Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   isaku.yamahata@intel.com
To:     linux-kernel@vger.kernel.org, kvm@vger.kernel.org,
        Paolo Bonzini <pbonzini@redhat.com>,
        Sean Christopherson <seanjc@google.com>,
        Thomas Gleixner <tglx@linutronix.de>,
        Marc Zyngier <maz@kernel.org>, Will Deacon <will@kernel.org>
Cc:     isaku.yamahata@intel.com, isaku.yamahata@gmail.com,
        Kai Huang <kai.huang@intel.com>, Chao Gao <chao.gao@intel.com>,
        Atish Patra <atishp@atishpatra.org>,
        Shaokun Zhang <zhangshaokun@hisilicon.com>,
        Daniel Lezcano <daniel.lezcano@linaro.org>,
        Huang Ying <ying.huang@intel.com>,
        Huacai Chen <chenhuacai@kernel.org>,
        Dave Hansen <dave.hansen@linux.intel.com>,
        Borislav Petkov <bp@alien8.de>, Yuan Yao <yuan.yao@intel.com>
Subject: [PATCH v5 07/30] KVM: Rename and move CPUHP_AP_KVM_STARTING to ONLINE section
Date:   Thu, 22 Sep 2022 11:20:36 -0700
Message-Id: <ea1a0d1cd293cf6da30ee85c6341ca20d0cafe25.1663869838.git.isaku.yamahata@intel.com>
In-Reply-To: <cover.1663869838.git.isaku.yamahata@intel.com>
References: <cover.1663869838.git.isaku.yamahata@intel.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: Chao Gao <chao.gao@intel.com>

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>
Link: https://lore.kernel.org/r/20220216031528.92558-6-chao.gao@intel.com
Reviewed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
Reviewed-by: Yuan Yao <yuan.yao@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 7337414e4947..de45be38dd27 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -185,7 +185,6 @@ 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,
@@ -200,6 +199,7 @@ 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 4f19c47aab1c..1bb7038e1ecf 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -5011,13 +5011,27 @@ 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;
+
 	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(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)
@@ -5030,7 +5044,7 @@ 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)
@@ -5841,8 +5855,8 @@ 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);
@@ -5903,7 +5917,7 @@ 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:
@@ -5929,7 +5943,7 @@ 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