diff mbox series

[v6,03/11] filemap: allocate mapping_min_order folios in the page cache

Message ID 20240529134509.120826-4-kernel@pankajraghav.com (mailing list archive)
State New
Headers show
Series enable bs > ps in XFS | expand

Commit Message

Pankaj Raghav (Samsung) May 29, 2024, 1:45 p.m. UTC
From: Pankaj Raghav <p.raghav@samsung.com>

filemap_create_folio() and do_read_cache_folio() were always allocating
folio of order 0. __filemap_get_folio was trying to allocate higher
order folios when fgp_flags had higher order hint set but it will default
to order 0 folio if higher order memory allocation fails.

Supporting mapping_min_order implies that we guarantee each folio in the
page cache has at least an order of mapping_min_order. When adding new
folios to the page cache we must also ensure the index used is aligned to
the mapping_min_order as the page cache requires the index to be aligned
to the order of the folio.

Signed-off-by: Pankaj Raghav <p.raghav@samsung.com>
Co-developed-by: Luis Chamberlain <mcgrof@kernel.org>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
---
 include/linux/pagemap.h | 20 ++++++++++++++++++++
 mm/filemap.c            | 24 +++++++++++++++++-------
 2 files changed, 37 insertions(+), 7 deletions(-)

Comments

Matthew Wilcox June 3, 2024, 12:18 p.m. UTC | #1
On Wed, May 29, 2024 at 03:45:01PM +0200, Pankaj Raghav (Samsung) wrote:
> @@ -1919,8 +1921,10 @@ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
>  		folio_wait_stable(folio);
>  no_page:
>  	if (!folio && (fgp_flags & FGP_CREAT)) {
> -		unsigned order = FGF_GET_ORDER(fgp_flags);
> +		unsigned int min_order = mapping_min_folio_order(mapping);
> +		unsigned int order = max(min_order, FGF_GET_ORDER(fgp_flags));
>  		int err;
> +		index = mapping_align_start_index(mapping, index);
>  
>  		if ((fgp_flags & FGP_WRITE) && mapping_can_writeback(mapping))
>  			gfp |= __GFP_WRITE;
> @@ -1958,7 +1962,7 @@ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
>  				break;
>  			folio_put(folio);
>  			folio = NULL;
> -		} while (order-- > 0);
> +		} while (order-- > min_order);

I'd argue you also need to change:

-                       if (order > 0)
+			if (order > min_order)
                                alloc_gfp |= __GFP_NORETRY | __GFP_NOWARN;

since that is the last point at which we can fall back.  If we can't
immediately allocate a min_order folio, we want to retry, and we
want to warn if we can't get it.
Pankaj Raghav (Samsung) June 4, 2024, 9:42 a.m. UTC | #2
On Mon, Jun 03, 2024 at 01:18:45PM +0100, Matthew Wilcox wrote:
> On Wed, May 29, 2024 at 03:45:01PM +0200, Pankaj Raghav (Samsung) wrote:
> > @@ -1919,8 +1921,10 @@ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
> >  		folio_wait_stable(folio);
> >  no_page:
> >  	if (!folio && (fgp_flags & FGP_CREAT)) {
> > -		unsigned order = FGF_GET_ORDER(fgp_flags);
> > +		unsigned int min_order = mapping_min_folio_order(mapping);
> > +		unsigned int order = max(min_order, FGF_GET_ORDER(fgp_flags));
> >  		int err;
> > +		index = mapping_align_start_index(mapping, index);
> >  
> >  		if ((fgp_flags & FGP_WRITE) && mapping_can_writeback(mapping))
> >  			gfp |= __GFP_WRITE;
> > @@ -1958,7 +1962,7 @@ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
> >  				break;
> >  			folio_put(folio);
> >  			folio = NULL;
> > -		} while (order-- > 0);
> > +		} while (order-- > min_order);
> 
> I'd argue you also need to change:
> 
> -                       if (order > 0)
> +			if (order > min_order)
>                                 alloc_gfp |= __GFP_NORETRY | __GFP_NOWARN;
> 
> since that is the last point at which we can fall back.  If we can't
> immediately allocate a min_order folio, we want to retry, and we
> want to warn if we can't get it.

That is a good point. It is also a feedback to the admin if they start
using LBS and assess the memory requirement based on memory alloc
warning?

--
Pankaj
diff mbox series

Patch

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 228275e7049f..899b8d751768 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -439,6 +439,26 @@  unsigned int mapping_min_folio_order(const struct address_space *mapping)
 	return (mapping->flags & AS_FOLIO_ORDER_MIN_MASK) >> AS_FOLIO_ORDER_MIN;
 }
 
+static inline unsigned long mapping_min_folio_nrpages(struct address_space *mapping)
+{
+	return 1UL << mapping_min_folio_order(mapping);
+}
+
+/**
+ * mapping_align_start_index() - Align starting index based on the min
+ * folio order of the page cache.
+ * @mapping: The address_space.
+ *
+ * Ensure the index used is aligned to the minimum folio order when adding
+ * new folios to the page cache by rounding down to the nearest minimum
+ * folio number of pages.
+ */
+static inline pgoff_t mapping_align_start_index(struct address_space *mapping,
+						pgoff_t index)
+{
+	return round_down(index, mapping_min_folio_nrpages(mapping));
+}
+
 /*
  * Large folio support currently depends on THP.  These dependencies are
  * being worked on but are not yet fixed.
diff --git a/mm/filemap.c b/mm/filemap.c
index 308714a44a0f..0914ef2e8256 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -859,6 +859,8 @@  noinline int __filemap_add_folio(struct address_space *mapping,
 
 	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
 	VM_BUG_ON_FOLIO(folio_test_swapbacked(folio), folio);
+	VM_BUG_ON_FOLIO(folio_order(folio) < mapping_min_folio_order(mapping),
+			folio);
 	mapping_set_update(&xas, mapping);
 
 	VM_BUG_ON_FOLIO(index & (folio_nr_pages(folio) - 1), folio);
@@ -1919,8 +1921,10 @@  struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
 		folio_wait_stable(folio);
 no_page:
 	if (!folio && (fgp_flags & FGP_CREAT)) {
-		unsigned order = FGF_GET_ORDER(fgp_flags);
+		unsigned int min_order = mapping_min_folio_order(mapping);
+		unsigned int order = max(min_order, FGF_GET_ORDER(fgp_flags));
 		int err;
+		index = mapping_align_start_index(mapping, index);
 
 		if ((fgp_flags & FGP_WRITE) && mapping_can_writeback(mapping))
 			gfp |= __GFP_WRITE;
@@ -1958,7 +1962,7 @@  struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
 				break;
 			folio_put(folio);
 			folio = NULL;
-		} while (order-- > 0);
+		} while (order-- > min_order);
 
 		if (err == -EEXIST)
 			goto repeat;
@@ -2447,13 +2451,16 @@  static int filemap_update_page(struct kiocb *iocb,
 }
 
 static int filemap_create_folio(struct file *file,
-		struct address_space *mapping, pgoff_t index,
+		struct address_space *mapping, loff_t pos,
 		struct folio_batch *fbatch)
 {
 	struct folio *folio;
 	int error;
+	unsigned int min_order = mapping_min_folio_order(mapping);
+	pgoff_t index;
 
-	folio = filemap_alloc_folio(mapping_gfp_mask(mapping), 0);
+	folio = filemap_alloc_folio(mapping_gfp_mask(mapping),
+				    min_order);
 	if (!folio)
 		return -ENOMEM;
 
@@ -2471,6 +2478,8 @@  static int filemap_create_folio(struct file *file,
 	 * well to keep locking rules simple.
 	 */
 	filemap_invalidate_lock_shared(mapping);
+	/* index in PAGE units but aligned to min_order number of pages. */
+	index = (pos >> (PAGE_SHIFT + min_order)) << min_order;
 	error = filemap_add_folio(mapping, folio, index,
 			mapping_gfp_constraint(mapping, GFP_KERNEL));
 	if (error == -EEXIST)
@@ -2531,8 +2540,7 @@  static int filemap_get_pages(struct kiocb *iocb, size_t count,
 	if (!folio_batch_count(fbatch)) {
 		if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_WAITQ))
 			return -EAGAIN;
-		err = filemap_create_folio(filp, mapping,
-				iocb->ki_pos >> PAGE_SHIFT, fbatch);
+		err = filemap_create_folio(filp, mapping, iocb->ki_pos, fbatch);
 		if (err == AOP_TRUNCATED_PAGE)
 			goto retry;
 		return err;
@@ -3748,9 +3756,11 @@  static struct folio *do_read_cache_folio(struct address_space *mapping,
 repeat:
 	folio = filemap_get_folio(mapping, index);
 	if (IS_ERR(folio)) {
-		folio = filemap_alloc_folio(gfp, 0);
+		folio = filemap_alloc_folio(gfp,
+					    mapping_min_folio_order(mapping));
 		if (!folio)
 			return ERR_PTR(-ENOMEM);
+		index = mapping_align_start_index(mapping, index);
 		err = filemap_add_folio(mapping, folio, index, gfp);
 		if (unlikely(err)) {
 			folio_put(folio);