The recent expansion of the sched switch tracepoint inserted a new argument

in the middle of the arguments. This reordering broke BPF programs which
 relied on the old argument list. While tracepoints are not considered
 stable ABI, it's not trivial to make BPF cope with such a change, but it's
 being worked on. For now restore the original argument order and move the
 new argument to the end of the argument list.
 -----BEGIN PGP SIGNATURE-----
 
 iQJHBAABCgAxFiEEQp8+kY+LLUocC4bMphj1TA10mKEFAmKAxKQTHHRnbHhAbGlu
 dXRyb25peC5kZQAKCRCmGPVMDXSYoThID/4jp/8GiKsf1jPgKkU39Yw7qAePzObQ
 V9K2XLxSwH27D+UpmOPODnckzHJMtX0M4Z+sGMgGSPe/IvOVj+NEmUiQGU29sDwg
 T7If2FSHMutPCB9QL26kxjmebU+SdllRwrJylOA1ZNduunczxKlpATJ5vneCC/Qt
 D5VpB3XlwT31pd9UdoW/kV5uQK6bFR7qREWXhONZ+HyzsKJdV0vGe2ZX6U7ek2/d
 XJxETE1eXlsMr+2VY5lkxhr596uPJgDAM9g+OknO/Lal/I7WoUchDN2giItzn6RY
 XWxPK85mE59MwTa6PQCJcO8A7r2KcHfGrbFVjA9h1jhREtsZigb9ZemDgQ+s8goT
 znIIlTO2l7ed2VDMU/mt3zZuS0rMshn/8Axk+AN3N6gKffV6F4q0BpZUUccGe+FM
 tfQ34YGmMKx6uuyHPPZCQd1buJuDuXNyZF7XFO3uxv9BGt3x42aswAbx1zYIV+ZR
 Uj/Vnojoc1aBdffVSUL0he+vjutYixx4gb8nh0ZFa5FTe70XDvPGTUTTOSW6BOq0
 yiFOWtG8MbziVBDE2iKmfUMT+dPQd0+PW8szk8J9yOJyOnTu9y6KkyWl2JRllSxT
 Qv7icnMN5P1xqN/c4P+8Iq0CrVItyxMJ0Ouc29tsNPHYkzsBo4c0XAn94mib1O17
 zyJYW0F9UVHOSg==
 =6Bvx
 -----END PGP SIGNATURE-----

Merge tag 'sched-urgent-2022-05-15' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler fix from Thomas Gleixner:
 "The recent expansion of the sched switch tracepoint inserted a new
  argument in the middle of the arguments. This reordering broke BPF
  programs which relied on the old argument list.

  While tracepoints are not considered stable ABI, it's not trivial to
  make BPF cope with such a change, but it's being worked on. For now
  restore the original argument order and move the new argument to the
  end of the argument list"

* tag 'sched-urgent-2022-05-15' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/tracing: Append prev_state to tp args instead

include/trace/events/sched.h

@@ -222,11 +222,11 @@ static inline long __trace_sched_switch_state(bool preempt,
 TRACE_EVENT(sched_switch,
 
 	TP_PROTO(bool preempt,
-		 unsigned int prev_state,
 		 struct task_struct *prev,
-		 struct task_struct *next),
+		 struct task_struct *next,
+		 unsigned int prev_state),
 
-	TP_ARGS(preempt, prev_state, prev, next),
+	TP_ARGS(preempt, prev, next, prev_state),
 
 	TP_STRUCT__entry(
 		__array(	char,	prev_comm,	TASK_COMM_LEN	)

kernel/sched/core.c

@@ -6382,7 +6382,7 @@ static void __sched notrace __schedule(unsigned int sched_mode)
 		migrate_disable_switch(rq, prev);
 		psi_sched_switch(prev, next, !task_on_rq_queued(prev));
 
-		trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev_state, prev, next);
+		trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev, next, prev_state);
 
 		/* Also unlocks the rq: */
 		rq = context_switch(rq, prev, next, &rf);

kernel/trace/fgraph.c

@@ -404,9 +404,9 @@ free:
 
 static void
 ftrace_graph_probe_sched_switch(void *ignore, bool preempt,
-				unsigned int prev_state,
 				struct task_struct *prev,
-				struct task_struct *next)
+				struct task_struct *next,
+				unsigned int prev_state)
 {
 	unsigned long long timestamp;
 	int index;

kernel/trace/ftrace.c

@@ -7420,9 +7420,9 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops)
 
 static void
 ftrace_filter_pid_sched_switch_probe(void *data, bool preempt,
-				     unsigned int prev_state,
 				     struct task_struct *prev,
-				     struct task_struct *next)
+				     struct task_struct *next,
+				     unsigned int prev_state)
 {
 	struct trace_array *tr = data;
 	struct trace_pid_list *pid_list;

kernel/trace/trace_events.c

@@ -773,9 +773,9 @@ void trace_event_follow_fork(struct trace_array *tr, bool enable)
 
 static void
 event_filter_pid_sched_switch_probe_pre(void *data, bool preempt,
-					unsigned int prev_state,
 					struct task_struct *prev,
-					struct task_struct *next)
+					struct task_struct *next,
+					unsigned int prev_state)
 {
 	struct trace_array *tr = data;
 	struct trace_pid_list *no_pid_list;
@@ -799,9 +799,9 @@ event_filter_pid_sched_switch_probe_pre(void *data, bool preempt,
 
 static void
 event_filter_pid_sched_switch_probe_post(void *data, bool preempt,
-					 unsigned int prev_state,
 					 struct task_struct *prev,
-					 struct task_struct *next)
+					 struct task_struct *next,
+					 unsigned int prev_state)
 {
 	struct trace_array *tr = data;
 	struct trace_pid_list *no_pid_list;

kernel/trace/trace_osnoise.c

@@ -1168,9 +1168,9 @@ thread_exit(struct osnoise_variables *osn_var, struct task_struct *t)
  */
 static void
 trace_sched_switch_callback(void *data, bool preempt,
-			    unsigned int prev_state,
 			    struct task_struct *p,
-			    struct task_struct *n)
+			    struct task_struct *n,
+			    unsigned int prev_state)
 {
 	struct osnoise_variables *osn_var = this_cpu_osn_var();
 

kernel/trace/trace_sched_switch.c

@@ -22,8 +22,8 @@ static DEFINE_MUTEX(sched_register_mutex);
 
 static void
 probe_sched_switch(void *ignore, bool preempt,
-		   unsigned int prev_state,
-		   struct task_struct *prev, struct task_struct *next)
+		   struct task_struct *prev, struct task_struct *next,
+		   unsigned int prev_state)
 {
 	int flags;
 

kernel/trace/trace_sched_wakeup.c

@@ -426,8 +426,8 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
 
 static void notrace
 probe_wakeup_sched_switch(void *ignore, bool preempt,
-			  unsigned int prev_state,
-			  struct task_struct *prev, struct task_struct *next)
+			  struct task_struct *prev, struct task_struct *next,
+			  unsigned int prev_state)
 {
 	struct trace_array_cpu *data;
 	u64 T0, T1, delta;

samples/trace_events/trace_custom_sched.h

@@ -25,11 +25,11 @@ TRACE_CUSTOM_EVENT(sched_switch,
 	 * that the custom event is using.
 	 */
 	TP_PROTO(bool preempt,
-		 unsigned int prev_state,
 		 struct task_struct *prev,
-		 struct task_struct *next),
+		 struct task_struct *next,
+		 unsigned int prev_state),
 
-	TP_ARGS(preempt, prev_state, prev, next),
+	TP_ARGS(preempt, prev, next, prev_state),
 
 	/*
 	 * The next fields are where the customization happens.