linux-stable/fs/btrfs/sysfs.c

1754 lines
46 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 2007 Oracle. All rights reserved.
*/
#include <linux/sched.h>
#include <linux/sched/mm.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/completion.h>
#include <linux/bug.h>
#include <crypto/hash.h>
#include "ctree.h"
#include "discard.h"
#include "disk-io.h"
#include "transaction.h"
#include "sysfs.h"
#include "volumes.h"
#include "space-info.h"
#include "block-group.h"
#include "qgroup.h"
struct btrfs_feature_attr {
struct kobj_attribute kobj_attr;
enum btrfs_feature_set feature_set;
u64 feature_bit;
};
/* For raid type sysfs entries */
struct raid_kobject {
u64 flags;
struct kobject kobj;
};
#define __INIT_KOBJ_ATTR(_name, _mode, _show, _store) \
{ \
.attr = { .name = __stringify(_name), .mode = _mode }, \
.show = _show, \
.store = _store, \
}
#define BTRFS_ATTR_RW(_prefix, _name, _show, _store) \
static struct kobj_attribute btrfs_attr_##_prefix##_##_name = \
__INIT_KOBJ_ATTR(_name, 0644, _show, _store)
#define BTRFS_ATTR(_prefix, _name, _show) \
static struct kobj_attribute btrfs_attr_##_prefix##_##_name = \
__INIT_KOBJ_ATTR(_name, 0444, _show, NULL)
#define BTRFS_ATTR_PTR(_prefix, _name) \
(&btrfs_attr_##_prefix##_##_name.attr)
#define BTRFS_FEAT_ATTR(_name, _feature_set, _feature_prefix, _feature_bit) \
static struct btrfs_feature_attr btrfs_attr_features_##_name = { \
.kobj_attr = __INIT_KOBJ_ATTR(_name, S_IRUGO, \
btrfs_feature_attr_show, \
btrfs_feature_attr_store), \
.feature_set = _feature_set, \
.feature_bit = _feature_prefix ##_## _feature_bit, \
}
#define BTRFS_FEAT_ATTR_PTR(_name) \
(&btrfs_attr_features_##_name.kobj_attr.attr)
#define BTRFS_FEAT_ATTR_COMPAT(name, feature) \
BTRFS_FEAT_ATTR(name, FEAT_COMPAT, BTRFS_FEATURE_COMPAT, feature)
#define BTRFS_FEAT_ATTR_COMPAT_RO(name, feature) \
BTRFS_FEAT_ATTR(name, FEAT_COMPAT_RO, BTRFS_FEATURE_COMPAT_RO, feature)
#define BTRFS_FEAT_ATTR_INCOMPAT(name, feature) \
BTRFS_FEAT_ATTR(name, FEAT_INCOMPAT, BTRFS_FEATURE_INCOMPAT, feature)
static inline struct btrfs_fs_info *to_fs_info(struct kobject *kobj);
static inline struct btrfs_fs_devices *to_fs_devs(struct kobject *kobj);
static struct btrfs_feature_attr *to_btrfs_feature_attr(struct kobj_attribute *a)
{
return container_of(a, struct btrfs_feature_attr, kobj_attr);
}
static struct kobj_attribute *attr_to_btrfs_attr(struct attribute *attr)
{
return container_of(attr, struct kobj_attribute, attr);
}
static struct btrfs_feature_attr *attr_to_btrfs_feature_attr(
struct attribute *attr)
{
return to_btrfs_feature_attr(attr_to_btrfs_attr(attr));
}
static u64 get_features(struct btrfs_fs_info *fs_info,
enum btrfs_feature_set set)
{
struct btrfs_super_block *disk_super = fs_info->super_copy;
if (set == FEAT_COMPAT)
return btrfs_super_compat_flags(disk_super);
else if (set == FEAT_COMPAT_RO)
return btrfs_super_compat_ro_flags(disk_super);
else
return btrfs_super_incompat_flags(disk_super);
}
static void set_features(struct btrfs_fs_info *fs_info,
enum btrfs_feature_set set, u64 features)
{
struct btrfs_super_block *disk_super = fs_info->super_copy;
if (set == FEAT_COMPAT)
btrfs_set_super_compat_flags(disk_super, features);
else if (set == FEAT_COMPAT_RO)
btrfs_set_super_compat_ro_flags(disk_super, features);
else
btrfs_set_super_incompat_flags(disk_super, features);
}
static int can_modify_feature(struct btrfs_feature_attr *fa)
{
int val = 0;
u64 set, clear;
switch (fa->feature_set) {
case FEAT_COMPAT:
set = BTRFS_FEATURE_COMPAT_SAFE_SET;
clear = BTRFS_FEATURE_COMPAT_SAFE_CLEAR;
break;
case FEAT_COMPAT_RO:
set = BTRFS_FEATURE_COMPAT_RO_SAFE_SET;
clear = BTRFS_FEATURE_COMPAT_RO_SAFE_CLEAR;
break;
case FEAT_INCOMPAT:
set = BTRFS_FEATURE_INCOMPAT_SAFE_SET;
clear = BTRFS_FEATURE_INCOMPAT_SAFE_CLEAR;
break;
default:
pr_warn("btrfs: sysfs: unknown feature set %d\n",
fa->feature_set);
return 0;
}
if (set & fa->feature_bit)
val |= 1;
if (clear & fa->feature_bit)
val |= 2;
return val;
}
static ssize_t btrfs_feature_attr_show(struct kobject *kobj,
struct kobj_attribute *a, char *buf)
{
int val = 0;
struct btrfs_fs_info *fs_info = to_fs_info(kobj);
struct btrfs_feature_attr *fa = to_btrfs_feature_attr(a);
if (fs_info) {
u64 features = get_features(fs_info, fa->feature_set);
if (features & fa->feature_bit)
val = 1;
} else
val = can_modify_feature(fa);
return scnprintf(buf, PAGE_SIZE, "%d\n", val);
}
static ssize_t btrfs_feature_attr_store(struct kobject *kobj,
struct kobj_attribute *a,
const char *buf, size_t count)
{
struct btrfs_fs_info *fs_info;
struct btrfs_feature_attr *fa = to_btrfs_feature_attr(a);
u64 features, set, clear;
unsigned long val;
int ret;
fs_info = to_fs_info(kobj);
if (!fs_info)
return -EPERM;
if (sb_rdonly(fs_info->sb))
return -EROFS;
ret = kstrtoul(skip_spaces(buf), 0, &val);
if (ret)
return ret;
if (fa->feature_set == FEAT_COMPAT) {
set = BTRFS_FEATURE_COMPAT_SAFE_SET;
clear = BTRFS_FEATURE_COMPAT_SAFE_CLEAR;
} else if (fa->feature_set == FEAT_COMPAT_RO) {
set = BTRFS_FEATURE_COMPAT_RO_SAFE_SET;
clear = BTRFS_FEATURE_COMPAT_RO_SAFE_CLEAR;
} else {
set = BTRFS_FEATURE_INCOMPAT_SAFE_SET;
clear = BTRFS_FEATURE_INCOMPAT_SAFE_CLEAR;
}
features = get_features(fs_info, fa->feature_set);
/* Nothing to do */
if ((val && (features & fa->feature_bit)) ||
(!val && !(features & fa->feature_bit)))
return count;
if ((val && !(set & fa->feature_bit)) ||
(!val && !(clear & fa->feature_bit))) {
btrfs_info(fs_info,
"%sabling feature %s on mounted fs is not supported.",
val ? "En" : "Dis", fa->kobj_attr.attr.name);
return -EPERM;
}
btrfs_info(fs_info, "%s %s feature flag",
val ? "Setting" : "Clearing", fa->kobj_attr.attr.name);
spin_lock(&fs_info->super_lock);
features = get_features(fs_info, fa->feature_set);
if (val)
features |= fa->feature_bit;
else
features &= ~fa->feature_bit;
set_features(fs_info, fa->feature_set, features);
spin_unlock(&fs_info->super_lock);
/*
* We don't want to do full transaction commit from inside sysfs
*/
btrfs_set_pending(fs_info, COMMIT);
wake_up_process(fs_info->transaction_kthread);
return count;
}
static umode_t btrfs_feature_visible(struct kobject *kobj,
struct attribute *attr, int unused)
{
struct btrfs_fs_info *fs_info = to_fs_info(kobj);
umode_t mode = attr->mode;
if (fs_info) {
struct btrfs_feature_attr *fa;
u64 features;
fa = attr_to_btrfs_feature_attr(attr);
features = get_features(fs_info, fa->feature_set);
if (can_modify_feature(fa))
mode |= S_IWUSR;
else if (!(features & fa->feature_bit))
mode = 0;
}
return mode;
}
BTRFS_FEAT_ATTR_INCOMPAT(mixed_backref, MIXED_BACKREF);
BTRFS_FEAT_ATTR_INCOMPAT(default_subvol, DEFAULT_SUBVOL);
BTRFS_FEAT_ATTR_INCOMPAT(mixed_groups, MIXED_GROUPS);
BTRFS_FEAT_ATTR_INCOMPAT(compress_lzo, COMPRESS_LZO);
btrfs: Add zstd support Add zstd compression and decompression support to BtrFS. zstd at its fastest level compresses almost as well as zlib, while offering much faster compression and decompression, approaching lzo speeds. I benchmarked btrfs with zstd compression against no compression, lzo compression, and zlib compression. I benchmarked two scenarios. Copying a set of files to btrfs, and then reading the files. Copying a tarball to btrfs, extracting it to btrfs, and then reading the extracted files. After every operation, I call `sync` and include the sync time. Between every pair of operations I unmount and remount the filesystem to avoid caching. The benchmark files can be found in the upstream zstd source repository under `contrib/linux-kernel/{btrfs-benchmark.sh,btrfs-extract-benchmark.sh}` [1] [2]. I ran the benchmarks on a Ubuntu 14.04 VM with 2 cores and 4 GiB of RAM. The VM is running on a MacBook Pro with a 3.1 GHz Intel Core i7 processor, 16 GB of RAM, and a SSD. The first compression benchmark is copying 10 copies of the unzipped Silesia corpus [3] into a BtrFS filesystem mounted with `-o compress-force=Method`. The decompression benchmark times how long it takes to `tar` all 10 copies into `/dev/null`. The compression ratio is measured by comparing the output of `df` and `du`. See the benchmark file [1] for details. I benchmarked multiple zstd compression levels, although the patch uses zstd level 1. | Method | Ratio | Compression MB/s | Decompression speed | |---------|-------|------------------|---------------------| | None | 0.99 | 504 | 686 | | lzo | 1.66 | 398 | 442 | | zlib | 2.58 | 65 | 241 | | zstd 1 | 2.57 | 260 | 383 | | zstd 3 | 2.71 | 174 | 408 | | zstd 6 | 2.87 | 70 | 398 | | zstd 9 | 2.92 | 43 | 406 | | zstd 12 | 2.93 | 21 | 408 | | zstd 15 | 3.01 | 11 | 354 | The next benchmark first copies `linux-4.11.6.tar` [4] to btrfs. Then it measures the compression ratio, extracts the tar, and deletes the tar. Then it measures the compression ratio again, and `tar`s the extracted files into `/dev/null`. See the benchmark file [2] for details. | Method | Tar Ratio | Extract Ratio | Copy (s) | Extract (s)| Read (s) | |--------|-----------|---------------|----------|------------|----------| | None | 0.97 | 0.78 | 0.981 | 5.501 | 8.807 | | lzo | 2.06 | 1.38 | 1.631 | 8.458 | 8.585 | | zlib | 3.40 | 1.86 | 7.750 | 21.544 | 11.744 | | zstd 1 | 3.57 | 1.85 | 2.579 | 11.479 | 9.389 | [1] https://github.com/facebook/zstd/blob/dev/contrib/linux-kernel/btrfs-benchmark.sh [2] https://github.com/facebook/zstd/blob/dev/contrib/linux-kernel/btrfs-extract-benchmark.sh [3] http://sun.aei.polsl.pl/~sdeor/index.php?page=silesia [4] https://cdn.kernel.org/pub/linux/kernel/v4.x/linux-4.11.6.tar.xz zstd source repository: https://github.com/facebook/zstd Signed-off-by: Nick Terrell <terrelln@fb.com> Signed-off-by: Chris Mason <clm@fb.com>
2017-08-10 02:39:02 +00:00
BTRFS_FEAT_ATTR_INCOMPAT(compress_zstd, COMPRESS_ZSTD);
BTRFS_FEAT_ATTR_INCOMPAT(big_metadata, BIG_METADATA);
BTRFS_FEAT_ATTR_INCOMPAT(extended_iref, EXTENDED_IREF);
BTRFS_FEAT_ATTR_INCOMPAT(raid56, RAID56);
BTRFS_FEAT_ATTR_INCOMPAT(skinny_metadata, SKINNY_METADATA);
BTRFS_FEAT_ATTR_INCOMPAT(no_holes, NO_HOLES);
BTRFS_FEAT_ATTR_INCOMPAT(metadata_uuid, METADATA_UUID);
BTRFS_FEAT_ATTR_COMPAT_RO(free_space_tree, FREE_SPACE_TREE);
BTRFS_FEAT_ATTR_INCOMPAT(raid1c34, RAID1C34);
static struct attribute *btrfs_supported_feature_attrs[] = {
BTRFS_FEAT_ATTR_PTR(mixed_backref),
BTRFS_FEAT_ATTR_PTR(default_subvol),
BTRFS_FEAT_ATTR_PTR(mixed_groups),
BTRFS_FEAT_ATTR_PTR(compress_lzo),
btrfs: Add zstd support Add zstd compression and decompression support to BtrFS. zstd at its fastest level compresses almost as well as zlib, while offering much faster compression and decompression, approaching lzo speeds. I benchmarked btrfs with zstd compression against no compression, lzo compression, and zlib compression. I benchmarked two scenarios. Copying a set of files to btrfs, and then reading the files. Copying a tarball to btrfs, extracting it to btrfs, and then reading the extracted files. After every operation, I call `sync` and include the sync time. Between every pair of operations I unmount and remount the filesystem to avoid caching. The benchmark files can be found in the upstream zstd source repository under `contrib/linux-kernel/{btrfs-benchmark.sh,btrfs-extract-benchmark.sh}` [1] [2]. I ran the benchmarks on a Ubuntu 14.04 VM with 2 cores and 4 GiB of RAM. The VM is running on a MacBook Pro with a 3.1 GHz Intel Core i7 processor, 16 GB of RAM, and a SSD. The first compression benchmark is copying 10 copies of the unzipped Silesia corpus [3] into a BtrFS filesystem mounted with `-o compress-force=Method`. The decompression benchmark times how long it takes to `tar` all 10 copies into `/dev/null`. The compression ratio is measured by comparing the output of `df` and `du`. See the benchmark file [1] for details. I benchmarked multiple zstd compression levels, although the patch uses zstd level 1. | Method | Ratio | Compression MB/s | Decompression speed | |---------|-------|------------------|---------------------| | None | 0.99 | 504 | 686 | | lzo | 1.66 | 398 | 442 | | zlib | 2.58 | 65 | 241 | | zstd 1 | 2.57 | 260 | 383 | | zstd 3 | 2.71 | 174 | 408 | | zstd 6 | 2.87 | 70 | 398 | | zstd 9 | 2.92 | 43 | 406 | | zstd 12 | 2.93 | 21 | 408 | | zstd 15 | 3.01 | 11 | 354 | The next benchmark first copies `linux-4.11.6.tar` [4] to btrfs. Then it measures the compression ratio, extracts the tar, and deletes the tar. Then it measures the compression ratio again, and `tar`s the extracted files into `/dev/null`. See the benchmark file [2] for details. | Method | Tar Ratio | Extract Ratio | Copy (s) | Extract (s)| Read (s) | |--------|-----------|---------------|----------|------------|----------| | None | 0.97 | 0.78 | 0.981 | 5.501 | 8.807 | | lzo | 2.06 | 1.38 | 1.631 | 8.458 | 8.585 | | zlib | 3.40 | 1.86 | 7.750 | 21.544 | 11.744 | | zstd 1 | 3.57 | 1.85 | 2.579 | 11.479 | 9.389 | [1] https://github.com/facebook/zstd/blob/dev/contrib/linux-kernel/btrfs-benchmark.sh [2] https://github.com/facebook/zstd/blob/dev/contrib/linux-kernel/btrfs-extract-benchmark.sh [3] http://sun.aei.polsl.pl/~sdeor/index.php?page=silesia [4] https://cdn.kernel.org/pub/linux/kernel/v4.x/linux-4.11.6.tar.xz zstd source repository: https://github.com/facebook/zstd Signed-off-by: Nick Terrell <terrelln@fb.com> Signed-off-by: Chris Mason <clm@fb.com>
2017-08-10 02:39:02 +00:00
BTRFS_FEAT_ATTR_PTR(compress_zstd),
BTRFS_FEAT_ATTR_PTR(big_metadata),
BTRFS_FEAT_ATTR_PTR(extended_iref),
BTRFS_FEAT_ATTR_PTR(raid56),
BTRFS_FEAT_ATTR_PTR(skinny_metadata),
BTRFS_FEAT_ATTR_PTR(no_holes),
BTRFS_FEAT_ATTR_PTR(metadata_uuid),
BTRFS_FEAT_ATTR_PTR(free_space_tree),
BTRFS_FEAT_ATTR_PTR(raid1c34),
NULL
};
/*
* Features which depend on feature bits and may differ between each fs.
*
* /sys/fs/btrfs/features lists all available features of this kernel while
* /sys/fs/btrfs/UUID/features shows features of the fs which are enabled or
* can be changed online.
*/
static const struct attribute_group btrfs_feature_attr_group = {
.name = "features",
.is_visible = btrfs_feature_visible,
.attrs = btrfs_supported_feature_attrs,
};
static ssize_t rmdir_subvol_show(struct kobject *kobj,
struct kobj_attribute *ka, char *buf)
{
return scnprintf(buf, PAGE_SIZE, "0\n");
}
BTRFS_ATTR(static_feature, rmdir_subvol, rmdir_subvol_show);
static ssize_t supported_checksums_show(struct kobject *kobj,
struct kobj_attribute *a, char *buf)
{
ssize_t ret = 0;
int i;
for (i = 0; i < btrfs_get_num_csums(); i++) {
/*
* This "trick" only works as long as 'enum btrfs_csum_type' has
* no holes in it
*/
ret += scnprintf(buf + ret, PAGE_SIZE - ret, "%s%s",
(i == 0 ? "" : " "), btrfs_super_csum_name(i));
}
ret += scnprintf(buf + ret, PAGE_SIZE - ret, "\n");
return ret;
}
BTRFS_ATTR(static_feature, supported_checksums, supported_checksums_show);
static struct attribute *btrfs_supported_static_feature_attrs[] = {
BTRFS_ATTR_PTR(static_feature, rmdir_subvol),
BTRFS_ATTR_PTR(static_feature, supported_checksums),
NULL
};
/*
* Features which only depend on kernel version.
*
* These are listed in /sys/fs/btrfs/features along with
* btrfs_feature_attr_group
*/
static const struct attribute_group btrfs_static_feature_attr_group = {
.name = "features",
.attrs = btrfs_supported_static_feature_attrs,
};
#ifdef CONFIG_BTRFS_DEBUG
/*
* Discard statistics and tunables
*/
#define discard_to_fs_info(_kobj) to_fs_info((_kobj)->parent->parent)
static ssize_t btrfs_discardable_bytes_show(struct kobject *kobj,
struct kobj_attribute *a,
char *buf)
{
struct btrfs_fs_info *fs_info = discard_to_fs_info(kobj);
return scnprintf(buf, PAGE_SIZE, "%lld\n",
atomic64_read(&fs_info->discard_ctl.discardable_bytes));
}
BTRFS_ATTR(discard, discardable_bytes, btrfs_discardable_bytes_show);
static ssize_t btrfs_discardable_extents_show(struct kobject *kobj,
struct kobj_attribute *a,
char *buf)
{
struct btrfs_fs_info *fs_info = discard_to_fs_info(kobj);
return scnprintf(buf, PAGE_SIZE, "%d\n",
atomic_read(&fs_info->discard_ctl.discardable_extents));
}
BTRFS_ATTR(discard, discardable_extents, btrfs_discardable_extents_show);
static ssize_t btrfs_discard_bitmap_bytes_show(struct kobject *kobj,
struct kobj_attribute *a,
char *buf)
{
struct btrfs_fs_info *fs_info = discard_to_fs_info(kobj);
return scnprintf(buf, PAGE_SIZE, "%lld\n",
fs_info->discard_ctl.discard_bitmap_bytes);
}
BTRFS_ATTR(discard, discard_bitmap_bytes, btrfs_discard_bitmap_bytes_show);
static ssize_t btrfs_discard_bytes_saved_show(struct kobject *kobj,
struct kobj_attribute *a,
char *buf)
{
struct btrfs_fs_info *fs_info = discard_to_fs_info(kobj);
return scnprintf(buf, PAGE_SIZE, "%lld\n",
atomic64_read(&fs_info->discard_ctl.discard_bytes_saved));
}
BTRFS_ATTR(discard, discard_bytes_saved, btrfs_discard_bytes_saved_show);
static ssize_t btrfs_discard_extent_bytes_show(struct kobject *kobj,
struct kobj_attribute *a,
char *buf)
{
struct btrfs_fs_info *fs_info = discard_to_fs_info(kobj);
return scnprintf(buf, PAGE_SIZE, "%lld\n",
fs_info->discard_ctl.discard_extent_bytes);
}
BTRFS_ATTR(discard, discard_extent_bytes, btrfs_discard_extent_bytes_show);
static ssize_t btrfs_discard_iops_limit_show(struct kobject *kobj,
struct kobj_attribute *a,
char *buf)
{
struct btrfs_fs_info *fs_info = discard_to_fs_info(kobj);
return scnprintf(buf, PAGE_SIZE, "%u\n",
READ_ONCE(fs_info->discard_ctl.iops_limit));
}
static ssize_t btrfs_discard_iops_limit_store(struct kobject *kobj,
struct kobj_attribute *a,
const char *buf, size_t len)
{
struct btrfs_fs_info *fs_info = discard_to_fs_info(kobj);
struct btrfs_discard_ctl *discard_ctl = &fs_info->discard_ctl;
u32 iops_limit;
int ret;
ret = kstrtou32(buf, 10, &iops_limit);
if (ret)
return -EINVAL;
WRITE_ONCE(discard_ctl->iops_limit, iops_limit);
return len;
}
BTRFS_ATTR_RW(discard, iops_limit, btrfs_discard_iops_limit_show,
btrfs_discard_iops_limit_store);
static ssize_t btrfs_discard_kbps_limit_show(struct kobject *kobj,
struct kobj_attribute *a,
char *buf)
{
struct btrfs_fs_info *fs_info = discard_to_fs_info(kobj);
return scnprintf(buf, PAGE_SIZE, "%u\n",
READ_ONCE(fs_info->discard_ctl.kbps_limit));
}
static ssize_t btrfs_discard_kbps_limit_store(struct kobject *kobj,
struct kobj_attribute *a,
const char *buf, size_t len)
{
struct btrfs_fs_info *fs_info = discard_to_fs_info(kobj);
struct btrfs_discard_ctl *discard_ctl = &fs_info->discard_ctl;
u32 kbps_limit;
int ret;
ret = kstrtou32(buf, 10, &kbps_limit);
if (ret)
return -EINVAL;
WRITE_ONCE(discard_ctl->kbps_limit, kbps_limit);
return len;
}
BTRFS_ATTR_RW(discard, kbps_limit, btrfs_discard_kbps_limit_show,
btrfs_discard_kbps_limit_store);
static ssize_t btrfs_discard_max_discard_size_show(struct kobject *kobj,
struct kobj_attribute *a,
char *buf)
{
struct btrfs_fs_info *fs_info = discard_to_fs_info(kobj);
return scnprintf(buf, PAGE_SIZE, "%llu\n",
READ_ONCE(fs_info->discard_ctl.max_discard_size));
}
static ssize_t btrfs_discard_max_discard_size_store(struct kobject *kobj,
struct kobj_attribute *a,
const char *buf, size_t len)
{
struct btrfs_fs_info *fs_info = discard_to_fs_info(kobj);
struct btrfs_discard_ctl *discard_ctl = &fs_info->discard_ctl;
u64 max_discard_size;
int ret;
ret = kstrtou64(buf, 10, &max_discard_size);
if (ret)
return -EINVAL;
WRITE_ONCE(discard_ctl->max_discard_size, max_discard_size);
return len;
}
BTRFS_ATTR_RW(discard, max_discard_size, btrfs_discard_max_discard_size_show,
btrfs_discard_max_discard_size_store);
static const struct attribute *discard_debug_attrs[] = {
BTRFS_ATTR_PTR(discard, discardable_bytes),
BTRFS_ATTR_PTR(discard, discardable_extents),
BTRFS_ATTR_PTR(discard, discard_bitmap_bytes),
BTRFS_ATTR_PTR(discard, discard_bytes_saved),
BTRFS_ATTR_PTR(discard, discard_extent_bytes),
BTRFS_ATTR_PTR(discard, iops_limit),
BTRFS_ATTR_PTR(discard, kbps_limit),
BTRFS_ATTR_PTR(discard, max_discard_size),
NULL,
};
/*
* Runtime debugging exported via sysfs
*
* /sys/fs/btrfs/debug - applies to module or all filesystems
* /sys/fs/btrfs/UUID - applies only to the given filesystem
*/
static const struct attribute *btrfs_debug_mount_attrs[] = {
NULL,
};
static struct attribute *btrfs_debug_feature_attrs[] = {
NULL
};
static const struct attribute_group btrfs_debug_feature_attr_group = {
.name = "debug",
.attrs = btrfs_debug_feature_attrs,
};
#endif
static ssize_t btrfs_show_u64(u64 *value_ptr, spinlock_t *lock, char *buf)
{
u64 val;
if (lock)
spin_lock(lock);
val = *value_ptr;
if (lock)
spin_unlock(lock);
return scnprintf(buf, PAGE_SIZE, "%llu\n", val);
}
static ssize_t global_rsv_size_show(struct kobject *kobj,
struct kobj_attribute *ka, char *buf)
{
struct btrfs_fs_info *fs_info = to_fs_info(kobj->parent);
struct btrfs_block_rsv *block_rsv = &fs_info->global_block_rsv;
return btrfs_show_u64(&block_rsv->size, &block_rsv->lock, buf);
}
BTRFS_ATTR(allocation, global_rsv_size, global_rsv_size_show);
static ssize_t global_rsv_reserved_show(struct kobject *kobj,
struct kobj_attribute *a, char *buf)
{
struct btrfs_fs_info *fs_info = to_fs_info(kobj->parent);
struct btrfs_block_rsv *block_rsv = &fs_info->global_block_rsv;
return btrfs_show_u64(&block_rsv->reserved, &block_rsv->lock, buf);
}
BTRFS_ATTR(allocation, global_rsv_reserved, global_rsv_reserved_show);
#define to_space_info(_kobj) container_of(_kobj, struct btrfs_space_info, kobj)
#define to_raid_kobj(_kobj) container_of(_kobj, struct raid_kobject, kobj)
static ssize_t raid_bytes_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf);
BTRFS_ATTR(raid, total_bytes, raid_bytes_show);
BTRFS_ATTR(raid, used_bytes, raid_bytes_show);
static ssize_t raid_bytes_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
struct btrfs_space_info *sinfo = to_space_info(kobj->parent);
struct btrfs_block_group *block_group;
int index = btrfs_bg_flags_to_raid_index(to_raid_kobj(kobj)->flags);
u64 val = 0;
down_read(&sinfo->groups_sem);
list_for_each_entry(block_group, &sinfo->block_groups[index], list) {
if (&attr->attr == BTRFS_ATTR_PTR(raid, total_bytes))
val += block_group->length;
else
val += block_group->used;
}
up_read(&sinfo->groups_sem);
return scnprintf(buf, PAGE_SIZE, "%llu\n", val);
}
static struct attribute *raid_attrs[] = {
BTRFS_ATTR_PTR(raid, total_bytes),
BTRFS_ATTR_PTR(raid, used_bytes),
NULL
};
ATTRIBUTE_GROUPS(raid);
static void release_raid_kobj(struct kobject *kobj)
{
kfree(to_raid_kobj(kobj));
}
static struct kobj_type btrfs_raid_ktype = {
.sysfs_ops = &kobj_sysfs_ops,
.release = release_raid_kobj,
.default_groups = raid_groups,
};
#define SPACE_INFO_ATTR(field) \
static ssize_t btrfs_space_info_show_##field(struct kobject *kobj, \
struct kobj_attribute *a, \
char *buf) \
{ \
struct btrfs_space_info *sinfo = to_space_info(kobj); \
return btrfs_show_u64(&sinfo->field, &sinfo->lock, buf); \
} \
BTRFS_ATTR(space_info, field, btrfs_space_info_show_##field)
static ssize_t btrfs_space_info_show_total_bytes_pinned(struct kobject *kobj,
struct kobj_attribute *a,
char *buf)
{
struct btrfs_space_info *sinfo = to_space_info(kobj);
s64 val = percpu_counter_sum(&sinfo->total_bytes_pinned);
return scnprintf(buf, PAGE_SIZE, "%lld\n", val);
}
SPACE_INFO_ATTR(flags);
SPACE_INFO_ATTR(total_bytes);
SPACE_INFO_ATTR(bytes_used);
SPACE_INFO_ATTR(bytes_pinned);
SPACE_INFO_ATTR(bytes_reserved);
SPACE_INFO_ATTR(bytes_may_use);
SPACE_INFO_ATTR(bytes_readonly);
SPACE_INFO_ATTR(disk_used);
SPACE_INFO_ATTR(disk_total);
BTRFS_ATTR(space_info, total_bytes_pinned,
btrfs_space_info_show_total_bytes_pinned);
static struct attribute *space_info_attrs[] = {
BTRFS_ATTR_PTR(space_info, flags),
BTRFS_ATTR_PTR(space_info, total_bytes),
BTRFS_ATTR_PTR(space_info, bytes_used),
BTRFS_ATTR_PTR(space_info, bytes_pinned),
BTRFS_ATTR_PTR(space_info, bytes_reserved),
BTRFS_ATTR_PTR(space_info, bytes_may_use),
BTRFS_ATTR_PTR(space_info, bytes_readonly),
BTRFS_ATTR_PTR(space_info, disk_used),
BTRFS_ATTR_PTR(space_info, disk_total),
BTRFS_ATTR_PTR(space_info, total_bytes_pinned),
NULL,
};
ATTRIBUTE_GROUPS(space_info);
static void space_info_release(struct kobject *kobj)
{
struct btrfs_space_info *sinfo = to_space_info(kobj);
percpu_counter_destroy(&sinfo->total_bytes_pinned);
kfree(sinfo);
}
static struct kobj_type space_info_ktype = {
.sysfs_ops = &kobj_sysfs_ops,
.release = space_info_release,
.default_groups = space_info_groups,
};
static const struct attribute *allocation_attrs[] = {
BTRFS_ATTR_PTR(allocation, global_rsv_reserved),
BTRFS_ATTR_PTR(allocation, global_rsv_size),
NULL,
};
static ssize_t btrfs_label_show(struct kobject *kobj,
struct kobj_attribute *a, char *buf)
{
struct btrfs_fs_info *fs_info = to_fs_info(kobj);
char *label = fs_info->super_copy->label;
ssize_t ret;
spin_lock(&fs_info->super_lock);
ret = scnprintf(buf, PAGE_SIZE, label[0] ? "%s\n" : "%s", label);
spin_unlock(&fs_info->super_lock);
return ret;
}
static ssize_t btrfs_label_store(struct kobject *kobj,
struct kobj_attribute *a,
const char *buf, size_t len)
{
struct btrfs_fs_info *fs_info = to_fs_info(kobj);
size_t p_len;
if (!fs_info)
return -EPERM;
if (sb_rdonly(fs_info->sb))
return -EROFS;
/*
* p_len is the len until the first occurrence of either
* '\n' or '\0'
*/
p_len = strcspn(buf, "\n");
if (p_len >= BTRFS_LABEL_SIZE)
return -EINVAL;
spin_lock(&fs_info->super_lock);
memset(fs_info->super_copy->label, 0, BTRFS_LABEL_SIZE);
memcpy(fs_info->super_copy->label, buf, p_len);
spin_unlock(&fs_info->super_lock);
/*
* We don't want to do full transaction commit from inside sysfs
*/
btrfs_set_pending(fs_info, COMMIT);
wake_up_process(fs_info->transaction_kthread);
return len;
}
BTRFS_ATTR_RW(, label, btrfs_label_show, btrfs_label_store);
static ssize_t btrfs_nodesize_show(struct kobject *kobj,
struct kobj_attribute *a, char *buf)
{
struct btrfs_fs_info *fs_info = to_fs_info(kobj);
return scnprintf(buf, PAGE_SIZE, "%u\n", fs_info->super_copy->nodesize);
}
BTRFS_ATTR(, nodesize, btrfs_nodesize_show);
static ssize_t btrfs_sectorsize_show(struct kobject *kobj,
struct kobj_attribute *a, char *buf)
{
struct btrfs_fs_info *fs_info = to_fs_info(kobj);
return scnprintf(buf, PAGE_SIZE, "%u\n",
fs_info->super_copy->sectorsize);
}
BTRFS_ATTR(, sectorsize, btrfs_sectorsize_show);
static ssize_t btrfs_clone_alignment_show(struct kobject *kobj,
struct kobj_attribute *a, char *buf)
{
struct btrfs_fs_info *fs_info = to_fs_info(kobj);
return scnprintf(buf, PAGE_SIZE, "%u\n", fs_info->super_copy->sectorsize);
}
BTRFS_ATTR(, clone_alignment, btrfs_clone_alignment_show);
static ssize_t quota_override_show(struct kobject *kobj,
struct kobj_attribute *a, char *buf)
{
struct btrfs_fs_info *fs_info = to_fs_info(kobj);
int quota_override;
quota_override = test_bit(BTRFS_FS_QUOTA_OVERRIDE, &fs_info->flags);
return scnprintf(buf, PAGE_SIZE, "%d\n", quota_override);
}
static ssize_t quota_override_store(struct kobject *kobj,
struct kobj_attribute *a,
const char *buf, size_t len)
{
struct btrfs_fs_info *fs_info = to_fs_info(kobj);
unsigned long knob;
int err;
if (!fs_info)
return -EPERM;
if (!capable(CAP_SYS_RESOURCE))
return -EPERM;
err = kstrtoul(buf, 10, &knob);
if (err)
return err;
if (knob > 1)
return -EINVAL;
if (knob)
set_bit(BTRFS_FS_QUOTA_OVERRIDE, &fs_info->flags);
else
clear_bit(BTRFS_FS_QUOTA_OVERRIDE, &fs_info->flags);
return len;
}
BTRFS_ATTR_RW(, quota_override, quota_override_show, quota_override_store);
static ssize_t btrfs_metadata_uuid_show(struct kobject *kobj,
struct kobj_attribute *a, char *buf)
{
struct btrfs_fs_info *fs_info = to_fs_info(kobj);
return scnprintf(buf, PAGE_SIZE, "%pU\n",
fs_info->fs_devices->metadata_uuid);
}
BTRFS_ATTR(, metadata_uuid, btrfs_metadata_uuid_show);
static ssize_t btrfs_checksum_show(struct kobject *kobj,
struct kobj_attribute *a, char *buf)
{
struct btrfs_fs_info *fs_info = to_fs_info(kobj);
u16 csum_type = btrfs_super_csum_type(fs_info->super_copy);
return scnprintf(buf, PAGE_SIZE, "%s (%s)\n",
btrfs_super_csum_name(csum_type),
crypto_shash_driver_name(fs_info->csum_shash));
}
BTRFS_ATTR(, checksum, btrfs_checksum_show);
static ssize_t btrfs_exclusive_operation_show(struct kobject *kobj,
struct kobj_attribute *a, char *buf)
{
struct btrfs_fs_info *fs_info = to_fs_info(kobj);
const char *str;
switch (READ_ONCE(fs_info->exclusive_operation)) {
case BTRFS_EXCLOP_NONE:
str = "none\n";
break;
case BTRFS_EXCLOP_BALANCE:
str = "balance\n";
break;
case BTRFS_EXCLOP_DEV_ADD:
str = "device add\n";
break;
case BTRFS_EXCLOP_DEV_REMOVE:
str = "device remove\n";
break;
case BTRFS_EXCLOP_DEV_REPLACE:
str = "device replace\n";
break;
case BTRFS_EXCLOP_RESIZE:
str = "resize\n";
break;
case BTRFS_EXCLOP_SWAP_ACTIVATE:
str = "swap activate\n";
break;
default:
str = "UNKNOWN\n";
break;
}
return scnprintf(buf, PAGE_SIZE, "%s", str);
}
BTRFS_ATTR(, exclusive_operation, btrfs_exclusive_operation_show);
static const struct attribute *btrfs_attrs[] = {
BTRFS_ATTR_PTR(, label),
BTRFS_ATTR_PTR(, nodesize),
BTRFS_ATTR_PTR(, sectorsize),
BTRFS_ATTR_PTR(, clone_alignment),
BTRFS_ATTR_PTR(, quota_override),
BTRFS_ATTR_PTR(, metadata_uuid),
BTRFS_ATTR_PTR(, checksum),
BTRFS_ATTR_PTR(, exclusive_operation),
NULL,
};
static void btrfs_release_fsid_kobj(struct kobject *kobj)
{
struct btrfs_fs_devices *fs_devs = to_fs_devs(kobj);
memset(&fs_devs->fsid_kobj, 0, sizeof(struct kobject));
complete(&fs_devs->kobj_unregister);
}
static struct kobj_type btrfs_ktype = {
.sysfs_ops = &kobj_sysfs_ops,
.release = btrfs_release_fsid_kobj,
};
static inline struct btrfs_fs_devices *to_fs_devs(struct kobject *kobj)
{
if (kobj->ktype != &btrfs_ktype)
return NULL;
return container_of(kobj, struct btrfs_fs_devices, fsid_kobj);
}
static inline struct btrfs_fs_info *to_fs_info(struct kobject *kobj)
{
if (kobj->ktype != &btrfs_ktype)
return NULL;
return to_fs_devs(kobj)->fs_info;
}
#define NUM_FEATURE_BITS 64
#define BTRFS_FEATURE_NAME_MAX 13
static char btrfs_unknown_feature_names[FEAT_MAX][NUM_FEATURE_BITS][BTRFS_FEATURE_NAME_MAX];
static struct btrfs_feature_attr btrfs_feature_attrs[FEAT_MAX][NUM_FEATURE_BITS];
static const u64 supported_feature_masks[FEAT_MAX] = {
[FEAT_COMPAT] = BTRFS_FEATURE_COMPAT_SUPP,
[FEAT_COMPAT_RO] = BTRFS_FEATURE_COMPAT_RO_SUPP,
[FEAT_INCOMPAT] = BTRFS_FEATURE_INCOMPAT_SUPP,
};
static int addrm_unknown_feature_attrs(struct btrfs_fs_info *fs_info, bool add)
{
int set;
for (set = 0; set < FEAT_MAX; set++) {
int i;
struct attribute *attrs[2];
struct attribute_group agroup = {
.name = "features",
.attrs = attrs,
};
u64 features = get_features(fs_info, set);
features &= ~supported_feature_masks[set];
if (!features)
continue;
attrs[1] = NULL;
for (i = 0; i < NUM_FEATURE_BITS; i++) {
struct btrfs_feature_attr *fa;
if (!(features & (1ULL << i)))
continue;
fa = &btrfs_feature_attrs[set][i];
attrs[0] = &fa->kobj_attr.attr;
if (add) {
int ret;
ret = sysfs_merge_group(&fs_info->fs_devices->fsid_kobj,
&agroup);
if (ret)
return ret;
} else
sysfs_unmerge_group(&fs_info->fs_devices->fsid_kobj,
&agroup);
}
}
return 0;
}
static void __btrfs_sysfs_remove_fsid(struct btrfs_fs_devices *fs_devs)
{
if (fs_devs->devinfo_kobj) {
kobject_del(fs_devs->devinfo_kobj);
kobject_put(fs_devs->devinfo_kobj);
fs_devs->devinfo_kobj = NULL;
}
if (fs_devs->devices_kobj) {
kobject_del(fs_devs->devices_kobj);
kobject_put(fs_devs->devices_kobj);
fs_devs->devices_kobj = NULL;
}
if (fs_devs->fsid_kobj.state_initialized) {
kobject_del(&fs_devs->fsid_kobj);
kobject_put(&fs_devs->fsid_kobj);
wait_for_completion(&fs_devs->kobj_unregister);
}
}
/* when fs_devs is NULL it will remove all fsid kobject */
void btrfs_sysfs_remove_fsid(struct btrfs_fs_devices *fs_devs)
{
struct list_head *fs_uuids = btrfs_get_fs_uuids();
if (fs_devs) {
__btrfs_sysfs_remove_fsid(fs_devs);
return;
}
list_for_each_entry(fs_devs, fs_uuids, fs_list) {
__btrfs_sysfs_remove_fsid(fs_devs);
}
}
void btrfs_sysfs_remove_mounted(struct btrfs_fs_info *fs_info)
{
struct kobject *fsid_kobj = &fs_info->fs_devices->fsid_kobj;
sysfs_remove_link(fsid_kobj, "bdi");
if (fs_info->space_info_kobj) {
sysfs_remove_files(fs_info->space_info_kobj, allocation_attrs);
kobject_del(fs_info->space_info_kobj);
kobject_put(fs_info->space_info_kobj);
}
#ifdef CONFIG_BTRFS_DEBUG
if (fs_info->discard_debug_kobj) {
sysfs_remove_files(fs_info->discard_debug_kobj,
discard_debug_attrs);
kobject_del(fs_info->discard_debug_kobj);
kobject_put(fs_info->discard_debug_kobj);
}
if (fs_info->debug_kobj) {
sysfs_remove_files(fs_info->debug_kobj, btrfs_debug_mount_attrs);
kobject_del(fs_info->debug_kobj);
kobject_put(fs_info->debug_kobj);
}
#endif
addrm_unknown_feature_attrs(fs_info, false);
sysfs_remove_group(fsid_kobj, &btrfs_feature_attr_group);
sysfs_remove_files(fsid_kobj, btrfs_attrs);
btrfs_sysfs_remove_devices_dir(fs_info->fs_devices, NULL);
}
static const char * const btrfs_feature_set_names[FEAT_MAX] = {
[FEAT_COMPAT] = "compat",
[FEAT_COMPAT_RO] = "compat_ro",
[FEAT_INCOMPAT] = "incompat",
};
const char *btrfs_feature_set_name(enum btrfs_feature_set set)
{
return btrfs_feature_set_names[set];
}
char *btrfs_printable_features(enum btrfs_feature_set set, u64 flags)
{
size_t bufsize = 4096; /* safe max, 64 names * 64 bytes */
int len = 0;
int i;
char *str;
str = kmalloc(bufsize, GFP_KERNEL);
if (!str)
return str;
for (i = 0; i < ARRAY_SIZE(btrfs_feature_attrs[set]); i++) {
const char *name;
if (!(flags & (1ULL << i)))
continue;
name = btrfs_feature_attrs[set][i].kobj_attr.attr.name;
len += scnprintf(str + len, bufsize - len, "%s%s",
len ? "," : "", name);
}
return str;
}
static void init_feature_attrs(void)
{
struct btrfs_feature_attr *fa;
int set, i;
BUILD_BUG_ON(ARRAY_SIZE(btrfs_unknown_feature_names) !=
ARRAY_SIZE(btrfs_feature_attrs));
BUILD_BUG_ON(ARRAY_SIZE(btrfs_unknown_feature_names[0]) !=
ARRAY_SIZE(btrfs_feature_attrs[0]));
memset(btrfs_feature_attrs, 0, sizeof(btrfs_feature_attrs));
memset(btrfs_unknown_feature_names, 0,
sizeof(btrfs_unknown_feature_names));
for (i = 0; btrfs_supported_feature_attrs[i]; i++) {
struct btrfs_feature_attr *sfa;
struct attribute *a = btrfs_supported_feature_attrs[i];
int bit;
sfa = attr_to_btrfs_feature_attr(a);
bit = ilog2(sfa->feature_bit);
fa = &btrfs_feature_attrs[sfa->feature_set][bit];
fa->kobj_attr.attr.name = sfa->kobj_attr.attr.name;
}
for (set = 0; set < FEAT_MAX; set++) {
for (i = 0; i < ARRAY_SIZE(btrfs_feature_attrs[set]); i++) {
char *name = btrfs_unknown_feature_names[set][i];
fa = &btrfs_feature_attrs[set][i];
if (fa->kobj_attr.attr.name)
continue;
snprintf(name, BTRFS_FEATURE_NAME_MAX, "%s:%u",
btrfs_feature_set_names[set], i);
fa->kobj_attr.attr.name = name;
fa->kobj_attr.attr.mode = S_IRUGO;
fa->feature_set = set;
fa->feature_bit = 1ULL << i;
}
}
}
/*
* Create a sysfs entry for a given block group type at path
* /sys/fs/btrfs/UUID/allocation/data/TYPE
*/
void btrfs_sysfs_add_block_group_type(struct btrfs_block_group *cache)
{
struct btrfs_fs_info *fs_info = cache->fs_info;
struct btrfs_space_info *space_info = cache->space_info;
struct raid_kobject *rkobj;
const int index = btrfs_bg_flags_to_raid_index(cache->flags);
unsigned int nofs_flag;
int ret;
/*
* Setup a NOFS context because kobject_add(), deep in its call chain,
* does GFP_KERNEL allocations, and we are often called in a context
* where if reclaim is triggered we can deadlock (we are either holding
* a transaction handle or some lock required for a transaction
* commit).
*/
nofs_flag = memalloc_nofs_save();
rkobj = kzalloc(sizeof(*rkobj), GFP_NOFS);
if (!rkobj) {
memalloc_nofs_restore(nofs_flag);
btrfs_warn(cache->fs_info,
"couldn't alloc memory for raid level kobject");
return;
}
rkobj->flags = cache->flags;
kobject_init(&rkobj->kobj, &btrfs_raid_ktype);
ret = kobject_add(&rkobj->kobj, &space_info->kobj, "%s",
btrfs_bg_type_to_raid_name(rkobj->flags));
memalloc_nofs_restore(nofs_flag);
if (ret) {
kobject_put(&rkobj->kobj);
btrfs_warn(fs_info,
"failed to add kobject for block cache, ignoring");
return;
}
space_info->block_group_kobjs[index] = &rkobj->kobj;
}
/*
* Remove sysfs directories for all block group types of a given space info and
* the space info as well
*/
void btrfs_sysfs_remove_space_info(struct btrfs_space_info *space_info)
{
int i;
for (i = 0; i < BTRFS_NR_RAID_TYPES; i++) {
struct kobject *kobj;
kobj = space_info->block_group_kobjs[i];
space_info->block_group_kobjs[i] = NULL;
if (kobj) {
kobject_del(kobj);
kobject_put(kobj);
}
}
kobject_del(&space_info->kobj);
kobject_put(&space_info->kobj);
}
static const char *alloc_name(u64 flags)
{
switch (flags) {
case BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_DATA:
return "mixed";
case BTRFS_BLOCK_GROUP_METADATA:
return "metadata";
case BTRFS_BLOCK_GROUP_DATA:
return "data";
case BTRFS_BLOCK_GROUP_SYSTEM:
return "system";
default:
WARN_ON(1);
return "invalid-combination";
};
}
/*
* Create a sysfs entry for a space info type at path
* /sys/fs/btrfs/UUID/allocation/TYPE
*/
int btrfs_sysfs_add_space_info_type(struct btrfs_fs_info *fs_info,
struct btrfs_space_info *space_info)
{
int ret;
ret = kobject_init_and_add(&space_info->kobj, &space_info_ktype,
fs_info->space_info_kobj, "%s",
alloc_name(space_info->flags));
if (ret) {
kobject_put(&space_info->kobj);
return ret;
}
return 0;
}
static void btrfs_sysfs_remove_device(struct btrfs_device *device)
{
struct hd_struct *disk;
struct kobject *disk_kobj;
struct kobject *devices_kobj;
/*
* Seed fs_devices devices_kobj aren't used, fetch kobject from the
* fs_info::fs_devices.
*/
devices_kobj = device->fs_info->fs_devices->devices_kobj;
ASSERT(devices_kobj);
if (device->bdev) {
disk = device->bdev->bd_part;
disk_kobj = &part_to_dev(disk)->kobj;
sysfs_remove_link(devices_kobj, disk_kobj->name);
}
btrfs: sysfs, add devid/dev_state kobject and device attributes New sysfs attributes that track the filesystem status of devices, stored in the per-filesystem directory in /sys/fs/btrfs/FSID/devinfo . There's a directory for each device, with name corresponding to the numerical device id. in_fs_metadata - device is in the list of fs metadata missing - device is missing (no device node or block device) replace_target - device is target of replace writeable - writes from fs are allowed These attributes reflect the state of the device::dev_state and created at mount time. Sample output: $ pwd /sys/fs/btrfs/6e1961f1-5918-4ecc-a22f-948897b409f7/devinfo/1/ $ ls in_fs_metadata missing replace_target writeable $ cat missing 0 The output from these attributes are 0 or 1. 0 indicates unset and 1 indicates set. These attributes are readonly. It is observed that the device delete thread and sysfs read thread will not race because the delete thread calls sysfs kobject_put() which in turn waits for existing sysfs read to complete. Note for device replace devid swap: During the replace the target device temporarily assumes devid 0 before assigning the devid of the soruce device. In btrfs_dev_replace_finishing() we remove source sysfs devid using the function btrfs_sysfs_remove_devices_attr(), so after that call kobject_rename() to update the devid in the sysfs. This adds and calls btrfs_sysfs_update_devid() helper function to update the device id. Signed-off-by: Anand Jain <anand.jain@oracle.com> Reviewed-by: David Sterba <dsterba@suse.com> [ update changelog ] Signed-off-by: David Sterba <dsterba@suse.com>
2020-01-06 11:38:31 +00:00
if (device->devid_kobj.state_initialized) {
kobject_del(&device->devid_kobj);
kobject_put(&device->devid_kobj);
wait_for_completion(&device->kobj_unregister);
}
}
/* When @device is NULL, remove all devices link */
void btrfs_sysfs_remove_devices_dir(struct btrfs_fs_devices *fs_devices,
struct btrfs_device *device)
{
if (device) {
btrfs_sysfs_remove_device(device);
return;
btrfs: sysfs, add devid/dev_state kobject and device attributes New sysfs attributes that track the filesystem status of devices, stored in the per-filesystem directory in /sys/fs/btrfs/FSID/devinfo . There's a directory for each device, with name corresponding to the numerical device id. in_fs_metadata - device is in the list of fs metadata missing - device is missing (no device node or block device) replace_target - device is target of replace writeable - writes from fs are allowed These attributes reflect the state of the device::dev_state and created at mount time. Sample output: $ pwd /sys/fs/btrfs/6e1961f1-5918-4ecc-a22f-948897b409f7/devinfo/1/ $ ls in_fs_metadata missing replace_target writeable $ cat missing 0 The output from these attributes are 0 or 1. 0 indicates unset and 1 indicates set. These attributes are readonly. It is observed that the device delete thread and sysfs read thread will not race because the delete thread calls sysfs kobject_put() which in turn waits for existing sysfs read to complete. Note for device replace devid swap: During the replace the target device temporarily assumes devid 0 before assigning the devid of the soruce device. In btrfs_dev_replace_finishing() we remove source sysfs devid using the function btrfs_sysfs_remove_devices_attr(), so after that call kobject_rename() to update the devid in the sysfs. This adds and calls btrfs_sysfs_update_devid() helper function to update the device id. Signed-off-by: Anand Jain <anand.jain@oracle.com> Reviewed-by: David Sterba <dsterba@suse.com> [ update changelog ] Signed-off-by: David Sterba <dsterba@suse.com>
2020-01-06 11:38:31 +00:00
}
list_for_each_entry(device, &fs_devices->devices, dev_list)
btrfs_sysfs_remove_device(device);
}
btrfs: sysfs, add devid/dev_state kobject and device attributes New sysfs attributes that track the filesystem status of devices, stored in the per-filesystem directory in /sys/fs/btrfs/FSID/devinfo . There's a directory for each device, with name corresponding to the numerical device id. in_fs_metadata - device is in the list of fs metadata missing - device is missing (no device node or block device) replace_target - device is target of replace writeable - writes from fs are allowed These attributes reflect the state of the device::dev_state and created at mount time. Sample output: $ pwd /sys/fs/btrfs/6e1961f1-5918-4ecc-a22f-948897b409f7/devinfo/1/ $ ls in_fs_metadata missing replace_target writeable $ cat missing 0 The output from these attributes are 0 or 1. 0 indicates unset and 1 indicates set. These attributes are readonly. It is observed that the device delete thread and sysfs read thread will not race because the delete thread calls sysfs kobject_put() which in turn waits for existing sysfs read to complete. Note for device replace devid swap: During the replace the target device temporarily assumes devid 0 before assigning the devid of the soruce device. In btrfs_dev_replace_finishing() we remove source sysfs devid using the function btrfs_sysfs_remove_devices_attr(), so after that call kobject_rename() to update the devid in the sysfs. This adds and calls btrfs_sysfs_update_devid() helper function to update the device id. Signed-off-by: Anand Jain <anand.jain@oracle.com> Reviewed-by: David Sterba <dsterba@suse.com> [ update changelog ] Signed-off-by: David Sterba <dsterba@suse.com>
2020-01-06 11:38:31 +00:00
static ssize_t btrfs_devinfo_in_fs_metadata_show(struct kobject *kobj,
struct kobj_attribute *a,
char *buf)
{
int val;
struct btrfs_device *device = container_of(kobj, struct btrfs_device,
devid_kobj);
val = !!test_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state);
return scnprintf(buf, PAGE_SIZE, "%d\n", val);
btrfs: sysfs, add devid/dev_state kobject and device attributes New sysfs attributes that track the filesystem status of devices, stored in the per-filesystem directory in /sys/fs/btrfs/FSID/devinfo . There's a directory for each device, with name corresponding to the numerical device id. in_fs_metadata - device is in the list of fs metadata missing - device is missing (no device node or block device) replace_target - device is target of replace writeable - writes from fs are allowed These attributes reflect the state of the device::dev_state and created at mount time. Sample output: $ pwd /sys/fs/btrfs/6e1961f1-5918-4ecc-a22f-948897b409f7/devinfo/1/ $ ls in_fs_metadata missing replace_target writeable $ cat missing 0 The output from these attributes are 0 or 1. 0 indicates unset and 1 indicates set. These attributes are readonly. It is observed that the device delete thread and sysfs read thread will not race because the delete thread calls sysfs kobject_put() which in turn waits for existing sysfs read to complete. Note for device replace devid swap: During the replace the target device temporarily assumes devid 0 before assigning the devid of the soruce device. In btrfs_dev_replace_finishing() we remove source sysfs devid using the function btrfs_sysfs_remove_devices_attr(), so after that call kobject_rename() to update the devid in the sysfs. This adds and calls btrfs_sysfs_update_devid() helper function to update the device id. Signed-off-by: Anand Jain <anand.jain@oracle.com> Reviewed-by: David Sterba <dsterba@suse.com> [ update changelog ] Signed-off-by: David Sterba <dsterba@suse.com>
2020-01-06 11:38:31 +00:00
}
BTRFS_ATTR(devid, in_fs_metadata, btrfs_devinfo_in_fs_metadata_show);
static ssize_t btrfs_devinfo_missing_show(struct kobject *kobj,
btrfs: sysfs, add devid/dev_state kobject and device attributes New sysfs attributes that track the filesystem status of devices, stored in the per-filesystem directory in /sys/fs/btrfs/FSID/devinfo . There's a directory for each device, with name corresponding to the numerical device id. in_fs_metadata - device is in the list of fs metadata missing - device is missing (no device node or block device) replace_target - device is target of replace writeable - writes from fs are allowed These attributes reflect the state of the device::dev_state and created at mount time. Sample output: $ pwd /sys/fs/btrfs/6e1961f1-5918-4ecc-a22f-948897b409f7/devinfo/1/ $ ls in_fs_metadata missing replace_target writeable $ cat missing 0 The output from these attributes are 0 or 1. 0 indicates unset and 1 indicates set. These attributes are readonly. It is observed that the device delete thread and sysfs read thread will not race because the delete thread calls sysfs kobject_put() which in turn waits for existing sysfs read to complete. Note for device replace devid swap: During the replace the target device temporarily assumes devid 0 before assigning the devid of the soruce device. In btrfs_dev_replace_finishing() we remove source sysfs devid using the function btrfs_sysfs_remove_devices_attr(), so after that call kobject_rename() to update the devid in the sysfs. This adds and calls btrfs_sysfs_update_devid() helper function to update the device id. Signed-off-by: Anand Jain <anand.jain@oracle.com> Reviewed-by: David Sterba <dsterba@suse.com> [ update changelog ] Signed-off-by: David Sterba <dsterba@suse.com>
2020-01-06 11:38:31 +00:00
struct kobj_attribute *a, char *buf)
{
int val;
struct btrfs_device *device = container_of(kobj, struct btrfs_device,
devid_kobj);
val = !!test_bit(BTRFS_DEV_STATE_MISSING, &device->dev_state);
return scnprintf(buf, PAGE_SIZE, "%d\n", val);
btrfs: sysfs, add devid/dev_state kobject and device attributes New sysfs attributes that track the filesystem status of devices, stored in the per-filesystem directory in /sys/fs/btrfs/FSID/devinfo . There's a directory for each device, with name corresponding to the numerical device id. in_fs_metadata - device is in the list of fs metadata missing - device is missing (no device node or block device) replace_target - device is target of replace writeable - writes from fs are allowed These attributes reflect the state of the device::dev_state and created at mount time. Sample output: $ pwd /sys/fs/btrfs/6e1961f1-5918-4ecc-a22f-948897b409f7/devinfo/1/ $ ls in_fs_metadata missing replace_target writeable $ cat missing 0 The output from these attributes are 0 or 1. 0 indicates unset and 1 indicates set. These attributes are readonly. It is observed that the device delete thread and sysfs read thread will not race because the delete thread calls sysfs kobject_put() which in turn waits for existing sysfs read to complete. Note for device replace devid swap: During the replace the target device temporarily assumes devid 0 before assigning the devid of the soruce device. In btrfs_dev_replace_finishing() we remove source sysfs devid using the function btrfs_sysfs_remove_devices_attr(), so after that call kobject_rename() to update the devid in the sysfs. This adds and calls btrfs_sysfs_update_devid() helper function to update the device id. Signed-off-by: Anand Jain <anand.jain@oracle.com> Reviewed-by: David Sterba <dsterba@suse.com> [ update changelog ] Signed-off-by: David Sterba <dsterba@suse.com>
2020-01-06 11:38:31 +00:00
}
BTRFS_ATTR(devid, missing, btrfs_devinfo_missing_show);
btrfs: sysfs, add devid/dev_state kobject and device attributes New sysfs attributes that track the filesystem status of devices, stored in the per-filesystem directory in /sys/fs/btrfs/FSID/devinfo . There's a directory for each device, with name corresponding to the numerical device id. in_fs_metadata - device is in the list of fs metadata missing - device is missing (no device node or block device) replace_target - device is target of replace writeable - writes from fs are allowed These attributes reflect the state of the device::dev_state and created at mount time. Sample output: $ pwd /sys/fs/btrfs/6e1961f1-5918-4ecc-a22f-948897b409f7/devinfo/1/ $ ls in_fs_metadata missing replace_target writeable $ cat missing 0 The output from these attributes are 0 or 1. 0 indicates unset and 1 indicates set. These attributes are readonly. It is observed that the device delete thread and sysfs read thread will not race because the delete thread calls sysfs kobject_put() which in turn waits for existing sysfs read to complete. Note for device replace devid swap: During the replace the target device temporarily assumes devid 0 before assigning the devid of the soruce device. In btrfs_dev_replace_finishing() we remove source sysfs devid using the function btrfs_sysfs_remove_devices_attr(), so after that call kobject_rename() to update the devid in the sysfs. This adds and calls btrfs_sysfs_update_devid() helper function to update the device id. Signed-off-by: Anand Jain <anand.jain@oracle.com> Reviewed-by: David Sterba <dsterba@suse.com> [ update changelog ] Signed-off-by: David Sterba <dsterba@suse.com>
2020-01-06 11:38:31 +00:00
static ssize_t btrfs_devinfo_replace_target_show(struct kobject *kobj,
struct kobj_attribute *a,
char *buf)
{
int val;
struct btrfs_device *device = container_of(kobj, struct btrfs_device,
devid_kobj);
val = !!test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state);
return scnprintf(buf, PAGE_SIZE, "%d\n", val);
btrfs: sysfs, add devid/dev_state kobject and device attributes New sysfs attributes that track the filesystem status of devices, stored in the per-filesystem directory in /sys/fs/btrfs/FSID/devinfo . There's a directory for each device, with name corresponding to the numerical device id. in_fs_metadata - device is in the list of fs metadata missing - device is missing (no device node or block device) replace_target - device is target of replace writeable - writes from fs are allowed These attributes reflect the state of the device::dev_state and created at mount time. Sample output: $ pwd /sys/fs/btrfs/6e1961f1-5918-4ecc-a22f-948897b409f7/devinfo/1/ $ ls in_fs_metadata missing replace_target writeable $ cat missing 0 The output from these attributes are 0 or 1. 0 indicates unset and 1 indicates set. These attributes are readonly. It is observed that the device delete thread and sysfs read thread will not race because the delete thread calls sysfs kobject_put() which in turn waits for existing sysfs read to complete. Note for device replace devid swap: During the replace the target device temporarily assumes devid 0 before assigning the devid of the soruce device. In btrfs_dev_replace_finishing() we remove source sysfs devid using the function btrfs_sysfs_remove_devices_attr(), so after that call kobject_rename() to update the devid in the sysfs. This adds and calls btrfs_sysfs_update_devid() helper function to update the device id. Signed-off-by: Anand Jain <anand.jain@oracle.com> Reviewed-by: David Sterba <dsterba@suse.com> [ update changelog ] Signed-off-by: David Sterba <dsterba@suse.com>
2020-01-06 11:38:31 +00:00
}
BTRFS_ATTR(devid, replace_target, btrfs_devinfo_replace_target_show);
static ssize_t btrfs_devinfo_writeable_show(struct kobject *kobj,
struct kobj_attribute *a, char *buf)
{
int val;
struct btrfs_device *device = container_of(kobj, struct btrfs_device,
devid_kobj);
val = !!test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state);
return scnprintf(buf, PAGE_SIZE, "%d\n", val);
btrfs: sysfs, add devid/dev_state kobject and device attributes New sysfs attributes that track the filesystem status of devices, stored in the per-filesystem directory in /sys/fs/btrfs/FSID/devinfo . There's a directory for each device, with name corresponding to the numerical device id. in_fs_metadata - device is in the list of fs metadata missing - device is missing (no device node or block device) replace_target - device is target of replace writeable - writes from fs are allowed These attributes reflect the state of the device::dev_state and created at mount time. Sample output: $ pwd /sys/fs/btrfs/6e1961f1-5918-4ecc-a22f-948897b409f7/devinfo/1/ $ ls in_fs_metadata missing replace_target writeable $ cat missing 0 The output from these attributes are 0 or 1. 0 indicates unset and 1 indicates set. These attributes are readonly. It is observed that the device delete thread and sysfs read thread will not race because the delete thread calls sysfs kobject_put() which in turn waits for existing sysfs read to complete. Note for device replace devid swap: During the replace the target device temporarily assumes devid 0 before assigning the devid of the soruce device. In btrfs_dev_replace_finishing() we remove source sysfs devid using the function btrfs_sysfs_remove_devices_attr(), so after that call kobject_rename() to update the devid in the sysfs. This adds and calls btrfs_sysfs_update_devid() helper function to update the device id. Signed-off-by: Anand Jain <anand.jain@oracle.com> Reviewed-by: David Sterba <dsterba@suse.com> [ update changelog ] Signed-off-by: David Sterba <dsterba@suse.com>
2020-01-06 11:38:31 +00:00
}
BTRFS_ATTR(devid, writeable, btrfs_devinfo_writeable_show);
static struct attribute *devid_attrs[] = {
BTRFS_ATTR_PTR(devid, in_fs_metadata),
BTRFS_ATTR_PTR(devid, missing),
BTRFS_ATTR_PTR(devid, replace_target),
BTRFS_ATTR_PTR(devid, writeable),
NULL
};
ATTRIBUTE_GROUPS(devid);
static void btrfs_release_devid_kobj(struct kobject *kobj)
{
struct btrfs_device *device = container_of(kobj, struct btrfs_device,
devid_kobj);
memset(&device->devid_kobj, 0, sizeof(struct kobject));
complete(&device->kobj_unregister);
}
static struct kobj_type devid_ktype = {
.sysfs_ops = &kobj_sysfs_ops,
.default_groups = devid_groups,
.release = btrfs_release_devid_kobj,
};
static int btrfs_sysfs_add_device(struct btrfs_device *device)
{
int ret;
btrfs: sysfs: use NOFS for device creation Dave hit this splat during testing btrfs/078: ====================================================== WARNING: possible circular locking dependency detected 5.8.0-rc6-default+ #1191 Not tainted ------------------------------------------------------ kswapd0/75 is trying to acquire lock: ffffa040e9d04ff8 (&delayed_node->mutex){+.+.}-{3:3}, at: __btrfs_release_delayed_node.part.0+0x3f/0x310 [btrfs] but task is already holding lock: ffffffff8b0c8040 (fs_reclaim){+.+.}-{0:0}, at: __fs_reclaim_acquire+0x5/0x30 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (fs_reclaim){+.+.}-{0:0}: __lock_acquire+0x56f/0xaa0 lock_acquire+0xa3/0x440 fs_reclaim_acquire.part.0+0x25/0x30 __kmalloc_track_caller+0x49/0x330 kstrdup+0x2e/0x60 __kernfs_new_node.constprop.0+0x44/0x250 kernfs_new_node+0x25/0x50 kernfs_create_link+0x34/0xa0 sysfs_do_create_link_sd+0x5e/0xd0 btrfs_sysfs_add_devices_dir+0x65/0x100 [btrfs] btrfs_init_new_device+0x44c/0x12b0 [btrfs] btrfs_ioctl+0xc3c/0x25c0 [btrfs] ksys_ioctl+0x68/0xa0 __x64_sys_ioctl+0x16/0x20 do_syscall_64+0x50/0xe0 entry_SYSCALL_64_after_hwframe+0x44/0xa9 -> #1 (&fs_info->chunk_mutex){+.+.}-{3:3}: __lock_acquire+0x56f/0xaa0 lock_acquire+0xa3/0x440 __mutex_lock+0xa0/0xaf0 btrfs_chunk_alloc+0x137/0x3e0 [btrfs] find_free_extent+0xb44/0xfb0 [btrfs] btrfs_reserve_extent+0x9b/0x180 [btrfs] btrfs_alloc_tree_block+0xc1/0x350 [btrfs] alloc_tree_block_no_bg_flush+0x4a/0x60 [btrfs] __btrfs_cow_block+0x143/0x7a0 [btrfs] btrfs_cow_block+0x15f/0x310 [btrfs] push_leaf_right+0x150/0x240 [btrfs] split_leaf+0x3cd/0x6d0 [btrfs] btrfs_search_slot+0xd14/0xf70 [btrfs] btrfs_insert_empty_items+0x64/0xc0 [btrfs] __btrfs_commit_inode_delayed_items+0xb2/0x840 [btrfs] btrfs_async_run_delayed_root+0x10e/0x1d0 [btrfs] btrfs_work_helper+0x2f9/0x650 [btrfs] process_one_work+0x22c/0x600 worker_thread+0x50/0x3b0 kthread+0x137/0x150 ret_from_fork+0x1f/0x30 -> #0 (&delayed_node->mutex){+.+.}-{3:3}: check_prev_add+0x98/0xa20 validate_chain+0xa8c/0x2a00 __lock_acquire+0x56f/0xaa0 lock_acquire+0xa3/0x440 __mutex_lock+0xa0/0xaf0 __btrfs_release_delayed_node.part.0+0x3f/0x310 [btrfs] btrfs_evict_inode+0x3bf/0x560 [btrfs] evict+0xd6/0x1c0 dispose_list+0x48/0x70 prune_icache_sb+0x54/0x80 super_cache_scan+0x121/0x1a0 do_shrink_slab+0x175/0x420 shrink_slab+0xb1/0x2e0 shrink_node+0x192/0x600 balance_pgdat+0x31f/0x750 kswapd+0x206/0x510 kthread+0x137/0x150 ret_from_fork+0x1f/0x30 other info that might help us debug this: Chain exists of: &delayed_node->mutex --> &fs_info->chunk_mutex --> fs_reclaim Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(fs_reclaim); lock(&fs_info->chunk_mutex); lock(fs_reclaim); lock(&delayed_node->mutex); *** DEADLOCK *** 3 locks held by kswapd0/75: #0: ffffffff8b0c8040 (fs_reclaim){+.+.}-{0:0}, at: __fs_reclaim_acquire+0x5/0x30 #1: ffffffff8b0b50b8 (shrinker_rwsem){++++}-{3:3}, at: shrink_slab+0x54/0x2e0 #2: ffffa040e057c0e8 (&type->s_umount_key#26){++++}-{3:3}, at: trylock_super+0x16/0x50 stack backtrace: CPU: 2 PID: 75 Comm: kswapd0 Not tainted 5.8.0-rc6-default+ #1191 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.0-59-gc9ba527-rebuilt.opensuse.org 04/01/2014 Call Trace: dump_stack+0x78/0xa0 check_noncircular+0x16f/0x190 check_prev_add+0x98/0xa20 validate_chain+0xa8c/0x2a00 __lock_acquire+0x56f/0xaa0 lock_acquire+0xa3/0x440 ? __btrfs_release_delayed_node.part.0+0x3f/0x310 [btrfs] __mutex_lock+0xa0/0xaf0 ? __btrfs_release_delayed_node.part.0+0x3f/0x310 [btrfs] ? __lock_acquire+0x56f/0xaa0 ? __btrfs_release_delayed_node.part.0+0x3f/0x310 [btrfs] ? lock_acquire+0xa3/0x440 ? btrfs_evict_inode+0x138/0x560 [btrfs] ? btrfs_evict_inode+0x2fe/0x560 [btrfs] ? __btrfs_release_delayed_node.part.0+0x3f/0x310 [btrfs] __btrfs_release_delayed_node.part.0+0x3f/0x310 [btrfs] btrfs_evict_inode+0x3bf/0x560 [btrfs] evict+0xd6/0x1c0 dispose_list+0x48/0x70 prune_icache_sb+0x54/0x80 super_cache_scan+0x121/0x1a0 do_shrink_slab+0x175/0x420 shrink_slab+0xb1/0x2e0 shrink_node+0x192/0x600 balance_pgdat+0x31f/0x750 kswapd+0x206/0x510 ? _raw_spin_unlock_irqrestore+0x3e/0x50 ? finish_wait+0x90/0x90 ? balance_pgdat+0x750/0x750 kthread+0x137/0x150 ? kthread_stop+0x2a0/0x2a0 ret_from_fork+0x1f/0x30 This is because we're holding the chunk_mutex while adding this device and adding its sysfs entries. We actually hold different locks in different places when calling this function, the dev_replace semaphore for instance in dev replace, so instead of moving this call around simply wrap it's operations in NOFS. CC: stable@vger.kernel.org # 4.14+ Reported-by: David Sterba <dsterba@suse.com> Signed-off-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-07-21 14:17:50 +00:00
unsigned int nofs_flag;
struct kobject *devices_kobj;
struct kobject *devinfo_kobj;
/*
* Make sure we use the fs_info::fs_devices to fetch the kobjects even
* for the seed fs_devices
*/
devices_kobj = device->fs_info->fs_devices->devices_kobj;
devinfo_kobj = device->fs_info->fs_devices->devinfo_kobj;
ASSERT(devices_kobj);
ASSERT(devinfo_kobj);
nofs_flag = memalloc_nofs_save();
if (device->bdev) {
struct hd_struct *disk;
struct kobject *disk_kobj;
btrfs: sysfs, add devid/dev_state kobject and device attributes New sysfs attributes that track the filesystem status of devices, stored in the per-filesystem directory in /sys/fs/btrfs/FSID/devinfo . There's a directory for each device, with name corresponding to the numerical device id. in_fs_metadata - device is in the list of fs metadata missing - device is missing (no device node or block device) replace_target - device is target of replace writeable - writes from fs are allowed These attributes reflect the state of the device::dev_state and created at mount time. Sample output: $ pwd /sys/fs/btrfs/6e1961f1-5918-4ecc-a22f-948897b409f7/devinfo/1/ $ ls in_fs_metadata missing replace_target writeable $ cat missing 0 The output from these attributes are 0 or 1. 0 indicates unset and 1 indicates set. These attributes are readonly. It is observed that the device delete thread and sysfs read thread will not race because the delete thread calls sysfs kobject_put() which in turn waits for existing sysfs read to complete. Note for device replace devid swap: During the replace the target device temporarily assumes devid 0 before assigning the devid of the soruce device. In btrfs_dev_replace_finishing() we remove source sysfs devid using the function btrfs_sysfs_remove_devices_attr(), so after that call kobject_rename() to update the devid in the sysfs. This adds and calls btrfs_sysfs_update_devid() helper function to update the device id. Signed-off-by: Anand Jain <anand.jain@oracle.com> Reviewed-by: David Sterba <dsterba@suse.com> [ update changelog ] Signed-off-by: David Sterba <dsterba@suse.com>
2020-01-06 11:38:31 +00:00
disk = device->bdev->bd_part;
disk_kobj = &part_to_dev(disk)->kobj;
btrfs: sysfs, add devid/dev_state kobject and device attributes New sysfs attributes that track the filesystem status of devices, stored in the per-filesystem directory in /sys/fs/btrfs/FSID/devinfo . There's a directory for each device, with name corresponding to the numerical device id. in_fs_metadata - device is in the list of fs metadata missing - device is missing (no device node or block device) replace_target - device is target of replace writeable - writes from fs are allowed These attributes reflect the state of the device::dev_state and created at mount time. Sample output: $ pwd /sys/fs/btrfs/6e1961f1-5918-4ecc-a22f-948897b409f7/devinfo/1/ $ ls in_fs_metadata missing replace_target writeable $ cat missing 0 The output from these attributes are 0 or 1. 0 indicates unset and 1 indicates set. These attributes are readonly. It is observed that the device delete thread and sysfs read thread will not race because the delete thread calls sysfs kobject_put() which in turn waits for existing sysfs read to complete. Note for device replace devid swap: During the replace the target device temporarily assumes devid 0 before assigning the devid of the soruce device. In btrfs_dev_replace_finishing() we remove source sysfs devid using the function btrfs_sysfs_remove_devices_attr(), so after that call kobject_rename() to update the devid in the sysfs. This adds and calls btrfs_sysfs_update_devid() helper function to update the device id. Signed-off-by: Anand Jain <anand.jain@oracle.com> Reviewed-by: David Sterba <dsterba@suse.com> [ update changelog ] Signed-off-by: David Sterba <dsterba@suse.com>
2020-01-06 11:38:31 +00:00
ret = sysfs_create_link(devices_kobj, disk_kobj, disk_kobj->name);
if (ret) {
btrfs_warn(device->fs_info,
"creating sysfs device link for devid %llu failed: %d",
device->devid, ret);
goto out;
btrfs: sysfs, add devid/dev_state kobject and device attributes New sysfs attributes that track the filesystem status of devices, stored in the per-filesystem directory in /sys/fs/btrfs/FSID/devinfo . There's a directory for each device, with name corresponding to the numerical device id. in_fs_metadata - device is in the list of fs metadata missing - device is missing (no device node or block device) replace_target - device is target of replace writeable - writes from fs are allowed These attributes reflect the state of the device::dev_state and created at mount time. Sample output: $ pwd /sys/fs/btrfs/6e1961f1-5918-4ecc-a22f-948897b409f7/devinfo/1/ $ ls in_fs_metadata missing replace_target writeable $ cat missing 0 The output from these attributes are 0 or 1. 0 indicates unset and 1 indicates set. These attributes are readonly. It is observed that the device delete thread and sysfs read thread will not race because the delete thread calls sysfs kobject_put() which in turn waits for existing sysfs read to complete. Note for device replace devid swap: During the replace the target device temporarily assumes devid 0 before assigning the devid of the soruce device. In btrfs_dev_replace_finishing() we remove source sysfs devid using the function btrfs_sysfs_remove_devices_attr(), so after that call kobject_rename() to update the devid in the sysfs. This adds and calls btrfs_sysfs_update_devid() helper function to update the device id. Signed-off-by: Anand Jain <anand.jain@oracle.com> Reviewed-by: David Sterba <dsterba@suse.com> [ update changelog ] Signed-off-by: David Sterba <dsterba@suse.com>
2020-01-06 11:38:31 +00:00
}
}
init_completion(&device->kobj_unregister);
ret = kobject_init_and_add(&device->devid_kobj, &devid_ktype,
devinfo_kobj, "%llu", device->devid);
if (ret) {
kobject_put(&device->devid_kobj);
btrfs_warn(device->fs_info,
"devinfo init for devid %llu failed: %d",
device->devid, ret);
}
out:
btrfs: sysfs: use NOFS for device creation Dave hit this splat during testing btrfs/078: ====================================================== WARNING: possible circular locking dependency detected 5.8.0-rc6-default+ #1191 Not tainted ------------------------------------------------------ kswapd0/75 is trying to acquire lock: ffffa040e9d04ff8 (&delayed_node->mutex){+.+.}-{3:3}, at: __btrfs_release_delayed_node.part.0+0x3f/0x310 [btrfs] but task is already holding lock: ffffffff8b0c8040 (fs_reclaim){+.+.}-{0:0}, at: __fs_reclaim_acquire+0x5/0x30 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (fs_reclaim){+.+.}-{0:0}: __lock_acquire+0x56f/0xaa0 lock_acquire+0xa3/0x440 fs_reclaim_acquire.part.0+0x25/0x30 __kmalloc_track_caller+0x49/0x330 kstrdup+0x2e/0x60 __kernfs_new_node.constprop.0+0x44/0x250 kernfs_new_node+0x25/0x50 kernfs_create_link+0x34/0xa0 sysfs_do_create_link_sd+0x5e/0xd0 btrfs_sysfs_add_devices_dir+0x65/0x100 [btrfs] btrfs_init_new_device+0x44c/0x12b0 [btrfs] btrfs_ioctl+0xc3c/0x25c0 [btrfs] ksys_ioctl+0x68/0xa0 __x64_sys_ioctl+0x16/0x20 do_syscall_64+0x50/0xe0 entry_SYSCALL_64_after_hwframe+0x44/0xa9 -> #1 (&fs_info->chunk_mutex){+.+.}-{3:3}: __lock_acquire+0x56f/0xaa0 lock_acquire+0xa3/0x440 __mutex_lock+0xa0/0xaf0 btrfs_chunk_alloc+0x137/0x3e0 [btrfs] find_free_extent+0xb44/0xfb0 [btrfs] btrfs_reserve_extent+0x9b/0x180 [btrfs] btrfs_alloc_tree_block+0xc1/0x350 [btrfs] alloc_tree_block_no_bg_flush+0x4a/0x60 [btrfs] __btrfs_cow_block+0x143/0x7a0 [btrfs] btrfs_cow_block+0x15f/0x310 [btrfs] push_leaf_right+0x150/0x240 [btrfs] split_leaf+0x3cd/0x6d0 [btrfs] btrfs_search_slot+0xd14/0xf70 [btrfs] btrfs_insert_empty_items+0x64/0xc0 [btrfs] __btrfs_commit_inode_delayed_items+0xb2/0x840 [btrfs] btrfs_async_run_delayed_root+0x10e/0x1d0 [btrfs] btrfs_work_helper+0x2f9/0x650 [btrfs] process_one_work+0x22c/0x600 worker_thread+0x50/0x3b0 kthread+0x137/0x150 ret_from_fork+0x1f/0x30 -> #0 (&delayed_node->mutex){+.+.}-{3:3}: check_prev_add+0x98/0xa20 validate_chain+0xa8c/0x2a00 __lock_acquire+0x56f/0xaa0 lock_acquire+0xa3/0x440 __mutex_lock+0xa0/0xaf0 __btrfs_release_delayed_node.part.0+0x3f/0x310 [btrfs] btrfs_evict_inode+0x3bf/0x560 [btrfs] evict+0xd6/0x1c0 dispose_list+0x48/0x70 prune_icache_sb+0x54/0x80 super_cache_scan+0x121/0x1a0 do_shrink_slab+0x175/0x420 shrink_slab+0xb1/0x2e0 shrink_node+0x192/0x600 balance_pgdat+0x31f/0x750 kswapd+0x206/0x510 kthread+0x137/0x150 ret_from_fork+0x1f/0x30 other info that might help us debug this: Chain exists of: &delayed_node->mutex --> &fs_info->chunk_mutex --> fs_reclaim Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(fs_reclaim); lock(&fs_info->chunk_mutex); lock(fs_reclaim); lock(&delayed_node->mutex); *** DEADLOCK *** 3 locks held by kswapd0/75: #0: ffffffff8b0c8040 (fs_reclaim){+.+.}-{0:0}, at: __fs_reclaim_acquire+0x5/0x30 #1: ffffffff8b0b50b8 (shrinker_rwsem){++++}-{3:3}, at: shrink_slab+0x54/0x2e0 #2: ffffa040e057c0e8 (&type->s_umount_key#26){++++}-{3:3}, at: trylock_super+0x16/0x50 stack backtrace: CPU: 2 PID: 75 Comm: kswapd0 Not tainted 5.8.0-rc6-default+ #1191 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.0-59-gc9ba527-rebuilt.opensuse.org 04/01/2014 Call Trace: dump_stack+0x78/0xa0 check_noncircular+0x16f/0x190 check_prev_add+0x98/0xa20 validate_chain+0xa8c/0x2a00 __lock_acquire+0x56f/0xaa0 lock_acquire+0xa3/0x440 ? __btrfs_release_delayed_node.part.0+0x3f/0x310 [btrfs] __mutex_lock+0xa0/0xaf0 ? __btrfs_release_delayed_node.part.0+0x3f/0x310 [btrfs] ? __lock_acquire+0x56f/0xaa0 ? __btrfs_release_delayed_node.part.0+0x3f/0x310 [btrfs] ? lock_acquire+0xa3/0x440 ? btrfs_evict_inode+0x138/0x560 [btrfs] ? btrfs_evict_inode+0x2fe/0x560 [btrfs] ? __btrfs_release_delayed_node.part.0+0x3f/0x310 [btrfs] __btrfs_release_delayed_node.part.0+0x3f/0x310 [btrfs] btrfs_evict_inode+0x3bf/0x560 [btrfs] evict+0xd6/0x1c0 dispose_list+0x48/0x70 prune_icache_sb+0x54/0x80 super_cache_scan+0x121/0x1a0 do_shrink_slab+0x175/0x420 shrink_slab+0xb1/0x2e0 shrink_node+0x192/0x600 balance_pgdat+0x31f/0x750 kswapd+0x206/0x510 ? _raw_spin_unlock_irqrestore+0x3e/0x50 ? finish_wait+0x90/0x90 ? balance_pgdat+0x750/0x750 kthread+0x137/0x150 ? kthread_stop+0x2a0/0x2a0 ret_from_fork+0x1f/0x30 This is because we're holding the chunk_mutex while adding this device and adding its sysfs entries. We actually hold different locks in different places when calling this function, the dev_replace semaphore for instance in dev replace, so instead of moving this call around simply wrap it's operations in NOFS. CC: stable@vger.kernel.org # 4.14+ Reported-by: David Sterba <dsterba@suse.com> Signed-off-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-07-21 14:17:50 +00:00
memalloc_nofs_restore(nofs_flag);
return ret;
}
int btrfs_sysfs_add_devices_dir(struct btrfs_fs_devices *fs_devices,
struct btrfs_device *device)
{
int ret;
if (device)
return btrfs_sysfs_add_device(device);
list_for_each_entry(device, &fs_devices->devices, dev_list) {
ret = btrfs_sysfs_add_device(device);
if (ret)
return ret;
}
return 0;
}
void btrfs_kobject_uevent(struct block_device *bdev, enum kobject_action action)
{
int ret;
ret = kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, action);
if (ret)
pr_warn("BTRFS: Sending event '%d' to kobject: '%s' (%p): failed\n",
action, kobject_name(&disk_to_dev(bdev->bd_disk)->kobj),
&disk_to_dev(bdev->bd_disk)->kobj);
}
void btrfs_sysfs_update_sprout_fsid(struct btrfs_fs_devices *fs_devices)
{
char fsid_buf[BTRFS_UUID_UNPARSED_SIZE];
/*
* Sprouting changes fsid of the mounted filesystem, rename the fsid
* directory
*/
snprintf(fsid_buf, BTRFS_UUID_UNPARSED_SIZE, "%pU", fs_devices->fsid);
if (kobject_rename(&fs_devices->fsid_kobj, fsid_buf))
btrfs_warn(fs_devices->fs_info,
"sysfs: failed to create fsid for sprout");
}
btrfs: sysfs, add devid/dev_state kobject and device attributes New sysfs attributes that track the filesystem status of devices, stored in the per-filesystem directory in /sys/fs/btrfs/FSID/devinfo . There's a directory for each device, with name corresponding to the numerical device id. in_fs_metadata - device is in the list of fs metadata missing - device is missing (no device node or block device) replace_target - device is target of replace writeable - writes from fs are allowed These attributes reflect the state of the device::dev_state and created at mount time. Sample output: $ pwd /sys/fs/btrfs/6e1961f1-5918-4ecc-a22f-948897b409f7/devinfo/1/ $ ls in_fs_metadata missing replace_target writeable $ cat missing 0 The output from these attributes are 0 or 1. 0 indicates unset and 1 indicates set. These attributes are readonly. It is observed that the device delete thread and sysfs read thread will not race because the delete thread calls sysfs kobject_put() which in turn waits for existing sysfs read to complete. Note for device replace devid swap: During the replace the target device temporarily assumes devid 0 before assigning the devid of the soruce device. In btrfs_dev_replace_finishing() we remove source sysfs devid using the function btrfs_sysfs_remove_devices_attr(), so after that call kobject_rename() to update the devid in the sysfs. This adds and calls btrfs_sysfs_update_devid() helper function to update the device id. Signed-off-by: Anand Jain <anand.jain@oracle.com> Reviewed-by: David Sterba <dsterba@suse.com> [ update changelog ] Signed-off-by: David Sterba <dsterba@suse.com>
2020-01-06 11:38:31 +00:00
void btrfs_sysfs_update_devid(struct btrfs_device *device)
{
char tmp[24];
snprintf(tmp, sizeof(tmp), "%llu", device->devid);
if (kobject_rename(&device->devid_kobj, tmp))
btrfs_warn(device->fs_devices->fs_info,
"sysfs: failed to update devid for %llu",
device->devid);
}
/* /sys/fs/btrfs/ entry */
static struct kset *btrfs_kset;
/*
* Creates:
* /sys/fs/btrfs/UUID
*
* Can be called by the device discovery thread.
*/
int btrfs_sysfs_add_fsid(struct btrfs_fs_devices *fs_devs)
{
int error;
init_completion(&fs_devs->kobj_unregister);
fs_devs->fsid_kobj.kset = btrfs_kset;
error = kobject_init_and_add(&fs_devs->fsid_kobj, &btrfs_ktype, NULL,
"%pU", fs_devs->fsid);
if (error) {
kobject_put(&fs_devs->fsid_kobj);
return error;
}
fs_devs->devices_kobj = kobject_create_and_add("devices",
&fs_devs->fsid_kobj);
if (!fs_devs->devices_kobj) {
btrfs_err(fs_devs->fs_info,
"failed to init sysfs device interface");
btrfs_sysfs_remove_fsid(fs_devs);
return -ENOMEM;
}
fs_devs->devinfo_kobj = kobject_create_and_add("devinfo",
&fs_devs->fsid_kobj);
if (!fs_devs->devinfo_kobj) {
btrfs_err(fs_devs->fs_info,
"failed to init sysfs devinfo kobject");
btrfs_sysfs_remove_fsid(fs_devs);
return -ENOMEM;
}
return 0;
}
int btrfs_sysfs_add_mounted(struct btrfs_fs_info *fs_info)
{
int error;
struct btrfs_fs_devices *fs_devs = fs_info->fs_devices;
struct kobject *fsid_kobj = &fs_devs->fsid_kobj;
error = btrfs_sysfs_add_devices_dir(fs_devs, NULL);
if (error)
return error;
error = sysfs_create_files(fsid_kobj, btrfs_attrs);
if (error) {
btrfs_sysfs_remove_devices_dir(fs_devs, NULL);
return error;
}
error = sysfs_create_group(fsid_kobj,
&btrfs_feature_attr_group);
if (error)
goto failure;
#ifdef CONFIG_BTRFS_DEBUG
fs_info->debug_kobj = kobject_create_and_add("debug", fsid_kobj);
if (!fs_info->debug_kobj) {
error = -ENOMEM;
goto failure;
}
error = sysfs_create_files(fs_info->debug_kobj, btrfs_debug_mount_attrs);
if (error)
goto failure;
/* Discard directory */
fs_info->discard_debug_kobj = kobject_create_and_add("discard",
fs_info->debug_kobj);
if (!fs_info->discard_debug_kobj) {
error = -ENOMEM;
goto failure;
}
error = sysfs_create_files(fs_info->discard_debug_kobj,
discard_debug_attrs);
if (error)
goto failure;
#endif
error = addrm_unknown_feature_attrs(fs_info, true);
if (error)
goto failure;
error = sysfs_create_link(fsid_kobj, &fs_info->sb->s_bdi->dev->kobj, "bdi");
if (error)
goto failure;
fs_info->space_info_kobj = kobject_create_and_add("allocation",
fsid_kobj);
if (!fs_info->space_info_kobj) {
error = -ENOMEM;
goto failure;
}
error = sysfs_create_files(fs_info->space_info_kobj, allocation_attrs);
if (error)
goto failure;
return 0;
failure:
btrfs_sysfs_remove_mounted(fs_info);
return error;
}
static inline struct btrfs_fs_info *qgroup_kobj_to_fs_info(struct kobject *kobj)
{
return to_fs_info(kobj->parent->parent);
}
#define QGROUP_ATTR(_member, _show_name) \
static ssize_t btrfs_qgroup_show_##_member(struct kobject *qgroup_kobj, \
struct kobj_attribute *a, \
char *buf) \
{ \
struct btrfs_fs_info *fs_info = qgroup_kobj_to_fs_info(qgroup_kobj); \
struct btrfs_qgroup *qgroup = container_of(qgroup_kobj, \
struct btrfs_qgroup, kobj); \
return btrfs_show_u64(&qgroup->_member, &fs_info->qgroup_lock, buf); \
} \
BTRFS_ATTR(qgroup, _show_name, btrfs_qgroup_show_##_member)
#define QGROUP_RSV_ATTR(_name, _type) \
static ssize_t btrfs_qgroup_rsv_show_##_name(struct kobject *qgroup_kobj, \
struct kobj_attribute *a, \
char *buf) \
{ \
struct btrfs_fs_info *fs_info = qgroup_kobj_to_fs_info(qgroup_kobj); \
struct btrfs_qgroup *qgroup = container_of(qgroup_kobj, \
struct btrfs_qgroup, kobj); \
return btrfs_show_u64(&qgroup->rsv.values[_type], \
&fs_info->qgroup_lock, buf); \
} \
BTRFS_ATTR(qgroup, rsv_##_name, btrfs_qgroup_rsv_show_##_name)
QGROUP_ATTR(rfer, referenced);
QGROUP_ATTR(excl, exclusive);
QGROUP_ATTR(max_rfer, max_referenced);
QGROUP_ATTR(max_excl, max_exclusive);
QGROUP_ATTR(lim_flags, limit_flags);
QGROUP_RSV_ATTR(data, BTRFS_QGROUP_RSV_DATA);
QGROUP_RSV_ATTR(meta_pertrans, BTRFS_QGROUP_RSV_META_PERTRANS);
QGROUP_RSV_ATTR(meta_prealloc, BTRFS_QGROUP_RSV_META_PREALLOC);
static struct attribute *qgroup_attrs[] = {
BTRFS_ATTR_PTR(qgroup, referenced),
BTRFS_ATTR_PTR(qgroup, exclusive),
BTRFS_ATTR_PTR(qgroup, max_referenced),
BTRFS_ATTR_PTR(qgroup, max_exclusive),
BTRFS_ATTR_PTR(qgroup, limit_flags),
BTRFS_ATTR_PTR(qgroup, rsv_data),
BTRFS_ATTR_PTR(qgroup, rsv_meta_pertrans),
BTRFS_ATTR_PTR(qgroup, rsv_meta_prealloc),
NULL
};
ATTRIBUTE_GROUPS(qgroup);
static void qgroup_release(struct kobject *kobj)
{
struct btrfs_qgroup *qgroup = container_of(kobj, struct btrfs_qgroup, kobj);
memset(&qgroup->kobj, 0, sizeof(*kobj));
}
static struct kobj_type qgroup_ktype = {
.sysfs_ops = &kobj_sysfs_ops,
.release = qgroup_release,
.default_groups = qgroup_groups,
};
int btrfs_sysfs_add_one_qgroup(struct btrfs_fs_info *fs_info,
struct btrfs_qgroup *qgroup)
{
struct kobject *qgroups_kobj = fs_info->qgroups_kobj;
int ret;
if (test_bit(BTRFS_FS_STATE_DUMMY_FS_INFO, &fs_info->fs_state))
return 0;
if (qgroup->kobj.state_initialized)
return 0;
if (!qgroups_kobj)
return -EINVAL;
ret = kobject_init_and_add(&qgroup->kobj, &qgroup_ktype, qgroups_kobj,
"%hu_%llu", btrfs_qgroup_level(qgroup->qgroupid),
btrfs_qgroup_subvolid(qgroup->qgroupid));
if (ret < 0)
kobject_put(&qgroup->kobj);
return ret;
}
void btrfs_sysfs_del_qgroups(struct btrfs_fs_info *fs_info)
{
struct btrfs_qgroup *qgroup;
struct btrfs_qgroup *next;
if (test_bit(BTRFS_FS_STATE_DUMMY_FS_INFO, &fs_info->fs_state))
return;
rbtree_postorder_for_each_entry_safe(qgroup, next,
&fs_info->qgroup_tree, node)
btrfs_sysfs_del_one_qgroup(fs_info, qgroup);
btrfs: sysfs: fix NULL pointer dereference at btrfs_sysfs_del_qgroups() [BUG] Unmounting a btrfs filesystem with quota disabled will cause the following NULL pointer dereference: BTRFS info (device dm-5): has skinny extents BUG: kernel NULL pointer dereference, address: 0000000000000018 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page CPU: 7 PID: 637 Comm: umount Not tainted 5.8.0-rc7-next-20200731-custom #76 RIP: 0010:kobject_del+0x6/0x20 Call Trace: btrfs_sysfs_del_qgroups+0xac/0xf0 [btrfs] btrfs_free_qgroup_config+0x63/0x70 [btrfs] close_ctree+0x1f5/0x323 [btrfs] btrfs_put_super+0x15/0x17 [btrfs] generic_shutdown_super+0x72/0x110 kill_anon_super+0x18/0x30 btrfs_kill_super+0x17/0x30 [btrfs] deactivate_locked_super+0x3b/0xa0 deactivate_super+0x40/0x50 cleanup_mnt+0x135/0x190 __cleanup_mnt+0x12/0x20 task_work_run+0x64/0xb0 exit_to_user_mode_prepare+0x18a/0x190 syscall_exit_to_user_mode+0x4f/0x270 do_syscall_64+0x45/0x50 entry_SYSCALL_64_after_hwframe+0x44/0xa9 ---[ end trace 37b7adca5c1d5c5d ]--- [CAUSE] Commit 079ad2fb4bf9 ("kobject: Avoid premature parent object freeing in kobject_cleanup()") changed kobject_del() that it no longer accepts NULL pointer. Before that commit, kobject_del() and kobject_put() all accept NULL pointers and just ignore such NULL pointers. But that mentioned commit needs to access the parent node, killing the old NULL pointer behavior. Unfortunately btrfs is relying on that hidden feature thus we will trigger such NULL pointer dereference. [FIX] Instead of just saving several lines, do proper fs_info->qgroups_kobj check before calling kobject_del() and kobject_put(). Reviewed-by: Nikolay Borisov <nborisov@suse.com> Signed-off-by: Qu Wenruo <wqu@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-08-03 06:20:11 +00:00
if (fs_info->qgroups_kobj) {
kobject_del(fs_info->qgroups_kobj);
kobject_put(fs_info->qgroups_kobj);
fs_info->qgroups_kobj = NULL;
}
}
/* Called when qgroups get initialized, thus there is no need for locking */
int btrfs_sysfs_add_qgroups(struct btrfs_fs_info *fs_info)
{
struct kobject *fsid_kobj = &fs_info->fs_devices->fsid_kobj;
struct btrfs_qgroup *qgroup;
struct btrfs_qgroup *next;
int ret = 0;
if (test_bit(BTRFS_FS_STATE_DUMMY_FS_INFO, &fs_info->fs_state))
return 0;
ASSERT(fsid_kobj);
if (fs_info->qgroups_kobj)
return 0;
fs_info->qgroups_kobj = kobject_create_and_add("qgroups", fsid_kobj);
if (!fs_info->qgroups_kobj) {
ret = -ENOMEM;
goto out;
}
rbtree_postorder_for_each_entry_safe(qgroup, next,
&fs_info->qgroup_tree, node) {
ret = btrfs_sysfs_add_one_qgroup(fs_info, qgroup);
if (ret < 0)
goto out;
}
out:
if (ret < 0)
btrfs_sysfs_del_qgroups(fs_info);
return ret;
}
void btrfs_sysfs_del_one_qgroup(struct btrfs_fs_info *fs_info,
struct btrfs_qgroup *qgroup)
{
if (test_bit(BTRFS_FS_STATE_DUMMY_FS_INFO, &fs_info->fs_state))
return;
if (qgroup->kobj.state_initialized) {
kobject_del(&qgroup->kobj);
kobject_put(&qgroup->kobj);
}
}
/*
* Change per-fs features in /sys/fs/btrfs/UUID/features to match current
* values in superblock. Call after any changes to incompat/compat_ro flags
*/
void btrfs_sysfs_feature_update(struct btrfs_fs_info *fs_info,
u64 bit, enum btrfs_feature_set set)
{
struct btrfs_fs_devices *fs_devs;
struct kobject *fsid_kobj;
u64 __maybe_unused features;
int __maybe_unused ret;
if (!fs_info)
return;
/*
* See 14e46e04958df74 and e410e34fad913dd, feature bit updates are not
* safe when called from some contexts (eg. balance)
*/
features = get_features(fs_info, set);
ASSERT(bit & supported_feature_masks[set]);
fs_devs = fs_info->fs_devices;
fsid_kobj = &fs_devs->fsid_kobj;
if (!fsid_kobj->state_initialized)
return;
/*
* FIXME: this is too heavy to update just one value, ideally we'd like
* to use sysfs_update_group but some refactoring is needed first.
*/
sysfs_remove_group(fsid_kobj, &btrfs_feature_attr_group);
ret = sysfs_create_group(fsid_kobj, &btrfs_feature_attr_group);
}
int __init btrfs_init_sysfs(void)
{
int ret;
btrfs_kset = kset_create_and_add("btrfs", NULL, fs_kobj);
if (!btrfs_kset)
return -ENOMEM;
init_feature_attrs();
ret = sysfs_create_group(&btrfs_kset->kobj, &btrfs_feature_attr_group);
Btrfs: add missing cleanup on sysfs init failure If we failed during initialization of sysfs, we weren't unregistering the top level btrfs sysfs entry nor the debugfs stuff. Not unregistering the top level sysfs entry makes future attempts to reload the btrfs module impossible and the following is reported in dmesg: [ 2246.451296] WARNING: CPU: 3 PID: 10999 at fs/sysfs/dir.c:486 sysfs_warn_dup+0x91/0xb0() [ 2246.451298] sysfs: cannot create duplicate filename '/fs/btrfs' [ 2246.451298] Modules linked in: btrfs(+) raid6_pq xor bnep rfcomm bluetooth binfmt_misc nfsd auth_rpcgss oid_registry nfs_acl nfs lockd fscache sunrpc parport_pc parport psmouse serio_raw pcspkr evbug i2c_piix4 e1000 floppy [last unloaded: btrfs] [ 2246.451310] CPU: 3 PID: 10999 Comm: modprobe Tainted: G W 3.13.0-fdm-btrfs-next-24+ #7 [ 2246.451311] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 [ 2246.451312] 0000000000000009 ffff8800d353fa08 ffffffff816f1da6 0000000000000410 [ 2246.451314] ffff8800d353fa58 ffff8800d353fa48 ffffffff8104a32c ffff88020821a290 [ 2246.451316] ffff88020821a290 ffff88020821a290 ffff8802148f0000 ffff8800d353fb80 [ 2246.451318] Call Trace: [ 2246.451322] [<ffffffff816f1da6>] dump_stack+0x4e/0x68 [ 2246.451324] [<ffffffff8104a32c>] warn_slowpath_common+0x8c/0xc0 [ 2246.451325] [<ffffffff8104a416>] warn_slowpath_fmt+0x46/0x50 [ 2246.451328] [<ffffffff81367dc5>] ? strlcat+0x65/0x90 (....) This fixes the following change: btrfs: add simple debugfs interface commit 1bae30982bc86ab66d61ccb6e22792593b45d44d Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
2015-01-23 18:27:00 +00:00
if (ret)
goto out2;
ret = sysfs_merge_group(&btrfs_kset->kobj,
&btrfs_static_feature_attr_group);
if (ret)
goto out_remove_group;
Btrfs: add missing cleanup on sysfs init failure If we failed during initialization of sysfs, we weren't unregistering the top level btrfs sysfs entry nor the debugfs stuff. Not unregistering the top level sysfs entry makes future attempts to reload the btrfs module impossible and the following is reported in dmesg: [ 2246.451296] WARNING: CPU: 3 PID: 10999 at fs/sysfs/dir.c:486 sysfs_warn_dup+0x91/0xb0() [ 2246.451298] sysfs: cannot create duplicate filename '/fs/btrfs' [ 2246.451298] Modules linked in: btrfs(+) raid6_pq xor bnep rfcomm bluetooth binfmt_misc nfsd auth_rpcgss oid_registry nfs_acl nfs lockd fscache sunrpc parport_pc parport psmouse serio_raw pcspkr evbug i2c_piix4 e1000 floppy [last unloaded: btrfs] [ 2246.451310] CPU: 3 PID: 10999 Comm: modprobe Tainted: G W 3.13.0-fdm-btrfs-next-24+ #7 [ 2246.451311] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 [ 2246.451312] 0000000000000009 ffff8800d353fa08 ffffffff816f1da6 0000000000000410 [ 2246.451314] ffff8800d353fa58 ffff8800d353fa48 ffffffff8104a32c ffff88020821a290 [ 2246.451316] ffff88020821a290 ffff88020821a290 ffff8802148f0000 ffff8800d353fb80 [ 2246.451318] Call Trace: [ 2246.451322] [<ffffffff816f1da6>] dump_stack+0x4e/0x68 [ 2246.451324] [<ffffffff8104a32c>] warn_slowpath_common+0x8c/0xc0 [ 2246.451325] [<ffffffff8104a416>] warn_slowpath_fmt+0x46/0x50 [ 2246.451328] [<ffffffff81367dc5>] ? strlcat+0x65/0x90 (....) This fixes the following change: btrfs: add simple debugfs interface commit 1bae30982bc86ab66d61ccb6e22792593b45d44d Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
2015-01-23 18:27:00 +00:00
#ifdef CONFIG_BTRFS_DEBUG
ret = sysfs_create_group(&btrfs_kset->kobj, &btrfs_debug_feature_attr_group);
if (ret)
goto out2;
#endif
Btrfs: add missing cleanup on sysfs init failure If we failed during initialization of sysfs, we weren't unregistering the top level btrfs sysfs entry nor the debugfs stuff. Not unregistering the top level sysfs entry makes future attempts to reload the btrfs module impossible and the following is reported in dmesg: [ 2246.451296] WARNING: CPU: 3 PID: 10999 at fs/sysfs/dir.c:486 sysfs_warn_dup+0x91/0xb0() [ 2246.451298] sysfs: cannot create duplicate filename '/fs/btrfs' [ 2246.451298] Modules linked in: btrfs(+) raid6_pq xor bnep rfcomm bluetooth binfmt_misc nfsd auth_rpcgss oid_registry nfs_acl nfs lockd fscache sunrpc parport_pc parport psmouse serio_raw pcspkr evbug i2c_piix4 e1000 floppy [last unloaded: btrfs] [ 2246.451310] CPU: 3 PID: 10999 Comm: modprobe Tainted: G W 3.13.0-fdm-btrfs-next-24+ #7 [ 2246.451311] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 [ 2246.451312] 0000000000000009 ffff8800d353fa08 ffffffff816f1da6 0000000000000410 [ 2246.451314] ffff8800d353fa58 ffff8800d353fa48 ffffffff8104a32c ffff88020821a290 [ 2246.451316] ffff88020821a290 ffff88020821a290 ffff8802148f0000 ffff8800d353fb80 [ 2246.451318] Call Trace: [ 2246.451322] [<ffffffff816f1da6>] dump_stack+0x4e/0x68 [ 2246.451324] [<ffffffff8104a32c>] warn_slowpath_common+0x8c/0xc0 [ 2246.451325] [<ffffffff8104a416>] warn_slowpath_fmt+0x46/0x50 [ 2246.451328] [<ffffffff81367dc5>] ? strlcat+0x65/0x90 (....) This fixes the following change: btrfs: add simple debugfs interface commit 1bae30982bc86ab66d61ccb6e22792593b45d44d Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
2015-01-23 18:27:00 +00:00
return 0;
out_remove_group:
sysfs_remove_group(&btrfs_kset->kobj, &btrfs_feature_attr_group);
Btrfs: add missing cleanup on sysfs init failure If we failed during initialization of sysfs, we weren't unregistering the top level btrfs sysfs entry nor the debugfs stuff. Not unregistering the top level sysfs entry makes future attempts to reload the btrfs module impossible and the following is reported in dmesg: [ 2246.451296] WARNING: CPU: 3 PID: 10999 at fs/sysfs/dir.c:486 sysfs_warn_dup+0x91/0xb0() [ 2246.451298] sysfs: cannot create duplicate filename '/fs/btrfs' [ 2246.451298] Modules linked in: btrfs(+) raid6_pq xor bnep rfcomm bluetooth binfmt_misc nfsd auth_rpcgss oid_registry nfs_acl nfs lockd fscache sunrpc parport_pc parport psmouse serio_raw pcspkr evbug i2c_piix4 e1000 floppy [last unloaded: btrfs] [ 2246.451310] CPU: 3 PID: 10999 Comm: modprobe Tainted: G W 3.13.0-fdm-btrfs-next-24+ #7 [ 2246.451311] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 [ 2246.451312] 0000000000000009 ffff8800d353fa08 ffffffff816f1da6 0000000000000410 [ 2246.451314] ffff8800d353fa58 ffff8800d353fa48 ffffffff8104a32c ffff88020821a290 [ 2246.451316] ffff88020821a290 ffff88020821a290 ffff8802148f0000 ffff8800d353fb80 [ 2246.451318] Call Trace: [ 2246.451322] [<ffffffff816f1da6>] dump_stack+0x4e/0x68 [ 2246.451324] [<ffffffff8104a32c>] warn_slowpath_common+0x8c/0xc0 [ 2246.451325] [<ffffffff8104a416>] warn_slowpath_fmt+0x46/0x50 [ 2246.451328] [<ffffffff81367dc5>] ? strlcat+0x65/0x90 (....) This fixes the following change: btrfs: add simple debugfs interface commit 1bae30982bc86ab66d61ccb6e22792593b45d44d Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
2015-01-23 18:27:00 +00:00
out2:
kset_unregister(btrfs_kset);
return ret;
}
void __cold btrfs_exit_sysfs(void)
{
sysfs_unmerge_group(&btrfs_kset->kobj,
&btrfs_static_feature_attr_group);
sysfs_remove_group(&btrfs_kset->kobj, &btrfs_feature_attr_group);
#ifdef CONFIG_BTRFS_DEBUG
sysfs_remove_group(&btrfs_kset->kobj, &btrfs_debug_feature_attr_group);
#endif
kset_unregister(btrfs_kset);
}