| Message ID | 20241019172459.2241939-3-dwmw2@infradead.org (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | Add PSCI v1.3 SYSTEM_OFF2 support for hibernation | expand |
Hi David, > On 19 Oct 2024, at 17:15, David Woodhouse <dwmw2@infradead.org> wrote: > > From: David Woodhouse <dwmw@amazon.co.uk> > > The PSCI v1.3 specification adds support for a SYSTEM_OFF2 function > which is analogous to ACPI S4 state. This will allow hosting > environments to determine that a guest is hibernated rather than just > powered off, and ensure that they preserve the virtual environment > appropriately to allow the guest to resume safely (or bump the > hardware_signature in the FACS to trigger a clean reboot instead). > > This feature is safe to enable unconditionally (in a subsequent commit) > because it is exposed to userspace through the existing > KVM_SYSTEM_EVENT_SHUTDOWN event, just with an additional flag which > userspace can use to know that the instance intended hibernation instead > of a plain power-off. > > As with SYSTEM_RESET2, there is only one type available (in this case > HIBERNATE_OFF), and it is not explicitly reported to userspace through > the event; userspace can get it from the registers if it cares). > > Signed-off-by: David Woodhouse <dwmw@amazon.co.uk> > --- > Documentation/virt/kvm/api.rst | 11 ++++++++ > arch/arm64/include/uapi/asm/kvm.h | 6 +++++ > arch/arm64/kvm/psci.c | 44 +++++++++++++++++++++++++++++++ > 3 files changed, 61 insertions(+) > > diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst > index e32471977d0a..1ec076d806e6 100644 > --- a/Documentation/virt/kvm/api.rst > +++ b/Documentation/virt/kvm/api.rst > @@ -6855,6 +6855,10 @@ the first `ndata` items (possibly zero) of the data array are valid. > the guest issued a SYSTEM_RESET2 call according to v1.1 of the PSCI > specification. > > + - for arm64, data[0] is set to KVM_SYSTEM_EVENT_SHUTDOWN_FLAG_PSCI_OFF2 > + if the guest issued a SYSTEM_OFF2 call according to v1.3 of the PSCI > + specification. > + > - for RISC-V, data[0] is set to the value of the second argument of the > ``sbi_system_reset`` call. > > @@ -6888,6 +6892,13 @@ either: > - Deny the guest request to suspend the VM. See ARM DEN0022D.b 5.19.2 > "Caller responsibilities" for possible return values. > > +Hibernation using the PSCI SYSTEM_OFF2 call is enabled when PSCI v1.3 > +is enabled. If a guest invokes the PSCI SYSTEM_OFF2 function, KVM will > +exit to userspace with the KVM_SYSTEM_EVENT_SHUTDOWN event type and with > +data[0] set to KVM_SYSTEM_EVENT_SHUTDOWN_FLAG_PSCI_OFF2. The only > +supported hibernate type for the SYSTEM_OFF2 function is HIBERNATE_OFF > +0x0). I don’t think that ‘0x0’ adds something to what’s already explained before, IMO. > + > :: > > /* KVM_EXIT_IOAPIC_EOI */ > diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h > index 964df31da975..66736ff04011 100644 > --- a/arch/arm64/include/uapi/asm/kvm.h > +++ b/arch/arm64/include/uapi/asm/kvm.h > @@ -484,6 +484,12 @@ enum { > */ > #define KVM_SYSTEM_EVENT_RESET_FLAG_PSCI_RESET2 (1ULL << 0) > > +/* > + * Shutdown caused by a PSCI v1.3 SYSTEM_OFF2 call. > + * Valid only when the system event has a type of KVM_SYSTEM_EVENT_SHUTDOWN. > + */ > +#define KVM_SYSTEM_EVENT_SHUTDOWN_FLAG_PSCI_OFF2 (1ULL << 0) > + > /* run->fail_entry.hardware_entry_failure_reason codes. */ > #define KVM_EXIT_FAIL_ENTRY_CPU_UNSUPPORTED (1ULL << 0) > > diff --git a/arch/arm64/kvm/psci.c b/arch/arm64/kvm/psci.c > index 1f69b667332b..df834f2e928e 100644 > --- a/arch/arm64/kvm/psci.c > +++ b/arch/arm64/kvm/psci.c > @@ -194,6 +194,12 @@ static void kvm_psci_system_off(struct kvm_vcpu *vcpu) > kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_SHUTDOWN, 0); > } > > +static void kvm_psci_system_off2(struct kvm_vcpu *vcpu) > +{ > + kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_SHUTDOWN, > + KVM_SYSTEM_EVENT_SHUTDOWN_FLAG_PSCI_OFF2); > +} > + > static void kvm_psci_system_reset(struct kvm_vcpu *vcpu) > { > kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_RESET, 0); > @@ -358,6 +364,11 @@ static int kvm_psci_1_x_call(struct kvm_vcpu *vcpu, u32 minor) > if (minor >= 1) > val = 0; > break; > + case PSCI_1_3_FN_SYSTEM_OFF2: > + case PSCI_1_3_FN64_SYSTEM_OFF2: > + if (minor >= 3) > + val = PSCI_1_3_OFF_TYPE_HIBERNATE_OFF; > + break; > } > break; > case PSCI_1_0_FN_SYSTEM_SUSPEND: > @@ -392,6 +403,39 @@ static int kvm_psci_1_x_call(struct kvm_vcpu *vcpu, u32 minor) > break; > } > break; > + case PSCI_1_3_FN_SYSTEM_OFF2: > + kvm_psci_narrow_to_32bit(vcpu); > + fallthrough; > + case PSCI_1_3_FN64_SYSTEM_OFF2: > + if (minor < 3) > + break; > + > + arg = smccc_get_arg1(vcpu); > + /* > + * PSCI v1.3 issue F.b requires that zero be accepted to mean > + * HIBERNATE_OFF (in line with pre-publication versions of the > + * spec, and thus some actual implementations in the wild). > + * The second argument must be zero. > + */ > + if ((arg && arg != PSCI_1_3_OFF_TYPE_HIBERNATE_OFF) || > + smccc_get_arg2(vcpu) != 0) { > + val = PSCI_RET_INVALID_PARAMS; > + break; > + } > + kvm_psci_system_off2(vcpu); > + /* > + * We shouldn't be going back to guest VCPU after > + * receiving SYSTEM_OFF2 request. > + * > + * If user space accidentally/deliberately resumes > + * guest VCPU after SYSTEM_OFF2 request then guest > + * VCPU should see internal failure from PSCI return > + * value. To achieve this, we preload r0 (or x0) with > + * PSCI return value INTERNAL_FAILURE. > + */ > + val = PSCI_RET_INTERNAL_FAILURE; > + ret = 0; > + break; Other than that it looks good to me: Reviewed-by: Miguel Luis <miguel.luis@oracle.com> Thanks, Miguel > default: > return kvm_psci_0_2_call(vcpu); > } > -- > 2.44.0 >
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index e32471977d0a..1ec076d806e6 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -6855,6 +6855,10 @@ the first `ndata` items (possibly zero) of the data array are valid. the guest issued a SYSTEM_RESET2 call according to v1.1 of the PSCI specification. + - for arm64, data[0] is set to KVM_SYSTEM_EVENT_SHUTDOWN_FLAG_PSCI_OFF2 + if the guest issued a SYSTEM_OFF2 call according to v1.3 of the PSCI + specification. + - for RISC-V, data[0] is set to the value of the second argument of the ``sbi_system_reset`` call. @@ -6888,6 +6892,13 @@ either: - Deny the guest request to suspend the VM. See ARM DEN0022D.b 5.19.2 "Caller responsibilities" for possible return values. +Hibernation using the PSCI SYSTEM_OFF2 call is enabled when PSCI v1.3 +is enabled. If a guest invokes the PSCI SYSTEM_OFF2 function, KVM will +exit to userspace with the KVM_SYSTEM_EVENT_SHUTDOWN event type and with +data[0] set to KVM_SYSTEM_EVENT_SHUTDOWN_FLAG_PSCI_OFF2. The only +supported hibernate type for the SYSTEM_OFF2 function is HIBERNATE_OFF +0x0). + :: /* KVM_EXIT_IOAPIC_EOI */ diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index 964df31da975..66736ff04011 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -484,6 +484,12 @@ enum { */ #define KVM_SYSTEM_EVENT_RESET_FLAG_PSCI_RESET2 (1ULL << 0) +/* + * Shutdown caused by a PSCI v1.3 SYSTEM_OFF2 call. + * Valid only when the system event has a type of KVM_SYSTEM_EVENT_SHUTDOWN. + */ +#define KVM_SYSTEM_EVENT_SHUTDOWN_FLAG_PSCI_OFF2 (1ULL << 0) + /* run->fail_entry.hardware_entry_failure_reason codes. */ #define KVM_EXIT_FAIL_ENTRY_CPU_UNSUPPORTED (1ULL << 0) diff --git a/arch/arm64/kvm/psci.c b/arch/arm64/kvm/psci.c index 1f69b667332b..df834f2e928e 100644 --- a/arch/arm64/kvm/psci.c +++ b/arch/arm64/kvm/psci.c @@ -194,6 +194,12 @@ static void kvm_psci_system_off(struct kvm_vcpu *vcpu) kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_SHUTDOWN, 0); } +static void kvm_psci_system_off2(struct kvm_vcpu *vcpu) +{ + kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_SHUTDOWN, + KVM_SYSTEM_EVENT_SHUTDOWN_FLAG_PSCI_OFF2); +} + static void kvm_psci_system_reset(struct kvm_vcpu *vcpu) { kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_RESET, 0); @@ -358,6 +364,11 @@ static int kvm_psci_1_x_call(struct kvm_vcpu *vcpu, u32 minor) if (minor >= 1) val = 0; break; + case PSCI_1_3_FN_SYSTEM_OFF2: + case PSCI_1_3_FN64_SYSTEM_OFF2: + if (minor >= 3) + val = PSCI_1_3_OFF_TYPE_HIBERNATE_OFF; + break; } break; case PSCI_1_0_FN_SYSTEM_SUSPEND: @@ -392,6 +403,39 @@ static int kvm_psci_1_x_call(struct kvm_vcpu *vcpu, u32 minor) break; } break; + case PSCI_1_3_FN_SYSTEM_OFF2: + kvm_psci_narrow_to_32bit(vcpu); + fallthrough; + case PSCI_1_3_FN64_SYSTEM_OFF2: + if (minor < 3) + break; + + arg = smccc_get_arg1(vcpu); + /* + * PSCI v1.3 issue F.b requires that zero be accepted to mean + * HIBERNATE_OFF (in line with pre-publication versions of the + * spec, and thus some actual implementations in the wild). + * The second argument must be zero. + */ + if ((arg && arg != PSCI_1_3_OFF_TYPE_HIBERNATE_OFF) || + smccc_get_arg2(vcpu) != 0) { + val = PSCI_RET_INVALID_PARAMS; + break; + } + kvm_psci_system_off2(vcpu); + /* + * We shouldn't be going back to guest VCPU after + * receiving SYSTEM_OFF2 request. + * + * If user space accidentally/deliberately resumes + * guest VCPU after SYSTEM_OFF2 request then guest + * VCPU should see internal failure from PSCI return + * value. To achieve this, we preload r0 (or x0) with + * PSCI return value INTERNAL_FAILURE. + */ + val = PSCI_RET_INTERNAL_FAILURE; + ret = 0; + break; default: return kvm_psci_0_2_call(vcpu); }