Merge tag 'kvm-x86-misc-6.17' of https://github.com/kvm-x86/linux into HEAD

KVM x86 misc changes for 6.17

 - Prevert the host's DEBUGCTL.FREEZE_IN_SMM (Intel only) when running the
   guest.  Failure to honor FREEZE_IN_SMM can bleed host state into the guest.

 - Explicitly check vmcs12.GUEST_DEBUGCTL on nested VM-Enter (Intel only) to
   prevent L1 from running L2 with features that KVM doesn't support, e.g. BTF.

 - Intercept SPEC_CTRL on AMD if the MSR shouldn't exist according to the
   vCPU's CPUID model.

 - Rework the MSR interception code so that the SVM and VMX APIs are more or
   less identical.

 - Recalculate all MSR intercepts from the "source" on MSR filter changes, and
   drop the dedicated "shadow" bitmaps (and their awful "max" size defines).

 - WARN and reject loading kvm-amd.ko instead of panicking the kernel if the
   nested SVM MSRPM offsets tracker can't handle an MSR.

 - Advertise support for LKGS (Load Kernel GS base), a new instruction that's
   loosely related to FRED, but is supported and enumerated independently.

 - Fix a user-triggerable WARN that syzkaller found by stuffing INIT_RECEIVED,
   a.k.a. WFS, and then putting the vCPU into VMX Root Mode (post-VMXON).  Use
   the same approach KVM uses for dealing with "impossible" emulation when
   running a !URG guest, and simply wait until KVM_RUN to detect that the vCPU
   has architecturally impossible state.

 - Add KVM_X86_DISABLE_EXITS_APERFMPERF to allow disabling interception of
   APERF/MPERF reads, so that a "properly" configured VM can "virtualize"
   APERF/MPERF (with many caveats).

 - Reject KVM_SET_TSC_KHZ if vCPUs have been created, as changing the "default"
   frequency is unsupported for VMs with a "secure" TSC, and there's no known
   use case for changing the default frequency for other VM types.

19 files changed, 638 insertions, 709 deletions

diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index 8897f509860c..18a5c3119e1a 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -49,7 +49,6 @@ KVM_X86_OP(set_idt)
 KVM_X86_OP(get_gdt)
 KVM_X86_OP(set_gdt)
 KVM_X86_OP(sync_dirty_debug_regs)
-KVM_X86_OP(set_dr6)
 KVM_X86_OP(set_dr7)
 KVM_X86_OP(cache_reg)
 KVM_X86_OP(get_rflags)
@@ -139,7 +138,7 @@ KVM_X86_OP(check_emulate_instruction)
 KVM_X86_OP(apic_init_signal_blocked)
 KVM_X86_OP_OPTIONAL(enable_l2_tlb_flush)
 KVM_X86_OP_OPTIONAL(migrate_timers)
-KVM_X86_OP(msr_filter_changed)
+KVM_X86_OP(recalc_msr_intercepts)
 KVM_X86_OP(complete_emulated_msr)
 KVM_X86_OP(vcpu_deliver_sipi_vector)
 KVM_X86_OP_OPTIONAL_RET0(vcpu_get_apicv_inhibit_reasons);
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index bfa6d05d38bc..c3cf1875606b 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1408,10 +1408,7 @@ struct kvm_arch {
 
 	gpa_t wall_clock;
 
-	bool mwait_in_guest;
-	bool hlt_in_guest;
-	bool pause_in_guest;
-	bool cstate_in_guest;
+	u64 disabled_exits;
 
 	s64 kvmclock_offset;
 
@@ -1687,6 +1684,12 @@ static inline u16 kvm_lapic_irq_dest_mode(bool dest_mode_logical)
 	return dest_mode_logical ? APIC_DEST_LOGICAL : APIC_DEST_PHYSICAL;
 }
 
+enum kvm_x86_run_flags {
+	KVM_RUN_FORCE_IMMEDIATE_EXIT	= BIT(0),
+	KVM_RUN_LOAD_GUEST_DR6		= BIT(1),
+	KVM_RUN_LOAD_DEBUGCTL		= BIT(2),
+};
+
 struct kvm_x86_ops {
 	const char *name;
 
@@ -1715,6 +1718,12 @@ struct kvm_x86_ops {
 	void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu);
 	void (*vcpu_put)(struct kvm_vcpu *vcpu);
 
+	/*
+	 * Mask of DEBUGCTL bits that are owned by the host, i.e. that need to
+	 * match the host's value even while the guest is active.
+	 */
+	const u64 HOST_OWNED_DEBUGCTL;
+
 	void (*update_exception_bitmap)(struct kvm_vcpu *vcpu);
 	int (*get_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr);
 	int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr);
@@ -1737,7 +1746,6 @@ struct kvm_x86_ops {
 	void (*get_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
 	void (*set_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
 	void (*sync_dirty_debug_regs)(struct kvm_vcpu *vcpu);
-	void (*set_dr6)(struct kvm_vcpu *vcpu, unsigned long value);
 	void (*set_dr7)(struct kvm_vcpu *vcpu, unsigned long value);
 	void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg);
 	unsigned long (*get_rflags)(struct kvm_vcpu *vcpu);
@@ -1768,7 +1776,7 @@ struct kvm_x86_ops {
 
 	int (*vcpu_pre_run)(struct kvm_vcpu *vcpu);
 	enum exit_fastpath_completion (*vcpu_run)(struct kvm_vcpu *vcpu,
-						  bool force_immediate_exit);
+						  u64 run_flags);
 	int (*handle_exit)(struct kvm_vcpu *vcpu,
 		enum exit_fastpath_completion exit_fastpath);
 	int (*skip_emulated_instruction)(struct kvm_vcpu *vcpu);
@@ -1900,7 +1908,7 @@ struct kvm_x86_ops {
 	int (*enable_l2_tlb_flush)(struct kvm_vcpu *vcpu);
 
 	void (*migrate_timers)(struct kvm_vcpu *vcpu);
-	void (*msr_filter_changed)(struct kvm_vcpu *vcpu);
+	void (*recalc_msr_intercepts)(struct kvm_vcpu *vcpu);
 	int (*complete_emulated_msr)(struct kvm_vcpu *vcpu, int err);
 
 	void (*vcpu_deliver_sipi_vector)(struct kvm_vcpu *vcpu, u8 vector);
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 5cfb5d74dd5f..c29127ac626a 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -419,6 +419,7 @@
 #define DEBUGCTLMSR_FREEZE_PERFMON_ON_PMI	(1UL << 12)
 #define DEBUGCTLMSR_FREEZE_IN_SMM_BIT	14
 #define DEBUGCTLMSR_FREEZE_IN_SMM	(1UL << DEBUGCTLMSR_FREEZE_IN_SMM_BIT)
+#define DEBUGCTLMSR_RTM_DEBUG		BIT(15)
 
 #define MSR_PEBS_FRONTEND		0x000003f7
 
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index f84bc0569c9c..e2836a255b16 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -979,6 +979,7 @@ void kvm_set_cpu_caps(void)
 		F(FSRS),
 		F(FSRC),
 		F(WRMSRNS),
+		X86_64_F(LKGS),
 		F(AMX_FP16),
 		F(AVX_IFMA),
 		F(LAM),
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index 4ce30db65828..4518b4e0552f 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -21,6 +21,8 @@
 #define APIC_BROADCAST			0xFF
 #define X2APIC_BROADCAST		0xFFFFFFFFul
 
+#define X2APIC_MSR(r) (APIC_BASE_MSR + ((r) >> 4))
+
 enum lapic_mode {
 	LAPIC_MODE_DISABLED = 0,
 	LAPIC_MODE_INVALID = X2APIC_ENABLE,
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 8427a48b8b7a..b7fd2e869998 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -185,12 +185,87 @@ void recalc_intercepts(struct vcpu_svm *svm)
 }
 
 /*
+ * This array (and its actual size) holds the set of offsets (indexing by chunk
+ * size) to process when merging vmcb12's MSRPM with vmcb01's MSRPM.  Note, the
+ * set of MSRs for which interception is disabled in vmcb01 is per-vCPU, e.g.
+ * based on CPUID features.  This array only tracks MSRs that *might* be passed
+ * through to the guest.
+ *
+ * Hardcode the capacity of the array based on the maximum number of _offsets_.
+ * MSRs are batched together, so there are fewer offsets than MSRs.
+ */
+static int nested_svm_msrpm_merge_offsets[7] __ro_after_init;
+static int nested_svm_nr_msrpm_merge_offsets __ro_after_init;
+typedef unsigned long nsvm_msrpm_merge_t;
+
+int __init nested_svm_init_msrpm_merge_offsets(void)
+{
+	static const u32 merge_msrs[] __initconst = {
+		MSR_STAR,
+		MSR_IA32_SYSENTER_CS,
+		MSR_IA32_SYSENTER_EIP,
+		MSR_IA32_SYSENTER_ESP,
+	#ifdef CONFIG_X86_64
+		MSR_GS_BASE,
+		MSR_FS_BASE,
+		MSR_KERNEL_GS_BASE,
+		MSR_LSTAR,
+		MSR_CSTAR,
+		MSR_SYSCALL_MASK,
+	#endif
+		MSR_IA32_SPEC_CTRL,
+		MSR_IA32_PRED_CMD,
+		MSR_IA32_FLUSH_CMD,
+		MSR_IA32_APERF,
+		MSR_IA32_MPERF,
+		MSR_IA32_LASTBRANCHFROMIP,
+		MSR_IA32_LASTBRANCHTOIP,
+		MSR_IA32_LASTINTFROMIP,
+		MSR_IA32_LASTINTTOIP,
+	};
+	int i, j;
+
+	for (i = 0; i < ARRAY_SIZE(merge_msrs); i++) {
+		int bit_nr = svm_msrpm_bit_nr(merge_msrs[i]);
+		u32 offset;
+
+		if (WARN_ON(bit_nr < 0))
+			return -EIO;
+
+		/*
+		 * Merging is done in chunks to reduce the number of accesses
+		 * to L1's bitmap.
+		 */
+		offset = bit_nr / BITS_PER_BYTE / sizeof(nsvm_msrpm_merge_t);
+
+		for (j = 0; j < nested_svm_nr_msrpm_merge_offsets; j++) {
+			if (nested_svm_msrpm_merge_offsets[j] == offset)
+				break;
+		}
+
+		if (j < nested_svm_nr_msrpm_merge_offsets)
+			continue;
+
+		if (WARN_ON(j >= ARRAY_SIZE(nested_svm_msrpm_merge_offsets)))
+			return -EIO;
+
+		nested_svm_msrpm_merge_offsets[j] = offset;
+		nested_svm_nr_msrpm_merge_offsets++;
+	}
+
+	return 0;
+}
+
+/*
  * Merge L0's (KVM) and L1's (Nested VMCB) MSR permission bitmaps. The function
  * is optimized in that it only merges the parts where KVM MSR permission bitmap
  * may contain zero bits.
  */
-static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm)
+static bool nested_svm_merge_msrpm(struct kvm_vcpu *vcpu)
 {
+	struct vcpu_svm *svm = to_svm(vcpu);
+	nsvm_msrpm_merge_t *msrpm02 = svm->nested.msrpm;
+	nsvm_msrpm_merge_t *msrpm01 = svm->msrpm;
 	int i;
 
 	/*
@@ -205,7 +280,7 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm)
 	if (!svm->nested.force_msr_bitmap_recalc) {
 		struct hv_vmcb_enlightenments *hve = &svm->nested.ctl.hv_enlightenments;
 
-		if (kvm_hv_hypercall_enabled(&svm->vcpu) &&
+		if (kvm_hv_hypercall_enabled(vcpu) &&
 		    hve->hv_enlightenments_control.msr_bitmap &&
 		    (svm->nested.ctl.clean & BIT(HV_VMCB_NESTED_ENLIGHTENMENTS)))
 			goto set_msrpm_base_pa;
@@ -215,25 +290,17 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm)
 	if (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT)))
 		return true;
 
-	for (i = 0; i < MSRPM_OFFSETS; i++) {
-		u32 value, p;
-		u64 offset;
+	for (i = 0; i < nested_svm_nr_msrpm_merge_offsets; i++) {
+		const int p = nested_svm_msrpm_merge_offsets[i];
+		nsvm_msrpm_merge_t l1_val;
+		gpa_t gpa;
 
-		if (msrpm_offsets[i] == 0xffffffff)
-			break;
+		gpa = svm->nested.ctl.msrpm_base_pa + (p * sizeof(l1_val));
 
-		p      = msrpm_offsets[i];
-
-		/* x2apic msrs are intercepted always for the nested guest */
-		if (is_x2apic_msrpm_offset(p))
-			continue;
-
-		offset = svm->nested.ctl.msrpm_base_pa + (p * 4);
-
-		if (kvm_vcpu_read_guest(&svm->vcpu, offset, &value, 4))
+		if (kvm_vcpu_read_guest(vcpu, gpa, &l1_val, sizeof(l1_val)))
 			return false;
 
-		svm->nested.msrpm[p] = svm->msrpm[p] | value;
+		msrpm02[p] = msrpm01[p] | l1_val;
 	}
 
 	svm->nested.force_msr_bitmap_recalc = false;
@@ -937,7 +1004,7 @@ int nested_svm_vmrun(struct kvm_vcpu *vcpu)
 	if (enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12, true))
 		goto out_exit_err;
 
-	if (nested_svm_vmrun_msrpm(svm))
+	if (nested_svm_merge_msrpm(vcpu))
 		goto out;
 
 out_exit_err:
@@ -1230,7 +1297,6 @@ int svm_allocate_nested(struct vcpu_svm *svm)
 	svm->nested.msrpm = svm_vcpu_alloc_msrpm();
 	if (!svm->nested.msrpm)
 		goto err_free_vmcb02;
-	svm_vcpu_init_msrpm(&svm->vcpu, svm->nested.msrpm);
 
 	svm->nested.initialized = true;
 	return 0;
@@ -1290,26 +1356,26 @@ void svm_leave_nested(struct kvm_vcpu *vcpu)
 
 static int nested_svm_exit_handled_msr(struct vcpu_svm *svm)
 {
-	u32 offset, msr, value;
-	int write, mask;
+	gpa_t base = svm->nested.ctl.msrpm_base_pa;
+	int write, bit_nr;
+	u8 value, mask;
+	u32 msr;
 
 	if (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT)))
 		return NESTED_EXIT_HOST;
 
 	msr    = svm->vcpu.arch.regs[VCPU_REGS_RCX];
-	offset = svm_msrpm_offset(msr);
+	bit_nr = svm_msrpm_bit_nr(msr);
 	write  = svm->vmcb->control.exit_info_1 & 1;
-	mask   = 1 << ((2 * (msr & 0xf)) + write);
 
-	if (offset == MSR_INVALID)
+	if (bit_nr < 0)
 		return NESTED_EXIT_DONE;
 
-	/* Offset is in 32 bit units but need in 8 bit units */
-	offset *= 4;
-
-	if (kvm_vcpu_read_guest(&svm->vcpu, svm->nested.ctl.msrpm_base_pa + offset, &value, 4))
+	if (kvm_vcpu_read_guest(&svm->vcpu, base + bit_nr / BITS_PER_BYTE,
+				&value, sizeof(value)))
 		return NESTED_EXIT_DONE;
 
+	mask = BIT(write) << (bit_nr & (BITS_PER_BYTE - 1));
 	return (value & mask) ? NESTED_EXIT_DONE : NESTED_EXIT_HOST;
 }
 
@@ -1819,13 +1885,11 @@ out_free:
 
 static bool svm_get_nested_state_pages(struct kvm_vcpu *vcpu)
 {
-	struct vcpu_svm *svm = to_svm(vcpu);
-
 	if (WARN_ON(!is_guest_mode(vcpu)))
 		return true;
 
 	if (!vcpu->arch.pdptrs_from_userspace &&
-	    !nested_npt_enabled(svm) && is_pae_paging(vcpu))
+	    !nested_npt_enabled(to_svm(vcpu)) && is_pae_paging(vcpu))
 		/*
 		 * Reload the guest's PDPTRs since after a migration
 		 * the guest CR3 might be restored prior to setting the nested
@@ -1834,7 +1898,7 @@ static bool svm_get_nested_state_pages(struct kvm_vcpu *vcpu)
 		if (CC(!load_pdptrs(vcpu, vcpu->arch.cr3)))
 			return false;
 
-	if (!nested_svm_vmrun_msrpm(svm)) {
+	if (!nested_svm_merge_msrpm(vcpu)) {
 		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		vcpu->run->internal.suberror =
 			KVM_INTERNAL_ERROR_EMULATION;
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index b201f77fcd49..d061ebb430ce 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -4390,16 +4390,17 @@ int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in)
 				    count, in);
 }
 
-static void sev_es_vcpu_after_set_cpuid(struct vcpu_svm *svm)
+void sev_es_recalc_msr_intercepts(struct kvm_vcpu *vcpu)
 {
-	struct kvm_vcpu *vcpu = &svm->vcpu;
-
-	if (boot_cpu_has(X86_FEATURE_V_TSC_AUX)) {
-		bool v_tsc_aux = guest_cpu_cap_has(vcpu, X86_FEATURE_RDTSCP) ||
-				 guest_cpu_cap_has(vcpu, X86_FEATURE_RDPID);
+	/* Clear intercepts on MSRs that are context switched by hardware. */
+	svm_disable_intercept_for_msr(vcpu, MSR_AMD64_SEV_ES_GHCB, MSR_TYPE_RW);
+	svm_disable_intercept_for_msr(vcpu, MSR_EFER, MSR_TYPE_RW);
+	svm_disable_intercept_for_msr(vcpu, MSR_IA32_CR_PAT, MSR_TYPE_RW);
 
-		set_msr_interception(vcpu, svm->msrpm, MSR_TSC_AUX, v_tsc_aux, v_tsc_aux);
-	}
+	if (boot_cpu_has(X86_FEATURE_V_TSC_AUX))
+		svm_set_intercept_for_msr(vcpu, MSR_TSC_AUX, MSR_TYPE_RW,
+					  !guest_cpu_cap_has(vcpu, X86_FEATURE_RDTSCP) &&
+					  !guest_cpu_cap_has(vcpu, X86_FEATURE_RDPID));
 
 	/*
 	 * For SEV-ES, accesses to MSR_IA32_XSS should not be intercepted if
@@ -4413,11 +4414,9 @@ static void sev_es_vcpu_after_set_cpuid(struct vcpu_svm *svm)
 	 * XSAVES being exposed to the guest so that KVM can at least honor
 	 * guest CPUID for RDMSR and WRMSR.
 	 */
-	if (guest_cpu_cap_has(vcpu, X86_FEATURE_XSAVES) &&
-	    guest_cpuid_has(vcpu, X86_FEATURE_XSAVES))
-		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_XSS, 1, 1);
-	else
-		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_XSS, 0, 0);
+	svm_set_intercept_for_msr(vcpu, MSR_IA32_XSS, MSR_TYPE_RW,
+				  !guest_cpu_cap_has(vcpu, X86_FEATURE_XSAVES) ||
+				  !guest_cpuid_has(vcpu, X86_FEATURE_XSAVES));
 }
 
 void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm)
@@ -4429,16 +4428,12 @@ void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm)
 	best = kvm_find_cpuid_entry(vcpu, 0x8000001F);
 	if (best)
 		vcpu->arch.reserved_gpa_bits &= ~(1UL << (best->ebx & 0x3f));
-
-	if (sev_es_guest(svm->vcpu.kvm))
-		sev_es_vcpu_after_set_cpuid(svm);
 }
 
 static void sev_es_init_vmcb(struct vcpu_svm *svm)
 {
 	struct kvm_sev_info *sev = to_kvm_sev_info(svm->vcpu.kvm);
 	struct vmcb *vmcb = svm->vmcb01.ptr;
-	struct kvm_vcpu *vcpu = &svm->vcpu;
 
 	svm->vmcb->control.nested_ctl |= SVM_NESTED_CTL_SEV_ES_ENABLE;
 
@@ -4496,10 +4491,6 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm)
 
 	/* Can't intercept XSETBV, HV can't modify XCR0 directly */
 	svm_clr_intercept(svm, INTERCEPT_XSETBV);
-
-	/* Clear intercepts on selected MSRs */
-	set_msr_interception(vcpu, svm->msrpm, MSR_EFER, 1, 1);
-	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_CR_PAT, 1, 1);
 }
 
 void sev_init_vmcb(struct vcpu_svm *svm)
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 7f0df9dbc232..f59026e8b855 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -72,8 +72,6 @@ MODULE_DEVICE_TABLE(x86cpu, svm_cpu_id);
 
 static bool erratum_383_found __read_mostly;
 
-u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly;
-
 /*
  * Set osvw_len to higher value when updated Revision Guides
  * are published and we know what the new status bits are
@@ -82,72 +80,6 @@ static uint64_t osvw_len = 4, osvw_status;
 
 static DEFINE_PER_CPU(u64, current_tsc_ratio);
 
-#define X2APIC_MSR(x)	(APIC_BASE_MSR + (x >> 4))
-
-static const struct svm_direct_access_msrs {
-	u32 index;   /* Index of the MSR */
-	bool always; /* True if intercept is initially cleared */
-} direct_access_msrs[MAX_DIRECT_ACCESS_MSRS] = {
-	{ .index = MSR_STAR,				.always = true  },
-	{ .index = MSR_IA32_SYSENTER_CS,		.always = true  },
-	{ .index = MSR_IA32_SYSENTER_EIP,		.always = false },
-	{ .index = MSR_IA32_SYSENTER_ESP,		.always = false },
-#ifdef CONFIG_X86_64
-	{ .index = MSR_GS_BASE,				.always = true  },
-	{ .index = MSR_FS_BASE,				.always = true  },
-	{ .index = MSR_KERNEL_GS_BASE,			.always = true  },
-	{ .index = MSR_LSTAR,				.always = true  },
-	{ .index = MSR_CSTAR,				.always = true  },
-	{ .index = MSR_SYSCALL_MASK,			.always = true  },
-#endif
-	{ .index = MSR_IA32_SPEC_CTRL,			.always = false },
-	{ .index = MSR_IA32_PRED_CMD,			.always = false },
-	{ .index = MSR_IA32_FLUSH_CMD,			.always = false },
-	{ .index = MSR_IA32_DEBUGCTLMSR,		.always = false },
-	{ .index = MSR_IA32_LASTBRANCHFROMIP,		.always = false },
-	{ .index = MSR_IA32_LASTBRANCHTOIP,		.always = false },
-	{ .index = MSR_IA32_LASTINTFROMIP,		.always = false },
-	{ .index = MSR_IA32_LASTINTTOIP,		.always = false },
-	{ .index = MSR_IA32_XSS,			.always = false },
-	{ .index = MSR_EFER,				.always = false },
-	{ .index = MSR_IA32_CR_PAT,			.always = false },
-	{ .index = MSR_AMD64_SEV_ES_GHCB,		.always = true  },
-	{ .index = MSR_TSC_AUX,				.always = false },
-	{ .index = X2APIC_MSR(APIC_ID),			.always = false },
-	{ .index = X2APIC_MSR(APIC_LVR),		.always = false },
-	{ .index = X2APIC_MSR(APIC_TASKPRI),		.always = false },
-	{ .index = X2APIC_MSR(APIC_ARBPRI),		.always = false },
-	{ .index = X2APIC_MSR(APIC_PROCPRI),		.always = false },
-	{ .index = X2APIC_MSR(APIC_EOI),		.always = false },
-	{ .index = X2APIC_MSR(APIC_RRR),		.always = false },
-	{ .index = X2APIC_MSR(APIC_LDR),		.always = false },
-	{ .index = X2APIC_MSR(APIC_DFR),		.always = false },
-	{ .index = X2APIC_MSR(APIC_SPIV),		.always = false },
-	{ .index = X2APIC_MSR(APIC_ISR),		.always = false },
-	{ .index = X2APIC_MSR(APIC_TMR),		.always = false },
-	{ .index = X2APIC_MSR(APIC_IRR),		.always = false },
-	{ .index = X2APIC_MSR(APIC_ESR),		.always = false },
-	{ .index = X2APIC_MSR(APIC_ICR),		.always = false },
-	{ .index = X2APIC_MSR(APIC_ICR2),		.always = false },
-
-	/*
-	 * Note:
-	 * AMD does not virtualize APIC TSC-deadline timer mode, but it is
-	 * emulated by KVM. When setting APIC LVTT (0x832) register bit 18,
-	 * the AVIC hardware would generate GP fault. Therefore, always
-	 * intercept the MSR 0x832, and do not setup direct_access_msr.
-	 */
-	{ .index = X2APIC_MSR(APIC_LVTTHMR),		.always = false },
-	{ .index = X2APIC_MSR(APIC_LVTPC),		.always = false },
-	{ .index = X2APIC_MSR(APIC_LVT0),		.always = false },
-	{ .index = X2APIC_MSR(APIC_LVT1),		.always = false },
-	{ .index = X2APIC_MSR(APIC_LVTERR),		.always = false },
-	{ .index = X2APIC_MSR(APIC_TMICT),		.always = false },
-	{ .index = X2APIC_MSR(APIC_TMCCT),		.always = false },
-	{ .index = X2APIC_MSR(APIC_TDCR),		.always = false },
-	{ .index = MSR_INVALID,				.always = false },
-};
-
 /*
  * These 2 parameters are used to config the controls for Pause-Loop Exiting:
  * pause_filter_count: On processors that support Pause filtering(indicated
@@ -265,33 +197,6 @@ static DEFINE_MUTEX(vmcb_dump_mutex);
  */
 static int tsc_aux_uret_slot __read_mostly = -1;
 
-static const u32 msrpm_ranges[] = {0, 0xc0000000, 0xc0010000};
-
-#define NUM_MSR_MAPS ARRAY_SIZE(msrpm_ranges)
-#define MSRS_RANGE_SIZE 2048
-#define MSRS_IN_RANGE (MSRS_RANGE_SIZE * 8 / 2)
-
-u32 svm_msrpm_offset(u32 msr)
-{
-	u32 offset;
-	int i;
-
-	for (i = 0; i < NUM_MSR_MAPS; i++) {
-		if (msr < msrpm_ranges[i] ||
-		    msr >= msrpm_ranges[i] + MSRS_IN_RANGE)
-			continue;
-
-		offset  = (msr - msrpm_ranges[i]) / 4; /* 4 msrs per u8 */
-		offset += (i * MSRS_RANGE_SIZE);       /* add range offset */
-
-		/* Now we have the u8 offset - but need the u32 offset */
-		return offset / 4;
-	}
-
-	/* MSR not in any range */
-	return MSR_INVALID;
-}
-
 static int get_npt_level(void)
 {
 #ifdef CONFIG_X86_64
@@ -758,50 +663,8 @@ static void clr_dr_intercepts(struct vcpu_svm *svm)
 	recalc_intercepts(svm);
 }
 
-static int direct_access_msr_slot(u32 msr)
-{
-	u32 i;
-
-	for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++)
-		if (direct_access_msrs[i].index == msr)
-			return i;
-
-	return -ENOENT;
-}
-
-static void set_shadow_msr_intercept(struct kvm_vcpu *vcpu, u32 msr, int read,
-				     int write)
-{
-	struct vcpu_svm *svm = to_svm(vcpu);
-	int slot = direct_access_msr_slot(msr);
-
-	if (slot == -ENOENT)
-		return;
-
-	/* Set the shadow bitmaps to the desired intercept states */
-	if (read)
-		set_bit(slot, svm->shadow_msr_intercept.read);
-	else
-		clear_bit(slot, svm->shadow_msr_intercept.read);
-
-	if (write)
-		set_bit(slot, svm->shadow_msr_intercept.write);
-	else
-		clear_bit(slot, svm->shadow_msr_intercept.write);
-}
-
-static bool valid_msr_intercept(u32 index)
-{
-	return direct_access_msr_slot(index) != -ENOENT;
-}
-
 static bool msr_write_intercepted(struct kvm_vcpu *vcpu, u32 msr)
 {
-	u8 bit_write;
-	unsigned long tmp;
-	u32 offset;
-	u32 *msrpm;
-
 	/*
 	 * For non-nested case:
 	 * If the L01 MSR bitmap does not intercept the MSR, then we need to
@@ -811,90 +674,102 @@ static bool msr_write_intercepted(struct kvm_vcpu *vcpu, u32 msr)
 	 * If the L02 MSR bitmap does not intercept the MSR, then we need to
 	 * save it.
 	 */
-	msrpm = is_guest_mode(vcpu) ? to_svm(vcpu)->nested.msrpm:
-				      to_svm(vcpu)->msrpm;
-
-	offset    = svm_msrpm_offset(msr);
-	bit_write = 2 * (msr & 0x0f) + 1;
-	tmp       = msrpm[offset];
+	void *msrpm = is_guest_mode(vcpu) ? to_svm(vcpu)->nested.msrpm :
+					    to_svm(vcpu)->msrpm;
 
-	BUG_ON(offset == MSR_INVALID);
-
-	return test_bit(bit_write, &tmp);
+	return svm_test_msr_bitmap_write(msrpm, msr);
 }
 
-static void set_msr_interception_bitmap(struct kvm_vcpu *vcpu, u32 *msrpm,
-					u32 msr, int read, int write)
+void svm_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type, bool set)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
-	u8 bit_read, bit_write;
-	unsigned long tmp;
-	u32 offset;
+	void *msrpm = svm->msrpm;
 
-	/*
-	 * If this warning triggers extend the direct_access_msrs list at the
-	 * beginning of the file
-	 */
-	WARN_ON(!valid_msr_intercept(msr));
-
-	/* Enforce non allowed MSRs to trap */
-	if (read && !kvm_msr_allowed(vcpu, msr, KVM_MSR_FILTER_READ))
-		read = 0;
-
-	if (write && !kvm_msr_allowed(vcpu, msr, KVM_MSR_FILTER_WRITE))
-		write = 0;
-
-	offset    = svm_msrpm_offset(msr);
-	bit_read  = 2 * (msr & 0x0f);
-	bit_write = 2 * (msr & 0x0f) + 1;
-	tmp       = msrpm[offset];
-
-	BUG_ON(offset == MSR_INVALID);
-
-	read  ? clear_bit(bit_read,  &tmp) : set_bit(bit_read,  &tmp);
-	write ? clear_bit(bit_write, &tmp) : set_bit(bit_write, &tmp);
+	/* Don't disable interception for MSRs userspace wants to handle. */
+	if (type & MSR_TYPE_R) {
+		if (!set && kvm_msr_allowed(vcpu, msr, KVM_MSR_FILTER_READ))
+			svm_clear_msr_bitmap_read(msrpm, msr);
+		else
+			svm_set_msr_bitmap_read(msrpm, msr);
+	}
 
-	msrpm[offset] = tmp;
+	if (type & MSR_TYPE_W) {
+		if (!set && kvm_msr_allowed(vcpu, msr, KVM_MSR_FILTER_WRITE))
+			svm_clear_msr_bitmap_write(msrpm, msr);
+		else
+			svm_set_msr_bitmap_write(msrpm, msr);
+	}
 
 	svm_hv_vmcb_dirty_nested_enlightenments(vcpu);
 	svm->nested.force_msr_bitmap_recalc = true;
 }
 
-void set_msr_interception(struct kvm_vcpu *vcpu, u32 *msrpm, u32 msr,
-			  int read, int write)
-{
-	set_shadow_msr_intercept(vcpu, msr, read, write);
-	set_msr_interception_bitmap(vcpu, msrpm, msr, read, write);
-}
-
-u32 *svm_vcpu_alloc_msrpm(void)
+void *svm_alloc_permissions_map(unsigned long size, gfp_t gfp_mask)
 {
-	unsigned int order = get_order(MSRPM_SIZE);
-	struct page *pages = alloc_pages(GFP_KERNEL_ACCOUNT, order);
-	u32 *msrpm;
+	unsigned int order = get_order(size);
+	struct page *pages = alloc_pages(gfp_mask, order);
+	void *pm;
 
 	if (!pages)
 		return NULL;
 
-	msrpm = page_address(pages);
-	memset(msrpm, 0xff, PAGE_SIZE * (1 << order));
+	/*
+	 * Set all bits in the permissions map so that all MSR and I/O accesses
+	 * are intercepted by default.
+	 */
+	pm = page_address(pages);
+	memset(pm, 0xff, PAGE_SIZE * (1 << order));
 
-	return msrpm;
+	return pm;
 }
 
-void svm_vcpu_init_msrpm(struct kvm_vcpu *vcpu, u32 *msrpm)
+static void svm_recalc_lbr_msr_intercepts(struct kvm_vcpu *vcpu)
 {
-	int i;
+	bool intercept = !(to_svm(vcpu)->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK);
 
-	for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++) {
-		if (!direct_access_msrs[i].always)
-			continue;
-		set_msr_interception(vcpu, msrpm, direct_access_msrs[i].index, 1, 1);
-	}
+	svm_set_intercept_for_msr(vcpu, MSR_IA32_LASTBRANCHFROMIP, MSR_TYPE_RW, intercept);
+	svm_set_intercept_for_msr(vcpu, MSR_IA32_LASTBRANCHTOIP, MSR_TYPE_RW, intercept);
+	svm_set_intercept_for_msr(vcpu, MSR_IA32_LASTINTFROMIP, MSR_TYPE_RW, intercept);
+	svm_set_intercept_for_msr(vcpu, MSR_IA32_LASTINTTOIP, MSR_TYPE_RW, intercept);
+
+	if (sev_es_guest(vcpu->kvm))
+		svm_set_intercept_for_msr(vcpu, MSR_IA32_DEBUGCTLMSR, MSR_TYPE_RW, intercept);
 }
 
 void svm_set_x2apic_msr_interception(struct vcpu_svm *svm, bool intercept)
 {
+	static const u32 x2avic_passthrough_msrs[] = {
+		X2APIC_MSR(APIC_ID),
+		X2APIC_MSR(APIC_LVR),
+		X2APIC_MSR(APIC_TASKPRI),
+		X2APIC_MSR(APIC_ARBPRI),
+		X2APIC_MSR(APIC_PROCPRI),
+		X2APIC_MSR(APIC_EOI),
+		X2APIC_MSR(APIC_RRR),
+		X2APIC_MSR(APIC_LDR),
+		X2APIC_MSR(APIC_DFR),
+		X2APIC_MSR(APIC_SPIV),
+		X2APIC_MSR(APIC_ISR),
+		X2APIC_MSR(APIC_TMR),
+		X2APIC_MSR(APIC_IRR),
+		X2APIC_MSR(APIC_ESR),
+		X2APIC_MSR(APIC_ICR),
+		X2APIC_MSR(APIC_ICR2),
+
+		/*
+		 * Note!  Always intercept LVTT, as TSC-deadline timer mode
+		 * isn't virtualized by hardware, and the CPU will generate a
+		 * #GP instead of a #VMEXIT.
+		 */
+		X2APIC_MSR(APIC_LVTTHMR),
+		X2APIC_MSR(APIC_LVTPC),
+		X2APIC_MSR(APIC_LVT0),
+		X2APIC_MSR(APIC_LVT1),
+		X2APIC_MSR(APIC_LVTERR),
+		X2APIC_MSR(APIC_TMICT),
+		X2APIC_MSR(APIC_TMCCT),
+		X2APIC_MSR(APIC_TDCR),
+	};
 	int i;
 
 	if (intercept == svm->x2avic_msrs_intercepted)
@@ -903,84 +778,79 @@ void svm_set_x2apic_msr_interception(struct vcpu_svm *svm, bool intercept)
 	if (!x2avic_enabled)
 		return;
 
-	for (i = 0; i < MAX_DIRECT_ACCESS_MSRS; i++) {
-		int index = direct_access_msrs[i].index;
-
-		if ((index < APIC_BASE_MSR) ||
-		    (index > APIC_BASE_MSR + 0xff))
-			continue;
-		set_msr_interception(&svm->vcpu, svm->msrpm, index,
-				     !intercept, !intercept);
-	}
+	for (i = 0; i < ARRAY_SIZE(x2avic_passthrough_msrs); i++)
+		svm_set_intercept_for_msr(&svm->vcpu, x2avic_passthrough_msrs[i],
+					  MSR_TYPE_RW, intercept);
 
 	svm->x2avic_msrs_intercepted = intercept;
 }
 
-void svm_vcpu_free_msrpm(u32 *msrpm)
+void svm_vcpu_free_msrpm(void *msrpm)
 {
 	__free_pages(virt_to_page(msrpm), get_order(MSRPM_SIZE));
 }
 
-static void svm_msr_filter_changed(struct kvm_vcpu *vcpu)
+static void svm_recalc_msr_intercepts(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
-	u32 i;
 
-	/*
-	 * Set intercept permissions for all direct access MSRs again. They
-	 * will automatically get filtered through the MSR filter, so we are
-	 * back in sync after this.
-	 */
-	for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++) {
-		u32 msr = direct_access_msrs[i].index;
-		u32 read = test_bit(i, svm->shadow_msr_intercept.read);
-		u32 write = test_bit(i, svm->shadow_msr_intercept.write);
-
-		set_msr_interception_bitmap(vcpu, svm->msrpm, msr, read, write);
-	}
-}
-
-static void add_msr_offset(u32 offset)
-{
-	int i;
+	svm_disable_intercept_for_msr(vcpu, MSR_STAR, MSR_TYPE_RW);
+	svm_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW);
 
-	for (i = 0; i < MSRPM_OFFSETS; ++i) {
-
-		/* Offset already in list? */
-		if (msrpm_offsets[i] == offset)
-			return;
+#ifdef CONFIG_X86_64
+	svm_disable_intercept_for_msr(vcpu, MSR_GS_BASE, MSR_TYPE_RW);
+	svm_disable_intercept_for_msr(vcpu, MSR_FS_BASE, MSR_TYPE_RW);
+	svm_disable_intercept_for_msr(vcpu, MSR_KERNEL_GS_BASE, MSR_TYPE_RW);
+	svm_disable_intercept_for_msr(vcpu, MSR_LSTAR, MSR_TYPE_RW);
+	svm_disable_intercept_for_msr(vcpu, MSR_CSTAR, MSR_TYPE_RW);
+	svm_disable_intercept_for_msr(vcpu, MSR_SYSCALL_MASK, MSR_TYPE_RW);
+#endif
 
-		/* Slot used by another offset? */
-		if (msrpm_offsets[i] != MSR_INVALID)
-			continue;
+	if (lbrv)
+		svm_recalc_lbr_msr_intercepts(vcpu);
 
-		/* Add offset to list */
-		msrpm_offsets[i] = offset;
+	if (cpu_feature_enabled(X86_FEATURE_IBPB))
+		svm_set_intercept_for_msr(vcpu, MSR_IA32_PRED_CMD, MSR_TYPE_W,
+					  !guest_has_pred_cmd_msr(vcpu));
 
-		return;
-	}
+	if (cpu_feature_enabled(X86_FEATURE_FLUSH_L1D))
+		svm_set_intercept_for_msr(vcpu, MSR_IA32_FLUSH_CMD, MSR_TYPE_W,
+					  !guest_cpu_cap_has(vcpu, X86_FEATURE_FLUSH_L1D));
 
 	/*
-	 * If this BUG triggers the msrpm_offsets table has an overflow. Just
-	 * increase MSRPM_OFFSETS in this case.
+	 * Disable interception of SPEC_CTRL if KVM doesn't need to manually
+	 * context switch the MSR (SPEC_CTRL is virtualized by the CPU), or if
+	 * the guest has a non-zero SPEC_CTRL value, i.e. is likely actively
+	 * using SPEC_CTRL.
 	 */
-	BUG();
-}
-
-static void init_msrpm_offsets(void)
-{
-	int i;
+	if (cpu_feature_enabled(X86_FEATURE_V_SPEC_CTRL))
+		svm_set_intercept_for_msr(vcpu, MSR_IA32_SPEC_CTRL, MSR_TYPE_RW,
+					  !guest_has_spec_ctrl_msr(vcpu));
+	else
+		svm_set_intercept_for_msr(vcpu, MSR_IA32_SPEC_CTRL, MSR_TYPE_RW,
+					  !svm->spec_ctrl);
 
-	memset(msrpm_offsets, 0xff, sizeof(msrpm_offsets));
+	/*
+	 * Intercept SYSENTER_EIP and SYSENTER_ESP when emulating an Intel CPU,
+	 * as AMD hardware only store 32 bits, whereas Intel CPUs track 64 bits.
+	 */
+	svm_set_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW,
+				  guest_cpuid_is_intel_compatible(vcpu));
+	svm_set_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW,
+				  guest_cpuid_is_intel_compatible(vcpu));
 
-	for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++) {
-		u32 offset;
+	if (kvm_aperfmperf_in_guest(vcpu->kvm)) {
+		svm_disable_intercept_for_msr(vcpu, MSR_IA32_APERF, MSR_TYPE_R);
+		svm_disable_intercept_for_msr(vcpu, MSR_IA32_MPERF, MSR_TYPE_R);
+	}
 
-		offset = svm_msrpm_offset(direct_access_msrs[i].index);
-		BUG_ON(offset == MSR_INVALID);
+	if (sev_es_guest(vcpu->kvm))
+		sev_es_recalc_msr_intercepts(vcpu);
 
-		add_msr_offset(offset);
-	}
+	/*
+	 * x2APIC intercepts are modified on-demand and cannot be filtered by
+	 * userspace.
+	 */
 }
 
 void svm_copy_lbrs(struct vmcb *to_vmcb, struct vmcb *from_vmcb)
@@ -999,13 +869,7 @@ void svm_enable_lbrv(struct kvm_vcpu *vcpu)
 	struct vcpu_svm *svm = to_svm(vcpu);
 
 	svm->vmcb->control.virt_ext |= LBR_CTL_ENABLE_MASK;
-	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 1, 1);
-	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1);
-	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1);
-	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1);
-
-	if (sev_es_guest(vcpu->kvm))
-		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_DEBUGCTLMSR, 1, 1);
+	svm_recalc_lbr_msr_intercepts(vcpu);
 
 	/* Move the LBR msrs to the vmcb02 so that the guest can see them. */
 	if (is_guest_mode(vcpu))
@@ -1017,12 +881,8 @@ static void svm_disable_lbrv(struct kvm_vcpu *vcpu)
 	struct vcpu_svm *svm = to_svm(vcpu);
 
 	KVM_BUG_ON(sev_es_guest(vcpu->kvm), vcpu->kvm);
-
 	svm->vmcb->control.virt_ext &= ~LBR_CTL_ENABLE_MASK;
-	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 0, 0);
-	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 0, 0);
-	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 0, 0);
-	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 0, 0);
+	svm_recalc_lbr_msr_intercepts(vcpu);
 
 	/*
 	 * Move the LBR msrs back to the vmcb01 to avoid copying them
@@ -1177,9 +1037,10 @@ void svm_write_tsc_multiplier(struct kvm_vcpu *vcpu)
 }
 
 /* Evaluate instruction intercepts that depend on guest CPUID features. */
-static void svm_recalc_instruction_intercepts(struct kvm_vcpu *vcpu,
-					      struct vcpu_svm *svm)
+static void svm_recalc_instruction_intercepts(struct kvm_vcpu *vcpu)
 {
+	struct vcpu_svm *svm = to_svm(vcpu);
+
 	/*
 	 * Intercept INVPCID if shadow paging is enabled to sync/free shadow
 	 * roots, or if INVPCID is disabled in the guest to inject #UD.
@@ -1198,24 +1059,11 @@ static void svm_recalc_instruction_intercepts(struct kvm_vcpu *vcpu,
 		else
 			svm_set_intercept(svm, INTERCEPT_RDTSCP);
 	}
-}
-
-static inline void init_vmcb_after_set_cpuid(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_svm *svm = to_svm(vcpu);
 
 	if (guest_cpuid_is_intel_compatible(vcpu)) {
-		/*
-		 * We must intercept SYSENTER_EIP and SYSENTER_ESP
-		 * accesses because the processor only stores 32 bits.
-		 * For the same reason we cannot use virtual VMLOAD/VMSAVE.
-		 */
 		svm_set_intercept(svm, INTERCEPT_VMLOAD);
 		svm_set_intercept(svm, INTERCEPT_VMSAVE);
 		svm->vmcb->control.virt_ext &= ~VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK;
-
-		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SYSENTER_EIP, 0, 0);
-		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SYSENTER_ESP, 0, 0);
 	} else {
 		/*
 		 * If hardware supports Virtual VMLOAD VMSAVE then enable it
@@ -1226,12 +1074,15 @@ static inline void init_vmcb_after_set_cpuid(struct kvm_vcpu *vcpu)
 			svm_clr_intercept(svm, INTERCEPT_VMSAVE);
 			svm->vmcb->control.virt_ext |= VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK;
 		}
-		/* No need to intercept these MSRs */
-		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SYSENTER_EIP, 1, 1);
-		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SYSENTER_ESP, 1, 1);
 	}
 }
 
+static void svm_recalc_intercepts_after_set_cpuid(struct kvm_vcpu *vcpu)
+{
+	svm_recalc_instruction_intercepts(vcpu);
+	svm_recalc_msr_intercepts(vcpu);
+}
+
 static void init_vmcb(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -1354,15 +1205,6 @@ static void init_vmcb(struct kvm_vcpu *vcpu)
 		svm_clr_intercept(svm, INTERCEPT_PAUSE);
 	}
 
-	svm_recalc_instruction_intercepts(vcpu, svm);
-
-	/*
-	 * If the host supports V_SPEC_CTRL then disable the interception
-	 * of MSR_IA32_SPEC_CTRL.
-	 */
-	if (boot_cpu_has(X86_FEATURE_V_SPEC_CTRL))
-		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SPEC_CTRL, 1, 1);
-
 	if (kvm_vcpu_apicv_active(vcpu))
 		avic_init_vmcb(svm, vmcb);
 
@@ -1382,7 +1224,8 @@ static void init_vmcb(struct kvm_vcpu *vcpu)
 		sev_init_vmcb(svm);
 
 	svm_hv_init_vmcb(vmcb);
-	init_vmcb_after_set_cpuid(vcpu);
+
+	svm_recalc_intercepts_after_set_cpuid(vcpu);
 
 	vmcb_mark_all_dirty(vmcb);
 
@@ -1393,8 +1236,6 @@ static void __svm_vcpu_reset(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	svm_vcpu_init_msrpm(vcpu, svm->msrpm);
-
 	svm_init_osvw(vcpu);
 
 	if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_STUFF_FEATURE_MSRS))
@@ -1499,7 +1340,7 @@ static void svm_vcpu_free(struct kvm_vcpu *vcpu)
 	sev_free_vcpu(vcpu);
 
 	__free_page(__sme_pa_to_page(svm->vmcb01.pa));
-	__free_pages(virt_to_page(svm->msrpm), get_order(MSRPM_SIZE));
+	svm_vcpu_free_msrpm(svm->msrpm);
 }
 
 #ifdef CONFIG_CPU_MITIGATIONS
@@ -2883,12 +2724,11 @@ static int svm_get_feature_msr(u32 msr, u64 *data)
 	return 0;
 }
 
-static bool
-sev_es_prevent_msr_access(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
+static bool sev_es_prevent_msr_access(struct kvm_vcpu *vcpu,
+				      struct msr_data *msr_info)
 {
 	return sev_es_guest(vcpu->kvm) &&
 	       vcpu->arch.guest_state_protected &&
-	       svm_msrpm_offset(msr_info->index) != MSR_INVALID &&
 	       !msr_write_intercepted(vcpu, msr_info->index);
 }
 
@@ -3119,11 +2959,11 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 		 *
 		 * For nested:
 		 * The handling of the MSR bitmap for L2 guests is done in
-		 * nested_svm_vmrun_msrpm.
+		 * nested_svm_merge_msrpm().
 		 * We update the L1 MSR bit as well since it will end up
 		 * touching the MSR anyway now.
 		 */
-		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SPEC_CTRL, 1, 1);
+		svm_disable_intercept_for_msr(vcpu, MSR_IA32_SPEC_CTRL, MSR_TYPE_RW);
 		break;
 	case MSR_AMD64_VIRT_SPEC_CTRL:
 		if (!msr->host_initiated &&
@@ -3189,8 +3029,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 
 		/*
 		 * TSC_AUX is usually changed only during boot and never read
-		 * directly.  Intercept TSC_AUX instead of exposing it to the
-		 * guest via direct_access_msrs, and switch it via user return.
+		 * directly.  Intercept TSC_AUX and switch it via user return.
 		 */
 		preempt_disable();
 		ret = kvm_set_user_return_msr(tsc_aux_uret_slot, data, -1ull);
@@ -4392,9 +4231,9 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, bool spec_ctrl_in
 	guest_state_exit_irqoff();
 }
 
-static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu,
-					  bool force_immediate_exit)
+static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags)
 {
+	bool force_immediate_exit = run_flags & KVM_RUN_FORCE_IMMEDIATE_EXIT;
 	struct vcpu_svm *svm = to_svm(vcpu);
 	bool spec_ctrl_intercepted = msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL);
 
@@ -4441,10 +4280,13 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu,
 	svm_hv_update_vp_id(svm->vmcb, vcpu);
 
 	/*
-	 * Run with all-zero DR6 unless needed, so that we can get the exact cause
-	 * of a #DB.
+	 * Run with all-zero DR6 unless the guest can write DR6 freely, so that
+	 * KVM can get the exact cause of a #DB.  Note, loading guest DR6 from
+	 * KVM's snapshot is only necessary when DR accesses won't exit.
 	 */
-	if (likely(!(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)))
+	if (unlikely(run_flags & KVM_RUN_LOAD_GUEST_DR6))
+		svm_set_dr6(vcpu, vcpu->arch.dr6);
+	else if (likely(!(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)))
 		svm_set_dr6(vcpu, DR6_ACTIVE_LOW);
 
 	clgi();
@@ -4624,20 +4466,10 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 	if (guest_cpuid_is_intel_compatible(vcpu))
 		guest_cpu_cap_clear(vcpu, X86_FEATURE_V_VMSAVE_VMLOAD);
 
-	svm_recalc_instruction_intercepts(vcpu, svm);
-
-	if (boot_cpu_has(X86_FEATURE_IBPB))
-		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_PRED_CMD, 0,
-				     !!guest_has_pred_cmd_msr(vcpu));
-
-	if (boot_cpu_has(X86_FEATURE_FLUSH_L1D))
-		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_FLUSH_CMD, 0,
-				     !!guest_cpu_cap_has(vcpu, X86_FEATURE_FLUSH_L1D));
-
 	if (sev_guest(vcpu->kvm))
 		sev_vcpu_after_set_cpuid(svm);
 
-	init_vmcb_after_set_cpuid(vcpu);
+	svm_recalc_intercepts_after_set_cpuid(vcpu);
 }
 
 static bool svm_has_wbinvd_exit(void)
@@ -5188,7 +5020,7 @@ static int svm_vm_init(struct kvm *kvm)
 	}
 
 	if (!pause_filter_count || !pause_filter_thresh)
-		kvm->arch.pause_in_guest = true;
+		kvm_disable_exits(kvm, KVM_X86_DISABLE_EXITS_PAUSE);
 
 	if (enable_apicv) {
 		int ret = avic_vm_init(kvm);
@@ -5255,7 +5087,6 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.set_idt = svm_set_idt,
 	.get_gdt = svm_get_gdt,
 	.set_gdt = svm_set_gdt,
-	.set_dr6 = svm_set_dr6,
 	.set_dr7 = svm_set_dr7,
 	.sync_dirty_debug_regs = svm_sync_dirty_debug_regs,
 	.cache_reg = svm_cache_reg,
@@ -5340,7 +5171,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 
 	.apic_init_signal_blocked = svm_apic_init_signal_blocked,
 
-	.msr_filter_changed = svm_msr_filter_changed,
+	.recalc_msr_intercepts = svm_recalc_msr_intercepts,
 	.complete_emulated_msr = svm_complete_emulated_msr,
 
 	.vcpu_deliver_sipi_vector = svm_vcpu_deliver_sipi_vector,
@@ -5476,11 +5307,8 @@ static __init void svm_set_cpu_caps(void)
 
 static __init int svm_hardware_setup(void)
 {
-	int cpu;
-	struct page *iopm_pages;
 	void *iopm_va;
-	int r;
-	unsigned int order = get_order(IOPM_SIZE);
+	int cpu, r;
 
 	/*
 	 * NX is required for shadow paging and for NPT if the NX huge pages
@@ -5492,17 +5320,6 @@ static __init int svm_hardware_setup(void)
 	}
 	kvm_enable_efer_bits(EFER_NX);
 
-	iopm_pages = alloc_pages(GFP_KERNEL, order);
-
-	if (!iopm_pages)
-		return -ENOMEM;
-
-	iopm_va = page_address(iopm_pages);
-	memset(iopm_va, 0xff, PAGE_SIZE * (1 << order));
-	iopm_base = __sme_page_pa(iopm_pages);
-
-	init_msrpm_offsets();
-
 	kvm_caps.supported_xcr0 &= ~(XFEATURE_MASK_BNDREGS |
 				     XFEATURE_MASK_BNDCSR);
 
@@ -5536,6 +5353,10 @@ static __init int svm_hardware_setup(void)
 	if (nested) {
 		pr_info("Nested Virtualization enabled\n");
 		kvm_enable_efer_bits(EFER_SVME | EFER_LMSLE);
+
+		r = nested_svm_init_msrpm_merge_offsets();
+		if (r)
+			return r;
 	}
 
 	/*
@@ -5567,6 +5388,13 @@ static __init int svm_hardware_setup(void)
 		else
 			pr_info("LBR virtualization supported\n");
 	}
+
+	iopm_va = svm_alloc_permissions_map(IOPM_SIZE, GFP_KERNEL);
+	if (!iopm_va)
+		return -ENOMEM;
+
+	iopm_base = __sme_set(__pa(iopm_va));
+
 	/*
 	 * Note, SEV setup consumes npt_enabled and enable_mmio_caching (which
 	 * may be modified by svm_adjust_mmio_mask()), as well as nrips.
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index b5cd1927b009..81c7b147b731 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -44,9 +44,6 @@ static inline struct page *__sme_pa_to_page(unsigned long pa)
 #define	IOPM_SIZE PAGE_SIZE * 3
 #define	MSRPM_SIZE PAGE_SIZE * 2
 
-#define MAX_DIRECT_ACCESS_MSRS	48
-#define MSRPM_OFFSETS	32
-extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly;
 extern bool npt_enabled;
 extern int nrips;
 extern int vgif;
@@ -189,8 +186,11 @@ struct svm_nested_state {
 	u64 vmcb12_gpa;
 	u64 last_vmcb12_gpa;
 
-	/* These are the merged vectors */
-	u32 *msrpm;
+	/*
+	 * The MSR permissions map used for vmcb02, which is the merge result
+	 * of vmcb01 and vmcb12
+	 */
+	void *msrpm;
 
 	/* A VMRUN has started but has not yet been performed, so
 	 * we cannot inject a nested vmexit yet.  */
@@ -271,7 +271,7 @@ struct vcpu_svm {
 	 */
 	u64 virt_spec_ctrl;
 
-	u32 *msrpm;
+	void *msrpm;
 
 	ulong nmi_iret_rip;
 
@@ -326,12 +326,6 @@ struct vcpu_svm {
 	struct list_head ir_list;
 	spinlock_t ir_list_lock;
 
-	/* Save desired MSR intercept (read: pass-through) state */
-	struct {
-		DECLARE_BITMAP(read, MAX_DIRECT_ACCESS_MSRS);
-		DECLARE_BITMAP(write, MAX_DIRECT_ACCESS_MSRS);
-	} shadow_msr_intercept;
-
 	struct vcpu_sev_es_state sev_es;
 
 	bool guest_state_loaded;
@@ -621,17 +615,74 @@ static inline void svm_vmgexit_no_action(struct vcpu_svm *svm, u64 data)
 	svm_vmgexit_set_return_code(svm, GHCB_HV_RESP_NO_ACTION, data);
 }
 
-/* svm.c */
-#define MSR_INVALID				0xffffffffU
+/*
+ * The MSRPM is 8KiB in size, divided into four 2KiB ranges (the fourth range
+ * is reserved).  Each MSR within a range is covered by two bits, one each for
+ * read (bit 0) and write (bit 1), where a bit value of '1' means intercepted.
+ */
+#define SVM_MSRPM_BYTES_PER_RANGE 2048
+#define SVM_BITS_PER_MSR 2
+#define SVM_MSRS_PER_BYTE (BITS_PER_BYTE / SVM_BITS_PER_MSR)
+#define SVM_MSRS_PER_RANGE (SVM_MSRPM_BYTES_PER_RANGE * SVM_MSRS_PER_BYTE)
+static_assert(SVM_MSRS_PER_RANGE == 8192);
+#define SVM_MSRPM_OFFSET_MASK (SVM_MSRS_PER_RANGE - 1)
+
+static __always_inline int svm_msrpm_bit_nr(u32 msr)
+{
+	int range_nr;
+
+	switch (msr & ~SVM_MSRPM_OFFSET_MASK) {
+	case 0:
+		range_nr = 0;
+		break;
+	case 0xc0000000:
+		range_nr = 1;
+		break;
+	case 0xc0010000:
+		range_nr = 2;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return range_nr * SVM_MSRPM_BYTES_PER_RANGE * BITS_PER_BYTE +
+	       (msr & SVM_MSRPM_OFFSET_MASK) * SVM_BITS_PER_MSR;
+}
+
+#define __BUILD_SVM_MSR_BITMAP_HELPER(rtype, action, bitop, access, bit_rw)	\
+static inline rtype svm_##action##_msr_bitmap_##access(unsigned long *bitmap,	\
+						       u32 msr)			\
+{										\
+	int bit_nr;								\
+										\
+	bit_nr = svm_msrpm_bit_nr(msr);						\
+	if (bit_nr < 0)								\
+		return (rtype)true;						\
+										\
+	return bitop##_bit(bit_nr + bit_rw, bitmap);				\
+}
+
+#define BUILD_SVM_MSR_BITMAP_HELPERS(ret_type, action, bitop)			\
+	__BUILD_SVM_MSR_BITMAP_HELPER(ret_type, action, bitop, read,  0)	\
+	__BUILD_SVM_MSR_BITMAP_HELPER(ret_type, action, bitop, write, 1)
+
+BUILD_SVM_MSR_BITMAP_HELPERS(bool, test, test)
+BUILD_SVM_MSR_BITMAP_HELPERS(void, clear, __clear)
+BUILD_SVM_MSR_BITMAP_HELPERS(void, set, __set)
 
 #define DEBUGCTL_RESERVED_BITS (~DEBUGCTLMSR_LBR)
 
+/* svm.c */
 extern bool dump_invalid_vmcb;
 
-u32 svm_msrpm_offset(u32 msr);
-u32 *svm_vcpu_alloc_msrpm(void);
-void svm_vcpu_init_msrpm(struct kvm_vcpu *vcpu, u32 *msrpm);
-void svm_vcpu_free_msrpm(u32 *msrpm);
+void *svm_alloc_permissions_map(unsigned long size, gfp_t gfp_mask);
+
+static inline void *svm_vcpu_alloc_msrpm(void)
+{
+	return svm_alloc_permissions_map(MSRPM_SIZE, GFP_KERNEL_ACCOUNT);
+}
+
+void svm_vcpu_free_msrpm(void *msrpm);
 void svm_copy_lbrs(struct vmcb *to_vmcb, struct vmcb *from_vmcb);
 void svm_enable_lbrv(struct kvm_vcpu *vcpu);
 void svm_update_lbrv(struct kvm_vcpu *vcpu);
@@ -651,6 +702,20 @@ void svm_set_x2apic_msr_interception(struct vcpu_svm *svm, bool disable);
 void svm_complete_interrupt_delivery(struct kvm_vcpu *vcpu, int delivery_mode,
 				     int trig_mode, int vec);
 
+void svm_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type, bool set);
+
+static inline void svm_disable_intercept_for_msr(struct kvm_vcpu *vcpu,
+						 u32 msr, int type)
+{
+	svm_set_intercept_for_msr(vcpu, msr, type, false);
+}
+
+static inline void svm_enable_intercept_for_msr(struct kvm_vcpu *vcpu,
+						u32 msr, int type)
+{
+	svm_set_intercept_for_msr(vcpu, msr, type, true);
+}
+
 /* nested.c */
 
 #define NESTED_EXIT_HOST	0	/* Exit handled on host level */
@@ -679,6 +744,8 @@ static inline bool nested_exit_on_nmi(struct vcpu_svm *svm)
 	return vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_NMI);
 }
 
+int __init nested_svm_init_msrpm_merge_offsets(void);
+
 int enter_svm_guest_mode(struct kvm_vcpu *vcpu,
 			 u64 vmcb_gpa, struct vmcb *vmcb12, bool from_vmrun);
 void svm_leave_nested(struct kvm_vcpu *vcpu);
@@ -762,6 +829,7 @@ void sev_init_vmcb(struct vcpu_svm *svm);
 void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm);
 int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in);
 void sev_es_vcpu_reset(struct vcpu_svm *svm);
+void sev_es_recalc_msr_intercepts(struct kvm_vcpu *vcpu);
 void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector);
 void sev_es_prepare_switch_to_guest(struct vcpu_svm *svm, struct sev_es_save_area *hostsa);
 void sev_es_unmap_ghcb(struct vcpu_svm *svm);
diff --git a/arch/x86/kvm/vmx/common.h b/arch/x86/kvm/vmx/common.h
index a0c5e8781c33..bc5ece76533a 100644
--- a/arch/x86/kvm/vmx/common.h
+++ b/arch/x86/kvm/vmx/common.h
@@ -53,8 +53,6 @@ struct vcpu_vt {
 #ifdef CONFIG_X86_64
 	u64		msr_host_kernel_gs_base;
 #endif
-
-	unsigned long	host_debugctlmsr;
 };
 
 #ifdef CONFIG_KVM_INTEL_TDX
diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c
index a986fc45145e..4259af6a2c6a 100644
--- a/arch/x86/kvm/vmx/main.c
+++ b/arch/x86/kvm/vmx/main.c
@@ -175,12 +175,12 @@ static int vt_vcpu_pre_run(struct kvm_vcpu *vcpu)
 	return vmx_vcpu_pre_run(vcpu);
 }
 
-static fastpath_t vt_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
+static fastpath_t vt_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags)
 {
 	if (is_td_vcpu(vcpu))
-		return tdx_vcpu_run(vcpu, force_immediate_exit);
+		return tdx_vcpu_run(vcpu, run_flags);
 
-	return vmx_vcpu_run(vcpu, force_immediate_exit);
+	return vmx_vcpu_run(vcpu, run_flags);
 }
 
 static int vt_handle_exit(struct kvm_vcpu *vcpu,
@@ -220,7 +220,7 @@ static int vt_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	return vmx_get_msr(vcpu, msr_info);
 }
 
-static void vt_msr_filter_changed(struct kvm_vcpu *vcpu)
+static void vt_recalc_msr_intercepts(struct kvm_vcpu *vcpu)
 {
 	/*
 	 * TDX doesn't allow VMM to configure interception of MSR accesses.
@@ -231,7 +231,7 @@ static void vt_msr_filter_changed(struct kvm_vcpu *vcpu)
 	if (is_td_vcpu(vcpu))
 		return;
 
-	vmx_msr_filter_changed(vcpu);
+	vmx_recalc_msr_intercepts(vcpu);
 }
 
 static int vt_complete_emulated_msr(struct kvm_vcpu *vcpu, int err)
@@ -489,14 +489,6 @@ static void vt_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
 	vmx_set_gdt(vcpu, dt);
 }
 
-static void vt_set_dr6(struct kvm_vcpu *vcpu, unsigned long val)
-{
-	if (is_td_vcpu(vcpu))
-		return;
-
-	vmx_set_dr6(vcpu, val);
-}
-
 static void vt_set_dr7(struct kvm_vcpu *vcpu, unsigned long val)
 {
 	if (is_td_vcpu(vcpu))
@@ -923,6 +915,8 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 	.vcpu_load = vt_op(vcpu_load),
 	.vcpu_put = vt_op(vcpu_put),
 
+	.HOST_OWNED_DEBUGCTL = VMX_HOST_OWNED_DEBUGCTL_BITS,
+
 	.update_exception_bitmap = vt_op(update_exception_bitmap),
 	.get_feature_msr = vmx_get_feature_msr,
 	.get_msr = vt_op(get_msr),
@@ -943,7 +937,6 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 	.set_idt = vt_op(set_idt),
 	.get_gdt = vt_op(get_gdt),
 	.set_gdt = vt_op(set_gdt),
-	.set_dr6 = vt_op(set_dr6),
 	.set_dr7 = vt_op(set_dr7),
 	.sync_dirty_debug_regs = vt_op(sync_dirty_debug_regs),
 	.cache_reg = vt_op(cache_reg),
@@ -1034,7 +1027,7 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 	.apic_init_signal_blocked = vt_op(apic_init_signal_blocked),
 	.migrate_timers = vmx_migrate_timers,
 
-	.msr_filter_changed = vt_op(msr_filter_changed),
+	.recalc_msr_intercepts = vt_op(recalc_msr_intercepts),
 	.complete_emulated_msr = vt_op(complete_emulated_msr),
 
 	.vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector,
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 7211c71d4241..b8ea1969113d 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -715,6 +715,12 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
 	nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0,
 					 MSR_IA32_FLUSH_CMD, MSR_TYPE_W);
 
+	nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0,
+					 MSR_IA32_APERF, MSR_TYPE_R);
+
+	nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0,
+					 MSR_IA32_MPERF, MSR_TYPE_R);
+
 	kvm_vcpu_unmap(vcpu, &map);
 
 	vmx->nested.force_msr_bitmap_recalc = false;
@@ -2663,10 +2669,11 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 	if (vmx->nested.nested_run_pending &&
 	    (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) {
 		kvm_set_dr(vcpu, 7, vmcs12->guest_dr7);
-		vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl);
+		vmx_guest_debugctl_write(vcpu, vmcs12->guest_ia32_debugctl &
+					       vmx_get_supported_debugctl(vcpu, false));
 	} else {
 		kvm_set_dr(vcpu, 7, vcpu->arch.dr7);
-		vmcs_write64(GUEST_IA32_DEBUGCTL, vmx->nested.pre_vmenter_debugctl);
+		vmx_guest_debugctl_write(vcpu, vmx->nested.pre_vmenter_debugctl);
 	}
 	if (kvm_mpx_supported() && (!vmx->nested.nested_run_pending ||
 	    !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS)))
@@ -3156,7 +3163,8 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
 		return -EINVAL;
 
 	if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) &&
-	    CC(!kvm_dr7_valid(vmcs12->guest_dr7)))
+	    (CC(!kvm_dr7_valid(vmcs12->guest_dr7)) ||
+	     CC(!vmx_is_valid_debugctl(vcpu, vmcs12->guest_ia32_debugctl, false))))
 		return -EINVAL;
 
 	if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT) &&
@@ -3530,7 +3538,7 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
 
 	if (!vmx->nested.nested_run_pending ||
 	    !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS))
-		vmx->nested.pre_vmenter_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL);
+		vmx->nested.pre_vmenter_debugctl = vmx_guest_debugctl_read();
 	if (kvm_mpx_supported() &&
 	    (!vmx->nested.nested_run_pending ||
 	     !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS)))
@@ -4608,6 +4616,12 @@ static void sync_vmcs02_to_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 		(vmcs12->vm_entry_controls & ~VM_ENTRY_IA32E_MODE) |
 		(vm_entry_controls_get(to_vmx(vcpu)) & VM_ENTRY_IA32E_MODE);
 
+	/*
+	 * Note!  Save DR7, but intentionally don't grab DEBUGCTL from vmcs02.
+	 * Writes to DEBUGCTL that aren't intercepted by L1 are immediately
+	 * propagated to vmcs12 (see vmx_set_msr()), as the value loaded into
+	 * vmcs02 doesn't strictly track vmcs12.
+	 */
 	if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_DEBUG_CONTROLS)
 		vmcs12->guest_dr7 = vcpu->arch.dr7;
 
@@ -4798,7 +4812,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 	__vmx_set_segment(vcpu, &seg, VCPU_SREG_LDTR);
 
 	kvm_set_dr(vcpu, 7, 0x400);
-	vmcs_write64(GUEST_IA32_DEBUGCTL, 0);
+	vmx_guest_debugctl_write(vcpu, 0);
 
 	if (nested_vmx_load_msr(vcpu, vmcs12->vm_exit_msr_load_addr,
 				vmcs12->vm_exit_msr_load_count))
@@ -4853,6 +4867,9 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu)
 			WARN_ON(kvm_set_dr(vcpu, 7, vmcs_readl(GUEST_DR7)));
 	}
 
+	/* Reload DEBUGCTL to ensure vmcs01 has a fresh FREEZE_IN_SMM value. */
+	vmx_reload_guest_debugctl(vcpu);
+
 	/*
 	 * Note that calling vmx_set_{efer,cr0,cr4} is important as they
 	 * handle a variety of side effects to KVM's software model.
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index bbf4509f32d0..0b173602821b 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -653,11 +653,11 @@ static void intel_pmu_reset(struct kvm_vcpu *vcpu)
  */
 static void intel_pmu_legacy_freezing_lbrs_on_pmi(struct kvm_vcpu *vcpu)
 {
-	u64 data = vmcs_read64(GUEST_IA32_DEBUGCTL);
+	u64 data = vmx_guest_debugctl_read();
 
 	if (data & DEBUGCTLMSR_FREEZE_LBRS_ON_PMI) {
 		data &= ~DEBUGCTLMSR_LBR;
-		vmcs_write64(GUEST_IA32_DEBUGCTL, data);
+		vmx_guest_debugctl_write(vcpu, data);
 	}
 }
 
@@ -730,7 +730,7 @@ void vmx_passthrough_lbr_msrs(struct kvm_vcpu *vcpu)
 
 	if (!lbr_desc->event) {
 		vmx_disable_lbr_msrs_passthrough(vcpu);
-		if (vmcs_read64(GUEST_IA32_DEBUGCTL) & DEBUGCTLMSR_LBR)
+		if (vmx_guest_debugctl_read() & DEBUGCTLMSR_LBR)
 			goto warn;
 		if (test_bit(INTEL_PMC_IDX_FIXED_VLBR, pmu->pmc_in_use))
 			goto warn;
@@ -752,7 +752,7 @@ warn:
 
 static void intel_pmu_cleanup(struct kvm_vcpu *vcpu)
 {
-	if (!(vmcs_read64(GUEST_IA32_DEBUGCTL) & DEBUGCTLMSR_LBR))
+	if (!(vmx_guest_debugctl_read() & DEBUGCTLMSR_LBR))
 		intel_pmu_release_guest_lbr_event(vcpu);
 }
 
diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index ec79aacc446f..020b472a1e68 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -783,8 +783,6 @@ void tdx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
 	else
 		vt->msr_host_kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE);
 
-	vt->host_debugctlmsr = get_debugctlmsr();
-
 	vt->guest_state_loaded = true;
 }
 
@@ -1025,20 +1023,20 @@ static void tdx_load_host_xsave_state(struct kvm_vcpu *vcpu)
 				DEBUGCTLMSR_FREEZE_PERFMON_ON_PMI | \
 				DEBUGCTLMSR_FREEZE_IN_SMM)
 
-fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
+fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags)
 {
 	struct vcpu_tdx *tdx = to_tdx(vcpu);
 	struct vcpu_vt *vt = to_vt(vcpu);
 
 	/*
-	 * force_immediate_exit requires vCPU entering for events injection with
-	 * an immediately exit followed. But The TDX module doesn't guarantee
-	 * entry, it's already possible for KVM to _think_ it completely entry
-	 * to the guest without actually having done so.
-	 * Since KVM never needs to force an immediate exit for TDX, and can't
-	 * do direct injection, just warn on force_immediate_exit.
+	 * WARN if KVM wants to force an immediate exit, as the TDX module does
+	 * not guarantee entry into the guest, i.e. it's possible for KVM to
+	 * _think_ it completed entry to the guest and forced an immediate exit
+	 * without actually having done so.  Luckily, KVM never needs to force
+	 * an immediate exit for TDX (KVM can't do direct event injection, so
+	 * just WARN and continue on.
 	 */
-	WARN_ON_ONCE(force_immediate_exit);
+	WARN_ON_ONCE(run_flags);
 
 	/*
 	 * Wait until retry of SEPT-zap-related SEAMCALL completes before
@@ -1048,7 +1046,7 @@ fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
 	if (unlikely(READ_ONCE(to_kvm_tdx(vcpu->kvm)->wait_for_sept_zap)))
 		return EXIT_FASTPATH_EXIT_HANDLED;
 
-	trace_kvm_entry(vcpu, force_immediate_exit);
+	trace_kvm_entry(vcpu, run_flags & KVM_RUN_FORCE_IMMEDIATE_EXIT);
 
 	if (pi_test_on(&vt->pi_desc)) {
 		apic->send_IPI_self(POSTED_INTR_VECTOR);
@@ -1060,8 +1058,8 @@ fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
 
 	tdx_vcpu_enter_exit(vcpu);
 
-	if (vt->host_debugctlmsr & ~TDX_DEBUGCTL_PRESERVED)
-		update_debugctlmsr(vt->host_debugctlmsr);
+	if (vcpu->arch.host_debugctl & ~TDX_DEBUGCTL_PRESERVED)
+		update_debugctlmsr(vcpu->arch.host_debugctl);
 
 	tdx_load_host_xsave_state(vcpu);
 	tdx->guest_entered = true;
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 2003e9097b4e..3de2c7ae37b4 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -168,31 +168,6 @@ module_param(allow_smaller_maxphyaddr, bool, S_IRUGO);
 	RTIT_STATUS_BYTECNT))
 
 /*
- * List of MSRs that can be directly passed to the guest.
- * In addition to these x2apic, PT and LBR MSRs are handled specially.
- */
-static u32 vmx_possible_passthrough_msrs[MAX_POSSIBLE_PASSTHROUGH_MSRS] = {
-	MSR_IA32_SPEC_CTRL,
-	MSR_IA32_PRED_CMD,
-	MSR_IA32_FLUSH_CMD,
-	MSR_IA32_TSC,
-#ifdef CONFIG_X86_64
-	MSR_FS_BASE,
-	MSR_GS_BASE,
-	MSR_KERNEL_GS_BASE,
-	MSR_IA32_XFD,
-	MSR_IA32_XFD_ERR,
-#endif
-	MSR_IA32_SYSENTER_CS,
-	MSR_IA32_SYSENTER_ESP,
-	MSR_IA32_SYSENTER_EIP,
-	MSR_CORE_C1_RES,
-	MSR_CORE_C3_RESIDENCY,
-	MSR_CORE_C6_RESIDENCY,
-	MSR_CORE_C7_RESIDENCY,
-};
-
-/*
  * These 2 parameters are used to config the controls for Pause-Loop Exiting:
  * ple_gap:    upper bound on the amount of time between two successive
  *             executions of PAUSE in a loop. Also indicate if ple enabled.
@@ -674,40 +649,6 @@ static inline bool cpu_need_virtualize_apic_accesses(struct kvm_vcpu *vcpu)
 	return flexpriority_enabled && lapic_in_kernel(vcpu);
 }
 
-static int vmx_get_passthrough_msr_slot(u32 msr)
-{
-	int i;
-
-	switch (msr) {
-	case 0x800 ... 0x8ff:
-		/* x2APIC MSRs. These are handled in vmx_update_msr_bitmap_x2apic() */
-		return -ENOENT;
-	case MSR_IA32_RTIT_STATUS:
-	case MSR_IA32_RTIT_OUTPUT_BASE:
-	case MSR_IA32_RTIT_OUTPUT_MASK:
-	case MSR_IA32_RTIT_CR3_MATCH:
-	case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B:
-		/* PT MSRs. These are handled in pt_update_intercept_for_msr() */
-	case MSR_LBR_SELECT:
-	case MSR_LBR_TOS:
-	case MSR_LBR_INFO_0 ... MSR_LBR_INFO_0 + 31:
-	case MSR_LBR_NHM_FROM ... MSR_LBR_NHM_FROM + 31:
-	case MSR_LBR_NHM_TO ... MSR_LBR_NHM_TO + 31:
-	case MSR_LBR_CORE_FROM ... MSR_LBR_CORE_FROM + 8:
-	case MSR_LBR_CORE_TO ... MSR_LBR_CORE_TO + 8:
-		/* LBR MSRs. These are handled in vmx_update_intercept_for_lbr_msrs() */
-		return -ENOENT;
-	}
-
-	for (i = 0; i < ARRAY_SIZE(vmx_possible_passthrough_msrs); i++) {
-		if (vmx_possible_passthrough_msrs[i] == msr)
-			return i;
-	}
-
-	WARN(1, "Invalid MSR %x, please adapt vmx_possible_passthrough_msrs[]", msr);
-	return -ENOENT;
-}
-
 struct vmx_uret_msr *vmx_find_uret_msr(struct vcpu_vmx *vmx, u32 msr)
 {
 	int i;
@@ -2153,7 +2094,7 @@ int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			msr_info->data = vmx->pt_desc.guest.addr_a[index / 2];
 		break;
 	case MSR_IA32_DEBUGCTLMSR:
-		msr_info->data = vmcs_read64(GUEST_IA32_DEBUGCTL);
+		msr_info->data = vmx_guest_debugctl_read();
 		break;
 	default:
 	find_uret_msr:
@@ -2178,7 +2119,7 @@ static u64 nested_vmx_truncate_sysenter_addr(struct kvm_vcpu *vcpu,
 	return (unsigned long)data;
 }
 
-static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated)
+u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated)
 {
 	u64 debugctl = 0;
 
@@ -2190,9 +2131,25 @@ static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated
 	    (host_initiated || intel_pmu_lbr_is_enabled(vcpu)))
 		debugctl |= DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI;
 
+	if (boot_cpu_has(X86_FEATURE_RTM) &&
+	    (host_initiated || guest_cpu_cap_has(vcpu, X86_FEATURE_RTM)))
+		debugctl |= DEBUGCTLMSR_RTM_DEBUG;
+
 	return debugctl;
 }
 
+bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data, bool host_initiated)
+{
+	u64 invalid;
+
+	invalid = data & ~vmx_get_supported_debugctl(vcpu, host_initiated);
+	if (invalid & (DEBUGCTLMSR_BTF | DEBUGCTLMSR_LBR)) {
+		kvm_pr_unimpl_wrmsr(vcpu, MSR_IA32_DEBUGCTLMSR, data);
+		invalid &= ~(DEBUGCTLMSR_BTF | DEBUGCTLMSR_LBR);
+	}
+	return !invalid;
+}
+
 /*
  * Writes msr value into the appropriate "register".
  * Returns 0 on success, non-0 otherwise.
@@ -2261,29 +2218,22 @@ int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		}
 		vmcs_writel(GUEST_SYSENTER_ESP, data);
 		break;
-	case MSR_IA32_DEBUGCTLMSR: {
-		u64 invalid;
-
-		invalid = data & ~vmx_get_supported_debugctl(vcpu, msr_info->host_initiated);
-		if (invalid & (DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR)) {
-			kvm_pr_unimpl_wrmsr(vcpu, msr_index, data);
-			data &= ~(DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR);
-			invalid &= ~(DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR);
-		}
-
-		if (invalid)
+	case MSR_IA32_DEBUGCTLMSR:
+		if (!vmx_is_valid_debugctl(vcpu, data, msr_info->host_initiated))
 			return 1;
 
+		data &= vmx_get_supported_debugctl(vcpu, msr_info->host_initiated);
+
 		if (is_guest_mode(vcpu) && get_vmcs12(vcpu)->vm_exit_controls &
 						VM_EXIT_SAVE_DEBUG_CONTROLS)
 			get_vmcs12(vcpu)->guest_ia32_debugctl = data;
 
-		vmcs_write64(GUEST_IA32_DEBUGCTL, data);
+		vmx_guest_debugctl_write(vcpu, data);
+
 		if (intel_pmu_lbr_is_enabled(vcpu) && !to_vmx(vcpu)->lbr_desc.event &&
 		    (data & DEBUGCTLMSR_LBR))
 			intel_pmu_create_guest_lbr_event(vcpu);
 		return 0;
-	}
 	case MSR_IA32_BNDCFGS:
 		if (!kvm_mpx_supported() ||
 		    (!msr_info->host_initiated &&
@@ -4017,76 +3967,29 @@ static void vmx_msr_bitmap_l01_changed(struct vcpu_vmx *vmx)
 	vmx->nested.force_msr_bitmap_recalc = true;
 }
 
-void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type)
+void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type, bool set)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap;
-	int idx;
 
 	if (!cpu_has_vmx_msr_bitmap())
 		return;
 
 	vmx_msr_bitmap_l01_changed(vmx);
 
-	/*
-	 * Mark the desired intercept state in shadow bitmap, this is needed
-	 * for resync when the MSR filters change.
-	 */
-	idx = vmx_get_passthrough_msr_slot(msr);
-	if (idx >= 0) {
-		if (type & MSR_TYPE_R)
-			clear_bit(idx, vmx->shadow_msr_intercept.read);
-		if (type & MSR_TYPE_W)
-			clear_bit(idx, vmx->shadow_msr_intercept.write);
-	}
-
-	if ((type & MSR_TYPE_R) &&
-	    !kvm_msr_allowed(vcpu, msr, KVM_MSR_FILTER_READ)) {
-		vmx_set_msr_bitmap_read(msr_bitmap, msr);
-		type &= ~MSR_TYPE_R;
-	}
-
-	if ((type & MSR_TYPE_W) &&
-	    !kvm_msr_allowed(vcpu, msr, KVM_MSR_FILTER_WRITE)) {
-		vmx_set_msr_bitmap_write(msr_bitmap, msr);
-		type &= ~MSR_TYPE_W;
+	if (type & MSR_TYPE_R) {
+		if (!set && kvm_msr_allowed(vcpu, msr, KVM_MSR_FILTER_READ))
+			vmx_clear_msr_bitmap_read(msr_bitmap, msr);
+		else
+			vmx_set_msr_bitmap_read(msr_bitmap, msr);
 	}
 
-	if (type & MSR_TYPE_R)
-		vmx_clear_msr_bitmap_read(msr_bitmap, msr);
-
-	if (type & MSR_TYPE_W)
-		vmx_clear_msr_bitmap_write(msr_bitmap, msr);
-}
-
-void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap;
-	int idx;
-
-	if (!cpu_has_vmx_msr_bitmap())
-		return;
-
-	vmx_msr_bitmap_l01_changed(vmx);
-
-	/*
-	 * Mark the desired intercept state in shadow bitmap, this is needed
-	 * for resync when the MSR filter changes.
-	 */
-	idx = vmx_get_passthrough_msr_slot(msr);
-	if (idx >= 0) {
-		if (type & MSR_TYPE_R)
-			set_bit(idx, vmx->shadow_msr_intercept.read);
-		if (type & MSR_TYPE_W)
-			set_bit(idx, vmx->shadow_msr_intercept.write);
+	if (type & MSR_TYPE_W) {
+		if (!set && kvm_msr_allowed(vcpu, msr, KVM_MSR_FILTER_WRITE))
+			vmx_clear_msr_bitmap_write(msr_bitmap, msr);
+		else
+			vmx_set_msr_bitmap_write(msr_bitmap, msr);
 	}
-
-	if (type & MSR_TYPE_R)
-		vmx_set_msr_bitmap_read(msr_bitmap, msr);
-
-	if (type & MSR_TYPE_W)
-		vmx_set_msr_bitmap_write(msr_bitmap, msr);
 }
 
 static void vmx_update_msr_bitmap_x2apic(struct kvm_vcpu *vcpu)
@@ -4165,35 +4068,57 @@ void pt_update_intercept_for_msr(struct kvm_vcpu *vcpu)
 	}
 }
 
-void vmx_msr_filter_changed(struct kvm_vcpu *vcpu)
+void vmx_recalc_msr_intercepts(struct kvm_vcpu *vcpu)
 {
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	u32 i;
-
 	if (!cpu_has_vmx_msr_bitmap())
 		return;
 
-	/*
-	 * Redo intercept permissions for MSRs that KVM is passing through to
-	 * the guest.  Disabling interception will check the new MSR filter and
-	 * ensure that KVM enables interception if usersepace wants to filter
-	 * the MSR.  MSRs that KVM is already intercepting don't need to be
-	 * refreshed since KVM is going to intercept them regardless of what
-	 * userspace wants.
-	 */
-	for (i = 0; i < ARRAY_SIZE(vmx_possible_passthrough_msrs); i++) {
-		u32 msr = vmx_possible_passthrough_msrs[i];
-
-		if (!test_bit(i, vmx->shadow_msr_intercept.read))
-			vmx_disable_intercept_for_msr(vcpu, msr, MSR_TYPE_R);
-
-		if (!test_bit(i, vmx->shadow_msr_intercept.write))
-			vmx_disable_intercept_for_msr(vcpu, msr, MSR_TYPE_W);
+	vmx_disable_intercept_for_msr(vcpu, MSR_IA32_TSC, MSR_TYPE_R);
+#ifdef CONFIG_X86_64
+	vmx_disable_intercept_for_msr(vcpu, MSR_FS_BASE, MSR_TYPE_RW);
+	vmx_disable_intercept_for_msr(vcpu, MSR_GS_BASE, MSR_TYPE_RW);
+	vmx_disable_intercept_for_msr(vcpu, MSR_KERNEL_GS_BASE, MSR_TYPE_RW);
+#endif
+	vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW);
+	vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW);
+	vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW);
+	if (kvm_cstate_in_guest(vcpu->kvm)) {
+		vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C1_RES, MSR_TYPE_R);
+		vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C3_RESIDENCY, MSR_TYPE_R);
+		vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C6_RESIDENCY, MSR_TYPE_R);
+		vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C7_RESIDENCY, MSR_TYPE_R);
+	}
+	if (kvm_aperfmperf_in_guest(vcpu->kvm)) {
+		vmx_disable_intercept_for_msr(vcpu, MSR_IA32_APERF, MSR_TYPE_R);
+		vmx_disable_intercept_for_msr(vcpu, MSR_IA32_MPERF, MSR_TYPE_R);
 	}
 
 	/* PT MSRs can be passed through iff PT is exposed to the guest. */
 	if (vmx_pt_mode_is_host_guest())
 		pt_update_intercept_for_msr(vcpu);
+
+	if (vcpu->arch.xfd_no_write_intercept)
+		vmx_disable_intercept_for_msr(vcpu, MSR_IA32_XFD, MSR_TYPE_RW);
+
+	vmx_set_intercept_for_msr(vcpu, MSR_IA32_SPEC_CTRL, MSR_TYPE_RW,
+				  !to_vmx(vcpu)->spec_ctrl);
+
+	if (kvm_cpu_cap_has(X86_FEATURE_XFD))
+		vmx_set_intercept_for_msr(vcpu, MSR_IA32_XFD_ERR, MSR_TYPE_R,
+					  !guest_cpu_cap_has(vcpu, X86_FEATURE_XFD));
+
+	if (cpu_feature_enabled(X86_FEATURE_IBPB))
+		vmx_set_intercept_for_msr(vcpu, MSR_IA32_PRED_CMD, MSR_TYPE_W,
+					  !guest_has_pred_cmd_msr(vcpu));
+
+	if (cpu_feature_enabled(X86_FEATURE_FLUSH_L1D))
+		vmx_set_intercept_for_msr(vcpu, MSR_IA32_FLUSH_CMD, MSR_TYPE_W,
+					  !guest_cpu_cap_has(vcpu, X86_FEATURE_FLUSH_L1D));
+
+	/*
+	 * x2APIC and LBR MSR intercepts are modified on-demand and cannot be
+	 * filtered by userspace.
+	 */
 }
 
 static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu,
@@ -4794,7 +4719,8 @@ static void init_vmcs(struct vcpu_vmx *vmx)
 	vmcs_write32(GUEST_SYSENTER_CS, 0);
 	vmcs_writel(GUEST_SYSENTER_ESP, 0);
 	vmcs_writel(GUEST_SYSENTER_EIP, 0);
-	vmcs_write64(GUEST_IA32_DEBUGCTL, 0);
+
+	vmx_guest_debugctl_write(&vmx->vcpu, 0);
 
 	if (cpu_has_vmx_tpr_shadow()) {
 		vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, 0);
@@ -5610,12 +5536,6 @@ void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu)
 	set_debugreg(DR6_RESERVED, 6);
 }
 
-void vmx_set_dr6(struct kvm_vcpu *vcpu, unsigned long val)
-{
-	lockdep_assert_irqs_disabled();
-	set_debugreg(vcpu->arch.dr6, 6);
-}
-
 void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val)
 {
 	vmcs_writel(GUEST_DR7, val);
@@ -7327,8 +7247,9 @@ out:
 	guest_state_exit_irqoff();
 }
 
-fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
+fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags)
 {
+	bool force_immediate_exit = run_flags & KVM_RUN_FORCE_IMMEDIATE_EXIT;
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	unsigned long cr3, cr4;
 
@@ -7373,6 +7294,12 @@ fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
 		vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]);
 	vcpu->arch.regs_dirty = 0;
 
+	if (run_flags & KVM_RUN_LOAD_GUEST_DR6)
+		set_debugreg(vcpu->arch.dr6, 6);
+
+	if (run_flags & KVM_RUN_LOAD_DEBUGCTL)
+		vmx_reload_guest_debugctl(vcpu);
+
 	/*
 	 * Refresh vmcs.HOST_CR3 if necessary.  This must be done immediately
 	 * prior to VM-Enter, as the kernel may load a new ASID (PCID) any time
@@ -7547,26 +7474,6 @@ int vmx_vcpu_create(struct kvm_vcpu *vcpu)
 		evmcs->hv_enlightenments_control.msr_bitmap = 1;
 	}
 
-	/* The MSR bitmap starts with all ones */
-	bitmap_fill(vmx->shadow_msr_intercept.read, MAX_POSSIBLE_PASSTHROUGH_MSRS);
-	bitmap_fill(vmx->shadow_msr_intercept.write, MAX_POSSIBLE_PASSTHROUGH_MSRS);
-
-	vmx_disable_intercept_for_msr(vcpu, MSR_IA32_TSC, MSR_TYPE_R);
-#ifdef CONFIG_X86_64
-	vmx_disable_intercept_for_msr(vcpu, MSR_FS_BASE, MSR_TYPE_RW);
-	vmx_disable_intercept_for_msr(vcpu, MSR_GS_BASE, MSR_TYPE_RW);
-	vmx_disable_intercept_for_msr(vcpu, MSR_KERNEL_GS_BASE, MSR_TYPE_RW);
-#endif
-	vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW);
-	vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW);
-	vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW);
-	if (kvm_cstate_in_guest(vcpu->kvm)) {
-		vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C1_RES, MSR_TYPE_R);
-		vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C3_RESIDENCY, MSR_TYPE_R);
-		vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C6_RESIDENCY, MSR_TYPE_R);
-		vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C7_RESIDENCY, MSR_TYPE_R);
-	}
-
 	vmx->loaded_vmcs = &vmx->vmcs01;
 
 	if (cpu_need_virtualize_apic_accesses(vcpu)) {
@@ -7616,7 +7523,7 @@ free_vpid:
 int vmx_vm_init(struct kvm *kvm)
 {
 	if (!ple_gap)
-		kvm->arch.pause_in_guest = true;
+		kvm_disable_exits(kvm, KVM_X86_DISABLE_EXITS_PAUSE);
 
 	if (boot_cpu_has(X86_BUG_L1TF) && enable_ept) {
 		switch (l1tf_mitigation) {
@@ -7853,18 +7760,6 @@ void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 		}
 	}
 
-	if (kvm_cpu_cap_has(X86_FEATURE_XFD))
-		vmx_set_intercept_for_msr(vcpu, MSR_IA32_XFD_ERR, MSR_TYPE_R,
-					  !guest_cpu_cap_has(vcpu, X86_FEATURE_XFD));
-
-	if (boot_cpu_has(X86_FEATURE_IBPB))
-		vmx_set_intercept_for_msr(vcpu, MSR_IA32_PRED_CMD, MSR_TYPE_W,
-					  !guest_has_pred_cmd_msr(vcpu));
-
-	if (boot_cpu_has(X86_FEATURE_FLUSH_L1D))
-		vmx_set_intercept_for_msr(vcpu, MSR_IA32_FLUSH_CMD, MSR_TYPE_W,
-					  !guest_cpu_cap_has(vcpu, X86_FEATURE_FLUSH_L1D));
-
 	set_cr4_guest_host_mask(vmx);
 
 	vmx_write_encls_bitmap(vcpu, NULL);
@@ -7880,6 +7775,9 @@ void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 		vmx->msr_ia32_feature_control_valid_bits &=
 			~FEAT_CTL_SGX_LC_ENABLED;
 
+	/* Recalc MSR interception to account for feature changes. */
+	vmx_recalc_msr_intercepts(vcpu);
+
 	/* Refresh #PF interception to account for MAXPHYADDR changes. */
 	vmx_update_exception_bitmap(vcpu);
 }
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index b5758c33c60f..d3389baf3ab3 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -19,8 +19,6 @@
 #include "../mmu.h"
 #include "common.h"
 
-#define X2APIC_MSR(r) (APIC_BASE_MSR + ((r) >> 4))
-
 #ifdef CONFIG_X86_64
 #define MAX_NR_USER_RETURN_MSRS	7
 #else
@@ -296,13 +294,6 @@ struct vcpu_vmx {
 	struct pt_desc pt_desc;
 	struct lbr_desc lbr_desc;
 
-	/* Save desired MSR intercept (read: pass-through) state */
-#define MAX_POSSIBLE_PASSTHROUGH_MSRS	16
-	struct {
-		DECLARE_BITMAP(read, MAX_POSSIBLE_PASSTHROUGH_MSRS);
-		DECLARE_BITMAP(write, MAX_POSSIBLE_PASSTHROUGH_MSRS);
-	} shadow_msr_intercept;
-
 	/* ve_info must be page aligned. */
 	struct vmx_ve_information *ve_info;
 };
@@ -395,24 +386,54 @@ bool __vmx_vcpu_run(struct vcpu_vmx *vmx, unsigned long *regs,
 int vmx_find_loadstore_msr_slot(struct vmx_msrs *m, u32 msr);
 void vmx_ept_load_pdptrs(struct kvm_vcpu *vcpu);
 
-void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type);
-void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type);
+void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type, bool set);
+
+static inline void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu,
+						 u32 msr, int type)
+{
+	vmx_set_intercept_for_msr(vcpu, msr, type, false);
+}
+
+static inline void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu,
+						u32 msr, int type)
+{
+	vmx_set_intercept_for_msr(vcpu, msr, type, true);
+}
 
 u64 vmx_get_l2_tsc_offset(struct kvm_vcpu *vcpu);
 u64 vmx_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu);
 
 gva_t vmx_get_untagged_addr(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags);
 
-static inline void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr,
-					     int type, bool value)
+void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu);
+
+u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated);
+bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data, bool host_initiated);
+
+#define VMX_HOST_OWNED_DEBUGCTL_BITS	(DEBUGCTLMSR_FREEZE_IN_SMM)
+
+static inline void vmx_guest_debugctl_write(struct kvm_vcpu *vcpu, u64 val)
 {
-	if (value)
-		vmx_enable_intercept_for_msr(vcpu, msr, type);
-	else
-		vmx_disable_intercept_for_msr(vcpu, msr, type);
+	WARN_ON_ONCE(val & VMX_HOST_OWNED_DEBUGCTL_BITS);
+
+	val |= vcpu->arch.host_debugctl & VMX_HOST_OWNED_DEBUGCTL_BITS;
+	vmcs_write64(GUEST_IA32_DEBUGCTL, val);
 }
 
-void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu);
+static inline u64 vmx_guest_debugctl_read(void)
+{
+	return vmcs_read64(GUEST_IA32_DEBUGCTL) & ~VMX_HOST_OWNED_DEBUGCTL_BITS;
+}
+
+static inline void vmx_reload_guest_debugctl(struct kvm_vcpu *vcpu)
+{
+	u64 val = vmcs_read64(GUEST_IA32_DEBUGCTL);
+
+	if (!((val ^ vcpu->arch.host_debugctl) & VMX_HOST_OWNED_DEBUGCTL_BITS))
+		return;
+
+	vmx_guest_debugctl_write(vcpu, val & ~VMX_HOST_OWNED_DEBUGCTL_BITS);
+}
 
 /*
  * Note, early Intel manuals have the write-low and read-high bitmap offsets
diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h
index b4596f651232..ffd72f036213 100644
--- a/arch/x86/kvm/vmx/x86_ops.h
+++ b/arch/x86/kvm/vmx/x86_ops.h
@@ -21,7 +21,7 @@ void vmx_vm_destroy(struct kvm *kvm);
 int vmx_vcpu_precreate(struct kvm *kvm);
 int vmx_vcpu_create(struct kvm_vcpu *vcpu);
 int vmx_vcpu_pre_run(struct kvm_vcpu *vcpu);
-fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit);
+fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags);
 void vmx_vcpu_free(struct kvm_vcpu *vcpu);
 void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event);
 void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
@@ -52,7 +52,7 @@ void vmx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode,
 			   int trig_mode, int vector);
 void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu);
 bool vmx_has_emulated_msr(struct kvm *kvm, u32 index);
-void vmx_msr_filter_changed(struct kvm_vcpu *vcpu);
+void vmx_recalc_msr_intercepts(struct kvm_vcpu *vcpu);
 void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu);
 void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu);
 int vmx_get_feature_msr(u32 msr, u64 *data);
@@ -133,7 +133,7 @@ void tdx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event);
 void tdx_vcpu_free(struct kvm_vcpu *vcpu);
 void tdx_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
 int tdx_vcpu_pre_run(struct kvm_vcpu *vcpu);
-fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit);
+fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags);
 void tdx_prepare_switch_to_guest(struct kvm_vcpu *vcpu);
 void tdx_vcpu_put(struct kvm_vcpu *vcpu);
 bool tdx_protected_apic_has_interrupt(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index f641903659e9..9ea2e54e7565 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4582,6 +4582,9 @@ static u64 kvm_get_allowed_disable_exits(void)
 {
 	u64 r = KVM_X86_DISABLE_EXITS_PAUSE;
 
+	if (boot_cpu_has(X86_FEATURE_APERFMPERF))
+		r |= KVM_X86_DISABLE_EXITS_APERFMPERF;
+
 	if (!mitigate_smt_rsb) {
 		r |= KVM_X86_DISABLE_EXITS_HLT |
 			KVM_X86_DISABLE_EXITS_CSTATE;
@@ -5495,12 +5498,6 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 	    (events->exception.nr > 31 || events->exception.nr == NMI_VECTOR))
 		return -EINVAL;
 
-	/* INITs are latched while in SMM */
-	if (events->flags & KVM_VCPUEVENT_VALID_SMM &&
-	    (events->smi.smm || events->smi.pending) &&
-	    vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED)
-		return -EINVAL;
-
 	process_nmi(vcpu);
 
 	/*
@@ -6490,17 +6487,11 @@ split_irqchip_unlock:
 
 		if (!mitigate_smt_rsb && boot_cpu_has_bug(X86_BUG_SMT_RSB) &&
 		    cpu_smt_possible() &&
-		    (cap->args[0] & ~KVM_X86_DISABLE_EXITS_PAUSE))
+		    (cap->args[0] & ~(KVM_X86_DISABLE_EXITS_PAUSE |
+				      KVM_X86_DISABLE_EXITS_APERFMPERF)))
 			pr_warn_once(SMT_RSB_MSG);
 
-		if (cap->args[0] & KVM_X86_DISABLE_EXITS_PAUSE)
-			kvm->arch.pause_in_guest = true;
-		if (cap->args[0] & KVM_X86_DISABLE_EXITS_MWAIT)
-			kvm->arch.mwait_in_guest = true;
-		if (cap->args[0] & KVM_X86_DISABLE_EXITS_HLT)
-			kvm->arch.hlt_in_guest = true;
-		if (cap->args[0] & KVM_X86_DISABLE_EXITS_CSTATE)
-			kvm->arch.cstate_in_guest = true;
+		kvm_disable_exits(kvm, cap->args[0]);
 		r = 0;
 disable_exits_unlock:
 		mutex_unlock(&kvm->lock);
@@ -7211,9 +7202,12 @@ set_pit2_out:
 		if (user_tsc_khz == 0)
 			user_tsc_khz = tsc_khz;
 
-		WRITE_ONCE(kvm->arch.default_tsc_khz, user_tsc_khz);
-		r = 0;
-
+		mutex_lock(&kvm->lock);
+		if (!kvm->created_vcpus) {
+			WRITE_ONCE(kvm->arch.default_tsc_khz, user_tsc_khz);
+			r = 0;
+		}
+		mutex_unlock(&kvm->lock);
 		goto out;
 	}
 	case KVM_GET_TSC_KHZ: {
@@ -10657,6 +10651,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		dm_request_for_irq_injection(vcpu) &&
 		kvm_cpu_accept_dm_intr(vcpu);
 	fastpath_t exit_fastpath;
+	u64 run_flags, debug_ctl;
 
 	bool req_immediate_exit = false;
 
@@ -10804,8 +10799,14 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			kvm_vcpu_update_apicv(vcpu);
 		if (kvm_check_request(KVM_REQ_APF_READY, vcpu))
 			kvm_check_async_pf_completion(vcpu);
+
+		/*
+		 * Recalc MSR intercepts as userspace may want to intercept
+		 * accesses to MSRs that KVM would otherwise pass through to
+		 * the guest.
+		 */
 		if (kvm_check_request(KVM_REQ_MSR_FILTER_CHANGED, vcpu))
-			kvm_x86_call(msr_filter_changed)(vcpu);
+			kvm_x86_call(recalc_msr_intercepts)(vcpu);
 
 		if (kvm_check_request(KVM_REQ_UPDATE_CPU_DIRTY_LOGGING, vcpu))
 			kvm_x86_call(update_cpu_dirty_logging)(vcpu);
@@ -10901,8 +10902,11 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		goto cancel_injection;
 	}
 
-	if (req_immediate_exit)
+	run_flags = 0;
+	if (req_immediate_exit) {
+		run_flags |= KVM_RUN_FORCE_IMMEDIATE_EXIT;
 		kvm_make_request(KVM_REQ_EVENT, vcpu);
+	}
 
 	fpregs_assert_state_consistent();
 	if (test_thread_flag(TIF_NEED_FPU_LOAD))
@@ -10920,12 +10924,22 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		set_debugreg(vcpu->arch.eff_db[3], 3);
 		/* When KVM_DEBUGREG_WONT_EXIT, dr6 is accessible in guest. */
 		if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT))
-			kvm_x86_call(set_dr6)(vcpu, vcpu->arch.dr6);
+			run_flags |= KVM_RUN_LOAD_GUEST_DR6;
 	} else if (unlikely(hw_breakpoint_active())) {
 		set_debugreg(DR7_FIXED_1, 7);
 	}
 
-	vcpu->arch.host_debugctl = get_debugctlmsr();
+	/*
+	 * Refresh the host DEBUGCTL snapshot after disabling IRQs, as DEBUGCTL
+	 * can be modified in IRQ context, e.g. via SMP function calls.  Inform
+	 * vendor code if any host-owned bits were changed, e.g. so that the
+	 * value loaded into hardware while running the guest can be updated.
+	 */
+	debug_ctl = get_debugctlmsr();
+	if ((debug_ctl ^ vcpu->arch.host_debugctl) & kvm_x86_ops.HOST_OWNED_DEBUGCTL &&
+	    !vcpu->arch.guest_state_protected)
+		run_flags |= KVM_RUN_LOAD_DEBUGCTL;
+	vcpu->arch.host_debugctl = debug_ctl;
 
 	guest_timing_enter_irqoff();
 
@@ -10939,8 +10953,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		WARN_ON_ONCE((kvm_vcpu_apicv_activated(vcpu) != kvm_vcpu_apicv_active(vcpu)) &&
 			     (kvm_get_apic_mode(vcpu) != LAPIC_MODE_DISABLED));
 
-		exit_fastpath = kvm_x86_call(vcpu_run)(vcpu,
-						       req_immediate_exit);
+		exit_fastpath = kvm_x86_call(vcpu_run)(vcpu, run_flags);
 		if (likely(exit_fastpath != EXIT_FASTPATH_REENTER_GUEST))
 			break;
 
@@ -10952,6 +10965,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			break;
 		}
 
+		run_flags = 0;
+
 		/* Note, VM-Exits that go down the "slow" path are accounted below. */
 		++vcpu->stat.exits;
 	}
@@ -11425,6 +11440,28 @@ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 	trace_kvm_fpu(0);
 }
 
+static int kvm_x86_vcpu_pre_run(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * SIPI_RECEIVED is obsolete; KVM leaves the vCPU in Wait-For-SIPI and
+	 * tracks the pending SIPI separately.  SIPI_RECEIVED is still accepted
+	 * by KVM_SET_VCPU_EVENTS for backwards compatibility, but should be
+	 * converted to INIT_RECEIVED.
+	 */
+	if (WARN_ON_ONCE(vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED))
+		return -EINVAL;
+
+	/*
+	 * Disallow running the vCPU if userspace forced it into an impossible
+	 * MP_STATE, e.g. if the vCPU is in WFS but SIPI is blocked.
+	 */
+	if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED &&
+	    !kvm_apic_init_sipi_allowed(vcpu))
+		return -EINVAL;
+
+	return kvm_x86_call(vcpu_pre_run)(vcpu);
+}
+
 int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 {
 	struct kvm_queued_exception *ex = &vcpu->arch.exception;
@@ -11527,7 +11564,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		goto out;
 	}
 
-	r = kvm_x86_call(vcpu_pre_run)(vcpu);
+	r = kvm_x86_vcpu_pre_run(vcpu);
 	if (r <= 0)
 		goto out;
 
@@ -11771,21 +11808,16 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 	}
 
 	/*
-	 * Pending INITs are reported using KVM_SET_VCPU_EVENTS, disallow
-	 * forcing the guest into INIT/SIPI if those events are supposed to be
-	 * blocked.  KVM prioritizes SMI over INIT, so reject INIT/SIPI state
-	 * if an SMI is pending as well.
+	 * SIPI_RECEIVED is obsolete and no longer used internally; KVM instead
+	 * leaves the vCPU in INIT_RECIEVED (Wait-For-SIPI) and pends the SIPI.
+	 * Translate SIPI_RECEIVED as appropriate for backwards compatibility.
 	 */
-	if ((!kvm_apic_init_sipi_allowed(vcpu) || vcpu->arch.smi_pending) &&
-	    (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED ||
-	     mp_state->mp_state == KVM_MP_STATE_INIT_RECEIVED))
-		goto out;
-
 	if (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED) {
-		kvm_set_mp_state(vcpu, KVM_MP_STATE_INIT_RECEIVED);
+		mp_state->mp_state = KVM_MP_STATE_INIT_RECEIVED;
 		set_bit(KVM_APIC_SIPI, &vcpu->arch.apic->pending_events);
-	} else
-		kvm_set_mp_state(vcpu, mp_state->mp_state);
+	}
+
+	kvm_set_mp_state(vcpu, mp_state->mp_state);
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
 
 	ret = 0;
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 832f0faf4779..e77281b6e2b2 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -499,24 +499,34 @@ static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec)
 	    __rem;						\
 	 })
 
+static inline void kvm_disable_exits(struct kvm *kvm, u64 mask)
+{
+	kvm->arch.disabled_exits |= mask;
+}
+
 static inline bool kvm_mwait_in_guest(struct kvm *kvm)
 {
-	return kvm->arch.mwait_in_guest;
+	return kvm->arch.disabled_exits & KVM_X86_DISABLE_EXITS_MWAIT;
 }
 
 static inline bool kvm_hlt_in_guest(struct kvm *kvm)
 {
-	return kvm->arch.hlt_in_guest;
+	return kvm->arch.disabled_exits & KVM_X86_DISABLE_EXITS_HLT;
 }
 
 static inline bool kvm_pause_in_guest(struct kvm *kvm)
 {
-	return kvm->arch.pause_in_guest;
+	return kvm->arch.disabled_exits & KVM_X86_DISABLE_EXITS_PAUSE;
 }
 
 static inline bool kvm_cstate_in_guest(struct kvm *kvm)
 {
-	return kvm->arch.cstate_in_guest;
+	return kvm->arch.disabled_exits & KVM_X86_DISABLE_EXITS_CSTATE;
+}
+
+static inline bool kvm_aperfmperf_in_guest(struct kvm *kvm)
+{
+	return kvm->arch.disabled_exits & KVM_X86_DISABLE_EXITS_APERFMPERF;
 }
 
 static inline bool kvm_notify_vmexit_enabled(struct kvm *kvm)