linux-kernel - Re: [PATCH v3 4/5] KVM: Rename and move CPUHP_AP_KVM

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <YgQdMRug21MJ926L@google.com>
Date:   Wed, 9 Feb 2022 19:59:45 +0000
From:   Sean Christopherson <seanjc@...gle.com>
To:     Chao Gao <chao.gao@...el.com>
Cc:     kvm@...r.kernel.org, pbonzini@...hat.com, kevin.tian@...el.com,
        tglx@...utronix.de, John Garry <john.garry@...wei.com>,
        Will Deacon <will@...nel.org>, Qi Liu <liuqi115@...wei.com>,
        Thomas Richter <tmricht@...ux.ibm.com>,
        Shaokun Zhang <zhangshaokun@...ilicon.com>,
        Hector Martin <marcan@...can.st>,
        Huang Ying <ying.huang@...el.com>,
        linux-kernel@...r.kernel.org, Marc Zyngier <maz@...nel.org>
Subject: Re: [PATCH v3 4/5] KVM: Rename and move CPUHP_AP_KVM_STARTING to
 ONLINE section

+Marc

On Wed, Feb 09, 2022, Chao Gao wrote:
> 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@...utronix.de>
> Signed-off-by: Chao Gao <chao.gao@...el.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 773c83730906..14d354c8ce35 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,
>  	CPUHP_AP_KVM_ARM_VGIC_INIT_STARTING,
>  	CPUHP_AP_KVM_ARM_VGIC_STARTING,
>  	CPUHP_AP_KVM_ARM_TIMER_STARTING,

This probably needs an ack from Marc.  IIUC, it changes the ordering between generic
KVM enabling hardware and KVM ARM doing its vGIC and timer stuff.

> @@ -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 23481fd746aa..f60724736cb1 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)
> @@ -5641,8 +5655,8 @@ 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);
> @@ -5705,7 +5719,7 @@ 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:
> @@ -5731,7 +5745,7 @@ 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
>