Merge tag 'v3.13-rc4' into core/locking

Merge Linux 3.13-rc4, to refresh this rather old tree with the latest fixes.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

12 files changed, 69 insertions, 65 deletions

diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index 523be38e37de..f2e15738534d 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -104,7 +104,10 @@ errout:
 static bool fib4_rule_suppress(struct fib_rule *rule, struct fib_lookup_arg *arg)
 {
         struct fib_result *result = (struct fib_result *) arg->result;
-        struct net_device *dev = result->fi->fib_dev;
+        struct net_device *dev = NULL;
+
+        if (result->fi)
+                dev = result->fi->fib_dev;
 
         /* do not accept result if the route does
          * not meet the required prefix length
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 3f858266fa7e..ddf32a6bc415 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -386,7 +386,7 @@ void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 port, u32 inf
 /*
  *      Handle MSG_ERRQUEUE
  */
-int ip_recv_error(struct sock *sk, struct msghdr *msg, int len)
+int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 {
         struct sock_exterr_skb *serr;
         struct sk_buff *skb, *skb2;
@@ -423,6 +423,7 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len)
                                                    serr->addr_offset);
                 sin->sin_port = serr->port;
                 memset(&sin->sin_zero, 0, sizeof(sin->sin_zero));
+                *addr_len = sizeof(*sin);
         }
 
         memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err));
diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c
index 01cffeaa0085..f13bd91d9a56 100644
--- a/net/ipv4/netfilter/ipt_SYNPROXY.c
+++ b/net/ipv4/netfilter/ipt_SYNPROXY.c
@@ -244,6 +244,7 @@ synproxy_recv_client_ack(const struct synproxy_net *snet,
 
         this_cpu_inc(snet->stats->cookie_valid);
         opts->mss = mss;
+        opts->options |= XT_SYNPROXY_OPT_MSS;
 
         if (opts->options & XT_SYNPROXY_OPT_TIMESTAMP)
                 synproxy_check_timestamp_cookie(opts);
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 876c6ca2d8f9..242e7f4ed6f4 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -772,7 +772,7 @@ int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
                 err = PTR_ERR(rt);
                 rt = NULL;
                 if (err == -ENETUNREACH)
-                        IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES);
+                        IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
                 goto out;
         }
 
@@ -841,10 +841,11 @@ int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 
         if (flags & MSG_ERRQUEUE) {
                 if (family == AF_INET) {
-                        return ip_recv_error(sk, msg, len);
+                        return ip_recv_error(sk, msg, len, addr_len);
 #if IS_ENABLED(CONFIG_IPV6)
                 } else if (family == AF_INET6) {
-                        return pingv6_ops.ipv6_recv_error(sk, msg, len);
+                        return pingv6_ops.ipv6_recv_error(sk, msg, len,
+                                                          addr_len);
 #endif
                 }
         }
diff --git a/net/ipv4/protocol.c b/net/ipv4/protocol.c
index ce848461acbb..46d6a1c923a8 100644
--- a/net/ipv4/protocol.c
+++ b/net/ipv4/protocol.c
@@ -31,10 +31,6 @@
 const struct net_protocol __rcu *inet_protos[MAX_INET_PROTOS] __read_mostly;
 const struct net_offload __rcu *inet_offloads[MAX_INET_PROTOS] __read_mostly;
 
-/*
- *      Add a protocol handler to the hash tables
- */
-
 int inet_add_protocol(const struct net_protocol *prot, unsigned char protocol)
 {
         if (!prot->netns_ok) {
@@ -55,10 +51,6 @@ int inet_add_offload(const struct net_offload *prot, unsigned char protocol)
 }
 EXPORT_SYMBOL(inet_add_offload);
 
-/*
- *      Remove a protocol from the hash tables.
- */
-
 int inet_del_protocol(const struct net_protocol *prot, unsigned char protocol)
 {
         int ret;
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 5cb8ddb505ee..23c3e5b5bb53 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -697,7 +697,7 @@ static int raw_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
                 goto out;
 
         if (flags & MSG_ERRQUEUE) {
-                err = ip_recv_error(sk, msg, len);
+                err = ip_recv_error(sk, msg, len, addr_len);
                 goto out;
         }
 
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index f428935c50db..f8da28278014 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1776,8 +1776,12 @@ local_input:
                 rth->dst.error= -err;
                 rth->rt_flags   &= ~RTCF_LOCAL;
         }
-        if (do_cache)
-                rt_cache_route(&FIB_RES_NH(res), rth);
+        if (do_cache) {
+                if (unlikely(!rt_cache_route(&FIB_RES_NH(res), rth))) {
+                        rth->dst.flags |= DST_NOCACHE;
+                        rt_add_uncached_list(rth);
+                }
+        }
         skb_dst_set(skb, &rth->dst);
         err = 0;
         goto out;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 3dc0c6cf02a8..c4638e6f0238 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1425,7 +1425,7 @@ static void tcp_service_net_dma(struct sock *sk, bool wait)
         do {
                 if (dma_async_is_tx_complete(tp->ucopy.dma_chan,
                                               last_issued, &done,
-                                              &used) == DMA_SUCCESS) {
+                                              &used) == DMA_COMPLETE) {
                         /* Safe to free early-copied skbs now */
                         __skb_queue_purge(&sk->sk_async_wait_queue);
                         break;
@@ -1433,7 +1433,7 @@ static void tcp_service_net_dma(struct sock *sk, bool wait)
                         struct sk_buff *skb;
                         while ((skb = skb_peek(&sk->sk_async_wait_queue)) &&
                                (dma_async_is_complete(skb->dma_cookie, done,
-                                                      used) == DMA_SUCCESS)) {
+                                                      used) == DMA_COMPLETE)) {
                                 __skb_dequeue(&sk->sk_async_wait_queue);
                                 kfree_skb(skb);
                         }
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 59a6f8b90cd9..067213924751 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -177,7 +177,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
         if (IS_ERR(rt)) {
                 err = PTR_ERR(rt);
                 if (err == -ENETUNREACH)
-                        IP_INC_STATS_BH(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
+                        IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
                 return err;
         }
 
diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c
index 03e9154f7e68..f7e522c558ba 100644
--- a/net/ipv4/tcp_memcontrol.c
+++ b/net/ipv4/tcp_memcontrol.c
@@ -6,13 +6,6 @@
 #include <linux/memcontrol.h>
 #include <linux/module.h>
 
-static void memcg_tcp_enter_memory_pressure(struct sock *sk)
-{
-        if (sk->sk_cgrp->memory_pressure)
-                sk->sk_cgrp->memory_pressure = 1;
-}
-EXPORT_SYMBOL(memcg_tcp_enter_memory_pressure);
-
 int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 {
         /*
@@ -60,7 +53,6 @@ EXPORT_SYMBOL(tcp_destroy_cgroup);
 static int tcp_update_limit(struct mem_cgroup *memcg, u64 val)
 {
         struct cg_proto *cg_proto;
-        u64 old_lim;
         int i;
         int ret;
 
@@ -71,7 +63,6 @@ static int tcp_update_limit(struct mem_cgroup *memcg, u64 val)
         if (val > RES_COUNTER_MAX)
                 val = RES_COUNTER_MAX;
 
-        old_lim = res_counter_read_u64(&cg_proto->memory_allocated, RES_LIMIT);
         ret = res_counter_set_limit(&cg_proto->memory_allocated, val);
         if (ret)
                 return ret;
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index a2b68a108eae..05606353c7e7 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -274,33 +274,32 @@ static struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *
 {
         const struct iphdr *iph = skb_gro_network_header(skb);
         __wsum wsum;
-        __sum16 sum;
+
+        /* Don't bother verifying checksum if we're going to flush anyway. */
+        if (NAPI_GRO_CB(skb)->flush)
+                goto skip_csum;
+
+        wsum = skb->csum;
 
         switch (skb->ip_summed) {
+        case CHECKSUM_NONE:
+                wsum = skb_checksum(skb, skb_gro_offset(skb), skb_gro_len(skb),
+                                    0);
+
+                /* fall through */
+
         case CHECKSUM_COMPLETE:
                 if (!tcp_v4_check(skb_gro_len(skb), iph->saddr, iph->daddr,
-                                  skb->csum)) {
+                                  wsum)) {
                         skb->ip_summed = CHECKSUM_UNNECESSARY;
                         break;
                 }
-flush:
+
                 NAPI_GRO_CB(skb)->flush = 1;
                 return NULL;
-
-        case CHECKSUM_NONE:
-                wsum = csum_tcpudp_nofold(iph->saddr, iph->daddr,
-                                          skb_gro_len(skb), IPPROTO_TCP, 0);
-                sum = csum_fold(skb_checksum(skb,
-                                             skb_gro_offset(skb),
-                                             skb_gro_len(skb),
-                                             wsum));
-                if (sum)
-                        goto flush;
-
-                skb->ip_summed = CHECKSUM_UNNECESSARY;
-                break;
         }
 
+skip_csum:
         return tcp_gro_receive(head, skb);
 }
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 5944d7d668dd..62c19fdd102d 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -560,15 +560,11 @@ static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb,
                                                  __be16 sport, __be16 dport,
                                                  struct udp_table *udptable)
 {
-        struct sock *sk;
         const struct iphdr *iph = ip_hdr(skb);
 
-        if (unlikely(sk = skb_steal_sock(skb)))
-                return sk;
-        else
-                return __udp4_lib_lookup(dev_net(skb_dst(skb)->dev), iph->saddr, sport,
-                                         iph->daddr, dport, inet_iif(skb),
-                                         udptable);
+        return __udp4_lib_lookup(dev_net(skb_dst(skb)->dev), iph->saddr, sport,
+                                 iph->daddr, dport, inet_iif(skb),
+                                 udptable);
 }
 
 struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
@@ -999,7 +995,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
                         err = PTR_ERR(rt);
                         rt = NULL;
                         if (err == -ENETUNREACH)
-                                IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES);
+                                IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
                         goto out;
                 }
 
@@ -1098,6 +1094,9 @@ int udp_sendpage(struct sock *sk, struct page *page, int offset,
         struct udp_sock *up = udp_sk(sk);
         int ret;
 
+        if (flags & MSG_SENDPAGE_NOTLAST)
+                flags |= MSG_MORE;
+
         if (!up->pending) {
                 struct msghdr msg = {   .msg_flags = flags|MSG_MORE };
 
@@ -1236,7 +1235,7 @@ int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
         bool slow;
 
         if (flags & MSG_ERRQUEUE)
-                return ip_recv_error(sk, msg, len);
+                return ip_recv_error(sk, msg, len, addr_len);
 
 try_again:
         skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0),
@@ -1600,12 +1599,21 @@ static void flush_stack(struct sock **stack, unsigned int count,
                 kfree_skb(skb1);
 }
 
-static void udp_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
+/* For TCP sockets, sk_rx_dst is protected by socket lock
+ * For UDP, we use sk_dst_lock to guard against concurrent changes.
+ */
+static void udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst)
 {
-        struct dst_entry *dst = skb_dst(skb);
+        struct dst_entry *old;
 
-        dst_hold(dst);
-        sk->sk_rx_dst = dst;
+        spin_lock(&sk->sk_dst_lock);
+        old = sk->sk_rx_dst;
+        if (likely(old != dst)) {
+                dst_hold(dst);
+                sk->sk_rx_dst = dst;
+                dst_release(old);
+        }
+        spin_unlock(&sk->sk_dst_lock);
 }
 
 /*
@@ -1736,15 +1744,16 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
         if (udp4_csum_init(skb, uh, proto))
                 goto csum_error;
 
-        if (skb->sk) {
+        sk = skb_steal_sock(skb);
+        if (sk) {
+                struct dst_entry *dst = skb_dst(skb);
                 int ret;
-                sk = skb->sk;
 
-                if (unlikely(sk->sk_rx_dst == NULL))
-                        udp_sk_rx_dst_set(sk, skb);
+                if (unlikely(sk->sk_rx_dst != dst))
+                        udp_sk_rx_dst_set(sk, dst);
 
                 ret = udp_queue_rcv_skb(sk, skb);
-
+                sock_put(sk);
                 /* a return value > 0 means to resubmit the input, but
                  * it wants the return to be -protocol, or 0
                  */
@@ -1910,17 +1919,20 @@ static struct sock *__udp4_lib_demux_lookup(struct net *net,
 
 void udp_v4_early_demux(struct sk_buff *skb)
 {
-        const struct iphdr *iph = ip_hdr(skb);
-        const struct udphdr *uh = udp_hdr(skb);
+        struct net *net = dev_net(skb->dev);
+        const struct iphdr *iph;
+        const struct udphdr *uh;
         struct sock *sk;
         struct dst_entry *dst;
-        struct net *net = dev_net(skb->dev);
         int dif = skb->dev->ifindex;
 
         /* validate the packet */
         if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct udphdr)))
                 return;
 
+        iph = ip_hdr(skb);
+        uh = udp_hdr(skb);
+
         if (skb->pkt_type == PACKET_BROADCAST ||
             skb->pkt_type == PACKET_MULTICAST)
                 sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr,