perf script: Support total cycles count

For 'perf script' brstackinsn also print a running cycles count.  This
makes it easier to calculate cycle deltas for code sections measured
with LBRs.

% perf record -b -a sleep 1
% perf script -F +brstackinsn
...
        00007f73ecc41083        insn: 74 06                     # PRED 9 cycles [17] 1.11 IPC
        00007f73ecc4108b        insn: a8 10
        00007f73ecc4108d        insn: 74 71                     # PRED 1 cycles [18] 1.00 IPC
        00007f73ecc41100        insn: 48 8b 46 10
        00007f73ecc41104        insn: 4c 8b 38
        00007f73ecc41107        insn: 4d 85 ff
        00007f73ecc4110a        insn: 0f 84 b0 00 00 00
        00007f73ecc41110        insn: 83 43 58 01
        00007f73ecc41114        insn: 48 89 df
        00007f73ecc41117        insn: e8 94 73 04 00            # PRED 6 cycles [24] 1.00 IPC

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Link: http://lkml.kernel.org/r/20180924170732.GA28040@tassilo.jf.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/builtin-script.c

@@ -913,7 +913,7 @@ static int grab_bb(u8 *buffer, u64 start, u64 end,
 
 static int ip__fprintf_jump(uint64_t ip, struct branch_entry *en,
 			    struct perf_insn *x, u8 *inbuf, int len,
-			    int insn, FILE *fp)
+			    int insn, FILE *fp, int *total_cycles)
 {
 	int printed = fprintf(fp, "\t%016" PRIx64 "\t%-30s\t#%s%s%s%s", ip,
 			      dump_insn(x, ip, inbuf, len, NULL),
@@ -922,7 +922,8 @@ static int ip__fprintf_jump(uint64_t ip, struct branch_entry *en,
 			      en->flags.in_tx ? " INTX" : "",
 			      en->flags.abort ? " ABORT" : "");
 	if (en->flags.cycles) {
-		printed += fprintf(fp, " %d cycles", en->flags.cycles);
+		*total_cycles += en->flags.cycles;
+		printed += fprintf(fp, " %d cycles [%d]", en->flags.cycles, *total_cycles);
 		if (insn)
 			printed += fprintf(fp, " %.2f IPC", (float)insn / en->flags.cycles);
 	}
@@ -979,6 +980,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 	u8 buffer[MAXBB];
 	unsigned off;
 	struct symbol *lastsym = NULL;
+	int total_cycles = 0;
 
 	if (!(br && br->nr))
 		return 0;
@@ -999,7 +1001,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 		printed += ip__fprintf_sym(br->entries[nr - 1].from, thread,
 					   x.cpumode, x.cpu, &lastsym, attr, fp);
 		printed += ip__fprintf_jump(br->entries[nr - 1].from, &br->entries[nr - 1],
-					    &x, buffer, len, 0, fp);
+					    &x, buffer, len, 0, fp, &total_cycles);
 	}
 
 	/* Print all blocks */
@@ -1027,7 +1029,8 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 
 			printed += ip__fprintf_sym(ip, thread, x.cpumode, x.cpu, &lastsym, attr, fp);
 			if (ip == end) {
-				printed += ip__fprintf_jump(ip, &br->entries[i], &x, buffer + off, len - off, insn, fp);
+				printed += ip__fprintf_jump(ip, &br->entries[i], &x, buffer + off, len - off, insn, fp,
+							    &total_cycles);
 				break;
 			} else {
 				printed += fprintf(fp, "\t%016" PRIx64 "\t%s\n", ip,