summaryrefslogtreecommitdiffstats
path: root/arch/arm/kernel
diff options
context:
space:
mode:
authorNicolas Pitre <nicolas.pitre@linaro.org>2018-01-19 18:17:46 +0100
committerRussell King <rmk+kernel@armlinux.org.uk>2018-01-21 15:37:56 +0000
commitff5fdafc9e9702846480e0cea55ba861f72140a2 (patch)
tree28531d5acbc851bf5f210062bc9d0e08f1fee85e /arch/arm/kernel
parentec80eb467171b511635b9e3086fec357f79afe3b (diff)
downloadlinux-ff5fdafc9e9702846480e0cea55ba861f72140a2.tar.bz2
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: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Nicolas Pitre <nico@linaro.org> Acked-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Acked-by: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Diffstat (limited to 'arch/arm/kernel')
-rw-r--r--arch/arm/kernel/armksyms.c1
-rw-r--r--arch/arm/kernel/head-common.S5
2 files changed, 3 insertions, 3 deletions
diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c
index 5266fd9ad6b4..783fbb4de5f9 100644
--- a/arch/arm/kernel/armksyms.c
+++ b/arch/arm/kernel/armksyms.c
@@ -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);
diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S
index 21dde771a7dd..6e0375e7db05 100644
--- a/arch/arm/kernel/head-common.S
+++ b/arch/arm/kernel/head-common.S
@@ -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