Merge tag 'perf_core_for_v5.17_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf updates from Borislav Petkov:
 "Cleanup of the perf/kvm interaction."

* tag 'perf_core_for_v5.17_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf: Drop guest callback (un)register stubs
  KVM: arm64: Drop perf.c and fold its tiny bits of code into arm.c
  KVM: arm64: Hide kvm_arm_pmu_available behind CONFIG_HW_PERF_EVENTS=y
  KVM: arm64: Convert to the generic perf callbacks
  KVM: x86: Move Intel Processor Trace interrupt handler to vmx.c
  KVM: Move x86's perf guest info callbacks to generic KVM
  KVM: x86: More precisely identify NMI from guest when handling PMI
  KVM: x86: Drop current_vcpu for kvm_running_vcpu + kvm_arch_vcpu variable
  perf/core: Use static_call to optimize perf_guest_info_callbacks
  perf: Force architectures to opt-in to guest callbacks
  perf: Add wrappers for invoking guest callbacks
  perf/core: Rework guest callbacks to prepare for static_call support
  perf: Drop dead and useless guest "support" from arm, csky, nds32 and riscv
  perf: Stop pretending that perf can handle multiple guest callbacks
  KVM: x86: Register Processor Trace interrupt hook iff PT enabled in guest
  KVM: x86: Register perf callbacks after calling vendor's hardware_setup()
  perf: Protect perf_guest_cbs with RCU

6 files changed, 50 insertions, 55 deletions

diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 619186138176..47bdbe705a76 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -36,6 +36,7 @@ config KVM
 	select KVM_MMIO
 	select SCHED_INFO
 	select PERF_EVENTS
+	select GUEST_PERF_EVENTS
 	select HAVE_KVM_MSI
 	select HAVE_KVM_CPU_RELAX_INTERCEPT
 	select HAVE_KVM_NO_POLL
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 09873f6488f7..0c2133eb4cf6 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -87,7 +87,7 @@ static void kvm_perf_overflow_intr(struct perf_event *perf_event,
 		 * woken up. So we should wake it, but this is impossible from
 		 * NMI context. Do it from irq work instead.
 		 */
-		if (!kvm_is_in_guest())
+		if (!kvm_handling_nmi_from_guest(pmc->vcpu))
 			irq_work_queue(&pmc_to_pmu(pmc)->irq_work);
 		else
 			kvm_make_request(KVM_REQ_PMI, pmc->vcpu);
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 5151efa424ac..9079d2fdc12e 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -3933,7 +3933,7 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu)
 	}
 
 	if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI))
-		kvm_before_interrupt(vcpu);
+		kvm_before_interrupt(vcpu, KVM_HANDLING_NMI);
 
 	kvm_load_host_xsave_state(vcpu);
 	stgi();
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 0dbf94eb954f..1187cd1e38aa 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -6344,7 +6344,9 @@ void vmx_do_interrupt_nmi_irqoff(unsigned long entry);
 static void handle_interrupt_nmi_irqoff(struct kvm_vcpu *vcpu,
 					unsigned long entry)
 {
-	kvm_before_interrupt(vcpu);
+	bool is_nmi = entry == (unsigned long)asm_exc_nmi_noist;
+
+	kvm_before_interrupt(vcpu, is_nmi ? KVM_HANDLING_NMI : KVM_HANDLING_IRQ);
 	vmx_do_interrupt_nmi_irqoff(entry);
 	kvm_after_interrupt(vcpu);
 }
@@ -7693,6 +7695,20 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = {
 	.vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector,
 };
 
+static unsigned int vmx_handle_intel_pt_intr(void)
+{
+	struct kvm_vcpu *vcpu = kvm_get_running_vcpu();
+
+	/* '0' on failure so that the !PT case can use a RET0 static call. */
+	if (!kvm_arch_pmi_in_guest(vcpu))
+		return 0;
+
+	kvm_make_request(KVM_REQ_PMI, vcpu);
+	__set_bit(MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI_BIT,
+		  (unsigned long *)&vcpu->arch.pmu.global_status);
+	return 1;
+}
+
 static __init void vmx_setup_user_return_msrs(void)
 {
 
@@ -7719,6 +7735,8 @@ static __init void vmx_setup_user_return_msrs(void)
 		kvm_add_user_return_msr(vmx_uret_msrs_list[i]);
 }
 
+static struct kvm_x86_init_ops vmx_init_ops __initdata;
+
 static __init int hardware_setup(void)
 {
 	unsigned long host_bndcfgs;
@@ -7877,6 +7895,10 @@ static __init int hardware_setup(void)
 		return -EINVAL;
 	if (!enable_ept || !cpu_has_vmx_intel_pt())
 		pt_mode = PT_MODE_SYSTEM;
+	if (pt_mode == PT_MODE_HOST_GUEST)
+		vmx_init_ops.handle_intel_pt_intr = vmx_handle_intel_pt_intr;
+	else
+		vmx_init_ops.handle_intel_pt_intr = NULL;
 
 	setup_default_sgx_lepubkeyhash();
 
@@ -7905,6 +7927,7 @@ static struct kvm_x86_init_ops vmx_init_ops __initdata = {
 	.disabled_by_bios = vmx_disabled_by_bios,
 	.check_processor_compatibility = vmx_check_processor_compat,
 	.hardware_setup = hardware_setup,
+	.handle_intel_pt_intr = NULL,
 
 	.runtime_ops = &vmx_x86_ops,
 };
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e50e97ac4408..829d03fcb481 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -8519,50 +8519,6 @@ static void kvm_timer_init(void)
 			  kvmclock_cpu_online, kvmclock_cpu_down_prep);
 }
 
-DEFINE_PER_CPU(struct kvm_vcpu *, current_vcpu);
-EXPORT_PER_CPU_SYMBOL_GPL(current_vcpu);
-
-int kvm_is_in_guest(void)
-{
-	return __this_cpu_read(current_vcpu) != NULL;
-}
-
-static int kvm_is_user_mode(void)
-{
-	int user_mode = 3;
-
-	if (__this_cpu_read(current_vcpu))
-		user_mode = static_call(kvm_x86_get_cpl)(__this_cpu_read(current_vcpu));
-
-	return user_mode != 0;
-}
-
-static unsigned long kvm_get_guest_ip(void)
-{
-	unsigned long ip = 0;
-
-	if (__this_cpu_read(current_vcpu))
-		ip = kvm_rip_read(__this_cpu_read(current_vcpu));
-
-	return ip;
-}
-
-static void kvm_handle_intel_pt_intr(void)
-{
-	struct kvm_vcpu *vcpu = __this_cpu_read(current_vcpu);
-
-	kvm_make_request(KVM_REQ_PMI, vcpu);
-	__set_bit(MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI_BIT,
-			(unsigned long *)&vcpu->arch.pmu.global_status);
-}
-
-static struct perf_guest_info_callbacks kvm_guest_cbs = {
-	.is_in_guest		= kvm_is_in_guest,
-	.is_user_mode		= kvm_is_user_mode,
-	.get_guest_ip		= kvm_get_guest_ip,
-	.handle_intel_pt_intr	= kvm_handle_intel_pt_intr,
-};
-
 #ifdef CONFIG_X86_64
 static void pvclock_gtod_update_fn(struct work_struct *work)
 {
@@ -8676,8 +8632,6 @@ int kvm_arch_init(void *opaque)
 
 	kvm_timer_init();
 
-	perf_register_guest_info_callbacks(&kvm_guest_cbs);
-
 	if (boot_cpu_has(X86_FEATURE_XSAVE)) {
 		host_xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
 		supported_xcr0 = host_xcr0 & KVM_SUPPORTED_XCR0;
@@ -8709,7 +8663,6 @@ void kvm_arch_exit(void)
 		clear_hv_tscchange_cb();
 #endif
 	kvm_lapic_exit();
-	perf_unregister_guest_info_callbacks(&kvm_guest_cbs);
 
 	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
 		cpufreq_unregister_notifier(&kvmclock_cpufreq_notifier_block,
@@ -9936,7 +9889,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	 * interrupts on processors that implement an interrupt shadow, the
 	 * stat.exits increment will do nicely.
 	 */
-	kvm_before_interrupt(vcpu);
+	kvm_before_interrupt(vcpu, KVM_HANDLING_IRQ);
 	local_irq_enable();
 	++vcpu->stat.exits;
 	local_irq_disable();
@@ -11269,6 +11222,8 @@ int kvm_arch_hardware_setup(void *opaque)
 	memcpy(&kvm_x86_ops, ops->runtime_ops, sizeof(kvm_x86_ops));
 	kvm_ops_static_call_update();
 
+	kvm_register_perf_callbacks(ops->handle_intel_pt_intr);
+
 	if (!kvm_cpu_cap_has(X86_FEATURE_XSAVES))
 		supported_xss = 0;
 
@@ -11296,6 +11251,8 @@ int kvm_arch_hardware_setup(void *opaque)
 
 void kvm_arch_hardware_unsetup(void)
 {
+	kvm_unregister_perf_callbacks();
+
 	static_call(kvm_x86_hardware_unsetup)();
 }
 
@@ -11885,6 +11842,11 @@ bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
 	return vcpu->arch.preempted_in_kernel;
 }
 
+unsigned long kvm_arch_vcpu_get_ip(struct kvm_vcpu *vcpu)
+{
+	return kvm_rip_read(vcpu);
+}
+
 int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
 {
 	return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE;
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 4abcd8d9836d..6aeca8f1da91 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -392,18 +392,27 @@ static inline bool kvm_cstate_in_guest(struct kvm *kvm)
 	return kvm->arch.cstate_in_guest;
 }
 
-DECLARE_PER_CPU(struct kvm_vcpu *, current_vcpu);
+enum kvm_intr_type {
+	/* Values are arbitrary, but must be non-zero. */
+	KVM_HANDLING_IRQ = 1,
+	KVM_HANDLING_NMI,
+};
 
-static inline void kvm_before_interrupt(struct kvm_vcpu *vcpu)
+static inline void kvm_before_interrupt(struct kvm_vcpu *vcpu,
+					enum kvm_intr_type intr)
 {
-	__this_cpu_write(current_vcpu, vcpu);
+	WRITE_ONCE(vcpu->arch.handling_intr_from_guest, (u8)intr);
 }
 
 static inline void kvm_after_interrupt(struct kvm_vcpu *vcpu)
 {
-	__this_cpu_write(current_vcpu, NULL);
+	WRITE_ONCE(vcpu->arch.handling_intr_from_guest, 0);
 }
 
+static inline bool kvm_handling_nmi_from_guest(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.handling_intr_from_guest == KVM_HANDLING_NMI;
+}
 
 static inline bool kvm_pat_valid(u64 data)
 {