Merge branch 'smp-hotplug-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull smp hotplug updates from Thomas Gleixner:
 "This is the next part of the hotplug rework.

   - Convert all notifiers with a priority assigned

   - Convert all CPU_STARTING/DYING notifiers

     The final removal of the STARTING/DYING infrastructure will happen
     when the merge window closes.

  Another 700 hundred line of unpenetrable maze gone :)"

* 'smp-hotplug-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (70 commits)
  timers/core: Correct callback order during CPU hot plug
  leds/trigger/cpu: Move from CPU_STARTING to ONLINE level
  powerpc/numa: Convert to hotplug state machine
  arm/perf: Fix hotplug state machine conversion
  irqchip/armada: Avoid unused function warnings
  ARC/time: Convert to hotplug state machine
  clocksource/atlas7: Convert to hotplug state machine
  clocksource/armada-370-xp: Convert to hotplug state machine
  clocksource/exynos_mct: Convert to hotplug state machine
  clocksource/arm_global_timer: Convert to hotplug state machine
  rcu: Convert rcutree to hotplug state machine
  KVM/arm/arm64/vgic-new: Convert to hotplug state machine
  smp/cfd: Convert core to hotplug state machine
  x86/x2apic: Convert to CPU hotplug state machine
  profile: Convert to hotplug state machine
  timers/core: Convert to hotplug state machine
  hrtimer: Convert to hotplug state machine
  x86/tboot: Convert to hotplug state machine
  arm64/armv8 deprecated: Convert to hotplug state machine
  hwtracing/coresight-etm4x: Convert to hotplug state machine
  ...

75 files changed, 1316 insertions, 2013 deletions

diff --git a/arch/arc/kernel/time.c b/arch/arc/kernel/time.c
index 98f22d2eb563..f927b8dc6edd 100644
--- a/arch/arc/kernel/time.c
+++ b/arch/arc/kernel/time.c
@@ -296,30 +296,23 @@ static irqreturn_t timer_irq_handler(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static int arc_timer_cpu_notify(struct notifier_block *self,
-				unsigned long action, void *hcpu)
+
+static int arc_timer_starting_cpu(unsigned int cpu)
 {
 	struct clock_event_device *evt = this_cpu_ptr(&arc_clockevent_device);
 
 	evt->cpumask = cpumask_of(smp_processor_id());
 
-	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_STARTING:
-		clockevents_config_and_register(evt, arc_timer_freq,
-						0, ULONG_MAX);
-		enable_percpu_irq(arc_timer_irq, 0);
-		break;
-	case CPU_DYING:
-		disable_percpu_irq(arc_timer_irq);
-		break;
-	}
-
-	return NOTIFY_OK;
+	clockevents_config_and_register(evt, arc_timer_freq, 0, ARC_TIMER_MAX);
+	enable_percpu_irq(arc_timer_irq, 0);
+	return 0;
 }
 
-static struct notifier_block arc_timer_cpu_nb = {
-	.notifier_call = arc_timer_cpu_notify,
-};
+static int arc_timer_dying_cpu(unsigned int cpu)
+{
+	disable_percpu_irq(arc_timer_irq);
+	return 0;
+}
 
 /*
  * clockevent setup for boot CPU
@@ -329,12 +322,6 @@ static int __init arc_clockevent_setup(struct device_node *node)
 	struct clock_event_device *evt = this_cpu_ptr(&arc_clockevent_device);
 	int ret;
 
-	ret = register_cpu_notifier(&arc_timer_cpu_nb);
-	if (ret) {
-		pr_err("Failed to register cpu notifier");
-		return ret;
-	}
-
 	arc_timer_irq = irq_of_parse_and_map(node, 0);
 	if (arc_timer_irq <= 0) {
 		pr_err("clockevent: missing irq");
@@ -347,11 +334,6 @@ static int __init arc_clockevent_setup(struct device_node *node)
 		return ret;
 	}
 
-	evt->irq = arc_timer_irq;
-	evt->cpumask = cpumask_of(smp_processor_id());
-	clockevents_config_and_register(evt, arc_timer_freq,
-					0, ARC_TIMER_MAX);
-
 	/* Needs apriori irq_set_percpu_devid() done in intc map function */
 	ret = request_percpu_irq(arc_timer_irq, timer_irq_handler,
 				 "Timer0 (per-cpu-tick)", evt);
@@ -360,8 +342,14 @@ static int __init arc_clockevent_setup(struct device_node *node)
 		return ret;
 	}
 
-	enable_percpu_irq(arc_timer_irq, 0);
-
+	ret = cpuhp_setup_state(CPUHP_AP_ARC_TIMER_STARTING,
+				"AP_ARC_TIMER_STARTING",
+				arc_timer_starting_cpu,
+				arc_timer_dying_cpu);
+	if (ret) {
+		pr_err("Failed to setup hotplug state");
+		return ret;
+	}
 	return 0;
 }
 
diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c
index b6ec65e68009..02d5e5e8d44c 100644
--- a/arch/arm/kernel/smp_twd.c
+++ b/arch/arm/kernel/smp_twd.c
@@ -310,24 +310,17 @@ static void twd_timer_setup(void)
 	enable_percpu_irq(clk->irq, 0);
 }
 
-static int twd_timer_cpu_notify(struct notifier_block *self,
-				unsigned long action, void *hcpu)
+static int twd_timer_starting_cpu(unsigned int cpu)
 {
-	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_STARTING:
-		twd_timer_setup();
-		break;
-	case CPU_DYING:
-		twd_timer_stop();
-		break;
-	}
-
-	return NOTIFY_OK;
+	twd_timer_setup();
+	return 0;
 }
 
-static struct notifier_block twd_timer_cpu_nb = {
-	.notifier_call = twd_timer_cpu_notify,
-};
+static int twd_timer_dying_cpu(unsigned int cpu)
+{
+	twd_timer_stop();
+	return 0;
+}
 
 static int __init twd_local_timer_common_register(struct device_node *np)
 {
@@ -345,9 +338,9 @@ static int __init twd_local_timer_common_register(struct device_node *np)
 		goto out_free;
 	}
 
-	err = register_cpu_notifier(&twd_timer_cpu_nb);
-	if (err)
-		goto out_irq;
+	cpuhp_setup_state_nocalls(CPUHP_AP_ARM_TWD_STARTING,
+				  "AP_ARM_TWD_STARTING",
+				  twd_timer_starting_cpu, twd_timer_dying_cpu);
 
 	twd_get_clock(np);
 	if (!of_property_read_bool(np, "always-on"))
@@ -365,8 +358,6 @@ static int __init twd_local_timer_common_register(struct device_node *np)
 
 	return 0;
 
-out_irq:
-	free_percpu_irq(twd_ppi, twd_evt);
 out_free:
 	iounmap(twd_base);
 	twd_base = NULL;
diff --git a/arch/arm/mach-mvebu/coherency.c b/arch/arm/mach-mvebu/coherency.c
index e80f0dde2189..ae2a018b9305 100644
--- a/arch/arm/mach-mvebu/coherency.c
+++ b/arch/arm/mach-mvebu/coherency.c
@@ -111,20 +111,12 @@ static struct notifier_block mvebu_hwcc_pci_nb __maybe_unused = {
 	.notifier_call = mvebu_hwcc_notifier,
 };
 
-static int armada_xp_clear_shared_l2_notifier_func(struct notifier_block *nfb,
-					unsigned long action, void *hcpu)
+static int armada_xp_clear_l2_starting(unsigned int cpu)
 {
-	if (action == CPU_STARTING || action == CPU_STARTING_FROZEN)
-		armada_xp_clear_shared_l2();
-
-	return NOTIFY_OK;
+	armada_xp_clear_shared_l2();
+	return 0;
 }
 
-static struct notifier_block armada_xp_clear_shared_l2_notifier = {
-	.notifier_call = armada_xp_clear_shared_l2_notifier_func,
-	.priority = 100,
-};
-
 static void __init armada_370_coherency_init(struct device_node *np)
 {
 	struct resource res;
@@ -155,8 +147,9 @@ static void __init armada_370_coherency_init(struct device_node *np)
 
 	of_node_put(cpu_config_np);
 
-	register_cpu_notifier(&armada_xp_clear_shared_l2_notifier);
-
+	cpuhp_setup_state_nocalls(CPUHP_AP_ARM_MVEBU_COHERENCY,
+				  "AP_ARM_MVEBU_COHERENCY",
+				  armada_xp_clear_l2_starting, NULL);
 exit:
 	set_cpu_coherent();
 }
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index c61996c256cc..cc12905ae6f8 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -597,17 +597,16 @@ static void l2c310_configure(void __iomem *base)
 			      L310_POWER_CTRL);
 }
 
-static int l2c310_cpu_enable_flz(struct notifier_block *nb, unsigned long act, void *data)
+static int l2c310_starting_cpu(unsigned int cpu)
 {
-	switch (act & ~CPU_TASKS_FROZEN) {
-	case CPU_STARTING:
-		set_auxcr(get_auxcr() | BIT(3) | BIT(2) | BIT(1));
-		break;
-	case CPU_DYING:
-		set_auxcr(get_auxcr() & ~(BIT(3) | BIT(2) | BIT(1)));
-		break;
-	}
-	return NOTIFY_OK;
+	set_auxcr(get_auxcr() | BIT(3) | BIT(2) | BIT(1));
+	return 0;
+}
+
+static int l2c310_dying_cpu(unsigned int cpu)
+{
+	set_auxcr(get_auxcr() & ~(BIT(3) | BIT(2) | BIT(1)));
+	return 0;
 }
 
 static void __init l2c310_enable(void __iomem *base, unsigned num_lock)
@@ -678,10 +677,10 @@ static void __init l2c310_enable(void __iomem *base, unsigned num_lock)
 			power_ctrl & L310_STNDBY_MODE_EN ? "en" : "dis");
 	}
 
-	if (aux & L310_AUX_CTRL_FULL_LINE_ZERO) {
-		set_auxcr(get_auxcr() | BIT(3) | BIT(2) | BIT(1));
-		cpu_notifier(l2c310_cpu_enable_flz, 0);
-	}
+	if (aux & L310_AUX_CTRL_FULL_LINE_ZERO)
+		cpuhp_setup_state(CPUHP_AP_ARM_L2X0_STARTING,
+				  "AP_ARM_L2X0_STARTING", l2c310_starting_cpu,
+				  l2c310_dying_cpu);
 }
 
 static void __init l2c310_fixup(void __iomem *base, u32 cache_id,
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index 73085d3482ed..da0b33deba6d 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -643,19 +643,19 @@ int vfp_restore_user_hwstate(struct user_vfp __user *ufp,
  * hardware state at every thread switch.  We clear our held state when
  * a CPU has been killed, indicating that the VFP hardware doesn't contain
  * a threads VFP state.  When a CPU starts up, we re-enable access to the
- * VFP hardware.
- *
- * Both CPU_DYING and CPU_STARTING are called on the CPU which
+ * VFP hardware. The callbacks below are called on the CPU which
  * is being offlined/onlined.
  */
-static int vfp_hotplug(struct notifier_block *b, unsigned long action,
-	void *hcpu)
+static int vfp_dying_cpu(unsigned int cpu)
 {
-	if (action == CPU_DYING || action == CPU_DYING_FROZEN)
-		vfp_current_hw_state[(long)hcpu] = NULL;
-	else if (action == CPU_STARTING || action == CPU_STARTING_FROZEN)
-		vfp_enable(NULL);
-	return NOTIFY_OK;
+	vfp_force_reload(cpu, current_thread_info());
+	return 0;
+}
+
+static int vfp_starting_cpu(unsigned int unused)
+{
+	vfp_enable(NULL);
+	return 0;
 }
 
 void vfp_kmode_exception(void)
@@ -732,6 +732,10 @@ static int __init vfp_init(void)
 	unsigned int vfpsid;
 	unsigned int cpu_arch = cpu_architecture();
 
+	/*
+	 * Enable the access to the VFP on all online CPUs so the
+	 * following test on FPSID will succeed.
+	 */
 	if (cpu_arch >= CPU_ARCH_ARMv6)
 		on_each_cpu(vfp_enable, NULL, 1);
 
@@ -794,7 +798,9 @@ static int __init vfp_init(void)
 		VFP_arch = (vfpsid & FPSID_ARCH_MASK) >> FPSID_ARCH_BIT;
 	}
 
-	hotcpu_notifier(vfp_hotplug, 0);
+	cpuhp_setup_state_nocalls(CPUHP_AP_ARM_VFP_STARTING,
+				  "AP_ARM_VFP_STARTING", vfp_starting_cpu,
+				  vfp_dying_cpu);
 
 	vfp_vector = vfp_support_entry;
 
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index 0bea3d271f6e..b0b82f5ea338 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -153,12 +153,11 @@ static struct notifier_block xen_pvclock_gtod_notifier = {
 	.notifier_call = xen_pvclock_gtod_notify,
 };
 
-static void xen_percpu_init(void)
+static int xen_starting_cpu(unsigned int cpu)
 {
 	struct vcpu_register_vcpu_info info;
 	struct vcpu_info *vcpup;
 	int err;
-	int cpu = get_cpu();
 
 	/* 
 	 * VCPUOP_register_vcpu_info cannot be called twice for the same
@@ -186,7 +185,13 @@ static void xen_percpu_init(void)
 
 after_register_vcpu_info:
 	enable_percpu_irq(xen_events_irq, 0);
-	put_cpu();
+	return 0;
+}
+
+static int xen_dying_cpu(unsigned int cpu)
+{
+	disable_percpu_irq(xen_events_irq);
+	return 0;
 }
 
 static void xen_restart(enum reboot_mode reboot_mode, const char *cmd)
@@ -205,28 +210,6 @@ static void xen_power_off(void)
 	BUG_ON(rc);
 }
 
-static int xen_cpu_notification(struct notifier_block *self,
-				unsigned long action,
-				void *hcpu)
-{
-	switch (action) {
-	case CPU_STARTING:
-		xen_percpu_init();
-		break;
-	case CPU_DYING:
-		disable_percpu_irq(xen_events_irq);
-		break;
-	default:
-		break;
-	}
-
-	return NOTIFY_OK;
-}
-
-static struct notifier_block xen_cpu_notifier = {
-	.notifier_call = xen_cpu_notification,
-};
-
 static irqreturn_t xen_arm_callback(int irq, void *arg)
 {
 	xen_hvm_evtchn_do_upcall();
@@ -425,16 +408,14 @@ static int __init xen_guest_init(void)
 		return -EINVAL;
 	}
 
-	xen_percpu_init();
-
-	register_cpu_notifier(&xen_cpu_notifier);
-
 	xen_time_setup_guest();
 
 	if (xen_initial_domain())
 		pvclock_gtod_register_notifier(&xen_pvclock_gtod_notifier);
 
-	return 0;
+	return cpuhp_setup_state(CPUHP_AP_ARM_XEN_STARTING,
+				 "AP_ARM_XEN_STARTING", xen_starting_cpu,
+				 xen_dying_cpu);
 }
 early_initcall(xen_guest_init);
 
diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c
index 5f72475e2e3b..42ffdb54e162 100644
--- a/arch/arm64/kernel/armv8_deprecated.c
+++ b/arch/arm64/kernel/armv8_deprecated.c
@@ -121,7 +121,7 @@ static int run_all_cpu_set_hw_mode(struct insn_emulation *insn, bool enable)
  *  0 		- If all the hooks ran successfully.
  * -EINVAL	- At least one hook is not supported by the CPU.
  */
-static int run_all_insn_set_hw_mode(unsigned long cpu)
+static int run_all_insn_set_hw_mode(unsigned int cpu)
 {
 	int rc = 0;
 	unsigned long flags;
@@ -131,7 +131,7 @@ static int run_all_insn_set_hw_mode(unsigned long cpu)
 	list_for_each_entry(insn, &insn_emulation, node) {
 		bool enable = (insn->current_mode == INSN_HW);
 		if (insn->ops->set_hw_mode && insn->ops->set_hw_mode(enable)) {
-			pr_warn("CPU[%ld] cannot support the emulation of %s",
+			pr_warn("CPU[%u] cannot support the emulation of %s",
 				cpu, insn->ops->name);
 			rc = -EINVAL;
 		}
@@ -611,20 +611,6 @@ static struct insn_emulation_ops setend_ops = {
 	.set_hw_mode = setend_set_hw_mode,
 };
 
-static int insn_cpu_hotplug_notify(struct notifier_block *b,
-			      unsigned long action, void *hcpu)
-{
-	int rc = 0;
-	if ((action & ~CPU_TASKS_FROZEN) == CPU_STARTING)
-		rc = run_all_insn_set_hw_mode((unsigned long)hcpu);
-
-	return notifier_from_errno(rc);
-}
-
-static struct notifier_block insn_cpu_hotplug_notifier = {
-	.notifier_call = insn_cpu_hotplug_notify,
-};
-
 /*
  * Invoked as late_initcall, since not needed before init spawned.
  */
@@ -643,7 +629,9 @@ static int __init armv8_deprecated_init(void)
 			pr_info("setend instruction emulation is not supported on the system");
 	}
 
-	register_cpu_notifier(&insn_cpu_hotplug_notifier);
+	cpuhp_setup_state_nocalls(CPUHP_AP_ARM64_ISNDEP_STARTING,
+				  "AP_ARM64_ISNDEP_STARTING",
+				  run_all_insn_set_hw_mode, NULL);
 	register_insn_emulation_sysctl(ctl_abi);
 
 	return 0;
diff --git a/arch/blackfin/kernel/perf_event.c b/arch/blackfin/kernel/perf_event.c
index 170d786807c4..6355e97d22b9 100644
--- a/arch/blackfin/kernel/perf_event.c
+++ b/arch/blackfin/kernel/perf_event.c
@@ -453,29 +453,13 @@ static struct pmu pmu = {
 	.read        = bfin_pmu_read,
 };
 
-static void bfin_pmu_setup(int cpu)
+static int bfin_pmu_prepare_cpu(unsigned int cpu)
 {
 	struct cpu_hw_events *cpuhw = &per_cpu(cpu_hw_events, cpu);
 
+	bfin_write_PFCTL(0);
 	memset(cpuhw, 0, sizeof(struct cpu_hw_events));
-}
-
-static int
-bfin_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
-{
-	unsigned int cpu = (long)hcpu;
-
-	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_UP_PREPARE:
-		bfin_write_PFCTL(0);
-		bfin_pmu_setup(cpu);
-		break;
-
-	default:
-		break;
-	}
-
-	return NOTIFY_OK;
+	return 0;
 }
 
 static int __init bfin_pmu_init(void)
@@ -491,8 +475,8 @@ static int __init bfin_pmu_init(void)
 
 	ret = perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW);
 	if (!ret)
-		perf_cpu_notifier(bfin_pmu_notifier);
-
+		cpuhp_setup_state(CPUHP_PERF_BFIN, "PERF_BFIN",
+				  bfin_pmu_prepare_cpu, NULL);
 	return ret;
 }