Blaster4385/linux-IllusionX
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity
linux-IllusionX/fs/btrfs/super.c
Hans van Kranenburg 583b723151 btrfs: Do not use data_alloc_cluster in ssd mode 
This patch provides a band aid to improve the 'out of the box'
behaviour of btrfs for disks that are detected as being an ssd.  In a
general purpose mixed workload scenario, the current ssd mode causes
overallocation of available raw disk space for data, while leaving
behind increasing amounts of unused fragmented free space. This
situation leads to early ENOSPC problems which are harming user
experience and adoption of btrfs as a general purpose filesystem.

This patch modifies the data extent allocation behaviour of the ssd mode
to make it behave identical to nossd mode.  The metadata behaviour and
additional ssd_spread option stay untouched so far.

Recommendations for future development are to reconsider the current
oversimplified nossd / ssd distinction and the broken detection
mechanism based on the rotational attribute in sysfs and provide
experienced users with a more flexible way to choose allocator behaviour
for data and metadata, optimized for certain use cases, while keeping
sane 'out of the box' default settings.  The internals of the current
btrfs code have more potential than what currently gets exposed to the
user to choose from.

    The SSD story...

    In the first year of btrfs development, around early 2008, btrfs
gained a mount option which enables specific functionality for
filesystems on solid state devices. The first occurance of this
functionality is in commit e18e4809, labeled "Add mount -o ssd, which
includes optimizations for seek free storage".

The effect on allocating free space for doing (data) writes is to
'cluster' writes together, writing them out in contiguous space, as
opposed to a 'tetris' way of putting all separate writes into any free
space fragment that fits (which is what the -o nossd behaviour does).

A somewhat simplified explanation of what happens is that, when for
example, the 'cluster' size is set to 2MiB, when we do some writes, the
data allocator will search for a free space block that is 2MiB big, and
put the writes in there. The ssd mode itself might allow a 2MiB cluster
to be composed of multiple free space extents with some existing data in
between, while the additional ssd_spread mount option kills off this
option and requires fully free space.

The idea behind this is (commit 536ac8ae): "The [...] clusters make it
more likely a given IO will completely overwrite the ssd block, so it
doesn't have to do an internal rwm cycle."; ssd block meaning nand erase
block. So, effectively this means applying a "locality based algorithm"
and trying to outsmart the actual ssd.

Since then, various changes have been made to the involved code, but the
basic idea is still present, and gets activated whenever the ssd mount
option is active. This also happens by default, when the rotational flag
as seen at /sys/block/<device>/queue/rotational is set to 0.

    However, there's a number of problems with this approach.

    First, what the optimization is trying to do is outsmart the ssd by
assuming there is a relation between the physical address space of the
block device as seen by btrfs and the actual physical storage of the
ssd, and then adjusting data placement. However, since the introduction
of the Flash Translation Layer (FTL) which is a part of the internal
controller of an ssd, these attempts are futile. The use of good quality
FTL in consumer ssd products might have been limited in 2008, but this
situation has changed drastically soon after that time. Today, even the
flash memory in your automatic cat feeding machine or your grandma's
wheelchair has a full featured one.

Second, the behaviour as described above results in the filesystem being
filled up with badly fragmented free space extents because of relatively
small pieces of space that are freed up by deletes, but not selected
again as part of a 'cluster'. Since the algorithm prefers allocating a
new chunk over going back to tetris mode, the end result is a filesystem
in which all raw space is allocated, but which is composed of
underutilized chunks with a 'shotgun blast' pattern of fragmented free
space. Usually, the next problematic thing that happens is the
filesystem wanting to allocate new space for metadata, which causes the
filesystem to fail in spectacular ways.

Third, the default mount options you get for an ssd ('ssd' mode enabled,
'discard' not enabled), in combination with spreading out writes over
the full address space and ignoring freed up space leads to worst case
behaviour in providing information to the ssd itself, since it will
never learn that all the free space left behind is actually free.  There
are two ways to let an ssd know previously written data does not have to
be preserved, which are sending explicit signals using discard or
fstrim, or by simply overwriting the space with new data.  The worst
case behaviour is the btrfs ssd_spread mount option in combination with
not having discard enabled. It has a side effect of minimizing the reuse
of free space previously written in.

Fourth, the rotational flag in /sys/ does not reliably indicate if the
device is a locally attached ssd. For example, iSCSI or NBD displays as
non-rotational, while a loop device on an ssd shows up as rotational.

The combination of the second and third problem effectively means that
despite all the good intentions, the btrfs ssd mode reliably causes the
ssd hardware and the filesystem structures and performance to be choked
to death. The clickbait version of the title of this story would have
been "Btrfs ssd optimizations considered harmful for ssds".

The current nossd 'tetris' mode (even still without discard) allows a
pattern of overwriting much more previously used space, causing many
more implicit discards to happen because of the overwrite information
the ssd gets. The actual location in the physical address space, as seen
from the point of view of btrfs is irrelevant, because the actual writes
to the low level flash are reordered anyway thanks to the FTL.

    Changes made in the code

1. Make ssd mode data allocation identical to tetris mode, like nossd.
2. Adjust and clean up filesystem mount messages so that we can easily
identify if a kernel has this patch applied or not, when providing
support to end users. Also, make better use of the *_and_info helpers to
only trigger messages on actual state changes.

    Backporting notes

Notes for whoever wants to backport this patch to their 4.9 LTS kernel:
* First apply commit 951e7966 "btrfs: drop the nossd flag when
  remounting with -o ssd", or fixup the differences manually.
* The rest of the conflicts are because of the fs_info refactoring. So,
  for example, instead of using fs_info, it's root->fs_info in
  extent-tree.c

Signed-off-by: Hans van Kranenburg <hans.van.kranenburg@mendix.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2017-08-21 17:47:42 +02:00

2437 lines
63 KiB
C
Raw Blame History

/*
* Copyright (C) 2007 Oracle. All rights reserved.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public
* License v2 as published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*
* You should have received a copy of the GNU General Public
* License along with this program; if not, write to the
* Free Software Foundation, Inc., 59 Temple Place - Suite 330,
* Boston, MA 021110-1307, USA.
*/
#include <linux/blkdev.h>
#include <linux/module.h>
#include <linux/buffer_head.h>
#include <linux/fs.h>
#include <linux/pagemap.h>
#include <linux/highmem.h>
#include <linux/time.h>
#include <linux/init.h>
#include <linux/seq_file.h>
#include <linux/string.h>
#include <linux/backing-dev.h>
#include <linux/mount.h>
#include <linux/mpage.h>
#include <linux/swap.h>
#include <linux/writeback.h>
#include <linux/statfs.h>
#include <linux/compat.h>
#include <linux/parser.h>
#include <linux/ctype.h>
#include <linux/namei.h>
#include <linux/miscdevice.h>
#include <linux/magic.h>
#include <linux/slab.h>
#include <linux/cleancache.h>
#include <linux/ratelimit.h>
#include <linux/btrfs.h>
#include "delayed-inode.h"
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
#include "btrfs_inode.h"
#include "print-tree.h"
#include "hash.h"
#include "props.h"
#include "xattr.h"
#include "volumes.h"
#include "export.h"
#include "compression.h"
#include "rcu-string.h"
#include "dev-replace.h"
#include "free-space-cache.h"
#include "backref.h"
#include "tests/btrfs-tests.h"
#include "qgroup.h"
#include "backref.h"
#define CREATE_TRACE_POINTS
#include <trace/events/btrfs.h>
static const struct super_operations btrfs_super_ops;
static struct file_system_type btrfs_fs_type;
static int btrfs_remount(struct super_block *sb, int *flags, char *data);
const char *btrfs_decode_error(int errno)
{
char *errstr = "unknown";
switch (errno) {
case -EIO:
errstr = "IO failure";
break;
case -ENOMEM:
errstr = "Out of memory";
break;
case -EROFS:
errstr = "Readonly filesystem";
break;
case -EEXIST:
errstr = "Object already exists";
break;
case -ENOSPC:
errstr = "No space left";
break;
case -ENOENT:
errstr = "No such entry";
break;
}
return errstr;
}
/* btrfs handle error by forcing the filesystem readonly */
static void btrfs_handle_error(struct btrfs_fs_info *fs_info)
{
struct super_block *sb = fs_info->sb;
if (sb->s_flags & MS_RDONLY)
return;
if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) {
sb->s_flags |= MS_RDONLY;
btrfs_info(fs_info, "forced readonly");
/*
* Note that a running device replace operation is not
* canceled here although there is no way to update
* the progress. It would add the risk of a deadlock,
* therefore the canceling is omitted. The only penalty
* is that some I/O remains active until the procedure
* completes. The next time when the filesystem is
* mounted writeable again, the device replace
* operation continues.
*/
}
}
/*
* __btrfs_handle_fs_error decodes expected errors from the caller and
* invokes the approciate error response.
*/
__cold
void __btrfs_handle_fs_error(struct btrfs_fs_info *fs_info, const char *function,
unsigned int line, int errno, const char *fmt, ...)
{
struct super_block *sb = fs_info->sb;
#ifdef CONFIG_PRINTK
const char *errstr;
#endif
/*
* Special case: if the error is EROFS, and we're already
* under MS_RDONLY, then it is safe here.
*/
if (errno == -EROFS && (sb->s_flags & MS_RDONLY))
return;
#ifdef CONFIG_PRINTK
errstr = btrfs_decode_error(errno);
if (fmt) {
struct va_format vaf;
va_list args;
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
pr_crit("BTRFS: error (device %s) in %s:%d: errno=%d %s (%pV)\n",
sb->s_id, function, line, errno, errstr, &vaf);
va_end(args);
} else {
pr_crit("BTRFS: error (device %s) in %s:%d: errno=%d %s\n",
sb->s_id, function, line, errno, errstr);
}
#endif
/*
* Today we only save the error info to memory. Long term we'll
* also send it down to the disk
*/
set_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state);
/* Don't go through full error handling during mount */
if (sb->s_flags & MS_BORN)
btrfs_handle_error(fs_info);
}
#ifdef CONFIG_PRINTK
static const char * const logtypes[] = {
"emergency",
"alert",
"critical",
"error",
"warning",
"notice",
"info",
"debug",
};
/*
* Use one ratelimit state per log level so that a flood of less important
* messages doesn't cause more important ones to be dropped.
*/
static struct ratelimit_state printk_limits[] = {
RATELIMIT_STATE_INIT(printk_limits[0], DEFAULT_RATELIMIT_INTERVAL, 100),
RATELIMIT_STATE_INIT(printk_limits[1], DEFAULT_RATELIMIT_INTERVAL, 100),
RATELIMIT_STATE_INIT(printk_limits[2], DEFAULT_RATELIMIT_INTERVAL, 100),
RATELIMIT_STATE_INIT(printk_limits[3], DEFAULT_RATELIMIT_INTERVAL, 100),
RATELIMIT_STATE_INIT(printk_limits[4], DEFAULT_RATELIMIT_INTERVAL, 100),
RATELIMIT_STATE_INIT(printk_limits[5], DEFAULT_RATELIMIT_INTERVAL, 100),
RATELIMIT_STATE_INIT(printk_limits[6], DEFAULT_RATELIMIT_INTERVAL, 100),
RATELIMIT_STATE_INIT(printk_limits[7], DEFAULT_RATELIMIT_INTERVAL, 100),
};
void btrfs_printk(const struct btrfs_fs_info *fs_info, const char *fmt, ...)
{
struct super_block *sb = fs_info->sb;
char lvl[PRINTK_MAX_SINGLE_HEADER_LEN + 1] = "\0";
struct va_format vaf;
va_list args;
int kern_level;
const char *type = logtypes[4];
struct ratelimit_state *ratelimit = &printk_limits[4];
va_start(args, fmt);
while ((kern_level = printk_get_level(fmt)) != 0) {
size_t size = printk_skip_level(fmt) - fmt;
if (kern_level >= '0' && kern_level <= '7') {
memcpy(lvl, fmt, size);
lvl[size] = '\0';
type = logtypes[kern_level - '0'];
ratelimit = &printk_limits[kern_level - '0'];
}
fmt += size;
}
vaf.fmt = fmt;
vaf.va = &args;
if (__ratelimit(ratelimit))
printk("%sBTRFS %s (device %s): %pV\n", lvl, type, sb->s_id, &vaf);
va_end(args);
}
#endif
/*
* We only mark the transaction aborted and then set the file system read-only.
* This will prevent new transactions from starting or trying to join this
* one.
*
* This means that error recovery at the call site is limited to freeing
* any local memory allocations and passing the error code up without
* further cleanup. The transaction should complete as it normally would
* in the call path but will return -EIO.
*
* We'll complete the cleanup in btrfs_end_transaction and
* btrfs_commit_transaction.
*/
__cold
void __btrfs_abort_transaction(struct btrfs_trans_handle *trans,
const char *function,
unsigned int line, int errno)
{
struct btrfs_fs_info *fs_info = trans->fs_info;
trans->aborted = errno;
/* Nothing used. The other threads that have joined this
* transaction may be able to continue. */
if (!trans->dirty && list_empty(&trans->new_bgs)) {
const char *errstr;
errstr = btrfs_decode_error(errno);
btrfs_warn(fs_info,
"%s:%d: Aborting unused transaction(%s).",
function, line, errstr);
return;
}
WRITE_ONCE(trans->transaction->aborted, errno);
/* Wake up anybody who may be waiting on this transaction */
wake_up(&fs_info->transaction_wait);
wake_up(&fs_info->transaction_blocked_wait);
__btrfs_handle_fs_error(fs_info, function, line, errno, NULL);
}
/*
* __btrfs_panic decodes unexpected, fatal errors from the caller,
* issues an alert, and either panics or BUGs, depending on mount options.
*/
__cold
void __btrfs_panic(struct btrfs_fs_info *fs_info, const char *function,
unsigned int line, int errno, const char *fmt, ...)
{
char *s_id = "<unknown>";
const char *errstr;
struct va_format vaf = { .fmt = fmt };
va_list args;
if (fs_info)
s_id = fs_info->sb->s_id;
va_start(args, fmt);
vaf.va = &args;
errstr = btrfs_decode_error(errno);
if (fs_info && (fs_info->mount_opt & BTRFS_MOUNT_PANIC_ON_FATAL_ERROR))
panic(KERN_CRIT "BTRFS panic (device %s) in %s:%d: %pV (errno=%d %s)\n",
s_id, function, line, &vaf, errno, errstr);
btrfs_crit(fs_info, "panic in %s:%d: %pV (errno=%d %s)",
function, line, &vaf, errno, errstr);
va_end(args);
/* Caller calls BUG() */
}
static void btrfs_put_super(struct super_block *sb)
{
close_ctree(btrfs_sb(sb));
}
enum {
Opt_degraded, Opt_subvol, Opt_subvolid, Opt_device, Opt_nodatasum,
Opt_nodatacow, Opt_max_inline, Opt_alloc_start, Opt_nobarrier, Opt_ssd,
Opt_nossd, Opt_ssd_spread, Opt_thread_pool, Opt_noacl, Opt_compress,
Opt_compress_type, Opt_compress_force, Opt_compress_force_type,
Opt_notreelog, Opt_ratio, Opt_flushoncommit, Opt_discard,
Opt_space_cache, Opt_space_cache_version, Opt_clear_cache,
Opt_user_subvol_rm_allowed, Opt_enospc_debug, Opt_subvolrootid,
Opt_defrag, Opt_inode_cache, Opt_no_space_cache, Opt_recovery,
Opt_skip_balance, Opt_check_integrity,
Opt_check_integrity_including_extent_data,
Opt_check_integrity_print_mask, Opt_fatal_errors, Opt_rescan_uuid_tree,
Opt_commit_interval, Opt_barrier, Opt_nodefrag, Opt_nodiscard,
Opt_noenospc_debug, Opt_noflushoncommit, Opt_acl, Opt_datacow,
Opt_datasum, Opt_treelog, Opt_noinode_cache, Opt_usebackuproot,
Opt_nologreplay, Opt_norecovery,
#ifdef CONFIG_BTRFS_DEBUG
Opt_fragment_data, Opt_fragment_metadata, Opt_fragment_all,
#endif
Opt_err,
};
static const match_table_t tokens = {
{Opt_degraded, "degraded"},
{Opt_subvol, "subvol=%s"},
{Opt_subvolid, "subvolid=%s"},
{Opt_device, "device=%s"},
{Opt_nodatasum, "nodatasum"},
{Opt_datasum, "datasum"},
{Opt_nodatacow, "nodatacow"},
{Opt_datacow, "datacow"},
{Opt_nobarrier, "nobarrier"},
{Opt_barrier, "barrier"},
{Opt_max_inline, "max_inline=%s"},
{Opt_alloc_start, "alloc_start=%s"},
{Opt_thread_pool, "thread_pool=%d"},
{Opt_compress, "compress"},
{Opt_compress_type, "compress=%s"},
{Opt_compress_force, "compress-force"},
{Opt_compress_force_type, "compress-force=%s"},
{Opt_ssd, "ssd"},
{Opt_ssd_spread, "ssd_spread"},
{Opt_nossd, "nossd"},
{Opt_acl, "acl"},
{Opt_noacl, "noacl"},
{Opt_notreelog, "notreelog"},
{Opt_treelog, "treelog"},
{Opt_nologreplay, "nologreplay"},
{Opt_norecovery, "norecovery"},
{Opt_flushoncommit, "flushoncommit"},
{Opt_noflushoncommit, "noflushoncommit"},
{Opt_ratio, "metadata_ratio=%d"},
{Opt_discard, "discard"},
{Opt_nodiscard, "nodiscard"},
{Opt_space_cache, "space_cache"},
{Opt_space_cache_version, "space_cache=%s"},
{Opt_clear_cache, "clear_cache"},
{Opt_user_subvol_rm_allowed, "user_subvol_rm_allowed"},
{Opt_enospc_debug, "enospc_debug"},
{Opt_noenospc_debug, "noenospc_debug"},
{Opt_subvolrootid, "subvolrootid=%d"},
{Opt_defrag, "autodefrag"},
{Opt_nodefrag, "noautodefrag"},
{Opt_inode_cache, "inode_cache"},
{Opt_noinode_cache, "noinode_cache"},
{Opt_no_space_cache, "nospace_cache"},
{Opt_recovery, "recovery"}, /* deprecated */
{Opt_usebackuproot, "usebackuproot"},
{Opt_skip_balance, "skip_balance"},
{Opt_check_integrity, "check_int"},
{Opt_check_integrity_including_extent_data, "check_int_data"},
{Opt_check_integrity_print_mask, "check_int_print_mask=%d"},
{Opt_rescan_uuid_tree, "rescan_uuid_tree"},
{Opt_fatal_errors, "fatal_errors=%s"},
{Opt_commit_interval, "commit=%d"},
#ifdef CONFIG_BTRFS_DEBUG
{Opt_fragment_data, "fragment=data"},
{Opt_fragment_metadata, "fragment=metadata"},
{Opt_fragment_all, "fragment=all"},
#endif
{Opt_err, NULL},
};
/*
* Regular mount options parser. Everything that is needed only when
* reading in a new superblock is parsed here.
* XXX JDM: This needs to be cleaned up for remount.
*/
int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
unsigned long new_flags)
{
substring_t args[MAX_OPT_ARGS];
char *p, *num, *orig = NULL;
u64 cache_gen;
int intarg;
int ret = 0;
char *compress_type;
bool compress_force = false;
enum btrfs_compression_type saved_compress_type;
bool saved_compress_force;
int no_compress = 0;
cache_gen = btrfs_super_cache_generation(info->super_copy);
if (btrfs_fs_compat_ro(info, FREE_SPACE_TREE))
btrfs_set_opt(info->mount_opt, FREE_SPACE_TREE);
else if (cache_gen)
btrfs_set_opt(info->mount_opt, SPACE_CACHE);
/*
* Even the options are empty, we still need to do extra check
* against new flags
*/
if (!options)
goto check;
/*
* strsep changes the string, duplicate it because parse_options
* gets called twice
*/
options = kstrdup(options, GFP_KERNEL);
if (!options)
return -ENOMEM;
orig = options;
while ((p = strsep(&options, ",")) != NULL) {
int token;
if (!*p)
continue;
token = match_token(p, tokens, args);
switch (token) {
case Opt_degraded:
btrfs_info(info, "allowing degraded mounts");
btrfs_set_opt(info->mount_opt, DEGRADED);
break;
case Opt_subvol:
case Opt_subvolid:
case Opt_subvolrootid:
case Opt_device:
/*
* These are parsed by btrfs_parse_early_options
* and can be happily ignored here.
*/
break;
case Opt_nodatasum:
btrfs_set_and_info(info, NODATASUM,
"setting nodatasum");
break;
case Opt_datasum:
if (btrfs_test_opt(info, NODATASUM)) {
if (btrfs_test_opt(info, NODATACOW))
btrfs_info(info,
"setting datasum, datacow enabled");
else
btrfs_info(info, "setting datasum");
}
btrfs_clear_opt(info->mount_opt, NODATACOW);
btrfs_clear_opt(info->mount_opt, NODATASUM);
break;
case Opt_nodatacow:
if (!btrfs_test_opt(info, NODATACOW)) {
if (!btrfs_test_opt(info, COMPRESS) ||
!btrfs_test_opt(info, FORCE_COMPRESS)) {
btrfs_info(info,
"setting nodatacow, compression disabled");
} else {
btrfs_info(info, "setting nodatacow");
}
}
btrfs_clear_opt(info->mount_opt, COMPRESS);
btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS);
btrfs_set_opt(info->mount_opt, NODATACOW);
btrfs_set_opt(info->mount_opt, NODATASUM);
break;
case Opt_datacow:
btrfs_clear_and_info(info, NODATACOW,
"setting datacow");
break;
case Opt_compress_force:
case Opt_compress_force_type:
compress_force = true;
/* Fallthrough */
case Opt_compress:
case Opt_compress_type:
saved_compress_type = btrfs_test_opt(info,
COMPRESS) ?
info->compress_type : BTRFS_COMPRESS_NONE;
saved_compress_force =
btrfs_test_opt(info, FORCE_COMPRESS);
if (token == Opt_compress ||
token == Opt_compress_force ||
strncmp(args[0].from, "zlib", 4) == 0) {
compress_type = "zlib";
info->compress_type = BTRFS_COMPRESS_ZLIB;
btrfs_set_opt(info->mount_opt, COMPRESS);
btrfs_clear_opt(info->mount_opt, NODATACOW);
btrfs_clear_opt(info->mount_opt, NODATASUM);
no_compress = 0;
} else if (strncmp(args[0].from, "lzo", 3) == 0) {
compress_type = "lzo";
info->compress_type = BTRFS_COMPRESS_LZO;
btrfs_set_opt(info->mount_opt, COMPRESS);
btrfs_clear_opt(info->mount_opt, NODATACOW);
btrfs_clear_opt(info->mount_opt, NODATASUM);
btrfs_set_fs_incompat(info, COMPRESS_LZO);
no_compress = 0;
} else if (strncmp(args[0].from, "no", 2) == 0) {
compress_type = "no";
btrfs_clear_opt(info->mount_opt, COMPRESS);
btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS);
compress_force = false;
no_compress++;
} else {
ret = -EINVAL;
goto out;
}
if (compress_force) {
btrfs_set_opt(info->mount_opt, FORCE_COMPRESS);
} else {
/*
* If we remount from compress-force=xxx to
* compress=xxx, we need clear FORCE_COMPRESS
* flag, otherwise, there is no way for users
* to disable forcible compression separately.
*/
btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS);
}
if ((btrfs_test_opt(info, COMPRESS) &&
(info->compress_type != saved_compress_type ||
compress_force != saved_compress_force)) ||
(!btrfs_test_opt(info, COMPRESS) &&
no_compress == 1)) {
btrfs_info(info, "%s %s compression",
(compress_force) ? "force" : "use",
compress_type);
}
compress_force = false;
break;
case Opt_ssd:
btrfs_set_and_info(info, SSD,
"enabling ssd optimizations");
btrfs_clear_opt(info->mount_opt, NOSSD);
break;
case Opt_ssd_spread:
btrfs_set_and_info(info, SSD,
"enabling ssd optimizations");
btrfs_set_and_info(info, SSD_SPREAD,
"using spread ssd allocation scheme");
btrfs_clear_opt(info->mount_opt, NOSSD);
break;
case Opt_nossd:
btrfs_set_opt(info->mount_opt, NOSSD);
btrfs_clear_and_info(info, SSD,
"not using ssd optimizations");
btrfs_clear_and_info(info, SSD_SPREAD,
"not using spread ssd allocation scheme");
break;
case Opt_barrier:
btrfs_clear_and_info(info, NOBARRIER,
"turning on barriers");
break;
case Opt_nobarrier:
btrfs_set_and_info(info, NOBARRIER,
"turning off barriers");
break;
case Opt_thread_pool:
ret = match_int(&args[0], &intarg);
if (ret) {
goto out;
} else if (intarg > 0) {
info->thread_pool_size = intarg;
} else {
ret = -EINVAL;
goto out;
}
break;
case Opt_max_inline:
num = match_strdup(&args[0]);
if (num) {
info->max_inline = memparse(num, NULL);
kfree(num);
if (info->max_inline) {
info->max_inline = min_t(u64,
info->max_inline,
info->sectorsize);
}
btrfs_info(info, "max_inline at %llu",
info->max_inline);
} else {
ret = -ENOMEM;
goto out;
}
break;
case Opt_alloc_start:
btrfs_info(info,
"option alloc_start is obsolete, ignored");
break;
case Opt_acl:
#ifdef CONFIG_BTRFS_FS_POSIX_ACL
info->sb->s_flags |= MS_POSIXACL;
break;
#else
btrfs_err(info, "support for ACL not compiled in!");
ret = -EINVAL;
goto out;
#endif
case Opt_noacl:
info->sb->s_flags &= ~MS_POSIXACL;
break;
case Opt_notreelog:
btrfs_set_and_info(info, NOTREELOG,
"disabling tree log");
break;
case Opt_treelog:
btrfs_clear_and_info(info, NOTREELOG,
"enabling tree log");
break;
case Opt_norecovery:
case Opt_nologreplay:
btrfs_set_and_info(info, NOLOGREPLAY,
"disabling log replay at mount time");
break;
case Opt_flushoncommit:
btrfs_set_and_info(info, FLUSHONCOMMIT,
"turning on flush-on-commit");
break;
case Opt_noflushoncommit:
btrfs_clear_and_info(info, FLUSHONCOMMIT,
"turning off flush-on-commit");
break;
case Opt_ratio:
ret = match_int(&args[0], &intarg);
if (ret) {
goto out;
} else if (intarg >= 0) {
info->metadata_ratio = intarg;
btrfs_info(info, "metadata ratio %d",
info->metadata_ratio);
} else {
ret = -EINVAL;
goto out;
}
break;
case Opt_discard:
btrfs_set_and_info(info, DISCARD,
"turning on discard");
break;
case Opt_nodiscard:
btrfs_clear_and_info(info, DISCARD,
"turning off discard");
break;
case Opt_space_cache:
case Opt_space_cache_version:
if (token == Opt_space_cache ||
strcmp(args[0].from, "v1") == 0) {
btrfs_clear_opt(info->mount_opt,
FREE_SPACE_TREE);
btrfs_set_and_info(info, SPACE_CACHE,
"enabling disk space caching");
} else if (strcmp(args[0].from, "v2") == 0) {
btrfs_clear_opt(info->mount_opt,
SPACE_CACHE);
btrfs_set_and_info(info, FREE_SPACE_TREE,
"enabling free space tree");
} else {
ret = -EINVAL;
goto out;
}
break;
case Opt_rescan_uuid_tree:
btrfs_set_opt(info->mount_opt, RESCAN_UUID_TREE);
break;
case Opt_no_space_cache:
if (btrfs_test_opt(info, SPACE_CACHE)) {
btrfs_clear_and_info(info, SPACE_CACHE,
"disabling disk space caching");
}
if (btrfs_test_opt(info, FREE_SPACE_TREE)) {
btrfs_clear_and_info(info, FREE_SPACE_TREE,
"disabling free space tree");
}
break;
case Opt_inode_cache:
btrfs_set_pending_and_info(info, INODE_MAP_CACHE,
"enabling inode map caching");
break;
case Opt_noinode_cache:
btrfs_clear_pending_and_info(info, INODE_MAP_CACHE,
"disabling inode map caching");
break;
case Opt_clear_cache:
btrfs_set_and_info(info, CLEAR_CACHE,
"force clearing of disk cache");
break;
case Opt_user_subvol_rm_allowed:
btrfs_set_opt(info->mount_opt, USER_SUBVOL_RM_ALLOWED);
break;
case Opt_enospc_debug:
btrfs_set_opt(info->mount_opt, ENOSPC_DEBUG);
break;
case Opt_noenospc_debug:
btrfs_clear_opt(info->mount_opt, ENOSPC_DEBUG);
break;
case Opt_defrag:
btrfs_set_and_info(info, AUTO_DEFRAG,
"enabling auto defrag");
break;
case Opt_nodefrag:
btrfs_clear_and_info(info, AUTO_DEFRAG,
"disabling auto defrag");
break;
case Opt_recovery:
btrfs_warn(info,
"'recovery' is deprecated, use 'usebackuproot' instead");
case Opt_usebackuproot:
btrfs_info(info,
"trying to use backup root at mount time");
btrfs_set_opt(info->mount_opt, USEBACKUPROOT);
break;
case Opt_skip_balance:
btrfs_set_opt(info->mount_opt, SKIP_BALANCE);
break;
#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
case Opt_check_integrity_including_extent_data:
btrfs_info(info,
"enabling check integrity including extent data");
btrfs_set_opt(info->mount_opt,
CHECK_INTEGRITY_INCLUDING_EXTENT_DATA);
btrfs_set_opt(info->mount_opt, CHECK_INTEGRITY);
break;
case Opt_check_integrity:
btrfs_info(info, "enabling check integrity");
btrfs_set_opt(info->mount_opt, CHECK_INTEGRITY);
break;
case Opt_check_integrity_print_mask:
ret = match_int(&args[0], &intarg);
if (ret) {
goto out;
} else if (intarg >= 0) {
info->check_integrity_print_mask = intarg;
btrfs_info(info,
"check_integrity_print_mask 0x%x",
info->check_integrity_print_mask);
} else {
ret = -EINVAL;
goto out;
}
break;
#else
case Opt_check_integrity_including_extent_data:
case Opt_check_integrity:
case Opt_check_integrity_print_mask:
btrfs_err(info,
"support for check_integrity* not compiled in!");
ret = -EINVAL;
goto out;
#endif
case Opt_fatal_errors:
if (strcmp(args[0].from, "panic") == 0)
btrfs_set_opt(info->mount_opt,
PANIC_ON_FATAL_ERROR);
else if (strcmp(args[0].from, "bug") == 0)
btrfs_clear_opt(info->mount_opt,
PANIC_ON_FATAL_ERROR);
else {
ret = -EINVAL;
goto out;
}
break;
case Opt_commit_interval:
intarg = 0;
ret = match_int(&args[0], &intarg);
if (ret < 0) {
btrfs_err(info, "invalid commit interval");
ret = -EINVAL;
goto out;
}
if (intarg > 0) {
if (intarg > 300) {
btrfs_warn(info,
"excessive commit interval %d",
intarg);
}
info->commit_interval = intarg;
} else {
btrfs_info(info,
"using default commit interval %ds",
BTRFS_DEFAULT_COMMIT_INTERVAL);
info->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL;
}
break;
#ifdef CONFIG_BTRFS_DEBUG
case Opt_fragment_all:
btrfs_info(info, "fragmenting all space");
btrfs_set_opt(info->mount_opt, FRAGMENT_DATA);
btrfs_set_opt(info->mount_opt, FRAGMENT_METADATA);
break;
case Opt_fragment_metadata:
btrfs_info(info, "fragmenting metadata");
btrfs_set_opt(info->mount_opt,
FRAGMENT_METADATA);
break;
case Opt_fragment_data:
btrfs_info(info, "fragmenting data");
btrfs_set_opt(info->mount_opt, FRAGMENT_DATA);
break;
#endif
case Opt_err:
btrfs_info(info, "unrecognized mount option '%s'", p);
ret = -EINVAL;
goto out;
default:
break;
}
}
check:
/*
* Extra check for current option against current flag
*/
if (btrfs_test_opt(info, NOLOGREPLAY) && !(new_flags & MS_RDONLY)) {
btrfs_err(info,
"nologreplay must be used with ro mount option");
ret = -EINVAL;
}
out:
if (btrfs_fs_compat_ro(info, FREE_SPACE_TREE) &&
!btrfs_test_opt(info, FREE_SPACE_TREE) &&
!btrfs_test_opt(info, CLEAR_CACHE)) {
btrfs_err(info, "cannot disable free space tree");
ret = -EINVAL;
}
if (!ret && btrfs_test_opt(info, SPACE_CACHE))
btrfs_info(info, "disk space caching is enabled");
if (!ret && btrfs_test_opt(info, FREE_SPACE_TREE))
btrfs_info(info, "using free space tree");
kfree(orig);
return ret;
}
/*
* Parse mount options that are required early in the mount process.
*
* All other options will be parsed on much later in the mount process and
* only when we need to allocate a new super block.
*/
static int btrfs_parse_early_options(const char *options, fmode_t flags,
void *holder, char **subvol_name, u64 *subvol_objectid,
struct btrfs_fs_devices **fs_devices)
{
substring_t args[MAX_OPT_ARGS];
char *device_name, *opts, *orig, *p;
char *num = NULL;
int error = 0;
if (!options)
return 0;
/*
* strsep changes the string, duplicate it because parse_options
* gets called twice
*/
opts = kstrdup(options, GFP_KERNEL);
if (!opts)
return -ENOMEM;
orig = opts;
while ((p = strsep(&opts, ",")) != NULL) {
int token;
if (!*p)
continue;
token = match_token(p, tokens, args);
switch (token) {
case Opt_subvol:
kfree(*subvol_name);
*subvol_name = match_strdup(&args[0]);
if (!*subvol_name) {
error = -ENOMEM;
goto out;
}
break;
case Opt_subvolid:
num = match_strdup(&args[0]);
if (num) {
*subvol_objectid = memparse(num, NULL);
kfree(num);
/* we want the original fs_tree */
if (!*subvol_objectid)
*subvol_objectid =
BTRFS_FS_TREE_OBJECTID;
} else {
error = -EINVAL;
goto out;
}
break;
case Opt_subvolrootid:
pr_warn("BTRFS: 'subvolrootid' mount option is deprecated and has no effect\n");
break;
case Opt_device:
device_name = match_strdup(&args[0]);
if (!device_name) {
error = -ENOMEM;
goto out;
}
error = btrfs_scan_one_device(device_name,
flags, holder, fs_devices);
kfree(device_name);
if (error)
goto out;
break;
default:
break;
}
}
out:
kfree(orig);
return error;
}
static char *get_subvol_name_from_objectid(struct btrfs_fs_info *fs_info,
u64 subvol_objectid)
{
struct btrfs_root *root = fs_info->tree_root;
struct btrfs_root *fs_root;
struct btrfs_root_ref *root_ref;
struct btrfs_inode_ref *inode_ref;
struct btrfs_key key;
struct btrfs_path *path = NULL;
char *name = NULL, *ptr;
u64 dirid;
int len;
int ret;
path = btrfs_alloc_path();
if (!path) {
ret = -ENOMEM;
goto err;
}
path->leave_spinning = 1;
name = kmalloc(PATH_MAX, GFP_KERNEL);
if (!name) {
ret = -ENOMEM;
goto err;
}
ptr = name + PATH_MAX - 1;
ptr[0] = '\0';
/*
* Walk up the subvolume trees in the tree of tree roots by root
* backrefs until we hit the top-level subvolume.
*/
while (subvol_objectid != BTRFS_FS_TREE_OBJECTID) {
key.objectid = subvol_objectid;
key.type = BTRFS_ROOT_BACKREF_KEY;
key.offset = (u64)-1;
ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
if (ret < 0) {
goto err;
} else if (ret > 0) {
ret = btrfs_previous_item(root, path, subvol_objectid,
BTRFS_ROOT_BACKREF_KEY);
if (ret < 0) {
goto err;
} else if (ret > 0) {
ret = -ENOENT;
goto err;
}
}
btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
subvol_objectid = key.offset;
root_ref = btrfs_item_ptr(path->nodes[0], path->slots[0],
struct btrfs_root_ref);
len = btrfs_root_ref_name_len(path->nodes[0], root_ref);
ptr -= len + 1;
if (ptr < name) {
ret = -ENAMETOOLONG;
goto err;
}
read_extent_buffer(path->nodes[0], ptr + 1,
(unsigned long)(root_ref + 1), len);
ptr[0] = '/';
dirid = btrfs_root_ref_dirid(path->nodes[0], root_ref);
btrfs_release_path(path);
key.objectid = subvol_objectid;
key.type = BTRFS_ROOT_ITEM_KEY;
key.offset = (u64)-1;
fs_root = btrfs_read_fs_root_no_name(fs_info, &key);
if (IS_ERR(fs_root)) {
ret = PTR_ERR(fs_root);
goto err;
}
/*
* Walk up the filesystem tree by inode refs until we hit the
* root directory.
*/
while (dirid != BTRFS_FIRST_FREE_OBJECTID) {
key.objectid = dirid;
key.type = BTRFS_INODE_REF_KEY;
key.offset = (u64)-1;
ret = btrfs_search_slot(NULL, fs_root, &key, path, 0, 0);
if (ret < 0) {
goto err;
} else if (ret > 0) {
ret = btrfs_previous_item(fs_root, path, dirid,
BTRFS_INODE_REF_KEY);
if (ret < 0) {
goto err;
} else if (ret > 0) {
ret = -ENOENT;
goto err;
}
}
btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
dirid = key.offset;
inode_ref = btrfs_item_ptr(path->nodes[0],
path->slots[0],
struct btrfs_inode_ref);
len = btrfs_inode_ref_name_len(path->nodes[0],
inode_ref);
ptr -= len + 1;
if (ptr < name) {
ret = -ENAMETOOLONG;
goto err;
}
read_extent_buffer(path->nodes[0], ptr + 1,
(unsigned long)(inode_ref + 1), len);
ptr[0] = '/';
btrfs_release_path(path);
}
}
btrfs_free_path(path);
if (ptr == name + PATH_MAX - 1) {
name[0] = '/';
name[1] = '\0';
} else {
memmove(name, ptr, name + PATH_MAX - ptr);
}
return name;
err:
btrfs_free_path(path);
kfree(name);
return ERR_PTR(ret);
}
static int get_default_subvol_objectid(struct btrfs_fs_info *fs_info, u64 *objectid)
{
struct btrfs_root *root = fs_info->tree_root;
struct btrfs_dir_item *di;
struct btrfs_path *path;
struct btrfs_key location;
u64 dir_id;
path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
path->leave_spinning = 1;
/*
* Find the "default" dir item which points to the root item that we
* will mount by default if we haven't been given a specific subvolume
* to mount.
*/
dir_id = btrfs_super_root_dir(fs_info->super_copy);
di = btrfs_lookup_dir_item(NULL, root, path, dir_id, "default", 7, 0);
if (IS_ERR(di)) {
btrfs_free_path(path);
return PTR_ERR(di);
}
if (!di) {
/*
* Ok the default dir item isn't there. This is weird since
* it's always been there, but don't freak out, just try and
* mount the top-level subvolume.
*/
btrfs_free_path(path);
*objectid = BTRFS_FS_TREE_OBJECTID;
return 0;
}
btrfs_dir_item_key_to_cpu(path->nodes[0], di, &location);
btrfs_free_path(path);
*objectid = location.objectid;
return 0;
}
static int btrfs_fill_super(struct super_block *sb,
struct btrfs_fs_devices *fs_devices,
void *data)
{
struct inode *inode;
struct btrfs_fs_info *fs_info = btrfs_sb(sb);
struct btrfs_key key;
int err;
sb->s_maxbytes = MAX_LFS_FILESIZE;
sb->s_magic = BTRFS_SUPER_MAGIC;
sb->s_op = &btrfs_super_ops;
sb->s_d_op = &btrfs_dentry_operations;
sb->s_export_op = &btrfs_export_ops;
sb->s_xattr = btrfs_xattr_handlers;
sb->s_time_gran = 1;
#ifdef CONFIG_BTRFS_FS_POSIX_ACL
sb->s_flags |= MS_POSIXACL;
#endif
sb->s_flags |= MS_I_VERSION;
sb->s_iflags |= SB_I_CGROUPWB;
err = super_setup_bdi(sb);
if (err) {
btrfs_err(fs_info, "super_setup_bdi failed");
return err;
}
err = open_ctree(sb, fs_devices, (char *)data);
if (err) {
btrfs_err(fs_info, "open_ctree failed");
return err;
}
key.objectid = BTRFS_FIRST_FREE_OBJECTID;
key.type = BTRFS_INODE_ITEM_KEY;
key.offset = 0;
inode = btrfs_iget(sb, &key, fs_info->fs_root, NULL);
if (IS_ERR(inode)) {
err = PTR_ERR(inode);
goto fail_close;
}
sb->s_root = d_make_root(inode);
if (!sb->s_root) {
err = -ENOMEM;
goto fail_close;
}
cleancache_init_fs(sb);
sb->s_flags |= MS_ACTIVE;
return 0;
fail_close:
close_ctree(fs_info);
return err;
}
int btrfs_sync_fs(struct super_block *sb, int wait)
{
struct btrfs_trans_handle *trans;
struct btrfs_fs_info *fs_info = btrfs_sb(sb);
struct btrfs_root *root = fs_info->tree_root;
trace_btrfs_sync_fs(fs_info, wait);
if (!wait) {
filemap_flush(fs_info->btree_inode->i_mapping);
return 0;
}
btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1);
trans = btrfs_attach_transaction_barrier(root);
if (IS_ERR(trans)) {
/* no transaction, don't bother */
if (PTR_ERR(trans) == -ENOENT) {
/*
* Exit unless we have some pending changes
* that need to go through commit
*/
if (fs_info->pending_changes == 0)
return 0;
/*
* A non-blocking test if the fs is frozen. We must not
* start a new transaction here otherwise a deadlock
* happens. The pending operations are delayed to the
* next commit after thawing.
*/
if (__sb_start_write(sb, SB_FREEZE_WRITE, false))
__sb_end_write(sb, SB_FREEZE_WRITE);
else
return 0;
trans = btrfs_start_transaction(root, 0);
}
if (IS_ERR(trans))
return PTR_ERR(trans);
}
return btrfs_commit_transaction(trans);
}
static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
{
struct btrfs_fs_info *info = btrfs_sb(dentry->d_sb);
char *compress_type;
if (btrfs_test_opt(info, DEGRADED))
seq_puts(seq, ",degraded");
if (btrfs_test_opt(info, NODATASUM))
seq_puts(seq, ",nodatasum");
if (btrfs_test_opt(info, NODATACOW))
seq_puts(seq, ",nodatacow");
if (btrfs_test_opt(info, NOBARRIER))
seq_puts(seq, ",nobarrier");
if (info->max_inline != BTRFS_DEFAULT_MAX_INLINE)
seq_printf(seq, ",max_inline=%llu", info->max_inline);
if (info->thread_pool_size != min_t(unsigned long,
num_online_cpus() + 2, 8))
seq_printf(seq, ",thread_pool=%d", info->thread_pool_size);
if (btrfs_test_opt(info, COMPRESS)) {
if (info->compress_type == BTRFS_COMPRESS_ZLIB)
compress_type = "zlib";
else
compress_type = "lzo";
if (btrfs_test_opt(info, FORCE_COMPRESS))
seq_printf(seq, ",compress-force=%s", compress_type);
else
seq_printf(seq, ",compress=%s", compress_type);
}
if (btrfs_test_opt(info, NOSSD))
seq_puts(seq, ",nossd");
if (btrfs_test_opt(info, SSD_SPREAD))
seq_puts(seq, ",ssd_spread");
else if (btrfs_test_opt(info, SSD))
seq_puts(seq, ",ssd");
if (btrfs_test_opt(info, NOTREELOG))
seq_puts(seq, ",notreelog");
if (btrfs_test_opt(info, NOLOGREPLAY))
seq_puts(seq, ",nologreplay");
if (btrfs_test_opt(info, FLUSHONCOMMIT))
seq_puts(seq, ",flushoncommit");
if (btrfs_test_opt(info, DISCARD))
seq_puts(seq, ",discard");
if (!(info->sb->s_flags & MS_POSIXACL))
seq_puts(seq, ",noacl");
if (btrfs_test_opt(info, SPACE_CACHE))
seq_puts(seq, ",space_cache");
else if (btrfs_test_opt(info, FREE_SPACE_TREE))
seq_puts(seq, ",space_cache=v2");
else
seq_puts(seq, ",nospace_cache");
if (btrfs_test_opt(info, RESCAN_UUID_TREE))
seq_puts(seq, ",rescan_uuid_tree");
if (btrfs_test_opt(info, CLEAR_CACHE))
seq_puts(seq, ",clear_cache");
if (btrfs_test_opt(info, USER_SUBVOL_RM_ALLOWED))
seq_puts(seq, ",user_subvol_rm_allowed");
if (btrfs_test_opt(info, ENOSPC_DEBUG))
seq_puts(seq, ",enospc_debug");
if (btrfs_test_opt(info, AUTO_DEFRAG))
seq_puts(seq, ",autodefrag");
if (btrfs_test_opt(info, INODE_MAP_CACHE))
seq_puts(seq, ",inode_cache");
if (btrfs_test_opt(info, SKIP_BALANCE))
seq_puts(seq, ",skip_balance");
#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
if (btrfs_test_opt(info, CHECK_INTEGRITY_INCLUDING_EXTENT_DATA))
seq_puts(seq, ",check_int_data");
else if (btrfs_test_opt(info, CHECK_INTEGRITY))
seq_puts(seq, ",check_int");
if (info->check_integrity_print_mask)
seq_printf(seq, ",check_int_print_mask=%d",
info->check_integrity_print_mask);
#endif
if (info->metadata_ratio)
seq_printf(seq, ",metadata_ratio=%d",
info->metadata_ratio);
if (btrfs_test_opt(info, PANIC_ON_FATAL_ERROR))
seq_puts(seq, ",fatal_errors=panic");
if (info->commit_interval != BTRFS_DEFAULT_COMMIT_INTERVAL)
seq_printf(seq, ",commit=%d", info->commit_interval);
#ifdef CONFIG_BTRFS_DEBUG
if (btrfs_test_opt(info, FRAGMENT_DATA))
seq_puts(seq, ",fragment=data");
if (btrfs_test_opt(info, FRAGMENT_METADATA))
seq_puts(seq, ",fragment=metadata");
#endif
seq_printf(seq, ",subvolid=%llu",
BTRFS_I(d_inode(dentry))->root->root_key.objectid);
seq_puts(seq, ",subvol=");
seq_dentry(seq, dentry, " \t\n\\");
return 0;
}
static int btrfs_test_super(struct super_block *s, void *data)
{
struct btrfs_fs_info *p = data;
struct btrfs_fs_info *fs_info = btrfs_sb(s);
return fs_info->fs_devices == p->fs_devices;
}
static int btrfs_set_super(struct super_block *s, void *data)
{
int err = set_anon_super(s, data);
if (!err)
s->s_fs_info = data;
return err;
}
/*
* subvolumes are identified by ino 256
*/
static inline int is_subvolume_inode(struct inode *inode)
{
if (inode && inode->i_ino == BTRFS_FIRST_FREE_OBJECTID)
return 1;
return 0;
}
/*
* This will add subvolid=0 to the argument string while removing any subvol=
* and subvolid= arguments to make sure we get the top-level root for path
* walking to the subvol we want.
*/
static char *setup_root_args(char *args)
{
char *buf, *dst, *sep;
if (!args)
return kstrdup("subvolid=0", GFP_KERNEL);
/* The worst case is that we add ",subvolid=0" to the end. */
buf = dst = kmalloc(strlen(args) + strlen(",subvolid=0") + 1,
GFP_KERNEL);
if (!buf)
return NULL;
while (1) {
sep = strchrnul(args, ',');
if (!strstarts(args, "subvol=") &&
!strstarts(args, "subvolid=")) {
memcpy(dst, args, sep - args);
dst += sep - args;
*dst++ = ',';
}
if (*sep)
args = sep + 1;
else
break;
}
strcpy(dst, "subvolid=0");
return buf;
}
static struct dentry *mount_subvol(const char *subvol_name, u64 subvol_objectid,
int flags, const char *device_name,
char *data)
{
struct dentry *root;
struct vfsmount *mnt = NULL;
char *newargs;
int ret;
newargs = setup_root_args(data);
if (!newargs) {
root = ERR_PTR(-ENOMEM);
goto out;
}
mnt = vfs_kern_mount(&btrfs_fs_type, flags, device_name, newargs);
if (PTR_ERR_OR_ZERO(mnt) == -EBUSY) {
if (flags & MS_RDONLY) {
mnt = vfs_kern_mount(&btrfs_fs_type, flags & ~MS_RDONLY,
device_name, newargs);
} else {
mnt = vfs_kern_mount(&btrfs_fs_type, flags | MS_RDONLY,
device_name, newargs);
if (IS_ERR(mnt)) {
root = ERR_CAST(mnt);
mnt = NULL;
goto out;
}
down_write(&mnt->mnt_sb->s_umount);
ret = btrfs_remount(mnt->mnt_sb, &flags, NULL);
up_write(&mnt->mnt_sb->s_umount);
if (ret < 0) {
root = ERR_PTR(ret);
goto out;
}
}
}
if (IS_ERR(mnt)) {
root = ERR_CAST(mnt);
mnt = NULL;
goto out;
}
if (!subvol_name) {
if (!subvol_objectid) {
ret = get_default_subvol_objectid(btrfs_sb(mnt->mnt_sb),
&subvol_objectid);
if (ret) {
root = ERR_PTR(ret);
goto out;
}
}
subvol_name = get_subvol_name_from_objectid(btrfs_sb(mnt->mnt_sb),
subvol_objectid);
if (IS_ERR(subvol_name)) {
root = ERR_CAST(subvol_name);
subvol_name = NULL;
goto out;
}
}
root = mount_subtree(mnt, subvol_name);
/* mount_subtree() drops our reference on the vfsmount. */
mnt = NULL;
if (!IS_ERR(root)) {
struct super_block *s = root->d_sb;
struct btrfs_fs_info *fs_info = btrfs_sb(s);
struct inode *root_inode = d_inode(root);
u64 root_objectid = BTRFS_I(root_inode)->root->root_key.objectid;
ret = 0;
if (!is_subvolume_inode(root_inode)) {
btrfs_err(fs_info, "'%s' is not a valid subvolume",
subvol_name);
ret = -EINVAL;
}
if (subvol_objectid && root_objectid != subvol_objectid) {
/*
* This will also catch a race condition where a
* subvolume which was passed by ID is renamed and
* another subvolume is renamed over the old location.
*/
btrfs_err(fs_info,
"subvol '%s' does not match subvolid %llu",
subvol_name, subvol_objectid);
ret = -EINVAL;
}
if (ret) {
dput(root);
root = ERR_PTR(ret);
deactivate_locked_super(s);
}
}
out:
mntput(mnt);
kfree(newargs);
kfree(subvol_name);
return root;
}
static int parse_security_options(char *orig_opts,
struct security_mnt_opts *sec_opts)
{
char *secdata = NULL;
int ret = 0;
secdata = alloc_secdata();
if (!secdata)
return -ENOMEM;
ret = security_sb_copy_data(orig_opts, secdata);
if (ret) {
free_secdata(secdata);
return ret;
}
ret = security_sb_parse_opts_str(secdata, sec_opts);
free_secdata(secdata);
return ret;
}
static int setup_security_options(struct btrfs_fs_info *fs_info,
struct super_block *sb,
struct security_mnt_opts *sec_opts)
{
int ret = 0;
/*
* Call security_sb_set_mnt_opts() to check whether new sec_opts
* is valid.
*/
ret = security_sb_set_mnt_opts(sb, sec_opts, 0, NULL);
if (ret)
return ret;
#ifdef CONFIG_SECURITY
if (!fs_info->security_opts.num_mnt_opts) {
/* first time security setup, copy sec_opts to fs_info */
memcpy(&fs_info->security_opts, sec_opts, sizeof(*sec_opts));
} else {
/*
* Since SELinux (the only one supporting security_mnt_opts)
* does NOT support changing context during remount/mount of
* the same sb, this must be the same or part of the same
* security options, just free it.
*/
security_free_mnt_opts(sec_opts);
}
#endif
return ret;
}
/*
* Find a superblock for the given device / mount point.
*
* Note: This is based on get_sb_bdev from fs/super.c with a few additions
* for multiple device setup. Make sure to keep it in sync.
*/
static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
const char *device_name, void *data)
{
struct block_device *bdev = NULL;
struct super_block *s;
struct btrfs_fs_devices *fs_devices = NULL;
struct btrfs_fs_info *fs_info = NULL;
struct security_mnt_opts new_sec_opts;
fmode_t mode = FMODE_READ;
char *subvol_name = NULL;
u64 subvol_objectid = 0;
int error = 0;
if (!(flags & MS_RDONLY))
mode |= FMODE_WRITE;
error = btrfs_parse_early_options(data, mode, fs_type,
&subvol_name, &subvol_objectid,
&fs_devices);
if (error) {
kfree(subvol_name);
return ERR_PTR(error);
}
if (subvol_name || subvol_objectid != BTRFS_FS_TREE_OBJECTID) {
/* mount_subvol() will free subvol_name. */
return mount_subvol(subvol_name, subvol_objectid, flags,
device_name, data);
}
security_init_mnt_opts(&new_sec_opts);
if (data) {
error = parse_security_options(data, &new_sec_opts);
if (error)
return ERR_PTR(error);
}
error = btrfs_scan_one_device(device_name, mode, fs_type, &fs_devices);
if (error)
goto error_sec_opts;
/*
* Setup a dummy root and fs_info for test/set super. This is because
* we don't actually fill this stuff out until open_ctree, but we need
* it for searching for existing supers, so this lets us do that and
* then open_ctree will properly initialize everything later.
*/
fs_info = kzalloc(sizeof(struct btrfs_fs_info), GFP_KERNEL);
if (!fs_info) {
error = -ENOMEM;
goto error_sec_opts;
}
fs_info->fs_devices = fs_devices;
fs_info->super_copy = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_KERNEL);
fs_info->super_for_commit = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_KERNEL);
security_init_mnt_opts(&fs_info->security_opts);
if (!fs_info->super_copy || !fs_info->super_for_commit) {
error = -ENOMEM;
goto error_fs_info;
}
error = btrfs_open_devices(fs_devices, mode, fs_type);
if (error)
goto error_fs_info;
if (!(flags & MS_RDONLY) && fs_devices->rw_devices == 0) {
error = -EACCES;
goto error_close_devices;
}
bdev = fs_devices->latest_bdev;
s = sget(fs_type, btrfs_test_super, btrfs_set_super, flags | MS_NOSEC,
fs_info);
if (IS_ERR(s)) {
error = PTR_ERR(s);
goto error_close_devices;
}
if (s->s_root) {
btrfs_close_devices(fs_devices);
free_fs_info(fs_info);
if ((flags ^ s->s_flags) & MS_RDONLY)
error = -EBUSY;
} else {
snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev);
btrfs_sb(s)->bdev_holder = fs_type;
error = btrfs_fill_super(s, fs_devices, data);
}
if (error) {
deactivate_locked_super(s);
goto error_sec_opts;
}
fs_info = btrfs_sb(s);
error = setup_security_options(fs_info, s, &new_sec_opts);
if (error) {
deactivate_locked_super(s);
goto error_sec_opts;
}
return dget(s->s_root);
error_close_devices:
btrfs_close_devices(fs_devices);
error_fs_info:
free_fs_info(fs_info);
error_sec_opts:
security_free_mnt_opts(&new_sec_opts);
return ERR_PTR(error);
}
static void btrfs_resize_thread_pool(struct btrfs_fs_info *fs_info,
int new_pool_size, int old_pool_size)
{
if (new_pool_size == old_pool_size)
return;
fs_info->thread_pool_size = new_pool_size;
btrfs_info(fs_info, "resize thread pool %d -> %d",
old_pool_size, new_pool_size);
btrfs_workqueue_set_max(fs_info->workers, new_pool_size);
btrfs_workqueue_set_max(fs_info->delalloc_workers, new_pool_size);
btrfs_workqueue_set_max(fs_info->submit_workers, new_pool_size);
btrfs_workqueue_set_max(fs_info->caching_workers, new_pool_size);
btrfs_workqueue_set_max(fs_info->endio_workers, new_pool_size);
btrfs_workqueue_set_max(fs_info->endio_meta_workers, new_pool_size);
btrfs_workqueue_set_max(fs_info->endio_meta_write_workers,
new_pool_size);
btrfs_workqueue_set_max(fs_info->endio_write_workers, new_pool_size);
btrfs_workqueue_set_max(fs_info->endio_freespace_worker, new_pool_size);
btrfs_workqueue_set_max(fs_info->delayed_workers, new_pool_size);
btrfs_workqueue_set_max(fs_info->readahead_workers, new_pool_size);
btrfs_workqueue_set_max(fs_info->scrub_wr_completion_workers,
new_pool_size);
}
static inline void btrfs_remount_prepare(struct btrfs_fs_info *fs_info)
{
set_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state);
}
static inline void btrfs_remount_begin(struct btrfs_fs_info *fs_info,
unsigned long old_opts, int flags)
{
if (btrfs_raw_test_opt(old_opts, AUTO_DEFRAG) &&
(!btrfs_raw_test_opt(fs_info->mount_opt, AUTO_DEFRAG) ||
(flags & MS_RDONLY))) {
/* wait for any defraggers to finish */
wait_event(fs_info->transaction_wait,
(atomic_read(&fs_info->defrag_running) == 0));
if (flags & MS_RDONLY)
sync_filesystem(fs_info->sb);
}
}
static inline void btrfs_remount_cleanup(struct btrfs_fs_info *fs_info,
unsigned long old_opts)
{
/*
* We need to cleanup all defragable inodes if the autodefragment is
* close or the filesystem is read only.
*/
if (btrfs_raw_test_opt(old_opts, AUTO_DEFRAG) &&
(!btrfs_raw_test_opt(fs_info->mount_opt, AUTO_DEFRAG) ||
(fs_info->sb->s_flags & MS_RDONLY))) {
btrfs_cleanup_defrag_inodes(fs_info);
}
clear_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state);
}
static int btrfs_remount(struct super_block *sb, int *flags, char *data)
{
struct btrfs_fs_info *fs_info = btrfs_sb(sb);
struct btrfs_root *root = fs_info->tree_root;
unsigned old_flags = sb->s_flags;
unsigned long old_opts = fs_info->mount_opt;
unsigned long old_compress_type = fs_info->compress_type;
u64 old_max_inline = fs_info->max_inline;
int old_thread_pool_size = fs_info->thread_pool_size;
unsigned int old_metadata_ratio = fs_info->metadata_ratio;
int ret;
sync_filesystem(sb);
btrfs_remount_prepare(fs_info);
if (data) {
struct security_mnt_opts new_sec_opts;
security_init_mnt_opts(&new_sec_opts);
ret = parse_security_options(data, &new_sec_opts);
if (ret)
goto restore;
ret = setup_security_options(fs_info, sb,
&new_sec_opts);
if (ret) {
security_free_mnt_opts(&new_sec_opts);
goto restore;
}
}
ret = btrfs_parse_options(fs_info, data, *flags);
if (ret) {
ret = -EINVAL;
goto restore;
}
btrfs_remount_begin(fs_info, old_opts, *flags);
btrfs_resize_thread_pool(fs_info,
fs_info->thread_pool_size, old_thread_pool_size);
if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY))
goto out;
if (*flags & MS_RDONLY) {
/*
* this also happens on 'umount -rf' or on shutdown, when
* the filesystem is busy.
*/
cancel_work_sync(&fs_info->async_reclaim_work);
/* wait for the uuid_scan task to finish */
down(&fs_info->uuid_tree_rescan_sem);
/* avoid complains from lockdep et al. */
up(&fs_info->uuid_tree_rescan_sem);
sb->s_flags |= MS_RDONLY;
/*
* Setting MS_RDONLY will put the cleaner thread to
* sleep at the next loop if it's already active.
* If it's already asleep, we'll leave unused block
* groups on disk until we're mounted read-write again
* unless we clean them up here.
*/
btrfs_delete_unused_bgs(fs_info);
btrfs_dev_replace_suspend_for_unmount(fs_info);
btrfs_scrub_cancel(fs_info);
btrfs_pause_balance(fs_info);
ret = btrfs_commit_super(fs_info);
if (ret)
goto restore;
} else {
if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) {
btrfs_err(fs_info,
"Remounting read-write after error is not allowed");
ret = -EINVAL;
goto restore;
}
if (fs_info->fs_devices->rw_devices == 0) {
ret = -EACCES;
goto restore;
}
if (!btrfs_check_rw_degradable(fs_info)) {
btrfs_warn(fs_info,
"too many missing devices, writeable remount is not allowed");
ret = -EACCES;
goto restore;
}
if (btrfs_super_log_root(fs_info->super_copy) != 0) {
ret = -EINVAL;
goto restore;
}
ret = btrfs_cleanup_fs_roots(fs_info);
if (ret)
goto restore;
/* recover relocation */
mutex_lock(&fs_info->cleaner_mutex);
ret = btrfs_recover_relocation(root);
mutex_unlock(&fs_info->cleaner_mutex);
if (ret)
goto restore;
ret = btrfs_resume_balance_async(fs_info);
if (ret)
goto restore;
ret = btrfs_resume_dev_replace_async(fs_info);
if (ret) {
btrfs_warn(fs_info, "failed to resume dev_replace");
goto restore;
}
btrfs_qgroup_rescan_resume(fs_info);
if (!fs_info->uuid_root) {
btrfs_info(fs_info, "creating UUID tree");
ret = btrfs_create_uuid_tree(fs_info);
if (ret) {
btrfs_warn(fs_info,
"failed to create the UUID tree %d",
ret);
goto restore;
}
}
sb->s_flags &= ~MS_RDONLY;
set_bit(BTRFS_FS_OPEN, &fs_info->flags);
}
out:
wake_up_process(fs_info->transaction_kthread);
btrfs_remount_cleanup(fs_info, old_opts);
return 0;
restore:
/* We've hit an error - don't reset MS_RDONLY */
if (sb->s_flags & MS_RDONLY)
old_flags |= MS_RDONLY;
sb->s_flags = old_flags;
fs_info->mount_opt = old_opts;
fs_info->compress_type = old_compress_type;
fs_info->max_inline = old_max_inline;
btrfs_resize_thread_pool(fs_info,
old_thread_pool_size, fs_info->thread_pool_size);
fs_info->metadata_ratio = old_metadata_ratio;
btrfs_remount_cleanup(fs_info, old_opts);
return ret;
}
/* Used to sort the devices by max_avail(descending sort) */
static int btrfs_cmp_device_free_bytes(const void *dev_info1,
const void *dev_info2)
{
if (((struct btrfs_device_info *)dev_info1)->max_avail >
((struct btrfs_device_info *)dev_info2)->max_avail)
return -1;
else if (((struct btrfs_device_info *)dev_info1)->max_avail <
((struct btrfs_device_info *)dev_info2)->max_avail)
return 1;
else
return 0;
}
/*
* sort the devices by max_avail, in which max free extent size of each device
* is stored.(Descending Sort)
*/
static inline void btrfs_descending_sort_devices(
struct btrfs_device_info *devices,
size_t nr_devices)
{
sort(devices, nr_devices, sizeof(struct btrfs_device_info),
btrfs_cmp_device_free_bytes, NULL);
}
/*
* The helper to calc the free space on the devices that can be used to store
* file data.
*/
static int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info,
u64 *free_bytes)
{
struct btrfs_device_info *devices_info;
struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
struct btrfs_device *device;
u64 skip_space;
u64 type;
u64 avail_space;
u64 min_stripe_size;
int min_stripes = 1, num_stripes = 1;
int i = 0, nr_devices;
/*
* We aren't under the device list lock, so this is racy-ish, but good
* enough for our purposes.
*/
nr_devices = fs_info->fs_devices->open_devices;
if (!nr_devices) {
smp_mb();
nr_devices = fs_info->fs_devices->open_devices;
ASSERT(nr_devices);
if (!nr_devices) {
*free_bytes = 0;
return 0;
}
}
devices_info = kmalloc_array(nr_devices, sizeof(*devices_info),
GFP_KERNEL);
if (!devices_info)
return -ENOMEM;
/* calc min stripe number for data space allocation */
type = btrfs_data_alloc_profile(fs_info);
if (type & BTRFS_BLOCK_GROUP_RAID0) {
min_stripes = 2;
num_stripes = nr_devices;
} else if (type & BTRFS_BLOCK_GROUP_RAID1) {
min_stripes = 2;
num_stripes = 2;
} else if (type & BTRFS_BLOCK_GROUP_RAID10) {
min_stripes = 4;
num_stripes = 4;
}
if (type & BTRFS_BLOCK_GROUP_DUP)
min_stripe_size = 2 * BTRFS_STRIPE_LEN;
else
min_stripe_size = BTRFS_STRIPE_LEN;
rcu_read_lock();
list_for_each_entry_rcu(device, &fs_devices->devices, dev_list) {
if (!device->in_fs_metadata || !device->bdev ||
device->is_tgtdev_for_dev_replace)
continue;
if (i >= nr_devices)
break;
avail_space = device->total_bytes - device->bytes_used;
/* align with stripe_len */
avail_space = div_u64(avail_space, BTRFS_STRIPE_LEN);
avail_space *= BTRFS_STRIPE_LEN;
/*
* In order to avoid overwriting the superblock on the drive,
* btrfs starts at an offset of at least 1MB when doing chunk
* allocation.
*/
skip_space = SZ_1M;
/*
* we can use the free space in [0, skip_space - 1], subtract
* it from the total.
*/
if (avail_space && avail_space >= skip_space)
avail_space -= skip_space;
else
avail_space = 0;
if (avail_space < min_stripe_size)
continue;
devices_info[i].dev = device;
devices_info[i].max_avail = avail_space;
i++;
}
rcu_read_unlock();
nr_devices = i;
btrfs_descending_sort_devices(devices_info, nr_devices);
i = nr_devices - 1;
avail_space = 0;
while (nr_devices >= min_stripes) {
if (num_stripes > nr_devices)
num_stripes = nr_devices;
if (devices_info[i].max_avail >= min_stripe_size) {
int j;
u64 alloc_size;
avail_space += devices_info[i].max_avail * num_stripes;
alloc_size = devices_info[i].max_avail;
for (j = i + 1 - num_stripes; j <= i; j++)
devices_info[j].max_avail -= alloc_size;
}
i--;
nr_devices--;
}
kfree(devices_info);
*free_bytes = avail_space;
return 0;
}
/*
* Calculate numbers for 'df', pessimistic in case of mixed raid profiles.
*
* If there's a redundant raid level at DATA block groups, use the respective
* multiplier to scale the sizes.
*
* Unused device space usage is based on simulating the chunk allocator
* algorithm that respects the device sizes and order of allocations. This is
* a close approximation of the actual use but there are other factors that may
* change the result (like a new metadata chunk).
*
* If metadata is exhausted, f_bavail will be 0.
*/
static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct btrfs_fs_info *fs_info = btrfs_sb(dentry->d_sb);
struct btrfs_super_block *disk_super = fs_info->super_copy;
struct list_head *head = &fs_info->space_info;
struct btrfs_space_info *found;
u64 total_used = 0;
u64 total_free_data = 0;
u64 total_free_meta = 0;
int bits = dentry->d_sb->s_blocksize_bits;
__be32 *fsid = (__be32 *)fs_info->fsid;
unsigned factor = 1;
struct btrfs_block_rsv *block_rsv = &fs_info->global_block_rsv;
int ret;
u64 thresh = 0;
int mixed = 0;
rcu_read_lock();
list_for_each_entry_rcu(found, head, list) {
if (found->flags & BTRFS_BLOCK_GROUP_DATA) {
int i;
total_free_data += found->disk_total - found->disk_used;
total_free_data -=
btrfs_account_ro_block_groups_free_space(found);
for (i = 0; i < BTRFS_NR_RAID_TYPES; i++) {
if (!list_empty(&found->block_groups[i])) {
switch (i) {
case BTRFS_RAID_DUP:
case BTRFS_RAID_RAID1:
case BTRFS_RAID_RAID10:
factor = 2;
}
}
}
}
/*
* Metadata in mixed block goup profiles are accounted in data
*/
if (!mixed && found->flags & BTRFS_BLOCK_GROUP_METADATA) {
if (found->flags & BTRFS_BLOCK_GROUP_DATA)
mixed = 1;
else
total_free_meta += found->disk_total -
found->disk_used;
}
total_used += found->disk_used;
}
rcu_read_unlock();
buf->f_blocks = div_u64(btrfs_super_total_bytes(disk_super), factor);
buf->f_blocks >>= bits;
buf->f_bfree = buf->f_blocks - (div_u64(total_used, factor) >> bits);
/* Account global block reserve as used, it's in logical size already */
spin_lock(&block_rsv->lock);
/* Mixed block groups accounting is not byte-accurate, avoid overflow */
if (buf->f_bfree >= block_rsv->size >> bits)
buf->f_bfree -= block_rsv->size >> bits;
else
buf->f_bfree = 0;
spin_unlock(&block_rsv->lock);
buf->f_bavail = div_u64(total_free_data, factor);
ret = btrfs_calc_avail_data_space(fs_info, &total_free_data);
if (ret)
return ret;
buf->f_bavail += div_u64(total_free_data, factor);
buf->f_bavail = buf->f_bavail >> bits;
/*
* We calculate the remaining metadata space minus global reserve. If
* this is (supposedly) smaller than zero, there's no space. But this
* does not hold in practice, the exhausted state happens where's still
* some positive delta. So we apply some guesswork and compare the
* delta to a 4M threshold. (Practically observed delta was ~2M.)
*
* We probably cannot calculate the exact threshold value because this
* depends on the internal reservations requested by various
* operations, so some operations that consume a few metadata will
* succeed even if the Avail is zero. But this is better than the other
* way around.
*/
thresh = 4 * 1024 * 1024;
if (!mixed && total_free_meta - thresh < block_rsv->size)
buf->f_bavail = 0;
buf->f_type = BTRFS_SUPER_MAGIC;
buf->f_bsize = dentry->d_sb->s_blocksize;
buf->f_namelen = BTRFS_NAME_LEN;
/* We treat it as constant endianness (it doesn't matter _which_)
because we want the fsid to come out the same whether mounted
on a big-endian or little-endian host */
buf->f_fsid.val[0] = be32_to_cpu(fsid[0]) ^ be32_to_cpu(fsid[2]);
buf->f_fsid.val[1] = be32_to_cpu(fsid[1]) ^ be32_to_cpu(fsid[3]);
/* Mask in the root object ID too, to disambiguate subvols */
buf->f_fsid.val[0] ^= BTRFS_I(d_inode(dentry))->root->objectid >> 32;
buf->f_fsid.val[1] ^= BTRFS_I(d_inode(dentry))->root->objectid;
return 0;
}
static void btrfs_kill_super(struct super_block *sb)
{
struct btrfs_fs_info *fs_info = btrfs_sb(sb);
kill_anon_super(sb);
free_fs_info(fs_info);
}
static struct file_system_type btrfs_fs_type = {
.owner = THIS_MODULE,
.name = "btrfs",
.mount = btrfs_mount,
.kill_sb = btrfs_kill_super,
.fs_flags = FS_REQUIRES_DEV | FS_BINARY_MOUNTDATA,
};
MODULE_ALIAS_FS("btrfs");
static int btrfs_control_open(struct inode *inode, struct file *file)
{
/*
* The control file's private_data is used to hold the
* transaction when it is started and is used to keep
* track of whether a transaction is already in progress.
*/
file->private_data = NULL;
return 0;
}
/*
* used by btrfsctl to scan devices when no FS is mounted
*/
static long btrfs_control_ioctl(struct file *file, unsigned int cmd,
unsigned long arg)
{
struct btrfs_ioctl_vol_args *vol;
struct btrfs_fs_devices *fs_devices;
int ret = -ENOTTY;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
vol = memdup_user((void __user *)arg, sizeof(*vol));
if (IS_ERR(vol))
return PTR_ERR(vol);
switch (cmd) {
case BTRFS_IOC_SCAN_DEV:
ret = btrfs_scan_one_device(vol->name, FMODE_READ,
&btrfs_fs_type, &fs_devices);
break;
case BTRFS_IOC_DEVICES_READY:
ret = btrfs_scan_one_device(vol->name, FMODE_READ,
&btrfs_fs_type, &fs_devices);
if (ret)
break;
ret = !(fs_devices->num_devices == fs_devices->total_devices);
break;
case BTRFS_IOC_GET_SUPPORTED_FEATURES:
ret = btrfs_ioctl_get_supported_features((void __user*)arg);
break;
}
kfree(vol);
return ret;
}
static int btrfs_freeze(struct super_block *sb)
{
struct btrfs_trans_handle *trans;
struct btrfs_fs_info *fs_info = btrfs_sb(sb);
struct btrfs_root *root = fs_info->tree_root;
set_bit(BTRFS_FS_FROZEN, &fs_info->flags);
/*
* We don't need a barrier here, we'll wait for any transaction that
* could be in progress on other threads (and do delayed iputs that
* we want to avoid on a frozen filesystem), or do the commit
* ourselves.
*/
trans = btrfs_attach_transaction_barrier(root);
if (IS_ERR(trans)) {
/* no transaction, don't bother */
if (PTR_ERR(trans) == -ENOENT)
return 0;
return PTR_ERR(trans);
}
return btrfs_commit_transaction(trans);
}
static int btrfs_unfreeze(struct super_block *sb)
{
struct btrfs_fs_info *fs_info = btrfs_sb(sb);
clear_bit(BTRFS_FS_FROZEN, &fs_info->flags);
return 0;
}
static int btrfs_show_devname(struct seq_file *m, struct dentry *root)
{
struct btrfs_fs_info *fs_info = btrfs_sb(root->d_sb);
struct btrfs_fs_devices *cur_devices;
struct btrfs_device *dev, *first_dev = NULL;
struct list_head *head;
struct rcu_string *name;
mutex_lock(&fs_info->fs_devices->device_list_mutex);
cur_devices = fs_info->fs_devices;
while (cur_devices) {
head = &cur_devices->devices;
list_for_each_entry(dev, head, dev_list) {
if (dev->missing)
continue;
if (!dev->name)
continue;
if (!first_dev || dev->devid < first_dev->devid)
first_dev = dev;
}
cur_devices = cur_devices->seed;
}
if (first_dev) {
rcu_read_lock();
name = rcu_dereference(first_dev->name);
seq_escape(m, name->str, " \t\n\\");
rcu_read_unlock();
} else {
WARN_ON(1);
}
mutex_unlock(&fs_info->fs_devices->device_list_mutex);
return 0;
}
static const struct super_operations btrfs_super_ops = {
.drop_inode = btrfs_drop_inode,
.evict_inode = btrfs_evict_inode,
.put_super = btrfs_put_super,
.sync_fs = btrfs_sync_fs,
.show_options = btrfs_show_options,
.show_devname = btrfs_show_devname,
.write_inode = btrfs_write_inode,
.alloc_inode = btrfs_alloc_inode,
.destroy_inode = btrfs_destroy_inode,
.statfs = btrfs_statfs,
.remount_fs = btrfs_remount,
.freeze_fs = btrfs_freeze,
.unfreeze_fs = btrfs_unfreeze,
};
static const struct file_operations btrfs_ctl_fops = {
.open = btrfs_control_open,
.unlocked_ioctl = btrfs_control_ioctl,
.compat_ioctl = btrfs_control_ioctl,
.owner = THIS_MODULE,
.llseek = noop_llseek,
};
static struct miscdevice btrfs_misc = {
.minor = BTRFS_MINOR,
.name = "btrfs-control",
.fops = &btrfs_ctl_fops
};
MODULE_ALIAS_MISCDEV(BTRFS_MINOR);
MODULE_ALIAS("devname:btrfs-control");
static int btrfs_interface_init(void)
{
return misc_register(&btrfs_misc);
}
static void btrfs_interface_exit(void)
{
misc_deregister(&btrfs_misc);
}
static void btrfs_print_mod_info(void)
{
pr_info("Btrfs loaded, crc32c=%s"
#ifdef CONFIG_BTRFS_DEBUG
", debug=on"
#endif
#ifdef CONFIG_BTRFS_ASSERT
", assert=on"
#endif
#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
", integrity-checker=on"
#endif
"\n",
btrfs_crc32c_impl());
}
static int __init init_btrfs_fs(void)
{
int err;
err = btrfs_hash_init();
if (err)
return err;
btrfs_props_init();
err = btrfs_init_sysfs();
if (err)
goto free_hash;
btrfs_init_compress();
err = btrfs_init_cachep();
if (err)
goto free_compress;
err = extent_io_init();
if (err)
goto free_cachep;
err = extent_map_init();
if (err)
goto free_extent_io;
err = ordered_data_init();
if (err)
goto free_extent_map;
err = btrfs_delayed_inode_init();
if (err)
goto free_ordered_data;
err = btrfs_auto_defrag_init();
if (err)
goto free_delayed_inode;
err = btrfs_delayed_ref_init();
if (err)
goto free_auto_defrag;
err = btrfs_prelim_ref_init();
if (err)
goto free_delayed_ref;
err = btrfs_end_io_wq_init();
if (err)
goto free_prelim_ref;
err = btrfs_interface_init();
if (err)
goto free_end_io_wq;
btrfs_init_lockdep();
btrfs_print_mod_info();
err = btrfs_run_sanity_tests();
if (err)
goto unregister_ioctl;
err = register_filesystem(&btrfs_fs_type);
if (err)
goto unregister_ioctl;
return 0;
unregister_ioctl:
btrfs_interface_exit();
free_end_io_wq:
btrfs_end_io_wq_exit();
free_prelim_ref:
btrfs_prelim_ref_exit();
free_delayed_ref:
btrfs_delayed_ref_exit();
free_auto_defrag:
btrfs_auto_defrag_exit();
free_delayed_inode:
btrfs_delayed_inode_exit();
free_ordered_data:
ordered_data_exit();
free_extent_map:
extent_map_exit();
free_extent_io:
extent_io_exit();
free_cachep:
btrfs_destroy_cachep();
free_compress:
btrfs_exit_compress();
btrfs_exit_sysfs();
free_hash:
btrfs_hash_exit();
return err;
}
static void __exit exit_btrfs_fs(void)
{
btrfs_destroy_cachep();
btrfs_delayed_ref_exit();
btrfs_auto_defrag_exit();
btrfs_delayed_inode_exit();
btrfs_prelim_ref_exit();
ordered_data_exit();
extent_map_exit();
extent_io_exit();
btrfs_interface_exit();
btrfs_end_io_wq_exit();
unregister_filesystem(&btrfs_fs_type);
btrfs_exit_sysfs();
btrfs_cleanup_fs_uuids();
btrfs_exit_compress();
btrfs_hash_exit();
}
late_initcall(init_btrfs_fs);
module_exit(exit_btrfs_fs)
MODULE_LICENSE("GPL");
Reference in a new issue View git blame Copy permalink