Re: [PATCH 3/4] perf top: Fix counter name fixup when fallbackingto cpu-clock

[David Ahern]

On 5/25/12 1:59 PM, Arnaldo Carvalho de Melo wrote:
> From: Arnaldo Carvalho de Melo<acme@xxxxxxxxxx>
>
> In 40491eaa "perf top: Update event name when falling back to cpu-clock"
> we freed counter->name but didn't reset it to NULL, then when setting it
> to the result of event_name(), event_name() would use the cached value,
> which by now was overwritten and thus we got garbage or a zero lenght
> string.
>
> Fix it by just freeing and setting counter->name to NULL, this way
> event_name() when called afterwards, will find the right counter name
> and cache it again.
>
> Found while trying 'cycles:pp' on a machine were :pp couldn't be
> honoured. Probably the best fallback here is to tell the user that that
> level of precision is not available on the PMU and then go removing 'p',
> levels of precision till we get to play 'cycles' and if even that fails,
> _then_ get to 'cpu-clock'.
>
> But that is the matter for another patch, this one just needs to fix the
> caching issue, which in the end will show 'cpu-clock' when tools ask for
> the event name being used, which clarifies things for the user, that
> will see that 'cycles:pp' or whatever not support event is not being
> used, some sort of fallback happened.
>
> Cc: David Ahern<dsahern@xxxxxxxxx>
> Cc: Frederic Weisbecker<fweisbec@xxxxxxxxx>
> Cc: Mike Galbraith<efault@xxxxxx>
> Cc: Namhyung Kim<namhyung@xxxxxxxxx>
> Cc: Paul Mackerras<paulus@xxxxxxxxx>
> Cc: Peter Zijlstra<peterz@xxxxxxxxxxxxx>
> Cc: Stephane Eranian<eranian@xxxxxxxxxx>
> Link: http://lkml.kernel.org/n/tip-w1neie2dqli89we1bzwkf4id@xxxxxxxxxxxxxx
> Signed-off-by: Arnaldo Carvalho de Melo<acme@xxxxxxxxxx>
> ---
>   tools/perf/builtin-top.c |    2 +-
>   1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
> index 6031dce..d4a5f9b 100644
> --- a/tools/perf/builtin-top.c
> +++ b/tools/perf/builtin-top.c
> @@ -953,7 +953,7 @@ try_again:
>   				attr->config = PERF_COUNT_SW_CPU_CLOCK;
>   				if (counter->name) {
>   					free(counter->name);
> -					counter->name = strdup(event_name(counter));
> +					counter->name = NULL;
>   				}
>   				goto try_again;
>   			}

The patch I sent had:

+ if (counter->name) {
+ free(counter->name);
+ counter->name = NULL;
+ counter->name = strdup(event_name(counter));
+ }

See http://lkml.indiana.edu/hypermail/linux/kernel/1205.1/00390.html



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