On Mon, Apr 21, 2008 at 01:04:18PM -0700, David Miller wrote: > From: Rusty Russell <rusty@xxxxxxxxxxxxxxx> > Date: Tue, 22 Apr 2008 05:06:16 +1000 > > > I'm not sure what the right number is here. Say worst case is header which > > goes over a page boundary then MAX_SKB_FRAGS in the skb, but for some reason > > that already has a +2: The +2 (i.e., extra +1) is for the virtio GSO header. > skb->data is linear, therefore it's not possible to need > more than one scatterlist entry for it. Theoretically yes :) But for virtualisation the underlying transport may present meta-physically contiguous memory that is physically discrete. So we may actually need to have multiple SG entries for skb->data. However, no current code path should generate packets with both long skb->data areas *and* skb page frags so we could just drop them if they show up. Cheers, -- Visit Openswan at http://www.openswan.org/ Email: Herbert Xu ~{PmV>HI~} <herbert@xxxxxxxxxxxxxxxxxxx> Home Page: http://gondor.apana.org.au/~herbert/ PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt _______________________________________________ Virtualization mailing list Virtualization@xxxxxxxxxxxxxxxxxxxxxxxxxx https://lists.linux-foundation.org/mailman/listinfo/virtualization
