Received-SPF: pass (google.com: domain of linux-kernel+bounces-100312-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45d1:ec00::1 as permitted sender) client-ip=2604:1380:45d1:ec00::1;
From: David Woodhouse <dwmw2@infradead.org>
To: linux-arm-kernel@lists.infradead.org,
	kvm@vger.kernel.org
Cc: Paolo Bonzini <pbonzini@redhat.com>,
	Jonathan Corbet <corbet@lwn.net>,
	Marc Zyngier <maz@kernel.org>,
	Oliver Upton <oliver.upton@linux.dev>,
	James Morse <james.morse@arm.com>,
	Suzuki K Poulose <suzuki.poulose@arm.com>,
	Zenghui Yu <yuzenghui@huawei.com>,
	Catalin Marinas <catalin.marinas@arm.com>,
	Will Deacon <will@kernel.org>,
	Mark Rutland <mark.rutland@arm.com>,
	Lorenzo Pieralisi <lpieralisi@kernel.org>,
	"Rafael J. Wysocki" <rafael@kernel.org>,
	Len Brown <len.brown@intel.com>,
	Pavel Machek <pavel@ucw.cz>,
	David Woodhouse <dwmw@amazon.co.uk>,
	Mostafa Saleh <smostafa@google.com>,
	Jean-Philippe Brucker <jean-philippe@linaro.org>,
	linux-doc@vger.kernel.org,
	linux-kernel@vger.kernel.org,
	kvmarm@lists.linux.dev,
	linux-pm@vger.kernel.org
Subject: [RFC PATCH 2/2] arm64: Use SYSTEM_OFF2 PSCI call to power off for hibernate
Date: Tue, 12 Mar 2024 13:51:29 +0000
Message-ID: <20240312135958.727765-3-dwmw2@infradead.org>
In-Reply-To: <20240312135958.727765-1-dwmw2@infradead.org>
References: <20240312135958.727765-1-dwmw2@infradead.org>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Sender: David Woodhouse <dwmw2@infradead.org>

From: David Woodhouse <dwmw@amazon.co.uk>

The PSCI v1.3 specification (alpha) 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 <dwmw@amazon.co.uk>
---
 drivers/firmware/psci/psci.c | 35 +++++++++++++++++++++++++++++++++++
 kernel/power/hibernate.c     |  5 ++++-
 2 files changed, 39 insertions(+), 1 deletion(-)

diff --git a/drivers/firmware/psci/psci.c b/drivers/firmware/psci/psci.c
index d9629ff87861..69d2f6969438 100644
--- a/drivers/firmware/psci/psci.c
+++ b/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_supported;
 
 static inline bool psci_has_ext_power_state(void)
 {
@@ -333,6 +334,28 @@ 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 (system_entering_hibernation())
+		invoke_psci_fn(PSCI_FN_NATIVE(1_3, SYSTEM_OFF2),
+			       PSCI_1_3_HIBERNATE_TYPE_OFF, 0, 0);
+	return NOTIFY_DONE;
+}
+
+static int __init psci_hibernate_init(void)
+{
+	if (psci_system_off2_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 +387,7 @@ 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)
@@ -523,6 +547,16 @@ 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 != PSCI_RET_NOT_SUPPORTED)
+		psci_system_off2_supported = true;
+}
+
 static void __init psci_init_system_suspend(void)
 {
 	int ret;
@@ -653,6 +687,7 @@ 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();
 	}
 
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 4b0b7cf2e019..ac87b3cb670c 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -676,8 +676,11 @@ 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();
-- 
2.44.0