[PATCH] x86: enable ARCH_USE_BUILTIN_BSWAP

[PATCH] x86: enable ARCH_USE_BUILTIN_BSWAP

[David Woodhouse]

[-- Attachment #1: Type: text/plain, Size: 1185 bytes --]

With -mmovbe enabled (implicit with -march=atom), this allows the
compiler to use the movbe instruction. This doesn't have a significant
effect on code size (unlike on PowerPC), because the movbe instruction
actually takes as many bytes to encode as a simple mov and a bswap. But
for Atom in particular I believe it should give a performance win over
the mov+bswap alternative. That was kind of why movbe was invented in
the first place, after all...

I've done basic functionality testing with IPv6 and Legacy IP, but no
performance testing. The EFI firmware on my test box unfortunately no
longer starts up.

Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Acked-by: H. Peter Anvin <hpa@linux.intel.com>
---
 arch/x86/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 97f8c5a..2ab0f0c 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -115,6 +115,7 @@ config X86
 	select MODULES_USE_ELF_REL if X86_32
 	select MODULES_USE_ELF_RELA if X86_64
 	select CLONE_BACKWARDS if X86_32
+	select ARCH_USE_BUILTIN_BSWAP
 
 config INSTRUCTION_DECODER
 	def_bool y
-- 
1.8.0.1


-- 
dwmw2


[-- Attachment #2: smime.p7s --]
[-- Type: application/x-pkcs7-signature, Size: 6171 bytes --]

[PATCH] x86: require MOVBE feature in cpuid when we use it

[David Woodhouse]

[-- Attachment #1: Type: text/plain, Size: 967 bytes --]

Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>

diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h
index 6c7fc25..5c6e4fb 100644
--- a/arch/x86/include/asm/required-features.h
+++ b/arch/x86/include/asm/required-features.h
@@ -47,6 +47,12 @@
 # define NEED_NOPL	0
 #endif
 
+#ifdef CONFIG_MATOM
+# define NEED_MOVBE	(1<<(X86_FEATURE_MOVBE & 31))
+#else
+# define NEED_MOVBE	0
+#endif
+
 #ifdef CONFIG_X86_64
 #ifdef CONFIG_PARAVIRT
 /* Paravirtualized systems may not have PSE or PGE available */
@@ -80,7 +86,7 @@
 
 #define REQUIRED_MASK2	0
 #define REQUIRED_MASK3	(NEED_NOPL)
-#define REQUIRED_MASK4	0
+#define REQUIRED_MASK4	(NEED_MOVBE)
 #define REQUIRED_MASK5	0
 #define REQUIRED_MASK6	0
 #define REQUIRED_MASK7	0

-- 
David Woodhouse                            Open Source Technology Centre
David.Woodhouse@intel.com                              Intel Corporation




[-- Attachment #2: smime.p7s --]
[-- Type: application/x-pkcs7-signature, Size: 6171 bytes --]