Russell King writes:
> I'm doing it _NOW_, but I'm having to rotate the checksum
> at the end if dst & 1, only to have it unrotated in an
> inefficient manner in csum_block_*. Seems a bit of a
> waste of CPU cycles.
This is certainly the kind of enhancement we can make, where
possible. No
On Sun, Apr 29, 2001 at 04:06:16AM -0700, David S. Miller wrote:
> I understand that you are frustruated about this and it
> requires you to touch some delicate assembly. But I'm
> going to be blunt and say "tough", because everyone has
> to implement this correctly. Just do it and get it
> over
Russell King writes:
> Or am I missing something?
csum_block_*() has nothing to do with checksumming buffers, it 2's
complement adds two integers passed as arguments based upon the offset
of one of the buffers (this decides if one of the csums needs to be
byte swapped before the 2's complement
On Sun, Apr 29, 2001 at 10:17:39AM +0100, Russell King wrote:
> On Sun, Apr 29, 2001 at 01:18:43AM -0700, David S. Miller wrote:
> > Occaisionally I find that sparc64 is making a gross error or invalid
> > assumption, and I accept this and fix it up.
>
> Ok, I see precisely what's going on here n
On Sun, Apr 29, 2001 at 01:18:43AM -0700, David S. Miller wrote:
> Occaisionally I find that sparc64 is making a gross error or invalid
> assumption, and I accept this and fix it up.
Ok, I see precisely what's going on here now, shame you didn't explain
about these csum_add stuff in your first ma
On Sun, Apr 29, 2001 at 01:18:43AM -0700, David S. Miller wrote:
> When I don't have the time, my port tends to break too.
> This isn't news to you is it?
Of course not.
> testl $2, %edi # Check alignment.
Hang on - you mean that this isn't equivalent to:
dst &
Russell King writes:
> Can someone please explain to me the rationale behind the zerocopy
> implementation that has appeared in 2.4.4 please?
You've had at least 2 months to ask this question. Like I have asked
several others I am going to ask you, why you are complaining now?
I see you merg
7 matches
Mail list logo
