#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);
#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)
{
return (unix_peer(osk) == NULL || unix_our_peer(sk, osk));
}
+static inline int unix_recvq_full(struct sock const *sk)
+{
+ return skb_queue_len(&sk->sk_receive_queue) > sk->sk_max_ack_backlog;
+}
+
static struct sock *unix_peer_get(struct sock *s)
{
struct sock *peer;
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;
sk_for_each(s, node, &unix_socket_table[hash ^ type]) {
struct unix_sock *u = unix_sk(s);
+ if (!net_eq(sock_net(s), net))
+ continue;
+
if (u->addr->len == len &&
!memcmp(u->addr->name, sunname, len))
goto 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;
&unix_socket_table[i->i_ino & (UNIX_HASH_SIZE - 1)]) {
struct dentry *dentry = unix_sk(s)->dentry;
+ if (!net_eq(sock_net(s), net))
+ continue;
+
if(dentry && dentry->d_inode == i)
{
sock_hold(s);
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);
}
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 */
static int unix_accept(struct socket *, struct socket *, int);
static int unix_getname(struct socket *, struct sockaddr *, int *, int);
static unsigned int unix_poll(struct file *, struct socket *, poll_table *);
+static unsigned int unix_datagram_poll(struct file *, struct socket *,
+ poll_table *);
static int unix_ioctl(struct socket *, unsigned int, unsigned long);
static int unix_shutdown(struct socket *, int);
static int unix_stream_sendmsg(struct kiocb *, struct socket *,
.socketpair = unix_socketpair,
.accept = sock_no_accept,
.getname = unix_getname,
- .poll = datagram_poll,
+ .poll = unix_datagram_poll,
.ioctl = unix_ioctl,
.listen = sock_no_listen,
.shutdown = unix_shutdown,
.socketpair = unix_socketpair,
.accept = unix_accept,
.getname = unix_getname,
- .poll = datagram_poll,
+ .poll = unix_datagram_poll,
.ioctl = unix_ioctl,
.listen = unix_listen,
.shutdown = unix_shutdown,
&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;
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;
static int unix_autobind(struct socket *sock)
{
struct sock *sk = sock->sk;
+ struct net *net = sock_net(sk);
struct unix_sock *u = unix_sk(sk);
static u32 ordernum = 1;
struct unix_address * addr;
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... */
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;
goto put_fail;
err = -ECONNREFUSED;
- if (!S_ISSOCK(nd.dentry->d_inode->i_mode))
+ if (!S_ISSOCK(nd.path.dentry->d_inode->i_mode))
goto put_fail;
- u=unix_find_socket_byinode(nd.dentry->d_inode);
+ u = unix_find_socket_byinode(net, nd.path.dentry->d_inode);
if (!u)
goto put_fail;
if (u->sk_type == type)
- touch_atime(nd.mnt, nd.dentry);
+ touch_atime(nd.path.mnt, nd.path.dentry);
- path_release(&nd);
+ path_put(&nd.path);
err=-EPROTOTYPE;
if (u->sk_type != type) {
}
} 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;
return u;
put_fail:
- path_release(&nd);
+ path_put(&nd.path);
fail:
*error=err;
return NULL;
static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
{
struct sock *sk = sock->sk;
+ struct net *net = sock_net(sk);
struct unix_sock *u = unix_sk(sk);
struct sockaddr_un *sunaddr=(struct sockaddr_un *)uaddr;
struct dentry * dentry = NULL;
*/
mode = S_IFSOCK |
(SOCK_INODE(sock)->i_mode & ~current->fs->umask);
- err = vfs_mknod(nd.dentry->d_inode, dentry, mode, 0);
+ err = mnt_want_write(nd.path.mnt);
+ if (err)
+ goto out_mknod_dput;
+ err = vfs_mknod(nd.path.dentry->d_inode, dentry, mode, 0);
+ mnt_drop_write(nd.path.mnt);
if (err)
goto out_mknod_dput;
- mutex_unlock(&nd.dentry->d_inode->i_mutex);
- dput(nd.dentry);
- nd.dentry = dentry;
+ mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
+ dput(nd.path.dentry);
+ nd.path.dentry = dentry;
addr->hash = UNIX_HASH_SIZE;
}
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;
list = &unix_socket_table[addr->hash];
} else {
list = &unix_socket_table[dentry->d_inode->i_ino & (UNIX_HASH_SIZE-1)];
- u->dentry = nd.dentry;
- u->mnt = nd.mnt;
+ u->dentry = nd.path.dentry;
+ u->mnt = nd.path.mnt;
}
err = 0;
out_mknod_dput:
dput(dentry);
out_mknod_unlock:
- mutex_unlock(&nd.dentry->d_inode->i_mutex);
- path_release(&nd);
+ mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
+ path_put(&nd.path);
out_mknod_parent:
if (err==-EEXIST)
err=-EADDRINUSE;
int alen, int flags)
{
struct sock *sk = sock->sk;
+ struct net *net = sock_net(sk);
struct sockaddr_un *sunaddr=(struct sockaddr_un*)addr;
struct sock *other;
unsigned hash;
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;
sched = !sock_flag(other, SOCK_DEAD) &&
!(other->sk_shutdown & RCV_SHUTDOWN) &&
- (skb_queue_len(&other->sk_receive_queue) >
- other->sk_max_ack_backlog);
+ unix_recvq_full(other);
unix_state_unlock(other);
{
struct sockaddr_un *sunaddr=(struct sockaddr_un *)uaddr;
struct sock *sk = sock->sk;
+ struct net *net = sock_net(sk);
struct unix_sock *u = unix_sk(sk), *newu, *otheru;
struct sock *newsk = NULL;
struct sock *other = NULL;
err = -ENOMEM;
/* create new sock for complete connection */
- newsk = unix_create1(sk->sk_net, NULL);
+ newsk = unix_create1(sock_net(sk), NULL);
if (newsk == NULL)
goto out;
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;
if (other->sk_state != TCP_LISTEN)
goto out_unlock;
- if (skb_queue_len(&other->sk_receive_queue) >
- other->sk_max_ack_backlog) {
+ if (unix_recvq_full(other)) {
err = -EAGAIN;
if (!timeo)
goto out_unlock;
{
struct sock_iocb *siocb = kiocb_to_siocb(kiocb);
struct sock *sk = sock->sk;
+ struct net *net = sock_net(sk);
struct unix_sock *u = unix_sk(sk);
struct sockaddr_un *sunaddr=msg->msg_name;
struct sock *other = NULL;
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;
goto out_unlock;
}
- if (unix_peer(other) != sk &&
- (skb_queue_len(&other->sk_receive_queue) >
- other->sk_max_ack_backlog)) {
+ if (unix_peer(other) != sk && unix_recvq_full(other)) {
if (!timeo) {
err = -EAGAIN;
goto out_unlock;
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)
return mask;
}
+static unsigned int unix_datagram_poll(struct file *file, struct socket *sock,
+ poll_table *wait)
+{
+ struct sock *sk = sock->sk, *peer;
+ unsigned int mask;
+
+ poll_wait(file, sk->sk_sleep, wait);
+
+ peer = unix_peer_get(sk);
+ if (peer) {
+ if (peer != sk) {
+ /*
+ * Writability of a connected socket additionally
+ * depends on the state of the receive queue of the
+ * peer.
+ */
+ poll_wait(file, &unix_sk(peer)->peer_wait, wait);
+ } else {
+ sock_put(peer);
+ peer = NULL;
+ }
+ }
+
+ mask = 0;
+
+ /* exceptional events? */
+ if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
+ mask |= POLLERR;
+ if (sk->sk_shutdown & RCV_SHUTDOWN)
+ mask |= POLLRDHUP;
+ if (sk->sk_shutdown == SHUTDOWN_MASK)
+ mask |= POLLHUP;
+
+ /* readable? */
+ if (!skb_queue_empty(&sk->sk_receive_queue) ||
+ (sk->sk_shutdown & RCV_SHUTDOWN))
+ mask |= POLLIN | POLLRDNORM;
+
+ /* Connection-based need to check for termination and startup */
+ if (sk->sk_type == SOCK_SEQPACKET) {
+ if (sk->sk_state == TCP_CLOSE)
+ mask |= POLLHUP;
+ /* connection hasn't started yet? */
+ if (sk->sk_state == TCP_SYN_SENT)
+ return mask;
+ }
+
+ /* writable? */
+ if (unix_writable(sk) && !(peer && unix_recvq_full(peer)))
+ mask |= POLLOUT | POLLWRNORM | POLLWRBAND;
+ else
+ set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+
+ if (peer)
+ sock_put(peer);
+
+ return mask;
+}
#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 seq_file *seq, loff_t pos)
+{
+ struct unix_iter_state *iter = seq->private;
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 (sock_net(s) != seq_file_net(seq))
+ continue;
if (off == pos)
return s;
++off;
static void *unix_seq_start(struct seq_file *seq, loff_t *pos)
+ __acquires(unix_table_lock)
{
spin_lock(&unix_table_lock);
- return *pos ? unix_seq_idx(seq->private, *pos - 1) : ((void *) 1);
+ return *pos ? unix_seq_idx(seq, *pos - 1) : SEQ_START_TOKEN;
}
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);
+ if (v == SEQ_START_TOKEN)
+ sk = first_unix_socket(&iter->i);
+ else
+ sk = next_unix_socket(&iter->i, sk);
+ while (sk && (sock_net(sk) != seq_file_net(seq)))
+ 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);
}
static int unix_seq_show(struct seq_file *seq, void *v)
{
- if (v == (void *)1)
+ if (v == SEQ_START_TOKEN)
seq_puts(seq, "Num RefCount Protocol Flags Type St "
"Inode Path\n");
else {
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 = {
.open = unix_seq_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = seq_release_private,
+ .release = seq_release_net,
};
#endif
.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;
rc = proto_register(&unix_proto, 1);
if (rc != 0) {
printk(KERN_CRIT "%s: Cannot create unix_sock SLAB cache!\n",
- __FUNCTION__);
+ __func__);
goto out;
}
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;
}
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);
+/* Earlier than device_initcall() so that other drivers invoking
+ request_module() don't end up in a loop when modprobe tries
+ to use a UNIX socket. But later than subsys_initcall() because
+ we depend on stuff initialised there */
+fs_initcall(af_unix_init);
module_exit(af_unix_exit);
MODULE_LICENSE("GPL");