RE: [PATCH 3/6] x86/tdx: Support vmalloc() for tdx_enc_status_changed()

[Dexuan Cui]

> From: Dave Hansen <dave.hansen@xxxxxxxxx>
> Sent: Monday, November 21, 2022 1:01 PM
> [...]
> On 11/21/22 11:51, Dexuan Cui wrote:
> > -static bool tdx_enc_status_changed(unsigned long vaddr, int numpages,
> bool enc)
> > +static bool tdx_enc_status_changed_for_contiguous_pages(unsigned long
> vaddr,
> > +							int numpages, bool enc)
> 
> That naming is unfortunate.
> 
> First, it's getting way too long.
> 
> Second, you don't need two of these functions because it's contiguous or
> not.  It's because tdx_enc_status_changed() only works on the direct map.

Will try to make one function with better naming.

> > +static bool tdx_enc_status_changed_for_vmalloc(unsigned long vaddr,
> > +					       int numpages, bool enc)
> > +{
> > +	void *start_va = (void *)vaddr;
> > +	void *end_va = start_va + numpages * PAGE_SIZE;
> > +	phys_addr_t pa;
> > +
> > +	if (offset_in_page(vaddr) != 0)
> > +		return false;
> > +
> > +	while (start_va < end_va) {
> > +		pa = slow_virt_to_phys(start_va);
> > +		if (!enc)
> > +			pa |= cc_mkdec(0);
> > +
> > +		if (!tdx_map_gpa(pa, pa + PAGE_SIZE, enc))
> > +			return false;
> > +
> > +		/*
> > +		 * private->shared conversion requires only MapGPA call.
> > +		 *
> > +		 * For shared->private conversion, accept the page using
> > +		 * TDX_ACCEPT_PAGE TDX module call.
> > +		 */
> > +		if (enc && !try_accept_one(&pa, PAGE_SIZE, PG_LEVEL_4K))
> > +			return false;
> 
> Don't we support large vmalloc() mappings these days?

I just noticed Nicholas Piggin's huge vmalloc mapping patches that were
merged in April 2021. I'll take a look and see what I can use here.

> > +		start_va += PAGE_SIZE;
> > +	}
> > +
> > +	return true;
> > +}
> 
> I really don't like the copy-and-paste fork here.
> 
> I'd almost just rather have this *one* "vmalloc" copy that does
> slow_virt_to_phys() on direct map addresses than have two copies.

It looks like typically set_memory_{de/en}crypted() are not invoked
frequently when Linux is running, e.g. the swiotlb bounce buffers are
only initialzed once with set_memory_decrypt(). A driver runs in a guest
on a hypervisor typically also only initializes the buffers (which need to
be shared with the hypervisor) with set_memory_decrypt() once when
the driver initializes the device. So, it looks like slow_virt_to_phys() may be
acceptable for configuous memory pages as well.

> Can you please look into making *one* function that works on either kind
> of mapping?

Ok. Looking into this using slow_virt_to_phys() for direct map
addresses as well.