mm: mmu_notifier fix for tlb_end_vma

The generic tlb_end_vma does not call invalidate_range mmu notifier, and
it resets resets the mmu_gather range, which means the notifier won't be
called on part of the range in case of an unmap that spans multiple
vmas.

ARM64 seems to be the only arch I could see that has notifiers and uses
the generic tlb_end_vma.  I have not actually tested it.

[ Catalin and Will point out that ARM64 currently only uses the
  notifiers for KVM, which doesn't use the ->invalidate_range()
  callback right now, so it's a bug, but one that happens to
  not affect them.  So not necessary for stable.  - Linus ]

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/asm-generic/tlb.h

@@ -15,6 +15,7 @@
 #ifndef _ASM_GENERIC__TLB_H
 #define _ASM_GENERIC__TLB_H
 
+#include <linux/mmu_notifier.h>
 #include <linux/swap.h>
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
@@ -138,6 +139,16 @@ static inline void __tlb_reset_range(struct mmu_gather *tlb)
 	}
 }
 
+static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
+{
+	if (!tlb->end)
+		return;
+
+	tlb_flush(tlb);
+	mmu_notifier_invalidate_range(tlb->mm, tlb->start, tlb->end);
+	__tlb_reset_range(tlb);
+}
+
 static inline void tlb_remove_page_size(struct mmu_gather *tlb,
 					struct page *page, int page_size)
 {
@@ -186,10 +197,8 @@ static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
 
 #define __tlb_end_vma(tlb, vma)					\
 	do {							\
-		if (!tlb->fullmm && tlb->end) {			\
+		if (!tlb->fullmm)				\
-			tlb_flush(tlb);				\
+			tlb_flush_mmu_tlbonly(tlb);		\
-			__tlb_reset_range(tlb);			\
-		}						\
 	} while (0)
 
 #ifndef tlb_end_vma

mm/memory.c

@@ -238,16 +238,6 @@ void arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
 	__tlb_reset_range(tlb);
 }
 
-static void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
-{
-	if (!tlb->end)
-		return;
-
-	tlb_flush(tlb);
-	mmu_notifier_invalidate_range(tlb->mm, tlb->start, tlb->end);
-	__tlb_reset_range(tlb);
-}
-
 static void tlb_flush_mmu_free(struct mmu_gather *tlb)
 {
 	struct mmu_gather_batch *batch;