Note that only the "linux-edge" kernel is used, and it's likely that
this kernel is still missing some functionality. I'd like to avoid using
a downstream/forked kernel if at all possible...
I chose to use gummiboot for now, since it's really simple to configure.
This can be moved to a more "standard" EFI boot mechanism once pmOS
figures that out.
[ci:skip-build]: already built successfully in CI
Move the elogind configuration and post-install call of "loginctl
reload" into an extra subpackage with install_if=elogind.
Fix for:
Executing device-pine64-pinebookpro-16-r0.post-install
* service nvme-powersave added to runlevel boot
* service sysfsconf added to runlevel default
lib/apk/exec/device-pine64-pinebookpro-16-r0.post-install: line 5: loginctl: not found
ERROR: device-pine64-pinebookpro-16-r0.post-install: script exited with error 127
Make the post-install scripts more robust while at it, by adding
"exit 0" at the end.
Update some alsa buffer params to solve sound quality issues
I got working values experimentally after trying
different buffer sizes and limits and watching to pw-top
to ensure there are no errors during playback from diffrent apps and
sinks.
Contributes to #1534
This sports:
- PM8953 GPIO enablement
- missing properties for motorola-aliIt
- re-generated panels
- Xiaomi Redmi S2/Y2 (xiaomi-ysl) support
- PM8953 thermal zone enablement
- enable modem on Fairphone FP3
[ci:skip-build]: already built successfully in CI
With the new pmbootstrap flasher flash_lk2nd action we should add the
lk2nd package to the device package dependencies. Add it so the flash
works nicely.
[ci:skip-build]: already built successfully in CI
MyCroft has seized development and the package has been removed from
aports. The OpenVoiceOS community has taken over development and has
with ovos a drop-in replacement.
This package originally existed to carry local patches not included
upstream. That is not longer the case, and using the Alpine package
works fine.
Additionally, this package tends to lag behind; Alpine currently ships
2.8.6.
References: https://gitlab.com/postmarketOS/pmaports/-/issues/1611
[ci:skip-build] already built successfully in CI
postmarketos-mkinitfs!30 and specifically postmarketos-mkinitfs@6fdc8937,
changes expected hooks location from /etc/postmarketos-mkinitfs/hooks
to /etc/mkinitfs/hooks, and another commit pushed later adds
/usr/share/mkinitfs/hooks to expected directories. This more or less
breaks new pmOS installs done by running pmbootstrap install on edge branch,
which pull current (2023-06-17T16:57+02:00) device-* packages from
https://mirror.postmarketos.org/postmarketos/master.
Many of those packages which included initfs-hook.sh no longer work in that
case, because they had those hooks in old location, which isn't used
by latest postmarketos-mkinitfs.
Rebuilding the affected packages solves the issue.
[ci:ignore-count]
[ci:skip-build]: already built successfully in CI
Apparently the ath6kl FW can hang at times, so this enables automatic
recovery. This should make wifi on tablets that use ath6kl a little more
reliable.
Otherwise there is a 3 min delay until we can ssh into the device.
Same issue as on samsung-crownlte, where rom4nik investigated and
found the solution [1].
Note that the display does not work for dreamlte and dream2lte at the
moment, the device gets stuck on the pmos boot splash screen. This
issue is tracked in
https://gitlab.com/postmarketOS/pmaports/-/issues/2102.
[1] https://gitlab.com/postmarketOS/pmaports/-/merge_requests/4176
[ci:skip-build] already built successfully in CI
- ath6kl fw is used by some tablets (e.g. baytrail)
- Add support for i2c touchscreens in initramfs, which enables FDE
support for tablets that have i2c touchscreens.
- Drop phosh subpackage / phoc.ini. Forcing 1X scaling is wrong on some
tablets... Phoc/phosh is capable of detecting screen scaling, if it's
wrong on a tablet then a patch should be submitted upstream to fix it.
[ci:skip-build] already built successfully in CI
This kernel release incorporates the following fix from Megi:
- fixed regression in Pinephone power consumption during sleep (touchscreen
was not disabled properly, consuming a lot of power)
[ci:skip-build]: already built successfully in CI
Most UIs already implicitly depend on this in some way, and from the
user-facing point of view, it is sensible to have the full DB of timezones
available, in case the user wants to swap timezone or requires working
with them in different ways. Having it as a explicit dependency makes more
sense than relying on backward dependencies.
Background: https://gitlab.com/postmarketOS/pmaports/-/issues/2168#note_1426261355
[ci:skip-build]: already built successfully in CI
Some tablets have eMMC, which pmOS can be installed to. These modules
are needed to detect/mount the boot and rootfs partitions.
This also adds i915, which sets up the display and allows the splash
screen / console to work on boot.
- make CONFIG_DRM_DISPLAY_CONNECTOR built-in. This resolves 'slow' tty
initialization that breaks pbsplash on N900
- use CONFIG_CMDLINE_FROM_BOOTLOADER instead of CONFIG_CMDLINE_FORCE, to allow
kernel to boot with u-boot provided parameters such as
PMOS_FORCE_PARTITION_RESIZE
- upgrade to 6.3.5
[ci:skip-build]: already built successfully in CI