version 1.1.2.7, 2001/07/02 13:39:10 |
version 1.1.2.8, 2002/01/30 14:55:05 |
Line 5 showstoppers for merge back to -current: |
|
Line 5 showstoppers for merge back to -current: |
|
- change splraise/spllower to not touch local apic, since that's very |
- change splraise/spllower to not touch local apic, since that's very |
slow (requires cheap per-cpu storage). |
slow (requires cheap per-cpu storage). |
|
|
- per-cpu GDT and MP-safing of gdt.c. this seems like severe |
|
overkill so just one descriptor is different. While we're in there, |
|
we *might* want to use per-cpu, more ephemeral, descriptors for TSS |
|
and LDT. |
|
|
|
- quad cpu ppro sporadically jumps into the stack; need to diagnose |
- quad cpu ppro sporadically jumps into the stack; need to diagnose |
this. |
this. |
|
|
Line 23 branch from/to" MSR contents) to allow f |
|
Line 18 branch from/to" MSR contents) to allow f |
|
|
|
- careful code review of all diffs from -current |
- careful code review of all diffs from -current |
|
|
|
- try to render APM *harmless* (and functional in uniprocessor |
|
configurations). it can't possibly work correctly when multiple cpu's |
|
are running, but.. |
|
|
"would be nice": |
"would be nice": |
|
|
- use atomic ops to modify ci_flags and cpu_feature to avoid losing bits. |
- use atomic ops to modify ci_flags and cpu_feature to avoid losing bits. |
Line 38 branch from/to" MSR contents) to allow f |
|
Line 37 branch from/to" MSR contents) to allow f |
|
- turn off rdtsc-based microtime on uniprocessor systems which might |
- turn off rdtsc-based microtime on uniprocessor systems which might |
have variable-speed TSC. |
have variable-speed TSC. |
|
|
|
- investigate using per-cpu, more ephemeral, descriptors for TSS and |
|
LDT. |
|
|
|
- make halt -p work in MULTIPROCESSOR config (the one APM feature |
|
everyone wants) |
|
|
----- |
----- |
|
|
DONE: |
DONE: |
Line 71 completed. significant rewrite of cpu s |
|
Line 76 completed. significant rewrite of cpu s |
|
[2001/05/26 20:03:41 sommerfeld] |
[2001/05/26 20:03:41 sommerfeld] |
answer: microtime was just doing the wrong thing. fixed. |
answer: microtime was just doing the wrong thing. fixed. |
|
|
|
[2002/01/30 09:52:17 sommerfeld] |
|
done a while ago: |
|
|
|
- per-cpu GDT and MP-safing of gdt.c. this seems like severe |
|
overkill so just one descriptor is different. |
|
|