Merge tag 'perf-tools-for-v5.15-2021-09-04' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tool updates from Arnaldo Carvalho de Melo:
 "New features:

   - Improvements for the flamegraph python script, including:
       - Display perf.data header
       - Display PIDs of user stacks
       - Added option to change color scheme
       - Default to blue/green color scheme to improve accessibility
       - Correctly identify kernel stacks when debuginfo is available

   - Improvements for 'perf bench futex':
       - Add --mlockall parameter
       - Add --broadcast and --pi to the 'requeue' sub benchmark

   - Add support for PMU aliases.

   - Introduce an ARM Coresight ETE decoder.

   - Add a 'perf bench' entry for evlist open/close operations, to help
     quantify improvements with multithreading 'perf record'.

   - Allow reporting the [un]throttle PERF_RECORD_ meta event in 'perf
     script's python scripting.

   - Add a 'perf test' entry for PMU aliases.

   - Add a 'perf test' entry for 'perf record/perf report/perf script'
     pipe mode.

  Fixes:

   - perf script dlfilter (API for filtering via dynamically loaded
     shared object introduced in v5.14) fixes and a 'perf test' entry
     for it.

   - Fix get_current_dir_name() compilation on Android.

   - Fix issues with asciidoc and double dashes uses.

   - Fix memory leaks in the BTF handling code.

   - Fix leftover problems in the Documentation from the infrastructure
     originally lifted from the git codebase.

   - Fix *probe_vfs_getname.sh 'perf test' failures.

   - Handle fd gaps in 'perf test's test__dso_data_reopen().

   - Make sure to show disasembly warnings for 'perf annotate --stdio'.

   - Fix output from pipe to file and vice-versa in 'perf
     record/report/script'.

   - Correct 'perf data -h' output.

   - Fix wrong comm in system-wide mode with 'perf record --delay'.

   - Do not allow --for-each-cgroup without cpu in 'perf stat'

   - Make 'perf test --skip' work on shell tests.

   - Fix libperf's verbose printing.

  Misc improvements:

   - Preparatory patches for multithreading various 'perf record' phases
     (synthesizing, opening, recording, etc).

   - Add sparse context/locking annotations in compiler-types.h, also to
     help with the multithreading effort.

   - Optimize the generation of the arch specific erno tables used in
     'perf trace'.

   - Optimize libperf's perf_cpu_map__max().

   - Improve ARM's CoreSight warnings.

   - Report collisions in AUX records.

   - Improve warnings for the LLVM 'perf test' entry.

   - Improve the PMU events 'perf test' codebase.

   - perf test: Do not compare overheads in the zstd comp test

   - Better support annotation on ARM.

   - Update 'perf trace's cmd string table to decode sys_bpf() first
     arg.

  Vendor events:

   - Add JSON events and metrics for Intel's Ice Lake, Tiger Lake and
     Elhart Lake.

   - Update JSON eventsand metrics for Intel's Cascade Lake and Sky Lake
     servers.

  Hardware tracing:

   - Improvements for the ARM hardware tracing auxtrace support"

* tag 'perf-tools-for-v5.15-2021-09-04' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (130 commits)
  perf tests: Add test for PMU aliases
  perf pmu: Add PMU alias support
  perf session: Report collisions in AUX records
  perf script python: Allow reporting the [un]throttle PERF_RECORD_ meta event
  perf build: Report failure for testing feature libopencsd
  perf cs-etm: Show a warning for an unknown magic number
  perf cs-etm: Print the decoder name
  perf cs-etm: Create ETE decoder
  perf cs-etm: Update OpenCSD decoder for ETE
  perf cs-etm: Fix typo
  perf cs-etm: Save TRCDEVARCH register
  perf cs-etm: Refactor out ETMv4 header saving
  perf cs-etm: Initialise architecture based on TRCIDR1
  perf cs-etm: Refactor initialisation of decoder params.
  tools build: Fix feature detect clean for out of source builds
  perf evlist: Add evlist__for_each_entry_from() macro
  perf evsel: Handle precise_ip fallback in evsel__open_cpu()
  perf evsel: Move bpf_counter__install_pe() to success path in evsel__open_cpu()
  perf evsel: Move test_attr__open() to success path in evsel__open_cpu()
  perf evsel: Move ignore_missing_thread() to fallback code
  ...

3 files changed, 254 insertions, 30 deletions

diff --git a/tools/perf/arch/arm/util/auxtrace.c b/tools/perf/arch/arm/util/auxtrace.c
index b187bddbd01a..c7c7ec0812d5 100644
--- a/tools/perf/arch/arm/util/auxtrace.c
+++ b/tools/perf/arch/arm/util/auxtrace.c
@@ -107,3 +107,35 @@ struct auxtrace_record
 	*err = 0;
 	return NULL;
 }
+
+#if defined(__arm__)
+u64 compat_auxtrace_mmap__read_head(struct auxtrace_mmap *mm)
+{
+	struct perf_event_mmap_page *pc = mm->userpg;
+	u64 result;
+
+	__asm__ __volatile__(
+"	ldrd    %0, %H0, [%1]"
+	: "=&r" (result)
+	: "r" (&pc->aux_head), "Qo" (pc->aux_head)
+	);
+
+	return result;
+}
+
+int compat_auxtrace_mmap__write_tail(struct auxtrace_mmap *mm, u64 tail)
+{
+	struct perf_event_mmap_page *pc = mm->userpg;
+
+	/* Ensure all reads are done before we write the tail out */
+	smp_mb();
+
+	__asm__ __volatile__(
+"	strd    %2, %H2, [%1]"
+	: "=Qo" (pc->aux_tail)
+	: "r" (&pc->aux_tail), "r" (tail)
+	);
+
+	return 0;
+}
+#endif
diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index 85168d87b2d7..515aae470e23 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -47,15 +47,17 @@ static const char *metadata_etmv3_ro[CS_ETM_PRIV_MAX] = {
 	[CS_ETM_ETMIDR]		= "mgmt/etmidr",
 };
 
-static const char *metadata_etmv4_ro[CS_ETMV4_PRIV_MAX] = {
+static const char * const metadata_etmv4_ro[] = {
 	[CS_ETMV4_TRCIDR0]		= "trcidr/trcidr0",
 	[CS_ETMV4_TRCIDR1]		= "trcidr/trcidr1",
 	[CS_ETMV4_TRCIDR2]		= "trcidr/trcidr2",
 	[CS_ETMV4_TRCIDR8]		= "trcidr/trcidr8",
 	[CS_ETMV4_TRCAUTHSTATUS]	= "mgmt/trcauthstatus",
+	[CS_ETE_TRCDEVARCH]		= "mgmt/trcdevarch"
 };
 
 static bool cs_etm_is_etmv4(struct auxtrace_record *itr, int cpu);
+static bool cs_etm_is_ete(struct auxtrace_record *itr, int cpu);
 
 static int cs_etm_set_context_id(struct auxtrace_record *itr,
 				 struct evsel *evsel, int cpu)
@@ -73,7 +75,7 @@ static int cs_etm_set_context_id(struct auxtrace_record *itr,
 	if (!cs_etm_is_etmv4(itr, cpu))
 		goto out;
 
-	/* Get a handle on TRCIRD2 */
+	/* Get a handle on TRCIDR2 */
 	snprintf(path, PATH_MAX, "cpu%d/%s",
 		 cpu, metadata_etmv4_ro[CS_ETMV4_TRCIDR2]);
 	err = perf_pmu__scan_file(cs_etm_pmu, path, "%x", &val);
@@ -533,7 +535,7 @@ cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused,
 		      struct evlist *evlist __maybe_unused)
 {
 	int i;
-	int etmv3 = 0, etmv4 = 0;
+	int etmv3 = 0, etmv4 = 0, ete = 0;
 	struct perf_cpu_map *event_cpus = evlist->core.cpus;
 	struct perf_cpu_map *online_cpus = perf_cpu_map__new(NULL);
 
@@ -544,7 +546,9 @@ cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused,
 			    !cpu_map__has(online_cpus, i))
 				continue;
 
-			if (cs_etm_is_etmv4(itr, i))
+			if (cs_etm_is_ete(itr, i))
+				ete++;
+			else if (cs_etm_is_etmv4(itr, i))
 				etmv4++;
 			else
 				etmv3++;
@@ -555,7 +559,9 @@ cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused,
 			if (!cpu_map__has(online_cpus, i))
 				continue;
 
-			if (cs_etm_is_etmv4(itr, i))
+			if (cs_etm_is_ete(itr, i))
+				ete++;
+			else if (cs_etm_is_etmv4(itr, i))
 				etmv4++;
 			else
 				etmv3++;
@@ -565,6 +571,7 @@ cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused,
 	perf_cpu_map__put(online_cpus);
 
 	return (CS_ETM_HEADER_SIZE +
+	       (ete   * CS_ETE_PRIV_SIZE) +
 	       (etmv4 * CS_ETMV4_PRIV_SIZE) +
 	       (etmv3 * CS_ETMV3_PRIV_SIZE));
 }
@@ -607,6 +614,49 @@ static int cs_etm_get_ro(struct perf_pmu *pmu, int cpu, const char *path)
 	return val;
 }
 
+#define TRCDEVARCH_ARCHPART_SHIFT 0
+#define TRCDEVARCH_ARCHPART_MASK  GENMASK(11, 0)
+#define TRCDEVARCH_ARCHPART(x)    (((x) & TRCDEVARCH_ARCHPART_MASK) >> TRCDEVARCH_ARCHPART_SHIFT)
+
+#define TRCDEVARCH_ARCHVER_SHIFT 12
+#define TRCDEVARCH_ARCHVER_MASK  GENMASK(15, 12)
+#define TRCDEVARCH_ARCHVER(x)    (((x) & TRCDEVARCH_ARCHVER_MASK) >> TRCDEVARCH_ARCHVER_SHIFT)
+
+static bool cs_etm_is_ete(struct auxtrace_record *itr, int cpu)
+{
+	struct cs_etm_recording *ptr = container_of(itr, struct cs_etm_recording, itr);
+	struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu;
+	int trcdevarch = cs_etm_get_ro(cs_etm_pmu, cpu, metadata_etmv4_ro[CS_ETE_TRCDEVARCH]);
+
+	/*
+	 * ETE if ARCHVER is 5 (ARCHVER is 4 for ETM) and ARCHPART is 0xA13.
+	 * See ETM_DEVARCH_ETE_ARCH in coresight-etm4x.h
+	 */
+	return TRCDEVARCH_ARCHVER(trcdevarch) == 5 && TRCDEVARCH_ARCHPART(trcdevarch) == 0xA13;
+}
+
+static void cs_etm_save_etmv4_header(__u64 data[], struct auxtrace_record *itr, int cpu)
+{
+	struct cs_etm_recording *ptr = container_of(itr, struct cs_etm_recording, itr);
+	struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu;
+
+	/* Get trace configuration register */
+	data[CS_ETMV4_TRCCONFIGR] = cs_etmv4_get_config(itr);
+	/* Get traceID from the framework */
+	data[CS_ETMV4_TRCTRACEIDR] = coresight_get_trace_id(cpu);
+	/* Get read-only information from sysFS */
+	data[CS_ETMV4_TRCIDR0] = cs_etm_get_ro(cs_etm_pmu, cpu,
+					       metadata_etmv4_ro[CS_ETMV4_TRCIDR0]);
+	data[CS_ETMV4_TRCIDR1] = cs_etm_get_ro(cs_etm_pmu, cpu,
+					       metadata_etmv4_ro[CS_ETMV4_TRCIDR1]);
+	data[CS_ETMV4_TRCIDR2] = cs_etm_get_ro(cs_etm_pmu, cpu,
+					       metadata_etmv4_ro[CS_ETMV4_TRCIDR2]);
+	data[CS_ETMV4_TRCIDR8] = cs_etm_get_ro(cs_etm_pmu, cpu,
+					       metadata_etmv4_ro[CS_ETMV4_TRCIDR8]);
+	data[CS_ETMV4_TRCAUTHSTATUS] = cs_etm_get_ro(cs_etm_pmu, cpu,
+						     metadata_etmv4_ro[CS_ETMV4_TRCAUTHSTATUS]);
+}
+
 static void cs_etm_get_metadata(int cpu, u32 *offset,
 				struct auxtrace_record *itr,
 				struct perf_record_auxtrace_info *info)
@@ -618,31 +668,20 @@ static void cs_etm_get_metadata(int cpu, u32 *offset,
 	struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu;
 
 	/* first see what kind of tracer this cpu is affined to */
-	if (cs_etm_is_etmv4(itr, cpu)) {
-		magic = __perf_cs_etmv4_magic;
-		/* Get trace configuration register */
-		info->priv[*offset + CS_ETMV4_TRCCONFIGR] =
-						cs_etmv4_get_config(itr);
-		/* Get traceID from the framework */
-		info->priv[*offset + CS_ETMV4_TRCTRACEIDR] =
-						coresight_get_trace_id(cpu);
-		/* Get read-only information from sysFS */
-		info->priv[*offset + CS_ETMV4_TRCIDR0] =
-			cs_etm_get_ro(cs_etm_pmu, cpu,
-				      metadata_etmv4_ro[CS_ETMV4_TRCIDR0]);
-		info->priv[*offset + CS_ETMV4_TRCIDR1] =
+	if (cs_etm_is_ete(itr, cpu)) {
+		magic = __perf_cs_ete_magic;
+		/* ETE uses the same registers as ETMv4 plus TRCDEVARCH */
+		cs_etm_save_etmv4_header(&info->priv[*offset], itr, cpu);
+		info->priv[*offset + CS_ETE_TRCDEVARCH] =
 			cs_etm_get_ro(cs_etm_pmu, cpu,
-				      metadata_etmv4_ro[CS_ETMV4_TRCIDR1]);
-		info->priv[*offset + CS_ETMV4_TRCIDR2] =
-			cs_etm_get_ro(cs_etm_pmu, cpu,
-				      metadata_etmv4_ro[CS_ETMV4_TRCIDR2]);
-		info->priv[*offset + CS_ETMV4_TRCIDR8] =
-			cs_etm_get_ro(cs_etm_pmu, cpu,
-				      metadata_etmv4_ro[CS_ETMV4_TRCIDR8]);
-		info->priv[*offset + CS_ETMV4_TRCAUTHSTATUS] =
-			cs_etm_get_ro(cs_etm_pmu, cpu,
-				      metadata_etmv4_ro
-				      [CS_ETMV4_TRCAUTHSTATUS]);
+				      metadata_etmv4_ro[CS_ETE_TRCDEVARCH]);
+
+		/* How much space was used */
+		increment = CS_ETE_PRIV_MAX;
+		nr_trc_params = CS_ETE_PRIV_MAX - CS_ETM_COMMON_BLK_MAX_V1;
+	} else if (cs_etm_is_etmv4(itr, cpu)) {
+		magic = __perf_cs_etmv4_magic;
+		cs_etm_save_etmv4_header(&info->priv[*offset], itr, cpu);
 
 		/* How much space was used */
 		increment = CS_ETMV4_PRIV_MAX;
diff --git a/tools/perf/arch/x86/util/pmu.c b/tools/perf/arch/x86/util/pmu.c
index d48d608517fd..74d69db1ea99 100644
--- a/tools/perf/arch/x86/util/pmu.c
+++ b/tools/perf/arch/x86/util/pmu.c
@@ -1,12 +1,30 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <string.h>
-
+#include <stdio.h>
+#include <sys/types.h>
+#include <dirent.h>
+#include <fcntl.h>
 #include <linux/stddef.h>
 #include <linux/perf_event.h>
+#include <linux/zalloc.h>
+#include <api/fs/fs.h>
+#include <errno.h>
 
 #include "../../../util/intel-pt.h"
 #include "../../../util/intel-bts.h"
 #include "../../../util/pmu.h"
+#include "../../../util/fncache.h"
+
+#define TEMPLATE_ALIAS	"%s/bus/event_source/devices/%s/alias"
+
+struct pmu_alias {
+	char *name;
+	char *alias;
+	struct list_head list;
+};
+
+static LIST_HEAD(pmu_alias_name_list);
+static bool cached_list;
 
 struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused)
 {
@@ -18,3 +36,138 @@ struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu __mayb
 #endif
 	return NULL;
 }
+
+static void pmu_alias__delete(struct pmu_alias *pmu_alias)
+{
+	if (!pmu_alias)
+		return;
+
+	zfree(&pmu_alias->name);
+	zfree(&pmu_alias->alias);
+	free(pmu_alias);
+}
+
+static struct pmu_alias *pmu_alias__new(char *name, char *alias)
+{
+	struct pmu_alias *pmu_alias = zalloc(sizeof(*pmu_alias));
+
+	if (pmu_alias) {
+		pmu_alias->name = strdup(name);
+		if (!pmu_alias->name)
+			goto out_delete;
+
+		pmu_alias->alias = strdup(alias);
+		if (!pmu_alias->alias)
+			goto out_delete;
+	}
+	return pmu_alias;
+
+out_delete:
+	pmu_alias__delete(pmu_alias);
+	return NULL;
+}
+
+static int setup_pmu_alias_list(void)
+{
+	char path[PATH_MAX];
+	DIR *dir;
+	struct dirent *dent;
+	const char *sysfs = sysfs__mountpoint();
+	struct pmu_alias *pmu_alias;
+	char buf[MAX_PMU_NAME_LEN];
+	FILE *file;
+	int ret = -ENOMEM;
+
+	if (!sysfs)
+		return -1;
+
+	snprintf(path, PATH_MAX,
+		 "%s" EVENT_SOURCE_DEVICE_PATH, sysfs);
+
+	dir = opendir(path);
+	if (!dir)
+		return -errno;
+
+	while ((dent = readdir(dir))) {
+		if (!strcmp(dent->d_name, ".") ||
+		    !strcmp(dent->d_name, ".."))
+			continue;
+
+		snprintf(path, PATH_MAX,
+			 TEMPLATE_ALIAS, sysfs, dent->d_name);
+
+		if (!file_available(path))
+			continue;
+
+		file = fopen(path, "r");
+		if (!file)
+			continue;
+
+		if (!fgets(buf, sizeof(buf), file)) {
+			fclose(file);
+			continue;
+		}
+
+		fclose(file);
+
+		/* Remove the last '\n' */
+		buf[strlen(buf) - 1] = 0;
+
+		pmu_alias = pmu_alias__new(dent->d_name, buf);
+		if (!pmu_alias)
+			goto close_dir;
+
+		list_add_tail(&pmu_alias->list, &pmu_alias_name_list);
+	}
+
+	ret = 0;
+
+close_dir:
+	closedir(dir);
+	return ret;
+}
+
+static char *__pmu_find_real_name(const char *name)
+{
+	struct pmu_alias *pmu_alias;
+
+	list_for_each_entry(pmu_alias, &pmu_alias_name_list, list) {
+		if (!strcmp(name, pmu_alias->alias))
+			return pmu_alias->name;
+	}
+
+	return (char *)name;
+}
+
+char *pmu_find_real_name(const char *name)
+{
+	if (cached_list)
+		return __pmu_find_real_name(name);
+
+	setup_pmu_alias_list();
+	cached_list = true;
+
+	return __pmu_find_real_name(name);
+}
+
+static char *__pmu_find_alias_name(const char *name)
+{
+	struct pmu_alias *pmu_alias;
+
+	list_for_each_entry(pmu_alias, &pmu_alias_name_list, list) {
+		if (!strcmp(name, pmu_alias->name))
+			return pmu_alias->alias;
+	}
+	return NULL;
+}
+
+char *pmu_find_alias_name(const char *name)
+{
+	if (cached_list)
+		return __pmu_find_alias_name(name);
+
+	setup_pmu_alias_list();
+	cached_list = true;
+
+	return __pmu_find_alias_name(name);
+}