19 files changed, 209 insertions, 202 deletions

diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index c903d358405d..68e10e30fe9b 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -120,7 +120,7 @@ static inline bool apic_is_x2apic_enabled(void)
 {
 	u64 msr;
 
-	if (rdmsrl_safe(MSR_IA32_APICBASE, &msr))
+	if (rdmsrq_safe(MSR_IA32_APICBASE, &msr))
 		return false;
 	return msr & X2APIC_ENABLE;
 }
@@ -209,12 +209,12 @@ static inline void native_apic_msr_write(u32 reg, u32 v)
 	    reg == APIC_LVR)
 		return;
 
-	wrmsr(APIC_BASE_MSR + (reg >> 4), v, 0);
+	wrmsrq(APIC_BASE_MSR + (reg >> 4), v);
 }
 
 static inline void native_apic_msr_eoi(void)
 {
-	__wrmsr(APIC_BASE_MSR + (APIC_EOI >> 4), APIC_EOI_ACK, 0);
+	native_wrmsrq(APIC_BASE_MSR + (APIC_EOI >> 4), APIC_EOI_ACK);
 }
 
 static inline u32 native_apic_msr_read(u32 reg)
@@ -224,20 +224,20 @@ static inline u32 native_apic_msr_read(u32 reg)
 	if (reg == APIC_DFR)
 		return -1;
 
-	rdmsrl(APIC_BASE_MSR + (reg >> 4), msr);
+	rdmsrq(APIC_BASE_MSR + (reg >> 4), msr);
 	return (u32)msr;
 }
 
 static inline void native_x2apic_icr_write(u32 low, u32 id)
 {
-	wrmsrl(APIC_BASE_MSR + (APIC_ICR >> 4), ((__u64) id) << 32 | low);
+	wrmsrq(APIC_BASE_MSR + (APIC_ICR >> 4), ((__u64) id) << 32 | low);
 }
 
 static inline u64 native_x2apic_icr_read(void)
 {
 	unsigned long val;
 
-	rdmsrl(APIC_BASE_MSR + (APIC_ICR >> 4), val);
+	rdmsrq(APIC_BASE_MSR + (APIC_ICR >> 4), val);
 	return val;
 }
 
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index eef0771512de..f963848024a5 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -238,5 +238,24 @@ register unsigned long current_stack_pointer asm(_ASM_SP);
 #define _ASM_EXTABLE_FAULT(from, to)				\
 	_ASM_EXTABLE_TYPE(from, to, EX_TYPE_FAULT)
 
+/*
+ * Both i386 and x86_64 returns 64-bit values in edx:eax for certain
+ * instructions, but GCC's "A" constraint has different meanings.
+ * For i386, "A" means exactly edx:eax, while for x86_64 it
+ * means rax *or* rdx.
+ *
+ * These helpers wrapping these semantic differences save one instruction
+ * clearing the high half of 'low':
+ */
+#ifdef CONFIG_X86_64
+# define EAX_EDX_DECLARE_ARGS(val, low, high)	unsigned long low, high
+# define EAX_EDX_VAL(val, low, high)		((low) | (high) << 32)
+# define EAX_EDX_RET(val, low, high)		"=a" (low), "=d" (high)
+#else
+# define EAX_EDX_DECLARE_ARGS(val, low, high)	u64 val
+# define EAX_EDX_VAL(val, low, high)		(val)
+# define EAX_EDX_RET(val, low, high)		"=A" (val)
+#endif
+
 #endif /* __KERNEL__ */
 #endif /* _ASM_X86_ASM_H */
diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h
index 719d95f1ab5e..363110e6b2e3 100644
--- a/arch/x86/include/asm/debugreg.h
+++ b/arch/x86/include/asm/debugreg.h
@@ -169,7 +169,7 @@ static inline unsigned long get_debugctlmsr(void)
 	if (boot_cpu_data.x86 < 6)
 		return 0;
 #endif
-	rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr);
+	rdmsrq(MSR_IA32_DEBUGCTLMSR, debugctlmsr);
 
 	return debugctlmsr;
 }
@@ -180,7 +180,7 @@ static inline void update_debugctlmsr(unsigned long debugctlmsr)
 	if (boot_cpu_data.x86 < 6)
 		return;
 #endif
-	wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr);
+	wrmsrq(MSR_IA32_DEBUGCTLMSR, debugctlmsr);
 }
 
 #endif /* _ASM_X86_DEBUGREG_H */
diff --git a/arch/x86/include/asm/fred.h b/arch/x86/include/asm/fred.h
index 2a29e5216881..12b34d5b2953 100644
--- a/arch/x86/include/asm/fred.h
+++ b/arch/x86/include/asm/fred.h
@@ -9,6 +9,7 @@
 #include <linux/const.h>
 
 #include <asm/asm.h>
+#include <asm/msr.h>
 #include <asm/trapnr.h>
 
 /*
diff --git a/arch/x86/include/asm/fsgsbase.h b/arch/x86/include/asm/fsgsbase.h
index 02f239569b93..ab2547f97c2c 100644
--- a/arch/x86/include/asm/fsgsbase.h
+++ b/arch/x86/include/asm/fsgsbase.h
@@ -60,7 +60,7 @@ static inline unsigned long x86_fsbase_read_cpu(void)
 	if (boot_cpu_has(X86_FEATURE_FSGSBASE))
 		fsbase = rdfsbase();
 	else
-		rdmsrl(MSR_FS_BASE, fsbase);
+		rdmsrq(MSR_FS_BASE, fsbase);
 
 	return fsbase;
 }
@@ -70,7 +70,7 @@ static inline void x86_fsbase_write_cpu(unsigned long fsbase)
 	if (boot_cpu_has(X86_FEATURE_FSGSBASE))
 		wrfsbase(fsbase);
 	else
-		wrmsrl(MSR_FS_BASE, fsbase);
+		wrmsrq(MSR_FS_BASE, fsbase);
 }
 
 extern unsigned long x86_gsbase_read_cpu_inactive(void);
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 7bc174a1f1cb..9c971f846108 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -34,6 +34,7 @@
 #include <asm/desc.h>
 #include <asm/mtrr.h>
 #include <asm/msr-index.h>
+#include <asm/msr.h>
 #include <asm/asm.h>
 #include <asm/irq_remapping.h>
 #include <asm/kvm_page_track.h>
@@ -2278,7 +2279,7 @@ static inline unsigned long read_msr(unsigned long msr)
 {
 	u64 value;
 
-	rdmsrl(msr, value);
+	rdmsrq(msr, value);
 	return value;
 }
 #endif
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index be7cddc414e4..8b41f26f003b 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -2,6 +2,8 @@
 #ifndef _ASM_X86_MICROCODE_H
 #define _ASM_X86_MICROCODE_H
 
+#include <asm/msr.h>
+
 struct cpu_signature {
 	unsigned int sig;
 	unsigned int pf;
@@ -63,7 +65,7 @@ static inline u32 intel_get_microcode_revision(void)
 {
 	u32 rev, dummy;
 
-	native_wrmsrl(MSR_IA32_UCODE_REV, 0);
+	native_wrmsrq(MSR_IA32_UCODE_REV, 0);
 
 	/* As documented in the SDM: Do a CPUID 1 here */
 	native_cpuid_eax(1);
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index bab5ccfc60a7..778444310cfb 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -8,6 +8,7 @@
 #include <linux/io.h>
 #include <asm/nospec-branch.h>
 #include <asm/paravirt.h>
+#include <asm/msr.h>
 #include <hyperv/hvhdk.h>
 
 /*
@@ -304,7 +305,7 @@ void hv_set_non_nested_msr(unsigned int reg, u64 value);
 
 static __always_inline u64 hv_raw_get_msr(unsigned int reg)
 {
-	return __rdmsr(reg);
+	return native_rdmsrq(reg);
 }
 
 #else /* CONFIG_HYPERV */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index e6134ef2263d..e0d60805b869 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -525,7 +525,7 @@
 #define MSR_HWP_CAPABILITIES		0x00000771
 #define MSR_HWP_REQUEST_PKG		0x00000772
 #define MSR_HWP_INTERRUPT		0x00000773
-#define MSR_HWP_REQUEST 		0x00000774
+#define MSR_HWP_REQUEST			0x00000774
 #define MSR_HWP_STATUS			0x00000777
 
 /* CPUID.6.EAX */
@@ -542,16 +542,16 @@
 #define HWP_LOWEST_PERF(x)		(((x) >> 24) & 0xff)
 
 /* IA32_HWP_REQUEST */
-#define HWP_MIN_PERF(x) 		(x & 0xff)
-#define HWP_MAX_PERF(x) 		((x & 0xff) << 8)
+#define HWP_MIN_PERF(x)			(x & 0xff)
+#define HWP_MAX_PERF(x)			((x & 0xff) << 8)
 #define HWP_DESIRED_PERF(x)		((x & 0xff) << 16)
-#define HWP_ENERGY_PERF_PREFERENCE(x)	(((unsigned long long) x & 0xff) << 24)
+#define HWP_ENERGY_PERF_PREFERENCE(x)	(((u64)x & 0xff) << 24)
 #define HWP_EPP_PERFORMANCE		0x00
 #define HWP_EPP_BALANCE_PERFORMANCE	0x80
 #define HWP_EPP_BALANCE_POWERSAVE	0xC0
 #define HWP_EPP_POWERSAVE		0xFF
-#define HWP_ACTIVITY_WINDOW(x)		((unsigned long long)(x & 0xff3) << 32)
-#define HWP_PACKAGE_CONTROL(x)		((unsigned long long)(x & 0x1) << 42)
+#define HWP_ACTIVITY_WINDOW(x)		((u64)(x & 0xff3) << 32)
+#define HWP_PACKAGE_CONTROL(x)		((u64)(x & 0x1) << 42)
 
 /* IA32_HWP_STATUS */
 #define HWP_GUARANTEED_CHANGE(x)	(x & 0x1)
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 9397a319d165..a9ce56fc8785 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -12,6 +12,7 @@
 #include <uapi/asm/msr.h>
 #include <asm/shared/msr.h>
 
+#include <linux/types.h>
 #include <linux/percpu.h>
 
 struct msr_info {
@@ -37,23 +38,6 @@ struct saved_msrs {
 };
 
 /*
- * both i386 and x86_64 returns 64-bit value in edx:eax, but gcc's "A"
- * constraint has different meanings. For i386, "A" means exactly
- * edx:eax, while for x86_64 it doesn't mean rdx:rax or edx:eax. Instead,
- * it means rax *or* rdx.
- */
-#ifdef CONFIG_X86_64
-/* Using 64-bit values saves one instruction clearing the high half of low */
-#define DECLARE_ARGS(val, low, high)	unsigned long low, high
-#define EAX_EDX_VAL(val, low, high)	((low) | (high) << 32)
-#define EAX_EDX_RET(val, low, high)	"=a" (low), "=d" (high)
-#else
-#define DECLARE_ARGS(val, low, high)	unsigned long long val
-#define EAX_EDX_VAL(val, low, high)	(val)
-#define EAX_EDX_RET(val, low, high)	"=A" (val)
-#endif
-
-/*
  * Be very careful with includes. This header is prone to include loops.
  */
 #include <asm/atomic.h>
@@ -63,13 +47,13 @@ struct saved_msrs {
 DECLARE_TRACEPOINT(read_msr);
 DECLARE_TRACEPOINT(write_msr);
 DECLARE_TRACEPOINT(rdpmc);
-extern void do_trace_write_msr(unsigned int msr, u64 val, int failed);
-extern void do_trace_read_msr(unsigned int msr, u64 val, int failed);
-extern void do_trace_rdpmc(unsigned int msr, u64 val, int failed);
+extern void do_trace_write_msr(u32 msr, u64 val, int failed);
+extern void do_trace_read_msr(u32 msr, u64 val, int failed);
+extern void do_trace_rdpmc(u32 msr, u64 val, int failed);
 #else
-static inline void do_trace_write_msr(unsigned int msr, u64 val, int failed) {}
-static inline void do_trace_read_msr(unsigned int msr, u64 val, int failed) {}
-static inline void do_trace_rdpmc(unsigned int msr, u64 val, int failed) {}
+static inline void do_trace_write_msr(u32 msr, u64 val, int failed) {}
+static inline void do_trace_read_msr(u32 msr, u64 val, int failed) {}
+static inline void do_trace_rdpmc(u32 msr, u64 val, int failed) {}
 #endif
 
 /*
@@ -79,9 +63,9 @@ static inline void do_trace_rdpmc(unsigned int msr, u64 val, int failed) {}
  * think of extending them - you will be slapped with a stinking trout or a frozen
  * shark will reach you, wherever you are! You've been warned.
  */
-static __always_inline unsigned long long __rdmsr(unsigned int msr)
+static __always_inline u64 __rdmsr(u32 msr)
 {
-	DECLARE_ARGS(val, low, high);
+	EAX_EDX_DECLARE_ARGS(val, low, high);
 
 	asm volatile("1: rdmsr\n"
 		     "2:\n"
@@ -91,12 +75,12 @@ static __always_inline unsigned long long __rdmsr(unsigned int msr)
 	return EAX_EDX_VAL(val, low, high);
 }
 
-static __always_inline void __wrmsr(unsigned int msr, u32 low, u32 high)
+static __always_inline void __wrmsrq(u32 msr, u64 val)
 {
 	asm volatile("1: wrmsr\n"
 		     "2:\n"
 		     _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_WRMSR)
-		     : : "c" (msr), "a"(low), "d" (high) : "memory");
+		     : : "c" (msr), "a" ((u32)val), "d" ((u32)(val >> 32)) : "memory");
 }
 
 #define native_rdmsr(msr, val1, val2)			\
@@ -106,16 +90,20 @@ do {							\
 	(void)((val2) = (u32)(__val >> 32));		\
 } while (0)
 
+static __always_inline u64 native_rdmsrq(u32 msr)
+{
+	return __rdmsr(msr);
+}
+
 #define native_wrmsr(msr, low, high)			\
-	__wrmsr(msr, low, high)
+	__wrmsrq((msr), (u64)(high) << 32 | (low))
 
-#define native_wrmsrl(msr, val)				\
-	__wrmsr((msr), (u32)((u64)(val)),		\
-		       (u32)((u64)(val) >> 32))
+#define native_wrmsrq(msr, val)				\
+	__wrmsrq((msr), (val))
 
-static inline unsigned long long native_read_msr(unsigned int msr)
+static inline u64 native_read_msr(u32 msr)
 {
-	unsigned long long val;
+	u64 val;
 
 	val = __rdmsr(msr);
 
@@ -125,34 +113,35 @@ static inline unsigned long long native_read_msr(unsigned int msr)
 	return val;
 }
 
-static inline unsigned long long native_read_msr_safe(unsigned int msr,
-						      int *err)
+static inline int native_read_msr_safe(u32 msr, u64 *p)
 {
-	DECLARE_ARGS(val, low, high);
+	int err;
+	EAX_EDX_DECLARE_ARGS(val, low, high);
 
 	asm volatile("1: rdmsr ; xor %[err],%[err]\n"
 		     "2:\n\t"
 		     _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_RDMSR_SAFE, %[err])
-		     : [err] "=r" (*err), EAX_EDX_RET(val, low, high)
+		     : [err] "=r" (err), EAX_EDX_RET(val, low, high)
 		     : "c" (msr));
 	if (tracepoint_enabled(read_msr))
-		do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), *err);
-	return EAX_EDX_VAL(val, low, high);
+		do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), err);
+
+	*p = EAX_EDX_VAL(val, low, high);
+
+	return err;
 }
 
 /* Can be uninlined because referenced by paravirt */
-static inline void notrace
-native_write_msr(unsigned int msr, u32 low, u32 high)
+static inline void notrace native_write_msr(u32 msr, u64 val)
 {
-	__wrmsr(msr, low, high);
+	native_wrmsrq(msr, val);
 
 	if (tracepoint_enabled(write_msr))
-		do_trace_write_msr(msr, ((u64)high << 32 | low), 0);
+		do_trace_write_msr(msr, val, 0);
 }
 
 /* Can be uninlined because referenced by paravirt */
-static inline int notrace
-native_write_msr_safe(unsigned int msr, u32 low, u32 high)
+static inline int notrace native_write_msr_safe(u32 msr, u64 val)
 {
 	int err;
 
@@ -160,73 +149,19 @@ native_write_msr_safe(unsigned int msr, u32 low, u32 high)
 		     "2:\n\t"
 		     _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_WRMSR_SAFE, %[err])
 		     : [err] "=a" (err)
-		     : "c" (msr), "0" (low), "d" (high)
+		     : "c" (msr), "0" ((u32)val), "d" ((u32)(val >> 32))
 		     : "memory");
 	if (tracepoint_enabled(write_msr))
-		do_trace_write_msr(msr, ((u64)high << 32 | low), err);
+		do_trace_write_msr(msr, val, err);
 	return err;
 }
 
 extern int rdmsr_safe_regs(u32 regs[8]);
 extern int wrmsr_safe_regs(u32 regs[8]);
 
-/**
- * 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)
+static inline u64 native_read_pmc(int counter)
 {
-	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 unsigned long long rdtsc_ordered(void)
-{
-	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);
-}
-
-static inline unsigned long long native_read_pmc(int counter)
-{
-	DECLARE_ARGS(val, low, high);
+	EAX_EDX_DECLARE_ARGS(val, low, high);
 
 	asm volatile("rdpmc" : EAX_EDX_RET(val, low, high) : "c" (counter));
 	if (tracepoint_enabled(rdpmc))
@@ -251,51 +186,44 @@ do {								\
 	(void)((high) = (u32)(__val >> 32));			\
 } while (0)
 
-static inline void wrmsr(unsigned int msr, u32 low, u32 high)
+static inline void wrmsr(u32 msr, u32 low, u32 high)
 {
-	native_write_msr(msr, low, high);
+	native_write_msr(msr, (u64)high << 32 | low);
 }
 
-#define rdmsrl(msr, val)			\
+#define rdmsrq(msr, val)			\
 	((val) = native_read_msr((msr)))
 
-static inline void wrmsrl(unsigned int msr, u64 val)
+static inline void wrmsrq(u32 msr, u64 val)
 {
-	native_write_msr(msr, (u32)(val & 0xffffffffULL), (u32)(val >> 32));
+	native_write_msr(msr, val);
 }
 
 /* wrmsr with exception handling */
-static inline int wrmsr_safe(unsigned int msr, u32 low, u32 high)
+static inline int wrmsrq_safe(u32 msr, u64 val)
 {
-	return native_write_msr_safe(msr, low, high);
+	return native_write_msr_safe(msr, val);
 }
 
 /* rdmsr with exception handling */
 #define rdmsr_safe(msr, low, high)				\
 ({								\
-	int __err;						\
-	u64 __val = native_read_msr_safe((msr), &__err);	\
+	u64 __val;						\
+	int __err = native_read_msr_safe((msr), &__val);	\
 	(*low) = (u32)__val;					\
 	(*high) = (u32)(__val >> 32);				\
 	__err;							\
 })
 
-static inline int rdmsrl_safe(unsigned int msr, unsigned long long *p)
+static inline int rdmsrq_safe(u32 msr, u64 *p)
 {
-	int err;
-
-	*p = native_read_msr_safe(msr, &err);
-	return err;
+	return native_read_msr_safe(msr, p);
 }
 
-#define rdpmc(counter, low, high)			\
-do {							\
-	u64 _l = native_read_pmc((counter));		\
-	(low)  = (u32)_l;				\
-	(high) = (u32)(_l >> 32);			\
-} while (0)
-
-#define rdpmcl(counter, val) ((val) = native_read_pmc(counter))
+static __always_inline u64 rdpmc(int counter)
+{
+	return native_read_pmc(counter);
+}
 
 #endif	/* !CONFIG_PARAVIRT_XXL */
 
@@ -315,11 +243,11 @@ static __always_inline void wrmsrns(u32 msr, u64 val)
 }
 
 /*
- * 64-bit version of wrmsr_safe():
+ * Dual u32 version of wrmsrq_safe():
  */
-static inline int wrmsrl_safe(u32 msr, u64 val)
+static inline int wrmsr_safe(u32 msr, u32 low, u32 high)
 {
-	return wrmsr_safe(msr, (u32)val,  (u32)(val >> 32));
+	return wrmsrq_safe(msr, (u64)high << 32 | low);
 }
 
 struct msr __percpu *msrs_alloc(void);
@@ -330,14 +258,14 @@ int msr_clear_bit(u32 msr, u8 bit);
 #ifdef CONFIG_SMP
 int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h);
 int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h);
-int rdmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 *q);
-int wrmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 q);
+int rdmsrq_on_cpu(unsigned int cpu, u32 msr_no, u64 *q);
+int wrmsrq_on_cpu(unsigned int cpu, u32 msr_no, u64 q);
 void rdmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr __percpu *msrs);
 void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr __percpu *msrs);
 int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h);
 int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h);
-int rdmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q);
-int wrmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 q);
+int rdmsrq_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q);
+int wrmsrq_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 q);
 int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]);
 int wrmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]);
 #else  /*  CONFIG_SMP  */
@@ -351,14 +279,14 @@ static inline int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
 	wrmsr(msr_no, l, h);
 	return 0;
 }
-static inline int rdmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 *q)
+static inline int rdmsrq_on_cpu(unsigned int cpu, u32 msr_no, u64 *q)
 {
-	rdmsrl(msr_no, *q);
+	rdmsrq(msr_no, *q);
 	return 0;
 }
-static inline int wrmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 q)
+static inline int wrmsrq_on_cpu(unsigned int cpu, u32 msr_no, u64 q)
 {
-	wrmsrl(msr_no, q);
+	wrmsrq(msr_no, q);
 	return 0;
 }
 static inline void rdmsr_on_cpus(const struct cpumask *m, u32 msr_no,
@@ -380,13 +308,13 @@ static inline int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
 {
 	return wrmsr_safe(msr_no, l, h);
 }
-static inline int rdmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q)
+static inline int rdmsrq_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q)
 {
-	return rdmsrl_safe(msr_no, q);
+	return rdmsrq_safe(msr_no, q);
 }
-static inline int wrmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 q)
+static inline int wrmsrq_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 q)
 {
-	return wrmsrl_safe(msr_no, q);
+	return wrmsrq_safe(msr_no, q);
 }
 static inline int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8])
 {
@@ -397,5 +325,10 @@ static inline int wrmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8])
 	return wrmsr_safe_regs(regs);
 }
 #endif  /* CONFIG_SMP */
+
+/* Compatibility wrappers: */
+#define rdmsrl(msr, val) rdmsrq(msr, val)
+#define wrmsrl(msr, val) wrmsrq(msr, val)
+
 #endif /* __ASSEMBLER__ */
 #endif /* _ASM_X86_MSR_H */
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index c4c23190925c..03f680d1057a 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -175,26 +175,24 @@ static inline void __write_cr4(unsigned long x)
 	PVOP_VCALL1(cpu.write_cr4, x);
 }
 
-static inline u64 paravirt_read_msr(unsigned msr)
+static inline u64 paravirt_read_msr(u32 msr)
 {
 	return PVOP_CALL1(u64, cpu.read_msr, msr);
 }
 
-static inline void paravirt_write_msr(unsigned msr,
-				      unsigned low, unsigned high)
+static inline void paravirt_write_msr(u32 msr, u64 val)
 {
-	PVOP_VCALL3(cpu.write_msr, msr, low, high);
+	PVOP_VCALL2(cpu.write_msr, msr, val);
 }
 
-static inline u64 paravirt_read_msr_safe(unsigned msr, int *err)
+static inline int paravirt_read_msr_safe(u32 msr, u64 *val)
 {
-	return PVOP_CALL2(u64, cpu.read_msr_safe, msr, err);
+	return PVOP_CALL2(int, cpu.read_msr_safe, msr, val);
 }
 
-static inline int paravirt_write_msr_safe(unsigned msr,
-					  unsigned low, unsigned high)
+static inline int paravirt_write_msr_safe(u32 msr, u64 val)
 {
-	return PVOP_CALL3(int, cpu.write_msr_safe, msr, low, high);
+	return PVOP_CALL2(int, cpu.write_msr_safe, msr, val);
 }
 
 #define rdmsr(msr, val1, val2)			\
@@ -204,55 +202,46 @@ do {						\
 	val2 = _l >> 32;			\
 } while (0)
 
-#define wrmsr(msr, val1, val2)			\
-do {						\
-	paravirt_write_msr(msr, val1, val2);	\
-} while (0)
+static __always_inline void wrmsr(u32 msr, u32 low, u32 high)
+{
+	paravirt_write_msr(msr, (u64)high << 32 | low);
+}
 
-#define rdmsrl(msr, val)			\
+#define rdmsrq(msr, val)			\
 do {						\
 	val = paravirt_read_msr(msr);		\
 } while (0)
 
-static inline void wrmsrl(unsigned msr, u64 val)
+static inline void wrmsrq(u32 msr, u64 val)
 {
-	wrmsr(msr, (u32)val, (u32)(val>>32));
+	paravirt_write_msr(msr, val);
 }
 
-#define wrmsr_safe(msr, a, b)	paravirt_write_msr_safe(msr, a, b)
+static inline int wrmsrq_safe(u32 msr, u64 val)
+{
+	return paravirt_write_msr_safe(msr, val);
+}
 
 /* rdmsr with exception handling */
 #define rdmsr_safe(msr, a, b)				\
 ({							\
-	int _err;					\
-	u64 _l = paravirt_read_msr_safe(msr, &_err);	\
+	u64 _l;						\
+	int _err = paravirt_read_msr_safe((msr), &_l);	\
 	(*a) = (u32)_l;					\
-	(*b) = _l >> 32;				\
+	(*b) = (u32)(_l >> 32);				\
 	_err;						\
 })
 
-static inline int rdmsrl_safe(unsigned msr, unsigned long long *p)
+static __always_inline int rdmsrq_safe(u32 msr, u64 *p)
 {
-	int err;
-
-	*p = paravirt_read_msr_safe(msr, &err);
-	return err;
+	return paravirt_read_msr_safe(msr, p);
 }
 
-static inline unsigned long long paravirt_read_pmc(int counter)
+static __always_inline u64 rdpmc(int counter)
 {
 	return PVOP_CALL1(u64, cpu.read_pmc, counter);
 }
 
-#define rdpmc(counter, low, high)		\
-do {						\
-	u64 _l = paravirt_read_pmc(counter);	\
-	low = (u32)_l;				\
-	high = _l >> 32;			\
-} while (0)
-
-#define rdpmcl(counter, val) ((val) = paravirt_read_pmc(counter))
-
 static inline void paravirt_alloc_ldt(struct desc_struct *ldt, unsigned entries)
 {
 	PVOP_VCALL2(cpu.alloc_ldt, ldt, entries);
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 631c306ce1ff..b08b9d3122d6 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -91,15 +91,15 @@ struct pv_cpu_ops {
 		      unsigned int *ecx, unsigned int *edx);
 
 	/* Unsafe MSR operations.  These will warn or panic on failure. */
-	u64 (*read_msr)(unsigned int msr);
-	void (*write_msr)(unsigned int msr, unsigned low, unsigned high);
+	u64 (*read_msr)(u32 msr);
+	void (*write_msr)(u32 msr, u64 val);
 
 	/*
 	 * Safe MSR operations.
-	 * read sets err to 0 or -EIO.  write returns 0 or -EIO.
+	 * Returns 0 or -EIO.
 	 */
-	u64 (*read_msr_safe)(unsigned int msr, int *err);
-	int (*write_msr_safe)(unsigned int msr, unsigned low, unsigned high);
+	int (*read_msr_safe)(u32 msr, u64 *val);
+	int (*write_msr_safe)(u32 msr, u64 val);
 
 	u64 (*read_pmc)(int counter);
 
diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h
index 011bf67a1866..bd6afe805cf6 100644
--- a/arch/x86/include/asm/resctrl.h
+++ b/arch/x86/include/asm/resctrl.h
@@ -9,6 +9,8 @@
 #include <linux/resctrl_types.h>
 #include <linux/sched.h>
 
+#include <asm/msr.h>
+
 /*
  * This value can never be a valid CLOSID, and is used when mapping a
  * (closid, rmid) pair to an index and back. On x86 only the RMID is
diff --git a/arch/x86/include/asm/sev-internal.h b/arch/x86/include/asm/sev-internal.h
index b7232081f8f7..3dfd306d1c9e 100644
--- a/arch/x86/include/asm/sev-internal.h
+++ b/arch/x86/include/asm/sev-internal.h
@@ -84,7 +84,7 @@ int svsm_perform_call_protocol(struct svsm_call *call);
 
 static inline u64 sev_es_rd_ghcb_msr(void)
 {
-	return __rdmsr(MSR_AMD64_SEV_ES_GHCB);
+	return native_rdmsrq(MSR_AMD64_SEV_ES_GHCB);
 }
 
 static __always_inline void sev_es_wr_ghcb_msr(u64 val)
diff --git a/arch/x86/include/asm/spec-ctrl.h b/arch/x86/include/asm/spec-ctrl.h
index 658b690b2ccb..00b7e0398210 100644
--- a/arch/x86/include/asm/spec-ctrl.h
+++ b/arch/x86/include/asm/spec-ctrl.h
@@ -84,7 +84,7 @@ static inline u64 ssbd_tif_to_amd_ls_cfg(u64 tifn)
 static __always_inline void __update_spec_ctrl(u64 val)
 {
 	__this_cpu_write(x86_spec_ctrl_current, val);
-	native_wrmsrl(MSR_IA32_SPEC_CTRL, val);
+	native_wrmsrq(MSR_IA32_SPEC_CTRL, val);
 }
 
 #ifdef CONFIG_SMP
diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h
index d8416b3bf832..e8e5aab06255 100644
--- a/arch/x86/include/asm/suspend_32.h
+++ b/arch/x86/include/asm/suspend_32.h
@@ -9,6 +9,7 @@
 
 #include <asm/desc.h>
 #include <asm/fpu/api.h>
+#include <asm/msr.h>
 
 /* image of the saved processor state */
 struct saved_context {
diff --git a/arch/x86/include/asm/suspend_64.h b/arch/x86/include/asm/suspend_64.h
index 54df06687d83..b512f9665f78 100644
--- a/arch/x86/include/asm/suspend_64.h
+++ b/arch/x86/include/asm/suspend_64.h
@@ -9,6 +9,7 @@
 
 #include <asm/desc.h>
 #include <asm/fpu/api.h>
+#include <asm/msr.h>
 
 /*
  * Image of the saved processor state, used by the low level ACPI suspend to
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
index 75248546403d..499b1c15cc8b 100644
--- a/arch/x86/include/asm/switch_to.h
+++ b/arch/x86/include/asm/switch_to.h
@@ -52,6 +52,8 @@ do {									\
 } while (0)
 
 #ifdef CONFIG_X86_32
+#include <asm/msr.h>
+
 static inline void refresh_sysenter_cs(struct thread_struct *thread)
 {
 	/* Only happens when SEP is enabled, no need to test "SEP"arately: */
@@ -59,7 +61,7 @@ static inline void refresh_sysenter_cs(struct thread_struct *thread)
 		return;
 
 	this_cpu_write(cpu_tss_rw.x86_tss.ss1, thread->sysenter_cs);
-	wrmsr(MSR_IA32_SYSENTER_CS, thread->sysenter_cs, 0);
+	wrmsrq(MSR_IA32_SYSENTER_CS, thread->sysenter_cs);
 }
 #endif
 
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index 94408a784c8e..4f7f09f50552 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -5,10 +5,65 @@
 #ifndef _ASM_X86_TSC_H
 #define _ASM_X86_TSC_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.
  */