Linux-mm Archive on lore.kernel.org
 help / color / Atom feed
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> (raw)
In-Reply-To: <20190404020046.32741-1-zi.yan@sent.com>

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


  parent reply index

Thread overview: 29+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-04-04  2:00 [RFC PATCH 00/25] Accelerate page migration and use memcg for PMEM management Zi Yan
2019-04-04  2:00 ` [RFC PATCH 01/25] mm: migrate: Change migrate_mode to support combination migration modes Zi Yan
2019-04-04  2:00 ` [RFC PATCH 02/25] mm: migrate: Add mode parameter to support future page copy routines Zi Yan
2019-04-04  2:00 ` [RFC PATCH 03/25] mm: migrate: Add a multi-threaded page migration function Zi Yan
2019-04-04  2:00 ` Zi Yan [this message]
2019-04-04  2:00 ` [RFC PATCH 05/25] mm: migrate: Add vm.accel_page_copy in sysfs to control page copy acceleration Zi Yan
2019-04-04  2:00 ` [RFC PATCH 06/25] mm: migrate: Make the number of copy threads adjustable via sysctl Zi Yan
2019-04-04  2:00 ` [RFC PATCH 07/25] mm: migrate: Add copy_page_dma to use DMA Engine to copy pages Zi Yan
2019-04-04  2:00 ` [RFC PATCH 08/25] mm: migrate: Add copy_page_dma into migrate_page_copy Zi Yan
2019-04-04  2:00 ` [RFC PATCH 09/25] mm: migrate: Add copy_page_lists_dma_always to support copy a list of pages Zi Yan
2019-04-04  2:00 ` [RFC PATCH 10/25] mm: migrate: copy_page_lists_mt() to copy a page list using multi-threads Zi Yan
2019-04-04  2:00 ` [RFC PATCH 11/25] mm: migrate: Add concurrent page migration into move_pages syscall Zi Yan
2019-04-04  2:00 ` [RFC PATCH 12/25] exchange pages: new page migration mechanism: exchange_pages() Zi Yan
2019-04-04  2:00 ` [RFC PATCH 13/25] exchange pages: add multi-threaded exchange pages Zi Yan
2019-04-04  2:00 ` [RFC PATCH 14/25] exchange pages: concurrent " Zi Yan
2019-04-04  2:00 ` [RFC PATCH 15/25] exchange pages: exchange anonymous page and file-backed page Zi Yan
2019-04-04  2:00 ` [RFC PATCH 16/25] exchange page: Add THP exchange support Zi Yan
2019-04-04  2:00 ` [RFC PATCH 17/25] exchange page: Add exchange_page() syscall Zi Yan
2019-04-04  2:00 ` [RFC PATCH 18/25] memcg: Add per node memory usage&max stats in memcg Zi Yan
2019-04-04  2:00 ` [RFC PATCH 19/25] mempolicy: add MPOL_F_MEMCG flag, enforcing memcg memory limit Zi Yan
2019-04-04  2:00 ` [RFC PATCH 20/25] memory manage: Add memory manage syscall Zi Yan
2019-04-04  2:00 ` [RFC PATCH 21/25] mm: move update_lru_sizes() to mm_inline.h for broader use Zi Yan
2019-04-04  2:00 ` [RFC PATCH 22/25] memory manage: active/inactive page list manipulation in memcg Zi Yan
2019-04-04  2:00 ` [RFC PATCH 23/25] memory manage: page migration based page manipulation between NUMA nodes Zi Yan
2019-04-04  2:00 ` [RFC PATCH 24/25] memory manage: limit migration batch size Zi Yan
2019-04-04  2:00 ` [RFC PATCH 25/25] memory manage: use exchange pages to memory manage to improve throughput Zi Yan
2019-04-04  7:13 ` [RFC PATCH 00/25] Accelerate page migration and use memcg for PMEM management Michal Hocko
2019-04-05  0:32 ` Yang Shi
2019-04-05 17:20   ` Zi Yan

Reply instructions:

You may reply publically 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=20190404020046.32741-5-zi.yan@sent.com \
    --to=zi.yan@sent.com \
    --cc=akpm@linux-foundation.org \
    --cc=daniel.m.jordan@oracle.com \
    --cc=dave.hansen@linux.intel.com \
    --cc=dnellans@nvidia.com \
    --cc=fengguang.wu@intel.com \
    --cc=jcabezas@nvidia.com \
    --cc=jhubbard@nvidia.com \
    --cc=keith.busch@intel.com \
    --cc=kirill.shutemov@linux.intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mgorman@techsingularity.net \
    --cc=mhairgrove@nvidia.com \
    --cc=mhocko@kernel.org \
    --cc=nigupta@nvidia.com \
    --cc=vbabka@suse.cz \
    --cc=yang.shi@linux.alibaba.com \
    --cc=ziy@nvidia.com \
    /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

Linux-mm Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-mm/0 linux-mm/git/0.git

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


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


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