Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
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>
In-Reply-To: <20190215220856.29749-1-zi.yan@sent.com>
References: <20190215220856.29749-1-zi.yan@sent.com>
Reply-To: ziy@nvidia.com
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

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