sched_ext: Rename scx_bpf_dispatch[_vtime]_from_dsq*() -> scx_bpf_dsq_move[_vtime]*()

In sched_ext API, a repeatedly reported pain point is the overuse of the
verb "dispatch" and confusion around "consume":

- ops.dispatch()
- scx_bpf_dispatch[_vtime]()
- scx_bpf_consume()
- scx_bpf_dispatch[_vtime]_from_dsq*()

This overloading of the term is historical. Originally, there were only
built-in DSQs and moving a task into a DSQ always dispatched it for
execution. Using the verb "dispatch" for the kfuncs to move tasks into these
DSQs made sense.

Later, user DSQs were added and scx_bpf_dispatch[_vtime]() updated to be
able to insert tasks into any DSQ. The only allowed DSQ to DSQ transfer was
from a non-local DSQ to a local DSQ and this operation was named "consume".
This was already confusing as a task could be dispatched to a user DSQ from
ops.enqueue() and then the DSQ would have to be consumed in ops.dispatch().
Later addition of scx_bpf_dispatch_from_dsq*() made the confusion even worse
as "dispatch" in this context meant moving a task to an arbitrary DSQ from a
user DSQ.

Clean up the API with the following renames:

1. scx_bpf_dispatch[_vtime]()		-> scx_bpf_dsq_insert[_vtime]()
2. scx_bpf_consume()			-> scx_bpf_dsq_move_to_local()
3. scx_bpf_dispatch[_vtime]_from_dsq*()	-> scx_bpf_dsq_move[_vtime]*()

This patch performs the third set of renames. Compatibility is maintained
by:

- The previous kfunc names are still provided by the kernel so that old
  binaries can run. Kernel generates a warning when the old names are used.

- compat.bpf.h provides wrappers for the new names which automatically fall
  back to the old names when running on older kernels. They also trigger
  build error if old names are used for new builds.

- scx_bpf_dispatch[_vtime]_from_dsq*() were already wrapped in __COMPAT
  macros as they were introduced during v6.12 cycle. Wrap new API in
  __COMPAT macros too and trigger build errors on both __COMPAT prefixed and
  naked usages of the old names.

The compat features will be dropped after v6.15.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Andrea Righi <arighi@nvidia.com>
Acked-by: Changwoo Min <changwoo@igalia.com>
Acked-by: Johannes Bechberger <me@mostlynerdless.de>
Acked-by: Giovanni Gherdovich <ggherdovich@suse.com>
Cc: Dan Schatzberg <dschatzberg@meta.com>
Cc: Ming Yang <yougmark94@gmail.com>

3 files changed, 84 insertions, 30 deletions

diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h
index 535377649a22..2f36b7b6418d 100644
--- a/tools/sched_ext/include/scx/common.bpf.h
+++ b/tools/sched_ext/include/scx/common.bpf.h
@@ -41,10 +41,10 @@ void scx_bpf_dsq_insert_vtime(struct task_struct *p, u64 dsq_id, u64 slice, u64
 u32 scx_bpf_dispatch_nr_slots(void) __ksym;
 void scx_bpf_dispatch_cancel(void) __ksym;
 bool scx_bpf_dsq_move_to_local(u64 dsq_id) __ksym;
-void scx_bpf_dispatch_from_dsq_set_slice(struct bpf_iter_scx_dsq *it__iter, u64 slice) __ksym __weak;
-void scx_bpf_dispatch_from_dsq_set_vtime(struct bpf_iter_scx_dsq *it__iter, u64 vtime) __ksym __weak;
-bool scx_bpf_dispatch_from_dsq(struct bpf_iter_scx_dsq *it__iter, struct task_struct *p, u64 dsq_id, u64 enq_flags) __ksym __weak;
-bool scx_bpf_dispatch_vtime_from_dsq(struct bpf_iter_scx_dsq *it__iter, struct task_struct *p, u64 dsq_id, u64 enq_flags) __ksym __weak;
+void scx_bpf_dsq_move_set_slice(struct bpf_iter_scx_dsq *it__iter, u64 slice) __ksym;
+void scx_bpf_dsq_move_set_vtime(struct bpf_iter_scx_dsq *it__iter, u64 vtime) __ksym;
+bool scx_bpf_dsq_move(struct bpf_iter_scx_dsq *it__iter, struct task_struct *p, u64 dsq_id, u64 enq_flags) __ksym __weak;
+bool scx_bpf_dsq_move_vtime(struct bpf_iter_scx_dsq *it__iter, struct task_struct *p, u64 dsq_id, u64 enq_flags) __ksym __weak;
 u32 scx_bpf_reenqueue_local(void) __ksym;
 void scx_bpf_kick_cpu(s32 cpu, u64 flags) __ksym;
 s32 scx_bpf_dsq_nr_queued(u64 dsq_id) __ksym;
@@ -74,8 +74,8 @@ struct rq *scx_bpf_cpu_rq(s32 cpu) __ksym;
 struct cgroup *scx_bpf_task_cgroup(struct task_struct *p) __ksym __weak;
 
 /*
- * Use the following as @it__iter when calling
- * scx_bpf_dispatch[_vtime]_from_dsq() from within bpf_for_each() loops.
+ * Use the following as @it__iter when calling scx_bpf_dsq_move[_vtime]() from
+ * within bpf_for_each() loops.
  */
 #define BPF_FOR_EACH_ITER	(&___it)
 
diff --git a/tools/sched_ext/include/scx/compat.bpf.h b/tools/sched_ext/include/scx/compat.bpf.h
index c00ed24a8721..d56520100a26 100644
--- a/tools/sched_ext/include/scx/compat.bpf.h
+++ b/tools/sched_ext/include/scx/compat.bpf.h
@@ -20,30 +20,24 @@
 	(bpf_ksym_exists(scx_bpf_task_cgroup) ?					\
 	 scx_bpf_task_cgroup((p)) : NULL)
 
-/* v6.12: 4c30f5ce4f7a ("sched_ext: Implement scx_bpf_dispatch[_vtime]_from_dsq()") */
-#define __COMPAT_scx_bpf_dispatch_from_dsq_set_slice(it, slice)			\
-	(bpf_ksym_exists(scx_bpf_dispatch_from_dsq_set_slice) ?			\
-	 scx_bpf_dispatch_from_dsq_set_slice((it), (slice)) : (void)0)
-#define __COMPAT_scx_bpf_dispatch_from_dsq_set_vtime(it, vtime)			\
-	(bpf_ksym_exists(scx_bpf_dispatch_from_dsq_set_vtime) ?			\
-	 scx_bpf_dispatch_from_dsq_set_vtime((it), (vtime)) : (void)0)
-#define __COMPAT_scx_bpf_dispatch_from_dsq(it, p, dsq_id, enq_flags)		\
-	(bpf_ksym_exists(scx_bpf_dispatch_from_dsq) ?				\
-	 scx_bpf_dispatch_from_dsq((it), (p), (dsq_id), (enq_flags)) : false)
-#define __COMPAT_scx_bpf_dispatch_vtime_from_dsq(it, p, dsq_id, enq_flags)	\
-	(bpf_ksym_exists(scx_bpf_dispatch_vtime_from_dsq) ?			\
-	 scx_bpf_dispatch_vtime_from_dsq((it), (p), (dsq_id), (enq_flags)) : false)
-
 /*
  * v6.13: The verb `dispatch` was too overloaded and confusing. kfuncs are
  * renamed to unload the verb.
  *
  * Build error is triggered if old names are used. New binaries work with both
  * new and old names. The compat macros will be removed on v6.15 release.
+ *
+ * scx_bpf_dispatch_from_dsq() and friends were added during v6.12 by
+ * 4c30f5ce4f7a ("sched_ext: Implement scx_bpf_dispatch[_vtime]_from_dsq()").
+ * Preserve __COMPAT macros until v6.15.
  */
 void scx_bpf_dispatch___compat(struct task_struct *p, u64 dsq_id, u64 slice, u64 enq_flags) __ksym __weak;
 void scx_bpf_dispatch_vtime___compat(struct task_struct *p, u64 dsq_id, u64 slice, u64 vtime, u64 enq_flags) __ksym __weak;
 bool scx_bpf_consume___compat(u64 dsq_id) __ksym __weak;
+void scx_bpf_dispatch_from_dsq_set_slice___compat(struct bpf_iter_scx_dsq *it__iter, u64 slice) __ksym __weak;
+void scx_bpf_dispatch_from_dsq_set_vtime___compat(struct bpf_iter_scx_dsq *it__iter, u64 vtime) __ksym __weak;
+bool scx_bpf_dispatch_from_dsq___compat(struct bpf_iter_scx_dsq *it__iter, struct task_struct *p, u64 dsq_id, u64 enq_flags) __ksym __weak;
+bool scx_bpf_dispatch_vtime_from_dsq___compat(struct bpf_iter_scx_dsq *it__iter, struct task_struct *p, u64 dsq_id, u64 enq_flags) __ksym __weak;
 
 #define scx_bpf_dsq_insert(p, dsq_id, slice, enq_flags)				\
 	(bpf_ksym_exists(scx_bpf_dsq_insert) ?					\
@@ -60,6 +54,34 @@ bool scx_bpf_consume___compat(u64 dsq_id) __ksym __weak;
 	 scx_bpf_dsq_move_to_local((dsq_id)) :					\
 	 scx_bpf_consume___compat((dsq_id)))
 
+#define __COMPAT_scx_bpf_dsq_move_set_slice(it__iter, slice)			\
+	(bpf_ksym_exists(scx_bpf_dsq_move_set_slice) ?				\
+	 scx_bpf_dsq_move_set_slice((it__iter), (slice)) :			\
+	 (bpf_ksym_exists(scx_bpf_dispatch_from_dsq_set_slice___compat) ?	\
+	  scx_bpf_dispatch_from_dsq_set_slice___compat((it__iter), (slice)) :	\
+	  (void)0))
+
+#define __COMPAT_scx_bpf_dsq_move_set_vtime(it__iter, vtime)			\
+	(bpf_ksym_exists(scx_bpf_dsq_move_set_vtime) ?				\
+	 scx_bpf_dsq_move_set_vtime((it__iter), (vtime)) :			\
+	 (bpf_ksym_exists(scx_bpf_dispatch_from_dsq_set_vtime___compat) ?	\
+	  scx_bpf_dispatch_from_dsq_set_vtime___compat((it__iter), (vtime)) :	\
+	  (void) 0))
+
+#define __COMPAT_scx_bpf_dsq_move(it__iter, p, dsq_id, enq_flags)		\
+	(bpf_ksym_exists(scx_bpf_dsq_move) ?					\
+	 scx_bpf_dsq_move((it__iter), (p), (dsq_id), (enq_flags)) :		\
+	 (bpf_ksym_exists(scx_bpf_dispatch_from_dsq___compat) ?			\
+	  scx_bpf_dispatch_from_dsq___compat((it__iter), (p), (dsq_id), (enq_flags)) : \
+	  false))
+
+#define __COMPAT_scx_bpf_dsq_move_vtime(it__iter, p, dsq_id, enq_flags)		\
+	(bpf_ksym_exists(scx_bpf_dsq_move_vtime) ?				\
+	 scx_bpf_dsq_move_vtime((it__iter), (p), (dsq_id), (enq_flags)) :	\
+	 (bpf_ksym_exists(scx_bpf_dispatch_vtime_from_dsq___compat) ?		\
+	  scx_bpf_dispatch_vtime_from_dsq___compat((it__iter), (p), (dsq_id), (enq_flags)) : \
+	  false))
+
 #define scx_bpf_dispatch(p, dsq_id, slice, enq_flags)				\
 	_Static_assert(false, "scx_bpf_dispatch() renamed to scx_bpf_dsq_insert()")
 
@@ -71,6 +93,38 @@ bool scx_bpf_consume___compat(u64 dsq_id) __ksym __weak;
 	false;									\
 })
 
+#define scx_bpf_dispatch_from_dsq_set_slice(it__iter, slice)		\
+	_Static_assert(false, "scx_bpf_dispatch_from_dsq_set_slice() renamed to scx_bpf_dsq_move_set_slice()")
+
+#define scx_bpf_dispatch_from_dsq_set_vtime(it__iter, vtime)		\
+	_Static_assert(false, "scx_bpf_dispatch_from_dsq_set_vtime() renamed to scx_bpf_dsq_move_set_vtime()")
+
+#define scx_bpf_dispatch_from_dsq(it__iter, p, dsq_id, enq_flags) ({	\
+	_Static_assert(false, "scx_bpf_dispatch_from_dsq() renamed to scx_bpf_dsq_move()"); \
+	false;									\
+})
+
+#define scx_bpf_dispatch_vtime_from_dsq(it__iter, p, dsq_id, enq_flags) ({  \
+	_Static_assert(false, "scx_bpf_dispatch_vtime_from_dsq() renamed to scx_bpf_dsq_move_vtime()"); \
+	false;									\
+})
+
+#define __COMPAT_scx_bpf_dispatch_from_dsq_set_slice(it__iter, slice)		\
+	_Static_assert(false, "__COMPAT_scx_bpf_dispatch_from_dsq_set_slice() renamed to __COMPAT_scx_bpf_dsq_move_set_slice()")
+
+#define __COMPAT_scx_bpf_dispatch_from_dsq_set_vtime(it__iter, vtime)		\
+	_Static_assert(false, "__COMPAT_scx_bpf_dispatch_from_dsq_set_vtime() renamed to __COMPAT_scx_bpf_dsq_move_set_vtime()")
+
+#define __COMPAT_scx_bpf_dispatch_from_dsq(it__iter, p, dsq_id, enq_flags) ({	\
+	_Static_assert(false, "__COMPAT_scx_bpf_dispatch_from_dsq() renamed to __COMPAT_scx_bpf_dsq_move()"); \
+	false;									\
+})
+
+#define __COMPAT_scx_bpf_dispatch_vtime_from_dsq(it__iter, p, dsq_id, enq_flags) ({  \
+	_Static_assert(false, "__COMPAT_scx_bpf_dispatch_vtime_from_dsq() renamed to __COMPAT_scx_bpf_dsq_move_vtime()"); \
+	false;									\
+})
+
 /*
  * Define sched_ext_ops. This may be expanded to define multiple variants for
  * backward compatibility. See compat.h::SCX_OPS_LOAD/ATTACH().
diff --git a/tools/sched_ext/scx_qmap.bpf.c b/tools/sched_ext/scx_qmap.bpf.c
index 08f121252c56..ee264947e0c3 100644
--- a/tools/sched_ext/scx_qmap.bpf.c
+++ b/tools/sched_ext/scx_qmap.bpf.c
@@ -294,10 +294,10 @@ static void update_core_sched_head_seq(struct task_struct *p)
 }
 
 /*
- * To demonstrate the use of scx_bpf_dispatch_from_dsq(), implement silly
- * selective priority boosting mechanism by scanning SHARED_DSQ looking for
- * highpri tasks, moving them to HIGHPRI_DSQ and then consuming them first. This
- * makes minor difference only when dsp_batch is larger than 1.
+ * To demonstrate the use of scx_bpf_dsq_move(), implement silly selective
+ * priority boosting mechanism by scanning SHARED_DSQ looking for highpri tasks,
+ * moving them to HIGHPRI_DSQ and then consuming them first. This makes minor
+ * difference only when dsp_batch is larger than 1.
  *
  * scx_bpf_dispatch[_vtime]_from_dsq() are allowed both from ops.dispatch() and
  * non-rq-lock holding BPF programs. As demonstration, this function is called
@@ -318,11 +318,11 @@ static bool dispatch_highpri(bool from_timer)
 
 		if (tctx->highpri) {
 			/* exercise the set_*() and vtime interface too */
-			__COMPAT_scx_bpf_dispatch_from_dsq_set_slice(
+			__COMPAT_scx_bpf_dsq_move_set_slice(
 				BPF_FOR_EACH_ITER, slice_ns * 2);
-			__COMPAT_scx_bpf_dispatch_from_dsq_set_vtime(
+			__COMPAT_scx_bpf_dsq_move_set_vtime(
 				BPF_FOR_EACH_ITER, highpri_seq++);
-			__COMPAT_scx_bpf_dispatch_vtime_from_dsq(
+			__COMPAT_scx_bpf_dsq_move_vtime(
 				BPF_FOR_EACH_ITER, p, HIGHPRI_DSQ, 0);
 		}
 	}
@@ -340,9 +340,9 @@ static bool dispatch_highpri(bool from_timer)
 		else
 			cpu = scx_bpf_pick_any_cpu(p->cpus_ptr, 0);
 
-		if (__COMPAT_scx_bpf_dispatch_from_dsq(BPF_FOR_EACH_ITER, p,
-						       SCX_DSQ_LOCAL_ON | cpu,
-						       SCX_ENQ_PREEMPT)) {
+		if (__COMPAT_scx_bpf_dsq_move(BPF_FOR_EACH_ITER, p,
+					      SCX_DSQ_LOCAL_ON | cpu,
+					      SCX_ENQ_PREEMPT)) {
 			if (cpu == this_cpu) {
 				dispatched = true;
 				__sync_fetch_and_add(&nr_expedited_local, 1);