linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Zi Yan <zi.yan@sent.com>
To: linux-mm@kvack.org, linux-kernel@vger.kernel.org
Cc: Dave Hansen <dave.hansen@linux.intel.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>,
	David Nellans <dnellans@nvidia.com>, Zi Yan <ziy@nvidia.com>
Subject: [RFC PATCH 19/31] mm: thp: 1GB THP support in try_to_unmap().
Date: Fri, 15 Feb 2019 14:08:44 -0800	[thread overview]
Message-ID: <20190215220856.29749-20-zi.yan@sent.com> (raw)
In-Reply-To: <20190215220856.29749-1-zi.yan@sent.com>

From: Zi Yan <ziy@nvidia.com>

Unmap different subpages in different sized THPs properly in the
try_to_unmap() function.

Signed-off-by: Zi Yan <ziy@nvidia.com>
---
 mm/migrate.c |   2 +-
 mm/rmap.c    | 140 +++++++++++++++++++++++++++++++++++++--------------
 2 files changed, 103 insertions(+), 39 deletions(-)

diff --git a/mm/migrate.c b/mm/migrate.c
index f7e5d88210ee..7deb64d75adb 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -223,7 +223,7 @@ static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma,
 
 #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
 		/* PMD-mapped THP migration entry */
-		if (!pvmw.pte) {
+		if (!pvmw.pte && pvmw.pmd) {
 			VM_BUG_ON_PAGE(PageHuge(page) || !PageTransCompound(page), page);
 			remove_migration_pmd(&pvmw, new);
 			continue;
diff --git a/mm/rmap.c b/mm/rmap.c
index 79908cfc518a..39f446a6775d 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1031,7 +1031,7 @@ void page_move_anon_rmap(struct page *page, struct vm_area_struct *vma)
  * __page_set_anon_rmap - set up new anonymous rmap
  * @page:	Page or Hugepage to add to rmap
  * @vma:	VM area to add page to.
- * @address:	User virtual address of the mapping	
+ * @address:	User virtual address of the mapping
  * @exclusive:	the page is exclusively owned by the current process
  */
 static void __page_set_anon_rmap(struct page *page,
@@ -1423,7 +1423,9 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 		.address = address,
 	};
 	pte_t pteval;
-	struct page *subpage;
+	pmd_t pmdval;
+	pud_t pudval;
+	struct page *subpage = NULL;
 	bool ret = true;
 	struct mmu_notifier_range range;
 	enum ttu_flags flags = (enum ttu_flags)arg;
@@ -1436,6 +1438,11 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 	    is_zone_device_page(page) && !is_device_private_page(page))
 		return true;
 
+	if (flags & TTU_SPLIT_HUGE_PUD) {
+		split_huge_pud_address(vma, address,
+				flags & TTU_SPLIT_FREEZE, page);
+	}
+
 	if (flags & TTU_SPLIT_HUGE_PMD) {
 		split_huge_pmd_address(vma, address,
 				flags & TTU_SPLIT_FREEZE, page);
@@ -1465,7 +1472,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 	while (page_vma_mapped_walk(&pvmw)) {
 #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
 		/* PMD-mapped THP migration entry */
-		if (!pvmw.pte && (flags & TTU_MIGRATION)) {
+		if (!pvmw.pte && pvmw.pmd && (flags & TTU_MIGRATION)) {
 			VM_BUG_ON_PAGE(PageHuge(page) || !PageTransCompound(page), page);
 
 			set_pmd_migration_entry(&pvmw, page);
@@ -1497,9 +1504,14 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 		}
 
 		/* Unexpected PMD-mapped THP? */
-		VM_BUG_ON_PAGE(!pvmw.pte, page);
 
-		subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte);
+		if (pvmw.pte)
+			subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte);
+		else if (!pvmw.pte && pvmw.pmd)
+			subpage = page - page_to_pfn(page) + pmd_pfn(*pvmw.pmd);
+		else if (!pvmw.pte && !pvmw.pmd && pvmw.pud)
+			subpage = page - page_to_pfn(page) + pud_pfn(*pvmw.pud);
+		VM_BUG_ON(!subpage);
 		address = pvmw.address;
 
 		if (PageHuge(page)) {
@@ -1556,16 +1568,26 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 		}
 
 		if (!(flags & TTU_IGNORE_ACCESS)) {
-			if (ptep_clear_flush_young_notify(vma, address,
-						pvmw.pte)) {
-				ret = false;
-				page_vma_mapped_walk_done(&pvmw);
-				break;
+			if ((pvmw.pte &&
+				 ptep_clear_flush_young_notify(vma, address, pvmw.pte)) ||
+				((!pvmw.pte && pvmw.pmd) &&
+				 pmdp_clear_flush_young_notify(vma, address, pvmw.pmd)) ||
+				((!pvmw.pte && !pvmw.pmd && pvmw.pud) &&
+				 pudp_clear_flush_young_notify(vma, address, pvmw.pud))
+				) {
+					ret = false;
+					page_vma_mapped_walk_done(&pvmw);
+					break;
 			}
 		}
 
 		/* Nuke the page table entry. */
-		flush_cache_page(vma, address, pte_pfn(*pvmw.pte));
+		if (pvmw.pte)
+			flush_cache_page(vma, address, pte_pfn(*pvmw.pte));
+		else if (!pvmw.pte && pvmw.pmd)
+			flush_cache_page(vma, address, pmd_pfn(*pvmw.pmd));
+		else if (!pvmw.pte && !pvmw.pmd && pvmw.pud)
+			flush_cache_page(vma, address, pud_pfn(*pvmw.pud));
 		if (should_defer_flush(mm, flags)) {
 			/*
 			 * We clear the PTE but do not flush so potentially
@@ -1575,16 +1597,34 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 			 * transition on a cached TLB entry is written through
 			 * and traps if the PTE is unmapped.
 			 */
-			pteval = ptep_get_and_clear(mm, address, pvmw.pte);
+			if (pvmw.pte) {
+				pteval = ptep_get_and_clear(mm, address, pvmw.pte);
+
+				set_tlb_ubc_flush_pending(mm, pte_dirty(pteval));
+			} else if (!pvmw.pte && pvmw.pmd) {
+				pmdval = pmdp_huge_get_and_clear(mm, address, pvmw.pmd);
 
-			set_tlb_ubc_flush_pending(mm, pte_dirty(pteval));
+				set_tlb_ubc_flush_pending(mm, pmd_dirty(pmdval));
+			} else if (!pvmw.pte && !pvmw.pmd && pvmw.pud) {
+				pudval = pudp_huge_get_and_clear(mm, address, pvmw.pud);
+
+				set_tlb_ubc_flush_pending(mm, pud_dirty(pudval));
+			}
 		} else {
-			pteval = ptep_clear_flush(vma, address, pvmw.pte);
+			if (pvmw.pte)
+				pteval = ptep_clear_flush(vma, address, pvmw.pte);
+			else if (!pvmw.pte && pvmw.pmd)
+				pmdval = pmdp_huge_clear_flush(vma, address, pvmw.pmd);
+			else if (!pvmw.pte && !pvmw.pmd && pvmw.pud)
+				pudval = pudp_huge_clear_flush(vma, address, pvmw.pud);
 		}
 
 		/* Move the dirty bit to the page. Now the pte is gone. */
-		if (pte_dirty(pteval))
-			set_page_dirty(page);
+			if ((pvmw.pte && pte_dirty(pteval)) ||
+				((!pvmw.pte && pvmw.pmd) && pmd_dirty(pmdval)) ||
+				((!pvmw.pte && !pvmw.pmd && pvmw.pud) && pud_dirty(pudval))
+				)
+				set_page_dirty(page);
 
 		/* Update high watermark before we lower rss */
 		update_hiwater_rss(mm);
@@ -1620,33 +1660,57 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 		} else if (IS_ENABLED(CONFIG_MIGRATION) &&
 				(flags & (TTU_MIGRATION|TTU_SPLIT_FREEZE))) {
 			swp_entry_t entry;
-			pte_t swp_pte;
 
-			if (arch_unmap_one(mm, vma, address, pteval) < 0) {
-				set_pte_at(mm, address, pvmw.pte, pteval);
-				ret = false;
-				page_vma_mapped_walk_done(&pvmw);
-				break;
-			}
+			if (pvmw.pte) {
+				pte_t swp_pte;
 
-			/*
-			 * Store the pfn of the page in a special migration
-			 * pte. do_swap_page() will wait until the migration
-			 * pte is removed and then restart fault handling.
-			 */
-			entry = make_migration_entry(subpage,
-					pte_write(pteval));
-			swp_pte = swp_entry_to_pte(entry);
-			if (pte_soft_dirty(pteval))
-				swp_pte = pte_swp_mksoft_dirty(swp_pte);
-			set_pte_at(mm, address, pvmw.pte, swp_pte);
-			/*
-			 * No need to invalidate here it will synchronize on
-			 * against the special swap migration pte.
-			 */
+				if (arch_unmap_one(mm, vma, address, pteval) < 0) {
+					set_pte_at(mm, address, pvmw.pte, pteval);
+					ret = false;
+					page_vma_mapped_walk_done(&pvmw);
+					break;
+				}
+
+				/*
+				 * Store the pfn of the page in a special migration
+				 * pte. do_swap_page() will wait until the migration
+				 * pte is removed and then restart fault handling.
+				 */
+				entry = make_migration_entry(subpage,
+						pte_write(pteval));
+				swp_pte = swp_entry_to_pte(entry);
+				if (pte_soft_dirty(pteval))
+					swp_pte = pte_swp_mksoft_dirty(swp_pte);
+				set_pte_at(mm, address, pvmw.pte, swp_pte);
+				/*
+				 * No need to invalidate here it will synchronize on
+				 * against the special swap migration pte.
+				 */
+			} else if (!pvmw.pte && pvmw.pmd) {
+				pmd_t swp_pmd;
+				/*
+				 * Store the pfn of the page in a special migration
+				 * pte. do_swap_page() will wait until the migration
+				 * pte is removed and then restart fault handling.
+				 */
+				entry = make_migration_entry(subpage,
+						pmd_write(pmdval));
+				swp_pmd = swp_entry_to_pmd(entry);
+				if (pmd_soft_dirty(pmdval))
+					swp_pmd = pmd_swp_mksoft_dirty(swp_pmd);
+				set_pmd_at(mm, address, pvmw.pmd, swp_pmd);
+				/*
+				 * No need to invalidate here it will synchronize on
+				 * against the special swap migration pte.
+				 */
+			} else if (!pvmw.pte && !pvmw.pmd && pvmw.pud) {
+				VM_BUG_ON(1);
+			}
 		} else if (PageAnon(page)) {
 			swp_entry_t entry = { .val = page_private(subpage) };
 			pte_t swp_pte;
+
+			VM_BUG_ON(!pvmw.pte);
 			/*
 			 * Store the swap location in the pte.
 			 * See handle_pte_fault() ...
-- 
2.20.1


  parent reply	other threads:[~2019-02-15 22:09 UTC|newest]

Thread overview: 49+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-02-15 22:08 [RFC PATCH 00/31] Generating physically contiguous memory after page allocation Zi Yan
2019-02-15 22:08 ` [RFC PATCH 01/31] mm: migrate: Add exchange_pages to exchange two lists of pages Zi Yan
2019-02-17 11:29   ` Matthew Wilcox
2019-02-18 17:31     ` Zi Yan
2019-02-18 17:42       ` Vlastimil Babka
2019-02-18 17:51         ` Zi Yan
2019-02-18 17:52           ` Matthew Wilcox
2019-02-18 17:59             ` Zi Yan
2019-02-19  7:42               ` Anshuman Khandual
2019-02-19 12:56                 ` Matthew Wilcox
2019-02-20  4:38                   ` Anshuman Khandual
2019-03-14  2:39                     ` Zi Yan
2019-02-21 21:10   ` Jerome Glisse
2019-02-21 21:25     ` Zi Yan
2019-02-15 22:08 ` [RFC PATCH 02/31] mm: migrate: Add THP exchange support Zi Yan
2019-02-15 22:08 ` [RFC PATCH 03/31] mm: migrate: Add tmpfs " Zi Yan
2019-02-15 22:08 ` [RFC PATCH 04/31] mm: add mem_defrag functionality Zi Yan
2019-02-15 22:08 ` [RFC PATCH 05/31] mem_defrag: split a THP if either src or dst is THP only Zi Yan
2019-02-15 22:08 ` [RFC PATCH 06/31] mm: Make MAX_ORDER configurable in Kconfig for buddy allocator Zi Yan
2019-02-15 22:08 ` [RFC PATCH 07/31] mm: deallocate pages with order > MAX_ORDER Zi Yan
2019-02-15 22:08 ` [RFC PATCH 08/31] mm: add pagechain container for storing multiple pages Zi Yan
2019-02-15 22:08 ` [RFC PATCH 09/31] mm: thp: 1GB anonymous page implementation Zi Yan
2019-02-15 22:08 ` [RFC PATCH 10/31] mm: proc: add 1GB THP kpageflag Zi Yan
2019-02-15 22:08 ` [RFC PATCH 11/31] mm: debug: print compound page order in dump_page() Zi Yan
2019-02-15 22:08 ` [RFC PATCH 12/31] mm: stats: Separate PMD THP and PUD THP stats Zi Yan
2019-02-15 22:08 ` [RFC PATCH 13/31] mm: thp: 1GB THP copy on write implementation Zi Yan
2019-02-15 22:08 ` [RFC PATCH 14/31] mm: thp: handling 1GB THP reference bit Zi Yan
2019-02-15 22:08 ` [RFC PATCH 15/31] mm: thp: add 1GB THP split_huge_pud_page() function Zi Yan
2019-02-15 22:08 ` [RFC PATCH 16/31] mm: thp: check compound_mapcount of PMD-mapped PUD THPs at free time Zi Yan
2019-02-15 22:08 ` [RFC PATCH 17/31] mm: thp: split properly PMD-mapped PUD THP to PTE-mapped PUD THP Zi Yan
2019-02-15 22:08 ` [RFC PATCH 18/31] mm: page_vma_walk: teach it about PMD-mapped " Zi Yan
2019-02-15 22:08 ` Zi Yan [this message]
2019-02-15 22:08 ` [RFC PATCH 20/31] mm: thp: split 1GB THPs at page reclaim Zi Yan
2019-02-15 22:08 ` [RFC PATCH 21/31] mm: thp: 1GB zero page shrinker Zi Yan
2019-02-15 22:08 ` [RFC PATCH 22/31] mm: thp: 1GB THP follow_p*d_page() support Zi Yan
2019-02-15 22:08 ` [RFC PATCH 23/31] mm: support 1GB THP pagemap support Zi Yan
2019-02-15 22:08 ` [RFC PATCH 24/31] sysctl: add an option to only print the head page virtual address Zi Yan
2019-02-15 22:08 ` [RFC PATCH 25/31] mm: thp: add a knob to enable/disable 1GB THPs Zi Yan
2019-02-15 22:08 ` [RFC PATCH 26/31] mm: thp: promote PTE-mapped THP to PMD-mapped THP Zi Yan
2019-02-15 22:08 ` [RFC PATCH 27/31] mm: thp: promote PMD-mapped PUD pages to PUD-mapped PUD pages Zi Yan
2019-02-15 22:08 ` [RFC PATCH 28/31] mm: vmstats: add page promotion stats Zi Yan
2019-02-15 22:08 ` [RFC PATCH 29/31] mm: madvise: add madvise options to split PMD and PUD THPs Zi Yan
2019-02-15 22:08 ` [RFC PATCH 30/31] mm: mem_defrag: thp: PMD THP and PUD THP in-place promotion support Zi Yan
2019-02-15 22:08 ` [RFC PATCH 31/31] sysctl: toggle to promote PUD-mapped 1GB THP or not Zi Yan
2019-02-20  1:42 ` [RFC PATCH 00/31] Generating physically contiguous memory after page allocation Mike Kravetz
2019-02-20  2:33   ` Zi Yan
2019-02-20  3:18     ` Mike Kravetz
2019-02-20  5:19       ` Zi Yan
2019-02-20  5:27         ` Mike Kravetz

Reply instructions:

You may reply publicly 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=20190215220856.29749-20-zi.yan@sent.com \
    --to=zi.yan@sent.com \
    --cc=akpm@linux-foundation.org \
    --cc=dave.hansen@linux.intel.com \
    --cc=dnellans@nvidia.com \
    --cc=jhubbard@nvidia.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=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
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).