Merge tag 'pm-5.19-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management fixes from Rafael Wysocki:
 "These fix an intel_idle issue introduced during the 5.16 development
  cycle and two recent regressions in the system reboot/poweroff code.

  Specifics:

   - Fix CPUIDLE_FLAG_IRQ_ENABLE handling in intel_idle (Peter Zijlstra)

   - Allow all platforms to use the global poweroff handler and make
     non-syscall poweroff code paths work again (Dmitry Osipenko)"

* tag 'pm-5.19-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  cpuidle,intel_idle: Fix CPUIDLE_FLAG_IRQ_ENABLE
  kernel/reboot: Fix powering off using a non-syscall code paths
  kernel/reboot: Use static handler for register_platform_power_off()

2 files changed, 87 insertions, 32 deletions

diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index b9bb94bd0f67..424ef470223d 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -115,6 +115,18 @@ static unsigned int mwait_substates __initdata;
 #define flg2MWAIT(flags) (((flags) >> 24) & 0xFF)
 #define MWAIT2flg(eax) ((eax & 0xFF) << 24)
 
+static __always_inline int __intel_idle(struct cpuidle_device *dev,
+					struct cpuidle_driver *drv, int index)
+{
+	struct cpuidle_state *state = &drv->states[index];
+	unsigned long eax = flg2MWAIT(state->flags);
+	unsigned long ecx = 1; /* break on interrupt flag */
+
+	mwait_idle_with_hints(eax, ecx);
+
+	return index;
+}
+
 /**
  * intel_idle - Ask the processor to enter the given idle state.
  * @dev: cpuidle device of the target CPU.
@@ -132,16 +144,19 @@ static unsigned int mwait_substates __initdata;
 static __cpuidle int intel_idle(struct cpuidle_device *dev,
 				struct cpuidle_driver *drv, int index)
 {
-	struct cpuidle_state *state = &drv->states[index];
-	unsigned long eax = flg2MWAIT(state->flags);
-	unsigned long ecx = 1; /* break on interrupt flag */
+	return __intel_idle(dev, drv, index);
+}
 
-	if (state->flags & CPUIDLE_FLAG_IRQ_ENABLE)
-		local_irq_enable();
+static __cpuidle int intel_idle_irq(struct cpuidle_device *dev,
+				    struct cpuidle_driver *drv, int index)
+{
+	int ret;
 
-	mwait_idle_with_hints(eax, ecx);
+	raw_local_irq_enable();
+	ret = __intel_idle(dev, drv, index);
+	raw_local_irq_disable();
 
-	return index;
+	return ret;
 }
 
 /**
@@ -1801,6 +1816,9 @@ static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv)
 		/* Structure copy. */
 		drv->states[drv->state_count] = cpuidle_state_table[cstate];
 
+		if (cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_IRQ_ENABLE)
+			drv->states[drv->state_count].enter = intel_idle_irq;
+
 		if ((disabled_states_mask & BIT(drv->state_count)) ||
 		    ((icpu->use_acpi || force_use_acpi) &&
 		     intel_idle_off_by_default(mwait_hint) &&
diff --git a/kernel/reboot.c b/kernel/reboot.c
index a091145ee710..b5a71d1ff603 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -315,6 +315,43 @@ static int sys_off_notify(struct notifier_block *nb,
 	return handler->sys_off_cb(&data);
 }
 
+static struct sys_off_handler platform_sys_off_handler;
+
+static struct sys_off_handler *alloc_sys_off_handler(int priority)
+{
+	struct sys_off_handler *handler;
+	gfp_t flags;
+
+	/*
+	 * Platforms like m68k can't allocate sys_off handler dynamically
+	 * at the early boot time because memory allocator isn't available yet.
+	 */
+	if (priority == SYS_OFF_PRIO_PLATFORM) {
+		handler = &platform_sys_off_handler;
+		if (handler->cb_data)
+			return ERR_PTR(-EBUSY);
+	} else {
+		if (system_state > SYSTEM_RUNNING)
+			flags = GFP_ATOMIC;
+		else
+			flags = GFP_KERNEL;
+
+		handler = kzalloc(sizeof(*handler), flags);
+		if (!handler)
+			return ERR_PTR(-ENOMEM);
+	}
+
+	return handler;
+}
+
+static void free_sys_off_handler(struct sys_off_handler *handler)
+{
+	if (handler == &platform_sys_off_handler)
+		memset(handler, 0, sizeof(*handler));
+	else
+		kfree(handler);
+}
+
 /**
  *	register_sys_off_handler - Register sys-off handler
  *	@mode: Sys-off mode
@@ -345,9 +382,9 @@ register_sys_off_handler(enum sys_off_mode mode,
 	struct sys_off_handler *handler;
 	int err;
 
-	handler = kzalloc(sizeof(*handler), GFP_KERNEL);
-	if (!handler)
-		return ERR_PTR(-ENOMEM);
+	handler = alloc_sys_off_handler(priority);
+	if (IS_ERR(handler))
+		return handler;
 
 	switch (mode) {
 	case SYS_OFF_MODE_POWER_OFF_PREPARE:
@@ -364,7 +401,7 @@ register_sys_off_handler(enum sys_off_mode mode,
 		break;
 
 	default:
-		kfree(handler);
+		free_sys_off_handler(handler);
 		return ERR_PTR(-EINVAL);
 	}
 
@@ -391,7 +428,7 @@ register_sys_off_handler(enum sys_off_mode mode,
 	}
 
 	if (err) {
-		kfree(handler);
+		free_sys_off_handler(handler);
 		return ERR_PTR(err);
 	}
 
@@ -409,7 +446,7 @@ void unregister_sys_off_handler(struct sys_off_handler *handler)
 {
 	int err;
 
-	if (!handler)
+	if (IS_ERR_OR_NULL(handler))
 		return;
 
 	if (handler->blocking)
@@ -422,7 +459,7 @@ void unregister_sys_off_handler(struct sys_off_handler *handler)
 	/* sanity check, shall never happen */
 	WARN_ON(err);
 
-	kfree(handler);
+	free_sys_off_handler(handler);
 }
 EXPORT_SYMBOL_GPL(unregister_sys_off_handler);
 
@@ -584,7 +621,23 @@ static void do_kernel_power_off_prepare(void)
  */
 void do_kernel_power_off(void)
 {
+	struct sys_off_handler *sys_off = NULL;
+
+	/*
+	 * Register sys-off handlers for legacy PM callback. This allows
+	 * legacy PM callbacks temporary co-exist with the new sys-off API.
+	 *
+	 * TODO: Remove legacy handlers once all legacy PM users will be
+	 *       switched to the sys-off based APIs.
+	 */
+	if (pm_power_off)
+		sys_off = register_sys_off_handler(SYS_OFF_MODE_POWER_OFF,
+						   SYS_OFF_PRIO_DEFAULT,
+						   legacy_pm_power_off, NULL);
+
 	atomic_notifier_call_chain(&power_off_handler_list, 0, NULL);
+
+	unregister_sys_off_handler(sys_off);
 }
 
 /**
@@ -595,7 +648,8 @@ void do_kernel_power_off(void)
  */
 bool kernel_can_power_off(void)
 {
-	return !atomic_notifier_call_chain_is_empty(&power_off_handler_list);
+	return !atomic_notifier_call_chain_is_empty(&power_off_handler_list) ||
+		pm_power_off;
 }
 EXPORT_SYMBOL_GPL(kernel_can_power_off);
 
@@ -630,7 +684,6 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
 		void __user *, arg)
 {
 	struct pid_namespace *pid_ns = task_active_pid_ns(current);
-	struct sys_off_handler *sys_off = NULL;
 	char buffer[256];
 	int ret = 0;
 
@@ -655,21 +708,6 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
 	if (ret)
 		return ret;
 
-	/*
-	 * Register sys-off handlers for legacy PM callback. This allows
-	 * legacy PM callbacks temporary co-exist with the new sys-off API.
-	 *
-	 * TODO: Remove legacy handlers once all legacy PM users will be
-	 *       switched to the sys-off based APIs.
-	 */
-	if (pm_power_off) {
-		sys_off = register_sys_off_handler(SYS_OFF_MODE_POWER_OFF,
-						   SYS_OFF_PRIO_DEFAULT,
-						   legacy_pm_power_off, NULL);
-		if (IS_ERR(sys_off))
-			return PTR_ERR(sys_off);
-	}
-
 	/* Instead of trying to make the power_off code look like
 	 * halt when pm_power_off is not set do it the easy way.
 	 */
@@ -727,7 +765,6 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
 		break;
 	}
 	mutex_unlock(&system_transition_mutex);
-	unregister_sys_off_handler(sys_off);
 	return ret;
 }