On Fri, Jun 07, 2024 at 01:38:15AM +0000, Michael Kelley wrote:
> From: Steven Price <steven.price@xxxxxxx> Sent: Wednesday, June 5, 2024 2:30 AM
> > This series adds support for running Linux in a protected VM under the
> > Arm Confidential Compute Architecture (CCA). This has been updated
> > following the feedback from the v2 posting[1]. Thanks for the feedback!
> > Individual patches have a change log for v3.
> >
> > The biggest change from v2 is fixing set_memory_{en,de}crypted() to
> > perform a break-before-make sequence. Note that only the virtual address
> > supplied is flipped between shared and protected, so if e.g. a vmalloc()
> > address is passed the linear map will still point to the (now invalid)
> > previous IPA. Attempts to access the wrong address may trigger a
> > Synchronous External Abort. However any code which attempts to access
> > the 'encrypted' alias after set_memory_decrypted() is already likely to
> > be broken on platforms that implement memory encryption, so I don't
> > expect problems.
>
> In the case of a vmalloc() address, load_unaligned_zeropad() could still
> make an access to the underlying pages through the linear address. In
> CoCo guests on x86, both the vmalloc PTE and the linear map PTE are
> flipped, so the load_unaligned_zeropad() problem can occur only during
> the transition between decrypted and encrypted. But even then, the
> exception handlers have code to fixup this case and allow everything to
> proceed normally.
>
> I haven't looked at the code in your patches, but do you handle that case,
> or somehow prevent it?
If we can guarantee that only full a vm_struct area is changed at a
time, the vmap guard page would prevent this issue (not sure we can
though). Otherwise I think we either change the set_memory_*() code to
deal with the other mappings or we handle the exception.
We also have potential user mappings, do we need to do anything about
them?
--
Catalin
