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
273 lines
5.7 KiB
C
273 lines
5.7 KiB
C
/*
|
|
* linux/fs/proc/root.c
|
|
*
|
|
* Copyright (C) 1991, 1992 Linus Torvalds
|
|
*
|
|
* proc root directory handling functions
|
|
*/
|
|
|
|
#include <asm/uaccess.h>
|
|
|
|
#include <linux/errno.h>
|
|
#include <linux/time.h>
|
|
#include <linux/proc_fs.h>
|
|
#include <linux/stat.h>
|
|
#include <linux/init.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/module.h>
|
|
#include <linux/bitops.h>
|
|
#include <linux/user_namespace.h>
|
|
#include <linux/mount.h>
|
|
#include <linux/pid_namespace.h>
|
|
#include <linux/parser.h>
|
|
|
|
#include "internal.h"
|
|
|
|
static int proc_test_super(struct super_block *sb, void *data)
|
|
{
|
|
return sb->s_fs_info == data;
|
|
}
|
|
|
|
static int proc_set_super(struct super_block *sb, void *data)
|
|
{
|
|
int err = set_anon_super(sb, NULL);
|
|
if (!err) {
|
|
struct pid_namespace *ns = (struct pid_namespace *)data;
|
|
sb->s_fs_info = get_pid_ns(ns);
|
|
}
|
|
return err;
|
|
}
|
|
|
|
enum {
|
|
Opt_gid, Opt_hidepid, Opt_err,
|
|
};
|
|
|
|
static const match_table_t tokens = {
|
|
{Opt_hidepid, "hidepid=%u"},
|
|
{Opt_gid, "gid=%u"},
|
|
{Opt_err, NULL},
|
|
};
|
|
|
|
static int proc_parse_options(char *options, struct pid_namespace *pid)
|
|
{
|
|
char *p;
|
|
substring_t args[MAX_OPT_ARGS];
|
|
int option;
|
|
|
|
if (!options)
|
|
return 1;
|
|
|
|
while ((p = strsep(&options, ",")) != NULL) {
|
|
int token;
|
|
if (!*p)
|
|
continue;
|
|
|
|
args[0].to = args[0].from = NULL;
|
|
token = match_token(p, tokens, args);
|
|
switch (token) {
|
|
case Opt_gid:
|
|
if (match_int(&args[0], &option))
|
|
return 0;
|
|
pid->pid_gid = make_kgid(current_user_ns(), option);
|
|
break;
|
|
case Opt_hidepid:
|
|
if (match_int(&args[0], &option))
|
|
return 0;
|
|
if (option < 0 || option > 2) {
|
|
pr_err("proc: hidepid value must be between 0 and 2.\n");
|
|
return 0;
|
|
}
|
|
pid->hide_pid = option;
|
|
break;
|
|
default:
|
|
pr_err("proc: unrecognized mount option \"%s\" "
|
|
"or missing value\n", p);
|
|
return 0;
|
|
}
|
|
}
|
|
|
|
return 1;
|
|
}
|
|
|
|
int proc_remount(struct super_block *sb, int *flags, char *data)
|
|
{
|
|
struct pid_namespace *pid = sb->s_fs_info;
|
|
|
|
sync_filesystem(sb);
|
|
return !proc_parse_options(data, pid);
|
|
}
|
|
|
|
static struct dentry *proc_mount(struct file_system_type *fs_type,
|
|
int flags, const char *dev_name, void *data)
|
|
{
|
|
int err;
|
|
struct super_block *sb;
|
|
struct pid_namespace *ns;
|
|
char *options;
|
|
|
|
if (flags & MS_KERNMOUNT) {
|
|
ns = (struct pid_namespace *)data;
|
|
options = NULL;
|
|
} else {
|
|
ns = task_active_pid_ns(current);
|
|
options = data;
|
|
|
|
if (!capable(CAP_SYS_ADMIN) && !fs_fully_visible(fs_type))
|
|
return ERR_PTR(-EPERM);
|
|
|
|
/* Does the mounter have privilege over the pid namespace? */
|
|
if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN))
|
|
return ERR_PTR(-EPERM);
|
|
}
|
|
|
|
sb = sget(fs_type, proc_test_super, proc_set_super, flags, ns);
|
|
if (IS_ERR(sb))
|
|
return ERR_CAST(sb);
|
|
|
|
if (!proc_parse_options(options, ns)) {
|
|
deactivate_locked_super(sb);
|
|
return ERR_PTR(-EINVAL);
|
|
}
|
|
|
|
if (!sb->s_root) {
|
|
err = proc_fill_super(sb);
|
|
if (err) {
|
|
deactivate_locked_super(sb);
|
|
return ERR_PTR(err);
|
|
}
|
|
|
|
sb->s_flags |= MS_ACTIVE;
|
|
}
|
|
|
|
return dget(sb->s_root);
|
|
}
|
|
|
|
static void proc_kill_sb(struct super_block *sb)
|
|
{
|
|
struct pid_namespace *ns;
|
|
|
|
ns = (struct pid_namespace *)sb->s_fs_info;
|
|
if (ns->proc_self)
|
|
dput(ns->proc_self);
|
|
kill_anon_super(sb);
|
|
put_pid_ns(ns);
|
|
}
|
|
|
|
static struct file_system_type proc_fs_type = {
|
|
.name = "proc",
|
|
.mount = proc_mount,
|
|
.kill_sb = proc_kill_sb,
|
|
.fs_flags = FS_USERNS_MOUNT,
|
|
};
|
|
|
|
void __init proc_root_init(void)
|
|
{
|
|
int err;
|
|
|
|
proc_init_inodecache();
|
|
err = register_filesystem(&proc_fs_type);
|
|
if (err)
|
|
return;
|
|
|
|
proc_self_init();
|
|
proc_symlink("mounts", NULL, "self/mounts");
|
|
|
|
proc_net_init();
|
|
|
|
#ifdef CONFIG_SYSVIPC
|
|
proc_mkdir("sysvipc", NULL);
|
|
#endif
|
|
proc_mkdir("fs", NULL);
|
|
proc_mkdir("driver", NULL);
|
|
proc_mkdir("fs/nfsd", NULL); /* somewhere for the nfsd filesystem to be mounted */
|
|
#if defined(CONFIG_SUN_OPENPROMFS) || defined(CONFIG_SUN_OPENPROMFS_MODULE)
|
|
/* just give it a mountpoint */
|
|
proc_mkdir("openprom", NULL);
|
|
#endif
|
|
proc_tty_init();
|
|
#ifdef CONFIG_PROC_DEVICETREE
|
|
proc_device_tree_init();
|
|
#endif
|
|
proc_mkdir("bus", NULL);
|
|
proc_sys_init();
|
|
}
|
|
|
|
static int proc_root_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat
|
|
)
|
|
{
|
|
generic_fillattr(dentry->d_inode, stat);
|
|
stat->nlink = proc_root.nlink + nr_processes();
|
|
return 0;
|
|
}
|
|
|
|
static struct dentry *proc_root_lookup(struct inode * dir, struct dentry * dentry, unsigned int flags)
|
|
{
|
|
if (!proc_lookup(dir, dentry, flags))
|
|
return NULL;
|
|
|
|
return proc_pid_lookup(dir, dentry, flags);
|
|
}
|
|
|
|
static int proc_root_readdir(struct file *file, struct dir_context *ctx)
|
|
{
|
|
if (ctx->pos < FIRST_PROCESS_ENTRY) {
|
|
int error = proc_readdir(file, ctx);
|
|
if (unlikely(error <= 0))
|
|
return error;
|
|
ctx->pos = FIRST_PROCESS_ENTRY;
|
|
}
|
|
|
|
return proc_pid_readdir(file, ctx);
|
|
}
|
|
|
|
/*
|
|
* The root /proc directory is special, as it has the
|
|
* <pid> directories. Thus we don't use the generic
|
|
* directory handling functions for that..
|
|
*/
|
|
static const struct file_operations proc_root_operations = {
|
|
.read = generic_read_dir,
|
|
.iterate = proc_root_readdir,
|
|
.llseek = default_llseek,
|
|
};
|
|
|
|
/*
|
|
* proc root can do almost nothing..
|
|
*/
|
|
static const struct inode_operations proc_root_inode_operations = {
|
|
.lookup = proc_root_lookup,
|
|
.getattr = proc_root_getattr,
|
|
};
|
|
|
|
/*
|
|
* This is the root "inode" in the /proc tree..
|
|
*/
|
|
struct proc_dir_entry proc_root = {
|
|
.low_ino = PROC_ROOT_INO,
|
|
.namelen = 5,
|
|
.mode = S_IFDIR | S_IRUGO | S_IXUGO,
|
|
.nlink = 2,
|
|
.count = ATOMIC_INIT(1),
|
|
.proc_iops = &proc_root_inode_operations,
|
|
.proc_fops = &proc_root_operations,
|
|
.parent = &proc_root,
|
|
.name = "/proc",
|
|
};
|
|
|
|
int pid_ns_prepare_proc(struct pid_namespace *ns)
|
|
{
|
|
struct vfsmount *mnt;
|
|
|
|
mnt = kern_mount_data(&proc_fs_type, ns);
|
|
if (IS_ERR(mnt))
|
|
return PTR_ERR(mnt);
|
|
|
|
ns->proc_mnt = mnt;
|
|
return 0;
|
|
}
|
|
|
|
void pid_ns_release_proc(struct pid_namespace *ns)
|
|
{
|
|
kern_unmount(ns->proc_mnt);
|
|
}
|