1 files changed, 81 insertions, 9 deletions

diff --git a/mm/mmap.c b/mm/mmap.c
index ed70a68e882a..ee2298936fe6 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1043,6 +1043,46 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 }
 EXPORT_SYMBOL(do_mmap_pgoff);
 
+SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
+		unsigned long, prot, unsigned long, flags,
+		unsigned long, fd, unsigned long, pgoff)
+{
+	struct file *file = NULL;
+	unsigned long retval = -EBADF;
+
+	if (!(flags & MAP_ANONYMOUS)) {
+		if (unlikely(flags & MAP_HUGETLB))
+			return -EINVAL;
+		file = fget(fd);
+		if (!file)
+			goto out;
+	} else if (flags & MAP_HUGETLB) {
+		struct user_struct *user = NULL;
+		/*
+		 * VM_NORESERVE is used because the reservations will be
+		 * taken when vm_ops->mmap() is called
+		 * A dummy user value is used because we are not locking
+		 * memory so no accounting is necessary
+		 */
+		len = ALIGN(len, huge_page_size(&default_hstate));
+		file = hugetlb_file_setup(HUGETLB_ANON_FILE, len, VM_NORESERVE,
+						&user, HUGETLB_ANONHUGE_INODE);
+		if (IS_ERR(file))
+			return PTR_ERR(file);
+	}
+
+	flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE);
+
+	down_write(&current->mm->mmap_sem);
+	retval = do_mmap_pgoff(file, addr, len, prot, flags, pgoff);
+	up_write(&current->mm->mmap_sem);
+
+	if (file)
+		fput(file);
+out:
+	return retval;
+}
+
 /*
  * Some shared mappigns will want the pages marked read-only
  * to track write events. If so, we'll downgrade vm_page_prot
@@ -1198,8 +1238,20 @@ munmap_back:
 			goto free_vma;
 	}
 
-	if (vma_wants_writenotify(vma))
+	if (vma_wants_writenotify(vma)) {
+		pgprot_t pprot = vma->vm_page_prot;
+
+		/* Can vma->vm_page_prot have changed??
+		 *
+		 * Answer: Yes, drivers may have changed it in their
+		 *         f_op->mmap method.
+		 *
+		 * Ensures that vmas marked as uncached stay that way.
+		 */
 		vma->vm_page_prot = vm_get_page_prot(vm_flags & ~VM_SHARED);
+		if (pgprot_val(pprot) == pgprot_val(pgprot_noncached(pprot)))
+			vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+	}
 
 	vma_link(mm, vma, prev, rb_link, rb_parent);
 	file = vma->vm_file;
@@ -1811,10 +1863,10 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma,
 }
 
 /*
- * Split a vma into two pieces at address 'addr', a new vma is allocated
- * either for the first part or the tail.
+ * __split_vma() bypasses sysctl_max_map_count checking.  We use this on the
+ * munmap path where it doesn't make sense to fail.
  */
-int split_vma(struct mm_struct * mm, struct vm_area_struct * vma,
+static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma,
 	      unsigned long addr, int new_below)
 {
 	struct mempolicy *pol;
@@ -1824,9 +1876,6 @@ int split_vma(struct mm_struct * mm, struct vm_area_struct * vma,
 					~(huge_page_mask(hstate_vma(vma)))))
 		return -EINVAL;
 
-	if (mm->map_count >= sysctl_max_map_count)
-		return -ENOMEM;
-
 	new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
 	if (!new)
 		return -ENOMEM;
@@ -1866,6 +1915,19 @@ int split_vma(struct mm_struct * mm, struct vm_area_struct * vma,
 	return 0;
 }
 
+/*
+ * Split a vma into two pieces at address 'addr', a new vma is allocated
+ * either for the first part or the tail.
+ */
+int split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
+	      unsigned long addr, int new_below)
+{
+	if (mm->map_count >= sysctl_max_map_count)
+		return -ENOMEM;
+
+	return __split_vma(mm, vma, addr, new_below);
+}
+
 /* Munmap is split into 2 main parts -- this part which finds
  * what needs doing, and the areas themselves, which do the
  * work.  This now handles partial unmappings.
@@ -1901,7 +1963,17 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len)
 	 * places tmp vma above, and higher split_vma places tmp vma below.
 	 */
 	if (start > vma->vm_start) {
-		int error = split_vma(mm, vma, start, 0);
+		int error;
+
+		/*
+		 * Make sure that map_count on return from munmap() will
+		 * not exceed its limit; but let map_count go just above
+		 * its limit temporarily, to help free resources as expected.
+		 */
+		if (end < vma->vm_end && mm->map_count >= sysctl_max_map_count)
+			return -ENOMEM;
+
+		error = __split_vma(mm, vma, start, 0);
 		if (error)
 			return error;
 		prev = vma;
@@ -1910,7 +1982,7 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len)
 	/* Does it split the last one? */
 	last = find_vma(mm, end);
 	if (last && end > last->vm_start) {
-		int error = split_vma(mm, last, end, 1);
+		int error = __split_vma(mm, last, end, 1);
 		if (error)
 			return error;
 	}