netdev
[Top] [All Lists]

Re: tun.c patch to fix "smp_processor_id() in preemptible code"

To: Lee Revell <rlrevell@xxxxxxxxxxx>
Subject: Re: tun.c patch to fix "smp_processor_id() in preemptible code"
From: "David S. Miller" <davem@xxxxxxxxxxxxx>
Date: Tue, 19 Oct 2004 15:42:49 -0700
Cc: herbert@xxxxxxxxxxxxxxxxxxx, vda@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxx, netdev@xxxxxxxxxxx, linux-kernel@xxxxxxxxxxxxxxx, maxk@xxxxxxxxxxxx, irda-users@xxxxxxxxxxxxxxxxxxxxx
In-reply-to: <1098225729.23628.2.camel@xxxxxxxxxxxxxxxx>
References: <E1CK1e6-0004F3-00@xxxxxxxxxxxxxxxxxxxxxxxx> <1098222676.23367.18.camel@xxxxxxxxxxxxxxxx> <20041019215401.GA16427@xxxxxxxxxxxxxxxxxxx> <1098223857.23367.35.camel@xxxxxxxxxxxxxxxx> <20041019153308.488d34c1.davem@xxxxxxxxxxxxx> <1098225729.23628.2.camel@xxxxxxxxxxxxxxxx>
Sender: netdev-bounce@xxxxxxxxxxx
On Tue, 19 Oct 2004 18:42:11 -0400
Lee Revell <rlrevell@xxxxxxxxxxx> wrote:

> On Tue, 2004-10-19 at 18:33, David S. Miller wrote:
> > On Tue, 19 Oct 2004 18:10:58 -0400
> > Lee Revell <rlrevell@xxxxxxxxxxx> wrote:
> > 
> > >   /*
> > >    * Since receiving is always initiated from a tasklet (in iucv.c),
> > >    * we must use netif_rx_ni() instead of netif_rx()
> > >    */
> > > 
> > > This implies that the author thought it was a matter of correctness to
> > > use netif_rx_ni vs. netif_rx.  But it looks like the only difference is
> > > that the former sacrifices preempt-safety for performance.
> > 
> > You can't really delete netif_rx_ni(), so if there is a preemptability
> > issue, just add the necessary preemption protection around the softirq
> > checks.
> > 
> 
> Why not?  AIUI the only valid reason to use preempt_disable/enable is in
> the case of per-CPU data.  This is not "real" per-CPU data, it's a
> performance hack.  Therefore it would be incorrect to add the preemption
> protection, the fix is not to manually call do_softirq but to let the
> softirq run by the normal mechanism.
> 
> Am I missing something?

In code paths where netif_rx_ni() is called, there is not a softirq return
path check, which is why it is checked here.

Theoretically, if you remove the check, softirq processing can be deferred
indefinitely.

What I'm saying, therefore, is that netif_rx_ni() it not just a performance
hack, it is necessary for correctness as well.

<Prev in Thread] Current Thread [Next in Thread>