diff options
Diffstat (limited to 'net/unix/af_unix.c')
| -rw-r--r-- | net/unix/af_unix.c | 2208 |
1 files changed, 1320 insertions, 888 deletions
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index c19569819866..55cdebfa0da0 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -77,57 +77,124 @@ #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/fs_struct.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/mount.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/string.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/net_namespace.h> #include <net/scm.h> -#include <linux/init.h> -#include <linux/poll.h> -#include <linux/rtnetlink.h> -#include <linux/mount.h> -#include <net/checksum.h> -#include <linux/security.h> -#include <linux/freezer.h> -#include <linux/file.h> -#include <linux/btf_ids.h> +#include <net/tcp_states.h> +#include <uapi/linux/sockios.h> +#include <uapi/linux/termios.h> -#include "scm.h" +#include "af_unix.h" -spinlock_t unix_table_locks[2 * UNIX_HASH_SIZE]; -EXPORT_SYMBOL_GPL(unix_table_locks); -struct hlist_head unix_socket_table[2 * UNIX_HASH_SIZE]; -EXPORT_SYMBOL_GPL(unix_socket_table); static atomic_long_t unix_nr_socks; +static struct hlist_head bsd_socket_buckets[UNIX_HASH_SIZE / 2]; +static spinlock_t bsd_socket_locks[UNIX_HASH_SIZE / 2]; /* SMP locking strategy: - * hash table is protected with spinlock unix_table_locks - * each socket state is protected by separate spin lock. + * 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) { @@ -137,12 +204,12 @@ static unsigned int unix_unbound_hash(struct sock *sk) hash ^= hash >> 8; hash ^= sk->sk_type; - return UNIX_HASH_SIZE + (hash & (UNIX_HASH_SIZE - 1)); + return hash & UNIX_HASH_MOD; } static unsigned int unix_bsd_hash(struct inode *i) { - return i->i_ino & (UNIX_HASH_SIZE - 1); + return i->i_ino & UNIX_HASH_MOD; } static unsigned int unix_abstract_hash(struct sockaddr_un *sunaddr, @@ -155,26 +222,34 @@ static unsigned int unix_abstract_hash(struct sockaddr_un *sunaddr, hash ^= hash >> 8; hash ^= type; - return hash & (UNIX_HASH_SIZE - 1); + return UNIX_HASH_MOD + 1 + (hash & UNIX_HASH_MOD); } -static void unix_table_double_lock(unsigned int hash1, unsigned int hash2) +static void unix_table_double_lock(struct net *net, + unsigned int hash1, unsigned int hash2) { - /* hash1 and hash2 is never the same because - * one is between 0 and UNIX_HASH_SIZE - 1, and - * another is between UNIX_HASH_SIZE and UNIX_HASH_SIZE * 2. - */ + if (hash1 == hash2) { + spin_lock(&net->unx.table.locks[hash1]); + return; + } + if (hash1 > hash2) swap(hash1, hash2); - spin_lock(&unix_table_locks[hash1]); - spin_lock_nested(&unix_table_locks[hash2], SINGLE_DEPTH_NESTING); + spin_lock(&net->unx.table.locks[hash1]); + spin_lock(&net->unx.table.locks[hash2]); } -static void unix_table_double_unlock(unsigned int hash1, unsigned int hash2) +static void unix_table_double_unlock(struct net *net, + unsigned int hash1, unsigned int hash2) { - spin_unlock(&unix_table_locks[hash1]); - spin_unlock(&unix_table_locks[hash2]); + if (hash1 == hash2) { + spin_unlock(&net->unx.table.locks[hash1]); + return; + } + + spin_unlock(&net->unx.table.locks[hash1]); + spin_unlock(&net->unx.table.locks[hash2]); } #ifdef CONFIG_SECURITY_NETWORK @@ -205,27 +280,14 @@ static inline bool unix_secdata_eq(struct scm_cookie *scm, struct sk_buff *skb) } #endif /* CONFIG_SECURITY_NETWORK */ -#define unix_peer(sk) (unix_sk(sk)->peer) - -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) @@ -282,17 +344,29 @@ static int unix_validate_addr(struct sockaddr_un *sunaddr, int addr_len) return 0; } -static void unix_mkname_bsd(struct sockaddr_un *sunaddr, int addr_len) +static int unix_mkname_bsd(struct sockaddr_un *sunaddr, int addr_len) { + struct sockaddr_storage *addr = (struct sockaddr_storage *)sunaddr; + short offset = offsetof(struct sockaddr_storage, __data); + + BUILD_BUG_ON(offset != offsetof(struct sockaddr_un, sun_path)); + /* This may look like an off by one error but it is a bit more * subtle. 108 is the longest valid AF_UNIX path for a binding. * sun_path[108] doesn't as such exist. However in kernel space * we are guaranteed that it is a valid memory location in our * kernel address buffer because syscall functions always pass * a pointer of struct sockaddr_storage which has a bigger buffer - * than 108. + * than 108. Also, we must terminate sun_path for strlen() in + * getname_kernel(). + */ + addr->__data[addr_len - offset] = 0; + + /* Don't pass sunaddr->sun_path to strlen(). Otherwise, 108 will + * cause panic if CONFIG_FORTIFY_SOURCE=y. Let __fortify_strlen() + * know the actual buffer. */ - ((char *)sunaddr)[addr_len] = 0; + return strlen(addr->__data) + offset + 1; } static void __unix_remove_socket(struct sock *sk) @@ -300,34 +374,52 @@ static void __unix_remove_socket(struct sock *sk) sk_del_node_init(sk); } -static void __unix_insert_socket(struct sock *sk) +static void __unix_insert_socket(struct net *net, struct sock *sk) { - WARN_ON(!sk_unhashed(sk)); - sk_add_node(sk, &unix_socket_table[sk->sk_hash]); + DEBUG_NET_WARN_ON_ONCE(!sk_unhashed(sk)); + sk_add_node(sk, &net->unx.table.buckets[sk->sk_hash]); } -static void __unix_set_addr_hash(struct sock *sk, struct unix_address *addr, - unsigned int hash) +static void __unix_set_addr_hash(struct net *net, struct sock *sk, + struct unix_address *addr, unsigned int hash) { __unix_remove_socket(sk); smp_store_release(&unix_sk(sk)->addr, addr); sk->sk_hash = hash; - __unix_insert_socket(sk); + __unix_insert_socket(net, sk); } -static void unix_remove_socket(struct sock *sk) +static void unix_remove_socket(struct net *net, struct sock *sk) { - spin_lock(&unix_table_locks[sk->sk_hash]); + spin_lock(&net->unx.table.locks[sk->sk_hash]); __unix_remove_socket(sk); - spin_unlock(&unix_table_locks[sk->sk_hash]); + spin_unlock(&net->unx.table.locks[sk->sk_hash]); } -static void unix_insert_unbound_socket(struct sock *sk) +static void unix_insert_unbound_socket(struct net *net, struct sock *sk) { - spin_lock(&unix_table_locks[sk->sk_hash]); - __unix_insert_socket(sk); - spin_unlock(&unix_table_locks[sk->sk_hash]); + spin_lock(&net->unx.table.locks[sk->sk_hash]); + __unix_insert_socket(net, sk); + spin_unlock(&net->unx.table.locks[sk->sk_hash]); +} + +static void unix_insert_bsd_socket(struct sock *sk) +{ + spin_lock(&bsd_socket_locks[sk->sk_hash]); + sk_add_bind_node(sk, &bsd_socket_buckets[sk->sk_hash]); + spin_unlock(&bsd_socket_locks[sk->sk_hash]); +} + +static void unix_remove_bsd_socket(struct sock *sk) +{ + if (!hlist_unhashed(&sk->sk_bind_node)) { + spin_lock(&bsd_socket_locks[sk->sk_hash]); + __sk_del_bind_node(sk); + spin_unlock(&bsd_socket_locks[sk->sk_hash]); + + sk_node_init(&sk->sk_bind_node); + } } static struct sock *__unix_find_socket_byname(struct net *net, @@ -336,12 +428,9 @@ static struct sock *__unix_find_socket_byname(struct net *net, { struct sock *s; - sk_for_each(s, &unix_socket_table[hash]) { + sk_for_each(s, &net->unx.table.buckets[hash]) { struct unix_sock *u = unix_sk(s); - if (!net_eq(sock_net(s), net)) - continue; - if (u->addr->len == len && !memcmp(u->addr->name, sunname, len)) return s; @@ -355,11 +444,11 @@ static inline struct sock *unix_find_socket_byname(struct net *net, { struct sock *s; - spin_lock(&unix_table_locks[hash]); + spin_lock(&net->unx.table.locks[hash]); s = __unix_find_socket_byname(net, sunname, len, hash); if (s) sock_hold(s); - spin_unlock(&unix_table_locks[hash]); + spin_unlock(&net->unx.table.locks[hash]); return s; } @@ -368,17 +457,17 @@ static struct sock *unix_find_socket_byinode(struct inode *i) unsigned int hash = unix_bsd_hash(i); struct sock *s; - spin_lock(&unix_table_locks[hash]); - sk_for_each(s, &unix_socket_table[hash]) { + spin_lock(&bsd_socket_locks[hash]); + sk_for_each_bound(s, &bsd_socket_buckets[hash]) { struct dentry *dentry = unix_sk(s)->path.dentry; if (dentry && d_backing_inode(dentry) == i) { sock_hold(s); - spin_unlock(&unix_table_locks[hash]); + spin_unlock(&bsd_socket_locks[hash]); return s; } } - spin_unlock(&unix_table_locks[hash]); + spin_unlock(&bsd_socket_locks[hash]); return NULL; } @@ -490,7 +579,7 @@ static int unix_dgram_peer_wake_me(struct sock *sk, struct sock *other) * -ECONNREFUSED. Otherwise, if we haven't queued any skbs * to other and its full, we will hang waiting for POLLOUT. */ - if (unix_recvq_full(other) && !sock_flag(other, SOCK_DEAD)) + if (unix_recvq_full_lockless(other) && !sock_flag(other, SOCK_DEAD)) return 1; if (connected) @@ -499,10 +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) @@ -510,12 +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(); } @@ -527,7 +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, @@ -535,28 +626,21 @@ static void unix_dgram_disconnected(struct sock *sk, struct sock *other) * when peer was not connected to us. */ if (!sock_flag(other, SOCK_DEAD) && unix_peer(other) == sk) { - other->sk_err = ECONNRESET; + WRITE_ONCE(other->sk_err, ECONNRESET); 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); -#if IS_ENABLED(CONFIG_AF_UNIX_OOB) - if (u->oob_skb) { - kfree_skb(u->oob_skb); - u->oob_skb = NULL; - } -#endif - WARN_ON(refcount_read(&sk->sk_wmem_alloc)); - WARN_ON(!sk_unhashed(sk)); - WARN_ON(sk->sk_socket); + DEBUG_NET_WARN_ON_ONCE(refcount_read(&sk->sk_wmem_alloc)); + DEBUG_NET_WARN_ON_ONCE(!sk_unhashed(sk)); + DEBUG_NET_WARN_ON_ONCE(sk->sk_socket); if (!sock_flag(sk, SOCK_DEAD)) { pr_info("Attempt to release alive unix socket: %p\n", sk); return; @@ -573,40 +657,56 @@ 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); - struct path path; struct sock *skpair; struct sk_buff *skb; + struct path path; int state; - unix_remove_socket(sk); + unix_remove_socket(sock_net(sk), sk); + unix_remove_bsd_socket(sk); /* Clear state */ unix_state_lock(sk); sock_orphan(sk); - sk->sk_shutdown = SHUTDOWN_MASK; + WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK); path = u->path; 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; unix_state_unlock(sk); +#if IS_ENABLED(CONFIG_AF_UNIX_OOB) + 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 */ - skpair->sk_shutdown = SHUTDOWN_MASK; - if (!skb_queue_empty(&sk->sk_receive_queue) || embrion) - skpair->sk_err = ECONNRESET; + WRITE_ONCE(skpair->sk_shutdown, SHUTDOWN_MASK); + if (skb || embrion) + WRITE_ONCE(skpair->sk_err, ECONNRESET); unix_state_unlock(skpair); skpair->sk_state_change(skpair); sk_wake_async(skpair, SOCK_WAKE_WAITD, POLL_HUP); @@ -621,9 +721,9 @@ 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) @@ -633,22 +733,50 @@ static void unix_release_sock(struct sock *sk, int embrion) /* ---- Socket is dead now and most probably destroyed ---- */ - /* - * Fixme: BSD difference: In BSD all sockets connected to us get - * ECONNRESET and we die on the spot. In Linux we behave - * like files and pipes do and wait for the last - * dereference. - * - * Can't we simply set sock->err? - * - * What the above comment does talk about? --ANK(980817) - */ + unix_schedule_gc(NULL); +} + +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; - if (unix_tot_inflight) - unix_gc(); /* Garbage collect fds */ + 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); + + 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 init_peercred(struct sock *sk) +static void update_peercred(struct sock *sk, struct unix_peercred *peercred) { const struct cred *old_cred; struct pid *old_pid; @@ -656,36 +784,26 @@ 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); 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) @@ -693,36 +811,42 @@ 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; } static int unix_release(struct socket *); -static int unix_bind(struct socket *, struct sockaddr *, int); -static int unix_stream_connect(struct socket *, struct sockaddr *, +static int unix_bind(struct socket *, struct sockaddr_unsized *, int); +static int unix_stream_connect(struct socket *, struct sockaddr_unsized *, 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 *, @@ -734,52 +858,111 @@ static int unix_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned lon static int unix_shutdown(struct socket *, int); static int unix_stream_sendmsg(struct socket *, struct msghdr *, size_t); static int unix_stream_recvmsg(struct socket *, struct msghdr *, size_t, int); -static ssize_t unix_stream_sendpage(struct socket *, struct page *, int offset, - size_t size, int flags); static ssize_t unix_stream_splice_read(struct socket *, loff_t *ppos, struct pipe_inode_info *, size_t size, unsigned int flags); static int unix_dgram_sendmsg(struct socket *, struct msghdr *, size_t); static int unix_dgram_recvmsg(struct socket *, struct msghdr *, size_t, int); -static int unix_read_sock(struct sock *sk, read_descriptor_t *desc, - sk_read_actor_t recv_actor); -static int unix_stream_read_sock(struct sock *sk, read_descriptor_t *desc, - sk_read_actor_t recv_actor); -static int unix_dgram_connect(struct socket *, struct sockaddr *, +static int unix_read_skb(struct sock *sk, skb_read_actor_t recv_actor); +static int unix_stream_read_skb(struct sock *sk, skb_read_actor_t recv_actor); +static int unix_dgram_connect(struct socket *, struct sockaddr_unsized *, int, int); static int unix_seqpacket_sendmsg(struct socket *, struct msghdr *, size_t); static int unix_seqpacket_recvmsg(struct socket *, struct msghdr *, size_t, int); -static int unix_set_peek_off(struct sock *sk, int val) +#ifdef CONFIG_PROC_FS +static int unix_count_nr_fds(struct sock *sk) { - struct unix_sock *u = unix_sk(sk); - - if (mutex_lock_interruptible(&u->iolock)) - return -EINTR; + struct sk_buff *skb; + struct unix_sock *u; + int nr_fds = 0; - sk->sk_peek_off = val; - mutex_unlock(&u->iolock); + spin_lock(&sk->sk_receive_queue.lock); + skb = skb_peek(&sk->sk_receive_queue); + while (skb) { + u = unix_sk(skb->sk); + nr_fds += atomic_read(&u->scm_stat.nr_fds); + skb = skb_peek_next(skb, &sk->sk_receive_queue); + } + spin_unlock(&sk->sk_receive_queue.lock); - return 0; + return nr_fds; } -#ifdef CONFIG_PROC_FS static void unix_show_fdinfo(struct seq_file *m, struct socket *sock) { struct sock *sk = sock->sk; + unsigned char s_state; struct unix_sock *u; + int nr_fds = 0; if (sk) { - u = unix_sk(sock->sk); - seq_printf(m, "scm_fds: %u\n", - atomic_read(&u->scm_stat.nr_fds)); + s_state = READ_ONCE(sk->sk_state); + u = unix_sk(sk); + + /* SOCK_STREAM and SOCK_SEQPACKET sockets never change their + * sk_state after switching to TCP_ESTABLISHED or TCP_LISTEN. + * SOCK_DGRAM is ordinary. So, no lock is needed. + */ + if (sock->type == SOCK_DGRAM || s_state == TCP_ESTABLISHED) + nr_fds = atomic_read(&u->scm_stat.nr_fds); + else if (s_state == TCP_LISTEN) + nr_fds = unix_count_nr_fds(sk); + + seq_printf(m, "scm_fds: %u\n", nr_fds); } } #else #define unix_show_fdinfo NULL #endif +static bool unix_custom_sockopt(int optname) +{ + switch (optname) { + case SO_INQ: + return true; + default: + return false; + } +} + +static int unix_setsockopt(struct socket *sock, int level, int optname, + sockptr_t optval, unsigned int optlen) +{ + struct unix_sock *u = unix_sk(sock->sk); + struct sock *sk = sock->sk; + int val; + + if (level != SOL_SOCKET) + return -EOPNOTSUPP; + + if (!unix_custom_sockopt(optname)) + return sock_setsockopt(sock, level, optname, optval, optlen); + + if (optlen != sizeof(int)) + return -EINVAL; + + if (copy_from_sockptr(&val, optval, sizeof(val))) + return -EFAULT; + + switch (optname) { + case SO_INQ: + if (sk->sk_type != SOCK_STREAM) + return -EINVAL; + + if (val > 1 || val < 0) + return -EINVAL; + + WRITE_ONCE(u->recvmsg_inq, val); + break; + default: + return -ENOPROTOOPT; + } + + return 0; +} + static const struct proto_ops unix_stream_ops = { .family = PF_UNIX, .owner = THIS_MODULE, @@ -796,13 +979,13 @@ static const struct proto_ops unix_stream_ops = { #endif .listen = unix_listen, .shutdown = unix_shutdown, + .setsockopt = unix_setsockopt, .sendmsg = unix_stream_sendmsg, .recvmsg = unix_stream_recvmsg, - .read_sock = unix_stream_read_sock, + .read_skb = unix_stream_read_skb, .mmap = sock_no_mmap, - .sendpage = unix_stream_sendpage, .splice_read = unix_stream_splice_read, - .set_peek_off = unix_set_peek_off, + .set_peek_off = sk_set_peek_off, .show_fdinfo = unix_show_fdinfo, }; @@ -823,11 +1006,10 @@ static const struct proto_ops unix_dgram_ops = { .listen = sock_no_listen, .shutdown = unix_shutdown, .sendmsg = unix_dgram_sendmsg, - .read_sock = unix_read_sock, + .read_skb = unix_read_skb, .recvmsg = unix_dgram_recvmsg, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, - .set_peek_off = unix_set_peek_off, + .set_peek_off = sk_set_peek_off, .show_fdinfo = unix_show_fdinfo, }; @@ -850,8 +1032,7 @@ static const struct proto_ops unix_seqpacket_ops = { .sendmsg = unix_seqpacket_sendmsg, .recvmsg = unix_seqpacket_recvmsg, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, - .set_peek_off = unix_set_peek_off, + .set_peek_off = sk_set_peek_off, .show_fdinfo = unix_show_fdinfo, }; @@ -862,11 +1043,18 @@ static void unix_close(struct sock *sk, long timeout) */ } -static void unix_unhash(struct sock *sk) +static bool unix_bpf_bypass_getsockopt(int level, int optname) { - /* Nothing to do here, unix socket does not need a ->unhash(). - * This is merely for sockmap. - */ + if (level == SOL_SOCKET) { + switch (optname) { + case SO_PEERPIDFD: + return true; + default: + return false; + } + } + + return false; } struct proto unix_dgram_proto = { @@ -874,6 +1062,7 @@ struct proto unix_dgram_proto = { .owner = THIS_MODULE, .obj_size = sizeof(struct unix_sock), .close = unix_close, + .bpf_bypass_getsockopt = unix_bpf_bypass_getsockopt, #ifdef CONFIG_BPF_SYSCALL .psock_update_sk_prot = unix_dgram_bpf_update_proto, #endif @@ -884,7 +1073,7 @@ 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, #endif @@ -914,25 +1103,29 @@ 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; - u = unix_sk(sk); + lock_set_cmp_fn(&sk->sk_receive_queue.lock, unix_recvq_lock_cmp_fn, NULL); + + u = unix_sk(sk); + u->listener = NULL; + u->vertex = NULL; u->path.dentry = NULL; u->path.mnt = NULL; spin_lock_init(&u->lock); - atomic_long_set(&u->inflight, 0); - 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); init_waitqueue_func_entry(&u->peer_wake, unix_dgram_peer_wake_relay); memset(&u->scm_stat, 0, sizeof(struct scm_stat)); - unix_insert_unbound_socket(sk); + unix_insert_unbound_socket(net, sk); - sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); + sock_prot_inuse_add(net, sk->sk_prot, 1); return sk; @@ -953,6 +1146,7 @@ static int unix_create(struct net *net, struct socket *sock, int protocol, switch (sock->type) { case SOCK_STREAM: + set_bit(SOCK_CUSTOM_SOCKOPT, &sock->flags); sock->ops = &unix_stream_ops; break; /* @@ -993,8 +1187,8 @@ static int unix_release(struct socket *sock) return 0; } -static struct sock *unix_find_bsd(struct net *net, struct sockaddr_un *sunaddr, - int addr_len, int type) +static struct sock *unix_find_bsd(struct sockaddr_un *sunaddr, int addr_len, + int type, int flags) { struct inode *inode; struct path path; @@ -1002,13 +1196,30 @@ static struct sock *unix_find_bsd(struct net *net, struct sockaddr_un *sunaddr, 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) { + struct path root; + + task_lock(&init_task); + get_fs_root(init_task.fs, &root); + task_unlock(&init_task); + + scoped_with_kernel_creds() + err = vfs_path_lookup(root.dentry, root.mnt, sunaddr->sun_path, + LOOKUP_BENEATH | LOOKUP_NO_SYMLINKS | + LOOKUP_NO_MAGICLINKS, &path); + 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); @@ -1058,12 +1269,12 @@ 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(net, sunaddr, addr_len, type); + sk = unix_find_bsd(sunaddr, addr_len, type, flags); else sk = unix_find_abstract(net, sunaddr, addr_len, type); @@ -1072,8 +1283,9 @@ 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; int err; @@ -1095,18 +1307,18 @@ static int unix_autobind(struct sock *sk) addr->name->sun_family = AF_UNIX; refcount_set(&addr->refcnt, 1); - ordernum = prandom_u32(); + old_hash = sk->sk_hash; + ordernum = get_random_u32(); lastnum = ordernum & 0xFFFFF; retry: ordernum = (ordernum + 1) & 0xFFFFF; sprintf(addr->name->sun_path + 1, "%05x", ordernum); new_hash = unix_abstract_hash(addr->name, addr->len, sk->sk_type); - unix_table_double_lock(old_hash, new_hash); + unix_table_double_lock(net, old_hash, new_hash); - if (__unix_find_socket_byname(sock_net(sk), addr->name, addr->len, - new_hash)) { - unix_table_double_unlock(old_hash, new_hash); + if (__unix_find_socket_byname(net, addr->name, addr->len, new_hash)) { + unix_table_double_unlock(net, old_hash, new_hash); /* __unix_find_socket_byname() may take long time if many names * are already in use. @@ -1123,8 +1335,8 @@ retry: goto retry; } - __unix_set_addr_hash(sk, addr, new_hash); - unix_table_double_unlock(old_hash, new_hash); + __unix_set_addr_hash(net, sk, addr, new_hash); + unix_table_double_unlock(net, old_hash, new_hash); err = 0; out: mutex_unlock(&u->bindlock); @@ -1136,18 +1348,16 @@ 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); - struct user_namespace *ns; // barf... + unsigned int new_hash, old_hash; + struct net *net = sock_net(sk); + struct mnt_idmap *idmap; struct unix_address *addr; struct dentry *dentry; struct path parent; int err; - unix_mkname_bsd(sunaddr, addr_len); - addr_len = strlen(sunaddr->sun_path) + - offsetof(struct sockaddr_un, sun_path) + 1; - + addr_len = unix_mkname_bsd(sunaddr, addr_len); addr = unix_create_addr(sunaddr, addr_len); if (!addr) return -ENOMEM; @@ -1156,7 +1366,7 @@ static int unix_bind_bsd(struct sock *sk, struct sockaddr_un *sunaddr, * Get the parent directory, calculate the hash for last * component. */ - dentry = kern_path_create(AT_FDCWD, addr->name->sun_path, &parent, 0); + dentry = start_creating_path(AT_FDCWD, addr->name->sun_path, &parent, 0); if (IS_ERR(dentry)) { err = PTR_ERR(dentry); goto out; @@ -1165,10 +1375,10 @@ static int unix_bind_bsd(struct sock *sk, struct sockaddr_un *sunaddr, /* * All right, let's create it. */ - ns = mnt_user_ns(parent.mnt); + idmap = mnt_idmap(parent.mnt); err = security_path_mknod(&parent, dentry, mode, 0); if (!err) - err = vfs_mknod(ns, d_inode(parent.dentry), dentry, mode, 0); + err = vfs_mknod(idmap, d_inode(parent.dentry), dentry, mode, 0, NULL); if (err) goto out_path; err = mutex_lock_interruptible(&u->bindlock); @@ -1177,14 +1387,16 @@ 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(old_hash, new_hash); + unix_table_double_lock(net, old_hash, new_hash); u->path.mnt = mntget(parent.mnt); u->path.dentry = dget(dentry); - __unix_set_addr_hash(sk, addr, new_hash); - unix_table_double_unlock(old_hash, new_hash); + __unix_set_addr_hash(net, sk, addr, new_hash); + unix_table_double_unlock(net, old_hash, new_hash); + unix_insert_bsd_socket(sk); mutex_unlock(&u->bindlock); - done_path_create(&parent, dentry); + end_creating_path(&parent, dentry); return 0; out_unlock: @@ -1192,9 +1404,9 @@ out_unlock: err = -EINVAL; out_unlink: /* failed after successful mknod? unlink what we'd created... */ - vfs_unlink(ns, d_inode(parent.dentry), dentry, NULL); + vfs_unlink(idmap, d_inode(parent.dentry), dentry, NULL); out_path: - done_path_create(&parent, dentry); + end_creating_path(&parent, dentry); out: unix_release_addr(addr); return err == -EEXIST ? -EADDRINUSE : err; @@ -1203,8 +1415,9 @@ 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; @@ -1221,20 +1434,20 @@ 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(old_hash, new_hash); + unix_table_double_lock(net, old_hash, new_hash); - if (__unix_find_socket_byname(sock_net(sk), addr->name, addr->len, - new_hash)) + if (__unix_find_socket_byname(net, addr->name, addr->len, new_hash)) goto out_spin; - __unix_set_addr_hash(sk, addr, new_hash); - unix_table_double_unlock(old_hash, new_hash); + __unix_set_addr_hash(net, sk, addr, new_hash); + unix_table_double_unlock(net, old_hash, new_hash); mutex_unlock(&u->bindlock); return 0; out_spin: - unix_table_double_unlock(old_hash, new_hash); + unix_table_double_unlock(net, old_hash, new_hash); err = -EADDRINUSE; out_mutex: mutex_unlock(&u->bindlock); @@ -1243,7 +1456,7 @@ out: return err; } -static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) +static int unix_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len) { struct sockaddr_un *sunaddr = (struct sockaddr_un *)uaddr; struct sock *sk = sock->sk; @@ -1271,13 +1484,12 @@ static void unix_state_double_lock(struct sock *sk1, struct sock *sk2) unix_state_lock(sk1); return; } - if (sk1 < sk2) { - unix_state_lock(sk1); - unix_state_lock_nested(sk2); - } else { - unix_state_lock(sk2); - unix_state_lock_nested(sk1); - } + + if (sk1 > sk2) + swap(sk1, sk2); + + unix_state_lock(sk1); + unix_state_lock(sk2); } static void unix_state_double_unlock(struct sock *sk1, struct sock *sk2) @@ -1290,12 +1502,11 @@ static void unix_state_double_unlock(struct sock *sk1, struct sock *sk2) unix_state_unlock(sk2); } -static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr, +static int unix_dgram_connect(struct socket *sock, struct sockaddr_unsized *addr, int alen, int flags) { - struct sock *sk = sock->sk; - struct net *net = sock_net(sk); struct sockaddr_un *sunaddr = (struct sockaddr_un *)addr; + struct sock *sk = sock->sk; struct sock *other; int err; @@ -1308,15 +1519,18 @@ static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr, if (err) goto out; - if (test_bit(SOCK_PASSCRED, &sock->flags) && - !unix_sk(sk)->addr) { + err = BPF_CGROUP_RUN_PROG_UNIX_CONNECT_LOCK(sk, addr, &alen); + if (err) + goto out; + + if (unix_may_passcred(sk) && !READ_ONCE(unix_sk(sk)->addr)) { err = unix_autobind(sk); if (err) goto out; } restart: - other = unix_find_other(net, 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; @@ -1339,7 +1553,8 @@ 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 @@ -1356,13 +1571,20 @@ 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; @@ -1379,7 +1601,6 @@ 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; @@ -1389,7 +1610,7 @@ static long unix_wait_for_peer(struct sock *other, long timeo) sched = !sock_flag(other, SOCK_DEAD) && !(other->sk_shutdown & RCV_SHUTDOWN) && - unix_recvq_full(other); + unix_recvq_full_lockless(other); unix_state_unlock(other); @@ -1400,25 +1621,28 @@ static long unix_wait_for_peer(struct sock *other, long timeo) return timeo; } -static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, +static int unix_stream_connect(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len, int flags) { struct sockaddr_un *sunaddr = (struct sockaddr_un *)uaddr; - struct sock *sk = sock->sk; - struct net *net = sock_net(sk); + struct sock *sk = sock->sk, *newsk = NULL, *other = NULL; struct unix_sock *u = unix_sk(sk), *newu, *otheru; - struct sock *newsk = NULL; - struct sock *other = NULL; + struct unix_peercred peercred = {}; + struct net *net = sock_net(sk); struct sk_buff *skb = NULL; - int st; - int err; + unsigned char state; long timeo; + int err; err = unix_validate_addr(sunaddr, addr_len); if (err) goto out; - if (test_bit(SOCK_PASSCRED, &sock->flags) && !u->addr) { + err = BPF_CGROUP_RUN_PROG_UNIX_CONNECT_LOCK(sk, uaddr, &addr_len); + if (err) + goto out; + + if (unix_may_passcred(sk) && !READ_ONCE(u->addr)) { err = unix_autobind(sk); if (err) goto out; @@ -1427,35 +1651,36 @@ 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(sock_net(sk), NULL, 0, sock->type); + 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. */ @@ -1465,59 +1690,43 @@ 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); + 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); @@ -1529,11 +1738,14 @@ 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); @@ -1541,9 +1753,9 @@ restart: * * The contents of *(otheru->addr) and otheru->path * are seen fully set up here, since we have found - * otheru in hash under unix_table_locks. Insertion - * into the hash chain we'd found it in had been done - * in an earlier critical area protected by unix_table_locks, + * otheru in hash under its lock. Insertion into the + * hash chain we'd found it in had been done in an + * earlier critical area protected by the chain's lock, * the same one where we'd set *(otheru->addr) contents, * as well as otheru->path and otheru->addr itself. * @@ -1565,7 +1777,7 @@ 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() */ @@ -1583,29 +1795,40 @@ 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; @@ -1614,40 +1837,31 @@ 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_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, 0, flags&O_NONBLOCK, &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; } @@ -1655,16 +1869,19 @@ static int unix_accept(struct socket *sock, struct socket *newsock, int flags, skb_free_datagram(sk, skb); wake_up_interruptible(&unix_sk(sk)->peer_wait); + if (tsk->sk_type == SOCK_STREAM) + set_bit(SOCK_CUSTOM_SOCKOPT, &newsock->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; } @@ -1694,64 +1911,80 @@ static int unix_getname(struct socket *sock, struct sockaddr *uaddr, int peer) } else { err = addr->len; memcpy(sunaddr, addr->name, addr->len); + + if (peer) + BPF_CGROUP_RUN_SA_PROG(sk, uaddr, &err, + CGROUP_UNIX_GETPEERNAME); + else + BPF_CGROUP_RUN_SA_PROG(sk, uaddr, &err, + CGROUP_UNIX_GETSOCKNAME); } sock_put(sk); out: return err; } +/* 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(READ_ONCE(user->unix_inflight) > task_rlimit(p, RLIMIT_NOFILE))) + return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN); + return false; +} + +static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) +{ + if (too_many_unix_fds(current)) + return -ETOOMANYREFS; + + UNIXCB(skb).fp = scm->fp; + scm->fp = NULL; + + if (unix_prepare_fpl(UNIXCB(skb).fp)) + return -ENOMEM; + + return 0; +} + +static void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb) +{ + scm->fp = UNIXCB(skb).fp; + UNIXCB(skb).fp = NULL; + + 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) +{ + struct scm_cookie scm; + + memset(&scm, 0, sizeof(scm)); + scm.pid = UNIXCB(skb).pid; + if (UNIXCB(skb).fp) + unix_detach_fds(&scm, skb); + + /* Alas, it calls VFS */ + /* So fscking what? fput() had been SMP-safe since the last Summer */ + scm_destroy(&scm); + sock_wfree(skb); } static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool send_fds) { 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; @@ -1763,56 +1996,54 @@ 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) +static void unix_skb_to_scm(struct sk_buff *skb, struct scm_cookie *scm) { - return test_bit(SOCK_PASSCRED, &sock->flags) || - !other->sk_socket || - test_bit(SOCK_PASSCRED, &other->sk_socket->flags); + scm_set_cred(scm, UNIXCB(skb).pid, UNIXCB(skb).uid, UNIXCB(skb).gid); + unix_set_secdata(scm, skb); } -/* +/** + * unix_maybe_add_creds() - Adds current task uid/gid and struct pid to skb if needed. + * @skb: skb to attach creds to. + * @sk: Sender sock. + * @other: Receiver sock. + * * Some apps rely on write() giving SCM_CREDENTIALS * We include credentials if source or destination socket * asserted SOCK_PASSCRED. + * + * Context: May sleep. + * Return: On success zero, on error a negative error code is returned. */ -static void maybe_add_creds(struct sk_buff *skb, const struct socket *sock, - const struct sock *other) +static int 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)); - current_uid_gid(&UNIXCB(skb).uid, &UNIXCB(skb).gid); - } -} + return 0; -static int maybe_init_creds(struct scm_cookie *scm, - struct socket *socket, - const struct sock *other) -{ - int err; - struct msghdr msg = { .msg_controllen = 0 }; + if (unix_may_passcred(sk) || unix_may_passcred(other) || + !other->sk_socket) { + struct pid *pid; + int err; - err = scm_send(socket, &msg, scm, false); - if (err) - return err; + pid = task_tgid(current); + err = pidfs_register_pid(pid); + if (unlikely(err)) + return err; - if (unix_passcred_enabled(socket, other)) { - scm->pid = get_pid(task_tgid(current)); - current_uid_gid(&scm->creds.uid, &scm->creds.gid); + UNIXCB(skb).pid = get_pid(pid); + current_uid_gid(&UNIXCB(skb).uid, &UNIXCB(skb).gid); } - return err; + + return 0; } static bool unix_skb_scm_eq(struct sk_buff *skb, struct scm_cookie *scm) { - const struct unix_skb_parms *u = &UNIXCB(skb); - - return u->pid == scm->pid && - uid_eq(u->uid, scm->creds.uid) && - gid_eq(u->gid, scm->creds.gid) && + return UNIXCB(skb).pid == scm->pid && + uid_eq(UNIXCB(skb).uid, scm->creds.uid) && + gid_eq(UNIXCB(skb).gid, scm->creds.gid) && unix_secdata_eq(scm, skb); } @@ -1821,8 +2052,10 @@ 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) @@ -1830,8 +2063,10 @@ 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); + } } /* @@ -1841,48 +2076,47 @@ 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) { - struct sock *sk = sock->sk; - struct net *net = sock_net(sk); + struct sock *sk = sock->sk, *other = NULL; struct unix_sock *u = unix_sk(sk); - DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr, msg->msg_name); - struct sock *other = NULL; - int err; - struct sk_buff *skb; - long timeo; struct scm_cookie scm; + struct sk_buff *skb; int data_len = 0; int sk_locked; + long timeo; + int err; - wait_for_unix_gc(); err = scm_send(sock, msg, &scm, false); if (err < 0) return err; - 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; - } else { - sunaddr = NULL; - err = -ENOTCONN; - other = unix_peer_get(sk); - if (!other) + + err = BPF_CGROUP_RUN_PROG_UNIX_SENDMSG_LOCK(sk, + msg->msg_name, + &msg->msg_namelen, + NULL); + if (err) goto out; } - if (test_bit(SOCK_PASSCRED, &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, @@ -1896,7 +2130,7 @@ 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); @@ -1912,17 +2146,18 @@ 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(net, 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; } } @@ -1930,51 +2165,73 @@ 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; } + err = unix_maybe_add_creds(skb, sk, other); + if (err) + 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 - */ + /* Check with 1003.1g - what should datagram error */ + unix_state_unlock(other); - sock_put(other); + + 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. + */ + err = -EPIPE; + goto out_sock_put; + } if (!sk_locked) unix_state_lock(sk); - err = 0; if (unix_peer(sk) == other) { unix_peer(sk) = NULL; unix_dgram_peer_wake_disconnect_wakeup(sk, other); + WRITE_ONCE(sk->sk_state, TCP_CLOSE); unix_state_unlock(sk); - sk->sk_state = TCP_CLOSE; 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); @@ -1994,7 +2251,7 @@ restart_locked: err = sock_intr_errno(timeo); if (signal_pending(current)) - goto out_free; + goto out_sock_put; goto restart; } @@ -2022,7 +2279,7 @@ restart_locked: if (sock_flag(other, SOCK_RCVTSTAMP)) __net_timestamp(skb); - maybe_add_creds(skb, sock, other); + scm_stat_add(other, skb); skb_queue_tail(&other->sk_receive_queue, skb); unix_state_unlock(other); @@ -2035,11 +2292,11 @@ 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; } @@ -2049,49 +2306,63 @@ 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) +#if IS_ENABLED(CONFIG_AF_UNIX_OOB) +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) + goto out; + + err = unix_maybe_add_creds(skb, sk, other); + if (err) + 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); + scm_stat_add(other, skb); - ousk->oob_skb = skb; + spin_lock(&other->sk_receive_queue.lock); + WRITE_ONCE(ousk->oob_skb, skb); + WRITE_ONCE(ousk->inq_len, ousk->inq_len + 1); + __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 @@ -2100,22 +2371,20 @@ 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 unix_sock *otheru; struct scm_cookie scm; bool fds_sent = false; - int data_len; + int err, sent = 0; - wait_for_unix_gc(); err = scm_send(sock, msg, &scm, false); if (err < 0) return err; - err = -EOPNOTSUPP; if (msg->msg_flags & MSG_OOB) { -#if (IS_ENABLED(CONFIG_AF_UNIX_OOB)) + err = -EOPNOTSUPP; +#if IS_ENABLED(CONFIG_AF_UNIX_OOB) if (len) len--; else @@ -2124,71 +2393,102 @@ 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 { + } + + other = unix_peer(sk); + if (!other) { err = -ENOTCONN; - other = unix_peer(sk); - if (!other) - goto out_err; + goto out_err; } - if (sk->sk_shutdown & SEND_SHUTDOWN) - goto pipe_err; + otheru = unix_sk(other); + + if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) + goto out_pipe; while (sent < len) { - size = len - sent; + int size = len - sent; + int data_len; - /* Keep two messages in the pipe so it schedules better */ - size = min_t(int, size, (sk->sk_sndbuf >> 1) - 64); + if (unlikely(msg->msg_flags & MSG_SPLICE_PAGES)) { + skb = sock_alloc_send_pskb(sk, 0, 0, + msg->msg_flags & MSG_DONTWAIT, + &err, 0); + } else { + /* Keep two messages in the pipe so it schedules better */ + 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); + /* allow fallback to order-0 allocations */ + size = min_t(int, size, SKB_MAX_HEAD(0) + UNIX_SKB_FRAGS_SZ); - data_len = max_t(int, 0, size - SKB_MAX_HEAD(0)); + data_len = max_t(int, 0, size - SKB_MAX_HEAD(0)); - data_len = min_t(size_t, size, PAGE_ALIGN(data_len)); + data_len = min_t(size_t, size, PAGE_ALIGN(data_len)); - skb = sock_alloc_send_pskb(sk, size - data_len, data_len, - msg->msg_flags & MSG_DONTWAIT, &err, - get_order(UNIX_SKB_FRAGS_SZ)); + skb = sock_alloc_send_pskb(sk, size - data_len, data_len, + msg->msg_flags & MSG_DONTWAIT, &err, + get_order(UNIX_SKB_FRAGS_SZ)); + } if (!skb) goto out_err; /* 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; - skb_put(skb, size - data_len); - 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; + err = unix_maybe_add_creds(skb, sk, other); + if (err) + goto out_free; + + if (unlikely(msg->msg_flags & MSG_SPLICE_PAGES)) { + skb->ip_summed = CHECKSUM_UNNECESSARY; + err = skb_splice_from_iter(skb, &msg->msg_iter, size); + if (err < 0) + goto out_free; + + size = err; + refcount_add(size, &sk->sk_wmem_alloc); + } else { + skb_put(skb, size - data_len); + skb->data_len = data_len; + skb->len = size; + err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, size); + 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; + + if (UNIXCB(skb).fp && !other->sk_scm_rights) { + unix_state_unlock(other); + err = -EPERM; + goto out_free; + } - maybe_add_creds(skb, sock, other); scm_stat_add(other, skb); - skb_queue_tail(&other->sk_receive_queue, skb); + + spin_lock(&other->sk_receive_queue.lock); + WRITE_ONCE(otheru->inq_len, otheru->inq_len + skb->len); + __skb_queue_tail(&other->sk_receive_queue, skb); + spin_unlock(&other->sk_receive_queue.lock); + unix_state_unlock(other); other->sk_data_ready(other); sent += size; } -#if (IS_ENABLED(CONFIG_AF_UNIX_OOB)) +#if IS_ENABLED(CONFIG_AF_UNIX_OOB) if (msg->msg_flags & MSG_OOB) { - err = queue_oob(sock, msg, other); + err = queue_oob(sk, msg, other, &scm, fds_sent); if (err) goto out_err; sent++; @@ -2199,134 +2499,19 @@ 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; } -static ssize_t unix_stream_sendpage(struct socket *socket, struct page *page, - int offset, size_t size, int flags) -{ - int err; - bool send_sigpipe = false; - bool init_scm = true; - struct scm_cookie scm; - struct sock *other, *sk = socket->sk; - struct sk_buff *skb, *newskb = NULL, *tail = NULL; - - if (flags & MSG_OOB) - return -EOPNOTSUPP; - - other = unix_peer(sk); - if (!other || sk->sk_state != TCP_ESTABLISHED) - return -ENOTCONN; - - if (false) { -alloc_skb: - unix_state_unlock(other); - 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 iolock as we modify already present - * skbs in the sk_receive_queue and mess with skb->len - */ - err = mutex_lock_interruptible(&unix_sk(other)->iolock); - if (err) { - err = flags & MSG_DONTWAIT ? -EAGAIN : -ERESTARTSYS; - goto err; - } - - if (sk->sk_shutdown & SEND_SHUTDOWN) { - err = -EPIPE; - send_sigpipe = true; - goto err_unlock; - } - - unix_state_lock(other); - - if (sock_flag(other, SOCK_DEAD) || - other->sk_shutdown & RCV_SHUTDOWN) { - err = -EPIPE; - send_sigpipe = true; - goto err_state_unlock; - } - - if (init_scm) { - err = maybe_init_creds(&scm, socket, other); - if (err) - goto err_state_unlock; - init_scm = false; - } - - skb = skb_peek_tail(&other->sk_receive_queue); - if (tail && tail == skb) { - skb = newskb; - } else if (!skb || !unix_skb_scm_eq(skb, &scm)) { - if (newskb) { - skb = newskb; - } else { - tail = skb; - goto alloc_skb; - } - } else if (newskb) { - /* this is fast path, we don't necessarily need to - * call to kfree_skb even though with newskb == NULL - * this - does no harm - */ - consume_skb(newskb); - newskb = NULL; - } - - if (skb_append_pagefrags(skb, page, offset, size)) { - tail = skb; - goto alloc_skb; - } - - skb->len += size; - skb->data_len += size; - skb->truesize += size; - refcount_add(size, &sk->sk_wmem_alloc); - - if (newskb) { - err = unix_scm_to_skb(&scm, skb, false); - if (err) - goto err_state_unlock; - spin_lock(&other->sk_receive_queue.lock); - __skb_queue_tail(&other->sk_receive_queue, newskb); - spin_unlock(&other->sk_receive_queue.lock); - } - - unix_state_unlock(other); - mutex_unlock(&unix_sk(other)->iolock); - - other->sk_data_ready(other); - scm_destroy(&scm); - return size; - -err_state_unlock: - unix_state_unlock(other); -err_unlock: - mutex_unlock(&unix_sk(other)->iolock); -err: - kfree_skb(newskb); - if (send_sigpipe && !(flags & MSG_NOSIGNAL)) - send_sig(SIGPIPE, current, 0); - if (!init_scm) - scm_destroy(&scm); - return err; -} - static int unix_seqpacket_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { @@ -2337,7 +2522,7 @@ 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) @@ -2351,7 +2536,7 @@ 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); @@ -2405,12 +2590,10 @@ int __unix_dgram_recvmsg(struct sock *sk, struct msghdr *msg, size_t size, &err, &timeo, last)); 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 && - (sk->sk_shutdown & RCV_SHUTDOWN)) + (READ_ONCE(sk->sk_shutdown) & RCV_SHUTDOWN)) err = 0; - unix_state_unlock(sk); goto out; } @@ -2419,9 +2602,14 @@ int __unix_dgram_recvmsg(struct sock *sk, struct msghdr *msg, size_t size, EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND); - if (msg->msg_name) + if (msg->msg_name) { unix_copy_addr(msg, skb->sk); + BPF_CGROUP_RUN_PROG_UNIX_RECVMSG_LOCK(sk, + msg->msg_name, + &msg->msg_namelen); + } + if (size > skb->len - skip) size = skb->len - skip; else if (size < skb->len - skip) @@ -2436,8 +2624,7 @@ int __unix_dgram_recvmsg(struct sock *sk, struct msghdr *msg, size_t size, memset(&scm, 0, sizeof(scm)); - scm_set_cred(&scm, UNIXCB(skb).pid, UNIXCB(skb).uid, UNIXCB(skb).gid); - unix_set_secdata(&scm, skb); + unix_skb_to_scm(skb, &scm); if (!(flags & MSG_PEEK)) { if (UNIXCB(skb).fp) @@ -2465,7 +2652,7 @@ int __unix_dgram_recvmsg(struct sock *sk, struct msghdr *msg, size_t size, } err = (flags & MSG_TRUNC) ? skb->len - skip : size; - scm_recv(sock, msg, &scm, flags); + scm_recv_unix(sock, msg, &scm, flags); out_free: skb_free_datagram(sk, skb); @@ -2483,44 +2670,24 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg, size_t si const struct proto *prot = READ_ONCE(sk->sk_prot); if (prot != &unix_dgram_proto) - return prot->recvmsg(sk, msg, size, flags & MSG_DONTWAIT, - flags & ~MSG_DONTWAIT, NULL); + return prot->recvmsg(sk, msg, size, flags, NULL); #endif return __unix_dgram_recvmsg(sk, msg, size, flags); } -static int unix_read_sock(struct sock *sk, read_descriptor_t *desc, - sk_read_actor_t recv_actor) +static int unix_read_skb(struct sock *sk, skb_read_actor_t recv_actor) { - int copied = 0; - - while (1) { - struct unix_sock *u = unix_sk(sk); - struct sk_buff *skb; - int used, err; - - mutex_lock(&u->iolock); - skb = skb_recv_datagram(sk, 0, 1, &err); - mutex_unlock(&u->iolock); - if (!skb) - return err; - - used = recv_actor(desc, skb, 0, skb->len); - if (used <= 0) { - if (!copied) - copied = used; - kfree_skb(skb); - break; - } else if (used <= skb->len) { - copied += used; - } + struct unix_sock *u = unix_sk(sk); + struct sk_buff *skb; + int err; - kfree_skb(skb); - if (!desc->count) - break; - } + mutex_lock(&u->iolock); + skb = skb_recv_datagram(sk, MSG_DONTWAIT, &err); + mutex_unlock(&u->iolock); + if (!skb) + return err; - return copied; + return recv_actor(sk, skb); } /* @@ -2530,13 +2697,14 @@ static long unix_stream_data_wait(struct sock *sk, long timeo, struct sk_buff *last, unsigned int last_len, bool freezable) { + unsigned int state = TASK_INTERRUPTIBLE | freezable * TASK_FREEZABLE; struct sk_buff *tail; DEFINE_WAIT(wait); unix_state_lock(sk); for (;;) { - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, state); tail = skb_peek_tail(&sk->sk_receive_queue); if (tail != last || @@ -2549,10 +2717,7 @@ static long unix_stream_data_wait(struct sock *sk, long timeo, sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); unix_state_unlock(sk); - if (freezable) - timeo = freezable_schedule_timeout(timeo); - else - timeo = schedule_timeout(timeo); + timeo = schedule_timeout(timeo); unix_state_lock(sk); if (sock_flag(sk, SOCK_DEAD)) @@ -2566,11 +2731,6 @@ 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 *); @@ -2585,16 +2745,18 @@ 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; @@ -2603,20 +2765,28 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state) oob_skb = u->oob_skb; if (!(state->flags & MSG_PEEK)) { - u->oob_skb = NULL; + WRITE_ONCE(u->oob_skb, NULL); + WRITE_ONCE(u->inq_len, u->inq_len - 1); + + 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); - if (!(state->flags & MSG_PEEK)) { + if (!(state->flags & MSG_PEEK)) UNIXCB(oob_skb).consumed += 1; - kfree_skb(oob_skb); - } mutex_unlock(&u->iolock); + consume_skb(read_skb); + if (chunk < 0) return -EFAULT; @@ -2627,60 +2797,119 @@ 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)) { - u->oob_skb = NULL; - consume_skb(skb); - } - } else if (!(flags & MSG_PEEK)) { - skb_unlink(skb, &sk->sk_receive_queue); - consume_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_sock(struct sock *sk, read_descriptor_t *desc, - sk_read_actor_t recv_actor) +static int unix_stream_read_skb(struct sock *sk, skb_read_actor_t recv_actor) { - if (unlikely(sk->sk_state != TCP_ESTABLISHED)) + struct sk_buff_head *queue = &sk->sk_receive_queue; + 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_sock(sk, desc, recv_actor); + err = sock_error(sk); + if (err) + return err; + + mutex_lock(&u->iolock); + spin_lock(&queue->lock); + + skb = __skb_dequeue(queue); + if (!skb) { + spin_unlock(&queue->lock); + mutex_unlock(&u->iolock); + return -EAGAIN; + } + + WRITE_ONCE(u->inq_len, u->inq_len - skb->len); + +#if IS_ENABLED(CONFIG_AF_UNIX_OOB) + if (skb == u->oob_skb) { + WRITE_ONCE(u->oob_skb, NULL); + spin_unlock(&queue->lock); + mutex_unlock(&u->iolock); + + kfree_skb_reason(skb, SKB_DROP_REASON_UNIX_SKIP_OOB); + return -EAGAIN; + } +#endif + + spin_unlock(&queue->lock); + mutex_unlock(&u->iolock); + + return recv_actor(sk, skb); } static int unix_stream_read_generic(struct unix_stream_read_state *state, bool freezable) { - struct scm_cookie scm; + int noblock = state->flags & MSG_DONTWAIT; struct socket *sock = state->socket; + struct msghdr *msg = state->msg; struct sock *sk = sock->sk; - struct unix_sock *u = unix_sk(sk); - int copied = 0; + size_t size = state->size; int flags = state->flags; - int noblock = flags & MSG_DONTWAIT; bool check_creds = false; - int target; + struct scm_cookie scm; + unsigned int last_len; + struct unix_sock *u; + int copied = 0; int err = 0; long timeo; + int target; int skip; - 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; } @@ -2698,6 +2927,9 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state, memset(&scm, 0, sizeof(scm)); + u = unix_sk(sk); + +redo: /* Lock the socket to prevent queue disordering * while sleeps in memcpy_tomsg */ @@ -2706,11 +2938,9 @@ 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); if (sock_flag(sk, SOCK_DEAD)) { err = -ECONNRESET; @@ -2719,18 +2949,16 @@ redo: last = skb = skb_peek(&sk->sk_receive_queue); last_len = last ? last->len : 0; +again: #if IS_ENABLED(CONFIG_AF_UNIX_OOB) if (skb) { skb = manage_oob(skb, sk, flags, copied); - if (!skb) { + if (!skb && copied) { unix_state_unlock(sk); - if (copied) - break; - goto redo; + break; } } #endif -again: if (skb == NULL) { if (copied >= target) goto unlock; @@ -2762,7 +2990,6 @@ again: goto out; } - mutex_lock(&u->iolock); goto redo; unlock: unix_state_unlock(sk); @@ -2784,27 +3011,25 @@ unlock: /* Never glue messages from different writers */ if (!unix_skb_scm_eq(skb, &scm)) break; - } else if (test_bit(SOCK_PASSCRED, &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); + unix_skb_to_scm(skb, &scm); check_creds = true; } /* Copy address just once */ - if (state->msg && state->msg->msg_name) { - DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr, - state->msg->msg_name); - unix_copy_addr(state->msg, skb->sk); + if (msg && msg->msg_name) { + DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr, msg->msg_name); + + unix_copy_addr(msg, skb->sk); + BPF_CGROUP_RUN_PROG_UNIX_RECVMSG_LOCK(sk, msg->msg_name, + &msg->msg_namelen); + sunaddr = NULL; } 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; @@ -2813,18 +3038,6 @@ 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; @@ -2839,7 +3052,11 @@ unlock: if (unix_skb_len(skb)) break; - skb_unlink(skb, &sk->sk_receive_queue); + spin_lock(&sk->sk_receive_queue.lock); + WRITE_ONCE(u->inq_len, u->inq_len - skb->len); + __skb_unlink(skb, &sk->sk_receive_queue); + spin_unlock(&sk->sk_receive_queue.lock); + consume_skb(skb); if (scm.fp) @@ -2868,10 +3085,17 @@ unlock: } while (size); mutex_unlock(&u->iolock); - if (state->msg) - scm_recv(sock, state->msg, &scm, flags); - else + if (msg) { + scm_recv_unix(sock, msg, &scm, flags); + + if (READ_ONCE(u->recvmsg_inq) || msg->msg_get_inq) { + msg->msg_inq = READ_ONCE(u->inq_len); + put_cmsg(msg, SOL_SOCKET, SCM_INQ, + sizeof(msg->msg_inq), &msg->msg_inq); + } + } else { scm_destroy(&scm); + } out: return copied ? : err; } @@ -2917,8 +3141,7 @@ static int unix_stream_recvmsg(struct socket *sock, struct msghdr *msg, const struct proto *prot = READ_ONCE(sk->sk_prot); if (prot != &unix_stream_proto) - return prot->recvmsg(sk, msg, size, flags & MSG_DONTWAIT, - flags & ~MSG_DONTWAIT, NULL); + return prot->recvmsg(sk, msg, size, flags, NULL); #endif return unix_stream_read_generic(&state, true); } @@ -2969,7 +3192,7 @@ static int unix_shutdown(struct socket *sock, int mode) ++mode; unix_state_lock(sk); - sk->sk_shutdown |= mode; + WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | mode); other = unix_peer(sk); if (other) sock_hold(other); @@ -2989,7 +3212,7 @@ static int unix_shutdown(struct socket *sock, int mode) if (mode&SEND_SHUTDOWN) peer_mode |= RCV_SHUTDOWN; unix_state_lock(other); - other->sk_shutdown |= peer_mode; + WRITE_ONCE(other->sk_shutdown, other->sk_shutdown | peer_mode); unix_state_unlock(other); other->sk_state_change(other); if (peer_mode == SHUTDOWN_MASK) @@ -3008,12 +3231,14 @@ 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; + if (sk->sk_type == SOCK_STREAM) + return READ_ONCE(unix_sk(sk)->inq_len); + spin_lock(&sk->sk_receive_queue.lock); - if (sk->sk_type == SOCK_STREAM || - sk->sk_type == SOCK_SEQPACKET) { + if (sk->sk_type == SOCK_SEQPACKET) { skb_queue_walk(&sk->sk_receive_queue, skb) amount += unix_skb_len(skb); } else { @@ -3035,38 +3260,16 @@ EXPORT_SYMBOL_GPL(unix_outq_len); static int unix_open_file(struct sock *sk) { - struct path path; - struct file *f; - int fd; - if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; if (!smp_load_acquire(&unix_sk(sk)->addr)) return -ENOENT; - path = unix_sk(sk)->path; - if (!path.dentry) + if (!unix_sk(sk)->path.dentry) return -ENOENT; - path_get(&path); - - fd = get_unused_fd_flags(O_CLOEXEC); - if (fd < 0) - goto out; - - f = dentry_open(&path, O_PATH, current_cred()); - if (IS_ERR(f)) { - put_unused_fd(fd); - fd = PTR_ERR(f); - goto out; - } - - fd_install(fd, f); -out: - path_put(&path); - - return fd; + return FD_ADD(O_CLOEXEC, dentry_open(&unix_sk(sk)->path, O_PATH, current_cred())); } static int unix_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) @@ -3093,13 +3296,27 @@ static int unix_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) #if IS_ENABLED(CONFIG_AF_UNIX_OOB) case SIOCATMARK: { - struct sk_buff *skb; 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 == u->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; @@ -3121,17 +3338,21 @@ 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 (sk->sk_err) + if (READ_ONCE(sk->sk_err)) mask |= EPOLLERR; - if (sk->sk_shutdown == SHUTDOWN_MASK) + if (shutdown == SHUTDOWN_MASK) mask |= EPOLLHUP; - if (sk->sk_shutdown & RCV_SHUTDOWN) + if (shutdown & RCV_SHUTDOWN) mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM; /* readable? */ @@ -3139,17 +3360,21 @@ static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wa mask |= EPOLLIN | EPOLLRDNORM; if (sk_is_readable(sk)) mask |= EPOLLIN | EPOLLRDNORM; +#if IS_ENABLED(CONFIG_AF_UNIX_OOB) + if (READ_ONCE(unix_sk(sk)->oob_skb)) + mask |= EPOLLPRI; +#endif /* 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; @@ -3160,19 +3385,24 @@ 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 (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue)) + if (READ_ONCE(sk->sk_err) || + !skb_queue_empty_lockless(&sk->sk_error_queue)) mask |= EPOLLERR | (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0); - if (sk->sk_shutdown & RCV_SHUTDOWN) + if (shutdown & RCV_SHUTDOWN) mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM; - if (sk->sk_shutdown == SHUTDOWN_MASK) + if (shutdown == SHUTDOWN_MASK) mask |= EPOLLHUP; /* readable? */ @@ -3182,19 +3412,14 @@ 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); @@ -3227,12 +3452,11 @@ static struct sock *unix_from_bucket(struct seq_file *seq, loff_t *pos) { unsigned long offset = get_offset(*pos); unsigned long bucket = get_bucket(*pos); - struct sock *sk; unsigned long count = 0; + struct sock *sk; - for (sk = sk_head(&unix_socket_table[bucket]); sk; sk = sk_next(sk)) { - if (sock_net(sk) != seq_file_net(seq)) - continue; + for (sk = sk_head(&seq_file_net(seq)->unx.table.buckets[bucket]); + sk; sk = sk_next(sk)) { if (++count == offset) break; } @@ -3240,49 +3464,60 @@ static struct sock *unix_from_bucket(struct seq_file *seq, loff_t *pos) return sk; } -static struct sock *unix_next_socket(struct seq_file *seq, - struct sock *sk, - loff_t *pos) +static struct sock *unix_get_first(struct seq_file *seq, loff_t *pos) { unsigned long bucket = get_bucket(*pos); + struct net *net = seq_file_net(seq); + struct sock *sk; - while (sk > (struct sock *)SEQ_START_TOKEN) { - sk = sk_next(sk); - if (!sk) - goto next_bucket; - if (sock_net(sk) == seq_file_net(seq)) - return sk; - } + while (bucket < UNIX_HASH_SIZE) { + spin_lock(&net->unx.table.locks[bucket]); - do { - spin_lock(&unix_table_locks[bucket]); sk = unix_from_bucket(seq, pos); if (sk) return sk; -next_bucket: - spin_unlock(&unix_table_locks[bucket++]); - *pos = set_bucket_offset(bucket, 1); - } while (bucket < ARRAY_SIZE(unix_socket_table)); + spin_unlock(&net->unx.table.locks[bucket]); + + *pos = set_bucket_offset(++bucket, 1); + } return NULL; } +static struct sock *unix_get_next(struct seq_file *seq, struct sock *sk, + loff_t *pos) +{ + unsigned long bucket = get_bucket(*pos); + + sk = sk_next(sk); + if (sk) + return sk; + + + spin_unlock(&seq_file_net(seq)->unx.table.locks[bucket]); + + *pos = set_bucket_offset(++bucket, 1); + + return unix_get_first(seq, pos); +} + static void *unix_seq_start(struct seq_file *seq, loff_t *pos) { if (!*pos) return SEQ_START_TOKEN; - if (get_bucket(*pos) >= ARRAY_SIZE(unix_socket_table)) - return NULL; - - return unix_next_socket(seq, NULL, pos); + return unix_get_first(seq, pos); } static void *unix_seq_next(struct seq_file *seq, void *v, loff_t *pos) { ++*pos; - return unix_next_socket(seq, v, pos); + + if (v == SEQ_START_TOKEN) + return unix_get_first(seq, pos); + + return unix_get_next(seq, v, pos); } static void unix_seq_stop(struct seq_file *seq, void *v) @@ -3290,7 +3525,7 @@ static void unix_seq_stop(struct seq_file *seq, void *v) struct sock *sk = v; if (sk) - spin_unlock(&unix_table_locks[sk->sk_hash]); + spin_unlock(&seq_file_net(seq)->unx.table.locks[sk->sk_hash]); } static int unix_seq_show(struct seq_file *seq, void *v) @@ -3315,7 +3550,7 @@ static int unix_seq_show(struct seq_file *seq, void *v) (s->sk_state == TCP_ESTABLISHED ? SS_CONNECTING : SS_DISCONNECTING), sock_i_ino(s)); - if (u->addr) { // under unix_table_locks here + if (u->addr) { // under a hash table lock here int i, len; seq_putc(seq, ' '); @@ -3346,7 +3581,16 @@ static const struct seq_operations unix_seq_ops = { .show = unix_seq_show, }; -#if IS_BUILTIN(CONFIG_UNIX) && defined(CONFIG_BPF_SYSCALL) +#ifdef CONFIG_BPF_SYSCALL +struct bpf_unix_iter_state { + struct seq_net_private p; + unsigned int cur_sk; + unsigned int end_sk; + unsigned int max_sk; + struct sock **batch; + bool st_bucket_done; +}; + struct bpf_iter__unix { __bpf_md_ptr(struct bpf_iter_meta *, meta); __bpf_md_ptr(struct unix_sock *, unix_sk); @@ -3365,24 +3609,153 @@ static int unix_prog_seq_show(struct bpf_prog *prog, struct bpf_iter_meta *meta, return bpf_iter_run_prog(prog, &ctx); } +static int bpf_iter_unix_hold_batch(struct seq_file *seq, struct sock *start_sk) + +{ + struct bpf_unix_iter_state *iter = seq->private; + unsigned int expected = 1; + struct sock *sk; + + sock_hold(start_sk); + iter->batch[iter->end_sk++] = start_sk; + + for (sk = sk_next(start_sk); sk; sk = sk_next(sk)) { + if (iter->end_sk < iter->max_sk) { + sock_hold(sk); + iter->batch[iter->end_sk++] = sk; + } + + expected++; + } + + spin_unlock(&seq_file_net(seq)->unx.table.locks[start_sk->sk_hash]); + + return expected; +} + +static void bpf_iter_unix_put_batch(struct bpf_unix_iter_state *iter) +{ + while (iter->cur_sk < iter->end_sk) + sock_put(iter->batch[iter->cur_sk++]); +} + +static int bpf_iter_unix_realloc_batch(struct bpf_unix_iter_state *iter, + unsigned int new_batch_sz) +{ + struct sock **new_batch; + + new_batch = kvmalloc(sizeof(*new_batch) * new_batch_sz, + GFP_USER | __GFP_NOWARN); + if (!new_batch) + return -ENOMEM; + + bpf_iter_unix_put_batch(iter); + kvfree(iter->batch); + iter->batch = new_batch; + iter->max_sk = new_batch_sz; + + return 0; +} + +static struct sock *bpf_iter_unix_batch(struct seq_file *seq, + loff_t *pos) +{ + struct bpf_unix_iter_state *iter = seq->private; + unsigned int expected; + bool resized = false; + struct sock *sk; + + if (iter->st_bucket_done) + *pos = set_bucket_offset(get_bucket(*pos) + 1, 1); + +again: + /* Get a new batch */ + iter->cur_sk = 0; + iter->end_sk = 0; + + sk = unix_get_first(seq, pos); + if (!sk) + return NULL; /* Done */ + + expected = bpf_iter_unix_hold_batch(seq, sk); + + if (iter->end_sk == expected) { + iter->st_bucket_done = true; + return sk; + } + + if (!resized && !bpf_iter_unix_realloc_batch(iter, expected * 3 / 2)) { + resized = true; + goto again; + } + + return sk; +} + +static void *bpf_iter_unix_seq_start(struct seq_file *seq, loff_t *pos) +{ + if (!*pos) + return SEQ_START_TOKEN; + + /* bpf iter does not support lseek, so it always + * continue from where it was stop()-ped. + */ + return bpf_iter_unix_batch(seq, pos); +} + +static void *bpf_iter_unix_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct bpf_unix_iter_state *iter = seq->private; + struct sock *sk; + + /* Whenever seq_next() is called, the iter->cur_sk is + * done with seq_show(), so advance to the next sk in + * the batch. + */ + if (iter->cur_sk < iter->end_sk) + sock_put(iter->batch[iter->cur_sk++]); + + ++*pos; + + if (iter->cur_sk < iter->end_sk) + sk = iter->batch[iter->cur_sk]; + else + sk = bpf_iter_unix_batch(seq, pos); + + return sk; +} + static int bpf_iter_unix_seq_show(struct seq_file *seq, void *v) { struct bpf_iter_meta meta; struct bpf_prog *prog; struct sock *sk = v; uid_t uid; + bool slow; + int ret; if (v == SEQ_START_TOKEN) return 0; - uid = from_kuid_munged(seq_user_ns(seq), sock_i_uid(sk)); + slow = lock_sock_fast(sk); + + if (unlikely(sk_unhashed(sk))) { + ret = SEQ_SKIP; + goto unlock; + } + + uid = from_kuid_munged(seq_user_ns(seq), sk_uid(sk)); meta.seq = seq; prog = bpf_iter_get_info(&meta, false); - return unix_prog_seq_show(prog, &meta, v, uid); + ret = unix_prog_seq_show(prog, &meta, v, uid); +unlock: + unlock_sock_fast(sk, slow); + return ret; } static void bpf_iter_unix_seq_stop(struct seq_file *seq, void *v) { + struct bpf_unix_iter_state *iter = seq->private; struct bpf_iter_meta meta; struct bpf_prog *prog; @@ -3393,12 +3766,13 @@ static void bpf_iter_unix_seq_stop(struct seq_file *seq, void *v) (void)unix_prog_seq_show(prog, &meta, v, 0); } - unix_seq_stop(seq, v); + if (iter->cur_sk < iter->end_sk) + bpf_iter_unix_put_batch(iter); } static const struct seq_operations bpf_iter_unix_seq_ops = { - .start = unix_seq_start, - .next = unix_seq_next, + .start = bpf_iter_unix_seq_start, + .next = bpf_iter_unix_seq_next, .stop = bpf_iter_unix_seq_stop, .show = bpf_iter_unix_seq_show, }; @@ -3414,7 +3788,7 @@ static const struct net_proto_family unix_family_ops = { static int __net_init unix_net_init(struct net *net) { - int error = -ENOMEM; + int i; net->unx.sysctl_max_dgram_qlen = 10; if (unix_sysctl_register(net)) @@ -3422,18 +3796,45 @@ static int __net_init unix_net_init(struct net *net) #ifdef CONFIG_PROC_FS if (!proc_create_net("unix", 0, net->proc_net, &unix_seq_ops, - sizeof(struct seq_net_private))) { - unix_sysctl_unregister(net); - goto out; + sizeof(struct seq_net_private))) + goto err_sysctl; +#endif + + net->unx.table.locks = kvmalloc_array(UNIX_HASH_SIZE, + sizeof(spinlock_t), GFP_KERNEL); + if (!net->unx.table.locks) + goto err_proc; + + net->unx.table.buckets = kvmalloc_array(UNIX_HASH_SIZE, + sizeof(struct hlist_head), + GFP_KERNEL); + if (!net->unx.table.buckets) + goto free_locks; + + 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]); } + + return 0; + +free_locks: + kvfree(net->unx.table.locks); +err_proc: +#ifdef CONFIG_PROC_FS + remove_proc_entry("unix", net->proc_net); +err_sysctl: #endif - error = 0; + unix_sysctl_unregister(net); out: - return error; + return -ENOMEM; } static void __net_exit unix_net_exit(struct net *net) { + kvfree(net->unx.table.buckets); + kvfree(net->unx.table.locks); unix_sysctl_unregister(net); remove_proc_entry("unix", net->proc_net); } @@ -3443,17 +3844,59 @@ static struct pernet_operations unix_net_ops = { .exit = unix_net_exit, }; -#if IS_BUILTIN(CONFIG_UNIX) && defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) +#if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) DEFINE_BPF_ITER_FUNC(unix, struct bpf_iter_meta *meta, struct unix_sock *unix_sk, uid_t uid) +#define INIT_BATCH_SZ 16 + +static int bpf_iter_init_unix(void *priv_data, struct bpf_iter_aux_info *aux) +{ + struct bpf_unix_iter_state *iter = priv_data; + int err; + + err = bpf_iter_init_seq_net(priv_data, aux); + if (err) + return err; + + err = bpf_iter_unix_realloc_batch(iter, INIT_BATCH_SZ); + if (err) { + bpf_iter_fini_seq_net(priv_data); + return err; + } + + return 0; +} + +static void bpf_iter_fini_unix(void *priv_data) +{ + struct bpf_unix_iter_state *iter = priv_data; + + bpf_iter_fini_seq_net(priv_data); + kvfree(iter->batch); +} + static const struct bpf_iter_seq_info unix_seq_info = { .seq_ops = &bpf_iter_unix_seq_ops, - .init_seq_private = bpf_iter_init_seq_net, - .fini_seq_private = bpf_iter_fini_seq_net, - .seq_priv_size = sizeof(struct seq_net_private), + .init_seq_private = bpf_iter_init_unix, + .fini_seq_private = bpf_iter_fini_unix, + .seq_priv_size = sizeof(struct bpf_unix_iter_state), }; +static const struct bpf_func_proto * +bpf_iter_unix_get_func_proto(enum bpf_func_id func_id, + const struct bpf_prog *prog) +{ + switch (func_id) { + case BPF_FUNC_setsockopt: + return &bpf_sk_setsockopt_proto; + case BPF_FUNC_getsockopt: + return &bpf_sk_getsockopt_proto; + default: + return NULL; + } +} + static struct bpf_iter_reg unix_reg_info = { .target = "unix", .ctx_arg_info_size = 1, @@ -3461,6 +3904,7 @@ static struct bpf_iter_reg unix_reg_info = { { offsetof(struct bpf_iter__unix, unix_sk), PTR_TO_BTF_ID_OR_NULL }, }, + .get_func_proto = bpf_iter_unix_get_func_proto, .seq_info = &unix_seq_info, }; @@ -3478,8 +3922,10 @@ static int __init af_unix_init(void) BUILD_BUG_ON(sizeof(struct unix_skb_parms) > sizeof_field(struct sk_buff, cb)); - for (i = 0; i < 2 * UNIX_HASH_SIZE; i++) - spin_lock_init(&unix_table_locks[i]); + for (i = 0; i < UNIX_HASH_SIZE / 2; i++) { + spin_lock_init(&bsd_socket_locks[i]); + INIT_HLIST_HEAD(&bsd_socket_buckets[i]); + } rc = proto_register(&unix_dgram_proto, 1); if (rc != 0) { @@ -3490,6 +3936,7 @@ static int __init af_unix_init(void) rc = proto_register(&unix_stream_proto, 1); if (rc != 0) { pr_crit("%s: Cannot create unix_sock SLAB cache!\n", __func__); + proto_unregister(&unix_dgram_proto); goto out; } @@ -3497,7 +3944,7 @@ static int __init af_unix_init(void) register_pernet_subsys(&unix_net_ops); unix_bpf_build_proto(); -#if IS_BUILTIN(CONFIG_UNIX) && defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) +#if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) bpf_iter_register(); #endif @@ -3505,20 +3952,5 @@ out: return rc; } -static void __exit af_unix_exit(void) -{ - sock_unregister(PF_UNIX); - proto_unregister(&unix_dgram_proto); - proto_unregister(&unix_stream_proto); - unregister_pernet_subsys(&unix_net_ops); -} - -/* Earlier than device_initcall() so that other drivers invoking - request_module() don't end up in a loop when modprobe tries - to use a UNIX socket. But later than subsys_initcall() because - we depend on stuff initialised there */ +/* Later than subsys_initcall() because we depend on stuff initialised there */ fs_initcall(af_unix_init); -module_exit(af_unix_exit); - -MODULE_LICENSE("GPL"); -MODULE_ALIAS_NETPROTO(PF_UNIX); |