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 | 73 | ||||
| -rw-r--r-- | net/unix/diag.c | 1 | ||||
| -rw-r--r-- | net/unix/garbage.c | 200 | ||||
| -rw-r--r-- | net/unix/scm.c | 159 | ||||
| -rw-r--r-- | net/unix/scm.h | 10 |
7 files changed, 193 insertions, 257 deletions
diff --git a/net/unix/Kconfig b/net/unix/Kconfig index 28b232f281ab..8b5d04210d7c 100644 --- a/net/unix/Kconfig +++ b/net/unix/Kconfig @@ -16,11 +16,6 @@ config UNIX Say Y unless you know what you are doing. -config UNIX_SCM - bool - depends on UNIX - default y - config AF_UNIX_OOB bool depends on UNIX diff --git a/net/unix/Makefile b/net/unix/Makefile index 20491825b4d0..4ddd125c4642 100644 --- a/net/unix/Makefile +++ b/net/unix/Makefile @@ -11,5 +11,3 @@ unix-$(CONFIG_BPF_SYSCALL) += unix_bpf.o obj-$(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 30b178ebba60..4892e9428c9f 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -118,8 +118,6 @@ #include <linux/btf_ids.h> #include <linux/bpf-cgroup.h> -#include "scm.h" - 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]; @@ -993,11 +991,11 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern, sk->sk_write_space = unix_write_space; sk->sk_max_ack_backlog = net->unx.sysctl_max_dgram_qlen; sk->sk_destruct = unix_sock_destructor; - u = unix_sk(sk); + u = unix_sk(sk); + u->inflight = 0; u->path.dentry = NULL; u->path.mnt = NULL; spin_lock_init(&u->lock); - atomic_long_set(&u->inflight, 0); INIT_LIST_HEAD(&u->link); mutex_init(&u->iolock); /* single task reading lock */ mutex_init(&u->bindlock); /* single task binding lock */ @@ -1788,6 +1786,52 @@ 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) +{ + int i; + + if (too_many_unix_fds(current)) + return -ETOOMANYREFS; + + /* Need to duplicate file references for the sake of garbage + * collection. Otherwise a socket in the fps might become a + * candidate for GC while the skb is not yet queued. + */ + UNIXCB(skb).fp = scm_fp_dup(scm->fp); + if (!UNIXCB(skb).fp) + return -ENOMEM; + + for (i = scm->fp->count - 1; i >= 0; i--) + unix_inflight(scm->fp->user, scm->fp->fp[i]); + + return 0; +} + +static void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb) +{ + int i; + + scm->fp = UNIXCB(skb).fp; + UNIXCB(skb).fp = NULL; + + for (i = scm->fp->count - 1; i >= 0; i--) + unix_notinflight(scm->fp->user, scm->fp->fp[i]); +} + static void unix_peek_fds(struct scm_cookie *scm, struct sk_buff *skb) { scm->fp = scm_fp_dup(UNIXCB(skb).fp); @@ -1835,6 +1879,21 @@ static void unix_peek_fds(struct scm_cookie *scm, struct sk_buff *skb) 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; @@ -1921,11 +1980,12 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg, long timeo; int err; - wait_for_unix_gc(); err = scm_send(sock, msg, &scm, false); if (err < 0) return err; + wait_for_unix_gc(scm.fp); + err = -EOPNOTSUPP; if (msg->msg_flags&MSG_OOB) goto out; @@ -2197,11 +2257,12 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, bool fds_sent = false; int data_len; - wait_for_unix_gc(); err = scm_send(sock, msg, &scm, false); if (err < 0) return err; + wait_for_unix_gc(scm.fp); + err = -EOPNOTSUPP; if (msg->msg_flags & MSG_OOB) { #if IS_ENABLED(CONFIG_AF_UNIX_OOB) diff --git a/net/unix/diag.c b/net/unix/diag.c index be19827eca36..ae39538c5042 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -322,6 +322,7 @@ static int unix_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) } static const struct sock_diag_handler unix_diag_handler = { + .owner = THIS_MODULE, .family = AF_UNIX, .dump = unix_diag_handler_dump, }; diff --git a/net/unix/garbage.c b/net/unix/garbage.c index 2ff7ddbaa782..51acf795f096 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -81,12 +81,80 @@ #include <net/scm.h> #include <net/tcp_states.h> -#include "scm.h" +struct unix_sock *unix_get_socket(struct file *filp) +{ + struct inode *inode = file_inode(filp); + + /* Socket ? */ + if (S_ISSOCK(inode->i_mode) && !(filp->f_mode & FMODE_PATH)) { + struct socket *sock = SOCKET_I(inode); + const struct proto_ops *ops; + struct sock *sk = sock->sk; + + ops = READ_ONCE(sock->ops); -/* Internal data structures and random procedures: */ + /* PF_UNIX ? */ + if (sk && ops && ops->family == PF_UNIX) + return unix_sk(sk); + } + + return NULL; +} +DEFINE_SPINLOCK(unix_gc_lock); +unsigned int unix_tot_inflight; static LIST_HEAD(gc_candidates); -static DECLARE_WAIT_QUEUE_HEAD(unix_gc_wait); +static LIST_HEAD(gc_inflight_list); + +/* 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 *filp) +{ + struct unix_sock *u = unix_get_socket(filp); + + spin_lock(&unix_gc_lock); + + if (u) { + if (!u->inflight) { + WARN_ON_ONCE(!list_empty(&u->link)); + list_add_tail(&u->link, &gc_inflight_list); + } else { + WARN_ON_ONCE(list_empty(&u->link)); + } + u->inflight++; + + /* Paired with READ_ONCE() in wait_for_unix_gc() */ + WRITE_ONCE(unix_tot_inflight, unix_tot_inflight + 1); + } + + WRITE_ONCE(user->unix_inflight, user->unix_inflight + 1); + + spin_unlock(&unix_gc_lock); +} + +void unix_notinflight(struct user_struct *user, struct file *filp) +{ + struct unix_sock *u = unix_get_socket(filp); + + spin_lock(&unix_gc_lock); + + if (u) { + WARN_ON_ONCE(!u->inflight); + WARN_ON_ONCE(list_empty(&u->link)); + + u->inflight--; + if (!u->inflight) + list_del_init(&u->link); + + /* Paired with READ_ONCE() in wait_for_unix_gc() */ + WRITE_ONCE(unix_tot_inflight, unix_tot_inflight - 1); + } + + WRITE_ONCE(user->unix_inflight, user->unix_inflight - 1); + + spin_unlock(&unix_gc_lock); +} static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *), struct sk_buff_head *hitlist) @@ -105,20 +173,15 @@ static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *), while (nfd--) { /* Get the socket the fd matches if it indeed does so */ - struct sock *sk = unix_get_socket(*fp++); - - if (sk) { - struct unix_sock *u = unix_sk(sk); + struct unix_sock *u = unix_get_socket(*fp++); - /* Ignore non-candidates, they could - * have been added to the queues after - * starting the garbage collection - */ - if (test_bit(UNIX_GC_CANDIDATE, &u->gc_flags)) { - hit = true; + /* Ignore non-candidates, they could have been added + * to the queues after starting the garbage collection + */ + if (u && test_bit(UNIX_GC_CANDIDATE, &u->gc_flags)) { + hit = true; - func(u); - } + func(u); } } if (hit && hitlist != NULL) { @@ -151,7 +214,7 @@ static void scan_children(struct sock *x, void (*func)(struct unix_sock *), /* An embryo cannot be in-flight, so it's safe * to use the list link. */ - BUG_ON(!list_empty(&u->link)); + WARN_ON_ONCE(!list_empty(&u->link)); list_add_tail(&u->link, &embryos); } spin_unlock(&x->sk_receive_queue.lock); @@ -166,17 +229,18 @@ static void scan_children(struct sock *x, void (*func)(struct unix_sock *), static void dec_inflight(struct unix_sock *usk) { - atomic_long_dec(&usk->inflight); + usk->inflight--; } static void inc_inflight(struct unix_sock *usk) { - atomic_long_inc(&usk->inflight); + usk->inflight++; } static void inc_inflight_move_tail(struct unix_sock *u) { - atomic_long_inc(&u->inflight); + u->inflight++; + /* If this still might be part of a cycle, move it to the end * of the list, so that it's checked even if it was already * passed over @@ -186,40 +250,16 @@ static void inc_inflight_move_tail(struct unix_sock *u) } static bool gc_in_progress; -#define UNIX_INFLIGHT_TRIGGER_GC 16000 - -void wait_for_unix_gc(void) -{ - /* If number of inflight sockets is insane, - * force a garbage collect right now. - * Paired with the WRITE_ONCE() in unix_inflight(), - * unix_notinflight() and gc_in_progress(). - */ - if (READ_ONCE(unix_tot_inflight) > UNIX_INFLIGHT_TRIGGER_GC && - !READ_ONCE(gc_in_progress)) - unix_gc(); - wait_event(unix_gc_wait, gc_in_progress == false); -} -/* The external entry point: unix_gc() */ -void unix_gc(void) +static void __unix_gc(struct work_struct *work) { - struct sk_buff *next_skb, *skb; - struct unix_sock *u; - struct unix_sock *next; struct sk_buff_head hitlist; - struct list_head cursor; + struct unix_sock *u, *next; LIST_HEAD(not_cycle_list); + struct list_head cursor; spin_lock(&unix_gc_lock); - /* Avoid a recursive GC. */ - if (gc_in_progress) - goto out; - - /* Paired with READ_ONCE() in wait_for_unix_gc(). */ - WRITE_ONCE(gc_in_progress, true); - /* First, select candidates for garbage collection. Only * in-flight sockets are considered, and from those only ones * which don't have any external reference. @@ -237,14 +277,12 @@ void unix_gc(void) */ list_for_each_entry_safe(u, next, &gc_inflight_list, link) { long total_refs; - long inflight_refs; total_refs = file_count(u->sk.sk_socket->file); - inflight_refs = atomic_long_read(&u->inflight); - BUG_ON(inflight_refs < 1); - BUG_ON(total_refs < inflight_refs); - if (total_refs == inflight_refs) { + WARN_ON_ONCE(!u->inflight); + WARN_ON_ONCE(total_refs < u->inflight); + if (total_refs == u->inflight) { list_move_tail(&u->link, &gc_candidates); __set_bit(UNIX_GC_CANDIDATE, &u->gc_flags); __set_bit(UNIX_GC_MAYBE_CYCLE, &u->gc_flags); @@ -271,7 +309,7 @@ void unix_gc(void) /* Move cursor to after the current position. */ list_move(&cursor, &u->link); - if (atomic_long_read(&u->inflight) > 0) { + if (u->inflight) { list_move_tail(&u->link, ¬_cycle_list); __clear_bit(UNIX_GC_MAYBE_CYCLE, &u->gc_flags); scan_children(&u->sk, inc_inflight_move_tail, NULL); @@ -298,19 +336,6 @@ void unix_gc(void) spin_unlock(&unix_gc_lock); - /* We need io_uring to clean its registered files, ignore all io_uring - * originated skbs. It's fine as io_uring doesn't keep references to - * other io_uring instances and so killing all other files in the cycle - * will put all io_uring references forcing it to go through normal - * release.path eventually putting registered files. - */ - skb_queue_walk_safe(&hitlist, skb, next_skb) { - if (skb->destructor == io_uring_destruct_scm) { - __skb_unlink(skb, &hitlist); - skb_queue_tail(&skb->sk->sk_receive_queue, skb); - } - } - /* Here we are. Hitlist is filled. Die. */ __skb_queue_purge(&hitlist); @@ -328,20 +353,45 @@ void unix_gc(void) spin_lock(&unix_gc_lock); - /* There could be io_uring registered files, just push them back to - * the inflight list - */ - list_for_each_entry_safe(u, next, &gc_candidates, link) - list_move_tail(&u->link, &gc_inflight_list); - /* All candidates should have been detached by now. */ - BUG_ON(!list_empty(&gc_candidates)); + WARN_ON_ONCE(!list_empty(&gc_candidates)); /* Paired with READ_ONCE() in wait_for_unix_gc(). */ WRITE_ONCE(gc_in_progress, false); - wake_up(&unix_gc_wait); - - out: spin_unlock(&unix_gc_lock); } + +static DECLARE_WORK(unix_gc_work, __unix_gc); + +void unix_gc(void) +{ + WRITE_ONCE(gc_in_progress, true); + queue_work(system_unbound_wq, &unix_gc_work); +} + +#define UNIX_INFLIGHT_TRIGGER_GC 16000 +#define UNIX_INFLIGHT_SANE_USER (SCM_MAX_FD * 8) + +void wait_for_unix_gc(struct scm_fp_list *fpl) +{ + /* If number of inflight sockets is insane, + * force a garbage collect right now. + * + * Paired with the WRITE_ONCE() in unix_inflight(), + * unix_notinflight(), and __unix_gc(). + */ + if (READ_ONCE(unix_tot_inflight) > UNIX_INFLIGHT_TRIGGER_GC && + !READ_ONCE(gc_in_progress)) + unix_gc(); + + /* Penalise users who want to send AF_UNIX sockets + * but whose sockets have not been received yet. + */ + if (!fpl || !fpl->count_unix || + READ_ONCE(fpl->user->unix_inflight) < UNIX_INFLIGHT_SANE_USER) + return; + + if (READ_ONCE(gc_in_progress)) + flush_work(&unix_gc_work); +} diff --git a/net/unix/scm.c b/net/unix/scm.c deleted file mode 100644 index 822ce0d0d791..000000000000 --- a/net/unix/scm.c +++ /dev/null @@ -1,159 +0,0 @@ -// 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 <linux/io_uring.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); - const struct proto_ops *ops = READ_ONCE(sock->ops); - struct sock *s = sock->sk; - - /* PF_UNIX ? */ - if (s && ops && 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)); - } - /* Paired with READ_ONCE() in wait_for_unix_gc() */ - WRITE_ONCE(unix_tot_inflight, unix_tot_inflight + 1); - } - WRITE_ONCE(user->unix_inflight, user->unix_inflight + 1); - 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); - /* Paired with READ_ONCE() in wait_for_unix_gc() */ - WRITE_ONCE(unix_tot_inflight, unix_tot_inflight - 1); - } - WRITE_ONCE(user->unix_inflight, user->unix_inflight - 1); - 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(READ_ONCE(user->unix_inflight) > task_rlimit(p, RLIMIT_NOFILE))) - return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN); - return false; -} - -int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) -{ - int i; - - if (too_many_unix_fds(current)) - return -ETOOMANYREFS; - - /* - * Need to duplicate file references for the sake of garbage - * collection. Otherwise a socket in the fps might become a - * candidate for GC while the skb is not yet queued. - */ - UNIXCB(skb).fp = scm_fp_dup(scm->fp); - if (!UNIXCB(skb).fp) - return -ENOMEM; - - for (i = scm->fp->count - 1; i >= 0; i--) - unix_inflight(scm->fp->user, scm->fp->fp[i]); - return 0; -} -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); - -void io_uring_destruct_scm(struct sk_buff *skb) -{ - unix_destruct_scm(skb); -} -EXPORT_SYMBOL(io_uring_destruct_scm); diff --git a/net/unix/scm.h b/net/unix/scm.h deleted file mode 100644 index 5a255a477f16..000000000000 --- a/net/unix/scm.h +++ /dev/null @@ -1,10 +0,0 @@ -#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 |