25 files changed, 59 insertions, 50 deletions

diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c
index ea33236190b1..6a9b96b4624d 100644
--- a/arch/x86/boot/compressed/aslr.c
+++ b/arch/x86/boot/compressed/aslr.c
@@ -82,7 +82,7 @@ static unsigned long get_random_long(void)
 
         if (has_cpuflag(X86_FEATURE_TSC)) {
                 debug_putstr(" RDTSC");
-                raw = native_read_tsc();
+                raw = rdtsc();
 
                 random ^= raw;
                 use_i8254 = false;
diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c
index 972b488ac16a..0340d93c18ca 100644
--- a/arch/x86/entry/vdso/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vclock_gettime.c
@@ -186,7 +186,7 @@ notrace static cycle_t vread_tsc(void)
          * but no one has ever seen it happen.
          */
         rdtsc_barrier();
-        ret = (cycle_t)native_read_tsc();
+        ret = (cycle_t)rdtsc();
 
         last = gtod->cycle_last;
 
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index c89ed6ceed02..ff0c120dafe5 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -109,7 +109,16 @@ notrace static inline int native_write_msr_safe(unsigned int msr,
 extern int rdmsr_safe_regs(u32 regs[8]);
 extern int wrmsr_safe_regs(u32 regs[8]);
 
-static __always_inline unsigned long long native_read_tsc(void)
+/**
+ * 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 unsigned long long rdtsc(void)
 {
         DECLARE_ARGS(val, low, high);
 
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index 2bd69d62c623..5c490db62e32 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -62,7 +62,7 @@ static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift)
 static __always_inline
 u64 pvclock_get_nsec_offset(const struct pvclock_vcpu_time_info *src)
 {
-        u64 delta = native_read_tsc() - src->tsc_timestamp;
+        u64 delta = rdtsc() - src->tsc_timestamp;
         return pvclock_scale_delta(delta, src->tsc_to_system_mul,
                                    src->tsc_shift);
 }
diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h
index bc5fa2af112e..58505f01962f 100644
--- a/arch/x86/include/asm/stackprotector.h
+++ b/arch/x86/include/asm/stackprotector.h
@@ -72,7 +72,7 @@ static __always_inline void boot_init_stack_canary(void)
          * on during the bootup the random pool has true entropy too.
          */
         get_random_bytes(&canary, sizeof(canary));
-        tsc = native_read_tsc();
+        tsc = rdtsc();
         canary += tsc + (tsc << 32UL);
 
         current->stack_canary = canary;
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index b4883902948b..3df7675debcf 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -26,7 +26,7 @@ static inline cycles_t get_cycles(void)
                 return 0;
 #endif
 
-        return native_read_tsc();
+        return rdtsc();
 }
 
 extern void tsc_init(void);
diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c
index 25efa534c4e4..222a57076039 100644
--- a/arch/x86/kernel/apb_timer.c
+++ b/arch/x86/kernel/apb_timer.c
@@ -263,7 +263,7 @@ static int apbt_clocksource_register(void)
 
         /* Verify whether apbt counter works */
         t1 = dw_apb_clocksource_read(clocksource_apbt);
-        start = native_read_tsc();
+        start = rdtsc();
 
         /*
          * We don't know the TSC frequency yet, but waiting for
@@ -273,7 +273,7 @@ static int apbt_clocksource_register(void)
          */
         do {
                 rep_nop();
-                now = native_read_tsc();
+                now = rdtsc();
         } while ((now - start) < 200000UL);
 
         /* APBT is the only always on clocksource, it has to work! */
@@ -390,13 +390,13 @@ unsigned long apbt_quick_calibrate(void)
         old = dw_apb_clocksource_read(clocksource_apbt);
         old += loop;
 
-        t1 = native_read_tsc();
+        t1 = rdtsc();
 
         do {
                 new = dw_apb_clocksource_read(clocksource_apbt);
         } while (new < old);
 
-        t2 = native_read_tsc();
+        t2 = rdtsc();
 
         shift = 5;
         if (unlikely(loop >> shift == 0)) {
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 51af1ed1ae2e..0d71cd9b4a50 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -457,7 +457,7 @@ static int lapic_next_deadline(unsigned long delta,
 {
         u64 tsc;
 
-        tsc = native_read_tsc();
+        tsc = rdtsc();
         wrmsrl(MSR_IA32_TSC_DEADLINE, tsc + (((u64) delta) * TSC_DIVISOR));
         return 0;
 }
@@ -592,7 +592,7 @@ static void __init lapic_cal_handler(struct clock_event_device *dev)
         unsigned long pm = acpi_pm_read_early();
 
         if (cpu_has_tsc)
-                tsc = native_read_tsc();
+                tsc = rdtsc();
 
         switch (lapic_cal_loops++) {
         case 0:
@@ -1209,7 +1209,7 @@ void setup_local_APIC(void)
         long long max_loops = cpu_khz ? cpu_khz : 1000000;
 
         if (cpu_has_tsc)
-                tsc = native_read_tsc();
+                tsc = rdtsc();
 
         if (disable_apic) {
                 disable_ioapic_support();
@@ -1293,7 +1293,7 @@ void setup_local_APIC(void)
                 }
                 if (queued) {
                         if (cpu_has_tsc && cpu_khz) {
-                                ntsc = native_read_tsc();
+                                ntsc = rdtsc();
                                 max_loops = (cpu_khz << 10) - (ntsc - tsc);
                         } else
                                 max_loops--;
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index a69710db6112..51ad2af84a72 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -125,10 +125,10 @@ static void init_amd_k6(struct cpuinfo_x86 *c)
 
                 n = K6_BUG_LOOP;
                 f_vide = vide;
-                d = native_read_tsc();
+                d = rdtsc();
                 while (n--)
                         f_vide();
-                d2 = native_read_tsc();
+                d2 = rdtsc();
                 d = d2-d;
 
                 if (d > 20*K6_BUG_LOOP)
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index a5283d2d0094..96cceccd11b4 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -125,7 +125,7 @@ void mce_setup(struct mce *m)
 {
         memset(m, 0, sizeof(struct mce));
         m->cpu = m->extcpu = smp_processor_id();
-        m->tsc = native_read_tsc();
+        m->tsc = rdtsc();
         /* We hope get_seconds stays lockless */
         m->time = get_seconds();
         m->cpuvendor = boot_cpu_data.x86_vendor;
@@ -1784,7 +1784,7 @@ static void collect_tscs(void *data)
 {
         unsigned long *cpu_tsc = (unsigned long *)data;
 
-        cpu_tsc[smp_processor_id()] = native_read_tsc();
+        cpu_tsc[smp_processor_id()] = rdtsc();
 }
 
 static int mce_apei_read_done;
diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c
index 334a2a9c034d..67315cd0132c 100644
--- a/arch/x86/kernel/espfix_64.c
+++ b/arch/x86/kernel/espfix_64.c
@@ -110,7 +110,7 @@ static void init_espfix_random(void)
          */
         if (!arch_get_random_long(&rand)) {
                 /* The constant is an arbitrary large prime */
-                rand = native_read_tsc();
+                rand = rdtsc();
                 rand *= 0xc345c6b72fd16123UL;
         }
 
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index cc390fe69b71..f75c5908c7a6 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -735,7 +735,7 @@ static int hpet_clocksource_register(void)
 
         /* Verify whether hpet counter works */
         t1 = hpet_readl(HPET_COUNTER);
-        start = native_read_tsc();
+        start = rdtsc();
 
         /*
          * We don't know the TSC frequency yet, but waiting for
@@ -745,7 +745,7 @@ static int hpet_clocksource_register(void)
          */
         do {
                 rep_nop();
-                now = native_read_tsc();
+                now = rdtsc();
         } while ((now - start) < 200000UL);
 
         if (t1 == hpet_readl(HPET_COUNTER)) {
diff --git a/arch/x86/kernel/trace_clock.c b/arch/x86/kernel/trace_clock.c
index bd8f4d41bd56..67efb8c96fc4 100644
--- a/arch/x86/kernel/trace_clock.c
+++ b/arch/x86/kernel/trace_clock.c
@@ -15,7 +15,7 @@ u64 notrace trace_clock_x86_tsc(void)
         u64 ret;
 
         rdtsc_barrier();
-        ret = native_read_tsc();
+        ret = rdtsc();
 
         return ret;
 }
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index e66f5dcaeb63..21d6e04e3e82 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -248,7 +248,7 @@ static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu)
 
         data = cyc2ns_write_begin(cpu);
 
-        tsc_now = native_read_tsc();
+        tsc_now = rdtsc();
         ns_now = cycles_2_ns(tsc_now);
 
         /*
@@ -290,7 +290,7 @@ u64 native_sched_clock(void)
         }
 
         /* read the Time Stamp Counter: */
-        tsc_now = native_read_tsc();
+        tsc_now = rdtsc();
 
         /* return the value in ns */
         return cycles_2_ns(tsc_now);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 954e98a8c2e3..2f0ade48614f 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1172,7 +1172,7 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu)
 
         tsc_deadline = apic->lapic_timer.expired_tscdeadline;
         apic->lapic_timer.expired_tscdeadline = 0;
-        guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu, native_read_tsc());
+        guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu, rdtsc());
         trace_kvm_wait_lapic_expire(vcpu->vcpu_id, guest_tsc - tsc_deadline);
 
         /* __delay is delay_tsc whenever the hardware has TSC, thus always.  */
@@ -1240,7 +1240,7 @@ static void start_apic_timer(struct kvm_lapic *apic)
                 local_irq_save(flags);
 
                 now = apic->lapic_timer.timer.base->get_time();
-                guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu, native_read_tsc());
+                guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu, rdtsc());
                 if (likely(tscdeadline > guest_tsc)) {
                         ns = (tscdeadline - guest_tsc) * 1000000ULL;
                         do_div(ns, this_tsc_khz);
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 602b974a60a6..8dfbad7a2c44 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1080,7 +1080,7 @@ static u64 svm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc)
 {
         u64 tsc;
 
-        tsc = svm_scale_tsc(vcpu, native_read_tsc());
+        tsc = svm_scale_tsc(vcpu, rdtsc());
 
         return target_tsc - tsc;
 }
@@ -3079,7 +3079,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
         switch (msr_info->index) {
         case MSR_IA32_TSC: {
                 msr_info->data = svm->vmcb->control.tsc_offset +
-                        svm_scale_tsc(vcpu, native_read_tsc());
+                        svm_scale_tsc(vcpu, rdtsc());
 
                 break;
         }
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 4fa1ccad7beb..10d69a6df14f 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2236,7 +2236,7 @@ static u64 guest_read_tsc(void)
 {
         u64 host_tsc, tsc_offset;
 
-        host_tsc = native_read_tsc();
+        host_tsc = rdtsc();
         tsc_offset = vmcs_read64(TSC_OFFSET);
         return host_tsc + tsc_offset;
 }
@@ -2317,7 +2317,7 @@ static void vmx_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment, bool ho
 
 static u64 vmx_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc)
 {
-        return target_tsc - native_read_tsc();
+        return target_tsc - rdtsc();
 }
 
 static bool guest_cpuid_has_vmx(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index f771058cfb5c..dfa97139282d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1455,7 +1455,7 @@ static cycle_t read_tsc(void)
          * but no one has ever seen it happen.
          */
         rdtsc_barrier();
-        ret = (cycle_t)native_read_tsc();
+        ret = (cycle_t)rdtsc();
 
         last = pvclock_gtod_data.clock.cycle_last;
 
@@ -1646,7 +1646,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
                 return 1;
         }
         if (!use_master_clock) {
-                host_tsc = native_read_tsc();
+                host_tsc = rdtsc();
                 kernel_ns = get_kernel_ns();
         }
 
@@ -2810,7 +2810,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
         if (unlikely(vcpu->cpu != cpu) || check_tsc_unstable()) {
                 s64 tsc_delta = !vcpu->arch.last_host_tsc ? 0 :
-                                native_read_tsc() - vcpu->arch.last_host_tsc;
+                                rdtsc() - vcpu->arch.last_host_tsc;
                 if (tsc_delta < 0)
                         mark_tsc_unstable("KVM discovered backwards TSC");
                 if (check_tsc_unstable()) {
@@ -2838,7 +2838,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
         kvm_x86_ops->vcpu_put(vcpu);
         kvm_put_guest_fpu(vcpu);
-        vcpu->arch.last_host_tsc = native_read_tsc();
+        vcpu->arch.last_host_tsc = rdtsc();
 }
 
 static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu,
@@ -6623,7 +6623,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
                 hw_breakpoint_restore();
 
         vcpu->arch.last_guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu,
-                                                           native_read_tsc());
+                                                           rdtsc());
 
         vcpu->mode = OUTSIDE_GUEST_MODE;
         smp_wmb();
@@ -7437,7 +7437,7 @@ int kvm_arch_hardware_enable(void)
         if (ret != 0)
                 return ret;
 
-        local_tsc = native_read_tsc();
+        local_tsc = rdtsc();
         stable = !check_tsc_unstable();
         list_for_each_entry(kvm, &vm_list, vm_list) {
                 kvm_for_each_vcpu(i, vcpu, kvm) {
diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c
index 35115f3786a9..f24bc59ab0a0 100644
--- a/arch/x86/lib/delay.c
+++ b/arch/x86/lib/delay.c
@@ -55,10 +55,10 @@ static void delay_tsc(unsigned long __loops)
         preempt_disable();
         cpu = smp_processor_id();
         rdtsc_barrier();
-        bclock = native_read_tsc();
+        bclock = rdtsc();
         for (;;) {
                 rdtsc_barrier();
-                now = native_read_tsc();
+                now = rdtsc();
                 if ((now - bclock) >= loops)
                         break;
 
@@ -80,7 +80,7 @@ static void delay_tsc(unsigned long __loops)
                         loops -= (now - bclock);
                         cpu = smp_processor_id();
                         rdtsc_barrier();
-                        bclock = native_read_tsc();
+                        bclock = rdtsc();
                 }
         }
         preempt_enable();
@@ -100,7 +100,7 @@ void use_tsc_delay(void)
 int read_current_timer(unsigned long *timer_val)
 {
         if (delay_fn == delay_tsc) {
-                *timer_val = native_read_tsc();
+                *timer_val = rdtsc();
                 return 0;
         }
         return -1;
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 15ada47bb720..7c56d7eaa671 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -765,7 +765,7 @@ static inline void intel_pstate_sample(struct cpudata *cpu)
         local_irq_save(flags);
         rdmsrl(MSR_IA32_APERF, aperf);
         rdmsrl(MSR_IA32_MPERF, mperf);
-        tsc = native_read_tsc();
+        tsc = rdtsc();
         local_irq_restore(flags);
 
         cpu->last_sample_time = cpu->sample.time;
diff --git a/drivers/input/gameport/gameport.c b/drivers/input/gameport/gameport.c
index abc0cb22e750..4a2a9e370be7 100644
--- a/drivers/input/gameport/gameport.c
+++ b/drivers/input/gameport/gameport.c
@@ -149,9 +149,9 @@ static int old_gameport_measure_speed(struct gameport *gameport)
 
         for(i = 0; i < 50; i++) {
                 local_irq_save(flags);
-                t1 = native_read_tsc();
+                t1 = rdtsc();
                 for (t = 0; t < 50; t++) gameport_read(gameport);
-                t2 = native_read_tsc();
+                t2 = rdtsc();
                 local_irq_restore(flags);
                 udelay(i * 10);
                 if (t2 - t1 < tx) tx = t2 - t1;
diff --git a/drivers/input/joystick/analog.c b/drivers/input/joystick/analog.c
index f871b4f00056..6f8b084e13d0 100644
--- a/drivers/input/joystick/analog.c
+++ b/drivers/input/joystick/analog.c
@@ -143,7 +143,7 @@ struct analog_port {
 
 #include <linux/i8253.h>
 
-#define GET_TIME(x)     do { if (cpu_has_tsc) x = (unsigned int)native_read_tsc(); else x = get_time_pit(); } while (0)
+#define GET_TIME(x)     do { if (cpu_has_tsc) x = (unsigned int)rdtsc(); else x = get_time_pit(); } while (0)
 #define DELTA(x,y)      (cpu_has_tsc ? ((y) - (x)) : ((x) - (y) + ((x) < (y) ? PIT_TICK_RATE / HZ : 0)))
 #define TIME_NAME       (cpu_has_tsc?"TSC":"PIT")
 static unsigned int get_time_pit(void)
@@ -160,7 +160,7 @@ static unsigned int get_time_pit(void)
         return count;
 }
 #elif defined(__x86_64__)
-#define GET_TIME(x)     do { x = (unsigned int)native_read_tsc(); } while (0)
+#define GET_TIME(x)     do { x = (unsigned int)rdtsc(); } while (0)
 #define DELTA(x,y)      ((y)-(x))
 #define TIME_NAME       "TSC"
 #elif defined(__alpha__) || defined(CONFIG_MN10300) || defined(CONFIG_ARM) || defined(CONFIG_ARM64) || defined(CONFIG_TILE)
diff --git a/drivers/net/hamradio/baycom_epp.c b/drivers/net/hamradio/baycom_epp.c
index 44e5c3b5e0af..72c9f1f352b4 100644
--- a/drivers/net/hamradio/baycom_epp.c
+++ b/drivers/net/hamradio/baycom_epp.c
@@ -638,7 +638,7 @@ static int receive(struct net_device *dev, int cnt)
 #define GETTICK(x)                                                \
 ({                                                                \
         if (cpu_has_tsc)                                          \
-                x = (unsigned int)native_read_tsc();              \
+                x = (unsigned int)rdtsc();                \
 })
 #else /* __i386__ */
 #define GETTICK(x)
diff --git a/drivers/thermal/intel_powerclamp.c b/drivers/thermal/intel_powerclamp.c
index ab13448defcf..2ac0c704bcb8 100644
--- a/drivers/thermal/intel_powerclamp.c
+++ b/drivers/thermal/intel_powerclamp.c
@@ -340,7 +340,7 @@ static bool powerclamp_adjust_controls(unsigned int target_ratio,
 
         /* check result for the last window */
         msr_now = pkg_state_counter();
-        tsc_now = native_read_tsc();
+        tsc_now = rdtsc();
 
         /* calculate pkg cstate vs tsc ratio */
         if (!msr_last || !tsc_last)
@@ -482,7 +482,7 @@ static void poll_pkg_cstate(struct work_struct *dummy)
         u64 val64;
 
         msr_now = pkg_state_counter();
-        tsc_now = native_read_tsc();
+        tsc_now = rdtsc();
         jiffies_now = jiffies;
 
         /* calculate pkg cstate vs tsc ratio */
diff --git a/tools/power/cpupower/debug/kernel/cpufreq-test_tsc.c b/tools/power/cpupower/debug/kernel/cpufreq-test_tsc.c
index f02b0c0bff9b..6ff8383f2941 100644
--- a/tools/power/cpupower/debug/kernel/cpufreq-test_tsc.c
+++ b/tools/power/cpupower/debug/kernel/cpufreq-test_tsc.c
@@ -81,11 +81,11 @@ static int __init cpufreq_test_tsc(void)
 
         printk(KERN_DEBUG "start--> \n");
         then = read_pmtmr();
-        then_tsc = native_read_tsc();
+        then_tsc = rdtsc();
         for (i=0;i<20;i++) {
                 mdelay(100);
                 now = read_pmtmr();
-                now_tsc = native_read_tsc();
+                now_tsc = rdtsc();
                 diff = (now - then) & 0xFFFFFF;
                 diff_tsc = now_tsc - then_tsc;
                 printk(KERN_DEBUG "t1: %08u t2: %08u diff_pmtmr: %08u diff_tsc: %016llu\n", then, now, diff, diff_tsc);