sched/tracing: Append prev_state to tp args instead

Commit fa2c325 (sched/tracing: Don't re-read p->state when emitting
sched_switch event, 2022-01-20) added a new prev_state argument to the
sched_switch tracepoint, before the prev task_struct pointer.

This reordering of arguments broke BPF programs that use the raw
tracepoint (e.g. tp_btf programs). The type of the second argument has
changed and existing programs that assume a task_struct* argument
(e.g. for bpf_task_storage access) will now fail to verify.

If we instead append the new argument to the end, all existing programs
would continue to work and can conditionally extract the prev_state
argument on supported kernel versions.

Fixes: fa2c325 (sched/tracing: Don't re-read p->state when emitting sched_switch event, 2022-01-20)
Signed-off-by: Delyan Kratunov <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Acked-by: Steven Rostedt (Google) <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]

Author: Delyan Kratunov

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 @@ static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list)
 
 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.