summaryrefslogtreecommitdiff
path: root/tools/perf/builtin-annotate.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2021-05-01 12:22:38 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2021-05-01 12:22:38 -0700
commit10a3efd0fee5e881b1866cf45950808575cb0f24 (patch)
tree38e9e98b096e89a0cac321344264d4bbf2c349c1 /tools/perf/builtin-annotate.c
parent22650f148126571be1098d34160eb4931fc77241 (diff)
parentc6e3bf437184d41d885ba679eab0ddd43f95db56 (diff)
Merge tag 'perf-tools-for-v5.13-2021-04-29' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux
Pull perf tool updates from Arnaldo Carvalho de Melo: "perf stat: - Add support for hybrid PMUs to support systems such as Intel Alderlake and its BIG/little core/atom cpus. - Introduce 'bperf' to share hardware PMCs with BPF. - New --iostat option to collect and present IO stats on Intel hardware. This functionality is based on recently introduced sysfs attributes for Intel® Xeon® Scalable processor family (code name Skylake-SP) in commit bb42b3d39781 ("perf/x86/intel/uncore: Expose an Uncore unit to IIO PMON mapping") It is intended to provide four I/O performance metrics in MB per each PCIe root port: - Inbound Read: I/O devices below root port read from the host memory - Inbound Write: I/O devices below root port write to the host memory - Outbound Read: CPU reads from I/O devices below root port - Outbound Write: CPU writes to I/O devices below root port - Align CSV output for summary. - Clarify --null use cases: Assess raw overhead of 'perf stat' or measure just wall clock time. - Improve readability of shadow stats. perf record: - Change the COMM when starting tha workload so that --exclude-perf doesn't seem to be not honoured. - Improve 'Workload failed' message printing events + what was exec'ed. - Fix cross-arch support for TIME_CONV. perf report: - Add option to disable raw event ordering. - Dump the contents of PERF_RECORD_TIME_CONV in 'perf report -D'. - Improvements to --stat output, that shows information about PERF_RECORD_ events. - Preserve identifier id in OCaml demangler. perf annotate: - Show full source location with 'l' hotkey in the 'perf annotate' TUI. - Add line number like in TUI and source location at EOL to the 'perf annotate' --stdio mode. - Add --demangle and --demangle-kernel to 'perf annotate'. - Allow configuring annotate.demangle{,_kernel} in 'perf config'. - Fix sample events lost in stdio mode. perf data: - Allow converting a perf.data file to JSON. libperf: - Add support for user space counter access. - Update topdown documentation to permit rdpmc calls. perf test: - Add 'perf test' for 'perf stat' CSV output. - Add 'perf test' entries to test the hybrid PMU support. - Cleanup 'perf test daemon' if its 'perf test' is interrupted. - Handle metric reuse in pmu-events parsing 'perf test' entry. - Add test for PE executable support. - Add timeout for wait for daemon start in its 'perf test' entries. Build: - Enable libtraceevent dynamic linking. - Improve feature detection output. - Fix caching of feature checks caching. - First round of updates for tools copies of kernel headers. - Enable warnings when compiling BPF programs. Vendor specific events: - Intel: - Add missing skylake & icelake model numbers. - arm64: - Add Hisi hip08 L1, L2 and L3 metrics. - Add Fujitsu A64FX PMU events. - PowerPC: - Initial JSON/events list for power10 platform. - Remove unsupported power9 metrics. - AMD: - Add Zen3 events. - Fix broken L2 Cache Hits from L2 HWPF metric. - Use lowercases for all the eventcodes and umasks. Hardware tracing: - arm64: - Update CoreSight ETM metadata format. - Fix bitmap for CS-ETM option. - Support PID tracing in config. - Detect pid in VMID for kernel running at EL2. Arch specific updates: - MIPS: - Support MIPS unwinding and dwarf-regs. - Generate mips syscalls_n64.c syscall table. - PowerPC: - Add support for PERF_SAMPLE_WEIGH_STRUCT on PowerPC. - Support pipeline stage cycles for powerpc. libbeauty: - Fix fsconfig generator" * tag 'perf-tools-for-v5.13-2021-04-29' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (132 commits) perf build: Defer printing detected features to the end of all feature checks tools build: Allow deferring printing the results of feature detection perf build: Regenerate the FEATURE_DUMP file after extra feature checks perf session: Dump PERF_RECORD_TIME_CONV event perf session: Add swap operation for event TIME_CONV perf jit: Let convert_timestamp() to be backwards-compatible perf tools: Change fields type in perf_record_time_conv perf tools: Enable libtraceevent dynamic linking perf Documentation: Document intel-hybrid support perf tests: Skip 'perf stat metrics (shadow stat) test' for hybrid perf tests: Support 'Convert perf time to TSC' test for hybrid perf tests: Support 'Session topology' test for hybrid perf tests: Support 'Parse and process metrics' test for hybrid perf tests: Support 'Track with sched_switch' test for hybrid perf tests: Skip 'Setup struct perf_event_attr' test for hybrid perf tests: Add hybrid cases for 'Roundtrip evsel->name' test perf tests: Add hybrid cases for 'Parse event definition strings' test perf record: Uniquify hybrid event name perf stat: Warn group events from different hybrid PMU perf stat: Filter out unmatched aggregation for hybrid event ...
Diffstat (limited to 'tools/perf/builtin-annotate.c')
-rw-r--r--tools/perf/builtin-annotate.c41
1 files changed, 23 insertions, 18 deletions
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index a23ba6bb99b6..49627a7bed7c 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -239,7 +239,7 @@ static int evsel__add_sample(struct evsel *evsel, struct perf_sample *sample,
}
/*
- * XXX filtered samples can still have branch entires pointing into our
+ * XXX filtered samples can still have branch entries pointing into our
* symbol and are missed.
*/
process_branch_stack(sample->branch_stack, al, sample);
@@ -374,13 +374,6 @@ find_next:
} else {
hist_entry__tty_annotate(he, evsel, ann);
nd = rb_next(nd);
- /*
- * Since we have a hist_entry per IP for the same
- * symbol, free he->ms.sym->src to signal we already
- * processed this symbol.
- */
- zfree(&notes->src->cycles_hist);
- zfree(&notes->src);
}
}
}
@@ -411,8 +404,8 @@ static int __cmd_annotate(struct perf_annotate *ann)
goto out;
if (dump_trace) {
- perf_session__fprintf_nr_events(session, stdout);
- evlist__fprintf_nr_events(session->evlist, stdout);
+ perf_session__fprintf_nr_events(session, stdout, false);
+ evlist__fprintf_nr_events(session->evlist, stdout, false);
goto out;
}
@@ -425,7 +418,7 @@ static int __cmd_annotate(struct perf_annotate *ann)
total_nr_samples = 0;
evlist__for_each_entry(session->evlist, pos) {
struct hists *hists = evsel__hists(pos);
- u32 nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE];
+ u32 nr_samples = hists->stats.nr_samples;
if (nr_samples > 0) {
total_nr_samples += nr_samples;
@@ -538,6 +531,10 @@ int cmd_annotate(int argc, const char **argv)
"Strip first N entries of source file path name in programs (with --prefix)"),
OPT_STRING(0, "objdump", &annotate.opts.objdump_path, "path",
"objdump binary to use for disassembly and annotations"),
+ OPT_BOOLEAN(0, "demangle", &symbol_conf.demangle,
+ "Enable symbol demangling"),
+ OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
+ "Enable kernel symbol demangling"),
OPT_BOOLEAN(0, "group", &symbol_conf.event_group,
"Show event group information together"),
OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period,
@@ -619,14 +616,22 @@ int cmd_annotate(int argc, const char **argv)
setup_browser(true);
- if ((use_browser == 1 || annotate.use_stdio2) && annotate.has_br_stack) {
+ /*
+ * Events of different processes may correspond to the same
+ * symbol, we do not care about the processes in annotate,
+ * set sort order to avoid repeated output.
+ */
+ sort_order = "dso,symbol";
+
+ /*
+ * Set SORT_MODE__BRANCH so that annotate display IPC/Cycle
+ * if branch info is in perf data in TUI mode.
+ */
+ if ((use_browser == 1 || annotate.use_stdio2) && annotate.has_br_stack)
sort__mode = SORT_MODE__BRANCH;
- if (setup_sorting(annotate.session->evlist) < 0)
- usage_with_options(annotate_usage, options);
- } else {
- if (setup_sorting(NULL) < 0)
- usage_with_options(annotate_usage, options);
- }
+
+ if (setup_sorting(NULL) < 0)
+ usage_with_options(annotate_usage, options);
ret = __cmd_annotate(&annotate);