Linux-mm Archive on lore.kernel.org
 help / 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 09/25] mm: migrate: Add copy_page_lists_dma_always to support copy a list of pages.
Date: Wed,  3 Apr 2019 19:00:30 -0700
Message-ID: <20190404020046.32741-10-zi.yan@sent.com> (raw)
In-Reply-To: <20190404020046.32741-1-zi.yan@sent.com>

From: Zi Yan <ziy@nvidia.com>

Both src and dst page lists should match the page size at each
page and the length of both lists is shared.

Signed-off-by: Zi Yan <ziy@nvidia.com>
---
 mm/copy_page.c | 166 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 mm/internal.h  |   4 ++
 2 files changed, 170 insertions(+)

diff --git a/mm/copy_page.c b/mm/copy_page.c
index 5e7a797..84f1c02 100644
--- a/mm/copy_page.c
+++ b/mm/copy_page.c
@@ -417,3 +417,169 @@ int copy_page_dma(struct page *to, struct page *from, int nr_pages)
 
 	return copy_page_dma_always(to, from, nr_pages);
 }
+
+/*
+ * Use DMA copy a list of pages to a new location
+ *
+ * Just put each page into individual DMA channel.
+ *
+ * */
+int copy_page_lists_dma_always(struct page **to, struct page **from, int nr_items)
+{
+	struct dma_async_tx_descriptor **tx = NULL;
+	dma_cookie_t *cookie = NULL;
+	enum dma_ctrl_flags flags[NUM_AVAIL_DMA_CHAN] = {0};
+	struct dmaengine_unmap_data *unmap[NUM_AVAIL_DMA_CHAN] = {0};
+	int ret_val = 0;
+	int total_available_chans = NUM_AVAIL_DMA_CHAN;
+	int i;
+	int page_idx;
+
+	for (i = 0; i < NUM_AVAIL_DMA_CHAN; ++i) {
+		if (!copy_chan[i]) {
+			total_available_chans = i;
+		}
+	}
+	if (total_available_chans != NUM_AVAIL_DMA_CHAN) {
+		pr_err("%d channels are missing\n", NUM_AVAIL_DMA_CHAN - total_available_chans);
+	}
+	if (limit_dma_chans < total_available_chans)
+		total_available_chans = limit_dma_chans;
+
+	/* round down to closest 2^x value  */
+	total_available_chans = 1<<ilog2(total_available_chans);
+
+	total_available_chans = min_t(int, total_available_chans, nr_items);
+
+
+	tx = kzalloc(sizeof(struct dma_async_tx_descriptor*)*nr_items, GFP_KERNEL);
+	if (!tx) {
+		ret_val = -ENOMEM;
+		goto out;
+	}
+	cookie = kzalloc(sizeof(dma_cookie_t)*nr_items, GFP_KERNEL);
+	if (!cookie) {
+		ret_val = -ENOMEM;
+		goto out_free_tx;
+	}
+
+	for (i = 0; i < total_available_chans; ++i) {
+		int num_xfer_per_dev = nr_items / total_available_chans;
+
+		if (i < (nr_items % total_available_chans))
+			num_xfer_per_dev += 1;
+
+		if (num_xfer_per_dev > 128) {
+			ret_val = -ENOMEM;
+			pr_err("%s: too many pages to be transferred\n", __func__);
+			goto out_free_both;
+		}
+
+		unmap[i] = dmaengine_get_unmap_data(copy_dev[i]->dev,
+						2 * num_xfer_per_dev, GFP_NOWAIT);
+		if (!unmap[i]) {
+			pr_err("%s: no unmap data at chan %d\n", __func__, i);
+			ret_val = -ENODEV;
+			goto unmap_dma;
+		}
+	}
+
+	page_idx = 0;
+	for (i = 0; i < total_available_chans; ++i) {
+		int num_xfer_per_dev = nr_items / total_available_chans;
+		int xfer_idx;
+
+		if (i < (nr_items % total_available_chans))
+			num_xfer_per_dev += 1;
+
+		unmap[i]->to_cnt = num_xfer_per_dev;
+		unmap[i]->from_cnt = num_xfer_per_dev;
+		unmap[i]->len = hpage_nr_pages(from[i]) * PAGE_SIZE;
+
+		for (xfer_idx = 0; xfer_idx < num_xfer_per_dev; ++xfer_idx, ++page_idx) {
+			size_t page_len = hpage_nr_pages(from[page_idx]) * PAGE_SIZE;
+
+			BUG_ON(page_len != hpage_nr_pages(to[page_idx]) * PAGE_SIZE);
+			BUG_ON(unmap[i]->len != page_len);
+
+			unmap[i]->addr[xfer_idx] =
+				 dma_map_page(copy_dev[i]->dev, from[page_idx],
+							  0,
+							  page_len,
+							  DMA_TO_DEVICE);
+
+			unmap[i]->addr[xfer_idx+num_xfer_per_dev] =
+				 dma_map_page(copy_dev[i]->dev, to[page_idx],
+							  0,
+							  page_len,
+							  DMA_FROM_DEVICE);
+		}
+	}
+
+	page_idx = 0;
+	for (i = 0; i < total_available_chans; ++i) {
+		int num_xfer_per_dev = nr_items / total_available_chans;
+		int xfer_idx;
+
+		if (i < (nr_items % total_available_chans))
+			num_xfer_per_dev += 1;
+
+		for (xfer_idx = 0; xfer_idx < num_xfer_per_dev; ++xfer_idx, ++page_idx) {
+
+			tx[page_idx] = copy_dev[i]->device_prep_dma_memcpy(copy_chan[i],
+								unmap[i]->addr[xfer_idx + num_xfer_per_dev],
+								unmap[i]->addr[xfer_idx],
+								unmap[i]->len,
+								flags[i]);
+			if (!tx[page_idx]) {
+				pr_err("%s: no tx descriptor at chan %d xfer %d\n",
+					   __func__, i, xfer_idx);
+				ret_val = -ENODEV;
+				goto unmap_dma;
+			}
+
+			cookie[page_idx] = tx[page_idx]->tx_submit(tx[page_idx]);
+
+			if (dma_submit_error(cookie[page_idx])) {
+				pr_err("%s: submission error at chan %d xfer %d\n",
+					   __func__, i, xfer_idx);
+				ret_val = -ENODEV;
+				goto unmap_dma;
+			}
+		}
+
+		dma_async_issue_pending(copy_chan[i]);
+	}
+
+	page_idx = 0;
+	for (i = 0; i < total_available_chans; ++i) {
+		int num_xfer_per_dev = nr_items / total_available_chans;
+		int xfer_idx;
+
+		if (i < (nr_items % total_available_chans))
+			num_xfer_per_dev += 1;
+
+		for (xfer_idx = 0; xfer_idx < num_xfer_per_dev; ++xfer_idx, ++page_idx) {
+
+			if (dma_sync_wait(copy_chan[i], cookie[page_idx]) != DMA_COMPLETE) {
+				ret_val = -6;
+				pr_err("%s: dma does not complete at chan %d, xfer %d\n",
+					   __func__, i, xfer_idx);
+			}
+		}
+	}
+
+unmap_dma:
+	for (i = 0; i < total_available_chans; ++i) {
+		if (unmap[i])
+			dmaengine_unmap_put(unmap[i]);
+	}
+
+out_free_both:
+	kfree(cookie);
+out_free_tx:
+	kfree(tx);
+out:
+
+	return ret_val;
+}
diff --git a/mm/internal.h b/mm/internal.h
index 9eeaf2b..cb1a610 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -555,4 +555,8 @@ static inline bool is_migrate_highatomic_page(struct page *page)
 
 void setup_zone_pageset(struct zone *zone);
 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);
+
 #endif	/* __MM_INTERNAL_H */
-- 
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 ` [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 ` Zi Yan [this message]
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=20190404020046.32741-10-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