x86: Add support for the clflushopt instruction

Add support for the new clflushopt instruction.  This instruction was
announced in the document "Intel Architecture Instruction Set Extensions
Programming Reference" with Ref # 319433-018.

http://download-software.intel.com/sites/default/files/managed/50/1a/319433-018.pdf

[ hpa: changed the feature flag to simply X86_FEATURE_CLFLUSHOPT - if
  that is what we want to report in /proc/cpuinfo anyway... ]

Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Link: http://lkml.kernel.org/r/1393441612-19729-2-git-send-email-ross.zwisler@linux.intel.com
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

2 files changed, 9 insertions, 0 deletions

diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 5f1296872aed..bc507d7640f8 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -221,6 +221,7 @@
 #define X86_FEATURE_RDSEED      (9*32+18) /* The RDSEED instruction */
 #define X86_FEATURE_ADX         (9*32+19) /* The ADCX and ADOX instructions */
 #define X86_FEATURE_SMAP        (9*32+20) /* Supervisor Mode Access Prevention */
+#define X86_FEATURE_CLFLUSHOPT  (9*32+23) /* CLFLUSHOPT instruction */
 #define X86_FEATURE_AVX512PF    (9*32+26) /* AVX-512 Prefetch */
 #define X86_FEATURE_AVX512ER    (9*32+27) /* AVX-512 Exponential and Reciprocal */
 #define X86_FEATURE_AVX512CD    (9*32+28) /* AVX-512 Conflict Detection */
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index 645cad2c95ff..e820c080a4e9 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -191,6 +191,14 @@ static inline void clflush(volatile void *__p)
         asm volatile("clflush %0" : "+m" (*(volatile char __force *)__p));
 }
 
+static inline void clflushopt(volatile void *__p)
+{
+        alternative_io(".byte " __stringify(NOP_DS_PREFIX) "; clflush %P0",
+                       ".byte 0x66; clflush %P0",
+                       X86_FEATURE_CLFLUSHOPT,
+                       "+m" (*(volatile char __force *)__p));
+}
+
 #define nop() asm volatile ("nop")