diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 46ca84600dca..d8d7859fc556 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -6015,6 +6015,7 @@ should put the acknowledged interrupt vector into the 'epr' field. #define KVM_SYSTEM_EVENT_RESET 2 #define KVM_SYSTEM_EVENT_CRASH 3 #define KVM_SYSTEM_EVENT_WAKEUP 4 + #define KVM_SYSTEM_EVENT_SUSPEND 5 __u32 type; __u32 ndata; __u64 data[16]; @@ -6042,6 +6043,34 @@ Valid values for 'type' are: - KVM_SYSTEM_EVENT_WAKEUP -- the exiting vCPU is in a suspended state and KVM has recognized a wakeup event. Userspace may honor this event by marking the exiting vCPU as runnable, or deny it and call KVM_RUN again. + - KVM_SYSTEM_EVENT_SUSPEND -- the guest has requested a suspension of + the VM. + +For arm/arm64: +^^^^^^^^^^^^^^ + + KVM_SYSTEM_EVENT_SUSPEND exits are enabled with the + KVM_CAP_ARM_SYSTEM_SUSPEND VM capability. If a guest invokes the PSCI + SYSTEM_SUSPEND function, KVM will exit to userspace with this event + type. + + It is the sole responsibility of userspace to implement the PSCI + SYSTEM_SUSPEND call according to ARM DEN0022D.b 5.19 "SYSTEM_SUSPEND". + KVM does not change the vCPU's state before exiting to userspace, so + the call parameters are left in-place in the vCPU registers. + + Userspace is _required_ to take action for such an exit. It must + either: + + - Honor the guest request to suspend the VM. Userspace can request + in-kernel emulation of suspension by setting the calling vCPU's + state to KVM_MP_STATE_SUSPENDED. Userspace must configure the vCPU's + state according to the parameters passed to the PSCI function when + the calling vCPU is resumed. See ARM DEN0022D.b 5.19.1 "Intended use" + for details on the function parameters. + + - Deny the guest request to suspend the VM. See ARM DEN0022D.b 5.19.2 + "Caller responsibilities" for possible return values. If KVM_CAP_SYSTEM_EVENT_DATA is present, the 'data' field can contain architecture specific information for the system-level event. Only @@ -7767,6 +7796,16 @@ At this time, KVM_PMU_CAP_DISABLE is the only capability. Setting this capability will disable PMU virtualization for that VM. Usermode should adjust CPUID leaf 0xA to reflect that the PMU is disabled. +8.36 KVM_CAP_ARM_SYSTEM_SUSPEND +------------------------------- + +:Capability: KVM_CAP_ARM_SYSTEM_SUSPEND +:Architectures: arm64 +:Type: vm + +When enabled, KVM will exit to userspace with KVM_EXIT_SYSTEM_EVENT of +type KVM_SYSTEM_EVENT_SUSPEND to process the guest suspend request. + 9. Known KVM API problems ========================= diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 46027b9b80ca..d9df81949f76 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -137,6 +137,8 @@ struct kvm_arch { */ #define KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED 3 #define KVM_ARCH_FLAG_EL1_32BIT 4 + /* PSCI SYSTEM_SUSPEND enabled for the guest */ +#define KVM_ARCH_FLAG_SYSTEM_SUSPEND_ENABLED 5 unsigned long flags; diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index abd32a84ed7a..f8a89ae52710 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -97,6 +97,10 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, } mutex_unlock(&kvm->lock); break; + case KVM_CAP_ARM_SYSTEM_SUSPEND: + r = 0; + set_bit(KVM_ARCH_FLAG_SYSTEM_SUSPEND_ENABLED, &kvm->arch.flags); + break; default: r = -EINVAL; break; @@ -210,6 +214,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_SET_GUEST_DEBUG: case KVM_CAP_VCPU_ATTRIBUTES: case KVM_CAP_PTP_KVM: + case KVM_CAP_ARM_SYSTEM_SUSPEND: r = 1; break; case KVM_CAP_SET_GUEST_DEBUG2: diff --git a/arch/arm64/kvm/psci.c b/arch/arm64/kvm/psci.c index 2e6f060214a7..5de30e72ad40 100644 --- a/arch/arm64/kvm/psci.c +++ b/arch/arm64/kvm/psci.c @@ -195,6 +195,15 @@ static void kvm_psci_system_reset2(struct kvm_vcpu *vcpu) KVM_SYSTEM_EVENT_RESET_FLAG_PSCI_RESET2); } +static void kvm_psci_system_suspend(struct kvm_vcpu *vcpu) +{ + struct kvm_run *run = vcpu->run; + + memset(&run->system_event, 0, sizeof(vcpu->run->system_event)); + run->system_event.type = KVM_SYSTEM_EVENT_SUSPEND; + run->exit_reason = KVM_EXIT_SYSTEM_EVENT; +} + static void kvm_psci_narrow_to_32bit(struct kvm_vcpu *vcpu) { int i; @@ -300,6 +309,7 @@ static int kvm_psci_1_x_call(struct kvm_vcpu *vcpu, u32 minor) { unsigned long val = PSCI_RET_NOT_SUPPORTED; u32 psci_fn = smccc_get_function(vcpu); + struct kvm *kvm = vcpu->kvm; u32 arg; int ret = 1; @@ -331,6 +341,11 @@ static int kvm_psci_1_x_call(struct kvm_vcpu *vcpu, u32 minor) case ARM_SMCCC_VERSION_FUNC_ID: val = 0; break; + case PSCI_1_0_FN_SYSTEM_SUSPEND: + case PSCI_1_0_FN64_SYSTEM_SUSPEND: + if (test_bit(KVM_ARCH_FLAG_SYSTEM_SUSPEND_ENABLED, &kvm->arch.flags)) + val = 0; + break; case PSCI_1_1_FN_SYSTEM_RESET2: case PSCI_1_1_FN64_SYSTEM_RESET2: if (minor >= 1) @@ -338,6 +353,20 @@ static int kvm_psci_1_x_call(struct kvm_vcpu *vcpu, u32 minor) break; } break; + case PSCI_1_0_FN_SYSTEM_SUSPEND: + kvm_psci_narrow_to_32bit(vcpu); + fallthrough; + case PSCI_1_0_FN64_SYSTEM_SUSPEND: + /* + * Return directly to userspace without changing the vCPU's + * registers. Userspace depends on reading the SMCCC parameters + * to implement SYSTEM_SUSPEND. + */ + if (test_bit(KVM_ARCH_FLAG_SYSTEM_SUSPEND_ENABLED, &kvm->arch.flags)) { + kvm_psci_system_suspend(vcpu); + return 0; + } + break; case PSCI_1_1_FN_SYSTEM_RESET2: kvm_psci_narrow_to_32bit(vcpu); fallthrough; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 7f72fb7b05f2..32c56384fd08 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -445,6 +445,7 @@ struct kvm_run { #define KVM_SYSTEM_EVENT_RESET 2 #define KVM_SYSTEM_EVENT_CRASH 3 #define KVM_SYSTEM_EVENT_WAKEUP 4 +#define KVM_SYSTEM_EVENT_SUSPEND 5 __u32 type; __u32 ndata; union { @@ -1154,6 +1155,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_DISABLE_QUIRKS2 213 /* #define KVM_CAP_VM_TSC_CONTROL 214 */ #define KVM_CAP_SYSTEM_EVENT_DATA 215 +#define KVM_CAP_ARM_SYSTEM_SUSPEND 216 #ifdef KVM_CAP_IRQ_ROUTING