Merge tag 'sched_ext-for-7.0-rc3-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/sched_ext

Pull sched_ext fixes from Tejun Heo:

 - Fix data races flagged by KCSAN: add missing READ_ONCE()/WRITE_ONCE()
   annotations for lock-free accesses to module parameters and dsq->seq

 - Fix silent truncation of upper 32 enqueue flags (SCX_ENQ_PREEMPT and
   above) when passed through the int sched_class interface

 - Documentation updates: scheduling class precedence, task ownership
   state machine, example scheduler descriptions, config list cleanup

 - Selftest fix for format specifier and buffer length in
   file_write_long()

* tag 'sched_ext-for-7.0-rc3-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/sched_ext:
  sched_ext: Use WRITE_ONCE() for the write side of scx_enable helper pointer
  sched_ext: Fix enqueue_task_scx() truncation of upper enqueue flags
  sched_ext: Documentation: Update sched-ext.rst
  sched_ext: Use READ_ONCE() for scx_slice_bypass_us in scx_bypass()
  sched_ext: Documentation: Mention scheduling class precedence
  sched_ext: Document task ownership state machine
  sched_ext: Use READ_ONCE() for lock-free reads of module param variables
  sched_ext/selftests: Fix format specifier and buffer length in file_write_long()
  sched_ext: Use WRITE_ONCE() for the write side of dsq->seq update

2 files changed, 109 insertions, 27 deletions

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 1594987d637b..26a6ac2f8826 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -1103,7 +1103,7 @@ static void dispatch_enqueue(struct scx_sched *sch, struct scx_dispatch_q *dsq,
 	}
 
 	/* seq records the order tasks are queued, used by BPF DSQ iterator */
-	dsq->seq++;
+	WRITE_ONCE(dsq->seq, dsq->seq + 1);
 	p->scx.dsq_seq = dsq->seq;
 
 	dsq_mod_nr(dsq, 1);
@@ -1470,16 +1470,15 @@ static void clr_task_runnable(struct task_struct *p, bool reset_runnable_at)
 		p->scx.flags |= SCX_TASK_RESET_RUNNABLE_AT;
 }
 
-static void enqueue_task_scx(struct rq *rq, struct task_struct *p, int enq_flags)
+static void enqueue_task_scx(struct rq *rq, struct task_struct *p, int core_enq_flags)
 {
 	struct scx_sched *sch = scx_root;
 	int sticky_cpu = p->scx.sticky_cpu;
+	u64 enq_flags = core_enq_flags | rq->scx.extra_enq_flags;
 
 	if (enq_flags & ENQUEUE_WAKEUP)
 		rq->scx.flags |= SCX_RQ_IN_WAKEUP;
 
-	enq_flags |= rq->scx.extra_enq_flags;
-
 	if (sticky_cpu >= 0)
 		p->scx.sticky_cpu = -1;
 
@@ -3908,8 +3907,8 @@ static u32 bypass_lb_cpu(struct scx_sched *sch, struct rq *rq,
 	 * consider offloading iff the total queued duration is over the
 	 * threshold.
 	 */
-	min_delta_us = scx_bypass_lb_intv_us / SCX_BYPASS_LB_MIN_DELTA_DIV;
-	if (delta < DIV_ROUND_UP(min_delta_us, scx_slice_bypass_us))
+	min_delta_us = READ_ONCE(scx_bypass_lb_intv_us) / SCX_BYPASS_LB_MIN_DELTA_DIV;
+	if (delta < DIV_ROUND_UP(min_delta_us, READ_ONCE(scx_slice_bypass_us)))
 		return 0;
 
 	raw_spin_rq_lock_irq(rq);
@@ -4137,7 +4136,7 @@ static void scx_bypass(bool bypass)
 		WARN_ON_ONCE(scx_bypass_depth <= 0);
 		if (scx_bypass_depth != 1)
 			goto unlock;
-		WRITE_ONCE(scx_slice_dfl, scx_slice_bypass_us * NSEC_PER_USEC);
+		WRITE_ONCE(scx_slice_dfl, READ_ONCE(scx_slice_bypass_us) * NSEC_PER_USEC);
 		bypass_timestamp = ktime_get_ns();
 		if (sch)
 			scx_add_event(sch, SCX_EV_BYPASS_ACTIVATE, 1);
@@ -5259,13 +5258,14 @@ static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 	if (!READ_ONCE(helper)) {
 		mutex_lock(&helper_mutex);
 		if (!helper) {
-			helper = kthread_run_worker(0, "scx_enable_helper");
-			if (IS_ERR_OR_NULL(helper)) {
-				helper = NULL;
+			struct kthread_worker *w =
+				kthread_run_worker(0, "scx_enable_helper");
+			if (IS_ERR_OR_NULL(w)) {
 				mutex_unlock(&helper_mutex);
 				return -ENOMEM;
 			}
-			sched_set_fifo(helper->task);
+			sched_set_fifo(w->task);
+			WRITE_ONCE(helper, w);
 		}
 		mutex_unlock(&helper_mutex);
 	}
diff --git a/kernel/sched/ext_internal.h b/kernel/sched/ext_internal.h
index 11ebb744d893..00b450597f3e 100644
--- a/kernel/sched/ext_internal.h
+++ b/kernel/sched/ext_internal.h
@@ -1035,26 +1035,108 @@ static const char *scx_enable_state_str[] = {
 };
 
 /*
- * sched_ext_entity->ops_state
+ * Task Ownership State Machine (sched_ext_entity->ops_state)
  *
- * Used to track the task ownership between the SCX core and the BPF scheduler.
- * State transitions look as follows:
+ * The sched_ext core uses this state machine to track task ownership
+ * between the SCX core and the BPF scheduler. This allows the BPF
+ * scheduler to dispatch tasks without strict ordering requirements, while
+ * the SCX core safely rejects invalid dispatches.
  *
- * NONE -> QUEUEING -> QUEUED -> DISPATCHING
- *   ^              |                 |
- *   |              v                 v
- *   \-------------------------------/
+ * State Transitions
  *
- * QUEUEING and DISPATCHING states can be waited upon. See wait_ops_state() call
- * sites for explanations on the conditions being waited upon and why they are
- * safe. Transitions out of them into NONE or QUEUED must store_release and the
- * waiters should load_acquire.
+ *       .------------> NONE (owned by SCX core)
+ *       |               |           ^
+ *       |       enqueue |           | direct dispatch
+ *       |               v           |
+ *       |           QUEUEING -------'
+ *       |               |
+ *       |       enqueue |
+ *       |     completes |
+ *       |               v
+ *       |            QUEUED (owned by BPF scheduler)
+ *       |               |
+ *       |      dispatch |
+ *       |               |
+ *       |               v
+ *       |          DISPATCHING
+ *       |               |
+ *       |      dispatch |
+ *       |     completes |
+ *       `---------------'
  *
- * Tracking scx_ops_state enables sched_ext core to reliably determine whether
- * any given task can be dispatched by the BPF scheduler at all times and thus
- * relaxes the requirements on the BPF scheduler. This allows the BPF scheduler
- * to try to dispatch any task anytime regardless of its state as the SCX core
- * can safely reject invalid dispatches.
+ * State Descriptions
+ *
+ * - %SCX_OPSS_NONE:
+ *     Task is owned by the SCX core. It's either on a run queue, running,
+ *     or being manipulated by the core scheduler. The BPF scheduler has no
+ *     claim on this task.
+ *
+ * - %SCX_OPSS_QUEUEING:
+ *     Transitional state while transferring a task from the SCX core to
+ *     the BPF scheduler. The task's rq lock is held during this state.
+ *     Since QUEUEING is both entered and exited under the rq lock, dequeue
+ *     can never observe this state (it would be a BUG). When finishing a
+ *     dispatch, if the task is still in %SCX_OPSS_QUEUEING the completion
+ *     path busy-waits for it to leave this state (via wait_ops_state())
+ *     before retrying.
+ *
+ * - %SCX_OPSS_QUEUED:
+ *     Task is owned by the BPF scheduler. It's on a DSQ (dispatch queue)
+ *     and the BPF scheduler is responsible for dispatching it. A QSEQ
+ *     (queue sequence number) is embedded in this state to detect
+ *     dispatch/dequeue races: if a task is dequeued and re-enqueued, the
+ *     QSEQ changes and any in-flight dispatch operations targeting the old
+ *     QSEQ are safely ignored.
+ *
+ * - %SCX_OPSS_DISPATCHING:
+ *     Transitional state while transferring a task from the BPF scheduler
+ *     back to the SCX core. This state indicates the BPF scheduler has
+ *     selected the task for execution. When dequeue needs to take the task
+ *     off a DSQ and it is still in %SCX_OPSS_DISPATCHING, the dequeue path
+ *     busy-waits for it to leave this state (via wait_ops_state()) before
+ *     proceeding. Exits to %SCX_OPSS_NONE when dispatch completes.
+ *
+ * Memory Ordering
+ *
+ * Transitions out of %SCX_OPSS_QUEUEING and %SCX_OPSS_DISPATCHING into
+ * %SCX_OPSS_NONE or %SCX_OPSS_QUEUED must use atomic_long_set_release()
+ * and waiters must use atomic_long_read_acquire(). This ensures proper
+ * synchronization between concurrent operations.
+ *
+ * Cross-CPU Task Migration
+ *
+ * When moving a task in the %SCX_OPSS_DISPATCHING state, we can't simply
+ * grab the target CPU's rq lock because a concurrent dequeue might be
+ * waiting on %SCX_OPSS_DISPATCHING while holding the source rq lock
+ * (deadlock).
+ *
+ * The sched_ext core uses a "lock dancing" protocol coordinated by
+ * p->scx.holding_cpu. When moving a task to a different rq:
+ *
+ *   1. Verify task can be moved (CPU affinity, migration_disabled, etc.)
+ *   2. Set p->scx.holding_cpu to the current CPU
+ *   3. Set task state to %SCX_OPSS_NONE; dequeue waits while DISPATCHING
+ *      is set, so clearing DISPATCHING first prevents the circular wait
+ *      (safe to lock the rq we need)
+ *   4. Unlock the current CPU's rq
+ *   5. Lock src_rq (where the task currently lives)
+ *   6. Verify p->scx.holding_cpu == current CPU, if not, dequeue won the
+ *      race (dequeue clears holding_cpu to -1 when it takes the task), in
+ *      this case migration is aborted
+ *   7. If src_rq == dst_rq: clear holding_cpu and enqueue directly
+ *      into dst_rq's local DSQ (no lock swap needed)
+ *   8. Otherwise: call move_remote_task_to_local_dsq(), which releases
+ *      src_rq, locks dst_rq, and performs the deactivate/activate
+ *      migration cycle (dst_rq is held on return)
+ *   9. Unlock dst_rq and re-lock the current CPU's rq to restore
+ *      the lock state expected by the caller
+ *
+ * If any verification fails, abort the migration.
+ *
+ * This state tracking allows the BPF scheduler to try to dispatch any task
+ * at any time regardless of its state. The SCX core can safely
+ * reject/ignore invalid dispatches, simplifying the BPF scheduler
+ * implementation.
  */
 enum scx_ops_state {
 	SCX_OPSS_NONE,		/* owned by the SCX core */