Merge tag 'trace-v6.8-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace

Pull tracing and eventfs fixes from Steven Rostedt:

 - Fix the return code for ring_buffer_poll_wait()

   It was returing a -EINVAL instead of EPOLLERR.

 - Zero out the tracefs_inode so that all fields are initialized.

   The ti->private could have had stale data, but instead of just
   initializing it to NULL, clear out the entire structure when it is
   allocated.

 - Fix a crash in timerlat

   The hrtimer was initialized at read and not open, but is canceled at
   close. If the file was opened and never read the close will pass a
   NULL pointer to hrtime_cancel().

 - Rewrite of eventfs.

   Linus wrote a patch series to remove the dentry references in the
   eventfs_inode and to use ref counting and more of proper VFS
   interfaces to make it work.

 - Add warning to put_ei() if ei is not set to free. That means
   something is about to free it when it shouldn't.

 - Restructure the eventfs_inode to make it more compact, and remove the
   unused llist field.

 - Remove the fsnotify*() funtions for when the inodes were being
   created in the lookup code. It doesn't make sense to notify about
   creation just because something is being looked up.

 - The inode hard link count was not accurate.

   It was being updated when a file was looked up. The inodes of
   directories were updating their parent inode hard link count every
   time the inode was created. That means if memory reclaim cleaned a
   stale directory inode and the inode was lookup up again, it would
   increment the parent inode again as well. Al Viro said to just have
   all eventfs directories have a hard link count of 1. That tells user
   space not to trust it.

* tag 'trace-v6.8-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  eventfs: Keep all directory links at 1
  eventfs: Remove fsnotify*() functions from lookup()
  eventfs: Restructure eventfs_inode structure to be more condensed
  eventfs: Warn if an eventfs_inode is freed without is_freed being set
  tracing/timerlat: Move hrtimer_init to timerlat_fd open()
  eventfs: Get rid of dentry pointers without refcounts
  eventfs: Clean up dentry ops and add revalidate function
  eventfs: Remove unused d_parent pointer field
  tracefs: dentry lookup crapectomy
  tracefs: Avoid using the ei->dentry pointer unnecessarily
  eventfs: Initialize the tracefs inode properly
  tracefs: Zero out the tracefs_inode when allocating it
  ring-buffer: Clean ring_buffer_poll_wait() error return

fs/tracefs/inode.c

@@ -38,8 +38,6 @@ static struct inode *tracefs_alloc_inode(struct super_block *sb)
 	if (!ti)
 		return NULL;
 
-	ti->flags = 0;
-
 	return &ti->vfs_inode;
 }
 
@@ -379,21 +377,30 @@ static const struct super_operations tracefs_super_operations = {
 	.show_options	= tracefs_show_options,
 };
 
-static void tracefs_dentry_iput(struct dentry *dentry, struct inode *inode)
+/*
+ * It would be cleaner if eventfs had its own dentry ops.
+ *
+ * Note that d_revalidate is called potentially under RCU,
+ * so it can't take the eventfs mutex etc. It's fine - if
+ * we open a file just as it's marked dead, things will
+ * still work just fine, and just see the old stale case.
+ */
+static void tracefs_d_release(struct dentry *dentry)
 {
-	struct tracefs_inode *ti;
+	if (dentry->d_fsdata)
+		eventfs_d_release(dentry);
+}
 
-	if (!dentry || !inode)
-		return;
+static int tracefs_d_revalidate(struct dentry *dentry, unsigned int flags)
+{
+	struct eventfs_inode *ei = dentry->d_fsdata;
 
-	ti = get_tracefs(inode);
-	if (ti && ti->flags & TRACEFS_EVENT_INODE)
-		eventfs_set_ei_status_free(ti, dentry);
-	iput(inode);
+	return !(ei && ei->is_freed);
 }
 
 static const struct dentry_operations tracefs_dentry_operations = {
-	.d_iput = tracefs_dentry_iput,
+	.d_revalidate = tracefs_d_revalidate,
+	.d_release = tracefs_d_release,
 };
 
 static int trace_fill_super(struct super_block *sb, void *data, int silent)
@@ -497,75 +504,6 @@ struct dentry *tracefs_end_creating(struct dentry *dentry)
 	return dentry;
 }
 
-/**
- * eventfs_start_creating - start the process of creating a dentry
- * @name: Name of the file created for the dentry
- * @parent: The parent dentry where this dentry will be created
- *
- * This is a simple helper function for the dynamically created eventfs
- * files. When the directory of the eventfs files are accessed, their
- * dentries are created on the fly. This function is used to start that
- * process.
- */
-struct dentry *eventfs_start_creating(const char *name, struct dentry *parent)
-{
-	struct dentry *dentry;
-	int error;
-
-	/* Must always have a parent. */
-	if (WARN_ON_ONCE(!parent))
-		return ERR_PTR(-EINVAL);
-
-	error = simple_pin_fs(&trace_fs_type, &tracefs_mount,
-			      &tracefs_mount_count);
-	if (error)
-		return ERR_PTR(error);
-
-	if (unlikely(IS_DEADDIR(parent->d_inode)))
-		dentry = ERR_PTR(-ENOENT);
-	else
-		dentry = lookup_one_len(name, parent, strlen(name));
-
-	if (!IS_ERR(dentry) && dentry->d_inode) {
-		dput(dentry);
-		dentry = ERR_PTR(-EEXIST);
-	}
-
-	if (IS_ERR(dentry))
-		simple_release_fs(&tracefs_mount, &tracefs_mount_count);
-
-	return dentry;
-}
-
-/**
- * eventfs_failed_creating - clean up a failed eventfs dentry creation
- * @dentry: The dentry to clean up
- *
- * If after calling eventfs_start_creating(), a failure is detected, the
- * resources created by eventfs_start_creating() needs to be cleaned up. In
- * that case, this function should be called to perform that clean up.
- */
-struct dentry *eventfs_failed_creating(struct dentry *dentry)
-{
-	dput(dentry);
-	simple_release_fs(&tracefs_mount, &tracefs_mount_count);
-	return NULL;
-}
-
-/**
- * eventfs_end_creating - Finish the process of creating a eventfs dentry
- * @dentry: The dentry that has successfully been created.
- *
- * This function is currently just a place holder to match
- * eventfs_start_creating(). In case any synchronization needs to be added,
- * this function will be used to implement that without having to modify
- * the callers of eventfs_start_creating().
- */
-struct dentry *eventfs_end_creating(struct dentry *dentry)
-{
-	return dentry;
-}
-
 /* Find the inode that this will use for default */
 static struct inode *instance_inode(struct dentry *parent, struct inode *inode)
 {
@@ -779,7 +717,11 @@ static void init_once(void *foo)
 {
 	struct tracefs_inode *ti = (struct tracefs_inode *) foo;
 
+	/* inode_init_once() calls memset() on the vfs_inode portion */
 	inode_init_once(&ti->vfs_inode);
+
+	/* Zero out the rest */
+	memset_after(ti, 0, vfs_inode);
 }
 
 static int __init tracefs_init(void)

fs/tracefs/internal.h

@@ -11,9 +11,10 @@ enum {
 };
 
 struct tracefs_inode {
+	struct inode            vfs_inode;
+	/* The below gets initialized with memset_after(ti, 0, vfs_inode) */
 	unsigned long           flags;
 	void                    *private;
-	struct inode            vfs_inode;
 };
 
 /*
@@ -31,43 +32,37 @@ struct eventfs_attr {
 /*
  * struct eventfs_inode - hold the properties of the eventfs directories.
  * @list:	link list into the parent directory
+ * @rcu:	Union with @list for freeing
+ * @children:	link list into the child eventfs_inode
  * @entries:	the array of entries representing the files in the directory
  * @name:	the name of the directory to create
- * @children:	link list into the child eventfs_inode
- * @dentry:     the dentry of the directory
- * @d_parent:   pointer to the parent's dentry
- * @d_children: The array of dentries to represent the files when created
+ * @events_dir: the dentry of the events directory
  * @entry_attrs: Saved mode and ownership of the @d_children
- * @attr:	Saved mode and ownership of eventfs_inode itself
  * @data:	The private data to pass to the callbacks
+ * @attr:	Saved mode and ownership of eventfs_inode itself
  * @is_freed:	Flag set if the eventfs is on its way to be freed
  *                Note if is_freed is set, then dentry is corrupted.
+ * @is_events:	Flag set for only the top level "events" directory
  * @nr_entries: The number of items in @entries
+ * @ino:	The saved inode number
  */
 struct eventfs_inode {
-	struct list_head		list;
+	union {
+		struct list_head	list;
+		struct rcu_head		rcu;
+	};
+	struct list_head		children;
 	const struct eventfs_entry	*entries;
 	const char			*name;
-	struct list_head		children;
-	struct dentry			*dentry; /* Check is_freed to access */
-	struct dentry			*d_parent;
-	struct dentry			**d_children;
+	struct dentry			*events_dir;
 	struct eventfs_attr		*entry_attrs;
-	struct eventfs_attr		attr;
 	void				*data;
+	struct eventfs_attr		attr;
+	struct kref			kref;
 	unsigned int			is_freed:1;
 	unsigned int			is_events:1;
 	unsigned int			nr_entries:30;
 	unsigned int			ino;
-	/*
-	 * Union - used for deletion
-	 * @llist:	for calling dput() if needed after RCU
-	 * @rcu:	eventfs_inode to delete in RCU
-	 */
-	union {
-		struct llist_node	llist;
-		struct rcu_head		rcu;
-	};
 };
 
 static inline struct tracefs_inode *get_tracefs(const struct inode *inode)
@@ -79,9 +74,7 @@ struct dentry *tracefs_start_creating(const char *name, struct dentry *parent);
 struct dentry *tracefs_end_creating(struct dentry *dentry);
 struct dentry *tracefs_failed_creating(struct dentry *dentry);
 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_set_ei_status_free(struct tracefs_inode *ti, struct dentry *dentry);
+
+void eventfs_d_release(struct dentry *dentry);
 
 #endif /* _TRACEFS_INTERNAL_H */

kernel/trace/ring_buffer.c

@@ -944,7 +944,7 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu,
 		full = 0;
 	} else {
 		if (!cpumask_test_cpu(cpu, buffer->cpumask))
-			return -EINVAL;
+			return EPOLLERR;
 
 		cpu_buffer = buffer->buffers[cpu];
 		work = &cpu_buffer->irq_work;

kernel/trace/trace_osnoise.c

@@ -2444,6 +2444,9 @@ static int timerlat_fd_open(struct inode *inode, struct file *file)
 	tlat = this_cpu_tmr_var();
 	tlat->count = 0;
 
+	hrtimer_init(&tlat->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED_HARD);
+	tlat->timer.function = timerlat_irq;
+
 	migrate_enable();
 	return 0;
 };
@@ -2526,9 +2529,6 @@ timerlat_fd_read(struct file *file, char __user *ubuf, size_t count,
 		tlat->tracing_thread = false;
 		tlat->kthread = current;
 
-		hrtimer_init(&tlat->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED_HARD);
-		tlat->timer.function = timerlat_irq;
-
 		/* Annotate now to drift new period */
 		tlat->abs_period = hrtimer_cb_get_time(&tlat->timer);