Merge branch 'af_unix-remove-io_uring-dead-code-in-gc'

Kuniyuki Iwashima says:

====================
af_unix: Remove io_uring dead code in GC.

I will post another series that rewrites the garbage collector for
AF_UNIX socket.

This is a prep series to clean up changes to GC made by io_uring but
now not necessary.
====================

Link: https://lore.kernel.org/r/20240129190435.57228-1-kuniyu@amazon.comSigned-off-by: Jakub Kicinski <kuba@kernel.org>

include/net/af_unix.h

@@ -17,20 +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 io_uring_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;

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-$(CONFIG_PACKET)		+= packet/
 obj-$(CONFIG_NET_KEY)		+= key/

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

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

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];
@@ -1790,6 +1788,52 @@ 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);
@@ -1837,6 +1881,21 @@ 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;

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;
+
+		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 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)
@@ -145,7 +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);
@@ -184,12 +253,10 @@ static bool gc_in_progress;
 
 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);
 
@@ -213,8 +280,8 @@ static void __unix_gc(struct work_struct *work)
 
 		total_refs = file_count(u->sk.sk_socket->file);
 
-		BUG_ON(!u->inflight);
-		BUG_ON(total_refs < u->inflight);
+		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);
@@ -269,32 +336,13 @@ static void __unix_gc(struct work_struct *work)
 
 	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);
 
 	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);

net/unix/scm.c

-// 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) {
-			BUG_ON(!list_empty(&u->link));
-			list_add_tail(&u->link, &gc_inflight_list);
-		} else {
-			BUG_ON(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) {
-		BUG_ON(!u->inflight);
-		BUG_ON(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);
-
-void io_uring_destruct_scm(struct sk_buff *skb)
-{
-	unix_destruct_scm(skb);
-}
-EXPORT_SYMBOL(io_uring_destruct_scm);

net/unix/scm.h

-#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