Merge tag 'perf-tools-for-v6.11-2024-07-16' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools

Pull perf tools updates from Namhyung Kim:
 "Build:

   - Build each directory as a library so that depedency check for the
     python extension module can be automatic

   - Use pkg-config to check libtraceevent and libtracefs

  perf sched:

   - Add --task-name and --fuzzy-name options for `perf sched map`

     It focuses on selected tasks only by removing unrelated tasks in
     the output. It matches the task comm with the given string and the
     --fuzzy-name option allows the partial matching:

       $ sudo perf sched record -a sleep 1

       $ sudo perf sched map --task-name kworker --fuzzy-name
          .   .   .   .   -  *A0  .   .    481065.315131 secs A0 => kworker/5:2-i91:438521
          .   .   .   .   -  *-   .   .    481065.315160 secs
         *B0  .   .   .   -   .   .   .    481065.316435 secs B0 => kworker/0:0-i91:437860
         *-   .   .   .   .   .   .   .    481065.316441 secs
          .   .   .   .   .  *A0  .   .    481065.318703 secs
          .   .   .   .   .  *-   .   .    481065.318717 secs
          .   .  *C0  .   .   .   .   .    481065.320544 secs C0 => kworker/u16:30-:430186
          .   .  *-   .   .   .   .   .    481065.320555 secs
          .   .  *D0  .   .   .   .   .    481065.328524 secs D0 => kworker/2:0-kdm:429654
         *B0  .   D0  .   -   .   .   .    481065.328527 secs
         *-   .   D0  .   -   .   .   .    481065.328535 secs
          .   .  *-   .   .   .   .   .    481065.328535 secs

   - Fix -r/--repeat option of perf sched replay

     The documentation said -1 will work as infinity but it didn't
     accept the value. Update the code and document to use 0 instead

   - Fix perf sched timehist to account the delay time for preempted
     tasks

  Perf event filtering:

   - perf top gained filtering support on regular events using BPF like
     perf record. Previously it was able to use it for tracepoints only

   - The BPF filter now supports filtering by UID/GID. This should be
     preferred than -u <UID> option as it's racy to scan /proc to check
     tasks for the user and fails to open an event for the task if it's
     already gone

       $ sudo perf top -e cycles --filter "uid == $(id -u)"

  perf report:

   - Skip dummy events in the group output by default. The --skip-empty
     option controls display of empty events without samples. But perf
     report can force display all events in a group

     In this case, auto-added a dummy event (for a system-wide record)
     ends up in the output. Now it can skip those empty events even in
     the group display mode

     To preserve the old behavior, run this:

       $ perf report --group --no-skip-empty

  perf stat:

   - Choose the most disaggregate option when multiple aggregation
     options are given. It used to pick the last option in the command
     line but it can be confusing and not consistent. Now it'll choose
     the smallest unit

     For example, it'd aggregate the result per-core when the user gave
     both --per-socket and --per-core options at the same time

  Internals:

   - Fix `perf bench` when some CPUs are offline

   - Fix handling of JIT symbol mappings to accept "/tmp/perf-${PID}.map
     patterns only so that it can not be confused by other /tmp/perf-*
     files

   - Many improvements and fixes for `perf test`

  Others:

   - Support some new instructions for Intel-PT

   - Fix syscall ID mapping in perf trace

   - Document AMD IBS PMU usages

   - Change `perf lock info` to show map and thread info by default

  Vendor JSON events:

   - Update Intel events and metrics

   - Add i.MX9[35] DDR metrics"

* tag 'perf-tools-for-v6.11-2024-07-16' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools: (125 commits)
  perf trace: Fix iteration of syscall ids in syscalltbl->entries
  perf dso: Fix address sanitizer build
  perf mem: Warn if memory events are not supported on all CPUs
  perf arm-spe: Support multiple Arm SPE PMUs
  perf build x86: Fix SC2034 error in syscalltbl.sh
  perf record: Fix memset out-of-range error
  perf sched map: Add --fuzzy-name option for fuzzy matching in task names
  perf sched map: Add support for multiple task names using CSV
  perf sched map: Add task-name option to filter the output map
  perf build: Conditionally add feature check flags for libtrace{event,fs}
  perf install: Don't propagate subdir to Documentation submake
  perf vendor events arm64:: Add i.MX95 DDR Performance Monitor metrics
  perf vendor events arm64:: Add i.MX93 DDR Performance Monitor metrics
  perf dsos: When adding a dso into sorted dsos maintain the sort order
  perf comm str: Avoid sort during insert
  perf report: Calling available function for stats printing
  perf intel-pt: Fix exclude_guest setting
  perf intel-pt: Fix aux_watermark calculation for 64-bit size
  perf sched replay: Fix -r/--repeat command line option for infinity
  perf: pmus: Remove unneeded semicolon
  ...

1 files changed, 98 insertions, 173 deletions

diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 0aeb97c11c03..3be882b2e845 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -10,21 +10,19 @@
 #endif
 #include <perf/mmap.h>
 #include "evlist.h"
-#include "callchain.h"
 #include "evsel.h"
 #include "event.h"
 #include "print_binary.h"
 #include "thread_map.h"
 #include "trace-event.h"
 #include "mmap.h"
-#include "stat.h"
-#include "metricgroup.h"
 #include "util/bpf-filter.h"
 #include "util/env.h"
-#include "util/pmu.h"
-#include "util/pmus.h"
+#include "util/kvm-stat.h"
+#include "util/kwork.h"
+#include "util/lock-contention.h"
 #include <internal/lib.h>
-#include "util.h"
+#include "../builtin.h"
 
 #if PY_MAJOR_VERSION < 3
 #define _PyUnicode_FromString(arg) \
@@ -50,166 +48,6 @@
 #define Py_TYPE(ob) (((PyObject*)(ob))->ob_type)
 #endif
 
-/*
- * Avoid bringing in event parsing.
- */
-int parse_event(struct evlist *evlist __maybe_unused, const char *str __maybe_unused)
-{
-	return 0;
-}
-
-/*
- * Provide these two so that we don't have to link against callchain.c and
- * start dragging hist.c, etc.
- */
-struct callchain_param callchain_param;
-
-int parse_callchain_record(const char *arg __maybe_unused,
-			   struct callchain_param *param __maybe_unused)
-{
-	return 0;
-}
-
-/*
- * Add these not to drag util/env.c
- */
-struct perf_env perf_env;
-
-const char *perf_env__cpuid(struct perf_env *env __maybe_unused)
-{
-	return NULL;
-}
-
-// This one is a bit easier, wouldn't drag too much, but leave it as a stub we need it here
-const char *perf_env__arch(struct perf_env *env __maybe_unused)
-{
-	return NULL;
-}
-
-/*
- * These ones are needed not to drag the PMU bandwagon, jevents generated
- * pmu_sys_event_tables, etc and evsel__find_pmu() is used so far just for
- * doing per PMU perf_event_attr.exclude_guest handling, not really needed, so
- * far, for the perf python binding known usecases, revisit if this become
- * necessary.
- */
-struct perf_pmu *evsel__find_pmu(const struct evsel *evsel __maybe_unused)
-{
-	return NULL;
-}
-
-int perf_pmu__scan_file(const struct perf_pmu *pmu, const char *name, const char *fmt, ...)
-{
-	return EOF;
-}
-
-const char *perf_pmu__name_from_config(struct perf_pmu *pmu __maybe_unused, u64 config __maybe_unused)
-{
-	return NULL;
-}
-
-struct perf_pmu *perf_pmus__find_by_type(unsigned int type __maybe_unused)
-{
-	return NULL;
-}
-
-int perf_pmus__num_core_pmus(void)
-{
-	return 1;
-}
-
-bool evsel__is_aux_event(const struct evsel *evsel __maybe_unused)
-{
-	return false;
-}
-
-bool perf_pmus__supports_extended_type(void)
-{
-	return false;
-}
-
-/*
- * Add this one here not to drag util/metricgroup.c
- */
-int metricgroup__copy_metric_events(struct evlist *evlist, struct cgroup *cgrp,
-				    struct rblist *new_metric_events,
-				    struct rblist *old_metric_events)
-{
-	return 0;
-}
-
-/*
- * Add this one here not to drag util/trace-event-info.c
- */
-char *tracepoint_id_to_name(u64 config)
-{
-	return NULL;
-}
-
-/*
- * XXX: All these evsel destructors need some better mechanism, like a linked
- * list of destructors registered when the relevant code indeed is used instead
- * of having more and more calls in perf_evsel__delete(). -- acme
- *
- * For now, add some more:
- *
- * Not to drag the BPF bandwagon...
- */
-void bpf_counter__destroy(struct evsel *evsel);
-int bpf_counter__install_pe(struct evsel *evsel, int cpu, int fd);
-int bpf_counter__disable(struct evsel *evsel);
-
-void bpf_counter__destroy(struct evsel *evsel __maybe_unused)
-{
-}
-
-int bpf_counter__install_pe(struct evsel *evsel __maybe_unused, int cpu __maybe_unused, int fd __maybe_unused)
-{
-	return 0;
-}
-
-int bpf_counter__disable(struct evsel *evsel __maybe_unused)
-{
-	return 0;
-}
-
-// not to drag util/bpf-filter.c
-#ifdef HAVE_BPF_SKEL
-int perf_bpf_filter__prepare(struct evsel *evsel __maybe_unused)
-{
-	return 0;
-}
-
-int perf_bpf_filter__destroy(struct evsel *evsel __maybe_unused)
-{
-	return 0;
-}
-#endif
-
-/*
- * Support debug printing even though util/debug.c is not linked.  That means
- * implementing 'verbose' and 'eprintf'.
- */
-int verbose;
-int debug_kmaps;
-int debug_peo_args;
-
-int eprintf(int level, int var, const char *fmt, ...);
-
-int eprintf(int level, int var, const char *fmt, ...)
-{
-	va_list args;
-	int ret = 0;
-
-	if (var >= level) {
-		va_start(args, fmt);
-		ret = vfprintf(stderr, fmt, args);
-		va_end(args);
-	}
-
-	return ret;
-}
-
 /* Define PyVarObject_HEAD_INIT for python 2.5 */
 #ifndef PyVarObject_HEAD_INIT
 # define PyVarObject_HEAD_INIT(type, size) PyObject_HEAD_INIT(type) size,
@@ -1510,15 +1348,102 @@ error:
 #endif
 }
 
-/*
- * Dummy, to avoid dragging all the test_attr infrastructure in the python
- * binding.
- */
-void test_attr__open(struct perf_event_attr *attr, pid_t pid, struct perf_cpu cpu,
-                     int fd, int group_fd, unsigned long flags)
+
+/* The following are stubs to avoid dragging in builtin-* objects. */
+/* TODO: move the code out of the builtin-* file into util. */
+
+unsigned int scripting_max_stack = PERF_MAX_STACK_DEPTH;
+
+bool kvm_entry_event(struct evsel *evsel __maybe_unused)
 {
+	return false;
+}
+
+bool kvm_exit_event(struct evsel *evsel __maybe_unused)
+{
+	return false;
+}
+
+bool exit_event_begin(struct evsel *evsel __maybe_unused,
+		      struct perf_sample *sample  __maybe_unused,
+		      struct event_key *key  __maybe_unused)
+{
+	return false;
+}
+
+bool exit_event_end(struct evsel *evsel __maybe_unused,
+		    struct perf_sample *sample __maybe_unused,
+		    struct event_key *key __maybe_unused)
+{
+	return false;
+}
+
+void exit_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused,
+			   struct event_key *key __maybe_unused,
+			   char *decode __maybe_unused)
+{
+}
+
+int find_scripts(char **scripts_array  __maybe_unused, char **scripts_path_array  __maybe_unused,
+		int num  __maybe_unused, int pathlen __maybe_unused)
+{
+	return -1;
+}
+
+void perf_stat__set_no_csv_summary(int set __maybe_unused)
+{
+}
+
+void perf_stat__set_big_num(int set __maybe_unused)
+{
+}
+
+int script_spec_register(const char *spec __maybe_unused, struct scripting_ops *ops __maybe_unused)
+{
+	return -1;
+}
+
+arch_syscalls__strerrno_t *arch_syscalls__strerrno_function(const char *arch __maybe_unused)
+{
+	return NULL;
+}
+
+struct kwork_work *perf_kwork_add_work(struct perf_kwork *kwork __maybe_unused,
+				       struct kwork_class *class __maybe_unused,
+				       struct kwork_work *key  __maybe_unused)
+{
+	return NULL;
+}
+
+void script_fetch_insn(struct perf_sample *sample __maybe_unused,
+		struct thread *thread __maybe_unused,
+		struct machine *machine __maybe_unused)
+{
+}
+
+int perf_sample__sprintf_flags(u32 flags __maybe_unused, char *str __maybe_unused,
+			size_t sz __maybe_unused)
+{
+	return -1;
+}
+
+bool match_callstack_filter(struct machine *machine __maybe_unused, u64 *callstack __maybe_unused)
+{
+	return false;
+}
+
+struct lock_stat *lock_stat_find(u64 addr __maybe_unused)
+{
+	return NULL;
+}
+
+struct lock_stat *lock_stat_findnew(u64 addr __maybe_unused, const char *name __maybe_unused,
+				int flags __maybe_unused)
+{
+	return NULL;
 }
 
-void evlist__free_stats(struct evlist *evlist)
+int cmd_inject(int argc __maybe_unused, const char *argv[] __maybe_unused)
 {
+	return -1;
 }