From 13483730a13bef372894aefcf73760f5c6c297be Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Thu, 1 Dec 2011 21:38:41 -0600 Subject: [SCSI] qla4xxx: fix flash/ddb support With open-iscsi support, target entries persisted in the FLASH were not login. Added support in the qla4xxx driver to do the login on probe time to the target entries saved in the FLASH by user. With this changes upgrade to the new kernel with open-iscsi support in qla4xxx will ensure users original target entries login on driver load Signed-off-by: Manish Rangankar Signed-off-by: Ravi Anand Signed-off-by: Mike Christie Signed-off-by: James Bottomley --- drivers/scsi/qla4xxx/ql4_def.h | 55 ++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 53 insertions(+), 2 deletions(-) (limited to 'drivers/scsi/qla4xxx/ql4_def.h') diff --git a/drivers/scsi/qla4xxx/ql4_def.h b/drivers/scsi/qla4xxx/ql4_def.h index ace637bf254e..fd5edc6e166d 100644 --- a/drivers/scsi/qla4xxx/ql4_def.h +++ b/drivers/scsi/qla4xxx/ql4_def.h @@ -147,7 +147,7 @@ #define ISCSI_ALIAS_SIZE 32 /* ISCSI Alias name size */ #define ISCSI_NAME_SIZE 0xE0 /* ISCSI Name size */ -#define QL4_SESS_RECOVERY_TMO 30 /* iSCSI session */ +#define QL4_SESS_RECOVERY_TMO 120 /* iSCSI session */ /* recovery timeout */ #define LSDW(x) ((u32)((u64)(x))) @@ -173,6 +173,8 @@ #define ISNS_DEREG_TOV 5 #define HBA_ONLINE_TOV 30 #define DISABLE_ACB_TOV 30 +#define IP_CONFIG_TOV 30 +#define LOGIN_TOV 12 #define MAX_RESET_HA_RETRIES 2 @@ -240,6 +242,45 @@ struct ddb_entry { uint16_t fw_ddb_index; /* DDB firmware index */ uint32_t fw_ddb_device_state; /* F/W Device State -- see ql4_fw.h */ + uint16_t ddb_type; +#define FLASH_DDB 0x01 + + struct dev_db_entry fw_ddb_entry; + int (*unblock_sess)(struct iscsi_cls_session *cls_session); + int (*ddb_change)(struct scsi_qla_host *ha, uint32_t fw_ddb_index, + struct ddb_entry *ddb_entry, uint32_t state); + + /* Driver Re-login */ + unsigned long flags; /* DDB Flags */ + uint16_t default_relogin_timeout; /* Max time to wait for + * relogin to complete */ + atomic_t retry_relogin_timer; /* Min Time between relogins + * (4000 only) */ + atomic_t relogin_timer; /* Max Time to wait for + * relogin to complete */ + atomic_t relogin_retry_count; /* Num of times relogin has been + * retried */ + uint32_t default_time2wait; /* Default Min time between + * relogins (+aens) */ + +}; + +struct qla_ddb_index { + struct list_head list; + uint16_t fw_ddb_idx; + struct dev_db_entry fw_ddb; +}; + +#define DDB_IPADDR_LEN 64 + +struct ql4_tuple_ddb { + int port; + int tpgt; + char ip_addr[DDB_IPADDR_LEN]; + char iscsi_name[ISCSI_NAME_SIZE]; + uint16_t options; +#define DDB_OPT_IPV6 0x0e0e +#define DDB_OPT_IPV4 0x0f0f }; /* @@ -411,7 +452,7 @@ struct scsi_qla_host { #define AF_FW_RECOVERY 19 /* 0x00080000 */ #define AF_EEH_BUSY 20 /* 0x00100000 */ #define AF_PCI_CHANNEL_IO_PERM_FAILURE 21 /* 0x00200000 */ - +#define AF_BUILD_DDB_LIST 22 /* 0x00400000 */ unsigned long dpc_flags; #define DPC_RESET_HA 1 /* 0x00000002 */ @@ -604,6 +645,7 @@ struct scsi_qla_host { uint16_t bootload_minor; uint16_t bootload_patch; uint16_t bootload_build; + uint16_t def_timeout; /* Default login timeout */ uint32_t flash_state; #define QLFLASH_WAITING 0 @@ -623,6 +665,11 @@ struct scsi_qla_host { uint16_t iscsi_pci_func_cnt; uint8_t model_name[16]; struct completion disable_acb_comp; + struct dma_pool *fw_ddb_dma_pool; +#define DDB_DMA_BLOCK_SIZE 512 + uint16_t pri_ddb_idx; + uint16_t sec_ddb_idx; + int is_reset; }; struct ql4_task_data { @@ -835,6 +882,10 @@ static inline int ql4xxx_reset_active(struct scsi_qla_host *ha) /*---------------------------------------------------------------------------*/ /* Defines for qla4xxx_initialize_adapter() and qla4xxx_recover_adapter() */ + +#define INIT_ADAPTER 0 +#define RESET_ADAPTER 1 + #define PRESERVE_DDB_LIST 0 #define REBUILD_DDB_LIST 1 -- cgit v1.2.3 From 9ee91a38b1e224b0ee4ddc9a69d41f732d776310 Mon Sep 17 00:00:00 2001 From: Shyam Sunder Date: Thu, 1 Dec 2011 22:42:13 -0800 Subject: [SCSI] qla4xxx: check for FW alive before calling chip_reset Check for firmware alive and do premature completion of mbox commands in case of FW hung before doing chip_reset Signed-off-by: Shyam Sunder Reviewed-by: Mike Christie Signed-off-by: Nilesh Javali Signed-off-by: Vikas Chaudhary Signed-off-by: James Bottomley --- drivers/scsi/qla4xxx/ql4_def.h | 1 + drivers/scsi/qla4xxx/ql4_os.c | 75 ++++++++++++++++++++++++++++-------------- 2 files changed, 52 insertions(+), 24 deletions(-) (limited to 'drivers/scsi/qla4xxx/ql4_def.h') diff --git a/drivers/scsi/qla4xxx/ql4_def.h b/drivers/scsi/qla4xxx/ql4_def.h index fd5edc6e166d..22a3ff02e48a 100644 --- a/drivers/scsi/qla4xxx/ql4_def.h +++ b/drivers/scsi/qla4xxx/ql4_def.h @@ -177,6 +177,7 @@ #define LOGIN_TOV 12 #define MAX_RESET_HA_RETRIES 2 +#define FW_ALIVE_WAIT_TOV 3 #define CMD_SP(Cmnd) ((Cmnd)->SCp.ptr) diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c index 0c9ee9378094..70778d5227a9 100644 --- a/drivers/scsi/qla4xxx/ql4_os.c +++ b/drivers/scsi/qla4xxx/ql4_os.c @@ -1975,9 +1975,10 @@ mem_alloc_error_exit: * * Context: Interrupt **/ -static void qla4_8xxx_check_fw_alive(struct scsi_qla_host *ha) +static int qla4_8xxx_check_fw_alive(struct scsi_qla_host *ha) { - uint32_t fw_heartbeat_counter, halt_status; + uint32_t fw_heartbeat_counter; + int status = QLA_SUCCESS; fw_heartbeat_counter = qla4_8xxx_rd_32(ha, QLA82XX_PEG_ALIVE_COUNTER); /* If PEG_ALIVE_COUNTER is 0xffffffff, AER/EEH is in progress, ignore */ @@ -1985,7 +1986,7 @@ static void qla4_8xxx_check_fw_alive(struct scsi_qla_host *ha) DEBUG2(printk(KERN_WARNING "scsi%ld: %s: Device in frozen " "state, QLA82XX_PEG_ALIVE_COUNTER is 0xffffffff\n", ha->host_no, __func__)); - return; + return status; } if (ha->fw_heartbeat_counter == fw_heartbeat_counter) { @@ -1993,8 +1994,6 @@ static void qla4_8xxx_check_fw_alive(struct scsi_qla_host *ha) /* FW not alive after 2 seconds */ if (ha->seconds_since_last_heartbeat == 2) { ha->seconds_since_last_heartbeat = 0; - halt_status = qla4_8xxx_rd_32(ha, - QLA82XX_PEG_HALT_STATUS1); ql4_printk(KERN_INFO, ha, "scsi(%ld): %s, Dumping hw/fw registers:\n " @@ -2002,7 +2001,9 @@ static void qla4_8xxx_check_fw_alive(struct scsi_qla_host *ha) " 0x%x,\n PEG_NET_0_PC: 0x%x, PEG_NET_1_PC:" " 0x%x,\n PEG_NET_2_PC: 0x%x, PEG_NET_3_PC:" " 0x%x,\n PEG_NET_4_PC: 0x%x\n", - ha->host_no, __func__, halt_status, + ha->host_no, __func__, + qla4_8xxx_rd_32(ha, + QLA82XX_PEG_HALT_STATUS1), qla4_8xxx_rd_32(ha, QLA82XX_PEG_HALT_STATUS2), qla4_8xxx_rd_32(ha, QLA82XX_CRB_PEG_NET_0 + @@ -2015,24 +2016,13 @@ static void qla4_8xxx_check_fw_alive(struct scsi_qla_host *ha) 0x3c), qla4_8xxx_rd_32(ha, QLA82XX_CRB_PEG_NET_4 + 0x3c)); - - /* Since we cannot change dev_state in interrupt - * context, set appropriate DPC flag then wakeup - * DPC */ - if (halt_status & HALT_STATUS_UNRECOVERABLE) - set_bit(DPC_HA_UNRECOVERABLE, &ha->dpc_flags); - else { - printk("scsi%ld: %s: detect abort needed!\n", - ha->host_no, __func__); - set_bit(DPC_RESET_HA, &ha->dpc_flags); - } - qla4xxx_wake_dpc(ha); - qla4xxx_mailbox_premature_completion(ha); + status = QLA_ERROR; } } else ha->seconds_since_last_heartbeat = 0; ha->fw_heartbeat_counter = fw_heartbeat_counter; + return status; } /** @@ -2043,14 +2033,13 @@ static void qla4_8xxx_check_fw_alive(struct scsi_qla_host *ha) **/ void qla4_8xxx_watchdog(struct scsi_qla_host *ha) { - uint32_t dev_state; - - dev_state = qla4_8xxx_rd_32(ha, QLA82XX_CRB_DEV_STATE); + uint32_t dev_state, halt_status; /* don't poll if reset is going on */ if (!(test_bit(DPC_RESET_ACTIVE, &ha->dpc_flags) || test_bit(DPC_RESET_HA, &ha->dpc_flags) || test_bit(DPC_RETRY_RESET_HA, &ha->dpc_flags))) { + dev_state = qla4_8xxx_rd_32(ha, QLA82XX_CRB_DEV_STATE); if (dev_state == QLA82XX_DEV_NEED_RESET && !test_bit(DPC_RESET_HA, &ha->dpc_flags)) { if (!ql4xdontresethba) { @@ -2058,7 +2047,6 @@ void qla4_8xxx_watchdog(struct scsi_qla_host *ha) "NEED RESET!\n", __func__); set_bit(DPC_RESET_HA, &ha->dpc_flags); qla4xxx_wake_dpc(ha); - qla4xxx_mailbox_premature_completion(ha); } } else if (dev_state == QLA82XX_DEV_NEED_QUIESCENT && !test_bit(DPC_HA_NEED_QUIESCENT, &ha->dpc_flags)) { @@ -2068,7 +2056,24 @@ void qla4_8xxx_watchdog(struct scsi_qla_host *ha) qla4xxx_wake_dpc(ha); } else { /* Check firmware health */ - qla4_8xxx_check_fw_alive(ha); + if (qla4_8xxx_check_fw_alive(ha)) { + halt_status = qla4_8xxx_rd_32(ha, + QLA82XX_PEG_HALT_STATUS1); + + /* Since we cannot change dev_state in interrupt + * context, set appropriate DPC flag then wakeup + * DPC */ + if (halt_status & HALT_STATUS_UNRECOVERABLE) + set_bit(DPC_HA_UNRECOVERABLE, + &ha->dpc_flags); + else { + ql4_printk(KERN_INFO, ha, "%s: detect " + "abort needed!\n", __func__); + set_bit(DPC_RESET_HA, &ha->dpc_flags); + } + qla4xxx_mailbox_premature_completion(ha); + qla4xxx_wake_dpc(ha); + } } } } @@ -2424,6 +2429,7 @@ static int qla4xxx_recover_adapter(struct scsi_qla_host *ha) int status = QLA_ERROR; uint8_t reset_chip = 0; uint32_t dev_state; + unsigned long wait; /* Stall incoming I/O until we are done */ scsi_block_requests(ha->host); @@ -2474,8 +2480,29 @@ static int qla4xxx_recover_adapter(struct scsi_qla_host *ha) * or if stop_firmware fails for ISP-82xx. * This is the default case for ISP-4xxx */ if (!is_qla8022(ha) || reset_chip) { + if (!is_qla8022(ha)) + goto chip_reset; + + /* Check if 82XX firmware is alive or not + * We may have arrived here from NEED_RESET + * detection only */ + if (test_bit(AF_FW_RECOVERY, &ha->flags)) + goto chip_reset; + + wait = jiffies + (FW_ALIVE_WAIT_TOV * HZ); + while (time_before(jiffies, wait)) { + if (qla4_8xxx_check_fw_alive(ha)) { + qla4xxx_mailbox_premature_completion(ha); + break; + } + + set_current_state(TASK_UNINTERRUPTIBLE); + schedule_timeout(HZ); + } + if (!test_bit(AF_FW_RECOVERY, &ha->flags)) qla4xxx_cmd_wait(ha); +chip_reset: qla4xxx_process_aen(ha, FLUSH_DDB_CHANGED_AENS); qla4xxx_abort_active_cmds(ha, DID_RESET << 16); DEBUG2(ql4_printk(KERN_INFO, ha, -- cgit v1.2.3 From 4f77083ed0325ceb9cd5701c0f335583df3dded2 Mon Sep 17 00:00:00 2001 From: Mike Hernandez Date: Wed, 11 Jan 2012 02:44:15 -0800 Subject: [SCSI] qla4xxx: Temperature monitoring for ISP82XX core. During watchdog, need to monitor temperature of ISP82XX core and set device state to FAILED when temperature reaches "Panic" level. Signed-off-by: Mike Hernandez Signed-off-by: Vikas Chaudhary Reviewed-by: Mike Christie Signed-off-by: James Bottomley --- drivers/scsi/qla4xxx/ql4_def.h | 1 + drivers/scsi/qla4xxx/ql4_nx.h | 19 ++++++++++++++++--- drivers/scsi/qla4xxx/ql4_os.c | 42 +++++++++++++++++++++++++++++++++++++++++- 3 files changed, 58 insertions(+), 4 deletions(-) (limited to 'drivers/scsi/qla4xxx/ql4_def.h') diff --git a/drivers/scsi/qla4xxx/ql4_def.h b/drivers/scsi/qla4xxx/ql4_def.h index 22a3ff02e48a..ec48dc30b9a2 100644 --- a/drivers/scsi/qla4xxx/ql4_def.h +++ b/drivers/scsi/qla4xxx/ql4_def.h @@ -671,6 +671,7 @@ struct scsi_qla_host { uint16_t pri_ddb_idx; uint16_t sec_ddb_idx; int is_reset; + uint16_t temperature; }; struct ql4_task_data { diff --git a/drivers/scsi/qla4xxx/ql4_nx.h b/drivers/scsi/qla4xxx/ql4_nx.h index 35376a1c3f1b..cfb2f2edac3a 100644 --- a/drivers/scsi/qla4xxx/ql4_nx.h +++ b/drivers/scsi/qla4xxx/ql4_nx.h @@ -19,12 +19,25 @@ #define PHAN_PEG_RCV_INITIALIZED 0xff01 /*CRB_RELATED*/ -#define QLA82XX_CRB_BASE QLA82XX_CAM_RAM(0x200) -#define QLA82XX_REG(X) (QLA82XX_CRB_BASE+(X)) - +#define QLA82XX_CRB_BASE (QLA82XX_CAM_RAM(0x200)) +#define QLA82XX_REG(X) (QLA82XX_CRB_BASE+(X)) #define CRB_CMDPEG_STATE QLA82XX_REG(0x50) #define CRB_RCVPEG_STATE QLA82XX_REG(0x13c) #define CRB_DMA_SHIFT QLA82XX_REG(0xcc) +#define CRB_TEMP_STATE QLA82XX_REG(0x1b4) + +#define qla82xx_get_temp_val(x) ((x) >> 16) +#define qla82xx_get_temp_state(x) ((x) & 0xffff) +#define qla82xx_encode_temp(val, state) (((val) << 16) | (state)) + +/* + * Temperature control. + */ +enum { + QLA82XX_TEMP_NORMAL = 0x1, /* Normal operating range */ + QLA82XX_TEMP_WARN, /* Sound alert, temperature getting high */ + QLA82XX_TEMP_PANIC /* Fatal error, hardware has shut down. */ +}; #define QLA82XX_HW_H0_CH_HUB_ADR 0x05 #define QLA82XX_HW_H1_CH_HUB_ADR 0x0E diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c index 0048a3facd7a..9d3eab513935 100644 --- a/drivers/scsi/qla4xxx/ql4_os.c +++ b/drivers/scsi/qla4xxx/ql4_os.c @@ -1971,6 +1971,42 @@ mem_alloc_error_exit: return QLA_ERROR; } +/** + * qla4_8xxx_check_temp - Check the ISP82XX temperature. + * @ha: adapter block pointer. + * + * Note: The caller should not hold the idc lock. + **/ +static int qla4_8xxx_check_temp(struct scsi_qla_host *ha) +{ + uint32_t temp, temp_state, temp_val; + int status = QLA_SUCCESS; + + temp = qla4_8xxx_rd_32(ha, CRB_TEMP_STATE); + + temp_state = qla82xx_get_temp_state(temp); + temp_val = qla82xx_get_temp_val(temp); + + if (temp_state == QLA82XX_TEMP_PANIC) { + ql4_printk(KERN_WARNING, ha, "Device temperature %d degrees C" + " exceeds maximum allowed. Hardware has been shut" + " down.\n", temp_val); + status = QLA_ERROR; + } else if (temp_state == QLA82XX_TEMP_WARN) { + if (ha->temperature == QLA82XX_TEMP_NORMAL) + ql4_printk(KERN_WARNING, ha, "Device temperature %d" + " degrees C exceeds operating range." + " Immediate action needed.\n", temp_val); + } else { + if (ha->temperature == QLA82XX_TEMP_WARN) + ql4_printk(KERN_INFO, ha, "Device temperature is" + " now %d degrees C in normal range.\n", + temp_val); + } + ha->temperature = temp_state; + return status; +} + /** * qla4_8xxx_check_fw_alive - Check firmware health * @ha: Pointer to host adapter structure. @@ -2042,7 +2078,11 @@ void qla4_8xxx_watchdog(struct scsi_qla_host *ha) test_bit(DPC_RESET_HA, &ha->dpc_flags) || test_bit(DPC_RETRY_RESET_HA, &ha->dpc_flags))) { dev_state = qla4_8xxx_rd_32(ha, QLA82XX_CRB_DEV_STATE); - if (dev_state == QLA82XX_DEV_NEED_RESET && + + if (qla4_8xxx_check_temp(ha)) { + set_bit(DPC_HA_UNRECOVERABLE, &ha->dpc_flags); + qla4xxx_wake_dpc(ha); + } else if (dev_state == QLA82XX_DEV_NEED_RESET && !test_bit(DPC_RESET_HA, &ha->dpc_flags)) { if (!ql4xdontresethba) { ql4_printk(KERN_INFO, ha, "%s: HW State: " -- cgit v1.2.3 From 527c8b2e962d21baa38a96b22e1bf50a47fdf4fb Mon Sep 17 00:00:00 2001 From: Nilesh Javali Date: Wed, 11 Jan 2012 02:44:17 -0800 Subject: [SCSI] qla4xxx: Added error logging for firmware abort Added debug print with error code in case of firmware error. Signed-off-by: Nilesh Javali Signed-off-by: Vikas Chaudhary Reviewed-by: Mike Christie Signed-off-by: James Bottomley --- drivers/scsi/qla4xxx/ql4_def.h | 2 ++ drivers/scsi/qla4xxx/ql4_os.c | 7 +++++++ 2 files changed, 9 insertions(+) (limited to 'drivers/scsi/qla4xxx/ql4_def.h') diff --git a/drivers/scsi/qla4xxx/ql4_def.h b/drivers/scsi/qla4xxx/ql4_def.h index ec48dc30b9a2..bfe68545203f 100644 --- a/drivers/scsi/qla4xxx/ql4_def.h +++ b/drivers/scsi/qla4xxx/ql4_def.h @@ -150,6 +150,8 @@ #define QL4_SESS_RECOVERY_TMO 120 /* iSCSI session */ /* recovery timeout */ +#define MSB(x) ((uint8_t)((uint16_t)(x) >> 8)) +#define LSW(x) ((uint16_t)(x)) #define LSDW(x) ((u32)((u64)(x))) #define MSDW(x) ((u32)((((u64)(x)) >> 16) >> 16)) diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c index e2ef7762dc24..b75590af8ed3 100644 --- a/drivers/scsi/qla4xxx/ql4_os.c +++ b/drivers/scsi/qla4xxx/ql4_os.c @@ -2112,6 +2112,13 @@ void qla4_8xxx_watchdog(struct scsi_qla_host *ha) halt_status = qla4_8xxx_rd_32(ha, QLA82XX_PEG_HALT_STATUS1); + if (LSW(MSB(halt_status)) == 0x67) + ql4_printk(KERN_ERR, ha, "%s:" + " Firmware aborted with" + " error code 0x00006700." + " Device is being reset\n", + __func__); + /* Since we cannot change dev_state in interrupt * context, set appropriate DPC flag then wakeup * DPC */ -- cgit v1.2.3