From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757871AbaISSbZ (ORCPT ); Fri, 19 Sep 2014 14:31:25 -0400 Received: from devils.ext.ti.com ([198.47.26.153]:44332 "EHLO devils.ext.ti.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1757853AbaISSbW (ORCPT ); Fri, 19 Sep 2014 14:31:22 -0400 Message-ID: <541C764C.9030301@ti.com> Date: Fri, 19 Sep 2014 21:30:36 +0300 From: Grygorii Strashko User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:31.0) Gecko/20100101 Thunderbird/31.1.1 MIME-Version: 1.0 To: Mark Salter , Will Deacon CC: Catalin Marinas , "linux-kernel@vger.kernel.org" , "linux-arm-kernel@lists.infradead.org" , "jcm@redhat.com" Subject: Re: [PATCH] arm64/pci: fix dma coherency inheritance for PCI devices References: <1411141886-11310-1-git-send-email-msalter@redhat.com> <20140919162859.GG20773@arm.com> <1411144934.25340.34.camel@deneb.redhat.com> In-Reply-To: <1411144934.25340.34.camel@deneb.redhat.com> Content-Type: text/plain; charset="windows-1252" Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Hi Mark, On 09/19/2014 07:42 PM, Mark Salter wrote: > On Fri, 2014-09-19 at 17:28 +0100, Will Deacon wrote: >> On Fri, Sep 19, 2014 at 04:51:26PM +0100, Mark Salter wrote: >>> The default dma_ops for devices on arm64 systems are noncoherent in >>> nature and rely upon special operations and bounce buffers to >>> perform a device DMA operation to/from memory. Some drivers rely >>> upon coherent operations involving suitably capable hardware. In >>> this case, a "dma-coherent" property will exist on the corresponding >>> Device Tree node for the bridge device, or one of its ancestors. >>> This patch adds support for applying a DMA coherent dma_ops for >>> PCI devices in the case of such a property. >>> >>> Signed-off-by: Jon Masters >>> [added search for device with of_node] >>> Signed-off-by: Mark Salter >>> --- >>> arch/arm64/mm/dma-mapping.c | 21 +++++++++++++++++++-- >>> 1 file changed, 19 insertions(+), 2 deletions(-) >>> >>> diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c >>> index 4164c5a..0e26bd7 100644 >>> --- a/arch/arm64/mm/dma-mapping.c >>> +++ b/arch/arm64/mm/dma-mapping.c >>> @@ -23,10 +23,12 @@ >>> #include >>> #include >>> #include >>> +#include >>> #include >>> #include >>> #include >>> #include >>> +#include >>> >>> #include >>> >>> @@ -316,8 +318,18 @@ static int dma_bus_notifier(struct notifier_block *nb, >>> if (event != BUS_NOTIFY_ADD_DEVICE) >>> return NOTIFY_DONE; >>> >>> - if (of_property_read_bool(dev->of_node, "dma-coherent")) >>> - set_dma_ops(dev, &coherent_swiotlb_dma_ops); >>> + /* >>> + * Some devices won't have an of_node but a bus controller/bridge will. >>> + * Search up the device chain until we find an of_node to check. >>> + */ >>> + while (dev) { >>> + if (dev->of_node) { >>> + if (of_dma_is_coherent(dev->of_node)) >>> + set_dma_ops(_dev, &coherent_swiotlb_dma_ops); >>> + break; >>> + } >>> + dev = dev->parent; >>> + } >> >> Hmm, how does this interact with of_dma_configure? I don't think the >> dma-coherent property is inherited there, so I'm uneasy about doing this for >> buses other than PCI (i.e. the platform bus). > > of_dma_configure() only gets called for platform bus and it It's going to be used for AMBA bus too - "[PATCH] of: amba: use of_dma_configure for AMBA devices" http://www.spinics.net/lists/arm-kernel/msg363169.html > uses of_dma_is_coherent() which searches device ancestors for > dma-coherent property. But it uses set_arch_dma_coherent_ops() of_dma_is_coherent() will search from current Device node and all its ancestors. > which is a no-op on arm64 now. Catalin mentions this in another > thread: https://lkml.org/lkml/2014/9/15/363 > > So maybe we should fix set_arch_dma_coherent_ops() and drop > platform bus from the notifier handler. Yes. That will allow you to drop platform bus notifier handler. Actually, if patch "[PATCH] of: amba: use of_dma_configure for AMBA devices" will be merged then notifier for AMBA bus can be dropped too. > >> >> In other words, we should move to using of_dma_configure for the platform >> and amba buses, and have a separate notifier for the PCI bus. Is it likely >> that people will have a mixture of coherent and non-coherent devices behind >> the same host controller? >> Also, there is a patch which updates DT documentation for DMA properties, but it's not been merged accidentally :( "Re: [PATCH] dt/documentation: add specification of dma bus information" https://lkml.org/lkml/2014/6/22/144 Regards, -grygorii