perf/core improvements and fixes

index d73ef8bb08c7..9892b0f0bec4 100644
@@ -145,7 +145,7 @@ static Dwarf_Frame *get_dwarf_frame(Dwfl_Module *mod, Dwarf_Addr pc)
  *		yet used)
  *	-1 in case of errors
  */
-static int check_return_addr(const char *exec_file, Dwarf_Addr pc)
+static int check_return_addr(struct dso *dso, Dwarf_Addr pc)
 {
 	int		rc = -1;
 	Dwfl		*dwfl;

@@ -156,15 +156,27 @@ static int check_return_addr(const char *exec_file, Dwarf_Addr pc)
 	Dwarf_Addr	end = pc;
 	bool		signalp;
 
-	dwfl = dwfl_begin(&offline_callbacks);
-	if (!dwfl) {
-		pr_debug("dwfl_begin() failed: %s\n", dwarf_errmsg(-1));
-		return -1;
-	}
+	dwfl = dso->dwfl;
 
-	if (dwfl_report_offline(dwfl, "",  exec_file, -1) == NULL) {
-		pr_debug("dwfl_report_offline() failed %s\n", dwarf_errmsg(-1));
-		goto out;
+	if (!dwfl) {
+		dwfl = dwfl_begin(&offline_callbacks);
+		if (!dwfl) {
+			pr_debug("dwfl_begin() failed: %s\n", dwarf_errmsg(-1));
+			return -1;
+		}
+
+		if (dwfl_report_offline(dwfl, "", dso->long_name, -1) == NULL) {
+			pr_debug("dwfl_report_offline() failed %s\n",
+						dwarf_errmsg(-1));
+			/*
+			 * We normally cache the DWARF debug info and never
+			 * call dwfl_end(). But to prevent fd leak, free in
+			 * case of error.
+			 */
+			dwfl_end(dwfl);
+			goto out;
+		}
+		dso->dwfl = dwfl;
 	}
 
 	mod = dwfl_addrmodule(dwfl, pc);

@@ -194,7 +206,6 @@ static int check_return_addr(const char *exec_file, Dwarf_Addr pc)
 	rc = check_return_reg(ra_regno, frame);
 
 out:
-	dwfl_end(dwfl);
 	return rc;
 }
 

@@ -246,7 +257,7 @@ int arch_skip_callchain_idx(struct machine *machine, struct thread *thread,
 		return skip_slot;
 	}
 
-	rc = check_return_addr(dso->long_name, ip);
+	rc = check_return_addr(dso, ip);
 
 	pr_debug("DSO %s, nr %" PRIx64 ", ip 0x%" PRIx64 "rc %d\n",
 				dso->long_name, chain->nr, ip, rc);

index acb651acc7fd..3c9b391493f9 100644
@@ -127,6 +127,7 @@ struct dso {
 	const char	 *long_name;
 	u16		 long_name_len;
 	u16		 short_name_len;
+	void		*dwfl;			/* DWARF debug info */
 
 	/* dso data file */
 	struct {

index 34fc7c8672e4..c70b3ff7b289 100644
@@ -21,7 +21,7 @@ static void dsos__init(struct dsos *dsos)
 
 int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 {
-	map_groups__init(&machine->kmaps);
+	map_groups__init(&machine->kmaps, machine);
 	RB_CLEAR_NODE(&machine->rb_node);
 	dsos__init(&machine->user_dsos);
 	dsos__init(&machine->kernel_dsos);

@@ -32,7 +32,6 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 
 	machine->vdso_info = NULL;
 
-	machine->kmaps.machine = machine;
 	machine->pid = pid;
 
 	machine->symbol_filter = NULL;

@@ -319,7 +318,7 @@ static void machine__update_thread_pid(struct machine *machine,
 		goto out_err;
 
 	if (!leader->mg)
-		leader->mg = map_groups__new();
+		leader->mg = map_groups__new(machine);
 
 	if (!leader->mg)
 		goto out_err;

index 2137c4596ec7..040a785c857b 100644
@@ -413,14 +413,14 @@ u64 map__objdump_2mem(struct map *map, u64 ip)
 	return ip + map->reloc;
 }
 
-void map_groups__init(struct map_groups *mg)
+void map_groups__init(struct map_groups *mg, struct machine *machine)
 {
 	int i;
 	for (i = 0; i < MAP__NR_TYPES; ++i) {
 		mg->maps[i] = RB_ROOT;
 		INIT_LIST_HEAD(&mg->removed_maps[i]);
 	}
-	mg->machine = NULL;
+	mg->machine = machine;
 	mg->refcnt = 1;
 }
 

@@ -471,12 +471,12 @@ bool map_groups__empty(struct map_groups *mg)
 	return true;
 }
 
-struct map_groups *map_groups__new(void)
+struct map_groups *map_groups__new(struct machine *machine)
 {
 	struct map_groups *mg = malloc(sizeof(*mg));
 
 	if (mg != NULL)
-		map_groups__init(mg);
+		map_groups__init(mg, machine);
 
 	return mg;
 }

index 2f83954af050..6951a9d42339 100644
@@ -64,7 +64,7 @@ struct map_groups {
 	int		 refcnt;
 };
 
-struct map_groups *map_groups__new(void);
+struct map_groups *map_groups__new(struct machine *machine);
 void map_groups__delete(struct map_groups *mg);
 bool map_groups__empty(struct map_groups *mg);
 

@@ -150,7 +150,7 @@ void maps__remove(struct rb_root *maps, struct map *map);
 struct map *maps__find(struct rb_root *maps, u64 addr);
 struct map *maps__first(struct rb_root *maps);
 struct map *maps__next(struct map *map);
-void map_groups__init(struct map_groups *mg);
+void map_groups__init(struct map_groups *mg, struct machine *machine);
 void map_groups__exit(struct map_groups *mg);
 int map_groups__clone(struct map_groups *mg,
 		      struct map_groups *parent, enum map_type type);

index 2b7b2d91c016..26386c9465a1 100644
@@ -15,7 +15,7 @@ int thread__init_map_groups(struct thread *thread, struct machine *machine)
 	pid_t pid = thread->pid_;
 
 	if (pid == thread->tid || pid == -1) {
-		thread->mg = map_groups__new();
+		thread->mg = map_groups__new(machine);
 	} else {
 		leader = machine__findnew_thread(machine, pid, pid);
 		if (leader)

index 9892b0f0bec4..3bb50eac5542 100644
@@ -232,8 +232,7 @@ out:
  *	index:	of callchain entry that needs to be ignored (if any)
  *	-1	if no entry needs to be ignored or in case of errors
  */
-int arch_skip_callchain_idx(struct machine *machine, struct thread *thread,
-				struct ip_callchain *chain)
+int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain)
 {
 	struct addr_location al;
 	struct dso *dso = NULL;

@@ -246,7 +245,7 @@ int arch_skip_callchain_idx(struct machine *machine, struct thread *thread,
 
 	ip = chain->ips[2];
 
-	thread__find_addr_location(thread, machine, PERF_RECORD_MISC_USER,
+	thread__find_addr_location(thread, PERF_RECORD_MISC_USER,
 			MAP__FUNCTION, ip, &al);
 
 	if (al.map)

index de99ca1bb942..06f1758951f1 100644
@@ -217,8 +217,7 @@ static int perf_event__inject_buildid(struct perf_tool *tool,
 		goto repipe;
 	}
 
-	thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
-			      sample->ip, &al);
+	thread__find_addr_map(thread, cpumode, MAP__FUNCTION, sample->ip, &al);
 
 	if (al.map != NULL) {
 		if (!al.map->dso->hit) {

index 9708a1290571..b35517f2ceb5 100644
@@ -379,7 +379,6 @@ static void print_sample_start(struct perf_sample *sample,
 
 static void print_sample_addr(union perf_event *event,
 			  struct perf_sample *sample,
-			  struct machine *machine,
 			  struct thread *thread,
 			  struct perf_event_attr *attr)
 {

@@ -390,7 +389,7 @@ static void print_sample_addr(union perf_event *event,
 	if (!sample_addr_correlates_sym(attr))
 		return;
 
-	perf_event__preprocess_sample_addr(event, sample, machine, thread, &al);
+	perf_event__preprocess_sample_addr(event, sample, thread, &al);
 
 	if (PRINT_FIELD(SYM)) {
 		printf(" ");

@@ -438,7 +437,7 @@ static void print_sample_bts(union perf_event *event,
 	    ((evsel->attr.sample_type & PERF_SAMPLE_ADDR) &&
 	     !output[attr->type].user_set)) {
 		printf(" => ");
-		print_sample_addr(event, sample, al->machine, thread, attr);
+		print_sample_addr(event, sample, thread, attr);
 	}
 
 	if (print_srcline_last)

@@ -475,7 +474,7 @@ static void process_event(union perf_event *event, struct perf_sample *sample,
 		event_format__print(evsel->tp_format, sample->cpu,
 				    sample->raw_data, sample->raw_size);
 	if (PRINT_FIELD(ADDR))
-		print_sample_addr(event, sample, al->machine, thread, attr);
+		print_sample_addr(event, sample, thread, attr);
 
 	if (PRINT_FIELD(IP)) {
 		if (!symbol_conf.use_callchain)

index 35b425b6293f..f5fb256d90d5 100644
@@ -528,7 +528,7 @@ static const char *cat_backtrace(union perf_event *event,
 		}
 
 		tal.filtered = 0;
-		thread__find_addr_location(al.thread, machine, cpumode,
+		thread__find_addr_location(al.thread, cpumode,
 					   MAP__FUNCTION, ip, &tal);
 
 		if (tal.sym)

index fb126459b134..83a4835c8118 100644
@@ -1846,7 +1846,7 @@ static int trace__pgfault(struct trace *trace,
 	if (trace->summary_only)
 		return 0;
 
-	thread__find_addr_location(thread, trace->host, cpumode, MAP__FUNCTION,
+	thread__find_addr_location(thread, cpumode, MAP__FUNCTION,
 			      sample->ip, &al);
 
 	trace__fprintf_entry_head(trace, thread, 0, sample->time, trace->output);

@@ -1859,11 +1859,11 @@ static int trace__pgfault(struct trace *trace,
 
 	fprintf(trace->output, "] => ");
 
-	thread__find_addr_location(thread, trace->host, cpumode, MAP__VARIABLE,
+	thread__find_addr_location(thread, cpumode, MAP__VARIABLE,
 				   sample->addr, &al);
 
 	if (!al.map) {
-		thread__find_addr_location(thread, trace->host, cpumode,
+		thread__find_addr_location(thread, cpumode,
 					   MAP__FUNCTION, sample->addr, &al);
 
 		if (al.map)

index 67f2d6323558..144a41236456 100644
@@ -145,8 +145,7 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode,
 
 	pr_debug("Reading object code for memory address: %#"PRIx64"\n", addr);
 
-	thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION, addr,
-			      &al);
+	thread__find_addr_map(thread, cpumode, MAP__FUNCTION, addr, &al);
 	if (!al.map || !al.map->dso) {
 		pr_debug("thread__find_addr_map failed\n");
 		return -1;

index 4a456fef66ca..2113f1c8611f 100644
@@ -187,7 +187,7 @@ static int mmap_events(synth_cb synth)
 
 		pr_debug("looking for map %p\n", td->map);
 
-		thread__find_addr_map(thread, machine,
+		thread__find_addr_map(thread,
 				      PERF_RECORD_MISC_USER, MAP__FUNCTION,
 				      (unsigned long) (td->map + 1), &al);
 

index a904a4cfe7d3..2e7c68e39330 100644
@@ -33,8 +33,7 @@ int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused,
 		return -1;
 	}
 
-	thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
-			      sample->ip, &al);
+	thread__find_addr_map(thread, cpumode, MAP__FUNCTION, sample->ip, &al);
 
 	if (al.map != NULL)
 		al.map->dso->hit = 1;

index 94cfefddf4db..3caccc2c173c 100644
@@ -184,11 +184,9 @@ static inline void callchain_cursor_snapshot(struct callchain_cursor *dest,
 }
 
 #ifdef HAVE_SKIP_CALLCHAIN_IDX
-extern int arch_skip_callchain_idx(struct machine *machine,
-			struct thread *thread, struct ip_callchain *chain);
+extern int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain);
 #else
-static inline int arch_skip_callchain_idx(struct machine *machine __maybe_unused,
-			struct thread *thread __maybe_unused,
+static inline int arch_skip_callchain_idx(struct thread *thread __maybe_unused,
 			struct ip_callchain *chain __maybe_unused)
 {
 	return -1;

index 4af6b279e34a..e00a29fb099f 100644
@@ -730,12 +730,12 @@ int perf_event__process(struct perf_tool *tool __maybe_unused,
 	return machine__process_event(machine, event, sample);
 }
 
-void thread__find_addr_map(struct thread *thread,
-			   struct machine *machine, u8 cpumode,
+void thread__find_addr_map(struct thread *thread, u8 cpumode,
 			   enum map_type type, u64 addr,
 			   struct addr_location *al)
 {
 	struct map_groups *mg = thread->mg;
+	struct machine *machine = mg->machine;
 	bool load_map = false;
 
 	al->machine = machine;

@@ -806,14 +806,14 @@ try_again:
 	}
 }
 
-void thread__find_addr_location(struct thread *thread, struct machine *machine,
+void thread__find_addr_location(struct thread *thread,
 				u8 cpumode, enum map_type type, u64 addr,
 				struct addr_location *al)
 {
-	thread__find_addr_map(thread, machine, cpumode, type, addr, al);
+	thread__find_addr_map(thread, cpumode, type, addr, al);
 	if (al->map != NULL)
 		al->sym = map__find_symbol(al->map, al->addr,
-					   machine->symbol_filter);
+					   thread->mg->machine->symbol_filter);
 	else
 		al->sym = NULL;
 }

@@ -842,8 +842,7 @@ int perf_event__preprocess_sample(const union perf_event *event,
 	    machine->vmlinux_maps[MAP__FUNCTION] == NULL)
 		machine__create_kernel_maps(machine);
 
-	thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
-			      sample->ip, al);
+	thread__find_addr_map(thread, cpumode, MAP__FUNCTION, sample->ip, al);
 	dump_printf(" ...... dso: %s\n",
 		    al->map ? al->map->dso->long_name :
 			al->level == 'H' ? "[hypervisor]" : "<not found>");

@@ -902,16 +901,14 @@ bool sample_addr_correlates_sym(struct perf_event_attr *attr)
 
 void perf_event__preprocess_sample_addr(union perf_event *event,
 					struct perf_sample *sample,
-					struct machine *machine,
 					struct thread *thread,
 					struct addr_location *al)
 {
 	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
-	thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
-			      sample->addr, al);
+	thread__find_addr_map(thread, cpumode, MAP__FUNCTION, sample->addr, al);
 	if (!al->map)
-		thread__find_addr_map(thread, machine, cpumode, MAP__VARIABLE,
+		thread__find_addr_map(thread, cpumode, MAP__VARIABLE,
 				      sample->addr, al);
 
 	al->cpu = sample->cpu;

index 5699e7e2a790..5f0e0b89e130 100644
@@ -322,7 +322,6 @@ bool is_bts_event(struct perf_event_attr *attr);
 bool sample_addr_correlates_sym(struct perf_event_attr *attr);
 void perf_event__preprocess_sample_addr(union perf_event *event,
 					struct perf_sample *sample,
-					struct machine *machine,
 					struct thread *thread,
 					struct addr_location *al);
 

index c70b3ff7b289..08e63fdbd14f 100644
@@ -1289,7 +1289,7 @@ static bool symbol__match_regex(struct symbol *sym, regex_t *regex)
 	return 0;
 }
 
-static void ip__resolve_ams(struct machine *machine, struct thread *thread,
+static void ip__resolve_ams(struct thread *thread,
 			    struct addr_map_symbol *ams,
 			    u64 ip)
 {

@@ -1303,7 +1303,7 @@ static void ip__resolve_ams(struct machine *machine, struct thread *thread,
 	 * Thus, we have to try consecutively until we find a match
 	 * or else, the symbol is unknown
 	 */
-	thread__find_cpumode_addr_location(thread, machine, MAP__FUNCTION, ip, &al);
+	thread__find_cpumode_addr_location(thread, MAP__FUNCTION, ip, &al);
 
 	ams->addr = ip;
 	ams->al_addr = al.addr;

@@ -1311,23 +1311,21 @@ static void ip__resolve_ams(struct machine *machine, struct thread *thread,
 	ams->map = al.map;
 }
 
-static void ip__resolve_data(struct machine *machine, struct thread *thread,
+static void ip__resolve_data(struct thread *thread,
 			     u8 m, struct addr_map_symbol *ams, u64 addr)
 {
 	struct addr_location al;
 
 	memset(&al, 0, sizeof(al));
 
-	thread__find_addr_location(thread, machine, m, MAP__VARIABLE, addr,
-				   &al);
+	thread__find_addr_location(thread, m, MAP__VARIABLE, addr, &al);
 	if (al.map == NULL) {
 		/*
 		 * some shared data regions have execute bit set which puts
 		 * their mapping in the MAP__FUNCTION type array.
 		 * Check there as a fallback option before dropping the sample.
 		 */
-		thread__find_addr_location(thread, machine, m, MAP__FUNCTION, addr,
-					   &al);
+		thread__find_addr_location(thread, m, MAP__FUNCTION, addr, &al);
 	}
 
 	ams->addr = addr;

@@ -1344,9 +1342,8 @@ struct mem_info *sample__resolve_mem(struct perf_sample *sample,
 	if (!mi)
 		return NULL;
 
-	ip__resolve_ams(al->machine, al->thread, &mi->iaddr, sample->ip);
-	ip__resolve_data(al->machine, al->thread, al->cpumode,
-			 &mi->daddr, sample->addr);
+	ip__resolve_ams(al->thread, &mi->iaddr, sample->ip);
+	ip__resolve_data(al->thread, al->cpumode, &mi->daddr, sample->addr);
 	mi->data_src.val = sample->data_src;
 
 	return mi;

@@ -1363,15 +1360,14 @@ struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
 		return NULL;
 
 	for (i = 0; i < bs->nr; i++) {
-		ip__resolve_ams(al->machine, al->thread, &bi[i].to, bs->entries[i].to);
-		ip__resolve_ams(al->machine, al->thread, &bi[i].from, bs->entries[i].from);
+		ip__resolve_ams(al->thread, &bi[i].to, bs->entries[i].to);
+		ip__resolve_ams(al->thread, &bi[i].from, bs->entries[i].from);
 		bi[i].flags = bs->entries[i].flags;
 	}
 	return bi;
 }
 
-static int machine__resolve_callchain_sample(struct machine *machine,
-					     struct thread *thread,
+static int thread__resolve_callchain_sample(struct thread *thread,
 					     struct ip_callchain *chain,
 					     struct symbol **parent,
 					     struct addr_location *root_al,

@@ -1395,7 +1391,7 @@ static int machine__resolve_callchain_sample(struct machine *machine,
 	 * Based on DWARF debug information, some architectures skip
 	 * a callchain entry saved by the kernel.
 	 */
-	skip_idx = arch_skip_callchain_idx(machine, thread, chain);
+	skip_idx = arch_skip_callchain_idx(thread, chain);
 
 	for (i = 0; i < chain_nr; i++) {
 		u64 ip;

@@ -1437,7 +1433,7 @@ static int machine__resolve_callchain_sample(struct machine *machine,
 		}
 
 		al.filtered = 0;
-		thread__find_addr_location(thread, machine, cpumode,
+		thread__find_addr_location(thread, cpumode,
 					   MAP__FUNCTION, ip, &al);
 		if (al.sym != NULL) {
 			if (sort__has_parent && !*parent &&

@@ -1476,11 +1472,8 @@ int machine__resolve_callchain(struct machine *machine,
 			       struct addr_location *root_al,
 			       int max_stack)
 {
-	int ret;
-
-	ret = machine__resolve_callchain_sample(machine, thread,
-						sample->callchain, parent,
-						root_al, max_stack);
+	int ret = thread__resolve_callchain_sample(thread, sample->callchain,
+						   parent, root_al, max_stack);
 	if (ret)
 		return ret;
 

index 26386c9465a1..855cbfc3725c 100644
@@ -195,7 +195,6 @@ int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp)
 }
 
 void thread__find_cpumode_addr_location(struct thread *thread,
-					struct machine *machine,
 					enum map_type type, u64 addr,
 					struct addr_location *al)
 {

@@ -208,8 +207,7 @@ void thread__find_cpumode_addr_location(struct thread *thread,
 	};
 
 	for (i = 0; i < ARRAY_SIZE(cpumodes); i++) {
-		thread__find_addr_location(thread, machine, cpumodes[i], type,
-					   addr, al);
+		thread__find_addr_location(thread, cpumodes[i], type, addr, al);
 		if (al->map)
 			break;
 	}

index 8c75fa774706..6ef9fe6ff8da 100644
@@ -54,16 +54,15 @@ void thread__insert_map(struct thread *thread, struct map *map);
 int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp);
 size_t thread__fprintf(struct thread *thread, FILE *fp);
 
-void thread__find_addr_map(struct thread *thread, struct machine *machine,
+void thread__find_addr_map(struct thread *thread,
 			   u8 cpumode, enum map_type type, u64 addr,
 			   struct addr_location *al);
 
-void thread__find_addr_location(struct thread *thread, struct machine *machine,
+void thread__find_addr_location(struct thread *thread,
 				u8 cpumode, enum map_type type, u64 addr,
 				struct addr_location *al);
 
 void thread__find_cpumode_addr_location(struct thread *thread,
-					struct machine *machine,
 					enum map_type type, u64 addr,
 					struct addr_location *al);
 

index 7419768c38b1..f24b350ab192 100644
@@ -26,7 +26,7 @@ static int __report_module(struct addr_location *al, u64 ip,
 	Dwfl_Module *mod;
 	struct dso *dso = NULL;
 
-	thread__find_addr_location(ui->thread, ui->machine,
+	thread__find_addr_location(ui->thread,
 				   PERF_RECORD_MISC_USER,
 				   MAP__FUNCTION, ip, al);
 

@@ -89,7 +89,7 @@ static int access_dso_mem(struct unwind_info *ui, Dwarf_Addr addr,
 	struct addr_location al;
 	ssize_t size;
 
-	thread__find_addr_map(ui->thread, ui->machine, PERF_RECORD_MISC_USER,
+	thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
 			      MAP__FUNCTION, addr, &al);
 	if (!al.map) {
 		pr_debug("unwind: no map for %lx\n", (unsigned long)addr);

index e060386165c5..ed0cb1bc356c 100644
@@ -284,7 +284,7 @@ static struct map *find_map(unw_word_t ip, struct unwind_info *ui)
 {
 	struct addr_location al;
 
-	thread__find_addr_map(ui->thread, ui->machine, PERF_RECORD_MISC_USER,
+	thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
 			      MAP__FUNCTION, ip, &al);
 	return al.map;
 }

@@ -374,7 +374,7 @@ static int access_dso_mem(struct unwind_info *ui, unw_word_t addr,
 	struct addr_location al;
 	ssize_t size;
 
-	thread__find_addr_map(ui->thread, ui->machine, PERF_RECORD_MISC_USER,
+	thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
 			      MAP__FUNCTION, addr, &al);
 	if (!al.map) {
 		pr_debug("unwind: no map for %lx\n", (unsigned long)addr);

@@ -476,14 +476,13 @@ static void put_unwind_info(unw_addr_space_t __maybe_unused as,
 	pr_debug("unwind: put_unwind_info called\n");
 }
 
-static int entry(u64 ip, struct thread *thread, struct machine *machine,
+static int entry(u64 ip, struct thread *thread,
 		 unwind_entry_cb_t cb, void *arg)
 {
 	struct unwind_entry e;
 	struct addr_location al;
 
-	thread__find_addr_location(thread, machine,
-				   PERF_RECORD_MISC_USER,
+	thread__find_addr_location(thread, PERF_RECORD_MISC_USER,
 				   MAP__FUNCTION, ip, &al);
 
 	e.ip = ip;

@@ -574,7 +573,7 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
 		unw_word_t ip;
 
 		unw_get_reg(&c, UNW_REG_IP, &ip);
-		ret = ip ? entry(ip, ui->thread, ui->machine, cb, arg) : 0;
+		ret = ip ? entry(ip, ui->thread, cb, arg) : 0;
 	}
 
 	return ret;

@@ -599,7 +598,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 	if (ret)
 		return ret;
 
-	ret = entry(ip, thread, machine, cb, arg);
+	ret = entry(ip, thread, cb, arg);
 	if (ret)
 		return -ENOMEM;
 

index c84d3f8dcb75..00229809a904 100644
@@ -754,8 +754,8 @@ int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent
 
 	if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain ||
 	    sort__has_parent) {
-		return machine__resolve_callchain(al->machine, evsel, al->thread,
-						  sample, parent, al, max_stack);
+		return thread__resolve_callchain(al->thread, evsel, sample,
+						 parent, al, max_stack);
 	}
 	return 0;
 }

index 08e63fdbd14f..fd192e4885cc 100644
@@ -1464,13 +1464,12 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 				       entry->map, entry->sym);
 }
 
-int machine__resolve_callchain(struct machine *machine,
-			       struct perf_evsel *evsel,
-			       struct thread *thread,
-			       struct perf_sample *sample,
-			       struct symbol **parent,
-			       struct addr_location *root_al,
-			       int max_stack)
+int thread__resolve_callchain(struct thread *thread,
+			      struct perf_evsel *evsel,
+			      struct perf_sample *sample,
+			      struct symbol **parent,
+			      struct addr_location *root_al,
+			      int max_stack)
 {
 	int ret = thread__resolve_callchain_sample(thread, sample->callchain,
 						   parent, root_al, max_stack);

@@ -1487,7 +1486,7 @@ int machine__resolve_callchain(struct machine *machine,
 	    (!sample->user_stack.size))
 		return 0;
 
-	return unwind__get_entries(unwind_entry, &callchain_cursor, machine,
+	return unwind__get_entries(unwind_entry, &callchain_cursor, thread->mg->machine,
 				   thread, sample, max_stack);
 
 }

index 2b651a7f5d0d..88ec74e18cbf 100644
@@ -122,13 +122,12 @@ struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
 					   struct addr_location *al);
 struct mem_info *sample__resolve_mem(struct perf_sample *sample,
 				     struct addr_location *al);
-int machine__resolve_callchain(struct machine *machine,
-			       struct perf_evsel *evsel,
-			       struct thread *thread,
-			       struct perf_sample *sample,
-			       struct symbol **parent,
-			       struct addr_location *root_al,
-			       int max_stack);
+int thread__resolve_callchain(struct thread *thread,
+			      struct perf_evsel *evsel,
+			      struct perf_sample *sample,
+			      struct symbol **parent,
+			      struct addr_location *root_al,
+			      int max_stack);
 
 /*
  * Default guest kernel is defined by parameter --guestkallsyms

index 496f21cadd97..25e5a238f1cb 100644
@@ -312,9 +312,9 @@ static PyObject *python_process_callchain(struct perf_sample *sample,
 	if (!symbol_conf.use_callchain || !sample->callchain)
 		goto exit;
 
-	if (machine__resolve_callchain(al->machine, evsel, al->thread,
-					   sample, NULL, NULL,
-					   PERF_MAX_STACK_DEPTH) != 0) {
+	if (thread__resolve_callchain(al->thread, evsel,
+				      sample, NULL, NULL,
+				      PERF_MAX_STACK_DEPTH) != 0) {
 		pr_err("Failed to resolve callchain. Skipping\n");
 		goto exit;
 	}

index 6702ac28754b..776010844cdc 100644
@@ -1417,9 +1417,9 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, struct perf_sample *sample,
 	if (symbol_conf.use_callchain && sample->callchain) {
 		struct addr_location node_al;
 
-		if (machine__resolve_callchain(al->machine, evsel, al->thread,
-					       sample, NULL, NULL,
-					       PERF_MAX_STACK_DEPTH) != 0) {
+		if (thread__resolve_callchain(al->thread, evsel,
+					      sample, NULL, NULL,
+					      PERF_MAX_STACK_DEPTH) != 0) {
 			if (verbose)
 				error("Failed to resolve callchain. Skipping\n");
 			return;

index fc25e57f4a5d..ab28cca2cb97 100644
@@ -59,7 +59,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 }
 
 __attribute__ ((noinline))
-static int unwind_thread(struct thread *thread, struct machine *machine)
+static int unwind_thread(struct thread *thread)
 {
 	struct perf_sample sample;
 	unsigned long cnt = 0;

@@ -72,7 +72,7 @@ static int unwind_thread(struct thread *thread, struct machine *machine)
 		goto out;
 	}
 
-	err = unwind__get_entries(unwind_entry, &cnt, machine, thread,
+	err = unwind__get_entries(unwind_entry, &cnt, thread,
 				  &sample, MAX_STACK);
 	if (err)
 		pr_debug("unwind failed\n");

@@ -89,21 +89,21 @@ static int unwind_thread(struct thread *thread, struct machine *machine)
 }
 
 __attribute__ ((noinline))
-static int krava_3(struct thread *thread, struct machine *machine)
+static int krava_3(struct thread *thread)
 {
-	return unwind_thread(thread, machine);
+	return unwind_thread(thread);
 }
 
 __attribute__ ((noinline))
-static int krava_2(struct thread *thread, struct machine *machine)
+static int krava_2(struct thread *thread)
 {
-	return krava_3(thread, machine);
+	return krava_3(thread);
 }
 
 __attribute__ ((noinline))
-static int krava_1(struct thread *thread, struct machine *machine)
+static int krava_1(struct thread *thread)
 {
-	return krava_2(thread, machine);
+	return krava_2(thread);
 }
 
 int test__dwarf_unwind(void)

@@ -137,7 +137,7 @@ int test__dwarf_unwind(void)
 		goto out;
 	}
 
-	err = krava_1(thread, machine);
+	err = krava_1(thread);
 
  out:
 	machine__delete_threads(machine);

index fd192e4885cc..51a630301afa 100644
@@ -1486,7 +1486,7 @@ int thread__resolve_callchain(struct thread *thread,
 	    (!sample->user_stack.size))
 		return 0;
 
-	return unwind__get_entries(unwind_entry, &callchain_cursor, thread->mg->machine,
+	return unwind__get_entries(unwind_entry, &callchain_cursor,
 				   thread, sample, max_stack);
 
 }

index f24b350ab192..2dcfe9a7c8d0 100644
@@ -164,14 +164,14 @@ frame_callback(Dwfl_Frame *state, void *arg)
 }
 
 int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
-			struct machine *machine, struct thread *thread,
+			struct thread *thread,
 			struct perf_sample *data,
 			int max_stack)
 {
 	struct unwind_info ui = {
 		.sample		= data,
 		.thread		= thread,
-		.machine	= machine,
+		.machine	= thread->mg->machine,
 		.cb		= cb,
 		.arg		= arg,
 		.max_stack	= max_stack,

index ed0cb1bc356c..3e1fa7f8776c 100644
@@ -580,14 +580,14 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
 }
 
 int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
-			struct machine *machine, struct thread *thread,
+			struct thread *thread,
 			struct perf_sample *data, int max_stack)
 {
 	u64 ip;
 	struct unwind_info ui = {
 		.sample       = data,
 		.thread       = thread,
-		.machine      = machine,
+		.machine      = thread->mg->machine,
 	};
 	int ret;
 

index c17c4855bdbc..412fd7975bdc 100644
@@ -16,7 +16,6 @@ typedef int (*unwind_entry_cb_t)(struct unwind_entry *entry, void *arg);
 
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
 int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
-			struct machine *machine,
 			struct thread *thread,
 			struct perf_sample *data, int max_stack);
 /* libunwind specific */

@@ -36,7 +35,6 @@ static inline void unwind__finish_access(struct thread *thread __maybe_unused) {
 static inline int
 unwind__get_entries(unwind_entry_cb_t cb __maybe_unused,
 		    void *arg __maybe_unused,
-		    struct machine *machine __maybe_unused,
 		    struct thread *thread __maybe_unused,
 		    struct perf_sample *data __maybe_unused,
 		    int max_stack __maybe_unused)

index 5a31787cc6b9..74f257a81265 100644
@@ -43,7 +43,7 @@ static struct sample fake_samples[] = {
 };
 
 static int add_hist_entries(struct perf_evlist *evlist,
-			    struct machine *machine __maybe_unused)
+			    struct machine *machine)
 {
 	struct perf_evsel *evsel;
 	struct addr_location al;

index 144a41236456..f671ec37a7c4 100644
@@ -133,8 +133,7 @@ static int read_via_objdump(const char *filename, u64 addr, void *buf,
 }
 
 static int read_object_code(u64 addr, size_t len, u8 cpumode,
-			    struct thread *thread, struct machine *machine,
-			    struct state *state)
+			    struct thread *thread, struct state *state)
 {
 	struct addr_location al;
 	unsigned char buf1[BUFSZ];

@@ -169,8 +168,8 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode,
 		len = al.map->end - addr;
 
 	/* Read the object code using perf */
-	ret_len = dso__data_read_offset(al.map->dso, machine, al.addr, buf1,
-					len);
+	ret_len = dso__data_read_offset(al.map->dso, thread->mg->machine,
+					al.addr, buf1, len);
 	if (ret_len != len) {
 		pr_debug("dso__data_read_offset failed\n");
 		return -1;

@@ -263,8 +262,7 @@ static int process_sample_event(struct machine *machine,
 
 	cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
-	return read_object_code(sample.ip, READLEN, cpumode, thread, machine,
-				state);
+	return read_object_code(sample.ip, READLEN, cpumode, thread, state);
 }
 
 static int process_event(struct machine *machine, struct perf_evlist *evlist,

index bf48092983c6..b6016101b40b 100644
@@ -42,6 +42,8 @@ static int get_value(struct parse_opt_ctx_t *p,
 		return opterror(opt, "takes no value", flags);
 	if (unset && (opt->flags & PARSE_OPT_NONEG))
 		return opterror(opt, "isn't available", flags);
+	if (opt->flags & PARSE_OPT_DISABLED)
+		return opterror(opt, "is not usable", flags);
 
 	if (!(flags & OPT_SHORT) && p->opt) {
 		switch (opt->type) {

@@ -509,6 +511,8 @@ static void print_option_help(const struct option *opts, int full)
 	}
 	if (!full && (opts->flags & PARSE_OPT_HIDDEN))
 		return;
+	if (opts->flags & PARSE_OPT_DISABLED)
+		return;
 
 	pos = fprintf(stderr, "    ");
 	if (opts->short_name)

@@ -679,3 +683,16 @@ int parse_opt_verbosity_cb(const struct option *opt,
 	}
 	return 0;
 }
+
+void set_option_flag(struct option *opts, int shortopt, const char *longopt,
+		     int flag)
+{
+	for (; opts->type != OPTION_END; opts++) {
+		if ((shortopt && opts->short_name == shortopt) ||
+		    (opts->long_name && longopt &&
+		     !strcmp(opts->long_name, longopt))) {
+			opts->flags |= flag;
+			break;
+		}
+	}
+}

index b59ba858e73d..b7c80dbc7627 100644
@@ -38,6 +38,7 @@ enum parse_opt_option_flags {
 	PARSE_OPT_NONEG   = 4,
 	PARSE_OPT_HIDDEN  = 8,
 	PARSE_OPT_LASTARG_DEFAULT = 16,
+	PARSE_OPT_DISABLED = 32,
 };
 
 struct option;

@@ -211,4 +212,5 @@ extern int parse_opt_verbosity_cb(const struct option *, const char *, int);
 
 extern const char *parse_options_fix_filename(const char *prefix, const char *file);
 
+void set_option_flag(struct option *opts, int sopt, const char *lopt, int flag);
 #endif /* __PERF_PARSE_OPTIONS_H */

index 2583a9b04317..5091a27e6d28 100644
@@ -680,11 +680,12 @@ static int perf_record_config(const char *var, const char *value, void *cb)
 	return perf_default_config(var, value, cb);
 }
 
-static const char * const record_usage[] = {
+static const char * const __record_usage[] = {
 	"perf record [<options>] [<command>]",
 	"perf record [<options>] -- <command> [<options>]",
 	NULL
 };
+const char * const *record_usage = __record_usage;
 
 /*
  * XXX Ideally would be local to cmd_record() and passed to a record__new

@@ -725,7 +726,7 @@ const char record_callchain_help[] = CALLCHAIN_HELP "fp";
  * perf_evlist__prepare_workload, etc instead of fork+exec'in 'perf record',
  * using pipes, etc.
  */
-const struct option record_options[] = {
+struct option __record_options[] = {
 	OPT_CALLBACK('e', "event", &record.evlist, "event",
 		     "event selector. use 'perf list' to list available events",
 		     parse_events_option),

@@ -802,6 +803,8 @@ const struct option record_options[] = {
 	OPT_END()
 };
 
+struct option *record_options = __record_options;
+
 int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	int err = -ENOMEM;

index b35517f2ceb5..ce304dfd962a 100644
@@ -23,7 +23,6 @@ static char const		*generate_script_lang;
 static bool			debug_mode;
 static u64			last_timestamp;
 static u64			nr_unordered;
-extern const struct option	record_options[];
 static bool			no_callchain;
 static bool			latency_format;
 static bool			system_wide;

index f5fb256d90d5..f3bb1a4bf060 100644
@@ -1963,7 +1963,7 @@ int cmd_timechart(int argc, const char **argv,
 		NULL
 	};
 
-	const struct option record_options[] = {
+	const struct option timechart_record_options[] = {
 	OPT_BOOLEAN('P', "power-only", &tchart.power_only, "output power data only"),
 	OPT_BOOLEAN('T', "tasks-only", &tchart.tasks_only,
 		    "output processes data only"),

@@ -1972,7 +1972,7 @@ int cmd_timechart(int argc, const char **argv,
 	OPT_BOOLEAN('g', "callchain", &tchart.with_backtrace, "record callchain"),
 	OPT_END()
 	};
-	const char * const record_usage[] = {
+	const char * const timechart_record_usage[] = {
 		"perf timechart record [<options>]",
 		NULL
 	};

@@ -1985,7 +1985,8 @@ int cmd_timechart(int argc, const char **argv,
 	}
 
 	if (argc && !strncmp(argv[0], "rec", 3)) {
-		argc = parse_options(argc, argv, record_options, record_usage,
+		argc = parse_options(argc, argv, timechart_record_options,
+				     timechart_record_usage,
 				     PARSE_OPT_STOP_AT_NON_OPTION);
 
 		if (tchart.power_only && tchart.tasks_only) {

index 220d44e44c1b..511c2831aa81 100644
@@ -62,4 +62,7 @@ struct record_opts {
 	unsigned     initial_delay;
 };
 
+struct option;
+extern const char * const *record_usage;
+extern struct option *record_options;
 #endif

index b65eb0507b38..3c0f3d4fb021 100644
@@ -1132,6 +1132,10 @@ kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv)
 		"-m", "1024",
 		"-c", "1",
 	};
+	const char * const kvm_stat_record_usage[] = {
+		"perf kvm stat record [<options>]",
+		NULL
+	};
 	const char * const *events_tp;
 	events_tp_size = 0;
 

@@ -1159,6 +1163,27 @@ kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv)
 	for (j = 1; j < (unsigned int)argc; j++, i++)
 		rec_argv[i] = argv[j];
 
+	set_option_flag(record_options, 'e', "event", PARSE_OPT_HIDDEN);
+	set_option_flag(record_options, 0, "filter", PARSE_OPT_HIDDEN);
+	set_option_flag(record_options, 'R', "raw-samples", PARSE_OPT_HIDDEN);
+
+	set_option_flag(record_options, 'F', "freq", PARSE_OPT_DISABLED);
+	set_option_flag(record_options, 0, "group", PARSE_OPT_DISABLED);
+	set_option_flag(record_options, 'g', NULL, PARSE_OPT_DISABLED);
+	set_option_flag(record_options, 0, "call-graph", PARSE_OPT_DISABLED);
+	set_option_flag(record_options, 'd', "data", PARSE_OPT_DISABLED);
+	set_option_flag(record_options, 'T', "timestamp", PARSE_OPT_DISABLED);
+	set_option_flag(record_options, 'P', "period", PARSE_OPT_DISABLED);
+	set_option_flag(record_options, 'n', "no-samples", PARSE_OPT_DISABLED);
+	set_option_flag(record_options, 'N', "no-buildid-cache", PARSE_OPT_DISABLED);
+	set_option_flag(record_options, 'B', "no-buildid", PARSE_OPT_DISABLED);
+	set_option_flag(record_options, 'G', "cgroup", PARSE_OPT_DISABLED);
+	set_option_flag(record_options, 'b', "branch-any", PARSE_OPT_DISABLED);
+	set_option_flag(record_options, 'j', "branch-filter", PARSE_OPT_DISABLED);
+	set_option_flag(record_options, 'W', "weight", PARSE_OPT_DISABLED);
+	set_option_flag(record_options, 0, "transaction", PARSE_OPT_DISABLED);
+
+	record_usage = kvm_stat_record_usage;
 	return cmd_record(i, rec_argv, NULL);
 }
 

index b6016101b40b..f62dee7bd924 100644
@@ -45,6 +45,23 @@ static int get_value(struct parse_opt_ctx_t *p,
 	if (opt->flags & PARSE_OPT_DISABLED)
 		return opterror(opt, "is not usable", flags);
 
+	if (opt->flags & PARSE_OPT_EXCLUSIVE) {
+		if (p->excl_opt) {
+			char msg[128];
+
+			if (((flags & OPT_SHORT) && p->excl_opt->short_name) ||
+			    p->excl_opt->long_name == NULL) {
+				scnprintf(msg, sizeof(msg), "cannot be used with switch `%c'",
+					  p->excl_opt->short_name);
+			} else {
+				scnprintf(msg, sizeof(msg), "cannot be used with %s",
+					  p->excl_opt->long_name);
+			}
+			opterror(opt, msg, flags);
+			return -3;
+		}
+		p->excl_opt = opt;
+	}
 	if (!(flags & OPT_SHORT) && p->opt) {
 		switch (opt->type) {
 		case OPTION_CALLBACK:

@@ -345,13 +362,14 @@ int parse_options_step(struct parse_opt_ctx_t *ctx,
 		       const char * const usagestr[])
 {
 	int internal_help = !(ctx->flags & PARSE_OPT_NO_INTERNAL_HELP);
+	int excl_short_opt = 1;
+	const char *arg;
 
 	/* we must reset ->opt, unknown short option leave it dangling */
 	ctx->opt = NULL;
 
 	for (; ctx->argc; ctx->argc--, ctx->argv++) {
-		const char *arg = ctx->argv[0];
-
+		arg = ctx->argv[0];
 		if (*arg != '-' || !arg[1]) {
 			if (ctx->flags & PARSE_OPT_STOP_AT_NON_OPTION)
 				break;

@@ -360,19 +378,21 @@ int parse_options_step(struct parse_opt_ctx_t *ctx,
 		}
 
 		if (arg[1] != '-') {
-			ctx->opt = arg + 1;
+			ctx->opt = ++arg;
 			if (internal_help && *ctx->opt == 'h')
 				return usage_with_options_internal(usagestr, options, 0);
 			switch (parse_short_opt(ctx, options)) {
 			case -1:
-				return parse_options_usage(usagestr, options, arg + 1, 1);
+				return parse_options_usage(usagestr, options, arg, 1);
 			case -2:
 				goto unknown;
+			case -3:
+				goto exclusive;
 			default:
 				break;
 			}
 			if (ctx->opt)
-				check_typos(arg + 1, options);
+				check_typos(arg, options);
 			while (ctx->opt) {
 				if (internal_help && *ctx->opt == 'h')
 					return usage_with_options_internal(usagestr, options, 0);

@@ -389,6 +409,8 @@ int parse_options_step(struct parse_opt_ctx_t *ctx,
 					ctx->argv[0] = strdup(ctx->opt - 1);
 					*(char *)ctx->argv[0] = '-';
 					goto unknown;
+				case -3:
+					goto exclusive;
 				default:
 					break;
 				}

@@ -404,19 +426,23 @@ int parse_options_step(struct parse_opt_ctx_t *ctx,
 			break;
 		}
 
-		if (internal_help && !strcmp(arg + 2, "help-all"))
+		arg += 2;
+		if (internal_help && !strcmp(arg, "help-all"))
 			return usage_with_options_internal(usagestr, options, 1);
-		if (internal_help && !strcmp(arg + 2, "help"))
+		if (internal_help && !strcmp(arg, "help"))
 			return usage_with_options_internal(usagestr, options, 0);
-		if (!strcmp(arg + 2, "list-opts"))
+		if (!strcmp(arg, "list-opts"))
 			return PARSE_OPT_LIST_OPTS;
-		if (!strcmp(arg + 2, "list-cmds"))
+		if (!strcmp(arg, "list-cmds"))
 			return PARSE_OPT_LIST_SUBCMDS;
-		switch (parse_long_opt(ctx, arg + 2, options)) {
+		switch (parse_long_opt(ctx, arg, options)) {
 		case -1:
-			return parse_options_usage(usagestr, options, arg + 2, 0);
+			return parse_options_usage(usagestr, options, arg, 0);
 		case -2:
 			goto unknown;
+		case -3:
+			excl_short_opt = 0;
+			goto exclusive;
 		default:
 			break;
 		}

@@ -428,6 +454,17 @@ unknown:
 		ctx->opt = NULL;
 	}
 	return PARSE_OPT_DONE;
+
+exclusive:
+	parse_options_usage(usagestr, options, arg, excl_short_opt);
+	if ((excl_short_opt && ctx->excl_opt->short_name) ||
+	    ctx->excl_opt->long_name == NULL) {
+		char opt = ctx->excl_opt->short_name;
+		parse_options_usage(NULL, options, &opt, 1);
+	} else {
+		parse_options_usage(NULL, options, ctx->excl_opt->long_name, 0);
+	}
+	return PARSE_OPT_HELP;
 }
 
 int parse_options_end(struct parse_opt_ctx_t *ctx)

index b7c80dbc7627..97b153fb4999 100644
@@ -39,6 +39,7 @@ enum parse_opt_option_flags {
 	PARSE_OPT_HIDDEN  = 8,
 	PARSE_OPT_LASTARG_DEFAULT = 16,
 	PARSE_OPT_DISABLED = 32,
+	PARSE_OPT_EXCLUSIVE = 64,
 };
 
 struct option;

@@ -174,6 +175,7 @@ struct parse_opt_ctx_t {
 	const char **out;
 	int argc, cpidx;
 	const char *opt;
+	const struct option *excl_opt;
 	int flags;
 };
 

index 04412b4770a2..23d6e7f03cf1 100644
@@ -312,7 +312,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 #endif
 		NULL
 };
-	const struct option options[] = {
+	struct option options[] = {
 	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show parsed arguments, etc)"),
 	OPT_BOOLEAN('l', "list", &params.list_events,

@@ -382,6 +382,14 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 	};
 	int ret;
 
+	set_option_flag(options, 'a', "add", PARSE_OPT_EXCLUSIVE);
+	set_option_flag(options, 'd', "del", PARSE_OPT_EXCLUSIVE);
+	set_option_flag(options, 'l', "list", PARSE_OPT_EXCLUSIVE);
+#ifdef HAVE_DWARF_SUPPORT
+	set_option_flag(options, 'L', "line", PARSE_OPT_EXCLUSIVE);
+	set_option_flag(options, 'V', "vars", PARSE_OPT_EXCLUSIVE);
+#endif
+
 	argc = parse_options(argc, argv, options, probe_usage,
 			     PARSE_OPT_STOP_AT_NON_OPTION);
 	if (argc > 0) {

@@ -409,22 +417,6 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 	symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
 
 	if (params.list_events) {
-		if (params.mod_events) {
-			pr_err("  Error: Don't use --list with --add/--del.\n");
-			usage_with_options(probe_usage, options);
-		}
-		if (params.show_lines) {
-			pr_err("  Error: Don't use --list with --line.\n");
-			usage_with_options(probe_usage, options);
-		}
-		if (params.show_vars) {
-			pr_err(" Error: Don't use --list with --vars.\n");
-			usage_with_options(probe_usage, options);
-		}
-		if (params.show_funcs) {
-			pr_err("  Error: Don't use --list with --funcs.\n");
-			usage_with_options(probe_usage, options);
-		}
 		if (params.uprobes) {
 			pr_warning("  Error: Don't use --list with --exec.\n");
 			usage_with_options(probe_usage, options);

@@ -435,19 +427,6 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 		return ret;
 	}
 	if (params.show_funcs) {
-		if (params.nevents != 0 || params.dellist) {
-			pr_err("  Error: Don't use --funcs with"
-			       " --add/--del.\n");
-			usage_with_options(probe_usage, options);
-		}
-		if (params.show_lines) {
-			pr_err("  Error: Don't use --funcs with --line.\n");
-			usage_with_options(probe_usage, options);
-		}
-		if (params.show_vars) {
-			pr_err("  Error: Don't use --funcs with --vars.\n");
-			usage_with_options(probe_usage, options);
-		}
 		if (!params.filter)
 			params.filter = strfilter__new(DEFAULT_FUNC_FILTER,
 						       NULL);

@@ -462,16 +441,6 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 
 #ifdef HAVE_DWARF_SUPPORT
 	if (params.show_lines) {
-		if (params.mod_events) {
-			pr_err("  Error: Don't use --line with"
-			       " --add/--del.\n");
-			usage_with_options(probe_usage, options);
-		}
-		if (params.show_vars) {
-			pr_err(" Error: Don't use --line with --vars.\n");
-			usage_with_options(probe_usage, options);
-		}
-
 		ret = show_line_range(&params.line_range, params.target,
 				      params.uprobes);
 		if (ret < 0)

@@ -479,11 +448,6 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 		return ret;
 	}
 	if (params.show_vars) {
-		if (params.mod_events) {
-			pr_err("  Error: Don't use --vars with"
-			       " --add/--del.\n");
-			usage_with_options(probe_usage, options);
-		}
 		if (!params.filter)
 			params.filter = strfilter__new(DEFAULT_VAR_FILTER,
 						       NULL);

index 855cbfc3725c..bf5bf858b7f6 100644
@@ -117,6 +117,9 @@ int __thread__set_comm(struct thread *thread, const char *str, u64 timestamp,
 		if (!new)
 			return -ENOMEM;
 		list_add(&new->list, &thread->comm_list);
+
+		if (exec)
+			unwind__flush_access(thread);
 	}
 
 	thread->comm_set = true;

index 3e1fa7f8776c..371219a6daf1 100644
@@ -538,11 +538,23 @@ int unwind__prepare_access(struct thread *thread)
 		return -ENOMEM;
 	}
 
+	unw_set_caching_policy(addr_space, UNW_CACHE_GLOBAL);
 	thread__set_priv(thread, addr_space);
 
 	return 0;
 }
 
+void unwind__flush_access(struct thread *thread)
+{
+	unw_addr_space_t addr_space;
+
+	if (callchain_param.record_mode != CALLCHAIN_DWARF)
+		return;
+
+	addr_space = thread__priv(thread);
+	unw_flush_cache(addr_space, 0, 0);
+}
+
 void unwind__finish_access(struct thread *thread)
 {
 	unw_addr_space_t addr_space;

index 412fd7975bdc..12790cf94618 100644
@@ -22,6 +22,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 #ifdef HAVE_LIBUNWIND_SUPPORT
 int libunwind__arch_reg_id(int regnum);
 int unwind__prepare_access(struct thread *thread);
+void unwind__flush_access(struct thread *thread);
 void unwind__finish_access(struct thread *thread);
 #else
 static inline int unwind__prepare_access(struct thread *thread __maybe_unused)

@@ -29,6 +30,7 @@ static inline int unwind__prepare_access(struct thread *thread __maybe_unused)
 	return 0;
 }
 
+static inline void unwind__flush_access(struct thread *thread __maybe_unused) {}
 static inline void unwind__finish_access(struct thread *thread __maybe_unused) {}
 #endif
 #else

@@ -47,6 +49,7 @@ static inline int unwind__prepare_access(struct thread *thread __maybe_unused)
 	return 0;
 }
 
+static inline void unwind__flush_access(struct thread *thread __maybe_unused) {}
 static inline void unwind__finish_access(struct thread *thread __maybe_unused) {}
 #endif /* HAVE_DWARF_UNWIND_SUPPORT */
 #endif /* __UNWIND_H */

index ce0de00399da..39b80ac9f698 100644
@@ -605,8 +605,10 @@ static int write_cpudesc(int fd, struct perf_header *h __maybe_unused,
 			break;
 	}
 
-	if (ret)
+	if (ret) {
+		ret = -1;
 		goto done;
+	}
 
 	s = buf;
 

@@ -950,7 +952,8 @@ static int write_total_mem(int fd, struct perf_header *h __maybe_unused,
 		n = sscanf(buf, "%*s %"PRIu64, &mem);
 		if (n == 1)
 			ret = do_write(fd, &mem, sizeof(mem));
-	}
+	} else
+		ret = -1;
 	free(buf);
 	fclose(fp);
 	return ret;

index e243ad962a4d..91dca604c422 100644
@@ -747,15 +747,18 @@ void print_pmu_events(const char *event_glob, bool name_only)
 
 	pmu = NULL;
 	len = 0;
-	while ((pmu = perf_pmu__scan(pmu)) != NULL)
+	while ((pmu = perf_pmu__scan(pmu)) != NULL) {
 		list_for_each_entry(alias, &pmu->aliases, list)
 			len++;
+		if (pmu->selectable)
+			len++;
+	}
 	aliases = malloc(sizeof(char *) * len);
 	if (!aliases)
 		return;
 	pmu = NULL;
 	j = 0;
-	while ((pmu = perf_pmu__scan(pmu)) != NULL)
+	while ((pmu = perf_pmu__scan(pmu)) != NULL) {
 		list_for_each_entry(alias, &pmu->aliases, list) {
 			char *name = format_alias(buf, sizeof(buf), pmu, alias);
 			bool is_cpu = !strcmp(pmu->name, "cpu");

@@ -772,6 +775,12 @@ void print_pmu_events(const char *event_glob, bool name_only)
 			aliases[j] = strdup(aliases[j]);
 			j++;
 		}
+		if (pmu->selectable) {
+			scnprintf(buf, sizeof(buf), "%s//", pmu->name);
+			aliases[j] = strdup(buf);
+			j++;
+		}
+	}
 	len = j;
 	qsort(aliases, len, sizeof(char *), cmp_string);
 	for (j = 0; j < len; j++) {

index fe9dfbee8eed..8092de78e818 100644
@@ -18,6 +18,7 @@ struct perf_event_attr;
 struct perf_pmu {
 	char *name;
 	__u32 type;
+	bool selectable;
 	struct perf_event_attr *default_config;
 	struct cpu_map *cpus;
 	struct list_head format;  /* HEAD struct perf_pmu_format -> list */

new file mode 100644
index 000000000000..31dbf45bf99c
@@ -0,0 +1,4 @@
+int main(void)
+{
+	return 0;
+}

new file mode 100644
index 000000000000..764e2547c25a
@@ -0,0 +1,34 @@
+#include <stdio.h>
+#include <string.h>
+
+#define VDSO__MAP_NAME "[vdso]"
+
+/*
+ * Include definition of find_vdso_map() also used in util/vdso.c for
+ * building perf.
+ */
+#include "util/find-vdso-map.c"
+
+int main(void)
+{
+	void *start, *end;
+	size_t size, written;
+
+	if (find_vdso_map(&start, &end))
+		return 1;
+
+	size = end - start;
+
+	while (size) {
+		written = fwrite(start, 1, size, stdout);
+		if (!written)
+			return 1;
+		start += written;
+		size -= written;
+	}
+
+	if (fflush(stdout))
+		return 1;
+
+	return 0;
+}

new file mode 100644
index 000000000000..95ef1cffc056
@@ -0,0 +1,30 @@
+static int find_vdso_map(void **start, void **end)
+{
+	FILE *maps;
+	char line[128];
+	int found = 0;
+
+	maps = fopen("/proc/self/maps", "r");
+	if (!maps) {
+		fprintf(stderr, "vdso: cannot open maps\n");
+		return -1;
+	}
+
+	while (!found && fgets(line, sizeof(line), maps)) {
+		int m = -1;
+
+		/* We care only about private r-x mappings. */
+		if (2 != sscanf(line, "%p-%p r-xp %*x %*x:%*x %*u %n",
+				start, end, &m))
+			continue;
+		if (m < 0)
+			continue;
+
+		if (!strncmp(&line[m], VDSO__MAP_NAME,
+			     sizeof(VDSO__MAP_NAME) - 1))
+			found = 1;
+	}
+
+	fclose(maps);
+	return !found;
+}

index adca69384fcc..f51390a1ed51 100644
@@ -15,6 +15,12 @@
 #include "linux/string.h"
 #include "debug.h"
 
+/*
+ * Include definition of find_vdso_map() also used in perf-read-vdso.c for
+ * building perf-read-vdso32 and perf-read-vdsox32.
+ */
+#include "find-vdso-map.c"
+
 #define VDSO__TEMP_FILE_NAME "/tmp/perf-vdso.so-XXXXXX"
 
 struct vdso_file {

@@ -40,37 +46,6 @@ static struct vdso_info *vdso_info__new(void)
 	return memdup(&vdso_info_init, sizeof(vdso_info_init));
 }
 
-static int find_vdso_map(void **start, void **end)
-{
-	FILE *maps;
-	char line[128];
-	int found = 0;
-
-	maps = fopen("/proc/self/maps", "r");
-	if (!maps) {
-		pr_err("vdso: cannot open maps\n");
-		return -1;
-	}
-
-	while (!found && fgets(line, sizeof(line), maps)) {
-		int m = -1;
-
-		/* We care only about private r-x mappings. */
-		if (2 != sscanf(line, "%p-%p r-xp %*x %*x:%*x %*u %n",
-				start, end, &m))
-			continue;
-		if (m < 0)
-			continue;
-
-		if (!strncmp(&line[m], VDSO__MAP_NAME,
-			     sizeof(VDSO__MAP_NAME) - 1))
-			found = 1;
-	}
-
-	fclose(maps);
-	return !found;
-}
-
 static char *get_file(struct vdso_file *vdso_file)
 {
 	char *vdso = NULL;

index f51390a1ed51..69daef6a17d5 100644
@@ -12,6 +12,7 @@
 #include "util.h"
 #include "symbol.h"
 #include "machine.h"
+#include "thread.h"
 #include "linux/string.h"
 #include "debug.h"
 

@@ -28,10 +29,15 @@ struct vdso_file {
 	bool error;
 	char temp_file_name[sizeof(VDSO__TEMP_FILE_NAME)];
 	const char *dso_name;
+	const char *read_prog;
 };
 
 struct vdso_info {
 	struct vdso_file vdso;
+#if BITS_PER_LONG == 64
+	struct vdso_file vdso32;
+	struct vdso_file vdsox32;
+#endif
 };
 
 static struct vdso_info *vdso_info__new(void)

@@ -41,6 +47,18 @@ static struct vdso_info *vdso_info__new(void)
 			.temp_file_name = VDSO__TEMP_FILE_NAME,
 			.dso_name = DSO__NAME_VDSO,
 		},
+#if BITS_PER_LONG == 64
+		.vdso32  = {
+			.temp_file_name = VDSO__TEMP_FILE_NAME,
+			.dso_name = DSO__NAME_VDSO32,
+			.read_prog = "perf-read-vdso32",
+		},
+		.vdsox32  = {
+			.temp_file_name = VDSO__TEMP_FILE_NAME,
+			.dso_name = DSO__NAME_VDSOX32,
+			.read_prog = "perf-read-vdsox32",
+		},
+#endif
 	};
 
 	return memdup(&vdso_info_init, sizeof(vdso_info_init));

@@ -92,6 +110,12 @@ void vdso__exit(struct machine *machine)
 
 	if (vdso_info->vdso.found)
 		unlink(vdso_info->vdso.temp_file_name);
+#if BITS_PER_LONG == 64
+	if (vdso_info->vdso32.found)
+		unlink(vdso_info->vdso32.temp_file_name);
+	if (vdso_info->vdsox32.found)
+		unlink(vdso_info->vdsox32.temp_file_name);
+#endif
 
 	zfree(&machine->vdso_info);
 }

@@ -110,6 +134,143 @@ static struct dso *vdso__new(struct machine *machine, const char *short_name,
 	return dso;
 }
 
+#if BITS_PER_LONG == 64
+
+static enum dso_type machine__thread_dso_type(struct machine *machine,
+					      struct thread *thread)
+{
+	enum dso_type dso_type = DSO__TYPE_UNKNOWN;
+	struct map *map;
+	struct dso *dso;
+
+	map = map_groups__first(thread->mg, MAP__FUNCTION);
+	for (; map ; map = map_groups__next(map)) {
+		dso = map->dso;
+		if (!dso || dso->long_name[0] != '/')
+			continue;
+		dso_type = dso__type(dso, machine);
+		if (dso_type != DSO__TYPE_UNKNOWN)
+			break;
+	}
+
+	return dso_type;
+}
+
+static int vdso__do_copy_compat(FILE *f, int fd)
+{
+	char buf[4096];
+	size_t count;
+
+	while (1) {
+		count = fread(buf, 1, sizeof(buf), f);
+		if (ferror(f))
+			return -errno;
+		if (feof(f))
+			break;
+		if (count && writen(fd, buf, count) != (ssize_t)count)
+			return -errno;
+	}
+
+	return 0;
+}
+
+static int vdso__copy_compat(const char *prog, int fd)
+{
+	FILE *f;
+	int err;
+
+	f = popen(prog, "r");
+	if (!f)
+		return -errno;
+
+	err = vdso__do_copy_compat(f, fd);
+
+	if (pclose(f) == -1)
+		return -errno;
+
+	return err;
+}
+
+static int vdso__create_compat_file(const char *prog, char *temp_name)
+{
+	int fd, err;
+
+	fd = mkstemp(temp_name);
+	if (fd < 0)
+		return -errno;
+
+	err = vdso__copy_compat(prog, fd);
+
+	if (close(fd) == -1)
+		return -errno;
+
+	return err;
+}
+
+static const char *vdso__get_compat_file(struct vdso_file *vdso_file)
+{
+	int err;
+
+	if (vdso_file->found)
+		return vdso_file->temp_file_name;
+
+	if (vdso_file->error)
+		return NULL;
+
+	err = vdso__create_compat_file(vdso_file->read_prog,
+				       vdso_file->temp_file_name);
+	if (err) {
+		pr_err("%s failed, error %d\n", vdso_file->read_prog, err);
+		vdso_file->error = true;
+		return NULL;
+	}
+
+	vdso_file->found = true;
+
+	return vdso_file->temp_file_name;
+}
+
+static struct dso *vdso__findnew_compat(struct machine *machine,
+					struct vdso_file *vdso_file)
+{
+	const char *file_name;
+	struct dso *dso;
+
+	dso = dsos__find(&machine->user_dsos, vdso_file->dso_name, true);
+	if (dso)
+		return dso;
+
+	file_name = vdso__get_compat_file(vdso_file);
+	if (!file_name)
+		return NULL;
+
+	return vdso__new(machine, vdso_file->dso_name, file_name);
+}
+
+static int vdso__dso_findnew_compat(struct machine *machine,
+				    struct thread *thread,
+				    struct vdso_info *vdso_info,
+				    struct dso **dso)
+{
+	enum dso_type dso_type;
+
+	dso_type = machine__thread_dso_type(machine, thread);
+	switch (dso_type) {
+	case DSO__TYPE_32BIT:
+		*dso = vdso__findnew_compat(machine, &vdso_info->vdso32);
+		return 1;
+	case DSO__TYPE_X32BIT:
+		*dso = vdso__findnew_compat(machine, &vdso_info->vdsox32);
+		return 1;
+	case DSO__TYPE_UNKNOWN:
+	case DSO__TYPE_64BIT:
+	default:
+		return 0;
+	}
+}
+
+#endif
+
 struct dso *vdso__dso_findnew(struct machine *machine,
 			      struct thread *thread __maybe_unused)
 {

@@ -123,6 +284,11 @@ struct dso *vdso__dso_findnew(struct machine *machine,
 	if (!vdso_info)
 		return NULL;
 
+#if BITS_PER_LONG == 64
+	if (vdso__dso_findnew_compat(machine, thread, vdso_info, &dso))
+		return dso;
+#endif
+
 	dso = dsos__find(&machine->user_dsos, DSO__NAME_VDSO, true);
 	if (!dso) {
 		char *file;

@@ -139,5 +305,7 @@ struct dso *vdso__dso_findnew(struct machine *machine,
 
 bool dso__is_vdso(struct dso *dso)
 {
-	return !strcmp(dso->short_name, DSO__NAME_VDSO);
+	return !strcmp(dso->short_name, DSO__NAME_VDSO) ||
+	       !strcmp(dso->short_name, DSO__NAME_VDSO32) ||
+	       !strcmp(dso->short_name, DSO__NAME_VDSOX32);
 }

index af9d6929a215..d97da1616f0c 100644
@@ -7,7 +7,9 @@
 
 #define VDSO__MAP_NAME "[vdso]"
 
-#define DSO__NAME_VDSO "[vdso]"
+#define DSO__NAME_VDSO    "[vdso]"
+#define DSO__NAME_VDSO32  "[vdso32]"
+#define DSO__NAME_VDSOX32 "[vdsox32]"
 
 static inline bool is_vdso_map(const char *filename)
 {

index 69daef6a17d5..5c7dd796979d 100644
@@ -255,6 +255,16 @@ static int vdso__dso_findnew_compat(struct machine *machine,
 	enum dso_type dso_type;
 
 	dso_type = machine__thread_dso_type(machine, thread);
+
+#ifndef HAVE_PERF_READ_VDSO32
+	if (dso_type == DSO__TYPE_32BIT)
+		return 0;
+#endif
+#ifndef HAVE_PERF_READ_VDSOX32
+	if (dso_type == DSO__TYPE_X32BIT)
+		return 0;
+#endif
+
 	switch (dso_type) {
 	case DSO__TYPE_32BIT:
 		*dso = vdso__findnew_compat(machine, &vdso_info->vdso32);

index 937e4324ad94..a3b13d7dc1d4 100644
@@ -13,7 +13,7 @@
 #define wmb()		asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
 #define rmb()		asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
 #define cpu_relax()	asm volatile("rep; nop" ::: "memory");
-#define CPUINFO_PROC	"model name"
+#define CPUINFO_PROC	{"model name"}
 #ifndef __NR_perf_event_open
 # define __NR_perf_event_open 336
 #endif

@@ -30,7 +30,7 @@
 #define wmb()		asm volatile("sfence" ::: "memory")
 #define rmb()		asm volatile("lfence" ::: "memory")
 #define cpu_relax()	asm volatile("rep; nop" ::: "memory");
-#define CPUINFO_PROC	"model name"
+#define CPUINFO_PROC	{"model name"}
 #ifndef __NR_perf_event_open
 # define __NR_perf_event_open 298
 #endif

@@ -47,14 +47,14 @@
 #define mb()		asm volatile ("sync" ::: "memory")
 #define wmb()		asm volatile ("sync" ::: "memory")
 #define rmb()		asm volatile ("sync" ::: "memory")
-#define CPUINFO_PROC	"cpu"
+#define CPUINFO_PROC	{"cpu"}
 #endif
 
 #ifdef __s390__
 #define mb()		asm volatile("bcr 15,0" ::: "memory")
 #define wmb()		asm volatile("bcr 15,0" ::: "memory")
 #define rmb()		asm volatile("bcr 15,0" ::: "memory")
-#define CPUINFO_PROC	"vendor_id"
+#define CPUINFO_PROC	{"vendor_id"}
 #endif
 
 #ifdef __sh__

@@ -67,14 +67,14 @@
 # define wmb()		asm volatile("" ::: "memory")
 # define rmb()		asm volatile("" ::: "memory")
 #endif
-#define CPUINFO_PROC	"cpu type"
+#define CPUINFO_PROC	{"cpu type"}
 #endif
 
 #ifdef __hppa__
 #define mb()		asm volatile("" ::: "memory")
 #define wmb()		asm volatile("" ::: "memory")
 #define rmb()		asm volatile("" ::: "memory")
-#define CPUINFO_PROC	"cpu"
+#define CPUINFO_PROC	{"cpu"}
 #endif
 
 #ifdef __sparc__

@@ -87,14 +87,14 @@
 #endif
 #define wmb()		asm volatile("":::"memory")
 #define rmb()		asm volatile("":::"memory")
-#define CPUINFO_PROC	"cpu"
+#define CPUINFO_PROC	{"cpu"}
 #endif
 
 #ifdef __alpha__
 #define mb()		asm volatile("mb" ::: "memory")
 #define wmb()		asm volatile("wmb" ::: "memory")
 #define rmb()		asm volatile("mb" ::: "memory")
-#define CPUINFO_PROC	"cpu model"
+#define CPUINFO_PROC	{"cpu model"}
 #endif
 
 #ifdef __ia64__

@@ -102,7 +102,7 @@
 #define wmb()		asm volatile ("mf" ::: "memory")
 #define rmb()		asm volatile ("mf" ::: "memory")
 #define cpu_relax()	asm volatile ("hint @pause" ::: "memory")
-#define CPUINFO_PROC	"model name"
+#define CPUINFO_PROC	{"model name"}
 #endif
 
 #ifdef __arm__

@@ -113,7 +113,7 @@
 #define mb()		((void(*)(void))0xffff0fa0)()
 #define wmb()		((void(*)(void))0xffff0fa0)()
 #define rmb()		((void(*)(void))0xffff0fa0)()
-#define CPUINFO_PROC	"Processor"
+#define CPUINFO_PROC	{"model name", "Processor"}
 #endif
 
 #ifdef __aarch64__

@@ -133,28 +133,28 @@
 				: "memory")
 #define wmb()	mb()
 #define rmb()	mb()
-#define CPUINFO_PROC	"cpu model"
+#define CPUINFO_PROC	{"cpu model"}
 #endif
 
 #ifdef __arc__
 #define mb()		asm volatile("" ::: "memory")
 #define wmb()		asm volatile("" ::: "memory")
 #define rmb()		asm volatile("" ::: "memory")
-#define CPUINFO_PROC	"Processor"
+#define CPUINFO_PROC	{"Processor"}
 #endif
 
 #ifdef __metag__
 #define mb()		asm volatile("" ::: "memory")
 #define wmb()		asm volatile("" ::: "memory")
 #define rmb()		asm volatile("" ::: "memory")
-#define CPUINFO_PROC	"CPU"
+#define CPUINFO_PROC	{"CPU"}
 #endif
 
 #ifdef __xtensa__
 #define mb()		asm volatile("memw" ::: "memory")
 #define wmb()		asm volatile("memw" ::: "memory")
 #define rmb()		asm volatile("" ::: "memory")
-#define CPUINFO_PROC	"core ID"
+#define CPUINFO_PROC	{"core ID"}
 #endif
 
 #ifdef __tile__

@@ -162,7 +162,7 @@
 #define wmb()		asm volatile ("mf" ::: "memory")
 #define rmb()		asm volatile ("mf" ::: "memory")
 #define cpu_relax()	asm volatile ("mfspr zero, PASS" ::: "memory")
-#define CPUINFO_PROC    "model name"
+#define CPUINFO_PROC    {"model name"}
 #endif
 
 #define barrier() asm volatile ("" ::: "memory")

index 39b80ac9f698..0ecf4a304cbc 100644
@@ -579,16 +579,12 @@ static int write_version(int fd, struct perf_header *h __maybe_unused,
 	return do_write_string(fd, perf_version_string);
 }
 
-static int write_cpudesc(int fd, struct perf_header *h __maybe_unused,
-		       struct perf_evlist *evlist __maybe_unused)
+static int __write_cpudesc(int fd, const char *cpuinfo_proc)
 {
-#ifndef CPUINFO_PROC
-#define CPUINFO_PROC NULL
-#endif
 	FILE *file;
 	char *buf = NULL;
 	char *s, *p;
-	const char *search = CPUINFO_PROC;
+	const char *search = cpuinfo_proc;
 	size_t len = 0;
 	int ret = -1;
 

@@ -640,6 +636,25 @@ done:
 	return ret;
 }
 
+static int write_cpudesc(int fd, struct perf_header *h __maybe_unused,
+		       struct perf_evlist *evlist __maybe_unused)
+{
+#ifndef CPUINFO_PROC
+#define CPUINFO_PROC {"model name", }
+#endif
+	const char *cpuinfo_procs[] = CPUINFO_PROC;
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(cpuinfo_procs); i++) {
+		int ret;
+		ret = __write_cpudesc(fd, cpuinfo_procs[i]);
+		if (ret >= 0)
+			return ret;
+	}
+	return -1;
+}
+
+
 static int write_nrcpus(int fd, struct perf_header *h __maybe_unused,
 			struct perf_evlist *evlist __maybe_unused)
 {

index 91dca604c422..881b75490533 100644
@@ -753,9 +753,9 @@ void print_pmu_events(const char *event_glob, bool name_only)
 		if (pmu->selectable)
 			len++;
 	}
-	aliases = malloc(sizeof(char *) * len);
+	aliases = zalloc(sizeof(char *) * len);
 	if (!aliases)
-		return;
+		goto out_enomem;
 	pmu = NULL;
 	j = 0;
 	while ((pmu = perf_pmu__scan(pmu)) != NULL) {

@@ -768,16 +768,20 @@ void print_pmu_events(const char *event_glob, bool name_only)
 			      (!is_cpu && strglobmatch(alias->name,
 						       event_glob))))
 				continue;
-			aliases[j] = name;
+
 			if (is_cpu && !name_only)
-				aliases[j] = format_alias_or(buf, sizeof(buf),
-							      pmu, alias);
-			aliases[j] = strdup(aliases[j]);
+				name = format_alias_or(buf, sizeof(buf), pmu, alias);
+
+			aliases[j] = strdup(name);
+			if (aliases[j] == NULL)
+				goto out_enomem;
 			j++;
 		}
 		if (pmu->selectable) {
-			scnprintf(buf, sizeof(buf), "%s//", pmu->name);
-			aliases[j] = strdup(buf);
+			char *s;
+			if (asprintf(&s, "%s//", pmu->name) < 0)
+				goto out_enomem;
+			aliases[j] = s;
 			j++;
 		}
 	}

@@ -789,12 +793,20 @@ void print_pmu_events(const char *event_glob, bool name_only)
 			continue;
 		}
 		printf("  %-50s [Kernel PMU event]\n", aliases[j]);
-		zfree(&aliases[j]);
 		printed++;
 	}
 	if (printed)
 		printf("\n");
-	free(aliases);
+out_free:
+	for (j = 0; j < len; j++)
+		zfree(&aliases[j]);
+	zfree(&aliases);
+	return;
+
+out_enomem:
+	printf("FATAL: not enough memory to print PMU events\n");
+	if (aliases)
+		goto out_free;
 }
 
 bool pmu_have_event(const char *pname, const char *name)

index 4906cd81cb56..82241fe54e4b 100644
@@ -989,6 +989,9 @@ struct sort_entry sort_mem_dcacheline = {
 static int64_t
 sort__abort_cmp(struct hist_entry *left, struct hist_entry *right)
 {
+	if (!left->branch_info || !right->branch_info)
+		return cmp_null(left->branch_info, right->branch_info);
+
 	return left->branch_info->flags.abort !=
 		right->branch_info->flags.abort;
 }

@@ -996,10 +999,15 @@ sort__abort_cmp(struct hist_entry *left, struct hist_entry *right)
 static int hist_entry__abort_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
 {
-	static const char *out = ".";
+	static const char *out = "N/A";
+
+	if (he->branch_info) {
+		if (he->branch_info->flags.abort)
+			out = "A";
+		else
+			out = ".";
+	}
 
-	if (he->branch_info->flags.abort)
-		out = "A";
 	return repsep_snprintf(bf, size, "%-*s", width, out);
 }
 

index 82241fe54e4b..9bcdb57076b8 100644
@@ -1021,6 +1021,9 @@ struct sort_entry sort_abort = {
 static int64_t
 sort__in_tx_cmp(struct hist_entry *left, struct hist_entry *right)
 {
+	if (!left->branch_info || !right->branch_info)
+		return cmp_null(left->branch_info, right->branch_info);
+
 	return left->branch_info->flags.in_tx !=
 		right->branch_info->flags.in_tx;
 }

@@ -1028,10 +1031,14 @@ sort__in_tx_cmp(struct hist_entry *left, struct hist_entry *right)
 static int hist_entry__in_tx_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
 {
-	static const char *out = ".";
+	static const char *out = "N/A";
 
-	if (he->branch_info->flags.in_tx)
-		out = "T";
+	if (he->branch_info) {
+		if (he->branch_info->flags.in_tx)
+			out = "T";
+		else
+			out = ".";
+	}
 
 	return repsep_snprintf(bf, size, "%-*s", width, out);
 }

index 9bcdb57076b8..0c68af83e7dd 100644
@@ -471,11 +471,13 @@ struct sort_entry sort_sym_to = {
 static int64_t
 sort__mispredict_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-	const unsigned char mp = left->branch_info->flags.mispred !=
-					right->branch_info->flags.mispred;
-	const unsigned char p = left->branch_info->flags.predicted !=
-					right->branch_info->flags.predicted;
+	unsigned char mp, p;
 
+	if (!left->branch_info || !right->branch_info)
+		return cmp_null(left->branch_info, right->branch_info);
+
+	mp = left->branch_info->flags.mispred != right->branch_info->flags.mispred;
+	p  = left->branch_info->flags.predicted != right->branch_info->flags.predicted;
 	return mp || p;
 }
 

@@ -483,10 +485,12 @@ static int hist_entry__mispredict_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width){
 	static const char *out = "N/A";
 
-	if (he->branch_info->flags.predicted)
-		out = "N";
-	else if (he->branch_info->flags.mispred)
-		out = "Y";
+	if (he->branch_info) {
+		if (he->branch_info->flags.predicted)
+			out = "N";
+		else if (he->branch_info->flags.mispred)
+			out = "Y";
+	}
 
 	return repsep_snprintf(bf, size, "%-*.*s", width, width, out);
 }

index 0c68af83e7dd..57047c0a247c 100644
@@ -413,8 +413,13 @@ sort__sym_from_cmp(struct hist_entry *left, struct hist_entry *right)
 static int64_t
 sort__sym_to_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-	struct addr_map_symbol *to_l = &left->branch_info->to;
-	struct addr_map_symbol *to_r = &right->branch_info->to;
+	struct addr_map_symbol *to_l, *to_r;
+
+	if (!left->branch_info || !right->branch_info)
+		return cmp_null(left->branch_info, right->branch_info);
+
+	to_l = &left->branch_info->to;
+	to_r = &right->branch_info->to;
 
 	if (!to_l->sym && !to_r->sym)
 		return _sort__addr_cmp(to_l->addr, to_r->addr);

@@ -434,10 +439,14 @@ static int hist_entry__sym_from_snprintf(struct hist_entry *he, char *bf,
 static int hist_entry__sym_to_snprintf(struct hist_entry *he, char *bf,
 				       size_t size, unsigned int width)
 {
-	struct addr_map_symbol *to = &he->branch_info->to;
-	return _hist_entry__sym_snprintf(to->map, to->sym, to->addr,
-					 he->level, bf, size, width);
+	if (he->branch_info) {
+		struct addr_map_symbol *to = &he->branch_info->to;
+
+		return _hist_entry__sym_snprintf(to->map, to->sym, to->addr,
+						 he->level, bf, size, width);
+	}
 
+	return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A");
 }
 
 struct sort_entry sort_dso_from = {