mm/hugetlb.c: call MMU notifiers when copying a hugetlb page range

When copy_hugetlb_page_range() is called to copy a range of hugetlb
mappings, the secondary MMUs are not notified if there is a protection
downgrade, which breaks COW semantics in KVM.

This patch adds the necessary MMU notifier calls.
Signed-off-by: Andreas Sandberg <andreas@sandberg.pp.se>
Acked-by: Steve Capper <steve.capper@linaro.org>
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

mm/hugetlb.c

@@ -2346,17 +2346,27 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 	int cow;
 	struct hstate *h = hstate_vma(vma);
 	unsigned long sz = huge_page_size(h);
+	unsigned long mmun_start;	/* For mmu_notifiers */
+	unsigned long mmun_end;		/* For mmu_notifiers */
+	int ret = 0;
 
 	cow = (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
 
+	mmun_start = vma->vm_start;
+	mmun_end = vma->vm_end;
+	if (cow)
+		mmu_notifier_invalidate_range_start(src, mmun_start, mmun_end);
+
 	for (addr = vma->vm_start; addr < vma->vm_end; addr += sz) {
 		spinlock_t *src_ptl, *dst_ptl;
 		src_pte = huge_pte_offset(src, addr);
 		if (!src_pte)
 			continue;
 		dst_pte = huge_pte_alloc(dst, addr, sz);
-		if (!dst_pte)
-			goto nomem;
+		if (!dst_pte) {
+			ret = -ENOMEM;
+			break;
+		}
 
 		/* If the pagetables are shared don't copy or take references */
 		if (dst_pte == src_pte)
@@ -2377,10 +2387,11 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 		spin_unlock(src_ptl);
 		spin_unlock(dst_ptl);
 	}
-	return 0;
 
-nomem:
-	return -ENOMEM;
+	if (cow)
+		mmu_notifier_invalidate_range_end(src, mmun_start, mmun_end);
+
+	return ret;
 }
 
 static int is_hugetlb_entry_migration(pte_t pte)