Commit cbb01c2f authored Mar 31, 2020 by Arun Easi Committed by Martin K. Petersen Apr 24, 2020

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>

parent e304142c

drivers/scsi/qla2xxx/qla_attr.c

+27 −3

Original line number	Diff line number	Diff line
		@@ -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,

drivers/scsi/qla2xxx/qla_def.h

+12 −1

Original line number	Diff line number	Diff line
		@@ -3223,6 +3223,7 @@ struct isp_operations {
		uint32_t);

		void (fw_dump) (struct scsi_qla_host , int);
		void (mpi_fw_dump)(struct scsi_qla_host , int);

		int (beacon_on) (struct scsi_qla_host );
		int (beacon_off) (struct scsi_qla_host );
		@@ -3748,6 +3749,11 @@ struct qlt_hw_data {

		#define LEAK_EXCHG_THRESH_HOLD_PERCENT 75 /* 75 percent */

		struct qla_hw_data_stat {
		u32 num_fw_dump;
		u32 num_mpi_reset;
		};

		/*
		* Qlogic host adapter specific data structure.
		*/
		@@ -4230,7 +4236,6 @@ struct qla_hw_data {
		uint32_t fw_dump_len;
		u32 fw_dump_alloc_len;
		bool fw_dumped;
		bool fw_dump_mpi;
		unsigned long fw_dump_cap_flags;
		#define RISC_PAUSE_CMPL 0
		#define DMA_SHUTDOWN_CMPL 1
		@@ -4241,6 +4246,10 @@ struct qla_hw_data {
		#define ISP_MBX_RDY 6
		#define ISP_SOFT_RESET_CMPL 7
		int fw_dump_reading;
		void *mpi_fw_dump;
		u32 mpi_fw_dump_len;
		int mpi_fw_dump_reading:1;
		int mpi_fw_dumped:1;
		int prev_minidump_failed;
		dma_addr_t eft_dma;
		void *eft;
		@@ -4454,6 +4463,8 @@ struct qla_hw_data {
		uint16_t last_zio_threshold;

		#define DEFAULT_ZIO_THRESHOLD 5

		struct qla_hw_data_stat stat;
		};

		struct active_regions {

drivers/scsi/qla2xxx/qla_gbl.h

+3 −0

Original line number	Diff line number	Diff line
		@@ -173,6 +173,7 @@ extern int ql2xenablemsix;
		extern int qla2xuseresexchforels;
		extern int ql2xexlogins;
		extern int ql2xdifbundlinginternalbuffers;
		extern int ql2xfulldump_on_mpifail;

		extern int qla2x00_loop_reset(scsi_qla_host_t *);
		extern void qla2x00_abort_all_cmds(scsi_qla_host_t *, int);
		@@ -645,6 +646,7 @@ extern void qla82xx_fw_dump(scsi_qla_host_t *, int);
		extern void qla8044_fw_dump(scsi_qla_host_t *, int);

		extern void qla27xx_fwdump(scsi_qla_host_t *, int);
		extern void qla27xx_mpi_fwdump(scsi_qla_host_t *, int);
		extern ulong qla27xx_fwdt_calculate_dump_size(struct scsi_qla_host , void );
		extern int qla27xx_fwdt_template_valid(void *);
		extern ulong qla27xx_fwdt_template_size(void *);
		@@ -933,5 +935,6 @@ extern void qla24xx_process_purex_list(struct purex_list *);

		/* nvme.c */
		void qla_nvme_unregister_remote_port(struct fc_port *fcport);
		void qla27xx_reset_mpi(scsi_qla_host_t *vha);
		void qla_handle_els_plogi_done(scsi_qla_host_t vha, struct event_arg ea);
		#endif /* _QLA_GBL_H */

drivers/scsi/qla2xxx/qla_init.c

+2 −0

Original line number	Diff line number	Diff line
		@@ -3339,6 +3339,8 @@ qla2x00_alloc_fw_dump(scsi_qla_host_t *vha)
		dump_size / 1024);

		if (IS_QLA27XX(ha) \|\| IS_QLA28XX(ha)) {
		ha->mpi_fw_dump = (char *)fw_dump +
		ha->fwdt[1].dump_size;
		mutex_unlock(&ha->optrom_mutex);
		return;
		}

drivers/scsi/qla2xxx/qla_isr.c

+37 −17

Original line number	Diff line number	Diff line
		@@ -757,6 +757,39 @@ qla2x00_find_fcport_by_nportid(scsi_qla_host_t vha, port_id_t id,
		return NULL;
		}

		/* Shall be called only on supported adapters. */
		static void
		qla27xx_handle_8200_aen(scsi_qla_host_t vha, uint16_t mb)
		{
		struct qla_hw_data *ha = vha->hw;
		bool reset_isp_needed = 0;

		ql_log(ql_log_warn, vha, 0x02f0,
		"MPI Heartbeat stop. MPI reset is%s needed. "
		"MB0[%xh] MB1[%xh] MB2[%xh] MB3[%xh]\n",
		mb[0] & BIT_8 ? "" : " not",
		mb[0], mb[1], mb[2], mb[3]);

		if ((mb[1] & BIT_8) == 0)
		return;

		ql_log(ql_log_warn, vha, 0x02f1,
		"MPI Heartbeat stop. FW dump needed\n");

		if (ql2xfulldump_on_mpifail) {
		ha->isp_ops->fw_dump(vha, 1);
		reset_isp_needed = 1;
		}

		ha->isp_ops->mpi_fw_dump(vha, 1);

		if (reset_isp_needed) {
		vha->hw->flags.fw_init_done = 0;
		set_bit(ISP_ABORT_NEEDED, &vha->dpc_flags);
		qla2xxx_wake_dpc(vha);
		}
		}

		/**
		* qla2x00_async_event() - Process aynchronous events.
		* @vha: SCSI driver HA context
		@@ -872,9 +905,9 @@ qla2x00_async_event(scsi_qla_host_t vha, struct rsp_que rsp, uint16_t *mb)
		"ISP System Error - mbx1=%xh mbx2=%xh mbx3=%xh.\n ",
		mb[1], mb[2], mb[3]);

		ha->fw_dump_mpi =
		(IS_QLA27XX(ha) \|\| IS_QLA28XX(ha)) &&
		RD_REG_WORD(&reg24->mailbox7) & BIT_8;
		if ((IS_QLA27XX(ha) \|\| IS_QLA28XX(ha)) &&
		RD_REG_WORD(&reg24->mailbox7) & BIT_8)
		ha->isp_ops->mpi_fw_dump(vha, 1);
		ha->isp_ops->fw_dump(vha, 1);
		ha->flags.fw_init_done = 0;
		QLA_FW_STOPPED(ha);
		@@ -1375,20 +1408,7 @@ qla2x00_async_event(scsi_qla_host_t vha, struct rsp_que rsp, uint16_t *mb)

		case MBA_IDC_AEN:
		if (IS_QLA27XX(ha) \|\| IS_QLA28XX(ha)) {
		ha->flags.fw_init_done = 0;
		ql_log(ql_log_warn, vha, 0xffff,
		"MPI Heartbeat stop. Chip reset needed. MB0[%xh] MB1[%xh] MB2[%xh] MB3[%xh]\n",
		mb[0], mb[1], mb[2], mb[3]);

		if ((mb[1] & BIT_8) \|\|
		(mb[2] & BIT_8)) {
		ql_log(ql_log_warn, vha, 0xd013,
		"MPI Heartbeat stop. FW dump needed\n");
		ha->fw_dump_mpi = 1;
		ha->isp_ops->fw_dump(vha, 1);
		}
		set_bit(ISP_ABORT_NEEDED, &vha->dpc_flags);
		qla2xxx_wake_dpc(vha);
		qla27xx_handle_8200_aen(vha, mb);
		} else if (IS_QLA83XX(ha)) {
		mb[4] = RD_REG_WORD(&reg24->mailbox4);
		mb[5] = RD_REG_WORD(&reg24->mailbox5);