Re: [PATCH v2 5/5] block: enable dax for raw block devices

[Jeff Moyer <jmoyer@redhat.com>]

Dan Williams <dan.j.williams@intel.com> writes:

> If an application wants exclusive access to all of the persistent memory
> provided by an NVDIMM namespace it can use this raw-block-dax facility
> to forgo establishing a filesystem.  This capability is targeted
> primarily to hypervisors wanting to provision persistent memory for
> guests.

OK, I'm going to expose my ignorance here.  :)  Why does the block device
need a page_mkwrite handler?

-Jeff

> Cc: Jeff Moyer <jmoyer@redhat.com>
> Cc: Christoph Hellwig <hch@lst.de>
> Cc: Dave Chinner <david@fromorbit.com>
> Cc: Andrew Morton <akpm@linux-foundation.org>
> Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
> Reviewed-by: Jan Kara <jack@suse.com>
> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
> ---
>  fs/block_dev.c |   60 +++++++++++++++++++++++++++++++++++++++++++++++++++++++-
>  1 file changed, 59 insertions(+), 1 deletion(-)
>
> diff --git a/fs/block_dev.c b/fs/block_dev.c
> index c1f691859a56..210d05103657 100644
> --- a/fs/block_dev.c
> +++ b/fs/block_dev.c
> @@ -1687,13 +1687,71 @@ static const struct address_space_operations def_blk_aops = {
>  	.is_dirty_writeback = buffer_check_dirty_writeback,
>  };
>  
> +#ifdef CONFIG_FS_DAX
> +/*
> + * In the raw block case we do not need to contend with truncation nor
> + * unwritten file extents.  Without those concerns there is no need for
> + * additional locking beyond the mmap_sem context that these routines
> + * are already executing under.
> + *
> + * Note, there is no protection if the block device is dynamically
> + * resized (partition grow/shrink) during a fault. A stable block device
> + * size is already not enforced in the blkdev_direct_IO path.
> + *
> + * For DAX, it is the responsibility of the block device driver to
> + * ensure the whole-disk device size is stable while requests are in
> + * flight.
> + *
> + * Finally, in contrast to the generic_file_mmap() path, there are no
> + * calls to sb_start_pagefault().  That is meant to synchronize write
> + * faults against requests to freeze the contents of the filesystem
> + * hosting vma->vm_file.  However, in the case of a block device special
> + * file, it is a 0-sized device node usually hosted on devtmpfs, i.e.
> + * nothing to do with the super_block for bdev_file_inode(vma->vm_file).
> + * We could call get_super() in this path to retrieve the right
> + * super_block, but the generic_file_mmap() path does not do this for
> + * the CONFIG_FS_DAX=n case.
> + */
> +static int blkdev_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
> +{
> +	return __dax_fault(vma, vmf, blkdev_get_block, NULL);
> +}
> +
> +static int blkdev_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
> +		pmd_t *pmd, unsigned int flags)
> +{
> +	return __dax_pmd_fault(vma, addr, pmd, flags, blkdev_get_block, NULL);
> +}
> +
> +static const struct vm_operations_struct blkdev_dax_vm_ops = {
> +	.page_mkwrite	= blkdev_dax_fault,
> +	.fault		= blkdev_dax_fault,
> +	.pmd_fault	= blkdev_dax_pmd_fault,
> +};
> +
> +static int blkdev_mmap(struct file *file, struct vm_area_struct *vma)
> +{
> +	struct inode *bd_inode = bdev_file_inode(file);
> +
> +	if (!IS_DAX(bd_inode))
> +		return generic_file_mmap(file, vma);
> +
> +	file_accessed(file);
> +	vma->vm_ops = &blkdev_dax_vm_ops;
> +	vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE;
> +	return 0;
> +}
> +#else
> +#define blkdev_mmap generic_file_mmap
> +#endif
> +
>  const struct file_operations def_blk_fops = {
>  	.open		= blkdev_open,
>  	.release	= blkdev_close,
>  	.llseek		= block_llseek,
>  	.read_iter	= blkdev_read_iter,
>  	.write_iter	= blkdev_write_iter,
> -	.mmap		= generic_file_mmap,
> +	.mmap		= blkdev_mmap,
>  	.fsync		= blkdev_fsync,
>  	.unlocked_ioctl	= block_ioctl,
>  #ifdef CONFIG_COMPAT