[PATCH 14/17] tools/sched_ext: scx_qmap: Restart on hotplug instead of cpu_online/offline

[PATCH 14/17] tools/sched_ext: scx_qmap: Restart on hotplug instead of cpu_online/offline

[Tejun Heo]

The cid mapping is built from the online cpu set at scheduler enable
and stays valid for that set; routine hotplug invalidates it. The
default cid behavior is to restart the scheduler so the mapping gets
rebuilt against the new online set, and that requires not implementing
cpu_online / cpu_offline (which suppress the kernel's ACT_RESTART).

Drop the two ops along with their print_cpus() helper - the cluster
view was only useful as a hotplug demo and is meaningless over the
dense cid space the scheduler will move to. Wire main() to handle the
ACT_RESTART exit by reopening the skel and reattaching, matching the
pattern in scx_simple / scx_central / scx_flatcg etc. Reset optind so
getopt re-parses argv into the fresh skel rodata each iteration.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Cheng-Yang Chou <yphbchou0911@gmail.com>
---
 tools/sched_ext/scx_qmap.bpf.c | 62 ----------------------------------
 tools/sched_ext/scx_qmap.c     | 13 +++----
 2 files changed, 7 insertions(+), 68 deletions(-)

diff --git a/tools/sched_ext/scx_qmap.bpf.c b/tools/sched_ext/scx_qmap.bpf.c
index ba4879031dac..78a1dd118c7e 100644
--- a/tools/sched_ext/scx_qmap.bpf.c
+++ b/tools/sched_ext/scx_qmap.bpf.c
@@ -843,63 +843,6 @@ void BPF_STRUCT_OPS(qmap_cgroup_set_bandwidth, struct cgroup *cgrp,
 			   cgrp->kn->id, period_us, quota_us, burst_us);
 }
 
-/*
- * Print out the online and possible CPU map using bpf_printk() as a
- * demonstration of using the cpumask kfuncs and ops.cpu_on/offline().
- */
-static void print_cpus(void)
-{
-	const struct cpumask *possible, *online;
-	s32 cpu;
-	char buf[128] = "", *p;
-	int idx;
-
-	possible = scx_bpf_get_possible_cpumask();
-	online = scx_bpf_get_online_cpumask();
-
-	idx = 0;
-	bpf_for(cpu, 0, scx_bpf_nr_cpu_ids()) {
-		if (!(p = MEMBER_VPTR(buf, [idx++])))
-			break;
-		if (bpf_cpumask_test_cpu(cpu, online))
-			*p++ = 'O';
-		else if (bpf_cpumask_test_cpu(cpu, possible))
-			*p++ = 'X';
-		else
-			*p++ = ' ';
-
-		if ((cpu & 7) == 7) {
-			if (!(p = MEMBER_VPTR(buf, [idx++])))
-				break;
-			*p++ = '|';
-		}
-	}
-	buf[sizeof(buf) - 1] = '\0';
-
-	scx_bpf_put_cpumask(online);
-	scx_bpf_put_cpumask(possible);
-
-	bpf_printk("CPUS: |%s", buf);
-}
-
-void BPF_STRUCT_OPS(qmap_cpu_online, s32 cpu)
-{
-	if (print_msgs) {
-		bpf_printk("CPU %d coming online", cpu);
-		/* @cpu is already online at this point */
-		print_cpus();
-	}
-}
-
-void BPF_STRUCT_OPS(qmap_cpu_offline, s32 cpu)
-{
-	if (print_msgs) {
-		bpf_printk("CPU %d going offline", cpu);
-		/* @cpu is still online at this point */
-		print_cpus();
-	}
-}
-
 struct monitor_timer {
 	struct bpf_timer timer;
 };
@@ -1078,9 +1021,6 @@ s32 BPF_STRUCT_OPS_SLEEPABLE(qmap_init)
 		slab[i].next_free = (i + 1 < max_tasks) ? &slab[i + 1] : NULL;
 	qa.task_free_head = &slab[0];
 
-	if (print_msgs && !sub_cgroup_id)
-		print_cpus();
-
 	ret = scx_bpf_create_dsq(SHARED_DSQ, -1);
 	if (ret) {
 		scx_bpf_error("failed to create DSQ %d (%d)", SHARED_DSQ, ret);
@@ -1174,8 +1114,6 @@ SCX_OPS_DEFINE(qmap_ops,
 	       .cgroup_set_bandwidth	= (void *)qmap_cgroup_set_bandwidth,
 	       .sub_attach		= (void *)qmap_sub_attach,
 	       .sub_detach		= (void *)qmap_sub_detach,
-	       .cpu_online		= (void *)qmap_cpu_online,
-	       .cpu_offline		= (void *)qmap_cpu_offline,
 	       .init			= (void *)qmap_init,
 	       .exit			= (void *)qmap_exit,
 	       .timeout_ms		= 5000U,
diff --git a/tools/sched_ext/scx_qmap.c b/tools/sched_ext/scx_qmap.c
index 725c4880058d..99408b1bb1ec 100644
--- a/tools/sched_ext/scx_qmap.c
+++ b/tools/sched_ext/scx_qmap.c
@@ -67,12 +67,14 @@ int main(int argc, char **argv)
 	struct bpf_link *link;
 	struct qmap_arena *qa;
 	__u32 test_error_cnt = 0;
+	__u64 ecode;
 	int opt;
 
 	libbpf_set_print(libbpf_print_fn);
 	signal(SIGINT, sigint_handler);
 	signal(SIGTERM, sigint_handler);
-
+restart:
+	optind = 1;
 	skel = SCX_OPS_OPEN(qmap_ops, scx_qmap);
 
 	skel->rodata->slice_ns = __COMPAT_ENUM_OR_ZERO("scx_public_consts", "SCX_SLICE_DFL");
@@ -184,11 +186,10 @@ int main(int argc, char **argv)
 	}
 
 	bpf_link__destroy(link);
-	UEI_REPORT(skel, uei);
+	ecode = UEI_REPORT(skel, uei);
 	scx_qmap__destroy(skel);
-	/*
-	 * scx_qmap implements ops.cpu_on/offline() and doesn't need to restart
-	 * on CPU hotplug events.
-	 */
+
+	if (UEI_ECODE_RESTART(ecode))
+		goto restart;
 	return 0;
 }
-- 
2.53.0

[PATCH 14/17] tools/sched_ext: scx_qmap: Restart on hotplug instead of cpu_online/offline

[Tejun Heo]

The cid mapping is built from the online cpu set at scheduler enable
and stays valid for that set; routine hotplug invalidates it. The
default cid behavior is to restart the scheduler so the mapping gets
rebuilt against the new online set, and that requires not implementing
cpu_online / cpu_offline (which suppress the kernel's ACT_RESTART).

Drop the two ops along with their print_cpus() helper - the cluster
view was only useful as a hotplug demo and is meaningless over the
dense cid space the scheduler will move to. Wire main() to handle the
ACT_RESTART exit by reopening the skel and reattaching, matching the
pattern in scx_simple / scx_central / scx_flatcg etc. Reset optind so
getopt re-parses argv into the fresh skel rodata each iteration.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Cheng-Yang Chou <yphbchou0911@gmail.com>
---
 tools/sched_ext/scx_qmap.bpf.c | 62 ----------------------------------
 tools/sched_ext/scx_qmap.c     | 13 +++----
 2 files changed, 7 insertions(+), 68 deletions(-)

diff --git a/tools/sched_ext/scx_qmap.bpf.c b/tools/sched_ext/scx_qmap.bpf.c
index ba4879031dac..78a1dd118c7e 100644
--- a/tools/sched_ext/scx_qmap.bpf.c
+++ b/tools/sched_ext/scx_qmap.bpf.c
@@ -843,63 +843,6 @@ void BPF_STRUCT_OPS(qmap_cgroup_set_bandwidth, struct cgroup *cgrp,
 			   cgrp->kn->id, period_us, quota_us, burst_us);
 }
 
-/*
- * Print out the online and possible CPU map using bpf_printk() as a
- * demonstration of using the cpumask kfuncs and ops.cpu_on/offline().
- */
-static void print_cpus(void)
-{
-	const struct cpumask *possible, *online;
-	s32 cpu;
-	char buf[128] = "", *p;
-	int idx;
-
-	possible = scx_bpf_get_possible_cpumask();
-	online = scx_bpf_get_online_cpumask();
-
-	idx = 0;
-	bpf_for(cpu, 0, scx_bpf_nr_cpu_ids()) {
-		if (!(p = MEMBER_VPTR(buf, [idx++])))
-			break;
-		if (bpf_cpumask_test_cpu(cpu, online))
-			*p++ = 'O';
-		else if (bpf_cpumask_test_cpu(cpu, possible))
-			*p++ = 'X';
-		else
-			*p++ = ' ';
-
-		if ((cpu & 7) == 7) {
-			if (!(p = MEMBER_VPTR(buf, [idx++])))
-				break;
-			*p++ = '|';
-		}
-	}
-	buf[sizeof(buf) - 1] = '\0';
-
-	scx_bpf_put_cpumask(online);
-	scx_bpf_put_cpumask(possible);
-
-	bpf_printk("CPUS: |%s", buf);
-}
-
-void BPF_STRUCT_OPS(qmap_cpu_online, s32 cpu)
-{
-	if (print_msgs) {
-		bpf_printk("CPU %d coming online", cpu);
-		/* @cpu is already online at this point */
-		print_cpus();
-	}
-}
-
-void BPF_STRUCT_OPS(qmap_cpu_offline, s32 cpu)
-{
-	if (print_msgs) {
-		bpf_printk("CPU %d going offline", cpu);
-		/* @cpu is still online at this point */
-		print_cpus();
-	}
-}
-
 struct monitor_timer {
 	struct bpf_timer timer;
 };
@@ -1078,9 +1021,6 @@ s32 BPF_STRUCT_OPS_SLEEPABLE(qmap_init)
 		slab[i].next_free = (i + 1 < max_tasks) ? &slab[i + 1] : NULL;
 	qa.task_free_head = &slab[0];
 
-	if (print_msgs && !sub_cgroup_id)
-		print_cpus();
-
 	ret = scx_bpf_create_dsq(SHARED_DSQ, -1);
 	if (ret) {
 		scx_bpf_error("failed to create DSQ %d (%d)", SHARED_DSQ, ret);
@@ -1174,8 +1114,6 @@ SCX_OPS_DEFINE(qmap_ops,
 	       .cgroup_set_bandwidth	= (void *)qmap_cgroup_set_bandwidth,
 	       .sub_attach		= (void *)qmap_sub_attach,
 	       .sub_detach		= (void *)qmap_sub_detach,
-	       .cpu_online		= (void *)qmap_cpu_online,
-	       .cpu_offline		= (void *)qmap_cpu_offline,
 	       .init			= (void *)qmap_init,
 	       .exit			= (void *)qmap_exit,
 	       .timeout_ms		= 5000U,
diff --git a/tools/sched_ext/scx_qmap.c b/tools/sched_ext/scx_qmap.c
index 725c4880058d..99408b1bb1ec 100644
--- a/tools/sched_ext/scx_qmap.c
+++ b/tools/sched_ext/scx_qmap.c
@@ -67,12 +67,14 @@ int main(int argc, char **argv)
 	struct bpf_link *link;
 	struct qmap_arena *qa;
 	__u32 test_error_cnt = 0;
+	__u64 ecode;
 	int opt;
 
 	libbpf_set_print(libbpf_print_fn);
 	signal(SIGINT, sigint_handler);
 	signal(SIGTERM, sigint_handler);
-
+restart:
+	optind = 1;
 	skel = SCX_OPS_OPEN(qmap_ops, scx_qmap);
 
 	skel->rodata->slice_ns = __COMPAT_ENUM_OR_ZERO("scx_public_consts", "SCX_SLICE_DFL");
@@ -184,11 +186,10 @@ int main(int argc, char **argv)
 	}
 
 	bpf_link__destroy(link);
-	UEI_REPORT(skel, uei);
+	ecode = UEI_REPORT(skel, uei);
 	scx_qmap__destroy(skel);
-	/*
-	 * scx_qmap implements ops.cpu_on/offline() and doesn't need to restart
-	 * on CPU hotplug events.
-	 */
+
+	if (UEI_ECODE_RESTART(ecode))
+		goto restart;
 	return 0;
 }
-- 
2.53.0

[PATCHSET v3 sched_ext/for-7.2] sched_ext: Topological CPU IDs and cid-form struct_ops

[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

[PATCH 01/17] sched_ext: Add ext_types.h for early subsystem-wide defs

[Tejun Heo]

Introduce kernel/sched/ext_types.h as the early-def header for the
sched_ext compilation unit. Included from kernel/sched/build_policy.c
before ext_internal.h so every later header and source in the unit
sees its content without re-inclusion. Later patches add their types
here (struct scx_cid_topo, scx_cmask, scx_cid_shard, etc.) so the
subsystem has one place to stash types shared across the TU.

Move enum scx_consts (SCX_DSP_DFL_MAX_BATCH, SCX_WATCHDOG_MAX_TIMEOUT,
SCX_SUB_MAX_DEPTH, etc.) here as the initial content. Ops-facing
content stays in ext_internal.h.

Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/sched/build_policy.c |  1 +
 kernel/sched/ext_internal.h | 32 ---------------------------
 kernel/sched/ext_types.h    | 43 +++++++++++++++++++++++++++++++++++++
 3 files changed, 44 insertions(+), 32 deletions(-)
 create mode 100644 kernel/sched/ext_types.h

diff --git a/kernel/sched/build_policy.c b/kernel/sched/build_policy.c
index ffb386889218..1d92f7d7a19f 100644
--- a/kernel/sched/build_policy.c
+++ b/kernel/sched/build_policy.c
@@ -59,6 +59,7 @@
 
 #ifdef CONFIG_SCHED_CLASS_EXT
 # include <linux/btf_ids.h>
+# include "ext_types.h"
 # include "ext_internal.h"
 # include "ext_idle.h"
 # include "ext.c"
diff --git a/kernel/sched/ext_internal.h b/kernel/sched/ext_internal.h
index a54903bb74b3..1b2ea6fa9fd6 100644
--- a/kernel/sched/ext_internal.h
+++ b/kernel/sched/ext_internal.h
@@ -8,38 +8,6 @@
 #define SCX_OP_IDX(op)		(offsetof(struct sched_ext_ops, op) / sizeof(void (*)(void)))
 #define SCX_MOFF_IDX(moff)	((moff) / sizeof(void (*)(void)))
 
-enum scx_consts {
-	SCX_DSP_DFL_MAX_BATCH		= 32,
-	SCX_DSP_MAX_LOOPS		= 32,
-	SCX_WATCHDOG_MAX_TIMEOUT	= 30 * HZ,
-
-	/* per-CPU chunk size for p->scx.tid allocation, see scx_alloc_tid() */
-	SCX_TID_CHUNK			= 1024,
-
-	SCX_EXIT_BT_LEN			= 64,
-	SCX_EXIT_MSG_LEN		= 1024,
-	SCX_EXIT_DUMP_DFL_LEN		= 32768,
-
-	SCX_CPUPERF_ONE			= SCHED_CAPACITY_SCALE,
-
-	/*
-	 * Iterating all tasks may take a while. Periodically drop
-	 * scx_tasks_lock to avoid causing e.g. CSD and RCU stalls.
-	 */
-	SCX_TASK_ITER_BATCH		= 32,
-
-	SCX_BYPASS_HOST_NTH		= 2,
-
-	SCX_BYPASS_LB_DFL_INTV_US	= 500 * USEC_PER_MSEC,
-	SCX_BYPASS_LB_DONOR_PCT		= 125,
-	SCX_BYPASS_LB_MIN_DELTA_DIV	= 4,
-	SCX_BYPASS_LB_BATCH		= 256,
-
-	SCX_REENQ_LOCAL_MAX_REPEAT	= 256,
-
-	SCX_SUB_MAX_DEPTH		= 4,
-};
-
 enum scx_exit_kind {
 	SCX_EXIT_NONE,
 	SCX_EXIT_DONE,
diff --git a/kernel/sched/ext_types.h b/kernel/sched/ext_types.h
new file mode 100644
index 000000000000..19299ec3920e
--- /dev/null
+++ b/kernel/sched/ext_types.h
@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Early sched_ext type definitions.
+ *
+ * Copyright (c) 2026 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2026 Tejun Heo <tj@kernel.org>
+ */
+#ifndef _KERNEL_SCHED_EXT_TYPES_H
+#define _KERNEL_SCHED_EXT_TYPES_H
+
+enum scx_consts {
+	SCX_DSP_DFL_MAX_BATCH		= 32,
+	SCX_DSP_MAX_LOOPS		= 32,
+	SCX_WATCHDOG_MAX_TIMEOUT	= 30 * HZ,
+
+	/* per-CPU chunk size for p->scx.tid allocation, see scx_alloc_tid() */
+	SCX_TID_CHUNK			= 1024,
+
+	SCX_EXIT_BT_LEN			= 64,
+	SCX_EXIT_MSG_LEN		= 1024,
+	SCX_EXIT_DUMP_DFL_LEN		= 32768,
+
+	SCX_CPUPERF_ONE			= SCHED_CAPACITY_SCALE,
+
+	/*
+	 * Iterating all tasks may take a while. Periodically drop
+	 * scx_tasks_lock to avoid causing e.g. CSD and RCU stalls.
+	 */
+	SCX_TASK_ITER_BATCH		= 32,
+
+	SCX_BYPASS_HOST_NTH		= 2,
+
+	SCX_BYPASS_LB_DFL_INTV_US	= 500 * USEC_PER_MSEC,
+	SCX_BYPASS_LB_DONOR_PCT		= 125,
+	SCX_BYPASS_LB_MIN_DELTA_DIV	= 4,
+	SCX_BYPASS_LB_BATCH		= 256,
+
+	SCX_REENQ_LOCAL_MAX_REPEAT	= 256,
+
+	SCX_SUB_MAX_DEPTH		= 4,
+};
+
+#endif /* _KERNEL_SCHED_EXT_TYPES_H */
-- 
2.54.0

[PATCH 02/17] sched_ext: Rename ops_cpu_valid() to scx_cpu_valid() and expose it

[Tejun Heo]

Rename the static ext.c helper and declare it in ext_internal.h so
ext_idle.c and the upcoming cid code can call it directly instead of
relying on build_policy.c textual inclusion.

Pure rename and visibility change.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Cheng-Yang Chou <yphbchou0911@gmail.com>
---
 kernel/sched/ext.c          | 22 +++++++++++-----------
 kernel/sched/ext_idle.c     |  6 +++---
 kernel/sched/ext_internal.h |  2 ++
 3 files changed, 16 insertions(+), 14 deletions(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 11893f00be06..980231c547ec 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -1062,7 +1062,7 @@ static inline bool __cpu_valid(s32 cpu)
 }
 
 /**
- * ops_cpu_valid - Verify a cpu number, to be used on ops input args
+ * scx_cpu_valid - Verify a cpu number, to be used on ops input args
  * @sch: scx_sched to abort on error
  * @cpu: cpu number which came from a BPF ops
  * @where: extra information reported on error
@@ -1071,7 +1071,7 @@ static inline bool __cpu_valid(s32 cpu)
  * Verify that it is in range and one of the possible cpus. If invalid, trigger
  * an ops error.
  */
-static bool ops_cpu_valid(struct scx_sched *sch, s32 cpu, const char *where)
+bool scx_cpu_valid(struct scx_sched *sch, s32 cpu, const char *where)
 {
 	if (__cpu_valid(cpu)) {
 		return true;
@@ -1686,7 +1686,7 @@ static struct scx_dispatch_q *find_dsq_for_dispatch(struct scx_sched *sch,
 	if ((dsq_id & SCX_DSQ_LOCAL_ON) == SCX_DSQ_LOCAL_ON) {
 		s32 cpu = dsq_id & SCX_DSQ_LOCAL_CPU_MASK;
 
-		if (!ops_cpu_valid(sch, cpu, "in SCX_DSQ_LOCAL_ON dispatch verdict"))
+		if (!scx_cpu_valid(sch, cpu, "in SCX_DSQ_LOCAL_ON dispatch verdict"))
 			return find_global_dsq(sch, tcpu);
 
 		return &cpu_rq(cpu)->scx.local_dsq;
@@ -3269,7 +3269,7 @@ static int select_task_rq_scx(struct task_struct *p, int prev_cpu, int wake_flag
 		this_rq()->scx.in_select_cpu = false;
 		p->scx.selected_cpu = cpu;
 		*ddsp_taskp = NULL;
-		if (ops_cpu_valid(sch, cpu, "from ops.select_cpu()"))
+		if (scx_cpu_valid(sch, cpu, "from ops.select_cpu()"))
 			return cpu;
 		else
 			return prev_cpu;
@@ -8791,7 +8791,7 @@ static void scx_kick_cpu(struct scx_sched *sch, s32 cpu, u64 flags)
 	struct rq *this_rq;
 	unsigned long irq_flags;
 
-	if (!ops_cpu_valid(sch, cpu, NULL))
+	if (!scx_cpu_valid(sch, cpu, NULL))
 		return;
 
 	local_irq_save(irq_flags);
@@ -8888,7 +8888,7 @@ __bpf_kfunc s32 scx_bpf_dsq_nr_queued(u64 dsq_id, const struct bpf_prog_aux *aux
 	} else if ((dsq_id & SCX_DSQ_LOCAL_ON) == SCX_DSQ_LOCAL_ON) {
 		s32 cpu = dsq_id & SCX_DSQ_LOCAL_CPU_MASK;
 
-		if (ops_cpu_valid(sch, cpu, NULL)) {
+		if (scx_cpu_valid(sch, cpu, NULL)) {
 			ret = READ_ONCE(cpu_rq(cpu)->scx.local_dsq.nr);
 			goto out;
 		}
@@ -9277,7 +9277,7 @@ __bpf_kfunc u32 scx_bpf_cpuperf_cap(s32 cpu, const struct bpf_prog_aux *aux)
 	guard(rcu)();
 
 	sch = scx_prog_sched(aux);
-	if (likely(sch) && ops_cpu_valid(sch, cpu, NULL))
+	if (likely(sch) && scx_cpu_valid(sch, cpu, NULL))
 		return arch_scale_cpu_capacity(cpu);
 	else
 		return SCX_CPUPERF_ONE;
@@ -9305,7 +9305,7 @@ __bpf_kfunc u32 scx_bpf_cpuperf_cur(s32 cpu, const struct bpf_prog_aux *aux)
 	guard(rcu)();
 
 	sch = scx_prog_sched(aux);
-	if (likely(sch) && ops_cpu_valid(sch, cpu, NULL))
+	if (likely(sch) && scx_cpu_valid(sch, cpu, NULL))
 		return arch_scale_freq_capacity(cpu);
 	else
 		return SCX_CPUPERF_ONE;
@@ -9341,7 +9341,7 @@ __bpf_kfunc void scx_bpf_cpuperf_set(s32 cpu, u32 perf, const struct bpf_prog_au
 		return;
 	}
 
-	if (ops_cpu_valid(sch, cpu, NULL)) {
+	if (scx_cpu_valid(sch, cpu, NULL)) {
 		struct rq *rq = cpu_rq(cpu), *locked_rq = scx_locked_rq();
 		struct rq_flags rf;
 
@@ -9454,7 +9454,7 @@ __bpf_kfunc struct rq *scx_bpf_cpu_rq(s32 cpu, const struct bpf_prog_aux *aux)
 	if (unlikely(!sch))
 		return NULL;
 
-	if (!ops_cpu_valid(sch, cpu, NULL))
+	if (!scx_cpu_valid(sch, cpu, NULL))
 		return NULL;
 
 	if (!sch->warned_deprecated_rq) {
@@ -9511,7 +9511,7 @@ __bpf_kfunc struct task_struct *scx_bpf_cpu_curr(s32 cpu, const struct bpf_prog_
 	if (unlikely(!sch))
 		return NULL;
 
-	if (!ops_cpu_valid(sch, cpu, NULL))
+	if (!scx_cpu_valid(sch, cpu, NULL))
 		return NULL;
 
 	return rcu_dereference(cpu_rq(cpu)->curr);
diff --git a/kernel/sched/ext_idle.c b/kernel/sched/ext_idle.c
index f0f4d9500997..860c4634f60e 100644
--- a/kernel/sched/ext_idle.c
+++ b/kernel/sched/ext_idle.c
@@ -916,7 +916,7 @@ static s32 select_cpu_from_kfunc(struct scx_sched *sch, struct task_struct *p,
 	bool we_locked = false;
 	s32 cpu;
 
-	if (!ops_cpu_valid(sch, prev_cpu, NULL))
+	if (!scx_cpu_valid(sch, prev_cpu, NULL))
 		return -EINVAL;
 
 	if (!check_builtin_idle_enabled(sch))
@@ -989,7 +989,7 @@ __bpf_kfunc s32 scx_bpf_cpu_node(s32 cpu, const struct bpf_prog_aux *aux)
 	guard(rcu)();
 
 	sch = scx_prog_sched(aux);
-	if (unlikely(!sch) || !ops_cpu_valid(sch, cpu, NULL))
+	if (unlikely(!sch) || !scx_cpu_valid(sch, cpu, NULL))
 		return NUMA_NO_NODE;
 	return cpu_to_node(cpu);
 }
@@ -1271,7 +1271,7 @@ __bpf_kfunc bool scx_bpf_test_and_clear_cpu_idle(s32 cpu, const struct bpf_prog_
 	if (!check_builtin_idle_enabled(sch))
 		return false;
 
-	if (!ops_cpu_valid(sch, cpu, NULL))
+	if (!scx_cpu_valid(sch, cpu, NULL))
 		return false;
 
 	return scx_idle_test_and_clear_cpu(cpu);
diff --git a/kernel/sched/ext_internal.h b/kernel/sched/ext_internal.h
index 1b2ea6fa9fd6..f59cd58b8175 100644
--- a/kernel/sched/ext_internal.h
+++ b/kernel/sched/ext_internal.h
@@ -1352,6 +1352,8 @@ DECLARE_PER_CPU(struct rq *, scx_locked_rq_state);
 
 int scx_kfunc_context_filter(const struct bpf_prog *prog, u32 kfunc_id);
 
+bool scx_cpu_valid(struct scx_sched *sch, s32 cpu, const char *where);
+
 /*
  * Return the rq currently locked from an scx callback, or NULL if no rq is
  * locked.
-- 
2.54.0

[PATCH 03/17] sched_ext: Move scx_exit(), scx_error() and friends to ext_internal.h

[Tejun Heo]

Things shared across multiple .c files belong in a header. scx_exit() /
scx_error() (and their scx_vexit() / scx_verror() siblings) are already
called from ext_idle.c and the upcoming ext_cid.c, and it was only
build_policy.c's textual inclusion of ext.c that made the references
resolve. Move the whole family to ext_internal.h.

Pure visibility change.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Cheng-Yang Chou <yphbchou0911@gmail.com>
---
 kernel/sched/ext.c          | 13 ++++---------
 kernel/sched/ext_internal.h |  8 ++++++++
 2 files changed, 12 insertions(+), 9 deletions(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 980231c547ec..8d41b4e2cce6 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -231,12 +231,10 @@ static void run_deferred(struct rq *rq);
 static bool task_dead_and_done(struct task_struct *p);
 static void scx_kick_cpu(struct scx_sched *sch, s32 cpu, u64 flags);
 static void scx_disable(struct scx_sched *sch, enum scx_exit_kind kind);
-static bool scx_vexit(struct scx_sched *sch, enum scx_exit_kind kind,
-		      s64 exit_code, const char *fmt, va_list args);
 
-static __printf(4, 5) bool scx_exit(struct scx_sched *sch,
-				    enum scx_exit_kind kind, s64 exit_code,
-				    const char *fmt, ...)
+__printf(4, 5) bool scx_exit(struct scx_sched *sch,
+			     enum scx_exit_kind kind, s64 exit_code,
+			     const char *fmt, ...)
 {
 	va_list args;
 	bool ret;
@@ -248,9 +246,6 @@ static __printf(4, 5) bool scx_exit(struct scx_sched *sch,
 	return ret;
 }
 
-#define scx_error(sch, fmt, args...)	scx_exit((sch), SCX_EXIT_ERROR, 0, fmt, ##args)
-#define scx_verror(sch, fmt, args)	scx_vexit((sch), SCX_EXIT_ERROR, 0, fmt, args)
-
 #define SCX_HAS_OP(sch, op)	test_bit(SCX_OP_IDX(op), (sch)->has_op)
 
 static long jiffies_delta_msecs(unsigned long at, unsigned long now)
@@ -6432,7 +6427,7 @@ static void scx_disable_irq_workfn(struct irq_work *irq_work)
 	kthread_queue_work(sch->helper, &sch->disable_work);
 }
 
-static bool scx_vexit(struct scx_sched *sch,
+bool scx_vexit(struct scx_sched *sch,
 		      enum scx_exit_kind kind, s64 exit_code,
 		      const char *fmt, va_list args)
 {
diff --git a/kernel/sched/ext_internal.h b/kernel/sched/ext_internal.h
index f59cd58b8175..d4960df23da4 100644
--- a/kernel/sched/ext_internal.h
+++ b/kernel/sched/ext_internal.h
@@ -1354,6 +1354,14 @@ int scx_kfunc_context_filter(const struct bpf_prog *prog, u32 kfunc_id);
 
 bool scx_cpu_valid(struct scx_sched *sch, s32 cpu, const char *where);
 
+bool scx_vexit(struct scx_sched *sch, enum scx_exit_kind kind, s64 exit_code,
+	       const char *fmt, va_list args);
+__printf(4, 5) bool scx_exit(struct scx_sched *sch, enum scx_exit_kind kind,
+			     s64 exit_code, const char *fmt, ...);
+
+#define scx_verror(sch, fmt, args)	scx_vexit((sch), SCX_EXIT_ERROR, 0, fmt, args)
+#define scx_error(sch, fmt, args...)	scx_exit((sch), SCX_EXIT_ERROR, 0, fmt, ##args)
+
 /*
  * Return the rq currently locked from an scx callback, or NULL if no rq is
  * locked.
-- 
2.54.0

[PATCH 04/17] sched_ext: Shift scx_kick_cpu() validity check to scx_bpf_kick_cpu()

[Tejun Heo]

Callers that already know the cpu is valid shouldn't have to pay for a
redundant check. scx_kick_cpu() is called from the in-kernel balance loop
break-out path with the current cpu (trivially valid) and from
scx_bpf_kick_cpu() with a BPF-supplied cpu that does need validation. Move
the check out of scx_kick_cpu() into scx_bpf_kick_cpu() so the backend is
reusable by callers that have already validated.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Cheng-Yang Chou <yphbchou0911@gmail.com>
---
 kernel/sched/ext.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 8d41b4e2cce6..e9cf9d8f4626 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -8786,9 +8786,6 @@ static void scx_kick_cpu(struct scx_sched *sch, s32 cpu, u64 flags)
 	struct rq *this_rq;
 	unsigned long irq_flags;
 
-	if (!scx_cpu_valid(sch, cpu, NULL))
-		return;
-
 	local_irq_save(irq_flags);
 
 	this_rq = this_rq();
@@ -8851,7 +8848,7 @@ __bpf_kfunc void scx_bpf_kick_cpu(s32 cpu, u64 flags, const struct bpf_prog_aux
 
 	guard(rcu)();
 	sch = scx_prog_sched(aux);
-	if (likely(sch))
+	if (likely(sch) && scx_cpu_valid(sch, cpu, NULL))
 		scx_kick_cpu(sch, cpu, flags);
 }
 
-- 
2.54.0

[PATCH 05/17] sched_ext: Relocate cpu_acquire/cpu_release to end of struct sched_ext_ops

[Tejun Heo]

cpu_acquire and cpu_release are deprecated and slated for removal. Move
their declarations to the end of struct sched_ext_ops so an upcoming
cid-form struct (sched_ext_ops_cid) can omit them entirely without
disturbing the offsets of the shared fields.

Switch the two SCX_HAS_OP() callers for these ops to direct field checks
since the relocated ops sit outside the SCX_OPI_END range covered by the
has_op bitmap.

scx_kf_allow_flags[] auto-sizes to the highest used SCX_OP_IDX, so
SCX_OP_IDX(cpu_release) moving to a higher index just enlarges the
sparse array; the lookup logic is unchanged.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Cheng-Yang Chou <yphbchou0911@gmail.com>
---
 kernel/sched/ext.c          |  4 +--
 kernel/sched/ext_internal.h | 54 ++++++++++++++++++++++---------------
 2 files changed, 34 insertions(+), 24 deletions(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index e9cf9d8f4626..b197da2b960d 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -2823,7 +2823,7 @@ static int balance_one(struct rq *rq, struct task_struct *prev)
 		 * core. This callback complements ->cpu_release(), which is
 		 * emitted in switch_class().
 		 */
-		if (SCX_HAS_OP(sch, cpu_acquire))
+		if (sch->ops.cpu_acquire)
 			SCX_CALL_OP(sch, cpu_acquire, rq, cpu, NULL);
 		rq->scx.cpu_released = false;
 	}
@@ -2969,7 +2969,7 @@ static void switch_class(struct rq *rq, struct task_struct *next)
 	 *  next time that balance_one() is invoked.
 	 */
 	if (!rq->scx.cpu_released) {
-		if (SCX_HAS_OP(sch, cpu_release)) {
+		if (sch->ops.cpu_release) {
 			struct scx_cpu_release_args args = {
 				.reason = preempt_reason_from_class(next_class),
 				.task = next,
diff --git a/kernel/sched/ext_internal.h b/kernel/sched/ext_internal.h
index d4960df23da4..919d4aa08656 100644
--- a/kernel/sched/ext_internal.h
+++ b/kernel/sched/ext_internal.h
@@ -523,28 +523,6 @@ struct sched_ext_ops {
 	 */
 	void (*update_idle)(s32 cpu, bool idle);
 
-	/**
-	 * @cpu_acquire: A CPU is becoming available to the BPF scheduler
-	 * @cpu: The CPU being acquired by the BPF scheduler.
-	 * @args: Acquire arguments, see the struct definition.
-	 *
-	 * A CPU that was previously released from the BPF scheduler is now once
-	 * again under its control.
-	 */
-	void (*cpu_acquire)(s32 cpu, struct scx_cpu_acquire_args *args);
-
-	/**
-	 * @cpu_release: A CPU is taken away from the BPF scheduler
-	 * @cpu: The CPU being released by the BPF scheduler.
-	 * @args: Release arguments, see the struct definition.
-	 *
-	 * The specified CPU is no longer under the control of the BPF
-	 * scheduler. This could be because it was preempted by a higher
-	 * priority sched_class, though there may be other reasons as well. The
-	 * caller should consult @args->reason to determine the cause.
-	 */
-	void (*cpu_release)(s32 cpu, struct scx_cpu_release_args *args);
-
 	/**
 	 * @init_task: Initialize a task to run in a BPF scheduler
 	 * @p: task to initialize for BPF scheduling
@@ -835,6 +813,38 @@ struct sched_ext_ops {
 
 	/* internal use only, must be NULL */
 	void __rcu *priv;
+
+	/*
+	 * Deprecated callbacks. Kept at the end of the struct so the cid-form
+	 * struct (sched_ext_ops_cid) can omit them without affecting the
+	 * shared field offsets. Use SCX_ENQ_IMMED instead. Sitting past
+	 * SCX_OPI_END means has_op doesn't cover them, so SCX_HAS_OP() cannot
+	 * be used; callers must test sch->ops.cpu_acquire / cpu_release
+	 * directly.
+	 */
+
+	/**
+	 * @cpu_acquire: A CPU is becoming available to the BPF scheduler
+	 * @cpu: The CPU being acquired by the BPF scheduler.
+	 * @args: Acquire arguments, see the struct definition.
+	 *
+	 * A CPU that was previously released from the BPF scheduler is now once
+	 * again under its control. Deprecated; use SCX_ENQ_IMMED instead.
+	 */
+	void (*cpu_acquire)(s32 cpu, struct scx_cpu_acquire_args *args);
+
+	/**
+	 * @cpu_release: A CPU is taken away from the BPF scheduler
+	 * @cpu: The CPU being released by the BPF scheduler.
+	 * @args: Release arguments, see the struct definition.
+	 *
+	 * The specified CPU is no longer under the control of the BPF
+	 * scheduler. This could be because it was preempted by a higher
+	 * priority sched_class, though there may be other reasons as well. The
+	 * caller should consult @args->reason to determine the cause.
+	 * Deprecated; use SCX_ENQ_IMMED instead.
+	 */
+	void (*cpu_release)(s32 cpu, struct scx_cpu_release_args *args);
 };
 
 enum scx_opi {
-- 
2.54.0

[PATCH 06/17] sched_ext: Make scx_enable() take scx_enable_cmd

[Tejun Heo]

Pass struct scx_enable_cmd to scx_enable() rather than unpacking @ops
at every call site and re-packing into a fresh cmd inside. bpf_scx_reg()
now builds the cmd on its stack and hands it in; scx_enable() just
wires up the kthread work and waits.

Relocate struct scx_enable_cmd above scx_alloc_and_add_sched() so
upcoming patches that also want the cmd can see it.

No behavior change.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Cheng-Yang Chou <yphbchou0911@gmail.com>
---
 kernel/sched/ext.c | 46 +++++++++++++++++++++++-----------------------
 1 file changed, 23 insertions(+), 23 deletions(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index b197da2b960d..f9a1f217bc47 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -6507,6 +6507,19 @@ static struct scx_sched_pnode *alloc_pnode(struct scx_sched *sch, int node)
 	return pnode;
 }
 
+/*
+ * scx_enable() is offloaded to a dedicated system-wide RT kthread to avoid
+ * starvation. During the READY -> ENABLED task switching loop, the calling
+ * thread's sched_class gets switched from fair to ext. As fair has higher
+ * priority than ext, the calling thread can be indefinitely starved under
+ * fair-class saturation, leading to a system hang.
+ */
+struct scx_enable_cmd {
+	struct kthread_work	work;
+	struct sched_ext_ops	*ops;
+	int			ret;
+};
+
 /*
  * Allocate and initialize a new scx_sched. @cgrp's reference is always
  * consumed whether the function succeeds or fails.
@@ -6749,19 +6762,6 @@ static int validate_ops(struct scx_sched *sch, const struct sched_ext_ops *ops)
 	return 0;
 }
 
-/*
- * scx_enable() is offloaded to a dedicated system-wide RT kthread to avoid
- * starvation. During the READY -> ENABLED task switching loop, the calling
- * thread's sched_class gets switched from fair to ext. As fair has higher
- * priority than ext, the calling thread can be indefinitely starved under
- * fair-class saturation, leading to a system hang.
- */
-struct scx_enable_cmd {
-	struct kthread_work	work;
-	struct sched_ext_ops	*ops;
-	int			ret;
-};
-
 static void scx_root_enable_workfn(struct kthread_work *work)
 {
 	struct scx_enable_cmd *cmd = container_of(work, struct scx_enable_cmd, work);
@@ -7346,11 +7346,10 @@ static s32 __init scx_cgroup_lifetime_notifier_init(void)
 core_initcall(scx_cgroup_lifetime_notifier_init);
 #endif	/* CONFIG_EXT_SUB_SCHED */
 
-static s32 scx_enable(struct sched_ext_ops *ops, struct bpf_link *link)
+static s32 scx_enable(struct scx_enable_cmd *cmd, struct bpf_link *link)
 {
 	static struct kthread_worker *helper;
 	static DEFINE_MUTEX(helper_mutex);
-	struct scx_enable_cmd cmd;
 
 	if (!cpumask_equal(housekeeping_cpumask(HK_TYPE_DOMAIN),
 			   cpu_possible_mask)) {
@@ -7374,16 +7373,15 @@ static s32 scx_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 	}
 
 #ifdef CONFIG_EXT_SUB_SCHED
-	if (ops->sub_cgroup_id > 1)
-		kthread_init_work(&cmd.work, scx_sub_enable_workfn);
+	if (cmd->ops->sub_cgroup_id > 1)
+		kthread_init_work(&cmd->work, scx_sub_enable_workfn);
 	else
 #endif	/* CONFIG_EXT_SUB_SCHED */
-		kthread_init_work(&cmd.work, scx_root_enable_workfn);
-	cmd.ops = ops;
+		kthread_init_work(&cmd->work, scx_root_enable_workfn);
 
-	kthread_queue_work(READ_ONCE(helper), &cmd.work);
-	kthread_flush_work(&cmd.work);
-	return cmd.ret;
+	kthread_queue_work(READ_ONCE(helper), &cmd->work);
+	kthread_flush_work(&cmd->work);
+	return cmd->ret;
 }
 
 
@@ -7555,7 +7553,9 @@ static int bpf_scx_check_member(const struct btf_type *t,
 
 static int bpf_scx_reg(void *kdata, struct bpf_link *link)
 {
-	return scx_enable(kdata, link);
+	struct scx_enable_cmd cmd = { .ops = kdata };
+
+	return scx_enable(&cmd, link);
 }
 
 static void bpf_scx_unreg(void *kdata, struct bpf_link *link)
-- 
2.54.0

[PATCH 07/17] sched_ext: Add topological CPU IDs (cids)

[Tejun Heo]

Raw cpu numbers are clumsy for sharding and cross-sched communication,
especially from BPF. The space is sparse, numerical closeness doesn't
track topological closeness (x86 hyperthreading often scatters SMT
siblings), and a range of cpu ids doesn't describe anything meaningful.
Sub-sched support makes this acute: cpu allocation, revocation, and
state constantly flow across sub-scheds. Passing whole cpumasks scales
poorly (every op scans 4K bits) and cpumasks are awkward in BPF.

cids assign every cpu a dense, topology-ordered id. CPUs sharing a core,
LLC, or NUMA node occupy contiguous cid ranges, so a topology unit
becomes a (start, length) slice. Communication passes slices; BPF can
process a u64 word of cids at a time.

Build the mapping once at root enable by walking online cpus node -> LLC
-> core. Possible-but-not-online cpus tail the space with no-topo cids.
Expose kfuncs to map cpu <-> cid in either direction and to query each
cid's topology metadata.

v2: Use kzalloc_objs()/kmalloc_objs() for the three allocs in
    scx_cid_arrays_alloc() (Cheng-Yang Chou).

v3: scx_cid_init() failure path now drops cpus_read_lock();
    BUILD_BUG_ON tightened to match BPF cmask helpers' NR_CPUS<=8192.
    (Sashiko)

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Cheng-Yang Chou <yphbchou0911@gmail.com>
---
 kernel/sched/build_policy.c              |   2 +
 kernel/sched/ext.c                       |  18 ++
 kernel/sched/ext_cid.c                   | 301 +++++++++++++++++++++++
 kernel/sched/ext_cid.h                   | 129 ++++++++++
 kernel/sched/ext_types.h                 |  23 ++
 tools/sched_ext/include/scx/common.bpf.h |   3 +
 6 files changed, 476 insertions(+)
 create mode 100644 kernel/sched/ext_cid.c
 create mode 100644 kernel/sched/ext_cid.h

diff --git a/kernel/sched/build_policy.c b/kernel/sched/build_policy.c
index 1d92f7d7a19f..5e76c9177d54 100644
--- a/kernel/sched/build_policy.c
+++ b/kernel/sched/build_policy.c
@@ -61,8 +61,10 @@
 # include <linux/btf_ids.h>
 # include "ext_types.h"
 # include "ext_internal.h"
+# include "ext_cid.h"
 # include "ext_idle.h"
 # include "ext.c"
+# include "ext_cid.c"
 # include "ext_idle.c"
 #endif
 
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index f9a1f217bc47..2b531256c763 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -6820,6 +6820,18 @@ static void scx_root_enable_workfn(struct kthread_work *work)
 	 */
 	cpus_read_lock();
 
+	/*
+	 * Build the cid mapping before publishing scx_root. The cid kfuncs
+	 * dereference the cid arrays unconditionally once scx_prog_sched()
+	 * returns non-NULL; the rcu_assign_pointer() below pairs with their
+	 * rcu_dereference() to make the populated arrays visible.
+	 */
+	ret = scx_cid_init(sch);
+	if (ret) {
+		cpus_read_unlock();
+		goto err_disable;
+	}
+
 	/*
 	 * Make the scheduler instance visible. Must be inside cpus_read_lock().
 	 * See handle_hotplug().
@@ -9888,6 +9900,12 @@ static int __init scx_init(void)
 		return ret;
 	}
 
+	ret = scx_cid_kfunc_init();
+	if (ret) {
+		pr_err("sched_ext: Failed to register cid kfuncs (%d)\n", ret);
+		return ret;
+	}
+
 	ret = register_bpf_struct_ops(&bpf_sched_ext_ops, sched_ext_ops);
 	if (ret) {
 		pr_err("sched_ext: Failed to register struct_ops (%d)\n", ret);
diff --git a/kernel/sched/ext_cid.c b/kernel/sched/ext_cid.c
new file mode 100644
index 000000000000..5b73900edc87
--- /dev/null
+++ b/kernel/sched/ext_cid.c
@@ -0,0 +1,301 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * BPF extensible scheduler class: Documentation/scheduler/sched-ext.rst
+ *
+ * Copyright (c) 2026 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2026 Tejun Heo <tj@kernel.org>
+ */
+#include <linux/cacheinfo.h>
+
+/*
+ * cid tables.
+ *
+ * Pointers are published once on first enable and never revoked. The default
+ * mapping is populated before ops.init() runs; scx_bpf_cid_override() commits
+ * before it returns. As long as the BPF scheduler only uses the tables from
+ * those points onward, it sees a consistent view.
+ */
+s16 *scx_cid_to_cpu_tbl;
+s16 *scx_cpu_to_cid_tbl;
+struct scx_cid_topo *scx_cid_topo;
+
+#define SCX_CID_TOPO_NEG	(struct scx_cid_topo) {				\
+	.core_cid = -1, .core_idx = -1, .llc_cid = -1, .llc_idx = -1,		\
+	.node_cid = -1, .node_idx = -1,						\
+}
+
+/*
+ * Return @cpu's LLC shared_cpu_map. If cacheinfo isn't populated (offline or
+ * !present), record @cpu in @fallbacks and return its node mask instead - the
+ * worst that can happen is that the cpu's LLC becomes coarser than reality.
+ */
+static const struct cpumask *cpu_llc_mask(int cpu, struct cpumask *fallbacks)
+{
+	struct cpu_cacheinfo *ci = get_cpu_cacheinfo(cpu);
+
+	if (!ci || !ci->info_list || !ci->num_leaves) {
+		cpumask_set_cpu(cpu, fallbacks);
+		return cpumask_of_node(cpu_to_node(cpu));
+	}
+	return &ci->info_list[ci->num_leaves - 1].shared_cpu_map;
+}
+
+/* Allocate the cid tables once on first enable; never freed. */
+static s32 scx_cid_arrays_alloc(void)
+{
+	u32 npossible = num_possible_cpus();
+	s16 *cid_to_cpu, *cpu_to_cid;
+	struct scx_cid_topo *cid_topo;
+
+	if (scx_cid_to_cpu_tbl)
+		return 0;
+
+	cid_to_cpu = kzalloc_objs(*scx_cid_to_cpu_tbl, npossible, GFP_KERNEL);
+	cpu_to_cid = kzalloc_objs(*scx_cpu_to_cid_tbl, nr_cpu_ids, GFP_KERNEL);
+	cid_topo = kmalloc_objs(*scx_cid_topo, npossible, GFP_KERNEL);
+
+	if (!cid_to_cpu || !cpu_to_cid || !cid_topo) {
+		kfree(cid_to_cpu);
+		kfree(cpu_to_cid);
+		kfree(cid_topo);
+		return -ENOMEM;
+	}
+
+	WRITE_ONCE(scx_cid_to_cpu_tbl, cid_to_cpu);
+	WRITE_ONCE(scx_cpu_to_cid_tbl, cpu_to_cid);
+	WRITE_ONCE(scx_cid_topo, cid_topo);
+	return 0;
+}
+
+/**
+ * scx_cid_init - build the cid mapping
+ * @sch: the scx_sched being initialized; used as the scx_error() target
+ *
+ * See "Topological CPU IDs" in ext_cid.h for the model. Walk online cpus by
+ * intersection at each level (parent_scratch & this_level_mask), which keeps
+ * containment correct by construction and naturally splits a physical LLC
+ * straddling two NUMA nodes into two LLC units. The caller must hold
+ * cpus_read_lock.
+ */
+s32 scx_cid_init(struct scx_sched *sch)
+{
+	cpumask_var_t to_walk __free(free_cpumask_var) = CPUMASK_VAR_NULL;
+	cpumask_var_t node_scratch __free(free_cpumask_var) = CPUMASK_VAR_NULL;
+	cpumask_var_t llc_scratch __free(free_cpumask_var) = CPUMASK_VAR_NULL;
+	cpumask_var_t core_scratch __free(free_cpumask_var) = CPUMASK_VAR_NULL;
+	cpumask_var_t llc_fallback __free(free_cpumask_var) = CPUMASK_VAR_NULL;
+	cpumask_var_t online_no_topo __free(free_cpumask_var) = CPUMASK_VAR_NULL;
+	u32 next_cid = 0;
+	s32 next_node_idx = 0, next_llc_idx = 0, next_core_idx = 0;
+	s32 cpu, ret;
+
+	/* CMASK_MAX_WORDS in cid.bpf.h covers NR_CPUS up to 8192 */
+	BUILD_BUG_ON(NR_CPUS > 8192);
+
+	lockdep_assert_cpus_held();
+
+	ret = scx_cid_arrays_alloc();
+	if (ret)
+		return ret;
+
+	if (!zalloc_cpumask_var(&to_walk, GFP_KERNEL) ||
+	    !zalloc_cpumask_var(&node_scratch, GFP_KERNEL) ||
+	    !zalloc_cpumask_var(&llc_scratch, GFP_KERNEL) ||
+	    !zalloc_cpumask_var(&core_scratch, GFP_KERNEL) ||
+	    !zalloc_cpumask_var(&llc_fallback, GFP_KERNEL) ||
+	    !zalloc_cpumask_var(&online_no_topo, GFP_KERNEL))
+		return -ENOMEM;
+
+	/* -1 sentinels for sparse-possible cpu id holes (0 is a valid cid) */
+	for (cpu = 0; cpu < nr_cpu_ids; cpu++)
+		scx_cpu_to_cid_tbl[cpu] = -1;
+
+	cpumask_copy(to_walk, cpu_online_mask);
+
+	while (!cpumask_empty(to_walk)) {
+		s32 next_cpu = cpumask_first(to_walk);
+		s32 nid = cpu_to_node(next_cpu);
+		s32 node_cid = next_cid;
+		s32 node_idx;
+
+		/*
+		 * No NUMA info: skip and let the tail loop assign a no-topo
+		 * cid. cpumask_of_node(-1) is undefined.
+		 */
+		if (nid < 0) {
+			cpumask_clear_cpu(next_cpu, to_walk);
+			continue;
+		}
+
+		node_idx = next_node_idx++;
+
+		/* node_scratch = to_walk & this node */
+		cpumask_and(node_scratch, to_walk, cpumask_of_node(nid));
+		if (WARN_ON_ONCE(!cpumask_test_cpu(next_cpu, node_scratch)))
+			return -EINVAL;
+
+		while (!cpumask_empty(node_scratch)) {
+			s32 ncpu = cpumask_first(node_scratch);
+			const struct cpumask *llc_mask = cpu_llc_mask(ncpu, llc_fallback);
+			s32 llc_cid = next_cid;
+			s32 llc_idx = next_llc_idx++;
+
+			/* llc_scratch = node_scratch & this llc */
+			cpumask_and(llc_scratch, node_scratch, llc_mask);
+			if (WARN_ON_ONCE(!cpumask_test_cpu(ncpu, llc_scratch)))
+				return -EINVAL;
+
+			while (!cpumask_empty(llc_scratch)) {
+				s32 lcpu = cpumask_first(llc_scratch);
+				const struct cpumask *sib = topology_sibling_cpumask(lcpu);
+				s32 core_cid = next_cid;
+				s32 core_idx = next_core_idx++;
+				s32 ccpu;
+
+				/* core_scratch = llc_scratch & this core */
+				cpumask_and(core_scratch, llc_scratch, sib);
+				if (WARN_ON_ONCE(!cpumask_test_cpu(lcpu, core_scratch)))
+					return -EINVAL;
+
+				for_each_cpu(ccpu, core_scratch) {
+					s32 cid = next_cid++;
+
+					scx_cid_to_cpu_tbl[cid] = ccpu;
+					scx_cpu_to_cid_tbl[ccpu] = cid;
+					scx_cid_topo[cid] = (struct scx_cid_topo){
+						.core_cid = core_cid,
+						.core_idx = core_idx,
+						.llc_cid = llc_cid,
+						.llc_idx = llc_idx,
+						.node_cid = node_cid,
+						.node_idx = node_idx,
+					};
+
+					cpumask_clear_cpu(ccpu, llc_scratch);
+					cpumask_clear_cpu(ccpu, node_scratch);
+					cpumask_clear_cpu(ccpu, to_walk);
+				}
+			}
+		}
+	}
+
+	/*
+	 * No-topo section: any possible cpu without a cid - normally just the
+	 * not-online ones. Collect any currently-online cpus that land here in
+	 * @online_no_topo so we can warn about them at the end.
+	 */
+	for_each_cpu(cpu, cpu_possible_mask) {
+		s32 cid;
+
+		if (__scx_cpu_to_cid(cpu) != -1)
+			continue;
+		if (cpu_online(cpu))
+			cpumask_set_cpu(cpu, online_no_topo);
+
+		cid = next_cid++;
+		scx_cid_to_cpu_tbl[cid] = cpu;
+		scx_cpu_to_cid_tbl[cpu] = cid;
+		scx_cid_topo[cid] = SCX_CID_TOPO_NEG;
+	}
+
+	if (!cpumask_empty(llc_fallback))
+		pr_warn("scx_cid: cpus without cacheinfo, using node mask as llc: %*pbl\n",
+			cpumask_pr_args(llc_fallback));
+	if (!cpumask_empty(online_no_topo))
+		pr_warn("scx_cid: online cpus with no usable topology: %*pbl\n",
+			cpumask_pr_args(online_no_topo));
+
+	return 0;
+}
+
+__bpf_kfunc_start_defs();
+
+/**
+ * scx_bpf_cid_to_cpu - Return the raw CPU id for @cid
+ * @cid: cid to look up
+ * @aux: implicit BPF argument to access bpf_prog_aux hidden from BPF progs
+ *
+ * Return the raw CPU id for @cid. Trigger scx_error() and return -EINVAL if
+ * @cid is invalid. The cid<->cpu mapping is static for the lifetime of the
+ * loaded scheduler, so the BPF side can cache the result to avoid repeated
+ * kfunc invocations.
+ */
+__bpf_kfunc s32 scx_bpf_cid_to_cpu(s32 cid, const struct bpf_prog_aux *aux)
+{
+	struct scx_sched *sch;
+
+	guard(rcu)();
+
+	sch = scx_prog_sched(aux);
+	if (unlikely(!sch))
+		return -EINVAL;
+	return scx_cid_to_cpu(sch, cid);
+}
+
+/**
+ * scx_bpf_cpu_to_cid - Return the cid for @cpu
+ * @cpu: cpu to look up
+ * @aux: implicit BPF argument to access bpf_prog_aux hidden from BPF progs
+ *
+ * Return the cid for @cpu. Trigger scx_error() and return -EINVAL if @cpu is
+ * invalid. The cid<->cpu mapping is static for the lifetime of the loaded
+ * scheduler, so the BPF side can cache the result to avoid repeated kfunc
+ * invocations.
+ */
+__bpf_kfunc s32 scx_bpf_cpu_to_cid(s32 cpu, const struct bpf_prog_aux *aux)
+{
+	struct scx_sched *sch;
+
+	guard(rcu)();
+
+	sch = scx_prog_sched(aux);
+	if (unlikely(!sch))
+		return -EINVAL;
+	return scx_cpu_to_cid(sch, cpu);
+}
+
+/**
+ * scx_bpf_cid_topo - Copy out per-cid topology info
+ * @cid: cid to look up
+ * @out__uninit: where to copy the topology info; fully written by this call
+ * @aux: implicit BPF argument to access bpf_prog_aux hidden from BPF progs
+ *
+ * Fill @out__uninit with the topology info for @cid. Trigger scx_error() if
+ * @cid is out of range. If @cid is valid but in the no-topo section, all fields
+ * are set to -1.
+ */
+__bpf_kfunc void scx_bpf_cid_topo(s32 cid, struct scx_cid_topo *out__uninit,
+				  const struct bpf_prog_aux *aux)
+{
+	struct scx_sched *sch;
+
+	guard(rcu)();
+
+	sch = scx_prog_sched(aux);
+	if (unlikely(!sch) || !cid_valid(sch, cid)) {
+		*out__uninit = SCX_CID_TOPO_NEG;
+		return;
+	}
+
+	*out__uninit = READ_ONCE(scx_cid_topo)[cid];
+}
+
+__bpf_kfunc_end_defs();
+
+BTF_KFUNCS_START(scx_kfunc_ids_cid)
+BTF_ID_FLAGS(func, scx_bpf_cid_to_cpu, KF_IMPLICIT_ARGS)
+BTF_ID_FLAGS(func, scx_bpf_cpu_to_cid, KF_IMPLICIT_ARGS)
+BTF_ID_FLAGS(func, scx_bpf_cid_topo, KF_IMPLICIT_ARGS)
+BTF_KFUNCS_END(scx_kfunc_ids_cid)
+
+static const struct btf_kfunc_id_set scx_kfunc_set_cid = {
+	.owner	= THIS_MODULE,
+	.set	= &scx_kfunc_ids_cid,
+};
+
+int scx_cid_kfunc_init(void)
+{
+	return register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &scx_kfunc_set_cid) ?:
+		register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &scx_kfunc_set_cid) ?:
+		register_btf_kfunc_id_set(BPF_PROG_TYPE_SYSCALL, &scx_kfunc_set_cid);
+}
diff --git a/kernel/sched/ext_cid.h b/kernel/sched/ext_cid.h
new file mode 100644
index 000000000000..1dbe8262ccdd
--- /dev/null
+++ b/kernel/sched/ext_cid.h
@@ -0,0 +1,129 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Topological CPU IDs (cids)
+ * --------------------------
+ *
+ * Raw cpu numbers are clumsy for sharding work and communication across
+ * topology units, especially from BPF: the space can be sparse, numerical
+ * closeness doesn't imply topological closeness (x86 hyperthreading often puts
+ * SMT siblings far apart), and a range of cpu ids doesn't mean anything.
+ * Sub-scheds make this acute - cpu allocation, revocation and other state are
+ * constantly communicated across sub-scheds, and passing whole cpumasks scales
+ * poorly with cpu count. cpumasks are also awkward in BPF: a variable-length
+ * kernel type sized for the maximum NR_CPUS (4k), with verbose helper sequences
+ * for every op.
+ *
+ * cids give every cpu a dense, topology-ordered id. CPUs sharing a core, LLC or
+ * NUMA node get contiguous cid ranges, so a topology unit becomes a (start,
+ * length) slice of cid space. Communication can pass a slice instead of a
+ * cpumask, and BPF code can process, for example, a u64 word's worth of cids at
+ * a time.
+ *
+ * The mapping is built once at root scheduler enable time by walking the
+ * topology of online cpus only. Going by online cpus is out of necessity:
+ * depending on the arch, topology info isn't reliably available for offline
+ * cpus. The expected usage model is restarting the scheduler on hotplug events
+ * so the mapping is rebuilt against the new online set. A scheduler that wants
+ * to handle hotplug without a restart can provide its own cid and shard mapping
+ * through the override interface.
+ *
+ * Copyright (c) 2026 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2026 Tejun Heo <tj@kernel.org>
+ */
+#ifndef _KERNEL_SCHED_EXT_CID_H
+#define _KERNEL_SCHED_EXT_CID_H
+
+struct scx_sched;
+
+/*
+ * Cid space (total is always num_possible_cpus()) is laid out with
+ * topology-annotated cids first, then no-topo cids at the tail. The
+ * topology-annotated block covers the cpus that were online when scx_cid_init()
+ * ran and remains valid even after those cpus go offline. The tail block covers
+ * possible-but-not-online cpus and carries all-(-1) topo info (see
+ * scx_cid_topo); callers detect it via the -1 sentinels.
+ *
+ * See the comment above the table definitions in ext_cid.c for the
+ * memory-ordering and visibility contract.
+ */
+extern s16 *scx_cid_to_cpu_tbl;
+extern s16 *scx_cpu_to_cid_tbl;
+extern struct scx_cid_topo *scx_cid_topo;
+
+s32 scx_cid_init(struct scx_sched *sch);
+int scx_cid_kfunc_init(void);
+
+/**
+ * cid_valid - Verify a cid value, to be used on ops input args
+ * @sch: scx_sched to abort on error
+ * @cid: cid which came from a BPF ops
+ *
+ * Return true if @cid is in [0, num_possible_cpus()). On failure, trigger
+ * scx_error() and return false.
+ */
+static inline bool cid_valid(struct scx_sched *sch, s32 cid)
+{
+	if (likely(cid >= 0 && cid < num_possible_cpus()))
+		return true;
+	scx_error(sch, "invalid cid %d", cid);
+	return false;
+}
+
+/**
+ * __scx_cid_to_cpu - Unchecked cid->cpu table lookup
+ * @cid: cid to look up. Must be in [0, num_possible_cpus()).
+ *
+ * Intended for callsites that have already validated @cid and that hold a
+ * non-NULL @sch from scx_prog_sched() - a live sched implies the table has
+ * been allocated, so no NULL check is needed here.
+ */
+static inline s32 __scx_cid_to_cpu(s32 cid)
+{
+	/* READ_ONCE pairs with WRITE_ONCE in scx_cid_arrays_alloc() */
+	return READ_ONCE(scx_cid_to_cpu_tbl)[cid];
+}
+
+/**
+ * __scx_cpu_to_cid - Unchecked cpu->cid table lookup
+ * @cpu: cpu to look up. Must be a valid possible cpu id.
+ *
+ * Same usage constraints as __scx_cid_to_cpu().
+ */
+static inline s32 __scx_cpu_to_cid(s32 cpu)
+{
+	return READ_ONCE(scx_cpu_to_cid_tbl)[cpu];
+}
+
+/**
+ * scx_cid_to_cpu - Translate @cid to its cpu
+ * @sch: scx_sched for error reporting
+ * @cid: cid to look up
+ *
+ * Return the cpu for @cid or a negative errno on failure. Invalid cid triggers
+ * scx_error() on @sch. The cid arrays are allocated on first scheduler enable
+ * and never freed, so the returned cpu is stable for the lifetime of the loaded
+ * scheduler.
+ */
+static inline s32 scx_cid_to_cpu(struct scx_sched *sch, s32 cid)
+{
+	if (!cid_valid(sch, cid))
+		return -EINVAL;
+	return __scx_cid_to_cpu(cid);
+}
+
+/**
+ * scx_cpu_to_cid - Translate @cpu to its cid
+ * @sch: scx_sched for error reporting
+ * @cpu: cpu to look up
+ *
+ * Return the cid for @cpu or a negative errno on failure. Invalid cpu triggers
+ * scx_error() on @sch. Same lifetime guarantee as scx_cid_to_cpu().
+ */
+static inline s32 scx_cpu_to_cid(struct scx_sched *sch, s32 cpu)
+{
+	if (!scx_cpu_valid(sch, cpu, NULL))
+		return -EINVAL;
+	return __scx_cpu_to_cid(cpu);
+}
+
+#endif /* _KERNEL_SCHED_EXT_CID_H */
diff --git a/kernel/sched/ext_types.h b/kernel/sched/ext_types.h
index 19299ec3920e..be4d3565ae8d 100644
--- a/kernel/sched/ext_types.h
+++ b/kernel/sched/ext_types.h
@@ -40,4 +40,27 @@ enum scx_consts {
 	SCX_SUB_MAX_DEPTH		= 4,
 };
 
+/*
+ * Per-cid topology info. For each topology level (core, LLC, node), records
+ * the first cid in the unit and its global index. Global indices are
+ * consecutive integers assigned in cid-walk order, so e.g. core_idx ranges
+ * over [0, nr_cores_at_init) with no gaps. No-topo cids have all fields set
+ * to -1.
+ *
+ * @core_cid: first cid of this cid's core (smt-sibling group)
+ * @core_idx: global index of that core, in [0, nr_cores_at_init)
+ * @llc_cid: first cid of this cid's LLC
+ * @llc_idx: global index of that LLC, in [0, nr_llcs_at_init)
+ * @node_cid: first cid of this cid's NUMA node
+ * @node_idx: global index of that node, in [0, nr_nodes_at_init)
+ */
+struct scx_cid_topo {
+	s32 core_cid;
+	s32 core_idx;
+	s32 llc_cid;
+	s32 llc_idx;
+	s32 node_cid;
+	s32 node_idx;
+};
+
 #endif /* _KERNEL_SCHED_EXT_TYPES_H */
diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h
index 67b4b179b422..18f823d424cc 100644
--- a/tools/sched_ext/include/scx/common.bpf.h
+++ b/tools/sched_ext/include/scx/common.bpf.h
@@ -102,6 +102,9 @@ struct task_struct *scx_bpf_cpu_curr(s32 cpu) __ksym __weak;
 struct task_struct *scx_bpf_tid_to_task(u64 tid) __ksym __weak;
 u64 scx_bpf_now(void) __ksym __weak;
 void scx_bpf_events(struct scx_event_stats *events, size_t events__sz) __ksym __weak;
+s32 scx_bpf_cpu_to_cid(s32 cpu) __ksym __weak;
+s32 scx_bpf_cid_to_cpu(s32 cid) __ksym __weak;
+void scx_bpf_cid_topo(s32 cid, struct scx_cid_topo *out) __ksym __weak;
 
 /*
  * Use the following as @it__iter when calling scx_bpf_dsq_move[_vtime]() from
-- 
2.54.0

[PATCH 08/17] sched_ext: Add scx_bpf_cid_override() kfunc

[Tejun Heo]

The auto-probed cid mapping reflects the kernel's view of topology
(node -> LLC -> core), but a BPF scheduler may want a different layout -
to align cid slices with its own partitioning, or to work around how the
kernel reports a particular machine.

Add scx_bpf_cid_override(), callable from ops.init() of the root
scheduler. It validates the caller-supplied cpu->cid array and replaces
the in-place mapping; topo info is invalidated. A compat.bpf.h wrapper
silently no-ops on kernels that lack the kfunc.

A new SCX_KF_ALLOW_INIT bit in the kfunc context filter restricts the
kfunc to ops.init() at verifier load time.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Cheng-Yang Chou <yphbchou0911@gmail.com>
---
 kernel/sched/ext.c                       | 16 +++--
 kernel/sched/ext_cid.c                   | 75 +++++++++++++++++++++++-
 kernel/sched/ext_cid.h                   |  1 +
 tools/sched_ext/include/scx/compat.bpf.h | 12 ++++
 4 files changed, 97 insertions(+), 7 deletions(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 2b531256c763..6f0b30fa970f 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -9755,10 +9755,11 @@ static const struct btf_kfunc_id_set scx_kfunc_set_any = {
  */
 enum scx_kf_allow_flags {
 	SCX_KF_ALLOW_UNLOCKED		= 1 << 0,
-	SCX_KF_ALLOW_CPU_RELEASE	= 1 << 1,
-	SCX_KF_ALLOW_DISPATCH		= 1 << 2,
-	SCX_KF_ALLOW_ENQUEUE		= 1 << 3,
-	SCX_KF_ALLOW_SELECT_CPU		= 1 << 4,
+	SCX_KF_ALLOW_INIT		= 1 << 1,
+	SCX_KF_ALLOW_CPU_RELEASE	= 1 << 2,
+	SCX_KF_ALLOW_DISPATCH		= 1 << 3,
+	SCX_KF_ALLOW_ENQUEUE		= 1 << 4,
+	SCX_KF_ALLOW_SELECT_CPU		= 1 << 5,
 };
 
 /*
@@ -9786,7 +9787,7 @@ static const u32 scx_kf_allow_flags[] = {
 	[SCX_OP_IDX(sub_detach)]	= SCX_KF_ALLOW_UNLOCKED,
 	[SCX_OP_IDX(cpu_online)]	= SCX_KF_ALLOW_UNLOCKED,
 	[SCX_OP_IDX(cpu_offline)]	= SCX_KF_ALLOW_UNLOCKED,
-	[SCX_OP_IDX(init)]		= SCX_KF_ALLOW_UNLOCKED,
+	[SCX_OP_IDX(init)]		= SCX_KF_ALLOW_UNLOCKED | SCX_KF_ALLOW_INIT,
 	[SCX_OP_IDX(exit)]		= SCX_KF_ALLOW_UNLOCKED,
 };
 
@@ -9801,6 +9802,7 @@ static const u32 scx_kf_allow_flags[] = {
 int scx_kfunc_context_filter(const struct bpf_prog *prog, u32 kfunc_id)
 {
 	bool in_unlocked = btf_id_set8_contains(&scx_kfunc_ids_unlocked, kfunc_id);
+	bool in_init = btf_id_set8_contains(&scx_kfunc_ids_init, kfunc_id);
 	bool in_select_cpu = btf_id_set8_contains(&scx_kfunc_ids_select_cpu, kfunc_id);
 	bool in_enqueue = btf_id_set8_contains(&scx_kfunc_ids_enqueue_dispatch, kfunc_id);
 	bool in_dispatch = btf_id_set8_contains(&scx_kfunc_ids_dispatch, kfunc_id);
@@ -9810,7 +9812,7 @@ int scx_kfunc_context_filter(const struct bpf_prog *prog, u32 kfunc_id)
 	u32 moff, flags;
 
 	/* Not an SCX kfunc - allow. */
-	if (!(in_unlocked || in_select_cpu || in_enqueue || in_dispatch ||
+	if (!(in_unlocked || in_init || in_select_cpu || in_enqueue || in_dispatch ||
 	      in_cpu_release || in_idle || in_any))
 		return 0;
 
@@ -9846,6 +9848,8 @@ int scx_kfunc_context_filter(const struct bpf_prog *prog, u32 kfunc_id)
 
 	if ((flags & SCX_KF_ALLOW_UNLOCKED) && in_unlocked)
 		return 0;
+	if ((flags & SCX_KF_ALLOW_INIT) && in_init)
+		return 0;
 	if ((flags & SCX_KF_ALLOW_CPU_RELEASE) && in_cpu_release)
 		return 0;
 	if ((flags & SCX_KF_ALLOW_DISPATCH) && in_dispatch)
diff --git a/kernel/sched/ext_cid.c b/kernel/sched/ext_cid.c
index 5b73900edc87..607937d9e4d1 100644
--- a/kernel/sched/ext_cid.c
+++ b/kernel/sched/ext_cid.c
@@ -210,6 +210,68 @@ s32 scx_cid_init(struct scx_sched *sch)
 
 __bpf_kfunc_start_defs();
 
+/**
+ * scx_bpf_cid_override - Install an explicit cpu->cid mapping
+ * @cpu_to_cid: array of nr_cpu_ids s32 entries (cid for each cpu)
+ * @cpu_to_cid__sz: must be nr_cpu_ids * sizeof(s32) bytes
+ * @aux: implicit BPF argument to access bpf_prog_aux hidden from BPF progs
+ *
+ * May only be called from ops.init() of the root scheduler. Replace the
+ * topology-probed cid mapping with the caller-provided one. Each possible cpu
+ * must map to a unique cid in [0, num_possible_cpus()). Topo info is cleared.
+ * On invalid input, trigger scx_error() to abort the scheduler.
+ */
+__bpf_kfunc void scx_bpf_cid_override(const s32 *cpu_to_cid, u32 cpu_to_cid__sz,
+				      const struct bpf_prog_aux *aux)
+{
+	cpumask_var_t seen __free(free_cpumask_var) = CPUMASK_VAR_NULL;
+	struct scx_sched *sch;
+	bool alloced;
+	s32 cpu, cid;
+
+	/* GFP_KERNEL alloc must happen before the rcu read section */
+	alloced = zalloc_cpumask_var(&seen, GFP_KERNEL);
+
+	guard(rcu)();
+
+	sch = scx_prog_sched(aux);
+	if (unlikely(!sch))
+		return;
+
+	if (!alloced) {
+		scx_error(sch, "scx_bpf_cid_override: failed to allocate cpumask");
+		return;
+	}
+
+	if (scx_parent(sch)) {
+		scx_error(sch, "scx_bpf_cid_override() only allowed from root sched");
+		return;
+	}
+
+	if (cpu_to_cid__sz != nr_cpu_ids * sizeof(s32)) {
+		scx_error(sch, "scx_bpf_cid_override: expected %zu bytes, got %u",
+			  nr_cpu_ids * sizeof(s32), cpu_to_cid__sz);
+		return;
+	}
+
+	for_each_possible_cpu(cpu) {
+		s32 c = cpu_to_cid[cpu];
+
+		if (!cid_valid(sch, c))
+			return;
+		if (cpumask_test_and_set_cpu(c, seen)) {
+			scx_error(sch, "cid %d assigned to multiple cpus", c);
+			return;
+		}
+		scx_cpu_to_cid_tbl[cpu] = c;
+		scx_cid_to_cpu_tbl[c] = cpu;
+	}
+
+	/* Invalidate stale topo info - the override carries no topology. */
+	for (cid = 0; cid < num_possible_cpus(); cid++)
+		scx_cid_topo[cid] = SCX_CID_TOPO_NEG;
+}
+
 /**
  * scx_bpf_cid_to_cpu - Return the raw CPU id for @cid
  * @cid: cid to look up
@@ -282,6 +344,16 @@ __bpf_kfunc void scx_bpf_cid_topo(s32 cid, struct scx_cid_topo *out__uninit,
 
 __bpf_kfunc_end_defs();
 
+BTF_KFUNCS_START(scx_kfunc_ids_init)
+BTF_ID_FLAGS(func, scx_bpf_cid_override, KF_IMPLICIT_ARGS | KF_SLEEPABLE)
+BTF_KFUNCS_END(scx_kfunc_ids_init)
+
+static const struct btf_kfunc_id_set scx_kfunc_set_init = {
+	.owner	= THIS_MODULE,
+	.set	= &scx_kfunc_ids_init,
+	.filter	= scx_kfunc_context_filter,
+};
+
 BTF_KFUNCS_START(scx_kfunc_ids_cid)
 BTF_ID_FLAGS(func, scx_bpf_cid_to_cpu, KF_IMPLICIT_ARGS)
 BTF_ID_FLAGS(func, scx_bpf_cpu_to_cid, KF_IMPLICIT_ARGS)
@@ -295,7 +367,8 @@ static const struct btf_kfunc_id_set scx_kfunc_set_cid = {
 
 int scx_cid_kfunc_init(void)
 {
-	return register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &scx_kfunc_set_cid) ?:
+	return register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &scx_kfunc_set_init) ?:
+		register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &scx_kfunc_set_cid) ?:
 		register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &scx_kfunc_set_cid) ?:
 		register_btf_kfunc_id_set(BPF_PROG_TYPE_SYSCALL, &scx_kfunc_set_cid);
 }
diff --git a/kernel/sched/ext_cid.h b/kernel/sched/ext_cid.h
index 1dbe8262ccdd..52edb66b53fd 100644
--- a/kernel/sched/ext_cid.h
+++ b/kernel/sched/ext_cid.h
@@ -49,6 +49,7 @@ struct scx_sched;
 extern s16 *scx_cid_to_cpu_tbl;
 extern s16 *scx_cpu_to_cid_tbl;
 extern struct scx_cid_topo *scx_cid_topo;
+extern struct btf_id_set8 scx_kfunc_ids_init;
 
 s32 scx_cid_init(struct scx_sched *sch);
 int scx_cid_kfunc_init(void);
diff --git a/tools/sched_ext/include/scx/compat.bpf.h b/tools/sched_ext/include/scx/compat.bpf.h
index 2808003eef04..6b9d054c3e4f 100644
--- a/tools/sched_ext/include/scx/compat.bpf.h
+++ b/tools/sched_ext/include/scx/compat.bpf.h
@@ -121,6 +121,18 @@ static inline bool scx_bpf_sub_dispatch(u64 cgroup_id)
 	return false;
 }
 
+/*
+ * v7.2: scx_bpf_cid_override() for explicit cpu->cid mapping. Ignore if
+ * missing.
+ */
+void scx_bpf_cid_override___compat(const s32 *cpu_to_cid, u32 cpu_to_cid__sz) __ksym __weak;
+
+static inline void scx_bpf_cid_override(const s32 *cpu_to_cid, u32 cpu_to_cid__sz)
+{
+	if (bpf_ksym_exists(scx_bpf_cid_override___compat))
+		return scx_bpf_cid_override___compat(cpu_to_cid, cpu_to_cid__sz);
+}
+
 /**
  * __COMPAT_is_enq_cpu_selected - Test if SCX_ENQ_CPU_SELECTED is on
  * in a compatible way. We will preserve this __COMPAT helper until v6.16.
-- 
2.54.0

[PATCH 09/17] tools/sched_ext: Add struct_size() helpers to common.bpf.h

[Tejun Heo]

Add flex_array_size(), struct_size() and struct_size_t() to
scx/common.bpf.h so BPF schedulers can size flex-array-containing
structs the same way kernel code does. These are abbreviated forms of
the <linux/overflow.h> macros.

v3: Use offsetof() instead of sizeof() in struct_size() to match kernel
    semantics (no inflation from trailing struct padding). (Sashiko)

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Cheng-Yang Chou <yphbchou0911@gmail.com>
---
 tools/sched_ext/include/scx/common.bpf.h | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h
index 18f823d424cc..087ae4f79c60 100644
--- a/tools/sched_ext/include/scx/common.bpf.h
+++ b/tools/sched_ext/include/scx/common.bpf.h
@@ -1043,6 +1043,16 @@ static inline u64 scx_clock_irq(u32 cpu)
 	return irqt ? BPF_CORE_READ(irqt, total) : 0;
 }
 
+/* Abbreviated forms of <linux/overflow.h>'s struct_size() family. */
+#define flex_array_size(p, member, count)	\
+	((count) * sizeof(*(p)->member))
+
+#define struct_size(p, member, count)		\
+	(offsetof(typeof(*(p)), member) + flex_array_size(p, member, count))
+
+#define struct_size_t(type, member, count)	\
+	struct_size((type *)NULL, member, count)
+
 #include "compat.bpf.h"
 #include "enums.bpf.h"
 
-- 
2.54.0

[PATCH 10/17] sched_ext: Add cmask, a base-windowed bitmap over cid space

[Tejun Heo]

Sub-scheduler code built on cids needs bitmaps scoped to a slice of cid
space (e.g. the idle cids of a shard). A cpumask sized for NR_CPUS wastes
most of its bits for a small window and is awkward in BPF.

scx_cmask covers [base, base + nr_bits). bits[] is aligned to the global
64-cid grid: bits[0] spans [base & ~63, (base & ~63) + 64). Any two
cmasks therefore address bits[] against the same global windows, so
cross-cmask word ops reduce to

	dest->bits[i] OP= operand->bits[i - delta]

with no bit-shifting, at the cost of up to one extra storage word for
head misalignment. This alignment guarantee is the reason binary ops
can stay word-level; every mutating helper preserves it.

Kernel side in ext_cid.[hc]; BPF side in tools/sched_ext/include/scx/
cid.bpf.h. BPF side drops the scx_ prefix (redundant in BPF code) and
adds the extra helpers that basic idle-cpu selection needs.

No callers yet.

v2: Narrow to helpers that will be used in the planned changes;
    set/bit/find/zero ops will be added as usage develops.

v3: cmask_copy_from_kernel: validate src->base == 0 via probe-read;
    bit-level nr_bits check instead of round-up word count. (Sashiko)

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Cheng-Yang Chou <yphbchou0911@gmail.com>
---
 kernel/sched/ext_cid.h                   |  25 +
 kernel/sched/ext_types.h                 |  38 ++
 tools/sched_ext/include/scx/cid.bpf.h    | 667 +++++++++++++++++++++++
 tools/sched_ext/include/scx/common.bpf.h |   1 +
 4 files changed, 731 insertions(+)
 create mode 100644 tools/sched_ext/include/scx/cid.bpf.h

diff --git a/kernel/sched/ext_cid.h b/kernel/sched/ext_cid.h
index 52edb66b53fd..c3c429d2c8e2 100644
--- a/kernel/sched/ext_cid.h
+++ b/kernel/sched/ext_cid.h
@@ -127,4 +127,29 @@ static inline s32 scx_cpu_to_cid(struct scx_sched *sch, s32 cpu)
 	return __scx_cpu_to_cid(cpu);
 }
 
+static inline bool __scx_cmask_contains(const struct scx_cmask *m, u32 cid)
+{
+	return likely(cid >= m->base && cid < m->base + m->nr_bits);
+}
+
+/* Word in bits[] covering @cid. @cid must satisfy __scx_cmask_contains(). */
+static inline u64 *__scx_cmask_word(const struct scx_cmask *m, u32 cid)
+{
+	return (u64 *)&m->bits[cid / 64 - m->base / 64];
+}
+
+static inline void scx_cmask_init(struct scx_cmask *m, u32 base, u32 nr_bits)
+{
+	m->base = base;
+	m->nr_bits = nr_bits;
+	memset(m->bits, 0, SCX_CMASK_NR_WORDS(nr_bits) * sizeof(u64));
+}
+
+static inline void __scx_cmask_set(struct scx_cmask *m, u32 cid)
+{
+	if (!__scx_cmask_contains(m, cid))
+		return;
+	*__scx_cmask_word(m, cid) |= BIT_U64(cid & 63);
+}
+
 #endif /* _KERNEL_SCHED_EXT_CID_H */
diff --git a/kernel/sched/ext_types.h b/kernel/sched/ext_types.h
index be4d3565ae8d..ebb8cdf90612 100644
--- a/kernel/sched/ext_types.h
+++ b/kernel/sched/ext_types.h
@@ -63,4 +63,42 @@ struct scx_cid_topo {
 	s32 node_idx;
 };
 
+/*
+ * cmask: variable-length, base-windowed bitmap over cid space
+ * -----------------------------------------------------------
+ *
+ * A cmask covers the cid range [base, base + nr_bits). bits[] is aligned to the
+ * global 64-cid grid: bits[0] spans [base & ~63, (base & ~63) + 64), so the
+ * first (base & 63) bits of bits[0] are head padding and any tail past base +
+ * nr_bits is tail padding. Both must stay zero for the lifetime of the mask;
+ * all mutating helpers preserve that invariant.
+ *
+ * Grid alignment means two cmasks always address bits[] against the same global
+ * 64-cid windows, so cross-cmask word ops (AND, OR, ...) reduce to
+ *
+ *	dst->bits[i] OP= src->bits[i - delta]
+ *
+ * with no bit-shifting, regardless of how the two bases relate mod 64.
+ */
+struct scx_cmask {
+	u32 base;
+	u32 nr_bits;
+	DECLARE_FLEX_ARRAY(u64, bits);
+};
+
+/*
+ * Number of u64 words of bits[] storage that covers @nr_bits regardless of base
+ * alignment. The +1 absorbs up to 63 bits of head padding when base is not
+ * 64-aligned - always allocating one extra word beats branching on base or
+ * splitting the compute.
+ */
+#define SCX_CMASK_NR_WORDS(nr_bits)	(((nr_bits) + 63) / 64 + 1)
+
+/*
+ * Define an on-stack cmask for up to @cap_bits. @name is a struct scx_cmask *
+ * aliasing zero-initialized storage; call scx_cmask_init() to set base/nr_bits.
+ */
+#define SCX_CMASK_DEFINE(name, cap_bits)	\
+	DEFINE_RAW_FLEX(struct scx_cmask, name, bits, SCX_CMASK_NR_WORDS(cap_bits))
+
 #endif /* _KERNEL_SCHED_EXT_TYPES_H */
diff --git a/tools/sched_ext/include/scx/cid.bpf.h b/tools/sched_ext/include/scx/cid.bpf.h
new file mode 100644
index 000000000000..960108708eed
--- /dev/null
+++ b/tools/sched_ext/include/scx/cid.bpf.h
@@ -0,0 +1,667 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * BPF-side helpers for cids and cmasks. See kernel/sched/ext_cid.h for the
+ * authoritative layout and semantics. The BPF-side helpers use the cmask_*
+ * naming (no scx_ prefix); cmask is the SCX bitmap type so the prefix is
+ * redundant in BPF code. Atomics use __sync_val_compare_and_swap and every
+ * helper is inline (no .c counterpart).
+ *
+ * Included by scx/common.bpf.h; don't include directly.
+ *
+ * Copyright (c) 2026 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2026 Tejun Heo <tj@kernel.org>
+ */
+#ifndef __SCX_CID_BPF_H
+#define __SCX_CID_BPF_H
+
+#include "bpf_arena_common.bpf.h"
+
+#ifndef BIT_U64
+#define BIT_U64(nr)		(1ULL << (nr))
+#endif
+#ifndef GENMASK_U64
+#define GENMASK_U64(h, l)	((~0ULL << (l)) & (~0ULL >> (63 - (h))))
+#endif
+
+/*
+ * Storage cap for bounded loops over bits[]. Sized to cover NR_CPUS=8192 with
+ * one extra word for head-misalignment. Increase if deployment targets larger
+ * NR_CPUS.
+ */
+#ifndef CMASK_MAX_WORDS
+#define CMASK_MAX_WORDS 129
+#endif
+
+#define CMASK_NR_WORDS(nr_bits)		(((nr_bits) + 63) / 64 + 1)
+
+static __always_inline bool __cmask_contains(const struct scx_cmask __arena *m, u32 cid)
+{
+	return cid >= m->base && cid < m->base + m->nr_bits;
+}
+
+static __always_inline u64 __arena *__cmask_word(const struct scx_cmask __arena *m, u32 cid)
+{
+	return (u64 __arena *)&m->bits[cid / 64 - m->base / 64];
+}
+
+static __always_inline void cmask_init(struct scx_cmask __arena *m, u32 base, u32 nr_bits)
+{
+	u32 nr_words = CMASK_NR_WORDS(nr_bits), i;
+
+	m->base = base;
+	m->nr_bits = nr_bits;
+
+	bpf_for(i, 0, CMASK_MAX_WORDS) {
+		if (i >= nr_words)
+			break;
+		m->bits[i] = 0;
+	}
+}
+
+static __always_inline bool cmask_test(const struct scx_cmask __arena *m, u32 cid)
+{
+	if (!__cmask_contains(m, cid))
+		return false;
+	return *__cmask_word(m, cid) & BIT_U64(cid & 63);
+}
+
+/*
+ * x86 BPF JIT rejects BPF_OR | BPF_FETCH and BPF_AND | BPF_FETCH on arena
+ * pointers (see bpf_jit_supports_insn() in arch/x86/net/bpf_jit_comp.c). Only
+ * BPF_CMPXCHG / BPF_XCHG / BPF_ADD with FETCH are allowed. Implement
+ * test_and_{set,clear} and the atomic set/clear via a cmpxchg loop.
+ *
+ * CMASK_CAS_TRIES is far above what any non-pathological contention needs.
+ * Exhausting it means the bit update was lost, which corrupts the caller's view
+ * of the bitmap, so raise scx_bpf_error() to abort the scheduler.
+ */
+#define CMASK_CAS_TRIES		1024
+
+static __always_inline void cmask_set(struct scx_cmask __arena *m, u32 cid)
+{
+	u64 __arena *w;
+	u64 bit, old, new;
+	u32 i;
+
+	if (!__cmask_contains(m, cid))
+		return;
+	w = __cmask_word(m, cid);
+	bit = BIT_U64(cid & 63);
+	bpf_for(i, 0, CMASK_CAS_TRIES) {
+		old = *w;
+		if (old & bit)
+			return;
+		new = old | bit;
+		if (__sync_val_compare_and_swap(w, old, new) == old)
+			return;
+	}
+	scx_bpf_error("cmask_set CAS exhausted at cid %u", cid);
+}
+
+static __always_inline void cmask_clear(struct scx_cmask __arena *m, u32 cid)
+{
+	u64 __arena *w;
+	u64 bit, old, new;
+	u32 i;
+
+	if (!__cmask_contains(m, cid))
+		return;
+	w = __cmask_word(m, cid);
+	bit = BIT_U64(cid & 63);
+	bpf_for(i, 0, CMASK_CAS_TRIES) {
+		old = *w;
+		if (!(old & bit))
+			return;
+		new = old & ~bit;
+		if (__sync_val_compare_and_swap(w, old, new) == old)
+			return;
+	}
+	scx_bpf_error("cmask_clear CAS exhausted at cid %u", cid);
+}
+
+static __always_inline bool cmask_test_and_set(struct scx_cmask __arena *m, u32 cid)
+{
+	u64 __arena *w;
+	u64 bit, old, new;
+	u32 i;
+
+	if (!__cmask_contains(m, cid))
+		return false;
+	w = __cmask_word(m, cid);
+	bit = BIT_U64(cid & 63);
+	bpf_for(i, 0, CMASK_CAS_TRIES) {
+		old = *w;
+		if (old & bit)
+			return true;
+		new = old | bit;
+		if (__sync_val_compare_and_swap(w, old, new) == old)
+			return false;
+	}
+	scx_bpf_error("cmask_test_and_set CAS exhausted at cid %u", cid);
+	return false;
+}
+
+static __always_inline bool cmask_test_and_clear(struct scx_cmask __arena *m, u32 cid)
+{
+	u64 __arena *w;
+	u64 bit, old, new;
+	u32 i;
+
+	if (!__cmask_contains(m, cid))
+		return false;
+	w = __cmask_word(m, cid);
+	bit = BIT_U64(cid & 63);
+	bpf_for(i, 0, CMASK_CAS_TRIES) {
+		old = *w;
+		if (!(old & bit))
+			return false;
+		new = old & ~bit;
+		if (__sync_val_compare_and_swap(w, old, new) == old)
+			return true;
+	}
+	scx_bpf_error("cmask_test_and_clear CAS exhausted at cid %u", cid);
+	return false;
+}
+
+static __always_inline void __cmask_set(struct scx_cmask __arena *m, u32 cid)
+{
+	if (!__cmask_contains(m, cid))
+		return;
+	*__cmask_word(m, cid) |= BIT_U64(cid & 63);
+}
+
+static __always_inline void __cmask_clear(struct scx_cmask __arena *m, u32 cid)
+{
+	if (!__cmask_contains(m, cid))
+		return;
+	*__cmask_word(m, cid) &= ~BIT_U64(cid & 63);
+}
+
+static __always_inline bool __cmask_test_and_set(struct scx_cmask __arena *m, u32 cid)
+{
+	u64 bit = BIT_U64(cid & 63);
+	u64 __arena *w;
+	u64 prev;
+
+	if (!__cmask_contains(m, cid))
+		return false;
+	w = __cmask_word(m, cid);
+	prev = *w & bit;
+	*w |= bit;
+	return prev;
+}
+
+static __always_inline bool __cmask_test_and_clear(struct scx_cmask __arena *m, u32 cid)
+{
+	u64 bit = BIT_U64(cid & 63);
+	u64 __arena *w;
+	u64 prev;
+
+	if (!__cmask_contains(m, cid))
+		return false;
+	w = __cmask_word(m, cid);
+	prev = *w & bit;
+	*w &= ~bit;
+	return prev;
+}
+
+static __always_inline void cmask_zero(struct scx_cmask __arena *m)
+{
+	u32 nr_words = CMASK_NR_WORDS(m->nr_bits), i;
+
+	bpf_for(i, 0, CMASK_MAX_WORDS) {
+		if (i >= nr_words)
+			break;
+		m->bits[i] = 0;
+	}
+}
+
+/*
+ * BPF_-prefixed to avoid colliding with the kernel's anonymous CMASK_OP_*
+ * enum in ext_cid.c, which is exported via BTF and reachable through
+ * vmlinux.h.
+ */
+enum {
+	BPF_CMASK_OP_AND,
+	BPF_CMASK_OP_OR,
+	BPF_CMASK_OP_COPY,
+	BPF_CMASK_OP_ANDNOT,
+};
+
+static __always_inline void cmask_op_word(struct scx_cmask __arena *dst,
+					  const struct scx_cmask __arena *src,
+					  u32 di, u32 si, u64 mask, int op)
+{
+	u64 dv = dst->bits[di];
+	u64 sv = src->bits[si];
+	u64 rv;
+
+	if (op == BPF_CMASK_OP_AND)
+		rv = dv & sv;
+	else if (op == BPF_CMASK_OP_OR)
+		rv = dv | sv;
+	else if (op == BPF_CMASK_OP_ANDNOT)
+		rv = dv & ~sv;
+	else
+		rv = sv;
+
+	dst->bits[di] = (dv & ~mask) | (rv & mask);
+}
+
+static __always_inline void cmask_op(struct scx_cmask __arena *dst,
+				     const struct scx_cmask __arena *src, int op)
+{
+	u32 d_end = dst->base + dst->nr_bits;
+	u32 s_end = src->base + src->nr_bits;
+	u32 lo = dst->base > src->base ? dst->base : src->base;
+	u32 hi = d_end < s_end ? d_end : s_end;
+	u32 d_base = dst->base / 64;
+	u32 s_base = src->base / 64;
+	u32 lo_word, hi_word, i;
+	u64 head_mask, tail_mask;
+
+	if (lo >= hi)
+		return;
+
+	lo_word = lo / 64;
+	hi_word = (hi - 1) / 64;
+	head_mask = GENMASK_U64(63, lo & 63);
+	tail_mask = GENMASK_U64((hi - 1) & 63, 0);
+
+	bpf_for(i, 0, CMASK_MAX_WORDS) {
+		u32 w = lo_word + i;
+		u64 m;
+
+		if (w > hi_word)
+			break;
+
+		m = GENMASK_U64(63, 0);
+		if (w == lo_word)
+			m &= head_mask;
+		if (w == hi_word)
+			m &= tail_mask;
+
+		cmask_op_word(dst, src, w - d_base, w - s_base, m, op);
+	}
+}
+
+/*
+ * cmask_and/or/copy only modify @dst bits that lie in the intersection of
+ * [@dst->base, @dst->base + @dst->nr_bits) and [@src->base,
+ * @src->base + @src->nr_bits). Bits in @dst outside that window
+ * keep their prior values - in particular, cmask_copy() does NOT zero @dst
+ * bits that lie outside @src's range.
+ */
+static __always_inline void cmask_and(struct scx_cmask __arena *dst,
+				      const struct scx_cmask __arena *src)
+{
+	cmask_op(dst, src, BPF_CMASK_OP_AND);
+}
+
+static __always_inline void cmask_or(struct scx_cmask __arena *dst,
+				     const struct scx_cmask __arena *src)
+{
+	cmask_op(dst, src, BPF_CMASK_OP_OR);
+}
+
+static __always_inline void cmask_copy(struct scx_cmask __arena *dst,
+				       const struct scx_cmask __arena *src)
+{
+	cmask_op(dst, src, BPF_CMASK_OP_COPY);
+}
+
+static __always_inline void cmask_andnot(struct scx_cmask __arena *dst,
+					 const struct scx_cmask __arena *src)
+{
+	cmask_op(dst, src, BPF_CMASK_OP_ANDNOT);
+}
+
+/*
+ * True iff @a and @b have identical bits over their (assumed equal) range.
+ * Callers are expected to pass same-shape cmasks; differing shapes always
+ * compare unequal.
+ */
+static __always_inline bool cmask_equal(const struct scx_cmask __arena *a,
+					const struct scx_cmask __arena *b)
+{
+	u32 nr_words, i;
+
+	if (a->base != b->base || a->nr_bits != b->nr_bits)
+		return false;
+	nr_words = CMASK_NR_WORDS(a->nr_bits);
+
+	bpf_for(i, 0, CMASK_MAX_WORDS) {
+		if (i >= nr_words)
+			break;
+		if (a->bits[i] != b->bits[i])
+			return false;
+	}
+	return true;
+}
+
+/*
+ * True iff every bit set in @a is also set in @b over the intersection of
+ * their ranges. Bits of @a outside @b's range fail the test.
+ */
+static __always_inline bool cmask_subset(const struct scx_cmask __arena *a,
+					 const struct scx_cmask __arena *b)
+{
+	u32 a_end = a->base + a->nr_bits;
+	u32 b_end = b->base + b->nr_bits;
+	u32 a_wbase = a->base / 64;
+	u32 b_wbase = b->base / 64;
+	u32 nr_words, i;
+
+	/* any bit of @a outside @b's range is a subset violation */
+	if (a->base < b->base || a_end > b_end)
+		return false;
+
+	nr_words = CMASK_NR_WORDS(a->nr_bits);
+	bpf_for(i, 0, CMASK_MAX_WORDS) {
+		u32 wi_b;
+
+		if (i >= nr_words)
+			break;
+		wi_b = a_wbase + i - b_wbase;
+		if (a->bits[i] & ~b->bits[wi_b])
+			return false;
+	}
+	return true;
+}
+
+/**
+ * cmask_next_set - find the first set bit at or after @cid
+ * @m: cmask to search
+ * @cid: starting cid (clamped to @m->base if below)
+ *
+ * Returns the smallest set cid in [@cid, @m->base + @m->nr_bits), or
+ * @m->base + @m->nr_bits if none (the out-of-range sentinel matches the
+ * termination condition used by cmask_for_each()).
+ */
+static __always_inline u32 cmask_next_set(const struct scx_cmask __arena *m, u32 cid)
+{
+	u32 end = m->base + m->nr_bits;
+	u32 base = m->base / 64;
+	u32 last_wi = (end - 1) / 64 - base;
+	u32 start_wi, start_bit, i;
+
+	if (cid < m->base)
+		cid = m->base;
+	if (cid >= end)
+		return end;
+
+	start_wi = cid / 64 - base;
+	start_bit = cid & 63;
+
+	bpf_for(i, 0, CMASK_MAX_WORDS) {
+		u32 wi = start_wi + i;
+		u64 word;
+		u32 found;
+
+		if (wi > last_wi)
+			break;
+
+		word = m->bits[wi];
+		if (i == 0)
+			word &= GENMASK_U64(63, start_bit);
+		if (!word)
+			continue;
+
+		found = (base + wi) * 64 + __builtin_ctzll(word);
+		if (found >= end)
+			return end;
+		return found;
+	}
+	return end;
+}
+
+static __always_inline u32 cmask_first_set(const struct scx_cmask __arena *m)
+{
+	return cmask_next_set(m, m->base);
+}
+
+#define cmask_for_each(cid, m)							\
+	for ((cid) = cmask_first_set(m);					\
+	     (cid) < (m)->base + (m)->nr_bits;					\
+	     (cid) = cmask_next_set((m), (cid) + 1))
+
+/*
+ * Population count over [base, base + nr_bits). Padding bits in the head/tail
+ * words are guaranteed zero by the mutating helpers, so a flat popcount over
+ * all words is correct.
+ */
+static __always_inline u32 cmask_weight(const struct scx_cmask __arena *m)
+{
+	u32 nr_words = CMASK_NR_WORDS(m->nr_bits), i;
+	u32 count = 0;
+
+	bpf_for(i, 0, CMASK_MAX_WORDS) {
+		if (i >= nr_words)
+			break;
+		count += __builtin_popcountll(m->bits[i]);
+	}
+	return count;
+}
+
+/*
+ * True if @a and @b share any set bit. Walk only the intersection of their
+ * ranges, matching the semantics of cmask_and().
+ */
+static __always_inline bool cmask_intersects(const struct scx_cmask __arena *a,
+					     const struct scx_cmask __arena *b)
+{
+	u32 a_end = a->base + a->nr_bits;
+	u32 b_end = b->base + b->nr_bits;
+	u32 lo = a->base > b->base ? a->base : b->base;
+	u32 hi = a_end < b_end ? a_end : b_end;
+	u32 a_base = a->base / 64;
+	u32 b_base = b->base / 64;
+	u32 lo_word, hi_word, i;
+	u64 head_mask, tail_mask;
+
+	if (lo >= hi)
+		return false;
+
+	lo_word = lo / 64;
+	hi_word = (hi - 1) / 64;
+	head_mask = GENMASK_U64(63, lo & 63);
+	tail_mask = GENMASK_U64((hi - 1) & 63, 0);
+
+	bpf_for(i, 0, CMASK_MAX_WORDS) {
+		u32 w = lo_word + i;
+		u64 mask, av, bv;
+
+		if (w > hi_word)
+			break;
+
+		mask = GENMASK_U64(63, 0);
+		if (w == lo_word)
+			mask &= head_mask;
+		if (w == hi_word)
+			mask &= tail_mask;
+
+		av = a->bits[w - a_base] & mask;
+		bv = b->bits[w - b_base] & mask;
+		if (av & bv)
+			return true;
+	}
+	return false;
+}
+
+/*
+ * Find the next cid set in both @a and @b at or after @start, bounded by the
+ * intersection of the two ranges. Return a->base + a->nr_bits if none found.
+ *
+ * Building block for cmask_next_and_set_wrap(). Callers that want a bounded
+ * scan without wrap call this directly.
+ */
+static __always_inline u32 cmask_next_and_set(const struct scx_cmask __arena *a,
+					      const struct scx_cmask __arena *b,
+					      u32 start)
+{
+	u32 a_end = a->base + a->nr_bits;
+	u32 b_end = b->base + b->nr_bits;
+	u32 a_wbase = a->base / 64;
+	u32 b_wbase = b->base / 64;
+	u32 lo = a->base > b->base ? a->base : b->base;
+	u32 hi = a_end < b_end ? a_end : b_end;
+	u32 last_wi, start_wi, start_bit, i;
+
+	if (lo >= hi)
+		return a_end;
+	if (start < lo)
+		start = lo;
+	if (start >= hi)
+		return a_end;
+
+	last_wi = (hi - 1) / 64;
+	start_wi = start / 64;
+	start_bit = start & 63;
+
+	bpf_for(i, 0, CMASK_MAX_WORDS) {
+		u32 abs_wi = start_wi + i;
+		u64 word;
+		u32 found;
+
+		if (abs_wi > last_wi)
+			break;
+
+		word = a->bits[abs_wi - a_wbase] & b->bits[abs_wi - b_wbase];
+		if (i == 0)
+			word &= GENMASK_U64(63, start_bit);
+		if (!word)
+			continue;
+
+		found = abs_wi * 64 + __builtin_ctzll(word);
+		if (found >= hi)
+			return a_end;
+		return found;
+	}
+	return a_end;
+}
+
+/*
+ * Find the next set cid in @m at or after @start, wrapping to @m->base if no
+ * set bit is found in [start, m->base + m->nr_bits). Return m->base +
+ * m->nr_bits if @m is empty.
+ *
+ * Callers do round-robin distribution by passing (last_cid + 1) as @start.
+ */
+static __always_inline u32 cmask_next_set_wrap(const struct scx_cmask __arena *m,
+					       u32 start)
+{
+	u32 end = m->base + m->nr_bits;
+	u32 found;
+
+	found = cmask_next_set(m, start);
+	if (found < end || start <= m->base)
+		return found;
+
+	found = cmask_next_set(m, m->base);
+	return found < start ? found : end;
+}
+
+/*
+ * Find the next cid set in both @a and @b at or after @start, wrapping to
+ * @a->base if none found in the forward half. Return a->base + a->nr_bits
+ * if the intersection is empty.
+ *
+ * Callers do round-robin distribution by passing (last_cid + 1) as @start.
+ */
+static __always_inline u32 cmask_next_and_set_wrap(const struct scx_cmask __arena *a,
+						   const struct scx_cmask __arena *b,
+						   u32 start)
+{
+	u32 a_end = a->base + a->nr_bits;
+	u32 found;
+
+	found = cmask_next_and_set(a, b, start);
+	if (found < a_end || start <= a->base)
+		return found;
+
+	found = cmask_next_and_set(a, b, a->base);
+	return found < start ? found : a_end;
+}
+
+/**
+ * cmask_from_cpumask - translate a kernel cpumask to a cid-space cmask
+ * @m: cmask to fill. Zeroed first; only bits within [@m->base, @m->base +
+ *     @m->nr_bits) are updated - cpus mapping to cids outside that range
+ *     are ignored.
+ * @cpumask: kernel cpumask to translate
+ *
+ * For each cpu in @cpumask, set the cpu's cid in @m. Caller must ensure
+ * @cpumask stays stable across the call (e.g. RCU read lock for
+ * task->cpus_ptr).
+ */
+static __always_inline void cmask_from_cpumask(struct scx_cmask __arena *m,
+					       const struct cpumask *cpumask)
+{
+	u32 nr_cpu_ids = scx_bpf_nr_cpu_ids();
+	s32 cpu;
+
+	cmask_zero(m);
+	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(m, cid);
+	}
+}
+
+/**
+ * cmask_copy_from_kernel - probe-read a kernel cmask into an arena cmask
+ * @dst: arena cmask to fill; must have @dst->base == 0 and be sized for @src.
+ * @src: kernel-memory cmask (e.g. ops.set_cmask() arg); @src->base must be 0.
+ *
+ * Word-for-word copy; @src and @dst must share base 0 alignment. Triggers
+ * scx_bpf_error() on probe failure or precondition violation.
+ */
+static __always_inline void cmask_copy_from_kernel(struct scx_cmask __arena *dst,
+						   const struct scx_cmask *src)
+{
+	u32 base = 0, nr_bits = 0, nr_words, wi;
+
+	if (dst->base != 0) {
+		scx_bpf_error("cmask_copy_from_kernel requires dst->base == 0");
+		return;
+	}
+
+	if (bpf_probe_read_kernel(&base, sizeof(base), &src->base)) {
+		scx_bpf_error("probe-read cmask->base failed");
+		return;
+	}
+	if (base != 0) {
+		scx_bpf_error("cmask_copy_from_kernel requires src->base == 0");
+		return;
+	}
+
+	if (bpf_probe_read_kernel(&nr_bits, sizeof(nr_bits), &src->nr_bits)) {
+		scx_bpf_error("probe-read cmask->nr_bits failed");
+		return;
+	}
+
+	if (nr_bits > dst->nr_bits) {
+		scx_bpf_error("src cmask nr_bits=%u exceeds dst nr_bits=%u",
+			      nr_bits, dst->nr_bits);
+		return;
+	}
+
+	nr_words = CMASK_NR_WORDS(nr_bits);
+	cmask_zero(dst);
+	bpf_for(wi, 0, CMASK_MAX_WORDS) {
+		u64 word = 0;
+		if (wi >= nr_words)
+			break;
+		if (bpf_probe_read_kernel(&word, sizeof(u64), &src->bits[wi])) {
+			scx_bpf_error("probe-read cmask->bits[%u] failed", wi);
+			return;
+		}
+		dst->bits[wi] = word;
+	}
+}
+
+#endif /* __SCX_CID_BPF_H */
diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h
index 087ae4f79c60..ff57a7acdbeb 100644
--- a/tools/sched_ext/include/scx/common.bpf.h
+++ b/tools/sched_ext/include/scx/common.bpf.h
@@ -1055,5 +1055,6 @@ static inline u64 scx_clock_irq(u32 cpu)
 
 #include "compat.bpf.h"
 #include "enums.bpf.h"
+#include "cid.bpf.h"
 
 #endif	/* __SCX_COMMON_BPF_H */
-- 
2.54.0

[PATCH 11/17] sched_ext: Add cid-form kfunc wrappers alongside cpu-form

[Tejun Heo]

cpumask is awkward from BPF and unusable from arena; cid/cmask work in
both. Sub-sched enqueue will need cmask. Without full cid coverage a
scheduler has to mix cid and cpu forms, which is a subtle-bug factory.
Close the gap with a cid-native interface.

Pair every cpu-form kfunc that takes a cpu id with a cid-form
equivalent (kick, task placement, cpuperf query/set, per-cpu current
task, nr-cpu-ids). Add two cid-natives with no cpu-form sibling:
scx_bpf_this_cid() (cid of the running cpu, scx equivalent of
bpf_get_smp_processor_id) and scx_bpf_nr_online_cids().

scx_bpf_cpu_rq is deprecated; no cid-form counterpart. NUMA node info
is reachable via scx_bpf_cid_topo() on the BPF side.

Each cid-form wrapper is a thin cid -> cpu translation that delegates
to the cpu path, registered in the same context sets so usage
constraints match.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Cheng-Yang Chou <yphbchou0911@gmail.com>
---
 kernel/sched/ext.c                       | 184 +++++++++++++++++++++++
 tools/sched_ext/include/scx/common.bpf.h |   9 ++
 2 files changed, 193 insertions(+)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 6f0b30fa970f..3f77e83044a1 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -8864,6 +8864,28 @@ __bpf_kfunc void scx_bpf_kick_cpu(s32 cpu, u64 flags, const struct bpf_prog_aux
 		scx_kick_cpu(sch, cpu, flags);
 }
 
+/**
+ * scx_bpf_kick_cid - Trigger reschedule on the CPU mapped to @cid
+ * @cid: cid to kick
+ * @flags: %SCX_KICK_* flags
+ * @aux: implicit BPF argument to access bpf_prog_aux hidden from BPF progs
+ *
+ * cid-addressed equivalent of scx_bpf_kick_cpu().
+ */
+__bpf_kfunc void scx_bpf_kick_cid(s32 cid, u64 flags, const struct bpf_prog_aux *aux)
+{
+	struct scx_sched *sch;
+	s32 cpu;
+
+	guard(rcu)();
+	sch = scx_prog_sched(aux);
+	if (unlikely(!sch))
+		return;
+	cpu = scx_cid_to_cpu(sch, cid);
+	if (cpu >= 0)
+		scx_kick_cpu(sch, cpu, flags);
+}
+
 /**
  * scx_bpf_dsq_nr_queued - Return the number of queued tasks
  * @dsq_id: id of the DSQ
@@ -9287,6 +9309,29 @@ __bpf_kfunc u32 scx_bpf_cpuperf_cap(s32 cpu, const struct bpf_prog_aux *aux)
 		return SCX_CPUPERF_ONE;
 }
 
+/**
+ * scx_bpf_cidperf_cap - Query the maximum relative capacity of the CPU at @cid
+ * @cid: cid of the CPU to query
+ * @aux: implicit BPF argument to access bpf_prog_aux hidden from BPF progs
+ *
+ * cid-addressed equivalent of scx_bpf_cpuperf_cap().
+ */
+__bpf_kfunc u32 scx_bpf_cidperf_cap(s32 cid, const struct bpf_prog_aux *aux)
+{
+	struct scx_sched *sch;
+	s32 cpu;
+
+	guard(rcu)();
+
+	sch = scx_prog_sched(aux);
+	if (unlikely(!sch))
+		return SCX_CPUPERF_ONE;
+	cpu = scx_cid_to_cpu(sch, cid);
+	if (cpu < 0)
+		return SCX_CPUPERF_ONE;
+	return arch_scale_cpu_capacity(cpu);
+}
+
 /**
  * scx_bpf_cpuperf_cur - Query the current relative performance of a CPU
  * @cpu: CPU of interest
@@ -9315,6 +9360,29 @@ __bpf_kfunc u32 scx_bpf_cpuperf_cur(s32 cpu, const struct bpf_prog_aux *aux)
 		return SCX_CPUPERF_ONE;
 }
 
+/**
+ * scx_bpf_cidperf_cur - Query the current performance of the CPU at @cid
+ * @cid: cid of the CPU to query
+ * @aux: implicit BPF argument to access bpf_prog_aux hidden from BPF progs
+ *
+ * cid-addressed equivalent of scx_bpf_cpuperf_cur().
+ */
+__bpf_kfunc u32 scx_bpf_cidperf_cur(s32 cid, const struct bpf_prog_aux *aux)
+{
+	struct scx_sched *sch;
+	s32 cpu;
+
+	guard(rcu)();
+
+	sch = scx_prog_sched(aux);
+	if (unlikely(!sch))
+		return SCX_CPUPERF_ONE;
+	cpu = scx_cid_to_cpu(sch, cid);
+	if (cpu < 0)
+		return SCX_CPUPERF_ONE;
+	return arch_scale_freq_capacity(cpu);
+}
+
 /**
  * scx_bpf_cpuperf_set - Set the relative performance target of a CPU
  * @cpu: CPU of interest
@@ -9375,6 +9443,31 @@ __bpf_kfunc void scx_bpf_cpuperf_set(s32 cpu, u32 perf, const struct bpf_prog_au
 	}
 }
 
+/**
+ * scx_bpf_cidperf_set - Set the performance target of the CPU at @cid
+ * @cid: cid of the CPU to target
+ * @perf: target performance level [0, %SCX_CPUPERF_ONE]
+ * @aux: implicit BPF argument to access bpf_prog_aux hidden from BPF progs
+ *
+ * cid-addressed equivalent of scx_bpf_cpuperf_set().
+ */
+__bpf_kfunc void scx_bpf_cidperf_set(s32 cid, u32 perf,
+				     const struct bpf_prog_aux *aux)
+{
+	struct scx_sched *sch;
+	s32 cpu;
+
+	guard(rcu)();
+
+	sch = scx_prog_sched(aux);
+	if (unlikely(!sch))
+		return;
+	cpu = scx_cid_to_cpu(sch, cid);
+	if (cpu < 0)
+		return;
+	scx_bpf_cpuperf_set(cpu, perf, aux);
+}
+
 /**
  * scx_bpf_nr_node_ids - Return the number of possible node IDs
  *
@@ -9395,6 +9488,47 @@ __bpf_kfunc u32 scx_bpf_nr_cpu_ids(void)
 	return nr_cpu_ids;
 }
 
+/**
+ * scx_bpf_nr_cids - Return the size of the cid space
+ *
+ * Equals num_possible_cpus(). All valid cids are in [0, return value).
+ */
+__bpf_kfunc u32 scx_bpf_nr_cids(void)
+{
+	return num_possible_cpus();
+}
+
+/**
+ * scx_bpf_nr_online_cids - Return current count of online CPUs in cid space
+ *
+ * Return num_online_cpus(). The standard model restarts the scheduler on
+ * 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.
+ */
+__bpf_kfunc u32 scx_bpf_nr_online_cids(void)
+{
+	return num_online_cpus();
+}
+
+/**
+ * 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.
+ * The current cpu is trivially valid, so this is just a table lookup. Return
+ * -EINVAL if called from a non-SCX program before any scheduler has ever
+ * been enabled (the cid table is still unallocated at that point).
+ */
+__bpf_kfunc s32 scx_bpf_this_cid(void)
+{
+	s16 *tbl = READ_ONCE(scx_cpu_to_cid_tbl);
+
+	if (!tbl)
+		return -EINVAL;
+	return tbl[raw_smp_processor_id()];
+}
+
 /**
  * scx_bpf_get_possible_cpumask - Get a referenced kptr to cpu_possible_mask
  */
@@ -9443,6 +9577,23 @@ __bpf_kfunc s32 scx_bpf_task_cpu(const struct task_struct *p)
 	return task_cpu(p);
 }
 
+/**
+ * scx_bpf_task_cid - cid a task is currently associated with
+ * @p: task of interest
+ *
+ * cid-addressed equivalent of scx_bpf_task_cpu(). task_cpu(p) is always a
+ * valid cpu, so this is just a table lookup. Return -EINVAL if called from
+ * a non-SCX program before any scheduler has ever been enabled.
+ */
+__bpf_kfunc s32 scx_bpf_task_cid(const struct task_struct *p)
+{
+	s16 *tbl = READ_ONCE(scx_cpu_to_cid_tbl);
+
+	if (!tbl)
+		return -EINVAL;
+	return tbl[task_cpu(p)];
+}
+
 /**
  * scx_bpf_cpu_rq - Fetch the rq of a CPU
  * @cpu: CPU of the rq
@@ -9521,6 +9672,30 @@ __bpf_kfunc struct task_struct *scx_bpf_cpu_curr(s32 cpu, const struct bpf_prog_
 	return rcu_dereference(cpu_rq(cpu)->curr);
 }
 
+/**
+ * scx_bpf_cid_curr - Return the curr task on the CPU at @cid
+ * @cid: cid of interest
+ * @aux: implicit BPF argument to access bpf_prog_aux hidden from BPF progs
+ *
+ * cid-addressed equivalent of scx_bpf_cpu_curr(). Callers must hold RCU
+ * read lock (KF_RCU).
+ */
+__bpf_kfunc struct task_struct *scx_bpf_cid_curr(s32 cid, const struct bpf_prog_aux *aux)
+{
+	struct scx_sched *sch;
+	s32 cpu;
+
+	guard(rcu)();
+
+	sch = scx_prog_sched(aux);
+	if (unlikely(!sch))
+		return NULL;
+	cpu = scx_cid_to_cpu(sch, cid);
+	if (cpu < 0)
+		return NULL;
+	return rcu_dereference(cpu_rq(cpu)->curr);
+}
+
 /**
  * scx_bpf_tid_to_task - Look up a task by its scx tid
  * @tid: task ID previously read from p->scx.tid
@@ -9708,6 +9883,7 @@ BTF_KFUNCS_START(scx_kfunc_ids_any)
 BTF_ID_FLAGS(func, scx_bpf_task_set_slice, KF_IMPLICIT_ARGS | KF_RCU);
 BTF_ID_FLAGS(func, scx_bpf_task_set_dsq_vtime, KF_IMPLICIT_ARGS | KF_RCU);
 BTF_ID_FLAGS(func, scx_bpf_kick_cpu, KF_IMPLICIT_ARGS)
+BTF_ID_FLAGS(func, scx_bpf_kick_cid, KF_IMPLICIT_ARGS)
 BTF_ID_FLAGS(func, scx_bpf_dsq_nr_queued, KF_IMPLICIT_ARGS)
 BTF_ID_FLAGS(func, scx_bpf_destroy_dsq, KF_IMPLICIT_ARGS)
 BTF_ID_FLAGS(func, scx_bpf_dsq_peek, KF_IMPLICIT_ARGS | KF_RCU_PROTECTED | KF_RET_NULL)
@@ -9722,16 +9898,24 @@ BTF_ID_FLAGS(func, scx_bpf_dump_bstr, KF_IMPLICIT_ARGS)
 BTF_ID_FLAGS(func, scx_bpf_cpuperf_cap, KF_IMPLICIT_ARGS)
 BTF_ID_FLAGS(func, scx_bpf_cpuperf_cur, KF_IMPLICIT_ARGS)
 BTF_ID_FLAGS(func, scx_bpf_cpuperf_set, KF_IMPLICIT_ARGS)
+BTF_ID_FLAGS(func, scx_bpf_cidperf_cap, KF_IMPLICIT_ARGS)
+BTF_ID_FLAGS(func, scx_bpf_cidperf_cur, KF_IMPLICIT_ARGS)
+BTF_ID_FLAGS(func, scx_bpf_cidperf_set, KF_IMPLICIT_ARGS)
 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_this_cid)
 BTF_ID_FLAGS(func, scx_bpf_get_possible_cpumask, KF_ACQUIRE)
 BTF_ID_FLAGS(func, scx_bpf_get_online_cpumask, KF_ACQUIRE)
 BTF_ID_FLAGS(func, scx_bpf_put_cpumask, KF_RELEASE)
 BTF_ID_FLAGS(func, scx_bpf_task_running, KF_RCU)
 BTF_ID_FLAGS(func, scx_bpf_task_cpu, KF_RCU)
+BTF_ID_FLAGS(func, scx_bpf_task_cid, KF_RCU)
 BTF_ID_FLAGS(func, scx_bpf_cpu_rq, KF_IMPLICIT_ARGS)
 BTF_ID_FLAGS(func, scx_bpf_locked_rq, KF_IMPLICIT_ARGS | KF_RET_NULL)
 BTF_ID_FLAGS(func, scx_bpf_cpu_curr, KF_IMPLICIT_ARGS | KF_RET_NULL | KF_RCU_PROTECTED)
+BTF_ID_FLAGS(func, scx_bpf_cid_curr, KF_IMPLICIT_ARGS | KF_RET_NULL | KF_RCU_PROTECTED)
 BTF_ID_FLAGS(func, scx_bpf_tid_to_task, KF_RET_NULL | KF_RCU_PROTECTED)
 BTF_ID_FLAGS(func, scx_bpf_now)
 BTF_ID_FLAGS(func, scx_bpf_events)
diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h
index ff57a7acdbeb..5f715d69cde6 100644
--- a/tools/sched_ext/include/scx/common.bpf.h
+++ b/tools/sched_ext/include/scx/common.bpf.h
@@ -105,6 +105,15 @@ void scx_bpf_events(struct scx_event_stats *events, size_t events__sz) __ksym __
 s32 scx_bpf_cpu_to_cid(s32 cpu) __ksym __weak;
 s32 scx_bpf_cid_to_cpu(s32 cid) __ksym __weak;
 void scx_bpf_cid_topo(s32 cid, struct scx_cid_topo *out) __ksym __weak;
+void scx_bpf_kick_cid(s32 cid, u64 flags) __ksym __weak;
+s32 scx_bpf_task_cid(const struct task_struct *p) __ksym __weak;
+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;
+u32 scx_bpf_cidperf_cap(s32 cid) __ksym __weak;
+u32 scx_bpf_cidperf_cur(s32 cid) __ksym __weak;
+void scx_bpf_cidperf_set(s32 cid, u32 perf) __ksym __weak;
 
 /*
  * Use the following as @it__iter when calling scx_bpf_dsq_move[_vtime]() from
-- 
2.54.0

[PATCH 12/17] sched_ext: Add bpf_sched_ext_ops_cid struct_ops type

[Tejun Heo]

cpumask is awkward from BPF and unusable from arena; cid/cmask work in
both. Sub-sched enqueue will need cmask. Without a full cid interface,
schedulers end up mixing forms - a subtle-bug factory.

Add sched_ext_ops_cid, which mirrors sched_ext_ops with cid/cmask
replacing cpu/cpumask in the topology-carrying callbacks.
cpu_acquire/cpu_release are deprecated and absent; a prior patch
moved them past @priv so the cid-form can omit them without
disturbing shared-field offsets.

The two structs share byte-identical layout up to @priv, so the
existing bpf_scx init/check hooks, has_op bitmap, and
scx_kf_allow_flags[] are offset-indexed and apply to both.
BUILD_BUG_ON in scx_init() pins the shared-field and renamed-callback
offsets so any future drift trips at boot.

The kernel<->BPF boundary translates between cpu and cid:

- A static key, enabled on cid-form sched load, gates the translation
  so cpu-form schedulers pay nothing.
- dispatch, update_idle, cpu_online/offline and dump_cpu translate
  the cpu arg at the callsite.
- select_cpu also translates the returned cid back to a cpu.
- set_cpumask is wrapped to synthesize a cmask in a per-cpu scratch
  before calling the cid-form callback.

All scheds in a hierarchy share one form. The static key drives the
hot-path branch.

v2: Use struct_size() for the set_cmask_scratch percpu alloc. Move
    cid-shard fields and assertions into the later cid-shard patch.

v3: Drop `static` on scx_set_cmask_scratch; add extern in ext_internal.h.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Cheng-Yang Chou <yphbchou0911@gmail.com>
---
 kernel/sched/ext.c                       | 281 +++++++++++++++++++++--
 kernel/sched/ext_cid.c                   |  37 ++-
 kernel/sched/ext_cid.h                   |   9 +
 kernel/sched/ext_idle.c                  |   2 +-
 kernel/sched/ext_internal.h              | 109 ++++++++-
 tools/sched_ext/include/scx/compat.bpf.h |  12 +
 6 files changed, 429 insertions(+), 21 deletions(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 3f77e83044a1..8e3c60affc0b 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -513,6 +513,33 @@ do {										\
 		update_locked_rq(__prev_locked_rq);				\
 } while (0)
 
+/*
+ * Flipped on enable per sch->is_cid_type. Declared in ext_internal.h so
+ * subsystem inlines can read it.
+ */
+DEFINE_STATIC_KEY_FALSE(__scx_is_cid_type);
+
+/*
+ * scx_cpu_arg() wraps a cpu arg being handed to an SCX op. For cid-form
+ * schedulers it resolves to the matching cid; for cpu-form it passes @cpu
+ * through. scx_cpu_ret() is the inverse for a cpu/cid returned from an op
+ * (currently only ops.select_cpu); it validates the BPF-supplied cid and
+ * triggers scx_error() on @sch if invalid.
+ */
+static s32 scx_cpu_arg(s32 cpu)
+{
+	if (scx_is_cid_type())
+		return __scx_cpu_to_cid(cpu);
+	return cpu;
+}
+
+static s32 scx_cpu_ret(struct scx_sched *sch, s32 cpu_or_cid)
+{
+	if (cpu_or_cid < 0 || !scx_is_cid_type())
+		return cpu_or_cid;
+	return scx_cid_to_cpu(sch, cpu_or_cid);
+}
+
 #define SCX_CALL_OP_RET(sch, op, locked_rq, args...)				\
 ({										\
 	struct rq *__prev_locked_rq;						\
@@ -574,6 +601,41 @@ do {										\
 	__ret;									\
 })
 
+/**
+ * scx_call_op_set_cpumask - invoke ops.set_cpumask / ops_cid.set_cmask for @task
+ * @sch: scx_sched being invoked
+ * @rq: rq to update as the currently-locked rq, or NULL
+ * @task: task whose affinity is changing
+ * @cpumask: new cpumask
+ *
+ * For cid-form schedulers, translate @cpumask to a cmask via the per-cpu
+ * scratch in ext_cid.c and dispatch through the ops_cid union view. Caller
+ * must hold @rq's rq lock so this_cpu_ptr is stable across the call.
+ */
+static inline void scx_call_op_set_cpumask(struct scx_sched *sch, struct rq *rq,
+					   struct task_struct *task,
+					   const struct cpumask *cpumask)
+{
+	WARN_ON_ONCE(current->scx.kf_tasks[0]);
+	current->scx.kf_tasks[0] = task;
+	if (rq)
+		update_locked_rq(rq);
+
+	if (scx_is_cid_type()) {
+		struct scx_cmask *cmask = this_cpu_ptr(scx_set_cmask_scratch);
+
+		lockdep_assert_irqs_disabled();
+		scx_cpumask_to_cmask(cpumask, cmask);
+		sch->ops_cid.set_cmask(task, cmask);
+	} else {
+		sch->ops.set_cpumask(task, cpumask);
+	}
+
+	if (rq)
+		update_locked_rq(NULL);
+	current->scx.kf_tasks[0] = NULL;
+}
+
 /* see SCX_CALL_OP_TASK() */
 static __always_inline bool scx_kf_arg_task_ok(struct scx_sched *sch,
 							struct task_struct *p)
@@ -1679,7 +1741,7 @@ static struct scx_dispatch_q *find_dsq_for_dispatch(struct scx_sched *sch,
 		return &rq->scx.local_dsq;
 
 	if ((dsq_id & SCX_DSQ_LOCAL_ON) == SCX_DSQ_LOCAL_ON) {
-		s32 cpu = dsq_id & SCX_DSQ_LOCAL_CPU_MASK;
+		s32 cpu = scx_cpu_ret(sch, dsq_id & SCX_DSQ_LOCAL_CPU_MASK);
 
 		if (!scx_cpu_valid(sch, cpu, "in SCX_DSQ_LOCAL_ON dispatch verdict"))
 			return find_global_dsq(sch, tcpu);
@@ -2761,11 +2823,13 @@ scx_dispatch_sched(struct scx_sched *sch, struct rq *rq,
 		dspc->nr_tasks = 0;
 
 		if (nested) {
-			SCX_CALL_OP(sch, dispatch, rq, cpu, prev_on_sch ? prev : NULL);
+			SCX_CALL_OP(sch, dispatch, rq, scx_cpu_arg(cpu),
+				    prev_on_sch ? prev : NULL);
 		} else {
 			/* stash @prev so that nested invocations can access it */
 			rq->scx.sub_dispatch_prev = prev;
-			SCX_CALL_OP(sch, dispatch, rq, cpu, prev_on_sch ? prev : NULL);
+			SCX_CALL_OP(sch, dispatch, rq, scx_cpu_arg(cpu),
+				    prev_on_sch ? prev : NULL);
 			rq->scx.sub_dispatch_prev = NULL;
 		}
 
@@ -3260,7 +3324,9 @@ static int select_task_rq_scx(struct task_struct *p, int prev_cpu, int wake_flag
 		*ddsp_taskp = p;
 
 		this_rq()->scx.in_select_cpu = true;
-		cpu = SCX_CALL_OP_TASK_RET(sch, select_cpu, NULL, p, prev_cpu, wake_flags);
+		cpu = SCX_CALL_OP_TASK_RET(sch, select_cpu, NULL, p,
+					   scx_cpu_arg(prev_cpu), wake_flags);
+		cpu = scx_cpu_ret(sch, cpu);
 		this_rq()->scx.in_select_cpu = false;
 		p->scx.selected_cpu = cpu;
 		*ddsp_taskp = NULL;
@@ -3310,7 +3376,7 @@ static void set_cpus_allowed_scx(struct task_struct *p,
 	 * designation pointless. Cast it away when calling the operation.
 	 */
 	if (SCX_HAS_OP(sch, set_cpumask))
-		SCX_CALL_OP_TASK(sch, set_cpumask, task_rq(p), p, (struct cpumask *)p->cpus_ptr);
+		scx_call_op_set_cpumask(sch, task_rq(p), p, (struct cpumask *)p->cpus_ptr);
 }
 
 static void handle_hotplug(struct rq *rq, bool online)
@@ -3332,9 +3398,9 @@ static void handle_hotplug(struct rq *rq, bool online)
 		scx_idle_update_selcpu_topology(&sch->ops);
 
 	if (online && SCX_HAS_OP(sch, cpu_online))
-		SCX_CALL_OP(sch, cpu_online, NULL, cpu);
+		SCX_CALL_OP(sch, cpu_online, NULL, scx_cpu_arg(cpu));
 	else if (!online && SCX_HAS_OP(sch, cpu_offline))
-		SCX_CALL_OP(sch, cpu_offline, NULL, cpu);
+		SCX_CALL_OP(sch, cpu_offline, NULL, scx_cpu_arg(cpu));
 	else
 		scx_exit(sch, SCX_EXIT_UNREG_KERN,
 			 SCX_ECODE_ACT_RESTART | SCX_ECODE_RSN_HOTPLUG,
@@ -3919,7 +3985,7 @@ static void switching_to_scx(struct rq *rq, struct task_struct *p)
 	 * different scheduler class. Keep the BPF scheduler up-to-date.
 	 */
 	if (SCX_HAS_OP(sch, set_cpumask))
-		SCX_CALL_OP_TASK(sch, set_cpumask, rq, p, (struct cpumask *)p->cpus_ptr);
+		scx_call_op_set_cpumask(sch, rq, p, (struct cpumask *)p->cpus_ptr);
 }
 
 static void switched_from_scx(struct rq *rq, struct task_struct *p)
@@ -5945,6 +6011,7 @@ static void scx_root_disable(struct scx_sched *sch)
 
 	/* no task is on scx, turn off all the switches and flush in-progress calls */
 	static_branch_disable(&__scx_enabled);
+	static_branch_disable(&__scx_is_cid_type);
 	if (sch->ops.flags & SCX_OPS_TID_TO_TASK)
 		static_branch_disable(&__scx_tid_to_task_enabled);
 	bitmap_zero(sch->has_op, SCX_OPI_END);
@@ -6360,7 +6427,7 @@ static void scx_dump_state(struct scx_sched *sch, struct scx_exit_info *ei,
 		used = seq_buf_used(&ns);
 		if (SCX_HAS_OP(sch, dump_cpu)) {
 			ops_dump_init(&ns, "  ");
-			SCX_CALL_OP(sch, dump_cpu, rq, &dctx, cpu, idle);
+			SCX_CALL_OP(sch, dump_cpu, rq, &dctx, scx_cpu_arg(cpu), idle);
 			ops_dump_exit();
 		}
 
@@ -6516,7 +6583,11 @@ static struct scx_sched_pnode *alloc_pnode(struct scx_sched *sch, int node)
  */
 struct scx_enable_cmd {
 	struct kthread_work	work;
-	struct sched_ext_ops	*ops;
+	union {
+		struct sched_ext_ops		*ops;
+		struct sched_ext_ops_cid	*ops_cid;
+	};
+	bool			is_cid_type;
 	int			ret;
 };
 
@@ -6524,10 +6595,11 @@ struct scx_enable_cmd {
  * Allocate and initialize a new scx_sched. @cgrp's reference is always
  * consumed whether the function succeeds or fails.
  */
-static struct scx_sched *scx_alloc_and_add_sched(struct sched_ext_ops *ops,
+static struct scx_sched *scx_alloc_and_add_sched(struct scx_enable_cmd *cmd,
 						 struct cgroup *cgrp,
 						 struct scx_sched *parent)
 {
+	struct sched_ext_ops *ops = cmd->ops;
 	struct scx_sched *sch;
 	s32 level = parent ? parent->level + 1 : 0;
 	s32 node, cpu, ret, bypass_fail_cpu = nr_cpu_ids;
@@ -6619,7 +6691,18 @@ static struct scx_sched *scx_alloc_and_add_sched(struct sched_ext_ops *ops,
 		ret = -ENOMEM;
 		goto err_free_lb_cpumask;
 	}
-	sch->ops = *ops;
+	/*
+	 * Copy ops through the right union view. For cid-form the source is
+	 * struct sched_ext_ops_cid which lacks the trailing cpu_acquire/
+	 * cpu_release; those stay zero from kzalloc.
+	 */
+	if (cmd->is_cid_type) {
+		sch->ops_cid = *cmd->ops_cid;
+		sch->is_cid_type = true;
+	} else {
+		sch->ops = *cmd->ops;
+	}
+
 	rcu_assign_pointer(ops->priv, sch);
 
 	sch->kobj.kset = scx_kset;
@@ -6756,7 +6839,12 @@ static int validate_ops(struct scx_sched *sch, const struct sched_ext_ops *ops)
 		return -EINVAL;
 	}
 
-	if (ops->cpu_acquire || ops->cpu_release)
+	/*
+	 * cid-form's struct is shorter and doesn't include the cpu_acquire /
+	 * cpu_release tail; reading those fields off a cid-form @ops would
+	 * run past the BPF allocation. Skip for cid-form.
+	 */
+	if (!sch->is_cid_type && (ops->cpu_acquire || ops->cpu_release))
 		pr_warn("ops->cpu_acquire/release() are deprecated, use sched_switch TP instead\n");
 
 	return 0;
@@ -6792,12 +6880,15 @@ static void scx_root_enable_workfn(struct kthread_work *work)
 #ifdef CONFIG_EXT_SUB_SCHED
 	cgroup_get(cgrp);
 #endif
-	sch = scx_alloc_and_add_sched(ops, cgrp, NULL);
+	sch = scx_alloc_and_add_sched(cmd, cgrp, NULL);
 	if (IS_ERR(sch)) {
 		ret = PTR_ERR(sch);
 		goto err_free_tid_hash;
 	}
 
+	if (sch->is_cid_type)
+		static_branch_enable(&__scx_is_cid_type);
+
 	/*
 	 * Transition to ENABLING and clear exit info to arm the disable path.
 	 * Failure triggers full disabling from here on.
@@ -7119,7 +7210,7 @@ static void scx_sub_enable_workfn(struct kthread_work *work)
 	raw_spin_unlock_irq(&scx_sched_lock);
 
 	/* scx_alloc_and_add_sched() consumes @cgrp whether it succeeds or not */
-	sch = scx_alloc_and_add_sched(ops, cgrp, parent);
+	sch = scx_alloc_and_add_sched(cmd, cgrp, parent);
 	kobject_put(&parent->kobj);
 	if (IS_ERR(sch)) {
 		ret = PTR_ERR(sch);
@@ -7570,6 +7661,13 @@ static int bpf_scx_reg(void *kdata, struct bpf_link *link)
 	return scx_enable(&cmd, link);
 }
 
+static int bpf_scx_reg_cid(void *kdata, struct bpf_link *link)
+{
+	struct scx_enable_cmd cmd = { .ops_cid = kdata, .is_cid_type = true };
+
+	return scx_enable(&cmd, link);
+}
+
 static void bpf_scx_unreg(void *kdata, struct bpf_link *link)
 {
 	struct sched_ext_ops *ops = kdata;
@@ -7701,6 +7799,73 @@ static struct bpf_struct_ops bpf_sched_ext_ops = {
 	.cfi_stubs = &__bpf_ops_sched_ext_ops
 };
 
+/*
+ * cid-form cfi stubs. Stubs whose signatures match the cpu-form (param types
+ * identical, only param names differ across structs) are reused; only
+ * set_cmask needs a fresh stub since the second argument type differs.
+ */
+static void sched_ext_ops_cid__set_cmask(struct task_struct *p,
+					 const struct scx_cmask *cmask) {}
+
+static struct sched_ext_ops_cid __bpf_ops_sched_ext_ops_cid = {
+	.select_cid		= sched_ext_ops__select_cpu,
+	.enqueue		= sched_ext_ops__enqueue,
+	.dequeue		= sched_ext_ops__dequeue,
+	.dispatch		= sched_ext_ops__dispatch,
+	.tick			= sched_ext_ops__tick,
+	.runnable		= sched_ext_ops__runnable,
+	.running		= sched_ext_ops__running,
+	.stopping		= sched_ext_ops__stopping,
+	.quiescent		= sched_ext_ops__quiescent,
+	.yield			= sched_ext_ops__yield,
+	.core_sched_before	= sched_ext_ops__core_sched_before,
+	.set_weight		= sched_ext_ops__set_weight,
+	.set_cmask		= sched_ext_ops_cid__set_cmask,
+	.update_idle		= sched_ext_ops__update_idle,
+	.init_task		= sched_ext_ops__init_task,
+	.exit_task		= sched_ext_ops__exit_task,
+	.enable			= sched_ext_ops__enable,
+	.disable		= sched_ext_ops__disable,
+#ifdef CONFIG_EXT_GROUP_SCHED
+	.cgroup_init		= sched_ext_ops__cgroup_init,
+	.cgroup_exit		= sched_ext_ops__cgroup_exit,
+	.cgroup_prep_move	= sched_ext_ops__cgroup_prep_move,
+	.cgroup_move		= sched_ext_ops__cgroup_move,
+	.cgroup_cancel_move	= sched_ext_ops__cgroup_cancel_move,
+	.cgroup_set_weight	= sched_ext_ops__cgroup_set_weight,
+	.cgroup_set_bandwidth	= sched_ext_ops__cgroup_set_bandwidth,
+	.cgroup_set_idle	= sched_ext_ops__cgroup_set_idle,
+#endif
+	.sub_attach		= sched_ext_ops__sub_attach,
+	.sub_detach		= sched_ext_ops__sub_detach,
+	.cid_online		= sched_ext_ops__cpu_online,
+	.cid_offline		= sched_ext_ops__cpu_offline,
+	.init			= sched_ext_ops__init,
+	.exit			= sched_ext_ops__exit,
+	.dump			= sched_ext_ops__dump,
+	.dump_cid		= sched_ext_ops__dump_cpu,
+	.dump_task		= sched_ext_ops__dump_task,
+};
+
+/*
+ * The cid-form struct_ops shares all bpf_struct_ops hooks with the cpu form.
+ * init_member, check_member, reg, unreg, etc. process kdata as the byte block
+ * verified to match by the BUILD_BUG_ON checks in scx_init().
+ */
+static struct bpf_struct_ops bpf_sched_ext_ops_cid = {
+	.verifier_ops = &bpf_scx_verifier_ops,
+	.reg = bpf_scx_reg_cid,
+	.unreg = bpf_scx_unreg,
+	.check_member = bpf_scx_check_member,
+	.init_member = bpf_scx_init_member,
+	.init = bpf_scx_init,
+	.update = bpf_scx_update,
+	.validate = bpf_scx_validate,
+	.name = "sched_ext_ops_cid",
+	.owner = THIS_MODULE,
+	.cfi_stubs = &__bpf_ops_sched_ext_ops_cid
+};
+
 
 /********************************************************************************
  * System integration and init.
@@ -8912,7 +9077,7 @@ __bpf_kfunc s32 scx_bpf_dsq_nr_queued(u64 dsq_id, const struct bpf_prog_aux *aux
 		ret = READ_ONCE(this_rq()->scx.local_dsq.nr);
 		goto out;
 	} else if ((dsq_id & SCX_DSQ_LOCAL_ON) == SCX_DSQ_LOCAL_ON) {
-		s32 cpu = dsq_id & SCX_DSQ_LOCAL_CPU_MASK;
+		s32 cpu = scx_cpu_ret(sch, dsq_id & SCX_DSQ_LOCAL_CPU_MASK);
 
 		if (scx_cpu_valid(sch, cpu, NULL)) {
 			ret = READ_ONCE(cpu_rq(cpu)->scx.local_dsq.nr);
@@ -10019,8 +10184,15 @@ int scx_kfunc_context_filter(const struct bpf_prog *prog, u32 kfunc_id)
 
 	/*
 	 * Non-SCX struct_ops: SCX kfuncs are not permitted.
-	 */
-	if (prog->aux->st_ops != &bpf_sched_ext_ops)
+	 *
+	 * Both bpf_sched_ext_ops (cpu-form) and bpf_sched_ext_ops_cid
+	 * (cid-form) are valid SCX struct_ops. Member offsets match between
+	 * the two (verified by BUILD_BUG_ON in scx_init()), so the shared
+	 * scx_kf_allow_flags[] table indexed by SCX_MOFF_IDX(moff) applies to
+	 * both.
+	 */
+	if (prog->aux->st_ops != &bpf_sched_ext_ops &&
+	    prog->aux->st_ops != &bpf_sched_ext_ops_cid)
 		return -EACCES;
 
 	/* SCX struct_ops: check the per-op allow list. */
@@ -10050,6 +10222,73 @@ static int __init scx_init(void)
 {
 	int ret;
 
+	/*
+	 * sched_ext_ops_cid mirrors sched_ext_ops up to and including @priv.
+	 * Both bpf_scx_init_member() and bpf_scx_check_member() use offsets
+	 * from struct sched_ext_ops; sched_ext_ops_cid relies on those offsets
+	 * matching for the shared fields. Catch any drift at boot.
+	 */
+#define CID_OFFSET_MATCH(cpu_field, cid_field)					\
+	BUILD_BUG_ON(offsetof(struct sched_ext_ops, cpu_field) !=		\
+		     offsetof(struct sched_ext_ops_cid, cid_field))
+	/* data fields used by bpf_scx_init_member() */
+	CID_OFFSET_MATCH(dispatch_max_batch, dispatch_max_batch);
+	CID_OFFSET_MATCH(flags, flags);
+	CID_OFFSET_MATCH(name, name);
+	CID_OFFSET_MATCH(timeout_ms, timeout_ms);
+	CID_OFFSET_MATCH(exit_dump_len, exit_dump_len);
+	CID_OFFSET_MATCH(hotplug_seq, hotplug_seq);
+	CID_OFFSET_MATCH(sub_cgroup_id, sub_cgroup_id);
+	/* shared callbacks: the union view requires byte-for-byte offset match */
+	CID_OFFSET_MATCH(enqueue, enqueue);
+	CID_OFFSET_MATCH(dequeue, dequeue);
+	CID_OFFSET_MATCH(dispatch, dispatch);
+	CID_OFFSET_MATCH(tick, tick);
+	CID_OFFSET_MATCH(runnable, runnable);
+	CID_OFFSET_MATCH(running, running);
+	CID_OFFSET_MATCH(stopping, stopping);
+	CID_OFFSET_MATCH(quiescent, quiescent);
+	CID_OFFSET_MATCH(yield, yield);
+	CID_OFFSET_MATCH(core_sched_before, core_sched_before);
+	CID_OFFSET_MATCH(set_weight, set_weight);
+	CID_OFFSET_MATCH(update_idle, update_idle);
+	CID_OFFSET_MATCH(init_task, init_task);
+	CID_OFFSET_MATCH(exit_task, exit_task);
+	CID_OFFSET_MATCH(enable, enable);
+	CID_OFFSET_MATCH(disable, disable);
+	CID_OFFSET_MATCH(dump, dump);
+	CID_OFFSET_MATCH(dump_task, dump_task);
+	CID_OFFSET_MATCH(sub_attach, sub_attach);
+	CID_OFFSET_MATCH(sub_detach, sub_detach);
+	CID_OFFSET_MATCH(init, init);
+	CID_OFFSET_MATCH(exit, exit);
+#ifdef CONFIG_EXT_GROUP_SCHED
+	CID_OFFSET_MATCH(cgroup_init, cgroup_init);
+	CID_OFFSET_MATCH(cgroup_exit, cgroup_exit);
+	CID_OFFSET_MATCH(cgroup_prep_move, cgroup_prep_move);
+	CID_OFFSET_MATCH(cgroup_move, cgroup_move);
+	CID_OFFSET_MATCH(cgroup_cancel_move, cgroup_cancel_move);
+	CID_OFFSET_MATCH(cgroup_set_weight, cgroup_set_weight);
+	CID_OFFSET_MATCH(cgroup_set_bandwidth, cgroup_set_bandwidth);
+	CID_OFFSET_MATCH(cgroup_set_idle, cgroup_set_idle);
+#endif
+	/* renamed callbacks must occupy the same slot as their cpu-form sibling */
+	CID_OFFSET_MATCH(select_cpu, select_cid);
+	CID_OFFSET_MATCH(set_cpumask, set_cmask);
+	CID_OFFSET_MATCH(cpu_online, cid_online);
+	CID_OFFSET_MATCH(cpu_offline, cid_offline);
+	CID_OFFSET_MATCH(dump_cpu, dump_cid);
+	/* @priv tail must align since both share the same data block */
+	CID_OFFSET_MATCH(priv, priv);
+	/*
+	 * cid-form must end exactly at @priv - validate_ops() skips
+	 * cpu_acquire/cpu_release for cid-form because reading those fields
+	 * past the BPF allocation would be UB.
+	 */
+	BUILD_BUG_ON(sizeof(struct sched_ext_ops_cid) !=
+		     offsetofend(struct sched_ext_ops, priv));
+#undef CID_OFFSET_MATCH
+
 	/*
 	 * kfunc registration can't be done from init_sched_ext_class() as
 	 * register_btf_kfunc_id_set() needs most of the system to be up.
@@ -10100,6 +10339,12 @@ static int __init scx_init(void)
 		return ret;
 	}
 
+	ret = register_bpf_struct_ops(&bpf_sched_ext_ops_cid, sched_ext_ops_cid);
+	if (ret) {
+		pr_err("sched_ext: Failed to register cid struct_ops (%d)\n", ret);
+		return ret;
+	}
+
 	ret = register_pm_notifier(&scx_pm_notifier);
 	if (ret) {
 		pr_err("sched_ext: Failed to register PM notifier (%d)\n", ret);
diff --git a/kernel/sched/ext_cid.c b/kernel/sched/ext_cid.c
index 607937d9e4d1..bdd8ef8eae3d 100644
--- a/kernel/sched/ext_cid.c
+++ b/kernel/sched/ext_cid.c
@@ -7,6 +7,14 @@
  */
 #include <linux/cacheinfo.h>
 
+/*
+ * Per-cpu scratch cmask used by scx_call_op_set_cpumask() to synthesize a
+ * cmask from a cpumask. Allocated alongside the cid arrays on first enable
+ * and never freed. Sized to the full cid space. Caller holds rq lock so
+ * this_cpu_ptr is safe.
+ */
+struct scx_cmask __percpu *scx_set_cmask_scratch;
+
 /*
  * cid tables.
  *
@@ -46,6 +54,7 @@ static s32 scx_cid_arrays_alloc(void)
 	u32 npossible = num_possible_cpus();
 	s16 *cid_to_cpu, *cpu_to_cid;
 	struct scx_cid_topo *cid_topo;
+	struct scx_cmask __percpu *set_cmask_scratch;
 
 	if (scx_cid_to_cpu_tbl)
 		return 0;
@@ -53,17 +62,22 @@ static s32 scx_cid_arrays_alloc(void)
 	cid_to_cpu = kzalloc_objs(*scx_cid_to_cpu_tbl, npossible, GFP_KERNEL);
 	cpu_to_cid = kzalloc_objs(*scx_cpu_to_cid_tbl, nr_cpu_ids, GFP_KERNEL);
 	cid_topo = kmalloc_objs(*scx_cid_topo, npossible, GFP_KERNEL);
+	set_cmask_scratch = __alloc_percpu(struct_size(set_cmask_scratch, bits,
+						       SCX_CMASK_NR_WORDS(npossible)),
+					   sizeof(u64));
 
-	if (!cid_to_cpu || !cpu_to_cid || !cid_topo) {
+	if (!cid_to_cpu || !cpu_to_cid || !cid_topo || !set_cmask_scratch) {
 		kfree(cid_to_cpu);
 		kfree(cpu_to_cid);
 		kfree(cid_topo);
+		free_percpu(set_cmask_scratch);
 		return -ENOMEM;
 	}
 
 	WRITE_ONCE(scx_cid_to_cpu_tbl, cid_to_cpu);
 	WRITE_ONCE(scx_cpu_to_cid_tbl, cpu_to_cid);
 	WRITE_ONCE(scx_cid_topo, cid_topo);
+	WRITE_ONCE(scx_set_cmask_scratch, set_cmask_scratch);
 	return 0;
 }
 
@@ -208,6 +222,27 @@ s32 scx_cid_init(struct scx_sched *sch)
 	return 0;
 }
 
+/**
+ * scx_cpumask_to_cmask - Translate a kernel cpumask into a cmask
+ * @src: source cpumask
+ * @dst: cmask to write
+ *
+ * Initialize @dst to cover the full cid space [0, num_possible_cpus()) and
+ * set the bit for each cid whose cpu is in @src.
+ */
+void scx_cpumask_to_cmask(const struct cpumask *src, struct scx_cmask *dst)
+{
+	s32 cpu;
+
+	scx_cmask_init(dst, 0, num_possible_cpus());
+	for_each_cpu(cpu, src) {
+		s32 cid = __scx_cpu_to_cid(cpu);
+
+		if (cid >= 0)
+			__scx_cmask_set(dst, cid);
+	}
+}
+
 __bpf_kfunc_start_defs();
 
 /**
diff --git a/kernel/sched/ext_cid.h b/kernel/sched/ext_cid.h
index c3c429d2c8e2..f41d48afb7d1 100644
--- a/kernel/sched/ext_cid.h
+++ b/kernel/sched/ext_cid.h
@@ -53,6 +53,7 @@ extern struct btf_id_set8 scx_kfunc_ids_init;
 
 s32 scx_cid_init(struct scx_sched *sch);
 int scx_cid_kfunc_init(void);
+void scx_cpumask_to_cmask(const struct cpumask *src, struct scx_cmask *dst);
 
 /**
  * cid_valid - Verify a cid value, to be used on ops input args
@@ -127,6 +128,14 @@ static inline s32 scx_cpu_to_cid(struct scx_sched *sch, s32 cpu)
 	return __scx_cpu_to_cid(cpu);
 }
 
+/**
+ * scx_is_cid_type - Test whether the active scheduler hierarchy is cid-form
+ */
+static inline bool scx_is_cid_type(void)
+{
+	return static_branch_unlikely(&__scx_is_cid_type);
+}
+
 static inline bool __scx_cmask_contains(const struct scx_cmask *m, u32 cid)
 {
 	return likely(cid >= m->base && cid < m->base + m->nr_bits);
diff --git a/kernel/sched/ext_idle.c b/kernel/sched/ext_idle.c
index 860c4634f60e..41785f65bbb2 100644
--- a/kernel/sched/ext_idle.c
+++ b/kernel/sched/ext_idle.c
@@ -788,7 +788,7 @@ void __scx_update_idle(struct rq *rq, bool idle, bool do_notify)
 	 */
 	if (SCX_HAS_OP(sch, update_idle) && do_notify &&
 	    !scx_bypassing(sch, cpu_of(rq)))
-		SCX_CALL_OP(sch, update_idle, rq, cpu_of(rq), idle);
+		SCX_CALL_OP(sch, update_idle, rq, scx_cpu_arg(cpu_of(rq)), idle);
 }
 
 static void reset_idle_masks(struct sched_ext_ops *ops)
diff --git a/kernel/sched/ext_internal.h b/kernel/sched/ext_internal.h
index 919d4aa08656..e5f52986d317 100644
--- a/kernel/sched/ext_internal.h
+++ b/kernel/sched/ext_internal.h
@@ -847,6 +847,93 @@ struct sched_ext_ops {
 	void (*cpu_release)(s32 cpu, struct scx_cpu_release_args *args);
 };
 
+/**
+ * struct sched_ext_ops_cid - cid-form alternative to struct sched_ext_ops
+ *
+ * Mirrors struct sched_ext_ops with cpu/cpumask substituted with cid/cmask
+ * where applicable. Layout up to and including @priv matches sched_ext_ops
+ * byte-for-byte (verified by BUILD_BUG_ON checks at scx_init() time) so
+ * shared field offsets work for both struct types in bpf_scx_init_member()
+ * and bpf_scx_check_member(). The deprecated cpu_acquire/cpu_release
+ * callbacks at the tail of sched_ext_ops are omitted here entirely.
+ *
+ * Differences from sched_ext_ops:
+ *   - select_cpu       -> select_cid (returns cid)
+ *   - dispatch         -> dispatch (cpu arg is now cid)
+ *   - update_idle      -> update_idle (cpu arg is now cid)
+ *   - set_cpumask      -> set_cmask (cmask instead of cpumask)
+ *   - cpu_online       -> cid_online
+ *   - cpu_offline      -> cid_offline
+ *   - dump_cpu         -> dump_cid
+ *   - cpu_acquire/cpu_release  -> not present (deprecated in sched_ext_ops)
+ *
+ * BPF schedulers using this type cannot call cpu-form scx_bpf_* kfuncs;
+ * use the cid-form variants instead. Enforced at BPF verifier time via
+ * scx_kfunc_context_filter() branching on prog->aux->st_ops.
+ *
+ * See sched_ext_ops for callback documentation.
+ */
+struct sched_ext_ops_cid {
+	s32 (*select_cid)(struct task_struct *p, s32 prev_cid, u64 wake_flags);
+	void (*enqueue)(struct task_struct *p, u64 enq_flags);
+	void (*dequeue)(struct task_struct *p, u64 deq_flags);
+	void (*dispatch)(s32 cid, struct task_struct *prev);
+	void (*tick)(struct task_struct *p);
+	void (*runnable)(struct task_struct *p, u64 enq_flags);
+	void (*running)(struct task_struct *p);
+	void (*stopping)(struct task_struct *p, bool runnable);
+	void (*quiescent)(struct task_struct *p, u64 deq_flags);
+	bool (*yield)(struct task_struct *from, struct task_struct *to);
+	bool (*core_sched_before)(struct task_struct *a,
+				   struct task_struct *b);
+	void (*set_weight)(struct task_struct *p, u32 weight);
+	void (*set_cmask)(struct task_struct *p,
+			   const struct scx_cmask *cmask);
+	void (*update_idle)(s32 cid, bool idle);
+	s32 (*init_task)(struct task_struct *p,
+			  struct scx_init_task_args *args);
+	void (*exit_task)(struct task_struct *p,
+			   struct scx_exit_task_args *args);
+	void (*enable)(struct task_struct *p);
+	void (*disable)(struct task_struct *p);
+	void (*dump)(struct scx_dump_ctx *ctx);
+	void (*dump_cid)(struct scx_dump_ctx *ctx, s32 cid, bool idle);
+	void (*dump_task)(struct scx_dump_ctx *ctx, struct task_struct *p);
+#ifdef CONFIG_EXT_GROUP_SCHED
+	s32 (*cgroup_init)(struct cgroup *cgrp,
+			    struct scx_cgroup_init_args *args);
+	void (*cgroup_exit)(struct cgroup *cgrp);
+	s32 (*cgroup_prep_move)(struct task_struct *p,
+				 struct cgroup *from, struct cgroup *to);
+	void (*cgroup_move)(struct task_struct *p,
+			     struct cgroup *from, struct cgroup *to);
+	void (*cgroup_cancel_move)(struct task_struct *p,
+				    struct cgroup *from, struct cgroup *to);
+	void (*cgroup_set_weight)(struct cgroup *cgrp, u32 weight);
+	void (*cgroup_set_bandwidth)(struct cgroup *cgrp,
+				      u64 period_us, u64 quota_us, u64 burst_us);
+	void (*cgroup_set_idle)(struct cgroup *cgrp, bool idle);
+#endif	/* CONFIG_EXT_GROUP_SCHED */
+	s32 (*sub_attach)(struct scx_sub_attach_args *args);
+	void (*sub_detach)(struct scx_sub_detach_args *args);
+	void (*cid_online)(s32 cid);
+	void (*cid_offline)(s32 cid);
+	s32 (*init)(void);
+	void (*exit)(struct scx_exit_info *info);
+
+	/* Data fields - must match sched_ext_ops layout exactly */
+	u32 dispatch_max_batch;
+	u64 flags;
+	u32 timeout_ms;
+	u32 exit_dump_len;
+	u64 hotplug_seq;
+	u64 sub_cgroup_id;
+	char name[SCX_OPS_NAME_LEN];
+
+	/* internal use only, must be NULL */
+	void __rcu *priv;
+};
+
 enum scx_opi {
 	SCX_OPI_BEGIN			= 0,
 	SCX_OPI_NORMAL_BEGIN		= 0,
@@ -1003,7 +1090,18 @@ struct scx_sched_pnode {
 };
 
 struct scx_sched {
-	struct sched_ext_ops	ops;
+	/*
+	 * cpu-form and cid-form ops share field offsets up to .priv (verified
+	 * by BUILD_BUG_ON in scx_init()). The anonymous union lets the kernel
+	 * access either view of the same storage without function-pointer
+	 * casts: use .ops for cpu-form and shared fields, .ops_cid for the
+	 * cid-renamed callbacks (set_cmask, select_cid, cid_online, ...).
+	 */
+	union {
+		struct sched_ext_ops		ops;
+		struct sched_ext_ops_cid	ops_cid;
+	};
+	bool			is_cid_type;	/* true if registered via bpf_sched_ext_ops_cid */
 	DECLARE_BITMAP(has_op, SCX_OPI_END);
 
 	/*
@@ -1360,6 +1458,15 @@ enum scx_ops_state {
 extern struct scx_sched __rcu *scx_root;
 DECLARE_PER_CPU(struct rq *, scx_locked_rq_state);
 
+extern struct scx_cmask __percpu *scx_set_cmask_scratch;
+
+/*
+ * True when the currently loaded scheduler hierarchy is cid-form. All scheds
+ * in a hierarchy share one form, so this single key tells callsites which
+ * view to use without per-sch dereferences. Use scx_is_cid_type() to test.
+ */
+DECLARE_STATIC_KEY_FALSE(__scx_is_cid_type);
+
 int scx_kfunc_context_filter(const struct bpf_prog *prog, u32 kfunc_id);
 
 bool scx_cpu_valid(struct scx_sched *sch, s32 cpu, const char *where);
diff --git a/tools/sched_ext/include/scx/compat.bpf.h b/tools/sched_ext/include/scx/compat.bpf.h
index 6b9d054c3e4f..87f15f296234 100644
--- a/tools/sched_ext/include/scx/compat.bpf.h
+++ b/tools/sched_ext/include/scx/compat.bpf.h
@@ -446,4 +446,16 @@ static inline void scx_bpf_dsq_reenq(u64 dsq_id, u64 reenq_flags)
 		__VA_ARGS__,							\
 	};
 
+/*
+ * Define a cid-form sched_ext_ops. Programs targeting this struct_ops type
+ * use cid-form callback signatures (select_cid, set_cmask, cid_online/offline,
+ * dispatch with cid arg, etc.) and may only call the cid-form scx_bpf_*
+ * kfuncs (kick_cid, task_cid, this_cid, ...).
+ */
+#define SCX_OPS_CID_DEFINE(__name, ...)						\
+	SEC(".struct_ops.link")							\
+	struct sched_ext_ops_cid __name = {					\
+		__VA_ARGS__,							\
+	};
+
 #endif	/* __SCX_COMPAT_BPF_H */
-- 
2.54.0

[PATCH 13/17] sched_ext: Forbid cpu-form kfuncs from cid-form schedulers

[Tejun Heo]

cid and cpu are both small s32s, trivially confused when a cid-form
scheduler calls a cpu-keyed kfunc. Reject cid-form programs that
reference any kfunc in the new scx_kfunc_ids_cpu_only at verifier load
time.

The reverse direction is intentionally permissive: cpu-form schedulers
can freely call cid-form kfuncs to ease a gradual cpumask -> cid
migration.

The check sits in scx_kfunc_context_filter() right after the SCX
struct_ops gate and before the any/idle allow and per-op allow-list
checks, so it catches cpu-only kfuncs regardless of which set they
belong to (any, idle, or select_cpu).

v2: Sync per-entry kfunc flags with their primary declarations (Zhao).
    pahole intersects flags across BTF_ID_FLAGS() occurrences, so
    omitting them drops the flags globally.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Cheng-Yang Chou <yphbchou0911@gmail.com>
Reviewed-by: Zhao Mengmeng <zhaomengmeng@kylinos.cn>
---
 kernel/sched/ext.c | 51 ++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 51 insertions(+)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 8e3c60affc0b..d8f8fca5ded9 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -10095,6 +10095,47 @@ static const struct btf_kfunc_id_set scx_kfunc_set_any = {
 	.filter			= scx_kfunc_context_filter,
 };
 
+/*
+ * cpu-form kfuncs that are forbidden from cid-form schedulers
+ * (bpf_sched_ext_ops_cid). Programs targeting the cid struct_ops type must
+ * use the cid-form alternative (cid/cmask kfuncs).
+ *
+ * Membership overlaps with scx_kfunc_ids_{any,idle,select_cpu}; the filter
+ * tests this set independently and rejects matches before the per-op
+ * allow-list check runs.
+ *
+ * pahole/resolve_btfids scans every BTF_ID_FLAGS() at build time and
+ * intersects flags across duplicate entries, so each entry must carry the
+ * same flags as the kfunc's primary declaration; otherwise the flags get
+ * dropped globally.
+ */
+BTF_KFUNCS_START(scx_kfunc_ids_cpu_only)
+BTF_ID_FLAGS(func, scx_bpf_kick_cpu, KF_IMPLICIT_ARGS)
+BTF_ID_FLAGS(func, scx_bpf_task_cpu, KF_RCU)
+BTF_ID_FLAGS(func, scx_bpf_cpu_rq, KF_IMPLICIT_ARGS)
+BTF_ID_FLAGS(func, scx_bpf_cpu_curr, KF_IMPLICIT_ARGS | KF_RET_NULL | KF_RCU_PROTECTED)
+BTF_ID_FLAGS(func, scx_bpf_cpu_node, KF_IMPLICIT_ARGS)
+BTF_ID_FLAGS(func, scx_bpf_cpuperf_cap, KF_IMPLICIT_ARGS)
+BTF_ID_FLAGS(func, scx_bpf_cpuperf_cur, KF_IMPLICIT_ARGS)
+BTF_ID_FLAGS(func, scx_bpf_cpuperf_set, KF_IMPLICIT_ARGS)
+BTF_ID_FLAGS(func, scx_bpf_get_possible_cpumask, KF_ACQUIRE)
+BTF_ID_FLAGS(func, scx_bpf_get_online_cpumask, KF_ACQUIRE)
+BTF_ID_FLAGS(func, scx_bpf_put_cpumask, KF_RELEASE)
+BTF_ID_FLAGS(func, scx_bpf_select_cpu_dfl, KF_IMPLICIT_ARGS | KF_RCU)
+BTF_ID_FLAGS(func, __scx_bpf_select_cpu_and, KF_IMPLICIT_ARGS | KF_RCU)
+BTF_ID_FLAGS(func, scx_bpf_select_cpu_and, KF_RCU)
+BTF_ID_FLAGS(func, scx_bpf_get_idle_cpumask, KF_IMPLICIT_ARGS | KF_ACQUIRE)
+BTF_ID_FLAGS(func, scx_bpf_get_idle_cpumask_node, KF_IMPLICIT_ARGS | KF_ACQUIRE)
+BTF_ID_FLAGS(func, scx_bpf_get_idle_smtmask, KF_IMPLICIT_ARGS | KF_ACQUIRE)
+BTF_ID_FLAGS(func, scx_bpf_get_idle_smtmask_node, KF_IMPLICIT_ARGS | KF_ACQUIRE)
+BTF_ID_FLAGS(func, scx_bpf_put_idle_cpumask, KF_RELEASE)
+BTF_ID_FLAGS(func, scx_bpf_test_and_clear_cpu_idle, KF_IMPLICIT_ARGS)
+BTF_ID_FLAGS(func, scx_bpf_pick_idle_cpu, KF_IMPLICIT_ARGS | KF_RCU)
+BTF_ID_FLAGS(func, scx_bpf_pick_idle_cpu_node, KF_IMPLICIT_ARGS | KF_RCU)
+BTF_ID_FLAGS(func, scx_bpf_pick_any_cpu, KF_IMPLICIT_ARGS | KF_RCU)
+BTF_ID_FLAGS(func, scx_bpf_pick_any_cpu_node, KF_IMPLICIT_ARGS | KF_RCU)
+BTF_KFUNCS_END(scx_kfunc_ids_cpu_only)
+
 /*
  * Per-op kfunc allow flags. Each bit corresponds to a context-sensitive kfunc
  * group; an op may permit zero or more groups, with the union expressed in
@@ -10158,6 +10199,7 @@ int scx_kfunc_context_filter(const struct bpf_prog *prog, u32 kfunc_id)
 	bool in_cpu_release = btf_id_set8_contains(&scx_kfunc_ids_cpu_release, kfunc_id);
 	bool in_idle = btf_id_set8_contains(&scx_kfunc_ids_idle, kfunc_id);
 	bool in_any = btf_id_set8_contains(&scx_kfunc_ids_any, kfunc_id);
+	bool in_cpu_only = btf_id_set8_contains(&scx_kfunc_ids_cpu_only, kfunc_id);
 	u32 moff, flags;
 
 	/* Not an SCX kfunc - allow. */
@@ -10195,6 +10237,15 @@ int scx_kfunc_context_filter(const struct bpf_prog *prog, u32 kfunc_id)
 	    prog->aux->st_ops != &bpf_sched_ext_ops_cid)
 		return -EACCES;
 
+	/*
+	 * cid-form schedulers must use cid/cmask kfuncs. cid and cpu are both
+	 * small s32s and trivially confused, so cpu-only kfuncs are rejected at
+	 * load time. The reverse (cpu-form calling cid-form kfuncs) is
+	 * intentionally permissive to ease gradual cpumask -> cid migration.
+	 */
+	if (prog->aux->st_ops == &bpf_sched_ext_ops_cid && in_cpu_only)
+		return -EACCES;
+
 	/* SCX struct_ops: check the per-op allow list. */
 	if (in_any || in_idle)
 		return 0;
-- 
2.54.0

[PATCH 14/17] tools/sched_ext: scx_qmap: Restart on hotplug instead of cpu_online/offline

[Tejun Heo]

The cid mapping is built from the online cpu set at scheduler enable
and stays valid for that set; routine hotplug invalidates it. The
default cid behavior is to restart the scheduler so the mapping gets
rebuilt against the new online set, and that requires not implementing
cpu_online / cpu_offline (which suppress the kernel's ACT_RESTART).

Drop the two ops along with their print_cpus() helper - the cluster
view was only useful as a hotplug demo and is meaningless over the
dense cid space the scheduler will move to. Wire main() to handle the
ACT_RESTART exit by reopening the skel and reattaching, matching the
pattern in scx_simple / scx_central / scx_flatcg etc. Reset optind so
getopt re-parses argv into the fresh skel rodata each iteration.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Cheng-Yang Chou <yphbchou0911@gmail.com>
---
 tools/sched_ext/scx_qmap.bpf.c | 62 ----------------------------------
 tools/sched_ext/scx_qmap.c     | 13 +++----
 2 files changed, 7 insertions(+), 68 deletions(-)

diff --git a/tools/sched_ext/scx_qmap.bpf.c b/tools/sched_ext/scx_qmap.bpf.c
index ba4879031dac..78a1dd118c7e 100644
--- a/tools/sched_ext/scx_qmap.bpf.c
+++ b/tools/sched_ext/scx_qmap.bpf.c
@@ -843,63 +843,6 @@ void BPF_STRUCT_OPS(qmap_cgroup_set_bandwidth, struct cgroup *cgrp,
 			   cgrp->kn->id, period_us, quota_us, burst_us);
 }
 
-/*
- * Print out the online and possible CPU map using bpf_printk() as a
- * demonstration of using the cpumask kfuncs and ops.cpu_on/offline().
- */
-static void print_cpus(void)
-{
-	const struct cpumask *possible, *online;
-	s32 cpu;
-	char buf[128] = "", *p;
-	int idx;
-
-	possible = scx_bpf_get_possible_cpumask();
-	online = scx_bpf_get_online_cpumask();
-
-	idx = 0;
-	bpf_for(cpu, 0, scx_bpf_nr_cpu_ids()) {
-		if (!(p = MEMBER_VPTR(buf, [idx++])))
-			break;
-		if (bpf_cpumask_test_cpu(cpu, online))
-			*p++ = 'O';
-		else if (bpf_cpumask_test_cpu(cpu, possible))
-			*p++ = 'X';
-		else
-			*p++ = ' ';
-
-		if ((cpu & 7) == 7) {
-			if (!(p = MEMBER_VPTR(buf, [idx++])))
-				break;
-			*p++ = '|';
-		}
-	}
-	buf[sizeof(buf) - 1] = '\0';
-
-	scx_bpf_put_cpumask(online);
-	scx_bpf_put_cpumask(possible);
-
-	bpf_printk("CPUS: |%s", buf);
-}
-
-void BPF_STRUCT_OPS(qmap_cpu_online, s32 cpu)
-{
-	if (print_msgs) {
-		bpf_printk("CPU %d coming online", cpu);
-		/* @cpu is already online at this point */
-		print_cpus();
-	}
-}
-
-void BPF_STRUCT_OPS(qmap_cpu_offline, s32 cpu)
-{
-	if (print_msgs) {
-		bpf_printk("CPU %d going offline", cpu);
-		/* @cpu is still online at this point */
-		print_cpus();
-	}
-}
-
 struct monitor_timer {
 	struct bpf_timer timer;
 };
@@ -1078,9 +1021,6 @@ s32 BPF_STRUCT_OPS_SLEEPABLE(qmap_init)
 		slab[i].next_free = (i + 1 < max_tasks) ? &slab[i + 1] : NULL;
 	qa.task_free_head = &slab[0];
 
-	if (print_msgs && !sub_cgroup_id)
-		print_cpus();
-
 	ret = scx_bpf_create_dsq(SHARED_DSQ, -1);
 	if (ret) {
 		scx_bpf_error("failed to create DSQ %d (%d)", SHARED_DSQ, ret);
@@ -1174,8 +1114,6 @@ SCX_OPS_DEFINE(qmap_ops,
 	       .cgroup_set_bandwidth	= (void *)qmap_cgroup_set_bandwidth,
 	       .sub_attach		= (void *)qmap_sub_attach,
 	       .sub_detach		= (void *)qmap_sub_detach,
-	       .cpu_online		= (void *)qmap_cpu_online,
-	       .cpu_offline		= (void *)qmap_cpu_offline,
 	       .init			= (void *)qmap_init,
 	       .exit			= (void *)qmap_exit,
 	       .timeout_ms		= 5000U,
diff --git a/tools/sched_ext/scx_qmap.c b/tools/sched_ext/scx_qmap.c
index 725c4880058d..99408b1bb1ec 100644
--- a/tools/sched_ext/scx_qmap.c
+++ b/tools/sched_ext/scx_qmap.c
@@ -67,12 +67,14 @@ int main(int argc, char **argv)
 	struct bpf_link *link;
 	struct qmap_arena *qa;
 	__u32 test_error_cnt = 0;
+	__u64 ecode;
 	int opt;
 
 	libbpf_set_print(libbpf_print_fn);
 	signal(SIGINT, sigint_handler);
 	signal(SIGTERM, sigint_handler);
-
+restart:
+	optind = 1;
 	skel = SCX_OPS_OPEN(qmap_ops, scx_qmap);
 
 	skel->rodata->slice_ns = __COMPAT_ENUM_OR_ZERO("scx_public_consts", "SCX_SLICE_DFL");
@@ -184,11 +186,10 @@ int main(int argc, char **argv)
 	}
 
 	bpf_link__destroy(link);
-	UEI_REPORT(skel, uei);
+	ecode = UEI_REPORT(skel, uei);
 	scx_qmap__destroy(skel);
-	/*
-	 * scx_qmap implements ops.cpu_on/offline() and doesn't need to restart
-	 * on CPU hotplug events.
-	 */
+
+	if (UEI_ECODE_RESTART(ecode))
+		goto restart;
 	return 0;
 }
-- 
2.54.0

[PATCH 15/17] tools/sched_ext: scx_qmap: Add cmask-based idle tracking and cid-based idle pick

[Tejun Heo]

Switch qmap's idle-cpu picker from scx_bpf_pick_idle_cpu() to a
BPF-side bitmap scan, still under cpu-form struct_ops. qa_idle_cids
tracks idle cids (updated in update_idle / cpu_offline) and each
task's taskc->cpus_allowed tracks its allowed cids (built in
set_cpumask / init_task); select_cpu / enqueue scan the intersection
for an idle cid. Callbacks translate cpu <-> cid on entry;
cid-qmap-port drops those translations.

The scan is barebone - no core preference or other topology-aware
picks like the in-kernel picker - but qmap is a demo and this is
enough to exercise the plumbing.

v3: qmap_init() refuses to load when nr_cids exceeds SCX_QMAP_MAX_CPUS;
    task_ctx's flex array would otherwise overflow into the next slab
    entry. (Sashiko)

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Cheng-Yang Chou <yphbchou0911@gmail.com>
---
 tools/sched_ext/scx_qmap.bpf.c | 137 +++++++++++++++++++++++++++++----
 1 file changed, 121 insertions(+), 16 deletions(-)

diff --git a/tools/sched_ext/scx_qmap.bpf.c b/tools/sched_ext/scx_qmap.bpf.c
index 78a1dd118c7e..88ef3936937d 100644
--- a/tools/sched_ext/scx_qmap.bpf.c
+++ b/tools/sched_ext/scx_qmap.bpf.c
@@ -72,6 +72,13 @@ struct {
 
 struct qmap_arena __arena qa;
 
+/*
+ * Global idle-cid tracking, maintained via update_idle / cpu_offline and
+ * scanned by the direct-dispatch path. Allocated in qmap_init() from one
+ * arena page, sized to the full cid space.
+ */
+struct scx_cmask __arena *qa_idle_cids;
+
 /* Per-queue locks. Each in its own .data section as bpf_res_spin_lock requires. */
 __hidden struct bpf_res_spin_lock qa_q_lock0 SEC(".data.qa_q_lock0");
 __hidden struct bpf_res_spin_lock qa_q_lock1 SEC(".data.qa_q_lock1");
@@ -132,8 +139,18 @@ struct task_ctx {
 	bool			force_local;	/* Dispatch directly to local_dsq */
 	bool			highpri;
 	u64			core_sched_seq;
+	struct scx_cmask	cpus_allowed;	/* per-task affinity in cid space */
 };
 
+/*
+ * Slab stride for task_ctx. cpus_allowed's flex array bits[] overlaps the
+ * tail bytes appended per entry; struct_size() gives the actual per-entry
+ * footprint.
+ */
+#define TASK_CTX_STRIDE							\
+	struct_size_t(struct task_ctx, cpus_allowed.bits,		\
+		      CMASK_NR_WORDS(SCX_QMAP_MAX_CPUS))
+
 /* All task_ctx pointers are arena pointers. */
 typedef struct task_ctx __arena task_ctx_t;
 
@@ -161,20 +178,37 @@ static int qmap_spin_lock(struct bpf_res_spin_lock *lock)
 	return 0;
 }
 
-static s32 pick_direct_dispatch_cpu(struct task_struct *p, s32 prev_cpu)
+/*
+ * 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.
+ */
+#define IDLE_PICK_RETRIES	16
+
+static s32 pick_direct_dispatch_cpu(struct task_struct *p, s32 prev_cpu,
+				    task_ctx_t *taskc)
 {
-	s32 cpu;
+	u32 nr_cids = scx_bpf_nr_cids();
+	s32 prev_cid, cid;
+	u32 i;
 
 	if (!always_enq_immed && p->nr_cpus_allowed == 1)
 		return prev_cpu;
 
-	if (scx_bpf_test_and_clear_cpu_idle(prev_cpu))
+	prev_cid = scx_bpf_cpu_to_cid(prev_cpu);
+	if (cmask_test_and_clear(qa_idle_cids, prev_cid))
 		return prev_cpu;
 
-	cpu = scx_bpf_pick_idle_cpu(p->cpus_ptr, 0);
-	if (cpu >= 0)
-		return cpu;
-
+	cid = prev_cid;
+	bpf_for(i, 0, IDLE_PICK_RETRIES) {
+		cid = cmask_next_and_set_wrap(&taskc->cpus_allowed,
+					      qa_idle_cids, cid + 1);
+		barrier_var(cid);
+		if (cid >= nr_cids)
+			return -1;
+		if (cmask_test_and_clear(qa_idle_cids, cid))
+			return scx_bpf_cid_to_cpu(cid);
+	}
 	return -1;
 }
 
@@ -286,7 +320,7 @@ s32 BPF_STRUCT_OPS(qmap_select_cpu, struct task_struct *p,
 	if (p->scx.weight < 2 && !(p->flags & PF_KTHREAD))
 		return prev_cpu;
 
-	cpu = pick_direct_dispatch_cpu(p, prev_cpu);
+	cpu = pick_direct_dispatch_cpu(p, prev_cpu, taskc);
 
 	if (cpu >= 0) {
 		taskc->force_local = true;
@@ -379,7 +413,7 @@ void BPF_STRUCT_OPS(qmap_enqueue, struct task_struct *p, u64 enq_flags)
 
 	/* if select_cpu() 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))) >= 0) {
+	    (cpu = pick_direct_dispatch_cpu(p, scx_bpf_task_cpu(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);
 		return;
@@ -726,6 +760,10 @@ s32 BPF_STRUCT_OPS_SLEEPABLE(qmap_init_task, struct task_struct *p,
 	taskc->force_local = false;
 	taskc->highpri = false;
 	taskc->core_sched_seq = 0;
+	cmask_init(&taskc->cpus_allowed, 0, scx_bpf_nr_cids());
+	bpf_rcu_read_lock();
+	cmask_from_cpumask(&taskc->cpus_allowed, p->cpus_ptr);
+	bpf_rcu_read_unlock();
 
 	v = bpf_task_storage_get(&task_ctx_stor, p, NULL,
 				 BPF_LOCAL_STORAGE_GET_F_CREATE);
@@ -843,6 +881,48 @@ 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)
+{
+	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)
+{
+	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);
+	}
+}
+
 struct monitor_timer {
 	struct bpf_timer timer;
 };
@@ -992,34 +1072,57 @@ static int lowpri_timerfn(void *map, int *key, struct bpf_timer *timer)
 
 s32 BPF_STRUCT_OPS_SLEEPABLE(qmap_init)
 {
-	task_ctx_t *slab;
+	u8 __arena *slab;
 	u32 nr_pages, key = 0, i;
 	struct bpf_timer *timer;
 	s32 ret;
 
+	if (scx_bpf_nr_cids() > SCX_QMAP_MAX_CPUS) {
+		scx_bpf_error("nr_cids=%u exceeds SCX_QMAP_MAX_CPUS=%d",
+			      scx_bpf_nr_cids(), SCX_QMAP_MAX_CPUS);
+		return -EINVAL;
+	}
+
 	/*
 	 * Allocate the task_ctx slab in arena and thread the entire slab onto
-	 * the free list. max_tasks is set by userspace before load.
+	 * the free list. max_tasks is set by userspace before load. Each entry
+	 * is TASK_CTX_STRIDE bytes - task_ctx's trailing cpus_allowed flex
+	 * array extends into the stride tail.
 	 */
 	if (!max_tasks) {
 		scx_bpf_error("max_tasks must be > 0");
 		return -EINVAL;
 	}
 
-	nr_pages = (max_tasks * sizeof(struct task_ctx) + PAGE_SIZE - 1) / PAGE_SIZE;
+	nr_pages = (max_tasks * TASK_CTX_STRIDE + PAGE_SIZE - 1) / PAGE_SIZE;
 	slab = bpf_arena_alloc_pages(&arena, NULL, nr_pages, NUMA_NO_NODE, 0);
 	if (!slab) {
 		scx_bpf_error("failed to allocate task_ctx slab");
 		return -ENOMEM;
 	}
-	qa.task_ctxs = slab;
+	qa.task_ctxs = (task_ctx_t *)slab;
 
 	bpf_for(i, 0, 5)
 		qa.fifos[i].idx = i;
 
-	bpf_for(i, 0, max_tasks)
-		slab[i].next_free = (i + 1 < max_tasks) ? &slab[i + 1] : NULL;
-	qa.task_free_head = &slab[0];
+	bpf_for(i, 0, max_tasks) {
+		task_ctx_t *cur = (task_ctx_t *)(slab + i * TASK_CTX_STRIDE);
+		task_ctx_t *next = (i + 1 < max_tasks) ?
+			(task_ctx_t *)(slab + (i + 1) * TASK_CTX_STRIDE) : NULL;
+		cur->next_free = next;
+	}
+	qa.task_free_head = (task_ctx_t *)slab;
+
+	/*
+	 * Allocate and initialize the idle cmask. Starts empty - update_idle
+	 * fills it as cpus enter idle.
+	 */
+	qa_idle_cids = bpf_arena_alloc_pages(&arena, NULL, 1, NUMA_NO_NODE, 0);
+	if (!qa_idle_cids) {
+		scx_bpf_error("failed to allocate idle cmask");
+		return -ENOMEM;
+	}
+	cmask_init(qa_idle_cids, 0, scx_bpf_nr_cids());
 
 	ret = scx_bpf_create_dsq(SHARED_DSQ, -1);
 	if (ret) {
@@ -1104,6 +1207,8 @@ SCX_OPS_DEFINE(qmap_ops,
 	       .dispatch		= (void *)qmap_dispatch,
 	       .tick			= (void *)qmap_tick,
 	       .core_sched_before	= (void *)qmap_core_sched_before,
+	       .set_cpumask		= (void *)qmap_set_cpumask,
+	       .update_idle		= (void *)qmap_update_idle,
 	       .init_task		= (void *)qmap_init_task,
 	       .exit_task		= (void *)qmap_exit_task,
 	       .dump			= (void *)qmap_dump,
-- 
2.54.0

[PATCH 16/17] tools/sched_ext: scx_qmap: Port to cid-form struct_ops

[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 | 231 +++++++++++++++++----------------
 tools/sched_ext/scx_qmap.c     |  59 ++++++++-
 tools/sched_ext/scx_qmap.h     |   2 +-
 3 files changed, 177 insertions(+), 115 deletions(-)

diff --git a/tools/sched_ext/scx_qmap.bpf.c b/tools/sched_ext/scx_qmap.bpf.c
index 88ef3936937d..f55192c7c51a 100644
--- a/tools/sched_ext/scx_qmap.bpf.c
+++ b/tools/sched_ext/scx_qmap.bpf.c
@@ -52,6 +52,28 @@ const volatile bool always_enq_immed;
 const volatile u32 immed_stress_nth;
 const volatile u32 max_tasks;
 
+/*
+ * Optional cid-override test harness. When cid_override_mode is non-zero,
+ * qmap_init() calls scx_bpf_cid_override() with the caller-supplied arrays
+ * to exercise the kfunc's acceptance and error paths.
+ *
+ *   0 = disabled
+ *   1 = valid reverse mapping
+ *   2 = invalid: duplicate cid assignment
+ *   3 = invalid: non-monotonic shard_start
+ */
+const volatile u32 cid_override_mode;
+const volatile u32 cid_override_nr_cpus;
+const volatile u32 cid_override_nr_shards;
+/*
+ * Arrays live in bss (writable) because scx_bpf_cid_override()'s BPF
+ * verifier signature treats its len-paired pointer as read/write - rodata
+ * fails verification with "write into map forbidden". Userspace populates
+ * them before SCX_OPS_LOAD, same as rodata, and nothing writes them after.
+ */
+s32 cid_override_cpu_to_cid[SCX_QMAP_MAX_CPUS];
+s32 cid_override_shard_start[SCX_QMAP_MAX_CPUS];
+
 UEI_DEFINE(uei);
 
 /*
@@ -179,25 +201,24 @@ 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 +228,7 @@ 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 +329,25 @@ 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 +371,12 @@ 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 +409,14 @@ 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 +432,11 @@ 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 +444,16 @@ 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 +505,8 @@ 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 +525,29 @@ 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 (bpf_cpumask_test_cpu(this_cpu, p->cpus_ptr))
-			cpu = this_cpu;
+		if (!(taskc = lookup_task_ctx(p)))
+			return false;
+
+		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 +566,7 @@ 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 +594,7 @@ 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 +659,8 @@ 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 +699,7 @@ 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 +711,7 @@ 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 +859,9 @@ 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 +912,24 @@ 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 +944,49 @@ 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);
 }
 
 /*
@@ -1083,6 +1082,18 @@ s32 BPF_STRUCT_OPS_SLEEPABLE(qmap_init)
 		return -EINVAL;
 	}
 
+	/*
+	 * cid-override test hook. Must run before anything that reads the
+	 * cid space (scx_bpf_nr_cids, cmask_init, etc.). On invalid input,
+	 * the kfunc calls scx_error() which aborts the scheduler.
+	 */
+	if (cid_override_mode) {
+		scx_bpf_cid_override((const s32 *)cid_override_cpu_to_cid,
+				     cid_override_nr_cpus * sizeof(s32),
+				     (const s32 *)cid_override_shard_start,
+				     cid_override_nr_shards * sizeof(s32));
+	}
+
 	/*
 	 * Allocate the task_ctx slab in arena and thread the entire slab onto
 	 * the free list. max_tasks is set by userspace before load. Each entry
@@ -1199,20 +1210,20 @@ 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..a533542e3ca5 100644
--- a/tools/sched_ext/scx_qmap.c
+++ b/tools/sched_ext/scx_qmap.c
@@ -43,6 +43,7 @@ const char help_fmt[] =
 "  -p            Switch only tasks on SCHED_EXT policy instead of all\n"
 "  -I            Turn on SCX_OPS_ALWAYS_ENQ_IMMED\n"
 "  -F COUNT      IMMED stress: force every COUNT'th enqueue to a busy local DSQ (use with -I)\n"
+"  -C MODE       cid-override test (shuffle|bad-dup|bad-mono)\n"
 "  -v            Print libbpf debug messages\n"
 "  -h            Display this help and exit\n";
 
@@ -73,6 +74,14 @@ 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);
@@ -80,7 +89,7 @@ int main(int argc, char **argv)
 	skel->rodata->slice_ns = __COMPAT_ENUM_OR_ZERO("scx_public_consts", "SCX_SLICE_DFL");
 	skel->rodata->max_tasks = 16384;
 
-	while ((opt = getopt(argc, argv, "s:e:t:T:l:b:N:PMHc:d:D:SpIF:vh")) != -1) {
+	while ((opt = getopt(argc, argv, "s:e:t:T:l:b:N:PMHc:d:D:SpIF:C:vh")) != -1) {
 		switch (opt) {
 		case 's':
 			skel->rodata->slice_ns = strtoull(optarg, NULL, 0) * 1000;
@@ -143,6 +152,48 @@ int main(int argc, char **argv)
 		case 'F':
 			skel->rodata->immed_stress_nth = strtoul(optarg, NULL, 0);
 			break;
+		case 'C': {
+			u32 nr_cpus = libbpf_num_possible_cpus();
+			u32 mode, i;
+			s32 shard_sz = 4;
+
+			if (!strcmp(optarg, "shuffle"))
+				mode = 1;
+			else if (!strcmp(optarg, "bad-dup"))
+				mode = 2;
+			else if (!strcmp(optarg, "bad-mono"))
+				mode = 3;
+			else {
+				fprintf(stderr, "unknown cid-override mode '%s'\n", optarg);
+				return 1;
+			}
+			skel->rodata->cid_override_mode = mode;
+			skel->rodata->cid_override_nr_cpus = nr_cpus;
+
+			/* shuffle: reversed cpu_to_cid, bad-dup: dup cid 0, bad-mono: identity */
+			for (i = 0; i < nr_cpus; i++) {
+				if (mode == 1)
+					skel->bss->cid_override_cpu_to_cid[i] = nr_cpus - 1 - i;
+				else
+					skel->bss->cid_override_cpu_to_cid[i] = i;
+			}
+			if (mode == 2 && nr_cpus >= 2)
+				skel->bss->cid_override_cpu_to_cid[1] = 0;
+
+			/* shards of shard_sz each */
+			skel->rodata->cid_override_nr_shards = (nr_cpus + shard_sz - 1) / shard_sz;
+			for (i = 0; i < skel->rodata->cid_override_nr_shards; i++)
+				skel->bss->cid_override_shard_start[i] = i * shard_sz;
+
+			if (mode == 3 && skel->rodata->cid_override_nr_shards >= 3) {
+				/* swap [1] and [2] so shard_start is not monotonically increasing */
+				s32 tmp = skel->bss->cid_override_shard_start[1];
+				skel->bss->cid_override_shard_start[1] =
+					skel->bss->cid_override_shard_start[2];
+				skel->bss->cid_override_shard_start[2] = tmp;
+			}
+			break;
+		}
 		case 'v':
 			verbose = true;
 			break;
@@ -162,9 +213,9 @@ 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 +224,7 @@ 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;
-- 
2.54.0

[PATCH 17/17] sched_ext: Require cid-form struct_ops for sub-sched support

[Tejun Heo]

Sub-scheduler support is tied to the cid-form struct_ops: sub_attach /
sub_detach will communicate allocation via cmask, and the hierarchy assumes
all participants share a single topological cid space. A cpu-form root that
accepts sub-scheds would need cpu <-> cid translation on every cross-sched
interaction, defeating the purpose.

Enforce this at validate_ops():
- A sub-scheduler (scx_parent(sch) non-NULL) must be cid-form.
- A root that exposes sub_attach / sub_detach must be cid-form.

scx_qmap, which is currently the only scheduler demoing sub-sched support,
was converted to cid-form in the preceding patch, so this doesn't cause
breakage.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Cheng-Yang Chou <yphbchou0911@gmail.com>
---
 kernel/sched/ext.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index d8f8fca5ded9..018c75b7ccf1 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -6847,6 +6847,23 @@ static int validate_ops(struct scx_sched *sch, const struct sched_ext_ops *ops)
 	if (!sch->is_cid_type && (ops->cpu_acquire || ops->cpu_release))
 		pr_warn("ops->cpu_acquire/release() are deprecated, use sched_switch TP instead\n");
 
+	/*
+	 * Sub-scheduler support is tied to the cid-form struct_ops. A sub-sched
+	 * attaches through a cid-form-only interface (sub_attach/sub_detach),
+	 * and a root that accepts sub-scheds must expose cid-form state to
+	 * them. Reject cpu-form schedulers on either side.
+	 */
+	if (!sch->is_cid_type) {
+		if (scx_parent(sch)) {
+			scx_error(sch, "sub-sched requires cid-form struct_ops");
+			return -EINVAL;
+		}
+		if (ops->sub_attach || ops->sub_detach) {
+			scx_error(sch, "sub_attach/sub_detach requires cid-form struct_ops");
+			return -EINVAL;
+		}
+	}
+
 	return 0;
 }
 
-- 
2.54.0