| 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
| ||
|
Message-ID: <9e062d47-ef96-4028-38a7-ffb54a451643@linux.ibm.com>
Date: Wed, 8 Sep 2021 15:09:48 +0200
From: Pierre Morel <pmorel@...ux.ibm.com>
To: Christian Borntraeger <borntraeger@...ibm.com>,
David Hildenbrand <david@...hat.com>, kvm@...r.kernel.org
Cc: linux-s390@...r.kernel.org, linux-kernel@...r.kernel.org,
frankja@...ux.ibm.com, cohuck@...hat.com, thuth@...hat.com,
imbrenda@...ux.ibm.com, hca@...ux.ibm.com, gor@...ux.ibm.com
Subject: Re: [PATCH v3 2/3] s390x: KVM: Implementation of Multiprocessor
Topology-Change-Report
On 9/8/21 9:07 AM, Christian Borntraeger wrote:
>
>
> On 07.09.21 14:28, Pierre Morel wrote:
>>
>>
>> On 9/6/21 8:37 PM, David Hildenbrand wrote:
>>> On 03.08.21 10:26, Pierre Morel wrote:
>>>> We let the userland hypervisor know if the machine support the CPU
>>>> topology facility using a new KVM capability:
>>>> KVM_CAP_S390_CPU_TOPOLOGY.
>>>>
>>>> The PTF instruction will report a topology change if there is any
>>>> change
>>>> with a previous STSI_15_2 SYSIB.
>>>> Changes inside a STSI_15_2 SYSIB occur if CPU bits are set or clear
>>>> inside the CPU Topology List Entry CPU mask field, which happens with
>>>> changes in CPU polarization, dedication, CPU types and adding or
>>>> removing CPUs in a socket.
>>>>
>>>> The reporting to the guest is done using the Multiprocessor
>>>> Topology-Change-Report (MTCR) bit of the utility entry of the guest's
>>>> SCA which will be cleared during the interpretation of PTF.
>>>>
>>>> To check if the topology has been modified we use a new field of the
>>>> arch vCPU to save the previous real CPU ID at the end of a schedule
>>>> and verify on next schedule that the CPU used is in the same socket.
>>>>
>>>> We deliberatly ignore:
>>>> - polarization: only horizontal polarization is currently used in
>>>> linux.
>>>> - CPU Type: only IFL Type are supported in Linux
>>>> - Dedication: we consider that only a complete dedicated CPU stack can
>>>> take benefit of the CPU Topology.
>>>>
>>>> Signed-off-by: Pierre Morel <pmorel@...ux.ibm.com>
>>>
>>>
>>>> @@ -228,7 +232,7 @@ struct kvm_s390_sie_block {
>>>> __u8 icptcode; /* 0x0050 */
>>>> __u8 icptstatus; /* 0x0051 */
>>>> __u16 ihcpu; /* 0x0052 */
>>>> - __u8 reserved54; /* 0x0054 */
>>>> + __u8 mtcr; /* 0x0054 */
>>>> #define IICTL_CODE_NONE 0x00
>>>> #define IICTL_CODE_MCHK 0x01
>>>> #define IICTL_CODE_EXT 0x02
>>>> @@ -246,6 +250,7 @@ struct kvm_s390_sie_block {
>>>> #define ECB_TE 0x10
>>>> #define ECB_SRSI 0x04
>>>> #define ECB_HOSTPROTINT 0x02
>>>> +#define ECB_PTF 0x01
>>>
>>> From below I understand, that ECB_PTF can be used with stfl(11) in
>>> the hypervisor.
>>>
>>> What is to happen if the hypervisor doesn't support stfl(11) and we
>>> consequently cannot use ECB_PTF? Will QEMU be able to emulate PTF fully?
>>>
>>>
>>>> __u8 ecb; /* 0x0061 */
>>>> #define ECB2_CMMA 0x80
>>>> #define ECB2_IEP 0x20
>>>> @@ -747,6 +752,7 @@ struct kvm_vcpu_arch {
>>>> bool skey_enabled;
>>>> struct kvm_s390_pv_vcpu pv;
>>>> union diag318_info diag318_info;
>>>> + int prev_cpu;
>>>> };
>>>> struct kvm_vm_stat {
>>>> diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
>>>> index b655a7d82bf0..ff6d8a2b511c 100644
>>>> --- a/arch/s390/kvm/kvm-s390.c
>>>> +++ b/arch/s390/kvm/kvm-s390.c
>>>> @@ -568,6 +568,7 @@ int kvm_vm_ioctl_check_extension(struct kvm
>>>> *kvm, long ext)
>>>> case KVM_CAP_S390_VCPU_RESETS:
>>>> case KVM_CAP_SET_GUEST_DEBUG:
>>>> case KVM_CAP_S390_DIAG318:
>>>> + case KVM_CAP_S390_CPU_TOPOLOGY:
>>>
>>> I would have expected instead
>>>
>>> r = test_facility(11);
>>> break
>>>
>>> ...
>>>
>>>> r = 1;
>>>> break;
>>>> case KVM_CAP_SET_GUEST_DEBUG2:
>>>> @@ -819,6 +820,23 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
>>>> struct kvm_enable_cap *cap)
>>>> icpt_operexc_on_all_vcpus(kvm);
>>>> r = 0;
>>>> break;
>>>> + case KVM_CAP_S390_CPU_TOPOLOGY:
>>>> + mutex_lock(&kvm->lock);
>>>> + if (kvm->created_vcpus) {
>>>> + r = -EBUSY;
>>>> + } else {
>>>
>>> ...
>>> } else if (test_facility(11)) {
>>> set_kvm_facility(kvm->arch.model.fac_mask, 11);
>>> set_kvm_facility(kvm->arch.model.fac_list, 11);
>>> r = 0;
>>> } else {
>>> r = -EINVAL;
>>> }
>>>
>>> similar to how we handle KVM_CAP_S390_VECTOR_REGISTERS.
>>>
>>> But I assume you want to be able to support hosts without ECB_PTF,
>>> correct?
>>>
>>>
>>>> + set_kvm_facility(kvm->arch.model.fac_mask, 11);
>>>> + set_kvm_facility(kvm->arch.model.fac_list, 11);
>>>> + r = 0;
>>>> + }
>>>> + mutex_unlock(&kvm->lock);
>>>> + VM_EVENT(kvm, 3, "ENABLE: CPU TOPOLOGY %s",
>>>> + r ? "(not available)" : "(success)");
>>>> + break;
>>>> +
>>>> + r = -EINVAL;
>>>> + break;
>>>
>>> ^ dead code
>>>
>>> [...]
>>>
>>>> }
>>>> void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
>>>> {
>>>> + vcpu->arch.prev_cpu = vcpu->cpu;
>>>> vcpu->cpu = -1;
>>>> if (vcpu->arch.cputm_enabled && !is_vcpu_idle(vcpu))
>>>> __stop_cpu_timer_accounting(vcpu);
>>>> @@ -3198,6 +3239,11 @@ static int kvm_s390_vcpu_setup(struct
>>>> kvm_vcpu *vcpu)
>>>> vcpu->arch.sie_block->ecb |= ECB_HOSTPROTINT;
>>>> if (test_kvm_facility(vcpu->kvm, 9))
>>>> vcpu->arch.sie_block->ecb |= ECB_SRSI;
>>>> +
>>>> + /* PTF needs both host and guest facilities to enable
>>>> interpretation */
>>>> + if (test_kvm_facility(vcpu->kvm, 11) && test_facility(11))
>>>> + vcpu->arch.sie_block->ecb |= ECB_PTF;
>>>
>>> Here you say we need both ...
>>>
>>>> +
>>>> if (test_kvm_facility(vcpu->kvm, 73))
>>>> vcpu->arch.sie_block->ecb |= ECB_TE;
>>>> diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
>>>> index 4002a24bc43a..50d67190bf65 100644
>>>> --- a/arch/s390/kvm/vsie.c
>>>> +++ b/arch/s390/kvm/vsie.c
>>>> @@ -503,6 +503,9 @@ static int shadow_scb(struct kvm_vcpu *vcpu,
>>>> struct vsie_page *vsie_page)
>>>> /* Host-protection-interruption introduced with ESOP */
>>>> if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_ESOP))
>>>> scb_s->ecb |= scb_o->ecb & ECB_HOSTPROTINT;
>>>> + /* CPU Topology */
>>>> + if (test_kvm_facility(vcpu->kvm, 11))
>>>> + scb_s->ecb |= scb_o->ecb & ECB_PTF;
>>>
>>> but here you don't check?
>>>
>>>> /* transactional execution */
>>>> if (test_kvm_facility(vcpu->kvm, 73) && wants_tx) {
>>>> /* remap the prefix is tx is toggled on */
>>>> diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
>>>> index d9e4aabcb31a..081ce0cd44b9 100644
>>>> --- a/include/uapi/linux/kvm.h
>>>> +++ b/include/uapi/linux/kvm.h
>>>> @@ -1112,6 +1112,7 @@ struct kvm_ppc_resize_hpt {
>>>> #define KVM_CAP_BINARY_STATS_FD 203
>>>> #define KVM_CAP_EXIT_ON_EMULATION_FAILURE 204
>>>> #define KVM_CAP_ARM_MTE 205
>>>> +#define KVM_CAP_S390_CPU_TOPOLOGY 206
>>>
>>> We'll need a Documentation/virt/kvm/api.rst description.
>>>
>>> I'm not completely confident that the way we're handling the
>>> capability+facility is the right approach. It all feels a bit
>>> suboptimal.
>>>
>>> Except stfl(74) -- STHYI --, we never enable a facility via
>>> set_kvm_facility() that's not available in the host. And STHYI is
>>> special such that it is never implemented in hardware.
>>>
>>> I'll think about what might be cleaner once I get some more details
>>> about the interaction with stfl(11) in the hypervisor.
>>>
>>
>> OK, may be we do not need to handle the case stfl(11) is not present
>> in the host, these are pre GA10...
>
> What about VSIE? For all existing KVM guests, stfl11 is off.
In VSIE the patch activates stfl(11) only if the host has stfl(11).
I do not see any problem to activate the interpretation in VSIE with
ECB_PTF (ECB.7) when the host has stfl(11) and QEMU asks to enable it
for the guest using the CAPABILITY as it is done in this patch.
if any intermediary hypervizor decide to not advertize stfl(11) for the
guest like an old QEMU not having the CAPABILITY, or a QEMU with
ctop=off, KVM will not set ECB_PTF and the PTF instruction will trigger
a program check as before.
Is it OK or did I missed something?
--
Pierre Morel
IBM Lab Boeblingen
Powered by blists - more mailing lists