Sand_Death Posted 5 hours ago Posted 5 hours ago @alexc I tested the modified kernel and asked Claude to report it, he reported it like this. System Refinement and Build Optimization Report Feedback 1. MSI Fix Confirmed Working Details: The MSI fix has been verified and successfully tested on Hailo8L (sun60iw2/A733 platform). Result: Massive reduction in system load: load avg dropped from 18+ to ~12, and Frigate CPU usage plummeted from 485% to 83% during real-world inference. High Priority 2. sunxi-autogen.h in .gitignore Issue: This file is currently ignored by .gitignore, yet it is strictly required for the build to succeed and is not automatically generated. Solution: Either implement automatic generation of this file inside the Makefile OR properly document the creation steps in the README. 3. Undocumented LOCALVERSION Behavior Issue: Building from a dirty Git tree automatically appends a + suffix to the kernel version string, leading to a critical vermagic mismatch for compiled modules. Solution: Document this behavior in the README or enforce proper default behavior in the default configuration file. Medium Priority 4. Missing BSP_TOP Export Issue: Running make olddefconfig crashes unless BSP_TOP=bsp/ is explicitly passed as an environment variable. Solution: Add path auto-detection directly into the root Makefile to make the build self-contained. 5. Missing DKMS Config for hailo_pci Issue: Since this is an out-of-tree module, users must manually rebuild it after every routine kernel update. Solution: Provide a DKMS configuration to automate the rebuild process on the OS level. Low Priority 6. hailo_pci Driver Integration in initramfs Issue: The module is not automatically included in the initramfs image during the build phase. Solution: Create a dedicated hook script or add a section in the documentation explaining manual configuration via modules-load.d and update-initramfs. 7. Overly Permissive /dev/hailo0 Permissions (World-Writable) Issue: The device node permissions are set to crw-rw-rw- (anyone can write to it), which poses a security risk. Solution: Deploy a standard udev rule to restrict permissions and grant access safely via a dedicated system group. !!! At the moment, I confirm that it works with these edits. 0 Quote
alexc Posted 2 hours ago Posted 2 hours ago (edited) @Sand_Death Really interesting read! Would it be possible to submit these changes through GitHub or as a kernel patch? We'd love to see the full context of the changes—the code actually provides such a clear picture of what's happening (even more so than the docs!), so a proper review of the diff would be great. EDIT: Looking at the description, it seems Claude addressed the issue on the Hailo driver side rather than fixing it in the PCIe driver. Personally, I don't think that's the ideal approach, since the BSP PCIe driver appears to be the root cause. If you get a chance to try my patch instead, I'd be interested to hear how it works for you. Edited 2 hours ago by alexc 0 Quote
Recommended Posts
Join the conversation
You can post now and register later. If you have an account, sign in now to post with your account.
Note: Your post will require moderator approval before it will be visible.