perf, x86: Fix AMD hotplug & constraint initialization

Commit 3f6da390 ("perf: Rework and fix the arch CPU-hotplug hooks") moved
the amd northbridge allocation from CPUS_ONLINE to CPUS_PREPARE_UP
however amd_nb_id() doesn't work yet on prepare so it would simply bail
basically reverting to a state where we do not properly track node wide
constraints - causing weird perf results.

Fix up the AMD NorthBridge initialization code by allocating from
CPU_UP_PREPARE and installing it from CPU_STARTING once we have the
proper nb_id. It also properly deals with the allocation failing.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
[ robustify using amd_has_nb() ]
Signed-off-by: Stephane Eranian <eranian@google.com>
LKML-Reference: <1269353485.5109.48.camel@twins>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

arch/x86/kernel/cpu/perf_event.c

@@ -158,7 +158,7 @@ struct x86_pmu {
 						 struct perf_event *event);
 	struct event_constraint *event_constraints;
 
-	void		(*cpu_prepare)(int cpu);
+	int		(*cpu_prepare)(int cpu);
 	void		(*cpu_starting)(int cpu);
 	void		(*cpu_dying)(int cpu);
 	void		(*cpu_dead)(int cpu);
@@ -1333,11 +1333,12 @@ static int __cpuinit
 x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
 {
 	unsigned int cpu = (long)hcpu;
+	int ret = NOTIFY_OK;
 
 	switch (action & ~CPU_TASKS_FROZEN) {
 	case CPU_UP_PREPARE:
 		if (x86_pmu.cpu_prepare)
-			x86_pmu.cpu_prepare(cpu);
+			ret = x86_pmu.cpu_prepare(cpu);
 		break;
 
 	case CPU_STARTING:
@@ -1350,6 +1351,7 @@ x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
 			x86_pmu.cpu_dying(cpu);
 		break;
 
+	case CPU_UP_CANCELED:
 	case CPU_DEAD:
 		if (x86_pmu.cpu_dead)
 			x86_pmu.cpu_dead(cpu);
@@ -1359,7 +1361,7 @@ x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
 		break;
 	}
 
-	return NOTIFY_OK;
+	return ret;
 }
 
 static void __init pmu_check_apic(void)

arch/x86/kernel/cpu/perf_event_amd.c

@@ -137,6 +137,13 @@ static inline int amd_is_nb_event(struct hw_perf_event *hwc)
 	return (hwc->config & 0xe0) == 0xe0;
 }
 
+static inline int amd_has_nb(struct cpu_hw_events *cpuc)
+{
+	struct amd_nb *nb = cpuc->amd_nb;
+
+	return nb && nb->nb_id != -1;
+}
+
 static void amd_put_event_constraints(struct cpu_hw_events *cpuc,
 				      struct perf_event *event)
 {
@@ -147,7 +154,7 @@ static void amd_put_event_constraints(struct cpu_hw_events *cpuc,
 	/*
 	 * only care about NB events
 	 */
-	if (!(nb && amd_is_nb_event(hwc)))
+	if (!(amd_has_nb(cpuc) && amd_is_nb_event(hwc)))
 		return;
 
 	/*
@@ -214,7 +221,7 @@ amd_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
 	/*
 	 * if not NB event or no NB, then no constraints
 	 */
-	if (!(nb && amd_is_nb_event(hwc)))
+	if (!(amd_has_nb(cpuc) && amd_is_nb_event(hwc)))
 		return &unconstrained;
 
 	/*
@@ -293,51 +300,55 @@ static struct amd_nb *amd_alloc_nb(int cpu, int nb_id)
 	return nb;
 }
 
-static void amd_pmu_cpu_online(int cpu)
+static int amd_pmu_cpu_prepare(int cpu)
+{
+	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
+
+	WARN_ON_ONCE(cpuc->amd_nb);
+
+	if (boot_cpu_data.x86_max_cores < 2)
+		return NOTIFY_OK;
+
+	cpuc->amd_nb = amd_alloc_nb(cpu, -1);
+	if (!cpuc->amd_nb)
+		return NOTIFY_BAD;
+
+	return NOTIFY_OK;
+}
+
+static void amd_pmu_cpu_starting(int cpu)
 {
-	struct cpu_hw_events *cpu1, *cpu2;
-	struct amd_nb *nb = NULL;
+	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
+	struct amd_nb *nb;
 	int i, nb_id;
 
 	if (boot_cpu_data.x86_max_cores < 2)
 		return;
 
-	/*
-	 * function may be called too early in the
-	 * boot process, in which case nb_id is bogus
-	 */
 	nb_id = amd_get_nb_id(cpu);
-	if (nb_id == BAD_APICID)
-		return;
-
-	cpu1 = &per_cpu(cpu_hw_events, cpu);
-	cpu1->amd_nb = NULL;
+	WARN_ON_ONCE(nb_id == BAD_APICID);
 
 	raw_spin_lock(&amd_nb_lock);
 
 	for_each_online_cpu(i) {
-		cpu2 = &per_cpu(cpu_hw_events, i);
-		nb = cpu2->amd_nb;
-		if (!nb)
+		nb = per_cpu(cpu_hw_events, i).amd_nb;
+		if (WARN_ON_ONCE(!nb))
 			continue;
-		if (nb->nb_id == nb_id)
-			goto found;
-	}
 
-	nb = amd_alloc_nb(cpu, nb_id);
-	if (!nb) {
-		pr_err("perf_events: failed NB allocation for CPU%d\n", cpu);
-		raw_spin_unlock(&amd_nb_lock);
-		return;
+		if (nb->nb_id == nb_id) {
+			kfree(cpuc->amd_nb);
+			cpuc->amd_nb = nb;
+			break;
 		}
-found:
-	nb->refcnt++;
-	cpu1->amd_nb = nb;
+	}
+
+	cpuc->amd_nb->nb_id = nb_id;
+	cpuc->amd_nb->refcnt++;
 
 	raw_spin_unlock(&amd_nb_lock);
 }
 
-static void amd_pmu_cpu_offline(int cpu)
+static void amd_pmu_cpu_dead(int cpu)
 {
 	struct cpu_hw_events *cpuhw;
 
@@ -349,8 +360,10 @@ static void amd_pmu_cpu_offline(int cpu)
 	raw_spin_lock(&amd_nb_lock);
 
 	if (cpuhw->amd_nb) {
-		if (--cpuhw->amd_nb->refcnt == 0)
-			kfree(cpuhw->amd_nb);
+		struct amd_nb *nb = cpuhw->amd_nb;
+
+		if (nb->nb_id == -1 || --nb->refcnt == 0)
+			kfree(nb);
 
 		cpuhw->amd_nb = NULL;
 	}
@@ -379,8 +392,9 @@ static __initconst struct x86_pmu amd_pmu = {
 	.get_event_constraints	= amd_get_event_constraints,
 	.put_event_constraints	= amd_put_event_constraints,
 
-	.cpu_prepare		= amd_pmu_cpu_online,
-	.cpu_dead		= amd_pmu_cpu_offline,
+	.cpu_prepare		= amd_pmu_cpu_prepare,
+	.cpu_starting		= amd_pmu_cpu_starting,
+	.cpu_dead		= amd_pmu_cpu_dead,
 };
 
 static __init int amd_pmu_init(void)