[PATCH 09/19] perf evsel: Support PERF_SAMPLE_BRANCH_HW_INDEX

From: Arnaldo Carvalho de Melo
Date: Tue Mar 10 2020 - 07:16:40 EST


From: Kan Liang <kan.liang@xxxxxxxxxxxxxxx>

A new branch sample type PERF_SAMPLE_BRANCH_HW_INDEX has been introduced
in latest kernel.

Enable HW_INDEX by default in LBR call stack mode.

If kernel doesn't support the sample type, switching it off.

Add HW_INDEX in attr_fprintf as well. User can check whether the branch
sample type is set via debug information or header.

Committer testing:

First collect some samples with LBR callchains, system wide, for a few
seconds:

# perf record --call-graph lbr -a sleep 5
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.625 MB perf.data (224 samples) ]
#

Now lets use 'perf evlist -v' to look at the branch_sample_type:

# perf evlist -v
cycles: size: 120, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|CALLCHAIN|CPU|PERIOD|BRANCH_STACK, read_format: ID, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, task: 1, precise_ip: 3, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, ksymbol: 1, bpf_event: 1, branch_sample_type: USER|CALL_STACK|NO_FLAGS|NO_CYCLES|HW_INDEX
#

So the machine has the kernel feature, and it was correctly added to
perf_event_attr.branch_sample_type, for the default 'cycles' event.

If we do it in another machine, where the kernel lacks the HW_INDEX
feature, we get:

# perf record --call-graph lbr -a sleep 2s
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 1.690 MB perf.data (499 samples) ]
# perf evlist -v
cycles: size: 120, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|CALLCHAIN|CPU|PERIOD|BRANCH_STACK, read_format: ID, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, task: 1, precise_ip: 3, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, ksymbol: 1, bpf_event: 1, branch_sample_type: USER|CALL_STACK|NO_FLAGS|NO_CYCLES
#

No HW_INDEX in attr.branch_sample_type.

Signed-off-by: Kan Liang <kan.liang@xxxxxxxxxxxxxxx>
Tested-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
Cc: Adrian Hunter <adrian.hunter@xxxxxxxxx>
Cc: Alexey Budankov <alexey.budankov@xxxxxxxxxxxxxxx>
Cc: Andi Kleen <ak@xxxxxxxxxxxxxxx>
Cc: Jiri Olsa <jolsa@xxxxxxxxxx>
Cc: Mathieu Poirier <mathieu.poirier@xxxxxxxxxx>
Cc: Michael Ellerman <mpe@xxxxxxxxxxxxxx>
Cc: Namhyung Kim <namhyung@xxxxxxxxxx>
Cc: Pavel Gerasimov <pavel.gerasimov@xxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Ravi Bangoria <ravi.bangoria@xxxxxxxxxxxxx>
Cc: Stephane Eranian <eranian@xxxxxxxxxx>
Cc: Vitaly Slobodskoy <vitaly.slobodskoy@xxxxxxxxx>
Link: http://lore.kernel.org/lkml/20200228163011.19358-3-kan.liang@xxxxxxxxxxxxxxx
Signed-off-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
---
tools/perf/util/evsel.c | 15 ++++++++++++---
tools/perf/util/evsel.h | 1 +
tools/perf/util/perf_event_attr_fprintf.c | 1 +
3 files changed, 14 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 05883a45de5b..816d930d774e 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -712,7 +712,8 @@ static void __perf_evsel__config_callchain(struct evsel *evsel,
attr->branch_sample_type = PERF_SAMPLE_BRANCH_USER |
PERF_SAMPLE_BRANCH_CALL_STACK |
PERF_SAMPLE_BRANCH_NO_CYCLES |
- PERF_SAMPLE_BRANCH_NO_FLAGS;
+ PERF_SAMPLE_BRANCH_NO_FLAGS |
+ PERF_SAMPLE_BRANCH_HW_INDEX;
}
} else
pr_warning("Cannot use LBR callstack with branch stack. "
@@ -763,7 +764,8 @@ perf_evsel__reset_callgraph(struct evsel *evsel,
if (param->record_mode == CALLCHAIN_LBR) {
perf_evsel__reset_sample_bit(evsel, BRANCH_STACK);
attr->branch_sample_type &= ~(PERF_SAMPLE_BRANCH_USER |
- PERF_SAMPLE_BRANCH_CALL_STACK);
+ PERF_SAMPLE_BRANCH_CALL_STACK |
+ PERF_SAMPLE_BRANCH_HW_INDEX);
}
if (param->record_mode == CALLCHAIN_DWARF) {
perf_evsel__reset_sample_bit(evsel, REGS_USER);
@@ -1673,6 +1675,8 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,
evsel->core.attr.ksymbol = 0;
if (perf_missing_features.bpf)
evsel->core.attr.bpf_event = 0;
+ if (perf_missing_features.branch_hw_idx)
+ evsel->core.attr.branch_sample_type &= ~PERF_SAMPLE_BRANCH_HW_INDEX;
retry_sample_id:
if (perf_missing_features.sample_id_all)
evsel->core.attr.sample_id_all = 0;
@@ -1784,7 +1788,12 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,
* Must probe features in the order they were added to the
* perf_event_attr interface.
*/
- if (!perf_missing_features.aux_output && evsel->core.attr.aux_output) {
+ if (!perf_missing_features.branch_hw_idx &&
+ (evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_HW_INDEX)) {
+ perf_missing_features.branch_hw_idx = true;
+ pr_debug2("switching off branch HW index support\n");
+ goto fallback_missing_features;
+ } else if (!perf_missing_features.aux_output && evsel->core.attr.aux_output) {
perf_missing_features.aux_output = true;
pr_debug2_peo("Kernel has no attr.aux_output support, bailing out\n");
goto out_close;
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 99a0cb60c556..33804740e2ca 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -119,6 +119,7 @@ struct perf_missing_features {
bool ksymbol;
bool bpf;
bool aux_output;
+ bool branch_hw_idx;
};

extern struct perf_missing_features perf_missing_features;
diff --git a/tools/perf/util/perf_event_attr_fprintf.c b/tools/perf/util/perf_event_attr_fprintf.c
index 651203126c71..355d3458d4e6 100644
--- a/tools/perf/util/perf_event_attr_fprintf.c
+++ b/tools/perf/util/perf_event_attr_fprintf.c
@@ -50,6 +50,7 @@ static void __p_branch_sample_type(char *buf, size_t size, u64 value)
bit_name(ABORT_TX), bit_name(IN_TX), bit_name(NO_TX),
bit_name(COND), bit_name(CALL_STACK), bit_name(IND_JUMP),
bit_name(CALL), bit_name(NO_FLAGS), bit_name(NO_CYCLES),
+ bit_name(HW_INDEX),
{ .name = NULL, }
};
#undef bit_name
--
2.21.1