Blob Blame History Raw
From 62fa3ce05d5d73c5eccc40b2db493f55fecfc446 Mon Sep 17 00:00:00 2001
From: Brian King <brking@linux.vnet.ibm.com>
Date: Wed, 26 Oct 2022 13:13:56 -0500
Subject: [PATCH] scsi: ibmvfc: Avoid path failures during live migration

References: bsc#1065729 bsc#1204810 ltc#200162
Patch-mainline: v6.1-rc5
Git-commit: 62fa3ce05d5d73c5eccc40b2db493f55fecfc446

Fix an issue reported when performing a live migration when multipath is
configured with a short fast fail timeout of 5 seconds and also to have
no_path_retry set to fail. In this scenario, all paths would go into the
devloss state while the ibmvfc driver went through discovery to log back
in. On a loaded system, the discovery might take longer than 5 seconds,
which was resulting in all paths being marked failed, which then resulted
in a read only filesystem.

This patch changes the migration code in ibmvfc to avoid deleting rports at
all in this scenario, so we avoid losing all paths.

Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Link: https://lore.kernel.org/r/20221026181356.148517-1-brking@linux.vnet.ibm.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Acked-by: Michal Suchanek <msuchanek@suse.de>
---
 drivers/scsi/ibmvscsi/ibmvfc.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -708,8 +708,13 @@ static void ibmvfc_init_host(struct ibmvfc_host *vhost)
 		memset(vhost->async_crq.msgs, 0, PAGE_SIZE);
 		vhost->async_crq.cur = 0;
 
-		list_for_each_entry(tgt, &vhost->targets, queue)
-			ibmvfc_del_tgt(tgt);
+		list_for_each_entry(tgt, &vhost->targets, queue) {
+			if (vhost->client_migrated)
+				tgt->need_login = 1;
+			else
+				ibmvfc_del_tgt(tgt);
+		}
+
 		scsi_block_requests(vhost->host);
 		ibmvfc_set_host_action(vhost, IBMVFC_HOST_ACTION_INIT);
 		vhost->job_step = ibmvfc_npiv_login;
@@ -3235,9 +3240,12 @@ static void ibmvfc_handle_crq(struct ibmvfc_crq *crq, struct ibmvfc_host *vhost,
 			/* We need to re-setup the interpartition connection */
 			dev_info(vhost->dev, "Partition migrated, Re-enabling adapter\n");
 			vhost->client_migrated = 1;
+
+			scsi_block_requests(vhost->host);
 			ibmvfc_purge_requests(vhost, DID_REQUEUE);
-			ibmvfc_link_down(vhost, IBMVFC_LINK_DOWN);
+			ibmvfc_set_host_state(vhost, IBMVFC_LINK_DOWN);
 			ibmvfc_set_host_action(vhost, IBMVFC_HOST_ACTION_REENABLE);
+			wake_up(&vhost->work_wait_q);
 		} else if (crq->format == IBMVFC_PARTNER_FAILED || crq->format == IBMVFC_PARTNER_DEREGISTER) {
 			dev_err(vhost->dev, "Host partner adapter deregistered or failed (rc=%d)\n", crq->format);
 			ibmvfc_purge_requests(vhost, DID_ERROR);
-- 
2.35.3