diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index 1adbb8a371c7..04c1e99c1624 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -1937,6 +1937,14 @@ There are some more advanced barrier functions:
      information on consistent memory.
 
 
+ (*) io_stop_wc();
+
+     For memory accesses with write-combining attributes (e.g. those returned
+     by ioremap_wc(), the CPU may wait for prior accesses to be merged with
+     subsequent ones. io_stop_wc() can be used to prevent the merging of
+     write-combining memory accesses before this macro with those after it when
+     such wait has performance implications.
+
 ===============================
 IMPLICIT KERNEL MEMORY BARRIERS
 ===============================
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index 0fcd854fc95f..37c17bcd00af 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -28,6 +28,13 @@
 #define spec_bar()	asm volatile(ALTERNATIVE("dsb nsh\nisb\n",		\
 						 SB_BARRIER_INSN"nop\n",	\
 						 ARM64_HAS_SB))
+/*
+ * Data Gathering Hint:
+ * This instruction prevents merging memory accesses with Normal-NC or
+ * Device-GRE attributes before the hint instruction with any memory accesses
+ * appearing after the hint instruction.
+ */
+#define dgh()		asm volatile("hint #6" : : : "memory")
 
 #define mb()		dsb(sy)
 #define rmb()		dsb(ld)
@@ -36,6 +43,8 @@
 #define dma_rmb()	dmb(oshld)
 #define dma_wmb()	dmb(oshst)
 
+#define io_stop_wc()	dgh()
+
 /*
  * Generate a mask for array_index__nospec() that is ~0UL when 0 <= idx < sz
  * and 0 otherwise.
diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h
index 85b28eb80b11..888f35d02a13 100644
--- a/include/asm-generic/barrier.h
+++ b/include/asm-generic/barrier.h
@@ -257,5 +257,16 @@ do {									\
 })
 #endif
 
+/*
+ * ioremap_wc() maps I/O memory as memory with write-combining attributes. For
+ * this kind of memory accesses, the CPU may wait for prior accesses to be
+ * merged with subsequent ones. In some situation, such wait is bad for the
+ * performance. io_stop_wc() can be used to prevent the merging of
+ * write-combining memory accesses before this macro with those after it.
+ */
+#ifndef io_stop_wc
+#define io_stop_wc do { } while (0)
+#endif
+
 #endif /* !__ASSEMBLY__ */
 #endif /* __ASM_GENERIC_BARRIER_H */