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

3 files changed, 36 insertions, 0 deletions

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;