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, 44 insertions, 28 deletions

diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index e31426167852..3466aa952442 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -355,11 +355,13 @@ static void print_nsecs(struct perf_stat_config *config,
 		print_metric(config, ctxp, NULL, NULL, "CPUs utilized", 0);
 }
 
-static int prepare_metric(struct evsel **metric_events,
-			  struct metric_ref *metric_refs,
+static int prepare_metric(const struct metric_expr *mexp,
+			  const struct evsel *evsel,
 			  struct expr_parse_ctx *pctx,
 			  int aggr_idx)
 {
+	struct evsel * const *metric_events = mexp->metric_events;
+	struct metric_ref *metric_refs = mexp->metric_refs;
 	int i;
 
 	for (i = 0; metric_events[i]; i++) {
@@ -398,12 +400,33 @@ static int prepare_metric(struct evsel **metric_events,
 			source_count = 1;
 		} else {
 			struct perf_stat_evsel *ps = metric_events[i]->stats;
-			struct perf_stat_aggr *aggr = &ps->aggr[aggr_idx];
+			struct perf_stat_aggr *aggr;
 
+			/*
+			 * If there are multiple uncore PMUs and we're not
+			 * reading the leader's stats, determine the stats for
+			 * the appropriate uncore PMU.
+			 */
+			if (evsel && evsel->metric_leader &&
+			    evsel->pmu != evsel->metric_leader->pmu &&
+			    mexp->metric_events[i]->pmu == evsel->metric_leader->pmu) {
+				struct evsel *pos;
+
+				evlist__for_each_entry(evsel->evlist, pos) {
+					if (pos->pmu != evsel->pmu)
+						continue;
+					if (pos->metric_leader != mexp->metric_events[i])
+						continue;
+					ps = pos->stats;
+					source_count = 1;
+					break;
+				}
+			}
+			aggr = &ps->aggr[aggr_idx];
 			if (!aggr)
 				break;
 
-                        if (!metric_events[i]->supported) {
+			if (!metric_events[i]->supported) {
 				/*
 				 * Not supported events will have a count of 0,
 				 * which can be confusing in a
@@ -414,13 +437,9 @@ static int prepare_metric(struct evsel **metric_events,
 				val = NAN;
 				source_count = 0;
 			} else {
-				/*
-				 * If an event was scaled during stat gathering,
-				 * reverse the scale before computing the
-				 * metric.
-				 */
-				val = aggr->counts.val * (1.0 / metric_events[i]->scale);
-				source_count = evsel__source_count(metric_events[i]);
+				val = aggr->counts.val;
+				if (!source_count)
+					source_count = evsel__source_count(metric_events[i]);
 			}
 		}
 		n = strdup(evsel__metric_id(metric_events[i]));
@@ -441,18 +460,18 @@ static int prepare_metric(struct evsel **metric_events,
 }
 
 static void generic_metric(struct perf_stat_config *config,
-			   const char *metric_expr,
-			   const char *metric_threshold,
-			   struct evsel **metric_events,
-			   struct metric_ref *metric_refs,
-			   char *name,
-			   const char *metric_name,
-			   const char *metric_unit,
-			   int runtime,
+			   struct metric_expr *mexp,
+			   struct evsel *evsel,
 			   int aggr_idx,
 			   struct perf_stat_output_ctx *out)
 {
 	print_metric_t print_metric = out->print_metric;
+	const char *metric_name = mexp->metric_name;
+	const char *metric_expr = mexp->metric_expr;
+	const char *metric_threshold = mexp->metric_threshold;
+	const char *metric_unit = mexp->metric_unit;
+	struct evsel * const *metric_events = mexp->metric_events;
+	int runtime = mexp->runtime;
 	struct expr_parse_ctx *pctx;
 	double ratio, scale, threshold;
 	int i;
@@ -467,7 +486,7 @@ static void generic_metric(struct perf_stat_config *config,
 		pctx->sctx.user_requested_cpu_list = strdup(config->user_requested_cpu_list);
 	pctx->sctx.runtime = runtime;
 	pctx->sctx.system_wide = config->system_wide;
-	i = prepare_metric(metric_events, metric_refs, pctx, aggr_idx);
+	i = prepare_metric(mexp, evsel, pctx, aggr_idx);
 	if (i < 0) {
 		expr__ctx_free(pctx);
 		return;
@@ -502,18 +521,18 @@ static void generic_metric(struct perf_stat_config *config,
 				print_metric(config, ctxp, color, "%8.2f",
 					metric_name ?
 					metric_name :
-					out->force_header ?  name : "",
+					out->force_header ?  evsel->name : "",
 					ratio);
 			}
 		} else {
 			print_metric(config, ctxp, color, /*unit=*/NULL,
 				     out->force_header ?
-				     (metric_name ? metric_name : name) : "", 0);
+				     (metric_name ?: evsel->name) : "", 0);
 		}
 	} else {
 		print_metric(config, ctxp, color, /*unit=*/NULL,
 			     out->force_header ?
-			     (metric_name ? metric_name : name) : "", 0);
+			     (metric_name ?: evsel->name) : "", 0);
 	}
 
 	expr__ctx_free(pctx);
@@ -528,7 +547,7 @@ double test_generic_metric(struct metric_expr *mexp, int aggr_idx)
 	if (!pctx)
 		return NAN;
 
-	if (prepare_metric(mexp->metric_events, mexp->metric_refs, pctx, aggr_idx) < 0)
+	if (prepare_metric(mexp, /*evsel=*/NULL, pctx, aggr_idx) < 0)
 		goto out;
 
 	if (expr__parse(&ratio, pctx, mexp->metric_expr))
@@ -630,10 +649,7 @@ void *perf_stat__print_shadow_stats_metricgroup(struct perf_stat_config *config,
 
 		if ((*num)++ > 0)
 			out->new_line(config, ctxp);
-		generic_metric(config, mexp->metric_expr, mexp->metric_threshold,
-			       mexp->metric_events, mexp->metric_refs, evsel->name,
-			       mexp->metric_name, mexp->metric_unit, mexp->runtime,
-			       aggr_idx, out);
+		generic_metric(config, mexp, evsel, aggr_idx, out);
 	}
 
 	return NULL;