Merge tag 'perf-tools-for-v6.5-1-2023-06-28' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools-next

Pull perf tools updates from Namhyung Kim:
 "Internal cleanup:

   - Refactor PMU data management to handle hybrid systems in a generic
     way.

     Do more work in the lexer so that legacy event types parse more
     easily. A side-effect of this is that if a PMU is specified,
     scanning sysfs is avoided improving start-up time.

   - Fix hybrid metrics, for example, the TopdownL1 works for both
     performance and efficiency cores on Intel machines. To support
     this, sort and regroup events after parsing.

   - Add reference count checking for the 'thread' data structure.

   - Lots of fixes for memory leaks in various places thanks to the ASAN
     and Ian's refcount checker.

   - Reduce the binary size by replacing static variables with local or
     dynamically allocated memory.

   - Introduce shared_mutex for annotate data to reduce memory
     footprint.

   - Make filesystem access library functions more thread safe.

  Test:

   - Organize cpu_map tests into a single suite.

   - Add metric value validation test to check if the values are within
     correct value ranges.

   - Add perf stat stdio output test to check if event and metric names
     match.

   - Add perf data converter JSON output test.

   - Fix a lot of issues reported by shellcheck(1). This is a
     preparation to enable shellcheck by default.

   - Make the large x86 new instructions test optional at build time
     using EXTRA_TESTS=1.

   - Add a test for libpfm4 events.

  perf script:

   - Add 'dsoff' outpuf field to display offset from the DSO.

      $ perf script -F comm,pid,event,ip,dsoff
         ls 2695501 cycles:      152cc73ef4b5 (/usr/lib/x86_64-linux-gnu/ld-2.31.so+0x1c4b5)
         ls 2695501 cycles:  ffffffff99045b3e ([kernel.kallsyms])
         ls 2695501 cycles:  ffffffff9968e107 ([kernel.kallsyms])
         ls 2695501 cycles:  ffffffffc1f54afb ([kernel.kallsyms])
         ls 2695501 cycles:  ffffffff9968382f ([kernel.kallsyms])
         ls 2695501 cycles:  ffffffff99e00094 ([kernel.kallsyms])
         ls 2695501 cycles:      152cc718a8d0 (/usr/lib/x86_64-linux-gnu/libselinux.so.1+0x68d0)
         ls 2695501 cycles:  ffffffff992a6db0 ([kernel.kallsyms])

   - Adjust width for large PID/TID values.

  perf report:

   - Robustify reading addr2line output for srcline by checking sentinel
     output before the actual data and by using timeout of 1 second.

   - Allow config terms (like 'name=ABC') with breakpoint events.

      $ perf record -e mem:0x55feb98dd169:x/name=breakpoint/ -p 19646 -- sleep 1

  perf annotate:

   - Handle x86 instruction suffix like 'l' in 'movl' generally.

   - Parse instruction operands properly even with a whitespace. This is
     needed for llvm-objdump output.

   - Support RISC-V binutils lookup using the triplet prefixes.

   - Add '<' and '>' key to navigate to prev/next symbols in TUI.

   - Fix instruction association and parsing for LoongArch.

  perf stat:

   - Add --per-cache aggregation option, optionally specify a cache
     level like `--per-cache=L2`.

      $ sudo perf stat --per-cache -a -e ls_dmnd_fills_from_sys.ext_cache_remote --\
        taskset -c 0-15,64-79,128-143,192-207\
        perf bench sched messaging -p -t -l 100000 -g 8

        # Running 'sched/messaging' benchmark:
        # 20 sender and receiver threads per group
        # 8 groups == 320 threads run

        Total time: 7.648 [sec]

        Performance counter stats for 'system wide':

        S0-D0-L3-ID0             16         17,145,912      ls_dmnd_fills_from_sys.ext_cache_remote
        S0-D0-L3-ID8             16         14,977,628      ls_dmnd_fills_from_sys.ext_cache_remote
        S0-D0-L3-ID16            16            262,539      ls_dmnd_fills_from_sys.ext_cache_remote
        S0-D0-L3-ID24            16              3,140      ls_dmnd_fills_from_sys.ext_cache_remote
        S0-D0-L3-ID32            16             27,403      ls_dmnd_fills_from_sys.ext_cache_remote
        S0-D0-L3-ID40            16             17,026      ls_dmnd_fills_from_sys.ext_cache_remote
        S0-D0-L3-ID48            16              7,292      ls_dmnd_fills_from_sys.ext_cache_remote
        S0-D0-L3-ID56            16              2,464      ls_dmnd_fills_from_sys.ext_cache_remote
        S1-D1-L3-ID64            16         22,489,306      ls_dmnd_fills_from_sys.ext_cache_remote
        S1-D1-L3-ID72            16         21,455,257      ls_dmnd_fills_from_sys.ext_cache_remote
        S1-D1-L3-ID80            16             11,619      ls_dmnd_fills_from_sys.ext_cache_remote
        S1-D1-L3-ID88            16             30,978      ls_dmnd_fills_from_sys.ext_cache_remote
        S1-D1-L3-ID96            16             37,628      ls_dmnd_fills_from_sys.ext_cache_remote
        S1-D1-L3-ID104           16             13,594      ls_dmnd_fills_from_sys.ext_cache_remote
        S1-D1-L3-ID112           16             10,164      ls_dmnd_fills_from_sys.ext_cache_remote
        S1-D1-L3-ID120           16             11,259      ls_dmnd_fills_from_sys.ext_cache_remote

              7.779171484 seconds time elapsed

   - Change default (no event/metric) formatting for default metrics so
     that events are hidden and the metric and group appear.

       Performance counter stats for 'ls /':

                    1.85 msec task-clock                       #    0.594 CPUs utilized
                       0      context-switches                 #    0.000 /sec
                       0      cpu-migrations                   #    0.000 /sec
                      97      page-faults                      #   52.517 K/sec
               2,187,173      cycles                           #    1.184 GHz
               2,474,459      instructions                     #    1.13  insn per cycle
                 531,584      branches                         #  287.805 M/sec
                  13,626      branch-misses                    #    2.56% of all branches
                              TopdownL1                 #     23.5 %  tma_backend_bound
                                                        #     11.5 %  tma_bad_speculation
                                                        #     39.1 %  tma_frontend_bound
                                                        #     25.9 %  tma_retiring

   - Allow --cputype option to have any PMU name (not just hybrid).

   - Fix output value not to added when it runs multiple times with -r
     option.

  perf list:

   - Show metricgroup description from JSON file called
     metricgroups.json.

   - Allow 'pfm' argument to list only libpfm4 events and check each
     event is supported before showing it.

  JSON vendor events:

   - Avoid event grouping using "NO_GROUP_EVENTS" constraints. The
     topdown events are correctly grouped even if no group exists.

   - Add "Default" metric group to print it in the default output. And
     use "DefaultMetricgroupName" to indicate the real metric group
     name.

   - Add AmpereOne core PMU events.

  Misc:

   - Define man page date correctly.

   - Track exception level properly on ARM CoreSight ETM.

   - Allow anonymous struct, union or enum when retrieving type names
     from DWARF.

   - Fix incorrect filename when calling `perf inject --jit`.

   - Handle PLT size correctly on LoongArch"

* tag 'perf-tools-for-v6.5-1-2023-06-28' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools-next: (269 commits)
  perf test: Skip metrics w/o event name in stat STD output linter
  perf test: Reorder event name checks in stat STD output linter
  perf pmu: Remove a hard coded cpu PMU assumption
  perf pmus: Add notion of default PMU for JSON events
  perf unwind: Fix map reference counts
  perf test: Set PERF_EXEC_PATH for script execution
  perf script: Initialize buffer for regs_map()
  perf tests: Fix test_arm_callgraph_fp variable expansion
  perf symbol: Add LoongArch case in get_plt_sizes()
  perf test: Remove x permission from lib/stat_output.sh
  perf test: Rerun failed metrics with longer workload
  perf test: Add skip list for metrics known would fail
  perf test: Add metric value validation test
  perf jit: Fix incorrect file name in DWARF line table
  perf annotate: Fix instruction association and parsing for LoongArch
  perf annotation: Switch lock from a mutex to a sharded_mutex
  perf sharded_mutex: Introduce sharded_mutex
  tools: Fix incorrect calculation of object size by sizeof
  perf subcmd: Fix missing check for return value of malloc() in add_cmdname()
  perf parse-events: Remove unneeded semicolon
  ...

1 files changed, 31 insertions, 18 deletions

diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 41d4f9e6a8b7..94312741443a 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -93,8 +93,6 @@ PyMODINIT_FUNC PyInit_perf_trace_context(void);
 #define TRACE_EVENT_TYPE_MAX				\
 	((1 << (sizeof(unsigned short) * 8)) - 1)
 
-static DECLARE_BITMAP(events_defined, TRACE_EVENT_TYPE_MAX);
-
 #define N_COMMON_FIELDS	7
 
 static char *cur_field_name;
@@ -419,6 +417,7 @@ static PyObject *python_process_callchain(struct perf_sample *sample,
 					 struct addr_location *al)
 {
 	PyObject *pylist;
+	struct callchain_cursor *cursor;
 
 	pylist = PyList_New(0);
 	if (!pylist)
@@ -427,19 +426,20 @@ static PyObject *python_process_callchain(struct perf_sample *sample,
 	if (!symbol_conf.use_callchain || !sample->callchain)
 		goto exit;
 
-	if (thread__resolve_callchain(al->thread, &callchain_cursor, evsel,
+	cursor = get_tls_callchain_cursor();
+	if (thread__resolve_callchain(al->thread, cursor, evsel,
 				      sample, NULL, NULL,
 				      scripting_max_stack) != 0) {
 		pr_err("Failed to resolve callchain. Skipping\n");
 		goto exit;
 	}
-	callchain_cursor_commit(&callchain_cursor);
+	callchain_cursor_commit(cursor);
 
 
 	while (1) {
 		PyObject *pyelem;
 		struct callchain_cursor_node *node;
-		node = callchain_cursor_current(&callchain_cursor);
+		node = callchain_cursor_current(cursor);
 		if (!node)
 			break;
 
@@ -471,9 +471,11 @@ static PyObject *python_process_callchain(struct perf_sample *sample,
 				struct addr_location node_al;
 				unsigned long offset;
 
+				addr_location__init(&node_al);
 				node_al.addr = map__map_ip(map, node->ip);
-				node_al.map  = map;
+				node_al.map  = map__get(map);
 				offset = get_offset(node->ms.sym, &node_al);
+				addr_location__exit(&node_al);
 
 				pydict_set_item_string_decref(
 					pyelem, "sym_off",
@@ -493,7 +495,7 @@ static PyObject *python_process_callchain(struct perf_sample *sample,
 					_PyUnicode_FromString(dsoname));
 		}
 
-		callchain_cursor_advance(&callchain_cursor);
+		callchain_cursor_advance(cursor);
 		PyList_Append(pylist, pyelem);
 		Py_DECREF(pyelem);
 	}
@@ -541,6 +543,7 @@ static PyObject *python_process_brstack(struct perf_sample *sample,
 		pydict_set_item_string_decref(pyelem, "cycles",
 		    PyLong_FromUnsignedLongLong(entries[i].flags.cycles));
 
+		addr_location__init(&al);
 		thread__find_map_fb(thread, sample->cpumode,
 				    entries[i].from, &al);
 		dsoname = get_dsoname(al.map);
@@ -553,6 +556,7 @@ static PyObject *python_process_brstack(struct perf_sample *sample,
 		pydict_set_item_string_decref(pyelem, "to_dsoname",
 					      _PyUnicode_FromString(dsoname));
 
+		addr_location__exit(&al);
 		PyList_Append(pylist, pyelem);
 		Py_DECREF(pyelem);
 	}
@@ -596,7 +600,6 @@ static PyObject *python_process_brstacksym(struct perf_sample *sample,
 	PyObject *pylist;
 	u64 i;
 	char bf[512];
-	struct addr_location al;
 
 	pylist = PyList_New(0);
 	if (!pylist)
@@ -607,7 +610,9 @@ static PyObject *python_process_brstacksym(struct perf_sample *sample,
 
 	for (i = 0; i < br->nr; i++) {
 		PyObject *pyelem;
+		struct addr_location al;
 
+		addr_location__init(&al);
 		pyelem = PyDict_New();
 		if (!pyelem)
 			Py_FatalError("couldn't create Python dictionary");
@@ -646,6 +651,7 @@ static PyObject *python_process_brstacksym(struct perf_sample *sample,
 
 		PyList_Append(pylist, pyelem);
 		Py_DECREF(pyelem);
+		addr_location__exit(&al);
 	}
 
 exit:
@@ -733,6 +739,9 @@ static void regs_map(struct regs_dump *regs, uint64_t mask, const char *arch, ch
 
 	bf[0] = 0;
 
+	if (size <= 0)
+		return;
+
 	if (!regs || !regs->regs)
 		return;
 
@@ -760,17 +769,18 @@ static void set_regs_in_dict(PyObject *dict,
 	 * 10 chars is for register name.
 	 */
 	int size = __sw_hweight64(attr->sample_regs_intr) * 28;
-	char bf[size];
+	char *bf = malloc(size);
 
-	regs_map(&sample->intr_regs, attr->sample_regs_intr, arch, bf, sizeof(bf));
+	regs_map(&sample->intr_regs, attr->sample_regs_intr, arch, bf, size);
 
 	pydict_set_item_string_decref(dict, "iregs",
 			_PyUnicode_FromString(bf));
 
-	regs_map(&sample->user_regs, attr->sample_regs_user, arch, bf, sizeof(bf));
+	regs_map(&sample->user_regs, attr->sample_regs_user, arch, bf, size);
 
 	pydict_set_item_string_decref(dict, "uregs",
 			_PyUnicode_FromString(bf));
+	free(bf);
 }
 
 static void set_sym_in_dict(PyObject *dict, struct addr_location *al,
@@ -934,6 +944,9 @@ static void python_process_tracepoint(struct perf_sample *sample,
 	unsigned long long nsecs = sample->time;
 	const char *comm = thread__comm_str(al->thread);
 	const char *default_handler_name = "trace_unhandled";
+	DECLARE_BITMAP(events_defined, TRACE_EVENT_TYPE_MAX);
+
+	bitmap_zero(events_defined, TRACE_EVENT_TYPE_MAX);
 
 	if (!event) {
 		snprintf(handler_name, sizeof(handler_name),
@@ -1162,11 +1175,11 @@ static int python_export_thread(struct db_export *dbe, struct thread *thread,
 
 	t = tuple_new(5);
 
-	tuple_set_d64(t, 0, thread->db_id);
+	tuple_set_d64(t, 0, thread__db_id(thread));
 	tuple_set_d64(t, 1, machine->db_id);
 	tuple_set_d64(t, 2, main_thread_db_id);
-	tuple_set_s32(t, 3, thread->pid_);
-	tuple_set_s32(t, 4, thread->tid);
+	tuple_set_s32(t, 3, thread__pid(thread));
+	tuple_set_s32(t, 4, thread__tid(thread));
 
 	call_object(tables->thread_handler, t, "thread_table");
 
@@ -1185,7 +1198,7 @@ static int python_export_comm(struct db_export *dbe, struct comm *comm,
 
 	tuple_set_d64(t, 0, comm->db_id);
 	tuple_set_string(t, 1, comm__str(comm));
-	tuple_set_d64(t, 2, thread->db_id);
+	tuple_set_d64(t, 2, thread__db_id(thread));
 	tuple_set_d64(t, 3, comm->start);
 	tuple_set_s32(t, 4, comm->exec);
 
@@ -1206,7 +1219,7 @@ static int python_export_comm_thread(struct db_export *dbe, u64 db_id,
 
 	tuple_set_d64(t, 0, db_id);
 	tuple_set_d64(t, 1, comm->db_id);
-	tuple_set_d64(t, 2, thread->db_id);
+	tuple_set_d64(t, 2, thread__db_id(thread));
 
 	call_object(tables->comm_thread_handler, t, "comm_thread_table");
 
@@ -1291,7 +1304,7 @@ static void python_export_sample_table(struct db_export *dbe,
 	tuple_set_d64(t, 0, es->db_id);
 	tuple_set_d64(t, 1, es->evsel->db_id);
 	tuple_set_d64(t, 2, maps__machine(es->al->maps)->db_id);
-	tuple_set_d64(t, 3, es->al->thread->db_id);
+	tuple_set_d64(t, 3, thread__db_id(es->al->thread));
 	tuple_set_d64(t, 4, es->comm_db_id);
 	tuple_set_d64(t, 5, es->dso_db_id);
 	tuple_set_d64(t, 6, es->sym_db_id);
@@ -1381,7 +1394,7 @@ static int python_export_call_return(struct db_export *dbe,
 	t = tuple_new(14);
 
 	tuple_set_d64(t, 0, cr->db_id);
-	tuple_set_d64(t, 1, cr->thread->db_id);
+	tuple_set_d64(t, 1, thread__db_id(cr->thread));
 	tuple_set_d64(t, 2, comm_db_id);
 	tuple_set_d64(t, 3, cr->cp->db_id);
 	tuple_set_d64(t, 4, cr->call_time);