From b565a73baec275a3f4b49c1300ab396daf4a748e Mon Sep 17 00:00:00 2001 From: Zicheng Qu Date: Wed, 27 May 2026 17:38:50 +0800 Subject: [PATCH 1/2] tools/sched_ext: Fix scx_show_state per-scheduler state reads scx_show_state.py still reads scx_aborting and scx_bypass_depth as global symbols. Those symbols no longer exist after the state was moved into struct scx_sched, so the drgn script fails when it reaches either field. Read aborting and bypass_depth from scx_root instead. This preserves the script's current root-scheduler view: with sub-scheduler support, the reported values are for the root scheduler and sub-schedulers are not enumerated. Fixes: 5c8d98a1b4de ("sched_ext: Move bypass state into scx_sched") Fixes: c1743da43cf5 ("sched_ext: Move aborting flag to per-scheduler field") Signed-off-by: Zicheng Qu Reviewed-by: Andrea Righi Signed-off-by: Tejun Heo --- tools/sched_ext/scx_show_state.py | 19 +++++++++++++------ 1 file changed, 13 insertions(+), 6 deletions(-) diff --git a/tools/sched_ext/scx_show_state.py b/tools/sched_ext/scx_show_state.py index 02e43c184d43..446d82807f90 100644 --- a/tools/sched_ext/scx_show_state.py +++ b/tools/sched_ext/scx_show_state.py @@ -27,18 +27,25 @@ def read_static_key(name): def state_str(state): return prog['scx_enable_state_str'][state].string_().decode() +def read_root_ops_name(): + if root: + return root.ops.name.string_().decode() + return '' + +def read_root_field(name, default): + if root: + return getattr(root, name).value_() + return default + root = prog['scx_root'] enable_state = read_atomic("scx_enable_state_var") -if root: - print(f'ops : {root.ops.name.string_().decode()}') -else: - print('ops : ') +print(f'ops : {read_root_ops_name()}') print(f'enabled : {read_static_key("__scx_enabled")}') print(f'switching_all : {read_int("scx_switching_all")}') print(f'switched_all : {read_static_key("__scx_switched_all")}') print(f'enable_state : {state_str(enable_state)} ({enable_state})') -print(f'aborting : {prog["scx_aborting"].value_()}') -print(f'bypass_depth : {prog["scx_bypass_depth"].value_()}') +print(f'aborting : {read_root_field("aborting", False)}') +print(f'bypass_depth : {read_root_field("bypass_depth", 0)}') print(f'nr_rejected : {read_atomic("scx_nr_rejected")}') print(f'enable_seq : {read_atomic("scx_enable_seq")}') From 02e545c4297a26dbbc41df81b831e7f605bcd306 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 1 Jun 2026 09:22:37 -1000 Subject: [PATCH 2/2] sched_ext: Don't warn on NULL cgrp_moving_from in scx_cgroup_move_task() A WARN fires when systemd's user manager writes "+cpu +memory +pids" to its own subtree_control while a sched_ext scheduler is loaded: WARNING: at kernel/sched/ext.c:3227 scx_cgroup_move_task+0xa8/0xb0 scx_cgroup_move_task+0xa8/0xb0 sched_move_task+0x134/0x290 cpu_cgroup_attach+0x39/0x70 cgroup_migrate_execute+0x37d/0x450 cgroup_update_dfl_csses+0x1e3/0x270 cgroup_subtree_control_write+0x3e7/0x440 scx_cgroup_can_attach() arms cgrp_moving_from only when a task's cpu cgroup changes. It can still be NULL when scx_cgroup_move_task() runs, through this sequence: Step Result --------------------------------- ---------------------------------- 1. cpu enabled on cgroup G cpu css = A 2. cpu toggled off then on for G A killed, B created (same cgroup) 3. an exiting task keeps A alive migration skips it, A now stale 4. +memory migrates G stale A vs current B pulls cpu in 5. cpu attach runs for all tasks hits a live, cpu-unchanged task 6. scx_cgroup_move_task() on it cgrp_moving_from NULL -> WARN The mismatch is that scx_cgroup_can_attach() keys on cgroup identity while migration drives the move on css identity, so a NULL cgrp_moving_from here is a legitimate css-only migration, not a missing prep. The call is already gated on cgrp_moving_from, so just drop the warning. ops.cgroup_prep_move() and ops.cgroup_move() stay paired. Fixes: 819513666966 ("sched_ext: Add cgroup support") Cc: stable@vger.kernel.org # v6.12+ Reported-by: Matt Fleming Closes: https://lore.kernel.org/all/20260601124156.2205704-1-mfleming@cloudflare.com/ Signed-off-by: Tejun Heo Reviewed-by: Andrea Righi --- kernel/sched/ext.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index c1762420cc35..8e88a25bc602 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -4402,11 +4402,13 @@ void scx_cgroup_move_task(struct task_struct *p) return; /* - * @p must have ops.cgroup_prep_move() called on it and thus - * cgrp_moving_from set. + * scx_cgroup_can_attach() sets cgrp_moving_from only when the task's + * cgroup changes. Migration keys off css rather than cgroup identity, + * so it can hand an unchanged-cgroup task here with cgrp_moving_from + * NULL. Nothing to report to the BPF scheduler then, so skip it and + * keep prep_move and move paired. */ - if (SCX_HAS_OP(sch, cgroup_move) && - !WARN_ON_ONCE(!p->scx.cgrp_moving_from)) + if (SCX_HAS_OP(sch, cgroup_move) && p->scx.cgrp_moving_from) SCX_CALL_OP_TASK(sch, cgroup_move, task_rq(p), p, p->scx.cgrp_moving_from, tg_cgrp(task_group(p)));