From 217d8c05ec6295947b0b71bc784012d112f0032e Mon Sep 17 00:00:00 2001
From: Tom Rix
Date: Mon, 7 Feb 2022 05:12:16 -0800
Subject: tracing: Cleanup double word in comment

Remove the second 'is' and 'to'.

Link: https://lkml.kernel.org/r/20220207131216.2059997-1-trix@redhat.com

Signed-off-by: Tom Rix <trix@redhat.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/pid_list.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/pid_list.c b/kernel/trace/pid_list.c
index a2ef1d18126a..95106d02b32d 100644
--- a/kernel/trace/pid_list.c
+++ b/kernel/trace/pid_list.c
@@ -118,9 +118,9 @@ static inline unsigned int pid_join(unsigned int upper1,
 /**
  * trace_pid_list_is_set - test if the pid is set in the list
  * @pid_list: The pid list to test
- * @pid: The pid to to see if set in the list.
+ * @pid: The pid to see if set in the list.
  *
- * Tests if @pid is is set in the @pid_list. This is usually called
+ * Tests if @pid is set in the @pid_list. This is usually called
  * from the scheduler when a task is scheduled. Its pid is checked
  * if it should be traced or not.
  *
-- 
cgit v1.2.3


From b8cc44a4d3c19296dfd1be1a018a8523e09ab919 Mon Sep 17 00:00:00 2001
From: Tom Zanussi
Date: Fri, 4 Feb 2022 16:12:04 -0600
Subject: tracing: Remove logic for registering multiple event triggers at a
 time

Code for registering triggers assumes it's possible to register more
than one trigger at a time.  In fact, it's unimplemented and there
doesn't seem to be a reason to do that.

Remove the n_registered param from event_trigger_register() and fix up
callers.

Doing so simplifies the logic in event_trigger_register to the point
that it just becomes a wrapper calling event_command.reg().

It also removes the problematic call to event_command.unreg() in case
of failure.  A new function, event_trigger_unregister() is also added
for callers to call themselves.

The changes to trace_events_hist.c simply allow compilation; a
separate patch follows which updates the hist triggers to work
correctly with the new changes.

Link: https://lkml.kernel.org/r/6149fec7a139d93e84fa4535672fb5bef88006b0.1644010575.git.zanussi@kernel.org

Signed-off-by: Tom Zanussi <zanussi@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace.h                |  9 ++--
 kernel/trace/trace_events_hist.c    | 17 +++----
 kernel/trace/trace_events_trigger.c | 96 +++++++++++++------------------------
 3 files changed, 45 insertions(+), 77 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 07d990270e2a..2bc8036b0659 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1629,10 +1629,11 @@ extern void event_trigger_reset_filter(struct event_command *cmd_ops,
 extern int event_trigger_register(struct event_command *cmd_ops,
 				  struct trace_event_file *file,
 				  char *glob,
-				  char *cmd,
-				  char *trigger,
-				  struct event_trigger_data *trigger_data,
-				  int *n_registered);
+				  struct event_trigger_data *trigger_data);
+extern void event_trigger_unregister(struct event_command *cmd_ops,
+				     struct trace_event_file *file,
+				     char *glob,
+				     struct event_trigger_data *trigger_data);
 
 /**
  * struct event_trigger_ops - callbacks for trace event triggers
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 44db5ba9cabb..b18d00905eae 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -6287,7 +6287,7 @@ static int event_hist_trigger_parse(struct event_command *cmd_ops,
 			goto out_free;
 		}
 
-		cmd_ops->unreg(glob+1, trigger_data, file);
+		event_trigger_unregister(cmd_ops, file, glob+1, trigger_data);
 		se_name = trace_event_name(file->event_call);
 		se = find_synth_event(se_name);
 		if (se)
@@ -6296,13 +6296,10 @@ static int event_hist_trigger_parse(struct event_command *cmd_ops,
 		goto out_free;
 	}
 
-	ret = cmd_ops->reg(glob, trigger_data, file);
-	/*
-	 * The above returns on success the # of triggers registered,
-	 * but if it didn't register any it returns zero.  Consider no
-	 * triggers registered a failure too.
-	 */
-	if (!ret) {
+	ret = event_trigger_register(cmd_ops, file, glob, trigger_data);
+	if (ret)
+		goto out_free;
+	if (ret == 0) {
 		if (!(attrs->pause || attrs->cont || attrs->clear))
 			ret = -ENOENT;
 		goto out_free;
@@ -6331,15 +6328,13 @@ enable:
 	se = find_synth_event(se_name);
 	if (se)
 		se->ref++;
-	/* Just return zero, not the number of registered triggers */
-	ret = 0;
  out:
 	if (ret == 0)
 		hist_err_clear();
 
 	return ret;
  out_unreg:
-	cmd_ops->unreg(glob+1, trigger_data, file);
+	event_trigger_unregister(cmd_ops, file, glob+1, trigger_data);
  out_free:
 	if (cmd_ops->set_filter)
 		cmd_ops->set_filter(NULL, trigger_data, NULL);
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 7eb9d04f1c2e..ea13679054a8 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -587,13 +587,12 @@ static int register_trigger(char *glob,
 	}
 
 	list_add_rcu(&data->list, &file->triggers);
-	ret++;
 
 	update_cond_flag(file);
-	if (trace_event_trigger_enable_disable(file, 1) < 0) {
+	ret = trace_event_trigger_enable_disable(file, 1);
+	if (ret < 0) {
 		list_del_rcu(&data->list);
 		update_cond_flag(file);
-		ret--;
 	}
 out:
 	return ret;
@@ -927,48 +926,37 @@ void event_trigger_reset_filter(struct event_command *cmd_ops,
  * @cmd_ops: The event_command operations for the trigger
  * @file: The event file for the trigger's event
  * @glob: The trigger command string, with optional remove(!) operator
- * @cmd: The cmd string
- * @param: The param string
  * @trigger_data: The trigger_data for the trigger
- * @n_registered: optional outparam, the number of triggers registered
  *
  * Register an event trigger.  The @cmd_ops are used to call the
- * cmd_ops->reg() function which actually does the registration. The
- * cmd_ops->reg() function returns the number of triggers registered,
- * which is assigned to n_registered, if n_registered is non-NULL.
+ * cmd_ops->reg() function which actually does the registration.
  *
  * Return: 0 on success, errno otherwise
  */
 int event_trigger_register(struct event_command *cmd_ops,
 			   struct trace_event_file *file,
 			   char *glob,
-			   char *cmd,
-			   char *param,
-			   struct event_trigger_data *trigger_data,
-			   int *n_registered)
+			   struct event_trigger_data *trigger_data)
 {
-	int ret;
-
-	if (n_registered)
-		*n_registered = 0;
-
-	ret = cmd_ops->reg(glob, trigger_data, file);
-	/*
-	 * The above returns on success the # of functions enabled,
-	 * but if it didn't find any functions it returns zero.
-	 * Consider no functions a failure too.
-	 */
-	if (!ret) {
-		cmd_ops->unreg(glob, trigger_data, file);
-		ret = -ENOENT;
-	} else if (ret > 0) {
-		if (n_registered)
-			*n_registered = ret;
-		/* Just return zero, not the number of enabled functions */
-		ret = 0;
-	}
+	return cmd_ops->reg(glob, trigger_data, file);
+}
 
-	return ret;
+/**
+ * event_trigger_unregister - unregister an event trigger
+ * @cmd_ops: The event_command operations for the trigger
+ * @file: The event file for the trigger's event
+ * @glob: The trigger command string, with optional remove(!) operator
+ * @trigger_data: The trigger_data for the trigger
+ *
+ * Unregister an event trigger.  The @cmd_ops are used to call the
+ * cmd_ops->unreg() function which actually does the unregistration.
+ */
+void event_trigger_unregister(struct event_command *cmd_ops,
+			      struct trace_event_file *file,
+			      char *glob,
+			      struct event_trigger_data *trigger_data)
+{
+	cmd_ops->unreg(glob, trigger_data, file);
 }
 
 /*
@@ -1027,7 +1015,7 @@ event_trigger_parse(struct event_command *cmd_ops,
 	INIT_LIST_HEAD(&trigger_data->named_list);
 
 	if (glob[0] == '!') {
-		cmd_ops->unreg(glob+1, trigger_data, file);
+		event_trigger_unregister(cmd_ops, file, glob+1, trigger_data);
 		kfree(trigger_data);
 		ret = 0;
 		goto out;
@@ -1062,17 +1050,10 @@ event_trigger_parse(struct event_command *cmd_ops,
  out_reg:
 	/* Up the trigger_data count to make sure reg doesn't free it on failure */
 	event_trigger_init(trigger_ops, trigger_data);
-	ret = cmd_ops->reg(glob, trigger_data, file);
-	/*
-	 * The above returns on success the # of functions enabled,
-	 * but if it didn't find any functions it returns zero.
-	 * Consider no functions a failure too.
-	 */
-	if (!ret) {
-		cmd_ops->unreg(glob, trigger_data, file);
-		ret = -ENOENT;
-	} else if (ret > 0)
-		ret = 0;
+
+	ret = event_trigger_register(cmd_ops, file, glob, trigger_data);
+	if (ret)
+		goto out_free;
 
 	/* Down the counter of trigger_data or free it if not used anymore */
 	event_trigger_free(trigger_ops, trigger_data);
@@ -1854,7 +1835,7 @@ int event_enable_trigger_parse(struct event_command *cmd_ops,
 	trigger_data->private_data = enable_data;
 
 	if (glob[0] == '!') {
-		cmd_ops->unreg(glob+1, trigger_data, file);
+		event_trigger_unregister(cmd_ops, file, glob+1, trigger_data);
 		kfree(trigger_data);
 		kfree(enable_data);
 		ret = 0;
@@ -1901,19 +1882,11 @@ int event_enable_trigger_parse(struct event_command *cmd_ops,
 	ret = trace_event_enable_disable(event_enable_file, 1, 1);
 	if (ret < 0)
 		goto out_put;
-	ret = cmd_ops->reg(glob, trigger_data, file);
-	/*
-	 * The above returns on success the # of functions enabled,
-	 * but if it didn't find any functions it returns zero.
-	 * Consider no functions a failure too.
-	 */
-	if (!ret) {
-		ret = -ENOENT;
-		goto out_disable;
-	} else if (ret < 0)
+
+	ret = event_trigger_register(cmd_ops, file, glob, trigger_data);
+	if (ret)
 		goto out_disable;
-	/* Just return zero, not the number of enabled functions */
-	ret = 0;
+
 	event_trigger_free(trigger_ops, trigger_data);
  out:
 	return ret;
@@ -1959,13 +1932,12 @@ int event_enable_register_trigger(char *glob,
 	}
 
 	list_add_rcu(&data->list, &file->triggers);
-	ret++;
 
 	update_cond_flag(file);
-	if (trace_event_trigger_enable_disable(file, 1) < 0) {
+	ret = trace_event_trigger_enable_disable(file, 1);
+	if (ret < 0) {
 		list_del_rcu(&data->list);
 		update_cond_flag(file);
-		ret--;
 	}
 out:
 	return ret;
-- 
cgit v1.2.3


From 476705419518a2f383b6695782ba1f285a2959b9 Mon Sep 17 00:00:00 2001
From: Tom Zanussi
Date: Fri, 4 Feb 2022 16:12:05 -0600
Subject: tracing: Remove redundant trigger_ops params

Since event_trigger_data contains the .ops trigger_ops field, there's
no reason to pass the trigger_ops separately. Remove it as a param
from functions whenever event_trigger_data is passed.

Link: https://lkml.kernel.org/r/9856c9bc81bde57077f5b8d6f8faa47156c6354a.1644010575.git.zanussi@kernel.org

Signed-off-by: Tom Zanussi <zanussi@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace.h                | 14 ++++-------
 kernel/trace/trace_eprobe.c         |  7 ++----
 kernel/trace/trace_events_hist.c    | 29 ++++++++++-------------
 kernel/trace/trace_events_trigger.c | 46 +++++++++++++++----------------------
 4 files changed, 36 insertions(+), 60 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 2bc8036b0659..f3e4cd1bb60e 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1573,10 +1573,8 @@ struct enable_trigger_data {
 };
 
 extern int event_enable_trigger_print(struct seq_file *m,
-				      struct event_trigger_ops *ops,
-				      struct event_trigger_data *data);
-extern void event_enable_trigger_free(struct event_trigger_ops *ops,
 				      struct event_trigger_data *data);
+extern void event_enable_trigger_free(struct event_trigger_data *data);
 extern int event_enable_trigger_parse(struct event_command *cmd_ops,
 				      struct trace_event_file *file,
 				      char *glob, char *cmd, char *param);
@@ -1587,8 +1585,7 @@ extern void event_enable_unregister_trigger(char *glob,
 					    struct event_trigger_data *test,
 					    struct trace_event_file *file);
 extern void trigger_data_free(struct event_trigger_data *data);
-extern int event_trigger_init(struct event_trigger_ops *ops,
-			      struct event_trigger_data *data);
+extern int event_trigger_init(struct event_trigger_data *data);
 extern int trace_event_trigger_enable_disable(struct trace_event_file *file,
 					      int trigger_enable);
 extern void update_cond_flag(struct trace_event_file *file);
@@ -1687,12 +1684,9 @@ struct event_trigger_ops {
 					   struct trace_buffer *buffer,
 					   void *rec,
 					   struct ring_buffer_event *rbe);
-	int			(*init)(struct event_trigger_ops *ops,
-					struct event_trigger_data *data);
-	void			(*free)(struct event_trigger_ops *ops,
-					struct event_trigger_data *data);
+	int			(*init)(struct event_trigger_data *data);
+	void			(*free)(struct event_trigger_data *data);
 	int			(*print)(struct seq_file *m,
-					 struct event_trigger_ops *ops,
 					 struct event_trigger_data *data);
 };
 
diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c
index 541aa13581b9..9b3dfc9da067 100644
--- a/kernel/trace/trace_eprobe.c
+++ b/kernel/trace/trace_eprobe.c
@@ -511,20 +511,17 @@ __eprobe_trace_func(struct eprobe_data *edata, void *rec)
  * functions are just stubs to fulfill what is needed to use the trigger
  * infrastructure.
  */
-static int eprobe_trigger_init(struct event_trigger_ops *ops,
-			       struct event_trigger_data *data)
+static int eprobe_trigger_init(struct event_trigger_data *data)
 {
 	return 0;
 }
 
-static void eprobe_trigger_free(struct event_trigger_ops *ops,
-				struct event_trigger_data *data)
+static void eprobe_trigger_free(struct event_trigger_data *data)
 {
 
 }
 
 static int eprobe_trigger_print(struct seq_file *m,
-				struct event_trigger_ops *ops,
 				struct event_trigger_data *data)
 {
 	/* Do not print eprobe event triggers */
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index b18d00905eae..40a7e5582dfb 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -5252,7 +5252,7 @@ static void hist_trigger_show(struct seq_file *m,
 		seq_puts(m, "\n\n");
 
 	seq_puts(m, "# event histogram\n#\n# trigger info: ");
-	data->ops->print(m, data->ops, data);
+	data->ops->print(m, data);
 	seq_puts(m, "#\n\n");
 
 	hist_data = data->private_data;
@@ -5484,7 +5484,7 @@ static void hist_trigger_debug_show(struct seq_file *m,
 		seq_puts(m, "\n\n");
 
 	seq_puts(m, "# event histogram\n#\n# trigger info: ");
-	data->ops->print(m, data->ops, data);
+	data->ops->print(m, data);
 	seq_puts(m, "#\n\n");
 
 	hist_data = data->private_data;
@@ -5621,7 +5621,6 @@ static void hist_field_print(struct seq_file *m, struct hist_field *hist_field)
 }
 
 static int event_hist_trigger_print(struct seq_file *m,
-				    struct event_trigger_ops *ops,
 				    struct event_trigger_data *data)
 {
 	struct hist_trigger_data *hist_data = data->private_data;
@@ -5729,8 +5728,7 @@ static int event_hist_trigger_print(struct seq_file *m,
 	return 0;
 }
 
-static int event_hist_trigger_init(struct event_trigger_ops *ops,
-				   struct event_trigger_data *data)
+static int event_hist_trigger_init(struct event_trigger_data *data)
 {
 	struct hist_trigger_data *hist_data = data->private_data;
 
@@ -5758,8 +5756,7 @@ static void unregister_field_var_hists(struct hist_trigger_data *hist_data)
 	}
 }
 
-static void event_hist_trigger_free(struct event_trigger_ops *ops,
-				    struct event_trigger_data *data)
+static void event_hist_trigger_free(struct event_trigger_data *data)
 {
 	struct hist_trigger_data *hist_data = data->private_data;
 
@@ -5788,25 +5785,23 @@ static struct event_trigger_ops event_hist_trigger_ops = {
 	.free			= event_hist_trigger_free,
 };
 
-static int event_hist_trigger_named_init(struct event_trigger_ops *ops,
-					 struct event_trigger_data *data)
+static int event_hist_trigger_named_init(struct event_trigger_data *data)
 {
 	data->ref++;
 
 	save_named_trigger(data->named_data->name, data);
 
-	event_hist_trigger_init(ops, data->named_data);
+	event_hist_trigger_init(data->named_data);
 
 	return 0;
 }
 
-static void event_hist_trigger_named_free(struct event_trigger_ops *ops,
-					  struct event_trigger_data *data)
+static void event_hist_trigger_named_free(struct event_trigger_data *data)
 {
 	if (WARN_ON_ONCE(data->ref <= 0))
 		return;
 
-	event_hist_trigger_free(ops, data->named_data);
+	event_hist_trigger_free(data->named_data);
 
 	data->ref--;
 	if (!data->ref) {
@@ -5993,7 +5988,7 @@ static int hist_register_trigger(char *glob,
 	}
 
 	if (data->ops->init) {
-		ret = data->ops->init(data->ops, data);
+		ret = data->ops->init(data);
 		if (ret < 0)
 			goto out;
 	}
@@ -6111,7 +6106,7 @@ static void hist_unregister_trigger(char *glob,
 	}
 
 	if (unregistered && test->ops->free)
-		test->ops->free(test->ops, test);
+		test->ops->free(test);
 
 	if (hist_data->enable_timestamps) {
 		if (!hist_data->remove || unregistered)
@@ -6164,7 +6159,7 @@ static void hist_unreg_all(struct trace_event_file *file)
 			if (hist_data->enable_timestamps)
 				tracing_set_filter_buffering(file->tr, false);
 			if (test->ops->free)
-				test->ops->free(test->ops, test);
+				test->ops->free(test);
 		}
 	}
 }
@@ -6458,7 +6453,7 @@ static void hist_enable_unreg_all(struct trace_event_file *file)
 			update_cond_flag(file);
 			trace_event_trigger_enable_disable(file, 0);
 			if (test->ops->free)
-				test->ops->free(test->ops, test);
+				test->ops->free(test);
 		}
 	}
 }
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index ea13679054a8..32202175875d 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -188,7 +188,7 @@ static int trigger_show(struct seq_file *m, void *v)
 	}
 
 	data = list_entry(v, struct event_trigger_data, list);
-	data->ops->print(m, data->ops, data);
+	data->ops->print(m, data);
 
 	return 0;
 }
@@ -432,7 +432,6 @@ event_trigger_print(const char *name, struct seq_file *m,
 
 /**
  * event_trigger_init - Generic event_trigger_ops @init implementation
- * @ops: The trigger ops associated with the trigger
  * @data: Trigger-specific data
  *
  * Common implementation of event trigger initialization.
@@ -442,8 +441,7 @@ event_trigger_print(const char *name, struct seq_file *m,
  *
  * Return: 0 on success, errno otherwise
  */
-int event_trigger_init(struct event_trigger_ops *ops,
-		       struct event_trigger_data *data)
+int event_trigger_init(struct event_trigger_data *data)
 {
 	data->ref++;
 	return 0;
@@ -451,7 +449,6 @@ int event_trigger_init(struct event_trigger_ops *ops,
 
 /**
  * event_trigger_free - Generic event_trigger_ops @free implementation
- * @ops: The trigger ops associated with the trigger
  * @data: Trigger-specific data
  *
  * Common implementation of event trigger de-initialization.
@@ -460,8 +457,7 @@ int event_trigger_init(struct event_trigger_ops *ops,
  * implementations.
  */
 static void
-event_trigger_free(struct event_trigger_ops *ops,
-		   struct event_trigger_data *data)
+event_trigger_free(struct event_trigger_data *data)
 {
 	if (WARN_ON_ONCE(data->ref <= 0))
 		return;
@@ -515,7 +511,7 @@ clear_event_triggers(struct trace_array *tr)
 			trace_event_trigger_enable_disable(file, 0);
 			list_del_rcu(&data->list);
 			if (data->ops->free)
-				data->ops->free(data->ops, data);
+				data->ops->free(data);
 		}
 	}
 }
@@ -581,7 +577,7 @@ static int register_trigger(char *glob,
 	}
 
 	if (data->ops->init) {
-		ret = data->ops->init(data->ops, data);
+		ret = data->ops->init(data);
 		if (ret < 0)
 			goto out;
 	}
@@ -629,7 +625,7 @@ static void unregister_trigger(char *glob,
 	}
 
 	if (unregistered && data->ops->free)
-		data->ops->free(data->ops, data);
+		data->ops->free(data);
 }
 
 /*
@@ -1049,14 +1045,14 @@ event_trigger_parse(struct event_command *cmd_ops,
 
  out_reg:
 	/* Up the trigger_data count to make sure reg doesn't free it on failure */
-	event_trigger_init(trigger_ops, trigger_data);
+	event_trigger_init(trigger_data);
 
 	ret = event_trigger_register(cmd_ops, file, glob, trigger_data);
 	if (ret)
 		goto out_free;
 
 	/* Down the counter of trigger_data or free it if not used anymore */
-	event_trigger_free(trigger_ops, trigger_data);
+	event_trigger_free(trigger_data);
  out:
 	return ret;
 
@@ -1382,16 +1378,14 @@ traceoff_count_trigger(struct event_trigger_data *data,
 }
 
 static int
-traceon_trigger_print(struct seq_file *m, struct event_trigger_ops *ops,
-		      struct event_trigger_data *data)
+traceon_trigger_print(struct seq_file *m, struct event_trigger_data *data)
 {
 	return event_trigger_print("traceon", m, (void *)data->count,
 				   data->filter_str);
 }
 
 static int
-traceoff_trigger_print(struct seq_file *m, struct event_trigger_ops *ops,
-		       struct event_trigger_data *data)
+traceoff_trigger_print(struct seq_file *m, struct event_trigger_data *data)
 {
 	return event_trigger_print("traceoff", m, (void *)data->count,
 				   data->filter_str);
@@ -1502,8 +1496,7 @@ register_snapshot_trigger(char *glob,
 }
 
 static int
-snapshot_trigger_print(struct seq_file *m, struct event_trigger_ops *ops,
-		       struct event_trigger_data *data)
+snapshot_trigger_print(struct seq_file *m, struct event_trigger_data *data)
 {
 	return event_trigger_print("snapshot", m, (void *)data->count,
 				   data->filter_str);
@@ -1598,8 +1591,7 @@ stacktrace_count_trigger(struct event_trigger_data *data,
 }
 
 static int
-stacktrace_trigger_print(struct seq_file *m, struct event_trigger_ops *ops,
-			 struct event_trigger_data *data)
+stacktrace_trigger_print(struct seq_file *m, struct event_trigger_data *data)
 {
 	return event_trigger_print("stacktrace", m, (void *)data->count,
 				   data->filter_str);
@@ -1689,7 +1681,6 @@ event_enable_count_trigger(struct event_trigger_data *data,
 }
 
 int event_enable_trigger_print(struct seq_file *m,
-			       struct event_trigger_ops *ops,
 			       struct event_trigger_data *data)
 {
 	struct enable_trigger_data *enable_data = data->private_data;
@@ -1714,8 +1705,7 @@ int event_enable_trigger_print(struct seq_file *m,
 	return 0;
 }
 
-void event_enable_trigger_free(struct event_trigger_ops *ops,
-			       struct event_trigger_data *data)
+void event_enable_trigger_free(struct event_trigger_data *data)
 {
 	struct enable_trigger_data *enable_data = data->private_data;
 
@@ -1843,7 +1833,7 @@ int event_enable_trigger_parse(struct event_command *cmd_ops,
 	}
 
 	/* Up the trigger_data count to make sure nothing frees it on failure */
-	event_trigger_init(trigger_ops, trigger_data);
+	event_trigger_init(trigger_data);
 
 	if (trigger) {
 		number = strsep(&trigger, ":");
@@ -1887,7 +1877,7 @@ int event_enable_trigger_parse(struct event_command *cmd_ops,
 	if (ret)
 		goto out_disable;
 
-	event_trigger_free(trigger_ops, trigger_data);
+	event_trigger_free(trigger_data);
  out:
 	return ret;
 
@@ -1898,7 +1888,7 @@ int event_enable_trigger_parse(struct event_command *cmd_ops,
  out_free:
 	if (cmd_ops->set_filter)
 		cmd_ops->set_filter(NULL, trigger_data, NULL);
-	event_trigger_free(trigger_ops, trigger_data);
+	event_trigger_free(trigger_data);
 	kfree(enable_data);
 	goto out;
 }
@@ -1926,7 +1916,7 @@ int event_enable_register_trigger(char *glob,
 	}
 
 	if (data->ops->init) {
-		ret = data->ops->init(data->ops, data);
+		ret = data->ops->init(data);
 		if (ret < 0)
 			goto out;
 	}
@@ -1969,7 +1959,7 @@ void event_enable_unregister_trigger(char *glob,
 	}
 
 	if (unregistered && data->ops->free)
-		data->ops->free(data->ops, data);
+		data->ops->free(data);
 }
 
 static struct event_trigger_ops *
-- 
cgit v1.2.3


From e1f187d09e11f50a50cbb02ae277d4e8bdfc7db8 Mon Sep 17 00:00:00 2001
From: Tom Zanussi
Date: Fri, 4 Feb 2022 16:12:06 -0600
Subject: tracing: Have existing event_command.parse() implementations use
 helpers

Simplify the existing event_command.parse() implementations by having
them make use of the helper functions previously introduced.

Link: https://lkml.kernel.org/r/b353e3427a81f9d3adafd98fd7d73e78a8209f43.1644010576.git.zanussi@kernel.org

Signed-off-by: Tom Zanussi <zanussi@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace.h                |   3 +-
 kernel/trace/trace_eprobe.c         |   3 +-
 kernel/trace/trace_events_hist.c    |  64 ++++++---------
 kernel/trace/trace_events_trigger.c | 150 ++++++++++--------------------------
 4 files changed, 69 insertions(+), 151 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index f3e4cd1bb60e..ff816fb41e48 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1577,7 +1577,8 @@ extern int event_enable_trigger_print(struct seq_file *m,
 extern void event_enable_trigger_free(struct event_trigger_data *data);
 extern int event_enable_trigger_parse(struct event_command *cmd_ops,
 				      struct trace_event_file *file,
-				      char *glob, char *cmd, char *param);
+				      char *glob, char *cmd,
+				      char *param_and_filter);
 extern int event_enable_register_trigger(char *glob,
 					 struct event_trigger_data *data,
 					 struct trace_event_file *file);
diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c
index 9b3dfc9da067..b045fa9f276c 100644
--- a/kernel/trace/trace_eprobe.c
+++ b/kernel/trace/trace_eprobe.c
@@ -546,7 +546,8 @@ static struct event_trigger_ops eprobe_trigger_ops = {
 
 static int eprobe_trigger_cmd_parse(struct event_command *cmd_ops,
 				    struct trace_event_file *file,
-				    char *glob, char *cmd, char *param)
+				    char *glob, char *cmd,
+				    char *param_and_filter)
 {
 	return -1;
 }
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 40a7e5582dfb..1b71bdb0bcb1 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -2785,7 +2785,8 @@ static char *find_trigger_filter(struct hist_trigger_data *hist_data,
 static struct event_command trigger_hist_cmd;
 static int event_hist_trigger_parse(struct event_command *cmd_ops,
 				    struct trace_event_file *file,
-				    char *glob, char *cmd, char *param);
+				    char *glob, char *cmd,
+				    char *param_and_filter);
 
 static bool compatible_keys(struct hist_trigger_data *target_hist_data,
 			    struct hist_trigger_data *hist_data,
@@ -6166,17 +6167,17 @@ static void hist_unreg_all(struct trace_event_file *file)
 
 static int event_hist_trigger_parse(struct event_command *cmd_ops,
 				    struct trace_event_file *file,
-				    char *glob, char *cmd, char *param)
+				    char *glob, char *cmd,
+				    char *param_and_filter)
 {
 	unsigned int hist_trigger_bits = TRACING_MAP_BITS_DEFAULT;
 	struct event_trigger_data *trigger_data;
 	struct hist_trigger_attrs *attrs;
-	struct event_trigger_ops *trigger_ops;
 	struct hist_trigger_data *hist_data;
+	char *param, *filter, *p, *start;
 	struct synth_event *se;
 	const char *se_name;
-	bool remove = false;
-	char *trigger, *p, *start;
+	bool remove;
 	int ret = 0;
 
 	lockdep_assert_held(&event_mutex);
@@ -6185,31 +6186,30 @@ static int event_hist_trigger_parse(struct event_command *cmd_ops,
 
 	if (strlen(glob)) {
 		hist_err_clear();
-		last_cmd_set(file, param);
+		last_cmd_set(file, param_and_filter);
 	}
 
-	if (!param)
-		return -EINVAL;
+	remove = event_trigger_check_remove(glob);
 
-	if (glob[0] == '!')
-		remove = true;
+	if (event_trigger_empty_param(param_and_filter))
+		return -EINVAL;
 
 	/*
 	 * separate the trigger from the filter (k:v [if filter])
 	 * allowing for whitespace in the trigger
 	 */
-	p = trigger = param;
+	p = param = param_and_filter;
 	do {
 		p = strstr(p, "if");
 		if (!p)
 			break;
-		if (p == param)
+		if (p == param_and_filter)
 			return -EINVAL;
 		if (*(p - 1) != ' ' && *(p - 1) != '\t') {
 			p++;
 			continue;
 		}
-		if (p >= param + strlen(param) - (sizeof("if") - 1) - 1)
+		if (p >= param_and_filter + strlen(param_and_filter) - (sizeof("if") - 1) - 1)
 			return -EINVAL;
 		if (*(p + sizeof("if") - 1) != ' ' && *(p + sizeof("if") - 1) != '\t') {
 			p++;
@@ -6219,24 +6219,24 @@ static int event_hist_trigger_parse(struct event_command *cmd_ops,
 	} while (1);
 
 	if (!p)
-		param = NULL;
+		filter = NULL;
 	else {
 		*(p - 1) = '\0';
-		param = strstrip(p);
-		trigger = strstrip(trigger);
+		filter = strstrip(p);
+		param = strstrip(param);
 	}
 
 	/*
 	 * To simplify arithmetic expression parsing, replace occurrences of
 	 * '.sym-offset' modifier with '.symXoffset'
 	 */
-	start = strstr(trigger, ".sym-offset");
+	start = strstr(param, ".sym-offset");
 	while (start) {
 		*(start + 4) = 'X';
 		start = strstr(start + 11, ".sym-offset");
 	}
 
-	attrs = parse_hist_trigger_attrs(file->tr, trigger);
+	attrs = parse_hist_trigger_attrs(file->tr, param);
 	if (IS_ERR(attrs))
 		return PTR_ERR(attrs);
 
@@ -6249,29 +6249,15 @@ static int event_hist_trigger_parse(struct event_command *cmd_ops,
 		return PTR_ERR(hist_data);
 	}
 
-	trigger_ops = cmd_ops->get_trigger_ops(cmd, trigger);
-
-	trigger_data = kzalloc(sizeof(*trigger_data), GFP_KERNEL);
+	trigger_data = event_trigger_alloc(cmd_ops, cmd, param, hist_data);
 	if (!trigger_data) {
 		ret = -ENOMEM;
 		goto out_free;
 	}
 
-	trigger_data->count = -1;
-	trigger_data->ops = trigger_ops;
-	trigger_data->cmd_ops = cmd_ops;
-
-	INIT_LIST_HEAD(&trigger_data->list);
-	RCU_INIT_POINTER(trigger_data->filter, NULL);
-
-	trigger_data->private_data = hist_data;
-
-	/* if param is non-empty, it's supposed to be a filter */
-	if (param && cmd_ops->set_filter) {
-		ret = cmd_ops->set_filter(param, trigger_data, file);
-		if (ret < 0)
-			goto out_free;
-	}
+	ret = event_trigger_set_filter(cmd_ops, file, filter, trigger_data);
+	if (ret < 0)
+		goto out_free;
 
 	if (remove) {
 		if (!have_hist_trigger_match(trigger_data, file))
@@ -6298,8 +6284,7 @@ static int event_hist_trigger_parse(struct event_command *cmd_ops,
 		if (!(attrs->pause || attrs->cont || attrs->clear))
 			ret = -ENOENT;
 		goto out_free;
-	} else if (ret < 0)
-		goto out_free;
+	}
 
 	if (get_named_trigger_data(trigger_data))
 		goto enable;
@@ -6331,8 +6316,7 @@ enable:
  out_unreg:
 	event_trigger_unregister(cmd_ops, file, glob+1, trigger_data);
  out_free:
-	if (cmd_ops->set_filter)
-		cmd_ops->set_filter(NULL, trigger_data, NULL);
+	event_trigger_reset_filter(cmd_ops, trigger_data);
 
 	remove_hist_vars(hist_data);
 
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 32202175875d..62c44dab8f46 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -965,7 +965,7 @@ void event_trigger_unregister(struct event_command *cmd_ops,
  * @file: The trace_event_file associated with the event
  * @glob: The raw string used to register the trigger
  * @cmd: The cmd portion of the string used to register the trigger
- * @param: The params portion of the string used to register the trigger
+ * @param_and_filter: The param and filter portion of the string used to register the trigger
  *
  * Common implementation for event command parsing and trigger
  * instantiation.
@@ -978,72 +978,39 @@ void event_trigger_unregister(struct event_command *cmd_ops,
 static int
 event_trigger_parse(struct event_command *cmd_ops,
 		    struct trace_event_file *file,
-		    char *glob, char *cmd, char *param)
+		    char *glob, char *cmd, char *param_and_filter)
 {
 	struct event_trigger_data *trigger_data;
-	struct event_trigger_ops *trigger_ops;
-	char *trigger = NULL;
-	char *number;
+	char *param, *filter;
+	bool remove;
 	int ret;
 
-	/* separate the trigger from the filter (t:n [if filter]) */
-	if (param && isdigit(param[0])) {
-		trigger = strsep(&param, " \t");
-		if (param) {
-			param = skip_spaces(param);
-			if (!*param)
-				param = NULL;
-		}
-	}
+	remove = event_trigger_check_remove(glob);
 
-	trigger_ops = cmd_ops->get_trigger_ops(cmd, trigger);
+	ret = event_trigger_separate_filter(param_and_filter, &param, &filter, false);
+	if (ret)
+		return ret;
 
 	ret = -ENOMEM;
-	trigger_data = kzalloc(sizeof(*trigger_data), GFP_KERNEL);
+	trigger_data = event_trigger_alloc(cmd_ops, cmd, param, file);
 	if (!trigger_data)
 		goto out;
 
-	trigger_data->count = -1;
-	trigger_data->ops = trigger_ops;
-	trigger_data->cmd_ops = cmd_ops;
-	trigger_data->private_data = file;
-	INIT_LIST_HEAD(&trigger_data->list);
-	INIT_LIST_HEAD(&trigger_data->named_list);
-
-	if (glob[0] == '!') {
+	if (remove) {
 		event_trigger_unregister(cmd_ops, file, glob+1, trigger_data);
 		kfree(trigger_data);
 		ret = 0;
 		goto out;
 	}
 
-	if (trigger) {
-		number = strsep(&trigger, ":");
-
-		ret = -EINVAL;
-		if (!strlen(number))
-			goto out_free;
-
-		/*
-		 * We use the callback data field (which is a pointer)
-		 * as our counter.
-		 */
-		ret = kstrtoul(number, 0, &trigger_data->count);
-		if (ret)
-			goto out_free;
-	}
-
-	if (!param) /* if param is non-empty, it's supposed to be a filter */
-		goto out_reg;
-
-	if (!cmd_ops->set_filter)
-		goto out_reg;
+	ret = event_trigger_parse_num(param, trigger_data);
+	if (ret)
+		goto out_free;
 
-	ret = cmd_ops->set_filter(param, trigger_data, file);
+	ret = event_trigger_set_filter(cmd_ops, file, filter, trigger_data);
 	if (ret < 0)
 		goto out_free;
 
- out_reg:
 	/* Up the trigger_data count to make sure reg doesn't free it on failure */
 	event_trigger_init(trigger_data);
 
@@ -1057,8 +1024,7 @@ event_trigger_parse(struct event_command *cmd_ops,
 	return ret;
 
  out_free:
-	if (cmd_ops->set_filter)
-		cmd_ops->set_filter(NULL, trigger_data, NULL);
+	event_trigger_reset_filter(cmd_ops, trigger_data);
 	kfree(trigger_data);
 	goto out;
 }
@@ -1752,39 +1718,33 @@ static struct event_trigger_ops event_disable_count_trigger_ops = {
 
 int event_enable_trigger_parse(struct event_command *cmd_ops,
 			       struct trace_event_file *file,
-			       char *glob, char *cmd, char *param)
+			       char *glob, char *cmd, char *param_and_filter)
 {
 	struct trace_event_file *event_enable_file;
 	struct enable_trigger_data *enable_data;
 	struct event_trigger_data *trigger_data;
-	struct event_trigger_ops *trigger_ops;
 	struct trace_array *tr = file->tr;
+	char *param, *filter;
+	bool enable, remove;
 	const char *system;
 	const char *event;
 	bool hist = false;
-	char *trigger;
-	char *number;
-	bool enable;
 	int ret;
 
-	if (!param)
-		return -EINVAL;
+	remove = event_trigger_check_remove(glob);
 
-	/* separate the trigger from the filter (s:e:n [if filter]) */
-	trigger = strsep(&param, " \t");
-	if (!trigger)
+	if (event_trigger_empty_param(param_and_filter))
 		return -EINVAL;
-	if (param) {
-		param = skip_spaces(param);
-		if (!*param)
-			param = NULL;
-	}
 
-	system = strsep(&trigger, ":");
-	if (!trigger)
+	ret = event_trigger_separate_filter(param_and_filter, &param, &filter, true);
+	if (ret)
+		return ret;
+
+	system = strsep(&param, ":");
+	if (!param)
 		return -EINVAL;
 
-	event = strsep(&trigger, ":");
+	event = strsep(&param, ":");
 
 	ret = -EINVAL;
 	event_enable_file = find_event_file(tr, system, event);
@@ -1800,31 +1760,23 @@ int event_enable_trigger_parse(struct event_command *cmd_ops,
 #else
 	enable = strcmp(cmd, ENABLE_EVENT_STR) == 0;
 #endif
-	trigger_ops = cmd_ops->get_trigger_ops(cmd, trigger);
-
 	ret = -ENOMEM;
-	trigger_data = kzalloc(sizeof(*trigger_data), GFP_KERNEL);
-	if (!trigger_data)
-		goto out;
 
 	enable_data = kzalloc(sizeof(*enable_data), GFP_KERNEL);
-	if (!enable_data) {
-		kfree(trigger_data);
+	if (!enable_data)
 		goto out;
-	}
-
-	trigger_data->count = -1;
-	trigger_data->ops = trigger_ops;
-	trigger_data->cmd_ops = cmd_ops;
-	INIT_LIST_HEAD(&trigger_data->list);
-	RCU_INIT_POINTER(trigger_data->filter, NULL);
 
 	enable_data->hist = hist;
 	enable_data->enable = enable;
 	enable_data->file = event_enable_file;
-	trigger_data->private_data = enable_data;
 
-	if (glob[0] == '!') {
+	trigger_data = event_trigger_alloc(cmd_ops, cmd, param, enable_data);
+	if (!trigger_data) {
+		kfree(enable_data);
+		goto out;
+	}
+
+	if (remove) {
 		event_trigger_unregister(cmd_ops, file, glob+1, trigger_data);
 		kfree(trigger_data);
 		kfree(enable_data);
@@ -1835,33 +1787,14 @@ int event_enable_trigger_parse(struct event_command *cmd_ops,
 	/* Up the trigger_data count to make sure nothing frees it on failure */
 	event_trigger_init(trigger_data);
 
-	if (trigger) {
-		number = strsep(&trigger, ":");
-
-		ret = -EINVAL;
-		if (!strlen(number))
-			goto out_free;
-
-		/*
-		 * We use the callback data field (which is a pointer)
-		 * as our counter.
-		 */
-		ret = kstrtoul(number, 0, &trigger_data->count);
-		if (ret)
-			goto out_free;
-	}
-
-	if (!param) /* if param is non-empty, it's supposed to be a filter */
-		goto out_reg;
-
-	if (!cmd_ops->set_filter)
-		goto out_reg;
+	ret = event_trigger_parse_num(param, trigger_data);
+	if (ret)
+		goto out_free;
 
-	ret = cmd_ops->set_filter(param, trigger_data, file);
+	ret = event_trigger_set_filter(cmd_ops, file, filter, trigger_data);
 	if (ret < 0)
 		goto out_free;
 
- out_reg:
 	/* Don't let event modules unload while probe registered */
 	ret = trace_event_try_get_ref(event_enable_file->event_call);
 	if (!ret) {
@@ -1880,16 +1813,15 @@ int event_enable_trigger_parse(struct event_command *cmd_ops,
 	event_trigger_free(trigger_data);
  out:
 	return ret;
-
  out_disable:
 	trace_event_enable_disable(event_enable_file, 0, 1);
  out_put:
 	trace_event_put_ref(event_enable_file->event_call);
  out_free:
-	if (cmd_ops->set_filter)
-		cmd_ops->set_filter(NULL, trigger_data, NULL);
+	event_trigger_reset_filter(cmd_ops, trigger_data);
 	event_trigger_free(trigger_data);
 	kfree(enable_data);
+
 	goto out;
 }
 
-- 
cgit v1.2.3


From a7e6b7dcfb19988ad2968a1fafd29b600abbf133 Mon Sep 17 00:00:00 2001
From: Tom Zanussi
Date: Fri, 4 Feb 2022 16:12:07 -0600
Subject: tracing: Separate hist state updates from hist registration

hist_register_trigger() handles both new hist registration as well as
existing hist registration through event_command.reg().

Adding a new function, existing_hist_update_only(), that checks and
updates existing histograms and exits after doing so allows the
confusing logic in event_hist_trigger_parse() to be simplified.

Link: https://lkml.kernel.org/r/211b2cd3e3d7e00f4f8ad45ef8b33063da6a7e05.1644010576.git.zanussi@kernel.org

Signed-off-by: Tom Zanussi <zanussi@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_events_hist.c | 66 +++++++++++++++++++++++++++++-----------
 1 file changed, 48 insertions(+), 18 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 1b71bdb0bcb1..998dfe2162fc 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -5929,6 +5929,48 @@ static bool hist_trigger_match(struct event_trigger_data *data,
 	return true;
 }
 
+static bool existing_hist_update_only(char *glob,
+				      struct event_trigger_data *data,
+				      struct trace_event_file *file)
+{
+	struct hist_trigger_data *hist_data = data->private_data;
+	struct event_trigger_data *test, *named_data = NULL;
+	bool updated = false;
+
+	if (!hist_data->attrs->pause && !hist_data->attrs->cont &&
+	    !hist_data->attrs->clear)
+		goto out;
+
+	if (hist_data->attrs->name) {
+		named_data = find_named_trigger(hist_data->attrs->name);
+		if (named_data) {
+			if (!hist_trigger_match(data, named_data, named_data,
+						true))
+				goto out;
+		}
+	}
+
+	if (hist_data->attrs->name && !named_data)
+		goto out;
+
+	list_for_each_entry(test, &file->triggers, list) {
+		if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
+			if (!hist_trigger_match(data, test, named_data, false))
+				continue;
+			if (hist_data->attrs->pause)
+				test->paused = true;
+			else if (hist_data->attrs->cont)
+				test->paused = false;
+			else if (hist_data->attrs->clear)
+				hist_clear(test);
+			updated = true;
+			goto out;
+		}
+	}
+ out:
+	return updated;
+}
+
 static int hist_register_trigger(char *glob,
 				 struct event_trigger_data *data,
 				 struct trace_event_file *file)
@@ -5957,19 +5999,11 @@ static int hist_register_trigger(char *glob,
 
 	list_for_each_entry(test, &file->triggers, list) {
 		if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
-			if (!hist_trigger_match(data, test, named_data, false))
-				continue;
-			if (hist_data->attrs->pause)
-				test->paused = true;
-			else if (hist_data->attrs->cont)
-				test->paused = false;
-			else if (hist_data->attrs->clear)
-				hist_clear(test);
-			else {
+			if (hist_trigger_match(data, test, named_data, false)) {
 				hist_err(tr, HIST_ERR_TRIGGER_EEXIST, 0);
 				ret = -EEXIST;
+				goto out;
 			}
-			goto out;
 		}
 	}
  new:
@@ -6008,8 +6042,6 @@ static int hist_register_trigger(char *glob,
 
 	if (named_data)
 		destroy_hist_data(hist_data);
-
-	ret++;
  out:
 	return ret;
 }
@@ -6277,14 +6309,12 @@ static int event_hist_trigger_parse(struct event_command *cmd_ops,
 		goto out_free;
 	}
 
-	ret = event_trigger_register(cmd_ops, file, glob, trigger_data);
-	if (ret)
+	if (existing_hist_update_only(glob, trigger_data, file))
 		goto out_free;
-	if (ret == 0) {
-		if (!(attrs->pause || attrs->cont || attrs->clear))
-			ret = -ENOENT;
+
+	ret = event_trigger_register(cmd_ops, file, glob, trigger_data);
+	if (ret < 0)
 		goto out_free;
-	}
 
 	if (get_named_trigger_data(trigger_data))
 		goto enable;
-- 
cgit v1.2.3


From cf2adec7479d875973fe10782f8bf20377628ef2 Mon Sep 17 00:00:00 2001
From: Oscar Shiang
Date: Thu, 17 Feb 2022 00:50:06 +0800
Subject: tracing: Fix inconsistent style of mini-HOWTO

Each description should start with a hyphen and a space. Insert
spaces to fix it.

Link: https://lkml.kernel.org/r/TYCP286MB19130AA4A9C6FC5A8793DED2A1359@TYCP286MB1913.JPNP286.PROD.OUTLOOK.COM

Signed-off-by: Oscar Shiang <oscar0225@livemail.tw>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index f4de111fa18f..4f9c499368c4 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -5475,7 +5475,7 @@ static const char readme_msg[] =
 	"  error_log\t- error log for failed commands (that support it)\n"
 	"  buffer_size_kb\t- view and modify size of per cpu buffer\n"
 	"  buffer_total_size_kb  - view total size of all cpu buffers\n\n"
-	"  trace_clock\t\t-change the clock used to order events\n"
+	"  trace_clock\t\t- change the clock used to order events\n"
 	"       local:   Per cpu clock but may not be synced across CPUs\n"
 	"      global:   Synced across CPUs but slows tracing down.\n"
 	"     counter:   Not a clock, but just an increment\n"
@@ -5484,7 +5484,7 @@ static const char readme_msg[] =
 #ifdef CONFIG_X86_64
 	"     x86-tsc:   TSC cycle counter\n"
 #endif
-	"\n  timestamp_mode\t-view the mode used to timestamp events\n"
+	"\n  timestamp_mode\t- view the mode used to timestamp events\n"
 	"       delta:   Delta difference against a buffer-wide timestamp\n"
 	"    absolute:   Absolute (standalone) timestamp\n"
 	"\n  trace_marker\t\t- Writes into this file writes into the kernel buffer\n"
-- 
cgit v1.2.3


From 3b57d8477cd0f427198930706958f1312cc3594b Mon Sep 17 00:00:00 2001
From: Jiapeng Chong
Date: Fri, 18 Feb 2022 18:08:49 +0800
Subject: tracing: Fix kernel-doc

Fix the following W=1 kernel warnings:

kernel/trace/trace.c:1181: warning: expecting prototype for
tracing_snapshot_cond_data(). Prototype was for
tracing_cond_snapshot_data() instead.

Link: https://lkml.kernel.org/r/20220218100849.122038-1-jiapeng.chong@linux.alibaba.com

Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Signed-off-by: Jiapeng Chong <jiapeng.chong@linux.alibaba.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 4f9c499368c4..aceeeea21c11 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1174,7 +1174,7 @@ void tracing_snapshot_cond(struct trace_array *tr, void *cond_data)
 EXPORT_SYMBOL_GPL(tracing_snapshot_cond);
 
 /**
- * tracing_snapshot_cond_data - get the user data associated with a snapshot
+ * tracing_cond_snapshot_data - get the user data associated with a snapshot
  * @tr:		The tracing instance
  *
  * When the user enables a conditional snapshot using
-- 
cgit v1.2.3


From adaa0a9f06d127b6a0a1b929ec0971df40993a9b Mon Sep 17 00:00:00 2001
From: Yang Li
Date: Sat, 2 Apr 2022 15:20:15 +0800
Subject: tracing: Fix tracing_map_sort_entries() kernel-doc comment

Add the description of @n_sort_keys and make @sort_key ->
@sort_keys in tracing_map_sort_entries() kernel-doc comment
to remove warnings found by running scripts/kernel-doc, which
is caused by using 'make W=1'.

kernel/trace/tracing_map.c:1073: warning: Function parameter or member
'sort_keys' not described in 'tracing_map_sort_entries'
kernel/trace/tracing_map.c:1073: warning: Function parameter or member
'n_sort_keys' not described in 'tracing_map_sort_entries'
kernel/trace/tracing_map.c:1073: warning: Excess function parameter
'sort_key' description in 'tracing_map_sort_entries'

Link: https://lkml.kernel.org/r/20220402072015.45864-1-yang.lee@linux.alibaba.com

Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Signed-off-by: Yang Li <yang.lee@linux.alibaba.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/tracing_map.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c
index 9628b5571846..9901708ce6b8 100644
--- a/kernel/trace/tracing_map.c
+++ b/kernel/trace/tracing_map.c
@@ -1045,7 +1045,8 @@ static void sort_secondary(struct tracing_map *map,
 /**
  * tracing_map_sort_entries - Sort the current set of tracing_map_elts in a map
  * @map: The tracing_map
- * @sort_key: The sort key to use for sorting
+ * @sort_keys: The sort key to use for sorting
+ * @n_sort_keys: hitcount, always have at least one
  * @sort_entries: outval: pointer to allocated and sorted array of entries
  *
  * tracing_map_sort_entries() sorts the current set of entries in the
-- 
cgit v1.2.3


From cb1c45fb68b8a4285ccf750842b1136f26cfe267 Mon Sep 17 00:00:00 2001
From: Jeff Xie
Date: Sun, 10 Apr 2022 22:50:25 +0800
Subject: tracing: Make tp_printk work on syscall tracepoints

Currently the tp_printk option has no effect on syscall tracepoint.
When adding the kernel option parameter tp_printk, then:

echo 1 > /sys/kernel/debug/tracing/events/syscalls/enable

When running any application, no trace information is printed on the
terminal.

Now added printk for syscall tracepoints.

Link: https://lkml.kernel.org/r/20220410145025.681144-1-xiehuan09@gmail.com

Signed-off-by: Jeff Xie <xiehuan09@gmail.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_syscalls.c | 35 +++++++++++------------------------
 1 file changed, 11 insertions(+), 24 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index f755bde42fd0..b69e207012c9 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -154,7 +154,7 @@ print_syscall_enter(struct trace_iterator *iter, int flags,
 			goto end;
 
 		/* parameter types */
-		if (tr->trace_flags & TRACE_ITER_VERBOSE)
+		if (tr && tr->trace_flags & TRACE_ITER_VERBOSE)
 			trace_seq_printf(s, "%s ", entry->types[i]);
 
 		/* parameter values */
@@ -296,9 +296,7 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
 	struct trace_event_file *trace_file;
 	struct syscall_trace_enter *entry;
 	struct syscall_metadata *sys_data;
-	struct ring_buffer_event *event;
-	struct trace_buffer *buffer;
-	unsigned int trace_ctx;
+	struct trace_event_buffer fbuffer;
 	unsigned long args[6];
 	int syscall_nr;
 	int size;
@@ -321,20 +319,16 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
 
 	size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args;
 
-	trace_ctx = tracing_gen_ctx();
-
-	event = trace_event_buffer_lock_reserve(&buffer, trace_file,
-			sys_data->enter_event->event.type, size, trace_ctx);
-	if (!event)
+	entry = trace_event_buffer_reserve(&fbuffer, trace_file, size);
+	if (!entry)
 		return;
 
-	entry = ring_buffer_event_data(event);
+	entry = ring_buffer_event_data(fbuffer.event);
 	entry->nr = syscall_nr;
 	syscall_get_arguments(current, regs, args);
 	memcpy(entry->args, args, sizeof(unsigned long) * sys_data->nb_args);
 
-	event_trigger_unlock_commit(trace_file, buffer, event, entry,
-				    trace_ctx);
+	trace_event_buffer_commit(&fbuffer);
 }
 
 static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
@@ -343,9 +337,7 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
 	struct trace_event_file *trace_file;
 	struct syscall_trace_exit *entry;
 	struct syscall_metadata *sys_data;
-	struct ring_buffer_event *event;
-	struct trace_buffer *buffer;
-	unsigned int trace_ctx;
+	struct trace_event_buffer fbuffer;
 	int syscall_nr;
 
 	syscall_nr = trace_get_syscall_nr(current, regs);
@@ -364,20 +356,15 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
 	if (!sys_data)
 		return;
 
-	trace_ctx = tracing_gen_ctx();
-
-	event = trace_event_buffer_lock_reserve(&buffer, trace_file,
-			sys_data->exit_event->event.type, sizeof(*entry),
-			trace_ctx);
-	if (!event)
+	entry = trace_event_buffer_reserve(&fbuffer, trace_file, sizeof(*entry));
+	if (!entry)
 		return;
 
-	entry = ring_buffer_event_data(event);
+	entry = ring_buffer_event_data(fbuffer.event);
 	entry->nr = syscall_nr;
 	entry->ret = syscall_get_return_value(current, regs);
 
-	event_trigger_unlock_commit(trace_file, buffer, event, entry,
-				    trace_ctx);
+	trace_event_buffer_commit(&fbuffer);
 }
 
 static int reg_event_syscall_enter(struct trace_event_file *file,
-- 
cgit v1.2.3


From 97a5d2e5e35f119b6d7a37c7538773ae7af82dd5 Mon Sep 17 00:00:00 2001
From: Ammar Faizi
Date: Mon, 18 Apr 2022 01:56:29 +0700
Subject: tracing: Return -EINVAL if WARN_ON(!glob) triggered in
 event_hist_trigger_parse()

If `WARN_ON(!glob)` is ever triggered, we will still continue executing
the next lines. This will trigger the more serious problem, a NULL
pointer dereference bug.

Just return -EINVAL if @glob is NULL.

Link: https://lkml.kernel.org/r/20220417185630.199062-2-ammarfaizi2@gnuweeb.org

Cc: Ingo Molnar <mingo@redhat.com>
Cc: GNU/Weeb Mailing List <gwml@vger.gnuweeb.org>
Signed-off-by: Ammar Faizi <ammarfaizi2@gnuweeb.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_events_hist.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 998dfe2162fc..80c25be23c45 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -6214,7 +6214,8 @@ static int event_hist_trigger_parse(struct event_command *cmd_ops,
 
 	lockdep_assert_held(&event_mutex);
 
-	WARN_ON(!glob);
+	if (WARN_ON(!glob))
+		return -EINVAL;
 
 	if (strlen(glob)) {
 		hist_err_clear();
-- 
cgit v1.2.3


From 69686fcbdcc0b6fed3b8d0907e641f282df2f827 Mon Sep 17 00:00:00 2001
From: Ammar Faizi
Date: Mon, 18 Apr 2022 01:56:30 +0700
Subject: tracing: Change `if (strlen(glob))` to `if (glob[0])`

No need to traverse to the end of string. If the first byte is not a NUL
char, it's guaranteed `if (strlen(glob))` is true.

Link: https://lkml.kernel.org/r/20220417185630.199062-3-ammarfaizi2@gnuweeb.org

Cc: Ingo Molnar <mingo@redhat.com>
Cc: GNU/Weeb Mailing List <gwml@vger.gnuweeb.org>
Signed-off-by: Ammar Faizi <ammarfaizi2@gnuweeb.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_events_hist.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 80c25be23c45..fe10179893c1 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -6217,7 +6217,7 @@ static int event_hist_trigger_parse(struct event_command *cmd_ops,
 	if (WARN_ON(!glob))
 		return -EINVAL;
 
-	if (strlen(glob)) {
+	if (glob[0]) {
 		hist_err_clear();
 		last_cmd_set(file, param_and_filter);
 	}
-- 
cgit v1.2.3


From 12025abdc8539ed9d5014e2d647a3fd1bd3de5cd Mon Sep 17 00:00:00 2001
From: Jun Miao
Date: Tue, 19 Apr 2022 09:39:10 +0800
Subject: tracing: Fix sleeping function called from invalid context on RT
 kernel

When setting bootparams="trace_event=initcall:initcall_start tp_printk=1" in the
cmdline, the output_printk() was called, and the spin_lock_irqsave() was called in the
atomic and irq disable interrupt context suitation. On the PREEMPT_RT kernel,
these locks are replaced with sleepable rt-spinlock, so the stack calltrace will
be triggered.
Fix it by raw_spin_lock_irqsave when PREEMPT_RT and "trace_event=initcall:initcall_start
tp_printk=1" enabled.

 BUG: sleeping function called from invalid context at kernel/locking/spinlock_rt.c:46
 in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 1, name: swapper/0
 preempt_count: 2, expected: 0
 RCU nest depth: 0, expected: 0
 Preemption disabled at:
 [<ffffffff8992303e>] try_to_wake_up+0x7e/0xba0
 CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.17.1-rt17+ #19 34c5812404187a875f32bee7977f7367f9679ea7
 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-2 04/01/2014
 Call Trace:
  <TASK>
  dump_stack_lvl+0x60/0x8c
  dump_stack+0x10/0x12
  __might_resched.cold+0x11d/0x155
  rt_spin_lock+0x40/0x70
  trace_event_buffer_commit+0x2fa/0x4c0
  ? map_vsyscall+0x93/0x93
  trace_event_raw_event_initcall_start+0xbe/0x110
  ? perf_trace_initcall_finish+0x210/0x210
  ? probe_sched_wakeup+0x34/0x40
  ? ttwu_do_wakeup+0xda/0x310
  ? trace_hardirqs_on+0x35/0x170
  ? map_vsyscall+0x93/0x93
  do_one_initcall+0x217/0x3c0
  ? trace_event_raw_event_initcall_level+0x170/0x170
  ? push_cpu_stop+0x400/0x400
  ? cblist_init_generic+0x241/0x290
  kernel_init_freeable+0x1ac/0x347
  ? _raw_spin_unlock_irq+0x65/0x80
  ? rest_init+0xf0/0xf0
  kernel_init+0x1e/0x150
  ret_from_fork+0x22/0x30
  </TASK>

Link: https://lkml.kernel.org/r/20220419013910.894370-1-jun.miao@intel.com

Signed-off-by: Jun Miao <jun.miao@intel.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index aceeeea21c11..27bb486c3f97 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2835,7 +2835,7 @@ trace_event_buffer_lock_reserve(struct trace_buffer **current_rb,
 }
 EXPORT_SYMBOL_GPL(trace_event_buffer_lock_reserve);
 
-static DEFINE_SPINLOCK(tracepoint_iter_lock);
+static DEFINE_RAW_SPINLOCK(tracepoint_iter_lock);
 static DEFINE_MUTEX(tracepoint_printk_mutex);
 
 static void output_printk(struct trace_event_buffer *fbuffer)
@@ -2863,14 +2863,14 @@ static void output_printk(struct trace_event_buffer *fbuffer)
 
 	event = &fbuffer->trace_file->event_call->event;
 
-	spin_lock_irqsave(&tracepoint_iter_lock, flags);
+	raw_spin_lock_irqsave(&tracepoint_iter_lock, flags);
 	trace_seq_init(&iter->seq);
 	iter->ent = fbuffer->entry;
 	event_call->event.funcs->trace(iter, 0, event);
 	trace_seq_putc(&iter->seq, 0);
 	printk("%s", iter->seq.buffer);
 
-	spin_unlock_irqrestore(&tracepoint_iter_lock, flags);
+	raw_spin_unlock_irqrestore(&tracepoint_iter_lock, flags);
 }
 
 int tracepoint_printk_sysctl(struct ctl_table *table, int write,
-- 
cgit v1.2.3


From 4ee51101e93f0c8d83876ae5c0c26ca14934629e Mon Sep 17 00:00:00 2001
From: Guo Zhengkui
Date: Sun, 24 Apr 2022 21:19:32 +0800
Subject: tracing: Use WARN instead of printk and WARN_ON

Use `WARN(cond, ...)` instead of `if (cond)` + `printk(...)` +
`WARN_ON(1)`.

Link: https://lkml.kernel.org/r/20220424131932.3606-1-guozhengkui@vivo.com

Suggested-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Guo Zhengkui <guozhengkui@vivo.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_output.c | 12 +++---------
 1 file changed, 3 insertions(+), 9 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 8aa493d25c73..d89e3f7e26eb 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -778,9 +778,8 @@ int register_trace_event(struct trace_event *event)
 
 		list_add_tail(&event->list, list);
 
-	} else if (event->type > __TRACE_LAST_TYPE) {
-		printk(KERN_WARNING "Need to add type to trace.h\n");
-		WARN_ON(1);
+	} else if (WARN(event->type > __TRACE_LAST_TYPE,
+			"Need to add type to trace.h")) {
 		goto out;
 	} else {
 		/* Is this event already used */
@@ -1571,13 +1570,8 @@ __init static int init_events(void)
 
 	for (i = 0; events[i]; i++) {
 		event = events[i];
-
 		ret = register_trace_event(event);
-		if (!ret) {
-			printk(KERN_WARNING "event %d failed to register\n",
-			       event->type);
-			WARN_ON_ONCE(1);
-		}
+		WARN_ONCE(!ret, "event %d failed to register", event->type);
 	}
 
 	return 0;
-- 
cgit v1.2.3


From ed888241a0ab9a3606bd986be6f0abafa1afdf19 Mon Sep 17 00:00:00 2001
From: Wan Jiabing
Date: Tue, 26 Apr 2022 15:06:28 +0800
Subject: ring-buffer: Simplify if-if to if-else

Use if and else instead of if(A) and if (!A).

Link: https://lkml.kernel.org/r/20220426070628.167565-1-wanjiabing@vivo.com

Signed-off-by: Wan Jiabing <wanjiabing@vivo.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/ring_buffer.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 05dfc7a12d3d..655d6db3e3c3 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -6011,10 +6011,10 @@ static __init int test_ringbuffer(void)
 		pr_info("        total events:   %ld\n", total_lost + total_read);
 		pr_info("  recorded len bytes:   %ld\n", total_len);
 		pr_info(" recorded size bytes:   %ld\n", total_size);
-		if (total_lost)
+		if (total_lost) {
 			pr_info(" With dropped events, record len and size may not match\n"
 				" alloced and written from above\n");
-		if (!total_lost) {
+		} else {
 			if (RB_WARN_ON(buffer, total_len != total_alloc ||
 				       total_size != total_written))
 				break;
-- 
cgit v1.2.3


From ef9188bcc6ca1d8a2ad83e826b548e6820721061 Mon Sep 17 00:00:00 2001
From: Mark-PK Tsai
Date: Tue, 26 Apr 2022 20:24:06 +0800
Subject: tracing: Avoid adding tracer option before update_tracer_options

To prepare for support asynchronous tracer_init_tracefs initcall,
avoid calling create_trace_option_files before __update_tracer_options.
Otherwise, create_trace_option_files will show warning because
some tracers in trace_types list are already in tr->topts.

For example, hwlat_tracer call register_tracer in late_initcall,
and global_trace.dir is already created in tracing_init_dentry,
hwlat_tracer will be put into tr->topts.
Then if the __update_tracer_options is executed after hwlat_tracer
registered, create_trace_option_files find that hwlat_tracer is
already in tr->topts.

Link: https://lkml.kernel.org/r/20220426122407.17042-2-mark-pk.tsai@mediatek.com

Link: https://lore.kernel.org/lkml/20220322133339.GA32582@xsang-OptiPlex-9020/
Reported-by: kernel test robot <oliver.sang@intel.com>
Signed-off-by: Mark-PK Tsai <mark-pk.tsai@mediatek.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 27bb486c3f97..7275173c55d0 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -6332,12 +6332,18 @@ static void tracing_set_nop(struct trace_array *tr)
 	tr->current_trace = &nop_trace;
 }
 
+static bool tracer_options_updated;
+
 static void add_tracer_options(struct trace_array *tr, struct tracer *t)
 {
 	/* Only enable if the directory has been created already. */
 	if (!tr->dir)
 		return;
 
+	/* Only create trace option files after update_tracer_options finish */
+	if (!tracer_options_updated)
+		return;
+
 	create_trace_option_files(tr, t);
 }
 
@@ -9176,6 +9182,7 @@ static void __update_tracer_options(struct trace_array *tr)
 static void update_tracer_options(struct trace_array *tr)
 {
 	mutex_lock(&trace_types_lock);
+	tracer_options_updated = true;
 	__update_tracer_options(tr);
 	mutex_unlock(&trace_types_lock);
 }
-- 
cgit v1.2.3


From 6621a7004684bfcff5af4c8e4d37989941f42a6b Mon Sep 17 00:00:00 2001
From: Mark-PK Tsai
Date: Tue, 26 Apr 2022 20:24:07 +0800
Subject: tracing: make tracer_init_tracefs initcall asynchronous

Move trace_eval_init() to subsys_initcall to make it start
earlier.
And to avoid tracer_init_tracefs being blocked by
trace_event_sem which trace_eval_init() hold [1],
queue tracer_init_tracefs() to eval_map_wq to let
the two works being executed sequentially.

It can speed up the initialization of kernel as result
of making tracer_init_tracefs asynchronous.

On my arm64 platform, it reduce ~20ms of 125ms which total
time do_initcalls spend.

Link: https://lkml.kernel.org/r/20220426122407.17042-3-mark-pk.tsai@mediatek.com

[1]: https://lore.kernel.org/r/68d7b3327052757d0cd6359a6c9015a85b437232.camel@pengutronix.de
Signed-off-by: Mark-PK Tsai <mark-pk.tsai@mediatek.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 32 ++++++++++++++++++++++----------
 1 file changed, 22 insertions(+), 10 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 7275173c55d0..400d3e9fe9ff 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -9615,6 +9615,7 @@ extern struct trace_eval_map *__stop_ftrace_eval_maps[];
 
 static struct workqueue_struct *eval_map_wq __initdata;
 static struct work_struct eval_map_work __initdata;
+static struct work_struct tracerfs_init_work __initdata;
 
 static void __init eval_map_work_func(struct work_struct *work)
 {
@@ -9640,6 +9641,8 @@ static int __init trace_eval_init(void)
 	return 0;
 }
 
+subsys_initcall(trace_eval_init);
+
 static int __init trace_eval_sync(void)
 {
 	/* Make sure the eval map updates are finished */
@@ -9722,15 +9725,8 @@ static struct notifier_block trace_module_nb = {
 };
 #endif /* CONFIG_MODULES */
 
-static __init int tracer_init_tracefs(void)
+static __init void tracer_init_tracefs_work_func(struct work_struct *work)
 {
-	int ret;
-
-	trace_access_lock_init();
-
-	ret = tracing_init_dentry();
-	if (ret)
-		return 0;
 
 	event_trace_init();
 
@@ -9752,8 +9748,6 @@ static __init int tracer_init_tracefs(void)
 	trace_create_file("saved_tgids", TRACE_MODE_READ, NULL,
 			NULL, &tracing_saved_tgids_fops);
 
-	trace_eval_init();
-
 	trace_create_eval_file(NULL);
 
 #ifdef CONFIG_MODULES
@@ -9768,6 +9762,24 @@ static __init int tracer_init_tracefs(void)
 	create_trace_instances(NULL);
 
 	update_tracer_options(&global_trace);
+}
+
+static __init int tracer_init_tracefs(void)
+{
+	int ret;
+
+	trace_access_lock_init();
+
+	ret = tracing_init_dentry();
+	if (ret)
+		return 0;
+
+	if (eval_map_wq) {
+		INIT_WORK(&tracerfs_init_work, tracer_init_tracefs_work_func);
+		queue_work(eval_map_wq, &tracerfs_init_work);
+	} else {
+		tracer_init_tracefs_work_func(NULL);
+	}
 
 	return 0;
 }
-- 
cgit v1.2.3


From 6695da58f9445f386516ed53a3e870f534d2645d Mon Sep 17 00:00:00 2001
From: Steven Rostedt (Google)
Date: Wed, 27 Apr 2022 15:33:39 -0400
Subject: ring-buffer: Have absolute time stamps handle large numbers

There's an absolute timestamp event in the ring buffer, but this only
saves 59 bits of the timestamp, as the 5 MSB is used for meta data
(stating it is an absolute time stamp). This was never an issue as all the
clocks currently in use never used those 5 MSB. But now there's a new
clock (TAI) that does.

To handle this case, when reading an absolute timestamp, a previous full
timestamp is passed in, and the 5 MSB of that timestamp is OR'd to the
absolute timestamp (if any of the 5 MSB are set), and then to test for
overflow, if the new result is smaller than the passed in previous
timestamp, then 1 << 59 is added to it.

All the extra processing is done on the reader "slow" path, with the
exception of the "too big delta" check, and the reading of timestamps
for histograms.

Note, libtraceevent will need to be updated to handle this case as well.
But this is not a user space regression, as user space was never able to
handle any timestamps that used more than 59 bits.

Link: https://lore.kernel.org/all/20220426175338.3807ca4f@gandalf.local.home/
Link: https://lkml.kernel.org/r/20220427153339.16c33f75@gandalf.local.home

Cc: Tom Zanussi <zanussi@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Kurt Kanzenbach <kurt@linutronix.de>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/ring_buffer.c | 49 +++++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 44 insertions(+), 5 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 655d6db3e3c3..3a0c7ed0e93f 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -29,6 +29,14 @@
 
 #include <asm/local.h>
 
+/*
+ * The "absolute" timestamp in the buffer is only 59 bits.
+ * If a clock has the 5 MSBs set, it needs to be saved and
+ * reinserted.
+ */
+#define TS_MSB		(0xf8ULL << 56)
+#define ABS_TS_MASK	(~TS_MSB)
+
 static void update_pages_handler(struct work_struct *work);
 
 /*
@@ -783,6 +791,24 @@ static inline void verify_event(struct ring_buffer_per_cpu *cpu_buffer,
 }
 #endif
 
+/*
+ * The absolute time stamp drops the 5 MSBs and some clocks may
+ * require them. The rb_fix_abs_ts() will take a previous full
+ * time stamp, and add the 5 MSB of that time stamp on to the
+ * saved absolute time stamp. Then they are compared in case of
+ * the unlikely event that the latest time stamp incremented
+ * the 5 MSB.
+ */
+static inline u64 rb_fix_abs_ts(u64 abs, u64 save_ts)
+{
+	if (save_ts & TS_MSB) {
+		abs |= save_ts & TS_MSB;
+		/* Check for overflow */
+		if (unlikely(abs < save_ts))
+			abs += 1ULL << 59;
+	}
+	return abs;
+}
 
 static inline u64 rb_time_stamp(struct trace_buffer *buffer);
 
@@ -811,8 +837,10 @@ u64 ring_buffer_event_time_stamp(struct trace_buffer *buffer,
 	u64 ts;
 
 	/* If the event includes an absolute time, then just use that */
-	if (event->type_len == RINGBUF_TYPE_TIME_STAMP)
-		return rb_event_time_stamp(event);
+	if (event->type_len == RINGBUF_TYPE_TIME_STAMP) {
+		ts = rb_event_time_stamp(event);
+		return rb_fix_abs_ts(ts, cpu_buffer->tail_page->page->time_stamp);
+	}
 
 	nest = local_read(&cpu_buffer->committing);
 	verify_event(cpu_buffer, event);
@@ -2754,8 +2782,15 @@ static void rb_add_timestamp(struct ring_buffer_per_cpu *cpu_buffer,
 		(RB_ADD_STAMP_FORCE | RB_ADD_STAMP_ABSOLUTE);
 
 	if (unlikely(info->delta > (1ULL << 59))) {
+		/*
+		 * Some timers can use more than 59 bits, and when a timestamp
+		 * is added to the buffer, it will lose those bits.
+		 */
+		if (abs && (info->ts & TS_MSB)) {
+			info->delta &= ABS_TS_MASK;
+
 		/* did the clock go backwards */
-		if (info->before == info->after && info->before > info->ts) {
+		} else if (info->before == info->after && info->before > info->ts) {
 			/* not interrupted */
 			static int once;
 
@@ -3304,7 +3339,7 @@ static void dump_buffer_page(struct buffer_data_page *bpage,
 
 		case RINGBUF_TYPE_TIME_STAMP:
 			delta = rb_event_time_stamp(event);
-			ts = delta;
+			ts = rb_fix_abs_ts(delta, ts);
 			pr_warn("  [%lld] absolute:%lld TIME STAMP\n", ts, delta);
 			break;
 
@@ -3380,7 +3415,7 @@ static void check_buffer(struct ring_buffer_per_cpu *cpu_buffer,
 
 		case RINGBUF_TYPE_TIME_STAMP:
 			delta = rb_event_time_stamp(event);
-			ts = delta;
+			ts = rb_fix_abs_ts(delta, ts);
 			break;
 
 		case RINGBUF_TYPE_PADDING:
@@ -4367,6 +4402,7 @@ rb_update_read_stamp(struct ring_buffer_per_cpu *cpu_buffer,
 
 	case RINGBUF_TYPE_TIME_STAMP:
 		delta = rb_event_time_stamp(event);
+		delta = rb_fix_abs_ts(delta, cpu_buffer->read_stamp);
 		cpu_buffer->read_stamp = delta;
 		return;
 
@@ -4397,6 +4433,7 @@ rb_update_iter_read_stamp(struct ring_buffer_iter *iter,
 
 	case RINGBUF_TYPE_TIME_STAMP:
 		delta = rb_event_time_stamp(event);
+		delta = rb_fix_abs_ts(delta, iter->read_stamp);
 		iter->read_stamp = delta;
 		return;
 
@@ -4650,6 +4687,7 @@ rb_buffer_peek(struct ring_buffer_per_cpu *cpu_buffer, u64 *ts,
 	case RINGBUF_TYPE_TIME_STAMP:
 		if (ts) {
 			*ts = rb_event_time_stamp(event);
+			*ts = rb_fix_abs_ts(*ts, reader->page->time_stamp);
 			ring_buffer_normalize_time_stamp(cpu_buffer->buffer,
 							 cpu_buffer->cpu, ts);
 		}
@@ -4741,6 +4779,7 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 	case RINGBUF_TYPE_TIME_STAMP:
 		if (ts) {
 			*ts = rb_event_time_stamp(event);
+			*ts = rb_fix_abs_ts(*ts, iter->head_page->page->time_stamp);
 			ring_buffer_normalize_time_stamp(cpu_buffer->buffer,
 							 cpu_buffer->cpu, ts);
 		}
-- 
cgit v1.2.3


From f03f2abce4f3944b9576bc4ad28b75890e907d7c Mon Sep 17 00:00:00 2001
From: Steven Rostedt (Google)
Date: Wed, 27 Apr 2022 17:08:12 -0400
Subject: ring-buffer: Have 32 bit time stamps use all 64 bits

When the new logic was made to handle deltas of events from interrupts
that interrupted other events, it required 64 bit local atomics.
Unfortunately, 64 bit local atomics are expensive on 32 bit architectures.
Thus, commit 10464b4aa605e ("ring-buffer: Add rb_time_t 64 bit operations
for speeding up 32 bit") created a type of seq lock timer for 32 bits.
It used two 32 bit local atomics, but required 2 bits from them each for
synchronization, making it only 60 bits.

Add a new "msb" field to hold the extra 4 bits that are cut off.

Link: https://lore.kernel.org/all/20220426175338.3807ca4f@gandalf.local.home/
Link: https://lkml.kernel.org/r/20220427170812.53cc7139@gandalf.local.home

Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/ring_buffer.c | 28 ++++++++++++++++++----------
 1 file changed, 18 insertions(+), 10 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 3a0c7ed0e93f..d59b6a328b7f 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -476,6 +476,7 @@ struct rb_time_struct {
 	local_t		cnt;
 	local_t		top;
 	local_t		bottom;
+	local_t		msb;
 };
 #else
 #include <asm/local64.h>
@@ -577,7 +578,6 @@ struct ring_buffer_iter {
  * For the ring buffer, 64 bit required operations for the time is
  * the following:
  *
- *  - Only need 59 bits (uses 60 to make it even).
  *  - Reads may fail if it interrupted a modification of the time stamp.
  *      It will succeed if it did not interrupt another write even if
  *      the read itself is interrupted by a write.
@@ -602,6 +602,7 @@ struct ring_buffer_iter {
  */
 #define RB_TIME_SHIFT	30
 #define RB_TIME_VAL_MASK ((1 << RB_TIME_SHIFT) - 1)
+#define RB_TIME_MSB_SHIFT	 60
 
 static inline int rb_time_cnt(unsigned long val)
 {
@@ -621,7 +622,7 @@ static inline u64 rb_time_val(unsigned long top, unsigned long bottom)
 
 static inline bool __rb_time_read(rb_time_t *t, u64 *ret, unsigned long *cnt)
 {
-	unsigned long top, bottom;
+	unsigned long top, bottom, msb;
 	unsigned long c;
 
 	/*
@@ -633,6 +634,7 @@ static inline bool __rb_time_read(rb_time_t *t, u64 *ret, unsigned long *cnt)
 		c = local_read(&t->cnt);
 		top = local_read(&t->top);
 		bottom = local_read(&t->bottom);
+		msb = local_read(&t->msb);
 	} while (c != local_read(&t->cnt));
 
 	*cnt = rb_time_cnt(top);
@@ -641,7 +643,8 @@ static inline bool __rb_time_read(rb_time_t *t, u64 *ret, unsigned long *cnt)
 	if (*cnt != rb_time_cnt(bottom))
 		return false;
 
-	*ret = rb_time_val(top, bottom);
+	/* The shift to msb will lose its cnt bits */
+	*ret = rb_time_val(top, bottom) | ((u64)msb << RB_TIME_MSB_SHIFT);
 	return true;
 }
 
@@ -657,10 +660,12 @@ static inline unsigned long rb_time_val_cnt(unsigned long val, unsigned long cnt
 	return (val & RB_TIME_VAL_MASK) | ((cnt & 3) << RB_TIME_SHIFT);
 }
 
-static inline void rb_time_split(u64 val, unsigned long *top, unsigned long *bottom)
+static inline void rb_time_split(u64 val, unsigned long *top, unsigned long *bottom,
+				 unsigned long *msb)
 {
 	*top = (unsigned long)((val >> RB_TIME_SHIFT) & RB_TIME_VAL_MASK);
 	*bottom = (unsigned long)(val & RB_TIME_VAL_MASK);
+	*msb = (unsigned long)(val >> RB_TIME_MSB_SHIFT);
 }
 
 static inline void rb_time_val_set(local_t *t, unsigned long val, unsigned long cnt)
@@ -671,15 +676,16 @@ static inline void rb_time_val_set(local_t *t, unsigned long val, unsigned long
 
 static void rb_time_set(rb_time_t *t, u64 val)
 {
-	unsigned long cnt, top, bottom;
+	unsigned long cnt, top, bottom, msb;
 
-	rb_time_split(val, &top, &bottom);
+	rb_time_split(val, &top, &bottom, &msb);
 
 	/* Writes always succeed with a valid number even if it gets interrupted. */
 	do {
 		cnt = local_inc_return(&t->cnt);
 		rb_time_val_set(&t->top, top, cnt);
 		rb_time_val_set(&t->bottom, bottom, cnt);
+		rb_time_val_set(&t->msb, val >> RB_TIME_MSB_SHIFT, cnt);
 	} while (cnt != local_read(&t->cnt));
 }
 
@@ -694,8 +700,8 @@ rb_time_read_cmpxchg(local_t *l, unsigned long expect, unsigned long set)
 
 static int rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set)
 {
-	unsigned long cnt, top, bottom;
-	unsigned long cnt2, top2, bottom2;
+	unsigned long cnt, top, bottom, msb;
+	unsigned long cnt2, top2, bottom2, msb2;
 	u64 val;
 
 	/* The cmpxchg always fails if it interrupted an update */
@@ -711,16 +717,18 @@ static int rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set)
 
 	 cnt2 = cnt + 1;
 
-	 rb_time_split(val, &top, &bottom);
+	 rb_time_split(val, &top, &bottom, &msb);
 	 top = rb_time_val_cnt(top, cnt);
 	 bottom = rb_time_val_cnt(bottom, cnt);
 
-	 rb_time_split(set, &top2, &bottom2);
+	 rb_time_split(set, &top2, &bottom2, &msb2);
 	 top2 = rb_time_val_cnt(top2, cnt2);
 	 bottom2 = rb_time_val_cnt(bottom2, cnt2);
 
 	if (!rb_time_read_cmpxchg(&t->cnt, cnt, cnt2))
 		return false;
+	if (!rb_time_read_cmpxchg(&t->msb, msb, msb2))
+		return false;
 	if (!rb_time_read_cmpxchg(&t->top, top, top2))
 		return false;
 	if (!rb_time_read_cmpxchg(&t->bottom, bottom, bottom2))
-- 
cgit v1.2.3


From c575afe21ccc47c5561d11493ede81ab7d072267 Mon Sep 17 00:00:00 2001
From: Kurt Kanzenbach
Date: Thu, 14 Apr 2022 11:18:04 +0200
Subject: tracing: Introduce trace clock tai

A fast/NMI safe accessor for CLOCK_TAI has been introduced.
Use it for adding the additional trace clock "tai".

Link: https://lkml.kernel.org/r/20220414091805.89667-3-kurt@linutronix.de

Signed-off-by: Kurt Kanzenbach <kurt@linutronix.de>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 400d3e9fe9ff..087740f63d92 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1542,6 +1542,7 @@ static struct {
 	{ ktime_get_mono_fast_ns,	"mono",		1 },
 	{ ktime_get_raw_fast_ns,	"mono_raw",	1 },
 	{ ktime_get_boot_fast_ns,	"boot",		1 },
+	{ ktime_get_tai_fast_ns,	"tai",		1 },
 	ARCH_TRACE_CLOCKS
 };
 
-- 
cgit v1.2.3


From 1da27a25054f7660f7bb27ad4ccf036ee6ba51e9 Mon Sep 17 00:00:00 2001
From: Jakob Koschel
Date: Wed, 27 Apr 2022 19:07:31 +0200
Subject: tracing: Remove usage of list iterator after the loop body

In preparation to limit the scope of the list iterator variable to the
traversal loop, use a dedicated pointer to point to the found element
[1].

Before, the code implicitly used the head when no element was found
when using &pos->list. Since the new variable is only set if an
element was found, the head needs to be used explicitly if the
variable is NULL.

Link: https://lkml.kernel.org/r/20220427170734.819891-2-jakobkoschel@gmail.com

Cc: Ingo Molnar <mingo@redhat.com>
Link: https://lore.kernel.org/all/CAHk-=wgRr_D8CB-D9Kg-c=EHreAsk5SqXPwr9Y7k9sA6cWXJ6w@mail.gmail.com/ [1]
Signed-off-by: Jakob Koschel <jakobkoschel@gmail.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_output.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index d89e3f7e26eb..67f47ea27921 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -692,7 +692,7 @@ static LIST_HEAD(ftrace_event_list);
 
 static int trace_search_list(struct list_head **list)
 {
-	struct trace_event *e;
+	struct trace_event *e = NULL, *iter;
 	int next = __TRACE_LAST_TYPE;
 
 	if (list_empty(&ftrace_event_list)) {
@@ -704,9 +704,11 @@ static int trace_search_list(struct list_head **list)
 	 * We used up all possible max events,
 	 * lets see if somebody freed one.
 	 */
-	list_for_each_entry(e, &ftrace_event_list, list) {
-		if (e->type != next)
+	list_for_each_entry(iter, &ftrace_event_list, list) {
+		if (iter->type != next) {
+			e = iter;
 			break;
+		}
 		next++;
 	}
 
@@ -714,7 +716,10 @@ static int trace_search_list(struct list_head **list)
 	if (next > TRACE_EVENT_TYPE_MAX)
 		return 0;
 
-	*list = &e->list;
+	if (e)
+		*list = &e->list;
+	else
+		*list = &ftrace_event_list;
 	return next;
 }
 
-- 
cgit v1.2.3


From 99d8ae4ec8a90ecf6c2a6a141bd4db4a3bc5146c Mon Sep 17 00:00:00 2001
From: Jakob Koschel
Date: Wed, 27 Apr 2022 19:07:32 +0200
Subject: tracing: Remove usage of list iterator variable after the loop

In preparation to limit the scope of a list iterator to the list
traversal loop, use a dedicated pointer to point to the found element
[1].

Link: https://lore.kernel.org/all/CAHk-=wgRr_D8CB-D9Kg-c=EHreAsk5SqXPwr9Y7k9sA6cWXJ6w@mail.gmail.com/ [1]
Link: https://lkml.kernel.org/r/20220427170734.819891-3-jakobkoschel@gmail.com

Cc: Ingo Molnar <mingo@redhat.com>
Signed-off-by: Jakob Koschel <jakobkoschel@gmail.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_events.c | 15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index e11e167b7809..e4a442060707 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1723,9 +1723,9 @@ static LIST_HEAD(event_subsystems);
 
 static int subsystem_open(struct inode *inode, struct file *filp)
 {
+	struct trace_subsystem_dir *dir = NULL, *iter_dir;
+	struct trace_array *tr = NULL, *iter_tr;
 	struct event_subsystem *system = NULL;
-	struct trace_subsystem_dir *dir = NULL; /* Initialize for gcc */
-	struct trace_array *tr;
 	int ret;
 
 	if (tracing_is_disabled())
@@ -1734,10 +1734,12 @@ static int subsystem_open(struct inode *inode, struct file *filp)
 	/* Make sure the system still exists */
 	mutex_lock(&event_mutex);
 	mutex_lock(&trace_types_lock);
-	list_for_each_entry(tr, &ftrace_trace_arrays, list) {
-		list_for_each_entry(dir, &tr->systems, list) {
-			if (dir == inode->i_private) {
+	list_for_each_entry(iter_tr, &ftrace_trace_arrays, list) {
+		list_for_each_entry(iter_dir, &iter_tr->systems, list) {
+			if (iter_dir == inode->i_private) {
 				/* Don't open systems with no events */
+				tr = iter_tr;
+				dir = iter_dir;
 				if (dir->nr_events) {
 					__get_system_dir(dir);
 					system = dir->subsystem;
@@ -1753,9 +1755,6 @@ static int subsystem_open(struct inode *inode, struct file *filp)
 	if (!system)
 		return -ENODEV;
 
-	/* Some versions of gcc think dir can be uninitialized here */
-	WARN_ON(!dir);
-
 	/* Still need to increment the ref count of the system */
 	if (trace_array_get(tr) < 0) {
 		put_system(dir);
-- 
cgit v1.2.3


From 45e333ce2ad5cbb0ee05686336de09058c6af8ca Mon Sep 17 00:00:00 2001
From: Jakob Koschel
Date: Wed, 27 Apr 2022 19:07:33 +0200
Subject: tracing: Replace usage of found with dedicated list iterator variable

To move the list iterator variable into the list_for_each_entry_*()
macro in the future it should be avoided to use the list iterator
variable after the loop body.

To *never* use the list iterator variable after the loop it was
concluded to use a separate iterator variable instead of a
found boolean [1].

This removes the need to use a found variable and simply checking if
the variable was set, can determine if the break/goto was hit.

Link: https://lkml.kernel.org/r/20220427170734.819891-4-jakobkoschel@gmail.com

Cc: Ingo Molnar <mingo@redhat.com>
Link: https://lore.kernel.org/all/CAHk-=wgRr_D8CB-D9Kg-c=EHreAsk5SqXPwr9Y7k9sA6cWXJ6w@mail.gmail.com/ [1]
Signed-off-by: Jakob Koschel <jakobkoschel@gmail.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_events_hist.c    | 15 +++++++--------
 kernel/trace/trace_events_trigger.c | 24 +++++++++++-------------
 2 files changed, 18 insertions(+), 21 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index fe10179893c1..038dc591545d 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -6117,20 +6117,19 @@ static void hist_unregister_trigger(char *glob,
 				    struct event_trigger_data *data,
 				    struct trace_event_file *file)
 {
+	struct event_trigger_data *test = NULL, *iter, *named_data = NULL;
 	struct hist_trigger_data *hist_data = data->private_data;
-	struct event_trigger_data *test, *named_data = NULL;
-	bool unregistered = false;
 
 	lockdep_assert_held(&event_mutex);
 
 	if (hist_data->attrs->name)
 		named_data = find_named_trigger(hist_data->attrs->name);
 
-	list_for_each_entry(test, &file->triggers, list) {
-		if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
-			if (!hist_trigger_match(data, test, named_data, false))
+	list_for_each_entry(iter, &file->triggers, list) {
+		if (iter->cmd_ops->trigger_type == ETT_EVENT_HIST) {
+			if (!hist_trigger_match(data, iter, named_data, false))
 				continue;
-			unregistered = true;
+			test = iter;
 			list_del_rcu(&test->list);
 			trace_event_trigger_enable_disable(file, 0);
 			update_cond_flag(file);
@@ -6138,11 +6137,11 @@ static void hist_unregister_trigger(char *glob,
 		}
 	}
 
-	if (unregistered && test->ops->free)
+	if (test && test->ops->free)
 		test->ops->free(test);
 
 	if (hist_data->enable_timestamps) {
-		if (!hist_data->remove || unregistered)
+		if (!hist_data->remove || test)
 			tracing_set_filter_buffering(file->tr, false);
 	}
 }
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 62c44dab8f46..21592bed2e89 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -609,14 +609,13 @@ static void unregister_trigger(char *glob,
 			       struct event_trigger_data *test,
 			       struct trace_event_file *file)
 {
-	struct event_trigger_data *data;
-	bool unregistered = false;
+	struct event_trigger_data *data = NULL, *iter;
 
 	lockdep_assert_held(&event_mutex);
 
-	list_for_each_entry(data, &file->triggers, list) {
-		if (data->cmd_ops->trigger_type == test->cmd_ops->trigger_type) {
-			unregistered = true;
+	list_for_each_entry(iter, &file->triggers, list) {
+		if (iter->cmd_ops->trigger_type == test->cmd_ops->trigger_type) {
+			data = iter;
 			list_del_rcu(&data->list);
 			trace_event_trigger_enable_disable(file, 0);
 			update_cond_flag(file);
@@ -624,7 +623,7 @@ static void unregister_trigger(char *glob,
 		}
 	}
 
-	if (unregistered && data->ops->free)
+	if (data && data->ops->free)
 		data->ops->free(data);
 }
 
@@ -1870,19 +1869,18 @@ void event_enable_unregister_trigger(char *glob,
 				     struct trace_event_file *file)
 {
 	struct enable_trigger_data *test_enable_data = test->private_data;
+	struct event_trigger_data *data = NULL, *iter;
 	struct enable_trigger_data *enable_data;
-	struct event_trigger_data *data;
-	bool unregistered = false;
 
 	lockdep_assert_held(&event_mutex);
 
-	list_for_each_entry(data, &file->triggers, list) {
-		enable_data = data->private_data;
+	list_for_each_entry(iter, &file->triggers, list) {
+		enable_data = iter->private_data;
 		if (enable_data &&
-		    (data->cmd_ops->trigger_type ==
+		    (iter->cmd_ops->trigger_type ==
 		     test->cmd_ops->trigger_type) &&
 		    (enable_data->file == test_enable_data->file)) {
-			unregistered = true;
+			data = iter;
 			list_del_rcu(&data->list);
 			trace_event_trigger_enable_disable(file, 0);
 			update_cond_flag(file);
@@ -1890,7 +1888,7 @@ void event_enable_unregister_trigger(char *glob,
 		}
 	}
 
-	if (unregistered && data->ops->free)
+	if (data && data->ops->free)
 		data->ops->free(data);
 }
 
-- 
cgit v1.2.3


From ba27d8555867b0e02e15709f4ddb79aec5cf2efc Mon Sep 17 00:00:00 2001
From: Jakob Koschel
Date: Wed, 27 Apr 2022 19:07:34 +0200
Subject: tracing: Remove check of list iterator against head past the loop
 body

When list_for_each_entry() completes the iteration over the whole list
without breaking the loop, the iterator value will be a bogus pointer
computed based on the head element.

While it is safe to use the pointer to determine if it was computed
based on the head element, either with list_entry_is_head() or
&pos->member == head, using the iterator variable after the loop should
be avoided.

In preparation to limit the scope of a list iterator to the list
traversal loop, use a dedicated pointer to point to the found element [1].

Link: https://lkml.kernel.org/r/20220427170734.819891-5-jakobkoschel@gmail.com

Cc: Ingo Molnar <mingo@redhat.com>
Link: https://lore.kernel.org/all/CAHk-=wgRr_D8CB-D9Kg-c=EHreAsk5SqXPwr9Y7k9sA6cWXJ6w@mail.gmail.com/
Signed-off-by: Jakob Koschel <jakobkoschel@gmail.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/ftrace.c       | 20 ++++++++++++--------
 kernel/trace/trace_eprobe.c | 14 ++++++++------
 kernel/trace/trace_events.c | 12 ++++++------
 3 files changed, 26 insertions(+), 20 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 4f1d2f5e7263..5c465e70d146 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -4560,8 +4560,8 @@ register_ftrace_function_probe(char *glob, struct trace_array *tr,
 			       struct ftrace_probe_ops *probe_ops,
 			       void *data)
 {
+	struct ftrace_func_probe *probe = NULL, *iter;
 	struct ftrace_func_entry *entry;
-	struct ftrace_func_probe *probe;
 	struct ftrace_hash **orig_hash;
 	struct ftrace_hash *old_hash;
 	struct ftrace_hash *hash;
@@ -4580,11 +4580,13 @@ register_ftrace_function_probe(char *glob, struct trace_array *tr,
 
 	mutex_lock(&ftrace_lock);
 	/* Check if the probe_ops is already registered */
-	list_for_each_entry(probe, &tr->func_probes, list) {
-		if (probe->probe_ops == probe_ops)
+	list_for_each_entry(iter, &tr->func_probes, list) {
+		if (iter->probe_ops == probe_ops) {
+			probe = iter;
 			break;
+		}
 	}
-	if (&probe->list == &tr->func_probes) {
+	if (!probe) {
 		probe = kzalloc(sizeof(*probe), GFP_KERNEL);
 		if (!probe) {
 			mutex_unlock(&ftrace_lock);
@@ -4702,9 +4704,9 @@ int
 unregister_ftrace_function_probe_func(char *glob, struct trace_array *tr,
 				      struct ftrace_probe_ops *probe_ops)
 {
+	struct ftrace_func_probe *probe = NULL, *iter;
 	struct ftrace_ops_hash old_hash_ops;
 	struct ftrace_func_entry *entry;
-	struct ftrace_func_probe *probe;
 	struct ftrace_glob func_g;
 	struct ftrace_hash **orig_hash;
 	struct ftrace_hash *old_hash;
@@ -4732,11 +4734,13 @@ unregister_ftrace_function_probe_func(char *glob, struct trace_array *tr,
 
 	mutex_lock(&ftrace_lock);
 	/* Check if the probe_ops is already registered */
-	list_for_each_entry(probe, &tr->func_probes, list) {
-		if (probe->probe_ops == probe_ops)
+	list_for_each_entry(iter, &tr->func_probes, list) {
+		if (iter->probe_ops == probe_ops) {
+			probe = iter;
 			break;
+		}
 	}
-	if (&probe->list == &tr->func_probes)
+	if (!probe)
 		goto err_unlock_ftrace;
 
 	ret = -EINVAL;
diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c
index b045fa9f276c..7d4478525c66 100644
--- a/kernel/trace/trace_eprobe.c
+++ b/kernel/trace/trace_eprobe.c
@@ -648,7 +648,7 @@ static struct trace_event_functions eprobe_funcs = {
 static int disable_eprobe(struct trace_eprobe *ep,
 			  struct trace_array *tr)
 {
-	struct event_trigger_data *trigger;
+	struct event_trigger_data *trigger = NULL, *iter;
 	struct trace_event_file *file;
 	struct eprobe_data *edata;
 
@@ -656,14 +656,16 @@ static int disable_eprobe(struct trace_eprobe *ep,
 	if (!file)
 		return -ENOENT;
 
-	list_for_each_entry(trigger, &file->triggers, list) {
-		if (!(trigger->flags & EVENT_TRIGGER_FL_PROBE))
+	list_for_each_entry(iter, &file->triggers, list) {
+		if (!(iter->flags & EVENT_TRIGGER_FL_PROBE))
 			continue;
-		edata = trigger->private_data;
-		if (edata->ep == ep)
+		edata = iter->private_data;
+		if (edata->ep == ep) {
+			trigger = iter;
 			break;
+		}
 	}
-	if (list_entry_is_head(trigger, &file->triggers, list))
+	if (!trigger)
 		return -ENODEV;
 
 	list_del_rcu(&trigger->list);
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index e4a442060707..78f313b7b315 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -2279,8 +2279,8 @@ static struct dentry *
 event_subsystem_dir(struct trace_array *tr, const char *name,
 		    struct trace_event_file *file, struct dentry *parent)
 {
+	struct event_subsystem *system, *iter;
 	struct trace_subsystem_dir *dir;
-	struct event_subsystem *system;
 	struct dentry *entry;
 
 	/* First see if we did not already create this dir */
@@ -2294,13 +2294,13 @@ event_subsystem_dir(struct trace_array *tr, const char *name,
 	}
 
 	/* Now see if the system itself exists. */
-	list_for_each_entry(system, &event_subsystems, list) {
-		if (strcmp(system->name, name) == 0)
+	system = NULL;
+	list_for_each_entry(iter, &event_subsystems, list) {
+		if (strcmp(iter->name, name) == 0) {
+			system = iter;
 			break;
+		}
 	}
-	/* Reset system variable when not found */
-	if (&system->list == &event_subsystems)
-		system = NULL;
 
 	dir = kmalloc(sizeof(*dir), GFP_KERNEL);
 	if (!dir)
-- 
cgit v1.2.3


From 499f12168aebd6da8fa32c9b7d6203ca9b5eb88d Mon Sep 17 00:00:00 2001
From: Steven Rostedt (Google)
Date: Thu, 7 Apr 2022 14:56:32 -0400
Subject: tracing: Have event format check not flag %p* on
 __get_dynamic_array()

The print fmt check against trace events to make sure that the format does
not use pointers that may be freed from the time of the trace to the time
the event is read, gives a false positive on %pISpc when reading data that
was saved in __get_dynamic_array() when it is perfectly fine to do so, as
the data being read is on the ring buffer.

Link: https://lore.kernel.org/all/20220407144524.2a592ed6@canb.auug.org.au/

Cc: stable@vger.kernel.org
Fixes: 5013f454a352c ("tracing: Add check of trace event print fmts for dereferencing pointers")
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_events.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 78f313b7b315..d5913487821a 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -392,12 +392,6 @@ static void test_event_printk(struct trace_event_call *call)
 			if (!(dereference_flags & (1ULL << arg)))
 				goto next_arg;
 
-			/* Check for __get_sockaddr */;
-			if (str_has_prefix(fmt + i, "__get_sockaddr(")) {
-				dereference_flags &= ~(1ULL << arg);
-				goto next_arg;
-			}
-
 			/* Find the REC-> in the argument */
 			c = strchr(fmt + i, ',');
 			r = strstr(fmt + i, "REC->");
@@ -413,7 +407,14 @@ static void test_event_printk(struct trace_event_call *call)
 				a = strchr(fmt + i, '&');
 				if ((a && (a < r)) || test_field(r, call))
 					dereference_flags &= ~(1ULL << arg);
+			} else if ((r = strstr(fmt + i, "__get_dynamic_array(")) &&
+				   (!c || r < c)) {
+				dereference_flags &= ~(1ULL << arg);
+			} else if ((r = strstr(fmt + i, "__get_sockaddr(")) &&
+				   (!c || r < c)) {
+				dereference_flags &= ~(1ULL << arg);
 			}
+
 		next_arg:
 			i--;
 			arg++;
-- 
cgit v1.2.3


From e35c2d8e22745751cf304ec3fe39616643db2e0a Mon Sep 17 00:00:00 2001
From: Li Huafei
Date: Wed, 27 Apr 2022 11:41:19 +0800
Subject: tracing: Reset the function filter after completing trampoline/graph
 selftest

The direct trampoline and graph coexistence test sets global_ops to
trace only 'trace_selftest_dynamic_test_func', but does not reset it
after the test is completed, resulting in the function filter being set
already after the system starts. Although it can be reset through the
tracefs interface, it is more or less confusing to the user, and we
should reset it to trace all functions after the trampoline/graph test
completes.

Link: https://lkml.kernel.org/r/20220427034119.24668-1-lihuafei1@huawei.com
Link: https://lore.kernel.org/all/20220418073958.104029-1-lihuafei1@huawei.com/

Fixes: 130c08065848 ("tracing: Add trampoline/graph selftest")
Signed-off-by: Li Huafei <lihuafei1@huawei.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_selftest.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index abcadbe933bb..a2d301f58ced 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -895,6 +895,9 @@ trace_selftest_startup_function_graph(struct tracer *trace,
 		ret = -1;
 		goto out;
 	}
+
+	/* Enable tracing on all functions again */
+	ftrace_set_global_filter(NULL, 0, 1);
 #endif
 
 	/* Don't test dynamic tracing, the function tracer already did */
-- 
cgit v1.2.3


From e4931b824a6f36cae9cc5632709f015cfa748a25 Mon Sep 17 00:00:00 2001
From: Yuntao Wang
Date: Fri, 14 Jan 2022 21:10:52 +0800
Subject: tracing: Use trace_create_file() to simplify creation of tracefs
 entries

Creating tracefs entries with tracefs_create_file() followed by pr_warn()
is tedious and repetitive, we can use trace_create_file() to simplify
this process and make the code more readable.

Link: https://lkml.kernel.org/r/20220114131052.534382-1-ytcoode@gmail.com

Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Yuntao Wang <ytcoode@gmail.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/ftrace.c                 |  9 +++------
 kernel/trace/trace_dynevent.c         |  9 ++-------
 kernel/trace/trace_events.c           | 29 ++++++++++-------------------
 kernel/trace/trace_kprobe.c           | 15 ++++-----------
 kernel/trace/trace_recursion_record.c |  7 ++-----
 5 files changed, 21 insertions(+), 48 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 5c465e70d146..6c5b12669e06 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -952,7 +952,6 @@ static struct tracer_stat function_stats __initdata = {
 static __init void ftrace_profile_tracefs(struct dentry *d_tracer)
 {
 	struct ftrace_profile_stat *stat;
-	struct dentry *entry;
 	char *name;
 	int ret;
 	int cpu;
@@ -983,11 +982,9 @@ static __init void ftrace_profile_tracefs(struct dentry *d_tracer)
 		}
 	}
 
-	entry = tracefs_create_file("function_profile_enabled",
-				    TRACE_MODE_WRITE, d_tracer, NULL,
-				    &ftrace_profile_fops);
-	if (!entry)
-		pr_warn("Could not create tracefs 'function_profile_enabled' entry\n");
+	trace_create_file("function_profile_enabled",
+			  TRACE_MODE_WRITE, d_tracer, NULL,
+			  &ftrace_profile_fops);
 }
 
 #else /* CONFIG_FUNCTION_PROFILER */
diff --git a/kernel/trace/trace_dynevent.c b/kernel/trace/trace_dynevent.c
index e34e8182ee4b..076b447a1b88 100644
--- a/kernel/trace/trace_dynevent.c
+++ b/kernel/trace/trace_dynevent.c
@@ -255,19 +255,14 @@ static const struct file_operations dynamic_events_ops = {
 /* Make a tracefs interface for controlling dynamic events */
 static __init int init_dynamic_event(void)
 {
-	struct dentry *entry;
 	int ret;
 
 	ret = tracing_init_dentry();
 	if (ret)
 		return 0;
 
-	entry = tracefs_create_file("dynamic_events", TRACE_MODE_WRITE, NULL,
-				    NULL, &dynamic_events_ops);
-
-	/* Event list interface */
-	if (!entry)
-		pr_warn("Could not create tracefs 'dynamic_events' entry\n");
+	trace_create_file("dynamic_events", TRACE_MODE_WRITE, NULL,
+			  NULL, &dynamic_events_ops);
 
 	return 0;
 }
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index d5913487821a..9a88de9d7815 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -3546,12 +3546,10 @@ create_event_toplevel_files(struct dentry *parent, struct trace_array *tr)
 	struct dentry *d_events;
 	struct dentry *entry;
 
-	entry = tracefs_create_file("set_event", TRACE_MODE_WRITE, parent,
-				    tr, &ftrace_set_event_fops);
-	if (!entry) {
-		pr_warn("Could not create tracefs 'set_event' entry\n");
+	entry = trace_create_file("set_event", TRACE_MODE_WRITE, parent,
+				  tr, &ftrace_set_event_fops);
+	if (!entry)
 		return -ENOMEM;
-	}
 
 	d_events = tracefs_create_dir("events", parent);
 	if (!d_events) {
@@ -3566,16 +3564,12 @@ create_event_toplevel_files(struct dentry *parent, struct trace_array *tr)
 
 	/* There are not as crucial, just warn if they are not created */
 
-	entry = tracefs_create_file("set_event_pid", TRACE_MODE_WRITE, parent,
-				    tr, &ftrace_set_event_pid_fops);
-	if (!entry)
-		pr_warn("Could not create tracefs 'set_event_pid' entry\n");
+	trace_create_file("set_event_pid", TRACE_MODE_WRITE, parent,
+			  tr, &ftrace_set_event_pid_fops);
 
-	entry = tracefs_create_file("set_event_notrace_pid",
-				    TRACE_MODE_WRITE, parent, tr,
-				    &ftrace_set_event_notrace_pid_fops);
-	if (!entry)
-		pr_warn("Could not create tracefs 'set_event_notrace_pid' entry\n");
+	trace_create_file("set_event_notrace_pid",
+			  TRACE_MODE_WRITE, parent, tr,
+			  &ftrace_set_event_notrace_pid_fops);
 
 	/* ring buffer internal formats */
 	trace_create_file("header_page", TRACE_MODE_READ, d_events,
@@ -3790,17 +3784,14 @@ static __init int event_trace_init_fields(void)
 __init int event_trace_init(void)
 {
 	struct trace_array *tr;
-	struct dentry *entry;
 	int ret;
 
 	tr = top_trace_array();
 	if (!tr)
 		return -ENODEV;
 
-	entry = tracefs_create_file("available_events", TRACE_MODE_READ,
-				    NULL, tr, &ftrace_avail_fops);
-	if (!entry)
-		pr_warn("Could not create tracefs 'available_events' entry\n");
+	trace_create_file("available_events", TRACE_MODE_READ,
+			  NULL, tr, &ftrace_avail_fops);
 
 	ret = early_event_add_tracer(NULL, tr);
 	if (ret)
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 47cebef78532..93507330462c 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1907,25 +1907,18 @@ core_initcall(init_kprobe_trace_early);
 static __init int init_kprobe_trace(void)
 {
 	int ret;
-	struct dentry *entry;
 
 	ret = tracing_init_dentry();
 	if (ret)
 		return 0;
 
-	entry = tracefs_create_file("kprobe_events", TRACE_MODE_WRITE,
-				    NULL, NULL, &kprobe_events_ops);
-
 	/* Event list interface */
-	if (!entry)
-		pr_warn("Could not create tracefs 'kprobe_events' entry\n");
+	trace_create_file("kprobe_events", TRACE_MODE_WRITE,
+			  NULL, NULL, &kprobe_events_ops);
 
 	/* Profile interface */
-	entry = tracefs_create_file("kprobe_profile", TRACE_MODE_READ,
-				    NULL, NULL, &kprobe_profile_ops);
-
-	if (!entry)
-		pr_warn("Could not create tracefs 'kprobe_profile' entry\n");
+	trace_create_file("kprobe_profile", TRACE_MODE_READ,
+			  NULL, NULL, &kprobe_profile_ops);
 
 	setup_boot_kprobe_events();
 
diff --git a/kernel/trace/trace_recursion_record.c b/kernel/trace/trace_recursion_record.c
index 4d4b78c8ca25..a520b11afb0d 100644
--- a/kernel/trace/trace_recursion_record.c
+++ b/kernel/trace/trace_recursion_record.c
@@ -224,12 +224,9 @@ static const struct file_operations recursed_functions_fops = {
 
 __init static int create_recursed_functions(void)
 {
-	struct dentry *dentry;
 
-	dentry = trace_create_file("recursed_functions", TRACE_MODE_WRITE,
-				   NULL, NULL, &recursed_functions_fops);
-	if (!dentry)
-		pr_warn("WARNING: Failed to create recursed_functions\n");
+	trace_create_file("recursed_functions", TRACE_MODE_WRITE,
+			  NULL, NULL, &recursed_functions_fops);
 	return 0;
 }
 
-- 
cgit v1.2.3


From 2889c658b2fbc7ad4c5d541734fdc1d97b130753 Mon Sep 17 00:00:00 2001
From: Yuntao Wang
Date: Thu, 20 Jan 2022 06:59:49 +0000
Subject: ftrace: Deal with error return code of the ftrace_process_locs()
 function

The ftrace_process_locs() function may return -ENOMEM error code, which
should be handled by the callers.

Link: https://lkml.kernel.org/r/20220120065949.1813231-1-ytcoode@gmail.com

Signed-off-by: Yuntao Wang <ytcoode@gmail.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/ftrace.c | 17 +++++++++++++----
 1 file changed, 13 insertions(+), 4 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 6c5b12669e06..737e895e2aad 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -6864,11 +6864,16 @@ void ftrace_module_enable(struct module *mod)
 
 void ftrace_module_init(struct module *mod)
 {
+	int ret;
+
 	if (ftrace_disabled || !mod->num_ftrace_callsites)
 		return;
 
-	ftrace_process_locs(mod, mod->ftrace_callsites,
-			    mod->ftrace_callsites + mod->num_ftrace_callsites);
+	ret = ftrace_process_locs(mod, mod->ftrace_callsites,
+				  mod->ftrace_callsites + mod->num_ftrace_callsites);
+	if (ret)
+		pr_warn("ftrace: failed to allocate entries for module '%s' functions\n",
+			mod->name);
 }
 
 static void save_ftrace_mod_rec(struct ftrace_mod_map *mod_map,
@@ -7201,15 +7206,19 @@ void __init ftrace_init(void)
 	pr_info("ftrace: allocating %ld entries in %ld pages\n",
 		count, count / ENTRIES_PER_PAGE + 1);
 
-	last_ftrace_enabled = ftrace_enabled = 1;
-
 	ret = ftrace_process_locs(NULL,
 				  __start_mcount_loc,
 				  __stop_mcount_loc);
+	if (ret) {
+		pr_warn("ftrace: failed to allocate entries for functions\n");
+		goto failed;
+	}
 
 	pr_info("ftrace: allocated %ld pages with %ld groups\n",
 		ftrace_number_of_pages, ftrace_number_of_groups);
 
+	last_ftrace_enabled = ftrace_enabled = 1;
+
 	set_ftrace_early_filters();
 
 	return;
-- 
cgit v1.2.3


From cb24693d94ceaf658944ad2e922203c0503775d2 Mon Sep 17 00:00:00 2001
From: Yuntao Wang
Date: Fri, 21 Jan 2022 09:56:23 +0000
Subject: tracing: Use strim() to remove whitespace instead of doing it
 manually

The tracing_set_trace_write() function just removes the trailing whitespace
from the user supplied tracer name, but the leading whitespace should also
be removed.

In addition, if the user supplied tracer name contains only a few
whitespace characters, the first one will not be removed using the current
method, which results it a single whitespace character left in the buf.

To fix all of these issues, we use strim() to correctly remove both the
leading and trailing whitespace.

Link: https://lkml.kernel.org/r/20220121095623.1826679-1-ytcoode@gmail.com

Signed-off-by: Yuntao Wang <ytcoode@gmail.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 087740f63d92..498ae22d4ffa 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -6461,7 +6461,7 @@ tracing_set_trace_write(struct file *filp, const char __user *ubuf,
 {
 	struct trace_array *tr = filp->private_data;
 	char buf[MAX_TRACER_SIZE+1];
-	int i;
+	char *name;
 	size_t ret;
 	int err;
 
@@ -6475,11 +6475,9 @@ tracing_set_trace_write(struct file *filp, const char __user *ubuf,
 
 	buf[cnt] = 0;
 
-	/* strip ending whitespace. */
-	for (i = cnt - 1; i > 0 && isspace(buf[i]); i--)
-		buf[i] = 0;
+	name = strim(buf);
 
-	err = tracing_set_tracer(tr, buf);
+	err = tracing_set_tracer(tr, name);
 	if (err)
 		return err;
 
-- 
cgit v1.2.3


From 99696a2592bca641eb88cc9a80c90e591afebd0f Mon Sep 17 00:00:00 2001
From: Keita Suzuki
Date: Mon, 25 Apr 2022 06:37:38 +0000
Subject: tracing: Fix potential double free in create_var_ref()

In create_var_ref(), init_var_ref() is called to initialize the fields
of variable ref_field, which is allocated in the previous function call
to create_hist_field(). Function init_var_ref() allocates the
corresponding fields such as ref_field->system, but frees these fields
when the function encounters an error. The caller later calls
destroy_hist_field() to conduct error handling, which frees the fields
and the variable itself. This results in double free of the fields which
are already freed in the previous function.

Fix this by storing NULL to the corresponding fields when they are freed
in init_var_ref().

Link: https://lkml.kernel.org/r/20220425063739.3859998-1-keitasuzuki.park@sslab.ics.keio.ac.jp

Fixes: 067fe038e70f ("tracing: Add variable reference handling to hist triggers")
CC: stable@vger.kernel.org
Reviewed-by: Masami Hiramatsu <mhiramat@kernel.org>
Reviewed-by: Tom Zanussi <zanussi@kernel.org>
Signed-off-by: Keita Suzuki <keitasuzuki.park@sslab.ics.keio.ac.jp>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_events_hist.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 038dc591545d..c6a65738feb3 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -2093,8 +2093,11 @@ static int init_var_ref(struct hist_field *ref_field,
 	return err;
  free:
 	kfree(ref_field->system);
+	ref_field->system = NULL;
 	kfree(ref_field->event_name);
+	ref_field->event_name = NULL;
 	kfree(ref_field->name);
+	ref_field->name = NULL;
 
 	goto out;
 }
-- 
cgit v1.2.3


From b27f266f74fbda4ee36c2b2b04d15992860cf23b Mon Sep 17 00:00:00 2001
From: Wonhyuk Yang
Date: Tue, 3 May 2022 14:05:46 +0900
Subject: tracing: Fix return value of trace_pid_write()

Setting set_event_pid with trailing whitespace lead to endless write
system calls like below.

    $ strace echo "123 " > /sys/kernel/debug/tracing/set_event_pid
    execve("/usr/bin/echo", ["echo", "123 "], ...) = 0
    ...
    write(1, "123 \n", 5)                   = 4
    write(1, "\n", 1)                       = 0
    write(1, "\n", 1)                       = 0
    write(1, "\n", 1)                       = 0
    write(1, "\n", 1)                       = 0
    write(1, "\n", 1)                       = 0
    ....

This is because, the result of trace_get_user's are not returned when it
read at least one pid. To fix it, update read variable even if
parser->idx == 0.

The result of applied patch is below.

    $ strace echo "123 " > /sys/kernel/debug/tracing/set_event_pid
    execve("/usr/bin/echo", ["echo", "123 "], ...) = 0
    ...
    write(1, "123 \n", 5)                   = 5
    close(1)                                = 0

Link: https://lkml.kernel.org/r/20220503050546.288911-1-vvghjk1234@gmail.com

Cc: Ingo Molnar <mingo@redhat.com>
Cc: Baik Song An <bsahn@etri.re.kr>
Cc: Hong Yeon Kim <kimhy@etri.re.kr>
Cc: Taeung Song <taeung@reallinux.co.kr>
Cc: linuxgeek@linuxgeek.io
Cc: stable@vger.kernel.org
Fixes: 4909010788640 ("tracing: Add set_event_pid directory for future use")
Signed-off-by: Wonhyuk Yang <vvghjk1234@gmail.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 498ae22d4ffa..4825883b2ffd 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -721,13 +721,16 @@ int trace_pid_write(struct trace_pid_list *filtered_pids,
 		pos = 0;
 
 		ret = trace_get_user(&parser, ubuf, cnt, &pos);
-		if (ret < 0 || !trace_parser_loaded(&parser))
+		if (ret < 0)
 			break;
 
 		read += ret;
 		ubuf += ret;
 		cnt -= ret;
 
+		if (!trace_parser_loaded(&parser))
+			break;
+
 		ret = -EINVAL;
 		if (kstrtoul(parser.buffer, 0, &val))
 			break;
@@ -753,7 +756,6 @@ int trace_pid_write(struct trace_pid_list *filtered_pids,
 	if (!nr_pids) {
 		/* Cleared the list of pids */
 		trace_pid_list_free(pid_list);
-		read = ret;
 		pid_list = NULL;
 	}
 
-- 
cgit v1.2.3


From aa748949b4e665f473bc5abdc5f66029cb5f5522 Mon Sep 17 00:00:00 2001
From: Daniel Bristot de Oliveira
Date: Tue, 10 May 2022 11:45:23 +0200
Subject: tracing/timerlat: Notify IRQ new max latency only if stop tracing is
 set

Currently, the notification of a new max latency is sent from
timerlat's IRQ handler anytime a new max latency is found.

While this behavior is not wrong, the send IPI overhead itself
will increase the thread latency and that is not the desired
effect (tracing overhead).

Moreover, the thread will notify a new max latency again because
the thread latency as it is always higher than the IRQ latency
that woke it up.

The only case in which it is helpful to notify a new max latency
from IRQ is when stop tracing (for the IRQ) is set, as in this
case, the thread will not be dispatched.

Notify a new max latency from the IRQ handler only if stop tracing is
set for the IRQ handler.

Link: https://lkml.kernel.org/r/2c2d9a56c0886c8402ba320de32856cbbb10c2bb.1652175637.git.bristot@kernel.org

Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Ingo Molnar <mingo@redhat.com>
Reported-by: Clark Williams <williams@redhat.com>
Fixes: a955d7eac177 ("trace: Add timerlat tracer")
Signed-off-by: Daniel Bristot de Oliveira <bristot@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_osnoise.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index e9ae1f33a7f0..6494ca27ea6f 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -1578,11 +1578,12 @@ static enum hrtimer_restart timerlat_irq(struct hrtimer *timer)
 
 	trace_timerlat_sample(&s);
 
-	notify_new_max_latency(diff);
-
-	if (osnoise_data.stop_tracing)
-		if (time_to_us(diff) >= osnoise_data.stop_tracing)
+	if (osnoise_data.stop_tracing) {
+		if (time_to_us(diff) >= osnoise_data.stop_tracing) {
 			osnoise_stop_tracing();
+			notify_new_max_latency(diff);
+		}
+	}
 
 	wake_up_process(tlat->kthread);
 
-- 
cgit v1.2.3


From 4dd2aea24ed7613735664feadc9879d37f718c23 Mon Sep 17 00:00:00 2001
From: Daniel Bristot de Oliveira
Date: Tue, 10 May 2022 11:45:24 +0200
Subject: tracing/timerlat: Print stacktrace in the IRQ handler if needed

If print_stack and stop_tracing_us are set, and stop_tracing_us is hit
with latency higher than or equal to print_stack, print the
stack at the IRQ handler as it is useful to define the root cause for
the IRQ latency.

Link: https://lkml.kernel.org/r/fd04530ce98ae9270e41bb124ee5bf67b05ecfed.1652175637.git.bristot@kernel.org

Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Clark Williams <williams@redhat.com>
Cc: Ingo Molnar <mingo@redhat.com>
Signed-off-by: Daniel Bristot de Oliveira <bristot@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 Documentation/trace/timerlat-tracer.rst |  5 +++--
 kernel/trace/trace_osnoise.c            | 13 +++++++++++++
 2 files changed, 16 insertions(+), 2 deletions(-)

(limited to 'kernel/trace')

diff --git a/Documentation/trace/timerlat-tracer.rst b/Documentation/trace/timerlat-tracer.rst
index 64d1fe6e9b93..d643c95c01eb 100644
--- a/Documentation/trace/timerlat-tracer.rst
+++ b/Documentation/trace/timerlat-tracer.rst
@@ -74,8 +74,9 @@ directory. The timerlat configs are:
  - stop_tracing_total_us: stop the system tracing if a
    timer latency at the *thread* context is higher than the configured
    value happens. Writing 0 disables this option.
- - print_stack: save the stack of the IRQ occurrence, and print
-   it after the *thread context* event".
+ - print_stack: save the stack of the IRQ occurrence. The stack is printed
+   after the *thread context* event, or at the IRQ handler if *stop_tracing_us*
+   is hit.
 
 timerlat and osnoise
 ----------------------------
diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index 6494ca27ea6f..9b204ee3c6f5 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -1580,6 +1580,19 @@ static enum hrtimer_restart timerlat_irq(struct hrtimer *timer)
 
 	if (osnoise_data.stop_tracing) {
 		if (time_to_us(diff) >= osnoise_data.stop_tracing) {
+
+			/*
+			 * At this point, if stop_tracing is set and <= print_stack,
+			 * print_stack is set and would be printed in the thread handler.
+			 *
+			 * Thus, print the stack trace as it is helpful to define the
+			 * root cause of an IRQ latency.
+			 */
+			if (osnoise_data.stop_tracing <= osnoise_data.print_stack) {
+				timerlat_save_stack(0);
+				timerlat_dump_stack(time_to_us(diff));
+			}
+
 			osnoise_stop_tracing();
 			notify_new_max_latency(diff);
 		}
-- 
cgit v1.2.3


From 9c556e5a4dd5cfc0939a0575577d0517118f98af Mon Sep 17 00:00:00 2001
From: Daniel Bristot de Oliveira
Date: Tue, 10 May 2022 11:45:25 +0200
Subject: tracing/timerlat: Do not wakeup the thread if the trace stops at the
 IRQ

There is no need to wakeup the timerlat/ thread if stop tracing is hit
at the timerlat's IRQ handler.

Return before waking up timerlat's thread.

Link: https://lkml.kernel.org/r/b392356c91b56aedd2b289513cc56a84cf87e60d.1652175637.git.bristot@kernel.org

Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Clark Williams <williams@redhat.com>
Cc: Ingo Molnar <mingo@redhat.com>
Signed-off-by: Daniel Bristot de Oliveira <bristot@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_osnoise.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index 9b204ee3c6f5..035ec8b84e12 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -1595,6 +1595,8 @@ static enum hrtimer_restart timerlat_irq(struct hrtimer *timer)
 
 			osnoise_stop_tracing();
 			notify_new_max_latency(diff);
+
+			return HRTIMER_NORESTART;
 		}
 	}
 
-- 
cgit v1.2.3


From 2d601b98643dd2846e2958d931826e7b7af44969 Mon Sep 17 00:00:00 2001
From: liqiong
Date: Thu, 12 May 2022 22:32:30 +0800
Subject: tracing: Change "char *" string form to "char []"

The "char []" string form declares a single variable. It is better
than "char *" which creates two variables in the final assembly.

Link: https://lkml.kernel.org/r/20220512143230.28796-1-liqiong@nfschina.com

Signed-off-by: liqiong <liqiong@nfschina.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace.c             | 2 +-
 kernel/trace/trace_events_hist.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 4825883b2ffd..e38a7ca4cdd0 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4252,7 +4252,7 @@ static void print_func_help_header_irq(struct array_buffer *buf, struct seq_file
 				       unsigned int flags)
 {
 	bool tgid = flags & TRACE_ITER_RECORD_TGID;
-	const char *space = "            ";
+	static const char space[] = "            ";
 	int prec = tgid ? 12 : 2;
 
 	print_event_info(buf, m);
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index c6a65738feb3..48e82e141d54 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -4165,7 +4165,7 @@ static int create_val_field(struct hist_trigger_data *hist_data,
 	return __create_val_field(hist_data, val_idx, file, NULL, field_str, 0);
 }
 
-static const char *no_comm = "(no comm)";
+static const char no_comm[] = "(no comm)";
 
 static u64 hist_field_execname(struct hist_field *hist_field,
 			       struct tracing_map_elt *elt,
-- 
cgit v1.2.3


From 2decd16f47e3df3234b5486fe89a9aa5a1102af1 Mon Sep 17 00:00:00 2001
From: liqiong
Date: Fri, 13 May 2022 15:52:21 +0800
Subject: tracing: Cleanup code by removing init "char *name"

The pointer is assigned to "type->name" anyway. no need to
initialize with "preemption".

Link: https://lkml.kernel.org/r/20220513075221.26275-1-liqiong@nfschina.com

Signed-off-by: liqiong <liqiong@nfschina.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index e38a7ca4cdd0..f400800bc910 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4276,9 +4276,7 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter)
 	struct tracer *type = iter->trace;
 	unsigned long entries;
 	unsigned long total;
-	const char *name = "preemption";
-
-	name = type->name;
+	const char *name = type->name;
 
 	get_total_entries(buf, &total, &entries);
 
-- 
cgit v1.2.3


From 3a2bfec0b02f2226ff3376a5d2ff604d799bd7ea Mon Sep 17 00:00:00 2001
From: Li kunyu
Date: Wed, 18 May 2022 10:36:40 +0800
Subject: ftrace: Remove return value of ftrace_arch_modify_*()

All instances of the function ftrace_arch_modify_prepare() and
  ftrace_arch_modify_post_process() return zero. There's no point in
  checking their return value. Just have them be void functions.

Link: https://lkml.kernel.org/r/20220518023639.4065-1-kunyu@nfschina.com

Signed-off-by: Li kunyu <kunyu@nfschina.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 arch/arm/kernel/ftrace.c   |  6 ++----
 arch/riscv/kernel/ftrace.c |  6 ++----
 arch/s390/kernel/ftrace.c  |  3 +--
 arch/x86/kernel/ftrace.c   |  6 ++----
 include/linux/ftrace.h     |  4 ++--
 kernel/trace/ftrace.c      | 16 ++++------------
 6 files changed, 13 insertions(+), 28 deletions(-)

(limited to 'kernel/trace')

diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c
index 83cc068586bc..a0b6d1e3812f 100644
--- a/arch/arm/kernel/ftrace.c
+++ b/arch/arm/kernel/ftrace.c
@@ -79,16 +79,14 @@ static unsigned long __ref adjust_address(struct dyn_ftrace *rec,
 	return (unsigned long)&ftrace_regs_caller_from_init;
 }
 
-int ftrace_arch_code_modify_prepare(void)
+void ftrace_arch_code_modify_prepare(void)
 {
-	return 0;
 }
 
-int ftrace_arch_code_modify_post_process(void)
+void ftrace_arch_code_modify_post_process(void)
 {
 	/* Make sure any TLB misses during machine stop are cleared. */
 	flush_tlb_all();
-	return 0;
 }
 
 static unsigned long ftrace_call_replace(unsigned long pc, unsigned long addr,
diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c
index 4716f4cdc038..2086f6585773 100644
--- a/arch/riscv/kernel/ftrace.c
+++ b/arch/riscv/kernel/ftrace.c
@@ -12,16 +12,14 @@
 #include <asm/patch.h>
 
 #ifdef CONFIG_DYNAMIC_FTRACE
-int ftrace_arch_code_modify_prepare(void) __acquires(&text_mutex)
+void ftrace_arch_code_modify_prepare(void) __acquires(&text_mutex)
 {
 	mutex_lock(&text_mutex);
-	return 0;
 }
 
-int ftrace_arch_code_modify_post_process(void) __releases(&text_mutex)
+void ftrace_arch_code_modify_post_process(void) __releases(&text_mutex)
 {
 	mutex_unlock(&text_mutex);
-	return 0;
 }
 
 static int ftrace_check_current_call(unsigned long hook_pos,
diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index 1852d46babb1..416b5a94353d 100644
--- a/arch/s390/kernel/ftrace.c
+++ b/arch/s390/kernel/ftrace.c
@@ -225,14 +225,13 @@ void arch_ftrace_update_code(int command)
 	ftrace_modify_all_code(command);
 }
 
-int ftrace_arch_code_modify_post_process(void)
+void ftrace_arch_code_modify_post_process(void)
 {
 	/*
 	 * Flush any pre-fetched instructions on all
 	 * CPUs to make the new code visible.
 	 */
 	text_poke_sync_lock();
-	return 0;
 }
 
 #ifdef CONFIG_MODULES
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 1e31c7d21597..73d2719ed12c 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -37,7 +37,7 @@
 
 static int ftrace_poke_late = 0;
 
-int ftrace_arch_code_modify_prepare(void)
+void ftrace_arch_code_modify_prepare(void)
     __acquires(&text_mutex)
 {
 	/*
@@ -47,10 +47,9 @@ int ftrace_arch_code_modify_prepare(void)
 	 */
 	mutex_lock(&text_mutex);
 	ftrace_poke_late = 1;
-	return 0;
 }
 
-int ftrace_arch_code_modify_post_process(void)
+void ftrace_arch_code_modify_post_process(void)
     __releases(&text_mutex)
 {
 	/*
@@ -61,7 +60,6 @@ int ftrace_arch_code_modify_post_process(void)
 	text_poke_finish();
 	ftrace_poke_late = 0;
 	mutex_unlock(&text_mutex);
-	return 0;
 }
 
 static const char *ftrace_nop_replace(void)
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 4816b7e11047..a5f74f6e7e4e 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -449,8 +449,8 @@ static inline void stack_tracer_enable(void) { }
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 
-int ftrace_arch_code_modify_prepare(void);
-int ftrace_arch_code_modify_post_process(void);
+void ftrace_arch_code_modify_prepare(void);
+void ftrace_arch_code_modify_post_process(void);
 
 enum ftrace_bug_type {
 	FTRACE_BUG_UNKNOWN,
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 737e895e2aad..852c731cbd9a 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -2704,18 +2704,16 @@ ftrace_nop_initialize(struct module *mod, struct dyn_ftrace *rec)
  * archs can override this function if they must do something
  * before the modifying code is performed.
  */
-int __weak ftrace_arch_code_modify_prepare(void)
+void __weak ftrace_arch_code_modify_prepare(void)
 {
-	return 0;
 }
 
 /*
  * archs can override this function if they must do something
  * after the modifying code is performed.
  */
-int __weak ftrace_arch_code_modify_post_process(void)
+void __weak ftrace_arch_code_modify_post_process(void)
 {
-	return 0;
 }
 
 void ftrace_modify_all_code(int command)
@@ -2801,12 +2799,7 @@ void __weak arch_ftrace_update_code(int command)
 
 static void ftrace_run_update_code(int command)
 {
-	int ret;
-
-	ret = ftrace_arch_code_modify_prepare();
-	FTRACE_WARN_ON(ret);
-	if (ret)
-		return;
+	ftrace_arch_code_modify_prepare();
 
 	/*
 	 * By default we use stop_machine() to modify the code.
@@ -2816,8 +2809,7 @@ static void ftrace_run_update_code(int command)
 	 */
 	arch_ftrace_update_code(command);
 
-	ret = ftrace_arch_code_modify_post_process();
-	FTRACE_WARN_ON(ret);
+	ftrace_arch_code_modify_post_process();
 }
 
 static void ftrace_run_modify_code(struct ftrace_ops *ops, int command,
-- 
cgit v1.2.3


From 50c697819d59c5013a66728940015348919a0c0c Mon Sep 17 00:00:00 2001
From: Julia Lawall
Date: Sat, 21 May 2022 13:11:31 +0200
Subject: ftrace: Fix typo in comment

Spelling mistake (triple letters) in comment.
Detected with the help of Coccinelle.

Link: https://lkml.kernel.org/r/20220521111145.81697-81-Julia.Lawall@inria.fr

Signed-off-by: Julia Lawall <Julia.Lawall@inria.fr>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/ftrace.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 852c731cbd9a..fb8f08b4bd41 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -119,7 +119,7 @@ struct ftrace_ops __rcu *ftrace_ops_list __read_mostly = &ftrace_list_end;
 ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub;
 struct ftrace_ops global_ops;
 
-/* Defined by vmlinux.lds.h see the commment above arch_ftrace_ops_list_func for details */
+/* Defined by vmlinux.lds.h see the comment above arch_ftrace_ops_list_func for details */
 void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
 			  struct ftrace_ops *op, struct ftrace_regs *fregs);
 
-- 
cgit v1.2.3


From 154827f8e53d8c492b3fb0cb757fbcadb5d516b5 Mon Sep 17 00:00:00 2001
From: Gautam Menghani
Date: Sat, 21 May 2022 23:18:26 -0700
Subject: tracing: Initialize integer variable to prevent garbage return value

Initialize the integer variable to 0 to fix the clang scan warning:
Undefined or garbage value returned to caller
[core.uninitialized.UndefReturn]
        return ret;

Link: https://lkml.kernel.org/r/20220522061826.1751-1-gautammenghani201@gmail.com

Cc: stable@vger.kernel.org
Fixes: 8993665abcce ("tracing/boot: Support multiple handlers for per-event histogram")
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Gautam Menghani <gautammenghani201@gmail.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_boot.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c
index 0580287d7a0d..778200dd8ede 100644
--- a/kernel/trace/trace_boot.c
+++ b/kernel/trace/trace_boot.c
@@ -300,7 +300,7 @@ trace_boot_hist_add_handlers(struct xbc_node *hnode, char **bufp,
 {
 	struct xbc_node *node;
 	const char *p, *handler;
-	int ret;
+	int ret = 0;
 
 	handler = xbc_node_get_data(hnode);
 
-- 
cgit v1.2.3


From bb5eb8f3b329789fbf22c85328dcf696a3e97ffb Mon Sep 17 00:00:00 2001
From: Congyu Liu
Date: Mon, 23 May 2022 06:30:33 +0000
Subject: tracing: Disable kcov on trace_preemptirq.c

Functions in trace_preemptirq.c could be invoked from early interrupt
code that bypasses kcov trace function's in_task() check. Disable kcov
on this file to reduce random code coverage.

Link: https://lkml.kernel.org/r/20220523063033.1778974-1-liu3101@purdue.edu

Acked-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Congyu Liu <liu3101@purdue.edu>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/Makefile | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'kernel/trace')

diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index d77cd8032213..0d261774d6f3 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -31,6 +31,10 @@ ifdef CONFIG_GCOV_PROFILE_FTRACE
 GCOV_PROFILE := y
 endif
 
+# Functions in this file could be invoked from early interrupt
+# code and produce random code coverage.
+KCOV_INSTRUMENT_trace_preemptirq.o := n
+
 CFLAGS_bpf_trace.o := -I$(src)
 
 CFLAGS_trace_benchmark.o := -I$(src)
-- 
cgit v1.2.3


From 0a54f556b035e5217e21724d82dd98ce695bd6d6 Mon Sep 17 00:00:00 2001
From: sunliming
Date: Tue, 24 May 2022 14:39:37 +0800
Subject: tracing: Fix comments of create_filter()

The name in comments of parameter "filter_string" in function
create_filter is annotated as "filter_str", just fix it.

Link: https://lkml.kernel.org/r/20220524063937.52873-1-sunliming@kylinos.cn

Signed-off-by: sunliming <sunliming@kylinos.cn>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_events_filter.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index b458a9afa2c0..4b1057ab9d96 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -1816,7 +1816,7 @@ static void create_filter_finish(struct filter_parse_error *pe)
  * create_filter - create a filter for a trace_event_call
  * @tr: the trace array associated with these events
  * @call: trace_event_call to create a filter for
- * @filter_str: filter string
+ * @filter_string: filter string
  * @set_str: remember @filter_str and enable detailed error in filter
  * @filterp: out param for created filter (always updated on return)
  *           Must be a pointer that references a NULL pointer.
-- 
cgit v1.2.3


From 7d54c15cb89a29a5f59e5ffc9ee62e6591769ef1 Mon Sep 17 00:00:00 2001
From: Song Liu
Date: Tue, 24 May 2022 10:08:39 -0700
Subject: ftrace: Clean up hash direct_functions on register failures

We see the following GPF when register_ftrace_direct fails:

[ ] general protection fault, probably for non-canonical address \
  0x200000000000010: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC PTI
[...]
[ ] RIP: 0010:ftrace_find_rec_direct+0x53/0x70
[ ] Code: 48 c1 e0 03 48 03 42 08 48 8b 10 31 c0 48 85 d2 74 [...]
[ ] RSP: 0018:ffffc9000138bc10 EFLAGS: 00010206
[ ] RAX: 0000000000000000 RBX: ffffffff813e0df0 RCX: 000000000000003b
[ ] RDX: 0200000000000000 RSI: 000000000000000c RDI: ffffffff813e0df0
[ ] RBP: ffffffffa00a3000 R08: ffffffff81180ce0 R09: 0000000000000001
[ ] R10: ffffc9000138bc18 R11: 0000000000000001 R12: ffffffff813e0df0
[ ] R13: ffffffff813e0df0 R14: ffff888171b56400 R15: 0000000000000000
[ ] FS:  00007fa9420c7780(0000) GS:ffff888ff6a00000(0000) knlGS:000000000
[ ] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ ] CR2: 000000000770d000 CR3: 0000000107d50003 CR4: 0000000000370ee0
[ ] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ ] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[ ] Call Trace:
[ ]  <TASK>
[ ]  register_ftrace_direct+0x54/0x290
[ ]  ? render_sigset_t+0xa0/0xa0
[ ]  bpf_trampoline_update+0x3f5/0x4a0
[ ]  ? 0xffffffffa00a3000
[ ]  bpf_trampoline_link_prog+0xa9/0x140
[ ]  bpf_tracing_prog_attach+0x1dc/0x450
[ ]  bpf_raw_tracepoint_open+0x9a/0x1e0
[ ]  ? find_held_lock+0x2d/0x90
[ ]  ? lock_release+0x150/0x430
[ ]  __sys_bpf+0xbd6/0x2700
[ ]  ? lock_is_held_type+0xd8/0x130
[ ]  __x64_sys_bpf+0x1c/0x20
[ ]  do_syscall_64+0x3a/0x80
[ ]  entry_SYSCALL_64_after_hwframe+0x44/0xae
[ ] RIP: 0033:0x7fa9421defa9
[ ] Code: 00 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 9 f8 [...]
[ ] RSP: 002b:00007ffed743bd78 EFLAGS: 00000246 ORIG_RAX: 0000000000000141
[ ] RAX: ffffffffffffffda RBX: 00000000069d2480 RCX: 00007fa9421defa9
[ ] RDX: 0000000000000078 RSI: 00007ffed743bd80 RDI: 0000000000000011
[ ] RBP: 00007ffed743be00 R08: 0000000000bb7270 R09: 0000000000000000
[ ] R10: 00000000069da210 R11: 0000000000000246 R12: 0000000000000001
[ ] R13: 00007ffed743c4b0 R14: 00000000069d2480 R15: 0000000000000001
[ ]  </TASK>
[ ] Modules linked in: klp_vm(OK)
[ ] ---[ end trace 0000000000000000 ]---

One way to trigger this is:
  1. load a livepatch that patches kernel function xxx;
  2. run bpftrace -e 'kfunc:xxx {}', this will fail (expected for now);
  3. repeat #2 => gpf.

This is because the entry is added to direct_functions, but not removed.
Fix this by remove the entry from direct_functions when
register_ftrace_direct fails.

Also remove the last trailing space from ftrace.c, so we don't have to
worry about it anymore.

Link: https://lkml.kernel.org/r/20220524170839.900849-1-song@kernel.org

Cc: stable@vger.kernel.org
Fixes: 763e34e74bb7 ("ftrace: Add register_ftrace_direct()")
Signed-off-by: Song Liu <song@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/ftrace.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index fb8f08b4bd41..d653ef4febc5 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -4454,7 +4454,7 @@ int ftrace_func_mapper_add_ip(struct ftrace_func_mapper *mapper,
  * @ip: The instruction pointer address to remove the data from
  *
  * Returns the data if it is found, otherwise NULL.
- * Note, if the data pointer is used as the data itself, (see 
+ * Note, if the data pointer is used as the data itself, (see
  * ftrace_func_mapper_find_ip(), then the return value may be meaningless,
  * if the data pointer was set to zero.
  */
@@ -5188,8 +5188,6 @@ int register_ftrace_direct(unsigned long ip, unsigned long addr)
 		goto out_unlock;
 
 	ret = ftrace_set_filter_ip(&direct_ops, ip, 0, 0);
-	if (ret)
-		remove_hash_entry(direct_functions, entry);
 
 	if (!ret && !(direct_ops.flags & FTRACE_OPS_FL_ENABLED)) {
 		ret = register_ftrace_function(&direct_ops);
@@ -5198,6 +5196,7 @@ int register_ftrace_direct(unsigned long ip, unsigned long addr)
 	}
 
 	if (ret) {
+		remove_hash_entry(direct_functions, entry);
 		kfree(entry);
 		if (!direct->count) {
 			list_del_rcu(&direct->next);
-- 
cgit v1.2.3


From 8d4a21b5ac9dad5d5221c60060b3ac28d22f57ca Mon Sep 17 00:00:00 2001
From: sunliming
Date: Thu, 26 May 2022 15:29:57 +0800
Subject: tracing: Fix comments for event_trigger_separate_filter()

The parameter name in comments of event_trigger_separate_filter() is
inconsistent with actual parameter name, fix it.

Link: https://lkml.kernel.org/r/20220526072957.165655-1-sunliming@kylinos.cn

Signed-off-by: sunliming <sunliming@kylinos.cn>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_events_trigger.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 21592bed2e89..cb866c3141af 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -738,15 +738,15 @@ bool event_trigger_empty_param(const char *param)
 
 /**
  * event_trigger_separate_filter - separate an event trigger from a filter
- * @param: The param string containing trigger and possibly filter
- * @trigger: outparam, will be filled with a pointer to the trigger
+ * @param_and_filter: String containing trigger and possibly filter
+ * @param: outparam, will be filled with a pointer to the trigger
  * @filter: outparam, will be filled with a pointer to the filter
  * @param_required: Specifies whether or not the param string is required
  *
  * Given a param string of the form '[trigger] [if filter]', this
  * function separates the filter from the trigger and returns the
- * trigger in *trigger and the filter in *filter.  Either the *trigger
- * or the *filter may be set to NULL by this function - if not set to
+ * trigger in @param and the filter in @filter.  Either the @param
+ * or the @filter may be set to NULL by this function - if not set to
  * NULL, they will contain strings corresponding to the trigger and
  * filter.
  *
-- 
cgit v1.2.3


From b39181f7c6907dc66ff937b74758671fa6ba430c Mon Sep 17 00:00:00 2001
From: Steven Rostedt (Google)
Date: Thu, 26 May 2022 14:19:12 -0400
Subject: ftrace: Add FTRACE_MCOUNT_MAX_OFFSET to avoid adding weak function

If an unused weak function was traced, it's call to fentry will still
exist, which gets added into the __mcount_loc table. Ftrace will use
kallsyms to retrieve the name for each location in __mcount_loc to display
it in the available_filter_functions and used to enable functions via the
name matching in set_ftrace_filter/notrace. Enabling these functions do
nothing but enable an unused call to ftrace_caller. If a traced weak
function is overridden, the symbol of the function would be used for it,
which will either created duplicate names, or if the previous function was
not traced, it would be incorrectly be listed in available_filter_functions
as a function that can be traced.

This became an issue with BPF[1] as there are tooling that enables the
direct callers via ftrace but then checks to see if the functions were
actually enabled. The case of one function that was marked notrace, but
was followed by an unused weak function that was traced. The unused
function's call to fentry was added to the __mcount_loc section, and
kallsyms retrieved the untraced function's symbol as the weak function was
overridden. Since the untraced function would not get traced, the BPF
check would detect this and fail.

The real fix would be to fix kallsyms to not show addresses of weak
functions as the function before it. But that would require adding code in
the build to add function size to kallsyms so that it can know when the
function ends instead of just using the start of the next known symbol.

In the mean time, this is a work around. Add a FTRACE_MCOUNT_MAX_OFFSET
macro that if defined, ftrace will ignore any function that has its call
to fentry/mcount that has an offset from the symbol that is greater than
FTRACE_MCOUNT_MAX_OFFSET.

If CONFIG_HAVE_FENTRY is defined for x86, define FTRACE_MCOUNT_MAX_OFFSET
to zero (unless IBT is enabled), which will have ftrace ignore all locations
that are not at the start of the function (or one after the ENDBR
instruction).

A worker thread is added at boot up to scan all the ftrace record entries,
and will mark any that fail the FTRACE_MCOUNT_MAX_OFFSET test as disabled.
They will still appear in the available_filter_functions file as:

  __ftrace_invalid_address___<invalid-offset>

(showing the offset that caused it to be invalid).

This is required for tools that use libtracefs (like trace-cmd does) that
scan the available_filter_functions and enable set_ftrace_filter and
set_ftrace_notrace using indexes of the function listed in the file (this
is a speedup, as enabling thousands of files via names is an O(n^2)
operation and can take minutes to complete, where the indexing takes less
than a second).

The invalid functions cannot be removed from available_filter_functions as
the names there correspond to the ftrace records in the array that manages
them (and the indexing depends on this).

[1] https://lore.kernel.org/all/20220412094923.0abe90955e5db486b7bca279@kernel.org/

Link: https://lkml.kernel.org/r/20220526141912.794c2786@gandalf.local.home

Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 arch/x86/include/asm/ftrace.h |   7 +++
 kernel/trace/ftrace.c         | 141 +++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 146 insertions(+), 2 deletions(-)

(limited to 'kernel/trace')

diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index 024d9797646e..b5ef474be858 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -9,6 +9,13 @@
 # define MCOUNT_ADDR		((unsigned long)(__fentry__))
 #define MCOUNT_INSN_SIZE	5 /* sizeof mcount call */
 
+/* Ignore unused weak functions which will have non zero offsets */
+#ifdef CONFIG_HAVE_FENTRY
+# include <asm/ibt.h>
+/* Add offset for endbr64 if IBT enabled */
+# define FTRACE_MCOUNT_MAX_OFFSET	ENDBR_INSN_SIZE
+#endif
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 #define ARCH_SUPPORTS_FTRACE_OPS 1
 #endif
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index d653ef4febc5..c5088c76a108 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -45,6 +45,8 @@
 #include "trace_output.h"
 #include "trace_stat.h"
 
+#define FTRACE_INVALID_FUNCTION		"__ftrace_invalid_address__"
+
 #define FTRACE_WARN_ON(cond)			\
 	({					\
 		int ___r = cond;		\
@@ -3654,6 +3656,105 @@ static void add_trampoline_func(struct seq_file *m, struct ftrace_ops *ops,
 		seq_printf(m, " ->%pS", ptr);
 }
 
+#ifdef FTRACE_MCOUNT_MAX_OFFSET
+/*
+ * Weak functions can still have an mcount/fentry that is saved in
+ * the __mcount_loc section. These can be detected by having a
+ * symbol offset of greater than FTRACE_MCOUNT_MAX_OFFSET, as the
+ * symbol found by kallsyms is not the function that the mcount/fentry
+ * is part of. The offset is much greater in these cases.
+ *
+ * Test the record to make sure that the ip points to a valid kallsyms
+ * and if not, mark it disabled.
+ */
+static int test_for_valid_rec(struct dyn_ftrace *rec)
+{
+	char str[KSYM_SYMBOL_LEN];
+	unsigned long offset;
+	const char *ret;
+
+	ret = kallsyms_lookup(rec->ip, NULL, &offset, NULL, str);
+
+	/* Weak functions can cause invalid addresses */
+	if (!ret || offset > FTRACE_MCOUNT_MAX_OFFSET) {
+		rec->flags |= FTRACE_FL_DISABLED;
+		return 0;
+	}
+	return 1;
+}
+
+static struct workqueue_struct *ftrace_check_wq __initdata;
+static struct work_struct ftrace_check_work __initdata;
+
+/*
+ * Scan all the mcount/fentry entries to make sure they are valid.
+ */
+static __init void ftrace_check_work_func(struct work_struct *work)
+{
+	struct ftrace_page *pg;
+	struct dyn_ftrace *rec;
+
+	mutex_lock(&ftrace_lock);
+	do_for_each_ftrace_rec(pg, rec) {
+		test_for_valid_rec(rec);
+	} while_for_each_ftrace_rec();
+	mutex_unlock(&ftrace_lock);
+}
+
+static int __init ftrace_check_for_weak_functions(void)
+{
+	INIT_WORK(&ftrace_check_work, ftrace_check_work_func);
+
+	ftrace_check_wq = alloc_workqueue("ftrace_check_wq", WQ_UNBOUND, 0);
+
+	queue_work(ftrace_check_wq, &ftrace_check_work);
+	return 0;
+}
+
+static int __init ftrace_check_sync(void)
+{
+	/* Make sure the ftrace_check updates are finished */
+	if (ftrace_check_wq)
+		destroy_workqueue(ftrace_check_wq);
+	return 0;
+}
+
+late_initcall_sync(ftrace_check_sync);
+subsys_initcall(ftrace_check_for_weak_functions);
+
+static int print_rec(struct seq_file *m, unsigned long ip)
+{
+	unsigned long offset;
+	char str[KSYM_SYMBOL_LEN];
+	char *modname;
+	const char *ret;
+
+	ret = kallsyms_lookup(ip, NULL, &offset, &modname, str);
+	/* Weak functions can cause invalid addresses */
+	if (!ret || offset > FTRACE_MCOUNT_MAX_OFFSET) {
+		snprintf(str, KSYM_SYMBOL_LEN, "%s_%ld",
+			 FTRACE_INVALID_FUNCTION, offset);
+		ret = NULL;
+	}
+
+	seq_puts(m, str);
+	if (modname)
+		seq_printf(m, " [%s]", modname);
+	return ret == NULL ? -1 : 0;
+}
+#else
+static inline int test_for_valid_rec(struct dyn_ftrace *rec)
+{
+	return 1;
+}
+
+static inline int print_rec(struct seq_file *m, unsigned long ip)
+{
+	seq_printf(m, "%ps", (void *)ip);
+	return 0;
+}
+#endif
+
 static int t_show(struct seq_file *m, void *v)
 {
 	struct ftrace_iterator *iter = m->private;
@@ -3678,7 +3779,13 @@ static int t_show(struct seq_file *m, void *v)
 	if (!rec)
 		return 0;
 
-	seq_printf(m, "%ps", (void *)rec->ip);
+	if (print_rec(m, rec->ip)) {
+		/* This should only happen when a rec is disabled */
+		WARN_ON_ONCE(!(rec->flags & FTRACE_FL_DISABLED));
+		seq_putc(m, '\n');
+		return 0;
+	}
+
 	if (iter->flags & FTRACE_ITER_ENABLED) {
 		struct ftrace_ops *ops;
 
@@ -3996,6 +4103,24 @@ add_rec_by_index(struct ftrace_hash *hash, struct ftrace_glob *func_g,
 	return 0;
 }
 
+#ifdef FTRACE_MCOUNT_MAX_OFFSET
+static int lookup_ip(unsigned long ip, char **modname, char *str)
+{
+	unsigned long offset;
+
+	kallsyms_lookup(ip, NULL, &offset, modname, str);
+	if (offset > FTRACE_MCOUNT_MAX_OFFSET)
+		return -1;
+	return 0;
+}
+#else
+static int lookup_ip(unsigned long ip, char **modname, char *str)
+{
+	kallsyms_lookup(ip, NULL, NULL, modname, str);
+	return 0;
+}
+#endif
+
 static int
 ftrace_match_record(struct dyn_ftrace *rec, struct ftrace_glob *func_g,
 		struct ftrace_glob *mod_g, int exclude_mod)
@@ -4003,7 +4128,12 @@ ftrace_match_record(struct dyn_ftrace *rec, struct ftrace_glob *func_g,
 	char str[KSYM_SYMBOL_LEN];
 	char *modname;
 
-	kallsyms_lookup(rec->ip, NULL, NULL, &modname, str);
+	if (lookup_ip(rec->ip, &modname, str)) {
+		/* This should only happen when a rec is disabled */
+		WARN_ON_ONCE(system_state == SYSTEM_RUNNING &&
+			     !(rec->flags & FTRACE_FL_DISABLED));
+		return 0;
+	}
 
 	if (mod_g) {
 		int mod_matches = (modname) ? ftrace_match(modname, mod_g) : 0;
@@ -6819,6 +6949,13 @@ void ftrace_module_enable(struct module *mod)
 		    !within_module_init(rec->ip, mod))
 			break;
 
+		/* Weak functions should still be ignored */
+		if (!test_for_valid_rec(rec)) {
+			/* Clear all other flags. Should not be enabled anyway */
+			rec->flags = FTRACE_FL_DISABLED;
+			continue;
+		}
+
 		cnt = 0;
 
 		/*
-- 
cgit v1.2.3