Initial import

5 files changed, 1287 insertions, 0 deletions

diff --git a/fs/notify/fanotify/Kconfig b/fs/notify/fanotify/Kconfig
new file mode 100644
index 000000000..e5f911bd8
--- /dev/null
+++ b/fs/notify/fanotify/Kconfig
@@ -0,0 +1,26 @@
+config FANOTIFY
+	bool "Filesystem wide access notification"
+	select FSNOTIFY
+	select ANON_INODES
+	default n
+	---help---
+	   Say Y here to enable fanotify support.  fanotify is a file access
+	   notification system which differs from inotify in that it sends
+	   an open file descriptor to the userspace listener along with
+	   the event.
+
+	   If unsure, say Y.
+
+config FANOTIFY_ACCESS_PERMISSIONS
+	bool "fanotify permissions checking"
+	depends on FANOTIFY
+	depends on SECURITY
+	default n
+	---help---
+	   Say Y here is you want fanotify listeners to be able to make permissions
+	   decisions concerning filesystem events.  This is used by some fanotify
+	   listeners which need to scan files before allowing the system access to
+	   use those files.  This is used by some anti-malware vendors and by some
+	   hierarchical storage managent systems.
+
+	   If unsure, say N.
diff --git a/fs/notify/fanotify/Makefile b/fs/notify/fanotify/Makefile
new file mode 100644
index 000000000..0999213e7
--- /dev/null
+++ b/fs/notify/fanotify/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_FANOTIFY)		+= fanotify.o fanotify_user.o
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
new file mode 100644
index 000000000..d2f97ecca
--- /dev/null
+++ b/fs/notify/fanotify/fanotify.c
@@ -0,0 +1,270 @@
+#include <linux/fanotify.h>
+#include <linux/fdtable.h>
+#include <linux/fsnotify_backend.h>
+#include <linux/init.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h> /* UINT_MAX */
+#include <linux/mount.h>
+#include <linux/sched.h>
+#include <linux/types.h>
+#include <linux/wait.h>
+
+#include "fanotify.h"
+
+static bool should_merge(struct fsnotify_event *old_fsn,
+			 struct fsnotify_event *new_fsn)
+{
+	struct fanotify_event_info *old, *new;
+
+	pr_debug("%s: old=%p new=%p\n", __func__, old_fsn, new_fsn);
+	old = FANOTIFY_E(old_fsn);
+	new = FANOTIFY_E(new_fsn);
+
+	if (old_fsn->inode == new_fsn->inode && old->tgid == new->tgid &&
+	    old->path.mnt == new->path.mnt &&
+	    old->path.dentry == new->path.dentry)
+		return true;
+	return false;
+}
+
+/* and the list better be locked by something too! */
+static int fanotify_merge(struct list_head *list, struct fsnotify_event *event)
+{
+	struct fsnotify_event *test_event;
+	bool do_merge = false;
+
+	pr_debug("%s: list=%p event=%p\n", __func__, list, event);
+
+#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+	/*
+	 * Don't merge a permission event with any other event so that we know
+	 * the event structure we have created in fanotify_handle_event() is the
+	 * one we should check for permission response.
+	 */
+	if (event->mask & FAN_ALL_PERM_EVENTS)
+		return 0;
+#endif
+
+	list_for_each_entry_reverse(test_event, list, list) {
+		if (should_merge(test_event, event)) {
+			do_merge = true;
+			break;
+		}
+	}
+
+	if (!do_merge)
+		return 0;
+
+	test_event->mask |= event->mask;
+	return 1;
+}
+
+#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+static int fanotify_get_response(struct fsnotify_group *group,
+				 struct fanotify_perm_event_info *event)
+{
+	int ret;
+
+	pr_debug("%s: group=%p event=%p\n", __func__, group, event);
+
+	wait_event(group->fanotify_data.access_waitq, event->response ||
+				atomic_read(&group->fanotify_data.bypass_perm));
+
+	if (!event->response) {	/* bypass_perm set */
+		/*
+		 * Event was canceled because group is being destroyed. Remove
+		 * it from group's event list because we are responsible for
+		 * freeing the permission event.
+		 */
+		fsnotify_remove_event(group, &event->fae.fse);
+		return 0;
+	}
+
+	/* userspace responded, convert to something usable */
+	switch (event->response) {
+	case FAN_ALLOW:
+		ret = 0;
+		break;
+	case FAN_DENY:
+	default:
+		ret = -EPERM;
+	}
+	event->response = 0;
+
+	pr_debug("%s: group=%p event=%p about to return ret=%d\n", __func__,
+		 group, event, ret);
+	
+	return ret;
+}
+#endif
+
+static bool fanotify_should_send_event(struct fsnotify_mark *inode_mark,
+				       struct fsnotify_mark *vfsmnt_mark,
+				       u32 event_mask,
+				       void *data, int data_type)
+{
+	__u32 marks_mask, marks_ignored_mask;
+	struct path *path = data;
+
+	pr_debug("%s: inode_mark=%p vfsmnt_mark=%p mask=%x data=%p"
+		 " data_type=%d\n", __func__, inode_mark, vfsmnt_mark,
+		 event_mask, data, data_type);
+
+	/* if we don't have enough info to send an event to userspace say no */
+	if (data_type != FSNOTIFY_EVENT_PATH)
+		return false;
+
+	/* sorry, fanotify only gives a damn about files and dirs */
+	if (!d_is_reg(path->dentry) &&
+	    !d_can_lookup(path->dentry))
+		return false;
+
+	if (inode_mark && vfsmnt_mark) {
+		marks_mask = (vfsmnt_mark->mask | inode_mark->mask);
+		marks_ignored_mask = (vfsmnt_mark->ignored_mask | inode_mark->ignored_mask);
+	} else if (inode_mark) {
+		/*
+		 * if the event is for a child and this inode doesn't care about
+		 * events on the child, don't send it!
+		 */
+		if ((event_mask & FS_EVENT_ON_CHILD) &&
+		    !(inode_mark->mask & FS_EVENT_ON_CHILD))
+			return false;
+		marks_mask = inode_mark->mask;
+		marks_ignored_mask = inode_mark->ignored_mask;
+	} else if (vfsmnt_mark) {
+		marks_mask = vfsmnt_mark->mask;
+		marks_ignored_mask = vfsmnt_mark->ignored_mask;
+	} else {
+		BUG();
+	}
+
+	if (d_is_dir(path->dentry) &&
+	    !(marks_mask & FS_ISDIR & ~marks_ignored_mask))
+		return false;
+
+	if (event_mask & FAN_ALL_OUTGOING_EVENTS & marks_mask &
+				 ~marks_ignored_mask)
+		return true;
+
+	return false;
+}
+
+struct fanotify_event_info *fanotify_alloc_event(struct inode *inode, u32 mask,
+						 struct path *path)
+{
+	struct fanotify_event_info *event;
+
+#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+	if (mask & FAN_ALL_PERM_EVENTS) {
+		struct fanotify_perm_event_info *pevent;
+
+		pevent = kmem_cache_alloc(fanotify_perm_event_cachep,
+					  GFP_KERNEL);
+		if (!pevent)
+			return NULL;
+		event = &pevent->fae;
+		pevent->response = 0;
+		goto init;
+	}
+#endif
+	event = kmem_cache_alloc(fanotify_event_cachep, GFP_KERNEL);
+	if (!event)
+		return NULL;
+init: __maybe_unused
+	fsnotify_init_event(&event->fse, inode, mask);
+	event->tgid = get_pid(task_tgid(current));
+	if (path) {
+		event->path = *path;
+		path_get(&event->path);
+	} else {
+		event->path.mnt = NULL;
+		event->path.dentry = NULL;
+	}
+	return event;
+}
+
+static int fanotify_handle_event(struct fsnotify_group *group,
+				 struct inode *inode,
+				 struct fsnotify_mark *inode_mark,
+				 struct fsnotify_mark *fanotify_mark,
+				 u32 mask, void *data, int data_type,
+				 const unsigned char *file_name, u32 cookie)
+{
+	int ret = 0;
+	struct fanotify_event_info *event;
+	struct fsnotify_event *fsn_event;
+
+	BUILD_BUG_ON(FAN_ACCESS != FS_ACCESS);
+	BUILD_BUG_ON(FAN_MODIFY != FS_MODIFY);
+	BUILD_BUG_ON(FAN_CLOSE_NOWRITE != FS_CLOSE_NOWRITE);
+	BUILD_BUG_ON(FAN_CLOSE_WRITE != FS_CLOSE_WRITE);
+	BUILD_BUG_ON(FAN_OPEN != FS_OPEN);
+	BUILD_BUG_ON(FAN_EVENT_ON_CHILD != FS_EVENT_ON_CHILD);
+	BUILD_BUG_ON(FAN_Q_OVERFLOW != FS_Q_OVERFLOW);
+	BUILD_BUG_ON(FAN_OPEN_PERM != FS_OPEN_PERM);
+	BUILD_BUG_ON(FAN_ACCESS_PERM != FS_ACCESS_PERM);
+	BUILD_BUG_ON(FAN_ONDIR != FS_ISDIR);
+
+	if (!fanotify_should_send_event(inode_mark, fanotify_mark, mask, data,
+					data_type))
+		return 0;
+
+	pr_debug("%s: group=%p inode=%p mask=%x\n", __func__, group, inode,
+		 mask);
+
+	event = fanotify_alloc_event(inode, mask, data);
+	if (unlikely(!event))
+		return -ENOMEM;
+
+	fsn_event = &event->fse;
+	ret = fsnotify_add_event(group, fsn_event, fanotify_merge);
+	if (ret) {
+		/* Permission events shouldn't be merged */
+		BUG_ON(ret == 1 && mask & FAN_ALL_PERM_EVENTS);
+		/* Our event wasn't used in the end. Free it. */
+		fsnotify_destroy_event(group, fsn_event);
+
+		return 0;
+	}
+
+#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+	if (mask & FAN_ALL_PERM_EVENTS) {
+		ret = fanotify_get_response(group, FANOTIFY_PE(fsn_event));
+		fsnotify_destroy_event(group, fsn_event);
+	}
+#endif
+	return ret;
+}
+
+static void fanotify_free_group_priv(struct fsnotify_group *group)
+{
+	struct user_struct *user;
+
+	user = group->fanotify_data.user;
+	atomic_dec(&user->fanotify_listeners);
+	free_uid(user);
+}
+
+static void fanotify_free_event(struct fsnotify_event *fsn_event)
+{
+	struct fanotify_event_info *event;
+
+	event = FANOTIFY_E(fsn_event);
+	path_put(&event->path);
+	put_pid(event->tgid);
+#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+	if (fsn_event->mask & FAN_ALL_PERM_EVENTS) {
+		kmem_cache_free(fanotify_perm_event_cachep,
+				FANOTIFY_PE(fsn_event));
+		return;
+	}
+#endif
+	kmem_cache_free(fanotify_event_cachep, event);
+}
+
+const struct fsnotify_ops fanotify_fsnotify_ops = {
+	.handle_event = fanotify_handle_event,
+	.free_group_priv = fanotify_free_group_priv,
+	.free_event = fanotify_free_event,
+};
diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h
new file mode 100644
index 000000000..2a5fb1411
--- /dev/null
+++ b/fs/notify/fanotify/fanotify.h
@@ -0,0 +1,50 @@
+#include <linux/fsnotify_backend.h>
+#include <linux/path.h>
+#include <linux/slab.h>
+
+extern struct kmem_cache *fanotify_event_cachep;
+extern struct kmem_cache *fanotify_perm_event_cachep;
+
+/*
+ * Structure for normal fanotify events. It gets allocated in
+ * fanotify_handle_event() and freed when the information is retrieved by
+ * userspace
+ */
+struct fanotify_event_info {
+	struct fsnotify_event fse;
+	/*
+	 * We hold ref to this path so it may be dereferenced at any point
+	 * during this object's lifetime
+	 */
+	struct path path;
+	struct pid *tgid;
+};
+
+#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+/*
+ * Structure for permission fanotify events. It gets allocated and freed in
+ * fanotify_handle_event() since we wait there for user response. When the
+ * information is retrieved by userspace the structure is moved from
+ * group->notification_list to group->fanotify_data.access_list to wait for
+ * user response.
+ */
+struct fanotify_perm_event_info {
+	struct fanotify_event_info fae;
+	int response;	/* userspace answer to question */
+	int fd;		/* fd we passed to userspace for this event */
+};
+
+static inline struct fanotify_perm_event_info *
+FANOTIFY_PE(struct fsnotify_event *fse)
+{
+	return container_of(fse, struct fanotify_perm_event_info, fae.fse);
+}
+#endif
+
+static inline struct fanotify_event_info *FANOTIFY_E(struct fsnotify_event *fse)
+{
+	return container_of(fse, struct fanotify_event_info, fse);
+}
+
+struct fanotify_event_info *fanotify_alloc_event(struct inode *inode, u32 mask,
+						 struct path *path);
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
new file mode 100644
index 000000000..cf275500a
--- /dev/null
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -0,0 +1,940 @@
+#include <linux/fanotify.h>
+#include <linux/fcntl.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/anon_inodes.h>
+#include <linux/fsnotify_backend.h>
+#include <linux/init.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+#include <linux/poll.h>
+#include <linux/security.h>
+#include <linux/syscalls.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+#include <linux/compat.h>
+
+#include <asm/ioctls.h>
+
+#include "../../mount.h"
+#include "../fdinfo.h"
+#include "fanotify.h"
+
+#define FANOTIFY_DEFAULT_MAX_EVENTS	16384
+#define FANOTIFY_DEFAULT_MAX_MARKS	8192
+#define FANOTIFY_DEFAULT_MAX_LISTENERS	128
+
+/*
+ * All flags that may be specified in parameter event_f_flags of fanotify_init.
+ *
+ * Internal and external open flags are stored together in field f_flags of
+ * struct file. Only external open flags shall be allowed in event_f_flags.
+ * Internal flags like FMODE_NONOTIFY, FMODE_EXEC, FMODE_NOCMTIME shall be
+ * excluded.
+ */
+#define	FANOTIFY_INIT_ALL_EVENT_F_BITS				( \
+		O_ACCMODE	| O_APPEND	| O_NONBLOCK	| \
+		__O_SYNC	| O_DSYNC	| O_CLOEXEC     | \
+		O_LARGEFILE	| O_NOATIME	)
+
+extern const struct fsnotify_ops fanotify_fsnotify_ops;
+
+static struct kmem_cache *fanotify_mark_cache __read_mostly;
+struct kmem_cache *fanotify_event_cachep __read_mostly;
+struct kmem_cache *fanotify_perm_event_cachep __read_mostly;
+
+/*
+ * Get an fsnotify notification event if one exists and is small
+ * enough to fit in "count". Return an error pointer if the count
+ * is not large enough.
+ *
+ * Called with the group->notification_mutex held.
+ */
+static struct fsnotify_event *get_one_event(struct fsnotify_group *group,
+					    size_t count)
+{
+	BUG_ON(!mutex_is_locked(&group->notification_mutex));
+
+	pr_debug("%s: group=%p count=%zd\n", __func__, group, count);
+
+	if (fsnotify_notify_queue_is_empty(group))
+		return NULL;
+
+	if (FAN_EVENT_METADATA_LEN > count)
+		return ERR_PTR(-EINVAL);
+
+	/* held the notification_mutex the whole time, so this is the
+	 * same event we peeked above */
+	return fsnotify_remove_first_event(group);
+}
+
+static int create_fd(struct fsnotify_group *group,
+		     struct fanotify_event_info *event,
+		     struct file **file)
+{
+	int client_fd;
+	struct file *new_file;
+
+	pr_debug("%s: group=%p event=%p\n", __func__, group, event);
+
+	client_fd = get_unused_fd_flags(group->fanotify_data.f_flags);
+	if (client_fd < 0)
+		return client_fd;
+
+	/*
+	 * we need a new file handle for the userspace program so it can read even if it was
+	 * originally opened O_WRONLY.
+	 */
+	/* it's possible this event was an overflow event.  in that case dentry and mnt
+	 * are NULL;  That's fine, just don't call dentry open */
+	if (event->path.dentry && event->path.mnt)
+		new_file = dentry_open(&event->path,
+				       group->fanotify_data.f_flags | FMODE_NONOTIFY,
+				       current_cred());
+	else
+		new_file = ERR_PTR(-EOVERFLOW);
+	if (IS_ERR(new_file)) {
+		/*
+		 * we still send an event even if we can't open the file.  this
+		 * can happen when say tasks are gone and we try to open their
+		 * /proc files or we try to open a WRONLY file like in sysfs
+		 * we just send the errno to userspace since there isn't much
+		 * else we can do.
+		 */
+		put_unused_fd(client_fd);
+		client_fd = PTR_ERR(new_file);
+	} else {
+		*file = new_file;
+	}
+
+	return client_fd;
+}
+
+static int fill_event_metadata(struct fsnotify_group *group,
+			       struct fanotify_event_metadata *metadata,
+			       struct fsnotify_event *fsn_event,
+			       struct file **file)
+{
+	int ret = 0;
+	struct fanotify_event_info *event;
+
+	pr_debug("%s: group=%p metadata=%p event=%p\n", __func__,
+		 group, metadata, fsn_event);
+
+	*file = NULL;
+	event = container_of(fsn_event, struct fanotify_event_info, fse);
+	metadata->event_len = FAN_EVENT_METADATA_LEN;
+	metadata->metadata_len = FAN_EVENT_METADATA_LEN;
+	metadata->vers = FANOTIFY_METADATA_VERSION;
+	metadata->reserved = 0;
+	metadata->mask = fsn_event->mask & FAN_ALL_OUTGOING_EVENTS;
+	metadata->pid = pid_vnr(event->tgid);
+	if (unlikely(fsn_event->mask & FAN_Q_OVERFLOW))
+		metadata->fd = FAN_NOFD;
+	else {
+		metadata->fd = create_fd(group, event, file);
+		if (metadata->fd < 0)
+			ret = metadata->fd;
+	}
+
+	return ret;
+}
+
+#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+static struct fanotify_perm_event_info *dequeue_event(
+				struct fsnotify_group *group, int fd)
+{
+	struct fanotify_perm_event_info *event, *return_e = NULL;
+
+	spin_lock(&group->fanotify_data.access_lock);
+	list_for_each_entry(event, &group->fanotify_data.access_list,
+			    fae.fse.list) {
+		if (event->fd != fd)
+			continue;
+
+		list_del_init(&event->fae.fse.list);
+		return_e = event;
+		break;
+	}
+	spin_unlock(&group->fanotify_data.access_lock);
+
+	pr_debug("%s: found return_re=%p\n", __func__, return_e);
+
+	return return_e;
+}
+
+static int process_access_response(struct fsnotify_group *group,
+				   struct fanotify_response *response_struct)
+{
+	struct fanotify_perm_event_info *event;
+	int fd = response_struct->fd;
+	int response = response_struct->response;
+
+	pr_debug("%s: group=%p fd=%d response=%d\n", __func__, group,
+		 fd, response);
+	/*
+	 * make sure the response is valid, if invalid we do nothing and either
+	 * userspace can send a valid response or we will clean it up after the
+	 * timeout
+	 */
+	switch (response) {
+	case FAN_ALLOW:
+	case FAN_DENY:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (fd < 0)
+		return -EINVAL;
+
+	event = dequeue_event(group, fd);
+	if (!event)
+		return -ENOENT;
+
+	event->response = response;
+	wake_up(&group->fanotify_data.access_waitq);
+
+	return 0;
+}
+#endif
+
+static ssize_t copy_event_to_user(struct fsnotify_group *group,
+				  struct fsnotify_event *event,
+				  char __user *buf)
+{
+	struct fanotify_event_metadata fanotify_event_metadata;
+	struct file *f;
+	int fd, ret;
+
+	pr_debug("%s: group=%p event=%p\n", __func__, group, event);
+
+	ret = fill_event_metadata(group, &fanotify_event_metadata, event, &f);
+	if (ret < 0)
+		return ret;
+
+	fd = fanotify_event_metadata.fd;
+	ret = -EFAULT;
+	if (copy_to_user(buf, &fanotify_event_metadata,
+			 fanotify_event_metadata.event_len))
+		goto out_close_fd;
+
+#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+	if (event->mask & FAN_ALL_PERM_EVENTS)
+		FANOTIFY_PE(event)->fd = fd;
+#endif
+
+	if (fd != FAN_NOFD)
+		fd_install(fd, f);
+	return fanotify_event_metadata.event_len;
+
+out_close_fd:
+	if (fd != FAN_NOFD) {
+		put_unused_fd(fd);
+		fput(f);
+	}
+	return ret;
+}
+
+/* intofiy userspace file descriptor functions */
+static unsigned int fanotify_poll(struct file *file, poll_table *wait)
+{
+	struct fsnotify_group *group = file->private_data;
+	int ret = 0;
+
+	poll_wait(file, &group->notification_waitq, wait);
+	mutex_lock(&group->notification_mutex);
+	if (!fsnotify_notify_queue_is_empty(group))
+		ret = POLLIN | POLLRDNORM;
+	mutex_unlock(&group->notification_mutex);
+
+	return ret;
+}
+
+static ssize_t fanotify_read(struct file *file, char __user *buf,
+			     size_t count, loff_t *pos)
+{
+	struct fsnotify_group *group;
+	struct fsnotify_event *kevent;
+	char __user *start;
+	int ret;
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
+
+	start = buf;
+	group = file->private_data;
+
+	pr_debug("%s: group=%p\n", __func__, group);
+
+	add_wait_queue(&group->notification_waitq, &wait);
+	while (1) {
+		mutex_lock(&group->notification_mutex);
+		kevent = get_one_event(group, count);
+		mutex_unlock(&group->notification_mutex);
+
+		if (IS_ERR(kevent)) {
+			ret = PTR_ERR(kevent);
+			break;
+		}
+
+		if (!kevent) {
+			ret = -EAGAIN;
+			if (file->f_flags & O_NONBLOCK)
+				break;
+
+			ret = -ERESTARTSYS;
+			if (signal_pending(current))
+				break;
+
+			if (start != buf)
+				break;
+
+			wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
+			continue;
+		}
+
+		ret = copy_event_to_user(group, kevent, buf);
+		/*
+		 * Permission events get queued to wait for response.  Other
+		 * events can be destroyed now.
+		 */
+		if (!(kevent->mask & FAN_ALL_PERM_EVENTS)) {
+			fsnotify_destroy_event(group, kevent);
+			if (ret < 0)
+				break;
+		} else {
+#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+			if (ret < 0) {
+				FANOTIFY_PE(kevent)->response = FAN_DENY;
+				wake_up(&group->fanotify_data.access_waitq);
+				break;
+			}
+			spin_lock(&group->fanotify_data.access_lock);
+			list_add_tail(&kevent->list,
+				      &group->fanotify_data.access_list);
+			spin_unlock(&group->fanotify_data.access_lock);
+#endif
+		}
+		buf += ret;
+		count -= ret;
+	}
+	remove_wait_queue(&group->notification_waitq, &wait);
+
+	if (start != buf && ret != -EFAULT)
+		ret = buf - start;
+	return ret;
+}
+
+static ssize_t fanotify_write(struct file *file, const char __user *buf, size_t count, loff_t *pos)
+{
+#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+	struct fanotify_response response = { .fd = -1, .response = -1 };
+	struct fsnotify_group *group;
+	int ret;
+
+	group = file->private_data;
+
+	if (count > sizeof(response))
+		count = sizeof(response);
+
+	pr_debug("%s: group=%p count=%zu\n", __func__, group, count);
+
+	if (copy_from_user(&response, buf, count))
+		return -EFAULT;
+
+	ret = process_access_response(group, &response);
+	if (ret < 0)
+		count = ret;
+
+	return count;
+#else
+	return -EINVAL;
+#endif
+}
+
+static int fanotify_release(struct inode *ignored, struct file *file)
+{
+	struct fsnotify_group *group = file->private_data;
+
+#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+	struct fanotify_perm_event_info *event, *next;
+
+	/*
+	 * There may be still new events arriving in the notification queue
+	 * but since userspace cannot use fanotify fd anymore, no event can
+	 * enter or leave access_list by now.
+	 */
+	spin_lock(&group->fanotify_data.access_lock);
+
+	atomic_inc(&group->fanotify_data.bypass_perm);
+
+	list_for_each_entry_safe(event, next, &group->fanotify_data.access_list,
+				 fae.fse.list) {
+		pr_debug("%s: found group=%p event=%p\n", __func__, group,
+			 event);
+
+		list_del_init(&event->fae.fse.list);
+		event->response = FAN_ALLOW;
+	}
+	spin_unlock(&group->fanotify_data.access_lock);
+
+	/*
+	 * Since bypass_perm is set, newly queued events will not wait for
+	 * access response. Wake up the already sleeping ones now.
+	 * synchronize_srcu() in fsnotify_destroy_group() will wait for all
+	 * processes sleeping in fanotify_handle_event() waiting for access
+	 * response and thus also for all permission events to be freed.
+	 */
+	wake_up(&group->fanotify_data.access_waitq);
+#endif
+
+	/* matches the fanotify_init->fsnotify_alloc_group */
+	fsnotify_destroy_group(group);
+
+	return 0;
+}
+
+static long fanotify_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	struct fsnotify_group *group;
+	struct fsnotify_event *fsn_event;
+	void __user *p;
+	int ret = -ENOTTY;
+	size_t send_len = 0;
+
+	group = file->private_data;
+
+	p = (void __user *) arg;
+
+	switch (cmd) {
+	case FIONREAD:
+		mutex_lock(&group->notification_mutex);
+		list_for_each_entry(fsn_event, &group->notification_list, list)
+			send_len += FAN_EVENT_METADATA_LEN;
+		mutex_unlock(&group->notification_mutex);
+		ret = put_user(send_len, (int __user *) p);
+		break;
+	}
+
+	return ret;
+}
+
+static const struct file_operations fanotify_fops = {
+	.show_fdinfo	= fanotify_show_fdinfo,
+	.poll		= fanotify_poll,
+	.read		= fanotify_read,
+	.write		= fanotify_write,
+	.fasync		= NULL,
+	.release	= fanotify_release,
+	.unlocked_ioctl	= fanotify_ioctl,
+	.compat_ioctl	= fanotify_ioctl,
+	.llseek		= noop_llseek,
+};
+
+static void fanotify_free_mark(struct fsnotify_mark *fsn_mark)
+{
+	kmem_cache_free(fanotify_mark_cache, fsn_mark);
+}
+
+static int fanotify_find_path(int dfd, const char __user *filename,
+			      struct path *path, unsigned int flags)
+{
+	int ret;
+
+	pr_debug("%s: dfd=%d filename=%p flags=%x\n", __func__,
+		 dfd, filename, flags);
+
+	if (filename == NULL) {
+		struct fd f = fdget(dfd);
+
+		ret = -EBADF;
+		if (!f.file)
+			goto out;
+
+		ret = -ENOTDIR;
+		if ((flags & FAN_MARK_ONLYDIR) &&
+		    !(S_ISDIR(file_inode(f.file)->i_mode))) {
+			fdput(f);
+			goto out;
+		}
+
+		*path = f.file->f_path;
+		path_get(path);
+		fdput(f);
+	} else {
+		unsigned int lookup_flags = 0;
+
+		if (!(flags & FAN_MARK_DONT_FOLLOW))
+			lookup_flags |= LOOKUP_FOLLOW;
+		if (flags & FAN_MARK_ONLYDIR)
+			lookup_flags |= LOOKUP_DIRECTORY;
+
+		ret = user_path_at(dfd, filename, lookup_flags, path);
+		if (ret)
+			goto out;
+	}
+
+	/* you can only watch an inode if you have read permissions on it */
+	ret = inode_permission(path->dentry->d_inode, MAY_READ);
+	if (ret)
+		path_put(path);
+out:
+	return ret;
+}
+
+static __u32 fanotify_mark_remove_from_mask(struct fsnotify_mark *fsn_mark,
+					    __u32 mask,
+					    unsigned int flags,
+					    int *destroy)
+{
+	__u32 oldmask = 0;
+
+	spin_lock(&fsn_mark->lock);
+	if (!(flags & FAN_MARK_IGNORED_MASK)) {
+		__u32 tmask = fsn_mark->mask & ~mask;
+
+		if (flags & FAN_MARK_ONDIR)
+			tmask &= ~FAN_ONDIR;
+
+		oldmask = fsn_mark->mask;
+		fsnotify_set_mark_mask_locked(fsn_mark, tmask);
+	} else {
+		__u32 tmask = fsn_mark->ignored_mask & ~mask;
+		if (flags & FAN_MARK_ONDIR)
+			tmask &= ~FAN_ONDIR;
+
+		fsnotify_set_mark_ignored_mask_locked(fsn_mark, tmask);
+	}
+	*destroy = !(fsn_mark->mask | fsn_mark->ignored_mask);
+	spin_unlock(&fsn_mark->lock);
+
+	return mask & oldmask;
+}
+
+static int fanotify_remove_vfsmount_mark(struct fsnotify_group *group,
+					 struct vfsmount *mnt, __u32 mask,
+					 unsigned int flags)
+{
+	struct fsnotify_mark *fsn_mark = NULL;
+	__u32 removed;
+	int destroy_mark;
+
+	mutex_lock(&group->mark_mutex);
+	fsn_mark = fsnotify_find_vfsmount_mark(group, mnt);
+	if (!fsn_mark) {
+		mutex_unlock(&group->mark_mutex);
+		return -ENOENT;
+	}
+
+	removed = fanotify_mark_remove_from_mask(fsn_mark, mask, flags,
+						 &destroy_mark);
+	if (destroy_mark)
+		fsnotify_destroy_mark_locked(fsn_mark, group);
+	mutex_unlock(&group->mark_mutex);
+
+	fsnotify_put_mark(fsn_mark);
+	if (removed & real_mount(mnt)->mnt_fsnotify_mask)
+		fsnotify_recalc_vfsmount_mask(mnt);
+
+	return 0;
+}
+
+static int fanotify_remove_inode_mark(struct fsnotify_group *group,
+				      struct inode *inode, __u32 mask,
+				      unsigned int flags)
+{
+	struct fsnotify_mark *fsn_mark = NULL;
+	__u32 removed;
+	int destroy_mark;
+
+	mutex_lock(&group->mark_mutex);
+	fsn_mark = fsnotify_find_inode_mark(group, inode);
+	if (!fsn_mark) {
+		mutex_unlock(&group->mark_mutex);
+		return -ENOENT;
+	}
+
+	removed = fanotify_mark_remove_from_mask(fsn_mark, mask, flags,
+						 &destroy_mark);
+	if (destroy_mark)
+		fsnotify_destroy_mark_locked(fsn_mark, group);
+	mutex_unlock(&group->mark_mutex);
+
+	/* matches the fsnotify_find_inode_mark() */
+	fsnotify_put_mark(fsn_mark);
+	if (removed & inode->i_fsnotify_mask)
+		fsnotify_recalc_inode_mask(inode);
+
+	return 0;
+}
+
+static __u32 fanotify_mark_add_to_mask(struct fsnotify_mark *fsn_mark,
+				       __u32 mask,
+				       unsigned int flags)
+{
+	__u32 oldmask = -1;
+
+	spin_lock(&fsn_mark->lock);
+	if (!(flags & FAN_MARK_IGNORED_MASK)) {
+		__u32 tmask = fsn_mark->mask | mask;
+
+		if (flags & FAN_MARK_ONDIR)
+			tmask |= FAN_ONDIR;
+
+		oldmask = fsn_mark->mask;
+		fsnotify_set_mark_mask_locked(fsn_mark, tmask);
+	} else {
+		__u32 tmask = fsn_mark->ignored_mask | mask;
+		if (flags & FAN_MARK_ONDIR)
+			tmask |= FAN_ONDIR;
+
+		fsnotify_set_mark_ignored_mask_locked(fsn_mark, tmask);
+		if (flags & FAN_MARK_IGNORED_SURV_MODIFY)
+			fsn_mark->flags |= FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY;
+	}
+	spin_unlock(&fsn_mark->lock);
+
+	return mask & ~oldmask;
+}
+
+static struct fsnotify_mark *fanotify_add_new_mark(struct fsnotify_group *group,
+						   struct inode *inode,
+						   struct vfsmount *mnt)
+{
+	struct fsnotify_mark *mark;
+	int ret;
+
+	if (atomic_read(&group->num_marks) > group->fanotify_data.max_marks)
+		return ERR_PTR(-ENOSPC);
+
+	mark = kmem_cache_alloc(fanotify_mark_cache, GFP_KERNEL);
+	if (!mark)
+		return ERR_PTR(-ENOMEM);
+
+	fsnotify_init_mark(mark, fanotify_free_mark);
+	ret = fsnotify_add_mark_locked(mark, group, inode, mnt, 0);
+	if (ret) {
+		fsnotify_put_mark(mark);
+		return ERR_PTR(ret);
+	}
+
+	return mark;
+}
+
+
+static int fanotify_add_vfsmount_mark(struct fsnotify_group *group,
+				      struct vfsmount *mnt, __u32 mask,
+				      unsigned int flags)
+{
+	struct fsnotify_mark *fsn_mark;
+	__u32 added;
+
+	mutex_lock(&group->mark_mutex);
+	fsn_mark = fsnotify_find_vfsmount_mark(group, mnt);
+	if (!fsn_mark) {
+		fsn_mark = fanotify_add_new_mark(group, NULL, mnt);
+		if (IS_ERR(fsn_mark)) {
+			mutex_unlock(&group->mark_mutex);
+			return PTR_ERR(fsn_mark);
+		}
+	}
+	added = fanotify_mark_add_to_mask(fsn_mark, mask, flags);
+	mutex_unlock(&group->mark_mutex);
+
+	if (added & ~real_mount(mnt)->mnt_fsnotify_mask)
+		fsnotify_recalc_vfsmount_mask(mnt);
+
+	fsnotify_put_mark(fsn_mark);
+	return 0;
+}
+
+static int fanotify_add_inode_mark(struct fsnotify_group *group,
+				   struct inode *inode, __u32 mask,
+				   unsigned int flags)
+{
+	struct fsnotify_mark *fsn_mark;
+	__u32 added;
+
+	pr_debug("%s: group=%p inode=%p\n", __func__, group, inode);
+
+	/*
+	 * If some other task has this inode open for write we should not add
+	 * an ignored mark, unless that ignored mark is supposed to survive
+	 * modification changes anyway.
+	 */
+	if ((flags & FAN_MARK_IGNORED_MASK) &&
+	    !(flags & FAN_MARK_IGNORED_SURV_MODIFY) &&
+	    (atomic_read(&inode->i_writecount) > 0))
+		return 0;
+
+	mutex_lock(&group->mark_mutex);
+	fsn_mark = fsnotify_find_inode_mark(group, inode);
+	if (!fsn_mark) {
+		fsn_mark = fanotify_add_new_mark(group, inode, NULL);
+		if (IS_ERR(fsn_mark)) {
+			mutex_unlock(&group->mark_mutex);
+			return PTR_ERR(fsn_mark);
+		}
+	}
+	added = fanotify_mark_add_to_mask(fsn_mark, mask, flags);
+	mutex_unlock(&group->mark_mutex);
+
+	if (added & ~inode->i_fsnotify_mask)
+		fsnotify_recalc_inode_mask(inode);
+
+	fsnotify_put_mark(fsn_mark);
+	return 0;
+}
+
+/* fanotify syscalls */
+SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
+{
+	struct fsnotify_group *group;
+	int f_flags, fd;
+	struct user_struct *user;
+	struct fanotify_event_info *oevent;
+
+	pr_debug("%s: flags=%d event_f_flags=%d\n",
+		__func__, flags, event_f_flags);
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (flags & ~FAN_ALL_INIT_FLAGS)
+		return -EINVAL;
+
+	if (event_f_flags & ~FANOTIFY_INIT_ALL_EVENT_F_BITS)
+		return -EINVAL;
+
+	switch (event_f_flags & O_ACCMODE) {
+	case O_RDONLY:
+	case O_RDWR:
+	case O_WRONLY:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	user = get_current_user();
+	if (atomic_read(&user->fanotify_listeners) > FANOTIFY_DEFAULT_MAX_LISTENERS) {
+		free_uid(user);
+		return -EMFILE;
+	}
+
+	f_flags = O_RDWR | FMODE_NONOTIFY;
+	if (flags & FAN_CLOEXEC)
+		f_flags |= O_CLOEXEC;
+	if (flags & FAN_NONBLOCK)
+		f_flags |= O_NONBLOCK;
+
+	/* fsnotify_alloc_group takes a ref.  Dropped in fanotify_release */
+	group = fsnotify_alloc_group(&fanotify_fsnotify_ops);
+	if (IS_ERR(group)) {
+		free_uid(user);
+		return PTR_ERR(group);
+	}
+
+	group->fanotify_data.user = user;
+	atomic_inc(&user->fanotify_listeners);
+
+	oevent = fanotify_alloc_event(NULL, FS_Q_OVERFLOW, NULL);
+	if (unlikely(!oevent)) {
+		fd = -ENOMEM;
+		goto out_destroy_group;
+	}
+	group->overflow_event = &oevent->fse;
+
+	if (force_o_largefile())
+		event_f_flags |= O_LARGEFILE;
+	group->fanotify_data.f_flags = event_f_flags;
+#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+	spin_lock_init(&group->fanotify_data.access_lock);
+	init_waitqueue_head(&group->fanotify_data.access_waitq);
+	INIT_LIST_HEAD(&group->fanotify_data.access_list);
+	atomic_set(&group->fanotify_data.bypass_perm, 0);
+#endif
+	switch (flags & FAN_ALL_CLASS_BITS) {
+	case FAN_CLASS_NOTIF:
+		group->priority = FS_PRIO_0;
+		break;
+	case FAN_CLASS_CONTENT:
+		group->priority = FS_PRIO_1;
+		break;
+	case FAN_CLASS_PRE_CONTENT:
+		group->priority = FS_PRIO_2;
+		break;
+	default:
+		fd = -EINVAL;
+		goto out_destroy_group;
+	}
+
+	if (flags & FAN_UNLIMITED_QUEUE) {
+		fd = -EPERM;
+		if (!capable(CAP_SYS_ADMIN))
+			goto out_destroy_group;
+		group->max_events = UINT_MAX;
+	} else {
+		group->max_events = FANOTIFY_DEFAULT_MAX_EVENTS;
+	}
+
+	if (flags & FAN_UNLIMITED_MARKS) {
+		fd = -EPERM;
+		if (!capable(CAP_SYS_ADMIN))
+			goto out_destroy_group;
+		group->fanotify_data.max_marks = UINT_MAX;
+	} else {
+		group->fanotify_data.max_marks = FANOTIFY_DEFAULT_MAX_MARKS;
+	}
+
+	fd = anon_inode_getfd("[fanotify]", &fanotify_fops, group, f_flags);
+	if (fd < 0)
+		goto out_destroy_group;
+
+	return fd;
+
+out_destroy_group:
+	fsnotify_destroy_group(group);
+	return fd;
+}
+
+SYSCALL_DEFINE5(fanotify_mark, int, fanotify_fd, unsigned int, flags,
+			      __u64, mask, int, dfd,
+			      const char  __user *, pathname)
+{
+	struct inode *inode = NULL;
+	struct vfsmount *mnt = NULL;
+	struct fsnotify_group *group;
+	struct fd f;
+	struct path path;
+	int ret;
+
+	pr_debug("%s: fanotify_fd=%d flags=%x dfd=%d pathname=%p mask=%llx\n",
+		 __func__, fanotify_fd, flags, dfd, pathname, mask);
+
+	/* we only use the lower 32 bits as of right now. */
+	if (mask & ((__u64)0xffffffff << 32))
+		return -EINVAL;
+
+	if (flags & ~FAN_ALL_MARK_FLAGS)
+		return -EINVAL;
+	switch (flags & (FAN_MARK_ADD | FAN_MARK_REMOVE | FAN_MARK_FLUSH)) {
+	case FAN_MARK_ADD:		/* fallthrough */
+	case FAN_MARK_REMOVE:
+		if (!mask)
+			return -EINVAL;
+		break;
+	case FAN_MARK_FLUSH:
+		if (flags & ~(FAN_MARK_MOUNT | FAN_MARK_FLUSH))
+			return -EINVAL;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (mask & FAN_ONDIR) {
+		flags |= FAN_MARK_ONDIR;
+		mask &= ~FAN_ONDIR;
+	}
+
+#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+	if (mask & ~(FAN_ALL_EVENTS | FAN_ALL_PERM_EVENTS | FAN_EVENT_ON_CHILD))
+#else
+	if (mask & ~(FAN_ALL_EVENTS | FAN_EVENT_ON_CHILD))
+#endif
+		return -EINVAL;
+
+	f = fdget(fanotify_fd);
+	if (unlikely(!f.file))
+		return -EBADF;
+
+	/* verify that this is indeed an fanotify instance */
+	ret = -EINVAL;
+	if (unlikely(f.file->f_op != &fanotify_fops))
+		goto fput_and_out;
+	group = f.file->private_data;
+
+	/*
+	 * group->priority == FS_PRIO_0 == FAN_CLASS_NOTIF.  These are not
+	 * allowed to set permissions events.
+	 */
+	ret = -EINVAL;
+	if (mask & FAN_ALL_PERM_EVENTS &&
+	    group->priority == FS_PRIO_0)
+		goto fput_and_out;
+
+	if (flags & FAN_MARK_FLUSH) {
+		ret = 0;
+		if (flags & FAN_MARK_MOUNT)
+			fsnotify_clear_vfsmount_marks_by_group(group);
+		else
+			fsnotify_clear_inode_marks_by_group(group);
+		goto fput_and_out;
+	}
+
+	ret = fanotify_find_path(dfd, pathname, &path, flags);
+	if (ret)
+		goto fput_and_out;
+
+	/* inode held in place by reference to path; group by fget on fd */
+	if (!(flags & FAN_MARK_MOUNT))
+		inode = path.dentry->d_inode;
+	else
+		mnt = path.mnt;
+
+	/* create/update an inode mark */
+	switch (flags & (FAN_MARK_ADD | FAN_MARK_REMOVE)) {
+	case FAN_MARK_ADD:
+		if (flags & FAN_MARK_MOUNT)
+			ret = fanotify_add_vfsmount_mark(group, mnt, mask, flags);
+		else
+			ret = fanotify_add_inode_mark(group, inode, mask, flags);
+		break;
+	case FAN_MARK_REMOVE:
+		if (flags & FAN_MARK_MOUNT)
+			ret = fanotify_remove_vfsmount_mark(group, mnt, mask, flags);
+		else
+			ret = fanotify_remove_inode_mark(group, inode, mask, flags);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	path_put(&path);
+fput_and_out:
+	fdput(f);
+	return ret;
+}
+
+#ifdef CONFIG_COMPAT
+COMPAT_SYSCALL_DEFINE6(fanotify_mark,
+				int, fanotify_fd, unsigned int, flags,
+				__u32, mask0, __u32, mask1, int, dfd,
+				const char  __user *, pathname)
+{
+	return sys_fanotify_mark(fanotify_fd, flags,
+#ifdef __BIG_ENDIAN
+				((__u64)mask0 << 32) | mask1,
+#else
+				((__u64)mask1 << 32) | mask0,
+#endif
+				 dfd, pathname);
+}
+#endif
+
+/*
+ * fanotify_user_setup - Our initialization function.  Note that we cannot return
+ * error because we have compiled-in VFS hooks.  So an (unlikely) failure here
+ * must result in panic().
+ */
+static int __init fanotify_user_setup(void)
+{
+	fanotify_mark_cache = KMEM_CACHE(fsnotify_mark, SLAB_PANIC);
+	fanotify_event_cachep = KMEM_CACHE(fanotify_event_info, SLAB_PANIC);
+#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+	fanotify_perm_event_cachep = KMEM_CACHE(fanotify_perm_event_info,
+						SLAB_PANIC);
+#endif
+
+	return 0;
+}
+device_initcall(fanotify_user_setup);