Merge tag 'perf-urgent-for-mingo-4.18-20180625' of git://git.kernel.o…

…rg/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Pull perf/urgent fixes from Arnaldo Carvalho de Melo:

perf bench: (Jiri Olsa):

- Fix NUMA report output code handling of less than 1s runtimes.

perf script: (Ravi Bangoria)

- Add missing output fields in a 'perf script -h' hint.

- Fix crash because of missing evsel->priv.

- Fix crash caused by accessing feat_ops[HEADER_LAST_FEATURE], which
  is just a end of features header marker.

perf stat: (Thomas Richter)

- Remove duplicate event counting

perf test:

- Wire parsing error handling in 'parse events' test (Jiri Olsa)

- Fix 'session topology' test on s/390 (Thomas Richter)

eBPF: (Yonghong Song)

- Fix a clang 7.0 compilation error when building perf linking
  with libclang

intel-pt: (Adrian Hunter)

- Fix packet decoding of CYC packets.

Copies of kernel files: (Arnaldo Carvalho de Melo)

- Synchronize drm/drm.h UAPI

- Update x86's syscall_64.tbl, adding support for 'io_pgetevents' and 'rseq'
  in 'perf trace'.

- Update powerpc uapi/asm/unistd.h, adding support for the 'rseq' syscall.

- Update if_link.h and bpf.h, no effect on tool features.

PowerPC: (Sandipan Das)

- Fix crash if callchain is empty.

s/390: (Thomas Richter)

- Support random socked_id assignment in the perf header.

- Support s390 random socket_id assignment in perf.data file.

- Make PMU alias definitions taken from sysfs and JSON files comparable
  by normalizing them wrt spaces and newlines.

Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>

tools/arch/powerpc/include/uapi/asm/unistd.h

@@ -398,5 +398,6 @@
 #define __NR_pkey_alloc		384
 #define __NR_pkey_free		385
 #define __NR_pkey_mprotect	386
+#define __NR_rseq		387
 
 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */

tools/include/uapi/drm/drm.h

@@ -680,6 +680,13 @@ struct drm_get_cap {
  */
 #define DRM_CLIENT_CAP_ATOMIC	3
 
+/**
+ * DRM_CLIENT_CAP_ASPECT_RATIO
+ *
+ * If set to 1, the DRM core will provide aspect ratio information in modes.
+ */
+#define DRM_CLIENT_CAP_ASPECT_RATIO    4
+
 /** DRM_IOCTL_SET_CLIENT_CAP ioctl argument type */
 struct drm_set_client_cap {
 	__u64 capability;

tools/include/uapi/linux/bpf.h

@@ -2630,7 +2630,7 @@ struct bpf_fib_lookup {
 	union {
 		/* inputs to lookup */
 		__u8	tos;		/* AF_INET  */
-		__be32	flowlabel;	/* AF_INET6 */
+		__be32	flowinfo;	/* AF_INET6, flow_label + priority */
 
 		/* output: metric of fib result (IPv4/IPv6 only) */
 		__u32	rt_metric;

tools/include/uapi/linux/if_link.h

@@ -333,6 +333,7 @@ enum {
 	IFLA_BRPORT_BCAST_FLOOD,
 	IFLA_BRPORT_GROUP_FWD_MASK,
 	IFLA_BRPORT_NEIGH_SUPPRESS,
+	IFLA_BRPORT_ISOLATED,
 	__IFLA_BRPORT_MAX
 };
 #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
@@ -516,6 +517,7 @@ enum {
 	IFLA_VXLAN_COLLECT_METADATA,
 	IFLA_VXLAN_LABEL,
 	IFLA_VXLAN_GPE,
+	IFLA_VXLAN_TTL_INHERIT,
 	__IFLA_VXLAN_MAX
 };
 #define IFLA_VXLAN_MAX	(__IFLA_VXLAN_MAX - 1)

tools/perf/arch/powerpc/util/skip-callchain-idx.c

@@ -243,7 +243,7 @@ int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain)
 	u64 ip;
 	u64 skip_slot = -1;
 
-	if (chain->nr < 3)
+	if (!chain || chain->nr < 3)
 		return skip_slot;
 
 	ip = chain->ips[2];

tools/perf/arch/x86/entry/syscalls/syscall_64.tbl

@@ -341,6 +341,8 @@
 330	common	pkey_alloc		__x64_sys_pkey_alloc
 331	common	pkey_free		__x64_sys_pkey_free
 332	common	statx			__x64_sys_statx
+333	common	io_pgetevents		__x64_sys_io_pgetevents
+334	common	rseq			__x64_sys_rseq
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact

tools/perf/bench/numa.c

@@ -1098,7 +1098,7 @@ static void *worker_thread(void *__tdata)
 	u8 *global_data;
 	u8 *process_data;
 	u8 *thread_data;
-	u64 bytes_done;
+	u64 bytes_done, secs;
 	long work_done;
 	u32 l;
 	struct rusage rusage;
@@ -1254,7 +1254,8 @@ static void *worker_thread(void *__tdata)
 	timersub(&stop, &start0, &diff);
 	td->runtime_ns = diff.tv_sec * NSEC_PER_SEC;
 	td->runtime_ns += diff.tv_usec * NSEC_PER_USEC;
-	td->speed_gbs = bytes_done / (td->runtime_ns / NSEC_PER_SEC) / 1e9;
+	secs = td->runtime_ns / NSEC_PER_SEC;
+	td->speed_gbs = secs ? bytes_done / secs / 1e9 : 0;
 
 	getrusage(RUSAGE_THREAD, &rusage);
 	td->system_time_ns = rusage.ru_stime.tv_sec * NSEC_PER_SEC;

tools/perf/builtin-annotate.c

@@ -283,6 +283,15 @@ static int process_sample_event(struct perf_tool *tool,
 	return ret;
 }
 
+static int process_feature_event(struct perf_tool *tool,
+				 union perf_event *event,
+				 struct perf_session *session)
+{
+	if (event->feat.feat_id < HEADER_LAST_FEATURE)
+		return perf_event__process_feature(tool, event, session);
+	return 0;
+}
+
 static int hist_entry__tty_annotate(struct hist_entry *he,
 				    struct perf_evsel *evsel,
 				    struct perf_annotate *ann)
@@ -471,7 +480,7 @@ int cmd_annotate(int argc, const char **argv)
 			.attr	= perf_event__process_attr,
 			.build_id = perf_event__process_build_id,
 			.tracing_data   = perf_event__process_tracing_data,
-			.feature	= perf_event__process_feature,
+			.feature	= process_feature_event,
 			.ordered_events = true,
 			.ordering_requires_timestamps = true,
 		},

tools/perf/builtin-report.c

@@ -217,7 +217,8 @@ static int process_feature_event(struct perf_tool *tool,
 	}
 
 	/*
-	 * All features are received, we can force the
+	 * (feat_id = HEADER_LAST_FEATURE) is the end marker which
+	 * means all features are received, now we can force the
 	 * group if needed.
 	 */
 	setup_forced_leader(rep, session->evlist);

tools/perf/builtin-script.c

@@ -1834,6 +1834,7 @@ static int process_attr(struct perf_tool *tool, union perf_event *event,
 	struct perf_evlist *evlist;
 	struct perf_evsel *evsel, *pos;
 	int err;
+	static struct perf_evsel_script *es;
 
 	err = perf_event__process_attr(tool, event, pevlist);
 	if (err)
@@ -1842,6 +1843,19 @@ static int process_attr(struct perf_tool *tool, union perf_event *event,
 	evlist = *pevlist;
 	evsel = perf_evlist__last(*pevlist);
 
+	if (!evsel->priv) {
+		if (scr->per_event_dump) {
+			evsel->priv = perf_evsel_script__new(evsel,
+						scr->session->data);
+		} else {
+			es = zalloc(sizeof(*es));
+			if (!es)
+				return -ENOMEM;
+			es->fp = stdout;
+			evsel->priv = es;
+		}
+	}
+
 	if (evsel->attr.type >= PERF_TYPE_MAX &&
 	    evsel->attr.type != PERF_TYPE_SYNTH)
 		return 0;
@@ -3030,6 +3044,15 @@ int process_cpu_map_event(struct perf_tool *tool __maybe_unused,
 	return set_maps(script);
 }
 
+static int process_feature_event(struct perf_tool *tool,
+				 union perf_event *event,
+				 struct perf_session *session)
+{
+	if (event->feat.feat_id < HEADER_LAST_FEATURE)
+		return perf_event__process_feature(tool, event, session);
+	return 0;
+}
+
 #ifdef HAVE_AUXTRACE_SUPPORT
 static int perf_script__process_auxtrace_info(struct perf_tool *tool,
 					      union perf_event *event,
@@ -3074,7 +3097,7 @@ int cmd_script(int argc, const char **argv)
 			.attr		 = process_attr,
 			.event_update   = perf_event__process_event_update,
 			.tracing_data	 = perf_event__process_tracing_data,
-			.feature	 = perf_event__process_feature,
+			.feature	 = process_feature_event,
 			.build_id	 = perf_event__process_build_id,
 			.id_index	 = perf_event__process_id_index,
 			.auxtrace_info	 = perf_script__process_auxtrace_info,
@@ -3125,8 +3148,9 @@ int cmd_script(int argc, const char **argv)
 		     "+field to add and -field to remove."
 		     "Valid types: hw,sw,trace,raw,synth. "
 		     "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
-		     "addr,symoff,period,iregs,uregs,brstack,brstacksym,flags,"
-		     "bpf-output,callindent,insn,insnlen,brstackinsn,synth,phys_addr",
+		     "addr,symoff,srcline,period,iregs,uregs,brstack,"
+		     "brstacksym,flags,bpf-output,brstackinsn,brstackoff,"
+		     "callindent,insn,insnlen,synth,phys_addr,metric,misc",
 		     parse_output_fields),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,
 		    "system-wide collection from all CPUs"),

tools/perf/tests/parse-events.c

@@ -1309,6 +1309,11 @@ static int test__checkevent_config_cache(struct perf_evlist *evlist)
 	return 0;
 }
 
+static bool test__intel_pt_valid(void)
+{
+	return !!perf_pmu__find("intel_pt");
+}
+
 static int test__intel_pt(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel = perf_evlist__first(evlist);
@@ -1375,6 +1380,7 @@ struct evlist_test {
 	const char *name;
 	__u32 type;
 	const int id;
+	bool (*valid)(void);
 	int (*check)(struct perf_evlist *evlist);
 };
 
@@ -1648,6 +1654,7 @@ static struct evlist_test test__events[] = {
 	},
 	{
 		.name  = "intel_pt//u",
+		.valid = test__intel_pt_valid,
 		.check = test__intel_pt,
 		.id    = 52,
 	},
@@ -1686,17 +1693,24 @@ static struct terms_test test__terms[] = {
 
 static int test_event(struct evlist_test *e)
 {
+	struct parse_events_error err = { .idx = 0, };
 	struct perf_evlist *evlist;
 	int ret;
 
+	if (e->valid && !e->valid()) {
+		pr_debug("... SKIP");
+		return 0;
+	}
+
 	evlist = perf_evlist__new();
 	if (evlist == NULL)
 		return -ENOMEM;
 
-	ret = parse_events(evlist, e->name, NULL);
+	ret = parse_events(evlist, e->name, &err);
 	if (ret) {
-		pr_debug("failed to parse event '%s', err %d\n",
-			 e->name, ret);
+		pr_debug("failed to parse event '%s', err %d, str '%s'\n",
+			 e->name, ret, err.str);
+		parse_events_print_error(&err, e->name);
 	} else {
 		ret = e->check(evlist);
 	}
@@ -1714,10 +1728,11 @@ static int test_events(struct evlist_test *events, unsigned cnt)
 	for (i = 0; i < cnt; i++) {
 		struct evlist_test *e = &events[i];
 
-		pr_debug("running test %d '%s'\n", e->id, e->name);
+		pr_debug("running test %d '%s'", e->id, e->name);
 		ret1 = test_event(e);
 		if (ret1)
 			ret2 = ret1;
+		pr_debug("\n");
 	}
 
 	return ret2;
@@ -1799,7 +1814,7 @@ static int test_pmu_events(void)
 	}
 
 	while (!ret && (ent = readdir(dir))) {
-		struct evlist_test e;
+		struct evlist_test e = { .id = 0, };
 		char name[2 * NAME_MAX + 1 + 12 + 3];
 
 		/* Names containing . are special and cannot be used directly */

tools/perf/tests/topology.c

@@ -45,6 +45,7 @@ static int session_write_header(char *path)
 
 	perf_header__set_feat(&session->header, HEADER_CPU_TOPOLOGY);
 	perf_header__set_feat(&session->header, HEADER_NRCPUS);
+	perf_header__set_feat(&session->header, HEADER_ARCH);
 
 	session->header.data_size += DATA_SIZE;
 

tools/perf/util/c++/clang.cpp

@@ -146,8 +146,15 @@ getBPFObjectFromModule(llvm::Module *Module)
 	raw_svector_ostream ostream(*Buffer);
 
 	legacy::PassManager PM;
-	if (TargetMachine->addPassesToEmitFile(PM, ostream,
-					       TargetMachine::CGFT_ObjectFile)) {
+	bool NotAdded;
+#if CLANG_VERSION_MAJOR < 7
+	NotAdded = TargetMachine->addPassesToEmitFile(PM, ostream,
+						      TargetMachine::CGFT_ObjectFile);
+#else
+	NotAdded = TargetMachine->addPassesToEmitFile(PM, ostream, nullptr,
+						      TargetMachine::CGFT_ObjectFile);
+#endif
+	if (NotAdded) {
 		llvm::errs() << "TargetMachine can't emit a file of this type\n";
 		return std::unique_ptr<llvm::SmallVectorImpl<char>>(nullptr);;
 	}

tools/perf/util/header.c

@@ -2129,6 +2129,7 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused)
 	int cpu_nr = ff->ph->env.nr_cpus_avail;
 	u64 size = 0;
 	struct perf_header *ph = ff->ph;
+	bool do_core_id_test = true;
 
 	ph->env.cpu = calloc(cpu_nr, sizeof(*ph->env.cpu));
 	if (!ph->env.cpu)
@@ -2183,6 +2184,13 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused)
 		return 0;
 	}
 
+	/* On s390 the socket_id number is not related to the numbers of cpus.
+	 * The socket_id number might be higher than the numbers of cpus.
+	 * This depends on the configuration.
+	 */
+	if (ph->env.arch && !strncmp(ph->env.arch, "s390", 4))
+		do_core_id_test = false;
+
 	for (i = 0; i < (u32)cpu_nr; i++) {
 		if (do_read_u32(ff, &nr))
 			goto free_cpu;
@@ -2192,7 +2200,7 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused)
 		if (do_read_u32(ff, &nr))
 			goto free_cpu;
 
-		if (nr != (u32)-1 && nr > (u32)cpu_nr) {
+		if (do_core_id_test && nr != (u32)-1 && nr > (u32)cpu_nr) {
 			pr_debug("socket_id number is too big."
 				 "You may need to upgrade the perf tool.\n");
 			goto free_cpu;
@@ -3456,7 +3464,7 @@ int perf_event__process_feature(struct perf_tool *tool,
 		pr_warning("invalid record type %d in pipe-mode\n", type);
 		return 0;
 	}
-	if (feat == HEADER_RESERVED || feat > HEADER_LAST_FEATURE) {
+	if (feat == HEADER_RESERVED || feat >= HEADER_LAST_FEATURE) {
 		pr_warning("invalid record type %d in pipe-mode\n", type);
 		return -1;
 	}

tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c

@@ -366,7 +366,7 @@ static int intel_pt_get_cyc(unsigned int byte, const unsigned char *buf,
 		if (len < offs)
 			return INTEL_PT_NEED_MORE_BYTES;
 		byte = buf[offs++];
-		payload |= (byte >> 1) << shift;
+		payload |= ((uint64_t)byte >> 1) << shift;
 	}
 
 	packet->type = INTEL_PT_CYC;