aboutsummaryrefslogtreecommitdiff
path: root/net/unix
diff options
context:
space:
mode:
Diffstat (limited to 'net/unix')
-rw-r--r--net/unix/Kconfig7
-rw-r--r--net/unix/Makefile3
-rw-r--r--net/unix/af_unix.c768
-rw-r--r--net/unix/diag.c327
-rw-r--r--net/unix/garbage.c25
-rw-r--r--net/unix/sysctl_net_unix.c16
6 files changed, 821 insertions, 325 deletions
diff --git a/net/unix/Kconfig b/net/unix/Kconfig
index 5a69733bcda..8b31ab85d05 100644
--- a/net/unix/Kconfig
+++ b/net/unix/Kconfig
@@ -19,3 +19,10 @@ config UNIX
Say Y unless you know what you are doing.
+config UNIX_DIAG
+ tristate "UNIX: socket monitoring interface"
+ depends on UNIX
+ default n
+ ---help---
+ Support for UNIX socket monitoring interface used by the ss tool.
+ If unsure, say Y.
diff --git a/net/unix/Makefile b/net/unix/Makefile
index b852a2bde9a..b663c607b1c 100644
--- a/net/unix/Makefile
+++ b/net/unix/Makefile
@@ -6,3 +6,6 @@ obj-$(CONFIG_UNIX) += unix.o
unix-y := af_unix.o garbage.o
unix-$(CONFIG_SYSCTL) += sysctl_net_unix.o
+
+obj-$(CONFIG_UNIX_DIAG) += unix_diag.o
+unix_diag-y := diag.o
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 7ff31c60186..e9688438073 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -80,6 +80,8 @@
* with BSD names.
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/signal.h>
@@ -114,14 +116,26 @@
#include <linux/mount.h>
#include <net/checksum.h>
#include <linux/security.h>
+#include <linux/freezer.h>
-static struct hlist_head unix_socket_table[UNIX_HASH_SIZE + 1];
-static DEFINE_SPINLOCK(unix_table_lock);
+struct hlist_head unix_socket_table[2 * UNIX_HASH_SIZE];
+EXPORT_SYMBOL_GPL(unix_socket_table);
+DEFINE_SPINLOCK(unix_table_lock);
+EXPORT_SYMBOL_GPL(unix_table_lock);
static atomic_long_t unix_nr_socks;
-#define unix_sockets_unbound (&unix_socket_table[UNIX_HASH_SIZE])
-#define UNIX_ABSTRACT(sk) (unix_sk(sk)->addr->hash != UNIX_HASH_SIZE)
+static struct hlist_head *unix_sockets_unbound(void *addr)
+{
+ unsigned long hash = (unsigned long)addr;
+
+ hash ^= hash >> 16;
+ hash ^= hash >> 8;
+ hash %= UNIX_HASH_SIZE;
+ return &unix_socket_table[UNIX_HASH_SIZE + hash];
+}
+
+#define UNIX_ABSTRACT(sk) (unix_sk(sk)->addr->hash < UNIX_HASH_SIZE)
#ifdef CONFIG_SECURITY_NETWORK
static void unix_get_secdata(struct scm_cookie *scm, struct sk_buff *skb)
@@ -147,10 +161,10 @@ static inline void unix_set_secdata(struct scm_cookie *scm, struct sk_buff *skb)
* each socket state is protected by separate spin lock.
*/
-static inline unsigned unix_hash_fold(__wsum n)
+static inline unsigned int unix_hash_fold(__wsum n)
{
- unsigned hash = (__force unsigned)n;
- hash ^= hash>>16;
+ unsigned int hash = (__force unsigned int)csum_fold(n);
+
hash ^= hash>>8;
return hash&(UNIX_HASH_SIZE-1);
}
@@ -172,7 +186,7 @@ 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 *unix_peer_get(struct sock *s)
{
struct sock *peer;
@@ -183,6 +197,7 @@ static struct sock *unix_peer_get(struct sock *s)
unix_state_unlock(s);
return peer;
}
+EXPORT_SYMBOL_GPL(unix_peer_get);
static inline void unix_release_addr(struct unix_address *addr)
{
@@ -197,7 +212,7 @@ static inline void unix_release_addr(struct unix_address *addr)
* - if started by zero, it is abstract name.
*/
-static int unix_mkname(struct sockaddr_un *sunaddr, int len, unsigned *hashp)
+static int unix_mkname(struct sockaddr_un *sunaddr, int len, unsigned int *hashp)
{
if (len <= sizeof(short) || len > sizeof(*sunaddr))
return -EINVAL;
@@ -207,7 +222,7 @@ static int unix_mkname(struct sockaddr_un *sunaddr, int len, unsigned *hashp)
/*
* This may look like an off by one error but it is a bit more
* subtle. 108 is the longest valid AF_UNIX path for a binding.
- * sun_path[108] doesnt as such exist. However in kernel space
+ * sun_path[108] doesn't as such exist. However in kernel space
* we are guaranteed that it is a valid memory location in our
* kernel address buffer.
*/
@@ -247,12 +262,11 @@ static inline void unix_insert_socket(struct hlist_head *list, struct sock *sk)
static struct sock *__unix_find_socket_byname(struct net *net,
struct sockaddr_un *sunname,
- int len, int type, unsigned hash)
+ int len, int type, unsigned int hash)
{
struct sock *s;
- struct hlist_node *node;
- sk_for_each(s, node, &unix_socket_table[hash ^ type]) {
+ sk_for_each(s, &unix_socket_table[hash ^ type]) {
struct unix_sock *u = unix_sk(s);
if (!net_eq(sock_net(s), net))
@@ -270,7 +284,7 @@ found:
static inline struct sock *unix_find_socket_byname(struct net *net,
struct sockaddr_un *sunname,
int len, int type,
- unsigned hash)
+ unsigned int hash)
{
struct sock *s;
@@ -285,12 +299,11 @@ static inline struct sock *unix_find_socket_byname(struct net *net,
static struct sock *unix_find_socket_byinode(struct inode *i)
{
struct sock *s;
- struct hlist_node *node;
spin_lock(&unix_table_lock);
- sk_for_each(s, node,
+ sk_for_each(s,
&unix_socket_table[i->i_ino & (UNIX_HASH_SIZE - 1)]) {
- struct dentry *dentry = unix_sk(s)->dentry;
+ struct dentry *dentry = unix_sk(s)->path.dentry;
if (dentry && dentry->d_inode == i) {
sock_hold(s);
@@ -354,7 +367,7 @@ static void unix_sock_destructor(struct sock *sk)
WARN_ON(!sk_unhashed(sk));
WARN_ON(sk->sk_socket);
if (!sock_flag(sk, SOCK_DEAD)) {
- printk(KERN_INFO "Attempt to release alive unix socket: %p\n", sk);
+ pr_info("Attempt to release alive unix socket: %p\n", sk);
return;
}
@@ -366,16 +379,15 @@ static void unix_sock_destructor(struct sock *sk)
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
local_bh_enable();
#ifdef UNIX_REFCNT_DEBUG
- printk(KERN_DEBUG "UNIX %p is destroyed, %ld are still alive.\n", sk,
+ pr_debug("UNIX %p is destroyed, %ld are still alive.\n", sk,
atomic_long_read(&unix_nr_socks));
#endif
}
-static int unix_release_sock(struct sock *sk, int embrion)
+static void unix_release_sock(struct sock *sk, int embrion)
{
struct unix_sock *u = unix_sk(sk);
- struct dentry *dentry;
- struct vfsmount *mnt;
+ struct path path;
struct sock *skpair;
struct sk_buff *skb;
int state;
@@ -386,10 +398,9 @@ static int unix_release_sock(struct sock *sk, int embrion)
unix_state_lock(sk);
sock_orphan(sk);
sk->sk_shutdown = SHUTDOWN_MASK;
- dentry = u->dentry;
- u->dentry = NULL;
- mnt = u->mnt;
- u->mnt = NULL;
+ path = u->path;
+ u->path.dentry = NULL;
+ u->path.mnt = NULL;
state = sk->sk_state;
sk->sk_state = TCP_CLOSE;
unix_state_unlock(sk);
@@ -422,17 +433,15 @@ static int unix_release_sock(struct sock *sk, int embrion)
kfree_skb(skb);
}
- if (dentry) {
- dput(dentry);
- mntput(mnt);
- }
+ if (path.dentry)
+ path_put(&path);
sock_put(sk);
/* ---- Socket is dead now and most probably destroyed ---- */
/*
- * Fixme: BSD difference: In BSD all sockets connected to use get
+ * Fixme: BSD difference: In BSD all sockets connected to us get
* ECONNRESET and we die on the spot. In Linux we behave
* like files and pipes do and wait for the last
* dereference.
@@ -444,8 +453,6 @@ static int unix_release_sock(struct sock *sk, int embrion)
if (unix_tot_inflight)
unix_gc(); /* Garbage collect fds */
-
- return 0;
}
static void init_peercred(struct sock *sk)
@@ -472,7 +479,6 @@ static int unix_listen(struct socket *sock, int backlog)
struct sock *sk = sock->sk;
struct unix_sock *u = unix_sk(sk);
struct pid *old_pid = NULL;
- const struct cred *old_cred = NULL;
err = -EOPNOTSUPP;
if (sock->type != SOCK_STREAM && sock->type != SOCK_SEQPACKET)
@@ -494,8 +500,6 @@ static int unix_listen(struct socket *sock, int backlog)
out_unlock:
unix_state_unlock(sk);
put_pid(old_pid);
- if (old_cred)
- put_cred(old_cred);
out:
return err;
}
@@ -524,6 +528,22 @@ static int unix_dgram_connect(struct socket *, struct sockaddr *,
int, int);
static int unix_seqpacket_sendmsg(struct kiocb *, struct socket *,
struct msghdr *, size_t);
+static int unix_seqpacket_recvmsg(struct kiocb *, struct socket *,
+ struct msghdr *, size_t, int);
+
+static int unix_set_peek_off(struct sock *sk, int val)
+{
+ struct unix_sock *u = unix_sk(sk);
+
+ if (mutex_lock_interruptible(&u->readlock))
+ return -EINTR;
+
+ sk->sk_peek_off = val;
+ mutex_unlock(&u->readlock);
+
+ return 0;
+}
+
static const struct proto_ops unix_stream_ops = {
.family = PF_UNIX,
@@ -544,6 +564,7 @@ static const struct proto_ops unix_stream_ops = {
.recvmsg = unix_stream_recvmsg,
.mmap = sock_no_mmap,
.sendpage = sock_no_sendpage,
+ .set_peek_off = unix_set_peek_off,
};
static const struct proto_ops unix_dgram_ops = {
@@ -565,6 +586,7 @@ static const struct proto_ops unix_dgram_ops = {
.recvmsg = unix_dgram_recvmsg,
.mmap = sock_no_mmap,
.sendpage = sock_no_sendpage,
+ .set_peek_off = unix_set_peek_off,
};
static const struct proto_ops unix_seqpacket_ops = {
@@ -583,9 +605,10 @@ static const struct proto_ops unix_seqpacket_ops = {
.setsockopt = sock_no_setsockopt,
.getsockopt = sock_no_getsockopt,
.sendmsg = unix_seqpacket_sendmsg,
- .recvmsg = unix_dgram_recvmsg,
+ .recvmsg = unix_seqpacket_recvmsg,
.mmap = sock_no_mmap,
.sendpage = sock_no_sendpage,
+ .set_peek_off = unix_set_peek_off,
};
static struct proto unix_proto = {
@@ -623,14 +646,14 @@ static struct sock *unix_create1(struct net *net, struct socket *sock)
sk->sk_max_ack_backlog = net->unx.sysctl_max_dgram_qlen;
sk->sk_destruct = unix_sock_destructor;
u = unix_sk(sk);
- u->dentry = NULL;
- u->mnt = NULL;
+ u->path.dentry = NULL;
+ u->path.mnt = NULL;
spin_lock_init(&u->lock);
atomic_long_set(&u->inflight, 0);
INIT_LIST_HEAD(&u->link);
mutex_init(&u->readlock); /* single task reading lock */
init_waitqueue_head(&u->peer_wait);
- unix_insert_socket(unix_sockets_unbound, sk);
+ unix_insert_socket(unix_sockets_unbound(sk), sk);
out:
if (sk == NULL)
atomic_long_dec(&unix_nr_socks);
@@ -680,9 +703,10 @@ static int unix_release(struct socket *sock)
if (!sk)
return 0;
+ unix_release_sock(sk, 0);
sock->sk = NULL;
- return unix_release_sock(sk, 0);
+ return 0;
}
static int unix_autobind(struct socket *sock)
@@ -695,7 +719,9 @@ static int unix_autobind(struct socket *sock)
int err;
unsigned int retries = 0;
- mutex_lock(&u->readlock);
+ err = mutex_lock_interruptible(&u->readlock);
+ if (err)
+ return err;
err = 0;
if (u->addr)
@@ -746,7 +772,7 @@ out: mutex_unlock(&u->readlock);
static struct sock *unix_find_other(struct net *net,
struct sockaddr_un *sunname, int len,
- int type, unsigned hash, int *error)
+ int type, unsigned int hash, int *error)
{
struct sock *u;
struct path path;
@@ -770,7 +796,7 @@ static struct sock *unix_find_other(struct net *net,
goto put_fail;
if (u->sk_type == type)
- touch_atime(path.mnt, path.dentry);
+ touch_atime(&path);
path_put(&path);
@@ -784,9 +810,9 @@ static struct sock *unix_find_other(struct net *net,
u = unix_find_socket_byname(net, sunname, len, type, hash);
if (u) {
struct dentry *dentry;
- dentry = unix_sk(u)->dentry;
+ dentry = unix_sk(u)->path.dentry;
if (dentry)
- touch_atime(unix_sk(u)->mnt, dentry);
+ touch_atime(&unix_sk(u)->path);
} else
goto fail;
}
@@ -799,6 +825,34 @@ fail:
return NULL;
}
+static int unix_mknod(const char *sun_path, umode_t mode, struct path *res)
+{
+ struct dentry *dentry;
+ struct path path;
+ int err = 0;
+ /*
+ * Get the parent directory, calculate the hash for last
+ * component.
+ */
+ dentry = kern_path_create(AT_FDCWD, sun_path, &path, 0);
+ err = PTR_ERR(dentry);
+ if (IS_ERR(dentry))
+ return err;
+
+ /*
+ * All right, let's create it.
+ */
+ err = security_path_mknod(&path, dentry, mode, 0);
+ if (!err) {
+ err = vfs_mknod(path.dentry->d_inode, dentry, mode, 0);
+ if (!err) {
+ res->mnt = mntget(path.mnt);
+ res->dentry = dget(dentry);
+ }
+ }
+ done_path_create(&path, dentry);
+ return err;
+}
static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
{
@@ -806,10 +860,9 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
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;
- struct nameidata nd;
+ char *sun_path = sunaddr->sun_path;
int err;
- unsigned hash;
+ unsigned int hash;
struct unix_address *addr;
struct hlist_head *list;
@@ -827,7 +880,9 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
goto out;
addr_len = err;
- mutex_lock(&u->readlock);
+ err = mutex_lock_interruptible(&u->readlock);
+ if (err)
+ goto out;
err = -EINVAL;
if (u->addr)
@@ -843,48 +898,24 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
addr->hash = hash ^ sk->sk_type;
atomic_set(&addr->refcnt, 1);
- if (sunaddr->sun_path[0]) {
- unsigned int mode;
- err = 0;
- /*
- * Get the parent directory, calculate the hash for last
- * component.
- */
- err = path_lookup(sunaddr->sun_path, LOOKUP_PARENT, &nd);
- if (err)
- goto out_mknod_parent;
-
- dentry = lookup_create(&nd, 0);
- err = PTR_ERR(dentry);
- if (IS_ERR(dentry))
- goto out_mknod_unlock;
-
- /*
- * All right, let's create it.
- */
- mode = S_IFSOCK |
+ if (sun_path[0]) {
+ struct path path;
+ umode_t mode = S_IFSOCK |
(SOCK_INODE(sock)->i_mode & ~current_umask());
- err = mnt_want_write(nd.path.mnt);
- if (err)
- goto out_mknod_dput;
- err = security_path_mknod(&nd.path, dentry, mode, 0);
- if (err)
- goto out_mknod_drop_write;
- err = vfs_mknod(nd.path.dentry->d_inode, dentry, mode, 0);
-out_mknod_drop_write:
- mnt_drop_write(nd.path.mnt);
- if (err)
- goto out_mknod_dput;
- mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
- dput(nd.path.dentry);
- nd.path.dentry = dentry;
-
+ err = unix_mknod(sun_path, mode, &path);
+ if (err) {
+ if (err == -EEXIST)
+ err = -EADDRINUSE;
+ unix_release_addr(addr);
+ goto out_up;
+ }
addr->hash = UNIX_HASH_SIZE;
- }
-
- spin_lock(&unix_table_lock);
-
- if (!sunaddr->sun_path[0]) {
+ hash = path.dentry->d_inode->i_ino & (UNIX_HASH_SIZE-1);
+ spin_lock(&unix_table_lock);
+ u->path = path;
+ list = &unix_socket_table[hash];
+ } else {
+ spin_lock(&unix_table_lock);
err = -EADDRINUSE;
if (__unix_find_socket_byname(net, sunaddr, addr_len,
sk->sk_type, hash)) {
@@ -893,10 +924,6 @@ out_mknod_drop_write:
}
list = &unix_socket_table[addr->hash];
- } else {
- list = &unix_socket_table[dentry->d_inode->i_ino & (UNIX_HASH_SIZE-1)];
- u->dentry = nd.path.dentry;
- u->mnt = nd.path.mnt;
}
err = 0;
@@ -910,17 +937,6 @@ out_up:
mutex_unlock(&u->readlock);
out:
return err;
-
-out_mknod_dput:
- dput(dentry);
-out_mknod_unlock:
- mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
- path_put(&nd.path);
-out_mknod_parent:
- if (err == -EEXIST)
- err = -EADDRINUSE;
- unix_release_addr(addr);
- goto out_up;
}
static void unix_state_double_lock(struct sock *sk1, struct sock *sk2)
@@ -955,7 +971,7 @@ static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr,
struct net *net = sock_net(sk);
struct sockaddr_un *sunaddr = (struct sockaddr_un *)addr;
struct sock *other;
- unsigned hash;
+ unsigned int hash;
int err;
if (addr->sa_family != AF_UNSPEC) {
@@ -1053,7 +1069,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
struct sock *newsk = NULL;
struct sock *other = NULL;
struct sk_buff *skb = NULL;
- unsigned hash;
+ unsigned int hash;
int st;
int err;
long timeo;
@@ -1124,7 +1140,7 @@ restart:
/* Latch our state.
- It is tricky place. We need to grab write lock and cannot
+ It is tricky place. We need to grab our state lock and cannot
drop lock on peer. It is dangerous because deadlock is
possible. Connect to self case and simultaneous
attempt to connect are eliminated by checking socket
@@ -1157,7 +1173,7 @@ restart:
goto restart;
}
- err = security_unix_stream_connect(sock, other->sk_socket, newsk);
+ err = security_unix_stream_connect(sk, other, newsk);
if (err) {
unix_state_unlock(sk);
goto out_unlock;
@@ -1171,7 +1187,7 @@ restart:
newsk->sk_type = sk->sk_type;
init_peercred(newsk);
newu = unix_sk(newsk);
- newsk->sk_wq = &newu->peer_wq;
+ RCU_INIT_POINTER(newsk->sk_wq, &newu->peer_wq);
otheru = unix_sk(other);
/* copy address information from listening to new sock*/
@@ -1179,9 +1195,9 @@ restart:
atomic_inc(&otheru->addr->refcnt);
newu->addr = otheru->addr;
}
- if (otheru->dentry) {
- newu->dentry = dget(otheru->dentry);
- newu->mnt = mntget(otheru->mnt);
+ if (otheru->path.dentry) {
+ path_get(&otheru->path);
+ newu->path = otheru->path;
}
/* Set credentials */
@@ -1191,7 +1207,7 @@ restart:
sk->sk_state = TCP_ESTABLISHED;
sock_hold(newsk);
- smp_mb__after_atomic_inc(); /* sock_hold() does an atomic_inc() */
+ smp_mb__after_atomic(); /* sock_hold() does an atomic_inc() */
unix_peer(sk) = newsk;
unix_state_unlock(sk);
@@ -1201,7 +1217,7 @@ restart:
__skb_queue_tail(&other->sk_receive_queue, skb);
spin_unlock(&other->sk_receive_queue.lock);
unix_state_unlock(other);
- other->sk_data_ready(other, 0);
+ other->sk_data_ready(other);
sock_put(other);
return 0;
@@ -1239,6 +1255,15 @@ static int unix_socketpair(struct socket *socka, struct socket *sockb)
return 0;
}
+static void unix_sock_inherit_flags(const struct socket *old,
+ struct socket *new)
+{
+ if (test_bit(SOCK_PASSCRED, &old->flags))
+ set_bit(SOCK_PASSCRED, &new->flags);
+ if (test_bit(SOCK_PASSSEC, &old->flags))
+ set_bit(SOCK_PASSSEC, &new->flags);
+}
+
static int unix_accept(struct socket *sock, struct socket *newsock, int flags)
{
struct sock *sk = sock->sk;
@@ -1273,6 +1298,7 @@ static int unix_accept(struct socket *sock, struct socket *newsock, int flags)
/* attach accepted sock to socket */
unix_state_lock(tsk);
newsock->state = SS_CONNECTED;
+ unix_sock_inherit_flags(sock, newsock);
sock_graft(tsk, newsock);
unix_state_unlock(tsk);
return 0;
@@ -1334,7 +1360,6 @@ static void unix_destruct_scm(struct sk_buff *skb)
struct scm_cookie scm;
memset(&scm, 0, sizeof(scm));
scm.pid = UNIXCB(skb).pid;
- scm.cred = UNIXCB(skb).cred;
if (UNIXCB(skb).fp)
unix_detach_fds(&scm, skb);
@@ -1344,9 +1369,25 @@ static void unix_destruct_scm(struct sk_buff *skb)
sock_wfree(skb);
}
+#define MAX_RECURSION_LEVEL 4
+
static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb)
{
int i;
+ unsigned char max_level = 0;
+ int unix_sock_count = 0;
+
+ for (i = scm->fp->count - 1; i >= 0; i--) {
+ struct sock *sk = unix_get_socket(scm->fp->fp[i]);
+
+ if (sk) {
+ unix_sock_count++;
+ max_level = max(max_level,
+ unix_sk(sk)->recursion_level);
+ }
+ }
+ if (unlikely(max_level > MAX_RECURSION_LEVEL))
+ return -ETOOMANYREFS;
/*
* Need to duplicate file references for the sake of garbage
@@ -1357,16 +1398,20 @@ static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb)
if (!UNIXCB(skb).fp)
return -ENOMEM;
- for (i = scm->fp->count-1; i >= 0; i--)
- unix_inflight(scm->fp->fp[i]);
- return 0;
+ if (unix_sock_count) {
+ for (i = scm->fp->count - 1; i >= 0; i--)
+ unix_inflight(scm->fp->fp[i]);
+ }
+ return max_level;
}
static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool send_fds)
{
int err = 0;
+
UNIXCB(skb).pid = get_pid(scm->pid);
- UNIXCB(skb).cred = get_cred(scm->cred);
+ UNIXCB(skb).uid = scm->creds.uid;
+ UNIXCB(skb).gid = scm->creds.gid;
UNIXCB(skb).fp = NULL;
if (scm->fp && send_fds)
err = unix_attach_fds(scm, skb);
@@ -1376,6 +1421,24 @@ static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool sen
}
/*
+ * Some apps rely on write() giving SCM_CREDENTIALS
+ * We include credentials if source or destination socket
+ * asserted SOCK_PASSCRED.
+ */
+static void maybe_add_creds(struct sk_buff *skb, const struct socket *sock,
+ const struct sock *other)
+{
+ if (UNIXCB(skb).pid)
+ return;
+ if (test_bit(SOCK_PASSCRED, &sock->flags) ||
+ !other->sk_socket ||
+ test_bit(SOCK_PASSCRED, &other->sk_socket->flags)) {
+ UNIXCB(skb).pid = get_pid(task_tgid(current));
+ current_uid_gid(&UNIXCB(skb).uid, &UNIXCB(skb).gid);
+ }
+}
+
+/*
* Send AF_UNIX data.
*/
@@ -1386,19 +1449,21 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock,
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;
+ DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr, msg->msg_name);
struct sock *other = NULL;
int namelen = 0; /* fake GCC */
int err;
- unsigned hash;
+ unsigned int hash;
struct sk_buff *skb;
long timeo;
struct scm_cookie tmp_scm;
+ int max_level;
+ int data_len = 0;
if (NULL == siocb->scm)
siocb->scm = &tmp_scm;
wait_for_unix_gc();
- err = scm_send(sock, msg, siocb->scm);
+ err = scm_send(sock, msg, siocb->scm, false);
if (err < 0)
return err;
@@ -1427,17 +1492,31 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock,
if (len > sk->sk_sndbuf - 32)
goto out;
- skb = sock_alloc_send_skb(sk, len, msg->msg_flags&MSG_DONTWAIT, &err);
+ if (len > SKB_MAX_ALLOC) {
+ data_len = min_t(size_t,
+ len - SKB_MAX_ALLOC,
+ MAX_SKB_FRAGS * PAGE_SIZE);
+ data_len = PAGE_ALIGN(data_len);
+
+ BUILD_BUG_ON(SKB_MAX_ALLOC < PAGE_SIZE);
+ }
+
+ skb = sock_alloc_send_pskb(sk, len - data_len, data_len,
+ msg->msg_flags & MSG_DONTWAIT, &err,
+ PAGE_ALLOC_COSTLY_ORDER);
if (skb == NULL)
goto out;
err = unix_scm_to_skb(siocb->scm, skb, true);
- if (err)
+ if (err < 0)
goto out_free;
+ max_level = err + 1;
unix_get_secdata(siocb->scm, skb);
- skb_reset_transport_header(skb);
- err = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len);
+ skb_put(skb, len - data_len);
+ skb->data_len = data_len;
+ skb->len = len;
+ err = skb_copy_datagram_from_iovec(skb, 0, msg->msg_iov, 0, len);
if (err)
goto out_free;
@@ -1455,6 +1534,12 @@ restart:
goto out_free;
}
+ if (sk_filter(other, skb) < 0) {
+ /* Toss the packet but do not return any error to the sender */
+ err = len;
+ goto out_free;
+ }
+
unix_state_lock(other);
err = -EPERM;
if (!unix_may_send(sk, other))
@@ -1514,9 +1599,12 @@ restart:
if (sock_flag(other, SOCK_RCVTSTAMP))
__net_timestamp(skb);
+ maybe_add_creds(skb, sock, other);
skb_queue_tail(&other->sk_receive_queue, skb);
+ if (max_level > unix_sk(other)->recursion_level)
+ unix_sk(other)->recursion_level = max_level;
unix_state_unlock(other);
- other->sk_data_ready(other, len);
+ other->sk_data_ready(other);
sock_put(other);
scm_destroy(siocb->scm);
return len;
@@ -1532,6 +1620,10 @@ out:
return err;
}
+/* We use paged skbs for stream sockets, and limit occupancy to 32768
+ * bytes, and a minimun of a full page.
+ */
+#define UNIX_SKB_FRAGS_SZ (PAGE_SIZE << get_order(32768))
static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
struct msghdr *msg, size_t len)
@@ -1539,17 +1631,18 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
struct sock_iocb *siocb = kiocb_to_siocb(kiocb);
struct sock *sk = sock->sk;
struct sock *other = NULL;
- struct sockaddr_un *sunaddr = msg->msg_name;
int err, size;
struct sk_buff *skb;
int sent = 0;
struct scm_cookie tmp_scm;
bool fds_sent = false;
+ int max_level;
+ int data_len;
if (NULL == siocb->scm)
siocb->scm = &tmp_scm;
wait_for_unix_gc();
- err = scm_send(sock, msg, siocb->scm);
+ err = scm_send(sock, msg, siocb->scm, false);
if (err < 0)
return err;
@@ -1561,7 +1654,6 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
err = sk->sk_state == TCP_ESTABLISHED ? -EISCONN : -EOPNOTSUPP;
goto out_err;
} else {
- sunaddr = NULL;
err = -ENOTCONN;
other = unix_peer(sk);
if (!other)
@@ -1572,49 +1664,38 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
goto pipe_err;
while (sent < len) {
- /*
- * Optimisation for the fact that under 0.01% of X
- * messages typically need breaking up.
- */
-
- size = len-sent;
+ size = len - sent;
/* Keep two messages in the pipe so it schedules better */
- if (size > ((sk->sk_sndbuf >> 1) - 64))
- size = (sk->sk_sndbuf >> 1) - 64;
+ size = min_t(int, size, (sk->sk_sndbuf >> 1) - 64);
- if (size > SKB_MAX_ALLOC)
- size = SKB_MAX_ALLOC;
+ /* allow fallback to order-0 allocations */
+ size = min_t(int, size, SKB_MAX_HEAD(0) + UNIX_SKB_FRAGS_SZ);
- /*
- * Grab a buffer
- */
+ data_len = max_t(int, 0, size - SKB_MAX_HEAD(0));
- skb = sock_alloc_send_skb(sk, size, msg->msg_flags&MSG_DONTWAIT,
- &err);
+ data_len = min_t(size_t, size, PAGE_ALIGN(data_len));
- if (skb == NULL)
+ skb = sock_alloc_send_pskb(sk, size - data_len, data_len,
+ msg->msg_flags & MSG_DONTWAIT, &err,
+ get_order(UNIX_SKB_FRAGS_SZ));
+ if (!skb)
goto out_err;
- /*
- * If you pass two values to the sock_alloc_send_skb
- * it tries to grab the large buffer with GFP_NOFS
- * (which can fail easily), and if it fails grab the
- * fallback size buffer which is under a page and will
- * succeed. [Alan]
- */
- size = min_t(int, size, skb_tailroom(skb));
-
-
/* Only send the fds in the first buffer */
err = unix_scm_to_skb(siocb->scm, skb, !fds_sent);
- if (err) {
+ if (err < 0) {
kfree_skb(skb);
goto out_err;
}
+ max_level = err + 1;
fds_sent = true;
- err = memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size);
+ skb_put(skb, size - data_len);
+ skb->data_len = data_len;
+ skb->len = size;
+ err = skb_copy_datagram_from_iovec(skb, 0, msg->msg_iov,
+ sent, size);
if (err) {
kfree_skb(skb);
goto out_err;
@@ -1626,9 +1707,12 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
(other->sk_shutdown & RCV_SHUTDOWN))
goto pipe_err_free;
+ maybe_add_creds(skb, sock, other);
skb_queue_tail(&other->sk_receive_queue, skb);
+ if (max_level > unix_sk(other)->recursion_level)
+ unix_sk(other)->recursion_level = max_level;
unix_state_unlock(other);
- other->sk_data_ready(other, size);
+ other->sk_data_ready(other);
sent += size;
}
@@ -1669,11 +1753,22 @@ static int unix_seqpacket_sendmsg(struct kiocb *kiocb, struct socket *sock,
return unix_dgram_sendmsg(kiocb, sock, msg, len);
}
+static int unix_seqpacket_recvmsg(struct kiocb *iocb, struct socket *sock,
+ struct msghdr *msg, size_t size,
+ int flags)
+{
+ struct sock *sk = sock->sk;
+
+ if (sk->sk_state != TCP_ESTABLISHED)
+ return -ENOTCONN;
+
+ return unix_dgram_recvmsg(iocb, sock, msg, size, flags);
+}
+
static void unix_copy_addr(struct msghdr *msg, struct sock *sk)
{
struct unix_sock *u = unix_sk(sk);
- msg->msg_namelen = 0;
if (u->addr) {
msg->msg_namelen = u->addr->len;
memcpy(msg->msg_name, u->addr->name, u->addr->len);
@@ -1691,16 +1786,24 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock,
int noblock = flags & MSG_DONTWAIT;
struct sk_buff *skb;
int err;
+ int peeked, skip;
err = -EOPNOTSUPP;
if (flags&MSG_OOB)
goto out;
- msg->msg_namelen = 0;
+ err = mutex_lock_interruptible(&u->readlock);
+ if (unlikely(err)) {
+ /* recvmsg() in non blocking mode is supposed to return -EAGAIN
+ * sk_rcvtimeo is not honored by mutex_lock_interruptible()
+ */
+ err = noblock ? -EAGAIN : -ERESTARTSYS;
+ goto out;
+ }
- mutex_lock(&u->readlock);
+ skip = sk_peek_offset(sk, flags);
- skb = skb_recv_datagram(sk, flags, noblock, &err);
+ skb = __skb_recv_datagram(sk, flags, &peeked, &skip, &err);
if (!skb) {
unix_state_lock(sk);
/* Signal EOF on disconnected non-blocking SEQPACKET socket. */
@@ -1717,12 +1820,12 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock,
if (msg->msg_name)
unix_copy_addr(msg, skb->sk);
- if (size > skb->len)
- size = skb->len;
- else if (size < skb->len)
+ if (size > skb->len - skip)
+ size = skb->len - skip;
+ else if (size < skb->len - skip)
msg->msg_flags |= MSG_TRUNC;
- err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, size);
+ err = skb_copy_datagram_iovec(skb, skip, msg->msg_iov, size);
if (err)
goto out_free;
@@ -1733,12 +1836,14 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock,
siocb->scm = &tmp_scm;
memset(&tmp_scm, 0, sizeof(tmp_scm));
}
- scm_set_cred(siocb->scm, UNIXCB(skb).pid, UNIXCB(skb).cred);
+ scm_set_cred(siocb->scm, UNIXCB(skb).pid, UNIXCB(skb).uid, UNIXCB(skb).gid);
unix_set_secdata(siocb->scm, skb);
if (!(flags & MSG_PEEK)) {
if (UNIXCB(skb).fp)
unix_detach_fds(siocb->scm, skb);
+
+ sk_peek_offset_bwd(sk, skb->len);
} else {
/* It is questionable: on PEEK we could:
- do not return fds - good, but too simple 8)
@@ -1752,10 +1857,13 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock,
clearly however!
*/
+
+ sk_peek_offset_fwd(sk, size);
+
if (UNIXCB(skb).fp)
siocb->scm->fp = scm_fp_dup(UNIXCB(skb).fp);
}
- err = size;
+ err = (flags & MSG_TRUNC) ? skb->len - skip : size;
scm_recv(sock, msg, siocb->scm, flags);
@@ -1768,10 +1876,10 @@ out:
}
/*
- * Sleep until data has arrive. But check for races..
+ * Sleep until more data has arrived. But check for races..
*/
-
-static long unix_stream_data_wait(struct sock *sk, long timeo)
+static long unix_stream_data_wait(struct sock *sk, long timeo,
+ struct sk_buff *last)
{
DEFINE_WAIT(wait);
@@ -1780,7 +1888,7 @@ static long unix_stream_data_wait(struct sock *sk, long timeo)
for (;;) {
prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
- if (!skb_queue_empty(&sk->sk_receive_queue) ||
+ if (skb_peek_tail(&sk->sk_receive_queue) != last ||
sk->sk_err ||
(sk->sk_shutdown & RCV_SHUTDOWN) ||
signal_pending(current) ||
@@ -1789,7 +1897,7 @@ static long unix_stream_data_wait(struct sock *sk, long timeo)
set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
unix_state_unlock(sk);
- timeo = schedule_timeout(timeo);
+ timeo = freezable_schedule_timeout(timeo);
unix_state_lock(sk);
clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
}
@@ -1799,7 +1907,10 @@ static long unix_stream_data_wait(struct sock *sk, long timeo)
return timeo;
}
-
+static unsigned int unix_skb_len(const struct sk_buff *skb)
+{
+ return skb->len - UNIXCB(skb).consumed;
+}
static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
struct msghdr *msg, size_t size,
@@ -1809,12 +1920,14 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
struct scm_cookie tmp_scm;
struct sock *sk = sock->sk;
struct unix_sock *u = unix_sk(sk);
- struct sockaddr_un *sunaddr = msg->msg_name;
+ DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr, msg->msg_name);
int copied = 0;
+ int noblock = flags & MSG_DONTWAIT;
int check_creds = 0;
int target;
int err = 0;
long timeo;
+ int skip;
err = -EINVAL;
if (sk->sk_state != TCP_ESTABLISHED)
@@ -1825,9 +1938,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
goto out;
target = sock_rcvlowat(sk, flags&MSG_WAITALL, size);
- timeo = sock_rcvtimeo(sk, flags&MSG_DONTWAIT);
-
- msg->msg_namelen = 0;
+ timeo = sock_rcvtimeo(sk, noblock);
/* Lock the socket to prevent queue disordering
* while sleeps in memcpy_tomsg
@@ -1838,15 +1949,24 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
memset(&tmp_scm, 0, sizeof(tmp_scm));
}
- mutex_lock(&u->readlock);
+ err = mutex_lock_interruptible(&u->readlock);
+ if (unlikely(err)) {
+ /* recvmsg() in non blocking mode is supposed to return -EAGAIN
+ * sk_rcvtimeo is not honored by mutex_lock_interruptible()
+ */
+ err = noblock ? -EAGAIN : -ERESTARTSYS;
+ goto out;
+ }
do {
int chunk;
- struct sk_buff *skb;
+ struct sk_buff *skb, *last;
unix_state_lock(sk);
- skb = skb_dequeue(&sk->sk_receive_queue);
+ last = skb = skb_peek(&sk->sk_receive_queue);
+again:
if (skb == NULL) {
+ unix_sk(sk)->recursion_level = 0;
if (copied >= target)
goto unlock;
@@ -1866,30 +1986,40 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
break;
mutex_unlock(&u->readlock);
- timeo = unix_stream_data_wait(sk, timeo);
+ timeo = unix_stream_data_wait(sk, timeo, last);
- if (signal_pending(current)) {
+ if (signal_pending(current)
+ || mutex_lock_interruptible(&u->readlock)) {
err = sock_intr_errno(timeo);
goto out;
}
- mutex_lock(&u->readlock);
+
continue;
unlock:
unix_state_unlock(sk);
break;
}
+
+ skip = sk_peek_offset(sk, flags);
+ while (skip >= unix_skb_len(skb)) {
+ skip -= unix_skb_len(skb);
+ last = skb;
+ skb = skb_peek_next(skb, &sk->sk_receive_queue);
+ if (!skb)
+ goto again;
+ }
+
unix_state_unlock(sk);
if (check_creds) {
/* Never glue messages from different writers */
if ((UNIXCB(skb).pid != siocb->scm->pid) ||
- (UNIXCB(skb).cred != siocb->scm->cred)) {
- skb_queue_head(&sk->sk_receive_queue, skb);
+ !uid_eq(UNIXCB(skb).uid, siocb->scm->creds.uid) ||
+ !gid_eq(UNIXCB(skb).gid, siocb->scm->creds.gid))
break;
- }
- } else {
+ } else if (test_bit(SOCK_PASSCRED, &sock->flags)) {
/* Copy credentials */
- scm_set_cred(siocb->scm, UNIXCB(skb).pid, UNIXCB(skb).cred);
+ scm_set_cred(siocb->scm, UNIXCB(skb).pid, UNIXCB(skb).uid, UNIXCB(skb).gid);
check_creds = 1;
}
@@ -1899,9 +2029,9 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
sunaddr = NULL;
}
- chunk = min_t(unsigned int, skb->len, size);
- if (memcpy_toiovec(msg->msg_iov, skb->data, chunk)) {
- skb_queue_head(&sk->sk_receive_queue, skb);
+ chunk = min_t(unsigned int, unix_skb_len(skb) - skip, size);
+ if (skb_copy_datagram_iovec(skb, UNIXCB(skb).consumed + skip,
+ msg->msg_iov, chunk)) {
if (copied == 0)
copied = -EFAULT;
break;
@@ -1911,17 +2041,17 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
/* Mark read part of skb as used */
if (!(flags & MSG_PEEK)) {
- skb_pull(skb, chunk);
+ UNIXCB(skb).consumed += chunk;
+
+ sk_peek_offset_bwd(sk, chunk);
if (UNIXCB(skb).fp)
unix_detach_fds(siocb->scm, skb);
- /* put the skb back if we didn't use it up.. */
- if (skb->len) {
- skb_queue_head(&sk->sk_receive_queue, skb);
+ if (unix_skb_len(skb))
break;
- }
+ skb_unlink(skb, &sk->sk_receive_queue);
consume_skb(skb);
if (siocb->scm->fp)
@@ -1932,8 +2062,8 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
if (UNIXCB(skb).fp)
siocb->scm->fp = scm_fp_dup(UNIXCB(skb).fp);
- /* put message back and return */
- skb_queue_head(&sk->sk_receive_queue, skb);
+ sk_peek_offset_fwd(sk, chunk);
+
break;
}
} while (size);
@@ -1949,41 +2079,77 @@ static int unix_shutdown(struct socket *sock, int mode)
struct sock *sk = sock->sk;
struct sock *other;
- mode = (mode+1)&(RCV_SHUTDOWN|SEND_SHUTDOWN);
+ if (mode < SHUT_RD || mode > SHUT_RDWR)
+ return -EINVAL;
+ /* This maps:
+ * SHUT_RD (0) -> RCV_SHUTDOWN (1)
+ * SHUT_WR (1) -> SEND_SHUTDOWN (2)
+ * SHUT_RDWR (2) -> SHUTDOWN_MASK (3)
+ */
+ ++mode;
- if (mode) {
- unix_state_lock(sk);
- sk->sk_shutdown |= mode;
- other = unix_peer(sk);
- if (other)
- sock_hold(other);
- unix_state_unlock(sk);
- sk->sk_state_change(sk);
-
- if (other &&
- (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET)) {
-
- int peer_mode = 0;
-
- if (mode&RCV_SHUTDOWN)
- peer_mode |= SEND_SHUTDOWN;
- if (mode&SEND_SHUTDOWN)
- peer_mode |= RCV_SHUTDOWN;
- unix_state_lock(other);
- other->sk_shutdown |= peer_mode;
- unix_state_unlock(other);
- other->sk_state_change(other);
- if (peer_mode == SHUTDOWN_MASK)
- sk_wake_async(other, SOCK_WAKE_WAITD, POLL_HUP);
- else if (peer_mode & RCV_SHUTDOWN)
- sk_wake_async(other, SOCK_WAKE_WAITD, POLL_IN);
- }
- if (other)
- sock_put(other);
+ unix_state_lock(sk);
+ sk->sk_shutdown |= mode;
+ other = unix_peer(sk);
+ if (other)
+ sock_hold(other);
+ unix_state_unlock(sk);
+ sk->sk_state_change(sk);
+
+ if (other &&
+ (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET)) {
+
+ int peer_mode = 0;
+
+ if (mode&RCV_SHUTDOWN)
+ peer_mode |= SEND_SHUTDOWN;
+ if (mode&SEND_SHUTDOWN)
+ peer_mode |= RCV_SHUTDOWN;
+ unix_state_lock(other);
+ other->sk_shutdown |= peer_mode;
+ unix_state_unlock(other);
+ other->sk_state_change(other);
+ if (peer_mode == SHUTDOWN_MASK)
+ sk_wake_async(other, SOCK_WAKE_WAITD, POLL_HUP);
+ else if (peer_mode & RCV_SHUTDOWN)
+ sk_wake_async(other, SOCK_WAKE_WAITD, POLL_IN);
}
+ if (other)
+ sock_put(other);
+
return 0;
}
+long unix_inq_len(struct sock *sk)
+{
+ struct sk_buff *skb;
+ long amount = 0;
+
+ if (sk->sk_state == TCP_LISTEN)
+ return -EINVAL;
+
+ spin_lock(&sk->sk_receive_queue.lock);
+ if (sk->sk_type == SOCK_STREAM ||
+ sk->sk_type == SOCK_SEQPACKET) {
+ skb_queue_walk(&sk->sk_receive_queue, skb)
+ amount += unix_skb_len(skb);
+ } else {
+ skb = skb_peek(&sk->sk_receive_queue);
+ if (skb)
+ amount = skb->len;
+ }
+ spin_unlock(&sk->sk_receive_queue.lock);
+
+ return amount;
+}
+EXPORT_SYMBOL_GPL(unix_inq_len);
+
+long unix_outq_len(struct sock *sk)
+{
+ return sk_wmem_alloc_get(sk);
+}
+EXPORT_SYMBOL_GPL(unix_outq_len);
+
static int unix_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
{
struct sock *sk = sock->sk;
@@ -1992,33 +2158,16 @@ static int unix_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
switch (cmd) {
case SIOCOUTQ:
- amount = sk_wmem_alloc_get(sk);
+ amount = unix_outq_len(sk);
err = put_user(amount, (int __user *)arg);
break;
case SIOCINQ:
- {
- struct sk_buff *skb;
-
- if (sk->sk_state == TCP_LISTEN) {
- err = -EINVAL;
- break;
- }
-
- spin_lock(&sk->sk_receive_queue.lock);
- if (sk->sk_type == SOCK_STREAM ||
- sk->sk_type == SOCK_SEQPACKET) {
- skb_queue_walk(&sk->sk_receive_queue, skb)
- amount += skb->len;
- } else {
- skb = skb_peek(&sk->sk_receive_queue);
- if (skb)
- amount = skb->len;
- }
- spin_unlock(&sk->sk_receive_queue.lock);
+ amount = unix_inq_len(sk);
+ if (amount < 0)
+ err = amount;
+ else
err = put_user(amount, (int __user *)arg);
- break;
- }
-
+ break;
default:
err = -ENOIOCTLCMD;
break;
@@ -2072,7 +2221,9 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock,
/* exceptional events? */
if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
- mask |= POLLERR;
+ mask |= POLLERR |
+ (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? POLLPRI : 0);
+
if (sk->sk_shutdown & RCV_SHUTDOWN)
mask |= POLLRDHUP | POLLIN | POLLRDNORM;
if (sk->sk_shutdown == SHUTDOWN_MASK)
@@ -2092,7 +2243,7 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock,
}
/* No write status requested, avoid expensive OUT tests. */
- if (wait && !(wait->key & (POLLWRBAND | POLLWRNORM | POLLOUT)))
+ if (!(poll_requested_events(wait) & (POLLWRBAND|POLLWRNORM|POLLOUT)))
return mask;
writable = unix_writable(sk);
@@ -2115,47 +2266,54 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock,
}
#ifdef CONFIG_PROC_FS
-static struct sock *first_unix_socket(int *i)
+
+#define BUCKET_SPACE (BITS_PER_LONG - (UNIX_HASH_BITS + 1) - 1)
+
+#define get_bucket(x) ((x) >> BUCKET_SPACE)
+#define get_offset(x) ((x) & ((1L << BUCKET_SPACE) - 1))
+#define set_bucket_offset(b, o) ((b) << BUCKET_SPACE | (o))
+
+static struct sock *unix_from_bucket(struct seq_file *seq, loff_t *pos)
{
- for (*i = 0; *i <= UNIX_HASH_SIZE; (*i)++) {
- if (!hlist_empty(&unix_socket_table[*i]))
- return __sk_head(&unix_socket_table[*i]);
+ unsigned long offset = get_offset(*pos);
+ unsigned long bucket = get_bucket(*pos);
+ struct sock *sk;
+ unsigned long count = 0;
+
+ for (sk = sk_head(&unix_socket_table[bucket]); sk; sk = sk_next(sk)) {
+ if (sock_net(sk) != seq_file_net(seq))
+ continue;
+ if (++count == offset)
+ break;
}
- return NULL;
+
+ return sk;
}
-static struct sock *next_unix_socket(int *i, struct sock *s)
+static struct sock *unix_next_socket(struct seq_file *seq,
+ struct sock *sk,
+ loff_t *pos)
{
- 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]);
+ unsigned long bucket;
+
+ while (sk > (struct sock *)SEQ_START_TOKEN) {
+ sk = sk_next(sk);
+ if (!sk)
+ goto next_bucket;
+ if (sock_net(sk) == seq_file_net(seq))
+ return sk;
}
- return NULL;
-}
-struct unix_iter_state {
- struct seq_net_private p;
- int i;
-};
+ do {
+ sk = unix_from_bucket(seq, pos);
+ if (sk)
+ return sk;
-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;
+next_bucket:
+ bucket = get_bucket(*pos) + 1;
+ *pos = set_bucket_offset(bucket, 1);
+ } while (bucket < ARRAY_SIZE(unix_socket_table));
- 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;
- }
return NULL;
}
@@ -2163,22 +2321,20 @@ 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, *pos - 1) : SEQ_START_TOKEN;
+
+ if (!*pos)
+ return SEQ_START_TOKEN;
+
+ if (get_bucket(*pos) >= ARRAY_SIZE(unix_socket_table))
+ return NULL;
+
+ return unix_next_socket(seq, NULL, pos);
}
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 == 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;
+ return unix_next_socket(seq, v, pos);
}
static void unix_seq_stop(struct seq_file *seq, void *v)
@@ -2198,7 +2354,7 @@ static int unix_seq_show(struct seq_file *seq, void *v)
struct unix_sock *u = unix_sk(s);
unix_state_lock(s);
- seq_printf(seq, "%p: %08X %08X %08X %04X %02X %5lu",
+ seq_printf(seq, "%pK: %08X %08X %08X %04X %02X %5lu",
s,
atomic_read(&s->sk_refcnt),
0,
@@ -2241,7 +2397,7 @@ static const struct seq_operations unix_seq_ops = {
static int unix_seq_open(struct inode *inode, struct file *file)
{
return seq_open_net(inode, file, &unix_seq_ops,
- sizeof(struct unix_iter_state));
+ sizeof(struct seq_net_private));
}
static const struct file_operations unix_seq_fops = {
@@ -2270,7 +2426,7 @@ static int __net_init unix_net_init(struct net *net)
goto out;
#ifdef CONFIG_PROC_FS
- if (!proc_net_fops_create(net, "unix", 0, &unix_seq_fops)) {
+ if (!proc_create("unix", 0, net->proc_net, &unix_seq_fops)) {
unix_sysctl_unregister(net);
goto out;
}
@@ -2283,7 +2439,7 @@ out:
static void __net_exit unix_net_exit(struct net *net)
{
unix_sysctl_unregister(net);
- proc_net_remove(net, "unix");
+ remove_proc_entry("unix", net->proc_net);
}
static struct pernet_operations unix_net_ops = {
@@ -2294,14 +2450,12 @@ static struct pernet_operations unix_net_ops = {
static int __init af_unix_init(void)
{
int rc = -1;
- struct sk_buff *dummy_skb;
- BUILD_BUG_ON(sizeof(struct unix_skb_parms) > sizeof(dummy_skb->cb));
+ BUILD_BUG_ON(sizeof(struct unix_skb_parms) > FIELD_SIZEOF(struct sk_buff, cb));
rc = proto_register(&unix_proto, 1);
if (rc != 0) {
- printk(KERN_CRIT "%s: Cannot create unix_sock SLAB cache!\n",
- __func__);
+ pr_crit("%s: Cannot create unix_sock SLAB cache!\n", __func__);
goto out;
}
diff --git a/net/unix/diag.c b/net/unix/diag.c
new file mode 100644
index 00000000000..86fa0f3b2ca
--- /dev/null
+++ b/net/unix/diag.c
@@ -0,0 +1,327 @@
+#include <linux/types.h>
+#include <linux/spinlock.h>
+#include <linux/sock_diag.h>
+#include <linux/unix_diag.h>
+#include <linux/skbuff.h>
+#include <linux/module.h>
+#include <net/netlink.h>
+#include <net/af_unix.h>
+#include <net/tcp_states.h>
+
+static int sk_diag_dump_name(struct sock *sk, struct sk_buff *nlskb)
+{
+ struct unix_address *addr = unix_sk(sk)->addr;
+
+ if (!addr)
+ return 0;
+
+ return nla_put(nlskb, UNIX_DIAG_NAME, addr->len - sizeof(short),
+ addr->name->sun_path);
+}
+
+static int sk_diag_dump_vfs(struct sock *sk, struct sk_buff *nlskb)
+{
+ struct dentry *dentry = unix_sk(sk)->path.dentry;
+
+ if (dentry) {
+ struct unix_diag_vfs uv = {
+ .udiag_vfs_ino = dentry->d_inode->i_ino,
+ .udiag_vfs_dev = dentry->d_sb->s_dev,
+ };
+
+ return nla_put(nlskb, UNIX_DIAG_VFS, sizeof(uv), &uv);
+ }
+
+ return 0;
+}
+
+static int sk_diag_dump_peer(struct sock *sk, struct sk_buff *nlskb)
+{
+ struct sock *peer;
+ int ino;
+
+ peer = unix_peer_get(sk);
+ if (peer) {
+ unix_state_lock(peer);
+ ino = sock_i_ino(peer);
+ unix_state_unlock(peer);
+ sock_put(peer);
+
+ return nla_put_u32(nlskb, UNIX_DIAG_PEER, ino);
+ }
+
+ return 0;
+}
+
+static int sk_diag_dump_icons(struct sock *sk, struct sk_buff *nlskb)
+{
+ struct sk_buff *skb;
+ struct nlattr *attr;
+ u32 *buf;
+ int i;
+
+ if (sk->sk_state == TCP_LISTEN) {
+ spin_lock(&sk->sk_receive_queue.lock);
+
+ attr = nla_reserve(nlskb, UNIX_DIAG_ICONS,
+ sk->sk_receive_queue.qlen * sizeof(u32));
+ if (!attr)
+ goto errout;
+
+ buf = nla_data(attr);
+ i = 0;
+ skb_queue_walk(&sk->sk_receive_queue, skb) {
+ struct sock *req, *peer;
+
+ req = skb->sk;
+ /*
+ * The state lock is outer for the same sk's
+ * queue lock. With the other's queue locked it's
+ * OK to lock the state.
+ */
+ unix_state_lock_nested(req);
+ peer = unix_sk(req)->peer;
+ buf[i++] = (peer ? sock_i_ino(peer) : 0);
+ unix_state_unlock(req);
+ }
+ spin_unlock(&sk->sk_receive_queue.lock);
+ }
+
+ return 0;
+
+errout:
+ spin_unlock(&sk->sk_receive_queue.lock);
+ return -EMSGSIZE;
+}
+
+static int sk_diag_show_rqlen(struct sock *sk, struct sk_buff *nlskb)
+{
+ struct unix_diag_rqlen rql;
+
+ if (sk->sk_state == TCP_LISTEN) {
+ rql.udiag_rqueue = sk->sk_receive_queue.qlen;
+ rql.udiag_wqueue = sk->sk_max_ack_backlog;
+ } else {
+ rql.udiag_rqueue = (u32) unix_inq_len(sk);
+ rql.udiag_wqueue = (u32) unix_outq_len(sk);
+ }
+
+ return nla_put(nlskb, UNIX_DIAG_RQLEN, sizeof(rql), &rql);
+}
+
+static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_req *req,
+ u32 portid, u32 seq, u32 flags, int sk_ino)
+{
+ struct nlmsghdr *nlh;
+ struct unix_diag_msg *rep;
+
+ nlh = nlmsg_put(skb, portid, seq, SOCK_DIAG_BY_FAMILY, sizeof(*rep),
+ flags);
+ if (!nlh)
+ return -EMSGSIZE;
+
+ rep = nlmsg_data(nlh);
+ rep->udiag_family = AF_UNIX;
+ rep->udiag_type = sk->sk_type;
+ rep->udiag_state = sk->sk_state;
+ rep->pad = 0;
+ rep->udiag_ino = sk_ino;
+ sock_diag_save_cookie(sk, rep->udiag_cookie);
+
+ if ((req->udiag_show & UDIAG_SHOW_NAME) &&
+ sk_diag_dump_name(sk, skb))
+ goto out_nlmsg_trim;
+
+ if ((req->udiag_show & UDIAG_SHOW_VFS) &&
+ sk_diag_dump_vfs(sk, skb))
+ goto out_nlmsg_trim;
+
+ if ((req->udiag_show & UDIAG_SHOW_PEER) &&
+ sk_diag_dump_peer(sk, skb))
+ goto out_nlmsg_trim;
+
+ if ((req->udiag_show & UDIAG_SHOW_ICONS) &&
+ sk_diag_dump_icons(sk, skb))
+ goto out_nlmsg_trim;
+
+ if ((req->udiag_show & UDIAG_SHOW_RQLEN) &&
+ sk_diag_show_rqlen(sk, skb))
+ goto out_nlmsg_trim;
+
+ if ((req->udiag_show & UDIAG_SHOW_MEMINFO) &&
+ sock_diag_put_meminfo(sk, skb, UNIX_DIAG_MEMINFO))
+ goto out_nlmsg_trim;
+
+ if (nla_put_u8(skb, UNIX_DIAG_SHUTDOWN, sk->sk_shutdown))
+ goto out_nlmsg_trim;
+
+ return nlmsg_end(skb, nlh);
+
+out_nlmsg_trim:
+ nlmsg_cancel(skb, nlh);
+ return -EMSGSIZE;
+}
+
+static int sk_diag_dump(struct sock *sk, struct sk_buff *skb, struct unix_diag_req *req,
+ u32 portid, u32 seq, u32 flags)
+{
+ int sk_ino;
+
+ unix_state_lock(sk);
+ sk_ino = sock_i_ino(sk);
+ unix_state_unlock(sk);
+
+ if (!sk_ino)
+ return 0;
+
+ return sk_diag_fill(sk, skb, req, portid, seq, flags, sk_ino);
+}
+
+static int unix_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ struct unix_diag_req *req;
+ int num, s_num, slot, s_slot;
+ struct net *net = sock_net(skb->sk);
+
+ req = nlmsg_data(cb->nlh);
+
+ s_slot = cb->args[0];
+ num = s_num = cb->args[1];
+
+ spin_lock(&unix_table_lock);
+ for (slot = s_slot;
+ slot < ARRAY_SIZE(unix_socket_table);
+ s_num = 0, slot++) {
+ struct sock *sk;
+
+ num = 0;
+ sk_for_each(sk, &unix_socket_table[slot]) {
+ if (!net_eq(sock_net(sk), net))
+ continue;
+ if (num < s_num)
+ goto next;
+ if (!(req->udiag_states & (1 << sk->sk_state)))
+ goto next;
+ if (sk_diag_dump(sk, skb, req,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq,
+ NLM_F_MULTI) < 0)
+ goto done;
+next:
+ num++;
+ }
+ }
+done:
+ spin_unlock(&unix_table_lock);
+ cb->args[0] = slot;
+ cb->args[1] = num;
+
+ return skb->len;
+}
+
+static struct sock *unix_lookup_by_ino(int ino)
+{
+ int i;
+ struct sock *sk;
+
+ spin_lock(&unix_table_lock);
+ for (i = 0; i < ARRAY_SIZE(unix_socket_table); i++) {
+ sk_for_each(sk, &unix_socket_table[i])
+ if (ino == sock_i_ino(sk)) {
+ sock_hold(sk);
+ spin_unlock(&unix_table_lock);
+
+ return sk;
+ }
+ }
+
+ spin_unlock(&unix_table_lock);
+ return NULL;
+}
+
+static int unix_diag_get_exact(struct sk_buff *in_skb,
+ const struct nlmsghdr *nlh,
+ struct unix_diag_req *req)
+{
+ int err = -EINVAL;
+ struct sock *sk;
+ struct sk_buff *rep;
+ unsigned int extra_len;
+ struct net *net = sock_net(in_skb->sk);
+
+ if (req->udiag_ino == 0)
+ goto out_nosk;
+
+ sk = unix_lookup_by_ino(req->udiag_ino);
+ err = -ENOENT;
+ if (sk == NULL)
+ goto out_nosk;
+
+ err = sock_diag_check_cookie(sk, req->udiag_cookie);
+ if (err)
+ goto out;
+
+ extra_len = 256;
+again:
+ err = -ENOMEM;
+ rep = nlmsg_new(sizeof(struct unix_diag_msg) + extra_len, GFP_KERNEL);
+ if (!rep)
+ goto out;
+
+ err = sk_diag_fill(sk, rep, req, NETLINK_CB(in_skb).portid,
+ nlh->nlmsg_seq, 0, req->udiag_ino);
+ if (err < 0) {
+ nlmsg_free(rep);
+ extra_len += 256;
+ if (extra_len >= PAGE_SIZE)
+ goto out;
+
+ goto again;
+ }
+ err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid,
+ MSG_DONTWAIT);
+ if (err > 0)
+ err = 0;
+out:
+ if (sk)
+ sock_put(sk);
+out_nosk:
+ return err;
+}
+
+static int unix_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h)
+{
+ int hdrlen = sizeof(struct unix_diag_req);
+ struct net *net = sock_net(skb->sk);
+
+ if (nlmsg_len(h) < hdrlen)
+ return -EINVAL;
+
+ if (h->nlmsg_flags & NLM_F_DUMP) {
+ struct netlink_dump_control c = {
+ .dump = unix_diag_dump,
+ };
+ return netlink_dump_start(net->diag_nlsk, skb, h, &c);
+ } else
+ return unix_diag_get_exact(skb, h, nlmsg_data(h));
+}
+
+static const struct sock_diag_handler unix_diag_handler = {
+ .family = AF_UNIX,
+ .dump = unix_diag_handler_dump,
+};
+
+static int __init unix_diag_init(void)
+{
+ return sock_diag_register(&unix_diag_handler);
+}
+
+static void __exit unix_diag_exit(void)
+{
+ sock_diag_unregister(&unix_diag_handler);
+}
+
+module_init(unix_diag_init);
+module_exit(unix_diag_exit);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 1 /* AF_LOCAL */);
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index c8df6fda0b1..9bc73f87f64 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -96,15 +96,15 @@ static DECLARE_WAIT_QUEUE_HEAD(unix_gc_wait);
unsigned int unix_tot_inflight;
-static struct sock *unix_get_socket(struct file *filp)
+struct sock *unix_get_socket(struct file *filp)
{
struct sock *u_sock = NULL;
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
/*
* Socket ?
*/
- if (S_ISSOCK(inode->i_mode)) {
+ if (S_ISSOCK(inode->i_mode) && !(filp->f_mode & FMODE_PATH)) {
struct socket *sock = SOCKET_I(inode);
struct sock *s = sock->sk;
@@ -185,7 +185,7 @@ static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *),
* have been added to the queues after
* starting the garbage collection
*/
- if (u->gc_candidate) {
+ if (test_bit(UNIX_GC_CANDIDATE, &u->gc_flags)) {
hit = true;
func(u);
}
@@ -254,14 +254,21 @@ static void inc_inflight_move_tail(struct unix_sock *u)
* of the list, so that it's checked even if it was already
* passed over
*/
- if (u->gc_maybe_cycle)
+ if (test_bit(UNIX_GC_MAYBE_CYCLE, &u->gc_flags))
list_move_tail(&u->link, &gc_candidates);
}
static bool gc_in_progress = false;
+#define UNIX_INFLIGHT_TRIGGER_GC 16000
void wait_for_unix_gc(void)
{
+ /*
+ * If number of inflight sockets is insane,
+ * force a garbage collect right now.
+ */
+ if (unix_tot_inflight > UNIX_INFLIGHT_TRIGGER_GC && !gc_in_progress)
+ unix_gc();
wait_event(unix_gc_wait, gc_in_progress == false);
}
@@ -308,8 +315,8 @@ void unix_gc(void)
BUG_ON(total_refs < inflight_refs);
if (total_refs == inflight_refs) {
list_move_tail(&u->link, &gc_candidates);
- u->gc_candidate = 1;
- u->gc_maybe_cycle = 1;
+ __set_bit(UNIX_GC_CANDIDATE, &u->gc_flags);
+ __set_bit(UNIX_GC_MAYBE_CYCLE, &u->gc_flags);
}
}
@@ -337,7 +344,7 @@ void unix_gc(void)
if (atomic_long_read(&u->inflight) > 0) {
list_move_tail(&u->link, &not_cycle_list);
- u->gc_maybe_cycle = 0;
+ __clear_bit(UNIX_GC_MAYBE_CYCLE, &u->gc_flags);
scan_children(&u->sk, inc_inflight_move_tail, NULL);
}
}
@@ -349,7 +356,7 @@ void unix_gc(void)
*/
while (!list_empty(&not_cycle_list)) {
u = list_entry(not_cycle_list.next, struct unix_sock, link);
- u->gc_candidate = 0;
+ __clear_bit(UNIX_GC_CANDIDATE, &u->gc_flags);
list_move_tail(&u->link, &gc_inflight_list);
}
diff --git a/net/unix/sysctl_net_unix.c b/net/unix/sysctl_net_unix.c
index 397cffebb3b..b3d515021b7 100644
--- a/net/unix/sysctl_net_unix.c
+++ b/net/unix/sysctl_net_unix.c
@@ -15,7 +15,7 @@
#include <net/af_unix.h>
-static ctl_table unix_table[] = {
+static struct ctl_table unix_table[] = {
{
.procname = "max_dgram_qlen",
.data = &init_net.unx.sysctl_max_dgram_qlen,
@@ -26,12 +26,6 @@ static ctl_table unix_table[] = {
{ }
};
-static struct ctl_path unix_path[] = {
- { .procname = "net", },
- { .procname = "unix", },
- { },
-};
-
int __net_init unix_sysctl_register(struct net *net)
{
struct ctl_table *table;
@@ -40,8 +34,12 @@ int __net_init unix_sysctl_register(struct net *net)
if (table == NULL)
goto err_alloc;
+ /* Don't export sysctls to unprivileged users */
+ if (net->user_ns != &init_user_ns)
+ table[0].procname = NULL;
+
table[0].data = &net->unx.sysctl_max_dgram_qlen;
- net->unx.ctl = register_net_sysctl_table(net, unix_path, table);
+ net->unx.ctl = register_net_sysctl(net, "net/unix", table);
if (net->unx.ctl == NULL)
goto err_reg;
@@ -58,6 +56,6 @@ void unix_sysctl_unregister(struct net *net)
struct ctl_table *table;
table = net->unx.ctl->ctl_table_arg;
- unregister_sysctl_table(net->unx.ctl);
+ unregister_net_sysctl_table(net->unx.ctl);
kfree(table);
}
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-04 22:29:10 +0000