On 2019-09-05, Peter Zijlstra <peterz@xxxxxxxxxxxxx> wrote:
> On Thu, Sep 05, 2019 at 07:26:22PM +1000, Aleksa Sarai wrote:
> > On 2019-09-05, Peter Zijlstra <peterz@xxxxxxxxxxxxx> wrote:
> > > On Thu, Sep 05, 2019 at 06:19:22AM +1000, Aleksa Sarai wrote:
> > > > +
> > > > + while (rest > 0) {
> > > > + size_t bufsize = min(rest, sizeof(buffer));
> > > > +
> > > > + if (__copy_from_user(buffer, addr, bufsize))
> > > > + return -EFAULT;
> > > > + if (memchr_inv(buffer, 0, bufsize))
> > > > + return -E2BIG;
> > > > +
> > > > + addr += bufsize;
> > > > + rest -= bufsize;
> > > > + }
> > >
> > > The perf implementation uses get_user(); but if that is too slow, surely
> > > we can do something with uaccess_try() here?
> >
> > Is there a non-x86-specific way to do that (unless I'm mistaken only x86
> > has uaccess_try() or the other *_try() wrappers)? The main "performance
> > improvement" (if you can even call it that) is that we use memchr_inv()
> > which finds non-matching characters more efficiently than just doing a
> > loop.
>
> Oh, you're right, that's x86 only :/
Though, I just had an idea -- am I wrong to think that the following
would work just as well (without the need for an intermediate buffer)?
if (memchr_inv((const char __force *) src + size, 0, rest))
return -E2BIG;
Or is this type of thing very much frowned upon? What if it was a
separate memchr_inv_user() instead -- I feel as though there's not a
strong argument for needing to use a buffer when we're single-passing
the __user buffer and doing a basic boolean check.
--
Aleksa Sarai
Senior Software Engineer (Containers)
SUSE Linux GmbH
<https://www.cyphar.com/>
Attachment:
signature.asc
Description: PGP signature
