summaryrefslogtreecommitdiff
path: root/tools/perf
diff options
context:
space:
mode:
Diffstat (limited to 'tools/perf')
-rw-r--r--tools/perf/Documentation/perf-diff.txt21
-rw-r--r--tools/perf/Documentation/perf-report.txt24
-rw-r--r--tools/perf/Documentation/perf-top.txt18
-rw-r--r--tools/perf/Makefile.perf4
-rw-r--r--tools/perf/arch/x86/tests/dwarf-unwind.c2
-rw-r--r--tools/perf/builtin-annotate.c3
-rw-r--r--tools/perf/builtin-diff.c43
-rw-r--r--tools/perf/builtin-kmem.c86
-rw-r--r--tools/perf/builtin-lock.c10
-rw-r--r--tools/perf/builtin-mem.c15
-rw-r--r--tools/perf/builtin-report.c155
-rw-r--r--tools/perf/builtin-sched.c10
-rw-r--r--tools/perf/builtin-top.c8
-rw-r--r--tools/perf/perf-completion.sh4
-rw-r--r--tools/perf/perf.h6
-rw-r--r--tools/perf/tests/builtin-test.c12
-rw-r--r--tools/perf/tests/hists_common.c148
-rw-r--r--tools/perf/tests/hists_common.h44
-rw-r--r--tools/perf/tests/hists_filter.c315
-rw-r--r--tools/perf/tests/hists_link.c141
-rw-r--r--tools/perf/tests/mmap-thread-lookup.c233
-rw-r--r--tools/perf/tests/tests.h3
-rw-r--r--tools/perf/tests/thread-mg-share.c90
-rw-r--r--tools/perf/ui/browsers/hists.c131
-rw-r--r--tools/perf/ui/gtk/hists.c11
-rw-r--r--tools/perf/ui/hist.c8
-rw-r--r--tools/perf/ui/stdio/hist.c2
-rw-r--r--tools/perf/util/callchain.c78
-rw-r--r--tools/perf/util/callchain.h1
-rw-r--r--tools/perf/util/config.c4
-rw-r--r--tools/perf/util/cpumap.c160
-rw-r--r--tools/perf/util/cpumap.h35
-rw-r--r--tools/perf/util/event.c2
-rw-r--r--tools/perf/util/hist.c112
-rw-r--r--tools/perf/util/hist.h19
-rw-r--r--tools/perf/util/machine.c11
-rw-r--r--tools/perf/util/map.c23
-rw-r--r--tools/perf/util/map.h12
-rw-r--r--tools/perf/util/pmu.c6
-rw-r--r--tools/perf/util/symbol.h3
-rw-r--r--tools/perf/util/thread.c52
-rw-r--r--tools/perf/util/thread.h3
42 files changed, 1605 insertions, 463 deletions
diff --git a/tools/perf/Documentation/perf-diff.txt b/tools/perf/Documentation/perf-diff.txt
index fdfceee0ffd0..fbfa1192923c 100644
--- a/tools/perf/Documentation/perf-diff.txt
+++ b/tools/perf/Documentation/perf-diff.txt
@@ -33,17 +33,20 @@ OPTIONS
-d::
--dsos=::
Only consider symbols in these dsos. CSV that understands
- file://filename entries.
+ file://filename entries. This option will affect the percentage
+ of the Baseline/Delta column. See --percentage for more info.
-C::
--comms=::
Only consider symbols in these comms. CSV that understands
- file://filename entries.
+ file://filename entries. This option will affect the percentage
+ of the Baseline/Delta column. See --percentage for more info.
-S::
--symbols=::
Only consider these symbols. CSV that understands
- file://filename entries.
+ file://filename entries. This option will affect the percentage
+ of the Baseline/Delta column. See --percentage for more info.
-s::
--sort=::
@@ -89,6 +92,14 @@ OPTIONS
--order::
Specify compute sorting column number.
+--percentage::
+ Determine how to display the overhead percentage of filtered entries.
+ Filters can be applied by --comms, --dsos and/or --symbols options.
+
+ "relative" means it's relative to filtered entries only so that the
+ sum of shown entries will be always 100%. "absolute" means it retains
+ the original value before and after the filter is applied.
+
COMPARISON
----------
The comparison is governed by the baseline file. The baseline perf.data
@@ -157,6 +168,10 @@ with:
- period_percent being the % of the hist entry period value within
single data file
+ - with filtering by -C, -d and/or -S, period_percent might be changed
+ relative to how entries are filtered. Use --percentage=absolute to
+ prevent such fluctuation.
+
ratio
~~~~~
If specified the 'Ratio' column is displayed with value 'r' computed as:
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 8eab8a4bdeb8..09af66298564 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -25,10 +25,6 @@ OPTIONS
--verbose::
Be more verbose. (show symbol address, etc)
--d::
---dsos=::
- Only consider symbols in these dsos. CSV that understands
- file://filename entries.
-n::
--show-nr-samples::
Show the number of samples for each symbol
@@ -42,11 +38,18 @@ OPTIONS
-c::
--comms=::
Only consider symbols in these comms. CSV that understands
- file://filename entries.
+ file://filename entries. This option will affect the percentage of
+ the overhead column. See --percentage for more info.
+-d::
+--dsos=::
+ Only consider symbols in these dsos. CSV that understands
+ file://filename entries. This option will affect the percentage of
+ the overhead column. See --percentage for more info.
-S::
--symbols=::
Only consider these symbols. CSV that understands
- file://filename entries.
+ file://filename entries. This option will affect the percentage of
+ the overhead column. See --percentage for more info.
--symbol-filter=::
Only show symbols that match (partially) with this filter.
@@ -237,6 +240,15 @@ OPTIONS
Do not show entries which have an overhead under that percent.
(Default: 0).
+--percentage::
+ Determine how to display the overhead percentage of filtered entries.
+ Filters can be applied by --comms, --dsos and/or --symbols options and
+ Zoom operations on the TUI (thread, dso, etc).
+
+ "relative" means it's relative to filtered entries only so that the
+ sum of shown entries will be always 100%. "absolute" means it retains
+ the original value before and after the filter is applied.
+
--header::
Show header information in the perf.data file. This includes
various information like hostname, OS and perf version, cpu/mem
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 976b00c6cdb1..64ed79c43639 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -123,13 +123,16 @@ Default is to monitor all CPUS.
Show a column with the sum of periods.
--dsos::
- Only consider symbols in these dsos.
+ Only consider symbols in these dsos. This option will affect the
+ percentage of the overhead column. See --percentage for more info.
--comms::
- Only consider symbols in these comms.
+ Only consider symbols in these comms. This option will affect the
+ percentage of the overhead column. See --percentage for more info.
--symbols::
- Only consider these symbols.
+ Only consider these symbols. This option will affect the
+ percentage of the overhead column. See --percentage for more info.
-M::
--disassembler-style=:: Set disassembler style for objdump.
@@ -165,6 +168,15 @@ Default is to monitor all CPUS.
Do not show entries which have an overhead under that percent.
(Default: 0).
+--percentage::
+ Determine how to display the overhead percentage of filtered entries.
+ Filters can be applied by --comms, --dsos and/or --symbols options and
+ Zoom operations on the TUI (thread, dso, etc).
+
+ "relative" means it's relative to filtered entries only so that the
+ sum of shown entries will be always 100%. "absolute" means it retains
+ the original value before and after the filter is applied.
+
INTERACTIVE PROMPTING KEYS
--------------------------
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 895edd32930c..5e21aad44142 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -397,7 +397,9 @@ LIB_OBJS += $(OUTPUT)tests/rdpmc.o
LIB_OBJS += $(OUTPUT)tests/evsel-roundtrip-name.o
LIB_OBJS += $(OUTPUT)tests/evsel-tp-sched.o
LIB_OBJS += $(OUTPUT)tests/pmu.o
+LIB_OBJS += $(OUTPUT)tests/hists_common.o
LIB_OBJS += $(OUTPUT)tests/hists_link.o
+LIB_OBJS += $(OUTPUT)tests/hists_filter.o
LIB_OBJS += $(OUTPUT)tests/python-use.o
LIB_OBJS += $(OUTPUT)tests/bp_signal.o
LIB_OBJS += $(OUTPUT)tests/bp_signal_overflow.o
@@ -414,6 +416,8 @@ ifeq ($(ARCH),x86)
LIB_OBJS += $(OUTPUT)tests/dwarf-unwind.o
endif
endif
+LIB_OBJS += $(OUTPUT)tests/mmap-thread-lookup.o
+LIB_OBJS += $(OUTPUT)tests/thread-mg-share.o
BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o
BUILTIN_OBJS += $(OUTPUT)builtin-bench.o
diff --git a/tools/perf/arch/x86/tests/dwarf-unwind.c b/tools/perf/arch/x86/tests/dwarf-unwind.c
index 83bc2385e6d3..9f89f899ccc7 100644
--- a/tools/perf/arch/x86/tests/dwarf-unwind.c
+++ b/tools/perf/arch/x86/tests/dwarf-unwind.c
@@ -23,7 +23,7 @@ static int sample_ustack(struct perf_sample *sample,
sp = (unsigned long) regs[PERF_REG_X86_SP];
- map = map_groups__find(&thread->mg, MAP__VARIABLE, (u64) sp);
+ map = map_groups__find(thread->mg, MAP__VARIABLE, (u64) sp);
if (!map) {
pr_debug("failed to get stack map\n");
free(buf);
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 0da603b79b61..d30d2c2e2a7a 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -46,7 +46,7 @@ struct perf_annotate {
};
static int perf_evsel__add_sample(struct perf_evsel *evsel,
- struct perf_sample *sample,
+ struct perf_sample *sample __maybe_unused,
struct addr_location *al,
struct perf_annotate *ann)
{
@@ -70,7 +70,6 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel,
return -ENOMEM;
ret = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
- evsel->hists.stats.total_period += sample->period;
hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
return ret;
}
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 204fffe22532..f3b10dcf6838 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -220,7 +220,8 @@ static int setup_compute(const struct option *opt, const char *str,
static double period_percent(struct hist_entry *he, u64 period)
{
- u64 total = he->hists->stats.total_period;
+ u64 total = hists__total_period(he->hists);
+
return (period * 100.0) / total;
}
@@ -259,11 +260,18 @@ static s64 compute_wdiff(struct hist_entry *he, struct hist_entry *pair)
static int formula_delta(struct hist_entry *he, struct hist_entry *pair,
char *buf, size_t size)
{
+ u64 he_total = he->hists->stats.total_period;
+ u64 pair_total = pair->hists->stats.total_period;
+
+ if (symbol_conf.filter_relative) {
+ he_total = he->hists->stats.total_non_filtered_period;
+ pair_total = pair->hists->stats.total_non_filtered_period;
+ }
return scnprintf(buf, size,
"(%" PRIu64 " * 100 / %" PRIu64 ") - "
"(%" PRIu64 " * 100 / %" PRIu64 ")",
- pair->stat.period, pair->hists->stats.total_period,
- he->stat.period, he->hists->stats.total_period);
+ pair->stat.period, pair_total,
+ he->stat.period, he_total);
}
static int formula_ratio(struct hist_entry *he, struct hist_entry *pair,
@@ -327,16 +335,22 @@ static int diff__process_sample_event(struct perf_tool *tool __maybe_unused,
return -1;
}
- if (al.filtered)
- return 0;
-
if (hists__add_entry(&evsel->hists, &al, sample->period,
sample->weight, sample->transaction)) {
pr_warning("problem incrementing symbol period, skipping event\n");
return -1;
}
+ /*
+ * The total_period is updated here before going to the output
+ * tree since normally only the baseline hists will call
+ * hists__output_resort() and precompute needs the total
+ * period in order to sort entries by percentage delta.
+ */
evsel->hists.stats.total_period += sample->period;
+ if (!al.filtered)
+ evsel->hists.stats.total_non_filtered_period += sample->period;
+
return 0;
}
@@ -564,8 +578,7 @@ static void hists__compute_resort(struct hists *hists)
hists->entries = RB_ROOT;
next = rb_first(root);
- hists->nr_entries = 0;
- hists->stats.total_period = 0;
+ hists__reset_stats(hists);
hists__reset_col_len(hists);
while (next != NULL) {
@@ -575,7 +588,10 @@ static void hists__compute_resort(struct hists *hists)
next = rb_next(&he->rb_node_in);
insert_hist_entry_by_compute(&hists->entries, he, compute);
- hists__inc_nr_entries(hists, he);
+ hists__inc_stats(hists, he);
+
+ if (!he->filtered)
+ hists__calc_col_len(hists, he);
}
}
@@ -732,13 +748,16 @@ static const struct option options[] = {
OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
"Look for files with symbols relative to this directory"),
OPT_UINTEGER('o', "order", &sort_compute, "Specify compute sorting."),
+ OPT_CALLBACK(0, "percentage", NULL, "relative|absolute",
+ "How to display percentage of filtered entries", parse_filter_percentage),
OPT_END()
};
static double baseline_percent(struct hist_entry *he)
{
- struct hists *hists = he->hists;
- return 100.0 * he->stat.period / hists->stats.total_period;
+ u64 total = hists__total_period(he->hists);
+
+ return 100.0 * he->stat.period / total;
}
static int hpp__color_baseline(struct perf_hpp_fmt *fmt,
@@ -1120,6 +1139,8 @@ static int data_init(int argc, const char **argv)
int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused)
{
+ perf_config(perf_default_config, NULL);
+
sort_order = diff__default_sort_order;
argc = parse_options(argc, argv, options, diff_usage, 0);
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 929462aa4943..f91fa4376f4b 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -14,6 +14,7 @@
#include "util/parse-options.h"
#include "util/trace-event.h"
#include "util/data.h"
+#include "util/cpumap.h"
#include "util/debug.h"
@@ -31,9 +32,6 @@ static int caller_lines = -1;
static bool raw_ip;
-static int *cpunode_map;
-static int max_cpu_num;
-
struct alloc_stat {
u64 call_site;
u64 ptr;
@@ -55,76 +53,6 @@ static struct rb_root root_caller_sorted;
static unsigned long total_requested, total_allocated;
static unsigned long nr_allocs, nr_cross_allocs;
-#define PATH_SYS_NODE "/sys/devices/system/node"
-
-static int init_cpunode_map(void)
-{
- FILE *fp;
- int i, err = -1;
-
- fp = fopen("/sys/devices/system/cpu/kernel_max", "r");
- if (!fp) {
- max_cpu_num = 4096;
- return 0;
- }
-
- if (fscanf(fp, "%d", &max_cpu_num) < 1) {
- pr_err("Failed to read 'kernel_max' from sysfs");
- goto out_close;
- }
-
- max_cpu_num++;
-
- cpunode_map = calloc(max_cpu_num, sizeof(int));
- if (!cpunode_map) {
- pr_err("%s: calloc failed\n", __func__);
- goto out_close;
- }
-
- for (i = 0; i < max_cpu_num; i++)
- cpunode_map[i] = -1;
-
- err = 0;
-out_close:
- fclose(fp);
- return err;
-}
-
-static int setup_cpunode_map(void)
-{
- struct dirent *dent1, *dent2;
- DIR *dir1, *dir2;
- unsigned int cpu, mem;
- char buf[PATH_MAX];
-
- if (init_cpunode_map())
- return -1;
-
- dir1 = opendir(PATH_SYS_NODE);
- if (!dir1)
- return 0;
-
- while ((dent1 = readdir(dir1)) != NULL) {
- if (dent1->d_type != DT_DIR ||
- sscanf(dent1->d_name, "node%u", &mem) < 1)
- continue;
-
- snprintf(buf, PATH_MAX, "%s/%s", PATH_SYS_NODE, dent1->d_name);
- dir2 = opendir(buf);
- if (!dir2)
- continue;
- while ((dent2 = readdir(dir2)) != NULL) {
- if (dent2->d_type != DT_LNK ||
- sscanf(dent2->d_name, "cpu%u", &cpu) < 1)
- continue;
- cpunode_map[cpu] = mem;
- }
- closedir(dir2);
- }
- closedir(dir1);
- return 0;
-}
-
static int insert_alloc_stat(unsigned long call_site, unsigned long ptr,
int bytes_req, int bytes_alloc, int cpu)
{
@@ -235,7 +163,7 @@ static int perf_evsel__process_alloc_node_event(struct perf_evsel *evsel,
int ret = perf_evsel__process_alloc_event(evsel, sample);
if (!ret) {
- int node1 = cpunode_map[sample->cpu],
+ int node1 = cpu__get_node(sample->cpu),
node2 = perf_evsel__intval(evsel, sample, "node");
if (node1 != node2)
@@ -756,11 +684,13 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
OPT_BOOLEAN(0, "raw-ip", &raw_ip, "show raw ip instead of symbol"),
OPT_END()
};
- const char * const kmem_usage[] = {
- "perf kmem [<options>] {record|stat}",
+ const char *const kmem_subcommands[] = { "record", "stat", NULL };
+ const char *kmem_usage[] = {
+ NULL,
NULL
};
- argc = parse_options(argc, argv, kmem_options, kmem_usage, 0);
+ argc = parse_options_subcommand(argc, argv, kmem_options,
+ kmem_subcommands, kmem_usage, 0);
if (!argc)
usage_with_options(kmem_usage, kmem_options);
@@ -770,7 +700,7 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
if (!strncmp(argv[0], "rec", 3)) {
return __cmd_record(argc, argv);
} else if (!strcmp(argv[0], "stat")) {
- if (setup_cpunode_map())
+ if (cpu__setup_cpunode_map())
return -1;
if (list_empty(&caller_sort))
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index c852c7a85d32..6148afc995c6 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -961,8 +961,10 @@ int cmd_lock(int argc, const char **argv, const char *prefix __maybe_unused)
"perf lock info [<options>]",
NULL
};
- const char * const lock_usage[] = {
- "perf lock [<options>] {record|report|script|info}",
+ const char *const lock_subcommands[] = { "record", "report", "script",
+ "info", NULL };
+ const char *lock_usage[] = {
+ NULL,
NULL
};
const char * const report_usage[] = {
@@ -976,8 +978,8 @@ int cmd_lock(int argc, const char **argv, const char *prefix __maybe_unused)
for (i = 0; i < LOCKHASH_SIZE; i++)
INIT_LIST_HEAD(lockhash_table + i);
- argc = parse_options(argc, argv, lock_options, lock_usage,
- PARSE_OPT_STOP_AT_NON_OPTION);
+ argc = parse_options_subcommand(argc, argv, lock_options, lock_subcommands,
+ lock_usage, PARSE_OPT_STOP_AT_NON_OPTION);
if (!argc)
usage_with_options(lock_usage, lock_options);
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 2e3ade69a58e..4a1a6c94a5eb 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -21,11 +21,6 @@ struct perf_mem {
DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
};
-static const char * const mem_usage[] = {
- "perf mem [<options>] {record <command> |report}",
- NULL
-};
-
static int __cmd_record(int argc, const char **argv)
{
int rec_argc, i = 0, j;
@@ -220,9 +215,15 @@ int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused)
" between columns '.' is reserved."),
OPT_END()
};
+ const char *const mem_subcommands[] = { "record", "report", NULL };
+ const char *mem_usage[] = {
+ NULL,
+ NULL
+ };
+
- argc = parse_options(argc, argv, mem_options, mem_usage,
- PARSE_OPT_STOP_AT_NON_OPTION);
+ argc = parse_options_subcommand(argc, argv, mem_options, mem_subcommands,
+ mem_usage, PARSE_OPT_STOP_AT_NON_OPTION);
if (!argc || !(strncmp(argv[0], "rec", 3) || mem_operation))
usage_with_options(mem_usage, mem_options);
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index c8f21137dfd8..89c95289fd51 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -57,6 +57,7 @@ struct report {
const char *cpu_list;
const char *symbol_filter_str;
float min_percent;
+ u64 nr_entries;
DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
};
@@ -75,6 +76,27 @@ static int report__config(const char *var, const char *value, void *cb)
return perf_default_config(var, value, cb);
}
+static void report__inc_stats(struct report *rep, struct hist_entry *he)
+{
+ /*
+ * The @he is either of a newly created one or an existing one
+ * merging current sample. We only want to count a new one so
+ * checking ->nr_events being 1.
+ */
+ if (he->stat.nr_events == 1)
+ rep->nr_entries++;
+
+ /*
+ * Only counts number of samples at this stage as it's more
+ * natural to do it here and non-sample events are also
+ * counted in perf_session_deliver_event(). The dump_trace
+ * requires this info is ready before going to the output tree.
+ */
+ hists__inc_nr_events(he->hists, PERF_RECORD_SAMPLE);
+ if (!he->filtered)
+ he->hists->stats.nr_non_filtered_samples++;
+}
+
static int report__add_mem_hist_entry(struct report *rep, struct addr_location *al,
struct perf_sample *sample, struct perf_evsel *evsel)
{
@@ -121,8 +143,8 @@ static int report__add_mem_hist_entry(struct report *rep, struct addr_location *
goto out;
}
- evsel->hists.stats.total_period += cost;
- hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
+ report__inc_stats(rep, he);
+
err = hist_entry__append_callchain(he, sample);
out:
return err;
@@ -173,9 +195,7 @@ static int report__add_branch_hist_entry(struct report *rep, struct addr_locatio
if (err)
goto out;
}
-
- evsel->hists.stats.total_period += 1;
- hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
+ report__inc_stats(rep, he);
} else
goto out;
}
@@ -208,8 +228,8 @@ static int report__add_hist_entry(struct report *rep, struct perf_evsel *evsel,
if (ui__has_annotation())
err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
- evsel->hists.stats.total_period += sample->period;
- hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
+ report__inc_stats(rep, he);
+
out:
return err;
}
@@ -337,6 +357,11 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report
char buf[512];
size_t size = sizeof(buf);
+ if (symbol_conf.filter_relative) {
+ nr_samples = hists->stats.nr_non_filtered_samples;
+ nr_events = hists->stats.total_non_filtered_period;
+ }
+
if (perf_evsel__is_group_event(evsel)) {
struct perf_evsel *pos;
@@ -344,8 +369,13 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report
evname = buf;
for_each_group_member(pos, evsel) {
- nr_samples += pos->hists.stats.nr_events[PERF_RECORD_SAMPLE];
- nr_events += pos->hists.stats.total_period;
+ if (symbol_conf.filter_relative) {
+ nr_samples += pos->hists.stats.nr_non_filtered_samples;
+ nr_events += pos->hists.stats.total_non_filtered_period;
+ } else {
+ nr_samples += pos->hists.stats.nr_events[PERF_RECORD_SAMPLE];
+ nr_events += pos->hists.stats.total_period;
+ }
}
}
@@ -470,24 +500,12 @@ static int report__browse_hists(struct report *rep)
return ret;
}
-static u64 report__collapse_hists(struct report *rep)
+static void report__collapse_hists(struct report *rep)
{
struct ui_progress prog;
struct perf_evsel *pos;
- u64 nr_samples = 0;
- /*
- * Count number of histogram entries to use when showing progress,
- * reusing nr_samples variable.
- */
- evlist__for_each(rep->session->evlist, pos)
- nr_samples += pos->hists.nr_entries;
- ui_progress__init(&prog, nr_samples, "Merging related events...");
- /*
- * Count total number of samples, will be used to check if this
- * session had any.
- */
- nr_samples = 0;
+ ui_progress__init(&prog, rep->nr_entries, "Merging related events...");
evlist__for_each(rep->session->evlist, pos) {
struct hists *hists = &pos->hists;
@@ -496,7 +514,6 @@ static u64 report__collapse_hists(struct report *rep)
hists->symbol_filter_str = rep->symbol_filter_str;
hists__collapse_resort(hists, &prog);
- nr_samples += hists->stats.nr_events[PERF_RECORD_SAMPLE];
/* Non-group events are considered as leader */
if (symbol_conf.event_group &&
@@ -509,14 +526,11 @@ static u64 report__collapse_hists(struct report *rep)
}
ui_progress__finish();
-
- return nr_samples;
}
static int __cmd_report(struct report *rep)
{
int ret;
- u64 nr_samples;
struct perf_session *session = rep->session;
struct perf_evsel *pos;
struct perf_data_file *file = session->file;
@@ -556,12 +570,12 @@ static int __cmd_report(struct report *rep)
}
}
- nr_samples = report__collapse_hists(rep);
+ report__collapse_hists(rep);
if (session_done())
return 0;
- if (nr_samples == 0) {
+ if (rep->nr_entries == 0) {
ui__error("The %s file has no samples!\n", file->path);
return 0;
}
@@ -573,11 +587,9 @@ static int __cmd_report(struct report *rep)
}
static int
-parse_callchain_opt(const struct option *opt, const char *arg, int unset)
+report_parse_callchain_opt(const struct option *opt, const char *arg, int unset)
{
struct report *rep = (struct report *)opt->value;
- char *tok, *tok2;
- char *endptr;
/*
* --no-call-graph
@@ -587,80 +599,7 @@ parse_callchain_opt(const struct option *opt, const char *arg, int unset)
return 0;
}
- symbol_conf.use_callchain = true;
-
- if (!arg)
- return 0;
-
- tok = strtok((char *)arg, ",");
- if (!tok)
- return -1;
-
- /* get the output mode */
- if (!strncmp(tok, "graph", strlen(arg)))
- callchain_param.mode = CHAIN_GRAPH_ABS;
-
- else if (!strncmp(tok, "flat", strlen(arg)))
- callchain_param.mode = CHAIN_FLAT;
-
- else if (!strncmp(tok, "fractal", strlen(arg)))
- callchain_param.mode = CHAIN_GRAPH_REL;
-
- else if (!strncmp(tok, "none", strlen(arg))) {
- callchain_param.mode = CHAIN_NONE;
- symbol_conf.use_callchain = false;
-
- return 0;
- }
-
- else
- return -1;
-
- /* get the min percentage */
- tok = strtok(NULL, ",");
- if (!tok)
- goto setup;
-
- callchain_param.min_percent = strtod(tok, &endptr);
- if (tok == endptr)
- return -1;
-
- /* get the print limit */
- tok2 = strtok(NULL, ",");
- if (!tok2)
- goto setup;
-
- if (tok2[0] != 'c') {
- callchain_param.print_limit = strtoul(tok2, &endptr, 0);
- tok2 = strtok(NULL, ",");
- if (!tok2)
- goto setup;
- }
-
- /* get the call chain order */
- if (!strncmp(tok2, "caller", strlen("caller")))
- callchain_param.order = ORDER_CALLER;
- else if (!strncmp(tok2, "callee", strlen("callee")))
- callchain_param.order = ORDER_CALLEE;
- else
- return -1;
-
- /* Get the sort key */
- tok2 = strtok(NULL, ",");
- if (!tok2)
- goto setup;
- if (!strncmp(tok2, "function", strlen("function")))
- callchain_param.key = CCKEY_FUNCTION;
- else if (!strncmp(tok2, "address", strlen("address")))
- callchain_param.key = CCKEY_ADDRESS;
- else
- return -1;
-setup:
- if (callchain_register_param(&callchain_param) < 0) {
- pr_err("Can't register callchain params\n");
- return -1;
- }
- return 0;
+ return parse_callchain_report_opt(arg);
}
int
@@ -772,7 +711,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
"Only display entries with parent-match"),
OPT_CALLBACK_DEFAULT('g', "call-graph", &report, "output_type,min_percent[,print_limit],call_order",
"Display callchains using output_type (graph, flat, fractal, or none) , min percent threshold, optional print limit, callchain order, key (function or address). "
- "Default: fractal,0.5,callee,function", &parse_callchain_opt, callchain_default_opt),
+ "Default: fractal,0.5,callee,function", &report_parse_callchain_opt, callchain_default_opt),
OPT_INTEGER(0, "max-stack", &report.max_stack,
"Set the maximum stack depth when parsing the callchain, "
"anything beyond the specified depth will be ignored. "
@@ -823,6 +762,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
OPT_BOOLEAN(0, "mem-mode", &report.mem_mode, "mem access profile"),
OPT_CALLBACK(0, "percent-limit", &report, "percent",
"Don't show entries under that percent", parse_percent_limit),
+ OPT_CALLBACK(0, "percentage", NULL, "relative|absolute",
+ "how to display percentage of filtered entries", parse_filter_percentage),
OPT_END()
};
struct perf_data_file file = {
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 9ac0a495c954..d3fb0ed7240a 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -1713,8 +1713,10 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
"perf sched replay [<options>]",
NULL
};
- const char * const sched_usage[] = {
- "perf sched [<options>] {record|latency|map|replay|script}",
+ const char *const sched_subcommands[] = { "record", "latency", "map",
+ "replay", "script", NULL };
+ const char *sched_usage[] = {
+ NULL,
NULL
};
struct trace_sched_handler lat_ops = {
@@ -1736,8 +1738,8 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
for (i = 0; i < ARRAY_SIZE(sched.curr_pid); i++)
sched.curr_pid[i] = -1;
- argc = parse_options(argc, argv, sched_options, sched_usage,
- PARSE_OPT_STOP_AT_NON_OPTION);
+ argc = parse_options_subcommand(argc, argv, sched_options, sched_subcommands,
+ sched_usage, PARSE_OPT_STOP_AT_NON_OPTION);
if (!argc)
usage_with_options(sched_usage, sched_options);
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 65aaa5bbf7ec..37d30460bada 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -253,6 +253,9 @@ static struct hist_entry *perf_evsel__add_hist_entry(struct perf_evsel *evsel,
return NULL;
hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
+ if (!he->filtered)
+ evsel->hists.stats.nr_non_filtered_samples++;
+
return he;
}
@@ -694,8 +697,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
if (event->header.misc & PERF_RECORD_MISC_EXACT_IP)
top->exact_samples++;
- if (perf_event__preprocess_sample(event, machine, &al, sample) < 0 ||
- al.filtered)
+ if (perf_event__preprocess_sample(event, machine, &al, sample) < 0)
return;
if (!top->kptr_restrict_warned &&
@@ -1116,6 +1118,8 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
OPT_STRING('u', "uid", &target->uid_str, "user", "user to profile"),
OPT_CALLBACK(0, "percent-limit", &top, "percent",
"Don't show entries under that percent", parse_percent_limit),
+ OPT_CALLBACK(0, "percentage", NULL, "relative|absolute",
+ "How to display percentage of filtered entries", parse_filter_percentage),
OPT_END()
};
const char * const top_usage[] = {
diff --git a/tools/perf/perf-completion.sh b/tools/perf/perf-completion.sh
index ae3a57694b6b..33569847fdcc 100644
--- a/tools/perf/perf-completion.sh
+++ b/tools/perf/perf-completion.sh
@@ -121,8 +121,8 @@ __perf_main ()
elif [[ $prev == "-e" && "${words[1]}" == @(record|stat|top) ]]; then
evts=$($cmd list --raw-dump)
__perfcomp_colon "$evts" "$cur"
- # List subcommands for 'perf kvm'
- elif [[ $prev == "kvm" ]]; then
+ # List subcommands for perf commands
+ elif [[ $prev == @(kvm|kmem|mem|lock|sched) ]]; then
subcmds=$($cmd $prev --list-cmds)
__perfcomp_colon "$subcmds" "$cur"
# List long option names
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 5c11ecad02a9..ebdad3376c67 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -15,6 +15,9 @@
#ifndef __NR_futex
# define __NR_futex 240
#endif
+#ifndef __NR_gettid
+# define __NR_gettid 224
+#endif
#endif
#if defined(__x86_64__)
@@ -29,6 +32,9 @@
#ifndef __NR_futex
# define __NR_futex 202
#endif
+#ifndef __NR_gettid
+# define __NR_gettid 186
+#endif
#endif
#ifdef __powerpc__
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index b11bf8a08430..0d5afaf72944 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -124,6 +124,18 @@ static struct test {
#endif
#endif
{
+ .desc = "Test filtering hist entries",
+ .func = test__hists_filter,
+ },
+ {
+ .desc = "Test mmap thread lookup",
+ .func = test__mmap_thread_lookup,
+ },
+ {
+ .desc = "Test thread mg sharing",
+ .func = test__thread_mg_share,
+ },
+ {
.func = NULL,
},
};
diff --git a/tools/perf/tests/hists_common.c b/tools/perf/tests/hists_common.c
new file mode 100644
index 000000000000..44655b395bb9
--- /dev/null
+++ b/tools/perf/tests/hists_common.c
@@ -0,0 +1,148 @@
+#include "perf.h"
+#include "util/debug.h"
+#include "util/symbol.h"
+#include "util/sort.h"
+#include "util/evsel.h"
+#include "util/evlist.h"
+#include "util/machine.h"
+#include "util/thread.h"
+#include "tests/hists_common.h"
+
+static struct {
+ u32 pid;
+ const char *comm;
+} fake_threads[] = {
+ { 100, "perf" },
+ { 200, "perf" },
+ { 300, "bash" },
+};
+
+static struct {
+ u32 pid;
+ u64 start;
+ const char *filename;
+} fake_mmap_info[] = {
+ { 100, 0x40000, "perf" },
+ { 100, 0x50000, "libc" },
+ { 100, 0xf0000, "[kernel]" },
+ { 200, 0x40000, "perf" },
+ { 200, 0x50000, "libc" },
+ { 200, 0xf0000, "[kernel]" },
+ { 300, 0x40000, "bash" },
+ { 300, 0x50000, "libc" },
+ { 300, 0xf0000, "[kernel]" },
+};
+
+struct fake_sym {
+ u64 start;
+ u64 length;
+ const char *name;
+};
+
+static struct fake_sym perf_syms[] = {
+ { 700, 100, "main" },
+ { 800, 100, "run_command" },
+ { 900, 100, "cmd_record" },
+};
+
+static struct fake_sym bash_syms[] = {
+ { 700, 100, "main" },
+ { 800, 100, "xmalloc" },
+ { 900, 100, "xfree" },
+};
+
+static struct fake_sym libc_syms[] = {
+ { 700, 100, "malloc" },
+ { 800, 100, "free" },
+ { 900, 100, "realloc" },
+};
+
+static struct fake_sym kernel_syms[] = {
+ { 700, 100, "schedule" },
+ { 800, 100, "page_fault" },
+ { 900, 100, "sys_perf_event_open" },
+};
+
+static struct {
+ const char *dso_name;
+ struct fake_sym *syms;
+ size_t nr_syms;
+} fake_symbols[] = {
+ { "perf", perf_syms, ARRAY_SIZE(perf_syms) },
+ { "bash", bash_syms, ARRAY_SIZE(bash_syms) },
+ { "libc", libc_syms, ARRAY_SIZE(libc_syms) },
+ { "[kernel]", kernel_syms, ARRAY_SIZE(kernel_syms) },
+};
+
+struct machine *setup_fake_machine(struct machines *machines)
+{
+ struct machine *machine = machines__find(machines, HOST_KERNEL_ID);
+ size_t i;
+
+ if (machine == NULL) {
+ pr_debug("Not enough memory for machine setup\n");
+ return NULL;
+ }
+
+ for (i = 0; i < ARRAY_SIZE(fake_threads); i++) {
+ struct thread *thread;
+
+ thread = machine__findnew_thread(machine, fake_threads[i].pid,
+ fake_threads[i].pid);
+ if (thread == NULL)
+ goto out;
+
+ thread__set_comm(thread, fake_threads[i].comm, 0);
+ }
+
+ for (i = 0; i < ARRAY_SIZE(fake_mmap_info); i++) {
+ union perf_event fake_mmap_event = {
+ .mmap = {
+ .header = { .misc = PERF_RECORD_MISC_USER, },
+ .pid = fake_mmap_info[i].pid,
+ .tid = fake_mmap_info[i].pid,
+ .start = fake_mmap_info[i].start,
+ .len = 0x1000ULL,
+ .pgoff = 0ULL,
+ },
+ };
+
+ strcpy(fake_mmap_event.mmap.filename,
+ fake_mmap_info[i].filename);
+
+ machine__process_mmap_event(machine, &fake_mmap_event, NULL);
+ }
+
+ for (i = 0; i < ARRAY_SIZE(fake_symbols); i++) {
+ size_t k;
+ struct dso *dso;
+
+ dso = __dsos__findnew(&machine->user_dsos,
+ fake_symbols[i].dso_name);
+ if (dso == NULL)
+ goto out;
+
+ /* emulate dso__load() */
+ dso__set_loaded(dso, MAP__FUNCTION);
+
+ for (k = 0; k < fake_symbols[i].nr_syms; k++) {
+ struct symbol *sym;
+ struct fake_sym *fsym = &fake_symbols[i].syms[k];
+
+ sym = symbol__new(fsym->start, fsym->length,
+ STB_GLOBAL, fsym->name);
+ if (sym == NULL)
+ goto out;
+
+ symbols__insert(&dso->symbols[MAP__FUNCTION], sym);
+ }
+ }
+
+ return machine;
+
+out:
+ pr_debug("Not enough memory for machine setup\n");
+ machine__delete_threads(machine);
+ machine__delete(machine);
+ return NULL;
+}
diff --git a/tools/perf/tests/hists_common.h b/tools/perf/tests/hists_common.h
new file mode 100644
index 000000000000..2528b8fc105a
--- /dev/null
+++ b/tools/perf/tests/hists_common.h
@@ -0,0 +1,44 @@
+#ifndef __PERF_TESTS__HISTS_COMMON_H__
+#define __PERF_TESTS__HISTS_COMMON_H__
+
+struct machine;
+struct machines;
+
+/*
+ * The setup_fake_machine() provides a test environment which consists
+ * of 3 processes that have 3 mappings and in turn, have 3 symbols
+ * respectively. See below table:
+ *
+ * Command: Pid Shared Object Symbol
+ * ............. ............. ...................
+ * perf: 100 perf main
+ * perf: 100 perf run_command
+ * perf: 100 perf comd_record
+ * perf: 100 libc malloc
+ * perf: 100 libc free
+ * perf: 100 libc realloc
+ * perf: 100 [kernel] schedule
+ * perf: 100 [kernel] page_fault
+ * perf: 100 [kernel] sys_perf_event_open
+ * perf: 200 perf main
+ * perf: 200 perf run_command
+ * perf: 200 perf comd_record
+ * perf: 200 libc malloc
+ * perf: 200 libc free
+ * perf: 200 libc realloc
+ * perf: 200 [kernel] schedule
+ * perf: 200 [kernel] page_fault
+ * perf: 200 [kernel] sys_perf_event_open
+ * bash: 300 bash main
+ * bash: 300 bash xmalloc
+ * bash: 300 bash xfree
+ * bash: 300 libc malloc
+ * bash: 300 libc free
+ * bash: 300 libc realloc
+ * bash: 300 [kernel] schedule
+ * bash: 300 [kernel] page_fault
+ * bash: 300 [kernel] sys_perf_event_open
+ */
+struct machine *setup_fake_machine(struct machines *machines);
+
+#endif /* __PERF_TESTS__HISTS_COMMON_H__ */
diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c
new file mode 100644
index 000000000000..23dc2f4d12c3
--- /dev/null
+++ b/tools/perf/tests/hists_filter.c
@@ -0,0 +1,315 @@
+#include "perf.h"
+#include "util/debug.h"
+#include "util/symbol.h"
+#include "util/sort.h"
+#include "util/evsel.h"
+#include "util/evlist.h"
+#include "util/machine.h"
+#include "util/thread.h"
+#include "util/parse-events.h"
+#include "tests/tests.h"
+#include "tests/hists_common.h"
+
+struct sample {
+ u32 pid;
+ u64 ip;
+ struct thread *thread;
+ struct map *map;
+ struct symbol *sym;
+};
+
+/* For the numbers, see hists_common.c */
+static struct sample fake_samples[] = {
+ /* perf [kernel] schedule() */
+ { .pid = 100, .ip = 0xf0000 + 700, },
+ /* perf [perf] main() */
+ { .pid = 100, .ip = 0x40000 + 700, },
+ /* perf [libc] malloc() */
+ { .pid = 100, .ip = 0x50000 + 700, },
+ /* perf [perf] main() */
+ { .pid = 200, .ip = 0x40000 + 700, }, /* will be merged */
+ /* perf [perf] cmd_record() */
+ { .pid = 200, .ip = 0x40000 + 900, },
+ /* perf [kernel] page_fault() */
+ { .pid = 200, .ip = 0xf0000 + 800, },
+ /* bash [bash] main() */
+ { .pid = 300, .ip = 0x40000 + 700, },
+ /* bash [bash] xmalloc() */
+ { .pid = 300, .ip = 0x40000 + 800, },
+ /* bash [libc] malloc() */
+ { .pid = 300, .ip = 0x50000 + 700, },
+ /* bash [kernel] page_fault() */
+ { .pid = 300, .ip = 0xf0000 + 800, },
+};
+
+static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
+{
+ struct perf_evsel *evsel;
+ struct addr_location al;
+ struct hist_entry *he;
+ struct perf_sample sample = { .cpu = 0, };
+ size_t i;
+
+ /*
+ * each evsel will have 10 samples but the 4th sample
+ * (perf [perf] main) will be collapsed to an existing entry
+ * so total 9 entries will be in the tree.
+ */
+ evlist__for_each(evlist, evsel) {
+ for (i = 0; i < ARRAY_SIZE(fake_samples); i++) {
+ const union perf_event event = {
+ .header = {
+ .misc = PERF_RECORD_MISC_USER,
+ },
+ };
+
+ /* make sure it has no filter at first */
+ evsel->hists.thread_filter = NULL;
+ evsel->hists.dso_filter = NULL;
+ evsel->hists.symbol_filter_str = NULL;
+
+ sample.pid = fake_samples[i].pid;
+ sample.ip = fake_samples[i].ip;
+
+ if (perf_event__preprocess_sample(&event, machine, &al,
+ &sample) < 0)
+ goto out;
+
+ he = __hists__add_entry(&evsel->hists, &al, NULL,
+ NULL, NULL, 100, 1, 0);
+ if (he == NULL)
+ goto out;
+
+ fake_samples[i].thread = al.thread;
+ fake_samples[i].map = al.map;
+ fake_samples[i].sym = al.sym;
+
+ hists__inc_nr_events(he->hists, PERF_RECORD_SAMPLE);
+ if (!he->filtered)
+ he->hists->stats.nr_non_filtered_samples++;
+ }
+ }
+
+ return 0;
+
+out:
+ pr_debug("Not enough memory for adding a hist entry\n");
+ return TEST_FAIL;
+}
+
+static void print_hists(struct hists *hists)
+{
+ int i = 0;
+ struct rb_root *root;
+ struct rb_node *node;
+
+ root = &hists->entries;
+
+ pr_info("----- %s --------\n", __func__);
+ node = rb_first(root);
+ while (node) {
+ struct hist_entry *he;
+
+ he = rb_entry(node, struct hist_entry, rb_node);
+
+ if (!he->filtered) {
+ pr_info("%2d: entry: %-8s [%-8s] %20s: period = %"PRIu64"\n",
+ i, thread__comm_str(he->thread),
+ he->ms.map->dso->short_name,
+ he->ms.sym->name, he->stat.period);
+ }
+
+ i++;
+ node = rb_next(node);
+ }
+}
+
+int test__hists_filter(void)
+{
+ int err = TEST_FAIL;
+ struct machines machines;
+ struct machine *machine;
+ struct perf_evsel *evsel;
+ struct perf_evlist *evlist = perf_evlist__new();
+
+ TEST_ASSERT_VAL("No memory", evlist);
+
+ err = parse_events(evlist, "cpu-clock");
+ if (err)
+ goto out;
+ err = parse_events(evlist, "task-clock");
+ if (err)
+ goto out;
+
+ /* default sort order (comm,dso,sym) will be used */
+ if (setup_sorting() < 0)
+ goto out;
+
+ machines__init(&machines);
+
+ /* setup threads/dso/map/symbols also */
+ machine = setup_fake_machine(&machines);
+ if (!machine)
+ goto out;
+
+ if (verbose > 1)
+ machine__fprintf(machine, stderr);
+
+ /* process sample events */
+ err = add_hist_entries(evlist, machine);
+ if (err < 0)
+ goto out;
+
+ evlist__for_each(evlist, evsel) {
+ struct hists *hists = &evsel->hists;
+
+ hists__collapse_resort(hists, NULL);
+ hists__output_resort(hists);
+
+ if (verbose > 2) {
+ pr_info("Normal histogram\n");
+ print_hists(hists);
+ }
+
+ TEST_ASSERT_VAL("Invalid nr samples",
+ hists->stats.nr_events[PERF_RECORD_SAMPLE] == 10);
+ TEST_ASSERT_VAL("Invalid nr hist entries",
+ hists->nr_entries == 9);
+ TEST_ASSERT_VAL("Invalid total period",
+ hists->stats.total_period == 1000);
+ TEST_ASSERT_VAL("Unmatched nr samples",
+ hists->stats.nr_events[PERF_RECORD_SAMPLE] ==
+ hists->stats.nr_non_filtered_samples);
+ TEST_ASSERT_VAL("Unmatched nr hist entries",
+ hists->nr_entries == hists->nr_non_filtered_entries);
+ TEST_ASSERT_VAL("Unmatched total period",
+ hists->stats.total_period ==
+ hists->stats.total_non_filtered_period);
+
+ /* now applying thread filter for 'bash' */
+ evsel->hists.thread_filter = fake_samples[9].thread;
+ hists__filter_by_thread(hists);
+
+ if (verbose > 2) {
+ pr_info("Histogram for thread filter\n");
+ print_hists(hists);
+ }
+
+ /* normal stats should be invariant */
+ TEST_ASSERT_VAL("Invalid nr samples",
+ hists->stats.nr_events[PERF_RECORD_SAMPLE] == 10);
+ TEST_ASSERT_VAL("Invalid nr hist entries",
+ hists->nr_entries == 9);
+ TEST_ASSERT_VAL("Invalid total period",
+ hists->stats.total_period == 1000);
+
+ /* but filter stats are changed */
+ TEST_ASSERT_VAL("Unmatched nr samples for thread filter",
+ hists->stats.nr_non_filtered_samples == 4);
+ TEST_ASSERT_VAL("Unmatched nr hist entries for thread filter",
+ hists->nr_non_filtered_entries == 4);
+ TEST_ASSERT_VAL("Unmatched total period for thread filter",
+ hists->stats.total_non_filtered_period == 400);
+
+ /* remove thread filter first */
+ evsel->hists.thread_filter = NULL;
+ hists__filter_by_thread(hists);
+
+ /* now applying dso filter for 'kernel' */
+ evsel->hists.dso_filter = fake_samples[0].map->dso;
+ hists__filter_by_dso(hists);
+
+ if (verbose > 2) {
+ pr_info("Histogram for dso filter\n");
+ print_hists(hists);
+ }
+
+ /* normal stats should be invariant */
+ TEST_ASSERT_VAL("Invalid nr samples",
+ hists->stats.nr_events[PERF_RECORD_SAMPLE] == 10);
+ TEST_ASSERT_VAL("Invalid nr hist entries",
+ hists->nr_entries == 9);
+ TEST_ASSERT_VAL("Invalid total period",
+ hists->stats.total_period == 1000);
+
+ /* but filter stats are changed */
+ TEST_ASSERT_VAL("Unmatched nr samples for dso filter",
+ hists->stats.nr_non_filtered_samples == 3);
+ TEST_ASSERT_VAL("Unmatched nr hist entries for dso filter",
+ hists->nr_non_filtered_entries == 3);
+ TEST_ASSERT_VAL("Unmatched total period for dso filter",
+ hists->stats.total_non_filtered_period == 300);
+
+ /* remove dso filter first */
+ evsel->hists.dso_filter = NULL;
+ hists__filter_by_dso(hists);
+
+ /*
+ * now applying symbol filter for 'main'. Also note that
+ * there's 3 samples that have 'main' symbol but the 4th
+ * entry of fake_samples was collapsed already so it won't
+ * be counted as a separate entry but the sample count and
+ * total period will be remained.
+ */
+ evsel->hists.symbol_filter_str = "main";
+ hists__filter_by_symbol(hists);
+
+ if (verbose > 2) {
+ pr_info("Histogram for symbol filter\n");
+ print_hists(hists);
+ }
+
+ /* normal stats should be invariant */
+ TEST_ASSERT_VAL("Invalid nr samples",
+ hists->stats.nr_events[PERF_RECORD_SAMPLE] == 10);
+ TEST_ASSERT_VAL("Invalid nr hist entries",
+ hists->nr_entries == 9);
+ TEST_ASSERT_VAL("Invalid total period",
+ hists->stats.total_period == 1000);
+
+ /* but filter stats are changed */
+ TEST_ASSERT_VAL("Unmatched nr samples for symbol filter",
+ hists->stats.nr_non_filtered_samples == 3);
+ TEST_ASSERT_VAL("Unmatched nr hist entries for symbol filter",
+ hists->nr_non_filtered_entries == 2);
+ TEST_ASSERT_VAL("Unmatched total period for symbol filter",
+ hists->stats.total_non_filtered_period == 300);
+
+ /* now applying all filters at once. */
+ evsel->hists.thread_filter = fake_samples[1].thread;
+ evsel->hists.dso_filter = fake_samples[1].map->dso;
+ hists__filter_by_thread(hists);
+ hists__filter_by_dso(hists);
+
+ if (verbose > 2) {
+ pr_info("Histogram for all filters\n");
+ print_hists(hists);
+ }
+
+ /* normal stats should be invariant */
+ TEST_ASSERT_VAL("Invalid nr samples",
+ hists->stats.nr_events[PERF_RECORD_SAMPLE] == 10);
+ TEST_ASSERT_VAL("Invalid nr hist entries",
+ hists->nr_entries == 9);
+ TEST_ASSERT_VAL("Invalid total period",
+ hists->stats.total_period == 1000);
+
+ /* but filter stats are changed */
+ TEST_ASSERT_VAL("Unmatched nr samples for all filter",
+ hists->stats.nr_non_filtered_samples == 2);
+ TEST_ASSERT_VAL("Unmatched nr hist entries for all filter",
+ hists->nr_non_filtered_entries == 1);
+ TEST_ASSERT_VAL("Unmatched total period for all filter",
+ hists->stats.total_non_filtered_period == 200);
+ }
+
+
+ err = TEST_OK;
+
+out:
+ /* tear down everything */
+ perf_evlist__delete(evlist);
+ machines__exit(&machines);
+
+ return err;
+}
diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
index 7ccbc7b6ae77..e42d6790811a 100644
--- a/tools/perf/tests/hists_link.c
+++ b/tools/perf/tests/hists_link.c
@@ -8,145 +8,7 @@
#include "machine.h"
#include "thread.h"
#include "parse-events.h"
-
-static struct {
- u32 pid;
- const char *comm;
-} fake_threads[] = {
- { 100, "perf" },
- { 200, "perf" },
- { 300, "bash" },
-};
-
-static struct {
- u32 pid;
- u64 start;
- const char *filename;
-} fake_mmap_info[] = {
- { 100, 0x40000, "perf" },
- { 100, 0x50000, "libc" },
- { 100, 0xf0000, "[kernel]" },
- { 200, 0x40000, "perf" },
- { 200, 0x50000, "libc" },
- { 200, 0xf0000, "[kernel]" },
- { 300, 0x40000, "bash" },
- { 300, 0x50000, "libc" },
- { 300, 0xf0000, "[kernel]" },
-};
-
-struct fake_sym {
- u64 start;
- u64 length;
- const char *name;
-};
-
-static struct fake_sym perf_syms[] = {
- { 700, 100, "main" },
- { 800, 100, "run_command" },
- { 900, 100, "cmd_record" },
-};
-
-static struct fake_sym bash_syms[] = {
- { 700, 100, "main" },
- { 800, 100, "xmalloc" },
- { 900, 100, "xfree" },
-};
-
-static struct fake_sym libc_syms[] = {
- { 700, 100, "malloc" },
- { 800, 100, "free" },
- { 900, 100, "realloc" },
-};
-
-static struct fake_sym kernel_syms[] = {
- { 700, 100, "schedule" },
- { 800, 100, "page_fault" },
- { 900, 100, "sys_perf_event_open" },
-};
-
-static struct {
- const char *dso_name;
- struct fake_sym *syms;
- size_t nr_syms;
-} fake_symbols[] = {
- { "perf", perf_syms, ARRAY_SIZE(perf_syms) },
- { "bash", bash_syms, ARRAY_SIZE(bash_syms) },
- { "libc", libc_syms, ARRAY_SIZE(libc_syms) },
- { "[kernel]", kernel_syms, ARRAY_SIZE(kernel_syms) },
-};
-
-static struct machine *setup_fake_machine(struct machines *machines)
-{
- struct machine *machine = machines__find(machines, HOST_KERNEL_ID);
- size_t i;
-
- if (machine == NULL) {
- pr_debug("Not enough memory for machine setup\n");
- return NULL;
- }
-
- for (i = 0; i < ARRAY_SIZE(fake_threads); i++) {
- struct thread *thread;
-
- thread = machine__findnew_thread(machine, fake_threads[i].pid,
- fake_threads[i].pid);
- if (thread == NULL)
- goto out;
-
- thread__set_comm(thread, fake_threads[i].comm, 0);
- }
-
- for (i = 0; i < ARRAY_SIZE(fake_mmap_info); i++) {
- union perf_event fake_mmap_event = {
- .mmap = {
- .header = { .misc = PERF_RECORD_MISC_USER, },
- .pid = fake_mmap_info[i].pid,
- .tid = fake_mmap_info[i].pid,
- .start = fake_mmap_info[i].start,
- .len = 0x1000ULL,
- .pgoff = 0ULL,
- },
- };
-
- strcpy(fake_mmap_event.mmap.filename,
- fake_mmap_info[i].filename);
-
- machine__process_mmap_event(machine, &fake_mmap_event, NULL);
- }
-
- for (i = 0; i < ARRAY_SIZE(fake_symbols); i++) {
- size_t k;
- struct dso *dso;
-
- dso = __dsos__findnew(&machine->user_dsos,
- fake_symbols[i].dso_name);
- if (dso == NULL)
- goto out;
-
- /* emulate dso__load() */
- dso__set_loaded(dso, MAP__FUNCTION);
-
- for (k = 0; k < fake_symbols[i].nr_syms; k++) {
- struct symbol *sym;
- struct fake_sym *fsym = &fake_symbols[i].syms[k];
-
- sym = symbol__new(fsym->start, fsym->length,
- STB_GLOBAL, fsym->name);
- if (sym == NULL)
- goto out;
-
- symbols__insert(&dso->symbols[MAP__FUNCTION], sym);
- }
- }
-
- return machine;
-
-out:
- pr_debug("Not enough memory for machine setup\n");
- machine__delete_threads(machine);
- machine__delete(machine);
- return NULL;
-}
+#include "hists_common.h"
struct sample {
u32 pid;
@@ -156,6 +18,7 @@ struct sample {
struct symbol *sym;
};
+/* For the numbers, see hists_common.c */
static struct sample fake_common_samples[] = {
/* perf [kernel] schedule() */
{ .pid = 100, .ip = 0xf0000 + 700, },
diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c
new file mode 100644
index 000000000000..4a456fef66ca
--- /dev/null
+++ b/tools/perf/tests/mmap-thread-lookup.c
@@ -0,0 +1,233 @@
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <sys/mman.h>
+#include <pthread.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include "debug.h"
+#include "tests.h"
+#include "machine.h"
+#include "thread_map.h"
+#include "symbol.h"
+#include "thread.h"
+
+#define THREADS 4
+
+static int go_away;
+
+struct thread_data {
+ pthread_t pt;
+ pid_t tid;
+ void *map;
+ int ready[2];
+};
+
+static struct thread_data threads[THREADS];
+
+static int thread_init(struct thread_data *td)
+{
+ void *map;
+
+ map = mmap(NULL, page_size,
+ PROT_READ|PROT_WRITE|PROT_EXEC,
+ MAP_SHARED|MAP_ANONYMOUS, -1, 0);
+
+ if (map == MAP_FAILED) {
+ perror("mmap failed");
+ return -1;
+ }
+
+ td->map = map;
+ td->tid = syscall(SYS_gettid);
+
+ pr_debug("tid = %d, map = %p\n", td->tid, map);
+ return 0;
+}
+
+static void *thread_fn(void *arg)
+{
+ struct thread_data *td = arg;
+ ssize_t ret;
+ int go;
+
+ if (thread_init(td))
+ return NULL;
+
+ /* Signal thread_create thread is initialized. */
+ ret = write(td->ready[1], &go, sizeof(int));
+ if (ret != sizeof(int)) {
+ pr_err("failed to notify\n");
+ return NULL;
+ }
+
+ while (!go_away) {
+ /* Waiting for main thread to kill us. */
+ usleep(100);
+ }
+
+ munmap(td->map, page_size);
+ return NULL;
+}
+
+static int thread_create(int i)
+{
+ struct thread_data *td = &threads[i];
+ int err, go;
+
+ if (pipe(td->ready))
+ return -1;
+
+ err = pthread_create(&td->pt, NULL, thread_fn, td);
+ if (!err) {
+ /* Wait for thread initialization. */
+ ssize_t ret = read(td->ready[0], &go, sizeof(int));
+ err = ret != sizeof(int);
+ }
+
+ close(td->ready[0]);
+ close(td->ready[1]);
+ return err;
+}
+
+static int threads_create(void)
+{
+ struct thread_data *td0 = &threads[0];
+ int i, err = 0;
+
+ go_away = 0;
+
+ /* 0 is main thread */
+ if (thread_init(td0))
+ return -1;
+
+ for (i = 1; !err && i < THREADS; i++)
+ err = thread_create(i);
+
+ return err;
+}
+
+static int threads_destroy(void)
+{
+ struct thread_data *td0 = &threads[0];
+ int i, err = 0;
+
+ /* cleanup the main thread */
+ munmap(td0->map, page_size);
+
+ go_away = 1;
+
+ for (i = 1; !err && i < THREADS; i++)
+ err = pthread_join(threads[i].pt, NULL);
+
+ return err;
+}
+
+typedef int (*synth_cb)(struct machine *machine);
+
+static int synth_all(struct machine *machine)
+{
+ return perf_event__synthesize_threads(NULL,
+ perf_event__process,
+ machine, 0);
+}
+
+static int synth_process(struct machine *machine)
+{
+ struct thread_map *map;
+ int err;
+
+ map = thread_map__new_by_pid(getpid());
+
+ err = perf_event__synthesize_thread_map(NULL, map,
+ perf_event__process,
+ machine, 0);
+
+ thread_map__delete(map);
+ return err;
+}
+
+static int mmap_events(synth_cb synth)
+{
+ struct machines machines;
+ struct machine *machine;
+ int err, i;
+
+ /*
+ * The threads_create will not return before all threads
+ * are spawned and all created memory map.
+ *
+ * They will loop until threads_destroy is called, so we
+ * can safely run synthesizing function.
+ */
+ TEST_ASSERT_VAL("failed to create threads", !threads_create());
+
+ machines__init(&machines);
+ machine = &machines.host;
+
+ dump_trace = verbose > 1 ? 1 : 0;
+
+ err = synth(machine);
+
+ dump_trace = 0;
+
+ TEST_ASSERT_VAL("failed to destroy threads", !threads_destroy());
+ TEST_ASSERT_VAL("failed to synthesize maps", !err);
+
+ /*
+ * All data is synthesized, try to find map for each
+ * thread object.
+ */
+ for (i = 0; i < THREADS; i++) {
+ struct thread_data *td = &threads[i];
+ struct addr_location al;
+ struct thread *thread;
+
+ thread = machine__findnew_thread(machine, getpid(), td->tid);
+
+ pr_debug("looking for map %p\n", td->map);
+
+ thread__find_addr_map(thread, machine,
+ PERF_RECORD_MISC_USER, MAP__FUNCTION,
+ (unsigned long) (td->map + 1), &al);
+
+ if (!al.map) {
+ pr_debug("failed, couldn't find map\n");
+ err = -1;
+ break;
+ }
+
+ pr_debug("map %p, addr %" PRIx64 "\n", al.map, al.map->start);
+ }
+
+ machine__delete_threads(machine);
+ machines__exit(&machines);
+ return err;
+}
+
+/*
+ * This test creates 'THREADS' number of threads (including
+ * main thread) and each thread creates memory map.
+ *
+ * When threads are created, we synthesize them with both
+ * (separate tests):
+ * perf_event__synthesize_thread_map (process based)
+ * perf_event__synthesize_threads (global)
+ *
+ * We test we can find all memory maps via:
+ * thread__find_addr_map
+ *
+ * by using all thread objects.
+ */
+int test__mmap_thread_lookup(void)
+{
+ /* perf_event__synthesize_threads synthesize */
+ TEST_ASSERT_VAL("failed with sythesizing all",
+ !mmap_events(synth_all));
+
+ /* perf_event__synthesize_thread_map synthesize */
+ TEST_ASSERT_VAL("failed with sythesizing process",
+ !mmap_events(synth_process));
+
+ return 0;
+}
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index a24795ca002d..a9d7cb019f9e 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -41,6 +41,9 @@ int test__sample_parsing(void);
int test__keep_tracking(void);
int test__parse_no_sample_id_all(void);
int test__dwarf_unwind(void);
+int test__hists_filter(void);
+int test__mmap_thread_lookup(void);
+int test__thread_mg_share(void);
#if defined(__x86_64__) || defined(__i386__)
#ifdef HAVE_DWARF_UNWIND_SUPPORT
diff --git a/tools/perf/tests/thread-mg-share.c b/tools/perf/tests/thread-mg-share.c
new file mode 100644
index 000000000000..2b2e0dbe114f
--- /dev/null
+++ b/tools/perf/tests/thread-mg-share.c
@@ -0,0 +1,90 @@
+#include "tests.h"
+#include "machine.h"
+#include "thread.h"
+#include "map.h"
+
+int test__thread_mg_share(void)
+{
+ struct machines machines;
+ struct machine *machine;
+
+ /* thread group */
+ struct thread *leader;
+ struct thread *t1, *t2, *t3;
+ struct map_groups *mg;
+
+ /* other process */
+ struct thread *other, *other_leader;
+ struct map_groups *other_mg;
+
+ /*
+ * This test create 2 processes abstractions (struct thread)
+ * with several threads and checks they properly share and
+ * maintain map groups info (struct map_groups).
+ *
+ * thread group (pid: 0, tids: 0, 1, 2, 3)
+ * other group (pid: 4, tids: 4, 5)
+ */
+
+ machines__init(&machines);
+ machine = &machines.host;
+
+ /* create process with 4 threads */
+ leader = machine__findnew_thread(machine, 0, 0);
+ t1 = machine__findnew_thread(machine, 0, 1);
+ t2 = machine__findnew_thread(machine, 0, 2);
+ t3 = machine__findnew_thread(machine, 0, 3);
+
+ /* and create 1 separated process, without thread leader */
+ other = machine__findnew_thread(machine, 4, 5);
+
+ TEST_ASSERT_VAL("failed to create threads",
+ leader && t1 && t2 && t3 && other);
+
+ mg = leader->mg;
+ TEST_ASSERT_VAL("wrong refcnt", mg->refcnt == 4);
+
+ /* test the map groups pointer is shared */
+ TEST_ASSERT_VAL("map groups don't match", mg == t1->mg);
+ TEST_ASSERT_VAL("map groups don't match", mg == t2->mg);
+ TEST_ASSERT_VAL("map groups don't match", mg == t3->mg);
+
+ /*
+ * Verify the other leader was created by previous call.
+ * It should have shared map groups with no change in
+ * refcnt.
+ */
+ other_leader = machine__find_thread(machine, 4, 4);
+ TEST_ASSERT_VAL("failed to find other leader", other_leader);
+
+ other_mg = other->mg;
+ TEST_ASSERT_VAL("wrong refcnt", other_mg->refcnt == 2);
+
+ TEST_ASSERT_VAL("map groups don't match", other_mg == other_leader->mg);
+
+ /* release thread group */
+ thread__delete(leader);
+ TEST_ASSERT_VAL("wrong refcnt", mg->refcnt == 3);
+
+ thread__delete(t1);
+ TEST_ASSERT_VAL("wrong refcnt", mg->refcnt == 2);
+
+ thread__delete(t2);
+ TEST_ASSERT_VAL("wrong refcnt", mg->refcnt == 1);
+
+ thread__delete(t3);
+
+ /* release other group */
+ thread__delete(other_leader);
+ TEST_ASSERT_VAL("wrong refcnt", other_mg->refcnt == 1);
+
+ thread__delete(other);
+
+ /*
+ * Cannot call machine__delete_threads(machine) now,
+ * because we've already released all the threads.
+ */
+
+ machines__exit(&machines);
+ return 0;
+}
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 7ec871af3f6f..b0861e3e50a5 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -26,13 +26,36 @@ struct hist_browser {
int print_seq;
bool show_dso;
float min_pcnt;
- u64 nr_pcnt_entries;
+ u64 nr_non_filtered_entries;
+ u64 nr_callchain_rows;
};
extern void hist_browser__init_hpp(void);
static int hists__browser_title(struct hists *hists, char *bf, size_t size,
const char *ev_name);
+static void hist_browser__update_nr_entries(struct hist_browser *hb);
+
+static struct rb_node *hists__filter_entries(struct rb_node *nd,
+ struct hists *hists,
+ float min_pcnt);
+
+static bool hist_browser__has_filter(struct hist_browser *hb)
+{
+ return hists__has_filter(hb->hists) || hb->min_pcnt;
+}
+
+static u32 hist_browser__nr_entries(struct hist_browser *hb)
+{
+ u32 nr_entries;
+
+ if (hist_browser__has_filter(hb))
+ nr_entries = hb->nr_non_filtered_entries;
+ else
+ nr_entries = hb->hists->nr_entries;
+
+ return nr_entries + hb->nr_callchain_rows;
+}
static void hist_browser__refresh_dimensions(struct hist_browser *browser)
{
@@ -43,7 +66,14 @@ static void hist_browser__refresh_dimensions(struct hist_browser *browser)
static void hist_browser__reset(struct hist_browser *browser)
{
- browser->b.nr_entries = browser->hists->nr_entries;
+ /*
+ * The hists__remove_entry_filter() already folds non-filtered
+ * entries so we can assume it has 0 callchain rows.
+ */
+ browser->nr_callchain_rows = 0;
+
+ hist_browser__update_nr_entries(browser);
+ browser->b.nr_entries = hist_browser__nr_entries(browser);
hist_browser__refresh_dimensions(browser);
ui_browser__reset_index(&browser->b);
}
@@ -198,14 +228,16 @@ static bool hist_browser__toggle_fold(struct hist_browser *browser)
struct hist_entry *he = browser->he_selection;
hist_entry__init_have_children(he);
- browser->hists->nr_entries -= he->nr_rows;
+ browser->b.nr_entries -= he->nr_rows;
+ browser->nr_callchain_rows -= he->nr_rows;
if (he->ms.unfolded)
he->nr_rows = callchain__count_rows(&he->sorted_chain);
else
he->nr_rows = 0;
- browser->hists->nr_entries += he->nr_rows;
- browser->b.nr_entries = browser->hists->nr_entries;
+
+ browser->b.nr_entries += he->nr_rows;
+ browser->nr_callchain_rows += he->nr_rows;
return true;
}
@@ -280,23 +312,27 @@ static void hist_entry__set_folding(struct hist_entry *he, bool unfold)
he->nr_rows = 0;
}
-static void hists__set_folding(struct hists *hists, bool unfold)
+static void
+__hist_browser__set_folding(struct hist_browser *browser, bool unfold)
{
struct rb_node *nd;
+ struct hists *hists = browser->hists;
- hists->nr_entries = 0;
-
- for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
+ for (nd = rb_first(&hists->entries);
+ (nd = hists__filter_entries(nd, hists, browser->min_pcnt)) != NULL;
+ nd = rb_next(nd)) {
struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node);
hist_entry__set_folding(he, unfold);
- hists->nr_entries += 1 + he->nr_rows;
+ browser->nr_callchain_rows += he->nr_rows;
}
}
static void hist_browser__set_folding(struct hist_browser *browser, bool unfold)
{
- hists__set_folding(browser->hists, unfold);
- browser->b.nr_entries = browser->hists->nr_entries;
+ browser->nr_callchain_rows = 0;
+ __hist_browser__set_folding(browser, unfold);
+
+ browser->b.nr_entries = hist_browser__nr_entries(browser);
/* Go to the start, we may be way after valid entries after a collapse */
ui_browser__reset_index(&browser->b);
}
@@ -310,8 +346,6 @@ static void ui_browser__warn_lost_events(struct ui_browser *browser)
"Or reduce the sampling frequency.");
}
-static void hist_browser__update_pcnt_entries(struct hist_browser *hb);
-
static int hist_browser__run(struct hist_browser *browser, const char *ev_name,
struct hist_browser_timer *hbt)
{
@@ -320,9 +354,7 @@ static int hist_browser__run(struct hist_browser *browser, const char *ev_name,
int delay_secs = hbt ? hbt->refresh : 0;
browser->b.entries = &browser->hists->entries;
- browser->b.nr_entries = browser->hists->nr_entries;
- if (browser->min_pcnt)
- browser->b.nr_entries = browser->nr_pcnt_entries;
+ browser->b.nr_entries = hist_browser__nr_entries(browser);
hist_browser__refresh_dimensions(browser);
hists__browser_title(browser->hists, title, sizeof(title), ev_name);
@@ -339,13 +371,10 @@ static int hist_browser__run(struct hist_browser *browser, const char *ev_name,
u64 nr_entries;
hbt->timer(hbt->arg);
- if (browser->min_pcnt) {
- hist_browser__update_pcnt_entries(browser);
- nr_entries = browser->nr_pcnt_entries;
- } else {
- nr_entries = browser->hists->nr_entries;
- }
+ if (hist_browser__has_filter(browser))
+ hist_browser__update_nr_entries(browser);
+ nr_entries = hist_browser__nr_entries(browser);
ui_browser__update_nr_entries(&browser->b, nr_entries);
if (browser->hists->stats.nr_lost_warned !=
@@ -769,12 +798,15 @@ static unsigned int hist_browser__refresh(struct ui_browser *browser)
for (nd = browser->top; nd; nd = rb_next(nd)) {
struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
- float percent = h->stat.period * 100.0 /
- hb->hists->stats.total_period;
+ u64 total = hists__total_period(h->hists);
+ float percent = 0.0;
if (h->filtered)
continue;
+ if (total)
+ percent = h->stat.period * 100.0 / total;
+
if (percent < hb->min_pcnt)
continue;
@@ -792,8 +824,11 @@ static struct rb_node *hists__filter_entries(struct rb_node *nd,
{
while (nd != NULL) {
struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
- float percent = h->stat.period * 100.0 /
- hists->stats.total_period;
+ u64 total = hists__total_period(hists);
+ float percent = 0.0;
+
+ if (total)
+ percent = h->stat.period * 100.0 / total;
if (percent < min_pcnt)
return NULL;
@@ -813,8 +848,11 @@ static struct rb_node *hists__filter_prev_entries(struct rb_node *nd,
{
while (nd != NULL) {
struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
- float percent = h->stat.period * 100.0 /
- hists->stats.total_period;
+ u64 total = hists__total_period(hists);
+ float percent = 0.0;
+
+ if (total)
+ percent = h->stat.period * 100.0 / total;
if (!h->filtered && percent >= min_pcnt)
return nd;
@@ -1189,6 +1227,11 @@ static int hists__browser_title(struct hists *hists, char *bf, size_t size,
char buf[512];
size_t buflen = sizeof(buf);
+ if (symbol_conf.filter_relative) {
+ nr_samples = hists->stats.nr_non_filtered_samples;
+ nr_events = hists->stats.total_non_filtered_period;
+ }
+
if (perf_evsel__is_group_event(evsel)) {
struct perf_evsel *pos;
@@ -1196,8 +1239,13 @@ static int hists__browser_title(struct hists *hists, char *bf, size_t size,
ev_name = buf;
for_each_group_member(pos, evsel) {
- nr_samples += pos->hists.stats.nr_events[PERF_RECORD_SAMPLE];
- nr_events += pos->hists.stats.total_period;
+ if (symbol_conf.filter_relative) {
+ nr_samples += pos->hists.stats.nr_non_filtered_samples;
+ nr_events += pos->hists.stats.total_non_filtered_period;
+ } else {
+ nr_samples += pos->hists.stats.nr_events[PERF_RECORD_SAMPLE];
+ nr_events += pos->hists.stats.total_period;
+ }
}
}
@@ -1324,18 +1372,23 @@ close_file_and_continue:
return ret;
}
-static void hist_browser__update_pcnt_entries(struct hist_browser *hb)
+static void hist_browser__update_nr_entries(struct hist_browser *hb)
{
u64 nr_entries = 0;
struct rb_node *nd = rb_first(&hb->hists->entries);
- while (nd) {
+ if (hb->min_pcnt == 0) {
+ hb->nr_non_filtered_entries = hb->hists->nr_non_filtered_entries;
+ return;
+ }
+
+ while ((nd = hists__filter_entries(nd, hb->hists,
+ hb->min_pcnt)) != NULL) {
nr_entries++;
- nd = hists__filter_entries(rb_next(nd), hb->hists,
- hb->min_pcnt);
+ nd = rb_next(nd);
}
- hb->nr_pcnt_entries = nr_entries;
+ hb->nr_non_filtered_entries = nr_entries;
}
static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
@@ -1370,6 +1423,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
"C Collapse all callchains\n" \
"d Zoom into current DSO\n" \
"E Expand all callchains\n" \
+ "F Toggle percentage of filtered entries\n" \
/* help messages are sorted by lexical order of the hotkey */
const char report_help[] = HIST_BROWSER_HELP_COMMON
@@ -1391,7 +1445,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
if (min_pcnt) {
browser->min_pcnt = min_pcnt;
- hist_browser__update_pcnt_entries(browser);
+ hist_browser__update_nr_entries(browser);
}
fstack = pstack__new(2);
@@ -1475,6 +1529,9 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
if (env->arch)
tui__header_window(env);
continue;
+ case 'F':
+ symbol_conf.filter_relative ^= 1;
+ continue;
case K_F1:
case 'h':
case '?':
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index e395ef9b0ae0..91f10f3f6dd1 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -228,12 +228,15 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
GtkTreeIter iter;
- float percent = h->stat.period * 100.0 /
- hists->stats.total_period;
+ u64 total = hists__total_period(h->hists);
+ float percent = 0.0;
if (h->filtered)
continue;
+ if (total)
+ percent = h->stat.period * 100.0 / total;
+
if (percent < min_pcnt)
continue;
@@ -261,12 +264,8 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
}
if (symbol_conf.use_callchain && sort__has_sym) {
- u64 total;
-
if (callchain_param.mode == CHAIN_GRAPH_REL)
total = h->stat.period;
- else
- total = hists->stats.total_period;
perf_gtk__add_callchain(&h->sorted_chain, store, &iter,
sym_col, total);
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 0f403b83e9d1..0912805c08f4 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -32,10 +32,10 @@ int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
if (fmt_percent) {
double percent = 0.0;
+ u64 total = hists__total_period(hists);
- if (hists->stats.total_period)
- percent = 100.0 * get_field(he) /
- hists->stats.total_period;
+ if (total)
+ percent = 100.0 * get_field(he) / total;
ret += hpp__call_print_fn(hpp, print_fn, fmt, percent);
} else
@@ -50,7 +50,7 @@ int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
list_for_each_entry(pair, &he->pairs.head, pairs.node) {
u64 period = get_field(pair);
- u64 total = pair->hists->stats.total_period;
+ u64 total = hists__total_period(pair->hists);
if (!total)
continue;
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index d59893edf031..9eccf7f4f367 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -495,7 +495,7 @@ print_entries:
break;
if (h->ms.map == NULL && verbose > 1) {
- __map_groups__fprintf_maps(&h->thread->mg,
+ __map_groups__fprintf_maps(h->thread->mg,
MAP__FUNCTION, verbose, fp);
fprintf(fp, "%.10s end\n", graph_dotted_line);
}
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 8d9db454f1a9..9a42382b3921 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -25,6 +25,84 @@
__thread struct callchain_cursor callchain_cursor;
+int
+parse_callchain_report_opt(const char *arg)
+{
+ char *tok, *tok2;
+ char *endptr;
+
+ symbol_conf.use_callchain = true;
+
+ if (!arg)
+ return 0;
+
+ tok = strtok((char *)arg, ",");
+ if (!tok)
+ return -1;
+
+ /* get the output mode */
+ if (!strncmp(tok, "graph", strlen(arg))) {
+ callchain_param.mode = CHAIN_GRAPH_ABS;
+
+ } else if (!strncmp(tok, "flat", strlen(arg))) {
+ callchain_param.mode = CHAIN_FLAT;
+ } else if (!strncmp(tok, "fractal", strlen(arg))) {
+ callchain_param.mode = CHAIN_GRAPH_REL;
+ } else if (!strncmp(tok, "none", strlen(arg))) {
+ callchain_param.mode = CHAIN_NONE;
+ symbol_conf.use_callchain = false;
+ return 0;
+ } else {
+ return -1;
+ }
+
+ /* get the min percentage */
+ tok = strtok(NULL, ",");
+ if (!tok)
+ goto setup;
+
+ callchain_param.min_percent = strtod(tok, &endptr);
+ if (tok == endptr)
+ return -1;
+
+ /* get the print limit */
+ tok2 = strtok(NULL, ",");
+ if (!tok2)
+ goto setup;
+
+ if (tok2[0] != 'c') {
+ callchain_param.print_limit = strtoul(tok2, &endptr, 0);
+ tok2 = strtok(NULL, ",");
+ if (!tok2)
+ goto setup;
+ }
+
+ /* get the call chain order */
+ if (!strncmp(tok2, "caller", strlen("caller")))
+ callchain_param.order = ORDER_CALLER;
+ else if (!strncmp(tok2, "callee", strlen("callee")))
+ callchain_param.order = ORDER_CALLEE;
+ else
+ return -1;
+
+ /* Get the sort key */
+ tok2 = strtok(NULL, ",");
+ if (!tok2)
+ goto setup;
+ if (!strncmp(tok2, "function", strlen("function")))
+ callchain_param.key = CCKEY_FUNCTION;
+ else if (!strncmp(tok2, "address", strlen("address")))
+ callchain_param.key = CCKEY_ADDRESS;
+ else
+ return -1;
+setup:
+ if (callchain_register_param(&callchain_param) < 0) {
+ pr_err("Can't register callchain params\n");
+ return -1;
+ }
+ return 0;
+}
+
static void
rb_insert_callchain(struct rb_root *root, struct callchain_node *chain,
enum chain_mode mode)
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 8ad97e9b119f..dda4cf8b534c 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -157,4 +157,5 @@ int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent
int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *sample);
extern const char record_callchain_help[];
+int parse_callchain_report_opt(const char *arg);
#endif /* __PERF_CALLCHAIN_H */
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 3e0fdd369ccb..24519e14ac56 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -11,6 +11,7 @@
#include "util.h"
#include "cache.h"
#include "exec_cmd.h"
+#include "util/hist.h" /* perf_hist_config */
#define MAXNAME (256)
@@ -355,6 +356,9 @@ int perf_default_config(const char *var, const char *value,
if (!prefixcmp(var, "core."))
return perf_default_core_config(var, value);
+ if (!prefixcmp(var, "hist."))
+ return perf_hist_config(var, value);
+
/* Add other config variables here. */
return 0;
}
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 7fe4994eeb63..c4e55b71010c 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -317,3 +317,163 @@ int cpu_map__build_core_map(struct cpu_map *cpus, struct cpu_map **corep)
{
return cpu_map__build_map(cpus, corep, cpu_map__get_core);
}
+
+/* setup simple routines to easily access node numbers given a cpu number */
+static int get_max_num(char *path, int *max)
+{
+ size_t num;
+ char *buf;
+ int err = 0;
+
+ if (filename__read_str(path, &buf, &num))
+ return -1;
+
+ buf[num] = '\0';
+
+ /* start on the right, to find highest node num */
+ while (--num) {
+ if ((buf[num] == ',') || (buf[num] == '-')) {
+ num++;
+ break;
+ }
+ }
+ if (sscanf(&buf[num], "%d", max) < 1) {
+ err = -1;
+ goto out;
+ }
+
+ /* convert from 0-based to 1-based */
+ (*max)++;
+
+out:
+ free(buf);
+ return err;
+}
+
+/* Determine highest possible cpu in the system for sparse allocation */
+static void set_max_cpu_num(void)
+{
+ const char *mnt;
+ char path[PATH_MAX];
+ int ret = -1;
+
+ /* set up default */
+ max_cpu_num = 4096;
+
+ mnt = sysfs__mountpoint();
+ if (!mnt)
+ goto out;
+
+ /* get the highest possible cpu number for a sparse allocation */
+ ret = snprintf(path, PATH_MAX, "%s/devices/system/cpu/possible", mnt);
+ if (ret == PATH_MAX) {
+ pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX);
+ goto out;
+ }
+
+ ret = get_max_num(path, &max_cpu_num);
+
+out:
+ if (ret)
+ pr_err("Failed to read max cpus, using default of %d\n", max_cpu_num);
+}
+
+/* Determine highest possible node in the system for sparse allocation */
+static void set_max_node_num(void)
+{
+ const char *mnt;
+ char path[PATH_MAX];
+ int ret = -1;
+
+ /* set up default */
+ max_node_num = 8;
+
+ mnt = sysfs__mountpoint();
+ if (!mnt)
+ goto out;
+
+ /* get the highest possible cpu number for a sparse allocation */
+ ret = snprintf(path, PATH_MAX, "%s/devices/system/node/possible", mnt);
+ if (ret == PATH_MAX) {
+ pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX);
+ goto out;
+ }
+
+ ret = get_max_num(path, &max_node_num);
+
+out:
+ if (ret)
+ pr_err("Failed to read max nodes, using default of %d\n", max_node_num);
+}
+
+static int init_cpunode_map(void)
+{
+ int i;
+
+ set_max_cpu_num();
+ set_max_node_num();
+
+ cpunode_map = calloc(max_cpu_num, sizeof(int));
+ if (!cpunode_map) {
+ pr_err("%s: calloc failed\n", __func__);
+ return -1;
+ }
+
+ for (i = 0; i < max_cpu_num; i++)
+ cpunode_map[i] = -1;
+
+ return 0;
+}
+
+int cpu__setup_cpunode_map(void)
+{
+ struct dirent *dent1, *dent2;
+ DIR *dir1, *dir2;
+ unsigned int cpu, mem;
+ char buf[PATH_MAX];
+ char path[PATH_MAX];
+ const char *mnt;
+ int n;
+
+ /* initialize globals */
+ if (init_cpunode_map())
+ return -1;
+
+ mnt = sysfs__mountpoint();
+ if (!mnt)
+ return 0;
+
+ n = snprintf(path, PATH_MAX, "%s/devices/system/node", mnt);
+ if (n == PATH_MAX) {
+ pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX);
+ return -1;
+ }
+
+ dir1 = opendir(path);
+ if (!dir1)
+ return 0;
+
+ /* walk tree and setup map */
+ while ((dent1 = readdir(dir1)) != NULL) {
+ if (dent1->d_type != DT_DIR || sscanf(dent1->d_name, "node%u", &mem) < 1)
+ continue;
+
+ n = snprintf(buf, PATH_MAX, "%s/%s", path, dent1->d_name);
+ if (n == PATH_MAX) {
+ pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX);
+ continue;
+ }
+
+ dir2 = opendir(buf);
+ if (!dir2)
+ continue;
+ while ((dent2 = readdir(dir2)) != NULL) {
+ if (dent2->d_type != DT_LNK || sscanf(dent2->d_name, "cpu%u", &cpu) < 1)
+ continue;
+ cpunode_map[cpu] = mem;
+ }
+ closedir(dir2);
+ }
+ closedir(dir1);
+ return 0;
+}
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index b123bb9d6f55..61a654849002 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -4,6 +4,9 @@
#include <stdio.h>
#include <stdbool.h>
+#include "perf.h"
+#include "util/debug.h"
+
struct cpu_map {
int nr;
int map[];
@@ -46,4 +49,36 @@ static inline bool cpu_map__empty(const struct cpu_map *map)
return map ? map->map[0] == -1 : true;
}
+int max_cpu_num;
+int max_node_num;
+int *cpunode_map;
+
+int cpu__setup_cpunode_map(void);
+
+static inline int cpu__max_node(void)
+{
+ if (unlikely(!max_node_num))
+ pr_debug("cpu_map not initialized\n");
+
+ return max_node_num;
+}
+
+static inline int cpu__max_cpu(void)
+{
+ if (unlikely(!max_cpu_num))
+ pr_debug("cpu_map not initialized\n");
+
+ return max_cpu_num;
+}
+
+static inline int cpu__get_node(int cpu)
+{
+ if (unlikely(cpunode_map == NULL)) {
+ pr_debug("cpu_map not initialized\n");
+ return -1;
+ }
+
+ return cpunode_map[cpu];
+}
+
#endif /* __PERF_CPUMAP_H */
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 9d12aa6dd485..dbcaea1a8180 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -699,7 +699,7 @@ void thread__find_addr_map(struct thread *thread,
enum map_type type, u64 addr,
struct addr_location *al)
{
- struct map_groups *mg = &thread->mg;
+ struct map_groups *mg = thread->mg;
bool load_map = false;
al->machine = machine;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index f38590d7561b..7f0236cea4fe 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -225,14 +225,18 @@ static void he_stat__decay(struct he_stat *he_stat)
static bool hists__decay_entry(struct hists *hists, struct hist_entry *he)
{
u64 prev_period = he->stat.period;
+ u64 diff;
if (prev_period == 0)
return true;
he_stat__decay(&he->stat);
+ diff = prev_period - he->stat.period;
+
+ hists->stats.total_period -= diff;
if (!he->filtered)
- hists->stats.total_period -= prev_period - he->stat.period;
+ hists->stats.total_non_filtered_period -= diff;
return he->stat.period == 0;
}
@@ -259,8 +263,11 @@ void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel)
if (sort__need_collapse)
rb_erase(&n->rb_node_in, &hists->entries_collapsed);
- hist_entry__free(n);
--hists->nr_entries;
+ if (!n->filtered)
+ --hists->nr_non_filtered_entries;
+
+ hist_entry__free(n);
}
}
}
@@ -317,15 +324,6 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template)
return he;
}
-void hists__inc_nr_entries(struct hists *hists, struct hist_entry *h)
-{
- if (!h->filtered) {
- hists__calc_col_len(hists, h);
- ++hists->nr_entries;
- hists->stats.total_period += h->stat.period;
- }
-}
-
static u8 symbol__parent_filter(const struct symbol *parent)
{
if (symbol_conf.exclude_other && parent == NULL)
@@ -391,7 +389,6 @@ static struct hist_entry *add_hist_entry(struct hists *hists,
if (!he)
return NULL;
- hists->nr_entries++;
rb_link_node(&he->rb_node_in, parent, p);
rb_insert_color(&he->rb_node_in, hists->entries_in);
out:
@@ -631,6 +628,35 @@ out:
return ret;
}
+static void hists__reset_filter_stats(struct hists *hists)
+{
+ hists->nr_non_filtered_entries = 0;
+ hists->stats.total_non_filtered_period = 0;
+}
+
+void hists__reset_stats(struct hists *hists)
+{
+ hists->nr_entries = 0;
+ hists->stats.total_period = 0;
+
+ hists__reset_filter_stats(hists);
+}
+
+static void hists__inc_filter_stats(struct hists *hists, struct hist_entry *h)
+{
+ hists->nr_non_filtered_entries++;
+ hists->stats.total_non_filtered_period += h->stat.period;
+}
+
+void hists__inc_stats(struct hists *hists, struct hist_entry *h)
+{
+ if (!h->filtered)
+ hists__inc_filter_stats(hists, h);
+
+ hists->nr_entries++;
+ hists->stats.total_period += h->stat.period;
+}
+
static void __hists__insert_output_entry(struct rb_root *entries,
struct hist_entry *he,
u64 min_callchain_hits)
@@ -674,8 +700,7 @@ void hists__output_resort(struct hists *hists)
next = rb_first(root);
hists->entries = RB_ROOT;
- hists->nr_entries = 0;
- hists->stats.total_period = 0;
+ hists__reset_stats(hists);
hists__reset_col_len(hists);
while (next) {
@@ -683,7 +708,10 @@ void hists__output_resort(struct hists *hists)
next = rb_next(&n->rb_node_in);
__hists__insert_output_entry(&hists->entries, n, min_callchain_hits);
- hists__inc_nr_entries(hists, n);
+ hists__inc_stats(hists, n);
+
+ if (!n->filtered)
+ hists__calc_col_len(hists, n);
}
}
@@ -694,13 +722,13 @@ static void hists__remove_entry_filter(struct hists *hists, struct hist_entry *h
if (h->filtered)
return;
- ++hists->nr_entries;
- if (h->ms.unfolded)
- hists->nr_entries += h->nr_rows;
+ /* force fold unfiltered entry for simplicity */
+ h->ms.unfolded = false;
h->row_offset = 0;
- hists->stats.total_period += h->stat.period;
- hists->stats.nr_events[PERF_RECORD_SAMPLE] += h->stat.nr_events;
+ hists->stats.nr_non_filtered_samples += h->stat.nr_events;
+
+ hists__inc_filter_stats(hists, h);
hists__calc_col_len(hists, h);
}
@@ -721,8 +749,9 @@ void hists__filter_by_dso(struct hists *hists)
{
struct rb_node *nd;
- hists->nr_entries = hists->stats.total_period = 0;
- hists->stats.nr_events[PERF_RECORD_SAMPLE] = 0;
+ hists->stats.nr_non_filtered_samples = 0;
+
+ hists__reset_filter_stats(hists);
hists__reset_col_len(hists);
for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
@@ -754,8 +783,9 @@ void hists__filter_by_thread(struct hists *hists)
{
struct rb_node *nd;
- hists->nr_entries = hists->stats.total_period = 0;
- hists->stats.nr_events[PERF_RECORD_SAMPLE] = 0;
+ hists->stats.nr_non_filtered_samples = 0;
+
+ hists__reset_filter_stats(hists);
hists__reset_col_len(hists);
for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
@@ -785,8 +815,9 @@ void hists__filter_by_symbol(struct hists *hists)
{
struct rb_node *nd;
- hists->nr_entries = hists->stats.total_period = 0;
- hists->stats.nr_events[PERF_RECORD_SAMPLE] = 0;
+ hists->stats.nr_non_filtered_samples = 0;
+
+ hists__reset_filter_stats(hists);
hists__reset_col_len(hists);
for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
@@ -847,7 +878,7 @@ static struct hist_entry *hists__add_dummy_entry(struct hists *hists,
he->hists = hists;
rb_link_node(&he->rb_node_in, parent, p);
rb_insert_color(&he->rb_node_in, root);
- hists__inc_nr_entries(hists, he);
+ hists__inc_stats(hists, he);
he->dummy = true;
}
out:
@@ -931,3 +962,30 @@ int hists__link(struct hists *leader, struct hists *other)
return 0;
}
+
+u64 hists__total_period(struct hists *hists)
+{
+ return symbol_conf.filter_relative ? hists->stats.total_non_filtered_period :
+ hists->stats.total_period;
+}
+
+int parse_filter_percentage(const struct option *opt __maybe_unused,
+ const char *arg, int unset __maybe_unused)
+{
+ if (!strcmp(arg, "relative"))
+ symbol_conf.filter_relative = true;
+ else if (!strcmp(arg, "absolute"))
+ symbol_conf.filter_relative = false;
+ else
+ return -1;
+
+ return 0;
+}
+
+int perf_hist_config(const char *var, const char *value)
+{
+ if (!strcmp(var, "hist.percentage"))
+ return parse_filter_percentage(NULL, value, 0);
+
+ return 0;
+}
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 1f1f513dfe7f..38c3e874c164 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -37,9 +37,11 @@ enum hist_filter {
*/
struct events_stats {
u64 total_period;
+ u64 total_non_filtered_period;
u64 total_lost;
u64 total_invalid_chains;
u32 nr_events[PERF_RECORD_HEADER_MAX];
+ u32 nr_non_filtered_samples;
u32 nr_lost_warned;
u32 nr_unknown_events;
u32 nr_invalid_chains;
@@ -83,6 +85,7 @@ struct hists {
struct rb_root entries;
struct rb_root entries_collapsed;
u64 nr_entries;
+ u64 nr_non_filtered_entries;
const struct thread *thread_filter;
const struct dso *dso_filter;
const char *uid_filter_str;
@@ -112,7 +115,9 @@ void hists__collapse_resort(struct hists *hists, struct ui_progress *prog);
void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel);
void hists__output_recalc_col_len(struct hists *hists, int max_rows);
-void hists__inc_nr_entries(struct hists *hists, struct hist_entry *h);
+u64 hists__total_period(struct hists *hists);
+void hists__reset_stats(struct hists *hists);
+void hists__inc_stats(struct hists *hists, struct hist_entry *h);
void hists__inc_nr_events(struct hists *hists, u32 type);
void events_stats__inc(struct events_stats *stats, u32 type);
size_t events_stats__fprintf(struct events_stats *stats, FILE *fp);
@@ -124,6 +129,12 @@ void hists__filter_by_dso(struct hists *hists);
void hists__filter_by_thread(struct hists *hists);
void hists__filter_by_symbol(struct hists *hists);
+static inline bool hists__has_filter(struct hists *hists)
+{
+ return hists->thread_filter || hists->dso_filter ||
+ hists->symbol_filter_str;
+}
+
u16 hists__col_len(struct hists *hists, enum hist_column col);
void hists__set_col_len(struct hists *hists, enum hist_column col, u16 len);
bool hists__new_col_len(struct hists *hists, enum hist_column col, u16 len);
@@ -250,4 +261,10 @@ static inline int script_browse(const char *script_opt __maybe_unused)
#endif
unsigned int hists__sort_list_width(struct hists *hists);
+
+struct option;
+int parse_filter_percentage(const struct option *opt __maybe_unused,
+ const char *arg, int unset __maybe_unused);
+int perf_hist_config(const char *var, const char *value);
+
#endif /* __PERF_HIST_H */
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 27c2a5efe450..7409ac8de51c 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -316,6 +316,17 @@ static struct thread *__machine__findnew_thread(struct machine *machine,
rb_link_node(&th->rb_node, parent, p);
rb_insert_color(&th->rb_node, &machine->threads);
machine->last_match = th;
+
+ /*
+ * We have to initialize map_groups separately
+ * after rb tree is updated.
+ *
+ * The reason is that we call machine__findnew_thread
+ * within thread__init_map_groups to find the thread
+ * leader and that would screwed the rb tree.
+ */
+ if (thread__init_map_groups(th, machine))
+ return NULL;
}
return th;
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 39cd2d0faff6..ba5f5c0c838b 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -323,6 +323,7 @@ void map_groups__init(struct map_groups *mg)
INIT_LIST_HEAD(&mg->removed_maps[i]);
}
mg->machine = NULL;
+ mg->refcnt = 1;
}
static void maps__delete(struct rb_root *maps)
@@ -358,6 +359,28 @@ void map_groups__exit(struct map_groups *mg)
}
}
+struct map_groups *map_groups__new(void)
+{
+ struct map_groups *mg = malloc(sizeof(*mg));
+
+ if (mg != NULL)
+ map_groups__init(mg);
+
+ return mg;
+}
+
+void map_groups__delete(struct map_groups *mg)
+{
+ map_groups__exit(mg);
+ free(mg);
+}
+
+void map_groups__put(struct map_groups *mg)
+{
+ if (--mg->refcnt == 0)
+ map_groups__delete(mg);
+}
+
void map_groups__flush(struct map_groups *mg)
{
int type;
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index f00f058afb3b..d6445b27d672 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -59,8 +59,20 @@ struct map_groups {
struct rb_root maps[MAP__NR_TYPES];
struct list_head removed_maps[MAP__NR_TYPES];
struct machine *machine;
+ int refcnt;
};
+struct map_groups *map_groups__new(void);
+void map_groups__delete(struct map_groups *mg);
+
+static inline struct map_groups *map_groups__get(struct map_groups *mg)
+{
+ ++mg->refcnt;
+ return mg;
+}
+
+void map_groups__put(struct map_groups *mg);
+
static inline struct kmap *map__kmap(struct map *map)
{
return (struct kmap *)(map + 1);
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 00a7dcb2f55c..7a811eb61f75 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -284,17 +284,17 @@ static int pmu_aliases(const char *name, struct list_head *head)
static int pmu_alias_terms(struct perf_pmu_alias *alias,
struct list_head *terms)
{
- struct parse_events_term *term, *clone;
+ struct parse_events_term *term, *cloned;
LIST_HEAD(list);
int ret;
list_for_each_entry(term, &alias->terms, list) {
- ret = parse_events_term__clone(&clone, term);
+ ret = parse_events_term__clone(&cloned, term);
if (ret) {
parse_events__free_terms(&list);
return ret;
}
- list_add_tail(&clone->list, &list);
+ list_add_tail(&cloned->list, &list);
}
list_splice(&list, terms);
return 0;
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 501e4e722e8e..ae94e006a52d 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -115,7 +115,8 @@ struct symbol_conf {
annotate_asm_raw,
annotate_src,
event_group,
- demangle;
+ demangle,
+ filter_relative;
const char *vmlinux_name,
*kallsyms_name,
*source_prefix,
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 3ce0498bdae6..2fde0d5e40b5 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -8,6 +8,22 @@
#include "debug.h"
#include "comm.h"
+int thread__init_map_groups(struct thread *thread, struct machine *machine)
+{
+ struct thread *leader;
+ pid_t pid = thread->pid_;
+
+ if (pid == thread->tid) {
+ thread->mg = map_groups__new();
+ } else {
+ leader = machine__findnew_thread(machine, pid, pid);
+ if (leader)
+ thread->mg = map_groups__get(leader->mg);
+ }
+
+ return thread->mg ? 0 : -1;
+}
+
struct thread *thread__new(pid_t pid, pid_t tid)
{
char *comm_str;
@@ -15,7 +31,6 @@ struct thread *thread__new(pid_t pid, pid_t tid)
struct thread *thread = zalloc(sizeof(*thread));
if (thread != NULL) {
- map_groups__init(&thread->mg);
thread->pid_ = pid;
thread->tid = tid;
thread->ppid = -1;
@@ -45,7 +60,8 @@ void thread__delete(struct thread *thread)
{
struct comm *comm, *tmp;
- map_groups__exit(&thread->mg);
+ map_groups__put(thread->mg);
+ thread->mg = NULL;
list_for_each_entry_safe(comm, tmp, &thread->comm_list, list) {
list_del(&comm->list);
comm__free(comm);
@@ -111,18 +127,35 @@ int thread__comm_len(struct thread *thread)
size_t thread__fprintf(struct thread *thread, FILE *fp)
{
return fprintf(fp, "Thread %d %s\n", thread->tid, thread__comm_str(thread)) +
- map_groups__fprintf(&thread->mg, verbose, fp);
+ map_groups__fprintf(thread->mg, verbose, fp);
}
void thread__insert_map(struct thread *thread, struct map *map)
{
- map_groups__fixup_overlappings(&thread->mg, map, verbose, stderr);
- map_groups__insert(&thread->mg, map);
+ map_groups__fixup_overlappings(thread->mg, map, verbose, stderr);
+ map_groups__insert(thread->mg, map);
+}
+
+static int thread__clone_map_groups(struct thread *thread,
+ struct thread *parent)
+{
+ int i;
+
+ /* This is new thread, we share map groups for process. */
+ if (thread->pid_ == parent->pid_)
+ return 0;
+
+ /* But this one is new process, copy maps. */
+ for (i = 0; i < MAP__NR_TYPES; ++i)
+ if (map_groups__clone(thread->mg, parent->mg, i) < 0)
+ return -ENOMEM;
+
+ return 0;
}
int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp)
{
- int i, err;
+ int err;
if (parent->comm_set) {
const char *comm = thread__comm_str(parent);
@@ -134,13 +167,8 @@ int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp)
thread->comm_set = true;
}
- for (i = 0; i < MAP__NR_TYPES; ++i)
- if (map_groups__clone(&thread->mg, &parent->mg, i) < 0)
- return -ENOMEM;
-
thread->ppid = parent->tid;
-
- return 0;
+ return thread__clone_map_groups(thread, parent);
}
void thread__find_cpumode_addr_location(struct thread *thread,
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 9b29f085aede..3c0c2724f82c 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -13,7 +13,7 @@ struct thread {
struct rb_node rb_node;
struct list_head node;
};
- struct map_groups mg;
+ struct map_groups *mg;
pid_t pid_; /* Not all tools update this */
pid_t tid;
pid_t ppid;
@@ -30,6 +30,7 @@ struct machine;
struct comm;
struct thread *thread__new(pid_t pid, pid_t tid);
+int thread__init_map_groups(struct thread *thread, struct machine *machine);
void thread__delete(struct thread *thread);
static inline void thread__exited(struct thread *thread)
{