diff options
Diffstat (limited to 'net/unix/af_unix.c')
| -rw-r--r-- | net/unix/af_unix.c | 1054 |
1 files changed, 599 insertions, 455 deletions
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 9a6ad5974dff..52b155123985 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -77,46 +77,40 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include <linux/module.h> -#include <linux/kernel.h> -#include <linux/signal.h> -#include <linux/sched/signal.h> -#include <linux/errno.h> -#include <linux/string.h> -#include <linux/stat.h> +#include <linux/bpf-cgroup.h> +#include <linux/btf_ids.h> #include <linux/dcache.h> -#include <linux/namei.h> -#include <linux/socket.h> -#include <linux/un.h> +#include <linux/errno.h> #include <linux/fcntl.h> +#include <linux/file.h> #include <linux/filter.h> -#include <linux/termios.h> -#include <linux/sockios.h> -#include <linux/net.h> -#include <linux/in.h> #include <linux/fs.h> -#include <linux/slab.h> -#include <linux/uaccess.h> -#include <linux/skbuff.h> -#include <linux/netdevice.h> -#include <net/net_namespace.h> -#include <net/sock.h> -#include <net/tcp_states.h> -#include <net/af_unix.h> -#include <linux/proc_fs.h> -#include <linux/seq_file.h> -#include <net/scm.h> +#include <linux/fs_struct.h> #include <linux/init.h> -#include <linux/poll.h> -#include <linux/rtnetlink.h> +#include <linux/kernel.h> #include <linux/mount.h> -#include <net/checksum.h> +#include <linux/namei.h> +#include <linux/net.h> +#include <linux/pidfs.h> +#include <linux/poll.h> +#include <linux/proc_fs.h> +#include <linux/sched/signal.h> #include <linux/security.h> +#include <linux/seq_file.h> +#include <linux/skbuff.h> +#include <linux/slab.h> +#include <linux/socket.h> #include <linux/splice.h> -#include <linux/freezer.h> -#include <linux/file.h> -#include <linux/btf_ids.h> -#include <linux/bpf-cgroup.h> +#include <linux/string.h> +#include <linux/uaccess.h> +#include <net/af_unix.h> +#include <net/net_namespace.h> +#include <net/scm.h> +#include <net/tcp_states.h> +#include <uapi/linux/sockios.h> +#include <uapi/linux/termios.h> + +#include "af_unix.h" static atomic_long_t unix_nr_socks; static struct hlist_head bsd_socket_buckets[UNIX_HASH_SIZE / 2]; @@ -126,6 +120,81 @@ static spinlock_t bsd_socket_locks[UNIX_HASH_SIZE / 2]; * hash table is protected with spinlock. * each socket state is protected by separate spinlock. */ +#ifdef CONFIG_PROVE_LOCKING +#define cmp_ptr(l, r) (((l) > (r)) - ((l) < (r))) + +static int unix_table_lock_cmp_fn(const struct lockdep_map *a, + const struct lockdep_map *b) +{ + return cmp_ptr(a, b); +} + +static int unix_state_lock_cmp_fn(const struct lockdep_map *_a, + const struct lockdep_map *_b) +{ + const struct unix_sock *a, *b; + + a = container_of(_a, struct unix_sock, lock.dep_map); + b = container_of(_b, struct unix_sock, lock.dep_map); + + if (a->sk.sk_state == TCP_LISTEN) { + /* unix_stream_connect(): Before the 2nd unix_state_lock(), + * + * 1. a is TCP_LISTEN. + * 2. b is not a. + * 3. concurrent connect(b -> a) must fail. + * + * Except for 2. & 3., the b's state can be any possible + * value due to concurrent connect() or listen(). + * + * 2. is detected in debug_spin_lock_before(), and 3. cannot + * be expressed as lock_cmp_fn. + */ + switch (b->sk.sk_state) { + case TCP_CLOSE: + case TCP_ESTABLISHED: + case TCP_LISTEN: + return -1; + default: + /* Invalid case. */ + return 0; + } + } + + /* Should never happen. Just to be symmetric. */ + if (b->sk.sk_state == TCP_LISTEN) { + switch (b->sk.sk_state) { + case TCP_CLOSE: + case TCP_ESTABLISHED: + return 1; + default: + return 0; + } + } + + /* unix_state_double_lock(): ascending address order. */ + return cmp_ptr(a, b); +} + +static int unix_recvq_lock_cmp_fn(const struct lockdep_map *_a, + const struct lockdep_map *_b) +{ + const struct sock *a, *b; + + a = container_of(_a, struct sock, sk_receive_queue.lock.dep_map); + b = container_of(_b, struct sock, sk_receive_queue.lock.dep_map); + + /* unix_collect_skb(): listener -> embryo order. */ + if (a->sk_state == TCP_LISTEN && unix_sk(b)->listener == a) + return -1; + + /* Should never happen. Just to be symmetric. */ + if (b->sk_state == TCP_LISTEN && unix_sk(a)->listener == b) + return 1; + + return 0; +} +#endif static unsigned int unix_unbound_hash(struct sock *sk) { @@ -168,7 +237,7 @@ static void unix_table_double_lock(struct net *net, swap(hash1, hash2); spin_lock(&net->unx.table.locks[hash1]); - spin_lock_nested(&net->unx.table.locks[hash2], SINGLE_DEPTH_NESTING); + spin_lock(&net->unx.table.locks[hash2]); } static void unix_table_double_unlock(struct net *net, @@ -211,25 +280,14 @@ static inline bool unix_secdata_eq(struct scm_cookie *scm, struct sk_buff *skb) } #endif /* CONFIG_SECURITY_NETWORK */ -static inline int unix_our_peer(struct sock *sk, struct sock *osk) -{ - return unix_peer(osk) == sk; -} - static inline int unix_may_send(struct sock *sk, struct sock *osk) { - return unix_peer(osk) == NULL || unix_our_peer(sk, osk); -} - -static inline int unix_recvq_full(const struct sock *sk) -{ - return skb_queue_len(&sk->sk_receive_queue) > sk->sk_max_ack_backlog; + return !unix_peer(osk) || unix_peer(osk) == sk; } static inline int unix_recvq_full_lockless(const struct sock *sk) { - return skb_queue_len_lockless(&sk->sk_receive_queue) > - READ_ONCE(sk->sk_max_ack_backlog); + return skb_queue_len_lockless(&sk->sk_receive_queue) > sk->sk_max_ack_backlog; } struct sock *unix_peer_get(struct sock *s) @@ -530,10 +588,10 @@ static int unix_dgram_peer_wake_me(struct sock *sk, struct sock *other) return 0; } -static int unix_writable(const struct sock *sk) +static int unix_writable(const struct sock *sk, unsigned char state) { - return sk->sk_state != TCP_LISTEN && - (refcount_read(&sk->sk_wmem_alloc) << 2) <= sk->sk_sndbuf; + return state != TCP_LISTEN && + (refcount_read(&sk->sk_wmem_alloc) << 2) <= READ_ONCE(sk->sk_sndbuf); } static void unix_write_space(struct sock *sk) @@ -541,12 +599,12 @@ static void unix_write_space(struct sock *sk) struct socket_wq *wq; rcu_read_lock(); - if (unix_writable(sk)) { + if (unix_writable(sk, READ_ONCE(sk->sk_state))) { wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible_sync_poll(&wq->wait, EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND); - sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); + sk_wake_async_rcu(sk, SOCK_WAKE_SPACE, POLL_OUT); } rcu_read_unlock(); } @@ -558,7 +616,9 @@ static void unix_write_space(struct sock *sk) static void unix_dgram_disconnected(struct sock *sk, struct sock *other) { if (!skb_queue_empty(&sk->sk_receive_queue)) { - skb_queue_purge(&sk->sk_receive_queue); + skb_queue_purge_reason(&sk->sk_receive_queue, + SKB_DROP_REASON_UNIX_DISCONNECT); + wake_up_interruptible_all(&unix_sk(sk)->peer_wait); /* If one link of bidirectional dgram pipe is disconnected, @@ -570,14 +630,13 @@ static void unix_dgram_disconnected(struct sock *sk, struct sock *other) sk_error_report(other); } } - other->sk_state = TCP_CLOSE; } static void unix_sock_destructor(struct sock *sk) { struct unix_sock *u = unix_sk(sk); - skb_queue_purge(&sk->sk_receive_queue); + skb_queue_purge_reason(&sk->sk_receive_queue, SKB_DROP_REASON_SOCKET_CLOSE); DEBUG_NET_WARN_ON_ONCE(refcount_read(&sk->sk_wmem_alloc)); DEBUG_NET_WARN_ON_ONCE(!sk_unhashed(sk)); @@ -587,6 +646,9 @@ static void unix_sock_destructor(struct sock *sk) return; } + if (sk->sk_peer_pid) + pidfs_put_pid(sk->sk_peer_pid); + if (u->addr) unix_release_addr(u->addr); @@ -598,6 +660,11 @@ static void unix_sock_destructor(struct sock *sk) #endif } +static unsigned int unix_skb_len(const struct sk_buff *skb) +{ + return skb->len - UNIXCB(skb).consumed; +} + static void unix_release_sock(struct sock *sk, int embrion) { struct unix_sock *u = unix_sk(sk); @@ -617,7 +684,7 @@ static void unix_release_sock(struct sock *sk, int embrion) u->path.dentry = NULL; u->path.mnt = NULL; state = sk->sk_state; - sk->sk_state = TCP_CLOSE; + WRITE_ONCE(sk->sk_state, TCP_CLOSE); skpair = unix_peer(sk); unix_peer(sk) = NULL; @@ -625,20 +692,23 @@ static void unix_release_sock(struct sock *sk, int embrion) unix_state_unlock(sk); #if IS_ENABLED(CONFIG_AF_UNIX_OOB) - if (u->oob_skb) { - kfree_skb(u->oob_skb); - u->oob_skb = NULL; - } + u->oob_skb = NULL; #endif wake_up_interruptible_all(&u->peer_wait); if (skpair != NULL) { if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) { + struct sk_buff *skb = skb_peek(&sk->sk_receive_queue); + +#if IS_ENABLED(CONFIG_AF_UNIX_OOB) + if (skb && !unix_skb_len(skb)) + skb = skb_peek_next(skb, &sk->sk_receive_queue); +#endif unix_state_lock(skpair); /* No more writes */ WRITE_ONCE(skpair->sk_shutdown, SHUTDOWN_MASK); - if (!skb_queue_empty(&sk->sk_receive_queue) || embrion) + if (skb || embrion) WRITE_ONCE(skpair->sk_err, ECONNRESET); unix_state_unlock(skpair); skpair->sk_state_change(skpair); @@ -654,9 +724,9 @@ static void unix_release_sock(struct sock *sk, int embrion) while ((skb = skb_dequeue(&sk->sk_receive_queue)) != NULL) { if (state == TCP_LISTEN) unix_release_sock(skb->sk, 1); - /* passed fds are erased in the kfree_skb hook */ - UNIXCB(skb).consumed = skb->len; - kfree_skb(skb); + + /* passed fds are erased in the kfree_skb hook */ + kfree_skb_reason(skb, SKB_DROP_REASON_SOCKET_CLOSE); } if (path.dentry) @@ -681,7 +751,48 @@ static void unix_release_sock(struct sock *sk, int embrion) unix_gc(); /* Garbage collect fds */ } -static void init_peercred(struct sock *sk) +struct unix_peercred { + struct pid *peer_pid; + const struct cred *peer_cred; +}; + +static inline int prepare_peercred(struct unix_peercred *peercred) +{ + struct pid *pid; + int err; + + pid = task_tgid(current); + err = pidfs_register_pid(pid); + if (likely(!err)) { + peercred->peer_pid = get_pid(pid); + peercred->peer_cred = get_current_cred(); + } + return err; +} + +static void drop_peercred(struct unix_peercred *peercred) +{ + const struct cred *cred = NULL; + struct pid *pid = NULL; + + might_sleep(); + + swap(peercred->peer_pid, pid); + swap(peercred->peer_cred, cred); + + pidfs_put_pid(pid); + put_pid(pid); + put_cred(cred); +} + +static inline void init_peercred(struct sock *sk, + const struct unix_peercred *peercred) +{ + sk->sk_peer_pid = peercred->peer_pid; + sk->sk_peer_cred = peercred->peer_cred; +} + +static void update_peercred(struct sock *sk, struct unix_peercred *peercred) { const struct cred *old_cred; struct pid *old_pid; @@ -689,36 +800,27 @@ static void init_peercred(struct sock *sk) spin_lock(&sk->sk_peer_lock); old_pid = sk->sk_peer_pid; old_cred = sk->sk_peer_cred; - sk->sk_peer_pid = get_pid(task_tgid(current)); - sk->sk_peer_cred = get_current_cred(); + init_peercred(sk, peercred); spin_unlock(&sk->sk_peer_lock); - put_pid(old_pid); - put_cred(old_cred); + peercred->peer_pid = old_pid; + peercred->peer_cred = old_cred; } static void copy_peercred(struct sock *sk, struct sock *peersk) { - const struct cred *old_cred; - struct pid *old_pid; + lockdep_assert_held(&unix_sk(peersk)->lock); - if (sk < peersk) { - spin_lock(&sk->sk_peer_lock); - spin_lock_nested(&peersk->sk_peer_lock, SINGLE_DEPTH_NESTING); - } else { - spin_lock(&peersk->sk_peer_lock); - spin_lock_nested(&sk->sk_peer_lock, SINGLE_DEPTH_NESTING); - } - old_pid = sk->sk_peer_pid; - old_cred = sk->sk_peer_cred; - sk->sk_peer_pid = get_pid(peersk->sk_peer_pid); + spin_lock(&sk->sk_peer_lock); + sk->sk_peer_pid = get_pid(peersk->sk_peer_pid); + pidfs_get_pid(sk->sk_peer_pid); sk->sk_peer_cred = get_cred(peersk->sk_peer_cred); - spin_unlock(&sk->sk_peer_lock); - spin_unlock(&peersk->sk_peer_lock); +} - put_pid(old_pid); - put_cred(old_cred); +static bool unix_may_passcred(const struct sock *sk) +{ + return sk->sk_scm_credentials || sk->sk_scm_pidfd; } static int unix_listen(struct socket *sock, int backlog) @@ -726,26 +828,32 @@ static int unix_listen(struct socket *sock, int backlog) int err; struct sock *sk = sock->sk; struct unix_sock *u = unix_sk(sk); + struct unix_peercred peercred = {}; err = -EOPNOTSUPP; if (sock->type != SOCK_STREAM && sock->type != SOCK_SEQPACKET) goto out; /* Only stream/seqpacket sockets accept */ err = -EINVAL; - if (!u->addr) + if (!READ_ONCE(u->addr)) goto out; /* No listens on an unbound socket */ + err = prepare_peercred(&peercred); + if (err) + goto out; unix_state_lock(sk); if (sk->sk_state != TCP_CLOSE && sk->sk_state != TCP_LISTEN) goto out_unlock; if (backlog > sk->sk_max_ack_backlog) wake_up_interruptible_all(&u->peer_wait); sk->sk_max_ack_backlog = backlog; - sk->sk_state = TCP_LISTEN; + WRITE_ONCE(sk->sk_state, TCP_LISTEN); + /* set credentials so connect can copy them */ - init_peercred(sk); + update_peercred(sk, &peercred); err = 0; out_unlock: unix_state_unlock(sk); + drop_peercred(&peercred); out: return err; } @@ -755,7 +863,7 @@ static int unix_bind(struct socket *, struct sockaddr *, int); static int unix_stream_connect(struct socket *, struct sockaddr *, int addr_len, int flags); static int unix_socketpair(struct socket *, struct socket *); -static int unix_accept(struct socket *, struct socket *, int, bool); +static int unix_accept(struct socket *, struct socket *, struct proto_accept_arg *arg); static int unix_getname(struct socket *, struct sockaddr *, int); static __poll_t unix_poll(struct file *, struct socket *, poll_table *); static __poll_t unix_dgram_poll(struct file *, struct socket *, @@ -905,13 +1013,6 @@ static void unix_close(struct sock *sk, long timeout) */ } -static void unix_unhash(struct sock *sk) -{ - /* Nothing to do here, unix socket does not need a ->unhash(). - * This is merely for sockmap. - */ -} - static bool unix_bpf_bypass_getsockopt(int level, int optname) { if (level == SOL_SOCKET) { @@ -942,7 +1043,6 @@ struct proto unix_stream_proto = { .owner = THIS_MODULE, .obj_size = sizeof(struct unix_sock), .close = unix_close, - .unhash = unix_unhash, .bpf_bypass_getsockopt = unix_bpf_bypass_getsockopt, #ifdef CONFIG_BPF_SYSCALL .psock_update_sk_prot = unix_stream_bpf_update_proto, @@ -973,17 +1073,21 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern, sock_init_data(sock, sk); + sk->sk_scm_rights = 1; sk->sk_hash = unix_unbound_hash(sk); sk->sk_allocation = GFP_KERNEL_ACCOUNT; sk->sk_write_space = unix_write_space; - sk->sk_max_ack_backlog = net->unx.sysctl_max_dgram_qlen; + sk->sk_max_ack_backlog = READ_ONCE(net->unx.sysctl_max_dgram_qlen); sk->sk_destruct = unix_sock_destructor; + lock_set_cmp_fn(&sk->sk_receive_queue.lock, unix_recvq_lock_cmp_fn, NULL); + u = unix_sk(sk); - u->inflight = 0; + u->listener = NULL; + u->vertex = NULL; u->path.dentry = NULL; u->path.mnt = NULL; spin_lock_init(&u->lock); - INIT_LIST_HEAD(&u->link); + lock_set_cmp_fn(&u->lock, unix_state_lock_cmp_fn, NULL); mutex_init(&u->iolock); /* single task reading lock */ mutex_init(&u->bindlock); /* single task binding lock */ init_waitqueue_head(&u->peer_wait); @@ -1053,7 +1157,7 @@ static int unix_release(struct socket *sock) } static struct sock *unix_find_bsd(struct sockaddr_un *sunaddr, int addr_len, - int type) + int type, int flags) { struct inode *inode; struct path path; @@ -1061,13 +1165,39 @@ static struct sock *unix_find_bsd(struct sockaddr_un *sunaddr, int addr_len, int err; unix_mkname_bsd(sunaddr, addr_len); - err = kern_path(sunaddr->sun_path, LOOKUP_FOLLOW, &path); - if (err) - goto fail; - err = path_permission(&path, MAY_WRITE); - if (err) - goto path_put; + if (flags & SOCK_COREDUMP) { + const struct cred *cred; + struct cred *kcred; + struct path root; + + kcred = prepare_kernel_cred(&init_task); + if (!kcred) { + err = -ENOMEM; + goto fail; + } + + task_lock(&init_task); + get_fs_root(init_task.fs, &root); + task_unlock(&init_task); + + cred = override_creds(kcred); + err = vfs_path_lookup(root.dentry, root.mnt, sunaddr->sun_path, + LOOKUP_BENEATH | LOOKUP_NO_SYMLINKS | + LOOKUP_NO_MAGICLINKS, &path); + put_cred(revert_creds(cred)); + path_put(&root); + if (err) + goto fail; + } else { + err = kern_path(sunaddr->sun_path, LOOKUP_FOLLOW, &path); + if (err) + goto fail; + + err = path_permission(&path, MAY_WRITE); + if (err) + goto path_put; + } err = -ECONNREFUSED; inode = d_backing_inode(path.dentry); @@ -1117,12 +1247,12 @@ static struct sock *unix_find_abstract(struct net *net, static struct sock *unix_find_other(struct net *net, struct sockaddr_un *sunaddr, - int addr_len, int type) + int addr_len, int type, int flags) { struct sock *sk; if (sunaddr->sun_path[0]) - sk = unix_find_bsd(sunaddr, addr_len, type); + sk = unix_find_bsd(sunaddr, addr_len, type, flags); else sk = unix_find_abstract(net, sunaddr, addr_len, type); @@ -1131,8 +1261,8 @@ static struct sock *unix_find_other(struct net *net, static int unix_autobind(struct sock *sk) { - unsigned int new_hash, old_hash = sk->sk_hash; struct unix_sock *u = unix_sk(sk); + unsigned int new_hash, old_hash; struct net *net = sock_net(sk); struct unix_address *addr; u32 lastnum, ordernum; @@ -1155,6 +1285,7 @@ static int unix_autobind(struct sock *sk) addr->name->sun_family = AF_UNIX; refcount_set(&addr->refcnt, 1); + old_hash = sk->sk_hash; ordernum = get_random_u32(); lastnum = ordernum & 0xFFFFF; retry: @@ -1195,8 +1326,8 @@ static int unix_bind_bsd(struct sock *sk, struct sockaddr_un *sunaddr, { umode_t mode = S_IFSOCK | (SOCK_INODE(sk->sk_socket)->i_mode & ~current_umask()); - unsigned int new_hash, old_hash = sk->sk_hash; struct unix_sock *u = unix_sk(sk); + unsigned int new_hash, old_hash; struct net *net = sock_net(sk); struct mnt_idmap *idmap; struct unix_address *addr; @@ -1234,6 +1365,7 @@ static int unix_bind_bsd(struct sock *sk, struct sockaddr_un *sunaddr, if (u->addr) goto out_unlock; + old_hash = sk->sk_hash; new_hash = unix_bsd_hash(d_backing_inode(dentry)); unix_table_double_lock(net, old_hash, new_hash); u->path.mnt = mntget(parent.mnt); @@ -1261,8 +1393,8 @@ out: static int unix_bind_abstract(struct sock *sk, struct sockaddr_un *sunaddr, int addr_len) { - unsigned int new_hash, old_hash = sk->sk_hash; struct unix_sock *u = unix_sk(sk); + unsigned int new_hash, old_hash; struct net *net = sock_net(sk); struct unix_address *addr; int err; @@ -1280,6 +1412,7 @@ static int unix_bind_abstract(struct sock *sk, struct sockaddr_un *sunaddr, goto out_mutex; } + old_hash = sk->sk_hash; new_hash = unix_abstract_hash(addr->name, addr->len, sk->sk_type); unix_table_double_lock(net, old_hash, new_hash); @@ -1329,11 +1462,12 @@ static void unix_state_double_lock(struct sock *sk1, struct sock *sk2) unix_state_lock(sk1); return; } + if (sk1 > sk2) swap(sk1, sk2); unix_state_lock(sk1); - unix_state_lock_nested(sk2, U_LOCK_SECOND); + unix_state_lock(sk2); } static void unix_state_double_unlock(struct sock *sk1, struct sock *sk2) @@ -1367,16 +1501,14 @@ static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr, if (err) goto out; - if ((test_bit(SOCK_PASSCRED, &sock->flags) || - test_bit(SOCK_PASSPIDFD, &sock->flags)) && - !unix_sk(sk)->addr) { + if (unix_may_passcred(sk) && !READ_ONCE(unix_sk(sk)->addr)) { err = unix_autobind(sk); if (err) goto out; } restart: - other = unix_find_other(sock_net(sk), sunaddr, alen, sock->type); + other = unix_find_other(sock_net(sk), sunaddr, alen, sock->type, 0); if (IS_ERR(other)) { err = PTR_ERR(other); goto out; @@ -1399,7 +1531,8 @@ restart: if (err) goto out_unlock; - sk->sk_state = other->sk_state = TCP_ESTABLISHED; + WRITE_ONCE(sk->sk_state, TCP_ESTABLISHED); + WRITE_ONCE(other->sk_state, TCP_ESTABLISHED); } else { /* * 1003.1g breaking connected state with AF_UNSPEC @@ -1416,13 +1549,20 @@ restart: unix_peer(sk) = other; if (!other) - sk->sk_state = TCP_CLOSE; + WRITE_ONCE(sk->sk_state, TCP_CLOSE); unix_dgram_peer_wake_disconnect_wakeup(sk, old_peer); unix_state_double_unlock(sk, other); - if (other != old_peer) + if (other != old_peer) { unix_dgram_disconnected(sk, old_peer); + + unix_state_lock(old_peer); + if (!unix_peer(old_peer)) + WRITE_ONCE(old_peer->sk_state, TCP_CLOSE); + unix_state_unlock(old_peer); + } + sock_put(old_peer); } else { unix_peer(sk) = other; @@ -1439,7 +1579,6 @@ out: } static long unix_wait_for_peer(struct sock *other, long timeo) - __releases(&unix_sk(other)->lock) { struct unix_sock *u = unix_sk(other); int sched; @@ -1466,11 +1605,12 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, struct sockaddr_un *sunaddr = (struct sockaddr_un *)uaddr; struct sock *sk = sock->sk, *newsk = NULL, *other = NULL; struct unix_sock *u = unix_sk(sk), *newu, *otheru; + struct unix_peercred peercred = {}; struct net *net = sock_net(sk); struct sk_buff *skb = NULL; + unsigned char state; long timeo; int err; - int st; err = unix_validate_addr(sunaddr, addr_len); if (err) @@ -1480,8 +1620,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, if (err) goto out; - if ((test_bit(SOCK_PASSCRED, &sock->flags) || - test_bit(SOCK_PASSPIDFD, &sock->flags)) && !u->addr) { + if (unix_may_passcred(sk) && !READ_ONCE(u->addr)) { err = unix_autobind(sk); if (err) goto out; @@ -1490,35 +1629,36 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, timeo = sock_sndtimeo(sk, flags & O_NONBLOCK); /* First of all allocate resources. - If we will make it after state is locked, - we will have to recheck all again in any case. + * If we will make it after state is locked, + * we will have to recheck all again in any case. */ /* create new sock for complete connection */ newsk = unix_create1(net, NULL, 0, sock->type); if (IS_ERR(newsk)) { err = PTR_ERR(newsk); - newsk = NULL; goto out; } - err = -ENOMEM; + err = prepare_peercred(&peercred); + if (err) + goto out; /* Allocate skb for sending to listening sock */ skb = sock_wmalloc(newsk, 1, 0, GFP_KERNEL); - if (skb == NULL) - goto out; + if (!skb) { + err = -ENOMEM; + goto out_free_sk; + } restart: /* Find listening sock. */ - other = unix_find_other(net, sunaddr, addr_len, sk->sk_type); + other = unix_find_other(net, sunaddr, addr_len, sk->sk_type, flags); if (IS_ERR(other)) { err = PTR_ERR(other); - other = NULL; - goto out; + goto out_free_skb; } - /* Latch state of peer */ unix_state_lock(other); /* Apparently VFS overslept socket death. Retry. */ @@ -1528,59 +1668,43 @@ restart: goto restart; } - err = -ECONNREFUSED; - if (other->sk_state != TCP_LISTEN) - goto out_unlock; - if (other->sk_shutdown & RCV_SHUTDOWN) + if (other->sk_state != TCP_LISTEN || + other->sk_shutdown & RCV_SHUTDOWN) { + err = -ECONNREFUSED; goto out_unlock; + } - if (unix_recvq_full(other)) { - err = -EAGAIN; - if (!timeo) + if (unix_recvq_full_lockless(other)) { + if (!timeo) { + err = -EAGAIN; goto out_unlock; + } timeo = unix_wait_for_peer(other, timeo); + sock_put(other); err = sock_intr_errno(timeo); if (signal_pending(current)) - goto out; - sock_put(other); + goto out_free_skb; + goto restart; } - /* Latch our state. - - 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 - state. other is TCP_LISTEN, if sk is TCP_LISTEN we - check this before attempt to grab lock. - - Well, and we have to recheck the state after socket locked. + /* self connect and simultaneous connect are eliminated + * by rejecting TCP_LISTEN socket to avoid deadlock. */ - st = sk->sk_state; - - switch (st) { - case TCP_CLOSE: - /* This is ok... continue with connect */ - break; - case TCP_ESTABLISHED: - /* Socket is already connected */ - err = -EISCONN; - goto out_unlock; - default: - err = -EINVAL; + state = READ_ONCE(sk->sk_state); + if (unlikely(state != TCP_CLOSE)) { + err = state == TCP_ESTABLISHED ? -EISCONN : -EINVAL; goto out_unlock; } - unix_state_lock_nested(sk, U_LOCK_SECOND); + unix_state_lock(sk); - if (sk->sk_state != st) { + if (unlikely(sk->sk_state != TCP_CLOSE)) { + err = sk->sk_state == TCP_ESTABLISHED ? -EISCONN : -EINVAL; unix_state_unlock(sk); - unix_state_unlock(other); - sock_put(other); - goto restart; + goto out_unlock; } err = security_unix_stream_connect(sk, other, newsk); @@ -1592,11 +1716,14 @@ restart: /* The way is open! Fastly set all the necessary fields... */ sock_hold(sk); - unix_peer(newsk) = sk; - newsk->sk_state = TCP_ESTABLISHED; - newsk->sk_type = sk->sk_type; - init_peercred(newsk); + unix_peer(newsk) = sk; + newsk->sk_state = TCP_ESTABLISHED; + newsk->sk_type = sk->sk_type; + newsk->sk_scm_recv_flags = other->sk_scm_recv_flags; + init_peercred(newsk, &peercred); + newu = unix_sk(newsk); + newu->listener = other; RCU_INIT_POINTER(newsk->sk_wq, &newu->peer_wq); otheru = unix_sk(other); @@ -1628,7 +1755,7 @@ restart: copy_peercred(sk, other); sock->state = SS_CONNECTED; - sk->sk_state = TCP_ESTABLISHED; + WRITE_ONCE(sk->sk_state, TCP_ESTABLISHED); sock_hold(newsk); smp_mb__after_atomic(); /* sock_hold() does an atomic_inc() */ @@ -1646,29 +1773,40 @@ restart: return 0; out_unlock: - if (other) - unix_state_unlock(other); - + unix_state_unlock(other); + sock_put(other); +out_free_skb: + consume_skb(skb); +out_free_sk: + unix_release_sock(newsk, 0); out: - kfree_skb(skb); - if (newsk) - unix_release_sock(newsk, 0); - if (other) - sock_put(other); + drop_peercred(&peercred); return err; } static int unix_socketpair(struct socket *socka, struct socket *sockb) { + struct unix_peercred ska_peercred = {}, skb_peercred = {}; struct sock *ska = socka->sk, *skb = sockb->sk; + int err; + + err = prepare_peercred(&ska_peercred); + if (err) + return err; + + err = prepare_peercred(&skb_peercred); + if (err) { + drop_peercred(&ska_peercred); + return err; + } /* Join our sockets back to back */ sock_hold(ska); sock_hold(skb); unix_peer(ska) = skb; unix_peer(skb) = ska; - init_peercred(ska); - init_peercred(skb); + init_peercred(ska, &ska_peercred); + init_peercred(skb, &skb_peercred); ska->sk_state = TCP_ESTABLISHED; skb->sk_state = TCP_ESTABLISHED; @@ -1677,43 +1815,31 @@ 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_PASSPIDFD, &old->flags)) - set_bit(SOCK_PASSPIDFD, &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, - bool kern) +static int unix_accept(struct socket *sock, struct socket *newsock, + struct proto_accept_arg *arg) { struct sock *sk = sock->sk; - struct sock *tsk; struct sk_buff *skb; - int err; + struct sock *tsk; - err = -EOPNOTSUPP; + arg->err = -EOPNOTSUPP; if (sock->type != SOCK_STREAM && sock->type != SOCK_SEQPACKET) goto out; - err = -EINVAL; - if (sk->sk_state != TCP_LISTEN) + arg->err = -EINVAL; + if (READ_ONCE(sk->sk_state) != TCP_LISTEN) goto out; /* If socket state is TCP_LISTEN it cannot change (for now...), * so that no locks are necessary. */ - skb = skb_recv_datagram(sk, (flags & O_NONBLOCK) ? MSG_DONTWAIT : 0, - &err); + skb = skb_recv_datagram(sk, (arg->flags & O_NONBLOCK) ? MSG_DONTWAIT : 0, + &arg->err); if (!skb) { /* This means receive shutdown. */ - if (err == 0) - err = -EINVAL; + if (arg->err == 0) + arg->err = -EINVAL; goto out; } @@ -1723,14 +1849,14 @@ static int unix_accept(struct socket *sock, struct socket *newsock, int flags, /* attach accepted sock to socket */ unix_state_lock(tsk); + unix_update_edges(unix_sk(tsk)); newsock->state = SS_CONNECTED; - unix_sock_inherit_flags(sock, newsock); sock_graft(tsk, newsock); unix_state_unlock(tsk); return 0; out: - return err; + return arg->err; } @@ -1789,81 +1915,29 @@ static inline bool too_many_unix_fds(struct task_struct *p) static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) { - int i; - if (too_many_unix_fds(current)) return -ETOOMANYREFS; - /* Need to duplicate file references for the sake of garbage - * collection. Otherwise a socket in the fps might become a - * candidate for GC while the skb is not yet queued. - */ - UNIXCB(skb).fp = scm_fp_dup(scm->fp); - if (!UNIXCB(skb).fp) - return -ENOMEM; + UNIXCB(skb).fp = scm->fp; + scm->fp = NULL; - for (i = scm->fp->count - 1; i >= 0; i--) - unix_inflight(scm->fp->user, scm->fp->fp[i]); + if (unix_prepare_fpl(UNIXCB(skb).fp)) + return -ENOMEM; return 0; } static void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb) { - int i; - scm->fp = UNIXCB(skb).fp; UNIXCB(skb).fp = NULL; - for (i = scm->fp->count - 1; i >= 0; i--) - unix_notinflight(scm->fp->user, scm->fp->fp[i]); + unix_destroy_fpl(scm->fp); } static void unix_peek_fds(struct scm_cookie *scm, struct sk_buff *skb) { scm->fp = scm_fp_dup(UNIXCB(skb).fp); - - /* - * Garbage collection of unix sockets starts by selecting a set of - * candidate sockets which have reference only from being in flight - * (total_refs == inflight_refs). This condition is checked once during - * the candidate collection phase, and candidates are marked as such, so - * that non-candidates can later be ignored. While inflight_refs is - * protected by unix_gc_lock, total_refs (file count) is not, hence this - * is an instantaneous decision. - * - * Once a candidate, however, the socket must not be reinstalled into a - * file descriptor while the garbage collection is in progress. - * - * If the above conditions are met, then the directed graph of - * candidates (*) does not change while unix_gc_lock is held. - * - * Any operations that changes the file count through file descriptors - * (dup, close, sendmsg) does not change the graph since candidates are - * not installed in fds. - * - * Dequeing a candidate via recvmsg would install it into an fd, but - * that takes unix_gc_lock to decrement the inflight count, so it's - * serialized with garbage collection. - * - * MSG_PEEK is special in that it does not change the inflight count, - * yet does install the socket into an fd. The following lock/unlock - * pair is to ensure serialization with garbage collection. It must be - * done between incrementing the file count and installing the file into - * an fd. - * - * If garbage collection starts after the barrier provided by the - * lock/unlock, then it will see the elevated refcount and not mark this - * as a candidate. If a garbage collection is already in progress - * before the file count was incremented, then the lock/unlock pair will - * ensure that garbage collection is finished before progressing to - * installing the fd. - * - * (*) A -> B where B is on the queue of A or B is on the queue of C - * which is on the queue of listening socket A. - */ - spin_lock(&unix_gc_lock); - spin_unlock(&unix_gc_lock); } static void unix_destruct_scm(struct sk_buff *skb) @@ -1885,7 +1959,7 @@ static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool sen { int err = 0; - UNIXCB(skb).pid = get_pid(scm->pid); + UNIXCB(skb).pid = get_pid(scm->pid); UNIXCB(skb).uid = scm->creds.uid; UNIXCB(skb).gid = scm->creds.gid; UNIXCB(skb).fp = NULL; @@ -1897,28 +1971,20 @@ static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool sen return err; } -static bool unix_passcred_enabled(const struct socket *sock, - const struct sock *other) -{ - return test_bit(SOCK_PASSCRED, &sock->flags) || - test_bit(SOCK_PASSPIDFD, &sock->flags) || - !other->sk_socket || - test_bit(SOCK_PASSCRED, &other->sk_socket->flags) || - test_bit(SOCK_PASSPIDFD, &other->sk_socket->flags); -} - /* * 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) +static void unix_maybe_add_creds(struct sk_buff *skb, const struct sock *sk, + const struct sock *other) { if (UNIXCB(skb).pid) return; - if (unix_passcred_enabled(sock, other)) { - UNIXCB(skb).pid = get_pid(task_tgid(current)); + + if (unix_may_passcred(sk) || unix_may_passcred(other) || + !other->sk_socket) { + UNIXCB(skb).pid = get_pid(task_tgid(current)); current_uid_gid(&UNIXCB(skb).uid, &UNIXCB(skb).gid); } } @@ -1937,8 +2003,10 @@ static void scm_stat_add(struct sock *sk, struct sk_buff *skb) struct scm_fp_list *fp = UNIXCB(skb).fp; struct unix_sock *u = unix_sk(sk); - if (unlikely(fp && fp->count)) + if (unlikely(fp && fp->count)) { atomic_add(fp->count, &u->scm_stat.nr_fds); + unix_add_edges(fp, u); + } } static void scm_stat_del(struct sock *sk, struct sk_buff *skb) @@ -1946,8 +2014,10 @@ static void scm_stat_del(struct sock *sk, struct sk_buff *skb) struct scm_fp_list *fp = UNIXCB(skb).fp; struct unix_sock *u = unix_sk(sk); - if (unlikely(fp && fp->count)) + if (unlikely(fp && fp->count)) { atomic_sub(fp->count, &u->scm_stat.nr_fds); + unix_del_edges(fp); + } } /* @@ -1957,7 +2027,6 @@ static void scm_stat_del(struct sock *sk, struct sk_buff *skb) static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { - DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr, msg->msg_name); struct sock *sk = sock->sk, *other = NULL; struct unix_sock *u = unix_sk(sk); struct scm_cookie scm; @@ -1973,12 +2042,13 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg, wait_for_unix_gc(scm.fp); - err = -EOPNOTSUPP; - if (msg->msg_flags&MSG_OOB) + if (msg->msg_flags & MSG_OOB) { + err = -EOPNOTSUPP; goto out; + } if (msg->msg_namelen) { - err = unix_validate_addr(sunaddr, msg->msg_namelen); + err = unix_validate_addr(msg->msg_name, msg->msg_namelen); if (err) goto out; @@ -1988,24 +2058,18 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg, NULL); if (err) goto out; - } else { - sunaddr = NULL; - err = -ENOTCONN; - other = unix_peer_get(sk); - if (!other) - goto out; } - if ((test_bit(SOCK_PASSCRED, &sock->flags) || - test_bit(SOCK_PASSPIDFD, &sock->flags)) && !u->addr) { + if (unix_may_passcred(sk) && !READ_ONCE(u->addr)) { err = unix_autobind(sk); if (err) goto out; } - err = -EMSGSIZE; - if (len > sk->sk_sndbuf - 32) + if (len > READ_ONCE(sk->sk_sndbuf) - 32) { + err = -EMSGSIZE; goto out; + } if (len > SKB_MAX_ALLOC) { data_len = min_t(size_t, @@ -2019,7 +2083,7 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg, skb = sock_alloc_send_pskb(sk, len - data_len, data_len, msg->msg_flags & MSG_DONTWAIT, &err, PAGE_ALLOC_COSTLY_ORDER); - if (skb == NULL) + if (!skb) goto out; err = unix_scm_to_skb(&scm, skb, true); @@ -2035,17 +2099,18 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg, timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); -restart: - if (!other) { - err = -ECONNRESET; - if (sunaddr == NULL) - goto out_free; - - other = unix_find_other(sock_net(sk), sunaddr, msg->msg_namelen, - sk->sk_type); + if (msg->msg_namelen) { +lookup: + other = unix_find_other(sock_net(sk), msg->msg_name, + msg->msg_namelen, sk->sk_type, 0); if (IS_ERR(other)) { err = PTR_ERR(other); - other = NULL; + goto out_free; + } + } else { + other = unix_peer_get(sk); + if (!other) { + err = -ENOTCONN; goto out_free; } } @@ -2053,58 +2118,69 @@ restart: if (sk_filter(other, skb) < 0) { /* Toss the packet but do not return any error to the sender */ err = len; - goto out_free; + goto out_sock_put; } +restart: sk_locked = 0; unix_state_lock(other); restart_locked: - err = -EPERM; - if (!unix_may_send(sk, other)) + + if (!unix_may_send(sk, other)) { + err = -EPERM; goto out_unlock; + } if (unlikely(sock_flag(other, SOCK_DEAD))) { - /* - * Check with 1003.1g - what should - * datagram error - */ - unix_state_unlock(other); - sock_put(other); + /* Check with 1003.1g - what should datagram error */ - if (!sk_locked) - unix_state_lock(sk); + unix_state_unlock(other); - err = 0; if (sk->sk_type == SOCK_SEQPACKET) { /* We are here only when racing with unix_release_sock() * is clearing @other. Never change state to TCP_CLOSE * unlike SOCK_DGRAM wants. */ - unix_state_unlock(sk); err = -EPIPE; - } else if (unix_peer(sk) == other) { + goto out_sock_put; + } + + if (!sk_locked) + unix_state_lock(sk); + + if (unix_peer(sk) == other) { unix_peer(sk) = NULL; unix_dgram_peer_wake_disconnect_wakeup(sk, other); - sk->sk_state = TCP_CLOSE; + WRITE_ONCE(sk->sk_state, TCP_CLOSE); unix_state_unlock(sk); unix_dgram_disconnected(sk, other); sock_put(other); err = -ECONNREFUSED; - } else { - unix_state_unlock(sk); + goto out_sock_put; } - other = NULL; - if (err) - goto out_free; - goto restart; + unix_state_unlock(sk); + + if (!msg->msg_namelen) { + err = -ECONNRESET; + goto out_sock_put; + } + + sock_put(other); + goto lookup; } - err = -EPIPE; - if (other->sk_shutdown & RCV_SHUTDOWN) + if (other->sk_shutdown & RCV_SHUTDOWN) { + err = -EPIPE; + goto out_unlock; + } + + if (UNIXCB(skb).fp && !other->sk_scm_rights) { + err = -EPERM; goto out_unlock; + } if (sk->sk_type != SOCK_SEQPACKET) { err = security_unix_may_send(sk->sk_socket, other->sk_socket); @@ -2124,7 +2200,7 @@ restart_locked: err = sock_intr_errno(timeo); if (signal_pending(current)) - goto out_free; + goto out_sock_put; goto restart; } @@ -2152,7 +2228,8 @@ restart_locked: if (sock_flag(other, SOCK_RCVTSTAMP)) __net_timestamp(skb); - maybe_add_creds(skb, sock, other); + + unix_maybe_add_creds(skb, sk, other); scm_stat_add(other, skb); skb_queue_tail(&other->sk_receive_queue, skb); unix_state_unlock(other); @@ -2165,11 +2242,11 @@ out_unlock: if (sk_locked) unix_state_unlock(sk); unix_state_unlock(other); +out_sock_put: + sock_put(other); out_free: - kfree_skb(skb); + consume_skb(skb); out: - if (other) - sock_put(other); scm_destroy(&scm); return err; } @@ -2180,54 +2257,58 @@ out: #define UNIX_SKB_FRAGS_SZ (PAGE_SIZE << get_order(32768)) #if IS_ENABLED(CONFIG_AF_UNIX_OOB) -static int queue_oob(struct socket *sock, struct msghdr *msg, struct sock *other, +static int queue_oob(struct sock *sk, struct msghdr *msg, struct sock *other, struct scm_cookie *scm, bool fds_sent) { struct unix_sock *ousk = unix_sk(other); struct sk_buff *skb; - int err = 0; + int err; - skb = sock_alloc_send_skb(sock->sk, 1, msg->msg_flags & MSG_DONTWAIT, &err); + skb = sock_alloc_send_skb(sk, 1, msg->msg_flags & MSG_DONTWAIT, &err); if (!skb) return err; err = unix_scm_to_skb(scm, skb, !fds_sent); - if (err < 0) { - kfree_skb(skb); - return err; - } + if (err < 0) + goto out; + skb_put(skb, 1); err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, 1); - if (err) { - kfree_skb(skb); - return err; - } + if (err) + goto out; unix_state_lock(other); if (sock_flag(other, SOCK_DEAD) || (other->sk_shutdown & RCV_SHUTDOWN)) { - unix_state_unlock(other); - kfree_skb(skb); - return -EPIPE; + err = -EPIPE; + goto out_unlock; } - maybe_add_creds(skb, sock, other); - skb_get(skb); + if (UNIXCB(skb).fp && !other->sk_scm_rights) { + err = -EPERM; + goto out_unlock; + } - if (ousk->oob_skb) - consume_skb(ousk->oob_skb); + unix_maybe_add_creds(skb, sk, other); + scm_stat_add(other, skb); + spin_lock(&other->sk_receive_queue.lock); WRITE_ONCE(ousk->oob_skb, skb); + __skb_queue_tail(&other->sk_receive_queue, skb); + spin_unlock(&other->sk_receive_queue.lock); - scm_stat_add(other, skb); - skb_queue_tail(&other->sk_receive_queue, skb); sk_send_sigurg(other); unix_state_unlock(other); other->sk_data_ready(other); + return 0; +out_unlock: + unix_state_unlock(other); +out: + consume_skb(skb); return err; } #endif @@ -2236,13 +2317,11 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; + struct sk_buff *skb = NULL; struct sock *other = NULL; - int err, size; - struct sk_buff *skb; - int sent = 0; struct scm_cookie scm; bool fds_sent = false; - int data_len; + int err, sent = 0; err = scm_send(sock, msg, &scm, false); if (err < 0) @@ -2250,8 +2329,8 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, wait_for_unix_gc(scm.fp); - err = -EOPNOTSUPP; if (msg->msg_flags & MSG_OOB) { + err = -EOPNOTSUPP; #if IS_ENABLED(CONFIG_AF_UNIX_OOB) if (len) len--; @@ -2261,20 +2340,22 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, } if (msg->msg_namelen) { - err = sk->sk_state == TCP_ESTABLISHED ? -EISCONN : -EOPNOTSUPP; + err = READ_ONCE(sk->sk_state) == TCP_ESTABLISHED ? -EISCONN : -EOPNOTSUPP; goto out_err; } else { - err = -ENOTCONN; other = unix_peer(sk); - if (!other) + if (!other) { + err = -ENOTCONN; goto out_err; + } } - if (sk->sk_shutdown & SEND_SHUTDOWN) - goto pipe_err; + if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) + goto out_pipe; while (sent < len) { - size = len - sent; + int size = len - sent; + int data_len; if (unlikely(msg->msg_flags & MSG_SPLICE_PAGES)) { skb = sock_alloc_send_pskb(sk, 0, 0, @@ -2282,7 +2363,7 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, &err, 0); } else { /* Keep two messages in the pipe so it schedules better */ - size = min_t(int, size, (sk->sk_sndbuf >> 1) - 64); + size = min_t(int, size, (READ_ONCE(sk->sk_sndbuf) >> 1) - 64); /* allow fallback to order-0 allocations */ size = min_t(int, size, SKB_MAX_HEAD(0) + UNIX_SKB_FRAGS_SZ); @@ -2300,19 +2381,18 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, /* Only send the fds in the first buffer */ err = unix_scm_to_skb(&scm, skb, !fds_sent); - if (err < 0) { - kfree_skb(skb); - goto out_err; - } + if (err < 0) + goto out_free; + fds_sent = true; if (unlikely(msg->msg_flags & MSG_SPLICE_PAGES)) { + skb->ip_summed = CHECKSUM_UNNECESSARY; err = skb_splice_from_iter(skb, &msg->msg_iter, size, sk->sk_allocation); - if (err < 0) { - kfree_skb(skb); - goto out_err; - } + if (err < 0) + goto out_free; + size = err; refcount_add(size, &sk->sk_wmem_alloc); } else { @@ -2320,19 +2400,23 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, skb->data_len = data_len; skb->len = size; err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, size); - if (err) { - kfree_skb(skb); - goto out_err; - } + if (err) + goto out_free; } unix_state_lock(other); if (sock_flag(other, SOCK_DEAD) || (other->sk_shutdown & RCV_SHUTDOWN)) - goto pipe_err_free; + goto out_pipe_unlock; - maybe_add_creds(skb, sock, other); + if (UNIXCB(skb).fp && !other->sk_scm_rights) { + unix_state_unlock(other); + err = -EPERM; + goto out_free; + } + + unix_maybe_add_creds(skb, sk, other); scm_stat_add(other, skb); skb_queue_tail(&other->sk_receive_queue, skb); unix_state_unlock(other); @@ -2342,7 +2426,7 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, #if IS_ENABLED(CONFIG_AF_UNIX_OOB) if (msg->msg_flags & MSG_OOB) { - err = queue_oob(sock, msg, other, &scm, fds_sent); + err = queue_oob(sk, msg, other, &scm, fds_sent); if (err) goto out_err; sent++; @@ -2353,13 +2437,14 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, return sent; -pipe_err_free: +out_pipe_unlock: unix_state_unlock(other); - kfree_skb(skb); -pipe_err: - if (sent == 0 && !(msg->msg_flags&MSG_NOSIGNAL)) +out_pipe: + if (!sent && !(msg->msg_flags & MSG_NOSIGNAL)) send_sig(SIGPIPE, current, 0); err = -EPIPE; +out_free: + consume_skb(skb); out_err: scm_destroy(&scm); return sent ? : err; @@ -2375,7 +2460,7 @@ static int unix_seqpacket_sendmsg(struct socket *sock, struct msghdr *msg, if (err) return err; - if (sk->sk_state != TCP_ESTABLISHED) + if (READ_ONCE(sk->sk_state) != TCP_ESTABLISHED) return -ENOTCONN; if (msg->msg_namelen) @@ -2389,7 +2474,7 @@ static int unix_seqpacket_recvmsg(struct socket *sock, struct msghdr *msg, { struct sock *sk = sock->sk; - if (sk->sk_state != TCP_ESTABLISHED) + if (READ_ONCE(sk->sk_state) != TCP_ESTABLISHED) return -ENOTCONN; return unix_dgram_recvmsg(sock, msg, size, flags); @@ -2587,11 +2672,6 @@ 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; -} - struct unix_stream_read_state { int (*recv_actor)(struct sk_buff *, int, int, struct unix_stream_read_state *); @@ -2606,16 +2686,18 @@ struct unix_stream_read_state { #if IS_ENABLED(CONFIG_AF_UNIX_OOB) static int unix_stream_recv_urg(struct unix_stream_read_state *state) { + struct sk_buff *oob_skb, *read_skb = NULL; struct socket *sock = state->socket; struct sock *sk = sock->sk; struct unix_sock *u = unix_sk(sk); int chunk = 1; - struct sk_buff *oob_skb; mutex_lock(&u->iolock); unix_state_lock(sk); + spin_lock(&sk->sk_receive_queue.lock); if (sock_flag(sk, SOCK_URGINLINE) || !u->oob_skb) { + spin_unlock(&sk->sk_receive_queue.lock); unix_state_unlock(sk); mutex_unlock(&u->iolock); return -EINVAL; @@ -2623,10 +2705,17 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state) oob_skb = u->oob_skb; - if (!(state->flags & MSG_PEEK)) + if (!(state->flags & MSG_PEEK)) { WRITE_ONCE(u->oob_skb, NULL); - else - skb_get(oob_skb); + + if (oob_skb->prev != (struct sk_buff *)&sk->sk_receive_queue && + !unix_skb_len(oob_skb->prev)) { + read_skb = oob_skb->prev; + __skb_unlink(read_skb, &sk->sk_receive_queue); + } + } + + spin_unlock(&sk->sk_receive_queue.lock); unix_state_unlock(sk); chunk = state->recv_actor(oob_skb, 0, chunk, state); @@ -2634,10 +2723,10 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state) if (!(state->flags & MSG_PEEK)) UNIXCB(oob_skb).consumed += 1; - consume_skb(oob_skb); - mutex_unlock(&u->iolock); + consume_skb(read_skb); + if (chunk < 0) return -EFAULT; @@ -2648,42 +2737,100 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state) static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk, int flags, int copied) { + struct sk_buff *read_skb = NULL, *unread_skb = NULL; struct unix_sock *u = unix_sk(sk); - if (!unix_skb_len(skb) && !(flags & MSG_PEEK)) { - skb_unlink(skb, &sk->sk_receive_queue); - consume_skb(skb); + if (likely(unix_skb_len(skb) && skb != READ_ONCE(u->oob_skb))) + return skb; + + spin_lock(&sk->sk_receive_queue.lock); + + if (!unix_skb_len(skb)) { + if (copied && (!u->oob_skb || skb == u->oob_skb)) { + skb = NULL; + } else if (flags & MSG_PEEK) { + skb = skb_peek_next(skb, &sk->sk_receive_queue); + } else { + read_skb = skb; + skb = skb_peek_next(skb, &sk->sk_receive_queue); + __skb_unlink(read_skb, &sk->sk_receive_queue); + } + + if (!skb) + goto unlock; + } + + if (skb != u->oob_skb) + goto unlock; + + if (copied) { skb = NULL; - } else { - if (skb == u->oob_skb) { - if (copied) { - skb = NULL; - } else if (sock_flag(sk, SOCK_URGINLINE)) { - if (!(flags & MSG_PEEK)) { - WRITE_ONCE(u->oob_skb, NULL); - consume_skb(skb); - } - } else if (flags & MSG_PEEK) { - skb = NULL; - } else { - skb_unlink(skb, &sk->sk_receive_queue); - WRITE_ONCE(u->oob_skb, NULL); - if (!WARN_ON_ONCE(skb_unref(skb))) - kfree_skb(skb); - skb = skb_peek(&sk->sk_receive_queue); - } + } else if (!(flags & MSG_PEEK)) { + WRITE_ONCE(u->oob_skb, NULL); + + if (!sock_flag(sk, SOCK_URGINLINE)) { + __skb_unlink(skb, &sk->sk_receive_queue); + unread_skb = skb; + skb = skb_peek(&sk->sk_receive_queue); } + } else if (!sock_flag(sk, SOCK_URGINLINE)) { + skb = skb_peek_next(skb, &sk->sk_receive_queue); } + +unlock: + spin_unlock(&sk->sk_receive_queue.lock); + + consume_skb(read_skb); + kfree_skb_reason(unread_skb, SKB_DROP_REASON_UNIX_SKIP_OOB); + return skb; } #endif static int unix_stream_read_skb(struct sock *sk, skb_read_actor_t recv_actor) { - if (unlikely(sk->sk_state != TCP_ESTABLISHED)) + struct unix_sock *u = unix_sk(sk); + struct sk_buff *skb; + int err; + + if (unlikely(READ_ONCE(sk->sk_state) != TCP_ESTABLISHED)) return -ENOTCONN; - return unix_read_skb(sk, recv_actor); + mutex_lock(&u->iolock); + skb = skb_recv_datagram(sk, MSG_DONTWAIT, &err); + mutex_unlock(&u->iolock); + if (!skb) + return err; + +#if IS_ENABLED(CONFIG_AF_UNIX_OOB) + if (unlikely(skb == READ_ONCE(u->oob_skb))) { + bool drop = false; + + unix_state_lock(sk); + + if (sock_flag(sk, SOCK_DEAD)) { + unix_state_unlock(sk); + kfree_skb_reason(skb, SKB_DROP_REASON_SOCKET_CLOSE); + return -ECONNRESET; + } + + spin_lock(&sk->sk_receive_queue.lock); + if (likely(skb == u->oob_skb)) { + WRITE_ONCE(u->oob_skb, NULL); + drop = true; + } + spin_unlock(&sk->sk_receive_queue.lock); + + unix_state_unlock(sk); + + if (drop) { + kfree_skb_reason(skb, SKB_DROP_REASON_UNIX_SKIP_OOB); + return -EAGAIN; + } + } +#endif + + return recv_actor(sk, skb); } static int unix_stream_read_generic(struct unix_stream_read_state *state, @@ -2704,7 +2851,7 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state, size_t size = state->size; unsigned int last_len; - if (unlikely(sk->sk_state != TCP_ESTABLISHED)) { + if (unlikely(READ_ONCE(sk->sk_state) != TCP_ESTABLISHED)) { err = -EINVAL; goto out; } @@ -2730,9 +2877,8 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state, skip = max(sk_peek_offset(sk, flags), 0); do { - int chunk; - bool drop_skb; struct sk_buff *skb, *last; + int chunk; redo: unix_state_lock(sk); @@ -2806,8 +2952,7 @@ unlock: /* Never glue messages from different writers */ if (!unix_skb_scm_eq(skb, &scm)) break; - } else if (test_bit(SOCK_PASSCRED, &sock->flags) || - test_bit(SOCK_PASSPIDFD, &sock->flags)) { + } else if (unix_may_passcred(sk)) { /* Copy credentials */ scm_set_cred(&scm, UNIXCB(skb).pid, UNIXCB(skb).uid, UNIXCB(skb).gid); unix_set_secdata(&scm, skb); @@ -2828,11 +2973,7 @@ unlock: } chunk = min_t(unsigned int, unix_skb_len(skb) - skip, size); - skb_get(skb); chunk = state->recv_actor(skb, skip, chunk, state); - drop_skb = !unix_skb_len(skb); - /* skb is only safe to use if !drop_skb */ - consume_skb(skb); if (chunk < 0) { if (copied == 0) copied = -EFAULT; @@ -2841,18 +2982,6 @@ unlock: copied += chunk; size -= chunk; - if (drop_skb) { - /* the skb was touched by a concurrent reader; - * we should not expect anything from this skb - * anymore and assume it invalid - we can be - * sure it was dropped from the socket queue - * - * let's report a short read - */ - err = 0; - break; - } - /* Mark read part of skb as used */ if (!(flags & MSG_PEEK)) { UNIXCB(skb).consumed += chunk; @@ -3035,7 +3164,7 @@ long unix_inq_len(struct sock *sk) struct sk_buff *skb; long amount = 0; - if (sk->sk_state == TCP_LISTEN) + if (READ_ONCE(sk->sk_state) == TCP_LISTEN) return -EINVAL; spin_lock(&sk->sk_receive_queue.lock); @@ -3120,12 +3249,27 @@ static int unix_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) #if IS_ENABLED(CONFIG_AF_UNIX_OOB) case SIOCATMARK: { + struct unix_sock *u = unix_sk(sk); struct sk_buff *skb; int answ = 0; + mutex_lock(&u->iolock); + skb = skb_peek(&sk->sk_receive_queue); - if (skb && skb == READ_ONCE(unix_sk(sk)->oob_skb)) - answ = 1; + if (skb) { + struct sk_buff *oob_skb = READ_ONCE(u->oob_skb); + struct sk_buff *next_skb; + + next_skb = skb_peek_next(skb, &sk->sk_receive_queue); + + if (skb == oob_skb || + (!unix_skb_len(skb) && + (!oob_skb || next_skb == oob_skb))) + answ = 1; + } + + mutex_unlock(&u->iolock); + err = put_user(answ, (int __user *)arg); } break; @@ -3147,12 +3291,14 @@ static int unix_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned lon static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wait) { struct sock *sk = sock->sk; + unsigned char state; __poll_t mask; u8 shutdown; sock_poll_wait(file, sock, wait); mask = 0; shutdown = READ_ONCE(sk->sk_shutdown); + state = READ_ONCE(sk->sk_state); /* exceptional events? */ if (READ_ONCE(sk->sk_err)) @@ -3174,14 +3320,14 @@ static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wa /* Connection-based need to check for termination and startup */ if ((sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) && - sk->sk_state == TCP_CLOSE) + state == TCP_CLOSE) mask |= EPOLLHUP; /* * we set writable also when the other side has shut down the * connection. This prevents stuck sockets. */ - if (unix_writable(sk)) + if (unix_writable(sk, state)) mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND; return mask; @@ -3192,12 +3338,14 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock, { struct sock *sk = sock->sk, *other; unsigned int writable; + unsigned char state; __poll_t mask; u8 shutdown; sock_poll_wait(file, sock, wait); mask = 0; shutdown = READ_ONCE(sk->sk_shutdown); + state = READ_ONCE(sk->sk_state); /* exceptional events? */ if (READ_ONCE(sk->sk_err) || @@ -3217,19 +3365,14 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock, mask |= EPOLLIN | EPOLLRDNORM; /* Connection-based need to check for termination and startup */ - if (sk->sk_type == SOCK_SEQPACKET) { - if (sk->sk_state == TCP_CLOSE) - mask |= EPOLLHUP; - /* connection hasn't started yet? */ - if (sk->sk_state == TCP_SYN_SENT) - return mask; - } + if (sk->sk_type == SOCK_SEQPACKET && state == TCP_CLOSE) + mask |= EPOLLHUP; /* No write status requested, avoid expensive OUT tests. */ if (!(poll_requested_events(wait) & (EPOLLWRBAND|EPOLLWRNORM|EPOLLOUT))) return mask; - writable = unix_writable(sk); + writable = unix_writable(sk, state); if (writable) { unix_state_lock(sk); @@ -3623,6 +3766,7 @@ static int __net_init unix_net_init(struct net *net) for (i = 0; i < UNIX_HASH_SIZE; i++) { spin_lock_init(&net->unx.table.locks[i]); + lock_set_cmp_fn(&net->unx.table.locks[i], unix_table_lock_cmp_fn, NULL); INIT_HLIST_HEAD(&net->unx.table.buckets[i]); } |