summaryrefslogtreecommitdiffstats
path: root/kernel/tools/perf
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/tools/perf')
-rw-r--r--kernel/tools/perf/Documentation/perf-stat.txt8
-rw-r--r--kernel/tools/perf/Makefile.perf2
-rw-r--r--kernel/tools/perf/arch/x86/util/intel-pt.c6
-rw-r--r--kernel/tools/perf/tests/bpf.c14
-rw-r--r--kernel/tools/perf/tests/llvm.c8
-rw-r--r--kernel/tools/perf/ui/browsers/hists.c11
-rw-r--r--kernel/tools/perf/util/event.c2
-rw-r--r--kernel/tools/perf/util/evlist.c4
-rw-r--r--kernel/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c38
-rw-r--r--kernel/tools/perf/util/intel-pt.c17
-rw-r--r--kernel/tools/perf/util/parse-events.c6
-rw-r--r--kernel/tools/perf/util/pmu.c15
-rw-r--r--kernel/tools/perf/util/setup.py4
-rw-r--r--kernel/tools/perf/util/stat.c10
-rw-r--r--kernel/tools/perf/util/symbol-elf.c3
-rw-r--r--kernel/tools/perf/util/symbol.c5
-rw-r--r--kernel/tools/perf/util/trace-event-scripting.c6
17 files changed, 118 insertions, 41 deletions
diff --git a/kernel/tools/perf/Documentation/perf-stat.txt b/kernel/tools/perf/Documentation/perf-stat.txt
index 4e074a660..90c3558c2 100644
--- a/kernel/tools/perf/Documentation/perf-stat.txt
+++ b/kernel/tools/perf/Documentation/perf-stat.txt
@@ -62,6 +62,14 @@ OPTIONS
--scale::
scale/normalize counter values
+-d::
+--detailed::
+ print more detailed statistics, can be specified up to 3 times
+
+ -d: detailed events, L1 and LLC data cache
+ -d -d: more detailed events, dTLB and iTLB events
+ -d -d -d: very detailed events, adding prefetch events
+
-r::
--repeat=<n>::
repeat command and print average + stddev (max: 100). 0 means forever.
diff --git a/kernel/tools/perf/Makefile.perf b/kernel/tools/perf/Makefile.perf
index 0d19d5447..929a32ba1 100644
--- a/kernel/tools/perf/Makefile.perf
+++ b/kernel/tools/perf/Makefile.perf
@@ -420,7 +420,7 @@ $(LIBTRACEEVENT)-clean:
$(call QUIET_CLEAN, libtraceevent)
$(Q)$(MAKE) -C $(TRACE_EVENT_DIR) O=$(OUTPUT) clean >/dev/null
-install-traceevent-plugins: $(LIBTRACEEVENT)
+install-traceevent-plugins: libtraceevent_plugins
$(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) install_plugins
$(LIBAPI): fixdep FORCE
diff --git a/kernel/tools/perf/arch/x86/util/intel-pt.c b/kernel/tools/perf/arch/x86/util/intel-pt.c
index b02af064f..c53f78767 100644
--- a/kernel/tools/perf/arch/x86/util/intel-pt.c
+++ b/kernel/tools/perf/arch/x86/util/intel-pt.c
@@ -499,7 +499,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
struct intel_pt_recording *ptr =
container_of(itr, struct intel_pt_recording, itr);
struct perf_pmu *intel_pt_pmu = ptr->intel_pt_pmu;
- bool have_timing_info;
+ bool have_timing_info, need_immediate = false;
struct perf_evsel *evsel, *intel_pt_evsel = NULL;
const struct cpu_map *cpus = evlist->cpus;
bool privileged = geteuid() == 0 || perf_event_paranoid() < 0;
@@ -653,6 +653,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
ptr->have_sched_switch = 3;
} else {
opts->record_switch_events = true;
+ need_immediate = true;
if (cpu_wide)
ptr->have_sched_switch = 3;
else
@@ -698,6 +699,9 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
tracking_evsel->attr.freq = 0;
tracking_evsel->attr.sample_period = 1;
+ if (need_immediate)
+ tracking_evsel->immediate = true;
+
/* In per-cpu case, always need the time of mmap events etc */
if (!cpu_map__empty(cpus)) {
perf_evsel__set_sample_bit(tracking_evsel, TIME);
diff --git a/kernel/tools/perf/tests/bpf.c b/kernel/tools/perf/tests/bpf.c
index ec16f7812..6ebfdee3e 100644
--- a/kernel/tools/perf/tests/bpf.c
+++ b/kernel/tools/perf/tests/bpf.c
@@ -146,7 +146,7 @@ prepare_bpf(void *obj_buf, size_t obj_buf_sz, const char *name)
return obj;
}
-static int __test__bpf(int index)
+static int __test__bpf(int idx)
{
int ret;
void *obj_buf;
@@ -154,27 +154,27 @@ static int __test__bpf(int index)
struct bpf_object *obj;
ret = test_llvm__fetch_bpf_obj(&obj_buf, &obj_buf_sz,
- bpf_testcase_table[index].prog_id,
+ bpf_testcase_table[idx].prog_id,
true);
if (ret != TEST_OK || !obj_buf || !obj_buf_sz) {
pr_debug("Unable to get BPF object, %s\n",
- bpf_testcase_table[index].msg_compile_fail);
- if (index == 0)
+ bpf_testcase_table[idx].msg_compile_fail);
+ if (idx == 0)
return TEST_SKIP;
else
return TEST_FAIL;
}
obj = prepare_bpf(obj_buf, obj_buf_sz,
- bpf_testcase_table[index].name);
+ bpf_testcase_table[idx].name);
if (!obj) {
ret = TEST_FAIL;
goto out;
}
ret = do_test(obj,
- bpf_testcase_table[index].target_func,
- bpf_testcase_table[index].expect_result);
+ bpf_testcase_table[idx].target_func,
+ bpf_testcase_table[idx].expect_result);
out:
bpf__clear();
return ret;
diff --git a/kernel/tools/perf/tests/llvm.c b/kernel/tools/perf/tests/llvm.c
index bc4cf507c..366e38ba8 100644
--- a/kernel/tools/perf/tests/llvm.c
+++ b/kernel/tools/perf/tests/llvm.c
@@ -50,7 +50,7 @@ static struct {
int
test_llvm__fetch_bpf_obj(void **p_obj_buf,
size_t *p_obj_buf_sz,
- enum test_llvm__testcase index,
+ enum test_llvm__testcase idx,
bool force)
{
const char *source;
@@ -59,11 +59,11 @@ test_llvm__fetch_bpf_obj(void **p_obj_buf,
char *tmpl_new = NULL, *clang_opt_new = NULL;
int err, old_verbose, ret = TEST_FAIL;
- if (index >= __LLVM_TESTCASE_MAX)
+ if (idx >= __LLVM_TESTCASE_MAX)
return TEST_FAIL;
- source = bpf_source_table[index].source;
- desc = bpf_source_table[index].desc;
+ source = bpf_source_table[idx].source;
+ desc = bpf_source_table[idx].desc;
perf_config(perf_config_cb, NULL);
diff --git a/kernel/tools/perf/ui/browsers/hists.c b/kernel/tools/perf/ui/browsers/hists.c
index 81def6c3f..d80293864 100644
--- a/kernel/tools/perf/ui/browsers/hists.c
+++ b/kernel/tools/perf/ui/browsers/hists.c
@@ -684,7 +684,6 @@ static int __hpp__slsmg_color_printf(struct perf_hpp *hpp, const char *fmt, ...)
ret = scnprintf(hpp->buf, hpp->size, fmt, len, percent);
ui_browser__printf(arg->b, "%s", hpp->buf);
- advance_hpp(hpp, ret);
return ret;
}
@@ -2059,10 +2058,12 @@ skip_annotation:
*
* See hist_browser__show_entry.
*/
- nr_options += add_script_opt(browser,
- &actions[nr_options],
- &options[nr_options],
- NULL, browser->selection->sym);
+ if (sort__has_sym && browser->selection->sym) {
+ nr_options += add_script_opt(browser,
+ &actions[nr_options],
+ &options[nr_options],
+ NULL, browser->selection->sym);
+ }
}
nr_options += add_script_opt(browser, &actions[nr_options],
&options[nr_options], NULL, NULL);
diff --git a/kernel/tools/perf/util/event.c b/kernel/tools/perf/util/event.c
index 8b10621b4..956187bf1 100644
--- a/kernel/tools/perf/util/event.c
+++ b/kernel/tools/perf/util/event.c
@@ -274,7 +274,7 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
strcpy(execname, "");
/* 00400000-0040c000 r-xp 00000000 fd:01 41038 /bin/cat */
- n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %x:%x %u %s\n",
+ n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %x:%x %u %[^\n]\n",
&event->mmap2.start, &event->mmap2.len, prot,
&event->mmap2.pgoff, &event->mmap2.maj,
&event->mmap2.min,
diff --git a/kernel/tools/perf/util/evlist.c b/kernel/tools/perf/util/evlist.c
index d1392194a..b4b96120f 100644
--- a/kernel/tools/perf/util/evlist.c
+++ b/kernel/tools/perf/util/evlist.c
@@ -1211,12 +1211,12 @@ void perf_evlist__set_maps(struct perf_evlist *evlist, struct cpu_map *cpus,
*/
if (cpus != evlist->cpus) {
cpu_map__put(evlist->cpus);
- evlist->cpus = cpus;
+ evlist->cpus = cpu_map__get(cpus);
}
if (threads != evlist->threads) {
thread_map__put(evlist->threads);
- evlist->threads = threads;
+ evlist->threads = thread_map__get(threads);
}
perf_evlist__propagate_maps(evlist);
diff --git a/kernel/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/kernel/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index 9409d014b..71df7acf8 100644
--- a/kernel/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/kernel/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -89,6 +89,7 @@ struct intel_pt_decoder {
bool pge;
bool have_tma;
bool have_cyc;
+ bool fixup_last_mtc;
uint64_t pos;
uint64_t last_ip;
uint64_t ip;
@@ -584,10 +585,31 @@ struct intel_pt_calc_cyc_to_tsc_info {
uint64_t tsc_timestamp;
uint64_t timestamp;
bool have_tma;
+ bool fixup_last_mtc;
bool from_mtc;
double cbr_cyc_to_tsc;
};
+/*
+ * MTC provides a 8-bit slice of CTC but the TMA packet only provides the lower
+ * 16 bits of CTC. If mtc_shift > 8 then some of the MTC bits are not in the CTC
+ * provided by the TMA packet. Fix-up the last_mtc calculated from the TMA
+ * packet by copying the missing bits from the current MTC assuming the least
+ * difference between the two, and that the current MTC comes after last_mtc.
+ */
+static void intel_pt_fixup_last_mtc(uint32_t mtc, int mtc_shift,
+ uint32_t *last_mtc)
+{
+ uint32_t first_missing_bit = 1U << (16 - mtc_shift);
+ uint32_t mask = ~(first_missing_bit - 1);
+
+ *last_mtc |= mtc & mask;
+ if (*last_mtc >= mtc) {
+ *last_mtc -= first_missing_bit;
+ *last_mtc &= 0xff;
+ }
+}
+
static int intel_pt_calc_cyc_cb(struct intel_pt_pkt_info *pkt_info)
{
struct intel_pt_decoder *decoder = pkt_info->decoder;
@@ -617,6 +639,11 @@ static int intel_pt_calc_cyc_cb(struct intel_pt_pkt_info *pkt_info)
return 0;
mtc = pkt_info->packet.payload;
+ if (decoder->mtc_shift > 8 && data->fixup_last_mtc) {
+ data->fixup_last_mtc = false;
+ intel_pt_fixup_last_mtc(mtc, decoder->mtc_shift,
+ &data->last_mtc);
+ }
if (mtc > data->last_mtc)
mtc_delta = mtc - data->last_mtc;
else
@@ -685,6 +712,7 @@ static int intel_pt_calc_cyc_cb(struct intel_pt_pkt_info *pkt_info)
data->ctc_delta = 0;
data->have_tma = true;
+ data->fixup_last_mtc = true;
return 0;
@@ -751,6 +779,7 @@ static void intel_pt_calc_cyc_to_tsc(struct intel_pt_decoder *decoder,
.tsc_timestamp = decoder->tsc_timestamp,
.timestamp = decoder->timestamp,
.have_tma = decoder->have_tma,
+ .fixup_last_mtc = decoder->fixup_last_mtc,
.from_mtc = from_mtc,
.cbr_cyc_to_tsc = 0,
};
@@ -1241,6 +1270,7 @@ static void intel_pt_calc_tma(struct intel_pt_decoder *decoder)
}
decoder->ctc_delta = 0;
decoder->have_tma = true;
+ decoder->fixup_last_mtc = true;
intel_pt_log("CTC timestamp " x64_fmt " last MTC %#x CTC rem %#x\n",
decoder->ctc_timestamp, decoder->last_mtc, ctc_rem);
}
@@ -1255,6 +1285,12 @@ static void intel_pt_calc_mtc_timestamp(struct intel_pt_decoder *decoder)
mtc = decoder->packet.payload;
+ if (decoder->mtc_shift > 8 && decoder->fixup_last_mtc) {
+ decoder->fixup_last_mtc = false;
+ intel_pt_fixup_last_mtc(mtc, decoder->mtc_shift,
+ &decoder->last_mtc);
+ }
+
if (mtc > decoder->last_mtc)
mtc_delta = mtc - decoder->last_mtc;
else
@@ -1323,6 +1359,8 @@ static void intel_pt_calc_cyc_timestamp(struct intel_pt_decoder *decoder)
timestamp, decoder->timestamp);
else
decoder->timestamp = timestamp;
+
+ decoder->timestamp_insn_cnt = 0;
}
/* Walk PSB+ packets when already in sync. */
diff --git a/kernel/tools/perf/util/intel-pt.c b/kernel/tools/perf/util/intel-pt.c
index 97f963a3d..89927b5be 100644
--- a/kernel/tools/perf/util/intel-pt.c
+++ b/kernel/tools/perf/util/intel-pt.c
@@ -238,7 +238,7 @@ static int intel_pt_get_trace(struct intel_pt_buffer *b, void *data)
}
queue = &ptq->pt->queues.queue_array[ptq->queue_nr];
-
+next:
buffer = auxtrace_buffer__next(queue, buffer);
if (!buffer) {
if (old_buffer)
@@ -261,9 +261,6 @@ static int intel_pt_get_trace(struct intel_pt_buffer *b, void *data)
intel_pt_do_fix_overlap(ptq->pt, old_buffer, buffer))
return -ENOMEM;
- if (old_buffer)
- auxtrace_buffer__drop_data(old_buffer);
-
if (buffer->use_data) {
b->len = buffer->use_size;
b->buf = buffer->use_data;
@@ -273,6 +270,16 @@ static int intel_pt_get_trace(struct intel_pt_buffer *b, void *data)
}
b->ref_timestamp = buffer->reference;
+ /*
+ * If in snapshot mode and the buffer has no usable data, get next
+ * buffer and again check overlap against old_buffer.
+ */
+ if (ptq->pt->snapshot_mode && !b->len)
+ goto next;
+
+ if (old_buffer)
+ auxtrace_buffer__drop_data(old_buffer);
+
if (!old_buffer || ptq->pt->sampling_mode || (ptq->pt->snapshot_mode &&
!buffer->consecutive)) {
b->consecutive = false;
@@ -1127,7 +1134,7 @@ static int intel_pt_synth_transaction_sample(struct intel_pt_queue *ptq)
pr_err("Intel Processor Trace: failed to deliver transaction event, error %d\n",
ret);
- if (pt->synth_opts.callchain)
+ if (pt->synth_opts.last_branch)
intel_pt_reset_last_branch_rb(ptq);
return ret;
diff --git a/kernel/tools/perf/util/parse-events.c b/kernel/tools/perf/util/parse-events.c
index b48e87693..a35db828b 100644
--- a/kernel/tools/perf/util/parse-events.c
+++ b/kernel/tools/perf/util/parse-events.c
@@ -2101,11 +2101,11 @@ char *parse_events_formats_error_string(char *additional_terms)
/* valid terms */
if (additional_terms) {
- if (!asprintf(&str, "valid terms: %s,%s",
- additional_terms, static_terms))
+ if (asprintf(&str, "valid terms: %s,%s",
+ additional_terms, static_terms) < 0)
goto fail;
} else {
- if (!asprintf(&str, "valid terms: %s", static_terms))
+ if (asprintf(&str, "valid terms: %s", static_terms) < 0)
goto fail;
}
return str;
diff --git a/kernel/tools/perf/util/pmu.c b/kernel/tools/perf/util/pmu.c
index e4b173dec..6f2a02794 100644
--- a/kernel/tools/perf/util/pmu.c
+++ b/kernel/tools/perf/util/pmu.c
@@ -283,13 +283,12 @@ static int pmu_aliases_parse(char *dir, struct list_head *head)
{
struct dirent *evt_ent;
DIR *event_dir;
- int ret = 0;
event_dir = opendir(dir);
if (!event_dir)
return -EINVAL;
- while (!ret && (evt_ent = readdir(event_dir))) {
+ while ((evt_ent = readdir(event_dir))) {
char path[PATH_MAX];
char *name = evt_ent->d_name;
FILE *file;
@@ -305,17 +304,19 @@ static int pmu_aliases_parse(char *dir, struct list_head *head)
snprintf(path, PATH_MAX, "%s/%s", dir, name);
- ret = -EINVAL;
file = fopen(path, "r");
- if (!file)
- break;
+ if (!file) {
+ pr_debug("Cannot open %s\n", path);
+ continue;
+ }
- ret = perf_pmu__new_alias(head, dir, name, file);
+ if (perf_pmu__new_alias(head, dir, name, file) < 0)
+ pr_debug("Cannot set up %s\n", name);
fclose(file);
}
closedir(event_dir);
- return ret;
+ return 0;
}
/*
diff --git a/kernel/tools/perf/util/setup.py b/kernel/tools/perf/util/setup.py
index 183310376..c8680984d 100644
--- a/kernel/tools/perf/util/setup.py
+++ b/kernel/tools/perf/util/setup.py
@@ -22,6 +22,7 @@ cflags = getenv('CFLAGS', '').split()
# switch off several checks (need to be at the end of cflags list)
cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter' ]
+src_perf = getenv('srctree') + '/tools/perf'
build_lib = getenv('PYTHON_EXTBUILD_LIB')
build_tmp = getenv('PYTHON_EXTBUILD_TMP')
libtraceevent = getenv('LIBTRACEEVENT')
@@ -30,6 +31,9 @@ libapikfs = getenv('LIBAPI')
ext_sources = [f.strip() for f in file('util/python-ext-sources')
if len(f.strip()) > 0 and f[0] != '#']
+# use full paths with source files
+ext_sources = map(lambda x: '%s/%s' % (src_perf, x) , ext_sources)
+
perf = Extension('perf',
sources = ext_sources,
include_dirs = ['util/include'],
diff --git a/kernel/tools/perf/util/stat.c b/kernel/tools/perf/util/stat.c
index 4a3a72cb5..6ce624cb7 100644
--- a/kernel/tools/perf/util/stat.c
+++ b/kernel/tools/perf/util/stat.c
@@ -311,6 +311,16 @@ int perf_stat_process_counter(struct perf_stat_config *config,
aggr->val = aggr->ena = aggr->run = 0;
+ /*
+ * We calculate counter's data every interval,
+ * and the display code shows ps->res_stats
+ * avg value. We need to zero the stats for
+ * interval mode, otherwise overall avg running
+ * averages will be shown for each interval.
+ */
+ if (config->interval)
+ init_stats(ps->res_stats);
+
if (counter->per_pkg)
zero_per_pkg(counter);
diff --git a/kernel/tools/perf/util/symbol-elf.c b/kernel/tools/perf/util/symbol-elf.c
index 475d88d0a..27ae382fe 100644
--- a/kernel/tools/perf/util/symbol-elf.c
+++ b/kernel/tools/perf/util/symbol-elf.c
@@ -1091,9 +1091,8 @@ new_symbol:
* For misannotated, zeroed, ASM function sizes.
*/
if (nr > 0) {
- if (!symbol_conf.allow_aliases)
- symbols__fixup_duplicate(&dso->symbols[map->type]);
symbols__fixup_end(&dso->symbols[map->type]);
+ symbols__fixup_duplicate(&dso->symbols[map->type]);
if (kmap) {
/*
* We need to fixup this here too because we create new
diff --git a/kernel/tools/perf/util/symbol.c b/kernel/tools/perf/util/symbol.c
index cd08027a6..520a32a12 100644
--- a/kernel/tools/perf/util/symbol.c
+++ b/kernel/tools/perf/util/symbol.c
@@ -151,6 +151,9 @@ void symbols__fixup_duplicate(struct rb_root *symbols)
struct rb_node *nd;
struct symbol *curr, *next;
+ if (symbol_conf.allow_aliases)
+ return;
+
nd = rb_first(symbols);
while (nd) {
@@ -1275,8 +1278,8 @@ int dso__load_kallsyms(struct dso *dso, const char *filename,
if (kallsyms__delta(map, filename, &delta))
return -1;
- symbols__fixup_duplicate(&dso->symbols[map->type]);
symbols__fixup_end(&dso->symbols[map->type]);
+ symbols__fixup_duplicate(&dso->symbols[map->type]);
if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
dso->symtab_type = DSO_BINARY_TYPE__GUEST_KALLSYMS;
diff --git a/kernel/tools/perf/util/trace-event-scripting.c b/kernel/tools/perf/util/trace-event-scripting.c
index 9df61059a..a2fd6e79d 100644
--- a/kernel/tools/perf/util/trace-event-scripting.c
+++ b/kernel/tools/perf/util/trace-event-scripting.c
@@ -95,7 +95,8 @@ static void register_python_scripting(struct scripting_ops *scripting_ops)
if (err)
die("error registering py script extension");
- scripting_context = malloc(sizeof(struct scripting_context));
+ if (scripting_context == NULL)
+ scripting_context = malloc(sizeof(*scripting_context));
}
#ifdef NO_LIBPYTHON
@@ -159,7 +160,8 @@ static void register_perl_scripting(struct scripting_ops *scripting_ops)
if (err)
die("error registering pl script extension");
- scripting_context = malloc(sizeof(struct scripting_context));
+ if (scripting_context == NULL)
+ scripting_context = malloc(sizeof(*scripting_context));
}
#ifdef NO_LIBPERL