[PATCH 4.14 033/140] scsi: qla2xxx: Fix Relogin being triggered too fast

From: Greg Kroah-Hartman
Date: Tue Mar 13 2018 - 11:36:37 EST


4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Quinn Tran <quinn.tran@xxxxxxxxxx>

commit 4005a995668b8fd58f4cf1460dd4cf63efa18363 upstream.

Current driver design schedules relogin process via DPC thread every 1
second. In a large fabric, this DPC thread tries to schedule too many
jobs and might get overloaded. As a result of this processing of DPC
thread, it can schedule relogin earlier than 1 second.

Fixes: 726b85487067d ("qla2xxx: Add framework for async fabric discovery")
Cc: <stable@xxxxxxxxxxxxxxx> # 4.10+
Signed-off-by: Quinn Tran <quinn.tran@xxxxxxxxxx>
Signed-off-by: Himanshu Madhani <himanshu.madhani@xxxxxxxxxx>
Reviewed-by: Hannes Reinecke <hare@xxxxxxxx>
Signed-off-by: Martin K. Petersen <martin.petersen@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>

---
drivers/scsi/qla2xxx/qla_def.h | 1 +
drivers/scsi/qla2xxx/qla_mid.c | 22 ++++++++++++++--------
drivers/scsi/qla2xxx/qla_os.c | 22 ++++++++++++++--------
3 files changed, 29 insertions(+), 16 deletions(-)

--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -4085,6 +4085,7 @@ typedef struct scsi_qla_host {
#define LOOP_READY 5
#define LOOP_DEAD 6

+ unsigned long relogin_jif;
unsigned long dpc_flags;
#define RESET_MARKER_NEEDED 0 /* Send marker to ISP. */
#define RESET_ACTIVE 1
--- a/drivers/scsi/qla2xxx/qla_mid.c
+++ b/drivers/scsi/qla2xxx/qla_mid.c
@@ -343,15 +343,21 @@ qla2x00_do_dpc_vp(scsi_qla_host_t *vha)
"FCPort update end.\n");
}

- if ((test_and_clear_bit(RELOGIN_NEEDED, &vha->dpc_flags)) &&
- !test_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags) &&
- atomic_read(&vha->loop_state) != LOOP_DOWN) {
+ if (test_bit(RELOGIN_NEEDED, &vha->dpc_flags) &&
+ !test_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags) &&
+ atomic_read(&vha->loop_state) != LOOP_DOWN) {

- ql_dbg(ql_dbg_dpc, vha, 0x4018,
- "Relogin needed scheduled.\n");
- qla2x00_relogin(vha);
- ql_dbg(ql_dbg_dpc, vha, 0x4019,
- "Relogin needed end.\n");
+ if (!vha->relogin_jif ||
+ time_after_eq(jiffies, vha->relogin_jif)) {
+ vha->relogin_jif = jiffies + HZ;
+ clear_bit(RELOGIN_NEEDED, &vha->dpc_flags);
+
+ ql_dbg(ql_dbg_dpc, vha, 0x4018,
+ "Relogin needed scheduled.\n");
+ qla2x00_relogin(vha);
+ ql_dbg(ql_dbg_dpc, vha, 0x4019,
+ "Relogin needed end.\n");
+ }
}

if (test_and_clear_bit(RESET_MARKER_NEEDED, &vha->dpc_flags) &&
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -4860,7 +4860,7 @@ void qla2x00_relogin(struct scsi_qla_hos
*/
if (atomic_read(&fcport->state) != FCS_ONLINE &&
fcport->login_retry && !(fcport->flags & FCF_ASYNC_SENT)) {
- fcport->login_retry--;
+
if (fcport->flags & FCF_FABRIC_DEVICE) {
ql_dbg(ql_dbg_disc, fcport->vha, 0x2108,
"%s %8phC DS %d LS %d\n", __func__,
@@ -4871,6 +4871,7 @@ void qla2x00_relogin(struct scsi_qla_hos
ea.fcport = fcport;
qla2x00_fcport_event_handler(vha, &ea);
} else {
+ fcport->login_retry--;
status = qla2x00_local_device_login(vha,
fcport);
if (status == QLA_SUCCESS) {
@@ -5853,16 +5854,21 @@ qla2x00_do_dpc(void *data)
}

/* Retry each device up to login retry count */
- if ((test_and_clear_bit(RELOGIN_NEEDED,
- &base_vha->dpc_flags)) &&
+ if (test_bit(RELOGIN_NEEDED, &base_vha->dpc_flags) &&
!test_bit(LOOP_RESYNC_NEEDED, &base_vha->dpc_flags) &&
atomic_read(&base_vha->loop_state) != LOOP_DOWN) {

- ql_dbg(ql_dbg_dpc, base_vha, 0x400d,
- "Relogin scheduled.\n");
- qla2x00_relogin(base_vha);
- ql_dbg(ql_dbg_dpc, base_vha, 0x400e,
- "Relogin end.\n");
+ if (!base_vha->relogin_jif ||
+ time_after_eq(jiffies, base_vha->relogin_jif)) {
+ base_vha->relogin_jif = jiffies + HZ;
+ clear_bit(RELOGIN_NEEDED, &base_vha->dpc_flags);
+
+ ql_dbg(ql_dbg_dpc, base_vha, 0x400d,
+ "Relogin scheduled.\n");
+ qla2x00_relogin(base_vha);
+ ql_dbg(ql_dbg_dpc, base_vha, 0x400e,
+ "Relogin end.\n");
+ }
}
loop_resync_check:
if (test_and_clear_bit(LOOP_RESYNC_NEEDED,