perf tools: Improve call graph documents and help messages

--call-graph::

	Setup and enable call-graph (stack chain/backtrace) recording,

	implies -g.

	implies -g.  Default is "fp".

	Allows specifying "fp" (frame pointer) or "dwarf"

	(DWARF's CFI - Call Frame Information) or "lbr"

	In some systems, where binaries are build with gcc

	--fomit-frame-pointer, using the "fp" method will produce bogus

	call graphs, using "dwarf", if available (perf tools linked to

	the libunwind library) should be used instead.

	the libunwind or libdw library) should be used instead.

	Using the "lbr" method doesn't require any compiler options. It

	will produce call graphs from the hardware LBR registers. The

	main limition is that it is only available on new Intel

	platforms, such as Haswell. It can only get user call chain. It

	doesn't work with branch stack sampling at the same time.

	When "dwarf" recording is used, perf also records (user) stack dump

	when sampled.  Default size of the stack dump is 8192 (bytes).

	User can change the size by passing the size after comma like

	"--call-graph dwarf,4096".

-q::

--quiet::

	Don't print any message, useful for scripting.

--dump-raw-trace::

        Dump raw trace in ASCII.

-g [type,min[,limit],order[,key][,branch]]::

--call-graph::

        Display call chains using type, min percent threshold, optional print

	limit and order.

	type can be either:

-g::

--call-graph=<print_type,threshold[,print_limit],order,sort_key,branch>::

        Display call chains using type, min percent threshold, print limit,

	call order, sort key and branch.  Note that ordering of parameters is not

	fixed so any parement can be given in an arbitraty order.  One exception

	is the print_limit which should be preceded by threshold.

	print_type can be either:

	- flat: single column, linear exposure of call chains.

	- graph: use a graph tree, displaying absolute overhead rates.

	- graph: use a graph tree, displaying absolute overhead rates. (default)

	- fractal: like graph, but displays relative rates. Each branch of

		 the tree is considered as a new profiled object. +

		 the tree is considered as a new profiled object.

	- none: disable call chain display.

	threshold is a percentage value which specifies a minimum percent to be

	included in the output call graph.  Default is 0.5 (%).

	print_limit is only applied when stdio interface is used.  It's to limit

	number of call graph entries in a single hist entry.  Note that it needs

	to be given after threshold (but not necessarily consecutive).

	Default is 0 (unlimited).

	order can be either:

	- callee: callee based call graph.

	- caller: inverted caller based call graph.

	Default is 'caller' when --children is used, otherwise 'callee'.

	key can be:

	- function: compare on functions

	sort_key can be:

	- function: compare on functions (default)

	- address: compare on individual code addresses

	branch can be:

	- branch: include last branch information in callgraph

	when available. Usually more convenient to use --branch-history

	for this.

	Default: graph,0.5,caller

	- branch: include last branch information in callgraph when available.

	          Usually more convenient to use --branch-history for this.

--children::

	Accumulate callchain of children to parent entry so that then can

	},

};

const char record_callchain_help[] = CALLCHAIN_RECORD_HELP;

const char record_callchain_help[] = CALLCHAIN_RECORD_HELP

	"\n\t\t\t\tDefault: fp";

/*

 * XXX Will stay a global variable till we fix builtin-script.c to stop messing

			   NULL, "enables call-graph recording" ,

			   &record_callchain_opt),

	OPT_CALLBACK(0, "call-graph", &record.opts,

		     "mode[,dump_size]", record_callchain_help,

		     "record_mode[,record_size]", record_callchain_help,

		     &record_parse_callchain_opt),

	OPT_INCR('v', "verbose", &verbose,

		    "be more verbose (show counter open errors, etc)"),

	return 0;

}

const char report_callchain_help[] = "Display callchains using " CALLCHAIN_REPORT_HELP ". "

				     "Default: graph,0.5,caller";

#define CALLCHAIN_DEFAULT_OPT  "graph,0.5,caller,function"

const char report_callchain_help[] = "Display call graph (stack chain/backtrace):\n\n"

				     CALLCHAIN_REPORT_HELP

				     "\n\t\t\t\tDefault: " CALLCHAIN_DEFAULT_OPT;

int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)

{

	bool has_br_stack = false;

	int branch_mode = -1;

	bool branch_call_mode = false;

	char callchain_default_opt[] = "graph,0.5,caller";

	char callchain_default_opt[] = CALLCHAIN_DEFAULT_OPT;

	const char * const report_usage[] = {

		"perf report [<options>]",

		NULL

	OPT_BOOLEAN('x', "exclude-other", &symbol_conf.exclude_other,

		    "Only display entries with parent-match"),

	OPT_CALLBACK_DEFAULT('g', "call-graph", &report,

			     "output_type,min_percent[,print_limit],call_order[,branch]",

			     "print_type,threshold[,print_limit],order,sort_key[,branch]",

			     report_callchain_help, &report_parse_callchain_opt,

			     callchain_default_opt),

	OPT_BOOLEAN(0, "children", &symbol_conf.cumulate_callchain,

	return 0;

}

const char top_callchain_help[] = CALLCHAIN_RECORD_HELP ", " CALLCHAIN_REPORT_HELP;

const char top_callchain_help[] = CALLCHAIN_RECORD_HELP CALLCHAIN_REPORT_HELP

	"\n\t\t\t\tDefault: fp,graph,0.5,caller,function";

int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)

{

			   NULL, "enables call-graph recording and display",

			   &callchain_opt),

	OPT_CALLBACK(0, "call-graph", &top.record_opts,

		     "mode[,dump_size],output_type,min_percent[,print_limit],call_order[,branch]",

		     "record_mode[,record_size],print_type,threshold[,print_limit],order,sort_key[,branch]",

		     top_callchain_help, &parse_callchain_opt),

	OPT_BOOLEAN(0, "children", &symbol_conf.cumulate_callchain,

		    "Accumulate callchains of children and show total overhead as well"),