1 files changed, 307 insertions, 70 deletions

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 60b914860f81..25b6a887adb9 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 */
@@ -180,7 +182,8 @@ 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);
 }
@@ -208,10 +211,10 @@ static void show_map_vma(struct seq_file *m, struct vm_area_struct *vma)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	struct file *file = vma->vm_file;
-	int flags = vma->vm_flags;
+	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;
 
@@ -224,13 +227,15 @@ 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;
+	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_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu %n",
 			start,
-			vma->vm_end,
+			end,
 			flags & VM_READ ? 'r' : '-',
 			flags & VM_WRITE ? 'w' : '-',
 			flags & VM_EXEC ? 'x' : '-',
@@ -249,8 +254,8 @@ 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 +282,8 @@ 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 +335,86 @@ 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 +450,7 @@ 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 +464,7 @@ 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 +472,8 @@ 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 +504,8 @@ 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;
@@ -497,15 +536,17 @@ 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;
+	int type;
+	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;
+	rv = kstrtoint(strstrip(buffer), 10, &type);
+	if (rv < 0)
+		return rv;
 	if (type < CLEAR_REFS_ALL || type > CLEAR_REFS_MAPPED)
 		return -EINVAL;
 	task = get_proc_task(file->f_path.dentry->d_inode);
@@ -623,6 +664,8 @@ 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) {
@@ -728,29 +771,25 @@ 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);
 	ret = -ENOMEM;
 	if (!pm.buffer)
-		goto out_mm;
+		goto out_task;
+
+	mm = mm_for_maps(task);
+	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;
@@ -793,7 +832,7 @@ 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;
@@ -803,10 +842,10 @@ 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:
@@ -820,7 +859,192 @@ const struct file_operations proc_pagemap_operations = {
 #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)
+{
+	int count = page_mapcount(page);
+
+	md->pages++;
+	if (pte_dirty || PageDirty(page))
+		md->dirty++;
+
+	if (PageSwapCache(page))
+		md->swapcache++;
+
+	if (PageActive(page) || PageUnevictable(page))
+		md->active++;
+
+	if (PageWriteback(page))
+		md->writeback++;
+
+	if (PageAnon(page))
+		md->anon++;
+
+	if (count > md->mapcount_max)
+		md->mapcount_max = count;
+
+	md->node[page_to_nid(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;
+	orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+	do {
+		struct page *page;
+		int nid;
+
+		if (!pte_present(*pte))
+			continue;
+
+		page = vm_normal_page(md->vma, addr, *pte);
+		if (!page)
+			continue;
+
+		if (PageReserved(page))
+			continue;
+
+		nid = page_to_nid(page);
+		if (!node_isset(nid, node_states[N_HIGH_MEMORY]))
+			continue;
+
+		gather_stats(page, md, pte_dirty(*pte));
+
+	} 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_none(*pte))
+		return 0;
+
+	page = pte_page(*pte);
+	if (!page)
+		return 0;
+
+	md = walk->private;
+	gather_stats(page, md, pte_dirty(*pte));
+	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)
+{
+	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 mm_struct *mm = vma->vm_mm;
+	struct mm_walk walk = {};
+	struct mempolicy *pol;
+	int n;
+	char buffer[50];
+
+	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(proc_priv->task, vma, vma->vm_start);
+	mpol_to_str(buffer, sizeof(buffer), pol, 0);
+	mpol_cond_put(pol);
+
+	seq_printf(m, "%08lx %s", vma->vm_start, buffer);
+
+	if (file) {
+		seq_printf(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");
+	} else if (vma->vm_start <= mm->start_stack &&
+			vma->vm_end >= mm->start_stack) {
+		seq_printf(m, " stack");
+	}
+
+	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(n, N_HIGH_MEMORY)
+		if (md->node[n])
+			seq_printf(m, " N%d=%lu", n, md->node[n]);
+out:
+	seq_putc(m, '\n');
+
+	if (m->count < m->size)
+		m->version = (vma != proc_priv->tail_vma) ? vma->vm_start : 0;
+	return 0;
+}
 
 static const struct seq_operations proc_pid_numa_maps_op = {
         .start  = m_start,
@@ -831,7 +1055,20 @@ static const struct seq_operations proc_pid_numa_maps_op = {
 
 static int numa_maps_open(struct inode *inode, struct file *file)
 {
-	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, &proc_pid_numa_maps_op);
+		if (!ret) {
+			struct seq_file *m = file->private_data;
+			m->private = priv;
+		} else {
+			kfree(priv);
+		}
+	}
+	return ret;
 }
 
 const struct file_operations proc_numa_maps_operations = {
@@ -840,4 +1077,4 @@ const struct file_operations proc_numa_maps_operations = {
 	.llseek		= seq_lseek,
 	.release	= seq_release_private,
 };
-#endif
+#endif /* CONFIG_NUMA */