On Wed, May 10, 2017 at 07:49:47PM -0700, Dan Williams wrote:
> The conversion of __dax_zero_page_range() to 'struct dax_operations'
> caused it to frequently fail. The mistake was treating the @size
> parameter as a dax mapping length rather than just a length of the
> clear_pmem() operation. The dax mapping length is assumed to be hard
> coded as PAGE_SIZE.
>
> Without this fix any page unaligned zeroing request will trigger a
> -EINVAL return from bdev_dax_pgoff().
>
> Cc: Jan Kara <j...@suse.com>
> Cc: Christoph Hellwig <h...@lst.de>
> Reported-by: Ross Zwisler <ross.zwis...@linux.intel.com>
Yep, this solves the issue for me. Thanks!
Tested-by: Ross Zwisler <ross.zwis...@linux.intel.com>
> Fixes: cccbce671582 ("filesystem-dax: convert to dax_direct_access()")
> Signed-off-by: Dan Williams <dan.j.willi...@intel.com>
> ---
> fs/dax.c | 4 ++--
> 1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/fs/dax.c b/fs/dax.c
> index ce9dc9c3e829..5ee1d212d81f 100644
> --- a/fs/dax.c
> +++ b/fs/dax.c
> @@ -971,12 +971,12 @@ int __dax_zero_page_range(struct block_device *bdev,
> void *kaddr;
> pfn_t pfn;
>
> - rc = bdev_dax_pgoff(bdev, sector, size, &pgoff);
> + rc = bdev_dax_pgoff(bdev, sector, PAGE_SIZE, &pgoff);
> if (rc)
> return rc;
>
> id = dax_read_lock();
> - rc = dax_direct_access(dax_dev, pgoff, PHYS_PFN(size), &kaddr,
> + rc = dax_direct_access(dax_dev, pgoff, 1, &kaddr,
> &pfn);
> if (rc < 0) {
> dax_read_unlock(id);
>
