Re: Dealing with SIOV/IMS

[Demi Marie Obenour <demiobenour@gmail.com>]

[-- Attachment #1.1.1: Type: text/plain, Size: 1115 bytes --]

On 1/1/26 20:22, Andrew Cooper wrote:
> On 01/01/2026 10:56 pm, Marek Marczykowski-Górecki wrote:
>> Hi,
>>
>> I've got yet another report[1] of device failing because (I assume) the
>> drivers reads MSI/MSI-X values (thinking it sees values actually set in
>> the HW) and then pass them to the device via some alternative means.
> 
> Ath11k is known broken in this regard.  It doesn't even work on native
> systems.  (It only works in Linux by dropping to a single interrupt and
> tying it to CPU 0).

I wonder what it does on Windows.  Does Windows play nice with IMS?

> But, my understand is that this is specific to Ath11k and not to do with
> IMS.

Does that mean that an ath11k-specific hack in QEMU might be an option?

>> IIUC this is what IMS does.
> 
> Not really.  IMS moves the MSI-X table out of a BAR and into host memory.
> 
> It was a short-sighted design which is very hard for native to use and
> impossible for virt to use.
> 
> AIUI, IMS has been abandoned as a technology, so I think we can simply
> ignore it.
-- 
Sincerely,
Demi Marie Obenour (she/her/hers)

[-- Attachment #1.1.2: OpenPGP public key --]
[-- Type: application/pgp-keys, Size: 7253 bytes --]

[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 833 bytes --]