aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--tools/build/Makefile.feature1
-rw-r--r--tools/build/feature/Makefile4
-rw-r--r--tools/build/feature/test-libtracefs.c10
-rw-r--r--tools/perf/Documentation/perf-record.txt16
-rw-r--r--tools/perf/Makefile.config21
-rw-r--r--tools/perf/Makefile.perf2
-rw-r--r--tools/perf/arch/riscv64/annotate/instructions.c34
-rw-r--r--tools/perf/arch/x86/annotate/instructions.c28
-rw-r--r--tools/perf/bench/synthesize.c4
-rw-r--r--tools/perf/builtin-daemon.c13
-rw-r--r--tools/perf/builtin-kvm.c2
-rw-r--r--tools/perf/builtin-record.c46
-rw-r--r--tools/perf/builtin-top.c2
-rw-r--r--tools/perf/builtin-trace.c4
-rw-r--r--tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-ddrc.json32
-rw-r--r--tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-hha.json120
-rw-r--r--tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-l3c.json52
-rw-r--r--tools/perf/pmu-events/arch/test/test_soc/sys/uncore.json7
-rw-r--r--tools/perf/pmu-events/jevents.c16
-rw-r--r--tools/perf/tests/code-reading.c3
-rw-r--r--tools/perf/tests/expr.c160
-rw-r--r--tools/perf/tests/mmap-thread-lookup.c4
-rw-r--r--tools/perf/tests/parse-events.c8
-rw-r--r--tools/perf/tests/pmu-events.c135
-rwxr-xr-xtools/perf/tests/shell/stat_all_metricgroups.sh12
-rwxr-xr-xtools/perf/tests/shell/stat_all_metrics.sh22
-rwxr-xr-xtools/perf/tests/shell/stat_all_pmu.sh22
-rw-r--r--tools/perf/tests/vmlinux-kallsyms.c102
-rw-r--r--tools/perf/util/annotate.c6
-rw-r--r--tools/perf/util/bpf_counter.c8
-rw-r--r--tools/perf/util/bpf_counter_cgroup.c8
-rw-r--r--tools/perf/util/debug.c19
-rw-r--r--tools/perf/util/expr.c121
-rw-r--r--tools/perf/util/expr.h20
-rw-r--r--tools/perf/util/expr.l9
-rw-r--r--tools/perf/util/expr.y325
-rw-r--r--tools/perf/util/metricgroup.c142
-rw-r--r--tools/perf/util/parse-events.c82
-rw-r--r--tools/perf/util/parse-events.h3
-rw-r--r--tools/perf/util/parse-events.l1
-rw-r--r--tools/perf/util/record.h1
-rw-r--r--tools/perf/util/srcline.c338
-rw-r--r--tools/perf/util/stat-shadow.c54
-rw-r--r--tools/perf/util/synthetic-events.c73
-rw-r--r--tools/perf/util/synthetic-events.h20
45 files changed, 1608 insertions, 504 deletions
diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index 3dd2f68366f9..45a9a59828c3 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -52,6 +52,7 @@ FEATURE_TESTS_BASIC := \
libslang \
libslang-include-subdir \
libtraceevent \
+ libtracefs \
libcrypto \
libunwind \
pthread-attr-setaffinity-np \
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index eff55d287db1..d024b5204ba0 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -36,6 +36,7 @@ FILES= \
test-libslang.bin \
test-libslang-include-subdir.bin \
test-libtraceevent.bin \
+ test-libtracefs.bin \
test-libcrypto.bin \
test-libunwind.bin \
test-libunwind-debug-frame.bin \
@@ -199,6 +200,9 @@ $(OUTPUT)test-libslang-include-subdir.bin:
$(OUTPUT)test-libtraceevent.bin:
$(BUILD) -ltraceevent
+$(OUTPUT)test-libtracefs.bin:
+ $(BUILD) -ltracefs
+
$(OUTPUT)test-libcrypto.bin:
$(BUILD) -lcrypto
diff --git a/tools/build/feature/test-libtracefs.c b/tools/build/feature/test-libtracefs.c
new file mode 100644
index 000000000000..8eff16c0c10b
--- /dev/null
+++ b/tools/build/feature/test-libtracefs.c
@@ -0,0 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <tracefs/tracefs.h>
+
+int main(void)
+{
+ struct tracefs_instance *inst = tracefs_instance_create("dummy");
+
+ tracefs_instance_destroy(inst);
+ return 0;
+}
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index f1079ee7f2ec..2d7df8703cf2 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -596,6 +596,22 @@ options.
'perf record --dry-run -e' can act as a BPF script compiler if llvm.dump-obj
in config file is set to true.
+--synth=TYPE::
+Collect and synthesize given type of events (comma separated). Note that
+this option controls the synthesis from the /proc filesystem which represent
+task status for pre-existing threads.
+
+Kernel (and some other) events are recorded regardless of the
+choice in this option. For example, --synth=no would have MMAP events for
+kernel and modules.
+
+Available types are:
+ 'task' - synthesize FORK and COMM events for each task
+ 'mmap' - synthesize MMAP events for each process (implies 'task')
+ 'cgroup' - synthesize CGROUP events for each cgroup
+ 'all' - synthesize all events (default)
+ 'no' - do not synthesize any of the above events
+
--tail-synthesize::
Instead of collecting non-sample events (for example, fork, comm, mmap) at
the beginning of record, collect them during finalizing an output file.
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 14e3e8d702a0..4a9baed28f2e 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -1093,11 +1093,32 @@ ifdef LIBTRACEEVENT_DYNAMIC
$(call feature_check,libtraceevent)
ifeq ($(feature-libtraceevent), 1)
EXTLIBS += -ltraceevent
+ LIBTRACEEVENT_VERSION := $(shell $(PKG_CONFIG) --modversion libtraceevent)
+ LIBTRACEEVENT_VERSION_1 := $(word 1, $(subst ., ,$(LIBTRACEEVENT_VERSION)))
+ LIBTRACEEVENT_VERSION_2 := $(word 2, $(subst ., ,$(LIBTRACEEVENT_VERSION)))
+ LIBTRACEEVENT_VERSION_3 := $(word 3, $(subst ., ,$(LIBTRACEEVENT_VERSION)))
+ LIBTRACEEVENT_VERSION_CPP := $(shell expr $(LIBTRACEEVENT_VERSION_1) \* 255 \* 255 + $(LIBTRACEEVENT_VERSION_2) \* 255 + $(LIBTRACEEVENT_VERSION_3))
+ CFLAGS += -DLIBTRACEEVENT_VERSION=$(LIBTRACEEVENT_VERSION_CPP)
else
dummy := $(error Error: No libtraceevent devel library found, please install libtraceevent-devel);
endif
endif
+ifdef LIBTRACEFS_DYNAMIC
+ $(call feature_check,libtracefs)
+ ifeq ($(feature-libtracefs), 1)
+ EXTLIBS += -ltracefs
+ LIBTRACEFS_VERSION := $(shell $(PKG_CONFIG) --modversion libtracefs)
+ LIBTRACEFS_VERSION_1 := $(word 1, $(subst ., ,$(LIBTRACEFS_VERSION)))
+ LIBTRACEFS_VERSION_2 := $(word 2, $(subst ., ,$(LIBTRACEFS_VERSION)))
+ LIBTRACEFS_VERSION_3 := $(word 3, $(subst ., ,$(LIBTRACEFS_VERSION)))
+ LIBTRACEFS_VERSION_CPP := $(shell expr $(LIBTRACEFS_VERSION_1) \* 255 \* 255 + $(LIBTRACEFS_VERSION_2) \* 255 + $(LIBTRACEFS_VERSION_3))
+ CFLAGS += -DLIBTRACEFS_VERSION=$(LIBTRACEFS_VERSION_CPP)
+ else
+ dummy := $(error Error: No libtracefs devel library found, please install libtracefs-dev);
+ endif
+endif
+
# Among the variables below, these:
# perfexecdir
# perf_include_dir
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 5cd702062a04..6b6154a52c4e 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -130,6 +130,8 @@ include ../scripts/utilities.mak
#
# Define LIBTRACEEVENT_DYNAMIC to enable libtraceevent dynamic linking
#
+# Define LIBTRACEFS_DYNAMIC to enable libtracefs dynamic linking
+#
# As per kernel Makefile, avoid funny character set dependencies
unexport LC_ALL
diff --git a/tools/perf/arch/riscv64/annotate/instructions.c b/tools/perf/arch/riscv64/annotate/instructions.c
new file mode 100644
index 000000000000..869a0eb28953
--- /dev/null
+++ b/tools/perf/arch/riscv64/annotate/instructions.c
@@ -0,0 +1,34 @@
+// SPDX-License-Identifier: GPL-2.0
+
+static
+struct ins_ops *riscv64__associate_ins_ops(struct arch *arch, const char *name)
+{
+ struct ins_ops *ops = NULL;
+
+ if (!strncmp(name, "jal", 3) ||
+ !strncmp(name, "jr", 2) ||
+ !strncmp(name, "call", 4))
+ ops = &call_ops;
+ else if (!strncmp(name, "ret", 3))
+ ops = &ret_ops;
+ else if (name[0] == 'j' || name[0] == 'b')
+ ops = &jump_ops;
+ else
+ return NULL;
+
+ arch__associate_ins_ops(arch, name, ops);
+
+ return ops;
+}
+
+static
+int riscv64__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
+{
+ if (!arch->initialized) {
+ arch->associate_instruction_ops = riscv64__associate_ins_ops;
+ arch->initialized = true;
+ arch->objdump.comment_char = '#';
+ }
+
+ return 0;
+}
diff --git a/tools/perf/arch/x86/annotate/instructions.c b/tools/perf/arch/x86/annotate/instructions.c
index 24ea12ec7e02..305872692bfd 100644
--- a/tools/perf/arch/x86/annotate/instructions.c
+++ b/tools/perf/arch/x86/annotate/instructions.c
@@ -144,9 +144,32 @@ static struct ins x86__instructions[] = {
{ .name = "xorps", .ops = &mov_ops, },
};
-static bool x86__ins_is_fused(struct arch *arch, const char *ins1,
+static bool amd__ins_is_fused(struct arch *arch, const char *ins1,
const char *ins2)
{
+ if (strstr(ins2, "jmp"))
+ return false;
+
+ /* Family >= 15h supports cmp/test + branch fusion */
+ if (arch->family >= 0x15 && (strstarts(ins1, "test") ||
+ (strstarts(ins1, "cmp") && !strstr(ins1, "xchg")))) {
+ return true;
+ }
+
+ /* Family >= 19h supports some ALU + branch fusion */
+ if (arch->family >= 0x19 && (strstarts(ins1, "add") ||
+ strstarts(ins1, "sub") || strstarts(ins1, "and") ||
+ strstarts(ins1, "inc") || strstarts(ins1, "dec") ||
+ strstarts(ins1, "or") || strstarts(ins1, "xor"))) {
+ return true;
+ }
+
+ return false;
+}
+
+static bool intel__ins_is_fused(struct arch *arch, const char *ins1,
+ const char *ins2)
+{
if (arch->family != 6 || arch->model < 0x1e || strstr(ins2, "jmp"))
return false;
@@ -184,6 +207,9 @@ static int x86__cpuid_parse(struct arch *arch, char *cpuid)
if (ret == 3) {
arch->family = family;
arch->model = model;
+ arch->ins_is_fused = strstarts(cpuid, "AuthenticAMD") ?
+ amd__ins_is_fused :
+ intel__ins_is_fused;
return 0;
}
diff --git a/tools/perf/bench/synthesize.c b/tools/perf/bench/synthesize.c
index 05f7c923c745..7401ebbac100 100644
--- a/tools/perf/bench/synthesize.c
+++ b/tools/perf/bench/synthesize.c
@@ -80,7 +80,7 @@ static int do_run_single_threaded(struct perf_session *session,
NULL,
target, threads,
process_synthesized_event,
- data_mmap,
+ true, data_mmap,
nr_threads_synthesize);
if (err)
return err;
@@ -171,7 +171,7 @@ static int do_run_multi_threaded(struct target *target,
NULL,
target, NULL,
process_synthesized_event,
- false,
+ true, false,
nr_threads_synthesize);
if (err) {
perf_session__delete(session);
diff --git a/tools/perf/builtin-daemon.c b/tools/perf/builtin-daemon.c
index 61929f63a047..c13201fb09c3 100644
--- a/tools/perf/builtin-daemon.c
+++ b/tools/perf/builtin-daemon.c
@@ -1403,8 +1403,10 @@ out:
static int send_cmd_list(struct daemon *daemon)
{
- union cmd cmd = { .cmd = CMD_LIST, };
+ union cmd cmd;
+ memset(&cmd, 0, sizeof(cmd));
+ cmd.list.cmd = CMD_LIST;
cmd.list.verbose = verbose;
cmd.list.csv_sep = daemon->csv_sep ? *daemon->csv_sep : 0;
@@ -1432,6 +1434,7 @@ static int __cmd_signal(struct daemon *daemon, struct option parent_options[],
return -1;
}
+ memset(&cmd, 0, sizeof(cmd));
cmd.signal.cmd = CMD_SIGNAL,
cmd.signal.sig = SIGUSR2;
strncpy(cmd.signal.name, name, sizeof(cmd.signal.name) - 1);
@@ -1446,7 +1449,7 @@ static int __cmd_stop(struct daemon *daemon, struct option parent_options[],
OPT_PARENT(parent_options),
OPT_END()
};
- union cmd cmd = { .cmd = CMD_STOP, };
+ union cmd cmd;
argc = parse_options(argc, argv, start_options, daemon_usage, 0);
if (argc)
@@ -1457,6 +1460,8 @@ static int __cmd_stop(struct daemon *daemon, struct option parent_options[],
return -1;
}
+ memset(&cmd, 0, sizeof(cmd));
+ cmd.cmd = CMD_STOP;
return send_cmd(daemon, &cmd);
}
@@ -1470,7 +1475,7 @@ static int __cmd_ping(struct daemon *daemon, struct option parent_options[],
OPT_PARENT(parent_options),
OPT_END()
};
- union cmd cmd = { .cmd = CMD_PING, };
+ union cmd cmd;
argc = parse_options(argc, argv, ping_options, daemon_usage, 0);
if (argc)
@@ -1481,6 +1486,8 @@ static int __cmd_ping(struct daemon *daemon, struct option parent_options[],
return -1;
}
+ memset(&cmd, 0, sizeof(cmd));
+ cmd.cmd = CMD_PING;
scnprintf(cmd.ping.name, sizeof(cmd.ping.name), "%s", name);
return send_cmd(daemon, &cmd);
}
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index aa1b127ffb5b..c6f352ee57e6 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -1456,7 +1456,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
perf_session__set_id_hdr_size(kvm->session);
ordered_events__set_copy_on_queue(&kvm->session->ordered_events, true);
machine__synthesize_threads(&kvm->session->machines.host, &kvm->opts.target,
- kvm->evlist->core.threads, false, 1);
+ kvm->evlist->core.threads, true, false, 1);
err = kvm_live_open_events(kvm);
if (err)
goto out;
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index b3509d9d20cc..41bb884f5a74 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -1255,6 +1255,7 @@ static int record__synthesize_workload(struct record *rec, bool tail)
{
int err;
struct perf_thread_map *thread_map;
+ bool needs_mmap = rec->opts.synth & PERF_SYNTH_MMAP;
if (rec->opts.tail_synthesize != tail)
return 0;
@@ -1266,6 +1267,7 @@ static int record__synthesize_workload(struct record *rec, bool tail)
err = perf_event__synthesize_thread_map(&rec->tool, thread_map,
process_synthesized_event,
&rec->session->machines.host,
+ needs_mmap,
rec->opts.sample_address);
perf_thread_map__put(thread_map);
return err;
@@ -1470,19 +1472,26 @@ static int record__synthesize(struct record *rec, bool tail)
if (err < 0)
pr_warning("Couldn't synthesize bpf events.\n");
- err = perf_event__synthesize_cgroups(tool, process_synthesized_event,
- machine);
- if (err < 0)
- pr_warning("Couldn't synthesize cgroup events.\n");
+ if (rec->opts.synth & PERF_SYNTH_CGROUP) {
+ err = perf_event__synthesize_cgroups(tool, process_synthesized_event,
+ machine);
+ if (err < 0)
+ pr_warning("Couldn't synthesize cgroup events.\n");
+ }
if (rec->opts.nr_threads_synthesize > 1) {
perf_set_multithreaded();
f = process_locked_synthesized_event;
}
- err = __machine__synthesize_threads(machine, tool, &opts->target, rec->evlist->core.threads,
- f, opts->sample_address,
- rec->opts.nr_threads_synthesize);
+ if (rec->opts.synth & PERF_SYNTH_TASK) {
+ bool needs_mmap = rec->opts.synth & PERF_SYNTH_MMAP;
+
+ err = __machine__synthesize_threads(machine, tool, &opts->target,
+ rec->evlist->core.threads,
+ f, needs_mmap, opts->sample_address,
+ rec->opts.nr_threads_synthesize);
+ }
if (rec->opts.nr_threads_synthesize > 1)
perf_set_singlethreaded();
@@ -2391,6 +2400,26 @@ static int process_timestamp_boundary(struct perf_tool *tool,
return 0;
}
+static int parse_record_synth_option(const struct option *opt,
+ const char *str,
+ int unset __maybe_unused)
+{
+ struct record_opts *opts = opt->value;
+ char *p = strdup(str);
+
+ if (p == NULL)
+ return -1;
+
+ opts->synth = parse_synth_opt(p);
+ free(p);
+
+ if (opts->synth < 0) {
+ pr_err("Invalid synth option: %s\n", str);
+ return -1;
+ }
+ return 0;
+}
+
/*
* XXX Ideally would be local to cmd_record() and passed to a record__new
* because we need to have access to it in record__exit, that is called
@@ -2416,6 +2445,7 @@ static struct record record = {
.nr_threads_synthesize = 1,
.ctl_fd = -1,
.ctl_fd_ack = -1,
+ .synth = PERF_SYNTH_ALL,
},
.tool = {
.sample = process_sample_event,
@@ -2631,6 +2661,8 @@ static struct option __record_options[] = {
"\t\t\t Optionally send control command completion ('ack\\n') to ack-fd descriptor.\n"
"\t\t\t Alternatively, ctl-fifo / ack-fifo will be opened and used as ctl-fd / ack-fd.",
parse_control_option),
+ OPT_CALLBACK(0, "synth", &record.opts, "no|all|task|mmap|cgroup",
+ "Fine-tune event synthesis: default=all", parse_record_synth_option),
OPT_END()
};
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index a3ae9176a83e..020c4f110c10 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1271,7 +1271,7 @@ static int __cmd_top(struct perf_top *top)
pr_debug("Couldn't synthesize cgroup events.\n");
machine__synthesize_threads(&top->session->machines.host, &opts->target,
- top->evlist->core.threads, false,
+ top->evlist->core.threads, true, false,
top->nr_threads_synthesize);
if (top->nr_threads_synthesize > 1)
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 2bf21194c7b3..2f1d20553a0a 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1628,8 +1628,8 @@ static int trace__symbols_init(struct trace *trace, struct evlist *evlist)
goto out;
err = __machine__synthesize_threads(trace->host, &trace->tool, &trace->opts.target,
- evlist->core.threads, trace__tool_process, false,
- 1);
+ evlist->core.threads, trace__tool_process,
+ true, false, 1);
out:
if (err)
symbol__exit();
diff --git a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-ddrc.json b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-ddrc.json
index 61514d38601b..2b3cb55df288 100644
--- a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-ddrc.json
+++ b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-ddrc.json
@@ -1,56 +1,56 @@
[
{
- "EventCode": "0x00",
- "EventName": "uncore_hisi_ddrc.flux_wr",
+ "ConfigCode": "0x00",
+ "EventName": "flux_wr",
"BriefDescription": "DDRC total write operations",
"PublicDescription": "DDRC total write operations",
"Unit": "hisi_sccl,ddrc"
},
{
- "EventCode": "0x01",
- "EventName": "uncore_hisi_ddrc.flux_rd",
+ "ConfigCode": "0x01",
+ "EventName": "flux_rd",
"BriefDescription": "DDRC total read operations",
"PublicDescription": "DDRC total read operations",
"Unit": "hisi_sccl,ddrc"
},
{
- "EventCode": "0x02",
- "EventName": "uncore_hisi_ddrc.flux_wcmd",
+ "ConfigCode": "0x02",
+ "EventName": "flux_wcmd",
"BriefDescription": "DDRC write commands",
"PublicDescription": "DDRC write commands",
"Unit": "hisi_sccl,ddrc"
},
{
- "EventCode": "0x03",
- "EventName": "uncore_hisi_ddrc.flux_rcmd",
+ "ConfigCode": "0x03",
+ "EventName": "flux_rcmd",
"BriefDescription": "DDRC read commands",
"PublicDescription": "DDRC read commands",
"Unit": "hisi_sccl,ddrc"
},
{
- "EventCode": "0x04",
- "EventName": "uncore_hisi_ddrc.pre_cmd",
+ "ConfigCode": "0x04",
+ "EventName": "pre_cmd",
"BriefDescription": "DDRC precharge commands",
"PublicDescription": "DDRC precharge commands",
"Unit": "hisi_sccl,ddrc"
},
{
- "EventCode": "0x05",
- "EventName": "uncore_hisi_ddrc.act_cmd",
+ "ConfigCode": "0x05",
+ "EventName": "act_cmd",
"BriefDescription": "DDRC active commands",
"PublicDescription": "DDRC active commands",
"Unit": "hisi_sccl,ddrc"
},
{
- "EventCode": "0x06",
- "EventName": "uncore_hisi_ddrc.rnk_chg",
+ "ConfigCode": "0x06",
+ "EventName": "rnk_chg",
"BriefDescription": "DDRC rank commands",
"PublicDescription": "DDRC rank commands",
"Unit": "hisi_sccl,ddrc"
},
{
- "EventCode": "0x07",
- "EventName": "uncore_hisi_ddrc.rw_chg",
+ "ConfigCode": "0x07",
+ "EventName": "rw_chg",
"BriefDescription": "DDRC read and write changes",
"PublicDescription": "DDRC read and write changes",
"Unit": "hisi_sccl,ddrc"
diff --git a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-hha.json b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-hha.json
index ada86782933f..9a7ec7af2060 100644
--- a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-hha.json
+++ b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-hha.json
@@ -1,72 +1,152 @@
[
{
- "EventCode": "0x00",
- "EventName": "uncore_hisi_hha.rx_ops_num",
+ "ConfigCode": "0x00",
+ "EventName": "rx_ops_num",
"BriefDescription": "The number of all operations received by the HHA",
"PublicDescription": "The number of all operations received by the HHA",
"Unit": "hisi_sccl,hha"
},
{
- "EventCode": "0x01",
- "EventName": "uncore_hisi_hha.rx_outer",
+ "ConfigCode": "0x01",
+ "EventName": "rx_outer",
"BriefDescription": "The number of all operations received by the HHA from another socket",
"PublicDescription": "The number of all operations received by the HHA from another socket",
"Unit": "hisi_sccl,hha"
},
{
- "EventCode": "0x02",
- "EventName": "uncore_hisi_hha.rx_sccl",
+ "ConfigCode": "0x02",
+ "EventName": "rx_sccl",
"BriefDescription": "The number of all operations received by the HHA from another SCCL in this socket",
"PublicDescription": "The number of all operations received by the HHA from another SCCL in this socket",
"Unit": "hisi_sccl,hha"
},
{
- "EventCode": "0x03",
- "EventName": "uncore_hisi_hha.rx_ccix",
+ "ConfigCode": "0x03",
+ "EventName": "rx_ccix",
"BriefDescription": "Count of the number of operations that HHA has received from CCIX",
"PublicDescription": "Count of the number of operations that HHA has received from CCIX",
"Unit": "hisi_sccl,hha"
},
{
- "EventCode": "0x1c",
- "EventName": "uncore_hisi_hha.rd_ddr_64b",
+ "ConfigCode": "0x4",
+ "EventName": "rx_wbi",
+ "Unit": "hisi_sccl,hha"
+ },
+ {
+ "ConfigCode": "0x5",
+ "EventName": "rx_wbip",
+ "Unit": "hisi_sccl,hha"
+ },
+ {
+ "ConfigCode": "0x11",
+ "EventName": "rx_wtistash",
+ "Unit": "hisi_sccl,hha"
+ },
+ {
+ "ConfigCode": "0x1c",
+ "EventName": "rd_ddr_64b",
"BriefDescription": "The number of read operations sent by HHA to DDRC which size is 64 bytes",
"PublicDescription": "The number of read operations sent by HHA to DDRC which size is 64bytes",
"Unit": "hisi_sccl,hha"
},
{
- "EventCode": "0x1d",
- "EventName": "uncore_hisi_hha.wr_ddr_64b",
+ "ConfigCode": "0x1d",
+ "EventName": "wr_ddr_64b",
"BriefDescription": "The number of write operations sent by HHA to DDRC which size is 64 bytes",
"PublicDescription": "The number of write operations sent by HHA to DDRC which size is 64 bytes",
"Unit": "hisi_sccl,hha"
},
{
- "EventCode": "0x1e",
- "EventName": "uncore_hisi_hha.rd_ddr_128b",
+ "ConfigCode": "0x1e",
+ "EventName": "rd_ddr_128b",
"BriefDescription": "The number of read operations sent by HHA to DDRC which size is 128 bytes",
"PublicDescription": "The number of read operations sent by HHA to DDRC which size is 128 bytes",
"Unit": "hisi_sccl,hha"
},
{
- "EventCode": "0x1f",
- "EventName": "uncore_hisi_hha.wr_ddr_128b",
+ "ConfigCode": "0x1f",
+ "EventName": "wr_ddr_128b",
"BriefDescription": "The number of write operations sent by HHA to DDRC which size is 128 bytes",
"PublicDescription": "The number of write operations sent by HHA to DDRC which size is 128 bytes",
"Unit": "hisi_sccl,hha"
},
{
- "EventCode": "0x20",
- "EventName": "uncore_hisi_hha.spill_num",
+ "ConfigCode": "0x20",
+ "EventName": "spill_num",
"BriefDescription": "Count of the number of spill operations that the HHA has sent",
"PublicDescription": "Count of the number of spill operations that the HHA has sent",
"Unit": "hisi_sccl,hha"
},
{
- "EventCode": "0x21",
- "EventName": "uncore_hisi_hha.spill_success",
+ "ConfigCode": "0x21",
+ "EventName": "spill_success",
"BriefDescription": "Count of the number of successful spill operations that the HHA has sent",
"PublicDescription": "Count of the number of successful spill operations that the HHA has sent",
"Unit": "hisi_sccl,hha"
+ },
+ {
+ "ConfigCode": "0x23",
+ "EventName": "bi_num",
+ "Unit": "hisi_sccl,hha"
+ },
+ {
+ "ConfigCode": "0x32",
+ "EventName": "mediated_num",
+ "Unit": "hisi_sccl,hha"
+ },
+ {
+ "ConfigCode": "0x33",
+ "EventName": "tx_snp_num",
+ "Unit": "hisi_sccl,hha"
+ },
+ {
+ "ConfigCode": "0x34",
+ "EventName": "tx_snp_outer",
+ "Unit": "hisi_sccl,hha"
+ },
+ {
+ "ConfigCode": "0x35",
+ "EventName": "tx_snp_ccix",
+ "Unit": "hisi_sccl,hha"
+ },
+ {
+ "ConfigCode": "0x38",
+ "EventName": "rx_snprspdata",
+ "Unit": "hisi_sccl,hha"
+ },
+ {
+ "ConfigCode": "0x3c",
+ "EventName": "rx_snprsp_outer",
+ "Unit": "hisi_sccl,hha"
+ },
+ {
+ "ConfigCode": "0x40",
+ "EventName": "sdir-lookup",
+ "Unit": "hisi_sccl,hha"
+ },
+ {
+ "ConfigCode": "0x41",
+ "EventName": "edir-lookup",
+ "Unit": "hisi_sccl,hha"
+ },
+ {
+ "ConfigCode": "0x42",
+ "EventName": "sdir-hit",
+ "Unit": "hisi_sccl,hha"
+ },
+ {
+ "ConfigCode": "0x43",
+ "EventName": "edir-hit",
+ "Unit": "hisi_sccl,hha"
+ },
+ {
+ "ConfigCode": "0x4c",
+ "EventName": "sdir-home-migrate",
+ "Unit": "hisi_sccl,hha"
+ },
+ {
+ "ConfigCode": "0x4d",
+ "EventName": "edir-home-migrate",
+ "Unit": "hisi_sccl,hha"
}
]
diff --git a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-l3c.json b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-l3c.json
index 67ab19e8cf3a..e3479b65be9a 100644
--- a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-l3c.json
+++ b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-l3c.json
@@ -1,91 +1,91 @@
[
{
- "EventCode": "0x00",
- "EventName": "uncore_hisi_l3c.rd_cpipe",
+ "ConfigCode": "0x00",
+ "EventName": "rd_cpipe",
"BriefDescription": "Total read accesses",
"PublicDescription": "Total read accesses",
"Unit": "hisi_sccl,l3c"
},
{
- "EventCode": "0x01",
- "EventName": "uncore_hisi_l3c.wr_cpipe",
+ "ConfigCode": "0x01",
+ "EventName": "wr_cpipe",
"BriefDescription": "Total write accesses",
"PublicDescription": "Total write accesses",
"Unit": "hisi_sccl,l3c"
},
{
- "EventCode": "0x02",
- "EventName": "uncore_hisi_l3c.rd_hit_cpipe",
+ "ConfigCode": "0x02",
+ "EventName": "rd_hit_cpipe",
"BriefDescription": "Total read hits",
"PublicDescription": "Total read hits",
"Unit": "hisi_sccl,l3c"
},
{
- "EventCode": "0x03",
- "EventName": "uncore_hisi_l3c.wr_hit_cpipe",
+ "ConfigCode": "0x03",
+ "EventName": "wr_hit_cpipe",
"BriefDescription": "Total write hits",
"PublicDescription": "Total write hits",
"Unit": "hisi_sccl,l3c"
},
{
- "EventCode": "0x04",
- "EventName": "uncore_hisi_l3c.victim_num",
+ "ConfigCode": "0x04",
+ "EventName": "victim_num",
"BriefDescription": "l3c precharge commands",
"PublicDescription": "l3c precharge commands",
"Unit": "hisi_sccl,l3c"
},
{
- "EventCode": "0x20",
- "EventName": "uncore_hisi_l3c.rd_spipe",
+ "ConfigCode": "0x20",
+ "EventName": "rd_spipe",
"BriefDescription": "Count of the number of read lines that come from this cluster of CPU core in spipe",
"PublicDescription": "Count of the number of read lines that come from this cluster of CPU core in spipe",
"Unit": "hisi_sccl,l3c"
},
{
- "EventCode": "0x21",
- "EventName": "uncore_hisi_l3c.wr_spipe",
+ "ConfigCode": "0x21",
+ "EventName": "wr_spipe",
"BriefDescription": "Count of the number of write lines that come from this cluster of CPU core in spipe",
"PublicDescription": "Count of the number of write lines that come from this cluster of CPU core in spipe",
"Unit": "hisi_sccl,l3c"
},
{
- "EventCode": "0x22",
- "EventName": "uncore_hisi_l3c.rd_hit_spipe",
+ "ConfigCode": "0x22",
+ "EventName": "rd_hit_spipe",
"BriefDescription": "Count of the number of read lines that hits in spipe of this L3C",
"PublicDescription": "Count of the number of read lines that hits in spipe of this L3C",
"Unit": "hisi_sccl,l3c"
},
{
- "EventCode": "0x23",
- "EventName": "uncore_hisi_l3c.wr_hit_spipe",
+ "ConfigCode": "0x23",
+ "EventName": "wr_hit_spipe",
"BriefDescription": "Count of the number of write lines that hits in spipe of this L3C",
"PublicDescription": "Count of the number of write lines that hits in spipe of this L3C",
"Unit": "hisi_sccl,l3c"
},
{
- "EventCode": "0x29",
- "EventName": "uncore_hisi_l3c.back_invalid",
+ "ConfigCode": "0x29",
+ "EventName": "back_invalid",
"BriefDescription": "Count of the number of L3C back invalid operations",
"PublicDescription": "Count of the number of L3C back invalid operations",
"Unit": "hisi_sccl,l3c"
},
{
- "EventCode": "0x40",
- "EventName": "uncore_hisi_l3c.retry_cpu",
+ "ConfigCode": "0x40",
+ "EventName": "retry_cpu",
"BriefDescription": "Count of the number of retry that L3C suppresses the CPU operations",
"PublicDescription": "Count of the number of retry that L3C suppresses the CPU operations",
"Unit": "hisi_sccl,l3c"
},
{
- "EventCode": "0x41",
- "EventName": "uncore_hisi_l3c.retry_ring",
+ "ConfigCode": "0x41",
+ "EventName": "retry_ring",
"BriefDescription": "Count of the number of retry that L3C suppresses the ring operations",
"PublicDescription": "Count of the number of retry that L3C suppresses the ring operations",
"Unit": "hisi_sccl,l3c"
},
{
- "EventCode": "0x42",
- "EventName": "uncore_hisi_l3c.prefetch_drop",
+ "ConfigCode": "0x42",
+ "EventName": "prefetch_drop",
"BriefDescription": "Count of the number of prefetch drops from this L3C",
"PublicDescription": "Count of the number of prefetch drops from this L3C",
"Unit": "hisi_sccl,l3c"
diff --git a/tools/perf/pmu-events/arch/test/test_soc/sys/uncore.json b/tools/perf/pmu-events/arch/test/test_soc/sys/uncore.json
index 0f681a6e10ea..c7e7528db315 100644
--- a/tools/perf/pmu-events/arch/test/test_soc/sys/uncore.json
+++ b/tools/perf/pmu-events/arch/test/test_soc/sys/uncore.json
@@ -6,4 +6,11 @@
"Unit": "sys_ddr_pmu",
"Compat": "v8"
},
+ {
+ "BriefDescription": "ccn read-cycles event",
+ "ConfigCode": "0x2c",
+ "EventName": "sys_ccn_pmu.read_cycles",
+ "Unit": "sys_ccn_pmu",
+ "Compat": "0x01"
+ }
]
diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c
index 7c887d37b893..b7c8aae6bcf1 100644
--- a/tools/perf/pmu-events/jevents.c
+++ b/tools/perf/pmu-events/jevents.c
@@ -45,6 +45,7 @@
#include <sys/resource.h> /* getrlimit */
#include <ftw.h>
#include <sys/stat.h>
+#include <linux/compiler.h>
#include <linux/list.h>
#include "jsmn.h"
#include "json.h"
@@ -470,7 +471,7 @@ static void free_arch_std_events(void)
}
}
-static int save_arch_std_events(void *data, struct json_event *je)
+static int save_arch_std_events(void *data __maybe_unused, struct json_event *je)
{
struct event_struct *es;
@@ -575,10 +576,12 @@ static int json_events(const char *fn,
struct json_event je = {};
char *arch_std = NULL;
unsigned long long eventcode = 0;
+ unsigned long long configcode = 0;
struct msrmap *msr = NULL;
jsmntok_t *msrval = NULL;
jsmntok_t *precise = NULL;
jsmntok_t *obj = tok++;
+ bool configcode_present = false;
EXPECT(obj->type == JSMN_OBJECT, obj, "expected object");
for (j = 0; j < obj->size; j += 2) {
@@ -601,6 +604,12 @@ static int json_events(const char *fn,
addfield(map, &code, "", "", val);
eventcode |= strtoul(code, NULL, 0);
free(code);
+ } else if (json_streq(map, field, "ConfigCode")) {
+ char *code = NULL;
+ addfield(map, &code, "", "", val);
+ configcode |= strtoul(code, NULL, 0);
+ free(code);
+ configcode_present = true;
} else if (json_streq(map, field, "ExtSel")) {
char *code = NULL;
addfield(map, &code, "", "", val);
@@ -682,7 +691,10 @@ static int json_events(const char *fn,
addfield(map, &extra_desc, " ",
"(Precise event)", NULL);
}
- snprintf(buf, sizeof buf, "event=%#llx", eventcode);
+ if (configcode_present)
+ snprintf(buf, sizeof buf, "config=%#llx", configcode);
+ else
+ snprintf(buf, sizeof buf, "event=%#llx", eventcode);
addfield(map, &event, ",", buf, NULL);
if (je.desc && extra_desc)
addfield(map, &je.desc, " ", extra_desc, NULL);
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 9b4a765e4b73..f439bd49da19 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -606,7 +606,8 @@ static int do_test_code_reading(bool try_kcore)
}
ret = perf_event__synthesize_thread_map(NULL, threads,
- perf_event__process, machine, false);
+ perf_event__process, machine,
+ true, false);
if (ret < 0) {
pr_debug("perf_event__synthesize_thread_map failed\n");
goto out_err;
diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c
index 4d01051951cd..f1d8411fce12 100644
--- a/tools/perf/tests/expr.c
+++ b/tools/perf/tests/expr.c
@@ -1,11 +1,57 @@
// SPDX-License-Identifier: GPL-2.0
#include "util/debug.h"
#include "util/expr.h"
+#include "util/smt.h"
#include "tests.h"
#include <stdlib.h>
#include <string.h>
#include <linux/zalloc.h>
+static int test_ids_union(void)
+{
+ struct hashmap *ids1, *ids2;
+
+ /* Empty union. */
+ ids1 = ids__new();
+ TEST_ASSERT_VAL("ids__new", ids1);
+ ids2 = ids__new();
+ TEST_ASSERT_VAL("ids__new", ids2);
+
+ ids1 = ids__union(ids1, ids2);
+ TEST_ASSERT_EQUAL("union", (int)hashmap__size(ids1), 0);
+
+ /* Union {foo, bar} against {}. */
+ ids2 = ids__new();
+ TEST_ASSERT_VAL("ids__new", ids2);
+
+ TEST_ASSERT_EQUAL("ids__insert", ids__insert(ids1, strdup("foo"), NULL), 0);
+ TEST_ASSERT_EQUAL("ids__insert", ids__insert(ids1, strdup("bar"), NULL), 0);
+
+ ids1 = ids__union(ids1, ids2);
+ TEST_ASSERT_EQUAL("union", (int)hashmap__size(ids1), 2);
+
+ /* Union {foo, bar} against {foo}. */
+ ids2 = ids__new();
+ TEST_ASSERT_VAL("ids__new", ids2);
+ TEST_ASSERT_EQUAL("ids__insert", ids__insert(ids2, strdup("foo"), NULL), 0);
+
+ ids1 = ids__union(ids1, ids2);
+ TEST_ASSERT_EQUAL("union", (int)hashmap__size(ids1), 2);
+
+ /* Union {foo, bar} against {bar,baz}. */
+ ids2 = ids__new();
+ TEST_ASSERT_VAL("ids__new", ids2);
+ TEST_ASSERT_EQUAL("ids__insert", ids__insert(ids2, strdup("bar"), NULL), 0);
+ TEST_ASSERT_EQUAL("ids__insert", ids__insert(ids2, strdup("baz"), NULL), 0);
+
+ ids1 = ids__union(ids1, ids2);
+ TEST_ASSERT_EQUAL("union", (int)hashmap__size(ids1), 3);
+
+ ids__free(ids1);
+
+ return 0;
+}
+
static int test(struct expr_parse_ctx *ctx, const char *e, double val2)
{
double val;
@@ -22,67 +68,89 @@ int test__expr(struct test *t __maybe_unused, int subtest __maybe_unused)
const char *p;
double val;
int ret;
- struct expr_parse_ctx ctx;
-
- expr__ctx_init(&ctx);
- expr__add_id_val(&ctx, strdup("FOO"), 1);
- expr__add_id_val(&ctx, strdup("BAR"), 2);
-
- ret = test(&ctx, "1+1", 2);
- ret |= test(&ctx, "FOO+BAR", 3);
- ret |= test(&ctx, "(BAR/2)%2", 1);
- ret |= test(&ctx, "1 - -4", 5);
- ret |= test(&ctx, "(FOO-1)*2 + (BAR/2)%2 - -4", 5);
- ret |= test(&ctx, "1-1 | 1", 1);
- ret |= test(&ctx, "1-1 & 1", 0);
- ret |= test(&ctx, "min(1,2) + 1", 2);
- ret |= test(&ctx, "max(1,2) + 1", 3);
- ret |= test(&ctx, "1+1 if 3*4 else 0", 2);
- ret |= test(&ctx, "1.1 + 2.1", 3.2);
- ret |= test(&ctx, ".1 + 2.", 2.1);
- ret |= test(&ctx, "d_ratio(1, 2)", 0.5);
- ret |= test(&ctx, "d_ratio(2.5, 0)", 0);
- ret |= test(&ctx, "1.1 < 2.2", 1);
- ret |= test(&ctx, "2.2 > 1.1", 1);
- ret |= test(&ctx, "1.1 < 1.1", 0);
- ret |= test(&ctx, "2.2 > 2.2", 0);
- ret |= test(&ctx, "2.2 < 1.1", 0);
- ret |= test(&ctx, "1.1 > 2.2", 0);
-
- if (ret)
+ struct expr_parse_ctx *ctx;
+
+ TEST_ASSERT_EQUAL("ids_union", test_ids_union(), 0);
+
+ ctx = expr__ctx_new();
+ TEST_ASSERT_VAL("expr__ctx_new", ctx);
+ expr__add_id_val(ctx, strdup("FOO"), 1);
+ expr__add_id_val(ctx, strdup("BAR"), 2);
+
+ ret = test(ctx, "1+1", 2);
+ ret |= test(ctx, "FOO+BAR", 3);
+ ret |= test(ctx, "(BAR/2)%2", 1);
+ ret |= test(ctx, "1 - -4", 5);
+ ret |= test(ctx, "(FOO-1)*2 + (BAR/2)%2 - -4", 5);
+ ret |= test(ctx, "1-1 | 1", 1);
+ ret |= test(ctx, "1-1 & 1", 0);
+ ret |= test(ctx, "min(1,2) + 1", 2);
+ ret |= test(ctx, "max(1,2) + 1", 3);
+ ret |= test(ctx, "1+1 if 3*4 else 0", 2);
+ ret |= test(ctx, "1.1 + 2.1", 3.2);
+ ret |= test(ctx, ".1 + 2.", 2.1);
+ ret |= test(ctx, "d_ratio(1, 2)", 0.5);
+ ret |= test(ctx, "d_ratio(2.5, 0)", 0);
+ ret |= test(ctx, "1.1 < 2.2", 1);
+ ret |= test(ctx, "2.2 > 1.1", 1);
+ ret |= test(ctx, "1.1 < 1.1", 0);
+ ret |= test(ctx, "2.2 > 2.2", 0);
+ ret |= test(ctx, "2.2 < 1.1", 0);
+ ret |= test(ctx, "1.1 > 2.2", 0);
+
+ if (ret) {
+ expr__ctx_free(ctx);
return ret;
+ }
p = "FOO/0";
- ret = expr__parse(&val, &ctx, p, 1);
+ ret = expr__parse(&val, ctx, p, 1);
TEST_ASSERT_VAL("division by zero", ret == -1);
p = "BAR/";
- ret = expr__parse(&val, &ctx, p, 1);
+ ret = expr__parse(&val, ctx, p, 1);
TEST_ASSERT_VAL("missing operand", ret == -1);
- expr__ctx_clear(&ctx);
- TEST_ASSERT_VAL("find other",
- expr__find_other("FOO + BAR + BAZ + BOZO", "FOO",
- &ctx, 1) == 0);
- TEST_ASSERT_VAL("find other", hashmap__size(&ctx.ids) == 3);
- TEST_ASSERT_VAL("find other", hashmap__find(&ctx.ids, "BAR",
+ expr__ctx_clear(ctx);
+ TEST_ASSERT_VAL("find ids",
+ expr__find_ids("FOO + BAR + BAZ + BOZO", "FOO",
+ ctx, 1) == 0);
+ TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 3);
+ TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "BAR",
(void **)&val_ptr));
- TEST_ASSERT_VAL("find other", hashmap__find(&ctx.ids, "BAZ",
+ TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "BAZ",
(void **)&val_ptr));
- TEST_ASSERT_VAL("find other", hashmap__find(&ctx.ids, "BOZO",
+ TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "BOZO",
(void **)&val_ptr));
- expr__ctx_clear(&ctx);
- TEST_ASSERT_VAL("find other",
- expr__find_other("EVENT1\\,param\\=?@ + EVENT2\\,param\\=?@",
- NULL, &ctx, 3) == 0);
- TEST_ASSERT_VAL("find other", hashmap__size(&ctx.ids) == 2);
- TEST_ASSERT_VAL("find other", hashmap__find(&ctx.ids, "EVENT1,param=3/",
+ expr__ctx_clear(ctx);
+ TEST_ASSERT_VAL("find ids",
+ expr__find_ids("EVENT1\\,param\\=?@ + EVENT2\\,param\\=?@",
+ NULL, ctx, 3) == 0);
+ TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 2);
+ TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "EVENT1,param=3/",
(void **)&val_ptr));
- TEST_ASSERT_VAL("find other", hashmap__find(&ctx.ids, "EVENT2,param=3/",
+ TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "EVENT2,param=3/",
(void **)&val_ptr));
- expr__ctx_clear(&ctx);
+ /* Only EVENT1 or EVENT2 need be measured depending on the value of smt_on. */
+ expr__ctx_clear(ctx);
+ TEST_ASSERT_VAL("find ids",
+ expr__find_ids("EVENT1 if #smt_on else EVENT2",
+ NULL, ctx, 0) == 0);
+ TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 1);
+ TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids,
+ smt_on() ? "EVENT1" : "EVENT2",
+ (void **)&val_ptr));
+
+ /* The expression is a constant 1.0 without needing to evaluate EVENT1. */
+ expr__ctx_clear(ctx);
+ TEST_ASSERT_VAL("find ids",
+ expr__find_ids("1.0 if EVENT1 > 100.0 else 1.0",
+ NULL, ctx, 0) == 0);
+ TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 0);
+
+ expr__ctx_free(ctx);
return 0;
}
diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c
index 8d9d4cbff76d..6f2da7a72f67 100644
--- a/tools/perf/tests/mmap-thread-lookup.c
+++ b/tools/perf/tests/mmap-thread-lookup.c
@@ -135,7 +135,7 @@ static int synth_all(struct machine *machine)
{
return perf_event__synthesize_threads(NULL,
perf_event__process,
- machine, 0, 1);
+ machine, 1, 0, 1);
}
static int synth_process(struct machine *machine)
@@ -147,7 +147,7 @@ static int synth_process(struct machine *machine)
err = perf_event__synthesize_thread_map(NULL, map,
perf_event__process,
- machine, 0);
+ machine, 1, 0);
perf_thread_map__put(map);
return err;
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index fd3556cc9ad4..8875e388563e 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -605,7 +605,7 @@ static int test__checkterms_simple(struct list_head *terms)
TEST_ASSERT_VAL("wrong type val",
term->type_val == PARSE_EVENTS__TERM_TYPE_NUM);
TEST_ASSERT_VAL("wrong val", term->val.num == 10);
- TEST_ASSERT_VAL("wrong config", !term->config);
+ TEST_ASSERT_VAL("wrong config", !strcmp(term->config, "config"));
/* config1 */
term = list_entry(term->list.next, struct parse_events_term, list);
@@ -614,7 +614,7 @@ static int test__checkterms_simple(struct list_head *terms)
TEST_ASSERT_VAL("wrong type val",
term->type_val == PARSE_EVENTS__TERM_TYPE_NUM);
TEST_ASSERT_VAL("wrong val", term->val.num == 1);
- TEST_ASSERT_VAL("wrong config", !term->config);
+ TEST_ASSERT_VAL("wrong config", !strcmp(term->config, "config1"));
/* config2=3 */
term = list_entry(term->list.next, struct parse_events_term, list);
@@ -623,7 +623,7 @@ static int test__checkterms_simple(struct list_head *terms)
TEST_ASSERT_VAL("wrong type val",
term->type_val == PARSE_EVENTS__TERM_TYPE_NUM);
TEST_ASSERT_VAL("wrong val", term->val.num == 3);
- TEST_ASSERT_VAL("wrong config", !term->config);
+ TEST_ASSERT_VAL("wrong config", !strcmp(term->config, "config2"));
/* umask=1*/
term = list_entry(term->list.next, struct parse_events_term, list);
@@ -661,7 +661,7 @@ static int test__checkterms_simple(struct list_head *terms)
TEST_ASSERT_VAL("wrong type val",
term->type_val == PARSE_EVENTS__TERM_TYPE_NUM);
TEST_ASSERT_VAL("wrong val", term->val.num == 0xead);
- TEST_ASSERT_VAL("wrong config", !term->config);
+ TEST_ASSERT_VAL("wrong config", !strcmp(term->config, "config"));
return 0;
}
diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c
index 43743cf719ef..d3534960ed25 100644
--- a/tools/perf/tests/pmu-events.c
+++ b/tools/perf/tests/pmu-events.c
@@ -67,7 +67,7 @@ static const struct perf_pmu_test_event segment_reg_loads_any = {
.desc = "Number of segment register loads",
.topic = "other",
},
- .alias_str = "umask=0x80,(null)=0x30d40,event=0x6",
+ .alias_str = "umask=0x80,period=0x30d40,event=0x6",
.alias_long_desc = "Number of segment register loads",
};
@@ -78,7 +78,7 @@ static const struct perf_pmu_test_event dispatch_blocked_any = {
.desc = "Memory cluster signals to block micro-op dispatch for any reason",
.topic = "other",
},
- .alias_str = "umask=0x20,(null)=0x30d40,event=0x9",
+ .alias_str = "umask=0x20,period=0x30d40,event=0x9",
.alias_long_desc = "Memory cluster signals to block micro-op dispatch for any reason",
};
@@ -89,7 +89,7 @@ static const struct perf_pmu_test_event eist_trans = {
.desc = "Number of Enhanced Intel SpeedStep(R) Technology (EIST) transitions",
.topic = "other",
},
- .alias_str = "umask=0,(null)=0x30d40,event=0x3a",
+ .alias_str = "umask=0,period=0x30d40,event=0x3a",
.alias_long_desc = "Number of Enhanced Intel SpeedStep(R) Technology (EIST) transitions",
};
@@ -146,7 +146,7 @@ static const struct perf_pmu_test_event unc_cbo_xsnp_response_miss_eviction = {
static const struct perf_pmu_test_event uncore_hisi_l3c_rd_hit_cpipe = {
.event = {
.name = "uncore_hisi_l3c.rd_hit_cpipe",
- .event = "event=0x2",
+ .event = "event=0x7",
.desc = "Total read hits. Unit: hisi_sccl,l3c ",
.topic = "uncore",
.long_desc = "Total read hits",
@@ -208,8 +208,23 @@ static const struct perf_pmu_test_event sys_ddr_pmu_write_cycles = {
.matching_pmu = "uncore_sys_ddr_pmu",
};
+static const struct perf_pmu_test_event sys_ccn_pmu_read_cycles = {
+ .event = {
+ .name = "sys_ccn_pmu.read_cycles",
+ .event = "config=0x2c",
+ .desc = "ccn read-cycles event. Unit: uncore_sys_ccn_pmu ",
+ .topic = "uncore",
+ .pmu = "uncore_sys_ccn_pmu",
+ .compat = "0x01",
+ },
+ .alias_str = "config=0x2c",
+ .alias_long_desc = "ccn read-cycles event. Unit: uncore_sys_ccn_pmu ",
+ .matching_pmu = "uncore_sys_ccn_pmu",
+};
+
static const struct perf_pmu_test_event *sys_events[] = {
&sys_ddr_pmu_write_cycles,
+ &sys_ccn_pmu_read_cycles,
NULL
};
@@ -255,6 +270,24 @@ static struct pmu_event *__test_pmu_get_sys_events_table(void)
static int compare_pmu_events(struct pmu_event *e1, const struct pmu_event *e2)
{
+ if (!is_same(e1->name, e2->name)) {
+ pr_debug2("testing event e1 %s: mismatched name string, %s vs %s\n",
+ e1->name, e1->name, e2->name);
+ return -1;
+ }
+
+ if (!is_same(e1->compat, e2->compat)) {
+ pr_debug2("testing event e1 %s: mismatched compat string, %s vs %s\n",
+ e1->name, e1->compat, e2->compat);
+ return -1;
+ }
+
+ if (!is_same(e1->event, e2->event)) {
+ pr_debug2("testing event e1 %s: mismatched event, %s vs %s\n",
+ e1->name, e1->event, e2->event);
+ return -1;
+ }
+
if (!is_same(e1->desc, e2->desc)) {
pr_debug2("testing event e1 %s: mismatched desc, %s vs %s\n",
e1->name, e1->desc, e2->desc);
@@ -273,6 +306,12 @@ static int compare_pmu_events(struct pmu_event *e1, const struct pmu_event *e2)
return -1;
}
+ if (!is_same(e1->pmu, e2->pmu)) {
+ pr_debug2("testing event e1 %s: mismatched pmu string, %s vs %s\n",
+ e1->name, e1->pmu, e2->pmu);
+ return -1;
+ }
+
if (!is_same(e1->unit, e2->unit)) {
pr_debug2("testing event e1 %s: mismatched unit, %s vs %s\n",
e1->name, e1->unit, e2->unit);
@@ -285,6 +324,12 @@ static int compare_pmu_events(struct pmu_event *e1, const struct pmu_event *e2)
return -1;
}
+ if (!is_same(e1->aggr_mode, e2->aggr_mode)) {
+ pr_debug2("testing event e1 %s: mismatched aggr_mode, %s vs %s\n",
+ e1->name, e1->aggr_mode, e2->aggr_mode);
+ return -1;
+ }
+
if (!is_same(e1->metric_expr, e2->metric_expr)) {
pr_debug2("testing event e1 %s: mismatched metric_expr, %s vs %s\n",
e1->name, e1->metric_expr, e2->metric_expr);
@@ -297,21 +342,21 @@ static int compare_pmu_events(struct pmu_event *e1, const struct pmu_event *e2)
return -1;
}
+ if (!is_same(e1->metric_group, e2->metric_group)) {
+ pr_debug2("testing event e1 %s: mismatched metric_group, %s vs %s\n",
+ e1->name, e1->metric_group, e2->metric_group);
+ return -1;
+ }
+
if (!is_same(e1->deprecated, e2->deprecated)) {
pr_debug2("testing event e1 %s: mismatched deprecated, %s vs %s\n",
e1->name, e1->deprecated, e2->deprecated);
return -1;
}
- if (!is_same(e1->pmu, e2->pmu)) {
- pr_debug2("testing event e1 %s: mismatched pmu string, %s vs %s\n",
- e1->name, e1->pmu, e2->pmu);
- return -1;
- }
-
- if (!is_same(e1->compat, e2->compat)) {
- pr_debug2("testing event e1 %s: mismatched compat string, %s vs %s\n",
- e1->name, e1->compat, e2->compat);
+ if (!is_same(e1->metric_constraint, e2->metric_constraint)) {
+ pr_debug2("testing event e1 %s: mismatched metric_constant, %s vs %s\n",
+ e1->name, e1->metric_constraint, e2->metric_constraint);
return -1;
}
@@ -647,6 +692,16 @@ static struct perf_pmu_test_pmu test_pmus[] = {
&sys_ddr_pmu_write_cycles,
},
},
+ {
+ .pmu = {
+ .name = (char *)"uncore_sys_ccn_pmu4",
+ .is_uncore = 1,
+ .id = (char *)"0x01",
+ },
+ .aliases = {
+ &sys_ccn_pmu_read_cycles,
+ },
+ },
};
/* Test that aliases generated are as expected */
@@ -781,7 +836,7 @@ static int resolve_metric_simple(struct expr_parse_ctx *pctx,
do {
all = true;
- hashmap__for_each_entry_safe((&pctx->ids), cur, cur_tmp, bkt) {
+ hashmap__for_each_entry_safe(pctx->ids, cur, cur_tmp, bkt) {
struct metric_ref *ref;
struct pmu_event *pe;
@@ -811,7 +866,7 @@ static int resolve_metric_simple(struct expr_parse_ctx *pctx,
ref->metric_expr = pe->metric_expr;
list_add_tail(&metric->list, compound_list);
- rc = expr__find_other(pe->metric_expr, NULL, pctx, 0);
+ rc = expr__find_ids(pe->metric_expr, NULL, pctx, 0);
if (rc)
goto out_err;
break; /* The hashmap has been modified, so restart */
@@ -835,9 +890,14 @@ static int test_parsing(void)
struct pmu_event *pe;
int i, j, k;
int ret = 0;
- struct expr_parse_ctx ctx;
+ struct expr_parse_ctx *ctx;
double result;
+ ctx = expr__ctx_new();
+ if (!ctx) {
+ pr_debug("expr__ctx_new failed");
+ return TEST_FAIL;
+ }
i = 0;
for (;;) {
map = &pmu_events_map[i++];
@@ -855,15 +915,14 @@ static int test_parsing(void)
break;
if (!pe->metric_expr)
continue;
- expr__ctx_init(&ctx);
- if (expr__find_other(pe->metric_expr, NULL, &ctx, 0)
- < 0) {
- expr_failure("Parse other failed", map, pe);
+ expr__ctx_clear(ctx);
+ if (expr__find_ids(pe->metric_expr, NULL, ctx, 0) < 0) {
+ expr_failure("Parse find ids failed", map, pe);
ret++;
continue;
}
- if (resolve_metric_simple(&ctx, &compound_list, map,
+ if (resolve_metric_simple(ctx, &compound_list, map,
pe->metric_name)) {
expr_failure("Could not resolve metrics", map, pe);
ret++;
@@ -876,27 +935,27 @@ static int test_parsing(void)
* make them unique.
*/
k = 1;
- hashmap__for_each_entry((&ctx.ids), cur, bkt)
- expr__add_id_val(&ctx, strdup(cur->key), k++);
+ hashmap__for_each_entry(ctx->ids, cur, bkt)
+ expr__add_id_val(ctx, strdup(cur->key), k++);
- hashmap__for_each_entry((&ctx.ids), cur, bkt) {
+ hashmap__for_each_entry(ctx->ids, cur, bkt) {
if (check_parse_cpu(cur->key, map == cpus_map,
pe))
ret++;
}
list_for_each_entry_safe(metric, tmp, &compound_list, list) {
- expr__add_ref(&ctx, &metric->metric_ref);
+ expr__add_ref(ctx, &metric->metric_ref);
free(metric);
}
- if (expr__parse(&result, &ctx, pe->metric_expr, 0)) {
+ if (expr__parse(&result, ctx, pe->metric_expr, 0)) {
expr_failure("Parse failed", map, pe);
ret++;
}
- expr__ctx_clear(&ctx);
}
}
+ expr__ctx_free(ctx);
/* TODO: fail when not ok */
exit:
return ret == 0 ? TEST_OK : TEST_SKIP;
@@ -916,7 +975,7 @@ static struct test_metric metrics[] = {
static int metric_parse_fake(const char *str)
{
- struct expr_parse_ctx ctx;
+ struct expr_parse_ctx *ctx;
struct hashmap_entry *cur;
double result;
int ret = -1;
@@ -925,9 +984,13 @@ static int metric_parse_fake(const char *str)
pr_debug("parsing '%s'\n", str);
- expr__ctx_init(&ctx);
- if (expr__find_other(str, NULL, &ctx, 0) < 0) {
- pr_err("expr__find_other failed\n");
+ ctx = expr__ctx_new();
+ if (!ctx) {
+ pr_debug("expr__ctx_new failed");
+ return TEST_FAIL;
+ }
+ if (expr__find_ids(str, NULL, ctx, 0) < 0) {
+ pr_err("expr__find_ids failed\n");
return -1;
}
@@ -937,23 +1000,23 @@ static int metric_parse_fake(const char *str)
* make them unique.
*/
i = 1;
- hashmap__for_each_entry((&ctx.ids), cur, bkt)
- expr__add_id_val(&ctx, strdup(cur->key), i++);
+ hashmap__for_each_entry(ctx->ids, cur, bkt)
+ expr__add_id_val(ctx, strdup(cur->key), i++);
- hashmap__for_each_entry((&ctx.ids), cur, bkt) {
+ hashmap__for_each_entry(ctx->ids, cur, bkt) {
if (check_parse_fake(cur->key)) {
pr_err("check_parse_fake failed\n");
goto out;
}
}
- if (expr__parse(&result, &ctx, str, 0))
+ if (expr__parse(&result, ctx, str, 0))
pr_err("expr__parse failed\n");
else
ret = 0;
out:
- expr__ctx_clear(&ctx);
+ expr__ctx_free(ctx);
return ret;
}
diff --git a/tools/perf/tests/shell/stat_all_metricgroups.sh b/tools/perf/tests/shell/stat_all_metricgroups.sh
new file mode 100755
index 000000000000..de24d374ce24
--- /dev/null
+++ b/tools/perf/tests/shell/stat_all_metricgroups.sh
@@ -0,0 +1,12 @@
+#!/bin/sh
+# perf all metricgroups test
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+for m in $(perf list --raw-dump metricgroups); do
+ echo "Testing $m"
+ perf stat -M "$m" true
+done
+
+exit 0
diff --git a/tools/perf/tests/shell/stat_all_metrics.sh b/tools/perf/tests/shell/stat_all_metrics.sh
new file mode 100755
index 000000000000..7f4ba3cad632
--- /dev/null
+++ b/tools/perf/tests/shell/stat_all_metrics.sh
@@ -0,0 +1,22 @@
+#!/bin/sh
+# perf all metrics test
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+for m in $(perf list --raw-dump metrics); do
+ echo "Testing $m"
+ result=$(perf stat -M "$m" true 2>&1)
+ if [[ ! "$result" =~ "$m" ]] && [[ ! "$result" =~ "<not supported>" ]]; then
+ # We failed to see the metric and the events are support. Possibly the
+ # workload was too small so retry with something longer.
+ result=$(perf stat -M "$m" perf bench internals synthesize 2>&1)
+ if [[ ! "$result" =~ "$m" ]]; then
+ echo "Metric '$m' not printed in:"
+ echo "$result"
+ exit 1
+ fi
+ fi
+done
+
+exit 0
diff --git a/tools/perf/tests/shell/stat_all_pmu.sh b/tools/perf/tests/shell/stat_all_pmu.sh
new file mode 100755
index 000000000000..2de7fd0394fd
--- /dev/null
+++ b/tools/perf/tests/shell/stat_all_pmu.sh
@@ -0,0 +1,22 @@
+#!/bin/sh
+# perf all PMU test
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+for p in $(perf list --raw-dump pmu); do
+ echo "Testing $p"
+ result=$(perf stat -e "$p" true 2>&1)
+ if [[ ! "$result" =~ "$p" ]] && [[ ! "$result" =~ "<not supported>" ]]; then
+ # We failed to see the event and it is supported. Possibly the workload was
+ # too small so retry with something longer.
+ result=$(perf stat -e "$p" perf bench internals synthesize 2>&1)
+ if [[ ! "$result" =~ "$p" ]]; then
+ echo "Event '$p' not printed in:"
+ echo "$result"
+ exit 1
+ fi
+ fi
+done
+
+exit 0
diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c
index 193b7c91b4e2..4f884aabc7f4 100644
--- a/tools/perf/tests/vmlinux-kallsyms.c
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -3,6 +3,7 @@
#include <linux/rbtree.h>
#include <inttypes.h>
#include <string.h>
+#include <ctype.h>
#include <stdlib.h>
#include "dso.h"
#include "map.h"
@@ -14,6 +15,102 @@
#define UM(x) kallsyms_map->unmap_ip(kallsyms_map, (x))
+static bool is_ignored_symbol(const char *name, char type)
+{
+ /* Symbol names that exactly match to the following are ignored.*/
+ static const char * const ignored_symbols[] = {
+ /*
+ * Symbols which vary between passes. Passes 1 and 2 must have
+ * identical symbol lists. The kallsyms_* symbols below are
+ * only added after pass 1, they would be included in pass 2
+ * when --all-symbols is specified so exclude them to get a
+ * stable symbol list.
+ */
+ "kallsyms_addresses",
+ "kallsyms_offsets",
+ "kallsyms_relative_base",
+ "kallsyms_num_syms",
+ "kallsyms_names",
+ "kallsyms_markers",
+ "kallsyms_token_table",
+ "kallsyms_token_index",
+ /* Exclude linker generated symbols which vary between passes */
+ "_SDA_BASE_", /* ppc */
+ "_SDA2_BASE_", /* ppc */
+ NULL
+ };
+
+ /* Symbol names that begin with the following are ignored.*/
+ static const char * const ignored_prefixes[] = {
+ "$", /* local symbols for ARM, MIPS, etc. */
+ ".LASANPC", /* s390 kasan local symbols */
+ "__crc_", /* modversions */
+ "__efistub_", /* arm64 EFI stub namespace */
+ "__kvm_nvhe_", /* arm64 non-VHE KVM namespace */
+ "__AArch64ADRPThunk_", /* arm64 lld */
+ "__ARMV5PILongThunk_", /* arm lld */
+ "__ARMV7PILongThunk_",
+ "__ThumbV7PILongThunk_",
+ "__LA25Thunk_", /* mips lld */
+ "__microLA25Thunk_",
+ NULL
+ };
+
+ /* Symbol names that end with the following are ignored.*/
+ static const char * const ignored_suffixes[] = {
+ "_from_arm", /* arm */
+ "_from_thumb", /* arm */
+ "_veneer", /* arm */
+ NULL
+ };
+
+ /* Symbol names that contain the following are ignored.*/
+ static const char * const ignored_matches[] = {
+ ".long_branch.", /* ppc stub */
+ ".plt_branch.", /* ppc stub */
+ NULL
+ };
+
+ const char * const *p;
+
+ for (p = ignored_symbols; *p; p++)
+ if (!strcmp(name, *p))
+ return true;
+
+ for (p = ignored_prefixes; *p; p++)
+ if (!strncmp(name, *p, strlen(*p)))
+ return true;
+
+ for (p = ignored_suffixes; *p; p++) {
+ int l = strlen(name) - strlen(*p);
+
+ if (l >= 0 && !strcmp(name + l, *p))
+ return true;
+ }
+
+ for (p = ignored_matches; *p; p++) {
+ if (strstr(name, *p))
+ return true;
+ }
+
+ if (type == 'U' || type == 'u')
+ return true;
+ /* exclude debugging symbols */
+ if (type == 'N' || type == 'n')
+ return true;
+
+ if (toupper(type) == 'A') {
+ /* Keep these useful absolute symbols */
+ if (strcmp(name, "__kernel_syscall_via_break") &&
+ strcmp(name, "__kernel_syscall_via_epc") &&
+ strcmp(name, "__kernel_sigtramp") &&
+ strcmp(name, "__gp"))
+ return true;
+ }
+
+ return false;
+}
+
int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest __maybe_unused)
{
int err = -1;
@@ -169,6 +266,11 @@ next_pair:
* such as __indirect_thunk_end.
*/
continue;
+ } else if (is_ignored_symbol(sym->name, sym->type)) {
+ /*
+ * Ignore hidden symbols, see scripts/kallsyms.c for the details
+ */
+ continue;
} else {
pr_debug("ERR : %#" PRIx64 ": %s not on kallsyms\n",
mem_start, sym->name);
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 0bae061b2d6d..4bab2273303a 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -151,6 +151,7 @@ static int arch__associate_ins_ops(struct arch* arch, const char *name, struct i
#include "arch/mips/annotate/instructions.c"
#include "arch/x86/annotate/instructions.c"
#include "arch/powerpc/annotate/instructions.c"
+#include "arch/riscv64/annotate/instructions.c"
#include "arch/s390/annotate/instructions.c"
#include "arch/sparc/annotate/instructions.c"
@@ -183,7 +184,6 @@ static struct arch architectures[] = {
.init = x86__annotate_init,
.instructions = x86__instructions,
.nr_instructions = ARRAY_SIZE(x86__instructions),
- .ins_is_fused = x86__ins_is_fused,
.objdump = {
.comment_char = '#',
},
@@ -193,6 +193,10 @@ static struct arch architectures[] = {
.init = powerpc__annotate_init,
},
{
+ .name = "riscv64",
+ .init = riscv64__annotate_init,
+ },
+ {
.name = "s390",
.init = s390__annotate_init,
.objdump = {
diff --git a/tools/perf/util/bpf_counter.c b/tools/perf/util/bpf_counter.c
index ba0f20853651..ced2dac31dcf 100644
--- a/tools/perf/util/bpf_counter.c
+++ b/tools/perf/util/bpf_counter.c
@@ -127,9 +127,9 @@ static int bpf_program_profiler_load_one(struct evsel *evsel, u32 prog_id)
skel->rodata->num_cpu = evsel__nr_cpus(evsel);
- bpf_map__resize(skel->maps.events, evsel__nr_cpus(evsel));
- bpf_map__resize(skel->maps.fentry_readings, 1);
- bpf_map__resize(skel->maps.accum_readings, 1);
+ bpf_map__set_max_entries(skel->maps.events, evsel__nr_cpus(evsel));
+ bpf_map__set_max_entries(skel->maps.fentry_readings, 1);
+ bpf_map__set_max_entries(skel->maps.accum_readings, 1);
prog_name = bpf_target_prog_name(prog_fd);
if (!prog_name) {
@@ -399,7 +399,7 @@ static int bperf_reload_leader_program(struct evsel *evsel, int attr_map_fd,
return -1;
}
- bpf_map__resize(skel->maps.events, libbpf_num_possible_cpus());
+ bpf_map__set_max_entries(skel->maps.events, libbpf_num_possible_cpus());
err = bperf_leader_bpf__load(skel);
if (err) {
pr_err("Failed to load leader skeleton\n");
diff --git a/tools/perf/util/bpf_counter_cgroup.c b/tools/perf/util/bpf_counter_cgroup.c
index 89aa5e71db1a..cbc6c2bca488 100644
--- a/tools/perf/util/bpf_counter_cgroup.c
+++ b/tools/perf/util/bpf_counter_cgroup.c
@@ -65,14 +65,14 @@ static int bperf_load_program(struct evlist *evlist)
/* we need one copy of events per cpu for reading */
map_size = total_cpus * evlist->core.nr_entries / nr_cgroups;
- bpf_map__resize(skel->maps.events, map_size);
- bpf_map__resize(skel->maps.cgrp_idx, nr_cgroups);
+ bpf_map__set_max_entries(skel->maps.events, map_size);
+ bpf_map__set_max_entries(skel->maps.cgrp_idx, nr_cgroups);
/* previous result is saved in a per-cpu array */
map_size = evlist->core.nr_entries / nr_cgroups;
- bpf_map__resize(skel->maps.prev_readings, map_size);
+ bpf_map__set_max_entries(skel->maps.prev_readings, map_size);
/* cgroup result needs all events (per-cpu) */
map_size = evlist->core.nr_entries;
- bpf_map__resize(skel->maps.cgrp_readings, map_size);
+ bpf_map__set_max_entries(skel->maps.cgrp_readings, map_size);
set_max_rlimit();
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 2c06abf6dcd2..c7a9fa0ffae9 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -24,6 +24,16 @@
#include "util/parse-sublevel-options.h"
#include <linux/ctype.h>
+#include <traceevent/event-parse.h>
+
+#define MAKE_LIBTRACEEVENT_VERSION(a, b, c) ((a)*255*255+(b)*255+(c))
+#ifndef LIBTRACEEVENT_VERSION
+/*
+ * If LIBTRACEEVENT_VERSION wasn't computed then set to version 1.1.0 that ships
+ * with the Linux kernel tools.
+ */
+#define LIBTRACEEVENT_VERSION MAKE_LIBTRACEEVENT_VERSION(1, 1, 0)
+#endif
int verbose;
int debug_peo_args;
@@ -228,6 +238,15 @@ int perf_debug_option(const char *str)
/* Allow only verbose value in range (0, 10), otherwise set 0. */
verbose = (verbose < 0) || (verbose > 10) ? 0 : verbose;
+#if MAKE_LIBTRACEEVENT_VERSION(1, 3, 0) <= LIBTRACEEVENT_VERSION
+ if (verbose == 1)
+ tep_set_loglevel(TEP_LOG_INFO);
+ else if (verbose == 2)
+ tep_set_loglevel(TEP_LOG_DEBUG);
+ else if (verbose >= 3)
+ tep_set_loglevel(TEP_LOG_ALL);
+#endif
+
return 0;
}
diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c
index a850fd0be3ee..db2445677c8c 100644
--- a/tools/perf/util/expr.c
+++ b/tools/perf/util/expr.c
@@ -59,8 +59,29 @@ static bool key_equal(const void *key1, const void *key2,
return !strcmp((const char *)key1, (const char *)key2);
}
-/* Caller must make sure id is allocated */
-int expr__add_id(struct expr_parse_ctx *ctx, const char *id)
+struct hashmap *ids__new(void)
+{
+ return hashmap__new(key_hash, key_equal, NULL);
+}
+
+void ids__free(struct hashmap *ids)
+{
+ struct hashmap_entry *cur;
+ size_t bkt;
+
+ if (ids == NULL)
+ return;
+
+ hashmap__for_each_entry(ids, cur, bkt) {
+ free((char *)cur->key);
+ free(cur->value);
+ }
+
+ hashmap__free(ids);
+}
+
+int ids__insert(struct hashmap *ids, const char *id,
+ struct expr_id *parent)
{
struct expr_id_data *data_ptr = NULL, *old_data = NULL;
char *old_key = NULL;
@@ -70,10 +91,10 @@ int expr__add_id(struct expr_parse_ctx *ctx, const char *id)
if (!data_ptr)
return -ENOMEM;
- data_ptr->parent = ctx->parent;
+ data_ptr->parent = parent;
data_ptr->kind = EXPR_ID_DATA__PARENT;
- ret = hashmap__set(&ctx->ids, id, data_ptr,
+ ret = hashmap__set(ids, id, data_ptr,
(const void **)&old_key, (void **)&old_data);
if (ret)
free(data_ptr);
@@ -82,6 +103,48 @@ int expr__add_id(struct expr_parse_ctx *ctx, const char *id)
return ret;
}
+struct hashmap *ids__union(struct hashmap *ids1, struct hashmap *ids2)
+{
+ size_t bkt;
+ struct hashmap_entry *cur;
+ int ret;
+ struct expr_id_data *old_data = NULL;
+ char *old_key = NULL;
+
+ if (!ids1)
+ return ids2;
+
+ if (!ids2)
+ return ids1;
+
+ if (hashmap__size(ids1) < hashmap__size(ids2)) {
+ struct hashmap *tmp = ids1;
+
+ ids1 = ids2;
+ ids2 = tmp;
+ }
+ hashmap__for_each_entry(ids2, cur, bkt) {
+ ret = hashmap__set(ids1, cur->key, cur->value,
+ (const void **)&old_key, (void **)&old_data);
+ free(old_key);
+ free(old_data);
+
+ if (ret) {
+ hashmap__free(ids1);
+ hashmap__free(ids2);
+ return NULL;
+ }
+ }
+ hashmap__free(ids2);
+ return ids1;
+}
+
+/* Caller must make sure id is allocated */
+int expr__add_id(struct expr_parse_ctx *ctx, const char *id)
+{
+ return ids__insert(ctx->ids, id, ctx->parent);
+}
+
/* Caller must make sure id is allocated */
int expr__add_id_val(struct expr_parse_ctx *ctx, const char *id, double val)
{
@@ -95,7 +158,7 @@ int expr__add_id_val(struct expr_parse_ctx *ctx, const char *id, double val)
data_ptr->val = val;
data_ptr->kind = EXPR_ID_DATA__VALUE;
- ret = hashmap__set(&ctx->ids, id, data_ptr,
+ ret = hashmap__set(ctx->ids, id, data_ptr,
(const void **)&old_key, (void **)&old_data);
if (ret)
free(data_ptr);
@@ -140,7 +203,7 @@ int expr__add_ref(struct expr_parse_ctx *ctx, struct metric_ref *ref)
data_ptr->ref.metric_expr = ref->metric_expr;
data_ptr->kind = EXPR_ID_DATA__REF;
- ret = hashmap__set(&ctx->ids, name, data_ptr,
+ ret = hashmap__set(ctx->ids, name, data_ptr,
(const void **)&old_key, (void **)&old_data);
if (ret)
free(data_ptr);
@@ -156,7 +219,7 @@ int expr__add_ref(struct expr_parse_ctx *ctx, struct metric_ref *ref)
int expr__get_id(struct expr_parse_ctx *ctx, const char *id,
struct expr_id_data **data)
{
- return hashmap__find(&ctx->ids, id, (void **)data) ? 0 : -1;
+ return hashmap__find(ctx->ids, id, (void **)data) ? 0 : -1;
}
int expr__resolve_id(struct expr_parse_ctx *ctx, const char *id,
@@ -205,15 +268,23 @@ void expr__del_id(struct expr_parse_ctx *ctx, const char *id)
struct expr_id_data *old_val = NULL;
char *old_key = NULL;
- hashmap__delete(&ctx->ids, id,
+ hashmap__delete(ctx->ids, id,
(const void **)&old_key, (void **)&old_val);
free(old_key);
free(old_val);
}
-void expr__ctx_init(struct expr_parse_ctx *ctx)
+struct expr_parse_ctx *expr__ctx_new(void)
{
- hashmap__init(&ctx->ids, key_hash, key_equal, NULL);
+ struct expr_parse_ctx *ctx;
+
+ ctx = malloc(sizeof(struct expr_parse_ctx));
+ if (!ctx)
+ return NULL;
+
+ ctx->ids = hashmap__new(key_hash, key_equal, NULL);
+ ctx->parent = NULL;
+ return ctx;
}
void expr__ctx_clear(struct expr_parse_ctx *ctx)
@@ -221,19 +292,31 @@ void expr__ctx_clear(struct expr_parse_ctx *ctx)
struct hashmap_entry *cur;
size_t bkt;
- hashmap__for_each_entry((&ctx->ids), cur, bkt) {
+ hashmap__for_each_entry(ctx->ids, cur, bkt) {
+ free((char *)cur->key);
+ free(cur->value);
+ }
+ hashmap__clear(ctx->ids);
+}
+
+void expr__ctx_free(struct expr_parse_ctx *ctx)
+{
+ struct hashmap_entry *cur;
+ size_t bkt;
+
+ hashmap__for_each_entry(ctx->ids, cur, bkt) {
free((char *)cur->key);
free(cur->value);
}
- hashmap__clear(&ctx->ids);
+ hashmap__free(ctx->ids);
+ free(ctx);
}
static int
__expr__parse(double *val, struct expr_parse_ctx *ctx, const char *expr,
- int start, int runtime)
+ bool compute_ids, int runtime)
{
struct expr_scanner_ctx scanner_ctx = {
- .start_token = start,
.runtime = runtime,
};
YY_BUFFER_STATE buffer;
@@ -253,7 +336,7 @@ __expr__parse(double *val, struct expr_parse_ctx *ctx, const char *expr,
expr_set_debug(1, scanner);
#endif
- ret = expr_parse(val, ctx, scanner);
+ ret = expr_parse(val, ctx, compute_ids, scanner);
expr__flush_buffer(buffer, scanner);
expr__delete_buffer(buffer, scanner);
@@ -264,13 +347,13 @@ __expr__parse(double *val, struct expr_parse_ctx *ctx, const char *expr,
int expr__parse(double *final_val, struct expr_parse_ctx *ctx,
const char *expr, int runtime)
{
- return __expr__parse(final_val, ctx, expr, EXPR_PARSE, runtime) ? -1 : 0;
+ return __expr__parse(final_val, ctx, expr, /*compute_ids=*/false, runtime) ? -1 : 0;
}
-int expr__find_other(const char *expr, const char *one,
- struct expr_parse_ctx *ctx, int runtime)
+int expr__find_ids(const char *expr, const char *one,
+ struct expr_parse_ctx *ctx, int runtime)
{
- int ret = __expr__parse(NULL, ctx, expr, EXPR_OTHER, runtime);
+ int ret = __expr__parse(NULL, ctx, expr, /*compute_ids=*/true, runtime);
if (one)
expr__del_id(ctx, one);
diff --git a/tools/perf/util/expr.h b/tools/perf/util/expr.h
index 85df3e4771e4..b20513f0ae59 100644
--- a/tools/perf/util/expr.h
+++ b/tools/perf/util/expr.h
@@ -19,19 +19,29 @@ struct expr_id {
};
struct expr_parse_ctx {
- struct hashmap ids;
+ struct hashmap *ids;
struct expr_id *parent;
};
struct expr_id_data;
struct expr_scanner_ctx {
- int start_token;
int runtime;
};
-void expr__ctx_init(struct expr_parse_ctx *ctx);
+struct hashmap *ids__new(void);
+void ids__free(struct hashmap *ids);
+int ids__insert(struct hashmap *ids, const char *id, struct expr_id *parent);
+/*
+ * Union two sets of ids (hashmaps) and construct a third, freeing ids1 and
+ * ids2.
+ */
+struct hashmap *ids__union(struct hashmap *ids1, struct hashmap *ids2);
+
+struct expr_parse_ctx *expr__ctx_new(void);
void expr__ctx_clear(struct expr_parse_ctx *ctx);
+void expr__ctx_free(struct expr_parse_ctx *ctx);
+
void expr__del_id(struct expr_parse_ctx *ctx, const char *id);
int expr__add_id(struct expr_parse_ctx *ctx, const char *id);
int expr__add_id_val(struct expr_parse_ctx *ctx, const char *id, double val);
@@ -40,9 +50,11 @@ int expr__get_id(struct expr_parse_ctx *ctx, const char *id,
struct expr_id_data **data);
int expr__resolve_id(struct expr_parse_ctx *ctx, const char *id,
struct expr_id_data **datap);
+
int expr__parse(double *final_val, struct expr_parse_ctx *ctx,
const char *expr, int runtime);
-int expr__find_other(const char *expr, const char *one,
+
+int expr__find_ids(const char *expr, const char *one,
struct expr_parse_ctx *ids, int runtime);
double expr_id_data__value(const struct expr_id_data *data);
diff --git a/tools/perf/util/expr.l b/tools/perf/util/expr.l
index 13e5e3c75f56..702fdf6456ca 100644
--- a/tools/perf/util/expr.l
+++ b/tools/perf/util/expr.l
@@ -91,15 +91,6 @@ symbol ({spec}|{sym})+
%%
struct expr_scanner_ctx *sctx = expr_get_extra(yyscanner);
- {
- int start_token = sctx->start_token;
-
- if (sctx->start_token) {
- sctx->start_token = 0;
- return start_token;
- }
- }
-
d_ratio { return D_RATIO; }
max { return MAX; }
min { return MIN; }
diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y
index b2ada8f8309a..ba7d3b667fcb 100644
--- a/tools/perf/util/expr.y
+++ b/tools/perf/util/expr.y
@@ -1,42 +1,43 @@
/* Simple expression parser */
%{
#define YYDEBUG 1
-#include <stdio.h>
-#include "util.h"
+#include <assert.h>
+#include <math.h>
#include "util/debug.h"
-#include <stdlib.h> // strtod()
+#include "smt.h"
#define IN_EXPR_Y 1
#include "expr.h"
-#include "smt.h"
-#include <string.h>
-
-static double d_ratio(double val0, double val1)
-{
- if (val1 == 0) {
- return 0;
- }
- return val0 / val1;
-}
-
%}
%define api.pure full
%parse-param { double *final_val }
%parse-param { struct expr_parse_ctx *ctx }
+%parse-param { bool compute_ids }
%parse-param {void *scanner}
%lex-param {void* scanner}
%union {
double num;
char *str;
+ struct ids {
+ /*
+ * When creating ids, holds the working set of event ids. NULL
+ * implies the set is empty.
+ */
+ struct hashmap *ids;
+ /*
+ * The metric value. When not creating ids this is the value
+ * read from a counter, a constant or some computed value. When
+ * creating ids the value is either a constant or BOTTOM. NAN is
+ * used as the special BOTTOM value, representing a "set of all
+ * values" case.
+ */
+ double val;
+ } ids;
}
-%token EXPR_PARSE EXPR_OTHER EXPR_ERROR
-%token <num> NUMBER
-%token <str> ID
-%destructor { free ($$); } <str>
-%token MIN MAX IF ELSE SMT_ON D_RATIO
+%token ID NUMBER MIN MAX IF ELSE SMT_ON D_RATIO EXPR_ERROR
%left MIN MAX IF
%left '|'
%left '^'
@@ -45,83 +46,245 @@ static double d_ratio(double val0, double val1)
%left '-' '+'
%left '*' '/' '%'
%left NEG NOT
-%type <num> expr if_expr
+%type <num> NUMBER
+%type <str> ID
+%destructor { free ($$); } <str>
+%type <ids> expr if_expr
+%destructor { ids__free($$.ids); } <ids>
%{
static void expr_error(double *final_val __maybe_unused,
struct expr_parse_ctx *ctx __maybe_unused,
+ bool compute_ids __maybe_unused,
void *scanner,
const char *s)
{
pr_debug("%s\n", s);
}
+/*
+ * During compute ids, the special "bottom" value uses NAN to represent the set
+ * of all values. NAN is selected as it isn't a useful constant value.
+ */
+#define BOTTOM NAN
+
+/* During computing ids, does val represent a constant (non-BOTTOM) value? */
+static bool is_const(double val)
+{
+ return isfinite(val);
+}
+
+static struct ids union_expr(struct ids ids1, struct ids ids2)
+{
+ struct ids result = {
+ .val = BOTTOM,
+ .ids = ids__union(ids1.ids, ids2.ids),
+ };
+ return result;
+}
+
+/*
+ * If we're not computing ids or $1 and $3 are constants, compute the new
+ * constant value using OP. Its invariant that there are no ids. If computing
+ * ids for non-constants union the set of IDs that must be computed.
+ */
+#define BINARY_LONG_OP(RESULT, OP, LHS, RHS) \
+ if (!compute_ids || (is_const(LHS.val) && is_const(RHS.val))) { \
+ assert(LHS.ids == NULL); \
+ assert(RHS.ids == NULL); \
+ RESULT.val = (long)LHS.val OP (long)RHS.val; \
+ RESULT.ids = NULL; \
+ } else { \
+ RESULT = union_expr(LHS, RHS); \
+ }
+
+#define BINARY_OP(RESULT, OP, LHS, RHS) \
+ if (!compute_ids || (is_const(LHS.val) && is_const(RHS.val))) { \
+ assert(LHS.ids == NULL); \
+ assert(RHS.ids == NULL); \
+ RESULT.val = LHS.val OP RHS.val; \
+ RESULT.ids = NULL; \
+ } else { \
+ RESULT = union_expr(LHS, RHS); \
+ }
+
%}
%%
-start:
-EXPR_PARSE all_expr
-|
-EXPR_OTHER all_other
+start: if_expr
+{
+ if (compute_ids)
+ ctx->ids = ids__union($1.ids, ctx->ids);
-all_other: all_other other
-|
+ if (final_val)
+ *final_val = $1.val;
+}
+;
+
+if_expr: expr IF expr ELSE expr
+{
+ if (fpclassify($3.val) == FP_ZERO) {
+ /*
+ * The IF expression evaluated to 0 so treat as false, take the
+ * ELSE and discard everything else.
+ */
+ $$.val = $5.val;
+ $$.ids = $5.ids;
+ ids__free($1.ids);
+ ids__free($3.ids);
+ } else if (!compute_ids || is_const($3.val)) {
+ /*
+ * If ids aren't computed then treat the expression as true. If
+ * ids are being computed and the IF expr is a non-zero
+ * constant, then also evaluate the true case.
+ */
+ $$.val = $1.val;
+ $$.ids = $1.ids;
+ ids__free($3.ids);
+ ids__free($5.ids);
+ } else if ($1.val == $5.val) {
+ /*
+ * LHS == RHS, so both are an identical constant. No need to
+ * evaluate any events.
+ */
+ $$.val = $1.val;
+ $$.ids = NULL;
+ ids__free($1.ids);
+ ids__free($3.ids);
+ ids__free($5.ids);
+ } else {
+ /*
+ * Value is either the LHS or RHS and we need the IF expression
+ * to compute it.
+ */
+ $$ = union_expr($1, union_expr($3, $5));
+ }
+}
+| expr
+;
-other: ID
+expr: NUMBER
{
- expr__add_id(ctx, $1);
-}
-|
-MIN | MAX | IF | ELSE | SMT_ON | NUMBER | '|' | '^' | '&' | '-' | '+' | '*' | '/' | '%' | '(' | ')' | ','
-|
-'<' | '>' | D_RATIO
-
-all_expr: if_expr { *final_val = $1; }
- ;
-
-if_expr:
- expr IF expr ELSE expr { $$ = $3 ? $1 : $5; }
- | expr
- ;
-
-expr: NUMBER
- | ID {
- struct expr_id_data *data;
-
- if (expr__resolve_id(ctx, $1, &data)) {
- free($1);
- YYABORT;
- }
-
- $$ = expr_id_data__value(data);
- free($1);
- }
- | expr '|' expr { $$ = (long)$1 | (long)$3; }
- | expr '&' expr { $$ = (long)$1 & (long)$3; }
- | expr '^' expr { $$ = (long)$1 ^ (long)$3; }
- | expr '<' expr { $$ = $1 < $3; }
- | expr '>' expr { $$ = $1 > $3; }
- | expr '+' expr { $$ = $1 + $3; }
- | expr '-' expr { $$ = $1 - $3; }
- | expr '*' expr { $$ = $1 * $3; }
- | expr '/' expr { if ($3 == 0) {
- pr_debug("division by zero\n");
- YYABORT;
- }
- $$ = $1 / $3;
- }
- | expr '%' expr { if ((long)$3 == 0) {
- pr_debug("division by zero\n");
- YYABORT;
- }
- $$ = (long)$1 % (long)$3;
- }
- | '-' expr %prec NEG { $$ = -$2; }
- | '(' if_expr ')' { $$ = $2; }
- | MIN '(' expr ',' expr ')' { $$ = $3 < $5 ? $3 : $5; }
- | MAX '(' expr ',' expr ')' { $$ = $3 > $5 ? $3 : $5; }
- | SMT_ON { $$ = smt_on() > 0; }
- | D_RATIO '(' expr ',' expr ')' { $$ = d_ratio($3,$5); }
- ;
+ $$.val = $1;
+ $$.ids = NULL;
+}
+| ID
+{
+ if (!compute_ids) {
+ /*
+ * Compute the event's value from ID. If the ID isn't known then
+ * it isn't used to compute the formula so set to NAN.
+ */
+ struct expr_id_data *data;
+
+ $$.val = NAN;
+ if (expr__resolve_id(ctx, $1, &data) == 0)
+ $$.val = expr_id_data__value(data);
+
+ $$.ids = NULL;
+ free($1);
+ } else {
+ /*
+ * Set the value to BOTTOM to show that any value is possible
+ * when the event is computed. Create a set of just the ID.
+ */
+ $$.val = BOTTOM;
+ $$.ids = ids__new();
+ if (!$$.ids || ids__insert($$.ids, $1, ctx->parent))
+ YYABORT;
+ }
+}
+| expr '|' expr { BINARY_LONG_OP($$, |, $1, $3); }
+| expr '&' expr { BINARY_LONG_OP($$, &, $1, $3); }
+| expr '^' expr { BINARY_LONG_OP($$, ^, $1, $3); }
+| expr '<' expr { BINARY_OP($$, <, $1, $3); }
+| expr '>' expr { BINARY_OP($$, >, $1, $3); }
+| expr '+' expr { BINARY_OP($$, +, $1, $3); }
+| expr '-' expr { BINARY_OP($$, -, $1, $3); }
+| expr '*' expr { BINARY_OP($$, *, $1, $3); }
+| expr '/' expr
+{
+ if (fpclassify($3.val) == FP_ZERO) {
+ pr_debug("division by zero\n");
+ YYABORT;
+ } else if (!compute_ids || (is_const($1.val) && is_const($3.val))) {
+ assert($1.ids == NULL);
+ assert($3.ids == NULL);
+ $$.val = $1.val / $3.val;
+ $$.ids = NULL;
+ } else {
+ /* LHS and/or RHS need computing from event IDs so union. */
+ $$ = union_expr($1, $3);
+ }
+}
+| expr '%' expr
+{
+ if (fpclassify($3.val) == FP_ZERO) {
+ pr_debug("division by zero\n");
+ YYABORT;
+ } else if (!compute_ids || (is_const($1.val) && is_const($3.val))) {
+ assert($1.ids == NULL);
+ assert($3.ids == NULL);
+ $$.val = (long)$1.val % (long)$3.val;
+ $$.ids = NULL;
+ } else {
+ /* LHS and/or RHS need computing from event IDs so union. */
+ $$ = union_expr($1, $3);
+ }
+}
+| D_RATIO '(' expr ',' expr ')'
+{
+ if (fpclassify($5.val) == FP_ZERO) {
+ /*
+ * Division by constant zero always yields zero and no events
+ * are necessary.
+ */
+ assert($5.ids == NULL);
+ $$.val = 0.0;
+ $$.ids = NULL;
+ ids__free($3.ids);
+ } else if (!compute_ids || (is_const($3.val) && is_const($5.val))) {
+ assert($3.ids == NULL);
+ assert($5.ids == NULL);
+ $$.val = $3.val / $5.val;
+ $$.ids = NULL;
+ } else {
+ /* LHS and/or RHS need computing from event IDs so union. */
+ $$ = union_expr($3, $5);
+ }
+}
+| '-' expr %prec NEG
+{
+ $$.val = -$2.val;
+ $$.ids = $2.ids;
+}
+| '(' if_expr ')'
+{
+ $$ = $2;
+}
+| MIN '(' expr ',' expr ')'
+{
+ if (!compute_ids) {
+ $$.val = $3.val < $5.val ? $3.val : $5.val;
+ $$.ids = NULL;
+ } else {
+ $$ = union_expr($3, $5);
+ }
+}
+| MAX '(' expr ',' expr ')'
+{
+ if (!compute_ids) {
+ $$.val = $3.val > $5.val ? $3.val : $5.val;
+ $$.ids = NULL;
+ } else {
+ $$ = union_expr($3, $5);
+ }
+}
+| SMT_ON
+{
+ $$.val = smt_on() > 0 ? 1.0 : 0.0;
+ $$.ids = NULL;
+}
+;
%%
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 29b747ac31c1..8ba5370f5f64 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -118,7 +118,7 @@ struct metric_ref_node {
struct metric {
struct list_head nd;
- struct expr_parse_ctx pctx;
+ struct expr_parse_ctx *pctx;
const char *metric_name;
const char *metric_expr;
const char *metric_unit;
@@ -198,65 +198,69 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist,
struct evsel *ev, *current_leader = NULL;
struct expr_id_data *val_ptr;
int i = 0, matched_events = 0, events_to_match;
- const int idnum = (int)hashmap__size(&pctx->ids);
+ int idnum = (int)hashmap__size(pctx->ids);
- /*
- * duration_time is always grouped separately, when events are grouped
- * (ie has_constraint is false) then ignore it in the matching loop and
- * add it to metric_events at the end.
- */
- if (!has_constraint &&
- hashmap__find(&pctx->ids, "duration_time", (void **)&val_ptr))
- events_to_match = idnum - 1;
- else
- events_to_match = idnum;
-
- evlist__for_each_entry (perf_evlist, ev) {
+ if (idnum != 0) {
/*
- * Events with a constraint aren't grouped and match the first
- * events available.
+ * duration_time is always grouped separately, when events are
+ * grouped (ie has_constraint is false) then ignore it in the
+ * matching loop and add it to metric_events at the end.
*/
- if (has_constraint && ev->weak_group)
- continue;
- /* Ignore event if already used and merging is disabled. */
- if (metric_no_merge && test_bit(ev->core.idx, evlist_used))
- continue;
- if (!has_constraint && !evsel__has_leader(ev, current_leader)) {
+ events_to_match = idnum;
+ if (!has_constraint && hashmap__find(pctx->ids, "duration_time", (void **)&val_ptr))
+ events_to_match--;
+
+ evlist__for_each_entry(perf_evlist, ev) {
/*
- * Start of a new group, discard the whole match and
- * start again.
+ * Events with a constraint aren't grouped and match the
+ * first events available.
*/
- matched_events = 0;
- memset(metric_events, 0,
- sizeof(struct evsel *) * idnum);
- current_leader = evsel__leader(ev);
+ if (has_constraint && ev->weak_group)
+ continue;
+ /* Ignore event if already used and merging is disabled. */
+ if (metric_no_merge && test_bit(ev->core.idx, evlist_used))
+ continue;
+ if (!has_constraint && !evsel__has_leader(ev, current_leader)) {
+ /*
+ * Start of a new group, discard the whole match
+ * and start again.
+ */
+ matched_events = 0;
+ memset(metric_events, 0, sizeof(struct evsel *) * idnum);
+ current_leader = evsel__leader(ev);
+ }
+ /*
+ * Check for duplicate events with the same name. For
+ * example, uncore_imc/cas_count_read/ will turn into 6
+ * events per socket on skylakex. Only the first such
+ * event is placed in metric_events. If events aren't
+ * grouped then this also ensures that the same event in
+ * different sibling groups aren't both added to
+ * metric_events.
+ */
+ if (contains_event(metric_events, matched_events, ev->name))
+ continue;
+ /* Does this event belong to the parse context? */
+ if (hashmap__find(pctx->ids, ev->name, (void **)&val_ptr))
+ metric_events[matched_events++] = ev;
+
+ if (matched_events == events_to_match)
+ break;
}
+ } else {
/*
- * Check for duplicate events with the same name. For example,
- * uncore_imc/cas_count_read/ will turn into 6 events per socket
- * on skylakex. Only the first such event is placed in
- * metric_events. If events aren't grouped then this also
- * ensures that the same event in different sibling groups
- * aren't both added to metric_events.
+ * There are no events to match, but we need to associate the
+ * metric with an event for printing. A duration_time event was
+ * parsed for this.
*/
- if (contains_event(metric_events, matched_events, ev->name))
- continue;
- /* Does this event belong to the parse context? */
- if (hashmap__find(&pctx->ids, ev->name, (void **)&val_ptr))
- metric_events[matched_events++] = ev;
-
- if (matched_events == events_to_match)
- break;
+ idnum = 1;
+ events_to_match = 0;
}
-
if (events_to_match != idnum) {
/* Add the first duration_time. */
- evlist__for_each_entry(perf_evlist, ev) {
- if (!strcmp(ev->name, "duration_time")) {
- metric_events[matched_events++] = ev;
- break;
- }
- }
+ ev = evlist__find_evsel_by_str(perf_evlist, "duration_time");
+ if (ev)
+ metric_events[matched_events++] = ev;
}
if (matched_events != idnum) {
@@ -320,14 +324,15 @@ static int metricgroup__setup_events(struct list_head *groups,
list_for_each_entry (m, groups, nd) {
struct evsel **metric_events;
struct metric_ref *metric_refs = NULL;
+ const size_t ids_size = hashmap__size(m->pctx->ids);
metric_events = calloc(sizeof(void *),
- hashmap__size(&m->pctx.ids) + 1);
+ ids_size == 0 ? 2 : ids_size + 1);
if (!metric_events) {
ret = -ENOMEM;
break;
}
- evsel = find_evsel_group(perf_evlist, &m->pctx,
+ evsel = find_evsel_group(perf_evlist, m->pctx,
metric_no_merge,
m->has_constraint, metric_events,
evlist_used);
@@ -693,7 +698,7 @@ static void metricgroup__add_metric_weak_group(struct strbuf *events,
size_t bkt;
bool no_group = true, has_duration = false;
- hashmap__for_each_entry((&ctx->ids), cur, bkt) {
+ hashmap__for_each_entry(ctx->ids, cur, bkt) {
pr_debug("found event %s\n", (const char *)cur->key);
/*
* Duration time maps to a software event and can make
@@ -724,7 +729,7 @@ static void metricgroup__add_metric_non_group(struct strbuf *events,
size_t bkt;
bool first = true;
- hashmap__for_each_entry((&ctx->ids), cur, bkt) {
+ hashmap__for_each_entry(ctx->ids, cur, bkt) {
if (!first)
strbuf_addf(events, ",");
strbuf_addf(events, "%s", (const char *)cur->key);
@@ -799,7 +804,11 @@ static int __add_metric(struct list_head *metric_list,
if (!m)
return -ENOMEM;
- expr__ctx_init(&m->pctx);
+ m->pctx = expr__ctx_new();
+ if (!m->pctx) {
+ free(m);
+ return -ENOMEM;
+ }
m->metric_name = pe->metric_name;
m->metric_expr = pe->metric_expr;
m->metric_unit = pe->unit;
@@ -847,15 +856,15 @@ static int __add_metric(struct list_head *metric_list,
/* Force all found IDs in metric to have us as parent ID. */
WARN_ON_ONCE(!parent);
- m->pctx.parent = parent;
+ m->pctx->parent = parent;
/*
* For both the parent and referenced metrics, we parse
* all the metric's IDs and add it to the parent context.
*/
- if (expr__find_other(pe->metric_expr, NULL, &m->pctx, runtime) < 0) {
+ if (expr__find_ids(pe->metric_expr, NULL, m->pctx, runtime) < 0) {
if (m->metric_refs_cnt == 0) {
- expr__ctx_clear(&m->pctx);
+ expr__ctx_free(m->pctx);
free(m);
*mp = NULL;
}
@@ -878,8 +887,8 @@ static int __add_metric(struct list_head *metric_list,
list_for_each_prev(pos, metric_list) {
struct metric *old = list_entry(pos, struct metric, nd);
- if (hashmap__size(&m->pctx.ids) <=
- hashmap__size(&old->pctx.ids))
+ if (hashmap__size(m->pctx->ids) <=
+ hashmap__size(old->pctx->ids))
break;
}
list_add(&m->nd, pos);
@@ -927,7 +936,7 @@ static int recursion_check(struct metric *m, const char *id, struct expr_id **pa
* if we already processed 'id', if we did, it's recursion
* and we fail.
*/
- ret = expr__get_id(&m->pctx, id, &data);
+ ret = expr__get_id(m->pctx, id, &data);
if (ret)
return ret;
@@ -982,7 +991,7 @@ static int __resolve_metric(struct metric *m,
*/
do {
all = true;
- hashmap__for_each_entry((&m->pctx.ids), cur, bkt) {
+ hashmap__for_each_entry(m->pctx->ids, cur, bkt) {
struct expr_id *parent;
struct pmu_event *pe;
@@ -996,7 +1005,7 @@ static int __resolve_metric(struct metric *m,
all = false;
/* The metric key itself needs to go out.. */
- expr__del_id(&m->pctx, cur->key);
+ expr__del_id(m->pctx, cur->key);
/* ... and it gets resolved to the parent context. */
ret = add_metric(metric_list, pe, metric_no_group, &m, parent, ids);
@@ -1144,10 +1153,10 @@ static int metricgroup__add_metric(const char *metric, bool metric_no_group,
if (m->has_constraint) {
metricgroup__add_metric_non_group(events,
- &m->pctx);
+ m->pctx);
} else {
metricgroup__add_metric_weak_group(events,
- &m->pctx);
+ m->pctx);
}
}
@@ -1210,7 +1219,7 @@ static void metricgroup__free_metrics(struct list_head *metric_list)
list_for_each_entry_safe (m, tmp, metric_list, nd) {
metric__free_refs(m);
- expr__ctx_clear(&m->pctx);
+ expr__ctx_free(m->pctx);
list_del_init(&m->nd);
free(m);
}
@@ -1236,7 +1245,8 @@ static int parse_groups(struct evlist *perf_evlist, const char *str,
goto out;
pr_debug("adding %s\n", extra_events.buf);
bzero(&parse_error, sizeof(parse_error));
- ret = __parse_events(perf_evlist, extra_events.buf, &parse_error, fake_pmu);
+ ret = __parse_events(perf_evlist, extra_events.len > 0 ? extra_events.buf : "duration_time",
+ &parse_error, fake_pmu);
if (ret) {
parse_events_print_error(&parse_error, extra_events.buf);
goto out;
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 51a2219df601..1acac3e13b32 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -19,8 +19,6 @@
#include <subcmd/exec-cmd.h>
#include "string2.h"
#include "strlist.h"
-#include "symbol.h"
-#include "header.h"
#include "bpf-loader.h"
#include "debug.h"
#include <api/fs/tracing_path.h>
@@ -1471,7 +1469,7 @@ out_free_terms:
int parse_events_add_tool(struct parse_events_state *parse_state,
struct list_head *list,
- enum perf_tool_event tool_event)
+ int tool_event)
{
return add_event_tool(list, &parse_state->idx, tool_event);
}
@@ -2703,7 +2701,7 @@ next:
return 0;
}
-static bool is_event_supported(u8 type, unsigned config)
+static bool is_event_supported(u8 type, u64 config)
{
bool ret = true;
int open_return;
@@ -2823,10 +2821,18 @@ void print_sdt_events(const char *subsys_glob, const char *event_glob,
int print_hwcache_events(const char *event_glob, bool name_only)
{
- unsigned int type, op, i, evt_i = 0, evt_num = 0;
- char name[64];
- char **evt_list = NULL;
+ unsigned int type, op, i, evt_i = 0, evt_num = 0, npmus = 0;
+ char name[64], new_name[128];
+ char **evt_list = NULL, **evt_pmus = NULL;
bool evt_num_known = false;
+ struct perf_pmu *pmu = NULL;
+
+ if (perf_pmu__has_hybrid()) {
+ npmus = perf_pmu__hybrid_pmu_num();
+ evt_pmus = zalloc(sizeof(char *) * npmus);
+ if (!evt_pmus)
+ goto out_enomem;
+ }
restart:
if (evt_num_known) {
@@ -2842,20 +2848,61 @@ restart:
continue;
for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) {
+ unsigned int hybrid_supported = 0, j;
+ bool supported;
+
__evsel__hw_cache_type_op_res_name(type, op, i, name, sizeof(name));
if (event_glob != NULL && !strglobmatch(name, event_glob))
continue;
- if (!is_event_supported(PERF_TYPE_HW_CACHE,
- type | (op << 8) | (i << 16)))
- continue;
+ if (!perf_pmu__has_hybrid()) {
+ if (!is_event_supported(PERF_TYPE_HW_CACHE,
+ type | (op << 8) | (i << 16))) {
+ continue;
+ }
+ } else {
+ perf_pmu__for_each_hybrid_pmu(pmu) {
+ if (!evt_num_known) {
+ evt_num++;
+ continue;
+ }
+
+ supported = is_event_supported(
+ PERF_TYPE_HW_CACHE,
+ type | (op << 8) | (i << 16) |
+ ((__u64)pmu->type << PERF_PMU_TYPE_SHIFT));
+ if (supported) {
+ snprintf(new_name, sizeof(new_name), "%s/%s/",
+ pmu->name, name);
+ evt_pmus[hybrid_supported] = strdup(new_name);
+ hybrid_supported++;
+ }
+ }
+
+ if (hybrid_supported == 0)
+ continue;
+ }
if (!evt_num_known) {
evt_num++;
continue;
}
- evt_list[evt_i] = strdup(name);
+ if ((hybrid_supported == 0) ||
+ (hybrid_supported == npmus)) {
+ evt_list[evt_i] = strdup(name);
+ if (npmus > 0) {
+ for (j = 0; j < npmus; j++)
+ zfree(&evt_pmus[j]);
+ }
+ } else {
+ for (j = 0; j < hybrid_supported; j++) {
+ evt_list[evt_i++] = evt_pmus[j];
+ evt_pmus[j] = NULL;
+ }
+ continue;
+ }
+
if (evt_list[evt_i] == NULL)
goto out_enomem;
evt_i++;
@@ -2867,6 +2914,13 @@ restart:
evt_num_known = true;
goto restart;
}
+
+ for (evt_i = 0; evt_i < evt_num; evt_i++) {
+ if (!evt_list[evt_i])
+ break;
+ }
+
+ evt_num = evt_i;
qsort(evt_list, evt_num, sizeof(char *), cmp_string);
evt_i = 0;
while (evt_i < evt_num) {
@@ -2885,6 +2939,10 @@ out_free:
for (evt_i = 0; evt_i < evt_num; evt_i++)
zfree(&evt_list[evt_i]);
zfree(&evt_list);
+
+ for (evt_i = 0; evt_i < npmus; evt_i++)
+ zfree(&evt_pmus[evt_i]);
+ zfree(&evt_pmus);
return evt_num;
out_enomem:
@@ -3083,7 +3141,7 @@ int parse_events_term__num(struct parse_events_term **term,
struct parse_events_term temp = {
.type_val = PARSE_EVENTS__TERM_TYPE_NUM,
.type_term = type_term,
- .config = config,
+ .config = config ? : strdup(config_term_names[type_term]),
.no_value = no_value,
.err_term = loc_term ? loc_term->first_column : 0,
.err_val = loc_val ? loc_val->first_column : 0,
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index bf6e41aa9b6a..b32ed3064c49 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -182,10 +182,9 @@ int parse_events_add_numeric(struct parse_events_state *parse_state,
struct list_head *list,
u32 type, u64 config,
struct list_head *head_config);
-enum perf_tool_event;
int parse_events_add_tool(struct parse_events_state *parse_state,
struct list_head *list,
- enum perf_tool_event tool_event);
+ int tool_event);
int parse_events_add_cache(struct list_head *list, int *idx,
char *type, char *op_result1, char *op_result2,
struct parse_events_error *error,
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 923849024b15..47da7a0c5df4 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -12,7 +12,6 @@
#include <sys/types.h>
#include <sys/stat.h>
#include <unistd.h>
-#include "../perf.h"
#include "parse-events.h"
#include "parse-events-bison.h"
#include "evsel.h"
diff --git a/tools/perf/util/record.h b/tools/perf/util/record.h
index 68f471d9a88b..ef6c2715fdd9 100644
--- a/tools/perf/util/record.h
+++ b/tools/perf/util/record.h
@@ -77,6 +77,7 @@ struct record_opts {
int ctl_fd;
int ctl_fd_ack;
bool ctl_fd_close;
+ int synth;
};
extern const char * const *record_usage;
diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
index 5b7d6c16d33f..af468e3bb6fa 100644
--- a/tools/perf/util/srcline.c
+++ b/tools/perf/util/srcline.c
@@ -1,8 +1,10 @@
// SPDX-License-Identifier: GPL-2.0
#include <inttypes.h>
+#include <signal.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
+#include <sys/types.h>
#include <linux/kernel.h>
#include <linux/string.h>
@@ -15,6 +17,7 @@
#include "srcline.h"
#include "string2.h"
#include "symbol.h"
+#include "subcmd/run-command.h"
bool srcline_full_filename;
@@ -119,6 +122,8 @@ static struct symbol *new_inline_sym(struct dso *dso,
return inline_sym;
}
+#define MAX_INLINE_NEST 1024
+
#ifdef HAVE_LIBBFD_SUPPORT
/*
@@ -273,8 +278,6 @@ static void addr2line_cleanup(struct a2l_data *a2l)
free(a2l);
}
-#define MAX_INLINE_NEST 1024
-
static int inline_list__append_dso_a2l(struct dso *dso,
struct inline_node *node,
struct symbol *sym)
@@ -361,26 +364,14 @@ void dso__free_a2l(struct dso *dso)
dso->a2l = NULL;
}
-static struct inline_node *addr2inlines(const char *dso_name, u64 addr,
- struct dso *dso, struct symbol *sym)
-{
- struct inline_node *node;
-
- node = zalloc(sizeof(*node));
- if (node == NULL) {
- perror("not enough memory for the inline node");
- return NULL;
- }
-
- INIT_LIST_HEAD(&node->val);
- node->addr = addr;
-
- addr2line(dso_name, addr, NULL, NULL, dso, true, node, sym);
- return node;
-}
-
#else /* HAVE_LIBBFD_SUPPORT */
+struct a2l_subprocess {
+ struct child_process addr2line;
+ FILE *to_child;
+ FILE *from_child;
+};
+
static int filename_split(char *filename, unsigned int *line_nr)
{
char *sep;
@@ -402,114 +393,285 @@ static int filename_split(char *filename, unsigned int *line_nr)
return 0;
}
-static int addr2line(const char *dso_name, u64 addr,
- char **file, unsigned int *line_nr,
- struct dso *dso __maybe_unused,
- bool unwind_inlines __maybe_unused,
- struct inline_node *node __maybe_unused,
- struct symbol *sym __maybe_unused)
+static void addr2line_subprocess_cleanup(struct a2l_subprocess *a2l)
{
- FILE *fp;
- char cmd[PATH_MAX];
- char *filename = NULL;
- size_t len;
- int ret = 0;
+ if (a2l->addr2line.pid != -1) {
+ kill(a2l->addr2line.pid, SIGKILL);
+ finish_command(&a2l->addr2line); /* ignore result, we don't care */
+ a2l->addr2line.pid = -1;
+ }
- scnprintf(cmd, sizeof(cmd), "addr2line -e %s %016"PRIx64,
- dso_name, addr);
+ if (a2l->to_child != NULL) {
+ fclose(a2l->to_child);
+ a2l->to_child = NULL;
+ }
- fp = popen(cmd, "r");
- if (fp == NULL) {
- pr_warning("popen failed for %s\n", dso_name);
- return 0;
+ if (a2l->from_child != NULL) {
+ fclose(a2l->from_child);
+ a2l->from_child = NULL;
+ }
+
+ free(a2l);
+}
+
+static struct a2l_subprocess *addr2line_subprocess_init(const char *path)
+{
+ const char *argv[] = { "addr2line", "-e", path, "-i", "-f", NULL };
+ struct a2l_subprocess *a2l = zalloc(sizeof(*a2l));
+ int start_command_status = 0;
+
+ if (a2l == NULL)
+ goto out;
+
+ a2l->to_child = NULL;
+ a2l->from_child = NULL;
+
+ a2l->addr2line.pid = -1;
+ a2l->addr2line.in = -1;
+ a2l->addr2line.out = -1;
+ a2l->addr2line.no_stderr = 1;
+
+ a2l->addr2line.argv = argv;
+ start_command_status = start_command(&a2l->addr2line);
+ a2l->addr2line.argv = NULL; /* it's not used after start_command; avoid dangling pointers */
+
+ if (start_command_status != 0) {
+ pr_warning("could not start addr2line for %s: start_command return code %d\n",
+ path,
+ start_command_status);
+ goto out;
}
- if (getline(&filename, &len, fp) < 0 || !len) {
- pr_warning("addr2line has no output for %s\n", dso_name);
+ a2l->to_child = fdopen(a2l->addr2line.in, "w");
+ if (a2l->to_child == NULL) {
+ pr_warning("could not open write-stream to addr2line of %s\n", path);
goto out;
}
- ret = filename_split(filename, line_nr);
- if (ret != 1) {
- free(filename);
+ a2l->from_child = fdopen(a2l->addr2line.out, "r");
+ if (a2l->from_child == NULL) {
+ pr_warning("could not open read-stream from addr2line of %s\n", path);
goto out;
}
- *file = filename;
+ return a2l;
out:
- pclose(fp);
- return ret;
+ if (a2l)
+ addr2line_subprocess_cleanup(a2l);
+
+ return NULL;
}
-void dso__free_a2l(struct dso *dso __maybe_unused)
+static int read_addr2line_record(struct a2l_subprocess *a2l,
+ char **function,
+ char **filename,
+ unsigned int *line_nr)
{
+ /*
+ * Returns:
+ * -1 ==> error
+ * 0 ==> sentinel (or other ill-formed) record read
+ * 1 ==> a genuine record read
+ */
+ char *line = NULL;
+ size_t line_len = 0;
+ unsigned int dummy_line_nr = 0;
+ int ret = -1;
+
+ if (function != NULL)
+ zfree(function);
+
+ if (filename != NULL)
+ zfree(filename);
+
+ if (line_nr != NULL)
+ *line_nr = 0;
+
+ if (getline(&line, &line_len, a2l->from_child) < 0 || !line_len)
+ goto error;
+
+ if (function != NULL)
+ *function = strdup(strim(line));
+
+ zfree(&line);
+ line_len = 0;
+
+ if (getline(&line, &line_len, a2l->from_child) < 0 || !line_len)
+ goto error;
+
+ if (filename_split(line, line_nr == NULL ? &dummy_line_nr : line_nr) == 0) {
+ ret = 0;
+ goto error;
+ }
+
+ if (filename != NULL)
+ *filename = strdup(line);
+
+ zfree(&line);
+ line_len = 0;
+
+ return 1;
+
+error:
+ free(line);
+ if (function != NULL)
+ zfree(function);
+ if (filename != NULL)
+ zfree(filename);
+ return ret;
}
-static struct inline_node *addr2inlines(const char *dso_name, u64 addr,
- struct dso *dso __maybe_unused,
- struct symbol *sym)
+static int inline_list__append_record(struct dso *dso,
+ struct inline_node *node,
+ struct symbol *sym,
+ const char *function,
+ const char *filename,
+ unsigned int line_nr)
{
- FILE *fp;
- char cmd[PATH_MAX];
- struct inline_node *node;
- char *filename = NULL;
- char *funcname = NULL;
- size_t filelen, funclen;
- unsigned int line_nr = 0;
+ struct symbol *inline_sym = new_inline_sym(dso, sym, function);
- scnprintf(cmd, sizeof(cmd), "addr2line -e %s -i -f %016"PRIx64,
- dso_name, addr);
+ return inline_list__append(inline_sym, srcline_from_fileline(filename, line_nr), node);
+}
- fp = popen(cmd, "r");
- if (fp == NULL) {
- pr_err("popen failed for %s\n", dso_name);
- return NULL;
+static int addr2line(const char *dso_name, u64 addr,
+ char **file, unsigned int *line_nr,
+ struct dso *dso,
+ bool unwind_inlines,
+ struct inline_node *node,
+ struct symbol *sym __maybe_unused)
+{
+ struct a2l_subprocess *a2l = dso->a2l;
+ char *record_function = NULL;
+ char *record_filename = NULL;
+ unsigned int record_line_nr = 0;
+ int record_status = -1;
+ int ret = 0;
+ size_t inline_count = 0;
+
+ if (!a2l) {
+ dso->a2l = addr2line_subprocess_init(dso_name);
+ a2l = dso->a2l;
}
- node = zalloc(sizeof(*node));
- if (node == NULL) {
- perror("not enough memory for the inline node");
+ if (a2l == NULL) {
+ if (!symbol_conf.disable_add2line_warn)
+ pr_warning("%s %s: addr2line_subprocess_init failed\n", __func__, dso_name);
goto out;
}
- INIT_LIST_HEAD(&node->val);
- node->addr = addr;
-
- /* addr2line -f generates two lines for each inlined functions */
- while (getline(&funcname, &funclen, fp) != -1) {
- char *srcline;
- struct symbol *inline_sym;
+ /*
+ * Send our request and then *deliberately* send something that can't be interpreted as
+ * a valid address to ask addr2line about (namely, ","). This causes addr2line to first
+ * write out the answer to our request, in an unbounded/unknown number of records, and
+ * then to write out the lines "??" and "??:0", so that we can detect when it has
+ * finished giving us anything useful. We have to be careful about the first record,
+ * though, because it may be genuinely unknown, in which case we'll get two sets of
+ * "??"/"??:0" lines.
+ */
+ if (fprintf(a2l->to_child, "%016"PRIx64"\n,\n", addr) < 0 || fflush(a2l->to_child) != 0) {
+ pr_warning("%s %s: could not send request\n", __func__, dso_name);
+ goto out;
+ }
- strim(funcname);
+ switch (read_addr2line_record(a2l, &record_function, &record_filename, &record_line_nr)) {
+ case -1:
+ pr_warning("%s %s: could not read first record\n", __func__, dso_name);
+ goto out;
+ case 0:
+ /*
+ * The first record was invalid, so return failure, but first read another
+ * record, since we asked a junk question and have to clear the answer out.
+ */
+ switch (read_addr2line_record(a2l, NULL, NULL, NULL)) {
+ case -1:
+ pr_warning("%s %s: could not read delimiter record\n", __func__, dso_name);
+ break;
+ case 0:
+ /* As expected. */
+ break;
+ default:
+ pr_warning("%s %s: unexpected record instead of sentinel",
+ __func__, dso_name);
+ break;
+ }
+ goto out;
+ default:
+ break;
+ }
- if (getline(&filename, &filelen, fp) == -1)
- goto out;
+ if (file) {
+ *file = strdup(record_filename);
+ ret = 1;
+ }
+ if (line_nr)
+ *line_nr = record_line_nr;
- if (filename_split(filename, &line_nr) != 1)
+ if (unwind_inlines) {
+ if (node && inline_list__append_record(dso, node, sym,
+ record_function,
+ record_filename,
+ record_line_nr)) {
+ ret = 0;
goto out;
+ }
+ }
- srcline = srcline_from_fileline(filename, line_nr);
- inline_sym = new_inline_sym(dso, sym, funcname);
-
- if (inline_list__append(inline_sym, srcline, node) != 0) {
- free(srcline);
- if (inline_sym && inline_sym->inlined)
- symbol__delete(inline_sym);
- goto out;
+ /* We have to read the records even if we don't care about the inline info. */
+ while ((record_status = read_addr2line_record(a2l,
+ &record_function,
+ &record_filename,
+ &record_line_nr)) == 1) {
+ if (unwind_inlines && node && inline_count++ < MAX_INLINE_NEST) {
+ if (inline_list__append_record(dso, node, sym,
+ record_function,
+ record_filename,
+ record_line_nr)) {
+ ret = 0;
+ goto out;
+ }
+ ret = 1; /* found at least one inline frame */
}
}
out:
- pclose(fp);
- free(filename);
- free(funcname);
+ free(record_function);
+ free(record_filename);
+ return ret;
+}
- return node;
+void dso__free_a2l(struct dso *dso)
+{
+ struct a2l_subprocess *a2l = dso->a2l;
+
+ if (!a2l)
+ return;
+
+ addr2line_subprocess_cleanup(a2l);
+
+ dso->a2l = NULL;
}
#endif /* HAVE_LIBBFD_SUPPORT */
+static struct inline_node *addr2inlines(const char *dso_name, u64 addr,
+ struct dso *dso, struct symbol *sym)
+{
+ struct inline_node *node;
+
+ node = zalloc(sizeof(*node));
+ if (node == NULL) {
+ perror("not enough memory for the inline node");
+ return NULL;
+ }
+
+ INIT_LIST_HEAD(&node->val);
+ node->addr = addr;
+
+ addr2line(dso_name, addr, NULL, NULL, dso, true, node, sym);
+ return node;
+}
+
/*
* Number of addr2line failures (without success) before disabling it for that
* dso.
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 34a7f5c1fff7..9bc841e09a0c 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -1,8 +1,10 @@
// SPDX-License-Identifier: GPL-2.0
+#include <math.h>
#include <stdio.h>
#include "evsel.h"
#include "stat.h"
#include "color.h"
+#include "debug.h"
#include "pmu.h"
#include "rblist.h"
#include "evlist.h"
@@ -370,12 +372,16 @@ void perf_stat__collect_metric_expr(struct evlist *evsel_list)
{
struct evsel *counter, *leader, **metric_events, *oc;
bool found;
- struct expr_parse_ctx ctx;
+ struct expr_parse_ctx *ctx;
struct hashmap_entry *cur;
size_t bkt;
int i;
- expr__ctx_init(&ctx);
+ ctx = expr__ctx_new();
+ if (!ctx) {
+ pr_debug("expr__ctx_new failed");
+ return;
+ }
evlist__for_each_entry(evsel_list, counter) {
bool invalid = false;
@@ -383,25 +389,25 @@ void perf_stat__collect_metric_expr(struct evlist *evsel_list)
if (!counter->metric_expr)
continue;
- expr__ctx_clear(&ctx);
+ expr__ctx_clear(ctx);
metric_events = counter->metric_events;
if (!metric_events) {
- if (expr__find_other(counter->metric_expr,
- counter->name,
- &ctx, 1) < 0)
+ if (expr__find_ids(counter->metric_expr,
+ counter->name,
+ ctx, 1) < 0)
continue;
metric_events = calloc(sizeof(struct evsel *),
- hashmap__size(&ctx.ids) + 1);
+ hashmap__size(ctx->ids) + 1);
if (!metric_events) {
- expr__ctx_clear(&ctx);
+ expr__ctx_free(ctx);
return;
}
counter->metric_events = metric_events;
}
i = 0;
- hashmap__for_each_entry((&ctx.ids), cur, bkt) {
+ hashmap__for_each_entry(ctx->ids, cur, bkt) {
const char *metric_name = (const char *)cur->key;
found = false;
@@ -453,7 +459,7 @@ void perf_stat__collect_metric_expr(struct evlist *evsel_list)
counter->metric_expr = NULL;
}
}
- expr__ctx_clear(&ctx);
+ expr__ctx_free(ctx);
}
static double runtime_stat_avg(struct runtime_stat *st,
@@ -818,7 +824,6 @@ static int prepare_metric(struct evsel **metric_events,
char *n, *pn;
int i, j, ret;
- expr__ctx_init(pctx);
for (i = 0; metric_events[i]; i++) {
struct saved_value *v;
struct stats *stats;
@@ -880,17 +885,22 @@ static void generic_metric(struct perf_stat_config *config,
struct runtime_stat *st)
{
print_metric_t print_metric = out->print_metric;
- struct expr_parse_ctx pctx;
+ struct expr_parse_ctx *pctx;
double ratio, scale;
int i;
void *ctxp = out->ctx;
- i = prepare_metric(metric_events, metric_refs, &pctx, cpu, st);
- if (i < 0)
+ pctx = expr__ctx_new();
+ if (!pctx)
return;
+ i = prepare_metric(metric_events, metric_refs, pctx, cpu, st);
+ if (i < 0) {
+ expr__ctx_free(pctx);
+ return;
+ }
if (!metric_events[i]) {
- if (expr__parse(&ratio, &pctx, metric_expr, runtime) == 0) {
+ if (expr__parse(&ratio, pctx, metric_expr, runtime) == 0) {
char *unit;
char metric_bf[64];
@@ -926,22 +936,26 @@ static void generic_metric(struct perf_stat_config *config,
(metric_name ? metric_name : name) : "", 0);
}
- expr__ctx_clear(&pctx);
+ expr__ctx_free(pctx);
}
double test_generic_metric(struct metric_expr *mexp, int cpu, struct runtime_stat *st)
{
- struct expr_parse_ctx pctx;
+ struct expr_parse_ctx *pctx;
double ratio = 0.0;
- if (prepare_metric(mexp->metric_events, mexp->metric_refs, &pctx, cpu, st) < 0)
+ pctx = expr__ctx_new();
+ if (!pctx)
+ return NAN;
+
+ if (prepare_metric(mexp->metric_events, mexp->metric_refs, pctx, cpu, st) < 0)
goto out;
- if (expr__parse(&ratio, &pctx, mexp->metric_expr, 1))
+ if (expr__parse(&ratio, pctx, mexp->metric_expr, 1))
ratio = 0.0;
out:
- expr__ctx_clear(&pctx);
+ expr__ctx_free(pctx);
return ratio;
}
diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index a7e981b2d7de..198982109f0f 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -715,7 +715,8 @@ static int __event__synthesize_thread(union perf_event *comm_event,
union perf_event *fork_event,
union perf_event *namespaces_event,
pid_t pid, int full, perf_event__handler_t process,
- struct perf_tool *tool, struct machine *machine, bool mmap_data)
+ struct perf_tool *tool, struct machine *machine,
+ bool needs_mmap, bool mmap_data)
{
char filename[PATH_MAX];
struct dirent **dirent;
@@ -739,7 +740,7 @@ static int __event__synthesize_thread(union perf_event *comm_event,
* send mmap only for thread group leader
* see thread__init_maps()
*/
- if (pid == tgid &&
+ if (pid == tgid && needs_mmap &&
perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
process, machine, mmap_data))
return -1;
@@ -786,7 +787,7 @@ static int __event__synthesize_thread(union perf_event *comm_event,
break;
rc = 0;
- if (_pid == pid && !kernel_thread) {
+ if (_pid == pid && !kernel_thread && needs_mmap) {
/* process the parent's maps too */
rc = perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
process, machine, mmap_data);
@@ -806,7 +807,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
struct perf_thread_map *threads,
perf_event__handler_t process,
struct machine *machine,
- bool mmap_data)
+ bool needs_mmap, bool mmap_data)
{
union perf_event *comm_event, *mmap_event, *fork_event;
union perf_event *namespaces_event;
@@ -836,7 +837,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
fork_event, namespaces_event,
perf_thread_map__pid(threads, thread), 0,
process, tool, machine,
- mmap_data)) {
+ needs_mmap, mmap_data)) {
err = -1;
break;
}
@@ -862,7 +863,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
fork_event, namespaces_event,
comm_event->comm.pid, 0,
process, tool, machine,
- mmap_data)) {
+ needs_mmap, mmap_data)) {
err = -1;
break;
}
@@ -882,6 +883,7 @@ out:
static int __perf_event__synthesize_threads(struct perf_tool *tool,
perf_event__handler_t process,
struct machine *machine,
+ bool needs_mmap,
bool mmap_data,
struct dirent **dirent,
int start,
@@ -926,7 +928,7 @@ static int __perf_event__synthesize_threads(struct perf_tool *tool,
*/
__event__synthesize_thread(comm_event, mmap_event, fork_event,
namespaces_event, pid, 1, process,
- tool, machine, mmap_data);
+ tool, machine, needs_mmap, mmap_data);
}
err = 0;
@@ -945,6 +947,7 @@ struct synthesize_threads_arg {
struct perf_tool *tool;
perf_event__handler_t process;
struct machine *machine;
+ bool needs_mmap;
bool mmap_data;
struct dirent **dirent;
int num;
@@ -956,7 +959,8 @@ static void *synthesize_threads_worker(void *arg)
struct synthesize_threads_arg *args = arg;
__perf_event__synthesize_threads(args->tool, args->process,
- args->machine, args->mmap_data,
+ args->machine,
+ args->needs_mmap, args->mmap_data,
args->dirent,
args->start, args->num);
return NULL;
@@ -965,7 +969,7 @@ static void *synthesize_threads_worker(void *arg)
int perf_event__synthesize_threads(struct perf_tool *tool,
perf_event__handler_t process,
struct machine *machine,
- bool mmap_data,
+ bool needs_mmap, bool mmap_data,
unsigned int nr_threads_synthesize)
{
struct synthesize_threads_arg *args = NULL;
@@ -994,7 +998,8 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
if (thread_nr <= 1) {
err = __perf_event__synthesize_threads(tool, process,
- machine, mmap_data,
+ machine,
+ needs_mmap, mmap_data,
dirent, base, n);
goto free_dirent;
}
@@ -1015,6 +1020,7 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
args[i].tool = tool;
args[i].process = process;
args[i].machine = machine;
+ args[i].needs_mmap = needs_mmap;
args[i].mmap_data = mmap_data;
args[i].dirent = dirent;
}
@@ -1775,26 +1781,27 @@ out_err:
int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
struct target *target, struct perf_thread_map *threads,
- perf_event__handler_t process, bool data_mmap,
- unsigned int nr_threads_synthesize)
+ perf_event__handler_t process, bool needs_mmap,
+ bool data_mmap, unsigned int nr_threads_synthesize)
{
if (target__has_task(target))
- return perf_event__synthesize_thread_map(tool, threads, process, machine, data_mmap);
+ return perf_event__synthesize_thread_map(tool, threads, process, machine,
+ needs_mmap, data_mmap);
else if (target__has_cpu(target))
- return perf_event__synthesize_threads(tool, process,
- machine, data_mmap,
+ return perf_event__synthesize_threads(tool, process, machine,
+ needs_mmap, data_mmap,
nr_threads_synthesize);
/* command specified */
return 0;
}
int machine__synthesize_threads(struct machine *machine, struct target *target,
- struct perf_thread_map *threads, bool data_mmap,
- unsigned int nr_threads_synthesize)
+ struct perf_thread_map *threads, bool needs_mmap,
+ bool data_mmap, unsigned int nr_threads_synthesize)
{
return __machine__synthesize_threads(machine, NULL, target, threads,
- perf_event__process, data_mmap,
- nr_threads_synthesize);
+ perf_event__process, needs_mmap,
+ data_mmap, nr_threads_synthesize);
}
static struct perf_record_event_update *event_update_event__new(size_t size, u64 type, u64 id)
@@ -2230,3 +2237,31 @@ int perf_event__synthesize_for_pipe(struct perf_tool *tool,
return ret;
}
+
+int parse_synth_opt(char *synth)
+{
+ char *p, *q;
+ int ret = 0;
+
+ if (synth == NULL)
+ return -1;
+
+ for (q = synth; (p = strsep(&q, ",")); p = q) {
+ if (!strcasecmp(p, "no") || !strcasecmp(p, "none"))
+ return 0;
+
+ if (!strcasecmp(p, "all"))
+ return PERF_SYNTH_ALL;
+
+ if (!strcasecmp(p, "task"))
+ ret |= PERF_SYNTH_TASK;
+ else if (!strcasecmp(p, "mmap"))
+ ret |= PERF_SYNTH_TASK | PERF_SYNTH_MMAP;
+ else if (!strcasecmp(p, "cgroup"))
+ ret |= PERF_SYNTH_CGROUP;
+ else
+ return -1;
+ }
+
+ return ret;
+}
diff --git a/tools/perf/util/synthetic-events.h b/tools/perf/util/synthetic-events.h
index c845e2b9b444..c931433bacbf 100644
--- a/tools/perf/util/synthetic-events.h
+++ b/tools/perf/util/synthetic-events.h
@@ -27,6 +27,18 @@ struct target;
union perf_event;
+enum perf_record_synth {
+ PERF_SYNTH_TASK = 1 << 0,
+ PERF_SYNTH_MMAP = 1 << 1,
+ PERF_SYNTH_CGROUP = 1 << 2,
+
+ /* last element */
+ PERF_SYNTH_MAX = 1 << 3,
+};
+#define PERF_SYNTH_ALL (PERF_SYNTH_MAX - 1)
+
+int parse_synth_opt(char *str);
+
typedef int (*perf_event__handler_t)(struct perf_tool *tool, union perf_event *event,
struct perf_sample *sample, struct machine *machine);
@@ -53,8 +65,8 @@ int perf_event__synthesize_stat_events(struct perf_stat_config *config, struct p
int perf_event__synthesize_stat_round(struct perf_tool *tool, u64 time, u64 type, perf_event__handler_t process, struct machine *machine);
int perf_event__synthesize_stat(struct perf_tool *tool, u32 cpu, u32 thread, u64 id, struct perf_counts_values *count, perf_event__handler_t process, struct machine *machine);
int perf_event__synthesize_thread_map2(struct perf_tool *tool, struct perf_thread_map *threads, perf_event__handler_t process, struct machine *machine);
-int perf_event__synthesize_thread_map(struct perf_tool *tool, struct perf_thread_map *threads, perf_event__handler_t process, struct machine *machine, bool mmap_data);
-int perf_event__synthesize_threads(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine, bool mmap_data, unsigned int nr_threads_synthesize);
+int perf_event__synthesize_thread_map(struct perf_tool *tool, struct perf_thread_map *threads, perf_event__handler_t process, struct machine *machine, bool needs_mmap, bool mmap_data);
+int perf_event__synthesize_threads(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine, bool needs_mmap, bool mmap_data, unsigned int nr_threads_synthesize);
int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd, struct evlist *evlist, perf_event__handler_t process);
int perf_event__synth_time_conv(const struct perf_event_mmap_page *pc, struct perf_tool *tool, perf_event__handler_t process, struct machine *machine);
pid_t perf_event__synthesize_comm(struct perf_tool *tool, union perf_event *event, pid_t pid, perf_event__handler_t process, struct machine *machine);
@@ -65,10 +77,10 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
struct target *target, struct perf_thread_map *threads,
- perf_event__handler_t process, bool data_mmap,
+ perf_event__handler_t process, bool needs_mmap, bool data_mmap,
unsigned int nr_threads_synthesize);
int machine__synthesize_threads(struct machine *machine, struct target *target,
- struct perf_thread_map *threads, bool data_mmap,
+ struct perf_thread_map *threads, bool needs_mmap, bool data_mmap,
unsigned int nr_threads_synthesize);
#ifdef HAVE_AUXTRACE_SUPPORT