linux-kernel - [PATCH v7 10/10] mm: memory_hotplug: memory hotremove supports thp migration

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20170620230715.81590-11-zi.yan@sent.com>
Date:   Tue, 20 Jun 2017 19:07:15 -0400
From:   Zi Yan <zi.yan@...t.com>
To:     kirill.shutemov@...ux.intel.com, linux-kernel@...r.kernel.org,
        linux-mm@...ck.org
Cc:     akpm@...ux-foundation.org, minchan@...nel.org, vbabka@...e.cz,
        mgorman@...hsingularity.net, mhocko@...nel.org,
        khandual@...ux.vnet.ibm.com, zi.yan@...rutgers.edu,
        dnellans@...dia.com, dave.hansen@...el.com,
        n-horiguchi@...jp.nec.com
Subject: [PATCH v7 10/10] mm: memory_hotplug: memory hotremove supports thp migration

From: Naoya Horiguchi <n-horiguchi@...jp.nec.com>

This patch enables thp migration for memory hotremove.

---
ChangeLog v1->v2:
- base code switched from alloc_migrate_target to new_node_page()

Signed-off-by: Naoya Horiguchi <n-horiguchi@...jp.nec.com>

ChangeLog v2->v7:
- base code switched from new_node_page() new_page_nodemask()

Signed-off-by: Zi Yan <zi.yan@...rutgers.edu>
---
 include/linux/migrate.h | 15 ++++++++++++++-
 mm/memory_hotplug.c     |  4 +++-
 2 files changed, 17 insertions(+), 2 deletions(-)

diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index f80c9882403a..f67755ae72c9 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -35,16 +35,29 @@ static inline struct page *new_page_nodemask(struct page *page, int preferred_ni
 		nodemask_t *nodemask)
 {
 	gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE;
+	unsigned int order = 0;
+	struct page *new_page = NULL;
 
 	if (PageHuge(page))
 		return alloc_huge_page_nodemask(page_hstate(compound_head(page)),
 				nodemask);
 
+	if (thp_migration_supported() && PageTransHuge(page)) {
+		order = HPAGE_PMD_ORDER;
+		gfp_mask |= GFP_TRANSHUGE;
+	}
+
 	if (PageHighMem(page)
 	    || (zone_idx(page_zone(page)) == ZONE_MOVABLE))
 		gfp_mask |= __GFP_HIGHMEM;
 
-	return __alloc_pages_nodemask(gfp_mask, 0, preferred_nid, nodemask);
+	new_page = __alloc_pages_nodemask(gfp_mask, order,
+				preferred_nid, nodemask);
+
+	if (new_page && PageTransHuge(page))
+		prep_transhuge_page(new_page);
+
+	return new_page;
 }
 
 #ifdef CONFIG_MIGRATION
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 567a1dcafa1a..1975acfc7326 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1483,7 +1483,9 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
 			if (isolate_huge_page(page, &source))
 				move_pages -= 1 << compound_order(head);
 			continue;
-		}
+		} else if (thp_migration_supported() && PageTransHuge(page))
+			pfn = page_to_pfn(compound_head(page))
+				+ hpage_nr_pages(page) - 1;
 
 		if (!get_page_unless_zero(page))
 			continue;
-- 
2.11.0