Re: [PATCH v38 17/24] x86/sgx: ptrace() support for the SGX driver'

From: Jarkko Sakkinen
Date: Thu Sep 24 2020 - 16:40:33 EST


On Thu, Sep 24, 2020 at 11:39:07PM +0300, Jarkko Sakkinen wrote:
> On Thu, Sep 24, 2020 at 05:57:51PM +0200, Borislav Petkov wrote:
> > On Thu, Sep 24, 2020 at 02:51:28PM +0300, Jarkko Sakkinen wrote:
> > > On Wed, Sep 23, 2020 at 06:17:33PM +0200, Borislav Petkov wrote:
> > > > > Add 'access' implementation to vm_ops with the help of these functions.
> > > >
> > > > "Add an ->access virtual MM function for accessing the enclave's memory... "
> > >
> > > Thank you. I wrote the last paragraph like this:
> > >
> > > "Add an '->access' virtual function for accessing the enclave's memory
> > > to vm_ops by using these functions. This allows to use ptrace() with
> >
> > "to vm_ops" must come after "function".
> >
> > But lemme ask what is "vm_ops"?
>
> I assume this is a rethorical question and I notice what I suggested
> looks as bad as my earlier commit message :-)
>
> So, I gave it some thought that and decided to "open code" the paragraph
> as
>
> "Add sgx_vma_access() function that implements 'access' virtual function
> of struct vm_operations_struct. Use formentioned leaf instructions to
> achieve read and write primitives for the enclave memory."
>
> I think this starts to have the right balance and is understandable.
>
> Still open for futher suggestion of course.

I'm not sure if I said it already but I also added cc to linux-mm (same
CC's in the patch as with mprotect callback commit). This should also
have mm ack I think.

/Jarkko