1 |
> Patch needs a minor modification for a single hunk in order to get it |
2 |
> applied on 3.6.7-hardened to 3.7.0-hardened. MCORE2 has also specified for |
3 |
> X86_ALIGNMENT_16 and X86_P6_NOP, but the patch would not introduce COREI7* |
4 |
> for those options. Also there are two instances of CORE2 in |
5 |
> security/Kconfig. I've applied a modified patch on hardened sources 3.7.0 |
6 |
> and compiled it on two machines using corei7 (E5620) and corei7-avx |
7 |
> (2630QM). Both kernels are seem to do fine, I notice nothing unusual. |
8 |
> |
9 |
> However I have to also add, that on the png images mentioned in the git |
10 |
> entry showing the result of the ANOVA analysis I notice only P values over |
11 |
> 0.05, not below. So for me it seems all these optimizations are |
12 |
> non-significant. Despite of the clear tendency, even for core2 compared to |
13 |
> generic_x86. Also I don't see the comparison between core2 and corei7*. |
14 |
> Which would be the most important. Since most users would start changing |
15 |
> from core2 to corei7* and not from generic_x86. Although it's highly |
16 |
> possible, that I'm reading the results wrong. So please confirm. |
17 |
|
18 |
I'm not the author of the patch so I'm not sure how to proceed with |
19 |
this. Which is the correct way to move this forward? |
20 |
|
21 |
- Grant |
22 |
|
23 |
|
24 |
>>> It turns out the extra choices are due to this patch: |
25 |
>>> https://github.com/init6/init_6/blob/master/sys-kernel/geek-sources/files/3.7.1/fix/kernel-37-gcc47-1.patch |
26 |
>>> I'm sorry to have bothered the hardened list with this. - Grant |
27 |
>> Actually looks like a quite interesting patch on the Gentoo spirit of |
28 |
>> letting the user choose an it doesn't imply big changes to the source |
29 |
>> (since only config seems to be changed), have you thought bringing it up |
30 |
>> to the kernel team? I'm CCing them here so they can share what they think. |