scsi: qla2xxx: Fix hang due to session stuck

commit c02aada06d19a215c8291bd968a99a270e96f734 upstream.

User experienced device lost. The log shows Get port data base command was
queued up, failed, and requeued again. Every time it is requeued, it set
the FCF_ASYNC_ACTIVE. This prevents any recovery code from occurring
because driver thinks a recovery is in progress for this session. In
essence, this session is hung.  The reason it gets into this place is the
session deletion got in front of this call due to link perturbation.

Break the requeue cycle and exit.  The session deletion code will trigger a
session relogin.

Link: https://lore.kernel.org/r/20220310092604.22950-8-njavali@marvell.com
Fixes: 726b85487067 ("qla2xxx: Add framework for async fabric discovery")
Cc: stable@vger.kernel.org
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
Signed-off-by: Quinn Tran <qutran@marvell.com>
Signed-off-by: Nilesh Javali <njavali@marvell.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 47835d26a973018f5377f0c4b4d5f46a49d9d3e4..300ef2e2ae5a9218498b774843c62a1c1c5cb154 100644 (file)
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -4655,4 +4655,8 @@ struct sff_8247_a0 {
 #include "qla_gbl.h"
 #include "qla_dbg.h"
 #include "qla_inline.h"
+
+#define IS_SESSION_DELETED(_fcport) (_fcport->disc_state == DSC_DELETE_PEND || \
+                                     _fcport->disc_state == DSC_DELETED)
+
 #endif

diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 481e061dc94a55f67f1d978ddf598d6071f9fd6b..3f8aa7f4585f8d4b853a200963a3d30c9ce96007 100644 (file)
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -891,6 +891,14 @@ int qla24xx_async_gnl(struct scsi_qla_host *vha, fc_port_t *fcport)
        unsigned long flags;
        u16 *mb;
 
+       if (IS_SESSION_DELETED(fcport)) {
+               ql_log(ql_log_warn, vha, 0xffff,
+                      "%s: %8phC is being delete - not sending command.\n",
+                      __func__, fcport->port_name);
+               fcport->flags &= ~FCF_ASYNC_ACTIVE;
+               return rval;
+       }
+
        if (!vha->flags.online || (fcport->flags & FCF_ASYNC_SENT))
                return rval;
 
@@ -1121,8 +1129,15 @@ int qla24xx_async_gpdb(struct scsi_qla_host *vha, fc_port_t *fcport, u8 opt)
        struct port_database_24xx *pd;
        struct qla_hw_data *ha = vha->hw;
 
-       if (!vha->flags.online || (fcport->flags & FCF_ASYNC_SENT) ||
-           fcport->loop_id == FC_NO_LOOP_ID) {
+       if (IS_SESSION_DELETED(fcport)) {
+               ql_log(ql_log_warn, vha, 0xffff,
+                      "%s: %8phC is being delete - not sending command.\n",
+                      __func__, fcport->port_name);
+               fcport->flags &= ~FCF_ASYNC_ACTIVE;
+               return rval;
+       }
+
+       if (!vha->flags.online || fcport->flags & FCF_ASYNC_SENT) {
                ql_log(ql_log_warn, vha, 0xffff,
                    "%s: %8phC - not sending command.\n",
                    __func__, fcport->port_name);