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

Conflicts:
	net/ipv4/Kconfig
	net/ipv4/tcp_timer.c

6 files changed, 33 insertions, 17 deletions

diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 5462e2d147a6..e848e6c062cd 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -223,7 +223,7 @@ config NET_IPGRE_DEMUX
 
 config NET_IPGRE
         tristate "IP: GRE tunnels over IP"
-        depends on NET_IPGRE_DEMUX
+        depends on (IPV6 || IPV6=n) && NET_IPGRE_DEMUX
         help
           Tunneling means encapsulating data of one protocol type within
           another protocol and sending it over a channel that understands the
@@ -419,7 +419,7 @@ config INET_XFRM_MODE_BEET
           If unsure, say Y.
 
 config INET_LRO
-        bool "Large Receive Offload (ipv4/tcp)"
+        tristate "Large Receive Offload (ipv4/tcp)"
         default y
         ---help---
           Support for Large Receive Offload (ipv4/tcp).
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 1fdcacd36ce7..2a4bb76f2132 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -834,7 +834,7 @@ static void igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb,
         int                     mark = 0;
 
 
-        if (len == 8 || IGMP_V2_SEEN(in_dev)) {
+        if (len == 8) {
                 if (ih->code == 0) {
                         /* Alas, old v1 router presents here. */
 
@@ -856,6 +856,18 @@ static void igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb,
                 igmpv3_clear_delrec(in_dev);
         } else if (len < 12) {
                 return; /* ignore bogus packet; freed by caller */
+        } else if (IGMP_V1_SEEN(in_dev)) {
+                /* This is a v3 query with v1 queriers present */
+                max_delay = IGMP_Query_Response_Interval;
+                group = 0;
+        } else if (IGMP_V2_SEEN(in_dev)) {
+                /* this is a v3 query with v2 queriers present;
+                 * Interpretation of the max_delay code is problematic here.
+                 * A real v2 host would use ih_code directly, while v3 has a
+                 * different encoding. We use the v3 encoding as more likely
+                 * to be intended in a v3 query.
+                 */
+                max_delay = IGMPV3_MRC(ih3->code)*(HZ/IGMP_TIMER_SCALE);
         } else { /* v3 */
                 if (!pskb_may_pull(skb, sizeof(struct igmpv3_query)))
                         return;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index c3cb8bd23638..04e0df82b88c 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1232,7 +1232,7 @@ restart:
                         }
 
                         if (net_ratelimit())
-                                printk(KERN_WARNING "Neighbour table overflow.\n");
+                                printk(KERN_WARNING "ipv4: Neighbour table overflow.\n");
                         rt_drop(rt);
                         return -ENOBUFS;
                 }
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 19192c5fe67a..1664a0590bb8 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -943,7 +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++;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index eaf20e7e61da..f6fdd727a23d 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2532,7 +2532,8 @@ static void tcp_mark_head_lost(struct sock *sk, int packets)
                         cnt += tcp_skb_pcount(skb);
 
                 if (cnt > packets) {
-                        if (tcp_is_sack(tp) || (oldcnt >= packets))
+                        if ((tcp_is_sack(tp) && !tcp_is_fack(tp)) ||
+                            (oldcnt >= packets))
                                 break;
 
                         mss = skb_shinfo(skb)->gso_size;
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index baea4a129022..f3c8c6c019ae 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -135,13 +135,16 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk)
 
 /* This function calculates a "timeout" which is equivalent to the timeout of a
  * TCP connection after "boundary" unsuccessful, exponentially backed-off
- * retransmissions with an initial RTO of TCP_RTO_MIN.
+ * retransmissions with an initial RTO of TCP_RTO_MIN or TCP_TIMEOUT_INIT if
+ * syn_set flag is set.
  */
 static bool retransmits_timed_out(struct sock *sk,
                                   unsigned int boundary,
-                                  unsigned int timeout)
+                                  unsigned int timeout,
+                                  bool syn_set)
 {
         unsigned int linear_backoff_thresh, start_ts;
+        unsigned int rto_base = syn_set ? TCP_TIMEOUT_INIT : TCP_RTO_MIN;
 
         if (!inet_csk(sk)->icsk_retransmits)
                 return false;
@@ -152,12 +155,12 @@ static bool retransmits_timed_out(struct sock *sk,
                 start_ts = tcp_sk(sk)->retrans_stamp;
 
         if (likely(timeout == 0)) {
-                linear_backoff_thresh = ilog2(TCP_RTO_MAX/TCP_RTO_MIN);
+                linear_backoff_thresh = ilog2(TCP_RTO_MAX/rto_base);
 
                 if (boundary <= linear_backoff_thresh)
-                        timeout = ((2 << boundary) - 1) * TCP_RTO_MIN;
+                        timeout = ((2 << boundary) - 1) * rto_base;
                 else
-                        timeout = ((2 << linear_backoff_thresh) - 1) * TCP_RTO_MIN +
+                        timeout = ((2 << linear_backoff_thresh) - 1) * rto_base +
                                 (boundary - linear_backoff_thresh) * TCP_RTO_MAX;
         }
         return (tcp_time_stamp - start_ts) >= timeout;
@@ -168,14 +171,15 @@ static int tcp_write_timeout(struct sock *sk)
 {
         struct inet_connection_sock *icsk = inet_csk(sk);
         int retry_until;
-        bool do_reset;
+        bool do_reset, syn_set = 0;
 
         if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
                 if (icsk->icsk_retransmits)
                         dst_negative_advice(sk);
                 retry_until = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries;
+                syn_set = 1;
         } else {
-                if (retransmits_timed_out(sk, sysctl_tcp_retries1, 0)) {
+                if (retransmits_timed_out(sk, sysctl_tcp_retries1, 0, 0)) {
                         /* Black hole detection */
                         tcp_mtu_probing(icsk, sk);
 
@@ -188,7 +192,7 @@ static int tcp_write_timeout(struct sock *sk)
 
                         retry_until = tcp_orphan_retries(sk, alive);
                         do_reset = alive ||
-                                   !retransmits_timed_out(sk, retry_until, 0);
+                                !retransmits_timed_out(sk, retry_until, 0, 0);
 
                         if (tcp_out_of_resources(sk, do_reset))
                                 return 1;
@@ -196,8 +200,7 @@ static int tcp_write_timeout(struct sock *sk)
         }
 
         if (retransmits_timed_out(sk, retry_until,
-            (1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV) ? 0 :
-            icsk->icsk_user_timeout)) {
+                                  syn_set ? 0 : icsk->icsk_user_timeout, syn_set)) {
                 /* Has it gone just too far? */
                 tcp_write_err(sk);
                 return 1;
@@ -439,7 +442,7 @@ out_reset_timer:
                 icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX);
         }
         inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, icsk->icsk_rto, TCP_RTO_MAX);
-        if (retransmits_timed_out(sk, sysctl_tcp_retries1 + 1, 0))
+        if (retransmits_timed_out(sk, sysctl_tcp_retries1 + 1, 0, 0))
                 __sk_dst_reset(sk);
 
 out:;