Skip to contentSkip to conversation

AF_UNIX bind(2) cleanup on failures after mknod

PATCH New Al Viro 2 participants 10 messages Jun 19, 2021 – Jun 21, 2021

Subsystems (3)
lore
Share & tools
lore

Al Viro

author
#0 lore raw

PATCH 1/1 AF_UNIX bind(2) cleanup on failures after mknod

Failures in unix_bind() coming after we'd created a socket
node in filesystem are possible and can leave an unpleasant mess behind. That had been reported back in February by Denis Kirjanov, but his proposed solution had holes.

	This is a rebase of the series I'd ended up with back then;

I'd prefer to have it go through the regular net.git path.

8 commits total, preliminary massage in the first 6, the fix is #7
and #8 is a minor followup cleanup. Branch is based at net.git/master, lives in vfs.git #misc.af_unix. Individual patches in followups.

Al Viro (8):
af_unix: take address assignment/hash insertion into a new helper unix_bind(): allocate addr earlier
unix_bind(): separate BSD and abstract cases
unix_bind(): take BSD and abstract address cases into new helpers fold unix_mknod() into unix_bind_bsd()
unix_bind_bsd(): move done_path_create() call after dealing with ->bindlock unix_bind_bsd(): unlink if we fail after successful mknod __unix_find_socket_byname(): don't pass hash and type separately

 net/unix/af_unix.c | 188 +++++++++++++++++++++++++++--------------------------
 1 file changed, 96 insertions(+), 92 deletions(-)
author
#1 lore raw

PATCH 1/8 af_unix: take address assignment/hash insertion into a new helper

Duplicated logics in all bind variants (autobind, bind-to-path, bind-to-abstract) gets taken into a common helper.

---
 net/unix/af_unix.c | 26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)
net/unix/af_unix.c +13 -13
index 4d4f24cbd86b..464473a78b05 100644
@@ -262,6 +262,14 @@ static void __unix_insert_socket(struct hlist_head *list, struct sock *sk)
 	sk_add_node(sk, list);
 }
 
+static void __unix_set_addr(struct sock *sk, struct unix_address *addr,
+			    unsigned hash)
+{
+	__unix_remove_socket(sk);
+	smp_store_release(&unix_sk(sk)->addr, addr);
+	__unix_insert_socket(&unix_socket_table[hash], sk);
+}
+
 static inline void unix_remove_socket(struct sock *sk)
 {
 	spin_lock(&unix_table_lock);
@@ -912,9 +920,7 @@ static int unix_autobind(struct socket *sock)
 	}
 	addr->hash ^= sk->sk_type;
 
-	__unix_remove_socket(sk);
-	smp_store_release(&u->addr, addr);
-	__unix_insert_socket(&unix_socket_table[addr->hash], sk);
+	__unix_set_addr(sk, addr, addr->hash);
 	spin_unlock(&unix_table_lock);
 	err = 0;
 
@@ -1017,7 +1023,6 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	int err;
 	unsigned int hash;
 	struct unix_address *addr;
-	struct hlist_head *list;
 	struct path path = { };
 
 	err = -EINVAL;
@@ -1069,25 +1074,20 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 		hash = d_backing_inode(path.dentry)->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)) {
+			spin_unlock(&unix_table_lock);
 			unix_release_addr(addr);
-			goto out_unlock;
+			goto out_up;
 		}
-
-		list = &unix_socket_table[addr->hash];
+		hash = addr->hash;
 	}
 
 	err = 0;
-	__unix_remove_socket(sk);
-	smp_store_release(&u->addr, addr);
-	__unix_insert_socket(list, sk);
-
-out_unlock:
+	__unix_set_addr(sk, addr, hash);
 	spin_unlock(&unix_table_lock);
 out_up:
 	mutex_unlock(&u->bindlock);
Signature · 1 line
2.11.0
author
#2 lore raw

PATCH 2/8 unix_bind(): allocate addr earlier

makes it easier to massage; we do pay for that by extra work (kmalloc+memcpy+kfree) in some error cases, but those are not on the hot paths anyway.

---
 net/unix/af_unix.c | 28 +++++++++++++++-------------
 1 file changed, 15 insertions(+), 13 deletions(-)
net/unix/af_unix.c +15 -13
index 464473a78b05..185f868db998 100644
@@ -1039,6 +1039,15 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	if (err < 0)
 		goto out;
 	addr_len = err;
+	err = -ENOMEM;
+	addr = kmalloc(sizeof(*addr)+addr_len, GFP_KERNEL);
+	if (!addr)
+		goto out;
+
+	memcpy(addr->name, sunaddr, addr_len);
+	addr->len = addr_len;
+	addr->hash = hash ^ sk->sk_type;
+	refcount_set(&addr->refcnt, 1);
 
 	if (sun_path[0]) {
 		umode_t mode = S_IFSOCK |
@@ -1047,7 +1056,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 		if (err) {
 			if (err == -EEXIST)
 				err = -EADDRINUSE;
-			goto out;
+			goto out_addr;
 		}
 	}
 
@@ -1059,16 +1068,6 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	if (u->addr)
 		goto out_up;
 
-	err = -ENOMEM;
-	addr = kmalloc(sizeof(*addr)+addr_len, GFP_KERNEL);
-	if (!addr)
-		goto out_up;
-
-	memcpy(addr->name, sunaddr, addr_len);
-	addr->len = addr_len;
-	addr->hash = hash ^ sk->sk_type;
-	refcount_set(&addr->refcnt, 1);
-
 	if (sun_path[0]) {
 		addr->hash = UNIX_HASH_SIZE;
 		hash = d_backing_inode(path.dentry)->i_ino & (UNIX_HASH_SIZE - 1);
@@ -1080,20 +1079,23 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 		if (__unix_find_socket_byname(net, sunaddr, addr_len,
 					      sk->sk_type, hash)) {
 			spin_unlock(&unix_table_lock);
-			unix_release_addr(addr);
 			goto out_up;
 		}
 		hash = addr->hash;
 	}
 
-	err = 0;
 	__unix_set_addr(sk, addr, hash);
 	spin_unlock(&unix_table_lock);
+	addr = NULL;
+	err = 0;
 out_up:
 	mutex_unlock(&u->bindlock);
 out_put:
 	if (err)
 		path_put(&path);
+out_addr:
+	if (addr)
+		unix_release_addr(addr);
 out:
 	return err;
 }
Signature · 1 line
2.11.0
author
#3 lore raw

PATCH 3/8 unix_bind(): separate BSD and abstract cases

In reply to Al Viro

We do get some duplication that way, but it's minor compared to parts that are different. What we get is an ability to change locking in BSD case without making failure exits very hard to follow.

---
 net/unix/af_unix.c | 55 +++++++++++++++++++++++++++++++++---------------------
 1 file changed, 34 insertions(+), 21 deletions(-)
net/unix/af_unix.c +34 -21
index 185f868db998..65a2545d969d 100644
@@ -1023,7 +1023,6 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	int err;
 	unsigned int hash;
 	struct unix_address *addr;
-	struct path path = { };
 
 	err = -EINVAL;
 	if (addr_len < offsetofend(struct sockaddr_un, sun_family) ||
@@ -1050,6 +1049,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	refcount_set(&addr->refcnt, 1);
 
 	if (sun_path[0]) {
+		struct path path = { };
 		umode_t mode = S_IFSOCK |
 		       (SOCK_INODE(sock)->i_mode & ~current_umask());
 		err = unix_mknod(sun_path, mode, &path);
@@ -1058,41 +1058,54 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 				err = -EADDRINUSE;
 			goto out_addr;
 		}
-	}
 
-	err = mutex_lock_interruptible(&u->bindlock);
-	if (err)
-		goto out_put;
+		err = mutex_lock_interruptible(&u->bindlock);
+		if (err) {
+			path_put(&path);
+			goto out_addr;
+		}
 
-	err = -EINVAL;
-	if (u->addr)
-		goto out_up;
+		err = -EINVAL;
+		if (u->addr) {
+			mutex_unlock(&u->bindlock);
+			path_put(&path);
+			goto out_addr;
+		}
 
-	if (sun_path[0]) {
 		addr->hash = UNIX_HASH_SIZE;
 		hash = d_backing_inode(path.dentry)->i_ino & (UNIX_HASH_SIZE - 1);
 		spin_lock(&unix_table_lock);
 		u->path = path;
+		__unix_set_addr(sk, addr, hash);
+		spin_unlock(&unix_table_lock);
+		mutex_unlock(&u->bindlock);
+		addr = NULL;
+		err = 0;
 	} else {
+		err = mutex_lock_interruptible(&u->bindlock);
+		if (err)
+			goto out_addr;
+
+		err = -EINVAL;
+		if (u->addr) {
+			mutex_unlock(&u->bindlock);
+			goto out_addr;
+		}
+
 		spin_lock(&unix_table_lock);
 		err = -EADDRINUSE;
 		if (__unix_find_socket_byname(net, sunaddr, addr_len,
 					      sk->sk_type, hash)) {
 			spin_unlock(&unix_table_lock);
-			goto out_up;
+			mutex_unlock(&u->bindlock);
+			goto out_addr;
 		}
-		hash = addr->hash;
+		__unix_set_addr(sk, addr, addr->hash);
+		spin_unlock(&unix_table_lock);
+		mutex_unlock(&u->bindlock);
+		addr = NULL;
+		err = 0;
 	}
-
-	__unix_set_addr(sk, addr, hash);
-	spin_unlock(&unix_table_lock);
-	addr = NULL;
-	err = 0;
-out_up:
-	mutex_unlock(&u->bindlock);
-out_put:
-	if (err)
-		path_put(&path);
 out_addr:
 	if (addr)
 		unix_release_addr(addr);
Signature · 1 line
2.11.0
author
#4 lore raw

PATCH 4/8 unix_bind(): take BSD and abstract address cases into new helpers

In reply to Al Viro

unix_bind_bsd() and unix_bind_abstract() respectively.

---
 net/unix/af_unix.c | 147 +++++++++++++++++++++++++++--------------------------
 1 file changed, 74 insertions(+), 73 deletions(-)
net/unix/af_unix.c +74 -73
index 65a2545d969d..04ec7be04909 100644
@@ -1013,104 +1013,105 @@ static int unix_mknod(const char *sun_path, umode_t mode, struct path *res)
 	return err;
 }
 
+static int unix_bind_bsd(struct sock *sk, struct unix_address *addr)
+{
+	struct unix_sock *u = unix_sk(sk);
+	struct path path = { };
+	umode_t mode = S_IFSOCK |
+	       (SOCK_INODE(sk->sk_socket)->i_mode & ~current_umask());
+	unsigned int hash;
+	int err;
+
+	err = unix_mknod(addr->name->sun_path, mode, &path);
+	if (err)
+		return err;
+
+	err = mutex_lock_interruptible(&u->bindlock);
+	if (err) {
+		path_put(&path);
+		return err;
+	}
+
+	if (u->addr) {
+		mutex_unlock(&u->bindlock);
+		path_put(&path);
+		return -EINVAL;
+	}
+
+	addr->hash = UNIX_HASH_SIZE;
+	hash = d_backing_inode(path.dentry)->i_ino & (UNIX_HASH_SIZE - 1);
+	spin_lock(&unix_table_lock);
+	u->path = path;
+	__unix_set_addr(sk, addr, hash);
+	spin_unlock(&unix_table_lock);
+	mutex_unlock(&u->bindlock);
+	return 0;
+}
+
+static int unix_bind_abstract(struct sock *sk, unsigned hash,
+			      struct unix_address *addr)
+{
+	struct unix_sock *u = unix_sk(sk);
+	int err;
+
+	err = mutex_lock_interruptible(&u->bindlock);
+	if (err)
+		return err;
+
+	if (u->addr) {
+		mutex_unlock(&u->bindlock);
+		return -EINVAL;
+	}
+
+	spin_lock(&unix_table_lock);
+	if (__unix_find_socket_byname(sock_net(sk), addr->name, addr->len,
+				      sk->sk_type, hash)) {
+		spin_unlock(&unix_table_lock);
+		mutex_unlock(&u->bindlock);
+		return -EADDRINUSE;
+	}
+	__unix_set_addr(sk, addr, addr->hash);
+	spin_unlock(&unix_table_lock);
+	mutex_unlock(&u->bindlock);
+	return 0;
+}
+
 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;
 	char *sun_path = sunaddr->sun_path;
 	int err;
 	unsigned int hash;
 	struct unix_address *addr;
 
-	err = -EINVAL;
 	if (addr_len < offsetofend(struct sockaddr_un, sun_family) ||
 	    sunaddr->sun_family != AF_UNIX)
-		goto out;
+		return -EINVAL;
 
-	if (addr_len == sizeof(short)) {
-		err = unix_autobind(sock);
-		goto out;
-	}
+	if (addr_len == sizeof(short))
+		return unix_autobind(sock);
 
 	err = unix_mkname(sunaddr, addr_len, &hash);
 	if (err < 0)
-		goto out;
+		return err;
 	addr_len = err;
-	err = -ENOMEM;
 	addr = kmalloc(sizeof(*addr)+addr_len, GFP_KERNEL);
 	if (!addr)
-		goto out;
+		return -ENOMEM;
 
 	memcpy(addr->name, sunaddr, addr_len);
 	addr->len = addr_len;
 	addr->hash = hash ^ sk->sk_type;
 	refcount_set(&addr->refcnt, 1);
 
-	if (sun_path[0]) {
-		struct path path = { };
-		umode_t mode = S_IFSOCK |
-		       (SOCK_INODE(sock)->i_mode & ~current_umask());
-		err = unix_mknod(sun_path, mode, &path);
-		if (err) {
-			if (err == -EEXIST)
-				err = -EADDRINUSE;
-			goto out_addr;
-		}
-
-		err = mutex_lock_interruptible(&u->bindlock);
-		if (err) {
-			path_put(&path);
-			goto out_addr;
-		}
-
-		err = -EINVAL;
-		if (u->addr) {
-			mutex_unlock(&u->bindlock);
-			path_put(&path);
-			goto out_addr;
-		}
-
-		addr->hash = UNIX_HASH_SIZE;
-		hash = d_backing_inode(path.dentry)->i_ino & (UNIX_HASH_SIZE - 1);
-		spin_lock(&unix_table_lock);
-		u->path = path;
-		__unix_set_addr(sk, addr, hash);
-		spin_unlock(&unix_table_lock);
-		mutex_unlock(&u->bindlock);
-		addr = NULL;
-		err = 0;
-	} else {
-		err = mutex_lock_interruptible(&u->bindlock);
-		if (err)
-			goto out_addr;
-
-		err = -EINVAL;
-		if (u->addr) {
-			mutex_unlock(&u->bindlock);
-			goto out_addr;
-		}
-
-		spin_lock(&unix_table_lock);
-		err = -EADDRINUSE;
-		if (__unix_find_socket_byname(net, sunaddr, addr_len,
-					      sk->sk_type, hash)) {
-			spin_unlock(&unix_table_lock);
-			mutex_unlock(&u->bindlock);
-			goto out_addr;
-		}
-		__unix_set_addr(sk, addr, addr->hash);
-		spin_unlock(&unix_table_lock);
-		mutex_unlock(&u->bindlock);
-		addr = NULL;
-		err = 0;
-	}
-out_addr:
-	if (addr)
+	if (sun_path[0])
+		err = unix_bind_bsd(sk, addr);
+	else
+		err = unix_bind_abstract(sk, hash, addr);
+	if (err)
 		unix_release_addr(addr);
-out:
-	return err;
+	return err == -EEXIST ? -EADDRINUSE : err;
 }
 
 static void unix_state_double_lock(struct sock *sk1, struct sock *sk2)
Signature · 1 line
2.11.0
author
#5 lore raw

PATCH 5/8 fold unix_mknod() into unix_bind_bsd()

In reply to Al Viro
---
 net/unix/af_unix.c | 42 +++++++++++++++++-------------------------
 1 file changed, 17 insertions(+), 25 deletions(-)
net/unix/af_unix.c +17 -25
index 04ec7be04909..d5ec0abd389d 100644
@@ -983,46 +983,38 @@ static struct sock *unix_find_other(struct net *net,
 	return NULL;
 }
 
-static int unix_mknod(const char *sun_path, umode_t mode, struct path *res)
+static int unix_bind_bsd(struct sock *sk, struct unix_address *addr)
 {
+	struct unix_sock *u = unix_sk(sk);
+	umode_t mode = S_IFSOCK |
+	       (SOCK_INODE(sk->sk_socket)->i_mode & ~current_umask());
+	struct path parent, path;
+	struct user_namespace *ns; // barf...
 	struct dentry *dentry;
-	struct path path;
-	int err = 0;
+	unsigned int hash;
+	int err;
+
 	/*
 	 * Get the parent directory, calculate the hash for last
 	 * component.
 	 */
-	dentry = kern_path_create(AT_FDCWD, sun_path, &path, 0);
-	err = PTR_ERR(dentry);
+	dentry = kern_path_create(AT_FDCWD, addr->name->sun_path, &parent, 0);
 	if (IS_ERR(dentry))
-		return err;
+		return PTR_ERR(dentry);
+	ns = mnt_user_ns(parent.mnt);
 
 	/*
 	 * All right, let's create it.
 	 */
-	err = security_path_mknod(&path, dentry, mode, 0);
+	err = security_path_mknod(&parent, dentry, mode, 0);
 	if (!err) {
-		err = vfs_mknod(mnt_user_ns(path.mnt), d_inode(path.dentry),
-				dentry, mode, 0);
+		err = vfs_mknod(ns, d_inode(parent.dentry), dentry, mode, 0);
 		if (!err) {
-			res->mnt = mntget(path.mnt);
-			res->dentry = dget(dentry);
+			path.mnt = mntget(parent.mnt);
+			path.dentry = dget(dentry);
 		}
 	}
-	done_path_create(&path, dentry);
-	return err;
-}
-
-static int unix_bind_bsd(struct sock *sk, struct unix_address *addr)
-{
-	struct unix_sock *u = unix_sk(sk);
-	struct path path = { };
-	umode_t mode = S_IFSOCK |
-	       (SOCK_INODE(sk->sk_socket)->i_mode & ~current_umask());
-	unsigned int hash;
-	int err;
-
-	err = unix_mknod(addr->name->sun_path, mode, &path);
+	done_path_create(&parent, dentry);
 	if (err)
 		return err;
 
Signature · 1 line
2.11.0
author
#6 lore raw

PATCH 6/8 unix_bind_bsd(): move done_path_create() call after dealing with ->bindlock

In reply to Al Viro

Final preparations for doing unlink on failure past the successful mknod. We can't hold ->bindlock over ->mknod() or ->unlink(), since either might do sb_start_write() (e.g. on overlayfs). However, we can do it while holding filesystem and VFS locks - doing

	kern_path_create()
	vfs_mknod()
	grab ->bindlock
	if u->addr had been set
		drop ->bindlock
		done_path_create
		return -EINVAL
	else
		assign the address to socket
		drop ->bindlock
		done_path_create
		return 0

would be deadlock-free. Here we massage unix_bind_bsd() to that form. We are still doing equivalent transformations.

Next commit will *not* be an equivalent transformation - it will add a call of vfs_unlink() before done_path_create() in "alread bound" case.

---
 net/unix/af_unix.c | 26 +++++++++++---------------
 1 file changed, 11 insertions(+), 15 deletions(-)
net/unix/af_unix.c +11 -15
index d5ec0abd389d..3c389a6bf670 100644
@@ -988,8 +988,8 @@ static int unix_bind_bsd(struct sock *sk, struct unix_address *addr)
 	struct unix_sock *u = unix_sk(sk);
 	umode_t mode = S_IFSOCK |
 	       (SOCK_INODE(sk->sk_socket)->i_mode & ~current_umask());
-	struct path parent, path;
 	struct user_namespace *ns; // barf...
+	struct path parent;
 	struct dentry *dentry;
 	unsigned int hash;
 	int err;
@@ -1007,36 +1007,32 @@ static int unix_bind_bsd(struct sock *sk, struct unix_address *addr)
 	 * All right, let's create it.
 	 */
 	err = security_path_mknod(&parent, dentry, mode, 0);
-	if (!err) {
+	if (!err)
 		err = vfs_mknod(ns, d_inode(parent.dentry), dentry, mode, 0);
-		if (!err) {
-			path.mnt = mntget(parent.mnt);
-			path.dentry = dget(dentry);
-		}
-	}
-	done_path_create(&parent, dentry);
-	if (err)
+	if (err) {
+		done_path_create(&parent, dentry);
 		return err;
-
+	}
 	err = mutex_lock_interruptible(&u->bindlock);
 	if (err) {
-		path_put(&path);
+		done_path_create(&parent, dentry);
 		return err;
 	}
-
 	if (u->addr) {
 		mutex_unlock(&u->bindlock);
-		path_put(&path);
+		done_path_create(&parent, dentry);
 		return -EINVAL;
 	}
 
 	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.mnt = mntget(parent.mnt);
+	u->path.dentry = dget(dentry);
 	__unix_set_addr(sk, addr, hash);
 	spin_unlock(&unix_table_lock);
 	mutex_unlock(&u->bindlock);
+	done_path_create(&parent, dentry);
 	return 0;
 }
 
Signature · 1 line
2.11.0
author
#7 lore raw

PATCH 7/8 unix_bind_bsd(): unlink if we fail after successful mknod

In reply to Al Viro

We can do that more or less safely, since the parent is held locked all along. Yes, somebody might observe the object via dcache, only to have it disappear afterwards, but there's really no good way to prevent that. It won't race with other bind(2) or attempts to move the sucker elsewhere, or put something else in its place - locked parent prevents that.

---
 net/unix/af_unix.c | 29 ++++++++++++++++-------------
 1 file changed, 16 insertions(+), 13 deletions(-)
net/unix/af_unix.c +16 -13
index 3c389a6bf670..fde3175aa3d3 100644
@@ -1009,20 +1009,13 @@ static int unix_bind_bsd(struct sock *sk, struct unix_address *addr)
 	err = security_path_mknod(&parent, dentry, mode, 0);
 	if (!err)
 		err = vfs_mknod(ns, d_inode(parent.dentry), dentry, mode, 0);
-	if (err) {
-		done_path_create(&parent, dentry);
-		return err;
-	}
+	if (err)
+		goto out;
 	err = mutex_lock_interruptible(&u->bindlock);
-	if (err) {
-		done_path_create(&parent, dentry);
-		return err;
-	}
-	if (u->addr) {
-		mutex_unlock(&u->bindlock);
-		done_path_create(&parent, dentry);
-		return -EINVAL;
-	}
+	if (err)
+		goto out_unlink;
+	if (u->addr)
+		goto out_unlock;
 
 	addr->hash = UNIX_HASH_SIZE;
 	hash = d_backing_inode(dentry)->i_ino & (UNIX_HASH_SIZE - 1);
@@ -1034,6 +1027,16 @@ static int unix_bind_bsd(struct sock *sk, struct unix_address *addr)
 	mutex_unlock(&u->bindlock);
 	done_path_create(&parent, dentry);
 	return 0;
+
+out_unlock:
+	mutex_unlock(&u->bindlock);
+	err = -EINVAL;
+out_unlink:
+	/* failed after successful mknod?  unlink what we'd created... */
+	vfs_unlink(ns, d_inode(parent.dentry), dentry, NULL);
+out:
+	done_path_create(&parent, dentry);
+	return err;
 }
 
 static int unix_bind_abstract(struct sock *sk, unsigned hash,
Signature · 1 line
2.11.0
author
#8 lore raw

PATCH 8/8 __unix_find_socket_byname(): don't pass hash and type separately

In reply to Al Viro

We only care about exclusive or of those, so pass that directly. Makes life simpler for callers as well...

---
 net/unix/af_unix.c | 23 ++++++++++-------------
 1 file changed, 10 insertions(+), 13 deletions(-)
net/unix/af_unix.c +10 -13
index fde3175aa3d3..52c685814685 100644
@@ -286,11 +286,11 @@ 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 int hash)
+					      int len, unsigned int hash)
 {
 	struct sock *s;
 
-	sk_for_each(s, &unix_socket_table[hash ^ type]) {
+	sk_for_each(s, &unix_socket_table[hash]) {
 		struct unix_sock *u = unix_sk(s);
 
 		if (!net_eq(sock_net(s), net))
@@ -305,13 +305,12 @@ static struct sock *__unix_find_socket_byname(struct net *net,
 
 static inline struct sock *unix_find_socket_byname(struct net *net,
 						   struct sockaddr_un *sunname,
-						   int len, int type,
-						   unsigned int hash)
+						   int len, unsigned int hash)
 {
 	struct sock *s;
 
 	spin_lock(&unix_table_lock);
-	s = __unix_find_socket_byname(net, sunname, len, type, hash);
+	s = __unix_find_socket_byname(net, sunname, len, hash);
 	if (s)
 		sock_hold(s);
 	spin_unlock(&unix_table_lock);
@@ -898,12 +897,12 @@ static int unix_autobind(struct socket *sock)
 retry:
 	addr->len = sprintf(addr->name->sun_path+1, "%05x", ordernum) + 1 + sizeof(short);
 	addr->hash = unix_hash_fold(csum_partial(addr->name, addr->len, 0));
+	addr->hash ^= sk->sk_type;
 
 	spin_lock(&unix_table_lock);
 	ordernum = (ordernum+1)&0xFFFFF;
 
-	if (__unix_find_socket_byname(net, addr->name, addr->len, sock->type,
-				      addr->hash)) {
+	if (__unix_find_socket_byname(net, addr->name, addr->len, addr->hash)) {
 		spin_unlock(&unix_table_lock);
 		/*
 		 * __unix_find_socket_byname() may take long time if many names
@@ -918,7 +917,6 @@ static int unix_autobind(struct socket *sock)
 		}
 		goto retry;
 	}
-	addr->hash ^= sk->sk_type;
 
 	__unix_set_addr(sk, addr, addr->hash);
 	spin_unlock(&unix_table_lock);
@@ -965,7 +963,7 @@ static struct sock *unix_find_other(struct net *net,
 		}
 	} else {
 		err = -ECONNREFUSED;
-		u = unix_find_socket_byname(net, sunname, len, type, hash);
+		u = unix_find_socket_byname(net, sunname, len, type ^ hash);
 		if (u) {
 			struct dentry *dentry;
 			dentry = unix_sk(u)->path.dentry;
@@ -1039,8 +1037,7 @@ static int unix_bind_bsd(struct sock *sk, struct unix_address *addr)
 	return err;
 }
 
-static int unix_bind_abstract(struct sock *sk, unsigned hash,
-			      struct unix_address *addr)
+static int unix_bind_abstract(struct sock *sk, struct unix_address *addr)
 {
 	struct unix_sock *u = unix_sk(sk);
 	int err;
@@ -1056,7 +1053,7 @@ static int unix_bind_abstract(struct sock *sk, unsigned hash,
 
 	spin_lock(&unix_table_lock);
 	if (__unix_find_socket_byname(sock_net(sk), addr->name, addr->len,
-				      sk->sk_type, hash)) {
+				      addr->hash)) {
 		spin_unlock(&unix_table_lock);
 		mutex_unlock(&u->bindlock);
 		return -EADDRINUSE;
@@ -1099,7 +1096,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	if (sun_path[0])
 		err = unix_bind_bsd(sk, addr);
 	else
-		err = unix_bind_abstract(sk, hash, addr);
+		err = unix_bind_abstract(sk, addr);
 	if (err)
 		unix_release_addr(addr);
 	return err == -EEXIST ? -EADDRINUSE : err;
Signature · 1 line
2.11.0
#9 lore raw

Re: [PATCH 1/8] af_unix: take address assignment/hash insertion into a new helper

In reply to Al Viro
This series was applied to netdev/net-next.git (refs/heads/master):

Hello:

This series was applied to netdev/net-next.git (refs/heads/master):

Quoted 7 lines · On Sat, 19 Jun 2021 03:50:26 +0000 you wrote:

Duplicated logics in all bind variants (autobind, bind-to-path, bind-to-abstract) gets taken into a common helper.

---
 net/unix/af_unix.c | 26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)

Here is the summary with links:
- [1/8] af_unix: take address assignment/hash insertion into a new helper

    https://git.kernel.org/netdev/net-next/c/185ab886d3fb
  - [2/8] unix_bind(): allocate addr earlier
    https://git.kernel.org/netdev/net-next/c/c34d4582518f
  - [3/8] unix_bind(): separate BSD and abstract cases
    https://git.kernel.org/netdev/net-next/c/aee515170576
  - [4/8] unix_bind(): take BSD and abstract address cases into new helpers
    https://git.kernel.org/netdev/net-next/c/fa42d910a38e
  - [5/8] fold unix_mknod() into unix_bind_bsd()
    https://git.kernel.org/netdev/net-next/c/71e6be6f7d2b
  - [6/8] unix_bind_bsd(): move done_path_create() call after dealing with ->bindlock
    https://git.kernel.org/netdev/net-next/c/56c1731b280d
  - [7/8] unix_bind_bsd(): unlink if we fail after successful mknod
    https://git.kernel.org/netdev/net-next/c/c0c3b8d380a8
  - [8/8] __unix_find_socket_byname(): don't pass hash and type separately
    https://git.kernel.org/netdev/net-next/c/be752283a2a2

You are awesome, thank you!
--
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html