perf/x86/intel/rapl: Make package handling more robust

The package management code in RAPL relies on package mapping being
available before a CPU is started. This changed with:

  9d85eb91 ("x86/smpboot: Make logical package management more robust")

because the ACPI/BIOS information turned out to be unreliable, but that
left RAPL in broken state. This was not noticed because on a regular boot
all CPUs are online before RAPL is initialized.

A possible fix would be to reintroduce the mess which allocates a package
data structure in CPU prepare and when it turns out to already exist in
starting throw it away later in the CPU online callback. But that's a
horrible hack and not required at all because RAPL becomes functional for
perf only in the CPU online callback. That's correct because user space is
not yet informed about the CPU being onlined, so nothing caan rely on RAPL
being available on that particular CPU.

Move the allocation to the CPU online callback and simplify the hotplug
handling. At this point the package mapping is established and correct.

This also adds a missing check for available package data in the
event_init() function.
Reported-by: Yasuaki Ishimatsu <yasu.isimatu@gmail.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sebastian Siewior <bigeasy@linutronix.de>
Cc: Stephane Eranian <eranian@google.com>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Fixes: 9d85eb91 ("x86/smpboot: Make logical package management more robust")
Link: http://lkml.kernel.org/r/20170131230141.212593966@linutronix.deSigned-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/events/intel/rapl.c

@@ -161,7 +161,13 @@ static u64 rapl_timer_ms;
 
 static inline struct rapl_pmu *cpu_to_rapl_pmu(unsigned int cpu)
 {
-	return rapl_pmus->pmus[topology_logical_package_id(cpu)];
+	unsigned int pkgid = topology_logical_package_id(cpu);
+
+	/*
+	 * The unsigned check also catches the '-1' return value for non
+	 * existent mappings in the topology map.
+	 */
+	return pkgid < rapl_pmus->maxpkg ? rapl_pmus->pmus[pkgid] : NULL;
 }
 
 static inline u64 rapl_read_counter(struct perf_event *event)
@@ -402,6 +408,8 @@ static int rapl_pmu_event_init(struct perf_event *event)
 
 	/* must be done before validate_group */
 	pmu = cpu_to_rapl_pmu(event->cpu);
+	if (!pmu)
+		return -EINVAL;
 	event->cpu = pmu->cpu;
 	event->pmu_private = pmu;
 	event->hw.event_base = msr;
@@ -585,26 +593,7 @@ static int rapl_cpu_online(unsigned int cpu)
 	struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
 	int target;
 
-	/*
-	 * Check if there is an online cpu in the package which collects rapl
-	 * events already.
-	 */
-	target = cpumask_any_and(&rapl_cpu_mask, topology_core_cpumask(cpu));
-	if (target < nr_cpu_ids)
-		return 0;
-
-	cpumask_set_cpu(cpu, &rapl_cpu_mask);
-	pmu->cpu = cpu;
-	return 0;
-}
-
-static int rapl_cpu_prepare(unsigned int cpu)
-{
-	struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
-
-	if (pmu)
-		return 0;
-
+	if (!pmu) {
 		pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu));
 		if (!pmu)
 			return -ENOMEM;
@@ -613,9 +602,21 @@ static int rapl_cpu_prepare(unsigned int cpu)
 		INIT_LIST_HEAD(&pmu->active_list);
 		pmu->pmu = &rapl_pmus->pmu;
 		pmu->timer_interval = ms_to_ktime(rapl_timer_ms);
-	pmu->cpu = -1;
 		rapl_hrtimer_init(pmu);
+
 		rapl_pmus->pmus[topology_logical_package_id(cpu)] = pmu;
+	}
+
+	/*
+	 * Check if there is an online cpu in the package which collects rapl
+	 * events already.
+	 */
+	target = cpumask_any_and(&rapl_cpu_mask, topology_core_cpumask(cpu));
+	if (target < nr_cpu_ids)
+		return 0;
+
+	cpumask_set_cpu(cpu, &rapl_cpu_mask);
+	pmu->cpu = cpu;
 	return 0;
 }
 
@@ -803,29 +804,21 @@ static int __init rapl_pmu_init(void)
 	/*
 	 * Install callbacks. Core will call them for each online cpu.
 	 */
-
-	ret = cpuhp_setup_state(CPUHP_PERF_X86_RAPL_PREP, "perf/x86/rapl:prepare",
-				rapl_cpu_prepare, NULL);
-	if (ret)
-		goto out;
-
 	ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_RAPL_ONLINE,
 				"perf/x86/rapl:online",
 				rapl_cpu_online, rapl_cpu_offline);
 	if (ret)
-		goto out1;
+		goto out;
 
 	ret = perf_pmu_register(&rapl_pmus->pmu, "power", -1);
 	if (ret)
-		goto out2;
+		goto out1;
 
 	rapl_advertise();
 	return 0;
 
-out2:
-	cpuhp_remove_state(CPUHP_AP_PERF_X86_RAPL_ONLINE);
 out1:
-	cpuhp_remove_state(CPUHP_PERF_X86_RAPL_PREP);
+	cpuhp_remove_state(CPUHP_AP_PERF_X86_RAPL_ONLINE);
 out:
 	pr_warn("Initialization failed (%d), disabled\n", ret);
 	cleanup_rapl_pmus();
@@ -836,7 +829,6 @@ module_init(rapl_pmu_init);
 static void __exit intel_rapl_exit(void)
 {
 	cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_RAPL_ONLINE);
-	cpuhp_remove_state_nocalls(CPUHP_PERF_X86_RAPL_PREP);
 	perf_pmu_unregister(&rapl_pmus->pmu);
 	cleanup_rapl_pmus();
 }

include/linux/cpuhotplug.h

@@ -10,7 +10,6 @@ enum cpuhp_state {
 	CPUHP_PERF_X86_PREPARE,
 	CPUHP_PERF_X86_UNCORE_PREP,
 	CPUHP_PERF_X86_AMD_UNCORE_PREP,
-	CPUHP_PERF_X86_RAPL_PREP,
 	CPUHP_PERF_BFIN,
 	CPUHP_PERF_POWER,
 	CPUHP_PERF_SUPERH,