Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6.25

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6.25: (1470 commits)
  [IPV6] ADDRLABEL: Fix double free on label deletion.
  [PPP]: Sparse warning fixes.
  [IPV4] fib_trie: remove unneeded NULL check
  [IPV4] fib_trie: More whitespace cleanup.
  [NET_SCHED]: Use nla_policy for attribute validation in ematches
  [NET_SCHED]: Use nla_policy for attribute validation in actions
  [NET_SCHED]: Use nla_policy for attribute validation in classifiers
  [NET_SCHED]: Use nla_policy for attribute validation in packet schedulers
  [NET_SCHED]: sch_api: introduce constant for rate table size
  [NET_SCHED]: Use typeful attribute parsing helpers
  [NET_SCHED]: Use typeful attribute construction helpers
  [NET_SCHED]: Use NLA_PUT_STRING for string dumping
  [NET_SCHED]: Use nla_nest_start/nla_nest_end
  [NET_SCHED]: Propagate nla_parse return value
  [NET_SCHED]: act_api: use PTR_ERR in tcf_action_init/tcf_action_get
  [NET_SCHED]: act_api: use nlmsg_parse
  [NET_SCHED]: act_api: fix netlink API conversion bug
  [NET_SCHED]: sch_netem: use nla_parse_nested_compat
  [NET_SCHED]: sch_atm: fix format string warning
  [NETNS]: Add namespace for ICMP replying code.
  ...

2 files changed, 138 insertions, 85 deletions

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 060bba4567d2..eea75888805e 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -117,8 +117,6 @@
 #include <net/checksum.h>
 #include <linux/security.h>
 
-int sysctl_unix_max_dgram_qlen __read_mostly = 10;
-
 static struct hlist_head unix_socket_table[UNIX_HASH_SIZE + 1];
 static DEFINE_SPINLOCK(unix_table_lock);
 static atomic_t unix_nr_socks = ATOMIC_INIT(0);
@@ -127,32 +125,6 @@ static atomic_t unix_nr_socks = ATOMIC_INIT(0);
 
 #define UNIX_ABSTRACT(sk)       (unix_sk(sk)->addr->hash != UNIX_HASH_SIZE)
 
-static struct sock *first_unix_socket(int *i)
-{
-        for (*i = 0; *i <= UNIX_HASH_SIZE; (*i)++) {
-                if (!hlist_empty(&unix_socket_table[*i]))
-                        return __sk_head(&unix_socket_table[*i]);
-        }
-        return NULL;
-}
-
-static struct sock *next_unix_socket(int *i, struct sock *s)
-{
-        struct sock *next = sk_next(s);
-        /* More in this chain? */
-        if (next)
-                return next;
-        /* Look for next non-empty chain. */
-        for ((*i)++; *i <= UNIX_HASH_SIZE; (*i)++) {
-                if (!hlist_empty(&unix_socket_table[*i]))
-                        return __sk_head(&unix_socket_table[*i]);
-        }
-        return NULL;
-}
-
-#define forall_unix_sockets(i, s) \
-        for (s = first_unix_socket(&(i)); s; s = next_unix_socket(&(i),(s)))
-
 #ifdef CONFIG_SECURITY_NETWORK
 static void unix_get_secdata(struct scm_cookie *scm, struct sk_buff *skb)
 {
@@ -270,7 +242,8 @@ static inline void unix_insert_socket(struct hlist_head *list, struct sock *sk)
         spin_unlock(&unix_table_lock);
 }
 
-static struct sock *__unix_find_socket_byname(struct sockaddr_un *sunname,
+static struct sock *__unix_find_socket_byname(struct net *net,
+                                              struct sockaddr_un *sunname,
                                               int len, int type, unsigned hash)
 {
         struct sock *s;
@@ -279,6 +252,9 @@ static struct sock *__unix_find_socket_byname(struct sockaddr_un *sunname,
         sk_for_each(s, node, &unix_socket_table[hash ^ type]) {
                 struct unix_sock *u = unix_sk(s);
 
+                if (s->sk_net != net)
+                        continue;
+
                 if (u->addr->len == len &&
                     !memcmp(u->addr->name, sunname, len))
                         goto found;
@@ -288,21 +264,22 @@ found:
         return s;
 }
 
-static inline struct sock *unix_find_socket_byname(struct sockaddr_un *sunname,
+static inline struct sock *unix_find_socket_byname(struct net *net,
+                                                   struct sockaddr_un *sunname,
                                                    int len, int type,
                                                    unsigned hash)
 {
         struct sock *s;
 
         spin_lock(&unix_table_lock);
-        s = __unix_find_socket_byname(sunname, len, type, hash);
+        s = __unix_find_socket_byname(net, sunname, len, type, hash);
         if (s)
                 sock_hold(s);
         spin_unlock(&unix_table_lock);
         return s;
 }
 
-static struct sock *unix_find_socket_byinode(struct inode *i)
+static struct sock *unix_find_socket_byinode(struct net *net, struct inode *i)
 {
         struct sock *s;
         struct hlist_node *node;
@@ -312,6 +289,9 @@ static struct sock *unix_find_socket_byinode(struct inode *i)
                     &unix_socket_table[i->i_ino & (UNIX_HASH_SIZE - 1)]) {
                 struct dentry *dentry = unix_sk(s)->dentry;
 
+                if (s->sk_net != net)
+                        continue;
+
                 if(dentry && dentry->d_inode == i)
                 {
                         sock_hold(s);
@@ -335,7 +315,7 @@ static void unix_write_space(struct sock *sk)
         if (unix_writable(sk)) {
                 if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
                         wake_up_interruptible_sync(sk->sk_sleep);
-                sk_wake_async(sk, 2, POLL_OUT);
+                sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT);
         }
         read_unlock(&sk->sk_callback_lock);
 }
@@ -421,7 +401,7 @@ static int unix_release_sock (struct sock *sk, int embrion)
                         unix_state_unlock(skpair);
                         skpair->sk_state_change(skpair);
                         read_lock(&skpair->sk_callback_lock);
-                        sk_wake_async(skpair,1,POLL_HUP);
+                        sk_wake_async(skpair, SOCK_WAKE_WAITD, POLL_HUP);
                         read_unlock(&skpair->sk_callback_lock);
                 }
                 sock_put(skpair); /* It may now die */
@@ -612,7 +592,7 @@ static struct sock * unix_create1(struct net *net, struct socket *sock)
                                 &af_unix_sk_receive_queue_lock_key);
 
         sk->sk_write_space      = unix_write_space;
-        sk->sk_max_ack_backlog  = sysctl_unix_max_dgram_qlen;
+        sk->sk_max_ack_backlog  = net->unx.sysctl_max_dgram_qlen;
         sk->sk_destruct         = unix_sock_destructor;
         u         = unix_sk(sk);
         u->dentry = NULL;
@@ -631,9 +611,6 @@ out:
 
 static int unix_create(struct net *net, struct socket *sock, int protocol)
 {
-        if (net != &init_net)
-                return -EAFNOSUPPORT;
-
         if (protocol && protocol != PF_UNIX)
                 return -EPROTONOSUPPORT;
 
@@ -677,6 +654,7 @@ static int unix_release(struct socket *sock)
 static int unix_autobind(struct socket *sock)
 {
         struct sock *sk = sock->sk;
+        struct net *net = sk->sk_net;
         struct unix_sock *u = unix_sk(sk);
         static u32 ordernum = 1;
         struct unix_address * addr;
@@ -703,7 +681,7 @@ retry:
         spin_lock(&unix_table_lock);
         ordernum = (ordernum+1)&0xFFFFF;
 
-        if (__unix_find_socket_byname(addr->name, addr->len, sock->type,
+        if (__unix_find_socket_byname(net, addr->name, addr->len, sock->type,
                                       addr->hash)) {
                 spin_unlock(&unix_table_lock);
                 /* Sanity yield. It is unusual case, but yet... */
@@ -723,7 +701,8 @@ out:	mutex_unlock(&u->readlock);
         return err;
 }
 
-static struct sock *unix_find_other(struct sockaddr_un *sunname, int len,
+static struct sock *unix_find_other(struct net *net,
+                                    struct sockaddr_un *sunname, int len,
                                     int type, unsigned hash, int *error)
 {
         struct sock *u;
@@ -741,7 +720,7 @@ static struct sock *unix_find_other(struct sockaddr_un *sunname, int len,
                 err = -ECONNREFUSED;
                 if (!S_ISSOCK(nd.dentry->d_inode->i_mode))
                         goto put_fail;
-                u=unix_find_socket_byinode(nd.dentry->d_inode);
+                u=unix_find_socket_byinode(net, nd.dentry->d_inode);
                 if (!u)
                         goto put_fail;
 
@@ -757,7 +736,7 @@ static struct sock *unix_find_other(struct sockaddr_un *sunname, int len,
                 }
         } else {
                 err = -ECONNREFUSED;
-                u=unix_find_socket_byname(sunname, len, type, hash);
+                u=unix_find_socket_byname(net, sunname, len, type, hash);
                 if (u) {
                         struct dentry *dentry;
                         dentry = unix_sk(u)->dentry;
@@ -779,6 +758,7 @@ fail:
 static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 {
         struct sock *sk = sock->sk;
+        struct net *net = sk->sk_net;
         struct unix_sock *u = unix_sk(sk);
         struct sockaddr_un *sunaddr=(struct sockaddr_un *)uaddr;
         struct dentry * dentry = NULL;
@@ -853,7 +833,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 
         if (!sunaddr->sun_path[0]) {
                 err = -EADDRINUSE;
-                if (__unix_find_socket_byname(sunaddr, addr_len,
+                if (__unix_find_socket_byname(net, sunaddr, addr_len,
                                               sk->sk_type, hash)) {
                         unix_release_addr(addr);
                         goto out_unlock;
@@ -919,6 +899,7 @@ static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr,
                               int alen, int flags)
 {
         struct sock *sk = sock->sk;
+        struct net *net = sk->sk_net;
         struct sockaddr_un *sunaddr=(struct sockaddr_un*)addr;
         struct sock *other;
         unsigned hash;
@@ -935,7 +916,7 @@ static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr,
                         goto out;
 
 restart:
-                other=unix_find_other(sunaddr, alen, sock->type, hash, &err);
+                other=unix_find_other(net, sunaddr, alen, sock->type, hash, &err);
                 if (!other)
                         goto out;
 
@@ -1015,6 +996,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 {
         struct sockaddr_un *sunaddr=(struct sockaddr_un *)uaddr;
         struct sock *sk = sock->sk;
+        struct net *net = sk->sk_net;
         struct unix_sock *u = unix_sk(sk), *newu, *otheru;
         struct sock *newsk = NULL;
         struct sock *other = NULL;
@@ -1054,7 +1036,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 
 restart:
         /*  Find listening sock. */
-        other = unix_find_other(sunaddr, addr_len, sk->sk_type, hash, &err);
+        other = unix_find_other(net, sunaddr, addr_len, sk->sk_type, hash, &err);
         if (!other)
                 goto out;
 
@@ -1330,6 +1312,7 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock,
 {
         struct sock_iocb *siocb = kiocb_to_siocb(kiocb);
         struct sock *sk = sock->sk;
+        struct net *net = sk->sk_net;
         struct unix_sock *u = unix_sk(sk);
         struct sockaddr_un *sunaddr=msg->msg_name;
         struct sock *other = NULL;
@@ -1393,7 +1376,7 @@ restart:
                 if (sunaddr == NULL)
                         goto out_free;
 
-                other = unix_find_other(sunaddr, namelen, sk->sk_type,
+                other = unix_find_other(net, sunaddr, namelen, sk->sk_type,
                                         hash, &err);
                 if (other==NULL)
                         goto out_free;
@@ -1915,9 +1898,9 @@ static int unix_shutdown(struct socket *sock, int mode)
                         other->sk_state_change(other);
                         read_lock(&other->sk_callback_lock);
                         if (peer_mode == SHUTDOWN_MASK)
-                                sk_wake_async(other,1,POLL_HUP);
+                                sk_wake_async(other, SOCK_WAKE_WAITD, POLL_HUP);
                         else if (peer_mode & RCV_SHUTDOWN)
-                                sk_wake_async(other,1,POLL_IN);
+                                sk_wake_async(other, SOCK_WAKE_WAITD, POLL_IN);
                         read_unlock(&other->sk_callback_lock);
                 }
                 if (other)
@@ -2006,12 +1989,41 @@ static unsigned int unix_poll(struct file * file, struct socket *sock, poll_tabl
 
 
 #ifdef CONFIG_PROC_FS
-static struct sock *unix_seq_idx(int *iter, loff_t pos)
+static struct sock *first_unix_socket(int *i)
+{
+        for (*i = 0; *i <= UNIX_HASH_SIZE; (*i)++) {
+                if (!hlist_empty(&unix_socket_table[*i]))
+                        return __sk_head(&unix_socket_table[*i]);
+        }
+        return NULL;
+}
+
+static struct sock *next_unix_socket(int *i, struct sock *s)
+{
+        struct sock *next = sk_next(s);
+        /* More in this chain? */
+        if (next)
+                return next;
+        /* Look for next non-empty chain. */
+        for ((*i)++; *i <= UNIX_HASH_SIZE; (*i)++) {
+                if (!hlist_empty(&unix_socket_table[*i]))
+                        return __sk_head(&unix_socket_table[*i]);
+        }
+        return NULL;
+}
+
+struct unix_iter_state {
+        struct seq_net_private p;
+        int i;
+};
+static struct sock *unix_seq_idx(struct unix_iter_state *iter, loff_t pos)
 {
         loff_t off = 0;
         struct sock *s;
 
-        for (s = first_unix_socket(iter); s; s = next_unix_socket(iter, s)) {
+        for (s = first_unix_socket(&iter->i); s; s = next_unix_socket(&iter->i, s)) {
+                if (s->sk_net != iter->p.net)
+                        continue;
                 if (off == pos)
                         return s;
                 ++off;
@@ -2021,21 +2033,30 @@ static struct sock *unix_seq_idx(int *iter, loff_t pos)
 
 
 static void *unix_seq_start(struct seq_file *seq, loff_t *pos)
+        __acquires(unix_table_lock)
 {
+        struct unix_iter_state *iter = seq->private;
         spin_lock(&unix_table_lock);
-        return *pos ? unix_seq_idx(seq->private, *pos - 1) : ((void *) 1);
+        return *pos ? unix_seq_idx(iter, *pos - 1) : ((void *) 1);
 }
 
 static void *unix_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
+        struct unix_iter_state *iter = seq->private;
+        struct sock *sk = v;
         ++*pos;
 
         if (v == (void *)1)
-                return first_unix_socket(seq->private);
-        return next_unix_socket(seq->private, v);
+                sk = first_unix_socket(&iter->i);
+        else
+                sk = next_unix_socket(&iter->i, sk);
+        while (sk && (sk->sk_net != iter->p.net))
+                sk = next_unix_socket(&iter->i, sk);
+        return sk;
 }
 
 static void unix_seq_stop(struct seq_file *seq, void *v)
+        __releases(unix_table_lock)
 {
         spin_unlock(&unix_table_lock);
 }
@@ -2094,7 +2115,8 @@ static const struct seq_operations unix_seq_ops = {
 
 static int unix_seq_open(struct inode *inode, struct file *file)
 {
-        return seq_open_private(file, &unix_seq_ops, sizeof(int));
+        return seq_open_net(inode, file, &unix_seq_ops,
+                            sizeof(struct unix_iter_state));
 }
 
 static const struct file_operations unix_seq_fops = {
@@ -2102,7 +2124,7 @@ static const struct file_operations unix_seq_fops = {
         .open           = unix_seq_open,
         .read           = seq_read,
         .llseek         = seq_lseek,
-        .release        = seq_release_private,
+        .release        = seq_release_net,
 };
 
 #endif
@@ -2113,6 +2135,37 @@ static struct net_proto_family unix_family_ops = {
         .owner  = THIS_MODULE,
 };
 
+
+static int unix_net_init(struct net *net)
+{
+        int error = -ENOMEM;
+
+        net->unx.sysctl_max_dgram_qlen = 10;
+        if (unix_sysctl_register(net))
+                goto out;
+
+#ifdef CONFIG_PROC_FS
+        if (!proc_net_fops_create(net, "unix", 0, &unix_seq_fops)) {
+                unix_sysctl_unregister(net);
+                goto out;
+        }
+#endif
+        error = 0;
+out:
+        return 0;
+}
+
+static void unix_net_exit(struct net *net)
+{
+        unix_sysctl_unregister(net);
+        proc_net_remove(net, "unix");
+}
+
+static struct pernet_operations unix_net_ops = {
+        .init = unix_net_init,
+        .exit = unix_net_exit,
+};
+
 static int __init af_unix_init(void)
 {
         int rc = -1;
@@ -2128,10 +2181,7 @@ static int __init af_unix_init(void)
         }
 
         sock_register(&unix_family_ops);
-#ifdef CONFIG_PROC_FS
-        proc_net_fops_create(&init_net, "unix", 0, &unix_seq_fops);
-#endif
-        unix_sysctl_register();
+        register_pernet_subsys(&unix_net_ops);
 out:
         return rc;
 }
@@ -2139,9 +2189,8 @@ out:
 static void __exit af_unix_exit(void)
 {
         sock_unregister(PF_UNIX);
-        unix_sysctl_unregister();
-        proc_net_remove(&init_net, "unix");
         proto_unregister(&unix_proto);
+        unregister_pernet_subsys(&unix_net_ops);
 }
 
 module_init(af_unix_init);
diff --git a/net/unix/sysctl_net_unix.c b/net/unix/sysctl_net_unix.c
index eb0bd57ebada..77513d7e35f2 100644
--- a/net/unix/sysctl_net_unix.c
+++ b/net/unix/sysctl_net_unix.c
@@ -18,7 +18,7 @@ static ctl_table unix_table[] = {
         {
                 .ctl_name       = NET_UNIX_MAX_DGRAM_QLEN,
                 .procname       = "max_dgram_qlen",
-                .data           = &sysctl_unix_max_dgram_qlen,
+                .data           = &init_net.unx.sysctl_max_dgram_qlen,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
                 .proc_handler   = &proc_dointvec
@@ -26,35 +26,39 @@ static ctl_table unix_table[] = {
         { .ctl_name = 0 }
 };
 
-static ctl_table unix_net_table[] = {
-        {
-                .ctl_name       = NET_UNIX,
-                .procname       = "unix",
-                .mode           = 0555,
-                .child          = unix_table
-        },
-        { .ctl_name = 0 }
+static struct ctl_path unix_path[] = {
+        { .procname = "net", .ctl_name = CTL_NET, },
+        { .procname = "unix", .ctl_name = NET_UNIX, },
+        { },
 };
 
-static ctl_table unix_root_table[] = {
-        {
-                .ctl_name       = CTL_NET,
-                .procname       = "net",
-                .mode           = 0555,
-                .child          = unix_net_table
-        },
-        { .ctl_name = 0 }
-};
+int unix_sysctl_register(struct net *net)
+{
+        struct ctl_table *table;
 
-static struct ctl_table_header * unix_sysctl_header;
+        table = kmemdup(unix_table, sizeof(unix_table), GFP_KERNEL);
+        if (table == NULL)
+                goto err_alloc;
 
-void unix_sysctl_register(void)
-{
-        unix_sysctl_header = register_sysctl_table(unix_root_table);
+        table[0].data = &net->unx.sysctl_max_dgram_qlen;
+        net->unx.ctl = register_net_sysctl_table(net, unix_path, table);
+        if (net->unx.ctl == NULL)
+                goto err_reg;
+
+        return 0;
+
+err_reg:
+        kfree(table);
+err_alloc:
+        return -ENOMEM;
 }
 
-void unix_sysctl_unregister(void)
+void unix_sysctl_unregister(struct net *net)
 {
-        unregister_sysctl_table(unix_sysctl_header);
+        struct ctl_table *table;
+
+        table = net->unx.ctl->ctl_table_arg;
+        unregister_sysctl_table(net->unx.ctl);
+        kfree(table);
 }