| 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
| ||
|
Date: Wed, 3 Apr 2019 19:00:24 -0700
From: Zi Yan <zi.yan@...t.com>
To: Dave Hansen <dave.hansen@...ux.intel.com>,
Yang Shi <yang.shi@...ux.alibaba.com>,
Keith Busch <keith.busch@...el.com>,
Fengguang Wu <fengguang.wu@...el.com>, linux-mm@...ck.org,
linux-kernel@...r.kernel.org
Cc: Daniel Jordan <daniel.m.jordan@...cle.com>,
Michal Hocko <mhocko@...nel.org>,
"Kirill A . Shutemov" <kirill.shutemov@...ux.intel.com>,
Andrew Morton <akpm@...ux-foundation.org>,
Vlastimil Babka <vbabka@...e.cz>,
Mel Gorman <mgorman@...hsingularity.net>,
John Hubbard <jhubbard@...dia.com>,
Mark Hairgrove <mhairgrove@...dia.com>,
Nitin Gupta <nigupta@...dia.com>,
Javier Cabezas <jcabezas@...dia.com>,
David Nellans <dnellans@...dia.com>, Zi Yan <ziy@...dia.com>
Subject: [RFC PATCH 03/25] mm: migrate: Add a multi-threaded page migration function.
From: Zi Yan <ziy@...dia.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@...dia.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@...dia.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
Powered by blists - more mailing lists