If a KVM guest is reset while running a nested guest, free_nested will
disable the shadow VMCS execution control in the vmcs01. However,
on the next KVM_RUN vmx_vcpu_run would nevertheless try to sync
the VMCS12 to the shadow VMCS which has since been freed.
This causes a vmptrld of a NULL pointer on my machime, but Jan reports
the host to hang altogether. Let's see how much this trivial patch fixes.
Reported-by: Jan Kiszka <[email protected]>
Cc: Liran Alon <[email protected]>
Cc: [email protected]
Signed-off-by: Paolo Bonzini <[email protected]>
---
arch/x86/kvm/vmx/nested.c | 8 +++++++-
1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 4f23e34f628b..0f1378789bd0 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -194,6 +194,7 @@ static void vmx_disable_shadow_vmcs(struct vcpu_vmx *vmx)
{
secondary_exec_controls_clearbit(vmx, SECONDARY_EXEC_SHADOW_VMCS);
vmcs_write64(VMCS_LINK_POINTER, -1ull);
+ vmx->nested.need_vmcs12_to_shadow_sync = false;
}
static inline void nested_release_evmcs(struct kvm_vcpu *vcpu)
@@ -1341,6 +1342,9 @@ static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx)
unsigned long val;
int i;
+ if (WARN_ON(!shadow_vmcs))
+ return;
+
preempt_disable();
vmcs_load(shadow_vmcs);
@@ -1373,6 +1377,9 @@ static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx)
unsigned long val;
int i, q;
+ if (WARN_ON(!shadow_vmcs))
+ return;
+
vmcs_load(shadow_vmcs);
for (q = 0; q < ARRAY_SIZE(fields); q++) {
@@ -4436,7 +4443,6 @@ static inline void nested_release_vmcs12(struct kvm_vcpu *vcpu)
/* copy to memory all shadowed fields in case
they were modified */
copy_shadow_to_vmcs12(vmx);
- vmx->nested.need_vmcs12_to_shadow_sync = false;
vmx_disable_shadow_vmcs(vmx);
}
vmx->nested.posted_intr_nv = -1;
--
1.8.3.1
> On 20 Jul 2019, at 0:39, Paolo Bonzini <[email protected]> wrote:
>
> If a KVM guest is reset while running a nested guest, free_nested will
> disable the shadow VMCS execution control in the vmcs01. However,
> on the next KVM_RUN vmx_vcpu_run would nevertheless try to sync
> the VMCS12 to the shadow VMCS which has since been freed.
>
> This causes a vmptrld of a NULL pointer on my machime, but Jan reports
> the host to hang altogether. Let's see how much this trivial patch fixes.
>
> Reported-by: Jan Kiszka <[email protected]>
> Cc: Liran Alon <[email protected]>
> Cc: [email protected]
> Signed-off-by: Paolo Bonzini <[email protected]>
1) Are we sure we prefer WARN_ON() instead of WARN_ON_ONCE()?
2) Should we also check for WARN_ON(!vmcs12)? As free_nested() also kfree(vmx->nested.cached_vmcs12).
In fact, because free_nested() don’t put NULL in cached_vmcs12 after kfree() it, I wonder if we shouldn’t create a separate patch that does:
(a) Modify free_nested() to put NULL in cached_vmcs12 after kfree().
(b) Put BUG_ON(!cached_vmcs12) in get_vmcs12() before returning value.
-Liran
> ---
> arch/x86/kvm/vmx/nested.c | 8 +++++++-
> 1 file changed, 7 insertions(+), 1 deletion(-)
>
> diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
> index 4f23e34f628b..0f1378789bd0 100644
> --- a/arch/x86/kvm/vmx/nested.c
> +++ b/arch/x86/kvm/vmx/nested.c
> @@ -194,6 +194,7 @@ static void vmx_disable_shadow_vmcs(struct vcpu_vmx *vmx)
> {
> secondary_exec_controls_clearbit(vmx, SECONDARY_EXEC_SHADOW_VMCS);
> vmcs_write64(VMCS_LINK_POINTER, -1ull);
> + vmx->nested.need_vmcs12_to_shadow_sync = false;
> }
>
> static inline void nested_release_evmcs(struct kvm_vcpu *vcpu)
> @@ -1341,6 +1342,9 @@ static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx)
> unsigned long val;
> int i;
>
> + if (WARN_ON(!shadow_vmcs))
> + return;
> +
> preempt_disable();
>
> vmcs_load(shadow_vmcs);
> @@ -1373,6 +1377,9 @@ static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx)
> unsigned long val;
> int i, q;
>
> + if (WARN_ON(!shadow_vmcs))
> + return;
> +
> vmcs_load(shadow_vmcs);
>
> for (q = 0; q < ARRAY_SIZE(fields); q++) {
> @@ -4436,7 +4443,6 @@ static inline void nested_release_vmcs12(struct kvm_vcpu *vcpu)
> /* copy to memory all shadowed fields in case
> they were modified */
> copy_shadow_to_vmcs12(vmx);
> - vmx->nested.need_vmcs12_to_shadow_sync = false;
> vmx_disable_shadow_vmcs(vmx);
> }
> vmx->nested.posted_intr_nv = -1;
> --
> 1.8.3.1
>
On 20/07/19 00:06, Liran Alon wrote:
>
>
>> On 20 Jul 2019, at 0:39, Paolo Bonzini <[email protected]> wrote:
>>
>> If a KVM guest is reset while running a nested guest, free_nested will
>> disable the shadow VMCS execution control in the vmcs01. However,
>> on the next KVM_RUN vmx_vcpu_run would nevertheless try to sync
>> the VMCS12 to the shadow VMCS which has since been freed.
>>
>> This causes a vmptrld of a NULL pointer on my machime, but Jan reports
>> the host to hang altogether. Let's see how much this trivial patch fixes.
>>
>> Reported-by: Jan Kiszka <[email protected]>
>> Cc: Liran Alon <[email protected]>
>> Cc: [email protected]
>> Signed-off-by: Paolo Bonzini <[email protected]>
>
> 1) Are we sure we prefer WARN_ON() instead of WARN_ON_ONCE()?
I don't think you can get it to be called in a loop, the calls are
generally guarded by ifs.
> 2) Should we also check for WARN_ON(!vmcs12)? As free_nested() also kfree(vmx->nested.cached_vmcs12).
Well, it doesn't NULL it but it does NULL shadow_vmcs so the extra
warning wouldn't add much.
> In fact, because free_nested() don’t put NULL in cached_vmcs12 after kfree() it, I wonder if we shouldn’t create a separate patch that does:
> (a) Modify free_nested() to put NULL in cached_vmcs12 after kfree().
> (b) Put BUG_ON(!cached_vmcs12) in get_vmcs12() before returning value.
This is useful but a separate improvement (and not a bugfix, I want this
patch to be small so it applies to older trees).
Paolo
> -Liran
>
>> ---
>> arch/x86/kvm/vmx/nested.c | 8 +++++++-
>> 1 file changed, 7 insertions(+), 1 deletion(-)
>>
>> diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
>> index 4f23e34f628b..0f1378789bd0 100644
>> --- a/arch/x86/kvm/vmx/nested.c
>> +++ b/arch/x86/kvm/vmx/nested.c
>> @@ -194,6 +194,7 @@ static void vmx_disable_shadow_vmcs(struct vcpu_vmx *vmx)
>> {
>> secondary_exec_controls_clearbit(vmx, SECONDARY_EXEC_SHADOW_VMCS);
>> vmcs_write64(VMCS_LINK_POINTER, -1ull);
>> + vmx->nested.need_vmcs12_to_shadow_sync = false;
>> }
>>
>> static inline void nested_release_evmcs(struct kvm_vcpu *vcpu)
>> @@ -1341,6 +1342,9 @@ static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx)
>> unsigned long val;
>> int i;
>>
>> + if (WARN_ON(!shadow_vmcs))
>> + return;
>> +
>> preempt_disable();
>>
>> vmcs_load(shadow_vmcs);
>> @@ -1373,6 +1377,9 @@ static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx)
>> unsigned long val;
>> int i, q;
>>
>> + if (WARN_ON(!shadow_vmcs))
>> + return;
>> +
>> vmcs_load(shadow_vmcs);
>>
>> for (q = 0; q < ARRAY_SIZE(fields); q++) {
>> @@ -4436,7 +4443,6 @@ static inline void nested_release_vmcs12(struct kvm_vcpu *vcpu)
>> /* copy to memory all shadowed fields in case
>> they were modified */
>> copy_shadow_to_vmcs12(vmx);
>> - vmx->nested.need_vmcs12_to_shadow_sync = false;
>> vmx_disable_shadow_vmcs(vmx);
>> }
>> vmx->nested.posted_intr_nv = -1;
>> --
>> 1.8.3.1
>>
>
> On 20 Jul 2019, at 1:21, Paolo Bonzini <[email protected]> wrote:
>
> On 20/07/19 00:06, Liran Alon wrote:
>>
>>
>>> On 20 Jul 2019, at 0:39, Paolo Bonzini <[email protected]> wrote:
>>>
>>> If a KVM guest is reset while running a nested guest, free_nested will
>>> disable the shadow VMCS execution control in the vmcs01. However,
>>> on the next KVM_RUN vmx_vcpu_run would nevertheless try to sync
>>> the VMCS12 to the shadow VMCS which has since been freed.
>>>
>>> This causes a vmptrld of a NULL pointer on my machime, but Jan reports
>>> the host to hang altogether. Let's see how much this trivial patch fixes.
>>>
>>> Reported-by: Jan Kiszka <[email protected]>
>>> Cc: Liran Alon <[email protected]>
>>> Cc: [email protected]
>>> Signed-off-by: Paolo Bonzini <[email protected]>
>>
>> 1) Are we sure we prefer WARN_ON() instead of WARN_ON_ONCE()?
>
> I don't think you can get it to be called in a loop, the calls are
> generally guarded by ifs.
>
>> 2) Should we also check for WARN_ON(!vmcs12)? As free_nested() also kfree(vmx->nested.cached_vmcs12).
>
> Well, it doesn't NULL it but it does NULL shadow_vmcs so the extra
> warning wouldn't add much.
>
>> In fact, because free_nested() don’t put NULL in cached_vmcs12 after kfree() it, I wonder if we shouldn’t create a separate patch that does:
>> (a) Modify free_nested() to put NULL in cached_vmcs12 after kfree().
>> (b) Put BUG_ON(!cached_vmcs12) in get_vmcs12() before returning value.
>
> This is useful but a separate improvement (and not a bugfix, I want this
> patch to be small so it applies to older trees).
>
> Paolo
ACK on all the above. :)
Reviewed-by: Liran Alon <[email protected]>
-Liran
>
>> -Liran
>>
>>> ---
>>> arch/x86/kvm/vmx/nested.c | 8 +++++++-
>>> 1 file changed, 7 insertions(+), 1 deletion(-)
>>>
>>> diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
>>> index 4f23e34f628b..0f1378789bd0 100644
>>> --- a/arch/x86/kvm/vmx/nested.c
>>> +++ b/arch/x86/kvm/vmx/nested.c
>>> @@ -194,6 +194,7 @@ static void vmx_disable_shadow_vmcs(struct vcpu_vmx *vmx)
>>> {
>>> secondary_exec_controls_clearbit(vmx, SECONDARY_EXEC_SHADOW_VMCS);
>>> vmcs_write64(VMCS_LINK_POINTER, -1ull);
>>> + vmx->nested.need_vmcs12_to_shadow_sync = false;
>>> }
>>>
>>> static inline void nested_release_evmcs(struct kvm_vcpu *vcpu)
>>> @@ -1341,6 +1342,9 @@ static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx)
>>> unsigned long val;
>>> int i;
>>>
>>> + if (WARN_ON(!shadow_vmcs))
>>> + return;
>>> +
>>> preempt_disable();
>>>
>>> vmcs_load(shadow_vmcs);
>>> @@ -1373,6 +1377,9 @@ static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx)
>>> unsigned long val;
>>> int i, q;
>>>
>>> + if (WARN_ON(!shadow_vmcs))
>>> + return;
>>> +
>>> vmcs_load(shadow_vmcs);
>>>
>>> for (q = 0; q < ARRAY_SIZE(fields); q++) {
>>> @@ -4436,7 +4443,6 @@ static inline void nested_release_vmcs12(struct kvm_vcpu *vcpu)
>>> /* copy to memory all shadowed fields in case
>>> they were modified */
>>> copy_shadow_to_vmcs12(vmx);
>>> - vmx->nested.need_vmcs12_to_shadow_sync = false;
>>> vmx_disable_shadow_vmcs(vmx);
>>> }
>>> vmx->nested.posted_intr_nv = -1;
>>> --
>>> 1.8.3.1
>>>
>>
>