diff options
Diffstat (limited to 'net/unix')
| -rw-r--r-- | net/unix/Kconfig | 5 | ||||
| -rw-r--r-- | net/unix/Makefile | 2 | ||||
| -rw-r--r-- | net/unix/af_unix.c | 151 | ||||
| -rw-r--r-- | net/unix/garbage.c | 68 | ||||
| -rw-r--r-- | net/unix/scm.c | 161 | ||||
| -rw-r--r-- | net/unix/scm.h | 10 |
6 files changed, 254 insertions, 143 deletions
diff --git a/net/unix/Kconfig b/net/unix/Kconfig index 8b31ab85d050..3b9e450656a4 100644 --- a/net/unix/Kconfig +++ b/net/unix/Kconfig @@ -19,6 +19,11 @@ config UNIX Say Y unless you know what you are doing. +config UNIX_SCM + bool + depends on UNIX + default y + config UNIX_DIAG tristate "UNIX: socket monitoring interface" depends on UNIX diff --git a/net/unix/Makefile b/net/unix/Makefile index b663c607b1c6..dc686c6757fb 100644 --- a/net/unix/Makefile +++ b/net/unix/Makefile @@ -9,3 +9,5 @@ unix-$(CONFIG_SYSCTL) += sysctl_net_unix.o obj-$(CONFIG_UNIX_DIAG) += unix_diag.o unix_diag-y := diag.o + +obj-$(CONFIG_UNIX_SCM) += scm.o diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 33948cc03ba6..242d170991b4 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -118,6 +118,8 @@ #include <linux/security.h> #include <linux/freezer.h> +#include "scm.h" + struct hlist_head unix_socket_table[2 * UNIX_HASH_SIZE]; EXPORT_SYMBOL_GPL(unix_socket_table); DEFINE_SPINLOCK(unix_table_lock); @@ -592,20 +594,42 @@ static void unix_release_sock(struct sock *sk, int embrion) static void init_peercred(struct sock *sk) { - put_pid(sk->sk_peer_pid); - if (sk->sk_peer_cred) - put_cred(sk->sk_peer_cred); + const struct cred *old_cred; + struct pid *old_pid; + + 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(); + spin_unlock(&sk->sk_peer_lock); + + put_pid(old_pid); + put_cred(old_cred); } static void copy_peercred(struct sock *sk, struct sock *peersk) { - put_pid(sk->sk_peer_pid); - if (sk->sk_peer_cred) - put_cred(sk->sk_peer_cred); + const struct cred *old_cred; + struct pid *old_pid; + + 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); 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 int unix_listen(struct socket *sock, int backlog) @@ -1504,78 +1528,51 @@ out: return err; } -static void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb) -{ - int i; - - scm->fp = UNIXCB(skb).fp; - UNIXCB(skb).fp = NULL; - - for (i = scm->fp->count-1; i >= 0; i--) - unix_notinflight(scm->fp->user, scm->fp->fp[i]); -} - -static void unix_destruct_scm(struct sk_buff *skb) +static void unix_peek_fds(struct scm_cookie *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); -} - -/* - * The "user->unix_inflight" variable is protected by the garbage - * collection lock, and we just read it locklessly here. If you go - * over the limit, there might be a tiny race in actually noticing - * it across threads. Tough. - */ -static inline bool too_many_unix_fds(struct task_struct *p) -{ - struct user_struct *user = current_user(); - - if (unlikely(user->unix_inflight > task_rlimit(p, RLIMIT_NOFILE))) - return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN); - return false; -} - -#define MAX_RECURSION_LEVEL 4 - -static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) -{ - int i; - unsigned char max_level = 0; - - if (too_many_unix_fds(current)) - return -ETOOMANYREFS; - - for (i = scm->fp->count - 1; i >= 0; i--) { - struct sock *sk = unix_get_socket(scm->fp->fp[i]); - - if (sk) - max_level = max(max_level, - unix_sk(sk)->recursion_level); - } - if (unlikely(max_level > MAX_RECURSION_LEVEL)) - return -ETOOMANYREFS; + scm->fp = scm_fp_dup(UNIXCB(skb).fp); /* - * Need to duplicate file references for the sake of garbage - * collection. Otherwise a socket in the fps might become a - * candidate for GC while the skb is not yet queued. + * 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. */ - UNIXCB(skb).fp = scm_fp_dup(scm->fp); - if (!UNIXCB(skb).fp) - return -ENOMEM; - - for (i = scm->fp->count - 1; i >= 0; i--) - unix_inflight(scm->fp->user, scm->fp->fp[i]); - return max_level; + spin_lock(&unix_gc_lock); + spin_unlock(&unix_gc_lock); } static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool send_fds) @@ -2203,7 +2200,7 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg, sk_peek_offset_fwd(sk, size); if (UNIXCB(skb).fp) - scm.fp = scm_fp_dup(UNIXCB(skb).fp); + unix_peek_fds(&scm, skb); } err = (flags & MSG_TRUNC) ? skb->len - skip : size; @@ -2448,7 +2445,7 @@ unlock: /* It is questionable, see note in unix_dgram_recvmsg. */ if (UNIXCB(skb).fp) - scm.fp = scm_fp_dup(UNIXCB(skb).fp); + unix_peek_fds(&scm, skb); sk_peek_offset_fwd(sk, chunk); @@ -2725,7 +2722,7 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock, other = unix_peer(sk); if (other && unix_peer(other) != sk && - unix_recvq_full(other) && + unix_recvq_full_lockless(other) && unix_dgram_peer_wake_me(sk, other)) writable = 0; diff --git a/net/unix/garbage.c b/net/unix/garbage.c index c36757e72844..8bbe1b8e4ff7 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -86,77 +86,13 @@ #include <net/scm.h> #include <net/tcp_states.h> +#include "scm.h" + /* Internal data structures and random procedures: */ -static LIST_HEAD(gc_inflight_list); static LIST_HEAD(gc_candidates); -static DEFINE_SPINLOCK(unix_gc_lock); static DECLARE_WAIT_QUEUE_HEAD(unix_gc_wait); -unsigned int unix_tot_inflight; - -struct sock *unix_get_socket(struct file *filp) -{ - struct sock *u_sock = NULL; - struct inode *inode = file_inode(filp); - - /* Socket ? */ - if (S_ISSOCK(inode->i_mode) && !(filp->f_mode & FMODE_PATH)) { - struct socket *sock = SOCKET_I(inode); - struct sock *s = sock->sk; - - /* PF_UNIX ? */ - if (s && sock->ops && sock->ops->family == PF_UNIX) - u_sock = s; - } - return u_sock; -} - -/* Keep the number of times in flight count for the file - * descriptor if it is for an AF_UNIX socket. - */ - -void unix_inflight(struct user_struct *user, struct file *fp) -{ - struct sock *s = unix_get_socket(fp); - - spin_lock(&unix_gc_lock); - - if (s) { - struct unix_sock *u = unix_sk(s); - - if (atomic_long_inc_return(&u->inflight) == 1) { - BUG_ON(!list_empty(&u->link)); - list_add_tail(&u->link, &gc_inflight_list); - } else { - BUG_ON(list_empty(&u->link)); - } - unix_tot_inflight++; - } - user->unix_inflight++; - spin_unlock(&unix_gc_lock); -} - -void unix_notinflight(struct user_struct *user, struct file *fp) -{ - struct sock *s = unix_get_socket(fp); - - spin_lock(&unix_gc_lock); - - if (s) { - struct unix_sock *u = unix_sk(s); - - BUG_ON(!atomic_long_read(&u->inflight)); - BUG_ON(list_empty(&u->link)); - - if (atomic_long_dec_and_test(&u->inflight)) - list_del_init(&u->link); - unix_tot_inflight--; - } - user->unix_inflight--; - spin_unlock(&unix_gc_lock); -} - static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *), struct sk_buff_head *hitlist) { diff --git a/net/unix/scm.c b/net/unix/scm.c new file mode 100644 index 000000000000..df8f636ab1d8 --- /dev/null +++ b/net/unix/scm.c @@ -0,0 +1,161 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/socket.h> +#include <linux/net.h> +#include <linux/fs.h> +#include <net/af_unix.h> +#include <net/scm.h> +#include <linux/init.h> + +#include "scm.h" + +unsigned int unix_tot_inflight; +EXPORT_SYMBOL(unix_tot_inflight); + +LIST_HEAD(gc_inflight_list); +EXPORT_SYMBOL(gc_inflight_list); + +DEFINE_SPINLOCK(unix_gc_lock); +EXPORT_SYMBOL(unix_gc_lock); + +struct sock *unix_get_socket(struct file *filp) +{ + struct sock *u_sock = NULL; + struct inode *inode = file_inode(filp); + + /* Socket ? */ + if (S_ISSOCK(inode->i_mode) && !(filp->f_mode & FMODE_PATH)) { + struct socket *sock = SOCKET_I(inode); + struct sock *s = sock->sk; + + /* PF_UNIX ? */ + if (s && sock->ops && sock->ops->family == PF_UNIX) + u_sock = s; + } + return u_sock; +} +EXPORT_SYMBOL(unix_get_socket); + +/* Keep the number of times in flight count for the file + * descriptor if it is for an AF_UNIX socket. + */ +void unix_inflight(struct user_struct *user, struct file *fp) +{ + struct sock *s = unix_get_socket(fp); + + spin_lock(&unix_gc_lock); + + if (s) { + struct unix_sock *u = unix_sk(s); + + if (atomic_long_inc_return(&u->inflight) == 1) { + BUG_ON(!list_empty(&u->link)); + list_add_tail(&u->link, &gc_inflight_list); + } else { + BUG_ON(list_empty(&u->link)); + } + unix_tot_inflight++; + } + user->unix_inflight++; + spin_unlock(&unix_gc_lock); +} + +void unix_notinflight(struct user_struct *user, struct file *fp) +{ + struct sock *s = unix_get_socket(fp); + + spin_lock(&unix_gc_lock); + + if (s) { + struct unix_sock *u = unix_sk(s); + + BUG_ON(!atomic_long_read(&u->inflight)); + BUG_ON(list_empty(&u->link)); + + if (atomic_long_dec_and_test(&u->inflight)) + list_del_init(&u->link); + unix_tot_inflight--; + } + user->unix_inflight--; + spin_unlock(&unix_gc_lock); +} + +/* + * The "user->unix_inflight" variable is protected by the garbage + * collection lock, and we just read it locklessly here. If you go + * over the limit, there might be a tiny race in actually noticing + * it across threads. Tough. + */ +static inline bool too_many_unix_fds(struct task_struct *p) +{ + struct user_struct *user = current_user(); + + if (unlikely(user->unix_inflight > task_rlimit(p, RLIMIT_NOFILE))) + return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN); + return false; +} + +#define MAX_RECURSION_LEVEL 4 + +int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) +{ + int i; + unsigned char max_level = 0; + + if (too_many_unix_fds(current)) + return -ETOOMANYREFS; + + for (i = scm->fp->count - 1; i >= 0; i--) { + struct sock *sk = unix_get_socket(scm->fp->fp[i]); + + if (sk) + max_level = max(max_level, + unix_sk(sk)->recursion_level); + } + if (unlikely(max_level > MAX_RECURSION_LEVEL)) + return -ETOOMANYREFS; + + /* + * Need to duplicate file references for the sake of garbage + * collection. Otherwise a socket in the fps might become a + * candidate for GC while the skb is not yet queued. + */ + UNIXCB(skb).fp = scm_fp_dup(scm->fp); + if (!UNIXCB(skb).fp) + return -ENOMEM; + + for (i = scm->fp->count - 1; i >= 0; i--) + unix_inflight(scm->fp->user, scm->fp->fp[i]); + return max_level; +} +EXPORT_SYMBOL(unix_attach_fds); + +void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb) +{ + int i; + + scm->fp = UNIXCB(skb).fp; + UNIXCB(skb).fp = NULL; + + for (i = scm->fp->count-1; i >= 0; i--) + unix_notinflight(scm->fp->user, scm->fp->fp[i]); +} +EXPORT_SYMBOL(unix_detach_fds); + +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); +} +EXPORT_SYMBOL(unix_destruct_scm); diff --git a/net/unix/scm.h b/net/unix/scm.h new file mode 100644 index 000000000000..5a255a477f16 --- /dev/null +++ b/net/unix/scm.h @@ -0,0 +1,10 @@ +#ifndef NET_UNIX_SCM_H +#define NET_UNIX_SCM_H + +extern struct list_head gc_inflight_list; +extern spinlock_t unix_gc_lock; + +int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb); +void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb); + +#endif |