[PATCH v2] perf: Rewrite core context handling

[Peter Zijlstra]

On Wed, Oct 12, 2022 at 02:09:00PM +0530, Ravi Bangoria wrote:

> > @@ -3366,6 +3370,14 @@ static void perf_event_sync_stat(struct
> >  	}
> >  }
> >  
> > +#define list_for_each_entry_double(pos1, pos2, head1, head2, member)	\
> > +	for (pos1 = list_first_entry(head1, typeof(*pos1), member),	\
> > +	     pos2 = list_first_entry(head2, typeof(*pos2), member);	\
> > +	     !list_entry_is_head(pos1, head1, member) &&		\
> > +	     !list_entry_is_head(pos2, head2, member);			\
> > +	     pos1 = list_next_entry(pos1, member),			\
> > +	     pos2 = list_next_entry(pos2, member))
> > +
> >  static void perf_event_swap_task_ctx_data(struct perf_event_context *prev_ctx,
> >  					  struct perf_event_context *next_ctx)
> >  {
> > @@ -3374,16 +3386,9 @@ static void perf_event_swap_task_ctx_dat
> >  	if (!prev_ctx->nr_task_data)
> >  		return;
> >  
> > -	prev_epc = list_first_entry(&prev_ctx->pmu_ctx_list,
> > -				    struct perf_event_pmu_context,
> > -				    pmu_ctx_entry);
> > -	next_epc = list_first_entry(&next_ctx->pmu_ctx_list,
> > -				    struct perf_event_pmu_context,
> > -				    pmu_ctx_entry);
> > -
> > -	while (&prev_epc->pmu_ctx_entry != &prev_ctx->pmu_ctx_list &&
> > -	       &next_epc->pmu_ctx_entry != &next_ctx->pmu_ctx_list) {
> > -
> > +	list_for_each_entry_double(prev_epc, next_epc,
> > +				   &prev_ctx->pmu_ctx_list, &next_ctx->pmu_ctx_list,
> > +				   pmu_ctx_entry) {
> 
> There are more places which can use list_for_each_entry_double().
> I'll fix those.

I've gone and renamed it: double_list_for_each_entry(), but yeah, didn't
look too hard for other users.

> > @@ -4859,7 +4879,14 @@ static void put_pmu_ctx(struct perf_even
> >  	if (epc->ctx) {
> >  		struct perf_event_context *ctx = epc->ctx;
> >  
> > -		// XXX ctx->mutex
> > +		/*
> > +		 * XXX
> > +		 *
> > +		 * lockdep_assert_held(&ctx->mutex);
> > +		 *
> > +		 * can't because of the call-site in _free_event()/put_event()
> > +		 * which isn't always called under ctx->mutex.
> > +		 */
> 
> Yes. I came across the same and could not figure out how to solve
> this. So Just kept XXX as is.

Yeah, I can sorta fix it, but it's ugly so there we are.

> >  
> >  		WARN_ON_ONCE(list_empty(&epc->pmu_ctx_entry));
> >  		raw_spin_lock_irqsave(&ctx->lock, flags);

> > @@ -12657,6 +12675,13 @@ perf_event_create_kernel_counter(struct
> >  		goto err_unlock;
> >  	}
> >  
> > +	pmu_ctx = find_get_pmu_context(pmu, ctx, event);
> > +	if (IS_ERR(pmu_ctx)) {
> > +		err = PTR_ERR(pmu_ctx);
> > +		goto err_unlock;
> > +	}
> > +	event->pmu_ctx = pmu_ctx;
> 
> We should call find_get_pmu_context() with ctx->mutex held and thus
> above perf_event_create_kernel_counter() change. Is my understanding
> correct?

That's the intent yeah. But due to not always holding ctx->mutex over
put_pmu_ctx() this might be moot. I'm almost through auditing epc usage
and I think ctx->lock is sufficient, fingers crossed.

> > +
> >  	if (!task) {
> >  		/*
> >  		 * Check if the @cpu we're creating an event for is online.

> > @@ -12998,7 +13022,7 @@ void perf_event_free_task(struct task_st
> >  	struct perf_event_context *ctx;
> >  	struct perf_event *event, *tmp;
> >  
> > -	ctx = rcu_dereference(task->perf_event_ctxp);
> > +	ctx = rcu_access_pointer(task->perf_event_ctxp);
> 
> We dereference ctx pointer but with mutex and lock held. And thus
> rcu_access_pointer() is sufficient. Is my understanding correct?

We do not in fact hold ctx->lock here IIRC; but this is a NULL test, if
it is !NULL we know we have a reference on it and are good.