da(4): Fix a TRIM regression introduced in r308155
According to Warner, multiple TRIM BIOs are collapsed into a single CCB with NULL bp. It is invalid to biotrack() NULL, and results in a fault. So, don't do that. Reported by: asomers@ Sponsored by: Dell EMC Isilon
This commit is contained in:
parent
e42e532ea5
commit
4087477929
@ -4169,7 +4169,8 @@ dadone(struct cam_periph *periph, union ccb *done_ccb)
|
||||
}
|
||||
}
|
||||
|
||||
biotrack(bp, __func__);
|
||||
if (bp != NULL)
|
||||
biotrack(bp, __func__);
|
||||
LIST_REMOVE(&done_ccb->ccb_h, periph_links.le);
|
||||
if (LIST_EMPTY(&softc->pending_ccbs))
|
||||
softc->flags |= DA_FLAG_WAS_OTAG;
|
||||
|
Loading…
Reference in New Issue
Block a user