Re: Problem with pat_enable() and commit 72cbc8f04fe2

[Juergen Gross <jgross@suse.com>]

[-- Attachment #1.1.1: Type: text/plain, Size: 2057 bytes --]

On 10.01.23 06:47, Juergen Gross wrote:
> On 09.01.23 19:28, Michael Kelley (LINUX) wrote:
>> I've come across a case with a VM running on Hyper-V that doesn't get
>> MTRRs, but the PAT is functional.  (This is a Confidential VM using
>> AMD's SEV-SNP encryption technology with the vTOM option.)  In this
>> case, the changes in commit 72cbc8f04fe2 ("x86/PAT: Have pat_enabled()
>> properly reflect state when running on Xen") apply.   pat_enabled() returns
>> "true", but the MTRRs are not enabled.
>>
>> But with this commit, there's a problem.  Consider memremap() on a RAM
>> region, called with MEMREMAP_WB plus MEMREMAP_DEC as the 3rd
>> argument. Because of the request for a decrypted mapping,
>> arch_memremap_can_ram_remap() returns false, and a new mapping
>> must be created, which is appropriate.
>>
>> The following call stack results:
>>
>>    memremap()
>>    arch_memremap_wb()
>>    ioremap_cache()
>>    __ioremap_caller()
>>    memtype_reserve()  <--- pcm is _PAGE_CACHE_MODE_WB
>>    pat_x_mtrr_type()  <-- only called after commit 72cbc8f04fe2
>>
>> pat_x_mtrr_type() returns _PAGE_CACHE_MODE_UC_MINUS because
>> mtrr_type_lookup() fails.  As a result, memremap() erroneously creates the
>> new mapping as uncached.   This uncached mapping is causing a significant
>> performance problem in certain Hyper-V Confidential VM configurations.
>>
>> Any thoughts on resolving this?  Should memtype_reserve() be checking
>> both pat_enabled() *and* whether MTRRs are enabled before calling
>> pat_x_mtrr_type()?  Or does that defeat the purpose of commit
>> 72cbc8f04fe2 in the Xen environment?
> 
> I think pat_x_mtrr_type() should return _PAGE_CACHE_MODE_UC_MINUS only if
> mtrr_type_lookup() is not failing and is returning a mode other than WB.

Another idea would be to let the mtrr_type_lookup() stub in
arch/x86/include/asm/mtrr.h return MTRR_TYPE_WRBACK, enabling to simplify
pud_set_huge() and pmd_set_huge() by removing the check for MTRR_TYPE_INVALID.


Juergen

[-- Attachment #1.1.2: OpenPGP public key --]
[-- Type: application/pgp-keys, Size: 3149 bytes --]

[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 495 bytes --]