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:   Oscar Salvador <osalvador@suse.de>
To:     Andrew Morton <akpm@linux-foundation.org>
Cc:     Mike Kravetz <mike.kravetz@oracle.com>,
        Vlastimil Babka <vbabka@suse.cz>,
        David Hildenbrand <david@redhat.com>,
        Michal Hocko <mhocko@kernel.org>,
        Muchun Song <songmuchun@bytedance.com>, linux-mm@kvack.org,
        linux-kernel@vger.kernel.org, Oscar Salvador <osalvador@suse.de>,
        Michal Hocko <mhocko@suse.com>
Subject: [PATCH v8 6/7] mm: Make alloc_contig_range handle in-use hugetlb pages
Date:   Thu, 15 Apr 2021 12:35:43 +0200
Message-Id: <20210415103544.6791-7-osalvador@suse.de>
In-Reply-To: <20210415103544.6791-1-osalvador@suse.de>
References: <20210415103544.6791-1-osalvador@suse.de>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

alloc_contig_range() will fail if it finds a HugeTLB page within the range,
without a chance to handle them. Since HugeTLB pages can be migrated as any
LRU or Movable page, it does not make sense to bail out without trying.
Enable the interface to recognize in-use HugeTLB pages so we can migrate
them, and have much better chances to succeed the call.

Signed-off-by: Oscar Salvador <osalvador@suse.de>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Acked-by: Michal Hocko <mhocko@suse.com>
---
 include/linux/hugetlb.h |  5 +++--
 mm/compaction.c         | 12 +++++++++++-
 mm/hugetlb.c            | 24 ++++++++++++++++++------
 mm/vmscan.c             |  5 +++--
 4 files changed, 35 insertions(+), 11 deletions(-)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index b2d2118bfd1a..b92f25ccef58 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -595,7 +595,7 @@ struct huge_bootmem_page {
 	struct hstate *hstate;
 };
 
-int isolate_or_dissolve_huge_page(struct page *page);
+int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list);
 struct page *alloc_huge_page(struct vm_area_struct *vma,
 				unsigned long addr, int avoid_reserve);
 struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
@@ -878,7 +878,8 @@ static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
 #else	/* CONFIG_HUGETLB_PAGE */
 struct hstate {};
 
-static inline int isolate_or_dissolve_huge_page(struct page *page)
+static inline int isolate_or_dissolve_huge_page(struct page *page,
+						struct list_head *list)
 {
 	return -ENOMEM;
 }
diff --git a/mm/compaction.c b/mm/compaction.c
index 73f00f36b6e7..8149ffc6bccd 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -907,7 +907,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		}
 
 		if (PageHuge(page) && cc->alloc_contig) {
-			ret = isolate_or_dissolve_huge_page(page);
+			ret = isolate_or_dissolve_huge_page(page, &cc->migratepages);
 
 			/*
 			 * Fail isolation in case isolate_or_dissolve_huge_page()
@@ -923,6 +923,15 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 				goto isolate_fail;
 			}
 
+			if (PageHuge(page)) {
+				/*
+				 * Hugepage was successfully isolated and placed
+				 * on the cc->migratepages list.
+				 */
+				low_pfn += compound_nr(page) - 1;
+				goto isolate_success_no_list;
+			}
+
 			/*
 			 * Ok, the hugepage was dissolved. Now these pages are
 			 * Buddy and cannot be re-allocated because they are
@@ -1064,6 +1073,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 
 isolate_success:
 		list_add(&page->lru, &cc->migratepages);
+isolate_success_no_list:
 		cc->nr_migratepages += compound_nr(page);
 		nr_isolated += compound_nr(page);
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 4abd4c4565dd..efe2f1fed74e 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2270,10 +2270,12 @@ static void restore_reserve_on_error(struct hstate *h,
  * alloc_and_dissolve_huge_page - Allocate a new page and dissolve the old one
  * @h: struct hstate old page belongs to
  * @old_page: Old page to dissolve
+ * @list: List to isolate the page in case we need to
  * Returns 0 on success, otherwise negated error.
  */
 
-static int alloc_and_dissolve_huge_page(struct hstate *h, struct page *old_page)
+static int alloc_and_dissolve_huge_page(struct hstate *h, struct page *old_page,
+					struct list_head *list)
 {
 	gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE;
 	int nid = page_to_nid(old_page);
@@ -2300,9 +2302,13 @@ static int alloc_and_dissolve_huge_page(struct hstate *h, struct page *old_page)
 		goto free_new;
 	} else if (page_count(old_page)) {
 		/*
-		 * Someone has grabbed the page, fail for now.
+		 * Someone has grabbed the page, try to isolate it here.
+		 * Fail with -EBUSY if not possible.
 		 */
-		ret = -EBUSY;
+		spin_unlock_irq(&hugetlb_lock);
+		if (!isolate_huge_page(old_page, list))
+			ret = -EBUSY;
+		spin_lock_irq(&hugetlb_lock);
 		goto free_new;
 	} else if (!HPageFreed(old_page)) {
 		/*
@@ -2352,10 +2358,11 @@ static int alloc_and_dissolve_huge_page(struct hstate *h, struct page *old_page)
 	return ret;
 }
 
-int isolate_or_dissolve_huge_page(struct page *page)
+int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list)
 {
 	struct hstate *h;
 	struct page *head;
+	int ret = -EBUSY;
 
 	/*
 	 * The page might have been dissolved from under our feet, so make sure
@@ -2374,13 +2381,18 @@ int isolate_or_dissolve_huge_page(struct page *page)
 
 	/*
 	 * Fence off gigantic pages as there is a cyclic dependency between
-	 * alloc_contig_range and them. Return -ENOME as this has the effect
+	 * alloc_contig_range and them. Return -ENOMEM as this has the effect
 	 * of bailing out right away without further retrying.
 	 */
 	if (hstate_is_gigantic(h))
 		return -ENOMEM;
 
-	return alloc_and_dissolve_huge_page(h, head);
+	if (page_count(head) && isolate_huge_page(head, list))
+		ret = 0;
+	else if (!page_count(head))
+		ret = alloc_and_dissolve_huge_page(h, head, list);
+
+	return ret;
 }
 
 struct page *alloc_huge_page(struct vm_area_struct *vma,
diff --git a/mm/vmscan.c b/mm/vmscan.c
index bb8321026c0c..5199b9696bab 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1703,8 +1703,9 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone,
 	LIST_HEAD(clean_pages);
 
 	list_for_each_entry_safe(page, next, page_list, lru) {
-		if (page_is_file_lru(page) && !PageDirty(page) &&
-		    !__PageMovable(page) && !PageUnevictable(page)) {
+		if (!PageHuge(page) && page_is_file_lru(page) &&
+		    !PageDirty(page) && !__PageMovable(page) &&
+		    !PageUnevictable(page)) {
 			ClearPageActive(page);
 			list_move(&page->lru, &clean_pages);
 		}
-- 
2.16.3