Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6

[cascardo/linux.git] / net / ipv4 / tcp.c

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 21387eb..524f976 100644 (file)
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -326,6 +326,43 @@ void tcp_enter_memory_pressure(struct sock *sk)
 
 EXPORT_SYMBOL(tcp_enter_memory_pressure);
 
+/* Convert seconds to retransmits based on initial and max timeout */
+static u8 secs_to_retrans(int seconds, int timeout, int rto_max)
+{
+       u8 res = 0;
+
+       if (seconds > 0) {
+               int period = timeout;
+
+               res = 1;
+               while (seconds > period && res < 255) {
+                       res++;
+                       timeout <<= 1;
+                       if (timeout > rto_max)
+                               timeout = rto_max;
+                       period += timeout;
+               }
+       }
+       return res;
+}
+
+/* Convert retransmits to seconds based on initial and max timeout */
+static int retrans_to_secs(u8 retrans, int timeout, int rto_max)
+{
+       int period = 0;
+
+       if (retrans > 0) {
+               period = timeout;
+               while (--retrans) {
+                       timeout <<= 1;
+                       if (timeout > rto_max)
+                               timeout = rto_max;
+                       period += timeout;
+               }
+       }
+       return period;
+}
+
 /*
  *     Wait for a TCP event.
  *
@@ -580,7 +617,7 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos,
 
        lock_sock(sk);
 
-       timeo = sock_rcvtimeo(sk, flags & SPLICE_F_NONBLOCK);
+       timeo = sock_rcvtimeo(sk, sock->file->f_flags & O_NONBLOCK);
        while (tss.len) {
                ret = __tcp_splice_read(sk, &tss);
                if (ret < 0)
@@ -1146,7 +1183,9 @@ void tcp_cleanup_rbuf(struct sock *sk, int copied)
 #if TCP_DEBUG
        struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);
 
-       WARN_ON(skb && !before(tp->copied_seq, TCP_SKB_CB(skb)->end_seq));
+       WARN(skb && !before(tp->copied_seq, TCP_SKB_CB(skb)->end_seq),
+            KERN_INFO "cleanup rbuf bug: copied %X seq %X rcvnxt %X\n",
+            tp->copied_seq, TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt);
 #endif
 
        if (inet_csk_ack_scheduled(sk)) {
@@ -1393,11 +1432,13 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
                        /* Now that we have two receive queues this
                         * shouldn't happen.
                         */
-                       if (before(*seq, TCP_SKB_CB(skb)->seq)) {
-                               printk(KERN_INFO "recvmsg bug: copied %X "
-                                      "seq %X\n", *seq, TCP_SKB_CB(skb)->seq);
+                       if (WARN(before(*seq, TCP_SKB_CB(skb)->seq),
+                            KERN_INFO "recvmsg bug: copied %X "
+                                      "seq %X rcvnxt %X fl %X\n", *seq,
+                                      TCP_SKB_CB(skb)->seq, tp->rcv_nxt,
+                                      flags))
                                break;
-                       }
+
                        offset = *seq - TCP_SKB_CB(skb)->seq;
                        if (tcp_hdr(skb)->syn)
                                offset--;
@@ -1405,7 +1446,10 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
                                goto found_ok_skb;
                        if (tcp_hdr(skb)->fin)
                                goto found_fin_ok;
-                       WARN_ON(!(flags & MSG_PEEK));
+                       WARN(!(flags & MSG_PEEK), KERN_INFO "recvmsg bug 2: "
+                                       "copied %X seq %X rcvnxt %X fl %X\n",
+                                       *seq, TCP_SKB_CB(skb)->seq,
+                                       tp->rcv_nxt, flags);
                }
 
                /* Well, if we have backlog, try to process it now yet. */
@@ -1998,7 +2042,7 @@ int tcp_disconnect(struct sock *sk, int flags)
        __skb_queue_purge(&sk->sk_async_wait_queue);
 #endif
 
-       inet->dport = 0;
+       inet->inet_dport = 0;
 
        if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
                inet_reset_saddr(sk);
@@ -2022,7 +2066,7 @@ int tcp_disconnect(struct sock *sk, int flags)
        memset(&tp->rx_opt, 0, sizeof(tp->rx_opt));
        __sk_dst_reset(sk);
 
-       WARN_ON(inet->num && !icsk->icsk_bind_hash);
+       WARN_ON(inet->inet_num && !icsk->icsk_bind_hash);
 
        sk->sk_error_report(sk);
        return err;
@@ -2032,7 +2076,7 @@ int tcp_disconnect(struct sock *sk, int flags)
  *     Socket option code for TCP.
  */
 static int do_tcp_setsockopt(struct sock *sk, int level,
-               int optname, char __user *optval, int optlen)
+               int optname, char __user *optval, unsigned int optlen)
 {
        struct tcp_sock *tp = tcp_sk(sk);
        struct inet_connection_sock *icsk = inet_csk(sk);
@@ -2047,7 +2091,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
                        return -EINVAL;
 
                val = strncpy_from_user(name, optval,
-                                       min(TCP_CA_NAME_MAX-1, optlen));
+                                       min_t(long, TCP_CA_NAME_MAX-1, optlen));
                if (val < 0)
                        return -EFAULT;
                name[val] = 0;
@@ -2163,16 +2207,10 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
                break;
 
        case TCP_DEFER_ACCEPT:
-               icsk->icsk_accept_queue.rskq_defer_accept = 0;
-               if (val > 0) {
-                       /* Translate value in seconds to number of
-                        * retransmits */
-                       while (icsk->icsk_accept_queue.rskq_defer_accept < 32 &&
-                              val > ((TCP_TIMEOUT_INIT / HZ) <<
-                                      icsk->icsk_accept_queue.rskq_defer_accept))
-                               icsk->icsk_accept_queue.rskq_defer_accept++;
-                       icsk->icsk_accept_queue.rskq_defer_accept++;
-               }
+               /* Translate value in seconds to number of retransmits */
+               icsk->icsk_accept_queue.rskq_defer_accept =
+                       secs_to_retrans(val, TCP_TIMEOUT_INIT / HZ,
+                                       TCP_RTO_MAX / HZ);
                break;
 
        case TCP_WINDOW_CLAMP:
@@ -2220,7 +2258,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 }
 
 int tcp_setsockopt(struct sock *sk, int level, int optname, char __user *optval,
-                  int optlen)
+                  unsigned int optlen)
 {
        struct inet_connection_sock *icsk = inet_csk(sk);
 
@@ -2232,7 +2270,7 @@ int tcp_setsockopt(struct sock *sk, int level, int optname, char __user *optval,
 
 #ifdef CONFIG_COMPAT
 int compat_tcp_setsockopt(struct sock *sk, int level, int optname,
-                         char __user *optval, int optlen)
+                         char __user *optval, unsigned int optlen)
 {
        if (level != SOL_TCP)
                return inet_csk_compat_setsockopt(sk, level, optname,
@@ -2353,8 +2391,8 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
                        val = (val ? : sysctl_tcp_fin_timeout) / HZ;
                break;
        case TCP_DEFER_ACCEPT:
-               val = !icsk->icsk_accept_queue.rskq_defer_accept ? 0 :
-                       ((TCP_TIMEOUT_INIT / HZ) << (icsk->icsk_accept_queue.rskq_defer_accept - 1));
+               val = retrans_to_secs(icsk->icsk_accept_queue.rskq_defer_accept,
+                                     TCP_TIMEOUT_INIT / HZ, TCP_RTO_MAX / HZ);
                break;
        case TCP_WINDOW_CLAMP:
                val = tp->window_clamp;
@@ -2865,11 +2903,10 @@ void __init tcp_init(void)
                                        (totalram_pages >= 128 * 1024) ?
                                        13 : 15,
                                        0,
-                                       &tcp_hashinfo.ehash_size,
                                        NULL,
+                                       &tcp_hashinfo.ehash_mask,
                                        thash_entries ? 0 : 512 * 1024);
-       tcp_hashinfo.ehash_size = 1 << tcp_hashinfo.ehash_size;
-       for (i = 0; i < tcp_hashinfo.ehash_size; i++) {
+       for (i = 0; i <= tcp_hashinfo.ehash_mask; i++) {
                INIT_HLIST_NULLS_HEAD(&tcp_hashinfo.ehash[i].chain, i);
                INIT_HLIST_NULLS_HEAD(&tcp_hashinfo.ehash[i].twchain, i);
        }
@@ -2878,7 +2915,7 @@ void __init tcp_init(void)
        tcp_hashinfo.bhash =
                alloc_large_system_hash("TCP bind",
                                        sizeof(struct inet_bind_hashbucket),
-                                       tcp_hashinfo.ehash_size,
+                                       tcp_hashinfo.ehash_mask + 1,
                                        (totalram_pages >= 128 * 1024) ?
                                        13 : 15,
                                        0,
@@ -2933,8 +2970,8 @@ void __init tcp_init(void)
        sysctl_tcp_rmem[2] = max(87380, max_share);
 
        printk(KERN_INFO "TCP: Hash tables configured "
-              "(established %d bind %d)\n",
-              tcp_hashinfo.ehash_size, tcp_hashinfo.bhash_size);
+              "(established %u bind %u)\n",
+              tcp_hashinfo.ehash_mask + 1, tcp_hashinfo.bhash_size);
 
        tcp_register_congestion_control(&tcp_reno);
 }