Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit e3b8a485 authored by Filipe Manana's avatar Filipe Manana Committed by David Sterba
Browse files

Btrfs: fix reported number of inode blocks after buffered append writes 



The patch from commit a7e3b975 ("Btrfs: fix reported number of inode
blocks") introduced a regression where if we do a buffered write starting
at position equal to or greater than the file's size and then stat(2) the
file before writeback is triggered, the number of used blocks does not
change (unless there's a prealloc/unwritten extent). Example:

  $ xfs_io -f -c "pwrite -S 0xab 0 64K" foobar
  $ du -h foobar
  0	foobar
  $ sync
  $ du -h foobar
  64K	foobar

The first version of that patch didn't had this regression and the second
version, which was the one committed, was made only to address some
performance regression detected by the intel test robots using fs_mark.

This fixes the regression by setting the new delaloc bit in the range, and
doing it at btrfs_dirty_pages() while setting the regular dealloc bit as
well, so that this way we set both bits at once avoiding navigation of the
inode's io tree twice. Doing it at btrfs_dirty_pages() is also the most
meaninful place, as we should set the new dellaloc bit when if we set the
delalloc bit, which happens only if we copied bytes into the pages at
__btrfs_buffered_write().

This was making some of LTP's du tests fail, which can be quickly run
using a command line like the following:

  $ ./runltp -q -p -l /ltp.log -f commands -s du -d /mnt

Fixes: a7e3b975 ("Btrfs: fix reported number of inode blocks")
Signed-off-by: default avatarFilipe Manana <fdmanana@suse.com>
Signed-off-by: default avatarDavid Sterba <dsterba@suse.com>
parent f48bf66b

fs/btrfs/ctree.h

+1 −0
Original line number Diff line number Diff line
@@ -3180,6 +3180,7 @@ int btrfs_start_delalloc_inodes(struct btrfs_root *root, int delay_iput); 
int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int delay_iput,

			       int nr);

int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end,

			      unsigned int extra_bits,

			      struct extent_state **cached_state, int dedupe);

int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,

			     struct btrfs_root *new_root,

fs/btrfs/extent_io.h

+3 −2
Original line number Diff line number Diff line
@@ -365,10 +365,11 @@ int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, 
		       struct extent_state **cached_state);



static inline int set_extent_delalloc(struct extent_io_tree *tree, u64 start,

		u64 end, struct extent_state **cached_state)

				      u64 end, unsigned int extra_bits,

				      struct extent_state **cached_state)

{

	return set_extent_bit(tree, start, end,

			      EXTENT_DELALLOC | EXTENT_UPTODATE,

			      EXTENT_DELALLOC | EXTENT_UPTODATE | extra_bits,

			      NULL, cached_state, GFP_NOFS);

}

fs/btrfs/file.c

+26 −17
Original line number Diff line number Diff line
@@ -538,14 +538,34 @@ int btrfs_dirty_pages(struct inode *inode, struct page **pages, 
	u64 end_of_last_block;

	u64 end_pos = pos + write_bytes;

	loff_t isize = i_size_read(inode);

	unsigned int extra_bits = 0;



	start_pos = pos & ~((u64) fs_info->sectorsize - 1);

	num_bytes = round_up(write_bytes + pos - start_pos,

			     fs_info->sectorsize);



	end_of_last_block = start_pos + num_bytes - 1;



	if (!btrfs_is_free_space_inode(BTRFS_I(inode))) {

		if (start_pos >= isize &&

		    !(BTRFS_I(inode)->flags & BTRFS_INODE_PREALLOC)) {

			/*

			 * There can't be any extents following eof in this case

			 * so just set the delalloc new bit for the range

			 * directly.

			 */

			extra_bits |= EXTENT_DELALLOC_NEW;

		} else {

			err = btrfs_find_new_delalloc_bytes(BTRFS_I(inode),

							    start_pos,

							    num_bytes, cached);

			if (err)

				return err;

		}

	}



	err = btrfs_set_extent_delalloc(inode, start_pos, end_of_last_block,

					cached, 0);

					extra_bits, cached, 0);

	if (err)

		return err;
@@ -1473,10 +1493,8 @@ lock_and_cleanup_extent_if_need(struct btrfs_inode *inode, struct page **pages, 
		+ round_up(pos + write_bytes - start_pos,

			   fs_info->sectorsize) - 1;



	if (start_pos < inode->vfs_inode.i_size ||

	    (inode->flags & BTRFS_INODE_PREALLOC)) {

	if (start_pos < inode->vfs_inode.i_size) {

		struct btrfs_ordered_extent *ordered;

		unsigned int clear_bits;



		lock_extent_bits(&inode->io_tree, start_pos, last_pos,

				cached_state);
@@ -1498,19 +1516,10 @@ lock_and_cleanup_extent_if_need(struct btrfs_inode *inode, struct page **pages, 
		}

		if (ordered)

			btrfs_put_ordered_extent(ordered);

		ret = btrfs_find_new_delalloc_bytes(inode, start_pos,

						    last_pos - start_pos + 1,

						    cached_state);

		clear_bits = EXTENT_DIRTY | EXTENT_DELALLOC |

			EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG;

		if (ret)

			clear_bits |= EXTENT_DELALLOC_NEW | EXTENT_LOCKED;

		clear_extent_bit(&inode->io_tree, start_pos,

				 last_pos, clear_bits,

				 (clear_bits & EXTENT_LOCKED) ? 1 : 0,

				 0, cached_state, GFP_NOFS);

		if (ret)

			return ret;

		clear_extent_bit(&inode->io_tree, start_pos, last_pos,

				 EXTENT_DIRTY | EXTENT_DELALLOC |

				 EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,

				 0, 0, cached_state, GFP_NOFS);

		*lockstart = start_pos;

		*lockend = last_pos;

		ret = 1;

fs/btrfs/inode.c

+5 −4
Original line number Diff line number Diff line
@@ -2032,11 +2032,12 @@ static noinline int add_pending_csums(struct btrfs_trans_handle *trans, 
}



int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end,

			      unsigned int extra_bits,

			      struct extent_state **cached_state, int dedupe)

{

	WARN_ON((end & (PAGE_SIZE - 1)) == 0);

	return set_extent_delalloc(&BTRFS_I(inode)->io_tree, start, end,

				   cached_state);

				   extra_bits, cached_state);

}



/* see btrfs_writepage_start_hook for details on why this is required */
@@ -2097,7 +2098,7 @@ static void btrfs_writepage_fixup_worker(struct btrfs_work *work) 
		goto out;

	 }



	btrfs_set_extent_delalloc(inode, page_start, page_end, &cached_state,

	btrfs_set_extent_delalloc(inode, page_start, page_end, 0, &cached_state,

				  0);

	ClearPageChecked(page);

	set_page_dirty(page);
@@ -4797,7 +4798,7 @@ int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len, 
			  EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,

			  0, 0, &cached_state, GFP_NOFS);



	ret = btrfs_set_extent_delalloc(inode, block_start, block_end,

	ret = btrfs_set_extent_delalloc(inode, block_start, block_end, 0,

					&cached_state, 0);

	if (ret) {

		unlock_extent_cached(io_tree, block_start, block_end,
@@ -9163,7 +9164,7 @@ int btrfs_page_mkwrite(struct vm_fault *vmf) 
			  EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,

			  0, 0, &cached_state, GFP_NOFS);



	ret = btrfs_set_extent_delalloc(inode, page_start, end,

	ret = btrfs_set_extent_delalloc(inode, page_start, end, 0,

					&cached_state, 0);

	if (ret) {

		unlock_extent_cached(io_tree, page_start, page_end,

fs/btrfs/relocation.c

+2 −1
Original line number Diff line number Diff line
@@ -3268,7 +3268,8 @@ static int relocate_file_extent_cluster(struct inode *inode, 
			nr++;

		}



		btrfs_set_extent_delalloc(inode, page_start, page_end, NULL, 0);

		btrfs_set_extent_delalloc(inode, page_start, page_end, 0, NULL,

					  0);

		set_page_dirty(page);



		unlock_extent(&BTRFS_I(inode)->io_tree,