Re: [PATCH v2] tracepoint: Fix out of sync data passing by static caller

[Peter Zijlstra]

On Thu, Oct 01, 2020 at 09:27:57PM -0400, Steven Rostedt wrote:
> From: Steven Rostedt (VMware) <rostedt@xxxxxxxxxxx>
> 
> Naresh reported a bug discovered in linux-next that I can reliably
> trigger myself. It appears to be a side effect of the static calls. It
> happens when going from more than one tracepoint callback to a single
> one, and removing the first callback on the list. The list of
> tracepoint callbacks holds data and a function to call with the
> parameters of that tracepoint and a handler to the associated data.
> 
>  old_list:
> 	0: func = foo; data = NULL;
> 	1: func = bar; data = &bar_struct;
> 
>  new_list:
> 	0: func = bar; data = &bar_struct;
> 
> 
> 	CPU 0				CPU 1
> 	-----				-----
>    tp_funcs = old_list;
>    tp_static_caller = tp_interator
> 
>    __DO_TRACE()
>  
>     data = tp_funcs[0].data = NULL;
> 
> 				   tp_funcs = new_list;
> 				   tracepoint_update_call()
> 				      tp_static_caller = tp_funcs[0] = bar;
>     tp_static_caller(data)
>        bar(data)
>          x = data->item = NULL->item
> 
>        BOOM!

> To solve this, add a tracepoint_synchronize_unregister() between
> changing tp_funcs and updating the static tracepoint, that does both a
> synchronize_rcu() and synchronize_srcu(). This will ensure that when
> the static call is updated to the single callback that it will be
> receiving the data that it registered with.

> Reported-by: Naresh Kamboju <naresh.kamboju@xxxxxxxxxx>
> Fixes: d25e37d89dd2f ("tracepoint: Optimize using static_call()")
> Signed-off-by: Steven Rostedt (VMware) <rostedt@xxxxxxxxxxx>
> ---

Urgh :/

I'll go stick this in tip/core/static_call.

> diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
> index 1b4be44d1d2b..3f659f855074 100644
> --- a/kernel/tracepoint.c
> +++ b/kernel/tracepoint.c
> @@ -221,7 +221,7 @@ static void *func_remove(struct tracepoint_func **funcs,
>  	return old;
>  }
>  
> -static void tracepoint_update_call(struct tracepoint *tp, struct tracepoint_func *tp_funcs)
> +static void tracepoint_update_call(struct tracepoint *tp, struct tracepoint_func *tp_funcs, bool sync)
>  {
>  	void *func = tp->iterator;
>  
> @@ -229,8 +229,17 @@ static void tracepoint_update_call(struct tracepoint *tp, struct tracepoint_func
>  	if (!tp->static_call_key)
>  		return;
>  
> -	if (!tp_funcs[1].func)
> +	if (!tp_funcs[1].func) {
>  		func = tp_funcs[0].func;
> +		/*
> +		 * If going from the iterator back to a single caller,
> +		 * we need to synchronize with __DO_TRACE to make sure
> +		 * that the data passed to the callback is the one that
> +		 * belongs to that callback.
> +		 */
> +		if (sync)
> +			tracepoint_synchronize_unregister();
> +	}
>  
>  	__static_call_update(tp->static_call_key, tp->static_call_tramp, func);
>  }
> @@ -265,7 +274,7 @@ static int tracepoint_add_func(struct tracepoint *tp,
>  	 * include/linux/tracepoint.h using rcu_dereference_sched().
>  	 */
>  	rcu_assign_pointer(tp->funcs, tp_funcs);
> -	tracepoint_update_call(tp, tp_funcs);
> +	tracepoint_update_call(tp, tp_funcs, false);
>  	static_key_enable(&tp->key);
>  
>  	release_probes(old);
> @@ -297,11 +306,12 @@ static int tracepoint_remove_func(struct tracepoint *tp,
>  			tp->unregfunc();
>  
>  		static_key_disable(&tp->key);
> +		rcu_assign_pointer(tp->funcs, tp_funcs);
>  	} else {
> -		tracepoint_update_call(tp, tp_funcs);
> +		rcu_assign_pointer(tp->funcs, tp_funcs);
> +		tracepoint_update_call(tp, tp_funcs,
> +				       tp_funcs[0].func != old[0].func);
>  	}
> -
> -	rcu_assign_pointer(tp->funcs, tp_funcs);
>  	release_probes(old);
>  	return 0;
>  }