1 files changed, 150 insertions, 48 deletions

diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 069e92856bda..9f3e9537417d 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -400,6 +400,20 @@ static bool process_string(const char *fmt, int len, struct trace_event_call *ca
 	return true;
 }
 
+static void handle_dereference_arg(const char *arg_str, u64 string_flags, int len,
+				   u64 *dereference_flags, int arg,
+				   struct trace_event_call *call)
+{
+	if (string_flags & (1ULL << arg)) {
+		if (process_string(arg_str, len, call))
+			*dereference_flags &= ~(1ULL << arg);
+	} else if (process_pointer(arg_str, len, call))
+		*dereference_flags &= ~(1ULL << arg);
+	else
+		pr_warn("TRACE EVENT ERROR: Bad dereference argument: '%.*s'\n",
+			len, arg_str);
+}
+
 /*
  * Examine the print fmt of the event looking for unsafe dereference
  * pointers using %p* that could be recorded in the trace event and
@@ -563,11 +577,9 @@ static void test_event_printk(struct trace_event_call *call)
 			}
 
 			if (dereference_flags & (1ULL << arg)) {
-				if (string_flags & (1ULL << arg)) {
-					if (process_string(fmt + start_arg, e - start_arg, call))
-						dereference_flags &= ~(1ULL << arg);
-				} else if (process_pointer(fmt + start_arg, e - start_arg, call))
-					dereference_flags &= ~(1ULL << arg);
+				handle_dereference_arg(fmt + start_arg, string_flags,
+						       e - start_arg,
+						       &dereference_flags, arg, call);
 			}
 
 			start_arg = i;
@@ -578,11 +590,9 @@ static void test_event_printk(struct trace_event_call *call)
 	}
 
 	if (dereference_flags & (1ULL << arg)) {
-		if (string_flags & (1ULL << arg)) {
-			if (process_string(fmt + start_arg, i - start_arg, call))
-				dereference_flags &= ~(1ULL << arg);
-		} else if (process_pointer(fmt + start_arg, i - start_arg, call))
-			dereference_flags &= ~(1ULL << arg);
+		handle_dereference_arg(fmt + start_arg, string_flags,
+				       i - start_arg,
+				       &dereference_flags, arg, call);
 	}
 
 	/*
@@ -622,7 +632,6 @@ EXPORT_SYMBOL_GPL(trace_event_raw_init);
 bool trace_event_ignore_this_pid(struct trace_event_file *trace_file)
 {
 	struct trace_array *tr = trace_file->tr;
-	struct trace_array_cpu *data;
 	struct trace_pid_list *no_pid_list;
 	struct trace_pid_list *pid_list;
 
@@ -632,9 +641,11 @@ bool trace_event_ignore_this_pid(struct trace_event_file *trace_file)
 	if (!pid_list && !no_pid_list)
 		return false;
 
-	data = this_cpu_ptr(tr->array_buffer.data);
-
-	return data->ignore_pid;
+	/*
+	 * This is recorded at every sched_switch for this task.
+	 * Thus, even if the task migrates the ignore value will be the same.
+	 */
+	return this_cpu_read(tr->array_buffer.data->ignore_pid) != 0;
 }
 EXPORT_SYMBOL_GPL(trace_event_ignore_this_pid);
 
@@ -757,6 +768,7 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file,
 {
 	struct trace_event_call *call = file->event_call;
 	struct trace_array *tr = file->tr;
+	bool soft_mode = atomic_read(&file->sm_ref) != 0;
 	int ret = 0;
 	int disable;
 
@@ -771,7 +783,7 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file,
 		 * is set we do not want the event to be enabled before we
 		 * clear the bit.
 		 *
-		 * When soft_disable is not set but the SOFT_MODE flag is,
+		 * When soft_disable is not set but the soft_mode is,
 		 * we do nothing. Do not disable the tracepoint, otherwise
 		 * "soft enable"s (clearing the SOFT_DISABLED bit) wont work.
 		 */
@@ -779,11 +791,11 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file,
 			if (atomic_dec_return(&file->sm_ref) > 0)
 				break;
 			disable = file->flags & EVENT_FILE_FL_SOFT_DISABLED;
-			clear_bit(EVENT_FILE_FL_SOFT_MODE_BIT, &file->flags);
+			soft_mode = false;
 			/* Disable use of trace_buffered_event */
 			trace_buffered_event_disable();
 		} else
-			disable = !(file->flags & EVENT_FILE_FL_SOFT_MODE);
+			disable = !soft_mode;
 
 		if (disable && (file->flags & EVENT_FILE_FL_ENABLED)) {
 			clear_bit(EVENT_FILE_FL_ENABLED_BIT, &file->flags);
@@ -801,8 +813,8 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file,
 
 			WARN_ON_ONCE(ret);
 		}
-		/* If in SOFT_MODE, just set the SOFT_DISABLE_BIT, else clear it */
-		if (file->flags & EVENT_FILE_FL_SOFT_MODE)
+		/* If in soft mode, just set the SOFT_DISABLE_BIT, else clear it */
+		if (soft_mode)
 			set_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags);
 		else
 			clear_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags);
@@ -812,7 +824,7 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file,
 		 * When soft_disable is set and enable is set, we want to
 		 * register the tracepoint for the event, but leave the event
 		 * as is. That means, if the event was already enabled, we do
-		 * nothing (but set SOFT_MODE). If the event is disabled, we
+		 * nothing (but set soft_mode). If the event is disabled, we
 		 * set SOFT_DISABLED before enabling the event tracepoint, so
 		 * it still seems to be disabled.
 		 */
@@ -821,7 +833,7 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file,
 		else {
 			if (atomic_inc_return(&file->sm_ref) > 1)
 				break;
-			set_bit(EVENT_FILE_FL_SOFT_MODE_BIT, &file->flags);
+			soft_mode = true;
 			/* Enable use of trace_buffered_event */
 			trace_buffered_event_enable();
 		}
@@ -829,7 +841,7 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file,
 		if (!(file->flags & EVENT_FILE_FL_ENABLED)) {
 			bool cmd = false, tgid = false;
 
-			/* Keep the event disabled, when going to SOFT_MODE. */
+			/* Keep the event disabled, when going to soft mode. */
 			if (soft_disable)
 				set_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags);
 
@@ -1781,8 +1793,7 @@ event_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
 	    !(flags & EVENT_FILE_FL_SOFT_DISABLED))
 		strcpy(buf, "1");
 
-	if (flags & EVENT_FILE_FL_SOFT_DISABLED ||
-	    flags & EVENT_FILE_FL_SOFT_MODE)
+	if (atomic_read(&file->sm_ref) != 0)
 		strcat(buf, "*");
 
 	strcat(buf, "\n");
@@ -3125,7 +3136,10 @@ __register_event(struct trace_event_call *call, struct module *mod)
 	if (ret < 0)
 		return ret;
 
+	down_write(&trace_event_sem);
 	list_add(&call->list, &ftrace_events);
+	up_write(&trace_event_sem);
+
 	if (call->flags & TRACE_EVENT_FL_DYNAMIC)
 		atomic_set(&call->refcnt, 0);
 	else
@@ -3253,43 +3267,120 @@ static void add_str_to_module(struct module *module, char *str)
 	list_add(&modstr->next, &module_strings);
 }
 
+#define ATTRIBUTE_STR "__attribute__("
+#define ATTRIBUTE_STR_LEN (sizeof(ATTRIBUTE_STR) - 1)
+
+/* Remove all __attribute__() from @type. Return allocated string or @type. */
+static char *sanitize_field_type(const char *type)
+{
+	char *attr, *tmp, *next, *ret = (char *)type;
+	int depth;
+
+	next = (char *)type;
+	while ((attr = strstr(next, ATTRIBUTE_STR))) {
+		/* Retry if "__attribute__(" is a part of another word. */
+		if (attr != next && !isspace(attr[-1])) {
+			next = attr + ATTRIBUTE_STR_LEN;
+			continue;
+		}
+
+		if (ret == type) {
+			ret = kstrdup(type, GFP_KERNEL);
+			if (WARN_ON_ONCE(!ret))
+				return NULL;
+			attr = ret + (attr - type);
+		}
+
+		/* the ATTRIBUTE_STR already has the first '(' */
+		depth = 1;
+		next = attr + ATTRIBUTE_STR_LEN;
+		do {
+			tmp = strpbrk(next, "()");
+			/* There is unbalanced parentheses */
+			if (WARN_ON_ONCE(!tmp)) {
+				kfree(ret);
+				return (char *)type;
+			}
+
+			if (*tmp == '(')
+				depth++;
+			else
+				depth--;
+			next = tmp + 1;
+		} while (depth > 0);
+		next = skip_spaces(next);
+		strcpy(attr, next);
+		next = attr;
+	}
+	return ret;
+}
+
+static char *find_replacable_eval(const char *type, const char *eval_string,
+				  int len)
+{
+	char *ptr;
+
+	if (!eval_string)
+		return NULL;
+
+	ptr = strchr(type, '[');
+	if (!ptr)
+		return NULL;
+	ptr++;
+
+	if (!isalpha(*ptr) && *ptr != '_')
+		return NULL;
+
+	if (strncmp(eval_string, ptr, len) != 0)
+		return NULL;
+
+	return ptr;
+}
+
 static void update_event_fields(struct trace_event_call *call,
 				struct trace_eval_map *map)
 {
 	struct ftrace_event_field *field;
+	const char *eval_string = NULL;
 	struct list_head *head;
+	int len = 0;
 	char *ptr;
 	char *str;
-	int len = strlen(map->eval_string);
 
 	/* Dynamic events should never have field maps */
-	if (WARN_ON_ONCE(call->flags & TRACE_EVENT_FL_DYNAMIC))
+	if (call->flags & TRACE_EVENT_FL_DYNAMIC)
 		return;
 
+	if (map) {
+		eval_string = map->eval_string;
+		len = strlen(map->eval_string);
+	}
+
 	head = trace_get_fields(call);
 	list_for_each_entry(field, head, link) {
-		ptr = strchr(field->type, '[');
-		if (!ptr)
-			continue;
-		ptr++;
-
-		if (!isalpha(*ptr) && *ptr != '_')
-			continue;
+		str = sanitize_field_type(field->type);
+		if (!str)
+			return;
 
-		if (strncmp(map->eval_string, ptr, len) != 0)
-			continue;
+		ptr = find_replacable_eval(str, eval_string, len);
+		if (ptr) {
+			if (str == field->type) {
+				str = kstrdup(field->type, GFP_KERNEL);
+				if (WARN_ON_ONCE(!str))
+					return;
+				ptr = str + (ptr - field->type);
+			}
 
-		str = kstrdup(field->type, GFP_KERNEL);
-		if (WARN_ON_ONCE(!str))
-			return;
-		ptr = str + (ptr - field->type);
-		ptr = eval_replace(ptr, map, len);
-		/* enum/sizeof string smaller than value */
-		if (WARN_ON_ONCE(!ptr)) {
-			kfree(str);
-			continue;
+			ptr = eval_replace(ptr, map, len);
+			/* enum/sizeof string smaller than value */
+			if (WARN_ON_ONCE(!ptr)) {
+				kfree(str);
+				continue;
+			}
 		}
 
+		if (str == field->type)
+			continue;
 		/*
 		 * If the event is part of a module, then we need to free the string
 		 * when the module is removed. Otherwise, it will stay allocated
@@ -3299,14 +3390,18 @@ static void update_event_fields(struct trace_event_call *call,
 			add_str_to_module(call->module, str);
 
 		field->type = str;
+		if (field->filter_type == FILTER_OTHER)
+			field->filter_type = filter_assign_type(field->type);
 	}
 }
 
-void trace_event_eval_update(struct trace_eval_map **map, int len)
+/* Update all events for replacing eval and sanitizing */
+void trace_event_update_all(struct trace_eval_map **map, int len)
 {
 	struct trace_event_call *call, *p;
 	const char *last_system = NULL;
 	bool first = false;
+	bool updated;
 	int last_i;
 	int i;
 
@@ -3319,6 +3414,7 @@ void trace_event_eval_update(struct trace_eval_map **map, int len)
 			last_system = call->class->system;
 		}
 
+		updated = false;
 		/*
 		 * Since calls are grouped by systems, the likelihood that the
 		 * next call in the iteration belongs to the same system as the
@@ -3338,8 +3434,12 @@ void trace_event_eval_update(struct trace_eval_map **map, int len)
 				}
 				update_event_printk(call, map[i]);
 				update_event_fields(call, map[i]);
+				updated = true;
 			}
 		}
+		/* If not updated yet, update field for sanitizing. */
+		if (!updated)
+			update_event_fields(call, NULL);
 		cond_resched();
 	}
 	up_write(&trace_event_sem);
@@ -3573,7 +3673,7 @@ static int probe_remove_event_call(struct trace_event_call *call)
 			continue;
 		/*
 		 * We can't rely on ftrace_event_enable_disable(enable => 0)
-		 * we are going to do, EVENT_FILE_FL_SOFT_MODE can suppress
+		 * we are going to do, soft mode can suppress
 		 * TRACE_REG_UNREGISTER.
 		 */
 		if (file->flags & EVENT_FILE_FL_ENABLED)
@@ -3684,7 +3784,7 @@ static void trace_module_remove_events(struct module *mod)
 		if (call->module == mod)
 			__trace_remove_event_call(call);
 	}
-	/* Check for any strings allocade for this module */
+	/* Check for any strings allocated for this module */
 	list_for_each_entry_safe(modstr, m, &module_strings, next) {
 		if (modstr->module != mod)
 			continue;
@@ -3739,6 +3839,8 @@ __trace_add_event_dirs(struct trace_array *tr)
 	struct trace_event_call *call;
 	int ret;
 
+	lockdep_assert_held(&trace_event_sem);
+
 	list_for_each_entry(call, &ftrace_events, list) {
 		ret = __trace_add_new_event(call, tr);
 		if (ret < 0)
@@ -3986,7 +4088,7 @@ static int free_probe_data(void *data)
 
 	edata->ref--;
 	if (!edata->ref) {
-		/* Remove the SOFT_MODE flag */
+		/* Remove soft mode */
 		__ftrace_event_enable_disable(edata->file, 0, 1);
 		trace_event_put_ref(edata->file->event_call);
 		kfree(edata);