默认配置下出现 PCIE BUS Error 导致死机，降低为PCIE gen1 后不会死机，但仍有PCIE BUS Err报错

[DKaiF]

软件环境：36.3
硬件：自定义载板，jeston agx orin 32G/64GB核心板
pcie设计：使用pcie UPHY1 接 I350-AM4网卡
板卡信息如下：

root@ubuntu:~# cat /proc/version
Linux version 5.15.136-rt-tegra (dev@8e8fbb755e79) (aarch64-buildroot-linux-gnu-gcc.br_real (Buildroot 2022.08) 11.3.0, GNU ld (GNU Binutils) 2.38) #1 SMP PREEMPT_RT Fri May 9 06:12:11 UTC 2025

Uphy配置为默认配置

ODMDATA=“gbe-uphy-config-22,hsstp-lane-map-3,nvhs-uphy-config-0,hsio-uphy-config-0,gbe0-enable-10g”; CHIPID=0x23; ITS_FILE=; OVERLAY_DTB_FILE=“L4TConfiguration.dtbo,tegra234-p3701-overlay.dtbo”; CMDLINE_ADD=“mminit_loglevel=4 console=ttyTCU0,115200 console=ttyAMA0,115200 firmware_class.path=/etc/firmware fbcon=map:0 net.ifnames=0 nospectre_bhb video=efifb:off console=tty0” target_board=“generic”;

可以通过lspci看到PCIE 网卡已被加载

root@ubuntu:~# lspci
0001:00:00.0 PCI bridge: NVIDIA Corporation Device 229e (rev a1)
0005:00:00.0 PCI bridge: NVIDIA Corporation Device 229a (rev a1)
0005:01:00.0 Ethernet controller: Intel Corporation I350 Gigabit Network Connection (rev 01)
0005:01:00.1 Ethernet controller: Intel Corporation I350 Gigabit Network Connection (rev 01)
0005:01:00.2 Ethernet controller: Intel Corporation I350 Gigabit Network Connection (rev 01)
0005:01:00.3 Ethernet controller: Intel Corporation I350 Gigabit Network Connection (rev 01)

可以看到当前已经降为gen1速率

root@ubuntu:~# lspci -vvv | grep LnkSta
LnkSta: Speed 2.5GT/s (ok), Width x4 (downgraded)
LnkSta2: Current De-emphasis Level: -3.5dB, EqualizationComplete- EqualizationPhase1-
LnkSta: Speed 2.5GT/s (downgraded), Width x4 (ok)
LnkSta2: Current De-emphasis Level: -6dB, EqualizationComplete- EqualizationPhase1-
LnkSta: Speed 2.5GT/s (downgraded), Width x4 (ok)
LnkSta2: Current De-emphasis Level: -6dB, EqualizationComplete- EqualizationPhase1-
LnkSta: Speed 2.5GT/s (downgraded), Width x4 (ok)
LnkSta2: Current De-emphasis Level: -6dB, EqualizationComplete- EqualizationPhase1-
LnkSta: Speed 2.5GT/s (downgraded), Width x4 (ok)
LnkSta2: Current De-emphasis Level: -6dB, EqualizationComplete- EqualizationPhase1-

dts文件配置如下，配置为gen1

  pcie@141a0000{
  	vpcie3v3-supply = <&vdd_3v3_i350>;
  	/delete-property/ vpcie12v-supply;
  	max-link-speed = <0x1>;
  };

lspci -vvv 详细信息如下：
lspci-vvv-show-log.txt (21.8 KB)
开机log如下：
当PCIE配置速录为gen1时候，有少许PCIE BUS Error 报错，LOG如下
PCIE BUS Err Gen1.txt (184.8 KB)

当PCIE配置速录为gen2
的时候，会有大量PCIE BUS Error报错， 导致死机重启，无法进入登录界面， LOG 如下
sku2_pcie_bus_err_32g_pcle_gen2_core_dump.txt (261.5 KB)

[DKaiF]

硬件连接如下，SOM UPHY1与i350-AM4 连接

[DKaiF]

硬件SI测试结果如下，测试显示通过

[WayneWWW]

Does the same PCIe card also hit this issue if testing on NV devkit?

[DKaiF]

我们没有PCIE 设备在 devkit 上进行测试， 所以没有遇到这个问题

[WayneWWW]

Then nothng we can check here.

Maybe you could get a pcie analyzer and dump some traces.

[DKaiF]

上文回复使用pcie analyzer 这个是个软件工具，还是类似示波器一样的工具呢

这里我在exlinux.conf文件中加了pci=nomsi 参数，报错明显消失，但仍有其他问题，想咨询下这个参数的添加会有什么影响

LABEL primary
MENU LABEL primary kernel
LINUX /boot/Image
INITRD /boot/initrd
FDT /boot/kernel_tegra234-p3737-0000+p3701-0005-robot.dtb
OVERLAYS /boot/tegra234-p3737-0000+robot-0000-camera.dtbo,/boot/tegra234-p3737-camera-isx031-overlay.dtbo
APPEND ${cbootargs} root=/dev/mmcblk0p1 rw rootwait rootfstype=ext4 mminit_loglevel=4 console=ttyTCU0,115200 console=ttyAMA0,115200 firmware_class.path=/etc/firmware fbcon=map:0 net.ifnames=0 nospectre_bhb video=efifb:off console=tty0 pci=nomsi