[PATCH v3 5/5] perf report: Show branch type in callchain entry

From: Jin Yao
Date: Mon Apr 10 2017 - 22:59:19 EST


Show branch type in callchain entry. The branch type is printed
with other LBR information (such as cycles/abort/...).

One example:
perf report --branch-history --stdio --no-children

--23.54%--main div.c:42 (CROSS_2M RET cycles:2)
compute_flag div.c:28 (RET cycles:2)
compute_flag div.c:27 (CROSS_2M RET cycles:1)
rand rand.c:28 (CROSS_4K RET cycles:1)
rand rand.c:28 (CROSS_2M RET cycles:1)
__random random.c:298 (CROSS_4K RET cycles:1)
__random random.c:297 (JCC backward CROSS_2M cycles:1)
__random random.c:295 (JCC forward CROSS_4K cycles:1)
__random random.c:295 (JCC backward CROSS_2M cycles:1)
__random random.c:295 (JCC forward CROSS_4K cycles:1)
__random random.c:295 (CROSS_2M RET cycles:9)

Signed-off-by: Jin Yao <yao.jin@xxxxxxxxxxxxxxx>
---
tools/perf/util/callchain.c | 195 ++++++++++++++++++++++++++++++--------------
tools/perf/util/callchain.h | 4 +-
tools/perf/util/machine.c | 26 ++++--
3 files changed, 152 insertions(+), 73 deletions(-)

diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 2e5eff5..3c875b1 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -467,6 +467,11 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
call->cycles_count = cursor_node->branch_flags.cycles;
call->iter_count = cursor_node->nr_loop_iter;
call->samples_count = cursor_node->samples;
+
+ branch_type_count(&call->brtype_stat,
+ &cursor_node->branch_flags,
+ cursor_node->branch_from,
+ cursor_node->ip);
}

list_add_tail(&call->list, &node->val);
@@ -579,6 +584,11 @@ static enum match_result match_chain(struct callchain_cursor_node *node,
cnode->cycles_count += node->branch_flags.cycles;
cnode->iter_count += node->nr_loop_iter;
cnode->samples_count += node->samples;
+
+ branch_type_count(&cnode->brtype_stat,
+ &node->branch_flags,
+ node->branch_from,
+ node->ip);
}

return MATCH_EQ;
@@ -813,7 +823,7 @@ merge_chain_branch(struct callchain_cursor *cursor,
list_for_each_entry_safe(list, next_list, &src->val, list) {
callchain_cursor_append(cursor, list->ip,
list->ms.map, list->ms.sym,
- false, NULL, 0, 0);
+ false, NULL, 0, 0, 0);
list_del(&list->list);
map__zput(list->ms.map);
free(list);
@@ -853,7 +863,7 @@ int callchain_merge(struct callchain_cursor *cursor,
int callchain_cursor_append(struct callchain_cursor *cursor,
u64 ip, struct map *map, struct symbol *sym,
bool branch, struct branch_flags *flags,
- int nr_loop_iter, int samples)
+ int nr_loop_iter, int samples, u64 branch_from)
{
struct callchain_cursor_node *node = *cursor->last;

@@ -877,6 +887,7 @@ int callchain_cursor_append(struct callchain_cursor *cursor,
memcpy(&node->branch_flags, flags,
sizeof(struct branch_flags));

+ node->branch_from = branch_from;
cursor->nr++;

cursor->last = &node->next;
@@ -1105,95 +1116,151 @@ int callchain_branch_counts(struct callchain_root *root,
cycles_count);
}

+static int branch_type_str(struct branch_type_stat *stat,
+ char *bf, int bfsize)
+{
+ int i, j = 0, printed = 0;
+ u64 total = 0;
+
+ for (i = 0; i < PERF_BR_MAX; i++)
+ total += stat->counts[i];
+
+ if (total == 0)
+ return 0;
+
+ printed += scnprintf(bf + printed, bfsize - printed, " (");
+
+ if (stat->jcc_fwd > 0) {
+ j++;
+ printed += scnprintf(bf + printed, bfsize - printed,
+ "JCC forward");
+ }
+
+ if (stat->jcc_bwd > 0) {
+ if (j++)
+ printed += scnprintf(bf + printed, bfsize - printed,
+ " JCC backward");
+ else
+ printed += scnprintf(bf + printed, bfsize - printed,
+ "JCC backward");
+ }
+
+ if (stat->cross_4k > 0) {
+ if (j++)
+ printed += scnprintf(bf + printed, bfsize - printed,
+ " CROSS_4K");
+ else
+ printed += scnprintf(bf + printed, bfsize - printed,
+ "CROSS_4K");
+ }
+
+ if (stat->cross_2m > 0) {
+ if (j++)
+ printed += scnprintf(bf + printed, bfsize - printed,
+ " CROSS_2M");
+ else
+ printed += scnprintf(bf + printed, bfsize - printed,
+ "CROSS_2M");
+ }
+
+ for (i = 0; i < PERF_BR_MAX; i++) {
+ if (i == PERF_BR_JCC)
+ continue;
+
+ if (stat->counts[i] > 0) {
+ if (j++)
+ printed += scnprintf(bf + printed,
+ bfsize - printed,
+ " %s",
+ branch_type_name(i));
+ else
+ printed += scnprintf(bf + printed,
+ bfsize - printed,
+ "%s",
+ branch_type_name(i));
+ }
+ }
+
+ return printed;
+}
+
static int counts_str_build(char *bf, int bfsize,
u64 branch_count, u64 predicted_count,
u64 abort_count, u64 cycles_count,
- u64 iter_count, u64 samples_count)
+ u64 iter_count, u64 samples_count,
+ struct branch_type_stat *brtype_stat)
{
- double predicted_percent = 0.0;
- const char *null_str = "";
- char iter_str[32];
- char cycle_str[32];
- char *istr, *cstr;
u64 cycles;
+ int printed, i = 0;

if (branch_count == 0)
return scnprintf(bf, bfsize, " (calltrace)");

+ printed = branch_type_str(brtype_stat, bf, bfsize);
+ if (printed)
+ i++;
+
cycles = cycles_count / branch_count;
+ if (cycles) {
+ if (i++)
+ printed += scnprintf(bf + printed, bfsize - printed,
+ " cycles:%" PRId64 "", cycles);
+ else
+ printed += scnprintf(bf + printed, bfsize - printed,
+ " (cycles:%" PRId64 "", cycles);
+ }

if (iter_count && samples_count) {
- if (cycles > 0)
- scnprintf(iter_str, sizeof(iter_str),
- " iterations:%" PRId64 "",
- iter_count / samples_count);
+ if (i++)
+ printed += scnprintf(bf + printed, bfsize - printed,
+ " iterations:%" PRId64 "",
+ iter_count / samples_count);
else
- scnprintf(iter_str, sizeof(iter_str),
- "iterations:%" PRId64 "",
- iter_count / samples_count);
- istr = iter_str;
- } else
- istr = (char *)null_str;
-
- if (cycles > 0) {
- scnprintf(cycle_str, sizeof(cycle_str),
- "cycles:%" PRId64 "", cycles);
- cstr = cycle_str;
- } else
- cstr = (char *)null_str;
-
- predicted_percent = predicted_count * 100.0 / branch_count;
+ printed += scnprintf(bf + printed, bfsize - printed,
+ " (iterations:%" PRId64 "",
+ iter_count / samples_count);
+ }

- if ((predicted_count == branch_count) && (abort_count == 0)) {
- if ((cycles > 0) || (istr != (char *)null_str))
- return scnprintf(bf, bfsize, " (%s%s)", cstr, istr);
+ if (predicted_count < branch_count) {
+ if (i++)
+ printed += scnprintf(bf + printed, bfsize - printed,
+ " predicted:%.1f%%",
+ predicted_count * 100.0 / branch_count);
else
- return scnprintf(bf, bfsize, "%s", (char *)null_str);
- }
-
- if ((predicted_count < branch_count) && (abort_count == 0)) {
- if ((cycles > 0) || (istr != (char *)null_str))
- return scnprintf(bf, bfsize,
- " (predicted:%.1f%% %s%s)",
- predicted_percent, cstr, istr);
- else {
- return scnprintf(bf, bfsize,
- " (predicted:%.1f%%)",
- predicted_percent);
- }
+ printed += scnprintf(bf + printed, bfsize - printed,
+ " (predicted:%.1f%%",
+ predicted_count * 100.0 / branch_count);
}

- if ((predicted_count == branch_count) && (abort_count > 0)) {
- if ((cycles > 0) || (istr != (char *)null_str))
- return scnprintf(bf, bfsize,
- " (abort:%" PRId64 " %s%s)",
- abort_count, cstr, istr);
+ if (abort_count) {
+ if (i++)
+ printed += scnprintf(bf + printed, bfsize - printed,
+ " abort:%.1f%%",
+ abort_count * 100.0 / branch_count);
else
- return scnprintf(bf, bfsize,
- " (abort:%" PRId64 ")",
- abort_count);
+ printed += scnprintf(bf + printed, bfsize - printed,
+ " (abort:%.1f%%",
+ abort_count * 100.0 / branch_count);
}

- if ((cycles > 0) || (istr != (char *)null_str))
- return scnprintf(bf, bfsize,
- " (predicted:%.1f%% abort:%" PRId64 " %s%s)",
- predicted_percent, abort_count, cstr, istr);
+ if (i)
+ return scnprintf(bf + printed, bfsize - printed, ")");

- return scnprintf(bf, bfsize,
- " (predicted:%.1f%% abort:%" PRId64 ")",
- predicted_percent, abort_count);
+ bf[0] = 0;
+ return 0;
}

static int callchain_counts_printf(FILE *fp, char *bf, int bfsize,
u64 branch_count, u64 predicted_count,
u64 abort_count, u64 cycles_count,
- u64 iter_count, u64 samples_count)
+ u64 iter_count, u64 samples_count,
+ struct branch_type_stat *brtype_stat)
{
- char str[128];
+ char str[256];

counts_str_build(str, sizeof(str), branch_count,
predicted_count, abort_count, cycles_count,
- iter_count, samples_count);
+ iter_count, samples_count, brtype_stat);

if (fp)
return fprintf(fp, "%s", str);
@@ -1225,7 +1292,8 @@ int callchain_list_counts__printf_value(struct callchain_node *node,

return callchain_counts_printf(fp, bf, bfsize, branch_count,
predicted_count, abort_count,
- cycles_count, iter_count, samples_count);
+ cycles_count, iter_count, samples_count,
+ &clist->brtype_stat);
}

static void free_callchain_node(struct callchain_node *node)
@@ -1350,7 +1418,8 @@ int callchain_cursor__copy(struct callchain_cursor *dst,

rc = callchain_cursor_append(dst, node->ip, node->map, node->sym,
node->branch, &node->branch_flags,
- node->nr_loop_iter, node->samples);
+ node->nr_loop_iter, node->samples,
+ node->branch_from);
if (rc)
break;

diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index c56c23d..b93897a 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -119,6 +119,7 @@ struct callchain_list {
u64 cycles_count;
u64 iter_count;
u64 samples_count;
+ struct branch_type_stat brtype_stat;
char *srcline;
struct list_head list;
};
@@ -135,6 +136,7 @@ struct callchain_cursor_node {
struct symbol *sym;
bool branch;
struct branch_flags branch_flags;
+ u64 branch_from;
int nr_loop_iter;
int samples;
struct callchain_cursor_node *next;
@@ -198,7 +200,7 @@ static inline void callchain_cursor_reset(struct callchain_cursor *cursor)
int callchain_cursor_append(struct callchain_cursor *cursor, u64 ip,
struct map *map, struct symbol *sym,
bool branch, struct branch_flags *flags,
- int nr_loop_iter, int samples);
+ int nr_loop_iter, int samples, u64 branch_from);

/* Close a cursor writing session. Initialize for the reader */
static inline void callchain_cursor_commit(struct callchain_cursor *cursor)
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index dfc6004..2309614 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1673,7 +1673,8 @@ static int add_callchain_ip(struct thread *thread,
bool branch,
struct branch_flags *flags,
int nr_loop_iter,
- int samples)
+ int samples,
+ u64 branch_from)
{
struct addr_location al;

@@ -1726,7 +1727,8 @@ static int add_callchain_ip(struct thread *thread,
if (symbol_conf.hide_unresolved && al.sym == NULL)
return 0;
return callchain_cursor_append(cursor, al.addr, al.map, al.sym,
- branch, flags, nr_loop_iter, samples);
+ branch, flags, nr_loop_iter, samples,
+ branch_from);
}

struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
@@ -1805,7 +1807,7 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
struct ip_callchain *chain = sample->callchain;
int chain_nr = min(max_stack, (int)chain->nr), i;
u8 cpumode = PERF_RECORD_MISC_USER;
- u64 ip;
+ u64 ip, branch_from = 0;

for (i = 0; i < chain_nr; i++) {
if (chain->ips[i] == PERF_CONTEXT_USER)
@@ -1847,6 +1849,8 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
ip = lbr_stack->entries[0].to;
branch = true;
flags = &lbr_stack->entries[0].flags;
+ branch_from =
+ lbr_stack->entries[0].from;
}
} else {
if (j < lbr_nr) {
@@ -1861,12 +1865,15 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
ip = lbr_stack->entries[0].to;
branch = true;
flags = &lbr_stack->entries[0].flags;
+ branch_from =
+ lbr_stack->entries[0].from;
}
}

err = add_callchain_ip(thread, cursor, parent,
root_al, &cpumode, ip,
- branch, flags, 0, 0);
+ branch, flags, 0, 0,
+ branch_from);
if (err)
return (err < 0) ? err : 0;
}
@@ -1965,19 +1972,20 @@ static int thread__resolve_callchain_sample(struct thread *thread,
root_al,
NULL, be[i].to,
true, &be[i].flags,
- nr_loop_iter, 1);
+ nr_loop_iter, 1,
+ be[i].from);
else
err = add_callchain_ip(thread, cursor, parent,
root_al,
NULL, be[i].to,
true, &be[i].flags,
- 0, 0);
+ 0, 0, be[i].from);

if (!err)
err = add_callchain_ip(thread, cursor, parent, root_al,
NULL, be[i].from,
true, &be[i].flags,
- 0, 0);
+ 0, 0, 0);
if (err == -EINVAL)
break;
if (err)
@@ -2007,7 +2015,7 @@ static int thread__resolve_callchain_sample(struct thread *thread,

err = add_callchain_ip(thread, cursor, parent,
root_al, &cpumode, ip,
- false, NULL, 0, 0);
+ false, NULL, 0, 0, 0);

if (err)
return (err < 0) ? err : 0;
@@ -2024,7 +2032,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
return 0;
return callchain_cursor_append(cursor, entry->ip,
entry->map, entry->sym,
- false, NULL, 0, 0);
+ false, NULL, 0, 0, 0);
}

static int thread__resolve_callchain_unwind(struct thread *thread,
--
2.7.4