OpenCloudOS-Kernel/fs/debugfs/inode.c

710 lines
18 KiB
C
Raw Normal View History

/*
* inode.c - part of debugfs, a tiny little debug file system
*
* Copyright (C) 2004 Greg Kroah-Hartman <greg@kroah.com>
* Copyright (C) 2004 IBM Inc.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License version
* 2 as published by the Free Software Foundation.
*
* debugfs is for people to use instead of /proc or /sys.
* See Documentation/DocBook/kernel-api for more details.
*
*/
#include <linux/module.h>
#include <linux/fs.h>
#include <linux/mount.h>
#include <linux/pagemap.h>
#include <linux/init.h>
#include <linux/kobject.h>
#include <linux/namei.h>
#include <linux/debugfs.h>
#include <linux/fsnotify.h>
#include <linux/string.h>
#include <linux/seq_file.h>
#include <linux/parser.h>
#include <linux/magic.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#define DEBUGFS_DEFAULT_MODE 0700
static struct vfsmount *debugfs_mount;
static int debugfs_mount_count;
static bool debugfs_registered;
static struct inode *debugfs_get_inode(struct super_block *sb, umode_t mode, dev_t dev,
void *data, const struct file_operations *fops)
{
struct inode *inode = new_inode(sb);
if (inode) {
inode->i_ino = get_next_ino();
inode->i_mode = mode;
inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
switch (mode & S_IFMT) {
default:
init_special_inode(inode, mode, dev);
break;
case S_IFREG:
inode->i_fop = fops ? fops : &debugfs_file_operations;
inode->i_private = data;
break;
case S_IFLNK:
inode->i_op = &debugfs_link_operations;
inode->i_private = data;
break;
case S_IFDIR:
inode->i_op = &simple_dir_inode_operations;
inode->i_fop = &simple_dir_operations;
/* directory inodes start off with i_nlink == 2
* (for "." entry) */
inc_nlink(inode);
break;
}
}
return inode;
}
/* SMP-safe */
static int debugfs_mknod(struct inode *dir, struct dentry *dentry,
umode_t mode, dev_t dev, void *data,
const struct file_operations *fops)
{
struct inode *inode;
int error = -EPERM;
if (dentry->d_inode)
return -EEXIST;
inode = debugfs_get_inode(dir->i_sb, mode, dev, data, fops);
if (inode) {
d_instantiate(dentry, inode);
dget(dentry);
error = 0;
}
return error;
}
static int debugfs_mkdir(struct dentry *dentry, umode_t mode)
{
struct inode *dir = dentry->d_parent->d_inode;
int res;
mode = (mode & (S_IRWXUGO | S_ISVTX)) | S_IFDIR;
res = debugfs_mknod(dir, dentry, mode, 0, NULL, NULL);
if (!res) {
inc_nlink(dir);
fsnotify_mkdir(dir, dentry);
}
return res;
}
static int debugfs_link(struct dentry *dentry, umode_t mode,
void *data)
{
struct inode *dir = dentry->d_parent->d_inode;
mode = (mode & S_IALLUGO) | S_IFLNK;
return debugfs_mknod(dir, dentry, mode, 0, data, NULL);
}
static int debugfs_create(struct dentry *dentry, umode_t mode,
void *data, const struct file_operations *fops)
{
struct inode *dir = dentry->d_parent->d_inode;
int res;
mode = (mode & S_IALLUGO) | S_IFREG;
res = debugfs_mknod(dir, dentry, mode, 0, data, fops);
if (!res)
fsnotify_create(dir, dentry);
return res;
}
static inline int debugfs_positive(struct dentry *dentry)
{
return dentry->d_inode && !d_unhashed(dentry);
}
struct debugfs_mount_opts {
kuid_t uid;
kgid_t gid;
umode_t mode;
};
enum {
Opt_uid,
Opt_gid,
Opt_mode,
Opt_err
};
static const match_table_t tokens = {
{Opt_uid, "uid=%u"},
{Opt_gid, "gid=%u"},
{Opt_mode, "mode=%o"},
{Opt_err, NULL}
};
struct debugfs_fs_info {
struct debugfs_mount_opts mount_opts;
};
static int debugfs_parse_options(char *data, struct debugfs_mount_opts *opts)
{
substring_t args[MAX_OPT_ARGS];
int option;
int token;
kuid_t uid;
kgid_t gid;
char *p;
opts->mode = DEBUGFS_DEFAULT_MODE;
while ((p = strsep(&data, ",")) != NULL) {
if (!*p)
continue;
token = match_token(p, tokens, args);
switch (token) {
case Opt_uid:
if (match_int(&args[0], &option))
return -EINVAL;
uid = make_kuid(current_user_ns(), option);
if (!uid_valid(uid))
return -EINVAL;
opts->uid = uid;
break;
case Opt_gid:
if (match_int(&args[0], &option))
return -EINVAL;
gid = make_kgid(current_user_ns(), option);
if (!gid_valid(gid))
return -EINVAL;
opts->gid = gid;
break;
case Opt_mode:
if (match_octal(&args[0], &option))
return -EINVAL;
opts->mode = option & S_IALLUGO;
break;
/*
* We might like to report bad mount options here;
* but traditionally debugfs has ignored all mount options
*/
}
}
return 0;
}
static int debugfs_apply_options(struct super_block *sb)
{
struct debugfs_fs_info *fsi = sb->s_fs_info;
struct inode *inode = sb->s_root->d_inode;
struct debugfs_mount_opts *opts = &fsi->mount_opts;
inode->i_mode &= ~S_IALLUGO;
inode->i_mode |= opts->mode;
inode->i_uid = opts->uid;
inode->i_gid = opts->gid;
return 0;
}
static int debugfs_remount(struct super_block *sb, int *flags, char *data)
{
int err;
struct debugfs_fs_info *fsi = sb->s_fs_info;
fs: push sync_filesystem() down to the file system's remount_fs() Previously, the no-op "mount -o mount /dev/xxx" operation when the file system is already mounted read-write causes an implied, unconditional syncfs(). This seems pretty stupid, and it's certainly documented or guaraunteed to do this, nor is it particularly useful, except in the case where the file system was mounted rw and is getting remounted read-only. However, it's possible that there might be some file systems that are actually depending on this behavior. In most file systems, it's probably fine to only call sync_filesystem() when transitioning from read-write to read-only, and there are some file systems where this is not needed at all (for example, for a pseudo-filesystem or something like romfs). Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Cc: linux-fsdevel@vger.kernel.org Cc: Christoph Hellwig <hch@infradead.org> Cc: Artem Bityutskiy <dedekind1@gmail.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Evgeniy Dushistov <dushistov@mail.ru> Cc: Jan Kara <jack@suse.cz> Cc: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Anders Larsen <al@alarsen.net> Cc: Phillip Lougher <phillip@squashfs.org.uk> Cc: Kees Cook <keescook@chromium.org> Cc: Mikulas Patocka <mikulas@artax.karlin.mff.cuni.cz> Cc: Petr Vandrovec <petr@vandrovec.name> Cc: xfs@oss.sgi.com Cc: linux-btrfs@vger.kernel.org Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Cc: codalist@coda.cs.cmu.edu Cc: linux-ext4@vger.kernel.org Cc: linux-f2fs-devel@lists.sourceforge.net Cc: fuse-devel@lists.sourceforge.net Cc: cluster-devel@redhat.com Cc: linux-mtd@lists.infradead.org Cc: jfs-discussion@lists.sourceforge.net Cc: linux-nfs@vger.kernel.org Cc: linux-nilfs@vger.kernel.org Cc: linux-ntfs-dev@lists.sourceforge.net Cc: ocfs2-devel@oss.oracle.com Cc: reiserfs-devel@vger.kernel.org
2014-03-13 22:14:33 +08:00
sync_filesystem(sb);
err = debugfs_parse_options(data, &fsi->mount_opts);
if (err)
goto fail;
debugfs_apply_options(sb);
fail:
return err;
}
static int debugfs_show_options(struct seq_file *m, struct dentry *root)
{
struct debugfs_fs_info *fsi = root->d_sb->s_fs_info;
struct debugfs_mount_opts *opts = &fsi->mount_opts;
if (!uid_eq(opts->uid, GLOBAL_ROOT_UID))
seq_printf(m, ",uid=%u",
from_kuid_munged(&init_user_ns, opts->uid));
if (!gid_eq(opts->gid, GLOBAL_ROOT_GID))
seq_printf(m, ",gid=%u",
from_kgid_munged(&init_user_ns, opts->gid));
if (opts->mode != DEBUGFS_DEFAULT_MODE)
seq_printf(m, ",mode=%o", opts->mode);
return 0;
}
static const struct super_operations debugfs_super_operations = {
.statfs = simple_statfs,
.remount_fs = debugfs_remount,
.show_options = debugfs_show_options,
};
static int debug_fill_super(struct super_block *sb, void *data, int silent)
{
static struct tree_descr debug_files[] = {{""}};
struct debugfs_fs_info *fsi;
int err;
save_mount_options(sb, data);
fsi = kzalloc(sizeof(struct debugfs_fs_info), GFP_KERNEL);
sb->s_fs_info = fsi;
if (!fsi) {
err = -ENOMEM;
goto fail;
}
err = debugfs_parse_options(data, &fsi->mount_opts);
if (err)
goto fail;
err = simple_fill_super(sb, DEBUGFS_MAGIC, debug_files);
if (err)
goto fail;
sb->s_op = &debugfs_super_operations;
debugfs_apply_options(sb);
return 0;
fail:
kfree(fsi);
sb->s_fs_info = NULL;
return err;
}
static struct dentry *debug_mount(struct file_system_type *fs_type,
[PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Nathan Scott <nathans@sgi.com> Cc: Roland Dreier <rolandd@cisco.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:02:57 +08:00
int flags, const char *dev_name,
void *data)
{
return mount_single(fs_type, flags, data, debug_fill_super);
}
static struct file_system_type debug_fs_type = {
.owner = THIS_MODULE,
.name = "debugfs",
.mount = debug_mount,
.kill_sb = kill_litter_super,
};
fs: Limit sys_mount to only request filesystem modules. Modify the request_module to prefix the file system type with "fs-" and add aliases to all of the filesystems that can be built as modules to match. A common practice is to build all of the kernel code and leave code that is not commonly needed as modules, with the result that many users are exposed to any bug anywhere in the kernel. Looking for filesystems with a fs- prefix limits the pool of possible modules that can be loaded by mount to just filesystems trivially making things safer with no real cost. Using aliases means user space can control the policy of which filesystem modules are auto-loaded by editing /etc/modprobe.d/*.conf with blacklist and alias directives. Allowing simple, safe, well understood work-arounds to known problematic software. This also addresses a rare but unfortunate problem where the filesystem name is not the same as it's module name and module auto-loading would not work. While writing this patch I saw a handful of such cases. The most significant being autofs that lives in the module autofs4. This is relevant to user namespaces because we can reach the request module in get_fs_type() without having any special permissions, and people get uncomfortable when a user specified string (in this case the filesystem type) goes all of the way to request_module. After having looked at this issue I don't think there is any particular reason to perform any filtering or permission checks beyond making it clear in the module request that we want a filesystem module. The common pattern in the kernel is to call request_module() without regards to the users permissions. In general all a filesystem module does once loaded is call register_filesystem() and go to sleep. Which means there is not much attack surface exposed by loading a filesytem module unless the filesystem is mounted. In a user namespace filesystems are not mounted unless .fs_flags = FS_USERNS_MOUNT, which most filesystems do not set today. Acked-by: Serge Hallyn <serge.hallyn@canonical.com> Acked-by: Kees Cook <keescook@chromium.org> Reported-by: Kees Cook <keescook@google.com> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
2013-03-03 11:39:14 +08:00
MODULE_ALIAS_FS("debugfs");
static struct dentry *start_creating(const char *name, struct dentry *parent)
{
struct dentry *dentry;
int error;
pr_debug("debugfs: creating file '%s'\n",name);
error = simple_pin_fs(&debug_fs_type, &debugfs_mount,
&debugfs_mount_count);
if (error)
return ERR_PTR(error);
/* If the parent is not specified, we create it in the root.
* We need the root dentry to do this, which is in the super
* block. A pointer to that is in the struct vfsmount that we
* have around.
*/
if (!parent)
parent = debugfs_mount->mnt_root;
mutex_lock(&parent->d_inode->i_mutex);
dentry = lookup_one_len(name, parent, strlen(name));
if (!IS_ERR(dentry) && dentry->d_inode) {
dput(dentry);
dentry = ERR_PTR(-EEXIST);
}
if (IS_ERR(dentry))
mutex_unlock(&parent->d_inode->i_mutex);
return dentry;
}
static struct dentry *end_creating(struct dentry *dentry, int error)
{
mutex_unlock(&dentry->d_parent->d_inode->i_mutex);
dput(dentry);
if (error) {
dentry = NULL;
simple_release_fs(&debugfs_mount, &debugfs_mount_count);
}
return dentry;
}
static struct dentry *__create_file(const char *name, umode_t mode,
struct dentry *parent, void *data,
const struct file_operations *fops)
{
struct dentry *dentry = start_creating(name, parent);
int error;
if (IS_ERR(dentry))
return NULL;
switch (mode & S_IFMT) {
case S_IFDIR:
error = debugfs_mkdir(dentry, mode);
break;
case S_IFLNK:
error = debugfs_link(dentry, mode, data);
break;
default:
error = debugfs_create(dentry, mode, data, fops);
break;
}
return end_creating(dentry, error);
}
/**
* debugfs_create_file - create a file in the debugfs filesystem
* @name: a pointer to a string containing the name of the file to create.
* @mode: the permission that the file should have.
* @parent: a pointer to the parent dentry for this file. This should be a
* directory dentry if set. If this parameter is NULL, then the
* file will be created in the root of the debugfs filesystem.
* @data: a pointer to something that the caller will want to get to later
* on. The inode.i_private pointer will point to this value on
* the open() call.
* @fops: a pointer to a struct file_operations that should be used for
* this file.
*
* This is the basic "create a file" function for debugfs. It allows for a
* wide range of flexibility in creating a file, or a directory (if you want
* to create a directory, the debugfs_create_dir() function is
* recommended to be used instead.)
*
* This function will return a pointer to a dentry if it succeeds. This
* pointer must be passed to the debugfs_remove() function when the file is
* to be removed (no automatic cleanup happens if your module is unloaded,
* you are responsible here.) If an error occurs, %NULL will be returned.
*
* If debugfs is not enabled in the kernel, the value -%ENODEV will be
* returned.
*/
struct dentry *debugfs_create_file(const char *name, umode_t mode,
struct dentry *parent, void *data,
const struct file_operations *fops)
{
switch (mode & S_IFMT) {
case S_IFREG:
case 0:
break;
default:
BUG();
}
return __create_file(name, mode, parent, data, fops);
}
EXPORT_SYMBOL_GPL(debugfs_create_file);
/**
* debugfs_create_dir - create a directory in the debugfs filesystem
* @name: a pointer to a string containing the name of the directory to
* create.
* @parent: a pointer to the parent dentry for this file. This should be a
* directory dentry if set. If this parameter is NULL, then the
* directory will be created in the root of the debugfs filesystem.
*
* This function creates a directory in debugfs with the given name.
*
* This function will return a pointer to a dentry if it succeeds. This
* pointer must be passed to the debugfs_remove() function when the file is
* to be removed (no automatic cleanup happens if your module is unloaded,
* you are responsible here.) If an error occurs, %NULL will be returned.
*
* If debugfs is not enabled in the kernel, the value -%ENODEV will be
* returned.
*/
struct dentry *debugfs_create_dir(const char *name, struct dentry *parent)
{
return __create_file(name, S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO,
parent, NULL, NULL);
}
EXPORT_SYMBOL_GPL(debugfs_create_dir);
/**
* debugfs_create_symlink- create a symbolic link in the debugfs filesystem
* @name: a pointer to a string containing the name of the symbolic link to
* create.
* @parent: a pointer to the parent dentry for this symbolic link. This
* should be a directory dentry if set. If this parameter is NULL,
* then the symbolic link will be created in the root of the debugfs
* filesystem.
* @target: a pointer to a string containing the path to the target of the
* symbolic link.
*
* This function creates a symbolic link with the given name in debugfs that
* links to the given target path.
*
* This function will return a pointer to a dentry if it succeeds. This
* pointer must be passed to the debugfs_remove() function when the symbolic
* link is to be removed (no automatic cleanup happens if your module is
* unloaded, you are responsible here.) If an error occurs, %NULL will be
* returned.
*
* If debugfs is not enabled in the kernel, the value -%ENODEV will be
* returned.
*/
struct dentry *debugfs_create_symlink(const char *name, struct dentry *parent,
const char *target)
{
struct dentry *result;
char *link;
link = kstrdup(target, GFP_KERNEL);
if (!link)
return NULL;
result = __create_file(name, S_IFLNK | S_IRWXUGO, parent, link, NULL);
if (!result)
kfree(link);
return result;
}
EXPORT_SYMBOL_GPL(debugfs_create_symlink);
static int __debugfs_remove(struct dentry *dentry, struct dentry *parent)
{
int ret = 0;
if (debugfs_positive(dentry)) {
if (dentry->d_inode) {
dget(dentry);
switch (dentry->d_inode->i_mode & S_IFMT) {
case S_IFDIR:
ret = simple_rmdir(parent->d_inode, dentry);
break;
case S_IFLNK:
kfree(dentry->d_inode->i_private);
/* fall through */
default:
simple_unlink(parent->d_inode, dentry);
break;
}
if (!ret)
d_delete(dentry);
dput(dentry);
}
}
return ret;
}
/**
* debugfs_remove - removes a file or directory from the debugfs filesystem
* @dentry: a pointer to a the dentry of the file or directory to be
* removed.
*
* This function removes a file or directory in debugfs that was previously
* created with a call to another debugfs function (like
* debugfs_create_file() or variants thereof.)
*
* This function is required to be called in order for the file to be
* removed, no automatic cleanup of files will happen when a module is
* removed, you are responsible here.
*/
void debugfs_remove(struct dentry *dentry)
{
struct dentry *parent;
int ret;
if (IS_ERR_OR_NULL(dentry))
return;
parent = dentry->d_parent;
if (!parent || !parent->d_inode)
return;
mutex_lock(&parent->d_inode->i_mutex);
ret = __debugfs_remove(dentry, parent);
mutex_unlock(&parent->d_inode->i_mutex);
if (!ret)
simple_release_fs(&debugfs_mount, &debugfs_mount_count);
}
EXPORT_SYMBOL_GPL(debugfs_remove);
/**
* debugfs_remove_recursive - recursively removes a directory
* @dentry: a pointer to a the dentry of the directory to be removed.
*
* This function recursively removes a directory tree in debugfs that
* was previously created with a call to another debugfs function
* (like debugfs_create_file() or variants thereof.)
*
* This function is required to be called in order for the file to be
* removed, no automatic cleanup of files will happen when a module is
* removed, you are responsible here.
*/
void debugfs_remove_recursive(struct dentry *dentry)
{
debugfs: Fix corrupted loop in debugfs_remove_recursive [ I'm currently running my tests on it now, and so far, after a few hours it has yet to blow up. I'll run it for 24 hours which it never succeeded in the past. ] The tracing code has a way to make directories within the debugfs file system as well as deleting them using mkdir/rmdir in the instance directory. This is very limited in functionality, such as there is no renames, and the parent directory "instance" can not be modified. The tracing code creates the instance directory from the debugfs code and then replaces the dentry->d_inode->i_op with its own to allow for mkdir/rmdir to work. When these are called, the d_entry and inode locks need to be released to call the instance creation and deletion code. That code has its own accounting and locking to serialize everything to prevent multiple users from causing harm. As the parent "instance" directory can not be modified this simplifies things. I created a stress test that creates several threads that randomly creates and deletes directories thousands of times a second. The code stood up to this test and I submitted it a while ago. Recently I added a new test that adds readers to the mix. While the instance directories were being added and deleted, readers would read from these directories and even enable tracing within them. This test was able to trigger a bug: general protection fault: 0000 [#1] PREEMPT SMP Modules linked in: ... CPU: 3 PID: 17789 Comm: rmdir Tainted: G W 3.15.0-rc2-test+ #41 Hardware name: To Be Filled By O.E.M. To Be Filled By O.E.M./To be filled by O.E.M., BIOS SDBLI944.86P 05/08/2007 task: ffff88003786ca60 ti: ffff880077018000 task.ti: ffff880077018000 RIP: 0010:[<ffffffff811ed5eb>] [<ffffffff811ed5eb>] debugfs_remove_recursive+0x1bd/0x367 RSP: 0018:ffff880077019df8 EFLAGS: 00010246 RAX: 0000000000000002 RBX: ffff88006f0fe490 RCX: 0000000000000000 RDX: dead000000100058 RSI: 0000000000000246 RDI: ffff88003786d454 RBP: ffff88006f0fe640 R08: 0000000000000628 R09: 0000000000000000 R10: 0000000000000628 R11: ffff8800795110a0 R12: ffff88006f0fe640 R13: ffff88006f0fe640 R14: ffffffff81817d0b R15: ffffffff818188b7 FS: 00007ff13ae24700(0000) GS:ffff88007d580000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 0000003054ec7be0 CR3: 0000000076d51000 CR4: 00000000000007e0 Stack: ffff88007a41ebe0 dead000000100058 00000000fffffffe ffff88006f0fe640 0000000000000000 ffff88006f0fe678 ffff88007a41ebe0 ffff88003793a000 00000000fffffffe ffffffff810bde82 ffff88006f0fe640 ffff88007a41eb28 Call Trace: [<ffffffff810bde82>] ? instance_rmdir+0x15b/0x1de [<ffffffff81132e2d>] ? vfs_rmdir+0x80/0xd3 [<ffffffff81132f51>] ? do_rmdir+0xd1/0x139 [<ffffffff8124ad9e>] ? trace_hardirqs_on_thunk+0x3a/0x3c [<ffffffff814fea62>] ? system_call_fastpath+0x16/0x1b Code: fe ff ff 48 8d 75 30 48 89 df e8 c9 fd ff ff 85 c0 75 13 48 c7 c6 b8 cc d2 81 48 c7 c7 b0 cc d2 81 e8 8c 7a f5 ff 48 8b 54 24 08 <48> 8b 82 a8 00 00 00 48 89 d3 48 2d a8 00 00 00 48 89 44 24 08 RIP [<ffffffff811ed5eb>] debugfs_remove_recursive+0x1bd/0x367 RSP <ffff880077019df8> It took a while, but every time it triggered, it was always in the same place: list_for_each_entry_safe(child, next, &parent->d_subdirs, d_u.d_child) { Where the child->d_u.d_child seemed to be corrupted. I added lots of trace_printk()s to see what was wrong, and sure enough, it was always the child's d_u.d_child field. I looked around to see what touches it and noticed that in __dentry_kill() which calls dentry_free(): static void dentry_free(struct dentry *dentry) { /* if dentry was never visible to RCU, immediate free is OK */ if (!(dentry->d_flags & DCACHE_RCUACCESS)) __d_free(&dentry->d_u.d_rcu); else call_rcu(&dentry->d_u.d_rcu, __d_free); } I also noticed that __dentry_kill() unlinks the child->d_u.child under the parent->d_lock spin_lock. Looking back at the loop in debugfs_remove_recursive() it never takes the parent->d_lock to do the list walk. Adding more tracing, I was able to prove this was the issue: ftrace-t-15385 1.... 246662024us : dentry_kill <ffffffff81138b91>: free ffff88006d573600 rmdir-15409 2.... 246662024us : debugfs_remove_recursive <ffffffff811ec7e5>: child=ffff88006d573600 next=dead000000100058 The dentry_kill freed ffff88006d573600 just as the remove recursive was walking it. In order to fix this, the list walk needs to be modified a bit to take the parent->d_lock. The safe version is no longer necessary, as every time we remove a child, the parent->d_lock must be released and the list walk must start over. Each time a child is removed, even though it may still be on the list, it should be skipped by the first check in the loop: if (!debugfs_positive(child)) continue; Cc: stable@vger.kernel.org Signed-off-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-06-10 02:06:07 +08:00
struct dentry *child, *parent;
if (IS_ERR_OR_NULL(dentry))
return;
parent = dentry->d_parent;
if (!parent || !parent->d_inode)
return;
parent = dentry;
debugfs: debugfs_remove_recursive() must not rely on list_empty(d_subdirs) debugfs_remove_recursive() is wrong, 1. it wrongly assumes that !list_empty(d_subdirs) means that this dir should be removed. This is not that bad by itself, but: 2. if d_subdirs does not becomes empty after __debugfs_remove() it gives up and silently fails, it doesn't even try to remove other entries. However ->d_subdirs can be non-empty because it still has the already deleted !debugfs_positive() entries. 3. simple_release_fs() is called even if __debugfs_remove() fails. Suppose we have dir1/ dir2/ file2 file1 and someone opens dir1/dir2/file2. Now, debugfs_remove_recursive(dir1/dir2) succeeds, and dir1/dir2 goes away. But debugfs_remove_recursive(dir1) silently fails and doesn't remove this directory. Because it tries to delete (the already deleted) dir1/dir2/file2 again and then fails due to "Avoid infinite loop" logic. Test-case: #!/bin/sh cd /sys/kernel/debug/tracing echo 'p:probe/sigprocmask sigprocmask' >> kprobe_events sleep 1000 < events/probe/sigprocmask/id & echo -n >| kprobe_events [ -d events/probe ] && echo "ERR!! failed to rm probe" And after that it is not possible to create another probe entry. With this patch debugfs_remove_recursive() skips !debugfs_positive() files although this is not strictly needed. The most important change is that it does not try to make ->d_subdirs empty, it simply scans the whole list(s) recursively and removes as much as possible. Link: http://lkml.kernel.org/r/20130726151256.GC19472@redhat.com Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-07-26 23:12:56 +08:00
down:
mutex_lock(&parent->d_inode->i_mutex);
debugfs: Fix corrupted loop in debugfs_remove_recursive [ I'm currently running my tests on it now, and so far, after a few hours it has yet to blow up. I'll run it for 24 hours which it never succeeded in the past. ] The tracing code has a way to make directories within the debugfs file system as well as deleting them using mkdir/rmdir in the instance directory. This is very limited in functionality, such as there is no renames, and the parent directory "instance" can not be modified. The tracing code creates the instance directory from the debugfs code and then replaces the dentry->d_inode->i_op with its own to allow for mkdir/rmdir to work. When these are called, the d_entry and inode locks need to be released to call the instance creation and deletion code. That code has its own accounting and locking to serialize everything to prevent multiple users from causing harm. As the parent "instance" directory can not be modified this simplifies things. I created a stress test that creates several threads that randomly creates and deletes directories thousands of times a second. The code stood up to this test and I submitted it a while ago. Recently I added a new test that adds readers to the mix. While the instance directories were being added and deleted, readers would read from these directories and even enable tracing within them. This test was able to trigger a bug: general protection fault: 0000 [#1] PREEMPT SMP Modules linked in: ... CPU: 3 PID: 17789 Comm: rmdir Tainted: G W 3.15.0-rc2-test+ #41 Hardware name: To Be Filled By O.E.M. To Be Filled By O.E.M./To be filled by O.E.M., BIOS SDBLI944.86P 05/08/2007 task: ffff88003786ca60 ti: ffff880077018000 task.ti: ffff880077018000 RIP: 0010:[<ffffffff811ed5eb>] [<ffffffff811ed5eb>] debugfs_remove_recursive+0x1bd/0x367 RSP: 0018:ffff880077019df8 EFLAGS: 00010246 RAX: 0000000000000002 RBX: ffff88006f0fe490 RCX: 0000000000000000 RDX: dead000000100058 RSI: 0000000000000246 RDI: ffff88003786d454 RBP: ffff88006f0fe640 R08: 0000000000000628 R09: 0000000000000000 R10: 0000000000000628 R11: ffff8800795110a0 R12: ffff88006f0fe640 R13: ffff88006f0fe640 R14: ffffffff81817d0b R15: ffffffff818188b7 FS: 00007ff13ae24700(0000) GS:ffff88007d580000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 0000003054ec7be0 CR3: 0000000076d51000 CR4: 00000000000007e0 Stack: ffff88007a41ebe0 dead000000100058 00000000fffffffe ffff88006f0fe640 0000000000000000 ffff88006f0fe678 ffff88007a41ebe0 ffff88003793a000 00000000fffffffe ffffffff810bde82 ffff88006f0fe640 ffff88007a41eb28 Call Trace: [<ffffffff810bde82>] ? instance_rmdir+0x15b/0x1de [<ffffffff81132e2d>] ? vfs_rmdir+0x80/0xd3 [<ffffffff81132f51>] ? do_rmdir+0xd1/0x139 [<ffffffff8124ad9e>] ? trace_hardirqs_on_thunk+0x3a/0x3c [<ffffffff814fea62>] ? system_call_fastpath+0x16/0x1b Code: fe ff ff 48 8d 75 30 48 89 df e8 c9 fd ff ff 85 c0 75 13 48 c7 c6 b8 cc d2 81 48 c7 c7 b0 cc d2 81 e8 8c 7a f5 ff 48 8b 54 24 08 <48> 8b 82 a8 00 00 00 48 89 d3 48 2d a8 00 00 00 48 89 44 24 08 RIP [<ffffffff811ed5eb>] debugfs_remove_recursive+0x1bd/0x367 RSP <ffff880077019df8> It took a while, but every time it triggered, it was always in the same place: list_for_each_entry_safe(child, next, &parent->d_subdirs, d_u.d_child) { Where the child->d_u.d_child seemed to be corrupted. I added lots of trace_printk()s to see what was wrong, and sure enough, it was always the child's d_u.d_child field. I looked around to see what touches it and noticed that in __dentry_kill() which calls dentry_free(): static void dentry_free(struct dentry *dentry) { /* if dentry was never visible to RCU, immediate free is OK */ if (!(dentry->d_flags & DCACHE_RCUACCESS)) __d_free(&dentry->d_u.d_rcu); else call_rcu(&dentry->d_u.d_rcu, __d_free); } I also noticed that __dentry_kill() unlinks the child->d_u.child under the parent->d_lock spin_lock. Looking back at the loop in debugfs_remove_recursive() it never takes the parent->d_lock to do the list walk. Adding more tracing, I was able to prove this was the issue: ftrace-t-15385 1.... 246662024us : dentry_kill <ffffffff81138b91>: free ffff88006d573600 rmdir-15409 2.... 246662024us : debugfs_remove_recursive <ffffffff811ec7e5>: child=ffff88006d573600 next=dead000000100058 The dentry_kill freed ffff88006d573600 just as the remove recursive was walking it. In order to fix this, the list walk needs to be modified a bit to take the parent->d_lock. The safe version is no longer necessary, as every time we remove a child, the parent->d_lock must be released and the list walk must start over. Each time a child is removed, even though it may still be on the list, it should be skipped by the first check in the loop: if (!debugfs_positive(child)) continue; Cc: stable@vger.kernel.org Signed-off-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-06-10 02:06:07 +08:00
loop:
/*
* The parent->d_subdirs is protected by the d_lock. Outside that
* lock, the child can be unlinked and set to be freed which can
* use the d_u.d_child as the rcu head and corrupt this list.
*/
spin_lock(&parent->d_lock);
list_for_each_entry(child, &parent->d_subdirs, d_child) {
debugfs: debugfs_remove_recursive() must not rely on list_empty(d_subdirs) debugfs_remove_recursive() is wrong, 1. it wrongly assumes that !list_empty(d_subdirs) means that this dir should be removed. This is not that bad by itself, but: 2. if d_subdirs does not becomes empty after __debugfs_remove() it gives up and silently fails, it doesn't even try to remove other entries. However ->d_subdirs can be non-empty because it still has the already deleted !debugfs_positive() entries. 3. simple_release_fs() is called even if __debugfs_remove() fails. Suppose we have dir1/ dir2/ file2 file1 and someone opens dir1/dir2/file2. Now, debugfs_remove_recursive(dir1/dir2) succeeds, and dir1/dir2 goes away. But debugfs_remove_recursive(dir1) silently fails and doesn't remove this directory. Because it tries to delete (the already deleted) dir1/dir2/file2 again and then fails due to "Avoid infinite loop" logic. Test-case: #!/bin/sh cd /sys/kernel/debug/tracing echo 'p:probe/sigprocmask sigprocmask' >> kprobe_events sleep 1000 < events/probe/sigprocmask/id & echo -n >| kprobe_events [ -d events/probe ] && echo "ERR!! failed to rm probe" And after that it is not possible to create another probe entry. With this patch debugfs_remove_recursive() skips !debugfs_positive() files although this is not strictly needed. The most important change is that it does not try to make ->d_subdirs empty, it simply scans the whole list(s) recursively and removes as much as possible. Link: http://lkml.kernel.org/r/20130726151256.GC19472@redhat.com Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-07-26 23:12:56 +08:00
if (!debugfs_positive(child))
continue;
debugfs: debugfs_remove_recursive() must not rely on list_empty(d_subdirs) debugfs_remove_recursive() is wrong, 1. it wrongly assumes that !list_empty(d_subdirs) means that this dir should be removed. This is not that bad by itself, but: 2. if d_subdirs does not becomes empty after __debugfs_remove() it gives up and silently fails, it doesn't even try to remove other entries. However ->d_subdirs can be non-empty because it still has the already deleted !debugfs_positive() entries. 3. simple_release_fs() is called even if __debugfs_remove() fails. Suppose we have dir1/ dir2/ file2 file1 and someone opens dir1/dir2/file2. Now, debugfs_remove_recursive(dir1/dir2) succeeds, and dir1/dir2 goes away. But debugfs_remove_recursive(dir1) silently fails and doesn't remove this directory. Because it tries to delete (the already deleted) dir1/dir2/file2 again and then fails due to "Avoid infinite loop" logic. Test-case: #!/bin/sh cd /sys/kernel/debug/tracing echo 'p:probe/sigprocmask sigprocmask' >> kprobe_events sleep 1000 < events/probe/sigprocmask/id & echo -n >| kprobe_events [ -d events/probe ] && echo "ERR!! failed to rm probe" And after that it is not possible to create another probe entry. With this patch debugfs_remove_recursive() skips !debugfs_positive() files although this is not strictly needed. The most important change is that it does not try to make ->d_subdirs empty, it simply scans the whole list(s) recursively and removes as much as possible. Link: http://lkml.kernel.org/r/20130726151256.GC19472@redhat.com Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-07-26 23:12:56 +08:00
/* perhaps simple_empty(child) makes more sense */
if (!list_empty(&child->d_subdirs)) {
debugfs: Fix corrupted loop in debugfs_remove_recursive [ I'm currently running my tests on it now, and so far, after a few hours it has yet to blow up. I'll run it for 24 hours which it never succeeded in the past. ] The tracing code has a way to make directories within the debugfs file system as well as deleting them using mkdir/rmdir in the instance directory. This is very limited in functionality, such as there is no renames, and the parent directory "instance" can not be modified. The tracing code creates the instance directory from the debugfs code and then replaces the dentry->d_inode->i_op with its own to allow for mkdir/rmdir to work. When these are called, the d_entry and inode locks need to be released to call the instance creation and deletion code. That code has its own accounting and locking to serialize everything to prevent multiple users from causing harm. As the parent "instance" directory can not be modified this simplifies things. I created a stress test that creates several threads that randomly creates and deletes directories thousands of times a second. The code stood up to this test and I submitted it a while ago. Recently I added a new test that adds readers to the mix. While the instance directories were being added and deleted, readers would read from these directories and even enable tracing within them. This test was able to trigger a bug: general protection fault: 0000 [#1] PREEMPT SMP Modules linked in: ... CPU: 3 PID: 17789 Comm: rmdir Tainted: G W 3.15.0-rc2-test+ #41 Hardware name: To Be Filled By O.E.M. To Be Filled By O.E.M./To be filled by O.E.M., BIOS SDBLI944.86P 05/08/2007 task: ffff88003786ca60 ti: ffff880077018000 task.ti: ffff880077018000 RIP: 0010:[<ffffffff811ed5eb>] [<ffffffff811ed5eb>] debugfs_remove_recursive+0x1bd/0x367 RSP: 0018:ffff880077019df8 EFLAGS: 00010246 RAX: 0000000000000002 RBX: ffff88006f0fe490 RCX: 0000000000000000 RDX: dead000000100058 RSI: 0000000000000246 RDI: ffff88003786d454 RBP: ffff88006f0fe640 R08: 0000000000000628 R09: 0000000000000000 R10: 0000000000000628 R11: ffff8800795110a0 R12: ffff88006f0fe640 R13: ffff88006f0fe640 R14: ffffffff81817d0b R15: ffffffff818188b7 FS: 00007ff13ae24700(0000) GS:ffff88007d580000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 0000003054ec7be0 CR3: 0000000076d51000 CR4: 00000000000007e0 Stack: ffff88007a41ebe0 dead000000100058 00000000fffffffe ffff88006f0fe640 0000000000000000 ffff88006f0fe678 ffff88007a41ebe0 ffff88003793a000 00000000fffffffe ffffffff810bde82 ffff88006f0fe640 ffff88007a41eb28 Call Trace: [<ffffffff810bde82>] ? instance_rmdir+0x15b/0x1de [<ffffffff81132e2d>] ? vfs_rmdir+0x80/0xd3 [<ffffffff81132f51>] ? do_rmdir+0xd1/0x139 [<ffffffff8124ad9e>] ? trace_hardirqs_on_thunk+0x3a/0x3c [<ffffffff814fea62>] ? system_call_fastpath+0x16/0x1b Code: fe ff ff 48 8d 75 30 48 89 df e8 c9 fd ff ff 85 c0 75 13 48 c7 c6 b8 cc d2 81 48 c7 c7 b0 cc d2 81 e8 8c 7a f5 ff 48 8b 54 24 08 <48> 8b 82 a8 00 00 00 48 89 d3 48 2d a8 00 00 00 48 89 44 24 08 RIP [<ffffffff811ed5eb>] debugfs_remove_recursive+0x1bd/0x367 RSP <ffff880077019df8> It took a while, but every time it triggered, it was always in the same place: list_for_each_entry_safe(child, next, &parent->d_subdirs, d_u.d_child) { Where the child->d_u.d_child seemed to be corrupted. I added lots of trace_printk()s to see what was wrong, and sure enough, it was always the child's d_u.d_child field. I looked around to see what touches it and noticed that in __dentry_kill() which calls dentry_free(): static void dentry_free(struct dentry *dentry) { /* if dentry was never visible to RCU, immediate free is OK */ if (!(dentry->d_flags & DCACHE_RCUACCESS)) __d_free(&dentry->d_u.d_rcu); else call_rcu(&dentry->d_u.d_rcu, __d_free); } I also noticed that __dentry_kill() unlinks the child->d_u.child under the parent->d_lock spin_lock. Looking back at the loop in debugfs_remove_recursive() it never takes the parent->d_lock to do the list walk. Adding more tracing, I was able to prove this was the issue: ftrace-t-15385 1.... 246662024us : dentry_kill <ffffffff81138b91>: free ffff88006d573600 rmdir-15409 2.... 246662024us : debugfs_remove_recursive <ffffffff811ec7e5>: child=ffff88006d573600 next=dead000000100058 The dentry_kill freed ffff88006d573600 just as the remove recursive was walking it. In order to fix this, the list walk needs to be modified a bit to take the parent->d_lock. The safe version is no longer necessary, as every time we remove a child, the parent->d_lock must be released and the list walk must start over. Each time a child is removed, even though it may still be on the list, it should be skipped by the first check in the loop: if (!debugfs_positive(child)) continue; Cc: stable@vger.kernel.org Signed-off-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-06-10 02:06:07 +08:00
spin_unlock(&parent->d_lock);
mutex_unlock(&parent->d_inode->i_mutex);
parent = child;
debugfs: debugfs_remove_recursive() must not rely on list_empty(d_subdirs) debugfs_remove_recursive() is wrong, 1. it wrongly assumes that !list_empty(d_subdirs) means that this dir should be removed. This is not that bad by itself, but: 2. if d_subdirs does not becomes empty after __debugfs_remove() it gives up and silently fails, it doesn't even try to remove other entries. However ->d_subdirs can be non-empty because it still has the already deleted !debugfs_positive() entries. 3. simple_release_fs() is called even if __debugfs_remove() fails. Suppose we have dir1/ dir2/ file2 file1 and someone opens dir1/dir2/file2. Now, debugfs_remove_recursive(dir1/dir2) succeeds, and dir1/dir2 goes away. But debugfs_remove_recursive(dir1) silently fails and doesn't remove this directory. Because it tries to delete (the already deleted) dir1/dir2/file2 again and then fails due to "Avoid infinite loop" logic. Test-case: #!/bin/sh cd /sys/kernel/debug/tracing echo 'p:probe/sigprocmask sigprocmask' >> kprobe_events sleep 1000 < events/probe/sigprocmask/id & echo -n >| kprobe_events [ -d events/probe ] && echo "ERR!! failed to rm probe" And after that it is not possible to create another probe entry. With this patch debugfs_remove_recursive() skips !debugfs_positive() files although this is not strictly needed. The most important change is that it does not try to make ->d_subdirs empty, it simply scans the whole list(s) recursively and removes as much as possible. Link: http://lkml.kernel.org/r/20130726151256.GC19472@redhat.com Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-07-26 23:12:56 +08:00
goto down;
}
debugfs: Fix corrupted loop in debugfs_remove_recursive [ I'm currently running my tests on it now, and so far, after a few hours it has yet to blow up. I'll run it for 24 hours which it never succeeded in the past. ] The tracing code has a way to make directories within the debugfs file system as well as deleting them using mkdir/rmdir in the instance directory. This is very limited in functionality, such as there is no renames, and the parent directory "instance" can not be modified. The tracing code creates the instance directory from the debugfs code and then replaces the dentry->d_inode->i_op with its own to allow for mkdir/rmdir to work. When these are called, the d_entry and inode locks need to be released to call the instance creation and deletion code. That code has its own accounting and locking to serialize everything to prevent multiple users from causing harm. As the parent "instance" directory can not be modified this simplifies things. I created a stress test that creates several threads that randomly creates and deletes directories thousands of times a second. The code stood up to this test and I submitted it a while ago. Recently I added a new test that adds readers to the mix. While the instance directories were being added and deleted, readers would read from these directories and even enable tracing within them. This test was able to trigger a bug: general protection fault: 0000 [#1] PREEMPT SMP Modules linked in: ... CPU: 3 PID: 17789 Comm: rmdir Tainted: G W 3.15.0-rc2-test+ #41 Hardware name: To Be Filled By O.E.M. To Be Filled By O.E.M./To be filled by O.E.M., BIOS SDBLI944.86P 05/08/2007 task: ffff88003786ca60 ti: ffff880077018000 task.ti: ffff880077018000 RIP: 0010:[<ffffffff811ed5eb>] [<ffffffff811ed5eb>] debugfs_remove_recursive+0x1bd/0x367 RSP: 0018:ffff880077019df8 EFLAGS: 00010246 RAX: 0000000000000002 RBX: ffff88006f0fe490 RCX: 0000000000000000 RDX: dead000000100058 RSI: 0000000000000246 RDI: ffff88003786d454 RBP: ffff88006f0fe640 R08: 0000000000000628 R09: 0000000000000000 R10: 0000000000000628 R11: ffff8800795110a0 R12: ffff88006f0fe640 R13: ffff88006f0fe640 R14: ffffffff81817d0b R15: ffffffff818188b7 FS: 00007ff13ae24700(0000) GS:ffff88007d580000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 0000003054ec7be0 CR3: 0000000076d51000 CR4: 00000000000007e0 Stack: ffff88007a41ebe0 dead000000100058 00000000fffffffe ffff88006f0fe640 0000000000000000 ffff88006f0fe678 ffff88007a41ebe0 ffff88003793a000 00000000fffffffe ffffffff810bde82 ffff88006f0fe640 ffff88007a41eb28 Call Trace: [<ffffffff810bde82>] ? instance_rmdir+0x15b/0x1de [<ffffffff81132e2d>] ? vfs_rmdir+0x80/0xd3 [<ffffffff81132f51>] ? do_rmdir+0xd1/0x139 [<ffffffff8124ad9e>] ? trace_hardirqs_on_thunk+0x3a/0x3c [<ffffffff814fea62>] ? system_call_fastpath+0x16/0x1b Code: fe ff ff 48 8d 75 30 48 89 df e8 c9 fd ff ff 85 c0 75 13 48 c7 c6 b8 cc d2 81 48 c7 c7 b0 cc d2 81 e8 8c 7a f5 ff 48 8b 54 24 08 <48> 8b 82 a8 00 00 00 48 89 d3 48 2d a8 00 00 00 48 89 44 24 08 RIP [<ffffffff811ed5eb>] debugfs_remove_recursive+0x1bd/0x367 RSP <ffff880077019df8> It took a while, but every time it triggered, it was always in the same place: list_for_each_entry_safe(child, next, &parent->d_subdirs, d_u.d_child) { Where the child->d_u.d_child seemed to be corrupted. I added lots of trace_printk()s to see what was wrong, and sure enough, it was always the child's d_u.d_child field. I looked around to see what touches it and noticed that in __dentry_kill() which calls dentry_free(): static void dentry_free(struct dentry *dentry) { /* if dentry was never visible to RCU, immediate free is OK */ if (!(dentry->d_flags & DCACHE_RCUACCESS)) __d_free(&dentry->d_u.d_rcu); else call_rcu(&dentry->d_u.d_rcu, __d_free); } I also noticed that __dentry_kill() unlinks the child->d_u.child under the parent->d_lock spin_lock. Looking back at the loop in debugfs_remove_recursive() it never takes the parent->d_lock to do the list walk. Adding more tracing, I was able to prove this was the issue: ftrace-t-15385 1.... 246662024us : dentry_kill <ffffffff81138b91>: free ffff88006d573600 rmdir-15409 2.... 246662024us : debugfs_remove_recursive <ffffffff811ec7e5>: child=ffff88006d573600 next=dead000000100058 The dentry_kill freed ffff88006d573600 just as the remove recursive was walking it. In order to fix this, the list walk needs to be modified a bit to take the parent->d_lock. The safe version is no longer necessary, as every time we remove a child, the parent->d_lock must be released and the list walk must start over. Each time a child is removed, even though it may still be on the list, it should be skipped by the first check in the loop: if (!debugfs_positive(child)) continue; Cc: stable@vger.kernel.org Signed-off-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-06-10 02:06:07 +08:00
spin_unlock(&parent->d_lock);
debugfs: debugfs_remove_recursive() must not rely on list_empty(d_subdirs) debugfs_remove_recursive() is wrong, 1. it wrongly assumes that !list_empty(d_subdirs) means that this dir should be removed. This is not that bad by itself, but: 2. if d_subdirs does not becomes empty after __debugfs_remove() it gives up and silently fails, it doesn't even try to remove other entries. However ->d_subdirs can be non-empty because it still has the already deleted !debugfs_positive() entries. 3. simple_release_fs() is called even if __debugfs_remove() fails. Suppose we have dir1/ dir2/ file2 file1 and someone opens dir1/dir2/file2. Now, debugfs_remove_recursive(dir1/dir2) succeeds, and dir1/dir2 goes away. But debugfs_remove_recursive(dir1) silently fails and doesn't remove this directory. Because it tries to delete (the already deleted) dir1/dir2/file2 again and then fails due to "Avoid infinite loop" logic. Test-case: #!/bin/sh cd /sys/kernel/debug/tracing echo 'p:probe/sigprocmask sigprocmask' >> kprobe_events sleep 1000 < events/probe/sigprocmask/id & echo -n >| kprobe_events [ -d events/probe ] && echo "ERR!! failed to rm probe" And after that it is not possible to create another probe entry. With this patch debugfs_remove_recursive() skips !debugfs_positive() files although this is not strictly needed. The most important change is that it does not try to make ->d_subdirs empty, it simply scans the whole list(s) recursively and removes as much as possible. Link: http://lkml.kernel.org/r/20130726151256.GC19472@redhat.com Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-07-26 23:12:56 +08:00
if (!__debugfs_remove(child, parent))
simple_release_fs(&debugfs_mount, &debugfs_mount_count);
debugfs: Fix corrupted loop in debugfs_remove_recursive [ I'm currently running my tests on it now, and so far, after a few hours it has yet to blow up. I'll run it for 24 hours which it never succeeded in the past. ] The tracing code has a way to make directories within the debugfs file system as well as deleting them using mkdir/rmdir in the instance directory. This is very limited in functionality, such as there is no renames, and the parent directory "instance" can not be modified. The tracing code creates the instance directory from the debugfs code and then replaces the dentry->d_inode->i_op with its own to allow for mkdir/rmdir to work. When these are called, the d_entry and inode locks need to be released to call the instance creation and deletion code. That code has its own accounting and locking to serialize everything to prevent multiple users from causing harm. As the parent "instance" directory can not be modified this simplifies things. I created a stress test that creates several threads that randomly creates and deletes directories thousands of times a second. The code stood up to this test and I submitted it a while ago. Recently I added a new test that adds readers to the mix. While the instance directories were being added and deleted, readers would read from these directories and even enable tracing within them. This test was able to trigger a bug: general protection fault: 0000 [#1] PREEMPT SMP Modules linked in: ... CPU: 3 PID: 17789 Comm: rmdir Tainted: G W 3.15.0-rc2-test+ #41 Hardware name: To Be Filled By O.E.M. To Be Filled By O.E.M./To be filled by O.E.M., BIOS SDBLI944.86P 05/08/2007 task: ffff88003786ca60 ti: ffff880077018000 task.ti: ffff880077018000 RIP: 0010:[<ffffffff811ed5eb>] [<ffffffff811ed5eb>] debugfs_remove_recursive+0x1bd/0x367 RSP: 0018:ffff880077019df8 EFLAGS: 00010246 RAX: 0000000000000002 RBX: ffff88006f0fe490 RCX: 0000000000000000 RDX: dead000000100058 RSI: 0000000000000246 RDI: ffff88003786d454 RBP: ffff88006f0fe640 R08: 0000000000000628 R09: 0000000000000000 R10: 0000000000000628 R11: ffff8800795110a0 R12: ffff88006f0fe640 R13: ffff88006f0fe640 R14: ffffffff81817d0b R15: ffffffff818188b7 FS: 00007ff13ae24700(0000) GS:ffff88007d580000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 0000003054ec7be0 CR3: 0000000076d51000 CR4: 00000000000007e0 Stack: ffff88007a41ebe0 dead000000100058 00000000fffffffe ffff88006f0fe640 0000000000000000 ffff88006f0fe678 ffff88007a41ebe0 ffff88003793a000 00000000fffffffe ffffffff810bde82 ffff88006f0fe640 ffff88007a41eb28 Call Trace: [<ffffffff810bde82>] ? instance_rmdir+0x15b/0x1de [<ffffffff81132e2d>] ? vfs_rmdir+0x80/0xd3 [<ffffffff81132f51>] ? do_rmdir+0xd1/0x139 [<ffffffff8124ad9e>] ? trace_hardirqs_on_thunk+0x3a/0x3c [<ffffffff814fea62>] ? system_call_fastpath+0x16/0x1b Code: fe ff ff 48 8d 75 30 48 89 df e8 c9 fd ff ff 85 c0 75 13 48 c7 c6 b8 cc d2 81 48 c7 c7 b0 cc d2 81 e8 8c 7a f5 ff 48 8b 54 24 08 <48> 8b 82 a8 00 00 00 48 89 d3 48 2d a8 00 00 00 48 89 44 24 08 RIP [<ffffffff811ed5eb>] debugfs_remove_recursive+0x1bd/0x367 RSP <ffff880077019df8> It took a while, but every time it triggered, it was always in the same place: list_for_each_entry_safe(child, next, &parent->d_subdirs, d_u.d_child) { Where the child->d_u.d_child seemed to be corrupted. I added lots of trace_printk()s to see what was wrong, and sure enough, it was always the child's d_u.d_child field. I looked around to see what touches it and noticed that in __dentry_kill() which calls dentry_free(): static void dentry_free(struct dentry *dentry) { /* if dentry was never visible to RCU, immediate free is OK */ if (!(dentry->d_flags & DCACHE_RCUACCESS)) __d_free(&dentry->d_u.d_rcu); else call_rcu(&dentry->d_u.d_rcu, __d_free); } I also noticed that __dentry_kill() unlinks the child->d_u.child under the parent->d_lock spin_lock. Looking back at the loop in debugfs_remove_recursive() it never takes the parent->d_lock to do the list walk. Adding more tracing, I was able to prove this was the issue: ftrace-t-15385 1.... 246662024us : dentry_kill <ffffffff81138b91>: free ffff88006d573600 rmdir-15409 2.... 246662024us : debugfs_remove_recursive <ffffffff811ec7e5>: child=ffff88006d573600 next=dead000000100058 The dentry_kill freed ffff88006d573600 just as the remove recursive was walking it. In order to fix this, the list walk needs to be modified a bit to take the parent->d_lock. The safe version is no longer necessary, as every time we remove a child, the parent->d_lock must be released and the list walk must start over. Each time a child is removed, even though it may still be on the list, it should be skipped by the first check in the loop: if (!debugfs_positive(child)) continue; Cc: stable@vger.kernel.org Signed-off-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-06-10 02:06:07 +08:00
/*
* The parent->d_lock protects agaist child from unlinking
* from d_subdirs. When releasing the parent->d_lock we can
* no longer trust that the next pointer is valid.
* Restart the loop. We'll skip this one with the
* debugfs_positive() check.
*/
goto loop;
}
debugfs: Fix corrupted loop in debugfs_remove_recursive [ I'm currently running my tests on it now, and so far, after a few hours it has yet to blow up. I'll run it for 24 hours which it never succeeded in the past. ] The tracing code has a way to make directories within the debugfs file system as well as deleting them using mkdir/rmdir in the instance directory. This is very limited in functionality, such as there is no renames, and the parent directory "instance" can not be modified. The tracing code creates the instance directory from the debugfs code and then replaces the dentry->d_inode->i_op with its own to allow for mkdir/rmdir to work. When these are called, the d_entry and inode locks need to be released to call the instance creation and deletion code. That code has its own accounting and locking to serialize everything to prevent multiple users from causing harm. As the parent "instance" directory can not be modified this simplifies things. I created a stress test that creates several threads that randomly creates and deletes directories thousands of times a second. The code stood up to this test and I submitted it a while ago. Recently I added a new test that adds readers to the mix. While the instance directories were being added and deleted, readers would read from these directories and even enable tracing within them. This test was able to trigger a bug: general protection fault: 0000 [#1] PREEMPT SMP Modules linked in: ... CPU: 3 PID: 17789 Comm: rmdir Tainted: G W 3.15.0-rc2-test+ #41 Hardware name: To Be Filled By O.E.M. To Be Filled By O.E.M./To be filled by O.E.M., BIOS SDBLI944.86P 05/08/2007 task: ffff88003786ca60 ti: ffff880077018000 task.ti: ffff880077018000 RIP: 0010:[<ffffffff811ed5eb>] [<ffffffff811ed5eb>] debugfs_remove_recursive+0x1bd/0x367 RSP: 0018:ffff880077019df8 EFLAGS: 00010246 RAX: 0000000000000002 RBX: ffff88006f0fe490 RCX: 0000000000000000 RDX: dead000000100058 RSI: 0000000000000246 RDI: ffff88003786d454 RBP: ffff88006f0fe640 R08: 0000000000000628 R09: 0000000000000000 R10: 0000000000000628 R11: ffff8800795110a0 R12: ffff88006f0fe640 R13: ffff88006f0fe640 R14: ffffffff81817d0b R15: ffffffff818188b7 FS: 00007ff13ae24700(0000) GS:ffff88007d580000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 0000003054ec7be0 CR3: 0000000076d51000 CR4: 00000000000007e0 Stack: ffff88007a41ebe0 dead000000100058 00000000fffffffe ffff88006f0fe640 0000000000000000 ffff88006f0fe678 ffff88007a41ebe0 ffff88003793a000 00000000fffffffe ffffffff810bde82 ffff88006f0fe640 ffff88007a41eb28 Call Trace: [<ffffffff810bde82>] ? instance_rmdir+0x15b/0x1de [<ffffffff81132e2d>] ? vfs_rmdir+0x80/0xd3 [<ffffffff81132f51>] ? do_rmdir+0xd1/0x139 [<ffffffff8124ad9e>] ? trace_hardirqs_on_thunk+0x3a/0x3c [<ffffffff814fea62>] ? system_call_fastpath+0x16/0x1b Code: fe ff ff 48 8d 75 30 48 89 df e8 c9 fd ff ff 85 c0 75 13 48 c7 c6 b8 cc d2 81 48 c7 c7 b0 cc d2 81 e8 8c 7a f5 ff 48 8b 54 24 08 <48> 8b 82 a8 00 00 00 48 89 d3 48 2d a8 00 00 00 48 89 44 24 08 RIP [<ffffffff811ed5eb>] debugfs_remove_recursive+0x1bd/0x367 RSP <ffff880077019df8> It took a while, but every time it triggered, it was always in the same place: list_for_each_entry_safe(child, next, &parent->d_subdirs, d_u.d_child) { Where the child->d_u.d_child seemed to be corrupted. I added lots of trace_printk()s to see what was wrong, and sure enough, it was always the child's d_u.d_child field. I looked around to see what touches it and noticed that in __dentry_kill() which calls dentry_free(): static void dentry_free(struct dentry *dentry) { /* if dentry was never visible to RCU, immediate free is OK */ if (!(dentry->d_flags & DCACHE_RCUACCESS)) __d_free(&dentry->d_u.d_rcu); else call_rcu(&dentry->d_u.d_rcu, __d_free); } I also noticed that __dentry_kill() unlinks the child->d_u.child under the parent->d_lock spin_lock. Looking back at the loop in debugfs_remove_recursive() it never takes the parent->d_lock to do the list walk. Adding more tracing, I was able to prove this was the issue: ftrace-t-15385 1.... 246662024us : dentry_kill <ffffffff81138b91>: free ffff88006d573600 rmdir-15409 2.... 246662024us : debugfs_remove_recursive <ffffffff811ec7e5>: child=ffff88006d573600 next=dead000000100058 The dentry_kill freed ffff88006d573600 just as the remove recursive was walking it. In order to fix this, the list walk needs to be modified a bit to take the parent->d_lock. The safe version is no longer necessary, as every time we remove a child, the parent->d_lock must be released and the list walk must start over. Each time a child is removed, even though it may still be on the list, it should be skipped by the first check in the loop: if (!debugfs_positive(child)) continue; Cc: stable@vger.kernel.org Signed-off-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-06-10 02:06:07 +08:00
spin_unlock(&parent->d_lock);
debugfs: debugfs_remove_recursive() must not rely on list_empty(d_subdirs) debugfs_remove_recursive() is wrong, 1. it wrongly assumes that !list_empty(d_subdirs) means that this dir should be removed. This is not that bad by itself, but: 2. if d_subdirs does not becomes empty after __debugfs_remove() it gives up and silently fails, it doesn't even try to remove other entries. However ->d_subdirs can be non-empty because it still has the already deleted !debugfs_positive() entries. 3. simple_release_fs() is called even if __debugfs_remove() fails. Suppose we have dir1/ dir2/ file2 file1 and someone opens dir1/dir2/file2. Now, debugfs_remove_recursive(dir1/dir2) succeeds, and dir1/dir2 goes away. But debugfs_remove_recursive(dir1) silently fails and doesn't remove this directory. Because it tries to delete (the already deleted) dir1/dir2/file2 again and then fails due to "Avoid infinite loop" logic. Test-case: #!/bin/sh cd /sys/kernel/debug/tracing echo 'p:probe/sigprocmask sigprocmask' >> kprobe_events sleep 1000 < events/probe/sigprocmask/id & echo -n >| kprobe_events [ -d events/probe ] && echo "ERR!! failed to rm probe" And after that it is not possible to create another probe entry. With this patch debugfs_remove_recursive() skips !debugfs_positive() files although this is not strictly needed. The most important change is that it does not try to make ->d_subdirs empty, it simply scans the whole list(s) recursively and removes as much as possible. Link: http://lkml.kernel.org/r/20130726151256.GC19472@redhat.com Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-07-26 23:12:56 +08:00
mutex_unlock(&parent->d_inode->i_mutex);
child = parent;
parent = parent->d_parent;
mutex_lock(&parent->d_inode->i_mutex);
debugfs: debugfs_remove_recursive() must not rely on list_empty(d_subdirs) debugfs_remove_recursive() is wrong, 1. it wrongly assumes that !list_empty(d_subdirs) means that this dir should be removed. This is not that bad by itself, but: 2. if d_subdirs does not becomes empty after __debugfs_remove() it gives up and silently fails, it doesn't even try to remove other entries. However ->d_subdirs can be non-empty because it still has the already deleted !debugfs_positive() entries. 3. simple_release_fs() is called even if __debugfs_remove() fails. Suppose we have dir1/ dir2/ file2 file1 and someone opens dir1/dir2/file2. Now, debugfs_remove_recursive(dir1/dir2) succeeds, and dir1/dir2 goes away. But debugfs_remove_recursive(dir1) silently fails and doesn't remove this directory. Because it tries to delete (the already deleted) dir1/dir2/file2 again and then fails due to "Avoid infinite loop" logic. Test-case: #!/bin/sh cd /sys/kernel/debug/tracing echo 'p:probe/sigprocmask sigprocmask' >> kprobe_events sleep 1000 < events/probe/sigprocmask/id & echo -n >| kprobe_events [ -d events/probe ] && echo "ERR!! failed to rm probe" And after that it is not possible to create another probe entry. With this patch debugfs_remove_recursive() skips !debugfs_positive() files although this is not strictly needed. The most important change is that it does not try to make ->d_subdirs empty, it simply scans the whole list(s) recursively and removes as much as possible. Link: http://lkml.kernel.org/r/20130726151256.GC19472@redhat.com Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-07-26 23:12:56 +08:00
debugfs: Fix corrupted loop in debugfs_remove_recursive [ I'm currently running my tests on it now, and so far, after a few hours it has yet to blow up. I'll run it for 24 hours which it never succeeded in the past. ] The tracing code has a way to make directories within the debugfs file system as well as deleting them using mkdir/rmdir in the instance directory. This is very limited in functionality, such as there is no renames, and the parent directory "instance" can not be modified. The tracing code creates the instance directory from the debugfs code and then replaces the dentry->d_inode->i_op with its own to allow for mkdir/rmdir to work. When these are called, the d_entry and inode locks need to be released to call the instance creation and deletion code. That code has its own accounting and locking to serialize everything to prevent multiple users from causing harm. As the parent "instance" directory can not be modified this simplifies things. I created a stress test that creates several threads that randomly creates and deletes directories thousands of times a second. The code stood up to this test and I submitted it a while ago. Recently I added a new test that adds readers to the mix. While the instance directories were being added and deleted, readers would read from these directories and even enable tracing within them. This test was able to trigger a bug: general protection fault: 0000 [#1] PREEMPT SMP Modules linked in: ... CPU: 3 PID: 17789 Comm: rmdir Tainted: G W 3.15.0-rc2-test+ #41 Hardware name: To Be Filled By O.E.M. To Be Filled By O.E.M./To be filled by O.E.M., BIOS SDBLI944.86P 05/08/2007 task: ffff88003786ca60 ti: ffff880077018000 task.ti: ffff880077018000 RIP: 0010:[<ffffffff811ed5eb>] [<ffffffff811ed5eb>] debugfs_remove_recursive+0x1bd/0x367 RSP: 0018:ffff880077019df8 EFLAGS: 00010246 RAX: 0000000000000002 RBX: ffff88006f0fe490 RCX: 0000000000000000 RDX: dead000000100058 RSI: 0000000000000246 RDI: ffff88003786d454 RBP: ffff88006f0fe640 R08: 0000000000000628 R09: 0000000000000000 R10: 0000000000000628 R11: ffff8800795110a0 R12: ffff88006f0fe640 R13: ffff88006f0fe640 R14: ffffffff81817d0b R15: ffffffff818188b7 FS: 00007ff13ae24700(0000) GS:ffff88007d580000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 0000003054ec7be0 CR3: 0000000076d51000 CR4: 00000000000007e0 Stack: ffff88007a41ebe0 dead000000100058 00000000fffffffe ffff88006f0fe640 0000000000000000 ffff88006f0fe678 ffff88007a41ebe0 ffff88003793a000 00000000fffffffe ffffffff810bde82 ffff88006f0fe640 ffff88007a41eb28 Call Trace: [<ffffffff810bde82>] ? instance_rmdir+0x15b/0x1de [<ffffffff81132e2d>] ? vfs_rmdir+0x80/0xd3 [<ffffffff81132f51>] ? do_rmdir+0xd1/0x139 [<ffffffff8124ad9e>] ? trace_hardirqs_on_thunk+0x3a/0x3c [<ffffffff814fea62>] ? system_call_fastpath+0x16/0x1b Code: fe ff ff 48 8d 75 30 48 89 df e8 c9 fd ff ff 85 c0 75 13 48 c7 c6 b8 cc d2 81 48 c7 c7 b0 cc d2 81 e8 8c 7a f5 ff 48 8b 54 24 08 <48> 8b 82 a8 00 00 00 48 89 d3 48 2d a8 00 00 00 48 89 44 24 08 RIP [<ffffffff811ed5eb>] debugfs_remove_recursive+0x1bd/0x367 RSP <ffff880077019df8> It took a while, but every time it triggered, it was always in the same place: list_for_each_entry_safe(child, next, &parent->d_subdirs, d_u.d_child) { Where the child->d_u.d_child seemed to be corrupted. I added lots of trace_printk()s to see what was wrong, and sure enough, it was always the child's d_u.d_child field. I looked around to see what touches it and noticed that in __dentry_kill() which calls dentry_free(): static void dentry_free(struct dentry *dentry) { /* if dentry was never visible to RCU, immediate free is OK */ if (!(dentry->d_flags & DCACHE_RCUACCESS)) __d_free(&dentry->d_u.d_rcu); else call_rcu(&dentry->d_u.d_rcu, __d_free); } I also noticed that __dentry_kill() unlinks the child->d_u.child under the parent->d_lock spin_lock. Looking back at the loop in debugfs_remove_recursive() it never takes the parent->d_lock to do the list walk. Adding more tracing, I was able to prove this was the issue: ftrace-t-15385 1.... 246662024us : dentry_kill <ffffffff81138b91>: free ffff88006d573600 rmdir-15409 2.... 246662024us : debugfs_remove_recursive <ffffffff811ec7e5>: child=ffff88006d573600 next=dead000000100058 The dentry_kill freed ffff88006d573600 just as the remove recursive was walking it. In order to fix this, the list walk needs to be modified a bit to take the parent->d_lock. The safe version is no longer necessary, as every time we remove a child, the parent->d_lock must be released and the list walk must start over. Each time a child is removed, even though it may still be on the list, it should be skipped by the first check in the loop: if (!debugfs_positive(child)) continue; Cc: stable@vger.kernel.org Signed-off-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-06-10 02:06:07 +08:00
if (child != dentry)
/* go up */
goto loop;
debugfs: debugfs_remove_recursive() must not rely on list_empty(d_subdirs) debugfs_remove_recursive() is wrong, 1. it wrongly assumes that !list_empty(d_subdirs) means that this dir should be removed. This is not that bad by itself, but: 2. if d_subdirs does not becomes empty after __debugfs_remove() it gives up and silently fails, it doesn't even try to remove other entries. However ->d_subdirs can be non-empty because it still has the already deleted !debugfs_positive() entries. 3. simple_release_fs() is called even if __debugfs_remove() fails. Suppose we have dir1/ dir2/ file2 file1 and someone opens dir1/dir2/file2. Now, debugfs_remove_recursive(dir1/dir2) succeeds, and dir1/dir2 goes away. But debugfs_remove_recursive(dir1) silently fails and doesn't remove this directory. Because it tries to delete (the already deleted) dir1/dir2/file2 again and then fails due to "Avoid infinite loop" logic. Test-case: #!/bin/sh cd /sys/kernel/debug/tracing echo 'p:probe/sigprocmask sigprocmask' >> kprobe_events sleep 1000 < events/probe/sigprocmask/id & echo -n >| kprobe_events [ -d events/probe ] && echo "ERR!! failed to rm probe" And after that it is not possible to create another probe entry. With this patch debugfs_remove_recursive() skips !debugfs_positive() files although this is not strictly needed. The most important change is that it does not try to make ->d_subdirs empty, it simply scans the whole list(s) recursively and removes as much as possible. Link: http://lkml.kernel.org/r/20130726151256.GC19472@redhat.com Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-07-26 23:12:56 +08:00
if (!__debugfs_remove(child, parent))
simple_release_fs(&debugfs_mount, &debugfs_mount_count);
mutex_unlock(&parent->d_inode->i_mutex);
}
EXPORT_SYMBOL_GPL(debugfs_remove_recursive);
/**
* debugfs_rename - rename a file/directory in the debugfs filesystem
* @old_dir: a pointer to the parent dentry for the renamed object. This
* should be a directory dentry.
* @old_dentry: dentry of an object to be renamed.
* @new_dir: a pointer to the parent dentry where the object should be
* moved. This should be a directory dentry.
* @new_name: a pointer to a string containing the target name.
*
* This function renames a file/directory in debugfs. The target must not
* exist for rename to succeed.
*
* This function will return a pointer to old_dentry (which is updated to
* reflect renaming) if it succeeds. If an error occurs, %NULL will be
* returned.
*
* If debugfs is not enabled in the kernel, the value -%ENODEV will be
* returned.
*/
struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry,
struct dentry *new_dir, const char *new_name)
{
int error;
struct dentry *dentry = NULL, *trap;
const char *old_name;
trap = lock_rename(new_dir, old_dir);
/* Source or destination directories don't exist? */
if (!old_dir->d_inode || !new_dir->d_inode)
goto exit;
/* Source does not exist, cyclic rename, or mountpoint? */
if (!old_dentry->d_inode || old_dentry == trap ||
d_mountpoint(old_dentry))
goto exit;
dentry = lookup_one_len(new_name, new_dir, strlen(new_name));
/* Lookup failed, cyclic rename or target exists? */
if (IS_ERR(dentry) || dentry == trap || dentry->d_inode)
goto exit;
old_name = fsnotify_oldname_init(old_dentry->d_name.name);
error = simple_rename(old_dir->d_inode, old_dentry, new_dir->d_inode,
dentry);
if (error) {
fsnotify_oldname_free(old_name);
goto exit;
}
d_move(old_dentry, dentry);
fsnotify_move(old_dir->d_inode, new_dir->d_inode, old_name,
S_ISDIR(old_dentry->d_inode->i_mode),
NULL, old_dentry);
fsnotify_oldname_free(old_name);
unlock_rename(new_dir, old_dir);
dput(dentry);
return old_dentry;
exit:
if (dentry && !IS_ERR(dentry))
dput(dentry);
unlock_rename(new_dir, old_dir);
return NULL;
}
EXPORT_SYMBOL_GPL(debugfs_rename);
/**
* debugfs_initialized - Tells whether debugfs has been registered
*/
bool debugfs_initialized(void)
{
return debugfs_registered;
}
EXPORT_SYMBOL_GPL(debugfs_initialized);
static struct kobject *debug_kobj;
static int __init debugfs_init(void)
{
int retval;
debug_kobj = kobject_create_and_add("debug", kernel_kobj);
if (!debug_kobj)
return -EINVAL;
retval = register_filesystem(&debug_fs_type);
if (retval)
kobject_put(debug_kobj);
else
debugfs_registered = true;
return retval;
}
core_initcall(debugfs_init);