lkml.org 
[lkml]   [2012]   [Aug]   [18]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH 46/74] x86, lto: Disable fancy hweight optimizations for LTO
Date
From: Andi Kleen <ak@linux.intel.com>

The fancy x86 hweight uses different compiler options for the
hweight file. This does not work with LTO. Just disable the optimization
with LTO

Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
arch/x86/Kconfig | 5 +++--
arch/x86/include/asm/arch_hweight.h | 9 +++++++++
2 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 8ec3a1a..9382b09 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -224,8 +224,9 @@ config X86_32_LAZY_GS

config ARCH_HWEIGHT_CFLAGS
string
- default "-fcall-saved-ecx -fcall-saved-edx" if X86_32
- default "-fcall-saved-rdi -fcall-saved-rsi -fcall-saved-rdx -fcall-saved-rcx -fcall-saved-r8 -fcall-saved-r9 -fcall-saved-r10 -fcall-saved-r11" if X86_64
+ default "-fcall-saved-ecx -fcall-saved-edx" if X86_32 && !LTO
+ default "-fcall-saved-rdi -fcall-saved-rsi -fcall-saved-rdx -fcall-saved-rcx -fcall-saved-r8 -fcall-saved-r9 -fcall-saved-r10 -fcall-saved-r11" if X86_64 && !LTO
+ default "" if LTO

config ARCH_CPU_PROBE_RELEASE
def_bool y
diff --git a/arch/x86/include/asm/arch_hweight.h b/arch/x86/include/asm/arch_hweight.h
index 9686c3d..ca80549 100644
--- a/arch/x86/include/asm/arch_hweight.h
+++ b/arch/x86/include/asm/arch_hweight.h
@@ -25,9 +25,14 @@ static inline unsigned int __arch_hweight32(unsigned int w)
{
unsigned int res = 0;

+#ifdef CONFIG_LTO
+ res = __sw_hweight32(w);
+#else
+
asm (ALTERNATIVE("call __sw_hweight32", POPCNT32, X86_FEATURE_POPCNT)
: "="REG_OUT (res)
: REG_IN (w));
+#endif

return res;
}
@@ -46,6 +51,9 @@ static inline unsigned long __arch_hweight64(__u64 w)
{
unsigned long res = 0;

+#ifdef CONFIG_LTO
+ res = __sw_hweight64(w);
+#else
#ifdef CONFIG_X86_32
return __arch_hweight32((u32)w) +
__arch_hweight32((u32)(w >> 32));
@@ -54,6 +62,7 @@ static inline unsigned long __arch_hweight64(__u64 w)
: "="REG_OUT (res)
: REG_IN (w));
#endif /* CONFIG_X86_32 */
+#endif

return res;
}
--
1.7.7.6


\
 
 \ /
  Last update: 2012-08-19 06:01    [W:1.016 / U:0.004 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site