1 files changed, 206 insertions, 72 deletions

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index ca5ce7f9f80..cfa63ee92c9 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1,4 +1,5 @@
 #include <linux/mm.h>
+#include <linux/vmacache.h>
 #include <linux/hugetlb.h>
 #include <linux/huge_mm.h>
 #include <linux/mount.h>
@@ -11,6 +12,7 @@
 #include <linux/rmap.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
+#include <linux/mmu_notifier.h>
 
 #include <asm/elf.h>
 #include <asm/uaccess.h>
@@ -61,7 +63,8 @@ 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)*mm->nr_ptes) >> 10,
+		(PTRS_PER_PTE * sizeof(pte_t) *
+		 atomic_long_read(&mm->nr_ptes)) >> 10,
 		swap << (PAGE_SHIFT-10));
 }
 
@@ -82,14 +85,6 @@ unsigned long task_statm(struct mm_struct *mm,
 	return mm->total_vm;
 }
 
-static void pad_len_spaces(struct seq_file *m, int len)
-{
-	len = 25 + sizeof(void*) * 6 - len;
-	if (len < 1)
-		len = 1;
-	seq_printf(m, "%*c", len, ' ');
-}
-
 #ifdef CONFIG_NUMA
 /*
  * These functions are for numa_maps but called in generic **maps seq_file
@@ -158,7 +153,7 @@ static void *m_start(struct seq_file *m, loff_t *pos)
 
 	/*
 	 * We remember last_addr rather than next_addr to hit with
-	 * mmap_cache most of the time. We have zero last_addr at
+	 * vmacache most of the time. We have zero last_addr at
 	 * the beginning and also after lseek. We will have -1 last_addr
 	 * after the end of the vmas.
 	 */
@@ -267,11 +262,10 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
 	unsigned long long pgoff = 0;
 	unsigned long start, end;
 	dev_t dev = 0;
-	int len;
 	const char *name = NULL;
 
 	if (file) {
-		struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
+		struct inode *inode = file_inode(vma->vm_file);
 		dev = inode->i_sb->s_dev;
 		ino = inode->i_ino;
 		pgoff = ((loff_t)vma->vm_pgoff) << PAGE_SHIFT;
@@ -285,7 +279,8 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
 	if (stack_guard_page_end(vma, end))
 		end -= PAGE_SIZE;
 
-	seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu %n",
+	seq_setwidth(m, 25 + sizeof(void *) * 6 - 1);
+	seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu ",
 			start,
 			end,
 			flags & VM_READ ? 'r' : '-',
@@ -293,18 +288,24 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
 			flags & VM_EXEC ? 'x' : '-',
 			flags & VM_MAYSHARE ? 's' : 'p',
 			pgoff,
-			MAJOR(dev), MINOR(dev), ino, &len);
+			MAJOR(dev), MINOR(dev), ino);
 
 	/*
 	 * Print the dentry name for named mappings, and a
 	 * special [heap] marker for the heap:
 	 */
 	if (file) {
-		pad_len_spaces(m, len);
+		seq_pad(m, ' ');
 		seq_path(m, &file->f_path, "\n");
 		goto done;
 	}
 
+	if (vma->vm_ops && vma->vm_ops->name) {
+		name = vma->vm_ops->name(vma);
+		if (name)
+			goto done;
+	}
+
 	name = arch_vma_name(vma);
 	if (!name) {
 		pid_t tid;
@@ -332,7 +333,7 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
 				name = "[stack]";
 			} else {
 				/* Thread stack in /proc/PID/maps */
-				pad_len_spaces(m, len);
+				seq_pad(m, ' ');
 				seq_printf(m, "[stack:%d]", tid);
 			}
 		}
@@ -340,7 +341,7 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
 
 done:
 	if (name) {
-		pad_len_spaces(m, len);
+		seq_pad(m, ' ');
 		seq_puts(m, name);
 	}
 	seq_putc(m, '\n');
@@ -504,9 +505,9 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	pte_t *pte;
 	spinlock_t *ptl;
 
-	if (pmd_trans_huge_lock(pmd, vma) == 1) {
+	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
 		smaps_pte_entry(*(pte_t *)pmd, addr, HPAGE_PMD_SIZE, walk);
-		spin_unlock(&walk->mm->page_table_lock);
+		spin_unlock(ptl);
 		mss->anonymous_thp += HPAGE_PMD_SIZE;
 		return 0;
 	}
@@ -560,6 +561,9 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
 		[ilog2(VM_NONLINEAR)]	= "nl",
 		[ilog2(VM_ARCH_1)]	= "ar",
 		[ilog2(VM_DONTDUMP)]	= "dd",
+#ifdef CONFIG_MEM_SOFT_DIRTY
+		[ilog2(VM_SOFTDIRTY)]	= "sd",
+#endif
 		[ilog2(VM_MIXEDMAP)]	= "mm",
 		[ilog2(VM_HUGEPAGE)]	= "hg",
 		[ilog2(VM_NOHUGEPAGE)]	= "nh",
@@ -688,10 +692,66 @@ const struct file_operations proc_tid_smaps_operations = {
 	.release	= seq_release_private,
 };
 
+/*
+ * We do not want to have constant page-shift bits sitting in
+ * pagemap entries and are about to reuse them some time soon.
+ *
+ * Here's the "migration strategy":
+ * 1. when the system boots these bits remain what they are,
+ *    but a warning about future change is printed in log;
+ * 2. once anyone clears soft-dirty bits via clear_refs file,
+ *    these flag is set to denote, that user is aware of the
+ *    new API and those page-shift bits change their meaning.
+ *    The respective warning is printed in dmesg;
+ * 3. In a couple of releases we will remove all the mentions
+ *    of page-shift in pagemap entries.
+ */
+
+static bool soft_dirty_cleared __read_mostly;
+
+enum clear_refs_types {
+	CLEAR_REFS_ALL = 1,
+	CLEAR_REFS_ANON,
+	CLEAR_REFS_MAPPED,
+	CLEAR_REFS_SOFT_DIRTY,
+	CLEAR_REFS_LAST,
+};
+
+struct clear_refs_private {
+	struct vm_area_struct *vma;
+	enum clear_refs_types type;
+};
+
+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
+	 * Documentation/vm/soft-dirty.txt for full description
+	 * of how soft-dirty works.
+	 */
+	pte_t ptent = *pte;
+
+	if (pte_present(ptent)) {
+		ptent = pte_wrprotect(ptent);
+		ptent = pte_clear_flags(ptent, _PAGE_SOFT_DIRTY);
+	} else if (is_swap_pte(ptent)) {
+		ptent = pte_swp_clear_soft_dirty(ptent);
+	} else if (pte_file(ptent)) {
+		ptent = pte_file_clear_soft_dirty(ptent);
+	}
+
+	set_pte_at(vma->vm_mm, addr, pte, ptent);
+#endif
+}
+
 static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
 				unsigned long end, struct mm_walk *walk)
 {
-	struct vm_area_struct *vma = walk->private;
+	struct clear_refs_private *cp = walk->private;
+	struct vm_area_struct *vma = cp->vma;
 	pte_t *pte, ptent;
 	spinlock_t *ptl;
 	struct page *page;
@@ -703,6 +763,12 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	for (; addr != end; pte++, addr += PAGE_SIZE) {
 		ptent = *pte;
+
+		if (cp->type == CLEAR_REFS_SOFT_DIRTY) {
+			clear_soft_dirty(vma, addr, pte);
+			continue;
+		}
+
 		if (!pte_present(ptent))
 			continue;
 
@@ -719,10 +785,6 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
 	return 0;
 }
 
-#define CLEAR_REFS_ALL 1
-#define CLEAR_REFS_ANON 2
-#define CLEAR_REFS_MAPPED 3
-
 static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 				size_t count, loff_t *ppos)
 {
@@ -730,7 +792,8 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 	char buffer[PROC_NUMBUF];
 	struct mm_struct *mm;
 	struct vm_area_struct *vma;
-	int type;
+	enum clear_refs_types type;
+	int itype;
 	int rv;
 
 	memset(buffer, 0, sizeof(buffer));
@@ -738,23 +801,38 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 		count = sizeof(buffer) - 1;
 	if (copy_from_user(buffer, buf, count))
 		return -EFAULT;
-	rv = kstrtoint(strstrip(buffer), 10, &type);
+	rv = kstrtoint(strstrip(buffer), 10, &itype);
 	if (rv < 0)
 		return rv;
-	if (type < CLEAR_REFS_ALL || type > CLEAR_REFS_MAPPED)
+	type = (enum clear_refs_types)itype;
+	if (type < CLEAR_REFS_ALL || type >= CLEAR_REFS_LAST)
 		return -EINVAL;
-	task = get_proc_task(file->f_path.dentry->d_inode);
+
+	if (type == CLEAR_REFS_SOFT_DIRTY) {
+		soft_dirty_cleared = true;
+		pr_warn_once("The pagemap bits 55-60 has changed their meaning!"
+			     " See the linux/Documentation/vm/pagemap.txt for "
+			     "details.\n");
+	}
+
+	task = get_proc_task(file_inode(file));
 	if (!task)
 		return -ESRCH;
 	mm = get_task_mm(task);
 	if (mm) {
+		struct clear_refs_private cp = {
+			.type = type,
+		};
 		struct mm_walk clear_refs_walk = {
 			.pmd_entry = clear_refs_pte_range,
 			.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) {
-			clear_refs_walk.private = vma;
+			cp.vma = vma;
 			if (is_vm_hugetlb_page(vma))
 				continue;
 			/*
@@ -765,14 +843,22 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 			 *
 			 * 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);
 		}
+		if (type == CLEAR_REFS_SOFT_DIRTY)
+			mmu_notifier_invalidate_range_end(mm, 0, -1);
 		flush_tlb_mm(mm);
 		up_read(&mm->mmap_sem);
 		mmput(mm);
@@ -792,14 +878,15 @@ typedef struct {
 } pagemap_entry_t;
 
 struct pagemapread {
-	int pos, len;
+	int pos, len;		/* units: PM_ENTRY_BYTES, not bytes */
 	pagemap_entry_t *buffer;
+	bool v2;
 };
 
 #define PAGEMAP_WALK_SIZE	(PMD_SIZE)
 #define PAGEMAP_WALK_MASK	(PMD_MASK)
 
-#define PM_ENTRY_BYTES      sizeof(u64)
+#define PM_ENTRY_BYTES      sizeof(pagemap_entry_t)
 #define PM_STATUS_BITS      3
 #define PM_STATUS_OFFSET    (64 - PM_STATUS_BITS)
 #define PM_STATUS_MASK      (((1LL << PM_STATUS_BITS) - 1) << PM_STATUS_OFFSET)
@@ -807,14 +894,17 @@ struct pagemapread {
 #define PM_PSHIFT_BITS      6
 #define PM_PSHIFT_OFFSET    (PM_STATUS_OFFSET - PM_PSHIFT_BITS)
 #define PM_PSHIFT_MASK      (((1LL << PM_PSHIFT_BITS) - 1) << PM_PSHIFT_OFFSET)
-#define PM_PSHIFT(x)        (((u64) (x) << PM_PSHIFT_OFFSET) & PM_PSHIFT_MASK)
+#define __PM_PSHIFT(x)      (((u64) (x) << PM_PSHIFT_OFFSET) & PM_PSHIFT_MASK)
 #define PM_PFRAME_MASK      ((1LL << PM_PSHIFT_OFFSET) - 1)
 #define PM_PFRAME(x)        ((x) & PM_PFRAME_MASK)
+/* in "new" pagemap pshift bits are occupied with more status bits */
+#define PM_STATUS2(v2, x)   (__PM_PSHIFT(v2 ? x : PAGE_SHIFT))
 
+#define __PM_SOFT_DIRTY      (1LL)
 #define PM_PRESENT          PM_STATUS(4LL)
 #define PM_SWAP             PM_STATUS(2LL)
 #define PM_FILE             PM_STATUS(1LL)
-#define PM_NOT_PRESENT      PM_PSHIFT(PAGE_SHIFT)
+#define PM_NOT_PRESENT(v2)  PM_STATUS2(v2, 0)
 #define PM_END_OF_BUFFER    1
 
 static inline pagemap_entry_t make_pme(u64 val)
@@ -837,7 +927,7 @@ static int pagemap_pte_hole(unsigned long start, unsigned long end,
 	struct pagemapread *pm = walk->private;
 	unsigned long addr;
 	int err = 0;
-	pagemap_entry_t pme = make_pme(PM_NOT_PRESENT);
+	pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2));
 
 	for (addr = start; addr < end; addr += PAGE_SIZE) {
 		err = add_to_pagemap(addr, &pme, pm);
@@ -847,38 +937,47 @@ static int pagemap_pte_hole(unsigned long start, unsigned long end,
 	return err;
 }
 
-static void pte_to_pagemap_entry(pagemap_entry_t *pme,
+static void pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
 		struct vm_area_struct *vma, unsigned long addr, pte_t pte)
 {
 	u64 frame, flags;
 	struct page *page = NULL;
+	int flags2 = 0;
 
 	if (pte_present(pte)) {
 		frame = pte_pfn(pte);
 		flags = PM_PRESENT;
 		page = vm_normal_page(vma, addr, pte);
+		if (pte_soft_dirty(pte))
+			flags2 |= __PM_SOFT_DIRTY;
 	} else if (is_swap_pte(pte)) {
-		swp_entry_t entry = pte_to_swp_entry(pte);
-
+		swp_entry_t entry;
+		if (pte_swp_soft_dirty(pte))
+			flags2 |= __PM_SOFT_DIRTY;
+		entry = pte_to_swp_entry(pte);
 		frame = swp_type(entry) |
 			(swp_offset(entry) << MAX_SWAPFILES_SHIFT);
 		flags = PM_SWAP;
 		if (is_migration_entry(entry))
 			page = migration_entry_to_page(entry);
 	} else {
-		*pme = make_pme(PM_NOT_PRESENT);
+		if (vma->vm_flags & VM_SOFTDIRTY)
+			flags2 |= __PM_SOFT_DIRTY;
+		*pme = make_pme(PM_NOT_PRESENT(pm->v2) | PM_STATUS2(pm->v2, flags2));
 		return;
 	}
 
 	if (page && !PageAnon(page))
 		flags |= PM_FILE;
+	if ((vma->vm_flags & VM_SOFTDIRTY))
+		flags2 |= __PM_SOFT_DIRTY;
 
-	*pme = make_pme(PM_PFRAME(frame) | PM_PSHIFT(PAGE_SHIFT) | flags);
+	*pme = make_pme(PM_PFRAME(frame) | PM_STATUS2(pm->v2, flags2) | flags);
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-static void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme,
-					pmd_t pmd, int offset)
+static void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
+		pmd_t pmd, int offset, int pmd_flags2)
 {
 	/*
 	 * Currently pmd for thp is always present because thp can not be
@@ -887,13 +986,13 @@ static void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme,
 	 */
 	if (pmd_present(pmd))
 		*pme = make_pme(PM_PFRAME(pmd_pfn(pmd) + offset)
-				| PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT);
+				| PM_STATUS2(pm->v2, pmd_flags2) | PM_PRESENT);
 	else
-		*pme = make_pme(PM_NOT_PRESENT);
+		*pme = make_pme(PM_NOT_PRESENT(pm->v2) | PM_STATUS2(pm->v2, pmd_flags2));
 }
 #else
-static inline void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme,
-						pmd_t pmd, int offset)
+static inline void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
+		pmd_t pmd, int offset, int pmd_flags2)
 {
 }
 #endif
@@ -903,36 +1002,49 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 {
 	struct vm_area_struct *vma;
 	struct pagemapread *pm = walk->private;
+	spinlock_t *ptl;
 	pte_t *pte;
 	int err = 0;
-	pagemap_entry_t pme = make_pme(PM_NOT_PRESENT);
+	pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2));
 
 	/* find the first VMA at or above 'addr' */
 	vma = find_vma(walk->mm, addr);
-	if (vma && pmd_trans_huge_lock(pmd, vma) == 1) {
+	if (vma && pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
+		int pmd_flags2;
+
+		if ((vma->vm_flags & VM_SOFTDIRTY) || pmd_soft_dirty(*pmd))
+			pmd_flags2 = __PM_SOFT_DIRTY;
+		else
+			pmd_flags2 = 0;
+
 		for (; addr != end; addr += PAGE_SIZE) {
 			unsigned long offset;
 
 			offset = (addr & ~PAGEMAP_WALK_MASK) >>
 					PAGE_SHIFT;
-			thp_pmd_to_pagemap_entry(&pme, *pmd, offset);
+			thp_pmd_to_pagemap_entry(&pme, pm, *pmd, offset, pmd_flags2);
 			err = add_to_pagemap(addr, &pme, pm);
 			if (err)
 				break;
 		}
-		spin_unlock(&walk->mm->page_table_lock);
+		spin_unlock(ptl);
 		return err;
 	}
 
 	if (pmd_trans_unstable(pmd))
 		return 0;
 	for (; addr != end; addr += PAGE_SIZE) {
+		int flags2;
 
 		/* check to see if we've left 'vma' behind
 		 * and need a new, higher one */
 		if (vma && (addr >= vma->vm_end)) {
 			vma = find_vma(walk->mm, addr);
-			pme = make_pme(PM_NOT_PRESENT);
+			if (vma && (vma->vm_flags & VM_SOFTDIRTY))
+				flags2 = __PM_SOFT_DIRTY;
+			else
+				flags2 = 0;
+			pme = make_pme(PM_NOT_PRESENT(pm->v2) | PM_STATUS2(pm->v2, flags2));
 		}
 
 		/* check that 'vma' actually covers this address,
@@ -940,7 +1052,7 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 		if (vma && (vma->vm_start <= addr) &&
 		    !is_vm_hugetlb_page(vma)) {
 			pte = pte_offset_map(pmd, addr);
-			pte_to_pagemap_entry(&pme, vma, addr, *pte);
+			pte_to_pagemap_entry(&pme, pm, vma, addr, *pte);
 			/* unmap before userspace copy */
 			pte_unmap(pte);
 		}
@@ -955,14 +1067,16 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 }
 
 #ifdef CONFIG_HUGETLB_PAGE
-static void huge_pte_to_pagemap_entry(pagemap_entry_t *pme,
-					pte_t pte, int offset)
+static void huge_pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
+					pte_t pte, int offset, int flags2)
 {
 	if (pte_present(pte))
-		*pme = make_pme(PM_PFRAME(pte_pfn(pte) + offset)
-				| PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT);
+		*pme = make_pme(PM_PFRAME(pte_pfn(pte) + offset)	|
+				PM_STATUS2(pm->v2, flags2)		|
+				PM_PRESENT);
 	else
-		*pme = make_pme(PM_NOT_PRESENT);
+		*pme = make_pme(PM_NOT_PRESENT(pm->v2)			|
+				PM_STATUS2(pm->v2, flags2));
 }
 
 /* This function walks within one hugetlb entry in the single call */
@@ -971,12 +1085,22 @@ 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;
 	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))
+		flags2 = __PM_SOFT_DIRTY;
+	else
+		flags2 = 0;
+
 	for (; addr != end; addr += PAGE_SIZE) {
 		int offset = (addr & ~hmask) >> PAGE_SHIFT;
-		huge_pte_to_pagemap_entry(&pme, *pte, offset);
+		huge_pte_to_pagemap_entry(&pme, pm, *pte, offset, flags2);
 		err = add_to_pagemap(addr, &pme, pm);
 		if (err)
 			return err;
@@ -1015,7 +1139,7 @@ static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask,
 static ssize_t pagemap_read(struct file *file, char __user *buf,
 			    size_t count, loff_t *ppos)
 {
-	struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode);
+	struct task_struct *task = get_proc_task(file_inode(file));
 	struct mm_struct *mm;
 	struct pagemapread pm;
 	int ret = -ESRCH;
@@ -1038,8 +1162,9 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 	if (!count)
 		goto out_task;
 
-	pm.len = PM_ENTRY_BYTES * (PAGEMAP_WALK_SIZE >> PAGE_SHIFT);
-	pm.buffer = kmalloc(pm.len, GFP_TEMPORARY);
+	pm.v2 = soft_dirty_cleared;
+	pm.len = (PAGEMAP_WALK_SIZE >> PAGE_SHIFT);
+	pm.buffer = kmalloc(pm.len * PM_ENTRY_BYTES, GFP_TEMPORARY);
 	ret = -ENOMEM;
 	if (!pm.buffer)
 		goto out_task;
@@ -1110,9 +1235,18 @@ out:
 	return ret;
 }
 
+static int pagemap_open(struct inode *inode, struct file *file)
+{
+	pr_warn_once("Bits 55-60 of /proc/PID/pagemap entries are about "
+			"to stop being page-shift some time soon. See the "
+			"linux/Documentation/vm/pagemap.txt for details.\n");
+	return 0;
+}
+
 const struct file_operations proc_pagemap_operations = {
 	.llseek		= mem_lseek, /* borrow this */
 	.read		= pagemap_read,
+	.open		= pagemap_open,
 };
 #endif /* CONFIG_PROC_PAGE_MONITOR */
 
@@ -1195,7 +1329,7 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
 
 	md = walk->private;
 
-	if (pmd_trans_huge_lock(pmd, md->vma) == 1) {
+	if (pmd_trans_huge_lock(pmd, md->vma, &ptl) == 1) {
 		pte_t huge_pte = *(pte_t *)pmd;
 		struct page *page;
 
@@ -1203,7 +1337,7 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
 		if (page)
 			gather_stats(page, md, pte_dirty(huge_pte),
 				     HPAGE_PMD_SIZE/PAGE_SIZE);
-		spin_unlock(&walk->mm->page_table_lock);
+		spin_unlock(ptl);
 		return 0;
 	}
 
@@ -1227,7 +1361,7 @@ static int gather_hugetbl_stats(pte_t *pte, unsigned long hmask,
 	struct numa_maps *md;
 	struct page *page;
 
-	if (pte_none(*pte))
+	if (!pte_present(*pte))
 		return 0;
 
 	page = pte_page(*pte);
@@ -1261,8 +1395,8 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 	struct mm_struct *mm = vma->vm_mm;
 	struct mm_walk walk = {};
 	struct mempolicy *pol;
-	int n;
-	char buffer[50];
+	char buffer[64];
+	int nid;
 
 	if (!mm)
 		return 0;
@@ -1284,10 +1418,10 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 	seq_printf(m, "%08lx %s", vma->vm_start, buffer);
 
 	if (file) {
-		seq_printf(m, " file=");
+		seq_puts(m, " file=");
 		seq_path(m, &file->f_path, "\n\t= ");
 	} else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) {
-		seq_printf(m, " heap");
+		seq_puts(m, " heap");
 	} else {
 		pid_t tid = vm_is_stack(task, vma, is_pid);
 		if (tid != 0) {
@@ -1297,14 +1431,14 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 			 */
 			if (!is_pid || (vma->vm_start <= mm->start_stack &&
 			    vma->vm_end >= mm->start_stack))
-				seq_printf(m, " stack");
+				seq_puts(m, " stack");
 			else
 				seq_printf(m, " stack:%d", tid);
 		}
 	}
 
 	if (is_vm_hugetlb_page(vma))
-		seq_printf(m, " huge");
+		seq_puts(m, " huge");
 
 	walk_page_range(vma->vm_start, vma->vm_end, &walk);
 
@@ -1332,9 +1466,9 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 	if (md->writeback)
 		seq_printf(m, " writeback=%lu", md->writeback);
 
-	for_each_node_state(n, N_MEMORY)
-		if (md->node[n])
-			seq_printf(m, " N%d=%lu", n, md->node[n]);
+	for_each_node_state(nid, N_MEMORY)
+		if (md->node[nid])
+			seq_printf(m, " N%d=%lu", nid, md->node[nid]);
 out:
 	seq_putc(m, '\n');