sched_ext: Avoid NULL scx_root deref in __scx_exit()
PATCH 1/1 sched_ext: Avoid NULL scx_root deref in __scx_exit()
A sched_ext scheduler may trigger __scx_exit() from a BPF timer callback, where scx_root may not be safely dereferenced.
This can lead to a NULL pointer dereference as shown below (triggered by scx_tickless):
BUG: kernel NULL pointer dereference, address: 0000000000000330 ... CPU: 0 UID: 0 PID: 0 Comm: swapper/0 Not tainted 6.14.0-virtme #1 PREEMPT(full) RIP: 0010:__scx_exit+0x2b/0x190 ... Call Trace: <IRQ> scx_bpf_get_idle_smtmask+0x59/0x80 bpf_prog_8320d4217989178c_dispatch_all_cpus+0x35/0x1b6 ... bpf_prog_97f847d871513f95_sched_timerfn+0x4c/0x264 bpf_timer_cb+0x7a/0x140 __hrtimer_run_queues+0x1f9/0x3a0 hrtimer_run_softirq+0x8c/0xd0 handle_softirqs+0xd3/0x3d0 __irq_exit_rcu+0x9a/0xc0 irq_exit_rcu+0xe/0x20
Fix this by checking for a valid scx_root and adding proper RCU protection.
Fixes 48e1267773866 ("sched_ext: Introduce scx_sched")
Signed-off-by Andrea Righi <[email protected]>
--- kernel/sched/ext.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-)
kernel/sched/ext.c +13 -4
@@ -5212,12 +5212,19 @@ static void scx_error_irq_workfn(struct irq_work *irq_work) static __printf(3, 4) void __scx_exit(enum scx_exit_kind kind, s64 exit_code, const char *fmt, ...) { - struct scx_exit_info *ei = scx_root->exit_info; + struct scx_sched *sch; +struct scx_exit_info *ei;int none =SCX_EXIT_NONE ;va_list args; -if (!atomic_try_cmpxchg (&scx_root->exit_kind, &none, kind)) -return ; +rcu_read_lock (); + sch =rcu_dereference (scx_root); +if (!sch) + goto out_unlock; + ei = sch->exit_info; + +if (!atomic_try_cmpxchg (&sch->exit_kind, &none, kind)) + goto out_unlock; ei->exit_code = exit_code;#ifdef CONFIG_STACKTRACE
@@ -5235,7 +5242,9 @@ static __printf(3, 4) void __scx_exit(enum scx_exit_kind kind, s64 exit_code, ei->kind = kind; ei->reason =scx_exit_reason (ei->kind); -irq_work_queue (&scx_root->error_irq_work); +irq_work_queue (&sch->error_irq_work); +out_unlock: +rcu_read_unlock (); }static struct scx_sched *scx_alloc_and_add_sched (struct sched_ext_ops *ops)
Signature · 1 line
2.49.0
Tejun Heo
AppliedQuoted 24 lines · Andrea Righi
A
sched_extscheduler may trigger__scx_exit()from a BPF timer callback, wherescx_rootmay not be safely dereferenced.This can lead to a NULL pointer dereference as shown below (triggered by
scx_tickless):BUG: kernel NULL pointer dereference, address: 0000000000000330 ... CPU: 0 UID: 0 PID: 0 Comm: swapper/0 Not tainted 6.14.0-virtme #1 PREEMPT(full) RIP: 0010:__scx_exit+0x2b/0x190 ... Call Trace: <IRQ> scx_bpf_get_idle_smtmask+0x59/0x80 bpf_prog_8320d4217989178c_dispatch_all_cpus+0x35/0x1b6 ... bpf_prog_97f847d871513f95_sched_timerfn+0x4c/0x264 bpf_timer_cb+0x7a/0x140 __hrtimer_run_queues+0x1f9/0x3a0 hrtimer_run_softirq+0x8c/0xd0 handle_softirqs+0xd3/0x3d0 __irq_exit_rcu+0x9a/0xc0 irq_exit_rcu+0xe/0x20
Quoted 5 lines
Fix this by checking for a valid
scx_rootand adding proper RCU protection.Fixes 48e1267773866 ("sched_ext: Introduce scx_sched")Signed-off-by Andrea Righi <[email protected]>
Applied to sched_ext/for-6.16.
Thanks.
Signature · 1 line
tejun