1 files changed, 97 insertions, 46 deletions

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index a4957bf2ca60..cd96ed3ccee4 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -455,9 +455,14 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol,
         if (nl_table[protocol].registered &&
             try_module_get(nl_table[protocol].module))
                 module = nl_table[protocol].module;
+        else
+                err = -EPROTONOSUPPORT;
         cb_mutex = nl_table[protocol].cb_mutex;
         netlink_unlock_table();
 
+        if (err < 0)
+                goto out;
+
         err = __netlink_create(net, sock, cb_mutex, protocol);
         if (err < 0)
                 goto out_module;
@@ -540,7 +545,7 @@ static int netlink_autobind(struct socket *sock)
         struct hlist_head *head;
         struct sock *osk;
         struct hlist_node *node;
-        s32 pid = current->tgid;
+        s32 pid = task_tgid_vnr(current);
         int err;
         static s32 rover = -4097;
 
@@ -678,6 +683,9 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr,
         struct netlink_sock *nlk = nlk_sk(sk);
         struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr;
 
+        if (alen < sizeof(addr->sa_family))
+                return -EINVAL;
+
         if (addr->sa_family == AF_UNSPEC) {
                 sk->sk_state    = NETLINK_UNCONNECTED;
                 nlk->dst_pid    = 0;
@@ -970,6 +978,8 @@ struct netlink_broadcast_data {
         int delivered;
         gfp_t allocation;
         struct sk_buff *skb, *skb2;
+        int (*tx_filter)(struct sock *dsk, struct sk_buff *skb, void *data);
+        void *tx_data;
 };
 
 static inline int do_one_broadcast(struct sock *sk,
@@ -1012,6 +1022,9 @@ static inline int do_one_broadcast(struct sock *sk,
                 p->failure = 1;
                 if (nlk->flags & NETLINK_BROADCAST_SEND_ERROR)
                         p->delivery_failure = 1;
+        } else if (p->tx_filter && p->tx_filter(sk, p->skb2, p->tx_data)) {
+                kfree_skb(p->skb2);
+                p->skb2 = NULL;
         } else if (sk_filter(sk, p->skb2)) {
                 kfree_skb(p->skb2);
                 p->skb2 = NULL;
@@ -1030,8 +1043,10 @@ out:
         return 0;
 }
 
-int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, u32 pid,
-                      u32 group, gfp_t allocation)
+int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb, u32 pid,
+        u32 group, gfp_t allocation,
+        int (*filter)(struct sock *dsk, struct sk_buff *skb, void *data),
+        void *filter_data)
 {
         struct net *net = sock_net(ssk);
         struct netlink_broadcast_data info;
@@ -1051,6 +1066,8 @@ int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, u32 pid,
         info.allocation = allocation;
         info.skb = skb;
         info.skb2 = NULL;
+        info.tx_filter = filter;
+        info.tx_data = filter_data;
 
         /* While we sleep in clone, do not allow to change socket list */
 
@@ -1059,14 +1076,15 @@ int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, u32 pid,
         sk_for_each_bound(sk, node, &nl_table[ssk->sk_protocol].mc_list)
                 do_one_broadcast(sk, &info);
 
-        kfree_skb(skb);
+        consume_skb(skb);
 
         netlink_unlock_table();
 
-        kfree_skb(info.skb2);
-
-        if (info.delivery_failure)
+        if (info.delivery_failure) {
+                kfree_skb(info.skb2);
                 return -ENOBUFS;
+        } else
+                consume_skb(info.skb2);
 
         if (info.delivered) {
                 if (info.congested && (allocation & __GFP_WAIT))
@@ -1075,6 +1093,14 @@ int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, u32 pid,
         }
         return -ESRCH;
 }
+EXPORT_SYMBOL(netlink_broadcast_filtered);
+
+int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, u32 pid,
+                      u32 group, gfp_t allocation)
+{
+        return netlink_broadcast_filtered(ssk, skb, pid, group, allocation,
+                NULL, NULL);
+}
 EXPORT_SYMBOL(netlink_broadcast);
 
 struct netlink_set_err_data {
@@ -1088,6 +1114,7 @@ static inline int do_one_set_err(struct sock *sk,
                                  struct netlink_set_err_data *p)
 {
         struct netlink_sock *nlk = nlk_sk(sk);
+        int ret = 0;
 
         if (sk == p->exclude_sk)
                 goto out;
@@ -1099,10 +1126,15 @@ static inline int do_one_set_err(struct sock *sk,
             !test_bit(p->group - 1, nlk->groups))
                 goto out;
 
+        if (p->code == ENOBUFS && nlk->flags & NETLINK_RECV_NO_ENOBUFS) {
+                ret = 1;
+                goto out;
+        }
+
         sk->sk_err = p->code;
         sk->sk_error_report(sk);
 out:
-        return 0;
+        return ret;
 }
 
 /**
@@ -1111,12 +1143,16 @@ out:
  * @pid: the PID of a process that we want to skip (if any)
  * @groups: the broadcast group that will notice the error
  * @code: error code, must be negative (as usual in kernelspace)
+ *
+ * This function returns the number of broadcast listeners that have set the
+ * NETLINK_RECV_NO_ENOBUFS socket option.
  */
-void netlink_set_err(struct sock *ssk, u32 pid, u32 group, int code)
+int netlink_set_err(struct sock *ssk, u32 pid, u32 group, int code)
 {
         struct netlink_set_err_data info;
         struct hlist_node *node;
         struct sock *sk;
+        int ret = 0;
 
         info.exclude_sk = ssk;
         info.pid = pid;
@@ -1127,9 +1163,10 @@ void netlink_set_err(struct sock *ssk, u32 pid, u32 group, int code)
         read_lock(&nl_table_lock);
 
         sk_for_each_bound(sk, node, &nl_table[ssk->sk_protocol].mc_list)
-                do_one_set_err(sk, &info);
+                ret += do_one_set_err(sk, &info);
 
         read_unlock(&nl_table_lock);
+        return ret;
 }
 EXPORT_SYMBOL(netlink_set_err);
 
@@ -1287,19 +1324,23 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
         if (msg->msg_flags&MSG_OOB)
                 return -EOPNOTSUPP;
 
-        if (NULL == siocb->scm)
+        if (NULL == siocb->scm) {
                 siocb->scm = &scm;
+                memset(&scm, 0, sizeof(scm));
+        }
         err = scm_send(sock, msg, siocb->scm);
         if (err < 0)
                 return err;
 
         if (msg->msg_namelen) {
+                err = -EINVAL;
                 if (addr->nl_family != AF_NETLINK)
-                        return -EINVAL;
+                        goto out;
                 dst_pid = addr->nl_pid;
                 dst_group = ffs(addr->nl_groups);
+                err =  -EPERM;
                 if (dst_group && !netlink_capable(sock, NL_NONROOT_SEND))
-                        return -EPERM;
+                        goto out;
         } else {
                 dst_pid = nlk->dst_pid;
                 dst_group = nlk->dst_group;
@@ -1351,6 +1392,7 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
         err = netlink_unicast(sk, skb, dst_pid, msg->msg_flags&MSG_DONTWAIT);
 
 out:
+        scm_destroy(siocb->scm);
         return err;
 }
 
@@ -1364,7 +1406,7 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock,
         struct netlink_sock *nlk = nlk_sk(sk);
         int noblock = flags&MSG_DONTWAIT;
         size_t copied;
-        struct sk_buff *skb, *frag __maybe_unused = NULL;
+        struct sk_buff *skb, *data_skb;
         int err;
 
         if (flags&MSG_OOB)
@@ -1376,45 +1418,35 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock,
         if (skb == NULL)
                 goto out;
 
+        data_skb = skb;
+
 #ifdef CONFIG_COMPAT_NETLINK_MESSAGES
         if (unlikely(skb_shinfo(skb)->frag_list)) {
-                bool need_compat = !!(flags & MSG_CMSG_COMPAT);
-
                 /*
-                 * If this skb has a frag_list, then here that means that
-                 * we will have to use the frag_list skb for compat tasks
-                 * and the regular skb for non-compat tasks.
+                 * If this skb has a frag_list, then here that means that we
+                 * will have to use the frag_list skb's data for compat tasks
+                 * and the regular skb's data for normal (non-compat) tasks.
                  *
-                 * The skb might (and likely will) be cloned, so we can't
-                 * just reset frag_list and go on with things -- we need to
-                 * keep that. For the compat case that's easy -- simply get
-                 * a reference to the compat skb and free the regular one
-                 * including the frag. For the non-compat case, we need to
-                 * avoid sending the frag to the user -- so assign NULL but
-                 * restore it below before freeing the skb.
+                 * If we need to send the compat skb, assign it to the
+                 * 'data_skb' variable so that it will be used below for data
+                 * copying. We keep 'skb' for everything else, including
+                 * freeing both later.
                  */
-                if (need_compat) {
-                        struct sk_buff *compskb = skb_shinfo(skb)->frag_list;
-                        skb_get(compskb);
-                        kfree_skb(skb);
-                        skb = compskb;
-                } else {
-                        frag = skb_shinfo(skb)->frag_list;
-                        skb_shinfo(skb)->frag_list = NULL;
-                }
+                if (flags & MSG_CMSG_COMPAT)
+                        data_skb = skb_shinfo(skb)->frag_list;
         }
 #endif
 
         msg->msg_namelen = 0;
 
-        copied = skb->len;
+        copied = data_skb->len;
         if (len < copied) {
                 msg->msg_flags |= MSG_TRUNC;
                 copied = len;
         }
 
-        skb_reset_transport_header(skb);
-        err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+        skb_reset_transport_header(data_skb);
+        err = skb_copy_datagram_iovec(data_skb, 0, msg->msg_iov, copied);
 
         if (msg->msg_name) {
                 struct sockaddr_nl *addr = (struct sockaddr_nl *)msg->msg_name;
@@ -1434,11 +1466,7 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock,
         }
         siocb->scm->creds = *NETLINK_CREDS(skb);
         if (flags & MSG_TRUNC)
-                copied = skb->len;
-
-#ifdef CONFIG_COMPAT_NETLINK_MESSAGES
-        skb_shinfo(skb)->frag_list = frag;
-#endif
+                copied = data_skb->len;
 
         skb_free_datagram(sk, skb);
 
@@ -1973,12 +2001,12 @@ static int netlink_seq_show(struct seq_file *seq, void *v)
         if (v == SEQ_START_TOKEN)
                 seq_puts(seq,
                          "sk       Eth Pid    Groups   "
-                         "Rmem     Wmem     Dump     Locks     Drops\n");
+                         "Rmem     Wmem     Dump     Locks     Drops     Inode\n");
         else {
                 struct sock *s = v;
                 struct netlink_sock *nlk = nlk_sk(s);
 
-                seq_printf(seq, "%p %-3d %-6d %08x %-8d %-8d %p %-8d %-8d\n",
+                seq_printf(seq, "%p %-3d %-6d %08x %-8d %-8d %p %-8d %-8d %-8lu\n",
                            s,
                            s->sk_protocol,
                            nlk->pid,
@@ -1987,7 +2015,8 @@ static int netlink_seq_show(struct seq_file *seq, void *v)
                            sk_wmem_alloc_get(s),
                            nlk->cb,
                            atomic_read(&s->sk_refcnt),
-                           atomic_read(&s->sk_drops)
+                           atomic_read(&s->sk_drops),
+                           sock_i_ino(s)
                         );
 
         }
@@ -2073,6 +2102,26 @@ static void __net_exit netlink_net_exit(struct net *net)
 #endif
 }
 
+static void __init netlink_add_usersock_entry(void)
+{
+        unsigned long *listeners;
+        int groups = 32;
+
+        listeners = kzalloc(NLGRPSZ(groups) + sizeof(struct listeners_rcu_head),
+                            GFP_KERNEL);
+        if (!listeners)
+                panic("netlink_add_usersock_entry: Cannot allocate listneres\n");
+
+        netlink_table_grab();
+
+        nl_table[NETLINK_USERSOCK].groups = groups;
+        nl_table[NETLINK_USERSOCK].listeners = listeners;
+        nl_table[NETLINK_USERSOCK].module = THIS_MODULE;
+        nl_table[NETLINK_USERSOCK].registered = 1;
+
+        netlink_table_ungrab();
+}
+
 static struct pernet_operations __net_initdata netlink_net_ops = {
         .init = netlink_net_init,
         .exit = netlink_net_exit,
@@ -2121,6 +2170,8 @@ static int __init netlink_proto_init(void)
                 hash->rehash_time = jiffies;
         }
 
+        netlink_add_usersock_entry();
+
         sock_register(&netlink_family_ops);
         register_pernet_subsys(&netlink_net_ops);
         /* The netlink device handler may be needed early. */