@traceback 使用2023042819-coolpi-4b-android镜像，会卡死在I/TC: Secondary CPU 7 switching to normal world boot

@george 你好，问题还是这样，有的时候卡死，有的时候无限重启，我买了新的读卡器和闪迪的SD卡，并且对SD卡进行了格式化，log如下：

Device 0: unknown device
switch to partitions #0, OK
mmc1 is current device
Scanning mmc 1:1...
Found /extlinux/extlinux.conf
Retrieving file: /extlinux/extlinux.conf
reading /extlinux/extlinux.conf
434 bytes read in 7 ms (60.5 KiB/s)
1:      Android coolpi
Retrieving file: /initrd.img
reading /initrd.img
13538757 bytes read in 1089 ms (11.9 MiB/s)
Retrieving file: /Image
reading /Image
38920200 bytes read in 3122 ms (11.9 MiB/s)
append: androidboot.mode=normal androidboot.serialno=9572efc46eee3f67 console=ttyS0,115200 firmware_class.path=/vendor/etc/firmware init=/init rootwait ro loop.max_part=7 androidboot.wificountrycode=CN androidboot.hardware=rk30board androidboot.boot_devices=fe2e0000.mmc androidboot.selinux=permissive irqchip.gicv3_pseudo_nmi=0 rtleth=ethaddr:22:6e:92:0d:db:66
Retrieving file: /rk3588s-cp4.dtb
reading /rk3588s-cp4.dtb
225093 bytes read in 24 ms (8.9 MiB/s)
## Flattened Device Tree blob at 0x0a100000
   Booting using the fdt blob at 0x0a100000
  'reserved-memory' ramoops@110000: addr=110000 size=e0000
   Loading Ramdisk to eacea000, end eb9d35c5 ... OK
   Loading Device Tree to 00000000eacb0000, end 00000000eace9f44 ... OK
Card did not respond to voltage select!
mmc_init: -95, time 17
Card did not respond to voltage select!
mmc_init: -95, time 16
** Bad device mmc 0 **
switch to partitions #0, OK
mmc1 is current device
** Unable to read file logo_kernel.bmp **
Card did not respond to voltage select!
mmc_init: -95, time 17
Card did not respond to voltage select!
mmc_init: -95, time 17
** Bad device mmc 0 **
switch to partitions #0, OK
mmc1 is current device
** Unable to read file logo_kernel.bmp **
Adding bank: 0x00200000 - 0x08400000 (size: 0x08200000)
Adding bank: 0x09400000 - 0xf0000000 (size: 0xe6c00000)
Adding bank: 0x100000000 - 0x200000000 (size: 0x100000000)
Adding bank: 0x2f0000000 - 0x300000000 (size: 0x10000000)
......
[   18.914489][    T7] combophy_avdd0v85: supplied by vdd_0v85_s0
[   18.914743][  T165] mali fb000000.gpu: Kernel DDK version g13p0-01eac0
[   18.921218][    T7] combophy_avdd1v8: supplied by avcc_1v8_s0
[   18.927539][  T165] mali fb000000.gpu: leakage=14
[   18.935651][    T7] vcc_mipidphy0: supplied by vcc_3v3_s3
[   18.937364][  T165] debugfs: Directory 'fb000000.gpu-mali' with parent 'vdd_gpu_s0' already present!
[   18.950906][    T7] vcc3v3_lcd0_n: supplied by vcc_3v3_s0
[   18.953473][  T165] mali fb000000.gpu: pvtm=859
[   18.960490][    T7] vcc_3v3_sd_s0: supplied by vcc_3v3_s3
[   18.964960][  T165] mali fb000000.gpu: pvtm-volt-sel=2
[   18.973526][  T165] mali fb000000.gpu: avs=0
[   18.973729][    T7] rockchip-vop2 fdd90000.vop: [drm:vop2_bind] vp0 assign plane mask: 0x5, primary plane phy id: 2
[   18.980417][  T165] W : [File] : drivers/gpu/arm/bifrost/platform/rk/mali_kbase_config_rk.c; [Line] : 136; [Func] : kbase_platform_rk_init(); power-off-delay-ms not available.
[   18.988343][    T7] rockchip-vop2 fdd90000.vop: [drm:vop2_bind] vp1 assign plane mask: 0xa, primary plane phy id: 3
[   19.005393][  T165] mali fb000000.gpu: GPU hardware issue table may need updating:
[   19.005393][  T165] r0p0 status 5 is unknown; treating as r0p0 status 0
[   19.014368][    T7] rockchip-vop2 fdd90000.vop: [drm:vop2_bind] vp2 assign plane mask: 0x140, primary plane phy id: 8
[   19.028533][  T165] mali fb000000.gpu: GPU identified as 0x7 arch 10.8.6 r0p0 status 0
[   19.039113][    T7] rockchip-vop2 fdd90000.vop: [drm:vop2_bind] vp3 assign plane mask: 0x280, primary plane phy id: 9
[   19.047048][  T165] mali fb000000.gpu: No priority control manager is configured
[   19.057596][    T7] rockchip-drm display-subsystem: failed to get hdmi0_phy_pll: -2
[   19.064985][  T165] mali fb000000.gpu: No memory group manager is configured
[   19.072619][    T7] rockchip-drm display-subsystem: failed to get hdmi1_phy_pll: -2
[   19.079672][  T165] mali fb000000.gpu: Protected memory allocator not available
[   19.095418][  T165] mali fb000000.gpu: Capping CSF_FIRMWARE_TIMEOUT to CSF_FIRMWARE_PING_TIMEOUT
[   19.099506][    T7] rockchip-drm display-subsystem: bound fdd90000.vop (ops vop2_component_ops)
[   19.104838][  T165] mali fb000000.gpu: Couldn't find power_model DT node matching 'arm,mali-simple-power-model'
[   19.114748][    T7] dwhdmi-rockchip fde80000.hdmi: registered ddc I2C bus driver
[   19.122965][  T165] mali fb000000.gpu: Error -22, no DT entry: mali-simple-power-model.static-coefficient = 1*[0]
[   19.130580][    T7] rockchip-drm display-subsystem: bound fde80000.hdmi (ops dw_hdmi_rockchip_ops)
[   19.140734][  T165] mali fb000000.gpu: Error -22, no DT entry: mali-simple-power-model.dynamic-coefficient = 1*[0]
[   19.149573][    T7] rockchip-drm display-subsystem: bound fde20000.dsi (ops dw_mipi_dsi2_ops)
[   19.160003][  T165] mali fb000000.gpu: Error -22, no DT entry: mali-simple-power-model.ts = 4*[0]
[   19.168438][    T7] rockchip-drm display-subsystem: bound fde50000.dp (ops dw_dp_component_ops)
[   19.177344][  T165] mali fb000000.gpu: Error -22, no DT entry: mali-simple-power-model.thermal-zone = ''
[   19.186998][    T7] rockchip-drm display-subsystem: route-dsi0: failed to get logo,offset
[   19.196941][  T165] mali fb000000.gpu: Using configured power model mali-lodx-power-model, and fallback mali-simple-power-model
[   19.203631][    T7] rockchip-drm display-subsystem: connector[HDMI-A-1] can't found any modes
[   19.215090][  T165] mali fb000000.gpu: l=10000 h=85000 hyst=5000 l_limit=0 h_limit=800000000 h_table=0
[   19.223542][    T7] rockchip-drm display-subsystem: can't not find any logo display
[   19.240476][    T7] rockchip-drm display-subsystem: failed to show kernel logo
[   19.248932][    T7] rockchip-drm display-subsystem: [drm] fb0: rockchipdrmfb frame buffer device
[   19.253405][  T165] mali fb000000.gpu: Probed as mali0
[   19.263466][    T7] [drm] Initialized rockchip 3.0.0 20140818 for display-subsystem on minor 0
[   19.272254][    T7] input: adc-keys as /devices/platform/adc-keys/input/input1
[   19.280578][    T7] debugfs: File 'Capture' in directory 'dapm' already present!
[   19.347784][  T165] dwmmc_rockchip fe2c0000.mmc: IDMAC supports 32-bit address mode.
[   19.348504][    T1] rkcif rkcif-mipi-lvds2: clear unready subdev num: 1
[   19.355569][  T165] dwmmc_rockchip fe2c0000.mmc: Using internal DMA controller.
[   19.362170][    T1] rockchip-csi2-dphy0: No link between dphy and sensor
[   19.369473][  T165] dwmmc_rockchip fe2c0000.mmc: Version ID is 270a
[   19.376298][    T1] rockchip-csi2-dphy0: No link between dphy and sensor
[   19.382434][  T165] dwmmc_rockchip fe2c0000.mmc: DW MMC controller at irq 80,32 bit host data width,256 deep fifo
[   19.389098][    T1] rkcif-mipi-lvds2: rkcif_update_sensor_info: stream[0] get remote terminal sensor failed!
[   19.389102][    T1] rkcif-mipi-lvds2: Async subdev notifier completed
[   19.412646][  T165] mmc_host mmc2: Bus speed (slot 0) = 400000Hz (slot req 400000Hz, actual 400000HZ div = 0)
[   19.415579][    T1] rockchip-csi2-dphy0: No link between dphy and sensor
[   19.415585][    T1] rkcif-mipi-lvds2: rkcif_update_sensor_info: stream[0] get remote terminal sensor failed!
[   19.441973][    T1] rkcif-mipi-lvds2: There is not terminal subdev, not synchronized with ISP
[   19.450545][  T181] rockchip-csi2-dphy0: No link between dphy and sensor
[   19.450978][    T1] RKNPU fdab0000.npu: Adding to iommu group 0
[   19.457269][  T181] rkcif-mipi-lvds2: rkcif_update_sensor_info: stream[0] get remote terminal sensor failed!
[   19.463222][    T1] RKNPU fdab0000.npu: RKNPU: rknpu iommu is enabled, using iommu mode
[   19.472984][  T181] rkcif-mipi-lvds2: There is not terminal subdev, not synchronized with ISP
[   19.492334][    T1] RKNPU fdab0000.npu: can't request region for resource [mem 0xfdab0000-0xfdabffff]
[   19.501553][    T1] RKNPU fdab0000.npu: can't request region for resource [mem 0xfdac0000-0xfdacffff]
[   19.510759][    T1] RKNPU fdab0000.npu: can't request region for resource [mem 0xfdad0000-0xfdadffff]
[   19.520096][    T1] [drm] Initialized rknpu 0.8.2 20220829 for fdab0000.npu on minor 1
[   19.522504][  T172] mmc_host mmc2: Bus speed (slot 0) = 148500000Hz (slot req 150000000Hz, actual 148500000HZ div = 0)
[   19.531219][    T1] RKNPU fdab0000.npu: leakage=7
[   19.543419][    T1] debugfs: Directory 'fdab0000.npu-rknpu' with parent 'vdd_npu_s0' already present!
[   19.559146][    T1] RKNPU fdab0000.npu: pvtm=871
[   19.560277][  T172] dwmmc_rockchip fe2c0000.mmc: Successfully tuned phase to 135
[   19.570375][    T1] RKNPU fdab0000.npu: pvtm-volt-sel=3
[   19.571173][  T172] mmc2: new ultra high speed SDR104 SDXC card at address aaaa
[   19.576605][    T1] RKNPU fdab0000.npu: avs=0
[   19.584318][  T172] mmcblk2: mmc2:aaaa SR64G 59.5 GiB
[   19.588080][    T1] RKNPU fdab0000.npu: l=10000 h=85000 hyst=5000 l_limit=0 h_limit=800000000 h_table=0
[   19.599272][  T172]  mmcblk2: p1 p2 p3 p4 p5 p6 p7 p8 p9 p10
[   19.631946][    T1] RKNPU fdab0000.npu: failed to find power_model node
[   19.638561][    T1] RKNPU fdab0000.npu: RKNPU: failed to initialize power model
[   19.645865][    T1] RKNPU fdab0000.npu: RKNPU: failed to get dynamic-coefficient
[   19.653876][    T1] cfg80211: Loading compiled-in X.509 certificates for regulatory database
[   19.663497][    T1] cfg80211: Loaded X.509 cert 'sforshee: 00b28ddf47aef9cea7'
[   19.670755][  T138] platform regulatory.0: Direct firmware load for regulatory.db failed with error -2
[   19.680057][  T138] cfg80211: failed to load regulatory.db
[   19.686056][    T1] rockchip-pm rockchip-suspend: not set pwm-regulator-config
[   19.693591][    T1] I : [File] : drivers/gpu/arm/mali400/mali/linux/mali_kernel_linux.c; [Line] : 409; [Func] : mali_module_init(); svn_rev_string_from_arm of this mali_ko is '', rk_ko_ver is '5', built at '18:43:18', on 'May 17 2023'.
[   19.714508][    T1] Mali:
[   19.714509][    T1] Mali device driver loaded
[   19.721558][    T1] rkisp rkisp0-vir0: clear unready subdev num: 1
[   19.727842][    T1] rkisp0-vir0: Async subdev notifier completed
[   19.733838][    T1] ALSA device list:
[   19.737493][    T1]   #0: rockchip,hdmi0
[   19.741405][    T1]   #1: rockchip,es8316-codec
[   19.745970][    T1] dw-apb-uart feb50000.serial: forbid DMA for kernel console
[   19.753392][    T1] Freeing unused kernel memory: 1344K
[   19.764203][    T1] Run /init as init process
wait for device.
0x5344
[   19.919481][  T250] Set signal voltage to initial state
[   19.925076][  T250] rk860-regulator 2-0042: rk860..... reset
[   19.931741][  T250] rk860-regulator 2-0042: force rk860x_reset ok!
[   19.937936][  T250] rk860-regulator 0-0043: rk860..... reset
[   19.944591][  T250] rk860-regulator 0-0043: force rk860x_reset ok!
[   19.950786][  T250] rk860-regulator 0-0042: rk860..... reset
[   19.957441][  T250] rk860-regulator 0-0042: force rk860x_reset ok!
[   19.968899][  T250] mpp_av1dec av1d-master: shutdown device
[   19.974480][  T250] mpp_av1dec av1d-master: shutdown success
[   19.980282][  T250] [WLAN_RFKILL]: Enter rfkill_wlan_shutdown
[   19.986026][  T250] [WLAN_RFKILL]: rockchip_wifi_power: 0
[   19.991424][  T250] [WLAN_RFKILL]: rockchip_wifi_power: toggle = false
[   19.998013][  T250] [WLAN_RFKILL]: wifi shut off power [GPIO-1-1]
[   20.004108][  T250] [WLAN_RFKILL]: rfkill_set_wifi_bt_power: 0
[   20.010059][  T250] rkisp_hw fdcb0000.rkisp: rkisp_hw_shutdown
[   20.015895][  T250] mpp_rkvdec2 fdc48100.rkvdec-core: shutdown device
[   20.022323][  T250] mpp_rkvdec2 fdc48100.rkvdec-core: shutdown success
[   20.028845][  T250] mpp_rkvdec2 fdc38100.rkvdec-core: shutdown device
[   20.035273][  T250] mpp_rkvdec2 fdc38100.rkvdec-core: shutdown success
[   20.041795][  T250] mpp_rkvenc2 fdbe0000.rkvenc-core: shutdown device
[   20.048222][  T250] mpp_rkvenc2 fdbe0000.rkvenc-core: shutdown success
[   20.054747][  T250] mpp_rkvenc2 fdbd0000.rkvenc-core: shutdown device
[   20.061176][  T250] mpp_rkvenc2 fdbd0000.rkvenc-core: shutdown success
[   20.067699][  T250] mpp-iep2 fdbb0000.iep: shutdown device
[   20.073173][  T250] mpp-iep2 fdbb0000.iep: shutdown success
[   20.078740][  T250] mpp_vepu2 fdbac000.jpege-core: shutdown device
[   20.084908][  T250] mpp_vepu2 fdbac000.jpege-core: shutdown success
[   20.091169][  T250] mpp_vepu2 fdba8000.jpege-core: shutdown device
[   20.097335][  T250] mpp_vepu2 fdba8000.jpege-core: shutdown success
[   20.103596][  T250] mpp_vepu2 fdba4000.jpege-core: shutdown device
[   20.109764][  T250] mpp_vepu2 fdba4000.jpege-core: shutdown success
[   20.116024][  T250] mpp_vepu2 fdba0000.jpege-core: shutdown device
[   20.122193][  T250] mpp_vepu2 fdba0000.jpege-core: shutdown success
[   20.128455][  T250] mpp_jpgdec fdb90000.jpegd: shutdown device
[   20.134276][  T250] mpp_jpgdec fdb90000.jpegd: shutdown success
[   20.140202][  T250] mpp_vepu2 fdb50000.vepu: shutdown device
[   20.145850][  T250] mpp_vepu2 fdb50000.vepu: shutdown success
[   20.151584][  T250] mpp_vdpu2 fdb50400.vdpu: shutdown device
[   20.157232][  T250] mpp_vdpu2 fdb50400.vdpu: shutdown success
[   20.163049][  T250] xhci-hcd xhci-hcd.4.auto: remove, state 4
[   20.168786][  T250] usb usb6: USB disconnect, device number 1
[   20.174793][  T250] xhci-hcd xhci-hcd.4.auto: USB bus 6 deregistered
[   20.181314][  T250] xhci-hcd xhci-hcd.4.auto: remove, state 4
[   20.187057][  T250] usb usb5: USB disconnect, device number 1
[   20.193103][  T250] xhci-hcd xhci-hcd.4.auto: USB bus 5 deregistered
[   20.200265][  T250] reboot: Restarting system

重启时的截图如下：

CoolPi 4B 从SD卡启动，在系统启动阶段会出现随机卡死/无限重启的情况，操作步骤如下：
下载20230517-coolpi-4b-android12镜像，使用balena etcher烧录到SD卡中，启动系统，从串口看输出，不能进入系统，具体表现是在加载系统时无限重启（之前遇到过，今天没有遇到）或卡死（如图）
尝试过的解决方案：
1.更换2023042819-coolpi-4b-android镜像，同样卡死
2.更换SD卡，仍然卡死
3.把SD卡插上读卡器，从靠下的USB3.0进行引导，仍然卡死
4.更换功率更大的充电器（之前用的是官方自带的）
请问一下有大佬遇见过这种情况吗？不胜感激！

@traceback
I found the solution in github:
FirstSecond

@george Is new kernel available now? Thank you!

I'm going to try rknn-llm, which need at least v0.9.6 driver version. The version in official ubuntu 22.04 is:

cat /sys/kernel/debug/rknpu/version
RKNPU driver: v0.8.2

I have tried built the rknpu v0.9.6 from rknn-llm repository,but it terminates with error

drivers/rknpu/rknpu_gem.c: In function 'rknpu_gem_mmap_buffer':
drivers/rknpu/rknpu_gem.c:988:9: error: implicit declaration of function 'vm_flags_clear' [-Werror=implicit-function-declaration]
  988 |         vm_flags_clear(vma, VM_PFNMAP);
      |         ^~~~~~~~~~~~~~
cc1: all warnings being treated as errors

Above outputs are raisen when I compile rknpu 0.9.6 under coolpi-kernel 5.10.110
Are there any way to solve the error or update the npu driver?

Thanks in advance!