LKML Archive on lore.kernel.org
 help / color / Atom feed
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>
Subject: [PATCH v7 6/7] mm: Make alloc_contig_range handle in-use hugetlb pages
Date: Tue, 13 Apr 2021 12:47:46 +0200
Message-ID: <20210413104747.12177-7-osalvador@suse.de> (raw)
In-Reply-To: <20210413104747.12177-1-osalvador@suse.de>

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            | 22 +++++++++++++++++-----
 mm/vmscan.c             |  5 +++--
 4 files changed, 34 insertions(+), 10 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 89426b6d1ea3..bb8ff3543972 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -909,7 +909,7 @@ 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
@@ -927,6 +927,15 @@ 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
@@ -1068,6 +1077,7 @@ 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 4a664d6e82c1..24a453ff47f2 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)) {
 		/*
@@ -2350,10 +2356,11 @@ 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
@@ -2378,7 +2385,12 @@ int isolate_or_dissolve_huge_page(struct page *page)
 	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


  parent reply index

Thread overview: 40+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-04-13 10:47 [PATCH v7 0/7] Make alloc_contig_range handle Hugetlb pages Oscar Salvador
2021-04-13 10:47 ` [PATCH v7 1/7] mm,page_alloc: Bail out earlier on -ENOMEM in alloc_contig_migrate_range Oscar Salvador
2021-04-13 17:00   ` Mike Kravetz
2021-04-13 10:47 ` [PATCH v7 2/7] mm,compaction: Let isolate_migratepages_{range,block} return error codes Oscar Salvador
2021-04-13 17:52   ` Mike Kravetz
2021-04-14 11:54   ` David Hildenbrand
2021-04-15  8:42     ` Oscar Salvador
2021-04-13 10:47 ` [PATCH v7 3/7] mm,hugetlb: Clear HPageFreed outside of the lock Oscar Salvador
2021-04-13 13:23   ` Michal Hocko
2021-04-13 21:19     ` Mike Kravetz
2021-04-14  6:04       ` Michal Hocko
2021-04-14  7:41         ` Oscar Salvador
2021-04-14  8:28           ` Michal Hocko
2021-04-14 10:01             ` Oscar Salvador
2021-04-14 10:03               ` Oscar Salvador
2021-04-14 10:32               ` Michal Hocko
2021-04-14 10:49                 ` Oscar Salvador
2021-04-14 11:09                   ` Michal Hocko
2021-04-14 12:02                     ` David Hildenbrand
2021-04-14 16:45                   ` Mike Kravetz
2021-04-13 10:47 ` [PATCH v7 4/7] mm,hugetlb: Split prep_new_huge_page functionality Oscar Salvador
2021-04-13 13:24   ` Michal Hocko
2021-04-13 13:26     ` Michal Hocko
2021-04-13 21:33   ` Mike Kravetz
2021-04-14  4:59     ` Oscar Salvador
2021-04-14 12:15       ` David Hildenbrand
2021-04-14 17:03       ` Mike Kravetz
2021-04-13 10:47 ` [PATCH v7 5/7] mm: Make alloc_contig_range handle free hugetlb pages Oscar Salvador
2021-04-13 13:40   ` Michal Hocko
2021-04-15  8:29     ` Oscar Salvador
2021-04-13 22:29   ` Mike Kravetz
2021-04-14  4:54     ` Oscar Salvador
2021-04-14 12:26   ` David Hildenbrand
2021-04-15  8:28     ` Oscar Salvador
2021-04-13 10:47 ` Oscar Salvador [this message]
2021-04-13 22:48   ` [PATCH v7 6/7] mm: Make alloc_contig_range handle in-use " Mike Kravetz
2021-04-14  4:52     ` Oscar Salvador
2021-04-14 17:07       ` Mike Kravetz
2021-04-13 10:47 ` [PATCH v7 7/7] mm,page_alloc: Drop unnecessary checks from pfn_range_valid_contig Oscar Salvador
2021-04-13 22:53   ` Mike Kravetz

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20210413104747.12177-7-osalvador@suse.de \
    --to=osalvador@suse.de \
    --cc=akpm@linux-foundation.org \
    --cc=david@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mhocko@kernel.org \
    --cc=mike.kravetz@oracle.com \
    --cc=songmuchun@bytedance.com \
    --cc=vbabka@suse.cz \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lore.kernel.org/lkml/7 lkml/git/7.git
	git clone --mirror https://lore.kernel.org/lkml/8 lkml/git/8.git
	git clone --mirror https://lore.kernel.org/lkml/9 lkml/git/9.git
	git clone --mirror https://lore.kernel.org/lkml/10 lkml/git/10.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 lkml lkml/ https://lore.kernel.org/lkml \
		linux-kernel@vger.kernel.org
	public-inbox-index lkml

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-kernel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git