| Age | Commit message (Collapse) | Author |
|---|
|
lower 12 bits contain the perms, no unused bits left,
but a couple for off-tlb use (as the ref implemented now).
do not use the hvt, which might get some use later
if proven to speed thigs up, tlb handlers would po
another dozen of insns though, but if that's worth its...
move on the data seg and map kernel text rdonly (idea form fredette),
since all of the page0 mods done before that we are all fine
except for some viper fluff, but later w/ that.
this also picks up a bit more of ddb magic for bpt and ss.
tlb handlers can use a little bit more of attention,
but things, visually, seem to be much faster already, --
sorry, no benchmarks for now.
* effort sponsored in part by the `henry st. old ale house'
* and mr.pete and mr.lee in particular in thier generous entrirety.
* the proj took a little more that 72man*h as it was expected,
* but within murhy's law estimations.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
the ANSI way.
|
|
__P removal.
|
|
there.
Win some uglyness points in fixing this.
|
|
Fix bug where altivec context was not freed on process exit.
Fix bug where vscr was not correctly saved/restored.
replace asm statement was macros which expand to the same
asm code or to .long XXX which evaluates to the same instruction
since in-tree gas does not support altivec.
Enable ALTIVEC support by default on macppc, still conditional
for other powerpc ports.
|
|
they are and declarre 'em accordingly also removing private externies of those
|
|
|
|
use Sbus level 5 for interrupts which means spltty() is not blocked correctly
because the sbus interrupt handling uses the implied spl of the interrupt
instead of the level passed to it.
|
|
|
|
|
|
|
|
wd@ics.nara-wu.ac.jp via pr#2457
|
|
|
|
|
|
ra->ra_name is needed and is the result of getpropstring
|
|
|
|
|
|
|
|
|
|
your kernel configuration file.
By default, GENERIC will enable this.
When PTRACE is not enabled, several ptrace-like features of the procfs
filesystem will be disabled as well (namely, the ability to read and write
any process' registers, as well as attching, single stepping and detaching
to/from processes).
This should help paranoid people build better sandboxens, and us to build
smaller ramdisks.
|
|
the spill list for each PTEG, the V->P translations are stored in
trees for each pmap. All valid kernel mappings are preallocated
in 1-1 memory so that tlb spill/loads for kernel accesses can be
looked up while physical, user mappings are not guaranteed to
be 1-1 mapped, thus the kernel must go virtual to look up user
mappings. While this is more expensive, the tree search is much
lower cost than the long linked list search. Also on each pmap_remove()
it was necessary to search the linked lists for each possible mapping,
now it just looks up the entry in the tree.
This change gives a 25-36% speedup in 'make build' time. What was
around 2:50 is now around 1:55 on a 733MHz G4.
This change causes a likely existing bug to appear quite often,
it deals with the segment register invalidation in kernel mode.
Because of that problem, currently this change limits the physical
memory used to 256MB. This limitation will be fixed soon, it is not
an error in the pmap code.
* Effort sponsored in part by the Defense Advanced Research Projects
* Agency (DARPA) and Air Force Research Laboratory, Air Force
* Materiel Command, USAF, under agreement number F30602-01-2-0537.
|
|
Instead of using a homegrown set of variables in this case, rely on uvmexp
fields once uvm has been initialized.
This requires a few #include <uvm/uvm_extern.h> here and there in the kernel
as well.
Idea from art@, changes by me.
|
|
|
|
|
|
marked as streaming.
|
|
|
|
More or less directly from FreeBSD.
|
|
ALTQify more drivers.
ok millert@
|
|
|
|
of the hardware clock. Prevent clock screwage due to lost battery on laptops
where the hardware clock goes back to 0. From NetBSD.
|
|
|
|
|
|
|
|
openfirmware commands (which apple seems to have removed), walk the device
tree attempting to detect what type of keyboard(s) are present. Give
preference to USB if USB and ADB both found. If none found hope for USB.
This does have a problem on RevC iMacs booting without USB keyboard,
it seems apple left the adb device tree information which indicates
an ADB kebyoard is present. This fixes newer ibook and PBG4 keyboard
detection.
|
|
|
|
they do not appear to be capable of handling all possible nested interrupts.
|
|
|
|
|
|
on reboot. perhaps OF uses it at other times?
Since OF always use the same memory addresses, this should always allocate
the same ram to the msgbuf, and allow it to be preserved across reboot.
|
|
BUS_DMA_READ, BUS_DMA_WRITE, and BUS_DMA_STREAMING
|
|
|
|
Fix calculation of dma segment length when the DVMA range is crossing the boundary.
|
|
speed (beware, old PDC will not support this!)
- increase the arbitrary device limit for the lists; some machines (743 and
748 come to mind) can have lots of heads and serial ports...
- be more clever when sorting the devices in our lists, so as to get the
correct order on machines where the built-in serial ports are GIO but
on different busses.
|
|
|
