@@ -1797,19 +1797,22 @@ lpfc_sli4_nvmet_xri_aborted(struct lpfc_hba *phba,
if (ctxp->ctxbuf->sglq->sli4_xritag != xri)
continue;
- spin_lock(&ctxp->ctxlock);
+ spin_unlock_irqrestore(&phba->sli4_hba.abts_nvmet_buf_list_lock,
+ iflag);
+
+ spin_lock_irqsave(&ctxp->ctxlock, iflag);
/* Check if we already received a free context call
* and we have completed processing an abort situation.
*/
if (ctxp->flag & LPFC_NVME_CTX_RLS &&
!(ctxp->flag & LPFC_NVME_ABORT_OP)) {
+ spin_lock(&phba->sli4_hba.abts_nvmet_buf_list_lock);
list_del_init(&ctxp->list);
+ spin_unlock(&phba->sli4_hba.abts_nvmet_buf_list_lock);
released = true;
}
ctxp->flag &= ~LPFC_NVME_XBUSY;
- spin_unlock(&ctxp->ctxlock);
- spin_unlock_irqrestore(&phba->sli4_hba.abts_nvmet_buf_list_lock,
- iflag);
+ spin_unlock_irqrestore(&ctxp->ctxlock, iflag);
rrq_empty = list_empty(&phba->active_rrq_list);
ndlp = lpfc_findnode_did(phba->pport, ctxp->sid);
The lpfc_sli4_nvmet_xri_aborted routine takes out the abts_buf_list_lock and traverses the buffer contexts to match the xri. Upon match, it then takes the context lock before potentially removing the context from the associated buffer list. This violates the lock hierarchy used elsewhere in the driver of locking context, then the abts_buf_list_lock - thus a possible deadlock. Resolve by: after matching, release the abts_buf_list_lock, then take the context lock, and if to be deleted from the list, retake the abts_buf_list_lock, maintaining lock hierarchy. This matches same list lock hierarchy as elsewhere in the driver Reported-by: Jia-Ju Bai <baijiaju1990@gmail.com> Signed-off-by: James Smart <jsmart2021@gmail.com> --- drivers/scsi/lpfc/lpfc_nvmet.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-)