[RFC PATCH v2 22/30] mm: thp: split PUD THPs at page reclaim.

From: Zi Yan <zi.yan@sent.com>
To: linux-mm@kvack.org
Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>,
	Roman Gushchin <guro@fb.com>, Rik van Riel <riel@surriel.com>,
	Matthew Wilcox <willy@infradead.org>,
	Shakeel Butt <shakeelb@google.com>,
	Yang Shi <shy828301@gmail.com>, Jason Gunthorpe <jgg@nvidia.com>,
	Mike Kravetz <mike.kravetz@oracle.com>,
	Michal Hocko <mhocko@suse.com>,
	David Hildenbrand <david@redhat.com>,
	William Kucharski <william.kucharski@oracle.com>,
	Andrea Arcangeli <aarcange@redhat.com>,
	John Hubbard <jhubbard@nvidia.com>,
	David Nellans <dnellans@nvidia.com>,
	linux-kernel@vger.kernel.org, Zi Yan <ziy@nvidia.com>
Subject: [RFC PATCH v2 22/30] mm: thp: split PUD THPs at page reclaim.
Date: Mon, 28 Sep 2020 13:54:20 -0400	[thread overview]
Message-ID: <20200928175428.4110504-23-zi.yan@sent.com> (raw)
In-Reply-To: <20200928175428.4110504-1-zi.yan@sent.com>

From: Zi Yan <ziy@nvidia.com>

We cannot swap PUD THPs, so split them before swap them out. PUD THPs
will be split into PMD THPs, so that if THP_SWAP is enabled, PMD THPs
can be swapped out as a whole.

Signed-off-by: Zi Yan <ziy@nvidia.com>
---
 mm/swap_slots.c |  2 ++
 mm/vmscan.c     | 33 +++++++++++++++++++++++++++------
 2 files changed, 29 insertions(+), 6 deletions(-)

diff --git a/mm/swap_slots.c b/mm/swap_slots.c
index 3e6453573a89..65b8742a0446 100644
--- a/mm/swap_slots.c
+++ b/mm/swap_slots.c
@@ -312,6 +312,8 @@ swp_entry_t get_swap_page(struct page *page)
 	entry.val = 0;
 
 	if (PageTransHuge(page)) {
+		if (compound_order(page) == HPAGE_PUD_ORDER)
+			return entry;
 		if (IS_ENABLED(CONFIG_THP_SWAP))
 			get_swap_pages(1, &entry, HPAGE_PMD_NR);
 		goto out;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index eae57d092931..12e169af663c 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1244,7 +1244,21 @@ static unsigned int shrink_page_list(struct list_head *page_list,
 			if (!PageSwapCache(page)) {
 				if (!(sc->gfp_mask & __GFP_IO))
 					goto keep_locked;
-				if (PageTransHuge(page)) {
+				if (!PageTransHuge(page))
+					goto try_to_swap;
+				if (compound_order(page) == HPAGE_PUD_ORDER) {
+					/* cannot split THP, skip it */
+					if (!can_split_huge_pud_page(page, NULL))
+						goto activate_locked;
+					/* Split PUD THPs before swapping */
+					if (split_huge_pud_page_to_list(page, page_list))
+						goto activate_locked;
+					else {
+						sc->nr_scanned -= (nr_pages - HPAGE_PMD_NR);
+						nr_pages = HPAGE_PMD_NR;
+					}
+				}
+				if (compound_order(page) == HPAGE_PMD_ORDER) {
 					/* cannot split THP, skip it */
 					if (!can_split_huge_page(page, NULL))
 						goto activate_locked;
@@ -1254,14 +1268,17 @@ static unsigned int shrink_page_list(struct list_head *page_list,
 					 * tail pages can be freed without IO.
 					 */
 					if (!compound_mapcount(page) &&
-					    split_huge_page_to_list(page,
-								    page_list))
+						split_huge_page_to_list(page,
+									page_list))
 						goto activate_locked;
 				}
+try_to_swap:
 				if (!add_to_swap(page)) {
 					if (!PageTransHuge(page))
 						goto activate_locked_split;
 					/* Fallback to swap normal pages */
+					VM_BUG_ON_PAGE(compound_order(page) != HPAGE_PMD_ORDER,
+						       page);
 					if (split_huge_page_to_list(page,
 								    page_list))
 						goto activate_locked;
@@ -1278,6 +1295,7 @@ static unsigned int shrink_page_list(struct list_head *page_list,
 				mapping = page_mapping(page);
 			}
 		} else if (unlikely(PageTransHuge(page))) {
+			VM_BUG_ON_PAGE(compound_order(page) != HPAGE_PMD_ORDER, page);
 			/* Split file THP */
 			if (split_huge_page_to_list(page, page_list))
 				goto keep_locked;
@@ -1303,9 +1321,12 @@ static unsigned int shrink_page_list(struct list_head *page_list,
 			enum ttu_flags flags = ttu_flags | TTU_BATCH_FLUSH;
 			bool was_swapbacked = PageSwapBacked(page);
 
-			if (unlikely(PageTransHuge(page)))
-				flags |= TTU_SPLIT_HUGE_PMD;
-
+			if (unlikely(PageTransHuge(page))) {
+				if (compound_order(page) == HPAGE_PMD_ORDER)
+					flags |= TTU_SPLIT_HUGE_PMD;
+				else if (compound_order(page) == HPAGE_PUD_ORDER)
+					flags |= TTU_SPLIT_HUGE_PUD;
+			}
 			if (!try_to_unmap(page, flags)) {
 				stat->nr_unmap_fail += nr_pages;
 				if (!was_swapbacked && PageSwapBacked(page))
-- 
2.28.0


