Re: CURRENT: FreeBSD not reporting AES-NI on Intel(R) Xeon(R) CPU E5-1650 v3

On 2017-03-17 12:53, O. Hartmann wrote:
> Am Fri, 17 Mar 2017 15:04:29 +0300
> Slawa Olhovchenkov <slw_at_zxy.spb.ru> schrieb:
> 
>> On Fri, Mar 17, 2017 at 12:36:25PM +0100, O. Hartmann wrote:
>>
>>> Running recent CURRENT on a Fujitsu Celsius M740 equipted with an Intel(R)
>>> Xeon(R) CPU E5-1650 v3 _at_ 3.50GHz CPU makes me some trouble.
>>>
>>> FreeBSD does not report the existence or availability of AES-NI feature, which
>>> is supposed to be a feature of this type of CPU:  
>>
>> What reassons to detect AES-NI by FreeBSD?
> 
> What do you mean? I do not understand! FreeBSD is supposed to read the CPUID and
> therefore the capabilities as every other OS, too. But there may some circumstances why
> FBSD won't. I do not know, that is the reason why I'm asking here.
> 
>> Other OS detect AES-NI on this server?
> 
> I havn't ried so far, the box is in heavy use. I'd like to check with some live USB drive
> versions and report later.
> 
>>
>> AES-NI may be disabled by BIOS/vendor/BIOS settings
> 
> There is no option for that, I'm looking for several time for that right now. Even with
> TPM enabled - which is considered to be necessary on several firmwares - there is no
> change.
> 
>>
>> https://forums.lenovo.com/t5/ThinkPad-11e-Windows-13-E-and/AES-NI-is-disabled-on-my-13-New-S2/td-p/3498468
>> http://h17007.www1.hpe.com/docs/iss/proliant_uefi/UEFI_Gen9_060216/s_enable_AES-NI.html
>> http://en.community.dell.com/support-forums/servers/f/956/t/19509653
> 
> As I said, even with the brand new firmware from January of this year (2017) there is no
> change - the firmware prior to that showed the same non-existing AES-NI feature.
> 

I have used the E5-1650 v3 in the FreeBSD test cluster, and AES-NI works
fine.

I had to enable it in the BIOS though. It is on the CPU features page,
and may have an odd name, rather than "AES-NI"

AES-NI is unrelated to TPM.

-- 
Allan Jude