1 files changed, 85 insertions, 50 deletions

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 60b914860f81..7c708a418acc 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1,5 +1,6 @@
 #include <linux/mm.h>
 #include <linux/hugetlb.h>
+#include <linux/huge_mm.h>
 #include <linux/mount.h>
 #include <linux/seq_file.h>
 #include <linux/highmem.h>
@@ -7,6 +8,7 @@
 #include <linux/slab.h>
 #include <linux/pagemap.h>
 #include <linux/mempolicy.h>
+#include <linux/rmap.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
 
@@ -119,14 +121,14 @@ 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;
+	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;
 
 	/* Start with last addr hint */
@@ -249,8 +251,8 @@ static void show_map_vma(struct seq_file *m, struct vm_area_struct *vma)
 		const char *name = arch_vma_name(vma);
 		if (!name) {
 			if (mm) {
-				if (vma->vm_start <= mm->start_brk &&
-						vma->vm_end >= mm->brk) {
+				if (vma->vm_start <= mm->brk &&
+						vma->vm_end >= mm->start_brk) {
 					name = "[heap]";
 				} else if (vma->vm_start <= mm->start_stack &&
 					   vma->vm_end >= mm->start_stack) {
@@ -277,7 +279,8 @@ static int show_map(struct seq_file *m, void *v)
 	show_map_vma(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;
 }
 
@@ -329,58 +332,86 @@ struct mem_size_stats {
 	unsigned long private_dirty;
 	unsigned long referenced;
 	unsigned long anonymous;
+	unsigned long anonymous_thp;
 	unsigned long swap;
 	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;
 	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 (is_swap_pte(ptent)) {
+		mss->swap += ptent_size;
+		return;
+	}
 
-		if (!pte_present(ptent))
-			continue;
+	if (!pte_present(ptent))
+		return;
+
+	page = vm_normal_page(vma, addr, ptent);
+	if (!page)
+		return;
+
+	if (PageAnon(page))
+		mss->anonymous += 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;
+	spin_lock(&walk->mm->page_table_lock);
+	if (pmd_trans_huge(*pmd)) {
+		if (pmd_trans_splitting(*pmd)) {
+			spin_unlock(&walk->mm->page_table_lock);
+			wait_split_huge_page(vma->anon_vma, pmd);
 		} else {
-			if (pte_dirty(ptent) || PageDirty(page))
-				mss->private_dirty += PAGE_SIZE;
-			else
-				mss->private_clean += PAGE_SIZE;
-			mss->pss += (PAGE_SIZE << PSS_SHIFT);
+			smaps_pte_entry(*(pte_t *)pmd, addr,
+					HPAGE_PMD_SIZE, walk);
+			spin_unlock(&walk->mm->page_table_lock);
+			mss->anonymous_thp += HPAGE_PMD_SIZE;
+			return 0;
 		}
+	} else {
+		spin_unlock(&walk->mm->page_table_lock);
 	}
+	/*
+	 * 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;
@@ -416,6 +447,7 @@ 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"
@@ -429,6 +461,7 @@ 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,
@@ -436,7 +469,8 @@ static int show_smap(struct seq_file *m, void *v)
 			(unsigned long)(mss.pss >> (10 + PSS_SHIFT)) : 0);
 
 	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;
 }
 
@@ -467,6 +501,8 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
 	spinlock_t *ptl;
 	struct page *page;
 
+	split_huge_page_pmd(walk->mm, pmd);
+
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	for (; addr != end; pte++, addr += PAGE_SIZE) {
 		ptent = *pte;
@@ -623,6 +659,8 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	pte_t *pte;
 	int err = 0;
 
+	split_huge_page_pmd(walk->mm, pmd);
+
 	/* find the first VMA at or above 'addr' */
 	vma = find_vma(walk->mm, addr);
 	for (; addr != end; addr += PAGE_SIZE) {
@@ -728,8 +766,9 @@ 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))
+	mm = mm_for_maps(task);
+	ret = PTR_ERR(mm);
+	if (!mm || IS_ERR(mm))
 		goto out_task;
 
 	ret = -EINVAL;
@@ -742,10 +781,6 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 	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);
 	ret = -ENOMEM;