Merge tag 'perf-tools-for-v6.9-2024-03-13' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools

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

   - Support new 'cluster' aggregation mode for shared resources
     depending on the hardware configuration:

        $ sudo perf stat -a --per-cluster -e cycles,instructions sleep 1

         Performance counter stats for 'system wide':

        S0-D0-CLS0    2         85,051,822      cycles
        S0-D0-CLS0    2         73,909,908      instructions      #    0.87  insn per cycle
        S0-D0-CLS2    2         93,365,918      cycles
        S0-D0-CLS2    2         83,006,158      instructions      #    0.89  insn per cycle
        S0-D0-CLS4    2        104,157,523      cycles
        S0-D0-CLS4    2         53,234,396      instructions      #    0.51  insn per cycle
        S0-D0-CLS6    2         65,891,079      cycles
        S0-D0-CLS6    2         41,478,273      instructions      #    0.63  insn per cycle

               1.002407989 seconds time elapsed

   - Various fixes and cleanups for event metrics including NaN handling

  perf script:

   - Use libcapstone if available to disassemble the instructions. This
     enables 'perf script -F disasm' and 'perf script --insn-trace=disasm'
     (for Intel-PT):

        $ perf script -F event,ip,disasm
        cycles:P:  ffffffffa988d428             wrmsr
        cycles:P:  ffffffffa9839d25             movq %rax, %r14
        cycles:P:  ffffffffa9cdcaf0             endbr64
        cycles:P:  ffffffffa988d428             wrmsr
        cycles:P:  ffffffffa988d428             wrmsr
        cycles:P:  ffffffffaa401f86             iretq
        cycles:P:  ffffffffa99c4de5             movq 0x30(%rcx), %r8
        cycles:P:  ffffffffa988d428             wrmsr
        cycles:P:  ffffffffaa401f86             iretq
        cycles:P:  ffffffffa9907983             movl 0x68(%rbx), %eax
        cycles:P:  ffffffffa988d428             wrmsr

   - Expose sample ID / stream ID to python scripts

  perf test:

   - Add more perf test cases from Redhat internal test suites. This
     time it adds the base infra and a few perf probe tests. More to
     come. :)

   - Add 'perf test -p' for parallel execution and fix some issues found
     by the parallel test

   - Support symbol test to print symbols in given (active) module:

        $ perf test -F -v Symbols --dso /lib/modules/$(uname -r)/kernel/fs/ext4/ext4.ko
        --- start ---
        Testing /lib/modules/6.5.13-1rodete2-amd64/kernel/fs/ext4/ext4.ko
        Overlapping symbols:
         7a990-7a9a0 l __pfx_ext4_exit_fs
         7a990-7a9a0 g __pfx_cleanup_module
        Overlapping symbols:
         7a9a0-7aa1c l ext4_exit_fs
         7a9a0-7aa1c g cleanup_module
        ...

  JSON metric updates:

   - A new round of Intel metric updates

   - Support Power11 PVR (compatible to Power10)

   - Fix cache latency events on Zen 4 to set SliceId properly

  Internal:

   - Fix reference counting for 'map' data structure, tireless work from
     Ian!

   - More memory optimization for struct thread and annotate histogram.
     Now, 'perf report' (TUI) and 'perf annotate' should be much
     lighter-weight in terms of memory footprint

   - Support cross-arch perf register access. Clean up the build
     configuration so that it can detect arch-register support at
     runtime. This can allow to parse register data in sample which was
     recorded in a different arch

  Others:

   - Sync task state in 'perf sched' to kernel using trace event fields.
     The task states have been changed so tools cannot assume a fixed
     encoding

   - Clean up 'perf mem' to generalize the arch-specific events

   - Add support for local and global variables to data type profiling.
     This would increase the success rate of type resolution with DWARF

   - Add short option -H for --hierarchy in 'perf report' and 'perf top'"

* tag 'perf-tools-for-v6.9-2024-03-13' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools: (154 commits)
  perf annotate: Add comments in the data structures
  perf annotate: Remove sym_hist.addr[] array
  perf annotate: Calculate instruction overhead using hashmap
  perf annotate: Add a hashmap for symbol histogram
  perf threads: Reduce table size from 256 to 8
  perf threads: Switch from rbtree to hashmap
  perf threads: Move threads to its own files
  perf machine: Move machine's threads into its own abstraction
  perf machine: Move fprintf to for_each loop and a callback
  perf trace: Ignore thread hashing in summary
  perf report: Sort child tasks by tid
  perf vendor events amd: Fix Zen 4 cache latency events
  perf version: Display availability of OpenCSD support
  perf vendor events intel: Add umasks/occ_sel to PCU events.
  perf map: Fix map reference count issues
  libperf evlist: Avoid out-of-bounds access
  perf lock contention: Account contending locks too
  perf metrics: Fix segv for metrics with no events
  perf metrics: Fix metric matching
  perf pmu: Fix a potential memory leak in perf_pmu__lookup()
  ...

1 files changed, 24 insertions, 21 deletions

diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index f78eea9e2153..16b40f5d43db 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -3215,12 +3215,19 @@ static int parse_record_events(const struct option *opt,
 			       const char *str, int unset __maybe_unused)
 {
 	bool *event_set = (bool *) opt->value;
+	struct perf_pmu *pmu;
+
+	pmu = perf_mem_events_find_pmu();
+	if (!pmu) {
+		pr_err("failed: there is no PMU that supports perf c2c\n");
+		exit(-1);
+	}
 
 	if (!strcmp(str, "list")) {
-		perf_mem_events__list();
+		perf_pmu__mem_events_list(pmu);
 		exit(0);
 	}
-	if (perf_mem_events__parse(str))
+	if (perf_pmu__mem_events_parse(pmu, str))
 		exit(-1);
 
 	*event_set = true;
@@ -3238,13 +3245,13 @@ static const char * const *record_mem_usage = __usage_record;
 
 static int perf_c2c__record(int argc, const char **argv)
 {
-	int rec_argc, i = 0, j, rec_tmp_nr = 0;
+	int rec_argc, i = 0, j;
 	const char **rec_argv;
-	char **rec_tmp;
 	int ret;
 	bool all_user = false, all_kernel = false;
 	bool event_set = false;
 	struct perf_mem_event *e;
+	struct perf_pmu *pmu;
 	struct option options[] = {
 	OPT_CALLBACK('e', "event", &event_set, "event",
 		     "event selector. Use 'perf c2c record -e list' to list available events",
@@ -3256,7 +3263,13 @@ static int perf_c2c__record(int argc, const char **argv)
 	OPT_END()
 	};
 
-	if (perf_mem_events__init()) {
+	pmu = perf_mem_events_find_pmu();
+	if (!pmu) {
+		pr_err("failed: no PMU supports the memory events\n");
+		return -1;
+	}
+
+	if (perf_pmu__mem_events_init(pmu)) {
 		pr_err("failed: memory events not supported\n");
 		return -1;
 	}
@@ -3265,22 +3278,16 @@ static int perf_c2c__record(int argc, const char **argv)
 			     PARSE_OPT_KEEP_UNKNOWN);
 
 	/* Max number of arguments multiplied by number of PMUs that can support them. */
-	rec_argc = argc + 11 * perf_pmus__num_mem_pmus();
+	rec_argc = argc + 11 * (perf_pmu__mem_events_num_mem_pmus(pmu) + 1);
 
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
 	if (!rec_argv)
 		return -1;
 
-	rec_tmp = calloc(rec_argc + 1, sizeof(char *));
-	if (!rec_tmp) {
-		free(rec_argv);
-		return -1;
-	}
-
 	rec_argv[i++] = "record";
 
 	if (!event_set) {
-		e = perf_mem_events__ptr(PERF_MEM_EVENTS__LOAD_STORE);
+		e = perf_pmu__mem_events_ptr(pmu, PERF_MEM_EVENTS__LOAD_STORE);
 		/*
 		 * The load and store operations are required, use the event
 		 * PERF_MEM_EVENTS__LOAD_STORE if it is supported.
@@ -3289,15 +3296,15 @@ static int perf_c2c__record(int argc, const char **argv)
 			e->record = true;
 			rec_argv[i++] = "-W";
 		} else {
-			e = perf_mem_events__ptr(PERF_MEM_EVENTS__LOAD);
+			e = perf_pmu__mem_events_ptr(pmu, PERF_MEM_EVENTS__LOAD);
 			e->record = true;
 
-			e = perf_mem_events__ptr(PERF_MEM_EVENTS__STORE);
+			e = perf_pmu__mem_events_ptr(pmu, PERF_MEM_EVENTS__STORE);
 			e->record = true;
 		}
 	}
 
-	e = perf_mem_events__ptr(PERF_MEM_EVENTS__LOAD);
+	e = perf_pmu__mem_events_ptr(pmu, PERF_MEM_EVENTS__LOAD);
 	if (e->record)
 		rec_argv[i++] = "-W";
 
@@ -3305,7 +3312,7 @@ static int perf_c2c__record(int argc, const char **argv)
 	rec_argv[i++] = "--phys-data";
 	rec_argv[i++] = "--sample-cpu";
 
-	ret = perf_mem_events__record_args(rec_argv, &i, rec_tmp, &rec_tmp_nr);
+	ret = perf_mem_events__record_args(rec_argv, &i);
 	if (ret)
 		goto out;
 
@@ -3332,10 +3339,6 @@ static int perf_c2c__record(int argc, const char **argv)
 
 	ret = cmd_record(i, rec_argv);
 out:
-	for (i = 0; i < rec_tmp_nr; i++)
-		free(rec_tmp[i]);
-
-	free(rec_tmp);
 	free(rec_argv);
 	return ret;
 }