Fixed MTP to work with TWRP

net/unix/Kconfig

@@ -0,0 +1,28 @@
+#
+# Unix Domain Sockets
+#
+
+config UNIX
+	tristate "Unix domain sockets"
+	---help---
+	  If you say Y here, you will include support for Unix domain sockets;
+	  sockets are the standard Unix mechanism for establishing and
+	  accessing network connections.  Many commonly used programs such as
+	  the X Window system and syslog use these sockets even if your
+	  machine is not connected to any network.  Unless you are working on
+	  an embedded system or something similar, you therefore definitely
+	  want to say Y here.
+
+	  To compile this driver as a module, choose M here: the module will be
+	  called unix.  Note that several important services won't work
+	  correctly if you say M here and then neglect to load the module.
+
+	  Say Y unless you know what you are doing.
+
+config UNIX_DIAG
+	tristate "UNIX: socket monitoring interface"
+	depends on UNIX
+	default n
+	---help---
+	  Support for UNIX socket monitoring interface used by the ss tool.
+	  If unsure, say Y.

net/unix/Makefile

@@ -0,0 +1,11 @@
+#
+# Makefile for the Linux unix domain socket layer.
+#
+
+obj-$(CONFIG_UNIX)	+= unix.o
+
+unix-y			:= af_unix.o garbage.o
+unix-$(CONFIG_SYSCTL)	+= sysctl_net_unix.o
+
+obj-$(CONFIG_UNIX_DIAG)	+= unix_diag.o
+unix_diag-y		:= diag.o

net/unix/diag.c

@@ -0,0 +1,327 @@
+#include <linux/types.h>
+#include <linux/spinlock.h>
+#include <linux/sock_diag.h>
+#include <linux/unix_diag.h>
+#include <linux/skbuff.h>
+#include <linux/module.h>
+#include <net/netlink.h>
+#include <net/af_unix.h>
+#include <net/tcp_states.h>
+
+static int sk_diag_dump_name(struct sock *sk, struct sk_buff *nlskb)
+{
+	struct unix_address *addr = unix_sk(sk)->addr;
+
+	if (!addr)
+		return 0;
+
+	return nla_put(nlskb, UNIX_DIAG_NAME, addr->len - sizeof(short),
+		       addr->name->sun_path);
+}
+
+static int sk_diag_dump_vfs(struct sock *sk, struct sk_buff *nlskb)
+{
+	struct dentry *dentry = unix_sk(sk)->path.dentry;
+
+	if (dentry) {
+		struct unix_diag_vfs uv = {
+			.udiag_vfs_ino = dentry->d_inode->i_ino,
+			.udiag_vfs_dev = dentry->d_sb->s_dev,
+		};
+
+		return nla_put(nlskb, UNIX_DIAG_VFS, sizeof(uv), &uv);
+	}
+
+	return 0;
+}
+
+static int sk_diag_dump_peer(struct sock *sk, struct sk_buff *nlskb)
+{
+	struct sock *peer;
+	int ino;
+
+	peer = unix_peer_get(sk);
+	if (peer) {
+		unix_state_lock(peer);
+		ino = sock_i_ino(peer);
+		unix_state_unlock(peer);
+		sock_put(peer);
+
+		return nla_put_u32(nlskb, UNIX_DIAG_PEER, ino);
+	}
+
+	return 0;
+}
+
+static int sk_diag_dump_icons(struct sock *sk, struct sk_buff *nlskb)
+{
+	struct sk_buff *skb;
+	struct nlattr *attr;
+	u32 *buf;
+	int i;
+
+	if (sk->sk_state == TCP_LISTEN) {
+		spin_lock(&sk->sk_receive_queue.lock);
+
+		attr = nla_reserve(nlskb, UNIX_DIAG_ICONS,
+				   sk->sk_receive_queue.qlen * sizeof(u32));
+		if (!attr)
+			goto errout;
+
+		buf = nla_data(attr);
+		i = 0;
+		skb_queue_walk(&sk->sk_receive_queue, skb) {
+			struct sock *req, *peer;
+
+			req = skb->sk;
+			/*
+			 * The state lock is outer for the same sk's
+			 * queue lock. With the other's queue locked it's
+			 * OK to lock the state.
+			 */
+			unix_state_lock_nested(req);
+			peer = unix_sk(req)->peer;
+			buf[i++] = (peer ? sock_i_ino(peer) : 0);
+			unix_state_unlock(req);
+		}
+		spin_unlock(&sk->sk_receive_queue.lock);
+	}
+
+	return 0;
+
+errout:
+	spin_unlock(&sk->sk_receive_queue.lock);
+	return -EMSGSIZE;
+}
+
+static int sk_diag_show_rqlen(struct sock *sk, struct sk_buff *nlskb)
+{
+	struct unix_diag_rqlen rql;
+
+	if (sk->sk_state == TCP_LISTEN) {
+		rql.udiag_rqueue = sk->sk_receive_queue.qlen;
+		rql.udiag_wqueue = sk->sk_max_ack_backlog;
+	} else {
+		rql.udiag_rqueue = (u32) unix_inq_len(sk);
+		rql.udiag_wqueue = (u32) unix_outq_len(sk);
+	}
+
+	return nla_put(nlskb, UNIX_DIAG_RQLEN, sizeof(rql), &rql);
+}
+
+static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_req *req,
+		u32 portid, u32 seq, u32 flags, int sk_ino)
+{
+	struct nlmsghdr *nlh;
+	struct unix_diag_msg *rep;
+
+	nlh = nlmsg_put(skb, portid, seq, SOCK_DIAG_BY_FAMILY, sizeof(*rep),
+			flags);
+	if (!nlh)
+		return -EMSGSIZE;
+
+	rep = nlmsg_data(nlh);
+	rep->udiag_family = AF_UNIX;
+	rep->udiag_type = sk->sk_type;
+	rep->udiag_state = sk->sk_state;
+	rep->pad = 0;
+	rep->udiag_ino = sk_ino;
+	sock_diag_save_cookie(sk, rep->udiag_cookie);
+
+	if ((req->udiag_show & UDIAG_SHOW_NAME) &&
+	    sk_diag_dump_name(sk, skb))
+		goto out_nlmsg_trim;
+
+	if ((req->udiag_show & UDIAG_SHOW_VFS) &&
+	    sk_diag_dump_vfs(sk, skb))
+		goto out_nlmsg_trim;
+
+	if ((req->udiag_show & UDIAG_SHOW_PEER) &&
+	    sk_diag_dump_peer(sk, skb))
+		goto out_nlmsg_trim;
+
+	if ((req->udiag_show & UDIAG_SHOW_ICONS) &&
+	    sk_diag_dump_icons(sk, skb))
+		goto out_nlmsg_trim;
+
+	if ((req->udiag_show & UDIAG_SHOW_RQLEN) &&
+	    sk_diag_show_rqlen(sk, skb))
+		goto out_nlmsg_trim;
+
+	if ((req->udiag_show & UDIAG_SHOW_MEMINFO) &&
+	    sock_diag_put_meminfo(sk, skb, UNIX_DIAG_MEMINFO))
+		goto out_nlmsg_trim;
+
+	if (nla_put_u8(skb, UNIX_DIAG_SHUTDOWN, sk->sk_shutdown))
+		goto out_nlmsg_trim;
+
+	return nlmsg_end(skb, nlh);
+
+out_nlmsg_trim:
+	nlmsg_cancel(skb, nlh);
+	return -EMSGSIZE;
+}
+
+static int sk_diag_dump(struct sock *sk, struct sk_buff *skb, struct unix_diag_req *req,
+		u32 portid, u32 seq, u32 flags)
+{
+	int sk_ino;
+
+	unix_state_lock(sk);
+	sk_ino = sock_i_ino(sk);
+	unix_state_unlock(sk);
+
+	if (!sk_ino)
+		return 0;
+
+	return sk_diag_fill(sk, skb, req, portid, seq, flags, sk_ino);
+}
+
+static int unix_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct unix_diag_req *req;
+	int num, s_num, slot, s_slot;
+	struct net *net = sock_net(skb->sk);
+
+	req = nlmsg_data(cb->nlh);
+
+	s_slot = cb->args[0];
+	num = s_num = cb->args[1];
+
+	spin_lock(&unix_table_lock);
+	for (slot = s_slot;
+	     slot < ARRAY_SIZE(unix_socket_table);
+	     s_num = 0, slot++) {
+		struct sock *sk;
+
+		num = 0;
+		sk_for_each(sk, &unix_socket_table[slot]) {
+			if (!net_eq(sock_net(sk), net))
+				continue;
+			if (num < s_num)
+				goto next;
+			if (!(req->udiag_states & (1 << sk->sk_state)))
+				goto next;
+			if (sk_diag_dump(sk, skb, req,
+					 NETLINK_CB(cb->skb).portid,
+					 cb->nlh->nlmsg_seq,
+					 NLM_F_MULTI) < 0)
+				goto done;
+next:
+			num++;
+		}
+	}
+done:
+	spin_unlock(&unix_table_lock);
+	cb->args[0] = slot;
+	cb->args[1] = num;
+
+	return skb->len;
+}
+
+static struct sock *unix_lookup_by_ino(int ino)
+{
+	int i;
+	struct sock *sk;
+
+	spin_lock(&unix_table_lock);
+	for (i = 0; i < ARRAY_SIZE(unix_socket_table); i++) {
+		sk_for_each(sk, &unix_socket_table[i])
+			if (ino == sock_i_ino(sk)) {
+				sock_hold(sk);
+				spin_unlock(&unix_table_lock);
+
+				return sk;
+			}
+	}
+
+	spin_unlock(&unix_table_lock);
+	return NULL;
+}
+
+static int unix_diag_get_exact(struct sk_buff *in_skb,
+			       const struct nlmsghdr *nlh,
+			       struct unix_diag_req *req)
+{
+	int err = -EINVAL;
+	struct sock *sk;
+	struct sk_buff *rep;
+	unsigned int extra_len;
+	struct net *net = sock_net(in_skb->sk);
+
+	if (req->udiag_ino == 0)
+		goto out_nosk;
+
+	sk = unix_lookup_by_ino(req->udiag_ino);
+	err = -ENOENT;
+	if (sk == NULL)
+		goto out_nosk;
+
+	err = sock_diag_check_cookie(sk, req->udiag_cookie);
+	if (err)
+		goto out;
+
+	extra_len = 256;
+again:
+	err = -ENOMEM;
+	rep = nlmsg_new(sizeof(struct unix_diag_msg) + extra_len, GFP_KERNEL);
+	if (!rep)
+		goto out;
+
+	err = sk_diag_fill(sk, rep, req, NETLINK_CB(in_skb).portid,
+			   nlh->nlmsg_seq, 0, req->udiag_ino);
+	if (err < 0) {
+		nlmsg_free(rep);
+		extra_len += 256;
+		if (extra_len >= PAGE_SIZE)
+			goto out;
+
+		goto again;
+	}
+	err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid,
+			      MSG_DONTWAIT);
+	if (err > 0)
+		err = 0;
+out:
+	if (sk)
+		sock_put(sk);
+out_nosk:
+	return err;
+}
+
+static int unix_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h)
+{
+	int hdrlen = sizeof(struct unix_diag_req);
+	struct net *net = sock_net(skb->sk);
+
+	if (nlmsg_len(h) < hdrlen)
+		return -EINVAL;
+
+	if (h->nlmsg_flags & NLM_F_DUMP) {
+		struct netlink_dump_control c = {
+			.dump = unix_diag_dump,
+		};
+		return netlink_dump_start(net->diag_nlsk, skb, h, &c);
+	} else
+		return unix_diag_get_exact(skb, h, nlmsg_data(h));
+}
+
+static const struct sock_diag_handler unix_diag_handler = {
+	.family = AF_UNIX,
+	.dump = unix_diag_handler_dump,
+};
+
+static int __init unix_diag_init(void)
+{
+	return sock_diag_register(&unix_diag_handler);
+}
+
+static void __exit unix_diag_exit(void)
+{
+	sock_diag_unregister(&unix_diag_handler);
+}
+
+module_init(unix_diag_init);
+module_exit(unix_diag_exit);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 1 /* AF_LOCAL */);

net/unix/garbage.c

@@ -0,0 +1,386 @@
+/*
+ * NET3:	Garbage Collector For AF_UNIX sockets
+ *
+ * Garbage Collector:
+ *	Copyright (C) Barak A. Pearlmutter.
+ *	Released under the GPL version 2 or later.
+ *
+ * Chopped about by Alan Cox 22/3/96 to make it fit the AF_UNIX socket problem.
+ * If it doesn't work blame me, it worked when Barak sent it.
+ *
+ * Assumptions:
+ *
+ *  - object w/ a bit
+ *  - free list
+ *
+ * Current optimizations:
+ *
+ *  - explicit stack instead of recursion
+ *  - tail recurse on first born instead of immediate push/pop
+ *  - we gather the stuff that should not be killed into tree
+ *    and stack is just a path from root to the current pointer.
+ *
+ *  Future optimizations:
+ *
+ *  - don't just push entire root set; process in place
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License
+ *	as published by the Free Software Foundation; either version
+ *	2 of the License, or (at your option) any later version.
+ *
+ *  Fixes:
+ *	Alan Cox	07 Sept	1997	Vmalloc internal stack as needed.
+ *					Cope with changing max_files.
+ *	Al Viro		11 Oct 1998
+ *		Graph may have cycles. That is, we can send the descriptor
+ *		of foo to bar and vice versa. Current code chokes on that.
+ *		Fix: move SCM_RIGHTS ones into the separate list and then
+ *		skb_free() them all instead of doing explicit fput's.
+ *		Another problem: since fput() may block somebody may
+ *		create a new unix_socket when we are in the middle of sweep
+ *		phase. Fix: revert the logic wrt MARKED. Mark everything
+ *		upon the beginning and unmark non-junk ones.
+ *
+ *		[12 Oct 1998] AAARGH! New code purges all SCM_RIGHTS
+ *		sent to connect()'ed but still not accept()'ed sockets.
+ *		Fixed. Old code had slightly different problem here:
+ *		extra fput() in situation when we passed the descriptor via
+ *		such socket and closed it (descriptor). That would happen on
+ *		each unix_gc() until the accept(). Since the struct file in
+ *		question would go to the free list and might be reused...
+ *		That might be the reason of random oopses on filp_close()
+ *		in unrelated processes.
+ *
+ *	AV		28 Feb 1999
+ *		Kill the explicit allocation of stack. Now we keep the tree
+ *		with root in dummy + pointer (gc_current) to one of the nodes.
+ *		Stack is represented as path from gc_current to dummy. Unmark
+ *		now means "add to tree". Push == "make it a son of gc_current".
+ *		Pop == "move gc_current to parent". We keep only pointers to
+ *		parents (->gc_tree).
+ *	AV		1 Mar 1999
+ *		Damn. Added missing check for ->dead in listen queues scanning.
+ *
+ *	Miklos Szeredi 25 Jun 2007
+ *		Reimplement with a cycle collecting algorithm. This should
+ *		solve several problems with the previous code, like being racy
+ *		wrt receive and holding up unrelated socket operations.
+ */
+
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/socket.h>
+#include <linux/un.h>
+#include <linux/net.h>
+#include <linux/fs.h>
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include <linux/file.h>
+#include <linux/proc_fs.h>
+#include <linux/mutex.h>
+#include <linux/wait.h>
+
+#include <net/sock.h>
+#include <net/af_unix.h>
+#include <net/scm.h>
+#include <net/tcp_states.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 file *fp)
+{
+	struct sock *s = unix_get_socket(fp);
+	if (s) {
+		struct unix_sock *u = unix_sk(s);
+		spin_lock(&unix_gc_lock);
+		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++;
+		spin_unlock(&unix_gc_lock);
+	}
+}
+
+void unix_notinflight(struct file *fp)
+{
+	struct sock *s = unix_get_socket(fp);
+	if (s) {
+		struct unix_sock *u = unix_sk(s);
+		spin_lock(&unix_gc_lock);
+		BUG_ON(list_empty(&u->link));
+		if (atomic_long_dec_and_test(&u->inflight))
+			list_del_init(&u->link);
+		unix_tot_inflight--;
+		spin_unlock(&unix_gc_lock);
+	}
+}
+
+static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *),
+			  struct sk_buff_head *hitlist)
+{
+	struct sk_buff *skb;
+	struct sk_buff *next;
+
+	spin_lock(&x->sk_receive_queue.lock);
+	skb_queue_walk_safe(&x->sk_receive_queue, skb, next) {
+		/*
+		 *	Do we have file descriptors ?
+		 */
+		if (UNIXCB(skb).fp) {
+			bool hit = false;
+			/*
+			 *	Process the descriptors of this socket
+			 */
+			int nfd = UNIXCB(skb).fp->count;
+			struct file **fp = UNIXCB(skb).fp->fp;
+			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);
+
+					/*
+					 * 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;
+						func(u);
+					}
+				}
+			}
+			if (hit && hitlist != NULL) {
+				__skb_unlink(skb, &x->sk_receive_queue);
+				__skb_queue_tail(hitlist, skb);
+			}
+		}
+	}
+	spin_unlock(&x->sk_receive_queue.lock);
+}
+
+static void scan_children(struct sock *x, void (*func)(struct unix_sock *),
+			  struct sk_buff_head *hitlist)
+{
+	if (x->sk_state != TCP_LISTEN)
+		scan_inflight(x, func, hitlist);
+	else {
+		struct sk_buff *skb;
+		struct sk_buff *next;
+		struct unix_sock *u;
+		LIST_HEAD(embryos);
+
+		/*
+		 * For a listening socket collect the queued embryos
+		 * and perform a scan on them as well.
+		 */
+		spin_lock(&x->sk_receive_queue.lock);
+		skb_queue_walk_safe(&x->sk_receive_queue, skb, next) {
+			u = unix_sk(skb->sk);
+
+			/*
+			 * An embryo cannot be in-flight, so it's safe
+			 * to use the list link.
+			 */
+			BUG_ON(!list_empty(&u->link));
+			list_add_tail(&u->link, &embryos);
+		}
+		spin_unlock(&x->sk_receive_queue.lock);
+
+		while (!list_empty(&embryos)) {
+			u = list_entry(embryos.next, struct unix_sock, link);
+			scan_inflight(&u->sk, func, hitlist);
+			list_del_init(&u->link);
+		}
+	}
+}
+
+static void dec_inflight(struct unix_sock *usk)
+{
+	atomic_long_dec(&usk->inflight);
+}
+
+static void inc_inflight(struct unix_sock *usk)
+{
+	atomic_long_inc(&usk->inflight);
+}
+
+static void inc_inflight_move_tail(struct unix_sock *u)
+{
+	atomic_long_inc(&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
+	 */
+	if (test_bit(UNIX_GC_MAYBE_CYCLE, &u->gc_flags))
+		list_move_tail(&u->link, &gc_candidates);
+}
+
+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.
+	 */
+	if (unix_tot_inflight > UNIX_INFLIGHT_TRIGGER_GC && !gc_in_progress)
+		unix_gc();
+	wait_event(unix_gc_wait, gc_in_progress == false);
+}
+
+/* The external entry point: unix_gc() */
+void unix_gc(void)
+{
+	struct unix_sock *u;
+	struct unix_sock *next;
+	struct sk_buff_head hitlist;
+	struct list_head cursor;
+	LIST_HEAD(not_cycle_list);
+
+	spin_lock(&unix_gc_lock);
+
+	/* Avoid a recursive GC. */
+	if (gc_in_progress)
+		goto out;
+
+	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.
+	 *
+	 * Holding unix_gc_lock will protect these candidates from
+	 * being detached, and hence from gaining an external
+	 * reference.  Since there are no possible receivers, all
+	 * buffers currently on the candidates' queues stay there
+	 * during the garbage collection.
+	 *
+	 * We also know that no new candidate can be added onto the
+	 * receive queues.  Other, non candidate sockets _can_ be
+	 * added to queue, so we must make sure only to touch
+	 * candidates.
+	 */
+	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) {
+			list_move_tail(&u->link, &gc_candidates);
+			__set_bit(UNIX_GC_CANDIDATE, &u->gc_flags);
+			__set_bit(UNIX_GC_MAYBE_CYCLE, &u->gc_flags);
+		}
+	}
+
+	/*
+	 * Now remove all internal in-flight reference to children of
+	 * the candidates.
+	 */
+	list_for_each_entry(u, &gc_candidates, link)
+		scan_children(&u->sk, dec_inflight, NULL);
+
+	/*
+	 * Restore the references for children of all candidates,
+	 * which have remaining references.  Do this recursively, so
+	 * only those remain, which form cyclic references.
+	 *
+	 * Use a "cursor" link, to make the list traversal safe, even
+	 * though elements might be moved about.
+	 */
+	list_add(&cursor, &gc_candidates);
+	while (cursor.next != &gc_candidates) {
+		u = list_entry(cursor.next, struct unix_sock, link);
+
+		/* Move cursor to after the current position. */
+		list_move(&cursor, &u->link);
+
+		if (atomic_long_read(&u->inflight) > 0) {
+			list_move_tail(&u->link, &not_cycle_list);
+			__clear_bit(UNIX_GC_MAYBE_CYCLE, &u->gc_flags);
+			scan_children(&u->sk, inc_inflight_move_tail, NULL);
+		}
+	}
+	list_del(&cursor);
+
+	/*
+	 * not_cycle_list contains those sockets which do not make up a
+	 * cycle.  Restore these to the inflight list.
+	 */
+	while (!list_empty(&not_cycle_list)) {
+		u = list_entry(not_cycle_list.next, struct unix_sock, link);
+		__clear_bit(UNIX_GC_CANDIDATE, &u->gc_flags);
+		list_move_tail(&u->link, &gc_inflight_list);
+	}
+
+	/*
+	 * Now gc_candidates contains only garbage.  Restore original
+	 * inflight counters for these as well, and remove the skbuffs
+	 * which are creating the cycle(s).
+	 */
+	skb_queue_head_init(&hitlist);
+	list_for_each_entry(u, &gc_candidates, link)
+	scan_children(&u->sk, inc_inflight, &hitlist);
+
+	spin_unlock(&unix_gc_lock);
+
+	/* Here we are. Hitlist is filled. Die. */
+	__skb_queue_purge(&hitlist);
+
+	spin_lock(&unix_gc_lock);
+
+	/* All candidates should have been detached by now. */
+	BUG_ON(!list_empty(&gc_candidates));
+	gc_in_progress = false;
+	wake_up(&unix_gc_wait);
+
+ out:
+	spin_unlock(&unix_gc_lock);
+}

net/unix/sysctl_net_unix.c

@@ -0,0 +1,61 @@
+/*
+ * NET4:	Sysctl interface to net af_unix subsystem.
+ *
+ * Authors:	Mike Shaver.
+ *
+ *		This program is free software; you can redistribute it and/or
+ *		modify it under the terms of the GNU General Public License
+ *		as published by the Free Software Foundation; either version
+ *		2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/sysctl.h>
+
+#include <net/af_unix.h>
+
+static struct ctl_table unix_table[] = {
+	{
+		.procname	= "max_dgram_qlen",
+		.data		= &init_net.unx.sysctl_max_dgram_qlen,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{ }
+};
+
+int __net_init unix_sysctl_register(struct net *net)
+{
+	struct ctl_table *table;
+
+	table = kmemdup(unix_table, sizeof(unix_table), GFP_KERNEL);
+	if (table == NULL)
+		goto err_alloc;
+
+	/* Don't export sysctls to unprivileged users */
+	if (net->user_ns != &init_user_ns)
+		table[0].procname = NULL;
+
+	table[0].data = &net->unx.sysctl_max_dgram_qlen;
+	net->unx.ctl = register_net_sysctl(net, "net/unix", table);
+	if (net->unx.ctl == NULL)
+		goto err_reg;
+
+	return 0;
+
+err_reg:
+	kfree(table);
+err_alloc:
+	return -ENOMEM;
+}
+
+void unix_sysctl_unregister(struct net *net)
+{
+	struct ctl_table *table;
+
+	table = net->unx.ctl->ctl_table_arg;
+	unregister_net_sysctl_table(net->unx.ctl);
+	kfree(table);
+}