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

Pull tracing updates from Steven Rostedt:

 - Remove eventfs_file descriptor

   This is the biggest change, and the second part of making eventfs
   create its files dynamically.

   In 6.6 the first part was added, and that maintained a one to one
   mapping between eventfs meta descriptors and the directories and file
   inodes and dentries that were dynamically created. The directories
   were represented by a eventfs_inode and the files were represented by
   a eventfs_file.

   In v6.7 the eventfs_file is removed. As all events have the same
   directory make up (sched_switch has an "enable", "id", "format", etc
   files), the handing of what files are underneath each leaf eventfs
   directory is moved back to the tracing subsystem via a callback.

   When an event is added to the eventfs, it registers an array of
   evenfs_entry's. These hold the names of the files and the callbacks
   to call when the file is referenced. The callback gets the name so
   that the same callback may be used by multiple files. The callback
   then supplies the filesystem_operations structure needed to create
   this file.

   This has brought the memory footprint of creating multiple eventfs
   instances down by 2 megs each!

 - User events now has persistent events that are not associated to a
   single processes. These are privileged events that hang around even
   if no process is attached to them

 - Clean up of seq_buf

   There's talk about using seq_buf more to replace strscpy() and
   friends. But this also requires some minor modifications of seq_buf
   to be able to do this

 - Expand instance ring buffers individually

   Currently if boot up creates an instance, and a trace event is
   enabled on that instance, the ring buffer for that instance and the
   top level ring buffer are expanded (1.4 MB per CPU). This wastes
   memory as this happens when nothing is using the top level instance

 - Other minor clean ups and fixes

* tag 'trace-v6.7' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: (34 commits)
  seq_buf: Export seq_buf_puts()
  seq_buf: Export seq_buf_putc()
  eventfs: Use simple_recursive_removal() to clean up dentries
  eventfs: Remove special processing of dput() of events directory
  eventfs: Delete eventfs_inode when the last dentry is freed
  eventfs: Hold eventfs_mutex when calling callback functions
  eventfs: Save ownership and mode
  eventfs: Test for ei->is_freed when accessing ei->dentry
  eventfs: Have a free_ei() that just frees the eventfs_inode
  eventfs: Remove "is_freed" union with rcu head
  eventfs: Fix kerneldoc of eventfs_remove_rec()
  tracing: Have the user copy of synthetic event address use correct context
  eventfs: Remove extra dget() in eventfs_create_events_dir()
  tracing: Have trace_event_file have ref counters
  seq_buf: Introduce DECLARE_SEQ_BUF and seq_buf_str()
  eventfs: Fix typo in eventfs_inode union comment
  eventfs: Fix WARN_ON() in create_file_dentry()
  powerpc: Remove initialisation of readpos
  tracing/histograms: Simplify last_cmd_set()
  seq_buf: fix a misleading comment
  ...

5 files changed, 94 insertions, 26 deletions

diff --git a/include/linux/seq_buf.h b/include/linux/seq_buf.h
index 515d7fcb9634..5fb1f12c33f9 100644
--- a/include/linux/seq_buf.h
+++ b/include/linux/seq_buf.h
@@ -14,19 +14,25 @@
  * @buffer:	pointer to the buffer
  * @size:	size of the buffer
  * @len:	the amount of data inside the buffer
- * @readpos:	The next position to read in the buffer.
  */
 struct seq_buf {
 	char			*buffer;
 	size_t			size;
 	size_t			len;
-	loff_t			readpos;
 };
 
+#define DECLARE_SEQ_BUF(NAME, SIZE)			\
+	char __ ## NAME ## _buffer[SIZE] = "";		\
+	struct seq_buf NAME = {				\
+		.buffer = &__ ## NAME ## _buffer,	\
+		.size = SIZE,				\
+	}
+
 static inline void seq_buf_clear(struct seq_buf *s)
 {
 	s->len = 0;
-	s->readpos = 0;
+	if (s->size)
+		s->buffer[0] = '\0';
 }
 
 static inline void
@@ -39,7 +45,7 @@ seq_buf_init(struct seq_buf *s, char *buf, unsigned int size)
 
 /*
  * seq_buf have a buffer that might overflow. When this happens
- * the len and size are set to be equal.
+ * len is set to be greater than size.
  */
 static inline bool
 seq_buf_has_overflowed(struct seq_buf *s)
@@ -72,8 +78,8 @@ static inline unsigned int seq_buf_used(struct seq_buf *s)
 }
 
 /**
- * seq_buf_terminate - Make sure buffer is nul terminated
- * @s: the seq_buf descriptor to terminate.
+ * seq_buf_str - get %NUL-terminated C string from seq_buf
+ * @s: the seq_buf handle
  *
  * This makes sure that the buffer in @s is nul terminated and
  * safe to read as a string.
@@ -84,16 +90,20 @@ static inline unsigned int seq_buf_used(struct seq_buf *s)
  *
  * After this function is called, s->buffer is safe to use
  * in string operations.
+ *
+ * Returns @s->buf after making sure it is terminated.
  */
-static inline void seq_buf_terminate(struct seq_buf *s)
+static inline const char *seq_buf_str(struct seq_buf *s)
 {
 	if (WARN_ON(s->size == 0))
-		return;
+		return "";
 
 	if (seq_buf_buffer_left(s))
 		s->buffer[s->len] = 0;
 	else
 		s->buffer[s->size - 1] = 0;
+
+	return s->buffer;
 }
 
 /**
@@ -143,7 +153,7 @@ extern __printf(2, 0)
 int seq_buf_vprintf(struct seq_buf *s, const char *fmt, va_list args);
 extern int seq_buf_print_seq(struct seq_file *m, struct seq_buf *s);
 extern int seq_buf_to_user(struct seq_buf *s, char __user *ubuf,
-			   int cnt);
+			   size_t start, int cnt);
 extern int seq_buf_puts(struct seq_buf *s, const char *str);
 extern int seq_buf_putc(struct seq_buf *s, unsigned char c);
 extern int seq_buf_putmem(struct seq_buf *s, const void *mem, unsigned int len);
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 5eb88a66eb68..d68ff9b1247f 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -492,6 +492,7 @@ enum {
 	EVENT_FILE_FL_TRIGGER_COND_BIT,
 	EVENT_FILE_FL_PID_FILTER_BIT,
 	EVENT_FILE_FL_WAS_ENABLED_BIT,
+	EVENT_FILE_FL_FREED_BIT,
 };
 
 extern struct trace_event_file *trace_get_event_file(const char *instance,
@@ -630,6 +631,7 @@ extern int __kprobe_event_add_fields(struct dynevent_cmd *cmd, ...);
  *  TRIGGER_COND  - When set, one or more triggers has an associated filter
  *  PID_FILTER    - When set, the event is filtered based on pid
  *  WAS_ENABLED   - Set when enabled to know to clear trace on module removal
+ *  FREED         - File descriptor is freed, all fields should be considered invalid
  */
 enum {
 	EVENT_FILE_FL_ENABLED		= (1 << EVENT_FILE_FL_ENABLED_BIT),
@@ -643,13 +645,14 @@ enum {
 	EVENT_FILE_FL_TRIGGER_COND	= (1 << EVENT_FILE_FL_TRIGGER_COND_BIT),
 	EVENT_FILE_FL_PID_FILTER	= (1 << EVENT_FILE_FL_PID_FILTER_BIT),
 	EVENT_FILE_FL_WAS_ENABLED	= (1 << EVENT_FILE_FL_WAS_ENABLED_BIT),
+	EVENT_FILE_FL_FREED		= (1 << EVENT_FILE_FL_FREED_BIT),
 };
 
 struct trace_event_file {
 	struct list_head		list;
 	struct trace_event_call		*event_call;
 	struct event_filter __rcu	*filter;
-	struct eventfs_file             *ef;
+	struct eventfs_inode		*ei;
 	struct trace_array		*tr;
 	struct trace_subsystem_dir	*system;
 	struct list_head		triggers;
@@ -671,6 +674,7 @@ struct trace_event_file {
 	 * caching and such. Which is mostly OK ;-)
 	 */
 	unsigned long		flags;
+	atomic_t		ref;	/* ref count for opened files */
 	atomic_t		sm_ref;	/* soft-mode reference counter */
 	atomic_t		tm_ref;	/* trigger-mode reference counter */
 };
diff --git a/include/linux/trace_seq.h b/include/linux/trace_seq.h
index 6be92bf559fe..3691e0e76a1a 100644
--- a/include/linux/trace_seq.h
+++ b/include/linux/trace_seq.h
@@ -14,6 +14,7 @@
 struct trace_seq {
 	char			buffer[PAGE_SIZE];
 	struct seq_buf		seq;
+	size_t			readpos;
 	int			full;
 };
 
@@ -22,6 +23,7 @@ trace_seq_init(struct trace_seq *s)
 {
 	seq_buf_init(&s->seq, s->buffer, PAGE_SIZE);
 	s->full = 0;
+	s->readpos = 0;
 }
 
 /**
diff --git a/include/linux/tracefs.h b/include/linux/tracefs.h
index 009072792fa3..7a5fe17b6bf9 100644
--- a/include/linux/tracefs.h
+++ b/include/linux/tracefs.h
@@ -23,26 +23,69 @@ struct file_operations;
 
 struct eventfs_file;
 
-struct dentry *eventfs_create_events_dir(const char *name,
-					 struct dentry *parent);
-
-struct eventfs_file *eventfs_add_subsystem_dir(const char *name,
-					       struct dentry *parent);
+/**
+ * eventfs_callback - A callback function to create dynamic files in eventfs
+ * @name: The name of the file that is to be created
+ * @mode: return the file mode for the file (RW access, etc)
+ * @data: data to pass to the created file ops
+ * @fops: the file operations of the created file
+ *
+ * The evetnfs files are dynamically created. The struct eventfs_entry array
+ * is passed to eventfs_create_dir() or eventfs_create_events_dir() that will
+ * be used to create the files within those directories. When a lookup
+ * or access to a file within the directory is made, the struct eventfs_entry
+ * array is used to find a callback() with the matching name that is being
+ * referenced (for lookups, the entire array is iterated and each callback
+ * will be called).
+ *
+ * The callback will be called with @name for the name of the file to create.
+ * The callback can return less than 1 to indicate  that no file should be
+ * created.
+ *
+ * If a file is to be created, then @mode should be populated with the file
+ * mode (permissions) for which the file is created for. This would be
+ * used to set the created inode i_mode field.
+ *
+ * The @data should be set to the data passed to the other file operations
+ * (read, write, etc). Note, @data will also point to the data passed in
+ * to eventfs_create_dir() or eventfs_create_events_dir(), but the callback
+ * can replace the data if it chooses to. Otherwise, the original data
+ * will be used for the file operation functions.
+ *
+ * The @fops should be set to the file operations that will be used to create
+ * the inode.
+ *
+ * NB. This callback is called while holding internal locks of the eventfs
+ *     system. The callback must not call any code that might also call into
+ *     the tracefs or eventfs system or it will risk creating a deadlock.
+ */
+typedef int (*eventfs_callback)(const char *name, umode_t *mode, void **data,
+				const struct file_operations **fops);
 
-struct eventfs_file *eventfs_add_dir(const char *name,
-				     struct eventfs_file *ef_parent);
+/**
+ * struct eventfs_entry - dynamically created eventfs file call back handler
+ * @name:	Then name of the dynamic file in an eventfs directory
+ * @callback:	The callback to get the fops of the file when it is created
+ *
+ * See evenfs_callback() typedef for how to set up @callback.
+ */
+struct eventfs_entry {
+	const char			*name;
+	eventfs_callback		callback;
+};
 
-int eventfs_add_file(const char *name, umode_t mode,
-		     struct eventfs_file *ef_parent, void *data,
-		     const struct file_operations *fops);
+struct eventfs_inode;
 
-int eventfs_add_events_file(const char *name, umode_t mode,
-			 struct dentry *parent, void *data,
-			 const struct file_operations *fops);
+struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry *parent,
+						const struct eventfs_entry *entries,
+						int size, void *data);
 
-void eventfs_remove(struct eventfs_file *ef);
+struct eventfs_inode *eventfs_create_dir(const char *name, struct eventfs_inode *parent,
+					 const struct eventfs_entry *entries,
+					 int size, void *data);
 
-void eventfs_remove_events_dir(struct dentry *dentry);
+void eventfs_remove_events_dir(struct eventfs_inode *ei);
+void eventfs_remove_dir(struct eventfs_inode *ei);
 
 struct dentry *tracefs_create_file(const char *name, umode_t mode,
 				   struct dentry *parent, void *data,
diff --git a/include/uapi/linux/user_events.h b/include/uapi/linux/user_events.h
index 2984aae4a2b4..f74f3aedd49c 100644
--- a/include/uapi/linux/user_events.h
+++ b/include/uapi/linux/user_events.h
@@ -17,6 +17,15 @@
 /* Create dynamic location entry within a 32-bit value */
 #define DYN_LOC(offset, size) ((size) << 16 | (offset))
 
+/* List of supported registration flags */
+enum user_reg_flag {
+	/* Event will not delete upon last reference closing */
+	USER_EVENT_REG_PERSIST		= 1U << 0,
+
+	/* This value or above is currently non-ABI */
+	USER_EVENT_REG_MAX		= 1U << 1,
+};
+
 /*
  * Describes an event registration and stores the results of the registration.
  * This structure is passed to the DIAG_IOCSREG ioctl, callers at a minimum
@@ -33,7 +42,7 @@ struct user_reg {
 	/* Input: Enable size in bytes at address */
 	__u8	enable_size;
 
-	/* Input: Flags for future use, set to 0 */
+	/* Input: Flags to use, if any */
 	__u16	flags;
 
 	/* Input: Address to update when enabled */