scsi: pm80xx: Completing pending I/O after fatal error

When controller runs into fatal error, I/Os get stuck with no response,
handler event is defined to complete the pending I/Os (SAS task and
internal task) and also perform the cleanup for the drives.

Link: https://lore.kernel.org/r/20210415103352.3580-7-Viswas.G@microchip.com
Acked-by: Jack Wang <jinpu.wang@cloud.ionos.com>
Signed-off-by: Ruksar Devadi <Ruksar.devadi@microchip.com>
Signed-off-by: Viswas G <Viswas.G@microchip.com>
Signed-off-by: Ashokkumar N <Ashokkumar.N@microchip.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

6 files changed, 65 insertions, 7 deletions

diff --git a/drivers/scsi/pm8001/pm8001_hwi.c b/drivers/scsi/pm8001/pm8001_hwi.c
index c1f9e7d0466b..8ed505051657 100644
--- a/drivers/scsi/pm8001/pm8001_hwi.c
+++ b/drivers/scsi/pm8001/pm8001_hwi.c
@@ -1499,12 +1499,14 @@ void pm8001_work_fn(struct work_struct *work)
 	 * was cancelled. This nullification happens when the device
 	 * goes away.
 	 */
-	pm8001_dev = pw->data; /* Most stash device structure */
-	if ((pm8001_dev == NULL)
-	 || ((pw->handler != IO_XFER_ERROR_BREAK)
-	  && (pm8001_dev->dev_type == SAS_PHY_UNUSED))) {
-		kfree(pw);
-		return;
+	if (pw->handler != IO_FATAL_ERROR) {
+		pm8001_dev = pw->data; /* Most stash device structure */
+		if ((pm8001_dev == NULL)
+		 || ((pw->handler != IO_XFER_ERROR_BREAK)
+			 && (pm8001_dev->dev_type == SAS_PHY_UNUSED))) {
+			kfree(pw);
+			return;
+		}
 	}
 
 	switch (pw->handler) {
@@ -1668,6 +1670,58 @@ void pm8001_work_fn(struct work_struct *work)
 		dev = pm8001_dev->sas_device;
 		pm8001_I_T_nexus_reset(dev);
 		break;
+	case IO_FATAL_ERROR:
+	{
+		struct pm8001_hba_info *pm8001_ha = pw->pm8001_ha;
+		struct pm8001_ccb_info *ccb;
+		struct task_status_struct *ts;
+		struct sas_task *task;
+		int i;
+		u32 tag, device_id;
+
+		for (i = 0; ccb = NULL, i < PM8001_MAX_CCB; i++) {
+			ccb = &pm8001_ha->ccb_info[i];
+			task = ccb->task;
+			ts = &task->task_status;
+			tag = ccb->ccb_tag;
+			/* check if tag is NULL */
+			if (!tag) {
+				pm8001_dbg(pm8001_ha, FAIL,
+					"tag Null\n");
+				continue;
+			}
+			if (task != NULL) {
+				dev = task->dev;
+				if (!dev) {
+					pm8001_dbg(pm8001_ha, FAIL,
+						"dev is NULL\n");
+					continue;
+				}
+				/*complete sas task and update to top layer */
+				pm8001_ccb_task_free(pm8001_ha, task, ccb, tag);
+				ts->resp = SAS_TASK_COMPLETE;
+				task->task_done(task);
+			} else if (tag != 0xFFFFFFFF) {
+				/* complete the internal commands/non-sas task */
+				pm8001_dev = ccb->device;
+				if (pm8001_dev->dcompletion) {
+					complete(pm8001_dev->dcompletion);
+					pm8001_dev->dcompletion = NULL;
+				}
+				complete(pm8001_ha->nvmd_completion);
+				pm8001_tag_free(pm8001_ha, tag);
+			}
+		}
+		/* Deregister all the device ids  */
+		for (i = 0; i < PM8001_MAX_DEVICES; i++) {
+			pm8001_dev = &pm8001_ha->devices[i];
+			device_id = pm8001_dev->device_id;
+			if (device_id) {
+				PM8001_CHIP_DISP->dereg_dev_req(pm8001_ha, device_id);
+				pm8001_free_dev(pm8001_dev);
+			}
+		}
+	}	break;
 	}
 	kfree(pw);
 }
diff --git a/drivers/scsi/pm8001/pm8001_hwi.h b/drivers/scsi/pm8001/pm8001_hwi.h
index 6d91e2446542..d1f3aa93325b 100644
--- a/drivers/scsi/pm8001/pm8001_hwi.h
+++ b/drivers/scsi/pm8001/pm8001_hwi.h
@@ -805,6 +805,7 @@ struct set_dev_state_resp {
 #define IO_ABORT_IN_PROGRESS				0x40
 #define IO_ABORT_DELAYED				0x41
 #define IO_INVALID_LENGTH				0x42
+#define IO_FATAL_ERROR					0x51
 
 /* WARNING: This error code must always be the last number.
  * If you add error code, modify this code also
diff --git a/drivers/scsi/pm8001/pm8001_sas.c b/drivers/scsi/pm8001/pm8001_sas.c
index a773ee6e810b..d28af413b93a 100644
--- a/drivers/scsi/pm8001/pm8001_sas.c
+++ b/drivers/scsi/pm8001/pm8001_sas.c
@@ -590,7 +590,7 @@ struct pm8001_device *pm8001_find_dev(struct pm8001_hba_info *pm8001_ha,
 	return NULL;
 }
 
-static void pm8001_free_dev(struct pm8001_device *pm8001_dev)
+void pm8001_free_dev(struct pm8001_device *pm8001_dev)
 {
 	u32 id = pm8001_dev->id;
 	memset(pm8001_dev, 0, sizeof(*pm8001_dev));
diff --git a/drivers/scsi/pm8001/pm8001_sas.h b/drivers/scsi/pm8001/pm8001_sas.h
index 07d1ac287d43..b5562f7fc7e5 100644
--- a/drivers/scsi/pm8001/pm8001_sas.h
+++ b/drivers/scsi/pm8001/pm8001_sas.h
@@ -726,6 +726,7 @@ ssize_t pm80xx_get_non_fatal_dump(struct device *cdev,
 		struct device_attribute *attr, char *buf);
 ssize_t pm8001_get_gsm_dump(struct device *cdev, u32, char *buf);
 int pm80xx_fatal_errors(struct pm8001_hba_info *pm8001_ha);
+void pm8001_free_dev(struct pm8001_device *pm8001_dev);
 /* ctl shared API */
 extern struct device_attribute *pm8001_host_attrs[];
 
diff --git a/drivers/scsi/pm8001/pm80xx_hwi.c b/drivers/scsi/pm8001/pm80xx_hwi.c
index f4f3956e658f..1c8dcdd5642c 100644
--- a/drivers/scsi/pm8001/pm80xx_hwi.c
+++ b/drivers/scsi/pm8001/pm80xx_hwi.c
@@ -4126,6 +4126,7 @@ static int process_oq(struct pm8001_hba_info *pm8001_ha, u8 vec)
 			pm8001_dbg(pm8001_ha, FAIL,
 				   "Firmware Fatal error! Regval:0x%x\n",
 				   regval);
+			pm8001_handle_event(pm8001_ha, NULL, IO_FATAL_ERROR);
 			print_scratchpad_registers(pm8001_ha);
 			return ret;
 		}
diff --git a/drivers/scsi/pm8001/pm80xx_hwi.h b/drivers/scsi/pm8001/pm80xx_hwi.h
index 2c8e85cfdbc4..c7e5d93bea92 100644
--- a/drivers/scsi/pm8001/pm80xx_hwi.h
+++ b/drivers/scsi/pm8001/pm80xx_hwi.h
@@ -1272,6 +1272,7 @@ typedef struct SASProtocolTimerConfig SASProtocolTimerConfig_t;
 #define IO_OPEN_CNX_ERROR_IT_NEXUS_LOSS_OPEN_COLLIDE	0x47
 #define IO_OPEN_CNX_ERROR_IT_NEXUS_LOSS_PATHWAY_BLOCKED	0x48
 #define IO_DS_INVALID					0x49
+#define IO_FATAL_ERROR					0x51
 /* WARNING: the value is not contiguous from here */
 #define IO_XFER_ERR_LAST_PIO_DATAIN_CRC_ERR	0x52
 #define IO_XFER_DMA_ACTIVATE_TIMEOUT		0x53