Merge tag 'perf-tools-fixes-2020-07-07' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tooling fixes from Arnaldo Carvalho de Melo:

 - Intel PT fixes for PEBS-via-PT with registers

 - Fixes for Intel PT python based GUI

 - Avoid duplicated sideband events with Intel PT in system wide tracing

 - Remove needless 'dummy' event from TUI menu, used when synthesizing
   meta data events for pre-existing processes

 - Fix corner case segfault when pressing enter in a screen without
   entries in the TUI for report/top

 - Fixes for time stamp handling in libtraceevent

 - Explicitly set utf-8 encoding in perf flamegraph

 - Update arch/x86/lib/memcpy_64.S copy used in 'perf bench mem memcpy',
   silencing perf build warning

* tag 'perf-tools-fixes-2020-07-07' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux:
  perf report TUI: Remove needless 'dummy' event from menu
  perf intel-pt: Fix PEBS sample for XMM registers
  perf intel-pt: Fix displaying PEBS-via-PT with registers
  perf intel-pt: Fix recording PEBS-via-PT with registers
  perf report TUI: Fix segmentation fault in perf_evsel__hists_browse()
  tools lib traceevent: Add proper KBUFFER_TYPE_TIME_STAMP handling
  tools lib traceevent: Add API to read time information from kbuffer
  perf scripts python: exported-sql-viewer.py: Fix time chart call tree
  perf scripts python: exported-sql-viewer.py: Fix zero id in call tree 'Find' result
  perf scripts python: exported-sql-viewer.py: Fix zero id in call graph 'Find' result
  perf scripts python: exported-sql-viewer.py: Fix unexpanded 'Find' result
  perf record: Fix duplicated sideband events with Intel PT system wide tracing
  perf scripts python: export-to-postgresql.py: Fix struct.pack() int argument
  tools arch: Update arch/x86/lib/memcpy_64.S copy used in 'perf bench mem memcpy'
  perf flamegraph: Explicitly set utf-8 encoding

tools/arch/x86/lib/memcpy_64.S

@@ -8,6 +8,8 @@
 #include <asm/alternative-asm.h>
 #include <asm/export.h>
 
+.pushsection .noinstr.text, "ax"
+
 /*
  * We build a jump to memcpy_orig by default which gets NOPped out on
  * the majority of x86 CPUs which set REP_GOOD. In addition, CPUs which
@@ -184,6 +186,8 @@ SYM_FUNC_START(memcpy_orig)
 	retq
 SYM_FUNC_END(memcpy_orig)
 
+.popsection
+
 #ifndef CONFIG_UML
 
 MCSAFE_TEST_CTL

tools/lib/traceevent/kbuffer-parse.c

@@ -361,6 +361,7 @@ translate_data(struct kbuffer *kbuf, void *data, void **rptr,
 		break;
 
 	case KBUFFER_TYPE_TIME_EXTEND:
+	case KBUFFER_TYPE_TIME_STAMP:
 		extend = read_4(kbuf, data);
 		data += 4;
 		extend <<= TS_SHIFT;
@@ -369,10 +370,6 @@ translate_data(struct kbuffer *kbuf, void *data, void **rptr,
 		*length = 0;
 		break;
 
-	case KBUFFER_TYPE_TIME_STAMP:
-		data += 12;
-		*length = 0;
-		break;
 	case 0:
 		*length = read_4(kbuf, data) - 4;
 		*length = (*length + 3) & ~3;
@@ -397,7 +394,11 @@ static unsigned int update_pointers(struct kbuffer *kbuf)
 
 	type_len = translate_data(kbuf, ptr, &ptr, &delta, &length);
 
-	kbuf->timestamp += delta;
+	if (type_len == KBUFFER_TYPE_TIME_STAMP)
+		kbuf->timestamp = delta;
+	else
+		kbuf->timestamp += delta;
+
 	kbuf->index = calc_index(kbuf, ptr);
 	kbuf->next = kbuf->index + length;
 
@@ -454,7 +455,9 @@ static int __next_event(struct kbuffer *kbuf)
 		if (kbuf->next >= kbuf->size)
 			return -1;
 		type = update_pointers(kbuf);
-	} while (type == KBUFFER_TYPE_TIME_EXTEND || type == KBUFFER_TYPE_PADDING);
+	} while (type == KBUFFER_TYPE_TIME_EXTEND ||
+		 type == KBUFFER_TYPE_TIME_STAMP ||
+		 type == KBUFFER_TYPE_PADDING);
 
 	return 0;
 }
@@ -546,6 +549,34 @@ int kbuffer_load_subbuffer(struct kbuffer *kbuf, void *subbuffer)
 	return 0;
 }
 
+/**
+ * kbuffer_subbuf_timestamp - read the timestamp from a sub buffer
+ * @kbuf:      The kbuffer to load
+ * @subbuf:    The subbuffer to read from.
+ *
+ * Return the timestamp from a subbuffer.
+ */
+unsigned long long kbuffer_subbuf_timestamp(struct kbuffer *kbuf, void *subbuf)
+{
+	return kbuf->read_8(subbuf);
+}
+
+/**
+ * kbuffer_ptr_delta - read the delta field from a record
+ * @kbuf:      The kbuffer to load
+ * @ptr:       The record in the buffe.
+ *
+ * Return the timestamp delta from a record
+ */
+unsigned int kbuffer_ptr_delta(struct kbuffer *kbuf, void *ptr)
+{
+	unsigned int type_len_ts;
+
+	type_len_ts = read_4(kbuf, ptr);
+	return ts4host(kbuf, type_len_ts);
+}
+
+
 /**
  * kbuffer_read_event - read the next event in the kbuffer subbuffer
  * @kbuf:	The kbuffer to read from

tools/lib/traceevent/kbuffer.h

@@ -49,6 +49,8 @@ int kbuffer_load_subbuffer(struct kbuffer *kbuf, void *subbuffer);
 void *kbuffer_read_event(struct kbuffer *kbuf, unsigned long long *ts);
 void *kbuffer_next_event(struct kbuffer *kbuf, unsigned long long *ts);
 unsigned long long kbuffer_timestamp(struct kbuffer *kbuf);
+unsigned long long kbuffer_subbuf_timestamp(struct kbuffer *kbuf, void *subbuf);
+unsigned int kbuffer_ptr_delta(struct kbuffer *kbuf, void *ptr);
 
 void *kbuffer_translate_data(int swap, void *data, unsigned int *size);
 

tools/perf/arch/x86/util/intel-pt.c

@@ -641,6 +641,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 			}
 			evsel->core.attr.freq = 0;
 			evsel->core.attr.sample_period = 1;
+			evsel->no_aux_samples = true;
 			intel_pt_evsel = evsel;
 			opts->full_auxtrace = true;
 		}

tools/perf/builtin-record.c

@@ -852,20 +852,20 @@ static int record__open(struct record *rec)
 	 * event synthesis.
 	 */
 	if (opts->initial_delay || target__has_cpu(&opts->target)) {
-		if (perf_evlist__add_dummy(evlist))
-			return -ENOMEM;
+		pos = perf_evlist__get_tracking_event(evlist);
+		if (!evsel__is_dummy_event(pos)) {
+			/* Set up dummy event. */
+			if (perf_evlist__add_dummy(evlist))
+				return -ENOMEM;
+			pos = evlist__last(evlist);
+			perf_evlist__set_tracking_event(evlist, pos);
+		}
 
-		/* Disable tracking of mmaps on lead event. */
-		pos = evlist__first(evlist);
-		pos->tracking = 0;
-		/* Set up dummy event. */
-		pos = evlist__last(evlist);
-		pos->tracking = 1;
 		/*
 		 * Enable the dummy event when the process is forked for
 		 * initial_delay, immediately for system wide.
 		 */
-		if (opts->initial_delay)
+		if (opts->initial_delay && !pos->immediate)
 			pos->core.attr.enable_on_exec = 1;
 		else
 			pos->immediate = 1;

tools/perf/builtin-script.c

@@ -462,7 +462,7 @@ static int perf_evsel__check_attr(struct evsel *evsel, struct perf_session *sess
 		return -EINVAL;
 
 	if (PRINT_FIELD(IREGS) &&
-	    evsel__check_stype(evsel, PERF_SAMPLE_REGS_INTR, "IREGS", PERF_OUTPUT_IREGS))
+	    evsel__do_check_stype(evsel, PERF_SAMPLE_REGS_INTR, "IREGS", PERF_OUTPUT_IREGS, allow_user_set))
 		return -EINVAL;
 
 	if (PRINT_FIELD(UREGS) &&

tools/perf/scripts/python/export-to-postgresql.py

@@ -1055,7 +1055,7 @@ def cbr(id, raw_buf):
 	cbr = data[0]
 	MHz = (data[4] + 500) / 1000
 	percent = ((cbr * 1000 / data[2]) + 5) / 10
-	value = struct.pack("!hiqiiiiii", 4, 8, id, 4, cbr, 4, MHz, 4, percent)
+	value = struct.pack("!hiqiiiiii", 4, 8, id, 4, cbr, 4, int(MHz), 4, int(percent))
 	cbr_file.write(value)
 
 def mwait(id, raw_buf):

tools/perf/scripts/python/exported-sql-viewer.py

@@ -768,7 +768,8 @@ class CallGraphModel(CallGraphModelBase):
 						" FROM calls"
 						" INNER JOIN call_paths ON calls.call_path_id = call_paths.id"
 						" INNER JOIN symbols ON call_paths.symbol_id = symbols.id"
-						" WHERE symbols.name" + match +
+						" WHERE calls.id <> 0"
+						" AND symbols.name" + match +
 						" GROUP BY comm_id, thread_id, call_path_id"
 						" ORDER BY comm_id, thread_id, call_path_id")
 
@@ -963,7 +964,8 @@ class CallTreeModel(CallGraphModelBase):
 						" FROM calls"
 						" INNER JOIN call_paths ON calls.call_path_id = call_paths.id"
 						" INNER JOIN symbols ON call_paths.symbol_id = symbols.id"
-						" WHERE symbols.name" + match +
+						" WHERE calls.id <> 0"
+						" AND symbols.name" + match +
 						" ORDER BY comm_id, thread_id, call_time, calls.id")
 
 	def FindPath(self, query):
@@ -1050,6 +1052,7 @@ class TreeWindowBase(QMdiSubWindow):
 				child = self.model.index(row, 0, parent)
 				if child.internalPointer().dbid == dbid:
 					found = True
+					self.view.setExpanded(parent, True)
 					self.view.setCurrentIndex(child)
 					parent = child
 					break
@@ -1127,6 +1130,7 @@ class CallTreeWindow(TreeWindowBase):
 				child = self.model.index(row, 0, parent)
 				if child.internalPointer().dbid == dbid:
 					found = True
+					self.view.setExpanded(parent, True)
 					self.view.setCurrentIndex(child)
 					parent = child
 					break
@@ -1139,6 +1143,7 @@ class CallTreeWindow(TreeWindowBase):
 				return
 			last_child = None
 			for row in xrange(n):
+				self.view.setExpanded(parent, True)
 				child = self.model.index(row, 0, parent)
 				child_call_time = child.internalPointer().call_time
 				if child_call_time < time:
@@ -1151,9 +1156,11 @@ class CallTreeWindow(TreeWindowBase):
 			if not last_child:
 				if not found:
 					child = self.model.index(0, 0, parent)
+					self.view.setExpanded(parent, True)
 					self.view.setCurrentIndex(child)
 				return
 			found = True
+			self.view.setExpanded(parent, True)
 			self.view.setCurrentIndex(last_child)
 			parent = last_child
 

tools/perf/scripts/python/flamegraph.py

@@ -17,6 +17,7 @@
 from __future__ import print_function
 import sys
 import os
+import io
 import argparse
 import json
 
@@ -81,7 +82,7 @@ class FlameGraphCLI:
 
         if self.args.format == "html":
             try:
-                with open(self.args.template) as f:
+                with io.open(self.args.template, encoding="utf-8") as f:
                     output_str = f.read().replace("/** @flamegraph_json **/",
                                                   json_str)
             except IOError as e:
@@ -93,11 +94,12 @@ class FlameGraphCLI:
             output_fn = self.args.output or "stacks.json"
 
         if output_fn == "-":
-            sys.stdout.write(output_str)
+            with io.open(sys.stdout.fileno(), "w", encoding="utf-8", closefd=False) as out:
+                out.write(output_str)
         else:
             print("dumping data to {}".format(output_fn))
             try:
-                with open(output_fn, "w") as out:
+                with io.open(output_fn, "w", encoding="utf-8") as out:
                     out.write(output_str)
             except IOError as e:
                 print("Error writing output file: {}".format(e), file=sys.stderr)

tools/perf/ui/browsers/hists.c

@@ -2288,6 +2288,11 @@ static struct thread *hist_browser__selected_thread(struct hist_browser *browser
 	return browser->he_selection->thread;
 }
 
+static struct res_sample *hist_browser__selected_res_sample(struct hist_browser *browser)
+{
+	return browser->he_selection ? browser->he_selection->res_samples : NULL;
+}
+
 /* Check whether the browser is for 'top' or 'report' */
 static inline bool is_report_browser(void *timer)
 {
@@ -3357,16 +3362,16 @@ static int perf_evsel__hists_browse(struct evsel *evsel, int nr_events,
 					     &options[nr_options], NULL, NULL, evsel);
 		nr_options += add_res_sample_opt(browser, &actions[nr_options],
 						 &options[nr_options],
-				 hist_browser__selected_entry(browser)->res_samples,
-				 evsel, A_NORMAL);
+						 hist_browser__selected_res_sample(browser),
+						 evsel, A_NORMAL);
 		nr_options += add_res_sample_opt(browser, &actions[nr_options],
 						 &options[nr_options],
-				 hist_browser__selected_entry(browser)->res_samples,
-				 evsel, A_ASM);
+						 hist_browser__selected_res_sample(browser),
+						 evsel, A_ASM);
 		nr_options += add_res_sample_opt(browser, &actions[nr_options],
 						 &options[nr_options],
-				 hist_browser__selected_entry(browser)->res_samples,
-				 evsel, A_SOURCE);
+						 hist_browser__selected_res_sample(browser),
+						 evsel, A_SOURCE);
 		nr_options += add_switch_opt(browser, &actions[nr_options],
 					     &options[nr_options]);
 skip_scripting:
@@ -3598,6 +3603,23 @@ static int __perf_evlist__tui_browse_hists(struct evlist *evlist,
 				    hbt, warn_lost_event);
 }
 
+static bool perf_evlist__single_entry(struct evlist *evlist)
+{
+	int nr_entries = evlist->core.nr_entries;
+
+	if (nr_entries == 1)
+	       return true;
+
+	if (nr_entries == 2) {
+		struct evsel *last = evlist__last(evlist);
+
+		if (evsel__is_dummy_event(last))
+			return true;
+	}
+
+	return false;
+}
+
 int perf_evlist__tui_browse_hists(struct evlist *evlist, const char *help,
 				  struct hist_browser_timer *hbt,
 				  float min_pcnt,
@@ -3608,7 +3630,7 @@ int perf_evlist__tui_browse_hists(struct evlist *evlist, const char *help,
 	int nr_entries = evlist->core.nr_entries;
 
 single_entry:
-	if (nr_entries == 1) {
+	if (perf_evlist__single_entry(evlist)) {
 		struct evsel *first = evlist__first(evlist);
 
 		return perf_evsel__hists_browse(first, nr_entries, help,

tools/perf/util/evlist.c

@@ -1566,6 +1566,18 @@ void perf_evlist__to_front(struct evlist *evlist,
 	list_splice(&move, &evlist->core.entries);
 }
 
+struct evsel *perf_evlist__get_tracking_event(struct evlist *evlist)
+{
+	struct evsel *evsel;
+
+	evlist__for_each_entry(evlist, evsel) {
+		if (evsel->tracking)
+			return evsel;
+	}
+
+	return evlist__first(evlist);
+}
+
 void perf_evlist__set_tracking_event(struct evlist *evlist,
 				     struct evsel *tracking_evsel)
 {

tools/perf/util/evlist.h

@@ -335,6 +335,7 @@ void perf_evlist__to_front(struct evlist *evlist,
 	evlist__cpu_iter_start(evlist);			\
 	perf_cpu_map__for_each_cpu (cpu, index, (evlist)->core.all_cpus)
 
+struct evsel *perf_evlist__get_tracking_event(struct evlist *evlist);
 void perf_evlist__set_tracking_event(struct evlist *evlist,
 				     struct evsel *tracking_evsel);
 

tools/perf/util/evsel.c

@@ -898,12 +898,6 @@ static void evsel__apply_config_terms(struct evsel *evsel,
 	}
 }
 
-static bool is_dummy_event(struct evsel *evsel)
-{
-	return (evsel->core.attr.type == PERF_TYPE_SOFTWARE) &&
-	       (evsel->core.attr.config == PERF_COUNT_SW_DUMMY);
-}
-
 struct evsel_config_term *__evsel__get_config_term(struct evsel *evsel, enum evsel_term_type type)
 {
 	struct evsel_config_term *term, *found_term = NULL;
@@ -1020,12 +1014,12 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts,
 	if (callchain && callchain->enabled && !evsel->no_aux_samples)
 		evsel__config_callchain(evsel, opts, callchain);
 
-	if (opts->sample_intr_regs) {
+	if (opts->sample_intr_regs && !evsel->no_aux_samples) {
 		attr->sample_regs_intr = opts->sample_intr_regs;
 		evsel__set_sample_bit(evsel, REGS_INTR);
 	}
 
-	if (opts->sample_user_regs) {
+	if (opts->sample_user_regs && !evsel->no_aux_samples) {
 		attr->sample_regs_user |= opts->sample_user_regs;
 		evsel__set_sample_bit(evsel, REGS_USER);
 	}
@@ -1161,7 +1155,7 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts,
 	 * The software event will trigger -EOPNOTSUPP error out,
 	 * if BRANCH_STACK bit is set.
 	 */
-	if (is_dummy_event(evsel))
+	if (evsel__is_dummy_event(evsel))
 		evsel__reset_sample_bit(evsel, BRANCH_STACK);
 }
 

tools/perf/util/evsel.h

@@ -399,6 +399,12 @@ static inline bool evsel__has_br_stack(const struct evsel *evsel)
 	       evsel->synth_sample_type & PERF_SAMPLE_BRANCH_STACK;
 }
 
+static inline bool evsel__is_dummy_event(struct evsel *evsel)
+{
+	return (evsel->core.attr.type == PERF_TYPE_SOFTWARE) &&
+	       (evsel->core.attr.config == PERF_COUNT_SW_DUMMY);
+}
+
 struct perf_env *evsel__env(struct evsel *evsel);
 
 int evsel__store_ids(struct evsel *evsel, struct evlist *evlist);

tools/perf/util/intel-pt.c

@@ -1735,6 +1735,7 @@ static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq)
 	u64 sample_type = evsel->core.attr.sample_type;
 	u64 id = evsel->core.id[0];
 	u8 cpumode;
+	u64 regs[8 * sizeof(sample.intr_regs.mask)];
 
 	if (intel_pt_skip_event(pt))
 		return 0;
@@ -1784,8 +1785,8 @@ static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq)
 	}
 
 	if (sample_type & PERF_SAMPLE_REGS_INTR &&
-	    items->mask[INTEL_PT_GP_REGS_POS]) {
-		u64 regs[sizeof(sample.intr_regs.mask)];
+	    (items->mask[INTEL_PT_GP_REGS_POS] ||
+	     items->mask[INTEL_PT_XMM_POS])) {
 		u64 regs_mask = evsel->core.attr.sample_regs_intr;
 		u64 *pos;