Merge branch 'for-7.3-fixes' into for-next

5 files changed, 94 insertions, 15 deletions

diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c
index 40fa1697bdb7..7642ab26a860 100644
--- a/kernel/sched/ext/ext.c
+++ b/kernel/sched/ext/ext.c
@@ -3670,8 +3670,20 @@ static void handle_hotplug(struct rq *rq, bool online)
 		s16 *tbl = rcu_dereference_check(scx_cpu_to_cid_tbl,
 						 lockdep_is_cpus_held());
 
-		if (tbl)
+		if (tbl) {
+			struct scx_sched *pos;
+
 			cpu_or_cid = tbl[cpu];
+
+			guard(raw_spinlock_irqsave)(&scx_sched_lock);
+			list_for_each_entry(pos, &scx_sched_all, all) {
+				struct scx_cmask *mask = pos->online_cmask;
+
+				if (mask)
+					__assign_bit(cpu_or_cid, (unsigned long *)mask->bits,
+						     online);
+			}
+		}
 	}
 
 	if (online && SCX_HAS_OP(sch, cpu_online))
@@ -5287,12 +5299,17 @@ static void free_exit_info(struct scx_exit_info *ei);
 static const char *scx_exit_reason(enum scx_exit_kind kind);
 static bool scx_claim_exit(struct scx_sched *sch, enum scx_exit_kind kind);
 
-s32 scx_set_cmask_scratch_alloc(struct scx_sched *sch)
+s32 scx_alloc_kern_arena_objs(struct scx_sched *sch)
 {
 	size_t size = struct_size_t(struct scx_cmask, bits,
 				    SCX_CMASK_NR_WORDS(num_possible_cpus()));
+	struct scx_cmask *online;
+	struct scx_cmask_ref ref;
 	int cpu;
 
+	/* hotplug stays excluded until the online mask is published */
+	lockdep_assert_cpus_held();
+
 	if (!sch->is_cid_type || !sch->arena_pool)
 		return 0;
 
@@ -5308,15 +5325,28 @@ s32 scx_set_cmask_scratch_alloc(struct scx_sched *sch)
 			return -ENOMEM;
 		scx_cmask_init(*slot, 0, num_possible_cpus());
 	}
+
+	/* pack the online mask alongside the scratch masks */
+	online = scx_arena_alloc(sch, size);
+	if (!online)
+		return -ENOMEM;
+
+	scoped_guard(rcu) {
+		scx_cmask_ref_init_kern(sch, online, 0, num_possible_cpus(), &ref);
+		scx_cmask_ref_from_cpumask(&ref, cpu_active_mask);
+	}
+	sch->online_cmask = online;
+
 	return 0;
 }
 
-static void scx_set_cmask_scratch_free(struct scx_sched *sch)
+static void scx_free_kern_arena_objs(struct scx_sched *sch)
 {
 	size_t size = struct_size_t(struct scx_cmask, bits,
 				    SCX_CMASK_NR_WORDS(num_possible_cpus()));
 	int cpu;
 
+	scx_arena_free(sch, sch->online_cmask, size);
 	if (!sch->set_cmask_scratch)
 		return;
 
@@ -5403,7 +5433,7 @@ static void scx_sched_free_rcu_work(struct work_struct *work)
 
 	rhashtable_free_and_destroy(&sch->dsq_hash, NULL, NULL);
 	free_exit_info(sch->exit_info);
-	scx_set_cmask_scratch_free(sch);
+	scx_free_kern_arena_objs(sch);
 	scx_arena_pool_destroy(sch);
 	if (sch->arena_map)
 		bpf_map_put(sch->arena_map);
@@ -7608,7 +7638,7 @@ static void scx_root_enable_workfn(struct kthread_work *work)
 		goto err_disable;
 	}
 
-	ret = scx_set_cmask_scratch_alloc(sch);
+	ret = scx_alloc_kern_arena_objs(sch);
 	if (ret) {
 		cpus_read_unlock();
 		goto err_disable;
@@ -10359,7 +10389,8 @@ __bpf_kfunc u32 scx_bpf_nr_cids(void)
  * hotplug, which lets schedulers treat [0, nr_online_cids) as the online
  * range. Schedulers that prefer to handle hotplug without a restart should
  * install a custom mapping via scx_bpf_cid_override() and track onlining
- * through the ops.cid_online / ops.cid_offline callbacks.
+ * through the ops.cid_online / ops.cid_offline callbacks, starting from the
+ * mask scx_bpf_online_cmask() returns.
  */
 __bpf_kfunc u32 scx_bpf_nr_online_cids(void)
 {
@@ -10367,6 +10398,37 @@ __bpf_kfunc u32 scx_bpf_nr_online_cids(void)
 }
 
 /**
+ * scx_bpf_online_cmask - Return the online cid mask in the scheduler arena
+ * @aux: implicit BPF argument to access bpf_prog_aux hidden from BPF progs
+ *
+ * Return a kernel-maintained cmask covering [0, scx_bpf_nr_cids()), or NULL if
+ * the calling program is not associated with a live cid-form scheduler or the
+ * mask is not allocated yet, as in ops.init_cids(). Treat the mask as read-only
+ * even though arena memory stays writable by the BPF scheduler. The mask
+ * follows the SCX hotplug notifications: a cid's bit is updated before
+ * ops.cid_online/offline() runs for it. The pointer is valid from ops.init()
+ * through ops.exit(). Root ops.init() runs with hotplug excluded. Other
+ * contexts can observe concurrent updates.
+ */
+__bpf_kfunc const void *scx_bpf_online_cmask(const struct bpf_prog_aux *aux)
+{
+	struct scx_sched *sch;
+	struct scx_cmask *online;
+
+	guard(rcu)();
+
+	sch = scx_prog_sched(aux);
+	if (unlikely(!sch))
+		return NULL;
+	online = sch->online_cmask;
+	if (unlikely(!online))
+		return NULL;
+
+	/* BPF rebases by the low 32 bits, like __arena callback args */
+	return (void *)((unsigned long)online - sch->arena_kern_base);
+}
+
+/**
  * scx_bpf_this_cid - Return the cid of the CPU this program is running on
  *
  * cid-addressed equivalent of bpf_get_smp_processor_id() for scx programs.
@@ -10729,6 +10791,7 @@ BTF_ID_FLAGS(func, scx_bpf_nr_node_ids)
 BTF_ID_FLAGS(func, scx_bpf_nr_cpu_ids)
 BTF_ID_FLAGS(func, scx_bpf_nr_cids)
 BTF_ID_FLAGS(func, scx_bpf_nr_online_cids)
+BTF_ID_FLAGS(func, scx_bpf_online_cmask, KF_IMPLICIT_ARGS | KF_ARENA_RET)
 BTF_ID_FLAGS(func, scx_bpf_this_cid)
 BTF_ID_FLAGS(func, scx_bpf_get_possible_cpumask, KF_ACQUIRE)
 BTF_ID_FLAGS(func, scx_bpf_get_online_cpumask, KF_ACQUIRE)
diff --git a/kernel/sched/ext/internal.h b/kernel/sched/ext/internal.h
index e1eb3a0d456c..8ea40f15bda1 100644
--- a/kernel/sched/ext/internal.h
+++ b/kernel/sched/ext/internal.h
@@ -572,6 +572,12 @@ struct sched_ext_ops {
 	 *
 	 * Specify the %SCX_OPS_KEEP_BUILTIN_IDLE flag to keep the built-in idle
 	 * tracking.
+	 *
+	 * Only actual transitions are reported. A CPU that is claimed with an
+	 * idle pick and kicked but dispatches no task returns to idle without a
+	 * transition. A scheduler tracking idle CPUs itself must restore the
+	 * idle state from ops.dispatch() when it returns without the next task
+	 * to run.
 	 */
 	void (*update_idle)(s32 cpu, bool idle);
 
@@ -1555,6 +1561,7 @@ struct scx_sched {
 	 * and passes it to the callback's __arena argument.
 	 */
 	struct scx_cmask * __percpu *set_cmask_scratch;
+	struct scx_cmask *online_cmask;
 
 	DECLARE_BITMAP(has_op, SCX_OPI_END);
 
@@ -2081,7 +2088,7 @@ void scx_disable_and_exit_task(struct scx_sched *sch, struct task_struct *p);
 void scx_cgroup_lock(void);
 void scx_cgroup_unlock(void);
 #endif
-s32 scx_set_cmask_scratch_alloc(struct scx_sched *sch);
+s32 scx_alloc_kern_arena_objs(struct scx_sched *sch);
 void scx_disable_bypass_dsp(struct scx_sched *sch);
 void scx_bypass(struct scx_sched *sch, bool bypass);
 s32 scx_link_sched(struct scx_sched *sch);
diff --git a/kernel/sched/ext/sub.c b/kernel/sched/ext/sub.c
index 380a5653dc52..dd93800f367f 100644
--- a/kernel/sched/ext/sub.c
+++ b/kernel/sched/ext/sub.c
@@ -1805,6 +1805,12 @@ void scx_sub_enable_workfn(struct kthread_work *work)
 		goto err_disable;
 	}
 
+	scoped_guard(cpus_read_lock) {
+		ret = scx_alloc_kern_arena_objs(sch);
+		if (ret)
+			goto err_disable;
+	}
+
 	if (sch->ops.init) {
 		ret = SCX_CALL_OP_RET(sch, init, NULL);
 		if (ret) {
@@ -1815,10 +1821,6 @@ void scx_sub_enable_workfn(struct kthread_work *work)
 		sch->exit_info->flags |= SCX_EFLAG_INITIALIZED;
 	}
 
-	ret = scx_set_cmask_scratch_alloc(sch);
-	if (ret)
-		goto err_disable;
-
 	struct scx_sub_attach_args sub_attach_args = {
 		.ops = &sch->ops,
 		.cgroup_path = sch->cgrp_path,
diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h
index 9660b43d612c..a14afc66b1cd 100644
--- a/tools/sched_ext/include/scx/common.bpf.h
+++ b/tools/sched_ext/include/scx/common.bpf.h
@@ -113,6 +113,7 @@ s32 scx_bpf_this_cid(void) __ksym __weak;
 struct task_struct *scx_bpf_cid_curr(s32 cid) __ksym __weak;
 u32 scx_bpf_nr_cids(void) __ksym __weak;
 u32 scx_bpf_nr_online_cids(void) __ksym __weak;
+const void __arena *scx_bpf_online_cmask(void) __ksym __weak;
 u32 scx_bpf_cidperf_cap(s32 cid) __ksym __weak;
 u32 scx_bpf_cidperf_cur(s32 cid) __ksym __weak;
 s32 scx_bpf_cidperf_set(s32 cid, u32 perf) __ksym __weak;
diff --git a/tools/sched_ext/scx_qmap.bpf.c b/tools/sched_ext/scx_qmap.bpf.c
index bda56c37acb5..67b7c01cae55 100644
--- a/tools/sched_ext/scx_qmap.bpf.c
+++ b/tools/sched_ext/scx_qmap.bpf.c
@@ -818,10 +818,10 @@ void BPF_STRUCT_OPS(qmap_dispatch, s32 cid, struct task_struct *prev)
 			batch--;
 			cpuc->dsp_cnt--;
 			if (!batch || !scx_bpf_dispatch_nr_slots()) {
-				if (scan_shared_dsq(false))
+				if (scan_shared_dsq(false) ||
+				    scx_bpf_dsq_move_to_local(SHARED_DSQ, needs_immed(cid)))
 					return;
-				scx_bpf_dsq_move_to_local(SHARED_DSQ, needs_immed(cid));
-				return;
+				goto prev;
 			}
 			if (!cpuc->dsp_cnt)
 				break;
@@ -832,10 +832,14 @@ void BPF_STRUCT_OPS(qmap_dispatch, s32 cid, struct task_struct *prev)
 
 	if (scan_shared_dsq(false))
 		return;
-
+prev:
 	/*
 	 * No other tasks. @prev will keep running. Update its core_sched_seq as
 	 * if the task were enqueued and dispatched immediately.
+	 *
+	 * No @prev to keep running means the CPU goes idle. If its claim was
+	 * never used, that is not a transition and ops.update_idle() stays
+	 * silent. Restore the claim here.
 	 */
 	if (prev) {
 		taskc = lookup_task_ctx(prev);
@@ -844,6 +848,8 @@ void BPF_STRUCT_OPS(qmap_dispatch, s32 cid, struct task_struct *prev)
 
 		taskc->core_sched_seq =
 			qa.core_sched_tail_seqs[weight_to_idx(prev->scx.weight)]++;
+	} else {
+		cmask_set(cid, &qa.idle_cids.mask);
 	}
 }