x86: introduce native_read_tscp

Targetting paravirt, this patch introduces native_read_tscp, in
place of rdtscp() macro. When in a paravirt guest, this will
involve a function call, and thus, cannot be done in the vdso area.
These users then have to call the native version directly

Signed-off-by: Glauber de Oliveira Costa <gcosta@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

arch/x86/kernel/vsyscall_64.c

@@ -190,7 +190,7 @@ time_t __vsyscall(1) vtime(time_t *t)
 long __vsyscall(2)
 vgetcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *tcache)
 {
-	unsigned int dummy, p;
+	unsigned int p;
 	unsigned long j = 0;
 
 	/* Fast cache - only recompute value once per jiffies and avoid
@@ -205,7 +205,7 @@ vgetcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *tcache)
 		p = tcache->blob[1];
 	} else if (__vgetcpu_mode == VGETCPU_RDTSCP) {
 		/* Load per CPU data from RDTSCP */
-		rdtscp(dummy, dummy, p);
+		native_read_tscp(&p);
 	} else {
 		/* Load per CPU data from GDT */
 		asm("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG));

arch/x86/vdso/vgetcpu.c

@@ -15,11 +15,11 @@
 
 long __vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *unused)
 {
-	unsigned int dummy, p;
+	unsigned int p;
 
 	if (*vdso_vgetcpu_mode == VGETCPU_RDTSCP) {
 		/* Load per CPU data from RDTSCP */
-		rdtscp(dummy, dummy, p);
+		native_read_tscp(&p);
 	} else {
 		/* Load per CPU data from GDT */
 		asm("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG));

include/asm-x86/msr.h

@@ -7,6 +7,27 @@
 # include <linux/types.h>
 #endif
 
+#ifdef __KERNEL__
+#ifndef __ASSEMBLY__
+static inline unsigned long long native_read_tscp(int *aux)
+{
+	unsigned long low, high;
+	asm volatile (".byte 0x0f,0x01,0xf9"
+		      : "=a" (low), "=d" (high), "=c" (*aux));
+	return low | ((u64)high >> 32);
+}
+
+#define rdtscp(low, high, aux)						\
+       do {                                                            \
+		unsigned long long _val = native_read_tscp(&(aux));     \
+		(low) = (u32)_val;                                      \
+		(high) = (u32)(_val >> 32);                             \
+       } while (0)
+
+#define rdtscpll(val, aux) (val) = native_read_tscp(&(aux))
+#endif
+#endif
+
 #ifdef __i386__
 
 #ifdef __KERNEL__
@@ -178,8 +199,6 @@ static inline int wrmsr_safe(u32 __msr, u32 __low, u32 __high)
 #define rdtscl(low) \
      __asm__ __volatile__ ("rdtsc" : "=a" (low) : : "edx")
 
-#define rdtscp(low,high,aux) \
-     __asm__ __volatile__ (".byte 0x0f,0x01,0xf9" : "=a" (low), "=d" (high), "=c" (aux))
 
 #define rdtscll(val) do { \
      unsigned int __a,__d; \
@@ -187,12 +206,6 @@ static inline int wrmsr_safe(u32 __msr, u32 __low, u32 __high)
      (val) = ((unsigned long)__a) | (((unsigned long)__d)<<32); \
 } while(0)
 
-#define rdtscpll(val, aux) do { \
-     unsigned long __a, __d; \
-     __asm__ __volatile__ (".byte 0x0f,0x01,0xf9" : "=a" (__a), "=d" (__d), "=c" (aux)); \
-     (val) = (__d << 32) | __a; \
-} while (0)
-
 #define write_tsc(val1,val2) wrmsr(0x10, val1, val2)
 
 #define write_rdtscp_aux(val) wrmsr(0xc0000103, val, 0)