tcp: Make TCP_MAXSEG minimum more correct.

[pandora-kernel.git] / net / ipv4 / tcp.c

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 176e11a..f15c36a 100644 (file)
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -282,7 +282,7 @@ int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT;
 struct percpu_counter tcp_orphan_count;
 EXPORT_SYMBOL_GPL(tcp_orphan_count);
 
-int sysctl_tcp_mem[3] __read_mostly;
+long sysctl_tcp_mem[3] __read_mostly;
 int sysctl_tcp_wmem[3] __read_mostly;
 int sysctl_tcp_rmem[3] __read_mostly;
 
@@ -290,7 +290,7 @@ EXPORT_SYMBOL(sysctl_tcp_mem);
 EXPORT_SYMBOL(sysctl_tcp_rmem);
 EXPORT_SYMBOL(sysctl_tcp_wmem);
 
-atomic_t tcp_memory_allocated; /* Current allocated memory. */
+atomic_long_t tcp_memory_allocated;    /* Current allocated memory. */
 EXPORT_SYMBOL(tcp_memory_allocated);
 
 /*
@@ -386,8 +386,6 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
         */
 
        mask = 0;
-       if (sk->sk_err)
-               mask = POLLERR;
 
        /*
         * POLLHUP is certainly not done right. But poll() doesn't
@@ -451,11 +449,17 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
                                if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk))
                                        mask |= POLLOUT | POLLWRNORM;
                        }
-               }
+               } else
+                       mask |= POLLOUT | POLLWRNORM;
 
                if (tp->urg_data & TCP_URG_VALID)
                        mask |= POLLPRI;
        }
+       /* This barrier is coupled with smp_wmb() in tcp_reset() */
+       smp_rmb();
+       if (sk->sk_err)
+               mask |= POLLERR;
+
        return mask;
 }
 EXPORT_SYMBOL(tcp_poll);
@@ -939,7 +943,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
        sg = sk->sk_route_caps & NETIF_F_SG;
 
        while (--iovlen >= 0) {
-               int seglen = iov->iov_len;
+               size_t seglen = iov->iov_len;
                unsigned char __user *from = iov->iov_base;
 
                iov++;
@@ -2011,11 +2015,8 @@ adjudge_to_death:
                }
        }
        if (sk->sk_state != TCP_CLOSE) {
-               int orphan_count = percpu_counter_read_positive(
-                                               sk->sk_prot->orphan_count);
-
                sk_mem_reclaim(sk);
-               if (tcp_too_many_orphans(sk, orphan_count)) {
+               if (tcp_too_many_orphans(sk, 0)) {
                        if (net_ratelimit())
                                printk(KERN_INFO "TCP: too many of orphaned "
                                       "sockets\n");
@@ -2245,7 +2246,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
                /* Values greater than interface MTU won't take effect. However
                 * at the point when this call is done we typically don't yet
                 * know which interface is going to be used */
-               if (val < 8 || val > MAX_TCP_WINDOW) {
+               if (val < TCP_MIN_MSS || val > MAX_TCP_WINDOW) {
                        err = -EINVAL;
                        break;
                }
@@ -2391,7 +2392,12 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
                err = tp->af_specific->md5_parse(sk, optval, optlen);
                break;
 #endif
-
+       case TCP_USER_TIMEOUT:
+               /* 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);
+               break;
        default:
                err = -ENOPROTOOPT;
                break;
@@ -2610,6 +2616,10 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
        case TCP_THIN_DUPACK:
                val = tp->thin_dupack;
                break;
+
+       case TCP_USER_TIMEOUT:
+               val = jiffies_to_msecs(icsk->icsk_user_timeout);
+               break;
        default:
                return -ENOPROTOOPT;
        }
@@ -3212,7 +3222,7 @@ void __init tcp_init(void)
 {
        struct sk_buff *skb = NULL;
        unsigned long nr_pages, limit;
-       int order, i, max_share;
+       int i, max_share, cnt;
        unsigned long jiffy = jiffies;
 
        BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb));
@@ -3261,22 +3271,12 @@ void __init tcp_init(void)
                INIT_HLIST_HEAD(&tcp_hashinfo.bhash[i].chain);
        }
 
-       /* Try to be a bit smarter and adjust defaults depending
-        * on available memory.
-        */
-       for (order = 0; ((1 << order) << PAGE_SHIFT) <
-                       (tcp_hashinfo.bhash_size * sizeof(struct inet_bind_hashbucket));
-                       order++)
-               ;
-       if (order >= 4) {
-               tcp_death_row.sysctl_max_tw_buckets = 180000;
-               sysctl_tcp_max_orphans = 4096 << (order - 4);
-               sysctl_max_syn_backlog = 1024;
-       } else if (order < 3) {
-               tcp_death_row.sysctl_max_tw_buckets >>= (3 - order);
-               sysctl_tcp_max_orphans >>= (3 - order);
-               sysctl_max_syn_backlog = 128;
-       }
+
+       cnt = tcp_hashinfo.ehash_mask + 1;
+
+       tcp_death_row.sysctl_max_tw_buckets = cnt / 2;
+       sysctl_tcp_max_orphans = cnt / 2;
+       sysctl_max_syn_backlog = max(128, cnt / 256);
 
        /* Set the pressure threshold to be a fraction of global memory that
         * is up to 1/2 at 256 MB, decreasing toward zero with the amount of