13 files changed, 85 insertions, 45 deletions

diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 571f8950ed0..7cd7760144f 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -217,6 +217,7 @@ config NET_IPIP
 
 config NET_IPGRE
         tristate "IP: GRE tunnels over IP"
+        depends on IPV6 || IPV6=n
         help
           Tunneling means encapsulating data of one protocol type within
           another protocol and sending it over a channel that understands the
@@ -412,7 +413,7 @@ 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 1fdcacd36ce..2a4bb76f213 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/ip_gre.c b/net/ipv4/ip_gre.c
index 945b20a5ad5..35c93e8b6a4 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -45,7 +45,7 @@
 #include <net/netns/generic.h>
 #include <net/rtnetlink.h>
 
-#ifdef CONFIG_IPV6
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
 #include <net/ipv6.h>
 #include <net/ip6_fib.h>
 #include <net/ip6_route.h>
@@ -699,7 +699,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
                         if ((dst = rt->rt_gateway) == 0)
                                 goto tx_error_icmp;
                 }
-#ifdef CONFIG_IPV6
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
                 else if (skb->protocol == htons(ETH_P_IPV6)) {
                         struct in6_addr *addr6;
                         int addr_type;
@@ -774,7 +774,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
                         goto tx_error;
                 }
         }
-#ifdef CONFIG_IPV6
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
         else if (skb->protocol == htons(ETH_P_IPV6)) {
                 struct rt6_info *rt6 = (struct rt6_info *)skb_dst(skb);
 
@@ -850,7 +850,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
         if ((iph->ttl = tiph->ttl) == 0) {
                 if (skb->protocol == htons(ETH_P_IP))
                         iph->ttl = old_iph->ttl;
-#ifdef CONFIG_IPV6
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
                 else if (skb->protocol == htons(ETH_P_IPV6))
                         iph->ttl = ((struct ipv6hdr *)old_iph)->hop_limit;
 #endif
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 04b69896df5..7649d775007 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -488,9 +488,8 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
          * we can switch to copy when see the first bad fragment.
          */
         if (skb_has_frags(skb)) {
-                struct sk_buff *frag;
+                struct sk_buff *frag, *frag2;
                 int first_len = skb_pagelen(skb);
-                int truesizes = 0;
 
                 if (first_len - hlen > mtu ||
                     ((first_len - hlen) & 7) ||
@@ -503,18 +502,18 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
                         if (frag->len > mtu ||
                             ((frag->len & 7) && frag->next) ||
                             skb_headroom(frag) < hlen)
-                            goto slow_path;
+                                goto slow_path_clean;
 
                         /* Partially cloned skb? */
                         if (skb_shared(frag))
-                                goto slow_path;
+                                goto slow_path_clean;
 
                         BUG_ON(frag->sk);
                         if (skb->sk) {
                                 frag->sk = skb->sk;
                                 frag->destructor = sock_wfree;
                         }
-                        truesizes += frag->truesize;
+                        skb->truesize -= frag->truesize;
                 }
 
                 /* Everything is OK. Generate! */
@@ -524,7 +523,6 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
                 frag = skb_shinfo(skb)->frag_list;
                 skb_frag_list_init(skb);
                 skb->data_len = first_len - skb_headlen(skb);
-                skb->truesize -= truesizes;
                 skb->len = first_len;
                 iph->tot_len = htons(first_len);
                 iph->frag_off = htons(IP_MF);
@@ -576,6 +574,15 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
                 }
                 IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS);
                 return err;
+
+slow_path_clean:
+                skb_walk_frags(skb, frag2) {
+                        if (frag2 == frag)
+                                break;
+                        frag2->sk = NULL;
+                        frag2->destructor = NULL;
+                        skb->truesize += frag2->truesize;
+                }
         }
 
 slow_path:
diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c
index b254dafaf42..43eec80c0e7 100644
--- a/net/ipv4/netfilter/ipt_REJECT.c
+++ b/net/ipv4/netfilter/ipt_REJECT.c
@@ -112,6 +112,7 @@ static void send_reset(struct sk_buff *oldskb, int hook)
         /* ip_route_me_harder expects skb->dst to be set */
         skb_dst_set_noref(nskb, skb_dst(oldskb));
 
+        nskb->protocol = htons(ETH_P_IP);
         if (ip_route_me_harder(nskb, addr_type))
                 goto free_nskb;
 
diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c
index eab8de32f20..f3a9b42b16c 100644
--- a/net/ipv4/netfilter/nf_defrag_ipv4.c
+++ b/net/ipv4/netfilter/nf_defrag_ipv4.c
@@ -66,9 +66,11 @@ static unsigned int ipv4_conntrack_defrag(unsigned int hooknum,
                                           const struct net_device *out,
                                           int (*okfn)(struct sk_buff *))
 {
+        struct sock *sk = skb->sk;
         struct inet_sock *inet = inet_sk(skb->sk);
 
-        if (inet && inet->nodefrag)
+        if (sk && (sk->sk_family == PF_INET) &&
+            inet->nodefrag)
                 return NF_ACCEPT;
 
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c
index 1679e2c0963..ee5f419d0a5 100644
--- a/net/ipv4/netfilter/nf_nat_snmp_basic.c
+++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c
@@ -893,13 +893,15 @@ static void fast_csum(__sum16 *csum,
         unsigned char s[4];
 
         if (offset & 1) {
-                s[0] = s[2] = 0;
+                s[0] = ~0;
                 s[1] = ~*optr;
+                s[2] = 0;
                 s[3] = *nptr;
         } else {
-                s[1] = s[3] = 0;
                 s[0] = ~*optr;
+                s[1] = ~0;
                 s[2] = *nptr;
+                s[3] = 0;
         }
 
         *csum = csum_fold(csum_partial(s, 4, ~csum_unfold(*csum)));
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 6298f75d5e9..ac6559cb54f 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1231,7 +1231,7 @@ 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 3fb1428e526..f115ea68a4e 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -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
@@ -457,6 +455,11 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
                 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);
@@ -940,7 +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 e663b78a2ef..b55f60f6fcb 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2545,7 +2545,8 @@ 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;
@@ -4048,6 +4049,8 @@ static void tcp_reset(struct sock *sk)
         default:
                 sk->sk_err = ECONNRESET;
         }
+        /* This barrier is coupled with smp_rmb() in tcp_poll() */
+        smp_wmb();
 
         if (!sock_flag(sk, SOCK_DEAD))
                 sk->sk_error_report(sk);
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index c35b469e851..74c54b30600 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 boundary,
+                                  bool syn_set)
 {
         unsigned int timeout, linear_backoff_thresh;
         unsigned int start_ts;
+        unsigned int rto_base = syn_set ? TCP_TIMEOUT_INIT : TCP_RTO_MIN;
 
         if (!inet_csk(sk)->icsk_retransmits)
                 return false;
@@ -151,12 +154,12 @@ static bool retransmits_timed_out(struct sock *sk,
         else
                 start_ts = tcp_sk(sk)->retrans_stamp;
 
-        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;
@@ -167,14 +170,15 @@ 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)) {
+                if (retransmits_timed_out(sk, sysctl_tcp_retries1, 0)) {
                         /* Black hole detection */
                         tcp_mtu_probing(icsk, sk);
 
@@ -187,14 +191,14 @@ static int tcp_write_timeout(struct sock *sk)
 
                         retry_until = tcp_orphan_retries(sk, alive);
                         do_reset = alive ||
-                                   !retransmits_timed_out(sk, retry_until);
+                                   !retransmits_timed_out(sk, retry_until, 0);
 
                         if (tcp_out_of_resources(sk, do_reset))
                                 return 1;
                 }
         }
 
-        if (retransmits_timed_out(sk, retry_until)) {
+        if (retransmits_timed_out(sk, retry_until, syn_set)) {
                 /* Has it gone just too far? */
                 tcp_write_err(sk);
                 return 1;
@@ -436,7 +440,7 @@ 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))
+        if (retransmits_timed_out(sk, sysctl_tcp_retries1 + 1, 0))
                 __sk_dst_reset(sk);
 
 out:;
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 869078d4eeb..a580349f0b8 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -61,7 +61,7 @@ static int xfrm4_get_saddr(struct net *net,
 
 static int xfrm4_get_tos(struct flowi *fl)
 {
-        return fl->fl4_tos;
+        return IPTOS_RT_MASK & fl->fl4_tos; /* Strip ECN bits */
 }
 
 static int xfrm4_init_path(struct xfrm_dst *path, struct dst_entry *dst,
diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c
index 1ef1366a0a0..47947624ecc 100644
--- a/net/ipv4/xfrm4_state.c
+++ b/net/ipv4/xfrm4_state.c
@@ -21,21 +21,25 @@ static int xfrm4_init_flags(struct xfrm_state *x)
 }
 
 static void
-__xfrm4_init_tempsel(struct xfrm_state *x, struct flowi *fl,
-                     struct xfrm_tmpl *tmpl,
-                     xfrm_address_t *daddr, xfrm_address_t *saddr)
+__xfrm4_init_tempsel(struct xfrm_selector *sel, struct flowi *fl)
+{
+        sel->daddr.a4 = fl->fl4_dst;
+        sel->saddr.a4 = fl->fl4_src;
+        sel->dport = xfrm_flowi_dport(fl);
+        sel->dport_mask = htons(0xffff);
+        sel->sport = xfrm_flowi_sport(fl);
+        sel->sport_mask = htons(0xffff);
+        sel->family = AF_INET;
+        sel->prefixlen_d = 32;
+        sel->prefixlen_s = 32;
+        sel->proto = fl->proto;
+        sel->ifindex = fl->oif;
+}
+
+static void
+xfrm4_init_temprop(struct xfrm_state *x, struct xfrm_tmpl *tmpl,
+                   xfrm_address_t *daddr, xfrm_address_t *saddr)
 {
-        x->sel.daddr.a4 = fl->fl4_dst;
-        x->sel.saddr.a4 = fl->fl4_src;
-        x->sel.dport = xfrm_flowi_dport(fl);
-        x->sel.dport_mask = htons(0xffff);
-        x->sel.sport = xfrm_flowi_sport(fl);
-        x->sel.sport_mask = htons(0xffff);
-        x->sel.family = AF_INET;
-        x->sel.prefixlen_d = 32;
-        x->sel.prefixlen_s = 32;
-        x->sel.proto = fl->proto;
-        x->sel.ifindex = fl->oif;
         x->id = tmpl->id;
         if (x->id.daddr.a4 == 0)
                 x->id.daddr.a4 = daddr->a4;
@@ -70,6 +74,7 @@ static struct xfrm_state_afinfo xfrm4_state_afinfo = {
         .owner                  = THIS_MODULE,
         .init_flags             = xfrm4_init_flags,
         .init_tempsel           = __xfrm4_init_tempsel,
+        .init_temprop           = xfrm4_init_temprop,
         .output                 = xfrm4_output,
         .extract_input          = xfrm4_extract_input,
         .extract_output         = xfrm4_extract_output,