14 files changed, 65 insertions, 60 deletions

diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h
index a29edf2219c8..c079cc0ec651 100644
--- a/net/ipv4/fib_lookup.h
+++ b/net/ipv4/fib_lookup.h
@@ -47,11 +47,8 @@ extern int fib_detect_death(struct fib_info *fi, int order,
 static inline void fib_result_assign(struct fib_result *res,
                                      struct fib_info *fi)
 {
-        if (res->fi != NULL)
-                fib_info_put(res->fi);
+        /* we used to play games with refcounts, but we now use RCU */
         res->fi = fi;
-        if (fi != NULL)
-                atomic_inc(&fi->fib_clntref);
 }
 
 #endif /* _FIB_LOOKUP_H */
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 200eb538fbb3..0f280348e0fd 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -365,7 +365,7 @@ static struct tnode *tnode_alloc(size_t size)
         if (size <= PAGE_SIZE)
                 return kzalloc(size, GFP_KERNEL);
         else
-                return __vmalloc(size, GFP_KERNEL | __GFP_ZERO, PAGE_KERNEL);
+                return vzalloc(size);
 }
 
 static void __tnode_vfree(struct work_struct *arg)
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 96bc7f9475a3..e5d1a44bcbdf 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -569,6 +569,9 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
                 /* No need to clone since we're just using its address. */
                 rt2 = rt;
 
+                if (!fl.nl_u.ip4_u.saddr)
+                        fl.nl_u.ip4_u.saddr = rt->rt_src;
+
                 err = xfrm_lookup(net, (struct dst_entry **)&rt, &fl, NULL, 0);
                 switch (err) {
                 case 0:
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index c8877c6c7216..3c53c2d89e3b 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -2306,10 +2306,8 @@ void ip_mc_drop_socket(struct sock *sk)
 
                 in_dev = inetdev_by_index(net, iml->multi.imr_ifindex);
                 (void) ip_mc_leave_src(sk, iml, in_dev);
-                if (in_dev != NULL) {
+                if (in_dev != NULL)
                         ip_mc_dec_group(in_dev, iml->multi.imr_multiaddr.s_addr);
-                        in_dev_put(in_dev);
-                }
                 /* decrease mem now to avoid the memleak warning */
                 atomic_sub(sizeof(*iml), &sk->sk_omem_alloc);
                 call_rcu(&iml->rcu, ip_mc_socklist_reclaim);
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index ba8042665849..2ada17129fce 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -490,9 +490,11 @@ static int inet_csk_diag_dump(struct sock *sk,
 {
         struct inet_diag_req *r = NLMSG_DATA(cb->nlh);
 
-        if (cb->nlh->nlmsg_len > 4 + NLMSG_SPACE(sizeof(*r))) {
+        if (nlmsg_attrlen(cb->nlh, sizeof(*r))) {
                 struct inet_diag_entry entry;
-                struct rtattr *bc = (struct rtattr *)(r + 1);
+                const struct nlattr *bc = nlmsg_find_attr(cb->nlh,
+                                                          sizeof(*r),
+                                                          INET_DIAG_REQ_BYTECODE);
                 struct inet_sock *inet = inet_sk(sk);
 
                 entry.family = sk->sk_family;
@@ -512,7 +514,7 @@ static int inet_csk_diag_dump(struct sock *sk,
                 entry.dport = ntohs(inet->inet_dport);
                 entry.userlocks = sk->sk_userlocks;
 
-                if (!inet_diag_bc_run(RTA_DATA(bc), RTA_PAYLOAD(bc), &entry))
+                if (!inet_diag_bc_run(nla_data(bc), nla_len(bc), &entry))
                         return 0;
         }
 
@@ -527,9 +529,11 @@ static int inet_twsk_diag_dump(struct inet_timewait_sock *tw,
 {
         struct inet_diag_req *r = NLMSG_DATA(cb->nlh);
 
-        if (cb->nlh->nlmsg_len > 4 + NLMSG_SPACE(sizeof(*r))) {
+        if (nlmsg_attrlen(cb->nlh, sizeof(*r))) {
                 struct inet_diag_entry entry;
-                struct rtattr *bc = (struct rtattr *)(r + 1);
+                const struct nlattr *bc = nlmsg_find_attr(cb->nlh,
+                                                          sizeof(*r),
+                                                          INET_DIAG_REQ_BYTECODE);
 
                 entry.family = tw->tw_family;
 #if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
@@ -548,7 +552,7 @@ static int inet_twsk_diag_dump(struct inet_timewait_sock *tw,
                 entry.dport = ntohs(tw->tw_dport);
                 entry.userlocks = 0;
 
-                if (!inet_diag_bc_run(RTA_DATA(bc), RTA_PAYLOAD(bc), &entry))
+                if (!inet_diag_bc_run(nla_data(bc), nla_len(bc), &entry))
                         return 0;
         }
 
@@ -618,7 +622,7 @@ static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk,
         struct inet_diag_req *r = NLMSG_DATA(cb->nlh);
         struct inet_connection_sock *icsk = inet_csk(sk);
         struct listen_sock *lopt;
-        struct rtattr *bc = NULL;
+        const struct nlattr *bc = NULL;
         struct inet_sock *inet = inet_sk(sk);
         int j, s_j;
         int reqnum, s_reqnum;
@@ -638,8 +642,9 @@ static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk,
         if (!lopt || !lopt->qlen)
                 goto out;
 
-        if (cb->nlh->nlmsg_len > 4 + NLMSG_SPACE(sizeof(*r))) {
-                bc = (struct rtattr *)(r + 1);
+        if (nlmsg_attrlen(cb->nlh, sizeof(*r))) {
+                bc = nlmsg_find_attr(cb->nlh, sizeof(*r),
+                                     INET_DIAG_REQ_BYTECODE);
                 entry.sport = inet->inet_num;
                 entry.userlocks = sk->sk_userlocks;
         }
@@ -672,8 +677,8 @@ static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk,
                                         &ireq->rmt_addr;
                                 entry.dport = ntohs(ireq->rmt_port);
 
-                                if (!inet_diag_bc_run(RTA_DATA(bc),
-                                                    RTA_PAYLOAD(bc), &entry))
+                                if (!inet_diag_bc_run(nla_data(bc),
+                                                      nla_len(bc), &entry))
                                         continue;
                         }
 
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 3cad2591ace0..3fac340a28d5 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -927,6 +927,7 @@ static int get_info(struct net *net, void __user *user,
                         private = &tmp;
                 }
 #endif
+                memset(&info, 0, sizeof(info));
                 info.valid_hooks = t->valid_hooks;
                 memcpy(info.hook_entry, private->hook_entry,
                        sizeof(info.hook_entry));
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index d31b007a6d80..a846d633b3b6 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -1124,6 +1124,7 @@ static int get_info(struct net *net, void __user *user,
                         private = &tmp;
                 }
 #endif
+                memset(&info, 0, sizeof(info));
                 info.valid_hooks = t->valid_hooks;
                 memcpy(info.hook_entry, private->hook_entry,
                        sizeof(info.hook_entry));
diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c
index 295c97431e43..c04787ce1a71 100644
--- a/net/ipv4/netfilter/nf_nat_core.c
+++ b/net/ipv4/netfilter/nf_nat_core.c
@@ -47,26 +47,6 @@ __nf_nat_proto_find(u_int8_t protonum)
         return rcu_dereference(nf_nat_protos[protonum]);
 }
 
-static const struct nf_nat_protocol *
-nf_nat_proto_find_get(u_int8_t protonum)
-{
-        const struct nf_nat_protocol *p;
-
-        rcu_read_lock();
-        p = __nf_nat_proto_find(protonum);
-        if (!try_module_get(p->me))
-                p = &nf_nat_unknown_protocol;
-        rcu_read_unlock();
-
-        return p;
-}
-
-static void
-nf_nat_proto_put(const struct nf_nat_protocol *p)
-{
-        module_put(p->me);
-}
-
 /* We keep an extra hash for each conntrack, for fast searching. */
 static inline unsigned int
 hash_by_src(const struct net *net, u16 zone,
@@ -588,6 +568,26 @@ static struct nf_ct_ext_type nat_extend __read_mostly = {
 #include <linux/netfilter/nfnetlink.h>
 #include <linux/netfilter/nfnetlink_conntrack.h>
 
+static const struct nf_nat_protocol *
+nf_nat_proto_find_get(u_int8_t protonum)
+{
+        const struct nf_nat_protocol *p;
+
+        rcu_read_lock();
+        p = __nf_nat_proto_find(protonum);
+        if (!try_module_get(p->me))
+                p = &nf_nat_unknown_protocol;
+        rcu_read_unlock();
+
+        return p;
+}
+
+static void
+nf_nat_proto_put(const struct nf_nat_protocol *p)
+{
+        module_put(p->me);
+}
+
 static const struct nla_policy protonat_nla_policy[CTA_PROTONAT_MAX+1] = {
         [CTA_PROTONAT_PORT_MIN] = { .type = NLA_U16 },
         [CTA_PROTONAT_PORT_MAX] = { .type = NLA_U16 },
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 4ae1f203f7cb..1b48eb1ed453 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -59,13 +59,13 @@ static int sockstat_seq_show(struct seq_file *seq, void *v)
         local_bh_enable();
 
         socket_seq_show(seq);
-        seq_printf(seq, "TCP: inuse %d orphan %d tw %d alloc %d mem %d\n",
+        seq_printf(seq, "TCP: inuse %d orphan %d tw %d alloc %d mem %ld\n",
                    sock_prot_inuse_get(net, &tcp_prot), orphans,
                    tcp_death_row.tw_count, sockets,
-                   atomic_read(&tcp_memory_allocated));
-        seq_printf(seq, "UDP: inuse %d mem %d\n",
+                   atomic_long_read(&tcp_memory_allocated));
+        seq_printf(seq, "UDP: inuse %d mem %ld\n",
                    sock_prot_inuse_get(net, &udp_prot),
-                   atomic_read(&udp_memory_allocated));
+                   atomic_long_read(&udp_memory_allocated));
         seq_printf(seq, "UDPLITE: inuse %d\n",
                    sock_prot_inuse_get(net, &udplite_prot));
         seq_printf(seq, "RAW: inuse %d\n",
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index d96c1da4b17c..e91911d7aae2 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -398,7 +398,7 @@ static struct ctl_table ipv4_table[] = {
                 .data           = &sysctl_tcp_mem,
                 .maxlen         = sizeof(sysctl_tcp_mem),
                 .mode           = 0644,
-                .proc_handler   = proc_dointvec
+                .proc_handler   = proc_doulongvec_minmax
         },
         {
                 .procname       = "tcp_wmem",
@@ -602,8 +602,7 @@ static struct ctl_table ipv4_table[] = {
                 .data           = &sysctl_udp_mem,
                 .maxlen         = sizeof(sysctl_udp_mem),
                 .mode           = 0644,
-                .proc_handler   = proc_dointvec_minmax,
-                .extra1         = &zero
+                .proc_handler   = proc_doulongvec_minmax,
         },
         {
                 .procname       = "udp_rmem_min",
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 1664a0590bb8..081419969485 100644
--- 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);
 
 /*
@@ -2246,7 +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 < 64 || val > MAX_TCP_WINDOW) {
                         err = -EINVAL;
                         break;
                 }
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 3357f69e353d..6d8ab1c4efc3 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -259,8 +259,11 @@ static void tcp_fixup_sndbuf(struct sock *sk)
         int sndmem = tcp_sk(sk)->rx_opt.mss_clamp + MAX_TCP_HEADER + 16 +
                      sizeof(struct sk_buff);
 
-        if (sk->sk_sndbuf < 3 * sndmem)
-                sk->sk_sndbuf = min(3 * sndmem, sysctl_tcp_wmem[2]);
+        if (sk->sk_sndbuf < 3 * sndmem) {
+                sk->sk_sndbuf = 3 * sndmem;
+                if (sk->sk_sndbuf > sysctl_tcp_wmem[2])
+                        sk->sk_sndbuf = sysctl_tcp_wmem[2];
+        }
 }
 
 /* 2. Tuning advertised window (window_clamp, rcv_ssthresh)
@@ -396,7 +399,7 @@ static void tcp_clamp_window(struct sock *sk)
         if (sk->sk_rcvbuf < sysctl_tcp_rmem[2] &&
             !(sk->sk_userlocks & SOCK_RCVBUF_LOCK) &&
             !tcp_memory_pressure &&
-            atomic_read(&tcp_memory_allocated) < sysctl_tcp_mem[0]) {
+            atomic_long_read(&tcp_memory_allocated) < sysctl_tcp_mem[0]) {
                 sk->sk_rcvbuf = min(atomic_read(&sk->sk_rmem_alloc),
                                     sysctl_tcp_rmem[2]);
         }
@@ -4861,7 +4864,7 @@ static int tcp_should_expand_sndbuf(struct sock *sk)
                 return 0;
 
         /* If we are under soft global TCP memory pressure, do not expand.  */
-        if (atomic_read(&tcp_memory_allocated) >= sysctl_tcp_mem[0])
+        if (atomic_long_read(&tcp_memory_allocated) >= sysctl_tcp_mem[0])
                 return 0;
 
         /* If we filled the congestion window, do not expand.  */
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 8f8527d41682..69ccbc1dde9c 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -415,6 +415,9 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
                     !icsk->icsk_backoff)
                         break;
 
+                if (sock_owned_by_user(sk))
+                        break;
+
                 icsk->icsk_backoff--;
                 inet_csk(sk)->icsk_rto = __tcp_set_rto(tp) <<
                                          icsk->icsk_backoff;
@@ -429,11 +432,6 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
                 if (remaining) {
                         inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
                                                   remaining, TCP_RTO_MAX);
-                } else if (sock_owned_by_user(sk)) {
-                        /* RTO revert clocked out retransmission,
-                         * but socket is locked. Will defer. */
-                        inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
-                                                  HZ/20, TCP_RTO_MAX);
                 } else {
                         /* RTO revert clocked out retransmission.
                          * Will retransmit now */
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 28cb2d733a3c..5e0a3a582a59 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -110,7 +110,7 @@
 struct udp_table udp_table __read_mostly;
 EXPORT_SYMBOL(udp_table);
 
-int sysctl_udp_mem[3] __read_mostly;
+long sysctl_udp_mem[3] __read_mostly;
 EXPORT_SYMBOL(sysctl_udp_mem);
 
 int sysctl_udp_rmem_min __read_mostly;
@@ -119,7 +119,7 @@ EXPORT_SYMBOL(sysctl_udp_rmem_min);
 int sysctl_udp_wmem_min __read_mostly;
 EXPORT_SYMBOL(sysctl_udp_wmem_min);
 
-atomic_t udp_memory_allocated;
+atomic_long_t udp_memory_allocated;
 EXPORT_SYMBOL(udp_memory_allocated);
 
 #define MAX_UDP_PORTS 65536