[PATCH v15 00/17] arm64: untag user pointers passed to the kernel

[Catalin Marinas]

On Wed, May 22, 2019 at 04:09:31PM -0700, enh wrote:
> On Wed, May 22, 2019 at 4:03 PM Evgenii Stepanov <eugenis at google.com> wrote:
> > On Wed, May 22, 2019 at 1:47 PM Kees Cook <keescook at chromium.org> wrote:
> > > On Wed, May 22, 2019 at 05:35:27PM +0100, Catalin Marinas wrote:
> > > > I would also expect the C library or dynamic loader to check for the
> > > > presence of a HWCAP_MTE bit before starting to tag memory allocations,
> > > > otherwise it would get SIGILL on the first MTE instruction it tries to
> > > > execute.
> > >
> > > I've got the same question as Elliot: aren't MTE instructions just NOP
> > > to older CPUs? I.e. if the CPU (or kernel) don't support it, it just
> > > gets entirely ignored: checking is only needed to satisfy curiosity
> > > or behavioral expectations.
> >
> > MTE instructions are not NOP. Most of them have side effects (changing
> > register values, zeroing memory).
> 
> no, i meant "they're encoded in a space that was previously no-ops, so
> running on MTE code on old hardware doesn't cause SIGILL".

It does result in SIGILL, there wasn't enough encoding left in the NOP
space for old/current CPU implementations (in hindsight, we should have
reserved a bigger NOP space).

As Evgenii said, the libc needs to be careful when tagging the heap as
it would cause a SIGILL if the HWCAP_MTE is not set. The standard
application doesn't need to be recompiled as it would not issue MTE
colouring instructions, just standard LDR/STR.

Stack tagging is problematic if you want to colour each frame
individually, the function prologue would need the non-NOP MTE
instructions. The best we can do here is just having the (thread) stacks
of different colours.

-- 
Catalin