diff mbox series

lpfc: fix possible ABBA deadlock in nvmet_xri_aborted

Message ID 20210730163309.25809-1-jsmart2021@gmail.com
State New
Headers show
Series lpfc: fix possible ABBA deadlock in nvmet_xri_aborted | expand

Commit Message

James Smart July 30, 2021, 4:33 p.m. UTC
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(-)

Comments

Martin K. Petersen July 31, 2021, 3:47 a.m. UTC | #1
James,

> 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.


Applied to 5.15/scsi-staging, thanks!

-- 
Martin K. Petersen	Oracle Linux Engineering
diff mbox series

Patch

diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c
index f2d9a3580887..6e3dd0b9bcfa 100644
--- a/drivers/scsi/lpfc/lpfc_nvmet.c
+++ b/drivers/scsi/lpfc/lpfc_nvmet.c
@@ -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);