Re: [PATCH] perf scripting python: expose symbol offset and source information

[Jiri Olsa]

On Thu, Feb 03, 2022 at 09:44:33AM -0500, Eelco Chaudron wrote:
> This change adds the symbol offset to the data exported for each
> call-chain entry. This can not be calculated from the script and
> only the ip value, and no related mmap information.
> 
> In addition, also export the source file and line information, if
> available, to avoid an external lookup if this information is needed.

could you please update Documentation/perf-script-python.txt with that?

any example script under scripts/python would be great

thanks,
jirka

> 
> Signed-off-by: Eelco Chaudron <echaudro@xxxxxxxxxx>
> ---
>  .../util/scripting-engines/trace-event-python.c    |   42 ++++++++++++++------
>  1 file changed, 30 insertions(+), 12 deletions(-)
> 
> diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
> index e752e1f4a5f0..0f392b4ff663 100644
> --- a/tools/perf/util/scripting-engines/trace-event-python.c
> +++ b/tools/perf/util/scripting-engines/trace-event-python.c
> @@ -392,6 +392,18 @@ static const char *get_dsoname(struct map *map)
>  	return dsoname;
>  }
>  
> +static unsigned long get_offset(struct symbol *sym, struct addr_location *al)
> +{
> +	unsigned long offset;
> +
> +	if (al->addr < sym->end)
> +		offset = al->addr - sym->start;
> +	else
> +		offset = al->addr - al->map->start - sym->start;
> +
> +	return offset;
> +}
> +
>  static PyObject *python_process_callchain(struct perf_sample *sample,
>  					 struct evsel *evsel,
>  					 struct addr_location *al)
> @@ -443,6 +455,24 @@ static PyObject *python_process_callchain(struct perf_sample *sample,
>  					_PyUnicode_FromStringAndSize(node->ms.sym->name,
>  							node->ms.sym->namelen));
>  			pydict_set_item_string_decref(pyelem, "sym", pysym);
> +
> +			if (node->ms.map) {
> +				struct map *map = node->ms.map;
> +				struct addr_location node_al;
> +				unsigned long offset;
> +
> +				node_al.addr = map->map_ip(map, node->ip);
> +				node_al.map  = map;
> +				offset = get_offset(node->ms.sym, &node_al);
> +
> +				pydict_set_item_string_decref(
> +					pyelem, "sym_off",
> +					PyLong_FromUnsignedLongLong(offset));
> +			}
> +			if (node->srcline && strcmp(":0", node->srcline))
> +				pydict_set_item_string_decref(
> +					pyelem, "sym_srcline",
> +					_PyUnicode_FromString(node->srcline));

nit missing { } for multiline if code

>  		}
>  
>  		if (node->ms.map) {
> @@ -520,18 +550,6 @@ static PyObject *python_process_brstack(struct perf_sample *sample,
>  	return pylist;
>  }
>  
> -static unsigned long get_offset(struct symbol *sym, struct addr_location *al)
> -{
> -	unsigned long offset;
> -
> -	if (al->addr < sym->end)
> -		offset = al->addr - sym->start;
> -	else
> -		offset = al->addr - al->map->start - sym->start;
> -
> -	return offset;
> -}
> -
>  static int get_symoff(struct symbol *sym, struct addr_location *al,
>  		      bool print_off, char *bf, int size)
>  {
>