From mboxrd@z Thu Jan 1 00:00:00 1970 From: Christoph Hellwig Subject: Re: [PATCH 22/28] sgiseeq: convert from dma_cache_sync to dma_sync_single_for_device Date: Thu, 3 Sep 2020 10:42:26 +0200 Message-ID: <20200903084226.GA24410@lst.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> <20200901173810.GA25282@alpha.franken.de> <20200902213809.GA7998@alpha.franken.de> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Content-Disposition: inline In-Reply-To: <20200902213809.GA7998@alpha.franken.de> Sender: netdev-owner@vger.kernel.org To: Thomas Bogendoerfer Cc: Christoph Hellwig , alsa-devel@alsa-project.org, linux-ia64@vger.kernel.org, linux-doc@vger.kernel.org, nouveau@lists.freedesktop.org, linux-nvme@lists.infradead.org, linux-kernel@vger.kernel.org, "James E.J. Bottomley" , linux-mm@kvack.org, Marek Szyprowski , linux-samsung-soc@vger.kernel.org, Joonyoung Shim , linux-scsi@vger.kernel.org, Kyungmin Park , Ben Skeggs , Matt Porter , linux-media@vger.kernel.org, Tom Lendacky , Pawel Osciak , Mauro Carvalho Chehab , linux-arm-kernel@lists.infradead.org, linux-parisc@vger.kern List-Id: nouveau.vger.kernel.org On Wed, Sep 02, 2020 at 11:38:09PM +0200, Thomas Bogendoerfer wrote: > the patch below fixes the problem. But is very wrong unfortunately. > static inline void dma_sync_desc_cpu(struct net_device *dev, void *addr) > { > - dma_cache_sync(dev->dev.parent, addr, sizeof(struct sgiseeq_rx_desc), > - DMA_FROM_DEVICE); > + struct sgiseeq_private *sp = netdev_priv(dev); > + > + dma_sync_single_for_device(dev->dev.parent, VIRT_TO_DMA(sp, addr), > + sizeof(struct sgiseeq_rx_desc), DMA_FROM_DEVICE); > } > > static inline void dma_sync_desc_dev(struct net_device *dev, void *addr) > { > - dma_cache_sync(dev->dev.parent, addr, sizeof(struct sgiseeq_rx_desc), > - DMA_TO_DEVICE); > + struct sgiseeq_private *sp = netdev_priv(dev); > + > + dma_sync_single_for_device(dev->dev.parent, VIRT_TO_DMA(sp, addr), > + sizeof(struct sgiseeq_rx_desc), DMA_TO_DEVICE); This is not how the DMA API works. You can only call dma_sync_single_for_{device,cpu} with the direction that the memory was mapped. It then transfer ownership to the device or the cpu, and the ownership of the memory is a fundamental concept that allows for reasoning about the caching interaction. > } > > -- > Crap can work. Given enough thrust pigs will fly, but it's not necessarily a > good idea. [ RFC1925, 2.3 ] ---end quoted text---