Re: [PATCH 4/8] btrfs: Switch to iomap_dio_rw() for dio

[Nikolay Borisov <nborisov@suse.com>]

On 11.12.19 г. 1:01 ч., Goldwyn Rodrigues wrote:
> From: Goldwyn Rodrigues <rgoldwyn@suse.com>
> 
> Switch from __blockdev_direct_IO() to iomap_dio_rw().
> Rename btrfs_get_blocks_direct() to btrfs_dio_iomap_begin() and use it
> as iomap_begin() for iomap direct I/O functions. This function
> allocates and locks all the blocks required for the I/O.
> btrfs_submit_direct() is used as the submit_io() hook for direct I/O
> ops.
> 
> Since we need direct I/O reads to go through iomap_dio_rw(), we change
> file_operations.read_iter() to a btrfs_file_read_iter() which calls
> btrfs_direct_IO() for direct reads and falls back to
> generic_file_buffered_read() for incomplete reads and buffered reads.
> 
> We don't need address_space.direct_IO() anymore so set it to noop.
> Similarly, we don't need flags used in __blockdev_direct_IO(). iomap is
> capable of direct I/O reads from a hole, so we don't need to return
> -ENOENT.
> 
> BTRFS direct I/O is now done under i_rwsem, shared in case of
> reads and exclusive in case of writes. This guards against simultaneous
> truncates.
> 
> Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
> ---
>  fs/btrfs/ctree.h |   1 +
>  fs/btrfs/file.c  |  21 ++++++-
>  fs/btrfs/inode.c | 184 ++++++++++++++++++++++++++-----------------------------
>  3 files changed, 107 insertions(+), 99 deletions(-)
> 

<snip>

> +
> +/*
> + * btrfs_direct_IO - perform direct I/O
> + * inode->i_rwsem must be locked before calling this function, shared or exclusive.

Instead of having this as a comment which cannot easily be checked
automatically I'd rather it gets codified via lockdep_assert_held. I
believe this is in line with Dave's comment comment on patch 3.

> + * @iocb - kernel iocb
> + * @iter - iter to/from data is copied
> + */
> +
> +ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
>  {
>  	struct file *file = iocb->ki_filp;
>  	struct inode *inode = file->f_mapping->host;
> @@ -8662,28 +8676,13 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
>  	struct extent_changeset *data_reserved = NULL;
>  	loff_t offset = iocb->ki_pos;
>  	size_t count = 0;
> -	int flags = 0;
> -	bool wakeup = true;
>  	bool relock = false;
>  	ssize_t ret;
>  
>  	if (check_direct_IO(fs_info, iter, offset))
>  		return 0;
>  
> -	inode_dio_begin(inode);
> -
> -	/*
> -	 * The generic stuff only does filemap_write_and_wait_range, which
> -	 * isn't enough if we've written compressed pages to this area, so
> -	 * we need to flush the dirty pages again to make absolutely sure
> -	 * that any outstanding dirty pages are on disk.
> -	 */
>  	count = iov_iter_count(iter);
> -	if (test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
> -		     &BTRFS_I(inode)->runtime_flags))
> -		filemap_fdatawrite_range(inode->i_mapping, offset,
> -					 offset + count - 1);
> -
>  	if (iov_iter_rw(iter) == WRITE) {
>  		/*
>  		 * If the write DIO is beyond the EOF, we need update
> @@ -8714,17 +8713,11 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
>  		dio_data.unsubmitted_oe_range_end = (u64)offset;
>  		current->journal_info = &dio_data;
>  		down_read(&BTRFS_I(inode)->dio_sem);
> -	} else if (test_bit(BTRFS_INODE_READDIO_NEED_LOCK,
> -				     &BTRFS_I(inode)->runtime_flags)) {
> -		inode_dio_end(inode);
> -		flags = DIO_LOCKING | DIO_SKIP_HOLES;
> -		wakeup = false;
>  	}
>  
> -	ret = __blockdev_direct_IO(iocb, inode,
> -				   fs_info->fs_devices->latest_bdev,
> -				   iter, btrfs_get_blocks_direct, NULL,
> -				   btrfs_submit_direct, flags);
> +	ret = iomap_dio_rw(iocb, iter, &btrfs_dio_iomap_ops, &btrfs_dops,
> +			is_sync_kiocb(iocb));
> +
>  	if (iov_iter_rw(iter) == WRITE) {
>  		up_read(&BTRFS_I(inode)->dio_sem);
>  		current->journal_info = NULL;
> @@ -8751,11 +8744,8 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
>  		btrfs_delalloc_release_extents(BTRFS_I(inode), count);
>  	}
>  out:
> -	if (wakeup)
> -		inode_dio_end(inode);
>  	if (relock)
>  		inode_lock(inode);
> -
>  	extent_changeset_free(data_reserved);
>  	return ret;
>  }
> @@ -11045,7 +11035,7 @@ static const struct address_space_operations btrfs_aops = {
>  	.writepage	= btrfs_writepage,
>  	.writepages	= btrfs_writepages,
>  	.readpages	= btrfs_readpages,
> -	.direct_IO	= btrfs_direct_IO,
> +	.direct_IO	= noop_direct_IO,
>  	.invalidatepage = btrfs_invalidatepage,
>  	.releasepage	= btrfs_releasepage,
>  	.set_page_dirty	= btrfs_set_page_dirty,
>