diff options
Diffstat (limited to 'net/ipv4')
-rw-r--r-- | net/ipv4/af_inet.c | 14 | ||||
-rw-r--r-- | net/ipv4/devinet.c | 76 | ||||
-rw-r--r-- | net/ipv4/esp4.c | 6 | ||||
-rw-r--r-- | net/ipv4/fib_frontend.c | 15 | ||||
-rw-r--r-- | net/ipv4/fib_semantics.c | 23 | ||||
-rw-r--r-- | net/ipv4/fib_trie.c | 33 | ||||
-rw-r--r-- | net/ipv4/icmp.c | 23 | ||||
-rw-r--r-- | net/ipv4/inet_connection_sock.c | 11 | ||||
-rw-r--r-- | net/ipv4/inet_fragment.c | 30 | ||||
-rw-r--r-- | net/ipv4/inet_hashtables.c | 8 | ||||
-rw-r--r-- | net/ipv4/inet_timewait_sock.c | 7 | ||||
-rw-r--r-- | net/ipv4/ip_fragment.c | 25 | ||||
-rw-r--r-- | net/ipv4/ip_gre.c | 30 | ||||
-rw-r--r-- | net/ipv4/ip_input.c | 6 | ||||
-rw-r--r-- | net/ipv4/ip_options.c | 7 | ||||
-rw-r--r-- | net/ipv4/ipconfig.c | 3 | ||||
-rw-r--r-- | net/ipv4/netfilter/Kconfig | 13 | ||||
-rw-r--r-- | net/ipv4/netfilter/ipt_CLUSTERIP.c | 2 | ||||
-rw-r--r-- | net/ipv4/netfilter/ipt_rpfilter.c | 8 | ||||
-rw-r--r-- | net/ipv4/ping.c | 4 | ||||
-rw-r--r-- | net/ipv4/raw.c | 8 | ||||
-rw-r--r-- | net/ipv4/syncookies.c | 4 | ||||
-rw-r--r-- | net/ipv4/tcp.c | 10 | ||||
-rw-r--r-- | net/ipv4/tcp_input.c | 77 | ||||
-rw-r--r-- | net/ipv4/tcp_ipv4.c | 21 | ||||
-rw-r--r-- | net/ipv4/tcp_output.c | 35 | ||||
-rw-r--r-- | net/ipv4/udp.c | 7 |
27 files changed, 278 insertions, 228 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index e225a4e5b572..c929d9c1c4b6 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -248,8 +248,12 @@ EXPORT_SYMBOL(inet_listen); u32 inet_ehash_secret __read_mostly; EXPORT_SYMBOL(inet_ehash_secret); +u32 ipv6_hash_secret __read_mostly; +EXPORT_SYMBOL(ipv6_hash_secret); + /* - * inet_ehash_secret must be set exactly once + * inet_ehash_secret must be set exactly once, and to a non nul value + * ipv6_hash_secret must be set exactly once. */ void build_ehash_secret(void) { @@ -259,7 +263,8 @@ void build_ehash_secret(void) get_random_bytes(&rnd, sizeof(rnd)); } while (rnd == 0); - cmpxchg(&inet_ehash_secret, 0, rnd); + if (cmpxchg(&inet_ehash_secret, 0, rnd) == 0) + get_random_bytes(&ipv6_hash_secret, sizeof(ipv6_hash_secret)); } EXPORT_SYMBOL(build_ehash_secret); @@ -1327,8 +1332,9 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, if (skb->next != NULL) iph->frag_off |= htons(IP_MF); offset += (skb->len - skb->mac_len - iph->ihl * 4); - } else + } else { iph->id = htons(id++); + } iph->tot_len = htons(skb->len - skb->mac_len); iph->check = 0; iph->check = ip_fast_csum(skb_network_header(skb), iph->ihl); @@ -1572,7 +1578,7 @@ static const struct net_offload udp_offload = { static const struct net_protocol icmp_protocol = { .handler = icmp_rcv, - .err_handler = ping_err, + .err_handler = icmp_err, .no_policy = 1, .netns_ok = 1, }; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 5281314886c1..c6287cd978c2 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -139,10 +139,9 @@ struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref) 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) { + hlist_for_each_entry_rcu(ifa, &inet_addr_lst[hash], hash) { if (ifa->ifa_local == addr) { struct net_device *dev = ifa->ifa_dev->dev; @@ -588,16 +587,17 @@ static void check_lifetime(struct work_struct *work) { unsigned long now, next, next_sec, next_sched; struct in_ifaddr *ifa; - struct hlist_node *node; + struct hlist_node *n; int i; now = jiffies; next = round_jiffies_up(now + ADDR_CHECK_FREQUENCY); - rcu_read_lock(); for (i = 0; i < IN4_ADDR_HSIZE; i++) { - hlist_for_each_entry_rcu(ifa, node, - &inet_addr_lst[i], hash) { + bool change_needed = false; + + rcu_read_lock(); + hlist_for_each_entry_rcu(ifa, &inet_addr_lst[i], hash) { unsigned long age; if (ifa->ifa_flags & IFA_F_PERMANENT) @@ -609,16 +609,7 @@ static void check_lifetime(struct work_struct *work) if (ifa->ifa_valid_lft != INFINITY_LIFE_TIME && age >= ifa->ifa_valid_lft) { - struct in_ifaddr **ifap ; - - rtnl_lock(); - for (ifap = &ifa->ifa_dev->ifa_list; - *ifap != NULL; ifap = &ifa->ifa_next) { - if (*ifap == ifa) - inet_del_ifa(ifa->ifa_dev, - ifap, 1); - } - rtnl_unlock(); + change_needed = true; } else if (ifa->ifa_preferred_lft == INFINITY_LIFE_TIME) { continue; @@ -628,10 +619,8 @@ static void check_lifetime(struct work_struct *work) next = ifa->ifa_tstamp + ifa->ifa_valid_lft * HZ; - if (!(ifa->ifa_flags & IFA_F_DEPRECATED)) { - ifa->ifa_flags |= IFA_F_DEPRECATED; - rtmsg_ifa(RTM_NEWADDR, ifa, NULL, 0); - } + if (!(ifa->ifa_flags & IFA_F_DEPRECATED)) + change_needed = true; } else if (time_before(ifa->ifa_tstamp + ifa->ifa_preferred_lft * HZ, next)) { @@ -639,8 +628,42 @@ static void check_lifetime(struct work_struct *work) ifa->ifa_preferred_lft * HZ; } } + rcu_read_unlock(); + if (!change_needed) + continue; + rtnl_lock(); + hlist_for_each_entry_safe(ifa, n, &inet_addr_lst[i], hash) { + unsigned long age; + + if (ifa->ifa_flags & IFA_F_PERMANENT) + continue; + + /* We try to batch several events at once. */ + age = (now - ifa->ifa_tstamp + + ADDRCONF_TIMER_FUZZ_MINUS) / HZ; + + if (ifa->ifa_valid_lft != INFINITY_LIFE_TIME && + age >= ifa->ifa_valid_lft) { + struct in_ifaddr **ifap; + + for (ifap = &ifa->ifa_dev->ifa_list; + *ifap != NULL; ifap = &(*ifap)->ifa_next) { + if (*ifap == ifa) { + inet_del_ifa(ifa->ifa_dev, + ifap, 1); + break; + } + } + } else if (ifa->ifa_preferred_lft != + INFINITY_LIFE_TIME && + age >= ifa->ifa_preferred_lft && + !(ifa->ifa_flags & IFA_F_DEPRECATED)) { + ifa->ifa_flags |= IFA_F_DEPRECATED; + rtmsg_ifa(RTM_NEWADDR, ifa, NULL, 0); + } + } + rtnl_unlock(); } - rcu_read_unlock(); next_sec = round_jiffies_up(next); next_sched = next; @@ -805,8 +828,12 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg if (nlh->nlmsg_flags & NLM_F_EXCL || !(nlh->nlmsg_flags & NLM_F_REPLACE)) return -EEXIST; - - set_ifa_lifetime(ifa_existing, valid_lft, prefered_lft); + ifa = ifa_existing; + set_ifa_lifetime(ifa, valid_lft, prefered_lft); + cancel_delayed_work(&check_lifetime_work); + schedule_delayed_work(&check_lifetime_work, 0); + rtmsg_ifa(RTM_NEWADDR, ifa, nlh, NETLINK_CB(skb).portid); + blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, ifa); } return 0; } @@ -1493,7 +1520,6 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) struct in_device *in_dev; struct in_ifaddr *ifa; struct hlist_head *head; - struct hlist_node *node; s_h = cb->args[0]; s_idx = idx = cb->args[1]; @@ -1503,7 +1529,7 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) idx = 0; head = &net->dev_index_head[h]; rcu_read_lock(); - hlist_for_each_entry_rcu(dev, node, head, index_hlist) { + hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; if (h > s_h || idx > s_idx) diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 3b4f0cd2e63e..4cfe34d4cc96 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -139,8 +139,6 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb) /* skb is pure payload to encrypt */ - err = -ENOMEM; - esp = x->data; aead = esp->aead; alen = crypto_aead_authsize(aead); @@ -176,8 +174,10 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb) } tmp = esp_alloc_tmp(aead, nfrags + sglists, seqhilen); - if (!tmp) + if (!tmp) { + err = -ENOMEM; goto error; + } seqhi = esp_tmp_seqhi(tmp); iv = esp_tmp_iv(aead, tmp, seqhilen); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 99f00d39d10b..eb4bb12b3eb4 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -112,7 +112,6 @@ struct fib_table *fib_new_table(struct net *net, u32 id) struct fib_table *fib_get_table(struct net *net, u32 id) { struct fib_table *tb; - struct hlist_node *node; struct hlist_head *head; unsigned int h; @@ -122,7 +121,7 @@ struct fib_table *fib_get_table(struct net *net, u32 id) rcu_read_lock(); head = &net->ipv4.fib_table_hash[h]; - hlist_for_each_entry_rcu(tb, node, head, tb_hlist) { + hlist_for_each_entry_rcu(tb, head, tb_hlist) { if (tb->tb_id == id) { rcu_read_unlock(); return tb; @@ -137,13 +136,12 @@ static void fib_flush(struct net *net) { int flushed = 0; struct fib_table *tb; - struct hlist_node *node; struct hlist_head *head; unsigned int h; for (h = 0; h < FIB_TABLE_HASHSZ; h++) { head = &net->ipv4.fib_table_hash[h]; - hlist_for_each_entry(tb, node, head, tb_hlist) + hlist_for_each_entry(tb, head, tb_hlist) flushed += fib_table_flush(tb); } @@ -656,7 +654,6 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) unsigned int h, s_h; unsigned int e = 0, s_e; struct fib_table *tb; - struct hlist_node *node; struct hlist_head *head; int dumped = 0; @@ -670,7 +667,7 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) for (h = s_h; h < FIB_TABLE_HASHSZ; h++, s_e = 0) { e = 0; head = &net->ipv4.fib_table_hash[h]; - hlist_for_each_entry(tb, node, head, tb_hlist) { + hlist_for_each_entry(tb, head, tb_hlist) { if (e < s_e) goto next; if (dumped) @@ -1117,11 +1114,11 @@ static void ip_fib_net_exit(struct net *net) for (i = 0; i < FIB_TABLE_HASHSZ; i++) { struct fib_table *tb; struct hlist_head *head; - struct hlist_node *node, *tmp; + struct hlist_node *tmp; head = &net->ipv4.fib_table_hash[i]; - hlist_for_each_entry_safe(tb, node, tmp, head, tb_hlist) { - hlist_del(node); + hlist_for_each_entry_safe(tb, tmp, head, tb_hlist) { + hlist_del(&tb->tb_hlist); fib_table_flush(tb); fib_free_table(tb); } diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 4797a800faf8..8f6cb7a87cd6 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -298,14 +298,13 @@ static inline unsigned int fib_info_hashfn(const struct fib_info *fi) static struct fib_info *fib_find_info(const struct fib_info *nfi) { struct hlist_head *head; - struct hlist_node *node; struct fib_info *fi; unsigned int hash; hash = fib_info_hashfn(nfi); head = &fib_info_hash[hash]; - hlist_for_each_entry(fi, node, head, fib_hash) { + hlist_for_each_entry(fi, head, fib_hash) { if (!net_eq(fi->fib_net, nfi->fib_net)) continue; if (fi->fib_nhs != nfi->fib_nhs) @@ -331,7 +330,6 @@ static struct fib_info *fib_find_info(const struct fib_info *nfi) int ip_fib_check_default(__be32 gw, struct net_device *dev) { struct hlist_head *head; - struct hlist_node *node; struct fib_nh *nh; unsigned int hash; @@ -339,7 +337,7 @@ int ip_fib_check_default(__be32 gw, struct net_device *dev) hash = fib_devindex_hashfn(dev->ifindex); head = &fib_info_devhash[hash]; - hlist_for_each_entry(nh, node, head, nh_hash) { + hlist_for_each_entry(nh, head, nh_hash) { if (nh->nh_dev == dev && nh->nh_gw == gw && !(nh->nh_flags & RTNH_F_DEAD)) { @@ -721,10 +719,10 @@ static void fib_info_hash_move(struct hlist_head *new_info_hash, for (i = 0; i < old_size; i++) { struct hlist_head *head = &fib_info_hash[i]; - struct hlist_node *node, *n; + struct hlist_node *n; struct fib_info *fi; - hlist_for_each_entry_safe(fi, node, n, head, fib_hash) { + hlist_for_each_entry_safe(fi, n, head, fib_hash) { struct hlist_head *dest; unsigned int new_hash; @@ -739,10 +737,10 @@ static void fib_info_hash_move(struct hlist_head *new_info_hash, for (i = 0; i < old_size; i++) { struct hlist_head *lhead = &fib_info_laddrhash[i]; - struct hlist_node *node, *n; + struct hlist_node *n; struct fib_info *fi; - hlist_for_each_entry_safe(fi, node, n, lhead, fib_lhash) { + hlist_for_each_entry_safe(fi, n, lhead, fib_lhash) { struct hlist_head *ldest; unsigned int new_hash; @@ -1096,13 +1094,12 @@ int fib_sync_down_addr(struct net *net, __be32 local) int ret = 0; unsigned int hash = fib_laddr_hashfn(local); struct hlist_head *head = &fib_info_laddrhash[hash]; - struct hlist_node *node; struct fib_info *fi; if (fib_info_laddrhash == NULL || local == 0) return 0; - hlist_for_each_entry(fi, node, head, fib_lhash) { + hlist_for_each_entry(fi, head, fib_lhash) { if (!net_eq(fi->fib_net, net)) continue; if (fi->fib_prefsrc == local) { @@ -1120,13 +1117,12 @@ int fib_sync_down_dev(struct net_device *dev, int force) struct fib_info *prev_fi = NULL; unsigned int hash = fib_devindex_hashfn(dev->ifindex); struct hlist_head *head = &fib_info_devhash[hash]; - struct hlist_node *node; struct fib_nh *nh; if (force) scope = -1; - hlist_for_each_entry(nh, node, head, nh_hash) { + hlist_for_each_entry(nh, head, nh_hash) { struct fib_info *fi = nh->nh_parent; int dead; @@ -1232,7 +1228,6 @@ int fib_sync_up(struct net_device *dev) struct fib_info *prev_fi; unsigned int hash; struct hlist_head *head; - struct hlist_node *node; struct fib_nh *nh; int ret; @@ -1244,7 +1239,7 @@ int fib_sync_up(struct net_device *dev) head = &fib_info_devhash[hash]; ret = 0; - hlist_for_each_entry(nh, node, head, nh_hash) { + hlist_for_each_entry(nh, head, nh_hash) { struct fib_info *fi = nh->nh_parent; int alive; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 61e03da3e1f5..ff06b7543d9f 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -920,10 +920,9 @@ nomem: static struct leaf_info *find_leaf_info(struct leaf *l, int plen) { struct hlist_head *head = &l->list; - struct hlist_node *node; struct leaf_info *li; - hlist_for_each_entry_rcu(li, node, head, hlist) + hlist_for_each_entry_rcu(li, head, hlist) if (li->plen == plen) return li; @@ -943,12 +942,11 @@ static inline struct list_head *get_fa_head(struct leaf *l, int plen) static void insert_leaf_info(struct hlist_head *head, struct leaf_info *new) { struct leaf_info *li = NULL, *last = NULL; - struct hlist_node *node; if (hlist_empty(head)) { hlist_add_head_rcu(&new->hlist, head); } else { - hlist_for_each_entry(li, node, head, hlist) { + hlist_for_each_entry(li, head, hlist) { if (new->plen > li->plen) break; @@ -1354,9 +1352,8 @@ static int check_leaf(struct fib_table *tb, struct trie *t, struct leaf *l, { struct leaf_info *li; struct hlist_head *hhead = &l->list; - struct hlist_node *node; - hlist_for_each_entry_rcu(li, node, hhead, hlist) { + hlist_for_each_entry_rcu(li, hhead, hlist) { struct fib_alias *fa; if (l->key != (key & li->mask_plen)) @@ -1740,10 +1737,10 @@ static int trie_flush_leaf(struct leaf *l) { int found = 0; struct hlist_head *lih = &l->list; - struct hlist_node *node, *tmp; + struct hlist_node *tmp; struct leaf_info *li = NULL; - hlist_for_each_entry_safe(li, node, tmp, lih, hlist) { + hlist_for_each_entry_safe(li, tmp, lih, hlist) { found += trie_flush_list(&li->falh); if (list_empty(&li->falh)) { @@ -1895,14 +1892,13 @@ static int fn_trie_dump_leaf(struct leaf *l, struct fib_table *tb, struct sk_buff *skb, struct netlink_callback *cb) { struct leaf_info *li; - struct hlist_node *node; int i, s_i; s_i = cb->args[4]; i = 0; /* rcu_read_lock is hold by caller */ - hlist_for_each_entry_rcu(li, node, &l->list, hlist) { + hlist_for_each_entry_rcu(li, &l->list, hlist) { if (i < s_i) { i++; continue; @@ -2092,14 +2088,13 @@ static void trie_collect_stats(struct trie *t, struct trie_stat *s) if (IS_LEAF(n)) { struct leaf *l = (struct leaf *)n; struct leaf_info *li; - struct hlist_node *tmp; s->leaves++; s->totdepth += iter.depth; if (iter.depth > s->maxdepth) s->maxdepth = iter.depth; - hlist_for_each_entry_rcu(li, tmp, &l->list, hlist) + hlist_for_each_entry_rcu(li, &l->list, hlist) ++s->prefixes; } else { const struct tnode *tn = (const struct tnode *) n; @@ -2200,10 +2195,9 @@ static int fib_triestat_seq_show(struct seq_file *seq, void *v) for (h = 0; h < FIB_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; - struct hlist_node *node; struct fib_table *tb; - hlist_for_each_entry_rcu(tb, node, head, tb_hlist) { + hlist_for_each_entry_rcu(tb, head, tb_hlist) { struct trie *t = (struct trie *) tb->tb_data; struct trie_stat stat; @@ -2245,10 +2239,9 @@ static struct rt_trie_node *fib_trie_get_idx(struct seq_file *seq, loff_t pos) for (h = 0; h < FIB_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; - struct hlist_node *node; struct fib_table *tb; - hlist_for_each_entry_rcu(tb, node, head, tb_hlist) { + hlist_for_each_entry_rcu(tb, head, tb_hlist) { struct rt_trie_node *n; for (n = fib_trie_get_first(iter, @@ -2298,7 +2291,7 @@ static void *fib_trie_seq_next(struct seq_file *seq, void *v, loff_t *pos) /* new hash chain */ while (++h < FIB_TABLE_HASHSZ) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; - hlist_for_each_entry_rcu(tb, tb_node, head, tb_hlist) { + hlist_for_each_entry_rcu(tb, head, tb_hlist) { n = fib_trie_get_first(iter, (struct trie *) tb->tb_data); if (n) goto found; @@ -2381,13 +2374,12 @@ static int fib_trie_seq_show(struct seq_file *seq, void *v) } else { struct leaf *l = (struct leaf *) n; struct leaf_info *li; - struct hlist_node *node; __be32 val = htonl(l->key); seq_indent(seq, iter->depth); seq_printf(seq, " |-- %pI4\n", &val); - hlist_for_each_entry_rcu(li, node, &l->list, hlist) { + hlist_for_each_entry_rcu(li, &l->list, hlist) { struct fib_alias *fa; list_for_each_entry_rcu(fa, &li->falh, fa_list) { @@ -2532,7 +2524,6 @@ static int fib_route_seq_show(struct seq_file *seq, void *v) { struct leaf *l = v; struct leaf_info *li; - struct hlist_node *node; if (v == SEQ_START_TOKEN) { seq_printf(seq, "%-127s\n", "Iface\tDestination\tGateway " @@ -2541,7 +2532,7 @@ static int fib_route_seq_show(struct seq_file *seq, void *v) return 0; } - hlist_for_each_entry_rcu(li, node, &l->list, hlist) { + hlist_for_each_entry_rcu(li, &l->list, hlist) { struct fib_alias *fa; __be32 mask, prefix; diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 17ff9fd7cdda..3ac5dff79627 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -934,6 +934,29 @@ error: goto drop; } +void icmp_err(struct sk_buff *skb, u32 info) +{ + struct iphdr *iph = (struct iphdr *)skb->data; + struct icmphdr *icmph = (struct icmphdr *)(skb->data+(iph->ihl<<2)); + int type = icmp_hdr(skb)->type; + int code = icmp_hdr(skb)->code; + struct net *net = dev_net(skb->dev); + + /* + * Use ping_err to handle all icmp errors except those + * triggered by ICMP_ECHOREPLY which sent from kernel. + */ + if (icmph->type != ICMP_ECHOREPLY) { + ping_err(skb, info); + return; + } + + if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) + ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_ICMP, 0); + else if (type == ICMP_REDIRECT) + ipv4_redirect(skb, net, 0, 0, IPPROTO_ICMP, 0); +} + /* * This table is the definition of how we handle ICMP. */ diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 11cb4979a465..786d97aee751 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -57,7 +57,6 @@ int inet_csk_bind_conflict(const struct sock *sk, const struct inet_bind_bucket *tb, bool relax) { struct sock *sk2; - struct hlist_node *node; int reuse = sk->sk_reuse; int reuseport = sk->sk_reuseport; kuid_t uid = sock_i_uid((struct sock *)sk); @@ -69,7 +68,7 @@ int inet_csk_bind_conflict(const struct sock *sk, * one this bucket belongs to. */ - sk_for_each_bound(sk2, node, &tb->owners) { + sk_for_each_bound(sk2, &tb->owners) { if (sk != sk2 && !inet_v6_ipv6only(sk2) && (!sk->sk_bound_dev_if || @@ -95,7 +94,7 @@ int inet_csk_bind_conflict(const struct sock *sk, } } } - return node != NULL; + return sk2 != NULL; } EXPORT_SYMBOL_GPL(inet_csk_bind_conflict); @@ -106,7 +105,6 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum) { struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; struct inet_bind_hashbucket *head; - struct hlist_node *node; struct inet_bind_bucket *tb; int ret, attempts = 5; struct net *net = sock_net(sk); @@ -129,7 +127,7 @@ again: head = &hashinfo->bhash[inet_bhashfn(net, rover, hashinfo->bhash_size)]; spin_lock(&head->lock); - inet_bind_bucket_for_each(tb, node, &head->chain) + inet_bind_bucket_for_each(tb, &head->chain) if (net_eq(ib_net(tb), net) && tb->port == rover) { if (((tb->fastreuse > 0 && sk->sk_reuse && @@ -183,7 +181,7 @@ have_snum: head = &hashinfo->bhash[inet_bhashfn(net, snum, hashinfo->bhash_size)]; spin_lock(&head->lock); - inet_bind_bucket_for_each(tb, node, &head->chain) + inet_bind_bucket_for_each(tb, &head->chain) if (net_eq(ib_net(tb), net) && tb->port == snum) goto tb_found; } @@ -737,6 +735,7 @@ EXPORT_SYMBOL(inet_csk_destroy_sock); * tcp/dccp_create_openreq_child(). */ void inet_csk_prepare_forced_close(struct sock *sk) + __releases(&sk->sk_lock.slock) { /* sk_clone_lock locked the socket and set refcnt to 2 */ bh_unlock_sock(sk); diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 2e453bde6992..f4fd23de9b13 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -21,6 +21,7 @@ #include <linux/rtnetlink.h> #include <linux/slab.h> +#include <net/sock.h> #include <net/inet_frag.h> static void inet_frag_secret_rebuild(unsigned long dummy) @@ -33,9 +34,9 @@ static void inet_frag_secret_rebuild(unsigned long dummy) get_random_bytes(&f->rnd, sizeof(u32)); for (i = 0; i < INETFRAGS_HASHSZ; i++) { struct inet_frag_queue *q; - struct hlist_node *p, *n; + struct hlist_node *n; - hlist_for_each_entry_safe(q, p, n, &f->hash[i], list) { + hlist_for_each_entry_safe(q, n, &f->hash[i], list) { unsigned int hval = f->hashfn(q); if (hval != i) { @@ -203,7 +204,6 @@ static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf, { struct inet_frag_queue *qp; #ifdef CONFIG_SMP - struct hlist_node *n; #endif unsigned int hash; @@ -219,7 +219,7 @@ static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf, * such entry could be created on other cpu, while we * promoted read lock to write lock. */ - hlist_for_each_entry(qp, n, &f->hash[hash], list) { + hlist_for_each_entry(qp, &f->hash[hash], list) { if (qp->net == nf && f->match(qp, arg)) { atomic_inc(&qp->refcnt); write_unlock(&f->lock); @@ -278,17 +278,33 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, __releases(&f->lock) { struct inet_frag_queue *q; - struct hlist_node *n; + int depth = 0; - hlist_for_each_entry(q, n, &f->hash[hash], list) { + hlist_for_each_entry(q, &f->hash[hash], list) { if (q->net == nf && f->match(q, key)) { atomic_inc(&q->refcnt); read_unlock(&f->lock); return q; } + depth++; } read_unlock(&f->lock); - return inet_frag_create(nf, f, key); + if (depth <= INETFRAGS_MAXDEPTH) + return inet_frag_create(nf, f, key); + else + return ERR_PTR(-ENOBUFS); } EXPORT_SYMBOL(inet_frag_find); + +void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q, + const char *prefix) +{ + static const char msg[] = "inet_frag_find: Fragment hash bucket" + " list length grew over limit " __stringify(INETFRAGS_MAXDEPTH) + ". Dropping fragment.\n"; + + if (PTR_ERR(q) == -ENOBUFS) + LIMIT_NETDEBUG(KERN_WARNING "%s%s", prefix, msg); +} +EXPORT_SYMBOL(inet_frag_maybe_warn_overflow); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 0ce0595d9861..6af375afeeef 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -120,13 +120,12 @@ int __inet_inherit_port(struct sock *sk, struct sock *child) * that the listener socket's icsk_bind_hash is the same * as that of the child socket. We have to look up or * create a new bind bucket for the child here. */ - struct hlist_node *node; - inet_bind_bucket_for_each(tb, node, &head->chain) { + inet_bind_bucket_for_each(tb, &head->chain) { if (net_eq(ib_net(tb), sock_net(sk)) && tb->port == port) break; } - if (!node) { + if (!tb) { tb = inet_bind_bucket_create(table->bind_bucket_cachep, sock_net(sk), head, port); if (!tb) { @@ -493,7 +492,6 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, int i, remaining, low, high, port; static u32 hint; u32 offset = hint + port_offset; - struct hlist_node *node; struct inet_timewait_sock *tw = NULL; inet_get_local_port_range(&low, &high); @@ -512,7 +510,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, * because the established check is already * unique enough. */ - inet_bind_bucket_for_each(tb, node, &head->chain) { + inet_bind_bucket_for_each(tb, &head->chain) { if (net_eq(ib_net(tb), net) && tb->port == port) { if (tb->fastreuse >= 0 || diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 2784db3155fb..1f27c9f4afd0 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -216,7 +216,6 @@ static int inet_twdr_do_twkill_work(struct inet_timewait_death_row *twdr, const int slot) { struct inet_timewait_sock *tw; - struct hlist_node *node; unsigned int killed; int ret; @@ -229,7 +228,7 @@ static int inet_twdr_do_twkill_work(struct inet_timewait_death_row *twdr, killed = 0; ret = 0; rescan: - inet_twsk_for_each_inmate(tw, node, &twdr->cells[slot]) { + inet_twsk_for_each_inmate(tw, &twdr->cells[slot]) { __inet_twsk_del_dead_node(tw); spin_unlock(&twdr->death_lock); __inet_twsk_kill(tw, twdr->hashinfo); @@ -438,10 +437,10 @@ void inet_twdr_twcal_tick(unsigned long data) for (n = 0; n < INET_TWDR_RECYCLE_SLOTS; n++) { if (time_before_eq(j, now)) { - struct hlist_node *node, *safe; + struct hlist_node *safe; struct inet_timewait_sock *tw; - inet_twsk_for_each_inmate_safe(tw, node, safe, + inet_twsk_for_each_inmate_safe(tw, safe, &twdr->twcal_row[slot]) { __inet_twsk_del_dead_node(tw); __inet_twsk_kill(tw, twdr->hashinfo); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index b6d30acb600c..52c273ea05c3 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -248,8 +248,7 @@ static void ip_expire(unsigned long arg) if (!head->dev) goto out_rcu_unlock; - /* skb dst is stale, drop it, and perform route lookup again */ - skb_dst_drop(head); + /* skb has no dst, perform route lookup again */ iph = ip_hdr(head); err = ip_route_input_noref(head, iph->daddr, iph->saddr, iph->tos, head->dev); @@ -292,14 +291,11 @@ static inline struct ipq *ip_find(struct net *net, struct iphdr *iph, u32 user) hash = ipqhashfn(iph->id, iph->saddr, iph->daddr, iph->protocol); q = inet_frag_find(&net->ipv4.frags, &ip4_frags, &arg, hash); - if (q == NULL) - goto out_nomem; - + if (IS_ERR_OR_NULL(q)) { + inet_frag_maybe_warn_overflow(q, pr_fmt()); + return NULL; + } return container_of(q, struct ipq, q); - -out_nomem: - LIMIT_NETDEBUG(KERN_ERR pr_fmt("ip_frag_create: no memory left !\n")); - return NULL; } /* Is the fragment too far ahead to be part of ipq? */ @@ -526,9 +522,16 @@ found: qp->q.max_size = skb->len + ihl; if (qp->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && - qp->q.meat == qp->q.len) - return ip_frag_reasm(qp, prev, dev); + qp->q.meat == qp->q.len) { + unsigned long orefdst = skb->_skb_refdst; + + skb->_skb_refdst = 0UL; + err = ip_frag_reasm(qp, prev, dev); + skb->_skb_refdst = orefdst; + return err; + } + skb_dst_drop(skb); inet_frag_lru_move(&qp->q); return -EINPROGRESS; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 5ef4da780ac1..91d66dbde9c0 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -735,7 +735,7 @@ drop: return 0; } -static struct sk_buff *handle_offloads(struct sk_buff *skb) +static struct sk_buff *handle_offloads(struct ip_tunnel *tunnel, struct sk_buff *skb) { int err; @@ -745,8 +745,12 @@ static struct sk_buff *handle_offloads(struct sk_buff *skb) goto error; skb_shinfo(skb)->gso_type |= SKB_GSO_GRE; return skb; - } - if (skb->ip_summed != CHECKSUM_PARTIAL) + } else if (skb->ip_summed == CHECKSUM_PARTIAL && + tunnel->parms.o_flags&GRE_CSUM) { + err = skb_checksum_help(skb); + if (unlikely(err)) + goto error; + } else if (skb->ip_summed != CHECKSUM_PARTIAL) skb->ip_summed = CHECKSUM_NONE; return skb; @@ -776,7 +780,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev int err; int pkt_len; - skb = handle_offloads(skb); + skb = handle_offloads(tunnel, skb); if (IS_ERR(skb)) { dev->stats.tx_dropped++; return NETDEV_TX_OK; @@ -794,10 +798,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev if (dev->header_ops && dev->type == ARPHRD_IPGRE) { gre_hlen = 0; - if (skb->protocol == htons(ETH_P_IP)) - tiph = (const struct iphdr *)skb->data; - else - tiph = &tunnel->parms.iph; + tiph = (const struct iphdr *)skb->data; } else { gre_hlen = tunnel->hlen; tiph = &tunnel->parms.iph; @@ -970,7 +971,8 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev iph->daddr = fl4.daddr; iph->saddr = fl4.saddr; iph->ttl = ttl; - iph->id = 0; + + tunnel_ip_select_ident(skb, old_iph, &rt->dst); if (ttl == 0) { if (skb->protocol == htons(ETH_P_IP)) @@ -1101,14 +1103,8 @@ static int ipgre_tunnel_bind_dev(struct net_device *dev) tunnel->hlen = addend; /* TCP offload with GRE SEQ is not supported. */ if (!(tunnel->parms.o_flags & GRE_SEQ)) { - /* device supports enc gso offload*/ - if (tdev->hw_enc_features & NETIF_F_GRE_GSO) { - dev->features |= NETIF_F_TSO; - dev->hw_features |= NETIF_F_TSO; - } else { - dev->features |= NETIF_F_GSO_SOFTWARE; - dev->hw_features |= NETIF_F_GSO_SOFTWARE; - } + dev->features |= NETIF_F_GSO_SOFTWARE; + dev->hw_features |= NETIF_F_GSO_SOFTWARE; } return mtu; diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 87abd3e2bd32..2bdf802e28e2 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -228,9 +228,11 @@ static int ip_local_deliver_finish(struct sk_buff *skb) icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PROT_UNREACH, 0); } - } else + kfree_skb(skb); + } else { IP_INC_STATS_BH(net, IPSTATS_MIB_INDELIVERS); - kfree_skb(skb); + consume_skb(skb); + } } } out: diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index f6289bf6f332..ec7264514a82 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -370,7 +370,6 @@ int ip_options_compile(struct net *net, } switch (optptr[3]&0xF) { case IPOPT_TS_TSONLY: - opt->ts = optptr - iph; if (skb) timeptr = &optptr[optptr[2]-1]; opt->ts_needtime = 1; @@ -381,7 +380,6 @@ int ip_options_compile(struct net *net, pp_ptr = optptr + 2; goto error; } - opt->ts = optptr - iph; if (rt) { spec_dst_fill(&spec_dst, skb); memcpy(&optptr[optptr[2]-1], &spec_dst, 4); @@ -396,7 +394,6 @@ int ip_options_compile(struct net *net, pp_ptr = optptr + 2; goto error; } - opt->ts = optptr - iph; { __be32 addr; memcpy(&addr, &optptr[optptr[2]-1], 4); @@ -423,18 +420,18 @@ int ip_options_compile(struct net *net, put_unaligned_be32(midtime, timeptr); opt->is_changed = 1; } - } else { + } else if ((optptr[3]&0xF) != IPOPT_TS_PRESPEC) { unsigned int overflow = optptr[3]>>4; if (overflow == 15) { pp_ptr = optptr + 3; goto error; } - opt->ts = optptr - iph; if (skb) { optptr[3] = (optptr[3]&0xF)|((overflow+1)<<4); opt->is_changed = 1; } } + opt->ts = optptr - iph; break; case IPOPT_RA: if (optlen < 4) { diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 98cbc6877019..bf6c5cf31aed 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -1522,7 +1522,8 @@ static int __init ip_auto_config(void) } for (i++; i < CONF_NAMESERVERS_MAX; i++) if (ic_nameservers[i] != NONE) - pr_cont(", nameserver%u=%pI4\n", i, &ic_nameservers[i]); + pr_cont(", nameserver%u=%pI4", i, &ic_nameservers[i]); + pr_cont("\n"); #endif /* !SILENT */ return 0; diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index ce2d43e1f09f..0d755c50994b 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -36,19 +36,6 @@ config NF_CONNTRACK_PROC_COMPAT If unsure, say Y. -config IP_NF_QUEUE - tristate "IP Userspace queueing via NETLINK (OBSOLETE)" - depends on NETFILTER_ADVANCED - help - Netfilter has the ability to queue packets to user space: the - netlink device can be used to access them using this driver. - - This option enables the old IPv4-only "ip_queue" implementation - which has been obsoleted by the new "nfnetlink_queue" code (see - CONFIG_NETFILTER_NETLINK_QUEUE). - - To compile it as a module, choose M here. If unsure, say N. - config IP_NF_IPTABLES tristate "IP tables support (required for filtering/masq/NAT)" default m if NETFILTER_ADVANCED=n diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 75e33a7048f8..5852b249054f 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -657,7 +657,7 @@ static int clusterip_proc_release(struct inode *inode, struct file *file) static ssize_t clusterip_proc_write(struct file *file, const char __user *input, size_t size, loff_t *ofs) { - struct clusterip_config *c = PDE(file->f_path.dentry->d_inode)->data; + struct clusterip_config *c = PDE(file_inode(file))->data; #define PROC_WRITELEN 10 char buffer[PROC_WRITELEN+1]; unsigned long nodenum; diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c index c30130062cd6..c49dcd0284a0 100644 --- a/net/ipv4/netfilter/ipt_rpfilter.c +++ b/net/ipv4/netfilter/ipt_rpfilter.c @@ -66,6 +66,12 @@ static bool rpfilter_lookup_reverse(struct flowi4 *fl4, return dev_match; } +static bool rpfilter_is_local(const struct sk_buff *skb) +{ + const struct rtable *rt = skb_rtable(skb); + return rt && (rt->rt_flags & RTCF_LOCAL); +} + static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_rpfilter_info *info; @@ -76,7 +82,7 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) info = par->matchinfo; invert = info->flags & XT_RPFILTER_INVERT; - if (par->in->flags & IFF_LOOPBACK) + if (rpfilter_is_local(skb)) return true ^ invert; iph = ip_hdr(skb); diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 55c4ee1bba06..2e91006d6076 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -322,8 +322,8 @@ void ping_err(struct sk_buff *skb, u32 info) struct iphdr *iph = (struct iphdr *)skb->data; struct icmphdr *icmph = (struct icmphdr *)(skb->data+(iph->ihl<<2)); struct inet_sock *inet_sock; - int type = icmph->type; - int code = icmph->code; + int type = icmp_hdr(skb)->type; + int code = icmp_hdr(skb)->code; struct net *net = dev_net(skb->dev); struct sock *sk; int harderr; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 53ddebc292b6..dd44e0ab600c 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -111,9 +111,7 @@ EXPORT_SYMBOL_GPL(raw_unhash_sk); static struct sock *__raw_v4_lookup(struct net *net, struct sock *sk, unsigned short num, __be32 raddr, __be32 laddr, int dif) { - struct hlist_node *node; - - sk_for_each_from(sk, node) { + sk_for_each_from(sk) { struct inet_sock *inet = inet_sk(sk); if (net_eq(sock_net(sk), net) && inet->inet_num == num && @@ -914,9 +912,7 @@ static struct sock *raw_get_first(struct seq_file *seq) for (state->bucket = 0; state->bucket < RAW_HTABLE_SIZE; ++state->bucket) { - struct hlist_node *node; - - sk_for_each(sk, node, &state->h->ht[state->bucket]) + sk_for_each(sk, &state->h->ht[state->bucket]) if (sock_net(sk) == seq_file_net(seq)) goto found; } diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index ef54377fb11c..397e0f69435f 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -349,8 +349,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, * hasn't changed since we received the original syn, but I see * no easy way to do this. */ - flowi4_init_output(&fl4, 0, sk->sk_mark, RT_CONN_FLAGS(sk), - RT_SCOPE_UNIVERSE, IPPROTO_TCP, + flowi4_init_output(&fl4, sk->sk_bound_dev_if, sk->sk_mark, + RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, IPPROTO_TCP, inet_sk_flowi_flags(sk), (opt && opt->srr) ? opt->faddr : ireq->rmt_addr, ireq->loc_addr, th->source, th->dest); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 7a5ba48c2cc9..e22020790709 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -775,7 +775,7 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp) * Make sure that we have exactly size bytes * available to the caller, no more, no less. */ - skb->avail_size = size; + skb->reserved_tailroom = skb->end - skb->tail - size; return skb; } __kfree_skb(skb); @@ -1409,10 +1409,10 @@ static void tcp_service_net_dma(struct sock *sk, bool wait) return; last_issued = tp->ucopy.dma_cookie; - dma_async_memcpy_issue_pending(tp->ucopy.dma_chan); + dma_async_issue_pending(tp->ucopy.dma_chan); do { - if (dma_async_memcpy_complete(tp->ucopy.dma_chan, + if (dma_async_is_tx_complete(tp->ucopy.dma_chan, last_issued, &done, &used) == DMA_SUCCESS) { /* Safe to free early-copied skbs now */ @@ -1754,7 +1754,7 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, tcp_service_net_dma(sk, true); tcp_cleanup_rbuf(sk, copied); } else - dma_async_memcpy_issue_pending(tp->ucopy.dma_chan); + dma_async_issue_pending(tp->ucopy.dma_chan); } #endif if (copied >= target) { @@ -1847,7 +1847,7 @@ do_prequeue: break; } - dma_async_memcpy_issue_pending(tp->ucopy.dma_chan); + dma_async_issue_pending(tp->ucopy.dma_chan); if ((offset + used) == skb->len) copied_early = true; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index a759e19496d2..13b9c08fc158 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -113,6 +113,7 @@ int sysctl_tcp_early_retrans __read_mostly = 2; #define FLAG_DSACKING_ACK 0x800 /* SACK blocks contained D-SACK info */ #define FLAG_NONHEAD_RETRANS_ACKED 0x1000 /* Non-head rexmitted data was ACKed */ #define FLAG_SACK_RENEGING 0x2000 /* snd_una advanced to a sacked seq */ +#define FLAG_UPDATE_TS_RECENT 0x4000 /* tcp_replace_ts_recent() */ #define FLAG_ACKED (FLAG_DATA_ACKED|FLAG_SYN_ACKED) #define FLAG_NOT_DUP (FLAG_DATA|FLAG_WIN_UPDATE|FLAG_ACKED) @@ -2059,11 +2060,8 @@ void tcp_enter_loss(struct sock *sk, int how) if (tcp_is_reno(tp)) tcp_reset_reno_sack(tp); - if (!how) { - /* Push undo marker, if it was plain RTO and nothing - * was retransmitted. */ - tp->undo_marker = tp->snd_una; - } else { + tp->undo_marker = tp->snd_una; + if (how) { tp->sacked_out = 0; tp->fackets_out = 0; } @@ -3567,6 +3565,27 @@ static void tcp_send_challenge_ack(struct sock *sk) } } +static void tcp_store_ts_recent(struct tcp_sock *tp) +{ + tp->rx_opt.ts_recent = tp->rx_opt.rcv_tsval; + tp->rx_opt.ts_recent_stamp = get_seconds(); +} + +static void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq) +{ + if (tp->rx_opt.saw_tstamp && !after(seq, tp->rcv_wup)) { + /* PAWS bug workaround wrt. ACK frames, the PAWS discard + * extra check below makes sure this can only happen + * for pure ACK frames. -DaveM + * + * Not only, also it occurs for expired timestamps. + */ + + if (tcp_paws_check(&tp->rx_opt, 0)) + tcp_store_ts_recent(tp); + } +} + /* This routine deals with incoming acks, but not outgoing ones. */ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) { @@ -3610,6 +3629,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) prior_fackets = tp->fackets_out; prior_in_flight = tcp_packets_in_flight(tp); + /* ts_recent update must be made after we are sure that the packet + * is in window. + */ + if (flag & FLAG_UPDATE_TS_RECENT) + tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq); + if (!(flag & FLAG_SLOWPATH) && after(ack, prior_snd_una)) { /* Window is constant, pure forward advance. * No more checks are required. @@ -3930,27 +3955,6 @@ const u8 *tcp_parse_md5sig_option(const struct tcphdr *th) EXPORT_SYMBOL(tcp_parse_md5sig_option); #endif -static inline void tcp_store_ts_recent(struct tcp_sock *tp) -{ - tp->rx_opt.ts_recent = tp->rx_opt.rcv_tsval; - tp->rx_opt.ts_recent_stamp = get_seconds(); -} - -static inline void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq) -{ - if (tp->rx_opt.saw_tstamp && !after(seq, tp->rcv_wup)) { - /* PAWS bug workaround wrt. ACK frames, the PAWS discard - * extra check below makes sure this can only happen - * for pure ACK frames. -DaveM - * - * Not only, also it occurs for expired timestamps. - */ - - if (tcp_paws_check(&tp->rx_opt, 0)) - tcp_store_ts_recent(tp); - } -} - /* Sorry, PAWS as specified is broken wrt. pure-ACKs -DaveM * * It is not fatal. If this ACK does _not_ change critical state (seqs, window) @@ -5485,6 +5489,9 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb, if (tcp_checksum_complete_user(sk, skb)) goto csum_error; + if ((int)skb->truesize > sk->sk_forward_alloc) + goto step5; + /* Predicted packet is in window by definition. * seq == rcv_nxt and rcv_wup <= rcv_nxt. * Hence, check seq<=rcv_wup reduces to: @@ -5496,9 +5503,6 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb, tcp_rcv_rtt_measure_ts(sk, skb); - if ((int)skb->truesize > sk->sk_forward_alloc) - goto step5; - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPHPHITS); /* Bulk data transfer: receiver */ @@ -5546,14 +5550,9 @@ slow_path: return 0; step5: - if (tcp_ack(sk, skb, FLAG_SLOWPATH) < 0) + if (tcp_ack(sk, skb, FLAG_SLOWPATH | FLAG_UPDATE_TS_RECENT) < 0) goto discard; - /* ts_recent update must be made after we are sure that the packet - * is in window. - */ - tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq); - tcp_rcv_rtt_measure_ts(sk, skb); /* Process urgent data. */ @@ -5989,7 +5988,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, /* step 5: check the ACK field */ if (true) { - int acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH) > 0; + int acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH | + FLAG_UPDATE_TS_RECENT) > 0; switch (sk->sk_state) { case TCP_SYN_RECV: @@ -6140,11 +6140,6 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, } } - /* ts_recent update must be made after we are sure that the packet - * is in window. - */ - tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq); - /* step 6: check the URG bit */ tcp_urg(sk, skb, th); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 145d3bf8df86..d09203c63264 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -274,13 +274,6 @@ static void tcp_v4_mtu_reduced(struct sock *sk) struct inet_sock *inet = inet_sk(sk); u32 mtu = tcp_sk(sk)->mtu_info; - /* We are not interested in TCP_LISTEN and open_requests (SYN-ACKs - * send out by Linux are always <576bytes so they should go through - * unfragmented). - */ - if (sk->sk_state == TCP_LISTEN) - return; - dst = inet_csk_update_pmtu(sk, mtu); if (!dst) return; @@ -408,6 +401,13 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) goto out; if (code == ICMP_FRAG_NEEDED) { /* PMTU discovery (RFC1191) */ + /* We are not interested in TCP_LISTEN and open_requests + * (SYN-ACKs send out by Linux are always <576bytes so + * they should go through unfragmented). + */ + if (sk->sk_state == TCP_LISTEN) + goto out; + tp->mtu_info = info; if (!sock_owned_by_user(sk)) { tcp_v4_mtu_reduced(sk); @@ -954,7 +954,6 @@ struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk, { struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_key *key; - struct hlist_node *pos; unsigned int size = sizeof(struct in_addr); struct tcp_md5sig_info *md5sig; @@ -968,7 +967,7 @@ struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk, if (family == AF_INET6) size = sizeof(struct in6_addr); #endif - hlist_for_each_entry_rcu(key, pos, &md5sig->head, node) { + hlist_for_each_entry_rcu(key, &md5sig->head, node) { if (key->family != family) continue; if (!memcmp(&key->addr, addr, size)) @@ -1069,14 +1068,14 @@ static void tcp_clear_md5_list(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_key *key; - struct hlist_node *pos, *n; + struct hlist_node *n; struct tcp_md5sig_info *md5sig; md5sig = rcu_dereference_protected(tp->md5sig_info, 1); if (!hlist_empty(&md5sig->head)) tcp_free_md5sig_pool(); - hlist_for_each_entry_safe(key, pos, n, &md5sig->head, node) { + hlist_for_each_entry_safe(key, n, &md5sig->head, node) { hlist_del_rcu(&key->node); atomic_sub(sizeof(*key), &sk->sk_omem_alloc); kfree_rcu(key, rcu); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index fd0cea114b5d..509912a5ff98 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1298,7 +1298,6 @@ static void __pskb_trim_head(struct sk_buff *skb, int len) eat = min_t(int, len, skb_headlen(skb)); if (eat) { __skb_pull(skb, eat); - skb->avail_size -= eat; len -= eat; if (!len) return; @@ -1351,8 +1350,8 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len) return 0; } -/* Calculate MSS. Not accounting for SACKs here. */ -int tcp_mtu_to_mss(struct sock *sk, int pmtu) +/* Calculate MSS not accounting any TCP options. */ +static inline int __tcp_mtu_to_mss(struct sock *sk, int pmtu) { const struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); @@ -1381,13 +1380,17 @@ int tcp_mtu_to_mss(struct sock *sk, int pmtu) /* Then reserve room for full set of TCP options and 8 bytes of data */ if (mss_now < 48) mss_now = 48; - - /* Now subtract TCP options size, not including SACKs */ - mss_now -= tp->tcp_header_len - sizeof(struct tcphdr); - return mss_now; } +/* Calculate MSS. Not accounting for SACKs here. */ +int tcp_mtu_to_mss(struct sock *sk, int pmtu) +{ + /* Subtract TCP options size, not including SACKs */ + return __tcp_mtu_to_mss(sk, pmtu) - + (tcp_sk(sk)->tcp_header_len - sizeof(struct tcphdr)); +} + /* Inverse of above */ int tcp_mss_to_mtu(struct sock *sk, int mss) { @@ -1806,8 +1809,11 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb) goto send_now; } - /* Ok, it looks like it is advisable to defer. */ - tp->tso_deferred = 1 | (jiffies << 1); + /* Ok, it looks like it is advisable to defer. + * Do not rearm the timer if already set to not break TCP ACK clocking. + */ + if (!tp->tso_deferred) + tp->tso_deferred = 1 | (jiffies << 1); return true; @@ -2382,8 +2388,12 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) */ TCP_SKB_CB(skb)->when = tcp_time_stamp; - /* make sure skb->data is aligned on arches that require it */ - if (unlikely(NET_IP_ALIGN && ((unsigned long)skb->data & 3))) { + /* make sure skb->data is aligned on arches that require it + * and check if ack-trimming & collapsing extended the headroom + * beyond what csum_start can cover. + */ + if (unlikely((NET_IP_ALIGN && ((unsigned long)skb->data & 3)) || + skb_headroom(skb) >= 0xFFFF)) { struct sk_buff *nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC); return nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) : @@ -2703,6 +2713,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, skb_reserve(skb, MAX_TCP_HEADER); skb_dst_set(skb, dst); + security_skb_owned_by(skb, sk); mss = dst_metric_advmss(dst); if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < mss) @@ -2930,7 +2941,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) */ if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < tp->rx_opt.mss_clamp) tp->rx_opt.mss_clamp = tp->rx_opt.user_mss; - space = tcp_mtu_to_mss(sk, inet_csk(sk)->icsk_pmtu_cookie) - + space = __tcp_mtu_to_mss(sk, inet_csk(sk)->icsk_pmtu_cookie) - MAX_TCP_OPTION_SPACE; syn_data = skb_copy_expand(syn, skb_headroom(syn), space, diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 265c42cf963c..0a073a263720 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1762,9 +1762,16 @@ int udp_rcv(struct sk_buff *skb) void udp_destroy_sock(struct sock *sk) { + struct udp_sock *up = udp_sk(sk); bool slow = lock_sock_fast(sk); udp_flush_pending_frames(sk); unlock_sock_fast(sk, slow); + if (static_key_false(&udp_encap_needed) && up->encap_type) { + void (*encap_destroy)(struct sock *sk); + encap_destroy = ACCESS_ONCE(up->encap_destroy); + if (encap_destroy) + encap_destroy(sk); + } } /* |