Re: [PATCH v4 05/38] perf: Add generic exclude_guest support

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

On 2025-05-21 3:55 p.m., Namhyung Kim wrote:
> On Mon, Mar 24, 2025 at 05:30:45PM +0000, Mingwei Zhang wrote:
>> From: Kan Liang <kan.liang@linux.intel.com>
>>
>> Only KVM knows the exact time when a guest is entering/exiting. Expose
>> two interfaces to KVM to switch the ownership of the PMU resources.
>>
>> All the pinned events must be scheduled in first. Extend the
>> perf_event_sched_in() helper to support extra flag, e.g., EVENT_GUEST.
>>
>> Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
>> Signed-off-by: Mingwei Zhang <mizhang@google.com>
>> ---
>>  include/linux/perf_event.h |  4 ++
>>  kernel/events/core.c       | 80 ++++++++++++++++++++++++++++++++++----
>>  2 files changed, 77 insertions(+), 7 deletions(-)
>>
>> diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
>> index 7bda1e20be12..37187ee8e226 100644
>> --- a/include/linux/perf_event.h
>> +++ b/include/linux/perf_event.h
>> @@ -1822,6 +1822,8 @@ extern int perf_event_period(struct perf_event *event, u64 value);
>>  extern u64 perf_event_pause(struct perf_event *event, bool reset);
>>  int perf_get_mediated_pmu(void);
>>  void perf_put_mediated_pmu(void);
>> +void perf_guest_enter(void);
>> +void perf_guest_exit(void);
>>  #else /* !CONFIG_PERF_EVENTS: */
>>  static inline void *
>>  perf_aux_output_begin(struct perf_output_handle *handle,
>> @@ -1919,6 +1921,8 @@ static inline int perf_get_mediated_pmu(void)
>>  }
>>  
>>  static inline void perf_put_mediated_pmu(void)			{ }
>> +static inline void perf_guest_enter(void)			{ }
>> +static inline void perf_guest_exit(void)			{ }
>>  #endif
>>  
>>  #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL)
>> diff --git a/kernel/events/core.c b/kernel/events/core.c
>> index 7a2115b2c5c1..d05487d465c9 100644
>> --- a/kernel/events/core.c
>> +++ b/kernel/events/core.c
>> @@ -2827,14 +2827,15 @@ static void task_ctx_sched_out(struct perf_event_context *ctx,
>>  
>>  static void perf_event_sched_in(struct perf_cpu_context *cpuctx,
>>  				struct perf_event_context *ctx,
>> -				struct pmu *pmu)
>> +				struct pmu *pmu,
>> +				enum event_type_t event_type)
>>  {
>> -	ctx_sched_in(&cpuctx->ctx, pmu, EVENT_PINNED);
>> +	ctx_sched_in(&cpuctx->ctx, pmu, EVENT_PINNED | event_type);
>>  	if (ctx)
>> -		 ctx_sched_in(ctx, pmu, EVENT_PINNED);
>> -	ctx_sched_in(&cpuctx->ctx, pmu, EVENT_FLEXIBLE);
>> +		ctx_sched_in(ctx, pmu, EVENT_PINNED | event_type);
>> +	ctx_sched_in(&cpuctx->ctx, pmu, EVENT_FLEXIBLE | event_type);
>>  	if (ctx)
>> -		 ctx_sched_in(ctx, pmu, EVENT_FLEXIBLE);
>> +		ctx_sched_in(ctx, pmu, EVENT_FLEXIBLE | event_type);
>>  }
>>  
>>  /*
>> @@ -2890,7 +2891,7 @@ static void ctx_resched(struct perf_cpu_context *cpuctx,
>>  	else if (event_type & EVENT_PINNED)
>>  		ctx_sched_out(&cpuctx->ctx, pmu, EVENT_FLEXIBLE);
>>  
>> -	perf_event_sched_in(cpuctx, task_ctx, pmu);
>> +	perf_event_sched_in(cpuctx, task_ctx, pmu, 0);
>>  
>>  	for_each_epc(epc, &cpuctx->ctx, pmu, 0)
>>  		perf_pmu_enable(epc->pmu);
>> @@ -4188,7 +4189,7 @@ static void perf_event_context_sched_in(struct task_struct *task)
>>  		ctx_sched_out(&cpuctx->ctx, NULL, EVENT_FLEXIBLE);
>>  	}
>>  
>> -	perf_event_sched_in(cpuctx, ctx, NULL);
>> +	perf_event_sched_in(cpuctx, ctx, NULL, 0);
>>  
>>  	perf_ctx_sched_task_cb(cpuctx->task_ctx, true);
>>  
>> @@ -6040,6 +6041,71 @@ void perf_put_mediated_pmu(void)
>>  }
>>  EXPORT_SYMBOL_GPL(perf_put_mediated_pmu);
>>  
>> +static inline void perf_host_exit(struct perf_cpu_context *cpuctx)
>> +{
>> +	perf_ctx_disable(&cpuctx->ctx, EVENT_GUEST);
>> +	ctx_sched_out(&cpuctx->ctx, NULL, EVENT_GUEST);
>> +	perf_ctx_enable(&cpuctx->ctx, EVENT_GUEST);
>> +	if (cpuctx->task_ctx) {
>> +		perf_ctx_disable(cpuctx->task_ctx, EVENT_GUEST);
>> +		task_ctx_sched_out(cpuctx->task_ctx, NULL, EVENT_GUEST);
>> +		perf_ctx_enable(cpuctx->task_ctx, EVENT_GUEST);
>> +	}
>> +}
> 
> Cpu context and task context may have events in the same PMU.
> How about this?
> 
> 	perf_ctx_disable(&cpuctx->ctx, EVENT_GUEST);
> 	if (cpuctx->task_ctx)
> 		perf_ctx_disable(cpuctx->task_ctx, EVENT_GUEST);
> 
> 	ctx_sched_out(&cpuctx->ctx, NULL, EVENT_GUEST);
> 	if (cpuctx->task_ctx)
> 		task_ctx_sched_out(cpuctx->task_ctx, NULL, EVENT_GUEST);
> 
> 	if (cpuctx->task_ctx)
> 		perf_ctx_enable(cpuctx->task_ctx, EVENT_GUEST);
> 	perf_ctx_enable(&cpuctx->ctx, EVENT_GUEST);
> 

Yes, this is what has to be fixed in V4.

No matter for load context or put context, I think the below steps have
to be followed.
- Disable both cpuctx->ctx and cpuctx->task_ctx
- schedule in/out host counters and load/put guest countext
- Enable both cpuctx->ctx and cpuctx->task_ctx

A similar proposed can be found at
https://lore.kernel.org/lkml/4aaf67ab-aa5c-41e6-bced-3cb000172c52@linux.intel.com/

Thanks,
Kan