Files
linux/fs/ramfs/inode.c
T
Linus Torvalds 1c3e8cef79 Merge tag 'vfs-7.3-rc1.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs
Pull misc vfs updates from Christian Brauner:
 "Bigger cleanups:

   - The lockref dead-count handling is tidied up.

     The open-coded check for a count below zero as the dead marker
     relies on information the caller should not have.

   - make put_mnt_ns() leave mounts connected. Destroying a mount
     namespace disconnected its mounts from their mount points. So a
     file descriptor still open on the parent of a mount point could be
     used to peek under it.

     Locked mounts were already kept connected to prevent exactly that.
     But a mount is only locked when its tree is copied across a user
     namespace boundary. So a mount namespace set up by a privileged
     component had no locked mounts and its mounts were disconnected.
     Passing UMOUNT_CONNECTED keeps every mount connected and prevents
     that bug.

   - vfs_prepare_mode() passes S_IFDIR for directories. I meant to fix
     that ago but didn't get to it. So now someone finally did it.

     This kills the exception where the mode could be 0 when a directory
     was created whereas every other creation operation passed it
     explicitly already.

   - move long delayed work for ufs, jffs2, hfsplus, hfs and affs from
     the per-cpu system_long_wq to the new unbound system_dfl_long_wq.

     None of that work relies on per-cpu state and the work item is
     enqueued with queue_delayed_work() whose timer is global anyway. So
     it may as well benefit from scheduler task placement.

  Smaller fixes and cleanups:

   - unlock_buffer() and journal_end_buffer_io_sync() use
     clear_and_wake_up_bit()

   - the pipe page pools are unified into a single per-pipe pool and the
     extra wake_up(rd_wait) is limited to EPOLLET consumers

   - eventpoll now computes its timer slack lazily in ep_poll()

   - shrink_dcache_for_umount() keeps making progress on busy roots

   - excess xarray nodes are freed in clear_inode()

   - romfs detects hard link cycles

   - the user path of nested backing files is fixed

   - pidfd holds exec_update_lock around the namespace ioctl

   - non-memcg-aware nr_cached_objects is skipped during memcg slab
     shrink

   - iomap_write_iter() always returns status

   - mangle_path() is renamed to seq_mangle_path()

   - inode timestamp accessors are annotated

   - new regression test for pipe->poll_usage.

   - a few documentation, kernel-doc and selftest fixes"

* tag 'vfs-7.3-rc1.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (67 commits)
  selftests/namespaces: Fix racy pipe handshake in timens and pidns_separate
  selftests/epoll: add a regression test for pipe->poll_usage
  pipe: only enable the extra wake_up(rd_wait) for EPOLLET consumers
  pidfd: hold exec_update_lock around namespace ioctl
  fs: fix user path of nested backing files
  fs: remove stale inode_insert5() kernel-doc parameter
  fs: fix switch/case indentation in sysfs() syscall
  fs: document semantics of kstat::{uid,gid} fields
  dcache: keep shrink_dcache_for_umount() making progress on busy roots
  seq_file: rename mangle_path to seq_mangle_path
  nstree: add/fix struct ns_id_req kernel-doc member fields
  dcache: use lockref routines for dead count checks
  lockref: tidy up dead count handling
  initramfs: fix typo in reserve_initrd_mem comment
  fs/pipe: unify the page pools into a single per-pipe pool
  fs: annotate inode timestamp accessors
  eventpoll: compute timer slack lazily in ep_poll()
  selftests/filesystems: add mntns cleanup test
  put_mnt_ns(): leave mounts connected
  affs: Move long delayed work on system_dfl_long_wq
  ...
2026-08-17 12:56:12 -07:00

330 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_make_persistent(dentry, inode);
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, 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)
{
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_make_persistent(dentry, inode);
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 = inode_just_drop,
.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_d_flags = DCACHE_DONTCACHE;
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_obj(*fsi);
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_anon_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);