linux/fs/btrfs/subpage.c

// SPDX-License-Identifier: GPL-2.0

#include <linux/slab.h>
#include "messages.h"
#include "ctree.h"
#include "subpage.h"
#include "btrfs_inode.h"

/*
 * Subpage (sectorsize < PAGE_SIZE) support overview:
 *
 * Limitations:
 *
 * - Only support 64K page size for now
 *   This is to make metadata handling easier, as 64K page would ensure
 *   all nodesize would fit inside one page, thus we don't need to handle
 *   cases where a tree block crosses several pages.
 *
 * - Only metadata read-write for now
 *   The data read-write part is in development.
 *
 * - Metadata can't cross 64K page boundary
 *   btrfs-progs and kernel have done that for a while, thus only ancient
 *   filesystems could have such problem.  For such case, do a graceful
 *   rejection.
 *
 * Special behavior:
 *
 * - Metadata
 *   Metadata read is fully supported.
 *   Meaning when reading one tree block will only trigger the read for the
 *   needed range, other unrelated range in the same page will not be touched.
 *
 *   Metadata write support is partial.
 *   The writeback is still for the full page, but we will only submit
 *   the dirty extent buffers in the page.
 *
 *   This means, if we have a metadata page like this:
 *
 *   Page offset
 *   0         16K         32K         48K        64K
 *   |/////////|           |///////////|
 *        \- Tree block A        \- Tree block B
 *
 *   Even if we just want to writeback tree block A, we will also writeback
 *   tree block B if it's also dirty.
 *
 *   This may cause extra metadata writeback which results more COW.
 *
 * Implementation:
 *
 * - Common
 *   Both metadata and data will use a new structure, btrfs_subpage, to
 *   record the status of each sector inside a page.  This provides the extra
 *   granularity needed.
 *
 * - Metadata
 *   Since we have multiple tree blocks inside one page, we can't rely on page
 *   locking anymore, or we will have greatly reduced concurrency or even
 *   deadlocks (hold one tree lock while trying to lock another tree lock in
 *   the same page).
 *
 *   Thus for metadata locking, subpage support relies on io_tree locking only.
 *   This means a slightly higher tree locking latency.
 */

#if PAGE_SIZE > SZ_4K
bool btrfs_is_subpage(const struct btrfs_fs_info *fs_info, struct address_space *mapping)
{
	if (fs_info->sectorsize >= PAGE_SIZE)
		return false;

	/*
	 * Only data pages (either through DIO or compression) can have no
	 * mapping. And if page->mapping->host is data inode, it's subpage.
	 * As we have ruled our sectorsize >= PAGE_SIZE case already.
	 */
	if (!mapping || !mapping->host || is_data_inode(BTRFS_I(mapping->host)))
		return true;

	/*
	 * Now the only remaining case is metadata, which we only go subpage
	 * routine if nodesize < PAGE_SIZE.
	 */
	if (fs_info->nodesize < PAGE_SIZE)
		return true;
	return false;
}
#endif

int btrfs_attach_subpage(const struct btrfs_fs_info *fs_info,
			 struct folio *folio, enum btrfs_subpage_type type)
{ … }

void btrfs_detach_subpage(const struct btrfs_fs_info *fs_info, struct folio *folio)
{ … }

struct btrfs_subpage *btrfs_alloc_subpage(const struct btrfs_fs_info *fs_info,
					  enum btrfs_subpage_type type)
{ … }

void btrfs_free_subpage(struct btrfs_subpage *subpage)
{ … }

/*
 * Increase the eb_refs of current subpage.
 *
 * This is important for eb allocation, to prevent race with last eb freeing
 * of the same page.
 * With the eb_refs increased before the eb inserted into radix tree,
 * detach_extent_buffer_page() won't detach the folio private while we're still
 * allocating the extent buffer.
 */
void btrfs_folio_inc_eb_refs(const struct btrfs_fs_info *fs_info, struct folio *folio)
{ … }

void btrfs_folio_dec_eb_refs(const struct btrfs_fs_info *fs_info, struct folio *folio)
{ … }

static void btrfs_subpage_assert(const struct btrfs_fs_info *fs_info,
				 struct folio *folio, u64 start, u32 len)
{ … }

#define subpage_calc_start_bit(fs_info, folio, name, start, len) …

void btrfs_subpage_start_reader(const struct btrfs_fs_info *fs_info,
				struct folio *folio, u64 start, u32 len)
{ … }

void btrfs_subpage_end_reader(const struct btrfs_fs_info *fs_info,
			      struct folio *folio, u64 start, u32 len)
{ … }

static void btrfs_subpage_clamp_range(struct folio *folio, u64 *start, u32 *len)
{ … }

static void btrfs_subpage_start_writer(const struct btrfs_fs_info *fs_info,
				       struct folio *folio, u64 start, u32 len)
{ … }

static bool btrfs_subpage_end_and_test_writer(const struct btrfs_fs_info *fs_info,
					      struct folio *folio, u64 start, u32 len)
{ … }

/*
 * Lock a folio for delalloc page writeback.
 *
 * Return -EAGAIN if the page is not properly initialized.
 * Return 0 with the page locked, and writer counter updated.
 *
 * Even with 0 returned, the page still need extra check to make sure
 * it's really the correct page, as the caller is using
 * filemap_get_folios_contig(), which can race with page invalidating.
 */
int btrfs_folio_start_writer_lock(const struct btrfs_fs_info *fs_info,
				  struct folio *folio, u64 start, u32 len)
{ … }

/*
 * Handle different locked folios:
 *
 * - Non-subpage folio
 *   Just unlock it.
 *
 * - folio locked but without any subpage locked
 *   This happens either before writepage_delalloc() or the delalloc range is
 *   already handled by previous folio.
 *   We can simple unlock it.
 *
 * - folio locked with subpage range locked.
 *   We go through the locked sectors inside the range and clear their locked
 *   bitmap, reduce the writer lock number, and unlock the page if that's
 *   the last locked range.
 */
void btrfs_folio_end_writer_lock(const struct btrfs_fs_info *fs_info,
				 struct folio *folio, u64 start, u32 len)
{ … }

void btrfs_folio_end_writer_lock_bitmap(const struct btrfs_fs_info *fs_info,
					struct folio *folio, unsigned long bitmap)
{ … }

#define subpage_test_bitmap_all_set(fs_info, subpage, name) …

#define subpage_test_bitmap_all_zero(fs_info, subpage, name) …

void btrfs_subpage_set_uptodate(const struct btrfs_fs_info *fs_info,
				struct folio *folio, u64 start, u32 len)
{ … }

void btrfs_subpage_clear_uptodate(const struct btrfs_fs_info *fs_info,
				  struct folio *folio, u64 start, u32 len)
{ … }

void btrfs_subpage_set_dirty(const struct btrfs_fs_info *fs_info,
			     struct folio *folio, u64 start, u32 len)
{ … }

/*
 * Extra clear_and_test function for subpage dirty bitmap.
 *
 * Return true if we're the last bits in the dirty_bitmap and clear the
 * dirty_bitmap.
 * Return false otherwise.
 *
 * NOTE: Callers should manually clear page dirty for true case, as we have
 * extra handling for tree blocks.
 */
bool btrfs_subpage_clear_and_test_dirty(const struct btrfs_fs_info *fs_info,
					struct folio *folio, u64 start, u32 len)
{ … }

void btrfs_subpage_clear_dirty(const struct btrfs_fs_info *fs_info,
			       struct folio *folio, u64 start, u32 len)
{ … }

void btrfs_subpage_set_writeback(const struct btrfs_fs_info *fs_info,
				 struct folio *folio, u64 start, u32 len)
{ … }

void btrfs_subpage_clear_writeback(const struct btrfs_fs_info *fs_info,
				   struct folio *folio, u64 start, u32 len)
{ … }

void btrfs_subpage_set_ordered(const struct btrfs_fs_info *fs_info,
			       struct folio *folio, u64 start, u32 len)
{ … }

void btrfs_subpage_clear_ordered(const struct btrfs_fs_info *fs_info,
				 struct folio *folio, u64 start, u32 len)
{ … }

void btrfs_subpage_set_checked(const struct btrfs_fs_info *fs_info,
			       struct folio *folio, u64 start, u32 len)
{ … }

void btrfs_subpage_clear_checked(const struct btrfs_fs_info *fs_info,
				 struct folio *folio, u64 start, u32 len)
{ … }

/*
 * Unlike set/clear which is dependent on each page status, for test all bits
 * are tested in the same way.
 */
#define IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(name) …
IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(uptodate);
IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(dirty);
IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(writeback);
IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(ordered);
IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(checked);

/*
 * Note that, in selftests (extent-io-tests), we can have empty fs_info passed
 * in.  We only test sectorsize == PAGE_SIZE cases so far, thus we can fall
 * back to regular sectorsize branch.
 */
#define IMPLEMENT_BTRFS_PAGE_OPS(name, folio_set_func,			\
				 folio_clear_func, folio_test_func) …
IMPLEMENT_BTRFS_PAGE_OPS(uptodate, folio_mark_uptodate, folio_clear_uptodate,
			 folio_test_uptodate);
IMPLEMENT_BTRFS_PAGE_OPS(dirty, folio_mark_dirty, folio_clear_dirty_for_io,
			 folio_test_dirty);
IMPLEMENT_BTRFS_PAGE_OPS(writeback, folio_start_writeback, folio_end_writeback,
			 folio_test_writeback);
IMPLEMENT_BTRFS_PAGE_OPS(ordered, folio_set_ordered, folio_clear_ordered,
			 folio_test_ordered);
IMPLEMENT_BTRFS_PAGE_OPS(checked, folio_set_checked, folio_clear_checked,
			 folio_test_checked);

/*
 * Make sure not only the page dirty bit is cleared, but also subpage dirty bit
 * is cleared.
 */
void btrfs_folio_assert_not_dirty(const struct btrfs_fs_info *fs_info,
				  struct folio *folio, u64 start, u32 len)
{ … }

/*
 * This is for folio already locked by plain lock_page()/folio_lock(), which
 * doesn't have any subpage awareness.
 *
 * This populates the involved subpage ranges so that subpage helpers can
 * properly unlock them.
 */
void btrfs_folio_set_writer_lock(const struct btrfs_fs_info *fs_info,
				 struct folio *folio, u64 start, u32 len)
{ … }

/*
 * Find any subpage writer locked range inside @folio, starting at file offset
 * @search_start. The caller should ensure the folio is locked.
 *
 * Return true and update @found_start_ret and @found_len_ret to the first
 * writer locked range.
 * Return false if there is no writer locked range.
 */
bool btrfs_subpage_find_writer_locked(const struct btrfs_fs_info *fs_info,
				      struct folio *folio, u64 search_start,
				      u64 *found_start_ret, u32 *found_len_ret)
{ … }

#define GET_SUBPAGE_BITMAP(subpage, fs_info, name, dst) …

void __cold btrfs_subpage_dump_bitmap(const struct btrfs_fs_info *fs_info,
				      struct folio *folio, u64 start, u32 len)
{ … }

void btrfs_get_subpage_dirty_bitmap(struct btrfs_fs_info *fs_info,
				    struct folio *folio,
				    unsigned long *ret_bitmap)
{ … }