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

Pull ftrace updates from Steven Rostedt:
 "Rewrite of function graph tracer to allow multiple users

  Up until now, the function graph tracer could only have a single user
  attached to it. If another user tried to attach to the function graph
  tracer while one was already attached, it would fail. Allowing
  function graph tracer to have more than one user has been asked for
  since 2009, but it required a rewrite to the logic to pull it off so
  it never happened. Until now!

  There's three systems that trace the return of a function. That is
  kretprobes, function graph tracer, and BPF. kretprobes and function
  graph tracing both do it similarly. The difference is that kretprobes
  uses a shadow stack per callback and function graph tracer creates a
  shadow stack for all tasks. The function graph tracer method makes it
  possible to trace the return of all functions. As kretprobes now needs
  that feature too, allowing it to use function graph tracer was needed.
  BPF also wants to trace the return of many probes and its method
  doesn't scale either. Having it use function graph tracer would
  improve that.

  By allowing function graph tracer to have multiple users allows both
  kretprobes and BPF to use function graph tracer in these cases. This
  will allow kretprobes code to be removed in the future as it's version
  will no longer be needed.

  Note, function graph tracer is only limited to 16 simultaneous users,
  due to shadow stack size and allocated slots"

* tag 'ftrace-v6.11' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: (49 commits)
  fgraph: Use str_plural() in test_graph_storage_single()
  function_graph: Add READ_ONCE() when accessing fgraph_array[]
  ftrace: Add missing kerneldoc parameters to unregister_ftrace_direct()
  function_graph: Everyone uses HAVE_FUNCTION_GRAPH_RET_ADDR_PTR, remove it
  function_graph: Fix up ftrace_graph_ret_addr()
  function_graph: Make fgraph_update_pid_func() a stub for !DYNAMIC_FTRACE
  function_graph: Rename BYTE_NUMBER to CHAR_NUMBER in selftests
  fgraph: Remove some unused functions
  ftrace: Hide one more entry in stack trace when ftrace_pid is enabled
  function_graph: Do not update pid func if CONFIG_DYNAMIC_FTRACE not enabled
  function_graph: Make fgraph_do_direct static key static
  ftrace: Fix prototypes for ftrace_startup/shutdown_subops()
  ftrace: Assign RCU list variable with rcu_assign_ptr()
  ftrace: Assign ftrace_list_end to ftrace_ops_list type cast to RCU
  ftrace: Declare function_trace_op in header to quiet sparse warning
  ftrace: Add comments to ftrace_hash_move() and friends
  ftrace: Convert "inc" parameter to bool in ftrace_hash_rec_update_modify()
  ftrace: Add comments to ftrace_hash_rec_disable/enable()
  ftrace: Remove "filter_hash" parameter from __ftrace_hash_rec_update()
  ftrace: Rename dup_hash() and comment it
  ...

3 files changed, 34 insertions, 55 deletions

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index b792274189a3..51575b76818e 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -227,6 +227,7 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops);
  *             ftrace_enabled.
  * DIRECT - Used by the direct ftrace_ops helper for direct functions
  *            (internal ftrace only, should not be used by others)
+ * SUBOP  - Is controlled by another op in field managed.
  */
 enum {
 	FTRACE_OPS_FL_ENABLED			= BIT(0),
@@ -247,6 +248,7 @@ enum {
 	FTRACE_OPS_FL_TRACE_ARRAY		= BIT(15),
 	FTRACE_OPS_FL_PERMANENT                 = BIT(16),
 	FTRACE_OPS_FL_DIRECT			= BIT(17),
+	FTRACE_OPS_FL_SUBOP			= BIT(18),
 };
 
 #ifndef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
@@ -334,7 +336,9 @@ struct ftrace_ops {
 	unsigned long			trampoline;
 	unsigned long			trampoline_size;
 	struct list_head		list;
+	struct list_head		subop_list;
 	ftrace_ops_func_t		ops_func;
+	struct ftrace_ops		*managed;
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 	unsigned long			direct_call;
 #endif
@@ -509,6 +513,15 @@ static inline void stack_tracer_disable(void) { }
 static inline void stack_tracer_enable(void) { }
 #endif
 
+enum {
+	FTRACE_UPDATE_CALLS		= (1 << 0),
+	FTRACE_DISABLE_CALLS		= (1 << 1),
+	FTRACE_UPDATE_TRACE_FUNC	= (1 << 2),
+	FTRACE_START_FUNC_RET		= (1 << 3),
+	FTRACE_STOP_FUNC_RET		= (1 << 4),
+	FTRACE_MAY_SLEEP		= (1 << 5),
+};
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 void ftrace_arch_code_modify_prepare(void);
@@ -603,15 +616,6 @@ void ftrace_set_global_notrace(unsigned char *buf, int len, int reset);
 void ftrace_free_filter(struct ftrace_ops *ops);
 void ftrace_ops_set_global_filter(struct ftrace_ops *ops);
 
-enum {
-	FTRACE_UPDATE_CALLS		= (1 << 0),
-	FTRACE_DISABLE_CALLS		= (1 << 1),
-	FTRACE_UPDATE_TRACE_FUNC	= (1 << 2),
-	FTRACE_START_FUNC_RET		= (1 << 3),
-	FTRACE_STOP_FUNC_RET		= (1 << 4),
-	FTRACE_MAY_SLEEP		= (1 << 5),
-};
-
 /*
  * The FTRACE_UPDATE_* enum is used to pass information back
  * from the ftrace_update_record() and ftrace_test_record()
@@ -1027,19 +1031,31 @@ struct ftrace_graph_ret {
 	unsigned long long rettime;
 } __packed;
 
+struct fgraph_ops;
+
 /* Type of the callback handlers for tracing function graph*/
-typedef void (*trace_func_graph_ret_t)(struct ftrace_graph_ret *); /* return */
-typedef int (*trace_func_graph_ent_t)(struct ftrace_graph_ent *); /* entry */
+typedef void (*trace_func_graph_ret_t)(struct ftrace_graph_ret *,
+				       struct fgraph_ops *); /* return */
+typedef int (*trace_func_graph_ent_t)(struct ftrace_graph_ent *,
+				      struct fgraph_ops *); /* entry */
 
-extern int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace);
+extern int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace, struct fgraph_ops *gops);
+bool ftrace_pids_enabled(struct ftrace_ops *ops);
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 
 struct fgraph_ops {
 	trace_func_graph_ent_t		entryfunc;
 	trace_func_graph_ret_t		retfunc;
+	struct ftrace_ops		ops; /* for the hash lists */
+	void				*private;
+	trace_func_graph_ent_t		saved_func;
+	int				idx;
 };
 
+void *fgraph_reserve_data(int idx, int size_bytes);
+void *fgraph_retrieve_data(int idx, int *size_bytes);
+
 /*
  * Stack of return addresses for functions
  * of a thread.
@@ -1055,9 +1071,7 @@ struct ftrace_ret_stack {
 #ifdef HAVE_FUNCTION_GRAPH_FP_TEST
 	unsigned long fp;
 #endif
-#ifdef HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
 	unsigned long *retp;
-#endif
 };
 
 /*
@@ -1072,10 +1086,11 @@ function_graph_enter(unsigned long ret, unsigned long func,
 		     unsigned long frame_pointer, unsigned long *retp);
 
 struct ftrace_ret_stack *
-ftrace_graph_get_ret_stack(struct task_struct *task, int idx);
+ftrace_graph_get_ret_stack(struct task_struct *task, int skip);
 
 unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx,
 				    unsigned long ret, unsigned long *retp);
+unsigned long *fgraph_get_task_var(struct fgraph_ops *gops);
 
 /*
  * Sometimes we don't want to trace a function with the function
@@ -1114,6 +1129,9 @@ extern void ftrace_graph_init_task(struct task_struct *t);
 extern void ftrace_graph_exit_task(struct task_struct *t);
 extern void ftrace_graph_init_idle_task(struct task_struct *t, int cpu);
 
+/* Used by assembly, but to quiet sparse warnings */
+extern struct ftrace_ops *function_trace_op;
+
 static inline void pause_graph_tracing(void)
 {
 	atomic_inc(&current->tracing_graph_pause);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 33dd8d9d2b85..e330ee0205c0 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1413,7 +1413,7 @@ struct task_struct {
 	int				curr_ret_depth;
 
 	/* Stack of return addresses for return function tracing: */
-	struct ftrace_ret_stack		*ret_stack;
+	unsigned long			*ret_stack;
 
 	/* Timestamp for last schedule: */
 	unsigned long long		ftrace_timestamp;
diff --git a/include/linux/trace_recursion.h b/include/linux/trace_recursion.h
index 24ea8ac049b4..ae04054a1be3 100644
--- a/include/linux/trace_recursion.h
+++ b/include/linux/trace_recursion.h
@@ -44,35 +44,6 @@ enum {
  */
 	TRACE_IRQ_BIT,
 
-	/* Set if the function is in the set_graph_function file */
-	TRACE_GRAPH_BIT,
-
-	/*
-	 * In the very unlikely case that an interrupt came in
-	 * at a start of graph tracing, and we want to trace
-	 * the function in that interrupt, the depth can be greater
-	 * than zero, because of the preempted start of a previous
-	 * trace. In an even more unlikely case, depth could be 2
-	 * if a softirq interrupted the start of graph tracing,
-	 * followed by an interrupt preempting a start of graph
-	 * tracing in the softirq, and depth can even be 3
-	 * if an NMI came in at the start of an interrupt function
-	 * that preempted a softirq start of a function that
-	 * preempted normal context!!!! Luckily, it can't be
-	 * greater than 3, so the next two bits are a mask
-	 * of what the depth is when we set TRACE_GRAPH_BIT
-	 */
-
-	TRACE_GRAPH_DEPTH_START_BIT,
-	TRACE_GRAPH_DEPTH_END_BIT,
-
-	/*
-	 * To implement set_graph_notrace, if this bit is set, we ignore
-	 * function graph tracing of called functions, until the return
-	 * function is called to clear it.
-	 */
-	TRACE_GRAPH_NOTRACE_BIT,
-
 	/* Used to prevent recursion recording from recursing. */
 	TRACE_RECORD_RECURSION_BIT,
 };
@@ -81,16 +52,6 @@ enum {
 #define trace_recursion_clear(bit)	do { (current)->trace_recursion &= ~(1<<(bit)); } while (0)
 #define trace_recursion_test(bit)	((current)->trace_recursion & (1<<(bit)))
 
-#define trace_recursion_depth() \
-	(((current)->trace_recursion >> TRACE_GRAPH_DEPTH_START_BIT) & 3)
-#define trace_recursion_set_depth(depth) \
-	do {								\
-		current->trace_recursion &=				\
-			~(3 << TRACE_GRAPH_DEPTH_START_BIT);		\
-		current->trace_recursion |=				\
-			((depth) & 3) << TRACE_GRAPH_DEPTH_START_BIT;	\
-	} while (0)
-
 #define TRACE_CONTEXT_BITS	4
 
 #define TRACE_FTRACE_START	TRACE_FTRACE_BIT