From ce9aaa3af445c391735c9d000c4db60dfd5640d4 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 13 May 2026 12:33:22 -0400 Subject: [PATCH] sched_ext: Read scx_root under scx_cgroup_ops_rwsem in cgroup setters [ Upstream commit 80afd4c84bc8f5e80145ce35279f5ce53f6043db ] scx_group_set_{weight,idle,bandwidth}() cache scx_root before acquiring scx_cgroup_ops_rwsem, so the pointer can be stale by the time the op runs. If the loaded scheduler is disabled and freed (via RCU work) and another is enabled between the naked load and the rwsem acquire, the reader sees scx_cgroup_enabled=true (the new scheduler's) but dereferences the freed one - UAF on SCX_HAS_OP(sch, ...) / SCX_CALL_OP(sch, ...). scx_cgroup_enabled is toggled only under scx_cgroup_ops_rwsem write (scx_cgroup_{init,exit}), so reading scx_root inside the rwsem read section correlates @sch with the enabled snapshot. Fixes: a5bd6ba30b33 ("sched_ext: Use cgroup_lock/unlock() to synchronize against cgroup operations") Cc: stable@vger.kernel.org # v6.18+ Reported-by: Chris Mason Signed-off-by: Tejun Heo Reviewed-by: Andrea Righi Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- kernel/sched/ext.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 423098966a29..177bbf31116d 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -3251,9 +3251,10 @@ void scx_cgroup_cancel_attach(struct cgroup_taskset *tset) void scx_group_set_weight(struct task_group *tg, unsigned long weight) { - struct scx_sched *sch = scx_root; + struct scx_sched *sch; percpu_down_read(&scx_cgroup_ops_rwsem); + sch = scx_root; if (scx_cgroup_enabled && SCX_HAS_OP(sch, cgroup_set_weight) && tg->scx.weight != weight) @@ -3267,9 +3268,10 @@ void scx_group_set_weight(struct task_group *tg, unsigned long weight) void scx_group_set_idle(struct task_group *tg, bool idle) { - struct scx_sched *sch = scx_root; + struct scx_sched *sch; percpu_down_read(&scx_cgroup_ops_rwsem); + sch = scx_root; if (scx_cgroup_enabled && SCX_HAS_OP(sch, cgroup_set_idle)) SCX_CALL_OP(sch, SCX_KF_UNLOCKED, cgroup_set_idle, NULL, @@ -3284,9 +3286,10 @@ void scx_group_set_idle(struct task_group *tg, bool idle) void scx_group_set_bandwidth(struct task_group *tg, u64 period_us, u64 quota_us, u64 burst_us) { - struct scx_sched *sch = scx_root; + struct scx_sched *sch; percpu_down_read(&scx_cgroup_ops_rwsem); + sch = scx_root; if (scx_cgroup_enabled && SCX_HAS_OP(sch, cgroup_set_bandwidth) && (tg->scx.bw_period_us != period_us ||