[mirror_ubuntu-hirsute-kernel.git] / fs / btrfs / block-group.h

/* 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,
};

/*
 * 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;

	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;

	/* Usage count */
	atomic_t count;

	/*
	 * 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;

	atomic_t trimming;

	/* 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;

	/* Record locked full stripes for RAID5/6 block group */
	struct btrfs_full_stripe_locks_tree full_stripe_locks_root;
};

#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);
int btrfs_read_block_groups(struct btrfs_fs_info *info);
int 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);
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);

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;
}

#endif /* BTRFS_BLOCK_GROUP_H */
Commit	Line	Data
aac0023c JB	1	/* SPDX-License-Identifier: GPL-2.0 */
	2
	3	#ifndef BTRFS_BLOCK_GROUP_H
	4	#define BTRFS_BLOCK_GROUP_H
	5
67b61aef DS	6	#include "free-space-cache.h"
67b61aef DS	7
aac0023c JB	8	enum btrfs_disk_cache_state {
	9	BTRFS_DC_WRITTEN,
	10	BTRFS_DC_ERROR,
	11	BTRFS_DC_CLEAR,
	12	BTRFS_DC_SETUP,
	13	};
	14
07730d87 JB	15	/*
	16	* Control flags for do_chunk_alloc's force field CHUNK_ALLOC_NO_FORCE means to
	17	* only allocate a chunk if we really need one.
	18	*
	19	* CHUNK_ALLOC_LIMITED means to only try and allocate one if we have very few
	20	* chunks already allocated. This is used as part of the clustering code to
	21	* help make sure we have a good pool of storage to cluster in, without filling
	22	* the FS with empty chunks
	23	*
	24	* CHUNK_ALLOC_FORCE means it must try to allocate one
	25	*/
	26	enum btrfs_chunk_alloc_enum {
	27	CHUNK_ALLOC_NO_FORCE,
	28	CHUNK_ALLOC_LIMITED,
	29	CHUNK_ALLOC_FORCE,
	30	};
	31
aac0023c JB	32	struct btrfs_caching_control {
	33	struct list_head list;
	34	struct mutex mutex;
	35	wait_queue_head_t wait;
	36	struct btrfs_work work;
32da5386	37	struct btrfs_block_group *block_group;
aac0023c JB	38	u64 progress;
	39	refcount_t count;
	40	};
	41
	42	/* Once caching_thread() finds this much free space, it will wake up waiters. */
	43	#define CACHING_CTL_WAKE_UP SZ_2M
	44
32da5386	45	struct btrfs_block_group {
aac0023c JB	46	struct btrfs_fs_info *fs_info;
	47	struct inode *inode;
	48	spinlock_t lock;
b3470b5d DS	49	u64 start;
b3470b5d DS	50	u64 length;
aac0023c JB	51	u64 pinned;
aac0023c JB	52	u64 reserved;
bf38be65	53	u64 used;
aac0023c JB	54	u64 delalloc_bytes;
	55	u64 bytes_super;
	56	u64 flags;
	57	u64 cache_generation;
	58
	59	/*
	60	* If the free space extent count exceeds this number, convert the block
	61	* group to bitmaps.
	62	*/
	63	u32 bitmap_high_thresh;
	64
	65	/*
	66	* If the free space extent count drops below this number, convert the
	67	* block group back to extents.
	68	*/
	69	u32 bitmap_low_thresh;
	70
	71	/*
	72	* It is just used for the delayed data space allocation because
	73	* only the data space allocation and the relative metadata update
	74	* can be done cross the transaction.
	75	*/
	76	struct rw_semaphore data_rwsem;
	77
	78	/* For raid56, this is a full stripe, without parity */
	79	unsigned long full_stripe_len;
	80
	81	unsigned int ro;
	82	unsigned int iref:1;
	83	unsigned int has_caching_ctl:1;
	84	unsigned int removed:1;
	85
	86	int disk_cache_state;
	87
	88	/* Cache tracking stuff */
	89	int cached;
	90	struct btrfs_caching_control *caching_ctl;
	91	u64 last_byte_to_unpin;
	92
	93	struct btrfs_space_info *space_info;
	94
	95	/* Free space cache stuff */
	96	struct btrfs_free_space_ctl *free_space_ctl;
	97
	98	/* Block group cache stuff */
	99	struct rb_node cache_node;
	100
	101	/* For block groups in the same raid type */
	102	struct list_head list;
	103
	104	/* Usage count */
	105	atomic_t count;
	106
	107	/*
	108	* List of struct btrfs_free_clusters for this block group.
	109	* Today it will only have one thing on it, but that may change
	110	*/
	111	struct list_head cluster_list;
	112
	113	/* For delayed block group creation or deletion of empty block groups */
	114	struct list_head bg_list;
	115
	116	/* For read-only block groups */
	117	struct list_head ro_list;
118
119	atomic_t trimming;
120
121	/* For dirty block groups */
122	struct list_head dirty_list;
123	struct list_head io_list;
124
125	struct btrfs_io_ctl io_ctl;
126
127	/*
128	* Incremented when doing extent allocations and holding a read lock
129	* on the space_info's groups_sem semaphore.
130	* Decremented when an ordered extent that represents an IO against this
131	* block group's range is created (after it's added to its inode's
132	* root's list of ordered extents) or immediately after the allocation
133	* if it's a metadata extent or fallocate extent (for these cases we
134	* don't create ordered extents).
135	*/
136	atomic_t reservations;
137
138	/*
139	* Incremented while holding the spinlock lock by a task checking if
140	* it can perform a nocow write (incremented if the value for the ro
141	* field is 0). Decremented by such tasks once they create an ordered
142	* extent or before that if some error happens before reaching that step.
143	* This is to prevent races between block group relocation and nocow
144	* writes through direct IO.
145	*/
146	atomic_t nocow_writers;
147
148	/* Lock for free space tree operations. */
149	struct mutex free_space_lock;
150
151	/*
152	* Does the block group need to be added to the free space tree?
153	* Protected by free_space_lock.
154	*/
155	int needs_free_space;
156
157	/* Record locked full stripes for RAID5/6 block group */
158	struct btrfs_full_stripe_locks_tree full_stripe_locks_root;
159	};
160
161	#ifdef CONFIG_BTRFS_DEBUG
162	static inline int btrfs_should_fragment_free_space(
32da5386	163	struct btrfs_block_group *block_group)
aac0023c JB	164	{
	165	struct btrfs_fs_info *fs_info = block_group->fs_info;
	166
	167	return (btrfs_test_opt(fs_info, FRAGMENT_METADATA) &&
	168	block_group->flags & BTRFS_BLOCK_GROUP_METADATA) \|\|
	169	(btrfs_test_opt(fs_info, FRAGMENT_DATA) &&
	170	block_group->flags & BTRFS_BLOCK_GROUP_DATA);
	171	}
	172	#endif
	173
32da5386	174	struct btrfs_block_group *btrfs_lookup_first_block_group(
2e405ad8	175	struct btrfs_fs_info *info, u64 bytenr);
32da5386	176	struct btrfs_block_group *btrfs_lookup_block_group(
2e405ad8	177	struct btrfs_fs_info *info, u64 bytenr);
32da5386 DS	178	struct btrfs_block_group *btrfs_next_block_group(
	179	struct btrfs_block_group *cache);
	180	void btrfs_get_block_group(struct btrfs_block_group *cache);
	181	void btrfs_put_block_group(struct btrfs_block_group *cache);
3eeb3226 JB	182	void btrfs_dec_block_group_reservations(struct btrfs_fs_info *fs_info,
3eeb3226 JB	183	const u64 start);
32da5386	184	void btrfs_wait_block_group_reservations(struct btrfs_block_group *bg);
3eeb3226 JB	185	bool btrfs_inc_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr);
3eeb3226 JB	186	void btrfs_dec_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr);
32da5386 DS	187	void btrfs_wait_nocow_writers(struct btrfs_block_group *bg);
32da5386 DS	188	void btrfs_wait_block_group_cache_progress(struct btrfs_block_group *cache,
676f1f75	189	u64 num_bytes);
32da5386 DS	190	int btrfs_wait_block_group_cache_done(struct btrfs_block_group *cache);
32da5386 DS	191	int btrfs_cache_block_group(struct btrfs_block_group *cache,
676f1f75	192	int load_cache_only);
e3cb339f JB	193	void btrfs_put_caching_control(struct btrfs_caching_control *ctl);
e3cb339f JB	194	struct btrfs_caching_control *btrfs_get_caching_control(
32da5386 DS	195	struct btrfs_block_group *cache);
32da5386 DS	196	u64 add_new_free_space(struct btrfs_block_group *block_group,
9f21246d	197	u64 start, u64 end);
e3e0520b JB	198	struct btrfs_trans_handle *btrfs_start_trans_remove_block_group(
	199	struct btrfs_fs_info *fs_info,
	200	const u64 chunk_offset);
	201	int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
	202	u64 group_start, struct extent_map *em);
	203	void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info);
32da5386	204	void btrfs_mark_bg_unused(struct btrfs_block_group *bg);
4358d963 JB	205	int btrfs_read_block_groups(struct btrfs_fs_info *info);
	206	int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used,
	207	u64 type, u64 chunk_offset, u64 size);
	208	void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans);
32da5386 DS	209	int btrfs_inc_block_group_ro(struct btrfs_block_group *cache);
32da5386 DS	210	void btrfs_dec_block_group_ro(struct btrfs_block_group *cache);
77745c05 JB	211	int btrfs_start_dirty_block_groups(struct btrfs_trans_handle *trans);
	212	int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans);
	213	int btrfs_setup_space_cache(struct btrfs_trans_handle *trans);
ade4b516 JB	214	int btrfs_update_block_group(struct btrfs_trans_handle *trans,
ade4b516 JB	215	u64 bytenr, u64 num_bytes, int alloc);
32da5386	216	int btrfs_add_reserved_bytes(struct btrfs_block_group *cache,
ade4b516	217	u64 ram_bytes, u64 num_bytes, int delalloc);
32da5386	218	void btrfs_free_reserved_bytes(struct btrfs_block_group *cache,
ade4b516	219	u64 num_bytes, int delalloc);
07730d87 JB	220	int btrfs_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags,
	221	enum btrfs_chunk_alloc_enum force);
	222	int btrfs_force_chunk_alloc(struct btrfs_trans_handle *trans, u64 type);
	223	void check_system_chunk(struct btrfs_trans_handle *trans, const u64 type);
878d7b67	224	u64 btrfs_get_alloc_profile(struct btrfs_fs_info *fs_info, u64 orig_flags);
3e43c279 JB	225	void btrfs_put_block_group_cache(struct btrfs_fs_info *info);
3e43c279 JB	226	int btrfs_free_block_groups(struct btrfs_fs_info *info);
878d7b67 JB	227
	228	static inline u64 btrfs_data_alloc_profile(struct btrfs_fs_info *fs_info)
	229	{
	230	return btrfs_get_alloc_profile(fs_info, BTRFS_BLOCK_GROUP_DATA);
	231	}
	232
	233	static inline u64 btrfs_metadata_alloc_profile(struct btrfs_fs_info *fs_info)
	234	{
	235	return btrfs_get_alloc_profile(fs_info, BTRFS_BLOCK_GROUP_METADATA);
	236	}
	237
	238	static inline u64 btrfs_system_alloc_profile(struct btrfs_fs_info *fs_info)
	239	{
	240	return btrfs_get_alloc_profile(fs_info, BTRFS_BLOCK_GROUP_SYSTEM);
	241	}
676f1f75	242
32da5386	243	static inline int btrfs_block_group_done(struct btrfs_block_group *cache)
676f1f75 JB	244	{
	245	smp_mb();
	246	return cache->cached == BTRFS_CACHE_FINISHED \|\|
	247	cache->cached == BTRFS_CACHE_ERROR;
	248	}
2e405ad8	249
aac0023c	250	#endif /* BTRFS_BLOCK_GROUP_H */