Re: [PATCH 10/18] dax: replace mmap entry in case of CoW

["Darrick J. Wong" <darrick.wong@oracle.com>]

On Tue, Apr 16, 2019 at 11:41:46AM -0500, Goldwyn Rodrigues wrote:
> From: Goldwyn Rodrigues <rgoldwyn@suse.com>
> 
> We replace the existing entry to the newly allocated one
> in case of CoW. Also, we mark the entry as PAGECACHE_TAG_TOWRITE
> so writeback marks this entry as writeprotected. This
> helps us snapshots so new write pagefaults after snapshots
> trigger a CoW.
> 
> Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
> ---
>  fs/dax.c | 23 +++++++++++++++--------
>  1 file changed, 15 insertions(+), 8 deletions(-)
> 
> diff --git a/fs/dax.c b/fs/dax.c
> index 45fc2e18969a..d5100cbe8bd2 100644
> --- a/fs/dax.c
> +++ b/fs/dax.c
> @@ -708,14 +708,15 @@ static int copy_user_dax(struct block_device *bdev, struct dax_device *dax_dev,
>   */
>  static void *dax_insert_entry(struct xa_state *xas,
>  		struct address_space *mapping, struct vm_fault *vmf,
> -		void *entry, pfn_t pfn, unsigned long flags, bool dirty)
> +		void *entry, pfn_t pfn, unsigned long flags, bool dirty,
> +		bool cow)

I still wish these were flags instead of double booleans that will be
easy to mix up, especially since this is a static function and nobody
else has to see the flags...

#define IE_DIRTY	(1 << 0) /* mark entry and inode dirty */
#define IE_REPLACE	(1 << 1) /* replacing one page with another */

...otoh maybe I'll just defer to the maintainer. :)

>  {
>  	void *new_entry = dax_make_entry(pfn, flags);
>  
>  	if (dirty)
>  		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
>  
> -	if (dax_is_zero_entry(entry) && !(flags & DAX_ZERO_PAGE)) {
> +	if (cow || (dax_is_zero_entry(entry) && !(flags & DAX_ZERO_PAGE))) {
>  		unsigned long index = xas->xa_index;
>  		/* we are replacing a zero page with block mapping */

These comments need updating.

Otherwise looks good to me...

--D

>  		if (dax_is_pmd_entry(entry))
> @@ -727,12 +728,12 @@ static void *dax_insert_entry(struct xa_state *xas,
>  
>  	xas_reset(xas);
>  	xas_lock_irq(xas);
> -	if (dax_entry_size(entry) != dax_entry_size(new_entry)) {
> +	if (cow || (dax_entry_size(entry) != dax_entry_size(new_entry))) {
>  		dax_disassociate_entry(entry, mapping, false);
>  		dax_associate_entry(new_entry, mapping, vmf->vma, vmf->address);
>  	}
>  
> -	if (dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) {
> +	if (cow || dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) {
>  		/*
>  		 * Only swap our new entry into the page cache if the current
>  		 * entry is a zero page or an empty entry.  If a normal PTE or
> @@ -752,6 +753,9 @@ static void *dax_insert_entry(struct xa_state *xas,
>  	if (dirty)
>  		xas_set_mark(xas, PAGECACHE_TAG_DIRTY);
>  
> +	if (cow)
> +		xas_set_mark(xas, PAGECACHE_TAG_TOWRITE);
> +
>  	xas_unlock_irq(xas);
>  	return entry;
>  }
> @@ -1031,7 +1035,7 @@ static vm_fault_t dax_load_hole(struct xa_state *xas,
>  	vm_fault_t ret;
>  
>  	*entry = dax_insert_entry(xas, mapping, vmf, *entry, pfn,
> -			DAX_ZERO_PAGE, false);
> +			DAX_ZERO_PAGE, false, false);
>  
>  	ret = vmf_insert_mixed(vmf->vma, vaddr, pfn);
>  	trace_dax_load_hole(inode, vmf, ret);
> @@ -1388,7 +1392,8 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
>  				memset(addr, 0, PAGE_SIZE);
>  		}
>  		entry = dax_insert_entry(&xas, mapping, vmf, entry, pfn,
> -						 0, write && !sync);
> +						 0, write && !sync,
> +						 iomap.type == IOMAP_DAX_COW);
>  
>  		/*
>  		 * If we are doing synchronous page fault and inode needs fsync,
> @@ -1467,7 +1472,8 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf,
>  
>  	pfn = page_to_pfn_t(zero_page);
>  	*entry = dax_insert_entry(xas, mapping, vmf, *entry, pfn,
> -			DAX_PMD | DAX_ZERO_PAGE, false);
> +			DAX_PMD | DAX_ZERO_PAGE, false,
> +			iomap->type == IOMAP_DAX_COW);
>  
>  	ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd);
>  	if (!pmd_none(*(vmf->pmd))) {
> @@ -1590,7 +1596,8 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
>  			goto finish_iomap;
>  
>  		entry = dax_insert_entry(&xas, mapping, vmf, entry, pfn,
> -						DAX_PMD, write && !sync);
> +						DAX_PMD, write && !sync,
> +						false);
>  
>  		/*
>  		 * If we are doing synchronous page fault and inode needs fsync,
> -- 
> 2.16.4
>