9 files changed, 88 insertions, 54 deletions

diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index c6b5092f29a..65f01dc4756 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1490,7 +1490,9 @@ static int devinet_conf_proc(ctl_table *ctl, int write,
                              void __user *buffer,
                              size_t *lenp, loff_t *ppos)
 {
+        int old_value = *(int *)ctl->data;
         int ret = proc_dointvec(ctl, write, buffer, lenp, ppos);
+        int new_value = *(int *)ctl->data;
 
         if (write) {
                 struct ipv4_devconf *cnf = ctl->extra1;
@@ -1501,6 +1503,9 @@ static int devinet_conf_proc(ctl_table *ctl, int write,
 
                 if (cnf == net->ipv4.devconf_dflt)
                         devinet_copy_dflt_conf(net, i);
+                if (i == IPV4_DEVCONF_ACCEPT_LOCAL - 1)
+                        if ((new_value == 0) && (old_value != 0))
+                                rt_cache_flush(net, 0);
         }
 
         return ret;
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index c7472eff2d5..b2ca095cb9d 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -1716,7 +1716,8 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode,
         if (err) {
                 int j;
 
-                pmc->sfcount[sfmode]--;
+                if (!delta)
+                        pmc->sfcount[sfmode]--;
                 for (j=0; j<i; j++)
                         (void) ip_mc_del1_src(pmc, sfmode, &psfsrc[j]);
         } else if (isexclude != (pmc->sfcount[MCAST_EXCLUDE] != 0)) {
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 68e8ac51438..ccee270a9b6 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -108,9 +108,6 @@ static int inet_csk_diag_fill(struct sock *sk,
                        icsk->icsk_ca_ops->name);
         }
 
-        if ((ext & (1 << (INET_DIAG_TOS - 1))) && (sk->sk_family != AF_INET6))
-                RTA_PUT_U8(skb, INET_DIAG_TOS, inet->tos);
-
         r->idiag_family = sk->sk_family;
         r->idiag_state = sk->sk_state;
         r->idiag_timer = 0;
@@ -125,16 +122,23 @@ static int inet_csk_diag_fill(struct sock *sk,
         r->id.idiag_src[0] = inet->inet_rcv_saddr;
         r->id.idiag_dst[0] = inet->inet_daddr;
 
+        /* IPv6 dual-stack sockets use inet->tos for IPv4 connections,
+         * hence this needs to be included regardless of socket family.
+         */
+        if (ext & (1 << (INET_DIAG_TOS - 1)))
+                RTA_PUT_U8(skb, INET_DIAG_TOS, inet->tos);
+
 #if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
         if (r->idiag_family == AF_INET6) {
                 const struct ipv6_pinfo *np = inet6_sk(sk);
 
+                if (ext & (1 << (INET_DIAG_TCLASS - 1)))
+                        RTA_PUT_U8(skb, INET_DIAG_TCLASS, np->tclass);
+
                 ipv6_addr_copy((struct in6_addr *)r->id.idiag_src,
                                &np->rcv_saddr);
                 ipv6_addr_copy((struct in6_addr *)r->id.idiag_dst,
                                &np->daddr);
-                if (ext & (1 << (INET_DIAG_TCLASS - 1)))
-                        RTA_PUT_U8(skb, INET_DIAG_TCLASS, np->tclass);
         }
 #endif
 
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 3b34d1c8627..29a07b6c716 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -84,7 +84,7 @@ int ip_forward(struct sk_buff *skb)
 
         rt = skb_rtable(skb);
 
-        if (opt->is_strictroute && ip_hdr(skb)->daddr != rt->rt_gateway)
+        if (opt->is_strictroute && opt->nexthop != rt->rt_gateway)
                 goto sr_failed;
 
         if (unlikely(skb->len > dst_mtu(&rt->dst) && !skb_is_gso(skb) &&
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index 05d20cca9d6..1e60f767907 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -568,12 +568,13 @@ void ip_forward_options(struct sk_buff *skb)
                      ) {
                         if (srrptr + 3 > srrspace)
                                 break;
-                        if (memcmp(&ip_hdr(skb)->daddr, &optptr[srrptr-1], 4) == 0)
+                        if (memcmp(&opt->nexthop, &optptr[srrptr-1], 4) == 0)
                                 break;
                 }
                 if (srrptr + 3 <= srrspace) {
                         opt->is_changed = 1;
                         ip_rt_get_source(&optptr[srrptr-1], skb, rt);
+                        ip_hdr(skb)->daddr = opt->nexthop;
                         optptr[2] = srrptr+4;
                 } else if (net_ratelimit())
                         printk(KERN_CRIT "ip_forward(): Argh! Destination lost!\n");
@@ -640,7 +641,7 @@ int ip_options_rcv_srr(struct sk_buff *skb)
         }
         if (srrptr <= srrspace) {
                 opt->srr_is_hit = 1;
-                iph->daddr = nexthop;
+                opt->nexthop = nexthop;
                 opt->is_changed = 1;
         }
         return 0;
diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c
index 9899619ab9b..4f47e064e26 100644
--- a/net/ipv4/netfilter.c
+++ b/net/ipv4/netfilter.c
@@ -64,7 +64,8 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type)
         /* Change in oif may mean change in hh_len. */
         hh_len = skb_dst(skb)->dev->hard_header_len;
         if (skb_headroom(skb) < hh_len &&
-            pskb_expand_head(skb, hh_len - skb_headroom(skb), 0, GFP_ATOMIC))
+            pskb_expand_head(skb, HH_DATA_ALIGN(hh_len - skb_headroom(skb)),
+                                0, GFP_ATOMIC))
                 return -1;
 
         return 0;
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index 1dfc18a03fd..f19f2182894 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -325,7 +325,6 @@ config IP_NF_TARGET_TTL
 # raw + specific targets
 config IP_NF_RAW
         tristate  'raw table support (required for NOTRACK/TRACE)'
-        depends on NETFILTER_ADVANCED
         help
           This option adds a `raw' table to iptables. This table is the very
           first in the netfilter framework and hooks in at the PREROUTING
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 0c74da8a047..46af62363b8 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -112,7 +112,7 @@
 #include <net/secure_seq.h>
 
 #define RT_FL_TOS(oldflp4) \
-    ((u32)(oldflp4->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK)))
+        ((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK))
 
 #define IP_MAX_MTU      0xFFF0
 
@@ -131,6 +131,7 @@ static int ip_rt_mtu_expires __read_mostly	= 10 * 60 * HZ;
 static int ip_rt_min_pmtu __read_mostly         = 512 + 20 + 20;
 static int ip_rt_min_advmss __read_mostly       = 256;
 static int rt_chain_length_max __read_mostly    = 20;
+static int redirect_genid;
 
 /*
  *      Interface to generic destination cache.
@@ -138,7 +139,7 @@ static int rt_chain_length_max __read_mostly	= 20;
 
 static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie);
 static unsigned int      ipv4_default_advmss(const struct dst_entry *dst);
-static unsigned int      ipv4_default_mtu(const struct dst_entry *dst);
+static unsigned int      ipv4_mtu(const struct dst_entry *dst);
 static void              ipv4_dst_destroy(struct dst_entry *dst);
 static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst);
 static void              ipv4_link_failure(struct sk_buff *skb);
@@ -193,7 +194,7 @@ static struct dst_ops ipv4_dst_ops = {
         .gc =                   rt_garbage_collect,
         .check =                ipv4_dst_check,
         .default_advmss =       ipv4_default_advmss,
-        .default_mtu =          ipv4_default_mtu,
+        .mtu =                  ipv4_mtu,
         .cow_metrics =          ipv4_cow_metrics,
         .destroy =              ipv4_dst_destroy,
         .ifdown =               ipv4_dst_ifdown,
@@ -416,9 +417,13 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v)
         else {
                 struct rtable *r = v;
                 struct neighbour *n;
-                int len;
+                int len, HHUptod;
 
+                rcu_read_lock();
                 n = dst_get_neighbour(&r->dst);
+                HHUptod = (n && (n->nud_state & NUD_CONNECTED)) ? 1 : 0;
+                rcu_read_unlock();
+
                 seq_printf(seq, "%s\t%08X\t%08X\t%8X\t%d\t%u\t%d\t"
                               "%08X\t%d\t%u\t%u\t%02X\t%d\t%1d\t%08X%n",
                         r->dst.dev ? r->dst.dev->name : "*",
@@ -432,7 +437,7 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v)
                               dst_metric(&r->dst, RTAX_RTTVAR)),
                         r->rt_key_tos,
                         -1,
-                        (n && (n->nud_state & NUD_CONNECTED)) ? 1 : 0,
+                        HHUptod,
                         r->rt_spec_dst, &len);
 
                 seq_printf(seq, "%*s\n", 127 - len, "");
@@ -837,6 +842,7 @@ static void rt_cache_invalidate(struct net *net)
 
         get_random_bytes(&shuffle, sizeof(shuffle));
         atomic_add(shuffle + 1U, &net->ipv4.rt_genid);
+        redirect_genid++;
 }
 
 /*
@@ -1304,7 +1310,7 @@ static void rt_del(unsigned hash, struct rtable *rt)
         spin_unlock_bh(rt_hash_lock_addr(hash));
 }
 
-static int check_peer_redir(struct dst_entry *dst, struct inet_peer *peer)
+static void check_peer_redir(struct dst_entry *dst, struct inet_peer *peer)
 {
         struct rtable *rt = (struct rtable *) dst;
         __be32 orig_gw = rt->rt_gateway;
@@ -1315,21 +1321,19 @@ static int check_peer_redir(struct dst_entry *dst, struct inet_peer *peer)
         rt->rt_gateway = peer->redirect_learned.a4;
 
         n = ipv4_neigh_lookup(&rt->dst, &rt->rt_gateway);
-        if (IS_ERR(n))
-                return PTR_ERR(n);
+        if (IS_ERR(n)) {
+                rt->rt_gateway = orig_gw;
+                return;
+        }
         old_n = xchg(&rt->dst._neighbour, n);
         if (old_n)
                 neigh_release(old_n);
-        if (!n || !(n->nud_state & NUD_VALID)) {
-                if (n)
-                        neigh_event_send(n, NULL);
-                rt->rt_gateway = orig_gw;
-                return -EAGAIN;
+        if (!(n->nud_state & NUD_VALID)) {
+                neigh_event_send(n, NULL);
         } else {
                 rt->rt_flags |= RTCF_REDIRECTED;
                 call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n);
         }
-        return 0;
 }
 
 /* called in rcu_read_lock() section */
@@ -1391,8 +1395,10 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
 
                                 peer = rt->peer;
                                 if (peer) {
-                                        if (peer->redirect_learned.a4 != new_gw) {
+                                        if (peer->redirect_learned.a4 != new_gw ||
+                                            peer->redirect_genid != redirect_genid) {
                                                 peer->redirect_learned.a4 = new_gw;
+                                                peer->redirect_genid = redirect_genid;
                                                 atomic_inc(&__rt_peer_genid);
                                         }
                                         check_peer_redir(&rt->dst, peer);
@@ -1685,12 +1691,8 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu)
 }
 
 
-static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
+static void ipv4_validate_peer(struct rtable *rt)
 {
-        struct rtable *rt = (struct rtable *) dst;
-
-        if (rt_is_expired(rt))
-                return NULL;
         if (rt->rt_peer_genid != rt_peer_genid()) {
                 struct inet_peer *peer;
 
@@ -1699,17 +1701,26 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
 
                 peer = rt->peer;
                 if (peer) {
-                        check_peer_pmtu(dst, peer);
+                        check_peer_pmtu(&rt->dst, peer);
 
+                        if (peer->redirect_genid != redirect_genid)
+                                peer->redirect_learned.a4 = 0;
                         if (peer->redirect_learned.a4 &&
-                            peer->redirect_learned.a4 != rt->rt_gateway) {
-                                if (check_peer_redir(dst, peer))
-                                        return NULL;
-                        }
+                            peer->redirect_learned.a4 != rt->rt_gateway)
+                                check_peer_redir(&rt->dst, peer);
                 }
 
                 rt->rt_peer_genid = rt_peer_genid();
         }
+}
+
+static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
+{
+        struct rtable *rt = (struct rtable *) dst;
+
+        if (rt_is_expired(rt))
+                return NULL;
+        ipv4_validate_peer(rt);
         return dst;
 }
 
@@ -1814,12 +1825,17 @@ static unsigned int ipv4_default_advmss(const struct dst_entry *dst)
         return advmss;
 }
 
-static unsigned int ipv4_default_mtu(const struct dst_entry *dst)
+static unsigned int ipv4_mtu(const struct dst_entry *dst)
 {
-        unsigned int mtu = dst->dev->mtu;
+        const struct rtable *rt = (const struct rtable *) dst;
+        unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
+
+        if (mtu && rt_is_output_route(rt))
+                return mtu;
+
+        mtu = dst->dev->mtu;
 
         if (unlikely(dst_metric_locked(dst, RTAX_MTU))) {
-                const struct rtable *rt = (const struct rtable *) dst;
 
                 if (rt->rt_gateway != rt->rt_dst && mtu > 576)
                         mtu = 576;
@@ -1852,6 +1868,8 @@ static void rt_init_metrics(struct rtable *rt, const struct flowi4 *fl4,
                 dst_init_metrics(&rt->dst, peer->metrics, false);
 
                 check_peer_pmtu(&rt->dst, peer);
+                if (peer->redirect_genid != redirect_genid)
+                        peer->redirect_learned.a4 = 0;
                 if (peer->redirect_learned.a4 &&
                     peer->redirect_learned.a4 != rt->rt_gateway) {
                         rt->rt_gateway = peer->redirect_learned.a4;
@@ -2357,6 +2375,7 @@ int ip_route_input_common(struct sk_buff *skb, __be32 daddr, __be32 saddr,
                     rth->rt_mark == skb->mark &&
                     net_eq(dev_net(rth->dst.dev), net) &&
                     !rt_is_expired(rth)) {
+                        ipv4_validate_peer(rth);
                         if (noref) {
                                 dst_use_noref(&rth->dst, jiffies);
                                 skb_dst_set_noref(skb, &rth->dst);
@@ -2415,11 +2434,11 @@ EXPORT_SYMBOL(ip_route_input_common);
 static struct rtable *__mkroute_output(const struct fib_result *res,
                                        const struct flowi4 *fl4,
                                        __be32 orig_daddr, __be32 orig_saddr,
-                                       int orig_oif, struct net_device *dev_out,
+                                       int orig_oif, __u8 orig_rtos,
+                                       struct net_device *dev_out,
                                        unsigned int flags)
 {
         struct fib_info *fi = res->fi;
-        u32 tos = RT_FL_TOS(fl4);
         struct in_device *in_dev;
         u16 type = res->type;
         struct rtable *rth;
@@ -2470,7 +2489,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
         rth->rt_genid = rt_genid(dev_net(dev_out));
         rth->rt_flags   = flags;
         rth->rt_type    = type;
-        rth->rt_key_tos = tos;
+        rth->rt_key_tos = orig_rtos;
         rth->rt_dst     = fl4->daddr;
         rth->rt_src     = fl4->saddr;
         rth->rt_route_iif = 0;
@@ -2520,7 +2539,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 static struct rtable *ip_route_output_slow(struct net *net, struct flowi4 *fl4)
 {
         struct net_device *dev_out = NULL;
-        u32 tos = RT_FL_TOS(fl4);
+        __u8 tos = RT_FL_TOS(fl4);
         unsigned int flags = 0;
         struct fib_result res;
         struct rtable *rth;
@@ -2696,7 +2715,7 @@ static struct rtable *ip_route_output_slow(struct net *net, struct flowi4 *fl4)
 
 make_route:
         rth = __mkroute_output(&res, fl4, orig_daddr, orig_saddr, orig_oif,
-                               dev_out, flags);
+                               tos, dev_out, flags);
         if (!IS_ERR(rth)) {
                 unsigned int hash;
 
@@ -2732,6 +2751,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *flp4)
                             (IPTOS_RT_MASK | RTO_ONLINK)) &&
                     net_eq(dev_net(rth->dst.dev), net) &&
                     !rt_is_expired(rth)) {
+                        ipv4_validate_peer(rth);
                         dst_use(&rth->dst, jiffies);
                         RT_CACHE_STAT_INC(out_hit);
                         rcu_read_unlock_bh();
@@ -2755,9 +2775,11 @@ static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 coo
         return NULL;
 }
 
-static unsigned int ipv4_blackhole_default_mtu(const struct dst_entry *dst)
+static unsigned int ipv4_blackhole_mtu(const struct dst_entry *dst)
 {
-        return 0;
+        unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
+
+        return mtu ? : dst->dev->mtu;
 }
 
 static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu)
@@ -2775,7 +2797,7 @@ static struct dst_ops ipv4_dst_blackhole_ops = {
         .protocol               =       cpu_to_be16(ETH_P_IP),
         .destroy                =       ipv4_dst_destroy,
         .check                  =       ipv4_blackhole_dst_check,
-        .default_mtu            =       ipv4_blackhole_default_mtu,
+        .mtu                    =       ipv4_blackhole_mtu,
         .default_advmss         =       ipv4_default_advmss,
         .update_pmtu            =       ipv4_rt_blackhole_update_pmtu,
         .cow_metrics            =       ipv4_rt_blackhole_cow_metrics,
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index ab0966df1e2..5a65eeac1d2 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1164,7 +1164,7 @@ int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
         struct inet_sock *inet = inet_sk(sk);
         struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name;
         struct sk_buff *skb;
-        unsigned int ulen;
+        unsigned int ulen, copied;
         int peeked;
         int err;
         int is_udplite = IS_UDPLITE(sk);
@@ -1186,9 +1186,10 @@ try_again:
                 goto out;
 
         ulen = skb->len - sizeof(struct udphdr);
-        if (len > ulen)
-                len = ulen;
-        else if (len < ulen)
+        copied = len;
+        if (copied > ulen)
+                copied = ulen;
+        else if (copied < ulen)
                 msg->msg_flags |= MSG_TRUNC;
 
         /*
@@ -1197,14 +1198,14 @@ try_again:
          * coverage checksum (UDP-Lite), do it before the copy.
          */
 
-        if (len < ulen || UDP_SKB_CB(skb)->partial_cov) {
+        if (copied < ulen || UDP_SKB_CB(skb)->partial_cov) {
                 if (udp_lib_checksum_complete(skb))
                         goto csum_copy_err;
         }
 
         if (skb_csum_unnecessary(skb))
                 err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr),
-                                              msg->msg_iov, len);
+                                              msg->msg_iov, copied);
         else {
                 err = skb_copy_and_csum_datagram_iovec(skb,
                                                        sizeof(struct udphdr),
@@ -1233,7 +1234,7 @@ try_again:
         if (inet->cmsg_flags)
                 ip_cmsg_recv(msg, skb);
 
-        err = len;
+        err = copied;
         if (flags & MSG_TRUNC)
                 err = ulen;