1 files changed, 227 insertions, 65 deletions

diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c
index e76f5e1efdf2..97325fbd6283 100644
--- a/kernel/trace/trace_events_user.c
+++ b/kernel/trace/trace_events_user.c
@@ -34,7 +34,8 @@
 
 /* Limit how long of an event name plus args within the subsystem. */
 #define MAX_EVENT_DESC 512
-#define EVENT_NAME(user_event) ((user_event)->tracepoint.name)
+#define EVENT_NAME(user_event) ((user_event)->reg_name)
+#define EVENT_TP_NAME(user_event) ((user_event)->tracepoint.name)
 #define MAX_FIELD_ARRAY_SIZE 1024
 
 /*
@@ -54,10 +55,13 @@
  * allows isolation for events by various means.
  */
 struct user_event_group {
-	char		*system_name;
-	struct		hlist_node node;
-	struct		mutex reg_mutex;
+	char			*system_name;
+	char			*system_multi_name;
+	struct hlist_node	node;
+	struct mutex		reg_mutex;
 	DECLARE_HASHTABLE(register_table, 8);
+	/* ID that moves forward within the group for multi-event names */
+	u64			multi_id;
 };
 
 /* Group for init_user_ns mapping, top-most group */
@@ -78,6 +82,7 @@ static unsigned int current_user_events;
  */
 struct user_event {
 	struct user_event_group		*group;
+	char				*reg_name;
 	struct tracepoint		tracepoint;
 	struct trace_event_call		call;
 	struct trace_event_class	class;
@@ -127,6 +132,8 @@ struct user_event_enabler {
 
 #define ENABLE_BIT(e) ((int)((e)->values & ENABLE_VAL_BIT_MASK))
 
+#define EVENT_MULTI_FORMAT(f) ((f) & USER_EVENT_REG_MULTI_FORMAT)
+
 /* Used for asynchronous faulting in of pages */
 struct user_event_enabler_fault {
 	struct work_struct		work;
@@ -202,6 +209,8 @@ static struct user_event_mm *user_event_mm_get(struct user_event_mm *mm);
 static struct user_event_mm *user_event_mm_get_all(struct user_event *user);
 static void user_event_mm_put(struct user_event_mm *mm);
 static int destroy_user_event(struct user_event *user);
+static bool user_fields_match(struct user_event *user, int argc,
+			      const char **argv);
 
 static u32 user_event_key(char *name)
 {
@@ -328,6 +337,7 @@ out:
 static void user_event_group_destroy(struct user_event_group *group)
 {
 	kfree(group->system_name);
+	kfree(group->system_multi_name);
 	kfree(group);
 }
 
@@ -346,6 +356,11 @@ static char *user_event_group_system_name(void)
 	return system_name;
 }
 
+static char *user_event_group_system_multi_name(void)
+{
+	return kstrdup(USER_EVENTS_MULTI_SYSTEM, GFP_KERNEL);
+}
+
 static struct user_event_group *current_user_event_group(void)
 {
 	return init_group;
@@ -365,6 +380,11 @@ static struct user_event_group *user_event_group_create(void)
 	if (!group->system_name)
 		goto error;
 
+	group->system_multi_name = user_event_group_system_multi_name();
+
+	if (!group->system_multi_name)
+		goto error;
+
 	mutex_init(&group->reg_mutex);
 	hash_init(group->register_table);
 
@@ -1480,6 +1500,11 @@ static int destroy_user_event(struct user_event *user)
 	hash_del(&user->node);
 
 	user_event_destroy_validators(user);
+
+	/* If we have different names, both must be freed */
+	if (EVENT_NAME(user) != EVENT_TP_NAME(user))
+		kfree(EVENT_TP_NAME(user));
+
 	kfree(user->call.print_fmt);
 	kfree(EVENT_NAME(user));
 	kfree(user);
@@ -1493,17 +1518,36 @@ static int destroy_user_event(struct user_event *user)
 }
 
 static struct user_event *find_user_event(struct user_event_group *group,
-					  char *name, u32 *outkey)
+					  char *name, int argc, const char **argv,
+					  u32 flags, u32 *outkey)
 {
 	struct user_event *user;
 	u32 key = user_event_key(name);
 
 	*outkey = key;
 
-	hash_for_each_possible(group->register_table, user, node, key)
-		if (!strcmp(EVENT_NAME(user), name))
+	hash_for_each_possible(group->register_table, user, node, key) {
+		/*
+		 * Single-format events shouldn't return multi-format
+		 * events. Callers expect the underlying tracepoint to match
+		 * the name exactly in these cases. Only check like-formats.
+		 */
+		if (EVENT_MULTI_FORMAT(flags) != EVENT_MULTI_FORMAT(user->reg_flags))
+			continue;
+
+		if (strcmp(EVENT_NAME(user), name))
+			continue;
+
+		if (user_fields_match(user, argc, argv))
 			return user_event_get(user);
 
+		/* Scan others if this is a multi-format event */
+		if (EVENT_MULTI_FORMAT(flags))
+			continue;
+
+		return ERR_PTR(-EADDRINUSE);
+	}
+
 	return NULL;
 }
 
@@ -1632,7 +1676,7 @@ static void update_enable_bit_for(struct user_event *user)
 	struct tracepoint *tp = &user->tracepoint;
 	char status = 0;
 
-	if (atomic_read(&tp->key.enabled) > 0) {
+	if (static_key_enabled(&tp->key)) {
 		struct tracepoint_func *probe_func_ptr;
 		user_event_func_t probe_func;
 
@@ -1860,6 +1904,9 @@ static bool user_fields_match(struct user_event *user, int argc,
 	struct list_head *head = &user->fields;
 	int i = 0;
 
+	if (argc == 0)
+		return list_empty(head);
+
 	list_for_each_entry_reverse(field, head, link) {
 		if (!user_field_match(field, argc, argv, &i))
 			return false;
@@ -1877,13 +1924,15 @@ static bool user_event_match(const char *system, const char *event,
 	struct user_event *user = container_of(ev, struct user_event, devent);
 	bool match;
 
-	match = strcmp(EVENT_NAME(user), event) == 0 &&
-		(!system || strcmp(system, USER_EVENTS_SYSTEM) == 0);
+	match = strcmp(EVENT_NAME(user), event) == 0;
 
-	if (match && argc > 0)
+	if (match && system) {
+		match = strcmp(system, user->group->system_name) == 0 ||
+			strcmp(system, user->group->system_multi_name) == 0;
+	}
+
+	if (match)
 		match = user_fields_match(user, argc, argv);
-	else if (match && argc == 0)
-		match = list_empty(&user->fields);
 
 	return match;
 }
@@ -1913,6 +1962,107 @@ static int user_event_trace_register(struct user_event *user)
 	return ret;
 }
 
+static int user_event_set_tp_name(struct user_event *user)
+{
+	lockdep_assert_held(&user->group->reg_mutex);
+
+	if (EVENT_MULTI_FORMAT(user->reg_flags)) {
+		char *multi_name;
+
+		multi_name = kasprintf(GFP_KERNEL_ACCOUNT, "%s.%llx",
+				       user->reg_name, user->group->multi_id);
+
+		if (!multi_name)
+			return -ENOMEM;
+
+		user->call.name = multi_name;
+		user->tracepoint.name = multi_name;
+
+		/* Inc to ensure unique multi-event name next time */
+		user->group->multi_id++;
+	} else {
+		/* Non Multi-format uses register name */
+		user->call.name = user->reg_name;
+		user->tracepoint.name = user->reg_name;
+	}
+
+	return 0;
+}
+
+/*
+ * Counts how many ';' without a trailing space are in the args.
+ */
+static int count_semis_no_space(char *args)
+{
+	int count = 0;
+
+	while ((args = strchr(args, ';'))) {
+		args++;
+
+		if (!isspace(*args))
+			count++;
+	}
+
+	return count;
+}
+
+/*
+ * Copies the arguments while ensuring all ';' have a trailing space.
+ */
+static char *insert_space_after_semis(char *args, int count)
+{
+	char *fixed, *pos;
+	int len;
+
+	len = strlen(args) + count;
+	fixed = kmalloc(len + 1, GFP_KERNEL);
+
+	if (!fixed)
+		return NULL;
+
+	pos = fixed;
+
+	/* Insert a space after ';' if there is no trailing space. */
+	while (*args) {
+		*pos = *args++;
+
+		if (*pos++ == ';' && !isspace(*args))
+			*pos++ = ' ';
+	}
+
+	*pos = '\0';
+
+	return fixed;
+}
+
+static char **user_event_argv_split(char *args, int *argc)
+{
+	char **split;
+	char *fixed;
+	int count;
+
+	/* Count how many ';' without a trailing space */
+	count = count_semis_no_space(args);
+
+	/* No fixup is required */
+	if (!count)
+		return argv_split(GFP_KERNEL, args, argc);
+
+	/* We must fixup 'field;field' to 'field; field' */
+	fixed = insert_space_after_semis(args, count);
+
+	if (!fixed)
+		return NULL;
+
+	/* We do a normal split afterwards */
+	split = argv_split(GFP_KERNEL, fixed, argc);
+
+	/* We can free since argv_split makes a copy */
+	kfree(fixed);
+
+	return split;
+}
+
 /*
  * Parses the event name, arguments and flags then registers if successful.
  * The name buffer lifetime is owned by this method for success cases only.
@@ -1922,11 +2072,11 @@ static int user_event_parse(struct user_event_group *group, char *name,
 			    char *args, char *flags,
 			    struct user_event **newuser, int reg_flags)
 {
-	int ret;
-	u32 key;
 	struct user_event *user;
+	char **argv = NULL;
 	int argc = 0;
-	char **argv;
+	int ret;
+	u32 key;
 
 	/* Currently don't support any text based flags */
 	if (flags != NULL)
@@ -1935,41 +2085,34 @@ static int user_event_parse(struct user_event_group *group, char *name,
 	if (!user_event_capable(reg_flags))
 		return -EPERM;
 
+	if (args) {
+		argv = user_event_argv_split(args, &argc);
+
+		if (!argv)
+			return -ENOMEM;
+	}
+
 	/* Prevent dyn_event from racing */
 	mutex_lock(&event_mutex);
-	user = find_user_event(group, name, &key);
+	user = find_user_event(group, name, argc, (const char **)argv,
+			       reg_flags, &key);
 	mutex_unlock(&event_mutex);
 
-	if (user) {
-		if (args) {
-			argv = argv_split(GFP_KERNEL, args, &argc);
-			if (!argv) {
-				ret = -ENOMEM;
-				goto error;
-			}
+	if (argv)
+		argv_free(argv);
 
-			ret = user_fields_match(user, argc, (const char **)argv);
-			argv_free(argv);
-
-		} else
-			ret = list_empty(&user->fields);
-
-		if (ret) {
-			*newuser = user;
-			/*
-			 * Name is allocated by caller, free it since it already exists.
-			 * Caller only worries about failure cases for freeing.
-			 */
-			kfree(name);
-		} else {
-			ret = -EADDRINUSE;
-			goto error;
-		}
+	if (IS_ERR(user))
+		return PTR_ERR(user);
+
+	if (user) {
+		*newuser = user;
+		/*
+		 * Name is allocated by caller, free it since it already exists.
+		 * Caller only worries about failure cases for freeing.
+		 */
+		kfree(name);
 
 		return 0;
-error:
-		user_event_put(user, false);
-		return ret;
 	}
 
 	user = kzalloc(sizeof(*user), GFP_KERNEL_ACCOUNT);
@@ -1982,7 +2125,13 @@ error:
 	INIT_LIST_HEAD(&user->validators);
 
 	user->group = group;
-	user->tracepoint.name = name;
+	user->reg_name = name;
+	user->reg_flags = reg_flags;
+
+	ret = user_event_set_tp_name(user);
+
+	if (ret)
+		goto put_user;
 
 	ret = user_event_parse_fields(user, args);
 
@@ -1996,11 +2145,14 @@ error:
 
 	user->call.data = user;
 	user->call.class = &user->class;
-	user->call.name = name;
 	user->call.flags = TRACE_EVENT_FL_TRACEPOINT;
 	user->call.tp = &user->tracepoint;
 	user->call.event.funcs = &user_event_funcs;
-	user->class.system = group->system_name;
+
+	if (EVENT_MULTI_FORMAT(user->reg_flags))
+		user->class.system = group->system_multi_name;
+	else
+		user->class.system = group->system_name;
 
 	user->class.fields_array = user_event_fields_array;
 	user->class.get_fields = user_event_get_fields;
@@ -2022,8 +2174,6 @@ error:
 	if (ret)
 		goto put_user_lock;
 
-	user->reg_flags = reg_flags;
-
 	if (user->reg_flags & USER_EVENT_REG_PERSIST) {
 		/* Ensure we track self ref and caller ref (2) */
 		refcount_set(&user->refcnt, 2);
@@ -2047,30 +2197,43 @@ put_user:
 	user_event_destroy_fields(user);
 	user_event_destroy_validators(user);
 	kfree(user->call.print_fmt);
+
+	/* Caller frees reg_name on error, but not multi-name */
+	if (EVENT_NAME(user) != EVENT_TP_NAME(user))
+		kfree(EVENT_TP_NAME(user));
+
 	kfree(user);
 	return ret;
 }
 
 /*
- * Deletes a previously created event if it is no longer being used.
+ * Deletes previously created events if they are no longer being used.
  */
 static int delete_user_event(struct user_event_group *group, char *name)
 {
-	u32 key;
-	struct user_event *user = find_user_event(group, name, &key);
+	struct user_event *user;
+	struct hlist_node *tmp;
+	u32 key = user_event_key(name);
+	int ret = -ENOENT;
 
-	if (!user)
-		return -ENOENT;
+	/* Attempt to delete all event(s) with the name passed in */
+	hash_for_each_possible_safe(group->register_table, user, tmp, node, key) {
+		if (strcmp(EVENT_NAME(user), name))
+			continue;
 
-	user_event_put(user, true);
+		if (!user_event_last_ref(user))
+			return -EBUSY;
 
-	if (!user_event_last_ref(user))
-		return -EBUSY;
+		if (!user_event_capable(user->reg_flags))
+			return -EPERM;
 
-	if (!user_event_capable(user->reg_flags))
-		return -EPERM;
+		ret = destroy_user_event(user);
 
-	return destroy_user_event(user);
+		if (ret)
+			goto out;
+	}
+out:
+	return ret;
 }
 
 /*
@@ -2117,7 +2280,7 @@ static ssize_t user_events_write_core(struct file *file, struct iov_iter *i)
 	 * It's possible key.enabled disables after this check, however
 	 * we don't mind if a few events are included in this condition.
 	 */
-	if (likely(atomic_read(&tp->key.enabled) > 0)) {
+	if (likely(static_key_enabled(&tp->key))) {
 		struct tracepoint_func *probe_func_ptr;
 		user_event_func_t probe_func;
 		struct iov_iter copy;
@@ -2628,7 +2791,7 @@ static int user_seq_show(struct seq_file *m, void *p)
 	hash_for_each(group->register_table, i, user, node) {
 		status = user->status;
 
-		seq_printf(m, "%s", EVENT_NAME(user));
+		seq_printf(m, "%s", EVENT_TP_NAME(user));
 
 		if (status != 0)
 			seq_puts(m, " #");
@@ -2722,7 +2885,7 @@ err:
 	return -ENODEV;
 }
 
-static int set_max_user_events_sysctl(struct ctl_table *table, int write,
+static int set_max_user_events_sysctl(const struct ctl_table *table, int write,
 				      void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret;
@@ -2736,7 +2899,7 @@ static int set_max_user_events_sysctl(struct ctl_table *table, int write,
 	return ret;
 }
 
-static struct ctl_table user_event_sysctls[] = {
+static const struct ctl_table user_event_sysctls[] = {
 	{
 		.procname	= "user_events_max",
 		.data		= &max_user_events,
@@ -2744,7 +2907,6 @@ static struct ctl_table user_event_sysctls[] = {
 		.mode		= 0644,
 		.proc_handler	= set_max_user_events_sysctl,
 	},
-	{}
 };
 
 static int __init trace_events_user_init(void)