public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
* [PATCH 16/17] tools/sched_ext: scx_qmap: Port to cid-form struct_ops
@ 2026-04-24  1:32 Tejun Heo
  0 siblings, 0 replies; 3+ messages in thread
From: Tejun Heo @ 2026-04-24  1:32 UTC (permalink / raw)
  To: David Vernet, Andrea Righi, Changwoo Min
  Cc: sched-ext, emil, linux-kernel, Cheng-Yang Chou, Zhao Mengmeng,
	Tejun Heo

Flip qmap's struct_ops to bpf_sched_ext_ops_cid. The kernel now passes
cids and cmasks to callbacks directly, so the per-callback cpu<->cid
translations that the prior patch added drop out and cpu_ctxs[] is
reindexed by cid. Cpu-form kfunc calls switch to their cid-form
counterparts.

The cpu-only kfuncs (idle/any pick, cpumask iteration) have no cid
substitute. Their callers already moved to cmask scans against
qa_idle_cids and taskc->cpus_allowed in the prior patch, so the kfunc
calls drop here without behavior changes.

set_cmask is wired up via cmask_copy_from_kernel() to copy the
kernel-supplied cmask into the arena-resident taskc cmask. The
cpuperf monitor iterates the cid-form perf kfuncs.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Cheng-Yang Chou <yphbchou0911@gmail.com>
---
 tools/sched_ext/scx_qmap.bpf.c | 197 +++++++++++++++------------------
 tools/sched_ext/scx_qmap.c     |  14 ++-
 tools/sched_ext/scx_qmap.h     |   2 +-
 3 files changed, 99 insertions(+), 114 deletions(-)

diff --git a/tools/sched_ext/scx_qmap.bpf.c b/tools/sched_ext/scx_qmap.bpf.c
index bbb3922bafd7..499ef47b83b6 100644
--- a/tools/sched_ext/scx_qmap.bpf.c
+++ b/tools/sched_ext/scx_qmap.bpf.c
@@ -179,25 +179,24 @@ static int qmap_spin_lock(struct bpf_res_spin_lock *lock)
 }
 
 /*
- * Try prev_cpu's cid, then scan taskc->cpus_allowed AND qa_idle_cids
- * round-robin from prev_cid + 1. Atomic claim retries on race; bounded
- * by IDLE_PICK_RETRIES to keep the verifier's insn budget in check.
+ * Try prev_cid, then scan taskc->cpus_allowed AND qa_idle_cids round-robin
+ * from prev_cid + 1. Atomic claim retries on race; bounded by
+ * IDLE_PICK_RETRIES to keep the verifier's insn budget in check.
  */
 #define IDLE_PICK_RETRIES	16
 
-static s32 pick_direct_dispatch_cpu(struct task_struct *p, s32 prev_cpu,
+static s32 pick_direct_dispatch_cid(struct task_struct *p, s32 prev_cid,
 				    task_ctx_t *taskc)
 {
 	u32 nr_cids = scx_bpf_nr_cids();
-	s32 prev_cid, cid;
+	s32 cid;
 	u32 i;
 
 	if (!always_enq_immed && p->nr_cpus_allowed == 1)
-		return prev_cpu;
+		return prev_cid;
 
-	prev_cid = scx_bpf_cpu_to_cid(prev_cpu);
 	if (cmask_test_and_clear(qa_idle_cids, prev_cid))
-		return prev_cpu;
+		return prev_cid;
 
 	cid = prev_cid;
 	bpf_for(i, 0, IDLE_PICK_RETRIES) {
@@ -207,7 +206,7 @@ static s32 pick_direct_dispatch_cpu(struct task_struct *p, s32 prev_cpu,
 		if (cid >= nr_cids)
 			return -1;
 		if (cmask_test_and_clear(qa_idle_cids, cid))
-			return scx_bpf_cid_to_cpu(cid);
+			return cid;
 	}
 	return -1;
 }
@@ -308,25 +307,25 @@ static void qmap_fifo_remove(task_ctx_t *taskc)
 	bpf_res_spin_unlock(lock);
 }
 
-s32 BPF_STRUCT_OPS(qmap_select_cpu, struct task_struct *p,
-		   s32 prev_cpu, u64 wake_flags)
+s32 BPF_STRUCT_OPS(qmap_select_cid, struct task_struct *p,
+		   s32 prev_cid, u64 wake_flags)
 {
 	task_ctx_t *taskc;
-	s32 cpu;
+	s32 cid;
 
 	if (!(taskc = lookup_task_ctx(p)))
-		return prev_cpu;
+		return prev_cid;
 
 	if (p->scx.weight < 2 && !(p->flags & PF_KTHREAD))
-		return prev_cpu;
+		return prev_cid;
 
-	cpu = pick_direct_dispatch_cpu(p, prev_cpu, taskc);
+	cid = pick_direct_dispatch_cid(p, prev_cid, taskc);
 
-	if (cpu >= 0) {
+	if (cid >= 0) {
 		taskc->force_local = true;
-		return cpu;
+		return cid;
 	} else {
-		return prev_cpu;
+		return prev_cid;
 	}
 }
 
@@ -350,12 +349,12 @@ void BPF_STRUCT_OPS(qmap_enqueue, struct task_struct *p, u64 enq_flags)
 	static u32 user_cnt, kernel_cnt;
 	task_ctx_t *taskc;
 	int idx = weight_to_idx(p->scx.weight);
-	s32 cpu;
+	s32 cid;
 
 	if (enq_flags & SCX_ENQ_REENQ) {
 		__sync_fetch_and_add(&qa.nr_reenqueued, 1);
-		if (scx_bpf_task_cpu(p) == 0)
-			__sync_fetch_and_add(&qa.nr_reenqueued_cpu0, 1);
+		if (scx_bpf_task_cid(p) == 0)
+			__sync_fetch_and_add(&qa.nr_reenqueued_cid0, 1);
 	}
 
 	if (p->flags & PF_KTHREAD) {
@@ -388,14 +387,14 @@ void BPF_STRUCT_OPS(qmap_enqueue, struct task_struct *p, u64 enq_flags)
 
 		if (!(++immed_stress_cnt % immed_stress_nth)) {
 			taskc->force_local = false;
-			scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL_ON | scx_bpf_task_cpu(p),
+			scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL_ON | scx_bpf_task_cid(p),
 					   slice_ns, enq_flags);
 			return;
 		}
 	}
 
 	/*
-	 * If qmap_select_cpu() is telling us to or this is the last runnable
+	 * If qmap_select_cid() is telling us to or this is the last runnable
 	 * task on the CPU, enqueue locally.
 	 */
 	if (taskc->force_local) {
@@ -411,11 +410,11 @@ void BPF_STRUCT_OPS(qmap_enqueue, struct task_struct *p, u64 enq_flags)
 		return;
 	}
 
-	/* if select_cpu() wasn't called, try direct dispatch */
+	/* if select_cid() wasn't called, try direct dispatch */
 	if (!__COMPAT_is_enq_cpu_selected(enq_flags) &&
-	    (cpu = pick_direct_dispatch_cpu(p, scx_bpf_task_cpu(p), taskc)) >= 0) {
+	    (cid = pick_direct_dispatch_cid(p, scx_bpf_task_cid(p), taskc)) >= 0) {
 		__sync_fetch_and_add(&qa.nr_ddsp_from_enq, 1);
-		scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL_ON | cpu, slice_ns, enq_flags);
+		scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL_ON | cid, slice_ns, enq_flags);
 		return;
 	}
 
@@ -423,15 +422,16 @@ void BPF_STRUCT_OPS(qmap_enqueue, struct task_struct *p, u64 enq_flags)
 	 * If the task was re-enqueued due to the CPU being preempted by a
 	 * higher priority scheduling class, just re-enqueue the task directly
 	 * on the global DSQ. As we want another CPU to pick it up, find and
-	 * kick an idle CPU.
+	 * kick an idle cid.
 	 */
 	if (enq_flags & SCX_ENQ_REENQ) {
-		s32 cpu;
+		s32 cid;
 
 		scx_bpf_dsq_insert(p, SHARED_DSQ, 0, enq_flags);
-		cpu = scx_bpf_pick_idle_cpu(p->cpus_ptr, 0);
-		if (cpu >= 0)
-			scx_bpf_kick_cpu(cpu, SCX_KICK_IDLE);
+		cid = cmask_next_and_set_wrap(&taskc->cpus_allowed,
+					      qa_idle_cids, 0);
+		if (cid < scx_bpf_nr_cids())
+			scx_bpf_kick_cid(cid, SCX_KICK_IDLE);
 		return;
 	}
 
@@ -483,7 +483,8 @@ static void update_core_sched_head_seq(struct task_struct *p)
 static bool dispatch_highpri(bool from_timer)
 {
 	struct task_struct *p;
-	s32 this_cpu = bpf_get_smp_processor_id();
+	s32 this_cid = scx_bpf_this_cid();
+	u32 nr_cids = scx_bpf_nr_cids();
 
 	/* scan SHARED_DSQ and move highpri tasks to HIGHPRI_DSQ */
 	bpf_for_each(scx_dsq, p, SHARED_DSQ, 0) {
@@ -502,21 +503,29 @@ static bool dispatch_highpri(bool from_timer)
 	}
 
 	/*
-	 * Scan HIGHPRI_DSQ and dispatch until a task that can run on this CPU
-	 * is found.
+	 * Scan HIGHPRI_DSQ and dispatch until a task that can run here is
+	 * found. Prefer this_cid if the task allows it; otherwise RR-scan the
+	 * task's cpus_allowed starting after this_cid.
 	 */
 	bpf_for_each(scx_dsq, p, HIGHPRI_DSQ, 0) {
+		task_ctx_t *taskc;
 		bool dispatched = false;
-		s32 cpu;
+		s32 cid;
+
+		if (!(taskc = lookup_task_ctx(p)))
+			return false;
 
-		if (bpf_cpumask_test_cpu(this_cpu, p->cpus_ptr))
-			cpu = this_cpu;
+		if (cmask_test(&taskc->cpus_allowed, this_cid))
+			cid = this_cid;
 		else
-			cpu = scx_bpf_pick_any_cpu(p->cpus_ptr, 0);
+			cid = cmask_next_set_wrap(&taskc->cpus_allowed,
+						  this_cid + 1);
+		if (cid >= nr_cids)
+			continue;
 
-		if (scx_bpf_dsq_move(BPF_FOR_EACH_ITER, p, SCX_DSQ_LOCAL_ON | cpu,
+		if (scx_bpf_dsq_move(BPF_FOR_EACH_ITER, p, SCX_DSQ_LOCAL_ON | cid,
 				     SCX_ENQ_PREEMPT)) {
-			if (cpu == this_cpu) {
+			if (cid == this_cid) {
 				dispatched = true;
 				__sync_fetch_and_add(&qa.nr_expedited_local, 1);
 			} else {
@@ -535,7 +544,7 @@ static bool dispatch_highpri(bool from_timer)
 	return false;
 }
 
-void BPF_STRUCT_OPS(qmap_dispatch, s32 cpu, struct task_struct *prev)
+void BPF_STRUCT_OPS(qmap_dispatch, s32 cid, struct task_struct *prev)
 {
 	struct task_struct *p;
 	struct cpu_ctx __arena *cpuc;
@@ -563,7 +572,7 @@ void BPF_STRUCT_OPS(qmap_dispatch, s32 cpu, struct task_struct *prev)
 		}
 	}
 
-	cpuc = &qa.cpu_ctxs[bpf_get_smp_processor_id()];
+	cpuc = &qa.cpu_ctxs[scx_bpf_this_cid()];
 
 	for (i = 0; i < 5; i++) {
 		/* Advance the dispatch cursor and pick the fifo. */
@@ -628,8 +637,8 @@ void BPF_STRUCT_OPS(qmap_dispatch, s32 cpu, struct task_struct *prev)
 			 * document this class of issue -- other schedulers
 			 * seeing similar warnings can use this as a reference.
 			 */
-			if (!bpf_cpumask_test_cpu(cpu, p->cpus_ptr))
-				scx_bpf_kick_cpu(scx_bpf_task_cpu(p), 0);
+			if (!cmask_test(&taskc->cpus_allowed, cid))
+				scx_bpf_kick_cid(scx_bpf_task_cid(p), 0);
 
 			batch--;
 			cpuc->dsp_cnt--;
@@ -668,7 +677,7 @@ void BPF_STRUCT_OPS(qmap_dispatch, s32 cpu, struct task_struct *prev)
 
 void BPF_STRUCT_OPS(qmap_tick, struct task_struct *p)
 {
-	struct cpu_ctx __arena *cpuc = &qa.cpu_ctxs[bpf_get_smp_processor_id()];
+	struct cpu_ctx __arena *cpuc = &qa.cpu_ctxs[scx_bpf_this_cid()];
 	int idx;
 
 	/*
@@ -680,7 +689,7 @@ void BPF_STRUCT_OPS(qmap_tick, struct task_struct *p)
 	idx = weight_to_idx(cpuc->avg_weight);
 	cpuc->cpuperf_target = qidx_to_cpuperf_target[idx];
 
-	scx_bpf_cpuperf_set(scx_bpf_task_cpu(p), cpuc->cpuperf_target);
+	scx_bpf_cidperf_set(scx_bpf_task_cid(p), cpuc->cpuperf_target);
 }
 
 /*
@@ -828,9 +837,9 @@ void BPF_STRUCT_OPS(qmap_dump, struct scx_dump_ctx *dctx)
 	}
 }
 
-void BPF_STRUCT_OPS(qmap_dump_cpu, struct scx_dump_ctx *dctx, s32 cpu, bool idle)
+void BPF_STRUCT_OPS(qmap_dump_cid, struct scx_dump_ctx *dctx, s32 cid, bool idle)
 {
-	struct cpu_ctx __arena *cpuc = &qa.cpu_ctxs[cpu];
+	struct cpu_ctx __arena *cpuc = &qa.cpu_ctxs[cid];
 
 	if (suppress_dump || idle)
 		return;
@@ -881,46 +890,24 @@ void BPF_STRUCT_OPS(qmap_cgroup_set_bandwidth, struct cgroup *cgrp,
 			   cgrp->kn->id, period_us, quota_us, burst_us);
 }
 
-void BPF_STRUCT_OPS(qmap_update_idle, s32 cpu, bool idle)
+void BPF_STRUCT_OPS(qmap_update_idle, s32 cid, bool idle)
 {
-	s32 cid = scx_bpf_cpu_to_cid(cpu);
-
 	QMAP_TOUCH_ARENA();
-	if (cid < 0)
-		return;
 	if (idle)
 		cmask_set(qa_idle_cids, cid);
 	else
 		cmask_clear(qa_idle_cids, cid);
 }
 
-/*
- * The cpumask received here is kernel-address memory; walk it bit by bit
- * (bpf_cpumask_test_cpu handles the access), convert each set cpu to its
- * cid, and populate the arena-resident taskc cmask.
- */
-void BPF_STRUCT_OPS(qmap_set_cpumask, struct task_struct *p,
-		    const struct cpumask *cpumask)
+void BPF_STRUCT_OPS(qmap_set_cmask, struct task_struct *p,
+		    const struct scx_cmask *cmask)
 {
 	task_ctx_t *taskc;
-	u32 nr_cpu_ids = scx_bpf_nr_cpu_ids();
-	s32 cpu;
 
 	taskc = lookup_task_ctx(p);
 	if (!taskc)
 		return;
-
-	cmask_zero(&taskc->cpus_allowed);
-
-	bpf_for(cpu, 0, nr_cpu_ids) {
-		s32 cid;
-
-		if (!bpf_cpumask_test_cpu(cpu, cpumask))
-			continue;
-		cid = scx_bpf_cpu_to_cid(cpu);
-		if (cid >= 0)
-			__cmask_set(&taskc->cpus_allowed, cid);
-	}
+	cmask_copy_from_kernel(&taskc->cpus_allowed, cmask);
 }
 
 struct monitor_timer {
@@ -935,59 +922,49 @@ struct {
 } monitor_timer SEC(".maps");
 
 /*
- * Print out the min, avg and max performance levels of CPUs every second to
- * demonstrate the cpuperf interface.
+ * Aggregate cidperf across the first nr_online_cids cids. Post-hotplug
+ * the first-N-are-online invariant drifts, so some cap/cur values may
+ * be stale. For this demo monitor that's fine; the scheduler exits on
+ * the enable-time hotplug_seq mismatch and userspace restarts, which
+ * rebuilds the layout.
  */
 static void monitor_cpuperf(void)
 {
-	u32 nr_cpu_ids;
+	u32 nr_online = scx_bpf_nr_online_cids();
 	u64 cap_sum = 0, cur_sum = 0, cur_min = SCX_CPUPERF_ONE, cur_max = 0;
 	u64 target_sum = 0, target_min = SCX_CPUPERF_ONE, target_max = 0;
-	const struct cpumask *online;
-	int i, nr_online_cpus = 0;
-
-	nr_cpu_ids = scx_bpf_nr_cpu_ids();
-	online = scx_bpf_get_online_cpumask();
-
-	bpf_for(i, 0, nr_cpu_ids) {
-		struct cpu_ctx __arena *cpuc = &qa.cpu_ctxs[i];
-		u32 cap, cur;
+	s32 cid;
 
-		if (!bpf_cpumask_test_cpu(i, online))
-			continue;
-		nr_online_cpus++;
+	QMAP_TOUCH_ARENA();
 
-		/* collect the capacity and current cpuperf */
-		cap = scx_bpf_cpuperf_cap(i);
-		cur = scx_bpf_cpuperf_cur(i);
+	bpf_for(cid, 0, nr_online) {
+		struct cpu_ctx __arena *cpuc = &qa.cpu_ctxs[cid];
+		u32 cap = scx_bpf_cidperf_cap(cid);
+		u32 cur = scx_bpf_cidperf_cur(cid);
+		u32 target;
 
 		cur_min = cur < cur_min ? cur : cur_min;
 		cur_max = cur > cur_max ? cur : cur_max;
 
-		/*
-		 * $cur is relative to $cap. Scale it down accordingly so that
-		 * it's in the same scale as other CPUs and $cur_sum/$cap_sum
-		 * makes sense.
-		 */
-		cur_sum += cur * cap / SCX_CPUPERF_ONE;
+		cur_sum += (u64)cur * cap / SCX_CPUPERF_ONE;
 		cap_sum += cap;
 
-		/* collect target */
-		cur = cpuc->cpuperf_target;
-		target_sum += cur;
-		target_min = cur < target_min ? cur : target_min;
-		target_max = cur > target_max ? cur : target_max;
+		target = cpuc->cpuperf_target;
+		target_sum += target;
+		target_min = target < target_min ? target : target_min;
+		target_max = target > target_max ? target : target_max;
 	}
 
+	if (!nr_online || !cap_sum)
+		return;
+
 	qa.cpuperf_min = cur_min;
 	qa.cpuperf_avg = cur_sum * SCX_CPUPERF_ONE / cap_sum;
 	qa.cpuperf_max = cur_max;
 
 	qa.cpuperf_target_min = target_min;
-	qa.cpuperf_target_avg = target_sum / nr_online_cpus;
+	qa.cpuperf_target_avg = target_sum / nr_online;
 	qa.cpuperf_target_max = target_max;
-
-	scx_bpf_put_cpumask(online);
 }
 
 /*
@@ -1193,20 +1170,20 @@ void BPF_STRUCT_OPS(qmap_sub_detach, struct scx_sub_detach_args *args)
 	}
 }
 
-SCX_OPS_DEFINE(qmap_ops,
+SCX_OPS_CID_DEFINE(qmap_ops,
 	       .flags			= SCX_OPS_ENQ_EXITING | SCX_OPS_TID_TO_TASK,
-	       .select_cpu		= (void *)qmap_select_cpu,
+	       .select_cid		= (void *)qmap_select_cid,
 	       .enqueue			= (void *)qmap_enqueue,
 	       .dequeue			= (void *)qmap_dequeue,
 	       .dispatch		= (void *)qmap_dispatch,
 	       .tick			= (void *)qmap_tick,
 	       .core_sched_before	= (void *)qmap_core_sched_before,
-	       .set_cpumask		= (void *)qmap_set_cpumask,
+	       .set_cmask		= (void *)qmap_set_cmask,
 	       .update_idle		= (void *)qmap_update_idle,
 	       .init_task		= (void *)qmap_init_task,
 	       .exit_task		= (void *)qmap_exit_task,
 	       .dump			= (void *)qmap_dump,
-	       .dump_cpu		= (void *)qmap_dump_cpu,
+	       .dump_cid		= (void *)qmap_dump_cid,
 	       .dump_task		= (void *)qmap_dump_task,
 	       .cgroup_init		= (void *)qmap_cgroup_init,
 	       .cgroup_set_weight	= (void *)qmap_cgroup_set_weight,
diff --git a/tools/sched_ext/scx_qmap.c b/tools/sched_ext/scx_qmap.c
index 99408b1bb1ec..2cc10fd36bec 100644
--- a/tools/sched_ext/scx_qmap.c
+++ b/tools/sched_ext/scx_qmap.c
@@ -73,6 +73,14 @@ int main(int argc, char **argv)
 	libbpf_set_print(libbpf_print_fn);
 	signal(SIGINT, sigint_handler);
 	signal(SIGTERM, sigint_handler);
+
+	if (libbpf_num_possible_cpus() > SCX_QMAP_MAX_CPUS) {
+		fprintf(stderr,
+			"scx_qmap: %d possible CPUs exceeds compile-time cap %d; "
+			"rebuild with larger SCX_QMAP_MAX_CPUS\n",
+			libbpf_num_possible_cpus(), SCX_QMAP_MAX_CPUS);
+		return 1;
+	}
 restart:
 	optind = 1;
 	skel = SCX_OPS_OPEN(qmap_ops, scx_qmap);
@@ -162,9 +170,9 @@ int main(int argc, char **argv)
 		long nr_enqueued = qa->nr_enqueued;
 		long nr_dispatched = qa->nr_dispatched;
 
-		printf("stats  : enq=%lu dsp=%lu delta=%ld reenq/cpu0=%llu/%llu deq=%llu core=%llu enq_ddsp=%llu\n",
+		printf("stats  : enq=%lu dsp=%lu delta=%ld reenq/cid0=%llu/%llu deq=%llu core=%llu enq_ddsp=%llu\n",
 		       nr_enqueued, nr_dispatched, nr_enqueued - nr_dispatched,
-		       qa->nr_reenqueued, qa->nr_reenqueued_cpu0,
+		       qa->nr_reenqueued, qa->nr_reenqueued_cid0,
 		       qa->nr_dequeued,
 		       qa->nr_core_sched_execed,
 		       qa->nr_ddsp_from_enq);
@@ -173,7 +181,7 @@ int main(int argc, char **argv)
 		       qa->nr_expedited_remote,
 		       qa->nr_expedited_from_timer,
 		       qa->nr_expedited_lost);
-		if (__COMPAT_has_ksym("scx_bpf_cpuperf_cur"))
+		if (__COMPAT_has_ksym("scx_bpf_cidperf_cur"))
 			printf("cpuperf: cur min/avg/max=%u/%u/%u target min/avg/max=%u/%u/%u\n",
 			       qa->cpuperf_min,
 			       qa->cpuperf_avg,
diff --git a/tools/sched_ext/scx_qmap.h b/tools/sched_ext/scx_qmap.h
index 9d9af2ad90c6..d15a705d5ac5 100644
--- a/tools/sched_ext/scx_qmap.h
+++ b/tools/sched_ext/scx_qmap.h
@@ -45,7 +45,7 @@ struct qmap_fifo {
 
 struct qmap_arena {
 	/* userspace-visible stats */
-	__u64 nr_enqueued, nr_dispatched, nr_reenqueued, nr_reenqueued_cpu0;
+	__u64 nr_enqueued, nr_dispatched, nr_reenqueued, nr_reenqueued_cid0;
 	__u64 nr_dequeued, nr_ddsp_from_enq;
 	__u64 nr_core_sched_execed;
 	__u64 nr_expedited_local, nr_expedited_remote;
-- 
2.53.0


^ permalink raw reply related	[flat|nested] 3+ messages in thread
* [PATCHSET v2 REPOST sched_ext/for-7.2] sched_ext: Topological CPU IDs and cid-form struct_ops
@ 2026-04-24 17:27 Tejun Heo
  2026-04-24 17:27 ` [PATCH 16/17] tools/sched_ext: scx_qmap: Port to " Tejun Heo
  0 siblings, 1 reply; 3+ messages in thread
From: Tejun Heo @ 2026-04-24 17:27 UTC (permalink / raw)
  To: David Vernet, Andrea Righi, Changwoo Min
  Cc: sched-ext, emil, linux-kernel, Cheng-Yang Chou, Zhao Mengmeng,
	Tejun Heo

Hello,

Reposting v2 because the original send was not properly threaded -
each patch went out as a standalone top-level message. Content is
unchanged from the original v2.

Original v2: https://lore.kernel.org/r/20260424013220.2923402-1-tj@kernel.org

v2 of https://lore.kernel.org/r/20260421071945.3110084-1-tj@kernel.org

v2:
- Add ext-types.h first patch for early subsystem-wide type defs.
- cid: publish the cid tables with WRITE_ONCE / read with READ_ONCE;
  document the visibility contract.
- cid-kfuncs: NULL-guard scx_bpf_this_cid / scx_bpf_task_cid for
  TRACING/SYSCALL callers before any SCX sched has enabled.
- cid-struct-ops: use struct_size() for the set_cmask_scratch percpu
  alloc; cluster __scx_is_cid_type disable with __scx_enabled disable
  in scx_root_disable().
- cid-kfunc-filter: sync per-entry kfunc flags with each kfunc's
  primary BTF_ID_FLAGS() declaration (Zhao). pahole intersects flags
  across occurrences; omitting them drops the flags globally - the
  visible symptom was KF_IMPLICIT_ARGS getting cleared on
  scx_bpf_kick_cpu, leaking bpf_prog_aux into vmlinux.h.
- cmask: narrow to the helpers this series actually uses;
  cmask_copy_from_kernel contract and runtime guard.

This patchset introduces topological CPU IDs (cids) - dense,
topology-ordered cpu identifiers - and an alternative cid-form struct_ops
type that lets BPF schedulers operate in cid space directly.

Key pieces:

- cid space: scx_cid_init() walks nodes * LLCs * cores * threads and packs
  a dense cid mapping. The mapping can be overridden via
  scx_bpf_cid_override(). See "Topological CPU IDs" in ext_cid.h for the
  model.

- cmask: a base-windowed bitmap over cid space. Kernel and BPF helpers with
  identical semantics. Used by scx_qmap for per-task affinity and idle-cid
  tracking; meant to be the substrate for sub-sched cid allocation.

- bpf_sched_ext_ops_cid: a parallel struct_ops type whose callbacks take
  cids/cmasks instead of cpus/cpumasks. Kernel translates at the boundary
  via scx_cpu_arg() / scx_cpu_ret(); the two struct types share offsets up
  through @priv (verified by BUILD_BUG_ON) so the union view in scx_sched
  works without function-pointer casts. Sub-sched support is tied to
  cid-form: validate_ops() rejects cpu-form sub-scheds and cpu-form roots
  that expose sub_attach / sub_detach.

- cid-form kfuncs: scx_bpf_kick_cid, scx_bpf_cidperf_{cap,cur,set},
  scx_bpf_cid_curr, scx_bpf_task_cid, scx_bpf_this_cid,
  scx_bpf_nr_{cids,online_cids}, scx_bpf_cid_to_cpu, scx_bpf_cpu_to_cid.
  A cid-form program may not call cpu-only kfuncs (enforced at verifier
  load via scx_kfunc_context_filter); the reverse is intentionally
  permissive to ease migration.

- scx_qmap port: scx_qmap is converted to cid-form. It uses the cmask-based
  idle picker, per-task cid-space cpus_allowed, and cid-form kfuncs
  throughout. Sub-sched dispatching via scx_bpf_sub_dispatch() continues to
  work.

v2 re-tested on the 16-cpu QEMU: cid-form scx_qmap, cpu-form scx_simple,
cid<->cpu cycling, scx_qmap under stress-ng, hotplug auto-restart, and
sub-sched (root scx_qmap + cgroup-scoped scx_qmap child). Clean.

Based on sched_ext/for-7.2 (c2929bc21dce).

 0001-sched_ext-Add-ext_types.h-for-early-subsystem-wide-d.patch
 0002-sched_ext-Rename-ops_cpu_valid-to-scx_cpu_valid-and-.patch
 0003-sched_ext-Move-scx_exit-scx_error-and-friends-to-ext.patch
 0004-sched_ext-Shift-scx_kick_cpu-validity-check-to-scx_b.patch
 0005-sched_ext-Relocate-cpu_acquire-cpu_release-to-end-of.patch
 0006-sched_ext-Make-scx_enable-take-scx_enable_cmd.patch
 0007-sched_ext-Add-topological-CPU-IDs-cids.patch
 0008-sched_ext-Add-scx_bpf_cid_override-kfunc.patch
 0009-tools-sched_ext-Add-struct_size-helpers-to-common.bp.patch
 0010-sched_ext-Add-cmask-a-base-windowed-bitmap-over-cid-.patch
 0011-sched_ext-Add-cid-form-kfunc-wrappers-alongside-cpu-.patch
 0012-sched_ext-Add-bpf_sched_ext_ops_cid-struct_ops-type.patch
 0013-sched_ext-Forbid-cpu-form-kfuncs-from-cid-form-sched.patch
 0014-tools-sched_ext-scx_qmap-Restart-on-hotplug-instead-.patch
 0015-tools-sched_ext-scx_qmap-Add-cmask-based-idle-tracki.patch
 0016-tools-sched_ext-scx_qmap-Port-to-cid-form-struct_ops.patch
 0017-sched_ext-Require-cid-form-struct_ops-for-sub-sched-.patch

Git tree: git://git.kernel.org/pub/scm/linux/kernel/git/tj/sched_ext.git scx-cid-v2

 kernel/sched/build_policy.c              |   2 +
 kernel/sched/ext.c                       | 650 +++++++++++++++++++++++++----
 kernel/sched/ext_cid.c                   | 417 ++++++++++++++++++++
 kernel/sched/ext_cid.h                   | 164 ++++++++
 kernel/sched/ext_idle.c                  |   8 +-
 kernel/sched/ext_internal.h              | 203 +++++++---
 kernel/sched/ext_types.h                 | 104 +++++
 tools/sched_ext/include/scx/cid.bpf.h    | 597 ++++++++++++++++++++++++++++
 tools/sched_ext/include/scx/common.bpf.h |  23 ++
 tools/sched_ext/include/scx/compat.bpf.h |  24 ++
 tools/sched_ext/scx_qmap.bpf.c           | 306 ++++++++-------
 tools/sched_ext/scx_qmap.c               |  25 +-
 tools/sched_ext/scx_qmap.h               |   2 +-
 13 files changed, 2240 insertions(+), 285 deletions(-)

--
tejun

^ permalink raw reply	[flat|nested] 3+ messages in thread
* [PATCHSET v3 sched_ext/for-7.2] sched_ext: Topological CPU IDs and cid-form struct_ops
@ 2026-04-28 20:35 Tejun Heo
  2026-04-28 20:35 ` [PATCH 16/17] tools/sched_ext: scx_qmap: Port to " Tejun Heo
  0 siblings, 1 reply; 3+ messages in thread
From: Tejun Heo @ 2026-04-28 20:35 UTC (permalink / raw)
  To: David Vernet, Andrea Righi, Changwoo Min
  Cc: sched-ext, Emil Tsalapatis, linux-kernel, Tejun Heo

Hello,

v3 (all from the Sashiko AI review at
https://sashiko.dev/#/patchset/20260424172721.3458520-1-tj%40kernel.org):

- cid: drop leaked cpus_read_lock() on scx_cid_init() failure;
  BUILD_BUG_ON tightened to NR_CPUS<=8192 to match the BPF cmask
  helpers' CMASK_MAX_WORDS coverage.
- bpf-struct-size: use offsetof() in struct_size() to match the
  kernel <linux/overflow.h> macro semantics (no inflation from
  trailing struct padding).
- cmask: cmask_copy_from_kernel() validates src->base==0 via
  probe-read; nr_bits check is bit-level rather than rounded-up
  word-count.
- cid-qmap-idle: qmap_init() refuses to load when scx_bpf_nr_cids()
  exceeds SCX_QMAP_MAX_CPUS; the task_ctx flex array would otherwise
  overflow into the next slab entry.

v2: https://lore.kernel.org/r/20260424172721.3458520-1-tj@kernel.org
v1: https://lore.kernel.org/r/20260421071945.3110084-1-tj@kernel.org

This patchset introduces topological CPU IDs (cids) - dense,
topology-ordered cpu identifiers - and an alternative cid-form struct_ops
type that lets BPF schedulers operate in cid space directly.

Key pieces:

- cid space: scx_cid_init() walks nodes * LLCs * cores * threads and packs
  a dense cid mapping. The mapping can be overridden via
  scx_bpf_cid_override(). See "Topological CPU IDs" in ext_cid.h for the
  model.

- cmask: a base-windowed bitmap over cid space. Kernel and BPF helpers with
  identical semantics. Used by scx_qmap for per-task affinity and idle-cid
  tracking; meant to be the substrate for sub-sched cid allocation.

- bpf_sched_ext_ops_cid: a parallel struct_ops type whose callbacks take
  cids/cmasks instead of cpus/cpumasks. Kernel translates at the boundary
  via scx_cpu_arg() / scx_cpu_ret(); the two struct types share offsets up
  through @priv (verified by BUILD_BUG_ON) so the union view in scx_sched
  works without function-pointer casts. Sub-sched support is tied to
  cid-form: validate_ops() rejects cpu-form sub-scheds and cpu-form roots
  that expose sub_attach / sub_detach.

- cid-form kfuncs: scx_bpf_kick_cid, scx_bpf_cidperf_{cap,cur,set},
  scx_bpf_cid_curr, scx_bpf_task_cid, scx_bpf_this_cid,
  scx_bpf_nr_{cids,online_cids}, scx_bpf_cid_to_cpu, scx_bpf_cpu_to_cid.
  A cid-form program may not call cpu-only kfuncs (enforced at verifier
  load via scx_kfunc_context_filter); the reverse is intentionally
  permissive to ease migration.

- scx_qmap port: scx_qmap is converted to cid-form. It uses the cmask-based
  idle picker, per-task cid-space cpus_allowed, and cid-form kfuncs
  throughout. Sub-sched dispatching via scx_bpf_sub_dispatch() continues to
  work.

v3 re-tested on the 16-cpu QEMU: cid-form scx_qmap under stress-ng plus
reload cycles, hotplug auto-restart, and sub-sched (root scx_qmap +
cgroup-scoped scx_qmap child). Clean.

Based on sched_ext/for-7.2 (4939721aad2e).

 0001-sched_ext-Add-ext_types.h-for-early-subsystem-wide-d.patch
 0002-sched_ext-Rename-ops_cpu_valid-to-scx_cpu_valid-and-.patch
 0003-sched_ext-Move-scx_exit-scx_error-and-friends-to-ext.patch
 0004-sched_ext-Shift-scx_kick_cpu-validity-check-to-scx_b.patch
 0005-sched_ext-Relocate-cpu_acquire-cpu_release-to-end-of.patch
 0006-sched_ext-Make-scx_enable-take-scx_enable_cmd.patch
 0007-sched_ext-Add-topological-CPU-IDs-cids.patch
 0008-sched_ext-Add-scx_bpf_cid_override-kfunc.patch
 0009-tools-sched_ext-Add-struct_size-helpers-to-common.bp.patch
 0010-sched_ext-Add-cmask-a-base-windowed-bitmap-over-cid-.patch
 0011-sched_ext-Add-cid-form-kfunc-wrappers-alongside-cpu-.patch
 0012-sched_ext-Add-bpf_sched_ext_ops_cid-struct_ops-type.patch
 0013-sched_ext-Forbid-cpu-form-kfuncs-from-cid-form-sched.patch
 0014-tools-sched_ext-scx_qmap-Restart-on-hotplug-instead-.patch
 0015-tools-sched_ext-scx_qmap-Add-cmask-based-idle-tracki.patch
 0016-tools-sched_ext-scx_qmap-Port-to-cid-form-struct_ops.patch
 0017-sched_ext-Require-cid-form-struct_ops-for-sub-sched-.patch

Git tree: git://git.kernel.org/pub/scm/linux/kernel/git/tj/sched_ext.git scx-cid-v3

 kernel/sched/build_policy.c              |   3 +
 kernel/sched/ext.c                       | 651 ++++++++++++++++++++++++++----
 kernel/sched/ext_cid.c                   | 409 +++++++++++++++++++
 kernel/sched/ext_cid.h                   | 164 ++++++++
 kernel/sched/ext_idle.c                  |   8 +-
 kernel/sched/ext_internal.h              | 205 +++++++---
 kernel/sched/ext_types.h                 | 104 +++++
 tools/sched_ext/include/scx/cid.bpf.h    | 667 +++++++++++++++++++++++++++++++
 tools/sched_ext/include/scx/common.bpf.h |  23 ++
 tools/sched_ext/include/scx/compat.bpf.h |  24 ++
 tools/sched_ext/scx_qmap.bpf.c           | 346 +++++++++-------
 tools/sched_ext/scx_qmap.c               |  70 +++-
 tools/sched_ext/scx_qmap.h               |   2 +-
 13 files changed, 2391 insertions(+), 285 deletions(-)

Thanks.

--
tejun

^ permalink raw reply	[flat|nested] 3+ messages in thread

end of thread, other threads:[~2026-04-28 20:36 UTC | newest]

Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-04-24  1:32 [PATCH 16/17] tools/sched_ext: scx_qmap: Port to cid-form struct_ops Tejun Heo
  -- strict thread matches above, loose matches on Subject: below --
2026-04-24 17:27 [PATCHSET v2 REPOST sched_ext/for-7.2] sched_ext: Topological CPU IDs and " Tejun Heo
2026-04-24 17:27 ` [PATCH 16/17] tools/sched_ext: scx_qmap: Port to " Tejun Heo
2026-04-28 20:35 [PATCHSET v3 sched_ext/for-7.2] sched_ext: Topological CPU IDs and " Tejun Heo
2026-04-28 20:35 ` [PATCH 16/17] tools/sched_ext: scx_qmap: Port to " Tejun Heo

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox