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>
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