[PATCH] af_unix: Fix splice-bind deadlock

From: Rainer Weikusat
Date: Sun Dec 27 2015 - 15:13:44 EST


On 2015/11/06, Dmitry Vyukov reported a deadlock involving the splice
system call and AF_UNIX sockets,

http://lists.openwall.net/netdev/2015/11/06/24

The situation was analyzed as

(a while ago) A: socketpair()
B: splice() from a pipe to /mnt/regular_file
does sb_start_write() on /mnt
C: try to freeze /mnt
wait for B to finish with /mnt
A: bind() try to bind our socket to /mnt/new_socket_name
lock our socket, see it not bound yet
decide that it needs to create something in /mnt
try to do sb_start_write() on /mnt, block (it's
waiting for C).
D: splice() from the same pipe to our socket
lock the pipe, see that socket is connected
try to lock the socket, block waiting for A
B: get around to actually feeding a chunk from
pipe to file, try to lock the pipe. Deadlock.

on 2015/11/10 by Al Viro,

http://lists.openwall.net/netdev/2015/11/10/4

The patch fixes this by removing the kern_path_create related code from
unix_mknod and executing it as part of unix_bind prior acquiring the
readlock of the socket in question. This means that A (as used above)
will sb_start_write on /mnt before it acquires the readlock, hence, it
won't indirectly block B which first did a sb_start_write and then
waited for a thread trying to acquire the readlock. Consequently, A
being blocked by C waiting for B won't cause a deadlock anymore
(effectively, both A and B acquire two locks in opposite order in the
situation described above).

Signed-off-by: Rainer Weikusat <rweikusat@xxxxxxxxxxxxxxxxxxxxxxx>
Tested-by: Dmitry Vyukov <dvyukov@xxxxxxxxxx>
---

I also think this is a better (or at least more correct) solution than
the pretty obvious idea to record that the socket is in the process of
being bound and performing the mknod without the lock. Assuming the
first bind fails with -EADDRINUSE, a concurrent bind which might have
succeeded had it waited for the ultimate outcome of the first will
meanwhile have failed with -EINVAL despite the socket will end up
unbound.

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index b1314c0..9b3d268 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -953,32 +953,20 @@ fail:
return NULL;
}

-static int unix_mknod(const char *sun_path, umode_t mode, struct path *res)
+static int unix_mknod(struct dentry *dentry, struct path *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;
+ int err;

- /*
- * All right, let's create it.
- */
- err = security_path_mknod(&path, dentry, mode, 0);
+ err = security_path_mknod(path, dentry, mode, 0);
if (!err) {
- err = vfs_mknod(d_inode(path.dentry), dentry, mode, 0);
+ err = vfs_mknod(d_inode(path->dentry), dentry, mode, 0);
if (!err) {
- res->mnt = mntget(path.mnt);
+ res->mnt = mntget(path->mnt);
res->dentry = dget(dentry);
}
}
- done_path_create(&path, dentry);
+
return err;
}

@@ -993,6 +981,8 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
unsigned int hash;
struct unix_address *addr;
struct hlist_head *list;
+ struct path path;
+ struct dentry *dentry;

err = -EINVAL;
if (sunaddr->sun_family != AF_UNIX)
@@ -1008,9 +998,21 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
goto out;
addr_len = err;

+ dentry = NULL;
+ if (sun_path[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))
+ goto out;
+ }
+
err = mutex_lock_interruptible(&u->readlock);
if (err)
- goto out;
+ goto out_path;

err = -EINVAL;
if (u->addr)
@@ -1026,11 +1028,11 @@ 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 (sun_path[0]) {
- struct path path;
+ if (dentry) {
+ struct path u_path;
umode_t mode = S_IFSOCK |
(SOCK_INODE(sock)->i_mode & ~current_umask());
- err = unix_mknod(sun_path, mode, &path);
+ err = unix_mknod(dentry, &path, mode, &u_path);
if (err) {
if (err == -EEXIST)
err = -EADDRINUSE;
@@ -1038,9 +1040,9 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
goto out_up;
}
addr->hash = UNIX_HASH_SIZE;
- hash = d_backing_inode(path.dentry)->i_ino & (UNIX_HASH_SIZE-1);
+ hash = d_backing_inode(dentry)->i_ino & (UNIX_HASH_SIZE - 1);
spin_lock(&unix_table_lock);
- u->path = path;
+ u->path = u_path;
list = &unix_socket_table[hash];
} else {
spin_lock(&unix_table_lock);
@@ -1063,6 +1065,10 @@ out_unlock:
spin_unlock(&unix_table_lock);
out_up:
mutex_unlock(&u->readlock);
+out_path:
+ if (dentry)
+ done_path_create(&path, dentry);
+
out:
return err;
}
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/