perf script: Enable printing of branch stack

This patch improves perf script by enabling printing of the
branch stack via the 'brstack' and 'brstacksym' arguments to
the field selection option -F. The option is off by default
and operates only if the perf.data file has branch stack content.

The branches are printed in to/from pairs. The most recent branch
is printed first. The number of branch entries vary based on the
underlying hardware and filtering used.

The brstack prints FROM/TO addresses in raw hexadecimal format.
The brstacksym prints FROM/TO addresses in symbolic form wherever
possible.

$ perf script -F ip,brstack
5d3000 0x401aa0/0x5d2000/M/-/-/-/0 ...

$ perf script -F ip,brstacksym
4011e0 noploop+0x0/noploop+0x0/P/-/-/0

The notation F/T/M/X/A/C describes the attributes of the branch.
F=from, T=to, M/P=misprediction/prediction, X=TSX, A=TSX abort, C=cycles (SKL)

Signed-off-by: Stephane Eranian <[e-mail]>
Cc: Adrian Hunter <[e-mail]>
Cc: Andi Kleen <[e-mail]>
Cc: David Ahern <[e-mail]>
Cc: Jiri Olsa <[e-mail]>
Cc: Kan Liang <[e-mail]>
Cc: Namhyung Kim <[e-mail]>
Cc: Peter Zijlstra <[e-mail]>
Cc: Yuanfang Chen <[e-mail]>
Link: http://lkml.kernel.org/r/[e-mail]
Signed-off-by: Arnaldo Carvalho de Melo <[e-mail]>

tools/perf/Documentation/perf-script.txt

···
 --debug-mode::
         Do various checks like samples ordering and lost events.
 
--f::
+-F::
 --fields::
         Comma separated list of fields to print. Options are:
         comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff,
-	srcline, period, iregs, flags.
+	srcline, period, iregs, brstack, brstacksym, flags.
         Field list can be prepended with the type, trace, sw or hw,
         to indicate to which event type the field list applies.
         e.g., -f sw:comm,tid,time,ip,sym  and -f trace:time,cpu,trace
···
 
 	Finally, a user may not set fields to none for all event types.
 	i.e., -f "" is not allowed.
+
+	The brstack output includes branch related information with raw addresses using the
+	/v/v/v/v/ syntax in the following order:
+	FROM: branch source instruction
+	TO  : branch target instruction
+        M/P/-: M=branch target mispredicted or branch direction was mispredicted, P=target predicted or direction predicted, -=not supported
+	X/- : X=branch inside a transactional region, -=not in transaction region or not supported
+	A/- : A=TSX abort entry, -=not aborted region or not supported
+
+	The brstacksym is identical to brstack, except that the FROM and TO addresses are printed in a symbolic form if possible.
 
 -k::
 --vmlinux=<file>::

tools/perf/builtin-script.c

···
 	PERF_OUTPUT_SRCLINE         = 1U << 12,
 	PERF_OUTPUT_PERIOD          = 1U << 13,
 	PERF_OUTPUT_IREGS	    = 1U << 14,
+	PERF_OUTPUT_BRSTACK	    = 1U << 15,
+	PERF_OUTPUT_BRSTACKSYM	    = 1U << 16,
 };
 
 struct output_option {
···
 	{.str = "srcline", .field = PERF_OUTPUT_SRCLINE},
 	{.str = "period", .field = PERF_OUTPUT_PERIOD},
 	{.str = "iregs", .field = PERF_OUTPUT_IREGS},
+	{.str = "brstack", .field = PERF_OUTPUT_BRSTACK},
+	{.str = "brstacksym", .field = PERF_OUTPUT_BRSTACKSYM},
 };
 
 /* default set to maintain compatibility with current format */
···
 	}
 }
 
+static inline char
+mispred_str(struct branch_entry *br)
+{
+	if (!(br->flags.mispred  || br->flags.predicted))
+		return '-';
+
+	return br->flags.predicted ? 'P' : 'M';
+}
+
+static void print_sample_brstack(union perf_event *event __maybe_unused,
+			  struct perf_sample *sample,
+			  struct thread *thread __maybe_unused,
+			  struct perf_event_attr *attr __maybe_unused)
+{
+	struct branch_stack *br = sample->branch_stack;
+	u64 i;
+
+	if (!(br && br->nr))
+		return;
+
+	for (i = 0; i < br->nr; i++) {
+		printf(" 0x%"PRIx64"/0x%"PRIx64"/%c/%c/%c/%d ",
+			br->entries[i].from,
+			br->entries[i].to,
+			mispred_str( br->entries + i),
+			br->entries[i].flags.in_tx? 'X' : '-',
+			br->entries[i].flags.abort? 'A' : '-',
+			br->entries[i].flags.cycles);
+	}
+}
+
+static void print_sample_brstacksym(union perf_event *event __maybe_unused,
+			  struct perf_sample *sample,
+			  struct thread *thread __maybe_unused,
+			  struct perf_event_attr *attr __maybe_unused)
+{
+	struct branch_stack *br = sample->branch_stack;
+	struct addr_location alf, alt;
+	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+	u64 i, from, to;
+
+	if (!(br && br->nr))
+		return;
+
+	for (i = 0; i < br->nr; i++) {
+
+		memset(&alf, 0, sizeof(alf));
+		memset(&alt, 0, sizeof(alt));
+		from = br->entries[i].from;
+		to   = br->entries[i].to;
+
+		thread__find_addr_map(thread, cpumode, MAP__FUNCTION, from, &alf);
+		if (alf.map)
+			alf.sym = map__find_symbol(alf.map, alf.addr, NULL);
+
+		thread__find_addr_map(thread, cpumode, MAP__FUNCTION, to, &alt);
+		if (alt.map)
+			alt.sym = map__find_symbol(alt.map, alt.addr, NULL);
+
+		symbol__fprintf_symname_offs(alf.sym, &alf, stdout);
+		putchar('/');
+		symbol__fprintf_symname_offs(alt.sym, &alt, stdout);
+		printf("/%c/%c/%c/%d ",
+			mispred_str( br->entries + i),
+			br->entries[i].flags.in_tx? 'X' : '-',
+			br->entries[i].flags.abort? 'A' : '-',
+			br->entries[i].flags.cycles);
+	}
+}
+
+
 static void print_sample_addr(union perf_event *event,
 			  struct perf_sample *sample,
 			  struct thread *thread,
···
 
 	if (PRINT_FIELD(IREGS))
 		print_sample_iregs(event, sample, thread, attr);
+
+	if (PRINT_FIELD(BRSTACK))
+		print_sample_brstack(event, sample, thread, attr);
+	else if (PRINT_FIELD(BRSTACKSYM))
+		print_sample_brstacksym(event, sample, thread, attr);
 
 	printf("\n");
 }
···
 		     "comma separated output fields prepend with 'type:'. "
 		     "Valid types: hw,sw,trace,raw. "
 		     "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
-		     "addr,symoff,period,iregs,flags", parse_output_fields),
+		     "addr,symoff,period,iregs,brstack,brstacksym,flags", parse_output_fields),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,
 		    "system-wide collection from all CPUs"),
 	OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",