554 lines
14 KiB
C
554 lines
14 KiB
C
// SPDX-License-Identifier: GPL-2.0-only
|
|
/*
|
|
* inode.c - part of tracefs, a pseudo file system for activating tracing
|
|
*
|
|
* Based on debugfs by: Greg Kroah-Hartman <greg@kroah.com>
|
|
*
|
|
* Copyright (C) 2014 Red Hat Inc, author: Steven Rostedt <srostedt@redhat.com>
|
|
*
|
|
* tracefs is the file system that is used by the tracing infrastructure.
|
|
*/
|
|
|
|
#include <linux/module.h>
|
|
#include <linux/fs.h>
|
|
#include <linux/mount.h>
|
|
#include <linux/kobject.h>
|
|
#include <linux/namei.h>
|
|
#include <linux/tracefs.h>
|
|
#include <linux/fsnotify.h>
|
|
#include <linux/security.h>
|
|
#include <linux/seq_file.h>
|
|
#include <linux/parser.h>
|
|
#include <linux/magic.h>
|
|
#include <linux/slab.h>
|
|
|
|
#define TRACEFS_DEFAULT_MODE 0700
|
|
|
|
static struct vfsmount *tracefs_mount;
|
|
static int tracefs_mount_count;
|
|
static bool tracefs_registered;
|
|
|
|
static ssize_t default_read_file(struct file *file, char __user *buf,
|
|
size_t count, loff_t *ppos)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static ssize_t default_write_file(struct file *file, const char __user *buf,
|
|
size_t count, loff_t *ppos)
|
|
{
|
|
return count;
|
|
}
|
|
|
|
static const struct file_operations tracefs_file_operations = {
|
|
.read = default_read_file,
|
|
.write = default_write_file,
|
|
.open = simple_open,
|
|
.llseek = noop_llseek,
|
|
};
|
|
|
|
static struct tracefs_dir_ops {
|
|
int (*mkdir)(const char *name);
|
|
int (*rmdir)(const char *name);
|
|
} tracefs_ops __ro_after_init;
|
|
|
|
static char *get_dname(struct dentry *dentry)
|
|
{
|
|
const char *dname;
|
|
char *name;
|
|
int len = dentry->d_name.len;
|
|
|
|
dname = dentry->d_name.name;
|
|
name = kmalloc(len + 1, GFP_KERNEL);
|
|
if (!name)
|
|
return NULL;
|
|
memcpy(name, dname, len);
|
|
name[len] = 0;
|
|
return name;
|
|
}
|
|
|
|
static int tracefs_syscall_mkdir(struct user_namespace *mnt_userns,
|
|
struct inode *inode, struct dentry *dentry,
|
|
umode_t mode)
|
|
{
|
|
char *name;
|
|
int ret;
|
|
|
|
name = get_dname(dentry);
|
|
if (!name)
|
|
return -ENOMEM;
|
|
|
|
/*
|
|
* The mkdir call can call the generic functions that create
|
|
* the files within the tracefs system. It is up to the individual
|
|
* mkdir routine to handle races.
|
|
*/
|
|
inode_unlock(inode);
|
|
ret = tracefs_ops.mkdir(name);
|
|
inode_lock(inode);
|
|
|
|
kfree(name);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static int tracefs_syscall_rmdir(struct inode *inode, struct dentry *dentry)
|
|
{
|
|
char *name;
|
|
int ret;
|
|
|
|
name = get_dname(dentry);
|
|
if (!name)
|
|
return -ENOMEM;
|
|
|
|
/*
|
|
* The rmdir call can call the generic functions that create
|
|
* the files within the tracefs system. It is up to the individual
|
|
* rmdir routine to handle races.
|
|
* This time we need to unlock not only the parent (inode) but
|
|
* also the directory that is being deleted.
|
|
*/
|
|
inode_unlock(inode);
|
|
inode_unlock(dentry->d_inode);
|
|
|
|
ret = tracefs_ops.rmdir(name);
|
|
|
|
inode_lock_nested(inode, I_MUTEX_PARENT);
|
|
inode_lock(dentry->d_inode);
|
|
|
|
kfree(name);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static const struct inode_operations tracefs_dir_inode_operations = {
|
|
.lookup = simple_lookup,
|
|
.mkdir = tracefs_syscall_mkdir,
|
|
.rmdir = tracefs_syscall_rmdir,
|
|
};
|
|
|
|
static struct inode *tracefs_get_inode(struct super_block *sb)
|
|
{
|
|
struct inode *inode = new_inode(sb);
|
|
if (inode) {
|
|
inode->i_ino = get_next_ino();
|
|
inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
|
|
}
|
|
return inode;
|
|
}
|
|
|
|
struct tracefs_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 tracefs_fs_info {
|
|
struct tracefs_mount_opts mount_opts;
|
|
};
|
|
|
|
static int tracefs_parse_options(char *data, struct tracefs_mount_opts *opts)
|
|
{
|
|
substring_t args[MAX_OPT_ARGS];
|
|
int option;
|
|
int token;
|
|
kuid_t uid;
|
|
kgid_t gid;
|
|
char *p;
|
|
|
|
opts->mode = TRACEFS_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 tracefs has ignored all mount options
|
|
*/
|
|
}
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int tracefs_apply_options(struct super_block *sb)
|
|
{
|
|
struct tracefs_fs_info *fsi = sb->s_fs_info;
|
|
struct inode *inode = sb->s_root->d_inode;
|
|
struct tracefs_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 tracefs_remount(struct super_block *sb, int *flags, char *data)
|
|
{
|
|
int err;
|
|
struct tracefs_fs_info *fsi = sb->s_fs_info;
|
|
|
|
sync_filesystem(sb);
|
|
err = tracefs_parse_options(data, &fsi->mount_opts);
|
|
if (err)
|
|
goto fail;
|
|
|
|
tracefs_apply_options(sb);
|
|
|
|
fail:
|
|
return err;
|
|
}
|
|
|
|
static int tracefs_show_options(struct seq_file *m, struct dentry *root)
|
|
{
|
|
struct tracefs_fs_info *fsi = root->d_sb->s_fs_info;
|
|
struct tracefs_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 != TRACEFS_DEFAULT_MODE)
|
|
seq_printf(m, ",mode=%o", opts->mode);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static const struct super_operations tracefs_super_operations = {
|
|
.statfs = simple_statfs,
|
|
.remount_fs = tracefs_remount,
|
|
.show_options = tracefs_show_options,
|
|
};
|
|
|
|
static int trace_fill_super(struct super_block *sb, void *data, int silent)
|
|
{
|
|
static const struct tree_descr trace_files[] = {{""}};
|
|
struct tracefs_fs_info *fsi;
|
|
int err;
|
|
|
|
fsi = kzalloc(sizeof(struct tracefs_fs_info), GFP_KERNEL);
|
|
sb->s_fs_info = fsi;
|
|
if (!fsi) {
|
|
err = -ENOMEM;
|
|
goto fail;
|
|
}
|
|
|
|
err = tracefs_parse_options(data, &fsi->mount_opts);
|
|
if (err)
|
|
goto fail;
|
|
|
|
err = simple_fill_super(sb, TRACEFS_MAGIC, trace_files);
|
|
if (err)
|
|
goto fail;
|
|
|
|
sb->s_op = &tracefs_super_operations;
|
|
|
|
tracefs_apply_options(sb);
|
|
|
|
return 0;
|
|
|
|
fail:
|
|
kfree(fsi);
|
|
sb->s_fs_info = NULL;
|
|
return err;
|
|
}
|
|
|
|
static struct dentry *trace_mount(struct file_system_type *fs_type,
|
|
int flags, const char *dev_name,
|
|
void *data)
|
|
{
|
|
return mount_single(fs_type, flags, data, trace_fill_super);
|
|
}
|
|
|
|
static struct file_system_type trace_fs_type = {
|
|
.owner = THIS_MODULE,
|
|
.name = "tracefs",
|
|
.mount = trace_mount,
|
|
.kill_sb = kill_litter_super,
|
|
};
|
|
MODULE_ALIAS_FS("tracefs");
|
|
|
|
static struct dentry *start_creating(const char *name, struct dentry *parent)
|
|
{
|
|
struct dentry *dentry;
|
|
int error;
|
|
|
|
pr_debug("tracefs: creating file '%s'\n",name);
|
|
|
|
error = simple_pin_fs(&trace_fs_type, &tracefs_mount,
|
|
&tracefs_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 = tracefs_mount->mnt_root;
|
|
|
|
inode_lock(parent->d_inode);
|
|
if (unlikely(IS_DEADDIR(parent->d_inode)))
|
|
dentry = ERR_PTR(-ENOENT);
|
|
else
|
|
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)) {
|
|
inode_unlock(parent->d_inode);
|
|
simple_release_fs(&tracefs_mount, &tracefs_mount_count);
|
|
}
|
|
|
|
return dentry;
|
|
}
|
|
|
|
static struct dentry *failed_creating(struct dentry *dentry)
|
|
{
|
|
inode_unlock(dentry->d_parent->d_inode);
|
|
dput(dentry);
|
|
simple_release_fs(&tracefs_mount, &tracefs_mount_count);
|
|
return NULL;
|
|
}
|
|
|
|
static struct dentry *end_creating(struct dentry *dentry)
|
|
{
|
|
inode_unlock(dentry->d_parent->d_inode);
|
|
return dentry;
|
|
}
|
|
|
|
/**
|
|
* tracefs_create_file - create a file in the tracefs 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 tracefs 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 tracefs. It allows for a
|
|
* wide range of flexibility in creating a file, or a directory (if you want
|
|
* to create a directory, the tracefs_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 tracefs_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 tracefs is not enabled in the kernel, the value -%ENODEV will be
|
|
* returned.
|
|
*/
|
|
struct dentry *tracefs_create_file(const char *name, umode_t mode,
|
|
struct dentry *parent, void *data,
|
|
const struct file_operations *fops)
|
|
{
|
|
struct dentry *dentry;
|
|
struct inode *inode;
|
|
|
|
if (security_locked_down(LOCKDOWN_TRACEFS))
|
|
return NULL;
|
|
|
|
if (!(mode & S_IFMT))
|
|
mode |= S_IFREG;
|
|
BUG_ON(!S_ISREG(mode));
|
|
dentry = start_creating(name, parent);
|
|
|
|
if (IS_ERR(dentry))
|
|
return NULL;
|
|
|
|
inode = tracefs_get_inode(dentry->d_sb);
|
|
if (unlikely(!inode))
|
|
return failed_creating(dentry);
|
|
|
|
inode->i_mode = mode;
|
|
inode->i_fop = fops ? fops : &tracefs_file_operations;
|
|
inode->i_private = data;
|
|
d_instantiate(dentry, inode);
|
|
fsnotify_create(dentry->d_parent->d_inode, dentry);
|
|
return end_creating(dentry);
|
|
}
|
|
|
|
static struct dentry *__create_dir(const char *name, struct dentry *parent,
|
|
const struct inode_operations *ops)
|
|
{
|
|
struct dentry *dentry = start_creating(name, parent);
|
|
struct inode *inode;
|
|
|
|
if (IS_ERR(dentry))
|
|
return NULL;
|
|
|
|
inode = tracefs_get_inode(dentry->d_sb);
|
|
if (unlikely(!inode))
|
|
return failed_creating(dentry);
|
|
|
|
/* Do not set bits for OTH */
|
|
inode->i_mode = S_IFDIR | S_IRWXU | S_IRUSR| S_IRGRP | S_IXUSR | S_IXGRP;
|
|
inode->i_op = ops;
|
|
inode->i_fop = &simple_dir_operations;
|
|
|
|
/* directory inodes start off with i_nlink == 2 (for "." entry) */
|
|
inc_nlink(inode);
|
|
d_instantiate(dentry, inode);
|
|
inc_nlink(dentry->d_parent->d_inode);
|
|
fsnotify_mkdir(dentry->d_parent->d_inode, dentry);
|
|
return end_creating(dentry);
|
|
}
|
|
|
|
/**
|
|
* tracefs_create_dir - create a directory in the tracefs 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 tracefs filesystem.
|
|
*
|
|
* This function creates a directory in tracefs with the given name.
|
|
*
|
|
* This function will return a pointer to a dentry if it succeeds. This
|
|
* pointer must be passed to the tracefs_remove() function when the file is
|
|
* to be removed. If an error occurs, %NULL will be returned.
|
|
*
|
|
* If tracing is not enabled in the kernel, the value -%ENODEV will be
|
|
* returned.
|
|
*/
|
|
struct dentry *tracefs_create_dir(const char *name, struct dentry *parent)
|
|
{
|
|
return __create_dir(name, parent, &simple_dir_inode_operations);
|
|
}
|
|
|
|
/**
|
|
* tracefs_create_instance_dir - create the tracing instances directory
|
|
* @name: The name of the instances directory to create
|
|
* @parent: The parent directory that the instances directory will exist
|
|
* @mkdir: The function to call when a mkdir is performed.
|
|
* @rmdir: The function to call when a rmdir is performed.
|
|
*
|
|
* Only one instances directory is allowed.
|
|
*
|
|
* The instances directory is special as it allows for mkdir and rmdir to
|
|
* to be done by userspace. When a mkdir or rmdir is performed, the inode
|
|
* locks are released and the methods passed in (@mkdir and @rmdir) are
|
|
* called without locks and with the name of the directory being created
|
|
* within the instances directory.
|
|
*
|
|
* Returns the dentry of the instances directory.
|
|
*/
|
|
__init struct dentry *tracefs_create_instance_dir(const char *name,
|
|
struct dentry *parent,
|
|
int (*mkdir)(const char *name),
|
|
int (*rmdir)(const char *name))
|
|
{
|
|
struct dentry *dentry;
|
|
|
|
/* Only allow one instance of the instances directory. */
|
|
if (WARN_ON(tracefs_ops.mkdir || tracefs_ops.rmdir))
|
|
return NULL;
|
|
|
|
dentry = __create_dir(name, parent, &tracefs_dir_inode_operations);
|
|
if (!dentry)
|
|
return NULL;
|
|
|
|
tracefs_ops.mkdir = mkdir;
|
|
tracefs_ops.rmdir = rmdir;
|
|
|
|
return dentry;
|
|
}
|
|
|
|
static void remove_one(struct dentry *victim)
|
|
{
|
|
simple_release_fs(&tracefs_mount, &tracefs_mount_count);
|
|
}
|
|
|
|
/**
|
|
* tracefs_remove - 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 tracefs that
|
|
* was previously created with a call to another tracefs function
|
|
* (like tracefs_create_file() or variants thereof.)
|
|
*/
|
|
void tracefs_remove(struct dentry *dentry)
|
|
{
|
|
if (IS_ERR_OR_NULL(dentry))
|
|
return;
|
|
|
|
simple_pin_fs(&trace_fs_type, &tracefs_mount, &tracefs_mount_count);
|
|
simple_recursive_removal(dentry, remove_one);
|
|
simple_release_fs(&tracefs_mount, &tracefs_mount_count);
|
|
}
|
|
|
|
/**
|
|
* tracefs_initialized - Tells whether tracefs has been registered
|
|
*/
|
|
bool tracefs_initialized(void)
|
|
{
|
|
return tracefs_registered;
|
|
}
|
|
|
|
static int __init tracefs_init(void)
|
|
{
|
|
int retval;
|
|
|
|
retval = sysfs_create_mount_point(kernel_kobj, "tracing");
|
|
if (retval)
|
|
return -EINVAL;
|
|
|
|
retval = register_filesystem(&trace_fs_type);
|
|
if (!retval)
|
|
tracefs_registered = true;
|
|
|
|
return retval;
|
|
}
|
|
core_initcall(tracefs_init);
|