Re: [PATCH v6 4/5] dax: for truncate/hole-punch, do zeroing through the driver if possible

[Jan Kara]

On Tue 10-05-16 12:49:15, Vishal Verma wrote:
> In the truncate or hole-punch path in dax, we clear out sub-page ranges.
> If these sub-page ranges are sector aligned and sized, we can do the
> zeroing through the driver instead so that error-clearing is handled
> automatically.
> 
> For sub-sector ranges, we still have to rely on clear_pmem and have the
> possibility of tripping over errors.
> 
> Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
> Cc: Ross Zwisler <ross.zwisler@xxxxxxxxxxxxxxx>
> Cc: Jeff Moyer <jmoyer@xxxxxxxxxx>
> Cc: Christoph Hellwig <hch@xxxxxxxxxxxxx>
> Cc: Dave Chinner <david@xxxxxxxxxxxxx>
> Cc: Jan Kara <jack@xxxxxxx>
> Reviewed-by: Christoph Hellwig <hch@xxxxxx>
> Signed-off-by: Vishal Verma <vishal.l.verma@xxxxxxxxx>

...

> +static bool dax_range_is_aligned(struct block_device *bdev,
> +				 struct blk_dax_ctl *dax, unsigned int offset,
> +				 unsigned int length)
> +{
> +	unsigned short sector_size = bdev_logical_block_size(bdev);
> +
> +	if (!IS_ALIGNED(((u64)dax->addr + offset), sector_size))

One more question: 'dax' is initialized in dax_zero_page_range() and
dax->addr is going to be always NULL here. So either you forgot to call
dax_map_atomic() to get the addr or the use of dax->addr is just bogus
(which is what I currently believe since I see no way how the address could
be unaligned with the sector_size)...

								Honza
> +		return false;
> +	if (!IS_ALIGNED(length, sector_size))
> +		return false;
> +
> +	return true;
> +}
> +
>  /**
>   * dax_zero_page_range - zero a range within a page of a DAX file
>   * @inode: The file being truncated
> @@ -1240,11 +1254,16 @@ int dax_zero_page_range(struct inode *inode, loff_t from, unsigned length,
>  			.size = PAGE_SIZE,
>  		};
>  
> -		if (dax_map_atomic(bdev, &dax) < 0)
> -			return PTR_ERR(dax.addr);
> -		clear_pmem(dax.addr + offset, length);
> -		wmb_pmem();
> -		dax_unmap_atomic(bdev, &dax);
> +		if (dax_range_is_aligned(bdev, &dax, offset, length))
> +			return blkdev_issue_zeroout(bdev, dax.sector,
> +					length >> 9, GFP_NOFS, true);
> +		else {
> +			if (dax_map_atomic(bdev, &dax) < 0)
> +				return PTR_ERR(dax.addr);
> +			clear_pmem(dax.addr + offset, length);
> +			wmb_pmem();
> +			dax_unmap_atomic(bdev, &dax);
> +		}
>  	}
>  
>  	return 0;
> -- 
> 2.5.5
> 
-- 
Jan Kara <jack@xxxxxxxx>
SUSE Labs, CR