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 03/25] mm: migrate: Add a multi-threaded page migration function.
Date: Wed,  3 Apr 2019 19:00:24 -0700
Message-ID: <20190404020046.32741-4-zi.yan@sent.com> (raw)
In-Reply-To: <20190404020046.32741-1-zi.yan@sent.com>

From: Zi Yan <ziy@nvidia.com>

copy_page_multithread() function is added to migrate huge pages
in multi-threaded way, which provides higher throughput than
a single-threaded way.

Internally, copy_page_multithread() splits and distributes a huge page
into multiple threads, then send them as jobs to system_highpri_wq.

Signed-off-by: Zi Yan <ziy@nvidia.com>
---
 include/linux/highmem.h |   2 +
 mm/Makefile             |   2 +
 mm/copy_page.c          | 128 ++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 132 insertions(+)
 create mode 100644 mm/copy_page.c

diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index ea5cdbd8c..0f50dc5 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -276,4 +276,6 @@ static inline void copy_highpage(struct page *to, struct page *from)
 
 #endif
 
+int copy_page_multithread(struct page *to, struct page *from, int nr_pages);
+
 #endif /* _LINUX_HIGHMEM_H */
diff --git a/mm/Makefile b/mm/Makefile
index d210cc9..fa02a9f 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -44,6 +44,8 @@ obj-y			:= filemap.o mempool.o oom_kill.o fadvise.o \
 obj-y += init-mm.o
 obj-y += memblock.o
 
+obj-y += copy_page.o
+
 ifdef CONFIG_MMU
 	obj-$(CONFIG_ADVISE_SYSCALLS)	+= madvise.o
 endif
diff --git a/mm/copy_page.c b/mm/copy_page.c
new file mode 100644
index 0000000..9cf849c
--- /dev/null
+++ b/mm/copy_page.c
@@ -0,0 +1,128 @@
+/*
+ * Enhanced page copy routine.
+ *
+ * Copyright 2019 by NVIDIA.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Authors: Zi Yan <ziy@nvidia.com>
+ *
+ */
+
+#include <linux/highmem.h>
+#include <linux/workqueue.h>
+#include <linux/slab.h>
+#include <linux/freezer.h>
+
+
+const unsigned int limit_mt_num = 4;
+
+/* ======================== multi-threaded copy page ======================== */
+
+struct copy_item {
+	char *to;
+	char *from;
+	unsigned long chunk_size;
+};
+
+struct copy_page_info {
+	struct work_struct copy_page_work;
+	unsigned long num_items;
+	struct copy_item item_list[0];
+};
+
+static void copy_page_routine(char *vto, char *vfrom,
+	unsigned long chunk_size)
+{
+	memcpy(vto, vfrom, chunk_size);
+}
+
+static void copy_page_work_queue_thread(struct work_struct *work)
+{
+	struct copy_page_info *my_work = (struct copy_page_info *)work;
+	int i;
+
+	for (i = 0; i < my_work->num_items; ++i)
+		copy_page_routine(my_work->item_list[i].to,
+						  my_work->item_list[i].from,
+						  my_work->item_list[i].chunk_size);
+}
+
+int copy_page_multithread(struct page *to, struct page *from, int nr_pages)
+{
+	unsigned int total_mt_num = limit_mt_num;
+	int to_node = page_to_nid(to);
+	int i;
+	struct copy_page_info *work_items[NR_CPUS] = {0};
+	char *vto, *vfrom;
+	unsigned long chunk_size;
+	const struct cpumask *per_node_cpumask = cpumask_of_node(to_node);
+	int cpu_id_list[NR_CPUS] = {0};
+	int cpu;
+	int err = 0;
+
+	total_mt_num = min_t(unsigned int, total_mt_num,
+						 cpumask_weight(per_node_cpumask));
+	if (total_mt_num > 1)
+		total_mt_num = (total_mt_num / 2) * 2;
+
+	if (total_mt_num > num_online_cpus() || total_mt_num <=1)
+		return -ENODEV;
+
+	for (cpu = 0; cpu < total_mt_num; ++cpu) {
+		work_items[cpu] = kzalloc(sizeof(struct copy_page_info)
+						+ sizeof(struct copy_item), GFP_KERNEL);
+		if (!work_items[cpu]) {
+			err = -ENOMEM;
+			goto free_work_items;
+		}
+	}
+
+	i = 0;
+	for_each_cpu(cpu, per_node_cpumask) {
+		if (i >= total_mt_num)
+			break;
+		cpu_id_list[i] = cpu;
+		++i;
+	}
+
+	vfrom = kmap(from);
+	vto = kmap(to);
+	chunk_size = PAGE_SIZE*nr_pages / total_mt_num;
+
+	for (i = 0; i < total_mt_num; ++i) {
+		INIT_WORK((struct work_struct *)work_items[i],
+				  copy_page_work_queue_thread);
+
+		work_items[i]->num_items = 1;
+		work_items[i]->item_list[0].to = vto + i * chunk_size;
+		work_items[i]->item_list[0].from = vfrom + i * chunk_size;
+		work_items[i]->item_list[0].chunk_size = chunk_size;
+
+		queue_work_on(cpu_id_list[i],
+					  system_highpri_wq,
+					  (struct work_struct *)work_items[i]);
+	}
+
+	/* Wait until it finishes  */
+	for (i = 0; i < total_mt_num; ++i)
+		flush_work((struct work_struct *)work_items[i]);
+
+	kunmap(to);
+	kunmap(from);
+
+free_work_items:
+	for (cpu = 0; cpu < total_mt_num; ++cpu)
+		if (work_items[cpu])
+			kfree(work_items[cpu]);
+
+	return err;
+}
-- 
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 ` Zi Yan [this message]
2019-04-04  2:00 ` [RFC PATCH 04/25] mm: migrate: Add copy_page_multithread into migrate_pages Zi Yan
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=20190404020046.32741-4-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