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 15:33:08 -0700
Cc: herbert@xxxxxxxxxxxxxxxxxxx, vda@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxx, netdev@xxxxxxxxxxx, linux-kernel@xxxxxxxxxxxxxxx, maxk@xxxxxxxxxxxx, irda-users@xxxxxxxxxxxxxxxxxxxxx
In-reply-to: <1098223857.23367.35.camel@krustophenia.net>
References: <E1CK1e6-0004F3-00@gondolin.me.apana.org.au> <1098222676.23367.18.camel@krustophenia.net> <20041019215401.GA16427@gondor.apana.org.au> <1098223857.23367.35.camel@krustophenia.net>
Sender: netdev-bounce@xxxxxxxxxxx
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.

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