perf bench: Add feature that measures the performance of the...

perf bench: Add feature that measures the performance of the arch/x86/lib/memcpy_64.S memcpy routines via 'perf bench mem'

This patch ports arch/x86/lib/memcpy_64.S to perf bench mem
memcpy for benchmarking memcpy() in userland with tricky and
dirty way.

util/include/asm/cpufeature.h, util/include/asm/dwarf2.h, and
util/include/linux/linkage.h are mostly dummy files with small
wrappers, so that we are able to include memcpy_64.S
unmodified.
Signed-off-by: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
Cc: h.mitake@gmail.com
Cc: Miao Xie <miaox@cn.fujitsu.com>
Cc: Ma Ling <ling.ma@intel.com>
Cc: Zhao Yakui <yakui.zhao@intel.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Andi Kleen <andi@firstfloor.org>
LKML-Reference: <1290668693-27068-2-git-send-email-mitake@dcl.info.waseda.ac.jp>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

tools/perf/Makefile

@@ -185,7 +185,10 @@ ifeq ($(ARCH),i386)
         ARCH := x86
 endif
 ifeq ($(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/prefetch.h
 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/swab.h
 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-finder.h
 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 @@ BUILTIN_OBJS += $(OUTPUT)builtin-bench.o
 # 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 += $(OUTPUT)builtin-diff.o
@@ -898,6 +908,7 @@ BASIC_CFLAGS += -DSHA1_HEADER='$(SHA1_HEADER_SQ)' \
 LIB_OBJS += $(COMPAT_OBJS)
 
 ALL_CFLAGS += $(BASIC_CFLAGS)
+ALL_CFLAGS += $(ARCH_CFLAGS)
 ALL_LDFLAGS += $(BASIC_LDFLAGS)
 
 export TAR INSTALL DESTDIR SHELL_PATH

tools/perf/bench/mem-memcpy-arch.h

+
+#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
+

tools/perf/bench/mem-memcpy-x86-64-asm-def.h

+
+MEMCPY_FN(__memcpy,
+	"x86-64-unrolled",
+	"unrolled memcpy() in arch/x86/lib/memcpy_64.S")

tools/perf/bench/mem-memcpy-x86-64-asm.S

+
+#include "../../../arch/x86/lib/memcpy_64.S"

tools/perf/util/include/asm/cpufeature.h

+
+#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 */

tools/perf/util/include/asm/dwarf2.h

+
+#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 */
+

tools/perf/util/include/linux/linkage.h

+
+#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_ */