From 5bc2cb95ad03d866422d7b3f19ec42a6720f3262 Mon Sep 17 00:00:00 2001
From: Oliver Upton <oupton@google.com>
Date: Wed, 4 May 2022 03:24:35 +0000
Subject: [PATCH 01/13] KVM: arm64: Don't depend on fallthrough to hide
 SYSTEM_RESET2

Depending on a fallthrough to the default case for hiding SYSTEM_RESET2
requires that any new case statements clean up the failure path for this
PSCI call.

Unhitch SYSTEM_RESET2 from the default case by setting val to
PSCI_RET_NOT_SUPPORTED outside of the switch statement. Apply the
cleanup to both the PSCI_1_1_FN_SYSTEM_RESET2 and
PSCI_1_0_FN_PSCI_FEATURES handlers.

No functional change intended.

Signed-off-by: Oliver Upton <oupton@google.com>
Reviewed-by: Reiji Watanabe <reijiw@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20220504032446.4133305-2-oupton@google.com
---
 arch/arm64/kvm/psci.c | 13 +++++--------
 1 file changed, 5 insertions(+), 8 deletions(-)

diff --git a/arch/arm64/kvm/psci.c b/arch/arm64/kvm/psci.c
index 708d80e8e60d..67fbd6ef022c 100644
--- a/arch/arm64/kvm/psci.c
+++ b/arch/arm64/kvm/psci.c
@@ -305,9 +305,9 @@ 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);
 	u32 arg;
-	unsigned long val;
 	int ret = 1;
 
 	switch(psci_fn) {
@@ -320,6 +320,8 @@ 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:
@@ -338,13 +340,8 @@ static int kvm_psci_1_x_call(struct kvm_vcpu *vcpu, u32 minor)
 			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;
 		}
 		break;
@@ -365,7 +362,7 @@ 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);
 	}

From 1e5794295c5dbfcc31cf5de840c9e095ae50efb7 Mon Sep 17 00:00:00 2001
From: Oliver Upton <oupton@google.com>
Date: Wed, 4 May 2022 03:24:36 +0000
Subject: [PATCH 02/13] KVM: arm64: Dedupe vCPU power off helpers

vcpu_power_off() and kvm_psci_vcpu_off() are equivalent; rename the
former and replace all callsites to the latter.

No functional change intended.

Signed-off-by: Oliver Upton <oupton@google.com>
Reviewed-by: Reiji Watanabe <reijiw@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20220504032446.4133305-3-oupton@google.com
---
 arch/arm64/include/asm/kvm_host.h |  2 ++
 arch/arm64/kvm/arm.c              |  6 +++---
 arch/arm64/kvm/psci.c             | 11 ++---------
 3 files changed, 7 insertions(+), 12 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 94a27a7520f4..490cd7f3a905 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -841,4 +841,6 @@ void __init kvm_hyp_reserve(void);
 static inline void kvm_hyp_reserve(void) { }
 #endif
 
+void kvm_arm_vcpu_power_off(struct kvm_vcpu *vcpu);
+
 #endif /* __ARM64_KVM_HOST_H__ */
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 523bc934fe2f..28c83c6ddbae 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -432,7 +432,7 @@ 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;
 	kvm_make_request(KVM_REQ_SLEEP, vcpu);
@@ -460,7 +460,7 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 		vcpu->arch.power_off = false;
 		break;
 	case KVM_MP_STATE_STOPPED:
-		vcpu_power_off(vcpu);
+		kvm_arm_vcpu_power_off(vcpu);
 		break;
 	default:
 		ret = -EINVAL;
@@ -1124,7 +1124,7 @@ 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;
 
diff --git a/arch/arm64/kvm/psci.c b/arch/arm64/kvm/psci.c
index 67fbd6ef022c..9b1f3acae155 100644
--- a/arch/arm64/kvm/psci.c
+++ b/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)
 {
@@ -245,7 +238,7 @@ 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:
@@ -379,7 +372,7 @@ 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:

From b171f9bbb130cb323f2101edd32da2a25d43ebfa Mon Sep 17 00:00:00 2001
From: Oliver Upton <oupton@google.com>
Date: Wed, 4 May 2022 03:24:37 +0000
Subject: [PATCH 03/13] KVM: arm64: Track vCPU power state using MP state
 values

A subsequent change to KVM will add support for additional power states.
Store the MP state by value rather than keeping track of it as a
boolean.

No functional change intended.

Signed-off-by: Oliver Upton <oupton@google.com>
Reviewed-by: Reiji Watanabe <reijiw@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20220504032446.4133305-4-oupton@google.com
---
 arch/arm64/include/asm/kvm_host.h |  5 +++--
 arch/arm64/kvm/arm.c              | 22 ++++++++++++----------
 arch/arm64/kvm/psci.c             | 12 ++++++------
 3 files changed, 21 insertions(+), 18 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 490cd7f3a905..f3f93d48e21a 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -365,8 +365,8 @@ 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;
@@ -842,5 +842,6 @@ 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__ */
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 28c83c6ddbae..29e107457c4d 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -434,18 +434,20 @@ void kvm_arch_vcpu_put(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;
+}
+
 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;
 }
@@ -457,7 +459,7 @@ 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:
 		kvm_arm_vcpu_power_off(vcpu);
@@ -480,7 +482,7 @@ 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)
@@ -597,10 +599,10 @@ static void vcpu_req_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);
 	}
@@ -1126,7 +1128,7 @@ static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu,
 	if (test_bit(KVM_ARM_VCPU_POWER_OFF, vcpu->arch.features))
 		kvm_arm_vcpu_power_off(vcpu);
 	else
-		vcpu->arch.power_off = false;
+		vcpu->arch.mp_state.mp_state = KVM_MP_STATE_RUNNABLE;
 
 	return 0;
 }
diff --git a/arch/arm64/kvm/psci.c b/arch/arm64/kvm/psci.c
index 9b1f3acae155..2e6f060214a7 100644
--- a/arch/arm64/kvm/psci.c
+++ b/arch/arm64/kvm/psci.c
@@ -76,7 +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
@@ -100,12 +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;
@@ -143,7 +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;
 		}
 	}
@@ -169,7 +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));

From 1c6219e3faf12e58d520b3b2cdfa8cd5e1efc9a5 Mon Sep 17 00:00:00 2001
From: Oliver Upton <oupton@google.com>
Date: Wed, 4 May 2022 03:24:38 +0000
Subject: [PATCH 04/13] KVM: arm64: Rename the KVM_REQ_SLEEP handler

The naming of the kvm_req_sleep function is confusing: the function
itself sleeps the vCPU, it does not request such an event. Rename the
function to make its purpose more clear.

No functional change intended.

Signed-off-by: Oliver Upton <oupton@google.com>
Reviewed-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20220504032446.4133305-5-oupton@google.com
---
 arch/arm64/kvm/arm.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 29e107457c4d..77b8b870c0fc 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -594,7 +594,7 @@ 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);
 
@@ -652,7 +652,7 @@ static void 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);

From 3fdd04592d38bb31a0bea567d9a66672b484bed3 Mon Sep 17 00:00:00 2001
From: Oliver Upton <oupton@google.com>
Date: Wed, 4 May 2022 03:24:39 +0000
Subject: [PATCH 05/13] KVM: arm64: Return a value from check_vcpu_requests()

A subsequent change to KVM will introduce a vCPU request that could
result in an exit to userspace. Change check_vcpu_requests() to return a
value and document the function. Unconditionally return 1 for now.

Signed-off-by: Oliver Upton <oupton@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20220504032446.4133305-6-oupton@google.com
---
 arch/arm64/kvm/arm.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 77b8b870c0fc..efe54aba5cce 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -648,7 +648,16 @@ void kvm_vcpu_wfi(struct kvm_vcpu *vcpu)
 	preempt_enable();
 }
 
-static void check_vcpu_requests(struct kvm_vcpu *vcpu)
+/**
+ * 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))
@@ -678,6 +687,8 @@ static void check_vcpu_requests(struct kvm_vcpu *vcpu)
 			kvm_pmu_handle_pmcr(vcpu,
 					    __vcpu_sys_reg(vcpu, PMCR_EL0));
 	}
+
+	return 1;
 }
 
 static bool vcpu_mode_is_bad_32bit(struct kvm_vcpu *vcpu)
@@ -793,7 +804,8 @@ 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

From 7b33a09d036ffd9a04506122840629c7e870cf08 Mon Sep 17 00:00:00 2001
From: Oliver Upton <oupton@google.com>
Date: Wed, 4 May 2022 03:24:40 +0000
Subject: [PATCH 06/13] KVM: arm64: Add support for userspace to suspend a vCPU

Introduce a new MP state, KVM_MP_STATE_SUSPENDED, which indicates a vCPU
is in a suspended state. In the suspended state the vCPU will block
until a wakeup event (pending interrupt) is recognized.

Add a new system event type, KVM_SYSTEM_EVENT_WAKEUP, to indicate to
userspace that KVM has recognized one such wakeup event. It is the
responsibility of userspace to then make the vCPU runnable, or leave it
suspended until the next wakeup event.

Signed-off-by: Oliver Upton <oupton@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20220504032446.4133305-7-oupton@google.com
---
 Documentation/virt/kvm/api.rst    | 37 ++++++++++++++++++++--
 arch/arm64/include/asm/kvm_host.h |  1 +
 arch/arm64/kvm/arm.c              | 51 +++++++++++++++++++++++++++++++
 include/uapi/linux/kvm.h          |  2 ++
 4 files changed, 89 insertions(+), 2 deletions(-)

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 4a900cdbc62e..46ca84600dca 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/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.
@@ -5985,6 +6014,7 @@ 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
 			__u32 type;
                         __u32 ndata;
                         __u64 data[16];
@@ -6009,6 +6039,9 @@ 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.
 
 If KVM_CAP_SYSTEM_EVENT_DATA is present, the 'data' field can contain
 architecture specific information for the system-level event.  Only
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index f3f93d48e21a..46027b9b80ca 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/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)
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index efe54aba5cce..abd32a84ed7a 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -444,6 +444,18 @@ 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)
 {
@@ -464,6 +476,9 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 	case KVM_MP_STATE_STOPPED:
 		kvm_arm_vcpu_power_off(vcpu);
 		break;
+	case KVM_MP_STATE_SUSPENDED:
+		kvm_arm_vcpu_suspend(vcpu);
+		break;
 	default:
 		ret = -EINVAL;
 	}
@@ -648,6 +663,39 @@ void kvm_vcpu_wfi(struct kvm_vcpu *vcpu)
 	preempt_enable();
 }
 
+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
@@ -686,6 +734,9 @@ static int 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;
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 6a184d260c7f..7f72fb7b05f2 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -444,6 +444,7 @@ 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
 			__u32 type;
 			__u32 ndata;
 			union {
@@ -646,6 +647,7 @@ 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;

From bfbab44568779e1682bc6f63688bb9c965f0e74a Mon Sep 17 00:00:00 2001
From: Oliver Upton <oupton@google.com>
Date: Wed, 4 May 2022 03:24:41 +0000
Subject: [PATCH 07/13] KVM: arm64: Implement PSCI SYSTEM_SUSPEND

ARM DEN0022D.b 5.19 "SYSTEM_SUSPEND" describes a PSCI call that allows
software to request that a system be placed in the deepest possible
low-power state. Effectively, software can use this to suspend itself to
RAM.

Unfortunately, there really is no good way to implement a system-wide
PSCI call in KVM. Any precondition checks done in the kernel will need
to be repeated by userspace since there is no good way to protect a
critical section that spans an exit to userspace. SYSTEM_RESET and
SYSTEM_OFF are equally plagued by this issue, although no users have
seemingly cared for the relatively long time these calls have been
supported.

The solution is to just make the whole implementation userspace's
problem. Introduce a new system event, KVM_SYSTEM_EVENT_SUSPEND, that
indicates to userspace a calling vCPU has invoked PSCI SYSTEM_SUSPEND.
Additionally, add a CAP to get buy-in from userspace for this new exit
type.

Only advertise the SYSTEM_SUSPEND PSCI call if userspace has opted in.
If a vCPU calls SYSTEM_SUSPEND, punt straight to userspace. Provide
explicit documentation of userspace's responsibilites for the exit and
point to the PSCI specification to describe the actual PSCI call.

Reviewed-by: Reiji Watanabe <reijiw@google.com>
Signed-off-by: Oliver Upton <oupton@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20220504032446.4133305-8-oupton@google.com
---
 Documentation/virt/kvm/api.rst    | 39 +++++++++++++++++++++++++++++++
 arch/arm64/include/asm/kvm_host.h |  2 ++
 arch/arm64/kvm/arm.c              |  5 ++++
 arch/arm64/kvm/psci.c             | 29 +++++++++++++++++++++++
 include/uapi/linux/kvm.h          |  2 ++
 5 files changed, 77 insertions(+)

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
 

From 6689fb8f21ecf5fd99278b622c9579ffbc2742c2 Mon Sep 17 00:00:00 2001
From: Oliver Upton <oupton@google.com>
Date: Wed, 4 May 2022 03:24:42 +0000
Subject: [PATCH 08/13] selftests: KVM: Rename psci_cpu_on_test to psci_test

There are other interactions with PSCI worth testing; rename the PSCI
test to make it more generic.

No functional change intended.

Signed-off-by: Oliver Upton <oupton@google.com>
Reviewed-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20220504032446.4133305-9-oupton@google.com
---
 tools/testing/selftests/kvm/.gitignore                          | 2 +-
 tools/testing/selftests/kvm/Makefile                            | 2 +-
 .../selftests/kvm/aarch64/{psci_cpu_on_test.c => psci_test.c}   | 0
 3 files changed, 2 insertions(+), 2 deletions(-)
 rename tools/testing/selftests/kvm/aarch64/{psci_cpu_on_test.c => psci_test.c} (100%)

diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 0b0e4402bba6..1bb575dfc42e 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -2,7 +2,7 @@
 /aarch64/arch_timer
 /aarch64/debug-exceptions
 /aarch64/get-reg-list
-/aarch64/psci_cpu_on_test
+/aarch64/psci_test
 /aarch64/vcpu_width_config
 /aarch64/vgic_init
 /aarch64/vgic_irq
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 681b173aa87c..c2cf4d318296 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -105,7 +105,7 @@ TEST_GEN_PROGS_x86_64 += system_counter_offset_test
 TEST_GEN_PROGS_aarch64 += aarch64/arch_timer
 TEST_GEN_PROGS_aarch64 += aarch64/debug-exceptions
 TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list
-TEST_GEN_PROGS_aarch64 += aarch64/psci_cpu_on_test
+TEST_GEN_PROGS_aarch64 += aarch64/psci_test
 TEST_GEN_PROGS_aarch64 += aarch64/vcpu_width_config
 TEST_GEN_PROGS_aarch64 += aarch64/vgic_init
 TEST_GEN_PROGS_aarch64 += aarch64/vgic_irq
diff --git a/tools/testing/selftests/kvm/aarch64/psci_cpu_on_test.c b/tools/testing/selftests/kvm/aarch64/psci_test.c
similarity index 100%
rename from tools/testing/selftests/kvm/aarch64/psci_cpu_on_test.c
rename to tools/testing/selftests/kvm/aarch64/psci_test.c

From 694e3dcc47471b8b409a0ef647319b746eabcb3a Mon Sep 17 00:00:00 2001
From: Oliver Upton <oupton@google.com>
Date: Wed, 4 May 2022 03:24:43 +0000
Subject: [PATCH 09/13] selftests: KVM: Create helper for making SMCCC calls

The PSCI and PV stolen time tests both need to make SMCCC calls within
the guest. Create a helper for making SMCCC calls and rework the
existing tests to use the library function.

Signed-off-by: Oliver Upton <oupton@google.com>
Reviewed-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20220504032446.4133305-10-oupton@google.com
---
 .../testing/selftests/kvm/aarch64/psci_test.c | 25 ++++++-------------
 .../selftests/kvm/include/aarch64/processor.h | 22 ++++++++++++++++
 .../selftests/kvm/lib/aarch64/processor.c     | 25 +++++++++++++++++++
 tools/testing/selftests/kvm/steal_time.c      | 13 +++-------
 4 files changed, 58 insertions(+), 27 deletions(-)

diff --git a/tools/testing/selftests/kvm/aarch64/psci_test.c b/tools/testing/selftests/kvm/aarch64/psci_test.c
index 4c5f6814030f..8c998f0b802c 100644
--- a/tools/testing/selftests/kvm/aarch64/psci_test.c
+++ b/tools/testing/selftests/kvm/aarch64/psci_test.c
@@ -26,32 +26,23 @@
 static uint64_t psci_cpu_on(uint64_t target_cpu, uint64_t entry_addr,
 			    uint64_t context_id)
 {
-	register uint64_t x0 asm("x0") = PSCI_0_2_FN64_CPU_ON;
-	register uint64_t x1 asm("x1") = target_cpu;
-	register uint64_t x2 asm("x2") = entry_addr;
-	register uint64_t x3 asm("x3") = context_id;
+	struct arm_smccc_res res;
 
-	asm("hvc #0"
-	    : "=r"(x0)
-	    : "r"(x0), "r"(x1), "r"(x2), "r"(x3)
-	    : "memory");
+	smccc_hvc(PSCI_0_2_FN64_CPU_ON, target_cpu, entry_addr, context_id,
+		  0, 0, 0, 0, &res);
 
-	return x0;
+	return res.a0;
 }
 
 static uint64_t psci_affinity_info(uint64_t target_affinity,
 				   uint64_t lowest_affinity_level)
 {
-	register uint64_t x0 asm("x0") = PSCI_0_2_FN64_AFFINITY_INFO;
-	register uint64_t x1 asm("x1") = target_affinity;
-	register uint64_t x2 asm("x2") = lowest_affinity_level;
+	struct arm_smccc_res res;
 
-	asm("hvc #0"
-	    : "=r"(x0)
-	    : "r"(x0), "r"(x1), "r"(x2)
-	    : "memory");
+	smccc_hvc(PSCI_0_2_FN64_AFFINITY_INFO, target_affinity, lowest_affinity_level,
+		  0, 0, 0, 0, 0, &res);
 
-	return x0;
+	return res.a0;
 }
 
 static void guest_main(uint64_t target_cpu)
diff --git a/tools/testing/selftests/kvm/include/aarch64/processor.h b/tools/testing/selftests/kvm/include/aarch64/processor.h
index 8f9f46979a00..59ece9d4e0d1 100644
--- a/tools/testing/selftests/kvm/include/aarch64/processor.h
+++ b/tools/testing/selftests/kvm/include/aarch64/processor.h
@@ -185,4 +185,26 @@ static inline void local_irq_disable(void)
 	asm volatile("msr daifset, #3" : : : "memory");
 }
 
+/**
+ * struct arm_smccc_res - Result from SMC/HVC call
+ * @a0-a3 result values from registers 0 to 3
+ */
+struct arm_smccc_res {
+	unsigned long a0;
+	unsigned long a1;
+	unsigned long a2;
+	unsigned long a3;
+};
+
+/**
+ * smccc_hvc - Invoke a SMCCC function using the hvc conduit
+ * @function_id: the SMCCC function to be called
+ * @arg0-arg6: SMCCC function arguments, corresponding to registers x1-x7
+ * @res: pointer to write the return values from registers x0-x3
+ *
+ */
+void smccc_hvc(uint32_t function_id, uint64_t arg0, uint64_t arg1,
+	       uint64_t arg2, uint64_t arg3, uint64_t arg4, uint64_t arg5,
+	       uint64_t arg6, struct arm_smccc_res *res);
+
 #endif /* SELFTEST_KVM_PROCESSOR_H */
diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
index 9343d82519b4..6a041289fa80 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/processor.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -500,3 +500,28 @@ void __attribute__((constructor)) init_guest_modes(void)
 {
        guest_modes_append_default();
 }
+
+void smccc_hvc(uint32_t function_id, uint64_t arg0, uint64_t arg1,
+	       uint64_t arg2, uint64_t arg3, uint64_t arg4, uint64_t arg5,
+	       uint64_t arg6, struct arm_smccc_res *res)
+{
+	asm volatile("mov   w0, %w[function_id]\n"
+		     "mov   x1, %[arg0]\n"
+		     "mov   x2, %[arg1]\n"
+		     "mov   x3, %[arg2]\n"
+		     "mov   x4, %[arg3]\n"
+		     "mov   x5, %[arg4]\n"
+		     "mov   x6, %[arg5]\n"
+		     "mov   x7, %[arg6]\n"
+		     "hvc   #0\n"
+		     "mov   %[res0], x0\n"
+		     "mov   %[res1], x1\n"
+		     "mov   %[res2], x2\n"
+		     "mov   %[res3], x3\n"
+		     : [res0] "=r"(res->a0), [res1] "=r"(res->a1),
+		       [res2] "=r"(res->a2), [res3] "=r"(res->a3)
+		     : [function_id] "r"(function_id), [arg0] "r"(arg0),
+		       [arg1] "r"(arg1), [arg2] "r"(arg2), [arg3] "r"(arg3),
+		       [arg4] "r"(arg4), [arg5] "r"(arg5), [arg6] "r"(arg6)
+		     : "x0", "x1", "x2", "x3", "x4", "x5", "x6", "x7");
+}
diff --git a/tools/testing/selftests/kvm/steal_time.c b/tools/testing/selftests/kvm/steal_time.c
index 62f2eb9ee3d5..8c4e811bd586 100644
--- a/tools/testing/selftests/kvm/steal_time.c
+++ b/tools/testing/selftests/kvm/steal_time.c
@@ -118,17 +118,10 @@ struct st_time {
 
 static int64_t smccc(uint32_t func, uint64_t arg)
 {
-	unsigned long ret;
+	struct arm_smccc_res res;
 
-	asm volatile(
-		"mov	w0, %w1\n"
-		"mov	x1, %2\n"
-		"hvc	#0\n"
-		"mov	%0, x0\n"
-	: "=r" (ret) : "r" (func), "r" (arg) :
-	  "x0", "x1", "x2", "x3");
-
-	return ret;
+	smccc_hvc(func, arg, 0, 0, 0, 0, 0, 0, &res);
+	return res.a0;
 }
 
 static void check_status(struct st_time *st)

From d135399a97cc3e27716a8e468a5fd1a209346831 Mon Sep 17 00:00:00 2001
From: Oliver Upton <oupton@google.com>
Date: Wed, 4 May 2022 03:24:44 +0000
Subject: [PATCH 10/13] selftests: KVM: Use KVM_SET_MP_STATE to power off vCPU
 in psci_test

Setting a vCPU's MP state to KVM_MP_STATE_STOPPED has the effect of
powering off the vCPU. Rather than using the vCPU init feature flag, use
the KVM_SET_MP_STATE ioctl to power off the target vCPU.

Signed-off-by: Oliver Upton <oupton@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20220504032446.4133305-11-oupton@google.com
---
 tools/testing/selftests/kvm/aarch64/psci_test.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/kvm/aarch64/psci_test.c b/tools/testing/selftests/kvm/aarch64/psci_test.c
index 8c998f0b802c..fe1d5d343a2f 100644
--- a/tools/testing/selftests/kvm/aarch64/psci_test.c
+++ b/tools/testing/selftests/kvm/aarch64/psci_test.c
@@ -60,6 +60,15 @@ static void guest_main(uint64_t target_cpu)
 	GUEST_DONE();
 }
 
+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);
+}
+
 int main(void)
 {
 	uint64_t target_mpidr, obs_pc, obs_x0;
@@ -75,12 +84,12 @@ int main(void)
 	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_TARGET, &init, guest_main);
 
 	/*
 	 * 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);
+	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);

From 67a36a821312e9c0d2a2f7e6c2225204500cc01c Mon Sep 17 00:00:00 2001
From: Oliver Upton <oupton@google.com>
Date: Wed, 4 May 2022 03:24:45 +0000
Subject: [PATCH 11/13] selftests: KVM: Refactor psci_test to make it amenable
 to new tests

Split up the current test into several helpers that will be useful to
subsequent test cases added to the PSCI test suite.

Signed-off-by: Oliver Upton <oupton@google.com>
Reviewed-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20220504032446.4133305-12-oupton@google.com
---
 .../testing/selftests/kvm/aarch64/psci_test.c | 109 +++++++++++-------
 1 file changed, 66 insertions(+), 43 deletions(-)

diff --git a/tools/testing/selftests/kvm/aarch64/psci_test.c b/tools/testing/selftests/kvm/aarch64/psci_test.c
index fe1d5d343a2f..535130d5e97f 100644
--- a/tools/testing/selftests/kvm/aarch64/psci_test.c
+++ b/tools/testing/selftests/kvm/aarch64/psci_test.c
@@ -45,11 +45,64 @@ static uint64_t psci_affinity_info(uint64_t target_affinity,
 	return res.a0;
 }
 
-static void guest_main(uint64_t target_cpu)
+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)
+{
+	struct kvm_vcpu_init init;
+	struct kvm_vm *vm;
+
+	vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR);
+	kvm_vm_elf_load(vm, program_invocation_name);
+	ucall_init(vm, NULL);
+
+	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_code);
+	aarch64_vcpu_add_default(vm, VCPU_ID_TARGET, &init, guest_code);
+
+	return vm;
+}
+
+static void enter_guest(struct kvm_vm *vm, uint32_t vcpuid)
+{
+	struct ucall uc;
+
+	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]);
+}
+
+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)",
+		    obs_pc, CPU_ON_ENTRY_ADDR);
+	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)
 {
-	GUEST_ASSERT(!psci_cpu_on(target_cpu, CPU_ON_ENTRY_ADDR, CPU_ON_CONTEXT_ID));
 	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);
 
@@ -60,31 +113,13 @@ static void guest_main(uint64_t target_cpu)
 	GUEST_DONE();
 }
 
-static void vcpu_power_off(struct kvm_vm *vm, uint32_t vcpuid)
+static void host_test_cpu_on(void)
 {
-	struct kvm_mp_state mp_state = {
-		.mp_state = KVM_MP_STATE_STOPPED,
-	};
-
-	vcpu_set_mp_state(vm, vcpuid, &mp_state);
-}
-
-int main(void)
-{
-	uint64_t target_mpidr, obs_pc, obs_x0;
-	struct kvm_vcpu_init init;
+	uint64_t target_mpidr;
 	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);
-	ucall_init(vm, NULL);
-
-	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_TARGET, &init, guest_main);
+	vm = setup_vm(guest_test_cpu_on);
 
 	/*
 	 * make sure the target is already off when executing the test.
@@ -93,29 +128,17 @@ int main(void)
 
 	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);
+	enter_guest(vm, VCPU_ID_SOURCE);
 
-	switch (get_ucall(vm, VCPU_ID_SOURCE, &uc)) {
-	case UCALL_DONE:
-		break;
-	case UCALL_ABORT:
-		TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], __FILE__,
-			  uc.args[1]);
-		break;
-	default:
+	if (get_ucall(vm, VCPU_ID_SOURCE, &uc) != UCALL_DONE)
 		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);
-
-	TEST_ASSERT(obs_pc == CPU_ON_ENTRY_ADDR,
-		    "unexpected target cpu pc: %lx (expected: %lx)",
-		    obs_pc, CPU_ON_ENTRY_ADDR);
-	TEST_ASSERT(obs_x0 == CPU_ON_CONTEXT_ID,
-		    "unexpected target context id: %lx (expected: %lx)",
-		    obs_x0, CPU_ON_CONTEXT_ID);
 
+	assert_vcpu_reset(vm, VCPU_ID_TARGET);
 	kvm_vm_free(vm);
+}
+
+int main(void)
+{
+	host_test_cpu_on();
 	return 0;
 }

From b26dafc8a9e74254a390e8f21ff028a2573ee4fc Mon Sep 17 00:00:00 2001
From: Oliver Upton <oupton@google.com>
Date: Wed, 4 May 2022 03:24:46 +0000
Subject: [PATCH 12/13] selftests: KVM: Test SYSTEM_SUSPEND PSCI call

Assert that the vCPU exits to userspace with KVM_SYSTEM_EVENT_SUSPEND if
the guest calls PSCI SYSTEM_SUSPEND. Additionally, guarantee that the
SMC32 and SMC64 flavors of this call are discoverable with the
PSCI_FEATURES call.

Signed-off-by: Oliver Upton <oupton@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20220504032446.4133305-13-oupton@google.com
---
 .../testing/selftests/kvm/aarch64/psci_test.c | 69 +++++++++++++++++++
 1 file changed, 69 insertions(+)

diff --git a/tools/testing/selftests/kvm/aarch64/psci_test.c b/tools/testing/selftests/kvm/aarch64/psci_test.c
index 535130d5e97f..88541de21c41 100644
--- a/tools/testing/selftests/kvm/aarch64/psci_test.c
+++ b/tools/testing/selftests/kvm/aarch64/psci_test.c
@@ -45,6 +45,25 @@ static uint64_t psci_affinity_info(uint64_t target_affinity,
 	return res.a0;
 }
 
+static uint64_t psci_system_suspend(uint64_t entry_addr, uint64_t context_id)
+{
+	struct arm_smccc_res res;
+
+	smccc_hvc(PSCI_1_0_FN64_SYSTEM_SUSPEND, entry_addr, context_id,
+		  0, 0, 0, 0, 0, &res);
+
+	return res.a0;
+}
+
+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;
+}
+
 static void vcpu_power_off(struct kvm_vm *vm, uint32_t vcpuid)
 {
 	struct kvm_mp_state mp_state = {
@@ -137,8 +156,58 @@ static void host_test_cpu_on(void)
 	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;
 }

From 582eb04e05ddd234ca32083c8457c6d409fd7b6a Mon Sep 17 00:00:00 2001
From: Stephen Rothwell <sfr@canb.auug.org.au>
Date: Thu, 5 May 2022 20:06:34 +1000
Subject: [PATCH 13/13] Documentation: KVM: Fix title level for PSCI_SUSPEND

The htmldoc build breaks in a funny way with:

<quote>
Sphinx parallel build error:
docutils.utils.SystemMessage: /home/sfr/next/next/Documentation/virt/kvm/api.rst:6175: (SEVERE/4) Title level inconsistent:

For arm/arm64:
^^^^^^^^^^^^^^
</quote>

Swap the ^^s for a bunch of --s...

Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
[maz: commit message]
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 Documentation/virt/kvm/api.rst | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index d8d7859fc556..25253b326730 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -6047,7 +6047,7 @@ Valid values for 'type' are:
    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