2 files changed, 30 insertions, 4 deletions

diff --git a/drivers/scsi/mpt3sas/mpt3sas_ctl.c b/drivers/scsi/mpt3sas/mpt3sas_ctl.c
index 87784c96249a..47faa27bc355 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_ctl.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_ctl.c
@@ -679,6 +679,7 @@ _ctl_do_mpt_command(struct MPT3SAS_ADAPTER *ioc, struct mpt3_ioctl_command karg,
 	size_t data_in_sz = 0;
 	long ret;
 	u16 device_handle = MPT3SAS_INVALID_DEVICE_HANDLE;
+	int tm_ret;
 
 	issue_reset = 0;
 
@@ -1120,18 +1121,25 @@ _ctl_do_mpt_command(struct MPT3SAS_ADAPTER *ioc, struct mpt3_ioctl_command karg,
 			if (pcie_device && (!ioc->tm_custom_handling) &&
 			    (!(mpt3sas_scsih_is_pcie_scsi_device(
 			    pcie_device->device_info))))
-				mpt3sas_scsih_issue_locked_tm(ioc,
+				tm_ret = mpt3sas_scsih_issue_locked_tm(ioc,
 				  le16_to_cpu(mpi_request->FunctionDependent1),
 				  0, 0, 0,
 				  MPI2_SCSITASKMGMT_TASKTYPE_TARGET_RESET, 0,
 				  0, pcie_device->reset_timeout,
 			MPI26_SCSITASKMGMT_MSGFLAGS_PROTOCOL_LVL_RST_PCIE);
 			else
-				mpt3sas_scsih_issue_locked_tm(ioc,
+				tm_ret = mpt3sas_scsih_issue_locked_tm(ioc,
 				  le16_to_cpu(mpi_request->FunctionDependent1),
 				  0, 0, 0,
 				  MPI2_SCSITASKMGMT_TASKTYPE_TARGET_RESET, 0,
 				  0, 30, MPI2_SCSITASKMGMT_MSGFLAGS_LINK_RESET);
+
+			if (tm_ret != SUCCESS) {
+				ioc_info(ioc,
+					 "target reset failed, issue hard reset: handle (0x%04x)\n",
+					 le16_to_cpu(mpi_request->FunctionDependent1));
+				mpt3sas_base_hard_reset_handler(ioc, FORCE_BIG_HAMMER);
+			}
 		} else
 			mpt3sas_base_hard_reset_handler(ioc, FORCE_BIG_HAMMER);
 	}
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index 9599d7a50028..9719da76461c 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -195,6 +195,14 @@ struct sense_info {
 #define MPT3SAS_PORT_ENABLE_COMPLETE (0xFFFD)
 #define MPT3SAS_ABRT_TASK_SET (0xFFFE)
 #define MPT3SAS_REMOVE_UNRESPONDING_DEVICES (0xFFFF)
+
+/*
+ * SAS Log info code for a NCQ collateral abort after an NCQ error:
+ * IOC_LOGINFO_PREFIX_PL | PL_LOGINFO_CODE_SATA_NCQ_FAIL_ALL_CMDS_AFTR_ERR
+ * See: drivers/message/fusion/lsi/mpi_log_sas.h
+ */
+#define IOC_LOGINFO_SATA_NCQ_FAIL_AFTER_ERR	0x31080000
+
 /**
  * struct fw_event_work - firmware event struct
  * @list: link list framework
@@ -5814,6 +5822,17 @@ _scsih_io_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply)
 			scmd->result = DID_TRANSPORT_DISRUPTED << 16;
 			goto out;
 		}
+		if (log_info == IOC_LOGINFO_SATA_NCQ_FAIL_AFTER_ERR) {
+			/*
+			 * This is a ATA NCQ command aborted due to another NCQ
+			 * command failure. We must retry this command
+			 * immediately but without incrementing its retry
+			 * counter.
+			 */
+			WARN_ON_ONCE(xfer_cnt != 0);
+			scmd->result = DID_IMM_RETRY << 16;
+			break;
+		}
 		if (log_info == 0x31110630) {
 			if (scmd->retries > 2) {
 				scmd->result = DID_NO_CONNECT << 16;
@@ -10790,8 +10809,7 @@ _mpt3sas_fw_work(struct MPT3SAS_ADAPTER *ioc, struct fw_event_work *fw_event)
 		break;
 	case MPI2_EVENT_PCIE_TOPOLOGY_CHANGE_LIST:
 		_scsih_pcie_topology_change_event(ioc, fw_event);
-		ioc->current_event = NULL;
-		return;
+		break;
 	}
 out:
 	fw_event_work_put(fw_event);