[PATCH AUTOSEL 5.4 02/52] nvme_fc: add module to ops template to allow module references

[PATCH AUTOSEL 5.4 02/52] nvme_fc: add module to ops template to allow module references

[Sasha Levin]

From: James Smart <jsmart2021@gmail.com>

[ Upstream commit 863fbae929c7a5b64e96b8a3ffb34a29eefb9f8f ]

In nvme-fc: it's possible to have connected active controllers
and as no references are taken on the LLDD, the LLDD can be
unloaded.  The controller would enter a reconnect state and as
long as the LLDD resumed within the reconnect timeout, the
controller would resume.  But if a namespace on the controller
is the root device, allowing the driver to unload can be problematic.
To reload the driver, it may require new io to the boot device,
and as it's no longer connected we get into a catch-22 that
eventually fails, and the system locks up.

Fix this issue by taking a module reference for every connected
controller (which is what the core layer did to the transport
module). Reference is cleared when the controller is removed.

Acked-by: Himanshu Madhani <hmadhani@marvell.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/nvme/host/fc.c          | 14 ++++++++++++--
 drivers/nvme/target/fcloop.c    |  1 +
 drivers/scsi/lpfc/lpfc_nvme.c   |  2 ++
 drivers/scsi/qla2xxx/qla_nvme.c |  1 +
 include/linux/nvme-fc-driver.h  |  4 ++++
 5 files changed, 20 insertions(+), 2 deletions(-)

diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 265f89e11d8b9..3f102d9f39b83 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -342,7 +342,8 @@ nvme_fc_register_localport(struct nvme_fc_port_info *pinfo,
 	    !template->ls_req || !template->fcp_io ||
 	    !template->ls_abort || !template->fcp_abort ||
 	    !template->max_hw_queues || !template->max_sgl_segments ||
-	    !template->max_dif_sgl_segments || !template->dma_boundary) {
+	    !template->max_dif_sgl_segments || !template->dma_boundary ||
+	    !template->module) {
 		ret = -EINVAL;
 		goto out_reghost_failed;
 	}
@@ -2015,6 +2016,7 @@ nvme_fc_ctrl_free(struct kref *ref)
 {
 	struct nvme_fc_ctrl *ctrl =
 		container_of(ref, struct nvme_fc_ctrl, ref);
+	struct nvme_fc_lport *lport = ctrl->lport;
 	unsigned long flags;
 
 	if (ctrl->ctrl.tagset) {
@@ -2041,6 +2043,7 @@ nvme_fc_ctrl_free(struct kref *ref)
 	if (ctrl->ctrl.opts)
 		nvmf_free_options(ctrl->ctrl.opts);
 	kfree(ctrl);
+	module_put(lport->ops->module);
 }
 
 static void
@@ -3056,10 +3059,15 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 		goto out_fail;
 	}
 
+	if (!try_module_get(lport->ops->module)) {
+		ret = -EUNATCH;
+		goto out_free_ctrl;
+	}
+
 	idx = ida_simple_get(&nvme_fc_ctrl_cnt, 0, 0, GFP_KERNEL);
 	if (idx < 0) {
 		ret = -ENOSPC;
-		goto out_free_ctrl;
+		goto out_mod_put;
 	}
 
 	ctrl->ctrl.opts = opts;
@@ -3212,6 +3220,8 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 out_free_ida:
 	put_device(ctrl->dev);
 	ida_simple_remove(&nvme_fc_ctrl_cnt, ctrl->cnum);
+out_mod_put:
+	module_put(lport->ops->module);
 out_free_ctrl:
 	kfree(ctrl);
 out_fail:
diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c
index b50b53db37462..1c50af6219f32 100644
--- a/drivers/nvme/target/fcloop.c
+++ b/drivers/nvme/target/fcloop.c
@@ -850,6 +850,7 @@ fcloop_targetport_delete(struct nvmet_fc_target_port *targetport)
 #define FCLOOP_DMABOUND_4G		0xFFFFFFFF
 
 static struct nvme_fc_port_template fctemplate = {
+	.module			= THIS_MODULE,
 	.localport_delete	= fcloop_localport_delete,
 	.remoteport_delete	= fcloop_remoteport_delete,
 	.create_queue		= fcloop_create_queue,
diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c
index a227e36cbdc2b..8e0f03ef346b6 100644
--- a/drivers/scsi/lpfc/lpfc_nvme.c
+++ b/drivers/scsi/lpfc/lpfc_nvme.c
@@ -1976,6 +1976,8 @@ lpfc_nvme_fcp_abort(struct nvme_fc_local_port *pnvme_lport,
 
 /* Declare and initialization an instance of the FC NVME template. */
 static struct nvme_fc_port_template lpfc_nvme_template = {
+	.module	= THIS_MODULE,
+
 	/* initiator-based functions */
 	.localport_delete  = lpfc_nvme_localport_delete,
 	.remoteport_delete = lpfc_nvme_remoteport_delete,
diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c
index 941aa53363f56..bfcd02fdf2b89 100644
--- a/drivers/scsi/qla2xxx/qla_nvme.c
+++ b/drivers/scsi/qla2xxx/qla_nvme.c
@@ -610,6 +610,7 @@ static void qla_nvme_remoteport_delete(struct nvme_fc_remote_port *rport)
 }
 
 static struct nvme_fc_port_template qla_nvme_fc_transport = {
+	.module	= THIS_MODULE,
 	.localport_delete = qla_nvme_localport_delete,
 	.remoteport_delete = qla_nvme_remoteport_delete,
 	.create_queue   = qla_nvme_alloc_queue,
diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h
index 10f81629b9cec..6d0d70f3219c5 100644
--- a/include/linux/nvme-fc-driver.h
+++ b/include/linux/nvme-fc-driver.h
@@ -270,6 +270,8 @@ struct nvme_fc_remote_port {
  *
  * Host/Initiator Transport Entrypoints/Parameters:
  *
+ * @module:  The LLDD module using the interface
+ *
  * @localport_delete:  The LLDD initiates deletion of a localport via
  *       nvme_fc_deregister_localport(). However, the teardown is
  *       asynchronous. This routine is called upon the completion of the
@@ -383,6 +385,8 @@ struct nvme_fc_remote_port {
  *       Value is Mandatory. Allowed to be zero.
  */
 struct nvme_fc_port_template {
+	struct module	*module;
+
 	/* initiator-based functions */
 	void	(*localport_delete)(struct nvme_fc_local_port *);
 	void	(*remoteport_delete)(struct nvme_fc_remote_port *);
-- 
2.20.1

[PATCH AUTOSEL 5.4 23/52] scsi: lpfc: Fix memory leak on lpfc_bsg_write_ebuf_set func

[Sasha Levin]

From: Bo Wu <wubo40@huawei.com>

[ Upstream commit 9a1b0b9a6dab452fb0e39fe96880c4faf3878369 ]

When phba->mbox_ext_buf_ctx.seqNum != phba->mbox_ext_buf_ctx.numBuf,
dd_data should be freed before return SLI_CONFIG_HANDLED.

When lpfc_sli_issue_mbox func return fails, pmboxq should be also freed in
job_error tag.

Link: https://lore.kernel.org/r/EDBAAA0BBBA2AC4E9C8B6B81DEEE1D6915E7A966@DGGEML525-MBS.china.huawei.com
Signed-off-by: Bo Wu <wubo40@huawei.com>
Reviewed-by: Zhiqiang Liu <liuzhiqiang26@huawei.com>
Reviewed-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/lpfc/lpfc_bsg.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_bsg.c b/drivers/scsi/lpfc/lpfc_bsg.c
index 39a736b887b16..6c2b03415a2cc 100644
--- a/drivers/scsi/lpfc/lpfc_bsg.c
+++ b/drivers/scsi/lpfc/lpfc_bsg.c
@@ -4489,12 +4489,6 @@ lpfc_bsg_write_ebuf_set(struct lpfc_hba *phba, struct bsg_job *job,
 	phba->mbox_ext_buf_ctx.seqNum++;
 	nemb_tp = phba->mbox_ext_buf_ctx.nembType;
 
-	dd_data = kmalloc(sizeof(struct bsg_job_data), GFP_KERNEL);
-	if (!dd_data) {
-		rc = -ENOMEM;
-		goto job_error;
-	}
-
 	pbuf = (uint8_t *)dmabuf->virt;
 	size = job->request_payload.payload_len;
 	sg_copy_to_buffer(job->request_payload.sg_list,
@@ -4531,6 +4525,13 @@ lpfc_bsg_write_ebuf_set(struct lpfc_hba *phba, struct bsg_job *job,
 				"2968 SLI_CONFIG ext-buffer wr all %d "
 				"ebuffers received\n",
 				phba->mbox_ext_buf_ctx.numBuf);
+
+		dd_data = kmalloc(sizeof(struct bsg_job_data), GFP_KERNEL);
+		if (!dd_data) {
+			rc = -ENOMEM;
+			goto job_error;
+		}
+
 		/* mailbox command structure for base driver */
 		pmboxq = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
 		if (!pmboxq) {
@@ -4579,6 +4580,8 @@ lpfc_bsg_write_ebuf_set(struct lpfc_hba *phba, struct bsg_job *job,
 	return SLI_CONFIG_HANDLED;
 
 job_error:
+	if (pmboxq)
+		mempool_free(pmboxq, phba->mbox_mem_pool);
 	lpfc_bsg_dma_page_free(phba, dmabuf);
 	kfree(dd_data);
 
-- 
2.20.1

[PATCH AUTOSEL 5.4 24/52] scsi: qla2xxx: Use explicit LOGO in target mode

[Sasha Levin]

From: Quinn Tran <qutran@marvell.com>

[ Upstream commit 86196a8fa8a84af1395a28ea0548f2ce6ae9bc22 ]

Target makes implicit LOGO on session teardown. LOGO ELS is not send on the
wire and initiator is not aware that target no longer wants talking to
it. Initiator keeps sending I/O requests, target responds with BA_RJT, they
time out and then initiator sends ABORT TASK (ABTS-LS).

Current behaviour incurs unneeded I/O timeout and can be fixed for some
initiators by making explicit LOGO on session deletion.

Link: https://lore.kernel.org/r/20191125165702.1013-3-r.bolshakov@yadro.com
Reviewed-by: Hannes Reinecke <hare@suse.de>
Tested-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Quinn Tran <qutran@marvell.com>
Signed-off-by: Himanshu Madhani <hmadhani@marvell.com>
Signed-off-by: Roman Bolshakov <r.bolshakov@yadro.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/qla2xxx/qla_def.h     |  1 +
 drivers/scsi/qla2xxx/qla_iocb.c    | 16 ++++++++++++----
 drivers/scsi/qla2xxx/qla_target.c  |  1 +
 drivers/scsi/qla2xxx/tcm_qla2xxx.c |  1 +
 4 files changed, 15 insertions(+), 4 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index d5386edddaf64..1eb3fe281cc3c 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -2401,6 +2401,7 @@ typedef struct fc_port {
 	unsigned int id_changed:1;
 	unsigned int scan_needed:1;
 	unsigned int n2n_flag:1;
+	unsigned int explicit_logout:1;
 
 	struct completion nvme_del_done;
 	uint32_t nvme_prli_service_param;
diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c
index 518eb954cf42c..44dc97cebb06b 100644
--- a/drivers/scsi/qla2xxx/qla_iocb.c
+++ b/drivers/scsi/qla2xxx/qla_iocb.c
@@ -2405,11 +2405,19 @@ qla2x00_login_iocb(srb_t *sp, struct mbx_entry *mbx)
 static void
 qla24xx_logout_iocb(srb_t *sp, struct logio_entry_24xx *logio)
 {
+	u16 control_flags = LCF_COMMAND_LOGO;
 	logio->entry_type = LOGINOUT_PORT_IOCB_TYPE;
-	logio->control_flags =
-	    cpu_to_le16(LCF_COMMAND_LOGO|LCF_IMPL_LOGO);
-	if (!sp->fcport->keep_nport_handle)
-		logio->control_flags |= cpu_to_le16(LCF_FREE_NPORT);
+
+	if (sp->fcport->explicit_logout) {
+		control_flags |= LCF_EXPL_LOGO|LCF_FREE_NPORT;
+	} else {
+		control_flags |= LCF_IMPL_LOGO;
+
+		if (!sp->fcport->keep_nport_handle)
+			control_flags |= LCF_FREE_NPORT;
+	}
+
+	logio->control_flags = cpu_to_le16(control_flags);
 	logio->nport_handle = cpu_to_le16(sp->fcport->loop_id);
 	logio->port_id[0] = sp->fcport->d_id.b.al_pa;
 	logio->port_id[1] = sp->fcport->d_id.b.area;
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index a06e56224a559..29729efac51f2 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -1104,6 +1104,7 @@ void qlt_free_session_done(struct work_struct *work)
 		}
 	}
 
+	sess->explicit_logout = 0;
 	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
 	sess->free_pending = 0;
 
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index 042a24314edcf..589cd22198bb0 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -348,6 +348,7 @@ static void tcm_qla2xxx_close_session(struct se_session *se_sess)
 	target_sess_cmd_list_set_waiting(se_sess);
 	spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags);
 
+	sess->explicit_logout = 1;
 	tcm_qla2xxx_put_sess(sess);
 }
 
-- 
2.20.1

[PATCH AUTOSEL 5.4 25/52] scsi: qla2xxx: Drop superfluous INIT_WORK of del_work

[Sasha Levin]

From: Roman Bolshakov <r.bolshakov@yadro.com>

[ Upstream commit 600954e6f2df695434887dfc6a99a098859990cf ]

del_work is already initialized inside qla2x00_alloc_fcport, there's no
need to overwrite it. Indeed, it might prevent complete traversal of
workqueue list.

Fixes: a01c77d2cbc45 ("scsi: qla2xxx: Move session delete to driver work queue")
Cc: Quinn Tran <qutran@marvell.com>
Link: https://lore.kernel.org/r/20191125165702.1013-5-r.bolshakov@yadro.com
Acked-by: Himanshu Madhani <hmadhani@marvell.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Tested-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Roman Bolshakov <r.bolshakov@yadro.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/qla2xxx/qla_target.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index 29729efac51f2..5bb5249bb822c 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -1266,7 +1266,6 @@ void qlt_schedule_sess_for_deletion(struct fc_port *sess)
 	    "Scheduling sess %p for deletion %8phC\n",
 	    sess, sess->port_name);
 
-	INIT_WORK(&sess->del_work, qla24xx_delete_sess_fn);
 	WARN_ON(!queue_work(sess->vha->hw->wq, &sess->del_work));
 }
 
-- 
2.20.1

[PATCH AUTOSEL 5.4 26/52] scsi: qla2xxx: Don't call qlt_async_event twice

[Sasha Levin]

From: Roman Bolshakov <r.bolshakov@yadro.com>

[ Upstream commit 2c2f4bed9b6299e6430a65a29b5d27b8763fdf25 ]

MBA_PORT_UPDATE generates duplicate log lines in target mode because
qlt_async_event is called twice. Drop the calls within the case as the
function will be called right after the switch statement.

Cc: Quinn Tran <qutran@marvell.com>
Link: https://lore.kernel.org/r/20191125165702.1013-8-r.bolshakov@yadro.com
Acked-by: Himanshu Madhani <hmadhani@marvel.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Tested-by: Hannes Reinecke <hare@suse.de>
Acked-by: Himanshu Madhani <hmadhani@marvell.com>
Signed-off-by: Roman Bolshakov <r.bolshakov@yadro.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/qla2xxx/qla_isr.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index 9204e8467a4ee..b3766b1879e3f 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -1061,8 +1061,6 @@ qla2x00_async_event(scsi_qla_host_t *vha, struct rsp_que *rsp, uint16_t *mb)
 			ql_dbg(ql_dbg_async, vha, 0x5011,
 			    "Asynchronous PORT UPDATE ignored %04x/%04x/%04x.\n",
 			    mb[1], mb[2], mb[3]);
-
-			qlt_async_event(mb[0], vha, mb);
 			break;
 		}
 
@@ -1079,8 +1077,6 @@ qla2x00_async_event(scsi_qla_host_t *vha, struct rsp_que *rsp, uint16_t *mb)
 		set_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags);
 		set_bit(LOCAL_LOOP_UPDATE, &vha->dpc_flags);
 		set_bit(VP_CONFIG_OK, &vha->vp_flags);
-
-		qlt_async_event(mb[0], vha, mb);
 		break;
 
 	case MBA_RSCN_UPDATE:		/* State Change Registration */
-- 
2.20.1

[PATCH AUTOSEL 5.4 27/52] scsi: qla2xxx: Fix PLOGI payload and ELS IOCB dump length

[Sasha Levin]

From: Roman Bolshakov <r.bolshakov@yadro.com>

[ Upstream commit 0334cdea1fba36fad8bdf9516f267ce01de625f7 ]

The size of the buffer is hardcoded as 0x70 or 112 bytes, while the size of
ELS IOCB is 0x40 and the size of PLOGI payload returned by Get Parameters
command is 0x74.

Cc: Quinn Tran <qutran@marvell.com>
Link: https://lore.kernel.org/r/20191125165702.1013-9-r.bolshakov@yadro.com
Acked-by: Himanshu Madhani <hmadhani@marvell.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Tested-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Roman Bolshakov <r.bolshakov@yadro.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/qla2xxx/qla_iocb.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c
index 44dc97cebb06b..bdf1994251b9b 100644
--- a/drivers/scsi/qla2xxx/qla_iocb.c
+++ b/drivers/scsi/qla2xxx/qla_iocb.c
@@ -2684,7 +2684,8 @@ qla24xx_els_logo_iocb(srb_t *sp, struct els_entry_24xx *els_iocb)
 		ql_dbg(ql_dbg_io + ql_dbg_buffer, vha, 0x3073,
 		    "PLOGI ELS IOCB:\n");
 		ql_dump_buffer(ql_log_info, vha, 0x0109,
-		    (uint8_t *)els_iocb, 0x70);
+		    (uint8_t *)els_iocb,
+		    sizeof(*els_iocb));
 	} else {
 		els_iocb->control_flags = 1 << 13;
 		els_iocb->tx_byte_count =
@@ -2850,7 +2851,8 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode,
 
 	ql_dbg(ql_dbg_disc + ql_dbg_buffer, vha, 0x3073, "PLOGI buffer:\n");
 	ql_dump_buffer(ql_dbg_disc + ql_dbg_buffer, vha, 0x0109,
-	    (uint8_t *)elsio->u.els_plogi.els_plogi_pyld, 0x70);
+	    (uint8_t *)elsio->u.els_plogi.els_plogi_pyld,
+	    sizeof(*elsio->u.els_plogi.els_plogi_pyld));
 
 	rval = qla2x00_start_sp(sp);
 	if (rval != QLA_SUCCESS) {
-- 
2.20.1

[PATCH AUTOSEL 5.4 28/52] scsi: qla2xxx: Configure local loop for N2N target

[Sasha Levin]

From: Roman Bolshakov <r.bolshakov@yadro.com>

[ Upstream commit fd1de5830a5abaf444cc4312871e02c41e24fdc1 ]

qla2x00_configure_local_loop initializes PLOGI payload for PLOGI ELS using
Get Parameters mailbox command.

In the case when the driver is running in target mode, the topology is N2N
and the target port has higher WWPN, LOCAL_LOOP_UPDATE bit is cleared too
early and PLOGI payload is not initialized by the Get Parameters
command. That causes a failure of ELS IOCB carrying the PLOGI with 0x15 aka
Data Underrun error.

LOCAL_LOOP_UPDATE has to be set to initialize PLOGI payload.

Fixes: 48acad099074 ("scsi: qla2xxx: Fix N2N link re-connect")
Link: https://lore.kernel.org/r/20191125165702.1013-10-r.bolshakov@yadro.com
Acked-by: Quinn Tran <qutran@marvell.com>
Acked-by: Himanshu Madhani <hmadhani@marvell.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Tested-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Roman Bolshakov <r.bolshakov@yadro.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/qla2xxx/qla_init.c | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index d400b51929a6e..7364f3b62b9d9 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -4925,14 +4925,8 @@ qla2x00_configure_loop(scsi_qla_host_t *vha)
 		set_bit(RSCN_UPDATE, &flags);
 		clear_bit(LOCAL_LOOP_UPDATE, &flags);
 
-	} else if (ha->current_topology == ISP_CFG_N) {
-		clear_bit(RSCN_UPDATE, &flags);
-		if (qla_tgt_mode_enabled(vha)) {
-			/* allow the other side to start the login */
-			clear_bit(LOCAL_LOOP_UPDATE, &flags);
-			set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
-		}
-	} else if (ha->current_topology == ISP_CFG_NL) {
+	} else if (ha->current_topology == ISP_CFG_NL ||
+		   ha->current_topology == ISP_CFG_N) {
 		clear_bit(RSCN_UPDATE, &flags);
 		set_bit(LOCAL_LOOP_UPDATE, &flags);
 	} else if (!vha->flags.online ||
-- 
2.20.1

[PATCH AUTOSEL 5.4 29/52] scsi: qla2xxx: Send Notify ACK after N2N PLOGI

[Sasha Levin]

From: Roman Bolshakov <r.bolshakov@yadro.com>

[ Upstream commit 5e6b01d84b9d20bcd77fc7c4733a2a4149bf220a ]

qlt_handle_login schedules session for deletion even if a login is in
progress. That causes login bouncing, i.e. a few logins are made before it
settles down.

Complete the first login by sending Notify Acknowledge IOCB via
qlt_plogi_ack_unref if the session is pending login completion.

Fixes: 9cd883f07a54 ("scsi: qla2xxx: Fix session cleanup for N2N")
Cc: Krishna Kant <krishna.kant@purestorage.com>
Cc: Alexei Potashnik <alexei@purestorage.com>
Link: https://lore.kernel.org/r/20191125165702.1013-11-r.bolshakov@yadro.com
Acked-by: Quinn Tran <qutran@marvell.com>
Acked-by: Himanshu Madhani <hmadhani@marvell.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Tested-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Roman Bolshakov <r.bolshakov@yadro.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/qla2xxx/qla_target.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index 5bb5249bb822c..ee0d07836b832 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -4804,6 +4804,7 @@ static int qlt_handle_login(struct scsi_qla_host *vha,
 
 	switch (sess->disc_state) {
 	case DSC_DELETED:
+	case DSC_LOGIN_PEND:
 		qlt_plogi_ack_unref(vha, pla);
 		break;
 
-- 
2.20.1

[PATCH AUTOSEL 5.4 30/52] scsi: qla2xxx: Don't defer relogin unconditonally

[Sasha Levin]

From: Roman Bolshakov <r.bolshakov@yadro.com>

[ Upstream commit dabc5ec915f3a2c657ecfb529cd3d4ec303a4412 ]

qla2x00_configure_local_loop sets RELOGIN_NEEDED bit and calls
qla24xx_fcport_handle_login to perform the login. This bit triggers a wake
up of DPC later after a successful login.

The deferred call is not needed if login succeeds, and it's set in
qla24xx_fcport_handle_login in case of errors, hence it should be safe to
drop.

Link: https://lore.kernel.org/r/20191125165702.1013-12-r.bolshakov@yadro.com
Acked-by: Himanshu Madhani <hmadhani@marvell.com>
Acked-by: Quinn Tran <qutran@marvell.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Tested-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Roman Bolshakov <r.bolshakov@yadro.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/qla2xxx/qla_init.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 7364f3b62b9d9..1c3a5fcbd3153 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -5043,7 +5043,6 @@ qla2x00_configure_local_loop(scsi_qla_host_t *vha)
 				memcpy(&ha->plogi_els_payld.data,
 				    (void *)ha->init_cb,
 				    sizeof(ha->plogi_els_payld.data));
-				set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
 			} else {
 				ql_dbg(ql_dbg_init, vha, 0x00d1,
 				    "PLOGI ELS param read fail.\n");
-- 
2.20.1

[PATCH AUTOSEL 5.4 31/52] scsi: qla2xxx: Ignore PORT UPDATE after N2N PLOGI

[Sasha Levin]

From: Roman Bolshakov <r.bolshakov@yadro.com>

[ Upstream commit af22f0c7b052c5c203207f1e5ebd6aa65f87c538 ]

PORT UPDATE asynchronous event is generated on the host that issues PLOGI
ELS (in the case of higher WWPN). In that case, the event shouldn't be
handled as it sets unwanted DPC flags (i.e. LOOP_RESYNC_NEEDED) that
trigger link flap.

Ignore the event if the host has higher WWPN, but handle otherwise.

Cc: Quinn Tran <qutran@marvell.com>
Link: https://lore.kernel.org/r/20191125165702.1013-13-r.bolshakov@yadro.com
Acked-by: Himanshu Madhani <hmadhani@marvell.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Tested-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Roman Bolshakov <r.bolshakov@yadro.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/qla2xxx/qla_mbx.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c
index 4d90cf101f5fc..eac76e934cbe2 100644
--- a/drivers/scsi/qla2xxx/qla_mbx.c
+++ b/drivers/scsi/qla2xxx/qla_mbx.c
@@ -3920,6 +3920,7 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha,
 					vha->d_id.b24 = 0;
 					vha->d_id.b.al_pa = 1;
 					ha->flags.n2n_bigger = 1;
+					ha->flags.n2n_ae = 0;
 
 					id.b.al_pa = 2;
 					ql_dbg(ql_dbg_async, vha, 0x5075,
@@ -3930,6 +3931,7 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha,
 					    "Format 1: Remote login - Waiting for WWPN %8phC.\n",
 					    rptid_entry->u.f1.port_name);
 					ha->flags.n2n_bigger = 0;
+					ha->flags.n2n_ae = 1;
 				}
 				qla24xx_post_newsess_work(vha, &id,
 				    rptid_entry->u.f1.port_name,
@@ -3941,7 +3943,6 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha,
 			/* if our portname is higher then initiate N2N login */
 
 			set_bit(N2N_LOGIN_NEEDED, &vha->dpc_flags);
-			ha->flags.n2n_ae = 1;
 			return;
 			break;
 		case TOPO_FL:
-- 
2.20.1

[PATCH AUTOSEL 5.4 32/52] scsi: iscsi: qla4xxx: fix double free in probe

[Sasha Levin]

From: Dan Carpenter <dan.carpenter@oracle.com>

[ Upstream commit fee92f25777789d73e1936b91472e9c4644457c8 ]

On this error path we call qla4xxx_mem_free() and then the caller also
calls qla4xxx_free_adapter() which calls qla4xxx_mem_free().  It leads to a
couple double frees:

drivers/scsi/qla4xxx/ql4_os.c:8856 qla4xxx_probe_adapter() warn: 'ha->chap_dma_pool' double freed
drivers/scsi/qla4xxx/ql4_os.c:8856 qla4xxx_probe_adapter() warn: 'ha->fw_ddb_dma_pool' double freed

Fixes: afaf5a2d341d ("[SCSI] Initial Commit of qla4xxx")
Link: https://lore.kernel.org/r/20191203094421.hw7ex7qr3j2rbsmx@kili.mountain
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/qla4xxx/ql4_os.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c
index 8c674eca09f13..2323432a0edbc 100644
--- a/drivers/scsi/qla4xxx/ql4_os.c
+++ b/drivers/scsi/qla4xxx/ql4_os.c
@@ -4275,7 +4275,6 @@ static int qla4xxx_mem_alloc(struct scsi_qla_host *ha)
 	return QLA_SUCCESS;
 
 mem_alloc_error_exit:
-	qla4xxx_mem_free(ha);
 	return QLA_ERROR;
 }
 
-- 
2.20.1

[PATCH AUTOSEL 5.4 33/52] scsi: libsas: stop discovering if oob mode is disconnected

[Sasha Levin]

From: Jason Yan <yanaijie@huawei.com>

[ Upstream commit f70267f379b5e5e11bdc5d72a56bf17e5feed01f ]

The discovering of sas port is driven by workqueue in libsas. When libsas
is processing port events or phy events in workqueue, new events may rise
up and change the state of some structures such as asd_sas_phy.  This may
cause some problems such as follows:

==>thread 1                       ==>thread 2

                                  ==>phy up
                                  ==>phy_up_v3_hw()
                                    ==>oob_mode = SATA_OOB_MODE;
                                  ==>phy down quickly
                                  ==>hisi_sas_phy_down()
                                    ==>sas_ha->notify_phy_event()
                                    ==>sas_phy_disconnected()
                                      ==>oob_mode = OOB_NOT_CONNECTED
==>workqueue wakeup
==>sas_form_port()
  ==>sas_discover_domain()
    ==>sas_get_port_device()
      ==>oob_mode is OOB_NOT_CONNECTED and device
         is wrongly taken as expander

This at last lead to the panic when libsas trying to issue a command to
discover the device.

[183047.614035] Unable to handle kernel NULL pointer dereference at
virtual address 0000000000000058
[183047.622896] Mem abort info:
[183047.625762]   ESR = 0x96000004
[183047.628893]   Exception class = DABT (current EL), IL = 32 bits
[183047.634888]   SET = 0, FnV = 0
[183047.638015]   EA = 0, S1PTW = 0
[183047.641232] Data abort info:
[183047.644189]   ISV = 0, ISS = 0x00000004
[183047.648100]   CM = 0, WnR = 0
[183047.651145] user pgtable: 4k pages, 48-bit VAs, pgdp =
00000000b7df67be
[183047.657834] [0000000000000058] pgd=0000000000000000
[183047.662789] Internal error: Oops: 96000004 [#1] SMP
[183047.667740] Process kworker/u16:2 (pid: 31291, stack limit =
0x00000000417c4974)
[183047.675208] CPU: 0 PID: 3291 Comm: kworker/u16:2 Tainted: G
W  OE 4.19.36-vhulk1907.1.0.h410.eulerosv2r8.aarch64 #1
[183047.687015] Hardware name: N/A N/A/Kunpeng Desktop Board D920S10,
BIOS 0.15 10/22/2019
[183047.695007] Workqueue: 0000:74:02.0_disco_q sas_discover_domain
[183047.700999] pstate: 20c00009 (nzCv daif +PAN +UAO)
[183047.705864] pc : prep_ata_v3_hw+0xf8/0x230 [hisi_sas_v3_hw]
[183047.711510] lr : prep_ata_v3_hw+0xb0/0x230 [hisi_sas_v3_hw]
[183047.717153] sp : ffff00000f28ba60
[183047.720541] x29: ffff00000f28ba60 x28: ffff8026852d7228
[183047.725925] x27: ffff8027dba3e0a8 x26: ffff8027c05fc200
[183047.731310] x25: 0000000000000000 x24: ffff8026bafa8dc0
[183047.736695] x23: ffff8027c05fc218 x22: ffff8026852d7228
[183047.742079] x21: ffff80007c2f2940 x20: ffff8027c05fc200
[183047.747464] x19: 0000000000f80800 x18: 0000000000000010
[183047.752848] x17: 0000000000000000 x16: 0000000000000000
[183047.758232] x15: ffff000089a5a4ff x14: 0000000000000005
[183047.763617] x13: ffff000009a5a50e x12: ffff8026bafa1e20
[183047.769001] x11: ffff0000087453b8 x10: ffff00000f28b870
[183047.774385] x9 : 0000000000000000 x8 : ffff80007e58f9b0
[183047.779770] x7 : 0000000000000000 x6 : 000000000000003f
[183047.785154] x5 : 0000000000000040 x4 : ffffffffffffffe0
[183047.790538] x3 : 00000000000000f8 x2 : 0000000002000007
[183047.795922] x1 : 0000000000000008 x0 : 0000000000000000
[183047.801307] Call trace:
[183047.803827]  prep_ata_v3_hw+0xf8/0x230 [hisi_sas_v3_hw]
[183047.809127]  hisi_sas_task_prep+0x750/0x888 [hisi_sas_main]
[183047.814773]  hisi_sas_task_exec.isra.7+0x88/0x1f0 [hisi_sas_main]
[183047.820939]  hisi_sas_queue_command+0x28/0x38 [hisi_sas_main]
[183047.826757]  smp_execute_task_sg+0xec/0x218
[183047.831013]  smp_execute_task+0x74/0xa0
[183047.834921]  sas_discover_expander.part.7+0x9c/0x5f8
[183047.839959]  sas_discover_root_expander+0x90/0x160
[183047.844822]  sas_discover_domain+0x1b8/0x1e8
[183047.849164]  process_one_work+0x1b4/0x3f8
[183047.853246]  worker_thread+0x54/0x470
[183047.856981]  kthread+0x134/0x138
[183047.860283]  ret_from_fork+0x10/0x18
[183047.863931] Code: f9407a80 528000e2 39409281 72a04002 (b9405800)
[183047.870097] kernel fault(0x1) notification starting on CPU 0
[183047.875828] kernel fault(0x1) notification finished on CPU 0
[183047.881559] Modules linked in: unibsp(OE) hns3(OE) hclge(OE)
hnae3(OE) mem_drv(OE) hisi_sas_v3_hw(OE) hisi_sas_main(OE)
[183047.892418] ---[ end trace 4cc26083fc11b783  ]---
[183047.897107] Kernel panic - not syncing: Fatal exception
[183047.902403] kernel fault(0x5) notification starting on CPU 0
[183047.908134] kernel fault(0x5) notification finished on CPU 0
[183047.913865] SMP: stopping secondary CPUs
[183047.917861] Kernel Offset: disabled
[183047.921422] CPU features: 0x2,a2a00a38
[183047.925243] Memory Limit: none
[183047.928372] kernel reboot(0x2) notification starting on CPU 0
[183047.934190] kernel reboot(0x2) notification finished on CPU 0
[183047.940008] ---[ end Kernel panic - not syncing: Fatal exception
]---

Fixes: 2908d778ab3e ("[SCSI] aic94xx: new driver")
Link: https://lore.kernel.org/r/20191206011118.46909-1-yanaijie@huawei.com
Reported-by: Gao Chuan <gaochuan4@huawei.com>
Reviewed-by: John Garry <john.garry@huawei.com>
Signed-off-by: Jason Yan <yanaijie@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/libsas/sas_discover.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/libsas/sas_discover.c b/drivers/scsi/libsas/sas_discover.c
index f47b4b281b14a..d7302c2052f91 100644
--- a/drivers/scsi/libsas/sas_discover.c
+++ b/drivers/scsi/libsas/sas_discover.c
@@ -81,12 +81,21 @@ static int sas_get_port_device(struct asd_sas_port *port)
 		else
 			dev->dev_type = SAS_SATA_DEV;
 		dev->tproto = SAS_PROTOCOL_SATA;
-	} else {
+	} else if (port->oob_mode == SAS_OOB_MODE) {
 		struct sas_identify_frame *id =
 			(struct sas_identify_frame *) dev->frame_rcvd;
 		dev->dev_type = id->dev_type;
 		dev->iproto = id->initiator_bits;
 		dev->tproto = id->target_bits;
+	} else {
+		/* If the oob mode is OOB_NOT_CONNECTED, the port is
+		 * disconnected due to race with PHY down. We cannot
+		 * continue to discover this port
+		 */
+		sas_put_device(dev);
+		pr_warn("Port %016llx is disconnected when discovering\n",
+			SAS_ADDR(port->attached_sas_addr));
+		return -ENODEV;
 	}
 
 	sas_init_dev(dev);
-- 
2.20.1

[PATCH AUTOSEL 5.4 34/52] scsi: iscsi: Avoid potential deadlock in iscsi_if_rx func

[Sasha Levin]

From: Bo Wu <wubo40@huawei.com>

[ Upstream commit bba340c79bfe3644829db5c852fdfa9e33837d6d ]

In iscsi_if_rx func, after receiving one request through
iscsi_if_recv_msg func, iscsi_if_send_reply will be called to try to
reply to the request in a do-while loop.  If the iscsi_if_send_reply
function keeps returning -EAGAIN, a deadlock will occur.

For example, a client only send msg without calling recvmsg func, then
it will result in the watchdog soft lockup.  The details are given as
follows:

	sock_fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_ISCSI);
	retval = bind(sock_fd, (struct sock addr*) & src_addr, sizeof(src_addr);
	while (1) {
		state_msg = sendmsg(sock_fd, &msg, 0);
		//Note: recvmsg(sock_fd, &msg, 0) is not processed here.
	}
	close(sock_fd);

watchdog: BUG: soft lockup - CPU#7 stuck for 22s! [netlink_test:253305] Sample time: 4000897528 ns(HZ: 250) Sample stat:
curr: user: 675503481560, nice: 321724050, sys: 448689506750, idle: 4654054240530, iowait: 40885550700, irq: 14161174020, softirq: 8104324140, st: 0
deta: user: 0, nice: 0, sys: 3998210100, idle: 0, iowait: 0, irq: 1547170, softirq: 242870, st: 0 Sample softirq:
         TIMER:        992
         SCHED:          8
Sample irqstat:
         irq    2: delta       1003, curr:    3103802, arch_timer
CPU: 7 PID: 253305 Comm: netlink_test Kdump: loaded Tainted: G           OE
Hardware name: QEMU KVM Virtual Machine, BIOS 0.0.0 02/06/2015
pstate: 40400005 (nZcv daif +PAN -UAO)
pc : __alloc_skb+0x104/0x1b0
lr : __alloc_skb+0x9c/0x1b0
sp : ffff000033603a30
x29: ffff000033603a30 x28: 00000000000002dd
x27: ffff800b34ced810 x26: ffff800ba7569f00
x25: 00000000ffffffff x24: 0000000000000000
x23: ffff800f7c43f600 x22: 0000000000480020
x21: ffff0000091d9000 x20: ffff800b34eff200
x19: ffff800ba7569f00 x18: 0000000000000000
x17: 0000000000000000 x16: 0000000000000000
x15: 0000000000000000 x14: 0001000101000100
x13: 0000000101010000 x12: 0101000001010100
x11: 0001010101010001 x10: 00000000000002dd
x9 : ffff000033603d58 x8 : ffff800b34eff400
x7 : ffff800ba7569200 x6 : ffff800b34eff400
x5 : 0000000000000000 x4 : 00000000ffffffff
x3 : 0000000000000000 x2 : 0000000000000001
x1 : ffff800b34eff2c0 x0 : 0000000000000300 Call trace:
__alloc_skb+0x104/0x1b0
iscsi_if_rx+0x144/0x12bc [scsi_transport_iscsi]
netlink_unicast+0x1e0/0x258
netlink_sendmsg+0x310/0x378
sock_sendmsg+0x4c/0x70
sock_write_iter+0x90/0xf0
__vfs_write+0x11c/0x190
vfs_write+0xac/0x1c0
ksys_write+0x6c/0xd8
__arm64_sys_write+0x24/0x30
el0_svc_common+0x78/0x130
el0_svc_handler+0x38/0x78
el0_svc+0x8/0xc

Link: https://lore.kernel.org/r/EDBAAA0BBBA2AC4E9C8B6B81DEEE1D6915E3D4D2@dggeml505-mbx.china.huawei.com
Signed-off-by: Bo Wu <wubo40@huawei.com>
Reviewed-by: Zhiqiang Liu <liuzhiqiang26@huawei.com>
Reviewed-by: Lee Duncan <lduncan@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/scsi_transport_iscsi.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
index 417b868d8735e..ed8d9709b9b96 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -24,6 +24,8 @@
 
 #define ISCSI_TRANSPORT_VERSION "2.0-870"
 
+#define ISCSI_SEND_MAX_ALLOWED  10
+
 #define CREATE_TRACE_POINTS
 #include <trace/events/iscsi.h>
 
@@ -3682,6 +3684,7 @@ iscsi_if_rx(struct sk_buff *skb)
 		struct nlmsghdr	*nlh;
 		struct iscsi_uevent *ev;
 		uint32_t group;
+		int retries = ISCSI_SEND_MAX_ALLOWED;
 
 		nlh = nlmsg_hdr(skb);
 		if (nlh->nlmsg_len < sizeof(*nlh) + sizeof(*ev) ||
@@ -3712,6 +3715,10 @@ iscsi_if_rx(struct sk_buff *skb)
 				break;
 			err = iscsi_if_send_reply(portid, nlh->nlmsg_type,
 						  ev, sizeof(*ev));
+			if (err == -EAGAIN && --retries < 0) {
+				printk(KERN_WARNING "Send reply failed, error %d\n", err);
+				break;
+			}
 		} while (err < 0 && err != -ECONNREFUSED && err != -ESRCH);
 		skb_pull(skb, rlen);
 	}
-- 
2.20.1