Re: [PATCH RFC v3 1/2] mm: Add personality flag to limit address to 47 bits

[Charlie Jenkins <charlie@rivosinc.com>]

On Fri, Sep 13, 2024 at 11:08:23AM +0100, Catalin Marinas wrote:
> On Thu, Sep 12, 2024 at 02:15:59PM -0700, Charlie Jenkins wrote:
> > On Thu, Sep 12, 2024 at 11:53:49AM +0100, Catalin Marinas wrote:
> > > On Wed, Sep 11, 2024 at 11:18:12PM -0700, Charlie Jenkins wrote:
> > > > Opting-in to the higher address space is reasonable. However, it is not
> > > > my preference, because the purpose of this flag is to ensure that
> > > > allocations do not exceed 47-bits, so it is a clearer ABI to have the
> > > > applications that want this guarantee to be the ones setting the flag,
> > > > rather than the applications that want the higher bits setting the flag.
> > > 
> > > Yes, this would be ideal. Unfortunately those applications don't know
> > > they need to set a flag in order to work.
> > 
> > It's not a regression, the applications never worked (on platforms that
> > do not have this default). The 47-bit default would allow applications
> > that didn't work to start working at the cost of a non-ideal ABI. That
> > doesn't seem like a reasonable tradeoff to me.  If applications want to
> > run on new hardware that has different requirements, shouldn't they be
> > required to update rather than expect the kernel will solve their
> > problems for them?
> 
> That's a valid point but it depends on the application and how much you
> want to spend updating user-space. OpenJDK is fine, if you need a JIT
> you'll have to add support for that architecture anyway. But others are
> arch-agnostic, you just recompile to your target. It's not an ABI
> problem, more of an API one.

The arch-agnosticism is my hope with this personality flag, it can be
added arch-agnostic userspace code and allow the application to work
everywhere, but it does have the downside of requiring that change to
user-space code.

> 
> The x86 case (and powerpc/arm64) was different, the 47-bit worked for a
> long time before expanding it. So it made a lot of sense to keep the
> same default.

Yes it is very reasonable that this solution was selected for those
architectures since the support for higher address spaces evolved in the
manner that it did!

- Charlie

> 
> Anyway, the prctl() can go both ways, either expanding or limiting the
> default address space. So I'd be fine with such interface.
> 
> -- 
> Catalin