On Thu, 2015-08-20 at 06:21 +0000, Grumbach, Emmanuel wrote: > > On 08/19/2015 11:39 PM, Eric Dumazet wrote: > > On Wed, 2015-08-19 at 19:17 +0000, Grumbach, Emmanuel wrote: > > > >> Hm.. how would net/core/tso.c avoid this? > > > > Because a driver using these helpers keep around the original LSO packet > > and frees it normally at TX completion time. > > > > Which is why I can't really use it. The complexity is that I have to > (ieee802.11 specification) split an LSO is several 802.11 packets. The > maximal 802.11 packet I can send under ideal condition is 11K long or > so. So I *must* generate several 802.11 frames from one single LSO > packet. OTOH, I can have more than MSS bytes in a 802.11 A-MSDU. >
Who said you had to free original packet ? Just keep it around. TCP will work better ( check skb_still_in_host_queue() helper if you want to know why) > Maybe what would help would be to be able to dynamically change the > maximal size of an LSO packet. That would allow the wifi driver to > ensure that the LSO can fit in a single 802.11 packet. Note that since > the maximal length of the A-MSDU can vary based on link conditions > (since there is only one CRC for the whole A-MSDU, you don't want long > A-MSDUs in bad link conditions) the driver would need to be able to tell > the TCP stack to modify the length of an LSO packet. > To me, this sounds to be ... an overkill? It is already doable. Check dev->gso_max_size ( and netif_set_gso_max_size()) Make sure you do not reinvent the wheel ;) -- To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
