Merge tag 'kvm-x86-misc-6.18' of https://github.com/kvm-x86/linux into HEAD

KVM x86 changes for 6.18

 - Don't (re)check L1 intercepts when completing userspace I/O to fix a flaw
   where a misbehaving usersepace (a.k.a. syzkaller) could swizzle L1's
   intercepts and trigger a variety of WARNs in KVM.

 - Emulate PERF_CNTR_GLOBAL_STATUS_SET for PerfMonV2 guests, as the MSR is
   supposed to exist for v2 PMUs.

 - Allow Centaur CPU leaves (base 0xC000_0000) for Zhaoxin CPUs.

 - Clean up KVM's vector hashing code for delivering lowest priority IRQs.

 - Clean up the fastpath handler code to only handle IPIs and WRMSRs that are
   actually "fast", as opposed to handling those that KVM _hopes_ are fast, and
   in the process of doing so add fastpath support for TSC_DEADLINE writes on
   AMD CPUs.

 - Clean up a pile of PMU code in anticipation of adding support for mediated
   vPMUs.

 - Add support for the immediate forms of RDMSR and WRMSRNS, sans full
   emulator support (KVM should never need to emulate the MSRs outside of
   forced emulation and other contrived testing scenarios).

 - Clean up the MSR APIs in preparation for CET and FRED virtualization, as
   well as mediated vPMU support.

 - Rejecting a fully in-kernel IRQCHIP if EOIs are protected, i.e. for TDX VMs,
   as KVM can't faithfully emulate an I/O APIC for such guests.

 - KVM_REQ_MSR_FILTER_CHANGED into a generic RECALC_INTERCEPTS in preparation
   for mediated vPMU support, as KVM will need to recalculate MSR intercepts in
   response to PMU refreshes for guests with mediated vPMUs.

 - Misc cleanups and minor fixes.

1 files changed, 186 insertions, 144 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 77bfee41e273..c34981d28e9c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -164,9 +164,6 @@ module_param(kvmclock_periodic_sync, bool, 0444);
 static u32 __read_mostly tsc_tolerance_ppm = 250;
 module_param(tsc_tolerance_ppm, uint, 0644);
 
-static bool __read_mostly vector_hashing = true;
-module_param(vector_hashing, bool, 0444);
-
 bool __read_mostly enable_vmware_backdoor = false;
 module_param(enable_vmware_backdoor, bool, 0444);
 EXPORT_SYMBOL_GPL(enable_vmware_backdoor);
@@ -367,6 +364,7 @@ static const u32 msrs_to_save_pmu[] = {
 	MSR_AMD64_PERF_CNTR_GLOBAL_CTL,
 	MSR_AMD64_PERF_CNTR_GLOBAL_STATUS,
 	MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR,
+	MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_SET,
 };
 
 static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_base) +
@@ -1579,10 +1577,10 @@ EXPORT_SYMBOL_GPL(kvm_get_dr);
 
 int kvm_emulate_rdpmc(struct kvm_vcpu *vcpu)
 {
-	u32 ecx = kvm_rcx_read(vcpu);
+	u32 pmc = kvm_rcx_read(vcpu);
 	u64 data;
 
-	if (kvm_pmu_rdpmc(vcpu, ecx, &data)) {
+	if (kvm_pmu_rdpmc(vcpu, pmc, &data)) {
 		kvm_inject_gp(vcpu, 0);
 		return 1;
 	}
@@ -1905,8 +1903,8 @@ static int kvm_set_msr_ignored_check(struct kvm_vcpu *vcpu,
  * Returns 0 on success, non-0 otherwise.
  * Assumes vcpu_load() was already called.
  */
-int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data,
-		  bool host_initiated)
+static int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data,
+			 bool host_initiated)
 {
 	struct msr_data msr;
 	int ret;
@@ -1932,6 +1930,16 @@ int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data,
 	return ret;
 }
 
+int kvm_msr_write(struct kvm_vcpu *vcpu, u32 index, u64 data)
+{
+	return __kvm_set_msr(vcpu, index, data, true);
+}
+
+int kvm_msr_read(struct kvm_vcpu *vcpu, u32 index, u64 *data)
+{
+	return __kvm_get_msr(vcpu, index, data, true);
+}
+
 static int kvm_get_msr_ignored_check(struct kvm_vcpu *vcpu,
 				     u32 index, u64 *data, bool host_initiated)
 {
@@ -1939,33 +1947,36 @@ static int kvm_get_msr_ignored_check(struct kvm_vcpu *vcpu,
 				 __kvm_get_msr);
 }
 
-int kvm_get_msr_with_filter(struct kvm_vcpu *vcpu, u32 index, u64 *data)
+int __kvm_emulate_msr_read(struct kvm_vcpu *vcpu, u32 index, u64 *data)
 {
-	if (!kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_READ))
-		return KVM_MSR_RET_FILTERED;
 	return kvm_get_msr_ignored_check(vcpu, index, data, false);
 }
-EXPORT_SYMBOL_GPL(kvm_get_msr_with_filter);
+EXPORT_SYMBOL_GPL(__kvm_emulate_msr_read);
 
-int kvm_set_msr_with_filter(struct kvm_vcpu *vcpu, u32 index, u64 data)
+int __kvm_emulate_msr_write(struct kvm_vcpu *vcpu, u32 index, u64 data)
 {
-	if (!kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_WRITE))
-		return KVM_MSR_RET_FILTERED;
 	return kvm_set_msr_ignored_check(vcpu, index, data, false);
 }
-EXPORT_SYMBOL_GPL(kvm_set_msr_with_filter);
+EXPORT_SYMBOL_GPL(__kvm_emulate_msr_write);
 
-int kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data)
+int kvm_emulate_msr_read(struct kvm_vcpu *vcpu, u32 index, u64 *data)
 {
-	return kvm_get_msr_ignored_check(vcpu, index, data, false);
+	if (!kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_READ))
+		return KVM_MSR_RET_FILTERED;
+
+	return __kvm_emulate_msr_read(vcpu, index, data);
 }
-EXPORT_SYMBOL_GPL(kvm_get_msr);
+EXPORT_SYMBOL_GPL(kvm_emulate_msr_read);
 
-int kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data)
+int kvm_emulate_msr_write(struct kvm_vcpu *vcpu, u32 index, u64 data)
 {
-	return kvm_set_msr_ignored_check(vcpu, index, data, false);
+	if (!kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_WRITE))
+		return KVM_MSR_RET_FILTERED;
+
+	return __kvm_emulate_msr_write(vcpu, index, data);
 }
-EXPORT_SYMBOL_GPL(kvm_set_msr);
+EXPORT_SYMBOL_GPL(kvm_emulate_msr_write);
+
 
 static void complete_userspace_rdmsr(struct kvm_vcpu *vcpu)
 {
@@ -1997,6 +2008,15 @@ static int complete_fast_rdmsr(struct kvm_vcpu *vcpu)
 	return complete_fast_msr_access(vcpu);
 }
 
+static int complete_fast_rdmsr_imm(struct kvm_vcpu *vcpu)
+{
+	if (!vcpu->run->msr.error)
+		kvm_register_write(vcpu, vcpu->arch.cui_rdmsr_imm_reg,
+				   vcpu->run->msr.data);
+
+	return complete_fast_msr_access(vcpu);
+}
+
 static u64 kvm_msr_reason(int r)
 {
 	switch (r) {
@@ -2031,56 +2051,83 @@ static int kvm_msr_user_space(struct kvm_vcpu *vcpu, u32 index,
 	return 1;
 }
 
-int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu)
+static int __kvm_emulate_rdmsr(struct kvm_vcpu *vcpu, u32 msr, int reg,
+			       int (*complete_rdmsr)(struct kvm_vcpu *))
 {
-	u32 ecx = kvm_rcx_read(vcpu);
 	u64 data;
 	int r;
 
-	r = kvm_get_msr_with_filter(vcpu, ecx, &data);
+	r = kvm_emulate_msr_read(vcpu, msr, &data);
 
 	if (!r) {
-		trace_kvm_msr_read(ecx, data);
+		trace_kvm_msr_read(msr, data);
 
-		kvm_rax_write(vcpu, data & -1u);
-		kvm_rdx_write(vcpu, (data >> 32) & -1u);
+		if (reg < 0) {
+			kvm_rax_write(vcpu, data & -1u);
+			kvm_rdx_write(vcpu, (data >> 32) & -1u);
+		} else {
+			kvm_register_write(vcpu, reg, data);
+		}
 	} else {
 		/* MSR read failed? See if we should ask user space */
-		if (kvm_msr_user_space(vcpu, ecx, KVM_EXIT_X86_RDMSR, 0,
-				       complete_fast_rdmsr, r))
+		if (kvm_msr_user_space(vcpu, msr, KVM_EXIT_X86_RDMSR, 0,
+				       complete_rdmsr, r))
 			return 0;
-		trace_kvm_msr_read_ex(ecx);
+		trace_kvm_msr_read_ex(msr);
 	}
 
 	return kvm_x86_call(complete_emulated_msr)(vcpu, r);
 }
+
+int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu)
+{
+	return __kvm_emulate_rdmsr(vcpu, kvm_rcx_read(vcpu), -1,
+				   complete_fast_rdmsr);
+}
 EXPORT_SYMBOL_GPL(kvm_emulate_rdmsr);
 
-int kvm_emulate_wrmsr(struct kvm_vcpu *vcpu)
+int kvm_emulate_rdmsr_imm(struct kvm_vcpu *vcpu, u32 msr, int reg)
 {
-	u32 ecx = kvm_rcx_read(vcpu);
-	u64 data = kvm_read_edx_eax(vcpu);
-	int r;
+	vcpu->arch.cui_rdmsr_imm_reg = reg;
+
+	return __kvm_emulate_rdmsr(vcpu, msr, reg, complete_fast_rdmsr_imm);
+}
+EXPORT_SYMBOL_GPL(kvm_emulate_rdmsr_imm);
 
-	r = kvm_set_msr_with_filter(vcpu, ecx, data);
+static int __kvm_emulate_wrmsr(struct kvm_vcpu *vcpu, u32 msr, u64 data)
+{
+	int r;
 
+	r = kvm_emulate_msr_write(vcpu, msr, data);
 	if (!r) {
-		trace_kvm_msr_write(ecx, data);
+		trace_kvm_msr_write(msr, data);
 	} else {
 		/* MSR write failed? See if we should ask user space */
-		if (kvm_msr_user_space(vcpu, ecx, KVM_EXIT_X86_WRMSR, data,
+		if (kvm_msr_user_space(vcpu, msr, KVM_EXIT_X86_WRMSR, data,
 				       complete_fast_msr_access, r))
 			return 0;
 		/* Signal all other negative errors to userspace */
 		if (r < 0)
 			return r;
-		trace_kvm_msr_write_ex(ecx, data);
+		trace_kvm_msr_write_ex(msr, data);
 	}
 
 	return kvm_x86_call(complete_emulated_msr)(vcpu, r);
 }
+
+int kvm_emulate_wrmsr(struct kvm_vcpu *vcpu)
+{
+	return __kvm_emulate_wrmsr(vcpu, kvm_rcx_read(vcpu),
+				   kvm_read_edx_eax(vcpu));
+}
 EXPORT_SYMBOL_GPL(kvm_emulate_wrmsr);
 
+int kvm_emulate_wrmsr_imm(struct kvm_vcpu *vcpu, u32 msr, int reg)
+{
+	return __kvm_emulate_wrmsr(vcpu, msr, kvm_register_read(vcpu, reg));
+}
+EXPORT_SYMBOL_GPL(kvm_emulate_wrmsr_imm);
+
 int kvm_emulate_as_nop(struct kvm_vcpu *vcpu)
 {
 	return kvm_skip_emulated_instruction(vcpu);
@@ -2093,6 +2140,15 @@ int kvm_emulate_invd(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_invd);
 
+fastpath_t handle_fastpath_invd(struct kvm_vcpu *vcpu)
+{
+	if (!kvm_emulate_invd(vcpu))
+		return EXIT_FASTPATH_EXIT_USERSPACE;
+
+	return EXIT_FASTPATH_REENTER_GUEST;
+}
+EXPORT_SYMBOL_GPL(handle_fastpath_invd);
+
 int kvm_handle_invalid_op(struct kvm_vcpu *vcpu)
 {
 	kvm_queue_exception(vcpu, UD_VECTOR);
@@ -2140,74 +2196,41 @@ static inline bool kvm_vcpu_exit_request(struct kvm_vcpu *vcpu)
 	       kvm_request_pending(vcpu) || xfer_to_guest_mode_work_pending();
 }
 
-/*
- * The fast path for frequent and performance sensitive wrmsr emulation,
- * i.e. the sending of IPI, sending IPI early in the VM-Exit flow reduces
- * the latency of virtual IPI by avoiding the expensive bits of transitioning
- * from guest to host, e.g. reacquiring KVM's SRCU lock. In contrast to the
- * other cases which must be called after interrupts are enabled on the host.
- */
-static int handle_fastpath_set_x2apic_icr_irqoff(struct kvm_vcpu *vcpu, u64 data)
-{
-	if (!lapic_in_kernel(vcpu) || !apic_x2apic_mode(vcpu->arch.apic))
-		return 1;
-
-	if (((data & APIC_SHORT_MASK) == APIC_DEST_NOSHORT) &&
-	    ((data & APIC_DEST_MASK) == APIC_DEST_PHYSICAL) &&
-	    ((data & APIC_MODE_MASK) == APIC_DM_FIXED) &&
-	    ((u32)(data >> 32) != X2APIC_BROADCAST))
-		return kvm_x2apic_icr_write(vcpu->arch.apic, data);
-
-	return 1;
-}
-
-static int handle_fastpath_set_tscdeadline(struct kvm_vcpu *vcpu, u64 data)
-{
-	if (!kvm_can_use_hv_timer(vcpu))
-		return 1;
-
-	kvm_set_lapic_tscdeadline_msr(vcpu, data);
-	return 0;
-}
-
-fastpath_t handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu)
+static fastpath_t __handle_fastpath_wrmsr(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 {
-	u32 msr = kvm_rcx_read(vcpu);
-	u64 data;
-	fastpath_t ret;
-	bool handled;
-
-	kvm_vcpu_srcu_read_lock(vcpu);
-
 	switch (msr) {
 	case APIC_BASE_MSR + (APIC_ICR >> 4):
-		data = kvm_read_edx_eax(vcpu);
-		handled = !handle_fastpath_set_x2apic_icr_irqoff(vcpu, data);
+		if (!lapic_in_kernel(vcpu) || !apic_x2apic_mode(vcpu->arch.apic) ||
+		    kvm_x2apic_icr_write_fast(vcpu->arch.apic, data))
+			return EXIT_FASTPATH_NONE;
 		break;
 	case MSR_IA32_TSC_DEADLINE:
-		data = kvm_read_edx_eax(vcpu);
-		handled = !handle_fastpath_set_tscdeadline(vcpu, data);
+		kvm_set_lapic_tscdeadline_msr(vcpu, data);
 		break;
 	default:
-		handled = false;
-		break;
+		return EXIT_FASTPATH_NONE;
 	}
 
-	if (handled) {
-		if (!kvm_skip_emulated_instruction(vcpu))
-			ret = EXIT_FASTPATH_EXIT_USERSPACE;
-		else
-			ret = EXIT_FASTPATH_REENTER_GUEST;
-		trace_kvm_msr_write(msr, data);
-	} else {
-		ret = EXIT_FASTPATH_NONE;
-	}
+	trace_kvm_msr_write(msr, data);
 
-	kvm_vcpu_srcu_read_unlock(vcpu);
+	if (!kvm_skip_emulated_instruction(vcpu))
+		return EXIT_FASTPATH_EXIT_USERSPACE;
 
-	return ret;
+	return EXIT_FASTPATH_REENTER_GUEST;
 }
-EXPORT_SYMBOL_GPL(handle_fastpath_set_msr_irqoff);
+
+fastpath_t handle_fastpath_wrmsr(struct kvm_vcpu *vcpu)
+{
+	return __handle_fastpath_wrmsr(vcpu, kvm_rcx_read(vcpu),
+				       kvm_read_edx_eax(vcpu));
+}
+EXPORT_SYMBOL_GPL(handle_fastpath_wrmsr);
+
+fastpath_t handle_fastpath_wrmsr_imm(struct kvm_vcpu *vcpu, u32 msr, int reg)
+{
+	return __handle_fastpath_wrmsr(vcpu, msr, kvm_register_read(vcpu, reg));
+}
+EXPORT_SYMBOL_GPL(handle_fastpath_wrmsr_imm);
 
 /*
  * Adapt set_msr() to msr_io()'s calling convention
@@ -6778,7 +6801,11 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm,
 
 	kvm_free_msr_filter(old_filter);
 
-	kvm_make_all_cpus_request(kvm, KVM_REQ_MSR_FILTER_CHANGED);
+	/*
+	 * Recalc MSR intercepts as userspace may want to intercept accesses to
+	 * MSRs that KVM would otherwise pass through to the guest.
+	 */
+	kvm_make_all_cpus_request(kvm, KVM_REQ_RECALC_INTERCEPTS);
 
 	return 0;
 }
@@ -6973,6 +7000,15 @@ set_identity_unlock:
 		if (irqchip_in_kernel(kvm))
 			goto create_irqchip_unlock;
 
+		/*
+		 * Disallow an in-kernel I/O APIC if the VM has protected EOIs,
+		 * i.e. if KVM can't intercept EOIs and thus can't properly
+		 * emulate level-triggered interrupts.
+		 */
+		r = -ENOTTY;
+		if (kvm->arch.has_protected_eoi)
+			goto create_irqchip_unlock;
+
 		r = -EINVAL;
 		if (kvm->created_vcpus)
 			goto create_irqchip_unlock;
@@ -7360,6 +7396,7 @@ static void kvm_probe_msr_to_save(u32 msr_index)
 	case MSR_AMD64_PERF_CNTR_GLOBAL_CTL:
 	case MSR_AMD64_PERF_CNTR_GLOBAL_STATUS:
 	case MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR:
+	case MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_SET:
 		if (!kvm_cpu_cap_has(X86_FEATURE_PERFMON_V2))
 			return;
 		break;
@@ -8360,7 +8397,7 @@ static int emulator_get_msr_with_filter(struct x86_emulate_ctxt *ctxt,
 	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
 	int r;
 
-	r = kvm_get_msr_with_filter(vcpu, msr_index, pdata);
+	r = kvm_emulate_msr_read(vcpu, msr_index, pdata);
 	if (r < 0)
 		return X86EMUL_UNHANDLEABLE;
 
@@ -8383,7 +8420,7 @@ static int emulator_set_msr_with_filter(struct x86_emulate_ctxt *ctxt,
 	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
 	int r;
 
-	r = kvm_set_msr_with_filter(vcpu, msr_index, data);
+	r = kvm_emulate_msr_write(vcpu, msr_index, data);
 	if (r < 0)
 		return X86EMUL_UNHANDLEABLE;
 
@@ -8403,7 +8440,7 @@ static int emulator_set_msr_with_filter(struct x86_emulate_ctxt *ctxt,
 static int emulator_get_msr(struct x86_emulate_ctxt *ctxt,
 			    u32 msr_index, u64 *pdata)
 {
-	return kvm_get_msr(emul_to_vcpu(ctxt), msr_index, pdata);
+	return __kvm_emulate_msr_read(emul_to_vcpu(ctxt), msr_index, pdata);
 }
 
 static int emulator_check_rdpmc_early(struct x86_emulate_ctxt *ctxt, u32 pmc)
@@ -8477,11 +8514,6 @@ static bool emulator_is_smm(struct x86_emulate_ctxt *ctxt)
 	return is_smm(emul_to_vcpu(ctxt));
 }
 
-static bool emulator_is_guest_mode(struct x86_emulate_ctxt *ctxt)
-{
-	return is_guest_mode(emul_to_vcpu(ctxt));
-}
-
 #ifndef CONFIG_KVM_SMM
 static int emulator_leave_smm(struct x86_emulate_ctxt *ctxt)
 {
@@ -8565,7 +8597,6 @@ static const struct x86_emulate_ops emulate_ops = {
 	.guest_cpuid_is_intel_compatible = emulator_guest_cpuid_is_intel_compatible,
 	.set_nmi_mask        = emulator_set_nmi_mask,
 	.is_smm              = emulator_is_smm,
-	.is_guest_mode       = emulator_is_guest_mode,
 	.leave_smm           = emulator_leave_smm,
 	.triple_fault        = emulator_triple_fault,
 	.set_xcr             = emulator_set_xcr,
@@ -8871,7 +8902,7 @@ int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu)
 	if (unlikely(!r))
 		return 0;
 
-	kvm_pmu_trigger_event(vcpu, kvm_pmu_eventsel.INSTRUCTIONS_RETIRED);
+	kvm_pmu_instruction_retired(vcpu);
 
 	/*
 	 * rflags is the old, "raw" value of the flags.  The new value has
@@ -9150,7 +9181,14 @@ restart:
 		ctxt->exception.address = 0;
 	}
 
-	r = x86_emulate_insn(ctxt);
+	/*
+	 * Check L1's instruction intercepts when emulating instructions for
+	 * L2, unless KVM is re-emulating a previously decoded instruction,
+	 * e.g. to complete userspace I/O, in which case KVM has already
+	 * checked the intercepts.
+	 */
+	r = x86_emulate_insn(ctxt, is_guest_mode(vcpu) &&
+				   !(emulation_type & EMULTYPE_NO_DECODE));
 
 	if (r == EMULATION_INTERCEPTED)
 		return 1;
@@ -9205,9 +9243,9 @@ writeback:
 		 */
 		if (!ctxt->have_exception ||
 		    exception_type(ctxt->exception.vector) == EXCPT_TRAP) {
-			kvm_pmu_trigger_event(vcpu, kvm_pmu_eventsel.INSTRUCTIONS_RETIRED);
+			kvm_pmu_instruction_retired(vcpu);
 			if (ctxt->is_branch)
-				kvm_pmu_trigger_event(vcpu, kvm_pmu_eventsel.BRANCH_INSTRUCTIONS_RETIRED);
+				kvm_pmu_branch_retired(vcpu);
 			kvm_rip_write(vcpu, ctxt->eip);
 			if (r && (ctxt->tf || (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)))
 				r = kvm_vcpu_do_singlestep(vcpu);
@@ -10803,13 +10841,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *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(recalc_msr_intercepts)(vcpu);
+		if (kvm_check_request(KVM_REQ_RECALC_INTERCEPTS, vcpu))
+			kvm_x86_call(recalc_intercepts)(vcpu);
 
 		if (kvm_check_request(KVM_REQ_UPDATE_CPU_DIRTY_LOGGING, vcpu))
 			kvm_x86_call(update_cpu_dirty_logging)(vcpu);
@@ -11310,13 +11343,7 @@ EXPORT_SYMBOL_GPL(kvm_emulate_halt);
 
 fastpath_t handle_fastpath_hlt(struct kvm_vcpu *vcpu)
 {
-	int ret;
-
-	kvm_vcpu_srcu_read_lock(vcpu);
-	ret = kvm_emulate_halt(vcpu);
-	kvm_vcpu_srcu_read_unlock(vcpu);
-
-	if (!ret)
+	if (!kvm_emulate_halt(vcpu))
 		return EXIT_FASTPATH_EXIT_USERSPACE;
 
 	if (kvm_vcpu_running(vcpu))
@@ -12395,6 +12422,41 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 	kvfree(vcpu->arch.cpuid_entries);
 }
 
+static void kvm_xstate_reset(struct kvm_vcpu *vcpu, bool init_event)
+{
+	struct fpstate *fpstate = vcpu->arch.guest_fpu.fpstate;
+	u64 xfeatures_mask;
+	int i;
+
+	/*
+	 * Guest FPU state is zero allocated and so doesn't need to be manually
+	 * cleared on RESET, i.e. during vCPU creation.
+	 */
+	if (!init_event || !fpstate)
+		return;
+
+	/*
+	 * On INIT, only select XSTATE components are zeroed, most components
+	 * are unchanged.  Currently, the only components that are zeroed and
+	 * supported by KVM are MPX related.
+	 */
+	xfeatures_mask = (kvm_caps.supported_xcr0 | kvm_caps.supported_xss) &
+			 (XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR);
+	if (!xfeatures_mask)
+		return;
+
+	BUILD_BUG_ON(sizeof(xfeatures_mask) * BITS_PER_BYTE <= XFEATURE_MAX);
+
+	/*
+	 * All paths that lead to INIT are required to load the guest's FPU
+	 * state (because most paths are buried in KVM_RUN).
+	 */
+	kvm_put_guest_fpu(vcpu);
+	for_each_set_bit(i, (unsigned long *)&xfeatures_mask, XFEATURE_MAX)
+		fpstate_clear_xstate_component(fpstate, i);
+	kvm_load_guest_fpu(vcpu);
+}
+
 void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 {
 	struct kvm_cpuid_entry2 *cpuid_0x1;
@@ -12452,22 +12514,7 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	kvm_async_pf_hash_reset(vcpu);
 	vcpu->arch.apf.halted = false;
 
-	if (vcpu->arch.guest_fpu.fpstate && kvm_mpx_supported()) {
-		struct fpstate *fpstate = vcpu->arch.guest_fpu.fpstate;
-
-		/*
-		 * All paths that lead to INIT are required to load the guest's
-		 * FPU state (because most paths are buried in KVM_RUN).
-		 */
-		if (init_event)
-			kvm_put_guest_fpu(vcpu);
-
-		fpstate_clear_xstate_component(fpstate, XFEATURE_BNDREGS);
-		fpstate_clear_xstate_component(fpstate, XFEATURE_BNDCSR);
-
-		if (init_event)
-			kvm_load_guest_fpu(vcpu);
-	}
+	kvm_xstate_reset(vcpu, init_event);
 
 	if (!init_event) {
 		vcpu->arch.smbase = 0x30000;
@@ -12479,7 +12526,7 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 						  MSR_IA32_MISC_ENABLE_BTS_UNAVAIL;
 
 		__kvm_set_xcr(vcpu, 0, XFEATURE_MASK_FP);
-		__kvm_set_msr(vcpu, MSR_IA32_XSS, 0, true);
+		kvm_msr_write(vcpu, MSR_IA32_XSS, 0);
 	}
 
 	/* All GPRs except RDX (handled below) are zeroed on RESET/INIT. */
@@ -13526,11 +13573,6 @@ bool kvm_arch_has_noncoherent_dma(struct kvm *kvm)
 }
 EXPORT_SYMBOL_GPL(kvm_arch_has_noncoherent_dma);
 
-bool kvm_vector_hashing_enabled(void)
-{
-	return vector_hashing;
-}
-
 bool kvm_arch_no_poll(struct kvm_vcpu *vcpu)
 {
 	return (vcpu->arch.msr_kvm_poll_control & 1) == 0;