Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Fix error output of boot instance creation failure

   Currently if a boot instance creation fails, instead of printing out
   the name of the instance that failed, it prints "(null)". That is
   because it prints "cur_str" that had already been processed by
   strsep(). Print the saved name instead.

   While at it, print the error code of the failure.

 - Fix use-after-free for same named historgrams

   Histograms can be named so that they can be used in multiple events.
   But if the named histogram has a variable attached, the second event
   that uses the named histogram which duplicates it and needs to free
   the original after duplication leaves the old variable in place and
   still visible. If another histogram uses than variable, it will use
   the stale one which will try to reference the freed duplicate
   histogram and crash the kernel.

   Free the duplicate variables along with the duplicated histogram
   data.

 - Check return value of kthread_run() in event self test

   The events self tests uses a kthread for testing but does not check
   if it succeeded in creating a kthread. If the kthread creation were
   to fail, the code will still try to call kthread_stop() on the error
   returned.

 - Fix race between reading trace_pipe and updating subbuffer size

   If a user is reading the trace_pipe file at the same time they update
   the ring buffer sub-buffer size, can cause the trace_pipe read to
   read stale data. Add trace_access_lock() around updating the ring
   buffer sub-buffer size.

 - Fix eventfs_inode on failure path in creation of the events directory

   In the creation of the "events" directory, if after allocating the
   eventfs_inode a failure is detected, it calls cleanup_ei() which
   calls free_ei(). The free_ei() will test if eventfs_inode being freed
   has no children. It is a bug if it does. But on the failure case of
   the creation of the "events" directory, the children lists have not
   yet been initialized and the free will trigger a warning because
   list_empty() on an uninitialized list returns false.

   Move the initialization into init_ei() where it makes more sense and
   makes sure that a created eventfs_inode has its lists initialized
   upon creation.

 - Check return value of kthread_run() in ftrace direct sample code

   The sample code that shows how to use the ftrace direct calls does
   not test the return of kthread_run() to see if it succeeds. Return a
   failure if the kthread_run() doesn't succeed.

 - Clear user events state on fork in case of alloc failure

   On fork, the child gets a pointer to the parent's user events state.
   It makes a copy of it then updates the child's pointer to it. But if
   the allocation fails, the duplication function leaves the child with
   a pointer to its parent's descriptor. When the child cleans up its
   data, it will free the parent's descriptor while the parent is still
   using it.

   In the duplication function, set the child's user_event_mm to NULL
   before testing if the allocation succeeded, and when it exits it will
   not free the parent's descriptor.

 - Fix retry exhaustion in simple ring buffer reader swap

   simple_ring_buffer_swap_reader_page() starts with retry set to 8 and
   post-decrements it only after a failed link replacement. On the final
   attempt, a successful replacement leaves retry at zero, while a
   failed replacement leaves it at -1.

   But the check for success expects the retry value to be non-zero and
   exits with an error on zero. This is the opposite result. Fix it.

 - Fail nicely when the remote swap_reader_page() returns an error

   Currently, if the swap_reader_page() of a remote buffer fails, it
   triggers a WARN_ON_ONCE() and continues normally. Instead, have it
   exit with an error and a pr_warn() print instead of a full WARNING.

* tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Stop remote reader update when page swap fails
  tracing: Fix retry exhaustion in simple ring buffer reader swap
  tracing/user_events: Clear copied tracing state before fork duplication
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify
  eventfs: Initialize ei->children and ei->list in init_ei()
  tracing: Fix use-after-free in trace_pipe read on sub-buffer order change
  tracing: Fix crash passing ERR_PTR to kthread_stop()
  tracing: Fix use-after-free with same-name named triggers
  tracing: Fix logged instance name on creation failure

5 files changed, 1145 insertions, 0 deletions

diff --git a/fs/notify/inotify/Kconfig b/fs/notify/inotify/Kconfig
new file mode 100644
index 000000000..1cc8be25d
--- /dev/null
+++ b/fs/notify/inotify/Kconfig
@@ -0,0 +1,17 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config INOTIFY_USER
+	bool "Inotify support for userspace"
+	select FSNOTIFY
+	default y
+	help
+	  Say Y here to enable inotify support for userspace, including the
+	  associated system calls.  Inotify allows monitoring of both files and
+	  directories via a single open fd.  Events are read from the file
+	  descriptor, which is also select()- and poll()-able.
+	  Inotify fixes numerous shortcomings in dnotify and introduces several
+	  new features including multiple file events, one-shot support, and
+	  unmount notification.
+
+	  For more information, see <file:Documentation/filesystems/inotify.rst>
+
+	  If unsure, say Y.
diff --git a/fs/notify/inotify/Makefile b/fs/notify/inotify/Makefile
new file mode 100644
index 000000000..812237eec
--- /dev/null
+++ b/fs/notify/inotify/Makefile
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_INOTIFY_USER)	+= inotify_fsnotify.o inotify_user.o
diff --git a/fs/notify/inotify/inotify.h b/fs/notify/inotify/inotify.h
new file mode 100644
index 000000000..7d5df7a21
--- /dev/null
+++ b/fs/notify/inotify/inotify.h
@@ -0,0 +1,69 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/fsnotify_backend.h>
+#include <linux/inotify.h>
+#include <linux/slab.h> /* struct kmem_cache */
+
+struct inotify_event_info {
+	struct fsnotify_event fse;
+	u32 mask;
+	int wd;
+	u32 sync_cookie;
+	int name_len;
+	char name[];
+};
+
+struct inotify_inode_mark {
+	struct fsnotify_mark fsn_mark;
+	int wd;
+};
+
+static inline struct inotify_event_info *INOTIFY_E(struct fsnotify_event *fse)
+{
+	return container_of(fse, struct inotify_event_info, fse);
+}
+
+/*
+ * INOTIFY_USER_FLAGS represents all of the mask bits that we expose to
+ * userspace.  There is at least one bit (FS_EVENT_ON_CHILD) which is
+ * used only internally to the kernel.
+ */
+#define INOTIFY_USER_MASK (IN_ALL_EVENTS)
+
+static inline __u32 inotify_mark_user_mask(struct fsnotify_mark *fsn_mark)
+{
+	__u32 mask = fsn_mark->mask & INOTIFY_USER_MASK;
+
+	if (fsn_mark->flags & FSNOTIFY_MARK_FLAG_EXCL_UNLINK)
+		mask |= IN_EXCL_UNLINK;
+	if (fsn_mark->flags & FSNOTIFY_MARK_FLAG_IN_ONESHOT)
+		mask |= IN_ONESHOT;
+
+	return mask;
+}
+
+extern void inotify_ignored_and_remove_idr(struct fsnotify_mark *fsn_mark,
+					   struct fsnotify_group *group);
+extern int inotify_handle_inode_event(struct fsnotify_mark *inode_mark,
+				      u32 mask, struct inode *inode,
+				      struct inode *dir,
+				      const struct qstr *name, u32 cookie);
+
+extern const struct fsnotify_ops inotify_fsnotify_ops;
+extern struct kmem_cache *inotify_inode_mark_cachep;
+
+#ifdef CONFIG_INOTIFY_USER
+static inline void dec_inotify_instances(struct ucounts *ucounts)
+{
+	dec_ucount(ucounts, UCOUNT_INOTIFY_INSTANCES);
+}
+
+static inline struct ucounts *inc_inotify_watches(struct ucounts *ucounts)
+{
+	return inc_ucount(ucounts->ns, ucounts->uid, UCOUNT_INOTIFY_WATCHES);
+}
+
+static inline void dec_inotify_watches(struct ucounts *ucounts)
+{
+	dec_ucount(ucounts, UCOUNT_INOTIFY_WATCHES);
+}
+#endif
diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c
new file mode 100644
index 000000000..7c326ec2e
--- /dev/null
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -0,0 +1,209 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * fs/inotify_user.c - inotify support for userspace
+ *
+ * Authors:
+ *	John McCutchan	<ttb@tentacle.dhs.org>
+ *	Robert Love	<rml@novell.com>
+ *
+ * Copyright (C) 2005 John McCutchan
+ * Copyright 2006 Hewlett-Packard Development Company, L.P.
+ *
+ * Copyright (C) 2009 Eric Paris <Red Hat Inc>
+ * inotify was largely rewritten to make use of the fsnotify infrastructure
+ */
+
+#include <linux/dcache.h> /* d_unlinked */
+#include <linux/fs.h> /* struct inode */
+#include <linux/fsnotify_backend.h>
+#include <linux/inotify.h>
+#include <linux/path.h> /* struct path */
+#include <linux/slab.h> /* kmem_* */
+#include <linux/types.h>
+#include <linux/sched.h>
+#include <linux/sched/user.h>
+#include <linux/sched/mm.h>
+
+#include "inotify.h"
+
+/*
+ * Check if 2 events contain the same information.
+ */
+static bool event_compare(struct fsnotify_event *old_fsn,
+			  struct fsnotify_event *new_fsn)
+{
+	struct inotify_event_info *old, *new;
+
+	old = INOTIFY_E(old_fsn);
+	new = INOTIFY_E(new_fsn);
+	if (old->mask & FS_IN_IGNORED)
+		return false;
+	if ((old->mask == new->mask) &&
+	    (old->wd == new->wd) &&
+	    (old->name_len == new->name_len) &&
+	    (!old->name_len || !strcmp(old->name, new->name)))
+		return true;
+	return false;
+}
+
+static int inotify_merge(struct fsnotify_group *group,
+			 struct fsnotify_event *event)
+{
+	struct list_head *list = &group->notification_list;
+	struct fsnotify_event *last_event;
+
+	last_event = list_entry(list->prev, struct fsnotify_event, list);
+	return event_compare(last_event, event);
+}
+
+int inotify_handle_inode_event(struct fsnotify_mark *inode_mark, u32 mask,
+			       struct inode *inode, struct inode *dir,
+			       const struct qstr *name, u32 cookie)
+{
+	struct inotify_inode_mark *i_mark;
+	struct inotify_event_info *event;
+	struct fsnotify_event *fsn_event;
+	struct fsnotify_group *group = inode_mark->group;
+	int ret;
+	int len = 0, wd;
+	int alloc_len = sizeof(struct inotify_event_info);
+	struct mem_cgroup *old_memcg;
+
+	if (name) {
+		len = name->len;
+		alloc_len += len + 1;
+	}
+
+	pr_debug("%s: group=%p mark=%p mask=%x\n", __func__, group, inode_mark,
+		 mask);
+
+	i_mark = container_of(inode_mark, struct inotify_inode_mark,
+			      fsn_mark);
+
+	/*
+	 * We can be racing with mark being detached. Don't report event with
+	 * invalid wd.
+	 */
+	wd = READ_ONCE(i_mark->wd);
+	if (wd == -1)
+		return 0;
+	/*
+	 * Whoever is interested in the event, pays for the allocation. Do not
+	 * trigger OOM killer in the target monitoring memcg as it may have
+	 * security repercussion.
+	 */
+	old_memcg = set_active_memcg(group->memcg);
+	event = kmalloc(alloc_len, GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL);
+	set_active_memcg(old_memcg);
+
+	if (unlikely(!event)) {
+		/*
+		 * Treat lost event due to ENOMEM the same way as queue
+		 * overflow to let userspace know event was lost.
+		 */
+		fsnotify_queue_overflow(group);
+		return -ENOMEM;
+	}
+
+	/*
+	 * We now report FS_ISDIR flag with MOVE_SELF and DELETE_SELF events
+	 * for fanotify. inotify never reported IN_ISDIR with those events.
+	 * It looks like an oversight, but to avoid the risk of breaking
+	 * existing inotify programs, mask the flag out from those events.
+	 */
+	if (mask & (IN_MOVE_SELF | IN_DELETE_SELF))
+		mask &= ~IN_ISDIR;
+
+	fsn_event = &event->fse;
+	fsnotify_init_event(fsn_event);
+	event->mask = mask;
+	event->wd = wd;
+	event->sync_cookie = cookie;
+	event->name_len = len;
+	if (len)
+		strscpy(event->name, name->name, event->name_len + 1);
+
+	ret = fsnotify_add_event(group, fsn_event, inotify_merge);
+	if (ret) {
+		/* Our event wasn't used in the end. Free it. */
+		fsnotify_destroy_event(group, fsn_event);
+	}
+
+	if (inode_mark->flags & FSNOTIFY_MARK_FLAG_IN_ONESHOT)
+		fsnotify_destroy_mark(inode_mark, group);
+
+	return 0;
+}
+
+static void inotify_freeing_mark(struct fsnotify_mark *fsn_mark, struct fsnotify_group *group)
+{
+	inotify_ignored_and_remove_idr(fsn_mark, group);
+}
+
+/*
+ * This is NEVER supposed to be called.  Inotify marks should either have been
+ * removed from the idr when the watch was removed or in the
+ * fsnotify_destroy_mark_by_group() call when the inotify instance was being
+ * torn down.  This is only called if the idr is about to be freed but there
+ * are still marks in it.
+ */
+static int idr_callback(int id, void *p, void *data)
+{
+	struct fsnotify_mark *fsn_mark;
+	struct inotify_inode_mark *i_mark;
+	static bool warned = false;
+
+	if (warned)
+		return 0;
+
+	warned = true;
+	fsn_mark = p;
+	i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark);
+
+	WARN(1, "inotify closing but id=%d for fsn_mark=%p in group=%p still in "
+		"idr.  Probably leaking memory\n", id, p, data);
+
+	/*
+	 * I'm taking the liberty of assuming that the mark in question is a
+	 * valid address and I'm dereferencing it.  This might help to figure
+	 * out why we got here and the panic is no worse than the original
+	 * BUG() that was here.
+	 */
+	if (fsn_mark)
+		printk(KERN_WARNING "fsn_mark->group=%p wd=%d\n",
+			fsn_mark->group, i_mark->wd);
+	return 0;
+}
+
+static void inotify_free_group_priv(struct fsnotify_group *group)
+{
+	/* ideally the idr is empty and we won't hit the BUG in the callback */
+	idr_for_each(&group->inotify_data.idr, idr_callback, group);
+	idr_destroy(&group->inotify_data.idr);
+	if (group->inotify_data.ucounts)
+		dec_inotify_instances(group->inotify_data.ucounts);
+}
+
+static void inotify_free_event(struct fsnotify_group *group,
+			       struct fsnotify_event *fsn_event)
+{
+	kfree(INOTIFY_E(fsn_event));
+}
+
+/* ding dong the mark is dead */
+static void inotify_free_mark(struct fsnotify_mark *fsn_mark)
+{
+	struct inotify_inode_mark *i_mark;
+
+	i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark);
+
+	kmem_cache_free(inotify_inode_mark_cachep, i_mark);
+}
+
+const struct fsnotify_ops inotify_fsnotify_ops = {
+	.handle_inode_event = inotify_handle_inode_event,
+	.free_group_priv = inotify_free_group_priv,
+	.free_event = inotify_free_event,
+	.freeing_mark = inotify_freeing_mark,
+	.free_mark = inotify_free_mark,
+};
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
new file mode 100644
index 000000000..5f19c24ec
--- /dev/null
+++ b/fs/notify/inotify/inotify_user.c
@@ -0,0 +1,848 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * fs/inotify_user.c - inotify support for userspace
+ *
+ * Authors:
+ *	John McCutchan	<ttb@tentacle.dhs.org>
+ *	Robert Love	<rml@novell.com>
+ *
+ * Copyright (C) 2005 John McCutchan
+ * Copyright 2006 Hewlett-Packard Development Company, L.P.
+ *
+ * Copyright (C) 2009 Eric Paris <Red Hat Inc>
+ * inotify was largely rewriten to make use of the fsnotify infrastructure
+ */
+
+#include <linux/file.h>
+#include <linux/fs.h> /* struct inode */
+#include <linux/fsnotify_backend.h>
+#include <linux/idr.h>
+#include <linux/init.h> /* fs_initcall */
+#include <linux/inotify.h>
+#include <linux/kernel.h> /* roundup() */
+#include <linux/namei.h> /* LOOKUP_FOLLOW */
+#include <linux/sched/signal.h>
+#include <linux/slab.h> /* struct kmem_cache */
+#include <linux/syscalls.h>
+#include <linux/types.h>
+#include <linux/anon_inodes.h>
+#include <linux/uaccess.h>
+#include <linux/poll.h>
+#include <linux/wait.h>
+#include <linux/memcontrol.h>
+#include <linux/security.h>
+
+#include "inotify.h"
+#include "../fdinfo.h"
+
+#include <asm/ioctls.h>
+
+/*
+ * An inotify watch requires allocating an inotify_inode_mark structure as
+ * well as pinning the watched inode. Doubling the size of a VFS inode
+ * should be more than enough to cover the additional filesystem inode
+ * size increase.
+ */
+#define INOTIFY_WATCH_COST	(sizeof(struct inotify_inode_mark) + \
+				 2 * sizeof(struct inode))
+
+/* configurable via /proc/sys/fs/inotify/ */
+static int inotify_max_queued_events __read_mostly;
+
+struct kmem_cache *inotify_inode_mark_cachep __ro_after_init;
+
+#ifdef CONFIG_SYSCTL
+
+#include <linux/sysctl.h>
+
+static long it_zero = 0;
+static long it_int_max = INT_MAX;
+
+static const struct ctl_table inotify_table[] = {
+	{
+		.procname	= "max_user_instances",
+		.data		= &init_user_ns.ucount_max[UCOUNT_INOTIFY_INSTANCES],
+		.maxlen		= sizeof(long),
+		.mode		= 0644,
+		.proc_handler	= proc_doulongvec_minmax,
+		.extra1		= &it_zero,
+		.extra2		= &it_int_max,
+	},
+	{
+		.procname	= "max_user_watches",
+		.data		= &init_user_ns.ucount_max[UCOUNT_INOTIFY_WATCHES],
+		.maxlen		= sizeof(long),
+		.mode		= 0644,
+		.proc_handler	= proc_doulongvec_minmax,
+		.extra1		= &it_zero,
+		.extra2		= &it_int_max,
+	},
+	{
+		.procname	= "max_queued_events",
+		.data		= &inotify_max_queued_events,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO
+	},
+};
+
+static void __init inotify_sysctls_init(void)
+{
+	register_sysctl("fs/inotify", inotify_table);
+}
+
+#else
+#define inotify_sysctls_init() do { } while (0)
+#endif /* CONFIG_SYSCTL */
+
+static inline __u32 inotify_arg_to_mask(struct inode *inode, u32 arg)
+{
+	__u32 mask;
+
+	/*
+	 * Everything should receive events when the inode is unmounted.
+	 * All directories care about children.
+	 */
+	mask = (FS_UNMOUNT);
+	if (S_ISDIR(inode->i_mode))
+		mask |= FS_EVENT_ON_CHILD;
+
+	/* mask off the flags used to open the fd */
+	mask |= (arg & INOTIFY_USER_MASK);
+
+	return mask;
+}
+
+#define INOTIFY_MARK_FLAGS \
+	(FSNOTIFY_MARK_FLAG_EXCL_UNLINK | FSNOTIFY_MARK_FLAG_IN_ONESHOT)
+
+static inline unsigned int inotify_arg_to_flags(u32 arg)
+{
+	unsigned int flags = 0;
+
+	if (arg & IN_EXCL_UNLINK)
+		flags |= FSNOTIFY_MARK_FLAG_EXCL_UNLINK;
+	if (arg & IN_ONESHOT)
+		flags |= FSNOTIFY_MARK_FLAG_IN_ONESHOT;
+
+	return flags;
+}
+
+static inline u32 inotify_mask_to_arg(__u32 mask)
+{
+	return mask & (IN_ALL_EVENTS | IN_ISDIR | IN_UNMOUNT | IN_IGNORED |
+		       IN_Q_OVERFLOW);
+}
+
+/* inotify userspace file descriptor functions */
+static __poll_t inotify_poll(struct file *file, poll_table *wait)
+{
+	struct fsnotify_group *group = file->private_data;
+	__poll_t ret = 0;
+
+	poll_wait(file, &group->notification_waitq, wait);
+	spin_lock(&group->notification_lock);
+	if (!fsnotify_notify_queue_is_empty(group))
+		ret = EPOLLIN | EPOLLRDNORM;
+	spin_unlock(&group->notification_lock);
+
+	return ret;
+}
+
+static int round_event_name_len(struct fsnotify_event *fsn_event)
+{
+	struct inotify_event_info *event;
+
+	event = INOTIFY_E(fsn_event);
+	if (!event->name_len)
+		return 0;
+	return roundup(event->name_len + 1, sizeof(struct inotify_event));
+}
+
+/*
+ * Get an inotify_kernel_event if one exists and is small
+ * enough to fit in "count". Return an error pointer if
+ * not large enough.
+ *
+ * Called with the group->notification_lock held.
+ */
+static struct fsnotify_event *get_one_event(struct fsnotify_group *group,
+					    size_t count)
+{
+	size_t event_size = sizeof(struct inotify_event);
+	struct fsnotify_event *event;
+
+	event = fsnotify_peek_first_event(group);
+	if (!event)
+		return NULL;
+
+	pr_debug("%s: group=%p event=%p\n", __func__, group, event);
+
+	event_size += round_event_name_len(event);
+	if (event_size > count)
+		return ERR_PTR(-EINVAL);
+
+	/* held the notification_lock the whole time, so this is the
+	 * same event we peeked above */
+	fsnotify_remove_first_event(group);
+
+	return event;
+}
+
+/*
+ * Copy an event to user space, returning how much we copied.
+ *
+ * We already checked that the event size is smaller than the
+ * buffer we had in "get_one_event()" above.
+ */
+static ssize_t copy_event_to_user(struct fsnotify_group *group,
+				  struct fsnotify_event *fsn_event,
+				  char __user *buf)
+{
+	struct inotify_event inotify_event;
+	struct inotify_event_info *event;
+	size_t event_size = sizeof(struct inotify_event);
+	size_t name_len;
+	size_t pad_name_len;
+
+	pr_debug("%s: group=%p event=%p\n", __func__, group, fsn_event);
+
+	event = INOTIFY_E(fsn_event);
+	name_len = event->name_len;
+	/*
+	 * round up name length so it is a multiple of event_size
+	 * plus an extra byte for the terminating '\0'.
+	 */
+	pad_name_len = round_event_name_len(fsn_event);
+	inotify_event.len = pad_name_len;
+	inotify_event.mask = inotify_mask_to_arg(event->mask);
+	inotify_event.wd = event->wd;
+	inotify_event.cookie = event->sync_cookie;
+
+	/* send the main event */
+	if (copy_to_user(buf, &inotify_event, event_size))
+		return -EFAULT;
+
+	buf += event_size;
+
+	/*
+	 * fsnotify only stores the pathname, so here we have to send the pathname
+	 * and then pad that pathname out to a multiple of sizeof(inotify_event)
+	 * with zeros.
+	 */
+	if (pad_name_len) {
+		/* copy the path name */
+		if (copy_to_user(buf, event->name, name_len))
+			return -EFAULT;
+		buf += name_len;
+
+		/* fill userspace with 0's */
+		if (clear_user(buf, pad_name_len - name_len))
+			return -EFAULT;
+		event_size += pad_name_len;
+	}
+
+	return event_size;
+}
+
+static ssize_t inotify_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;
+
+	add_wait_queue(&group->notification_waitq, &wait);
+	while (1) {
+		spin_lock(&group->notification_lock);
+		kevent = get_one_event(group, count);
+		spin_unlock(&group->notification_lock);
+
+		pr_debug("%s: group=%p kevent=%p\n", __func__, group, kevent);
+
+		if (kevent) {
+			ret = PTR_ERR(kevent);
+			if (IS_ERR(kevent))
+				break;
+			ret = copy_event_to_user(group, kevent, buf);
+			fsnotify_destroy_event(group, kevent);
+			if (ret < 0)
+				break;
+			buf += ret;
+			count -= ret;
+			continue;
+		}
+
+		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);
+	}
+	remove_wait_queue(&group->notification_waitq, &wait);
+
+	if (start != buf && ret != -EFAULT)
+		ret = buf - start;
+	return ret;
+}
+
+static int inotify_release(struct inode *ignored, struct file *file)
+{
+	struct fsnotify_group *group = file->private_data;
+
+	pr_debug("%s: group=%p\n", __func__, group);
+
+	/* free this group, matching get was inotify_init->fsnotify_obtain_group */
+	fsnotify_destroy_group(group);
+
+	return 0;
+}
+
+static long inotify_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;
+
+	pr_debug("%s: group=%p cmd=%u\n", __func__, group, cmd);
+
+	switch (cmd) {
+	case FIONREAD:
+		spin_lock(&group->notification_lock);
+		list_for_each_entry(fsn_event, &group->notification_list,
+				    list) {
+			send_len += sizeof(struct inotify_event);
+			send_len += round_event_name_len(fsn_event);
+		}
+		spin_unlock(&group->notification_lock);
+		ret = put_user(send_len, (int __user *) p);
+		break;
+#ifdef CONFIG_CHECKPOINT_RESTORE
+	case INOTIFY_IOC_SETNEXTWD:
+		ret = -EINVAL;
+		if (arg >= 1 && arg <= INT_MAX) {
+			struct inotify_group_private_data *data;
+
+			data = &group->inotify_data;
+			spin_lock(&data->idr_lock);
+			idr_set_cursor(&data->idr, (unsigned int)arg);
+			spin_unlock(&data->idr_lock);
+			ret = 0;
+		}
+		break;
+#endif /* CONFIG_CHECKPOINT_RESTORE */
+	}
+
+	return ret;
+}
+
+static const struct file_operations inotify_fops = {
+	.show_fdinfo	= inotify_show_fdinfo,
+	.poll		= inotify_poll,
+	.read		= inotify_read,
+	.fasync		= fsnotify_fasync,
+	.release	= inotify_release,
+	.unlocked_ioctl	= inotify_ioctl,
+	.compat_ioctl	= inotify_ioctl,
+	.llseek		= noop_llseek,
+};
+
+
+/*
+ * find_inode - resolve a user-given path to a specific inode
+ */
+static int inotify_find_inode(const char __user *dirname, struct path *path,
+						unsigned int flags, __u64 mask)
+{
+	int error;
+
+	error = user_path_at(AT_FDCWD, dirname, flags, path);
+	if (error)
+		return error;
+	/* you can only watch an inode if you have read permissions on it */
+	error = path_permission(path, MAY_READ);
+	if (error) {
+		path_put(path);
+		return error;
+	}
+	error = security_path_notify(path, mask,
+				FSNOTIFY_OBJ_TYPE_INODE);
+	if (error)
+		path_put(path);
+
+	return error;
+}
+
+static int inotify_add_to_idr(struct idr *idr, spinlock_t *idr_lock,
+			      struct inotify_inode_mark *i_mark)
+{
+	int ret;
+
+	idr_preload(GFP_KERNEL);
+	spin_lock(idr_lock);
+
+	ret = idr_alloc_cyclic(idr, i_mark, 1, 0, GFP_NOWAIT);
+	if (ret >= 0) {
+		/* we added the mark to the idr, take a reference */
+		i_mark->wd = ret;
+		fsnotify_get_mark(&i_mark->fsn_mark);
+	}
+
+	spin_unlock(idr_lock);
+	idr_preload_end();
+	return ret < 0 ? ret : 0;
+}
+
+static struct inotify_inode_mark *inotify_idr_find_locked(struct fsnotify_group *group,
+								int wd)
+{
+	struct idr *idr = &group->inotify_data.idr;
+	spinlock_t *idr_lock = &group->inotify_data.idr_lock;
+	struct inotify_inode_mark *i_mark;
+
+	assert_spin_locked(idr_lock);
+
+	i_mark = idr_find(idr, wd);
+	if (i_mark) {
+		struct fsnotify_mark *fsn_mark = &i_mark->fsn_mark;
+
+		fsnotify_get_mark(fsn_mark);
+		/* One ref for being in the idr, one ref we just took */
+		BUG_ON(refcount_read(&fsn_mark->refcnt) < 2);
+	}
+
+	return i_mark;
+}
+
+static struct inotify_inode_mark *inotify_idr_find(struct fsnotify_group *group,
+							 int wd)
+{
+	struct inotify_inode_mark *i_mark;
+	spinlock_t *idr_lock = &group->inotify_data.idr_lock;
+
+	spin_lock(idr_lock);
+	i_mark = inotify_idr_find_locked(group, wd);
+	spin_unlock(idr_lock);
+
+	return i_mark;
+}
+
+/*
+ * Remove the mark from the idr (if present) and drop the reference
+ * on the mark because it was in the idr.
+ */
+static void inotify_remove_from_idr(struct fsnotify_group *group,
+				    struct inotify_inode_mark *i_mark)
+{
+	struct idr *idr = &group->inotify_data.idr;
+	spinlock_t *idr_lock = &group->inotify_data.idr_lock;
+	struct inotify_inode_mark *found_i_mark = NULL;
+	int wd;
+
+	spin_lock(idr_lock);
+	wd = i_mark->wd;
+
+	/*
+	 * does this i_mark think it is in the idr?  we shouldn't get called
+	 * if it wasn't....
+	 */
+	if (wd == -1) {
+		WARN_ONCE(1, "%s: i_mark=%p i_mark->wd=%d i_mark->group=%p\n",
+			__func__, i_mark, i_mark->wd, i_mark->fsn_mark.group);
+		goto out;
+	}
+
+	/* Lets look in the idr to see if we find it */
+	found_i_mark = inotify_idr_find_locked(group, wd);
+	if (unlikely(!found_i_mark)) {
+		WARN_ONCE(1, "%s: i_mark=%p i_mark->wd=%d i_mark->group=%p\n",
+			__func__, i_mark, i_mark->wd, i_mark->fsn_mark.group);
+		goto out;
+	}
+
+	/*
+	 * We found an mark in the idr at the right wd, but it's
+	 * not the mark we were told to remove.  eparis seriously
+	 * fucked up somewhere.
+	 */
+	if (unlikely(found_i_mark != i_mark)) {
+		WARN_ONCE(1, "%s: i_mark=%p i_mark->wd=%d i_mark->group=%p "
+			"found_i_mark=%p found_i_mark->wd=%d "
+			"found_i_mark->group=%p\n", __func__, i_mark,
+			i_mark->wd, i_mark->fsn_mark.group, found_i_mark,
+			found_i_mark->wd, found_i_mark->fsn_mark.group);
+		goto out;
+	}
+
+	/*
+	 * One ref for being in the idr
+	 * one ref grabbed by inotify_idr_find
+	 */
+	if (unlikely(refcount_read(&i_mark->fsn_mark.refcnt) < 2)) {
+		printk(KERN_ERR "%s: i_mark=%p i_mark->wd=%d i_mark->group=%p\n",
+			 __func__, i_mark, i_mark->wd, i_mark->fsn_mark.group);
+		/* we can't really recover with bad ref cnting.. */
+		BUG();
+	}
+
+	idr_remove(idr, wd);
+	/* Removed from the idr, drop that ref. */
+	fsnotify_put_mark(&i_mark->fsn_mark);
+out:
+	i_mark->wd = -1;
+	spin_unlock(idr_lock);
+	/* match the ref taken by inotify_idr_find_locked() */
+	if (found_i_mark)
+		fsnotify_put_mark(&found_i_mark->fsn_mark);
+}
+
+/*
+ * Send IN_IGNORED for this wd, remove this wd from the idr.
+ */
+void inotify_ignored_and_remove_idr(struct fsnotify_mark *fsn_mark,
+				    struct fsnotify_group *group)
+{
+	struct inotify_inode_mark *i_mark;
+
+	/* Queue ignore event for the watch */
+	inotify_handle_inode_event(fsn_mark, FS_IN_IGNORED, NULL, NULL, NULL,
+				   0);
+
+	i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark);
+	/* remove this mark from the idr */
+	inotify_remove_from_idr(group, i_mark);
+
+	dec_inotify_watches(group->inotify_data.ucounts);
+}
+
+static int inotify_update_existing_watch(struct fsnotify_group *group,
+					 struct inode *inode,
+					 u32 arg)
+{
+	struct fsnotify_mark *fsn_mark;
+	struct inotify_inode_mark *i_mark;
+	int replace = !(arg & IN_MASK_ADD);
+	int create = (arg & IN_MASK_CREATE);
+	int ret;
+
+	fsn_mark = fsnotify_find_inode_mark(inode, group);
+	if (!fsn_mark)
+		return -ENOENT;
+	else if (create) {
+		ret = -EEXIST;
+		goto out;
+	}
+
+	i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark);
+
+	spin_lock(&fsn_mark->lock);
+	if (replace) {
+		fsn_mark->mask = 0;
+		fsn_mark->flags &= ~INOTIFY_MARK_FLAGS;
+	}
+	fsn_mark->mask |= inotify_arg_to_mask(inode, arg);
+	fsn_mark->flags |= inotify_arg_to_flags(arg);
+	spin_unlock(&fsn_mark->lock);
+
+	fsnotify_recalc_mask(fsn_mark->connector);
+
+	/* return the wd */
+	ret = i_mark->wd;
+
+out:
+	/* match the get from fsnotify_find_mark() */
+	fsnotify_put_mark(fsn_mark);
+
+	return ret;
+}
+
+static int inotify_new_watch(struct fsnotify_group *group,
+			     struct inode *inode,
+			     u32 arg)
+{
+	struct inotify_inode_mark *tmp_i_mark;
+	int ret;
+	struct idr *idr = &group->inotify_data.idr;
+	spinlock_t *idr_lock = &group->inotify_data.idr_lock;
+
+	tmp_i_mark = kmem_cache_alloc(inotify_inode_mark_cachep, GFP_KERNEL);
+	if (unlikely(!tmp_i_mark))
+		return -ENOMEM;
+
+	fsnotify_init_mark(&tmp_i_mark->fsn_mark, group);
+	tmp_i_mark->fsn_mark.mask = inotify_arg_to_mask(inode, arg);
+	tmp_i_mark->fsn_mark.flags = inotify_arg_to_flags(arg);
+	tmp_i_mark->wd = -1;
+
+	ret = inotify_add_to_idr(idr, idr_lock, tmp_i_mark);
+	if (ret)
+		goto out_err;
+
+	/* increment the number of watches the user has */
+	if (!inc_inotify_watches(group->inotify_data.ucounts)) {
+		inotify_remove_from_idr(group, tmp_i_mark);
+		ret = -ENOSPC;
+		goto out_err;
+	}
+
+	/* we are on the idr, now get on the inode */
+	ret = fsnotify_add_inode_mark_locked(&tmp_i_mark->fsn_mark, inode, 0);
+	if (ret) {
+		/* we failed to get on the inode, get off the idr */
+		inotify_remove_from_idr(group, tmp_i_mark);
+		dec_inotify_watches(group->inotify_data.ucounts);
+		goto out_err;
+	}
+
+
+	/* return the watch descriptor for this new mark */
+	ret = tmp_i_mark->wd;
+
+out_err:
+	/* match the ref from fsnotify_init_mark() */
+	fsnotify_put_mark(&tmp_i_mark->fsn_mark);
+
+	return ret;
+}
+
+static int inotify_update_watch(struct fsnotify_group *group, struct inode *inode, u32 arg)
+{
+	int ret = 0;
+
+	fsnotify_group_lock(group);
+	/* try to update and existing watch with the new arg */
+	ret = inotify_update_existing_watch(group, inode, arg);
+	/* no mark present, try to add a new one */
+	if (ret == -ENOENT)
+		ret = inotify_new_watch(group, inode, arg);
+	fsnotify_group_unlock(group);
+
+	return ret;
+}
+
+static struct fsnotify_group *inotify_new_group(unsigned int max_events)
+{
+	struct fsnotify_group *group;
+	struct inotify_event_info *oevent;
+
+	group = fsnotify_alloc_group(&inotify_fsnotify_ops,
+				     FSNOTIFY_GROUP_USER);
+	if (IS_ERR(group))
+		return group;
+
+	oevent = kmalloc_obj(struct inotify_event_info, GFP_KERNEL_ACCOUNT);
+	if (unlikely(!oevent)) {
+		fsnotify_destroy_group(group);
+		return ERR_PTR(-ENOMEM);
+	}
+	group->overflow_event = &oevent->fse;
+	fsnotify_init_event(group->overflow_event);
+	oevent->mask = FS_Q_OVERFLOW;
+	oevent->wd = -1;
+	oevent->sync_cookie = 0;
+	oevent->name_len = 0;
+
+	group->max_events = max_events;
+	group->memcg = get_mem_cgroup_from_mm(current->mm);
+
+	spin_lock_init(&group->inotify_data.idr_lock);
+	idr_init(&group->inotify_data.idr);
+	group->inotify_data.ucounts = inc_ucount(current_user_ns(),
+						 current_euid(),
+						 UCOUNT_INOTIFY_INSTANCES);
+
+	if (!group->inotify_data.ucounts) {
+		fsnotify_destroy_group(group);
+		return ERR_PTR(-EMFILE);
+	}
+
+	return group;
+}
+
+
+/* inotify syscalls */
+static int do_inotify_init(int flags)
+{
+	struct fsnotify_group *group;
+	int ret;
+
+	/* Check the IN_* constants for consistency.  */
+	BUILD_BUG_ON(IN_CLOEXEC != O_CLOEXEC);
+	BUILD_BUG_ON(IN_NONBLOCK != O_NONBLOCK);
+
+	if (flags & ~(IN_CLOEXEC | IN_NONBLOCK))
+		return -EINVAL;
+
+	/* fsnotify_obtain_group took a reference to group, we put this when we kill the file in the end */
+	group = inotify_new_group(inotify_max_queued_events);
+	if (IS_ERR(group))
+		return PTR_ERR(group);
+
+	ret = anon_inode_getfd("inotify", &inotify_fops, group,
+				  O_RDONLY | flags);
+	if (ret < 0)
+		fsnotify_destroy_group(group);
+
+	return ret;
+}
+
+SYSCALL_DEFINE1(inotify_init1, int, flags)
+{
+	return do_inotify_init(flags);
+}
+
+SYSCALL_DEFINE0(inotify_init)
+{
+	return do_inotify_init(0);
+}
+
+SYSCALL_DEFINE3(inotify_add_watch, int, fd, const char __user *, pathname,
+		u32, mask)
+{
+	struct fsnotify_group *group;
+	struct inode *inode;
+	struct path path;
+	int ret;
+	unsigned flags = 0;
+
+	/*
+	 * We share a lot of code with fs/dnotify.  We also share
+	 * the bit layout between inotify's IN_* and the fsnotify
+	 * FS_*.  This check ensures that only the inotify IN_*
+	 * bits get passed in and set in watches/events.
+	 */
+	if (unlikely(mask & ~ALL_INOTIFY_BITS))
+		return -EINVAL;
+	/*
+	 * Require at least one valid bit set in the mask.
+	 * Without _something_ set, we would have no events to
+	 * watch for.
+	 */
+	if (unlikely(!(mask & ALL_INOTIFY_BITS)))
+		return -EINVAL;
+
+	CLASS(fd, f)(fd);
+	if (fd_empty(f))
+		return -EBADF;
+
+	/* IN_MASK_ADD and IN_MASK_CREATE don't make sense together */
+	if (unlikely((mask & IN_MASK_ADD) && (mask & IN_MASK_CREATE)))
+		return -EINVAL;
+
+	/* verify that this is indeed an inotify instance */
+	if (unlikely(fd_file(f)->f_op != &inotify_fops))
+		return -EINVAL;
+
+	if (!(mask & IN_DONT_FOLLOW))
+		flags |= LOOKUP_FOLLOW;
+	if (mask & IN_ONLYDIR)
+		flags |= LOOKUP_DIRECTORY;
+
+	ret = inotify_find_inode(pathname, &path, flags,
+			(mask & IN_ALL_EVENTS));
+	if (ret)
+		return ret;
+
+	/* inode held in place by reference to path; group by fget on fd */
+	inode = path.dentry->d_inode;
+	group = fd_file(f)->private_data;
+
+	/* create/update an inode mark */
+	ret = inotify_update_watch(group, inode, mask);
+	path_put(&path);
+	return ret;
+}
+
+SYSCALL_DEFINE2(inotify_rm_watch, int, fd, __s32, wd)
+{
+	struct fsnotify_group *group;
+	struct inotify_inode_mark *i_mark;
+	CLASS(fd, f)(fd);
+
+	if (fd_empty(f))
+		return -EBADF;
+
+	/* verify that this is indeed an inotify instance */
+	if (unlikely(fd_file(f)->f_op != &inotify_fops))
+		return -EINVAL;
+
+	group = fd_file(f)->private_data;
+
+	i_mark = inotify_idr_find(group, wd);
+	if (unlikely(!i_mark))
+		return -EINVAL;
+
+	fsnotify_destroy_mark(&i_mark->fsn_mark, group);
+
+	/* match ref taken by inotify_idr_find */
+	fsnotify_put_mark(&i_mark->fsn_mark);
+	return 0;
+}
+
+/*
+ * inotify_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 inotify_user_setup(void)
+{
+	unsigned long watches_max;
+	struct sysinfo si;
+
+	si_meminfo(&si);
+	/*
+	 * Allow up to 1% of addressable memory to be allocated for inotify
+	 * watches (per user) limited to the range [8192, 1048576].
+	 */
+	watches_max = (((si.totalram - si.totalhigh) / 100) << PAGE_SHIFT) /
+			INOTIFY_WATCH_COST;
+	watches_max = clamp(watches_max, 8192UL, 1048576UL);
+
+	BUILD_BUG_ON(IN_ACCESS != FS_ACCESS);
+	BUILD_BUG_ON(IN_MODIFY != FS_MODIFY);
+	BUILD_BUG_ON(IN_ATTRIB != FS_ATTRIB);
+	BUILD_BUG_ON(IN_CLOSE_WRITE != FS_CLOSE_WRITE);
+	BUILD_BUG_ON(IN_CLOSE_NOWRITE != FS_CLOSE_NOWRITE);
+	BUILD_BUG_ON(IN_OPEN != FS_OPEN);
+	BUILD_BUG_ON(IN_MOVED_FROM != FS_MOVED_FROM);
+	BUILD_BUG_ON(IN_MOVED_TO != FS_MOVED_TO);
+	BUILD_BUG_ON(IN_CREATE != FS_CREATE);
+	BUILD_BUG_ON(IN_DELETE != FS_DELETE);
+	BUILD_BUG_ON(IN_DELETE_SELF != FS_DELETE_SELF);
+	BUILD_BUG_ON(IN_MOVE_SELF != FS_MOVE_SELF);
+	BUILD_BUG_ON(IN_UNMOUNT != FS_UNMOUNT);
+	BUILD_BUG_ON(IN_Q_OVERFLOW != FS_Q_OVERFLOW);
+	BUILD_BUG_ON(IN_IGNORED != FS_IN_IGNORED);
+	BUILD_BUG_ON(IN_ISDIR != FS_ISDIR);
+
+	BUILD_BUG_ON(HWEIGHT32(ALL_INOTIFY_BITS) != 22);
+
+	inotify_inode_mark_cachep = KMEM_CACHE(inotify_inode_mark,
+					       SLAB_PANIC|SLAB_ACCOUNT);
+
+	inotify_max_queued_events = 16384;
+	init_user_ns.ucount_max[UCOUNT_INOTIFY_INSTANCES] = 128;
+	init_user_ns.ucount_max[UCOUNT_INOTIFY_WATCHES] = watches_max;
+	inotify_sysctls_init();
+
+	return 0;
+}
+fs_initcall(inotify_user_setup);