Merge branch 'akpm' (patches from Andrew)

Merge second set of updates from Andrew Morton:
 "More of MM"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (83 commits)
  mm/nommu.c: fix arithmetic overflow in __vm_enough_memory()
  mm/mmap.c: fix arithmetic overflow in __vm_enough_memory()
  vmstat: Reduce time interval to stat update on idle cpu
  mm/page_owner.c: remove unnecessary stack_trace field
  Documentation/filesystems/proc.txt: describe /proc/<pid>/map_files
  mm: incorporate read-only pages into transparent huge pages
  vmstat: do not use deferrable delayed work for vmstat_update
  mm: more aggressive page stealing for UNMOVABLE allocations
  mm: always steal split buddies in fallback allocations
  mm: when stealing freepages, also take pages created by splitting buddy page
  mincore: apply page table walker on do_mincore()
  mm: /proc/pid/clear_refs: avoid split_huge_page()
  mm: pagewalk: fix misbehavior of walk_page_range for vma(VM_PFNMAP)
  mempolicy: apply page table walker on queue_pages_range()
  arch/powerpc/mm/subpage-prot.c: use walk->vma and walk_page_vma()
  memcg: cleanup preparation for page table walk
  numa_maps: remove numa_maps->vma
  numa_maps: fix typo in gather_hugetbl_stats
  pagemap: use walk->vma instead of calling find_vma()
  clear_refs: remove clear_refs_private->vma and introduce clear_refs_test_walk()
  ...

3 files changed, 124 insertions, 112 deletions

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 790dbae..c73df6a 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1407,8 +1407,8 @@ int extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end)
 	while (index <= end_index) {
 		page = find_get_page(inode->i_mapping, index);
 		BUG_ON(!page); /* Pages should be in the extent_io_tree */
-		account_page_redirty(page);
 		__set_page_dirty_nobuffers(page);
+		account_page_redirty(page);
 		page_cache_release(page);
 		index++;
 	}
diff --git a/fs/proc/page.c b/fs/proc/page.c
index 1e3187d..7eee2d8 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -5,6 +5,7 @@
 #include <linux/ksm.h>
 #include <linux/mm.h>
 #include <linux/mmzone.h>
+#include <linux/huge_mm.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/hugetlb.h>
@@ -121,9 +122,18 @@ u64 stable_page_flags(struct page *page)
 	 * just checks PG_head/PG_tail, so we need to check PageLRU/PageAnon
 	 * to make sure a given page is a thp, not a non-huge compound page.
 	 */
-	else if (PageTransCompound(page) && (PageLRU(compound_head(page)) ||
-					     PageAnon(compound_head(page))))
-		u |= 1 << KPF_THP;
+	else if (PageTransCompound(page)) {
+		struct page *head = compound_head(page);
+
+		if (PageLRU(head) || PageAnon(head))
+			u |= 1 << KPF_THP;
+		else if (is_huge_zero_page(head)) {
+			u |= 1 << KPF_ZERO_PAGE;
+			u |= 1 << KPF_THP;
+		}
+	} else if (is_zero_pfn(page_to_pfn(page)))
+		u |= 1 << KPF_ZERO_PAGE;
+
 
 	/*
 	 * Caveats on high order pages: page->_count will only be set
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 6396f88..0e36c1e 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -21,7 +21,7 @@
 
 void task_mem(struct seq_file *m, struct mm_struct *mm)
 {
-	unsigned long data, text, lib, swap;
+	unsigned long data, text, lib, swap, ptes, pmds;
 	unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss;
 
 	/*
@@ -42,6 +42,8 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
 	text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> 10;
 	lib = (mm->exec_vm << (PAGE_SHIFT-10)) - text;
 	swap = get_mm_counter(mm, MM_SWAPENTS);
+	ptes = PTRS_PER_PTE * sizeof(pte_t) * atomic_long_read(&mm->nr_ptes);
+	pmds = PTRS_PER_PMD * sizeof(pmd_t) * mm_nr_pmds(mm);
 	seq_printf(m,
 		"VmPeak:\t%8lu kB\n"
 		"VmSize:\t%8lu kB\n"
@@ -54,6 +56,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
 		"VmExe:\t%8lu kB\n"
 		"VmLib:\t%8lu kB\n"
 		"VmPTE:\t%8lu kB\n"
+		"VmPMD:\t%8lu kB\n"
 		"VmSwap:\t%8lu kB\n",
 		hiwater_vm << (PAGE_SHIFT-10),
 		total_vm << (PAGE_SHIFT-10),
@@ -63,8 +66,8 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
 		total_rss << (PAGE_SHIFT-10),
 		data << (PAGE_SHIFT-10),
 		mm->stack_vm << (PAGE_SHIFT-10), text, lib,
-		(PTRS_PER_PTE * sizeof(pte_t) *
-		 atomic_long_read(&mm->nr_ptes)) >> 10,
+		ptes >> 10,
+		pmds >> 10,
 		swap << (PAGE_SHIFT-10));
 }
 
@@ -433,7 +436,6 @@ const struct file_operations proc_tid_maps_operations = {
 
 #ifdef CONFIG_PROC_PAGE_MONITOR
 struct mem_size_stats {
-	struct vm_area_struct *vma;
 	unsigned long resident;
 	unsigned long shared_clean;
 	unsigned long shared_dirty;
@@ -482,7 +484,7 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
 		struct mm_walk *walk)
 {
 	struct mem_size_stats *mss = walk->private;
-	struct vm_area_struct *vma = mss->vma;
+	struct vm_area_struct *vma = walk->vma;
 	struct page *page = NULL;
 
 	if (pte_present(*pte)) {
@@ -506,7 +508,7 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
 		struct mm_walk *walk)
 {
 	struct mem_size_stats *mss = walk->private;
-	struct vm_area_struct *vma = mss->vma;
+	struct vm_area_struct *vma = walk->vma;
 	struct page *page;
 
 	/* FOLL_DUMP will return -EFAULT on huge zero page */
@@ -527,8 +529,7 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
 static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 			   struct mm_walk *walk)
 {
-	struct mem_size_stats *mss = walk->private;
-	struct vm_area_struct *vma = mss->vma;
+	struct vm_area_struct *vma = walk->vma;
 	pte_t *pte;
 	spinlock_t *ptl;
 
@@ -620,10 +621,8 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
 	};
 
 	memset(&mss, 0, sizeof mss);
-	mss.vma = vma;
 	/* mmap_sem is held in m_start */
-	if (vma->vm_mm && !is_vm_hugetlb_page(vma))
-		walk_page_range(vma->vm_start, vma->vm_end, &smaps_walk);
+	walk_page_vma(vma, &smaps_walk);
 
 	show_map_vma(m, vma, is_pid);
 
@@ -737,14 +736,13 @@ enum clear_refs_types {
 };
 
 struct clear_refs_private {
-	struct vm_area_struct *vma;
 	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
@@ -761,19 +759,60 @@ 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)
 {
 	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;
 
-	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;
 
@@ -802,6 +841,28 @@ 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;
+
+	if (vma->vm_flags & VM_PFNMAP)
+		return 1;
+
+	/*
+	 * 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;
+	return 0;
+}
+
 static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 				size_t count, loff_t *ppos)
 {
@@ -842,6 +903,7 @@ 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,
 		};
@@ -861,28 +923,7 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 			}
 			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;
-			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);
@@ -1050,15 +1091,13 @@ static inline void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, struct pagemap
 static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 			     struct mm_walk *walk)
 {
-	struct vm_area_struct *vma;
+	struct vm_area_struct *vma = walk->vma;
 	struct pagemapread *pm = walk->private;
 	spinlock_t *ptl;
-	pte_t *pte;
+	pte_t *pte, *orig_pte;
 	int err = 0;
 
-	/* find the first VMA at or above 'addr' */
-	vma = find_vma(walk->mm, addr);
-	if (vma && pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
+	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
 		int pmd_flags2;
 
 		if ((vma->vm_flags & VM_SOFTDIRTY) || pmd_soft_dirty(*pmd))
@@ -1084,51 +1123,20 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	if (pmd_trans_unstable(pmd))
 		return 0;
 
-	while (1) {
-		/* End of address space hole, which we mark as non-present. */
-		unsigned long hole_end;
-
-		if (vma)
-			hole_end = min(end, vma->vm_start);
-		else
-			hole_end = end;
-
-		for (; addr < hole_end; addr += PAGE_SIZE) {
-			pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2));
-
-			err = add_to_pagemap(addr, &pme, pm);
-			if (err)
-				return err;
-		}
-
-		if (!vma || vma->vm_start >= end)
-			break;
-		/*
-		 * We can't possibly be in a hugetlb VMA. In general,
-		 * for a mm_walk with a pmd_entry and a hugetlb_entry,
-		 * the pmd_entry can only be called on addresses in a
-		 * hugetlb if the walk starts in a non-hugetlb VMA and
-		 * spans a hugepage VMA. Since pagemap_read walks are
-		 * PMD-sized and PMD-aligned, this will never be true.
-		 */
-		BUG_ON(is_vm_hugetlb_page(vma));
-
-		/* Addresses in the VMA. */
-		for (; addr < min(end, vma->vm_end); addr += PAGE_SIZE) {
-			pagemap_entry_t pme;
-			pte = pte_offset_map(pmd, addr);
-			pte_to_pagemap_entry(&pme, pm, vma, addr, *pte);
-			pte_unmap(pte);
-			err = add_to_pagemap(addr, &pme, pm);
-			if (err)
-				return err;
-		}
+	/*
+	 * We can assume that @vma always points to a valid one and @end never
+	 * goes beyond vma->vm_end.
+	 */
+	orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+	for (; addr < end; pte++, addr += PAGE_SIZE) {
+		pagemap_entry_t pme;
 
-		if (addr == end)
+		pte_to_pagemap_entry(&pme, pm, vma, addr, *pte);
+		err = add_to_pagemap(addr, &pme, pm);
+		if (err)
 			break;
-
-		vma = find_vma(walk->mm, addr);
 	}
+	pte_unmap_unlock(orig_pte, ptl);
 
 	cond_resched();
 
@@ -1154,15 +1162,12 @@ 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;
@@ -1322,7 +1327,6 @@ 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;
@@ -1391,18 +1395,17 @@ 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);
@@ -1414,7 +1417,7 @@ 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);
@@ -1424,7 +1427,7 @@ 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;
@@ -1443,7 +1446,7 @@ 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;
@@ -1461,7 +1464,12 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 	struct numa_maps *md = &numa_priv->md;
 	struct file *file = vma->vm_file;
 	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;
@@ -1472,13 +1480,6 @@ 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_hugetbl_stats;
-	walk.pmd_entry = gather_pte_stats;
-	walk.private = md;
-	walk.mm = mm;
-
 	pol = __get_vma_policy(vma, vma->vm_start);
 	if (pol) {
 		mpol_to_str(buffer, sizeof(buffer), pol);
@@ -1512,7 +1513,8 @@ 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;