[PATCH v4 00/13] pagewalk: improve vma handling, apply to new users

@@ -1080,15 +1080,12 @@ static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask,
 				 struct mm_walk *walk)
 {
 	struct pagemapread *pm = walk->private;
-	struct vm_area_struct *vma;
+	struct vm_area_struct *vma = walk->vma;
 	int err = 0;
 	int flags2;
 	pagemap_entry_t pme;
 
-	vma = find_vma(walk->mm, addr);
-	WARN_ON_ONCE(!vma);
-
-	if (vma && (vma->vm_flags & VM_SOFTDIRTY))
+	if (vma->vm_flags & VM_SOFTDIRTY)
 		flags2 = __PM_SOFT_DIRTY;
 	else
 		flags2 = 0;

@@ -715,7 +715,6 @@ enum clear_refs_types {
 };
 
 struct clear_refs_private {
-	struct vm_area_struct *vma;
 	enum clear_refs_types type;
 };
 

@@ -748,7 +747,7 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
 				unsigned long end, struct mm_walk *walk)
 {
 	struct clear_refs_private *cp = walk->private;
-	struct vm_area_struct *vma = cp->vma;
+	struct vm_area_struct *vma = walk->vma;
 	pte_t *pte, ptent;
 	spinlock_t *ptl;
 	struct page *page;

@@ -782,6 +781,29 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
 	return 0;
 }
 
+static int clear_refs_test_walk(unsigned long start, unsigned long end,
+				struct mm_walk *walk)
+{
+	struct clear_refs_private *cp = walk->private;
+	struct vm_area_struct *vma = walk->vma;
+
+	/*
+	 * Writing 1 to /proc/pid/clear_refs affects all pages.
+	 * Writing 2 to /proc/pid/clear_refs only affects anonymous pages.
+	 * Writing 3 to /proc/pid/clear_refs only affects file mapped pages.
+	 * Writing 4 to /proc/pid/clear_refs affects all pages.
+	 */
+	if (cp->type == CLEAR_REFS_ANON && vma->vm_file)
+		return 1;
+	if (cp->type == CLEAR_REFS_MAPPED && !vma->vm_file)
+		return 1;
+	if (cp->type == CLEAR_REFS_SOFT_DIRTY) {
+		if (vma->vm_flags & VM_SOFTDIRTY)
+			vma->vm_flags &= ~VM_SOFTDIRTY;
+	}
+	return 0;
+}
+
 static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 				size_t count, loff_t *ppos)
 {

@@ -822,38 +844,14 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 		};
 		struct mm_walk clear_refs_walk = {
 			.pmd_entry = clear_refs_pte_range,
+			.test_walk = clear_refs_test_walk,
 			.mm = mm,
 			.private = &cp,
 		};
 		down_read(&mm->mmap_sem);
 		if (type == CLEAR_REFS_SOFT_DIRTY)
 			mmu_notifier_invalidate_range_start(mm, 0, -1);
-		for (vma = mm->mmap; vma; vma = vma->vm_next) {
-			cp.vma = vma;
-			if (is_vm_hugetlb_page(vma))
-				continue;
-			/*
-			 * Writing 1 to /proc/pid/clear_refs affects all pages.
-			 *
-			 * Writing 2 to /proc/pid/clear_refs only affects
-			 * Anonymous pages.
-			 *
-			 * Writing 3 to /proc/pid/clear_refs only affects file
-			 * mapped pages.
-			 *
-			 * Writing 4 to /proc/pid/clear_refs affects all pages.
-			 */
-			if (type == CLEAR_REFS_ANON && vma->vm_file)
-				continue;
-			if (type == CLEAR_REFS_MAPPED && !vma->vm_file)
-				continue;
-			if (type == CLEAR_REFS_SOFT_DIRTY) {
-				if (vma->vm_flags & VM_SOFTDIRTY)
-					vma->vm_flags &= ~VM_SOFTDIRTY;
-			}
-			walk_page_range(vma->vm_start, vma->vm_end,
-					&clear_refs_walk);
-		}
+		walk_page_range(0, ~0UL, &clear_refs_walk);
 		if (type == CLEAR_REFS_SOFT_DIRTY)
 			mmu_notifier_invalidate_range_end(mm, 0, -1);
 		flush_tlb_mm(mm);

@@ -1347,7 +1347,7 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
 	return 0;
 }
 #ifdef CONFIG_HUGETLB_PAGE
-static int gather_hugetbl_stats(pte_t *pte, unsigned long hmask,
+static int gather_hugetlb_stats(pte_t *pte, unsigned long hmask,
 		unsigned long addr, unsigned long end, struct mm_walk *walk)
 {
 	struct numa_maps *md;

@@ -1366,7 +1366,7 @@ static int gather_hugetbl_stats(pte_t *pte, unsigned long hmask,
 }
 
 #else
-static int gather_hugetbl_stats(pte_t *pte, unsigned long hmask,
+static int gather_hugetlb_stats(pte_t *pte, unsigned long hmask,
 		unsigned long addr, unsigned long end, struct mm_walk *walk)
 {
 	return 0;

@@ -1398,7 +1398,7 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 
 	md->vma = vma;
 
-	walk.hugetlb_entry = gather_hugetbl_stats;
+	walk.hugetlb_entry = gather_hugetlb_stats;
 	walk.pmd_entry = gather_pte_stats;
 	walk.private = md;
 	walk.mm = mm;

@@ -1245,7 +1245,6 @@ const struct file_operations proc_pagemap_operations = {
 #ifdef CONFIG_NUMA
 
 struct numa_maps {
-	struct vm_area_struct *vma;
 	unsigned long pages;
 	unsigned long anon;
 	unsigned long active;

@@ -1314,18 +1313,17 @@ static struct page *can_gather_numa_stats(pte_t pte, struct vm_area_struct *vma,
 static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
 		unsigned long end, struct mm_walk *walk)
 {
-	struct numa_maps *md;
+	struct numa_maps *md = walk->private;
+	struct vm_area_struct *vma = walk->vma;
 	spinlock_t *ptl;
 	pte_t *orig_pte;
 	pte_t *pte;
 
-	md = walk->private;
-
-	if (pmd_trans_huge_lock(pmd, md->vma, &ptl) == 1) {
+	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
 		pte_t huge_pte = *(pte_t *)pmd;
 		struct page *page;
 
-		page = can_gather_numa_stats(huge_pte, md->vma, addr);
+		page = can_gather_numa_stats(huge_pte, vma, addr);
 		if (page)
 			gather_stats(page, md, pte_dirty(huge_pte),
 				     HPAGE_PMD_SIZE/PAGE_SIZE);

@@ -1337,7 +1335,7 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
 		return 0;
 	orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
 	do {
-		struct page *page = can_gather_numa_stats(*pte, md->vma, addr);
+		struct page *page = can_gather_numa_stats(*pte, vma, addr);
 		if (!page)
 			continue;
 		gather_stats(page, md, pte_dirty(*pte), 1);

@@ -1385,7 +1383,12 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 	struct file *file = vma->vm_file;
 	struct task_struct *task = proc_priv->task;
 	struct mm_struct *mm = vma->vm_mm;
-	struct mm_walk walk = {};
+	struct mm_walk walk = {
+		.hugetlb_entry = gather_hugetlb_stats,
+		.pmd_entry = gather_pte_stats,
+		.private = md,
+		.mm = mm,
+	};
 	struct mempolicy *pol;
 	char buffer[64];
 	int nid;

@@ -1396,13 +1399,6 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 	/* Ensure we start with an empty set of numa_maps statistics. */
 	memset(md, 0, sizeof(*md));
 
-	md->vma = vma;
-
-	walk.hugetlb_entry = gather_hugetlb_stats;
-	walk.pmd_entry = gather_pte_stats;
-	walk.private = md;
-	walk.mm = mm;
-
 	pol = get_vma_policy(task, vma, vma->vm_start);
 	mpol_to_str(buffer, sizeof(buffer), pol);
 	mpol_cond_put(pol);

@@ -1432,7 +1428,8 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 	if (is_vm_hugetlb_page(vma))
 		seq_puts(m, " huge");
 
-	walk_page_range(vma->vm_start, vma->vm_end, &walk);
+	/* mmap_sem is held by m_start */
+	walk_page_vma(vma, &walk);
 
 	if (!md->pages)
 		goto out;

@@ -134,7 +134,7 @@ static void subpage_prot_clear(unsigned long addr, unsigned long len)
 static int subpage_walk_pmd_entry(pmd_t *pmd, unsigned long addr,
 				  unsigned long end, struct mm_walk *walk)
 {
-	struct vm_area_struct *vma = walk->private;
+	struct vm_area_struct *vma = walk->vma;
 	split_huge_page_pmd(vma, addr, pmd);
 	return 0;
 }

@@ -163,9 +163,7 @@ static void subpage_mark_vma_nohuge(struct mm_struct *mm, unsigned long addr,
 		if (vma->vm_start >= (addr + len))
 			break;
 		vma->vm_flags |= VM_NOHUGEPAGE;
-		subpage_proto_walk.private = vma;
-		walk_page_range(vma->vm_start, vma->vm_end,
-				&subpage_proto_walk);
+		walk_page_vma(vma, &subpage_proto_walk);
 		vma = vma->vm_next;
 	}
 }

@@ -1410,26 +1410,6 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	return ret;
 }
 
-int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
-		unsigned long addr, unsigned long end,
-		unsigned char *vec)
-{
-	spinlock_t *ptl;
-	int ret = 0;
-
-	if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
-		/*
-		 * All logical pages in the range are present
-		 * if backed by a huge page.
-		 */
-		spin_unlock(ptl);
-		memset(vec, 1, (end - addr) >> PAGE_SHIFT);
-		ret = 1;
-	}
-
-	return ret;
-}
-
 int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma,
 		  unsigned long old_addr,
 		  unsigned long new_addr, unsigned long old_end,

@@ -19,38 +19,26 @@
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
 
-static void mincore_hugetlb_page_range(struct vm_area_struct *vma,
-				unsigned long addr, unsigned long end,
-				unsigned char *vec)
+static int mincore_hugetlb(pte_t *pte, unsigned long hmask, unsigned long addr,
+			unsigned long end, struct mm_walk *walk)
 {
+	int err = 0;
 #ifdef CONFIG_HUGETLB_PAGE
-	struct hstate *h;
+	unsigned char present;
+	unsigned char *vec = walk->private;
 
-	h = hstate_vma(vma);
-	while (1) {
-		unsigned char present;
-		pte_t *ptep;
-		/*
-		 * Huge pages are always in RAM for now, but
-		 * theoretically it needs to be checked.
-		 */
-		ptep = huge_pte_offset(current->mm,
-				       addr & huge_page_mask(h));
-		present = ptep && !huge_pte_none(huge_ptep_get(ptep));
-		while (1) {
-			*vec = present;
-			vec++;
-			addr += PAGE_SIZE;
-			if (addr == end)
-				return;
-			/* check hugepage border */
-			if (!(addr & ~huge_page_mask(h)))
-				break;
-		}
-	}
+	/*
+	 * Hugepages under user process are always in RAM and never
+	 * swapped out, but theoretically it needs to be checked.
+	 */
+	present = pte && !huge_pte_none(huge_ptep_get(pte));
+	for (; addr != end; vec++, addr += PAGE_SIZE)
+		*vec = present;
+	walk->private += (end - addr) >> PAGE_SHIFT;
 #else
 	BUG();
 #endif
+	return err;
 }
 
 /*

@@ -94,14 +82,15 @@ static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff)
 	return present;
 }
 
-static void mincore_unmapped_range(struct vm_area_struct *vma,
-				unsigned long addr, unsigned long end,
-				unsigned char *vec)
+static int mincore_unmapped_range(unsigned long addr, unsigned long end,
+				   struct mm_walk *walk)
 {
+	struct vm_area_struct *vma = walk->vma;
+	unsigned char *vec = walk->private;
 	unsigned long nr = (end - addr) >> PAGE_SHIFT;
 	int i;
 
-	if (vma->vm_file) {
+	if (vma && vma->vm_file) {
 		pgoff_t pgoff;
 
 		pgoff = linear_page_index(vma, addr);

@@ -111,25 +100,38 @@ static void mincore_unmapped_range(struct vm_area_struct *vma,
 		for (i = 0; i < nr; i++)
 			vec[i] = 0;
 	}
+	walk->private += nr;
+	return 0;
 }
 
-static void mincore_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
-			unsigned long addr, unsigned long end,
-			unsigned char *vec)
+static int mincore_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
+			struct mm_walk *walk)
 {
-	unsigned long next;
 	spinlock_t *ptl;
+	struct vm_area_struct *vma = walk->vma;
 	pte_t *ptep;
 
-	ptep = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
-	do {
+	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
+		memset(walk->private, 1, (end - addr) >> PAGE_SHIFT);
+		walk->private += (end - addr) >> PAGE_SHIFT;
+		spin_unlock(ptl);
+		return 0;
+	}
+
+	if (pmd_trans_unstable(pmd))
+		return 0;
+
+	ptep = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+	for (; addr != end; ptep++, addr += PAGE_SIZE) {
 		pte_t pte = *ptep;
 		pgoff_t pgoff;
+		unsigned char *vec = walk->private;
 
-		next = addr + PAGE_SIZE;
-		if (pte_none(pte))
-			mincore_unmapped_range(vma, addr, next, vec);
-		else if (pte_present(pte))
+		if (pte_none(pte)) {
+			mincore_unmapped_range(addr, addr + PAGE_SIZE, walk);
+			continue;
+		}
+		if (pte_present(pte))
 			*vec = 1;
 		else if (pte_file(pte)) {
 			pgoff = pte_to_pgoff(pte);

@@ -151,70 +153,11 @@ static void mincore_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 #endif
 			}
 		}
-		vec++;
-	} while (ptep++, addr = next, addr != end);
+		walk->private++;
+	}
 	pte_unmap_unlock(ptep - 1, ptl);
-}
-
-static void mincore_pmd_range(struct vm_area_struct *vma, pud_t *pud,
-			unsigned long addr, unsigned long end,
-			unsigned char *vec)
-{
-	unsigned long next;
-	pmd_t *pmd;
-
-	pmd = pmd_offset(pud, addr);
-	do {
-		next = pmd_addr_end(addr, end);
-		if (pmd_trans_huge(*pmd)) {
-			if (mincore_huge_pmd(vma, pmd, addr, next, vec)) {
-				vec += (next - addr) >> PAGE_SHIFT;
-				continue;
-			}
-			/* fall through */
-		}
-		if (pmd_none_or_trans_huge_or_clear_bad(pmd))
-			mincore_unmapped_range(vma, addr, next, vec);
-		else
-			mincore_pte_range(vma, pmd, addr, next, vec);
-		vec += (next - addr) >> PAGE_SHIFT;
-	} while (pmd++, addr = next, addr != end);
-}
-
-static void mincore_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
-			unsigned long addr, unsigned long end,
-			unsigned char *vec)
-{
-	unsigned long next;
-	pud_t *pud;
-
-	pud = pud_offset(pgd, addr);
-	do {
-		next = pud_addr_end(addr, end);
-		if (pud_none_or_clear_bad(pud))
-			mincore_unmapped_range(vma, addr, next, vec);
-		else
-			mincore_pmd_range(vma, pud, addr, next, vec);
-		vec += (next - addr) >> PAGE_SHIFT;
-	} while (pud++, addr = next, addr != end);
-}
-
-static void mincore_page_range(struct vm_area_struct *vma,
-			unsigned long addr, unsigned long end,
-			unsigned char *vec)
-{
-	unsigned long next;
-	pgd_t *pgd;
-
-	pgd = pgd_offset(vma->vm_mm, addr);
-	do {
-		next = pgd_addr_end(addr, end);
-		if (pgd_none_or_clear_bad(pgd))
-			mincore_unmapped_range(vma, addr, next, vec);
-		else
-			mincore_pud_range(vma, pgd, addr, next, vec);
-		vec += (next - addr) >> PAGE_SHIFT;
-	} while (pgd++, addr = next, addr != end);
+	cond_resched();
+	return 0;
 }
 
 /*

@@ -225,20 +168,28 @@ static void mincore_page_range(struct vm_area_struct *vma,
 static long do_mincore(unsigned long addr, unsigned long pages, unsigned char *vec)
 {
 	struct vm_area_struct *vma;
-	unsigned long end;
+	int err;
+	struct mm_walk mincore_walk = {
+		.pmd_entry = mincore_pte_range,
+		.pte_hole = mincore_unmapped_range,
+		.hugetlb_entry = mincore_hugetlb,
+		.private = vec,
+	};
 
 	vma = find_vma(current->mm, addr);
 	if (!vma || addr < vma->vm_start)
 		return -ENOMEM;
+	mincore_walk.mm = vma->vm_mm;
 
-	end = min(vma->vm_end, addr + (pages << PAGE_SHIFT));
-
-	if (is_vm_hugetlb_page(vma))
-		mincore_hugetlb_page_range(vma, addr, end, vec);
-	else
-		mincore_page_range(vma, addr, end, vec);
+	err = walk_page_vma(vma, &mincore_walk);
+	if (err < 0)
+		return err;
+	else {
+		unsigned long end;
 
-	return (end - addr) >> PAGE_SHIFT;
+		end = min(vma->vm_end, addr + (pages << PAGE_SHIFT));
+		return (end - addr) >> PAGE_SHIFT;
+	}
 }
 
 /*

@@ -718,10 +718,10 @@ struct clear_refs_private {
 	enum clear_refs_types type;
 };
 
+#ifdef CONFIG_MEM_SOFT_DIRTY
 static inline void clear_soft_dirty(struct vm_area_struct *vma,
 		unsigned long addr, pte_t *pte)
 {
-#ifdef CONFIG_MEM_SOFT_DIRTY
 	/*
 	 * The soft-dirty tracker uses #PF-s to catch writes
 	 * to pages, so write-protect the pte as well. See the

@@ -740,9 +740,35 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma,
 	}
 
 	set_pte_at(vma->vm_mm, addr, pte, ptent);
-#endif
 }
 
+static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma,
+		unsigned long addr, pmd_t *pmdp)
+{
+	pmd_t pmd = *pmdp;
+
+	pmd = pmd_wrprotect(pmd);
+	pmd = pmd_clear_flags(pmd, _PAGE_SOFT_DIRTY);
+
+	if (vma->vm_flags & VM_SOFTDIRTY)
+		vma->vm_flags &= ~VM_SOFTDIRTY;
+
+	set_pmd_at(vma->vm_mm, addr, pmdp, pmd);
+}
+
+#else
+
+static inline void clear_soft_dirty(struct vm_area_struct *vma,
+		unsigned long addr, pte_t *pte)
+{
+}
+
+static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma,
+		unsigned long addr, pmd_t *pmdp)
+{
+}
+#endif
+
 static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
 				unsigned long end, struct mm_walk *walk)
 {

@@ -752,7 +778,22 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
 	spinlock_t *ptl;
 	struct page *page;
 
-	split_huge_page_pmd(vma, addr, pmd);
+	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
+		if (cp->type == CLEAR_REFS_SOFT_DIRTY) {
+			clear_soft_dirty_pmd(vma, addr, pmd);
+			goto out;
+		}
+
+		page = pmd_page(*pmd);
+
+		/* Clear accessed and referenced bits. */
+		pmdp_test_and_clear_young(vma, addr, pmd);
+		ClearPageReferenced(page);
+out:
+		spin_unlock(ptl);
+		return 0;
+	}
+
 	if (pmd_trans_unstable(pmd))
 		return 0;
 

@@ -479,24 +479,34 @@ static const struct mempolicy_operations mpol_ops[MPOL_MAX] = {
 static void migrate_page_add(struct page *page, struct list_head *pagelist,
 				unsigned long flags);
 
+struct queue_pages {
+	struct list_head *pagelist;
+	unsigned long flags;
+	nodemask_t *nmask;
+	struct vm_area_struct *prev;
+};
+
 /*
  * Scan through pages checking if pages follow certain conditions,
  * and move them to the pagelist if they do.
  */
-static int queue_pages_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
-		unsigned long addr, unsigned long end,
-		const nodemask_t *nodes, unsigned long flags,
-		void *private)
+static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr,
+			unsigned long end, struct mm_walk *walk)
 {
-	pte_t *orig_pte;
+	struct vm_area_struct *vma = walk->vma;
+	struct page *page;
+	struct queue_pages *qp = walk->private;
+	unsigned long flags = qp->flags;
+	int nid;
 	pte_t *pte;
 	spinlock_t *ptl;
 
-	orig_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
-	do {
-		struct page *page;
-		int nid;
+	split_huge_page_pmd(vma, addr, pmd);
+	if (pmd_trans_unstable(pmd))
+		return 0;
 
+	pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+	for (; addr != end; pte++, addr += PAGE_SIZE) {
 		if (!pte_present(*pte))
 			continue;
 		page = vm_normal_page(vma, addr, *pte);

@@ -509,114 +519,46 @@ static int queue_pages_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 		if (PageReserved(page))
 			continue;
 		nid = page_to_nid(page);
-		if (node_isset(nid, *nodes) == !!(flags & MPOL_MF_INVERT))
+		if (node_isset(nid, *qp->nmask) == !!(flags & MPOL_MF_INVERT))
 			continue;
 
 		if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
-			migrate_page_add(page, private, flags);
-		else
-			break;
-	} while (pte++, addr += PAGE_SIZE, addr != end);
-	pte_unmap_unlock(orig_pte, ptl);
-	return addr != end;
+			migrate_page_add(page, qp->pagelist, flags);
+	}
+	pte_unmap_unlock(pte - 1, ptl);
+	cond_resched();
+	return 0;
 }
 
-static void queue_pages_hugetlb_pmd_range(struct vm_area_struct *vma,
-		pmd_t *pmd, const nodemask_t *nodes, unsigned long flags,
-				    void *private)
+static int queue_pages_hugetlb(pte_t *pte, unsigned long hmask,
+			       unsigned long addr, unsigned long end,
+			       struct mm_walk *walk)
 {
 #ifdef CONFIG_HUGETLB_PAGE
+	struct queue_pages *qp = walk->private;
+	unsigned long flags = qp->flags;
 	int nid;
 	struct page *page;
 	spinlock_t *ptl;
 	pte_t entry;
 
-	ptl = huge_pte_lock(hstate_vma(vma), vma->vm_mm, (pte_t *)pmd);
-	entry = huge_ptep_get((pte_t *)pmd);
+	ptl = huge_pte_lock(hstate_vma(walk->vma), walk->mm, pte);
+	entry = huge_ptep_get(pte);
 	if (!pte_present(entry))
 		goto unlock;
 	page = pte_page(entry);
 	nid = page_to_nid(page);
-	if (node_isset(nid, *nodes) == !!(flags & MPOL_MF_INVERT))
+	if (node_isset(nid, *qp->nmask) == !!(flags & MPOL_MF_INVERT))
 		goto unlock;
 	/* With MPOL_MF_MOVE, we migrate only unshared hugepage. */
 	if (flags & (MPOL_MF_MOVE_ALL) ||
 	    (flags & MPOL_MF_MOVE && page_mapcount(page) == 1))
-		isolate_huge_page(page, private);
+		isolate_huge_page(page, qp->pagelist);
 unlock:
 	spin_unlock(ptl);
 #else
 	BUG();
 #endif
-}
-
-static inline int queue_pages_pmd_range(struct vm_area_struct *vma, pud_t *pud,
-		unsigned long addr, unsigned long end,
-		const nodemask_t *nodes, unsigned long flags,
-		void *private)
-{
-	pmd_t *pmd;
-	unsigned long next;
-
-	pmd = pmd_offset(pud, addr);
-	do {
-		next = pmd_addr_end(addr, end);
-		if (!pmd_present(*pmd))
-			continue;
-		if (pmd_huge(*pmd) && is_vm_hugetlb_page(vma)) {
-			queue_pages_hugetlb_pmd_range(vma, pmd, nodes,
-						flags, private);
-			continue;
-		}
-		split_huge_page_pmd(vma, addr, pmd);
-		if (pmd_none_or_trans_huge_or_clear_bad(pmd))
-			continue;
-		if (queue_pages_pte_range(vma, pmd, addr, next, nodes,
-				    flags, private))
-			return -EIO;
-	} while (pmd++, addr = next, addr != end);
-	return 0;
-}
-
-static inline int queue_pages_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
-		unsigned long addr, unsigned long end,
-		const nodemask_t *nodes, unsigned long flags,
-		void *private)
-{
-	pud_t *pud;
-	unsigned long next;
-
-	pud = pud_offset(pgd, addr);
-	do {
-		next = pud_addr_end(addr, end);
-		if (pud_huge(*pud) && is_vm_hugetlb_page(vma))
-			continue;
-		if (pud_none_or_clear_bad(pud))
-			continue;
-		if (queue_pages_pmd_range(vma, pud, addr, next, nodes,
-				    flags, private))
-			return -EIO;
-	} while (pud++, addr = next, addr != end);
-	return 0;
-}
-
-static inline int queue_pages_pgd_range(struct vm_area_struct *vma,
-		unsigned long addr, unsigned long end,
-		const nodemask_t *nodes, unsigned long flags,
-		void *private)
-{
-	pgd_t *pgd;
-	unsigned long next;
-
-	pgd = pgd_offset(vma->vm_mm, addr);
-	do {
-		next = pgd_addr_end(addr, end);
-		if (pgd_none_or_clear_bad(pgd))
-			continue;
-		if (queue_pages_pud_range(vma, pgd, addr, next, nodes,
-				    flags, private))
-			return -EIO;
-	} while (pgd++, addr = next, addr != end);
 	return 0;
 }
 

@@ -649,6 +591,44 @@ static unsigned long change_prot_numa(struct vm_area_struct *vma,
 }
 #endif /* CONFIG_NUMA_BALANCING */
 
+static int queue_pages_test_walk(unsigned long start, unsigned long end,
+				struct mm_walk *walk)
+{
+	struct vm_area_struct *vma = walk->vma;
+	struct queue_pages *qp = walk->private;
+	unsigned long endvma = vma->vm_end;
+	unsigned long flags = qp->flags;
+
+	if (endvma > end)
+		endvma = end;
+	if (vma->vm_start > start)
+		start = vma->vm_start;
+
+	if (!(flags & MPOL_MF_DISCONTIG_OK)) {
+		if (!vma->vm_next && vma->vm_end < end)
+			return -EFAULT;
+		if (qp->prev && qp->prev->vm_end < vma->vm_start)
+			return -EFAULT;
+	}
+
+	qp->prev = vma;
+
+	if (vma->vm_flags & VM_PFNMAP)
+		return 1;
+
+	if (flags & MPOL_MF_LAZY) {
+		change_prot_numa(vma, start, endvma);
+		return 1;
+	}
+
+	if ((flags & MPOL_MF_STRICT) ||
+	    ((flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) &&
+	     vma_migratable(vma)))
+		/* queue pages from current vma */
+		return 0;
+	return 1;
+}
+
 /*
  * Walk through page tables and collect pages to be migrated.
  *

@@ -658,48 +638,24 @@ static unsigned long change_prot_numa(struct vm_area_struct *vma,
  */
 static int
 queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end,
-		const nodemask_t *nodes, unsigned long flags, void *private)
-{
-	int err = 0;
-	struct vm_area_struct *vma, *prev;
-
-	vma = find_vma(mm, start);
-	if (!vma)
-		return -EFAULT;
-	prev = NULL;
-	for (; vma && vma->vm_start < end; vma = vma->vm_next) {
-		unsigned long endvma = vma->vm_end;
-
-		if (endvma > end)
-			endvma = end;
-		if (vma->vm_start > start)
-			start = vma->vm_start;
-
-		if (!(flags & MPOL_MF_DISCONTIG_OK)) {
-			if (!vma->vm_next && vma->vm_end < end)
-				return -EFAULT;
-			if (prev && prev->vm_end < vma->vm_start)
-				return -EFAULT;
-		}
-
-		if (flags & MPOL_MF_LAZY) {
-			change_prot_numa(vma, start, endvma);
-			goto next;
-		}
-
-		if ((flags & MPOL_MF_STRICT) ||
-		     ((flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) &&
-		      vma_migratable(vma))) {
-
-			err = queue_pages_pgd_range(vma, start, endvma, nodes,
-						flags, private);
-			if (err)
-				break;
-		}
-next:
-		prev = vma;
-	}
-	return err;
+		nodemask_t *nodes, unsigned long flags,
+		struct list_head *pagelist)
+{
+	struct queue_pages qp = {
+		.pagelist = pagelist,
+		.flags = flags,
+		.nmask = nodes,
+		.prev = NULL,
+	};
+	struct mm_walk queue_pages_walk = {
+		.hugetlb_entry = queue_pages_hugetlb,
+		.pmd_entry = queue_pages_pte_range,
+		.test_walk = queue_pages_test_walk,
+		.mm = mm,
+		.private = &qp,
+	};
+
+	return walk_page_range(start, end, &queue_pages_walk);
 }
 
 /*