Merge tag 'perf-tools-fixes-for-v5.17-2022-02-06' of...

Merge tag 'perf-tools-fixes-for-v5.17-2022-02-06' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tools fixes from Arnaldo Carvalho de Melo:

 - Fix display of grouped aliased events in 'perf stat'.

 - Add missing branch_sample_type to perf_event_attr__fprintf().

 - Apply correct label to user/kernel symbols in branch mode.

 - Fix 'perf ftrace' system_wide tracing, it has to be set before
   creating the maps.

 - Return error if procfs isn't mounted for PID namespaces when
   synthesizing records for pre-existing processes.

 - Set error stream of objdump process for 'perf annotate' TUI, to avoid
   garbling the screen.

 - Add missing arm64 support to perf_mmap__read_self(), the kernel part
   got into 5.17.

 - Check for NULL pointer before dereference writing debug info about a
   sample.

 - Update UAPI copies for asound, perf_event, prctl and kvm headers.

 - Fix a typo in bpf_counter_cgroup.c.

* tag 'perf-tools-fixes-for-v5.17-2022-02-06' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux:
  perf ftrace: system_wide collection is not effective by default
  libperf: Add arm64 support to perf_mmap__read_self()
  tools include UAPI: Sync sound/asound.h copy with the kernel sources
  perf stat: Fix display of grouped aliased events
  perf tools: Apply correct label to user/kernel symbols in branch mode
  perf bpf: Fix a typo in bpf_counter_cgroup.c
  perf synthetic-events: Return error if procfs isn't mounted for PID namespaces
  perf session: Check for NULL pointer before dereference
  perf annotate: Set error stream of objdump process for TUI
  perf tools: Add missing branch_sample_type to perf_event_attr__fprintf()
  tools headers UAPI: Sync linux/kvm.h with the kernel sources
  tools headers UAPI: Sync linux/prctl.h with the kernel sources
  perf beauty: Make the prctl arg regexp more strict to cope with PR_SET_VMA
  tools headers cpufeatures: Sync with the kernel sources
  tools headers UAPI: Sync linux/perf_event.h with the kernel sources
  tools include UAPI: Sync sound/asound.h copy with the kernel sources

tools/arch/x86/include/asm/cpufeatures.h

@@ -299,7 +299,9 @@
 /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
 #define X86_FEATURE_AVX_VNNI		(12*32+ 4) /* AVX VNNI instructions */
 #define X86_FEATURE_AVX512_BF16		(12*32+ 5) /* AVX512 BFLOAT16 instructions */
+#define X86_FEATURE_AMX_BF16		(18*32+22) /* AMX bf16 Support */
 #define X86_FEATURE_AMX_TILE		(18*32+24) /* AMX tile Support */
+#define X86_FEATURE_AMX_INT8		(18*32+25) /* AMX int8 Support */
 
 /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */
 #define X86_FEATURE_CLZERO		(13*32+ 0) /* CLZERO instruction */

tools/include/uapi/linux/kvm.h

@@ -1624,9 +1624,6 @@ struct kvm_enc_region {
 #define KVM_S390_NORMAL_RESET	_IO(KVMIO,   0xc3)
 #define KVM_S390_CLEAR_RESET	_IO(KVMIO,   0xc4)
 
-/* Available with KVM_CAP_XSAVE2 */
-#define KVM_GET_XSAVE2		  _IOR(KVMIO,  0xcf, struct kvm_xsave)
-
 struct kvm_s390_pv_sec_parm {
 	__u64 origin;
 	__u64 length;
@@ -2048,4 +2045,7 @@ struct kvm_stats_desc {
 
 #define KVM_GET_STATS_FD  _IO(KVMIO,  0xce)
 
+/* Available with KVM_CAP_XSAVE2 */
+#define KVM_GET_XSAVE2		  _IOR(KVMIO,  0xcf, struct kvm_xsave)
+
 #endif /* __LINUX_KVM_H */

tools/include/uapi/linux/prctl.h

@@ -272,4 +272,7 @@ struct prctl_mm_map {
 # define PR_SCHED_CORE_SCOPE_THREAD_GROUP	1
 # define PR_SCHED_CORE_SCOPE_PROCESS_GROUP	2
 
+#define PR_SET_VMA		0x53564d41
+# define PR_SET_VMA_ANON_NAME		0
+
 #endif /* _LINUX_PRCTL_H */

tools/include/uapi/sound/asound.h

@@ -56,8 +56,10 @@
  *                                                                          *
  ****************************************************************************/
 
+#define AES_IEC958_STATUS_SIZE		24
+
 struct snd_aes_iec958 {
-	unsigned char status[24];	/* AES/IEC958 channel status bits */
+	unsigned char status[AES_IEC958_STATUS_SIZE]; /* AES/IEC958 channel status bits */
 	unsigned char subcode[147];	/* AES/IEC958 subcode bits */
 	unsigned char pad;		/* nothing */
 	unsigned char dig_subframe[4];	/* AES/IEC958 subframe bits */
@@ -202,6 +204,11 @@ typedef int __bitwise snd_pcm_format_t;
 #define	SNDRV_PCM_FORMAT_S24_BE	((__force snd_pcm_format_t) 7) /* low three bytes */
 #define	SNDRV_PCM_FORMAT_U24_LE	((__force snd_pcm_format_t) 8) /* low three bytes */
 #define	SNDRV_PCM_FORMAT_U24_BE	((__force snd_pcm_format_t) 9) /* low three bytes */
+/*
+ * For S32/U32 formats, 'msbits' hardware parameter is often used to deliver information about the
+ * available bit count in most significant bit. It's for the case of so-called 'left-justified' or
+ * `right-padding` sample which has less width than 32 bit.
+ */
 #define	SNDRV_PCM_FORMAT_S32_LE	((__force snd_pcm_format_t) 10)
 #define	SNDRV_PCM_FORMAT_S32_BE	((__force snd_pcm_format_t) 11)
 #define	SNDRV_PCM_FORMAT_U32_LE	((__force snd_pcm_format_t) 12)
@@ -300,7 +307,7 @@ typedef int __bitwise snd_pcm_subformat_t;
 #define SNDRV_PCM_INFO_HAS_LINK_ESTIMATED_ATIME    0x04000000  /* report estimated link audio time */
 #define SNDRV_PCM_INFO_HAS_LINK_SYNCHRONIZED_ATIME 0x08000000  /* report synchronized audio/system time */
 #define SNDRV_PCM_INFO_EXPLICIT_SYNC	0x10000000	/* needs explicit sync of pointers and data */
-
+#define SNDRV_PCM_INFO_NO_REWINDS	0x20000000	/* hardware can only support monotonic changes of appl_ptr */
 #define SNDRV_PCM_INFO_DRAIN_TRIGGER	0x40000000		/* internal kernel flag - trigger in drain */
 #define SNDRV_PCM_INFO_FIFO_IN_FRAMES	0x80000000	/* internal kernel flag - FIFO size is in frames */
 

tools/lib/perf/mmap.c

@@ -13,6 +13,7 @@
 #include <internal/lib.h>
 #include <linux/kernel.h>
 #include <linux/math64.h>
+#include <linux/stringify.h>
 #include "internal.h"
 
 void perf_mmap__init(struct perf_mmap *map, struct perf_mmap *prev,
@@ -294,6 +295,103 @@ static u64 read_timestamp(void)
 
 	return low | ((u64)high) << 32;
 }
+#elif defined(__aarch64__)
+#define read_sysreg(r) ({						\
+	u64 __val;							\
+	asm volatile("mrs %0, " __stringify(r) : "=r" (__val));		\
+	__val;								\
+})
+
+static u64 read_pmccntr(void)
+{
+	return read_sysreg(pmccntr_el0);
+}
+
+#define PMEVCNTR_READ(idx)					\
+	static u64 read_pmevcntr_##idx(void) {			\
+		return read_sysreg(pmevcntr##idx##_el0);	\
+	}
+
+PMEVCNTR_READ(0);
+PMEVCNTR_READ(1);
+PMEVCNTR_READ(2);
+PMEVCNTR_READ(3);
+PMEVCNTR_READ(4);
+PMEVCNTR_READ(5);
+PMEVCNTR_READ(6);
+PMEVCNTR_READ(7);
+PMEVCNTR_READ(8);
+PMEVCNTR_READ(9);
+PMEVCNTR_READ(10);
+PMEVCNTR_READ(11);
+PMEVCNTR_READ(12);
+PMEVCNTR_READ(13);
+PMEVCNTR_READ(14);
+PMEVCNTR_READ(15);
+PMEVCNTR_READ(16);
+PMEVCNTR_READ(17);
+PMEVCNTR_READ(18);
+PMEVCNTR_READ(19);
+PMEVCNTR_READ(20);
+PMEVCNTR_READ(21);
+PMEVCNTR_READ(22);
+PMEVCNTR_READ(23);
+PMEVCNTR_READ(24);
+PMEVCNTR_READ(25);
+PMEVCNTR_READ(26);
+PMEVCNTR_READ(27);
+PMEVCNTR_READ(28);
+PMEVCNTR_READ(29);
+PMEVCNTR_READ(30);
+
+/*
+ * Read a value direct from PMEVCNTR<idx>
+ */
+static u64 read_perf_counter(unsigned int counter)
+{
+	static u64 (* const read_f[])(void) = {
+		read_pmevcntr_0,
+		read_pmevcntr_1,
+		read_pmevcntr_2,
+		read_pmevcntr_3,
+		read_pmevcntr_4,
+		read_pmevcntr_5,
+		read_pmevcntr_6,
+		read_pmevcntr_7,
+		read_pmevcntr_8,
+		read_pmevcntr_9,
+		read_pmevcntr_10,
+		read_pmevcntr_11,
+		read_pmevcntr_13,
+		read_pmevcntr_12,
+		read_pmevcntr_14,
+		read_pmevcntr_15,
+		read_pmevcntr_16,
+		read_pmevcntr_17,
+		read_pmevcntr_18,
+		read_pmevcntr_19,
+		read_pmevcntr_20,
+		read_pmevcntr_21,
+		read_pmevcntr_22,
+		read_pmevcntr_23,
+		read_pmevcntr_24,
+		read_pmevcntr_25,
+		read_pmevcntr_26,
+		read_pmevcntr_27,
+		read_pmevcntr_28,
+		read_pmevcntr_29,
+		read_pmevcntr_30,
+		read_pmccntr
+	};
+
+	if (counter < ARRAY_SIZE(read_f))
+		return (read_f[counter])();
+
+	return 0;
+}
+
+static u64 read_timestamp(void) { return read_sysreg(cntvct_el0); }
+
 #else
 static u64 read_perf_counter(unsigned int counter __maybe_unused) { return 0; }
 static u64 read_timestamp(void) { return 0; }

tools/lib/perf/tests/test-evsel.c

@@ -130,6 +130,9 @@ static int test_stat_user_read(int event)
 	struct perf_event_attr attr = {
 		.type	= PERF_TYPE_HARDWARE,
 		.config	= event,
+#ifdef __aarch64__
+		.config1 = 0x2,		/* Request user access */
+#endif
 	};
 	int err, i;
 
@@ -150,7 +153,7 @@ static int test_stat_user_read(int event)
 	pc = perf_evsel__mmap_base(evsel, 0, 0);
 	__T("failed to get mmapped address", pc);
 
-#if defined(__i386__) || defined(__x86_64__)
+#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__)
 	__T("userspace counter access not supported", pc->cap_user_rdpmc);
 	__T("userspace counter access not enabled", pc->index);
 	__T("userspace counter width not set", pc->pmc_width >= 32);

tools/perf/builtin-ftrace.c

@@ -1115,6 +1115,7 @@ enum perf_ftrace_subcommand {
 int cmd_ftrace(int argc, const char **argv)
 {
 	int ret;
+	int (*cmd_func)(struct perf_ftrace *) = NULL;
 	struct perf_ftrace ftrace = {
 		.tracer = DEFAULT_TRACER,
 		.target = { .uid = UINT_MAX, },
@@ -1221,6 +1222,28 @@ int cmd_ftrace(int argc, const char **argv)
 		goto out_delete_filters;
 	}
 
+	switch (subcmd) {
+	case PERF_FTRACE_TRACE:
+		if (!argc && target__none(&ftrace.target))
+			ftrace.target.system_wide = true;
+		cmd_func = __cmd_ftrace;
+		break;
+	case PERF_FTRACE_LATENCY:
+		if (list_empty(&ftrace.filters)) {
+			pr_err("Should provide a function to measure\n");
+			parse_options_usage(ftrace_usage, options, "T", 1);
+			ret = -EINVAL;
+			goto out_delete_filters;
+		}
+		cmd_func = __cmd_latency;
+		break;
+	case PERF_FTRACE_NONE:
+	default:
+		pr_err("Invalid subcommand\n");
+		ret = -EINVAL;
+		goto out_delete_filters;
+	}
+
 	ret = target__validate(&ftrace.target);
 	if (ret) {
 		char errbuf[512];
@@ -1248,27 +1271,7 @@ int cmd_ftrace(int argc, const char **argv)
 			goto out_delete_evlist;
 	}
 
-	switch (subcmd) {
-	case PERF_FTRACE_TRACE:
-		if (!argc && target__none(&ftrace.target))
-			ftrace.target.system_wide = true;
-		ret = __cmd_ftrace(&ftrace);
-		break;
-	case PERF_FTRACE_LATENCY:
-		if (list_empty(&ftrace.filters)) {
-			pr_err("Should provide a function to measure\n");
-			parse_options_usage(ftrace_usage, options, "T", 1);
-			ret = -EINVAL;
-			goto out_delete_evlist;
-		}
-		ret = __cmd_latency(&ftrace);
-		break;
-	case PERF_FTRACE_NONE:
-	default:
-		pr_err("Invalid subcommand\n");
-		ret = -EINVAL;
-		break;
-	}
+	ret = cmd_func(&ftrace);
 
 out_delete_evlist:
 	evlist__delete(ftrace.evlist);

tools/perf/trace/beauty/prctl_option.sh

@@ -4,7 +4,7 @@
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
 printf "static const char *prctl_options[] = {\n"
-regex='^#define[[:space:]]+PR_(\w+)[[:space:]]*([[:xdigit:]]+).*'
+regex='^#define[[:space:]]{1}PR_(\w+)[[:space:]]*([[:xdigit:]]+)([[:space:]]*\/.*)?$'
 egrep $regex ${header_dir}/prctl.h | grep -v PR_SET_PTRACER | \
 	sed -r "s/$regex/\2 \1/g"	| \
 	sort -n | xargs printf "\t[%s] = \"%s\",\n"

tools/perf/util/annotate.c

@@ -2036,6 +2036,7 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 	memset(&objdump_process, 0, sizeof(objdump_process));
 	objdump_process.argv = objdump_argv;
 	objdump_process.out = -1;
+	objdump_process.err = -1;
 	if (start_command(&objdump_process)) {
 		pr_err("Failure starting to run %s\n", command);
 		err = -1;

tools/perf/util/bpf_counter_cgroup.c

@@ -266,7 +266,7 @@ static int bperf_cgrp__read(struct evsel *evsel)
 		idx = evsel->core.idx;
 		err = bpf_map_lookup_elem(reading_map_fd, &idx, values);
 		if (err) {
-			pr_err("bpf map lookup falied: idx=%u, event=%s, cgrp=%s\n",
+			pr_err("bpf map lookup failed: idx=%u, event=%s, cgrp=%s\n",
 			       idx, evsel__name(evsel), evsel->cgrp->name);
 			goto out;
 		}

tools/perf/util/machine.c

@@ -2073,6 +2073,7 @@ static void ip__resolve_ams(struct thread *thread,
 
 	ams->addr = ip;
 	ams->al_addr = al.addr;
+	ams->al_level = al.level;
 	ams->ms.maps = al.maps;
 	ams->ms.sym = al.sym;
 	ams->ms.map = al.map;
@@ -2092,6 +2093,7 @@ static void ip__resolve_data(struct thread *thread,
 
 	ams->addr = addr;
 	ams->al_addr = al.addr;
+	ams->al_level = al.level;
 	ams->ms.maps = al.maps;
 	ams->ms.sym = al.sym;
 	ams->ms.map = al.map;

tools/perf/util/map_symbol.h

@@ -18,6 +18,7 @@ struct addr_map_symbol {
 	struct map_symbol ms;
 	u64	      addr;
 	u64	      al_addr;
+	char	      al_level;
 	u64	      phys_addr;
 	u64	      data_page_size;
 };

tools/perf/util/perf_event_attr_fprintf.c

@@ -52,7 +52,7 @@ static void __p_branch_sample_type(char *buf, size_t size, u64 value)
 		bit_name(ABORT_TX), bit_name(IN_TX), bit_name(NO_TX),
 		bit_name(COND), bit_name(CALL_STACK), bit_name(IND_JUMP),
 		bit_name(CALL), bit_name(NO_FLAGS), bit_name(NO_CYCLES),
-		bit_name(HW_INDEX),
+		bit_name(TYPE_SAVE), bit_name(HW_INDEX),
 		{ .name = NULL, }
 	};
 #undef bit_name

tools/perf/util/session.c

@@ -1503,11 +1503,12 @@ static int machines__deliver_event(struct machines *machines,
 			++evlist->stats.nr_unknown_id;
 			return 0;
 		}
-		dump_sample(evsel, event, sample, perf_env__arch(machine->env));
 		if (machine == NULL) {
 			++evlist->stats.nr_unprocessable_samples;
+			dump_sample(evsel, event, sample, perf_env__arch(NULL));
 			return 0;
 		}
+		dump_sample(evsel, event, sample, perf_env__arch(machine->env));
 		return evlist__deliver_sample(evlist, tool, event, sample, evsel, machine);
 	case PERF_RECORD_MMAP:
 		return tool->mmap(tool, event, sample, machine);

tools/perf/util/sort.c

@@ -915,7 +915,7 @@ static int hist_entry__sym_from_snprintf(struct hist_entry *he, char *bf,
 		struct addr_map_symbol *from = &he->branch_info->from;
 
 		return _hist_entry__sym_snprintf(&from->ms, from->al_addr,
-						 he->level, bf, size, width);
+						 from->al_level, bf, size, width);
 	}
 
 	return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A");
@@ -928,7 +928,7 @@ static int hist_entry__sym_to_snprintf(struct hist_entry *he, char *bf,
 		struct addr_map_symbol *to = &he->branch_info->to;
 
 		return _hist_entry__sym_snprintf(&to->ms, to->al_addr,
-						 he->level, bf, size, width);
+						 to->al_level, bf, size, width);
 	}
 
 	return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A");

tools/perf/util/stat-display.c

@@ -585,16 +585,17 @@ static void collect_all_aliases(struct perf_stat_config *config, struct evsel *c
 
 	alias = list_prepare_entry(counter, &(evlist->core.entries), core.node);
 	list_for_each_entry_continue (alias, &evlist->core.entries, core.node) {
-		if (strcmp(evsel__name(alias), evsel__name(counter)) ||
-		    alias->scale != counter->scale ||
-		    alias->cgrp != counter->cgrp ||
-		    strcmp(alias->unit, counter->unit) ||
-		    evsel__is_clock(alias) != evsel__is_clock(counter) ||
-		    !strcmp(alias->pmu_name, counter->pmu_name))
-			break;
+		/* Merge events with the same name, etc. but on different PMUs. */
+		if (!strcmp(evsel__name(alias), evsel__name(counter)) &&
+			alias->scale == counter->scale &&
+			alias->cgrp == counter->cgrp &&
+			!strcmp(alias->unit, counter->unit) &&
+			evsel__is_clock(alias) == evsel__is_clock(counter) &&
+			strcmp(alias->pmu_name, counter->pmu_name)) {
 			alias->merged_stat = true;
 			cb(config, alias, data, false);
 		}
+	}
 }
 
 static bool is_uncore(struct evsel *evsel)

tools/perf/util/synthetic-events.c

@@ -1784,6 +1784,25 @@ int __machine__synthesize_threads(struct machine *machine, struct perf_tool *too
 				  perf_event__handler_t process, bool needs_mmap,
 				  bool data_mmap, unsigned int nr_threads_synthesize)
 {
+	/*
+	 * When perf runs in non-root PID namespace, and the namespace's proc FS
+	 * is not mounted, nsinfo__is_in_root_namespace() returns false.
+	 * In this case, the proc FS is coming for the parent namespace, thus
+	 * perf tool will wrongly gather process info from its parent PID
+	 * namespace.
+	 *
+	 * To avoid the confusion that the perf tool runs in a child PID
+	 * namespace but it synthesizes thread info from its parent PID
+	 * namespace, returns failure with warning.
+	 */
+	if (!nsinfo__is_in_root_namespace()) {
+		pr_err("Perf runs in non-root PID namespace but it tries to ");
+		pr_err("gather process info from its parent PID namespace.\n");
+		pr_err("Please mount the proc file system properly, e.g. ");
+		pr_err("add the option '--mount-proc' for unshare command.\n");
+		return -EPERM;
+	}
+
 	if (target__has_task(target))
 		return perf_event__synthesize_thread_map(tool, threads, process, machine,
 							 needs_mmap, data_mmap);