Merge branch 'next' into for-linus

1 files changed, 79 insertions, 62 deletions

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 1c12b8ec849d..a9db4b1a2215 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -92,7 +92,7 @@ EXPORT_SYMBOL(sysctl_tcp_low_latency);
 static struct tcp_md5sig_key *tcp_v4_md5_do_lookup(struct sock *sk,
                                                    __be32 addr);
 static int tcp_v4_md5_hash_hdr(char *md5_hash, struct tcp_md5sig_key *key,
-                               __be32 daddr, __be32 saddr, struct tcphdr *th);
+                               __be32 daddr, __be32 saddr, const struct tcphdr *th);
 #else
 static inline
 struct tcp_md5sig_key *tcp_v4_md5_do_lookup(struct sock *sk, __be32 addr)
@@ -104,7 +104,7 @@ struct tcp_md5sig_key *tcp_v4_md5_do_lookup(struct sock *sk, __be32 addr)
 struct inet_hashinfo tcp_hashinfo;
 EXPORT_SYMBOL(tcp_hashinfo);
 
-static inline __u32 tcp_v4_init_sequence(struct sk_buff *skb)
+static inline __u32 tcp_v4_init_sequence(const struct sk_buff *skb)
 {
         return secure_tcp_sequence_number(ip_hdr(skb)->daddr,
                                           ip_hdr(skb)->saddr,
@@ -552,7 +552,7 @@ static void __tcp_v4_send_check(struct sk_buff *skb,
 /* This routine computes an IPv4 TCP checksum. */
 void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb)
 {
-        struct inet_sock *inet = inet_sk(sk);
+        const struct inet_sock *inet = inet_sk(sk);
 
         __tcp_v4_send_check(skb, inet->inet_saddr, inet->inet_daddr);
 }
@@ -590,7 +590,7 @@ int tcp_v4_gso_send_check(struct sk_buff *skb)
 
 static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
 {
-        struct tcphdr *th = tcp_hdr(skb);
+        const struct tcphdr *th = tcp_hdr(skb);
         struct {
                 struct tcphdr th;
 #ifdef CONFIG_TCP_MD5SIG
@@ -652,6 +652,7 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
         arg.flags = (sk && inet_sk(sk)->transparent) ? IP_REPLY_ARG_NOSRCCHECK : 0;
 
         net = dev_net(skb_dst(skb)->dev);
+        arg.tos = ip_hdr(skb)->tos;
         ip_send_reply(net->ipv4.tcp_sock, skb, ip_hdr(skb)->saddr,
                       &arg, arg.iov[0].iov_len);
 
@@ -666,9 +667,9 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
 static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
                             u32 win, u32 ts, int oif,
                             struct tcp_md5sig_key *key,
-                            int reply_flags)
+                            int reply_flags, u8 tos)
 {
-        struct tcphdr *th = tcp_hdr(skb);
+        const struct tcphdr *th = tcp_hdr(skb);
         struct {
                 struct tcphdr th;
                 __be32 opt[(TCPOLEN_TSTAMP_ALIGNED >> 2)
@@ -726,7 +727,7 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
         arg.csumoffset = offsetof(struct tcphdr, check) / 2;
         if (oif)
                 arg.bound_dev_if = oif;
-
+        arg.tos = tos;
         ip_send_reply(net->ipv4.tcp_sock, skb, ip_hdr(skb)->saddr,
                       &arg, arg.iov[0].iov_len);
 
@@ -743,7 +744,8 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
                         tcptw->tw_ts_recent,
                         tw->tw_bound_dev_if,
                         tcp_twsk_md5_key(tcptw),
-                        tw->tw_transparent ? IP_REPLY_ARG_NOSRCCHECK : 0
+                        tw->tw_transparent ? IP_REPLY_ARG_NOSRCCHECK : 0,
+                        tw->tw_tos
                         );
 
         inet_twsk_put(tw);
@@ -757,7 +759,8 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
                         req->ts_recent,
                         0,
                         tcp_v4_md5_do_lookup(sk, ip_hdr(skb)->daddr),
-                        inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0);
+                        inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0,
+                        ip_hdr(skb)->tos);
 }
 
 /*
@@ -808,20 +811,38 @@ static void tcp_v4_reqsk_destructor(struct request_sock *req)
         kfree(inet_rsk(req)->opt);
 }
 
-static void syn_flood_warning(const struct sk_buff *skb)
+/*
+ * Return 1 if a syncookie should be sent
+ */
+int tcp_syn_flood_action(struct sock *sk,
+                         const struct sk_buff *skb,
+                         const char *proto)
 {
-        const char *msg;
+        const char *msg = "Dropping request";
+        int want_cookie = 0;
+        struct listen_sock *lopt;
+
+
 
 #ifdef CONFIG_SYN_COOKIES
-        if (sysctl_tcp_syncookies)
+        if (sysctl_tcp_syncookies) {
                 msg = "Sending cookies";
-        else
+                want_cookie = 1;
+                NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPREQQFULLDOCOOKIES);
+        } else
 #endif
-                msg = "Dropping request";
+                NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPREQQFULLDROP);
 
-        pr_info("TCP: Possible SYN flooding on port %d. %s.\n",
-                                ntohs(tcp_hdr(skb)->dest), msg);
+        lopt = inet_csk(sk)->icsk_accept_queue.listen_opt;
+        if (!lopt->synflood_warned) {
+                lopt->synflood_warned = 1;
+                pr_info("%s: Possible SYN flooding on port %d. %s. "
+                        " Check SNMP counters.\n",
+                        proto, ntohs(tcp_hdr(skb)->dest), msg);
+        }
+        return want_cookie;
 }
+EXPORT_SYMBOL(tcp_syn_flood_action);
 
 /*
  * Save and compile IPv4 options into the request_sock if needed.
@@ -909,18 +930,21 @@ int tcp_v4_md5_do_add(struct sock *sk, __be32 addr,
                         }
                         sk_nocaps_add(sk, NETIF_F_GSO_MASK);
                 }
-                if (tcp_alloc_md5sig_pool(sk) == NULL) {
+
+                md5sig = tp->md5sig_info;
+                if (md5sig->entries4 == 0 &&
+                    tcp_alloc_md5sig_pool(sk) == NULL) {
                         kfree(newkey);
                         return -ENOMEM;
                 }
-                md5sig = tp->md5sig_info;
 
                 if (md5sig->alloced4 == md5sig->entries4) {
                         keys = kmalloc((sizeof(*keys) *
                                         (md5sig->entries4 + 1)), GFP_ATOMIC);
                         if (!keys) {
                                 kfree(newkey);
-                                tcp_free_md5sig_pool();
+                                if (md5sig->entries4 == 0)
+                                        tcp_free_md5sig_pool();
                                 return -ENOMEM;
                         }
 
@@ -964,6 +988,7 @@ int tcp_v4_md5_do_del(struct sock *sk, __be32 addr)
                                 kfree(tp->md5sig_info->keys4);
                                 tp->md5sig_info->keys4 = NULL;
                                 tp->md5sig_info->alloced4 = 0;
+                                tcp_free_md5sig_pool();
                         } else if (tp->md5sig_info->entries4 != i) {
                                 /* Need to do some manipulation */
                                 memmove(&tp->md5sig_info->keys4[i],
@@ -971,7 +996,6 @@ int tcp_v4_md5_do_del(struct sock *sk, __be32 addr)
                                         (tp->md5sig_info->entries4 - i) *
                                          sizeof(struct tcp4_md5sig_key));
                         }
-                        tcp_free_md5sig_pool();
                         return 0;
                 }
         }
@@ -1069,7 +1093,7 @@ static int tcp_v4_md5_hash_pseudoheader(struct tcp_md5sig_pool *hp,
 }
 
 static int tcp_v4_md5_hash_hdr(char *md5_hash, struct tcp_md5sig_key *key,
-                               __be32 daddr, __be32 saddr, struct tcphdr *th)
+                               __be32 daddr, __be32 saddr, const struct tcphdr *th)
 {
         struct tcp_md5sig_pool *hp;
         struct hash_desc *desc;
@@ -1101,12 +1125,12 @@ clear_hash_noput:
 }
 
 int tcp_v4_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key,
-                        struct sock *sk, struct request_sock *req,
-                        struct sk_buff *skb)
+                        const struct sock *sk, const struct request_sock *req,
+                        const struct sk_buff *skb)
 {
         struct tcp_md5sig_pool *hp;
         struct hash_desc *desc;
-        struct tcphdr *th = tcp_hdr(skb);
+        const struct tcphdr *th = tcp_hdr(skb);
         __be32 saddr, daddr;
 
         if (sk) {
@@ -1151,7 +1175,7 @@ clear_hash_noput:
 }
 EXPORT_SYMBOL(tcp_v4_md5_hash_skb);
 
-static int tcp_v4_inbound_md5_hash(struct sock *sk, struct sk_buff *skb)
+static int tcp_v4_inbound_md5_hash(struct sock *sk, const struct sk_buff *skb)
 {
         /*
          * This gets called for each TCP segment that arrives
@@ -1161,10 +1185,10 @@ static int tcp_v4_inbound_md5_hash(struct sock *sk, struct sk_buff *skb)
          * o MD5 hash and we're not expecting one.
          * o MD5 hash and its wrong.
          */
-        __u8 *hash_location = NULL;
+        const __u8 *hash_location = NULL;
         struct tcp_md5sig_key *hash_expected;
         const struct iphdr *iph = ip_hdr(skb);
-        struct tcphdr *th = tcp_hdr(skb);
+        const struct tcphdr *th = tcp_hdr(skb);
         int genhash;
         unsigned char newhash[16];
 
@@ -1227,7 +1251,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 {
         struct tcp_extend_values tmp_ext;
         struct tcp_options_received tmp_opt;
-        u8 *hash_location;
+        const u8 *hash_location;
         struct request_sock *req;
         struct inet_request_sock *ireq;
         struct tcp_sock *tp = tcp_sk(sk);
@@ -1235,11 +1259,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
         __be32 saddr = ip_hdr(skb)->saddr;
         __be32 daddr = ip_hdr(skb)->daddr;
         __u32 isn = TCP_SKB_CB(skb)->when;
-#ifdef CONFIG_SYN_COOKIES
         int want_cookie = 0;
-#else
-#define want_cookie 0 /* Argh, why doesn't gcc optimize this :( */
-#endif
 
         /* Never answer to SYNs send to broadcast or multicast */
         if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
@@ -1250,14 +1270,9 @@ 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;
-                } else
-#endif
-                goto drop;
+                want_cookie = tcp_syn_flood_action(sk, skb, "TCP");
+                if (!want_cookie)
+                        goto drop;
         }
 
         /* Accept backlog is full. If we have already queued enough
@@ -1303,9 +1318,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
                 while (l-- > 0)
                         *c++ ^= *hash_location++;
 
-#ifdef CONFIG_SYN_COOKIES
                 want_cookie = 0;        /* not our kind of cookie */
-#endif
                 tmp_ext.cookie_out_never = 0; /* false */
                 tmp_ext.cookie_plus = tmp_opt.cookie_plus;
         } else if (!tp->rx_opt.cookie_in_always) {
@@ -1497,6 +1510,8 @@ exit:
         NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
         return NULL;
 put_and_exit:
+        tcp_clear_xmit_timers(newsk);
+        bh_unlock_sock(newsk);
         sock_put(newsk);
         goto exit;
 }
@@ -1578,7 +1593,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
 #endif
 
         if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
-                sock_rps_save_rxhash(sk, skb->rxhash);
+                sock_rps_save_rxhash(sk, skb);
                 if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len)) {
                         rsk = sk;
                         goto reset;
@@ -1595,7 +1610,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
                         goto discard;
 
                 if (nsk != sk) {
-                        sock_rps_save_rxhash(nsk, skb->rxhash);
+                        sock_rps_save_rxhash(nsk, skb);
                         if (tcp_child_process(sk, nsk, skb)) {
                                 rsk = nsk;
                                 goto reset;
@@ -1603,7 +1618,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
                         return 0;
                 }
         } else
-                sock_rps_save_rxhash(sk, skb->rxhash);
+                sock_rps_save_rxhash(sk, skb);
 
         if (tcp_rcv_state_process(sk, skb, tcp_hdr(skb), skb->len)) {
                 rsk = sk;
@@ -1635,7 +1650,7 @@ EXPORT_SYMBOL(tcp_v4_do_rcv);
 int tcp_v4_rcv(struct sk_buff *skb)
 {
         const struct iphdr *iph;
-        struct tcphdr *th;
+        const struct tcphdr *th;
         struct sock *sk;
         int ret;
         struct net *net = dev_net(skb->dev);
@@ -1670,7 +1685,7 @@ int tcp_v4_rcv(struct sk_buff *skb)
                                     skb->len - th->doff * 4);
         TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
         TCP_SKB_CB(skb)->when    = 0;
-        TCP_SKB_CB(skb)->flags   = iph->tos;
+        TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph);
         TCP_SKB_CB(skb)->sacked  = 0;
 
         sk = __inet_lookup_skb(&tcp_hashinfo, skb, th->source, th->dest);
@@ -1799,7 +1814,7 @@ EXPORT_SYMBOL(tcp_v4_get_peer);
 
 void *tcp_v4_tw_get_peer(struct sock *sk)
 {
-        struct inet_timewait_sock *tw = inet_twsk(sk);
+        const struct inet_timewait_sock *tw = inet_twsk(sk);
 
         return inet_getpeer_v4(tw->tw_daddr, 1);
 }
@@ -2326,7 +2341,7 @@ static void tcp_seq_stop(struct seq_file *seq, void *v)
         }
 }
 
-static int tcp_seq_open(struct inode *inode, struct file *file)
+int tcp_seq_open(struct inode *inode, struct file *file)
 {
         struct tcp_seq_afinfo *afinfo = PDE(inode)->data;
         struct tcp_iter_state *s;
@@ -2342,23 +2357,19 @@ static int tcp_seq_open(struct inode *inode, struct file *file)
         s->last_pos             = 0;
         return 0;
 }
+EXPORT_SYMBOL(tcp_seq_open);
 
 int tcp_proc_register(struct net *net, struct tcp_seq_afinfo *afinfo)
 {
         int rc = 0;
         struct proc_dir_entry *p;
 
-        afinfo->seq_fops.open           = tcp_seq_open;
-        afinfo->seq_fops.read           = seq_read;
-        afinfo->seq_fops.llseek         = seq_lseek;
-        afinfo->seq_fops.release        = seq_release_net;
-
         afinfo->seq_ops.start           = tcp_seq_start;
         afinfo->seq_ops.next            = tcp_seq_next;
         afinfo->seq_ops.stop            = tcp_seq_stop;
 
         p = proc_create_data(afinfo->name, S_IRUGO, net->proc_net,
-                             &afinfo->seq_fops, afinfo);
+                             afinfo->seq_fops, afinfo);
         if (!p)
                 rc = -ENOMEM;
         return rc;
@@ -2371,7 +2382,7 @@ void tcp_proc_unregister(struct net *net, struct tcp_seq_afinfo *afinfo)
 }
 EXPORT_SYMBOL(tcp_proc_unregister);
 
-static void get_openreq4(struct sock *sk, struct request_sock *req,
+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);
@@ -2401,9 +2412,9 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i, int *len)
 {
         int timer_active;
         unsigned long timer_expires;
-        struct tcp_sock *tp = tcp_sk(sk);
+        const struct tcp_sock *tp = tcp_sk(sk);
         const struct inet_connection_sock *icsk = inet_csk(sk);
-        struct inet_sock *inet = inet_sk(sk);
+        const struct inet_sock *inet = inet_sk(sk);
         __be32 dest = inet->inet_daddr;
         __be32 src = inet->inet_rcv_saddr;
         __u16 destp = ntohs(inet->inet_dport);
@@ -2452,7 +2463,7 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i, int *len)
                 len);
 }
 
-static void get_timewait4_sock(struct inet_timewait_sock *tw,
+static void get_timewait4_sock(const struct inet_timewait_sock *tw,
                                struct seq_file *f, int i, int *len)
 {
         __be32 dest, src;
@@ -2507,12 +2518,18 @@ out:
         return 0;
 }
 
+static const struct file_operations tcp_afinfo_seq_fops = {
+        .owner   = THIS_MODULE,
+        .open    = tcp_seq_open,
+        .read    = seq_read,
+        .llseek  = seq_lseek,
+        .release = seq_release_net
+};
+
 static struct tcp_seq_afinfo tcp4_seq_afinfo = {
         .name           = "tcp",
         .family         = AF_INET,
-        .seq_fops       = {
-                .owner          = THIS_MODULE,
-        },
+        .seq_fops       = &tcp_afinfo_seq_fops,
         .seq_ops        = {
                 .show           = tcp4_seq_show,
         },