2
0
mirror of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git synced 2025-09-04 20:19:47 +08:00
linux/fs/ramfs/inode.c
NeilBrown 88d5baf690
Change inode_operations.mkdir to return struct dentry *
Some filesystems, such as NFS, cifs, ceph, and fuse, do not have
complete control of sequencing on the actual filesystem (e.g.  on a
different server) and may find that the inode created for a mkdir
request already exists in the icache and dcache by the time the mkdir
request returns.  For example, if the filesystem is mounted twice the
directory could be visible on the other mount before it is on the
original mount, and a pair of name_to_handle_at(), open_by_handle_at()
calls could instantiate the directory inode with an IS_ROOT() dentry
before the first mkdir returns.

This means that the dentry passed to ->mkdir() may not be the one that
is associated with the inode after the ->mkdir() completes.  Some
callers need to interact with the inode after the ->mkdir completes and
they currently need to perform a lookup in the (rare) case that the
dentry is no longer hashed.

This lookup-after-mkdir requires that the directory remains locked to
avoid races.  Planned future patches to lock the dentry rather than the
directory will mean that this lookup cannot be performed atomically with
the mkdir.

To remove this barrier, this patch changes ->mkdir to return the
resulting dentry if it is different from the one passed in.
Possible returns are:
  NULL - the directory was created and no other dentry was used
  ERR_PTR() - an error occurred
  non-NULL - this other dentry was spliced in

This patch only changes file-systems to return "ERR_PTR(err)" instead of
"err" or equivalent transformations.  Subsequent patches will make
further changes to some file-systems to return a correct dentry.

Not all filesystems reliably result in a positive hashed dentry:

- NFS, cifs, hostfs will sometimes need to perform a lookup of
  the name to get inode information.  Races could result in this
  returning something different. Note that this lookup is
  non-atomic which is what we are trying to avoid.  Placing the
  lookup in filesystem code means it only happens when the filesystem
  has no other option.
- kernfs and tracefs leave the dentry negative and the ->revalidate
  operation ensures that lookup will be called to correctly populate
  the dentry.  This could be fixed but I don't think it is important
  to any of the users of vfs_mkdir() which look at the dentry.

The recommendation to use
    d_drop();d_splice_alias()
is ugly but fits with current practice.  A planned future patch will
change this.

Reviewed-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: NeilBrown <neilb@suse.de>
Link: https://lore.kernel.org/r/20250227013949.536172-2-neilb@suse.de
Signed-off-by: Christian Brauner <brauner@kernel.org>
2025-02-27 20:00:17 +01:00

331 lines
7.5 KiB
C

/*
* Resizable simple ram filesystem for Linux.
*
* Copyright (C) 2000 Linus Torvalds.
* 2000 Transmeta Corp.
*
* Usage limits added by David Gibson, Linuxcare Australia.
* This file is released under the GPL.
*/
/*
* NOTE! This filesystem is probably most useful
* not as a real filesystem, but as an example of
* how virtual filesystems can be written.
*
* It doesn't get much simpler than this. Consider
* that this file implements the full semantics of
* a POSIX-compliant read-write filesystem.
*
* Note in particular how the filesystem does not
* need to implement any data structures of its own
* to keep track of the virtual data: using the VFS
* caches is sufficient.
*/
#include <linux/fs.h>
#include <linux/pagemap.h>
#include <linux/highmem.h>
#include <linux/time.h>
#include <linux/init.h>
#include <linux/string.h>
#include <linux/backing-dev.h>
#include <linux/ramfs.h>
#include <linux/sched.h>
#include <linux/parser.h>
#include <linux/magic.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
#include <linux/fs_context.h>
#include <linux/fs_parser.h>
#include <linux/seq_file.h>
#include "internal.h"
struct ramfs_mount_opts {
umode_t mode;
};
struct ramfs_fs_info {
struct ramfs_mount_opts mount_opts;
};
#define RAMFS_DEFAULT_MODE 0755
static const struct super_operations ramfs_ops;
static const struct inode_operations ramfs_dir_inode_operations;
struct inode *ramfs_get_inode(struct super_block *sb,
const struct inode *dir, umode_t mode, dev_t dev)
{
struct inode * inode = new_inode(sb);
if (inode) {
inode->i_ino = get_next_ino();
inode_init_owner(&nop_mnt_idmap, inode, dir, mode);
inode->i_mapping->a_ops = &ram_aops;
mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER);
mapping_set_unevictable(inode->i_mapping);
simple_inode_init_ts(inode);
switch (mode & S_IFMT) {
default:
init_special_inode(inode, mode, dev);
break;
case S_IFREG:
inode->i_op = &ramfs_file_inode_operations;
inode->i_fop = &ramfs_file_operations;
break;
case S_IFDIR:
inode->i_op = &ramfs_dir_inode_operations;
inode->i_fop = &simple_dir_operations;
/* directory inodes start off with i_nlink == 2 (for "." entry) */
inc_nlink(inode);
break;
case S_IFLNK:
inode->i_op = &page_symlink_inode_operations;
inode_nohighmem(inode);
break;
}
}
return inode;
}
/*
* File creation. Allocate an inode, and we're done..
*/
/* SMP-safe */
static int
ramfs_mknod(struct mnt_idmap *idmap, struct inode *dir,
struct dentry *dentry, umode_t mode, dev_t dev)
{
struct inode * inode = ramfs_get_inode(dir->i_sb, dir, mode, dev);
int error = -ENOSPC;
if (inode) {
error = security_inode_init_security(inode, dir,
&dentry->d_name, NULL,
NULL);
if (error) {
iput(inode);
goto out;
}
d_instantiate(dentry, inode);
dget(dentry); /* Extra count - pin the dentry in core */
error = 0;
inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
}
out:
return error;
}
static struct dentry *ramfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
struct dentry *dentry, umode_t mode)
{
int retval = ramfs_mknod(&nop_mnt_idmap, dir, dentry, mode | S_IFDIR, 0);
if (!retval)
inc_nlink(dir);
return ERR_PTR(retval);
}
static int ramfs_create(struct mnt_idmap *idmap, struct inode *dir,
struct dentry *dentry, umode_t mode, bool excl)
{
return ramfs_mknod(&nop_mnt_idmap, dir, dentry, mode | S_IFREG, 0);
}
static int ramfs_symlink(struct mnt_idmap *idmap, struct inode *dir,
struct dentry *dentry, const char *symname)
{
struct inode *inode;
int error = -ENOSPC;
inode = ramfs_get_inode(dir->i_sb, dir, S_IFLNK|S_IRWXUGO, 0);
if (inode) {
int l = strlen(symname)+1;
error = security_inode_init_security(inode, dir,
&dentry->d_name, NULL,
NULL);
if (error) {
iput(inode);
goto out;
}
error = page_symlink(inode, symname, l);
if (!error) {
d_instantiate(dentry, inode);
dget(dentry);
inode_set_mtime_to_ts(dir,
inode_set_ctime_current(dir));
} else
iput(inode);
}
out:
return error;
}
static int ramfs_tmpfile(struct mnt_idmap *idmap,
struct inode *dir, struct file *file, umode_t mode)
{
struct inode *inode;
int error;
inode = ramfs_get_inode(dir->i_sb, dir, mode, 0);
if (!inode)
return -ENOSPC;
error = security_inode_init_security(inode, dir,
&file_dentry(file)->d_name, NULL,
NULL);
if (error) {
iput(inode);
goto out;
}
d_tmpfile(file, inode);
out:
return finish_open_simple(file, error);
}
static const struct inode_operations ramfs_dir_inode_operations = {
.create = ramfs_create,
.lookup = simple_lookup,
.link = simple_link,
.unlink = simple_unlink,
.symlink = ramfs_symlink,
.mkdir = ramfs_mkdir,
.rmdir = simple_rmdir,
.mknod = ramfs_mknod,
.rename = simple_rename,
.tmpfile = ramfs_tmpfile,
};
/*
* Display the mount options in /proc/mounts.
*/
static int ramfs_show_options(struct seq_file *m, struct dentry *root)
{
struct ramfs_fs_info *fsi = root->d_sb->s_fs_info;
if (fsi->mount_opts.mode != RAMFS_DEFAULT_MODE)
seq_printf(m, ",mode=%o", fsi->mount_opts.mode);
return 0;
}
static const struct super_operations ramfs_ops = {
.statfs = simple_statfs,
.drop_inode = generic_delete_inode,
.show_options = ramfs_show_options,
};
enum ramfs_param {
Opt_mode,
};
const struct fs_parameter_spec ramfs_fs_parameters[] = {
fsparam_u32oct("mode", Opt_mode),
{}
};
static int ramfs_parse_param(struct fs_context *fc, struct fs_parameter *param)
{
struct fs_parse_result result;
struct ramfs_fs_info *fsi = fc->s_fs_info;
int opt;
opt = fs_parse(fc, ramfs_fs_parameters, param, &result);
if (opt == -ENOPARAM) {
opt = vfs_parse_fs_param_source(fc, param);
if (opt != -ENOPARAM)
return opt;
/*
* We might like to report bad mount options here;
* but traditionally ramfs has ignored all mount options,
* and as it is used as a !CONFIG_SHMEM simple substitute
* for tmpfs, better continue to ignore other mount options.
*/
return 0;
}
if (opt < 0)
return opt;
switch (opt) {
case Opt_mode:
fsi->mount_opts.mode = result.uint_32 & S_IALLUGO;
break;
}
return 0;
}
static int ramfs_fill_super(struct super_block *sb, struct fs_context *fc)
{
struct ramfs_fs_info *fsi = sb->s_fs_info;
struct inode *inode;
sb->s_maxbytes = MAX_LFS_FILESIZE;
sb->s_blocksize = PAGE_SIZE;
sb->s_blocksize_bits = PAGE_SHIFT;
sb->s_magic = RAMFS_MAGIC;
sb->s_op = &ramfs_ops;
sb->s_time_gran = 1;
inode = ramfs_get_inode(sb, NULL, S_IFDIR | fsi->mount_opts.mode, 0);
sb->s_root = d_make_root(inode);
if (!sb->s_root)
return -ENOMEM;
return 0;
}
static int ramfs_get_tree(struct fs_context *fc)
{
return get_tree_nodev(fc, ramfs_fill_super);
}
static void ramfs_free_fc(struct fs_context *fc)
{
kfree(fc->s_fs_info);
}
static const struct fs_context_operations ramfs_context_ops = {
.free = ramfs_free_fc,
.parse_param = ramfs_parse_param,
.get_tree = ramfs_get_tree,
};
int ramfs_init_fs_context(struct fs_context *fc)
{
struct ramfs_fs_info *fsi;
fsi = kzalloc(sizeof(*fsi), GFP_KERNEL);
if (!fsi)
return -ENOMEM;
fsi->mount_opts.mode = RAMFS_DEFAULT_MODE;
fc->s_fs_info = fsi;
fc->ops = &ramfs_context_ops;
return 0;
}
void ramfs_kill_sb(struct super_block *sb)
{
kfree(sb->s_fs_info);
kill_litter_super(sb);
}
static struct file_system_type ramfs_fs_type = {
.name = "ramfs",
.init_fs_context = ramfs_init_fs_context,
.parameters = ramfs_fs_parameters,
.kill_sb = ramfs_kill_sb,
.fs_flags = FS_USERNS_MOUNT,
};
static int __init init_ramfs_fs(void)
{
return register_filesystem(&ramfs_fs_type);
}
fs_initcall(init_ramfs_fs);