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 10/25] mm: migrate: copy_page_lists_mt() to copy a page list using multi-threads.
Date:   Wed,  3 Apr 2019 19:00:31 -0700
Message-Id: <20190404020046.32741-11-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>

This prepare the support for migrate_page_concur(), which migrates
multiple pages at the same time.

Signed-off-by: Zi Yan <ziy@nvidia.com>
---
 mm/copy_page.c | 123 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 mm/internal.h  |   2 +
 2 files changed, 125 insertions(+)

diff --git a/mm/copy_page.c b/mm/copy_page.c
index 84f1c02..d2fd67e 100644
--- a/mm/copy_page.c
+++ b/mm/copy_page.c
@@ -126,6 +126,129 @@ int copy_page_multithread(struct page *to, struct page *from, int nr_pages)
 
 	return err;
 }
+
+int copy_page_lists_mt(struct page **to, struct page **from, int nr_items)
+{
+	int err = 0;
+	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};
+	const struct cpumask *per_node_cpumask = cpumask_of_node(to_node);
+	int cpu_id_list[NR_CPUS] = {0};
+	int cpu;
+	int max_items_per_thread;
+	int item_idx;
+
+	total_mt_num = min_t(unsigned int, total_mt_num,
+						 cpumask_weight(per_node_cpumask));
+
+
+	if (total_mt_num > num_online_cpus())
+		return -ENODEV;
+
+	/* Each threads get part of each page, if nr_items < totla_mt_num */
+	if (nr_items < total_mt_num)
+		max_items_per_thread = nr_items;
+	else
+		max_items_per_thread = (nr_items / total_mt_num) +
+				((nr_items % total_mt_num)?1:0);
+
+
+	for (cpu = 0; cpu < total_mt_num; ++cpu) {
+		work_items[cpu] = kzalloc(sizeof(struct copy_page_info) +
+					sizeof(struct copy_item)*max_items_per_thread, 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;
+	}
+
+	if (nr_items < total_mt_num) {
+		for (cpu = 0; cpu < total_mt_num; ++cpu) {
+			INIT_WORK((struct work_struct *)work_items[cpu],
+					  copy_page_work_queue_thread);
+			work_items[cpu]->num_items = max_items_per_thread;
+		}
+
+		for (item_idx = 0; item_idx < nr_items; ++item_idx) {
+			unsigned long chunk_size = PAGE_SIZE * hpage_nr_pages(from[item_idx]) / total_mt_num;
+			char *vfrom = kmap(from[item_idx]);
+			char *vto = kmap(to[item_idx]);
+			VM_BUG_ON(PAGE_SIZE * hpage_nr_pages(from[item_idx]) % total_mt_num);
+			BUG_ON(hpage_nr_pages(to[item_idx]) !=
+				   hpage_nr_pages(from[item_idx]));
+
+			for (cpu = 0; cpu < total_mt_num; ++cpu) {
+				work_items[cpu]->item_list[item_idx].to = vto + chunk_size * cpu;
+				work_items[cpu]->item_list[item_idx].from = vfrom + chunk_size * cpu;
+				work_items[cpu]->item_list[item_idx].chunk_size =
+					chunk_size;
+			}
+		}
+
+		for (cpu = 0; cpu < total_mt_num; ++cpu)
+			queue_work_on(cpu_id_list[cpu],
+						  system_highpri_wq,
+						  (struct work_struct *)work_items[cpu]);
+	} else {
+		item_idx = 0;
+		for (cpu = 0; cpu < total_mt_num; ++cpu) {
+			int num_xfer_per_thread = nr_items / total_mt_num;
+			int per_cpu_item_idx;
+
+			if (cpu < (nr_items % total_mt_num))
+				num_xfer_per_thread += 1;
+
+			INIT_WORK((struct work_struct *)work_items[cpu],
+					  copy_page_work_queue_thread);
+
+			work_items[cpu]->num_items = num_xfer_per_thread;
+			for (per_cpu_item_idx = 0; per_cpu_item_idx < work_items[cpu]->num_items;
+				 ++per_cpu_item_idx, ++item_idx) {
+				work_items[cpu]->item_list[per_cpu_item_idx].to = kmap(to[item_idx]);
+				work_items[cpu]->item_list[per_cpu_item_idx].from =
+					kmap(from[item_idx]);
+				work_items[cpu]->item_list[per_cpu_item_idx].chunk_size =
+					PAGE_SIZE * hpage_nr_pages(from[item_idx]);
+
+				BUG_ON(hpage_nr_pages(to[item_idx]) !=
+					   hpage_nr_pages(from[item_idx]));
+			}
+
+			queue_work_on(cpu_id_list[cpu],
+						  system_highpri_wq,
+						  (struct work_struct *)work_items[cpu]);
+		}
+		if (item_idx != nr_items)
+			pr_err("%s: only %d out of %d pages are transferred\n", __func__,
+				item_idx - 1, nr_items);
+	}
+
+	/* Wait until it finishes  */
+	for (i = 0; i < total_mt_num; ++i)
+		flush_work((struct work_struct *)work_items[i]);
+
+	for (i = 0; i < nr_items; ++i) {
+			kunmap(to[i]);
+			kunmap(from[i]);
+	}
+
+free_work_items:
+	for (cpu = 0; cpu < total_mt_num; ++cpu)
+		if (work_items[cpu])
+			kfree(work_items[cpu]);
+
+	return err;
+}
 /* ======================== DMA copy page ======================== */
 #include <linux/dmaengine.h>
 #include <linux/dma-mapping.h>
diff --git a/mm/internal.h b/mm/internal.h
index cb1a610..51f5e1b 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -558,5 +558,7 @@ extern struct page *alloc_new_node_page(struct page *page, unsigned long node);
 
 extern int copy_page_lists_dma_always(struct page **to,
 			struct page **from, int nr_pages);
+extern int copy_page_lists_mt(struct page **to,
+			struct page **from, int nr_pages);
 
 #endif	/* __MM_INTERNAL_H */
-- 
2.7.4