[PATCH] audit: watching subtrees

New kind of audit rule predicates: "object is visible in given subtree".
The part that can be sanely implemented, that is.  Limitations:
	* if you have hardlink from outside of tree, you'd better watch
it too (or just watch the object itself, obviously)
	* if you mount something under a watched tree, tell audit
that new chunk should be added to watched subtrees
	* if you umount something in a watched tree and it's still mounted
elsewhere, you will get matches on events happening there.  New command
tells audit to recalculate the trees, trimming such sources of false
positives.

Note that it's _not_ about path - if something mounted in several places
(multiple mount, bindings, different namespaces, etc.), the match does
_not_ depend on which one we are using for access.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

10 files changed, 1310 insertions, 10 deletions

diff --git a/fs/dcache.c b/fs/dcache.c
index 5489b2d98a0..2bb3f7ac683 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -38,7 +38,7 @@ int sysctl_vfs_cache_pressure __read_mostly = 100;
 EXPORT_SYMBOL_GPL(sysctl_vfs_cache_pressure);
 
  __cacheline_aligned_in_smp DEFINE_SPINLOCK(dcache_lock);
-static __cacheline_aligned_in_smp DEFINE_SEQLOCK(rename_lock);
+__cacheline_aligned_in_smp DEFINE_SEQLOCK(rename_lock);
 
 EXPORT_SYMBOL(dcache_lock);
 
diff --git a/include/linux/audit.h b/include/linux/audit.h
index 133b81be60a..c6878169283 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -63,6 +63,8 @@
 #define AUDIT_ADD_RULE		1011	/* Add syscall filtering rule */
 #define AUDIT_DEL_RULE		1012	/* Delete syscall filtering rule */
 #define AUDIT_LIST_RULES	1013	/* List syscall filtering rules */
+#define AUDIT_TRIM		1014	/* Trim junk from watched tree */
+#define AUDIT_MAKE_EQUIV	1015	/* Append to watched tree */
 #define AUDIT_TTY_GET		1016	/* Get TTY auditing status */
 #define AUDIT_TTY_SET		1017	/* Set TTY auditing status */
 
@@ -203,6 +205,7 @@
 #define AUDIT_SUCCESS   104	/* exit >= 0; value ignored */
 #define AUDIT_WATCH	105
 #define AUDIT_PERM	106
+#define AUDIT_DIR	107
 
 #define AUDIT_ARG0      200
 #define AUDIT_ARG1      (AUDIT_ARG0+1)
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index aab53df4faf..c2c153f97e8 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -178,6 +178,7 @@ d_iput:		no		no		no       yes
 #define DCACHE_INOTIFY_PARENT_WATCHED	0x0020 /* Parent inode is watched */
 
 extern spinlock_t dcache_lock;
+extern seqlock_t rename_lock;
 
 /**
  * d_drop - drop a dentry
diff --git a/init/Kconfig b/init/Kconfig
index 541382d539a..b7dffa83792 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -234,6 +234,10 @@ config AUDITSYSCALL
 	  such as SELinux.  To use audit's filesystem watch feature, please
 	  ensure that INOTIFY is configured.
 
+config AUDIT_TREE
+	def_bool y
+	depends on AUDITSYSCALL && INOTIFY
+
 config IKCONFIG
 	tristate "Kernel .config support"
 	---help---
diff --git a/kernel/Makefile b/kernel/Makefile
index 79f017e09fb..f60afe74259 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -46,6 +46,7 @@ obj-$(CONFIG_IKCONFIG) += configs.o
 obj-$(CONFIG_STOP_MACHINE) += stop_machine.o
 obj-$(CONFIG_AUDIT) += audit.o auditfilter.o
 obj-$(CONFIG_AUDITSYSCALL) += auditsc.o
+obj-$(CONFIG_AUDIT_TREE) += audit_tree.o
 obj-$(CONFIG_KPROBES) += kprobes.o
 obj-$(CONFIG_SYSFS) += ksysfs.o
 obj-$(CONFIG_DETECT_SOFTLOCKUP) += softlockup.o
diff --git a/kernel/audit.c b/kernel/audit.c
index 6977ea57a7e..f93c2713017 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -468,6 +468,21 @@ int audit_send_list(void *_dest)
 	return 0;
 }
 
+#ifdef CONFIG_AUDIT_TREE
+static int prune_tree_thread(void *unused)
+{
+	mutex_lock(&audit_cmd_mutex);
+	audit_prune_trees();
+	mutex_unlock(&audit_cmd_mutex);
+	return 0;
+}
+
+void audit_schedule_prune(void)
+{
+	kthread_run(prune_tree_thread, NULL, "audit_prune_tree");
+}
+#endif
+
 struct sk_buff *audit_make_reply(int pid, int seq, int type, int done,
 				 int multi, void *payload, int size)
 {
@@ -540,6 +555,8 @@ static int audit_netlink_ok(struct sk_buff *skb, u16 msg_type)
 	case AUDIT_SIGNAL_INFO:
 	case AUDIT_TTY_GET:
 	case AUDIT_TTY_SET:
+	case AUDIT_TRIM:
+	case AUDIT_MAKE_EQUIV:
 		if (security_netlink_recv(skb, CAP_AUDIT_CONTROL))
 			err = -EPERM;
 		break;
@@ -756,6 +773,76 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 					   uid, seq, data, nlmsg_len(nlh),
 					   loginuid, sid);
 		break;
+	case AUDIT_TRIM:
+		audit_trim_trees();
+		ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE);
+		if (!ab)
+			break;
+		audit_log_format(ab, "auid=%u", loginuid);
+		if (sid) {
+			u32 len;
+			ctx = NULL;
+			if (selinux_sid_to_string(sid, &ctx, &len))
+				audit_log_format(ab, " ssid=%u", sid);
+			else
+				audit_log_format(ab, " subj=%s", ctx);
+			kfree(ctx);
+		}
+		audit_log_format(ab, " op=trim res=1");
+		audit_log_end(ab);
+		break;
+	case AUDIT_MAKE_EQUIV: {
+		void *bufp = data;
+		u32 sizes[2];
+		size_t len = nlmsg_len(nlh);
+		char *old, *new;
+
+		err = -EINVAL;
+		if (len < 2 * sizeof(u32))
+			break;
+		memcpy(sizes, bufp, 2 * sizeof(u32));
+		bufp += 2 * sizeof(u32);
+		len -= 2 * sizeof(u32);
+		old = audit_unpack_string(&bufp, &len, sizes[0]);
+		if (IS_ERR(old)) {
+			err = PTR_ERR(old);
+			break;
+		}
+		new = audit_unpack_string(&bufp, &len, sizes[1]);
+		if (IS_ERR(new)) {
+			err = PTR_ERR(new);
+			kfree(old);
+			break;
+		}
+		/* OK, here comes... */
+		err = audit_tag_tree(old, new);
+
+		ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE);
+		if (!ab) {
+			kfree(old);
+			kfree(new);
+			break;
+		}
+		audit_log_format(ab, "auid=%u", loginuid);
+		if (sid) {
+			u32 len;
+			ctx = NULL;
+			if (selinux_sid_to_string(sid, &ctx, &len))
+				audit_log_format(ab, " ssid=%u", sid);
+			else
+				audit_log_format(ab, " subj=%s", ctx);
+			kfree(ctx);
+		}
+		audit_log_format(ab, " op=make_equiv old=");
+		audit_log_untrustedstring(ab, old);
+		audit_log_format(ab, " new=");
+		audit_log_untrustedstring(ab, new);
+		audit_log_format(ab, " res=%d", !err);
+		audit_log_end(ab);
+		kfree(old);
+		kfree(new);
+		break;
+	}
 	case AUDIT_SIGNAL_INFO:
 		err = selinux_sid_to_string(audit_sig_sid, &ctx, &len);
 		if (err)
diff --git a/kernel/audit.h b/kernel/audit.h
index 95877435c34..2554bd524fd 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -73,6 +73,9 @@ struct audit_field {
 	struct selinux_audit_rule	*se_rule;
 };
 
+struct audit_tree;
+struct audit_chunk;
+
 struct audit_krule {
 	int			vers_ops;
 	u32			flags;
@@ -86,7 +89,8 @@ struct audit_krule {
 	struct audit_field	*arch_f; /* quick access to arch field */
 	struct audit_field	*inode_f; /* quick access to an inode field */
 	struct audit_watch	*watch;	/* associated watch */
-	struct list_head	rlist;	/* entry in audit_watch.rules list */
+	struct audit_tree	*tree;	/* associated watched tree */
+	struct list_head	rlist;	/* entry in audit_{watch,tree}.rules list */
 };
 
 struct audit_entry {
@@ -130,6 +134,34 @@ extern void audit_handle_ievent(struct inotify_watch *, u32, u32, u32,
 				const char *, struct inode *);
 extern int selinux_audit_rule_update(void);
 
+extern struct mutex audit_filter_mutex;
+extern void audit_free_rule_rcu(struct rcu_head *);
+
+#ifdef CONFIG_AUDIT_TREE
+extern struct audit_chunk *audit_tree_lookup(const struct inode *);
+extern void audit_put_chunk(struct audit_chunk *);
+extern int audit_tree_match(struct audit_chunk *, struct audit_tree *);
+extern int audit_make_tree(struct audit_krule *, char *, u32);
+extern int audit_add_tree_rule(struct audit_krule *);
+extern int audit_remove_tree_rule(struct audit_krule *);
+extern void audit_trim_trees(void);
+extern int audit_tag_tree(char *old, char *new);
+extern void audit_schedule_prune(void);
+extern void audit_prune_trees(void);
+extern const char *audit_tree_path(struct audit_tree *);
+extern void audit_put_tree(struct audit_tree *);
+#else
+#define audit_remove_tree_rule(rule) BUG()
+#define audit_add_tree_rule(rule) -EINVAL
+#define audit_make_tree(rule, str, op) -EINVAL
+#define audit_trim_trees() (void)0
+#define audit_put_tree(tree) (void)0
+#define audit_tag_tree(old, new) -EINVAL
+#define audit_tree_path(rule) ""	/* never called */
+#endif
+
+extern char *audit_unpack_string(void **, size_t *, size_t);
+
 #ifdef CONFIG_AUDITSYSCALL
 extern int __audit_signal_info(int sig, struct task_struct *t);
 static inline int audit_signal_info(int sig, struct task_struct *t)
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
new file mode 100644
index 00000000000..f4fcf58f20f
--- /dev/null
+++ b/kernel/audit_tree.c
@@ -0,0 +1,903 @@
+#include "audit.h"
+#include <linux/inotify.h>
+#include <linux/namei.h>
+#include <linux/mount.h>
+
+struct audit_tree;
+struct audit_chunk;
+
+struct audit_tree {
+	atomic_t count;
+	int goner;
+	struct audit_chunk *root;
+	struct list_head chunks;
+	struct list_head rules;
+	struct list_head list;
+	struct list_head same_root;
+	struct rcu_head head;
+	char pathname[];
+};
+
+struct audit_chunk {
+	struct list_head hash;
+	struct inotify_watch watch;
+	struct list_head trees;		/* with root here */
+	int dead;
+	int count;
+	struct rcu_head head;
+	struct node {
+		struct list_head list;
+		struct audit_tree *owner;
+		unsigned index;		/* index; upper bit indicates 'will prune' */
+	} owners[];
+};
+
+static LIST_HEAD(tree_list);
+static LIST_HEAD(prune_list);
+
+/*
+ * One struct chunk is attached to each inode of interest.
+ * We replace struct chunk on tagging/untagging.
+ * Rules have pointer to struct audit_tree.
+ * Rules have struct list_head rlist forming a list of rules over
+ * the same tree.
+ * References to struct chunk are collected at audit_inode{,_child}()
+ * time and used in AUDIT_TREE rule matching.
+ * These references are dropped at the same time we are calling
+ * audit_free_names(), etc.
+ *
+ * Cyclic lists galore:
+ * tree.chunks anchors chunk.owners[].list			hash_lock
+ * tree.rules anchors rule.rlist				audit_filter_mutex
+ * chunk.trees anchors tree.same_root				hash_lock
+ * chunk.hash is a hash with middle bits of watch.inode as
+ * a hash function.						RCU, hash_lock
+ *
+ * tree is refcounted; one reference for "some rules on rules_list refer to
+ * it", one for each chunk with pointer to it.
+ *
+ * chunk is refcounted by embedded inotify_watch.
+ *
+ * node.index allows to get from node.list to containing chunk.
+ * MSB of that sucker is stolen to mark taggings that we might have to
+ * revert - several operations have very unpleasant cleanup logics and
+ * that makes a difference.  Some.
+ */
+
+static struct inotify_handle *rtree_ih;
+
+static struct audit_tree *alloc_tree(const char *s)
+{
+	struct audit_tree *tree;
+
+	tree = kmalloc(sizeof(struct audit_tree) + strlen(s) + 1, GFP_KERNEL);
+	if (tree) {
+		atomic_set(&tree->count, 1);
+		tree->goner = 0;
+		INIT_LIST_HEAD(&tree->chunks);
+		INIT_LIST_HEAD(&tree->rules);
+		INIT_LIST_HEAD(&tree->list);
+		INIT_LIST_HEAD(&tree->same_root);
+		tree->root = NULL;
+		strcpy(tree->pathname, s);
+	}
+	return tree;
+}
+
+static inline void get_tree(struct audit_tree *tree)
+{
+	atomic_inc(&tree->count);
+}
+
+static void __put_tree(struct rcu_head *rcu)
+{
+	struct audit_tree *tree = container_of(rcu, struct audit_tree, head);
+	kfree(tree);
+}
+
+static inline void put_tree(struct audit_tree *tree)
+{
+	if (atomic_dec_and_test(&tree->count))
+		call_rcu(&tree->head, __put_tree);
+}
+
+/* to avoid bringing the entire thing in audit.h */
+const char *audit_tree_path(struct audit_tree *tree)
+{
+	return tree->pathname;
+}
+
+static struct audit_chunk *alloc_chunk(int count)
+{
+	struct audit_chunk *chunk;
+	size_t size;
+	int i;
+
+	size = offsetof(struct audit_chunk, owners) + count * sizeof(struct node);
+	chunk = kzalloc(size, GFP_KERNEL);
+	if (!chunk)
+		return NULL;
+
+	INIT_LIST_HEAD(&chunk->hash);
+	INIT_LIST_HEAD(&chunk->trees);
+	chunk->count = count;
+	for (i = 0; i < count; i++) {
+		INIT_LIST_HEAD(&chunk->owners[i].list);
+		chunk->owners[i].index = i;
+	}
+	inotify_init_watch(&chunk->watch);
+	return chunk;
+}
+
+static void __free_chunk(struct rcu_head *rcu)
+{
+	struct audit_chunk *chunk = container_of(rcu, struct audit_chunk, head);
+	int i;
+
+	for (i = 0; i < chunk->count; i++) {
+		if (chunk->owners[i].owner)
+			put_tree(chunk->owners[i].owner);
+	}
+	kfree(chunk);
+}
+
+static inline void free_chunk(struct audit_chunk *chunk)
+{
+	call_rcu(&chunk->head, __free_chunk);
+}
+
+void audit_put_chunk(struct audit_chunk *chunk)
+{
+	put_inotify_watch(&chunk->watch);
+}
+
+enum {HASH_SIZE = 128};
+static struct list_head chunk_hash_heads[HASH_SIZE];
+static __cacheline_aligned_in_smp DEFINE_SPINLOCK(hash_lock);
+
+static inline struct list_head *chunk_hash(const struct inode *inode)
+{
+	unsigned long n = (unsigned long)inode / L1_CACHE_BYTES;
+	return chunk_hash_heads + n % HASH_SIZE;
+}
+
+/* hash_lock is held by caller */
+static void insert_hash(struct audit_chunk *chunk)
+{
+	struct list_head *list = chunk_hash(chunk->watch.inode);
+	list_add_rcu(&chunk->hash, list);
+}
+
+/* called under rcu_read_lock */
+struct audit_chunk *audit_tree_lookup(const struct inode *inode)
+{
+	struct list_head *list = chunk_hash(inode);
+	struct list_head *pos;
+
+	list_for_each_rcu(pos, list) {
+		struct audit_chunk *p = container_of(pos, struct audit_chunk, hash);
+		if (p->watch.inode == inode) {
+			get_inotify_watch(&p->watch);
+			return p;
+		}
+	}
+	return NULL;
+}
+
+int audit_tree_match(struct audit_chunk *chunk, struct audit_tree *tree)
+{
+	int n;
+	for (n = 0; n < chunk->count; n++)
+		if (chunk->owners[n].owner == tree)
+			return 1;
+	return 0;
+}
+
+/* tagging and untagging inodes with trees */
+
+static void untag_chunk(struct audit_chunk *chunk, struct node *p)
+{
+	struct audit_chunk *new;
+	struct audit_tree *owner;
+	int size = chunk->count - 1;
+	int i, j;
+
+	mutex_lock(&chunk->watch.inode->inotify_mutex);
+	if (chunk->dead) {
+		mutex_unlock(&chunk->watch.inode->inotify_mutex);
+		return;
+	}
+
+	owner = p->owner;
+
+	if (!size) {
+		chunk->dead = 1;
+		spin_lock(&hash_lock);
+		list_del_init(&chunk->trees);
+		if (owner->root == chunk)
+			owner->root = NULL;
+		list_del_init(&p->list);
+		list_del_rcu(&chunk->hash);
+		spin_unlock(&hash_lock);
+		inotify_evict_watch(&chunk->watch);
+		mutex_unlock(&chunk->watch.inode->inotify_mutex);
+		put_inotify_watch(&chunk->watch);
+		return;
+	}
+
+	new = alloc_chunk(size);
+	if (!new)
+		goto Fallback;
+	if (inotify_clone_watch(&chunk->watch, &new->watch) < 0) {
+		free_chunk(new);
+		goto Fallback;
+	}
+
+	chunk->dead = 1;
+	spin_lock(&hash_lock);
+	list_replace_init(&chunk->trees, &new->trees);
+	if (owner->root == chunk) {
+		list_del_init(&owner->same_root);
+		owner->root = NULL;
+	}
+
+	for (i = j = 0; i < size; i++, j++) {
+		struct audit_tree *s;
+		if (&chunk->owners[j] == p) {
+			list_del_init(&p->list);
+			i--;
+			continue;
+		}
+		s = chunk->owners[j].owner;
+		new->owners[i].owner = s;
+		new->owners[i].index = chunk->owners[j].index - j + i;
+		if (!s) /* result of earlier fallback */
+			continue;
+		get_tree(s);
+		list_replace_init(&chunk->owners[i].list, &new->owners[j].list);
+	}
+
+	list_replace_rcu(&chunk->hash, &new->hash);
+	list_for_each_entry(owner, &new->trees, same_root)
+		owner->root = new;
+	spin_unlock(&hash_lock);
+	inotify_evict_watch(&chunk->watch);
+	mutex_unlock(&chunk->watch.inode->inotify_mutex);
+	put_inotify_watch(&chunk->watch);
+	return;
+
+Fallback:
+	// do the best we can
+	spin_lock(&hash_lock);
+	if (owner->root == chunk) {
+		list_del_init(&owner->same_root);
+		owner->root = NULL;
+	}
+	list_del_init(&p->list);
+	p->owner = NULL;
+	put_tree(owner);
+	spin_unlock(&hash_lock);
+	mutex_unlock(&chunk->watch.inode->inotify_mutex);
+}
+
+static int create_chunk(struct inode *inode, struct audit_tree *tree)
+{
+	struct audit_chunk *chunk = alloc_chunk(1);
+	if (!chunk)
+		return -ENOMEM;
+
+	if (inotify_add_watch(rtree_ih, &chunk->watch, inode, IN_IGNORED | IN_DELETE_SELF) < 0) {
+		free_chunk(chunk);
+		return -ENOSPC;
+	}
+
+	mutex_lock(&inode->inotify_mutex);
+	spin_lock(&hash_lock);
+	if (tree->goner) {
+		spin_unlock(&hash_lock);
+		chunk->dead = 1;
+		inotify_evict_watch(&chunk->watch);
+		mutex_unlock(&inode->inotify_mutex);
+		put_inotify_watch(&chunk->watch);
+		return 0;
+	}
+	chunk->owners[0].index = (1U << 31);
+	chunk->owners[0].owner = tree;
+	get_tree(tree);
+	list_add(&chunk->owners[0].list, &tree->chunks);
+	if (!tree->root) {
+		tree->root = chunk;
+		list_add(&tree->same_root, &chunk->trees);
+	}
+	insert_hash(chunk);
+	spin_unlock(&hash_lock);
+	mutex_unlock(&inode->inotify_mutex);
+	return 0;
+}
+
+/* the first tagged inode becomes root of tree */
+static int tag_chunk(struct inode *inode, struct audit_tree *tree)
+{
+	struct inotify_watch *watch;
+	struct audit_tree *owner;
+	struct audit_chunk *chunk, *old;
+	struct node *p;
+	int n;
+
+	if (inotify_find_watch(rtree_ih, inode, &watch) < 0)
+		return create_chunk(inode, tree);
+
+	old = container_of(watch, struct audit_chunk, watch);
+
+	/* are we already there? */
+	spin_lock(&hash_lock);
+	for (n = 0; n < old->count; n++) {
+		if (old->owners[n].owner == tree) {
+			spin_unlock(&hash_lock);
+			put_inotify_watch(watch);
+			return 0;
+		}
+	}
+	spin_unlock(&hash_lock);
+
+	chunk = alloc_chunk(old->count + 1);
+	if (!chunk)
+		return -ENOMEM;
+
+	mutex_lock(&inode->inotify_mutex);
+	if (inotify_clone_watch(&old->watch, &chunk->watch) < 0) {
+		mutex_unlock(&inode->inotify_mutex);
+		free_chunk(chunk);
+		return -ENOSPC;
+	}
+	spin_lock(&hash_lock);
+	if (tree->goner) {
+		spin_unlock(&hash_lock);
+		chunk->dead = 1;
+		inotify_evict_watch(&chunk->watch);
+		mutex_unlock(&inode->inotify_mutex);
+		put_inotify_watch(&chunk->watch);
+		return 0;
+	}
+	list_replace_init(&old->trees, &chunk->trees);
+	for (n = 0, p = chunk->owners; n < old->count; n++, p++) {
+		struct audit_tree *s = old->owners[n].owner;
+		p->owner = s;
+		p->index = old->owners[n].index;
+		if (!s) /* result of fallback in untag */
+			continue;
+		get_tree(s);
+		list_replace_init(&old->owners[n].list, &p->list);
+	}
+	p->index = (chunk->count - 1) | (1U<<31);
+	p->owner = tree;
+	get_tree(tree);
+	list_add(&p->list, &tree->chunks);
+	list_replace_rcu(&old->hash, &chunk->hash);
+	list_for_each_entry(owner, &chunk->trees, same_root)
+		owner->root = chunk;
+	old->dead = 1;
+	if (!tree->root) {
+		tree->root = chunk;
+		list_add(&tree->same_root, &chunk->trees);
+	}
+	spin_unlock(&hash_lock);
+	inotify_evict_watch(&old->watch);
+	mutex_unlock(&inode->inotify_mutex);
+	put_inotify_watch(&old->watch);
+	return 0;
+}
+
+static struct audit_chunk *find_chunk(struct node *p)
+{
+	int index = p->index & ~(1U<<31);
+	p -= index;
+	return container_of(p, struct audit_chunk, owners[0]);
+}
+
+static void kill_rules(struct audit_tree *tree)
+{
+	struct audit_krule *rule, *next;
+	struct audit_entry *entry;
+	struct audit_buffer *ab;
+
+	list_for_each_entry_safe(rule, next, &tree->rules, rlist) {
+		entry = container_of(rule, struct audit_entry, rule);
+
+		list_del_init(&rule->rlist);
+		if (rule->tree) {
+			/* not a half-baked one */
+			ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE);
+			audit_log_format(ab, "op=remove rule dir=");
+			audit_log_untrustedstring(ab, rule->tree->pathname);
+			if (rule->filterkey) {
+				audit_log_format(ab, " key=");
+				audit_log_untrustedstring(ab, rule->filterkey);
+			} else
+				audit_log_format(ab, " key=(null)");
+			audit_log_format(ab, " list=%d res=1", rule->listnr);
+			audit_log_end(ab);
+			rule->tree = NULL;
+			list_del_rcu(&entry->list);
+			call_rcu(&entry->rcu, audit_free_rule_rcu);
+		}
+	}
+}
+
+/*
+ * finish killing struct audit_tree
+ */
+static void prune_one(struct audit_tree *victim)
+{
+	spin_lock(&hash_lock);
+	while (!list_empty(&victim->chunks)) {
+		struct node *p;
+		struct audit_chunk *chunk;
+
+		p = list_entry(victim->chunks.next, struct node, list);
+		chunk = find_chunk(p);
+		get_inotify_watch(&chunk->watch);
+		spin_unlock(&hash_lock);
+
+		untag_chunk(chunk, p);
+
+		put_inotify_watch(&chunk->watch);
+		spin_lock(&hash_lock);
+	}
+	spin_unlock(&hash_lock);
+	put_tree(victim);
+}
+
+/* trim the uncommitted chunks from tree */
+
+static void trim_marked(struct audit_tree *tree)
+{
+	struct list_head *p, *q;
+	spin_lock(&hash_lock);
+	if (tree->goner) {
+		spin_unlock(&hash_lock);
+		return;
+	}
+	/* reorder */
+	for (p = tree->chunks.next; p != &tree->chunks; p = q) {
+		struct node *node = list_entry(p, struct node, list);
+		q = p->next;
+		if (node->index & (1U<<31)) {
+			list_del_init(p);
+			list_add(p, &tree->chunks);
+		}
+	}
+
+	while (!list_empty(&tree->chunks)) {
+		struct node *node;
+		struct audit_chunk *chunk;
+
+		node = list_entry(tree->chunks.next, struct node, list);
+
+		/* have we run out of marked? */
+		if (!(node->index & (1U<<31)))
+			break;
+
+		chunk = find_chunk(node);
+		get_inotify_watch(&chunk->watch);
+		spin_unlock(&hash_lock);
+
+		untag_chunk(chunk, node);
+
+		put_inotify_watch(&chunk->watch);
+		spin_lock(&hash_lock);
+	}
+	if (!tree->root && !tree->goner) {
+		tree->goner = 1;
+		spin_unlock(&hash_lock);
+		mutex_lock(&audit_filter_mutex);
+		kill_rules(tree);
+		list_del_init(&tree->list);
+		mutex_unlock(&audit_filter_mutex);
+		prune_one(tree);
+	} else {
+		spin_unlock(&hash_lock);
+	}
+}
+
+/* called with audit_filter_mutex */
+int audit_remove_tree_rule(struct audit_krule *rule)
+{
+	struct audit_tree *tree;
+	tree = rule->tree;
+	if (tree) {
+		spin_lock(&hash_lock);
+		list_del_init(&rule->rlist);
+		if (list_empty(&tree->rules) && !tree->goner) {
+			tree->root = NULL;
+			list_del_init(&tree->same_root);
+			tree->goner = 1;
+			list_move(&tree->list, &prune_list);
+			rule->tree = NULL;
+			spin_unlock(&hash_lock);
+			audit_schedule_prune();
+			return 1;
+		}
+		rule->tree = NULL;
+		spin_unlock(&hash_lock);
+		return 1;
+	}
+	return 0;
+}
+
+void audit_trim_trees(void)
+{
+	struct list_head cursor;
+
+	mutex_lock(&audit_filter_mutex);
+	list_add(&cursor, &tree_list);
+	while (cursor.next != &tree_list) {
+		struct audit_tree *tree;
+		struct nameidata nd;
+		struct vfsmount *root_mnt;
+		struct node *node;
+		struct list_head list;
+		int err;
+
+		tree = container_of(cursor.next, struct audit_tree, list);
+		get_tree(tree);
+		list_del(&cursor);
+		list_add(&cursor, &tree->list);
+		mutex_unlock(&audit_filter_mutex);
+
+		err = path_lookup(tree->pathname, 0, &nd);
+		if (err)
+			goto skip_it;
+
+		root_mnt = collect_mounts(nd.mnt, nd.dentry);
+		path_release(&nd);
+		if (!root_mnt)
+			goto skip_it;
+
+		list_add_tail(&list, &root_mnt->mnt_list);
+		spin_lock(&hash_lock);
+		list_for_each_entry(node, &tree->chunks, list) {
+			struct audit_chunk *chunk = find_chunk(node);
+			struct inode *inode = chunk->watch.inode;
+			struct vfsmount *mnt;
+			node->index |= 1U<<31;
+			list_for_each_entry(mnt, &list, mnt_list) {
+				if (mnt->mnt_root->d_inode == inode) {
+					node->index &= ~(1U<<31);
+					break;
+				}
+			}
+		}
+		spin_unlock(&hash_lock);
+		trim_marked(tree);
+		put_tree(tree);
+		list_del_init(&list);
+		drop_collected_mounts(root_mnt);
+skip_it:
+		mutex_lock(&audit_filter_mutex);
+	}
+	list_del(&cursor);
+	mutex_unlock(&audit_filter_mutex);
+}
+
+static int is_under(struct vfsmount *mnt, struct dentry *dentry,
+		    struct nameidata *nd)
+{
+	if (mnt != nd->mnt) {
+		for (;;) {
+			if (mnt->mnt_parent == mnt)
+				return 0;
+			if (mnt->mnt_parent == nd->mnt)
+					break;
+			mnt = mnt->mnt_parent;
+		}
+		dentry = mnt->mnt_mountpoint;
+	}
+	return is_subdir(dentry, nd->dentry);
+}
+
+int audit_make_tree(struct audit_krule *rule, char *pathname, u32 op)
+{
+
+	if (pathname[0] != '/' ||
+	    rule->listnr != AUDIT_FILTER_EXIT ||
+	    op & ~AUDIT_EQUAL ||
+	    rule->inode_f || rule->watch || rule->tree)
+		return -EINVAL;
+	rule->tree = alloc_tree(pathname);
+	if (!rule->tree)
+		return -ENOMEM;
+	return 0;
+}
+
+void audit_put_tree(struct audit_tree *tree)
+{
+	put_tree(tree);
+}
+
+/* called with audit_filter_mutex */
+int audit_add_tree_rule(struct audit_krule *rule)
+{
+	struct audit_tree *seed = rule->tree, *tree;
+	struct nameidata nd;
+	struct vfsmount *mnt, *p;
+	struct list_head list;
+	int err;
+
+	list_for_each_entry(tree, &tree_list, list) {
+		if (!strcmp(seed->pathname, tree->pathname)) {
+			put_tree(seed);
+			rule->tree = tree;
+			list_add(&rule->rlist, &tree->rules);
+			return 0;
+		}
+	}
+	tree = seed;
+	list_add(&tree->list, &tree_list);
+	list_add(&rule->rlist, &tree->rules);
+	/* do not set rule->tree yet */
+	mutex_unlock(&audit_filter_mutex);
+
+	err = path_lookup(tree->pathname, 0, &nd);
+	if (err)
+		goto Err;
+	mnt = collect_mounts(nd.mnt, nd.dentry);
+	path_release(&nd);
+	if (!mnt) {
+		err = -ENOMEM;
+		goto Err;
+	}
+	list_add_tail(&list, &mnt->mnt_list);
+
+	get_tree(tree);
+	list_for_each_entry(p, &list, mnt_list) {
+		err = tag_chunk(p->mnt_root->d_inode, tree);
+		if (err)
+			break;
+	}
+
+	list_del(&list);
+	drop_collected_mounts(mnt);
+
+	if (!err) {
+		struct node *node;
+		spin_lock(&hash_lock);
+		list_for_each_entry(node, &tree->chunks, list)
+			node->index &= ~(1U<<31);
+		spin_unlock(&hash_lock);
+	} else {
+		trim_marked(tree);
+		goto Err;
+	}
+
+	mutex_lock(&audit_filter_mutex);
+	if (list_empty(&rule->rlist)) {
+		put_tree(tree);
+		return -ENOENT;
+	}
+	rule->tree = tree;
+	put_tree(tree);
+
+	return 0;
+Err:
+	mutex_lock(&audit_filter_mutex);
+	list_del_init(&tree->list);
+	list_del_init(&tree->rules);
+	put_tree(tree);
+	return err;
+}
+
+int audit_tag_tree(char *old, char *new)
+{
+	struct list_head cursor, barrier;
+	int failed = 0;
+	struct nameidata nd;
+	struct vfsmount *tagged;
+	struct list_head list;
+	struct vfsmount *mnt;
+	struct dentry *dentry;
+	int err;
+
+	err = path_lookup(new, 0, &nd);
+	if (err)
+		return err;
+	tagged = collect_mounts(nd.mnt, nd.dentry);
+	path_release(&nd);
+	if (!tagged)
+		return -ENOMEM;
+
+	err = path_lookup(old, 0, &nd);
+	if (err) {
+		drop_collected_mounts(tagged);
+		return err;
+	}
+	mnt = mntget(nd.mnt);
+	dentry = dget(nd.dentry);
+	path_release(&nd);
+
+	if (dentry == tagged->mnt_root && dentry == mnt->mnt_root)
+		follow_up(&mnt, &dentry);
+
+	list_add_tail(&list, &tagged->mnt_list);
+
+	mutex_lock(&audit_filter_mutex);
+	list_add(&barrier, &tree_list);
+	list_add(&cursor, &barrier);
+
+	while (cursor.next != &tree_list) {
+		struct audit_tree *tree;
+		struct vfsmount *p;
+
+		tree = container_of(cursor.next, struct audit_tree, list);
+		get_tree(tree);
+		list_del(&cursor);
+		list_add(&cursor, &tree->list);
+		mutex_unlock(&audit_filter_mutex);
+
+		err = path_lookup(tree->pathname, 0, &nd);
+		if (err) {
+			put_tree(tree);
+			mutex_lock(&audit_filter_mutex);
+			continue;
+		}
+
+		spin_lock(&vfsmount_lock);
+		if (!is_under(mnt, dentry, &nd)) {
+			spin_unlock(&vfsmount_lock);
+			path_release(&nd);
+			put_tree(tree);
+			mutex_lock(&audit_filter_mutex);
+			continue;
+		}
+		spin_unlock(&vfsmount_lock);
+		path_release(&nd);
+
+		list_for_each_entry(p, &list, mnt_list) {
+			failed = tag_chunk(p->mnt_root->d_inode, tree);
+			if (failed)
+				break;
+		}
+
+		if (failed) {
+			put_tree(tree);
+			mutex_lock(&audit_filter_mutex);
+			break;
+		}
+
+		mutex_lock(&audit_filter_mutex);
+		spin_lock(&hash_lock);
+		if (!tree->goner) {
+			list_del(&tree->list);
+			list_add(&tree->list, &tree_list);
+		}
+		spin_unlock(&hash_lock);
+		put_tree(tree);
+	}
+
+	while (barrier.prev != &tree_list) {
+		struct audit_tree *tree;
+
+		tree = container_of(barrier.prev, struct audit_tree, list);
+		get_tree(tree);
+		list_del(&tree->list);
+		list_add(&tree->list, &barrier);
+		mutex_unlock(&audit_filter_mutex);
+
+		if (!failed) {
+			struct node *node;
+			spin_lock(&hash_lock);
+			list_for_each_entry(node, &tree->chunks, list)
+				node->index &= ~(1U<<31);
+			spin_unlock(&hash_lock);
+		} else {
+			trim_marked(tree);
+		}
+
+		put_tree(tree);
+		mutex_lock(&audit_filter_mutex);
+	}
+	list_del(&barrier);
+	list_del(&cursor);
+	list_del(&list);
+	mutex_unlock(&audit_filter_mutex);
+	dput(dentry);
+	mntput(mnt);
+	drop_collected_mounts(tagged);
+	return failed;
+}
+
+/*
+ * That gets run when evict_chunk() ends up needing to kill audit_tree.
+ * Runs from a separate thread, with audit_cmd_mutex held.
+ */
+void audit_prune_trees(void)
+{
+	mutex_lock(&audit_filter_mutex);
+
+	while (!list_empty(&prune_list)) {
+		struct audit_tree *victim;
+
+		victim = list_entry(prune_list.next, struct audit_tree, list);
+		list_del_init(&victim->list);
+
+		mutex_unlock(&audit_filter_mutex);
+
+		prune_one(victim);
+
+		mutex_lock(&audit_filter_mutex);
+	}
+
+	mutex_unlock(&audit_filter_mutex);
+}
+
+/*
+ *  Here comes the stuff asynchronous to auditctl operations
+ */
+
+/* inode->inotify_mutex is locked */
+static void evict_chunk(struct audit_chunk *chunk)
+{
+	struct audit_tree *owner;
+	int n;
+
+	if (chunk->dead)
+		return;
+
+	chunk->dead = 1;
+	mutex_lock(&audit_filter_mutex);