perf tools: Fix building error in x86_64 when dwarf unwind is on

When build with 'make ARCH=x86' and dwarf unwind is on, there is a
compiling error:

   CC       /home/wn/perf/arch/x86/util/unwind-libdw.o
   CC       /home/wn/perf/arch/x86/tests/regs_load.o
 arch/x86/tests/regs_load.S: Assembler messages:
 arch/x86/tests/regs_load.S:65: Error: operand type mismatch for `push'
 arch/x86/tests/regs_load.S:72: Error: operand type mismatch for `pop'
 make[1]: *** [/home/wn/perf/arch/x86/tests/regs_load.o] Error 1
 make[1]: INTERNAL: Exiting with 25 jobserver tokens available; should be 24!
 make: *** [all] Error 2
 ...

Which is caused by incorrectly undefine macro HAVE_ARCH_X86_64_SUPPORT.
'config/Makefile.arch' tests __x86_64__ only when 'ARCH=x86_64'.
However, when building x86_64 kernel, ARCH=x86 is valid and commonly
used. Build systems, such as yocto, uses x86_64 compiler with 'ARCH=x86'
to build x86_64 perf, which causes mismatching.

As __LP64__ is defined for x86_64 as well, we can consolidate the
__x86_64__ check to the __LP64__ check and get rid of the IS_X86_64
IMHO.

(This patch is made by Namhyung Kim when replying my v1 patch:

https://lkml.org/lkml/2015/1/7/17

I modified the code to remove dependency on RAW_ARCH:

https://lkml.org/lkml/2015/1/7/865

Namhyung Kim didn't provide his SOB in his original email. I add
mine only for my modification.)

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Wang Nan <wangnan0@huawei.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Li Zefan <lizefan@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/r/1421029255-23039-1-git-send-email-wangnan0@huawei.com
[ Namhyung provided his S-o-B on a followup to this patch thread on lkml ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/Makefile.perf

@@ -462,10 +462,12 @@ 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)
+ifeq ($(ARCH), x86)
+ifeq ($(IS_64_BIT), 1)
 BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy-x86-64-asm.o
 BUILTIN_OBJS += $(OUTPUT)bench/mem-memset-x86-64-asm.o
 endif
+endif
 BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy.o
 BUILTIN_OBJS += $(OUTPUT)bench/futex-hash.o
 BUILTIN_OBJS += $(OUTPUT)bench/futex-wake.o

tools/perf/config/Makefile

@@ -20,7 +20,7 @@ NO_PERF_REGS := 1
 
 # Additional ARCH settings for x86
 ifeq ($(ARCH),x86)
-  ifeq (${IS_X86_64}, 1)
+  ifeq (${IS_64_BIT}, 1)
     CFLAGS += -DHAVE_ARCH_X86_64_SUPPORT
     ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S
     LIBUNWIND_LIBS = -lunwind -lunwind-x86_64

tools/perf/config/Makefile.arch

@@ -1,7 +1,7 @@
 
 uname_M := $(shell uname -m 2>/dev/null || echo not)
 
-ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \
+RAW_ARCH := $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \
                                   -e s/arm.*/arm/ -e s/sa110/arm/ \
                                   -e s/s390x/s390/ -e s/parisc64/parisc/ \
                                   -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \
@@ -9,23 +9,23 @@ ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \
                                   -e s/tile.*/tile/ )
 
 # Additional ARCH settings for x86
-ifeq ($(ARCH),i386)
+ifeq ($(RAW_ARCH),i386)
-  override ARCH := x86
+  ARCH ?= x86
 endif
 
-ifeq ($(ARCH),x86_64)
+ifeq ($(RAW_ARCH),x86_64)
-  override ARCH := x86
+  ARCH ?= x86
-  IS_X86_64 := 0
+
-  ifeq (, $(findstring m32,$(CFLAGS)))
+  ifneq (, $(findstring m32,$(CFLAGS)))
-    IS_X86_64 := $(shell echo __x86_64__ | ${CC} -E -x c - | tail -n 1)
+    RAW_ARCH := x86_32
-    RAW_ARCH := x86_64
   endif
 endif
 
-ifeq (${IS_X86_64}, 1)
+ARCH ?= $(RAW_ARCH)
+
+LP64 := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1)
+ifeq ($(LP64), 1)
   IS_64_BIT := 1
-else ifeq ($(ARCH),x86)
-  IS_64_BIT := 0
 else
-  IS_64_BIT := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1)
+  IS_64_BIT := 0
 endif