Linux-mm Archive on lore.kernel.org
 help / color / 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 29/31] mm: madvise: add madvise options to split PMD and PUD THPs.
Date: Fri, 15 Feb 2019 14:08:54 -0800
Message-ID: <20190215220856.29749-30-zi.yan@sent.com> (raw)
In-Reply-To: <20190215220856.29749-1-zi.yan@sent.com>

From: Zi Yan <ziy@nvidia.com>

Signed-off-by: Zi Yan <ziy@nvidia.com>
---
 include/uapi/asm-generic/mman-common.h |  12 +++
 mm/madvise.c                           | 106 +++++++++++++++++++++++++
 2 files changed, 118 insertions(+)

diff --git a/include/uapi/asm-generic/mman-common.h b/include/uapi/asm-generic/mman-common.h
index d1ec94a1970d..33db8b6a2ce0 100644
--- a/include/uapi/asm-generic/mman-common.h
+++ b/include/uapi/asm-generic/mman-common.h
@@ -69,6 +69,18 @@
 #define MADV_MEMDEFRAG	20		/* Worth backing with hugepages */
 #define MADV_NOMEMDEFRAG	21		/* Not worth backing with hugepages */
 
+#define MADV_SPLITHUGEPAGE	24		/* Split huge page in range once */
+#define MADV_PROMOTEHUGEPAGE	25		/* Promote range into huge page */
+
+#define MADV_SPLITHUGEMAP	26		/* Split huge page table entry in range once */
+#define MADV_PROMOTEHUGEMAP	27		/* Promote range into huge page table entry */
+
+#define MADV_SPLITHUGEPUDPAGE	28		/* Split huge page in range once */
+#define MADV_PROMOTEHUGEPUDPAGE	29		/* Promote range into huge page */
+
+#define MADV_SPLITHUGEPUDMAP	30		/* Split huge page table entry in range once */
+#define MADV_PROMOTEHUGEPUDMAP	31		/* Promote range into huge page table entry */
+
 /* compatibility flags */
 #define MAP_FILE	0
 
diff --git a/mm/madvise.c b/mm/madvise.c
index 9cef96d633e8..be3818c06e17 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -624,6 +624,95 @@ static long madvise_memdefrag(struct vm_area_struct *vma,
 	*prev = vma;
 	return memdefrag_madvise(vma, &vma->vm_flags, behavior);
 }
+
+static long madvise_split_promote_hugepage(struct vm_area_struct *vma,
+		     struct vm_area_struct **prev,
+		     unsigned long start, unsigned long end, int behavior)
+{
+	struct page *page;
+	unsigned long addr = start, haddr;
+	int ret = 0;
+	*prev = vma;
+
+	while (addr < end && !ret) {
+		switch (behavior) {
+		case MADV_SPLITHUGEMAP:
+			split_huge_pmd_address(vma, addr, false, NULL);
+			addr += HPAGE_PMD_SIZE;
+			break;
+		case MADV_SPLITHUGEPUDMAP:
+			split_huge_pud_address(vma, addr, false, NULL);
+			addr += HPAGE_PUD_SIZE;
+			break;
+		case MADV_SPLITHUGEPAGE:
+			page = follow_page(vma, addr, FOLL_GET);
+			if (page) {
+				lock_page(page);
+				if (split_huge_page(page)) {
+					pr_debug("%s: fail to split page\n", __func__);
+					ret = -EBUSY;
+				}
+				unlock_page(page);
+				put_page(page);
+			} else
+				ret = -ENODEV;
+			addr += HPAGE_PMD_SIZE;
+			break;
+		case MADV_SPLITHUGEPUDPAGE:
+			page = follow_page(vma, addr, FOLL_GET);
+			if (page) {
+				lock_page(page);
+				if (split_huge_pud_page(page)) {
+					pr_debug("%s: fail to split pud page\n", __func__);
+					ret = -EBUSY;
+				}
+				unlock_page(page);
+				put_page(page);
+			} else
+				ret = -ENODEV;
+			addr += HPAGE_PUD_SIZE;
+			break;
+		case MADV_PROMOTEHUGEMAP:
+			haddr = addr & HPAGE_PMD_MASK;
+			if (haddr >= start && (haddr + HPAGE_PMD_SIZE) <= end)
+				promote_huge_pmd_address(vma, haddr);
+			else
+				ret = -ENODEV;
+			addr += HPAGE_PMD_SIZE;
+			break;
+		case MADV_PROMOTEHUGEPUDMAP:
+			haddr = addr & HPAGE_PUD_MASK;
+			if (haddr >= start && (haddr + HPAGE_PUD_SIZE) <= end)
+				promote_huge_pud_address(vma, haddr);
+			else
+				ret = -ENODEV;
+			addr += HPAGE_PUD_SIZE;
+			break;
+		case MADV_PROMOTEHUGEPAGE:
+			haddr = addr & HPAGE_PMD_MASK;
+			if (haddr >= start && (haddr + HPAGE_PMD_SIZE) <= end)
+				promote_huge_page_address(vma, haddr);
+			else
+				ret = -ENODEV;
+			addr += HPAGE_PMD_SIZE;
+			break;
+		case MADV_PROMOTEHUGEPUDPAGE:
+			haddr = addr & HPAGE_PUD_MASK;
+			if (haddr >= start && (haddr + HPAGE_PUD_SIZE) <= end)
+				promote_huge_pud_page_address(vma, haddr);
+			else
+				ret = -ENODEV;
+			addr += HPAGE_PUD_SIZE;
+			break;
+		default:
+			ret = -EINVAL;
+			break;
+		}
+	}
+
+	return ret;
+}
+
 #ifdef CONFIG_MEMORY_FAILURE
 /*
  * Error injection support for memory error handling.
@@ -708,6 +797,15 @@ madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev,
 	case MADV_MEMDEFRAG:
 	case MADV_NOMEMDEFRAG:
 		return madvise_memdefrag(vma, prev, start, end, behavior);
+	case MADV_SPLITHUGEPAGE:
+	case MADV_PROMOTEHUGEPAGE:
+	case MADV_SPLITHUGEMAP:
+	case MADV_PROMOTEHUGEMAP:
+	case MADV_SPLITHUGEPUDPAGE:
+	case MADV_PROMOTEHUGEPUDPAGE:
+	case MADV_SPLITHUGEPUDMAP:
+	case MADV_PROMOTEHUGEPUDMAP:
+		return madvise_split_promote_hugepage(vma, prev, start, end, behavior);
 	default:
 		return madvise_behavior(vma, prev, start, end, behavior);
 	}
@@ -744,6 +842,14 @@ madvise_behavior_valid(int behavior)
 #endif
 	case MADV_MEMDEFRAG:
 	case MADV_NOMEMDEFRAG:
+	case MADV_SPLITHUGEPAGE:
+	case MADV_PROMOTEHUGEPAGE:
+	case MADV_SPLITHUGEMAP:
+	case MADV_PROMOTEHUGEMAP:
+	case MADV_SPLITHUGEPUDPAGE:
+	case MADV_PROMOTEHUGEPUDPAGE:
+	case MADV_SPLITHUGEPUDMAP:
+	case MADV_PROMOTEHUGEPUDMAP:
 		return true;
 
 	default:
-- 
2.20.1


  parent reply index

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 ` [RFC PATCH 19/31] mm: thp: 1GB THP support in try_to_unmap() Zi Yan
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 ` Zi Yan [this message]
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 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=20190215220856.29749-30-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

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