From: Justin Tee <justin.tee@broadcom.com>
Date: Mon, 9 Oct 2023 09:18:08 -0700
Subject: scsi: lpfc: Treat IOERR_SLI_DOWN I/O completion status the same as
 pci offline
Patch-mainline: v6.7-rc1
Git-commit: d472a76603d8a04246dda05c4918281dfb61ed60
References: bsc#1217124

During receipt of a hardware error attention ACQE, IOERR_SLI_DOWN status is
set by the driver for all outstanding I/Os.

In such hardware error attention cases, we can treat the situation exactly
the same as pci_channel_offline.  Thus, add IOERR_SLI_DOWN status to the
same category as pci_channel_offline handling in lpfc_nvme_io_cmd_cmpl.

Signed-off-by: Justin Tee <justin.tee@broadcom.com>
Link: https://lore.kernel.org/r/20231009161812.97232-3-justintee8345@gmail.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Acked-by: Daniel Wagner <dwagner@suse.de>
---
 drivers/scsi/lpfc/lpfc_nvme.c |    6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

--- a/drivers/scsi/lpfc/lpfc_nvme.c
+++ b/drivers/scsi/lpfc/lpfc_nvme.c
@@ -950,7 +950,7 @@ lpfc_nvme_io_cmd_cmpl(struct lpfc_hba *p
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
 	int cpu;
 #endif
-	int offline = 0;
+	bool offline = false;
 
 	/* Sanity check on return of outstanding command */
 	if (!lpfc_ncmd) {
@@ -1124,7 +1124,9 @@ lpfc_nvme_io_cmd_cmpl(struct lpfc_hba *p
 			nCmd->transferred_length = 0;
 			nCmd->rcv_rsplen = 0;
 			nCmd->status = NVME_SC_INTERNAL;
-			offline = pci_channel_offline(vport->phba->pcidev);
+			if (pci_channel_offline(vport->phba->pcidev) ||
+			    lpfc_ncmd->result == IOERR_SLI_DOWN)
+				offline = true;
 		}
 	}