mekotronics-r58x-4g: usb fixes + u-boot v2026.04-rc2 + analog audio#9412
Merged
rpardini merged 10 commits intoarmbian:mainfrom Feb 19, 2026
Conversation
github-actions
bot
added
size/large
Contributor
|
Caution Review failedThe pull request is closed. 📝 WalkthroughWalkthroughUpdated Mekotronics R58X-4G board onboarding: bumped U-Boot references to v2026.04, added a UMS DT-patching helper (duplicated in file), introduced a new U-Boot "fileenv" command and Kconfig/Makefile entries, added u-boot patching overlays mapping, and expanded kernel DT with audio, OTG regulator, Type-C, and USB host nodes. Changes
Sequence Diagram(s)mermaid User->>U-Boot: run "fileenv dev:part " Estimated code review effort🎯 4 (Complex) | ⏱️ ~45 minutes Possibly related issues
Possibly related PRs
Suggested reviewers
Poem
🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
github-actions
bot
added
Needs review
Member
Author
|
@igorpecovnik -- follow-up to #9398 "proof" of USB-enablement, all type-a and the type-c port work now. type-c is orientation-sensitive still, and in u-boot is reserved for UMS. |
rpardini
requested review from
ColorfulRhino,
HeyMeco,
JohnTheCoolingFan,
NicoD-SBC,
SuperKali,
TheSnowfield,
Tonymac32,
ahoneybun,
amazingfate,
brentr,
catalinii,
chainsx,
efectn,
igorpecovnik,
joekhoobyar,
krachlatte,
lanefu,
paolosabatino,
prahal,
pyavitz and
schwar3kat
as code owners
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
patch/kernel/archive/rockchip64-6.19/dt/rk3588-blueberry-edge-v12-linux.dts (1)
1008-1014: 🛠️ Refactor suggestion | 🟠 MajorDuplicate
&usb_host0_xhcioverrides — consolidate into one block.There are two
&usb_host0_xhciblocks: lines 1008–1014 setdr_mode = "peripheral"with PHY bindings and speed limit, then lines 1052–1055 overridedr_mode = "host". The later block silently wins ondr_mode, but the staledr_mode = "peripheral"at line 1009 is dead/misleading. This split makes the final effective state hard to reason about.Consolidate into a single block with the intended final state:
♻️ Merge into one coherent block
-&usb_host0_xhci { // usb@fc000000 - dr_mode = "peripheral"; - maximum-speed = "high-speed"; - phys = <&u2phy0_otg>; - phy-names = "usb2-phy"; - status = "okay"; -}; ... -&usb_host0_xhci { - dr_mode = "host"; - status = "okay"; -}; +&usb_host0_xhci { // usb@fc000000 - Type-C port, USB2 only (usbdp_phy0 not wired) + dr_mode = "host"; + maximum-speed = "high-speed"; + phys = <&u2phy0_otg>; + phy-names = "usb2-phy"; + status = "okay"; +};Also applies to: 1052-1055
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@patch/kernel/archive/rockchip64-6.19/dt/rk3588-blueberry-edge-v12-linux.dts` around lines 1008 - 1014, Two duplicate &usb_host0_xhci override blocks exist; consolidate them into one coherent override by merging properties from both blocks (maximum-speed, phys, phy-names, status) and keeping the intended final dr_mode ("host" as set in the later block) so there are no conflicting or stale settings—remove the earlier dr_mode="peripheral" and the redundant second &usb_host0_xhci block so a single &usb_host0_xhci contains dr_mode="host", maximum-speed, phys, phy-names and status.
🧹 Nitpick comments (2)
config/boards/mekotronics-r58x-4g.csc (1)
57-69: Inconsistent function name prefix:ekor58x_4gvsmekor58x_4gused elsewhere.Other hook functions in this file use the
mekor58x_4gprefix (e.g.,pre_config_uboot_target__mekor58x_4g_patch_rockchip_common_boot_order), but this one usesekor58x_4g. While functionally harmless (Armbian hooks just need unique names), it makes grepping/discovering board-related hooks harder.♻️ Suggested rename for consistency
-function pre_config_uboot_target__ekor58x_4g_patch_uboot_dtsi_for_ums() { +function pre_config_uboot_target__mekor58x_4g_patch_uboot_dtsi_for_ums() {🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@config/boards/mekotronics-r58x-4g.csc` around lines 57 - 69, The function name pre_config_uboot_target__ekor58x_4g_patch_uboot_dtsi_for_ums uses the wrong board prefix; rename it to pre_config_uboot_target__mekor58x_4g_patch_uboot_dtsi_for_ums to match other hooks (e.g., pre_config_uboot_target__mekor58x_4g_patch_rockchip_common_boot_order), and update any internal references or registrations to use the new name so all mekotronics-r58x-4g hooks share the same prefix for discoverability.patch/kernel/archive/rockchip64-6.19/dt/rk3588-blueberry-edge-v12-linux.dts (1)
389-390: Endpoint labels sayes8316but the codec is an ES8388.The label
es8316_p0_0(line 389) and its remote-endpoint reference&es8316_p0_0(line 433) refer to a different Everest codec model (ES8316). While functionally harmless (labels are just internal references), this is confusing for anyone reading or maintaining the DTS.♻️ Rename labels to match the actual codec
port { - es8316_p0_0: endpoint { + es8388_p0_0: endpoint { remote-endpoint = <&i2s0_8ch_p0_0>; };i2s0_8ch_p0_0: endpoint { dai-format = "i2s"; mclk-fs = <256>; - remote-endpoint = <&es8316_p0_0>; + remote-endpoint = <&es8388_p0_0>; };Also applies to: 430-433
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@patch/kernel/archive/rockchip64-6.19/dt/rk3588-blueberry-edge-v12-linux.dts` around lines 389 - 390, Rename the misleading ES8316 labels to ES8388 to match the actual codec: change the endpoint label es8316_p0_0 to es8388_p0_0 and update any remote-endpoint references (e.g., &es8316_p0_0) to &es8388_p0_0; ensure both the endpoint declaration (es8316_p0_0: endpoint { ... }) and its consumers (remote-endpoint = <&es8316_p0_0> and any other occurrences around the same block) are updated so the label names are consistent.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@patch/kernel/archive/rockchip64-6.19/dt/rk3588-blueberry-edge-v12-linux.dts`:
- Around line 379-381: The device tree node es8388: audio-codec@11 has a
mismatched unit address and reg value (node name uses `@11` while reg = <0x10>);
update the node's unit address to match the reg value (change audio-codec@11 to
audio-codec@10) or adjust the reg to <0x11> so the unit address and the first
reg entry match, ensuring consistency for the node es8388: audio-codec and its
reg property.
---
Outside diff comments:
In `@patch/kernel/archive/rockchip64-6.19/dt/rk3588-blueberry-edge-v12-linux.dts`:
- Around line 1008-1014: Two duplicate &usb_host0_xhci override blocks exist;
consolidate them into one coherent override by merging properties from both
blocks (maximum-speed, phys, phy-names, status) and keeping the intended final
dr_mode ("host" as set in the later block) so there are no conflicting or stale
settings—remove the earlier dr_mode="peripheral" and the redundant second
&usb_host0_xhci block so a single &usb_host0_xhci contains dr_mode="host",
maximum-speed, phys, phy-names and status.
---
Nitpick comments:
In `@config/boards/mekotronics-r58x-4g.csc`:
- Around line 57-69: The function name
pre_config_uboot_target__ekor58x_4g_patch_uboot_dtsi_for_ums uses the wrong
board prefix; rename it to
pre_config_uboot_target__mekor58x_4g_patch_uboot_dtsi_for_ums to match other
hooks (e.g.,
pre_config_uboot_target__mekor58x_4g_patch_rockchip_common_boot_order), and
update any internal references or registrations to use the new name so all
mekotronics-r58x-4g hooks share the same prefix for discoverability.
In `@patch/kernel/archive/rockchip64-6.19/dt/rk3588-blueberry-edge-v12-linux.dts`:
- Around line 389-390: Rename the misleading ES8316 labels to ES8388 to match
the actual codec: change the endpoint label es8316_p0_0 to es8388_p0_0 and
update any remote-endpoint references (e.g., &es8316_p0_0) to &es8388_p0_0;
ensure both the endpoint declaration (es8316_p0_0: endpoint { ... }) and its
consumers (remote-endpoint = <&es8316_p0_0> and any other occurrences around the
same block) are updated so the label names are consistent.
patch/kernel/archive/rockchip64-6.19/dt/rk3588-blueberry-edge-v12-linux.dts
Outdated
Show resolved
Hide resolved
igorpecovnik
approved these changes
Feb 18, 2026
Contributor
|
✅ This PR has been reviewed and approved — all set for merge! |
- drop invalid and useless enable-gpios on hdmi0 node - was from vendor kernel - does nothing in mainline - is not required in mainline for working HDMI
…_PA7) - probably type-c stuff, but we never know with Meko
- this gets the 3 usb type-A ports in the front working
- also: drop old modem (4G) to-do, as modem already works without it
- fileenv patch (same as v2026.01)
- fdt_fixup_ethernet logging patch (same as v2026.01)
- 0000.patching_config.yaml: defconfig/dt_upstream_rockchip/dt_uboot
- notable in v2026.04:
- dt-rebasing bumped up to v6.18 (which has NPU nodes)
- this allows us to share complete DTs between kernel and u-boot via symlinks
- Kwiboo had a go at LWIP which should be usable now; Kwiboo rocks.
- u-boot v2026.04-rcX has bumped dt-rebasing to v6.18, thus it knows about NPU nodes now and we can simply symlink to kernel DT, reducing duplication by a lot
- works as far as I can tell - both orientations - also wired DP, but can't test (I've no USB-DP hw)
- also `tcpm` cmd for debugging
- saves one .dtsi file in patch/.../dt_uboot - I had the wrong name (missing `-u-boot` suffix) too so this fixes it too
- This reverts commit e94425f. - I am clearly not up to par with type-c/fusb302 stuff yet - sending this for future reference
rpardini
force-pushed
the
pr/mekotronics-r58x-4g-usb-fixes--u-boot-v202604-rc2--analog-audio
branch
from
c0db53c to
f40fb9d
Compare
github-actions
bot
added
Needs review
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
mekotronics-r58x-4g: usb fixes + u-boot v2026.04-rc2 + analog audio
tcpmcmd for debugging-u-boot.dtsivia hook-u-bootsuffix) too so this fixes it tooSummary by CodeRabbit
Release Notes
New Features
Chores