mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-21 16:29:59 +00:00
![Jens Axboe](/assets/img/avatar_default.png)
This gets rid of pdflush for bdi writeout and kupdated style cleaning. pdflush writeout suffers from lack of locality and also requires more threads to handle the same workload, since it has to work in a non-blocking fashion against each queue. This also introduces lumpy behaviour and potential request starvation, since pdflush can be starved for queue access if others are accessing it. A sample ffsb workload that does random writes to files is about 8% faster here on a simple SATA drive during the benchmark phase. File layout also seems a LOT more smooth in vmstat: r b swpd free buff cache si so bi bo in cs us sy id wa 0 1 0 608848 2652 375372 0 0 0 71024 604 24 1 10 48 42 0 1 0 549644 2712 433736 0 0 0 60692 505 27 1 8 48 44 1 0 0 476928 2784 505192 0 0 4 29540 553 24 0 9 53 37 0 1 0 457972 2808 524008 0 0 0 54876 331 16 0 4 38 58 0 1 0 366128 2928 614284 0 0 4 92168 710 58 0 13 53 34 0 1 0 295092 3000 684140 0 0 0 62924 572 23 0 9 53 37 0 1 0 236592 3064 741704 0 0 4 58256 523 17 0 8 48 44 0 1 0 165608 3132 811464 0 0 0 57460 560 21 0 8 54 38 0 1 0 102952 3200 873164 0 0 4 74748 540 29 1 10 48 41 0 1 0 48604 3252 926472 0 0 0 53248 469 29 0 7 47 45 where vanilla tends to fluctuate a lot in the creation phase: r b swpd free buff cache si so bi bo in cs us sy id wa 1 1 0 678716 5792 303380 0 0 0 74064 565 50 1 11 52 36 1 0 0 662488 5864 319396 0 0 4 352 302 329 0 2 47 51 0 1 0 599312 5924 381468 0 0 0 78164 516 55 0 9 51 40 0 1 0 519952 6008 459516 0 0 4 78156 622 56 1 11 52 37 1 1 0 436640 6092 541632 0 0 0 82244 622 54 0 11 48 41 0 1 0 436640 6092 541660 0 0 0 8 152 39 0 0 51 49 0 1 0 332224 6200 644252 0 0 4 102800 728 46 1 13 49 36 1 0 0 274492 6260 701056 0 0 4 12328 459 49 0 7 50 43 0 1 0 211220 6324 763356 0 0 0 106940 515 37 1 10 51 39 1 0 0 160412 6376 813468 0 0 0 8224 415 43 0 6 49 45 1 1 0 85980 6452 886556 0 0 4 113516 575 39 1 11 54 34 0 2 0 85968 6452 886620 0 0 0 1640 158 211 0 0 46 54 A 10 disk test with btrfs performs 26% faster with per-bdi flushing. A SSD based writeback test on XFS performs over 20% better as well, with the throughput being very stable around 1GB/sec, where pdflush only manages 750MB/sec and fluctuates wildly while doing so. Random buffered writes to many files behave a lot better as well, as does random mmap'ed writes. A separate thread is added to sync the super blocks. In the long term, adding sync_supers_bdi() functionality could get rid of this thread again. Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
951 lines
22 KiB
C
951 lines
22 KiB
C
/*
|
|
* linux/fs/super.c
|
|
*
|
|
* Copyright (C) 1991, 1992 Linus Torvalds
|
|
*
|
|
* super.c contains code to handle: - mount structures
|
|
* - super-block tables
|
|
* - filesystem drivers list
|
|
* - mount system call
|
|
* - umount system call
|
|
* - ustat system call
|
|
*
|
|
* GK 2/5/95 - Changed to support mounting the root fs via NFS
|
|
*
|
|
* Added kerneld support: Jacques Gelinas and Bjorn Ekwall
|
|
* Added change_root: Werner Almesberger & Hans Lermen, Feb '96
|
|
* Added options to /proc/mounts:
|
|
* Torbjörn Lindh (torbjorn.lindh@gopta.se), April 14, 1996.
|
|
* Added devfs support: Richard Gooch <rgooch@atnf.csiro.au>, 13-JAN-1998
|
|
* Heavily rewritten for 'one fs - one tree' dcache architecture. AV, Mar 2000
|
|
*/
|
|
|
|
#include <linux/module.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/init.h>
|
|
#include <linux/smp_lock.h>
|
|
#include <linux/acct.h>
|
|
#include <linux/blkdev.h>
|
|
#include <linux/quotaops.h>
|
|
#include <linux/namei.h>
|
|
#include <linux/mount.h>
|
|
#include <linux/security.h>
|
|
#include <linux/syscalls.h>
|
|
#include <linux/vfs.h>
|
|
#include <linux/writeback.h> /* for the emergency remount stuff */
|
|
#include <linux/idr.h>
|
|
#include <linux/kobject.h>
|
|
#include <linux/mutex.h>
|
|
#include <linux/file.h>
|
|
#include <asm/uaccess.h>
|
|
#include "internal.h"
|
|
|
|
|
|
LIST_HEAD(super_blocks);
|
|
DEFINE_SPINLOCK(sb_lock);
|
|
|
|
/**
|
|
* alloc_super - create new superblock
|
|
* @type: filesystem type superblock should belong to
|
|
*
|
|
* Allocates and initializes a new &struct super_block. alloc_super()
|
|
* returns a pointer new superblock or %NULL if allocation had failed.
|
|
*/
|
|
static struct super_block *alloc_super(struct file_system_type *type)
|
|
{
|
|
struct super_block *s = kzalloc(sizeof(struct super_block), GFP_USER);
|
|
static struct super_operations default_op;
|
|
|
|
if (s) {
|
|
if (security_sb_alloc(s)) {
|
|
kfree(s);
|
|
s = NULL;
|
|
goto out;
|
|
}
|
|
INIT_LIST_HEAD(&s->s_files);
|
|
INIT_LIST_HEAD(&s->s_instances);
|
|
INIT_HLIST_HEAD(&s->s_anon);
|
|
INIT_LIST_HEAD(&s->s_inodes);
|
|
INIT_LIST_HEAD(&s->s_dentry_lru);
|
|
init_rwsem(&s->s_umount);
|
|
mutex_init(&s->s_lock);
|
|
lockdep_set_class(&s->s_umount, &type->s_umount_key);
|
|
/*
|
|
* The locking rules for s_lock are up to the
|
|
* filesystem. For example ext3fs has different
|
|
* lock ordering than usbfs:
|
|
*/
|
|
lockdep_set_class(&s->s_lock, &type->s_lock_key);
|
|
/*
|
|
* sget() can have s_umount recursion.
|
|
*
|
|
* When it cannot find a suitable sb, it allocates a new
|
|
* one (this one), and tries again to find a suitable old
|
|
* one.
|
|
*
|
|
* In case that succeeds, it will acquire the s_umount
|
|
* lock of the old one. Since these are clearly distrinct
|
|
* locks, and this object isn't exposed yet, there's no
|
|
* risk of deadlocks.
|
|
*
|
|
* Annotate this by putting this lock in a different
|
|
* subclass.
|
|
*/
|
|
down_write_nested(&s->s_umount, SINGLE_DEPTH_NESTING);
|
|
s->s_count = S_BIAS;
|
|
atomic_set(&s->s_active, 1);
|
|
mutex_init(&s->s_vfs_rename_mutex);
|
|
mutex_init(&s->s_dquot.dqio_mutex);
|
|
mutex_init(&s->s_dquot.dqonoff_mutex);
|
|
init_rwsem(&s->s_dquot.dqptr_sem);
|
|
init_waitqueue_head(&s->s_wait_unfrozen);
|
|
s->s_maxbytes = MAX_NON_LFS;
|
|
s->dq_op = sb_dquot_ops;
|
|
s->s_qcop = sb_quotactl_ops;
|
|
s->s_op = &default_op;
|
|
s->s_time_gran = 1000000000;
|
|
}
|
|
out:
|
|
return s;
|
|
}
|
|
|
|
/**
|
|
* destroy_super - frees a superblock
|
|
* @s: superblock to free
|
|
*
|
|
* Frees a superblock.
|
|
*/
|
|
static inline void destroy_super(struct super_block *s)
|
|
{
|
|
security_sb_free(s);
|
|
kfree(s->s_subtype);
|
|
kfree(s->s_options);
|
|
kfree(s);
|
|
}
|
|
|
|
/* Superblock refcounting */
|
|
|
|
/*
|
|
* Drop a superblock's refcount. Returns non-zero if the superblock was
|
|
* destroyed. The caller must hold sb_lock.
|
|
*/
|
|
static int __put_super(struct super_block *sb)
|
|
{
|
|
int ret = 0;
|
|
|
|
if (!--sb->s_count) {
|
|
destroy_super(sb);
|
|
ret = 1;
|
|
}
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* Drop a superblock's refcount.
|
|
* Returns non-zero if the superblock is about to be destroyed and
|
|
* at least is already removed from super_blocks list, so if we are
|
|
* making a loop through super blocks then we need to restart.
|
|
* The caller must hold sb_lock.
|
|
*/
|
|
int __put_super_and_need_restart(struct super_block *sb)
|
|
{
|
|
/* check for race with generic_shutdown_super() */
|
|
if (list_empty(&sb->s_list)) {
|
|
/* super block is removed, need to restart... */
|
|
__put_super(sb);
|
|
return 1;
|
|
}
|
|
/* can't be the last, since s_list is still in use */
|
|
sb->s_count--;
|
|
BUG_ON(sb->s_count == 0);
|
|
return 0;
|
|
}
|
|
|
|
/**
|
|
* put_super - drop a temporary reference to superblock
|
|
* @sb: superblock in question
|
|
*
|
|
* Drops a temporary reference, frees superblock if there's no
|
|
* references left.
|
|
*/
|
|
void put_super(struct super_block *sb)
|
|
{
|
|
spin_lock(&sb_lock);
|
|
__put_super(sb);
|
|
spin_unlock(&sb_lock);
|
|
}
|
|
|
|
|
|
/**
|
|
* deactivate_super - drop an active reference to superblock
|
|
* @s: superblock to deactivate
|
|
*
|
|
* Drops an active reference to superblock, acquiring a temprory one if
|
|
* there is no active references left. In that case we lock superblock,
|
|
* tell fs driver to shut it down and drop the temporary reference we
|
|
* had just acquired.
|
|
*/
|
|
void deactivate_super(struct super_block *s)
|
|
{
|
|
struct file_system_type *fs = s->s_type;
|
|
if (atomic_dec_and_lock(&s->s_active, &sb_lock)) {
|
|
s->s_count -= S_BIAS-1;
|
|
spin_unlock(&sb_lock);
|
|
vfs_dq_off(s, 0);
|
|
down_write(&s->s_umount);
|
|
fs->kill_sb(s);
|
|
put_filesystem(fs);
|
|
put_super(s);
|
|
}
|
|
}
|
|
|
|
EXPORT_SYMBOL(deactivate_super);
|
|
|
|
/**
|
|
* deactivate_locked_super - drop an active reference to superblock
|
|
* @s: superblock to deactivate
|
|
*
|
|
* Equivalent of up_write(&s->s_umount); deactivate_super(s);, except that
|
|
* it does not unlock it until it's all over. As the result, it's safe to
|
|
* use to dispose of new superblock on ->get_sb() failure exits - nobody
|
|
* will see the sucker until it's all over. Equivalent using up_write +
|
|
* deactivate_super is safe for that purpose only if superblock is either
|
|
* safe to use or has NULL ->s_root when we unlock.
|
|
*/
|
|
void deactivate_locked_super(struct super_block *s)
|
|
{
|
|
struct file_system_type *fs = s->s_type;
|
|
if (atomic_dec_and_lock(&s->s_active, &sb_lock)) {
|
|
s->s_count -= S_BIAS-1;
|
|
spin_unlock(&sb_lock);
|
|
vfs_dq_off(s, 0);
|
|
fs->kill_sb(s);
|
|
put_filesystem(fs);
|
|
put_super(s);
|
|
} else {
|
|
up_write(&s->s_umount);
|
|
}
|
|
}
|
|
|
|
EXPORT_SYMBOL(deactivate_locked_super);
|
|
|
|
/**
|
|
* grab_super - acquire an active reference
|
|
* @s: reference we are trying to make active
|
|
*
|
|
* Tries to acquire an active reference. grab_super() is used when we
|
|
* had just found a superblock in super_blocks or fs_type->fs_supers
|
|
* and want to turn it into a full-blown active reference. grab_super()
|
|
* is called with sb_lock held and drops it. Returns 1 in case of
|
|
* success, 0 if we had failed (superblock contents was already dead or
|
|
* dying when grab_super() had been called).
|
|
*/
|
|
static int grab_super(struct super_block *s) __releases(sb_lock)
|
|
{
|
|
s->s_count++;
|
|
spin_unlock(&sb_lock);
|
|
down_write(&s->s_umount);
|
|
if (s->s_root) {
|
|
spin_lock(&sb_lock);
|
|
if (s->s_count > S_BIAS) {
|
|
atomic_inc(&s->s_active);
|
|
s->s_count--;
|
|
spin_unlock(&sb_lock);
|
|
return 1;
|
|
}
|
|
spin_unlock(&sb_lock);
|
|
}
|
|
up_write(&s->s_umount);
|
|
put_super(s);
|
|
yield();
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* Superblock locking. We really ought to get rid of these two.
|
|
*/
|
|
void lock_super(struct super_block * sb)
|
|
{
|
|
get_fs_excl();
|
|
mutex_lock(&sb->s_lock);
|
|
}
|
|
|
|
void unlock_super(struct super_block * sb)
|
|
{
|
|
put_fs_excl();
|
|
mutex_unlock(&sb->s_lock);
|
|
}
|
|
|
|
EXPORT_SYMBOL(lock_super);
|
|
EXPORT_SYMBOL(unlock_super);
|
|
|
|
/**
|
|
* generic_shutdown_super - common helper for ->kill_sb()
|
|
* @sb: superblock to kill
|
|
*
|
|
* generic_shutdown_super() does all fs-independent work on superblock
|
|
* shutdown. Typical ->kill_sb() should pick all fs-specific objects
|
|
* that need destruction out of superblock, call generic_shutdown_super()
|
|
* and release aforementioned objects. Note: dentries and inodes _are_
|
|
* taken care of and do not need specific handling.
|
|
*
|
|
* Upon calling this function, the filesystem may no longer alter or
|
|
* rearrange the set of dentries belonging to this super_block, nor may it
|
|
* change the attachments of dentries to inodes.
|
|
*/
|
|
void generic_shutdown_super(struct super_block *sb)
|
|
{
|
|
const struct super_operations *sop = sb->s_op;
|
|
|
|
|
|
if (sb->s_root) {
|
|
shrink_dcache_for_umount(sb);
|
|
sync_filesystem(sb);
|
|
get_fs_excl();
|
|
sb->s_flags &= ~MS_ACTIVE;
|
|
|
|
/* bad name - it should be evict_inodes() */
|
|
invalidate_inodes(sb);
|
|
|
|
if (sop->put_super)
|
|
sop->put_super(sb);
|
|
|
|
/* Forget any remaining inodes */
|
|
if (invalidate_inodes(sb)) {
|
|
printk("VFS: Busy inodes after unmount of %s. "
|
|
"Self-destruct in 5 seconds. Have a nice day...\n",
|
|
sb->s_id);
|
|
}
|
|
put_fs_excl();
|
|
}
|
|
spin_lock(&sb_lock);
|
|
/* should be initialized for __put_super_and_need_restart() */
|
|
list_del_init(&sb->s_list);
|
|
list_del(&sb->s_instances);
|
|
spin_unlock(&sb_lock);
|
|
up_write(&sb->s_umount);
|
|
}
|
|
|
|
EXPORT_SYMBOL(generic_shutdown_super);
|
|
|
|
/**
|
|
* sget - find or create a superblock
|
|
* @type: filesystem type superblock should belong to
|
|
* @test: comparison callback
|
|
* @set: setup callback
|
|
* @data: argument to each of them
|
|
*/
|
|
struct super_block *sget(struct file_system_type *type,
|
|
int (*test)(struct super_block *,void *),
|
|
int (*set)(struct super_block *,void *),
|
|
void *data)
|
|
{
|
|
struct super_block *s = NULL;
|
|
struct super_block *old;
|
|
int err;
|
|
|
|
retry:
|
|
spin_lock(&sb_lock);
|
|
if (test) {
|
|
list_for_each_entry(old, &type->fs_supers, s_instances) {
|
|
if (!test(old, data))
|
|
continue;
|
|
if (!grab_super(old))
|
|
goto retry;
|
|
if (s) {
|
|
up_write(&s->s_umount);
|
|
destroy_super(s);
|
|
}
|
|
return old;
|
|
}
|
|
}
|
|
if (!s) {
|
|
spin_unlock(&sb_lock);
|
|
s = alloc_super(type);
|
|
if (!s)
|
|
return ERR_PTR(-ENOMEM);
|
|
goto retry;
|
|
}
|
|
|
|
err = set(s, data);
|
|
if (err) {
|
|
spin_unlock(&sb_lock);
|
|
up_write(&s->s_umount);
|
|
destroy_super(s);
|
|
return ERR_PTR(err);
|
|
}
|
|
s->s_type = type;
|
|
strlcpy(s->s_id, type->name, sizeof(s->s_id));
|
|
list_add_tail(&s->s_list, &super_blocks);
|
|
list_add(&s->s_instances, &type->fs_supers);
|
|
spin_unlock(&sb_lock);
|
|
get_filesystem(type);
|
|
return s;
|
|
}
|
|
|
|
EXPORT_SYMBOL(sget);
|
|
|
|
void drop_super(struct super_block *sb)
|
|
{
|
|
up_read(&sb->s_umount);
|
|
put_super(sb);
|
|
}
|
|
|
|
EXPORT_SYMBOL(drop_super);
|
|
|
|
/**
|
|
* sync_supers - helper for periodic superblock writeback
|
|
*
|
|
* Call the write_super method if present on all dirty superblocks in
|
|
* the system. This is for the periodic writeback used by most older
|
|
* filesystems. For data integrity superblock writeback use
|
|
* sync_filesystems() instead.
|
|
*
|
|
* Note: check the dirty flag before waiting, so we don't
|
|
* hold up the sync while mounting a device. (The newly
|
|
* mounted device won't need syncing.)
|
|
*/
|
|
void sync_supers(void)
|
|
{
|
|
struct super_block *sb;
|
|
|
|
spin_lock(&sb_lock);
|
|
restart:
|
|
list_for_each_entry(sb, &super_blocks, s_list) {
|
|
if (sb->s_op->write_super && sb->s_dirt) {
|
|
sb->s_count++;
|
|
spin_unlock(&sb_lock);
|
|
|
|
down_read(&sb->s_umount);
|
|
if (sb->s_root && sb->s_dirt)
|
|
sb->s_op->write_super(sb);
|
|
up_read(&sb->s_umount);
|
|
|
|
spin_lock(&sb_lock);
|
|
if (__put_super_and_need_restart(sb))
|
|
goto restart;
|
|
}
|
|
}
|
|
spin_unlock(&sb_lock);
|
|
}
|
|
|
|
/**
|
|
* get_super - get the superblock of a device
|
|
* @bdev: device to get the superblock for
|
|
*
|
|
* Scans the superblock list and finds the superblock of the file system
|
|
* mounted on the device given. %NULL is returned if no match is found.
|
|
*/
|
|
|
|
struct super_block * get_super(struct block_device *bdev)
|
|
{
|
|
struct super_block *sb;
|
|
|
|
if (!bdev)
|
|
return NULL;
|
|
|
|
spin_lock(&sb_lock);
|
|
rescan:
|
|
list_for_each_entry(sb, &super_blocks, s_list) {
|
|
if (sb->s_bdev == bdev) {
|
|
sb->s_count++;
|
|
spin_unlock(&sb_lock);
|
|
down_read(&sb->s_umount);
|
|
if (sb->s_root)
|
|
return sb;
|
|
up_read(&sb->s_umount);
|
|
/* restart only when sb is no longer on the list */
|
|
spin_lock(&sb_lock);
|
|
if (__put_super_and_need_restart(sb))
|
|
goto rescan;
|
|
}
|
|
}
|
|
spin_unlock(&sb_lock);
|
|
return NULL;
|
|
}
|
|
|
|
EXPORT_SYMBOL(get_super);
|
|
|
|
struct super_block * user_get_super(dev_t dev)
|
|
{
|
|
struct super_block *sb;
|
|
|
|
spin_lock(&sb_lock);
|
|
rescan:
|
|
list_for_each_entry(sb, &super_blocks, s_list) {
|
|
if (sb->s_dev == dev) {
|
|
sb->s_count++;
|
|
spin_unlock(&sb_lock);
|
|
down_read(&sb->s_umount);
|
|
if (sb->s_root)
|
|
return sb;
|
|
up_read(&sb->s_umount);
|
|
/* restart only when sb is no longer on the list */
|
|
spin_lock(&sb_lock);
|
|
if (__put_super_and_need_restart(sb))
|
|
goto rescan;
|
|
}
|
|
}
|
|
spin_unlock(&sb_lock);
|
|
return NULL;
|
|
}
|
|
|
|
SYSCALL_DEFINE2(ustat, unsigned, dev, struct ustat __user *, ubuf)
|
|
{
|
|
struct super_block *s;
|
|
struct ustat tmp;
|
|
struct kstatfs sbuf;
|
|
int err = -EINVAL;
|
|
|
|
s = user_get_super(new_decode_dev(dev));
|
|
if (s == NULL)
|
|
goto out;
|
|
err = vfs_statfs(s->s_root, &sbuf);
|
|
drop_super(s);
|
|
if (err)
|
|
goto out;
|
|
|
|
memset(&tmp,0,sizeof(struct ustat));
|
|
tmp.f_tfree = sbuf.f_bfree;
|
|
tmp.f_tinode = sbuf.f_ffree;
|
|
|
|
err = copy_to_user(ubuf,&tmp,sizeof(struct ustat)) ? -EFAULT : 0;
|
|
out:
|
|
return err;
|
|
}
|
|
|
|
/**
|
|
* do_remount_sb - asks filesystem to change mount options.
|
|
* @sb: superblock in question
|
|
* @flags: numeric part of options
|
|
* @data: the rest of options
|
|
* @force: whether or not to force the change
|
|
*
|
|
* Alters the mount options of a mounted file system.
|
|
*/
|
|
int do_remount_sb(struct super_block *sb, int flags, void *data, int force)
|
|
{
|
|
int retval;
|
|
int remount_rw;
|
|
|
|
#ifdef CONFIG_BLOCK
|
|
if (!(flags & MS_RDONLY) && bdev_read_only(sb->s_bdev))
|
|
return -EACCES;
|
|
#endif
|
|
if (flags & MS_RDONLY)
|
|
acct_auto_close(sb);
|
|
shrink_dcache_sb(sb);
|
|
sync_filesystem(sb);
|
|
|
|
/* If we are remounting RDONLY and current sb is read/write,
|
|
make sure there are no rw files opened */
|
|
if ((flags & MS_RDONLY) && !(sb->s_flags & MS_RDONLY)) {
|
|
if (force)
|
|
mark_files_ro(sb);
|
|
else if (!fs_may_remount_ro(sb))
|
|
return -EBUSY;
|
|
retval = vfs_dq_off(sb, 1);
|
|
if (retval < 0 && retval != -ENOSYS)
|
|
return -EBUSY;
|
|
}
|
|
remount_rw = !(flags & MS_RDONLY) && (sb->s_flags & MS_RDONLY);
|
|
|
|
if (sb->s_op->remount_fs) {
|
|
retval = sb->s_op->remount_fs(sb, &flags, data);
|
|
if (retval)
|
|
return retval;
|
|
}
|
|
sb->s_flags = (sb->s_flags & ~MS_RMT_MASK) | (flags & MS_RMT_MASK);
|
|
if (remount_rw)
|
|
vfs_dq_quota_on_remount(sb);
|
|
return 0;
|
|
}
|
|
|
|
static void do_emergency_remount(struct work_struct *work)
|
|
{
|
|
struct super_block *sb;
|
|
|
|
spin_lock(&sb_lock);
|
|
list_for_each_entry(sb, &super_blocks, s_list) {
|
|
sb->s_count++;
|
|
spin_unlock(&sb_lock);
|
|
down_write(&sb->s_umount);
|
|
if (sb->s_root && sb->s_bdev && !(sb->s_flags & MS_RDONLY)) {
|
|
/*
|
|
* ->remount_fs needs lock_kernel().
|
|
*
|
|
* What lock protects sb->s_flags??
|
|
*/
|
|
do_remount_sb(sb, MS_RDONLY, NULL, 1);
|
|
}
|
|
up_write(&sb->s_umount);
|
|
put_super(sb);
|
|
spin_lock(&sb_lock);
|
|
}
|
|
spin_unlock(&sb_lock);
|
|
kfree(work);
|
|
printk("Emergency Remount complete\n");
|
|
}
|
|
|
|
void emergency_remount(void)
|
|
{
|
|
struct work_struct *work;
|
|
|
|
work = kmalloc(sizeof(*work), GFP_ATOMIC);
|
|
if (work) {
|
|
INIT_WORK(work, do_emergency_remount);
|
|
schedule_work(work);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Unnamed block devices are dummy devices used by virtual
|
|
* filesystems which don't use real block-devices. -- jrs
|
|
*/
|
|
|
|
static DEFINE_IDA(unnamed_dev_ida);
|
|
static DEFINE_SPINLOCK(unnamed_dev_lock);/* protects the above */
|
|
static int unnamed_dev_start = 0; /* don't bother trying below it */
|
|
|
|
int set_anon_super(struct super_block *s, void *data)
|
|
{
|
|
int dev;
|
|
int error;
|
|
|
|
retry:
|
|
if (ida_pre_get(&unnamed_dev_ida, GFP_ATOMIC) == 0)
|
|
return -ENOMEM;
|
|
spin_lock(&unnamed_dev_lock);
|
|
error = ida_get_new_above(&unnamed_dev_ida, unnamed_dev_start, &dev);
|
|
if (!error)
|
|
unnamed_dev_start = dev + 1;
|
|
spin_unlock(&unnamed_dev_lock);
|
|
if (error == -EAGAIN)
|
|
/* We raced and lost with another CPU. */
|
|
goto retry;
|
|
else if (error)
|
|
return -EAGAIN;
|
|
|
|
if ((dev & MAX_ID_MASK) == (1 << MINORBITS)) {
|
|
spin_lock(&unnamed_dev_lock);
|
|
ida_remove(&unnamed_dev_ida, dev);
|
|
if (unnamed_dev_start > dev)
|
|
unnamed_dev_start = dev;
|
|
spin_unlock(&unnamed_dev_lock);
|
|
return -EMFILE;
|
|
}
|
|
s->s_dev = MKDEV(0, dev & MINORMASK);
|
|
return 0;
|
|
}
|
|
|
|
EXPORT_SYMBOL(set_anon_super);
|
|
|
|
void kill_anon_super(struct super_block *sb)
|
|
{
|
|
int slot = MINOR(sb->s_dev);
|
|
|
|
generic_shutdown_super(sb);
|
|
spin_lock(&unnamed_dev_lock);
|
|
ida_remove(&unnamed_dev_ida, slot);
|
|
if (slot < unnamed_dev_start)
|
|
unnamed_dev_start = slot;
|
|
spin_unlock(&unnamed_dev_lock);
|
|
}
|
|
|
|
EXPORT_SYMBOL(kill_anon_super);
|
|
|
|
void kill_litter_super(struct super_block *sb)
|
|
{
|
|
if (sb->s_root)
|
|
d_genocide(sb->s_root);
|
|
kill_anon_super(sb);
|
|
}
|
|
|
|
EXPORT_SYMBOL(kill_litter_super);
|
|
|
|
static int ns_test_super(struct super_block *sb, void *data)
|
|
{
|
|
return sb->s_fs_info == data;
|
|
}
|
|
|
|
static int ns_set_super(struct super_block *sb, void *data)
|
|
{
|
|
sb->s_fs_info = data;
|
|
return set_anon_super(sb, NULL);
|
|
}
|
|
|
|
int get_sb_ns(struct file_system_type *fs_type, int flags, void *data,
|
|
int (*fill_super)(struct super_block *, void *, int),
|
|
struct vfsmount *mnt)
|
|
{
|
|
struct super_block *sb;
|
|
|
|
sb = sget(fs_type, ns_test_super, ns_set_super, data);
|
|
if (IS_ERR(sb))
|
|
return PTR_ERR(sb);
|
|
|
|
if (!sb->s_root) {
|
|
int err;
|
|
sb->s_flags = flags;
|
|
err = fill_super(sb, data, flags & MS_SILENT ? 1 : 0);
|
|
if (err) {
|
|
deactivate_locked_super(sb);
|
|
return err;
|
|
}
|
|
|
|
sb->s_flags |= MS_ACTIVE;
|
|
}
|
|
|
|
simple_set_mnt(mnt, sb);
|
|
return 0;
|
|
}
|
|
|
|
EXPORT_SYMBOL(get_sb_ns);
|
|
|
|
#ifdef CONFIG_BLOCK
|
|
static int set_bdev_super(struct super_block *s, void *data)
|
|
{
|
|
s->s_bdev = data;
|
|
s->s_dev = s->s_bdev->bd_dev;
|
|
return 0;
|
|
}
|
|
|
|
static int test_bdev_super(struct super_block *s, void *data)
|
|
{
|
|
return (void *)s->s_bdev == data;
|
|
}
|
|
|
|
int get_sb_bdev(struct file_system_type *fs_type,
|
|
int flags, const char *dev_name, void *data,
|
|
int (*fill_super)(struct super_block *, void *, int),
|
|
struct vfsmount *mnt)
|
|
{
|
|
struct block_device *bdev;
|
|
struct super_block *s;
|
|
fmode_t mode = FMODE_READ;
|
|
int error = 0;
|
|
|
|
if (!(flags & MS_RDONLY))
|
|
mode |= FMODE_WRITE;
|
|
|
|
bdev = open_bdev_exclusive(dev_name, mode, fs_type);
|
|
if (IS_ERR(bdev))
|
|
return PTR_ERR(bdev);
|
|
|
|
/*
|
|
* once the super is inserted into the list by sget, s_umount
|
|
* will protect the lockfs code from trying to start a snapshot
|
|
* while we are mounting
|
|
*/
|
|
down(&bdev->bd_mount_sem);
|
|
s = sget(fs_type, test_bdev_super, set_bdev_super, bdev);
|
|
up(&bdev->bd_mount_sem);
|
|
if (IS_ERR(s))
|
|
goto error_s;
|
|
|
|
if (s->s_root) {
|
|
if ((flags ^ s->s_flags) & MS_RDONLY) {
|
|
deactivate_locked_super(s);
|
|
error = -EBUSY;
|
|
goto error_bdev;
|
|
}
|
|
|
|
close_bdev_exclusive(bdev, mode);
|
|
} else {
|
|
char b[BDEVNAME_SIZE];
|
|
|
|
s->s_flags = flags;
|
|
s->s_mode = mode;
|
|
strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id));
|
|
sb_set_blocksize(s, block_size(bdev));
|
|
error = fill_super(s, data, flags & MS_SILENT ? 1 : 0);
|
|
if (error) {
|
|
deactivate_locked_super(s);
|
|
goto error;
|
|
}
|
|
|
|
s->s_flags |= MS_ACTIVE;
|
|
bdev->bd_super = s;
|
|
}
|
|
|
|
simple_set_mnt(mnt, s);
|
|
return 0;
|
|
|
|
error_s:
|
|
error = PTR_ERR(s);
|
|
error_bdev:
|
|
close_bdev_exclusive(bdev, mode);
|
|
error:
|
|
return error;
|
|
}
|
|
|
|
EXPORT_SYMBOL(get_sb_bdev);
|
|
|
|
void kill_block_super(struct super_block *sb)
|
|
{
|
|
struct block_device *bdev = sb->s_bdev;
|
|
fmode_t mode = sb->s_mode;
|
|
|
|
bdev->bd_super = NULL;
|
|
generic_shutdown_super(sb);
|
|
sync_blockdev(bdev);
|
|
close_bdev_exclusive(bdev, mode);
|
|
}
|
|
|
|
EXPORT_SYMBOL(kill_block_super);
|
|
#endif
|
|
|
|
int get_sb_nodev(struct file_system_type *fs_type,
|
|
int flags, void *data,
|
|
int (*fill_super)(struct super_block *, void *, int),
|
|
struct vfsmount *mnt)
|
|
{
|
|
int error;
|
|
struct super_block *s = sget(fs_type, NULL, set_anon_super, NULL);
|
|
|
|
if (IS_ERR(s))
|
|
return PTR_ERR(s);
|
|
|
|
s->s_flags = flags;
|
|
|
|
error = fill_super(s, data, flags & MS_SILENT ? 1 : 0);
|
|
if (error) {
|
|
deactivate_locked_super(s);
|
|
return error;
|
|
}
|
|
s->s_flags |= MS_ACTIVE;
|
|
simple_set_mnt(mnt, s);
|
|
return 0;
|
|
}
|
|
|
|
EXPORT_SYMBOL(get_sb_nodev);
|
|
|
|
static int compare_single(struct super_block *s, void *p)
|
|
{
|
|
return 1;
|
|
}
|
|
|
|
int get_sb_single(struct file_system_type *fs_type,
|
|
int flags, void *data,
|
|
int (*fill_super)(struct super_block *, void *, int),
|
|
struct vfsmount *mnt)
|
|
{
|
|
struct super_block *s;
|
|
int error;
|
|
|
|
s = sget(fs_type, compare_single, set_anon_super, NULL);
|
|
if (IS_ERR(s))
|
|
return PTR_ERR(s);
|
|
if (!s->s_root) {
|
|
s->s_flags = flags;
|
|
error = fill_super(s, data, flags & MS_SILENT ? 1 : 0);
|
|
if (error) {
|
|
deactivate_locked_super(s);
|
|
return error;
|
|
}
|
|
s->s_flags |= MS_ACTIVE;
|
|
}
|
|
do_remount_sb(s, flags, data, 0);
|
|
simple_set_mnt(mnt, s);
|
|
return 0;
|
|
}
|
|
|
|
EXPORT_SYMBOL(get_sb_single);
|
|
|
|
struct vfsmount *
|
|
vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void *data)
|
|
{
|
|
struct vfsmount *mnt;
|
|
char *secdata = NULL;
|
|
int error;
|
|
|
|
if (!type)
|
|
return ERR_PTR(-ENODEV);
|
|
|
|
error = -ENOMEM;
|
|
mnt = alloc_vfsmnt(name);
|
|
if (!mnt)
|
|
goto out;
|
|
|
|
if (data && !(type->fs_flags & FS_BINARY_MOUNTDATA)) {
|
|
secdata = alloc_secdata();
|
|
if (!secdata)
|
|
goto out_mnt;
|
|
|
|
error = security_sb_copy_data(data, secdata);
|
|
if (error)
|
|
goto out_free_secdata;
|
|
}
|
|
|
|
error = type->get_sb(type, flags, name, data, mnt);
|
|
if (error < 0)
|
|
goto out_free_secdata;
|
|
BUG_ON(!mnt->mnt_sb);
|
|
|
|
error = security_sb_kern_mount(mnt->mnt_sb, flags, secdata);
|
|
if (error)
|
|
goto out_sb;
|
|
|
|
mnt->mnt_mountpoint = mnt->mnt_root;
|
|
mnt->mnt_parent = mnt;
|
|
up_write(&mnt->mnt_sb->s_umount);
|
|
free_secdata(secdata);
|
|
return mnt;
|
|
out_sb:
|
|
dput(mnt->mnt_root);
|
|
deactivate_locked_super(mnt->mnt_sb);
|
|
out_free_secdata:
|
|
free_secdata(secdata);
|
|
out_mnt:
|
|
free_vfsmnt(mnt);
|
|
out:
|
|
return ERR_PTR(error);
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(vfs_kern_mount);
|
|
|
|
static struct vfsmount *fs_set_subtype(struct vfsmount *mnt, const char *fstype)
|
|
{
|
|
int err;
|
|
const char *subtype = strchr(fstype, '.');
|
|
if (subtype) {
|
|
subtype++;
|
|
err = -EINVAL;
|
|
if (!subtype[0])
|
|
goto err;
|
|
} else
|
|
subtype = "";
|
|
|
|
mnt->mnt_sb->s_subtype = kstrdup(subtype, GFP_KERNEL);
|
|
err = -ENOMEM;
|
|
if (!mnt->mnt_sb->s_subtype)
|
|
goto err;
|
|
return mnt;
|
|
|
|
err:
|
|
mntput(mnt);
|
|
return ERR_PTR(err);
|
|
}
|
|
|
|
struct vfsmount *
|
|
do_kern_mount(const char *fstype, int flags, const char *name, void *data)
|
|
{
|
|
struct file_system_type *type = get_fs_type(fstype);
|
|
struct vfsmount *mnt;
|
|
if (!type)
|
|
return ERR_PTR(-ENODEV);
|
|
mnt = vfs_kern_mount(type, flags, name, data);
|
|
if (!IS_ERR(mnt) && (type->fs_flags & FS_HAS_SUBTYPE) &&
|
|
!mnt->mnt_sb->s_subtype)
|
|
mnt = fs_set_subtype(mnt, fstype);
|
|
put_filesystem(type);
|
|
return mnt;
|
|
}
|
|
EXPORT_SYMBOL_GPL(do_kern_mount);
|
|
|
|
struct vfsmount *kern_mount_data(struct file_system_type *type, void *data)
|
|
{
|
|
return vfs_kern_mount(type, MS_KERNMOUNT, type->name, data);
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(kern_mount_data);
|