userfaultfd: wp: support write protection for userfault vma range

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

[peterx@redhat.com:
 - use the helper to find VMA;
 - return -ENOENT if not found to match mcopy case;
 - use the new MM_CP_UFFD_WP* flags for change_protection
 - check against mmap_changing for failures
 - replace find_dst_vma with vma_find_uffd]
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Jerome Glisse <jglisse@redhat.com>
Reviewed-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Andrea Arcangeli <aarcange@redhat.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>
Cc: Bobby Powers <bobbypowers@gmail.com>
Cc: Brian Geffon <bgeffon@google.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Denis Plotnikov <dplotnikov@virtuozzo.com>
Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com>
Cc: Martin Cracauer <cracauer@cons.org>
Cc: Marty McFadden <mcfadden8@llnl.gov>
Cc: Maya Gokhale <gokhale2@llnl.gov>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Pavel Emelyanov <xemul@openvz.org>
Link: http://lkml.kernel.org/r/20200220163112.11409-13-peterx@redhat.comSigned-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/linux/userfaultfd_k.h

@@ -41,6 +41,9 @@ extern ssize_t mfill_zeropage(struct mm_struct *dst_mm,
 			      unsigned long dst_start,
 			      unsigned long len,
 			      bool *mmap_changing);
+extern int mwriteprotect_range(struct mm_struct *dst_mm,
+			       unsigned long start, unsigned long len,
+			       bool enable_wp, bool *mmap_changing);
 
 /* mm helpers */
 static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma,

mm/userfaultfd.c

@@ -638,3 +638,57 @@ ssize_t mfill_zeropage(struct mm_struct *dst_mm, unsigned long start,
 {
 	return __mcopy_atomic(dst_mm, start, 0, len, true, mmap_changing, 0);
 }
+
+int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start,
+			unsigned long len, bool enable_wp, bool *mmap_changing)
+{
+	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);
+
+	/*
+	 * If memory mappings are changing because of non-cooperative
+	 * operation (e.g. mremap) running in parallel, bail out and
+	 * request the user to retry later
+	 */
+	err = -EAGAIN;
+	if (mmap_changing && READ_ONCE(*mmap_changing))
+		goto out_unlock;
+
+	err = -ENOENT;
+	dst_vma = find_dst_vma(dst_mm, start, len);
+	/*
+	 * Make sure the vma is not shared, that the dst range is
+	 * both valid and fully within a single existing vma.
+	 */
+	if (!dst_vma || (dst_vma->vm_flags & VM_SHARED))
+		goto out_unlock;
+	if (!userfaultfd_wp(dst_vma))
+		goto out_unlock;
+	if (!vma_is_anonymous(dst_vma))
+		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 ? MM_CP_UFFD_WP : MM_CP_UFFD_WP_RESOLVE);
+
+	err = 0;
+out_unlock:
+	up_read(&dst_mm->mmap_sem);
+	return err;
+}