From 477869bfafea65492d23de62c1b5208147c09dd2 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 16 Jul 2026 10:43:25 -1000 Subject: [PATCH 1/6] sched_ext: Reject setting disallow from init_task outside the enable path The p->scx.disallow revert assumes the root enable path, where the switching loop reads the reverted policy right afterwards and leaves the task off SCX. The sub-scheduler disable path also reaches it when re-initializing the returned tasks on a root parent. Nothing reads the policy there: the task is enabled on root anyway and keeps running on the ext class with a silently rewritten policy. Kill the sched instead, matching the fork and non-root branches, and update the disallow documentation, which equated !fork with the load path and pointed at a stale debugfs path for nr_rejected. Fixes: 337ec00b1d9c ("sched_ext: Implement cgroup sub-sched enabling and disabling") Signed-off-by: Tejun Heo Reviewed-by: Andrea Righi --- include/linux/sched/ext.h | 10 +++++----- kernel/sched/ext/ext.c | 3 +++ 2 files changed, 8 insertions(+), 5 deletions(-) diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h index 20b2343aa344..87e353f7e011 100644 --- a/include/linux/sched/ext.h +++ b/include/linux/sched/ext.h @@ -244,11 +244,11 @@ struct sched_ext_entity { * to %SCHED_EXT with -%EACCES. * * Can be set from ops.init_task() while the BPF scheduler is being - * loaded (!scx_init_task_args->fork). If set and the task's policy is - * already %SCHED_EXT, the task's policy is rejected and forcefully - * reverted to %SCHED_NORMAL. The number of such events are reported - * through /sys/kernel/debug/sched_ext::nr_rejected. Setting this flag - * during fork is not allowed. + * loaded. If set and the task's policy is already %SCHED_EXT, the + * task's policy is rejected and forcefully reverted to %SCHED_NORMAL. + * The number of such events are reported through + * /sys/kernel/sched_ext/nr_rejected. Setting this flag from any other + * ops.init_task() invocation, such as during fork, fails the scheduler. */ bool disallow; /* reject switching into SCX */ diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c index e3fa7b2fac9d..46f135bddd46 100644 --- a/kernel/sched/ext/ext.c +++ b/kernel/sched/ext/ext.c @@ -3606,6 +3606,9 @@ static int __scx_init_task(struct scx_sched *sch, struct task_struct *p, bool fo } else if (unlikely(fork)) { scx_error(sch, "ops.init_task() set task->scx.disallow for %s[%d] during fork", p->comm, p->pid); + } else if (unlikely(scx_enable_state() != SCX_ENABLING)) { + scx_error(sch, "ops.init_task() set task->scx.disallow for %s[%d] outside the enable path", + p->comm, p->pid); } else { struct rq *rq; struct rq_flags rf; From 5f8b69642d18e1f3e11996707842ac530444e959 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 16 Jul 2026 10:44:02 -1000 Subject: [PATCH 2/6] sched_ext: Take cgroup_lock() first in scx_cgroup_lock() scx_cgroup_lock() write-locks scx_cgroup_ops_rwsem and then takes cgroup_lock(), which can deadlock through kernfs: scx enable/disable cgroup rmdir cpu.weight write ------------------ ------------ ---------------- cgroup_lock() percpu_down_write(rwsem) cgroup_lock() kernfs_get_active() percpu_down_read(rwsem) kernfs_drain() The enable path waits for the rmdir to release cgroup_mutex. The rmdir, deactivating the cpu controller's files, waits in kernfs_drain() for the write's active reference. The write, in scx_group_set_weight(), waits for the rwsem behind the pending writer. Take cgroup_lock() first. The set_* paths take no cgroup locks inside the read side, so a pending write-lock then only waits for read sections that always run to completion, and no dependency from the rwsem back to cgroup_mutex remains. Fixes: a5bd6ba30b33 ("sched_ext: Use cgroup_lock/unlock() to synchronize against cgroup operations") Cc: stable@vger.kernel.org # v6.18+ Signed-off-by: Tejun Heo Reviewed-by: Andrea Righi --- kernel/sched/ext/ext.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c index 46f135bddd46..58898cd0727b 100644 --- a/kernel/sched/ext/ext.c +++ b/kernel/sched/ext/ext.c @@ -4580,20 +4580,25 @@ static struct cgroup *root_cgroup(void) return &cgrp_dfl_root.cgrp; } +/* + * cgroup_lock() must nest outside the rwsem write side: a writer waiting + * for cgroup_mutex deadlocks with cgroup teardown, which holds it while + * draining a set_* file write blocked on the rwsem behind the writer. + */ static void scx_cgroup_lock(void) { + cgroup_lock(); #ifdef CONFIG_EXT_GROUP_SCHED percpu_down_write(&scx_cgroup_ops_rwsem); #endif - cgroup_lock(); } static void scx_cgroup_unlock(void) { - cgroup_unlock(); #ifdef CONFIG_EXT_GROUP_SCHED percpu_up_write(&scx_cgroup_ops_rwsem); #endif + cgroup_unlock(); } #else /* CONFIG_EXT_GROUP_SCHED || CONFIG_EXT_SUB_SCHED */ static inline struct cgroup *root_cgroup(void) { return NULL; } From 8c13364db9c9a43ed286f3a8d0fb9477b1adc43c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 16 Jul 2026 10:45:23 -1000 Subject: [PATCH 3/6] sched_ext: Skip sub-disable teardown for never-linked sub-schedulers A sub-scheduler enable can fail before scx_link_sched() links the sched into the hierarchy, e.g. when the parent is already being disabled, and cleanup still runs the full scx_sub_disable(). That is racy against root disable: drain_descendants() is the only ordering between a sub's disable-time task walk and root disable's all-task teardown, and an unlinked sub is invisible to it. Root's teardown can thus run between the never-linked sub's drain and its walk, exiting every task to no scheduler. The walk then trips the membership WARN and re-homes the exited tasks onto the dying hierarchy, a use-after-free. Skip the cgroup ownership reset and the task walk if @sch was never linked, indicated by the empty ->sibling as unlinking only happens later in the same function. The membership WARN remains valid: a linked sub is always waited on by an ancestor's drain. Fixes: 337ec00b1d9c ("sched_ext: Implement cgroup sub-sched enabling and disabling") Signed-off-by: Tejun Heo Reviewed-by: Andrea Righi --- kernel/sched/ext/ext.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c index 58898cd0727b..98dd7df88db4 100644 --- a/kernel/sched/ext/ext.c +++ b/kernel/sched/ext/ext.c @@ -5937,6 +5937,15 @@ static void scx_sub_disable(struct scx_sched *sch) percpu_down_write(&scx_fork_rwsem); scx_cgroup_lock(); + /* + * An enable that failed before scx_link_sched() never owned a cgroup or + * task and won't be waited on by an ancestor's drain_descendants(). + * Nothing to reparent and walking the tasks can misbehave as the task + * ownership invariant (either owned by self or parent) does not hold. + */ + if (list_empty(&sch->sibling)) + goto dump; + set_cgroup_sched(sch_cgroup(sch), parent); scx_task_iter_start(&sti, sch->cgrp); @@ -5949,8 +5958,8 @@ static void scx_sub_disable(struct scx_sched *sch) continue; /* - * By the time control reaches here, all descendant schedulers - * should already have been disabled. + * By the time control reaches here, all linked descendant + * schedulers should have been disabled. */ WARN_ON_ONCE(!scx_task_on_sched(sch, p)); @@ -6017,6 +6026,7 @@ static void scx_sub_disable(struct scx_sched *sch) } scx_task_iter_stop(&sti); +dump: scx_disable_dump(sch); scx_cgroup_unlock(); From 5cdc928598095b2c7d5f265e5f21eadd1634bfbe Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 16 Jul 2026 10:46:04 -1000 Subject: [PATCH 4/6] sched_ext: Don't enable non-ext tasks in the sub-sched task loops Root enable and scx_post_fork() enable a task only if it's on the ext class. Tasks on other classes, possible under an SCX_OPS_SWITCH_PARTIAL root, are left READY and enabled by switching_to_scx() when they switch over. The sub enable-commit pass and the sub-disable re-home loop enable unconditionally, so a fair-class READY task in the subtree becomes ENABLED while not on sched_ext. A later switch to SCHED_EXT then trips the task state validation WARN (ENABLED with the previous state not READY) and calls ops.enable() a second time. Gate scx_enable_task() on the task's class in both loops. Fixes: 337ec00b1d9c ("sched_ext: Implement cgroup sub-sched enabling and disabling") Signed-off-by: Tejun Heo Reviewed-by: Andrea Righi --- kernel/sched/ext/ext.c | 21 ++++++++++++++++----- 1 file changed, 16 insertions(+), 5 deletions(-) diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c index 98dd7df88db4..18183062f751 100644 --- a/kernel/sched/ext/ext.c +++ b/kernel/sched/ext/ext.c @@ -6010,15 +6010,22 @@ static void scx_sub_disable(struct scx_sched *sch) /* * $p is initialized for $parent and still attached to * @sch. Disable and exit for @sch, switch over to - * $parent, override the state to READY to account for - * $p having already been initialized, and then enable. + * $parent and override the state to READY to account + * for $p having already been initialized. */ scx_disable_and_exit_task(sch, p); scx_set_task_state(p, SCX_TASK_INIT_BEGIN); scx_set_task_state(p, SCX_TASK_INIT); scx_set_task_sched(p, parent); scx_set_task_state(p, SCX_TASK_READY); - scx_enable_task(parent, p); + + /* + * A task on a non-ext class, possible under an + * %SCX_OPS_SWITCH_PARTIAL root, stays READY and is + * enabled by switching_to_scx() if it switches over. + */ + if (p->sched_class == &ext_sched_class) + scx_enable_task(parent, p); } task_rq_unlock(rq, p, &rf); @@ -7726,10 +7733,14 @@ static void scx_sub_enable_workfn(struct kthread_work *work) /* * $p is now only initialized for @sch and READY, which - * is what we want. Assign it to @sch and enable. + * is what we want. Assign it to @sch and, if it's on + * the ext class, enable. A non-ext task, possible under + * an %SCX_OPS_SWITCH_PARTIAL root, stays READY and is + * enabled by switching_to_scx() if it switches over. */ scx_set_task_sched(p, sch); - scx_enable_task(sch, p); + if (p->sched_class == &ext_sched_class) + scx_enable_task(sch, p); p->scx.flags &= ~SCX_TASK_SUB_INIT; } From 9591fcc95dddfd24298724f8eb5239e907980779 Mon Sep 17 00:00:00 2001 From: Kuba Piecuch Date: Wed, 22 Jul 2026 14:33:07 +0000 Subject: [PATCH 5/6] sched_ext: Mark waker CPU busy when selected in WAKE_SYNC case SCX's built-in idle CPU tracking is imperfect and can be out-of-sync with the actual idle state of CPUs, especially immediately after enabling SCX due to scx_idle_enable() marking all online CPUs idle. scx_select_cpu_dfl() skips marking the selected CPU as busy if the selected CPU is the waker CPU in the SCX_WAKE_SYNC case. If the waker CPU was marked idle by SCX, it will still be marked idle after CPU selection and potentially even after switching to the wakee. In the allowed_cpus selftest, this can manifest as the test failing with the following message in dmesg: allowed_cpus.bpf.c:21: CPU 0 should be marked as busy This patch explicitly marks the waker CPU as busy. With this patch, the test failure no longer reproduces. There are still some pretty unlikely races that could make the test fail (e.g. pick_task_idle() marking the selected CPU idle between selection and validation), but these can't be fixed easily. Signed-off-by: Kuba Piecuch Signed-off-by: Tejun Heo --- kernel/sched/ext/idle.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/kernel/sched/ext/idle.c b/kernel/sched/ext/idle.c index 8e8c6201b7df..6f93cc32b650 100644 --- a/kernel/sched/ext/idle.c +++ b/kernel/sched/ext/idle.c @@ -554,8 +554,10 @@ s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, cpu_rq(cpu)->scx.local_dsq.nr == 0 && (!(flags & SCX_PICK_IDLE_IN_NODE) || (waker_node == node)) && !cpumask_empty(idle_cpumask(waker_node)->cpu)) { - if (cpumask_test_cpu(cpu, allowed)) + if (cpumask_test_cpu(cpu, allowed)) { + scx_idle_test_and_clear_cpu(cpu); goto out_unlock; + } } } From d4a00d61a5c2c24973175ace5368d1f6acf9bb0a Mon Sep 17 00:00:00 2001 From: Kuba Piecuch Date: Thu, 23 Jul 2026 09:59:55 +0000 Subject: [PATCH 6/6] selftests/sched_ext: Handle sleeping task affinity changes in numa test When a sleeping task's affinity is changed, task_cpu(p) can be outside of p->cpus_ptr until after select_task_rq() selects a new runqueue for the task during wakeup. Thus, the task's NUMA node determined by numa_select_cpu() can be completely outside of the task's cpumask, leading to scx_pick_{idle,any}_cpu_node() failing to find an eligible CPU and returning -EBUSY. This leads to the numa.bpf.c scheduler abnormally exiting with the following message in dmesg: sched_ext: numa: invalid CPU -16 scx_bpf_cpu_node+0x120/0x190 bpf_prog_0a34b8e0f515771f_numa_select_cpu+0x108/0x14e bpf__sched_ext_ops_select_cpu+0x4f/0xb4 select_task_rq_scx+0xb0/0x210 select_task_rq+0xa0/0xd0 __try_to_wake_up+0x196/0x650 complete_all+0x76/0x100 migration_cpu_stop+0x22b/0x300 cpu_stopper_thread+0xc1/0x180 smpboot_thread_fn+0x16b/0x230 kthread+0x2d7/0x350 ret_from_fork+0x1c2/0x350 ret_from_fork_asm+0x1a/0x30 Make numa_select_cpu() robust against this case by returning @prev_cpu if no CPU could be found in the selected NUMA node _and_ we have reason to believe that the task's affinity was changed while it was sleeping. Fixes: 5ae5161820e5 ("selftests/sched_ext: Add NUMA-aware scheduler test") Signed-off-by: Kuba Piecuch Signed-off-by: Tejun Heo --- tools/testing/selftests/sched_ext/numa.bpf.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/sched_ext/numa.bpf.c b/tools/testing/selftests/sched_ext/numa.bpf.c index 78cc49a7f9a6..6b4515c28aa0 100644 --- a/tools/testing/selftests/sched_ext/numa.bpf.c +++ b/tools/testing/selftests/sched_ext/numa.bpf.c @@ -34,7 +34,8 @@ static bool is_cpu_idle(s32 cpu, int node) s32 BPF_STRUCT_OPS(numa_select_cpu, struct task_struct *p, s32 prev_cpu, u64 wake_flags) { - int node = __COMPAT_scx_bpf_cpu_node(scx_bpf_task_cpu(p)); + s32 task_cpu = scx_bpf_task_cpu(p); + int node = __COMPAT_scx_bpf_cpu_node(task_cpu); s32 cpu; /* @@ -48,6 +49,16 @@ s32 BPF_STRUCT_OPS(numa_select_cpu, cpu = __COMPAT_scx_bpf_pick_any_cpu_node(p->cpus_ptr, node, __COMPAT_SCX_PICK_IDLE_IN_NODE); + /* + * @task_cpu may be outside of p->cpus_ptr if @p's affinity + * changed while it was sleeping. This means it's possible for + * p->cpus_ptr to not include any CPUs from @node. + * If we failed to find a cpu in @node, check if @task_cpu + * is outside of p->cpus_ptr and just return @prev_cpu if it is. + */ + if (cpu < 0 && !bpf_cpumask_test_cpu(task_cpu, p->cpus_ptr)) + return prev_cpu; + if (is_cpu_idle(cpu, node)) scx_bpf_error("CPU %d should be marked as busy", cpu);