On Mon, Jun 09, 2003 at 02:22:53AM -0700, David S. Miller wrote: > From: Herbert Xu <herbert@gondor.apana.org.au> > Date: Mon, 9 Jun 2003 19:21:56 +1000 > > However, should I bother with smp_call_function? It seems that I'll have > to disable local IRQs at least once on the fast path to use it. > Alternatively I can stay with the rcu and just wait for the callbacks > to finish. > > A forced operation is the only way. If no more packets traverse the > flow cache lookup, the whole engine deadlocks. It really is necessary > to get in there and force the issue. Please have a look at my previous patch (just ignore the destructors :) The references will disappear after the next rcu transition which is not dependent on packets flowing through the engine. -- Debian GNU/Linux 3.0 is out! ( http://www.debian.org/ ) Email: Herbert Xu ~{PmV>HI~} <herbert@gondor.apana.org.au> Home Page: http://gondor.apana.org.au/~herbert/ PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt - : send the line "unsubscribe linux-net" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
