From: Paolo Bonzini <pbonzini@redhat.com>
Date: Sat, 14 Sep 2024 13:38:08 +0000 (-0400)
Subject: Merge tag 'kvm-x86-misc-6.12' of https://github.com/kvm-x86/linux into HEAD
X-Git-Tag: v6.12-rc1~11^2~6
X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=41786cc5ea89b71437dd6fece444f3766edb4db7;p=thirdparty%2Fkernel%2Flinux.git

Merge tag 'kvm-x86-misc-6.12' of https://github.com/kvm-x86/linux into HEAD

KVM x86 misc changes for 6.12

 - Advertise AVX10.1 to userspace (effectively prep work for the "real" AVX10
   functionality that is on the horizon).

 - Rework common MSR handling code to suppress errors on userspace accesses to
   unsupported-but-advertised MSRs.  This will allow removing (almost?) all of
   KVM's exemptions for userspace access to MSRs that shouldn't exist based on
   the vCPU model (the actual cleanup is non-trivial future work).

 - Rework KVM's handling of x2APIC ICR, again, because AMD (x2AVIC) splits the
   64-bit value into the legacy ICR and ICR2 storage, whereas Intel (APICv)
   stores the entire 64-bit value a the ICR offset.

 - Fix a bug where KVM would fail to exit to userspace if one was triggered by
   a fastpath exit handler.

 - Add fastpath handling of HLT VM-Exit to expedite re-entering the guest when
   there's already a pending wake event at the time of the exit.

 - Finally fix the RSM vs. nested VM-Enter WARN by forcing the vCPU out of
   guest mode prior to signalling SHUTDOWN (architecturally, the SHUTDOWN is
   supposed to hit L1, not L2).
---

41786cc5ea89b71437dd6fece444f3766edb4db7
diff --cc arch/x86/kvm/x86.c
index 0f7342b574f91,92fade53c79f9..a877c0764fc56
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@@ -9898,78 -9883,33 +9887,33 @@@ void kvm_x86_vendor_exit(void
  
  #ifdef CONFIG_X86_64
  	if (hypervisor_is_type(X86_HYPER_MS_HYPERV))
- 		clear_hv_tscchange_cb();
- #endif
- 	kvm_lapic_exit();
- 
- 	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) {
- 		cpufreq_unregister_notifier(&kvmclock_cpufreq_notifier_block,
- 					    CPUFREQ_TRANSITION_NOTIFIER);
- 		cpuhp_remove_state_nocalls(CPUHP_AP_X86_KVM_CLK_ONLINE);
- 	}
- #ifdef CONFIG_X86_64
- 	pvclock_gtod_unregister_notifier(&pvclock_gtod_notifier);
- 	irq_work_sync(&pvclock_irq_work);
- 	cancel_work_sync(&pvclock_gtod_work);
- #endif
- 	kvm_x86_call(hardware_unsetup)();
- 	kvm_mmu_vendor_module_exit();
- 	free_percpu(user_return_msrs);
- 	kmem_cache_destroy(x86_emulator_cache);
- #ifdef CONFIG_KVM_XEN
- 	static_key_deferred_flush(&kvm_xen_enabled);
- 	WARN_ON(static_branch_unlikely(&kvm_xen_enabled.key));
- #endif
- 	mutex_lock(&vendor_module_lock);
- 	kvm_x86_ops.enable_virtualization_cpu = NULL;
- 	mutex_unlock(&vendor_module_lock);
- }
- EXPORT_SYMBOL_GPL(kvm_x86_vendor_exit);
- 
- static int __kvm_emulate_halt(struct kvm_vcpu *vcpu, int state, int reason)
- {
- 	/*
- 	 * The vCPU has halted, e.g. executed HLT.  Update the run state if the
- 	 * local APIC is in-kernel, the run loop will detect the non-runnable
- 	 * state and halt the vCPU.  Exit to userspace if the local APIC is
- 	 * managed by userspace, in which case userspace is responsible for
- 	 * handling wake events.
- 	 */
- 	++vcpu->stat.halt_exits;
- 	if (lapic_in_kernel(vcpu)) {
- 		vcpu->arch.mp_state = state;
- 		return 1;
- 	} else {
- 		vcpu->run->exit_reason = reason;
- 		return 0;
- 	}
- }
- 
- int kvm_emulate_halt_noskip(struct kvm_vcpu *vcpu)
- {
- 	return __kvm_emulate_halt(vcpu, KVM_MP_STATE_HALTED, KVM_EXIT_HLT);
- }
- EXPORT_SYMBOL_GPL(kvm_emulate_halt_noskip);
- 
- int kvm_emulate_halt(struct kvm_vcpu *vcpu)
- {
- 	int ret = kvm_skip_emulated_instruction(vcpu);
- 	/*
- 	 * TODO: we might be squashing a GUESTDBG_SINGLESTEP-triggered
- 	 * KVM_EXIT_DEBUG here.
- 	 */
- 	return kvm_emulate_halt_noskip(vcpu) && ret;
- }
- EXPORT_SYMBOL_GPL(kvm_emulate_halt);
- 
- int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu)
- {
- 	int ret = kvm_skip_emulated_instruction(vcpu);
+ 		clear_hv_tscchange_cb();
+ #endif
+ 	kvm_lapic_exit();
  
- 	return __kvm_emulate_halt(vcpu, KVM_MP_STATE_AP_RESET_HOLD,
- 					KVM_EXIT_AP_RESET_HOLD) && ret;
+ 	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) {
+ 		cpufreq_unregister_notifier(&kvmclock_cpufreq_notifier_block,
+ 					    CPUFREQ_TRANSITION_NOTIFIER);
+ 		cpuhp_remove_state_nocalls(CPUHP_AP_X86_KVM_CLK_ONLINE);
+ 	}
+ #ifdef CONFIG_X86_64
+ 	pvclock_gtod_unregister_notifier(&pvclock_gtod_notifier);
+ 	irq_work_sync(&pvclock_irq_work);
+ 	cancel_work_sync(&pvclock_gtod_work);
+ #endif
+ 	kvm_x86_call(hardware_unsetup)();
+ 	kvm_mmu_vendor_module_exit();
+ 	free_percpu(user_return_msrs);
+ 	kmem_cache_destroy(x86_emulator_cache);
+ #ifdef CONFIG_KVM_XEN
+ 	static_key_deferred_flush(&kvm_xen_enabled);
+ 	WARN_ON(static_branch_unlikely(&kvm_xen_enabled.key));
+ #endif
+ 	mutex_lock(&vendor_module_lock);
 -	kvm_x86_ops.hardware_enable = NULL;
++	kvm_x86_ops.enable_virtualization_cpu = NULL;
+ 	mutex_unlock(&vendor_module_lock);
  }
- EXPORT_SYMBOL_GPL(kvm_emulate_ap_reset_hold);
+ EXPORT_SYMBOL_GPL(kvm_x86_vendor_exit);
  
  #ifdef CONFIG_X86_64
  static int kvm_pv_clock_pairing(struct kvm_vcpu *vcpu, gpa_t paddr,