[PATCH 4/4] optimize and simplify get_cycles_sync()

[Joerg Roedel]

From: Joerg Roedel <joerg.roedel@xxxxxxx>

This patch simplifies the get_cycles_sync() function by removing the
#ifdefs from it. Further it introduces an optimization for AMD
processors. There the RDTSCP instruction is used instead of CPUID;RDTSC
which is helpfull if the kernel runs as a KVM guest. Running as a guest
makes CPUID very expensive because it causes an intercept of the guest.

Signed-off-by: Joerg Roedel <joerg.roedel@xxxxxxx>

-- 
Joerg Roedel
Operating System Research Center
AMD Saxony LLC & Co. KG
diff --git a/include/asm-i386/cpufeature.h b/include/asm-i386/cpufeature.h
index 3f92b94..a9f1f01 100644
--- a/include/asm-i386/cpufeature.h
+++ b/include/asm-i386/cpufeature.h
@@ -49,6 +49,7 @@
 #define X86_FEATURE_MP		(1*32+19) /* MP Capable. */
 #define X86_FEATURE_NX		(1*32+20) /* Execute Disable */
 #define X86_FEATURE_MMXEXT	(1*32+22) /* AMD MMX extensions */
+#define X86_FEATURE_RDTSCP      (1*32+27) /* RDTSCP */
 #define X86_FEATURE_LM		(1*32+29) /* Long Mode (x86-64) */
 #define X86_FEATURE_3DNOWEXT	(1*32+30) /* AMD 3DNow! extensions */
 #define X86_FEATURE_3DNOW	(1*32+31) /* 3DNow! */
diff --git a/include/asm-x86_64/tsc.h b/include/asm-x86_64/tsc.h
index 9a0a368..05df3f6 100644
--- a/include/asm-x86_64/tsc.h
+++ b/include/asm-x86_64/tsc.h
@@ -34,22 +34,15 @@ static inline cycles_t get_cycles(void)
 /* Like get_cycles, but make sure the CPU is synchronized. */
 static __always_inline cycles_t get_cycles_sync(void)
 {
-	unsigned long long ret;
-#ifdef X86_FEATURE_SYNC_RDTSC
-	unsigned eax;
+	unsigned int a, d;
 
-	/*
-	 * Don't do an additional sync on CPUs where we know
-	 * RDTSC is already synchronous:
-	 */
-	alternative_io("cpuid", ASM_NOP2, X86_FEATURE_SYNC_RDTSC,
-			  "=a" (eax), "0" (1) : "ebx","ecx","edx","memory");
-#else
-	sync_core();
-#endif
-	rdtscll(ret);
+	alternative_io_two("cpuid\nrdtsc",
+			   "rdtsc", X86_FEATURE_SYNC_RDTSC,
+			   "rdtscp", X86_FEATURE_RDTSCP,
+			   ASM_OUTPUT2("=a" (a), "=d" (d)),
+			   "0" (1) : "ecx", "memory");
 
-	return ret;
+	return ((unsigned long long)a) | (((unsigned long long)d)<<32);
 }
 
 extern void tsc_init(void);