KVM: Rename and move CPUHP_AP_KVM_STARTING to ONLINE section

The CPU STARTING section doesn't allow callbacks to fail. Move KVM's
hotplug callback to ONLINE section so that it can abort onlining a CPU in
certain cases to avoid potentially breaking VMs running on existing CPUs.
For example, when KVM fails to enable hardware virtualization on the
hotplugged CPU.

Place KVM's hotplug state before CPUHP_AP_SCHED_WAIT_EMPTY as it ensures
when offlining a CPU, all user tasks and non-pinned kernel tasks have left
the CPU, i.e. there cannot be a vCPU task around. So, it is safe for KVM's
CPU offline callback to disable hardware virtualization at that point.
Likewise, KVM's online callback can enable hardware virtualization before
any vCPU task gets a chance to run on hotplugged CPUs.

Drop kvm_x86_check_processor_compatibility()'s WARN that IRQs are
disabled, as the ONLINE section runs with IRQs disabled.  The WARN wasn't
intended to be a requirement, e.g. disabling preemption is sufficient,
the IRQ thing was purely an aggressive sanity check since the helper was
only ever invoked via SMP function call.

Rename KVM's CPU hotplug callbacks accordingly.

Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Chao Gao <chao.gao@intel.com>
Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
Reviewed-by: Yuan Yao <yuan.yao@intel.com>
[sean: drop WARN that IRQs are disabled]
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20221130230934.1014142-42-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

3 files changed, 23 insertions, 11 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 6575d9e7b9b6..f2971821ec26 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -9298,8 +9298,6 @@ static int kvm_x86_check_processor_compatibility(void)
 {
 	struct cpuinfo_x86 *c = &cpu_data(smp_processor_id());
 
-	WARN_ON(!irqs_disabled());
-
 	if (__cr4_reserved_bits(cpu_has, c) !=
 	    __cr4_reserved_bits(cpu_has, &boot_cpu_data))
 		return -EIO;
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 5cae6bd22f7f..5b2f8147d1ae 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -187,7 +187,6 @@ enum cpuhp_state {
 	CPUHP_AP_CSKY_TIMER_STARTING,
 	CPUHP_AP_TI_GP_TIMER_STARTING,
 	CPUHP_AP_HYPERV_TIMER_STARTING,
-	CPUHP_AP_KVM_STARTING,
 	/* Must be the last timer callback */
 	CPUHP_AP_DUMMY_TIMER_STARTING,
 	CPUHP_AP_ARM_XEN_STARTING,
@@ -202,6 +201,7 @@ enum cpuhp_state {
 
 	/* Online section invoked on the hotplugged CPU from the hotplug thread */
 	CPUHP_AP_ONLINE_IDLE,
+	CPUHP_AP_KVM_ONLINE,
 	CPUHP_AP_SCHED_WAIT_EMPTY,
 	CPUHP_AP_SMPBOOT_THREADS,
 	CPUHP_AP_X86_VDSO_VMA_ONLINE,
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index e13b369cfc1b..ee1005cb99e1 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -5114,13 +5114,27 @@ static void hardware_enable_nolock(void *junk)
 	}
 }
 
-static int kvm_starting_cpu(unsigned int cpu)
+static int kvm_online_cpu(unsigned int cpu)
 {
+	int ret = 0;
+
+	/*
+	 * Abort the CPU online process if hardware virtualization cannot
+	 * be enabled. Otherwise running VMs would encounter unrecoverable
+	 * errors when scheduled to this CPU.
+	 */
 	raw_spin_lock(&kvm_count_lock);
-	if (kvm_usage_count)
+	if (kvm_usage_count) {
+		WARN_ON_ONCE(atomic_read(&hardware_enable_failed));
+
 		hardware_enable_nolock(NULL);
+		if (atomic_read(&hardware_enable_failed)) {
+			atomic_set(&hardware_enable_failed, 0);
+			ret = -EIO;
+		}
+	}
 	raw_spin_unlock(&kvm_count_lock);
-	return 0;
+	return ret;
 }
 
 static void hardware_disable_nolock(void *junk)
@@ -5133,7 +5147,7 @@ static void hardware_disable_nolock(void *junk)
 	kvm_arch_hardware_disable();
 }
 
-static int kvm_dying_cpu(unsigned int cpu)
+static int kvm_offline_cpu(unsigned int cpu)
 {
 	raw_spin_lock(&kvm_count_lock);
 	if (kvm_usage_count)
@@ -5910,8 +5924,8 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module)
 	if (!zalloc_cpumask_var(&cpus_hardware_enabled, GFP_KERNEL))
 		return -ENOMEM;
 
-	r = cpuhp_setup_state_nocalls(CPUHP_AP_KVM_STARTING, "kvm/cpu:starting",
-				      kvm_starting_cpu, kvm_dying_cpu);
+	r = cpuhp_setup_state_nocalls(CPUHP_AP_KVM_ONLINE, "kvm/cpu:online",
+				      kvm_online_cpu, kvm_offline_cpu);
 	if (r)
 		goto out_free_2;
 	register_reboot_notifier(&kvm_reboot_notifier);
@@ -5985,7 +5999,7 @@ out_free_4:
 	kmem_cache_destroy(kvm_vcpu_cache);
 out_free_3:
 	unregister_reboot_notifier(&kvm_reboot_notifier);
-	cpuhp_remove_state_nocalls(CPUHP_AP_KVM_STARTING);
+	cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE);
 out_free_2:
 	free_cpumask_var(cpus_hardware_enabled);
 	return r;
@@ -6011,7 +6025,7 @@ void kvm_exit(void)
 	kvm_async_pf_deinit();
 	unregister_syscore_ops(&kvm_syscore_ops);
 	unregister_reboot_notifier(&kvm_reboot_notifier);
-	cpuhp_remove_state_nocalls(CPUHP_AP_KVM_STARTING);
+	cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE);
 	on_each_cpu(hardware_disable_nolock, NULL, 1);
 	kvm_irqfd_exit();
 	free_cpumask_var(cpus_hardware_enabled);