[v8,11/13] s390/mm: hugetlb pages within a gmap can not be freed

Commit Message

Janosch Frank July 20, 2018, 8:44 a.m. UTC

Guests backed by huge pages could theoretically free unused pages via
the diagnose 10 instruction. We currently don't allow that, so we
don't have to refault it once it's needed again.

Signed-off-by: Dominik Dingel <[e-mail]>
Reviewed-by: Martin Schwidefsky <[e-mail]>
Reviewed-by: David Hildenbrand <[e-mail]>
---
 arch/s390/mm/gmap.c | 6 ++++++
 1 file changed, 6 insertions(+)

Patch

diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 409bc8f9d5b6..1aad4101c42d 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -707,6 +707,12 @@  void gmap_discard(struct gmap *gmap, unsigned long from, unsigned long to)
 		vmaddr |= gaddr & ~PMD_MASK;
 		/* Find vma in the parent mm */
 		vma = find_vma(gmap->mm, vmaddr);
+		/*
+		 * We do not discard pages that are backed by
+		 * hugetlbfs, so we don't have to refault them.
+		 */
+		if (vma && is_vm_hugetlb_page(vma))
+			continue;
 		size = min(to - gaddr, PMD_SIZE - (gaddr & ~PMD_MASK));
 		zap_page_range(vma, vmaddr, size);
 	}