linux-stable/fs/btrfs/block-group.h
Filipe Manana 79bd37120b btrfs: rework chunk allocation to avoid exhaustion of the system chunk array
Commit eafa4fd0ad ("btrfs: fix exhaustion of the system chunk array
due to concurrent allocations") fixed a problem that resulted in
exhausting the system chunk array in the superblock when there are many
tasks allocating chunks in parallel. Basically too many tasks enter the
first phase of chunk allocation without previous tasks having finished
their second phase of allocation, resulting in too many system chunks
being allocated. That was originally observed when running the fallocate
tests of stress-ng on a PowerPC machine, using a node size of 64K.

However that commit also introduced a deadlock where a task in phase 1 of
the chunk allocation waited for another task that had allocated a system
chunk to finish its phase 2, but that other task was waiting on an extent
buffer lock held by the first task, therefore resulting in both tasks not
making any progress. That change was later reverted by a patch with the
subject "btrfs: fix deadlock with concurrent chunk allocations involving
system chunks", since there is no simple and short solution to address it
and the deadlock is relatively easy to trigger on zoned filesystems, while
the system chunk array exhaustion is not so common.

This change reworks the chunk allocation to avoid the system chunk array
exhaustion. It accomplishes that by making the first phase of chunk
allocation do the updates of the device items in the chunk btree and the
insertion of the new chunk item in the chunk btree. This is done while
under the protection of the chunk mutex (fs_info->chunk_mutex), in the
same critical section that checks for available system space, allocates
a new system chunk if needed and reserves system chunk space. This way
we do not have chunk space reserved until the second phase completes.

The same logic is applied to chunk removal as well, since it keeps
reserved system space long after it is done updating the chunk btree.

For direct allocation of system chunks, the previous behaviour remains,
because otherwise we would deadlock on extent buffers of the chunk btree.
Changes to the chunk btree are by large done by chunk allocation and chunk
removal, which first reserve chunk system space and then later do changes
to the chunk btree. The other remaining cases are uncommon and correspond
to adding a device, removing a device and resizing a device. All these
other cases do not pre-reserve system space, they modify the chunk btree
right away, so they don't hold reserved space for a long period like chunk
allocation and chunk removal do.

The diff of this change is huge, but more than half of it is just addition
of comments describing both how things work regarding chunk allocation and
removal, including both the new behavior and the parts of the old behavior
that did not change.

CC: stable@vger.kernel.org # 5.12+
Tested-by: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Tested-by: Naohiro Aota <naohiro.aota@wdc.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Tested-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-07 17:42:41 +02:00

329 lines
11 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef BTRFS_BLOCK_GROUP_H
#define BTRFS_BLOCK_GROUP_H
#include "free-space-cache.h"
enum btrfs_disk_cache_state {
BTRFS_DC_WRITTEN,
BTRFS_DC_ERROR,
BTRFS_DC_CLEAR,
BTRFS_DC_SETUP,
};
/*
* This describes the state of the block_group for async discard. This is due
* to the two pass nature of it where extent discarding is prioritized over
* bitmap discarding. BTRFS_DISCARD_RESET_CURSOR is set when we are resetting
* between lists to prevent contention for discard state variables
* (eg. discard_cursor).
*/
enum btrfs_discard_state {
BTRFS_DISCARD_EXTENTS,
BTRFS_DISCARD_BITMAPS,
BTRFS_DISCARD_RESET_CURSOR,
};
/*
* Control flags for do_chunk_alloc's force field CHUNK_ALLOC_NO_FORCE means to
* only allocate a chunk if we really need one.
*
* CHUNK_ALLOC_LIMITED means to only try and allocate one if we have very few
* chunks already allocated. This is used as part of the clustering code to
* help make sure we have a good pool of storage to cluster in, without filling
* the FS with empty chunks
*
* CHUNK_ALLOC_FORCE means it must try to allocate one
*/
enum btrfs_chunk_alloc_enum {
CHUNK_ALLOC_NO_FORCE,
CHUNK_ALLOC_LIMITED,
CHUNK_ALLOC_FORCE,
};
struct btrfs_caching_control {
struct list_head list;
struct mutex mutex;
wait_queue_head_t wait;
struct btrfs_work work;
struct btrfs_block_group *block_group;
u64 progress;
refcount_t count;
};
/* Once caching_thread() finds this much free space, it will wake up waiters. */
#define CACHING_CTL_WAKE_UP SZ_2M
struct btrfs_block_group {
struct btrfs_fs_info *fs_info;
struct inode *inode;
spinlock_t lock;
u64 start;
u64 length;
u64 pinned;
u64 reserved;
u64 used;
u64 delalloc_bytes;
u64 bytes_super;
u64 flags;
u64 cache_generation;
/*
* If the free space extent count exceeds this number, convert the block
* group to bitmaps.
*/
u32 bitmap_high_thresh;
/*
* If the free space extent count drops below this number, convert the
* block group back to extents.
*/
u32 bitmap_low_thresh;
/*
* It is just used for the delayed data space allocation because
* only the data space allocation and the relative metadata update
* can be done cross the transaction.
*/
struct rw_semaphore data_rwsem;
/* For raid56, this is a full stripe, without parity */
unsigned long full_stripe_len;
unsigned int ro;
unsigned int iref:1;
unsigned int has_caching_ctl:1;
unsigned int removed:1;
unsigned int to_copy:1;
unsigned int relocating_repair:1;
unsigned int chunk_item_inserted:1;
int disk_cache_state;
/* Cache tracking stuff */
int cached;
struct btrfs_caching_control *caching_ctl;
u64 last_byte_to_unpin;
struct btrfs_space_info *space_info;
/* Free space cache stuff */
struct btrfs_free_space_ctl *free_space_ctl;
/* Block group cache stuff */
struct rb_node cache_node;
/* For block groups in the same raid type */
struct list_head list;
refcount_t refs;
/*
* List of struct btrfs_free_clusters for this block group.
* Today it will only have one thing on it, but that may change
*/
struct list_head cluster_list;
/* For delayed block group creation or deletion of empty block groups */
struct list_head bg_list;
/* For read-only block groups */
struct list_head ro_list;
/*
* When non-zero it means the block group's logical address and its
* device extents can not be reused for future block group allocations
* until the counter goes down to 0. This is to prevent them from being
* reused while some task is still using the block group after it was
* deleted - we want to make sure they can only be reused for new block
* groups after that task is done with the deleted block group.
*/
atomic_t frozen;
/* For discard operations */
struct list_head discard_list;
int discard_index;
u64 discard_eligible_time;
u64 discard_cursor;
enum btrfs_discard_state discard_state;
/* For dirty block groups */
struct list_head dirty_list;
struct list_head io_list;
struct btrfs_io_ctl io_ctl;
/*
* Incremented when doing extent allocations and holding a read lock
* on the space_info's groups_sem semaphore.
* Decremented when an ordered extent that represents an IO against this
* block group's range is created (after it's added to its inode's
* root's list of ordered extents) or immediately after the allocation
* if it's a metadata extent or fallocate extent (for these cases we
* don't create ordered extents).
*/
atomic_t reservations;
/*
* Incremented while holding the spinlock *lock* by a task checking if
* it can perform a nocow write (incremented if the value for the *ro*
* field is 0). Decremented by such tasks once they create an ordered
* extent or before that if some error happens before reaching that step.
* This is to prevent races between block group relocation and nocow
* writes through direct IO.
*/
atomic_t nocow_writers;
/* Lock for free space tree operations. */
struct mutex free_space_lock;
/*
* Does the block group need to be added to the free space tree?
* Protected by free_space_lock.
*/
int needs_free_space;
/* Flag indicating this block group is placed on a sequential zone */
bool seq_zone;
/*
* Number of extents in this block group used for swap files.
* All accesses protected by the spinlock 'lock'.
*/
int swap_extents;
/* Record locked full stripes for RAID5/6 block group */
struct btrfs_full_stripe_locks_tree full_stripe_locks_root;
/*
* Allocation offset for the block group to implement sequential
* allocation. This is used only on a zoned filesystem.
*/
u64 alloc_offset;
u64 zone_unusable;
u64 meta_write_pointer;
};
static inline u64 btrfs_block_group_end(struct btrfs_block_group *block_group)
{
return (block_group->start + block_group->length);
}
static inline bool btrfs_is_block_group_data_only(
struct btrfs_block_group *block_group)
{
/*
* In mixed mode the fragmentation is expected to be high, lowering the
* efficiency, so only proper data block groups are considered.
*/
return (block_group->flags & BTRFS_BLOCK_GROUP_DATA) &&
!(block_group->flags & BTRFS_BLOCK_GROUP_METADATA);
}
#ifdef CONFIG_BTRFS_DEBUG
static inline int btrfs_should_fragment_free_space(
struct btrfs_block_group *block_group)
{
struct btrfs_fs_info *fs_info = block_group->fs_info;
return (btrfs_test_opt(fs_info, FRAGMENT_METADATA) &&
block_group->flags & BTRFS_BLOCK_GROUP_METADATA) ||
(btrfs_test_opt(fs_info, FRAGMENT_DATA) &&
block_group->flags & BTRFS_BLOCK_GROUP_DATA);
}
#endif
struct btrfs_block_group *btrfs_lookup_first_block_group(
struct btrfs_fs_info *info, u64 bytenr);
struct btrfs_block_group *btrfs_lookup_block_group(
struct btrfs_fs_info *info, u64 bytenr);
struct btrfs_block_group *btrfs_next_block_group(
struct btrfs_block_group *cache);
void btrfs_get_block_group(struct btrfs_block_group *cache);
void btrfs_put_block_group(struct btrfs_block_group *cache);
void btrfs_dec_block_group_reservations(struct btrfs_fs_info *fs_info,
const u64 start);
void btrfs_wait_block_group_reservations(struct btrfs_block_group *bg);
bool btrfs_inc_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr);
void btrfs_dec_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr);
void btrfs_wait_nocow_writers(struct btrfs_block_group *bg);
void btrfs_wait_block_group_cache_progress(struct btrfs_block_group *cache,
u64 num_bytes);
int btrfs_wait_block_group_cache_done(struct btrfs_block_group *cache);
int btrfs_cache_block_group(struct btrfs_block_group *cache,
int load_cache_only);
void btrfs_put_caching_control(struct btrfs_caching_control *ctl);
struct btrfs_caching_control *btrfs_get_caching_control(
struct btrfs_block_group *cache);
u64 add_new_free_space(struct btrfs_block_group *block_group,
u64 start, u64 end);
struct btrfs_trans_handle *btrfs_start_trans_remove_block_group(
struct btrfs_fs_info *fs_info,
const u64 chunk_offset);
int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
u64 group_start, struct extent_map *em);
void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info);
void btrfs_mark_bg_unused(struct btrfs_block_group *bg);
void btrfs_reclaim_bgs_work(struct work_struct *work);
void btrfs_reclaim_bgs(struct btrfs_fs_info *fs_info);
void btrfs_mark_bg_to_reclaim(struct btrfs_block_group *bg);
int btrfs_read_block_groups(struct btrfs_fs_info *info);
struct btrfs_block_group *btrfs_make_block_group(struct btrfs_trans_handle *trans,
u64 bytes_used, u64 type,
u64 chunk_offset, u64 size);
void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans);
int btrfs_inc_block_group_ro(struct btrfs_block_group *cache,
bool do_chunk_alloc);
void btrfs_dec_block_group_ro(struct btrfs_block_group *cache);
int btrfs_start_dirty_block_groups(struct btrfs_trans_handle *trans);
int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans);
int btrfs_setup_space_cache(struct btrfs_trans_handle *trans);
int btrfs_update_block_group(struct btrfs_trans_handle *trans,
u64 bytenr, u64 num_bytes, int alloc);
int btrfs_add_reserved_bytes(struct btrfs_block_group *cache,
u64 ram_bytes, u64 num_bytes, int delalloc);
void btrfs_free_reserved_bytes(struct btrfs_block_group *cache,
u64 num_bytes, int delalloc);
int btrfs_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags,
enum btrfs_chunk_alloc_enum force);
int btrfs_force_chunk_alloc(struct btrfs_trans_handle *trans, u64 type);
void check_system_chunk(struct btrfs_trans_handle *trans, const u64 type);
u64 btrfs_get_alloc_profile(struct btrfs_fs_info *fs_info, u64 orig_flags);
void btrfs_put_block_group_cache(struct btrfs_fs_info *info);
int btrfs_free_block_groups(struct btrfs_fs_info *info);
void btrfs_wait_space_cache_v1_finished(struct btrfs_block_group *cache,
struct btrfs_caching_control *caching_ctl);
int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start,
struct block_device *bdev, u64 physical, u64 **logical,
int *naddrs, int *stripe_len);
static inline u64 btrfs_data_alloc_profile(struct btrfs_fs_info *fs_info)
{
return btrfs_get_alloc_profile(fs_info, BTRFS_BLOCK_GROUP_DATA);
}
static inline u64 btrfs_metadata_alloc_profile(struct btrfs_fs_info *fs_info)
{
return btrfs_get_alloc_profile(fs_info, BTRFS_BLOCK_GROUP_METADATA);
}
static inline u64 btrfs_system_alloc_profile(struct btrfs_fs_info *fs_info)
{
return btrfs_get_alloc_profile(fs_info, BTRFS_BLOCK_GROUP_SYSTEM);
}
static inline int btrfs_block_group_done(struct btrfs_block_group *cache)
{
smp_mb();
return cache->cached == BTRFS_CACHE_FINISHED ||
cache->cached == BTRFS_CACHE_ERROR;
}
void btrfs_freeze_block_group(struct btrfs_block_group *cache);
void btrfs_unfreeze_block_group(struct btrfs_block_group *cache);
bool btrfs_inc_block_group_swap_extents(struct btrfs_block_group *bg);
void btrfs_dec_block_group_swap_extents(struct btrfs_block_group *bg, int amount);
#endif /* BTRFS_BLOCK_GROUP_H */