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

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

 User visible changes:

  * Add a visual cue for toggle zeroing of samples in 'perf top' (Taeung Song)

  * Fix for double free in 'perf stat' when using some specific invalid
    command line combo (Yasser Shalabi)

 Infrastructure changes:

  * Add option to copy events when queuing for sorting across cpu buffers
    and enable it for 'perf kvm stat live', to avoid having events left
    in the queue pointing to the ring buffer be rewritten in high volume
    sessions.  (Alexander Yarygin, improving work done by David Ahern):

  * Document sysfs events/ interfaces (Cody P Schafer)

  * Add support to new style format of kernel PMU event. (Kan Liang)

  * Fix typos in perf/Documentation (Masanari Iida)

  * Improve callchains when using libunwind (Namhyung Kim)

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

Author: Ingo Molnar

Documentation/ABI/testing/sysfs-bus-event_source-devices-events

@@ -196,10 +196,10 @@ If specified the 'Weighted diff' column is displayed with value 'd' computed as:
 
   - period being the hist entry period value
 
-  - WEIGHT-A/WEIGHT-B being user suplied weights in the the '-c' option
+  - WEIGHT-A/WEIGHT-B being user supplied weights in the the '-c' option
     behind ':' separator like '-c wdiff:1,2'.
-    - WIEGHT-A being the weight of the data file
-    - WIEGHT-B being the weight of the baseline data file
+    - WEIGHT-A being the weight of the data file
+    - WEIGHT-B being the weight of the baseline data file
 
 SEE ALSO
 --------

tools/perf/Documentation/perf-diff.txt

@@ -100,7 +100,7 @@ OPTIONS
 STAT REPORT OPTIONS
 -------------------
 --vcpu=<value>::
-       analyze events which occures on this vcpu. (default: all vcpus)
+       analyze events which occur on this vcpu. (default: all vcpus)
 
 --event=<value>::
        event to be analyzed. Possible values: vmexit, mmio (x86 only),
@@ -134,7 +134,7 @@ STAT LIVE OPTIONS
     Analyze events only for given process ID(s) (comma separated list).
 
 --vcpu=<value>::
-       analyze events which occures on this vcpu. (default: all vcpus)
+       analyze events which occur on this vcpu. (default: all vcpus)
 
 
 --event=<value>::

tools/perf/Documentation/perf-kvm.txt

@@ -19,7 +19,7 @@ various perf commands with the -e option.
 EVENT MODIFIERS
 ---------------
 
-Events can optionally have a modifer by appending a colon and one or
+Events can optionally have a modifier by appending a colon and one or
 more modifiers. Modifiers allow the user to restrict the events to be
 counted. The following modifiers exist:
 

tools/perf/Documentation/perf-list.txt

@@ -146,7 +146,7 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
 
 -N::
 --no-buildid-cache::
-Do not update the builid cache. This saves some overhead in situations
+Do not update the buildid cache. This saves some overhead in situations
 where the information in the perf.data file (which includes buildids)
 is sufficient.
 

tools/perf/Documentation/perf-record.txt

@@ -181,8 +181,8 @@ strings for flag and symbolic fields.  These correspond to the strings
 and values parsed from the 'print fmt' fields of the event format
 files:
 
-  flag_str($event_name, $field_name, $field_value) - returns the string represention corresponding to $field_value for the flag field $field_name of event $event_name
-  symbol_str($event_name, $field_name, $field_value) - returns the string represention corresponding to $field_value for the symbolic field $field_name of event $event_name
+  flag_str($event_name, $field_name, $field_value) - returns the string representation corresponding to $field_value for the flag field $field_name of event $event_name
+  symbol_str($event_name, $field_name, $field_value) - returns the string representation corresponding to $field_value for the symbolic field $field_name of event $event_name
 
 Perf::Trace::Context Module
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~

tools/perf/Documentation/perf-script-perl.txt

@@ -263,7 +263,7 @@ and having the counts we've tallied as values.
 
 The print_syscall_totals() function iterates over the entries in the
 dictionary and displays a line for each entry containing the syscall
-name (the dictonary keys contain the syscall ids, which are passed to
+name (the dictionary keys contain the syscall ids, which are passed to
 the Util function syscall_name(), which translates the raw syscall
 numbers to the corresponding syscall name strings).  The output is
 displayed after all the events in the trace have been processed, by
@@ -576,8 +576,8 @@ strings for flag and symbolic fields.  These correspond to the strings
 and values parsed from the 'print fmt' fields of the event format
 files:
 
-  flag_str(event_name, field_name, field_value) - returns the string represention corresponding to field_value for the flag field field_name of event event_name
-  symbol_str(event_name, field_name, field_value) - returns the string represention corresponding to field_value for the symbolic field field_name of event event_name
+  flag_str(event_name, field_name, field_value) - returns the string representation corresponding to field_value for the flag field field_name of event event_name
+  symbol_str(event_name, field_name, field_value) - returns the string representation corresponding to field_value for the symbolic field field_name of event event_name
 
 The *autodict* function returns a special kind of Python
 dictionary that implements Perl's 'autovivifying' hashes in Python

tools/perf/Documentation/perf-script-python.txt

@@ -140,7 +140,7 @@ OPTIONS
 
 		"Overriding previous field request for all events."
 
-	Alternativey, consider the order:
+	Alternatively, consider the order:
 
 		-f comm,tid,time,ip,sym -f trace:
 

tools/perf/Documentation/perf-script.txt

@@ -25,7 +25,7 @@ OPTIONS
 -------
 -s::
 --skip::
-	Tests to skip (comma separater numeric list).
+	Tests to skip (comma separated numeric list).
 
 -v::
 --verbose::

tools/perf/Documentation/perf-test.txt

@@ -20,7 +20,7 @@ scheduling events, etc.
 This is a live mode tool in addition to working with perf.data files like
 the other perf tools. Files can be generated using the 'perf record' command
 but the session needs to include the raw_syscalls events (-e 'raw_syscalls:*').
-Alernatively, the 'perf trace record' can be used as a shortcut to
+Alternatively, 'perf trace record' can be used as a shortcut to
 automatically include the raw_syscalls events when writing events to a file.
 
 The following options apply to perf trace; options to perf trace record are

tools/perf/Documentation/perf-trace.txt

@@ -376,7 +376,7 @@ struct vcpu_event_record *per_vcpu_record(struct thread *thread,
 					  struct perf_sample *sample)
 {
 	/* Only kvm_entry records vcpu id. */
-	if (!thread->priv && kvm_entry_event(evsel)) {
+	if (!thread__priv(thread) && kvm_entry_event(evsel)) {
 		struct vcpu_event_record *vcpu_record;
 
 		vcpu_record = zalloc(sizeof(*vcpu_record));
@@ -386,10 +386,10 @@ struct vcpu_event_record *per_vcpu_record(struct thread *thread,
 		}
 
 		vcpu_record->vcpu_id = perf_evsel__intval(evsel, sample, VCPU_ID);
-		thread->priv = vcpu_record;
+		thread__set_priv(thread, vcpu_record);
 	}
 
-	return thread->priv;
+	return thread__priv(thread);
 }
 
 static bool handle_kvm_event(struct perf_kvm_stat *kvm,
@@ -1358,6 +1358,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
 	}
 	kvm->session->evlist = kvm->evlist;
 	perf_session__set_id_hdr_size(kvm->session);
+	ordered_events__set_copy_on_queue(&kvm->session->ordered_events, true);
 	machine__synthesize_threads(&kvm->session->machines.host, &kvm->opts.target,
 				    kvm->evlist->threads, false);
 	err = kvm_live_open_events(kvm);

tools/perf/builtin-kvm.c

@@ -257,6 +257,13 @@ static int report__setup_sample_type(struct report *rep)
 		}
 	}
 
+	if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain) {
+		if ((sample_type & PERF_SAMPLE_REGS_USER) &&
+		    (sample_type & PERF_SAMPLE_STACK_USER))
+			callchain_param.record_mode = CALLCHAIN_DWARF;
+		else
+			callchain_param.record_mode = CALLCHAIN_FP;
+	}
 	return 0;
 }
 

tools/perf/builtin-report.c

@@ -1189,13 +1189,13 @@ static struct thread_trace *thread__trace(struct thread *thread, FILE *fp)
 	if (thread == NULL)
 		goto fail;
 
-	if (thread->priv == NULL)
-		thread->priv = thread_trace__new();
+	if (thread__priv(thread) == NULL)
+		thread__set_priv(thread, thread_trace__new());
 
-	if (thread->priv == NULL)
+	if (thread__priv(thread) == NULL)
 		goto fail;
 
-	ttrace = thread->priv;
+	ttrace = thread__priv(thread);
 	++ttrace->nr_events;
 
 	return ttrace;
@@ -1248,7 +1248,7 @@ struct trace {
 
 static int trace__set_fd_pathname(struct thread *thread, int fd, const char *pathname)
 {
-	struct thread_trace *ttrace = thread->priv;
+	struct thread_trace *ttrace = thread__priv(thread);
 
 	if (fd > ttrace->paths.max) {
 		char **npath = realloc(ttrace->paths.table, (fd + 1) * sizeof(char *));
@@ -1301,7 +1301,7 @@ static int thread__read_fd_path(struct thread *thread, int fd)
 static const char *thread__fd_path(struct thread *thread, int fd,
 				   struct trace *trace)
 {
-	struct thread_trace *ttrace = thread->priv;
+	struct thread_trace *ttrace = thread__priv(thread);
 
 	if (ttrace == NULL)
 		return NULL;
@@ -1338,7 +1338,7 @@ static size_t syscall_arg__scnprintf_close_fd(char *bf, size_t size,
 {
 	int fd = arg->val;
 	size_t printed = syscall_arg__scnprintf_fd(bf, size, arg);
-	struct thread_trace *ttrace = arg->thread->priv;
+	struct thread_trace *ttrace = thread__priv(arg->thread);
 
 	if (ttrace && fd >= 0 && fd <= ttrace->paths.max)
 		zfree(&ttrace->paths.table[fd]);
@@ -2381,7 +2381,7 @@ static int trace__fprintf_one_thread(struct thread *thread, void *priv)
 	FILE *fp = data->fp;
 	size_t printed = data->printed;
 	struct trace *trace = data->trace;
-	struct thread_trace *ttrace = thread->priv;
+	struct thread_trace *ttrace = thread__priv(thread);
 	double ratio;
 
 	if (ttrace == NULL)

tools/perf/builtin-trace.c

@@ -9,6 +9,7 @@
 #include "perf_regs.h"
 #include "map.h"
 #include "thread.h"
+#include "callchain.h"
 
 static int mmap_handler(struct perf_tool *tool __maybe_unused,
 			union perf_event *event,
@@ -120,6 +121,8 @@ int test__dwarf_unwind(void)
 		return -1;
 	}
 
+	callchain_param.record_mode = CALLCHAIN_DWARF;
+
 	if (init_live_machine(machine)) {
 		pr_err("Could not init machine\n");
 		goto out;

tools/perf/tests/dwarf-unwind.c

@@ -457,6 +457,36 @@ static int test__checkevent_pmu_events(struct perf_evlist *evlist)
 	return 0;
 }
 
+
+static int test__checkevent_pmu_events_mix(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	/* pmu-event:u */
+	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong exclude_user",
+			!evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel",
+			evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong pinned", !evsel->attr.pinned);
+
+	/* cpu/pmu-event/u*/
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong exclude_user",
+			!evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel",
+			evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong pinned", !evsel->attr.pinned);
+
+	return 0;
+}
+
 static int test__checkterms_simple(struct list_head *terms)
 {
 	struct parse_events_term *term;
@@ -1554,6 +1584,12 @@ static int test_pmu_events(void)
 		e.check = test__checkevent_pmu_events;
 
 		ret = test_event(&e);
+		if (ret)
+			break;
+		snprintf(name, MAX_NAME, "%s:u,cpu/event=%s/u", ent->d_name, ent->d_name);
+		e.name  = name;
+		e.check = test__checkevent_pmu_events_mix;
+		ret = test_event(&e);
 #undef MAX_NAME
 	}
 

tools/perf/tests/parse-events.c

@@ -35,7 +35,9 @@ struct hist_browser {
 
 extern void hist_browser__init_hpp(void);
 
-static int hists__browser_title(struct hists *hists, char *bf, size_t size);
+static int hists__browser_title(struct hists *hists,
+				struct hist_browser_timer *hbt,
+				char *bf, size_t size);
 static void hist_browser__update_nr_entries(struct hist_browser *hb);
 
 static struct rb_node *hists__filter_entries(struct rb_node *nd,
@@ -390,7 +392,7 @@ static int hist_browser__run(struct hist_browser *browser,
 	browser->b.entries = &browser->hists->entries;
 	browser->b.nr_entries = hist_browser__nr_entries(browser);
 
-	hists__browser_title(browser->hists, title, sizeof(title));
+	hists__browser_title(browser->hists, hbt, title, sizeof(title));
 
 	if (ui_browser__show(&browser->b, title,
 			     "Press '?' for help on key bindings") < 0)
@@ -417,7 +419,8 @@ static int hist_browser__run(struct hist_browser *browser,
 				ui_browser__warn_lost_events(&browser->b);
 			}
 
-			hists__browser_title(browser->hists, title, sizeof(title));
+			hists__browser_title(browser->hists,
+					     hbt, title, sizeof(title));
 			ui_browser__show_title(&browser->b, title);
 			continue;
 		}
@@ -1204,7 +1207,15 @@ static struct thread *hist_browser__selected_thread(struct hist_browser *browser
 	return browser->he_selection->thread;
 }
 
-static int hists__browser_title(struct hists *hists, char *bf, size_t size)
+/* Check whether the browser is for 'top' or 'report' */
+static inline bool is_report_browser(void *timer)
+{
+	return timer == NULL;
+}
+
+static int hists__browser_title(struct hists *hists,
+				struct hist_browser_timer *hbt,
+				char *bf, size_t size)
 {
 	char unit;
 	int printed;
@@ -1258,6 +1269,13 @@ static int hists__browser_title(struct hists *hists, char *bf, size_t size)
 	if (dso)
 		printed += scnprintf(bf + printed, size - printed,
 				    ", DSO: %s", dso->short_name);
+	if (!is_report_browser(hbt)) {
+		struct perf_top *top = hbt->arg;
+
+		if (top->zero)
+			printed += scnprintf(bf + printed, size - printed, " [z]");
+	}
+
 	return printed;
 }
 
@@ -1269,12 +1287,6 @@ static inline void free_popup_options(char **options, int n)
 		zfree(&options[i]);
 }
 
-/* Check whether the browser is for 'top' or 'report' */
-static inline bool is_report_browser(void *timer)
-{
-	return timer == NULL;
-}
-
 /*
  * Only runtime switching of perf data file will make "input_name" point
  * to a malloced buffer. So add "is_input_name_malloced" flag to decide

tools/perf/ui/browsers/hists.c

@@ -1003,6 +1003,7 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
 
 out_delete_threads:
 	thread_map__delete(evlist->threads);
+	evlist->threads = NULL;
 	return -1;
 }
 

tools/perf/util/evlist.c

@@ -1,4 +1,3 @@
 #include <string.h>
 
 void *memdup(const void *src, size_t len);
-int str_append(char **s, int *len, const char *a);