* [PATCH 06/17] sched_ext: Make scx_enable() take scx_enable_cmd
@ 2026-04-24 1:32 Tejun Heo
0 siblings, 0 replies; 3+ messages in thread
From: Tejun Heo @ 2026-04-24 1:32 UTC (permalink / raw)
To: David Vernet, Andrea Righi, Changwoo Min
Cc: sched-ext, emil, linux-kernel, Cheng-Yang Chou, Zhao Mengmeng,
Tejun Heo
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 ad255268f207..cd4c235e0c82 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -6425,6 +6425,19 @@ 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.
@@ -6656,19 +6669,6 @@ 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);
@@ -7244,11 +7244,10 @@ 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)) {
@@ -7272,16 +7271,15 @@ 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;
}
@@ -7453,7 +7451,9 @@ 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)
--
2.53.0
^ permalink raw reply related [flat|nested] 3+ messages in thread* [PATCHSET v2 REPOST sched_ext/for-7.2] sched_ext: Topological CPU IDs and cid-form struct_ops
@ 2026-04-24 17:27 Tejun Heo
2026-04-24 17:27 ` [PATCH 06/17] sched_ext: Make scx_enable() take scx_enable_cmd Tejun Heo
0 siblings, 1 reply; 3+ messages in thread
From: Tejun Heo @ 2026-04-24 17:27 UTC (permalink / raw)
To: David Vernet, Andrea Righi, Changwoo Min
Cc: sched-ext, emil, linux-kernel, Cheng-Yang Chou, Zhao Mengmeng,
Tejun Heo
Hello,
Reposting v2 because the original send was not properly threaded -
each patch went out as a standalone top-level message. Content is
unchanged from the original v2.
Original v2: https://lore.kernel.org/r/20260424013220.2923402-1-tj@kernel.org
v2 of https://lore.kernel.org/r/20260421071945.3110084-1-tj@kernel.org
v2:
- Add ext-types.h first patch for early subsystem-wide type defs.
- cid: publish the cid tables with WRITE_ONCE / read with READ_ONCE;
document the visibility contract.
- cid-kfuncs: NULL-guard scx_bpf_this_cid / scx_bpf_task_cid for
TRACING/SYSCALL callers before any SCX sched has enabled.
- cid-struct-ops: use struct_size() for the set_cmask_scratch percpu
alloc; cluster __scx_is_cid_type disable with __scx_enabled disable
in scx_root_disable().
- cid-kfunc-filter: sync per-entry kfunc flags with each kfunc's
primary BTF_ID_FLAGS() declaration (Zhao). pahole intersects flags
across occurrences; omitting them drops the flags globally - the
visible symptom was KF_IMPLICIT_ARGS getting cleared on
scx_bpf_kick_cpu, leaking bpf_prog_aux into vmlinux.h.
- cmask: narrow to the helpers this series actually uses;
cmask_copy_from_kernel contract and runtime guard.
This patchset introduces topological CPU IDs (cids) - dense,
topology-ordered cpu identifiers - and an alternative cid-form struct_ops
type that lets BPF schedulers operate in cid space directly.
Key pieces:
- cid space: scx_cid_init() walks nodes * LLCs * cores * threads and packs
a dense cid mapping. The mapping can be overridden via
scx_bpf_cid_override(). See "Topological CPU IDs" in ext_cid.h for the
model.
- cmask: a base-windowed bitmap over cid space. Kernel and BPF helpers with
identical semantics. Used by scx_qmap for per-task affinity and idle-cid
tracking; meant to be the substrate for sub-sched cid allocation.
- bpf_sched_ext_ops_cid: a parallel struct_ops type whose callbacks take
cids/cmasks instead of cpus/cpumasks. Kernel translates at the boundary
via scx_cpu_arg() / scx_cpu_ret(); the two struct types share offsets up
through @priv (verified by BUILD_BUG_ON) so the union view in scx_sched
works without function-pointer casts. Sub-sched support is tied to
cid-form: validate_ops() rejects cpu-form sub-scheds and cpu-form roots
that expose sub_attach / sub_detach.
- cid-form kfuncs: scx_bpf_kick_cid, scx_bpf_cidperf_{cap,cur,set},
scx_bpf_cid_curr, scx_bpf_task_cid, scx_bpf_this_cid,
scx_bpf_nr_{cids,online_cids}, scx_bpf_cid_to_cpu, scx_bpf_cpu_to_cid.
A cid-form program may not call cpu-only kfuncs (enforced at verifier
load via scx_kfunc_context_filter); the reverse is intentionally
permissive to ease migration.
- scx_qmap port: scx_qmap is converted to cid-form. It uses the cmask-based
idle picker, per-task cid-space cpus_allowed, and cid-form kfuncs
throughout. Sub-sched dispatching via scx_bpf_sub_dispatch() continues to
work.
v2 re-tested on the 16-cpu QEMU: cid-form scx_qmap, cpu-form scx_simple,
cid<->cpu cycling, scx_qmap under stress-ng, hotplug auto-restart, and
sub-sched (root scx_qmap + cgroup-scoped scx_qmap child). Clean.
Based on sched_ext/for-7.2 (c2929bc21dce).
0001-sched_ext-Add-ext_types.h-for-early-subsystem-wide-d.patch
0002-sched_ext-Rename-ops_cpu_valid-to-scx_cpu_valid-and-.patch
0003-sched_ext-Move-scx_exit-scx_error-and-friends-to-ext.patch
0004-sched_ext-Shift-scx_kick_cpu-validity-check-to-scx_b.patch
0005-sched_ext-Relocate-cpu_acquire-cpu_release-to-end-of.patch
0006-sched_ext-Make-scx_enable-take-scx_enable_cmd.patch
0007-sched_ext-Add-topological-CPU-IDs-cids.patch
0008-sched_ext-Add-scx_bpf_cid_override-kfunc.patch
0009-tools-sched_ext-Add-struct_size-helpers-to-common.bp.patch
0010-sched_ext-Add-cmask-a-base-windowed-bitmap-over-cid-.patch
0011-sched_ext-Add-cid-form-kfunc-wrappers-alongside-cpu-.patch
0012-sched_ext-Add-bpf_sched_ext_ops_cid-struct_ops-type.patch
0013-sched_ext-Forbid-cpu-form-kfuncs-from-cid-form-sched.patch
0014-tools-sched_ext-scx_qmap-Restart-on-hotplug-instead-.patch
0015-tools-sched_ext-scx_qmap-Add-cmask-based-idle-tracki.patch
0016-tools-sched_ext-scx_qmap-Port-to-cid-form-struct_ops.patch
0017-sched_ext-Require-cid-form-struct_ops-for-sub-sched-.patch
Git tree: git://git.kernel.org/pub/scm/linux/kernel/git/tj/sched_ext.git scx-cid-v2
kernel/sched/build_policy.c | 2 +
kernel/sched/ext.c | 650 +++++++++++++++++++++++++----
kernel/sched/ext_cid.c | 417 ++++++++++++++++++++
kernel/sched/ext_cid.h | 164 ++++++++
kernel/sched/ext_idle.c | 8 +-
kernel/sched/ext_internal.h | 203 +++++++---
kernel/sched/ext_types.h | 104 +++++
tools/sched_ext/include/scx/cid.bpf.h | 597 ++++++++++++++++++++++++++++
tools/sched_ext/include/scx/common.bpf.h | 23 ++
tools/sched_ext/include/scx/compat.bpf.h | 24 ++
tools/sched_ext/scx_qmap.bpf.c | 306 ++++++++-------
tools/sched_ext/scx_qmap.c | 25 +-
tools/sched_ext/scx_qmap.h | 2 +-
13 files changed, 2240 insertions(+), 285 deletions(-)
--
tejun
^ permalink raw reply [flat|nested] 3+ messages in thread* [PATCH 06/17] sched_ext: Make scx_enable() take scx_enable_cmd
2026-04-24 17:27 [PATCHSET v2 REPOST sched_ext/for-7.2] sched_ext: Topological CPU IDs and cid-form struct_ops Tejun Heo
@ 2026-04-24 17:27 ` Tejun Heo
0 siblings, 0 replies; 3+ messages in thread
From: Tejun Heo @ 2026-04-24 17:27 UTC (permalink / raw)
To: David Vernet, Andrea Righi, Changwoo Min
Cc: sched-ext, emil, linux-kernel, Cheng-Yang Chou, Zhao Mengmeng,
Tejun Heo
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 ad255268f207..cd4c235e0c82 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -6425,6 +6425,19 @@ 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.
@@ -6656,19 +6669,6 @@ 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);
@@ -7244,11 +7244,10 @@ 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)) {
@@ -7272,16 +7271,15 @@ 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;
}
@@ -7453,7 +7451,9 @@ 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)
--
2.53.0
^ permalink raw reply related [flat|nested] 3+ messages in thread
* [PATCHSET v3 sched_ext/for-7.2] sched_ext: Topological CPU IDs and cid-form struct_ops
@ 2026-04-28 20:35 Tejun Heo
2026-04-28 20:35 ` [PATCH 06/17] sched_ext: Make scx_enable() take scx_enable_cmd Tejun Heo
0 siblings, 1 reply; 3+ messages in thread
From: Tejun Heo @ 2026-04-28 20:35 UTC (permalink / raw)
To: David Vernet, Andrea Righi, Changwoo Min
Cc: sched-ext, Emil Tsalapatis, linux-kernel, Tejun Heo
Hello,
v3 (all from the Sashiko AI review at
https://sashiko.dev/#/patchset/20260424172721.3458520-1-tj%40kernel.org):
- cid: drop leaked cpus_read_lock() on scx_cid_init() failure;
BUILD_BUG_ON tightened to NR_CPUS<=8192 to match the BPF cmask
helpers' CMASK_MAX_WORDS coverage.
- bpf-struct-size: use offsetof() in struct_size() to match the
kernel <linux/overflow.h> macro semantics (no inflation from
trailing struct padding).
- cmask: cmask_copy_from_kernel() validates src->base==0 via
probe-read; nr_bits check is bit-level rather than rounded-up
word-count.
- cid-qmap-idle: qmap_init() refuses to load when scx_bpf_nr_cids()
exceeds SCX_QMAP_MAX_CPUS; the task_ctx flex array would otherwise
overflow into the next slab entry.
v2: https://lore.kernel.org/r/20260424172721.3458520-1-tj@kernel.org
v1: https://lore.kernel.org/r/20260421071945.3110084-1-tj@kernel.org
This patchset introduces topological CPU IDs (cids) - dense,
topology-ordered cpu identifiers - and an alternative cid-form struct_ops
type that lets BPF schedulers operate in cid space directly.
Key pieces:
- cid space: scx_cid_init() walks nodes * LLCs * cores * threads and packs
a dense cid mapping. The mapping can be overridden via
scx_bpf_cid_override(). See "Topological CPU IDs" in ext_cid.h for the
model.
- cmask: a base-windowed bitmap over cid space. Kernel and BPF helpers with
identical semantics. Used by scx_qmap for per-task affinity and idle-cid
tracking; meant to be the substrate for sub-sched cid allocation.
- bpf_sched_ext_ops_cid: a parallel struct_ops type whose callbacks take
cids/cmasks instead of cpus/cpumasks. Kernel translates at the boundary
via scx_cpu_arg() / scx_cpu_ret(); the two struct types share offsets up
through @priv (verified by BUILD_BUG_ON) so the union view in scx_sched
works without function-pointer casts. Sub-sched support is tied to
cid-form: validate_ops() rejects cpu-form sub-scheds and cpu-form roots
that expose sub_attach / sub_detach.
- cid-form kfuncs: scx_bpf_kick_cid, scx_bpf_cidperf_{cap,cur,set},
scx_bpf_cid_curr, scx_bpf_task_cid, scx_bpf_this_cid,
scx_bpf_nr_{cids,online_cids}, scx_bpf_cid_to_cpu, scx_bpf_cpu_to_cid.
A cid-form program may not call cpu-only kfuncs (enforced at verifier
load via scx_kfunc_context_filter); the reverse is intentionally
permissive to ease migration.
- scx_qmap port: scx_qmap is converted to cid-form. It uses the cmask-based
idle picker, per-task cid-space cpus_allowed, and cid-form kfuncs
throughout. Sub-sched dispatching via scx_bpf_sub_dispatch() continues to
work.
v3 re-tested on the 16-cpu QEMU: cid-form scx_qmap under stress-ng plus
reload cycles, hotplug auto-restart, and sub-sched (root scx_qmap +
cgroup-scoped scx_qmap child). Clean.
Based on sched_ext/for-7.2 (4939721aad2e).
0001-sched_ext-Add-ext_types.h-for-early-subsystem-wide-d.patch
0002-sched_ext-Rename-ops_cpu_valid-to-scx_cpu_valid-and-.patch
0003-sched_ext-Move-scx_exit-scx_error-and-friends-to-ext.patch
0004-sched_ext-Shift-scx_kick_cpu-validity-check-to-scx_b.patch
0005-sched_ext-Relocate-cpu_acquire-cpu_release-to-end-of.patch
0006-sched_ext-Make-scx_enable-take-scx_enable_cmd.patch
0007-sched_ext-Add-topological-CPU-IDs-cids.patch
0008-sched_ext-Add-scx_bpf_cid_override-kfunc.patch
0009-tools-sched_ext-Add-struct_size-helpers-to-common.bp.patch
0010-sched_ext-Add-cmask-a-base-windowed-bitmap-over-cid-.patch
0011-sched_ext-Add-cid-form-kfunc-wrappers-alongside-cpu-.patch
0012-sched_ext-Add-bpf_sched_ext_ops_cid-struct_ops-type.patch
0013-sched_ext-Forbid-cpu-form-kfuncs-from-cid-form-sched.patch
0014-tools-sched_ext-scx_qmap-Restart-on-hotplug-instead-.patch
0015-tools-sched_ext-scx_qmap-Add-cmask-based-idle-tracki.patch
0016-tools-sched_ext-scx_qmap-Port-to-cid-form-struct_ops.patch
0017-sched_ext-Require-cid-form-struct_ops-for-sub-sched-.patch
Git tree: git://git.kernel.org/pub/scm/linux/kernel/git/tj/sched_ext.git scx-cid-v3
kernel/sched/build_policy.c | 3 +
kernel/sched/ext.c | 651 ++++++++++++++++++++++++++----
kernel/sched/ext_cid.c | 409 +++++++++++++++++++
kernel/sched/ext_cid.h | 164 ++++++++
kernel/sched/ext_idle.c | 8 +-
kernel/sched/ext_internal.h | 205 +++++++---
kernel/sched/ext_types.h | 104 +++++
tools/sched_ext/include/scx/cid.bpf.h | 667 +++++++++++++++++++++++++++++++
tools/sched_ext/include/scx/common.bpf.h | 23 ++
tools/sched_ext/include/scx/compat.bpf.h | 24 ++
tools/sched_ext/scx_qmap.bpf.c | 346 +++++++++-------
tools/sched_ext/scx_qmap.c | 70 +++-
tools/sched_ext/scx_qmap.h | 2 +-
13 files changed, 2391 insertions(+), 285 deletions(-)
Thanks.
--
tejun
^ permalink raw reply [flat|nested] 3+ messages in thread* [PATCH 06/17] sched_ext: Make scx_enable() take scx_enable_cmd
2026-04-28 20:35 [PATCHSET v3 sched_ext/for-7.2] sched_ext: Topological CPU IDs and cid-form struct_ops Tejun Heo
@ 2026-04-28 20:35 ` Tejun Heo
0 siblings, 0 replies; 3+ messages in thread
From: Tejun Heo @ 2026-04-28 20:35 UTC (permalink / raw)
To: David Vernet, Andrea Righi, Changwoo Min
Cc: sched-ext, Emil Tsalapatis, linux-kernel, Tejun Heo,
Cheng-Yang Chou
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
^ permalink raw reply related [flat|nested] 3+ messages in thread
end of thread, other threads:[~2026-04-28 20:35 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-04-24 1:32 [PATCH 06/17] sched_ext: Make scx_enable() take scx_enable_cmd Tejun Heo
-- strict thread matches above, loose matches on Subject: below --
2026-04-24 17:27 [PATCHSET v2 REPOST sched_ext/for-7.2] sched_ext: Topological CPU IDs and cid-form struct_ops Tejun Heo
2026-04-24 17:27 ` [PATCH 06/17] sched_ext: Make scx_enable() take scx_enable_cmd Tejun Heo
2026-04-28 20:35 [PATCHSET v3 sched_ext/for-7.2] sched_ext: Topological CPU IDs and cid-form struct_ops Tejun Heo
2026-04-28 20:35 ` [PATCH 06/17] sched_ext: Make scx_enable() take scx_enable_cmd Tejun Heo
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox