linux-kernel - [PATCH] sched_ext: Fix unsafe locking in the scx_dump

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Message-Id: <20251112073328.14303-1-qiang.zhang@linux.dev>
Date: Wed, 12 Nov 2025 15:33:28 +0800
From: Zqiang <qiang.zhang@...ux.dev>
To: tj@...nel.org,
	void@...ifault.com,
	arighi@...dia.com,
	changwoo@...lia.com
Cc: sched-ext@...ts.linux.dev,
	linux-kernel@...r.kernel.org,
	qiang.zhang@...ux.dev
Subject: [PATCH] sched_ext: Fix unsafe locking in the scx_dump_state()

For built with CONFIG_PREEMPT_RT=y kernels, the dump_lock will be converted
sleepable spinlock and not disable-irq, so the following scenarios occur:

inconsistent {IN-HARDIRQ-W} -> {HARDIRQ-ON-W} usage.
irq_work/0/27 [HC0[0]:SC0[0]:HE1:SE1] takes:
(&rq->__lock){?...}-{2:2}, at: raw_spin_rq_lock_nested+0x2b/0x40
{IN-HARDIRQ-W} state was registered at:
   lock_acquire+0x1e1/0x510
   _raw_spin_lock_nested+0x42/0x80
   raw_spin_rq_lock_nested+0x2b/0x40
   sched_tick+0xae/0x7b0
   update_process_times+0x14c/0x1b0
   tick_periodic+0x62/0x1f0
   tick_handle_periodic+0x48/0xf0
   timer_interrupt+0x55/0x80
   __handle_irq_event_percpu+0x20a/0x5c0
   handle_irq_event_percpu+0x18/0xc0
   handle_irq_event+0xb5/0x150
   handle_level_irq+0x220/0x460
   __common_interrupt+0xa2/0x1e0
   common_interrupt+0xb0/0xd0
   asm_common_interrupt+0x2b/0x40
   _raw_spin_unlock_irqrestore+0x45/0x80
   __setup_irq+0xc34/0x1a30
   request_threaded_irq+0x214/0x2f0
   hpet_time_init+0x3e/0x60
   x86_late_time_init+0x5b/0xb0
   start_kernel+0x308/0x410
   x86_64_start_reservations+0x1c/0x30
   x86_64_start_kernel+0x96/0xa0
   common_startup_64+0x13e/0x148

 other info that might help us debug this:
 Possible unsafe locking scenario:

        CPU0
        ----
   lock(&rq->__lock);
   <Interrupt>
     lock(&rq->__lock);

  *** DEADLOCK ***

 stack backtrace:
 CPU: 0 UID: 0 PID: 27 Comm: irq_work/0
 Call Trace:
  <TASK>
  dump_stack_lvl+0x8c/0xd0
  dump_stack+0x14/0x20
  print_usage_bug+0x42e/0x690
  mark_lock.part.44+0x867/0xa70
  ? __pfx_mark_lock.part.44+0x10/0x10
  ? string_nocheck+0x19c/0x310
  ? number+0x739/0x9f0
  ? __pfx_string_nocheck+0x10/0x10
  ? __pfx_check_pointer+0x10/0x10
  ? kvm_sched_clock_read+0x15/0x30
  ? sched_clock_noinstr+0xd/0x20
  ? local_clock_noinstr+0x1c/0xe0
  __lock_acquire+0xc4b/0x62b0
  ? __pfx_format_decode+0x10/0x10
  ? __pfx_string+0x10/0x10
  ? __pfx___lock_acquire+0x10/0x10
  ? __pfx_vsnprintf+0x10/0x10
  lock_acquire+0x1e1/0x510
  ? raw_spin_rq_lock_nested+0x2b/0x40
  ? __pfx_lock_acquire+0x10/0x10
  ? dump_line+0x12e/0x270
  ? raw_spin_rq_lock_nested+0x20/0x40
  _raw_spin_lock_nested+0x42/0x80
  ? raw_spin_rq_lock_nested+0x2b/0x40
  raw_spin_rq_lock_nested+0x2b/0x40
  scx_dump_state+0x3b3/0x1270
  ? finish_task_switch+0x27e/0x840
  scx_ops_error_irq_workfn+0x67/0x80
  irq_work_single+0x113/0x260
  irq_work_run_list.part.3+0x44/0x70
  run_irq_workd+0x6b/0x90
  ? __pfx_run_irq_workd+0x10/0x10
  smpboot_thread_fn+0x529/0x870
  ? __pfx_smpboot_thread_fn+0x10/0x10
  kthread+0x305/0x3f0
  ? __pfx_kthread+0x10/0x10
  ret_from_fork+0x40/0x70
  ? __pfx_kthread+0x10/0x10
  ret_from_fork_asm+0x1a/0x30
  </TASK>

This commit therefore use rq_lock_irqsave/irqrestore() to replace
rq_lock/unlock() in the scx_dump_state().

Fixes: 07814a9439a3 ("sched_ext: Print debug dump after an error exit")
Signed-off-by: Zqiang <qiang.zhang@...ux.dev>
---
 kernel/sched/ext.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 2b0e88206d07..56aa8e6d335b 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -4216,7 +4216,7 @@ static void scx_dump_state(struct scx_exit_info *ei, size_t dump_len)
 		size_t avail, used;
 		bool idle;

-		rq_lock(rq, &rf);
+		rq_lock_irqsave(rq, &rf);

 		idle = list_empty(&rq->scx.runnable_list) &&
 			rq->curr->sched_class == &idle_sched_class;
@@ -4285,7 +4285,7 @@ static void scx_dump_state(struct scx_exit_info *ei, size_t dump_len)
 		list_for_each_entry(p, &rq->scx.runnable_list, scx.runnable_node)
 			scx_dump_task(&s, &dctx, p, ' ');
 	next:
-		rq_unlock(rq, &rf);
+		rq_unlock_irqrestore(rq, &rf);
 	}

 	dump_newline(&s);
-- 
2.17.1