perf session: Fix Intel LBR callstack entries and nr print message

When generating callstack information from branch_stack(Intel LBR), the
actual number of callstack entry should be bigger than the number of
branch_stack, for example:

	branch_stack records:
		B() -> C()
		A() -> B()
	converted callstack records should be:
		C()
		B()
		A()
though, the number of callstack equals
to the number of branch stack plus 1.

This patch fixes above issue in branch_stack__printf(). For example,

	# echo 'scale=2000; 4*a(1)' > cmd
	# perf record --call-graph lbr bc -l < cmd

Before applying this patch, `perf script -D` output:

	1220022677386876 0x2a40 [0xd8]: PERF_RECORD_SAMPLE(IP, 0x4002): 17990/17990: 0x40a6d6 period: 894172 addr: 0
	... LBR call chain: nr:8
	.....  0: fffffffffffffe00
	.....  1: 000000000040a410
	.....  2: 000000000040573c
	.....  3: 0000000000408650
	.....  4: 00000000004022f2
	.....  5: 00000000004015f5
	.....  6: 00007f5ed6dcb553
	.....  7: 0000000000401698
	... FP chain: nr:2
	.....  0: fffffffffffffe00
	.....  1: 000000000040a6d8
	... branch callstack: nr:6    # which is not consistent with LBR records.
	.....  0: 000000000040a410
	.....  1: 0000000000408650    # ditto
	.....  2: 00000000004022f2
	.....  3: 00000000004015f5
	.....  4: 00007f5ed6dcb553
	.....  5: 0000000000401698
	 ... thread: bc:17990
	 ...... dso: /usr/bin/bc
	bc 17990 1220022.677386:     894172 cycles:
			  40a410 [unknown] (/usr/bin/bc)
			  40573c [unknown] (/usr/bin/bc)
			  408650 [unknown] (/usr/bin/bc)
			  4022f2 [unknown] (/usr/bin/bc)
			  4015f5 [unknown] (/usr/bin/bc)
		    7f5ed6dcb553 __libc_start_main+0xf3 (/usr/lib64/libc-2.17.so)
			  401698 [unknown] (/usr/bin/bc)

After applied:

	1220022677386876 0x2a40 [0xd8]: PERF_RECORD_SAMPLE(IP, 0x4002): 17990/17990: 0x40a6d6 period: 894172 addr: 0
	... LBR call chain: nr:8
	.....  0: fffffffffffffe00
	.....  1: 000000000040a410
	.....  2: 000000000040573c
	.....  3: 0000000000408650
	.....  4: 00000000004022f2
	.....  5: 00000000004015f5
	.....  6: 00007f5ed6dcb553
	.....  7: 0000000000401698
	... FP chain: nr:2
	.....  0: fffffffffffffe00
	.....  1: 000000000040a6d8
	... branch callstack: nr:7
	.....  0: 000000000040a410
	.....  1: 000000000040573c
	.....  2: 0000000000408650
	.....  3: 00000000004022f2
	.....  4: 00000000004015f5
	.....  5: 00007f5ed6dcb553
	.....  6: 0000000000401698
	 ... thread: bc:17990
	 ...... dso: /usr/bin/bc
	bc 17990 1220022.677386:     894172 cycles:
			  40a410 [unknown] (/usr/bin/bc)
			  40573c [unknown] (/usr/bin/bc)
			  408650 [unknown] (/usr/bin/bc)
			  4022f2 [unknown] (/usr/bin/bc)
			  4015f5 [unknown] (/usr/bin/bc)
		    7f5ed6dcb553 __libc_start_main+0xf3 (/usr/lib64/libc-2.17.so)
			  401698 [unknown] (/usr/bin/bc)

Change from v1:
	- refined code style according to Jiri's review comments.

Signed-off-by: Chengdong Li <chengdongli@tencent.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Riccardo Mancini <rickyman7@gmail.com>
Cc: likexu@tencent.com
Link: https://lore.kernel.org/r/20220517015726.96131-1-chengdongli@tencent.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

Author: Chengdong Li

tools/perf/util/session.c

@@ -1151,9 +1151,20 @@ static void branch_stack__printf(struct perf_sample *sample, bool callstack)
 	struct branch_entry *entries = perf_sample__branch_entries(sample);
 	uint64_t i;
 
-	printf("%s: nr:%" PRIu64 "\n",
-		!callstack ? "... branch stack" : "... branch callstack",
-		sample->branch_stack->nr);
+	if (!callstack) {
+		printf("%s: nr:%" PRIu64 "\n", "... branch stack", sample->branch_stack->nr);
+	} else {
+		/* the reason of adding 1 to nr is because after expanding
+		 * branch stack it generates nr + 1 callstack records. e.g.,
+		 *         B()->C()
+		 *         A()->B()
+		 * the final callstack should be:
+		 *         C()
+		 *         B()
+		 *         A()
+		 */
+		printf("%s: nr:%" PRIu64 "\n", "... branch callstack", sample->branch_stack->nr+1);
+	}
 
 	for (i = 0; i < sample->branch_stack->nr; i++) {
 		struct branch_entry *e = &entries[i];
@@ -1169,8 +1180,13 @@ static void branch_stack__printf(struct perf_sample *sample, bool callstack)
 				(unsigned)e->flags.reserved,
 				e->flags.type ? branch_type_name(e->flags.type) : "");
 		} else {
-			printf("..... %2"PRIu64": %016" PRIx64 "\n",
-				i, i > 0 ? e->from : e->to);
+			if (i == 0) {
+				printf("..... %2"PRIu64": %016" PRIx64 "\n"
+				       "..... %2"PRIu64": %016" PRIx64 "\n",
+						i, e->to, i+1, e->from);
+			} else {
+				printf("..... %2"PRIu64": %016" PRIx64 "\n", i+1, e->from);
+			}
 		}
 	}
 }