This is a very early draft - in a different world would be replaced by hallway discussion at in-person conference - aimed at outlining some ideas and collect feedback on the overall outlook. There are still bugs to be fixed, more test and benchmark need, etc. There are 3 main goals: - [try to] avoid the overhead for uncommon conditions at GRO time (patches 1-4) - enable backpressure for the veth GRO path (patches 5-6) - reduce the number of cacheline used by the sk_buff lifecycle from 4 to 3, at least in some common scenarios (patches 1,7-9). The idea here is avoid the initialization of some fields and control their validity with a bitmask, as presented by at least Florian and Jesper in the past. The above requires a bit of code churn in some places and, yes, a few new bits in the sk_buff struct (using some existing holes) Paolo Abeni (9): sk_buff: track nfct status in newly added skb->_state sk_buff: track dst status in skb->_state sk_buff: move the active_extensions into the state bitfield net: optimize GRO for the common case. skbuff: introduce has_sk state bit. veth: use skb_prepare_for_gro() sk_buff: move inner header fields after tail sk_buff: move vlan field after tail. sk_buff: access secmark via getter/setter drivers/net/veth.c | 2 +- include/linux/skbuff.h | 117 ++++++++++++++++++++++--------- include/net/dst.h | 3 + include/net/sock.h | 9 +++ net/core/dev.c | 31 +++++--- net/core/skbuff.c | 40 +++++++---- net/netfilter/nfnetlink_queue.c | 6 +- net/netfilter/nft_meta.c | 6 +- net/netfilter/xt_CONNSECMARK.c | 8 +-- net/netfilter/xt_SECMARK.c | 2 +- security/apparmor/lsm.c | 15 ++-- security/selinux/hooks.c | 10 +-- security/smack/smack_lsm.c | 4 +- security/smack/smack_netfilter.c | 4 +- 14 files changed, 175 insertions(+), 82 deletions(-) -- 2.26.3
