Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Zi Yan <zi.yan@sent.com>
To:     linux-mm@kvack.org, Roman Gushchin <guro@fb.com>
Cc:     Rik van Riel <riel@surriel.com>,
        "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>,
        Matthew Wilcox <willy@infradead.org>,
        Shakeel Butt <shakeelb@google.com>,
        Yang Shi <yang.shi@linux.alibaba.com>,
        David Nellans <dnellans@nvidia.com>,
        linux-kernel@vger.kernel.org, Zi Yan <ziy@nvidia.com>
Subject: [RFC PATCH 10/16] mm: thp: split 1GB THPs at page reclaim.
Date:   Wed,  2 Sep 2020 14:06:22 -0400
Message-Id: <20200902180628.4052244-11-zi.yan@sent.com>
In-Reply-To: <20200902180628.4052244-1-zi.yan@sent.com>
References: <20200902180628.4052244-1-zi.yan@sent.com>
Reply-To: Zi Yan <ziy@nvidia.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

From: Zi Yan <ziy@nvidia.com>

We cannot swap 1GB THPs, so split them before swap them out.

Signed-off-by: Zi Yan <ziy@nvidia.com>
---
 mm/swap_slots.c |  2 ++
 mm/vmscan.c     | 58 +++++++++++++++++++++++++++++++++++++------------
 2 files changed, 46 insertions(+), 14 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 99e1796eb833..617d15a041f8 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1240,23 +1240,49 @@ static unsigned int shrink_page_list(struct list_head *page_list,
 				if (!(sc->gfp_mask & __GFP_IO))
 					goto keep_locked;
 				if (PageTransHuge(page)) {
-					/* cannot split THP, skip it */
-					if (!can_split_huge_page(page, NULL))
-						goto activate_locked;
-					/*
-					 * Split pages without a PMD map right
-					 * away. Chances are some or all of the
-					 * tail pages can be freed without IO.
-					 */
-					if (!compound_mapcount(page) &&
-					    split_huge_page_to_list(page,
-								    page_list))
+					if (compound_order(page) == HPAGE_PUD_ORDER) {
+						/* cannot split THP, skip it */
+						if (!can_split_huge_pud_page(page, NULL))
+							goto activate_locked;
+						/*
+						 * Split pages without a PUD map right
+						 * away. Chances are some or all of the
+						 * tail pages can be freed without IO.
+						 */
+						if (!compound_mapcount(page) &&
+							split_huge_pud_page_to_list(page,
+										page_list))
+							goto activate_locked;
+					}
+					if (compound_order(page) == HPAGE_PMD_ORDER) {
+						/* cannot split THP, skip it */
+						if (!can_split_huge_page(page, NULL))
+							goto activate_locked;
+						/*
+						 * Split pages without a PMD map right
+						 * away. Chances are some or all of the
+						 * tail pages can be freed without IO.
+						 */
+						if (!compound_mapcount(page) &&
+							split_huge_page_to_list(page,
+										page_list))
+							goto activate_locked;
+					}
+				}
+				/* Split PUD THPs before swapping */
+				if (compound_order(page) == HPAGE_PUD_ORDER) {
+					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 (!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;
@@ -1273,6 +1299,7 @@ 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;
@@ -1298,9 +1325,12 @@ 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