[PATCH v2 3/7] mm: introduce memfd_secret system call to create "secret" memory areas

[Catalin Marinas]

On Fri, Jul 31, 2020 at 03:29:05PM +0100, Mark Rutland wrote:
> On Thu, Jul 30, 2020 at 05:22:10PM +0100, Catalin Marinas wrote:
> > On Mon, Jul 27, 2020 at 07:29:31PM +0300, Mike Rapoport wrote:
> > > +static int secretmem_mmap(struct file *file, struct vm_area_struct *vma)
> > > +{
> > > +	struct secretmem_ctx *ctx = file->private_data;
> > > +	unsigned long mode = ctx->mode;
> > > +	unsigned long len = vma->vm_end - vma->vm_start;
> > > +
> > > +	if (!mode)
> > > +		return -EINVAL;
> > > +
> > > +	if ((vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) == 0)
> > > +		return -EINVAL;
> > > +
> > > +	if (mlock_future_check(vma->vm_mm, vma->vm_flags | VM_LOCKED, len))
> > > +		return -EAGAIN;
> > > +
> > > +	switch (mode) {
> > > +	case SECRETMEM_UNCACHED:
> > > +		vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
> > > +		fallthrough;
> > > +	case SECRETMEM_EXCLUSIVE:
> > > +		vma->vm_ops = &secretmem_vm_ops;
> > > +		break;
> > > +	default:
> > > +		return -EINVAL;
> > > +	}
> > > +
> > > +	vma->vm_flags |= VM_LOCKED;
> > > +
> > > +	return 0;
> > > +}
> > 
> > I think the uncached mapping is not the right thing for arm/arm64. First
> > of all, pgprot_noncached() gives us Strongly Ordered (Device memory)
> > semantics together with not allowing unaligned accesses. I suspect the
> > semantics are different on x86.
> 
> > The second, more serious problem, is that I can't find any place where
> > the caches are flushed for the page mapped on fault. When a page is
> > allocated, assuming GFP_ZERO, only the caches are guaranteed to be
> > zeroed. Exposing this subsequently to user space as uncached would allow
> > the user to read stale data prior to zeroing. The arm64
> > set_direct_map_default_noflush() doesn't do any cache maintenance.
> 
> It's also worth noting that in a virtual machine this is liable to be
> either broken (with a potential loss of coherency if the host has a
> cacheable alias as existing KVM hosts have), or pointless (if the host
> uses S2FWB to upgrade Stage-1 attribues to cacheable as existing KVM
> hosts also have).
> 
> I think that trying to avoid the data caches creates many more problems
> than it solves, and I don't think there's a strong justification for
> trying to support that on arm64 to begin with, so I'd rather entirely
> opt-out on supporting SECRETMEM_UNCACHED.

Good point, I forgot the virtualisation aspect. So unless there is a
hypervisor API to unmap it from the host memory, the uncached option
isn't of much use on arm64.

-- 
Catalin