RE: [PATCH v7 0/8] Raid: enable talitos xor offload for improving performance

-----Original Message-----
From: Dan Williams [mailto:djbw@fb.com]
Sent: Wednesday, August 29, 2012 10:53 PM
To: Liu Qiang-B32616
Cc: vinod.koul@intel.com; arnd@arndb.de; herbert@gondor.apana.org.au;
gregkh@linuxfoundation.org; linuxppc-dev@lists.ozlabs.org; linux-
kernel@vger.kernel.org; linux-crypto@vger.kernel.org; Ira W. Snyder
Subject: Re: [PATCH v7 0/8] Raid: enable talitos xor offload for
improving performance

On Wed, 2012-08-29 at 11:15 +0000, Liu Qiang-B32616 wrote:

quoted

Hi Dan,

Ping?
Can you apply these patches? Thanks.

I'm working my way through them.

The first thing I notice is that xor_chan->desc_lock is taken
inconsistently.  I.e. spin_lock_irqsave() in talitos_process_pending()
and spin_lock_bh() everywhere else.  Have you run these patches with
lockdep?

Thanks for your reply.
LOCKDEP is enabled as you suggested, there is not any info about "inconsistent lock state" displayed.
I don't know whether it's enough.

I'm confused about the attribute of DMA_INTERRUPT, my understanding is this interface is only used to trigger an interrupt (make sure all former operations are finished before switching to other channels), but fsl-dma will trigger an interrupt by "Programmed Error". I'm wondering whether other hardware are same with fsl-dma (the interrupt is a normal interrupt, but not an error) i.e. xscale-iop?
If other hardware also trigger an interrupt by an abnormal error, maybe my patch 2/8 should be reverted because it violates the rules of this attribute.

BTW, could you please reply in the patch if you have any comments. Thanks.

--
Dan