1 files changed, 159 insertions, 95 deletions

diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 7cc7d3fb1862..b372fb2c56bd 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * fs/inotify_user.c - inotify support for userspace
  *
@@ -10,16 +11,6 @@
  *
  * Copyright (C) 2009 Eric Paris <Red Hat Inc>
  * inotify was largely rewriten to make use of the fsnotify infrastructure
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the
- * Free Software Foundation; either version 2, or (at your option) any
- * later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
  */
 
 #include <linux/file.h>
@@ -38,39 +29,53 @@
 #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 __read_mostly;
+struct kmem_cache *inotify_inode_mark_cachep __ro_after_init;
 
 #ifdef CONFIG_SYSCTL
 
 #include <linux/sysctl.h>
 
-static int zero;
+static long it_zero = 0;
+static long it_int_max = INT_MAX;
 
-struct ctl_table inotify_table[] = {
+static const struct ctl_table inotify_table[] = {
 	{
 		.procname	= "max_user_instances",
 		.data		= &init_user_ns.ucount_max[UCOUNT_INOTIFY_INSTANCES],
-		.maxlen		= sizeof(int),
+		.maxlen		= sizeof(long),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
+		.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(int),
+		.maxlen		= sizeof(long),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
+		.proc_handler	= proc_doulongvec_minmax,
+		.extra1		= &it_zero,
+		.extra2		= &it_int_max,
 	},
 	{
 		.procname	= "max_queued_events",
@@ -78,44 +83,68 @@ struct ctl_table inotify_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero
+		.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(u32 arg)
+static inline __u32 inotify_arg_to_mask(struct inode *inode, u32 arg)
 {
 	__u32 mask;
 
 	/*
-	 * everything should accept their own ignored, cares about children,
-	 * and should receive events when the inode is unmounted
+	 * Everything should receive events when the inode is unmounted.
+	 * All directories care about children.
 	 */
-	mask = (FS_IN_IGNORED | FS_EVENT_ON_CHILD | FS_UNMOUNT);
+	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 & (IN_ALL_EVENTS | IN_ONESHOT | IN_EXCL_UNLINK));
+	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);
 }
 
-/* intofiy userspace file descriptor functions */
-static unsigned int inotify_poll(struct file *file, poll_table *wait)
+/* inotify userspace file descriptor functions */
+static __poll_t inotify_poll(struct file *file, poll_table *wait)
 {
 	struct fsnotify_group *group = file->private_data;
-	int ret = 0;
+	__poll_t ret = 0;
 
 	poll_wait(file, &group->notification_waitq, wait);
 	spin_lock(&group->notification_lock);
 	if (!fsnotify_notify_queue_is_empty(group))
-		ret = POLLIN | POLLRDNORM;
+		ret = EPOLLIN | EPOLLRDNORM;
 	spin_unlock(&group->notification_lock);
 
 	return ret;
@@ -144,10 +173,9 @@ static struct fsnotify_event *get_one_event(struct fsnotify_group *group,
 	size_t event_size = sizeof(struct inotify_event);
 	struct fsnotify_event *event;
 
-	if (fsnotify_notify_queue_is_empty(group))
-		return NULL;
-
 	event = fsnotify_peek_first_event(group);
+	if (!event)
+		return NULL;
 
 	pr_debug("%s: group=%p event=%p\n", __func__, group, event);
 
@@ -188,7 +216,7 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
 	 */
 	pad_name_len = round_event_name_len(fsn_event);
 	inotify_event.len = pad_name_len;
-	inotify_event.mask = inotify_mask_to_arg(fsn_event->mask);
+	inotify_event.mask = inotify_mask_to_arg(event->mask);
 	inotify_event.wd = event->wd;
 	inotify_event.cookie = event->sync_cookie;
 
@@ -307,6 +335,20 @@ static long inotify_ioctl(struct file *file, unsigned int cmd,
 		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;
@@ -327,7 +369,8 @@ static const struct file_operations inotify_fops = {
 /*
  * find_inode - resolve a user-given path to a specific inode
  */
-static int inotify_find_inode(const char __user *dirname, struct path *path, unsigned flags)
+static int inotify_find_inode(const char __user *dirname, struct path *path,
+						unsigned int flags, __u64 mask)
 {
 	int error;
 
@@ -335,9 +378,16 @@ static int inotify_find_inode(const char __user *dirname, struct path *path, uns
 	if (error)
 		return error;
 	/* you can only watch an inode if you have read permissions on it */
-	error = inode_permission(path->dentry->d_inode, MAY_READ);
+	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;
 }
 
@@ -376,7 +426,7 @@ static struct inotify_inode_mark *inotify_idr_find_locked(struct fsnotify_group
 
 		fsnotify_get_mark(fsn_mark);
 		/* One ref for being in the idr, one ref we just took */
-		BUG_ON(atomic_read(&fsn_mark->refcnt) < 2);
+		BUG_ON(refcount_read(&fsn_mark->refcnt) < 2);
 	}
 
 	return i_mark;
@@ -446,7 +496,7 @@ static void inotify_remove_from_idr(struct fsnotify_group *group,
 	 * One ref for being in the idr
 	 * one ref grabbed by inotify_idr_find
 	 */
-	if (unlikely(atomic_read(&i_mark->fsn_mark.refcnt) < 2)) {
+	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.. */
@@ -473,8 +523,8 @@ void inotify_ignored_and_remove_idr(struct fsnotify_mark *fsn_mark,
 	struct inotify_inode_mark *i_mark;
 
 	/* Queue ignore event for the watch */
-	inotify_handle_event(group, NULL, fsn_mark, NULL, FS_IN_IGNORED,
-			     NULL, FSNOTIFY_EVENT_NONE, NULL, 0, NULL);
+	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 */
@@ -490,24 +540,28 @@ static int inotify_update_existing_watch(struct fsnotify_group *group,
 	struct fsnotify_mark *fsn_mark;
 	struct inotify_inode_mark *i_mark;
 	__u32 old_mask, new_mask;
-	__u32 mask;
-	int add = (arg & IN_MASK_ADD);
+	int replace = !(arg & IN_MASK_ADD);
+	int create = (arg & IN_MASK_CREATE);
 	int ret;
 
-	mask = inotify_arg_to_mask(arg);
-
-	fsn_mark = fsnotify_find_mark(&inode->i_fsnotify_marks, group);
+	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 (add)
-		fsn_mark->mask |= mask;
-	else
-		fsn_mark->mask = 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);
 
@@ -515,7 +569,7 @@ static int inotify_update_existing_watch(struct fsnotify_group *group,
 		/* 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 & ~inode->i_fsnotify_mask);
+		int do_inode = (new_mask & ~READ_ONCE(inode->i_fsnotify_mask));
 
 		/* update the inode with this new fsn_mark */
 		if (dropped || do_inode)
@@ -526,6 +580,7 @@ static int inotify_update_existing_watch(struct fsnotify_group *group,
 	/* return the wd */
 	ret = i_mark->wd;
 
+out:
 	/* match the get from fsnotify_find_mark() */
 	fsnotify_put_mark(fsn_mark);
 
@@ -537,19 +592,17 @@ static int inotify_new_watch(struct fsnotify_group *group,
 			     u32 arg)
 {
 	struct inotify_inode_mark *tmp_i_mark;
-	__u32 mask;
 	int ret;
 	struct idr *idr = &group->inotify_data.idr;
 	spinlock_t *idr_lock = &group->inotify_data.idr_lock;
 
-	mask = inotify_arg_to_mask(arg);
-
 	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 = mask;
+	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);
@@ -564,7 +617,7 @@ static int inotify_new_watch(struct fsnotify_group *group,
 	}
 
 	/* we are on the idr, now get on the inode */
-	ret = fsnotify_add_mark_locked(&tmp_i_mark->fsn_mark, inode, NULL, 0);
+	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);
@@ -586,13 +639,13 @@ static int inotify_update_watch(struct fsnotify_group *group, struct inode *inod
 {
 	int ret = 0;
 
-	mutex_lock(&group->mark_mutex);
+	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);
-	mutex_unlock(&group->mark_mutex);
+	fsnotify_group_unlock(group);
 
 	return ret;
 }
@@ -602,22 +655,25 @@ 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);
+	group = fsnotify_alloc_group(&inotify_fsnotify_ops,
+				     FSNOTIFY_GROUP_USER);
 	if (IS_ERR(group))
 		return group;
 
-	oevent = kmalloc(sizeof(struct inotify_event_info), GFP_KERNEL);
+	oevent = kmalloc(sizeof(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, NULL, FS_Q_OVERFLOW);
+	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);
@@ -635,7 +691,7 @@ static struct fsnotify_group *inotify_new_group(unsigned int max_events)
 
 
 /* inotify syscalls */
-SYSCALL_DEFINE1(inotify_init1, int, flags)
+static int do_inotify_init(int flags)
 {
 	struct fsnotify_group *group;
 	int ret;
@@ -660,9 +716,14 @@ SYSCALL_DEFINE1(inotify_init1, int, flags)
 	return ret;
 }
 
+SYSCALL_DEFINE1(inotify_init1, int, flags)
+{
+	return do_inotify_init(flags);
+}
+
 SYSCALL_DEFINE0(inotify_init)
 {
-	return sys_inotify_init1(0);
+	return do_inotify_init(0);
 }
 
 SYSCALL_DEFINE3(inotify_add_watch, int, fd, const char __user *, pathname,
@@ -671,7 +732,6 @@ SYSCALL_DEFINE3(inotify_add_watch, int, fd, const char __user *, pathname,
 	struct fsnotify_group *group;
 	struct inode *inode;
 	struct path path;
-	struct fd f;
 	int ret;
 	unsigned flags = 0;
 
@@ -691,34 +751,35 @@ SYSCALL_DEFINE3(inotify_add_watch, int, fd, const char __user *, pathname,
 	if (unlikely(!(mask & ALL_INOTIFY_BITS)))
 		return -EINVAL;
 
-	f = fdget(fd);
-	if (unlikely(!f.file))
+	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(f.file->f_op != &inotify_fops)) {
-		ret = -EINVAL;
-		goto fput_and_out;
-	}
+	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);
+	ret = inotify_find_inode(pathname, &path, flags,
+			(mask & IN_ALL_EVENTS));
 	if (ret)
-		goto fput_and_out;
+		return ret;
 
 	/* inode held in place by reference to path; group by fget on fd */
 	inode = path.dentry->d_inode;
-	group = f.file->private_data;
+	group = fd_file(f)->private_data;
 
 	/* create/update an inode mark */
 	ret = inotify_update_watch(group, inode, mask);
 	path_put(&path);
-fput_and_out:
-	fdput(f);
 	return ret;
 }
 
@@ -726,35 +787,26 @@ SYSCALL_DEFINE2(inotify_rm_watch, int, fd, __s32, wd)
 {
 	struct fsnotify_group *group;
 	struct inotify_inode_mark *i_mark;
-	struct fd f;
-	int ret = 0;
+	CLASS(fd, f)(fd);
 
-	f = fdget(fd);
-	if (unlikely(!f.file))
+	if (fd_empty(f))
 		return -EBADF;
 
 	/* verify that this is indeed an inotify instance */
-	ret = -EINVAL;
-	if (unlikely(f.file->f_op != &inotify_fops))
-		goto out;
+	if (unlikely(fd_file(f)->f_op != &inotify_fops))
+		return -EINVAL;
 
-	group = f.file->private_data;
+	group = fd_file(f)->private_data;
 
-	ret = -EINVAL;
 	i_mark = inotify_idr_find(group, wd);
 	if (unlikely(!i_mark))
-		goto out;
-
-	ret = 0;
+		return -EINVAL;
 
 	fsnotify_destroy_mark(&i_mark->fsn_mark, group);
 
 	/* match ref taken by inotify_idr_find */
 	fsnotify_put_mark(&i_mark->fsn_mark);
-
-out:
-	fdput(f);
-	return ret;
+	return 0;
 }
 
 /*
@@ -764,6 +816,18 @@ out:
  */
 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);
@@ -779,17 +843,17 @@ static int __init inotify_user_setup(void)
 	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_EXCL_UNLINK != FS_EXCL_UNLINK);
 	BUILD_BUG_ON(IN_ISDIR != FS_ISDIR);
-	BUILD_BUG_ON(IN_ONESHOT != FS_IN_ONESHOT);
 
-	BUG_ON(hweight32(ALL_INOTIFY_BITS) != 21);
+	BUILD_BUG_ON(HWEIGHT32(ALL_INOTIFY_BITS) != 22);
 
-	inotify_inode_mark_cachep = KMEM_CACHE(inotify_inode_mark, SLAB_PANIC);
+	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] = 8192;
+	init_user_ns.ucount_max[UCOUNT_INOTIFY_WATCHES] = watches_max;
+	inotify_sysctls_init();
 
 	return 0;
 }