Re: [PATCH 2/9] perf, tools: Add --branch-history option to report v3

[Namhyung Kim <namhyung@gmail.com>]

On Fri, 16 May 2014 10:05:31 -0700, Andi Kleen wrote:
> From: Andi Kleen <ak@linux.intel.com>
>
> Add a --branch-history option to perf report that changes all
> the settings necessary for using the branches in callstacks.
>
> This is just a short cut to make this nicer to use, it does
> not enable any functionality by itself.
>
> v2: Change sort order. Rename option to --branch-history to
> be less confusing.
> v3: Updates
> Signed-off-by: Andi Kleen <ak@linux.intel.com>
> ---
>  tools/perf/Documentation/perf-report.txt |  5 +++++
>  tools/perf/builtin-report.c              | 33 +++++++++++++++++++++++++++-----
>  tools/perf/util/machine.c                | 12 ++++++------
>  3 files changed, 39 insertions(+), 11 deletions(-)
>
> diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
> index 4f0f3d9..23bce9b 100644
> --- a/tools/perf/Documentation/perf-report.txt
> +++ b/tools/perf/Documentation/perf-report.txt
> @@ -231,6 +231,11 @@ OPTIONS
>  	branch stacks and it will automatically switch to the branch view mode,
>  	unless --no-branch-stack is used.
>  
> +--branch-history::
> +	Add the addresses of sampled taken branches to the callstack.
> +	This allows to examine the path the program took to each sample.
> +	The data collection must have used -b (or -j) and -g.
> +
>  --objdump=<path>::
>          Path to objdump binary.
>  
> diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
> index 1a2d7fc..e6d8ed0 100644
> --- a/tools/perf/builtin-report.c
> +++ b/tools/perf/builtin-report.c
> @@ -315,8 +315,9 @@ static int report__setup_sample_type(struct report *rep)
>  			return -EINVAL;
>  		}
>  		if (symbol_conf.use_callchain) {
> -			ui__error("Selected -g but no callchain data. Did "
> -				    "you call 'perf record' without -g?\n");
> +			ui__error("Selected -g or --branch-history but no "
> +				  "callchain data. Did\n"

An unwanted newline in the message.


> +				  "you call 'perf record' without -g?\n");
>  			return -1;
>  		}
>  	} else if (!rep->dont_use_callchains &&
> @@ -631,6 +632,16 @@ parse_branch_mode(const struct option *opt __maybe_unused,
>  }
>  
>  static int
> +parse_branch_call_mode(const struct option *opt __maybe_unused,
> +		  const char *str __maybe_unused, int unset)
> +{
> +	int *branch_mode = opt->value;
> +
> +	*branch_mode = !unset;
> +	return 0;
> +}
> +
> +static int
>  parse_percent_limit(const struct option *opt, const char *str,
>  		    int unset __maybe_unused)
>  {
> @@ -645,7 +656,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
>  	struct perf_session *session;
>  	struct stat st;
>  	bool has_br_stack = false;
> -	int branch_mode = -1;
> +	int branch_mode = -1, branch_call_mode = -1;
>  	int ret = -1;
>  	char callchain_default_opt[] = "fractal,0.5,callee";
>  	const char * const report_usage[] = {
> @@ -754,7 +765,11 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
>  	OPT_BOOLEAN(0, "group", &symbol_conf.event_group,
>  		    "Show event group information together"),
>  	OPT_CALLBACK_NOOPT('b', "branch-stack", &branch_mode, "",
> -		    "use branch records for histogram filling", parse_branch_mode),
> +		    "use branch records for per branch histogram filling",
> +		    parse_branch_mode),
> +	OPT_CALLBACK_NOOPT(0, "branch-history", &branch_call_mode, "",
> +		    "add last branch records to call history",
> +		    parse_branch_call_mode),

Looks like it can be a boolean option, or at least can share
parse_branch_mode() callback.


>  	OPT_STRING(0, "objdump", &objdump_path, "path",
>  		   "objdump binary to use for disassembly and annotations"),
>  	OPT_BOOLEAN(0, "demangle", &symbol_conf.demangle,
> @@ -804,8 +819,16 @@ repeat:
>  	has_br_stack = perf_header__has_feat(&session->header,
>  					     HEADER_BRANCH_STACK);
>  
> -	if (branch_mode == -1 && has_br_stack)
> +	if (branch_mode == -1 && has_br_stack && branch_call_mode == -1)
>  		sort__mode = SORT_MODE__BRANCH;
> +	if (branch_call_mode != -1) {

s/-1/1/ ?


> +		callchain_param.branch_callstack = 1;
> +		callchain_param.key = CCKEY_ADDRESS;
> +		symbol_conf.use_callchain = true;
> +		callchain_register_param(&callchain_param);

Isn't it better doing this in report__setup_sample_type()?

Thanks,
Namhyung


> +		if (sort_order == default_sort_order)
> +			sort_order = "srcline,symbol,dso";
> +	}
>  
>  	/* sort__mode could be NORMAL if --no-branch-stack */
>  	if (sort__mode == SORT_MODE__BRANCH) {
> diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
> index 5238506..f828c87 100644
> --- a/tools/perf/util/machine.c
> +++ b/tools/perf/util/machine.c
> @@ -1379,15 +1379,15 @@ static int machine__resolve_callchain_sample(struct machine *machine,
>  	 * - No annotations (should annotate somehow)
>  	 */
>  
> -	if (branch->nr > PERF_MAX_BRANCH_DEPTH) {
> -		pr_warning("corrupted branch chain. skipping...\n");
> -		return 0;
> -	}
> -
> -	if (callchain_param.branch_callstack) {
> +	if (branch && callchain_param.branch_callstack) {
>  		int nr = min(max_stack, (int)branch->nr);
>  		struct branch_entry be[nr];
>  
> +		if (branch->nr > PERF_MAX_BRANCH_DEPTH) {
> +			pr_warning("corrupted branch chain. skipping...\n");
> +			return 0;
> +		}
> +
>  		for (i = 0; i < nr; i++) {
>  			if (callchain_param.order == ORDER_CALLEE) {
>  				be[i] = branch->entries[i];