[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <CAHrpEqTQBbNVAVN5FDTYAnnO9gX_WXdC9xgq7X4+gtYJoHjpDg@mail.gmail.com>
Date: Tue, 29 Jan 2013 13:03:38 +0800
From: Frank Li <lznuaa@...il.com>
To: Francois Romieu <romieu@...zoreil.com>
Cc: "Waskiewicz Jr, Peter P" <peter.p.waskiewicz.jr@...el.com>,
Frank Li <Frank.Li@...escale.com>, shawn.guo@...aro.org,
B38611@...escale.com, davem@...emloft.net,
linux-arm-kernel@...ts.infradead.org, netdev@...r.kernel.org,
s.hauer@...gutronix.de
Subject: Re: [PATCH v3 1/1 net-next] net: fec: add napi support to improve proformance
2013/1/26 Francois Romieu <romieu@...zoreil.com>:
> Waskiewicz Jr, Peter P <peter.p.waskiewicz.jr@...el.com> :
> [...]
>> Also, when you're disabling interrupts above, you're doing that in your
>> HW interrupt handler, you should be using spin_lock_irqsave()/irq_restore().
>
> Does the platform forbid to defer FEC_EIR / FEC_IEVENT write to the napi
I can clean FEC_IEVENT, but rx irq still issue if new package
received. I tested, performance drop if just clean FEC_IEVENT
> poll handler and only disable the irq through FEC_EIMR / FEC_IMASK in
> fec_enet_interrupt so as to remove the spinlock ?
I can remove this spin lock in other way. I will send new patch.
>
> (Frank, please keep an empty line between variables declarations and
> function body).
Okay.
>
> --
> Ueimor
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists