[patch 09/66] perf/x86: Convert the core to the hotplug state machine

[Anna-Maria Gleixner]

From: Thomas Gleixner <tglx@xxxxxxxxxxxxx>

Replace the perf_notifier() install mechanism, which invokes magically
the callback on the current CPU. Convert the hardware specific
callbacks which are invoked from the x86 perf core to return proper
error codes instead of totally pointless NOTIFY_BAD return values.

Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Reviewed-by: Sebastian Andrzej Siewior <bigeasy@xxxxxxxxxxxxx>
Signed-off-by: Anna-Maria Gleixner <anna-maria@xxxxxxxxxxxxx>
---
 arch/x86/events/amd/core.c   |    6 +-
 arch/x86/events/core.c       |  103 +++++++++++++++++++++++++++----------------
 arch/x86/events/intel/core.c |    4 -
 include/linux/cpuhotplug.h   |    3 +
 4 files changed, 74 insertions(+), 42 deletions(-)

--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -370,13 +370,13 @@ static int amd_pmu_cpu_prepare(int cpu)
 	WARN_ON_ONCE(cpuc->amd_nb);
 
 	if (!x86_pmu.amd_nb_constraints)
-		return NOTIFY_OK;
+		return 0;
 
 	cpuc->amd_nb = amd_alloc_nb(cpu);
 	if (!cpuc->amd_nb)
-		return NOTIFY_BAD;
+		return -ENOMEM;
 
-	return NOTIFY_OK;
+	return 0;
 }
 
 static void amd_pmu_cpu_starting(int cpu)
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1477,49 +1477,49 @@ NOKPROBE_SYMBOL(perf_event_nmi_handler);
 struct event_constraint emptyconstraint;
 struct event_constraint unconstrained;
 
-static int
-x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
+static int x86_pmu_prepare_cpu(unsigned int cpu)
 {
-	unsigned int cpu = (long)hcpu;
 	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
-	int i, ret = NOTIFY_OK;
+	int i;
 
-	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_UP_PREPARE:
-		for (i = 0 ; i < X86_PERF_KFREE_MAX; i++)
-			cpuc->kfree_on_online[i] = NULL;
-		if (x86_pmu.cpu_prepare)
-			ret = x86_pmu.cpu_prepare(cpu);
-		break;
-
-	case CPU_STARTING:
-		if (x86_pmu.cpu_starting)
-			x86_pmu.cpu_starting(cpu);
-		break;
-
-	case CPU_ONLINE:
-		for (i = 0 ; i < X86_PERF_KFREE_MAX; i++) {
-			kfree(cpuc->kfree_on_online[i]);
-			cpuc->kfree_on_online[i] = NULL;
-		}
-		break;
+	for (i = 0 ; i < X86_PERF_KFREE_MAX; i++)
+		cpuc->kfree_on_online[i] = NULL;
+	if (x86_pmu.cpu_prepare)
+		return x86_pmu.cpu_prepare(cpu);
+	return 0;
+}
 
-	case CPU_DYING:
-		if (x86_pmu.cpu_dying)
-			x86_pmu.cpu_dying(cpu);
-		break;
+static int x86_pmu_dead_cpu(unsigned int cpu)
+{
+	if (x86_pmu.cpu_dead)
+		x86_pmu.cpu_dead(cpu);
+	return 0;
+}
 
-	case CPU_UP_CANCELED:
-	case CPU_DEAD:
-		if (x86_pmu.cpu_dead)
-			x86_pmu.cpu_dead(cpu);
-		break;
+static int x86_pmu_online_cpu(unsigned int cpu)
+{
+	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
+	int i;
 
-	default:
-		break;
+	for (i = 0 ; i < X86_PERF_KFREE_MAX; i++) {
+		kfree(cpuc->kfree_on_online[i]);
+		cpuc->kfree_on_online[i] = NULL;
 	}
+	return 0;
+}
 
-	return ret;
+static int x86_pmu_starting_cpu(unsigned int cpu)
+{
+	if (x86_pmu.cpu_starting)
+		x86_pmu.cpu_starting(cpu);
+	return 0;
+}
+
+static int x86_pmu_dying_cpu(unsigned int cpu)
+{
+	if (x86_pmu.cpu_dying)
+		x86_pmu.cpu_dying(cpu);
+	return 0;
 }
 
 static void __init pmu_check_apic(void)
@@ -1764,10 +1764,39 @@ static int __init init_hw_perf_events(vo
 	pr_info("... fixed-purpose events:   %d\n",     x86_pmu.num_counters_fixed);
 	pr_info("... event mask:             %016Lx\n", x86_pmu.intel_ctrl);
 
-	perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW);
-	perf_cpu_notifier(x86_pmu_notifier);
+	/*
+	 * Install callbacks. Core will call them for each online
+	 * cpu.
+	 */
+	err = cpuhp_setup_state(CPUHP_PERF_X86_PREPARE, "PERF_X86_PREPARE",
+				x86_pmu_prepare_cpu, x86_pmu_dead_cpu);
+	if (err)
+		return err;
+
+	err = cpuhp_setup_state(CPUHP_AP_PERF_X86_STARTING,
+				"AP_PERF_X86_STARTING", x86_pmu_starting_cpu,
+				x86_pmu_dying_cpu);
+	if (err)
+		goto out;
+
+	err = cpuhp_setup_state(CPUHP_AP_PERF_X86_ONLINE, "AP_PERF_X86_ONLINE",
+				x86_pmu_online_cpu, NULL);
+	if (err)
+		goto out1;
+
+	err = perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW);
+	if (err)
+		goto out2;
 
 	return 0;
+
+out2:
+	cpuhp_remove_state(CPUHP_AP_PERF_X86_ONLINE);
+out1:
+	cpuhp_remove_state(CPUHP_AP_PERF_X86_STARTING);
+out:
+	cpuhp_remove_state(CPUHP_PERF_X86_PREPARE);
+	return err;
 }
 early_initcall(init_hw_perf_events);
 
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3050,7 +3050,7 @@ static int intel_pmu_cpu_prepare(int cpu
 		cpuc->excl_thread_id = 0;
 	}
 
-	return NOTIFY_OK;
+	return 0;
 
 err_constraint_list:
 	kfree(cpuc->constraint_list);
@@ -3061,7 +3061,7 @@ static int intel_pmu_cpu_prepare(int cpu
 	cpuc->shared_regs = NULL;
 
 err:
-	return NOTIFY_BAD;
+	return -ENOMEM;
 }
 
 static void intel_pmu_cpu_starting(int cpu)
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -5,6 +5,7 @@ enum cpuhp_state {
 	CPUHP_OFFLINE,
 	CPUHP_CREATE_THREADS,
 	CPUHP_PERF_PREPARE,
+	CPUHP_PERF_X86_PREPARE,
 	CPUHP_NOTIFY_PREPARE,
 	CPUHP_BRINGUP_CPU,
 	CPUHP_AP_IDLE_DEAD,
@@ -17,6 +18,7 @@ enum cpuhp_state {
 	CPUHP_AP_IRQ_ARMADA_CASC_STARTING,
 	CPUHP_AP_IRQ_BCM2836_STARTING,
 	CPUHP_AP_ARM_MVEBU_COHERENCY,
+	CPUHP_AP_PERF_X86_STARTING,
 	CPUHP_AP_NOTIFY_STARTING,
 	CPUHP_AP_ONLINE,
 	CPUHP_TEARDOWN_CPU,
@@ -24,6 +26,7 @@ enum cpuhp_state {
 	CPUHP_AP_SMPBOOT_THREADS,
 	CPUHP_AP_X86_VDSO_VMA_ONLINE,
 	CPUHP_AP_PERF_ONLINE,
+	CPUHP_AP_PERF_X86_ONLINE,
 	CPUHP_AP_NOTIFY_ONLINE,
 	CPUHP_AP_ONLINE_DYN,
 	CPUHP_AP_ONLINE_DYN_END		= CPUHP_AP_ONLINE_DYN + 30,