From a3cf988fcb88301912f95ecf66913502bcb90200 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Wed, 31 Jan 2018 16:18:20 -0800
Subject: mm: use updated pmdp_invalidate() interface to track dirty/accessed
 bits

Use the modifed pmdp_invalidate() that returns the previous value of pmd
to transfer dirty and accessed bits.

Link: http://lkml.kernel.org/r/20171213105756.69879-12-kirill.shutemov@linux.intel.com
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: David Daney <david.daney@cavium.com>
Cc: David Miller <davem@davemloft.net>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Nitin Gupta <nitin.m.gupta@oracle.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vineet Gupta <vgupta@synopsys.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/huge_memory.c | 29 ++++++++++++-----------------
 1 file changed, 12 insertions(+), 17 deletions(-)

(limited to 'mm')

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 0d3ae51ce4f7..2a79a6b7d19b 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1910,17 +1910,7 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 	 * pmdp_invalidate() is required to make sure we don't miss
 	 * dirty/young flags set by hardware.
 	 */
-	entry = *pmd;
-	pmdp_invalidate(vma, addr, pmd);
-
-	/*
-	 * Recover dirty/young flags.  It relies on pmdp_invalidate to not
-	 * corrupt them.
-	 */
-	if (pmd_dirty(*pmd))
-		entry = pmd_mkdirty(entry);
-	if (pmd_young(*pmd))
-		entry = pmd_mkyoung(entry);
+	entry = pmdp_invalidate(vma, addr, pmd);
 
 	entry = pmd_modify(entry, newprot);
 	if (preserve_write)
@@ -2073,8 +2063,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 	struct mm_struct *mm = vma->vm_mm;
 	struct page *page;
 	pgtable_t pgtable;
-	pmd_t _pmd;
-	bool young, write, dirty, soft_dirty, pmd_migration = false;
+	pmd_t old, _pmd;
+	bool young, write, soft_dirty, pmd_migration = false;
 	unsigned long addr;
 	int i;
 
@@ -2130,7 +2120,6 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 	page_ref_add(page, HPAGE_PMD_NR - 1);
 	write = pmd_write(*pmd);
 	young = pmd_young(*pmd);
-	dirty = pmd_dirty(*pmd);
 	soft_dirty = pmd_soft_dirty(*pmd);
 
 	pmdp_huge_split_prepare(vma, haddr, pmd);
@@ -2160,8 +2149,6 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 			if (soft_dirty)
 				entry = pte_mksoft_dirty(entry);
 		}
-		if (dirty)
-			SetPageDirty(page + i);
 		pte = pte_offset_map(&_pmd, addr);
 		BUG_ON(!pte_none(*pte));
 		set_pte_at(mm, addr, pte, entry);
@@ -2209,7 +2196,15 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 	 * for this pmd), then we flush the SMP TLB and finally we write the
 	 * non-huge version of the pmd entry with pmd_populate.
 	 */
-	pmdp_invalidate(vma, haddr, pmd);
+	old = pmdp_invalidate(vma, haddr, pmd);
+
+	/*
+	 * Transfer dirty bit using value returned by pmd_invalidate() to be
+	 * sure we don't race with CPU that can set the bit under us.
+	 */
+	if (pmd_dirty(old))
+		SetPageDirty(page);
+
 	pmd_populate(mm, pmd, pgtable);
 
 	if (freeze) {
-- 
cgit v1.2.3-59-g8ed1b