sprintf(buffer, "%pI4", @@ -187,7 +188,7 @@ static unsigned int ip_nat_sip(struct sk_buff *skb, unsigned int dataoff, * from which the server received the request. */ if (ct_sip_parse_address_param(ct, *dptr, matchend, *datalen, "received=", &poff, &plen, - &addr) > 0 && + &addr, false) > 0 && addr.ip == ct->tuplehash[dir].tuple.dst.u3.ip && addr.ip != ct->tuplehash[!dir].tuple.src.u3.ip) { buflen = sprintf(buffer, "%pI4", diff --git a/net/ipv4/route.c b/net/ipv4/route.c index fc1a81ca79a7..50f6d3adb474 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -70,7 +70,6 @@ #include <linux/types.h> #include <linux/kernel.h> #include <linux/mm.h> -#include <linux/bootmem.h> #include <linux/string.h> #include <linux/socket.h> #include <linux/sockios.h> @@ -80,7 +79,6 @@ #include <linux/netdevice.h> #include <linux/proc_fs.h> #include <linux/init.h> -#include <linux/workqueue.h> #include <linux/skbuff.h> #include <linux/inetdevice.h> #include <linux/igmp.h> @@ -88,11 +86,9 @@ #include <linux/mroute.h> #include <linux/netfilter_ipv4.h> #include <linux/random.h> -#include <linux/jhash.h> #include <linux/rcupdate.h> #include <linux/times.h> #include <linux/slab.h> -#include <linux/prefetch.h> #include <net/dst.h> #include <net/net_namespace.h> #include <net/protocol.h> @@ -147,6 +143,7 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu); static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); +static void ipv4_dst_destroy(struct dst_entry *dst); static void ipv4_dst_ifdown(struct dst_entry *dst, struct net_device *dev, int how) @@ -170,6 +167,7 @@ static struct dst_ops ipv4_dst_ops = { .default_advmss = ipv4_default_advmss, .mtu = ipv4_mtu, .cow_metrics = ipv4_cow_metrics, + .destroy = ipv4_dst_destroy, .ifdown = ipv4_dst_ifdown, .negative_advice = ipv4_negative_advice, .link_failure = ipv4_link_failure, @@ -587,11 +585,17 @@ static void ip_rt_build_flow_key(struct flowi4 *fl4, const struct sock *sk, build_sk_flow_key(fl4, sk); } -static DEFINE_SEQLOCK(fnhe_seqlock); +static inline void rt_free(struct rtable *rt) +{ + call_rcu(&rt->dst.rcu_head, dst_rcu_free); +} + +static DEFINE_SPINLOCK(fnhe_lock); static struct fib_nh_exception *fnhe_oldest(struct fnhe_hash_bucket *hash) { struct fib_nh_exception *fnhe, *oldest; + struct rtable *orig; oldest = rcu_dereference(hash->chain); for (fnhe = rcu_dereference(oldest->fnhe_next); fnhe; @@ -599,6 +603,11 @@ static struct fib_nh_exception *fnhe_oldest(struct fnhe_hash_bucket *hash) if (time_before(fnhe->fnhe_stamp, oldest->fnhe_stamp)) oldest = fnhe; } + orig = rcu_dereference(oldest->fnhe_rth); + if (orig) { + RCU_INIT_POINTER(oldest->fnhe_rth, NULL); + rt_free(orig); + } return oldest; } @@ -620,7 +629,7 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, int depth; u32 hval = fnhe_hashfun(daddr); - write_seqlock_bh(&fnhe_seqlock); + spin_lock_bh(&fnhe_lock); hash = nh->nh_exceptions; if (!hash) { @@ -667,7 +676,7 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, fnhe->fnhe_stamp = jiffies; out_unlock: - write_sequnlock_bh(&fnhe_seqlock); + spin_unlock_bh(&fnhe_lock); return; } @@ -1164,53 +1173,62 @@ static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr) return NULL; } -static void rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe, +static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe, __be32 daddr) { - __be32 fnhe_daddr, gw; - unsigned long expires; - unsigned int seq; - u32 pmtu; - -restart: - seq = read_seqbegin(&fnhe_seqlock); - fnhe_daddr = fnhe->fnhe_daddr; - gw = fnhe->fnhe_gw; - pmtu = fnhe->fnhe_pmtu; - expires = fnhe->fnhe_expires; - if (read_seqretry(&fnhe_seqlock, seq)) - goto restart; - - if (daddr != fnhe_daddr) - return; + bool ret = false; + + spin_lock_bh(&fnhe_lock); + + if (daddr == fnhe->fnhe_daddr) { + struct rtable *orig; - if (pmtu) { - unsigned long diff = expires - jiffies; + if (fnhe->fnhe_pmtu) { + unsigned long expires = fnhe->fnhe_expires; + unsigned long diff = expires - jiffies; - if (time_before(jiffies, expires)) { - rt->rt_pmtu = pmtu; - dst_set_expires(&rt->dst, diff); + if (time_before(jiffies, expires)) { + rt->rt_pmtu = fnhe->fnhe_pmtu; + dst_set_expires(&rt->dst, diff); + } } + if (fnhe->fnhe_gw) { + rt->rt_flags |= RTCF_REDIRECTED; + rt->rt_gateway = fnhe->fnhe_gw; + } + + orig = rcu_dereference(fnhe->fnhe_rth); + rcu_assign_pointer(fnhe->fnhe_rth, rt); + if (orig) + rt_free(orig); + + fnhe->fnhe_stamp = jiffies; + ret = true; + } else { + /* Routes we intend to cache in nexthop exception have + * the DST_NOCACHE bit clear. However, if we are + * unsuccessful at storing this route into the cache + * we really need to set it. + */ + rt->dst.flags |= DST_NOCACHE; } - if (gw) { - rt->rt_flags |= RTCF_REDIRECTED; - rt->rt_gateway = gw; - } - fnhe->fnhe_stamp = jiffies; -} + spin_unlock_bh(&fnhe_lock); -static inline void rt_free(struct rtable *rt) -{ - call_rcu_bh(&rt->dst.rcu_head, dst_rcu_free); + return ret; } -static void rt_cache_route(struct fib_nh *nh, struct rtable *rt) +static bool rt_cache_route(struct fib_nh *nh, struct rtable *rt) { - struct rtable *orig, *prev, **p = &nh->nh_rth_output; - - if (rt_is_input_route(rt)) - p = &nh->nh_rth_input; + struct rtable *orig, *prev, **p; + bool ret = true; + if (rt_is_input_route(rt)) { + p = (struct rtable **)&nh->nh_rth_input; + } else { + if (!nh->nh_pcpu_rth_output) + goto nocache; + p = (struct rtable **)__this_cpu_ptr(nh->nh_pcpu_rth_output); + } orig = *p; prev = cmpxchg(p, orig, rt); @@ -1223,7 +1241,50 @@ static void rt_cache_route(struct fib_nh *nh, struct rtable *rt) * unsuccessful at storing this route into the cache * we really need to set it. */ +nocache: rt->dst.flags |= DST_NOCACHE; + ret = false; + } + + return ret; +} + +static DEFINE_SPINLOCK(rt_uncached_lock); +static LIST_HEAD(rt_uncached_list); + +static void rt_add_uncached_list(struct rtable *rt) +{ + spin_lock_bh(&rt_uncached_lock); + list_add_tail(&rt->rt_uncached, &rt_uncached_list); + spin_unlock_bh(&rt_uncached_lock); +} + +static void ipv4_dst_destroy(struct dst_entry *dst) +{ + struct rtable *rt = (struct rtable *) dst; + + if (dst->flags & DST_NOCACHE) { + spin_lock_bh(&rt_uncached_lock); + list_del(&rt->rt_uncached); + spin_unlock_bh(&rt_uncached_lock); + } +} + +void rt_flush_dev(struct net_device *dev) +{ + if (!list_empty(&rt_uncached_list)) { + struct net *net = dev_net(dev); + struct rtable *rt; + + spin_lock_bh(&rt_uncached_lock); + list_for_each_entry(rt, &rt_uncached_list, rt_uncached) { + if (rt->dst.dev != dev) + continue; + rt->dst.dev = net->loopback_dev; + dev_hold(rt->dst.dev); + dev_put(dev); + } + spin_unlock_bh(&rt_uncached_lock); } } @@ -1239,20 +1300,24 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr, struct fib_nh_exception *fnhe, struct fib_info *fi, u16 type, u32 itag) { + bool cached = false; + if (fi) { struct fib_nh *nh = &FIB_RES_NH(*res); if (nh->nh_gw && nh->nh_scope == RT_SCOPE_LINK) rt->rt_gateway = nh->nh_gw; - if (unlikely(fnhe)) - rt_bind_exception(rt, fnhe, daddr); dst_init_metrics(&rt->dst, fi->fib_metrics, true); #ifdef CONFIG_IP_ROUTE_CLASSID rt->dst.tclassid = nh->nh_tclassid; #endif - if (!(rt->dst.flags & DST_NOCACHE)) - rt_cache_route(nh, rt); + if (unlikely(fnhe)) + cached = rt_bind_exception(rt, fnhe, daddr); + else if (!(rt->dst.flags & DST_NOCACHE)) + cached = rt_cache_route(nh, rt); } + if (unlikely(!cached)) + rt_add_uncached_list(rt); #ifdef CONFIG_IP_ROUTE_CLASSID #ifdef CONFIG_IP_MULTIPLE_TABLES @@ -1319,6 +1384,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, rth->rt_iif = 0; rth->rt_pmtu = 0; rth->rt_gateway = 0; + INIT_LIST_HEAD(&rth->rt_uncached); if (our) { rth->dst.input= ip_local_deliver; rth->rt_flags |= RTCF_LOCAL; @@ -1420,7 +1486,7 @@ static int __mkroute_input(struct sk_buff *skb, do_cache = false; if (res->fi) { if (!itag) { - rth = FIB_RES_NH(*res).nh_rth_input; + rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input); if (rt_cache_valid(rth)) { skb_dst_set_noref(skb, &rth->dst); goto out; @@ -1444,6 +1510,7 @@ static int __mkroute_input(struct sk_buff *skb, rth->rt_iif = 0; rth->rt_pmtu = 0; rth->rt_gateway = 0; + INIT_LIST_HEAD(&rth->rt_uncached); rth->dst.input = ip_forward; rth->dst.output = ip_output; @@ -1520,11 +1587,14 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (ipv4_is_zeronet(daddr)) goto martian_destination; - if (likely(!IN_DEV_ROUTE_LOCALNET(in_dev))) { - if (ipv4_is_loopback(daddr)) + /* Following code try to avoid calling IN_DEV_NET_ROUTE_LOCALNET(), + * and call it once if daddr or/and saddr are loopback addresses + */ + if (ipv4_is_loopback(daddr)) { + if (!IN_DEV_NET_ROUTE_LOCALNET(in_dev, net)) goto martian_destination; - - if (ipv4_is_loopback(saddr)) + } else if (ipv4_is_loopback(saddr)) { + if (!IN_DEV_NET_ROUTE_LOCALNET(in_dev, net)) goto martian_source; } @@ -1549,7 +1619,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (res.type == RTN_LOCAL) { err = fib_validate_source(skb, saddr, daddr, tos, - net->loopback_dev->ifindex, + LOOPBACK_IFINDEX, dev, in_dev, &itag); if (err < 0) goto martian_source_keep_err; @@ -1582,7 +1652,7 @@ local_input: do_cache = false; if (res.fi) { if (!itag) { - rth = FIB_RES_NH(res).nh_rth_input; + rth = rcu_dereference(FIB_RES_NH(res).nh_rth_input); if (rt_cache_valid(rth)) { skb_dst_set_noref(skb, &rth->dst); err = 0; @@ -1610,6 +1680,7 @@ local_input: rth->rt_iif = 0; rth->rt_pmtu = 0; rth->rt_gateway = 0; + INIT_LIST_HEAD(&rth->rt_uncached); if (res.type == RTN_UNREACHABLE) { rth->dst.input= ip_error; rth->dst.error= -err; @@ -1748,19 +1819,23 @@ static struct rtable *__mkroute_output(const struct fib_result *res, fnhe = NULL; if (fi) { + struct rtable __rcu **prth; + fnhe = find_exception(&FIB_RES_NH(*res), fl4->daddr); - if (!fnhe) { - rth = FIB_RES_NH(*res).nh_rth_output; - if (rt_cache_valid(rth)) { - dst_hold(&rth->dst); - return rth; - } + if (fnhe) + prth = &fnhe->fnhe_rth; + else + prth = __this_cpu_ptr(FIB_RES_NH(*res).nh_pcpu_rth_output); + rth = rcu_dereference(*prth); + if (rt_cache_valid(rth)) { + dst_hold(&rth->dst); + return rth; } } rth = rt_dst_alloc(dev_out, IN_DEV_CONF_GET(in_dev, NOPOLICY), IN_DEV_CONF_GET(in_dev, NOXFRM), - fi && !fnhe); + fi); if (!rth) return ERR_PTR(-ENOBUFS); @@ -1773,6 +1848,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res, rth->rt_iif = orig_oif ? : 0; rth->rt_pmtu = 0; rth->rt_gateway = 0; + INIT_LIST_HEAD(&rth->rt_uncached); RT_CACHE_STAT_INC(out_slow_tot); @@ -1819,7 +1895,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) orig_oif = fl4->flowi4_oif; - fl4->flowi4_iif = net->loopback_dev->ifindex; + fl4->flowi4_iif = LOOPBACK_IFINDEX; fl4->flowi4_tos = tos & IPTOS_RT_MASK; fl4->flowi4_scope = ((tos & RTO_ONLINK) ? RT_SCOPE_LINK : RT_SCOPE_UNIVERSE); @@ -1908,7 +1984,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) if (!fl4->daddr) fl4->daddr = fl4->saddr = htonl(INADDR_LOOPBACK); dev_out = net->loopback_dev; - fl4->flowi4_oif = net->loopback_dev->ifindex; + fl4->flowi4_oif = LOOPBACK_IFINDEX; res.type = RTN_LOCAL; flags |= RTCF_LOCAL; goto make_route; @@ -1955,7 +2031,6 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) } dev_out = net->loopback_dev; fl4->flowi4_oif = dev_out->ifindex; - res.fi = NULL; flags |= RTCF_LOCAL; goto make_route; } @@ -2052,6 +2127,8 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or rt->rt_type = ort->rt_type; rt->rt_gateway = ort->rt_gateway; + INIT_LIST_HEAD(&rt->rt_uncached); + dst_free(new); } diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 5840c3255721..1b5ce96707a3 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -184,7 +184,7 @@ static int ipv4_tcp_mem(ctl_table *ctl, int write, int ret; unsigned long vec[3]; struct net *net = current->nsproxy->net_ns; -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM +#ifdef CONFIG_MEMCG_KMEM struct mem_cgroup *memcg; #endif @@ -203,7 +203,7 @@ static int ipv4_tcp_mem(ctl_table *ctl, int write, if (ret) return ret; -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM +#ifdef CONFIG_MEMCG_KMEM rcu_read_lock(); memcg = mem_cgroup_from_task(current); @@ -784,13 +784,6 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = proc_dointvec }, { - .procname = "rt_cache_rebuild_count", - .data = &init_net.ipv4.sysctl_rt_cache_rebuild_count, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { .procname = "ping_group_range", .data = &init_net.ipv4.sysctl_ping_group_range, .maxlen = sizeof(init_net.ipv4.sysctl_ping_group_range), @@ -829,8 +822,6 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) table[5].data = &net->ipv4.sysctl_icmp_ratemask; table[6].data = - &net->ipv4.sysctl_rt_cache_rebuild_count; - table[7].data = &net->ipv4.sysctl_ping_group_range; } @@ -842,8 +833,6 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) net->ipv4.sysctl_ping_group_range[0] = 1; net->ipv4.sysctl_ping_group_range[1] = 0; - net->ipv4.sysctl_rt_cache_rebuild_count = 4; - tcp_init_mem(net); net->ipv4.ipv4_hdr = register_net_sysctl(net, "net/ipv4", table); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 581ecf02c6b5..2109ff4a1daf 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -811,7 +811,9 @@ static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now, old_size_goal + mss_now > xmit_size_goal)) { xmit_size_goal = old_size_goal; } else { - tp->xmit_size_goal_segs = xmit_size_goal / mss_now; + tp->xmit_size_goal_segs = + min_t(u16, xmit_size_goal / mss_now, + sk->sk_gso_max_segs); xmit_size_goal = tp->xmit_size_goal_segs * mss_now; } } @@ -2681,7 +2683,10 @@ static int do_tcp_setsockopt(struct sock *sk, int level, /* Cap the max timeout in ms TCP will retry/retrans * before giving up and aborting (ETIMEDOUT) a connection. */ - icsk->icsk_user_timeout = msecs_to_jiffies(val); + if (val < 0) + err = -EINVAL; + else + icsk->icsk_user_timeout = msecs_to_jiffies(val); break; default: err = -ENOPROTOOPT; diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 4d4db16e336e..1432cdb0644c 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -291,7 +291,8 @@ bool tcp_is_cwnd_limited(const struct sock *sk, u32 in_flight) left = tp->snd_cwnd - in_flight; if (sk_can_gso(sk) && left * sysctl_tcp_tso_win_divisor < tp->snd_cwnd && - left * tp->mss_cache < sk->sk_gso_max_size) + left * tp->mss_cache < sk->sk_gso_max_size && + left < sk->sk_gso_max_segs) return true; return left <= tcp_max_tso_deferred_mss(tp); } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 3e07a64ca44e..bcfccc5cb8d0 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -237,7 +237,11 @@ static inline void TCP_ECN_check_ce(struct tcp_sock *tp, const struct sk_buff *s tcp_enter_quickack_mode((struct sock *)tp); break; case INET_ECN_CE: - tp->ecn_flags |= TCP_ECN_DEMAND_CWR; + if (!(tp->ecn_flags & TCP_ECN_DEMAND_CWR)) { + /* Better not delay acks, sender can have a very low cwnd */ + tcp_enter_quickack_mode((struct sock *)tp); + tp->ecn_flags |= TCP_ECN_DEMAND_CWR; + } /* fallinto */ default: tp->ecn_flags |= TCP_ECN_SEEN; @@ -4351,19 +4355,20 @@ static void tcp_ofo_queue(struct sock *sk) static bool tcp_prune_ofo_queue(struct sock *sk); static int tcp_prune_queue(struct sock *sk); -static int tcp_try_rmem_schedule(struct sock *sk, unsigned int size) +static int tcp_try_rmem_schedule(struct sock *sk, struct sk_buff *skb, + unsigned int size) { if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf || - !sk_rmem_schedule(sk, size)) { + !sk_rmem_schedule(sk, skb, size)) { if (tcp_prune_queue(sk) < 0) return -1; - if (!sk_rmem_schedule(sk, size)) { + if (!sk_rmem_schedule(sk, skb, size)) { if (!tcp_prune_ofo_queue(sk)) return -1; - if (!sk_rmem_schedule(sk, size)) + if (!sk_rmem_schedule(sk, skb, size)) return -1; } } @@ -4418,7 +4423,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) TCP_ECN_check_ce(tp, skb); - if (unlikely(tcp_try_rmem_schedule(sk, skb->truesize))) { + if (unlikely(tcp_try_rmem_schedule(sk, skb, skb->truesize))) { NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPOFODROP); __kfree_skb(skb); return; @@ -4552,17 +4557,17 @@ static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, int int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size) { - struct sk_buff *skb; + struct sk_buff *skb = NULL; struct tcphdr *th; bool fragstolen; - if (tcp_try_rmem_schedule(sk, size + sizeof(*th))) - goto err; - skb = alloc_skb(size + sizeof(*th), sk->sk_allocation); if (!skb) goto err; + if (tcp_try_rmem_schedule(sk, skb, size + sizeof(*th))) + goto err_free; + th = (struct tcphdr *)skb_put(skb, sizeof(*th)); skb_reset_transport_header(skb); memset(th, 0, sizeof(*th)); @@ -4633,7 +4638,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) if (eaten <= 0) { queue_and_out: if (eaten < 0 && - tcp_try_rmem_schedule(sk, skb->truesize)) + tcp_try_rmem_schedule(sk, skb, skb->truesize)) goto drop; eaten = tcp_queue_rcv(sk, skb, 0, &fragstolen); @@ -5391,6 +5396,8 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb, { struct tcp_sock *tp = tcp_sk(sk); + if (unlikely(sk->sk_rx_dst == NULL)) + inet_csk(sk)->icsk_af_ops->sk_rx_dst_set(sk, skb); /* * Header prediction. * The code loosely follows the one in the famous @@ -5475,7 +5482,9 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb, if (tp->copied_seq == tp->rcv_nxt && len - tcp_header_len <= tp->ucopy.len) { #ifdef CONFIG_NET_DMA - if (tcp_dma_try_early_copy(sk, skb, tcp_header_len)) { + if (tp->ucopy.task == current && + sock_owned_by_user(sk) && + tcp_dma_try_early_copy(sk, skb, tcp_header_len)) { copied_early = 1; eaten = 1; } @@ -5602,7 +5611,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb) tcp_set_state(sk, TCP_ESTABLISHED); if (skb != NULL) { - sk->sk_rx_dst = dst_clone(skb_dst(skb)); + icsk->icsk_af_ops->sk_rx_dst_set(sk, skb); security_inet_conn_established(sk, skb); } @@ -5737,7 +5746,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, TCP_ECN_rcv_synack(tp, th); - tp->snd_wl1 = TCP_SKB_CB(skb)->seq; + tcp_init_wl(tp, TCP_SKB_CB(skb)->seq); tcp_ack(sk, skb, FLAG_SLOWPATH); /* Ok.. it's good. Set up sequence numbers and @@ -5750,7 +5759,6 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, * never scaled. */ tp->snd_wnd = ntohs(th->window); - tcp_init_wl(tp, TCP_SKB_CB(skb)->seq); if (!tp->rx_opt.wscale_ok) { tp->rx_opt.snd_wscale = tp->rx_opt.rcv_wscale = 0; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index b6b07c93924c..1e15c5be04e7 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -417,10 +417,12 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) if (code == ICMP_FRAG_NEEDED) { /* PMTU discovery (RFC1191) */ tp->mtu_info = info; - if (!sock_owned_by_user(sk)) + if (!sock_owned_by_user(sk)) { tcp_v4_mtu_reduced(sk); - else - set_bit(TCP_MTU_REDUCED_DEFERRED, &tp->tsq_flags); + } else { + if (!test_and_set_bit(TCP_MTU_REDUCED_DEFERRED, &tp->tsq_flags)) + sock_hold(sk); + } goto out; } @@ -1462,6 +1464,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, goto exit_nonewsk; newsk->sk_gso_type = SKB_GSO_TCPV4; + inet_sk_rx_dst_set(newsk, skb); newtp = tcp_sk(newsk); newinet = inet_sk(newsk); @@ -1617,21 +1620,16 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) #endif if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ + struct dst_entry *dst = sk->sk_rx_dst; + sock_rps_save_rxhash(sk, skb); - if (sk->sk_rx_dst) { - struct dst_entry *dst = sk->sk_rx_dst; - if (dst->ops->check(dst, 0) == NULL) { + if (dst) { + if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif || + dst->ops->check(dst, 0) == NULL) { dst_release(dst); sk->sk_rx_dst = NULL; } } - if (unlikely(sk->sk_rx_dst == NULL)) { - struct inet_sock *icsk = inet_sk(sk); - struct rtable *rt = skb_rtable(skb); - - sk->sk_rx_dst = dst_clone(&rt->dst); - icsk->rx_dst_ifindex = inet_iif(skb); - } if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len)) { rsk = sk; goto reset; @@ -1709,11 +1707,11 @@ void tcp_v4_early_demux(struct sk_buff *skb) skb->destructor = sock_edemux; if (sk->sk_state != TCP_TIME_WAIT) { struct dst_entry *dst = sk->sk_rx_dst; - struct inet_sock *icsk = inet_sk(sk); + if (dst) dst = dst_check(dst, 0); if (dst && - icsk->rx_dst_ifindex == skb->skb_iif) + inet_sk(sk)->rx_dst_ifindex == skb->skb_iif) skb_dst_set_noref(skb, dst); } } @@ -1874,10 +1872,21 @@ static struct timewait_sock_ops tcp_timewait_sock_ops = { .twsk_destructor= tcp_twsk_destructor, }; +void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) +{ + struct dst_entry *dst = skb_dst(skb); + + dst_hold(dst); + sk->sk_rx_dst = dst; + inet_sk(sk)->rx_dst_ifindex = skb->skb_iif; +} +EXPORT_SYMBOL(inet_sk_rx_dst_set); + const struct inet_connection_sock_af_ops ipv4_specific = { .queue_xmit = ip_queue_xmit, .send_check = tcp_v4_send_check, .rebuild_header = inet_sk_rebuild_header, + .sk_rx_dst_set = inet_sk_rx_dst_set, .conn_request = tcp_v4_conn_request, .syn_recv_sock = tcp_v4_syn_recv_sock, .net_header_len = sizeof(struct iphdr), @@ -2387,7 +2396,7 @@ static void get_openreq4(const struct sock *sk, const struct request_sock *req, struct seq_file *f, int i, int uid, int *len) { const struct inet_request_sock *ireq = inet_rsk(req); - int ttd = req->expires - jiffies; + long delta = req->expires - jiffies; seq_printf(f, "%4d: %08X:%04X %08X:%04X" " %02X %08X:%08X %02X:%08lX %08X %5d %8d %u %d %pK%n", @@ -2399,7 +2408,7 @@ static void get_openreq4(const struct sock *sk, const struct request_sock *req, TCP_SYN_RECV, 0, 0, /* could print option size, but that is af dependent. */ 1, /* timers active (only the expire timer) */ - jiffies_to_clock_t(ttd), + jiffies_delta_to_clock_t(delta), req->retrans, uid, 0, /* non standard timer */ @@ -2450,7 +2459,7 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i, int *len) tp->write_seq - tp->snd_una, rx_queue, timer_active, - jiffies_to_clock_t(timer_expires - jiffies), + jiffies_delta_to_clock_t(timer_expires - jiffies), icsk->icsk_retransmits, sock_i_uid(sk), icsk->icsk_probes_out, @@ -2469,10 +2478,7 @@ static void get_timewait4_sock(const struct inet_timewait_sock *tw, { __be32 dest, src; __u16 destp, srcp; - int ttd = tw->tw_ttd - jiffies; - - if (ttd < 0) - ttd = 0; + long delta = tw->tw_ttd - jiffies; dest = tw->tw_daddr; src = tw->tw_rcv_saddr; @@ -2482,7 +2488,7 @@ static void get_timewait4_sock(const struct inet_timewait_sock *tw, seq_printf(f, "%4d: %08X:%04X %08X:%04X" " %02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK%n", i, src, srcp, dest, destp, tw->tw_substate, 0, 0, - 3, jiffies_to_clock_t(ttd), 0, 0, 0, 0, + 3, jiffies_delta_to_clock_t(delta), 0, 0, 0, 0, atomic_read(&tw->tw_refcnt), tw, len); } @@ -2635,7 +2641,7 @@ struct proto tcp_prot = { .compat_setsockopt = compat_tcp_setsockopt, .compat_getsockopt = compat_tcp_getsockopt, #endif -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM +#ifdef CONFIG_MEMCG_KMEM .init_cgroup = tcp_init_cgroup, .destroy_cgroup = tcp_destroy_cgroup, .proto_cgroup = tcp_proto_cgroup, diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 2288a6399e1e..0abe67bb4d3a 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -731,6 +731,18 @@ static int __net_init tcp_net_metrics_init(struct net *net) static void __net_exit tcp_net_metrics_exit(struct net *net) { + unsigned int i; + + for (i = 0; i < (1U << net->ipv4.tcp_metrics_hash_log) ; i++) { + struct tcp_metrics_block *tm, *next; + + tm = rcu_dereference_protected(net->ipv4.tcp_metrics_hash[i].chain, 1); + while (tm) { + next = rcu_dereference_protected(tm->tcpm_next, 1); + kfree(tm); + tm = next; + } + } kfree(net->ipv4.tcp_metrics_hash); } diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 5912ac3fd240..6ff7f10dce9d 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -387,8 +387,6 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, struct tcp_sock *oldtp = tcp_sk(sk); struct tcp_cookie_values *oldcvp = oldtp->cookie_values; - newsk->sk_rx_dst = dst_clone(skb_dst(skb)); - /* TCP Cookie Transactions require space for the cookie pair, * as it differs for each connection. There is no need to * copy any s_data_payload stored at the original socket. diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 33cd065cfbd8..d04632673a9e 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -910,14 +910,18 @@ void tcp_release_cb(struct sock *sk) if (flags & (1UL << TCP_TSQ_DEFERRED)) tcp_tsq_handler(sk); - if (flags & (1UL << TCP_WRITE_TIMER_DEFERRED)) + if (flags & (1UL << TCP_WRITE_TIMER_DEFERRED)) { tcp_write_timer_handler(sk); - - if (flags & (1UL << TCP_DELACK_TIMER_DEFERRED)) + __sock_put(sk); + } + if (flags & (1UL << TCP_DELACK_TIMER_DEFERRED)) { tcp_delack_timer_handler(sk); - - if (flags & (1UL << TCP_MTU_REDUCED_DEFERRED)) + __sock_put(sk); + } + if (flags & (1UL << TCP_MTU_REDUCED_DEFERRED)) { sk->sk_prot->mtu_reduced(sk); + __sock_put(sk); + } } EXPORT_SYMBOL(tcp_release_cb); @@ -940,7 +944,7 @@ void __init tcp_tasklet_init(void) * We cant xmit new skbs from this context, as we might already * hold qdisc lock. */ -void tcp_wfree(struct sk_buff *skb) +static void tcp_wfree(struct sk_buff *skb) { struct sock *sk = skb->sk; struct tcp_sock *tp = tcp_sk(sk); @@ -1522,21 +1526,21 @@ static void tcp_cwnd_validate(struct sock *sk) * when we would be allowed to send the split-due-to-Nagle skb fully. */ static unsigned int tcp_mss_split_point(const struct sock *sk, const struct sk_buff *skb, - unsigned int mss_now, unsigned int cwnd) + unsigned int mss_now, unsigned int max_segs) { const struct tcp_sock *tp = tcp_sk(sk); - u32 needed, window, cwnd_len; + u32 needed, window, max_len; window = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq; - cwnd_len = mss_now * cwnd; + max_len = mss_now * max_segs; - if (likely(cwnd_len <= window && skb != tcp_write_queue_tail(sk))) - return cwnd_len; + if (likely(max_len <= window && skb != tcp_write_queue_tail(sk))) + return max_len; needed = min(skb->len, window); - if (cwnd_len <= needed) - return cwnd_len; + if (max_len <= needed) + return max_len; return needed - needed % mss_now; } @@ -1765,7 +1769,8 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb) limit = min(send_win, cong_win); /* If a full-sized TSO skb can be sent, do it. */ - if (limit >= sk->sk_gso_max_size) + if (limit >= min_t(unsigned int, sk->sk_gso_max_size, + sk->sk_gso_max_segs * tp->mss_cache)) goto send_now; /* Middle in queue won't get any more data, full sendable already? */ @@ -1999,7 +2004,9 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, limit = mss_now; if (tso_segs > 1 && !tcp_urg_mode(tp)) limit = tcp_mss_split_point(sk, skb, mss_now, - cwnd_quota); + min_t(unsigned int, + cwnd_quota, + sk->sk_gso_max_segs)); if (skb->len > limit && unlikely(tso_fragment(sk, skb, limit, mss_now, gfp))) @@ -2045,7 +2052,8 @@ void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss, if (unlikely(sk->sk_state == TCP_CLOSE)) return; - if (tcp_write_xmit(sk, cur_mss, nonagle, 0, GFP_ATOMIC)) + if (tcp_write_xmit(sk, cur_mss, nonagle, 0, + sk_gfp_atomic(sk, GFP_ATOMIC))) tcp_check_probe_timer(sk); } @@ -2666,7 +2674,8 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, if (cvp != NULL && cvp->s_data_constant && cvp->s_data_desired) s_data_desired = cvp->s_data_desired; - skb = alloc_skb(MAX_TCP_HEADER + 15 + s_data_desired, GFP_ATOMIC); + skb = alloc_skb(MAX_TCP_HEADER + 15 + s_data_desired, + sk_gfp_atomic(sk, GFP_ATOMIC)); if (unlikely(!skb)) { dst_release(dst); return NULL; @@ -3064,7 +3073,7 @@ void tcp_send_ack(struct sock *sk) * tcp_transmit_skb() will set the ownership to this * sock. */ - buff = alloc_skb(MAX_TCP_HEADER, GFP_ATOMIC); + buff = alloc_skb(MAX_TCP_HEADER, sk_gfp_atomic(sk, GFP_ATOMIC)); if (buff == NULL) { inet_csk_schedule_ack(sk); inet_csk(sk)->icsk_ack.ato = TCP_ATO_MIN; @@ -3079,7 +3088,7 @@ void tcp_send_ack(struct sock *sk) /* Send it off, this clears delayed acks for us. */ TCP_SKB_CB(buff)->when = tcp_time_stamp; - tcp_transmit_skb(sk, buff, 0, GFP_ATOMIC); + tcp_transmit_skb(sk, buff, 0, sk_gfp_atomic(sk, GFP_ATOMIC)); } /* This routine sends a packet with an out of date sequence @@ -3099,7 +3108,7 @@ static int tcp_xmit_probe_skb(struct sock *sk, int urgent) struct sk_buff *skb; /* We don't queue it, tcp_transmit_skb() sets ownership. */ - skb = alloc_skb(MAX_TCP_HEADER, GFP_ATOMIC); + skb = alloc_skb(MAX_TCP_HEADER, sk_gfp_atomic(sk, GFP_ATOMIC)); if (skb == NULL) return -1; diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 6df36ad55a38..b774a03bd1dc 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -252,7 +252,8 @@ static void tcp_delack_timer(unsigned long data) inet_csk(sk)->icsk_ack.blocked = 1; NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_DELAYEDACKLOCKED); /* deleguate our work to tcp_release_cb() */ - set_bit(TCP_WRITE_TIMER_DEFERRED, &tcp_sk(sk)->tsq_flags); + if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED, &tcp_sk(sk)->tsq_flags)) + sock_hold(sk); } bh_unlock_sock(sk); sock_put(sk); @@ -481,7 +482,8 @@ static void tcp_write_timer(unsigned long data) tcp_write_timer_handler(sk); } else { /* deleguate our work to tcp_release_cb() */ - set_bit(TCP_WRITE_TIMER_DEFERRED, &tcp_sk(sk)->tsq_flags); + if (!test_and_set_bit(TCP_WRITE_TIMER_DEFERRED, &tcp_sk(sk)->tsq_flags)) + sock_hold(sk); } bh_unlock_sock(sk); sock_put(sk); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index b4c3582a991f..6f6d1aca3c3d 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -758,7 +758,7 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4) uh->check = CSUM_MANGLED_0; send: - err = ip_send_skb(skb); + err = ip_send_skb(sock_net(sk), skb); if (err) { if (err == -ENOBUFS && !inet->recverr) { UDP_INC_STATS_USER(sock_net(sk), diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index c6281847f16a..681ea2f413e2 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -92,6 +92,7 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, xdst->u.rt.rt_type = rt->rt_type; xdst->u.rt.rt_gateway = rt->rt_gateway; xdst->u.rt.rt_pmtu = rt->rt_pmtu; + INIT_LIST_HEAD(&xdst->u.rt.rt_uncached); return 0; } |