Re: [PATCH v3 08/23] ceph: Convert ceph_writepages_start() to use filemap_get_folios_tag()

[Jeff Layton]

On Mon, 2022-10-17 at 13:24 -0700, Vishal Moola (Oracle) wrote:
> Convert function to use a folio_batch instead of pagevec. This is in
> preparation for the removal of find_get_pages_range_tag().
> 
> Also some minor renaming for consistency.
> 
> Signed-off-by: Vishal Moola (Oracle) <vishal.moola@xxxxxxxxx>
> ---
>  fs/ceph/addr.c | 58 ++++++++++++++++++++++++++------------------------
>  1 file changed, 30 insertions(+), 28 deletions(-)
> 
> diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
> index dcf701b05cc1..d2361d51db39 100644
> --- a/fs/ceph/addr.c
> +++ b/fs/ceph/addr.c
> @@ -792,7 +792,7 @@ static int ceph_writepages_start(struct address_space *mapping,
>  	struct ceph_vino vino = ceph_vino(inode);
>  	pgoff_t index, start_index, end = -1;
>  	struct ceph_snap_context *snapc = NULL, *last_snapc = NULL, *pgsnapc;
> -	struct pagevec pvec;
> +	struct folio_batch fbatch;
>  	int rc = 0;
>  	unsigned int wsize = i_blocksize(inode);
>  	struct ceph_osd_request *req = NULL;
> @@ -821,7 +821,7 @@ static int ceph_writepages_start(struct address_space *mapping,
>  	if (fsc->mount_options->wsize < wsize)
>  		wsize = fsc->mount_options->wsize;
>  
> -	pagevec_init(&pvec);
> +	folio_batch_init(&fbatch);
>  
>  	start_index = wbc->range_cyclic ? mapping->writeback_index : 0;
>  	index = start_index;
> @@ -869,7 +869,7 @@ static int ceph_writepages_start(struct address_space *mapping,
>  
>  	while (!done && index <= end) {
>  		int num_ops = 0, op_idx;
> -		unsigned i, pvec_pages, max_pages, locked_pages = 0;
> +		unsigned i, nr_folios, max_pages, locked_pages = 0;
>  		struct page **pages = NULL, **data_pages;
>  		struct page *page;
>  		pgoff_t strip_unit_end = 0;
> @@ -879,13 +879,13 @@ static int ceph_writepages_start(struct address_space *mapping,
>  		max_pages = wsize >> PAGE_SHIFT;
>  
>  get_more_pages:
> -		pvec_pages = pagevec_lookup_range_tag(&pvec, mapping, &index,
> -						end, PAGECACHE_TAG_DIRTY);
> -		dout("pagevec_lookup_range_tag got %d\n", pvec_pages);
> -		if (!pvec_pages && !locked_pages)
> +		nr_folios = filemap_get_folios_tag(mapping, &index,
> +				end, PAGECACHE_TAG_DIRTY, &fbatch);
> +		dout("pagevec_lookup_range_tag got %d\n", nr_folios);
> +		if (!nr_folios && !locked_pages)
>  			break;
> -		for (i = 0; i < pvec_pages && locked_pages < max_pages; i++) {
> -			page = pvec.pages[i];
> +		for (i = 0; i < nr_folios && locked_pages < max_pages; i++) {
> +			page = &fbatch.folios[i]->page;
>  			dout("? %p idx %lu\n", page, page->index);
>  			if (locked_pages == 0)
>  				lock_page(page);  /* first page */
> @@ -995,7 +995,7 @@ static int ceph_writepages_start(struct address_space *mapping,
>  				len = 0;
>  			}
>  
> -			/* note position of first page in pvec */
> +			/* note position of first page in fbatch */
>  			dout("%p will write page %p idx %lu\n",
>  			     inode, page, page->index);
>  
> @@ -1005,30 +1005,30 @@ static int ceph_writepages_start(struct address_space *mapping,
>  				fsc->write_congested = true;
>  
>  			pages[locked_pages++] = page;
> -			pvec.pages[i] = NULL;
> +			fbatch.folios[i] = NULL;
>  
>  			len += thp_size(page);
>  		}
>  
>  		/* did we get anything? */
>  		if (!locked_pages)
> -			goto release_pvec_pages;
> +			goto release_folios;
>  		if (i) {
>  			unsigned j, n = 0;
> -			/* shift unused page to beginning of pvec */
> -			for (j = 0; j < pvec_pages; j++) {
> -				if (!pvec.pages[j])
> +			/* shift unused page to beginning of fbatch */
> +			for (j = 0; j < nr_folios; j++) {
> +				if (!fbatch.folios[j])
>  					continue;
>  				if (n < j)
> -					pvec.pages[n] = pvec.pages[j];
> +					fbatch.folios[n] = fbatch.folios[j];
>  				n++;
>  			}
> -			pvec.nr = n;
> +			fbatch.nr = n;
>  
> -			if (pvec_pages && i == pvec_pages &&
> +			if (nr_folios && i == nr_folios &&
>  			    locked_pages < max_pages) {
> -				dout("reached end pvec, trying for more\n");
> -				pagevec_release(&pvec);
> +				dout("reached end fbatch, trying for more\n");
> +				folio_batch_release(&fbatch);
>  				goto get_more_pages;
>  			}
>  		}
> @@ -1164,10 +1164,10 @@ static int ceph_writepages_start(struct address_space *mapping,
>  		if (wbc->nr_to_write <= 0 && wbc->sync_mode == WB_SYNC_NONE)
>  			done = true;
>  
> -release_pvec_pages:
> -		dout("pagevec_release on %d pages (%p)\n", (int)pvec.nr,
> -		     pvec.nr ? pvec.pages[0] : NULL);
> -		pagevec_release(&pvec);
> +release_folios:
> +		dout("folio_batch release on %d folios (%p)\n", (int)fbatch.nr,
> +		     fbatch.nr ? fbatch.folios[0] : NULL);
> +		folio_batch_release(&fbatch);
>  	}
>  
>  	if (should_loop && !done) {
> @@ -1184,15 +1184,17 @@ static int ceph_writepages_start(struct address_space *mapping,
>  			unsigned i, nr;
>  			index = 0;
>  			while ((index <= end) &&
> -			       (nr = pagevec_lookup_tag(&pvec, mapping, &index,
> -						PAGECACHE_TAG_WRITEBACK))) {
> +			       (nr = filemap_get_folios_tag(mapping, &index,
> +						(pgoff_t)-1,
> +						PAGECACHE_TAG_WRITEBACK,
> +						&fbatch))) {
>  				for (i = 0; i < nr; i++) {
> -					page = pvec.pages[i];
> +					page = &fbatch.folios[i]->page;
>  					if (page_snap_context(page) != snapc)
>  						continue;
>  					wait_on_page_writeback(page);
>  				}
> -				pagevec_release(&pvec);
> +				folio_batch_release(&fbatch);
>  				cond_resched();
>  			}
>  		}

I took a brief look and this looks like a fairly straightforward
conversion. It definitely needs testing however.

The hope was to get ceph converted over to using the netfs write
helpers, but that's taking a lot longer than expected. It's really up to
Xiubo at this point, but I don't have an issue in principle with taking
this patch in before the netfs conversion, particularly if it's blocking
other work.

Acked-by: Jeff Layton <jlayton@xxxxxxxxxx>