On 8/18/16 10:17 PM, Eric Dumazet wrote: > Why are you iterating the whole table ? > > Normally, udp_hashfn(net, ntohs(dport), udptable->mask) slot should be > enough to find all sockets bound to dport.
I took a tangent after in early mistake with the socket lookup and after that I
was focused on doing the right thing in udp_abort and did not revisit the
socket lookup. Reverted to __udp{4,6}_lib_lookup.
