v2.6.25: WARNING: at kernel/lockdep.c:2437 __lock_acquire+0xc69/0xfa0()
Hi,
This appears in clean v2.6.25:
------------[ cut here ]------------ WARNING: at kernel/lockdep.c:2437 __lock_acquire+0xc69/0xfa0() Pid: 1002, comm: scsi_eh_4 Not tainted 2.6.25 #379 [<c011bb5c>] warn_on_slowpath+0x3c/0x50 [<c013b0f9>] ? __lock_acquire+0x219/0xfa0 [<c013b0f9>] ? __lock_acquire+0x219/0xfa0 [<c012c2c8>] ? __kernel_text_address+0x8/0x20 [<c0104fce>] ? dump_trace+0xce/0x120 [<c010a56c>] ? save_stack_trace+0x1c/0x40 [<c0138659>] ? save_trace+0x39/0xa0 [<c013a3d1>] ? mark_lock+0x61/0x540 [<c013bb49>] __lock_acquire+0xc69/0xfa0 [<c012b46a>] ? __cancel_work_timer+0x5a/0x140 [<c01082ac>] ? native_sched_clock+0x5c/0xb0 [<c013beee>] lock_acquire+0x6e/0x90 [<c02a8e23>] ? ata_scsi_error+0x33/0x6a0 [<c02e4946>] _spin_lock_irqsave+0x26/0x60 [<c02a8e23>] ? ata_scsi_error+0x33/0x6a0 [<c02a4ee0>] ? ata_bmdma_error_handler+0x0/0x50 [<c02a8e23>] ata_scsi_error+0x33/0x6a0 [<c02e249a>] ? schedule+0x27a/0x410 [<c0256dd1>] ? __scsi_iterate_devices+0x51/0x70 [<c025c681>] ? scsi_run_host_queues+0x21/0x30 [<c025ae5e>] scsi_error_handler+0x9e/0x4e0 [<c02e249a>] ? schedule+0x27a/0x410 [<c025adc0>] ? scsi_error_handler+0x0/0x4e0 [<c012dd86>] kthread+0x36/0x60 [<c012dd50>] ? kthread+0x0/0x60 [<c0104c27>] kernel_thread_helper+0x7/0x10 ======================= ---[ end trace 5e5d737e76fd4940 ]---
Full log and config:
http://folk.uio.no/vegardno/linux/log-20080420.txt
http://folk.uio.no/vegardno/linux/config-20080420.txt
(The bootup is from qemu for the ease of harvesting the log -- but it happens on real hardware too!)
Vegard
Signature · 4 lines
"The animistic metaphor of the bug that maliciously sneaked in while the programmer was not looking is intellectually dishonest as it disguises that the error is the programmer's own creation." -- E. W. Dijkstra, EWD1036
Quoted 27 lines · Vegard Nossum
Hi,
This appears in clean v2.6.25:
------------[ cut here ]------------ WARNING: at kernel/lockdep.c:2437 __lock_acquire+0xc69/0xfa0() Pid: 1002, comm: scsi_eh_4 Not tainted 2.6.25 #379 [<c011bb5c>] warn_on_slowpath+0x3c/0x50 [<c013b0f9>] ? __lock_acquire+0x219/0xfa0 [<c013b0f9>] ? __lock_acquire+0x219/0xfa0 [<c012c2c8>] ? __kernel_text_address+0x8/0x20 [<c0104fce>] ? dump_trace+0xce/0x120 [<c010a56c>] ? save_stack_trace+0x1c/0x40 [<c0138659>] ? save_trace+0x39/0xa0 [<c013a3d1>] ? mark_lock+0x61/0x540 [<c013bb49>] __lock_acquire+0xc69/0xfa0 [<c012b46a>] ? __cancel_work_timer+0x5a/0x140 [<c01082ac>] ? native_sched_clock+0x5c/0xb0 [<c013beee>] lock_acquire+0x6e/0x90 [<c02a8e23>] ? ata_scsi_error+0x33/0x6a0 [<c02e4946>] _spin_lock_irqsave+0x26/0x60 [<c02a8e23>] ? ata_scsi_error+0x33/0x6a0 [<c02a4ee0>] ? ata_bmdma_error_handler+0x0/0x50 [<c02a8e23>] ata_scsi_error+0x33/0x6a0 [<c02e249a>] ? schedule+0x27a/0x410 [<c0256dd1>] ? __scsi_iterate_devices+0x51/0x70 [<c025c681>] ? scsi_run_host_queues+0x21/0x30
Quoted 8 lines
[<c025ae5e>] scsi_error_handler+0x9e/0x4e0 [<c02e249a>] ? schedule+0x27a/0x410 [<c025adc0>] ? scsi_error_handler+0x0/0x4e0 [<c012dd86>] kthread+0x36/0x60 [<c012dd50>] ? kthread+0x0/0x60 [<c0104c27>] kernel_thread_helper+0x7/0x10 ======================= ---[ end trace 5e5d737e76fd4940 ]---
Indeed, quite easy to reproduce:
kernel/lockdep.c +7 -0
@@ -2434,6 +2434,13 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,* the hash, not class->key. */ id = class - lock_classes; +if (id >=MAX_LOCKDEP_KEYS ) { +spinlock_t *slock =container_of (lock, spinlock_t, dep_map); + +printk (KERN_EMERG "magic: %x\n" , slock->magic); +printk (KERN_EMERG "class: %p\n" , class); +printk (KERN_EMERG "id: %u\n" , id); + }if (DEBUG_LOCKS_WARN_ON (id >=MAX_LOCKDEP_KEYS ))return 0 ;
gives me:
ata3: PATA max PIO4 cmd 0x1e8 ctl 0x3ee irq 11
magic: c050cf60
class: c7c20e54
id: 2265185251
------------[ cut here ]------------ WARNING: at /mnt/md0/src/linux-2.6-2/kernel/lockdep.c:2444 __lock_acquire+0x57b/0xfd0()
Looks like someone is stomping on the spinlock or just passing us garbage.
Quoted 65 lines · Peter Zijlstra
Quoted 27 lines · Vegard Nossum
Hi,
This appears in clean v2.6.25:
------------[ cut here ]------------ WARNING: at kernel/lockdep.c:2437 __lock_acquire+0xc69/0xfa0() Pid: 1002, comm: scsi_eh_4 Not tainted 2.6.25 #379 [<c011bb5c>] warn_on_slowpath+0x3c/0x50 [<c013b0f9>] ? __lock_acquire+0x219/0xfa0 [<c013b0f9>] ? __lock_acquire+0x219/0xfa0 [<c012c2c8>] ? __kernel_text_address+0x8/0x20 [<c0104fce>] ? dump_trace+0xce/0x120 [<c010a56c>] ? save_stack_trace+0x1c/0x40 [<c0138659>] ? save_trace+0x39/0xa0 [<c013a3d1>] ? mark_lock+0x61/0x540 [<c013bb49>] __lock_acquire+0xc69/0xfa0 [<c012b46a>] ? __cancel_work_timer+0x5a/0x140 [<c01082ac>] ? native_sched_clock+0x5c/0xb0 [<c013beee>] lock_acquire+0x6e/0x90 [<c02a8e23>] ? ata_scsi_error+0x33/0x6a0 [<c02e4946>] _spin_lock_irqsave+0x26/0x60 [<c02a8e23>] ? ata_scsi_error+0x33/0x6a0 [<c02a4ee0>] ? ata_bmdma_error_handler+0x0/0x50 [<c02a8e23>] ata_scsi_error+0x33/0x6a0 [<c02e249a>] ? schedule+0x27a/0x410 [<c0256dd1>] ? __scsi_iterate_devices+0x51/0x70 [<c025c681>] ? scsi_run_host_queues+0x21/0x30Quoted 8 lines
[<c025ae5e>] scsi_error_handler+0x9e/0x4e0 [<c02e249a>] ? schedule+0x27a/0x410 [<c025adc0>] ? scsi_error_handler+0x0/0x4e0 [<c012dd86>] kthread+0x36/0x60 [<c012dd50>] ? kthread+0x0/0x60 [<c0104c27>] kernel_thread_helper+0x7/0x10 ======================= ---[ end trace 5e5d737e76fd4940 ]---Indeed, quite easy to reproduce:
kernel/lockdep.c +7
-0@@ -2434,6 +2434,13 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,* the hash, not class->key. */ id = class - lock_classes; +if (id >=MAX_LOCKDEP_KEYS ) { +spinlock_t *slock =container_of (lock, spinlock_t, dep_map); + +printk (KERN_EMERG "magic: %x\n" , slock->magic); +printk (KERN_EMERG "class: %p\n" , class); +printk (KERN_EMERG "id: %u\n" , id); + }if (DEBUG_LOCKS_WARN_ON (id >=MAX_LOCKDEP_KEYS ))return 0 ;gives me:
ata3: PATA max PIO4 cmd
0x1e8ctl0x3eeirq 11
magic:c050cf60
class:c7c20e54
id: 2265185251
Quoted 7 lines
------------[ cut here ]------------ WARNING: at /mnt/md0/src/linux-2.6-2/kernel/lockdep.c:2444 __lock_acquire+0x57b/0xfd0()Looks like someone is stomping on the spinlock or just passing us garbage.
Does the attached patch help?
Signature · 1 line
tejun
drivers/ata/pata_legacy.c +1 -0
@@ -1037,6 +1037,7 @@ static __init int legacy_init_one(struct legacy_probe *probe)return 0 ; } } +ata_host_detach (host); fail:platform_device_unregister (pdev);return ret;
Quoted 45 lines · Tejun Heo
Quoted 29 lines · Peter Zijlstra
Indeed, quite easy to reproduce:
kernel/lockdep.c +7
-0@@ -2434,6 +2434,13 @@ static int __lock_acquire(struct lockdep_map*lock, unsigned int subclass, * the hash, not class->key. */ id = class - lock_classes; +if (id >=MAX_LOCKDEP_KEYS ) { +spinlock_t *slock =container_of (lock, spinlock_t, dep_map); + +printk (KERN_EMERG "magic: %x\n" , slock->magic); +printk (KERN_EMERG "class: %p\n" , class); +printk (KERN_EMERG "id: %u\n" , id); + }if (DEBUG_LOCKS_WARN_ON (id >=MAX_LOCKDEP_KEYS ))return 0 ;gives me:
ata3: PATA max PIO4 cmd
0x1e8ctl0x3eeirq 11
magic:c050cf60
class:c7c20e54
id: 2265185251Quoted 7 lines
------------[ cut here ]------------ WARNING: at /mnt/md0/src/linux-2.6-2/kernel/lockdep.c:2444 __lock_acquire+0x57b/0xfd0()Looks like someone is stomping on the spinlock or just passing us garbage.
Does the attached patch help?
drivers/ata/pata_legacy.c +0
-0
drivers/ata/pata_legacy.c static __init int legacy_init_one(struct legacy_probe *probe) · line 1043
Quoted 7 lines
drivers/ata/pata_legacy.c +1
-0@@ -1037,6 +1037,7 @@ static __init int legacy_init_one(struct legacy_probe *probe)return 0 ; } } +ata_host_detach (host); fail:platform_device_unregister (pdev);return ret;
(going through old, unresolved email)
It looks like this might still be needed? I never saw an "it works" response to this email.
Jeff
Quoted 4 lines · Jeff Garzik
(going through old, unresolved email)
It looks like this might still be needed? I never saw an "it works" response to this email.
Indeed. Peter Zijlstra, can you please test it?
Signature · 1 line
tejun
PATCH 1/1 pata_legacy: fix no device fail path
When pata_legacy can't detect any device, it unregisters the platform_device and fails detection. However, it forgets to detach ata host triggering weird failures as the host later gets freed by devres while still attached. Fix it.
---
Well, with or without test verification, this patch is correct. Thanks.
drivers/ata/pata_legacy.c | 1 + 1 file changed, 1 insertion(+)
drivers/ata/pata_legacy.c +1 -0
@@ -1032,6 +1032,7 @@ static __init int legacy_init_one(struct legacy_probe *probe)return 0 ; } } +ata_host_detach (host); fail:platform_device_unregister (pdev);return ret;
Jeff Garzik
AppliedRe: [PATCH #upstream-fixes] pata_legacy: fix no device fail path
Quoted 5 lines · Tejun Heo
When
pata_legacycan't detect any device, it unregisters theplatform_deviceand fails detection. However, it forgets to detach ata host triggering weird failures as the host later gets freed by devres while still attached. Fix it.
Quoted 7 lines
Signed-off-by Tejun Heo <[email protected]>Reported-by Peter Zijlstra <[email protected]>---
Well, with or without test verification, this patch is correct. Thanks.drivers/ata/pata_legacy.c | 1 + 1 file changed, 1 insertion(+)
applied