Merge tag 'trace-v6.4-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace

Pull tracing fixes from Steven Rostedt:
 "User events:

   - Use long instead of int for storing the enable set/clear bit, as it
     was found that big endian machines could end up using the wrong
     bits.

   - Split allocating mm and attaching it. This keeps the allocation
     separate from the registration and avoids various races.

   - Remove RCU locking around pin_user_pages_remote() as that can
     schedule. The RCU protection is no longer needed with the above
     split of mm allocation and attaching.

   - Rename the "link" fields of the various structs to something more
     meaningful.

   - Add comments around user_event_mm struct usage and locking
     requirements.

  Timerlat tracer:

   - Fix missed wakeup of timerlat thread caused by the timerlat
     interrupt triggering when tracing is off. The timer interrupt
     handler needs to always wake up the timerlat thread regardless if
     tracing is enabled or not, otherwise, it will never wake up.

  Histograms:

   - Fix regression of breaking the "stacktrace" modifier for variables.
     That modifier cannot be used for values, but can be used for
     variables that are passed from one histogram to the next. This was
     broken when adding the restriction to values as the variable logic
     used the same code.

   - Rename the special field "stacktrace" to "common_stacktrace".

     Special fields (that are not actually part of the event, but can
     act just like event fields, like 'comm' and 'timestamp') should be
     prefixed with 'common_' for consistency. To keep backward
     compatibility, 'stacktrace' can still be used (as with the special
     field 'cpu'), but can be overridden if the event has a field called
     'stacktrace'.

   - Update the synthetic event selftests to use the new name (synthetic
     events are created by histograms)

  Tracing bootup selftests:

   - Reorganize the code to keep artifacts of the selftests not compiled
     in when selftests are not configured.

   - Add various cond_resched() around the selftest code, as the
     softlock watchdog was triggering much more often. It appears that
     the kernel runs slower now with full debugging enabled.

   - While debugging ftrace with ftrace (using an instance ring buffer
     instead of the top level one), I found that the selftests were
     disabling prints to the debug instance.

     This should not happen, as the selftests only disable printing to
     the main buffer as the selftests examine the main buffer to see if
     it has what it expects, and prints can make the tests fail.

     Make the selftests only disable printing to the toplevel buffer,
     and leave the instance buffers alone"

* tag 'trace-v6.4-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  tracing: Have function_graph selftest call cond_resched()
  tracing: Only make selftest conditionals affect the global_trace
  tracing: Make tracing_selftest_running/delete nops when not used
  tracing: Have tracer selftests call cond_resched() before running
  tracing: Move setting of tracing_selftest_running out of register_tracer()
  tracing/selftests: Update synthetic event selftest to use common_stacktrace
  tracing: Rename stacktrace field to common_stacktrace
  tracing/histograms: Allow variables to have some modifiers
  tracing/user_events: Document user_event_mm one-shot list usage
  tracing/user_events: Rename link fields for clarity
  tracing/user_events: Remove RCU lock while pinning pages
  tracing/user_events: Split up mm alloc and attach
  tracing/timerlat: Always wakeup the timerlat thread
  tracing/user_events: Use long vs int for atomic bit ops

include/linux/trace_events.h

@@ -806,6 +806,7 @@ enum {
 	FILTER_TRACE_FN,
 	FILTER_COMM,
 	FILTER_CPU,
+	FILTER_STACKTRACE,
 };
 
 extern int trace_event_raw_init(struct trace_event_call *call);

include/linux/user_events.h

@@ -17,9 +17,10 @@
 
 #ifdef CONFIG_USER_EVENTS
 struct user_event_mm {
-	struct list_head	link;
+	struct list_head	mms_link;
 	struct list_head	enablers;
 	struct mm_struct	*mm;
+	/* Used for one-shot lists, protected by event_mutex */
 	struct user_event_mm	*next;
 	refcount_t		refcnt;
 	refcount_t		tasks;

kernel/trace/trace.c

@@ -60,6 +60,7 @@
  */
 bool ring_buffer_expanded;
 
+#ifdef CONFIG_FTRACE_STARTUP_TEST
 /*
  * We need to change this state when a selftest is running.
  * A selftest will lurk into the ring-buffer to count the
@@ -75,7 +76,6 @@ static bool __read_mostly tracing_selftest_running;
  */
 bool __read_mostly tracing_selftest_disabled;
 
-#ifdef CONFIG_FTRACE_STARTUP_TEST
 void __init disable_tracing_selftest(const char *reason)
 {
 	if (!tracing_selftest_disabled) {
@@ -83,6 +83,9 @@ void __init disable_tracing_selftest(const char *reason)
 		pr_info("Ftrace startup test is disabled due to %s\n", reason);
 	}
 }
+#else
+#define tracing_selftest_running	0
+#define tracing_selftest_disabled	0
 #endif
 
 /* Pipe tracepoints to printk */
@@ -1051,7 +1054,10 @@ int __trace_array_puts(struct trace_array *tr, unsigned long ip,
 	if (!(tr->trace_flags & TRACE_ITER_PRINTK))
 		return 0;
 
-	if (unlikely(tracing_selftest_running || tracing_disabled))
+	if (unlikely(tracing_selftest_running && tr == &global_trace))
+		return 0;
+
+	if (unlikely(tracing_disabled))
 		return 0;
 
 	alloc = sizeof(*entry) + size + 2; /* possible \n added */
@@ -2041,6 +2047,24 @@ static int run_tracer_selftest(struct tracer *type)
 	return 0;
 }
 
+static int do_run_tracer_selftest(struct tracer *type)
+{
+	int ret;
+
+	/*
+	 * Tests can take a long time, especially if they are run one after the
+	 * other, as does happen during bootup when all the tracers are
+	 * registered. This could cause the soft lockup watchdog to trigger.
+	 */
+	cond_resched();
+
+	tracing_selftest_running = true;
+	ret = run_tracer_selftest(type);
+	tracing_selftest_running = false;
+
+	return ret;
+}
+
 static __init int init_trace_selftests(void)
 {
 	struct trace_selftests *p, *n;
@@ -2092,6 +2116,10 @@ static inline int run_tracer_selftest(struct tracer *type)
 {
 	return 0;
 }
+static inline int do_run_tracer_selftest(struct tracer *type)
+{
+	return 0;
+}
 #endif /* CONFIG_FTRACE_STARTUP_TEST */
 
 static void add_tracer_options(struct trace_array *tr, struct tracer *t);
@@ -2127,8 +2155,6 @@ int __init register_tracer(struct tracer *type)
 
 	mutex_lock(&trace_types_lock);
 
-	tracing_selftest_running = true;
-
 	for (t = trace_types; t; t = t->next) {
 		if (strcmp(type->name, t->name) == 0) {
 			/* already found */
@@ -2157,7 +2183,7 @@ int __init register_tracer(struct tracer *type)
 	/* store the tracer for __set_tracer_option */
 	type->flags->trace = type;
 
-	ret = run_tracer_selftest(type);
+	ret = do_run_tracer_selftest(type);
 	if (ret < 0)
 		goto out;
 
@@ -2166,7 +2192,6 @@ int __init register_tracer(struct tracer *type)
 	add_tracer_options(&global_trace, type);
 
  out:
-	tracing_selftest_running = false;
 	mutex_unlock(&trace_types_lock);
 
 	if (ret || !default_bootup_tracer)
@@ -3490,7 +3515,7 @@ __trace_array_vprintk(struct trace_buffer *buffer,
 	unsigned int trace_ctx;
 	char *tbuffer;
 
-	if (tracing_disabled || tracing_selftest_running)
+	if (tracing_disabled)
 		return 0;
 
 	/* Don't pollute graph traces with trace_vprintk internals */
@@ -3538,6 +3563,9 @@ __printf(3, 0)
 int trace_array_vprintk(struct trace_array *tr,
 			unsigned long ip, const char *fmt, va_list args)
 {
+	if (tracing_selftest_running && tr == &global_trace)
+		return 0;
+
 	return __trace_array_vprintk(tr->array_buffer.buffer, ip, fmt, args);
 }
 
@@ -5752,7 +5780,7 @@ static const char readme_msg[] =
 	"\t    table using the key(s) and value(s) named, and the value of a\n"
 	"\t    sum called 'hitcount' is incremented.  Keys and values\n"
 	"\t    correspond to fields in the event's format description.  Keys\n"
-	"\t    can be any field, or the special string 'stacktrace'.\n"
+	"\t    can be any field, or the special string 'common_stacktrace'.\n"
 	"\t    Compound keys consisting of up to two fields can be specified\n"
 	"\t    by the 'keys' keyword.  Values must correspond to numeric\n"
 	"\t    fields.  Sort keys consisting of up to two fields can be\n"

kernel/trace/trace_events.c

@@ -194,6 +194,8 @@ static int trace_define_generic_fields(void)
 	__generic_field(int, common_cpu, FILTER_CPU);
 	__generic_field(char *, COMM, FILTER_COMM);
 	__generic_field(char *, comm, FILTER_COMM);
+	__generic_field(char *, stacktrace, FILTER_STACKTRACE);
+	__generic_field(char *, STACKTRACE, FILTER_STACKTRACE);
 
 	return ret;
 }

kernel/trace/trace_events_hist.c

@@ -1364,7 +1364,7 @@ static const char *hist_field_name(struct hist_field *field,
 		if (field->field)
 			field_name = field->field->name;
 		else
-			field_name = "stacktrace";
+			field_name = "common_stacktrace";
 	} else if (field->flags & HIST_FIELD_FL_HITCOUNT)
 		field_name = "hitcount";
 
@@ -2367,7 +2367,7 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file,
 		hist_data->enable_timestamps = true;
 		if (*flags & HIST_FIELD_FL_TIMESTAMP_USECS)
 			hist_data->attrs->ts_in_usecs = true;
-	} else if (strcmp(field_name, "stacktrace") == 0) {
+	} else if (strcmp(field_name, "common_stacktrace") == 0) {
 		*flags |= HIST_FIELD_FL_STACKTRACE;
 	} else if (strcmp(field_name, "common_cpu") == 0)
 		*flags |= HIST_FIELD_FL_CPU;
@@ -2378,11 +2378,15 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file,
 		if (!field || !field->size) {
 			/*
 			 * For backward compatibility, if field_name
-			 * was "cpu", then we treat this the same as
-			 * common_cpu. This also works for "CPU".
+			 * was "cpu" or "stacktrace", then we treat this
+			 * the same as common_cpu and common_stacktrace
+			 * respectively. This also works for "CPU", and
+			 * "STACKTRACE".
 			 */
 			if (field && field->filter_type == FILTER_CPU) {
 				*flags |= HIST_FIELD_FL_CPU;
+			} else if (field && field->filter_type == FILTER_STACKTRACE) {
+				*flags |= HIST_FIELD_FL_STACKTRACE;
 			} else {
 				hist_err(tr, HIST_ERR_FIELD_NOT_FOUND,
 					 errpos(field_name));
@@ -4238,13 +4242,19 @@ static int __create_val_field(struct hist_trigger_data *hist_data,
 		goto out;
 	}
 
-	/* Some types cannot be a value */
+	/* values and variables should not have some modifiers */
+	if (hist_field->flags & HIST_FIELD_FL_VAR) {
+		/* Variable */
+		if (hist_field->flags & (HIST_FIELD_FL_GRAPH | HIST_FIELD_FL_PERCENT |
+					 HIST_FIELD_FL_BUCKET | HIST_FIELD_FL_LOG2))
+			goto err;
+	} else {
+		/* Value */
 		if (hist_field->flags & (HIST_FIELD_FL_GRAPH | HIST_FIELD_FL_PERCENT |
 					 HIST_FIELD_FL_BUCKET | HIST_FIELD_FL_LOG2 |
 					 HIST_FIELD_FL_SYM | HIST_FIELD_FL_SYM_OFFSET |
-				 HIST_FIELD_FL_SYSCALL | HIST_FIELD_FL_STACKTRACE)) {
-		hist_err(file->tr, HIST_ERR_BAD_FIELD_MODIFIER, errpos(field_str));
-		ret = -EINVAL;
+					 HIST_FIELD_FL_SYSCALL | HIST_FIELD_FL_STACKTRACE))
+			goto err;
 	}
 
 	hist_data->fields[val_idx] = hist_field;
@@ -4256,6 +4266,9 @@ static int __create_val_field(struct hist_trigger_data *hist_data,
 		ret = -EINVAL;
  out:
 	return ret;
+ err:
+	hist_err(file->tr, HIST_ERR_BAD_FIELD_MODIFIER, errpos(field_str));
+	return -EINVAL;
 }
 
 static int create_val_field(struct hist_trigger_data *hist_data,
@@ -5385,7 +5398,7 @@ static void hist_trigger_print_key(struct seq_file *m,
 			if (key_field->field)
 				seq_printf(m, "%s.stacktrace", key_field->field->name);
 			else
-				seq_puts(m, "stacktrace:\n");
+				seq_puts(m, "common_stacktrace:\n");
 			hist_trigger_stacktrace_print(m,
 						      key + key_field->offset,
 						      HIST_STACKTRACE_DEPTH);
@@ -5968,7 +5981,7 @@ static int event_hist_trigger_print(struct seq_file *m,
 			if (field->field)
 				seq_printf(m, "%s.stacktrace", field->field->name);
 			else
-				seq_puts(m, "stacktrace");
+				seq_puts(m, "common_stacktrace");
 		} else
 			hist_field_print(m, field);
 	}

kernel/trace/trace_osnoise.c

@@ -1652,6 +1652,8 @@ static enum hrtimer_restart timerlat_irq(struct hrtimer *timer)
 			osnoise_stop_tracing();
 			notify_new_max_latency(diff);
 
+			wake_up_process(tlat->kthread);
+
 			return HRTIMER_NORESTART;
 		}
 	}

kernel/trace/trace_selftest.c

@@ -848,6 +848,12 @@ trace_selftest_startup_function_graph(struct tracer *trace,
 	}
 
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+	/*
+	 * These tests can take some time to run. Make sure on non PREEMPT
+	 * kernels, we do not trigger the softlockup detector.
+	 */
+	cond_resched();
+
 	tracing_reset_online_cpus(&tr->array_buffer);
 	set_graph_array(tr);
 
@@ -869,6 +875,8 @@ trace_selftest_startup_function_graph(struct tracer *trace,
 	if (ret)
 		goto out;
 
+	cond_resched();
+
 	ret = register_ftrace_graph(&fgraph_ops);
 	if (ret) {
 		warn_failed_init_tracer(trace, ret);
@@ -891,6 +899,8 @@ trace_selftest_startup_function_graph(struct tracer *trace,
 	if (ret)
 		goto out;
 
+	cond_resched();
+
 	tracing_start();
 
 	if (!ret && !count) {

tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack-legacy.tc

+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: event trigger - test inter-event histogram trigger trace action with dynamic string param (legacy stack)
+# requires: set_event synthetic_events events/sched/sched_process_exec/hist "long[] stack' >> synthetic_events":README
+
+fail() { #msg
+    echo $1
+    exit_fail
+}
+
+echo "Test create synthetic event with stack"
+
+# Test the old stacktrace keyword (for backward compatibility)
+echo 's:wake_lat pid_t pid; u64 delta; unsigned long[] stack;' > dynamic_events
+echo 'hist:keys=next_pid:ts=common_timestamp.usecs,st=stacktrace  if prev_state == 1||prev_state == 2' >> events/sched/sched_switch/trigger
+echo 'hist:keys=prev_pid:delta=common_timestamp.usecs-$ts,s=$st:onmax($delta).trace(wake_lat,prev_pid,$delta,$s)' >> events/sched/sched_switch/trigger
+echo 1 > events/synthetic/wake_lat/enable
+sleep 1
+
+if ! grep -q "=>.*sched" trace; then
+    fail "Failed to create synthetic event with stack"
+fi
+
+exit 0

tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack.tc

 #!/bin/sh
 # SPDX-License-Identifier: GPL-2.0
 # description: event trigger - test inter-event histogram trigger trace action with dynamic string param
-# requires: set_event synthetic_events events/sched/sched_process_exec/hist "long[]' >> synthetic_events":README
+# requires: set_event synthetic_events events/sched/sched_process_exec/hist "can be any field, or the special string 'common_stacktrace'":README
 
 fail() { #msg
     echo $1
@@ -10,9 +10,8 @@ fail() { #msg
 
 echo "Test create synthetic event with stack"
 
-
 echo 's:wake_lat pid_t pid; u64 delta; unsigned long[] stack;' > dynamic_events
-echo 'hist:keys=next_pid:ts=common_timestamp.usecs,st=stacktrace  if prev_state == 1||prev_state == 2' >> events/sched/sched_switch/trigger
+echo 'hist:keys=next_pid:ts=common_timestamp.usecs,st=common_stacktrace  if prev_state == 1||prev_state == 2' >> events/sched/sched_switch/trigger
 echo 'hist:keys=prev_pid:delta=common_timestamp.usecs-$ts,s=$st:onmax($delta).trace(wake_lat,prev_pid,$delta,$s)' >> events/sched/sched_switch/trigger
 echo 1 > events/synthetic/wake_lat/enable
 sleep 1