Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Zi Yan <zi.yan@sent.com>
To:     Dave Hansen <dave.hansen@linux.intel.com>,
        Yang Shi <yang.shi@linux.alibaba.com>,
        Keith Busch <keith.busch@intel.com>,
        Fengguang Wu <fengguang.wu@intel.com>, linux-mm@kvack.org,
        linux-kernel@vger.kernel.org
Cc:     Daniel Jordan <daniel.m.jordan@oracle.com>,
        Michal Hocko <mhocko@kernel.org>,
        "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>,
        Andrew Morton <akpm@linux-foundation.org>,
        Vlastimil Babka <vbabka@suse.cz>,
        Mel Gorman <mgorman@techsingularity.net>,
        John Hubbard <jhubbard@nvidia.com>,
        Mark Hairgrove <mhairgrove@nvidia.com>,
        Nitin Gupta <nigupta@nvidia.com>,
        Javier Cabezas <jcabezas@nvidia.com>,
        David Nellans <dnellans@nvidia.com>, Zi Yan <ziy@nvidia.com>
Subject: [RFC PATCH 04/25] mm: migrate: Add copy_page_multithread into migrate_pages.
Date:   Wed,  3 Apr 2019 19:00:25 -0700
Message-Id: <20190404020046.32741-5-zi.yan@sent.com>
In-Reply-To: <20190404020046.32741-1-zi.yan@sent.com>
References: <20190404020046.32741-1-zi.yan@sent.com>
Reply-To: 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>

An option is added to move_pages() syscall to use multi-threaded
page migration.

Signed-off-by: Zi Yan <ziy@nvidia.com>
---
 include/linux/migrate_mode.h   |  1 +
 include/uapi/linux/mempolicy.h |  2 ++
 mm/migrate.c                   | 29 +++++++++++++++++++----------
 3 files changed, 22 insertions(+), 10 deletions(-)

diff --git a/include/linux/migrate_mode.h b/include/linux/migrate_mode.h
index da44940..5bc8a77 100644
--- a/include/linux/migrate_mode.h
+++ b/include/linux/migrate_mode.h
@@ -22,6 +22,7 @@ enum migrate_mode {
 
 	MIGRATE_MODE_MASK = 3,
 	MIGRATE_SINGLETHREAD	= 0,
+	MIGRATE_MT				= 1<<4,
 };
 
 #endif		/* MIGRATE_MODE_H_INCLUDED */
diff --git a/include/uapi/linux/mempolicy.h b/include/uapi/linux/mempolicy.h
index 3354774..890269b 100644
--- a/include/uapi/linux/mempolicy.h
+++ b/include/uapi/linux/mempolicy.h
@@ -48,6 +48,8 @@ enum {
 #define MPOL_MF_LAZY	 (1<<3)	/* Modifies '_MOVE:  lazy migrate on fault */
 #define MPOL_MF_INTERNAL (1<<4)	/* Internal flags start here */
 
+#define MPOL_MF_MOVE_MT  (1<<6)	/* Use multi-threaded page copy routine */
+
 #define MPOL_MF_VALID	(MPOL_MF_STRICT   | 	\
 			 MPOL_MF_MOVE     | 	\
 			 MPOL_MF_MOVE_ALL)
diff --git a/mm/migrate.c b/mm/migrate.c
index 2b2653e..dd6ccbe 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -572,6 +572,7 @@ static void copy_huge_page(struct page *dst, struct page *src,
 {
 	int i;
 	int nr_pages;
+	int rc = -EFAULT;
 
 	if (PageHuge(src)) {
 		/* hugetlbfs page */
@@ -588,10 +589,14 @@ static void copy_huge_page(struct page *dst, struct page *src,
 		nr_pages = hpage_nr_pages(src);
 	}
 
-	for (i = 0; i < nr_pages; i++) {
-		cond_resched();
-		copy_highpage(dst + i, src + i);
-	}
+	if (mode & MIGRATE_MT)
+		rc = copy_page_multithread(dst, src, nr_pages);
+
+	if (rc)
+		for (i = 0; i < nr_pages; i++) {
+			cond_resched();
+			copy_highpage(dst + i, src + i);
+		}
 }
 
 /*
@@ -1500,7 +1505,7 @@ static int store_status(int __user *status, int start, int value, int nr)
 }
 
 static int do_move_pages_to_node(struct mm_struct *mm,
-		struct list_head *pagelist, int node)
+		struct list_head *pagelist, int node, bool migrate_mt)
 {
 	int err;
 
@@ -1508,7 +1513,8 @@ static int do_move_pages_to_node(struct mm_struct *mm,
 		return 0;
 
 	err = migrate_pages(pagelist, alloc_new_node_page, NULL, node,
-			MIGRATE_SYNC, MR_SYSCALL);
+			MIGRATE_SYNC | (migrate_mt ? MIGRATE_MT : MIGRATE_SINGLETHREAD),
+			MR_SYSCALL);
 	if (err)
 		putback_movable_pages(pagelist);
 	return err;
@@ -1629,7 +1635,8 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes,
 			current_node = node;
 			start = i;
 		} else if (node != current_node) {
-			err = do_move_pages_to_node(mm, &pagelist, current_node);
+			err = do_move_pages_to_node(mm, &pagelist, current_node,
+				flags & MPOL_MF_MOVE_MT);
 			if (err)
 				goto out;
 			err = store_status(status, start, current_node, i - start);
@@ -1652,7 +1659,8 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes,
 		if (err)
 			goto out_flush;
 
-		err = do_move_pages_to_node(mm, &pagelist, current_node);
+		err = do_move_pages_to_node(mm, &pagelist, current_node,
+				flags & MPOL_MF_MOVE_MT);
 		if (err)
 			goto out;
 		if (i > start) {
@@ -1667,7 +1675,8 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes,
 		return err;
 
 	/* Make sure we do not overwrite the existing error */
-	err1 = do_move_pages_to_node(mm, &pagelist, current_node);
+	err1 = do_move_pages_to_node(mm, &pagelist, current_node,
+				flags & MPOL_MF_MOVE_MT);
 	if (!err1)
 		err1 = store_status(status, start, current_node, i - start);
 	if (!err)
@@ -1763,7 +1772,7 @@ static int kernel_move_pages(pid_t pid, unsigned long nr_pages,
 	nodemask_t task_nodes;
 
 	/* Check flags */
-	if (flags & ~(MPOL_MF_MOVE|MPOL_MF_MOVE_ALL))
+	if (flags & ~(MPOL_MF_MOVE|MPOL_MF_MOVE_ALL|MPOL_MF_MOVE_MT))
 		return -EINVAL;
 
 	if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_NICE))
-- 
2.7.4