1 files changed, 123 insertions, 52 deletions

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index fe193e53af44..020766292bb0 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -84,6 +84,7 @@
 
 int sysctl_tcp_tw_reuse __read_mostly;
 int sysctl_tcp_low_latency __read_mostly;
+EXPORT_SYMBOL(sysctl_tcp_low_latency);
 
 
 #ifdef CONFIG_TCP_MD5SIG
@@ -100,6 +101,7 @@ struct tcp_md5sig_key *tcp_v4_md5_do_lookup(struct sock *sk, __be32 addr)
 #endif
 
 struct inet_hashinfo tcp_hashinfo;
+EXPORT_SYMBOL(tcp_hashinfo);
 
 static inline __u32 tcp_v4_init_sequence(struct sk_buff *skb)
 {
@@ -139,7 +141,6 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
 
         return 0;
 }
-
 EXPORT_SYMBOL_GPL(tcp_twsk_unique);
 
 /* This will initiate an outgoing connection. */
@@ -204,10 +205,12 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
                  * TIME-WAIT * and initialize rx_opt.ts_recent from it,
                  * when trying new connection.
                  */
-                if (peer != NULL &&
-                    (u32)get_seconds() - peer->tcp_ts_stamp <= TCP_PAWS_MSL) {
-                        tp->rx_opt.ts_recent_stamp = peer->tcp_ts_stamp;
-                        tp->rx_opt.ts_recent = peer->tcp_ts;
+                if (peer) {
+                        inet_peer_refcheck(peer);
+                        if ((u32)get_seconds() - peer->tcp_ts_stamp <= TCP_PAWS_MSL) {
+                                tp->rx_opt.ts_recent_stamp = peer->tcp_ts_stamp;
+                                tp->rx_opt.ts_recent = peer->tcp_ts;
+                        }
                 }
         }
 
@@ -237,7 +240,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 
         /* OK, now commit destination to socket.  */
         sk->sk_gso_type = SKB_GSO_TCPV4;
-        sk_setup_caps(sk, &rt->u.dst);
+        sk_setup_caps(sk, &rt->dst);
 
         if (!tp->write_seq)
                 tp->write_seq = secure_tcp_sequence_number(inet->inet_saddr,
@@ -265,6 +268,7 @@ failure:
         inet->inet_dport = 0;
         return err;
 }
+EXPORT_SYMBOL(tcp_v4_connect);
 
 /*
  * This routine does path mtu discovery as defined in RFC1191.
@@ -543,6 +547,7 @@ void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb)
 
         __tcp_v4_send_check(skb, inet->inet_saddr, inet->inet_daddr);
 }
+EXPORT_SYMBOL(tcp_v4_send_check);
 
 int tcp_v4_gso_send_check(struct sk_buff *skb)
 {
@@ -793,19 +798,20 @@ static void tcp_v4_reqsk_destructor(struct request_sock *req)
         kfree(inet_rsk(req)->opt);
 }
 
-#ifdef CONFIG_SYN_COOKIES
-static void syn_flood_warning(struct sk_buff *skb)
+static void syn_flood_warning(const struct sk_buff *skb)
 {
-        static unsigned long warntime;
+        const char *msg;
 
-        if (time_after(jiffies, (warntime + HZ * 60))) {
-                warntime = jiffies;
-                printk(KERN_INFO
-                       "possible SYN flooding on port %d. Sending cookies.\n",
-                       ntohs(tcp_hdr(skb)->dest));
-        }
-}
+#ifdef CONFIG_SYN_COOKIES
+        if (sysctl_tcp_syncookies)
+                msg = "Sending cookies";
+        else
 #endif
+                msg = "Dropping request";
+
+        pr_info("TCP: Possible SYN flooding on port %d. %s.\n",
+                                ntohs(tcp_hdr(skb)->dest), msg);
+}
 
 /*
  * Save and compile IPv4 options into the request_sock if needed.
@@ -857,7 +863,6 @@ struct tcp_md5sig_key *tcp_v4_md5_lookup(struct sock *sk,
 {
         return tcp_v4_md5_do_lookup(sk, inet_sk(addr_sk)->inet_daddr);
 }
-
 EXPORT_SYMBOL(tcp_v4_md5_lookup);
 
 static struct tcp_md5sig_key *tcp_v4_reqsk_md5_lookup(struct sock *sk,
@@ -924,7 +929,6 @@ int tcp_v4_md5_do_add(struct sock *sk, __be32 addr,
         }
         return 0;
 }
-
 EXPORT_SYMBOL(tcp_v4_md5_do_add);
 
 static int tcp_v4_md5_add_func(struct sock *sk, struct sock *addr_sk,
@@ -962,7 +966,6 @@ int tcp_v4_md5_do_del(struct sock *sk, __be32 addr)
         }
         return -ENOENT;
 }
-
 EXPORT_SYMBOL(tcp_v4_md5_do_del);
 
 static void tcp_v4_clear_md5_list(struct sock *sk)
@@ -1135,7 +1138,6 @@ clear_hash_noput:
         memset(md5_hash, 0, 16);
         return 1;
 }
-
 EXPORT_SYMBOL(tcp_v4_md5_hash_skb);
 
 static int tcp_v4_inbound_md5_hash(struct sock *sk, struct sk_buff *skb)
@@ -1243,6 +1245,8 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
          * evidently real one.
          */
         if (inet_csk_reqsk_queue_is_full(sk) && !isn) {
+                if (net_ratelimit())
+                        syn_flood_warning(skb);
 #ifdef CONFIG_SYN_COOKIES
                 if (sysctl_tcp_syncookies) {
                         want_cookie = 1;
@@ -1323,15 +1327,12 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
         if (security_inet_conn_request(sk, skb, req))
                 goto drop_and_free;
 
-        if (!want_cookie)
+        if (!want_cookie || tmp_opt.tstamp_ok)
                 TCP_ECN_create_request(req, tcp_hdr(skb));
 
         if (want_cookie) {
-#ifdef CONFIG_SYN_COOKIES
-                syn_flood_warning(skb);
-                req->cookie_ts = tmp_opt.tstamp_ok;
-#endif
                 isn = cookie_v4_init_sequence(sk, skb, &req->mss);
+                req->cookie_ts = tmp_opt.tstamp_ok;
         } else if (!isn) {
                 struct inet_peer *peer = NULL;
 
@@ -1349,6 +1350,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
                     (dst = inet_csk_route_req(sk, req)) != NULL &&
                     (peer = rt_get_peer((struct rtable *)dst)) != NULL &&
                     peer->v4daddr == saddr) {
+                        inet_peer_refcheck(peer);
                         if ((u32)get_seconds() - peer->tcp_ts_stamp < TCP_PAWS_MSL &&
                             (s32)(peer->tcp_ts - req->ts_recent) >
                                                         TCP_PAWS_WINDOW) {
@@ -1393,6 +1395,7 @@ drop_and_free:
 drop:
         return 0;
 }
+EXPORT_SYMBOL(tcp_v4_conn_request);
 
 
 /*
@@ -1478,6 +1481,7 @@ exit:
         dst_release(dst);
         return NULL;
 }
+EXPORT_SYMBOL(tcp_v4_syn_recv_sock);
 
 static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb)
 {
@@ -1504,7 +1508,7 @@ static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb)
         }
 
 #ifdef CONFIG_SYN_COOKIES
-        if (!th->rst && !th->syn && th->ack)
+        if (!th->syn)
                 sk = cookie_v4_check(sk, skb, &(IPCB(skb)->opt));
 #endif
         return sk;
@@ -1607,6 +1611,7 @@ csum_err:
         TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_INERRS);
         goto discard;
 }
+EXPORT_SYMBOL(tcp_v4_do_rcv);
 
 /*
  *      From tcp_input.c
@@ -1793,6 +1798,7 @@ int tcp_v4_remember_stamp(struct sock *sk)
 
         return 0;
 }
+EXPORT_SYMBOL(tcp_v4_remember_stamp);
 
 int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw)
 {
@@ -1832,6 +1838,7 @@ const struct inet_connection_sock_af_ops ipv4_specific = {
         .compat_getsockopt = compat_ip_getsockopt,
 #endif
 };
+EXPORT_SYMBOL(ipv4_specific);
 
 #ifdef CONFIG_TCP_MD5SIG
 static const struct tcp_sock_af_ops tcp_sock_ipv4_specific = {
@@ -1960,7 +1967,6 @@ void tcp_v4_destroy_sock(struct sock *sk)
 
         percpu_counter_dec(&tcp_sockets_allocated);
 }
-
 EXPORT_SYMBOL(tcp_v4_destroy_sock);
 
 #ifdef CONFIG_PROC_FS
@@ -1978,6 +1984,11 @@ static inline struct inet_timewait_sock *tw_next(struct inet_timewait_sock *tw)
                 hlist_nulls_entry(tw->tw_node.next, typeof(*tw), tw_node) : NULL;
 }
 
+/*
+ * Get next listener socket follow cur.  If cur is NULL, get first socket
+ * starting from bucket given in st->bucket; when st->bucket is zero the
+ * very first socket in the hash table is returned.
+ */
 static void *listening_get_next(struct seq_file *seq, void *cur)
 {
         struct inet_connection_sock *icsk;
@@ -1988,14 +1999,15 @@ static void *listening_get_next(struct seq_file *seq, void *cur)
         struct net *net = seq_file_net(seq);
 
         if (!sk) {
-                st->bucket = 0;
-                ilb = &tcp_hashinfo.listening_hash[0];
+                ilb = &tcp_hashinfo.listening_hash[st->bucket];
                 spin_lock_bh(&ilb->lock);
                 sk = sk_nulls_head(&ilb->head);
+                st->offset = 0;
                 goto get_sk;
         }
         ilb = &tcp_hashinfo.listening_hash[st->bucket];
         ++st->num;
+        ++st->offset;
 
         if (st->state == TCP_SEQ_STATE_OPENREQ) {
                 struct request_sock *req = cur;
@@ -2010,6 +2022,7 @@ static void *listening_get_next(struct seq_file *seq, void *cur)
                                 }
                                 req = req->dl_next;
                         }
+                        st->offset = 0;
                         if (++st->sbucket >= icsk->icsk_accept_queue.listen_opt->nr_table_entries)
                                 break;
 get_req:
@@ -2045,6 +2058,7 @@ start_req:
                 read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
         }
         spin_unlock_bh(&ilb->lock);
+        st->offset = 0;
         if (++st->bucket < INET_LHTABLE_SIZE) {
                 ilb = &tcp_hashinfo.listening_hash[st->bucket];
                 spin_lock_bh(&ilb->lock);
@@ -2058,7 +2072,12 @@ out:
 
 static void *listening_get_idx(struct seq_file *seq, loff_t *pos)
 {
-        void *rc = listening_get_next(seq, NULL);
+        struct tcp_iter_state *st = seq->private;
+        void *rc;
+
+        st->bucket = 0;
+        st->offset = 0;
+        rc = listening_get_next(seq, NULL);
 
         while (rc && *pos) {
                 rc = listening_get_next(seq, rc);
@@ -2073,13 +2092,18 @@ static inline int empty_bucket(struct tcp_iter_state *st)
                 hlist_nulls_empty(&tcp_hashinfo.ehash[st->bucket].twchain);
 }
 
+/*
+ * Get first established socket starting from bucket given in st->bucket.
+ * If st->bucket is zero, the very first socket in the hash is returned.
+ */
 static void *established_get_first(struct seq_file *seq)
 {
         struct tcp_iter_state *st = seq->private;
         struct net *net = seq_file_net(seq);
         void *rc = NULL;
 
-        for (st->bucket = 0; st->bucket <= tcp_hashinfo.ehash_mask; ++st->bucket) {
+        st->offset = 0;
+        for (; st->bucket <= tcp_hashinfo.ehash_mask; ++st->bucket) {
                 struct sock *sk;
                 struct hlist_nulls_node *node;
                 struct inet_timewait_sock *tw;
@@ -2124,6 +2148,7 @@ static void *established_get_next(struct seq_file *seq, void *cur)
         struct net *net = seq_file_net(seq);
 
         ++st->num;
+        ++st->offset;
 
         if (st->state == TCP_SEQ_STATE_TIME_WAIT) {
                 tw = cur;
@@ -2140,6 +2165,7 @@ get_tw:
                 st->state = TCP_SEQ_STATE_ESTABLISHED;
 
                 /* Look for next non empty bucket */
+                st->offset = 0;
                 while (++st->bucket <= tcp_hashinfo.ehash_mask &&
                                 empty_bucket(st))
                         ;
@@ -2167,7 +2193,11 @@ out:
 
 static void *established_get_idx(struct seq_file *seq, loff_t pos)
 {
-        void *rc = established_get_first(seq);
+        struct tcp_iter_state *st = seq->private;
+        void *rc;
+
+        st->bucket = 0;
+        rc = established_get_first(seq);
 
         while (rc && pos) {
                 rc = established_get_next(seq, rc);
@@ -2192,24 +2222,72 @@ static void *tcp_get_idx(struct seq_file *seq, loff_t pos)
         return rc;
 }
 
+static void *tcp_seek_last_pos(struct seq_file *seq)
+{
+        struct tcp_iter_state *st = seq->private;
+        int offset = st->offset;
+        int orig_num = st->num;
+        void *rc = NULL;
+
+        switch (st->state) {
+        case TCP_SEQ_STATE_OPENREQ:
+        case TCP_SEQ_STATE_LISTENING:
+                if (st->bucket >= INET_LHTABLE_SIZE)
+                        break;
+                st->state = TCP_SEQ_STATE_LISTENING;
+                rc = listening_get_next(seq, NULL);
+                while (offset-- && rc)
+                        rc = listening_get_next(seq, rc);
+                if (rc)
+                        break;
+                st->bucket = 0;
+                /* Fallthrough */
+        case TCP_SEQ_STATE_ESTABLISHED:
+        case TCP_SEQ_STATE_TIME_WAIT:
+                st->state = TCP_SEQ_STATE_ESTABLISHED;
+                if (st->bucket > tcp_hashinfo.ehash_mask)
+                        break;
+                rc = established_get_first(seq);
+                while (offset-- && rc)
+                        rc = established_get_next(seq, rc);
+        }
+
+        st->num = orig_num;
+
+        return rc;
+}
+
 static void *tcp_seq_start(struct seq_file *seq, loff_t *pos)
 {
         struct tcp_iter_state *st = seq->private;
+        void *rc;
+
+        if (*pos && *pos == st->last_pos) {
+                rc = tcp_seek_last_pos(seq);
+                if (rc)
+                        goto out;
+        }
+
         st->state = TCP_SEQ_STATE_LISTENING;
         st->num = 0;
-        return *pos ? tcp_get_idx(seq, *pos - 1) : SEQ_START_TOKEN;
+        st->bucket = 0;
+        st->offset = 0;
+        rc = *pos ? tcp_get_idx(seq, *pos - 1) : SEQ_START_TOKEN;
+
+out:
+        st->last_pos = *pos;
+        return rc;
 }
 
 static void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
+        struct tcp_iter_state *st = seq->private;
         void *rc = NULL;
-        struct tcp_iter_state *st;
 
         if (v == SEQ_START_TOKEN) {
                 rc = tcp_get_idx(seq, 0);
                 goto out;
         }
-        st = seq->private;
 
         switch (st->state) {
         case TCP_SEQ_STATE_OPENREQ:
@@ -2217,6 +2295,8 @@ static void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
                 rc = listening_get_next(seq, v);
                 if (!rc) {
                         st->state = TCP_SEQ_STATE_ESTABLISHED;
+                        st->bucket = 0;
+                        st->offset = 0;
                         rc        = established_get_first(seq);
                 }
                 break;
@@ -2227,6 +2307,7 @@ static void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
         }
 out:
         ++*pos;
+        st->last_pos = *pos;
         return rc;
 }
 
@@ -2265,6 +2346,7 @@ static int tcp_seq_open(struct inode *inode, struct file *file)
 
         s = ((struct seq_file *)file->private_data)->private;
         s->family               = afinfo->family;
+        s->last_pos             = 0;
         return 0;
 }
 
@@ -2288,11 +2370,13 @@ int tcp_proc_register(struct net *net, struct tcp_seq_afinfo *afinfo)
                 rc = -ENOMEM;
         return rc;
 }
+EXPORT_SYMBOL(tcp_proc_register);
 
 void tcp_proc_unregister(struct net *net, struct tcp_seq_afinfo *afinfo)
 {
         proc_net_remove(net, afinfo->name);
 }
+EXPORT_SYMBOL(tcp_proc_unregister);
 
 static void get_openreq4(struct sock *sk, struct request_sock *req,
                          struct seq_file *f, int i, int uid, int *len)
@@ -2516,6 +2600,8 @@ struct proto tcp_prot = {
         .setsockopt             = tcp_setsockopt,
         .getsockopt             = tcp_getsockopt,
         .recvmsg                = tcp_recvmsg,
+        .sendmsg                = tcp_sendmsg,
+        .sendpage               = tcp_sendpage,
         .backlog_rcv            = tcp_v4_do_rcv,
         .hash                   = inet_hash,
         .unhash                 = inet_unhash,
@@ -2534,11 +2620,13 @@ struct proto tcp_prot = {
         .twsk_prot              = &tcp_timewait_sock_ops,
         .rsk_prot               = &tcp_request_sock_ops,
         .h.hashinfo             = &tcp_hashinfo,
+        .no_autobind            = true,
 #ifdef CONFIG_COMPAT
         .compat_setsockopt      = compat_tcp_setsockopt,
         .compat_getsockopt      = compat_tcp_getsockopt,
 #endif
 };
+EXPORT_SYMBOL(tcp_prot);
 
 
 static int __net_init tcp_sk_init(struct net *net)
@@ -2569,20 +2657,3 @@ void __init tcp_v4_init(void)
         if (register_pernet_subsys(&tcp_sk_ops))
                 panic("Failed to create the TCP control socket.\n");
 }
-
-EXPORT_SYMBOL(ipv4_specific);
-EXPORT_SYMBOL(tcp_hashinfo);
-EXPORT_SYMBOL(tcp_prot);
-EXPORT_SYMBOL(tcp_v4_conn_request);
-EXPORT_SYMBOL(tcp_v4_connect);
-EXPORT_SYMBOL(tcp_v4_do_rcv);
-EXPORT_SYMBOL(tcp_v4_remember_stamp);
-EXPORT_SYMBOL(tcp_v4_send_check);
-EXPORT_SYMBOL(tcp_v4_syn_recv_sock);
-
-#ifdef CONFIG_PROC_FS
-EXPORT_SYMBOL(tcp_proc_register);
-EXPORT_SYMBOL(tcp_proc_unregister);
-#endif
-EXPORT_SYMBOL(sysctl_tcp_low_latency);
-