From mboxrd@z Thu Jan 1 00:00:00 1970 From: Thomas Bogendoerfer Subject: Re: [PATCH 22/28] sgiseeq: convert from dma_cache_sync to dma_sync_single_for_device Date: Tue, 1 Sep 2020 19:38:10 +0200 Message-ID: <20200901173810.GA25282@alpha.franken.de> References: <20200819065555.1802761-1-hch@lst.de> <20200819065555.1802761-23-hch@lst.de> <20200901152209.GA14288@alpha.franken.de> <20200901171241.GA20685@alpha.franken.de> <20200901171627.GA8255@lst.de> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: Content-Disposition: inline In-Reply-To: <20200901171627.GA8255-jcswGhMUV9g@public.gmane.org> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: iommu-bounces-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org Sender: "iommu" To: Christoph Hellwig Cc: alsa-devel-K7yf7f+aM1XWsZ/bQMPhNw@public.gmane.org, linux-ia64-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, linux-doc-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, nouveau-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org, linux-nvme-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r@public.gmane.org, linux-mips-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, "James E.J. Bottomley" , linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org, linux-samsung-soc-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, Joonyoung Shim , linux-scsi-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org, Ben Skeggs , Matt Porter , linux-media-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, Tom Lendacky , Pawel Osciak , Mauro Carvalho Chehab , linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r@public.gmane.org, linux-parisc-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, netdev-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, Seung-Woo Kim , linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, Kyungmin Park List-Id: nouveau.vger.kernel.org On Tue, Sep 01, 2020 at 07:16:27PM +0200, Christoph Hellwig wrote: > Well, if IP22 doesn't speculate (which I'm pretty sure is the case), > dma_sync_single_for_cpu should indeeed be a no-op. But then there > also shouldn't be anything in the cache, as the previous > dma_sync_single_for_device should have invalidated it. So it seems like > we are missing one (or more) ownership transfers to the device. I'll > try to look at the the ownership management in a little more detail > tomorrow. this is the problem: /* Always check for received packets. */ sgiseeq_rx(dev, sp, hregs, sregs); so the driver will look at the rx descriptor on every interrupt, so we cache the rx descriptor on the first interrupt and if there was $no rx packet, we will only see it, if cache line gets flushed for some other reason. kick_tx() does a busy loop checking tx descriptors, with just sync_desc_cpu... Thomas. -- Crap can work. Given enough thrust pigs will fly, but it's not necessarily a good idea. [ RFC1925, 2.3 ]