perf/core improvements and fixes

index 44d440da15dc..8f81c415723d 100644
@@ -134,8 +134,6 @@ static struct dso *__machine__addnew_vdso(struct machine *machine, const char *s
 	return dso;
 }
 
-#if BITS_PER_LONG == 64
-
 static enum dso_type machine__thread_dso_type(struct machine *machine,
 					      struct thread *thread)
 {

@@ -156,6 +154,8 @@ static enum dso_type machine__thread_dso_type(struct machine *machine,
 	return dso_type;
 }
 
+#if BITS_PER_LONG == 64
+
 static int vdso__do_copy_compat(FILE *f, int fd)
 {
 	char buf[4096];

@@ -283,8 +283,38 @@ static int __machine__findnew_vdso_compat(struct machine *machine,
 
 #endif
 
+static struct dso *machine__find_vdso(struct machine *machine,
+				      struct thread *thread)
+{
+	struct dso *dso = NULL;
+	enum dso_type dso_type;
+
+	dso_type = machine__thread_dso_type(machine, thread);
+	switch (dso_type) {
+	case DSO__TYPE_32BIT:
+		dso = __dsos__find(&machine->dsos, DSO__NAME_VDSO32, true);
+		if (!dso) {
+			dso = __dsos__find(&machine->dsos, DSO__NAME_VDSO,
+					   true);
+			if (dso_type != dso__type(dso, machine))
+				dso = NULL;
+		}
+		break;
+	case DSO__TYPE_X32BIT:
+		dso = __dsos__find(&machine->dsos, DSO__NAME_VDSOX32, true);
+		break;
+	case DSO__TYPE_64BIT:
+	case DSO__TYPE_UNKNOWN:
+	default:
+		dso = __dsos__find(&machine->dsos, DSO__NAME_VDSO, true);
+		break;
+	}
+
+	return dso;
+}
+
 struct dso *machine__findnew_vdso(struct machine *machine,
-				  struct thread *thread __maybe_unused)
+				  struct thread *thread)
 {
 	struct vdso_info *vdso_info;
 	struct dso *dso = NULL;

@@ -297,6 +327,10 @@ struct dso *machine__findnew_vdso(struct machine *machine,
 	if (!vdso_info)
 		goto out_unlock;
 
+	dso = machine__find_vdso(machine, thread);
+	if (dso)
+		goto out_unlock;
+
 #if BITS_PER_LONG == 64
 	if (__machine__findnew_vdso_compat(machine, thread, vdso_info, &dso))
 		goto out_unlock;

index 7ba9fadb68af..b277984aaa93 100644
@@ -1135,10 +1135,10 @@ int machine__create_kernel_maps(struct machine *machine)
 {
 	struct dso *kernel = machine__get_kernel(machine);
 	const char *name;
-	u64 addr = machine__get_running_kernel_start(machine, &name);
+	u64 addr;
 	int ret;
 
-	if (!addr || kernel == NULL)
+	if (kernel == NULL)
 		return -1;
 
 	ret = __machine__create_kernel_maps(machine, kernel);

@@ -1160,8 +1160,9 @@ int machine__create_kernel_maps(struct machine *machine)
 	 */
 	map_groups__fixup_end(&machine->kmaps);
 
-	if (maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps, name,
-					     addr)) {
+	addr = machine__get_running_kernel_start(machine, &name);
+	if (!addr) {
+	} else if (maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps, name, addr)) {
 		machine__destroy_kernel_maps(machine);
 		return -1;
 	}

index 6e5c325148e4..e488ac756f39 100644
@@ -1160,6 +1160,24 @@ static int trace__tool_process(struct perf_tool *tool,
 	return trace__process_event(trace, machine, event, sample);
 }
 
+static char *trace__machine__resolve_kernel_addr(void *vmachine, unsigned long long *addrp, char **modp)
+{
+	struct machine *machine = vmachine;
+
+	if (machine->kptr_restrict_warned)
+		return NULL;
+
+	if (symbol_conf.kptr_restrict) {
+		pr_warning("Kernel address maps (/proc/{kallsyms,modules}) are restricted.\n\n"
+			   "Check /proc/sys/kernel/kptr_restrict.\n\n"
+			   "Kernel samples will not be resolved.\n");
+		machine->kptr_restrict_warned = true;
+		return NULL;
+	}
+
+	return machine__resolve_kernel_addr(vmachine, addrp, modp);
+}
+
 static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist)
 {
 	int err = symbol__init(NULL);

@@ -1171,7 +1189,7 @@ static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist)
 	if (trace->host == NULL)
 		return -ENOMEM;
 
-	if (trace_event__register_resolver(trace->host, machine__resolve_kernel_addr) < 0)
+	if (trace_event__register_resolver(trace->host, trace__machine__resolve_kernel_addr) < 0)
 		return -errno;
 
 	err = __machine__synthesize_threads(trace->host, &trace->tool, &trace->opts.target,

index b277984aaa93..bdc33ce40bdc 100644
@@ -43,6 +43,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 
 	machine->symbol_filter = NULL;
 	machine->id_hdr_size = 0;
+	machine->kptr_restrict_warned = false;
 	machine->comm_exec = false;
 	machine->kernel_start = 0;
 

index 83f46790c52f..41ac9cfd416b 100644
@@ -28,6 +28,7 @@ struct machine {
 	pid_t		  pid;
 	u16		  id_hdr_size;
 	bool		  comm_exec;
+	bool		  kptr_restrict_warned;
 	char		  *root_dir;
 	struct rb_root	  threads;
 	pthread_rwlock_t  threads_lock;

index 1793da585676..2a6cc254ad0c 100644
@@ -732,7 +732,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
 	if (machine__resolve(machine, &al, sample) < 0)
 		return;
 
-	if (!top->kptr_restrict_warned &&
+	if (!machine->kptr_restrict_warned &&
 	    symbol_conf.kptr_restrict &&
 	    al.cpumode == PERF_RECORD_MISC_KERNEL) {
 		ui__warning(

@@ -743,7 +743,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
 			  " modules" : "");
 		if (use_browser <= 0)
 			sleep(5);
-		top->kptr_restrict_warned = true;
+		machine->kptr_restrict_warned = true;
 	}
 
 	if (al.sym == NULL) {

@@ -759,7 +759,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
 		 * --hide-kernel-symbols, even if the user specifies an
 		 * invalid --vmlinux ;-)
 		 */
-		if (!top->kptr_restrict_warned && !top->vmlinux_warned &&
+		if (!machine->kptr_restrict_warned && !top->vmlinux_warned &&
 		    al.map == machine->vmlinux_maps[MAP__FUNCTION] &&
 		    RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION])) {
 			if (symbol_conf.vmlinux_name) {

index f92c37abb0a8..b2940c88734a 100644
@@ -27,7 +27,6 @@ struct perf_top {
 	int		   max_stack;
 	bool		   hide_kernel_symbols, hide_user_symbols, zero;
 	bool		   use_tui, use_stdio;
-	bool		   kptr_restrict_warned;
 	bool		   vmlinux_warned;
 	bool		   dump_symtab;
 	struct hist_entry  *sym_filter_entry;

index e488ac756f39..a2f3aa09c7f4 100644
@@ -1552,7 +1552,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 	if (sc->is_exit) {
 		if (!(trace->duration_filter || trace->summary_only || trace->min_stack)) {
 			trace__fprintf_entry_head(trace, thread, 1, sample->time, trace->output);
-			fprintf(trace->output, "%-70s\n", ttrace->entry_str);
+			fprintf(trace->output, "%-70s)\n", ttrace->entry_str);
 		}
 	} else {
 		ttrace->entry_pending = true;

index bdc33ce40bdc..205d27017361 100644
@@ -1771,11 +1771,6 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
 		 */
 		int mix_chain_nr = i + 1 + lbr_nr + 1;
 
-		if (mix_chain_nr > (int)sysctl_perf_event_max_stack + PERF_MAX_BRANCH_DEPTH) {
-			pr_warning("corrupted callchain. skipping...\n");
-			return 0;
-		}
-
 		for (j = 0; j < mix_chain_nr; j++) {
 			if (callchain_param.order == ORDER_CALLEE) {
 				if (j < i + 1)

@@ -1815,7 +1810,7 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 	struct ip_callchain *chain = sample->callchain;
 	int chain_nr = chain->nr;
 	u8 cpumode = PERF_RECORD_MISC_USER;
-	int i, j, err, nr_entries, nr_contexts;
+	int i, j, err, nr_entries;
 	int skip_idx = -1;
 	int first_call = 0;
 

@@ -1830,8 +1825,7 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 	 * Based on DWARF debug information, some architectures skip
 	 * a callchain entry saved by the kernel.
 	 */
-	if (chain_nr < sysctl_perf_event_max_stack)
-		skip_idx = arch_skip_callchain_idx(thread, chain);
+	skip_idx = arch_skip_callchain_idx(thread, chain);
 
 	/*
 	 * Add branches to call stack for easier browsing. This gives

@@ -1891,7 +1885,7 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 	}
 
 check_calls:
-	for (i = first_call, nr_entries = 0, nr_contexts = 0;
+	for (i = first_call, nr_entries = 0;
 	     i < chain_nr && nr_entries < max_stack; i++) {
 		u64 ip;
 

@@ -1906,13 +1900,8 @@ check_calls:
 #endif
 		ip = chain->ips[j];
 
-		if (ip >= PERF_CONTEXT_MAX) {
-			if (++nr_contexts > sysctl_perf_event_max_contexts_per_stack)
-				goto out_corrupted_callchain;
-		} else {
-			if (++nr_entries > sysctl_perf_event_max_stack)
-				goto out_corrupted_callchain;
-		}
+		if (ip < PERF_CONTEXT_MAX)
+                       ++nr_entries;
 
 		err = add_callchain_ip(thread, cursor, parent, root_al, &cpumode, ip);
 

@@ -1921,10 +1910,6 @@ check_calls:
 	}
 
 	return 0;
-
-out_corrupted_callchain:
-	pr_warning("corrupted callchain. skipping...\n");
-	return 0;
 }
 
 static int unwind_entry(struct unwind_entry *entry, void *arg)

index 87d40e3c4078..9bc71c6a54f6 100644
@@ -691,7 +691,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 			.ordered_events	 = true,
 			.ordering_requires_timestamps = true,
 		},
-		.max_stack		 = sysctl_perf_event_max_stack,
+		.max_stack		 = PERF_MAX_STACK_DEPTH,
 		.pretty_printing_style	 = "normal",
 		.socket_filter		 = -1,
 	};

index efca81679bb3..0a83f4bacc7c 100644
@@ -2067,8 +2067,6 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 		NULL
 	};
 
-	scripting_max_stack = sysctl_perf_event_max_stack;
-
 	setup_scripting();
 
 	argc = parse_options_subcommand(argc, argv, options, script_subcommands, script_usage,

index a2f3aa09c7f4..7401de71d097 100644
@@ -2905,7 +2905,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 		mmap_pages_user_set = false;
 
 	if (trace.max_stack == UINT_MAX) {
-		trace.max_stack = sysctl_perf_event_max_stack;
+		trace.max_stack = input_name ? PERF_MAX_STACK_DEPTH : sysctl_perf_event_max_stack;
 		max_stack_user_set = false;
 	}
 

index 8d96c80cc67e..c9a6dc173e74 100644
@@ -298,8 +298,7 @@ static struct call_path *call_path_from_sample(struct db_export *dbe,
 	 */
 	callchain_param.order = ORDER_CALLER;
 	err = thread__resolve_callchain(thread, &callchain_cursor, evsel,
-					sample, NULL, NULL,
-					sysctl_perf_event_max_stack);
+					sample, NULL, NULL, PERF_MAX_STACK_DEPTH);
 	if (err) {
 		callchain_param.order = saved_order;
 		return NULL;

index 62c7f6988e0e..5d1eb1ccd96c 100644
@@ -264,8 +264,7 @@ static SV *perl_process_callchain(struct perf_sample *sample,
 		goto exit;
 
 	if (thread__resolve_callchain(al->thread, &callchain_cursor, evsel,
-				      sample, NULL, NULL,
-				      sysctl_perf_event_max_stack) != 0) {
+				      sample, NULL, NULL, scripting_max_stack) != 0) {
 		pr_err("Failed to resolve callchain. Skipping\n");
 		goto exit;
 	}

index b811924e5e1b..3d9f2ca2ed2d 100644
@@ -372,8 +372,8 @@ static struct ins instructions[] = {
 	{ .name = "bgt",   .ops  = &jump_ops, },
 	{ .name = "bhi",   .ops  = &jump_ops, },
 	{ .name = "bl",    .ops  = &call_ops, },
-	{ .name = "blt",   .ops  = &jump_ops, },
 	{ .name = "bls",   .ops  = &jump_ops, },
+	{ .name = "blt",   .ops  = &jump_ops, },
 	{ .name = "blx",   .ops  = &call_ops, },
 	{ .name = "bne",   .ops  = &jump_ops, },
 #endif

index 3d9f2ca2ed2d..7e5a1e8874ce 100644
@@ -354,9 +354,6 @@ static struct ins_ops nop_ops = {
 	.scnprintf = nop__scnprintf,
 };
 
-/*
- * Must be sorted by name!
- */
 static struct ins instructions[] = {
 	{ .name = "add",   .ops  = &mov_ops, },
 	{ .name = "addl",  .ops  = &mov_ops, },

@@ -449,18 +446,39 @@ static struct ins instructions[] = {
 	{ .name = "xbeginq", .ops  = &jump_ops, },
 };
 
-static int ins__cmp(const void *name, const void *insp)
+static int ins__key_cmp(const void *name, const void *insp)
 {
 	const struct ins *ins = insp;
 
 	return strcmp(name, ins->name);
 }
 
+static int ins__cmp(const void *a, const void *b)
+{
+	const struct ins *ia = a;
+	const struct ins *ib = b;
+
+	return strcmp(ia->name, ib->name);
+}
+
+static void ins__sort(void)
+{
+	const int nmemb = ARRAY_SIZE(instructions);
+
+	qsort(instructions, nmemb, sizeof(struct ins), ins__cmp);
+}
+
 static struct ins *ins__find(const char *name)
 {
 	const int nmemb = ARRAY_SIZE(instructions);
+	static bool sorted;
+
+	if (!sorted) {
+		ins__sort();
+		sorted = true;
+	}
 
-	return bsearch(name, instructions, nmemb, sizeof(struct ins), ins__cmp);
+	return bsearch(name, instructions, nmemb, sizeof(struct ins), ins__key_cmp);
 }
 
 int symbol__annotate_init(struct map *map __maybe_unused, struct symbol *sym)

index 7401de71d097..487c10401d46 100644
@@ -2910,7 +2910,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 	}
 
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
-	if ((trace.min_stack || max_stack_user_set) && !callchain_param.enabled)
+	if ((trace.min_stack || max_stack_user_set) && !callchain_param.enabled && trace.trace_syscalls)
 		record_opts__parse_callchain(&trace.opts, &callchain_param, "dwarf", false);
 #endif
 

index 814158393656..25c81734a950 100644
@@ -324,8 +324,9 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_BOOLEAN(0, "skip-missing", &annotate.skip_missing,
 		    "Skip symbols that cannot be annotated"),
 	OPT_STRING('C', "cpu", &annotate.cpu_list, "cpu", "list of cpus to profile"),
-	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
-		   "Look for files with symbols relative to this directory"),
+	OPT_CALLBACK(0, "symfs", NULL, "directory",
+		     "Look for files with symbols relative to this directory",
+		     symbol__config_symfs),
 	OPT_BOOLEAN(0, "source", &symbol_conf.annotate_src,
 		    "Interleave source code with assembly code (default)"),
 	OPT_BOOLEAN(0, "asm-raw", &symbol_conf.annotate_asm_raw,

index 9ce354f469dc..f7645a42708e 100644
@@ -812,8 +812,9 @@ static const struct option options[] = {
 	OPT_STRING_NOEMPTY('t', "field-separator", &symbol_conf.field_sep, "separator",
 		   "separator for columns, no spaces will be added between "
 		   "columns '.' is reserved."),
-	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
-		    "Look for files with symbols relative to this directory"),
+	OPT_CALLBACK(0, "symfs", NULL, "directory",
+		     "Look for files with symbols relative to this directory",
+		     symbol__config_symfs),
 	OPT_UINTEGER('o', "order", &sort_compute, "Specify compute sorting."),
 	OPT_CALLBACK(0, "percentage", NULL, "relative|absolute",
 		     "How to display percentage of filtered entries", parse_filter_percentage),

index 9bc71c6a54f6..a87cb338bdf1 100644
@@ -770,8 +770,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 		   "columns '.' is reserved."),
 	OPT_BOOLEAN('U', "hide-unresolved", &symbol_conf.hide_unresolved,
 		    "Only display entries resolved to a symbol"),
-	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
-		    "Look for files with symbols relative to this directory"),
+	OPT_CALLBACK(0, "symfs", NULL, "directory",
+		     "Look for files with symbols relative to this directory",
+		     symbol__config_symfs),
 	OPT_STRING('C', "cpu", &report.cpu_list, "cpu",
 		   "list of cpus to profile"),
 	OPT_BOOLEAN('I', "show-info", &report.show_full_info,

index 0a83f4bacc7c..e3ce2f34d3ad 100644
@@ -2010,8 +2010,9 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 		   "file", "kallsyms pathname"),
 	OPT_BOOLEAN('G', "hide-call-graph", &no_callchain,
 		    "When printing symbols do not display call chain"),
-	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
-		    "Look for files with symbols relative to this directory"),
+	OPT_CALLBACK(0, "symfs", NULL, "directory",
+		     "Look for files with symbols relative to this directory",
+		     symbol__config_symfs),
 	OPT_CALLBACK('F', "fields", NULL, "str",
 		     "comma separated output fields prepend with 'type:'. "
 		     "Valid types: hw,sw,trace,raw. "

index 40cc9bb3506c..733a55422d03 100644
@@ -1945,8 +1945,9 @@ int cmd_timechart(int argc, const char **argv,
 	OPT_CALLBACK('p', "process", NULL, "process",
 		      "process selector. Pass a pid or process name.",
 		       parse_process),
-	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
-		    "Look for files with symbols relative to this directory"),
+	OPT_CALLBACK(0, "symfs", NULL, "directory",
+		     "Look for files with symbols relative to this directory",
+		     symbol__config_symfs),
 	OPT_INTEGER('n', "proc-num", &tchart.proc_num,
 		    "min. number of tasks to print"),
 	OPT_BOOLEAN('t', "topology", &tchart.topology,

index 75b75615e2f8..5d286f5d7906 100644
@@ -63,9 +63,7 @@ int dso__read_binary_type_filename(const struct dso *dso,
 		}
 		break;
 	case DSO_BINARY_TYPE__BUILD_ID_CACHE:
-		/* skip the locally configured cache if a symfs is given */
-		if (symbol_conf.symfs[0] ||
-		    (dso__build_id_filename(dso, filename, size) == NULL))
+		if (dso__build_id_filename(dso, filename, size) == NULL)
 			ret = -1;
 		break;
 

index 2252b545ff43..20f9cb32b703 100644
@@ -2033,3 +2033,26 @@ void symbol__exit(void)
 	symbol_conf.sym_list = symbol_conf.dso_list = symbol_conf.comm_list = NULL;
 	symbol_conf.initialized = false;
 }
+
+int symbol__config_symfs(const struct option *opt __maybe_unused,
+			 const char *dir, int unset __maybe_unused)
+{
+	char *bf = NULL;
+	int ret;
+
+	symbol_conf.symfs = strdup(dir);
+	if (symbol_conf.symfs == NULL)
+		return -ENOMEM;
+
+	/* skip the locally configured cache if a symfs is given, and
+	 * config buildid dir to symfs/.debug
+	 */
+	ret = asprintf(&bf, "%s/%s", dir, ".debug");
+	if (ret < 0)
+		return -ENOMEM;
+
+	set_buildid_dir(bf);
+
+	free(bf);
+	return 0;
+}

index 25f2fd672c2e..fa415347dbf9 100644
@@ -290,6 +290,8 @@ bool symbol_type__is_a(char symbol_type, enum map_type map_type);
 bool symbol__restricted_filename(const char *filename,
 				 const char *restricted_filename);
 bool symbol__is_idle(struct symbol *sym);
+int symbol__config_symfs(const struct option *opt __maybe_unused,
+			 const char *dir, int unset __maybe_unused);
 
 int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 		  struct symsrc *runtime_ss, symbol_filter_t filter,

index 8f81c415723d..3a9321f83d00 100644
@@ -293,12 +293,12 @@ static struct dso *machine__find_vdso(struct machine *machine,
 	switch (dso_type) {
 	case DSO__TYPE_32BIT:
 		dso = __dsos__find(&machine->dsos, DSO__NAME_VDSO32, true);
-		if (!dso) {
-			dso = __dsos__find(&machine->dsos, DSO__NAME_VDSO,
-					   true);
-			if (dso_type != dso__type(dso, machine))
-				dso = NULL;
-		}
+		if (dso)
+			break;
+
+		dso = __dsos__find(&machine->dsos, DSO__NAME_VDSO, true);
+		if (dso && dso_type != dso__type(dso, machine))
+			dso = NULL;
 		break;
 	case DSO__TYPE_X32BIT:
 		dso = __dsos__find(&machine->dsos, DSO__NAME_VDSOX32, true);