OpenCloudOS-Kernel/fs/tracefs/inode.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);