lkml.org 
[lkml]   [2022]   [Aug]   [12]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
SubjectRe: [PATCH v2 1/2] x86/sev: Put PSC struct on the stack in prep for unaccepted memory support
From


On 8/12/22 08:03, Borislav Petkov wrote:
> On Mon, Aug 08, 2022 at 12:16:24PM -0500, Tom Lendacky wrote:
>> In advance of providing support for unaccepted memory, switch from using
>> kmalloc() for allocating the Page State Change (PSC) structure to using a
>> local variable that lives on the stack. This is needed to avoid a possible
>> recursive call into set_pages_state() if the kmalloc() call requires
>> (more) memory to be accepted, which would result in a hang.
>
> I don't understand: kmalloc() allocates memory which is unaccepted?

In order to satisfy the kmalloc() some memory has to be accepted. So it
tries to accept some additional memory, but we're already in the accept
memory path... deadlock.

>
>> The current size of the PSC struct is 2,032 bytes. To make the struct more
>> stack friendly, reduce the number of PSC entries from 253 down to 64,
>> resulting in a size of 520 bytes. This is a nice compromise on struct size
>> and total PSC requests.
>
> Why can't you simply allocate that one PSC page once at boot, accept the
> memory for it and use it throughout? Under locking, ofc, if multiple PSC
> calls need to happen in parallel...
>
> Instead of limiting the PSC req size.

There was a whole discussion on this and I would prefer to keep the
ability to parallelize PSC without locking.

>
>> @@ -1254,6 +1260,8 @@ void setup_ghcb(void)
>> if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
>> snp_register_per_cpu_ghcb();
>>
>> + ghcb_percpu_ready = true;
>
> You know how I can't stand those random boolean vars stating something
> has been initialized?
>
> Can't you at least use some field in struct ghcb.reserved_1[] or so
> which the spec can provide to OS use so that FW doesn't touch it?

Well when we don't know which GHCB is in use, using that reserved area in
the GHCB doesn't help. Also, I don't want to update the GHCB specification
for a single bit that is only required because of the way Linux went about
establishing the GHCB usage.

Thanks,
Tom

>
> And then stick a "percpu_ready" bit there.
>
> Thx.
>

\
 
 \ /
  Last update: 2022-08-12 16:11    [W:0.356 / U:1.128 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site