scsi: qla2xxx: Fix MPI failure AEN (8200) handling

Today, upon an MPI failure AEN, on top of collecting an MPI dump, a regular
firmware dump is also taken and then chip reset. This is disruptive to IOs
and not required. Make the firmware dump collection, followed by chip
reset, optional (not done by default).

Firmware dump buffer and MPI dump buffer are independent of each
other with this change and each can have dump that was taken at two
different times for two different issues. The MPI dump is saved in a
separate buffer and is retrieved differently from firmware dump.

To collect full dump on MPI failure AEN, a module parameter is
introduced:
    ql2xfulldump_on_mpifail (default: 0)

Link: https://lore.kernel.org/r/20200331104015.24868-2-njavali@marvell.com
Reported-by: kbuild test robot <lkp@intel.com>
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
Signed-off-by: Arun Easi <aeasi@marvell.com>
Signed-off-by: Nilesh Javali <njavali@marvell.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

1 files changed, 27 insertions, 3 deletions

diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c
index 97cabd7e0014..3a5f6f27587e 100644
--- a/drivers/scsi/qla2xxx/qla_attr.c
+++ b/drivers/scsi/qla2xxx/qla_attr.c
@@ -26,7 +26,8 @@ qla2x00_sysfs_read_fw_dump(struct file *filp, struct kobject *kobj,
 	struct qla_hw_data *ha = vha->hw;
 	int rval = 0;
 
-	if (!(ha->fw_dump_reading || ha->mctp_dump_reading))
+	if (!(ha->fw_dump_reading || ha->mctp_dump_reading ||
+	      ha->mpi_fw_dump_reading))
 		return 0;
 
 	mutex_lock(&ha->optrom_mutex);
@@ -42,6 +43,10 @@ qla2x00_sysfs_read_fw_dump(struct file *filp, struct kobject *kobj,
 	} else if (ha->mctp_dumped && ha->mctp_dump_reading) {
 		rval = memory_read_from_buffer(buf, count, &off, ha->mctp_dump,
 		    MCTP_DUMP_SIZE);
+	} else if (ha->mpi_fw_dumped && ha->mpi_fw_dump_reading) {
+		rval = memory_read_from_buffer(buf, count, &off,
+					       ha->mpi_fw_dump,
+					       ha->mpi_fw_dump_len);
 	} else if (ha->fw_dump_reading) {
 		rval = memory_read_from_buffer(buf, count, &off, ha->fw_dump,
 					ha->fw_dump_len);
@@ -103,7 +108,6 @@ qla2x00_sysfs_write_fw_dump(struct file *filp, struct kobject *kobj,
 			qla82xx_set_reset_owner(vha);
 			qla8044_idc_unlock(ha);
 		} else {
-			ha->fw_dump_mpi = 1;
 			qla2x00_system_error(vha);
 		}
 		break;
@@ -137,6 +141,22 @@ qla2x00_sysfs_write_fw_dump(struct file *filp, struct kobject *kobj,
 			    vha->host_no);
 		}
 		break;
+	case 8:
+		if (!ha->mpi_fw_dump_reading)
+			break;
+		ql_log(ql_log_info, vha, 0x70e7,
+		       "MPI firmware dump cleared on (%ld).\n", vha->host_no);
+		ha->mpi_fw_dump_reading = 0;
+		ha->mpi_fw_dumped = 0;
+		break;
+	case 9:
+		if (ha->mpi_fw_dumped && !ha->mpi_fw_dump_reading) {
+			ha->mpi_fw_dump_reading = 1;
+			ql_log(ql_log_info, vha, 0x70e8,
+			       "Raw MPI firmware dump ready for read on (%ld).\n",
+			       vha->host_no);
+		}
+		break;
 	}
 	return count;
 }
@@ -706,7 +726,8 @@ qla2x00_sysfs_write_reset(struct file *filp, struct kobject *kobj,
 		scsi_unblock_requests(vha->host);
 		break;
 	case 0x2025d:
-		if (!IS_QLA81XX(ha) && !IS_QLA83XX(ha))
+		if (!IS_QLA81XX(ha) && !IS_QLA83XX(ha) &&
+		    !IS_QLA27XX(ha) && !IS_QLA28XX(ha))
 			return -EPERM;
 
 		ql_log(ql_log_info, vha, 0x706f,
@@ -724,6 +745,8 @@ qla2x00_sysfs_write_reset(struct file *filp, struct kobject *kobj,
 			qla83xx_idc_audit(vha, IDC_AUDIT_TIMESTAMP);
 			qla83xx_idc_unlock(vha, 0);
 			break;
+		} else if (IS_QLA27XX(ha) || IS_QLA28XX(ha)) {
+			qla27xx_reset_mpi(vha);
 		} else {
 			/* Make sure FC side is not in reset */
 			WARN_ON_ONCE(qla2x00_wait_for_hba_online(vha) !=
@@ -737,6 +760,7 @@ qla2x00_sysfs_write_reset(struct file *filp, struct kobject *kobj,
 			scsi_unblock_requests(vha->host);
 			break;
 		}
+		break;
 	case 0x2025e:
 		if (!IS_P3P_TYPE(ha) || vha != base_vha) {
 			ql_log(ql_log_info, vha, 0x7071,