[RFC 2/8] userfaultfd: support write protection for userfault vma range

[Shaohua Li <shli@fb.com>]

Add API to enable/disable writeprotect a vma range. Unlike mprotect,
this doesn't split/merge vmas.

Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Hugh Dickins <hughd@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Shaohua Li <shli@fb.com>
---
 include/linux/userfaultfd_k.h |  2 ++
 mm/userfaultfd.c              | 52 +++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 54 insertions(+)

diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index 4e22d11..44f5b09 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -35,6 +35,8 @@ extern ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start,
 extern ssize_t mfill_zeropage(struct mm_struct *dst_mm,
 			      unsigned long dst_start,
 			      unsigned long len);
+extern int mwriteprotect_range(struct mm_struct *dst_mm,
+		unsigned long start, unsigned long len, bool enable_wp);
 
 /* mm helpers */
 static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma,
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 77fee93..3e97e24 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -306,3 +306,55 @@ ssize_t mfill_zeropage(struct mm_struct *dst_mm, unsigned long start,
 {
 	return __mcopy_atomic(dst_mm, start, 0, len, true);
 }
+
+int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start,
+	unsigned long len, bool enable_wp)
+{
+	struct vm_area_struct *dst_vma;
+	pgprot_t newprot;
+	int err;
+
+	/*
+	 * Sanitize the command parameters:
+	 */
+	BUG_ON(start & ~PAGE_MASK);
+	BUG_ON(len & ~PAGE_MASK);
+
+	/* Does the address range wrap, or is the span zero-sized? */
+	BUG_ON(start + len <= start);
+
+	down_read(&dst_mm->mmap_sem);
+
+	/*
+	 * Make sure the vma is not shared, that the dst range is
+	 * both valid and fully within a single existing vma.
+	 */
+	err = -EINVAL;
+	dst_vma = find_vma(dst_mm, start);
+	if (!dst_vma || (dst_vma->vm_flags & VM_SHARED))
+		goto out_unlock;
+	if (start < dst_vma->vm_start ||
+	    start + len > dst_vma->vm_end)
+		goto out_unlock;
+
+	if (!dst_vma->vm_userfaultfd_ctx.ctx)
+		goto out_unlock;
+	if (!userfaultfd_wp(dst_vma))
+		goto out_unlock;
+
+	if (dst_vma->vm_ops)
+		goto out_unlock;
+
+	if (enable_wp)
+		newprot = vm_get_page_prot(dst_vma->vm_flags & ~(VM_WRITE));
+	else
+		newprot = vm_get_page_prot(dst_vma->vm_flags);
+
+	change_protection(dst_vma, start, start + len, newprot,
+				!enable_wp, 0);
+
+	err = 0;
+out_unlock:
+	up_read(&dst_mm->mmap_sem);
+	return err;
+}
-- 
2.4.6

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>