WARNING: at kernel/mutex.c:134

While try to trigger bug 9778, press ctrl+alt+sysrq +w, the following warnings appeared:

usb0: unregister 'cdc_ether' usb-0000:00:1d.7-1.3, CDC Ethernet Device
unregister_netdevice: waiting for usb0 to become free. Usage count = 1 SysRq : Show Blocked State
task PC stack pid father
Sched Debug Version: v0.07, 2.6.24-rc8-mm1 #5
now at 2660467.699238 msecs

  .sysctl_sched_latency                    : 40.000000
  .sysctl_sched_min_granularity            : 8.000000
  .sysctl_sched_wakeup_granularity         : 20.000000
  .sysctl_sched_batch_wakeup_granularity   : 20.000000
  .sysctl_sched_child_runs_first           : 0.000001
  .sysctl_sched_features                   : 39

cpu#0, 2793.192 MHz

  .nr_running                    : 2
  .load                          : 4096
  .nr_switches                   : 1627754
  .nr_load_updates               : 241563
  .nr_uninterruptible            : 4294967012
  .jiffies                       : 708140
  .next_balance                  : 0.708327
  .curr->pid                     : 0
  .clock                         : 2656959.965268
  .idle_clock                    : 0.000000
  .prev_clock_raw                : 2674890.031768
  .clock_warps                   : 0
  .clock_overflows               : 5805
  .clock_underflows              : 127079
  .clock_deep_idle_events        : 2
  .clock_max_delta               : 671.628710
  .cpu_load[0]                   : 0
  .cpu_load[1]                   : 0
  .cpu_load[2]                   : 6
  .cpu_load[3]                   : 48
  .cpu_load[4]                   : 85

cfs_rq

  .exec_clock                    : 0.000000
  .MIN_vruntime                  : 180379.753201
  .min_vruntime                  : 180379.753201
  .max_vruntime                  : 180379.753201
  .spread                        : 0.000000
  .spread0                       : 0.000000
  .nr_running                    : 1
  .load                          : 4096
  .nr_spread_over                : 0
------------[ cut here ]------------
WARNING: at kernel/mutex.c:134 mutex_lock_nested+0x277/0x290()
Modules linked in: cdc_ether usbnet snd_seq_dummy snd_seq_oss snd_seq_midi_event snd_seq snd_seq_device snd_pcm_oss snd_mixer_oss eeprom e100 psmouse snd_hda_intel snd_pcm intel_agp btusb snd_timer rtc_cmos bluetooth sg rtc_core 3c59x evdev agpgart snd serio_raw button thermal processor soundcore rtc_lib snd_page_alloc i2c_i801 pcspkr dcdbas
Pid: 0, comm: swapper Not tainted 2.6.24-rc8-mm1 #5
 [<c0132100>] ? printk+0x0/0x20
 [<c0131834>] warn_on_slowpath+0x54/0x80
 [<c043641e>] ? _spin_unlock_irqrestore+0x5e/0x70
 [<c0132791>] ? release_console_sem+0xd1/0xe0
 [<c0132428>] ? vprintk+0x308/0x320
 [<c0153241>] ? put_lock_stats+0x21/0x30
 [<c01532b0>] ? lock_release_holdtime+0x60/0x80
 [<c0126b07>] ? print_cfs_rq+0x117/0x500
 [<c0156b87>] ? __lock_release+0x47/0x70
 [<c0126b07>] ? print_cfs_rq+0x117/0x500
 [<c0132118>] ? printk+0x18/0x20
 [<c0434757>] mutex_lock_nested+0x277/0x290
 [<c0132428>] ? vprintk+0x308/0x320
 [<c0124f60>] ? print_cfs_stats+0x30/0xb0
 [<c0124f60>] print_cfs_stats+0x30/0xb0
 [<c012770c>] print_cpu+0x81c/0x830
 [<c012794a>] sched_debug_show+0x22a/0x430
 [<c0127b5c>] sysrq_sched_debug_show+0xc/0x10
 [<c012bb06>] show_state_filter+0x86/0xb0
 [<c02c95cd>] sysrq_handle_showstate_blocked+0xd/0x10
 [<c02c97a9>] __handle_sysrq+0x89/0x120
 [<c02c9873>] handle_sysrq+0x33/0x40
 [<c02c39ae>] kbd_keycode+0x39e/0x480
 [<c013b320>] ? __mod_timer+0xa0/0xb0
 [<c02c3b7a>] kbd_event+0xea/0x100
 [<c0386d0c>] input_pass_event+0xec/0x100
 [<c0386c20>] ? input_pass_event+0x0/0x100
 [<c013b3b6>] ? mod_timer+0x26/0x40
 [<c0386ef2>] input_handle_event+0xb2/0x2b0
 [<c038714f>] input_event+0x5f/0x80
 [<c03a1e2f>] hidinput_hid_event+0xef/0x390
 [<c039f410>] ? hid_input_field+0x40/0x340
 [<c039f3a3>] hid_process_event+0x63/0x90
 [<c039f695>] hid_input_field+0x2c5/0x340
 [<c039fc66>] hid_input_report+0x106/0x260
 [<c015322d>] ? put_lock_stats+0xd/0x30
 [<c01532b0>] ? lock_release_holdtime+0x60/0x80
 [<c03a44e1>] hid_irq_in+0x181/0x190
 [<c03816fa>] ? uhci_giveback_urb+0x8a/0x160
 [<c0368b31>] usb_hcd_giveback_urb+0x41/0xa0
 [<c0381707>] uhci_giveback_urb+0x97/0x160
 [<c0381840>] uhci_scan_qh+0x70/0x1c0
 [<c0381b0b>] uhci_scan_schedule+0x8b/0x130
 [<c03828f5>] uhci_irq+0xb5/0x150
 [<c0156b87>] ? __lock_release+0x47/0x70
 [<c0368ec4>] usb_hcd_irq+0x24/0x60
 [<c0164fd8>] handle_IRQ_event+0x28/0x60
 [<c016626e>] handle_fasteoi_irq+0x6e/0xd0
 [<c01078ac>] do_IRQ+0x3c/0x80
 [<c0151d2c>] ? tick_nohz_stop_sched_tick+0x25c/0x350
 [<c01059ca>] common_interrupt+0x2e/0x34
 [<c0103390>] ? mwait_idle_with_hints+0x40/0x50
 [<c01033a0>] ? mwait_idle+0x0/0x20
 [<c01033b2>] mwait_idle+0x12/0x20
 [<c0103141>] cpu_idle+0x61/0x110
 [<c04333bd>] rest_init+0x5d/0x60
 [<c05a47fa>] start_kernel+0x1fa/0x260
 [<c05a4190>] ? unknown_bootoption+0x0/0x130
 =======================
---[ end trace bc131943b9b4ac4c ]---

--

kernel/sched_fair.c +1 -1

-	unlock_task_group_list();
+	rcu_read_unlock();
 }
 #endif

kernel/sched_fair.c static void print_cfs_stats(struct seq_f · line 1433

Quoted 8 lines · Peter Zijlstra

kernel/sched_fair.c +1 -1

@@ -1428,9 +1428,9 @@ static void print_cfs_stats(struct seq_f
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	print_cfs_rq(m, cpu, &cpu_rq(cpu)->cfs);
 #endif
-	lock_task_group_list();
+	rcu_read_lock();
 	for_each_leaf_cfs_rq(cpu_rq(cpu), cfs_rq)
 		print_cfs_rq(m, cpu, cfs_rq);

Isn't there a possibility that print_cfs_rq() can block?

Quoted 6 lines

kernel/sched_fair.c +1 -1

-	unlock_task_group_list();
+	rcu_read_unlock();
 }
 #endif

It should not, that would be another bug, but from a quick glance at the code it doesn't do that.

Quoted 1 line

WARNING: at kernel/mutex.c:134 mutex_lock_nested+0x277/0x290()

Subject: sched: don't take a mutex from interrupt context

print_cfs_stats is callable from interrupt context (sysrq), hence it should not take mutexes. Change it to use RCU since the task group data is RCU freed anyway.