Resguardo inicial

linux-7.2.3/fs/notify/Kconfig

@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config FSNOTIFY
+	def_bool n
+
+source "fs/notify/dnotify/Kconfig"
+source "fs/notify/inotify/Kconfig"
+source "fs/notify/fanotify/Kconfig"

linux-7.2.3/fs/notify/Makefile

@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_FSNOTIFY)		+= fsnotify.o notification.o group.o mark.o \
+				   fdinfo.o
+
+obj-y			+= dnotify/
+obj-y			+= inotify/
+obj-y			+= fanotify/

linux-7.2.3/fs/notify/dnotify/Kconfig

@@ -0,0 +1,12 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config DNOTIFY
+	bool "Dnotify support"
+	select FSNOTIFY
+	default y
+	help
+	  Dnotify is a directory-based per-fd file change notification system
+	  that uses signals to communicate events to user-space.  There exist
+	  superior alternatives, but some applications may still rely on
+	  dnotify.
+
+	  If unsure, say Y.

linux-7.2.3/fs/notify/dnotify/Makefile

@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_DNOTIFY)		+= dnotify.o

linux-7.2.3/fs/notify/dnotify/dnotify.c

@@ -0,0 +1,413 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Directory notifications for Linux.
+ *
+ * Copyright (C) 2000,2001,2002 Stephen Rothwell
+ *
+ * Copyright (C) 2009 Eric Paris <Red Hat Inc>
+ * dnotify was largly rewritten to use the new fsnotify infrastructure
+ */
+#include <linux/fs.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/sched/signal.h>
+#include <linux/dnotify.h>
+#include <linux/init.h>
+#include <linux/security.h>
+#include <linux/spinlock.h>
+#include <linux/slab.h>
+#include <linux/fsnotify_backend.h>
+
+static int dir_notify_enable __read_mostly = 1;
+#ifdef CONFIG_SYSCTL
+static const struct ctl_table dnotify_sysctls[] = {
+	{
+		.procname	= "dir-notify-enable",
+		.data		= &dir_notify_enable,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+};
+static void __init dnotify_sysctl_init(void)
+{
+	register_sysctl_init("fs", dnotify_sysctls);
+}
+#else
+#define dnotify_sysctl_init() do { } while (0)
+#endif
+
+static struct kmem_cache *dnotify_struct_cache __ro_after_init;
+static struct kmem_cache *dnotify_mark_cache __ro_after_init;
+static struct fsnotify_group *dnotify_group __ro_after_init;
+
+/*
+ * dnotify will attach one of these to each inode (i_fsnotify_marks) which
+ * is being watched by dnotify.  If multiple userspace applications are watching
+ * the same directory with dnotify their information is chained in dn
+ */
+struct dnotify_mark {
+	struct fsnotify_mark fsn_mark;
+	struct dnotify_struct *dn;
+};
+
+/*
+ * When a process starts or stops watching an inode the set of events which
+ * dnotify cares about for that inode may change.  This function runs the
+ * list of everything receiving dnotify events about this directory and calculates
+ * the set of all those events.  After it updates what dnotify is interested in
+ * it calls the fsnotify function so it can update the set of all events relevant
+ * to this inode.
+ */
+static void dnotify_recalc_inode_mask(struct fsnotify_mark *fsn_mark)
+{
+	__u32 new_mask = 0;
+	struct dnotify_struct *dn;
+	struct dnotify_mark *dn_mark  = container_of(fsn_mark,
+						     struct dnotify_mark,
+						     fsn_mark);
+
+	assert_spin_locked(&fsn_mark->lock);
+
+	for (dn = dn_mark->dn; dn != NULL; dn = dn->dn_next)
+		new_mask |= (dn->dn_mask & ~FS_DN_MULTISHOT);
+	if (fsn_mark->mask == new_mask)
+		return;
+	fsn_mark->mask = new_mask;
+
+	fsnotify_recalc_mask(fsn_mark->connector);
+}
+
+/*
+ * Mains fsnotify call where events are delivered to dnotify.
+ * Find the dnotify mark on the relevant inode, run the list of dnotify structs
+ * on that mark and determine which of them has expressed interest in receiving
+ * events of this type.  When found send the correct process and signal and
+ * destroy the dnotify struct if it was not registered to receive multiple
+ * events.
+ */
+static int dnotify_handle_event(struct fsnotify_mark *inode_mark, u32 mask,
+				struct inode *inode, struct inode *dir,
+				const struct qstr *name, u32 cookie)
+{
+	struct dnotify_mark *dn_mark;
+	struct dnotify_struct *dn;
+	struct dnotify_struct **prev;
+	struct fown_struct *fown;
+	__u32 test_mask = mask & ~FS_EVENT_ON_CHILD;
+
+	/* not a dir, dnotify doesn't care */
+	if (!dir && !(mask & FS_ISDIR))
+		return 0;
+
+	dn_mark = container_of(inode_mark, struct dnotify_mark, fsn_mark);
+
+	spin_lock(&inode_mark->lock);
+	prev = &dn_mark->dn;
+	while ((dn = *prev) != NULL) {
+		if ((dn->dn_mask & test_mask) == 0) {
+			prev = &dn->dn_next;
+			continue;
+		}
+		fown = file_f_owner(dn->dn_filp);
+		send_sigio(fown, dn->dn_fd, POLL_MSG);
+		if (dn->dn_mask & FS_DN_MULTISHOT)
+			prev = &dn->dn_next;
+		else {
+			*prev = dn->dn_next;
+			kmem_cache_free(dnotify_struct_cache, dn);
+			dnotify_recalc_inode_mask(inode_mark);
+		}
+	}
+
+	spin_unlock(&inode_mark->lock);
+
+	return 0;
+}
+
+static void dnotify_free_mark(struct fsnotify_mark *fsn_mark)
+{
+	struct dnotify_mark *dn_mark = container_of(fsn_mark,
+						    struct dnotify_mark,
+						    fsn_mark);
+
+	BUG_ON(dn_mark->dn);
+
+	kmem_cache_free(dnotify_mark_cache, dn_mark);
+}
+
+static const struct fsnotify_ops dnotify_fsnotify_ops = {
+	.handle_inode_event = dnotify_handle_event,
+	.free_mark = dnotify_free_mark,
+};
+
+/*
+ * Called every time a file is closed.  Looks first for a dnotify mark on the
+ * inode.  If one is found run all of the ->dn structures attached to that
+ * mark for one relevant to this process closing the file and remove that
+ * dnotify_struct.  If that was the last dnotify_struct also remove the
+ * fsnotify_mark.
+ */
+void dnotify_flush(struct file *filp, fl_owner_t id)
+{
+	struct fsnotify_mark *fsn_mark;
+	struct dnotify_mark *dn_mark;
+	struct dnotify_struct *dn;
+	struct dnotify_struct **prev;
+	struct inode *inode;
+	bool free = false;
+
+	inode = file_inode(filp);
+	if (!S_ISDIR(inode->i_mode))
+		return;
+
+	fsn_mark = fsnotify_find_inode_mark(inode, dnotify_group);
+	if (!fsn_mark)
+		return;
+	dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark);
+
+	fsnotify_group_lock(dnotify_group);
+
+	spin_lock(&fsn_mark->lock);
+	prev = &dn_mark->dn;
+	while ((dn = *prev) != NULL) {
+		if ((dn->dn_owner == id) && (dn->dn_filp == filp)) {
+			*prev = dn->dn_next;
+			kmem_cache_free(dnotify_struct_cache, dn);
+			dnotify_recalc_inode_mask(fsn_mark);
+			break;
+		}
+		prev = &dn->dn_next;
+	}
+
+	spin_unlock(&fsn_mark->lock);
+
+	/* nothing else could have found us thanks to the dnotify_groups
+	   mark_mutex */
+	if (dn_mark->dn == NULL) {
+		fsnotify_detach_mark(fsn_mark);
+		free = true;
+	}
+
+	fsnotify_group_unlock(dnotify_group);
+
+	if (free)
+		fsnotify_free_mark(fsn_mark);
+	fsnotify_put_mark(fsn_mark);
+}
+
+/* this conversion is done only at watch creation */
+static __u32 convert_arg(unsigned int arg)
+{
+	__u32 new_mask = FS_EVENT_ON_CHILD;
+
+	if (arg & DN_MULTISHOT)
+		new_mask |= FS_DN_MULTISHOT;
+	if (arg & DN_DELETE)
+		new_mask |= (FS_DELETE | FS_MOVED_FROM);
+	if (arg & DN_MODIFY)
+		new_mask |= FS_MODIFY;
+	if (arg & DN_ACCESS)
+		new_mask |= FS_ACCESS;
+	if (arg & DN_ATTRIB)
+		new_mask |= FS_ATTRIB;
+	if (arg & DN_RENAME)
+		new_mask |= FS_RENAME;
+	if (arg & DN_CREATE)
+		new_mask |= (FS_CREATE | FS_MOVED_TO);
+
+	return new_mask;
+}
+
+/*
+ * If multiple processes watch the same inode with dnotify there is only one
+ * dnotify mark in inode->i_fsnotify_marks but we chain a dnotify_struct
+ * onto that mark.  This function either attaches the new dnotify_struct onto
+ * that list, or it |= the mask onto an existing dnofiy_struct.
+ */
+static int attach_dn(struct dnotify_struct *dn, struct dnotify_mark *dn_mark,
+		     fl_owner_t id, int fd, struct file *filp, __u32 mask)
+{
+	struct dnotify_struct *odn;
+
+	odn = dn_mark->dn;
+	while (odn != NULL) {
+		/* adding more events to existing dnofiy_struct? */
+		if ((odn->dn_owner == id) && (odn->dn_filp == filp)) {
+			odn->dn_fd = fd;
+			odn->dn_mask |= mask;
+			return -EEXIST;
+		}
+		odn = odn->dn_next;
+	}
+
+	dn->dn_mask = mask;
+	dn->dn_fd = fd;
+	dn->dn_filp = filp;
+	dn->dn_owner = id;
+	dn->dn_next = dn_mark->dn;
+	dn_mark->dn = dn;
+
+	return 0;
+}
+
+/*
+ * When a process calls fcntl to attach a dnotify watch to a directory it ends
+ * up here.  Allocate both a mark for fsnotify to add and a dnotify_struct to be
+ * attached to the fsnotify_mark.
+ */
+int fcntl_dirnotify(int fd, struct file *filp, unsigned int arg)
+{
+	struct dnotify_mark *new_dn_mark, *dn_mark;
+	struct fsnotify_mark *new_fsn_mark, *fsn_mark;
+	struct dnotify_struct *dn;
+	struct inode *inode;
+	fl_owner_t id = current->files;
+	struct file *f = NULL;
+	int destroy = 0, error = 0;
+	__u32 mask;
+
+	/* we use these to tell if we need to kfree */
+	new_fsn_mark = NULL;
+	dn = NULL;
+
+	if (!dir_notify_enable) {
+		error = -EINVAL;
+		goto out_err;
+	}
+
+	/* a 0 mask means we are explicitly removing the watch */
+	if ((arg & ~DN_MULTISHOT) == 0) {
+		dnotify_flush(filp, id);
+		error = 0;
+		goto out_err;
+	}
+
+	/* dnotify only works on directories */
+	inode = file_inode(filp);
+	if (!S_ISDIR(inode->i_mode)) {
+		error = -ENOTDIR;
+		goto out_err;
+	}
+
+	/*
+	 * convert the userspace DN_* "arg" to the internal FS_*
+	 * defined in fsnotify
+	 */
+	mask = convert_arg(arg);
+
+	error = security_path_notify(&filp->f_path, mask,
+			FSNOTIFY_OBJ_TYPE_INODE);
+	if (error)
+		goto out_err;
+
+	/* expect most fcntl to add new rather than augment old */
+	dn = kmem_cache_alloc(dnotify_struct_cache, GFP_KERNEL);
+	if (!dn) {
+		error = -ENOMEM;
+		goto out_err;
+	}
+
+	error = file_f_owner_allocate(filp);
+	if (error)
+		goto out_err;
+
+	/* new fsnotify mark, we expect most fcntl calls to add a new mark */
+	new_dn_mark = kmem_cache_alloc(dnotify_mark_cache, GFP_KERNEL);
+	if (!new_dn_mark) {
+		error = -ENOMEM;
+		goto out_err;
+	}
+
+	/* set up the new_fsn_mark and new_dn_mark */
+	new_fsn_mark = &new_dn_mark->fsn_mark;
+	fsnotify_init_mark(new_fsn_mark, dnotify_group);
+	new_fsn_mark->mask = mask;
+	new_dn_mark->dn = NULL;
+
+	/* this is needed to prevent the fcntl/close race described below */
+	fsnotify_group_lock(dnotify_group);
+
+	/* add the new_fsn_mark or find an old one. */
+	fsn_mark = fsnotify_find_inode_mark(inode, dnotify_group);
+	if (fsn_mark) {
+		dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark);
+		spin_lock(&fsn_mark->lock);
+	} else {
+		error = fsnotify_add_inode_mark_locked(new_fsn_mark, inode, 0);
+		if (error) {
+			fsnotify_group_unlock(dnotify_group);
+			goto out_err;
+		}
+		spin_lock(&new_fsn_mark->lock);
+		fsn_mark = new_fsn_mark;
+		dn_mark = new_dn_mark;
+		/* we used new_fsn_mark, so don't free it */
+		new_fsn_mark = NULL;
+	}
+
+	f = fget_raw(fd);
+
+	/* if (f != filp) means that we lost a race and another task/thread
+	 * actually closed the fd we are still playing with before we grabbed
+	 * the dnotify_groups mark_mutex and fsn_mark->lock.  Since closing the
+	 * fd is the only time we clean up the marks we need to get our mark
+	 * off the list. */
+	if (f != filp) {
+		/* if we added ourselves, shoot ourselves, it's possible that
+		 * the flush actually did shoot this fsn_mark.  That's fine too
+		 * since multiple calls to destroy_mark is perfectly safe, if
+		 * we found a dn_mark already attached to the inode, just sod
+		 * off silently as the flush at close time dealt with it.
+		 */
+		if (dn_mark == new_dn_mark)
+			destroy = 1;
+		error = 0;
+		goto out;
+	}
+
+	__f_setown(filp, task_pid(current), PIDTYPE_TGID, 0);
+
+	error = attach_dn(dn, dn_mark, id, fd, filp, mask);
+	/* !error means that we attached the dn to the dn_mark, so don't free it */
+	if (!error)
+		dn = NULL;
+	/* -EEXIST means that we didn't add this new dn and used an old one.
+	 * that isn't an error (and the unused dn should be freed) */
+	else if (error == -EEXIST)
+		error = 0;
+
+	dnotify_recalc_inode_mask(fsn_mark);
+out:
+	spin_unlock(&fsn_mark->lock);
+
+	if (destroy)
+		fsnotify_detach_mark(fsn_mark);
+	fsnotify_group_unlock(dnotify_group);
+	if (destroy)
+		fsnotify_free_mark(fsn_mark);
+	fsnotify_put_mark(fsn_mark);
+out_err:
+	if (new_fsn_mark)
+		fsnotify_put_mark(new_fsn_mark);
+	if (dn)
+		kmem_cache_free(dnotify_struct_cache, dn);
+	if (f)
+		fput(f);
+	return error;
+}
+
+static int __init dnotify_init(void)
+{
+	dnotify_struct_cache = KMEM_CACHE(dnotify_struct,
+					  SLAB_PANIC|SLAB_ACCOUNT);
+	dnotify_mark_cache = KMEM_CACHE(dnotify_mark, SLAB_PANIC|SLAB_ACCOUNT);
+
+	dnotify_group = fsnotify_alloc_group(&dnotify_fsnotify_ops, 0);
+	if (IS_ERR(dnotify_group))
+		panic("unable to allocate fsnotify group for dnotify\n");
+	dnotify_sysctl_init();
+	return 0;
+}
+
+module_init(dnotify_init)

linux-7.2.3/fs/notify/fanotify/Kconfig

@@ -0,0 +1,26 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config FANOTIFY
+	bool "Filesystem wide access notification"
+	select FSNOTIFY
+	select EXPORTFS
+	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
+	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 management systems.
+
+	   If unsure, say N.

linux-7.2.3/fs/notify/fanotify/Makefile

@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_FANOTIFY)		+= fanotify.o fanotify_user.o

linux-7.2.3/fs/notify/fanotify/fanotify.h

@@ -0,0 +1,555 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/fsnotify_backend.h>
+#include <linux/path.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/exportfs.h>
+#include <linux/hashtable.h>
+
+extern struct kmem_cache *fanotify_mark_cache;
+extern struct kmem_cache *fanotify_fid_event_cachep;
+extern struct kmem_cache *fanotify_path_event_cachep;
+extern struct kmem_cache *fanotify_perm_event_cachep;
+extern struct kmem_cache *fanotify_mnt_event_cachep;
+
+/* Possible states of the permission event */
+enum {
+	FAN_EVENT_INIT,
+	FAN_EVENT_REPORTED,
+	FAN_EVENT_ANSWERED,
+	FAN_EVENT_CANCELED,
+};
+
+/*
+ * 3 dwords are sufficient for most local fs (64bit ino, 32bit generation).
+ * fh buf should be dword aligned. On 64bit arch, the ext_buf pointer is
+ * stored in either the first or last 2 dwords.
+ */
+#define FANOTIFY_INLINE_FH_LEN	(3 << 2)
+#define FANOTIFY_FH_HDR_LEN	sizeof(struct fanotify_fh)
+
+/* Fixed size struct for file handle */
+struct fanotify_fh {
+	u8 type;
+	u8 len;
+#define FANOTIFY_FH_FLAG_EXT_BUF 1
+	u8 flags;
+	u8 pad;
+} __aligned(4);
+
+/* Variable size struct for dir file handle + child file handle + name */
+struct fanotify_info {
+	/* size of dir_fh/file_fh including fanotify_fh hdr size */
+	u8 dir_fh_totlen;
+	u8 dir2_fh_totlen;
+	u8 file_fh_totlen;
+	u8 name_len;
+	u8 name2_len;
+	u8 pad[3];
+	unsigned char buf[];
+	/*
+	 * (struct fanotify_fh) dir_fh starts at buf[0]
+	 * (optional) dir2_fh starts at buf[dir_fh_totlen]
+	 * (optional) file_fh starts at buf[dir_fh_totlen + dir2_fh_totlen]
+	 * name starts at buf[dir_fh_totlen + dir2_fh_totlen + file_fh_totlen]
+	 * ...
+	 */
+#define FANOTIFY_DIR_FH_SIZE(info)	((info)->dir_fh_totlen)
+#define FANOTIFY_DIR2_FH_SIZE(info)	((info)->dir2_fh_totlen)
+#define FANOTIFY_FILE_FH_SIZE(info)	((info)->file_fh_totlen)
+#define FANOTIFY_NAME_SIZE(info)	((info)->name_len + 1)
+#define FANOTIFY_NAME2_SIZE(info)	((info)->name2_len + 1)
+
+#define FANOTIFY_DIR_FH_OFFSET(info)	0
+#define FANOTIFY_DIR2_FH_OFFSET(info) \
+	(FANOTIFY_DIR_FH_OFFSET(info) + FANOTIFY_DIR_FH_SIZE(info))
+#define FANOTIFY_FILE_FH_OFFSET(info) \
+	(FANOTIFY_DIR2_FH_OFFSET(info) + FANOTIFY_DIR2_FH_SIZE(info))
+#define FANOTIFY_NAME_OFFSET(info) \
+	(FANOTIFY_FILE_FH_OFFSET(info) + FANOTIFY_FILE_FH_SIZE(info))
+#define FANOTIFY_NAME2_OFFSET(info) \
+	(FANOTIFY_NAME_OFFSET(info) + FANOTIFY_NAME_SIZE(info))
+
+#define FANOTIFY_DIR_FH_BUF(info) \
+	((info)->buf + FANOTIFY_DIR_FH_OFFSET(info))
+#define FANOTIFY_DIR2_FH_BUF(info) \
+	((info)->buf + FANOTIFY_DIR2_FH_OFFSET(info))
+#define FANOTIFY_FILE_FH_BUF(info) \
+	((info)->buf + FANOTIFY_FILE_FH_OFFSET(info))
+#define FANOTIFY_NAME_BUF(info) \
+	((info)->buf + FANOTIFY_NAME_OFFSET(info))
+#define FANOTIFY_NAME2_BUF(info) \
+	((info)->buf + FANOTIFY_NAME2_OFFSET(info))
+} __aligned(4);
+
+static inline bool fanotify_fh_has_ext_buf(struct fanotify_fh *fh)
+{
+	return (fh->flags & FANOTIFY_FH_FLAG_EXT_BUF);
+}
+
+static inline char **fanotify_fh_ext_buf_ptr(struct fanotify_fh *fh)
+{
+	BUILD_BUG_ON(FANOTIFY_FH_HDR_LEN % 4);
+	BUILD_BUG_ON(__alignof__(char *) - 4 + sizeof(char *) >
+		     FANOTIFY_INLINE_FH_LEN);
+	return (char **)ALIGN((unsigned long)(fh + 1), __alignof__(char *));
+}
+
+static inline void *fanotify_fh_ext_buf(struct fanotify_fh *fh)
+{
+	return *fanotify_fh_ext_buf_ptr(fh);
+}
+
+static inline void *fanotify_fh_buf(struct fanotify_fh *fh)
+{
+	return fanotify_fh_has_ext_buf(fh) ? fanotify_fh_ext_buf(fh) : fh + 1;
+}
+
+static inline int fanotify_info_dir_fh_len(struct fanotify_info *info)
+{
+	if (!info->dir_fh_totlen ||
+	    WARN_ON_ONCE(info->dir_fh_totlen < FANOTIFY_FH_HDR_LEN))
+		return 0;
+
+	return info->dir_fh_totlen - FANOTIFY_FH_HDR_LEN;
+}
+
+static inline struct fanotify_fh *fanotify_info_dir_fh(struct fanotify_info *info)
+{
+	BUILD_BUG_ON(offsetof(struct fanotify_info, buf) % 4);
+
+	return (struct fanotify_fh *)FANOTIFY_DIR_FH_BUF(info);
+}
+
+static inline int fanotify_info_dir2_fh_len(struct fanotify_info *info)
+{
+	if (!info->dir2_fh_totlen ||
+	    WARN_ON_ONCE(info->dir2_fh_totlen < FANOTIFY_FH_HDR_LEN))
+		return 0;
+
+	return info->dir2_fh_totlen - FANOTIFY_FH_HDR_LEN;
+}
+
+static inline struct fanotify_fh *fanotify_info_dir2_fh(struct fanotify_info *info)
+{
+	return (struct fanotify_fh *)FANOTIFY_DIR2_FH_BUF(info);
+}
+
+static inline int fanotify_info_file_fh_len(struct fanotify_info *info)
+{
+	if (!info->file_fh_totlen ||
+	    WARN_ON_ONCE(info->file_fh_totlen < FANOTIFY_FH_HDR_LEN))
+		return 0;
+
+	return info->file_fh_totlen - FANOTIFY_FH_HDR_LEN;
+}
+
+static inline struct fanotify_fh *fanotify_info_file_fh(struct fanotify_info *info)
+{
+	return (struct fanotify_fh *)FANOTIFY_FILE_FH_BUF(info);
+}
+
+static inline char *fanotify_info_name(struct fanotify_info *info)
+{
+	if (!info->name_len)
+		return NULL;
+
+	return FANOTIFY_NAME_BUF(info);
+}
+
+static inline char *fanotify_info_name2(struct fanotify_info *info)
+{
+	if (!info->name2_len)
+		return NULL;
+
+	return FANOTIFY_NAME2_BUF(info);
+}
+
+static inline void fanotify_info_init(struct fanotify_info *info)
+{
+	BUILD_BUG_ON(FANOTIFY_FH_HDR_LEN + MAX_HANDLE_SZ > U8_MAX);
+	BUILD_BUG_ON(NAME_MAX > U8_MAX);
+
+	info->dir_fh_totlen = 0;
+	info->dir2_fh_totlen = 0;
+	info->file_fh_totlen = 0;
+	info->name_len = 0;
+	info->name2_len = 0;
+}
+
+/* These set/copy helpers MUST be called by order */
+static inline void fanotify_info_set_dir_fh(struct fanotify_info *info,
+					    unsigned int totlen)
+{
+	if (WARN_ON_ONCE(info->dir2_fh_totlen > 0) ||
+	    WARN_ON_ONCE(info->file_fh_totlen > 0) ||
+	    WARN_ON_ONCE(info->name_len > 0) ||
+	    WARN_ON_ONCE(info->name2_len > 0))
+		return;
+
+	info->dir_fh_totlen = totlen;
+}
+
+static inline void fanotify_info_set_dir2_fh(struct fanotify_info *info,
+					     unsigned int totlen)
+{
+	if (WARN_ON_ONCE(info->file_fh_totlen > 0) ||
+	    WARN_ON_ONCE(info->name_len > 0) ||
+	    WARN_ON_ONCE(info->name2_len > 0))
+		return;
+
+	info->dir2_fh_totlen = totlen;
+}
+
+static inline void fanotify_info_set_file_fh(struct fanotify_info *info,
+					     unsigned int totlen)
+{
+	if (WARN_ON_ONCE(info->name_len > 0) ||
+	    WARN_ON_ONCE(info->name2_len > 0))
+		return;
+
+	info->file_fh_totlen = totlen;
+}
+
+static inline void fanotify_info_copy_name(struct fanotify_info *info,
+					   const struct qstr *name)
+{
+	if (WARN_ON_ONCE(name->len > NAME_MAX) ||
+	    WARN_ON_ONCE(info->name2_len > 0))
+		return;
+
+	info->name_len = name->len;
+	strscpy(fanotify_info_name(info), name->name, name->len + 1);
+}
+
+static inline void fanotify_info_copy_name2(struct fanotify_info *info,
+					    const struct qstr *name)
+{
+	if (WARN_ON_ONCE(name->len > NAME_MAX))
+		return;
+
+	info->name2_len = name->len;
+	strscpy(fanotify_info_name2(info), name->name, name->len + 1);
+}
+
+/*
+ * Common structure for fanotify events. Concrete structs are allocated in
+ * fanotify_handle_event() and freed when the information is retrieved by
+ * userspace. The type of event determines how it was allocated, how it will
+ * be freed and which concrete struct it may be cast to.
+ */
+enum fanotify_event_type {
+	FANOTIFY_EVENT_TYPE_FID, /* fixed length */
+	FANOTIFY_EVENT_TYPE_FID_NAME, /* variable length */
+	FANOTIFY_EVENT_TYPE_PATH,
+	FANOTIFY_EVENT_TYPE_PATH_PERM,
+	FANOTIFY_EVENT_TYPE_OVERFLOW, /* struct fanotify_event */
+	FANOTIFY_EVENT_TYPE_FS_ERROR, /* struct fanotify_error_event */
+	FANOTIFY_EVENT_TYPE_MNT,
+	__FANOTIFY_EVENT_TYPE_NUM
+};
+
+#define FANOTIFY_EVENT_TYPE_BITS \
+	(ilog2(__FANOTIFY_EVENT_TYPE_NUM - 1) + 1)
+#define FANOTIFY_EVENT_HASH_BITS \
+	(32 - FANOTIFY_EVENT_TYPE_BITS)
+
+struct fanotify_event {
+	struct fsnotify_event fse;
+	struct hlist_node merge_list;	/* List for hashed merge */
+	u32 mask;
+	struct {
+		unsigned int type : FANOTIFY_EVENT_TYPE_BITS;
+		unsigned int hash : FANOTIFY_EVENT_HASH_BITS;
+	};
+	struct pid *pid;
+};
+
+static inline void fanotify_init_event(struct fanotify_event *event,
+				       unsigned int hash, u32 mask)
+{
+	fsnotify_init_event(&event->fse);
+	INIT_HLIST_NODE(&event->merge_list);
+	event->hash = hash;
+	event->mask = mask;
+	event->pid = NULL;
+}
+
+#define FANOTIFY_INLINE_FH(name, size)					\
+struct {								\
+	struct fanotify_fh name;					\
+	/* Space for filehandle - access with fanotify_fh_buf() */	\
+	unsigned char _inline_fh_buf[size];				\
+}
+
+struct fanotify_fid_event {
+	struct fanotify_event fae;
+	__kernel_fsid_t fsid;
+
+	FANOTIFY_INLINE_FH(object_fh, FANOTIFY_INLINE_FH_LEN);
+};
+
+static inline struct fanotify_fid_event *
+FANOTIFY_FE(struct fanotify_event *event)
+{
+	return container_of(event, struct fanotify_fid_event, fae);
+}
+
+struct fanotify_name_event {
+	struct fanotify_event fae;
+	__kernel_fsid_t fsid;
+	struct fanotify_info info;
+};
+
+static inline struct fanotify_name_event *
+FANOTIFY_NE(struct fanotify_event *event)
+{
+	return container_of(event, struct fanotify_name_event, fae);
+}
+
+struct fanotify_error_event {
+	struct fanotify_event fae;
+	s32 error; /* Error reported by the Filesystem. */
+	u32 err_count; /* Suppressed errors count */
+
+	__kernel_fsid_t fsid; /* FSID this error refers to. */
+
+	FANOTIFY_INLINE_FH(object_fh, MAX_HANDLE_SZ);
+};
+
+static inline struct fanotify_error_event *
+FANOTIFY_EE(struct fanotify_event *event)
+{
+	return container_of(event, struct fanotify_error_event, fae);
+}
+
+static inline __kernel_fsid_t *fanotify_event_fsid(struct fanotify_event *event)
+{
+	if (event->type == FANOTIFY_EVENT_TYPE_FID)
+		return &FANOTIFY_FE(event)->fsid;
+	else if (event->type == FANOTIFY_EVENT_TYPE_FID_NAME)
+		return &FANOTIFY_NE(event)->fsid;
+	else if (event->type == FANOTIFY_EVENT_TYPE_FS_ERROR)
+		return &FANOTIFY_EE(event)->fsid;
+	else
+		return NULL;
+}
+
+static inline struct fanotify_fh *fanotify_event_object_fh(
+						struct fanotify_event *event)
+{
+	if (event->type == FANOTIFY_EVENT_TYPE_FID)
+		return &FANOTIFY_FE(event)->object_fh;
+	else if (event->type == FANOTIFY_EVENT_TYPE_FID_NAME)
+		return fanotify_info_file_fh(&FANOTIFY_NE(event)->info);
+	else if (event->type == FANOTIFY_EVENT_TYPE_FS_ERROR)
+		return &FANOTIFY_EE(event)->object_fh;
+	else
+		return NULL;
+}
+
+static inline struct fanotify_info *fanotify_event_info(
+						struct fanotify_event *event)
+{
+	if (event->type == FANOTIFY_EVENT_TYPE_FID_NAME)
+		return &FANOTIFY_NE(event)->info;
+	else
+		return NULL;
+}
+
+static inline int fanotify_event_object_fh_len(struct fanotify_event *event)
+{
+	struct fanotify_info *info = fanotify_event_info(event);
+	struct fanotify_fh *fh = fanotify_event_object_fh(event);
+
+	if (info)
+		return info->file_fh_totlen ? fh->len : 0;
+	else
+		return fh ? fh->len : 0;
+}
+
+static inline int fanotify_event_dir_fh_len(struct fanotify_event *event)
+{
+	struct fanotify_info *info = fanotify_event_info(event);
+
+	return info ? fanotify_info_dir_fh_len(info) : 0;
+}
+
+static inline int fanotify_event_dir2_fh_len(struct fanotify_event *event)
+{
+	struct fanotify_info *info = fanotify_event_info(event);
+
+	return info ? fanotify_info_dir2_fh_len(info) : 0;
+}
+
+static inline bool fanotify_event_has_object_fh(struct fanotify_event *event)
+{
+	/* For error events, even zeroed fh are reported. */
+	if (event->type == FANOTIFY_EVENT_TYPE_FS_ERROR)
+		return true;
+	return fanotify_event_object_fh_len(event) > 0;
+}
+
+static inline bool fanotify_event_has_dir_fh(struct fanotify_event *event)
+{
+	return fanotify_event_dir_fh_len(event) > 0;
+}
+
+static inline bool fanotify_event_has_dir2_fh(struct fanotify_event *event)
+{
+	return fanotify_event_dir2_fh_len(event) > 0;
+}
+
+static inline bool fanotify_event_has_any_dir_fh(struct fanotify_event *event)
+{
+	return fanotify_event_has_dir_fh(event) ||
+		fanotify_event_has_dir2_fh(event);
+}
+
+struct fanotify_path_event {
+	struct fanotify_event fae;
+	struct path path;
+};
+
+struct fanotify_mnt_event {
+	struct fanotify_event fae;
+	u64 mnt_id;
+};
+
+static inline struct fanotify_path_event *
+FANOTIFY_PE(struct fanotify_event *event)
+{
+	return container_of(event, struct fanotify_path_event, fae);
+}
+
+static inline struct fanotify_mnt_event *
+FANOTIFY_ME(struct fanotify_event *event)
+{
+	return container_of(event, struct fanotify_mnt_event, fae);
+}
+
+/*
+ * 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 {
+	struct fanotify_event fae;
+	struct path path;
+	const loff_t *ppos;		/* optional file range info */
+	size_t count;
+	u32 response;			/* userspace answer to the event */
+	unsigned short state;		/* state of the event */
+	unsigned short watchdog_cnt;	/* already scanned by watchdog? */
+	int fd;		/* fd we passed to userspace for this event */
+	pid_t recv_pid;	/* pid of task receiving the event */
+	union {
+		struct fanotify_response_info_header hdr;
+		struct fanotify_response_info_audit_rule audit_rule;
+	};
+};
+
+static inline struct fanotify_perm_event *
+FANOTIFY_PERM(struct fanotify_event *event)
+{
+	return container_of(event, struct fanotify_perm_event, fae);
+}
+
+static inline bool fanotify_is_perm_event(u32 mask)
+{
+	return IS_ENABLED(CONFIG_FANOTIFY_ACCESS_PERMISSIONS) &&
+		mask & FANOTIFY_PERM_EVENTS;
+}
+
+static inline bool fanotify_event_has_access_range(struct fanotify_event *event)
+{
+	if (!(event->mask & FANOTIFY_PRE_CONTENT_EVENTS))
+		return false;
+
+	return FANOTIFY_PERM(event)->ppos;
+}
+
+static inline struct fanotify_event *FANOTIFY_E(struct fsnotify_event *fse)
+{
+	return container_of(fse, struct fanotify_event, fse);
+}
+
+static inline bool fanotify_is_error_event(u32 mask)
+{
+	return mask & FAN_FS_ERROR;
+}
+
+static inline bool fanotify_is_mnt_event(u32 mask)
+{
+	return mask & (FAN_MNT_ATTACH | FAN_MNT_DETACH);
+}
+
+static inline const struct path *fanotify_event_path(struct fanotify_event *event)
+{
+	if (event->type == FANOTIFY_EVENT_TYPE_PATH)
+		return &FANOTIFY_PE(event)->path;
+	else if (event->type == FANOTIFY_EVENT_TYPE_PATH_PERM)
+		return &FANOTIFY_PERM(event)->path;
+	else
+		return NULL;
+}
+
+/*
+ * Use 128 size hash table to speed up events merge.
+ */
+#define FANOTIFY_HTABLE_BITS	(7)
+#define FANOTIFY_HTABLE_SIZE	(1 << FANOTIFY_HTABLE_BITS)
+#define FANOTIFY_HTABLE_MASK	(FANOTIFY_HTABLE_SIZE - 1)
+
+/*
+ * Permission events and overflow event do not get merged - don't hash them.
+ */
+static inline bool fanotify_is_hashed_event(u32 mask)
+{
+	return !(fanotify_is_perm_event(mask) ||
+		 fsnotify_is_overflow_event(mask));
+}
+
+static inline unsigned int fanotify_event_hash_bucket(
+						struct fsnotify_group *group,
+						struct fanotify_event *event)
+{
+	return event->hash & FANOTIFY_HTABLE_MASK;
+}
+
+struct fanotify_mark {
+	struct fsnotify_mark fsn_mark;
+	__kernel_fsid_t fsid;
+};
+
+static inline struct fanotify_mark *FANOTIFY_MARK(struct fsnotify_mark *mark)
+{
+	return container_of(mark, struct fanotify_mark, fsn_mark);
+}
+
+static inline bool fanotify_fsid_equal(__kernel_fsid_t *fsid1,
+				       __kernel_fsid_t *fsid2)
+{
+	return fsid1->val[0] == fsid2->val[0] && fsid1->val[1] == fsid2->val[1];
+}
+
+static inline unsigned int fanotify_mark_user_flags(struct fsnotify_mark *mark)
+{
+	unsigned int mflags = 0;
+
+	if (mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY)
+		mflags |= FAN_MARK_IGNORED_SURV_MODIFY;
+	if (mark->flags & FSNOTIFY_MARK_FLAG_NO_IREF)
+		mflags |= FAN_MARK_EVICTABLE;
+	if (mark->flags & FSNOTIFY_MARK_FLAG_HAS_IGNORE_FLAGS)
+		mflags |= FAN_MARK_IGNORE;
+
+	return mflags;
+}
+
+static inline u32 fanotify_get_response_errno(int res)
+{
+	return (res >> FAN_ERRNO_SHIFT) & FAN_ERRNO_MASK;
+}

linux-7.2.3/fs/notify/fdinfo.c

@@ -0,0 +1,153 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/fsnotify_backend.h>
+#include <linux/idr.h>
+#include <linux/init.h>
+#include <linux/inotify.h>
+#include <linux/fanotify.h>
+#include <linux/kernel.h>
+#include <linux/namei.h>
+#include <linux/sched.h>
+#include <linux/types.h>
+#include <linux/seq_file.h>
+#include <linux/exportfs.h>
+
+#include "inotify/inotify.h"
+#include "fanotify/fanotify.h"
+#include "fdinfo.h"
+#include "fsnotify.h"
+#include "../internal.h"
+
+#if defined(CONFIG_PROC_FS)
+
+#if defined(CONFIG_INOTIFY_USER) || defined(CONFIG_FANOTIFY)
+
+static void show_fdinfo(struct seq_file *m, struct file *f,
+			void (*show)(struct seq_file *m,
+				     struct fsnotify_mark *mark))
+{
+	struct fsnotify_group *group = f->private_data;
+	struct fsnotify_mark *mark;
+
+	fsnotify_group_lock(group);
+	list_for_each_entry(mark, &group->marks_list, g_list) {
+		show(m, mark);
+		if (seq_has_overflowed(m))
+			break;
+	}
+	fsnotify_group_unlock(group);
+}
+
+#if defined(CONFIG_EXPORTFS)
+static void show_mark_fhandle(struct seq_file *m, struct inode *inode)
+{
+	DEFINE_FLEX(struct file_handle, f, f_handle, handle_bytes, MAX_HANDLE_SZ);
+	int size, ret, i;
+
+	size = f->handle_bytes >> 2;
+
+	if (!super_trylock_shared(inode->i_sb))
+		return;
+
+	ret = exportfs_encode_fid(inode, (struct fid *)f->f_handle, &size);
+	up_read(&inode->i_sb->s_umount);
+
+	if ((ret == FILEID_INVALID) || (ret < 0))
+		return;
+
+	f->handle_type = ret;
+	f->handle_bytes = size * sizeof(u32);
+
+	seq_printf(m, "fhandle-bytes:%x fhandle-type:%x f_handle:",
+		   f->handle_bytes, f->handle_type);
+
+	for (i = 0; i < f->handle_bytes; i++)
+		seq_printf(m, "%02x", (int)f->f_handle[i]);
+}
+#else
+static void show_mark_fhandle(struct seq_file *m, struct inode *inode)
+{
+}
+#endif
+
+#ifdef CONFIG_INOTIFY_USER
+
+static void inotify_fdinfo(struct seq_file *m, struct fsnotify_mark *mark)
+{
+	struct inotify_inode_mark *inode_mark;
+	struct inode *inode;
+
+	if (mark->connector->type != FSNOTIFY_OBJ_TYPE_INODE)
+		return;
+
+	inode_mark = container_of(mark, struct inotify_inode_mark, fsn_mark);
+	inode = igrab(fsnotify_conn_inode(mark->connector));
+	if (inode) {
+		seq_printf(m, "inotify wd:%x ino:%llx sdev:%x mask:%x ignored_mask:0 ",
+			   inode_mark->wd, inode->i_ino, inode->i_sb->s_dev,
+			   inotify_mark_user_mask(mark));
+		show_mark_fhandle(m, inode);
+		seq_putc(m, '\n');
+		iput(inode);
+	}
+}
+
+void inotify_show_fdinfo(struct seq_file *m, struct file *f)
+{
+	show_fdinfo(m, f, inotify_fdinfo);
+}
+
+#endif /* CONFIG_INOTIFY_USER */
+
+#ifdef CONFIG_FANOTIFY
+
+static void fanotify_fdinfo(struct seq_file *m, struct fsnotify_mark *mark)
+{
+	unsigned int mflags = fanotify_mark_user_flags(mark);
+	struct inode *inode;
+
+	if (mark->connector->type == FSNOTIFY_OBJ_TYPE_INODE) {
+		inode = igrab(fsnotify_conn_inode(mark->connector));
+		if (!inode)
+			return;
+		seq_printf(m, "fanotify ino:%llx sdev:%x mflags:%x mask:%x ignored_mask:%x ",
+			   inode->i_ino, inode->i_sb->s_dev,
+			   mflags, mark->mask, mark->ignore_mask);
+		show_mark_fhandle(m, inode);
+		seq_putc(m, '\n');
+		iput(inode);
+	} else if (mark->connector->type == FSNOTIFY_OBJ_TYPE_VFSMOUNT) {
+		struct mount *mnt = fsnotify_conn_mount(mark->connector);
+
+		seq_printf(m, "fanotify mnt_id:%x mflags:%x mask:%x ignored_mask:%x\n",
+			   mnt->mnt_id, mflags, mark->mask, mark->ignore_mask);
+	} else if (mark->connector->type == FSNOTIFY_OBJ_TYPE_SB) {
+		struct super_block *sb = fsnotify_conn_sb(mark->connector);
+
+		seq_printf(m, "fanotify sdev:%x mflags:%x mask:%x ignored_mask:%x\n",
+			   sb->s_dev, mflags, mark->mask, mark->ignore_mask);
+	} else if (mark->connector->type == FSNOTIFY_OBJ_TYPE_MNTNS) {
+		struct mnt_namespace *mnt_ns = fsnotify_conn_mntns(mark->connector);
+
+		seq_printf(m, "fanotify mnt_ns:%u mflags:%x mask:%x ignored_mask:%x\n",
+			   mnt_ns->ns.inum, mflags, mark->mask, mark->ignore_mask);
+	}
+}
+
+void fanotify_show_fdinfo(struct seq_file *m, struct file *f)
+{
+	struct fsnotify_group *group = f->private_data;
+
+	seq_printf(m, "fanotify flags:%x event-flags:%x\n",
+		   group->fanotify_data.flags & FANOTIFY_INIT_FLAGS,
+		   group->fanotify_data.f_flags);
+
+	show_fdinfo(m, f, fanotify_fdinfo);
+}
+
+#endif /* CONFIG_FANOTIFY */
+
+#endif /* CONFIG_INOTIFY_USER || CONFIG_FANOTIFY */
+
+#endif /* CONFIG_PROC_FS */

linux-7.2.3/fs/notify/fdinfo.h

@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __FSNOTIFY_FDINFO_H__
+#define __FSNOTIFY_FDINFO_H__
+
+#include <linux/errno.h>
+#include <linux/proc_fs.h>
+
+struct seq_file;
+struct file;
+
+#ifdef CONFIG_PROC_FS
+
+#ifdef CONFIG_INOTIFY_USER
+void inotify_show_fdinfo(struct seq_file *m, struct file *f);
+#endif
+
+#ifdef CONFIG_FANOTIFY
+void fanotify_show_fdinfo(struct seq_file *m, struct file *f);
+#endif
+
+#else /* CONFIG_PROC_FS */
+
+#define inotify_show_fdinfo	NULL
+#define fanotify_show_fdinfo	NULL
+
+#endif /* CONFIG_PROC_FS */
+
+#endif /* __FSNOTIFY_FDINFO_H__ */

linux-7.2.3/fs/notify/fsnotify.c

@@ -0,0 +1,733 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ *  Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com>
+ */
+
+#include <linux/dcache.h>
+#include <linux/fs.h>
+#include <linux/gfp.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/mount.h>
+#include <linux/srcu.h>
+
+#include <linux/fsnotify_backend.h>
+#include "fsnotify.h"
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/fsnotify.h>
+
+/*
+ * Clear all of the marks on an inode when it is being evicted from core
+ */
+void __fsnotify_inode_delete(struct inode *inode)
+{
+	fsnotify_clear_marks_by_inode(inode);
+}
+EXPORT_SYMBOL_GPL(__fsnotify_inode_delete);
+
+void __fsnotify_vfsmount_delete(struct vfsmount *mnt)
+{
+	fsnotify_clear_marks_by_mount(mnt);
+}
+
+void __fsnotify_mntns_delete(struct mnt_namespace *mntns)
+{
+	fsnotify_clear_marks_by_mntns(mntns);
+}
+
+void fsnotify_sb_delete(struct super_block *sb)
+{
+	struct fsnotify_sb_info *sbinfo = fsnotify_sb_info(sb);
+
+	/* Were any marks ever added to any object on this sb? */
+	if (!sbinfo)
+		return;
+
+	fsnotify_unmount_inodes(sbinfo);
+	fsnotify_clear_marks_by_sb(sb);
+	/* Wait for outstanding object references from connectors */
+	wait_var_event(fsnotify_sb_watched_objects(sb),
+		       !atomic_long_read(fsnotify_sb_watched_objects(sb)));
+	WARN_ON(fsnotify_sb_has_priority_watchers(sb, FSNOTIFY_PRIO_CONTENT));
+	WARN_ON(fsnotify_sb_has_priority_watchers(sb,
+						  FSNOTIFY_PRIO_PRE_CONTENT));
+}
+
+void fsnotify_sb_free(struct super_block *sb)
+{
+	if (sb->s_fsnotify_info) {
+		WARN_ON_ONCE(!list_empty(&sb->s_fsnotify_info->inode_conn_list));
+		kfree(sb->s_fsnotify_info);
+	}
+}
+
+/*
+ * Given an inode, first check if we care what happens to our children.  Inotify
+ * and dnotify both tell their parents about events.  If we care about any event
+ * on a child we run all of our children and set a dentry flag saying that the
+ * parent cares.  Thus when an event happens on a child it can quickly tell
+ * if there is a need to find a parent and send the event to the parent.
+ */
+void fsnotify_set_children_dentry_flags(struct inode *inode)
+{
+	struct dentry *alias;
+
+	if (!S_ISDIR(inode->i_mode))
+		return;
+
+	spin_lock(&inode->i_lock);
+	/* run all of the dentries associated with this inode.  Since this is a
+	 * directory, there damn well better only be one item on this list */
+	for_each_alias(alias, inode) {
+		struct dentry *child;
+
+		/* run all of the children of the original inode and fix their
+		 * d_flags to indicate parental interest (their parent is the
+		 * original inode) */
+		spin_lock(&alias->d_lock);
+		hlist_for_each_entry(child, &alias->d_children, d_sib) {
+			if (!child->d_inode)
+				continue;
+
+			spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED);
+			child->d_flags |= DCACHE_FSNOTIFY_PARENT_WATCHED;
+			spin_unlock(&child->d_lock);
+		}
+		spin_unlock(&alias->d_lock);
+	}
+	spin_unlock(&inode->i_lock);
+}
+
+/*
+ * Lazily clear false positive PARENT_WATCHED flag for child whose parent had
+ * stopped watching children.
+ */
+static void fsnotify_clear_child_dentry_flag(struct inode *pinode,
+					     struct dentry *dentry)
+{
+	spin_lock(&dentry->d_lock);
+	/*
+	 * d_lock is a sufficient barrier to prevent observing a non-watched
+	 * parent state from before the fsnotify_set_children_dentry_flags()
+	 * or fsnotify_update_flags() call that had set PARENT_WATCHED.
+	 */
+	if (!fsnotify_inode_watches_children(pinode))
+		dentry->d_flags &= ~DCACHE_FSNOTIFY_PARENT_WATCHED;
+	spin_unlock(&dentry->d_lock);
+}
+
+/* Are inode/sb/mount interested in parent and name info with this event? */
+static bool fsnotify_event_needs_parent(struct inode *inode, __u32 mnt_mask,
+					__u32 mask)
+{
+	__u32 marks_mask = 0;
+
+	/* We only send parent/name to inode/sb/mount for events on non-dir */
+	if (mask & FS_ISDIR)
+		return false;
+
+	/*
+	 * All events that are possible on child can also may be reported with
+	 * parent/name info to inode/sb/mount.  Otherwise, a watching parent
+	 * could result in events reported with unexpected name info to sb/mount.
+	 */
+	BUILD_BUG_ON(FS_EVENTS_POSS_ON_CHILD & ~FS_EVENTS_POSS_TO_PARENT);
+
+	/* Did either inode/sb/mount subscribe for events with parent/name? */
+	marks_mask |= fsnotify_parent_needed_mask(
+				READ_ONCE(inode->i_fsnotify_mask));
+	marks_mask |= fsnotify_parent_needed_mask(
+				READ_ONCE(inode->i_sb->s_fsnotify_mask));
+	marks_mask |= fsnotify_parent_needed_mask(mnt_mask);
+
+	/* Did they subscribe for this event with parent/name info? */
+	return mask & marks_mask;
+}
+
+/* Are there any inode/mount/sb objects that watch for these events? */
+static inline __u32 fsnotify_object_watched(struct inode *inode, __u32 mnt_mask,
+					    __u32 mask)
+{
+	__u32 marks_mask = READ_ONCE(inode->i_fsnotify_mask) | mnt_mask |
+			   READ_ONCE(inode->i_sb->s_fsnotify_mask);
+
+	return mask & marks_mask & ALL_FSNOTIFY_EVENTS;
+}
+
+/* Report pre-content event with optional range info */
+int fsnotify_pre_content(const struct path *path, const loff_t *ppos,
+			 size_t count)
+{
+	struct file_range range;
+
+	/* Report page aligned range only when pos is known */
+	if (!ppos)
+		return fsnotify_path(path, FS_PRE_ACCESS);
+
+	range.path = path;
+	range.pos = PAGE_ALIGN_DOWN(*ppos);
+	range.count = PAGE_ALIGN(*ppos + count) - range.pos;
+
+	return fsnotify_parent(path->dentry, FS_PRE_ACCESS, &range,
+			       FSNOTIFY_EVENT_FILE_RANGE);
+}
+
+/*
+ * Notify this dentry's parent about a child's events with child name info
+ * if parent is watching or if inode/sb/mount are interested in events with
+ * parent and name info.
+ *
+ * Notify only the child without name info if parent is not watching and
+ * inode/sb/mount are not interested in events with parent and name info.
+ */
+int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data,
+		      int data_type)
+{
+	const struct path *path = fsnotify_data_path(data, data_type);
+	__u32 mnt_mask = path ?
+		READ_ONCE(real_mount(path->mnt)->mnt_fsnotify_mask) : 0;
+	struct inode *inode = d_inode(dentry);
+	struct dentry *parent;
+	bool parent_watched = dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED;
+	bool parent_needed, parent_interested;
+	__u32 p_mask;
+	struct inode *p_inode = NULL;
+	struct name_snapshot name;
+	struct qstr *file_name = NULL;
+	int ret = 0;
+
+	/* Optimize the likely case of nobody watching this path */
+	if (likely(!parent_watched &&
+		   !fsnotify_object_watched(inode, mnt_mask, mask)))
+		return 0;
+
+	parent = NULL;
+	parent_needed = fsnotify_event_needs_parent(inode, mnt_mask, mask);
+	if (!parent_watched && !parent_needed)
+		goto notify;
+
+	/* Does parent inode care about events on children? */
+	parent = dget_parent(dentry);
+	p_inode = parent->d_inode;
+	p_mask = fsnotify_inode_watches_children(p_inode);
+	if (unlikely(parent_watched && !p_mask))
+		fsnotify_clear_child_dentry_flag(p_inode, dentry);
+
+	/*
+	 * Include parent/name in notification either if some notification
+	 * groups require parent info or the parent is interested in this event.
+	 * The parent interest in ACCESS/MODIFY events does not apply to special
+	 * files, where read/write are not on the filesystem of the parent and
+	 * events can provide an undesirable side-channel for information
+	 * exfiltration.
+	 */
+	parent_interested = mask & p_mask & ALL_FSNOTIFY_EVENTS &&
+			    !(data_type == FSNOTIFY_EVENT_PATH &&
+			      d_is_special(dentry) &&
+			      (mask & (FS_ACCESS | FS_MODIFY)));
+	if (parent_needed || parent_interested) {
+		/* When notifying parent, child should be passed as data */
+		WARN_ON_ONCE(inode != fsnotify_data_inode(data, data_type));
+
+		/* Notify both parent and child with child name info */
+		take_dentry_name_snapshot(&name, dentry);
+		file_name = &name.name;
+		if (parent_interested)
+			mask |= FS_EVENT_ON_CHILD;
+	}
+
+notify:
+	ret = fsnotify(mask, data, data_type, p_inode, file_name, inode, 0);
+
+	if (file_name)
+		release_dentry_name_snapshot(&name);
+	dput(parent);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(__fsnotify_parent);
+
+static int fsnotify_handle_inode_event(struct fsnotify_group *group,
+				       struct fsnotify_mark *inode_mark,
+				       u32 mask, const void *data, int data_type,
+				       struct inode *dir, const struct qstr *name,
+				       u32 cookie)
+{
+	const struct path *path = fsnotify_data_path(data, data_type);
+	struct inode *inode = fsnotify_data_inode(data, data_type);
+	const struct fsnotify_ops *ops = group->ops;
+
+	if (WARN_ON_ONCE(!ops->handle_inode_event))
+		return 0;
+
+	if (WARN_ON_ONCE(!inode && !dir))
+		return 0;
+
+	if ((inode_mark->flags & FSNOTIFY_MARK_FLAG_EXCL_UNLINK) &&
+	    path && d_unlinked(path->dentry))
+		return 0;
+
+	/* Check interest of this mark in case event was sent with two marks */
+	if (!(mask & inode_mark->mask & ALL_FSNOTIFY_EVENTS))
+		return 0;
+
+	return ops->handle_inode_event(inode_mark, mask, inode, dir, name, cookie);
+}
+
+static int fsnotify_handle_event(struct fsnotify_group *group, __u32 mask,
+				 const void *data, int data_type,
+				 struct inode *dir, const struct qstr *name,
+				 u32 cookie, struct fsnotify_iter_info *iter_info)
+{
+	struct fsnotify_mark *inode_mark = fsnotify_iter_inode_mark(iter_info);
+	struct fsnotify_mark *parent_mark = fsnotify_iter_parent_mark(iter_info);
+	int ret;
+
+	if (WARN_ON_ONCE(fsnotify_iter_sb_mark(iter_info)) ||
+	    WARN_ON_ONCE(fsnotify_iter_vfsmount_mark(iter_info)))
+		return 0;
+
+	/*
+	 * For FS_RENAME, 'dir' is old dir and 'data' is new dentry.
+	 * The only ->handle_inode_event() backend that supports FS_RENAME is
+	 * dnotify, where it means file was renamed within same parent.
+	 */
+	if (mask & FS_RENAME) {
+		struct dentry *moved = fsnotify_data_dentry(data, data_type);
+
+		if (dir != moved->d_parent->d_inode)
+			return 0;
+	}
+
+	if (parent_mark) {
+		ret = fsnotify_handle_inode_event(group, parent_mark, mask,
+						  data, data_type, dir, name, 0);
+		if (ret)
+			return ret;
+	}
+
+	if (!inode_mark)
+		return 0;
+
+	/*
+	 * Some events can be sent on both parent dir and child marks (e.g.
+	 * FS_ATTRIB).  If both parent dir and child are watching, report the
+	 * event once to parent dir with name (if interested) and once to child
+	 * without name (if interested).
+	 *
+	 * In any case regardless whether the parent is watching or not, the
+	 * child watcher is expecting an event without the FS_EVENT_ON_CHILD
+	 * flag. The file name is expected if and only if this is a directory
+	 * event.
+	 */
+	mask &= ~FS_EVENT_ON_CHILD;
+	if (!(mask & ALL_FSNOTIFY_DIRENT_EVENTS)) {
+		dir = NULL;
+		name = NULL;
+	}
+
+	return fsnotify_handle_inode_event(group, inode_mark, mask, data, data_type,
+					   dir, name, cookie);
+}
+
+static int send_to_group(__u32 mask, const void *data, int data_type,
+			 struct inode *dir, const struct qstr *file_name,
+			 u32 cookie, struct fsnotify_iter_info *iter_info)
+{
+	struct fsnotify_group *group = NULL;
+	__u32 test_mask = (mask & ALL_FSNOTIFY_EVENTS);
+	__u32 marks_mask = 0;
+	__u32 marks_ignore_mask = 0;
+	bool is_dir = mask & FS_ISDIR;
+	struct fsnotify_mark *mark;
+	int type;
+
+	if (!iter_info->report_mask)
+		return 0;
+
+	/* clear ignored on inode modification */
+	if (mask & FS_MODIFY) {
+		fsnotify_foreach_iter_mark_type(iter_info, mark, type) {
+			if (!(mark->flags &
+			      FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY))
+				mark->ignore_mask = 0;
+		}
+	}
+
+	/* Are any of the group marks interested in this event? */
+	fsnotify_foreach_iter_mark_type(iter_info, mark, type) {
+		group = mark->group;
+		marks_mask |= mark->mask;
+		marks_ignore_mask |=
+			fsnotify_effective_ignore_mask(mark, is_dir, type);
+	}
+
+	pr_debug("%s: group=%p mask=%x marks_mask=%x marks_ignore_mask=%x data=%p data_type=%d dir=%p cookie=%d\n",
+		 __func__, group, mask, marks_mask, marks_ignore_mask,
+		 data, data_type, dir, cookie);
+
+	if (!(test_mask & marks_mask & ~marks_ignore_mask))
+		return 0;
+
+	if (group->ops->handle_event) {
+		return group->ops->handle_event(group, mask, data, data_type, dir,
+						file_name, cookie, iter_info);
+	}
+
+	return fsnotify_handle_event(group, mask, data, data_type, dir,
+				     file_name, cookie, iter_info);
+}
+
+static struct fsnotify_mark *fsnotify_first_mark(struct fsnotify_mark_connector *const *connp)
+{
+	struct fsnotify_mark_connector *conn;
+	struct hlist_node *node = NULL;
+
+	conn = srcu_dereference(*connp, &fsnotify_mark_srcu);
+	if (conn)
+		node = srcu_dereference(conn->list.first, &fsnotify_mark_srcu);
+
+	return hlist_entry_safe(node, struct fsnotify_mark, obj_list);
+}
+
+struct fsnotify_mark *fsnotify_next_mark(struct fsnotify_mark *mark)
+{
+	struct hlist_node *node = NULL;
+
+	if (mark)
+		node = srcu_dereference(mark->obj_list.next,
+					&fsnotify_mark_srcu);
+
+	return hlist_entry_safe(node, struct fsnotify_mark, obj_list);
+}
+
+/*
+ * iter_info is a multi head priority queue of marks.
+ * Pick a subset of marks from queue heads, all with the same group
+ * and set the report_mask to a subset of the selected marks.
+ * Returns false if there are no more groups to iterate.
+ */
+static bool fsnotify_iter_select_report_types(
+		struct fsnotify_iter_info *iter_info)
+{
+	struct fsnotify_group *max_prio_group = NULL;
+	struct fsnotify_mark *mark;
+	int type;
+
+	/* Choose max prio group among groups of all queue heads */
+	fsnotify_foreach_iter_type(type) {
+		mark = iter_info->marks[type];
+		if (mark &&
+		    fsnotify_compare_groups(max_prio_group, mark->group) > 0)
+			max_prio_group = mark->group;
+	}
+
+	if (!max_prio_group)
+		return false;
+
+	/* Set the report mask for marks from same group as max prio group */
+	iter_info->current_group = max_prio_group;
+	iter_info->report_mask = 0;
+	fsnotify_foreach_iter_type(type) {
+		mark = iter_info->marks[type];
+		if (mark && mark->group == iter_info->current_group) {
+			/*
+			 * FSNOTIFY_ITER_TYPE_PARENT indicates that this inode
+			 * is watching children and interested in this event,
+			 * which is an event possible on child.
+			 * But is *this mark* watching children?
+			 */
+			if (type == FSNOTIFY_ITER_TYPE_PARENT &&
+			    !(mark->mask & FS_EVENT_ON_CHILD) &&
+			    !(fsnotify_ignore_mask(mark) & FS_EVENT_ON_CHILD))
+				continue;
+
+			fsnotify_iter_set_report_type(iter_info, type);
+		}
+	}
+
+	return true;
+}
+
+/*
+ * Pop from iter_info multi head queue, the marks that belong to the group of
+ * current iteration step.
+ */
+static void fsnotify_iter_next(struct fsnotify_iter_info *iter_info)
+{
+	struct fsnotify_mark *mark;
+	int type;
+
+	/*
+	 * We cannot use fsnotify_foreach_iter_mark_type() here because we
+	 * may need to advance a mark of type X that belongs to current_group
+	 * but was not selected for reporting.
+	 */
+	fsnotify_foreach_iter_type(type) {
+		mark = iter_info->marks[type];
+		if (mark && mark->group == iter_info->current_group)
+			iter_info->marks[type] =
+				fsnotify_next_mark(iter_info->marks[type]);
+	}
+}
+
+/*
+ * fsnotify - This is the main call to fsnotify.
+ *
+ * The VFS calls into hook specific functions in linux/fsnotify.h.
+ * Those functions then in turn call here.  Here will call out to all of the
+ * registered fsnotify_group.  Those groups can then use the notification event
+ * in whatever means they feel necessary.
+ *
+ * @mask:	event type and flags
+ * @data:	object that event happened on
+ * @data_type:	type of object for fanotify_data_XXX() accessors
+ * @dir:	optional directory associated with event -
+ *		if @file_name is not NULL, this is the directory that
+ *		@file_name is relative to
+ * @file_name:	optional file name associated with event
+ * @inode:	optional inode associated with event -
+ *		If @dir and @inode are both non-NULL, event may be
+ *		reported to both.
+ * @cookie:	inotify rename cookie
+ */
+int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir,
+	     const struct qstr *file_name, struct inode *inode, u32 cookie)
+{
+	const struct path *path = fsnotify_data_path(data, data_type);
+	struct super_block *sb = fsnotify_data_sb(data, data_type);
+	const struct fsnotify_mnt *mnt_data = fsnotify_data_mnt(data, data_type);
+	struct fsnotify_sb_info *sbinfo = sb ? fsnotify_sb_info(sb) : NULL;
+	struct fsnotify_iter_info iter_info = {};
+	struct mount *mnt = NULL;
+	struct inode *inode2 = NULL;
+	struct dentry *moved;
+	int inode2_type;
+	int ret = 0;
+	__u32 test_mask, marks_mask = 0;
+
+	trace_fsnotify(mask, data, data_type, dir, file_name, inode, cookie);
+
+	if (path)
+		mnt = real_mount(path->mnt);
+
+	if (!inode) {
+		/* Dirent event - report on TYPE_INODE to dir */
+		inode = dir;
+		/* For FS_RENAME, inode is old_dir and inode2 is new_dir */
+		if (mask & FS_RENAME) {
+			moved = fsnotify_data_dentry(data, data_type);
+			inode2 = moved->d_parent->d_inode;
+			inode2_type = FSNOTIFY_ITER_TYPE_INODE2;
+		}
+	} else if (mask & FS_EVENT_ON_CHILD) {
+		/*
+		 * Event on child - report on TYPE_PARENT to dir if it is
+		 * watching children and on TYPE_INODE to child.
+		 */
+		inode2 = dir;
+		inode2_type = FSNOTIFY_ITER_TYPE_PARENT;
+	}
+
+	/*
+	 * Optimization: srcu_read_lock() has a memory barrier which can
+	 * be expensive.  It protects walking the *_fsnotify_marks lists.
+	 * However, if we do not walk the lists, we do not have to do
+	 * SRCU because we have no references to any objects and do not
+	 * need SRCU to keep them "alive".
+	 */
+	if ((!sbinfo || !sbinfo->sb_marks) &&
+	    (!mnt || !mnt->mnt_fsnotify_marks) &&
+	    (!inode || !inode->i_fsnotify_marks) &&
+	    (!inode2 || !inode2->i_fsnotify_marks) &&
+	    (!mnt_data || !mnt_data->ns->n_fsnotify_marks))
+		return 0;
+
+	if (sb)
+		marks_mask |= READ_ONCE(sb->s_fsnotify_mask);
+	if (mnt)
+		marks_mask |= READ_ONCE(mnt->mnt_fsnotify_mask);
+	if (inode)
+		marks_mask |= READ_ONCE(inode->i_fsnotify_mask);
+	if (inode2)
+		marks_mask |= READ_ONCE(inode2->i_fsnotify_mask);
+	if (mnt_data)
+		marks_mask |= READ_ONCE(mnt_data->ns->n_fsnotify_mask);
+
+	/*
+	 * If this is a modify event we may need to clear some ignore masks.
+	 * In that case, the object with ignore masks will have the FS_MODIFY
+	 * event in its mask.
+	 * Otherwise, return if none of the marks care about this type of event.
+	 */
+	test_mask = (mask & ALL_FSNOTIFY_EVENTS);
+	if (!(test_mask & marks_mask))
+		return 0;
+
+	iter_info.srcu_idx = srcu_read_lock(&fsnotify_mark_srcu);
+
+	if (sbinfo) {
+		iter_info.marks[FSNOTIFY_ITER_TYPE_SB] =
+			fsnotify_first_mark(&sbinfo->sb_marks);
+	}
+	if (mnt) {
+		iter_info.marks[FSNOTIFY_ITER_TYPE_VFSMOUNT] =
+			fsnotify_first_mark(&mnt->mnt_fsnotify_marks);
+	}
+	if (inode) {
+		iter_info.marks[FSNOTIFY_ITER_TYPE_INODE] =
+			fsnotify_first_mark(&inode->i_fsnotify_marks);
+	}
+	if (inode2) {
+		iter_info.marks[inode2_type] =
+			fsnotify_first_mark(&inode2->i_fsnotify_marks);
+	}
+	if (mnt_data) {
+		iter_info.marks[FSNOTIFY_ITER_TYPE_MNTNS] =
+			fsnotify_first_mark(&mnt_data->ns->n_fsnotify_marks);
+	}
+
+	/*
+	 * We need to merge inode/vfsmount/sb mark lists so that e.g. inode mark
+	 * ignore masks are properly reflected for mount/sb mark notifications.
+	 * That's why this traversal is so complicated...
+	 */
+	while (fsnotify_iter_select_report_types(&iter_info)) {
+		ret = send_to_group(mask, data, data_type, dir, file_name,
+				    cookie, &iter_info);
+
+		if (ret && (mask & ALL_FSNOTIFY_PERM_EVENTS))
+			goto out;
+
+		fsnotify_iter_next(&iter_info);
+	}
+	ret = 0;
+out:
+	srcu_read_unlock(&fsnotify_mark_srcu, iter_info.srcu_idx);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(fsnotify);
+
+#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+/*
+ * At open time we check fsnotify_sb_has_priority_watchers(), call the open perm
+ * hook and set the FMODE_NONOTIFY_ mode bits accordignly.
+ * Later, fsnotify permission hooks do not check if there are permission event
+ * watches, but that there were permission event watches at open time.
+ */
+int fsnotify_open_perm_and_set_mode(struct file *file)
+{
+	struct dentry *dentry = file->f_path.dentry, *parent;
+	struct super_block *sb = dentry->d_sb;
+	__u32 mnt_mask, p_mask = 0;
+
+	/* Is it a file opened by fanotify? */
+	if (FMODE_FSNOTIFY_NONE(file->f_mode))
+		return 0;
+
+	/*
+	 * Permission events is a super set of pre-content events, so if there
+	 * are no permission event watchers, there are also no pre-content event
+	 * watchers and this is implied from the single FMODE_NONOTIFY_PERM bit.
+	 */
+	if (likely(!fsnotify_sb_has_priority_watchers(sb,
+						FSNOTIFY_PRIO_CONTENT))) {
+		file_set_fsnotify_mode(file, FMODE_NONOTIFY_PERM);
+		return 0;
+	}
+
+	/*
+	 * OK, there are some permission event watchers. Check if anybody is
+	 * watching for permission events on *this* file.
+	 */
+	mnt_mask = READ_ONCE(real_mount(file->f_path.mnt)->mnt_fsnotify_mask);
+	p_mask = fsnotify_object_watched(d_inode(dentry), mnt_mask,
+					 ALL_FSNOTIFY_PERM_EVENTS);
+	if (dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED) {
+		parent = dget_parent(dentry);
+		p_mask |= fsnotify_inode_watches_children(d_inode(parent));
+		dput(parent);
+	}
+
+	/*
+	 * Legacy FAN_ACCESS_PERM events have very high performance overhead,
+	 * so unlikely to be used in the wild. If they are used there will be
+	 * no optimizations at all.
+	 */
+	if (unlikely(p_mask & FS_ACCESS_PERM)) {
+		/* Enable all permission and pre-content events */
+		file_set_fsnotify_mode(file, 0);
+		goto open_perm;
+	}
+
+	/*
+	 * Pre-content events are only supported on regular files.
+	 * If there are pre-content event watchers and no permission access
+	 * watchers, set FMODE_NONOTIFY | FMODE_NONOTIFY_PERM to indicate that.
+	 * That is the common case with HSM service.
+	 */
+	if (d_is_reg(dentry) && (p_mask & FSNOTIFY_PRE_CONTENT_EVENTS)) {
+		file_set_fsnotify_mode(file, FMODE_NONOTIFY |
+					     FMODE_NONOTIFY_PERM);
+		goto open_perm;
+	}
+
+	/* Nobody watching permission and pre-content events on this file */
+	file_set_fsnotify_mode(file, FMODE_NONOTIFY_PERM);
+
+open_perm:
+	/*
+	 * Send open perm events depending on object masks and regardless of
+	 * FMODE_NONOTIFY_PERM.
+	 */
+	if (file->f_flags & __FMODE_EXEC && p_mask & FS_OPEN_EXEC_PERM) {
+		int ret = fsnotify_path(&file->f_path, FS_OPEN_EXEC_PERM);
+
+		if (ret)
+			return ret;
+	}
+
+	if (p_mask & FS_OPEN_PERM)
+		return fsnotify_path(&file->f_path, FS_OPEN_PERM);
+
+	return 0;
+}
+#endif
+
+void fsnotify_mnt(__u32 mask, struct mnt_namespace *ns, struct vfsmount *mnt)
+{
+	struct fsnotify_mnt data = {
+		.ns = ns,
+		.mnt_id = real_mount(mnt)->mnt_id_unique,
+	};
+
+	if (WARN_ON_ONCE(!ns))
+		return;
+
+	/*
+	 * This is an optimization as well as making sure fsnotify_init() has
+	 * been called.
+	 */
+	if (!ns->n_fsnotify_marks)
+		return;
+
+	fsnotify(mask, &data, FSNOTIFY_EVENT_MNT, NULL, NULL, NULL, 0);
+}
+
+static __init int fsnotify_init(void)
+{
+	int ret;
+
+	BUILD_BUG_ON(HWEIGHT32(ALL_FSNOTIFY_BITS) != 26);
+
+	ret = init_srcu_struct(&fsnotify_mark_srcu);
+	if (ret)
+		panic("initializing fsnotify_mark_srcu");
+
+	fsnotify_init_connector_caches();
+
+	return 0;
+}
+core_initcall(fsnotify_init);

linux-7.2.3/fs/notify/fsnotify.h

@@ -0,0 +1,114 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __FS_NOTIFY_FSNOTIFY_H_
+#define __FS_NOTIFY_FSNOTIFY_H_
+
+#include <linux/list.h>
+#include <linux/fsnotify.h>
+#include <linux/srcu.h>
+#include <linux/types.h>
+
+#include "../mount.h"
+
+/*
+ * fsnotify_connp_t is what we embed in objects which connector can be attached
+ * to.
+ */
+typedef struct fsnotify_mark_connector __rcu *fsnotify_connp_t;
+
+static inline struct inode *fsnotify_conn_inode(
+				struct fsnotify_mark_connector *conn)
+{
+	return conn->obj;
+}
+
+static inline struct mount *fsnotify_conn_mount(
+				struct fsnotify_mark_connector *conn)
+{
+	return real_mount(conn->obj);
+}
+
+static inline struct super_block *fsnotify_conn_sb(
+				struct fsnotify_mark_connector *conn)
+{
+	return conn->obj;
+}
+
+static inline struct mnt_namespace *fsnotify_conn_mntns(
+				struct fsnotify_mark_connector *conn)
+{
+	return conn->obj;
+}
+
+static inline struct super_block *fsnotify_object_sb(void *obj,
+			enum fsnotify_obj_type obj_type)
+{
+	switch (obj_type) {
+	case FSNOTIFY_OBJ_TYPE_INODE:
+		return ((struct inode *)obj)->i_sb;
+	case FSNOTIFY_OBJ_TYPE_VFSMOUNT:
+		return ((struct vfsmount *)obj)->mnt_sb;
+	case FSNOTIFY_OBJ_TYPE_SB:
+		return (struct super_block *)obj;
+	default:
+		return NULL;
+	}
+}
+
+static inline struct super_block *fsnotify_connector_sb(
+				struct fsnotify_mark_connector *conn)
+{
+	return fsnotify_object_sb(conn->obj, conn->type);
+}
+
+static inline fsnotify_connp_t *fsnotify_sb_marks(struct super_block *sb)
+{
+	struct fsnotify_sb_info *sbinfo = fsnotify_sb_info(sb);
+
+	return sbinfo ? &sbinfo->sb_marks : NULL;
+}
+
+/* destroy all events sitting in this groups notification queue */
+extern void fsnotify_flush_notify(struct fsnotify_group *group);
+
+/* protects reads of inode and vfsmount marks list */
+extern struct srcu_struct fsnotify_mark_srcu;
+
+/* compare two groups for sorting of marks lists */
+extern int fsnotify_compare_groups(struct fsnotify_group *a,
+				   struct fsnotify_group *b);
+
+/* Destroy all inode marks for given superblock */
+void fsnotify_unmount_inodes(struct fsnotify_sb_info *sbinfo);
+
+/* Destroy all marks attached to an object via connector */
+extern void fsnotify_destroy_marks(fsnotify_connp_t *connp);
+/* run the list of all marks associated with inode and destroy them */
+static inline void fsnotify_clear_marks_by_inode(struct inode *inode)
+{
+	fsnotify_destroy_marks(&inode->i_fsnotify_marks);
+}
+/* run the list of all marks associated with vfsmount and destroy them */
+static inline void fsnotify_clear_marks_by_mount(struct vfsmount *mnt)
+{
+	fsnotify_destroy_marks(&real_mount(mnt)->mnt_fsnotify_marks);
+}
+/* run the list of all marks associated with sb and destroy them */
+static inline void fsnotify_clear_marks_by_sb(struct super_block *sb)
+{
+	fsnotify_destroy_marks(fsnotify_sb_marks(sb));
+}
+
+static inline void fsnotify_clear_marks_by_mntns(struct mnt_namespace *mntns)
+{
+	fsnotify_destroy_marks(&mntns->n_fsnotify_marks);
+}
+
+/*
+ * update the dentry->d_flags of all of inode's children to indicate if inode cares
+ * about events that happen to its children.
+ */
+extern void fsnotify_set_children_dentry_flags(struct inode *inode);
+
+void fsnotify_init_connector_caches(void);
+
+#endif	/* __FS_NOTIFY_FSNOTIFY_H_ */

linux-7.2.3/fs/notify/group.c

@@ -0,0 +1,160 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ *  Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com>
+ */
+
+#include <linux/list.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/srcu.h>
+#include <linux/rculist.h>
+#include <linux/wait.h>
+#include <linux/memcontrol.h>
+
+#include <linux/fsnotify_backend.h>
+#include "fsnotify.h"
+
+#include <linux/atomic.h>
+
+/*
+ * Final freeing of a group
+ */
+static void fsnotify_final_destroy_group(struct fsnotify_group *group)
+{
+	if (group->ops->free_group_priv)
+		group->ops->free_group_priv(group);
+
+	mem_cgroup_put(group->memcg);
+	mutex_destroy(&group->mark_mutex);
+
+	kfree(group);
+}
+
+/*
+ * Stop queueing new events for this group. Once this function returns
+ * fsnotify_add_event() will not add any new events to the group's queue.
+ */
+void fsnotify_group_stop_queueing(struct fsnotify_group *group)
+{
+	spin_lock(&group->notification_lock);
+	group->shutdown = true;
+	spin_unlock(&group->notification_lock);
+}
+
+/*
+ * Trying to get rid of a group. Remove all marks, flush all events and release
+ * the group reference.
+ * Note that another thread calling fsnotify_clear_marks_by_group() may still
+ * hold a ref to the group.
+ */
+void fsnotify_destroy_group(struct fsnotify_group *group)
+{
+	/*
+	 * Stop queueing new events. The code below is careful enough to not
+	 * require this but fanotify needs to stop queuing events even before
+	 * fsnotify_destroy_group() is called and this makes the other callers
+	 * of fsnotify_destroy_group() to see the same behavior.
+	 */
+	fsnotify_group_stop_queueing(group);
+
+	/* Clear all marks for this group and queue them for destruction */
+	fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_ANY);
+
+	/*
+	 * Some marks can still be pinned when waiting for response from
+	 * userspace. Wait for those now. fsnotify_prepare_user_wait() will
+	 * not succeed now so this wait is race-free.
+	 */
+	wait_event(group->notification_waitq, !atomic_read(&group->user_waits));
+
+	/*
+	 * Wait until all marks get really destroyed. We could actually destroy
+	 * them ourselves instead of waiting for worker to do it, however that
+	 * would be racy as worker can already be processing some marks before
+	 * we even entered fsnotify_destroy_group().
+	 */
+	fsnotify_wait_marks_destroyed();
+
+	/*
+	 * Since we have waited for fsnotify_mark_srcu in
+	 * fsnotify_mark_destroy_list() there can be no outstanding event
+	 * notification against this group. So clearing the notification queue
+	 * of all events is reliable now.
+	 */
+	fsnotify_flush_notify(group);
+
+	/*
+	 * Destroy overflow event (we cannot use fsnotify_destroy_event() as
+	 * that deliberately ignores overflow events.
+	 */
+	if (group->overflow_event)
+		group->ops->free_event(group, group->overflow_event);
+
+	fsnotify_put_group(group);
+}
+
+/*
+ * Get reference to a group.
+ */
+void fsnotify_get_group(struct fsnotify_group *group)
+{
+	refcount_inc(&group->refcnt);
+}
+
+/*
+ * Drop a reference to a group.  Free it if it's through.
+ */
+void fsnotify_put_group(struct fsnotify_group *group)
+{
+	if (refcount_dec_and_test(&group->refcnt))
+		fsnotify_final_destroy_group(group);
+}
+EXPORT_SYMBOL_GPL(fsnotify_put_group);
+
+static struct fsnotify_group *__fsnotify_alloc_group(
+				const struct fsnotify_ops *ops,
+				int flags, gfp_t gfp)
+{
+	struct fsnotify_group *group;
+
+	group = kzalloc_obj(struct fsnotify_group, gfp);
+	if (!group)
+		return ERR_PTR(-ENOMEM);
+
+	/* set to 0 when there a no external references to this group */
+	refcount_set(&group->refcnt, 1);
+	atomic_set(&group->user_waits, 0);
+
+	spin_lock_init(&group->notification_lock);
+	INIT_LIST_HEAD(&group->notification_list);
+	init_waitqueue_head(&group->notification_waitq);
+	group->max_events = UINT_MAX;
+
+	mutex_init(&group->mark_mutex);
+	INIT_LIST_HEAD(&group->marks_list);
+
+	group->ops = ops;
+	group->flags = flags;
+
+	return group;
+}
+
+/*
+ * Create a new fsnotify_group and hold a reference for the group returned.
+ */
+struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops,
+					    int flags)
+{
+	gfp_t gfp = (flags & FSNOTIFY_GROUP_USER) ? GFP_KERNEL_ACCOUNT :
+						    GFP_KERNEL;
+
+	return __fsnotify_alloc_group(ops, flags, gfp);
+}
+EXPORT_SYMBOL_GPL(fsnotify_alloc_group);
+
+int fsnotify_fasync(int fd, struct file *file, int on)
+{
+	struct fsnotify_group *group = file->private_data;
+
+	return fasync_helper(fd, file, on, &group->fsn_fa) >= 0 ? 0 : -EIO;
+}

linux-7.2.3/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.

linux-7.2.3/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

linux-7.2.3/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

linux-7.2.3/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,
+};

linux-7.2.3/fs/notify/inotify/inotify_user.c

@@ -0,0 +1,861 @@
+// 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;
+	__u32 old_mask, new_mask;
+	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);
+	old_mask = fsn_mark->mask;
+	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);
+	new_mask = fsn_mark->mask;
+	spin_unlock(&fsn_mark->lock);
+
+	if (old_mask != new_mask) {
+		/* more bits in old than in new? */
+		int dropped = (old_mask & ~new_mask);
+		/* more bits in this fsn_mark than the inode's mask? */
+		int do_inode = (new_mask & ~READ_ONCE(inode->i_fsnotify_mask));
+
+		/* update the inode with this new fsn_mark */
+		if (dropped || do_inode)
+			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);

linux-7.2.3/fs/notify/notification.c

@@ -0,0 +1,193 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ *  Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com>
+ */
+
+/*
+ * Basic idea behind the notification queue: An fsnotify group (like inotify)
+ * sends the userspace notification about events asynchronously some time after
+ * the event happened.  When inotify gets an event it will need to add that
+ * event to the group notify queue.  Since a single event might need to be on
+ * multiple group's notification queues we can't add the event directly to each
+ * queue and instead add a small "event_holder" to each queue.  This event_holder
+ * has a pointer back to the original event.  Since the majority of events are
+ * going to end up on one, and only one, notification queue we embed one
+ * event_holder into each event.  This means we have a single allocation instead
+ * of always needing two.  If the embedded event_holder is already in use by
+ * another group a new event_holder (from fsnotify_event_holder_cachep) will be
+ * allocated and used.
+ */
+
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/mount.h>
+#include <linux/mutex.h>
+#include <linux/namei.h>
+#include <linux/path.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+
+#include <linux/atomic.h>
+
+#include <linux/fsnotify_backend.h>
+#include "fsnotify.h"
+
+static atomic_t fsnotify_sync_cookie = ATOMIC_INIT(0);
+
+/**
+ * fsnotify_get_cookie - return a unique cookie for use in synchronizing events.
+ * Called from fsnotify_move, which is inlined into filesystem modules.
+ */
+u32 fsnotify_get_cookie(void)
+{
+	return atomic_inc_return(&fsnotify_sync_cookie);
+}
+EXPORT_SYMBOL_GPL(fsnotify_get_cookie);
+
+void fsnotify_destroy_event(struct fsnotify_group *group,
+			    struct fsnotify_event *event)
+{
+	/* Overflow events are per-group and we don't want to free them */
+	if (!event || event == group->overflow_event)
+		return;
+	/*
+	 * If the event is still queued, we have a problem... Do an unreliable
+	 * lockless check first to avoid locking in the common case. The
+	 * locking may be necessary for permission events which got removed
+	 * from the list by a different CPU than the one freeing the event.
+	 */
+	if (!list_empty(&event->list)) {
+		spin_lock(&group->notification_lock);
+		WARN_ON(!list_empty(&event->list));
+		spin_unlock(&group->notification_lock);
+	}
+	group->ops->free_event(group, event);
+}
+
+/*
+ * Try to add an event to the notification queue.
+ * The group can later pull this event off the queue to deal with.
+ * The group can use the @merge hook to merge the event with a queued event.
+ * The group can use the @insert hook to insert the event into hash table.
+ * The function returns:
+ * 0 if the event was added to a queue
+ * 1 if the event was merged with some other queued event
+ * 2 if the event was not queued - either the queue of events has overflown
+ *   or the group is shutting down.
+ */
+int fsnotify_insert_event(struct fsnotify_group *group,
+			  struct fsnotify_event *event,
+			  int (*merge)(struct fsnotify_group *,
+				       struct fsnotify_event *),
+			  void (*insert)(struct fsnotify_group *,
+					 struct fsnotify_event *))
+{
+	int ret = 0;
+	struct list_head *list = &group->notification_list;
+
+	pr_debug("%s: group=%p event=%p\n", __func__, group, event);
+
+	spin_lock(&group->notification_lock);
+
+	if (group->shutdown) {
+		spin_unlock(&group->notification_lock);
+		return 2;
+	}
+
+	if (event == group->overflow_event ||
+	    group->q_len >= group->max_events) {
+		ret = 2;
+		/* Queue overflow event only if it isn't already queued */
+		if (!list_empty(&group->overflow_event->list)) {
+			spin_unlock(&group->notification_lock);
+			return ret;
+		}
+		event = group->overflow_event;
+		goto queue;
+	}
+
+	if (!list_empty(list) && merge) {
+		ret = merge(group, event);
+		if (ret) {
+			spin_unlock(&group->notification_lock);
+			return ret;
+		}
+	}
+
+queue:
+	group->q_len++;
+	list_add_tail(&event->list, list);
+	if (insert)
+		insert(group, event);
+	spin_unlock(&group->notification_lock);
+
+	wake_up(&group->notification_waitq);
+	kill_fasync(&group->fsn_fa, SIGIO, POLL_IN);
+	return ret;
+}
+
+void fsnotify_remove_queued_event(struct fsnotify_group *group,
+				  struct fsnotify_event *event)
+{
+	assert_spin_locked(&group->notification_lock);
+	/*
+	 * We need to init list head for the case of overflow event so that
+	 * check in fsnotify_add_event() works
+	 */
+	list_del_init(&event->list);
+	group->q_len--;
+}
+
+/*
+ * Return the first event on the notification list without removing it.
+ * Returns NULL if the list is empty.
+ */
+struct fsnotify_event *fsnotify_peek_first_event(struct fsnotify_group *group)
+{
+	assert_spin_locked(&group->notification_lock);
+
+	if (fsnotify_notify_queue_is_empty(group))
+		return NULL;
+
+	return list_first_entry(&group->notification_list,
+				struct fsnotify_event, list);
+}
+
+/*
+ * Remove and return the first event from the notification list.  It is the
+ * responsibility of the caller to destroy the obtained event
+ */
+struct fsnotify_event *fsnotify_remove_first_event(struct fsnotify_group *group)
+{
+	struct fsnotify_event *event = fsnotify_peek_first_event(group);
+
+	if (!event)
+		return NULL;
+
+	pr_debug("%s: group=%p event=%p\n", __func__, group, event);
+
+	fsnotify_remove_queued_event(group, event);
+
+	return event;
+}
+
+/*
+ * Called when a group is being torn down to clean up any outstanding
+ * event notifications.
+ */
+void fsnotify_flush_notify(struct fsnotify_group *group)
+{
+	struct fsnotify_event *event;
+
+	spin_lock(&group->notification_lock);
+	while (!fsnotify_notify_queue_is_empty(group)) {
+		event = fsnotify_remove_first_event(group);
+		spin_unlock(&group->notification_lock);
+		fsnotify_destroy_event(group, event);
+		spin_lock(&group->notification_lock);
+	}
+	spin_unlock(&group->notification_lock);
+}