Re: [tip: perf/core] perf/x86: Reset the dirty counter to prevent the leak for an RDPMC task

["Liang, Kan" <kan.liang@linux.intel.com>]

On 4/16/2021 12:45 PM, Peter Zijlstra wrote:
> On Fri, Apr 16, 2021 at 03:01:48PM -0000, tip-bot2 for Kan Liang wrote:
>> @@ -2331,6 +2367,9 @@ static void x86_pmu_event_unmapped(struct perf_event *event, struct mm_struct *m
>>   	if (!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED))
>>   		return;
>>   
>> +	if (x86_pmu.sched_task && event->hw.target)
>> +		perf_sched_cb_dec(event->ctx->pmu);
>> +
>>   	if (atomic_dec_and_test(&mm->context.perf_rdpmc_allowed))
>>   		on_each_cpu_mask(mm_cpumask(mm), cr4_update_pce, NULL, 1);
>>   }
> 
> 'perf test' on a kernel with CONFIG_DEBUG_PREEMPT=y gives:
> 
> [  244.439538] BUG: using smp_processor_id() in preemptible [00000000] code: perf/1771

If it's a preemptible env, I think we should disable the interrupts and 
preemption to protect the sched_cb_list.

Seems we don't need perf_ctx_lock() here. I don't think we touch the 
area in NMI. I think disabling the interrupts should be good enough to 
protect the cpuctx.

How about the below patch?

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index e34eb72..45630beed 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2333,6 +2333,8 @@ static void x86_pmu_clear_dirty_counters(void)

  static void x86_pmu_event_mapped(struct perf_event *event, struct 
mm_struct *mm)
  {
+	unsigned long flags;
+
  	if (!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED))
  		return;

@@ -2341,8 +2343,10 @@ static void x86_pmu_event_mapped(struct 
perf_event *event, struct mm_struct *mm)
  	 * and clear the existing dirty counters.
  	 */
  	if (x86_pmu.sched_task && event->hw.target) {
+		local_irq_save(flags);
  		perf_sched_cb_inc(event->ctx->pmu);
  		x86_pmu_clear_dirty_counters();
+		local_irq_restore(flags);
  	}

  	/*
@@ -2363,12 +2367,16 @@ static void x86_pmu_event_mapped(struct 
perf_event *event, struct mm_struct *mm)

  static void x86_pmu_event_unmapped(struct perf_event *event, struct 
mm_struct *mm)
  {
+	unsigned long flags;

  	if (!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED))
  		return;

-	if (x86_pmu.sched_task && event->hw.target)
+	if (x86_pmu.sched_task && event->hw.target) {
+		local_irq_save(flags);
  		perf_sched_cb_dec(event->ctx->pmu);
+		local_irq_restore(flags);
+	}

  	if (atomic_dec_and_test(&mm->context.perf_rdpmc_allowed))
  		on_each_cpu_mask(mm_cpumask(mm), cr4_update_pce, NULL, 1);

Thanks,
Kan