Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit ff5fdafc authored by Nicolas Pitre's avatar Nicolas Pitre Committed by Russell King
Browse files

ARM: 8745/1: get rid of __memzero() 

The __memzero assembly code is almost identical to memset's except for
two orr instructions. The runtime performance of __memset(p, n) and
memset(p, 0, n) is accordingly almost identical.

However, the memset() macro used to guard against a zero length and to
call __memzero at compile time when the fill value is a constant zero
interferes with compiler optimizations.

Arnd found tha the test against a zero length brings up some new
warnings with gcc v8:

  https://gcc.gnu.org/bugzilla/show_bug.cgi?id=82103



And successively rremoving the test against a zero length and the call
to __memzero optimization produces the following kernel sizes for
defconfig with gcc 6:

    text     data     bss       dec       hex  filename
12248142  6278960  413588  18940690   1210312  vmlinux.orig
12244474  6278960  413588  18937022   120f4be  vmlinux.no_zero_test
12239160  6278960  413588  18931708   120dffc  vmlinux.no_memzero

So it is probably not worth keeping __memzero around given that the
compiler can do a better job at inlining trivial memset(p,0,n) on its
own. And the memset code already handles a zero length just fine.

Suggested-by: default avatarArnd Bergmann <arnd@arndb.de>
Signed-off-by: default avatarNicolas Pitre <nico@linaro.org>
Acked-by: default avatarArd Biesheuvel <ard.biesheuvel@linaro.org>
Acked-by: default avatarArnd Bergmann <arnd@arndb.de>
Signed-off-by: default avatarRussell King <rmk+kernel@armlinux.org.uk>
parent ec80eb46

arch/arm/boot/compressed/string.c

+0 −5
Original line number Diff line number Diff line
@@ -130,8 +130,3 @@ void *memset(void *s, int c, size_t count) 
		*xs++ = c;

	return s;

}
 


void __memzero(void *s, size_t count)

{

	memset(s, 0, count);

}

arch/arm/include/asm/string.h

+0 −14
Original line number Diff line number Diff line
@@ -39,18 +39,4 @@ static inline void *memset64(uint64_t *p, uint64_t v, __kernel_size_t n) 
	return __memset64(p, v, n * 8, v >> 32);

}



extern void __memzero(void *ptr, __kernel_size_t n);



#define memset(p,v,n)							\

	({								\

	 	void *__p = (p); size_t __n = n;			\

		if ((__n) != 0) {					\

			if (__builtin_constant_p((v)) && (v) == 0)	\

				__memzero((__p),(__n));			\

			else						\

				memset((__p),(v),(__n));		\

		}							\

		(__p);							\

	})



#endif

arch/arm/kernel/armksyms.c

+0 −1
Original line number Diff line number Diff line
@@ -92,7 +92,6 @@ EXPORT_SYMBOL(__memset64); 
EXPORT_SYMBOL(memcpy);

EXPORT_SYMBOL(memmove);

EXPORT_SYMBOL(memchr);

EXPORT_SYMBOL(__memzero);



EXPORT_SYMBOL(mmioset);

EXPORT_SYMBOL(mmiocpy);

arch/arm/kernel/head-common.S

+3 −2
Original line number Diff line number Diff line
@@ -105,8 +105,9 @@ __mmap_switched: 
   ARM(	ldmia	r4!, {r0, r1, sp} )

 THUMB(	ldmia	r4!, {r0, r1, r3} )

 THUMB(	mov	sp, r3 )

	sub	r1, r1, r0

	bl	__memzero			@ clear .bss

	sub	r2, r1, r0

	mov	r1, #0

	bl	memset				@ clear .bss



	ldmia	r4, {r0, r1, r2, r3}

	str	r9, [r0]			@ Save processor ID

arch/arm/lib/Makefile

+1 −1
Original line number Diff line number Diff line
@@ -8,7 +8,7 @@ 
lib-y		:= backtrace.o changebit.o csumipv6.o csumpartial.o   \

		   csumpartialcopy.o csumpartialcopyuser.o clearbit.o \

		   delay.o delay-loop.o findbit.o memchr.o memcpy.o   \

		   memmove.o memset.o memzero.o setbit.o              \

		   memmove.o memset.o setbit.o                        \

		   strchr.o strrchr.o                                 \

		   testchangebit.o testclearbit.o testsetbit.o        \

		   ashldi3.o ashrdi3.o lshrdi3.o muldi3.o             \