linux/fs/btrfs/fs.c

228 lines
6.3 KiB
C
Raw Permalink Normal View History

// SPDX-License-Identifier: GPL-2.0
#include "messages.h"
#include "fs.h"
#include "accessors.h"
#include "volumes.h"
static const struct btrfs_csums {
u16 size;
const char name[10];
const char driver[12];
} btrfs_csums[] = {
[BTRFS_CSUM_TYPE_CRC32] = { .size = 4, .name = "crc32c" },
[BTRFS_CSUM_TYPE_XXHASH] = { .size = 8, .name = "xxhash64" },
[BTRFS_CSUM_TYPE_SHA256] = { .size = 32, .name = "sha256" },
[BTRFS_CSUM_TYPE_BLAKE2] = { .size = 32, .name = "blake2b",
.driver = "blake2b-256" },
};
/* This exists for btrfs-progs usages. */
u16 btrfs_csum_type_size(u16 type)
{
return btrfs_csums[type].size;
}
int btrfs_super_csum_size(const struct btrfs_super_block *s)
{
u16 t = btrfs_super_csum_type(s);
/* csum type is validated at mount time. */
return btrfs_csum_type_size(t);
}
const char *btrfs_super_csum_name(u16 csum_type)
{
/* csum type is validated at mount time. */
return btrfs_csums[csum_type].name;
}
/*
* Return driver name if defined, otherwise the name that's also a valid driver
* name.
*/
const char *btrfs_super_csum_driver(u16 csum_type)
{
/* csum type is validated at mount time */
return btrfs_csums[csum_type].driver[0] ?
btrfs_csums[csum_type].driver :
btrfs_csums[csum_type].name;
}
size_t __attribute_const__ btrfs_get_num_csums(void)
{
return ARRAY_SIZE(btrfs_csums);
}
/*
* Start exclusive operation @type, return true on success.
*/
bool btrfs_exclop_start(struct btrfs_fs_info *fs_info,
enum btrfs_exclusive_operation type)
{
bool ret = false;
spin_lock(&fs_info->super_lock);
if (fs_info->exclusive_operation == BTRFS_EXCLOP_NONE) {
fs_info->exclusive_operation = type;
ret = true;
}
spin_unlock(&fs_info->super_lock);
return ret;
}
/*
* Conditionally allow to enter the exclusive operation in case it's compatible
* with the running one. This must be paired with btrfs_exclop_start_unlock()
* and btrfs_exclop_finish().
*
* Compatibility:
* - the same type is already running
* - when trying to add a device and balance has been paused
* - not BTRFS_EXCLOP_NONE - this is intentionally incompatible and the caller
* must check the condition first that would allow none -> @type
*/
bool btrfs_exclop_start_try_lock(struct btrfs_fs_info *fs_info,
enum btrfs_exclusive_operation type)
{
spin_lock(&fs_info->super_lock);
if (fs_info->exclusive_operation == type ||
(fs_info->exclusive_operation == BTRFS_EXCLOP_BALANCE_PAUSED &&
type == BTRFS_EXCLOP_DEV_ADD))
return true;
spin_unlock(&fs_info->super_lock);
return false;
}
void btrfs_exclop_start_unlock(struct btrfs_fs_info *fs_info)
{
spin_unlock(&fs_info->super_lock);
}
void btrfs_exclop_finish(struct btrfs_fs_info *fs_info)
{
spin_lock(&fs_info->super_lock);
WRITE_ONCE(fs_info->exclusive_operation, BTRFS_EXCLOP_NONE);
spin_unlock(&fs_info->super_lock);
sysfs_notify(&fs_info->fs_devices->fsid_kobj, NULL, "exclusive_operation");
}
void btrfs_exclop_balance(struct btrfs_fs_info *fs_info,
enum btrfs_exclusive_operation op)
{
switch (op) {
case BTRFS_EXCLOP_BALANCE_PAUSED:
spin_lock(&fs_info->super_lock);
ASSERT(fs_info->exclusive_operation == BTRFS_EXCLOP_BALANCE ||
fs_info->exclusive_operation == BTRFS_EXCLOP_DEV_ADD ||
fs_info->exclusive_operation == BTRFS_EXCLOP_NONE ||
fs_info->exclusive_operation == BTRFS_EXCLOP_BALANCE_PAUSED);
fs_info->exclusive_operation = BTRFS_EXCLOP_BALANCE_PAUSED;
spin_unlock(&fs_info->super_lock);
break;
case BTRFS_EXCLOP_BALANCE:
spin_lock(&fs_info->super_lock);
ASSERT(fs_info->exclusive_operation == BTRFS_EXCLOP_BALANCE_PAUSED);
fs_info->exclusive_operation = BTRFS_EXCLOP_BALANCE;
spin_unlock(&fs_info->super_lock);
break;
default:
btrfs_warn(fs_info,
"invalid exclop balance operation %d requested", op);
}
}
void __btrfs_set_fs_incompat(struct btrfs_fs_info *fs_info, u64 flag,
const char *name)
{
struct btrfs_super_block *disk_super;
u64 features;
disk_super = fs_info->super_copy;
features = btrfs_super_incompat_flags(disk_super);
if (!(features & flag)) {
spin_lock(&fs_info->super_lock);
features = btrfs_super_incompat_flags(disk_super);
if (!(features & flag)) {
features |= flag;
btrfs_set_super_incompat_flags(disk_super, features);
btrfs_info(fs_info,
"setting incompat feature flag for %s (0x%llx)",
name, flag);
}
spin_unlock(&fs_info->super_lock);
btrfs: sysfs: update fs features directory asynchronously [BUG] Since the introduction of per-fs feature sysfs interface (/sys/fs/btrfs/<UUID>/features/), the content of that directory is never updated. Thus for the following case, that directory will not show the new features like RAID56: # mkfs.btrfs -f $dev1 $dev2 $dev3 # mount $dev1 $mnt # btrfs balance start -f -mconvert=raid5 $mnt # ls /sys/fs/btrfs/$uuid/features/ extended_iref free_space_tree no_holes skinny_metadata While after unmount and mount, we got the correct features: # umount $mnt # mount $dev1 $mnt # ls /sys/fs/btrfs/$uuid/features/ extended_iref free_space_tree no_holes raid56 skinny_metadata [CAUSE] Because we never really try to update the content of per-fs features/ directory. We had an attempt to update the features directory dynamically in commit 14e46e04958d ("btrfs: synchronize incompat feature bits with sysfs files"), but unfortunately it get reverted in commit e410e34fad91 ("Revert "btrfs: synchronize incompat feature bits with sysfs files""). The problem in the original patch is, in the context of btrfs_create_chunk(), we can not afford to update the sysfs group. The exported but never utilized function, btrfs_sysfs_feature_update() is the leftover of such attempt. As even if we go sysfs_update_group(), new files will need extra memory allocation, and we have no way to specify the sysfs update to go GFP_NOFS. [FIX] This patch will address the old problem by doing asynchronous sysfs update in the cleaner thread. This involves the following changes: - Make __btrfs_(set|clear)_fs_(incompat|compat_ro) helpers to set BTRFS_FS_FEATURE_CHANGED flag when needed - Update btrfs_sysfs_feature_update() to use sysfs_update_group() And drop unnecessary arguments. - Call btrfs_sysfs_feature_update() in cleaner_kthread If we have the BTRFS_FS_FEATURE_CHANGED flag set. - Wake up cleaner_kthread in btrfs_commit_transaction if we have BTRFS_FS_FEATURE_CHANGED flag By this, all the previously dangerous call sites like btrfs_create_chunk() need no new changes, as above helpers would have already set the BTRFS_FS_FEATURE_CHANGED flag. The real work happens at cleaner_kthread, thus we pay the cost of delaying the update to sysfs directory, but the delayed time should be small enough that end user can not distinguish though it might get delayed if the cleaner thread is busy with removing subvolumes or defrag. CC: stable@vger.kernel.org # 4.14+ Reviewed-by: Anand Jain <anand.jain@oracle.com> Signed-off-by: Qu Wenruo <wqu@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2023-01-13 19:11:39 +08:00
set_bit(BTRFS_FS_FEATURE_CHANGED, &fs_info->flags);
}
}
void __btrfs_clear_fs_incompat(struct btrfs_fs_info *fs_info, u64 flag,
const char *name)
{
struct btrfs_super_block *disk_super;
u64 features;
disk_super = fs_info->super_copy;
features = btrfs_super_incompat_flags(disk_super);
if (features & flag) {
spin_lock(&fs_info->super_lock);
features = btrfs_super_incompat_flags(disk_super);
if (features & flag) {
features &= ~flag;
btrfs_set_super_incompat_flags(disk_super, features);
btrfs_info(fs_info,
"clearing incompat feature flag for %s (0x%llx)",
name, flag);
}
spin_unlock(&fs_info->super_lock);
btrfs: sysfs: update fs features directory asynchronously [BUG] Since the introduction of per-fs feature sysfs interface (/sys/fs/btrfs/<UUID>/features/), the content of that directory is never updated. Thus for the following case, that directory will not show the new features like RAID56: # mkfs.btrfs -f $dev1 $dev2 $dev3 # mount $dev1 $mnt # btrfs balance start -f -mconvert=raid5 $mnt # ls /sys/fs/btrfs/$uuid/features/ extended_iref free_space_tree no_holes skinny_metadata While after unmount and mount, we got the correct features: # umount $mnt # mount $dev1 $mnt # ls /sys/fs/btrfs/$uuid/features/ extended_iref free_space_tree no_holes raid56 skinny_metadata [CAUSE] Because we never really try to update the content of per-fs features/ directory. We had an attempt to update the features directory dynamically in commit 14e46e04958d ("btrfs: synchronize incompat feature bits with sysfs files"), but unfortunately it get reverted in commit e410e34fad91 ("Revert "btrfs: synchronize incompat feature bits with sysfs files""). The problem in the original patch is, in the context of btrfs_create_chunk(), we can not afford to update the sysfs group. The exported but never utilized function, btrfs_sysfs_feature_update() is the leftover of such attempt. As even if we go sysfs_update_group(), new files will need extra memory allocation, and we have no way to specify the sysfs update to go GFP_NOFS. [FIX] This patch will address the old problem by doing asynchronous sysfs update in the cleaner thread. This involves the following changes: - Make __btrfs_(set|clear)_fs_(incompat|compat_ro) helpers to set BTRFS_FS_FEATURE_CHANGED flag when needed - Update btrfs_sysfs_feature_update() to use sysfs_update_group() And drop unnecessary arguments. - Call btrfs_sysfs_feature_update() in cleaner_kthread If we have the BTRFS_FS_FEATURE_CHANGED flag set. - Wake up cleaner_kthread in btrfs_commit_transaction if we have BTRFS_FS_FEATURE_CHANGED flag By this, all the previously dangerous call sites like btrfs_create_chunk() need no new changes, as above helpers would have already set the BTRFS_FS_FEATURE_CHANGED flag. The real work happens at cleaner_kthread, thus we pay the cost of delaying the update to sysfs directory, but the delayed time should be small enough that end user can not distinguish though it might get delayed if the cleaner thread is busy with removing subvolumes or defrag. CC: stable@vger.kernel.org # 4.14+ Reviewed-by: Anand Jain <anand.jain@oracle.com> Signed-off-by: Qu Wenruo <wqu@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2023-01-13 19:11:39 +08:00
set_bit(BTRFS_FS_FEATURE_CHANGED, &fs_info->flags);
}
}
void __btrfs_set_fs_compat_ro(struct btrfs_fs_info *fs_info, u64 flag,
const char *name)
{
struct btrfs_super_block *disk_super;
u64 features;
disk_super = fs_info->super_copy;
features = btrfs_super_compat_ro_flags(disk_super);
if (!(features & flag)) {
spin_lock(&fs_info->super_lock);
features = btrfs_super_compat_ro_flags(disk_super);
if (!(features & flag)) {
features |= flag;
btrfs_set_super_compat_ro_flags(disk_super, features);
btrfs_info(fs_info,
"setting compat-ro feature flag for %s (0x%llx)",
name, flag);
}
spin_unlock(&fs_info->super_lock);
btrfs: sysfs: update fs features directory asynchronously [BUG] Since the introduction of per-fs feature sysfs interface (/sys/fs/btrfs/<UUID>/features/), the content of that directory is never updated. Thus for the following case, that directory will not show the new features like RAID56: # mkfs.btrfs -f $dev1 $dev2 $dev3 # mount $dev1 $mnt # btrfs balance start -f -mconvert=raid5 $mnt # ls /sys/fs/btrfs/$uuid/features/ extended_iref free_space_tree no_holes skinny_metadata While after unmount and mount, we got the correct features: # umount $mnt # mount $dev1 $mnt # ls /sys/fs/btrfs/$uuid/features/ extended_iref free_space_tree no_holes raid56 skinny_metadata [CAUSE] Because we never really try to update the content of per-fs features/ directory. We had an attempt to update the features directory dynamically in commit 14e46e04958d ("btrfs: synchronize incompat feature bits with sysfs files"), but unfortunately it get reverted in commit e410e34fad91 ("Revert "btrfs: synchronize incompat feature bits with sysfs files""). The problem in the original patch is, in the context of btrfs_create_chunk(), we can not afford to update the sysfs group. The exported but never utilized function, btrfs_sysfs_feature_update() is the leftover of such attempt. As even if we go sysfs_update_group(), new files will need extra memory allocation, and we have no way to specify the sysfs update to go GFP_NOFS. [FIX] This patch will address the old problem by doing asynchronous sysfs update in the cleaner thread. This involves the following changes: - Make __btrfs_(set|clear)_fs_(incompat|compat_ro) helpers to set BTRFS_FS_FEATURE_CHANGED flag when needed - Update btrfs_sysfs_feature_update() to use sysfs_update_group() And drop unnecessary arguments. - Call btrfs_sysfs_feature_update() in cleaner_kthread If we have the BTRFS_FS_FEATURE_CHANGED flag set. - Wake up cleaner_kthread in btrfs_commit_transaction if we have BTRFS_FS_FEATURE_CHANGED flag By this, all the previously dangerous call sites like btrfs_create_chunk() need no new changes, as above helpers would have already set the BTRFS_FS_FEATURE_CHANGED flag. The real work happens at cleaner_kthread, thus we pay the cost of delaying the update to sysfs directory, but the delayed time should be small enough that end user can not distinguish though it might get delayed if the cleaner thread is busy with removing subvolumes or defrag. CC: stable@vger.kernel.org # 4.14+ Reviewed-by: Anand Jain <anand.jain@oracle.com> Signed-off-by: Qu Wenruo <wqu@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2023-01-13 19:11:39 +08:00
set_bit(BTRFS_FS_FEATURE_CHANGED, &fs_info->flags);
}
}
void __btrfs_clear_fs_compat_ro(struct btrfs_fs_info *fs_info, u64 flag,
const char *name)
{
struct btrfs_super_block *disk_super;
u64 features;
disk_super = fs_info->super_copy;
features = btrfs_super_compat_ro_flags(disk_super);
if (features & flag) {
spin_lock(&fs_info->super_lock);
features = btrfs_super_compat_ro_flags(disk_super);
if (features & flag) {
features &= ~flag;
btrfs_set_super_compat_ro_flags(disk_super, features);
btrfs_info(fs_info,
"clearing compat-ro feature flag for %s (0x%llx)",
name, flag);
}
spin_unlock(&fs_info->super_lock);
btrfs: sysfs: update fs features directory asynchronously [BUG] Since the introduction of per-fs feature sysfs interface (/sys/fs/btrfs/<UUID>/features/), the content of that directory is never updated. Thus for the following case, that directory will not show the new features like RAID56: # mkfs.btrfs -f $dev1 $dev2 $dev3 # mount $dev1 $mnt # btrfs balance start -f -mconvert=raid5 $mnt # ls /sys/fs/btrfs/$uuid/features/ extended_iref free_space_tree no_holes skinny_metadata While after unmount and mount, we got the correct features: # umount $mnt # mount $dev1 $mnt # ls /sys/fs/btrfs/$uuid/features/ extended_iref free_space_tree no_holes raid56 skinny_metadata [CAUSE] Because we never really try to update the content of per-fs features/ directory. We had an attempt to update the features directory dynamically in commit 14e46e04958d ("btrfs: synchronize incompat feature bits with sysfs files"), but unfortunately it get reverted in commit e410e34fad91 ("Revert "btrfs: synchronize incompat feature bits with sysfs files""). The problem in the original patch is, in the context of btrfs_create_chunk(), we can not afford to update the sysfs group. The exported but never utilized function, btrfs_sysfs_feature_update() is the leftover of such attempt. As even if we go sysfs_update_group(), new files will need extra memory allocation, and we have no way to specify the sysfs update to go GFP_NOFS. [FIX] This patch will address the old problem by doing asynchronous sysfs update in the cleaner thread. This involves the following changes: - Make __btrfs_(set|clear)_fs_(incompat|compat_ro) helpers to set BTRFS_FS_FEATURE_CHANGED flag when needed - Update btrfs_sysfs_feature_update() to use sysfs_update_group() And drop unnecessary arguments. - Call btrfs_sysfs_feature_update() in cleaner_kthread If we have the BTRFS_FS_FEATURE_CHANGED flag set. - Wake up cleaner_kthread in btrfs_commit_transaction if we have BTRFS_FS_FEATURE_CHANGED flag By this, all the previously dangerous call sites like btrfs_create_chunk() need no new changes, as above helpers would have already set the BTRFS_FS_FEATURE_CHANGED flag. The real work happens at cleaner_kthread, thus we pay the cost of delaying the update to sysfs directory, but the delayed time should be small enough that end user can not distinguish though it might get delayed if the cleaner thread is busy with removing subvolumes or defrag. CC: stable@vger.kernel.org # 4.14+ Reviewed-by: Anand Jain <anand.jain@oracle.com> Signed-off-by: Qu Wenruo <wqu@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2023-01-13 19:11:39 +08:00
set_bit(BTRFS_FS_FEATURE_CHANGED, &fs_info->flags);
}
}