Merge branch 'x86/msr' into x86/core, to resolve conflicts

 Conflicts:
	arch/x86/boot/startup/sme.c
	arch/x86/coco/sev/core.c
	arch/x86/kernel/fpu/core.c
	arch/x86/kernel/fpu/xstate.c

 Semantic conflict:
	arch/x86/include/asm/sev-internal.h

Signed-off-by: Ingo Molnar <mingo@kernel.org>

28 files changed, 247 insertions, 230 deletions

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 2b36379ff675..d8365c4d9057 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -21,6 +21,7 @@
 #include <asm/delay.h>
 #include <asm/debugreg.h>
 #include <asm/resctrl.h>
+#include <asm/msr.h>
 #include <asm/sev.h>
 
 #ifdef CONFIG_X86_64
@@ -31,7 +32,7 @@
 
 u16 invlpgb_count_max __ro_after_init;
 
-static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
+static inline int rdmsrq_amd_safe(unsigned msr, u64 *p)
 {
 	u32 gprs[8] = { 0 };
 	int err;
@@ -49,7 +50,7 @@ static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
 	return err;
 }
 
-static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val)
+static inline int wrmsrq_amd_safe(unsigned msr, u64 val)
 {
 	u32 gprs[8] = { 0 };
 
@@ -383,7 +384,7 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
 		    (c->x86 == 0x10 && c->x86_model >= 0x2)) {
 			u64 val;
 
-			rdmsrl(MSR_K7_HWCR, val);
+			rdmsrq(MSR_K7_HWCR, val);
 			if (!(val & BIT(24)))
 				pr_warn(FW_BUG "TSC doesn't count with P0 frequency!\n");
 		}
@@ -422,7 +423,7 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
 		 * Try to cache the base value so further operations can
 		 * avoid RMW. If that faults, do not enable SSBD.
 		 */
-		if (!rdmsrl_safe(MSR_AMD64_LS_CFG, &x86_amd_ls_cfg_base)) {
+		if (!rdmsrq_safe(MSR_AMD64_LS_CFG, &x86_amd_ls_cfg_base)) {
 			setup_force_cpu_cap(X86_FEATURE_LS_CFG_SSBD);
 			setup_force_cpu_cap(X86_FEATURE_SSBD);
 			x86_amd_ls_cfg_ssbd_mask = 1ULL << bit;
@@ -508,7 +509,7 @@ static void early_detect_mem_encrypt(struct cpuinfo_x86 *c)
 	 */
 	if (cpu_has(c, X86_FEATURE_SME) || cpu_has(c, X86_FEATURE_SEV)) {
 		/* Check if memory encryption is enabled */
-		rdmsrl(MSR_AMD64_SYSCFG, msr);
+		rdmsrq(MSR_AMD64_SYSCFG, msr);
 		if (!(msr & MSR_AMD64_SYSCFG_MEM_ENCRYPT))
 			goto clear_all;
 
@@ -525,7 +526,7 @@ static void early_detect_mem_encrypt(struct cpuinfo_x86 *c)
 		if (!sme_me_mask)
 			setup_clear_cpu_cap(X86_FEATURE_SME);
 
-		rdmsrl(MSR_K7_HWCR, msr);
+		rdmsrq(MSR_K7_HWCR, msr);
 		if (!(msr & MSR_K7_HWCR_SMMLOCK))
 			goto clear_sev;
 
@@ -612,7 +613,7 @@ static void early_init_amd(struct cpuinfo_x86 *c)
 	if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && !cpu_has(c, X86_FEATURE_IBPB_BRTYPE)) {
 		if (c->x86 == 0x17 && boot_cpu_has(X86_FEATURE_AMD_IBPB))
 			setup_force_cpu_cap(X86_FEATURE_IBPB_BRTYPE);
-		else if (c->x86 >= 0x19 && !wrmsrl_safe(MSR_IA32_PRED_CMD, PRED_CMD_SBPB)) {
+		else if (c->x86 >= 0x19 && !wrmsrq_safe(MSR_IA32_PRED_CMD, PRED_CMD_SBPB)) {
 			setup_force_cpu_cap(X86_FEATURE_IBPB_BRTYPE);
 			setup_force_cpu_cap(X86_FEATURE_SBPB);
 		}
@@ -636,9 +637,9 @@ static void init_amd_k8(struct cpuinfo_x86 *c)
 	 */
 	if (c->x86_model < 0x14 && cpu_has(c, X86_FEATURE_LAHF_LM) && !cpu_has(c, X86_FEATURE_HYPERVISOR)) {
 		clear_cpu_cap(c, X86_FEATURE_LAHF_LM);
-		if (!rdmsrl_amd_safe(0xc001100d, &value)) {
+		if (!rdmsrq_amd_safe(0xc001100d, &value)) {
 			value &= ~BIT_64(32);
-			wrmsrl_amd_safe(0xc001100d, value);
+			wrmsrq_amd_safe(0xc001100d, value);
 		}
 	}
 
@@ -788,9 +789,9 @@ static void init_amd_bd(struct cpuinfo_x86 *c)
 	 * Disable it on the affected CPUs.
 	 */
 	if ((c->x86_model >= 0x02) && (c->x86_model < 0x20)) {
-		if (!rdmsrl_safe(MSR_F15H_IC_CFG, &value) && !(value & 0x1E)) {
+		if (!rdmsrq_safe(MSR_F15H_IC_CFG, &value) && !(value & 0x1E)) {
 			value |= 0x1E;
-			wrmsrl_safe(MSR_F15H_IC_CFG, value);
+			wrmsrq_safe(MSR_F15H_IC_CFG, value);
 		}
 	}
 
@@ -839,9 +840,9 @@ void init_spectral_chicken(struct cpuinfo_x86 *c)
 	 * suppresses non-branch predictions.
 	 */
 	if (!cpu_has(c, X86_FEATURE_HYPERVISOR)) {
-		if (!rdmsrl_safe(MSR_ZEN2_SPECTRAL_CHICKEN, &value)) {
+		if (!rdmsrq_safe(MSR_ZEN2_SPECTRAL_CHICKEN, &value)) {
 			value |= MSR_ZEN2_SPECTRAL_CHICKEN_BIT;
-			wrmsrl_safe(MSR_ZEN2_SPECTRAL_CHICKEN, value);
+			wrmsrq_safe(MSR_ZEN2_SPECTRAL_CHICKEN, value);
 		}
 	}
 #endif
@@ -1025,7 +1026,7 @@ static void init_amd(struct cpuinfo_x86 *c)
 	init_amd_cacheinfo(c);
 
 	if (cpu_has(c, X86_FEATURE_SVM)) {
-		rdmsrl(MSR_VM_CR, vm_cr);
+		rdmsrq(MSR_VM_CR, vm_cr);
 		if (vm_cr & SVM_VM_CR_SVM_DIS_MASK) {
 			pr_notice_once("SVM disabled (by BIOS) in MSR_VM_CR\n");
 			clear_cpu_cap(c, X86_FEATURE_SVM);
@@ -1206,7 +1207,7 @@ void amd_set_dr_addr_mask(unsigned long mask, unsigned int dr)
 	if (per_cpu(amd_dr_addr_mask, cpu)[dr] == mask)
 		return;
 
-	wrmsr(amd_msr_dr_addr_masks[dr], mask, 0);
+	wrmsrq(amd_msr_dr_addr_masks[dr], mask);
 	per_cpu(amd_dr_addr_mask, cpu)[dr] = mask;
 }
 
diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c
index 6cf31a1649c4..a315b0627dfb 100644
--- a/arch/x86/kernel/cpu/aperfmperf.c
+++ b/arch/x86/kernel/cpu/aperfmperf.c
@@ -20,6 +20,7 @@
 #include <asm/cpu.h>
 #include <asm/cpu_device_id.h>
 #include <asm/intel-family.h>
+#include <asm/msr.h>
 
 #include "cpu.h"
 
@@ -40,8 +41,8 @@ static void init_counter_refs(void)
 {
 	u64 aperf, mperf;
 
-	rdmsrl(MSR_IA32_APERF, aperf);
-	rdmsrl(MSR_IA32_MPERF, mperf);
+	rdmsrq(MSR_IA32_APERF, aperf);
+	rdmsrq(MSR_IA32_MPERF, mperf);
 
 	this_cpu_write(cpu_samples.aperf, aperf);
 	this_cpu_write(cpu_samples.mperf, mperf);
@@ -99,7 +100,7 @@ static bool __init turbo_disabled(void)
 	u64 misc_en;
 	int err;
 
-	err = rdmsrl_safe(MSR_IA32_MISC_ENABLE, &misc_en);
+	err = rdmsrq_safe(MSR_IA32_MISC_ENABLE, &misc_en);
 	if (err)
 		return false;
 
@@ -110,11 +111,11 @@ static bool __init slv_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq)
 {
 	int err;
 
-	err = rdmsrl_safe(MSR_ATOM_CORE_RATIOS, base_freq);
+	err = rdmsrq_safe(MSR_ATOM_CORE_RATIOS, base_freq);
 	if (err)
 		return false;
 
-	err = rdmsrl_safe(MSR_ATOM_CORE_TURBO_RATIOS, turbo_freq);
+	err = rdmsrq_safe(MSR_ATOM_CORE_TURBO_RATIOS, turbo_freq);
 	if (err)
 		return false;
 
@@ -152,13 +153,13 @@ static bool __init knl_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq,
 	int err, i;
 	u64 msr;
 
-	err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq);
+	err = rdmsrq_safe(MSR_PLATFORM_INFO, base_freq);
 	if (err)
 		return false;
 
 	*base_freq = (*base_freq >> 8) & 0xFF;	    /* max P state */
 
-	err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &msr);
+	err = rdmsrq_safe(MSR_TURBO_RATIO_LIMIT, &msr);
 	if (err)
 		return false;
 
@@ -190,17 +191,17 @@ static bool __init skx_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, int s
 	u32 group_size;
 	int err, i;
 
-	err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq);
+	err = rdmsrq_safe(MSR_PLATFORM_INFO, base_freq);
 	if (err)
 		return false;
 
 	*base_freq = (*base_freq >> 8) & 0xFF;      /* max P state */
 
-	err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &ratios);
+	err = rdmsrq_safe(MSR_TURBO_RATIO_LIMIT, &ratios);
 	if (err)
 		return false;
 
-	err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT1, &counts);
+	err = rdmsrq_safe(MSR_TURBO_RATIO_LIMIT1, &counts);
 	if (err)
 		return false;
 
@@ -220,11 +221,11 @@ static bool __init core_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq)
 	u64 msr;
 	int err;
 
-	err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq);
+	err = rdmsrq_safe(MSR_PLATFORM_INFO, base_freq);
 	if (err)
 		return false;
 
-	err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &msr);
+	err = rdmsrq_safe(MSR_TURBO_RATIO_LIMIT, &msr);
 	if (err)
 		return false;
 
@@ -474,8 +475,8 @@ void arch_scale_freq_tick(void)
 	if (!cpu_feature_enabled(X86_FEATURE_APERFMPERF))
 		return;
 
-	rdmsrl(MSR_IA32_APERF, aperf);
-	rdmsrl(MSR_IA32_MPERF, mperf);
+	rdmsrq(MSR_IA32_APERF, aperf);
+	rdmsrq(MSR_IA32_MPERF, mperf);
 	acnt = aperf - s->aperf;
 	mcnt = mperf - s->mperf;
 
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 7caba0bb737d..a938fb4add65 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -112,7 +112,7 @@ void (*x86_return_thunk)(void) __ro_after_init = __x86_return_thunk;
 static void update_spec_ctrl(u64 val)
 {
 	this_cpu_write(x86_spec_ctrl_current, val);
-	wrmsrl(MSR_IA32_SPEC_CTRL, val);
+	wrmsrq(MSR_IA32_SPEC_CTRL, val);
 }
 
 /*
@@ -131,7 +131,7 @@ void update_spec_ctrl_cond(u64 val)
 	 * forced the update can be delayed until that time.
 	 */
 	if (!cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS))
-		wrmsrl(MSR_IA32_SPEC_CTRL, val);
+		wrmsrq(MSR_IA32_SPEC_CTRL, val);
 }
 
 noinstr u64 spec_ctrl_current(void)
@@ -185,7 +185,7 @@ void __init cpu_select_mitigations(void)
 	 * init code as it is not enumerated and depends on the family.
 	 */
 	if (cpu_feature_enabled(X86_FEATURE_MSR_SPEC_CTRL)) {
-		rdmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
+		rdmsrq(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
 
 		/*
 		 * Previously running kernel (kexec), may have some controls
@@ -303,9 +303,9 @@ static void x86_amd_ssb_disable(void)
 	u64 msrval = x86_amd_ls_cfg_base | x86_amd_ls_cfg_ssbd_mask;
 
 	if (boot_cpu_has(X86_FEATURE_VIRT_SSBD))
-		wrmsrl(MSR_AMD64_VIRT_SPEC_CTRL, SPEC_CTRL_SSBD);
+		wrmsrq(MSR_AMD64_VIRT_SPEC_CTRL, SPEC_CTRL_SSBD);
 	else if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD))
-		wrmsrl(MSR_AMD64_LS_CFG, msrval);
+		wrmsrq(MSR_AMD64_LS_CFG, msrval);
 }
 
 #undef pr_fmt
@@ -761,7 +761,7 @@ void update_srbds_msr(void)
 	if (!boot_cpu_has(X86_FEATURE_SRBDS_CTRL))
 		return;
 
-	rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
+	rdmsrq(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
 
 	switch (srbds_mitigation) {
 	case SRBDS_MITIGATION_OFF:
@@ -775,7 +775,7 @@ void update_srbds_msr(void)
 		break;
 	}
 
-	wrmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
+	wrmsrq(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
 }
 
 static void __init srbds_select_mitigation(void)
@@ -891,7 +891,7 @@ void update_gds_msr(void)
 
 	switch (gds_mitigation) {
 	case GDS_MITIGATION_OFF:
-		rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
+		rdmsrq(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
 		mcu_ctrl |= GDS_MITG_DIS;
 		break;
 	case GDS_MITIGATION_FULL_LOCKED:
@@ -901,7 +901,7 @@ void update_gds_msr(void)
 		 * CPUs.
 		 */
 	case GDS_MITIGATION_FULL:
-		rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
+		rdmsrq(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
 		mcu_ctrl &= ~GDS_MITG_DIS;
 		break;
 	case GDS_MITIGATION_FORCE:
@@ -911,14 +911,14 @@ void update_gds_msr(void)
 		return;
 	}
 
-	wrmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
+	wrmsrq(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
 
 	/*
 	 * Check to make sure that the WRMSR value was not ignored. Writes to
 	 * GDS_MITG_DIS will be ignored if this processor is locked but the boot
 	 * processor was not.
 	 */
-	rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl_after);
+	rdmsrq(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl_after);
 	WARN_ON_ONCE(mcu_ctrl != mcu_ctrl_after);
 }
 
@@ -952,7 +952,7 @@ static void __init gds_select_mitigation(void)
 	if (gds_mitigation == GDS_MITIGATION_FORCE)
 		gds_mitigation = GDS_MITIGATION_FULL;
 
-	rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
+	rdmsrq(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
 	if (mcu_ctrl & GDS_MITG_LOCKED) {
 		if (gds_mitigation == GDS_MITIGATION_OFF)
 			pr_warn("Mitigation locked. Disable failed.\n");
diff --git a/arch/x86/kernel/cpu/bus_lock.c b/arch/x86/kernel/cpu/bus_lock.c
index 237faf7e700c..981f8b1f0792 100644
--- a/arch/x86/kernel/cpu/bus_lock.c
+++ b/arch/x86/kernel/cpu/bus_lock.c
@@ -10,6 +10,7 @@
 #include <asm/cmdline.h>
 #include <asm/traps.h>
 #include <asm/cpu.h>
+#include <asm/msr.h>
 
 enum split_lock_detect_state {
 	sld_off = 0,
@@ -95,15 +96,15 @@ static bool split_lock_verify_msr(bool on)
 {
 	u64 ctrl, tmp;
 
-	if (rdmsrl_safe(MSR_TEST_CTRL, &ctrl))
+	if (rdmsrq_safe(MSR_TEST_CTRL, &ctrl))
 		return false;
 	if (on)
 		ctrl |= MSR_TEST_CTRL_SPLIT_LOCK_DETECT;
 	else
 		ctrl &= ~MSR_TEST_CTRL_SPLIT_LOCK_DETECT;
-	if (wrmsrl_safe(MSR_TEST_CTRL, ctrl))
+	if (wrmsrq_safe(MSR_TEST_CTRL, ctrl))
 		return false;
-	rdmsrl(MSR_TEST_CTRL, tmp);
+	rdmsrq(MSR_TEST_CTRL, tmp);
 	return ctrl == tmp;
 }
 
@@ -137,7 +138,7 @@ static void __init __split_lock_setup(void)
 		return;
 	}
 
-	rdmsrl(MSR_TEST_CTRL, msr_test_ctrl_cache);
+	rdmsrq(MSR_TEST_CTRL, msr_test_ctrl_cache);
 
 	if (!split_lock_verify_msr(true)) {
 		pr_info("MSR access failed: Disabled\n");
@@ -145,7 +146,7 @@ static void __init __split_lock_setup(void)
 	}
 
 	/* Restore the MSR to its cached value. */
-	wrmsrl(MSR_TEST_CTRL, msr_test_ctrl_cache);
+	wrmsrq(MSR_TEST_CTRL, msr_test_ctrl_cache);
 
 	setup_force_cpu_cap(X86_FEATURE_SPLIT_LOCK_DETECT);
 }
@@ -162,7 +163,7 @@ static void sld_update_msr(bool on)
 	if (on)
 		test_ctrl_val |= MSR_TEST_CTRL_SPLIT_LOCK_DETECT;
 
-	wrmsrl(MSR_TEST_CTRL, test_ctrl_val);
+	wrmsrq(MSR_TEST_CTRL, test_ctrl_val);
 }
 
 void split_lock_init(void)
@@ -297,7 +298,7 @@ void bus_lock_init(void)
 	if (!boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT))
 		return;
 
-	rdmsrl(MSR_IA32_DEBUGCTLMSR, val);
+	rdmsrq(MSR_IA32_DEBUGCTLMSR, val);
 
 	if ((boot_cpu_has(X86_FEATURE_SPLIT_LOCK_DETECT) &&
 	    (sld_state == sld_warn || sld_state == sld_fatal)) ||
@@ -311,7 +312,7 @@ void bus_lock_init(void)
 		val |= DEBUGCTLMSR_BUS_LOCK_DETECT;
 	}
 
-	wrmsrl(MSR_IA32_DEBUGCTLMSR, val);
+	wrmsrq(MSR_IA32_DEBUGCTLMSR, val);
 }
 
 bool handle_user_split_lock(struct pt_regs *regs, long error_code)
@@ -375,7 +376,7 @@ static void __init split_lock_setup(struct cpuinfo_x86 *c)
 	 * MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT is.  All CPUs that set
 	 * it have split lock detection.
 	 */
-	rdmsrl(MSR_IA32_CORE_CAPS, ia32_core_caps);
+	rdmsrq(MSR_IA32_CORE_CAPS, ia32_core_caps);
 	if (ia32_core_caps & MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT)
 		goto supported;
 
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index f2b902200948..34efb9d2519a 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -148,7 +148,7 @@ static void ppin_init(struct cpuinfo_x86 *c)
 	 */
 	info = (struct ppin_info *)id->driver_data;
 
-	if (rdmsrl_safe(info->msr_ppin_ctl, &val))
+	if (rdmsrq_safe(info->msr_ppin_ctl, &val))
 		goto clear_ppin;
 
 	if ((val & 3UL) == 1UL) {
@@ -158,13 +158,13 @@ static void ppin_init(struct cpuinfo_x86 *c)
 
 	/* If PPIN is disabled, try to enable */
 	if (!(val & 2UL)) {
-		wrmsrl_safe(info->msr_ppin_ctl,  val | 2UL);
-		rdmsrl_safe(info->msr_ppin_ctl, &val);
+		wrmsrq_safe(info->msr_ppin_ctl,  val | 2UL);
+		rdmsrq_safe(info->msr_ppin_ctl, &val);
 	}
 
 	/* Is the enable bit set? */
 	if (val & 2UL) {
-		c->ppin = __rdmsr(info->msr_ppin);
+		c->ppin = native_rdmsrq(info->msr_ppin);
 		set_cpu_cap(c, info->feature);
 		return;
 	}
@@ -563,9 +563,9 @@ __noendbr u64 ibt_save(bool disable)
 	u64 msr = 0;
 
 	if (cpu_feature_enabled(X86_FEATURE_IBT)) {
-		rdmsrl(MSR_IA32_S_CET, msr);
+		rdmsrq(MSR_IA32_S_CET, msr);
 		if (disable)
-			wrmsrl(MSR_IA32_S_CET, msr & ~CET_ENDBR_EN);
+			wrmsrq(MSR_IA32_S_CET, msr & ~CET_ENDBR_EN);
 	}
 
 	return msr;
@@ -576,10 +576,10 @@ __noendbr void ibt_restore(u64 save)
 	u64 msr;
 
 	if (cpu_feature_enabled(X86_FEATURE_IBT)) {
-		rdmsrl(MSR_IA32_S_CET, msr);
+		rdmsrq(MSR_IA32_S_CET, msr);
 		msr &= ~CET_ENDBR_EN;
 		msr |= (save & CET_ENDBR_EN);
-		wrmsrl(MSR_IA32_S_CET, msr);
+		wrmsrq(MSR_IA32_S_CET, msr);
 	}
 }
 
@@ -603,15 +603,15 @@ static __always_inline void setup_cet(struct cpuinfo_x86 *c)
 		set_cpu_cap(c, X86_FEATURE_USER_SHSTK);
 
 	if (kernel_ibt)
-		wrmsrl(MSR_IA32_S_CET, CET_ENDBR_EN);
+		wrmsrq(MSR_IA32_S_CET, CET_ENDBR_EN);
 	else
-		wrmsrl(MSR_IA32_S_CET, 0);
+		wrmsrq(MSR_IA32_S_CET, 0);
 
 	cr4_set_bits(X86_CR4_CET);
 
 	if (kernel_ibt && ibt_selftest()) {
 		pr_err("IBT selftest: Failed!\n");
-		wrmsrl(MSR_IA32_S_CET, 0);
+		wrmsrq(MSR_IA32_S_CET, 0);
 		setup_clear_cpu_cap(X86_FEATURE_IBT);
 	}
 }
@@ -622,8 +622,8 @@ __noendbr void cet_disable(void)
 	      cpu_feature_enabled(X86_FEATURE_SHSTK)))
 		return;
 
-	wrmsrl(MSR_IA32_S_CET, 0);
-	wrmsrl(MSR_IA32_U_CET, 0);
+	wrmsrq(MSR_IA32_S_CET, 0);
+	wrmsrq(MSR_IA32_U_CET, 0);
 }
 
 /*
@@ -752,9 +752,9 @@ void __init switch_gdt_and_percpu_base(int cpu)
 	 * No need to load %gs. It is already correct.
 	 *
 	 * Writing %gs on 64bit would zero GSBASE which would make any per
-	 * CPU operation up to the point of the wrmsrl() fault.
+	 * CPU operation up to the point of the wrmsrq() fault.
 	 *
-	 * Set GSBASE to the new offset. Until the wrmsrl() happens the
+	 * Set GSBASE to the new offset. Until the wrmsrq() happens the
 	 * early mapping is still valid. That means the GSBASE update will
 	 * lose any prior per CPU data which was not copied over in
 	 * setup_per_cpu_areas().
@@ -762,7 +762,7 @@ void __init switch_gdt_and_percpu_base(int cpu)
 	 * This works even with stackprotector enabled because the
 	 * per CPU stack canary is 0 in both per CPU areas.
 	 */
-	wrmsrl(MSR_GS_BASE, cpu_kernelmode_gs_base(cpu));
+	wrmsrq(MSR_GS_BASE, cpu_kernelmode_gs_base(cpu));
 #else
 	/*
 	 * %fs is already set to __KERNEL_PERCPU, but after switching GDT
@@ -1290,7 +1290,7 @@ u64 x86_read_arch_cap_msr(void)
 	u64 x86_arch_cap_msr = 0;
 
 	if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES))
-		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, x86_arch_cap_msr);
+		rdmsrq(MSR_IA32_ARCH_CAPABILITIES, x86_arch_cap_msr);
 
 	return x86_arch_cap_msr;
 }
@@ -1788,11 +1788,11 @@ static bool detect_null_seg_behavior(void)
 	 */
 
 	unsigned long old_base, tmp;
-	rdmsrl(MSR_FS_BASE, old_base);
-	wrmsrl(MSR_FS_BASE, 1);
+	rdmsrq(MSR_FS_BASE, old_base);
+	wrmsrq(MSR_FS_BASE, 1);
 	loadsegment(fs, 0);
-	rdmsrl(MSR_FS_BASE, tmp);
-	wrmsrl(MSR_FS_BASE, old_base);
+	rdmsrq(MSR_FS_BASE, tmp);
+	wrmsrq(MSR_FS_BASE, old_base);
 	return tmp == 0;
 }
 
@@ -2021,9 +2021,9 @@ void enable_sep_cpu(void)
 	 */
 
 	tss->x86_tss.ss1 = __KERNEL_CS;
-	wrmsr(MSR_IA32_SYSENTER_CS, tss->x86_tss.ss1, 0);
-	wrmsr(MSR_IA32_SYSENTER_ESP, (unsigned long)(cpu_entry_stack(cpu) + 1), 0);
-	wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)entry_SYSENTER_32, 0);
+	wrmsrq(MSR_IA32_SYSENTER_CS, tss->x86_tss.ss1);
+	wrmsrq(MSR_IA32_SYSENTER_ESP, (unsigned long)(cpu_entry_stack(cpu) + 1));
+	wrmsrq(MSR_IA32_SYSENTER_EIP, (unsigned long)entry_SYSENTER_32);
 
 	put_cpu();
 }
@@ -2130,7 +2130,7 @@ DEFINE_PER_CPU_CACHE_HOT(unsigned long, cpu_current_top_of_stack) = TOP_OF_INIT_
 DEFINE_PER_CPU_CACHE_HOT(u64, __x86_call_depth);
 EXPORT_PER_CPU_SYMBOL(__x86_call_depth);
 
-static void wrmsrl_cstar(unsigned long val)
+static void wrmsrq_cstar(unsigned long val)
 {
 	/*
 	 * Intel CPUs do not support 32-bit SYSCALL. Writing to MSR_CSTAR
@@ -2138,37 +2138,37 @@ static void wrmsrl_cstar(unsigned long val)
 	 * guest. Avoid the pointless write on all Intel CPUs.
 	 */
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
-		wrmsrl(MSR_CSTAR, val);
+		wrmsrq(MSR_CSTAR, val);
 }
 
 static inline void idt_syscall_init(void)
 {
-	wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64);
+	wrmsrq(MSR_LSTAR, (unsigned long)entry_SYSCALL_64);
 
 	if (ia32_enabled()) {
-		wrmsrl_cstar((unsigned long)entry_SYSCALL_compat);
+		wrmsrq_cstar((unsigned long)entry_SYSCALL_compat);
 		/*
 		 * This only works on Intel CPUs.
 		 * On AMD CPUs these MSRs are 32-bit, CPU truncates MSR_IA32_SYSENTER_EIP.
 		 * This does not cause SYSENTER to jump to the wrong location, because
 		 * AMD doesn't allow SYSENTER in long mode (either 32- or 64-bit).
 		 */
-		wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS);
-		wrmsrl_safe(MSR_IA32_SYSENTER_ESP,
+		wrmsrq_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS);
+		wrmsrq_safe(MSR_IA32_SYSENTER_ESP,
 			    (unsigned long)(cpu_entry_stack(smp_processor_id()) + 1));
-		wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat);
+		wrmsrq_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat);
 	} else {
-		wrmsrl_cstar((unsigned long)entry_SYSCALL32_ignore);
-		wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)GDT_ENTRY_INVALID_SEG);
-		wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL);
-		wrmsrl_safe(MSR_IA32_SYSENTER_EIP, 0ULL);
+		wrmsrq_cstar((unsigned long)entry_SYSCALL32_ignore);
+		wrmsrq_safe(MSR_IA32_SYSENTER_CS, (u64)GDT_ENTRY_INVALID_SEG);
+		wrmsrq_safe(MSR_IA32_SYSENTER_ESP, 0ULL);
+		wrmsrq_safe(MSR_IA32_SYSENTER_EIP, 0ULL);
 	}
 
 	/*
 	 * Flags to clear on syscall; clear as much as possible
 	 * to minimize user space-kernel interference.
 	 */
-	wrmsrl(MSR_SYSCALL_MASK,
+	wrmsrq(MSR_SYSCALL_MASK,
 	       X86_EFLAGS_CF|X86_EFLAGS_PF|X86_EFLAGS_AF|
 	       X86_EFLAGS_ZF|X86_EFLAGS_SF|X86_EFLAGS_TF|
 	       X86_EFLAGS_IF|X86_EFLAGS_DF|X86_EFLAGS_OF|
@@ -2237,7 +2237,7 @@ static inline void setup_getcpu(int cpu)
 	struct desc_struct d = { };
 
 	if (boot_cpu_has(X86_FEATURE_RDTSCP) || boot_cpu_has(X86_FEATURE_RDPID))
-		wrmsr(MSR_TSC_AUX, cpudata, 0);
+		wrmsrq(MSR_TSC_AUX, cpudata);
 
 	/* Store CPU and node number in limit. */
 	d.limit0 = cpudata;
@@ -2352,8 +2352,8 @@ void cpu_init(void)
 		memset(cur->thread.tls_array, 0, GDT_ENTRY_TLS_ENTRIES * 8);
 		syscall_init();
 
-		wrmsrl(MSR_FS_BASE, 0);
-		wrmsrl(MSR_KERNEL_GS_BASE, 0);
+		wrmsrq(MSR_FS_BASE, 0);
+		wrmsrq(MSR_KERNEL_GS_BASE, 0);
 		barrier();
 
 		x2apic_setup();
diff --git a/arch/x86/kernel/cpu/feat_ctl.c b/arch/x86/kernel/cpu/feat_ctl.c
index 4a4118784c13..d69757246bde 100644
--- a/arch/x86/kernel/cpu/feat_ctl.c
+++ b/arch/x86/kernel/cpu/feat_ctl.c
@@ -4,6 +4,7 @@
 #include <asm/cpu.h>
 #include <asm/cpufeature.h>
 #include <asm/msr-index.h>
+#include <asm/msr.h>
 #include <asm/processor.h>
 #include <asm/vmx.h>
 
@@ -118,7 +119,7 @@ void init_ia32_feat_ctl(struct cpuinfo_x86 *c)
 	bool enable_vmx;
 	u64 msr;
 
-	if (rdmsrl_safe(MSR_IA32_FEAT_CTL, &msr)) {
+	if (rdmsrq_safe(MSR_IA32_FEAT_CTL, &msr)) {
 		clear_cpu_cap(c, X86_FEATURE_VMX);
 		clear_cpu_cap(c, X86_FEATURE_SGX);
 		return;
@@ -165,7 +166,7 @@ void init_ia32_feat_ctl(struct cpuinfo_x86 *c)
 			msr |= FEAT_CTL_SGX_LC_ENABLED;
 	}
 
-	wrmsrl(MSR_IA32_FEAT_CTL, msr);
+	wrmsrq(MSR_IA32_FEAT_CTL, msr);
 
 update_caps:
 	set_cpu_cap(c, X86_FEATURE_MSR_IA32_FEAT_CTL);
diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c
index 6af4a4a90a52..2154f12766fb 100644
--- a/arch/x86/kernel/cpu/hygon.c
+++ b/arch/x86/kernel/cpu/hygon.c
@@ -15,6 +15,7 @@
 #include <asm/cacheinfo.h>
 #include <asm/spec-ctrl.h>
 #include <asm/delay.h>
+#include <asm/msr.h>
 
 #include "cpu.h"
 
@@ -96,7 +97,7 @@ static void bsp_init_hygon(struct cpuinfo_x86 *c)
 	if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) {
 		u64 val;
 
-		rdmsrl(MSR_K7_HWCR, val);
+		rdmsrq(MSR_K7_HWCR, val);
 		if (!(val & BIT(24)))
 			pr_warn(FW_BUG "TSC doesn't count with P0 frequency!\n");
 	}
@@ -110,7 +111,7 @@ static void bsp_init_hygon(struct cpuinfo_x86 *c)
 		 * Try to cache the base value so further operations can
 		 * avoid RMW. If that faults, do not enable SSBD.
 		 */
-		if (!rdmsrl_safe(MSR_AMD64_LS_CFG, &x86_amd_ls_cfg_base)) {
+		if (!rdmsrq_safe(MSR_AMD64_LS_CFG, &x86_amd_ls_cfg_base)) {
 			setup_force_cpu_cap(X86_FEATURE_LS_CFG_SSBD);
 			setup_force_cpu_cap(X86_FEATURE_SSBD);
 			x86_amd_ls_cfg_ssbd_mask = 1ULL << 10;
@@ -194,7 +195,7 @@ static void init_hygon(struct cpuinfo_x86 *c)
 	init_hygon_cacheinfo(c);
 
 	if (cpu_has(c, X86_FEATURE_SVM)) {
-		rdmsrl(MSR_VM_CR, vm_cr);
+		rdmsrq(MSR_VM_CR, vm_cr);
 		if (vm_cr & SVM_VM_CR_SVM_DIS_MASK) {
 			pr_notice_once("SVM disabled (by BIOS) in MSR_VM_CR\n");
 			clear_cpu_cap(c, X86_FEATURE_SVM);
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index a6493f60b3f2..584dd55bf739 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -159,7 +159,7 @@ static void detect_tme_early(struct cpuinfo_x86 *c)
 	u64 tme_activate;
 	int keyid_bits;
 
-	rdmsrl(MSR_IA32_TME_ACTIVATE, tme_activate);
+	rdmsrq(MSR_IA32_TME_ACTIVATE, tme_activate);
 
 	if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) {
 		pr_info_once("x86/tme: not enabled by BIOS\n");
@@ -301,7 +301,7 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 	 * string flag and enhanced fast string capabilities accordingly.
 	 */
 	if (c->x86_vfm >= INTEL_PENTIUM_M_DOTHAN) {
-		rdmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
+		rdmsrq(MSR_IA32_MISC_ENABLE, misc_enable);
 		if (misc_enable & MSR_IA32_MISC_ENABLE_FAST_STRING) {
 			/* X86_FEATURE_ERMS is set based on CPUID */
 			set_cpu_cap(c, X86_FEATURE_REP_GOOD);
@@ -490,7 +490,7 @@ static void init_cpuid_fault(struct cpuinfo_x86 *c)
 {
 	u64 msr;
 
-	if (!rdmsrl_safe(MSR_PLATFORM_INFO, &msr)) {
+	if (!rdmsrq_safe(MSR_PLATFORM_INFO, &msr)) {
 		if (msr & MSR_PLATFORM_INFO_CPUID_FAULT)
 			set_cpu_cap(c, X86_FEATURE_CPUID_FAULT);
 	}
@@ -500,7 +500,7 @@ static void init_intel_misc_features(struct cpuinfo_x86 *c)
 {
 	u64 msr;
 
-	if (rdmsrl_safe(MSR_MISC_FEATURES_ENABLES, &msr))
+	if (rdmsrq_safe(MSR_MISC_FEATURES_ENABLES, &msr))
 		return;
 
 	/* Clear all MISC features */
@@ -511,7 +511,7 @@ static void init_intel_misc_features(struct cpuinfo_x86 *c)
 	probe_xeon_phi_r3mwait(c);
 
 	msr = this_cpu_read(msr_misc_features_shadow);
-	wrmsrl(MSR_MISC_FEATURES_ENABLES, msr);
+	wrmsrq(MSR_MISC_FEATURES_ENABLES, msr);
 }
 
 /*
diff --git a/arch/x86/kernel/cpu/intel_epb.c b/arch/x86/kernel/cpu/intel_epb.c
index 30b1d63b97f3..bc7671f920a7 100644
--- a/arch/x86/kernel/cpu/intel_epb.c
+++ b/arch/x86/kernel/cpu/intel_epb.c
@@ -79,7 +79,7 @@ static int intel_epb_save(void)
 {
 	u64 epb;
 
-	rdmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb);
+	rdmsrq(MSR_IA32_ENERGY_PERF_BIAS, epb);
 	/*
 	 * Ensure that saved_epb will always be nonzero after this write even if
 	 * the EPB value read from the MSR is 0.
@@ -94,7 +94,7 @@ static void intel_epb_restore(void)
 	u64 val = this_cpu_read(saved_epb);
 	u64 epb;
 
-	rdmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb);
+	rdmsrq(MSR_IA32_ENERGY_PERF_BIAS, epb);
 	if (val) {
 		val &= EPB_MASK;
 	} else {
@@ -111,7 +111,7 @@ static void intel_epb_restore(void)
 			pr_warn_once("ENERGY_PERF_BIAS: Set to 'normal', was 'performance'\n");
 		}
 	}
-	wrmsrl(MSR_IA32_ENERGY_PERF_BIAS, (epb & ~EPB_MASK) | val);
+	wrmsrq(MSR_IA32_ENERGY_PERF_BIAS, (epb & ~EPB_MASK) | val);
 }
 
 static struct syscore_ops intel_epb_syscore_ops = {
@@ -135,7 +135,7 @@ static ssize_t energy_perf_bias_show(struct device *dev,
 	u64 epb;
 	int ret;
 
-	ret = rdmsrl_on_cpu(cpu, MSR_IA32_ENERGY_PERF_BIAS, &epb);
+	ret = rdmsrq_on_cpu(cpu, MSR_IA32_ENERGY_PERF_BIAS, &epb);
 	if (ret < 0)
 		return ret;
 
@@ -157,11 +157,11 @@ static ssize_t energy_perf_bias_store(struct device *dev,
 	else if (kstrtou64(buf, 0, &val) || val > MAX_EPB)
 		return -EINVAL;
 
-	ret = rdmsrl_on_cpu(cpu, MSR_IA32_ENERGY_PERF_BIAS, &epb);
+	ret = rdmsrq_on_cpu(cpu, MSR_IA32_ENERGY_PERF_BIAS, &epb);
 	if (ret < 0)
 		return ret;
 
-	ret = wrmsrl_on_cpu(cpu, MSR_IA32_ENERGY_PERF_BIAS,
+	ret = wrmsrq_on_cpu(cpu, MSR_IA32_ENERGY_PERF_BIAS,
 			    (epb & ~EPB_MASK) | val);
 	if (ret < 0)
 		return ret;
diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index 1075a90141da..9d852c3b2cb5 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -662,12 +662,12 @@ static void disable_err_thresholding(struct cpuinfo_x86 *c, unsigned int bank)
 		return;
 	}
 
-	rdmsrl(MSR_K7_HWCR, hwcr);
+	rdmsrq(MSR_K7_HWCR, hwcr);
 
 	/* McStatusWrEn has to be set */
 	need_toggle = !(hwcr & BIT(18));
 	if (need_toggle)
-		wrmsrl(MSR_K7_HWCR, hwcr | BIT(18));
+		wrmsrq(MSR_K7_HWCR, hwcr | BIT(18));
 
 	/* Clear CntP bit safely */
 	for (i = 0; i < num_msrs; i++)
@@ -675,7 +675,7 @@ static void disable_err_thresholding(struct cpuinfo_x86 *c, unsigned int bank)
 
 	/* restore old settings */
 	if (need_toggle)
-		wrmsrl(MSR_K7_HWCR, hwcr);
+		wrmsrq(MSR_K7_HWCR, hwcr);
 }
 
 /* cpu init entry point, called from mce.c with preempt off */
@@ -805,12 +805,12 @@ static void __log_error(unsigned int bank, u64 status, u64 addr, u64 misc)
 	}
 
 	if (mce_flags.smca) {
-		rdmsrl(MSR_AMD64_SMCA_MCx_IPID(bank), m->ipid);
+		rdmsrq(MSR_AMD64_SMCA_MCx_IPID(bank), m->ipid);
 
 		if (m->status & MCI_STATUS_SYNDV) {
-			rdmsrl(MSR_AMD64_SMCA_MCx_SYND(bank), m->synd);
-			rdmsrl(MSR_AMD64_SMCA_MCx_SYND1(bank), err.vendor.amd.synd1);
-			rdmsrl(MSR_AMD64_SMCA_MCx_SYND2(bank), err.vendor.amd.synd2);
+			rdmsrq(MSR_AMD64_SMCA_MCx_SYND(bank), m->synd);
+			rdmsrq(MSR_AMD64_SMCA_MCx_SYND1(bank), err.vendor.amd.synd1);
+			rdmsrq(MSR_AMD64_SMCA_MCx_SYND2(bank), err.vendor.amd.synd2);
 		}
 	}
 
@@ -834,16 +834,16 @@ _log_error_bank(unsigned int bank, u32 msr_stat, u32 msr_addr, u64 misc)
 {
 	u64 status, addr = 0;
 
-	rdmsrl(msr_stat, status);
+	rdmsrq(msr_stat, status);
 	if (!(status & MCI_STATUS_VAL))
 		return false;
 
 	if (status & MCI_STATUS_ADDRV)
-		rdmsrl(msr_addr, addr);
+		rdmsrq(msr_addr, addr);
 
 	__log_error(bank, status, addr, misc);
 
-	wrmsrl(msr_stat, 0);
+	wrmsrq(msr_stat, 0);
 
 	return status & MCI_STATUS_DEFERRED;
 }
@@ -862,7 +862,7 @@ static bool _log_error_deferred(unsigned int bank, u32 misc)
 		return true;
 
 	/* Clear MCA_DESTAT if the deferred error was logged from MCA_STATUS. */
-	wrmsrl(MSR_AMD64_SMCA_MCx_DESTAT(bank), 0);
+	wrmsrq(MSR_AMD64_SMCA_MCx_DESTAT(bank), 0);
 	return true;
 }
 
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index f6fd71b64b66..e9b3c5d4a52e 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -121,7 +121,7 @@ void mce_prep_record_common(struct mce *m)
 {
 	m->cpuid	= cpuid_eax(1);
 	m->cpuvendor	= boot_cpu_data.x86_vendor;
-	m->mcgcap	= __rdmsr(MSR_IA32_MCG_CAP);
+	m->mcgcap	= native_rdmsrq(MSR_IA32_MCG_CAP);
 	/* need the internal __ version to avoid deadlocks */
 	m->time		= __ktime_get_real_seconds();
 }
@@ -388,9 +388,9 @@ void ex_handler_msr_mce(struct pt_regs *regs, bool wrmsr)
 }
 
 /* MSR access wrappers used for error injection */
-noinstr u64 mce_rdmsrl(u32 msr)
+noinstr u64 mce_rdmsrq(u32 msr)
 {
-	DECLARE_ARGS(val, low, high);
+	EAX_EDX_DECLARE_ARGS(val, low, high);
 
 	if (__this_cpu_read(injectm.finished)) {
 		int offset;
@@ -423,7 +423,7 @@ noinstr u64 mce_rdmsrl(u32 msr)
 	return EAX_EDX_VAL(val, low, high);
 }
 
-static noinstr void mce_wrmsrl(u32 msr, u64 v)
+static noinstr void mce_wrmsrq(u32 msr, u64 v)
 {
 	u32 low, high;
 
@@ -444,7 +444,7 @@ static noinstr void mce_wrmsrl(u32 msr, u64 v)
 	low  = (u32)v;
 	high = (u32)(v >> 32);
 
-	/* See comment in mce_rdmsrl() */
+	/* See comment in mce_rdmsrq() */
 	asm volatile("1: wrmsr\n"
 		     "2:\n"
 		     _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_WRMSR_IN_MCE)
@@ -468,7 +468,7 @@ static noinstr void mce_gather_info(struct mce_hw_err *err, struct pt_regs *regs
 	instrumentation_end();
 
 	m = &err->m;
-	m->mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS);
+	m->mcgstatus = mce_rdmsrq(MSR_IA32_MCG_STATUS);
 	if (regs) {
 		/*
 		 * Get the address of the instruction at the time of
@@ -488,7 +488,7 @@ static noinstr void mce_gather_info(struct mce_hw_err *err, struct pt_regs *regs
 		}
 		/* Use accurate RIP reporting if available. */
 		if (mca_cfg.rip_msr)
-			m->ip = mce_rdmsrl(mca_cfg.rip_msr);
+			m->ip = mce_rdmsrq(mca_cfg.rip_msr);
 	}
 }
 
@@ -684,10 +684,10 @@ static noinstr void mce_read_aux(struct mce_hw_err *err, int i)
 	struct mce *m = &err->m;
 
 	if (m->status & MCI_STATUS_MISCV)
-		m->misc = mce_rdmsrl(mca_msr_reg(i, MCA_MISC));
+		m->misc = mce_rdmsrq(mca_msr_reg(i, MCA_MISC));
 
 	if (m->status & MCI_STATUS_ADDRV) {
-		m->addr = mce_rdmsrl(mca_msr_reg(i, MCA_ADDR));
+		m->addr = mce_rdmsrq(mca_msr_reg(i, MCA_ADDR));
 
 		/*
 		 * Mask the reported address by the reported granularity.
@@ -702,12 +702,12 @@ static noinstr void mce_read_aux(struct mce_hw_err *err, int i)
 	}
 
 	if (mce_flags.smca) {
-		m->ipid = mce_rdmsrl(MSR_AMD64_SMCA_MCx_IPID(i));
+		m->ipid = mce_rdmsrq(MSR_AMD64_SMCA_MCx_IPID(i));
 
 		if (m->status & MCI_STATUS_SYNDV) {
-			m->synd = mce_rdmsrl(MSR_AMD64_SMCA_MCx_SYND(i));
-			err->vendor.amd.synd1 = mce_rdmsrl(MSR_AMD64_SMCA_MCx_SYND1(i));
-			err->vendor.amd.synd2 = mce_rdmsrl(MSR_AMD64_SMCA_MCx_SYND2(i));
+			m->synd = mce_rdmsrq(MSR_AMD64_SMCA_MCx_SYND(i));
+			err->vendor.amd.synd1 = mce_rdmsrq(MSR_AMD64_SMCA_MCx_SYND1(i));
+			err->vendor.amd.synd2 = mce_rdmsrq(MSR_AMD64_SMCA_MCx_SYND2(i));
 		}
 	}
 }
@@ -753,7 +753,7 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
 		m->bank = i;
 
 		barrier();
-		m->status = mce_rdmsrl(mca_msr_reg(i, MCA_STATUS));
+		m->status = mce_rdmsrq(mca_msr_reg(i, MCA_STATUS));
 
 		/*
 		 * Update storm tracking here, before checking for the
@@ -829,7 +829,7 @@ clear_it:
 		/*
 		 * Clear state for this bank.
 		 */
-		mce_wrmsrl(mca_msr_reg(i, MCA_STATUS), 0);
+		mce_wrmsrq(mca_msr_reg(i, MCA_STATUS), 0);
 	}
 
 	/*
@@ -887,8 +887,8 @@ quirk_sandybridge_ifu(int bank, struct mce *m, struct pt_regs *regs)
  */
 static noinstr bool quirk_skylake_repmov(void)
 {
-	u64 mcgstatus   = mce_rdmsrl(MSR_IA32_MCG_STATUS);
-	u64 misc_enable = mce_rdmsrl(MSR_IA32_MISC_ENABLE);
+	u64 mcgstatus   = mce_rdmsrq(MSR_IA32_MCG_STATUS);
+	u64 misc_enable = mce_rdmsrq(MSR_IA32_MISC_ENABLE);
 	u64 mc1_status;
 
 	/*
@@ -899,7 +899,7 @@ static noinstr bool quirk_skylake_repmov(void)
 	    !(misc_enable & MSR_IA32_MISC_ENABLE_FAST_STRING))
 		return false;
 
-	mc1_status = mce_rdmsrl(MSR_IA32_MCx_STATUS(1));
+	mc1_status = mce_rdmsrq(MSR_IA32_MCx_STATUS(1));
 
 	/* Check for a software-recoverable data fetch error. */
 	if ((mc1_status &
@@ -910,8 +910,8 @@ static noinstr bool quirk_skylake_repmov(void)
 	      MCI_STATUS_ADDRV | MCI_STATUS_MISCV |
 	      MCI_STATUS_AR | MCI_STATUS_S)) {
 		misc_enable &= ~MSR_IA32_MISC_ENABLE_FAST_STRING;
-		mce_wrmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
-		mce_wrmsrl(MSR_IA32_MCx_STATUS(1), 0);
+		mce_wrmsrq(MSR_IA32_MISC_ENABLE, misc_enable);
+		mce_wrmsrq(MSR_IA32_MCx_STATUS(1), 0);
 
 		instrumentation_begin();
 		pr_err_once("Erratum detected, disable fast string copy instructions.\n");
@@ -955,7 +955,7 @@ static __always_inline int mce_no_way_out(struct mce_hw_err *err, char **msg, un
 	int i;
 
 	for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
-		m->status = mce_rdmsrl(mca_msr_reg(i, MCA_STATUS));
+		m->status = mce_rdmsrq(mca_msr_reg(i, MCA_STATUS));
 		if (!(m->status & MCI_STATUS_VAL))
 			continue;
 
@@ -1274,7 +1274,7 @@ static __always_inline void mce_clear_state(unsigned long *toclear)
 
 	for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
 		if (arch_test_bit(i, toclear))
-			mce_wrmsrl(mca_msr_reg(i, MCA_STATUS), 0);
+			mce_wrmsrq(mca_msr_reg(i, MCA_STATUS), 0);
 	}
 }
 
@@ -1298,7 +1298,7 @@ static noinstr bool mce_check_crashing_cpu(void)
 	    (crashing_cpu != -1 && crashing_cpu != cpu)) {
 		u64 mcgstatus;
 
-		mcgstatus = __rdmsr(MSR_IA32_MCG_STATUS);
+		mcgstatus = native_rdmsrq(MSR_IA32_MCG_STATUS);
 
 		if (boot_cpu_data.x86_vendor == X86_VENDOR_ZHAOXIN) {
 			if (mcgstatus & MCG_STATUS_LMCES)
@@ -1306,7 +1306,7 @@ static noinstr bool mce_check_crashing_cpu(void)
 		}
 
 		if (mcgstatus & MCG_STATUS_RIPV) {
-			__wrmsr(MSR_IA32_MCG_STATUS, 0, 0);
+			native_wrmsrq(MSR_IA32_MCG_STATUS, 0);
 			return true;
 		}
 	}
@@ -1335,7 +1335,7 @@ __mc_scan_banks(struct mce_hw_err *err, struct pt_regs *regs,
 		m->addr = 0;
 		m->bank = i;
 
-		m->status = mce_rdmsrl(mca_msr_reg(i, MCA_STATUS));
+		m->status = mce_rdmsrq(mca_msr_reg(i, MCA_STATUS));
 		if (!(m->status & MCI_STATUS_VAL))
 			continue;
 
@@ -1693,7 +1693,7 @@ out:
 	instrumentation_end();
 
 clear:
-	mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
+	mce_wrmsrq(MSR_IA32_MCG_STATUS, 0);
 }
 EXPORT_SYMBOL_GPL(do_machine_check);
 
@@ -1822,7 +1822,7 @@ static void __mcheck_cpu_cap_init(void)
 	u64 cap;
 	u8 b;
 
-	rdmsrl(MSR_IA32_MCG_CAP, cap);
+	rdmsrq(MSR_IA32_MCG_CAP, cap);
 
 	b = cap & MCG_BANKCNT_MASK;
 
@@ -1863,7 +1863,7 @@ static void __mcheck_cpu_init_generic(void)
 
 	cr4_set_bits(X86_CR4_MCE);
 
-	rdmsrl(MSR_IA32_MCG_CAP, cap);
+	rdmsrq(MSR_IA32_MCG_CAP, cap);
 	if (cap & MCG_CTL_P)
 		wrmsr(MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff);
 }
@@ -1878,8 +1878,8 @@ static void __mcheck_cpu_init_clear_banks(void)
 
 		if (!b->init)
 			continue;
-		wrmsrl(mca_msr_reg(i, MCA_CTL), b->ctl);
-		wrmsrl(mca_msr_reg(i, MCA_STATUS), 0);
+		wrmsrq(mca_msr_reg(i, MCA_CTL), b->ctl);
+		wrmsrq(mca_msr_reg(i, MCA_STATUS), 0);
 	}
 }
 
@@ -1905,7 +1905,7 @@ static void __mcheck_cpu_check_banks(void)
 		if (!b->init)
 			continue;
 
-		rdmsrl(mca_msr_reg(i, MCA_CTL), msrval);
+		rdmsrq(mca_msr_reg(i, MCA_CTL), msrval);
 		b->init = !!msrval;
 	}
 }
@@ -2436,7 +2436,7 @@ static void mce_disable_error_reporting(void)
 		struct mce_bank *b = &mce_banks[i];
 
 		if (b->init)
-			wrmsrl(mca_msr_reg(i, MCA_CTL), 0);
+			wrmsrq(mca_msr_reg(i, MCA_CTL), 0);
 	}
 	return;
 }
@@ -2786,7 +2786,7 @@ static void mce_reenable_cpu(void)
 		struct mce_bank *b = &mce_banks[i];
 
 		if (b->init)
-			wrmsrl(mca_msr_reg(i, MCA_CTL), b->ctl);
+			wrmsrq(mca_msr_reg(i, MCA_CTL), b->ctl);
 	}
 }
 
diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c
index bb060f8326ef..d02c4f556cd0 100644
--- a/arch/x86/kernel/cpu/mce/inject.c
+++ b/arch/x86/kernel/cpu/mce/inject.c
@@ -28,6 +28,7 @@
 #include <asm/apic.h>
 #include <asm/irq_vectors.h>
 #include <asm/mce.h>
+#include <asm/msr.h>
 #include <asm/nmi.h>
 #include <asm/smp.h>
 
@@ -475,27 +476,27 @@ static void prepare_msrs(void *info)
 	struct mce m = *(struct mce *)info;
 	u8 b = m.bank;
 
-	wrmsrl(MSR_IA32_MCG_STATUS, m.mcgstatus);
+	wrmsrq(MSR_IA32_MCG_STATUS, m.mcgstatus);
 
 	if (boot_cpu_has(X86_FEATURE_SMCA)) {
 		if (m.inject_flags == DFR_INT_INJ) {
-			wrmsrl(MSR_AMD64_SMCA_MCx_DESTAT(b), m.status);
-			wrmsrl(MSR_AMD64_SMCA_MCx_DEADDR(b), m.addr);
+			wrmsrq(MSR_AMD64_SMCA_MCx_DESTAT(b), m.status);
+			wrmsrq(MSR_AMD64_SMCA_MCx_DEADDR(b), m.addr);
 		} else {
-			wrmsrl(MSR_AMD64_SMCA_MCx_STATUS(b), m.status);
-			wrmsrl(MSR_AMD64_SMCA_MCx_ADDR(b), m.addr);
+			wrmsrq(MSR_AMD64_SMCA_MCx_STATUS(b), m.status);
+			wrmsrq(MSR_AMD64_SMCA_MCx_ADDR(b), m.addr);
 		}
 
-		wrmsrl(MSR_AMD64_SMCA_MCx_SYND(b), m.synd);
+		wrmsrq(MSR_AMD64_SMCA_MCx_SYND(b), m.synd);
 
 		if (m.misc)
-			wrmsrl(MSR_AMD64_SMCA_MCx_MISC(b), m.misc);
+			wrmsrq(MSR_AMD64_SMCA_MCx_MISC(b), m.misc);
 	} else {
-		wrmsrl(MSR_IA32_MCx_STATUS(b), m.status);
-		wrmsrl(MSR_IA32_MCx_ADDR(b), m.addr);
+		wrmsrq(MSR_IA32_MCx_STATUS(b), m.status);
+		wrmsrq(MSR_IA32_MCx_ADDR(b), m.addr);
 
 		if (m.misc)
-			wrmsrl(MSR_IA32_MCx_MISC(b), m.misc);
+			wrmsrq(MSR_IA32_MCx_MISC(b), m.misc);
 	}
 }
 
@@ -589,7 +590,7 @@ static int inj_bank_set(void *data, u64 val)
 	u64 cap;
 
 	/* Get bank count on target CPU so we can handle non-uniform values. */
-	rdmsrl_on_cpu(m->extcpu, MSR_IA32_MCG_CAP, &cap);
+	rdmsrq_on_cpu(m->extcpu, MSR_IA32_MCG_CAP, &cap);
 	n_banks = cap & MCG_BANKCNT_MASK;
 
 	if (val >= n_banks) {
@@ -613,7 +614,7 @@ static int inj_bank_set(void *data, u64 val)
 	if (cpu_feature_enabled(X86_FEATURE_SMCA)) {
 		u64 ipid;
 
-		if (rdmsrl_on_cpu(m->extcpu, MSR_AMD64_SMCA_MCx_IPID(val), &ipid)) {
+		if (rdmsrq_on_cpu(m->extcpu, MSR_AMD64_SMCA_MCx_IPID(val), &ipid)) {
 			pr_err("Error reading IPID on CPU%d\n", m->extcpu);
 			return -EINVAL;
 		}
@@ -741,15 +742,15 @@ static void check_hw_inj_possible(void)
 		u64 status = MCI_STATUS_VAL, ipid;
 
 		/* Check whether bank is populated */
-		rdmsrl(MSR_AMD64_SMCA_MCx_IPID(bank), ipid);
+		rdmsrq(MSR_AMD64_SMCA_MCx_IPID(bank), ipid);
 		if (!ipid)
 			continue;
 
 		toggle_hw_mce_inject(cpu, true);
 
-		wrmsrl_safe(mca_msr_reg(bank, MCA_STATUS), status);
-		rdmsrl_safe(mca_msr_reg(bank, MCA_STATUS), &status);
-		wrmsrl_safe(mca_msr_reg(bank, MCA_STATUS), 0);
+		wrmsrq_safe(mca_msr_reg(bank, MCA_STATUS), status);
+		rdmsrq_safe(mca_msr_reg(bank, MCA_STATUS), &status);
+		wrmsrq_safe(mca_msr_reg(bank, MCA_STATUS), 0);
 
 		if (!status) {
 			hw_injection_possible = false;
diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c
index f863df0ff42c..efcf21e9552e 100644
--- a/arch/x86/kernel/cpu/mce/intel.c
+++ b/arch/x86/kernel/cpu/mce/intel.c
@@ -94,7 +94,7 @@ static bool cmci_supported(int *banks)
 	if (!boot_cpu_has(X86_FEATURE_APIC) || lapic_get_maxlvt() < 6)
 		return false;
 
-	rdmsrl(MSR_IA32_MCG_CAP, cap);
+	rdmsrq(MSR_IA32_MCG_CAP, cap);
 	*banks = min_t(unsigned, MAX_NR_BANKS, cap & MCG_BANKCNT_MASK);
 	return !!(cap & MCG_CMCI_P);
 }
@@ -106,7 +106,7 @@ static bool lmce_supported(void)
 	if (mca_cfg.lmce_disabled)
 		return false;
 
-	rdmsrl(MSR_IA32_MCG_CAP, tmp);
+	rdmsrq(MSR_IA32_MCG_CAP, tmp);
 
 	/*
 	 * LMCE depends on recovery support in the processor. Hence both
@@ -123,7 +123,7 @@ static bool lmce_supported(void)
 	 * WARN if the MSR isn't locked as init_ia32_feat_ctl() unconditionally
 	 * locks the MSR in the event that it wasn't already locked by BIOS.
 	 */
-	rdmsrl(MSR_IA32_FEAT_CTL, tmp);
+	rdmsrq(MSR_IA32_FEAT_CTL, tmp);
 	if (WARN_ON_ONCE(!(tmp & FEAT_CTL_LOCKED)))
 		return false;
 
@@ -141,9 +141,9 @@ static void cmci_set_threshold(int bank, int thresh)
 	u64 val;
 
 	raw_spin_lock_irqsave(&cmci_discover_lock, flags);
-	rdmsrl(MSR_IA32_MCx_CTL2(bank), val);
+	rdmsrq(MSR_IA32_MCx_CTL2(bank), val);
 	val &= ~MCI_CTL2_CMCI_THRESHOLD_MASK;
-	wrmsrl(MSR_IA32_MCx_CTL2(bank), val | thresh);
+	wrmsrq(MSR_IA32_MCx_CTL2(bank), val | thresh);
 	raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
 }
 
@@ -184,7 +184,7 @@ static bool cmci_skip_bank(int bank, u64 *val)
 	if (test_bit(bank, mce_banks_ce_disabled))
 		return true;
 
-	rdmsrl(MSR_IA32_MCx_CTL2(bank), *val);
+	rdmsrq(MSR_IA32_MCx_CTL2(bank), *val);
 
 	/* Already owned by someone else? */
 	if (*val & MCI_CTL2_CMCI_EN) {
@@ -232,8 +232,8 @@ static void cmci_claim_bank(int bank, u64 val, int bios_zero_thresh, int *bios_w
 	struct mca_storm_desc *storm = this_cpu_ptr(&storm_desc);
 
 	val |= MCI_CTL2_CMCI_EN;
-	wrmsrl(MSR_IA32_MCx_CTL2(bank), val);
-	rdmsrl(MSR_IA32_MCx_CTL2(bank), val);
+	wrmsrq(MSR_IA32_MCx_CTL2(bank), val);
+	rdmsrq(MSR_IA32_MCx_CTL2(bank), val);
 
 	/* If the enable bit did not stick, this bank should be polled. */
 	if (!(val & MCI_CTL2_CMCI_EN)) {
@@ -324,9 +324,9 @@ static void __cmci_disable_bank(int bank)
 
 	if (!test_bit(bank, this_cpu_ptr(mce_banks_owned)))
 		return;
-	rdmsrl(MSR_IA32_MCx_CTL2(bank), val);
+	rdmsrq(MSR_IA32_MCx_CTL2(bank), val);
 	val &= ~MCI_CTL2_CMCI_EN;
-	wrmsrl(MSR_IA32_MCx_CTL2(bank), val);
+	wrmsrq(MSR_IA32_MCx_CTL2(bank), val);
 	__clear_bit(bank, this_cpu_ptr(mce_banks_owned));
 
 	if ((val & MCI_CTL2_CMCI_THRESHOLD_MASK) == CMCI_STORM_THRESHOLD)
@@ -430,10 +430,10 @@ void intel_init_lmce(void)
 	if (!lmce_supported())
 		return;
 
-	rdmsrl(MSR_IA32_MCG_EXT_CTL, val);
+	rdmsrq(MSR_IA32_MCG_EXT_CTL, val);
 
 	if (!(val & MCG_EXT_CTL_LMCE_EN))
-		wrmsrl(MSR_IA32_MCG_EXT_CTL, val | MCG_EXT_CTL_LMCE_EN);
+		wrmsrq(MSR_IA32_MCG_EXT_CTL, val | MCG_EXT_CTL_LMCE_EN);
 }
 
 void intel_clear_lmce(void)
@@ -443,9 +443,9 @@ void intel_clear_lmce(void)
 	if (!lmce_supported())
 		return;
 
-	rdmsrl(MSR_IA32_MCG_EXT_CTL, val);
+	rdmsrq(MSR_IA32_MCG_EXT_CTL, val);
 	val &= ~MCG_EXT_CTL_LMCE_EN;
-	wrmsrl(MSR_IA32_MCG_EXT_CTL, val);
+	wrmsrq(MSR_IA32_MCG_EXT_CTL, val);
 }
 
 /*
@@ -460,10 +460,10 @@ static void intel_imc_init(struct cpuinfo_x86 *c)
 	case INTEL_SANDYBRIDGE_X:
 	case INTEL_IVYBRIDGE_X:
 	case INTEL_HASWELL_X:
-		if (rdmsrl_safe(MSR_ERROR_CONTROL, &error_control))
+		if (rdmsrq_safe(MSR_ERROR_CONTROL, &error_control))
 			return;
 		error_control |= 2;
-		wrmsrl_safe(MSR_ERROR_CONTROL, error_control);
+		wrmsrq_safe(MSR_ERROR_CONTROL, error_control);
 		break;
 	}
 }
diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h
index 95a504ece43e..b5ba598e54cb 100644
--- a/arch/x86/kernel/cpu/mce/internal.h
+++ b/arch/x86/kernel/cpu/mce/internal.h
@@ -312,7 +312,7 @@ static __always_inline void pentium_machine_check(struct pt_regs *regs) {}
 static __always_inline void winchip_machine_check(struct pt_regs *regs) {}
 #endif
 
-noinstr u64 mce_rdmsrl(u32 msr);
+noinstr u64 mce_rdmsrq(u32 msr);
 
 static __always_inline u32 mca_msr_reg(int bank, enum mca_msr reg)
 {
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 9c44b007c946..097e39327942 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -604,7 +604,7 @@ static bool __apply_microcode_amd(struct microcode_amd *mc, u32 *cur_rev,
 	if (!verify_sha256_digest(mc->hdr.patch_id, *cur_rev, (const u8 *)p_addr, psize))
 		return false;
 
-	native_wrmsrl(MSR_AMD64_PATCH_LOADER, p_addr);
+	native_wrmsrq(MSR_AMD64_PATCH_LOADER, p_addr);
 
 	if (x86_family(bsp_cpuid_1_eax) == 0x17) {
 		unsigned long p_addr_end = p_addr + psize - 1;
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index e8021d3e5882..a3bcb6d43f5c 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -37,6 +37,7 @@
 #include <asm/perf_event.h>
 #include <asm/processor.h>
 #include <asm/cmdline.h>
+#include <asm/msr.h>
 #include <asm/setup.h>
 
 #include "internal.h"
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 2a397da43923..371ca6eac00e 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -320,7 +320,7 @@ static enum ucode_state __apply_microcode(struct ucode_cpu_info *uci,
 	}
 
 	/* write microcode via MSR 0x79 */
-	native_wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits);
+	native_wrmsrq(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits);
 
 	rev = intel_get_microcode_revision();
 	if (rev != mc->hdr.rev)
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 3e2533954675..c78f860419d6 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -30,6 +30,7 @@
 #include <asm/reboot.h>
 #include <asm/nmi.h>
 #include <clocksource/hyperv_timer.h>
+#include <asm/msr.h>
 #include <asm/numa.h>
 #include <asm/svm.h>
 
@@ -70,7 +71,7 @@ u64 hv_get_non_nested_msr(unsigned int reg)
 	if (hv_is_synic_msr(reg) && ms_hyperv.paravisor_present)
 		hv_ivm_msr_read(reg, &value);
 	else
-		rdmsrl(reg, value);
+		rdmsrq(reg, value);
 	return value;
 }
 EXPORT_SYMBOL_GPL(hv_get_non_nested_msr);
@@ -82,9 +83,9 @@ void hv_set_non_nested_msr(unsigned int reg, u64 value)
 
 		/* Write proxy bit via wrmsl instruction */
 		if (hv_is_sint_msr(reg))
-			wrmsrl(reg, value | 1 << 20);
+			wrmsrq(reg, value | 1 << 20);
 	} else {
-		wrmsrl(reg, value);
+		wrmsrq(reg, value);
 	}
 }
 EXPORT_SYMBOL_GPL(hv_set_non_nested_msr);
@@ -345,7 +346,7 @@ static unsigned long hv_get_tsc_khz(void)
 {
 	unsigned long freq;
 
-	rdmsrl(HV_X64_MSR_TSC_FREQUENCY, freq);
+	rdmsrq(HV_X64_MSR_TSC_FREQUENCY, freq);
 
 	return freq / 1000;
 }
@@ -541,7 +542,7 @@ static void __init ms_hyperv_init_platform(void)
 		 */
 		u64	hv_lapic_frequency;
 
-		rdmsrl(HV_X64_MSR_APIC_FREQUENCY, hv_lapic_frequency);
+		rdmsrq(HV_X64_MSR_APIC_FREQUENCY, hv_lapic_frequency);
 		hv_lapic_frequency = div_u64(hv_lapic_frequency, HZ);
 		lapic_timer_period = hv_lapic_frequency;
 		pr_info("Hyper-V: LAPIC Timer Frequency: %#x\n",
@@ -574,7 +575,7 @@ static void __init ms_hyperv_init_platform(void)
 		 * setting of this MSR bit should happen before init_intel()
 		 * is called.
 		 */
-		wrmsrl(HV_X64_MSR_TSC_INVARIANT_CONTROL, HV_EXPOSE_INVARIANT_TSC);
+		wrmsrq(HV_X64_MSR_TSC_INVARIANT_CONTROL, HV_EXPOSE_INVARIANT_TSC);
 		setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE);
 	}
 
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index cf29681d01e0..d987b11c168c 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -22,6 +22,7 @@
 #include <linux/cpuhotplug.h>
 
 #include <asm/cpu_device_id.h>
+#include <asm/msr.h>
 #include <asm/resctrl.h>
 #include "internal.h"
 
@@ -145,10 +146,10 @@ static inline void cache_alloc_hsw_probe(void)
 	struct rdt_resource *r  = &hw_res->r_resctrl;
 	u64 max_cbm = BIT_ULL_MASK(20) - 1, l3_cbm_0;
 
-	if (wrmsrl_safe(MSR_IA32_L3_CBM_BASE, max_cbm))
+	if (wrmsrq_safe(MSR_IA32_L3_CBM_BASE, max_cbm))
 		return;
 
-	rdmsrl(MSR_IA32_L3_CBM_BASE, l3_cbm_0);
+	rdmsrq(MSR_IA32_L3_CBM_BASE, l3_cbm_0);
 
 	/* If all the bits were set in MSR, return success */
 	if (l3_cbm_0 != max_cbm)
@@ -309,7 +310,7 @@ static void mba_wrmsr_amd(struct msr_param *m)
 	unsigned int i;
 
 	for (i = m->low; i < m->high; i++)
-		wrmsrl(hw_res->msr_base + i, hw_dom->ctrl_val[i]);
+		wrmsrq(hw_res->msr_base + i, hw_dom->ctrl_val[i]);
 }
 
 /*
@@ -334,7 +335,7 @@ static void mba_wrmsr_intel(struct msr_param *m)
 
 	/*  Write the delay values for mba. */
 	for (i = m->low; i < m->high; i++)
-		wrmsrl(hw_res->msr_base + i, delay_bw_map(hw_dom->ctrl_val[i], m->res));
+		wrmsrq(hw_res->msr_base + i, delay_bw_map(hw_dom->ctrl_val[i], m->res));
 }
 
 static void cat_wrmsr(struct msr_param *m)
@@ -344,7 +345,7 @@ static void cat_wrmsr(struct msr_param *m)
 	unsigned int i;
 
 	for (i = m->low; i < m->high; i++)
-		wrmsrl(hw_res->msr_base + i, hw_dom->ctrl_val[i]);
+		wrmsrq(hw_res->msr_base + i, hw_dom->ctrl_val[i]);
 }
 
 u32 resctrl_arch_get_num_closid(struct rdt_resource *r)
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index a93ed7d2a160..591b0b44d260 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -23,6 +23,7 @@
 #include <linux/slab.h>
 
 #include <asm/cpu_device_id.h>
+#include <asm/msr.h>
 #include <asm/resctrl.h>
 
 #include "internal.h"
@@ -238,7 +239,7 @@ static int __rmid_read_phys(u32 prmid, enum resctrl_event_id eventid, u64 *val)
 	 * are error bits.
 	 */
 	wrmsr(MSR_IA32_QM_EVTSEL, eventid, prmid);
-	rdmsrl(MSR_IA32_QM_CTR, msr_val);
+	rdmsrq(MSR_IA32_QM_CTR, msr_val);
 
 	if (msr_val & RMID_VAL_ERROR)
 		return -EIO;
diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
index 92ea1472bde9..1190c48a16b2 100644
--- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
+++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
@@ -25,6 +25,7 @@
 #include <asm/cpu_device_id.h>
 #include <asm/resctrl.h>
 #include <asm/perf_event.h>
+#include <asm/msr.h>
 
 #include "../../events/perf_event.h" /* For X86_CONFIG() */
 #include "internal.h"
@@ -481,8 +482,8 @@ int resctrl_arch_pseudo_lock_fn(void *_plr)
 	 * the buffer and evict pseudo-locked memory read earlier from the
 	 * cache.
 	 */
-	saved_msr = __rdmsr(MSR_MISC_FEATURE_CONTROL);
-	__wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0);
+	saved_msr = native_rdmsrq(MSR_MISC_FEATURE_CONTROL);
+	native_wrmsrq(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits);
 	closid_p = this_cpu_read(pqr_state.cur_closid);
 	rmid_p = this_cpu_read(pqr_state.cur_rmid);
 	mem_r = plr->kmem;
@@ -494,7 +495,7 @@ int resctrl_arch_pseudo_lock_fn(void *_plr)
 	 * pseudo-locked followed by reading of kernel memory to load it
 	 * into the cache.
 	 */
-	__wrmsr(MSR_IA32_PQR_ASSOC, rmid_p, plr->closid);
+	native_wrmsr(MSR_IA32_PQR_ASSOC, rmid_p, plr->closid);
 
 	/*
 	 * Cache was flushed earlier. Now access kernel memory to read it
@@ -531,10 +532,10 @@ int resctrl_arch_pseudo_lock_fn(void *_plr)
 	 * Critical section end: restore closid with capacity bitmask that
 	 * does not overlap with pseudo-locked region.
 	 */
-	__wrmsr(MSR_IA32_PQR_ASSOC, rmid_p, closid_p);
+	native_wrmsr(MSR_IA32_PQR_ASSOC, rmid_p, closid_p);
 
 	/* Re-enable the hardware prefetcher(s) */
-	wrmsrl(MSR_MISC_FEATURE_CONTROL, saved_msr);
+	wrmsrq(MSR_MISC_FEATURE_CONTROL, saved_msr);
 	local_irq_enable();
 
 	plr->thread_done = 1;
@@ -904,7 +905,7 @@ int resctrl_arch_measure_cycles_lat_fn(void *_plr)
 	 * Disable hardware prefetchers.
 	 */
 	rdmsr(MSR_MISC_FEATURE_CONTROL, saved_low, saved_high);
-	wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0);
+	wrmsrq(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits);
 	mem_r = READ_ONCE(plr->kmem);
 	/*
 	 * Dummy execute of the time measurement to load the needed
@@ -1000,7 +1001,7 @@ static int measure_residency_fn(struct perf_event_attr *miss_attr,
 	 * Disable hardware prefetchers.
 	 */
 	rdmsr(MSR_MISC_FEATURE_CONTROL, saved_low, saved_high);
-	wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0);
+	wrmsrq(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits);
 
 	/* Initialize rest of local variables */
 	/*
@@ -1018,8 +1019,8 @@ static int measure_residency_fn(struct perf_event_attr *miss_attr,
 	 * used in L1 cache, second to capture accurate value that does not
 	 * include cache misses incurred because of instruction loads.
 	 */
-	rdpmcl(hit_pmcnum, hits_before);
-	rdpmcl(miss_pmcnum, miss_before);
+	hits_before = rdpmc(hit_pmcnum);
+	miss_before = rdpmc(miss_pmcnum);
 	/*
 	 * From SDM: Performing back-to-back fast reads are not guaranteed
 	 * to be monotonic.
@@ -1027,8 +1028,8 @@ static int measure_residency_fn(struct perf_event_attr *miss_attr,
 	 * before proceeding.
 	 */
 	rmb();
-	rdpmcl(hit_pmcnum, hits_before);
-	rdpmcl(miss_pmcnum, miss_before);
+	hits_before = rdpmc(hit_pmcnum);
+	miss_before = rdpmc(miss_pmcnum);
 	/*
 	 * Use LFENCE to ensure all previous instructions are retired
 	 * before proceeding.
@@ -1050,8 +1051,8 @@ static int measure_residency_fn(struct perf_event_attr *miss_attr,
 	 * before proceeding.
 	 */
 	rmb();
-	rdpmcl(hit_pmcnum, hits_after);
-	rdpmcl(miss_pmcnum, miss_after);
+	hits_after = rdpmc(hit_pmcnum);
+	miss_after = rdpmc(miss_pmcnum);
 	/*
 	 * Use LFENCE to ensure all previous instructions are retired
 	 * before proceeding.
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index cc4a54145c83..c85ace29ea3a 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -28,6 +28,7 @@
 
 #include <uapi/linux/magic.h>
 
+#include <asm/msr.h>
 #include <asm/resctrl.h>
 #include "internal.h"
 
@@ -1635,7 +1636,7 @@ void resctrl_arch_mon_event_config_read(void *_config_info)
 		pr_warn_once("Invalid event id %d\n", config_info->evtid);
 		return;
 	}
-	rdmsrl(MSR_IA32_EVT_CFG_BASE + index, msrval);
+	rdmsrq(MSR_IA32_EVT_CFG_BASE + index, msrval);
 
 	/* Report only the valid event configuration bits */
 	config_info->mon_config = msrval & MAX_EVT_CONFIG_BITS;
@@ -1707,7 +1708,7 @@ void resctrl_arch_mon_event_config_write(void *_config_info)
 		pr_warn_once("Invalid event id %d\n", config_info->evtid);
 		return;
 	}
-	wrmsr(MSR_IA32_EVT_CFG_BASE + index, config_info->mon_config, 0);
+	wrmsrq(MSR_IA32_EVT_CFG_BASE + index, config_info->mon_config);
 }
 
 static void mbm_config_write_domain(struct rdt_resource *r,
@@ -2326,14 +2327,14 @@ static void l3_qos_cfg_update(void *arg)
 {
 	bool *enable = arg;
 
-	wrmsrl(MSR_IA32_L3_QOS_CFG, *enable ? L3_QOS_CDP_ENABLE : 0ULL);
+	wrmsrq(MSR_IA32_L3_QOS_CFG, *enable ? L3_QOS_CDP_ENABLE : 0ULL);
 }
 
 static void l2_qos_cfg_update(void *arg)
 {
 	bool *enable = arg;
 
-	wrmsrl(MSR_IA32_L2_QOS_CFG, *enable ? L2_QOS_CDP_ENABLE : 0ULL);
+	wrmsrq(MSR_IA32_L2_QOS_CFG, *enable ? L2_QOS_CDP_ENABLE : 0ULL);
 }
 
 static inline bool is_mba_linear(void)
diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c
index 8ce352fc72ac..6722b2fc82cf 100644
--- a/arch/x86/kernel/cpu/sgx/main.c
+++ b/arch/x86/kernel/cpu/sgx/main.c
@@ -14,6 +14,7 @@
 #include <linux/slab.h>
 #include <linux/sysfs.h>
 #include <linux/vmalloc.h>
+#include <asm/msr.h>
 #include <asm/sgx.h>
 #include "driver.h"
 #include "encl.h"
@@ -871,7 +872,7 @@ void sgx_update_lepubkeyhash(u64 *lepubkeyhash)
 	WARN_ON_ONCE(preemptible());
 
 	for (i = 0; i < 4; i++)
-		wrmsrl(MSR_IA32_SGXLEPUBKEYHASH0 + i, lepubkeyhash[i]);
+		wrmsrq(MSR_IA32_SGXLEPUBKEYHASH0 + i, lepubkeyhash[i]);
 }
 
 const struct file_operations sgx_provision_fops = {
diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c
index 01456236a6dd..e35ccdc84910 100644
--- a/arch/x86/kernel/cpu/topology.c
+++ b/arch/x86/kernel/cpu/topology.c
@@ -30,6 +30,7 @@
 #include <asm/hypervisor.h>
 #include <asm/io_apic.h>
 #include <asm/mpspec.h>
+#include <asm/msr.h>
 #include <asm/smp.h>
 
 #include "cpu.h"
@@ -154,7 +155,7 @@ static __init bool check_for_real_bsp(u32 apic_id)
 	 * kernel must rely on the firmware enumeration order.
 	 */
 	if (has_apic_base) {
-		rdmsrl(MSR_IA32_APICBASE, msr);
+		rdmsrq(MSR_IA32_APICBASE, msr);
 		is_bsp = !!(msr & MSR_IA32_APICBASE_BSP);
 	}
 
diff --git a/arch/x86/kernel/cpu/topology_amd.c b/arch/x86/kernel/cpu/topology_amd.c
index eb799e2405f9..843b1655ab45 100644
--- a/arch/x86/kernel/cpu/topology_amd.c
+++ b/arch/x86/kernel/cpu/topology_amd.c
@@ -3,6 +3,7 @@
 
 #include <asm/apic.h>
 #include <asm/memtype.h>
+#include <asm/msr.h>
 #include <asm/processor.h>
 
 #include "cpu.h"
@@ -133,7 +134,7 @@ static void parse_fam10h_node_id(struct topo_scan *tscan)
 	if (!boot_cpu_has(X86_FEATURE_NODEID_MSR))
 		return;
 
-	rdmsrl(MSR_FAM10H_NODE_ID, nid.msr);
+	rdmsrq(MSR_FAM10H_NODE_ID, nid.msr);
 	store_node(tscan, nid.nodes_per_pkg + 1, nid.node_id);
 	tscan->c->topo.llc_id = nid.node_id;
 }
@@ -160,7 +161,7 @@ static void topoext_fixup(struct topo_scan *tscan)
 	if (msr_set_bit(0xc0011005, 54) <= 0)
 		return;
 
-	rdmsrl(0xc0011005, msrval);
+	rdmsrq(0xc0011005, msrval);
 	if (msrval & BIT_64(54)) {
 		set_cpu_cap(c, X86_FEATURE_TOPOEXT);
 		pr_info_once(FW_INFO "CPU: Re-enabling disabled Topology Extensions Support.\n");
diff --git a/arch/x86/kernel/cpu/tsx.c b/arch/x86/kernel/cpu/tsx.c
index b31ee4f1657a..49782724a943 100644
--- a/arch/x86/kernel/cpu/tsx.c
+++ b/arch/x86/kernel/cpu/tsx.c
@@ -12,6 +12,7 @@
 
 #include <asm/cmdline.h>
 #include <asm/cpu.h>
+#include <asm/msr.h>
 
 #include "cpu.h"
 
@@ -24,7 +25,7 @@ static void tsx_disable(void)
 {
 	u64 tsx;
 
-	rdmsrl(MSR_IA32_TSX_CTRL, tsx);
+	rdmsrq(MSR_IA32_TSX_CTRL, tsx);
 
 	/* Force all transactions to immediately abort */
 	tsx |= TSX_CTRL_RTM_DISABLE;
@@ -37,14 +38,14 @@ static void tsx_disable(void)
 	 */
 	tsx |= TSX_CTRL_CPUID_CLEAR;
 
-	wrmsrl(MSR_IA32_TSX_CTRL, tsx);
+	wrmsrq(MSR_IA32_TSX_CTRL, tsx);
 }
 
 static void tsx_enable(void)
 {
 	u64 tsx;
 
-	rdmsrl(MSR_IA32_TSX_CTRL, tsx);
+	rdmsrq(MSR_IA32_TSX_CTRL, tsx);
 
 	/* Enable the RTM feature in the cpu */
 	tsx &= ~TSX_CTRL_RTM_DISABLE;
@@ -56,7 +57,7 @@ static void tsx_enable(void)
 	 */
 	tsx &= ~TSX_CTRL_CPUID_CLEAR;
 
-	wrmsrl(MSR_IA32_TSX_CTRL, tsx);
+	wrmsrq(MSR_IA32_TSX_CTRL, tsx);
 }
 
 static enum tsx_ctrl_states x86_get_tsx_auto_mode(void)
@@ -115,13 +116,13 @@ static void tsx_clear_cpuid(void)
 	 */
 	if (boot_cpu_has(X86_FEATURE_RTM_ALWAYS_ABORT) &&
 	    boot_cpu_has(X86_FEATURE_TSX_FORCE_ABORT)) {
-		rdmsrl(MSR_TSX_FORCE_ABORT, msr);
+		rdmsrq(MSR_TSX_FORCE_ABORT, msr);
 		msr |= MSR_TFA_TSX_CPUID_CLEAR;
-		wrmsrl(MSR_TSX_FORCE_ABORT, msr);
+		wrmsrq(MSR_TSX_FORCE_ABORT, msr);
 	} else if (cpu_feature_enabled(X86_FEATURE_MSR_TSX_CTRL)) {
-		rdmsrl(MSR_IA32_TSX_CTRL, msr);
+		rdmsrq(MSR_IA32_TSX_CTRL, msr);
 		msr |= TSX_CTRL_CPUID_CLEAR;
-		wrmsrl(MSR_IA32_TSX_CTRL, msr);
+		wrmsrq(MSR_IA32_TSX_CTRL, msr);
 	}
 }
 
@@ -146,11 +147,11 @@ static void tsx_dev_mode_disable(void)
 	    !cpu_feature_enabled(X86_FEATURE_SRBDS_CTRL))
 		return;
 
-	rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_opt_ctrl);
+	rdmsrq(MSR_IA32_MCU_OPT_CTRL, mcu_opt_ctrl);
 
 	if (mcu_opt_ctrl & RTM_ALLOW) {
 		mcu_opt_ctrl &= ~RTM_ALLOW;
-		wrmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_opt_ctrl);
+		wrmsrq(MSR_IA32_MCU_OPT_CTRL, mcu_opt_ctrl);
 		setup_force_cpu_cap(X86_FEATURE_RTM_ALWAYS_ABORT);
 	}
 }
diff --git a/arch/x86/kernel/cpu/umwait.c b/arch/x86/kernel/cpu/umwait.c
index 2293efd6ffa6..933fcd7ff250 100644
--- a/arch/x86/kernel/cpu/umwait.c
+++ b/arch/x86/kernel/cpu/umwait.c
@@ -33,7 +33,7 @@ static DEFINE_MUTEX(umwait_lock);
 static void umwait_update_control_msr(void * unused)
 {
 	lockdep_assert_irqs_disabled();
-	wrmsr(MSR_IA32_UMWAIT_CONTROL, READ_ONCE(umwait_control_cached), 0);
+	wrmsrq(MSR_IA32_UMWAIT_CONTROL, READ_ONCE(umwait_control_cached));
 }
 
 /*
@@ -71,7 +71,7 @@ static int umwait_cpu_offline(unsigned int cpu)
 	 * the original control MSR value in umwait_init(). So there
 	 * is no race condition here.
 	 */
-	wrmsr(MSR_IA32_UMWAIT_CONTROL, orig_umwait_control_cached, 0);
+	wrmsrq(MSR_IA32_UMWAIT_CONTROL, orig_umwait_control_cached);
 
 	return 0;
 }
@@ -214,7 +214,7 @@ static int __init umwait_init(void)
 	 * changed. This is the only place where orig_umwait_control_cached
 	 * is modified.
 	 */
-	rdmsrl(MSR_IA32_UMWAIT_CONTROL, orig_umwait_control_cached);
+	rdmsrq(MSR_IA32_UMWAIT_CONTROL, orig_umwait_control_cached);
 
 	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "umwait:online",
 				umwait_cpu_online, umwait_cpu_offline);
diff --git a/arch/x86/kernel/cpu/zhaoxin.c b/arch/x86/kernel/cpu/zhaoxin.c
index 90eba7eb5335..89b1c8a70fe8 100644
--- a/arch/x86/kernel/cpu/zhaoxin.c
+++ b/arch/x86/kernel/cpu/zhaoxin.c
@@ -4,6 +4,7 @@
 
 #include <asm/cpu.h>
 #include <asm/cpufeature.h>
+#include <asm/msr.h>
 
 #include "cpu.h"