5 files changed, 46 insertions, 15 deletions
diff --git a/fs/proc/fd.c b/fs/proc/fd.c
index 75f2890abbd8..0ff80f9b930f 100644
--- a/fs/proc/fd.c
+++ b/fs/proc/fd.c
@@ -230,8 +230,6 @@ static int proc_readfd_common(struct file *file, struct dir_context *ctx,
 
 	if (!dir_emit_dots(file, ctx))
 		goto out;
-	if (!dir_emit_dots(file, ctx))
-		goto out;
 	files = get_files_struct(p);
 	if (!files)
 		goto out;
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 94441a407337..737e15615b04 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -271,7 +271,7 @@ int proc_readdir_de(struct proc_dir_entry *de, struct file *file,
 		de = next;
 	} while (de);
 	spin_unlock(&proc_subdir_lock);
-	return 0;
+	return 1;
 }
 
 int proc_readdir(struct file *file, struct dir_context *ctx)
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 073aea60cf8f..9f8ef9b7674d 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -285,6 +285,20 @@ static int proc_reg_mmap(struct file *file, struct vm_area_struct *vma)
 	return rv;
 }
 
+static unsigned long proc_reg_get_unmapped_area(struct file *file, unsigned long orig_addr, unsigned long len, unsigned long pgoff, unsigned long flags)
+{
+	struct proc_dir_entry *pde = PDE(file_inode(file));
+	int rv = -EIO;
+	unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long);
+	if (use_pde(pde)) {
+		get_unmapped_area = pde->proc_fops->get_unmapped_area;
+		if (get_unmapped_area)
+			rv = get_unmapped_area(file, orig_addr, len, pgoff, flags);
+		unuse_pde(pde);
+	}
+	return rv;
+}
+
 static int proc_reg_open(struct inode *inode, struct file *file)
 {
 	struct proc_dir_entry *pde = PDE(inode);
@@ -356,6 +370,7 @@ static const struct file_operations proc_reg_file_ops = {
 	.compat_ioctl	= proc_reg_compat_ioctl,
 #endif
 	.mmap		= proc_reg_mmap,
+	.get_unmapped_area = proc_reg_get_unmapped_area,
 	.open		= proc_reg_open,
 	.release	= proc_reg_release,
 };
@@ -368,6 +383,7 @@ static const struct file_operations proc_reg_file_ops_no_compat = {
 	.poll		= proc_reg_poll,
 	.unlocked_ioctl	= proc_reg_unlocked_ioctl,
 	.mmap		= proc_reg_mmap,
+	.get_unmapped_area = proc_reg_get_unmapped_area,
 	.open		= proc_reg_open,
 	.release	= proc_reg_release,
 };
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 229e366598da..87dbcbef7fe4 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -110,7 +110,11 @@ static struct dentry *proc_mount(struct file_system_type *fs_type,
 		ns = task_active_pid_ns(current);
 		options = data;
 
-		if (!current_user_ns()->may_mount_proc)
+		if (!capable(CAP_SYS_ADMIN) && !fs_fully_visible(fs_type))
+			return ERR_PTR(-EPERM);
+
+		/* Does the mounter have privilege over the pid namespace? */
+		if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN))
 			return ERR_PTR(-EPERM);
 	}
 
@@ -205,7 +209,9 @@ static struct dentry *proc_root_lookup(struct inode * dir, struct dentry * dentr
 static int proc_root_readdir(struct file *file, struct dir_context *ctx)
 {
 	if (ctx->pos < FIRST_PROCESS_ENTRY) {
-		proc_readdir(file, ctx);
+		int error = proc_readdir(file, ctx);
+		if (unlikely(error <= 0))
+			return error;
 		ctx->pos = FIRST_PROCESS_ENTRY;
 	}
 
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index dbf61f6174f0..107d026f5d6e 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -730,8 +730,16 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma,
 	 * of how soft-dirty works.
 	 */
 	pte_t ptent = *pte;
-	ptent = pte_wrprotect(ptent);
-	ptent = pte_clear_flags(ptent, _PAGE_SOFT_DIRTY);
+
+	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
 }
@@ -752,14 +760,15 @@ 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 (!pte_present(ptent))
-			continue;
 
 		if (cp->type == CLEAR_REFS_SOFT_DIRTY) {
 			clear_soft_dirty(vma, addr, pte);
 			continue;
 		}
 
+		if (!pte_present(ptent))
+			continue;
+
 		page = vm_normal_page(vma, addr, ptent);
 		if (!page)
 			continue;
@@ -859,7 +868,7 @@ 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;
 };
@@ -867,7 +876,7 @@ struct pagemapread {
 #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)
@@ -930,8 +939,10 @@ static void pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
 		flags = PM_PRESENT;
 		page = vm_normal_page(vma, addr, pte);
 	} 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;
@@ -1116,8 +1127,8 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 		goto out_task;
 
 	pm.v2 = soft_dirty_cleared;
-	pm.len = PM_ENTRY_BYTES * (PAGEMAP_WALK_SIZE >> PAGE_SHIFT);
-	pm.buffer = kmalloc(pm.len, GFP_TEMPORARY);
+	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;