diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 9997521fc5cd6621a14eda391c739a420524df73..e1aa17a468a858050f7f0becfd98043d72ae64fb 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -399,4 +399,40 @@ extern bool arch_memremap_can_ram_remap(resource_size_t offset,
 extern bool phys_mem_access_encrypted(unsigned long phys_addr,
 				      unsigned long size);
 
+/**
+ * iosubmit_cmds512 - copy data to single MMIO location, in 512-bit units
+ * @__dst: destination, in MMIO space (must be 512-bit aligned)
+ * @src: source
+ * @count: number of 512 bits quantities to submit
+ *
+ * Submit data from kernel space to MMIO space, in units of 512 bits at a
+ * time.  Order of access is not guaranteed, nor is a memory barrier
+ * performed afterwards.
+ *
+ * Warning: Do not use this helper unless your driver has checked that the CPU
+ * instruction is supported on the platform.
+ */
+static inline void iosubmit_cmds512(void __iomem *__dst, const void *src,
+				    size_t count)
+{
+	/*
+	 * Note that this isn't an "on-stack copy", just definition of "dst"
+	 * as a pointer to 64-bytes of stuff that is going to be overwritten.
+	 * In the MOVDIR64B case that may be needed as you can use the
+	 * MOVDIR64B instruction to copy arbitrary memory around. This trick
+	 * lets the compiler know how much gets clobbered.
+	 */
+	volatile struct { char _[64]; } *dst = __dst;
+	const u8 *from = src;
+	const u8 *end = from + count * 64;
+
+	while (from < end) {
+		/* MOVDIR64B [rdx], rax */
+		asm volatile(".byte 0x66, 0x0f, 0x38, 0xf8, 0x02"
+			     : "=m" (dst)
+			     : "d" (from), "a" (dst));
+		from += 64;
+	}
+}
+
 #endif /* _ASM_X86_IO_H */