Merge branch 'pm-sysoff'

Merge system power off handling rework from Dmitry Osipenko for
5.19-rc1.

This introduces a mechanism allowing power sequences to be used for
powering off the system and makes related changes in platform-specific
code for multiple platforms.

* pm-sysoff: (29 commits)
  kernel/reboot: Change registration order of legacy power-off handler
  m68k: virt: Switch to new sys-off handler API
  kernel/reboot: Add devm_register_restart_handler()
  kernel/reboot: Add devm_register_power_off_handler()
  soc/tegra: pmc: Use sys-off handler API to power off Nexus 7 properly
  reboot: Remove pm_power_off_prepare()
  regulator: pfuze100: Use devm_register_sys_off_handler()
  ACPI: power: Switch to sys-off handler API
  memory: emif: Use kernel_can_power_off()
  mips: Use do_kernel_power_off()
  ia64: Use do_kernel_power_off()
  x86: Use do_kernel_power_off()
  sh: Use do_kernel_power_off()
  m68k: Switch to new sys-off handler API
  powerpc: Use do_kernel_power_off()
  xen/x86: Use do_kernel_power_off()
  parisc: Use do_kernel_power_off()
  arm64: Use do_kernel_power_off()
  riscv: Use do_kernel_power_off()
  csky: Use do_kernel_power_off()
  ...

arch/arm/kernel/reboot.c

@@ -116,9 +116,7 @@ void machine_power_off(void)
 {
 	local_irq_disable();
 	smp_send_stop();
-
-	if (pm_power_off)
-		pm_power_off();
+	do_kernel_power_off();
 }
 
 /*

arch/arm64/kernel/process.c

@@ -111,8 +111,7 @@ void machine_power_off(void)
 {
 	local_irq_disable();
 	smp_send_stop();
-	if (pm_power_off)
-		pm_power_off();
+	do_kernel_power_off();
 }
 
 /*

arch/csky/kernel/power.c

@@ -9,16 +9,14 @@ EXPORT_SYMBOL(pm_power_off);
 void machine_power_off(void)
 {
 	local_irq_disable();
-	if (pm_power_off)
-		pm_power_off();
+	do_kernel_power_off();
 	asm volatile ("bkpt");
 }
 
 void machine_halt(void)
 {
 	local_irq_disable();
-	if (pm_power_off)
-		pm_power_off();
+	do_kernel_power_off();
 	asm volatile ("bkpt");
 }
 

arch/ia64/kernel/process.c

@@ -19,6 +19,7 @@
 #include <linux/module.h>
 #include <linux/notifier.h>
 #include <linux/personality.h>
+#include <linux/reboot.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/hotplug.h>
@@ -599,8 +600,7 @@ machine_halt (void)
 void
 machine_power_off (void)
 {
-	if (pm_power_off)
-		pm_power_off();
+	do_kernel_power_off();
 	machine_halt();
 }
 

arch/m68k/emu/natfeat.c

@@ -15,6 +15,7 @@
 #include <linux/string.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/reboot.h>
 #include <linux/io.h>
 #include <asm/machdep.h>
 #include <asm/natfeat.h>
@@ -90,5 +91,5 @@ void __init nf_init(void)
 	pr_info("NatFeats found (%s, %lu.%lu)\n", buf, version >> 16,
 		version & 0xffff);
 
-	mach_power_off = nf_poweroff;
+	register_platform_power_off(nf_poweroff);
 }

arch/m68k/include/asm/machdep.h

@@ -24,7 +24,6 @@ extern int (*mach_get_rtc_pll)(struct rtc_pll_info *);
 extern int (*mach_set_rtc_pll)(struct rtc_pll_info *);
 extern void (*mach_reset)( void );
 extern void (*mach_halt)( void );
-extern void (*mach_power_off)( void );
 extern unsigned long (*mach_hd_init) (unsigned long, unsigned long);
 extern void (*mach_hd_setup)(char *, int *);
 extern void (*mach_heartbeat) (int);

arch/m68k/kernel/process.c

@@ -67,12 +67,11 @@ void machine_halt(void)
 
 void machine_power_off(void)
 {
-	if (mach_power_off)
-		mach_power_off();
+	do_kernel_power_off();
 	for (;;);
 }
 
-void (*pm_power_off)(void) = machine_power_off;
+void (*pm_power_off)(void);
 EXPORT_SYMBOL(pm_power_off);
 
 void show_regs(struct pt_regs * regs)

arch/m68k/kernel/setup_mm.c

@@ -98,7 +98,6 @@ EXPORT_SYMBOL(mach_get_rtc_pll);
 EXPORT_SYMBOL(mach_set_rtc_pll);
 void (*mach_reset)( void );
 void (*mach_halt)( void );
-void (*mach_power_off)( void );
 #ifdef CONFIG_HEARTBEAT
 void (*mach_heartbeat) (int);
 EXPORT_SYMBOL(mach_heartbeat);

arch/m68k/kernel/setup_no.c

@@ -55,7 +55,6 @@ int (*mach_hwclk) (int, struct rtc_time*);
 /* machine dependent reboot functions */
 void (*mach_reset)(void);
 void (*mach_halt)(void);
-void (*mach_power_off)(void);
 
 #ifdef CONFIG_M68000
 #if defined(CONFIG_M68328)

arch/m68k/mac/config.c

@@ -12,6 +12,7 @@
 
 #include <linux/errno.h>
 #include <linux/module.h>
+#include <linux/reboot.h>
 #include <linux/types.h>
 #include <linux/mm.h>
 #include <linux/tty.h>
@@ -140,7 +141,6 @@ void __init config_mac(void)
 	mach_hwclk = mac_hwclk;
 	mach_reset = mac_reset;
 	mach_halt = mac_poweroff;
-	mach_power_off = mac_poweroff;
 #if IS_ENABLED(CONFIG_INPUT_M68K_BEEP)
 	mach_beep = mac_mksound;
 #endif
@@ -160,6 +160,8 @@ void __init config_mac(void)
 
 	if (macintosh_config->ident == MAC_MODEL_IICI)
 		mach_l2_flush = via_l2_flush;
+
+	register_platform_power_off(mac_poweroff);
 }
 
 

arch/m68k/virt/config.c

 // SPDX-License-Identifier: GPL-2.0
 
+#include <linux/reboot.h>
 #include <linux/serial_core.h>
 #include <clocksource/timer-goldfish.h>
 
@@ -126,5 +127,6 @@ void __init config_virt(void)
 	mach_get_model = virt_get_model;
 	mach_reset = virt_reset;
 	mach_halt = virt_halt;
-	mach_power_off = virt_halt;
+
+	register_platform_power_off(virt_halt);
 }

arch/mips/kernel/reset.c

@@ -114,8 +114,7 @@ void machine_halt(void)
 
 void machine_power_off(void)
 {
-	if (pm_power_off)
-		pm_power_off();
+	do_kernel_power_off();
 
 #ifdef CONFIG_SMP
 	preempt_disable();

arch/parisc/kernel/process.c

@@ -26,6 +26,7 @@
 #include <linux/module.h>
 #include <linux/personality.h>
 #include <linux/ptrace.h>
+#include <linux/reboot.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task.h>
@@ -116,8 +117,7 @@ void machine_power_off(void)
 	pdc_chassis_send_status(PDC_CHASSIS_DIRECT_SHUTDOWN);
 
 	/* ipmi_poweroff may have been installed. */
-	if (pm_power_off)
-		pm_power_off();
+	do_kernel_power_off();
 		
 	/* It seems we have no way to power the system off via
 	 * software. The user has to press the button himself. */

arch/powerpc/kernel/setup-common.c

@@ -161,9 +161,7 @@ void machine_restart(char *cmd)
 void machine_power_off(void)
 {
 	machine_shutdown();
-	if (pm_power_off)
-		pm_power_off();
-
+	do_kernel_power_off();
 	smp_send_stop();
 	machine_hang();
 }

arch/powerpc/xmon/xmon.c

@@ -1243,8 +1243,7 @@ static void bootcmds(void)
 	} else if (cmd == 'h') {
 		ppc_md.halt();
 	} else if (cmd == 'p') {
-		if (pm_power_off)
-			pm_power_off();
+		do_kernel_power_off();
 	}
 }
 

arch/riscv/kernel/reset.c

@@ -23,16 +23,12 @@ void machine_restart(char *cmd)
 
 void machine_halt(void)
 {
-	if (pm_power_off != NULL)
-		pm_power_off();
-	else
+	do_kernel_power_off();
 	default_power_off();
 }
 
 void machine_power_off(void)
 {
-	if (pm_power_off != NULL)
-		pm_power_off();
-	else
+	do_kernel_power_off();
 	default_power_off();
 }

arch/sh/kernel/reboot.c

@@ -46,8 +46,7 @@ static void native_machine_shutdown(void)
 
 static void native_machine_power_off(void)
 {
-	if (pm_power_off)
-		pm_power_off();
+	do_kernel_power_off();
 }
 
 static void native_machine_halt(void)

arch/x86/kernel/reboot.c

@@ -739,10 +739,10 @@ static void native_machine_halt(void)
 
 static void native_machine_power_off(void)
 {
-	if (pm_power_off) {
+	if (kernel_can_power_off()) {
 		if (!reboot_force)
 			machine_shutdown();
-		pm_power_off();
+		do_kernel_power_off();
 	}
 	/* A fallback in case there is no PM info available */
 	tboot_shutdown(TB_SHUTDOWN_HALT);

arch/x86/xen/enlighten_pv.c

@@ -30,6 +30,7 @@
 #include <linux/pci.h>
 #include <linux/gfp.h>
 #include <linux/edd.h>
+#include <linux/reboot.h>
 
 #include <xen/xen.h>
 #include <xen/events.h>
@@ -1069,8 +1070,7 @@ static void xen_machine_halt(void)
 
 static void xen_machine_power_off(void)
 {
-	if (pm_power_off)
-		pm_power_off();
+	do_kernel_power_off();
 	xen_reboot(SHUTDOWN_poweroff);
 }
 

drivers/acpi/sleep.c

@@ -1035,20 +1035,22 @@ static void acpi_sleep_hibernate_setup(void)
 static inline void acpi_sleep_hibernate_setup(void) {}
 #endif /* !CONFIG_HIBERNATION */
 
-static void acpi_power_off_prepare(void)
+static int acpi_power_off_prepare(struct sys_off_data *data)
 {
 	/* Prepare to power off the system */
 	acpi_sleep_prepare(ACPI_STATE_S5);
 	acpi_disable_all_gpes();
 	acpi_os_wait_events_complete();
+	return NOTIFY_DONE;
 }
 
-static void acpi_power_off(void)
+static int acpi_power_off(struct sys_off_data *data)
 {
 	/* acpi_sleep_prepare(ACPI_STATE_S5) should have already been called */
 	pr_debug("%s called\n", __func__);
 	local_irq_disable();
 	acpi_enter_sleep_state(ACPI_STATE_S5);
+	return NOTIFY_DONE;
 }
 
 int __init acpi_sleep_init(void)
@@ -1067,8 +1069,14 @@ int __init acpi_sleep_init(void)
 
 	if (acpi_sleep_state_supported(ACPI_STATE_S5)) {
 		sleep_states[ACPI_STATE_S5] = 1;
-		pm_power_off_prepare = acpi_power_off_prepare;
-		pm_power_off = acpi_power_off;
+
+		register_sys_off_handler(SYS_OFF_MODE_POWER_OFF_PREPARE,
+					 SYS_OFF_PRIO_FIRMWARE,
+					 acpi_power_off_prepare, NULL);
+
+		register_sys_off_handler(SYS_OFF_MODE_POWER_OFF,
+					 SYS_OFF_PRIO_FIRMWARE,
+					 acpi_power_off, NULL);
 	} else {
 		acpi_no_s5 = true;
 	}

drivers/memory/emif.c

@@ -630,7 +630,7 @@ static irqreturn_t emif_threaded_isr(int irq, void *dev_id)
 		dev_emerg(emif->dev, "SDRAM temperature exceeds operating limit.. Needs shut down!!!\n");
 
 		/* If we have Power OFF ability, use it, else try restarting */
-		if (pm_power_off) {
+		if (kernel_can_power_off()) {
 			kernel_power_off();
 		} else {
 			WARN(1, "FIXME: NO pm_power_off!!! trying restart\n");

drivers/regulator/pfuze100-regulator.c

@@ -10,6 +10,7 @@
 #include <linux/of_device.h>
 #include <linux/regulator/of_regulator.h>
 #include <linux/platform_device.h>
+#include <linux/reboot.h>
 #include <linux/regulator/driver.h>
 #include <linux/regulator/machine.h>
 #include <linux/regulator/pfuze100.h>
@@ -571,10 +572,10 @@ static inline struct device_node *match_of_node(int index)
 	return pfuze_matches[index].of_node;
 }
 
-static struct pfuze_chip *syspm_pfuze_chip;
-
-static void pfuze_power_off_prepare(void)
+static int pfuze_power_off_prepare(struct sys_off_data *data)
 {
+	struct pfuze_chip *syspm_pfuze_chip = data->cb_data;
+
 	dev_info(syspm_pfuze_chip->dev, "Configure standby mode for power off");
 
 	/* Switch from default mode: APS/APS to APS/Off */
@@ -609,28 +610,30 @@ static void pfuze_power_off_prepare(void)
 	regmap_update_bits(syspm_pfuze_chip->regmap, PFUZE100_VGEN6VOL,
 			   PFUZE100_VGENxLPWR | PFUZE100_VGENxSTBY,
 			   PFUZE100_VGENxSTBY);
+
+	return NOTIFY_DONE;
 }
 
 static int pfuze_power_off_prepare_init(struct pfuze_chip *pfuze_chip)
 {
+	int err;
+
 	if (pfuze_chip->chip_id != PFUZE100) {
 		dev_warn(pfuze_chip->dev, "Requested pm_power_off_prepare handler for not supported chip\n");
 		return -ENODEV;
 	}
 
-	if (pm_power_off_prepare) {
-		dev_warn(pfuze_chip->dev, "pm_power_off_prepare is already registered.\n");
-		return -EBUSY;
+	err = devm_register_sys_off_handler(pfuze_chip->dev,
+					    SYS_OFF_MODE_POWER_OFF_PREPARE,
+					    SYS_OFF_PRIO_DEFAULT,
+					    pfuze_power_off_prepare,
+					    pfuze_chip);
+	if (err) {
+		dev_err(pfuze_chip->dev, "failed to register sys-off handler: %d\n",
+			err);
+		return err;
 	}
 
-	if (syspm_pfuze_chip) {
-		dev_warn(pfuze_chip->dev, "syspm_pfuze_chip is already set.\n");
-		return -EBUSY;
-	}
-
-	syspm_pfuze_chip = pfuze_chip;
-	pm_power_off_prepare = pfuze_power_off_prepare;
-
 	return 0;
 }
 
@@ -839,23 +842,12 @@ static int pfuze100_regulator_probe(struct i2c_client *client,
 	return 0;
 }
 
-static int pfuze100_regulator_remove(struct i2c_client *client)
-{
-	if (syspm_pfuze_chip) {
-		syspm_pfuze_chip = NULL;
-		pm_power_off_prepare = NULL;
-	}
-
-	return 0;
-}
-
 static struct i2c_driver pfuze_driver = {
 	.driver = {
 		.name = "pfuze100-regulator",
 		.of_match_table = pfuze_dt_ids,
 	},
 	.probe = pfuze100_regulator_probe,
-	.remove = pfuze100_regulator_remove,
 };
 module_i2c_driver(pfuze_driver);
 

drivers/soc/tegra/pmc.c

@@ -39,6 +39,7 @@
 #include <linux/platform_device.h>
 #include <linux/pm_domain.h>
 #include <linux/pm_opp.h>
+#include <linux/power_supply.h>
 #include <linux/reboot.h>
 #include <linux/regmap.h>
 #include <linux/reset.h>
@@ -108,6 +109,7 @@
 #define PMC_USB_DEBOUNCE_DEL		0xec
 #define PMC_USB_AO			0xf0
 
+#define PMC_SCRATCH37			0x130
 #define PMC_SCRATCH41			0x140
 
 #define PMC_WAKE2_MASK			0x160
@@ -1099,8 +1101,7 @@ static struct notifier_block tegra_pmc_reboot_notifier = {
 	.notifier_call = tegra_pmc_reboot_notify,
 };
 
-static int tegra_pmc_restart_notify(struct notifier_block *this,
-				    unsigned long action, void *data)
+static void tegra_pmc_restart(void)
 {
 	u32 value;
 
@@ -1108,14 +1109,31 @@ static int tegra_pmc_restart_notify(struct notifier_block *this,
 	value = tegra_pmc_readl(pmc, PMC_CNTRL);
 	value |= PMC_CNTRL_MAIN_RST;
 	tegra_pmc_writel(pmc, value, PMC_CNTRL);
+}
+
+static int tegra_pmc_restart_handler(struct sys_off_data *data)
+{
+	tegra_pmc_restart();
 
 	return NOTIFY_DONE;
 }
 
-static struct notifier_block tegra_pmc_restart_handler = {
-	.notifier_call = tegra_pmc_restart_notify,
-	.priority = 128,
-};
+static int tegra_pmc_power_off_handler(struct sys_off_data *data)
+{
+	/*
+	 * Reboot Nexus 7 into special bootloader mode if USB cable is
+	 * connected in order to display battery status and power off.
+	 */
+	if (of_machine_is_compatible("asus,grouper") &&
+	    power_supply_is_system_supplied()) {
+		const u32 go_to_charger_mode = 0xa5a55a5a;
+
+		tegra_pmc_writel(pmc, go_to_charger_mode, PMC_SCRATCH37);
+		tegra_pmc_restart();
+	}
+
+	return NOTIFY_DONE;
+}
 
 static int powergate_show(struct seq_file *s, void *data)
 {
@@ -2877,6 +2895,42 @@ static int tegra_pmc_probe(struct platform_device *pdev)
 		pmc->clk = NULL;
 	}
 
+	/*
+	 * PMC should be last resort for restarting since it soft-resets
+	 * CPU without resetting everything else.
+	 */
+	err = devm_register_reboot_notifier(&pdev->dev,
+					    &tegra_pmc_reboot_notifier);
+	if (err) {
+		dev_err(&pdev->dev, "unable to register reboot notifier, %d\n",
+			err);
+		return err;
+	}
+
+	err = devm_register_sys_off_handler(&pdev->dev,
+					    SYS_OFF_MODE_RESTART,
+					    SYS_OFF_PRIO_LOW,
+					    tegra_pmc_restart_handler, NULL);
+	if (err) {
+		dev_err(&pdev->dev, "failed to register sys-off handler: %d\n",
+			err);
+		return err;
+	}
+
+	/*
+	 * PMC should be primary power-off method if it soft-resets CPU,
+	 * asking bootloader to shutdown hardware.
+	 */
+	err = devm_register_sys_off_handler(&pdev->dev,
+					    SYS_OFF_MODE_POWER_OFF,
+					    SYS_OFF_PRIO_FIRMWARE,
+					    tegra_pmc_power_off_handler, NULL);
+	if (err) {
+		dev_err(&pdev->dev, "failed to register sys-off handler: %d\n",
+			err);
+		return err;
+	}
+
 	/*
 	 * PCLK clock rate can't be retrieved using CLK API because it
 	 * causes lockup if CPU enters LP2 idle state from some other
@@ -2908,28 +2962,13 @@ static int tegra_pmc_probe(struct platform_device *pdev)
 			goto cleanup_sysfs;
 	}
 
-	err = devm_register_reboot_notifier(&pdev->dev,
-					    &tegra_pmc_reboot_notifier);
-	if (err) {
-		dev_err(&pdev->dev, "unable to register reboot notifier, %d\n",
-			err);
-		goto cleanup_debugfs;
-	}
-
-	err = register_restart_handler(&tegra_pmc_restart_handler);
-	if (err) {
-		dev_err(&pdev->dev, "unable to register restart handler, %d\n",
-			err);
-		goto cleanup_debugfs;
-	}
-
 	err = tegra_pmc_pinctrl_init(pmc);
 	if (err)
-		goto cleanup_restart_handler;
+		goto cleanup_debugfs;
 
 	err = tegra_pmc_regmap_init(pmc);
 	if (err < 0)
-		goto cleanup_restart_handler;
+		goto cleanup_debugfs;
 
 	err = tegra_powergate_init(pmc, pdev->dev.of_node);
 	if (err < 0)
@@ -2952,8 +2991,6 @@ static int tegra_pmc_probe(struct platform_device *pdev)
 
 cleanup_powergates:
 	tegra_powergate_remove_all(pdev->dev.of_node);
-cleanup_restart_handler:
-	unregister_restart_handler(&tegra_pmc_restart_handler);
 cleanup_debugfs:
 	debugfs_remove(pmc->debugfs);
 cleanup_sysfs:

include/linux/notifier.h

@@ -150,6 +150,11 @@ extern int raw_notifier_chain_register(struct raw_notifier_head *nh,
 extern int srcu_notifier_chain_register(struct srcu_notifier_head *nh,
 		struct notifier_block *nb);
 
+extern int atomic_notifier_chain_register_unique_prio(
+		struct atomic_notifier_head *nh, struct notifier_block *nb);
+extern int blocking_notifier_chain_register_unique_prio(
+		struct blocking_notifier_head *nh, struct notifier_block *nb);
+
 extern int atomic_notifier_chain_unregister(struct atomic_notifier_head *nh,
 		struct notifier_block *nb);
 extern int blocking_notifier_chain_unregister(struct blocking_notifier_head *nh,
@@ -173,6 +178,8 @@ extern int blocking_notifier_call_chain_robust(struct blocking_notifier_head *nh
 extern int raw_notifier_call_chain_robust(struct raw_notifier_head *nh,
 		unsigned long val_up, unsigned long val_down, void *v);
 
+extern bool atomic_notifier_call_chain_is_empty(struct atomic_notifier_head *nh);
+
 #define NOTIFY_DONE		0x0000		/* Don't care */
 #define NOTIFY_OK		0x0001		/* Suits me */
 #define NOTIFY_STOP_MASK	0x8000		/* Don't call further */

include/linux/pm.h

@@ -21,7 +21,6 @@
  * Callbacks for platform drivers to implement.
  */
 extern void (*pm_power_off)(void);
-extern void (*pm_power_off_prepare)(void);
 
 struct device; /* we have a circular dep with device.h */
 #ifdef CONFIG_VT_CONSOLE_SLEEP

include/linux/reboot.h

@@ -7,6 +7,7 @@
 #include <uapi/linux/reboot.h>
 
 struct device;
+struct sys_off_handler;
 
 #define SYS_DOWN	0x0001	/* Notify of system down */
 #define SYS_RESTART	SYS_DOWN
@@ -62,6 +63,95 @@ extern void machine_shutdown(void);
 struct pt_regs;
 extern void machine_crash_shutdown(struct pt_regs *);
 
+void do_kernel_power_off(void);
+
+/*
+ * sys-off handler API.
+ */
+
+/*
+ * Standard sys-off priority levels. Users are expected to set priorities
+ * relative to the standard levels.
+ *
+ * SYS_OFF_PRIO_PLATFORM:	Use this for platform-level handlers.
+ *
+ * SYS_OFF_PRIO_LOW:		Use this for handler of last resort.
+ *
+ * SYS_OFF_PRIO_DEFAULT:	Use this for normal handlers.
+ *
+ * SYS_OFF_PRIO_HIGH:		Use this for higher priority handlers.
+ *
+ * SYS_OFF_PRIO_FIRMWARE:	Use this if handler uses firmware call.
+ */
+#define SYS_OFF_PRIO_PLATFORM		-256
+#define SYS_OFF_PRIO_LOW		-128
+#define SYS_OFF_PRIO_DEFAULT		0
+#define SYS_OFF_PRIO_HIGH		192
+#define SYS_OFF_PRIO_FIRMWARE		224
+
+enum sys_off_mode {
+	/**
+	 * @SYS_OFF_MODE_POWER_OFF_PREPARE:
+	 *
+	 * Handlers prepare system to be powered off. Handlers are
+	 * allowed to sleep.
+	 */
+	SYS_OFF_MODE_POWER_OFF_PREPARE,
+
+	/**
+	 * @SYS_OFF_MODE_POWER_OFF:
+	 *
+	 * Handlers power-off system. Handlers are disallowed to sleep.
+	 */
+	SYS_OFF_MODE_POWER_OFF,
+
+	/**
+	 * @SYS_OFF_MODE_RESTART:
+	 *
+	 * Handlers restart system. Handlers are disallowed to sleep.
+	 */
+	SYS_OFF_MODE_RESTART,
+};
+
+/**
+ * struct sys_off_data - sys-off callback argument
+ *
+ * @mode: Mode ID. Currently used only by the sys-off restart mode,
+ *        see enum reboot_mode for the available modes.
+ * @cb_data: User's callback data.
+ * @cmd: Command string. Currently used only by the sys-off restart mode,
+ *       NULL otherwise.
+ */
+struct sys_off_data {
+	int mode;
+	void *cb_data;
+	const char *cmd;
+};
+
+struct sys_off_handler *
+register_sys_off_handler(enum sys_off_mode mode,
+			 int priority,
+			 int (*callback)(struct sys_off_data *data),
+			 void *cb_data);
+void unregister_sys_off_handler(struct sys_off_handler *handler);
+
+int devm_register_sys_off_handler(struct device *dev,
+				  enum sys_off_mode mode,
+				  int priority,
+				  int (*callback)(struct sys_off_data *data),
+				  void *cb_data);
+
+int devm_register_power_off_handler(struct device *dev,
+				    int (*callback)(struct sys_off_data *data),
+				    void *cb_data);
+
+int devm_register_restart_handler(struct device *dev,
+				  int (*callback)(struct sys_off_data *data),
+				  void *cb_data);
+
+int register_platform_power_off(void (*power_off)(void));
+void unregister_platform_power_off(void (*power_off)(void));
+
 /*
  * Architecture independent implemenations of sys_reboot commands.
  */
@@ -70,6 +160,7 @@ extern void kernel_restart_prepare(char *cmd);
 extern void kernel_restart(char *cmd);
 extern void kernel_halt(void);
 extern void kernel_power_off(void);
+extern bool kernel_can_power_off(void);
 
 extern int C_A_D; /* for sysctl */
 void ctrl_alt_del(void);

kernel/notifier.c

@@ -20,7 +20,8 @@ BLOCKING_NOTIFIER_HEAD(reboot_notifier_list);
  */
 
 static int notifier_chain_register(struct notifier_block **nl,
-				   struct notifier_block *n)
+				   struct notifier_block *n,
+				   bool unique_priority)
 {
 	while ((*nl) != NULL) {
 		if (unlikely((*nl) == n)) {
@@ -30,6 +31,8 @@ static int notifier_chain_register(struct notifier_block **nl,
 		}
 		if (n->priority > (*nl)->priority)
 			break;
+		if (n->priority == (*nl)->priority && unique_priority)
+			return -EBUSY;
 		nl = &((*nl)->next);
 	}
 	n->next = *nl;
@@ -144,12 +147,35 @@ int atomic_notifier_chain_register(struct atomic_notifier_head *nh,
 	int ret;
 
 	spin_lock_irqsave(&nh->lock, flags);
-	ret = notifier_chain_register(&nh->head, n);
+	ret = notifier_chain_register(&nh->head, n, false);
 	spin_unlock_irqrestore(&nh->lock, flags);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(atomic_notifier_chain_register);
 
+/**
+ *	atomic_notifier_chain_register_unique_prio - Add notifier to an atomic notifier chain
+ *	@nh: Pointer to head of the atomic notifier chain
+ *	@n: New entry in notifier chain
+ *
+ *	Adds a notifier to an atomic notifier chain if there is no other
+ *	notifier registered using the same priority.
+ *
+ *	Returns 0 on success, %-EEXIST or %-EBUSY on error.
+ */
+int atomic_notifier_chain_register_unique_prio(struct atomic_notifier_head *nh,
+					       struct notifier_block *n)
+{
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&nh->lock, flags);
+	ret = notifier_chain_register(&nh->head, n, true);
+	spin_unlock_irqrestore(&nh->lock, flags);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(atomic_notifier_chain_register_unique_prio);
+
 /**
  *	atomic_notifier_chain_unregister - Remove notifier from an atomic notifier chain
  *	@nh: Pointer to head of the atomic notifier chain
@@ -204,11 +230,44 @@ int atomic_notifier_call_chain(struct atomic_notifier_head *nh,
 EXPORT_SYMBOL_GPL(atomic_notifier_call_chain);
 NOKPROBE_SYMBOL(atomic_notifier_call_chain);
 
+/**
+ *	atomic_notifier_call_chain_is_empty - Check whether notifier chain is empty
+ *	@nh: Pointer to head of the atomic notifier chain
+ *
+ *	Checks whether notifier chain is empty.
+ *
+ *	Returns true is notifier chain is empty, false otherwise.
+ */
+bool atomic_notifier_call_chain_is_empty(struct atomic_notifier_head *nh)
+{
+	return !rcu_access_pointer(nh->head);
+}
+
 /*
  *	Blocking notifier chain routines.  All access to the chain is
  *	synchronized by an rwsem.
  */
 
+static int __blocking_notifier_chain_register(struct blocking_notifier_head *nh,
+					      struct notifier_block *n,
+					      bool unique_priority)
+{
+	int ret;
+
+	/*
+	 * This code gets used during boot-up, when task switching is
+	 * not yet working and interrupts must remain disabled.  At
+	 * such times we must not call down_write().
+	 */
+	if (unlikely(system_state == SYSTEM_BOOTING))
+		return notifier_chain_register(&nh->head, n, unique_priority);
+
+	down_write(&nh->rwsem);
+	ret = notifier_chain_register(&nh->head, n, unique_priority);
+	up_write(&nh->rwsem);
+	return ret;
+}
+
 /**
  *	blocking_notifier_chain_register - Add notifier to a blocking notifier chain
  *	@nh: Pointer to head of the blocking notifier chain
@@ -222,22 +281,26 @@ NOKPROBE_SYMBOL(atomic_notifier_call_chain);
 int blocking_notifier_chain_register(struct blocking_notifier_head *nh,
 		struct notifier_block *n)
 {
-	int ret;
+	return __blocking_notifier_chain_register(nh, n, false);
+}
+EXPORT_SYMBOL_GPL(blocking_notifier_chain_register);
 
-	/*
-	 * This code gets used during boot-up, when task switching is
-	 * not yet working and interrupts must remain disabled.  At
-	 * such times we must not call down_write().
+/**
+ *	blocking_notifier_chain_register_unique_prio - Add notifier to a blocking notifier chain
+ *	@nh: Pointer to head of the blocking notifier chain
+ *	@n: New entry in notifier chain
+ *
+ *	Adds a notifier to an blocking notifier chain if there is no other
+ *	notifier registered using the same priority.
+ *
+ *	Returns 0 on success, %-EEXIST or %-EBUSY on error.
  */
-	if (unlikely(system_state == SYSTEM_BOOTING))
-		return notifier_chain_register(&nh->head, n);
-
-	down_write(&nh->rwsem);
-	ret = notifier_chain_register(&nh->head, n);
-	up_write(&nh->rwsem);
-	return ret;
+int blocking_notifier_chain_register_unique_prio(struct blocking_notifier_head *nh,
+						 struct notifier_block *n)
+{
+	return __blocking_notifier_chain_register(nh, n, true);
 }
-EXPORT_SYMBOL_GPL(blocking_notifier_chain_register);
+EXPORT_SYMBOL_GPL(blocking_notifier_chain_register_unique_prio);
 
 /**
  *	blocking_notifier_chain_unregister - Remove notifier from a blocking notifier chain
@@ -341,7 +404,7 @@ EXPORT_SYMBOL_GPL(blocking_notifier_call_chain);
 int raw_notifier_chain_register(struct raw_notifier_head *nh,
 		struct notifier_block *n)
 {
-	return notifier_chain_register(&nh->head, n);
+	return notifier_chain_register(&nh->head, n, false);
 }
 EXPORT_SYMBOL_GPL(raw_notifier_chain_register);
 
@@ -420,10 +483,10 @@ int srcu_notifier_chain_register(struct srcu_notifier_head *nh,
 	 * such times we must not call mutex_lock().
 	 */
 	if (unlikely(system_state == SYSTEM_BOOTING))
-		return notifier_chain_register(&nh->head, n);
+		return notifier_chain_register(&nh->head, n, false);
 
 	mutex_lock(&nh->mutex);
-	ret = notifier_chain_register(&nh->head, n);
+	ret = notifier_chain_register(&nh->head, n, false);
 	mutex_unlock(&nh->mutex);
 	return ret;
 }

kernel/reboot.c

@@ -48,12 +48,20 @@ int reboot_cpu;
 enum reboot_type reboot_type = BOOT_ACPI;
 int reboot_force;
 
+struct sys_off_handler {
+	struct notifier_block nb;
+	int (*sys_off_cb)(struct sys_off_data *data);
+	void *cb_data;
+	enum sys_off_mode mode;
+	bool blocking;
+	void *list;
+};
+
 /*
- * If set, this is used for preparing the system to power off.
+ * Temporary stub that prevents linkage failure while we're in process
+ * of removing all uses of legacy pm_power_off() around the kernel.
  */
-
-void (*pm_power_off_prepare)(void);
-EXPORT_SYMBOL_GPL(pm_power_off_prepare);
+void __weak (*pm_power_off)(void);
 
 /**
  *	emergency_restart - reboot the system
@@ -281,6 +289,316 @@ void kernel_halt(void)
 }
 EXPORT_SYMBOL_GPL(kernel_halt);
 
+/*
+ *	Notifier list for kernel code which wants to be called
+ *	to prepare system for power off.
+ */
+static BLOCKING_NOTIFIER_HEAD(power_off_prep_handler_list);
+
+/*
+ *	Notifier list for kernel code which wants to be called
+ *	to power off system.
+ */
+static ATOMIC_NOTIFIER_HEAD(power_off_handler_list);
+
+static int sys_off_notify(struct notifier_block *nb,
+			  unsigned long mode, void *cmd)
+{
+	struct sys_off_handler *handler;
+	struct sys_off_data data = {};
+
+	handler = container_of(nb, struct sys_off_handler, nb);
+	data.cb_data = handler->cb_data;
+	data.mode = mode;
+	data.cmd = cmd;
+
+	return handler->sys_off_cb(&data);
+}
+
+/**
+ *	register_sys_off_handler - Register sys-off handler
+ *	@mode: Sys-off mode
+ *	@priority: Handler priority
+ *	@callback: Callback function
+ *	@cb_data: Callback argument
+ *
+ *	Registers system power-off or restart handler that will be invoked
+ *	at the step corresponding to the given sys-off mode. Handler's callback
+ *	should return NOTIFY_DONE to permit execution of the next handler in
+ *	the call chain or NOTIFY_STOP to break the chain (in error case for
+ *	example).
+ *
+ *	Multiple handlers can be registered at the default priority level.
+ *
+ *	Only one handler can be registered at the non-default priority level,
+ *	otherwise ERR_PTR(-EBUSY) is returned.
+ *
+ *	Returns a new instance of struct sys_off_handler on success, or
+ *	an ERR_PTR()-encoded error code otherwise.
+ */
+struct sys_off_handler *
+register_sys_off_handler(enum sys_off_mode mode,
+			 int priority,
+			 int (*callback)(struct sys_off_data *data),
+			 void *cb_data)
+{
+	struct sys_off_handler *handler;
+	int err;
+
+	handler = kzalloc(sizeof(*handler), GFP_KERNEL);
+	if (!handler)
+		return ERR_PTR(-ENOMEM);
+
+	switch (mode) {
+	case SYS_OFF_MODE_POWER_OFF_PREPARE:
+		handler->list = &power_off_prep_handler_list;
+		handler->blocking = true;
+		break;
+
+	case SYS_OFF_MODE_POWER_OFF:
+		handler->list = &power_off_handler_list;
+		break;
+
+	case SYS_OFF_MODE_RESTART:
+		handler->list = &restart_handler_list;
+		break;
+
+	default:
+		kfree(handler);
+		return ERR_PTR(-EINVAL);
+	}
+
+	handler->nb.notifier_call = sys_off_notify;
+	handler->nb.priority = priority;
+	handler->sys_off_cb = callback;
+	handler->cb_data = cb_data;
+	handler->mode = mode;
+
+	if (handler->blocking) {
+		if (priority == SYS_OFF_PRIO_DEFAULT)
+			err = blocking_notifier_chain_register(handler->list,
+							       &handler->nb);
+		else
+			err = blocking_notifier_chain_register_unique_prio(handler->list,
+									   &handler->nb);
+	} else {
+		if (priority == SYS_OFF_PRIO_DEFAULT)
+			err = atomic_notifier_chain_register(handler->list,
+							     &handler->nb);
+		else
+			err = atomic_notifier_chain_register_unique_prio(handler->list,
+									 &handler->nb);
+	}
+
+	if (err) {
+		kfree(handler);
+		return ERR_PTR(err);
+	}
+
+	return handler;
+}
+EXPORT_SYMBOL_GPL(register_sys_off_handler);
+
+/**
+ *	unregister_sys_off_handler - Unregister sys-off handler
+ *	@handler: Sys-off handler
+ *
+ *	Unregisters given sys-off handler.
+ */
+void unregister_sys_off_handler(struct sys_off_handler *handler)
+{
+	int err;
+
+	if (!handler)
+		return;
+
+	if (handler->blocking)
+		err = blocking_notifier_chain_unregister(handler->list,
+							 &handler->nb);
+	else
+		err = atomic_notifier_chain_unregister(handler->list,
+						       &handler->nb);
+
+	/* sanity check, shall never happen */
+	WARN_ON(err);
+
+	kfree(handler);
+}
+EXPORT_SYMBOL_GPL(unregister_sys_off_handler);
+
+static void devm_unregister_sys_off_handler(void *data)
+{
+	struct sys_off_handler *handler = data;
+
+	unregister_sys_off_handler(handler);
+}
+
+/**
+ *	devm_register_sys_off_handler - Register sys-off handler
+ *	@dev: Device that registers handler
+ *	@mode: Sys-off mode
+ *	@priority: Handler priority
+ *	@callback: Callback function
+ *	@cb_data: Callback argument
+ *
+ *	Registers resource-managed sys-off handler.
+ *
+ *	Returns zero on success, or error code on failure.
+ */
+int devm_register_sys_off_handler(struct device *dev,
+				  enum sys_off_mode mode,
+				  int priority,
+				  int (*callback)(struct sys_off_data *data),
+				  void *cb_data)
+{
+	struct sys_off_handler *handler;
+
+	handler = register_sys_off_handler(mode, priority, callback, cb_data);
+	if (IS_ERR(handler))
+		return PTR_ERR(handler);
+
+	return devm_add_action_or_reset(dev, devm_unregister_sys_off_handler,
+					handler);
+}
+EXPORT_SYMBOL_GPL(devm_register_sys_off_handler);
+
+/**
+ *	devm_register_power_off_handler - Register power-off handler
+ *	@dev: Device that registers callback
+ *	@callback: Callback function
+ *	@cb_data: Callback's argument
+ *
+ *	Registers resource-managed sys-off handler with a default priority
+ *	and using power-off mode.
+ *
+ *	Returns zero on success, or error code on failure.
+ */
+int devm_register_power_off_handler(struct device *dev,
+				    int (*callback)(struct sys_off_data *data),
+				    void *cb_data)
+{
+	return devm_register_sys_off_handler(dev,
+					     SYS_OFF_MODE_POWER_OFF,
+					     SYS_OFF_PRIO_DEFAULT,
+					     callback, cb_data);
+}
+EXPORT_SYMBOL_GPL(devm_register_power_off_handler);
+
+/**
+ *	devm_register_restart_handler - Register restart handler
+ *	@dev: Device that registers callback
+ *	@callback: Callback function
+ *	@cb_data: Callback's argument
+ *
+ *	Registers resource-managed sys-off handler with a default priority
+ *	and using restart mode.
+ *
+ *	Returns zero on success, or error code on failure.
+ */
+int devm_register_restart_handler(struct device *dev,
+				  int (*callback)(struct sys_off_data *data),
+				  void *cb_data)
+{
+	return devm_register_sys_off_handler(dev,
+					     SYS_OFF_MODE_RESTART,
+					     SYS_OFF_PRIO_DEFAULT,
+					     callback, cb_data);
+}
+EXPORT_SYMBOL_GPL(devm_register_restart_handler);
+
+static struct sys_off_handler *platform_power_off_handler;
+
+static int platform_power_off_notify(struct sys_off_data *data)
+{
+	void (*platform_power_power_off_cb)(void) = data->cb_data;
+
+	platform_power_power_off_cb();
+
+	return NOTIFY_DONE;
+}
+
+/**
+ *	register_platform_power_off - Register platform-level power-off callback
+ *	@power_off: Power-off callback
+ *
+ *	Registers power-off callback that will be called as last step
+ *	of the power-off sequence. This callback is expected to be invoked
+ *	for the last resort. Only one platform power-off callback is allowed
+ *	to be registered at a time.
+ *
+ *	Returns zero on success, or error code on failure.
+ */
+int register_platform_power_off(void (*power_off)(void))
+{
+	struct sys_off_handler *handler;
+
+	handler = register_sys_off_handler(SYS_OFF_MODE_POWER_OFF,
+					   SYS_OFF_PRIO_PLATFORM,
+					   platform_power_off_notify,
+					   power_off);
+	if (IS_ERR(handler))
+		return PTR_ERR(handler);
+
+	platform_power_off_handler = handler;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(register_platform_power_off);
+
+/**
+ *	unregister_platform_power_off - Unregister platform-level power-off callback
+ *	@power_off: Power-off callback
+ *
+ *	Unregisters previously registered platform power-off callback.
+ */
+void unregister_platform_power_off(void (*power_off)(void))
+{
+	if (platform_power_off_handler &&
+	    platform_power_off_handler->cb_data == power_off) {
+		unregister_sys_off_handler(platform_power_off_handler);
+		platform_power_off_handler = NULL;
+	}
+}
+EXPORT_SYMBOL_GPL(unregister_platform_power_off);
+
+static int legacy_pm_power_off(struct sys_off_data *data)
+{
+	if (pm_power_off)
+		pm_power_off();
+
+	return NOTIFY_DONE;
+}
+
+static void do_kernel_power_off_prepare(void)
+{
+	blocking_notifier_call_chain(&power_off_prep_handler_list, 0, NULL);
+}
+
+/**
+ *	do_kernel_power_off - Execute kernel power-off handler call chain
+ *
+ *	Expected to be called as last step of the power-off sequence.
+ *
+ *	Powers off the system immediately if a power-off handler function has
+ *	been registered. Otherwise does nothing.
+ */
+void do_kernel_power_off(void)
+{
+	atomic_notifier_call_chain(&power_off_handler_list, 0, NULL);
+}
+
+/**
+ *	kernel_can_power_off - check whether system can be powered off
+ *
+ *	Returns true if power-off handler is registered and system can be
+ *	powered off, false otherwise.
+ */
+bool kernel_can_power_off(void)
+{
+	return !atomic_notifier_call_chain_is_empty(&power_off_handler_list);
+}
+EXPORT_SYMBOL_GPL(kernel_can_power_off);
+
 /**
  *	kernel_power_off - power_off the system
  *
@@ -289,8 +607,7 @@ EXPORT_SYMBOL_GPL(kernel_halt);
 void kernel_power_off(void)
 {
 	kernel_shutdown_prepare(SYSTEM_POWER_OFF);
-	if (pm_power_off_prepare)
-		pm_power_off_prepare();
+	do_kernel_power_off_prepare();
 	migrate_to_reboot_cpu();
 	syscore_shutdown();
 	pr_emerg("Power down\n");
@@ -313,6 +630,7 @@ 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;
 
@@ -337,10 +655,25 @@ 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.
 	 */
-	if ((cmd == LINUX_REBOOT_CMD_POWER_OFF) && !pm_power_off)
+	if ((cmd == LINUX_REBOOT_CMD_POWER_OFF) && !kernel_can_power_off())
 		cmd = LINUX_REBOOT_CMD_HALT;
 
 	mutex_lock(&system_transition_mutex);
@@ -394,6 +727,7 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
 		break;
 	}
 	mutex_unlock(&system_transition_mutex);
+	unregister_sys_off_handler(sys_off);
 	return ret;
 }