On 23.01.2018 19:58, Eric Dumazet wrote: >> >> Your original patch did not provide any test results. Only the fact >> synchronize_rcu_expedited() >> completes faster than plain synchronize_rcu(). But this is an obvious fact >> just because of the design, and this is described even in the documentation. >> Beleive me, I don't want to offend you this words, but it's strange you >> hadn't >> gone the way you suggest me. > > Well, I guess you missed the fine changelog. > > Please carefully read it : > > https://git.kernel.org/pub/scm/linux/kernel/git/davem/net.git/commit/?id=be3fc413da9eb17cce0991f214ab019d16c88c41
This is just what I said. > And you' ll noticed I had an Ack from Paul E. McKenney, the RCU maintainer. I won't ask you either you had the ACK before you sent the patch, because the answer is obvious. Anyway, this doesn't matter. I don't insist on the fix for this place. If you're so negative on this question, we may leave everything as is, and live with this ambiguous place several years more. Kirill