diff --git a/arch/riscv/include/asm/mmio.h b/arch/riscv/include/asm/mmio.h
index aff6c33ab0c0..4c58ee7f95ec 100644
--- a/arch/riscv/include/asm/mmio.h
+++ b/arch/riscv/include/asm/mmio.h
@@ -101,9 +101,9 @@ static inline u64 __raw_readq(const volatile void __iomem *addr)
  * Relaxed I/O memory access primitives. These follow the Device memory
  * ordering rules but do not guarantee any ordering relative to Normal memory
  * accesses.  These are defined to order the indicated access (either a read or
- * write) with all other I/O memory accesses. Since the platform specification
- * defines that all I/O regions are strongly ordered on channel 2, no explicit
- * fences are required to enforce this ordering.
+ * write) with all other I/O memory accesses to the same peripheral. Since the
+ * platform specification defines that all I/O regions are strongly ordered on
+ * channel 0, no explicit fences are required to enforce this ordering.
  */
 /* FIXME: These are now the same as asm-generic */
 #define __io_rbr()		do {} while (0)
@@ -125,14 +125,14 @@ static inline u64 __raw_readq(const volatile void __iomem *addr)
 #endif
 
 /*
- * I/O memory access primitives. Reads are ordered relative to any
- * following Normal memory access. Writes are ordered relative to any prior
- * Normal memory access.  The memory barriers here are necessary as RISC-V
+ * I/O memory access primitives.  Reads are ordered relative to any following
+ * Normal memory read and delay() loop.  Writes are ordered relative to any
+ * prior Normal memory write.  The memory barriers here are necessary as RISC-V
  * doesn't define any ordering between the memory space and the I/O space.
  */
 #define __io_br()	do {} while (0)
-#define __io_ar(v)	__asm__ __volatile__ ("fence i,r" : : : "memory")
-#define __io_bw()	__asm__ __volatile__ ("fence w,o" : : : "memory")
+#define __io_ar(v)	({ __asm__ __volatile__ ("fence i,ir" : : : "memory"); })
+#define __io_bw()	({ __asm__ __volatile__ ("fence w,o" : : : "memory"); })
 #define __io_aw()	mmiowb_set_pending()
 
 #define readb(c)	({ u8  __v; __io_br(); __v = readb_cpu(c); __io_ar(__v); __v; })