Merge tag 'trace-latency-v6.15' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace

Pull latency tracing updates from Steven Rostedt:

 - Add some trace events to osnoise and timerlat sample generation

   This adds more information to the osnoise and timerlat tracers as
   well as allows BPF programs to be attached to these locations to
   extract even more data.

 - Fix to DECLARE_TRACE_CONDITION() macro

   It wasn't used but now will be and it happened to be broken causing
   the build to fail.

 - Add scheduler specification monitors to runtime verifier (RV)

   This is a continuation of Daniel Bristot's work.

   RV allows monitors to run and react concurrently. Running the
   cumulative model is equivalent to running single components using the
   same reactors, with the advantage that it's easier to point out which
   specification failed in case of error.

   This update introduces nested monitors to RV, in short, the sysfs
   monitor folder will contain a monitor named sched, which is nothing
   but an empty container for other monitors. Controlling the sched
   monitor (enable, disable, set reactors) controls all nested monitors.

   The following scheduling monitors are added:

     - sco: scheduling context operations
       Monitor to ensure sched_set_state happens only in thread context

     - tss: task switch while scheduling
       Monitor to ensure sched_switch happens only in scheduling context

     - snroc: set non runnable on its own context
       Monitor to ensure set_state happens only in the respective task's context

     - scpd: schedule called with preemption disabled
       Monitor to ensure schedule is called with preemption disabled

     - snep: schedule does not enable preempt
       Monitor to ensure schedule does not enable preempt

     - sncid: schedule not called with interrupt disabled
       Monitor to ensure schedule is not called with interrupt disabled

* tag 'trace-latency-v6.15' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  tools/rv: Allow rv list to filter for container
  Documentation/rv: Add docs for the sched monitors
  verification/dot2k: Add support for nested monitors
  tools/rv: Add support for nested monitors
  rv: Add scpd, snep and sncid per-cpu monitors
  rv: Add snroc per-task monitor
  rv: Add sco and tss per-cpu monitors
  rv: Add option for nested monitors and include sched
  sched: Add sched tracepoints for RV task model
  rv: Add license identifiers to monitor files
  tracing: Fix DECLARE_TRACE_CONDITION
  trace/osnoise: Add trace events for samples

2 files changed, 18 insertions, 2 deletions

diff --git a/include/linux/rv.h b/include/linux/rv.h
index 8883b41d88ec..3452b5e4b29e 100644
--- a/include/linux/rv.h
+++ b/include/linux/rv.h
@@ -7,7 +7,7 @@
 #ifndef _LINUX_RV_H
 #define _LINUX_RV_H
 
-#define MAX_DA_NAME_LEN	24
+#define MAX_DA_NAME_LEN	32
 
 #ifdef CONFIG_RV
 /*
@@ -56,7 +56,7 @@ struct rv_monitor {
 
 bool rv_monitoring_on(void);
 int rv_unregister_monitor(struct rv_monitor *monitor);
-int rv_register_monitor(struct rv_monitor *monitor);
+int rv_register_monitor(struct rv_monitor *monitor, struct rv_monitor *parent);
 int rv_get_task_monitor_slot(void);
 void rv_put_task_monitor_slot(int slot);
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 6e5c38718ff5..56ddeb37b5cd 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -46,6 +46,7 @@
 #include <linux/rv.h>
 #include <linux/livepatch_sched.h>
 #include <linux/uidgid_types.h>
+#include <linux/tracepoint-defs.h>
 #include <asm/kmap_size.h>
 
 /* task_struct member predeclarations (sorted alphabetically): */
@@ -187,6 +188,12 @@ struct user_event_mm;
 # define debug_rtlock_wait_restore_state()	do { } while (0)
 #endif
 
+#define trace_set_current_state(state_value)                     \
+	do {                                                     \
+		if (tracepoint_enabled(sched_set_state_tp))      \
+			__trace_set_current_state(state_value); \
+	} while (0)
+
 /*
  * set_current_state() includes a barrier so that the write of current->__state
  * is correctly serialised wrt the caller's subsequent test of whether to
@@ -227,12 +234,14 @@ struct user_event_mm;
 #define __set_current_state(state_value)				\
 	do {								\
 		debug_normal_state_change((state_value));		\
+		trace_set_current_state(state_value);			\
 		WRITE_ONCE(current->__state, (state_value));		\
 	} while (0)
 
 #define set_current_state(state_value)					\
 	do {								\
 		debug_normal_state_change((state_value));		\
+		trace_set_current_state(state_value);			\
 		smp_store_mb(current->__state, (state_value));		\
 	} while (0)
 
@@ -248,6 +257,7 @@ struct user_event_mm;
 									\
 		raw_spin_lock_irqsave(&current->pi_lock, flags);	\
 		debug_special_state_change((state_value));		\
+		trace_set_current_state(state_value);			\
 		WRITE_ONCE(current->__state, (state_value));		\
 		raw_spin_unlock_irqrestore(&current->pi_lock, flags);	\
 	} while (0)
@@ -283,6 +293,7 @@ struct user_event_mm;
 		raw_spin_lock(&current->pi_lock);			\
 		current->saved_state = current->__state;		\
 		debug_rtlock_wait_set_state();				\
+		trace_set_current_state(TASK_RTLOCK_WAIT);		\
 		WRITE_ONCE(current->__state, TASK_RTLOCK_WAIT);		\
 		raw_spin_unlock(&current->pi_lock);			\
 	} while (0);
@@ -292,6 +303,7 @@ struct user_event_mm;
 		lockdep_assert_irqs_disabled();				\
 		raw_spin_lock(&current->pi_lock);			\
 		debug_rtlock_wait_restore_state();			\
+		trace_set_current_state(current->saved_state);		\
 		WRITE_ONCE(current->__state, current->saved_state);	\
 		current->saved_state = TASK_RUNNING;			\
 		raw_spin_unlock(&current->pi_lock);			\
@@ -328,6 +340,10 @@ extern void io_schedule_finish(int token);
 extern long io_schedule_timeout(long timeout);
 extern void io_schedule(void);
 
+/* wrapper function to trace from this header file */
+DECLARE_TRACEPOINT(sched_set_state_tp);
+extern void __trace_set_current_state(int state_value);
+
 /**
  * struct prev_cputime - snapshot of system and user cputime
  * @utime: time spent in user mode