[v5,05/11] mm: split a folio in minimum folio order chunks

Commit Message

Luis Chamberlain May 3, 2024, 9:53 a.m. UTC

split_folio() and split_folio_to_list() assume order 0, to support
minorder we must expand these to check the folio mapping order and use
that.

Set new_order to be at least minimum folio order if it is set in
split_huge_page_to_list() so that we can maintain minimum folio order
requirement in the page cache.

Update the debugfs write files used for testing to ensure the order
is respected as well. We simply enforce the min order when a file
mapping is used.

Signed-off-by: Pankaj Raghav <[e-mail]>
Signed-off-by: Luis Chamberlain <[e-mail]>
---
 include/linux/huge_mm.h | 12 ++++++----
 mm/huge_memory.c        | 50 ++++++++++++++++++++++++++++++++++++++---
 2 files changed, 55 insertions(+), 7 deletions(-)

Comments

Zi Yan May 3, 2024, 2:53 p.m. UTC | #1

On 3 May 2024, at 5:53, Luis Chamberlain wrote:

> split_folio() and split_folio_to_list() assume order 0, to support
> minorder we must expand these to check the folio mapping order and use
> that.
>
> Set new_order to be at least minimum folio order if it is set in
> split_huge_page_to_list() so that we can maintain minimum folio order
> requirement in the page cache.
>
> Update the debugfs write files used for testing to ensure the order
> is respected as well. We simply enforce the min order when a file
> mapping is used.
>
> Signed-off-by: Pankaj Raghav <[e-mail]>
> Signed-off-by: Luis Chamberlain <[e-mail]>
> ---
>  include/linux/huge_mm.h | 12 ++++++----
>  mm/huge_memory.c        | 50 ++++++++++++++++++++++++++++++++++++++---
>  2 files changed, 55 insertions(+), 7 deletions(-)
>
It makes sense to me. Reviewed-by: Zi Yan <[e-mail]>

--
Best Regards,
Yan, Zi

Matthew Wilcox May 15, 2024, 3:32 p.m. UTC | #2

On Fri, May 03, 2024 at 02:53:47AM -0700, Luis Chamberlain wrote:
> +int split_folio_to_list(struct folio *folio, struct list_head *list);

...

> +static inline int split_folio_to_list(struct page *page, struct list_head *list)
> +{

Type mismatch.  Surprised the build bots didn't whine yet.

>  
> +		min_order = mapping_min_folio_order(folio->mapping);
> +		if (new_order < min_order) {
> +			VM_WARN_ONCE(1, "Cannot split mapped folio below min-order: %u",
> +				     min_order);
> +			ret = -EINVAL;
> +			goto out;
> +		}

Wouldn't we prefer this as:

		if (VM_WARN_ONCE(new_order < min_order,
				"Cannot split mapped folio below min-order: %u",
				min_order) {
			ret = -EINVAL;
			goto out;
		}

Pankaj Raghav (Samsung) May 16, 2024, 2:56 p.m. UTC | #3

On Wed, May 15, 2024 at 04:32:36PM +0100, Matthew Wilcox wrote:
> On Fri, May 03, 2024 at 02:53:47AM -0700, Luis Chamberlain wrote:
> > +int split_folio_to_list(struct folio *folio, struct list_head *list);
> 
> ...
> 
> > +static inline int split_folio_to_list(struct page *page, struct list_head *list)
> > +{
> 
> Type mismatch.  Surprised the build bots didn't whine yet.

Good catch. As we always enabled CONFIG_THP, we didn't detect this
issue.

> 
> >  
> > +		min_order = mapping_min_folio_order(folio->mapping);
> > +		if (new_order < min_order) {
> > +			VM_WARN_ONCE(1, "Cannot split mapped folio below min-order: %u",
> > +				     min_order);
> > +			ret = -EINVAL;
> > +			goto out;
> > +		}
> 
> Wouldn't we prefer this as:
> 
> 		if (VM_WARN_ONCE(new_order < min_order,
> 				"Cannot split mapped folio below min-order: %u",
> 				min_order) {
> 			ret = -EINVAL;
> 			goto out;
> 		}
> 
I don't think so:
#define VM_WARN_ONCE(cond, format...) (void)WARN_ONCE(cond, format)

So we get a build error as follows:
In file included from ./include/linux/mm.h:6,
                 from mm/huge_memory.c:8:
mm/huge_memory.c: In function ‘split_huge_page_to_list_to_order’:
./include/linux/mmdebug.h:93:39: error: void value not ignored as it ought to be
   93 | #define VM_WARN_ONCE(cond, format...) (void)WARN_ONCE(cond, format)
      |                                       ^
mm/huge_memory.c:3158:21: note: in expansion of macro ‘VM_WARN_ONCE’
 3158 |                 if (VM_WARN_ONCE(new_order < min_order,

Patch

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index de0c89105076..06748a8fa43b 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -87,6 +87,8 @@  extern struct kobj_attribute shmem_enabled_attr;
 #define thp_vma_allowable_order(vma, vm_flags, smaps, in_pf, enforce_sysfs, order) \
 	(!!thp_vma_allowable_orders(vma, vm_flags, smaps, in_pf, enforce_sysfs, BIT(order)))
 
+#define split_folio(f) split_folio_to_list(f, NULL)
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define HPAGE_PMD_SHIFT PMD_SHIFT
 #define HPAGE_PMD_SIZE	((1UL) << HPAGE_PMD_SHIFT)
@@ -267,9 +269,10 @@  void folio_prep_large_rmappable(struct folio *folio);
 bool can_split_folio(struct folio *folio, int *pextra_pins);
 int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
 		unsigned int new_order);
+int split_folio_to_list(struct folio *folio, struct list_head *list);
 static inline int split_huge_page(struct page *page)
 {
-	return split_huge_page_to_list_to_order(page, NULL, 0);
+	return split_folio(page_folio(page));
 }
 void deferred_split_folio(struct folio *folio);
 
@@ -432,6 +435,10 @@  static inline int split_huge_page(struct page *page)
 {
 	return 0;
 }
+static inline int split_folio_to_list(struct page *page, struct list_head *list)
+{
+	return 0;
+}
 static inline void deferred_split_folio(struct folio *folio) {}
 #define split_huge_pmd(__vma, __pmd, __address)	\
 	do { } while (0)
@@ -532,9 +539,6 @@  static inline int split_folio_to_order(struct folio *folio, int new_order)
 	return split_folio_to_list_to_order(folio, NULL, new_order);
 }
 
-#define split_folio_to_list(f, l) split_folio_to_list_to_order(f, l, 0)
-#define split_folio(f) split_folio_to_order(f, 0)
-
 /*
  * archs that select ARCH_WANTS_THP_SWAP but don't support THP_SWP due to
  * limitations in the implementation like arm64 MTE can override this to
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 89f58c7603b2..c0cc8f32fe42 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -3035,6 +3035,9 @@  bool can_split_folio(struct folio *folio, int *pextra_pins)
  * Returns 0 if the hugepage is split successfully.
  * Returns -EBUSY if the page is pinned or if anon_vma disappeared from under
  * us.
+ *
+ * Callers should ensure that the order respects the address space mapping
+ * min-order if one is set.
  */
 int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
 				     unsigned int new_order)
@@ -3107,6 +3110,7 @@  int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
 		mapping = NULL;
 		anon_vma_lock_write(anon_vma);
 	} else {
+		unsigned int min_order;
 		gfp_t gfp;
 
 		mapping = folio->mapping;
@@ -3117,6 +3121,14 @@  int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
 			goto out;
 		}
 
+		min_order = mapping_min_folio_order(folio->mapping);
+		if (new_order < min_order) {
+			VM_WARN_ONCE(1, "Cannot split mapped folio below min-order: %u",
+				     min_order);
+			ret = -EINVAL;
+			goto out;
+		}
+
 		gfp = current_gfp_context(mapping_gfp_mask(mapping) &
 							GFP_RECLAIM_MASK);
 
@@ -3227,6 +3239,21 @@  int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
 	return ret;
 }
 
+int split_folio_to_list(struct folio *folio, struct list_head *list)
+{
+	unsigned int min_order = 0;
+
+	if (!folio_test_anon(folio)) {
+		if (!folio->mapping) {
+			count_vm_event(THP_SPLIT_PAGE_FAILED);
+			return -EBUSY;
+		}
+		min_order = mapping_min_folio_order(folio->mapping);
+	}
+
+	return split_huge_page_to_list_to_order(&folio->page, list, min_order);
+}
+
 void folio_undo_large_rmappable(struct folio *folio)
 {
 	struct deferred_split *ds_queue;
@@ -3466,6 +3493,7 @@  static int split_huge_pages_pid(int pid, unsigned long vaddr_start,
 		struct vm_area_struct *vma = vma_lookup(mm, addr);
 		struct page *page;
 		struct folio *folio;
+		unsigned int target_order = new_order;
 
 		if (!vma)
 			break;
@@ -3502,7 +3530,18 @@  static int split_huge_pages_pid(int pid, unsigned long vaddr_start,
 		if (!folio_trylock(folio))
 			goto next;
 
-		if (!split_folio_to_order(folio, new_order))
+		if (!folio_test_anon(folio)) {
+			unsigned int min_order;
+
+			if (!folio->mapping)
+				goto next;
+
+			min_order = mapping_min_folio_order(folio->mapping);
+			if (new_order < target_order)
+				target_order = min_order;
+		}
+
+		if (!split_folio_to_order(folio, target_order))
 			split++;
 
 		folio_unlock(folio);
@@ -3545,14 +3584,19 @@  static int split_huge_pages_in_file(const char *file_path, pgoff_t off_start,
 
 	for (index = off_start; index < off_end; index += nr_pages) {
 		struct folio *folio = filemap_get_folio(mapping, index);
+		unsigned int min_order, target_order = new_order;
 
 		nr_pages = 1;
 		if (IS_ERR(folio))
 			continue;
 
-		if (!folio_test_large(folio))
+		if (!folio->mapping || !folio_test_large(folio))
 			goto next;
 
+		min_order = mapping_min_folio_order(mapping);
+		if (new_order < min_order)
+			target_order = min_order;
+
 		total++;
 		nr_pages = folio_nr_pages(folio);
 
@@ -3562,7 +3606,7 @@  static int split_huge_pages_in_file(const char *file_path, pgoff_t off_start,
 		if (!folio_trylock(folio))
 			goto next;
 
-		if (!split_folio_to_order(folio, new_order))
+		if (!split_folio_to_order(folio, target_order))
 			split++;
 
 		folio_unlock(folio);