fs/btrfs/extent_io.h

/* SPDX-License-Identifier: GPL-2.0 */

#ifndef BTRFS_EXTENT_IO_H
#define BTRFS_EXTENT_IO_H

#include <linux/rbtree.h>
#include <linux/refcount.h>
#include <linux/fiemap.h>
#include <linux/btrfs_tree.h>
#include <linux/spinlock.h>
#include <linux/atomic.h>
#include <linux/rwsem.h>
#include <linux/list.h>
#include <linux/slab.h>
#include "messages.h"
#include "ulist.h"
#include "misc.h"

struct page;
struct file;
struct folio;
struct inode;
struct fiemap_extent_info;
struct readahead_control;
struct address_space;
struct writeback_control;
struct extent_io_tree;
struct extent_map_tree;
struct extent_state;
struct btrfs_block_group;
struct btrfs_fs_info;
struct btrfs_inode;
struct btrfs_root;
struct btrfs_trans_handle;
struct btrfs_tree_parent_check;

enum {
	EXTENT_BUFFER_UPTODATE,
	EXTENT_BUFFER_DIRTY,
	EXTENT_BUFFER_TREE_REF,
	EXTENT_BUFFER_STALE,
	EXTENT_BUFFER_WRITEBACK,
	EXTENT_BUFFER_UNMAPPED,
	/* write IO error */
	EXTENT_BUFFER_WRITE_ERR,
	/* Indicate the extent buffer is written zeroed out (for zoned) */
	EXTENT_BUFFER_ZONED_ZEROOUT,
	/* Indicate that extent buffer pages a being read */
	EXTENT_BUFFER_READING,
};

/* these are flags for __process_pages_contig */
enum {
	ENUM_BIT(PAGE_UNLOCK),
	/* Page starts writeback, clear dirty bit and set writeback bit */
	ENUM_BIT(PAGE_START_WRITEBACK),
	ENUM_BIT(PAGE_END_WRITEBACK),
};

/*
 * Folio private values.  Every page that is controlled by the extent map has
 * folio private set to this value.
 */
#define EXTENT_FOLIO_PRIVATE			1

/*
 * The extent buffer bitmap operations are done with byte granularity instead of
 * word granularity for two reasons:
 * 1. The bitmaps must be little-endian on disk.
 * 2. Bitmap items are not guaranteed to be aligned to a word and therefore a
 *    single word in a bitmap may straddle two pages in the extent buffer.
 */
#define BIT_BYTE(nr) ((nr) / BITS_PER_BYTE)
#define BYTE_MASK ((1U << BITS_PER_BYTE) - 1)
#define BITMAP_FIRST_BYTE_MASK(start) \
	((BYTE_MASK << ((start) & (BITS_PER_BYTE - 1))) & BYTE_MASK)
#define BITMAP_LAST_BYTE_MASK(nbits) \
	(BYTE_MASK >> (-(nbits) & (BITS_PER_BYTE - 1)))


int __init extent_buffer_init_cachep(void);
void __cold extent_buffer_free_cachep(void);

#define INLINE_EXTENT_BUFFER_PAGES     (BTRFS_MAX_METADATA_BLOCKSIZE / PAGE_SIZE)
struct extent_buffer {
	u64 start;
	u32 len;
	u32 folio_size;
	unsigned long bflags;
	struct btrfs_fs_info *fs_info;

	/*
	 * The address where the eb can be accessed without any cross-page handling.
	 * This can be NULL if not possible.
	 */
	void *addr;

	spinlock_t refs_lock;
	refcount_t refs;
	int read_mirror;
	/* Inhibit WB_SYNC_NONE writeback when > 0. */
	atomic_t writeback_inhibitors;
	/* >= 0 if eb belongs to a log tree, -1 otherwise */
	s8 log_index;
	u8 folio_shift;
	struct rcu_head rcu_head;

	struct rw_semaphore lock;

	/*
	 * Pointers to all the folios of the extent buffer.
	 *
	 * For now the folio is always order 0 (aka, a single page).
	 */
	struct folio *folios[INLINE_EXTENT_BUFFER_PAGES];
#ifdef CONFIG_BTRFS_DEBUG
	struct list_head leak_list;
	pid_t lock_owner;
#endif
};

/*
 * Wrapper struct for managing preallocating an extent_buffer, its folios and a
 * btrfs_folio_state if needed.
 *
 * Only used to mediate allocation, do not refer to the eb directly if not
 * returned from a successful eb allocating API.
 *
 * The eb folios and bfs should generally not be fully attached, except briefly
 * before they are NULLed in the struct after successful attachment.
 */
struct btrfs_eb_prealloc {
	struct extent_buffer *eb;
	struct btrfs_folio_state *bfs;
	/* eb alloc may use GFP_NOWAIT; caller can drop locks and retry. */
	bool supports_nowait;
	/* GFP_NOWAIT eb alloc failed; preallocate again and retry. */
	bool needs_prealloc;
};

struct btrfs_eb_write_context {
	struct writeback_control *wbc;
	struct extent_buffer *eb;
	/* Block group @eb resides in. Only used for zoned mode. */
	struct btrfs_block_group *zoned_bg;
};

static inline unsigned long offset_in_eb_folio(const struct extent_buffer *eb,
					       u64 start)
{
	ASSERT(eb->folio_size);
	return start & (eb->folio_size - 1);
}

/*
 * Get the correct offset inside the page of extent buffer.
 *
 * @eb:		target extent buffer
 * @start:	offset inside the extent buffer
 *
 * Will handle both sectorsize == PAGE_SIZE and sectorsize < PAGE_SIZE cases.
 */
static inline size_t get_eb_offset_in_folio(const struct extent_buffer *eb,
					    unsigned long offset)
{
	/*
	 * 1) sectorsize == PAGE_SIZE and nodesize >= PAGE_SIZE case
	 *    1.1) One large folio covering the whole eb
	 *	   The eb->start is aligned to folio size, thus adding it
	 *	   won't cause any difference.
	 *    1.2) Several page sized folios
	 *	   The eb->start is aligned to folio (page) size, thus
	 *	   adding it won't cause any difference.
	 *
	 * 2) sectorsize < PAGE_SIZE and nodesize < PAGE_SIZE case
	 *    In this case there would only be one page sized folio, and there
	 *    may be several different extent buffers in the page/folio.
	 *    We need to add eb->start to properly access the offset inside
	 *    that eb.
	 */
	return offset_in_folio(eb->folios[0], offset + eb->start);
}

static inline unsigned long get_eb_folio_index(const struct extent_buffer *eb,
					       unsigned long offset)
{
	/*
	 * 1) sectorsize == PAGE_SIZE and nodesize >= PAGE_SIZE case
	 *    1.1) One large folio covering the whole eb.
	 *	   the folio_shift would be large enough to always make us
	 *	   return 0 as index.
	 *    1.2) Several page sized folios
	 *         The folio_shift would be PAGE_SHIFT, giving us the correct
	 *         index.
	 *
	 * 2) sectorsize < PAGE_SIZE and nodesize < PAGE_SIZE case
	 *    The folio would only be page sized, and always give us 0 as index.
	 */
	return offset >> eb->folio_shift;
}

/*
 * Structure to record how many bytes and which ranges are set/cleared
 */
struct extent_changeset {
	/* How many bytes are set/cleared in this operation */
	u64 bytes_changed;

	/* Changed ranges */
	struct ulist range_changed;
};

static inline void extent_changeset_init(struct extent_changeset *changeset)
{
	changeset->bytes_changed = 0;
	ulist_init(&changeset->range_changed);
}

/*
 * Sentinel value for range_changed.prealloc indicating that the changeset
 * only tracks bytes_changed and does not record individual ranges. This
 * avoids GFP_ATOMIC allocations inside add_extent_changeset() when the
 * caller doesn't need to iterate the changed ranges afterwards.
 */
#define EXTENT_CHANGESET_BYTES_ONLY	((struct ulist_node *)1)

static inline void extent_changeset_init_bytes_only(struct extent_changeset *changeset)
{
	changeset->bytes_changed = 0;
	changeset->range_changed.prealloc = EXTENT_CHANGESET_BYTES_ONLY;
}

static inline bool extent_changeset_tracks_ranges(const struct extent_changeset *changeset)
{
	return changeset->range_changed.prealloc != EXTENT_CHANGESET_BYTES_ONLY;
}

static inline struct extent_changeset *extent_changeset_alloc(void)
{
	struct extent_changeset *ret;

	ret = kmalloc_obj(*ret);
	if (!ret)
		return NULL;

	extent_changeset_init(ret);
	return ret;
}

static inline void extent_changeset_prealloc(struct extent_changeset *changeset, gfp_t gfp_mask)
{
	ASSERT(extent_changeset_tracks_ranges(changeset));
	ulist_prealloc(&changeset->range_changed, gfp_mask);
}

static inline void extent_changeset_release(struct extent_changeset *changeset)
{
	if (!changeset)
		return;
	changeset->bytes_changed = 0;
	if (extent_changeset_tracks_ranges(changeset))
		ulist_release(&changeset->range_changed);
}

static inline void extent_changeset_free(struct extent_changeset *changeset)
{
	if (!changeset)
		return;
	extent_changeset_release(changeset);
	kfree(changeset);
}

bool try_release_extent_mapping(struct folio *folio, gfp_t mask);
int try_release_extent_buffer(struct folio *folio);

int btrfs_read_folio(struct file *file, struct folio *folio);
#ifdef CONFIG_BTRFS_DEBUG
void btrfs_check_folio_write_protected(struct folio *folio);
#else
static inline void btrfs_check_folio_write_protected(struct folio *folio) { }
#endif
void extent_write_locked_range(struct inode *inode, const struct folio *locked_folio,
			       u64 start, u64 end, struct writeback_control *wbc,
			       bool pages_dirty);
int btrfs_writepages(struct address_space *mapping, struct writeback_control *wbc);
int btree_writepages(struct address_space *mapping, struct writeback_control *wbc);
void btrfs_btree_wait_writeback_range(struct btrfs_fs_info *fs_info, u64 start, u64 end);
void btrfs_readahead(struct readahead_control *rac);
int set_folio_extent_mapped(struct folio *folio);
void clear_folio_extent_mapped(struct folio *folio);

struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
					  struct btrfs_eb_prealloc *pa,
					  u64 start, u64 owner_root, int level);
int btrfs_init_eb_prealloc(struct btrfs_fs_info *fs_info,
			   struct btrfs_eb_prealloc *pa, bool nowait);
void btrfs_free_eb_prealloc(struct btrfs_eb_prealloc *pa);
struct extent_buffer *alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
						u64 start);
struct extent_buffer *btrfs_clone_extent_buffer(const struct extent_buffer *src);
struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info,
					 u64 start);
void free_extent_buffer(struct extent_buffer *eb);
void free_extent_buffer_stale(struct extent_buffer *eb);
int read_extent_buffer_pages(struct extent_buffer *eb, int mirror_num,
			     const struct btrfs_tree_parent_check *parent_check);
int read_extent_buffer_pages_nowait(struct extent_buffer *eb, int mirror_num,
				    const struct btrfs_tree_parent_check *parent_check);

static inline void wait_on_extent_buffer_writeback(struct extent_buffer *eb)
{
	wait_on_bit_io(&eb->bflags, EXTENT_BUFFER_WRITEBACK,
		       TASK_UNINTERRUPTIBLE);
}

void btrfs_readahead_tree_block(struct btrfs_fs_info *fs_info,
				u64 bytenr, u64 owner_root, u64 gen, int level,
				const struct btrfs_key *first_key);
void btrfs_readahead_node_child(struct extent_buffer *node, int slot);

/* Note: this can be used in for loops without caching the value in a variable. */
static inline int __pure num_extent_pages(const struct extent_buffer *eb)
{
	/*
	 * For sectorsize == PAGE_SIZE case, since nodesize is always aligned to
	 * sectorsize, it's just eb->len >> PAGE_SHIFT.
	 *
	 * For sectorsize < PAGE_SIZE case, we could have nodesize < PAGE_SIZE,
	 * thus have to ensure we get at least one page.
	 */
	return (eb->len >> PAGE_SHIFT) ?: 1;
}

/*
 * This can only be determined at runtime by checking eb::folios[0].
 *
 * As we can have either one large folio covering the whole eb
 * (either nodesize <= PAGE_SIZE, or high order folio), or multiple
 * single-paged folios.
 *
 * Note: this can be used in for loops without caching the value in a variable.
 */
static inline int __pure num_extent_folios(const struct extent_buffer *eb)
{
	if (!eb->folios[0])
		return 0;
	if (folio_order(eb->folios[0]))
		return 1;
	return num_extent_pages(eb);
}

static inline bool extent_buffer_uptodate(const struct extent_buffer *eb)
{
	return test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
}

static inline bool extent_buffer_under_io(const struct extent_buffer *eb)
{
	return (test_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags) ||
		test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags));
}

int memcmp_extent_buffer(const struct extent_buffer *eb, const void *ptrv,
			 unsigned long start, unsigned long len);
void read_extent_buffer(const struct extent_buffer *eb, void *dst,
			unsigned long start,
			unsigned long len);
int read_extent_buffer_to_user_nofault(const struct extent_buffer *eb,
				       void __user *dst, unsigned long start,
				       unsigned long len);
void write_extent_buffer(const struct extent_buffer *eb, const void *src,
			 unsigned long start, unsigned long len);

static inline void write_extent_buffer_chunk_tree_uuid(
		const struct extent_buffer *eb, const void *chunk_tree_uuid)
{
	write_extent_buffer(eb, chunk_tree_uuid,
			    offsetof(struct btrfs_header, chunk_tree_uuid),
			    BTRFS_FSID_SIZE);
}

static inline void write_extent_buffer_fsid(const struct extent_buffer *eb,
					    const void *fsid)
{
	write_extent_buffer(eb, fsid, offsetof(struct btrfs_header, fsid),
			    BTRFS_FSID_SIZE);
}

void copy_extent_buffer_full(const struct extent_buffer *dst,
			     const struct extent_buffer *src);
void copy_extent_buffer(const struct extent_buffer *dst,
			const struct extent_buffer *src,
			unsigned long dst_offset, unsigned long src_offset,
			unsigned long len);
void memcpy_extent_buffer(const struct extent_buffer *dst,
			  unsigned long dst_offset, unsigned long src_offset,
			  unsigned long len);
void memmove_extent_buffer(const struct extent_buffer *dst,
			   unsigned long dst_offset, unsigned long src_offset,
			   unsigned long len);
void memzero_extent_buffer(const struct extent_buffer *eb, unsigned long start,
			   unsigned long len);
bool extent_buffer_test_bit(const struct extent_buffer *eb, unsigned long start,
			    unsigned long pos);
void extent_buffer_bitmap_set(const struct extent_buffer *eb, unsigned long start,
			      unsigned long pos, unsigned long len);
void extent_buffer_bitmap_clear(const struct extent_buffer *eb,
				unsigned long start, unsigned long pos,
				unsigned long len);
void set_extent_buffer_dirty(struct extent_buffer *eb);
void set_extent_buffer_uptodate(struct extent_buffer *eb);
void clear_extent_buffer_uptodate(struct extent_buffer *eb);
void extent_clear_unlock_delalloc(struct btrfs_inode *inode, u64 start, u64 end,
				  const struct folio *locked_folio,
				  struct extent_state **cached,
				  u32 bits_to_clear, unsigned long page_ops);
void btrfs_clear_buffer_dirty(struct btrfs_trans_handle *trans,
			      struct extent_buffer *buf);
void btrfs_zoned_release_dirty_metadata(struct btrfs_fs_info *fs_info);

static inline void btrfs_clear_folio_dirty_tag(struct folio *folio)
{
	ASSERT(!folio_test_dirty(folio));
	ASSERT(folio_test_locked(folio));
	ASSERT(folio->mapping);
	xa_lock_irq(&folio->mapping->i_pages);
	__xa_clear_mark(&folio->mapping->i_pages, folio->index,
			PAGECACHE_TAG_DIRTY);
	xa_unlock_irq(&folio->mapping->i_pages);
}

int btrfs_alloc_page_array(unsigned int nr_pages, struct page **page_array, gfp_t gfp);
int btrfs_alloc_folio_array(unsigned int nr_folios, unsigned int order,
			    struct folio **folio_array, gfp_t gfp);

#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
bool find_lock_delalloc_range(struct inode *inode,
			      struct folio *locked_folio, u64 *start,
			     u64 *end);
#endif
struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info,
					       u64 start);

#ifdef CONFIG_BTRFS_DEBUG
void btrfs_extent_buffer_leak_debug_check(struct btrfs_fs_info *fs_info);
#else
#define btrfs_extent_buffer_leak_debug_check(fs_info)	do {} while (0)
#endif

void btrfs_inhibit_eb_writeback(struct btrfs_trans_handle *trans,
			       struct extent_buffer *eb);
void btrfs_uninhibit_all_eb_writeback(struct btrfs_trans_handle *trans);

#endif