scsi: mpt3sas: Handle CoreDump state from watchdog thread

Watchdog thread polls for IOC state every 1 second.  If it detects that IOC
state is in CoreDump state then it immediately stops the IOs and also
clears the outstanding commands issued to the HBA firmware and then it will
poll for IOC state to be out of CoreDump state and once it detects that IOC
state is changed from CoreDump state to Fault state (or) CoreDumpTOSec
number of seconds are elapsed then it will issue host reset operation and
moves the IOC state to Operational state and resumes the IOs.

Whenever any TM is received from SML then if driver detects the IOC state
is in CoreDump state then it will wait for CoreDump state to be cleared and
will host reset operation.

Link: https://lore.kernel.org/r/20191226111333.26131-6-sreekanth.reddy@broadcom.com
Signed-off-by: Sreekanth Reddy <sreekanth.reddy@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

3 files changed, 91 insertions, 7 deletions

diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index b753cd63f341..0a1828391e3c 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -128,6 +128,10 @@ _base_wait_on_iocstate(struct MPT3SAS_ADAPTER *ioc,
 		u32 ioc_state, int timeout);
 static int
 _base_get_ioc_facts(struct MPT3SAS_ADAPTER *ioc);
+static void
+_base_mask_interrupts(struct MPT3SAS_ADAPTER *ioc);
+static void
+_base_clear_outstanding_commands(struct MPT3SAS_ADAPTER *ioc);
 
 /**
  * mpt3sas_base_check_cmd_timeout - Function
@@ -612,7 +616,8 @@ _base_fault_reset_work(struct work_struct *work)
 
 
 	spin_lock_irqsave(&ioc->ioc_reset_in_progress_lock, flags);
-	if (ioc->shost_recovery || ioc->pci_error_recovery)
+	if ((ioc->shost_recovery && (ioc->ioc_coredump_loop == 0)) ||
+			ioc->pci_error_recovery)
 		goto rearm_timer;
 	spin_unlock_irqrestore(&ioc->ioc_reset_in_progress_lock, flags);
 
@@ -659,20 +664,64 @@ _base_fault_reset_work(struct work_struct *work)
 		return; /* don't rearm timer */
 	}
 
-	ioc->non_operational_loop = 0;
+	if ((doorbell & MPI2_IOC_STATE_MASK) == MPI2_IOC_STATE_COREDUMP) {
+		u8 timeout = (ioc->manu_pg11.CoreDumpTOSec) ?
+		    ioc->manu_pg11.CoreDumpTOSec :
+		    MPT3SAS_DEFAULT_COREDUMP_TIMEOUT_SECONDS;
+
+		timeout /= (FAULT_POLLING_INTERVAL/1000);
+
+		if (ioc->ioc_coredump_loop == 0) {
+			mpt3sas_base_coredump_info(ioc,
+			    doorbell & MPI2_DOORBELL_DATA_MASK);
+			/* do not accept any IOs and disable the interrupts */
+			spin_lock_irqsave(
+			    &ioc->ioc_reset_in_progress_lock, flags);
+			ioc->shost_recovery = 1;
+			spin_unlock_irqrestore(
+			    &ioc->ioc_reset_in_progress_lock, flags);
+			_base_mask_interrupts(ioc);
+			_base_clear_outstanding_commands(ioc);
+		}
+
+		ioc_info(ioc, "%s: CoreDump loop %d.",
+		    __func__, ioc->ioc_coredump_loop);
+
+		/* Wait until CoreDump completes or times out */
+		if (ioc->ioc_coredump_loop++ < timeout) {
+			spin_lock_irqsave(
+			    &ioc->ioc_reset_in_progress_lock, flags);
+			goto rearm_timer;
+		}
+	}
 
+	if (ioc->ioc_coredump_loop) {
+		if ((doorbell & MPI2_IOC_STATE_MASK) != MPI2_IOC_STATE_COREDUMP)
+			ioc_err(ioc, "%s: CoreDump completed. LoopCount: %d",
+			    __func__, ioc->ioc_coredump_loop);
+		else
+			ioc_err(ioc, "%s: CoreDump Timed out. LoopCount: %d",
+			    __func__, ioc->ioc_coredump_loop);
+		ioc->ioc_coredump_loop = MPT3SAS_COREDUMP_LOOP_DONE;
+	}
+	ioc->non_operational_loop = 0;
 	if ((doorbell & MPI2_IOC_STATE_MASK) != MPI2_IOC_STATE_OPERATIONAL) {
 		rc = mpt3sas_base_hard_reset_handler(ioc, FORCE_BIG_HAMMER);
 		ioc_warn(ioc, "%s: hard reset: %s\n",
 			 __func__, rc == 0 ? "success" : "failed");
 		doorbell = mpt3sas_base_get_iocstate(ioc, 0);
-		if ((doorbell & MPI2_IOC_STATE_MASK) == MPI2_IOC_STATE_FAULT)
+		if ((doorbell & MPI2_IOC_STATE_MASK) == MPI2_IOC_STATE_FAULT) {
 			mpt3sas_base_fault_info(ioc, doorbell &
 			    MPI2_DOORBELL_DATA_MASK);
+		} else if ((doorbell & MPI2_IOC_STATE_MASK) ==
+		    MPI2_IOC_STATE_COREDUMP)
+			mpt3sas_base_coredump_info(ioc, doorbell &
+			    MPI2_DOORBELL_DATA_MASK);
 		if (rc && (doorbell & MPI2_IOC_STATE_MASK) !=
 		    MPI2_IOC_STATE_OPERATIONAL)
 			return; /* don't rearm timer */
 	}
+	ioc->ioc_coredump_loop = 0;
 
 	spin_lock_irqsave(&ioc->ioc_reset_in_progress_lock, flags);
  rearm_timer:
@@ -6815,9 +6864,19 @@ _base_make_ioc_ready(struct MPT3SAS_ADAPTER *ioc, enum reset_type type)
 	}
 
 	if ((ioc_state & MPI2_IOC_STATE_MASK) == MPI2_IOC_STATE_COREDUMP) {
-		mpt3sas_base_coredump_info(ioc, ioc_state &
-		    MPI2_DOORBELL_DATA_MASK);
-		mpt3sas_base_wait_for_coredump_completion(ioc, __func__);
+		/*
+		 * if host reset is invoked while watch dog thread is waiting
+		 * for IOC state to be changed to Fault state then driver has
+		 * to wait here for CoreDump state to clear otherwise reset
+		 * will be issued to the FW and FW move the IOC state to
+		 * reset state without copying the FW logs to coredump region.
+		 */
+		if (ioc->ioc_coredump_loop != MPT3SAS_COREDUMP_LOOP_DONE) {
+			mpt3sas_base_coredump_info(ioc, ioc_state &
+			    MPI2_DOORBELL_DATA_MASK);
+			mpt3sas_base_wait_for_coredump_completion(ioc,
+			    __func__);
+		}
 		goto issue_diag_reset;
 	}
 
@@ -7301,6 +7360,7 @@ mpt3sas_base_attach(struct MPT3SAS_ADAPTER *ioc)
 	    sizeof(struct mpt3sas_facts));
 
 	ioc->non_operational_loop = 0;
+	ioc->ioc_coredump_loop = 0;
 	ioc->got_task_abort_from_ioctl = 0;
 	return 0;
 
@@ -7591,7 +7651,9 @@ mpt3sas_base_hard_reset_handler(struct MPT3SAS_ADAPTER *ioc,
 	    MPT3_DIAG_BUFFER_IS_RELEASED))) {
 		is_trigger = 1;
 		ioc_state = mpt3sas_base_get_iocstate(ioc, 0);
-		if ((ioc_state & MPI2_IOC_STATE_MASK) == MPI2_IOC_STATE_FAULT)
+		if ((ioc_state & MPI2_IOC_STATE_MASK) == MPI2_IOC_STATE_FAULT ||
+		    (ioc_state & MPI2_IOC_STATE_MASK) ==
+		    MPI2_IOC_STATE_COREDUMP)
 			is_fault = 1;
 	}
 	_base_pre_reset_handler(ioc);
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h
index 3f453e74bf20..01eaaca9a844 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.h
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.h
@@ -92,6 +92,7 @@
 
 /* CoreDump: Default timeout */
 #define MPT3SAS_DEFAULT_COREDUMP_TIMEOUT_SECONDS	(15) /*15 seconds*/
+#define MPT3SAS_COREDUMP_LOOP_DONE                     (0xFF)
 
 /*
  * Set MPT3SAS_SG_DEPTH value based on user input.
@@ -1054,6 +1055,7 @@ typedef void (*MPT3SAS_FLUSH_RUNNING_CMDS)(struct MPT3SAS_ADAPTER *ioc);
  * @cpu_msix_table: table for mapping cpus to msix index
  * @cpu_msix_table_sz: table size
  * @total_io_cnt: Gives total IO count, used to load balance the interrupts
+ * @ioc_coredump_loop: will have non-zero value when FW is in CoreDump state
  * @high_iops_outstanding: used to load balance the interrupts
  *				within high iops reply queues
  * @msix_load_balance: Enables load balancing of interrupts across
@@ -1244,6 +1246,7 @@ struct MPT3SAS_ADAPTER {
 	u32		ioc_reset_count;
 	MPT3SAS_FLUSH_RUNNING_CMDS schedule_dead_ioc_flush_running_cmds;
 	u32             non_operational_loop;
+	u8              ioc_coredump_loop;
 	atomic64_t      total_io_cnt;
 	atomic64_t	high_iops_outstanding;
 	bool            msix_load_balance;
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index 9cc12f7ebf07..81711f2307a9 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -2749,6 +2749,12 @@ mpt3sas_scsih_issue_tm(struct MPT3SAS_ADAPTER *ioc, u16 handle, u64 lun,
 		    MPI2_DOORBELL_DATA_MASK);
 		rc = mpt3sas_base_hard_reset_handler(ioc, FORCE_BIG_HAMMER);
 		return (!rc) ? SUCCESS : FAILED;
+	} else if ((ioc_state & MPI2_IOC_STATE_MASK) ==
+	    MPI2_IOC_STATE_COREDUMP) {
+		mpt3sas_base_coredump_info(ioc, ioc_state &
+		    MPI2_DOORBELL_DATA_MASK);
+		rc = mpt3sas_base_hard_reset_handler(ioc, FORCE_BIG_HAMMER);
+		return (!rc) ? SUCCESS : FAILED;
 	}
 
 	smid = mpt3sas_base_get_smid_hpr(ioc, ioc->tm_cb_idx);
@@ -4525,6 +4531,7 @@ static void
 _scsih_temp_threshold_events(struct MPT3SAS_ADAPTER *ioc,
 	Mpi2EventDataTemperature_t *event_data)
 {
+	u32 doorbell;
 	if (ioc->temp_sensors_count >= event_data->SensorNum) {
 		ioc_err(ioc, "Temperature Threshold flags %s%s%s%s exceeded for Sensor: %d !!!\n",
 			le16_to_cpu(event_data->Status) & 0x1 ? "0 " : " ",
@@ -4534,6 +4541,18 @@ _scsih_temp_threshold_events(struct MPT3SAS_ADAPTER *ioc,
 			event_data->SensorNum);
 		ioc_err(ioc, "Current Temp In Celsius: %d\n",
 			event_data->CurrentTemperature);
+		if (ioc->hba_mpi_version_belonged != MPI2_VERSION) {
+			doorbell = mpt3sas_base_get_iocstate(ioc, 0);
+			if ((doorbell & MPI2_IOC_STATE_MASK) ==
+			    MPI2_IOC_STATE_FAULT) {
+				mpt3sas_base_fault_info(ioc,
+				    doorbell & MPI2_DOORBELL_DATA_MASK);
+			} else if ((doorbell & MPI2_IOC_STATE_MASK) ==
+			    MPI2_IOC_STATE_COREDUMP) {
+				mpt3sas_base_coredump_info(ioc,
+				    doorbell & MPI2_DOORBELL_DATA_MASK);
+			}
+		}
 	}
 }