Merge tag 'perf-tools-for-v6.13-2024-11-24' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools

Pull perf tools updates from Namhyung Kim:
 "perf record:

   - Enable leader sampling for inherited task events. It was supported
     only for system-wide events but the kernel started to support such
     a setup since v6.12.

     This is to reduce the number of PMU interrupts. The samples of the
     leader event will contain counts of other events and no samples
     will be generated for the other member events.

       $ perf record -e '{cycles,instructions}:S'  ${MYPROG}

  perf report:

   - Fix --branch-history option to display more branch-related
     information like prediction, abort and cycles which is available
     on Intel machines.

       $ perf record -bg -- perf test -w brstack

       $ perf report --branch-history
       ...
       #
       # Overhead  Source:Line               Symbol          Shared Object         Predicted  Abort  Cycles  IPC   [IPC Coverage]
       # ........  ........................  ..............  ....................  .........  .....  ......  ....................
       #
            8.17%  copy_page_64.S:19         [k] copy_page   [kernel.kallsyms]     50.0%      0      5       -      -
                   |
                   ---xas_load xarray.h:171
                      |
                      |--5.68%--xas_load xarray.c:245 (cycles:1)
                      |          xas_load xarray.c:242
                      |          xas_load xarray.h:1260 (cycles:1)
                      |          xas_descend xarray.c:146
                      |          xas_load xarray.c:244 (cycles:2)
                      |          xas_load xarray.c:245
                      |          xas_descend xarray.c:218 (cycles:10)
       ...

  perf stat:

   - Add HWMON PMU support.

     The HWMON provides various system information like CPU/GPU
     temperature, fan speed and so on. Expose them as PMU events so that
     users can see the values using perf stat commands.

       $ perf stat -e temp_cpu,fan1 true

        Performance counter stats for 'true':

                    60.00 'C   temp_cpu
                        0 rpm  fan1

              0.000745382 seconds time elapsed

              0.000883000 seconds user
              0.000000000 seconds sys

   - Display metric threshold in JSON output.

     Some metrics define thresholds to classify value ranges. It used to
     be in a different color but it won't work for JSON.

     Add "metric-threshold" field to the JSON that can be one of "good",
     "less good", "nearly bad" and "bad".

       # perf stat -a -M TopdownL1 -j true
       {"counter-value" : "18693525.000000", "unit" : "", "event" : "TOPDOWN.SLOTS", "event-runtime" : 5552708, "pcnt-running" : 100.00, "metric-value" : "43.226002", "metric-unit" : "%  tma_backend_bound", "metric-threshold" : "bad"}
       {"metric-value" : "29.212267", "metric-unit" : "%  tma_frontend_bound", "metric-threshold" : "bad"}
       {"metric-value" : "7.138972", "metric-unit" : "%  tma_bad_speculation", "metric-threshold" : "good"}
       {"metric-value" : "20.422759", "metric-unit" : "%  tma_retiring", "metric-threshold" : "good"}
       {"counter-value" : "3817732.000000", "unit" : "", "event" : "topdown-retiring", "event-runtime" : 5552708, "pcnt-running" : 100.00, }
       {"counter-value" : "5472824.000000", "unit" : "", "event" : "topdown-fe-bound", "event-runtime" : 5552708, "pcnt-running" : 100.00, }
       {"counter-value" : "7984780.000000", "unit" : "", "event" : "topdown-be-bound", "event-runtime" : 5552708, "pcnt-running" : 100.00, }
       {"counter-value" : "1418181.000000", "unit" : "", "event" : "topdown-bad-spec", "event-runtime" : 5552708, "pcnt-running" : 100.00, }
       ...

  perf sched:

   - Add -P/--pre-migrations option for 'timehist' sub-command to track
     time a task waited on a run-queue before migrating to a different
     CPU.

       $ perf sched timehist -P
                  time    cpu  task name                       wait time  sch delay   run time  pre-mig time
                               [tid/pid]                          (msec)     (msec)     (msec)     (msec)
       --------------- ------  ------------------------------  ---------  ---------  ---------  ---------
         585940.535527 [0000]  perf[584885]                        0.000      0.000      0.000      0.000
         585940.535535 [0000]  migration/0[20]                     0.000      0.002      0.008      0.000
         585940.535559 [0001]  perf[584885]                        0.000      0.000      0.000      0.000
         585940.535563 [0001]  migration/1[25]                     0.000      0.001      0.004      0.000
         585940.535678 [0002]  perf[584885]                        0.000      0.000      0.000      0.000
         585940.535686 [0002]  migration/2[31]                     0.000      0.002      0.008      0.000
         585940.535905 [0001]  <idle>                              0.000      0.000      0.342      0.000
         585940.535938 [0003]  perf[584885]                        0.000      0.000      0.000      0.000
         585940.537048 [0001]  sleep[584886]                       0.000      0.019      1.142      0.001
         585940.537749 [0002]  <idle>                              0.000      0.000      2.062      0.000
       ...

  Build:

   - Make libunwind opt-in (LIBUNWIND=1) rather than opt-out.

     The perf tools are generally built with libelf and libdw which has
     unwinder functionality. The libunwind support predates it and no
     need to have duplicate unwinders by default.

   - Rename NO_DWARF=1 build option to NO_LIBDW=1 in order to clarify
     it's using libdw for handling DWARF information.

  Internals:

   - Do not set exclude_guest bit in the perf_event_attr by default.

     This was causing a trouble in AMD IBS PMU as it doesn't support the
     bit. The bit will be set when it's needed later by the fallback
     logic. Also update the missing feature detection logic to make sure
     not clear supported bits unnecessarily.

   - Run perf test in parallel by default and mark flaky tests
     "exclusive" to run them serially at the end. Some test numbers are
     changed but the test can complete in less than half the time.

  JSON vendor events:

   - Add AMD Zen 5 events and metrics.

   - Add i.MX91 and i.MX95 DDR metrics

   - Fix HiSilicon HIP08 Topdown metric name.

   - Support compat events on PowerPC"

* tag 'perf-tools-for-v6.13-2024-11-24' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools: (232 commits)
  perf tests: Fix hwmon parsing with PMU name test
  perf hwmon_pmu: Ensure hwmon key union is zeroed before use
  perf tests hwmon_pmu: Remove double evlist__delete()
  perf/test: fix perf ftrace test on s390
  perf bpf-filter: Return -ENOMEM directly when pfi allocation fails
  perf test: Correct hwmon test PMU detection
  perf: Remove unused del_perf_probe_events()
  perf pmu: Move pmu_metrics_table__find and remove ARM override
  perf jevents: Add map_for_cpu()
  perf header: Pass a perf_cpu rather than a PMU to get_cpuid_str
  perf header: Avoid transitive PMU includes
  perf arm64 header: Use cpu argument in get_cpuid
  perf header: Refactor get_cpuid to take a CPU for ARM
  perf header: Move is_cpu_online to numa bench
  perf jevents: fix breakage when do perf stat on system metric
  perf test: Add missing __exit calls in tool/hwmon tests
  perf tests: Make leader sampling test work without branch event
  perf util: Remove kernel version deadcode
  perf test shell trace_exit_race: Use --no-comm to avoid cases where COMM isn't resolved
  perf test shell trace_exit_race: Show what went wrong in verbose mode
  ...

6 files changed, 145 insertions, 4 deletions

diff --git a/tools/lib/api/io.h b/tools/lib/api/io.h
index d3eb04d1bc89..1731996b2c32 100644
--- a/tools/lib/api/io.h
+++ b/tools/lib/api/io.h
@@ -189,6 +189,7 @@ static inline ssize_t io__getdelim(struct io *io, char **line_out, size_t *line_
 err_out:
 	free(line);
 	*line_out = NULL;
+	*line_len_out = 0;
 	return -ENOMEM;
 }
 
diff --git a/tools/lib/perf/Documentation/Makefile b/tools/lib/perf/Documentation/Makefile
index 972754082a85..573ca5b27556 100644
--- a/tools/lib/perf/Documentation/Makefile
+++ b/tools/lib/perf/Documentation/Makefile
@@ -121,7 +121,7 @@ install-man: all
 		$(INSTALL) -d -m 755 $(DESTDIR)$(man7dir); \
 		$(INSTALL) -m 644 $(MAN_7) $(DESTDIR)$(man7dir);
 
-install-html:
+install-html: $(MAN_HTML)
 	$(call QUIET_INSTALL, html) \
 		$(INSTALL) -d -m 755 $(DESTDIR)$(htmldir); \
 		$(INSTALL) -m 644 $(MAN_HTML) $(DESTDIR)$(htmldir); \
diff --git a/tools/lib/perf/evsel.c b/tools/lib/perf/evsel.c
index c07160953224..c475319e2e41 100644
--- a/tools/lib/perf/evsel.c
+++ b/tools/lib/perf/evsel.c
@@ -5,6 +5,7 @@
 #include <perf/evsel.h>
 #include <perf/cpumap.h>
 #include <perf/threadmap.h>
+#include <linux/hash.h>
 #include <linux/list.h>
 #include <internal/evsel.h>
 #include <linux/zalloc.h>
@@ -23,6 +24,7 @@ void perf_evsel__init(struct perf_evsel *evsel, struct perf_event_attr *attr,
 		      int idx)
 {
 	INIT_LIST_HEAD(&evsel->node);
+	INIT_LIST_HEAD(&evsel->per_stream_periods);
 	evsel->attr = *attr;
 	evsel->idx  = idx;
 	evsel->leader = evsel;
@@ -531,10 +533,56 @@ int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads)
 
 void perf_evsel__free_id(struct perf_evsel *evsel)
 {
+	struct perf_sample_id_period *pos, *n;
+
 	xyarray__delete(evsel->sample_id);
 	evsel->sample_id = NULL;
 	zfree(&evsel->id);
 	evsel->ids = 0;
+
+	perf_evsel_for_each_per_thread_period_safe(evsel, n, pos) {
+		list_del_init(&pos->node);
+		free(pos);
+	}
+}
+
+bool perf_evsel__attr_has_per_thread_sample_period(struct perf_evsel *evsel)
+{
+	return (evsel->attr.sample_type & PERF_SAMPLE_READ) &&
+		(evsel->attr.sample_type & PERF_SAMPLE_TID) &&
+		evsel->attr.inherit;
+}
+
+u64 *perf_sample_id__get_period_storage(struct perf_sample_id *sid, u32 tid, bool per_thread)
+{
+	struct hlist_head *head;
+	struct perf_sample_id_period *res;
+	int hash;
+
+	if (!per_thread)
+		return &sid->period;
+
+	hash = hash_32(tid, PERF_SAMPLE_ID__HLIST_BITS);
+	head = &sid->periods[hash];
+
+	hlist_for_each_entry(res, head, hnode)
+		if (res->tid == tid)
+			return &res->period;
+
+	if (sid->evsel == NULL)
+		return NULL;
+
+	res = zalloc(sizeof(struct perf_sample_id_period));
+	if (res == NULL)
+		return NULL;
+
+	INIT_LIST_HEAD(&res->node);
+	res->tid = tid;
+
+	list_add_tail(&res->node, &sid->evsel->per_stream_periods);
+	hlist_add_head(&res->hnode, &sid->periods[hash]);
+
+	return &res->period;
 }
 
 void perf_counts_values__scale(struct perf_counts_values *count,
diff --git a/tools/lib/perf/include/internal/evsel.h b/tools/lib/perf/include/internal/evsel.h
index 5cd220a61962..ea78defa77d0 100644
--- a/tools/lib/perf/include/internal/evsel.h
+++ b/tools/lib/perf/include/internal/evsel.h
@@ -11,6 +11,32 @@
 struct perf_thread_map;
 struct xyarray;
 
+/**
+ * The per-thread accumulated period storage node.
+ */
+struct perf_sample_id_period {
+	struct list_head	node;
+	struct hlist_node	hnode;
+	/* Holds total ID period value for PERF_SAMPLE_READ processing. */
+	u64			period;
+	/* The TID that the values belongs to */
+	u32			tid;
+};
+
+/**
+ * perf_evsel_for_each_per_thread_period_safe - safely iterate thru all the
+ * per_stream_periods
+ * @evlist:perf_evsel instance to iterate
+ * @item: struct perf_sample_id_period iterator
+ * @tmp: struct perf_sample_id_period temp iterator
+ */
+#define perf_evsel_for_each_per_thread_period_safe(evsel, tmp, item) \
+	list_for_each_entry_safe(item, tmp, &(evsel)->per_stream_periods, node)
+
+
+#define PERF_SAMPLE_ID__HLIST_BITS 4
+#define PERF_SAMPLE_ID__HLIST_SIZE (1 << PERF_SAMPLE_ID__HLIST_BITS)
+
 /*
  * Per fd, to map back from PERF_SAMPLE_ID to evsel, only used when there are
  * more than one entry in the evlist.
@@ -34,8 +60,32 @@ struct perf_sample_id {
 	pid_t			 machine_pid;
 	struct perf_cpu		 vcpu;
 
-	/* Holds total ID period value for PERF_SAMPLE_READ processing. */
-	u64			 period;
+	/*
+	 * Per-thread, and global event counts are mutually exclusive:
+	 * Whilst it is possible to combine events into a group with differing
+	 * values of PERF_SAMPLE_READ, it is not valid to have inconsistent
+	 * values for `inherit`. Therefore it is not possible to have a
+	 * situation where a per-thread event is sampled as a global event;
+	 * all !inherit groups are global, and all groups where the sampling
+	 * event is inherit + PERF_SAMPLE_READ will be per-thread. Any event
+	 * that is part of such a group that is inherit but not PERF_SAMPLE_READ
+	 * will be read as per-thread. If such an event can also trigger a
+	 * sample (such as with sample_period > 0) then it will not cause
+	 * `read_format` to be included in its PERF_RECORD_SAMPLE, and
+	 * therefore will not expose the per-thread group members as global.
+	 */
+	union {
+		/*
+		 * Holds total ID period value for PERF_SAMPLE_READ processing
+		 * (when period is not per-thread).
+		 */
+		u64			period;
+		/*
+		 * Holds total ID period value for PERF_SAMPLE_READ processing
+		 * (when period is per-thread).
+		 */
+		struct hlist_head	periods[PERF_SAMPLE_ID__HLIST_SIZE];
+	};
 };
 
 struct perf_evsel {
@@ -58,6 +108,10 @@ struct perf_evsel {
 	u32			 ids;
 	struct perf_evsel	*leader;
 
+	/* For events where the read_format value is per-thread rather than
+	 * global, stores the per-thread cumulative period */
+	struct list_head	per_stream_periods;
+
 	/* parse modifier helper */
 	int			 nr_members;
 	/*
@@ -88,4 +142,9 @@ int perf_evsel__apply_filter(struct perf_evsel *evsel, const char *filter);
 int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads);
 void perf_evsel__free_id(struct perf_evsel *evsel);
 
+bool perf_evsel__attr_has_per_thread_sample_period(struct perf_evsel *evsel);
+
+u64 *perf_sample_id__get_period_storage(struct perf_sample_id *sid, u32 tid,
+					bool per_thread);
+
 #endif /* __LIBPERF_INTERNAL_EVSEL_H */
diff --git a/tools/lib/subcmd/run-command.c b/tools/lib/subcmd/run-command.c
index 4e3a557a2f37..0a764c25c384 100644
--- a/tools/lib/subcmd/run-command.c
+++ b/tools/lib/subcmd/run-command.c
@@ -2,6 +2,7 @@
 #include <unistd.h>
 #include <sys/types.h>
 #include <sys/stat.h>
+#include <ctype.h>
 #include <fcntl.h>
 #include <string.h>
 #include <linux/string.h>
@@ -217,8 +218,40 @@ static int wait_or_whine(struct child_process *cmd, bool block)
 
 int check_if_command_finished(struct child_process *cmd)
 {
+#ifdef __linux__
+	char filename[FILENAME_MAX + 12];
+	char status_line[256];
+	FILE *status_file;
+
+	/*
+	 * Check by reading /proc/<pid>/status as calling waitpid causes
+	 * stdout/stderr to be closed and data lost.
+	 */
+	sprintf(filename, "/proc/%d/status", cmd->pid);
+	status_file = fopen(filename, "r");
+	if (status_file == NULL) {
+		/* Open failed assume finish_command was called. */
+		return true;
+	}
+	while (fgets(status_line, sizeof(status_line), status_file) != NULL) {
+		char *p;
+
+		if (strncmp(status_line, "State:", 6))
+			continue;
+
+		fclose(status_file);
+		p = status_line + 6;
+		while (isspace(*p))
+			p++;
+		return *p == 'Z' ? 1 : 0;
+	}
+	/* Read failed assume finish_command was called. */
+	fclose(status_file);
+	return 1;
+#else
 	wait_or_whine(cmd, /*block=*/false);
 	return cmd->finished;
+#endif
 }
 
 int finish_command(struct child_process *cmd)
diff --git a/tools/lib/subcmd/subcmd-util.h b/tools/lib/subcmd/subcmd-util.h
index dfac76e35ac7..c742b08815dc 100644
--- a/tools/lib/subcmd/subcmd-util.h
+++ b/tools/lib/subcmd/subcmd-util.h
@@ -20,8 +20,8 @@ static __noreturn inline void die(const char *err, ...)
 
 	va_start(params, err);
 	report(" Fatal: ", err, params);
-	exit(128);
 	va_end(params);
+	exit(128);
 }
 
 #define zfree(ptr) ({ free(*ptr); *ptr = NULL; })