Merge tag 'trace-v6.7-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace

Pull tracing fixes from Steven Rostedt:

 - Fix readers that are blocked on the ring buffer when buffer_percent
   is 100%. They are supposed to wake up when the buffer is full, but
   because the sub-buffer that the writer is on is never considered
   "dirty" in the calculation, dirty pages will never equal nr_pages.
   Add +1 to the dirty count in order to count for the sub-buffer that
   the writer is on.

 - When a reader is blocked on the "snapshot_raw" file, it is to be
   woken up when a snapshot is done and be able to read the snapshot
   buffer. But because the snapshot swaps the buffers (the main one with
   the snapshot one), and the snapshot reader is waiting on the old
   snapshot buffer, it was not woken up (because it is now on the main
   buffer after the swap). Worse yet, when it reads the buffer after a
   snapshot, it's not reading the snapshot buffer, it's reading the live
   active main buffer.

   Fix this by forcing a wakeup of all readers on the snapshot buffer
   when a new snapshot happens, and then update the buffer that the
   reader is reading to be back on the snapshot buffer.

 - Fix the modification of the direct_function hash. There was a race
   when new functions were added to the direct_function hash as when it
   moved function entries from the old hash to the new one, a direct
   function trace could be hit and not see its entry.

   This is fixed by allocating the new hash, copy all the old entries
   onto it as well as the new entries, and then use rcu_assign_pointer()
   to update the new direct_function hash with it.

   This also fixes a memory leak in that code.

 - Fix eventfs ownership

* tag 'trace-v6.7-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ftrace: Fix modification of direct_function hash while in use
  tracing: Fix blocked reader of snapshot buffer
  ring-buffer: Fix wake ups when buffer_percent is set to 100
  eventfs: Fix file and directory uid and gid ownership

3 files changed, 103 insertions, 10 deletions

diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c
index 2ccc849a5bda..f0677ea0ec24 100644
--- a/fs/tracefs/event_inode.c
+++ b/fs/tracefs/event_inode.c
@@ -113,7 +113,14 @@ static int eventfs_set_attr(struct mnt_idmap *idmap, struct dentry *dentry,
 	 * determined by the parent directory.
 	 */
 	if (dentry->d_inode->i_mode & S_IFDIR) {
-		update_attr(&ei->attr, iattr);
+		/*
+		 * The events directory dentry is never freed, unless its
+		 * part of an instance that is deleted. It's attr is the
+		 * default for its child files and directories.
+		 * Do not update it. It's not used for its own mode or ownership
+		 */
+		if (!ei->is_events)
+			update_attr(&ei->attr, iattr);
 
 	} else {
 		name = dentry->d_name.name;
@@ -148,28 +155,93 @@ static const struct file_operations eventfs_file_operations = {
 	.release	= eventfs_release,
 };
 
+/* Return the evenfs_inode of the "events" directory */
+static struct eventfs_inode *eventfs_find_events(struct dentry *dentry)
+{
+	struct eventfs_inode *ei;
+
+	mutex_lock(&eventfs_mutex);
+	do {
+		/* The parent always has an ei, except for events itself */
+		ei = dentry->d_parent->d_fsdata;
+
+		/*
+		 * If the ei is being freed, the ownership of the children
+		 * doesn't matter.
+		 */
+		if (ei->is_freed) {
+			ei = NULL;
+			break;
+		}
+
+		dentry = ei->dentry;
+	} while (!ei->is_events);
+	mutex_unlock(&eventfs_mutex);
+
+	return ei;
+}
+
 static void update_inode_attr(struct dentry *dentry, struct inode *inode,
 			      struct eventfs_attr *attr, umode_t mode)
 {
-	if (!attr) {
-		inode->i_mode = mode;
+	struct eventfs_inode *events_ei = eventfs_find_events(dentry);
+
+	if (!events_ei)
+		return;
+
+	inode->i_mode = mode;
+	inode->i_uid = events_ei->attr.uid;
+	inode->i_gid = events_ei->attr.gid;
+
+	if (!attr)
 		return;
-	}
 
 	if (attr->mode & EVENTFS_SAVE_MODE)
 		inode->i_mode = attr->mode & EVENTFS_MODE_MASK;
-	else
-		inode->i_mode = mode;
 
 	if (attr->mode & EVENTFS_SAVE_UID)
 		inode->i_uid = attr->uid;
-	else
-		inode->i_uid = d_inode(dentry->d_parent)->i_uid;
 
 	if (attr->mode & EVENTFS_SAVE_GID)
 		inode->i_gid = attr->gid;
-	else
-		inode->i_gid = d_inode(dentry->d_parent)->i_gid;
+}
+
+static void update_gid(struct eventfs_inode *ei, kgid_t gid, int level)
+{
+	struct eventfs_inode *ei_child;
+
+	/* at most we have events/system/event */
+	if (WARN_ON_ONCE(level > 3))
+		return;
+
+	ei->attr.gid = gid;
+
+	if (ei->entry_attrs) {
+		for (int i = 0; i < ei->nr_entries; i++) {
+			ei->entry_attrs[i].gid = gid;
+		}
+	}
+
+	/*
+	 * Only eventfs_inode with dentries are updated, make sure
+	 * all eventfs_inodes are updated. If one of the children
+	 * do not have a dentry, this function must traverse it.
+	 */
+	list_for_each_entry_srcu(ei_child, &ei->children, list,
+				 srcu_read_lock_held(&eventfs_srcu)) {
+		if (!ei_child->dentry)
+			update_gid(ei_child, gid, level + 1);
+	}
+}
+
+void eventfs_update_gid(struct dentry *dentry, kgid_t gid)
+{
+	struct eventfs_inode *ei = dentry->d_fsdata;
+	int idx;
+
+	idx = srcu_read_lock(&eventfs_srcu);
+	update_gid(ei, gid, 0);
+	srcu_read_unlock(&eventfs_srcu, idx);
 }
 
 /**
@@ -860,6 +932,8 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry
 	struct eventfs_inode *ei;
 	struct tracefs_inode *ti;
 	struct inode *inode;
+	kuid_t uid;
+	kgid_t gid;
 
 	if (security_locked_down(LOCKDOWN_TRACEFS))
 		return NULL;
@@ -884,11 +958,20 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry
 	ei->dentry = dentry;
 	ei->entries = entries;
 	ei->nr_entries = size;
+	ei->is_events = 1;
 	ei->data = data;
 	ei->name = kstrdup_const(name, GFP_KERNEL);
 	if (!ei->name)
 		goto fail;
 
+	/* Save the ownership of this directory */
+	uid = d_inode(dentry->d_parent)->i_uid;
+	gid = d_inode(dentry->d_parent)->i_gid;
+
+	/* This is used as the default ownership of the files and directories */
+	ei->attr.uid = uid;
+	ei->attr.gid = gid;
+
 	INIT_LIST_HEAD(&ei->children);
 	INIT_LIST_HEAD(&ei->list);
 
@@ -897,6 +980,8 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry
 	ti->private = ei;
 
 	inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO;
+	inode->i_uid = uid;
+	inode->i_gid = gid;
 	inode->i_op = &eventfs_root_dir_inode_operations;
 	inode->i_fop = &eventfs_file_operations;
 
diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c
index ae648deed019..62524b20964e 100644
--- a/fs/tracefs/inode.c
+++ b/fs/tracefs/inode.c
@@ -210,6 +210,7 @@ repeat:
 	next = this_parent->d_subdirs.next;
 resume:
 	while (next != &this_parent->d_subdirs) {
+		struct tracefs_inode *ti;
 		struct list_head *tmp = next;
 		struct dentry *dentry = list_entry(tmp, struct dentry, d_child);
 		next = tmp->next;
@@ -218,6 +219,11 @@ resume:
 
 		change_gid(dentry, gid);
 
+		/* If this is the events directory, update that too */
+		ti = get_tracefs(dentry->d_inode);
+		if (ti && (ti->flags & TRACEFS_EVENT_INODE))
+			eventfs_update_gid(dentry, gid);
+
 		if (!list_empty(&dentry->d_subdirs)) {
 			spin_unlock(&this_parent->d_lock);
 			spin_release(&dentry->d_lock.dep_map, _RET_IP_);
diff --git a/fs/tracefs/internal.h b/fs/tracefs/internal.h
index ccee18ca66c7..899e447778ac 100644
--- a/fs/tracefs/internal.h
+++ b/fs/tracefs/internal.h
@@ -62,6 +62,7 @@ struct eventfs_inode {
 		struct rcu_head		rcu;
 	};
 	unsigned int			is_freed:1;
+	unsigned int			is_events:1;
 	unsigned int			nr_entries:31;
 };
 
@@ -77,6 +78,7 @@ struct inode *tracefs_get_inode(struct super_block *sb);
 struct dentry *eventfs_start_creating(const char *name, struct dentry *parent);
 struct dentry *eventfs_failed_creating(struct dentry *dentry);
 struct dentry *eventfs_end_creating(struct dentry *dentry);
+void eventfs_update_gid(struct dentry *dentry, kgid_t gid);
 void eventfs_set_ei_status_free(struct tracefs_inode *ti, struct dentry *dentry);
 
 #endif /* _TRACEFS_INTERNAL_H */