From 244b2c5ca8b14627e4a17755e5922221e121c771 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Wed, 09 Oct 2024 06:15:07 +0000
Subject: [PATCH] change system file
---
kernel/fs/notify/fsnotify.c | 323 ++++++++++++++++++++++++++++++++++++++++-------------
1 files changed, 244 insertions(+), 79 deletions(-)
diff --git a/kernel/fs/notify/fsnotify.c b/kernel/fs/notify/fsnotify.c
index e8ee426..30d422b 100644
--- a/kernel/fs/notify/fsnotify.c
+++ b/kernel/fs/notify/fsnotify.c
@@ -1,19 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com>
- *
- * 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.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; see the file COPYING. If not, write to
- * the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#include <linux/dcache.h>
@@ -48,7 +35,7 @@
* Called during unmount with no locks held, so needs to be safe against
* concurrent modifiers. We temporarily drop sb->s_inode_list_lock and CAN block.
*/
-void fsnotify_unmount_inodes(struct super_block *sb)
+static void fsnotify_unmount_inodes(struct super_block *sb)
{
struct inode *inode, *iput_inode = NULL;
@@ -70,6 +57,9 @@
* doing an __iget/iput with SB_ACTIVE clear would actually
* evict all inodes with zero i_count from icache which is
* unnecessarily violent and may in fact be illegal to do.
+ * However, we should have been called /after/ evict_inodes
+ * removed all zero refcount inodes, in any case. Test to
+ * be sure.
*/
if (!atomic_read(&inode->i_count)) {
spin_unlock(&inode->i_lock);
@@ -84,7 +74,7 @@
iput(iput_inode);
/* for each watch, send FS_UNMOUNT and then remove it */
- fsnotify(inode, FS_UNMOUNT, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
+ fsnotify_inode(inode, FS_UNMOUNT);
fsnotify_inode_delete(inode);
@@ -100,6 +90,12 @@
/* Wait for outstanding inode references from connectors */
wait_var_event(&sb->s_fsnotify_inode_refs,
!atomic_long_read(&sb->s_fsnotify_inode_refs));
+}
+
+void fsnotify_sb_delete(struct super_block *sb)
+{
+ fsnotify_unmount_inodes(sb);
+ fsnotify_clear_marks_by_sb(sb);
}
/*
@@ -146,52 +142,178 @@
spin_unlock(&inode->i_lock);
}
-/* Notify this dentry's parent about a child's events. */
-int __fsnotify_parent(const struct path *path, struct dentry *dentry, __u32 mask)
+/* Are inode/sb/mount interested in parent and name info with this event? */
+static bool fsnotify_event_needs_parent(struct inode *inode, struct mount *mnt,
+ __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(inode->i_fsnotify_mask);
+ marks_mask |= fsnotify_parent_needed_mask(inode->i_sb->s_fsnotify_mask);
+ if (mnt)
+ marks_mask |= fsnotify_parent_needed_mask(mnt->mnt_fsnotify_mask);
+
+ /* Did they subscribe for this event with parent/name info? */
+ return mask & marks_mask;
+}
+
+/*
+ * 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);
+ struct mount *mnt = path ? real_mount(path->mnt) : NULL;
+ struct inode *inode = d_inode(dentry);
struct dentry *parent;
- struct inode *p_inode;
+ 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;
- if (!dentry)
- dentry = path->dentry;
-
- if (!(dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED))
+ /*
+ * Do inode/sb/mount care about parent and name info on non-dir?
+ * Do they care about any event at all?
+ */
+ if (!inode->i_fsnotify_marks && !inode->i_sb->s_fsnotify_marks &&
+ (!mnt || !mnt->mnt_fsnotify_marks) && !parent_watched)
return 0;
+ parent = NULL;
+ parent_needed = fsnotify_event_needs_parent(inode, mnt, 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;
-
- if (unlikely(!fsnotify_inode_watches_children(p_inode))) {
+ p_mask = fsnotify_inode_watches_children(p_inode);
+ if (unlikely(parent_watched && !p_mask))
__fsnotify_update_child_dentry_flags(p_inode);
- } else if (p_inode->i_fsnotify_mask & mask & ALL_FSNOTIFY_EVENTS) {
- struct name_snapshot name;
- /* we are notifying a parent so come up with the new mask which
- * specifies these are events which came from a child. */
- mask |= FS_EVENT_ON_CHILD;
+ /*
+ * Include parent/name in notification either if some notification
+ * groups require parent info or the parent is interested in this event.
+ */
+ parent_interested = mask & p_mask & ALL_FSNOTIFY_EVENTS;
+ 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);
- if (path)
- ret = fsnotify(p_inode, mask, path, FSNOTIFY_EVENT_PATH,
- name.name, 0);
- else
- ret = fsnotify(p_inode, mask, dentry->d_inode, FSNOTIFY_EVENT_INODE,
- name.name, 0);
- release_dentry_name_snapshot(&name);
+ 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 send_to_group(struct inode *to_tell,
- __u32 mask, const void *data,
- int data_is, u32 cookie,
- const unsigned char *file_name,
- struct fsnotify_iter_info *iter_info)
+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 ((inode_mark->mask & FS_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;
+
+ if (parent_mark) {
+ /*
+ * parent_mark indicates that the parent inode is watching
+ * children and interested in this event, which is an event
+ * possible on child. But is *this mark* watching children and
+ * interested in this event?
+ */
+ if (parent_mark->mask & FS_EVENT_ON_CHILD) {
+ ret = fsnotify_handle_inode_event(group, parent_mark, mask,
+ data, data_type, dir, name, 0);
+ if (ret)
+ return ret;
+ }
+ if (!inode_mark)
+ return 0;
+ }
+
+ if (mask & FS_EVENT_ON_CHILD) {
+ /*
+ * 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).
+ * The child watcher is expecting an event without a file name
+ * and without the FS_EVENT_ON_CHILD flag.
+ */
+ mask &= ~FS_EVENT_ON_CHILD;
+ 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);
@@ -227,16 +349,20 @@
}
}
- pr_debug("%s: group=%p to_tell=%p mask=%x marks_mask=%x marks_ignored_mask=%x"
- " data=%p data_is=%d cookie=%d\n",
- __func__, group, to_tell, mask, marks_mask, marks_ignored_mask,
- data, data_is, cookie);
+ pr_debug("%s: group=%p mask=%x marks_mask=%x marks_ignored_mask=%x data=%p data_type=%d dir=%p cookie=%d\n",
+ __func__, group, mask, marks_mask, marks_ignored_mask,
+ data, data_type, dir, cookie);
if (!(test_mask & marks_mask & ~marks_ignored_mask))
return 0;
- return group->ops->handle_event(group, to_tell, mask, data, data_is,
- file_name, cookie, iter_info);
+ 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 **connp)
@@ -314,27 +440,50 @@
}
/*
- * 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.
+ * 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 -
+ * either @dir or @inode must be non-NULL.
+ * if both are non-NULL event may be reported to both.
+ * @cookie: inotify rename cookie
*/
-int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_is,
- const unsigned char *file_name, u32 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 fsnotify_iter_info iter_info = {};
- struct mount *mnt;
+ struct super_block *sb;
+ struct mount *mnt = NULL;
+ struct inode *parent = NULL;
int ret = 0;
- __u32 test_mask = (mask & ALL_FSNOTIFY_EVENTS);
+ __u32 test_mask, marks_mask;
- if (data_is == FSNOTIFY_EVENT_PATH)
- mnt = real_mount(((const struct path *)data)->mnt);
- else
- mnt = NULL;
+ if (path)
+ mnt = real_mount(path->mnt);
- /* An event "on child" is not intended for a mount mark */
- if (mask & FS_EVENT_ON_CHILD)
- mnt = NULL;
+ if (!inode) {
+ /* Dirent event - report on TYPE_INODE to dir */
+ inode = dir;
+ } 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.
+ */
+ parent = dir;
+ }
+ sb = inode->i_sb;
/*
* Optimization: srcu_read_lock() has a memory barrier which can
@@ -343,36 +492,54 @@
* SRCU because we have no references to any objects and do not
* need SRCU to keep them "alive".
*/
- if (!to_tell->i_fsnotify_marks &&
- (!mnt || !mnt->mnt_fsnotify_marks))
+ if (!sb->s_fsnotify_marks &&
+ (!mnt || !mnt->mnt_fsnotify_marks) &&
+ (!inode || !inode->i_fsnotify_marks) &&
+ (!parent || !parent->i_fsnotify_marks))
return 0;
+
+ marks_mask = sb->s_fsnotify_mask;
+ if (mnt)
+ marks_mask |= mnt->mnt_fsnotify_mask;
+ if (inode)
+ marks_mask |= inode->i_fsnotify_mask;
+ if (parent)
+ marks_mask |= parent->i_fsnotify_mask;
+
+
/*
* if this is a modify event we may need to clear the ignored masks
- * otherwise return if neither the inode nor the vfsmount care about
- * this type of event.
+ * otherwise return if none of the marks care about this type of event.
*/
- if (!(mask & FS_MODIFY) &&
- !(test_mask & to_tell->i_fsnotify_mask) &&
- !(mnt && test_mask & mnt->mnt_fsnotify_mask))
+ test_mask = (mask & ALL_FSNOTIFY_EVENTS);
+ if (!(mask & FS_MODIFY) && !(test_mask & marks_mask))
return 0;
iter_info.srcu_idx = srcu_read_lock(&fsnotify_mark_srcu);
- iter_info.marks[FSNOTIFY_OBJ_TYPE_INODE] =
- fsnotify_first_mark(&to_tell->i_fsnotify_marks);
+ iter_info.marks[FSNOTIFY_OBJ_TYPE_SB] =
+ fsnotify_first_mark(&sb->s_fsnotify_marks);
if (mnt) {
iter_info.marks[FSNOTIFY_OBJ_TYPE_VFSMOUNT] =
fsnotify_first_mark(&mnt->mnt_fsnotify_marks);
}
+ if (inode) {
+ iter_info.marks[FSNOTIFY_OBJ_TYPE_INODE] =
+ fsnotify_first_mark(&inode->i_fsnotify_marks);
+ }
+ if (parent) {
+ iter_info.marks[FSNOTIFY_OBJ_TYPE_PARENT] =
+ fsnotify_first_mark(&parent->i_fsnotify_marks);
+ }
/*
- * We need to merge inode & vfsmount mark lists so that inode mark
- * ignore masks are properly reflected for mount mark notifications.
+ * 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(to_tell, mask, data, data_is, cookie,
- file_name, &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;
@@ -387,13 +554,11 @@
}
EXPORT_SYMBOL_GPL(fsnotify);
-extern struct kmem_cache *fsnotify_mark_connector_cachep;
-
static __init int fsnotify_init(void)
{
int ret;
- BUG_ON(hweight32(ALL_FSNOTIFY_BITS) != 23);
+ BUILD_BUG_ON(HWEIGHT32(ALL_FSNOTIFY_BITS) != 25);
ret = init_srcu_struct(&fsnotify_mark_srcu);
if (ret)
--
Gitblit v1.6.2