Merge tag 'perf-tools-fixes-for-v6.0-2022-08-13' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull more perf tool updates from Arnaldo Carvalho de Melo:

 - 'perf c2c' now supports ARM64, adjust its output to cope with
   differences with what is in x86_64. Now go find false sharing on
   ARM64 (at least Neoverse) as well!

 - Refactor the JSON processing, making the output more compact and thus
   reducing the size of the resulting perf binary

 - Improvements for 'perf offcpu' profiling, including tracking child
   processes

 - Update Intel JSON metrics and events files for broadwellde,
   broadwellx, cascadelakex, haswellx, icelakex, ivytown, jaketown,
   knightslanding, sapphirerapids, skylakex and snowridgex

 - Add 'perf stat' JSON output and a 'perf test' entry for it

 - Ignore memfd and anonymous mmap events if jitdump present

 - Refactor 'perf test' shell tests allowing subdirs

 - Fix an error handling path in 'parse_perf_probe_command()'

 - Fixes for the guest Intel PT tracing patchkit in the 1st batch of
   this merge window

 - Print debuginfod queries if -v option is used, to explain delays in
   processing when debuginfo servers are enabled to fetch DSOs with
   richer symbol tables

 - Improve error message for 'perf record -p not_existing_pid'

 - Fix openssl and libbpf feature detection

 - Add PMU pai_crypto event description for IBM z16 on 'perf list'

 - Fix typos and duplicated words on comments in various places

* tag 'perf-tools-fixes-for-v6.0-2022-08-13' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (81 commits)
  perf test: Refactor shell tests allowing subdirs
  perf vendor events: Update events for snowridgex
  perf vendor events: Update events and metrics for skylakex
  perf vendor events: Update metrics for sapphirerapids
  perf vendor events: Update events for knightslanding
  perf vendor events: Update metrics for jaketown
  perf vendor events: Update metrics for ivytown
  perf vendor events: Update events and metrics for icelakex
  perf vendor events: Update events and metrics for haswellx
  perf vendor events: Update events and metrics for cascadelakex
  perf vendor events: Update events and metrics for broadwellx
  perf vendor events: Update metrics for broadwellde
  perf jevents: Fold strings optimization
  perf jevents: Compress the pmu_events_table
  perf metrics: Copy entire pmu_event in find metric
  perf pmu-events: Hide the pmu_events
  perf pmu-events: Don't assume pmu_event is an array
  perf pmu-events: Move test events/metrics to JSON
  perf test: Use full metric resolution
  perf pmu-events: Hide pmu_events_map
  ...

1 files changed, 194 insertions, 10 deletions

diff --git a/tools/perf/pmu-events/empty-pmu-events.c b/tools/perf/pmu-events/empty-pmu-events.c
index 77e655c6f116..5ed8c0aa4817 100644
--- a/tools/perf/pmu-events/empty-pmu-events.c
+++ b/tools/perf/pmu-events/empty-pmu-events.c
@@ -6,6 +6,10 @@
  * The test cpu/soc is provided for testing.
  */
 #include "pmu-events/pmu-events.h"
+#include "util/header.h"
+#include "util/pmu.h"
+#include <string.h>
+#include <stddef.h>
 
 static const struct pmu_event pme_test_soc_cpu[] = {
 	{
@@ -102,24 +106,109 @@ static const struct pmu_event pme_test_soc_cpu[] = {
 		.topic = "branch",
 	},
 	{
+		.metric_expr	= "1 / IPC",
+		.metric_name	= "CPI",
+	},
+	{
+		.metric_expr	= "inst_retired.any / cpu_clk_unhalted.thread",
+		.metric_name	= "IPC",
+		.metric_group	= "group1",
+	},
+	{
+		.metric_expr	= "idq_uops_not_delivered.core / (4 * (( ( cpu_clk_unhalted.thread / 2 ) * "
+		"( 1 + cpu_clk_unhalted.one_thread_active / cpu_clk_unhalted.ref_xclk ) )))",
+		.metric_name	= "Frontend_Bound_SMT",
+	},
+	{
+		.metric_expr	= "l1d\\-loads\\-misses / inst_retired.any",
+		.metric_name	= "dcache_miss_cpi",
+	},
+	{
+		.metric_expr	= "l1i\\-loads\\-misses / inst_retired.any",
+		.metric_name	= "icache_miss_cycles",
+	},
+	{
+		.metric_expr	= "(dcache_miss_cpi + icache_miss_cycles)",
+		.metric_name	= "cache_miss_cycles",
+		.metric_group	= "group1",
+	},
+	{
+		.metric_expr	= "l2_rqsts.demand_data_rd_hit + l2_rqsts.pf_hit + l2_rqsts.rfo_hit",
+		.metric_name	= "DCache_L2_All_Hits",
+	},
+	{
+		.metric_expr	= "max(l2_rqsts.all_demand_data_rd - l2_rqsts.demand_data_rd_hit, 0) + "
+		"l2_rqsts.pf_miss + l2_rqsts.rfo_miss",
+		.metric_name	= "DCache_L2_All_Miss",
+	},
+	{
+		.metric_expr	= "dcache_l2_all_hits + dcache_l2_all_miss",
+		.metric_name	= "DCache_L2_All",
+	},
+	{
+		.metric_expr	= "d_ratio(dcache_l2_all_hits, dcache_l2_all)",
+		.metric_name	= "DCache_L2_Hits",
+	},
+	{
+		.metric_expr	= "d_ratio(dcache_l2_all_miss, dcache_l2_all)",
+		.metric_name	= "DCache_L2_Misses",
+	},
+	{
+		.metric_expr	= "ipc + M2",
+		.metric_name	= "M1",
+	},
+	{
+		.metric_expr	= "ipc + M1",
+		.metric_name	= "M2",
+	},
+	{
+		.metric_expr	= "1/M3",
+		.metric_name	= "M3",
+	},
+	{
+		.metric_expr	= "64 * l1d.replacement / 1000000000 / duration_time",
+		.metric_name	= "L1D_Cache_Fill_BW",
+	},
+	{
 		.name = 0,
 		.event = 0,
 		.desc = 0,
 	},
 };
 
-const struct pmu_events_map pmu_events_map[] = {
+/* Struct used to make the PMU event table implementation opaque to callers. */
+struct pmu_events_table {
+	const struct pmu_event *entries;
+};
+
+/*
+ * Map a CPU to its table of PMU events. The CPU is identified by the
+ * cpuid field, which is an arch-specific identifier for the CPU.
+ * The identifier specified in tools/perf/pmu-events/arch/xxx/mapfile
+ * must match the get_cpuid_str() in tools/perf/arch/xxx/util/header.c)
+ *
+ * The  cpuid can contain any character other than the comma.
+ */
+struct pmu_events_map {
+	const char *arch;
+	const char *cpuid;
+	const struct pmu_events_table table;
+};
+
+/*
+ * Global table mapping each known CPU for the architecture to its
+ * table of PMU events.
+ */
+static const struct pmu_events_map pmu_events_map[] = {
 	{
+		.arch = "testarch",
 		.cpuid = "testcpu",
-		.version = "v1",
-		.type = "core",
-		.table = pme_test_soc_cpu,
+		.table = { pme_test_soc_cpu },
 	},
 	{
+		.arch = 0,
 		.cpuid = 0,
-		.version = 0,
-		.type = 0,
-		.table = 0,
+		.table = { 0 },
 	},
 };
 
@@ -147,12 +236,107 @@ static const struct pmu_event pme_test_soc_sys[] = {
 	},
 };
 
-const struct pmu_sys_events pmu_sys_event_tables[] = {
+struct pmu_sys_events {
+	const char *name;
+	const struct pmu_events_table table;
+};
+
+static const struct pmu_sys_events pmu_sys_event_tables[] = {
 	{
-		.table = pme_test_soc_sys,
+		.table = { pme_test_soc_sys },
 		.name = "pme_test_soc_sys",
 	},
 	{
-		.table = 0
+		.table = { 0 }
 	},
 };
+
+int pmu_events_table_for_each_event(const struct pmu_events_table *table, pmu_event_iter_fn fn,
+				    void *data)
+{
+	for (const struct pmu_event *pe = &table->entries[0];
+	     pe->name || pe->metric_group || pe->metric_name;
+	     pe++) {
+		int ret = fn(pe, table, data);
+
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
+const struct pmu_events_table *perf_pmu__find_table(struct perf_pmu *pmu)
+{
+	const struct pmu_events_table *table = NULL;
+	char *cpuid = perf_pmu__getcpuid(pmu);
+	int i;
+
+	/* on some platforms which uses cpus map, cpuid can be NULL for
+	 * PMUs other than CORE PMUs.
+	 */
+	if (!cpuid)
+		return NULL;
+
+	i = 0;
+	for (;;) {
+		const struct pmu_events_map *map = &pmu_events_map[i++];
+
+		if (!map->cpuid)
+			break;
+
+		if (!strcmp_cpuid_str(map->cpuid, cpuid)) {
+			table = &map->table;
+			break;
+		}
+	}
+	free(cpuid);
+	return table;
+}
+
+const struct pmu_events_table *find_core_events_table(const char *arch, const char *cpuid)
+{
+	for (const struct pmu_events_map *tables = &pmu_events_map[0];
+	     tables->arch;
+	     tables++) {
+		if (!strcmp(tables->arch, arch) && !strcmp_cpuid_str(tables->cpuid, cpuid))
+			return &tables->table;
+	}
+	return NULL;
+}
+
+int pmu_for_each_core_event(pmu_event_iter_fn fn, void *data)
+{
+	for (const struct pmu_events_map *tables = &pmu_events_map[0];
+	     tables->arch;
+	     tables++) {
+		int ret = pmu_events_table_for_each_event(&tables->table, fn, data);
+
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
+const struct pmu_events_table *find_sys_events_table(const char *name)
+{
+	for (const struct pmu_sys_events *tables = &pmu_sys_event_tables[0];
+	     tables->name;
+	     tables++) {
+		if (!strcmp(tables->name, name))
+			return &tables->table;
+	}
+	return NULL;
+}
+
+int pmu_for_each_sys_event(pmu_event_iter_fn fn, void *data)
+{
+	for (const struct pmu_sys_events *tables = &pmu_sys_event_tables[0];
+	     tables->name;
+	     tables++) {
+		int ret = pmu_events_table_for_each_event(&tables->table, fn, data);
+
+		if (ret)
+			return ret;
+	}
+	return 0;
+}