Merge branch kvm-arm64/psci-suspend into kvmarm-master/next

* kvm-arm64/psci-suspend:
  : .
  : Add support for PSCI SYSTEM_SUSPEND and allow userspace to
  : filter the wake-up events.
  :
  : Patches courtesy of Oliver.
  : .
  Documentation: KVM: Fix title level for PSCI_SUSPEND
  selftests: KVM: Test SYSTEM_SUSPEND PSCI call
  selftests: KVM: Refactor psci_test to make it amenable to new tests
  selftests: KVM: Use KVM_SET_MP_STATE to power off vCPU in psci_test
  selftests: KVM: Create helper for making SMCCC calls
  selftests: KVM: Rename psci_cpu_on_test to psci_test
  KVM: arm64: Implement PSCI SYSTEM_SUSPEND
  KVM: arm64: Add support for userspace to suspend a vCPU
  KVM: arm64: Return a value from check_vcpu_requests()
  KVM: arm64: Rename the KVM_REQ_SLEEP handler
  KVM: arm64: Track vCPU power state using MP state values
  KVM: arm64: Dedupe vCPU power off helpers
  KVM: arm64: Don't depend on fallthrough to hide SYSTEM_RESET2
Signed-off-by: Marc Zyngier <maz@kernel.org>

Documentation/virt/kvm/api.rst

@@ -1476,14 +1476,43 @@ Possible values are:
                                  [s390]
    KVM_MP_STATE_LOAD             the vcpu is in a special load/startup state
                                  [s390]
+   KVM_MP_STATE_SUSPENDED        the vcpu is in a suspend state and is waiting
+                                 for a wakeup event [arm64]
    ==========================    ===============================================
 
 On x86, this ioctl is only useful after KVM_CREATE_IRQCHIP. Without an
 in-kernel irqchip, the multiprocessing state must be maintained by userspace on
 these architectures.
 
-For arm64/riscv:
-^^^^^^^^^^^^^^^^
+For arm64:
+^^^^^^^^^^
+
+If a vCPU is in the KVM_MP_STATE_SUSPENDED state, KVM will emulate the
+architectural execution of a WFI instruction.
+
+If a wakeup event is recognized, KVM will exit to userspace with a
+KVM_SYSTEM_EVENT exit, where the event type is KVM_SYSTEM_EVENT_WAKEUP. If
+userspace wants to honor the wakeup, it must set the vCPU's MP state to
+KVM_MP_STATE_RUNNABLE. If it does not, KVM will continue to await a wakeup
+event in subsequent calls to KVM_RUN.
+
+.. warning::
+
+     If userspace intends to keep the vCPU in a SUSPENDED state, it is
+     strongly recommended that userspace take action to suppress the
+     wakeup event (such as masking an interrupt). Otherwise, subsequent
+     calls to KVM_RUN will immediately exit with a KVM_SYSTEM_EVENT_WAKEUP
+     event and inadvertently waste CPU cycles.
+
+     Additionally, if userspace takes action to suppress a wakeup event,
+     it is strongly recommended that it also restores the vCPU to its
+     original state when the vCPU is made RUNNABLE again. For example,
+     if userspace masked a pending interrupt to suppress the wakeup,
+     the interrupt should be unmasked before returning control to the
+     guest.
+
+For riscv:
+^^^^^^^^^^
 
 The only states that are valid are KVM_MP_STATE_STOPPED and
 KVM_MP_STATE_RUNNABLE which reflect if the vcpu is paused or not.
@@ -6003,6 +6032,8 @@ should put the acknowledged interrupt vector into the 'epr' field.
   #define KVM_SYSTEM_EVENT_SHUTDOWN       1
   #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];
@@ -6027,6 +6058,37 @@ Valid values for 'type' are:
    has requested a crash condition maintenance. Userspace can choose
    to ignore the request, or to gather VM memory core dump and/or
    reset/shutdown of the VM.
+ - 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
@@ -7752,6 +7814,16 @@ 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
 =========================
 

arch/arm64/include/asm/kvm_host.h

@@ -46,6 +46,7 @@
 #define KVM_REQ_RECORD_STEAL	KVM_ARCH_REQ(3)
 #define KVM_REQ_RELOAD_GICv4	KVM_ARCH_REQ(4)
 #define KVM_REQ_RELOAD_PMU	KVM_ARCH_REQ(5)
+#define KVM_REQ_SUSPEND		KVM_ARCH_REQ(6)
 
 #define KVM_DIRTY_LOG_MANUAL_CAPS   (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \
 				     KVM_DIRTY_LOG_INITIALLY_SET)
@@ -149,6 +150,8 @@ 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;
 
@@ -384,8 +387,8 @@ struct kvm_vcpu_arch {
 		u32	mdscr_el1;
 	} guest_debug_preserved;
 
-	/* vcpu power-off state */
-	bool power_off;
+	/* vcpu power state */
+	struct kvm_mp_state mp_state;
 
 	/* Don't run the guest (internal implementation need) */
 	bool pause;
@@ -863,4 +866,7 @@ void __init kvm_hyp_reserve(void);
 static inline void kvm_hyp_reserve(void) { }
 #endif
 
+void kvm_arm_vcpu_power_off(struct kvm_vcpu *vcpu);
+bool kvm_arm_vcpu_stopped(struct kvm_vcpu *vcpu);
+
 #endif /* __ARM64_KVM_HOST_H__ */

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;
@@ -211,6 +215,7 @@ 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:
@@ -428,20 +433,34 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 	vcpu->cpu = -1;
 }
 
-static void vcpu_power_off(struct kvm_vcpu *vcpu)
+void kvm_arm_vcpu_power_off(struct kvm_vcpu *vcpu)
 {
-	vcpu->arch.power_off = true;
+	vcpu->arch.mp_state.mp_state = KVM_MP_STATE_STOPPED;
 	kvm_make_request(KVM_REQ_SLEEP, vcpu);
 	kvm_vcpu_kick(vcpu);
 }
 
+bool kvm_arm_vcpu_stopped(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.mp_state.mp_state == KVM_MP_STATE_STOPPED;
+}
+
+static void kvm_arm_vcpu_suspend(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.mp_state.mp_state = KVM_MP_STATE_SUSPENDED;
+	kvm_make_request(KVM_REQ_SUSPEND, vcpu);
+	kvm_vcpu_kick(vcpu);
+}
+
+static bool kvm_arm_vcpu_suspended(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.mp_state.mp_state == KVM_MP_STATE_SUSPENDED;
+}
+
 int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
 				    struct kvm_mp_state *mp_state)
 {
-	if (vcpu->arch.power_off)
-		mp_state->mp_state = KVM_MP_STATE_STOPPED;
-	else
-		mp_state->mp_state = KVM_MP_STATE_RUNNABLE;
+	*mp_state = vcpu->arch.mp_state;
 
 	return 0;
 }
@@ -453,10 +472,13 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 
 	switch (mp_state->mp_state) {
 	case KVM_MP_STATE_RUNNABLE:
-		vcpu->arch.power_off = false;
+		vcpu->arch.mp_state = *mp_state;
 		break;
 	case KVM_MP_STATE_STOPPED:
-		vcpu_power_off(vcpu);
+		kvm_arm_vcpu_power_off(vcpu);
+		break;
+	case KVM_MP_STATE_SUSPENDED:
+		kvm_arm_vcpu_suspend(vcpu);
 		break;
 	default:
 		ret = -EINVAL;
@@ -476,7 +498,7 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
 {
 	bool irq_lines = *vcpu_hcr(v) & (HCR_VI | HCR_VF);
 	return ((irq_lines || kvm_vgic_vcpu_pending_irq(v))
-		&& !v->arch.power_off && !v->arch.pause);
+		&& !kvm_arm_vcpu_stopped(v) && !v->arch.pause);
 }
 
 bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
@@ -588,15 +610,15 @@ void kvm_arm_resume_guest(struct kvm *kvm)
 	}
 }
 
-static void vcpu_req_sleep(struct kvm_vcpu *vcpu)
+static void kvm_vcpu_sleep(struct kvm_vcpu *vcpu)
 {
 	struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu);
 
 	rcuwait_wait_event(wait,
-			   (!vcpu->arch.power_off) &&(!vcpu->arch.pause),
+			   (!kvm_arm_vcpu_stopped(vcpu)) && (!vcpu->arch.pause),
 			   TASK_INTERRUPTIBLE);
 
-	if (vcpu->arch.power_off || vcpu->arch.pause) {
+	if (kvm_arm_vcpu_stopped(vcpu) || vcpu->arch.pause) {
 		/* Awaken to handle a signal, request we sleep again later. */
 		kvm_make_request(KVM_REQ_SLEEP, vcpu);
 	}
@@ -643,11 +665,53 @@ void kvm_vcpu_wfi(struct kvm_vcpu *vcpu)
 	preempt_enable();
 }
 
-static void check_vcpu_requests(struct kvm_vcpu *vcpu)
+static int kvm_vcpu_suspend(struct kvm_vcpu *vcpu)
+{
+	if (!kvm_arm_vcpu_suspended(vcpu))
+		return 1;
+
+	kvm_vcpu_wfi(vcpu);
+
+	/*
+	 * The suspend state is sticky; we do not leave it until userspace
+	 * explicitly marks the vCPU as runnable. Request that we suspend again
+	 * later.
+	 */
+	kvm_make_request(KVM_REQ_SUSPEND, vcpu);
+
+	/*
+	 * Check to make sure the vCPU is actually runnable. If so, exit to
+	 * userspace informing it of the wakeup condition.
+	 */
+	if (kvm_arch_vcpu_runnable(vcpu)) {
+		memset(&vcpu->run->system_event, 0, sizeof(vcpu->run->system_event));
+		vcpu->run->system_event.type = KVM_SYSTEM_EVENT_WAKEUP;
+		vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT;
+		return 0;
+	}
+
+	/*
+	 * Otherwise, we were unblocked to process a different event, such as a
+	 * pending signal. Return 1 and allow kvm_arch_vcpu_ioctl_run() to
+	 * process the event.
+	 */
+	return 1;
+}
+
+/**
+ * check_vcpu_requests - check and handle pending vCPU requests
+ * @vcpu:	the VCPU pointer
+ *
+ * Return: 1 if we should enter the guest
+ *	   0 if we should exit to userspace
+ *	   < 0 if we should exit to userspace, where the return value indicates
+ *	   an error
+ */
+static int check_vcpu_requests(struct kvm_vcpu *vcpu)
 {
 	if (kvm_request_pending(vcpu)) {
 		if (kvm_check_request(KVM_REQ_SLEEP, vcpu))
-			vcpu_req_sleep(vcpu);
+			kvm_vcpu_sleep(vcpu);
 
 		if (kvm_check_request(KVM_REQ_VCPU_RESET, vcpu))
 			kvm_reset_vcpu(vcpu);
@@ -672,7 +736,12 @@ static void check_vcpu_requests(struct kvm_vcpu *vcpu)
 		if (kvm_check_request(KVM_REQ_RELOAD_PMU, vcpu))
 			kvm_pmu_handle_pmcr(vcpu,
 					    __vcpu_sys_reg(vcpu, PMCR_EL0));
+
+		if (kvm_check_request(KVM_REQ_SUSPEND, vcpu))
+			return kvm_vcpu_suspend(vcpu);
 	}
+
+	return 1;
 }
 
 static bool vcpu_mode_is_bad_32bit(struct kvm_vcpu *vcpu)
@@ -788,7 +857,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		if (!ret)
 			ret = 1;
 
-		check_vcpu_requests(vcpu);
+		if (ret > 0)
+			ret = check_vcpu_requests(vcpu);
 
 		/*
 		 * Preparing the interrupts to be injected also
@@ -1121,9 +1191,9 @@ static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu,
 	 * Handle the "start in power-off" case.
 	 */
 	if (test_bit(KVM_ARM_VCPU_POWER_OFF, vcpu->arch.features))
-		vcpu_power_off(vcpu);
+		kvm_arm_vcpu_power_off(vcpu);
 	else
-		vcpu->arch.power_off = false;
+		vcpu->arch.mp_state.mp_state = KVM_MP_STATE_RUNNABLE;
 
 	return 0;
 }

arch/arm64/kvm/psci.c

@@ -51,13 +51,6 @@ static unsigned long kvm_psci_vcpu_suspend(struct kvm_vcpu *vcpu)
 	return PSCI_RET_SUCCESS;
 }
 
-static void kvm_psci_vcpu_off(struct kvm_vcpu *vcpu)
-{
-	vcpu->arch.power_off = true;
-	kvm_make_request(KVM_REQ_SLEEP, vcpu);
-	kvm_vcpu_kick(vcpu);
-}
-
 static inline bool kvm_psci_valid_affinity(struct kvm_vcpu *vcpu,
 					   unsigned long affinity)
 {
@@ -83,7 +76,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 	 */
 	if (!vcpu)
 		return PSCI_RET_INVALID_PARAMS;
-	if (!vcpu->arch.power_off) {
+	if (!kvm_arm_vcpu_stopped(vcpu)) {
 		if (kvm_psci_version(source_vcpu) != KVM_ARM_PSCI_0_1)
 			return PSCI_RET_ALREADY_ON;
 		else
@@ -107,12 +100,12 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 	kvm_make_request(KVM_REQ_VCPU_RESET, vcpu);
 
 	/*
-	 * Make sure the reset request is observed if the change to
-	 * power_off is observed.
+	 * Make sure the reset request is observed if the RUNNABLE mp_state is
+	 * observed.
 	 */
 	smp_wmb();
 
-	vcpu->arch.power_off = false;
+	vcpu->arch.mp_state.mp_state = KVM_MP_STATE_RUNNABLE;
 	kvm_vcpu_wake_up(vcpu);
 
 	return PSCI_RET_SUCCESS;
@@ -150,7 +143,7 @@ static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu)
 		mpidr = kvm_vcpu_get_mpidr_aff(tmp);
 		if ((mpidr & target_affinity_mask) == target_affinity) {
 			matching_cpus++;
-			if (!tmp->arch.power_off)
+			if (!kvm_arm_vcpu_stopped(tmp))
 				return PSCI_0_2_AFFINITY_LEVEL_ON;
 		}
 	}
@@ -176,7 +169,7 @@ static void kvm_prepare_system_event(struct kvm_vcpu *vcpu, u32 type, u64 flags)
 	 * re-initialized.
 	 */
 	kvm_for_each_vcpu(i, tmp, vcpu->kvm)
-		tmp->arch.power_off = true;
+		tmp->arch.mp_state.mp_state = KVM_MP_STATE_STOPPED;
 	kvm_make_all_cpus_request(vcpu->kvm, KVM_REQ_SLEEP);
 
 	memset(&vcpu->run->system_event, 0, sizeof(vcpu->run->system_event));
@@ -202,6 +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;
@@ -245,7 +247,7 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 		val = kvm_psci_vcpu_suspend(vcpu);
 		break;
 	case PSCI_0_2_FN_CPU_OFF:
-		kvm_psci_vcpu_off(vcpu);
+		kvm_arm_vcpu_power_off(vcpu);
 		val = PSCI_RET_SUCCESS;
 		break;
 	case PSCI_0_2_FN_CPU_ON:
@@ -305,9 +307,10 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 
 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;
-	unsigned long val;
 	int ret = 1;
 
 	switch(psci_fn) {
@@ -320,6 +323,8 @@ static int kvm_psci_1_x_call(struct kvm_vcpu *vcpu, u32 minor)
 		if (val)
 			break;
 
+		val = PSCI_RET_NOT_SUPPORTED;
+
 		switch(arg) {
 		case PSCI_0_2_FN_PSCI_VERSION:
 		case PSCI_0_2_FN_CPU_SUSPEND:
@@ -336,16 +341,30 @@ 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) {
+			if (minor >= 1)
 				val = 0;
 			break;
 		}
-			fallthrough;
-		default:
-			val = PSCI_RET_NOT_SUPPORTED;
 		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:
@@ -365,7 +384,7 @@ static int kvm_psci_1_x_call(struct kvm_vcpu *vcpu, u32 minor)
 			val = PSCI_RET_INVALID_PARAMS;
 			break;
 		}
-		fallthrough;
+		break;
 	default:
 		return kvm_psci_0_2_call(vcpu);
 	}
@@ -382,7 +401,7 @@ static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu)
 
 	switch (psci_fn) {
 	case KVM_PSCI_FN_CPU_OFF:
-		kvm_psci_vcpu_off(vcpu);
+		kvm_arm_vcpu_power_off(vcpu);
 		val = PSCI_RET_SUCCESS;
 		break;
 	case KVM_PSCI_FN_CPU_ON:

include/uapi/linux/kvm.h

@@ -444,6 +444,8 @@ struct kvm_run {
 #define KVM_SYSTEM_EVENT_SHUTDOWN       1
 #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 {
@@ -646,6 +648,7 @@ struct kvm_vapic_addr {
 #define KVM_MP_STATE_OPERATING         7
 #define KVM_MP_STATE_LOAD              8
 #define KVM_MP_STATE_AP_RESET_HOLD     9
+#define KVM_MP_STATE_SUSPENDED         10
 
 struct kvm_mp_state {
 	__u32 mp_state;
@@ -1152,6 +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
 

tools/testing/selftests/kvm/aarch64/psci_test.c

@@ -45,27 +45,38 @@ static uint64_t psci_affinity_info(uint64_t target_affinity,
 	return res.a0;
 }
 
-static void guest_main(uint64_t target_cpu)
+static uint64_t psci_system_suspend(uint64_t entry_addr, uint64_t context_id)
 {
-	GUEST_ASSERT(!psci_cpu_on(target_cpu, CPU_ON_ENTRY_ADDR, CPU_ON_CONTEXT_ID));
-	uint64_t target_state;
+	struct arm_smccc_res res;
 
-	do {
-		target_state = psci_affinity_info(target_cpu, 0);
+	smccc_hvc(PSCI_1_0_FN64_SYSTEM_SUSPEND, entry_addr, context_id,
+		  0, 0, 0, 0, 0, &res);
 
-		GUEST_ASSERT((target_state == PSCI_0_2_AFFINITY_LEVEL_ON) ||
-			     (target_state == PSCI_0_2_AFFINITY_LEVEL_OFF));
-	} while (target_state != PSCI_0_2_AFFINITY_LEVEL_ON);
+	return res.a0;
+}
 
-	GUEST_DONE();
+static uint64_t psci_features(uint32_t func_id)
+{
+	struct arm_smccc_res res;
+
+	smccc_hvc(PSCI_1_0_FN_PSCI_FEATURES, func_id, 0, 0, 0, 0, 0, 0, &res);
+
+	return res.a0;
 }
 
-int main(void)
+static void vcpu_power_off(struct kvm_vm *vm, uint32_t vcpuid)
+{
+	struct kvm_mp_state mp_state = {
+		.mp_state = KVM_MP_STATE_STOPPED,
+	};
+
+	vcpu_set_mp_state(vm, vcpuid, &mp_state);
+}
+
+static struct kvm_vm *setup_vm(void *guest_code)
 {
-	uint64_t target_mpidr, obs_pc, obs_x0;
 	struct kvm_vcpu_init init;
 	struct kvm_vm *vm;
-	struct ucall uc;
 
 	vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR);
 	kvm_vm_elf_load(vm, program_invocation_name);
@@ -74,31 +85,28 @@ int main(void)
 	vm_ioctl(vm, KVM_ARM_PREFERRED_TARGET, &init);
 	init.features[0] |= (1 << KVM_ARM_VCPU_PSCI_0_2);
 
-	aarch64_vcpu_add_default(vm, VCPU_ID_SOURCE, &init, guest_main);
+	aarch64_vcpu_add_default(vm, VCPU_ID_SOURCE, &init, guest_code);
+	aarch64_vcpu_add_default(vm, VCPU_ID_TARGET, &init, guest_code);
 
-	/*
-	 * make sure the target is already off when executing the test.
-	 */
-	init.features[0] |= (1 << KVM_ARM_VCPU_POWER_OFF);
-	aarch64_vcpu_add_default(vm, VCPU_ID_TARGET, &init, guest_main);
+	return vm;
+}
 
-	get_reg(vm, VCPU_ID_TARGET, KVM_ARM64_SYS_REG(SYS_MPIDR_EL1), &target_mpidr);
-	vcpu_args_set(vm, VCPU_ID_SOURCE, 1, target_mpidr & MPIDR_HWID_BITMASK);
-	vcpu_run(vm, VCPU_ID_SOURCE);
+static void enter_guest(struct kvm_vm *vm, uint32_t vcpuid)
+{
+	struct ucall uc;
 
-	switch (get_ucall(vm, VCPU_ID_SOURCE, &uc)) {
-	case UCALL_DONE:
-		break;
-	case UCALL_ABORT:
+	vcpu_run(vm, vcpuid);
+	if (get_ucall(vm, vcpuid, &uc) == UCALL_ABORT)
 		TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], __FILE__,
 			  uc.args[1]);
-		break;
-	default:
-		TEST_FAIL("Unhandled ucall: %lu", uc.cmd);
-	}
+}
 
-	get_reg(vm, VCPU_ID_TARGET, ARM64_CORE_REG(regs.pc), &obs_pc);
-	get_reg(vm, VCPU_ID_TARGET, ARM64_CORE_REG(regs.regs[0]), &obs_x0);
+static void assert_vcpu_reset(struct kvm_vm *vm, uint32_t vcpuid)
+{
+	uint64_t obs_pc, obs_x0;
+
+	get_reg(vm, vcpuid, ARM64_CORE_REG(regs.pc), &obs_pc);
+	get_reg(vm, vcpuid, ARM64_CORE_REG(regs.regs[0]), &obs_x0);
 
 	TEST_ASSERT(obs_pc == CPU_ON_ENTRY_ADDR,
 		    "unexpected target cpu pc: %lx (expected: %lx)",
@@ -106,7 +114,100 @@ int main(void)
 	TEST_ASSERT(obs_x0 == CPU_ON_CONTEXT_ID,
 		    "unexpected target context id: %lx (expected: %lx)",
 		    obs_x0, CPU_ON_CONTEXT_ID);
+}
+
+static void guest_test_cpu_on(uint64_t target_cpu)
+{
+	uint64_t target_state;
 
+	GUEST_ASSERT(!psci_cpu_on(target_cpu, CPU_ON_ENTRY_ADDR, CPU_ON_CONTEXT_ID));
+
+	do {
+		target_state = psci_affinity_info(target_cpu, 0);
+
+		GUEST_ASSERT((target_state == PSCI_0_2_AFFINITY_LEVEL_ON) ||
+			     (target_state == PSCI_0_2_AFFINITY_LEVEL_OFF));
+	} while (target_state != PSCI_0_2_AFFINITY_LEVEL_ON);
+
+	GUEST_DONE();
+}
+
+static void host_test_cpu_on(void)
+{
+	uint64_t target_mpidr;
+	struct kvm_vm *vm;
+	struct ucall uc;
+
+	vm = setup_vm(guest_test_cpu_on);
+
+	/*
+	 * make sure the target is already off when executing the test.
+	 */
+	vcpu_power_off(vm, VCPU_ID_TARGET);
+
+	get_reg(vm, VCPU_ID_TARGET, KVM_ARM64_SYS_REG(SYS_MPIDR_EL1), &target_mpidr);
+	vcpu_args_set(vm, VCPU_ID_SOURCE, 1, target_mpidr & MPIDR_HWID_BITMASK);
+	enter_guest(vm, VCPU_ID_SOURCE);
+
+	if (get_ucall(vm, VCPU_ID_SOURCE, &uc) != UCALL_DONE)
+		TEST_FAIL("Unhandled ucall: %lu", uc.cmd);
+
+	assert_vcpu_reset(vm, VCPU_ID_TARGET);
 	kvm_vm_free(vm);
+}
+
+static void enable_system_suspend(struct kvm_vm *vm)
+{
+	struct kvm_enable_cap cap = {
+		.cap = KVM_CAP_ARM_SYSTEM_SUSPEND,
+	};
+
+	vm_enable_cap(vm, &cap);
+}
+
+static void guest_test_system_suspend(void)
+{
+	uint64_t ret;
+
+	/* assert that SYSTEM_SUSPEND is discoverable */
+	GUEST_ASSERT(!psci_features(PSCI_1_0_FN_SYSTEM_SUSPEND));
+	GUEST_ASSERT(!psci_features(PSCI_1_0_FN64_SYSTEM_SUSPEND));
+
+	ret = psci_system_suspend(CPU_ON_ENTRY_ADDR, CPU_ON_CONTEXT_ID);
+	GUEST_SYNC(ret);
+}
+
+static void host_test_system_suspend(void)
+{
+	struct kvm_run *run;
+	struct kvm_vm *vm;
+
+	vm = setup_vm(guest_test_system_suspend);
+	enable_system_suspend(vm);
+
+	vcpu_power_off(vm, VCPU_ID_TARGET);
+	run = vcpu_state(vm, VCPU_ID_SOURCE);
+
+	enter_guest(vm, VCPU_ID_SOURCE);
+
+	TEST_ASSERT(run->exit_reason == KVM_EXIT_SYSTEM_EVENT,
+		    "Unhandled exit reason: %u (%s)",
+		    run->exit_reason, exit_reason_str(run->exit_reason));
+	TEST_ASSERT(run->system_event.type == KVM_SYSTEM_EVENT_SUSPEND,
+		    "Unhandled system event: %u (expected: %u)",
+		    run->system_event.type, KVM_SYSTEM_EVENT_SUSPEND);
+
+	kvm_vm_free(vm);
+}
+
+int main(void)
+{
+	if (!kvm_check_cap(KVM_CAP_ARM_SYSTEM_SUSPEND)) {
+		print_skip("KVM_CAP_ARM_SYSTEM_SUSPEND not supported");
+		exit(KSFT_SKIP);
+	}
+
+	host_test_cpu_on();
+	host_test_system_suspend();
 	return 0;
 }