76c3819639
[ Upstream commit a47bd78d0c44621efb98b525d04d60dc4d1a79b0 ] 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> Signed-off-by: Sasha Levin <sashal@kernel.org>
966 lines
24 KiB
C
966 lines
24 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* Copyright (C) 2007 Oracle. All rights reserved.
|
|
*/
|
|
|
|
#include <linux/sched.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/spinlock.h>
|
|
#include <linux/completion.h>
|
|
#include <linux/kobject.h>
|
|
#include <linux/bug.h>
|
|
#include <linux/debugfs.h>
|
|
#include <linux/sched/mm.h>
|
|
|
|
#include "ctree.h"
|
|
#include "disk-io.h"
|
|
#include "transaction.h"
|
|
#include "sysfs.h"
|
|
#include "volumes.h"
|
|
|
|
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 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 snprintf(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_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_COMPAT_RO(free_space_tree, FREE_SPACE_TREE);
|
|
|
|
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_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(free_space_tree),
|
|
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 snprintf(buf, PAGE_SIZE, "0\n");
|
|
}
|
|
BTRFS_ATTR(static_feature, rmdir_subvol, rmdir_subvol_show);
|
|
|
|
static struct attribute *btrfs_supported_static_feature_attrs[] = {
|
|
BTRFS_ATTR_PTR(static_feature, rmdir_subvol),
|
|
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,
|
|
};
|
|
|
|
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 snprintf(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_cache *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->key.offset;
|
|
else
|
|
val += btrfs_block_group_used(&block_group->item);
|
|
}
|
|
up_read(&sinfo->groups_sem);
|
|
return snprintf(buf, PAGE_SIZE, "%llu\n", val);
|
|
}
|
|
|
|
static struct attribute *raid_attributes[] = {
|
|
BTRFS_ATTR_PTR(raid, total_bytes),
|
|
BTRFS_ATTR_PTR(raid, used_bytes),
|
|
NULL
|
|
};
|
|
|
|
static void release_raid_kobj(struct kobject *kobj)
|
|
{
|
|
kfree(to_raid_kobj(kobj));
|
|
}
|
|
|
|
struct kobj_type btrfs_raid_ktype = {
|
|
.sysfs_ops = &kobj_sysfs_ops,
|
|
.release = release_raid_kobj,
|
|
.default_attrs = raid_attributes,
|
|
};
|
|
|
|
#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 snprintf(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,
|
|
};
|
|
|
|
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);
|
|
}
|
|
|
|
struct kobj_type space_info_ktype = {
|
|
.sysfs_ops = &kobj_sysfs_ops,
|
|
.release = space_info_release,
|
|
.default_attrs = space_info_attrs,
|
|
};
|
|
|
|
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 = snprintf(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 snprintf(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 snprintf(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 snprintf(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 snprintf(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 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),
|
|
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->device_dir_kobj) {
|
|
kobject_del(fs_devs->device_dir_kobj);
|
|
kobject_put(fs_devs->device_dir_kobj);
|
|
fs_devs->device_dir_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)
|
|
{
|
|
btrfs_reset_fs_info_ptr(fs_info);
|
|
|
|
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);
|
|
}
|
|
addrm_unknown_feature_attrs(fs_info, false);
|
|
sysfs_remove_group(&fs_info->fs_devices->fsid_kobj, &btrfs_feature_attr_group);
|
|
sysfs_remove_files(&fs_info->fs_devices->fsid_kobj, btrfs_attrs);
|
|
btrfs_sysfs_rm_device_link(fs_info->fs_devices, NULL);
|
|
}
|
|
|
|
const char * const btrfs_feature_set_names[FEAT_MAX] = {
|
|
[FEAT_COMPAT] = "compat",
|
|
[FEAT_COMPAT_RO] = "compat_ro",
|
|
[FEAT_INCOMPAT] = "incompat",
|
|
};
|
|
|
|
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 += snprintf(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;
|
|
}
|
|
}
|
|
}
|
|
|
|
/* when one_device is NULL, it removes all device links */
|
|
|
|
int btrfs_sysfs_rm_device_link(struct btrfs_fs_devices *fs_devices,
|
|
struct btrfs_device *one_device)
|
|
{
|
|
struct hd_struct *disk;
|
|
struct kobject *disk_kobj;
|
|
|
|
if (!fs_devices->device_dir_kobj)
|
|
return -EINVAL;
|
|
|
|
if (one_device && one_device->bdev) {
|
|
disk = one_device->bdev->bd_part;
|
|
disk_kobj = &part_to_dev(disk)->kobj;
|
|
|
|
sysfs_remove_link(fs_devices->device_dir_kobj,
|
|
disk_kobj->name);
|
|
}
|
|
|
|
if (one_device)
|
|
return 0;
|
|
|
|
list_for_each_entry(one_device,
|
|
&fs_devices->devices, dev_list) {
|
|
if (!one_device->bdev)
|
|
continue;
|
|
disk = one_device->bdev->bd_part;
|
|
disk_kobj = &part_to_dev(disk)->kobj;
|
|
|
|
sysfs_remove_link(fs_devices->device_dir_kobj,
|
|
disk_kobj->name);
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
int btrfs_sysfs_add_device(struct btrfs_fs_devices *fs_devs)
|
|
{
|
|
if (!fs_devs->device_dir_kobj)
|
|
fs_devs->device_dir_kobj = kobject_create_and_add("devices",
|
|
&fs_devs->fsid_kobj);
|
|
|
|
if (!fs_devs->device_dir_kobj)
|
|
return -ENOMEM;
|
|
|
|
return 0;
|
|
}
|
|
|
|
int btrfs_sysfs_add_device_link(struct btrfs_fs_devices *fs_devices,
|
|
struct btrfs_device *one_device)
|
|
{
|
|
int error = 0;
|
|
struct btrfs_device *dev;
|
|
unsigned int nofs_flag;
|
|
|
|
nofs_flag = memalloc_nofs_save();
|
|
list_for_each_entry(dev, &fs_devices->devices, dev_list) {
|
|
struct hd_struct *disk;
|
|
struct kobject *disk_kobj;
|
|
|
|
if (!dev->bdev)
|
|
continue;
|
|
|
|
if (one_device && one_device != dev)
|
|
continue;
|
|
|
|
disk = dev->bdev->bd_part;
|
|
disk_kobj = &part_to_dev(disk)->kobj;
|
|
|
|
error = sysfs_create_link(fs_devices->device_dir_kobj,
|
|
disk_kobj, disk_kobj->name);
|
|
if (error)
|
|
break;
|
|
}
|
|
memalloc_nofs_restore(nofs_flag);
|
|
|
|
return error;
|
|
}
|
|
|
|
/* /sys/fs/btrfs/ entry */
|
|
static struct kset *btrfs_kset;
|
|
|
|
/* /sys/kernel/debug/btrfs */
|
|
static struct dentry *btrfs_debugfs_root_dentry;
|
|
|
|
/* Debugging tunables and exported data */
|
|
u64 btrfs_debugfs_test;
|
|
|
|
/*
|
|
* Can be called by the device discovery thread.
|
|
* And parent can be specified for seed device
|
|
*/
|
|
int btrfs_sysfs_add_fsid(struct btrfs_fs_devices *fs_devs,
|
|
struct kobject *parent)
|
|
{
|
|
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, parent, "%pU", fs_devs->fsid);
|
|
if (error) {
|
|
kobject_put(&fs_devs->fsid_kobj);
|
|
return error;
|
|
}
|
|
|
|
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;
|
|
|
|
btrfs_set_fs_info_ptr(fs_info);
|
|
|
|
error = btrfs_sysfs_add_device_link(fs_devs, NULL);
|
|
if (error)
|
|
return error;
|
|
|
|
error = sysfs_create_files(fsid_kobj, btrfs_attrs);
|
|
if (error) {
|
|
btrfs_sysfs_rm_device_link(fs_devs, NULL);
|
|
return error;
|
|
}
|
|
|
|
error = sysfs_create_group(fsid_kobj,
|
|
&btrfs_feature_attr_group);
|
|
if (error)
|
|
goto failure;
|
|
|
|
error = addrm_unknown_feature_attrs(fs_info, true);
|
|
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;
|
|
}
|
|
|
|
|
|
/*
|
|
* 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 features;
|
|
int ret;
|
|
|
|
if (!fs_info)
|
|
return;
|
|
|
|
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);
|
|
}
|
|
|
|
static int btrfs_init_debugfs(void)
|
|
{
|
|
#ifdef CONFIG_DEBUG_FS
|
|
btrfs_debugfs_root_dentry = debugfs_create_dir("btrfs", NULL);
|
|
if (!btrfs_debugfs_root_dentry)
|
|
return -ENOMEM;
|
|
|
|
/*
|
|
* Example code, how to export data through debugfs.
|
|
*
|
|
* file: /sys/kernel/debug/btrfs/test
|
|
* contents of: btrfs_debugfs_test
|
|
*/
|
|
#ifdef CONFIG_BTRFS_DEBUG
|
|
debugfs_create_u64("test", S_IRUGO | S_IWUSR, btrfs_debugfs_root_dentry,
|
|
&btrfs_debugfs_test);
|
|
#endif
|
|
|
|
#endif
|
|
return 0;
|
|
}
|
|
|
|
int __init btrfs_init_sysfs(void)
|
|
{
|
|
int ret;
|
|
|
|
btrfs_kset = kset_create_and_add("btrfs", NULL, fs_kobj);
|
|
if (!btrfs_kset)
|
|
return -ENOMEM;
|
|
|
|
ret = btrfs_init_debugfs();
|
|
if (ret)
|
|
goto out1;
|
|
|
|
init_feature_attrs();
|
|
ret = sysfs_create_group(&btrfs_kset->kobj, &btrfs_feature_attr_group);
|
|
if (ret)
|
|
goto out2;
|
|
ret = sysfs_merge_group(&btrfs_kset->kobj,
|
|
&btrfs_static_feature_attr_group);
|
|
if (ret)
|
|
goto out_remove_group;
|
|
|
|
return 0;
|
|
|
|
out_remove_group:
|
|
sysfs_remove_group(&btrfs_kset->kobj, &btrfs_feature_attr_group);
|
|
out2:
|
|
debugfs_remove_recursive(btrfs_debugfs_root_dentry);
|
|
out1:
|
|
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);
|
|
kset_unregister(btrfs_kset);
|
|
debugfs_remove_recursive(btrfs_debugfs_root_dentry);
|
|
}
|
|
|