| 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: <adbeb3e7-0edd-502e-4d6b-a51350d596bf@redhat.com>
Date: Thu, 27 Jan 2022 15:47:03 +0100
From: Eric Auger <eauger@...hat.com>
To: Gavin Shan <gshan@...hat.com>, kvmarm@...ts.cs.columbia.edu
Cc: maz@...nel.org, linux-kernel@...r.kernel.org,
Jonathan.Cameron@...wei.com, pbonzini@...hat.com, will@...nel.org
Subject: Re: [PATCH v4 14/21] KVM: arm64: Support SDEI_EVENT_{COMPLETE,
COMPLETE_AND_RESUME} hypercall
Hi Gavin,
On 1/12/22 7:43 AM, Gavin Shan wrote:
> Hi Eric,
>
> On 11/10/21 6:58 PM, Eric Auger wrote:
>> On 8/15/21 2:13 AM, Gavin Shan wrote:
>>> This supports SDEI_EVENT_{COMPLETE, COMPLETE_AND_RESUME} hypercall.
>>> They are used by the guest to notify the completion of the SDEI
>>> event in the handler. The registers are changed according to the
>>> SDEI specification as below:
>>>
>>> * x0 - x17, PC and PState are restored to what values we had in
>>> the interrupted context.
>>>
>>> * If it's SDEI_EVENT_COMPLETE_AND_RESUME hypercall, IRQ exception
>>> is injected.
>>>
>>> Signed-off-by: Gavin Shan <gshan@...hat.com>
>>> ---
>>> arch/arm64/include/asm/kvm_emulate.h | 1 +
>>> arch/arm64/include/asm/kvm_host.h | 1 +
>>> arch/arm64/kvm/hyp/exception.c | 7 +++
>>> arch/arm64/kvm/inject_fault.c | 27 ++++++++++
>>> arch/arm64/kvm/sdei.c | 75 ++++++++++++++++++++++++++++
>>> 5 files changed, 111 insertions(+)
>>>
>>> diff --git a/arch/arm64/include/asm/kvm_emulate.h
>>> b/arch/arm64/include/asm/kvm_emulate.h
>>> index fd418955e31e..923b4d08ea9a 100644
>>> --- a/arch/arm64/include/asm/kvm_emulate.h
>>> +++ b/arch/arm64/include/asm/kvm_emulate.h
>>> @@ -37,6 +37,7 @@ bool kvm_condition_valid32(const struct kvm_vcpu
>>> *vcpu);
>>> void kvm_skip_instr32(struct kvm_vcpu *vcpu);
>>> void kvm_inject_undefined(struct kvm_vcpu *vcpu);
>>> +void kvm_inject_irq(struct kvm_vcpu *vcpu);
>>> void kvm_inject_vabt(struct kvm_vcpu *vcpu);
>>> void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr);
>>> void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr);
>>> diff --git a/arch/arm64/include/asm/kvm_host.h
>>> b/arch/arm64/include/asm/kvm_host.h
>>> index 46f363aa6524..1824f7e1f9ab 100644
>>> --- a/arch/arm64/include/asm/kvm_host.h
>>> +++ b/arch/arm64/include/asm/kvm_host.h
>>> @@ -437,6 +437,7 @@ struct kvm_vcpu_arch {
>>> #define KVM_ARM64_EXCEPT_AA32_UND (0 << 9)
>>> #define KVM_ARM64_EXCEPT_AA32_IABT (1 << 9)
>>> #define KVM_ARM64_EXCEPT_AA32_DABT (2 << 9)
>>> +#define KVM_ARM64_EXCEPT_AA32_IRQ (3 << 9)
>>> /* For AArch64: */
>>> #define KVM_ARM64_EXCEPT_AA64_ELx_SYNC (0 << 9)
>>> #define KVM_ARM64_EXCEPT_AA64_ELx_IRQ (1 << 9)
>>> diff --git a/arch/arm64/kvm/hyp/exception.c
>>> b/arch/arm64/kvm/hyp/exception.c
>>> index 0418399e0a20..ef458207d152 100644
>>> --- a/arch/arm64/kvm/hyp/exception.c
>>> +++ b/arch/arm64/kvm/hyp/exception.c
>>> @@ -310,6 +310,9 @@ static void kvm_inject_exception(struct kvm_vcpu
>>> *vcpu)
>>> case KVM_ARM64_EXCEPT_AA32_DABT:
>>> enter_exception32(vcpu, PSR_AA32_MODE_ABT, 16);
>>> break;
>>> + case KVM_ARM64_EXCEPT_AA32_IRQ:
>>> + enter_exception32(vcpu, PSR_AA32_MODE_IRQ, 4);
>>> + break;
>>> default:
>>> /* Err... */
>>> break;
>>> @@ -320,6 +323,10 @@ static void kvm_inject_exception(struct kvm_vcpu
>>> *vcpu)
>>> KVM_ARM64_EXCEPT_AA64_EL1):
>>> enter_exception64(vcpu, PSR_MODE_EL1h, except_type_sync);
>>> break;
>>> + case (KVM_ARM64_EXCEPT_AA64_ELx_IRQ |
>>> + KVM_ARM64_EXCEPT_AA64_EL1):
>>> + enter_exception64(vcpu, PSR_MODE_EL1h, except_type_irq);
>>> + break;
>>> default:
>>> /*
>>> * Only EL1_SYNC makes sense so far, EL2_{SYNC,IRQ}
>>> diff --git a/arch/arm64/kvm/inject_fault.c
>>> b/arch/arm64/kvm/inject_fault.c
>>> index b47df73e98d7..3a8c55867d2f 100644
>>> --- a/arch/arm64/kvm/inject_fault.c
>>> +++ b/arch/arm64/kvm/inject_fault.c
>>> @@ -66,6 +66,13 @@ static void inject_undef64(struct kvm_vcpu *vcpu)
>>> vcpu_write_sys_reg(vcpu, esr, ESR_EL1);
>>> }
>>> +static void inject_irq64(struct kvm_vcpu *vcpu)
>>> +{
>>> + vcpu->arch.flags |= (KVM_ARM64_EXCEPT_AA64_EL1 |
>>> + KVM_ARM64_EXCEPT_AA64_ELx_IRQ |
>>> + KVM_ARM64_PENDING_EXCEPTION);
>>> +}
>>> +
>>> #define DFSR_FSC_EXTABT_LPAE 0x10
>>> #define DFSR_FSC_EXTABT_nLPAE 0x08
>>> #define DFSR_LPAE BIT(9)
>>> @@ -77,6 +84,12 @@ static void inject_undef32(struct kvm_vcpu *vcpu)
>>> KVM_ARM64_PENDING_EXCEPTION);
>>> }
>>> +static void inject_irq32(struct kvm_vcpu *vcpu)
>>> +{
>>> + vcpu->arch.flags |= (KVM_ARM64_EXCEPT_AA32_IRQ |
>>> + KVM_ARM64_PENDING_EXCEPTION);
>>> +}
>>> +
>>> /*
>>> * Modelled after TakeDataAbortException() and
>>> TakePrefetchAbortException
>>> * pseudocode.
>>> @@ -160,6 +173,20 @@ void kvm_inject_undefined(struct kvm_vcpu *vcpu)
>>> inject_undef64(vcpu);
>>> }
>>> +/**
>>> + * kvm_inject_irq - inject an IRQ into the guest
>>> + *
>>> + * It is assumed that this code is called from the VCPU thread and
>>> that the
>>> + * VCPU therefore is not currently executing guest code.
>>> + */
>>> +void kvm_inject_irq(struct kvm_vcpu *vcpu)
>>> +{
>>> + if (vcpu_el1_is_32bit(vcpu))
>>> + inject_irq32(vcpu);
>>> + else
>>> + inject_irq64(vcpu);
>>> +}
>>> +
>>> void kvm_set_sei_esr(struct kvm_vcpu *vcpu, u64 esr)
>>> {
>>> vcpu_set_vsesr(vcpu, esr & ESR_ELx_ISS_MASK);
>>> diff --git a/arch/arm64/kvm/sdei.c b/arch/arm64/kvm/sdei.c
>>> index b5d6d1ed3858..1e8e213c9d70 100644
>>> --- a/arch/arm64/kvm/sdei.c
>>> +++ b/arch/arm64/kvm/sdei.c
>>> @@ -308,6 +308,75 @@ static unsigned long
>>> kvm_sdei_hypercall_context(struct kvm_vcpu *vcpu)
>>> return ret;
>>> }
>>> +static unsigned long kvm_sdei_hypercall_complete(struct kvm_vcpu
>>> *vcpu,
>>> + bool resume)
>>> +{
>>> + struct kvm *kvm = vcpu->kvm;
>>> + struct kvm_sdei_kvm *ksdei = kvm->arch.sdei;
>>> + struct kvm_sdei_vcpu *vsdei = vcpu->arch.sdei;
>>> + struct kvm_sdei_kvm_event *kske = NULL;
>>> + struct kvm_sdei_vcpu_event *ksve = NULL;
>>> + struct kvm_sdei_vcpu_regs *regs;
>>> + unsigned long ret = SDEI_SUCCESS;
>> for the RESUME you never seem to read resume_addr arg? How does it work?
>> I don't get the irq injection path. Please could you explain?
>
> The guest kernel uses COMPLETE and COMPLETE_AND_RESUME hypercalls to
> notify the
> SDEI event has been acknoledged by it. The difference between them is
> COMPLETE_AND_RESUME
> fires the pending interrupts, but COMPLETE doesn't.
so resume_addr never is used, right?
>
>>> + int index;
>>> +
>>> + /* Sanity check */
>>> + if (!(ksdei && vsdei)) {
>>> + ret = SDEI_NOT_SUPPORTED;
>>> + goto out;
>>> + }
>>> +
>>> + spin_lock(&vsdei->lock);
>>> + if (vsdei->critical_event) {
>>> + ksve = vsdei->critical_event;
>>> + regs = &vsdei->state.critical_regs;
>>> + vsdei->critical_event = NULL;
>>> + vsdei->state.critical_num = KVM_SDEI_INVALID_NUM;
>>> + } else if (vsdei->normal_event) {
>>> + ksve = vsdei->normal_event;
>>> + regs = &vsdei->state.normal_regs;
>>> + vsdei->normal_event = NULL;
>>> + vsdei->state.normal_num = KVM_SDEI_INVALID_NUM;
>>> + } else {
>>> + ret = SDEI_DENIED;
>>> + goto unlock;
>>> + }
>>> +
>>> + /* Restore registers: x0 -> x17, PC, PState */
>>> + for (index = 0; index < ARRAY_SIZE(regs->regs); index++)
>>> + vcpu_set_reg(vcpu, index, regs->regs[index]);
>>> +
>>> + *vcpu_cpsr(vcpu) = regs->pstate;
>>> + *vcpu_pc(vcpu) = regs->pc;
>>> +
>>> + /* Inject interrupt if needed */
>>> + if (resume)
>>> + kvm_inject_irq(vcpu);
>>> +
>>> + /*
>>> + * Update state. We needn't take lock in order to update the KVM
>>> + * event state as it's not destroyed because of the reference
>>> + * count.
>>> + */
>>> + kske = ksve->kske;
>>> + ksve->state.refcount--;
>>> + kske->state.refcount--;
>> why double --?
>
> On each SDEI event is queued for delivery, both reference count are
> increased. I guess
> it's a bit confusing. I will change in next revision:
>
> ksve->state.refcount: Increased on each SDEI event is queued for delivered
> kske->state.refcount: Increased on each @ksve is created
>
>
>>> + if (!ksve->state.refcount) {
>> why not using a struct kref directly?
>
> The reason is kref isn't friendly to userspace. This field (@refcount)
> needs to be
> migrated :)
I will see with next version migration doc
Thanks
Eric
>
>>> + list_del(&ksve->link);
>>> + kfree(ksve);
>>> + }
>>> +
>>> + /* Make another request if there is pending event */
>>> + if (!(list_empty(&vsdei->critical_events) &&
>>> + list_empty(&vsdei->normal_events)))
>>> + kvm_make_request(KVM_REQ_SDEI, vcpu);
>>> +
>>> +unlock:
>>> + spin_unlock(&vsdei->lock);
>>> +out:
>>> + return ret;
>>> +}
>>> +
>>> static unsigned long kvm_sdei_hypercall_unregister(struct kvm_vcpu
>>> *vcpu)
>>> {
>>> struct kvm *kvm = vcpu->kvm;
>>> @@ -628,7 +697,13 @@ int kvm_sdei_hypercall(struct kvm_vcpu *vcpu)
>>> ret = kvm_sdei_hypercall_context(vcpu);
>>> break;
>>> case SDEI_1_0_FN_SDEI_EVENT_COMPLETE:
>>> + has_result = false;
>>> + ret = kvm_sdei_hypercall_complete(vcpu, false);
>>> + break;
>>> case SDEI_1_0_FN_SDEI_EVENT_COMPLETE_AND_RESUME:
>>> + has_result = false;
>>> + ret = kvm_sdei_hypercall_complete(vcpu, true);
>>> + break;
>>> case SDEI_1_0_FN_SDEI_EVENT_UNREGISTER:
>>> ret = kvm_sdei_hypercall_unregister(vcpu);
>>> break;
>>>
>
> Thanks,
> Gavin
>
Powered by blists - more mailing lists