1 files changed, 134 insertions, 53 deletions

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 7d12c6a9b19b..6a1100c25a9f 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -86,6 +86,7 @@
 #include <linux/poll.h>
 #include <linux/netfilter_ipv4.h>
 #include <linux/random.h>
+#include <linux/slab.h>
 
 #include <asm/uaccess.h>
 #include <asm/system.h>
@@ -153,7 +154,7 @@ void inet_sock_destruct(struct sock *sk)
         WARN_ON(sk->sk_forward_alloc);
 
         kfree(inet->opt);
-        dst_release(sk->sk_dst_cache);
+        dst_release(rcu_dereference_check(sk->sk_dst_cache, 1));
         sk_refcnt_debug_dec(sk);
 }
 EXPORT_SYMBOL(inet_sock_destruct);
@@ -354,6 +355,8 @@ lookup_protocol:
         inet = inet_sk(sk);
         inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) != 0;
 
+        inet->nodefrag = 0;
+
         if (SOCK_RAW == sock->type) {
                 inet->inet_num = protocol;
                 if (IPPROTO_RAW == protocol)
@@ -418,6 +421,8 @@ int inet_release(struct socket *sock)
         if (sk) {
                 long timeout;
 
+                sock_rps_reset_flow(sk);
+
                 /* Applications forget to leave groups before exiting */
                 ip_mc_drop_socket(sk);
 
@@ -530,6 +535,8 @@ int inet_dgram_connect(struct socket *sock, struct sockaddr * uaddr,
 {
         struct sock *sk = sock->sk;
 
+        if (addr_len < sizeof(uaddr->sa_family))
+                return -EINVAL;
         if (uaddr->sa_family == AF_UNSPEC)
                 return sk->sk_prot->disconnect(sk, flags);
 
@@ -543,7 +550,7 @@ static long inet_wait_for_connect(struct sock *sk, long timeo)
 {
         DEFINE_WAIT(wait);
 
-        prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+        prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
 
         /* Basic assumption: if someone sets sk->sk_err, he _must_
          * change state of the socket from TCP_SYN_*.
@@ -556,9 +563,9 @@ static long inet_wait_for_connect(struct sock *sk, long timeo)
                 lock_sock(sk);
                 if (signal_pending(current) || !timeo)
                         break;
-                prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+                prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
         }
-        finish_wait(sk->sk_sleep, &wait);
+        finish_wait(sk_sleep(sk), &wait);
         return timeo;
 }
 
@@ -573,6 +580,9 @@ int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
         int err;
         long timeo;
 
+        if (addr_len < sizeof(uaddr->sa_family))
+                return -EINVAL;
+
         lock_sock(sk);
 
         if (uaddr->sa_family == AF_UNSPEC) {
@@ -714,29 +724,51 @@ int inet_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
 {
         struct sock *sk = sock->sk;
 
+        sock_rps_record_flow(sk);
+
         /* We may need to bind the socket. */
-        if (!inet_sk(sk)->inet_num && inet_autobind(sk))
+        if (!inet_sk(sk)->inet_num && !sk->sk_prot->no_autobind &&
+            inet_autobind(sk))
                 return -EAGAIN;
 
         return sk->sk_prot->sendmsg(iocb, sk, msg, size);
 }
 EXPORT_SYMBOL(inet_sendmsg);
 
-
-static ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset,
-                             size_t size, int flags)
+ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset,
+                      size_t size, int flags)
 {
         struct sock *sk = sock->sk;
 
+        sock_rps_record_flow(sk);
+
         /* We may need to bind the socket. */
-        if (!inet_sk(sk)->inet_num && inet_autobind(sk))
+        if (!inet_sk(sk)->inet_num && !sk->sk_prot->no_autobind &&
+            inet_autobind(sk))
                 return -EAGAIN;
 
         if (sk->sk_prot->sendpage)
                 return sk->sk_prot->sendpage(sk, page, offset, size, flags);
         return sock_no_sendpage(sock, page, offset, size, flags);
 }
+EXPORT_SYMBOL(inet_sendpage);
 
+int inet_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
+                 size_t size, int flags)
+{
+        struct sock *sk = sock->sk;
+        int addr_len = 0;
+        int err;
+
+        sock_rps_record_flow(sk);
+
+        err = sk->sk_prot->recvmsg(iocb, sk, msg, size, flags & MSG_DONTWAIT,
+                                   flags & ~MSG_DONTWAIT, &addr_len);
+        if (err >= 0)
+                msg->msg_namelen = addr_len;
+        return err;
+}
+EXPORT_SYMBOL(inet_recvmsg);
 
 int inet_shutdown(struct socket *sock, int how)
 {
@@ -865,10 +897,10 @@ const struct proto_ops inet_stream_ops = {
         .shutdown          = inet_shutdown,
         .setsockopt        = sock_common_setsockopt,
         .getsockopt        = sock_common_getsockopt,
-        .sendmsg           = tcp_sendmsg,
-        .recvmsg           = sock_common_recvmsg,
+        .sendmsg           = inet_sendmsg,
+        .recvmsg           = inet_recvmsg,
         .mmap              = sock_no_mmap,
-        .sendpage          = tcp_sendpage,
+        .sendpage          = inet_sendpage,
         .splice_read       = tcp_splice_read,
 #ifdef CONFIG_COMPAT
         .compat_setsockopt = compat_sock_common_setsockopt,
@@ -893,7 +925,7 @@ const struct proto_ops inet_dgram_ops = {
         .setsockopt        = sock_common_setsockopt,
         .getsockopt        = sock_common_getsockopt,
         .sendmsg           = inet_sendmsg,
-        .recvmsg           = sock_common_recvmsg,
+        .recvmsg           = inet_recvmsg,
         .mmap              = sock_no_mmap,
         .sendpage          = inet_sendpage,
 #ifdef CONFIG_COMPAT
@@ -923,7 +955,7 @@ static const struct proto_ops inet_sockraw_ops = {
         .setsockopt        = sock_common_setsockopt,
         .getsockopt        = sock_common_getsockopt,
         .sendmsg           = inet_sendmsg,
-        .recvmsg           = sock_common_recvmsg,
+        .recvmsg           = inet_recvmsg,
         .mmap              = sock_no_mmap,
         .sendpage          = inet_sendpage,
 #ifdef CONFIG_COMPAT
@@ -1073,7 +1105,7 @@ static int inet_sk_reselect_saddr(struct sock *sk)
         if (err)
                 return err;
 
-        sk_setup_caps(sk, &rt->u.dst);
+        sk_setup_caps(sk, &rt->dst);
 
         new_saddr = rt->rt_src;
 
@@ -1139,7 +1171,7 @@ int inet_sk_rebuild_header(struct sock *sk)
         err = ip_route_output_flow(sock_net(sk), &rt, &fl, sk, 0);
 }
         if (!err)
-                sk_setup_caps(sk, &rt->u.dst);
+                sk_setup_caps(sk, &rt->dst);
         else {
                 /* Routing failed... */
                 sk->sk_route_caps = 0;
@@ -1296,8 +1328,8 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head,
         if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl)))
                 goto out_unlock;
 
-        id = ntohl(*(u32 *)&iph->id);
-        flush = (u16)((ntohl(*(u32 *)iph) ^ skb_gro_len(skb)) | (id ^ IP_DF));
+        id = ntohl(*(__be32 *)&iph->id);
+        flush = (u16)((ntohl(*(__be32 *)iph) ^ skb_gro_len(skb)) | (id ^ IP_DF));
         id >>= 16;
 
         for (p = *head; p; p = p->next) {
@@ -1310,8 +1342,8 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head,
 
                 if ((iph->protocol ^ iph2->protocol) |
                     (iph->tos ^ iph2->tos) |
-                    (iph->saddr ^ iph2->saddr) |
-                    (iph->daddr ^ iph2->daddr)) {
+                    ((__force u32)iph->saddr ^ (__force u32)iph2->saddr) |
+                    ((__force u32)iph->daddr ^ (__force u32)iph2->daddr)) {
                         NAPI_GRO_CB(p)->same_flow = 0;
                         continue;
                 }
@@ -1385,7 +1417,7 @@ int inet_ctl_sock_create(struct sock **sk, unsigned short family,
 }
 EXPORT_SYMBOL_GPL(inet_ctl_sock_create);
 
-unsigned long snmp_fold_field(void *mib[], int offt)
+unsigned long snmp_fold_field(void __percpu *mib[], int offt)
 {
         unsigned long res = 0;
         int i;
@@ -1398,13 +1430,49 @@ unsigned long snmp_fold_field(void *mib[], int offt)
 }
 EXPORT_SYMBOL_GPL(snmp_fold_field);
 
-int snmp_mib_init(void *ptr[2], size_t mibsize)
+#if BITS_PER_LONG==32
+
+u64 snmp_fold_field64(void __percpu *mib[], int offt, size_t syncp_offset)
+{
+        u64 res = 0;
+        int cpu;
+
+        for_each_possible_cpu(cpu) {
+                void *bhptr, *userptr;
+                struct u64_stats_sync *syncp;
+                u64 v_bh, v_user;
+                unsigned int start;
+
+                /* first mib used by softirq context, we must use _bh() accessors */
+                bhptr = per_cpu_ptr(SNMP_STAT_BHPTR(mib), cpu);
+                syncp = (struct u64_stats_sync *)(bhptr + syncp_offset);
+                do {
+                        start = u64_stats_fetch_begin_bh(syncp);
+                        v_bh = *(((u64 *) bhptr) + offt);
+                } while (u64_stats_fetch_retry_bh(syncp, start));
+
+                /* second mib used in USER context */
+                userptr = per_cpu_ptr(SNMP_STAT_USRPTR(mib), cpu);
+                syncp = (struct u64_stats_sync *)(userptr + syncp_offset);
+                do {
+                        start = u64_stats_fetch_begin(syncp);
+                        v_user = *(((u64 *) userptr) + offt);
+                } while (u64_stats_fetch_retry(syncp, start));
+
+                res += v_bh + v_user;
+        }
+        return res;
+}
+EXPORT_SYMBOL_GPL(snmp_fold_field64);
+#endif
+
+int snmp_mib_init(void __percpu *ptr[2], size_t mibsize, size_t align)
 {
         BUG_ON(ptr == NULL);
-        ptr[0] = __alloc_percpu(mibsize, __alignof__(unsigned long long));
+        ptr[0] = __alloc_percpu(mibsize, align);
         if (!ptr[0])
                 goto err0;
-        ptr[1] = __alloc_percpu(mibsize, __alignof__(unsigned long long));
+        ptr[1] = __alloc_percpu(mibsize, align);
         if (!ptr[1])
                 goto err1;
         return 0;
@@ -1416,7 +1484,7 @@ err0:
 }
 EXPORT_SYMBOL_GPL(snmp_mib_init);
 
-void snmp_mib_free(void *ptr[2])
+void snmp_mib_free(void __percpu *ptr[2])
 {
         BUG_ON(ptr == NULL);
         free_percpu(ptr[0]);
@@ -1460,56 +1528,63 @@ static const struct net_protocol icmp_protocol = {
 
 static __net_init int ipv4_mib_init_net(struct net *net)
 {
-        if (snmp_mib_init((void **)net->mib.tcp_statistics,
-                          sizeof(struct tcp_mib)) < 0)
+        if (snmp_mib_init((void __percpu **)net->mib.tcp_statistics,
+                          sizeof(struct tcp_mib),
+                          __alignof__(struct tcp_mib)) < 0)
                 goto err_tcp_mib;
-        if (snmp_mib_init((void **)net->mib.ip_statistics,
-                          sizeof(struct ipstats_mib)) < 0)
+        if (snmp_mib_init((void __percpu **)net->mib.ip_statistics,
+                          sizeof(struct ipstats_mib),
+                          __alignof__(struct ipstats_mib)) < 0)
                 goto err_ip_mib;
-        if (snmp_mib_init((void **)net->mib.net_statistics,
-                          sizeof(struct linux_mib)) < 0)
+        if (snmp_mib_init((void __percpu **)net->mib.net_statistics,
+                          sizeof(struct linux_mib),
+                          __alignof__(struct linux_mib)) < 0)
                 goto err_net_mib;
-        if (snmp_mib_init((void **)net->mib.udp_statistics,
-                          sizeof(struct udp_mib)) < 0)
+        if (snmp_mib_init((void __percpu **)net->mib.udp_statistics,
+                          sizeof(struct udp_mib),
+                          __alignof__(struct udp_mib)) < 0)
                 goto err_udp_mib;
-        if (snmp_mib_init((void **)net->mib.udplite_statistics,
-                          sizeof(struct udp_mib)) < 0)
+        if (snmp_mib_init((void __percpu **)net->mib.udplite_statistics,
+                          sizeof(struct udp_mib),
+                          __alignof__(struct udp_mib)) < 0)
                 goto err_udplite_mib;
-        if (snmp_mib_init((void **)net->mib.icmp_statistics,
-                          sizeof(struct icmp_mib)) < 0)
+        if (snmp_mib_init((void __percpu **)net->mib.icmp_statistics,
+                          sizeof(struct icmp_mib),
+                          __alignof__(struct icmp_mib)) < 0)
                 goto err_icmp_mib;
-        if (snmp_mib_init((void **)net->mib.icmpmsg_statistics,
-                          sizeof(struct icmpmsg_mib)) < 0)
+        if (snmp_mib_init((void __percpu **)net->mib.icmpmsg_statistics,
+                          sizeof(struct icmpmsg_mib),
+                          __alignof__(struct icmpmsg_mib)) < 0)
                 goto err_icmpmsg_mib;
 
         tcp_mib_init(net);
         return 0;
 
 err_icmpmsg_mib:
-        snmp_mib_free((void **)net->mib.icmp_statistics);
+        snmp_mib_free((void __percpu **)net->mib.icmp_statistics);
 err_icmp_mib:
-        snmp_mib_free((void **)net->mib.udplite_statistics);
+        snmp_mib_free((void __percpu **)net->mib.udplite_statistics);
 err_udplite_mib:
-        snmp_mib_free((void **)net->mib.udp_statistics);
+        snmp_mib_free((void __percpu **)net->mib.udp_statistics);
 err_udp_mib:
-        snmp_mib_free((void **)net->mib.net_statistics);
+        snmp_mib_free((void __percpu **)net->mib.net_statistics);
 err_net_mib:
-        snmp_mib_free((void **)net->mib.ip_statistics);
+        snmp_mib_free((void __percpu **)net->mib.ip_statistics);
 err_ip_mib:
-        snmp_mib_free((void **)net->mib.tcp_statistics);
+        snmp_mib_free((void __percpu **)net->mib.tcp_statistics);
 err_tcp_mib:
         return -ENOMEM;
 }
 
 static __net_exit void ipv4_mib_exit_net(struct net *net)
 {
-        snmp_mib_free((void **)net->mib.icmpmsg_statistics);
-        snmp_mib_free((void **)net->mib.icmp_statistics);
-        snmp_mib_free((void **)net->mib.udplite_statistics);
-        snmp_mib_free((void **)net->mib.udp_statistics);
-        snmp_mib_free((void **)net->mib.net_statistics);
-        snmp_mib_free((void **)net->mib.ip_statistics);
-        snmp_mib_free((void **)net->mib.tcp_statistics);
+        snmp_mib_free((void __percpu **)net->mib.icmpmsg_statistics);
+        snmp_mib_free((void __percpu **)net->mib.icmp_statistics);
+        snmp_mib_free((void __percpu **)net->mib.udplite_statistics);
+        snmp_mib_free((void __percpu **)net->mib.udp_statistics);
+        snmp_mib_free((void __percpu **)net->mib.net_statistics);
+        snmp_mib_free((void __percpu **)net->mib.ip_statistics);
+        snmp_mib_free((void __percpu **)net->mib.tcp_statistics);
 }
 
 static __net_initdata struct pernet_operations ipv4_mib_ops = {
@@ -1546,9 +1621,13 @@ static int __init inet_init(void)
 
         BUILD_BUG_ON(sizeof(struct inet_skb_parm) > sizeof(dummy_skb->cb));
 
+        sysctl_local_reserved_ports = kzalloc(65536 / 8, GFP_KERNEL);
+        if (!sysctl_local_reserved_ports)
+                goto out;
+
         rc = proto_register(&tcp_prot, 1);
         if (rc)
-                goto out;
+                goto out_free_reserved_ports;
 
         rc = proto_register(&udp_prot, 1);
         if (rc)
@@ -1647,6 +1726,8 @@ out_unregister_udp_proto:
         proto_unregister(&udp_prot);
 out_unregister_tcp_proto:
         proto_unregister(&tcp_prot);
+out_free_reserved_ports:
+        kfree(sysctl_local_reserved_ports);
         goto out;
 }