On 2019-09-05, Peter Zijlstra [off-list ref] wrote:

On Thu, Sep 05, 2019 at 07:26:22PM +1000, Aleksa Sarai wrote:

quoted

On 2019-09-05, Peter Zijlstra [off-list ref] wrote:

quoted

On Thu, Sep 05, 2019 at 06:19:22AM +1000, Aleksa Sarai wrote:

quoted

+
+		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/>