Merge tag 'trace-v4.13-rc1' of git://git.kernel.org/pub/scm/linux/ker…

…nel/git/rostedt/linux-trace

Pull tracing fixes from Steven Rostedt:
 "Three minor updates

   - Use the new GFP_RETRY_MAYFAIL to be more aggressive in allocating
     memory for the ring buffer without causing OOMs

   - Fix a memory leak in adding and removing instances

   - Add __rcu annotation to be able to debug RCU usage of function
     tracing a bit better"

* tag 'trace-v4.13-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace:
  trace: fix the errors caused by incompatible type of RCU variables
  tracing: Fix kmemleak in instance_rmdir
  tracing/ring_buffer: Try harder to allocate

include/linux/ftrace.h

@@ -145,8 +145,8 @@ enum {
 #ifdef CONFIG_DYNAMIC_FTRACE
 /* The hash used to know what functions callbacks trace */
 struct ftrace_ops_hash {
-	struct ftrace_hash		*notrace_hash;
-	struct ftrace_hash		*filter_hash;
+	struct ftrace_hash __rcu	*notrace_hash;
+	struct ftrace_hash __rcu	*filter_hash;
 	struct mutex			regex_lock;
 };
 
@@ -168,7 +168,7 @@ static inline void ftrace_free_init_mem(void) { }
  */
 struct ftrace_ops {
 	ftrace_func_t			func;
-	struct ftrace_ops		*next;
+	struct ftrace_ops __rcu		*next;
 	unsigned long			flags;
 	void				*private;
 	ftrace_func_t			saved_func;

include/linux/trace_events.h

@@ -338,7 +338,7 @@ enum {
 struct trace_event_file {
 	struct list_head		list;
 	struct trace_event_call		*event_call;
-	struct event_filter		*filter;
+	struct event_filter __rcu	*filter;
 	struct dentry			*dir;
 	struct trace_array		*tr;
 	struct trace_subsystem_dir	*system;

kernel/trace/ftrace.c

@@ -113,7 +113,7 @@ static int ftrace_disabled __read_mostly;
 
 static DEFINE_MUTEX(ftrace_lock);
 
-static struct ftrace_ops *ftrace_ops_list __read_mostly = &ftrace_list_end;
+static struct ftrace_ops __rcu *ftrace_ops_list __read_mostly = &ftrace_list_end;
 ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub;
 static struct ftrace_ops global_ops;
 
@@ -169,8 +169,11 @@ int ftrace_nr_registered_ops(void)
 
 	mutex_lock(&ftrace_lock);
 
-	for (ops = ftrace_ops_list;
-	     ops != &ftrace_list_end; ops = ops->next)
+	for (ops = rcu_dereference_protected(ftrace_ops_list,
+					     lockdep_is_held(&ftrace_lock));
+	     ops != &ftrace_list_end;
+	     ops = rcu_dereference_protected(ops->next,
+					     lockdep_is_held(&ftrace_lock)))
 		cnt++;
 
 	mutex_unlock(&ftrace_lock);
@@ -275,18 +278,20 @@ static void update_ftrace_function(void)
 	 * If there's only one ftrace_ops registered, the ftrace_ops_list
 	 * will point to the ops we want.
 	 */
-	set_function_trace_op = ftrace_ops_list;
+	set_function_trace_op = rcu_dereference_protected(ftrace_ops_list,
+						lockdep_is_held(&ftrace_lock));
 
 	/* If there's no ftrace_ops registered, just call the stub function */
-	if (ftrace_ops_list == &ftrace_list_end) {
+	if (set_function_trace_op == &ftrace_list_end) {
 		func = ftrace_stub;
 
 	/*
 	 * If we are at the end of the list and this ops is
 	 * recursion safe and not dynamic and the arch supports passing ops,
 	 * then have the mcount trampoline call the function directly.
 	 */
-	} else if (ftrace_ops_list->next == &ftrace_list_end) {
+	} else if (rcu_dereference_protected(ftrace_ops_list->next,
+			lockdep_is_held(&ftrace_lock)) == &ftrace_list_end) {
 		func = ftrace_ops_get_list_func(ftrace_ops_list);
 
 	} else {
@@ -348,9 +353,11 @@ int using_ftrace_ops_list_func(void)
 	return ftrace_trace_function == ftrace_ops_list_func;
 }
 
-static void add_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops)
+static void add_ftrace_ops(struct ftrace_ops __rcu **list,
+			   struct ftrace_ops *ops)
 {
-	ops->next = *list;
+	rcu_assign_pointer(ops->next, *list);
+
 	/*
 	 * We are entering ops into the list but another
 	 * CPU might be walking that list. We need to make sure
@@ -360,15 +367,19 @@ static void add_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops)
 	rcu_assign_pointer(*list, ops);
 }
 
-static int remove_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops)
+static int remove_ftrace_ops(struct ftrace_ops __rcu **list,
+			     struct ftrace_ops *ops)
 {
 	struct ftrace_ops **p;
 
 	/*
 	 * If we are removing the last function, then simply point
 	 * to the ftrace_stub.
 	 */
-	if (*list == ops && ops->next == &ftrace_list_end) {
+	if (rcu_dereference_protected(*list,
+			lockdep_is_held(&ftrace_lock)) == ops &&
+	    rcu_dereference_protected(ops->next,
+			lockdep_is_held(&ftrace_lock)) == &ftrace_list_end) {
 		*list = &ftrace_list_end;
 		return 0;
 	}
@@ -1569,8 +1580,8 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs)
 		return 0;
 #endif
 
-	hash.filter_hash = rcu_dereference_raw_notrace(ops->func_hash->filter_hash);
-	hash.notrace_hash = rcu_dereference_raw_notrace(ops->func_hash->notrace_hash);
+	rcu_assign_pointer(hash.filter_hash, ops->func_hash->filter_hash);
+	rcu_assign_pointer(hash.notrace_hash, ops->func_hash->notrace_hash);
 
 	if (hash_contains_ip(ip, &hash))
 		ret = 1;
@@ -2840,7 +2851,8 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command)
 	 * If there's no more ops registered with ftrace, run a
 	 * sanity check to make sure all rec flags are cleared.
 	 */
-	if (ftrace_ops_list == &ftrace_list_end) {
+	if (rcu_dereference_protected(ftrace_ops_list,
+			lockdep_is_held(&ftrace_lock)) == &ftrace_list_end) {
 		struct ftrace_page *pg;
 		struct dyn_ftrace *rec;
 
@@ -6453,7 +6465,8 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
 	if (ftrace_enabled) {
 
 		/* we are starting ftrace again */
-		if (ftrace_ops_list != &ftrace_list_end)
+		if (rcu_dereference_protected(ftrace_ops_list,
+			lockdep_is_held(&ftrace_lock)) != &ftrace_list_end)
 			update_ftrace_function();
 
 		ftrace_startup_sysctl();

kernel/trace/ring_buffer.c

@@ -1136,20 +1136,20 @@ static int __rb_allocate_pages(long nr_pages, struct list_head *pages, int cpu)
 	for (i = 0; i < nr_pages; i++) {
 		struct page *page;
 		/*
-		 * __GFP_NORETRY flag makes sure that the allocation fails
-		 * gracefully without invoking oom-killer and the system is
-		 * not destabilized.
+		 * __GFP_RETRY_MAYFAIL flag makes sure that the allocation fails
+		 * gracefully without invoking oom-killer and the system is not
+		 * destabilized.
 		 */
 		bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()),
-				    GFP_KERNEL | __GFP_NORETRY,
+				    GFP_KERNEL | __GFP_RETRY_MAYFAIL,
 				    cpu_to_node(cpu));
 		if (!bpage)
 			goto free_pages;
 
 		list_add(&bpage->list, pages);
 
 		page = alloc_pages_node(cpu_to_node(cpu),
-					GFP_KERNEL | __GFP_NORETRY, 0);
+					GFP_KERNEL | __GFP_RETRY_MAYFAIL, 0);
 		if (!page)
 			goto free_pages;
 		bpage->page = page_address(page);

kernel/trace/trace.c

@@ -7774,6 +7774,7 @@ static int instance_rmdir(const char *name)
 	}
 	kfree(tr->topts);
 
+	free_cpumask_var(tr->tracing_cpumask);
 	kfree(tr->name);
 	kfree(tr);
 

kernel/trace/trace.h

@@ -1210,9 +1210,9 @@ struct ftrace_event_field {
 struct event_filter {
 	int			n_preds;	/* Number assigned */
 	int			a_preds;	/* allocated */
-	struct filter_pred	*preds;
-	struct filter_pred	*root;
-	char			*filter_string;
+	struct filter_pred __rcu	*preds;
+	struct filter_pred __rcu	*root;
+	char				*filter_string;
 };
 
 struct event_subsystem {