arm64: Use SYSTEM_OFF2 PSCI call to power off for hibernate

The PSCI v1.3 specification adds support for a SYSTEM_OFF2 function
which is analogous to ACPI S4 state. This will allow hosting
environments to determine that a guest is hibernated rather than just
powered off, and handle that state appropriately on subsequent launches.

Since commit 60c0d45a7f7a ("efi/arm64: use UEFI for system reset and
poweroff") the EFI shutdown method is deliberately preferred over PSCI
or other methods. So register a SYS_OFF_MODE_POWER_OFF handler which
*only* handles the hibernation, leaving the original PSCI SYSTEM_OFF as
a last resort via the legacy pm_power_off function pointer.

The hibernation code already exports a system_entering_hibernation()
function which is be used by the higher-priority handler to check for
hibernation. That existing function just returns the value of a static
boolean variable from hibernate.c, which was previously only set in the
hibernation_platform_enter() code path. Set the same flag in the simpler
code path around the call to kernel_power_off() too.

An alternative way to hook SYSTEM_OFF2 into the hibernation code would
be to register a platform_hibernation_ops structure with an ->enter()
method which makes the new SYSTEM_OFF2 call. But that would have the
unwanted side-effect of making hibernation take a completely different
code path in hibernation_platform_enter(), invoking a lot of special dpm
callbacks.

Another option might be to add a new SYS_OFF_MODE_HIBERNATE mode, with
fallback to SYS_OFF_MODE_POWER_OFF. Or to use the sys_off_data to
indicate whether the power off is for hibernation.

But this version works and is relatively simple.

Signed-off-by: David Woodhouse <[e-mail]>
Acked-by: Rafael J. Wysocki <[e-mail]>
Acked-by: Catalin Marinas <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Oliver Upton <[e-mail]>

drivers/firmware/psci/psci.c

···
 
 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)
 {
···
 	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,
···
 	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)
···
 		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;
···
 		psci_init_cpu_suspend();
 		psci_init_system_suspend();
 		psci_init_system_reset2();
+		psci_init_system_off2();
 		kvm_init_hyp_services();
 	}
 

kernel/power/hibernate.c

···
 		}
 		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();