Hi,
I've got kernel panic on my box which works as FibreChannel initiator.
I was able to reproduce this panic by setting dev_loss_tmo=2 and
enabling/disabling ports every 5 seconds on the switch in 5 minutes. I
added some debug points in the kernel code and that's what I've got so far:
1. system is inserting new device into __devices list
DEBUG: scsi_sysfs_device_initialize(): sdev=ffff88046a931000 7:0:5:0
Pid: 910, comm: kworker/u:2 Tainted: P O 3.2.48-swt9004 #33
Call Trace:
[<ffffffff81245c42>] ? scsi_alloc_sdev+0x1d2/0x240
[<ffffffff8123d4bd>] ? scsi_device_lookup_by_target+0x8d/0xc0
[<ffffffff8124623a>] ? scsi_probe_and_add_lun+0x42a/0xb20
[<ffffffff811acb7d>] ? kobject_set_name_vargs+0x6d/0x80
[<ffffffff81230b4f>] ? dev_set_name+0x3f/0x50
[<ffffffff811ac782>] ? kobject_get+0x12/0x20
[<ffffffffa000b3e4>] ? fc_host_match+0x14/0x70 [scsi_transport_fc]
[<ffffffff8123726f>] ? attribute_container_add_device+0x4f/0x160
[<ffffffff811ac782>] ? kobject_get+0x12/0x20
[<ffffffff812304e4>] ? get_device+0x14/0x20
[<ffffffff812459c5>] ? scsi_alloc_target+0x295/0x2d0
[<ffffffff81230bca>] ? device_release+0x1a/0x80
[<ffffffff81246bce>] ? __scsi_scan_target+0xce/0x5f0
[<ffffffff8102ec22>] ? dequeue_task_fair+0x52/0x150
[<ffffffff8139a91d>] ? __schedule+0x25d/0x7d0
[<ffffffff812477b6>] ? scsi_scan_target+0xc6/0xe0
[<ffffffffa000e75f>] ? fc_scsi_scan_rport+0xaf/0xc0 [scsi_transport_fc]
[<ffffffff8104eb06>] ? process_one_work+0x116/0x3a0
[<ffffffff8104f1ec>] ? worker_thread+0x14c/0x400
[<ffffffff8104f0a0>] ? rescuer_thread+0x310/0x310
[<ffffffff8104f0a0>] ? rescuer_thread+0x310/0x310
[<ffffffff81052f06>] ? kthread+0x96/0xa0
[<ffffffff8139f134>] ? kernel_thread_helper+0x4/0x10
[<ffffffff81052e70>] ? kthread_worker_fn+0x120/0x120
[<ffffffff8139f130>] ? gs_change+0xb/0xb
2. later in scsi_probe_and_add_lun() this device is removing
DEBUG: __scsi_remove_device(): sdev=ffff88046a931000 7:0:5:0
Pid: 910, comm: kworker/u:2 Tainted: P O 3.2.48-swt9004 #33
Call Trace:
[<ffffffff81248c66>] ? __scsi_remove_device+0x46/0x110
[<ffffffff81246268>] ? scsi_probe_and_add_lun+0x458/0xb20
[<ffffffff81230b4f>] ? dev_set_name+0x3f/0x50
[<ffffffff811ac782>] ? kobject_get+0x12/0x20
[<ffffffff812459c5>] ? scsi_alloc_target+0x295/0x2d0
[<ffffffff81230bca>] ? device_release+0x1a/0x80
[<ffffffff81246bce>] ? __scsi_scan_target+0xce/0x5f0
[<ffffffff8102ec22>] ? dequeue_task_fair+0x52/0x150
[<ffffffff8139a91d>] ? __schedule+0x25d/0x7d0
[<ffffffff812477b6>] ? scsi_scan_target+0xc6/0xe0
[<ffffffffa000e75f>] ? fc_scsi_scan_rport+0xaf/0xc0 [scsi_transport_fc]
[<ffffffff8104eb06>] ? process_one_work+0x116/0x3a0
[<ffffffff8104f1ec>] ? worker_thread+0x14c/0x400
[<ffffffff8104f0a0>] ? rescuer_thread+0x310/0x310
[<ffffffff8104f0a0>] ? rescuer_thread+0x310/0x310
[<ffffffff81052f06>] ? kthread+0x96/0xa0
[<ffffffff8139f134>] ? kernel_thread_helper+0x4/0x10
[<ffffffff81052e70>] ? kthread_worker_fn+0x120/0x120
[<ffffffff8139f130>] ? gs_change+0xb/0xb
3. another thread is trying to remove this device because of timeout
DEBUG: __scsi_remove_device(): sdev=ffff88046a931000 7:0:5:0
Pid: 4, comm: kworker/0:0 Tainted: P O 3.2.48-swt9004 #33
Call Trace:
[<ffffffff81248c66>] ? __scsi_remove_device+0x46/0x110
[<ffffffff8139b63a>] ? mutex_lock+0x1a/0x40
[<ffffffff81248d58>] ? scsi_remove_device+0x28/0x40
[<ffffffff81242a00>] ? scsi_kmap_atomic_sg+0x180/0x180
[<ffffffff81248ed1>] ? scsi_remove_target+0x141/0x1e0
[<ffffffff8104eb06>] ? process_one_work+0x116/0x3a0
[<ffffffff8104f1ec>] ? worker_thread+0x14c/0x400
[<ffffffff8104f0a0>] ? rescuer_thread+0x310/0x310
[<ffffffff8104f0a0>] ? rescuer_thread+0x310/0x310
[<ffffffff81052f06>] ? kthread+0x96/0xa0
[<ffffffff8139f134>] ? kernel_thread_helper+0x4/0x10
[<ffffffff81052e70>] ? kthread_worker_fn+0x120/0x120
[<ffffffff8139f130>] ? gs_change+0xb/0xb
and it's got dead sdev object. I don't understand how this can happen
because __scsi_remove_target() iterating over __devices and getting sdev
reference under host_lock and that should be enough.
DEBUG: kref_put(): kref=ffff88046a9312e0 val=-1
------------[ cut here ]------------
WARNING: at lib/kref.c:61 kref_put+0x88/0xc0()
Hardware name: X9DRi-LN4+/X9DR3-LN4+
Modules linked in: qla2xxx(O) igb ehci_hcd scsi_transport_fc
Pid: 4, comm: kworker/0:0 Tainted: P O 3.2.48-swt9004 #33
Call Trace:
[<ffffffff81037bfb>] ? warn_slowpath_common+0x7b/0xc0
[<ffffffff811ac6c0>] ? kobject_del+0x30/0x30
[<ffffffff811adb08>] ? kref_put+0x88/0xc0
[<ffffffff81248cac>] ? __scsi_remove_device+0x8c/0x110
[<ffffffff8139b63a>] ? mutex_lock+0x1a/0x40
[<ffffffff81248d58>] ? scsi_remove_device+0x28/0x40
[<ffffffff81242a00>] ? scsi_kmap_atomic_sg+0x180/0x180
[<ffffffff81248ed1>] ? scsi_remove_target+0x141/0x1e0
[<ffffffff8104eb06>] ? process_one_work+0x116/0x3a0
[<ffffffff8104f1ec>] ? worker_thread+0x14c/0x400
[<ffffffff8104f0a0>] ? rescuer_thread+0x310/0x310
[<ffffffff8104f0a0>] ? rescuer_thread+0x310/0x310
[<ffffffff81052f06>] ? kthread+0x96/0xa0
[<ffffffff8139f134>] ? kernel_thread_helper+0x4/0x10
[<ffffffff81052e70>] ? kthread_worker_fn+0x120/0x120
[<ffffffff8139f130>] ? gs_change+0xb/0xb
Here is the patch which helped me:
diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
index 9117d0b..676e5ff 100644
--- a/drivers/scsi/scsi_sysfs.c
+++ b/drivers/scsi/scsi_sysfs.c
@@ -1094,6 +1094,7 @@ static void __scsi_remove_target(struct
scsi_target *starget)
unsigned long flags;
struct scsi_device *sdev;
+ mutex_lock(&shost->scan_mutex);
spin_lock_irqsave(shost->host_lock, flags);
restart:
list_for_each_entry(sdev, &shost->__devices, siblings) {
@@ -1102,12 +1103,13 @@ static void __scsi_remove_target(struct
scsi_target *starget)
scsi_device_get(sdev))
continue;
spin_unlock_irqrestore(shost->host_lock, flags);
- scsi_remove_device(sdev);
+ __scsi_remove_device(sdev);
scsi_device_put(sdev);
spin_lock_irqsave(shost->host_lock, flags);
goto restart;
}
spin_unlock_irqrestore(shost->host_lock, flags);
+ mutex_unlock(&shost->scan_mutex);
}
/**
I'm not sure about the fix is correct, but I was not able to reproduce
the panic.
P.S. Here is another patch which help to detect reference count underflow
diff --git a/include/linux/kref.h b/include/linux/kref.h
index 484604d..05dd2b3 100644
--- a/include/linux/kref.h
+++ b/include/linux/kref.h
@@ -68,9 +68,13 @@ static inline void kref_get(struct kref *kref)
static inline int kref_sub(struct kref *kref, unsigned int count,
void (*release)(struct kref *kref))
{
+ long refs;
+
WARN_ON(release == NULL);
- if (atomic_sub_and_test((int) count, &kref->refcount)) {
+ refs = atomic_sub_return((int) count, &kref->refcount);
+ WARN_ON(refs < 0);
+ if (refs == 0) {
release(kref);
return 1;
}
--
Andrey Zonov
--
To unsubscribe from this list: send the line "unsubscribe linux-scsi" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
