Merge tag 'perf-tools-for-v5.16-2021-11-07-without-bpftool-fix' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tools updates from Arnaldo Carvalho de Melo:
 "perf annotate:
   - Add riscv64 support.
   - Add fusion logic for AMD microarchs.

  perf record:
   - Add an option to control the synthesizing behavior:
       --synth <no|all|task|mmap|cgroup>

  core:
   - Allow controlling synthesizing PERF_RECORD_ metadata events during
     record.
   - perf.data reader prep work for multithreaded processing.
   - Fix missing exclude_{host,guest} setting in PMUs that don't support
     it and that were causing the feature detection code to disable it
     for all events, even the ones in PMUs that support it.
   - Fix the default use of precise events on AMD, that were always
     falling back to non-precise because perf_event_attr.exclude_guest=1
     was set and IBS does not have filtering capability, refusing
     precise + exclude_guest.
   - Add bitfield_swap() to handle branch_stack endian issue.

  perf script:
   - Show binary offsets for userspace addresses in callchains.
   - Support instruction latency via new "ins_lat" selectable field.
   - Add dlfilter-show-cycles

  perf inject:
   - Add vmlinux and ignore-vmlinux arguments, similar to other tools.

  perf list:
   - Display PMU prefix for partially supported hybrid cache events.
   - Display hybrid PMU events with cpu type.

  perf stat:
   - Improve metrics documentation of data structures.
   - Fix memory leaks in the metric code.
   - Use NAN for missing event IDs.
   - Don't compute unused events.
   - Fix memory leak on error path.
   - Encode and use metric-id as a metric qualifier.
   - Allow metrics with no events.
   - Avoid events for an 'if' constant result.
   - Only add a referenced metric once.
   - Simplify metric_refs calculation.
   - Allow modifiers on metrics.

  perf test:
   - Add workload test of metric and metric groups.
   - Workload test of all PMUs.
   - vmlinux-kallsyms: Ignore hidden symbols.
   - Add pmu-event test for event described as "config=".
   - Verify more event members in pmu-events test.
   - Add endian test for struct branch_flags on the sample-parsing test.
   - Improve temp file cleanup in several tests.

  perf daemon:
   - Address MSAN warnings on send_cmd().

  perf kmem:
   - Improve man page for record options

  perf srcline:
   - Use long-running addr2line per DSO, greatly speeding up the
     'srcline' sort order.

  perf symbols:
   - Ignore $a/$d symbols for ARM modules.
   - Fix /proc/kcore access on 32 bit systems.

  Kernel UAPI copies:
   - Update copy of linux/socket.h with the kernel sources, no change in
     tooling output.

  libbpf:
   - Pull in bpf_program__get_prog_info_linear() from libbpf, too much
     specific to perf.
   - Deprecate bpf_map__resize() in favor of bpf_map_set_max_entries()
   - Install libbpf headers locally when building.
   - Bump minimum LLVM C++ std to GNU++14.

  libperf:
   - Use binary search in perf_cpu_map__idx() as array are sorted.

  libtracefs:
   - Enable libtracefs dynamic linking.

  libtraceevent:
   - Increase logging when verbose.

  Arch specific:

   * PowerPC:
      - Add support to expose instruction and data address registers as
        part of extended regs.

  Vendor events:

   * JSON parser:
      - Support ConfigCode to set the config= in PMUs
      - Make the JSON parser more conformant when in strict mode.

   * All JSON files:
      - Fix all remaining invalid JSON files.

   * ARM:
      - Syntax corrections in Neoverse N1 json.
      - Categorise the Neoverse V1 counters.
      - Add new armv8 PMU events.
      - Revise hip08 uncore events.

  Hardware tracing:

   * auxtrace:
      - Add missing Z option to ITRACE_HELP.
      - Add itrace A option to approximate IPC.
      - Add itrace d+o option to direct debug log to stdout.

   * Intel PT:
      - Add support for PERF_RECORD_AUX_OUTPUT_HW_ID
      - Support itrace A option to approximate IPC
      - Support itrace d+o option to direct debug log to stdout"

* tag 'perf-tools-for-v5.16-2021-11-07-without-bpftool-fix' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (120 commits)
  perf build: Install libbpf headers locally when building
  perf MANIFEST: Add bpftool files to allow building with BUILD_BPF_SKEL=1
  perf metric: Fix memory leaks
  perf parse-event: Add init and exit to parse_event_error
  perf parse-events: Rename parse_events_error functions
  perf stat: Fix memory leak on error path
  perf tools: Use __BYTE_ORDER__
  perf inject: Add vmlinux and ignore-vmlinux arguments
  perf tools: Check vmlinux/kallsyms arguments in all tools
  perf tools: Refactor out kernel symbol argument sanity checking
  perf symbols: Ignore $a/$d symbols for ARM modules
  perf evsel: Don't set exclude_guest by default
  perf evsel: Fix missing exclude_{host,guest} setting
  perf bpf: Add missing free to bpf_event__print_bpf_prog_info()
  perf beauty: Update copy of linux/socket.h with the kernel sources
  perf clang: Fixes for more recent LLVM/clang
  tools: Bump minimum LLVM C++ std to GNU++14
  perf bpf: Pull in bpf_program__get_prog_info_linear()
  Revert "perf bench futex: Add support for 32-bit systems with 64-bit time_t"
  perf test sample-parsing: Add endian test for struct branch_flags
  ...

1 files changed, 40 insertions, 36 deletions

diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 34a7f5c1fff7d..e4fb02b051304 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -1,8 +1,10 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <math.h>
 #include <stdio.h>
 #include "evsel.h"
 #include "stat.h"
 #include "color.h"
+#include "debug.h"
 #include "pmu.h"
 #include "rblist.h"
 #include "evlist.h"
@@ -370,12 +372,16 @@ void perf_stat__collect_metric_expr(struct evlist *evsel_list)
 {
 	struct evsel *counter, *leader, **metric_events, *oc;
 	bool found;
-	struct expr_parse_ctx ctx;
+	struct expr_parse_ctx *ctx;
 	struct hashmap_entry *cur;
 	size_t bkt;
 	int i;
 
-	expr__ctx_init(&ctx);
+	ctx = expr__ctx_new();
+	if (!ctx) {
+		pr_debug("expr__ctx_new failed");
+		return;
+	}
 	evlist__for_each_entry(evsel_list, counter) {
 		bool invalid = false;
 
@@ -383,25 +389,25 @@ void perf_stat__collect_metric_expr(struct evlist *evsel_list)
 		if (!counter->metric_expr)
 			continue;
 
-		expr__ctx_clear(&ctx);
+		expr__ctx_clear(ctx);
 		metric_events = counter->metric_events;
 		if (!metric_events) {
-			if (expr__find_other(counter->metric_expr,
-					     counter->name,
-					     &ctx, 1) < 0)
+			if (expr__find_ids(counter->metric_expr,
+					   counter->name,
+					   ctx) < 0)
 				continue;
 
 			metric_events = calloc(sizeof(struct evsel *),
-					       hashmap__size(&ctx.ids) + 1);
+					       hashmap__size(ctx->ids) + 1);
 			if (!metric_events) {
-				expr__ctx_clear(&ctx);
+				expr__ctx_free(ctx);
 				return;
 			}
 			counter->metric_events = metric_events;
 		}
 
 		i = 0;
-		hashmap__for_each_entry((&ctx.ids), cur, bkt) {
+		hashmap__for_each_entry(ctx->ids, cur, bkt) {
 			const char *metric_name = (const char *)cur->key;
 
 			found = false;
@@ -438,6 +444,7 @@ void perf_stat__collect_metric_expr(struct evlist *evsel_list)
 						"Add %s event to groups to get metric expression for %s\n",
 						metric_name,
 						counter->name);
+					free(printed);
 					printed = strdup(metric_name);
 				}
 				invalid = true;
@@ -453,7 +460,7 @@ void perf_stat__collect_metric_expr(struct evlist *evsel_list)
 			counter->metric_expr = NULL;
 		}
 	}
-	expr__ctx_clear(&ctx);
+	expr__ctx_free(ctx);
 }
 
 static double runtime_stat_avg(struct runtime_stat *st,
@@ -815,10 +822,9 @@ static int prepare_metric(struct evsel **metric_events,
 			  struct runtime_stat *st)
 {
 	double scale;
-	char *n, *pn;
+	char *n;
 	int i, j, ret;
 
-	expr__ctx_init(pctx);
 	for (i = 0; metric_events[i]; i++) {
 		struct saved_value *v;
 		struct stats *stats;
@@ -839,23 +845,11 @@ static int prepare_metric(struct evsel **metric_events,
 			if (v->metric_other)
 				metric_total = v->metric_total;
 		}
-
-		n = strdup(metric_events[i]->name);
+		n = strdup(evsel__metric_id(metric_events[i]));
 		if (!n)
 			return -ENOMEM;
-		/*
-		 * This display code with --no-merge adds [cpu] postfixes.
-		 * These are not supported by the parser. Remove everything
-		 * after the space.
-		 */
-		pn = strchr(n, ' ');
-		if (pn)
-			*pn = 0;
-
-		if (metric_total)
-			expr__add_id_val(pctx, n, metric_total);
-		else
-			expr__add_id_val(pctx, n, avg_stats(stats)*scale);
+
+		expr__add_id_val(pctx, n, metric_total ? : avg_stats(stats) * scale);
 	}
 
 	for (j = 0; metric_refs && metric_refs[j].metric_name; j++) {
@@ -880,17 +874,23 @@ static void generic_metric(struct perf_stat_config *config,
 			   struct runtime_stat *st)
 {
 	print_metric_t print_metric = out->print_metric;
-	struct expr_parse_ctx pctx;
+	struct expr_parse_ctx *pctx;
 	double ratio, scale;
 	int i;
 	void *ctxp = out->ctx;
 
-	i = prepare_metric(metric_events, metric_refs, &pctx, cpu, st);
-	if (i < 0)
+	pctx = expr__ctx_new();
+	if (!pctx)
 		return;
 
+	pctx->runtime = runtime;
+	i = prepare_metric(metric_events, metric_refs, pctx, cpu, st);
+	if (i < 0) {
+		expr__ctx_free(pctx);
+		return;
+	}
 	if (!metric_events[i]) {
-		if (expr__parse(&ratio, &pctx, metric_expr, runtime) == 0) {
+		if (expr__parse(&ratio, pctx, metric_expr) == 0) {
 			char *unit;
 			char metric_bf[64];
 
@@ -926,22 +926,26 @@ static void generic_metric(struct perf_stat_config *config,
 			     (metric_name ? metric_name : name) : "", 0);
 	}
 
-	expr__ctx_clear(&pctx);
+	expr__ctx_free(pctx);
 }
 
 double test_generic_metric(struct metric_expr *mexp, int cpu, struct runtime_stat *st)
 {
-	struct expr_parse_ctx pctx;
+	struct expr_parse_ctx *pctx;
 	double ratio = 0.0;
 
-	if (prepare_metric(mexp->metric_events, mexp->metric_refs, &pctx, cpu, st) < 0)
+	pctx = expr__ctx_new();
+	if (!pctx)
+		return NAN;
+
+	if (prepare_metric(mexp->metric_events, mexp->metric_refs, pctx, cpu, st) < 0)
 		goto out;
 
-	if (expr__parse(&ratio, &pctx, mexp->metric_expr, 1))
+	if (expr__parse(&ratio, pctx, mexp->metric_expr))
 		ratio = 0.0;
 
 out:
-	expr__ctx_clear(&pctx);
+	expr__ctx_free(pctx);
 	return ratio;
 }