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 07/25] mm: migrate: Add copy_page_dma to use DMA Engine to copy pages.
Date: Wed,  3 Apr 2019 19:00:28 -0700
Message-ID: <20190404020046.32741-8-zi.yan@sent.com> (raw)
In-Reply-To: <20190404020046.32741-1-zi.yan@sent.com>

From: Zi Yan <ziy@nvidia.com>

vm.use_all_dma_chans will grab all usable DMA channels
vm.limit_dma_chans will limit how many DMA channels in use

Signed-off-by: Zi Yan <ziy@nvidia.com>
---
 include/linux/highmem.h      |   1 +
 include/linux/sched/sysctl.h |   3 +
 kernel/sysctl.c              |  19 +++
 mm/copy_page.c               | 291 +++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 314 insertions(+)

diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 0f50dc5..119bb39 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -277,5 +277,6 @@ 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);
+int copy_page_dma(struct page *to, struct page *from, int nr_pages);
 
 #endif /* _LINUX_HIGHMEM_H */
diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index 99ce6d7..ce11241 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -90,4 +90,7 @@ extern int sched_energy_aware_handler(struct ctl_table *table, int write,
 				 loff_t *ppos);
 #endif
 
+extern int sysctl_dma_page_migration(struct ctl_table *table, int write,
+				 void __user *buffer, size_t *lenp,
+				 loff_t *ppos);
 #endif /* _LINUX_SCHED_SYSCTL_H */
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 0eae0b8..b8712eb 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -103,6 +103,8 @@
 
 extern int accel_page_copy;
 extern unsigned int limit_mt_num;
+extern int use_all_dma_chans;
+extern int limit_dma_chans;
 
 /* External variables not in a header file. */
 extern int suid_dumpable;
@@ -1451,6 +1453,23 @@ static struct ctl_table vm_table[] = {
 		.extra1		= &zero,
 	},
 	 {
+		.procname	= "use_all_dma_chans",
+		.data		= &use_all_dma_chans,
+		.maxlen		= sizeof(use_all_dma_chans),
+		.mode		= 0644,
+		.proc_handler	= sysctl_dma_page_migration,
+		.extra1		= &zero,
+		.extra2		= &one,
+	 },
+	 {
+		.procname	= "limit_dma_chans",
+		.data		= &limit_dma_chans,
+		.maxlen		= sizeof(limit_dma_chans),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+		.extra1		= &zero,
+	 },
+	 {
 		.procname	= "hugetlb_shm_group",
 		.data		= &sysctl_hugetlb_shm_group,
 		.maxlen		= sizeof(gid_t),
diff --git a/mm/copy_page.c b/mm/copy_page.c
index 6665e3d..5e7a797 100644
--- a/mm/copy_page.c
+++ b/mm/copy_page.c
@@ -126,3 +126,294 @@ int copy_page_multithread(struct page *to, struct page *from, int nr_pages)
 
 	return err;
 }
+/* ======================== DMA copy page ======================== */
+#include <linux/dmaengine.h>
+#include <linux/dma-mapping.h>
+
+#define NUM_AVAIL_DMA_CHAN 16
+
+
+int use_all_dma_chans = 0;
+int limit_dma_chans = NUM_AVAIL_DMA_CHAN;
+
+
+struct dma_chan *copy_chan[NUM_AVAIL_DMA_CHAN] = {0};
+struct dma_device *copy_dev[NUM_AVAIL_DMA_CHAN] = {0};
+
+
+
+#ifdef CONFIG_PROC_SYSCTL
+extern int proc_dointvec_minmax(struct ctl_table *table, int write,
+		  void __user *buffer, size_t *lenp, loff_t *ppos);
+int sysctl_dma_page_migration(struct ctl_table *table, int write,
+				 void __user *buffer, size_t *lenp,
+				 loff_t *ppos)
+{
+	int err = 0;
+	int use_all_dma_chans_prior_val = use_all_dma_chans;
+	dma_cap_mask_t copy_mask;
+
+	if (write && !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	err = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+
+	if (err < 0)
+		return err;
+	if (write) {
+		/* Grab all DMA channels  */
+		if (use_all_dma_chans_prior_val == 0 && use_all_dma_chans == 1) {
+			int i;
+
+			dma_cap_zero(copy_mask);
+			dma_cap_set(DMA_MEMCPY, copy_mask);
+
+			dmaengine_get();
+			for (i = 0; i < NUM_AVAIL_DMA_CHAN; ++i) {
+				if (!copy_chan[i]) {
+					copy_chan[i] = dma_request_channel(copy_mask, NULL, NULL);
+				}
+				if (!copy_chan[i]) {
+					pr_err("%s: cannot grab channel: %d\n", __func__, i);
+					continue;
+				}
+
+				copy_dev[i] = copy_chan[i]->device;
+
+				if (!copy_dev[i]) {
+					pr_err("%s: no device: %d\n", __func__, i);
+					continue;
+				}
+			}
+
+		}
+		/* Release all DMA channels  */
+		else if (use_all_dma_chans_prior_val == 1 && use_all_dma_chans == 0) {
+			int i;
+
+			for (i = 0; i < NUM_AVAIL_DMA_CHAN; ++i) {
+				if (copy_chan[i]) {
+					dma_release_channel(copy_chan[i]);
+					copy_chan[i] = NULL;
+					copy_dev[i] = NULL;
+				}
+			}
+
+			dmaengine_put();
+		}
+
+		if (err)
+			use_all_dma_chans = use_all_dma_chans_prior_val;
+	}
+	return err;
+}
+
+#endif
+
+static int copy_page_dma_once(struct page *to, struct page *from, int nr_pages)
+{
+	static struct dma_chan *copy_chan = NULL;
+	struct dma_device *device = NULL;
+	struct dma_async_tx_descriptor *tx = NULL;
+	dma_cookie_t cookie;
+	enum dma_ctrl_flags flags = 0;
+	struct dmaengine_unmap_data *unmap = NULL;
+	dma_cap_mask_t mask;
+	int ret_val = 0;
+
+
+	dma_cap_zero(mask);
+	dma_cap_set(DMA_MEMCPY, mask);
+
+	dmaengine_get();
+
+	copy_chan = dma_request_channel(mask, NULL, NULL);
+
+	if (!copy_chan) {
+		pr_err("%s: cannot get a channel\n", __func__);
+		ret_val = -1;
+		goto no_chan;
+	}
+
+	device = copy_chan->device;
+
+	if (!device) {
+		pr_err("%s: cannot get a device\n", __func__);
+		ret_val = -2;
+		goto release;
+	}
+
+	unmap = dmaengine_get_unmap_data(device->dev, 2, GFP_NOWAIT);
+
+	if (!unmap) {
+		pr_err("%s: cannot get unmap data\n", __func__);
+		ret_val = -3;
+		goto release;
+	}
+
+	unmap->to_cnt = 1;
+	unmap->addr[0] = dma_map_page(device->dev, from, 0, PAGE_SIZE*nr_pages,
+					  DMA_TO_DEVICE);
+	unmap->from_cnt = 1;
+	unmap->addr[1] = dma_map_page(device->dev, to, 0, PAGE_SIZE*nr_pages,
+					  DMA_FROM_DEVICE);
+	unmap->len = PAGE_SIZE*nr_pages;
+
+	tx = device->device_prep_dma_memcpy(copy_chan,
+						unmap->addr[1],
+						unmap->addr[0], unmap->len,
+						flags);
+
+	if (!tx) {
+		pr_err("%s: null tx descriptor\n", __func__);
+		ret_val = -4;
+		goto unmap_dma;
+	}
+
+	cookie = tx->tx_submit(tx);
+
+	if (dma_submit_error(cookie)) {
+		pr_err("%s: submission error\n", __func__);
+		ret_val = -5;
+		goto unmap_dma;
+	}
+
+	if (dma_sync_wait(copy_chan, cookie) != DMA_COMPLETE) {
+		pr_err("%s: dma does not complete properly\n", __func__);
+		ret_val = -6;
+	}
+
+unmap_dma:
+	dmaengine_unmap_put(unmap);
+release:
+	if (copy_chan) {
+		dma_release_channel(copy_chan);
+	}
+no_chan:
+	dmaengine_put();
+
+	return ret_val;
+}
+
+static int copy_page_dma_always(struct page *to, struct page *from, int nr_pages)
+{
+	struct dma_async_tx_descriptor *tx[NUM_AVAIL_DMA_CHAN] = {0};
+	dma_cookie_t cookie[NUM_AVAIL_DMA_CHAN];
+	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;
+	size_t page_offset;
+
+	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", NUM_AVAIL_DMA_CHAN - total_available_chans);
+	}
+
+	total_available_chans = min_t(int, total_available_chans, limit_dma_chans);
+
+	/* round down to closest 2^x value  */
+	total_available_chans = 1<<ilog2(total_available_chans);
+
+	if ((nr_pages != 1) && (nr_pages % total_available_chans != 0))
+		return -5;
+
+	for (i = 0; i < total_available_chans; ++i) {
+		unmap[i] = dmaengine_get_unmap_data(copy_dev[i]->dev, 2, GFP_NOWAIT);
+		if (!unmap[i]) {
+			pr_err("%s: no unmap data at chan %d\n", __func__, i);
+			ret_val = -3;
+			goto unmap_dma;
+		}
+	}
+
+	for (i = 0; i < total_available_chans; ++i) {
+		if (nr_pages == 1) {
+			page_offset = PAGE_SIZE / total_available_chans;
+
+			unmap[i]->to_cnt = 1;
+			unmap[i]->addr[0] = dma_map_page(copy_dev[i]->dev, from, page_offset*i,
+							  page_offset,
+							  DMA_TO_DEVICE);
+			unmap[i]->from_cnt = 1;
+			unmap[i]->addr[1] = dma_map_page(copy_dev[i]->dev, to, page_offset*i,
+							  page_offset,
+							  DMA_FROM_DEVICE);
+			unmap[i]->len = page_offset;
+		} else {
+			page_offset = nr_pages / total_available_chans;
+
+			unmap[i]->to_cnt = 1;
+			unmap[i]->addr[0] = dma_map_page(copy_dev[i]->dev,
+								from + page_offset*i,
+								0,
+								PAGE_SIZE*page_offset,
+								DMA_TO_DEVICE);
+			unmap[i]->from_cnt = 1;
+			unmap[i]->addr[1] = dma_map_page(copy_dev[i]->dev,
+								to + page_offset*i,
+								0,
+								PAGE_SIZE*page_offset,
+								DMA_FROM_DEVICE);
+			unmap[i]->len = PAGE_SIZE*page_offset;
+		}
+	}
+
+	for (i = 0; i < total_available_chans; ++i) {
+		tx[i] = copy_dev[i]->device_prep_dma_memcpy(copy_chan[i],
+							unmap[i]->addr[1],
+							unmap[i]->addr[0],
+							unmap[i]->len,
+							flags[i]);
+		if (!tx[i]) {
+			pr_err("%s: no tx descriptor at chan %d\n", __func__, i);
+			ret_val = -4;
+			goto unmap_dma;
+		}
+	}
+
+	for (i = 0; i < total_available_chans; ++i) {
+		cookie[i] = tx[i]->tx_submit(tx[i]);
+
+		if (dma_submit_error(cookie[i])) {
+			pr_err("%s: submission error at chan %d\n", __func__, i);
+			ret_val = -5;
+			goto unmap_dma;
+		}
+
+		dma_async_issue_pending(copy_chan[i]);
+	}
+
+	for (i = 0; i < total_available_chans; ++i) {
+		if (dma_sync_wait(copy_chan[i], cookie[i]) != DMA_COMPLETE) {
+			ret_val = -6;
+			pr_err("%s: dma does not complete at chan %d\n", __func__, i);
+		}
+	}
+
+unmap_dma:
+
+	for (i = 0; i < total_available_chans; ++i) {
+		if (unmap[i])
+			dmaengine_unmap_put(unmap[i]);
+	}
+
+	return ret_val;
+}
+
+int copy_page_dma(struct page *to, struct page *from, int nr_pages)
+{
+	BUG_ON(hpage_nr_pages(from) != nr_pages);
+	BUG_ON(hpage_nr_pages(to) != nr_pages);
+
+	if (!use_all_dma_chans) {
+		return copy_page_dma_once(to, from, nr_pages);
+	}
+
+	return copy_page_dma_always(to, from, nr_pages);
+}
-- 
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 ` Zi Yan [this message]
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=20190404020046.32741-8-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