Merge tag 'trace-v6.11-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace

Pull tracing fixes from Steven Rostedt:

 - Have reading of event format files test if the metadata still exists.

   When a event is freed, a flag (EVENT_FILE_FL_FREED) in the metadata
   is set to state that it is to prevent any new references to it from
   happening while waiting for existing references to close. When the
   last reference closes, the metadata is freed. But the "format" was
   missing a check to this flag (along with some other files) that
   allowed new references to happen, and a use-after-free bug to occur.

 - Have the trace event meta data use the refcount infrastructure
   instead of relying on its own atomic counters.

 - Have tracefs inodes use alloc_inode_sb() for allocation instead of
   using kmem_cache_alloc() directly.

 - Have eventfs_create_dir() return an ERR_PTR instead of NULL as the
   callers expect a real object or an ERR_PTR.

 - Have release_ei() use call_srcu() and not call_rcu() as all the
   protection is on SRCU and not RCU.

 - Fix ftrace_graph_ret_addr() to use the task passed in and not
   current.

 - Fix overflow bug in get_free_elt() where the counter can overflow the
   integer and cause an infinite loop.

 - Remove unused function ring_buffer_nr_pages()

 - Have tracefs freeing use the inode RCU infrastructure instead of
   creating its own.

   When the kernel had randomize structure fields enabled, the rcu field
   of the tracefs_inode was overlapping the rcu field of the inode
   structure, and corrupting it. Instead, use the destroy_inode()
   callback to do the initial cleanup of the code, and then have
   free_inode() free it.

* tag 'trace-v6.11-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  tracefs: Use generic inode RCU for synchronizing freeing
  ring-buffer: Remove unused function ring_buffer_nr_pages()
  tracing: Fix overflow in get_free_elt()
  function_graph: Fix the ret_stack used by ftrace_graph_ret_addr()
  eventfs: Use SRCU for freeing eventfs_inodes
  eventfs: Don't return NULL in eventfs_create_dir()
  tracefs: Fix inode allocation
  tracing: Use refcount for trace_event_file reference counter
  tracing: Have format file honor EVENT_FILE_FL_FREED

8 files changed, 57 insertions, 39 deletions

diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index fc205ad167a9..d1d5ea2d0a1b 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -902,7 +902,7 @@ unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx,
 
 	i = *idx ? : task->curr_ret_stack;
 	while (i > 0) {
-		ret_stack = get_ret_stack(current, i, &i);
+		ret_stack = get_ret_stack(task, i, &i);
 		if (!ret_stack)
 			break;
 		/*
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 28853966aa9a..cebd879a30cb 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -693,18 +693,6 @@ u64 ring_buffer_event_time_stamp(struct trace_buffer *buffer,
 }
 
 /**
- * ring_buffer_nr_pages - get the number of buffer pages in the ring buffer
- * @buffer: The ring_buffer to get the number of pages from
- * @cpu: The cpu of the ring_buffer to get the number of pages from
- *
- * Returns the number of pages used by a per_cpu buffer of the ring buffer.
- */
-size_t ring_buffer_nr_pages(struct trace_buffer *buffer, int cpu)
-{
-	return buffer->buffers[cpu]->nr_pages;
-}
-
-/**
  * ring_buffer_nr_dirty_pages - get the number of used pages in the ring buffer
  * @buffer: The ring_buffer to get the number of pages from
  * @cpu: The cpu of the ring_buffer to get the number of pages from
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 8783bebd0562..bd3e3069300e 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1634,6 +1634,29 @@ static inline void *event_file_data(struct file *filp)
 extern struct mutex event_mutex;
 extern struct list_head ftrace_events;
 
+/*
+ * When the trace_event_file is the filp->i_private pointer,
+ * it must be taken under the event_mutex lock, and then checked
+ * if the EVENT_FILE_FL_FREED flag is set. If it is, then the
+ * data pointed to by the trace_event_file can not be trusted.
+ *
+ * Use the event_file_file() to access the trace_event_file from
+ * the filp the first time under the event_mutex and check for
+ * NULL. If it is needed to be retrieved again and the event_mutex
+ * is still held, then the event_file_data() can be used and it
+ * is guaranteed to be valid.
+ */
+static inline struct trace_event_file *event_file_file(struct file *filp)
+{
+	struct trace_event_file *file;
+
+	lockdep_assert_held(&event_mutex);
+	file = READ_ONCE(file_inode(filp)->i_private);
+	if (!file || file->flags & EVENT_FILE_FL_FREED)
+		return NULL;
+	return file;
+}
+
 extern const struct file_operations event_trigger_fops;
 extern const struct file_operations event_hist_fops;
 extern const struct file_operations event_hist_debug_fops;
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 6ef29eba90ce..7266ec2a4eea 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -992,18 +992,18 @@ static void remove_subsystem(struct trace_subsystem_dir *dir)
 
 void event_file_get(struct trace_event_file *file)
 {
-	atomic_inc(&file->ref);
+	refcount_inc(&file->ref);
 }
 
 void event_file_put(struct trace_event_file *file)
 {
-	if (WARN_ON_ONCE(!atomic_read(&file->ref))) {
+	if (WARN_ON_ONCE(!refcount_read(&file->ref))) {
 		if (file->flags & EVENT_FILE_FL_FREED)
 			kmem_cache_free(file_cachep, file);
 		return;
 	}
 
-	if (atomic_dec_and_test(&file->ref)) {
+	if (refcount_dec_and_test(&file->ref)) {
 		/* Count should only go to zero when it is freed */
 		if (WARN_ON_ONCE(!(file->flags & EVENT_FILE_FL_FREED)))
 			return;
@@ -1386,12 +1386,12 @@ event_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
 	char buf[4] = "0";
 
 	mutex_lock(&event_mutex);
-	file = event_file_data(filp);
+	file = event_file_file(filp);
 	if (likely(file))
 		flags = file->flags;
 	mutex_unlock(&event_mutex);
 
-	if (!file || flags & EVENT_FILE_FL_FREED)
+	if (!file)
 		return -ENODEV;
 
 	if (flags & EVENT_FILE_FL_ENABLED &&
@@ -1424,8 +1424,8 @@ event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
 	case 1:
 		ret = -ENODEV;
 		mutex_lock(&event_mutex);
-		file = event_file_data(filp);
-		if (likely(file && !(file->flags & EVENT_FILE_FL_FREED))) {
+		file = event_file_file(filp);
+		if (likely(file)) {
 			ret = tracing_update_buffers(file->tr);
 			if (ret < 0) {
 				mutex_unlock(&event_mutex);
@@ -1540,7 +1540,8 @@ enum {
 
 static void *f_next(struct seq_file *m, void *v, loff_t *pos)
 {
-	struct trace_event_call *call = event_file_data(m->private);
+	struct trace_event_file *file = event_file_data(m->private);
+	struct trace_event_call *call = file->event_call;
 	struct list_head *common_head = &ftrace_common_fields;
 	struct list_head *head = trace_get_fields(call);
 	struct list_head *node = v;
@@ -1572,7 +1573,8 @@ static void *f_next(struct seq_file *m, void *v, loff_t *pos)
 
 static int f_show(struct seq_file *m, void *v)
 {
-	struct trace_event_call *call = event_file_data(m->private);
+	struct trace_event_file *file = event_file_data(m->private);
+	struct trace_event_call *call = file->event_call;
 	struct ftrace_event_field *field;
 	const char *array_descriptor;
 
@@ -1627,12 +1629,14 @@ static int f_show(struct seq_file *m, void *v)
 
 static void *f_start(struct seq_file *m, loff_t *pos)
 {
+	struct trace_event_file *file;
 	void *p = (void *)FORMAT_HEADER;
 	loff_t l = 0;
 
 	/* ->stop() is called even if ->start() fails */
 	mutex_lock(&event_mutex);
-	if (!event_file_data(m->private))
+	file = event_file_file(m->private);
+	if (!file)
 		return ERR_PTR(-ENODEV);
 
 	while (l < *pos && p)
@@ -1706,8 +1710,8 @@ event_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
 	trace_seq_init(s);
 
 	mutex_lock(&event_mutex);
-	file = event_file_data(filp);
-	if (file && !(file->flags & EVENT_FILE_FL_FREED))
+	file = event_file_file(filp);
+	if (file)
 		print_event_filter(file, s);
 	mutex_unlock(&event_mutex);
 
@@ -1736,9 +1740,13 @@ event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
 		return PTR_ERR(buf);
 
 	mutex_lock(&event_mutex);
-	file = event_file_data(filp);
-	if (file)
-		err = apply_event_filter(file, buf);
+	file = event_file_file(filp);
+	if (file) {
+		if (file->flags & EVENT_FILE_FL_FREED)
+			err = -ENODEV;
+		else
+			err = apply_event_filter(file, buf);
+	}
 	mutex_unlock(&event_mutex);
 
 	kfree(buf);
@@ -2485,7 +2493,6 @@ static int event_callback(const char *name, umode_t *mode, void **data,
 	if (strcmp(name, "format") == 0) {
 		*mode = TRACE_MODE_READ;
 		*fops = &ftrace_event_format_fops;
-		*data = call;
 		return 1;
 	}
 
@@ -2996,7 +3003,7 @@ trace_create_new_event(struct trace_event_call *call,
 	atomic_set(&file->tm_ref, 0);
 	INIT_LIST_HEAD(&file->triggers);
 	list_add(&file->list, &tr->events);
-	event_file_get(file);
+	refcount_set(&file->ref, 1);
 
 	return file;
 }
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 6ece1308d36a..5f9119eb7c67 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -5601,7 +5601,7 @@ static int hist_show(struct seq_file *m, void *v)
 
 	mutex_lock(&event_mutex);
 
-	event_file = event_file_data(m->private);
+	event_file = event_file_file(m->private);
 	if (unlikely(!event_file)) {
 		ret = -ENODEV;
 		goto out_unlock;
@@ -5880,7 +5880,7 @@ static int hist_debug_show(struct seq_file *m, void *v)
 
 	mutex_lock(&event_mutex);
 
-	event_file = event_file_data(m->private);
+	event_file = event_file_file(m->private);
 	if (unlikely(!event_file)) {
 		ret = -ENODEV;
 		goto out_unlock;
diff --git a/kernel/trace/trace_events_inject.c b/kernel/trace/trace_events_inject.c
index 8650562bdaa9..a8f076809db4 100644
--- a/kernel/trace/trace_events_inject.c
+++ b/kernel/trace/trace_events_inject.c
@@ -299,7 +299,7 @@ event_inject_write(struct file *filp, const char __user *ubuf, size_t cnt,
 	strim(buf);
 
 	mutex_lock(&event_mutex);
-	file = event_file_data(filp);
+	file = event_file_file(filp);
 	if (file) {
 		call = file->event_call;
 		size = parse_entry(buf, call, &entry);
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 4bec043c8690..a5e3d6acf1e1 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -159,7 +159,7 @@ static void *trigger_start(struct seq_file *m, loff_t *pos)
 
 	/* ->stop() is called even if ->start() fails */
 	mutex_lock(&event_mutex);
-	event_file = event_file_data(m->private);
+	event_file = event_file_file(m->private);
 	if (unlikely(!event_file))
 		return ERR_PTR(-ENODEV);
 
@@ -213,7 +213,7 @@ static int event_trigger_regex_open(struct inode *inode, struct file *file)
 
 	mutex_lock(&event_mutex);
 
-	if (unlikely(!event_file_data(file))) {
+	if (unlikely(!event_file_file(file))) {
 		mutex_unlock(&event_mutex);
 		return -ENODEV;
 	}
@@ -293,7 +293,7 @@ static ssize_t event_trigger_regex_write(struct file *file,
 	strim(buf);
 
 	mutex_lock(&event_mutex);
-	event_file = event_file_data(file);
+	event_file = event_file_file(file);
 	if (unlikely(!event_file)) {
 		mutex_unlock(&event_mutex);
 		kfree(buf);
diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c
index a4dcf0f24352..3a56e7c8aa4f 100644
--- a/kernel/trace/tracing_map.c
+++ b/kernel/trace/tracing_map.c
@@ -454,7 +454,7 @@ static struct tracing_map_elt *get_free_elt(struct tracing_map *map)
 	struct tracing_map_elt *elt = NULL;
 	int idx;
 
-	idx = atomic_inc_return(&map->next_elt);
+	idx = atomic_fetch_add_unless(&map->next_elt, 1, map->max_elts);
 	if (idx < map->max_elts) {
 		elt = *(TRACING_MAP_ELT(map->elts, idx));
 		if (map->ops && map->ops->elt_init)
@@ -699,7 +699,7 @@ void tracing_map_clear(struct tracing_map *map)
 {
 	unsigned int i;
 
-	atomic_set(&map->next_elt, -1);
+	atomic_set(&map->next_elt, 0);
 	atomic64_set(&map->hits, 0);
 	atomic64_set(&map->drops, 0);
 
@@ -783,7 +783,7 @@ struct tracing_map *tracing_map_create(unsigned int map_bits,
 
 	map->map_bits = map_bits;
 	map->max_elts = (1 << map_bits);
-	atomic_set(&map->next_elt, -1);
+	atomic_set(&map->next_elt, 0);
 
 	map->map_size = (1 << (map_bits + 1));
 	map->ops = ops;