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

[Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>]

On 2010年11月26日 19:31, tip-bot for Hitoshi Mitake wrote:
 > Commit-ID:  ea7872b9d6a81101f6ba0ec141544a62fea35876
 > Gitweb: 
http://git.kernel.org/tip/ea7872b9d6a81101f6ba0ec141544a62fea35876
 > Author:     Hitoshi Mitake<mitake@dcl.info.waseda.ac.jp>
 > AuthorDate: Thu, 25 Nov 2010 16:04:53 +0900
 > Committer:  Ingo Molnar<mingo@elte.hu>
 > CommitDate: Fri, 26 Nov 2010 08:15:57 +0100
 >
 > 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                          |   11 +++++++++++
 >   tools/perf/bench/mem-memcpy-arch.h           |   12 ++++++++++++
 >   tools/perf/bench/mem-memcpy-x86-64-asm-def.h |    4 ++++
 >   tools/perf/bench/mem-memcpy-x86-64-asm.S     |    2 ++
 >   tools/perf/util/include/asm/cpufeature.h     |    9 +++++++++
 >   tools/perf/util/include/asm/dwarf2.h         |   11 +++++++++++
 >   tools/perf/util/include/linux/linkage.h      |   13 +++++++++++++
 >   7 files changed, 62 insertions(+), 0 deletions(-)
 >
 > 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 @@ 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
 > 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_ */
 >

Thanks for your applying, Ingo!

BTW, I have a question.
Why does the symbol name of rep prefix memcpy() start from '.'?
The symbol name starts from '.' like ".Lmemcpy_c" cannot seen as
symbol name after compile.

I couldn't find the reason why .Lmemcpy_c has to start from '.'.
For example, clear_page in arch/x86/lib/clear_page_64.S
doesn't start from '.' but it is alternative function.

If there is no special reason, I'd like to rename it.

Thanks,
	Hitoshi