Re: [PATCH v5 4/5] dax: for truncate/hole-punch, do zeroing through the driver if possible

[Jan Kara <jack@xxxxxxx>]

On Fri 06-05-16 15:53:10, Vishal Verma wrote:
> +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 (((u64)dax->addr + offset) % sector_size)
> +             return false;
> +     if (length % sector_size)
> +             return false;

sector_size should better be a power of two so you can save some cycles by
using & instead of %.

> @@ -1240,11 +1254,17 @@ 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 / bdev_logical_block_size(bdev),
> +                                     GFP_NOFS, true);

This is actually wrong. blkdev_issue_zeroout() expects length to be simply
in units of 512-bytes. So you need length >> 9 here.

                                                                Honza
-- 
Jan Kara <jack@xxxxxxxx>
SUSE Labs, CR