[PATCH AUTOSEL 4.19 034/237] scsi: hisi_sas: Feed back linkrate(max/min) when re-attached

[PATCH AUTOSEL 4.19 034/237] scsi: hisi_sas: Feed back linkrate(max/min) when re-attached

[Sasha Levin]

From: Luo Jiaxing <luojiaxing@huawei.com>

[ Upstream commit 5a54691f874ab29ec82f08bc6936866a3ccdaa91 ]

At directly attached situation, if the user modifies the sysfs interface
of maximum_linkrate and minimum_linkrate to renegotiate the linkrate
between SAS controller and target, the value of both files mentioned
above should have change to user setting after renegotiate is over, but
it remains unchanged.

To fix this bug, maximum_linkrate and minimum_linkrate will be directly
fed back to relevant sas_phy structure.

Signed-off-by: Luo Jiaxing <luojiaxing@huawei.com>
Signed-off-by: John Garry <john.garry@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/hisi_sas/hisi_sas_main.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index fd9d82c9033de..e9747379384b2 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -906,6 +906,9 @@ static void hisi_sas_phy_set_linkrate(struct hisi_hba *hisi_hba, int phy_no,
 	_r.maximum_linkrate = max;
 	_r.minimum_linkrate = min;
 
+	sas_phy->phy->maximum_linkrate = max;
+	sas_phy->phy->minimum_linkrate = min;
+
 	hisi_hba->hw->phy_disable(hisi_hba, phy_no);
 	msleep(100);
 	hisi_hba->hw->phy_set_linkrate(hisi_hba, phy_no, &_r);
-- 
2.20.1

[PATCH AUTOSEL 4.19 035/237] scsi: hisi_sas: Fix the race between IO completion and timeout for SMP/internal IO

[Sasha Levin]

From: Xiang Chen <chenxiang66@hisilicon.com>

[ Upstream commit 584f53fe5f529d877968c711a095923c1ed12307 ]

If SMP/internal IO times out, we will possibly free the task immediately.

However if the IO actually completes at the same time, the IO completion
may refer to task which has been freed.

So to solve the issue, flush the tasklet to finish IO completion before
free'ing slot/task.

Signed-off-by: Xiang Chen <chenxiang66@hisilicon.com>
Signed-off-by: John Garry <john.garry@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/hisi_sas/hisi_sas_main.c | 55 ++++++++++++++++++++++-----
 1 file changed, 46 insertions(+), 9 deletions(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index e9747379384b2..d4a2625a44232 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -955,8 +955,7 @@ static int hisi_sas_control_phy(struct asd_sas_phy *sas_phy, enum phy_func func,
 
 static void hisi_sas_task_done(struct sas_task *task)
 {
-	if (!del_timer(&task->slow_task->timer))
-		return;
+	del_timer(&task->slow_task->timer);
 	complete(&task->slow_task->completion);
 }
 
@@ -965,13 +964,17 @@ static void hisi_sas_tmf_timedout(struct timer_list *t)
 	struct sas_task_slow *slow = from_timer(slow, t, timer);
 	struct sas_task *task = slow->task;
 	unsigned long flags;
+	bool is_completed = true;
 
 	spin_lock_irqsave(&task->task_state_lock, flags);
-	if (!(task->task_state_flags & SAS_TASK_STATE_DONE))
+	if (!(task->task_state_flags & SAS_TASK_STATE_DONE)) {
 		task->task_state_flags |= SAS_TASK_STATE_ABORTED;
+		is_completed = false;
+	}
 	spin_unlock_irqrestore(&task->task_state_lock, flags);
 
-	complete(&task->slow_task->completion);
+	if (!is_completed)
+		complete(&task->slow_task->completion);
 }
 
 #define TASK_TIMEOUT 20
@@ -1022,10 +1025,18 @@ static int hisi_sas_exec_internal_tmf_task(struct domain_device *device,
 		if ((task->task_state_flags & SAS_TASK_STATE_ABORTED)) {
 			if (!(task->task_state_flags & SAS_TASK_STATE_DONE)) {
 				struct hisi_sas_slot *slot = task->lldd_task;
+				struct hisi_sas_cq *cq =
+					&hisi_hba->cq[slot->dlvry_queue];
 
 				dev_err(dev, "abort tmf: TMF task timeout and not done\n");
-				if (slot)
+				if (slot) {
+					/*
+					 * flush tasklet to avoid free'ing task
+					 * before using task in IO completion
+					 */
+					tasklet_kill(&cq->tasklet);
 					slot->task = NULL;
+				}
 
 				goto ex_err;
 			} else
@@ -1401,6 +1412,17 @@ static int hisi_sas_abort_task(struct sas_task *task)
 
 	spin_lock_irqsave(&task->task_state_lock, flags);
 	if (task->task_state_flags & SAS_TASK_STATE_DONE) {
+		struct hisi_sas_slot *slot = task->lldd_task;
+		struct hisi_sas_cq *cq;
+
+		if (slot) {
+			/*
+			 * flush tasklet to avoid free'ing task
+			 * before using task in IO completion
+			 */
+			cq = &hisi_hba->cq[slot->dlvry_queue];
+			tasklet_kill(&cq->tasklet);
+		}
 		spin_unlock_irqrestore(&task->task_state_lock, flags);
 		rc = TMF_RESP_FUNC_COMPLETE;
 		goto out;
@@ -1456,12 +1478,19 @@ static int hisi_sas_abort_task(struct sas_task *task)
 		/* SMP */
 		struct hisi_sas_slot *slot = task->lldd_task;
 		u32 tag = slot->idx;
+		struct hisi_sas_cq *cq = &hisi_hba->cq[slot->dlvry_queue];
 
 		rc = hisi_sas_internal_task_abort(hisi_hba, device,
 			     HISI_SAS_INT_ABT_CMD, tag);
 		if (((rc < 0) || (rc == TMF_RESP_FUNC_FAILED)) &&
-					task->lldd_task)
-			hisi_sas_do_release_task(hisi_hba, task, slot);
+					task->lldd_task) {
+			/*
+			 * flush tasklet to avoid free'ing task
+			 * before using task in IO completion
+			 */
+			tasklet_kill(&cq->tasklet);
+			slot->task = NULL;
+		}
 	}
 
 out:
@@ -1827,9 +1856,17 @@ hisi_sas_internal_task_abort(struct hisi_hba *hisi_hba,
 	if ((task->task_state_flags & SAS_TASK_STATE_ABORTED)) {
 		if (!(task->task_state_flags & SAS_TASK_STATE_DONE)) {
 			struct hisi_sas_slot *slot = task->lldd_task;
-
-			if (slot)
+			struct hisi_sas_cq *cq =
+				&hisi_hba->cq[slot->dlvry_queue];
+
+			if (slot) {
+				/*
+				 * flush tasklet to avoid free'ing task
+				 * before using task in IO completion
+				 */
+				tasklet_kill(&cq->tasklet);
 				slot->task = NULL;
+			}
 			dev_err(dev, "internal task abort: timeout and not done.\n");
 			res = -EIO;
 			goto exit;
-- 
2.20.1

[PATCH AUTOSEL 4.19 036/237] scsi: hisi_sas: Free slot later in slot_complete_vx_hw()

[Sasha Levin]

From: Xiang Chen <chenxiang66@hisilicon.com>

[ Upstream commit 3e178f3ecfcf91a258e832b0f0843a4cfd9059ac ]

If an SSP/SMP IO times out, it may be actually in reality be
simultaneously processing completion of the slot in
slot_complete_vx_hw().

Then if the slot is freed in slot_complete_vx_hw() (this IPTT is freed
and it may be re-used by other slot), and we may abort the wrong slot in
hisi_sas_abort_task().

So to solve the issue, free the slot after the check of
SAS_TASK_STATE_ABORTED in slot_complete_vx_hw().

Signed-off-by: Xiang Chen <chenxiang66@hisilicon.com>
Signed-off-by: John Garry <john.garry@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/hisi_sas/hisi_sas_v2_hw.c | 2 +-
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
index 1c4ea58da1ae1..c4774d63d5d04 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
@@ -2481,7 +2481,6 @@ slot_complete_v2_hw(struct hisi_hba *hisi_hba, struct hisi_sas_slot *slot)
 	}
 
 out:
-	hisi_sas_slot_task_free(hisi_hba, task, slot);
 	sts = ts->stat;
 	spin_lock_irqsave(&task->task_state_lock, flags);
 	if (task->task_state_flags & SAS_TASK_STATE_ABORTED) {
@@ -2491,6 +2490,7 @@ slot_complete_v2_hw(struct hisi_hba *hisi_hba, struct hisi_sas_slot *slot)
 	}
 	task->task_state_flags |= SAS_TASK_STATE_DONE;
 	spin_unlock_irqrestore(&task->task_state_lock, flags);
+	hisi_sas_slot_task_free(hisi_hba, task, slot);
 
 	if (!is_internal && (task->task_proto != SAS_PROTOCOL_SMP)) {
 		spin_lock_irqsave(&device->done_lock, flags);
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index 3922b17e2ea39..fb2a5969181b5 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -1749,7 +1749,6 @@ slot_complete_v3_hw(struct hisi_hba *hisi_hba, struct hisi_sas_slot *slot)
 	}
 
 out:
-	hisi_sas_slot_task_free(hisi_hba, task, slot);
 	sts = ts->stat;
 	spin_lock_irqsave(&task->task_state_lock, flags);
 	if (task->task_state_flags & SAS_TASK_STATE_ABORTED) {
@@ -1759,6 +1758,7 @@ slot_complete_v3_hw(struct hisi_hba *hisi_hba, struct hisi_sas_slot *slot)
 	}
 	task->task_state_flags |= SAS_TASK_STATE_DONE;
 	spin_unlock_irqrestore(&task->task_state_lock, flags);
+	hisi_sas_slot_task_free(hisi_hba, task, slot);
 
 	if (!is_internal && (task->task_proto != SAS_PROTOCOL_SMP)) {
 		spin_lock_irqsave(&device->done_lock, flags);
-- 
2.20.1

[PATCH AUTOSEL 4.19 045/237] scsi: ips: fix missing break in switch

[Sasha Levin]

From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>

[ Upstream commit 5d25ff7a544889bc4b749fda31778d6a18dddbcb ]

Add missing break statement in order to prevent the code from falling
through to case TEST_UNIT_READY.

Addresses-Coverity-ID: 1357338 ("Missing break in switch")
Suggested-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/ips.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/scsi/ips.c b/drivers/scsi/ips.c
index bd6ac6b5980a1..fe587ef1741d4 100644
--- a/drivers/scsi/ips.c
+++ b/drivers/scsi/ips.c
@@ -3485,6 +3485,7 @@ ips_send_cmd(ips_ha_t * ha, ips_scb_t * scb)
 
 		case START_STOP:
 			scb->scsi_cmd->result = DID_OK << 16;
+			break;
 
 		case TEST_UNIT_READY:
 		case INQUIRY:
-- 
2.20.1

[PATCH AUTOSEL 4.19 051/237] scsi: isci: Use proper enumerated type in atapi_d2h_reg_frame_handler

[Sasha Levin]

From: Nathan Chancellor <natechancellor@gmail.com>

[ Upstream commit e9e9a103528c7e199ead6e5374c9c52cf16b5802 ]

Clang warns when one enumerated type is implicitly converted to another.

drivers/scsi/isci/request.c:1629:13: warning: implicit conversion from
enumeration type 'enum sci_io_status' to different enumeration type
'enum sci_status' [-Wenum-conversion]
                        status = SCI_IO_FAILURE_RESPONSE_VALID;
                               ~ ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
drivers/scsi/isci/request.c:1631:12: warning: implicit conversion from
enumeration type 'enum sci_io_status' to different enumeration type
'enum sci_status' [-Wenum-conversion]
                status = SCI_IO_FAILURE_RESPONSE_VALID;
                       ~ ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~

status is of type sci_status but SCI_IO_FAILURE_RESPONSE_VALID is of
type sci_io_status. Use SCI_FAILURE_IO_RESPONSE_VALID, which is from
sci_status and has SCI_IO_FAILURE_RESPONSE_VALID's exact value since
that is what SCI_IO_FAILURE_RESPONSE_VALID is mapped to in the isci.h
file.

Link: https://github.com/ClangBuiltLinux/linux/issues/153
Signed-off-by: Nathan Chancellor <natechancellor@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/isci/request.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/isci/request.c b/drivers/scsi/isci/request.c
index ed197bc8e801a..2f151708b59ae 100644
--- a/drivers/scsi/isci/request.c
+++ b/drivers/scsi/isci/request.c
@@ -1626,9 +1626,9 @@ static enum sci_status atapi_d2h_reg_frame_handler(struct isci_request *ireq,
 
 	if (status == SCI_SUCCESS) {
 		if (ireq->stp.rsp.status & ATA_ERR)
-			status = SCI_IO_FAILURE_RESPONSE_VALID;
+			status = SCI_FAILURE_IO_RESPONSE_VALID;
 	} else {
-		status = SCI_IO_FAILURE_RESPONSE_VALID;
+		status = SCI_FAILURE_IO_RESPONSE_VALID;
 	}
 
 	if (status != SCI_SUCCESS) {
-- 
2.20.1

[PATCH AUTOSEL 4.19 052/237] scsi: isci: Change sci_controller_start_task's return type to sci_status

[Sasha Levin]

From: Nathan Chancellor <natechancellor@gmail.com>

[ Upstream commit 362b5da3dfceada6e74ecdd7af3991bbe42c0c0f ]

Clang warns when an enumerated type is implicitly converted to another.

drivers/scsi/isci/request.c:3476:13: warning: implicit conversion from
enumeration type 'enum sci_task_status' to different enumeration type
'enum sci_status' [-Wenum-conversion]
                        status = sci_controller_start_task(ihost,
                               ~ ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
drivers/scsi/isci/host.c:2744:10: warning: implicit conversion from
enumeration type 'enum sci_status' to different enumeration type 'enum
sci_task_status' [-Wenum-conversion]
                return SCI_SUCCESS;
                ~~~~~~ ^~~~~~~~~~~
drivers/scsi/isci/host.c:2753:9: warning: implicit conversion from
enumeration type 'enum sci_status' to different enumeration type 'enum
sci_task_status' [-Wenum-conversion]
        return status;
        ~~~~~~ ^~~~~~

Avoid all of these implicit conversion by just making
sci_controller_start_task use sci_status. This silences
Clang and has no functional change since sci_task_status
has all of its values mapped to something in sci_status.

Link: https://github.com/ClangBuiltLinux/linux/issues/153
Signed-off-by: Nathan Chancellor <natechancellor@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/isci/host.c | 8 ++++----
 drivers/scsi/isci/host.h | 2 +-
 drivers/scsi/isci/task.c | 4 ++--
 3 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/scsi/isci/host.c b/drivers/scsi/isci/host.c
index 1ee3868ade079..7b5deae68d33b 100644
--- a/drivers/scsi/isci/host.c
+++ b/drivers/scsi/isci/host.c
@@ -2717,9 +2717,9 @@ enum sci_status sci_controller_continue_io(struct isci_request *ireq)
  *    the task management request.
  * @task_request: the handle to the task request object to start.
  */
-enum sci_task_status sci_controller_start_task(struct isci_host *ihost,
-					       struct isci_remote_device *idev,
-					       struct isci_request *ireq)
+enum sci_status sci_controller_start_task(struct isci_host *ihost,
+					  struct isci_remote_device *idev,
+					  struct isci_request *ireq)
 {
 	enum sci_status status;
 
@@ -2728,7 +2728,7 @@ enum sci_task_status sci_controller_start_task(struct isci_host *ihost,
 			 "%s: SCIC Controller starting task from invalid "
 			 "state\n",
 			 __func__);
-		return SCI_TASK_FAILURE_INVALID_STATE;
+		return SCI_FAILURE_INVALID_STATE;
 	}
 
 	status = sci_remote_device_start_task(ihost, idev, ireq);
diff --git a/drivers/scsi/isci/host.h b/drivers/scsi/isci/host.h
index b3539928073c6..6bc3f022630a2 100644
--- a/drivers/scsi/isci/host.h
+++ b/drivers/scsi/isci/host.h
@@ -489,7 +489,7 @@ enum sci_status sci_controller_start_io(
 	struct isci_remote_device *idev,
 	struct isci_request *ireq);
 
-enum sci_task_status sci_controller_start_task(
+enum sci_status sci_controller_start_task(
 	struct isci_host *ihost,
 	struct isci_remote_device *idev,
 	struct isci_request *ireq);
diff --git a/drivers/scsi/isci/task.c b/drivers/scsi/isci/task.c
index 6dcaed0c1fc8c..fb6eba331ac6e 100644
--- a/drivers/scsi/isci/task.c
+++ b/drivers/scsi/isci/task.c
@@ -258,7 +258,7 @@ static int isci_task_execute_tmf(struct isci_host *ihost,
 				 struct isci_tmf *tmf, unsigned long timeout_ms)
 {
 	DECLARE_COMPLETION_ONSTACK(completion);
-	enum sci_task_status status = SCI_TASK_FAILURE;
+	enum sci_status status = SCI_FAILURE;
 	struct isci_request *ireq;
 	int ret = TMF_RESP_FUNC_FAILED;
 	unsigned long flags;
@@ -301,7 +301,7 @@ static int isci_task_execute_tmf(struct isci_host *ihost,
 	/* start the TMF io. */
 	status = sci_controller_start_task(ihost, idev, ireq);
 
-	if (status != SCI_TASK_SUCCESS) {
+	if (status != SCI_SUCCESS) {
 		dev_dbg(&ihost->pdev->dev,
 			 "%s: start_io failed - status = 0x%x, request = %p\n",
 			 __func__,
-- 
2.20.1

[PATCH AUTOSEL 4.19 053/237] scsi: bfa: Avoid implicit enum conversion in bfad_im_post_vendor_event

[Sasha Levin]

From: Nathan Chancellor <natechancellor@gmail.com>

[ Upstream commit 761c830ec7b3d0674b3ad89cefd77a692634e305 ]

Clang warns when one enumerated type is implicitly converted to another.

drivers/scsi/bfa/bfa_fcs_lport.c:379:26: warning: implicit conversion
from enumeration type 'enum bfa_lport_aen_event' to different
enumeration type 'enum bfa_ioc_aen_event' [-Wenum-conversion]
                                  BFA_AEN_CAT_LPORT, event);
                                                     ^~~~~

The root cause of these warnings is the bfad_im_post_vendor_event
function, which expects a value from enum bfa_ioc_aen_event but there
are multiple instances of values from enums bfa_port_aen_event,
bfa_audit_aen_event, and bfa_lport_aen_event being used in this
function.

Given that this doesn't appear to be a problem since cat helps with
differentiating the events, just change evt's type to int so that no
conversion needs to happen and Clang won't warn. Update aen_type's type
in bfa_aen_entry_s as members that hold enumerated types should be int.

Link: https://github.com/ClangBuiltLinux/linux/issues/147
Signed-off-by: Nathan Chancellor <natechancellor@gmail.com>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/bfa/bfa_defs_svc.h | 2 +-
 drivers/scsi/bfa/bfad_im.h      | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/bfa/bfa_defs_svc.h b/drivers/scsi/bfa/bfa_defs_svc.h
index 3d0c96a5c8735..c19c26e0e405e 100644
--- a/drivers/scsi/bfa/bfa_defs_svc.h
+++ b/drivers/scsi/bfa/bfa_defs_svc.h
@@ -1453,7 +1453,7 @@ union bfa_aen_data_u {
 struct bfa_aen_entry_s {
 	struct list_head	qe;
 	enum bfa_aen_category   aen_category;
-	u32                     aen_type;
+	int                     aen_type;
 	union bfa_aen_data_u    aen_data;
 	u64			aen_tv_sec;
 	u64			aen_tv_usec;
diff --git a/drivers/scsi/bfa/bfad_im.h b/drivers/scsi/bfa/bfad_im.h
index e61ed8dad0b4f..bd4ac187fd8e7 100644
--- a/drivers/scsi/bfa/bfad_im.h
+++ b/drivers/scsi/bfa/bfad_im.h
@@ -143,7 +143,7 @@ struct bfad_im_s {
 static inline void bfad_im_post_vendor_event(struct bfa_aen_entry_s *entry,
 					     struct bfad_s *drv, int cnt,
 					     enum bfa_aen_category cat,
-					     enum bfa_ioc_aen_event evt)
+					     int evt)
 {
 	struct timespec64 ts;
 
-- 
2.20.1

[PATCH AUTOSEL 4.19 054/237] scsi: iscsi_tcp: Explicitly cast param in iscsi_sw_tcp_host_get_param

[Sasha Levin]

From: Nathan Chancellor <natechancellor@gmail.com>

[ Upstream commit 20054597f169090109fc3f0dfa1a48583f4178a4 ]

Clang warns when one enumerated type is implicitly converted to another.

drivers/scsi/iscsi_tcp.c:803:15: warning: implicit conversion from
enumeration type 'enum iscsi_host_param' to different enumeration type
'enum iscsi_param' [-Wenum-conversion]
                                                 &addr, param, buf);
                                                        ^~~~~
1 warning generated.

iscsi_conn_get_addr_param handles ISCSI_HOST_PARAM_IPADDRESS just fine
so add an explicit cast to iscsi_param to make it clear to Clang that
this is expected behavior.

Link: https://github.com/ClangBuiltLinux/linux/issues/153
Signed-off-by: Nathan Chancellor <natechancellor@gmail.com>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/iscsi_tcp.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c
index b025a0b743417..23354f206533b 100644
--- a/drivers/scsi/iscsi_tcp.c
+++ b/drivers/scsi/iscsi_tcp.c
@@ -800,7 +800,8 @@ static int iscsi_sw_tcp_host_get_param(struct Scsi_Host *shost,
 			return rc;
 
 		return iscsi_conn_get_addr_param((struct sockaddr_storage *)
-						 &addr, param, buf);
+						 &addr,
+						 (enum iscsi_param)param, buf);
 	default:
 		return iscsi_host_get_param(shost, param, buf);
 	}
-- 
2.20.1

[PATCH AUTOSEL 4.19 063/237] scsi: dc395x: fix dma API usage in srb_done

[Sasha Levin]

From: Christoph Hellwig <hch@lst.de>

[ Upstream commit 3a5bd7021184dec2946f2a4d7a8943f8a5713e52 ]

We can't just transfer ownership to the CPU and then unmap, as this will
break with swiotlb.

Instead unmap the command and sense buffer a little earlier in the I/O
completion handler and get rid of the pci_dma_sync_sg_for_cpu call
entirely.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/dc395x.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/scsi/dc395x.c b/drivers/scsi/dc395x.c
index 1ed2cd82129d2..08161df64ead5 100644
--- a/drivers/scsi/dc395x.c
+++ b/drivers/scsi/dc395x.c
@@ -3447,14 +3447,12 @@ static void srb_done(struct AdapterCtlBlk *acb, struct DeviceCtlBlk *dcb,
 		}
 	}
 
-	if (dir != PCI_DMA_NONE && scsi_sg_count(cmd))
-		pci_dma_sync_sg_for_cpu(acb->dev, scsi_sglist(cmd),
-					scsi_sg_count(cmd), dir);
-
 	ckc_only = 0;
 /* Check Error Conditions */
       ckc_e:
 
+	pci_unmap_srb(acb, srb);
+
 	if (cmd->cmnd[0] == INQUIRY) {
 		unsigned char *base = NULL;
 		struct ScsiInqData *ptr;
@@ -3507,7 +3505,6 @@ static void srb_done(struct AdapterCtlBlk *acb, struct DeviceCtlBlk *dcb,
 			cmd, cmd->result);
 		srb_free_insert(acb, srb);
 	}
-	pci_unmap_srb(acb, srb);
 
 	cmd->scsi_done(cmd);
 	waiting_process_next(acb);
-- 
2.20.1

[PATCH AUTOSEL 4.19 064/237] scsi: dc395x: fix DMA API usage in sg_update_list

[Sasha Levin]

From: Christoph Hellwig <hch@lst.de>

[ Upstream commit 6c404a68bf83b4135a8a9aa1c388ebdf98e8ba7f ]

We need to transfer device ownership to the CPU before we can manipulate
the mapped data.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/dc395x.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/scsi/dc395x.c b/drivers/scsi/dc395x.c
index 08161df64ead5..3943347ec3c7c 100644
--- a/drivers/scsi/dc395x.c
+++ b/drivers/scsi/dc395x.c
@@ -1969,6 +1969,11 @@ static void sg_update_list(struct ScsiReqBlk *srb, u32 left)
 			xferred -= psge->length;
 		} else {
 			/* Partial SG entry done */
+			pci_dma_sync_single_for_cpu(srb->dcb->
+					    acb->dev,
+					    srb->sg_bus_addr,
+					    SEGMENTX_LEN,
+					    PCI_DMA_TODEVICE);
 			psge->length -= xferred;
 			psge->address += xferred;
 			srb->sg_index = idx;
-- 
2.20.1

[PATCH AUTOSEL 4.19 065/237] scsi: zorro_esp: Limit DMA transfers to 65535 bytes

[Sasha Levin]

From: Finn Thain <fthain@telegraphics.com.au>

[ Upstream commit b7ded0e8b0d11b6df1c4e5aa23a26e6629c21985 ]

The core driver, esp_scsi, does not use the ESP_CONFIG2_FENAB bit, so the
chip's Transfer Counter register is only 16 bits wide (not 24).  A larger
transfer cannot work and will theoretically result in a failed command
and a "DMA length is zero" error.

Fixes: 3109e5ae0311 ("scsi: zorro_esp: New driver for Amiga Zorro NCR53C9x boards")
Signed-off-by: Finn Thain <fthain@telegraphics.com.au>
Cc: Michael Schmitz <schmitzmic@gmail.com>
Tested-by: Michael Schmitz <schmitzmic@gmail.com>
Reviewed-by: Michael Schmitz <schmitzmic@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/zorro_esp.c | 8 +-------
 1 file changed, 1 insertion(+), 7 deletions(-)

diff --git a/drivers/scsi/zorro_esp.c b/drivers/scsi/zorro_esp.c
index bb70882e6b56e..be79127db5946 100644
--- a/drivers/scsi/zorro_esp.c
+++ b/drivers/scsi/zorro_esp.c
@@ -245,7 +245,7 @@ static int fastlane_esp_irq_pending(struct esp *esp)
 static u32 zorro_esp_dma_length_limit(struct esp *esp, u32 dma_addr,
 					u32 dma_len)
 {
-	return dma_len > 0xFFFFFF ? 0xFFFFFF : dma_len;
+	return dma_len > 0xFFFF ? 0xFFFF : dma_len;
 }
 
 static void zorro_esp_reset_dma(struct esp *esp)
@@ -484,7 +484,6 @@ static void zorro_esp_send_blz1230_dma_cmd(struct esp *esp, u32 addr,
 	scsi_esp_cmd(esp, ESP_CMD_DMA);
 	zorro_esp_write8(esp, (esp_count >> 0) & 0xff, ESP_TCLOW);
 	zorro_esp_write8(esp, (esp_count >> 8) & 0xff, ESP_TCMED);
-	zorro_esp_write8(esp, (esp_count >> 16) & 0xff, ESP_TCHI);
 
 	scsi_esp_cmd(esp, cmd);
 }
@@ -529,7 +528,6 @@ static void zorro_esp_send_blz1230II_dma_cmd(struct esp *esp, u32 addr,
 	scsi_esp_cmd(esp, ESP_CMD_DMA);
 	zorro_esp_write8(esp, (esp_count >> 0) & 0xff, ESP_TCLOW);
 	zorro_esp_write8(esp, (esp_count >> 8) & 0xff, ESP_TCMED);
-	zorro_esp_write8(esp, (esp_count >> 16) & 0xff, ESP_TCHI);
 
 	scsi_esp_cmd(esp, cmd);
 }
@@ -574,7 +572,6 @@ static void zorro_esp_send_blz2060_dma_cmd(struct esp *esp, u32 addr,
 	scsi_esp_cmd(esp, ESP_CMD_DMA);
 	zorro_esp_write8(esp, (esp_count >> 0) & 0xff, ESP_TCLOW);
 	zorro_esp_write8(esp, (esp_count >> 8) & 0xff, ESP_TCMED);
-	zorro_esp_write8(esp, (esp_count >> 16) & 0xff, ESP_TCHI);
 
 	scsi_esp_cmd(esp, cmd);
 }
@@ -599,7 +596,6 @@ static void zorro_esp_send_cyber_dma_cmd(struct esp *esp, u32 addr,
 
 	zorro_esp_write8(esp, (esp_count >> 0) & 0xff, ESP_TCLOW);
 	zorro_esp_write8(esp, (esp_count >> 8) & 0xff, ESP_TCMED);
-	zorro_esp_write8(esp, (esp_count >> 16) & 0xff, ESP_TCHI);
 
 	if (write) {
 		/* DMA receive */
@@ -649,7 +645,6 @@ static void zorro_esp_send_cyberII_dma_cmd(struct esp *esp, u32 addr,
 
 	zorro_esp_write8(esp, (esp_count >> 0) & 0xff, ESP_TCLOW);
 	zorro_esp_write8(esp, (esp_count >> 8) & 0xff, ESP_TCMED);
-	zorro_esp_write8(esp, (esp_count >> 16) & 0xff, ESP_TCHI);
 
 	if (write) {
 		/* DMA receive */
@@ -691,7 +686,6 @@ static void zorro_esp_send_fastlane_dma_cmd(struct esp *esp, u32 addr,
 
 	zorro_esp_write8(esp, (esp_count >> 0) & 0xff, ESP_TCLOW);
 	zorro_esp_write8(esp, (esp_count >> 8) & 0xff, ESP_TCMED);
-	zorro_esp_write8(esp, (esp_count >> 16) & 0xff, ESP_TCHI);
 
 	if (write) {
 		/* DMA receive */
-- 
2.20.1

[PATCH AUTOSEL 4.19 090/237] scsi: hisi_sas: Fix NULL pointer dereference

[Sasha Levin]

From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>

[ Upstream commit f4445bb93d82a984657b469e63118c2794a4c3d3 ]

There is a NULL pointer dereference in case *slot* happens to be NULL at
lines 1053 and 1878:

struct hisi_sas_cq *cq =
	&hisi_hba->cq[slot->dlvry_queue];

Notice that *slot* is being NULL checked at lines 1057 and 1881:
if (slot), which implies it may be NULL.

Fix this by placing the declaration and definition of variable cq, which
contains the pointer dereference slot->dlvry_queue, after slot has been
properly NULL checked.

Addresses-Coverity-ID: 1474515 ("Dereference before null check")
Addresses-Coverity-ID: 1474520 ("Dereference before null check")
Fixes: 584f53fe5f52 ("scsi: hisi_sas: Fix the race between IO completion and timeout for SMP/internal IO")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Reviewed-by: Xiang Chen <chenxiang66@hisilicon.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/hisi_sas/hisi_sas_main.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index d4a2625a44232..f478d1f50dfc0 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -1025,11 +1025,11 @@ static int hisi_sas_exec_internal_tmf_task(struct domain_device *device,
 		if ((task->task_state_flags & SAS_TASK_STATE_ABORTED)) {
 			if (!(task->task_state_flags & SAS_TASK_STATE_DONE)) {
 				struct hisi_sas_slot *slot = task->lldd_task;
-				struct hisi_sas_cq *cq =
-					&hisi_hba->cq[slot->dlvry_queue];
 
 				dev_err(dev, "abort tmf: TMF task timeout and not done\n");
 				if (slot) {
+					struct hisi_sas_cq *cq =
+					       &hisi_hba->cq[slot->dlvry_queue];
 					/*
 					 * flush tasklet to avoid free'ing task
 					 * before using task in IO completion
@@ -1856,10 +1856,10 @@ hisi_sas_internal_task_abort(struct hisi_hba *hisi_hba,
 	if ((task->task_state_flags & SAS_TASK_STATE_ABORTED)) {
 		if (!(task->task_state_flags & SAS_TASK_STATE_DONE)) {
 			struct hisi_sas_slot *slot = task->lldd_task;
-			struct hisi_sas_cq *cq =
-				&hisi_hba->cq[slot->dlvry_queue];
 
 			if (slot) {
+				struct hisi_sas_cq *cq =
+					&hisi_hba->cq[slot->dlvry_queue];
 				/*
 				 * flush tasklet to avoid free'ing task
 				 * before using task in IO completion
-- 
2.20.1

[PATCH AUTOSEL 4.19 207/237] scsi: mpt3sas: Fix Sync cache command failure during driver unload

[Sasha Levin]

From: Suganath Prabu <suganath-prabu.subramani@broadcom.com>

[ Upstream commit 9029a72500b95578a35877a43473b82cb0386c53 ]

This is to fix SYNC CACHE and START STOP command failures with
DID_NO_CONNECT during driver unload.

In driver's IO submission patch (i.e. in driver's .queuecommand()) driver
won't allow any SCSI commands to the IOC when ioc->remove_host flag is set
and hence SYNC CACHE commands which are issued to the target drives (where
write cache is enabled) during driver unload time is failed with
DID_NO_CONNECT status.

Now modified the driver to allow SYNC CACHE and START STOP commands to IOC,
even when remove_host flag is set.

Signed-off-by: Suganath Prabu <suganath-prabu.subramani@broadcom.com>
Reviewed-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/mpt3sas/mpt3sas_scsih.c | 36 +++++++++++++++++++++++++++-
 1 file changed, 35 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index 73d661a0ecbb9..d3c944d997039 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -3791,6 +3791,40 @@ _scsih_tm_tr_complete(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index,
 	return _scsih_check_for_pending_tm(ioc, smid);
 }
 
+/** _scsih_allow_scmd_to_device - check whether scmd needs to
+ *				 issue to IOC or not.
+ * @ioc: per adapter object
+ * @scmd: pointer to scsi command object
+ *
+ * Returns true if scmd can be issued to IOC otherwise returns false.
+ */
+inline bool _scsih_allow_scmd_to_device(struct MPT3SAS_ADAPTER *ioc,
+	struct scsi_cmnd *scmd)
+{
+
+	if (ioc->pci_error_recovery)
+		return false;
+
+	if (ioc->hba_mpi_version_belonged == MPI2_VERSION) {
+		if (ioc->remove_host)
+			return false;
+
+		return true;
+	}
+
+	if (ioc->remove_host) {
+
+		switch (scmd->cmnd[0]) {
+		case SYNCHRONIZE_CACHE:
+		case START_STOP:
+			return true;
+		default:
+			return false;
+		}
+	}
+
+	return true;
+}
 
 /**
  * _scsih_sas_control_complete - completion routine
@@ -4623,7 +4657,7 @@ scsih_qcmd(struct Scsi_Host *shost, struct scsi_cmnd *scmd)
 		return 0;
 	}
 
-	if (ioc->pci_error_recovery || ioc->remove_host) {
+	if (!(_scsih_allow_scmd_to_device(ioc, scmd))) {
 		scmd->result = DID_NO_CONNECT << 16;
 		scmd->scsi_done(scmd);
 		return 0;
-- 
2.20.1

[PATCH AUTOSEL 4.19 208/237] scsi: mpt3sas: Don't modify EEDPTagMode field setting on SAS3.5 HBA devices

[Sasha Levin]

From: Suganath Prabu <suganath-prabu.subramani@broadcom.com>

[ Upstream commit 6cd1bc7b9b5075d395ba0120923903873fc7ea0e ]

If EEDPTagMode field in manufacturing page11 is set then unset it. This is
needed to fix a hardware bug only in SAS3/SAS2 cards. So, skipping
EEDPTagMode changes in Manufacturing page11 for SAS 3.5 controllers.

Signed-off-by: Suganath Prabu <suganath-prabu.subramani@broadcom.com>
Reviewed-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/mpt3sas/mpt3sas_base.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index d2ab52026014f..2c556c7fcf0dc 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -4117,7 +4117,7 @@ _base_static_config_pages(struct MPT3SAS_ADAPTER *ioc)
 	 * flag unset in NVDATA.
 	 */
 	mpt3sas_config_get_manufacturing_pg11(ioc, &mpi_reply, &ioc->manu_pg11);
-	if (ioc->manu_pg11.EEDPTagMode == 0) {
+	if (!ioc->is_gen35_ioc && ioc->manu_pg11.EEDPTagMode == 0) {
 		pr_err("%s: overriding NVDATA EEDPTagMode setting\n",
 		    ioc->name);
 		ioc->manu_pg11.EEDPTagMode &= ~0x3;
-- 
2.20.1

[PATCH AUTOSEL 4.19 209/237] scsi: mpt3sas: Fix driver modifying persistent data in Manufacturing page11

[Sasha Levin]

From: Suganath Prabu <suganath-prabu.subramani@broadcom.com>

[ Upstream commit 97f35194093362a63b33caba2485521ddabe2c95 ]

Currently driver is modifying both current & NVRAM/persistent data in
Manufacturing page11. Driver should change only current copy of
Manufacturing page11. It should not modify the persistent data.

So removed the section of code where driver is modifying the persistent
data of Manufacturing page11.

Signed-off-by: Suganath Prabu <suganath-prabu.subramani@broadcom.com>
Reviewed-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/mpt3sas/mpt3sas_config.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/scsi/mpt3sas/mpt3sas_config.c b/drivers/scsi/mpt3sas/mpt3sas_config.c
index d29a2dcc7d0ec..9b01c5a7aebd9 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_config.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_config.c
@@ -692,10 +692,6 @@ mpt3sas_config_set_manufacturing_pg11(struct MPT3SAS_ADAPTER *ioc,
 	r = _config_request(ioc, &mpi_request, mpi_reply,
 	    MPT3_CONFIG_PAGE_DEFAULT_TIMEOUT, config_page,
 	    sizeof(*config_page));
-	mpi_request.Action = MPI2_CONFIG_ACTION_PAGE_WRITE_NVRAM;
-	r = _config_request(ioc, &mpi_request, mpi_reply,
-	    MPT3_CONFIG_PAGE_DEFAULT_TIMEOUT, config_page,
-	    sizeof(*config_page));
  out:
 	return r;
 }
-- 
2.20.1

[PATCH AUTOSEL 4.19 210/237] scsi: megaraid_sas: Fix msleep granularity

[Sasha Levin]

From: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>

[ Upstream commit 9155cf30a3c4ef97e225d6daddf9bd4b173267e8 ]

In megasas_transition_to_ready() driver waits 180seconds for controller to
change FW state. Here we are calling msleep(1) in a loop for this.  As
explained in timers-howto.txt, msleep(1) will actually sleep longer than
1ms. If a faulty controller is connected, we will end up waiting for much
more than 180 seconds causing unnecessary delays during load.

Change the granularity of msleep() call from 1ms to 1000ms.

Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/megaraid/megaraid_sas_base.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index bc37666f998e6..2f94ab9c23540 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -3894,12 +3894,12 @@ megasas_transition_to_ready(struct megasas_instance *instance, int ocr)
 		/*
 		 * The cur_state should not last for more than max_wait secs
 		 */
-		for (i = 0; i < (max_wait * 1000); i++) {
+		for (i = 0; i < max_wait; i++) {
 			curr_abs_state = instance->instancet->
 				read_fw_status_reg(instance->reg_set);
 
 			if (abs_state == curr_abs_state) {
-				msleep(1);
+				msleep(1000);
 			} else
 				break;
 		}
-- 
2.20.1

[PATCH AUTOSEL 4.19 211/237] scsi: megaraid_sas: Fix goto labels in error handling

[Sasha Levin]

From: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>

[ Upstream commit 8a25fa17b6ed6e6c8101e9c68a10ae68a9025f2c ]

During init, if pci_alloc_irq_vectors() fails, the driver has not yet setup
the IRQs. Fix the goto labels and error handling for this case.

Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/megaraid/megaraid_sas_base.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index 2f94ab9c23540..2f31d266339f8 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -5410,7 +5410,7 @@ static int megasas_init_fw(struct megasas_instance *instance)
 	if (!instance->msix_vectors) {
 		i = pci_alloc_irq_vectors(instance->pdev, 1, 1, PCI_IRQ_LEGACY);
 		if (i < 0)
-			goto fail_setup_irqs;
+			goto fail_init_adapter;
 	}
 
 	megasas_setup_reply_map(instance);
@@ -5619,9 +5619,8 @@ static int megasas_init_fw(struct megasas_instance *instance)
 
 fail_get_ld_pd_list:
 	instance->instancet->disable_intr(instance);
-fail_init_adapter:
 	megasas_destroy_irqs(instance);
-fail_setup_irqs:
+fail_init_adapter:
 	if (instance->msix_vectors)
 		pci_free_irq_vectors(instance->pdev);
 	instance->msix_vectors = 0;
-- 
2.20.1

[PATCH AUTOSEL 4.19 212/237] scsi: lpfc: fcoe: Fix link down issue after 1000+ link bounces

[Sasha Levin]

From: James Smart <jsmart2021@gmail.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@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.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 f3c6801c0b312..8bf916b9a987d 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -1157,6 +1157,7 @@ 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) {
@@ -1171,6 +1172,7 @@ 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 ccdd82b1123f7..38a9245fddba1 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -1997,6 +1997,26 @@ 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 9acb5b44ce4c1..a7d3e532e0f58 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -5044,7 +5044,7 @@ 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 a490e63c94b67..210c05da64b47 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -18435,15 +18435,8 @@ 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 399c0015c5465..3dcc6615a23b2 100644
--- a/drivers/scsi/lpfc/lpfc_sli4.h
+++ b/drivers/scsi/lpfc/lpfc_sli4.h
@@ -279,6 +279,7 @@ 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

[PATCH AUTOSEL 4.19 213/237] scsi: lpfc: Fix odd recovery in duplicate FLOGIs in point-to-point

[Sasha Levin]

From: James Smart <jsmart2021@gmail.com>

[ Upstream commit d496b9a7246cb9813da1fe49e14edbbbf8e232d5 ]

Testing a point-to-point topology and a case of re-FLOGI without
intervening link bouncing, showed an odd interaction with firmware and
a resulting scenario where the driver no longer probed after accepting
the new FLOGI.

Work around the firmware issue by issuing a link bounce if a FLOGI is
received after the link is already up and FLOGI's accepted.

While debugging the issue, realized that some debug traces should be
clarified to help in the future.

Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/lpfc/lpfc.h         |  1 +
 drivers/scsi/lpfc/lpfc_els.c     | 66 ++++++++++++++++++++++++++------
 drivers/scsi/lpfc/lpfc_hbadisc.c |  9 +++++
 3 files changed, 64 insertions(+), 12 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h
index 43732e8d13473..ebcfcbb8b4ccc 100644
--- a/drivers/scsi/lpfc/lpfc.h
+++ b/drivers/scsi/lpfc/lpfc.h
@@ -490,6 +490,7 @@ struct lpfc_vport {
 	struct nvme_fc_local_port *localport;
 	uint8_t  nvmei_support; /* driver supports NVME Initiator */
 	uint32_t last_fcp_wqidx;
+	uint32_t rcv_flogi_cnt; /* How many unsol FLOGIs ACK'd. */
 };
 
 struct hbq_s {
diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index 8bf916b9a987d..e263a486b1c6c 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -1057,9 +1057,9 @@ lpfc_cmpl_els_flogi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 			goto flogifail;
 
 		lpfc_printf_vlog(vport, KERN_WARNING, LOG_ELS,
-				 "0150 FLOGI failure Status:x%x/x%x TMO:x%x\n",
+				 "0150 FLOGI failure Status:x%x/x%x xri x%x TMO:x%x\n",
 				 irsp->ulpStatus, irsp->un.ulpWord[4],
-				 irsp->ulpTimeout);
+				 cmdiocb->sli4_xritag, irsp->ulpTimeout);
 
 		/* FLOGI failed, so there is no fabric */
 		spin_lock_irq(shost->host_lock);
@@ -1113,7 +1113,8 @@ lpfc_cmpl_els_flogi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	/* FLOGI completes successfully */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
 			 "0101 FLOGI completes successfully, I/O tag:x%x, "
-			 "Data: x%x x%x x%x x%x x%x x%x\n", cmdiocb->iotag,
+			 "xri x%x Data: x%x x%x x%x x%x x%x %x\n",
+			 cmdiocb->iotag, cmdiocb->sli4_xritag,
 			 irsp->un.ulpWord[4], sp->cmn.e_d_tov,
 			 sp->cmn.w2.r_a_tov, sp->cmn.edtovResolution,
 			 vport->port_state, vport->fc_flag);
@@ -4266,14 +4267,6 @@ lpfc_els_rsp_acc(struct lpfc_vport *vport, uint32_t flag,
 	default:
 		return 1;
 	}
-	/* Xmit ELS ACC response tag <ulpIoTag> */
-	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
-			 "0128 Xmit ELS ACC response tag x%x, XRI: x%x, "
-			 "DID: x%x, nlp_flag: x%x nlp_state: x%x RPI: x%x "
-			 "fc_flag x%x\n",
-			 elsiocb->iotag, elsiocb->iocb.ulpContext,
-			 ndlp->nlp_DID, ndlp->nlp_flag, ndlp->nlp_state,
-			 ndlp->nlp_rpi, vport->fc_flag);
 	if (ndlp->nlp_flag & NLP_LOGO_ACC) {
 		spin_lock_irq(shost->host_lock);
 		if (!(ndlp->nlp_flag & NLP_RPI_REGISTERED ||
@@ -4442,6 +4435,15 @@ lpfc_els_rsp_adisc_acc(struct lpfc_vport *vport, struct lpfc_iocbq *oldiocb,
 		lpfc_els_free_iocb(phba, elsiocb);
 		return 1;
 	}
+
+	/* Xmit ELS ACC response tag <ulpIoTag> */
+	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
+			 "0128 Xmit ELS ACC response Status: x%x, IoTag: x%x, "
+			 "XRI: x%x, DID: x%x, nlp_flag: x%x nlp_state: x%x "
+			 "RPI: x%x, fc_flag x%x\n",
+			 rc, elsiocb->iotag, elsiocb->sli4_xritag,
+			 ndlp->nlp_DID, ndlp->nlp_flag, ndlp->nlp_state,
+			 ndlp->nlp_rpi, vport->fc_flag);
 	return 0;
 }
 
@@ -6452,6 +6454,11 @@ lpfc_els_rcv_flogi(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb,
 	port_state = vport->port_state;
 	vport->fc_flag |= FC_PT2PT;
 	vport->fc_flag &= ~(FC_FABRIC | FC_PUBLIC_LOOP);
+
+	/* Acking an unsol FLOGI.  Count 1 for link bounce
+	 * work-around.
+	 */
+	vport->rcv_flogi_cnt++;
 	spin_unlock_irq(shost->host_lock);
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
 			 "3311 Rcv Flogi PS x%x new PS x%x "
@@ -7849,8 +7856,9 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 	struct ls_rjt stat;
 	uint32_t *payload;
 	uint32_t cmd, did, newnode;
-	uint8_t rjt_exp, rjt_err = 0;
+	uint8_t rjt_exp, rjt_err = 0, init_link = 0;
 	IOCB_t *icmd = &elsiocb->iocb;
+	LPFC_MBOXQ_t *mbox;
 
 	if (!vport || !(elsiocb->context2))
 		goto dropit;
@@ -7999,6 +8007,19 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 			did, vport->port_state, ndlp->nlp_flag);
 
 		phba->fc_stat.elsRcvFLOGI++;
+
+		/* If the driver believes fabric discovery is done and is ready,
+		 * bounce the link.  There is some descrepancy.
+		 */
+		if (vport->port_state >= LPFC_LOCAL_CFG_LINK &&
+		    vport->fc_flag & FC_PT2PT &&
+		    vport->rcv_flogi_cnt >= 1) {
+			rjt_err = LSRJT_LOGICAL_BSY;
+			rjt_exp = LSEXP_NOTHING_MORE;
+			init_link++;
+			goto lsrjt;
+		}
+
 		lpfc_els_rcv_flogi(vport, elsiocb, ndlp);
 		if (newnode)
 			lpfc_nlp_put(ndlp);
@@ -8227,6 +8248,27 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 
 	lpfc_nlp_put(elsiocb->context1);
 	elsiocb->context1 = NULL;
+
+	/* Special case.  Driver received an unsolicited command that
+	 * unsupportable given the driver's current state.  Reset the
+	 * link and start over.
+	 */
+	if (init_link) {
+		mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
+		if (!mbox)
+			return;
+		lpfc_linkdown(phba);
+		lpfc_init_link(phba, mbox,
+			       phba->cfg_topology,
+			       phba->cfg_link_speed);
+		mbox->u.mb.un.varInitLnk.lipsr_AL_PA = 0;
+		mbox->mbox_cmpl = lpfc_sli_def_mbox_cmpl;
+		mbox->vport = vport;
+		if (lpfc_sli_issue_mbox(phba, mbox, MBX_NOWAIT) ==
+		    MBX_NOT_FINISHED)
+			mempool_free(mbox, phba->mbox_mem_pool);
+	}
+
 	return;
 
 dropit:
diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index 38a9245fddba1..5ec60c221d846 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -952,6 +952,7 @@ lpfc_linkdown(struct lpfc_hba *phba)
 		}
 		spin_lock_irq(shost->host_lock);
 		phba->pport->fc_flag &= ~(FC_PT2PT | FC_PT2PT_PLOGI);
+		phba->pport->rcv_flogi_cnt = 0;
 		spin_unlock_irq(shost->host_lock);
 	}
 	return 0;
@@ -1023,6 +1024,7 @@ lpfc_linkup(struct lpfc_hba *phba)
 {
 	struct lpfc_vport **vports;
 	int i;
+	struct Scsi_Host  *shost = lpfc_shost_from_vport(phba->pport);
 
 	phba->link_state = LPFC_LINK_UP;
 
@@ -1036,6 +1038,13 @@ lpfc_linkup(struct lpfc_hba *phba)
 			lpfc_linkup_port(vports[i]);
 	lpfc_destroy_vport_work_array(phba, vports);
 
+	/* Clear the pport flogi counter in case the link down was
+	 * absorbed without an ACQE. No lock here - in worker thread
+	 * and discovery is synchronized.
+	 */
+	spin_lock_irq(shost->host_lock);
+	phba->pport->rcv_flogi_cnt = 0;
+	spin_unlock_irq(shost->host_lock);
 	return 0;
 }
 
-- 
2.20.1

[PATCH AUTOSEL 4.19 214/237] scsi: lpfc: Correct loss of fc4 type on remote port address change

[Sasha Levin]

From: James Smart <jsmart2021@gmail.com>

[ Upstream commit d83ca3ea833d7a66d49225e4191c4e37cab8f079 ]

An address change for a remote port cause PRLI for the wrong protocol
to be sent.  The node copy done in the discovery code skipped copying
the fc4 protocols supported as well.

Fix the copy logic for the address change.  Beefed up log messages in
this area as well.

Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/lpfc/lpfc_els.c       | 27 +++++++++++++++++++++++----
 drivers/scsi/lpfc/lpfc_nportdisc.c |  5 +++--
 2 files changed, 26 insertions(+), 6 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index e263a486b1c6c..222fa9b7f4788 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -1556,8 +1556,10 @@ lpfc_plogi_confirm_nport(struct lpfc_hba *phba, uint32_t *prsp,
 	 */
 	new_ndlp = lpfc_findnode_wwpn(vport, &sp->portName);
 
+	/* return immediately if the WWPN matches ndlp */
 	if (new_ndlp == ndlp && NLP_CHK_NODE_ACT(new_ndlp))
 		return ndlp;
+
 	if (phba->sli_rev == LPFC_SLI_REV4) {
 		active_rrqs_xri_bitmap = mempool_alloc(phba->active_rrq_pool,
 						       GFP_KERNEL);
@@ -1566,9 +1568,13 @@ lpfc_plogi_confirm_nport(struct lpfc_hba *phba, uint32_t *prsp,
 			       phba->cfg_rrq_xri_bitmap_sz);
 	}
 
-	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
-		 "3178 PLOGI confirm: ndlp %p x%x: new_ndlp %p\n",
-		 ndlp, ndlp->nlp_DID, new_ndlp);
+	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS | LOG_NODE,
+			 "3178 PLOGI confirm: ndlp x%x x%x x%x: "
+			 "new_ndlp x%x x%x x%x\n",
+			 ndlp->nlp_DID, ndlp->nlp_flag,  ndlp->nlp_fc4_type,
+			 (new_ndlp ? new_ndlp->nlp_DID : 0),
+			 (new_ndlp ? new_ndlp->nlp_flag : 0),
+			 (new_ndlp ? new_ndlp->nlp_fc4_type : 0));
 
 	if (!new_ndlp) {
 		rc = memcmp(&ndlp->nlp_portname, name,
@@ -1617,6 +1623,14 @@ lpfc_plogi_confirm_nport(struct lpfc_hba *phba, uint32_t *prsp,
 			       phba->cfg_rrq_xri_bitmap_sz);
 	}
 
+	/* At this point in this routine, we know new_ndlp will be
+	 * returned. however, any previous GID_FTs that were done
+	 * would have updated nlp_fc4_type in ndlp, so we must ensure
+	 * new_ndlp has the right value.
+	 */
+	if (vport->fc_flag & FC_FABRIC)
+		new_ndlp->nlp_fc4_type = ndlp->nlp_fc4_type;
+
 	lpfc_unreg_rpi(vport, new_ndlp);
 	new_ndlp->nlp_DID = ndlp->nlp_DID;
 	new_ndlp->nlp_prev_state = ndlp->nlp_prev_state;
@@ -1666,7 +1680,6 @@ lpfc_plogi_confirm_nport(struct lpfc_hba *phba, uint32_t *prsp,
 		if (ndlp->nrport) {
 			ndlp->nrport = NULL;
 			lpfc_nlp_put(ndlp);
-			new_ndlp->nlp_fc4_type = ndlp->nlp_fc4_type;
 		}
 
 		/* We shall actually free the ndlp with both nlp_DID and
@@ -1740,6 +1753,12 @@ lpfc_plogi_confirm_nport(struct lpfc_hba *phba, uint32_t *prsp,
 	    active_rrqs_xri_bitmap)
 		mempool_free(active_rrqs_xri_bitmap,
 			     phba->active_rrq_pool);
+
+	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS | LOG_NODE,
+			 "3173 PLOGI confirm exit: new_ndlp x%x x%x x%x\n",
+			 new_ndlp->nlp_DID, new_ndlp->nlp_flag,
+			 new_ndlp->nlp_fc4_type);
+
 	return new_ndlp;
 }
 
diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c
index ae6301c796785..f72a0d628bd3d 100644
--- a/drivers/scsi/lpfc/lpfc_nportdisc.c
+++ b/drivers/scsi/lpfc/lpfc_nportdisc.c
@@ -2865,8 +2865,9 @@ lpfc_disc_state_machine(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	/* DSM in event <evt> on NPort <nlp_DID> in state <cur_state> */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
 			 "0211 DSM in event x%x on NPort x%x in "
-			 "state %d Data: x%x\n",
-			 evt, ndlp->nlp_DID, cur_state, ndlp->nlp_flag);
+			 "state %d Data: x%x x%x\n",
+			 evt, ndlp->nlp_DID, cur_state,
+			 ndlp->nlp_flag, ndlp->nlp_fc4_type);
 
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_DSM,
 		 "DSM in:          evt:%d ste:%d did:x%x",
-- 
2.20.1