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 12/25] exchange pages: new page migration mechanism: exchange_pages()
Date: Wed,  3 Apr 2019 19:00:33 -0700
Message-ID: <20190404020046.32741-13-zi.yan@sent.com> (raw)
In-Reply-To: <20190404020046.32741-1-zi.yan@sent.com>

From: Zi Yan <ziy@nvidia.com>

It exchanges two pages by unmapping both first, then exchanging the
data of the pages using a u64 register, and finally remapping both
pages.

It saves the overheads of allocating two new pages in two
back-to-back migrate_pages().

Signed-off-by: Zi Yan <ziy@nvidia.com>
---
 include/linux/exchange.h |  23 ++
 include/linux/ksm.h      |   4 +
 mm/Makefile              |   1 +
 mm/exchange.c            | 597 +++++++++++++++++++++++++++++++++++++++++++++++
 mm/ksm.c                 |  35 +++
 5 files changed, 660 insertions(+)
 create mode 100644 include/linux/exchange.h
 create mode 100644 mm/exchange.c

diff --git a/include/linux/exchange.h b/include/linux/exchange.h
new file mode 100644
index 0000000..778068e
--- /dev/null
+++ b/include/linux/exchange.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_EXCHANGE_H
+#define _LINUX_EXCHANGE_H
+
+#include <linux/migrate.h>
+
+struct exchange_page_info {
+	struct page *from_page;
+	struct page *to_page;
+
+	struct anon_vma *from_anon_vma;
+	struct anon_vma *to_anon_vma;
+
+	int from_page_was_mapped;
+	int to_page_was_mapped;
+
+	struct list_head list;
+};
+
+int exchange_pages(struct list_head *exchange_list,
+			enum migrate_mode mode,
+			int reason);
+#endif /* _LINUX_EXCHANGE_H */
diff --git a/include/linux/ksm.h b/include/linux/ksm.h
index e48b1e4..170312d 100644
--- a/include/linux/ksm.h
+++ b/include/linux/ksm.h
@@ -55,6 +55,7 @@ void rmap_walk_ksm(struct page *page, struct rmap_walk_control *rwc);
 void ksm_migrate_page(struct page *newpage, struct page *oldpage);
 bool reuse_ksm_page(struct page *page,
 			struct vm_area_struct *vma, unsigned long address);
+void ksm_exchange_page(struct page *to_page, struct page *from_page);
 
 #else  /* !CONFIG_KSM */
 
@@ -92,6 +93,9 @@ static inline bool reuse_ksm_page(struct page *page,
 			struct vm_area_struct *vma, unsigned long address)
 {
 	return false;
+static inline void ksm_exchange_page(struct page *to_page,
+				struct page *from_page)
+{
 }
 #endif /* CONFIG_MMU */
 #endif /* !CONFIG_KSM */
diff --git a/mm/Makefile b/mm/Makefile
index fa02a9f..5e6c591 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -45,6 +45,7 @@ obj-y += init-mm.o
 obj-y += memblock.o
 
 obj-y += copy_page.o
+obj-y += exchange.o
 
 ifdef CONFIG_MMU
 	obj-$(CONFIG_ADVISE_SYSCALLS)	+= madvise.o
diff --git a/mm/exchange.c b/mm/exchange.c
new file mode 100644
index 0000000..626bbea
--- /dev/null
+++ b/mm/exchange.c
@@ -0,0 +1,597 @@
+/*
+ * Exchange two in-use pages. Page flags and page->mapping are exchanged
+ * as well. Only anonymous pages are supported.
+ *
+ * Copyright (C) 2016 NVIDIA, Zi Yan <ziy@nvidia.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ */
+
+#include <linux/syscalls.h>
+#include <linux/migrate.h>
+#include <linux/exchange.h>
+#include <linux/security.h>
+#include <linux/cpuset.h>
+#include <linux/hugetlb.h>
+#include <linux/mm_inline.h>
+#include <linux/page_idle.h>
+#include <linux/page-flags.h>
+#include <linux/ksm.h>
+#include <linux/memcontrol.h>
+#include <linux/balloon_compaction.h>
+#include <linux/buffer_head.h>
+
+
+#include "internal.h"
+
+/*
+ * Move a list of individual pages
+ */
+struct pages_to_node {
+	unsigned long from_addr;
+	int from_status;
+
+	unsigned long to_addr;
+	int to_status;
+};
+
+struct page_flags {
+	unsigned int page_error :1;
+	unsigned int page_referenced:1;
+	unsigned int page_uptodate:1;
+	unsigned int page_active:1;
+	unsigned int page_unevictable:1;
+	unsigned int page_checked:1;
+	unsigned int page_mappedtodisk:1;
+	unsigned int page_dirty:1;
+	unsigned int page_is_young:1;
+	unsigned int page_is_idle:1;
+	unsigned int page_swapcache:1;
+	unsigned int page_writeback:1;
+	unsigned int page_private:1;
+	unsigned int __pad:3;
+};
+
+
+static void exchange_page(char *to, char *from)
+{
+	u64 tmp;
+	int i;
+
+	for (i = 0; i < PAGE_SIZE; i += sizeof(tmp)) {
+		tmp = *((u64*)(from + i));
+		*((u64*)(from + i)) = *((u64*)(to + i));
+		*((u64*)(to + i)) = tmp;
+	}
+}
+
+static inline void exchange_highpage(struct page *to, struct page *from)
+{
+	char *vfrom, *vto;
+
+	vfrom = kmap_atomic(from);
+	vto = kmap_atomic(to);
+	exchange_page(vto, vfrom);
+	kunmap_atomic(vto);
+	kunmap_atomic(vfrom);
+}
+
+static void __exchange_gigantic_page(struct page *dst, struct page *src,
+				int nr_pages)
+{
+	int i;
+	struct page *dst_base = dst;
+	struct page *src_base = src;
+
+	for (i = 0; i < nr_pages; ) {
+		cond_resched();
+		exchange_highpage(dst, src);
+
+		i++;
+		dst = mem_map_next(dst, dst_base, i);
+		src = mem_map_next(src, src_base, i);
+	}
+}
+
+static void exchange_huge_page(struct page *dst, struct page *src)
+{
+	int i;
+	int nr_pages;
+
+	if (PageHuge(src)) {
+		/* hugetlbfs page */
+		struct hstate *h = page_hstate(src);
+		nr_pages = pages_per_huge_page(h);
+
+		if (unlikely(nr_pages > MAX_ORDER_NR_PAGES)) {
+			__exchange_gigantic_page(dst, src, nr_pages);
+			return;
+		}
+	} else {
+		/* thp page */
+		BUG_ON(!PageTransHuge(src));
+		nr_pages = hpage_nr_pages(src);
+	}
+
+	for (i = 0; i < nr_pages; i++) {
+		cond_resched();
+		exchange_highpage(dst + i, src + i);
+	}
+}
+
+/*
+ * Copy the page to its new location without polluting cache
+ */
+static void exchange_page_flags(struct page *to_page, struct page *from_page)
+{
+	int from_cpupid, to_cpupid;
+	struct page_flags from_page_flags, to_page_flags;
+	struct mem_cgroup *to_memcg = page_memcg(to_page),
+					  *from_memcg = page_memcg(from_page);
+
+	from_cpupid = page_cpupid_xchg_last(from_page, -1);
+
+	from_page_flags.page_error = TestClearPageError(from_page);
+	from_page_flags.page_referenced = TestClearPageReferenced(from_page);
+	from_page_flags.page_uptodate = PageUptodate(from_page);
+	ClearPageUptodate(from_page);
+	from_page_flags.page_active = TestClearPageActive(from_page);
+	from_page_flags.page_unevictable = TestClearPageUnevictable(from_page);
+	from_page_flags.page_checked = PageChecked(from_page);
+	ClearPageChecked(from_page);
+	from_page_flags.page_mappedtodisk = PageMappedToDisk(from_page);
+	ClearPageMappedToDisk(from_page);
+	from_page_flags.page_dirty = PageDirty(from_page);
+	ClearPageDirty(from_page);
+	from_page_flags.page_is_young = test_and_clear_page_young(from_page);
+	from_page_flags.page_is_idle = page_is_idle(from_page);
+	clear_page_idle(from_page);
+	from_page_flags.page_swapcache = PageSwapCache(from_page);
+	from_page_flags.page_private = PagePrivate(from_page);
+	ClearPagePrivate(from_page);
+	from_page_flags.page_writeback = test_clear_page_writeback(from_page);
+
+
+	to_cpupid = page_cpupid_xchg_last(to_page, -1);
+
+	to_page_flags.page_error = TestClearPageError(to_page);
+	to_page_flags.page_referenced = TestClearPageReferenced(to_page);
+	to_page_flags.page_uptodate = PageUptodate(to_page);
+	ClearPageUptodate(to_page);
+	to_page_flags.page_active = TestClearPageActive(to_page);
+	to_page_flags.page_unevictable = TestClearPageUnevictable(to_page);
+	to_page_flags.page_checked = PageChecked(to_page);
+	ClearPageChecked(to_page);
+	to_page_flags.page_mappedtodisk = PageMappedToDisk(to_page);
+	ClearPageMappedToDisk(to_page);
+	to_page_flags.page_dirty = PageDirty(to_page);
+	ClearPageDirty(to_page);
+	to_page_flags.page_is_young = test_and_clear_page_young(to_page);
+	to_page_flags.page_is_idle = page_is_idle(to_page);
+	clear_page_idle(to_page);
+	to_page_flags.page_swapcache = PageSwapCache(to_page);
+	to_page_flags.page_private = PagePrivate(to_page);
+	ClearPagePrivate(to_page);
+	to_page_flags.page_writeback = test_clear_page_writeback(to_page);
+
+	/* set to_page */
+	if (from_page_flags.page_error)
+		SetPageError(to_page);
+	if (from_page_flags.page_referenced)
+		SetPageReferenced(to_page);
+	if (from_page_flags.page_uptodate)
+		SetPageUptodate(to_page);
+	if (from_page_flags.page_active) {
+		VM_BUG_ON_PAGE(from_page_flags.page_unevictable, from_page);
+		SetPageActive(to_page);
+	} else if (from_page_flags.page_unevictable)
+		SetPageUnevictable(to_page);
+	if (from_page_flags.page_checked)
+		SetPageChecked(to_page);
+	if (from_page_flags.page_mappedtodisk)
+		SetPageMappedToDisk(to_page);
+
+	/* Move dirty on pages not done by migrate_page_move_mapping() */
+	if (from_page_flags.page_dirty)
+		SetPageDirty(to_page);
+
+	if (from_page_flags.page_is_young)
+		set_page_young(to_page);
+	if (from_page_flags.page_is_idle)
+		set_page_idle(to_page);
+
+	/* set from_page */
+	if (to_page_flags.page_error)
+		SetPageError(from_page);
+	if (to_page_flags.page_referenced)
+		SetPageReferenced(from_page);
+	if (to_page_flags.page_uptodate)
+		SetPageUptodate(from_page);
+	if (to_page_flags.page_active) {
+		VM_BUG_ON_PAGE(to_page_flags.page_unevictable, from_page);
+		SetPageActive(from_page);
+	} else if (to_page_flags.page_unevictable)
+		SetPageUnevictable(from_page);
+	if (to_page_flags.page_checked)
+		SetPageChecked(from_page);
+	if (to_page_flags.page_mappedtodisk)
+		SetPageMappedToDisk(from_page);
+
+	/* Move dirty on pages not done by migrate_page_move_mapping() */
+	if (to_page_flags.page_dirty)
+		SetPageDirty(from_page);
+
+	if (to_page_flags.page_is_young)
+		set_page_young(from_page);
+	if (to_page_flags.page_is_idle)
+		set_page_idle(from_page);
+
+	/*
+	 * Copy NUMA information to the new page, to prevent over-eager
+	 * future migrations of this same page.
+	 */
+	page_cpupid_xchg_last(to_page, from_cpupid);
+	page_cpupid_xchg_last(from_page, to_cpupid);
+
+	ksm_exchange_page(to_page, from_page);
+	/*
+	 * Please do not reorder this without considering how mm/ksm.c's
+	 * get_ksm_page() depends upon ksm_migrate_page() and PageSwapCache().
+	 */
+	ClearPageSwapCache(to_page);
+	ClearPageSwapCache(from_page);
+	if (from_page_flags.page_swapcache)
+		SetPageSwapCache(to_page);
+	if (to_page_flags.page_swapcache)
+		SetPageSwapCache(from_page);
+
+
+#ifdef CONFIG_PAGE_OWNER
+	/* exchange page owner  */
+	BUG();
+#endif
+	/* exchange mem cgroup  */
+	to_page->mem_cgroup = from_memcg;
+	from_page->mem_cgroup = to_memcg;
+
+}
+
+/*
+ * Replace the page in the mapping.
+ *
+ * The number of remaining references must be:
+ * 1 for anonymous pages without a mapping
+ * 2 for pages with a mapping
+ * 3 for pages with a mapping and PagePrivate/PagePrivate2 set.
+ */
+
+static int exchange_page_move_mapping(struct address_space *to_mapping,
+			struct address_space *from_mapping,
+			struct page *to_page, struct page *from_page,
+			enum migrate_mode mode,
+			int to_extra_count, int from_extra_count)
+{
+	int to_expected_count = 1 + to_extra_count,
+		from_expected_count = 1 + from_extra_count;
+	unsigned long from_page_index = page_index(from_page),
+				  to_page_index = page_index(to_page);
+	int to_swapbacked = PageSwapBacked(to_page),
+		from_swapbacked = PageSwapBacked(from_page);
+	struct address_space *to_mapping_value = to_page->mapping,
+						 *from_mapping_value = from_page->mapping;
+
+
+	if (!to_mapping) {
+		/* Anonymous page without mapping */
+		if (page_count(to_page) != to_expected_count)
+			return -EAGAIN;
+	}
+
+	if (!from_mapping) {
+		/* Anonymous page without mapping */
+		if (page_count(from_page) != from_expected_count)
+			return -EAGAIN;
+	}
+
+	/*
+	 * Now we know that no one else is looking at the page:
+	 * no turning back from here.
+	 */
+	/* from_page  */
+	from_page->index = to_page_index;
+	from_page->mapping = to_mapping_value;
+
+	ClearPageSwapBacked(from_page);
+	if (to_swapbacked)
+		SetPageSwapBacked(from_page);
+
+
+	/* to_page  */
+	to_page->index = from_page_index;
+	to_page->mapping = from_mapping_value;
+
+	ClearPageSwapBacked(to_page);
+	if (from_swapbacked)
+		SetPageSwapBacked(to_page);
+
+	return MIGRATEPAGE_SUCCESS;
+}
+
+static int exchange_from_to_pages(struct page *to_page, struct page *from_page,
+				enum migrate_mode mode)
+{
+	int rc = -EBUSY;
+	struct address_space *to_page_mapping, *from_page_mapping;
+
+	VM_BUG_ON_PAGE(!PageLocked(from_page), from_page);
+	VM_BUG_ON_PAGE(!PageLocked(to_page), to_page);
+
+	/* copy page->mapping not use page_mapping()  */
+	to_page_mapping = page_mapping(to_page);
+	from_page_mapping = page_mapping(from_page);
+
+	BUG_ON(from_page_mapping);
+	BUG_ON(to_page_mapping);
+
+	BUG_ON(PageWriteback(from_page));
+	BUG_ON(PageWriteback(to_page));
+
+	/* actual page mapping exchange */
+	rc = exchange_page_move_mapping(to_page_mapping, from_page_mapping,
+						to_page, from_page, mode, 0, 0);
+	/* actual page data exchange  */
+	if (rc != MIGRATEPAGE_SUCCESS)
+		return rc;
+
+	rc = -EFAULT;
+
+	if (PageHuge(from_page) || PageTransHuge(from_page))
+		exchange_huge_page(to_page, from_page);
+	else
+		exchange_highpage(to_page, from_page);
+	rc = 0;
+
+	exchange_page_flags(to_page, from_page);
+
+	return rc;
+}
+
+static int unmap_and_exchange(struct page *from_page, struct page *to_page,
+				enum migrate_mode mode)
+{
+	int rc = -EAGAIN;
+	int from_page_was_mapped = 0, to_page_was_mapped = 0;
+	pgoff_t from_index, to_index;
+	struct anon_vma *from_anon_vma = NULL, *to_anon_vma = NULL;
+
+	/* from_page lock down  */
+	if (!trylock_page(from_page)) {
+		if ((mode & MIGRATE_MODE_MASK) == MIGRATE_ASYNC)
+			goto out;
+
+		lock_page(from_page);
+	}
+
+	BUG_ON(PageWriteback(from_page));
+
+	/*
+	 * By try_to_unmap(), page->mapcount goes down to 0 here. In this case,
+	 * we cannot notice that anon_vma is freed while we migrates a page.
+	 * This get_anon_vma() delays freeing anon_vma pointer until the end
+	 * of migration. File cache pages are no problem because of page_lock()
+	 * File Caches may use write_page() or lock_page() in migration, then,
+	 * just care Anon page here.
+	 *
+	 * Only page_get_anon_vma() understands the subtleties of
+	 * getting a hold on an anon_vma from outside one of its mms.
+	 * But if we cannot get anon_vma, then we won't need it anyway,
+	 * because that implies that the anon page is no longer mapped
+	 * (and cannot be remapped so long as we hold the page lock).
+	 */
+	if (PageAnon(from_page) && !PageKsm(from_page))
+		from_anon_vma = page_get_anon_vma(from_page);
+
+	/* to_page lock down  */
+	if (!trylock_page(to_page)) {
+		if ((mode & MIGRATE_MODE_MASK) == MIGRATE_ASYNC)
+			goto out_unlock;
+
+		lock_page(to_page);
+	}
+
+	BUG_ON(PageWriteback(to_page));
+
+	/*
+	 * By try_to_unmap(), page->mapcount goes down to 0 here. In this case,
+	 * we cannot notice that anon_vma is freed while we migrates a page.
+	 * This get_anon_vma() delays freeing anon_vma pointer until the end
+	 * of migration. File cache pages are no problem because of page_lock()
+	 * File Caches may use write_page() or lock_page() in migration, then,
+	 * just care Anon page here.
+	 *
+	 * Only page_get_anon_vma() understands the subtleties of
+	 * getting a hold on an anon_vma from outside one of its mms.
+	 * But if we cannot get anon_vma, then we won't need it anyway,
+	 * because that implies that the anon page is no longer mapped
+	 * (and cannot be remapped so long as we hold the page lock).
+	 */
+	if (PageAnon(to_page) && !PageKsm(to_page))
+		to_anon_vma = page_get_anon_vma(to_page);
+
+	from_index = from_page->index;
+	to_index = to_page->index;
+
+	/*
+	 * Corner case handling:
+	 * 1. When a new swap-cache page is read into, it is added to the LRU
+	 * and treated as swapcache but it has no rmap yet.
+	 * Calling try_to_unmap() against a page->mapping==NULL page will
+	 * trigger a BUG.  So handle it here.
+	 * 2. An orphaned page (see truncate_complete_page) might have
+	 * fs-private metadata. The page can be picked up due to memory
+	 * offlining.  Everywhere else except page reclaim, the page is
+	 * invisible to the vm, so the page can not be migrated.  So try to
+	 * free the metadata, so the page can be freed.
+	 */
+	if (!from_page->mapping) {
+		VM_BUG_ON_PAGE(PageAnon(from_page), from_page);
+		if (page_has_private(from_page)) {
+			try_to_free_buffers(from_page);
+			goto out_unlock_both;
+		}
+	} else if (page_mapped(from_page)) {
+		/* Establish migration ptes */
+		VM_BUG_ON_PAGE(PageAnon(from_page) && !PageKsm(from_page) &&
+					   !from_anon_vma, from_page);
+		try_to_unmap(from_page,
+			TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS);
+		from_page_was_mapped = 1;
+	}
+
+	if (!to_page->mapping) {
+		VM_BUG_ON_PAGE(PageAnon(to_page), to_page);
+		if (page_has_private(to_page)) {
+			try_to_free_buffers(to_page);
+			goto out_unlock_both_remove_from_migration_pte;
+		}
+	} else if (page_mapped(to_page)) {
+		/* Establish migration ptes */
+		VM_BUG_ON_PAGE(PageAnon(to_page) && !PageKsm(to_page) &&
+					   !to_anon_vma, to_page);
+		try_to_unmap(to_page,
+			TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS);
+		to_page_was_mapped = 1;
+	}
+
+	if (!page_mapped(from_page) && !page_mapped(to_page))
+		rc = exchange_from_to_pages(to_page, from_page, mode);
+
+	/* In remove_migration_ptes(), page_walk_vma() assumes
+	 * from_page and to_page have the same index.
+	 * Thus, we restore old_page->index here.
+	 * Here to_page is the old_page.
+	 */
+	if (to_page_was_mapped) {
+		if (rc == MIGRATEPAGE_SUCCESS)
+			swap(to_page->index, to_index);
+
+		remove_migration_ptes(to_page,
+			rc == MIGRATEPAGE_SUCCESS ? from_page : to_page, false);
+
+		if (rc == MIGRATEPAGE_SUCCESS)
+			swap(to_page->index, to_index);
+	}
+
+out_unlock_both_remove_from_migration_pte:
+	if (from_page_was_mapped) {
+		if (rc == MIGRATEPAGE_SUCCESS)
+			swap(from_page->index, from_index);
+
+		remove_migration_ptes(from_page,
+			rc == MIGRATEPAGE_SUCCESS ? to_page : from_page, false);
+
+		if (rc == MIGRATEPAGE_SUCCESS)
+			swap(from_page->index, from_index);
+	}
+
+
+
+out_unlock_both:
+	if (to_anon_vma)
+		put_anon_vma(to_anon_vma);
+	unlock_page(to_page);
+out_unlock:
+	/* Drop an anon_vma reference if we took one */
+	if (from_anon_vma)
+		put_anon_vma(from_anon_vma);
+	unlock_page(from_page);
+out:
+
+	return rc;
+}
+
+/*
+ * Exchange pages in the exchange_list
+ *
+ * Caller should release the exchange_list resource.
+ *
+ * */
+int exchange_pages(struct list_head *exchange_list,
+			enum migrate_mode mode,
+			int reason)
+{
+	struct exchange_page_info *one_pair, *one_pair2;
+	int failed = 0;
+
+	list_for_each_entry_safe(one_pair, one_pair2, exchange_list, list) {
+		struct page *from_page = one_pair->from_page;
+		struct page *to_page = one_pair->to_page;
+		int rc;
+		int retry = 0;
+
+again:
+		if (page_count(from_page) == 1) {
+			/* page was freed from under us. So we are done  */
+			ClearPageActive(from_page);
+			ClearPageUnevictable(from_page);
+
+			put_page(from_page);
+			dec_node_page_state(from_page, NR_ISOLATED_ANON +
+					page_is_file_cache(from_page));
+
+			if (page_count(to_page) == 1) {
+				ClearPageActive(to_page);
+				ClearPageUnevictable(to_page);
+				put_page(to_page);
+			} else
+				goto putback_to_page;
+
+			continue;
+		}
+
+		if (page_count(to_page) == 1) {
+			/* page was freed from under us. So we are done  */
+			ClearPageActive(to_page);
+			ClearPageUnevictable(to_page);
+
+			put_page(to_page);
+
+			dec_node_page_state(to_page, NR_ISOLATED_ANON +
+					page_is_file_cache(to_page));
+
+			dec_node_page_state(from_page, NR_ISOLATED_ANON +
+					page_is_file_cache(from_page));
+			putback_lru_page(from_page);
+			continue;
+		}
+
+		/* TODO: compound page not supported */
+		if (PageCompound(from_page) || page_mapping(from_page)) {
+			++failed;
+			goto putback;
+		}
+
+		rc = unmap_and_exchange(from_page, to_page, mode);
+
+		if (rc == -EAGAIN && retry < 3) {
+			++retry;
+			goto again;
+		}
+
+		if (rc != MIGRATEPAGE_SUCCESS)
+			++failed;
+
+putback:
+		dec_node_page_state(from_page, NR_ISOLATED_ANON +
+				page_is_file_cache(from_page));
+
+		putback_lru_page(from_page);
+putback_to_page:
+		dec_node_page_state(to_page, NR_ISOLATED_ANON +
+				page_is_file_cache(to_page));
+
+		putback_lru_page(to_page);
+
+	}
+	return failed;
+}
diff --git a/mm/ksm.c b/mm/ksm.c
index fc64874..e5b492b 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -2716,6 +2716,41 @@ void ksm_migrate_page(struct page *newpage, struct page *oldpage)
 		set_page_stable_node(oldpage, NULL);
 	}
 }
+
+void ksm_exchange_page(struct page *to_page, struct page *from_page)
+{
+	struct stable_node *to_stable_node, *from_stable_node;
+
+	VM_BUG_ON_PAGE(!PageLocked(to_page), to_page);
+	VM_BUG_ON_PAGE(!PageLocked(from_page), from_page);
+
+	to_stable_node = page_stable_node(to_page);
+	from_stable_node = page_stable_node(from_page);
+	if (to_stable_node) {
+		VM_BUG_ON_PAGE(to_stable_node->kpfn != page_to_pfn(from_page),
+					from_page);
+		to_stable_node->kpfn = page_to_pfn(to_page);
+		/*
+		 * newpage->mapping was set in advance; now we need smp_wmb()
+		 * to make sure that the new stable_node->kpfn is visible
+		 * to get_ksm_page() before it can see that oldpage->mapping
+		 * has gone stale (or that PageSwapCache has been cleared).
+		 */
+		smp_wmb();
+	}
+	if (from_stable_node) {
+		VM_BUG_ON_PAGE(from_stable_node->kpfn != page_to_pfn(to_page),
+					to_page);
+		from_stable_node->kpfn = page_to_pfn(from_page);
+		/*
+		 * newpage->mapping was set in advance; now we need smp_wmb()
+		 * to make sure that the new stable_node->kpfn is visible
+		 * to get_ksm_page() before it can see that oldpage->mapping
+		 * has gone stale (or that PageSwapCache has been cleared).
+		 */
+		smp_wmb();
+	}
+}
 #endif /* CONFIG_MIGRATION */
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
-- 
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 ` [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 ` Zi Yan [this message]
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=20190404020046.32741-13-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