Commit 9c2136be authored by Delyan Kratunov's avatar Delyan Kratunov Committed by Peter Zijlstra
Browse files

sched/tracing: Append prev_state to tp args instead 



Commit fa2c3254 (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: fa2c3254 (sched/tracing: Don't re-read p->state when emitting sched_switch event, 2022-01-20)
Signed-off-by: default avatarDelyan Kratunov <delyank@fb.com>
Signed-off-by: default avatarPeter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: default avatarSteven Rostedt (Google) <rostedt@goodmis.org>
Link: https://lkml.kernel.org/r/c8a6930dfdd58a4a5755fc01732675472979732b.camel@fb.com
parent c5eb0a61

include/trace/events/sched.h

+3 −3
Original line number Diff line number Diff line
@@ -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

+1 −1
Original line number Diff line number Diff line
@@ -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

+2 −2
Original line number Diff line number Diff line
@@ -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

+2 −2
Original line number Diff line number Diff line
@@ -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

+4 −4
Original line number Diff line number Diff line
@@ -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;