From 38f7bd94a97b542de86a2be9229289717e33a7a4 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 1 Sep 2016 14:56:49 -0700 Subject: Revert "af_unix: Fix splice-bind deadlock" This reverts commit c845acb324aa85a39650a14e7696982ceea75dc1. It turns out that it just replaces one deadlock with another one: we can still get the wrong lock ordering with the readlock due to overlayfs calling back into the filesystem layer and still taking the vfs locks after the readlock. The proper solution ends up being to just split the readlock into two pieces: the bind lock (taken *outside* the vfs locks) and the IO lock (taken *inside* the filesystem locks). The two locks are independent anyway. Signed-off-by: Linus Torvalds Reviewed-by: Shmulik Ladkani Signed-off-by: David S. Miller --- net/unix/af_unix.c | 66 +++++++++++++++++++++--------------------------------- 1 file changed, 26 insertions(+), 40 deletions(-) (limited to 'net/unix/af_unix.c') diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index f1dffe84f0d5..433ae1bbef97 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -954,20 +954,32 @@ fail: return NULL; } -static int unix_mknod(struct dentry *dentry, const struct path *path, umode_t mode, - struct path *res) +static int unix_mknod(const char *sun_path, umode_t mode, struct path *res) { - int err; + 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; - err = security_path_mknod(path, dentry, mode, 0); + /* + * All right, let's create it. + */ + 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; } @@ -978,12 +990,10 @@ 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, name_err; + int 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) @@ -999,34 +1009,14 @@ 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_path; + goto out; 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) @@ -1037,11 +1027,11 @@ 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 (dentry) { - struct path u_path; + if (sun_path[0]) { + struct path path; umode_t mode = S_IFSOCK | (SOCK_INODE(sock)->i_mode & ~current_umask()); - err = unix_mknod(dentry, &path, mode, &u_path); + err = unix_mknod(sun_path, mode, &path); if (err) { if (err == -EEXIST) err = -EADDRINUSE; @@ -1049,9 +1039,9 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto out_up; } addr->hash = UNIX_HASH_SIZE; - hash = d_real_inode(dentry)->i_ino & (UNIX_HASH_SIZE - 1); + hash = d_real_inode(path.dentry)->i_ino & (UNIX_HASH_SIZE - 1); spin_lock(&unix_table_lock); - u->path = u_path; + u->path = path; list = &unix_socket_table[hash]; } else { spin_lock(&unix_table_lock); @@ -1074,10 +1064,6 @@ 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 6e1ce3c3451291142a57c4f3f6f999a29fb5b3bc Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 1 Sep 2016 14:43:53 -0700 Subject: af_unix: split 'u->readlock' into two: 'iolock' and 'bindlock' Right now we use the 'readlock' both for protecting some of the af_unix IO path and for making the bind be single-threaded. The two are independent, but using the same lock makes for a nasty deadlock due to ordering with regards to filesystem locking. The bind locking would want to nest outside the VSF pathname locking, but the IO locking wants to nest inside some of those same locks. We tried to fix this earlier with commit c845acb324aa ("af_unix: Fix splice-bind deadlock") which moved the readlock inside the vfs locks, but that caused problems with overlayfs that will then call back into filesystem routines that take the lock in the wrong order anyway. Splitting the locks means that we can go back to having the bind lock be the outermost lock, and we don't have any deadlocks with lock ordering. Acked-by: Rainer Weikusat Acked-by: Al Viro Signed-off-by: Linus Torvalds Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/net/af_unix.h | 2 +- net/unix/af_unix.c | 45 +++++++++++++++++++++++---------------------- 2 files changed, 24 insertions(+), 23 deletions(-) (limited to 'net/unix/af_unix.c') diff --git a/include/net/af_unix.h b/include/net/af_unix.h index 9b4c418bebd8..fd60eccb59a6 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -52,7 +52,7 @@ struct unix_sock { struct sock sk; struct unix_address *addr; struct path path; - struct mutex readlock; + struct mutex iolock, bindlock; struct sock *peer; struct list_head link; atomic_long_t inflight; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 433ae1bbef97..8309687a56b0 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -661,11 +661,11 @@ static int unix_set_peek_off(struct sock *sk, int val) { struct unix_sock *u = unix_sk(sk); - if (mutex_lock_interruptible(&u->readlock)) + if (mutex_lock_interruptible(&u->iolock)) return -EINTR; sk->sk_peek_off = val; - mutex_unlock(&u->readlock); + mutex_unlock(&u->iolock); return 0; } @@ -779,7 +779,8 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern) spin_lock_init(&u->lock); atomic_long_set(&u->inflight, 0); INIT_LIST_HEAD(&u->link); - mutex_init(&u->readlock); /* single task reading lock */ + mutex_init(&u->iolock); /* single task reading lock */ + mutex_init(&u->bindlock); /* single task binding lock */ init_waitqueue_head(&u->peer_wait); init_waitqueue_func_entry(&u->peer_wake, unix_dgram_peer_wake_relay); unix_insert_socket(unix_sockets_unbound(sk), sk); @@ -848,7 +849,7 @@ static int unix_autobind(struct socket *sock) int err; unsigned int retries = 0; - err = mutex_lock_interruptible(&u->readlock); + err = mutex_lock_interruptible(&u->bindlock); if (err) return err; @@ -895,7 +896,7 @@ retry: spin_unlock(&unix_table_lock); err = 0; -out: mutex_unlock(&u->readlock); +out: mutex_unlock(&u->bindlock); return err; } @@ -1009,7 +1010,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto out; addr_len = err; - err = mutex_lock_interruptible(&u->readlock); + err = mutex_lock_interruptible(&u->bindlock); if (err) goto out; @@ -1063,7 +1064,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) out_unlock: spin_unlock(&unix_table_lock); out_up: - mutex_unlock(&u->readlock); + mutex_unlock(&u->bindlock); out: return err; } @@ -1955,17 +1956,17 @@ static ssize_t unix_stream_sendpage(struct socket *socket, struct page *page, if (false) { alloc_skb: unix_state_unlock(other); - mutex_unlock(&unix_sk(other)->readlock); + mutex_unlock(&unix_sk(other)->iolock); newskb = sock_alloc_send_pskb(sk, 0, 0, flags & MSG_DONTWAIT, &err, 0); if (!newskb) goto err; } - /* we must acquire readlock as we modify already present + /* we must acquire iolock as we modify already present * skbs in the sk_receive_queue and mess with skb->len */ - err = mutex_lock_interruptible(&unix_sk(other)->readlock); + err = mutex_lock_interruptible(&unix_sk(other)->iolock); if (err) { err = flags & MSG_DONTWAIT ? -EAGAIN : -ERESTARTSYS; goto err; @@ -2032,7 +2033,7 @@ alloc_skb: } unix_state_unlock(other); - mutex_unlock(&unix_sk(other)->readlock); + mutex_unlock(&unix_sk(other)->iolock); other->sk_data_ready(other); scm_destroy(&scm); @@ -2041,7 +2042,7 @@ alloc_skb: err_state_unlock: unix_state_unlock(other); err_unlock: - mutex_unlock(&unix_sk(other)->readlock); + mutex_unlock(&unix_sk(other)->iolock); err: kfree_skb(newskb); if (send_sigpipe && !(flags & MSG_NOSIGNAL)) @@ -2109,7 +2110,7 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg, timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); do { - mutex_lock(&u->readlock); + mutex_lock(&u->iolock); skip = sk_peek_offset(sk, flags); skb = __skb_try_recv_datagram(sk, flags, &peeked, &skip, &err, @@ -2117,14 +2118,14 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg, if (skb) break; - mutex_unlock(&u->readlock); + mutex_unlock(&u->iolock); if (err != -EAGAIN) break; } while (timeo && !__skb_wait_for_more_packets(sk, &err, &timeo, last)); - if (!skb) { /* implies readlock unlocked */ + if (!skb) { /* implies iolock unlocked */ unix_state_lock(sk); /* Signal EOF on disconnected non-blocking SEQPACKET socket. */ if (sk->sk_type == SOCK_SEQPACKET && err == -EAGAIN && @@ -2189,7 +2190,7 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg, out_free: skb_free_datagram(sk, skb); - mutex_unlock(&u->readlock); + mutex_unlock(&u->iolock); out: return err; } @@ -2284,7 +2285,7 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state) /* Lock the socket to prevent queue disordering * while sleeps in memcpy_tomsg */ - mutex_lock(&u->readlock); + mutex_lock(&u->iolock); if (flags & MSG_PEEK) skip = sk_peek_offset(sk, flags); @@ -2326,7 +2327,7 @@ again: break; } - mutex_unlock(&u->readlock); + mutex_unlock(&u->iolock); timeo = unix_stream_data_wait(sk, timeo, last, last_len); @@ -2337,7 +2338,7 @@ again: goto out; } - mutex_lock(&u->readlock); + mutex_lock(&u->iolock); goto redo; unlock: unix_state_unlock(sk); @@ -2440,7 +2441,7 @@ unlock: } } while (size); - mutex_unlock(&u->readlock); + mutex_unlock(&u->iolock); if (state->msg) scm_recv(sock, state->msg, &scm, flags); else @@ -2481,9 +2482,9 @@ static ssize_t skb_unix_socket_splice(struct sock *sk, int ret; struct unix_sock *u = unix_sk(sk); - mutex_unlock(&u->readlock); + mutex_unlock(&u->iolock); ret = splice_to_pipe(pipe, spd); - mutex_lock(&u->readlock); + mutex_lock(&u->iolock); return ret; } -- cgit v1.2.3 From 25869262ef7af24ccde988867ac3eb1c3d4b88d4 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 17 Sep 2016 21:02:10 -0400 Subject: skb_splice_bits(): get rid of callback since pipe_lock is the outermost now, we don't need to drop/regain socket locks around the call of splice_to_pipe() from skb_splice_bits(), which kills the need to have a socket-specific callback; we can just call splice_to_pipe() and be done with that. Signed-off-by: Al Viro --- include/linux/skbuff.h | 8 +------- net/core/skbuff.c | 28 ++-------------------------- net/ipv4/tcp.c | 3 +-- net/kcm/kcmsock.c | 16 +--------------- net/unix/af_unix.c | 17 +---------------- 5 files changed, 6 insertions(+), 66 deletions(-) (limited to 'net/unix/af_unix.c') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 0f665cb26b50..f520251ec43f 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3021,15 +3021,9 @@ int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len); int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len); __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, u8 *to, int len, __wsum csum); -ssize_t skb_socket_splice(struct sock *sk, - struct pipe_inode_info *pipe, - struct splice_pipe_desc *spd); int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset, struct pipe_inode_info *pipe, unsigned int len, - unsigned int flags, - ssize_t (*splice_cb)(struct sock *, - struct pipe_inode_info *, - struct splice_pipe_desc *)); + unsigned int flags); void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to); unsigned int skb_zerocopy_headlen(const struct sk_buff *from); int skb_zerocopy(struct sk_buff *to, struct sk_buff *from, diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 3864b4b68fa1..208a9bc4af74 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1962,37 +1962,13 @@ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, return false; } -ssize_t skb_socket_splice(struct sock *sk, - struct pipe_inode_info *pipe, - struct splice_pipe_desc *spd) -{ - int ret; - - /* Drop the socket lock, otherwise we have reverse - * locking dependencies between sk_lock and i_mutex - * here as compared to sendfile(). We enter here - * with the socket lock held, and splice_to_pipe() will - * grab the pipe inode lock. For sendfile() emulation, - * we call into ->sendpage() with the i_mutex lock held - * and networking will grab the socket lock. - */ - release_sock(sk); - ret = splice_to_pipe(pipe, spd); - lock_sock(sk); - - return ret; -} - /* * Map data from the skb to a pipe. Should handle both the linear part, * the fragments, and the frag list. */ int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset, struct pipe_inode_info *pipe, unsigned int tlen, - unsigned int flags, - ssize_t (*splice_cb)(struct sock *, - struct pipe_inode_info *, - struct splice_pipe_desc *)) + unsigned int flags) { struct partial_page partial[MAX_SKB_FRAGS]; struct page *pages[MAX_SKB_FRAGS]; @@ -2009,7 +1985,7 @@ int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset, __skb_splice_bits(skb, pipe, &offset, &tlen, &spd, sk); if (spd.nr_pages) - ret = splice_cb(sk, pipe, &spd); + ret = splice_to_pipe(pipe, &spd); return ret; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index ffbb218de520..ddd2179538f7 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -688,8 +688,7 @@ static int tcp_splice_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, int ret; ret = skb_splice_bits(skb, skb->sk, offset, tss->pipe, - min(rd_desc->count, len), tss->flags, - skb_socket_splice); + min(rd_desc->count, len), tss->flags); if (ret > 0) rd_desc->count -= ret; return ret; diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 411693288648..8a720ba50061 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -1462,19 +1462,6 @@ out: return copied ? : err; } -static ssize_t kcm_sock_splice(struct sock *sk, - struct pipe_inode_info *pipe, - struct splice_pipe_desc *spd) -{ - int ret; - - release_sock(sk); - ret = splice_to_pipe(pipe, spd); - lock_sock(sk); - - return ret; -} - static ssize_t kcm_splice_read(struct socket *sock, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) @@ -1504,8 +1491,7 @@ static ssize_t kcm_splice_read(struct socket *sock, loff_t *ppos, if (len > rxm->full_len) len = rxm->full_len; - copied = skb_splice_bits(skb, sk, rxm->offset, pipe, len, flags, - kcm_sock_splice); + copied = skb_splice_bits(skb, sk, rxm->offset, pipe, len, flags); if (copied < 0) { err = copied; goto err_out; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 8309687a56b0..145082e2ba36 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2475,28 +2475,13 @@ static int unix_stream_recvmsg(struct socket *sock, struct msghdr *msg, return unix_stream_read_generic(&state); } -static ssize_t skb_unix_socket_splice(struct sock *sk, - struct pipe_inode_info *pipe, - struct splice_pipe_desc *spd) -{ - int ret; - struct unix_sock *u = unix_sk(sk); - - mutex_unlock(&u->iolock); - ret = splice_to_pipe(pipe, spd); - mutex_lock(&u->iolock); - - return ret; -} - static int unix_stream_splice_actor(struct sk_buff *skb, int skip, int chunk, struct unix_stream_read_state *state) { return skb_splice_bits(skb, state->socket->sk, UNIXCB(skb).consumed + skip, - state->pipe, chunk, state->splice_flags, - skb_unix_socket_splice); + state->pipe, chunk, state->splice_flags); } static ssize_t unix_stream_splice_read(struct socket *sock, loff_t *ppos, -- cgit v1.2.3