-Greg Ungerer has m68knommu updates, for 3.7, of course, James
Morris updates linux-security, Mauro Carvalho Chehab announces
the first part of media updates:
- A major tree renaming patch series: now, drivers are organized internally
by their used bus, instead of by V4L2 and/or DVB API, providing a cleaner
driver location for hybrid drivers that implement both APIs, and allowing to
cleanup the Kconfig items and make them more intuitive for the end user;
- Media Kernel developers are typically very lazy with their duties of
keeping the MAINTAINERS entries for their drivers updated. As now the tree
is more organized, we’re doing an effort to add/update those entries
for the drivers that aren’t currently orphan;
- Several DVB USB drivers got moved to a new DVB USB v2 core; the new core
fixes several bugs (as the existing one that got bitroted). Now,
suspend/resume finally started to work fine (at least with some devices -
we should expect more work with regards to it);
- added multistream support for DVB-T2, and unified the API for DVB-S2
and ISDB-S. Backward binary support is preserved;
- as usual, a few new drivers, some V4L2 core improvements and lots of
drivers improvements and fixes.
There are some points to notice on this series:
1) you should expect a trivial merge conflict on your tree, with the removal
of Documentation/feature-removal-schedule.txt: this series would be adding
two additional entries there. I opted to not rebase it due to this recent
2) With regards to the PCTV 520e udev-related breakage, I opted to fix it
in a way that the patches can be backported to 3.5 even without your
firmware fix patch. This way, Greg doesn’t need to rush backporting your
patch (as there are still the firmware cache and firmware path customization
issues to be addressed there). I’ll send later a patch (likely after the end
of the merge window) reverting the rest of the DRX-K async firmware request,
fully restoring its original behaviour to allow media drivers to initialize
everything serialized as before for 3.7 and upper.
3) I’m planning to work on this weekend to test the DMABUF patches for V4L2.
The patches are on my queue for several Kernel cycles, but, up to now,
there is/was no way to test the series locally. I have some concerns about
this particular changeset with regards to security issues, and with regards
to the replacement of the old VIDIOC_OVERLAY ioctl’s that is broken on
modern systems, due to GPU drivers change. The Overlay API allows direct
PCI2PCI transfers from a media capture card into the GPU framebuffer, but
its API is crappy. Also, the only existing X11 driver that implements it
requires a XV extension that is not available anymore on modern drivers.
The DMABUF can do the same thing, but with it is promising to be a
properly-designed API. If I can successfully test this series and
be happy with it, I should be asking you to pull them next week.
-Michal Simek updates microblaze for -rc1, Joerg Roedel ups IOMMU. also for -rc1,
and that’s about it for now.