1 files changed, 60 insertions, 11 deletions

diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index 01a300a9700b..4f7f09f50552 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -5,8 +5,64 @@
 #ifndef _ASM_X86_TSC_H
 #define _ASM_X86_TSC_H
 
-#include <asm/processor.h>
+#include <asm/asm.h>
 #include <asm/cpufeature.h>
+#include <asm/processor.h>
+#include <asm/msr.h>
+
+/**
+ * rdtsc() - returns the current TSC without ordering constraints
+ *
+ * rdtsc() returns the result of RDTSC as a 64-bit integer.  The
+ * only ordering constraint it supplies is the ordering implied by
+ * "asm volatile": it will put the RDTSC in the place you expect.  The
+ * CPU can and will speculatively execute that RDTSC, though, so the
+ * results can be non-monotonic if compared on different CPUs.
+ */
+static __always_inline u64 rdtsc(void)
+{
+	EAX_EDX_DECLARE_ARGS(val, low, high);
+
+	asm volatile("rdtsc" : EAX_EDX_RET(val, low, high));
+
+	return EAX_EDX_VAL(val, low, high);
+}
+
+/**
+ * rdtsc_ordered() - read the current TSC in program order
+ *
+ * rdtsc_ordered() returns the result of RDTSC as a 64-bit integer.
+ * It is ordered like a load to a global in-memory counter.  It should
+ * be impossible to observe non-monotonic rdtsc_unordered() behavior
+ * across multiple CPUs as long as the TSC is synced.
+ */
+static __always_inline u64 rdtsc_ordered(void)
+{
+	EAX_EDX_DECLARE_ARGS(val, low, high);
+
+	/*
+	 * The RDTSC instruction is not ordered relative to memory
+	 * access.  The Intel SDM and the AMD APM are both vague on this
+	 * point, but empirically an RDTSC instruction can be
+	 * speculatively executed before prior loads.  An RDTSC
+	 * immediately after an appropriate barrier appears to be
+	 * ordered as a normal load, that is, it provides the same
+	 * ordering guarantees as reading from a global memory location
+	 * that some other imaginary CPU is updating continuously with a
+	 * time stamp.
+	 *
+	 * Thus, use the preferred barrier on the respective CPU, aiming for
+	 * RDTSCP as the default.
+	 */
+	asm volatile(ALTERNATIVE_2("rdtsc",
+				   "lfence; rdtsc", X86_FEATURE_LFENCE_RDTSC,
+				   "rdtscp", X86_FEATURE_RDTSCP)
+			: EAX_EDX_RET(val, low, high)
+			/* RDTSCP clobbers ECX with MSR_TSC_AUX. */
+			:: "ecx");
+
+	return EAX_EDX_VAL(val, low, high);
+}
 
 /*
  * Standard way to access the cycle counter.
@@ -20,20 +76,15 @@ extern void disable_TSC(void);
 
 static inline cycles_t get_cycles(void)
 {
-#ifndef CONFIG_X86_TSC
-	if (!boot_cpu_has(X86_FEATURE_TSC))
+	if (!IS_ENABLED(CONFIG_X86_TSC) &&
+	    !cpu_feature_enabled(X86_FEATURE_TSC))
 		return 0;
-#endif
-
 	return rdtsc();
 }
-
-extern struct system_counterval_t convert_art_to_tsc(u64 art);
-extern struct system_counterval_t convert_art_ns_to_tsc(u64 art_ns);
+#define get_cycles get_cycles
 
 extern void tsc_early_init(void);
 extern void tsc_init(void);
-extern unsigned long calibrate_delay_is_known(void);
 extern void mark_tsc_unstable(char *reason);
 extern int unsynchronized_tsc(void);
 extern int check_tsc_unstable(void);
@@ -56,12 +107,10 @@ extern bool tsc_async_resets;
 #ifdef CONFIG_X86_TSC
 extern bool tsc_store_and_check_tsc_adjust(bool bootcpu);
 extern void tsc_verify_tsc_adjust(bool resume);
-extern void check_tsc_sync_source(int cpu);
 extern void check_tsc_sync_target(void);
 #else
 static inline bool tsc_store_and_check_tsc_adjust(bool bootcpu) { return false; }
 static inline void tsc_verify_tsc_adjust(bool resume) { }
-static inline void check_tsc_sync_source(int cpu) { }
 static inline void check_tsc_sync_target(void) { }
 #endif