[Top] [All Lists]

Re: serious netpoll bug w/NAPI

To: Matt Mackall <mpm@xxxxxxxxxxx>
Subject: Re: serious netpoll bug w/NAPI
From: "David S. Miller" <davem@xxxxxxxxxxxxx>
Date: Wed, 16 Feb 2005 15:02:36 -0800
Cc: jmoyer@xxxxxxxxxx, netdev@xxxxxxxxxxx
In-reply-to: <20050216050722.GC3358@xxxxxxxxx>
References: <20050208201634.03074349.davem@xxxxxxxxxxxxx> <20050209183219.GA2366@xxxxxxxxx> <20050209164658.409f8950.davem@xxxxxxxxxxxxx> <20050210011104.GF2366@xxxxxxxxx> <16914.31886.665975.522710@xxxxxxxxxxxxxxxxxxxxxxxxxx> <20050216050722.GC3358@xxxxxxxxx>
Sender: netdev-bounce@xxxxxxxxxxx
On Tue, 15 Feb 2005 21:07:22 -0800
Matt Mackall <mpm@xxxxxxxxxxx> wrote:

> Because dev->np->poll_lock now serializes all access to ->poll (when
> netpoll is enabled on said device).

I think there is still a problem.

Sure, we won't recurse into ->poll(), but instead we'll loop forever
in netpoll_send_skb() in this case when netif_queue_stopped() is true.
We can't get into the ->poll() routine, so the TX queue can't make
forward progress, yet we keep looping to the "repeat" label over
and over again.

So we've replaced a crash via ->poll() re-entry with a deadlock
in netpoll_send_skb() :-)

I also think that taking a global spinlock for every ->poll()
call is a huge price to pay on SMP.

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