netdev
[Top] [All Lists]

Re: [PATCH 2.6] natsemi.c NAPI

To: "David S. Miller" <davem@xxxxxxxxxxxxx>
Subject: Re: [PATCH 2.6] natsemi.c NAPI
From: Jeff Garzik <jgarzik@xxxxxxxxx>
Date: Mon, 20 Sep 2004 15:07:46 -0400
Cc: Harald Welte <laforge@xxxxxxxxxxxx>, netdev@xxxxxxxxxxx
In-reply-to: <20040920115746.7ccbfb45.davem@xxxxxxxxxxxxx>
References: <20040920141030.GV1307@xxxxxxxxxxxxxxxxxxxxxxx> <20040920115746.7ccbfb45.davem@xxxxxxxxxxxxx>
Sender: netdev-bounce@xxxxxxxxxxx
User-agent: Mutt/1.4.1i
On Mon, Sep 20, 2004 at 11:57:46AM -0700, David S. Miller wrote:
> This driver (before the NAPI patch) is a bit buggy, it does
> no RX processing SMP locking.  So if one one cpu you're doing
> RX interrupt processing, and on another cpu tx_timeout() runs
> we're totally screwed.

RX processing in current natsemi only happens in irq, and the natsemi
driver properly disables irqs when it needs to, AFAICS, using
enable/disable_irq().

        Jeff




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