Remove all KII Pro patches as they got merged into 6.4. Also remove V=1
as it's now unnecessary.
Signed-off-by: Ferass El Hafidi <vitali64pmemail@protonmail.com>
[ci:skip-build]: already built successfully in CI
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
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
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
This allows the user (upon loading the module) to handle non-native
binaries transparently - after registering the magic number and the
command for handling execution, the programs can be ran as if compiled
for the host architecture. (Similarly how the shebang line allows
the interpreter to be specified for scirpts).
Common use-cases include
* Using qemu user-space emulation to run
x86 binaries on ARM (or the other way around), or simply running
64-bit binaries on 32-bit architectures.
* Allow Java programs to be run transparently.
* Creating cross-architecture chroots (for cross-compilation e.g.)
Add a dummy subpackage that does not install any kernel. This is useful
for testing 'pmbootstrap install' code quickly without actually
downloading and installing a kernel package.
- fix wifi signal quality display, since /proc/net/wireless is no longer
available in omap kernel
Suggested-by: DvaMishkiLapa <thesame.personal@gmail.com>
- add `polkit-elogind` so tools like `loginctl poweroff` and `nmtui` do not
require sudo under i3wm
[ci:skip-build]: already built successfully in CI
The call_audio_idle_suspend_workaround init service was moved to the
-pulseaudio subpackage, but the -modem subpackage still had a
.post-upgrade referring to it. This moves that to the (recently) new
-pulseaudio package
[ci:skip-build]: already built successfully in CI
Out of the box audio is really quiet and distorted on SDM845 devices when
using PipeWire. This can be worked around by forcing audio to 16 bits
(which PulseAudio uses by default and thus works). This seems to be a
kernel problem and should be fixed properly there but for now we can
apply this workaround to at least be able to switch to PipeWire anytime
soon. The actual workaround is applied by Wireplumber so the dependency
for the subpackage is set to that.
Upstream issue https://gitlab.freedesktop.org/pipewire/pipewire/-/issues/3193
[ci:skip-build]: already built successfully in CI
It doesn't build currently (issue 2146) and also it's not used by any
device package currently (with other ports we support selecting between
mainline and downstream kernel in some cases, but not here).
If it's useful, the build can be fixed and it can be added back in a
future patch.
changes:
- don't try to set gnss-share socket in geoclue
- install Alsa UCM configs from purism
Upstream ucm is broken when migrating from the purism ucm, so let's
just use ucm from purism until someone upstreams something that works.
What I upstreamed was based on an older ucm from Purism, what they are
shipping is more correct than upstream ucm...
This reverts commit 70b7813fee.
fixes#2134
[ci:skip-build] already built successfully in CI
The `firmware-pine64-pinebookpro` predates the firmware for this device
being available upstream. It is now packaged in two separate packages:
linux-firmware-brcm and linux-firmware-rockchip.
Install those two linux-firmware packages and drop the custom one. This
drop a custom firmware package and also ensure that firmware is kept up to
date with the rest of linux-firmware-*.
The resulting installation includes all the previously included firmware
files and I've confirmed that both sound and wifi work fine (dmesg
indicates bluetooth is available too).
This also enables a few other things for Amlogic SBCs, including some
kernel config that enables video decoding support, however userspace
still doesn't support it (e.g. requires patched ffmpeg)
[ci:skip-build] already built successfully in CI
Previously, this extra rule was needed to grant regular users
permissions for the embedded display's backlight. It no longer seems to
be necessary; the presence of this rule is currently a no-op.
Someone else on IRC has tested removing the rule and also confirms this
new behaviour. I suspect this was fixed upstream in eudev.
Rebase of sdm660 patchset on top of linux-stable/linux-6.3.y
branch.
Notable changes:
* New device: HMD Global Nokia 6.1 (nokia-pl2)
* New device: Xiaomi Mi A2 (xiaomi-jasmine_sprout)
* usage of pmb:kconfigcheck-community only
* LOCALVERSION is no longer set in kconfig, but at build time
Signed-off-by: Gianluca Boiano <morf3089@gmail.com>
[ci:skip-build] already built successfully in CI
