Re: [PATCH v3 1/8] KVM: Use dedicated mutex to protect kvm_usage_count to avoid deadlock

[Paolo Bonzini <pbonzini@redhat.com>]

On 6/8/24 02:06, Sean Christopherson wrote:
> Use a dedicated mutex to guard kvm_usage_count to fix a potential deadlock
> on x86 due to a chain of locks and SRCU synchronizations.  Translating the
> below lockdep splat, CPU1 #6 will wait on CPU0 #1, CPU0 #8 will wait on
> CPU2 #3, and CPU2 #7 will wait on CPU1 #4 (if there's a writer, due to the
> fairness of r/w semaphores).
> 
>      CPU0                     CPU1                     CPU2
> 1   lock(&kvm->slots_lock);
> 2                                                     lock(&vcpu->mutex);
> 3                                                     lock(&kvm->srcu);
> 4                            lock(cpu_hotplug_lock);
> 5                            lock(kvm_lock);
> 6                            lock(&kvm->slots_lock);
> 7                                                     lock(cpu_hotplug_lock);
> 8   sync(&kvm->srcu);
> 
> Note, there are likely more potential deadlocks in KVM x86, e.g. the same
> pattern of taking cpu_hotplug_lock outside of kvm_lock likely exists with
> __kvmclock_cpufreq_notifier()

Offhand I couldn't see any places where {,__}cpufreq_driver_target() is 
called within cpus_read_lock().  I didn't look too closely though.

> +``kvm_usage_count``
> +^^^^^^^^^^^^^^^^^^^

``kvm_usage_lock``

Paolo

> +
> +:Type:		mutex
> +:Arch:		any
> +:Protects:	- kvm_usage_count
>   		- hardware virtualization enable/disable
>   :Comment:	KVM also disables CPU hotplug via cpus_read_lock() during
>   		enable/disable.
> @@ -290,11 +296,12 @@ time it will be set using the Dirty tracking mechanism described above.
>   		wakeup.
>   
>   ``vendor_module_lock``
> -^^^^^^^^^^^^^^^^^^^^^^^^^^^^
> +^^^^^^^^^^^^^^^^^^^^^^
>   :Type:		mutex
>   :Arch:		x86
>   :Protects:	loading a vendor module (kvm_amd or kvm_intel)
> -:Comment:	Exists because using kvm_lock leads to deadlock.  cpu_hotplug_lock is
> -    taken outside of kvm_lock, e.g. in KVM's CPU online/offline callbacks, and
> -    many operations need to take cpu_hotplug_lock when loading a vendor module,
> -    e.g. updating static calls.
> +:Comment:	Exists because using kvm_lock leads to deadlock.  kvm_lock is taken
> +    in notifiers, e.g. __kvmclock_cpufreq_notifier(), that may be invoked while
> +    cpu_hotplug_lock is held, e.g. from cpufreq_boost_trigger_state(), and many
> +    operations need to take cpu_hotplug_lock when loading a vendor module, e.g.
> +    updating static calls.
> diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
> index 4965196cad58..d9b0579d3eea 100644
> --- a/virt/kvm/kvm_main.c
> +++ b/virt/kvm/kvm_main.c
> @@ -5499,6 +5499,7 @@ __visible bool kvm_rebooting;
>   EXPORT_SYMBOL_GPL(kvm_rebooting);
>   
>   static DEFINE_PER_CPU(bool, hardware_enabled);
> +static DEFINE_MUTEX(kvm_usage_lock);
>   static int kvm_usage_count;
>   
>   static int __hardware_enable_nolock(void)
> @@ -5531,10 +5532,10 @@ static int kvm_online_cpu(unsigned int cpu)
>   	 * be enabled. Otherwise running VMs would encounter unrecoverable
>   	 * errors when scheduled to this CPU.
>   	 */
> -	mutex_lock(&kvm_lock);
> +	mutex_lock(&kvm_usage_lock);
>   	if (kvm_usage_count)
>   		ret = __hardware_enable_nolock();
> -	mutex_unlock(&kvm_lock);
> +	mutex_unlock(&kvm_usage_lock);
>   	return ret;
>   }
>   
> @@ -5554,10 +5555,10 @@ static void hardware_disable_nolock(void *junk)
>   
>   static int kvm_offline_cpu(unsigned int cpu)
>   {
> -	mutex_lock(&kvm_lock);
> +	mutex_lock(&kvm_usage_lock);
>   	if (kvm_usage_count)
>   		hardware_disable_nolock(NULL);
> -	mutex_unlock(&kvm_lock);
> +	mutex_unlock(&kvm_usage_lock);
>   	return 0;
>   }
>   
> @@ -5573,9 +5574,9 @@ static void hardware_disable_all_nolock(void)
>   static void hardware_disable_all(void)
>   {
>   	cpus_read_lock();
> -	mutex_lock(&kvm_lock);
> +	mutex_lock(&kvm_usage_lock);
>   	hardware_disable_all_nolock();
> -	mutex_unlock(&kvm_lock);
> +	mutex_unlock(&kvm_usage_lock);
>   	cpus_read_unlock();
>   }
>   
> @@ -5606,7 +5607,7 @@ static int hardware_enable_all(void)
>   	 * enable hardware multiple times.
>   	 */
>   	cpus_read_lock();
> -	mutex_lock(&kvm_lock);
> +	mutex_lock(&kvm_usage_lock);
>   
>   	r = 0;
>   
> @@ -5620,7 +5621,7 @@ static int hardware_enable_all(void)
>   		}
>   	}
>   
> -	mutex_unlock(&kvm_lock);
> +	mutex_unlock(&kvm_usage_lock);
>   	cpus_read_unlock();
>   
>   	return r;
> @@ -5648,13 +5649,13 @@ static int kvm_suspend(void)
>   {
>   	/*
>   	 * Secondary CPUs and CPU hotplug are disabled across the suspend/resume
> -	 * callbacks, i.e. no need to acquire kvm_lock to ensure the usage count
> -	 * is stable.  Assert that kvm_lock is not held to ensure the system
> -	 * isn't suspended while KVM is enabling hardware.  Hardware enabling
> -	 * can be preempted, but the task cannot be frozen until it has dropped
> -	 * all locks (userspace tasks are frozen via a fake signal).
> +	 * callbacks, i.e. no need to acquire kvm_usage_lock to ensure the usage
> +	 * count is stable.  Assert that kvm_usage_lock is not held to ensure
> +	 * the system isn't suspended while KVM is enabling hardware.  Hardware
> +	 * enabling can be preempted, but the task cannot be frozen until it has
> +	 * dropped all locks (userspace tasks are frozen via a fake signal).
>   	 */
> -	lockdep_assert_not_held(&kvm_lock);
> +	lockdep_assert_not_held(&kvm_usage_lock);
>   	lockdep_assert_irqs_disabled();
>   
>   	if (kvm_usage_count)
> @@ -5664,7 +5665,7 @@ static int kvm_suspend(void)
>   
>   static void kvm_resume(void)
>   {
> -	lockdep_assert_not_held(&kvm_lock);
> +	lockdep_assert_not_held(&kvm_usage_lock);
>   	lockdep_assert_irqs_disabled();
>   
>   	if (kvm_usage_count)