diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 6e71c5734e78fece8cb26c689a3b49f8257e2d90..7fb7af66b8059d891cc4c5557877a9d981cfa635 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -22,6 +22,7 @@
 #include <asm/memory.h>
 #include <asm/pgtable-hwdef.h>
 #include <asm/pgtable-prot.h>
+#include <asm/tlbflush.h>
 
 /*
  * VMALLOC range.
@@ -653,6 +654,27 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
 	return __ptep_test_and_clear_young(ptep);
 }
 
+#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
+static inline int ptep_clear_flush_young(struct vm_area_struct *vma,
+					 unsigned long address, pte_t *ptep)
+{
+	int young = ptep_test_and_clear_young(vma, address, ptep);
+
+	if (young) {
+		/*
+		 * We can elide the trailing DSB here since the worst that can
+		 * happen is that a CPU continues to use the young entry in its
+		 * TLB and we mistakenly reclaim the associated page. The
+		 * window for such an event is bounded by the next
+		 * context-switch, which provides a DSB to complete the TLB
+		 * invalidation.
+		 */
+		flush_tlb_page_nosync(vma, address);
+	}
+
+	return young;
+}
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
 static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index c3c0387aee18f2aaa2b1be745eeee6c340da2d5f..a629a4067aae551c67cd3f9e1e9aaabc5bd94ae5 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -21,6 +21,7 @@
 
 #ifndef __ASSEMBLY__
 
+#include <linux/mm_types.h>
 #include <linux/sched.h>
 #include <asm/cputype.h>
 #include <asm/mmu.h>
@@ -164,14 +165,20 @@ static inline void flush_tlb_mm(struct mm_struct *mm)
 	dsb(ish);
 }
 
-static inline void flush_tlb_page(struct vm_area_struct *vma,
-				  unsigned long uaddr)
+static inline void flush_tlb_page_nosync(struct vm_area_struct *vma,
+					 unsigned long uaddr)
 {
 	unsigned long addr = __TLBI_VADDR(uaddr, ASID(vma->vm_mm));
 
 	dsb(ishst);
 	__tlbi(vale1is, addr);
 	__tlbi_user(vale1is, addr);
+}
+
+static inline void flush_tlb_page(struct vm_area_struct *vma,
+				  unsigned long uaddr)
+{
+	flush_tlb_page_nosync(vma, uaddr);
 	dsb(ish);
 }