Re: [PATCH] tracing: Allow perf to read synthetic events

[Jiri Olsa <olsajiri@gmail.com>]

On Wed, Dec 17, 2025 at 11:39:20AM -0500, Steven Rostedt wrote:
> From: Steven Rostedt <rostedt@goodmis.org>
> 
> Currently, perf can not enable synthetic events. When it does, it either
> causes a warning in the kernel or errors with "no such device".
> 
> Add the necessary code to allow perf to also attach to synthetic events.
> 
> Reported-by: Ian Rogers <irogers@google.com>
> Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>

hi,
I don't see the crash, but perf record/script gives me 'FAILED TO PARSE' in perf script:

  # cd /sys/kernel/tracing
  # echo 's:block_lat pid_t pid; u64 delta; unsigned long[] stack;' > dynamic_events
  # echo 'hist:keys=next_pid:ts=common_timestamp.usecs,st=common_stacktrace  if prev_state == 2' >> events/sched/sched_switch/trigger
  # echo 'hist:keys=prev_pid:delta=common_timestamp.usecs-$ts,s=$st:onmax($delta).trace(block_lat,prev_pid,$delta,$s)' >> events/sched/sched_switch/trigger
  # echo 1 > events/synthetic/block_lat/enable

  # perf record -e 'synthetic:block_lat' -a
  ^C[ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.259 MB perf.data (1 samples) ]
  # perf script
  kworker/u33:2-w     244 [000]  1707.836263: synthetic:block_lat: [FAILED TO PARSE] pid=244 delta=21 stack=ARRAY[0b, 00, 00, 00, 00, 00, 00, 00, 1d, 72, 9d, 82, ff, ff, ff, ff, 0d, 7d, 9d, 82, ff, ff, ff, ff, 3d, 3d, 9e, 82, ff, ff, ff, ff, 05, 91, 9d, 82, ff, ff, ff, ff, 40, 7a, 42, 81, ff, ff, ff, ff, 5e, f4, 0c, 82, ff, ff, ff, ff, 43, 8d, 0c, 82, ff, ff, ff, ff, 82, 2d, 89, 81, ff, ff, ff, ff, 9b, 39, 89, 81, ff, ff, ff, ff, a6, 5a, 9c, 82, ff, ff, ff, ff, 2f, 01, 00, 81, ff, ff, ff, ff]

not sure it's fixed in the latest libtraceevent, mine is
  libtraceevent-1.8.4-3.fc42.x86_64

jirka


> ---
>  kernel/trace/trace_events_synth.c | 121 +++++++++++++++++++++++-------
>  1 file changed, 94 insertions(+), 27 deletions(-)
> 
> diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
> index 4554c458b78c..026e06f28958 100644
> --- a/kernel/trace/trace_events_synth.c
> +++ b/kernel/trace/trace_events_synth.c
> @@ -493,28 +493,19 @@ static unsigned int trace_stack(struct synth_trace_event *entry,
>  	return len;
>  }
>  
> -static notrace void trace_event_raw_event_synth(void *__data,
> -						u64 *var_ref_vals,
> -						unsigned int *var_ref_idx)
> +static __always_inline int get_field_size(struct synth_event *event,
> +					  u64 *var_ref_vals,
> +					  unsigned int *var_ref_idx)
>  {
> -	unsigned int i, n_u64, val_idx, len, data_size = 0;
> -	struct trace_event_file *trace_file = __data;
> -	struct synth_trace_event *entry;
> -	struct trace_event_buffer fbuffer;
> -	struct trace_buffer *buffer;
> -	struct synth_event *event;
> -	int fields_size = 0;
> -
> -	event = trace_file->event_call->data;
> -
> -	if (trace_trigger_soft_disabled(trace_file))
> -		return;
> +	int fields_size;
>  
>  	fields_size = event->n_u64 * sizeof(u64);
>  
> -	for (i = 0; i < event->n_dynamic_fields; i++) {
> +	for (int i = 0; i < event->n_dynamic_fields; i++) {
>  		unsigned int field_pos = event->dynamic_fields[i]->field_pos;
>  		char *str_val;
> +		int val_idx;
> +		int len;
>  
>  		val_idx = var_ref_idx[field_pos];
>  		str_val = (char *)(long)var_ref_vals[val_idx];
> @@ -529,18 +520,18 @@ static notrace void trace_event_raw_event_synth(void *__data,
>  
>  		fields_size += len;
>  	}
> +	return fields_size;
> +}
>  
> -	/*
> -	 * Avoid ring buffer recursion detection, as this event
> -	 * is being performed within another event.
> -	 */
> -	buffer = trace_file->tr->array_buffer.buffer;
> -	guard(ring_buffer_nest)(buffer);
> -
> -	entry = trace_event_buffer_reserve(&fbuffer, trace_file,
> -					   sizeof(*entry) + fields_size);
> -	if (!entry)
> -		return;
> +static __always_inline void write_synth_entry(struct synth_event *event,
> +					      struct synth_trace_event *entry,
> +					      u64 *var_ref_vals,
> +					      unsigned int *var_ref_idx)
> +{
> +	int data_size = 0;
> +	int i, n_u64;
> +	int val_idx;
> +	int len;
>  
>  	for (i = 0, n_u64 = 0; i < event->n_fields; i++) {
>  		val_idx = var_ref_idx[i];
> @@ -581,10 +572,83 @@ static notrace void trace_event_raw_event_synth(void *__data,
>  			n_u64++;
>  		}
>  	}
> +}
> +
> +static notrace void trace_event_raw_event_synth(void *__data,
> +						u64 *var_ref_vals,
> +						unsigned int *var_ref_idx)
> +{
> +	struct trace_event_file *trace_file = __data;
> +	struct synth_trace_event *entry;
> +	struct trace_event_buffer fbuffer;
> +	struct trace_buffer *buffer;
> +	struct synth_event *event;
> +	int fields_size;
> +
> +	event = trace_file->event_call->data;
> +
> +	if (trace_trigger_soft_disabled(trace_file))
> +		return;
> +
> +	fields_size = get_field_size(event, var_ref_vals, var_ref_idx);
> +
> +	/*
> +	 * Avoid ring buffer recursion detection, as this event
> +	 * is being performed within another event.
> +	 */
> +	buffer = trace_file->tr->array_buffer.buffer;
> +	guard(ring_buffer_nest)(buffer);
> +
> +	entry = trace_event_buffer_reserve(&fbuffer, trace_file,
> +					   sizeof(*entry) + fields_size);
> +	if (!entry)
> +		return;
> +
> +	write_synth_entry(event, entry, var_ref_vals, var_ref_idx);
>  
>  	trace_event_buffer_commit(&fbuffer);
>  }
>  
> +#ifdef CONFIG_PERF_EVENTS
> +static notrace void perf_event_raw_event_synth(void *__data,
> +					       u64 *var_ref_vals,
> +					       unsigned int *var_ref_idx)
> +{
> +	struct trace_event_call *call = __data;
> +	struct synth_trace_event *entry;
> +	struct hlist_head *perf_head;
> +	struct synth_event *event;
> +	struct pt_regs *regs;
> +	int fields_size;
> +	size_t size;
> +	int context;
> +
> +	event = call->data;
> +
> +	perf_head = this_cpu_ptr(call->perf_events);
> +
> +	if (!perf_head || hlist_empty(perf_head))
> +		return;
> +
> +	fields_size = get_field_size(event, var_ref_vals, var_ref_idx);
> +
> +	size = ALIGN(sizeof(*entry) + fields_size, 8);
> +
> +	entry = perf_trace_buf_alloc(size, &regs, &context);
> +
> +	if (unlikely(!entry))
> +		return;
> +
> +	write_synth_entry(event, entry, var_ref_vals, var_ref_idx);
> +
> +	perf_fetch_caller_regs(regs);
> +
> +	perf_trace_buf_submit(entry, size, context,
> +			      call->event.type, 1, regs,
> +			      perf_head, NULL);
> +}
> +#endif
> +
>  static void free_synth_event_print_fmt(struct trace_event_call *call)
>  {
>  	if (call) {
> @@ -911,6 +975,9 @@ static int register_synth_event(struct synth_event *event)
>  	call->flags = TRACE_EVENT_FL_TRACEPOINT;
>  	call->class->reg = synth_event_reg;
>  	call->class->probe = trace_event_raw_event_synth;
> +#ifdef CONFIG_PERF_EVENTS
> +	call->class->perf_probe = perf_event_raw_event_synth;
> +#endif
>  	call->data = event;
>  	call->tp = event->tp;
>  
> -- 
> 2.51.0
>