Merge tag 'trace-v6.13-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace

Pull more tracing updates from Steven Rostedt:

 - Add trace flag for NEED_RESCHED_LAZY

   Now that NEED_RESCHED_LAZY is upstream, add it to the status bits of
   the common_flags. This will now show when the NEED_RESCHED_LAZY flag
   is set that is used for debugging latency issues in the kernel via a
   trace.

 - Remove leftover "__idx" variable when SRCU was removed from the
   tracepoint code

 - Add rcu_tasks_trace guard

   To add a guard() around the tracepoint code, a rcu_tasks_trace guard
   needs to be created first.

 - Remove __DO_TRACE() macro and just call __DO_TRACE_CALL() directly

   The DO_TRACE() macro has conditional locking depending on what was
   passed into the macro parameters. As the guts of the macro has been
   moved to __DO_TRACE_CALL() to handle static call logic, there's no
   reason to keep the __DO_TRACE() macro around.

   It is better to just do the locking in place without the conditionals
   and call __DO_TRACE_CALL() from those locations. The "cond" passed in
   can also be moved out of that macro. This simplifies the code.

 - Remove the "cond" from the system call tracepoint macros

   The "cond" variable was added to allow some tracepoints to check a
   condition within the static_branch (jump/nop) logic. The system calls
   do not need this. Removing it simplifies the code.

 - Replace scoped_guard() with just guard() in the tracepoint logic

   guard() works just as well as scoped_guard() in the tracepoint logic
   and the scoped_guard() causes some issues.

* tag 'trace-v6.13-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  tracing: Use guard() rather than scoped_guard()
  tracing: Remove cond argument from __DECLARE_TRACE_SYSCALL
  tracing: Remove conditional locking from __DO_TRACE()
  rcupdate_trace: Define rcu_tasks_trace lock guard
  tracing: Remove __idx variable from __DO_TRACE
  tracing: Move it_func[0] comment to the relevant context
  tracing: Record task flag NEED_RESCHED_LAZY.

Documentation/trace/ftrace.rst

@@ -1033,9 +1033,13 @@ explains which is which.
   irqs-off: 'd' interrupts are disabled. '.' otherwise.
 
   need-resched:
+	- 'B' all, TIF_NEED_RESCHED, PREEMPT_NEED_RESCHED and TIF_RESCHED_LAZY is set,
 	- 'N' both TIF_NEED_RESCHED and PREEMPT_NEED_RESCHED is set,
 	- 'n' only TIF_NEED_RESCHED is set,
 	- 'p' only PREEMPT_NEED_RESCHED is set,
+	- 'L' both PREEMPT_NEED_RESCHED and TIF_RESCHED_LAZY is set,
+	- 'b' both TIF_NEED_RESCHED and TIF_RESCHED_LAZY is set,
+	- 'l' only TIF_RESCHED_LAZY is set
 	- '.' otherwise.
 
   hardirq/softirq:

include/linux/rcupdate_trace.h

@@ -10,6 +10,7 @@
 
 #include <linux/sched.h>
 #include <linux/rcupdate.h>
+#include <linux/cleanup.h>
 
 extern struct lockdep_map rcu_trace_lock_map;
 
@@ -98,4 +99,8 @@ static inline void rcu_read_lock_trace(void) { BUG(); }
 static inline void rcu_read_unlock_trace(void) { BUG(); }
 #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */
 
+DEFINE_LOCK_GUARD_0(rcu_tasks_trace,
+	rcu_read_lock_trace(),
+	rcu_read_unlock_trace())
+
 #endif /* __LINUX_RCUPDATE_TRACE_H */

include/linux/trace_events.h

@@ -184,6 +184,7 @@ unsigned int tracing_gen_ctx_irq_test(unsigned int irqs_status);
 
 enum trace_flag_type {
 	TRACE_FLAG_IRQS_OFF		= 0x01,
+	TRACE_FLAG_NEED_RESCHED_LAZY	= 0x02,
 	TRACE_FLAG_NEED_RESCHED		= 0x04,
 	TRACE_FLAG_HARDIRQ		= 0x08,
 	TRACE_FLAG_SOFTIRQ		= 0x10,

include/linux/tracepoint.h

@@ -209,36 +209,6 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 #define __DO_TRACE_CALL(name, args)	__traceiter_##name(NULL, args)
 #endif /* CONFIG_HAVE_STATIC_CALL */
 
-/*
- * it_func[0] is never NULL because there is at least one element in the array
- * when the array itself is non NULL.
- *
- * With @syscall=0, the tracepoint callback array dereference is
- * protected by disabling preemption.
- * With @syscall=1, the tracepoint callback array dereference is
- * protected by Tasks Trace RCU, which allows probes to handle page
- * faults.
- */
-#define __DO_TRACE(name, args, cond, syscall)				\
-	do {								\
-		int __maybe_unused __idx = 0;				\
-									\
-		if (!(cond))						\
-			return;						\
-									\
-		if (syscall)						\
-			rcu_read_lock_trace();				\
-		else							\
-			preempt_disable_notrace();			\
-									\
-		__DO_TRACE_CALL(name, TP_ARGS(args));			\
-									\
-		if (syscall)						\
-			rcu_read_unlock_trace();			\
-		else							\
-			preempt_enable_notrace();			\
-	} while (0)
-
 /*
  * Declare an exported function that Rust code can call to trigger this
  * tracepoint. This function does not include the static branch; that is done
@@ -262,7 +232,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
  * site if it is not watching, as it will need to be active when the
  * tracepoint is enabled.
  */
-#define __DECLARE_TRACE_COMMON(name, proto, args, cond, data_proto)	\
+#define __DECLARE_TRACE_COMMON(name, proto, args, data_proto)		\
 	extern int __traceiter_##name(data_proto);			\
 	DECLARE_STATIC_CALL(tp_func_##name, __traceiter_##name);	\
 	extern struct tracepoint __tracepoint_##name;			\
@@ -297,41 +267,43 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 	}
 
 #define __DECLARE_TRACE(name, proto, args, cond, data_proto)		\
-	__DECLARE_TRACE_COMMON(name, PARAMS(proto), PARAMS(args), cond, PARAMS(data_proto)) \
+	__DECLARE_TRACE_COMMON(name, PARAMS(proto), PARAMS(args), PARAMS(data_proto)) \
 	static inline void __rust_do_trace_##name(proto)		\
 	{								\
-		__DO_TRACE(name,					\
-			TP_ARGS(args),					\
-			TP_CONDITION(cond), 0);				\
+		if (cond) {						\
+			guard(preempt_notrace)();			\
+			__DO_TRACE_CALL(name, TP_ARGS(args));		\
+		}							\
 	}								\
 	static inline void trace_##name(proto)				\
 	{								\
-		if (static_branch_unlikely(&__tracepoint_##name.key))	\
-			__DO_TRACE(name,				\
-				TP_ARGS(args),				\
-				TP_CONDITION(cond), 0);			\
+		if (static_branch_unlikely(&__tracepoint_##name.key)) { \
+			if (cond) {					\
+				guard(preempt_notrace)();		\
+				__DO_TRACE_CALL(name, TP_ARGS(args));	\
+			}						\
+		}							\
 		if (IS_ENABLED(CONFIG_LOCKDEP) && (cond)) {		\
 			WARN_ONCE(!rcu_is_watching(),			\
 				  "RCU not watching for tracepoint");	\
 		}							\
 	}
 
-#define __DECLARE_TRACE_SYSCALL(name, proto, args, cond, data_proto)	\
-	__DECLARE_TRACE_COMMON(name, PARAMS(proto), PARAMS(args), cond, PARAMS(data_proto)) \
+#define __DECLARE_TRACE_SYSCALL(name, proto, args, data_proto)		\
+	__DECLARE_TRACE_COMMON(name, PARAMS(proto), PARAMS(args), PARAMS(data_proto)) \
 	static inline void __rust_do_trace_##name(proto)		\
 	{								\
-		__DO_TRACE(name,					\
-			TP_ARGS(args),					\
-			TP_CONDITION(cond), 1);				\
+		guard(rcu_tasks_trace)();				\
+		__DO_TRACE_CALL(name, TP_ARGS(args));			\
 	}								\
 	static inline void trace_##name(proto)				\
 	{								\
 		might_fault();						\
-		if (static_branch_unlikely(&__tracepoint_##name.key))	\
-			__DO_TRACE(name,				\
-				TP_ARGS(args),				\
-				TP_CONDITION(cond), 1);			\
-		if (IS_ENABLED(CONFIG_LOCKDEP) && (cond)) {		\
+		if (static_branch_unlikely(&__tracepoint_##name.key)) {	\
+			guard(rcu_tasks_trace)();			\
+			__DO_TRACE_CALL(name, TP_ARGS(args));		\
+		}							\
+		if (IS_ENABLED(CONFIG_LOCKDEP)) {			\
 			WARN_ONCE(!rcu_is_watching(),			\
 				  "RCU not watching for tracepoint");	\
 		}							\
@@ -341,6 +313,9 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
  * We have no guarantee that gcc and the linker won't up-align the tracepoint
  * structures, so we create an array of pointers that will be used for iteration
  * on the tracepoints.
+ *
+ * it_func[0] is never NULL because there is at least one element in the array
+ * when the array itself is non NULL.
  */
 #define __DEFINE_TRACE_EXT(_name, _ext, proto, args)			\
 	static const char __tpstrtab_##_name[]				\
@@ -412,7 +387,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 
 
 #else /* !TRACEPOINTS_ENABLED */
-#define __DECLARE_TRACE(name, proto, args, cond, data_proto)		\
+#define __DECLARE_TRACE_COMMON(name, proto, args, data_proto)		\
 	static inline void trace_##name(proto)				\
 	{ }								\
 	static inline int						\
@@ -436,7 +411,11 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 		return false;						\
 	}
 
-#define __DECLARE_TRACE_SYSCALL	__DECLARE_TRACE
+#define __DECLARE_TRACE(name, proto, args, cond, data_proto)		\
+	__DECLARE_TRACE_COMMON(name, PARAMS(proto), PARAMS(args), PARAMS(data_proto))
+
+#define __DECLARE_TRACE_SYSCALL(name, proto, args, data_proto)		\
+	__DECLARE_TRACE_COMMON(name, PARAMS(proto), PARAMS(args), PARAMS(data_proto))
 
 #define DEFINE_TRACE_FN(name, reg, unreg, proto, args)
 #define DEFINE_TRACE_SYSCALL(name, reg, unreg, proto, args)
@@ -502,7 +481,6 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 
 #define DECLARE_TRACE_SYSCALL(name, proto, args)			\
 	__DECLARE_TRACE_SYSCALL(name, PARAMS(proto), PARAMS(args),	\
-				cpu_online(raw_smp_processor_id()),	\
 				PARAMS(void *__data, proto))
 
 #define TRACE_EVENT_FLAGS(event, flag)

kernel/trace/trace.c

@@ -2552,6 +2552,8 @@ unsigned int tracing_gen_ctx_irq_test(unsigned int irqs_status)
 		trace_flags |= TRACE_FLAG_NEED_RESCHED;
 	if (test_preempt_need_resched())
 		trace_flags |= TRACE_FLAG_PREEMPT_RESCHED;
+	if (IS_ENABLED(CONFIG_ARCH_HAS_PREEMPT_LAZY) && tif_test_bit(TIF_NEED_RESCHED_LAZY))
+		trace_flags |= TRACE_FLAG_NEED_RESCHED_LAZY;
 	return (trace_flags << 16) | (min_t(unsigned int, pc & 0xff, 0xf)) |
 		(min_t(unsigned int, migration_disable_value(), 0xf)) << 4;
 }

kernel/trace/trace_output.c

@@ -462,17 +462,29 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry)
 		bh_off ? 'b' :
 		'.';
 
-	switch (entry->flags & (TRACE_FLAG_NEED_RESCHED |
+	switch (entry->flags & (TRACE_FLAG_NEED_RESCHED | TRACE_FLAG_NEED_RESCHED_LAZY |
 				TRACE_FLAG_PREEMPT_RESCHED)) {
+	case TRACE_FLAG_NEED_RESCHED | TRACE_FLAG_NEED_RESCHED_LAZY | TRACE_FLAG_PREEMPT_RESCHED:
+		need_resched = 'B';
+		break;
 	case TRACE_FLAG_NEED_RESCHED | TRACE_FLAG_PREEMPT_RESCHED:
 		need_resched = 'N';
 		break;
+	case TRACE_FLAG_NEED_RESCHED_LAZY | TRACE_FLAG_PREEMPT_RESCHED:
+		need_resched = 'L';
+		break;
+	case TRACE_FLAG_NEED_RESCHED | TRACE_FLAG_NEED_RESCHED_LAZY:
+		need_resched = 'b';
+		break;
 	case TRACE_FLAG_NEED_RESCHED:
 		need_resched = 'n';
 		break;
 	case TRACE_FLAG_PREEMPT_RESCHED:
 		need_resched = 'p';
 		break;
+	case TRACE_FLAG_NEED_RESCHED_LAZY:
+		need_resched = 'l';
+		break;
 	default:
 		need_resched = '.';
 		break;