Merge tag 'perf-core-for-mingo-5.1-20190307' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Pull perf/core changes from Arnaldo Carvalho de Melo:

perf bpf:

  Arnaldo Carvalho de Melo:

  - Automatically add BTF ELF markers to 'perf trace' BPF programs, so that
    tools such as 'bpftool map dump' can pretty print map keys and values.

perf c2c:

  Jiri Olsa:

  - Fix report for empty NUMA node.

perf diff:

  Jin Yao:

  - Support --time, --cpu, --pid and --tid filter options.

perf probe:

  Arnaldo Carvalho de Melo:

  - Clarify error message about not finding kernel modules debuginfo.

perf record:

  Jiri Olsa:

  - Fixup probing for max attr.precise_ip.

perf trace:

  Arnaldo Carvalho de Melo:

  - Add missing %s lost in the 'msg_flags' recvmmsg arg when adding prefix suppression logic.

perf annotate:

  Arnaldo Carvalho de Melo:

  - Calculate the max instruction name, align column to that, removing the
    hardcoded max 6 chars and cope with instructions with names longer than that,
    such as vpmovmskb, vpcmpeqb, etc.

kernel:

  Song Liu:

  - Consider events with attr.bpf_event set as side-band.

  Gustavo A. R. Silva:

  - Mark expected switch fall-through in perf_event_parse_addr_filter().

Libraries:

  Jiri Olsa:

  - Fix leaks and double frees on error paths.

libtraceevent:

  Tony Jones:

  - Fix buffer overflow in arg_eval().

python scripting:

  Tony Jones:

  - More python3 fixes.

Trivial:

  Yang Wei:

  - Remove needless extra semicolon in clang C++ glue code.

Intel PT/BTS:

  Adrian Hunter:

  - Improve auxtrace address filter error message when there is no DSO.

  - Fix divide by zero when TSC is not available.

  - Further improvements to the export to sqlite/posgresql python scripts
    and to the GUI sqlviewer, exporting 'parent_id' so that we have enable
    the creation of call trees.

  Andi Kleen:

  - Generalize function to copy from thread addr space from intel-bts code.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

tools/perf/util/annotate.c

@@ -198,18 +198,18 @@ static void ins__delete(struct ins_operands *ops)
 }
 
 static int ins__raw_scnprintf(struct ins *ins, char *bf, size_t size,
-			      struct ins_operands *ops)
+			      struct ins_operands *ops, int max_ins_name)
 {
-	return scnprintf(bf, size, "%-6s %s", ins->name, ops->raw);
+	return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name, ops->raw);
 }
 
 int ins__scnprintf(struct ins *ins, char *bf, size_t size,
-		  struct ins_operands *ops)
+		   struct ins_operands *ops, int max_ins_name)
 {
 	if (ins->ops->scnprintf)
-		return ins->ops->scnprintf(ins, bf, size, ops);
+		return ins->ops->scnprintf(ins, bf, size, ops, max_ins_name);
 
-	return ins__raw_scnprintf(ins, bf, size, ops);
+	return ins__raw_scnprintf(ins, bf, size, ops, max_ins_name);
 }
 
 bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2)
@@ -273,18 +273,18 @@ indirect_call:
 }
 
 static int call__scnprintf(struct ins *ins, char *bf, size_t size,
-			   struct ins_operands *ops)
+			   struct ins_operands *ops, int max_ins_name)
 {
 	if (ops->target.sym)
-		return scnprintf(bf, size, "%-6s %s", ins->name, ops->target.sym->name);
+		return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name, ops->target.sym->name);
 
 	if (ops->target.addr == 0)
-		return ins__raw_scnprintf(ins, bf, size, ops);
+		return ins__raw_scnprintf(ins, bf, size, ops, max_ins_name);
 
 	if (ops->target.name)
-		return scnprintf(bf, size, "%-6s %s", ins->name, ops->target.name);
+		return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name, ops->target.name);
 
-	return scnprintf(bf, size, "%-6s *%" PRIx64, ins->name, ops->target.addr);
+	return scnprintf(bf, size, "%-*s *%" PRIx64, max_ins_name, ins->name, ops->target.addr);
 }
 
 static struct ins_ops call_ops = {
@@ -388,15 +388,15 @@ static int jump__parse(struct arch *arch, struct ins_operands *ops, struct map_s
 }
 
 static int jump__scnprintf(struct ins *ins, char *bf, size_t size,
-			   struct ins_operands *ops)
+			   struct ins_operands *ops, int max_ins_name)
 {
 	const char *c;
 
 	if (!ops->target.addr || ops->target.offset < 0)
-		return ins__raw_scnprintf(ins, bf, size, ops);
+		return ins__raw_scnprintf(ins, bf, size, ops, max_ins_name);
 
 	if (ops->target.outside && ops->target.sym != NULL)
-		return scnprintf(bf, size, "%-6s %s", ins->name, ops->target.sym->name);
+		return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name, ops->target.sym->name);
 
 	c = strchr(ops->raw, ',');
 	c = validate_comma(c, ops);
@@ -415,7 +415,7 @@ static int jump__scnprintf(struct ins *ins, char *bf, size_t size,
 			c++;
 	}
 
-	return scnprintf(bf, size, "%-6s %.*s%" PRIx64,
+	return scnprintf(bf, size, "%-*s %.*s%" PRIx64, max_ins_name,
 			 ins->name, c ? c - ops->raw : 0, ops->raw,
 			 ops->target.offset);
 }
@@ -483,16 +483,16 @@ out_free_ops:
 }
 
 static int lock__scnprintf(struct ins *ins, char *bf, size_t size,
-			   struct ins_operands *ops)
+			   struct ins_operands *ops, int max_ins_name)
 {
 	int printed;
 
 	if (ops->locked.ins.ops == NULL)
-		return ins__raw_scnprintf(ins, bf, size, ops);
+		return ins__raw_scnprintf(ins, bf, size, ops, max_ins_name);
 
-	printed = scnprintf(bf, size, "%-6s ", ins->name);
+	printed = scnprintf(bf, size, "%-*s ", max_ins_name, ins->name);
 	return printed + ins__scnprintf(&ops->locked.ins, bf + printed,
-					size - printed, ops->locked.ops);
+					size - printed, ops->locked.ops, max_ins_name);
 }
 
 static void lock__delete(struct ins_operands *ops)
@@ -564,9 +564,9 @@ out_free_source:
 }
 
 static int mov__scnprintf(struct ins *ins, char *bf, size_t size,
-			   struct ins_operands *ops)
+			   struct ins_operands *ops, int max_ins_name)
 {
-	return scnprintf(bf, size, "%-6s %s,%s", ins->name,
+	return scnprintf(bf, size, "%-*s %s,%s", max_ins_name, ins->name,
 			 ops->source.name ?: ops->source.raw,
 			 ops->target.name ?: ops->target.raw);
 }
@@ -604,9 +604,9 @@ static int dec__parse(struct arch *arch __maybe_unused, struct ins_operands *ops
 }
 
 static int dec__scnprintf(struct ins *ins, char *bf, size_t size,
-			   struct ins_operands *ops)
+			   struct ins_operands *ops, int max_ins_name)
 {
-	return scnprintf(bf, size, "%-6s %s", ins->name,
+	return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name,
 			 ops->target.name ?: ops->target.raw);
 }
 
@@ -616,9 +616,9 @@ static struct ins_ops dec_ops = {
 };
 
 static int nop__scnprintf(struct ins *ins __maybe_unused, char *bf, size_t size,
-			  struct ins_operands *ops __maybe_unused)
+			  struct ins_operands *ops __maybe_unused, int max_ins_name)
 {
-	return scnprintf(bf, size, "%-6s", "nop");
+	return scnprintf(bf, size, "%-*s", max_ins_name, "nop");
 }
 
 static struct ins_ops nop_ops = {
@@ -1232,12 +1232,12 @@ void disasm_line__free(struct disasm_line *dl)
 	annotation_line__delete(&dl->al);
 }
 
-int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw)
+int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw, int max_ins_name)
 {
 	if (raw || !dl->ins.ops)
-		return scnprintf(bf, size, "%-6s %s", dl->ins.name, dl->ops.raw);
+		return scnprintf(bf, size, "%-*s %s", max_ins_name, dl->ins.name, dl->ops.raw);
 
-	return ins__scnprintf(&dl->ins, bf, size, &dl->ops);
+	return ins__scnprintf(&dl->ins, bf, size, &dl->ops, max_ins_name);
 }
 
 static void annotation_line__add(struct annotation_line *al, struct list_head *head)
@@ -2414,12 +2414,30 @@ static inline int width_jumps(int n)
 	return 1;
 }
 
+static int annotation__max_ins_name(struct annotation *notes)
+{
+	int max_name = 0, len;
+	struct annotation_line *al;
+
+        list_for_each_entry(al, &notes->src->source, node) {
+		if (al->offset == -1)
+			continue;
+
+		len = strlen(disasm_line(al)->ins.name);
+		if (max_name < len)
+			max_name = len;
+	}
+
+	return max_name;
+}
+
 void annotation__init_column_widths(struct annotation *notes, struct symbol *sym)
 {
 	notes->widths.addr = notes->widths.target =
 		notes->widths.min_addr = hex_width(symbol__size(sym));
 	notes->widths.max_addr = hex_width(sym->end);
 	notes->widths.jumps = width_jumps(notes->max_jump_sources);
+	notes->widths.max_ins_name = annotation__max_ins_name(notes);
 }
 
 void annotation__update_column_widths(struct annotation *notes)
@@ -2583,7 +2601,7 @@ call_like:
 		obj__printf(obj, "  ");
 	}
 
-	disasm_line__scnprintf(dl, bf, size, !notes->options->use_offset);
+	disasm_line__scnprintf(dl, bf, size, !notes->options->use_offset, notes->widths.max_ins_name);
 }
 
 static void ipc_coverage_string(char *bf, int size, struct annotation *notes)

tools/perf/util/annotate.h

@@ -59,14 +59,14 @@ struct ins_ops {
 	void (*free)(struct ins_operands *ops);
 	int (*parse)(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms);
 	int (*scnprintf)(struct ins *ins, char *bf, size_t size,
-			 struct ins_operands *ops);
+			 struct ins_operands *ops, int max_ins_name);
 };
 
 bool ins__is_jump(const struct ins *ins);
 bool ins__is_call(const struct ins *ins);
 bool ins__is_ret(const struct ins *ins);
 bool ins__is_lock(const struct ins *ins);
-int ins__scnprintf(struct ins *ins, char *bf, size_t size, struct ins_operands *ops);
+int ins__scnprintf(struct ins *ins, char *bf, size_t size, struct ins_operands *ops, int max_ins_name);
 bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2);
 
 #define ANNOTATION__IPC_WIDTH 6
@@ -219,7 +219,7 @@ int __annotation__scnprintf_samples_period(struct annotation *notes,
 					   struct perf_evsel *evsel,
 					   bool show_freq);
 
-int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw);
+int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw, int max_ins_name);
 size_t disasm__fprintf(struct list_head *head, FILE *fp);
 void symbol__calc_percent(struct symbol *sym, struct perf_evsel *evsel);
 
@@ -289,6 +289,7 @@ struct annotation {
 		u8		target;
 		u8		min_addr;
 		u8		max_addr;
+		u8		max_ins_name;
 	} widths;
 	bool			have_cycles;
 	struct annotated_source *src;

tools/perf/util/auxtrace.c

@@ -1918,7 +1918,8 @@ static struct dso *load_dso(const char *name)
 	if (!map)
 		return NULL;
 
-	map__load(map);
+	if (map__load(map) < 0)
+		pr_err("File '%s' not found or has no symbols.\n", name);
 
 	dso = dso__get(map->dso);
 

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

@@ -156,7 +156,7 @@ getBPFObjectFromModule(llvm::Module *Module)
 #endif
 	if (NotAdded) {
 		llvm::errs() << "TargetMachine can't emit a file of this type\n";
-		return std::unique_ptr<llvm::SmallVectorImpl<char>>(nullptr);;
+		return std::unique_ptr<llvm::SmallVectorImpl<char>>(nullptr);
 	}
 	PM.run(*Module);
 

tools/perf/util/data.c

@@ -237,7 +237,7 @@ static int open_file(struct perf_data *data)
 	     open_file_read(data) : open_file_write(data);
 
 	if (fd < 0) {
-		free(data->file.path);
+		zfree(&data->file.path);
 		return -1;
 	}
 
@@ -270,7 +270,7 @@ int perf_data__open(struct perf_data *data)
 
 void perf_data__close(struct perf_data *data)
 {
-	free(data->file.path);
+	zfree(&data->file.path);
 	close(data->file.fd);
 }
 

tools/perf/util/db-export.c

@@ -510,18 +510,23 @@ int db_export__call_path(struct db_export *dbe, struct call_path *cp)
 	return 0;
 }
 
-int db_export__call_return(struct db_export *dbe, struct call_return *cr)
+int db_export__call_return(struct db_export *dbe, struct call_return *cr,
+			   u64 *parent_db_id)
 {
 	int err;
 
-	if (cr->db_id)
-		return 0;
-
 	err = db_export__call_path(dbe, cr->cp);
 	if (err)
 		return err;
 
-	cr->db_id = ++dbe->call_return_last_db_id;
+	if (!cr->db_id)
+		cr->db_id = ++dbe->call_return_last_db_id;
+
+	if (parent_db_id) {
+		if (!*parent_db_id)
+			*parent_db_id = ++dbe->call_return_last_db_id;
+		cr->parent_db_id = *parent_db_id;
+	}
 
 	if (dbe->export_call_return)
 		return dbe->export_call_return(dbe, cr);

tools/perf/util/db-export.h

@@ -104,6 +104,7 @@ int db_export__sample(struct db_export *dbe, union perf_event *event,
 int db_export__branch_types(struct db_export *dbe);
 
 int db_export__call_path(struct db_export *dbe, struct call_path *cp);
-int db_export__call_return(struct db_export *dbe, struct call_return *cr);
+int db_export__call_return(struct db_export *dbe, struct call_return *cr,
+			   u64 *parent_db_id);
 
 #endif

tools/perf/util/evlist.c

@@ -230,18 +230,33 @@ void perf_evlist__set_leader(struct perf_evlist *evlist)
 	}
 }
 
-void perf_event_attr__set_max_precise_ip(struct perf_event_attr *attr)
+void perf_event_attr__set_max_precise_ip(struct perf_event_attr *pattr)
 {
-	attr->precise_ip = 3;
+	struct perf_event_attr attr = {
+		.type		= PERF_TYPE_HARDWARE,
+		.config		= PERF_COUNT_HW_CPU_CYCLES,
+		.exclude_kernel	= 1,
+		.precise_ip	= 3,
+	};
 
-	while (attr->precise_ip != 0) {
-		int fd = sys_perf_event_open(attr, 0, -1, -1, 0);
+	event_attr_init(&attr);
+
+	/*
+	 * Unnamed union member, not supported as struct member named
+	 * initializer in older compilers such as gcc 4.4.7
+	 */
+	attr.sample_period = 1;
+
+	while (attr.precise_ip != 0) {
+		int fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
 		if (fd != -1) {
 			close(fd);
 			break;
 		}
-		--attr->precise_ip;
+		--attr.precise_ip;
 	}
+
+	pattr->precise_ip = attr.precise_ip;
 }
 
 int __perf_evlist__add_default(struct perf_evlist *evlist, bool precise)

tools/perf/util/evsel.c

@@ -294,20 +294,12 @@ struct perf_evsel *perf_evsel__new_cycles(bool precise)
 
 	if (!precise)
 		goto new_event;
-	/*
-	 * Unnamed union member, not supported as struct member named
-	 * initializer in older compilers such as gcc 4.4.7
-	 *
-	 * Just for probing the precise_ip:
-	 */
-	attr.sample_period = 1;
 
 	perf_event_attr__set_max_precise_ip(&attr);
 	/*
 	 * Now let the usual logic to set up the perf_event_attr defaults
 	 * to kick in when we return and before perf_evsel__open() is called.
 	 */
-	attr.sample_period = 0;
 new_event:
 	evsel = perf_evsel__new(&attr);
 	if (evsel == NULL)

tools/perf/util/hist.c

@@ -396,11 +396,8 @@ static int hist_entry__init(struct hist_entry *he,
 		 * adding new entries.  So we need to save a copy.
 		 */
 		he->branch_info = malloc(sizeof(*he->branch_info));
-		if (he->branch_info == NULL) {
-			map__zput(he->ms.map);
-			free(he->stat_acc);
-			return -ENOMEM;
-		}
+		if (he->branch_info == NULL)
+			goto err;
 
 		memcpy(he->branch_info, template->branch_info,
 		       sizeof(*he->branch_info));
@@ -419,22 +416,16 @@ static int hist_entry__init(struct hist_entry *he,
 
 	if (he->raw_data) {
 		he->raw_data = memdup(he->raw_data, he->raw_size);
-
-		if (he->raw_data == NULL) {
-			map__put(he->ms.map);
-			if (he->branch_info) {
-				map__put(he->branch_info->from.map);
-				map__put(he->branch_info->to.map);
-				free(he->branch_info);
-			}
-			if (he->mem_info) {
-				map__put(he->mem_info->iaddr.map);
-				map__put(he->mem_info->daddr.map);
-			}
-			free(he->stat_acc);
-			return -ENOMEM;
-		}
+		if (he->raw_data == NULL)
+			goto err_infos;
 	}
+
+	if (he->srcline) {
+		he->srcline = strdup(he->srcline);
+		if (he->srcline == NULL)
+			goto err_rawdata;
+	}
+
 	INIT_LIST_HEAD(&he->pairs.node);
 	thread__get(he->thread);
 	he->hroot_in  = RB_ROOT_CACHED;
@@ -444,6 +435,24 @@ static int hist_entry__init(struct hist_entry *he,
 		he->leaf = true;
 
 	return 0;
+
+err_rawdata:
+	free(he->raw_data);
+
+err_infos:
+	if (he->branch_info) {
+		map__put(he->branch_info->from.map);
+		map__put(he->branch_info->to.map);
+		free(he->branch_info);
+	}
+	if (he->mem_info) {
+		map__put(he->mem_info->iaddr.map);
+		map__put(he->mem_info->daddr.map);
+	}
+err:
+	map__zput(he->ms.map);
+	free(he->stat_acc);
+	return -ENOMEM;
 }
 
 static void *hist_entry__zalloc(size_t size)
@@ -606,7 +615,7 @@ __hists__add_entry(struct hists *hists,
 			.map	= al->map,
 			.sym	= al->sym,
 		},
-		.srcline = al->srcline ? strdup(al->srcline) : NULL,
+		.srcline = (char *) al->srcline,
 		.socket	 = al->socket,
 		.cpu	 = al->cpu,
 		.cpumode = al->cpumode,
@@ -963,7 +972,7 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
 			.map = al->map,
 			.sym = al->sym,
 		},
-		.srcline = al->srcline ? strdup(al->srcline) : NULL,
+		.srcline = (char *) al->srcline,
 		.parent = iter->parent,
 		.raw_data = sample->raw_data,
 		.raw_size = sample->raw_size,

tools/perf/util/intel-bts.c

@@ -328,35 +328,19 @@ static int intel_bts_get_next_insn(struct intel_bts_queue *btsq, u64 ip)
 {
 	struct machine *machine = btsq->bts->machine;
 	struct thread *thread;
-	struct addr_location al;
 	unsigned char buf[INTEL_PT_INSN_BUF_SZ];
 	ssize_t len;
-	int x86_64;
-	uint8_t cpumode;
+	bool x86_64;
 	int err = -1;
 
-	if (machine__kernel_ip(machine, ip))
-		cpumode = PERF_RECORD_MISC_KERNEL;
-	else
-		cpumode = PERF_RECORD_MISC_USER;
-
 	thread = machine__find_thread(machine, -1, btsq->tid);
 	if (!thread)
 		return -1;
 
-	if (!thread__find_map(thread, cpumode, ip, &al) || !al.map->dso)
-		goto out_put;
-
-	len = dso__data_read_addr(al.map->dso, al.map, machine, ip, buf,
-				  INTEL_PT_INSN_BUF_SZ);
+	len = thread__memcpy(thread, machine, buf, ip, INTEL_PT_INSN_BUF_SZ, &x86_64);
 	if (len <= 0)
 		goto out_put;
 
-	/* Load maps to ensure dso->is_64_bit has been updated */
-	map__load(al.map);
-
-	x86_64 = al.map->dso->is_64_bit;
-
 	if (intel_pt_get_insn(buf, len, x86_64, &btsq->intel_pt_insn))
 		goto out_put;
 

tools/perf/util/intel-pt.c

@@ -2531,6 +2531,8 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
 	}
 
 	pt->timeless_decoding = intel_pt_timeless_decoding(pt);
+	if (pt->timeless_decoding && !pt->tc.time_mult)
+		pt->tc.time_mult = 1;
 	pt->have_tsc = intel_pt_have_tsc(pt);
 	pt->sampling_mode = false;
 	pt->est_tsc = !pt->timeless_decoding;

tools/perf/util/pmu.c

@@ -752,6 +752,19 @@ perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused)
 	return NULL;
 }
 
+static int pmu_max_precise(const char *name)
+{
+	char path[PATH_MAX];
+	int max_precise = -1;
+
+	scnprintf(path, PATH_MAX,
+		 "bus/event_source/devices/%s/caps/max_precise",
+		 name);
+
+	sysfs__read_int(path, &max_precise);
+	return max_precise;
+}
+
 static struct perf_pmu *pmu_lookup(const char *name)
 {
 	struct perf_pmu *pmu;
@@ -784,6 +797,7 @@ static struct perf_pmu *pmu_lookup(const char *name)
 	pmu->name = strdup(name);
 	pmu->type = type;
 	pmu->is_uncore = pmu_is_uncore(name);
+	pmu->max_precise = pmu_max_precise(name);
 	pmu_add_cpu_aliases(&aliases, pmu);
 
 	INIT_LIST_HEAD(&pmu->format);

tools/perf/util/pmu.h

@@ -26,6 +26,7 @@ struct perf_pmu {
 	__u32 type;
 	bool selectable;
 	bool is_uncore;
+	int max_precise;
 	struct perf_event_attr *default_config;
 	struct cpu_map *cpus;
 	struct list_head format;  /* HEAD struct perf_pmu_format -> list */

tools/perf/util/probe-event.c

@@ -472,9 +472,12 @@ static struct debuginfo *open_debuginfo(const char *module, struct nsinfo *nsi,
 					strcpy(reason, "(unknown)");
 			} else
 				dso__strerror_load(dso, reason, STRERR_BUFSIZE);
-			if (!silent)
-				pr_err("Failed to find the path for %s: %s\n",
-					module ?: "kernel", reason);
+			if (!silent) {
+				if (module)
+					pr_err("Module %s is not loaded, please specify its full path name.\n", module);
+				else
+					pr_err("Failed to find the path for the kernel: %s\n", reason);
+			}
 			return NULL;
 		}
 		path = dso->long_name;

tools/perf/util/scripting-engines/trace-event-python.c

@@ -1173,7 +1173,7 @@ static int python_export_call_return(struct db_export *dbe,
 	u64 comm_db_id = cr->comm ? cr->comm->db_id : 0;
 	PyObject *t;
 
-	t = tuple_new(11);
+	t = tuple_new(12);
 
 	tuple_set_u64(t, 0, cr->db_id);
 	tuple_set_u64(t, 1, cr->thread->db_id);
@@ -1186,6 +1186,7 @@ static int python_export_call_return(struct db_export *dbe,
 	tuple_set_u64(t, 8, cr->return_ref);
 	tuple_set_u64(t, 9, cr->cp->parent->db_id);
 	tuple_set_s32(t, 10, cr->flags);
+	tuple_set_u64(t, 11, cr->parent_db_id);
 
 	call_object(tables->call_return_handler, t, "call_return_table");
 
@@ -1194,11 +1195,12 @@ static int python_export_call_return(struct db_export *dbe,
 	return 0;
 }
 
-static int python_process_call_return(struct call_return *cr, void *data)
+static int python_process_call_return(struct call_return *cr, u64 *parent_db_id,
+				      void *data)
 {
 	struct db_export *dbe = data;
 
-	return db_export__call_return(dbe, cr);
+	return db_export__call_return(dbe, cr, parent_db_id);
 }
 
 static void python_process_general_event(struct perf_sample *sample,

tools/perf/util/session.c

@@ -140,7 +140,7 @@ struct perf_session *perf_session__new(struct perf_data *data,
 
 		if (perf_data__is_read(data)) {
 			if (perf_session__open(session) < 0)
-				goto out_close;
+				goto out_delete;
 
 			/*
 			 * set session attributes that are present in perf.data
@@ -181,8 +181,6 @@ struct perf_session *perf_session__new(struct perf_data *data,
 
 	return session;
 
- out_close:
-	perf_data__close(data);
  out_delete:
 	perf_session__delete(session);
  out:

tools/perf/util/thread-stack.c

@@ -49,6 +49,7 @@ enum retpoline_state_t {
  * @timestamp: timestamp (if known)
  * @ref: external reference (e.g. db_id of sample)
  * @branch_count: the branch count when the entry was created
+ * @db_id: id used for db-export
  * @cp: call path
  * @no_call: a 'call' was not seen
  * @trace_end: a 'call' but trace ended
@@ -59,6 +60,7 @@ struct thread_stack_entry {
 	u64 timestamp;
 	u64 ref;
 	u64 branch_count;
+	u64 db_id;
 	struct call_path *cp;
 	bool no_call;
 	bool trace_end;
@@ -280,12 +282,14 @@ static int thread_stack__call_return(struct thread *thread,
 		.comm = ts->comm,
 		.db_id = 0,
 	};
+	u64 *parent_db_id;
 
 	tse = &ts->stack[idx];
 	cr.cp = tse->cp;
 	cr.call_time = tse->timestamp;
 	cr.return_time = timestamp;
 	cr.branch_count = ts->branch_count - tse->branch_count;
+	cr.db_id = tse->db_id;
 	cr.call_ref = tse->ref;
 	cr.return_ref = ref;
 	if (tse->no_call)
@@ -295,7 +299,14 @@ static int thread_stack__call_return(struct thread *thread,
 	if (tse->non_call)
 		cr.flags |= CALL_RETURN_NON_CALL;
 
-	return crp->process(&cr, crp->data);
+	/*
+	 * The parent db_id must be assigned before exporting the child. Note
+	 * it is not possible to export the parent first because its information
+	 * is not yet complete because its 'return' has not yet been processed.
+	 */
+	parent_db_id = idx ? &(tse - 1)->db_id : NULL;
+
+	return crp->process(&cr, parent_db_id, crp->data);
 }
 
 static int __thread_stack__flush(struct thread *thread, struct thread_stack *ts)
@@ -484,7 +495,7 @@ void thread_stack__sample(struct thread *thread, int cpu,
 }
 
 struct call_return_processor *
-call_return_processor__new(int (*process)(struct call_return *cr, void *data),
+call_return_processor__new(int (*process)(struct call_return *cr, u64 *parent_db_id, void *data),
 			   void *data)
 {
 	struct call_return_processor *crp;
@@ -537,6 +548,7 @@ static int thread_stack__push_cp(struct thread_stack *ts, u64 ret_addr,
 	tse->no_call = no_call;
 	tse->trace_end = trace_end;
 	tse->non_call = false;
+	tse->db_id = 0;
 
 	return 0;
 }

tools/perf/util/thread-stack.h

@@ -55,6 +55,7 @@ enum {
  * @call_ref: external reference to 'call' sample (e.g. db_id)
  * @return_ref:  external reference to 'return' sample (e.g. db_id)
  * @db_id: id used for db-export
+ * @parent_db_id: id of parent call used for db-export
  * @flags: Call/Return flags
  */
 struct call_return {
@@ -67,6 +68,7 @@ struct call_return {
 	u64 call_ref;
 	u64 return_ref;
 	u64 db_id;
+	u64 parent_db_id;
 	u32 flags;
 };
 
@@ -79,7 +81,7 @@ struct call_return {
  */
 struct call_return_processor {
 	struct call_path_root *cpr;
-	int (*process)(struct call_return *cr, void *data);
+	int (*process)(struct call_return *cr, u64 *parent_db_id, void *data);
 	void *data;
 };
 
@@ -93,7 +95,7 @@ void thread_stack__free(struct thread *thread);
 size_t thread_stack__depth(struct thread *thread, int cpu);
 
 struct call_return_processor *
-call_return_processor__new(int (*process)(struct call_return *cr, void *data),
+call_return_processor__new(int (*process)(struct call_return *cr, u64 *parent_db_id, void *data),
 			   void *data);
 void call_return_processor__free(struct call_return_processor *crp);
 int thread_stack__process(struct thread *thread, struct comm *comm,

tools/perf/util/thread.c

@@ -12,6 +12,7 @@
 #include "debug.h"
 #include "namespaces.h"
 #include "comm.h"
+#include "map.h"
 #include "symbol.h"
 #include "unwind.h"
 
@@ -393,3 +394,25 @@ struct thread *thread__main_thread(struct machine *machine, struct thread *threa
 
 	return machine__find_thread(machine, thread->pid_, thread->pid_);
 }
+
+int thread__memcpy(struct thread *thread, struct machine *machine,
+		   void *buf, u64 ip, int len, bool *is64bit)
+{
+       u8 cpumode = PERF_RECORD_MISC_USER;
+       struct addr_location al;
+       long offset;
+
+       if (machine__kernel_ip(machine, ip))
+               cpumode = PERF_RECORD_MISC_KERNEL;
+
+       if (!thread__find_map(thread, cpumode, ip, &al) || !al.map->dso ||
+	   al.map->dso->data.status == DSO_DATA_STATUS_ERROR ||
+	   map__load(al.map) < 0)
+               return -1;
+
+       offset = al.map->map_ip(al.map, ip);
+       if (is64bit)
+               *is64bit = al.map->dso->is_64_bit;
+
+       return dso__data_read_offset(al.map->dso, machine, offset, buf, len);
+}

tools/perf/util/thread.h

@@ -113,6 +113,9 @@ struct symbol *thread__find_symbol_fb(struct thread *thread, u8 cpumode,
 void thread__find_cpumode_addr_location(struct thread *thread, u64 addr,
 					struct addr_location *al);
 
+int thread__memcpy(struct thread *thread, struct machine *machine,
+		   void *buf, u64 ip, int len, bool *is64bit);
+
 static inline void *thread__priv(struct thread *thread)
 {
 	return thread->priv;

tools/perf/util/time-utils.c

@@ -11,6 +11,8 @@
 #include "perf.h"
 #include "debug.h"
 #include "time-utils.h"
+#include "session.h"
+#include "evlist.h"
 
 int parse_nsec_time(const char *str, u64 *ptime)
 {
@@ -374,7 +376,7 @@ bool perf_time__ranges_skip_sample(struct perf_time_interval *ptime_buf,
 	struct perf_time_interval *ptime;
 	int i;
 
-	if ((timestamp == 0) || (num == 0))
+	if ((!ptime_buf) || (timestamp == 0) || (num == 0))
 		return false;
 
 	if (num == 1)
@@ -396,6 +398,53 @@ bool perf_time__ranges_skip_sample(struct perf_time_interval *ptime_buf,
 	return (i == num) ? true : false;
 }
 
+int perf_time__parse_for_ranges(const char *time_str,
+				struct perf_session *session,
+				struct perf_time_interval **ranges,
+				int *range_size, int *range_num)
+{
+	struct perf_time_interval *ptime_range;
+	int size, num, ret;
+
+	ptime_range = perf_time__range_alloc(time_str, &size);
+	if (!ptime_range)
+		return -ENOMEM;
+
+	if (perf_time__parse_str(ptime_range, time_str) != 0) {
+		if (session->evlist->first_sample_time == 0 &&
+		    session->evlist->last_sample_time == 0) {
+			pr_err("HINT: no first/last sample time found in perf data.\n"
+			       "Please use latest perf binary to execute 'perf record'\n"
+			       "(if '--buildid-all' is enabled, please set '--timestamp-boundary').\n");
+			ret = -EINVAL;
+			goto error;
+		}
+
+		num = perf_time__percent_parse_str(
+				ptime_range, size,
+				time_str,
+				session->evlist->first_sample_time,
+				session->evlist->last_sample_time);
+
+		if (num < 0) {
+			pr_err("Invalid time string\n");
+			ret = -EINVAL;
+			goto error;
+		}
+	} else {
+		num = 1;
+	}
+
+	*range_size = size;
+	*range_num = num;
+	*ranges = ptime_range;
+	return 0;
+
+error:
+	free(ptime_range);
+	return ret;
+}
+
 int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz)
 {
 	u64  sec = timestamp / NSEC_PER_SEC;

tools/perf/util/time-utils.h

@@ -23,6 +23,12 @@ bool perf_time__skip_sample(struct perf_time_interval *ptime, u64 timestamp);
 bool perf_time__ranges_skip_sample(struct perf_time_interval *ptime_buf,
 				   int num, u64 timestamp);
 
+struct perf_session;
+
+int perf_time__parse_for_ranges(const char *str, struct perf_session *session,
+				struct perf_time_interval **ranges,
+				int *range_size, int *range_num);
+
 int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz);
 
 int fetch_current_timestamp(char *buf, size_t sz);