Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > linux.kernel > #1287193 > unrolled thread

Re: [tip:perf/core] perf: Add pmu specific data for perf task context

Started byPeter Zijlstra <peterz@infradead.org>
First post2015-12-09 09:40 +0100
Last post2015-12-09 16:30 +0100
Articles 4 — 2 participants

Back to article view | Back to linux.kernel

This discussion starts older than the indexed window; earlier articles aren't shown. The article labeled Started by below is the oldest one visible, not the original post.


Contents

  Re: [tip:perf/core] perf: Add pmu specific data for perf task context Peter Zijlstra <peterz@infradead.org> - 2015-12-09 09:40 +0100
    RE: [tip:perf/core] perf: Add pmu specific data for perf task  context "Liang, Kan" <kan.liang@intel.com> - 2015-12-09 16:00 +0100
      Re: [tip:perf/core] perf: Add pmu specific data for perf task context Peter Zijlstra <peterz@infradead.org> - 2015-12-09 16:20 +0100
        RE: [tip:perf/core] perf: Add pmu specific data for perf task  context "Liang, Kan" <kan.liang@intel.com> - 2015-12-09 16:30 +0100

#1287193 — Re: [tip:perf/core] perf: Add pmu specific data for perf task context

FromPeter Zijlstra <peterz@infradead.org>
Date2015-12-09 09:40 +0100
SubjectRe: [tip:perf/core] perf: Add pmu specific data for perf task context
Message-ID<qDIs1-5V9-9@gated-at.bofh.it>
On Wed, Feb 18, 2015 at 09:15:06AM -0800, tip-bot for Yan, Zheng wrote:
> +find_get_context(struct pmu *pmu, struct task_struct *task,
> +		struct perf_event *event)
>  {
>  	struct perf_event_context *ctx, *clone_ctx = NULL;
>  	struct perf_cpu_context *cpuctx;
> +	void *task_ctx_data = NULL;
>  	unsigned long flags;
>  	int ctxn, err;
> +	int cpu = event->cpu;
>  
>  	if (!task) {
>  		/* Must be root to operate on a CPU event: */
> @@ -3342,11 +3354,24 @@ find_get_context(struct pmu *pmu, struct task_struct *task, int cpu)
>  	if (ctxn < 0)
>  		goto errout;
>  
> +	if (event->attach_state & PERF_ATTACH_TASK_DATA) {
> +		task_ctx_data = kzalloc(pmu->task_ctx_size, GFP_KERNEL);
> +		if (!task_ctx_data) {
> +			err = -ENOMEM;
> +			goto errout;
> +		}
> +	}
> +
>  retry:
>  	ctx = perf_lock_task_context(task, ctxn, &flags);
>  	if (ctx) {
>  		clone_ctx = unclone_ctx(ctx);
>  		++ctx->pin_count;
> +
> +		if (task_ctx_data && !ctx->task_ctx_data) {
> +			ctx->task_ctx_data = task_ctx_data;
> +			task_ctx_data = NULL;
> +		}
>  		raw_spin_unlock_irqrestore(&ctx->lock, flags);
>  
>  		if (clone_ctx)
> @@ -3357,6 +3382,11 @@ retry:
>  		if (!ctx)
>  			goto errout;
>  
> +		if (task_ctx_data) {
> +			ctx->task_ctx_data = task_ctx_data;
> +			task_ctx_data = NULL;
> +		}
> +
>  		err = 0;
>  		mutex_lock(&task->perf_event_mutex);
>  		/*
> @@ -3383,9 +3413,11 @@ retry:
>  		}
>  	}
>  
> +	kfree(task_ctx_data);
>  	return ctx;
>  
>  errout:
> +	kfree(task_ctx_data);
>  	return ERR_PTR(err);
>  }


diff --git a/kernel/events/core.c b/kernel/events/core.c
index 36babfd..97aa610 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3508,11 +3515,6 @@ retry:
 		if (!ctx)
 			goto errout;
 
-		if (task_ctx_data) {
-			ctx->task_ctx_data = task_ctx_data;
-			task_ctx_data = NULL;
-		}
-
 		err = 0;
 		mutex_lock(&task->perf_event_mutex);
 		/*
@@ -3526,6 +3528,10 @@ retry:
 		else {
 			get_ctx(ctx);
 			++ctx->pin_count;
+			if (task_ctx_data) {
+				ctx->task_ctx_data = task_ctx_data;
+				task_ctx_data = NULL;
+			}
 			rcu_assign_pointer(task->perf_event_ctxp[ctxn], ctx);
 		}
 		mutex_unlock(&task->perf_event_mutex);


Does that make sense? No point in setting task_ctx_data if we're going
to free the ctx and try again.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [next] | [standalone]


#1287537 — RE: [tip:perf/core] perf: Add pmu specific data for perf task context

From"Liang, Kan" <kan.liang@intel.com>
Date2015-12-09 16:00 +0100
SubjectRE: [tip:perf/core] perf: Add pmu specific data for perf task context
Message-ID<qDOnL-1h9-5@gated-at.bofh.it>
In reply to#1287193
> 
> On Wed, Feb 18, 2015 at 09:15:06AM -0800, tip-bot for Yan, Zheng wrote:
> > +find_get_context(struct pmu *pmu, struct task_struct *task,
> > +		struct perf_event *event)
> >  {
> >  	struct perf_event_context *ctx, *clone_ctx = NULL;
> >  	struct perf_cpu_context *cpuctx;
> > +	void *task_ctx_data = NULL;
> >  	unsigned long flags;
> >  	int ctxn, err;
> > +	int cpu = event->cpu;
> >
> >  	if (!task) {
> >  		/* Must be root to operate on a CPU event: */ @@ -
> 3342,11 +3354,24
> > @@ find_get_context(struct pmu *pmu, struct task_struct *task, int cpu)
> >  	if (ctxn < 0)
> >  		goto errout;
> >
> > +	if (event->attach_state & PERF_ATTACH_TASK_DATA) {
> > +		task_ctx_data = kzalloc(pmu->task_ctx_size, GFP_KERNEL);
> > +		if (!task_ctx_data) {
> > +			err = -ENOMEM;
> > +			goto errout;
> > +		}
> > +	}
> > +
> >  retry:
> >  	ctx = perf_lock_task_context(task, ctxn, &flags);
> >  	if (ctx) {
> >  		clone_ctx = unclone_ctx(ctx);
> >  		++ctx->pin_count;
> > +
> > +		if (task_ctx_data && !ctx->task_ctx_data) {
> > +			ctx->task_ctx_data = task_ctx_data;
> > +			task_ctx_data = NULL;
> > +		}
> >  		raw_spin_unlock_irqrestore(&ctx->lock, flags);
> >
> >  		if (clone_ctx)
> > @@ -3357,6 +3382,11 @@ retry:
> >  		if (!ctx)
> >  			goto errout;
> >
> > +		if (task_ctx_data) {
> > +			ctx->task_ctx_data = task_ctx_data;
> > +			task_ctx_data = NULL;
> > +		}
> > +
> >  		err = 0;
> >  		mutex_lock(&task->perf_event_mutex);
> >  		/*
> > @@ -3383,9 +3413,11 @@ retry:
> >  		}
> >  	}
> >
> > +	kfree(task_ctx_data);
> >  	return ctx;
> >
> >  errout:
> > +	kfree(task_ctx_data);
> >  	return ERR_PTR(err);
> >  }
> 
> 
> diff --git a/kernel/events/core.c b/kernel/events/core.c index
> 36babfd..97aa610 100644
> --- a/kernel/events/core.c
> +++ b/kernel/events/core.c
> @@ -3508,11 +3515,6 @@ retry:
>  		if (!ctx)
>  			goto errout;
> 
> -		if (task_ctx_data) {
> -			ctx->task_ctx_data = task_ctx_data;
> -			task_ctx_data = NULL;
> -		}
> -
>  		err = 0;
>  		mutex_lock(&task->perf_event_mutex);
>  		/*
> @@ -3526,6 +3528,10 @@ retry:
>  		else {
>  			get_ctx(ctx);
>  			++ctx->pin_count;
> +			if (task_ctx_data) {
> +				ctx->task_ctx_data = task_ctx_data;
> +				task_ctx_data = NULL;
> +			}
>  			rcu_assign_pointer(task->perf_event_ctxp[ctxn],
> ctx);
>  		}
>  		mutex_unlock(&task->perf_event_mutex);
> 
> 
> Does that make sense? No point in setting task_ctx_data if we're going to
> free the ctx and try again.

The task_ctx_data will be checked before use. So it wouldn't crash the
system if it's NULL.
The problem is that LBR stack info will not be save/store on context switch
anymore. The user probably get wrong call stack information.
May I know why you want to do that?

Thanks,
Kan


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [prev] | [next] | [standalone]


#1287554

FromPeter Zijlstra <peterz@infradead.org>
Date2015-12-09 16:20 +0100
Message-ID<qDOH8-1CS-13@gated-at.bofh.it>
In reply to#1287537
On Wed, Dec 09, 2015 at 02:59:21PM +0000, Liang, Kan wrote:
> > diff --git a/kernel/events/core.c b/kernel/events/core.c index
> > 36babfd..97aa610 100644
> > --- a/kernel/events/core.c
> > +++ b/kernel/events/core.c
> > @@ -3508,11 +3515,6 @@ retry:
> >  		if (!ctx)
> >  			goto errout;
> > 
> > -		if (task_ctx_data) {
> > -			ctx->task_ctx_data = task_ctx_data;
> > -			task_ctx_data = NULL;
> > -		}
> > -
> >  		err = 0;
> >  		mutex_lock(&task->perf_event_mutex);
> >  		/*
> > @@ -3526,6 +3528,10 @@ retry:
> >  		else {
> >  			get_ctx(ctx);
> >  			++ctx->pin_count;
> > +			if (task_ctx_data) {
> > +				ctx->task_ctx_data = task_ctx_data;
> > +				task_ctx_data = NULL;
> > +			}
> >  			rcu_assign_pointer(task->perf_event_ctxp[ctxn],
> > ctx);
> >  		}
> >  		mutex_unlock(&task->perf_event_mutex);
> > 
> > 
> > Does that make sense? No point in setting task_ctx_data if we're going to
> > free the ctx and try again.
> 
> The task_ctx_data will be checked before use. So it wouldn't crash the
> system if it's NULL.

Yeah, I know, I checked :-)

> The problem is that LBR stack info will not be save/store on context
> switch anymore. The user probably get wrong call stack information.

Yep

> May I know why you want to do that?

Because this seemed like a less fragile construct. When there's multiple
event creations racing it seems possible (ableit entirely unlikely) to
assign the allocated task_ctx_data to a ctx that we'll delete, and on
the second go around re-allocate a ctx, but are left wihtout
task_ctx_data to assign to it.

So by only assigning the task_ctx_data when we _know_ we've succeeded,
we'll avoid this scenario.


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [prev] | [next] | [standalone]


#1287575 — RE: [tip:perf/core] perf: Add pmu specific data for perf task context

From"Liang, Kan" <kan.liang@intel.com>
Date2015-12-09 16:30 +0100
SubjectRE: [tip:perf/core] perf: Add pmu specific data for perf task context
Message-ID<qDOQO-1FV-27@gated-at.bofh.it>
In reply to#1287554
> 
> On Wed, Dec 09, 2015 at 02:59:21PM +0000, Liang, Kan wrote:
> > > diff --git a/kernel/events/core.c b/kernel/events/core.c index
> > > 36babfd..97aa610 100644
> > > --- a/kernel/events/core.c
> > > +++ b/kernel/events/core.c
> > > @@ -3508,11 +3515,6 @@ retry:
> > >  		if (!ctx)
> > >  			goto errout;
> > >
> > > -		if (task_ctx_data) {
> > > -			ctx->task_ctx_data = task_ctx_data;
> > > -			task_ctx_data = NULL;
> > > -		}
> > > -
> > >  		err = 0;
> > >  		mutex_lock(&task->perf_event_mutex);
> > >  		/*
> > > @@ -3526,6 +3528,10 @@ retry:
> > >  		else {
> > >  			get_ctx(ctx);
> > >  			++ctx->pin_count;
> > > +			if (task_ctx_data) {
> > > +				ctx->task_ctx_data = task_ctx_data;
> > > +				task_ctx_data = NULL;
> > > +			}
> > >  			rcu_assign_pointer(task->perf_event_ctxp[ctxn],
> > > ctx);
> > >  		}
> > >  		mutex_unlock(&task->perf_event_mutex);
> > >
> > >
> > > Does that make sense? No point in setting task_ctx_data if we're
> > > going to free the ctx and try again.
> >
> > The task_ctx_data will be checked before use. So it wouldn't crash the
> > system if it's NULL.
> 
> Yeah, I know, I checked :-)
> 
> > The problem is that LBR stack info will not be save/store on context
> > switch anymore. The user probably get wrong call stack information.
> 
> Yep
> 
> > May I know why you want to do that?
> 
> Because this seemed like a less fragile construct. When there's multiple
> event creations racing it seems possible (ableit entirely unlikely) to assign
> the allocated task_ctx_data to a ctx that we'll delete, and on the second go
> around re-allocate a ctx, but are left wihtout task_ctx_data to assign to it.
> 
> So by only assigning the task_ctx_data when we _know_ we've succeeded,
> we'll avoid this scenario.

Yes, I think it make sense to that.

Thanks,
Kan


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [prev] | [standalone]


Back to top | Article view | linux.kernel


csiph-web