diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 74b684d..e0db197 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -185,7 +185,10 @@
         ARCH := x86
 endif
 ifeq ($(ARCH),x86_64)
+	RAW_ARCH := x86_64
         ARCH := x86
+	ARCH_CFLAGS := -DARCH_X86_64
+	ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S
 endif
 
 # CFLAGS and LDFLAGS are for the users to override from the command line.
@@ -375,6 +378,7 @@
 LIB_H += util/include/linux/rbtree.h
 LIB_H += util/include/linux/string.h
 LIB_H += util/include/linux/types.h
+LIB_H += util/include/linux/linkage.h
 LIB_H += util/include/asm/asm-offsets.h
 LIB_H += util/include/asm/bug.h
 LIB_H += util/include/asm/byteorder.h
@@ -383,6 +387,8 @@
 LIB_H += util/include/asm/system.h
 LIB_H += util/include/asm/uaccess.h
 LIB_H += util/include/dwarf-regs.h
+LIB_H += util/include/asm/dwarf2.h
+LIB_H += util/include/asm/cpufeature.h
 LIB_H += perf.h
 LIB_H += util/cache.h
 LIB_H += util/callchain.h
@@ -417,6 +423,7 @@
 LIB_H += util/probe-event.h
 LIB_H += util/pstack.h
 LIB_H += util/cpumap.h
+LIB_H += $(ARCH_INCLUDE)
 
 LIB_OBJS += $(OUTPUT)util/abspath.o
 LIB_OBJS += $(OUTPUT)util/alias.o
@@ -472,6 +479,9 @@
 # Benchmark modules
 BUILTIN_OBJS += $(OUTPUT)bench/sched-messaging.o
 BUILTIN_OBJS += $(OUTPUT)bench/sched-pipe.o
+ifeq ($(RAW_ARCH),x86_64)
+BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy-x86-64-asm.o
+endif
 BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy.o
 
 BUILTIN_OBJS += $(OUTPUT)builtin-diff.o
@@ -898,6 +908,7 @@
 LIB_OBJS += $(COMPAT_OBJS)
 
 ALL_CFLAGS += $(BASIC_CFLAGS)
+ALL_CFLAGS += $(ARCH_CFLAGS)
 ALL_LDFLAGS += $(BASIC_LDFLAGS)
 
 export TAR INSTALL DESTDIR SHELL_PATH
diff --git a/tools/perf/bench/mem-memcpy-arch.h b/tools/perf/bench/mem-memcpy-arch.h
new file mode 100644
index 0000000..a72e36c
--- /dev/null
+++ b/tools/perf/bench/mem-memcpy-arch.h
@@ -0,0 +1,12 @@
+
+#ifdef ARCH_X86_64
+
+#define MEMCPY_FN(fn, name, desc)		\
+	extern void *fn(void *, const void *, size_t);
+
+#include "mem-memcpy-x86-64-asm-def.h"
+
+#undef MEMCPY_FN
+
+#endif
+
diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm-def.h b/tools/perf/bench/mem-memcpy-x86-64-asm-def.h
new file mode 100644
index 0000000..d588b87
--- /dev/null
+++ b/tools/perf/bench/mem-memcpy-x86-64-asm-def.h
@@ -0,0 +1,4 @@
+
+MEMCPY_FN(__memcpy,
+	"x86-64-unrolled",
+	"unrolled memcpy() in arch/x86/lib/memcpy_64.S")
diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S
new file mode 100644
index 0000000..a57b66e
--- /dev/null
+++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S
@@ -0,0 +1,2 @@
+
+#include "../../../arch/x86/lib/memcpy_64.S"
diff --git a/tools/perf/util/include/asm/cpufeature.h b/tools/perf/util/include/asm/cpufeature.h
new file mode 100644
index 0000000..acffd5e
--- /dev/null
+++ b/tools/perf/util/include/asm/cpufeature.h
@@ -0,0 +1,9 @@
+
+#ifndef PERF_CPUFEATURE_H
+#define PERF_CPUFEATURE_H
+
+/* cpufeature.h ... dummy header file for including arch/x86/lib/memcpy_64.S */
+
+#define X86_FEATURE_REP_GOOD 0
+
+#endif	/* PERF_CPUFEATURE_H */
diff --git a/tools/perf/util/include/asm/dwarf2.h b/tools/perf/util/include/asm/dwarf2.h
new file mode 100644
index 0000000..bb4198e
--- /dev/null
+++ b/tools/perf/util/include/asm/dwarf2.h
@@ -0,0 +1,11 @@
+
+#ifndef PERF_DWARF2_H
+#define PERF_DWARF2_H
+
+/* dwarf2.h ... dummy header file for including arch/x86/lib/memcpy_64.S */
+
+#define CFI_STARTPROC
+#define CFI_ENDPROC
+
+#endif	/* PERF_DWARF2_H */
+
diff --git a/tools/perf/util/include/linux/linkage.h b/tools/perf/util/include/linux/linkage.h
new file mode 100644
index 0000000..06387cf
--- /dev/null
+++ b/tools/perf/util/include/linux/linkage.h
@@ -0,0 +1,13 @@
+
+#ifndef PERF_LINUX_LINKAGE_H_
+#define PERF_LINUX_LINKAGE_H_
+
+/* linkage.h ... for including arch/x86/lib/memcpy_64.S */
+
+#define ENTRY(name)				\
+	.globl name;				\
+	name:
+
+#define ENDPROC(name)
+
+#endif	/* PERF_LINUX_LINKAGE_H_ */