[SCSI] scsi_dh: check queuedata pointer before proceeding further

This patch validates sdev pointer in scsi_dh_activate before proceeding further.

Without this check we might see the panic as below. I have seen this
panic multiple times..

Call trace:

 #0 [ffff88007d647b50] machine_kexec at ffffffff81020902
 #1 [ffff88007d647ba0] crash_kexec at ffffffff810875b0
 #2 [ffff88007d647c70] oops_end at ffffffff8139c650
 #3 [ffff88007d647c90] __bad_area_nosemaphore at ffffffff8102dd15
 #4 [ffff88007d647d50] page_fault at ffffffff8139b8cf
    [exception RIP: scsi_dh_activate+0x82]
    RIP: ffffffffa0041922  RSP: ffff88007d647e00  RFLAGS: 00010046
    RAX: 0000000000000000  RBX: 0000000000000000  RCX: 00000000000093c5
    RDX: 00000000000093c5  RSI: ffffffffa02e6640  RDI: ffff88007cc88988
    RBP: 000000000000000f   R8: ffff88007d646000   R9: 0000000000000000
    R10: ffff880082293790  R11: 00000000ffffffff  R12: ffff88007cc88988
    R13: 0000000000000000  R14: 0000000000000286  R15: ffff880037b845e0
    ORIG_RAX: ffffffffffffffff  CS: 0010  SS: 0000
 #5 [ffff88007d647e38] run_workqueue at ffffffff81060268
 #6 [ffff88007d647e78] worker_thread at ffffffff81060386
 #7 [ffff88007d647ee8] kthread at ffffffff81064436
 #8 [ffff88007d647f48] kernel_thread at ffffffff81003fba

Signed-off-by: Babu Moger <babu.moger@netapp.com>
Cc: stable@kernel.org
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
This commit is contained in:
Moger, Babu 2011-10-26 14:29:38 -04:00 committed by James Bottomley
parent a0c124137a
commit a18a920c70

View File

@ -441,7 +441,15 @@ int scsi_dh_activate(struct request_queue *q, activate_complete fn, void *data)
spin_lock_irqsave(q->queue_lock, flags);
sdev = q->queuedata;
if (sdev && sdev->scsi_dh_data)
if (!sdev) {
spin_unlock_irqrestore(q->queue_lock, flags);
err = SCSI_DH_NOSYS;
if (fn)
fn(data, err);
return err;
}
if (sdev->scsi_dh_data)
scsi_dh = sdev->scsi_dh_data->scsi_dh;
dev = get_device(&sdev->sdev_gendev);
if (!scsi_dh || !dev ||