Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:18 as permitted sender) client-ip=2620:137:e000::1:18;
From:   Chao Gao <chao.gao@intel.com>
To:     seanjc@google.com, maz@kernel.org, kvm@vger.kernel.org,
        pbonzini@redhat.com, kevin.tian@intel.com, tglx@linutronix.de
Cc:     Chao Gao <chao.gao@intel.com>, John Garry <john.garry@huawei.com>,
        Will Deacon <will@kernel.org>,
        Shaokun Zhang <zhangshaokun@hisilicon.com>,
        Qi Liu <liuqi115@huawei.com>,
        Sumanth Korikkar <sumanthk@linux.ibm.com>,
        Thomas Richter <tmricht@linux.ibm.com>,
        Dave Chinner <dchinner@redhat.com>,
        linux-kernel@vger.kernel.org
Subject: [PATCH v4 5/6] KVM: Rename and move CPUHP_AP_KVM_STARTING to ONLINE section
Date:   Wed, 16 Feb 2022 11:15:20 +0800
Message-Id: <20220216031528.92558-6-chao.gao@intel.com>
In-Reply-To: <20220216031528.92558-1-chao.gao@intel.com>
References: <20220216031528.92558-1-chao.gao@intel.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

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.

KVM's CPU hotplug callbacks are renamed as well.

Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Chao Gao <chao.gao@intel.com>
---
 include/linux/cpuhotplug.h |  2 +-
 virt/kvm/kvm_main.c        | 30 ++++++++++++++++++++++--------
 2 files changed, 23 insertions(+), 9 deletions(-)

diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 4345b8eafc03..2c88770d3681 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -182,7 +182,6 @@ 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,
@@ -197,6 +196,7 @@ 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 c7229f5c9f66..bd60f8278867 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -4853,13 +4853,27 @@ static void hardware_enable_nolock(void *caller_name)
 	}
 }
 
-static int kvm_starting_cpu(unsigned int cpu)
+static int kvm_online_cpu(unsigned int cpu)
 {
+	int ret = 0;
+
 	raw_spin_lock(&kvm_count_lock);
-	if (kvm_usage_count)
+	/*
+	 * Abort the CPU online process if hardware virtualization cannot
+	 * be enabled. Otherwise running VMs would encounter unrecoverable
+	 * errors when scheduled to this CPU.
+	 */
+	if (kvm_usage_count) {
+		WARN_ON_ONCE(atomic_read(&hardware_enable_failed));
+
 		hardware_enable_nolock((void *)__func__);
+		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)
@@ -4872,7 +4886,7 @@ 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)
@@ -5685,8 +5699,8 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
 			goto out_free_2;
 	}
 
-	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);
@@ -5749,7 +5763,7 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
 	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:
 	kvm_arch_hardware_unsetup();
 out_free_1:
@@ -5775,7 +5789,7 @@ 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_arch_hardware_unsetup();
 	kvm_arch_exit();
-- 
2.25.1