linux-kernel - [PATCH 4.4 089/132] scsi: lpfc: fcoe: Fix link down issue after 1000+ link bounces

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20191127203018.376194124@linuxfoundation.org>
Date:   Wed, 27 Nov 2019 21:31:20 +0100
From:   Greg Kroah-Hartman <gregkh@...uxfoundation.org>
To:     linux-kernel@...r.kernel.org
Cc:     Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
        stable@...r.kernel.org, Dick Kennedy <dick.kennedy@...adcom.com>,
        James Smart <jsmart2021@...il.com>,
        Hannes Reinecke <hare@...e.com>,
        "Martin K. Petersen" <martin.petersen@...cle.com>,
        Sasha Levin <sashal@...nel.org>
Subject: [PATCH 4.4 089/132] scsi: lpfc: fcoe: Fix link down issue after 1000+ link bounces

From: James Smart <jsmart2021@...il.com>

[ Upstream commit 036cad1f1ac9ce03e2db94b8460f98eaf1e1ee4c ]

On FCoE adapters, when running link bounce test in a loop, initiator
failed to login with switch switch and required driver reload to
recover. Switch reached a point where all subsequent FLOGIs would be
LS_RJT'd. Further testing showed the condition to be related to not
performing FCF discovery between FLOGI's.

Fix by monitoring FLOGI failures and once a repeated error is seen
repeat FCF discovery.

Signed-off-by: Dick Kennedy <dick.kennedy@...adcom.com>
Signed-off-by: James Smart <jsmart2021@...il.com>
Reviewed-by: Hannes Reinecke <hare@...e.com>
Signed-off-by: Martin K. Petersen <martin.petersen@...cle.com>
Signed-off-by: Sasha Levin <sashal@...nel.org>
---
 drivers/scsi/lpfc/lpfc_els.c     |  2 ++
 drivers/scsi/lpfc/lpfc_hbadisc.c | 20 ++++++++++++++++++++
 drivers/scsi/lpfc/lpfc_init.c    |  2 +-
 drivers/scsi/lpfc/lpfc_sli.c     | 11 ++---------
 drivers/scsi/lpfc/lpfc_sli4.h    |  1 +
 5 files changed, 26 insertions(+), 10 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index 82a690924f5eb..7ca8c2522c928 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -1124,6 +1124,7 @@ lpfc_cmpl_els_flogi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 			phba->fcf.fcf_flag &= ~FCF_DISCOVERY;
 			phba->hba_flag &= ~(FCF_RR_INPROG | HBA_DEVLOSS_TMO);
 			spin_unlock_irq(&phba->hbalock);
+			phba->fcf.fcf_redisc_attempted = 0; /* reset */
 			goto out;
 		}
 		if (!rc) {
@@ -1138,6 +1139,7 @@ lpfc_cmpl_els_flogi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 			phba->fcf.fcf_flag &= ~FCF_DISCOVERY;
 			phba->hba_flag &= ~(FCF_RR_INPROG | HBA_DEVLOSS_TMO);
 			spin_unlock_irq(&phba->hbalock);
+			phba->fcf.fcf_redisc_attempted = 0; /* reset */
 			goto out;
 		}
 	}
diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index a67950908db17..d50db2004d21e 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -1966,6 +1966,26 @@ int lpfc_sli4_fcf_rr_next_proc(struct lpfc_vport *vport, uint16_t fcf_index)
 				"failover and change port state:x%x/x%x\n",
 				phba->pport->port_state, LPFC_VPORT_UNKNOWN);
 		phba->pport->port_state = LPFC_VPORT_UNKNOWN;
+
+		if (!phba->fcf.fcf_redisc_attempted) {
+			lpfc_unregister_fcf(phba);
+
+			rc = lpfc_sli4_redisc_fcf_table(phba);
+			if (!rc) {
+				lpfc_printf_log(phba, KERN_INFO, LOG_FIP,
+						"3195 Rediscover FCF table\n");
+				phba->fcf.fcf_redisc_attempted = 1;
+				lpfc_sli4_clear_fcf_rr_bmask(phba);
+			} else {
+				lpfc_printf_log(phba, KERN_WARNING, LOG_FIP,
+						"3196 Rediscover FCF table "
+						"failed. Status:x%x\n", rc);
+			}
+		} else {
+			lpfc_printf_log(phba, KERN_WARNING, LOG_FIP,
+					"3197 Already rediscover FCF table "
+					"attempted. No more retry\n");
+		}
 		goto stop_flogi_current_fcf;
 	} else {
 		lpfc_printf_log(phba, KERN_INFO, LOG_FIP | LOG_ELS,
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index 60c21093f8656..7e06fd6127ccb 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -4376,7 +4376,7 @@ lpfc_sli4_async_fip_evt(struct lpfc_hba *phba,
 			break;
 		}
 		/* If fast FCF failover rescan event is pending, do nothing */
-		if (phba->fcf.fcf_flag & FCF_REDISC_EVT) {
+		if (phba->fcf.fcf_flag & (FCF_REDISC_EVT | FCF_REDISC_PEND)) {
 			spin_unlock_irq(&phba->hbalock);
 			break;
 		}
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index ad4f16ab7f7a2..523a1058078a5 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -16350,15 +16350,8 @@ lpfc_sli4_fcf_rr_next_index_get(struct lpfc_hba *phba)
 			goto initial_priority;
 		lpfc_printf_log(phba, KERN_WARNING, LOG_FIP,
 				"2844 No roundrobin failover FCF available\n");
-		if (next_fcf_index >= LPFC_SLI4_FCF_TBL_INDX_MAX)
-			return LPFC_FCOE_FCF_NEXT_NONE;
-		else {
-			lpfc_printf_log(phba, KERN_WARNING, LOG_FIP,
-				"3063 Only FCF available idx %d, flag %x\n",
-				next_fcf_index,
-			phba->fcf.fcf_pri[next_fcf_index].fcf_rec.flag);
-			return next_fcf_index;
-		}
+
+		return LPFC_FCOE_FCF_NEXT_NONE;
 	}
 
 	if (next_fcf_index < LPFC_SLI4_FCF_TBL_INDX_MAX &&
diff --git a/drivers/scsi/lpfc/lpfc_sli4.h b/drivers/scsi/lpfc/lpfc_sli4.h
index 1e916e16ce989..0ecf92c8a2882 100644
--- a/drivers/scsi/lpfc/lpfc_sli4.h
+++ b/drivers/scsi/lpfc/lpfc_sli4.h
@@ -237,6 +237,7 @@ struct lpfc_fcf {
 #define FCF_REDISC_EVT	0x100 /* FCF rediscovery event to worker thread */
 #define FCF_REDISC_FOV	0x200 /* Post FCF rediscovery fast failover */
 #define FCF_REDISC_PROG (FCF_REDISC_PEND | FCF_REDISC_EVT)
+	uint16_t fcf_redisc_attempted;
 	uint32_t addr_mode;
 	uint32_t eligible_fcf_cnt;
 	struct lpfc_fcf_rec current_rec;
-- 
2.20.1