On Mon, Nov 03, 2025 at 11:20:13AM +0100, Stefano Brivio wrote:
> On Mon,  3 Nov 2025 11:16:08 +0100
> Stefano Brivio <sbrivio@redhat.com> wrote:
> 
> > IEEE 802.3 requires a minimum frame payload of 46 bytes, without a
> > 802.1Q tag. Add padding for the simple tap_send_single() case using
> > a zero-filled 60-byte buffer and copying data to it if needed.
> > 
> > In theory, we could add a further element in the iovec array, say:
> > 
> > 	uint8_t padding[ETH_ZLEN] = { 0 };
> > 	struct iovec iov[3];
> > 
> > 	...
> > 
> > 		if (l2len < ETH_ZLEN) {
> > 			iov[iovcnt].iov_base = (void *)padding;
> > 			iov[iovcnt].iov_len = ETH_ZLEN - l2len;
> > 			iovcnt++;
> > 		}
> > 
> > and avoid a copy, but that would substantially complicate the
> > vhost-user path, and it's questionable whether passing a reference
> > to a further buffer actually causes lower overhead than the simple
> > copy.
> > 
> > Link: https://bugs.passt.top/show_bug.cgi?id=166
> > Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
> > ---
> >  tap.c | 7 +++++++
> >  1 file changed, 7 insertions(+)
> > 
> > diff --git a/tap.c b/tap.c
> > index bb139d6..8d8d84b 100644
> > --- a/tap.c
> > +++ b/tap.c
> > @@ -131,9 +131,16 @@ unsigned long tap_l2_max_len(const struct ctx *c)
> >  void tap_send_single(const struct ctx *c, const void *data, size_t l2len)
> >  {
> >  	uint32_t vnet_len = htonl(l2len);
> > +	uint8_t padded[ETH_ZLEN] = { 0 };
> >  	struct iovec iov[2];
> >  	size_t iovcnt = 0;
> >  
> > +	if (l2len < ETH_ZLEN) {
> > +		memcpy(padded, data, l2len);
> > +		data = padded;
> > +		l2len = ETH_ZLEN;
> > +	}
> 
> Sorry, botched rebase, this should update vnet_len as well, which I
> missed on the first attempt. I'll fix this in the next spin.

Oh... yeah... should have caught that, oops.

> 
> > +
> >  	switch (c->mode) {
> >  	case MODE_PASST:
> >  		iov[iovcnt] = IOV_OF_LVALUE(vnet_len);
> 
> -- 
> Stefano
> 

-- 
David Gibson (he or they)	| I'll have my music baroque, and my code
david AT gibson.dropbear.id.au	| minimalist, thank you, not the other way
				| around.
http://www.ozlabs.org/~dgibson