1 files changed, 883 insertions, 175 deletions

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index da6b01d70f0..cfa63ee92c9 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1,5 +1,7 @@
 #include <linux/mm.h>
+#include <linux/vmacache.h>
 #include <linux/hugetlb.h>
+#include <linux/huge_mm.h>
 #include <linux/mount.h>
 #include <linux/seq_file.h>
 #include <linux/highmem.h>
@@ -7,8 +9,10 @@
 #include <linux/slab.h>
 #include <linux/pagemap.h>
 #include <linux/mempolicy.h>
+#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>
@@ -42,6 +46,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
 		"VmPeak:\t%8lu kB\n"
 		"VmSize:\t%8lu kB\n"
 		"VmLck:\t%8lu kB\n"
+		"VmPin:\t%8lu kB\n"
 		"VmHWM:\t%8lu kB\n"
 		"VmRSS:\t%8lu kB\n"
 		"VmData:\t%8lu kB\n"
@@ -51,13 +56,15 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
 		"VmPTE:\t%8lu kB\n"
 		"VmSwap:\t%8lu kB\n",
 		hiwater_vm << (PAGE_SHIFT-10),
-		(total_vm - mm->reserved_vm) << (PAGE_SHIFT-10),
+		total_vm << (PAGE_SHIFT-10),
 		mm->locked_vm << (PAGE_SHIFT-10),
+		mm->pinned_vm << (PAGE_SHIFT-10),
 		hiwater_rss << (PAGE_SHIFT-10),
 		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));
 }
 
@@ -66,8 +73,9 @@ unsigned long task_vsize(struct mm_struct *mm)
 	return PAGE_SIZE * mm->total_vm;
 }
 
-int task_statm(struct mm_struct *mm, int *shared, int *text,
-	       int *data, int *resident)
+unsigned long task_statm(struct mm_struct *mm,
+			 unsigned long *shared, unsigned long *text,
+			 unsigned long *data, unsigned long *resident)
 {
 	*shared = get_mm_counter(mm, MM_FILEPAGES);
 	*text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK))
@@ -77,18 +85,55 @@ int task_statm(struct mm_struct *mm, int *shared, int *text,
 	return mm->total_vm;
 }
 
-static void pad_len_spaces(struct seq_file *m, int len)
+#ifdef CONFIG_NUMA
+/*
+ * These functions are for numa_maps but called in generic **maps seq_file
+ * ->start(), ->stop() ops.
+ *
+ * numa_maps scans all vmas under mmap_sem and checks their mempolicy.
+ * Each mempolicy object is controlled by reference counting. The problem here
+ * is how to avoid accessing dead mempolicy object.
+ *
+ * Because we're holding mmap_sem while reading seq_file, it's safe to access
+ * each vma's mempolicy, no vma objects will never drop refs to mempolicy.
+ *
+ * A task's mempolicy (task->mempolicy) has different behavior. task->mempolicy
+ * is set and replaced under mmap_sem but unrefed and cleared under task_lock().
+ * So, without task_lock(), we cannot trust get_vma_policy() because we cannot
+ * gurantee the task never exits under us. But taking task_lock() around
+ * get_vma_plicy() causes lock order problem.
+ *
+ * To access task->mempolicy without lock, we hold a reference count of an
+ * object pointed by task->mempolicy and remember it. This will guarantee
+ * that task->mempolicy points to an alive object or NULL in numa_maps accesses.
+ */
+static void hold_task_mempolicy(struct proc_maps_private *priv)
+{
+	struct task_struct *task = priv->task;
+
+	task_lock(task);
+	priv->task_mempolicy = task->mempolicy;
+	mpol_get(priv->task_mempolicy);
+	task_unlock(task);
+}
+static void release_task_mempolicy(struct proc_maps_private *priv)
 {
-	len = 25 + sizeof(void*) * 6 - len;
-	if (len < 1)
-		len = 1;
-	seq_printf(m, "%*c", len, ' ');
+	mpol_put(priv->task_mempolicy);
 }
+#else
+static void hold_task_mempolicy(struct proc_maps_private *priv)
+{
+}
+static void release_task_mempolicy(struct proc_maps_private *priv)
+{
+}
+#endif
 
 static void vma_stop(struct proc_maps_private *priv, struct vm_area_struct *vma)
 {
 	if (vma && vma != priv->tail_vma) {
 		struct mm_struct *mm = vma->vm_mm;
+		release_task_mempolicy(priv);
 		up_read(&mm->mmap_sem);
 		mmput(mm);
 	}
@@ -108,7 +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.
 	 */
@@ -118,16 +163,16 @@ static void *m_start(struct seq_file *m, loff_t *pos)
 
 	priv->task = get_pid_task(priv->pid, PIDTYPE_PID);
 	if (!priv->task)
-		return NULL;
+		return ERR_PTR(-ESRCH);
 
-	mm = mm_for_maps(priv->task);
-	if (!mm)
-		return NULL;
+	mm = mm_access(priv->task, PTRACE_MODE_READ);
+	if (!mm || IS_ERR(mm))
+		return mm;
 	down_read(&mm->mmap_sem);
 
-	tail_vma = get_gate_vma(priv->task);
+	tail_vma = get_gate_vma(priv->task->mm);
 	priv->tail_vma = tail_vma;
-
+	hold_task_mempolicy(priv);
 	/* Start with last addr hint */
 	vma = find_vma(mm, last_addr);
 	if (last_addr && vma) {
@@ -154,6 +199,7 @@ out:
 	if (vma)
 		return vma;
 
+	release_task_mempolicy(priv);
 	/* End of vmas has been reached */
 	m->version = (tail_vma != NULL)? 0: -1UL;
 	up_read(&mm->mmap_sem);
@@ -179,7 +225,8 @@ static void m_stop(struct seq_file *m, void *v)
 	struct proc_maps_private *priv = m->private;
 	struct vm_area_struct *vma = v;
 
-	vma_stop(priv, vma);
+	if (!IS_ERR(vma))
+		vma_stop(priv, vma);
 	if (priv->task)
 		put_task_struct(priv->task);
 }
@@ -203,19 +250,22 @@ static int do_maps_open(struct inode *inode, struct file *file,
 	return ret;
 }
 
-static void show_map_vma(struct seq_file *m, struct vm_area_struct *vma)
+static void
+show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	struct file *file = vma->vm_file;
-	int flags = vma->vm_flags;
+	struct proc_maps_private *priv = m->private;
+	struct task_struct *task = priv->task;
+	vm_flags_t flags = vma->vm_flags;
 	unsigned long ino = 0;
 	unsigned long long pgoff = 0;
-	unsigned long start;
+	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;
@@ -223,77 +273,137 @@ static void show_map_vma(struct seq_file *m, struct vm_area_struct *vma)
 
 	/* We don't show the stack guard page in /proc/maps */
 	start = vma->vm_start;
-	if (vma->vm_flags & VM_GROWSDOWN)
-		if (!vma_stack_continue(vma->vm_prev, vma->vm_start))
-			start += PAGE_SIZE;
-
-	seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu %n",
+	if (stack_guard_page_start(vma, start))
+		start += PAGE_SIZE;
+	end = vma->vm_end;
+	if (stack_guard_page_end(vma, end))
+		end -= PAGE_SIZE;
+
+	seq_setwidth(m, 25 + sizeof(void *) * 6 - 1);
+	seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu ",
 			start,
-			vma->vm_end,
+			end,
 			flags & VM_READ ? 'r' : '-',
 			flags & VM_WRITE ? 'w' : '-',
 			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");
-	} else {
-		const char *name = arch_vma_name(vma);
-		if (!name) {
-			if (mm) {
-				if (vma->vm_start <= mm->start_brk &&
-						vma->vm_end >= mm->brk) {
-					name = "[heap]";
-				} else if (vma->vm_start <= mm->start_stack &&
-					   vma->vm_end >= mm->start_stack) {
-					name = "[stack]";
-				}
+		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;
+
+		if (!mm) {
+			name = "[vdso]";
+			goto done;
+		}
+
+		if (vma->vm_start <= mm->brk &&
+		    vma->vm_end >= mm->start_brk) {
+			name = "[heap]";
+			goto done;
+		}
+
+		tid = vm_is_stack(task, vma, is_pid);
+
+		if (tid != 0) {
+			/*
+			 * Thread stack in /proc/PID/task/TID/maps or
+			 * the main process stack.
+			 */
+			if (!is_pid || (vma->vm_start <= mm->start_stack &&
+			    vma->vm_end >= mm->start_stack)) {
+				name = "[stack]";
 			} else {
-				name = "[vdso]";
+				/* Thread stack in /proc/PID/maps */
+				seq_pad(m, ' ');
+				seq_printf(m, "[stack:%d]", tid);
 			}
 		}
-		if (name) {
-			pad_len_spaces(m, len);
-			seq_puts(m, name);
-		}
+	}
+
+done:
+	if (name) {
+		seq_pad(m, ' ');
+		seq_puts(m, name);
 	}
 	seq_putc(m, '\n');
 }
 
-static int show_map(struct seq_file *m, void *v)
+static int show_map(struct seq_file *m, void *v, int is_pid)
 {
 	struct vm_area_struct *vma = v;
 	struct proc_maps_private *priv = m->private;
 	struct task_struct *task = priv->task;
 
-	show_map_vma(m, vma);
+	show_map_vma(m, vma, is_pid);
 
 	if (m->count < m->size)  /* vma is copied successfully */
-		m->version = (vma != get_gate_vma(task))? vma->vm_start: 0;
+		m->version = (vma != get_gate_vma(task->mm))
+			? vma->vm_start : 0;
 	return 0;
 }
 
+static int show_pid_map(struct seq_file *m, void *v)
+{
+	return show_map(m, v, 1);
+}
+
+static int show_tid_map(struct seq_file *m, void *v)
+{
+	return show_map(m, v, 0);
+}
+
 static const struct seq_operations proc_pid_maps_op = {
 	.start	= m_start,
 	.next	= m_next,
 	.stop	= m_stop,
-	.show	= show_map
+	.show	= show_pid_map
 };
 
-static int maps_open(struct inode *inode, struct file *file)
+static const struct seq_operations proc_tid_maps_op = {
+	.start	= m_start,
+	.next	= m_next,
+	.stop	= m_stop,
+	.show	= show_tid_map
+};
+
+static int pid_maps_open(struct inode *inode, struct file *file)
 {
 	return do_maps_open(inode, file, &proc_pid_maps_op);
 }
 
-const struct file_operations proc_maps_operations = {
-	.open		= maps_open,
+static int tid_maps_open(struct inode *inode, struct file *file)
+{
+	return do_maps_open(inode, file, &proc_tid_maps_op);
+}
+
+const struct file_operations proc_pid_maps_operations = {
+	.open		= pid_maps_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release_private,
+};
+
+const struct file_operations proc_tid_maps_operations = {
+	.open		= tid_maps_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
 	.release	= seq_release_private,
@@ -328,64 +438,150 @@ struct mem_size_stats {
 	unsigned long private_dirty;
 	unsigned long referenced;
 	unsigned long anonymous;
+	unsigned long anonymous_thp;
 	unsigned long swap;
+	unsigned long nonlinear;
 	u64 pss;
 };
 
-static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
-			   struct mm_walk *walk)
+
+static void smaps_pte_entry(pte_t ptent, unsigned long addr,
+		unsigned long ptent_size, struct mm_walk *walk)
 {
 	struct mem_size_stats *mss = walk->private;
 	struct vm_area_struct *vma = mss->vma;
-	pte_t *pte, ptent;
-	spinlock_t *ptl;
-	struct page *page;
+	pgoff_t pgoff = linear_page_index(vma, addr);
+	struct page *page = NULL;
 	int mapcount;
 
-	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
-	for (; addr != end; pte++, addr += PAGE_SIZE) {
-		ptent = *pte;
-
-		if (is_swap_pte(ptent)) {
-			mss->swap += PAGE_SIZE;
-			continue;
-		}
+	if (pte_present(ptent)) {
+		page = vm_normal_page(vma, addr, ptent);
+	} else if (is_swap_pte(ptent)) {
+		swp_entry_t swpent = pte_to_swp_entry(ptent);
+
+		if (!non_swap_entry(swpent))
+			mss->swap += ptent_size;
+		else if (is_migration_entry(swpent))
+			page = migration_entry_to_page(swpent);
+	} else if (pte_file(ptent)) {
+		if (pte_to_pgoff(ptent) != pgoff)
+			mss->nonlinear += ptent_size;
+	}
 
-		if (!pte_present(ptent))
-			continue;
+	if (!page)
+		return;
+
+	if (PageAnon(page))
+		mss->anonymous += ptent_size;
+
+	if (page->index != pgoff)
+		mss->nonlinear += ptent_size;
+
+	mss->resident += ptent_size;
+	/* Accumulate the size in pages that have been accessed. */
+	if (pte_young(ptent) || PageReferenced(page))
+		mss->referenced += ptent_size;
+	mapcount = page_mapcount(page);
+	if (mapcount >= 2) {
+		if (pte_dirty(ptent) || PageDirty(page))
+			mss->shared_dirty += ptent_size;
+		else
+			mss->shared_clean += ptent_size;
+		mss->pss += (ptent_size << PSS_SHIFT) / mapcount;
+	} else {
+		if (pte_dirty(ptent) || PageDirty(page))
+			mss->private_dirty += ptent_size;
+		else
+			mss->private_clean += ptent_size;
+		mss->pss += (ptent_size << PSS_SHIFT);
+	}
+}
 
-		page = vm_normal_page(vma, addr, ptent);
-		if (!page)
-			continue;
+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;
+	pte_t *pte;
+	spinlock_t *ptl;
 
-		if (PageAnon(page))
-			mss->anonymous += PAGE_SIZE;
-
-		mss->resident += PAGE_SIZE;
-		/* Accumulate the size in pages that have been accessed. */
-		if (pte_young(ptent) || PageReferenced(page))
-			mss->referenced += PAGE_SIZE;
-		mapcount = page_mapcount(page);
-		if (mapcount >= 2) {
-			if (pte_dirty(ptent) || PageDirty(page))
-				mss->shared_dirty += PAGE_SIZE;
-			else
-				mss->shared_clean += PAGE_SIZE;
-			mss->pss += (PAGE_SIZE << PSS_SHIFT) / mapcount;
-		} else {
-			if (pte_dirty(ptent) || PageDirty(page))
-				mss->private_dirty += PAGE_SIZE;
-			else
-				mss->private_clean += PAGE_SIZE;
-			mss->pss += (PAGE_SIZE << PSS_SHIFT);
-		}
+	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
+		smaps_pte_entry(*(pte_t *)pmd, addr, HPAGE_PMD_SIZE, walk);
+		spin_unlock(ptl);
+		mss->anonymous_thp += HPAGE_PMD_SIZE;
+		return 0;
 	}
+
+	if (pmd_trans_unstable(pmd))
+		return 0;
+	/*
+	 * The mmap_sem held all the way back in m_start() is what
+	 * keeps khugepaged out of here and from collapsing things
+	 * in here.
+	 */
+	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+	for (; addr != end; pte++, addr += PAGE_SIZE)
+		smaps_pte_entry(*pte, addr, PAGE_SIZE, walk);
 	pte_unmap_unlock(pte - 1, ptl);
 	cond_resched();
 	return 0;
 }
 
-static int show_smap(struct seq_file *m, void *v)
+static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
+{
+	/*
+	 * Don't forget to update Documentation/ on changes.
+	 */
+	static const char mnemonics[BITS_PER_LONG][2] = {
+		/*
+		 * In case if we meet a flag we don't know about.
+		 */
+		[0 ... (BITS_PER_LONG-1)] = "??",
+
+		[ilog2(VM_READ)]	= "rd",
+		[ilog2(VM_WRITE)]	= "wr",
+		[ilog2(VM_EXEC)]	= "ex",
+		[ilog2(VM_SHARED)]	= "sh",
+		[ilog2(VM_MAYREAD)]	= "mr",
+		[ilog2(VM_MAYWRITE)]	= "mw",
+		[ilog2(VM_MAYEXEC)]	= "me",
+		[ilog2(VM_MAYSHARE)]	= "ms",
+		[ilog2(VM_GROWSDOWN)]	= "gd",
+		[ilog2(VM_PFNMAP)]	= "pf",
+		[ilog2(VM_DENYWRITE)]	= "dw",
+		[ilog2(VM_LOCKED)]	= "lo",
+		[ilog2(VM_IO)]		= "io",
+		[ilog2(VM_SEQ_READ)]	= "sr",
+		[ilog2(VM_RAND_READ)]	= "rr",
+		[ilog2(VM_DONTCOPY)]	= "dc",
+		[ilog2(VM_DONTEXPAND)]	= "de",
+		[ilog2(VM_ACCOUNT)]	= "ac",
+		[ilog2(VM_NORESERVE)]	= "nr",
+		[ilog2(VM_HUGETLB)]	= "ht",
+		[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",
+		[ilog2(VM_MERGEABLE)]	= "mg",
+	};
+	size_t i;
+
+	seq_puts(m, "VmFlags: ");
+	for (i = 0; i < BITS_PER_LONG; i++) {
+		if (vma->vm_flags & (1UL << i)) {
+			seq_printf(m, "%c%c ",
+				   mnemonics[i][0], mnemonics[i][1]);
+		}
+	}
+	seq_putc(m, '\n');
+}
+
+static int show_smap(struct seq_file *m, void *v, int is_pid)
 {
 	struct proc_maps_private *priv = m->private;
 	struct task_struct *task = priv->task;
@@ -403,7 +599,7 @@ static int show_smap(struct seq_file *m, void *v)
 	if (vma->vm_mm && !is_vm_hugetlb_page(vma))
 		walk_page_range(vma->vm_start, vma->vm_end, &smaps_walk);
 
-	show_map_vma(m, vma);
+	show_map_vma(m, vma, is_pid);
 
 	seq_printf(m,
 		   "Size:           %8lu kB\n"
@@ -415,9 +611,11 @@ static int show_smap(struct seq_file *m, void *v)
 		   "Private_Dirty:  %8lu kB\n"
 		   "Referenced:     %8lu kB\n"
 		   "Anonymous:      %8lu kB\n"
+		   "AnonHugePages:  %8lu kB\n"
 		   "Swap:           %8lu kB\n"
 		   "KernelPageSize: %8lu kB\n"
-		   "MMUPageSize:    %8lu kB\n",
+		   "MMUPageSize:    %8lu kB\n"
+		   "Locked:         %8lu kB\n",
 		   (vma->vm_end - vma->vm_start) >> 10,
 		   mss.resident >> 10,
 		   (unsigned long)(mss.pss >> (10 + PSS_SHIFT)),
@@ -427,45 +625,150 @@ static int show_smap(struct seq_file *m, void *v)
 		   mss.private_dirty >> 10,
 		   mss.referenced >> 10,
 		   mss.anonymous >> 10,
+		   mss.anonymous_thp >> 10,
 		   mss.swap >> 10,
 		   vma_kernel_pagesize(vma) >> 10,
-		   vma_mmu_pagesize(vma) >> 10);
+		   vma_mmu_pagesize(vma) >> 10,
+		   (vma->vm_flags & VM_LOCKED) ?
+			(unsigned long)(mss.pss >> (10 + PSS_SHIFT)) : 0);
+
+	if (vma->vm_flags & VM_NONLINEAR)
+		seq_printf(m, "Nonlinear:      %8lu kB\n",
+				mss.nonlinear >> 10);
+
+	show_smap_vma_flags(m, vma);
 
 	if (m->count < m->size)  /* vma is copied successfully */
-		m->version = (vma != get_gate_vma(task)) ? vma->vm_start : 0;
+		m->version = (vma != get_gate_vma(task->mm))
+			? vma->vm_start : 0;
 	return 0;
 }
 
+static int show_pid_smap(struct seq_file *m, void *v)
+{
+	return show_smap(m, v, 1);
+}
+
+static int show_tid_smap(struct seq_file *m, void *v)
+{
+	return show_smap(m, v, 0);
+}
+
 static const struct seq_operations proc_pid_smaps_op = {
 	.start	= m_start,
 	.next	= m_next,
 	.stop	= m_stop,
-	.show	= show_smap
+	.show	= show_pid_smap
+};
+
+static const struct seq_operations proc_tid_smaps_op = {
+	.start	= m_start,
+	.next	= m_next,
+	.stop	= m_stop,
+	.show	= show_tid_smap
 };
 
-static int smaps_open(struct inode *inode, struct file *file)
+static int pid_smaps_open(struct inode *inode, struct file *file)
 {
 	return do_maps_open(inode, file, &proc_pid_smaps_op);
 }
 
-const struct file_operations proc_smaps_operations = {
-	.open		= smaps_open,
+static int tid_smaps_open(struct inode *inode, struct file *file)
+{
+	return do_maps_open(inode, file, &proc_tid_smaps_op);
+}
+
+const struct file_operations proc_pid_smaps_operations = {
+	.open		= pid_smaps_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release_private,
+};
+
+const struct file_operations proc_tid_smaps_operations = {
+	.open		= tid_smaps_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
 	.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;
 
+	split_huge_page_pmd(vma, addr, pmd);
+	if (pmd_trans_unstable(pmd))
+		return 0;
+
 	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;
 
@@ -482,10 +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)
 {
@@ -493,29 +792,47 @@ 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;
-	long type;
+	enum clear_refs_types type;
+	int itype;
+	int rv;
 
 	memset(buffer, 0, sizeof(buffer));
 	if (count > sizeof(buffer) - 1)
 		count = sizeof(buffer) - 1;
 	if (copy_from_user(buffer, buf, count))
 		return -EFAULT;
-	if (strict_strtol(strstrip(buffer), 10, &type))
-		return -EINVAL;
-	if (type < CLEAR_REFS_ALL || type > CLEAR_REFS_MAPPED)
+	rv = kstrtoint(strstrip(buffer), 10, &itype);
+	if (rv < 0)
+		return rv;
+	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;
 			/*
@@ -526,14 +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);
@@ -548,12 +873,20 @@ const struct file_operations proc_clear_refs_operations = {
 	.llseek		= noop_llseek,
 };
 
+typedef struct {
+	u64 pme;
+} pagemap_entry_t;
+
 struct pagemapread {
-	int pos, len;
-	u64 *buffer;
+	int pos, len;		/* units: PM_ENTRY_BYTES, not bytes */
+	pagemap_entry_t *buffer;
+	bool v2;
 };
 
-#define PM_ENTRY_BYTES      sizeof(u64)
+#define PAGEMAP_WALK_SIZE	(PMD_SIZE)
+#define PAGEMAP_WALK_MASK	(PMD_MASK)
+
+#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)
@@ -561,19 +894,28 @@ 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_NOT_PRESENT      PM_PSHIFT(PAGE_SHIFT)
+#define PM_FILE             PM_STATUS(1LL)
+#define PM_NOT_PRESENT(v2)  PM_STATUS2(v2, 0)
 #define PM_END_OF_BUFFER    1
 
-static int add_to_pagemap(unsigned long addr, u64 pfn,
+static inline pagemap_entry_t make_pme(u64 val)
+{
+	return (pagemap_entry_t) { .pme = val };
+}
+
+static int add_to_pagemap(unsigned long addr, pagemap_entry_t *pme,
 			  struct pagemapread *pm)
 {
-	pm->buffer[pm->pos++] = pfn;
+	pm->buffer[pm->pos++] = *pme;
 	if (pm->pos >= pm->len)
 		return PM_END_OF_BUFFER;
 	return 0;
@@ -585,60 +927,136 @@ 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(pm->v2));
+
 	for (addr = start; addr < end; addr += PAGE_SIZE) {
-		err = add_to_pagemap(addr, PM_NOT_PRESENT, pm);
+		err = add_to_pagemap(addr, &pme, pm);
 		if (err)
 			break;
 	}
 	return err;
 }
 
-static u64 swap_pte_to_pagemap_entry(pte_t pte)
+static void pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
+		struct vm_area_struct *vma, unsigned long addr, pte_t pte)
 {
-	swp_entry_t e = pte_to_swp_entry(pte);
-	return swp_type(e) | (swp_offset(e) << MAX_SWAPFILES_SHIFT);
+	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;
+		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 {
+		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_STATUS2(pm->v2, flags2) | flags);
 }
 
-static u64 pte_to_pagemap_entry(pte_t pte)
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+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
+	 * swapped-out, migrated, or HWPOISONed (split in such cases instead.)
+	 * This if-check is just to prepare for future implementation.
+	 */
+	if (pmd_present(pmd))
+		*pme = make_pme(PM_PFRAME(pmd_pfn(pmd) + offset)
+				| PM_STATUS2(pm->v2, pmd_flags2) | PM_PRESENT);
+	else
+		*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, struct pagemapread *pm,
+		pmd_t pmd, int offset, int pmd_flags2)
 {
-	u64 pme = 0;
-	if (is_swap_pte(pte))
-		pme = PM_PFRAME(swap_pte_to_pagemap_entry(pte))
-			| PM_PSHIFT(PAGE_SHIFT) | PM_SWAP;
-	else if (pte_present(pte))
-		pme = PM_PFRAME(pte_pfn(pte))
-			| PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT;
-	return pme;
 }
+#endif
 
 static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 			     struct mm_walk *walk)
 {
 	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(pm->v2));
 
 	/* find the first VMA at or above 'addr' */
 	vma = find_vma(walk->mm, addr);
+	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, pm, *pmd, offset, pmd_flags2);
+			err = add_to_pagemap(addr, &pme, pm);
+			if (err)
+				break;
+		}
+		spin_unlock(ptl);
+		return err;
+	}
+
+	if (pmd_trans_unstable(pmd))
+		return 0;
 	for (; addr != end; addr += PAGE_SIZE) {
-		u64 pfn = PM_NOT_PRESENT;
+		int flags2;
 
 		/* check to see if we've left 'vma' behind
 		 * and need a new, higher one */
-		if (vma && (addr >= vma->vm_end))
+		if (vma && (addr >= vma->vm_end)) {
 			vma = find_vma(walk->mm, addr);
+			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,
 		 * and that it isn't a huge page vma */
 		if (vma && (vma->vm_start <= addr) &&
 		    !is_vm_hugetlb_page(vma)) {
 			pte = pte_offset_map(pmd, addr);
-			pfn = pte_to_pagemap_entry(*pte);
+			pte_to_pagemap_entry(&pme, pm, vma, addr, *pte);
 			/* unmap before userspace copy */
 			pte_unmap(pte);
 		}
-		err = add_to_pagemap(addr, pfn, pm);
+		err = add_to_pagemap(addr, &pme, pm);
 		if (err)
 			return err;
 	}
@@ -649,13 +1067,16 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 }
 
 #ifdef CONFIG_HUGETLB_PAGE
-static u64 huge_pte_to_pagemap_entry(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)
 {
-	u64 pme = 0;
 	if (pte_present(pte))
-		pme = PM_PFRAME(pte_pfn(pte) + offset)
-			| PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT;
-	return pme;
+		*pme = make_pme(PM_PFRAME(pte_pfn(pte) + offset)	|
+				PM_STATUS2(pm->v2, flags2)		|
+				PM_PRESENT);
+	else
+		*pme = make_pme(PM_NOT_PRESENT(pm->v2)			|
+				PM_STATUS2(pm->v2, flags2));
 }
 
 /* This function walks within one hugetlb entry in the single call */
@@ -664,13 +1085,23 @@ 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;
-	u64 pfn;
+	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;
-		pfn = huge_pte_to_pagemap_entry(*pte, offset);
-		err = add_to_pagemap(addr, pfn, pm);
+		huge_pte_to_pagemap_entry(&pme, pm, *pte, offset, flags2);
+		err = add_to_pagemap(addr, &pme, pm);
 		if (err)
 			return err;
 	}
@@ -687,11 +1118,11 @@ static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask,
  * For each page in the address space, this file contains one 64-bit entry
  * consisting of the following:
  *
- * Bits 0-55  page frame number (PFN) if present
+ * Bits 0-54  page frame number (PFN) if present
  * Bits 0-4   swap type if swapped
- * Bits 5-55  swap offset if swapped
+ * Bits 5-54  swap offset if swapped
  * Bits 55-60 page shift (page size = 1<<page shift)
- * Bit  61    reserved for future use
+ * Bit  61    page is file-page or shared-anon
  * Bit  62    page swapped
  * Bit  63    page present
  *
@@ -705,11 +1136,10 @@ static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask,
  * determine which areas of memory are actually mapped and llseek to
  * skip over unmapped regions.
  */
-#define PAGEMAP_WALK_SIZE	(PMD_SIZE)
 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;
@@ -723,29 +1153,26 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 	if (!task)
 		goto out;
 
-	ret = -EACCES;
-	if (!ptrace_may_access(task, PTRACE_MODE_READ))
-		goto out_task;
-
 	ret = -EINVAL;
 	/* file position must be aligned */
 	if ((*ppos % PM_ENTRY_BYTES) || (count % PM_ENTRY_BYTES))
 		goto out_task;
 
 	ret = 0;
-
 	if (!count)
 		goto out_task;
 
-	mm = get_task_mm(task);
-	if (!mm)
-		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_mm;
+		goto out_task;
+
+	mm = mm_access(task, PTRACE_MODE_READ);
+	ret = PTR_ERR(mm);
+	if (!mm || IS_ERR(mm))
+		goto out_free;
 
 	pagemap_walk.pmd_entry = pagemap_pte_range;
 	pagemap_walk.pte_hole = pagemap_pte_hole;
@@ -776,7 +1203,7 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 		unsigned long end;
 
 		pm.pos = 0;
-		end = start_vaddr + PAGEMAP_WALK_SIZE;
+		end = (start_vaddr + PAGEMAP_WALK_SIZE) & PAGEMAP_WALK_MASK;
 		/* overflow ? */
 		if (end < start_vaddr || end > end_vaddr)
 			end = end_vaddr;
@@ -788,7 +1215,7 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 		len = min(count, PM_ENTRY_BYTES * pm.pos);
 		if (copy_to_user(buf, pm.buffer, len)) {
 			ret = -EFAULT;
-			goto out_free;
+			goto out_mm;
 		}
 		copied += len;
 		buf += len;
@@ -798,41 +1225,322 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 	if (!ret || ret == PM_END_OF_BUFFER)
 		ret = copied;
 
-out_free:
-	kfree(pm.buffer);
 out_mm:
 	mmput(mm);
+out_free:
+	kfree(pm.buffer);
 out_task:
 	put_task_struct(task);
 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 */
 
 #ifdef CONFIG_NUMA
-extern int show_numa_map(struct seq_file *m, void *v);
+
+struct numa_maps {
+	struct vm_area_struct *vma;
+	unsigned long pages;
+	unsigned long anon;
+	unsigned long active;
+	unsigned long writeback;
+	unsigned long mapcount_max;
+	unsigned long dirty;
+	unsigned long swapcache;
+	unsigned long node[MAX_NUMNODES];
+};
+
+struct numa_maps_private {
+	struct proc_maps_private proc_maps;
+	struct numa_maps md;
+};
+
+static void gather_stats(struct page *page, struct numa_maps *md, int pte_dirty,
+			unsigned long nr_pages)
+{
+	int count = page_mapcount(page);
+
+	md->pages += nr_pages;
+	if (pte_dirty || PageDirty(page))
+		md->dirty += nr_pages;
+
+	if (PageSwapCache(page))
+		md->swapcache += nr_pages;
+
+	if (PageActive(page) || PageUnevictable(page))
+		md->active += nr_pages;
+
+	if (PageWriteback(page))
+		md->writeback += nr_pages;
+
+	if (PageAnon(page))
+		md->anon += nr_pages;
+
+	if (count > md->mapcount_max)
+		md->mapcount_max = count;
+
+	md->node[page_to_nid(page)] += nr_pages;
+}
+
+static struct page *can_gather_numa_stats(pte_t pte, struct vm_area_struct *vma,
+		unsigned long addr)
+{
+	struct page *page;
+	int nid;
+
+	if (!pte_present(pte))
+		return NULL;
+
+	page = vm_normal_page(vma, addr, pte);
+	if (!page)
+		return NULL;
+
+	if (PageReserved(page))
+		return NULL;
+
+	nid = page_to_nid(page);
+	if (!node_isset(nid, node_states[N_MEMORY]))
+		return NULL;
+
+	return page;
+}
+
+static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
+		unsigned long end, struct mm_walk *walk)
+{
+	struct numa_maps *md;
+	spinlock_t *ptl;
+	pte_t *orig_pte;
+	pte_t *pte;
+
+	md = walk->private;
+
+	if (pmd_trans_huge_lock(pmd, md->vma, &ptl) == 1) {
+		pte_t huge_pte = *(pte_t *)pmd;
+		struct page *page;
+
+		page = can_gather_numa_stats(huge_pte, md->vma, addr);
+		if (page)
+			gather_stats(page, md, pte_dirty(huge_pte),
+				     HPAGE_PMD_SIZE/PAGE_SIZE);
+		spin_unlock(ptl);
+		return 0;
+	}
+
+	if (pmd_trans_unstable(pmd))
+		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);
+		if (!page)
+			continue;
+		gather_stats(page, md, pte_dirty(*pte), 1);
+
+	} while (pte++, addr += PAGE_SIZE, addr != end);
+	pte_unmap_unlock(orig_pte, ptl);
+	return 0;
+}
+#ifdef CONFIG_HUGETLB_PAGE
+static int gather_hugetbl_stats(pte_t *pte, unsigned long hmask,
+		unsigned long addr, unsigned long end, struct mm_walk *walk)
+{
+	struct numa_maps *md;
+	struct page *page;
+
+	if (!pte_present(*pte))
+		return 0;
+
+	page = pte_page(*pte);
+	if (!page)
+		return 0;
+
+	md = walk->private;
+	gather_stats(page, md, pte_dirty(*pte), 1);
+	return 0;
+}
+
+#else
+static int gather_hugetbl_stats(pte_t *pte, unsigned long hmask,
+		unsigned long addr, unsigned long end, struct mm_walk *walk)
+{
+	return 0;
+}
+#endif
+
+/*
+ * Display pages allocated per node and memory policy via /proc.
+ */
+static int show_numa_map(struct seq_file *m, void *v, int is_pid)
+{
+	struct numa_maps_private *numa_priv = m->private;
+	struct proc_maps_private *proc_priv = &numa_priv->proc_maps;
+	struct vm_area_struct *vma = v;
+	struct numa_maps *md = &numa_priv->md;
+	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 mempolicy *pol;
+	char buffer[64];
+	int nid;
+
+	if (!mm)
+		return 0;
+
+	/* 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(task, vma, vma->vm_start);
+	mpol_to_str(buffer, sizeof(buffer), pol);
+	mpol_cond_put(pol);
+
+	seq_printf(m, "%08lx %s", vma->vm_start, buffer);
+
+	if (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_puts(m, " heap");
+	} else {
+		pid_t tid = vm_is_stack(task, vma, is_pid);
+		if (tid != 0) {
+			/*
+			 * Thread stack in /proc/PID/task/TID/maps or
+			 * the main process stack.
+			 */
+			if (!is_pid || (vma->vm_start <= mm->start_stack &&
+			    vma->vm_end >= mm->start_stack))
+				seq_puts(m, " stack");
+			else
+				seq_printf(m, " stack:%d", tid);
+		}
+	}
+
+	if (is_vm_hugetlb_page(vma))
+		seq_puts(m, " huge");
+
+	walk_page_range(vma->vm_start, vma->vm_end, &walk);
+
+	if (!md->pages)
+		goto out;
+
+	if (md->anon)
+		seq_printf(m, " anon=%lu", md->anon);
+
+	if (md->dirty)
+		seq_printf(m, " dirty=%lu", md->dirty);
+
+	if (md->pages != md->anon && md->pages != md->dirty)
+		seq_printf(m, " mapped=%lu", md->pages);
+
+	if (md->mapcount_max > 1)
+		seq_printf(m, " mapmax=%lu", md->mapcount_max);
+
+	if (md->swapcache)
+		seq_printf(m, " swapcache=%lu", md->swapcache);
+
+	if (md->active < md->pages && !is_vm_hugetlb_page(vma))
+		seq_printf(m, " active=%lu", md->active);
+
+	if (md->writeback)
+		seq_printf(m, " writeback=%lu", md->writeback);
+
+	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');
+
+	if (m->count < m->size)
+		m->version = (vma != proc_priv->tail_vma) ? vma->vm_start : 0;
+	return 0;
+}
+
+static int show_pid_numa_map(struct seq_file *m, void *v)
+{
+	return show_numa_map(m, v, 1);
+}
+
+static int show_tid_numa_map(struct seq_file *m, void *v)
+{
+	return show_numa_map(m, v, 0);
+}
 
 static const struct seq_operations proc_pid_numa_maps_op = {
-        .start  = m_start,
-        .next   = m_next,
-        .stop   = m_stop,
-        .show   = show_numa_map,
+	.start  = m_start,
+	.next   = m_next,
+	.stop   = m_stop,
+	.show   = show_pid_numa_map,
+};
+
+static const struct seq_operations proc_tid_numa_maps_op = {
+	.start  = m_start,
+	.next   = m_next,
+	.stop   = m_stop,
+	.show   = show_tid_numa_map,
 };
 
-static int numa_maps_open(struct inode *inode, struct file *file)
+static int numa_maps_open(struct inode *inode, struct file *file,
+			  const struct seq_operations *ops)
 {
-	return do_maps_open(inode, file, &proc_pid_numa_maps_op);
+	struct numa_maps_private *priv;
+	int ret = -ENOMEM;
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (priv) {
+		priv->proc_maps.pid = proc_pid(inode);
+		ret = seq_open(file, ops);
+		if (!ret) {
+			struct seq_file *m = file->private_data;
+			m->private = priv;
+		} else {
+			kfree(priv);
+		}
+	}
+	return ret;
+}
+
+static int pid_numa_maps_open(struct inode *inode, struct file *file)
+{
+	return numa_maps_open(inode, file, &proc_pid_numa_maps_op);
 }
 
-const struct file_operations proc_numa_maps_operations = {
-	.open		= numa_maps_open,
+static int tid_numa_maps_open(struct inode *inode, struct file *file)
+{
+	return numa_maps_open(inode, file, &proc_tid_numa_maps_op);
+}
+
+const struct file_operations proc_pid_numa_maps_operations = {
+	.open		= pid_numa_maps_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
 	.release	= seq_release_private,
 };
-#endif
+
+const struct file_operations proc_tid_numa_maps_operations = {
+	.open		= tid_numa_maps_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release_private,
+};
+#endif /* CONFIG_NUMA */