From: Kuniyuki Iwashima kuniyu@amazon.com
[ Upstream commit 99a7a5b9943ea2d05fb0dee38e4ae2290477ed83 ]
Originally, the code related to garbage collection was all in garbage.c.
Commit f4e65870e5ce ("net: split out functions related to registering inflight socket files") moved some functions to scm.c for io_uring and added CONFIG_UNIX_SCM just in case AF_UNIX was built as module.
However, since commit 97154bcf4d1b ("af_unix: Kconfig: make CONFIG_UNIX bool"), AF_UNIX is no longer built separately. Also, io_uring does not support SCM_RIGHTS now.
Let's move the functions back to garbage.c
Signed-off-by: Kuniyuki Iwashima kuniyu@amazon.com Acked-by: Jens Axboe axboe@kernel.dk Link: https://lore.kernel.org/r/20240129190435.57228-4-kuniyu@amazon.com Signed-off-by: Jakub Kicinski kuba@kernel.org (cherry picked from commit 99a7a5b9943ea2d05fb0dee38e4ae2290477ed83) Signed-off-by: Lee Jones lee@kernel.org --- include/net/af_unix.h | 7 +- net/Makefile | 2 +- net/unix/Kconfig | 5 -- net/unix/Makefile | 2 - net/unix/af_unix.c | 63 +++++++++++++++++- net/unix/garbage.c | 73 +++++++++++++++++++- net/unix/scm.c | 150 ------------------------------------------ net/unix/scm.h | 10 --- 8 files changed, 137 insertions(+), 175 deletions(-) delete mode 100644 net/unix/scm.c delete mode 100644 net/unix/scm.h
diff --git a/include/net/af_unix.h b/include/net/af_unix.h index 4d35204c08570..3dee0b2721aa4 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -17,19 +17,20 @@ static inline struct unix_sock *unix_get_socket(struct file *filp) } #endif
+extern spinlock_t unix_gc_lock; +extern unsigned int unix_tot_inflight; + void unix_inflight(struct user_struct *user, struct file *fp); void unix_notinflight(struct user_struct *user, struct file *fp); -void unix_destruct_scm(struct sk_buff *skb); void unix_gc(void); void wait_for_unix_gc(struct scm_fp_list *fpl); + struct sock *unix_peer_get(struct sock *sk);
#define UNIX_HASH_MOD (256 - 1) #define UNIX_HASH_SIZE (256 * 2) #define UNIX_HASH_BITS 8
-extern unsigned int unix_tot_inflight; - struct unix_address { refcount_t refcnt; int len; diff --git a/net/Makefile b/net/Makefile index 4c4dc535453df..45f3fbaae644e 100644 --- a/net/Makefile +++ b/net/Makefile @@ -17,7 +17,7 @@ obj-$(CONFIG_NETFILTER) += netfilter/ obj-$(CONFIG_INET) += ipv4/ obj-$(CONFIG_TLS) += tls/ obj-$(CONFIG_XFRM) += xfrm/ -obj-$(CONFIG_UNIX_SCM) += unix/ +obj-$(CONFIG_UNIX) += unix/ obj-y += ipv6/ obj-$(CONFIG_BPFILTER) += bpfilter/ obj-$(CONFIG_PACKET) += packet/ diff --git a/net/unix/Kconfig b/net/unix/Kconfig index 28b232f281ab1..8b5d04210d7cf 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 20491825b4d0d..4ddd125c4642c 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 bb92b1ed94aaf..78758af2c6f38 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -117,8 +117,6 @@ #include <linux/file.h> #include <linux/btf_ids.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]; @@ -1752,6 +1750,52 @@ static int unix_getname(struct socket *sock, struct sockaddr *uaddr, int peer) 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); @@ -1799,6 +1843,21 @@ 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; diff --git a/net/unix/garbage.c b/net/unix/garbage.c index c04f82489abb9..0104be9d47045 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -81,11 +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;
-/* Internal data structures and random procedures: */ + ops = READ_ONCE(sock->ops);
+ /* 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 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) diff --git a/net/unix/scm.c b/net/unix/scm.c deleted file mode 100644 index db65b0ab59479..0000000000000 --- a/net/unix/scm.c +++ /dev/null @@ -1,150 +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 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 = READ_ONCE(sock->ops); - struct sock *s = sock->sk; - - /* PF_UNIX ? */ - if (s && ops && ops->family == PF_UNIX) - return unix_sk(s); - } - - return NULL; -} -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 unix_sock *u = unix_get_socket(fp); - - 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 *fp) -{ - struct unix_sock *u = unix_get_socket(fp); - - 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); -} - -/* - * 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); diff --git a/net/unix/scm.h b/net/unix/scm.h deleted file mode 100644 index 5a255a477f160..0000000000000 --- 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