hinic: add some error messages for debug
Subsystems (3)
cover hinic: add some error messages for debug
patch #1: support to handle hw abnormal event
patch #2: improve the error messages when functions return failure and
dump relevant registers in some exception handling processes
Luo bin (2):
hinic: add support to handle hw abnormal event
hinic: add log in exception handling processes
.../ethernet/huawei/hinic/hinic_hw_api_cmd.c | 27 +- .../ethernet/huawei/hinic/hinic_hw_api_cmd.h | 4 + .../net/ethernet/huawei/hinic/hinic_hw_cmdq.c | 2 + .../net/ethernet/huawei/hinic/hinic_hw_cmdq.h | 2 + .../net/ethernet/huawei/hinic/hinic_hw_dev.c | 261 +++++++++++++++++- .../net/ethernet/huawei/hinic/hinic_hw_dev.h | 144 +++++++++- .../net/ethernet/huawei/hinic/hinic_hw_eqs.c | 39 +++ .../net/ethernet/huawei/hinic/hinic_hw_eqs.h | 4 + .../net/ethernet/huawei/hinic/hinic_hw_if.c | 23 ++ .../net/ethernet/huawei/hinic/hinic_hw_if.h | 2 + .../net/ethernet/huawei/hinic/hinic_hw_mbox.c | 2 + .../net/ethernet/huawei/hinic/hinic_hw_mgmt.c | 1 + .../net/ethernet/huawei/hinic/hinic_hw_mgmt.h | 4 + .../net/ethernet/huawei/hinic/hinic_main.c | 56 ++++ .../net/ethernet/huawei/hinic/hinic_port.c | 62 ++--- .../net/ethernet/huawei/hinic/hinic_port.h | 25 ++ .../net/ethernet/huawei/hinic/hinic_sriov.c | 6 +- 17 files changed, 616 insertions(+), 48 deletions(-)
Signature · 1 line
2.17.1
PATCH 1/2 hinic: add support to handle hw abnormal event
add support to handle hw abnormal event such as hardware failure, cable unplugged,link error
--- .../net/ethernet/huawei/hinic/hinic_hw_dev.c | 249 +++++++++++++++++- .../net/ethernet/huawei/hinic/hinic_hw_dev.h | 144 +++++++++- .../net/ethernet/huawei/hinic/hinic_hw_mgmt.h | 4 + .../net/ethernet/huawei/hinic/hinic_main.c | 56 ++++ .../net/ethernet/huawei/hinic/hinic_port.h | 25 ++ 5 files changed, 472 insertions(+), 6 deletions(-)
drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c +245 -4
@@ -621,6 +621,231 @@ static void nic_mgmt_msg_handler(void *handle, u8 cmd, void *buf_in, nic_cb->cb_state &= ~HINIC_CB_RUNNING ; } +static void hinic_comm_recv_mgmt_self_cmd_reg (struct hinic_pfhwdev *pfhwdev, +u8 cmd, +comm_mgmt_self_msg_proc proc) +{ +u8 cmd_idx; + + cmd_idx = pfhwdev->proc.cmd_num; +if (cmd_idx >=HINIC_COMM_SELF_CMD_MAX ) { +dev_err (&pfhwdev->hwdev.hwif->pdev->dev, +"Register recv mgmt process failed, cmd: 0x%x\n" , cmd); +return ; + } + + pfhwdev->proc.info[cmd_idx].cmd = cmd; + pfhwdev->proc.info[cmd_idx].proc = proc; + pfhwdev->proc.cmd_num++; +} + +static void hinic_comm_recv_mgmt_self_cmd_unreg (struct hinic_pfhwdev *pfhwdev, +u8 cmd) +{ +u8 cmd_idx; + + cmd_idx = pfhwdev->proc.cmd_num; +if (cmd_idx >=HINIC_COMM_SELF_CMD_MAX ) { +dev_err (&pfhwdev->hwdev.hwif->pdev->dev,"Unregister recv mgmt process failed, cmd: 0x%x\n" , + cmd); +return ; + } + +for (cmd_idx =0 ; cmd_idx <HINIC_COMM_SELF_CMD_MAX ; cmd_idx++) { +if (cmd == pfhwdev->proc.info[cmd_idx].cmd) { + pfhwdev->proc.info[cmd_idx].cmd =0 ; + pfhwdev->proc.info[cmd_idx].proc =NULL ; + pfhwdev->proc.cmd_num--; + } + } +} + +static void comm_mgmt_msg_handler (void *handle,u8 cmd,void *buf_in, +u16 in_size,void *buf_out,u16 *out_size) +{ +struct hinic_pfhwdev *pfhwdev = handle; +u8 cmd_idx; + +for (cmd_idx =0 ; cmd_idx < pfhwdev->proc.cmd_num; cmd_idx++) { +if (cmd == pfhwdev->proc.info[cmd_idx].cmd) { +if (!pfhwdev->proc.info[cmd_idx].proc) { +dev_warn (&pfhwdev->hwdev.hwif->pdev->dev, +"PF recv mgmt comm msg handle null, cmd: 0x%x\n" , + cmd); + }else { + pfhwdev->proc.info[cmd_idx].proc + (&pfhwdev->hwdev, buf_in, in_size, + buf_out, out_size); + } + +return ; + } + } + +dev_warn (&pfhwdev->hwdev.hwif->pdev->dev,"Received unknown mgmt cpu event: 0x%x\n" , + cmd); + + *out_size =0 ; +} + +static void chip_fault_show (struct hinic_hwdev *hwdev, +struct hinic_fault_event *event) +{ +char fault_level[FAULT_TYPE_MAX ][FAULT_SHOW_STR_LEN +1 ] = { +"fatal" ,"reset" ,"flr" ,"general" ,"suggestion" }; +char level_str[FAULT_SHOW_STR_LEN +1 ] = {0 }; +u8 level; + + level = event->event.chip.err_level; +if (level <FAULT_LEVEL_MAX ) +strncpy (level_str, fault_level[level], +FAULT_SHOW_STR_LEN ); +else +strncpy (level_str,"Unknown" ,FAULT_SHOW_STR_LEN ); + +if (level ==FAULT_LEVEL_SERIOUS_FLR ) +dev_err (&hwdev->hwif->pdev->dev,"err_level: %d [%s], flr func_id: %d\n" , + level, level_str, event->event.chip.func_id); + +dev_err (&hwdev->hwif->pdev->dev,"Module_id: 0x%x, err_type: 0x%x, err_level: %d[%s], err_csr_addr: 0x%08x, err_csr_value: 0x%08x\n" , + event->event.chip.node_id, + event->event.chip.err_type, level, level_str, + event->event.chip.err_csr_addr, + event->event.chip.err_csr_value); +} + +static void fault_report_show (struct hinic_hwdev *hwdev, +struct hinic_fault_event *event) +{ +char fault_type[FAULT_TYPE_MAX ][FAULT_SHOW_STR_LEN +1 ] = { +"chip" ,"ucode" ,"mem rd timeout" ,"mem wr timeout" , +"reg rd timeout" ,"reg wr timeout" ,"phy fault" }; +char type_str[FAULT_SHOW_STR_LEN +1 ] = {0 }; + +dev_err (&hwdev->hwif->pdev->dev,"Fault event report received, func_id: %d\n" , +HINIC_HWIF_FUNC_IDX (hwdev->hwif)); + +if (event->type <FAULT_TYPE_MAX ) +strncpy (type_str, fault_type[event->type],FAULT_SHOW_STR_LEN ); +else +strncpy (type_str,"Unknown" ,FAULT_SHOW_STR_LEN ); + +dev_err (&hwdev->hwif->pdev->dev,"Fault type: %d [%s]\n" , event->type, + type_str); +dev_err (&hwdev->hwif->pdev->dev,"Fault val[0]: 0x%08x, val[1]: 0x%08x, val[2]: 0x%08x, val[3]: 0x%08x\n" , + event->event.val[0 ], event->event.val[1 ], event->event.val[2 ], + event->event.val[3 ]); + +switch (event->type) { +case FAULT_TYPE_CHIP : +chip_fault_show (hwdev, event); +break ; +case FAULT_TYPE_UCODE : +dev_err (&hwdev->hwif->pdev->dev,"Cause_id: %d, core_id: %d, c_id: %d, epc: 0x%08x\n" , + event->event.ucode.cause_id, event->event.ucode.core_id, + event->event.ucode.c_id, event->event.ucode.epc); +break ; +case FAULT_TYPE_MEM_RD_TIMEOUT : +case FAULT_TYPE_MEM_WR_TIMEOUT : +dev_err (&hwdev->hwif->pdev->dev,"Err_csr_ctrl: 0x%08x, err_csr_data: 0x%08x, ctrl_tab: 0x%08x, mem_index: 0x%08x\n" , + event->event.mem_timeout.err_csr_ctrl, + event->event.mem_timeout.err_csr_data, + event->event.mem_timeout.ctrl_tab, + event->event.mem_timeout.mem_index); +break ; +case FAULT_TYPE_REG_RD_TIMEOUT : +case FAULT_TYPE_REG_WR_TIMEOUT : +dev_err (&hwdev->hwif->pdev->dev,"Err_csr: 0x%08x\n" , + event->event.reg_timeout.err_csr); +break ; +case FAULT_TYPE_PHY_FAULT : +dev_err (&hwdev->hwif->pdev->dev,"Op_type: %u, port_id: %u, dev_ad: %u, csr_addr: 0x%08x, op_data: 0x%08x\n" , + event->event.phy_fault.op_type, + event->event.phy_fault.port_id, + event->event.phy_fault.dev_ad, + event->event.phy_fault.csr_addr, + event->event.phy_fault.op_data); +break ; +default : +break ; + } +} + +/* pf fault report event */ +static void pf_fault_event_handler (void *hwdev,void *buf_in,u16 in_size, +void *buf_out,u16 *out_size) +{ +struct hinic_cmd_fault_event *fault_event = buf_in; + +fault_report_show (hwdev, &fault_event->event); +} + +static void mgmt_watchdog_timeout_event_handler (void *dev, +void *buf_in,u16 in_size, +void *buf_out,u16 *out_size) +{ +struct hinic_mgmt_watchdog_info *watchdog_info =NULL ; +struct hinic_hwdev *hwdev = dev; +u32 *dump_addr =NULL ; +u32 stack_len, i, j; +u32 *reg =NULL ; + +if (in_size !=sizeof (*watchdog_info)) { +dev_err (&hwdev->hwif->pdev->dev,"Invalid mgmt watchdog report, length: %d, should be %ld\n" , + in_size,sizeof (*watchdog_info)); +return ; + } + + watchdog_info = buf_in; + +dev_err (&hwdev->hwif->pdev->dev,"Mgmt deadloop time: 0x%x 0x%x, task id: 0x%x, sp: 0x%x\n" , + watchdog_info->curr_time_h, watchdog_info->curr_time_l, + watchdog_info->task_id, watchdog_info->sp); +dev_err (&hwdev->hwif->pdev->dev,"Stack current used: 0x%x, peak used: 0x%x, overflow flag: 0x%x, top: 0x%x, bottom: 0x%x\n" , + watchdog_info->curr_used, watchdog_info->peak_used, + watchdog_info->is_overflow, watchdog_info->stack_top, + watchdog_info->stack_bottom); + +dev_err (&hwdev->hwif->pdev->dev,"Mgmt pc: 0x%08x, lr: 0x%08x, cpsr:0x%08x\n" , + watchdog_info->pc, watchdog_info->lr, watchdog_info->cpsr); + +dev_err (&hwdev->hwif->pdev->dev,"Mgmt register info\n" ); + +for (i =0 ; i <3 ; i++) { + reg = watchdog_info->reg + (u64)(u32)(4 * i); +dev_err (&hwdev->hwif->pdev->dev,"0x%08x 0x%08x 0x%08x 0x%08x\n" , + *(reg), *(reg +1 ), *(reg +2 ), *(reg +3 )); + } + +dev_err (&hwdev->hwif->pdev->dev,"0x%08x\n" , watchdog_info->reg[12 ]); + +if (watchdog_info->stack_actlen <=1024 ) { + stack_len = watchdog_info->stack_actlen; + }else { +dev_err (&hwdev->hwif->pdev->dev,"Oops stack length: 0x%x is wrong\n" , + watchdog_info->stack_actlen); + stack_len =1024 ; + } + +dev_err (&hwdev->hwif->pdev->dev,"Mgmt dump stack, 16Bytes per line(start from sp)\n" ); +for (i =0 ; i < (stack_len /16 ); i++) { + dump_addr = (u32 *)(watchdog_info->data + ((u64)(u32)(i *16 ))); +dev_err (&hwdev->hwif->pdev->dev,"0x%08x 0x%08x 0x%08x 0x%08x\n" , + *dump_addr, *(dump_addr +1 ), *(dump_addr +2 ), + *(dump_addr +3 )); + } + +for (j =0 ; j < ((stack_len %16 ) /4 ); j++) { + dump_addr = (u32 *)(watchdog_info->data + + ((u64)(u32)(i *16 + j *4 ))); +dev_err (&hwdev->hwif->pdev->dev,"0x%08x " , *dump_addr); + } + + *out_size =sizeof (*watchdog_info); + watchdog_info = buf_out; + watchdog_info->status =0 ; +} +/** * init_pfhwdev - Initialize the extended components of PF * @pfhwdev: the HW device for PF
@@ -647,13 +872,22 @@ static int init_pfhwdev(struct hinic_pfhwdev *pfhwdev)return err; } -if (!HINIC_IS_VF (hwif)) +if (!HINIC_IS_VF (hwif)) {hinic_register_mgmt_msg_cb (&pfhwdev->pf_to_mgmt,HINIC_MOD_L2NIC , pfhwdev, nic_mgmt_msg_handler); -else +hinic_register_mgmt_msg_cb (&pfhwdev->pf_to_mgmt,HINIC_MOD_COMM , + pfhwdev, comm_mgmt_msg_handler); +hinic_comm_recv_mgmt_self_cmd_reg (pfhwdev, +HINIC_COMM_CMD_FAULT_REPORT , + pf_fault_event_handler); +hinic_comm_recv_mgmt_self_cmd_reg + (pfhwdev,HINIC_COMM_CMD_WATCHDOG_INFO , + mgmt_watchdog_timeout_event_handler); + }else {hinic_register_vf_mbox_cb (hwdev,HINIC_MOD_L2NIC , nic_mgmt_msg_handler); + }hinic_set_pf_action (hwif,HINIC_PF_MGMT_ACTIVE );
@@ -670,11 +904,18 @@ static void free_pfhwdev(struct hinic_pfhwdev *pfhwdev)hinic_set_pf_action (hwdev->hwif,HINIC_PF_MGMT_INIT ); -if (!HINIC_IS_VF (hwdev->hwif)) +if (!HINIC_IS_VF (hwdev->hwif)) { +hinic_comm_recv_mgmt_self_cmd_unreg (pfhwdev, +HINIC_COMM_CMD_WATCHDOG_INFO ); +hinic_comm_recv_mgmt_self_cmd_unreg (pfhwdev, +HINIC_COMM_CMD_FAULT_REPORT ); +hinic_unregister_mgmt_msg_cb (&pfhwdev->pf_to_mgmt, +HINIC_MOD_COMM );hinic_unregister_mgmt_msg_cb (&pfhwdev->pf_to_mgmt,HINIC_MOD_L2NIC ); -else + }else {hinic_unregister_vf_mbox_cb (hwdev,HINIC_MOD_L2NIC ); + }hinic_func_to_func_free (hwdev);
drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h +142 -2
169 lines not on this page · raw message
drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h +4 -0
@@ -81,6 +81,8 @@ enum hinic_comm_cmd {HINIC_COMM_CMD_MSI_CTRL_REG_WR_BY_UP ,HINIC_COMM_CMD_MSI_CTRL_REG_RD_BY_UP , +HINIC_COMM_CMD_FAULT_REPORT =0x37 , +HINIC_COMM_CMD_SET_LED_STATUS =0x4a , HINIC_COMM_CMD_L2NIC_RESET = 0x4b,
@@ -89,6 +91,8 @@ enum hinic_comm_cmd {HINIC_COMM_CMD_GET_BOARD_INFO =0x52 , +HINIC_COMM_CMD_WATCHDOG_INFO =0x56 , + HINIC_COMM_CMD_MAX, };
drivers/net/ethernet/huawei/hinic/hinic_main.c +56 -0
86 lines not on this page · raw message
drivers/net/ethernet/huawei/hinic/hinic_port.h +25 -0
@@ -189,6 +189,31 @@ struct hinic_port_link_status {u8 port_id; }; +struct hinic_cable_plug_event { +u8 status; +u8 version; +u8 rsvd0[6 ]; + +u16 func_id; +u8 plugged;/* 0: unplugged, 1: plugged */ +u8 port_id; +}; + +enum link_err_type { +LINK_ERR_MODULE_UNRECOGENIZED , +LINK_ERR_NUM , +}; + +struct hinic_link_err_event { +u8 status; +u8 version; +u8 rsvd0[6 ]; + +u16 func_id; +u8 err_type; +u8 port_id; +}; +struct hinic_port_func_state_cmd {u8 status;u8 version;
Signature · 1 line
2.17.1
kernel test robot
build botRe: [PATCH net-next 1/2] hinic: add support to handle hw abnormal event
Thank you for the patch! Perhaps something to improve:
Hi Luo,
Thank you for the patch! Perhaps something to improve:
[auto build test WARNING on net-next/master]
url: https://github.com/0day-ci/linux/commits/Luo-bin/hinic-add-some-error-messages-for-debug/20200716-205321 base: https://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next.git 59632b220f2d61df274ed3a14a204e941051fdad config: i386-allyesconfig (attached as .config) compiler: gcc-9 (Debian 9.3.0-14) 9.3.0 reproduce (this is a W=1 build): # save the attached .config to linux build tree make W=1 ARCH=i386
If you fix the issue, kindly add following tag as appropriate
All warnings (new ones prefixed by >>):
In file included from include/linux/device.h:15,
from include/linux/pci.h:37,
from drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c:9:
drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c: In function 'mgmt_watchdog_timeout_event_handler':
>> drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c:794:36: warning: format '%ld' expects argument of type 'long int', but argument 4 has type 'unsigned int' [-Wformat=]
794 | dev_err(&hwdev->hwif->pdev->dev, "Invalid mgmt watchdog report, length: %d, should be %ld\n",
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
include/linux/dev_printk.h:19:22: note: in definition of macro 'dev_fmt'
19 | #define dev_fmt(fmt) fmt
| ^~~
drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c:794:3: note: in expansion of macro 'dev_err'
794 | dev_err(&hwdev->hwif->pdev->dev, "Invalid mgmt watchdog report, length: %d, should be %ld\n",
| ^~~~~~~
drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c:794:91: note: format string is defined here
794 | dev_err(&hwdev->hwif->pdev->dev, "Invalid mgmt watchdog report, length: %d, should be %ld\n",
| ~~^
| |
| long int
| %dvim +794 drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
782
783 static void mgmt_watchdog_timeout_event_handler(void *dev,
784 void *buf_in, u16 in_size,
785 void *buf_out, u16 *out_size)
786 {
787 struct hinic_mgmt_watchdog_info *watchdog_info = NULL;
788 struct hinic_hwdev *hwdev = dev;
789 u32 *dump_addr = NULL;
790 u32 stack_len, i, j;
791 u32 *reg = NULL;
792
793 if (in_size != sizeof(*watchdog_info)) {
> 794 dev_err(&hwdev->hwif->pdev->dev, "Invalid mgmt watchdog report, length: %d, should be %ld\n",
795 in_size, sizeof(*watchdog_info));
796 return;
797 }
798
799 watchdog_info = buf_in;
800
801 dev_err(&hwdev->hwif->pdev->dev, "Mgmt deadloop time: 0x%x 0x%x, task id: 0x%x, sp: 0x%x\n",
802 watchdog_info->curr_time_h, watchdog_info->curr_time_l,
803 watchdog_info->task_id, watchdog_info->sp);
804 dev_err(&hwdev->hwif->pdev->dev, "Stack current used: 0x%x, peak used: 0x%x, overflow flag: 0x%x, top: 0x%x, bottom: 0x%x\n",
805 watchdog_info->curr_used, watchdog_info->peak_used,
806 watchdog_info->is_overflow, watchdog_info->stack_top,
807 watchdog_info->stack_bottom);
808
809 dev_err(&hwdev->hwif->pdev->dev, "Mgmt pc: 0x%08x, lr: 0x%08x, cpsr:0x%08x\n",
810 watchdog_info->pc, watchdog_info->lr, watchdog_info->cpsr);
811
812 dev_err(&hwdev->hwif->pdev->dev, "Mgmt register info\n");
813
814 for (i = 0; i < 3; i++) {
815 reg = watchdog_info->reg + (u64)(u32)(4 * i);
816 dev_err(&hwdev->hwif->pdev->dev, "0x%08x 0x%08x 0x%08x 0x%08x\n",
817 *(reg), *(reg + 1), *(reg + 2), *(reg + 3));
818 }
819
820 dev_err(&hwdev->hwif->pdev->dev, "0x%08x\n", watchdog_info->reg[12]);
821
822 if (watchdog_info->stack_actlen <= 1024) {
823 stack_len = watchdog_info->stack_actlen;
824 } else {
825 dev_err(&hwdev->hwif->pdev->dev, "Oops stack length: 0x%x is wrong\n",
826 watchdog_info->stack_actlen);
827 stack_len = 1024;
828 }
829
830 dev_err(&hwdev->hwif->pdev->dev, "Mgmt dump stack, 16Bytes per line(start from sp)\n");
831 for (i = 0; i < (stack_len / 16); i++) {
832 dump_addr = (u32 *)(watchdog_info->data + ((u64)(u32)(i * 16)));
833 dev_err(&hwdev->hwif->pdev->dev, "0x%08x 0x%08x 0x%08x 0x%08x\n",
834 *dump_addr, *(dump_addr + 1), *(dump_addr + 2),
835 *(dump_addr + 3));
836 }
837
838 for (j = 0; j < ((stack_len % 16) / 4); j++) {
839 dump_addr = (u32 *)(watchdog_info->data +
840 ((u64)(u32)(i * 16 + j * 4)));
841 dev_err(&hwdev->hwif->pdev->dev, "0x%08x ", *dump_addr);
842 }
843
844 *out_size = sizeof(*watchdog_info);
845 watchdog_info = buf_out;
846 watchdog_info->status = 0;
847 }
848
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all(a)lists.01.org
PATCH 2/2 hinic: add log in exception handling processes
In reply to Luo binimprove the error message when functions return failure and dump relevant registers in some exception handling processes
--- .../ethernet/huawei/hinic/hinic_hw_api_cmd.c | 27 +++++++- .../ethernet/huawei/hinic/hinic_hw_api_cmd.h | 4 ++ .../net/ethernet/huawei/hinic/hinic_hw_cmdq.c | 2 + .../net/ethernet/huawei/hinic/hinic_hw_cmdq.h | 2 + .../net/ethernet/huawei/hinic/hinic_hw_dev.c | 12 ++-- .../net/ethernet/huawei/hinic/hinic_hw_eqs.c | 39 ++++++++++++ .../net/ethernet/huawei/hinic/hinic_hw_eqs.h | 4 ++ .../net/ethernet/huawei/hinic/hinic_hw_if.c | 23 +++++++ .../net/ethernet/huawei/hinic/hinic_hw_if.h | 2 + .../net/ethernet/huawei/hinic/hinic_hw_mbox.c | 2 + .../net/ethernet/huawei/hinic/hinic_hw_mgmt.c | 1 + .../net/ethernet/huawei/hinic/hinic_port.c | 62 +++++++++---------- .../net/ethernet/huawei/hinic/hinic_sriov.c | 6 +- 13 files changed, 144 insertions(+), 42 deletions(-)
drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c +25 -2
@@ -112,6 +112,26 @@ static u32 get_hw_cons_idx(struct hinic_api_cmd_chain *chain)return HINIC_API_CMD_STATUS_GET (val,CONS_IDX ); } +static void dump_api_chain_reg (struct hinic_api_cmd_chain *chain) +{ +u32 addr, val; + + addr =HINIC_CSR_API_CMD_STATUS_ADDR (chain->chain_type); + val =hinic_hwif_read_reg (chain->hwif, addr); + +dev_err (&chain->hwif->pdev->dev,"Chain type: 0x%x, cpld error: 0x%x, check error: 0x%x, current fsm: 0x%x\n" , + chain->chain_type,HINIC_API_CMD_STATUS_GET (val,CPLD_ERR ), +HINIC_API_CMD_STATUS_GET (val,CHKSUM_ERR ), +HINIC_API_CMD_STATUS_GET (val,FSM )); + +dev_err (&chain->hwif->pdev->dev,"Chain hw current ci: 0x%x\n" , +HINIC_API_CMD_STATUS_GET (val,CONS_IDX )); + + addr =HINIC_CSR_API_CMD_CHAIN_PI_ADDR (chain->chain_type); + val =hinic_hwif_read_reg (chain->hwif, addr); +dev_err (&chain->hwif->pdev->dev,"Chain hw current pi: 0x%x\n" , val); +} +/** * chain_busy - check if the chain is still processing last requests * @chain: chain to check
@@ -131,8 +151,10 @@ static int chain_busy(struct hinic_api_cmd_chain *chain)/* check for a space for a new command */ if (chain->cons_idx ==MASKED_IDX (chain, prod_idx +1 )) { -dev_err (&pdev->dev,"API CMD chain %d is busy\n" , - chain->chain_type); +dev_err (&pdev->dev,"API CMD chain %d is busy, cons_idx: %d, prod_idx: %d\n" , + chain->chain_type, chain->cons_idx, + chain->prod_idx); +dump_api_chain_reg (chain);return -EBUSY ; }break ;
@@ -332,6 +354,7 @@ static int wait_for_api_cmd_completion(struct hinic_api_cmd_chain *chain) err =wait_for_status_poll (chain);if (err) {dev_err (&pdev->dev,"API CMD Poll status timeout\n" ); +dump_api_chain_reg (chain);break ; }break ;
drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.h +4 -0
@@ -103,10 +103,14 @@ HINIC_API_CMD_STATUS_HEADER_##member##_MASK)#define HINIC_API_CMD_STATUS_CONS_IDX_SHIFT 0 +#define HINIC_API_CMD_STATUS_FSM_SHIFT 24#define HINIC_API_CMD_STATUS_CHKSUM_ERR_SHIFT 28 +#define HINIC_API_CMD_STATUS_CPLD_ERR_SHIFT 30#define HINIC_API_CMD_STATUS_CONS_IDX_MASK 0xFFFFFF +#define HINIC_API_CMD_STATUS_FSM_MASK 0xFU#define HINIC_API_CMD_STATUS_CHKSUM_ERR_MASK 0x3 +#define HINIC_API_CMD_STATUS_CPLD_ERR_MASK 0x1U#define HINIC_API_CMD_STATUS_GET (val, member) \ (((val) >> HINIC_API_CMD_STATUS_##member##_SHIFT) & \
drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c +2 -0
@@ -401,6 +401,7 @@ static int cmdq_sync_cmd_direct_resp(struct hinic_cmdq *cmdq,spin_unlock_bh (&cmdq->cmdq_lock); +hinic_dump_ceq_info (cmdq->hwdev);return -ETIMEDOUT ; }
@@ -807,6 +808,7 @@ static int init_cmdqs_ctxt(struct hinic_hwdev *hwdev, cmdq_type =HINIC_CMDQ_SYNC ;for (; cmdq_type <HINIC_MAX_CMDQ_TYPES ; cmdq_type++) { + cmdqs->cmdq[cmdq_type].hwdev = hwdev; err =init_cmdq (&cmdqs->cmdq[cmdq_type], &cmdqs->saved_wqs[cmdq_type], cmdq_type, db_area[cmdq_type]);
drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.h +2 -0
@@ -130,6 +130,8 @@ struct hinic_cmdq_ctxt { };struct hinic_cmdq { +struct hinic_hwdev *hwdev; +struct hinic_wq *wq;enum hinic_cmdq_type cmdq_type;
drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c +6 -6
@@ -255,9 +255,9 @@ static int init_fw_ctxt(struct hinic_hwdev *hwdev) &fw_ctxt,sizeof (fw_ctxt), &fw_ctxt, &out_size);if (err || (out_size !=sizeof (fw_ctxt)) || fw_ctxt.status) { -dev_err (&pdev->dev,"Failed to init FW ctxt, ret = %d\n" , - fw_ctxt.status); -return -EFAULT ; +dev_err (&pdev->dev,"Failed to init FW ctxt, err: %d, status: 0x%x, out size: 0x%x\n" , + err, fw_ctxt.status, out_size); +return -EIO ; }return 0 ;
@@ -422,9 +422,9 @@ static int get_base_qpn(struct hinic_hwdev *hwdev, u16 *base_qpn) &cmd_base_qpn,sizeof (cmd_base_qpn), &cmd_base_qpn, &out_size);if (err || (out_size !=sizeof (cmd_base_qpn)) || cmd_base_qpn.status) { -dev_err (&pdev->dev,"Failed to get base qpn, status = %d\n" , - cmd_base_qpn.status); -return -EFAULT ; +dev_err (&pdev->dev,"Failed to get base qpn, err: %d, status: 0x%x, out size: 0x%x\n" , + err, cmd_base_qpn.status, out_size); +return -EIO ; } *base_qpn = cmd_base_qpn.qpn;
drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c +39 -0
@@ -953,3 +953,42 @@ void hinic_ceqs_free(struct hinic_ceqs *ceqs)for (q_id =0 ; q_id < ceqs->num_ceqs; q_id++)remove_eq (&ceqs->ceq[q_id]); } + +void hinic_dump_ceq_info (struct hinic_hwdev *hwdev) +{ +struct hinic_eq *eq =NULL ; +u32 addr, ci, pi; +int q_id; + +for (q_id =0 ; q_id < hwdev->func_to_io.ceqs.num_ceqs; q_id++) { + eq = &hwdev->func_to_io.ceqs.ceq[q_id]; + addr =EQ_CONS_IDX_REG_ADDR (eq); + ci =hinic_hwif_read_reg (hwdev->hwif, addr); + addr =EQ_PROD_IDX_REG_ADDR (eq); + pi =hinic_hwif_read_reg (hwdev->hwif, addr); +dev_err (&hwdev->hwif->pdev->dev,"Ceq id: %d, ci: 0x%08x, sw_ci: 0x%08x, pi: 0x%x, tasklet_state: 0x%lx, wrap: %d, ceqe: 0x%x\n" , + q_id, ci, eq->cons_idx, pi, + eq->ceq_tasklet.state, + eq->wrapped,be32_to_cpu (*(GET_CURR_CEQ_ELEM (eq)))); + } +} + +void hinic_dump_aeq_info (struct hinic_hwdev *hwdev) +{ +struct hinic_aeq_elem *aeqe_pos =NULL ; +struct hinic_eq *eq =NULL ; +u32 addr, ci, pi; +int q_id; + +for (q_id =0 ; q_id < hwdev->aeqs.num_aeqs; q_id++) { + eq = &hwdev->aeqs.aeq[q_id]; + addr =EQ_CONS_IDX_REG_ADDR (eq); + ci =hinic_hwif_read_reg (hwdev->hwif, addr); + addr =EQ_PROD_IDX_REG_ADDR (eq); + pi =hinic_hwif_read_reg (hwdev->hwif, addr); + aeqe_pos =GET_CURR_AEQ_ELEM (eq); +dev_err (&hwdev->hwif->pdev->dev,"Aeq id: %d, ci: 0x%08x, pi: 0x%x, work_state: 0x%x, wrap: %d, desc: 0x%x\n" , + q_id, ci, pi,work_busy (&eq->aeq_work.work), + eq->wrapped,be32_to_cpu (aeqe_pos->desc)); + } +}
drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.h +4 -0
@@ -254,4 +254,8 @@ int hinic_ceqs_init(struct hinic_ceqs *ceqs, struct hinic_hwif *hwif,void hinic_ceqs_free (struct hinic_ceqs *ceqs); +void hinic_dump_ceq_info (struct hinic_hwdev *hwdev); + +void hinic_dump_aeq_info (struct hinic_hwdev *hwdev); +#endif
drivers/net/ethernet/huawei/hinic/hinic_hw_if.c +23 -0
@@ -21,6 +21,8 @@#define WAIT_HWIF_READY_TIMEOUT 10000 +#define HINIC_SELFTEST_RESULT 0x883C +/** * hinic_msix_attr_set - set message attribute for msix entry * @hwif: the HW interface of a pci function device
@@ -369,6 +371,26 @@ u16 hinic_pf_id_of_vf_hw(struct hinic_hwif *hwif)return HINIC_FA0_GET (attr0,PF_IDX ); } +static void __print_selftest_reg (struct hinic_hwif *hwif) +{ +u32 addr, attr0, attr1; + + addr =HINIC_CSR_FUNC_ATTR1_ADDR ; + attr1 =hinic_hwif_read_reg (hwif, addr); + +if (attr1 ==HINIC_PCIE_LINK_DOWN ) { +dev_err (&hwif->pdev->dev,"PCIE is link down\n" ); +return ; + } + + addr =HINIC_CSR_FUNC_ATTR0_ADDR ; + attr0 =hinic_hwif_read_reg (hwif, addr); +if (HINIC_FA0_GET (attr0,FUNC_TYPE ) !=HINIC_VF && + !HINIC_FA0_GET (attr0,PCI_INTF_IDX )) +dev_err (&hwif->pdev->dev,"Selftest reg: 0x%08x\n" , +hinic_hwif_read_reg (hwif,HINIC_SELFTEST_RESULT )); +} +/** * hinic_init_hwif - initialize the hw interface * @hwif: the HW interface of a pci function device
@@ -398,6 +420,7 @@ int hinic_init_hwif(struct hinic_hwif *hwif, struct pci_dev *pdev) err =wait_hwif_ready (hwif);if (err) {dev_err (&pdev->dev,"HW interface is not ready\n" ); +__print_selftest_reg (hwif); goto err_hwif_ready; }
drivers/net/ethernet/huawei/hinic/hinic_hw_if.h +2 -0
@@ -12,6 +12,8 @@#include <linux/types.h> #include <asm/byteorder.h> +#define HINIC_PCIE_LINK_DOWN 0xFFFFFFFF +#define HINIC_DMA_ATTR_ST_SHIFT 0#define HINIC_DMA_ATTR_AT_SHIFT 8#define HINIC_DMA_ATTR_PH_SHIFT 10
drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c +2 -0
@@ -650,6 +650,7 @@ wait_for_mbox_seg_completion(struct hinic_mbox_func_to_func *func_to_func,if (!wait_for_completion_timeout (done, jif)) {dev_err (&hwdev->hwif->pdev->dev,"Send mailbox segment timeout\n" );dump_mox_reg (hwdev); +hinic_dump_aeq_info (hwdev);return -ETIMEDOUT ; }
@@ -897,6 +898,7 @@ int hinic_mbox_to_func(struct hinic_mbox_func_to_func *func_to_func,set_mbox_to_func_event (func_to_func,EVENT_TIMEOUT );dev_err (&func_to_func->hwif->pdev->dev,"Send mbox msg timeout, msg_id: %d\n" , msg_info.msg_id); +hinic_dump_aeq_info (func_to_func->hwdev); err = -ETIMEDOUT ; goto err_send_mbox; }
drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c +1 -0
@@ -274,6 +274,7 @@ static int msg_to_mgmt_sync(struct hinic_pf_to_mgmt *pf_to_mgmt,if (!wait_for_completion_timeout (recv_done, timeo)) {dev_err (&pdev->dev,"MGMT timeout, MSG id = %d\n" , msg_id); +hinic_dump_aeq_info (pf_to_mgmt->hwdev); err = -ETIMEDOUT ; goto unlock_sync_msg; }
drivers/net/ethernet/huawei/hinic/hinic_port.c +31 -31
135 lines not on this page · raw message
drivers/net/ethernet/huawei/hinic/hinic_sriov.c +3 -3
@@ -40,9 +40,9 @@ static int hinic_set_mac(struct hinic_hwdev *hwdev, const u8 *mac_addr,if (err || out_size !=sizeof (mac_info) || (mac_info.status && mac_info.status !=HINIC_PF_SET_VF_ALREADY && mac_info.status !=HINIC_MGMT_STATUS_EXIST )) { -dev_err (&hwdev->func_to_io.hwif->pdev->dev,"Failed to change MAC, ret = %d\n" , - mac_info.status); -return -EFAULT ; +dev_err (&hwdev->func_to_io.hwif->pdev->dev,"Failed to set MAC, err: %d, status: 0x%x, out size: 0x%x\n" , + err, mac_info.status, out_size); +return -EIO ; }return 0 ;
Signature · 1 line
2.17.1
Jakub Kicinski
maintainerRe: [PATCH net-next 2/2] hinic: add log in exception handling processes
Quoted 4 lines · On Thu, 16 Jul 2020 20:50:56 +0800 Luo bin wrote:
improve the error message when functions return failure and dump relevant registers in some exception handling processes
Signed-off-by Luo bin <[email protected]>
For kernel builds with W=1 C=1 flags this patch adds 12 warnings to drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c and 39 warnings to drivers/net/ethernet/huawei/hinic/hinic_hw_if.h.
It seems like you're missing byte swaps.
Re: [PATCH net-next 2/2] hinic: add log in exception handling processes
Quoted 4 lines · Jakub Kicinski
Quoted 3 lines · On Thu, 16 Jul 2020 20:50:56 +0800 Luo bin wrote:
improve the error message when functions return failure and dump relevant registers in some exception handling processes
Quoted 9 lines
Quoted 1 line
Signed-off-by Luo bin <[email protected]>For kernel builds with W=1 C=1 flags this patch adds 12 warnings to
drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.cand 39 warnings todrivers/net/ethernet/huawei/hinic/hinic_hw_if.h.It seems like you're missing byte swaps.
.
Will fix. Thank you!