diff mbox series

qla2xxx: Fix crash when IO abort times out

Message ID 20221129092634.15347-1-njavali@marvell.com
State New
Headers show
Series qla2xxx: Fix crash when IO abort times out | expand

Commit Message

Nilesh Javali Nov. 29, 2022, 9:26 a.m. UTC 
From: Arun Easi <aeasi@marvell.com>

While performing CPU hotplug, a crash with the following stack was
seen:

Call Trace:
     qla24xx_process_response_queue+0x42a/0x970 [qla2xxx]
     qla2x00_start_nvme_mq+0x3a2/0x4b0 [qla2xxx]
     qla_nvme_post_cmd+0x166/0x240 [qla2xxx]
     nvme_fc_start_fcp_op.part.0+0x119/0x2e0 [nvme_fc]
     blk_mq_dispatch_rq_list+0x17b/0x610
     __blk_mq_sched_dispatch_requests+0xb0/0x140
     blk_mq_sched_dispatch_requests+0x30/0x60
     __blk_mq_run_hw_queue+0x35/0x90
     __blk_mq_delay_run_hw_queue+0x161/0x180
     blk_execute_rq+0xbe/0x160
     __nvme_submit_sync_cmd+0x16f/0x220 [nvme_core]
     nvmf_connect_admin_queue+0x11a/0x170 [nvme_fabrics]
     nvme_fc_create_association.cold+0x50/0x3dc [nvme_fc]
     nvme_fc_connect_ctrl_work+0x19/0x30 [nvme_fc]
     process_one_work+0x1e8/0x3c0

On abort timeout, an IO completion was called without
checking if that was already completed or not leading
up to a crash.

Verify IO and abort request are indeed outstanding before
attempting completion.

Fixes: ca66aa0949a0 ("scsi: qla2xxx: Do command completion on abort timeout")
Reported-by: Marco Patalano <mpatalan@redhat.com>
Tested-by: Marco Patalano <mpatalan@redhat.com>
Cc: stable@vger.kernel.org
Signed-off-by: Arun Easi <aeasi@marvell.com>
Signed-off-by: Nilesh Javali <njavali@marvell.com>
---
 drivers/scsi/qla2xxx/qla_init.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

Comments

Martin K. Petersen Dec. 1, 2022, 3:34 a.m. UTC | #1 
Nilesh,

> On abort timeout, an IO completion was called without checking if that
> was already completed or not leading up to a crash.
>
> Verify IO and abort request are indeed outstanding before attempting
> completion.
>
> Fixes: ca66aa0949a0 ("scsi: qla2xxx: Do command completion on abort timeout")

I believe that was supposed to be 71c80b75ce8f. Fixed it up and applied
to 6.2/scsi-staging!
diff mbox series

Patch

diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 29ce6a55ce5e..ee5927cb51ca 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -110,6 +110,7 @@  static void qla24xx_abort_iocb_timeout(void *data)
 	struct qla_qpair *qpair = sp->qpair;
 	u32 handle;
 	unsigned long flags;
+	int sp_found = 0, cmdsp_found = 0;
 
 	if (sp->cmd_sp)
 		ql_dbg(ql_dbg_async, sp->vha, 0x507c,
@@ -124,18 +125,21 @@  static void qla24xx_abort_iocb_timeout(void *data)
 	spin_lock_irqsave(qpair->qp_lock_ptr, flags);
 	for (handle = 1; handle < qpair->req->num_outstanding_cmds; handle++) {
 		if (sp->cmd_sp && (qpair->req->outstanding_cmds[handle] ==
-		    sp->cmd_sp))
+		    sp->cmd_sp)) {
 			qpair->req->outstanding_cmds[handle] = NULL;
+			cmdsp_found = 1;
+		}
 
 		/* removing the abort */
 		if (qpair->req->outstanding_cmds[handle] == sp) {
 			qpair->req->outstanding_cmds[handle] = NULL;
+			sp_found = 1;
 			break;
 		}
 	}
 	spin_unlock_irqrestore(qpair->qp_lock_ptr, flags);
 
-	if (sp->cmd_sp) {
+	if (cmdsp_found && sp->cmd_sp) {
 		/*
 		 * This done function should take care of
 		 * original command ref: INIT
@@ -143,8 +147,10 @@  static void qla24xx_abort_iocb_timeout(void *data)
 		sp->cmd_sp->done(sp->cmd_sp, QLA_OS_TIMER_EXPIRED);
 	}
 
-	abt->u.abt.comp_status = cpu_to_le16(CS_TIMEOUT);
-	sp->done(sp, QLA_OS_TIMER_EXPIRED);
+	if (sp_found) {
+		abt->u.abt.comp_status = cpu_to_le16(CS_TIMEOUT);
+		sp->done(sp, QLA_OS_TIMER_EXPIRED);
+	}
 }
 
 static void qla24xx_abort_sp_done(srb_t *sp, int res)