linux/fs/btrfs/fiemap.c

// SPDX-License-Identifier: GPL-2.0

#include "backref.h"
#include "btrfs_inode.h"
#include "fiemap.h"
#include "file.h"
#include "file-item.h"

struct btrfs_fiemap_entry { … };

/*
 * Indicate the caller of emit_fiemap_extent() that it needs to unlock the file
 * range from the inode's io tree, unlock the subvolume tree search path, flush
 * the fiemap cache and relock the file range and research the subvolume tree.
 * The value here is something negative that can't be confused with a valid
 * errno value and different from 1 because that's also a return value from
 * fiemap_fill_next_extent() and also it's often used to mean some btree search
 * did not find a key, so make it some distinct negative value.
 */
#define BTRFS_FIEMAP_FLUSH_CACHE …

/*
 * Used to:
 *
 * - Cache the next entry to be emitted to the fiemap buffer, so that we can
 *   merge extents that are contiguous and can be grouped as a single one;
 *
 * - Store extents ready to be written to the fiemap buffer in an intermediary
 *   buffer. This intermediary buffer is to ensure that in case the fiemap
 *   buffer is memory mapped to the fiemap target file, we don't deadlock
 *   during btrfs_page_mkwrite(). This is because during fiemap we are locking
 *   an extent range in order to prevent races with delalloc flushing and
 *   ordered extent completion, which is needed in order to reliably detect
 *   delalloc in holes and prealloc extents. And this can lead to a deadlock
 *   if the fiemap buffer is memory mapped to the file we are running fiemap
 *   against (a silly, useless in practice scenario, but possible) because
 *   btrfs_page_mkwrite() will try to lock the same extent range.
 */
struct fiemap_cache { … };

static int flush_fiemap_cache(struct fiemap_extent_info *fieinfo,
			      struct fiemap_cache *cache)
{ … }

/*
 * Helper to submit fiemap extent.
 *
 * Will try to merge current fiemap extent specified by @offset, @phys,
 * @len and @flags with cached one.
 * And only when we fails to merge, cached one will be submitted as
 * fiemap extent.
 *
 * Return value is the same as fiemap_fill_next_extent().
 */
static int emit_fiemap_extent(struct fiemap_extent_info *fieinfo,
				struct fiemap_cache *cache,
				u64 offset, u64 phys, u64 len, u32 flags)
{ … }

/*
 * Emit last fiemap cache
 *
 * The last fiemap cache may still be cached in the following case:
 * 0		      4k		    8k
 * |<- Fiemap range ->|
 * |<------------  First extent ----------->|
 *
 * In this case, the first extent range will be cached but not emitted.
 * So we must emit it before ending extent_fiemap().
 */
static int emit_last_fiemap_cache(struct fiemap_extent_info *fieinfo,
				  struct fiemap_cache *cache)
{ … }

static int fiemap_next_leaf_item(struct btrfs_inode *inode, struct btrfs_path *path)
{ … }

/*
 * Search for the first file extent item that starts at a given file offset or
 * the one that starts immediately before that offset.
 * Returns: 0 on success, < 0 on error, 1 if not found.
 */
static int fiemap_search_slot(struct btrfs_inode *inode, struct btrfs_path *path,
			      u64 file_offset)
{ … }

/*
 * Process a range which is a hole or a prealloc extent in the inode's subvolume
 * btree. If @disk_bytenr is 0, we are dealing with a hole, otherwise a prealloc
 * extent. The end offset (@end) is inclusive.
 */
static int fiemap_process_hole(struct btrfs_inode *inode,
			       struct fiemap_extent_info *fieinfo,
			       struct fiemap_cache *cache,
			       struct extent_state **delalloc_cached_state,
			       struct btrfs_backref_share_check_ctx *backref_ctx,
			       u64 disk_bytenr, u64 extent_offset,
			       u64 extent_gen,
			       u64 start, u64 end)
{ … }

static int fiemap_find_last_extent_offset(struct btrfs_inode *inode,
					  struct btrfs_path *path,
					  u64 *last_extent_end_ret)
{ … }

static int extent_fiemap(struct btrfs_inode *inode,
			 struct fiemap_extent_info *fieinfo,
			 u64 start, u64 len)
{ … }

int btrfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
		 u64 start, u64 len)
{ … }