perf/x86/intel: Add cpu_(prepare|starting|dying) for core_pmu

The core_pmu does not define cpu_* callbacks, which handles
allocation of 'struct cpu_hw_events::shared_regs' data,
initialization of debug store and PMU_FL_EXCL_CNTRS counters.

While this probably won't happen on bare metal, virtual CPU can
define x86_pmu.extra_regs together with PMU version 1 and thus
be using core_pmu -> using shared_regs data without it being
allocated. That could could leave to following panic:

	BUG: unable to handle kernel NULL pointer dereference at (null)
	IP: [<ffffffff8152cd4f>] _spin_lock_irqsave+0x1f/0x40

	SNIP

	 [<ffffffff81024bd9>] __intel_shared_reg_get_constraints+0x69/0x1e0
	 [<ffffffff81024deb>] intel_get_event_constraints+0x9b/0x180
	 [<ffffffff8101e815>] x86_schedule_events+0x75/0x1d0
	 [<ffffffff810586dc>] ? check_preempt_curr+0x7c/0x90
	 [<ffffffff810649fe>] ? try_to_wake_up+0x24e/0x3e0
	 [<ffffffff81064ba2>] ? default_wake_function+0x12/0x20
	 [<ffffffff8109eb16>] ? autoremove_wake_function+0x16/0x40
	 [<ffffffff810577e9>] ? __wake_up_common+0x59/0x90
	 [<ffffffff811a9517>] ? __d_lookup+0xa7/0x150
	 [<ffffffff8119db5f>] ? do_lookup+0x9f/0x230
	 [<ffffffff811a993a>] ? dput+0x9a/0x150
	 [<ffffffff8119c8f5>] ? path_to_nameidata+0x25/0x60
	 [<ffffffff8119e90a>] ? __link_path_walk+0x7da/0x1000
	 [<ffffffff8101d8f9>] ? x86_pmu_add+0xb9/0x170
	 [<ffffffff8101d7a7>] x86_pmu_commit_txn+0x67/0xc0
	 [<ffffffff811b07b0>] ? mntput_no_expire+0x30/0x110
	 [<ffffffff8119c731>] ? path_put+0x31/0x40
	 [<ffffffff8107c297>] ? current_fs_time+0x27/0x30
	 [<ffffffff8117d170>] ? mem_cgroup_get_reclaim_stat_from_page+0x20/0x70
	 [<ffffffff8111b7aa>] group_sched_in+0x13a/0x170
	 [<ffffffff81014a29>] ? sched_clock+0x9/0x10
	 [<ffffffff8111bac8>] ctx_sched_in+0x2e8/0x330
	 [<ffffffff8111bb7b>] perf_event_sched_in+0x6b/0xb0
	 [<ffffffff8111bc36>] perf_event_context_sched_in+0x76/0xc0
	 [<ffffffff8111eb3b>] perf_event_comm+0x1bb/0x2e0
	 [<ffffffff81195ee9>] set_task_comm+0x69/0x80
	 [<ffffffff81195fe1>] setup_new_exec+0xe1/0x2e0
	 [<ffffffff811ea68e>] load_elf_binary+0x3ce/0x1ab0

Adding cpu_(prepare|starting|dying) for core_pmu to have
shared_regs data allocated for core_pmu. AFAICS there's no harm
to initialize debug store and PMU_FL_EXCL_CNTRS either for
core_pmu.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/20150421152623.GC13169@krava.redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/kernel/cpu/perf_event_intel.c

@@ -2533,34 +2533,6 @@ ssize_t intel_event_sysfs_show(char *page, u64 config)
 	return x86_event_sysfs_show(page, config, event);
 }
 
-static __initconst const struct x86_pmu core_pmu = {
-	.name			= "core",
-	.handle_irq		= x86_pmu_handle_irq,
-	.disable_all		= x86_pmu_disable_all,
-	.enable_all		= core_pmu_enable_all,
-	.enable			= core_pmu_enable_event,
-	.disable		= x86_pmu_disable_event,
-	.hw_config		= x86_pmu_hw_config,
-	.schedule_events	= x86_schedule_events,
-	.eventsel		= MSR_ARCH_PERFMON_EVENTSEL0,
-	.perfctr		= MSR_ARCH_PERFMON_PERFCTR0,
-	.event_map		= intel_pmu_event_map,
-	.max_events		= ARRAY_SIZE(intel_perfmon_event_map),
-	.apic			= 1,
-	/*
-	 * Intel PMCs cannot be accessed sanely above 32 bit width,
-	 * so we install an artificial 1<<31 period regardless of
-	 * the generic event period:
-	 */
-	.max_period		= (1ULL << 31) - 1,
-	.get_event_constraints	= intel_get_event_constraints,
-	.put_event_constraints	= intel_put_event_constraints,
-	.event_constraints	= intel_core_event_constraints,
-	.guest_get_msrs		= core_guest_get_msrs,
-	.format_attrs		= intel_arch_formats_attr,
-	.events_sysfs_show	= intel_event_sysfs_show,
-};
-
 struct intel_shared_regs *allocate_shared_regs(int cpu)
 {
 	struct intel_shared_regs *regs;
@@ -2743,6 +2715,44 @@ static struct attribute *intel_arch3_formats_attr[] = {
 	NULL,
 };
 
+static __initconst const struct x86_pmu core_pmu = {
+	.name			= "core",
+	.handle_irq		= x86_pmu_handle_irq,
+	.disable_all		= x86_pmu_disable_all,
+	.enable_all		= core_pmu_enable_all,
+	.enable			= core_pmu_enable_event,
+	.disable		= x86_pmu_disable_event,
+	.hw_config		= x86_pmu_hw_config,
+	.schedule_events	= x86_schedule_events,
+	.eventsel		= MSR_ARCH_PERFMON_EVENTSEL0,
+	.perfctr		= MSR_ARCH_PERFMON_PERFCTR0,
+	.event_map		= intel_pmu_event_map,
+	.max_events		= ARRAY_SIZE(intel_perfmon_event_map),
+	.apic			= 1,
+	/*
+	 * Intel PMCs cannot be accessed sanely above 32-bit width,
+	 * so we install an artificial 1<<31 period regardless of
+	 * the generic event period:
+	 */
+	.max_period		= (1ULL<<31) - 1,
+	.get_event_constraints	= intel_get_event_constraints,
+	.put_event_constraints	= intel_put_event_constraints,
+	.event_constraints	= intel_core_event_constraints,
+	.guest_get_msrs		= core_guest_get_msrs,
+	.format_attrs		= intel_arch_formats_attr,
+	.events_sysfs_show	= intel_event_sysfs_show,
+
+	/*
+	 * Virtual (or funny metal) CPU can define x86_pmu.extra_regs
+	 * together with PMU version 1 and thus be using core_pmu with
+	 * shared_regs. We need following callbacks here to allocate
+	 * it properly.
+	 */
+	.cpu_prepare		= intel_pmu_cpu_prepare,
+	.cpu_starting		= intel_pmu_cpu_starting,
+	.cpu_dying		= intel_pmu_cpu_dying,
+};
+
 static __initconst const struct x86_pmu intel_pmu = {
 	.name			= "Intel",
 	.handle_irq		= intel_pmu_handle_irq,