Merge branch kvm-arm64/psci-1.3 into kvmarm/next

* kvm-arm64/psci-1.3:
  : PSCI v1.3 support, courtesy of David Woodhouse
  :
  : Bump KVM's PSCI implementation up to v1.3, with the added bonus of
  : implementing the SYSTEM_OFF2 call. Like other system-scoped PSCI calls,
  : this gets relayed to userspace for further processing with a new
  : KVM_SYSTEM_EVENT_SHUTDOWN flag.
  :
  : As an added bonus, implement client-side support for hibernation with
  : the SYSTEM_OFF2 call.
  arm64: Use SYSTEM_OFF2 PSCI call to power off for hibernate
  KVM: arm64: nvhe: Pass through PSCI v1.3 SYSTEM_OFF2 call
  KVM: selftests: Add test for PSCI SYSTEM_OFF2
  KVM: arm64: Add support for PSCI v1.2 and v1.3
  KVM: arm64: Add PSCI v1.3 SYSTEM_OFF2 function for hibernation
  firmware/psci: Add definitions for PSCI v1.3 specification

Signed-off-by: Oliver Upton <oliver.upton@linux.dev>

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 +6892,12 @@ 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.
+
 ::
 
 		/* KVM_EXIT_IOAPIC_EOI */

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)
 

arch/arm64/kvm/hyp/nvhe/psci-relay.c

@@ -265,6 +265,8 @@ static unsigned long psci_1_0_handler(u64 func_id, struct kvm_cpu_context *host_
 	case PSCI_1_0_FN_PSCI_FEATURES:
 	case PSCI_1_0_FN_SET_SUSPEND_MODE:
 	case PSCI_1_1_FN64_SYSTEM_RESET2:
+	case PSCI_1_3_FN_SYSTEM_OFF2:
+	case PSCI_1_3_FN64_SYSTEM_OFF2:
 		return psci_forward(host_ctxt);
 	case PSCI_1_0_FN64_SYSTEM_SUSPEND:
 		return psci_system_suspend(func_id, host_ctxt);

arch/arm64/kvm/hypercalls.c

@@ -575,6 +575,8 @@ int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 		case KVM_ARM_PSCI_0_2:
 		case KVM_ARM_PSCI_1_0:
 		case KVM_ARM_PSCI_1_1:
+		case KVM_ARM_PSCI_1_2:
+		case KVM_ARM_PSCI_1_3:
 			if (!wants_02)
 				return -EINVAL;
 			vcpu->kvm->arch.psci_version = val;

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);
@@ -322,7 +328,7 @@ static int kvm_psci_1_x_call(struct kvm_vcpu *vcpu, u32 minor)
 
 	switch(psci_fn) {
 	case PSCI_0_2_FN_PSCI_VERSION:
-		val = minor == 0 ? KVM_ARM_PSCI_1_0 : KVM_ARM_PSCI_1_1;
+		val = PSCI_VERSION(1, minor);
 		break;
 	case PSCI_1_0_FN_PSCI_FEATURES:
 		arg = smccc_get_arg1(vcpu);
@@ -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 +403,33 @@ 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);
+		/*
+		 * SYSTEM_OFF2 defaults to HIBERNATE_OFF if arg1 is zero. arg2
+		 * 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 the guest after receiving a
+		 * SYSTEM_OFF2 request. Preload a return value of
+		 * INTERNAL_FAILURE should userspace ignore the exit and resume
+		 * the vCPU.
+		 */
+		val = PSCI_RET_INTERNAL_FAILURE;
+		ret = 0;
+		break;
 	default:
 		return kvm_psci_0_2_call(vcpu);
 	}
@@ -449,6 +487,10 @@ int kvm_psci_call(struct kvm_vcpu *vcpu)
 	}
 
 	switch (version) {
+	case KVM_ARM_PSCI_1_3:
+		return kvm_psci_1_x_call(vcpu, 3);
+	case KVM_ARM_PSCI_1_2:
+		return kvm_psci_1_x_call(vcpu, 2);
 	case KVM_ARM_PSCI_1_1:
 		return kvm_psci_1_x_call(vcpu, 1);
 	case KVM_ARM_PSCI_1_0:

drivers/firmware/psci/psci.c

@@ -78,6 +78,7 @@ struct psci_0_1_function_ids get_psci_0_1_function_ids(void)
 
 static u32 psci_cpu_suspend_feature;
 static bool psci_system_reset2_supported;
+static bool psci_system_off2_hibernate_supported;
 
 static inline bool psci_has_ext_power_state(void)
 {
@@ -333,6 +334,36 @@ static void psci_sys_poweroff(void)
 	invoke_psci_fn(PSCI_0_2_FN_SYSTEM_OFF, 0, 0, 0);
 }
 
+#ifdef CONFIG_HIBERNATION
+static int psci_sys_hibernate(struct sys_off_data *data)
+{
+	/*
+	 * If no hibernate type is specified SYSTEM_OFF2 defaults to selecting
+	 * HIBERNATE_OFF.
+	 *
+	 * There are hypervisors in the wild that do not align with the spec and
+	 * reject calls that explicitly provide a hibernate type. For
+	 * compatibility with these nonstandard implementations, pass 0 as the
+	 * type.
+	 */
+	if (system_entering_hibernation())
+		invoke_psci_fn(PSCI_FN_NATIVE(1_3, SYSTEM_OFF2), 0, 0, 0);
+	return NOTIFY_DONE;
+}
+
+static int __init psci_hibernate_init(void)
+{
+	if (psci_system_off2_hibernate_supported) {
+		/* Higher priority than EFI shutdown, but only for hibernate */
+		register_sys_off_handler(SYS_OFF_MODE_POWER_OFF,
+					 SYS_OFF_PRIO_FIRMWARE + 2,
+					 psci_sys_hibernate, NULL);
+	}
+	return 0;
+}
+subsys_initcall(psci_hibernate_init);
+#endif
+
 static int psci_features(u32 psci_func_id)
 {
 	return invoke_psci_fn(PSCI_1_0_FN_PSCI_FEATURES,
@@ -364,6 +395,7 @@ static const struct {
 	PSCI_ID_NATIVE(1_1, SYSTEM_RESET2),
 	PSCI_ID(1_1, MEM_PROTECT),
 	PSCI_ID_NATIVE(1_1, MEM_PROTECT_CHECK_RANGE),
+	PSCI_ID_NATIVE(1_3, SYSTEM_OFF2),
 };
 
 static int psci_debugfs_read(struct seq_file *s, void *data)
@@ -525,6 +557,18 @@ static void __init psci_init_system_reset2(void)
 		psci_system_reset2_supported = true;
 }
 
+static void __init psci_init_system_off2(void)
+{
+	int ret;
+
+	ret = psci_features(PSCI_FN_NATIVE(1_3, SYSTEM_OFF2));
+	if (ret < 0)
+		return;
+
+	if (ret & PSCI_1_3_OFF_TYPE_HIBERNATE_OFF)
+		psci_system_off2_hibernate_supported = true;
+}
+
 static void __init psci_init_system_suspend(void)
 {
 	int ret;
@@ -655,6 +699,7 @@ static int __init psci_probe(void)
 		psci_init_cpu_suspend();
 		psci_init_system_suspend();
 		psci_init_system_reset2();
+		psci_init_system_off2();
 		kvm_init_hyp_services();
 	}
 

include/kvm/arm_psci.h

@@ -14,8 +14,10 @@
 #define KVM_ARM_PSCI_0_2	PSCI_VERSION(0, 2)
 #define KVM_ARM_PSCI_1_0	PSCI_VERSION(1, 0)
 #define KVM_ARM_PSCI_1_1	PSCI_VERSION(1, 1)
+#define KVM_ARM_PSCI_1_2	PSCI_VERSION(1, 2)
+#define KVM_ARM_PSCI_1_3	PSCI_VERSION(1, 3)
 
-#define KVM_ARM_PSCI_LATEST	KVM_ARM_PSCI_1_1
+#define KVM_ARM_PSCI_LATEST	KVM_ARM_PSCI_1_3
 
 static inline int kvm_psci_version(struct kvm_vcpu *vcpu)
 {

include/uapi/linux/psci.h

@@ -59,6 +59,7 @@
 #define PSCI_1_1_FN_SYSTEM_RESET2		PSCI_0_2_FN(18)
 #define PSCI_1_1_FN_MEM_PROTECT			PSCI_0_2_FN(19)
 #define PSCI_1_1_FN_MEM_PROTECT_CHECK_RANGE	PSCI_0_2_FN(20)
+#define PSCI_1_3_FN_SYSTEM_OFF2			PSCI_0_2_FN(21)
 
 #define PSCI_1_0_FN64_CPU_DEFAULT_SUSPEND	PSCI_0_2_FN64(12)
 #define PSCI_1_0_FN64_NODE_HW_STATE		PSCI_0_2_FN64(13)
@@ -68,6 +69,7 @@
 
 #define PSCI_1_1_FN64_SYSTEM_RESET2		PSCI_0_2_FN64(18)
 #define PSCI_1_1_FN64_MEM_PROTECT_CHECK_RANGE	PSCI_0_2_FN64(20)
+#define PSCI_1_3_FN64_SYSTEM_OFF2		PSCI_0_2_FN64(21)
 
 /* PSCI v0.2 power state encoding for CPU_SUSPEND function */
 #define PSCI_0_2_POWER_STATE_ID_MASK		0xffff
@@ -100,6 +102,9 @@
 #define PSCI_1_1_RESET_TYPE_SYSTEM_WARM_RESET	0
 #define PSCI_1_1_RESET_TYPE_VENDOR_START	0x80000000U
 
+/* PSCI v1.3 hibernate type for SYSTEM_OFF2 */
+#define PSCI_1_3_OFF_TYPE_HIBERNATE_OFF		BIT(0)
+
 /* PSCI version decoding (independent of PSCI version) */
 #define PSCI_VERSION_MAJOR_SHIFT		16
 #define PSCI_VERSION_MINOR_MASK			\

kernel/power/hibernate.c

@@ -685,8 +685,11 @@ static void power_down(void)
 		}
 		fallthrough;
 	case HIBERNATION_SHUTDOWN:
-		if (kernel_can_power_off())
+		if (kernel_can_power_off()) {
+			entering_platform_hibernation = true;
 			kernel_power_off();
+			entering_platform_hibernation = false;
+		}
 		break;
 	}
 	kernel_halt();

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

@@ -54,6 +54,15 @@ static uint64_t psci_system_suspend(uint64_t entry_addr, uint64_t context_id)
 	return res.a0;
 }
 
+static uint64_t psci_system_off2(uint64_t type, uint64_t cookie)
+{
+	struct arm_smccc_res res;
+
+	smccc_hvc(PSCI_1_3_FN64_SYSTEM_OFF2, type, cookie, 0, 0, 0, 0, 0, &res);
+
+	return res.a0;
+}
+
 static uint64_t psci_features(uint32_t func_id)
 {
 	struct arm_smccc_res res;
@@ -188,11 +197,94 @@ static void host_test_system_suspend(void)
 	kvm_vm_free(vm);
 }
 
+static void guest_test_system_off2(void)
+{
+	uint64_t ret;
+
+	/* assert that SYSTEM_OFF2 is discoverable */
+	GUEST_ASSERT(psci_features(PSCI_1_3_FN_SYSTEM_OFF2) &
+		     PSCI_1_3_OFF_TYPE_HIBERNATE_OFF);
+	GUEST_ASSERT(psci_features(PSCI_1_3_FN64_SYSTEM_OFF2) &
+		     PSCI_1_3_OFF_TYPE_HIBERNATE_OFF);
+
+	/* With non-zero 'cookie' field, it should fail */
+	ret = psci_system_off2(PSCI_1_3_OFF_TYPE_HIBERNATE_OFF, 1);
+	GUEST_ASSERT(ret == PSCI_RET_INVALID_PARAMS);
+
+	/*
+	 * This would normally never return, so KVM sets the return value
+	 * to PSCI_RET_INTERNAL_FAILURE. The test case *does* return, so
+	 * that it can test both values for HIBERNATE_OFF.
+	 */
+	ret = psci_system_off2(PSCI_1_3_OFF_TYPE_HIBERNATE_OFF, 0);
+	GUEST_ASSERT(ret == PSCI_RET_INTERNAL_FAILURE);
+
+	/*
+	 * Revision F.b of the PSCI v1.3 specification documents zero as an
+	 * alias for HIBERNATE_OFF, since that's the value used in earlier
+	 * revisions of the spec and some implementations in the field.
+	 */
+	ret = psci_system_off2(0, 1);
+	GUEST_ASSERT(ret == PSCI_RET_INVALID_PARAMS);
+
+	ret = psci_system_off2(0, 0);
+	GUEST_ASSERT(ret == PSCI_RET_INTERNAL_FAILURE);
+
+	GUEST_DONE();
+}
+
+static void host_test_system_off2(void)
+{
+	struct kvm_vcpu *source, *target;
+	struct kvm_mp_state mps;
+	uint64_t psci_version = 0;
+	int nr_shutdowns = 0;
+	struct kvm_run *run;
+	struct ucall uc;
+
+	setup_vm(guest_test_system_off2, &source, &target);
+
+	vcpu_get_reg(target, KVM_REG_ARM_PSCI_VERSION, &psci_version);
+
+	TEST_ASSERT(psci_version >= PSCI_VERSION(1, 3),
+		    "Unexpected PSCI version %lu.%lu",
+		    PSCI_VERSION_MAJOR(psci_version),
+		    PSCI_VERSION_MINOR(psci_version));
+
+	vcpu_power_off(target);
+	run = source->run;
+
+	enter_guest(source);
+	while (run->exit_reason == KVM_EXIT_SYSTEM_EVENT) {
+		TEST_ASSERT(run->system_event.type == KVM_SYSTEM_EVENT_SHUTDOWN,
+			    "Unhandled system event: %u (expected: %u)",
+			    run->system_event.type, KVM_SYSTEM_EVENT_SHUTDOWN);
+		TEST_ASSERT(run->system_event.ndata >= 1,
+			    "Unexpected amount of system event data: %u (expected, >= 1)",
+			    run->system_event.ndata);
+		TEST_ASSERT(run->system_event.data[0] & KVM_SYSTEM_EVENT_SHUTDOWN_FLAG_PSCI_OFF2,
+			    "PSCI_OFF2 flag not set. Flags %llu (expected %llu)",
+			    run->system_event.data[0], KVM_SYSTEM_EVENT_SHUTDOWN_FLAG_PSCI_OFF2);
+
+		nr_shutdowns++;
+
+		/* Restart the vCPU */
+	        mps.mp_state = KVM_MP_STATE_RUNNABLE;
+		vcpu_mp_state_set(source, &mps);
+
+		enter_guest(source);
+	}
+
+	TEST_ASSERT(get_ucall(source, &uc) == UCALL_DONE, "Guest did not exit cleanly");
+	TEST_ASSERT(nr_shutdowns == 2, "Two shutdown events were expected, but saw %d", nr_shutdowns);
+}
+
 int main(void)
 {
 	TEST_REQUIRE(kvm_has_cap(KVM_CAP_ARM_SYSTEM_SUSPEND));
 
 	host_test_cpu_on();
 	host_test_system_suspend();
+	host_test_system_off2();
 	return 0;
 }