-Ben Hutchings announces 3.2.31, Trond Myklebust
has NFS client updates, Stefan Richter has a small
Firewire fix, and Jens Axboe has block IO updates
- First series from Kent cleaning up and generalizing bio allocation
- WRITE_SAME support from Martin.
- Mikulas patches to prevent O_DIRECT crashes when someone changes
the block size of a device.
- Make bio_split() work on data-less bio’s (like trim/discards).
- A few other minor fixups.
Please pull. Do note that it will merge cleanly into the current master
(as of right now), but the end-result wont compile due to the prio-tree
removal and change in the vm. You will get an error ala:
fs/block_dev.c: In function ‘set_blocksize’:
fs/block_dev.c:135:2: error: implicit declaration of function ‘prio_tree_empty’ [-Werror=implicit-function-declaration]
I’ve attached a patch from Andrew to fix that up, I’m guessing you
prefer that rather than me merging master into for-3.7/core at this
-Olof Johansson has ARM SoC fixes, and Linus Waleij has patches for 3.7:
here is a late pinctrl pull request with stuff that wasn’t quite
tested at the first
The main reason to not hold off is that the modifications to
as reviewed by Rob Herring introduce new infrastructure for irqdomains that will
be useful for the next cycle: instead of sprinkling irq descriptor
allocation all over
the kernel wherever a “legacy” domain is registered, which is necessary for any
platform using sparse IRQs, and many irq chips are say GPIO controllers which
may be used with several systems, some with sparse IRQs some not, we
push this into the irq_domain_add_simple() so we can atleast do mistakes in
The irq_domain_add_simple() is currently unused in the kernel, so I need to
provide a user. The Nomadik stuff that goes with are changes to the driver I use
day-to-day to make use of this facility (and a dependency), so see it
as a way to
eat my own dogfood: if this blows up the egg hits my face.
-Jonas Bonn has OpenRISC updates, and that’s it for now.