From 4c6e734a347b811980593de1cd5561b7a6af89bf Mon Sep 17 00:00:00 2001 From: Rainer Weikusat Date: Sun, 3 Jan 2016 18:56:38 +0000 Subject: af_unix: Fix splice-bind deadlock [ Upstream commit c845acb324aa85a39650a14e7696982ceea75dc1 ] 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). Dmitry Vyukov() tested the original patch. Signed-off-by: Rainer Weikusat Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/unix/af_unix.c | 66 +++++++++++++++++++++++++++++++++--------------------- 1 file changed, 40 insertions(+), 26 deletions(-) (limited to 'net/unix/af_unix.c') diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 0fc6dbaed39c..0e7bf2b3d42f 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -952,32 +952,20 @@ 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; } @@ -988,10 +976,12 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) struct unix_sock *u = unix_sk(sk); struct sockaddr_un *sunaddr = (struct sockaddr_un *)uaddr; char *sun_path = sunaddr->sun_path; - int err; + int err, name_err; 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) @@ -1007,14 +997,34 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto out; addr_len = err; + name_err = 0; + 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); + + if (IS_ERR(dentry)) { + /* delay report until after 'already bound' check */ + name_err = PTR_ERR(dentry); + dentry = NULL; + } + } + err = mutex_lock_interruptible(&u->readlock); if (err) - goto out; + goto out_path; err = -EINVAL; if (u->addr) goto out_up; + if (name_err) { + err = name_err == -EEXIST ? -EADDRINUSE : name_err; + goto out_up; + } + err = -ENOMEM; addr = kmalloc(sizeof(*addr)+addr_len, GFP_KERNEL); if (!addr) @@ -1025,11 +1035,11 @@ 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; @@ -1037,9 +1047,9 @@ 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); @@ -1062,6 +1072,10 @@ 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; } -- cgit v1.2.3 From 9b8b611fe0f86f07a4ff4a5f3bcb0ea7ceb7da3b Mon Sep 17 00:00:00 2001 From: willy tarreau Date: Sun, 10 Jan 2016 07:54:56 +0100 Subject: unix: properly account for FDs passed over unix sockets [ Upstream commit 712f4aad406bb1ed67f3f98d04c044191f0ff593 ] It is possible for a process to allocate and accumulate far more FDs than the process' limit by sending them over a unix socket then closing them to keep the process' fd count low. This change addresses this problem by keeping track of the number of FDs in flight per user and preventing non-privileged processes from having more FDs in flight than their configured FD limit. Reported-by: socketpair@gmail.com Reported-by: Tetsuo Handa Mitigates: CVE-2013-4312 (Linux 2.0+) Suggested-by: Linus Torvalds Acked-by: Hannes Frederic Sowa Signed-off-by: Willy Tarreau Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- include/linux/sched.h | 1 + net/unix/af_unix.c | 24 ++++++++++++++++++++---- net/unix/garbage.c | 13 ++++++++----- 3 files changed, 29 insertions(+), 9 deletions(-) (limited to 'net/unix/af_unix.c') diff --git a/include/linux/sched.h b/include/linux/sched.h index b7b9501b41af..f477e87ca46f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -830,6 +830,7 @@ struct user_struct { unsigned long mq_bytes; /* How many bytes can be allocated to mqueue? */ #endif unsigned long locked_shm; /* How many pages of mlocked shm ? */ + unsigned long unix_inflight; /* How many files in flight in unix sockets */ #ifdef CONFIG_KEYS struct key *uid_keyring; /* UID specific keyring */ diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 0e7bf2b3d42f..7926de14e930 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1512,6 +1512,21 @@ static void unix_destruct_scm(struct sk_buff *skb) sock_wfree(skb); } +/* + * The "user->unix_inflight" variable is protected by the garbage + * collection lock, and we just read it locklessly here. If you go + * over the limit, there might be a tiny race in actually noticing + * it across threads. Tough. + */ +static inline bool too_many_unix_fds(struct task_struct *p) +{ + struct user_struct *user = current_user(); + + if (unlikely(user->unix_inflight > task_rlimit(p, RLIMIT_NOFILE))) + return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN); + return false; +} + #define MAX_RECURSION_LEVEL 4 static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) @@ -1520,6 +1535,9 @@ static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) unsigned char max_level = 0; int unix_sock_count = 0; + if (too_many_unix_fds(current)) + return -ETOOMANYREFS; + for (i = scm->fp->count - 1; i >= 0; i--) { struct sock *sk = unix_get_socket(scm->fp->fp[i]); @@ -1541,10 +1559,8 @@ static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) if (!UNIXCB(skb).fp) return -ENOMEM; - if (unix_sock_count) { - for (i = scm->fp->count - 1; i >= 0; i--) - unix_inflight(scm->fp->fp[i]); - } + for (i = scm->fp->count - 1; i >= 0; i--) + unix_inflight(scm->fp->fp[i]); return max_level; } diff --git a/net/unix/garbage.c b/net/unix/garbage.c index a73a226f2d33..8fcdc2283af5 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -120,11 +120,11 @@ void unix_inflight(struct file *fp) { struct sock *s = unix_get_socket(fp); + spin_lock(&unix_gc_lock); + if (s) { struct unix_sock *u = unix_sk(s); - spin_lock(&unix_gc_lock); - if (atomic_long_inc_return(&u->inflight) == 1) { BUG_ON(!list_empty(&u->link)); list_add_tail(&u->link, &gc_inflight_list); @@ -132,25 +132,28 @@ void unix_inflight(struct file *fp) BUG_ON(list_empty(&u->link)); } unix_tot_inflight++; - spin_unlock(&unix_gc_lock); } + fp->f_cred->user->unix_inflight++; + spin_unlock(&unix_gc_lock); } void unix_notinflight(struct file *fp) { struct sock *s = unix_get_socket(fp); + spin_lock(&unix_gc_lock); + if (s) { struct unix_sock *u = unix_sk(s); - spin_lock(&unix_gc_lock); BUG_ON(list_empty(&u->link)); if (atomic_long_dec_and_test(&u->inflight)) list_del_init(&u->link); unix_tot_inflight--; - spin_unlock(&unix_gc_lock); } + fp->f_cred->user->unix_inflight--; + spin_unlock(&unix_gc_lock); } static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *), -- cgit v1.2.3