From: "Andrew F. Davis" <afd@ti.com> To: Christoph Hellwig <hch@infradead.org>, Laura Abbott <labbott@redhat.com> Cc: John Stultz <john.stultz@linaro.org>, lkml <linux-kernel@vger.kernel.org>, Benjamin Gaignard <benjamin.gaignard@linaro.org>, Sumit Semwal <sumit.semwal@linaro.org>, Liam Mark <lmark@codeaurora.org>, Pratik Patel <pratikp@codeaurora.org>, Brian Starkey <Brian.Starkey@arm.com>, Vincent Donnefort <Vincent.Donnefort@arm.com>, Sudipto Paul <Sudipto.Paul@arm.com>, Xu YiPing <xuyiping@hisilicon.com>, "Chenfeng (puck)" <puck.chen@hisilicon.com>, butao <butao@hisilicon.com>, "Xiaqing (A)" <saberlily.xia@hisilicon.com>, Yudongbin <yudongbin@hisilicon.com>, Chenbo Feng <fengc@google.com>, Alistair Strachan <astrachan@google.com>, dri-devel <dri-devel@lists.freedesktop.org> Subject: Re: [PATCH v6 4/5] dma-buf: heaps: Add CMA heap to dmabuf heaps Date: Thu, 25 Jul 2019 09:47:11 -0400 [thread overview] Message-ID: <18975c1a-7e4e-fab3-eec8-387fbf9dcfe5@ti.com> (raw) In-Reply-To: <20190725124820.GC20286@infradead.org> On 7/25/19 8:48 AM, Christoph Hellwig wrote: > On Wed, Jul 24, 2019 at 07:38:07AM -0400, Laura Abbott wrote: >> It's not just an optimization for Ion though. Ion was designed to >> let the callers choose between system and multiple CMA heaps. > > Who cares about ion? That some out of tree android crap that should > not be relevant for upstream except as an example for how not to design > things.. > Tell us how you really feel about ION :) >> On other >> systems there may be multiple CMA regions dedicated to a specific >> purpose or placed at a specific address. The callers need to >> be able to choose exactly whether they want a particular CMA region >> or discontiguous regions. > > At least in cma is only used either with the global pool or a per-device > cma pool. I think if you want to make this new dma-buf API fit in with > the rest with the kernel you follow that model, and pass in a struct > device to select the particular cma area, similar how the DMA allocator > works. > This is a central allocator, it is not tied to any one device. If we knew the one device ahead of time we would just use the existing dma_alloc. We might be able to solve some of that with late mapping after all the devices attach to the buffer, but even then, which device's CMA area would we chose to use from all the attached devices? I can agree that allocating from per-device CMA using Heaps doesn't make much sense, but for global pools I'm not sure I see any way to allow devices to select which pool is right for a specific use. They don't have the full use-case information like the application does, the selection needs to be made from the application. Andrew
WARNING: multiple messages have this Message-ID (diff)
From: "Andrew F. Davis" <afd@ti.com> To: Christoph Hellwig <hch@infradead.org>, Laura Abbott <labbott@redhat.com> Cc: Yudongbin <yudongbin@hisilicon.com>, Alistair Strachan <astrachan@google.com>, Xu YiPing <xuyiping@hisilicon.com>, Vincent Donnefort <Vincent.Donnefort@arm.com>, "Chenfeng (puck)" <puck.chen@hisilicon.com>, dri-devel <dri-devel@lists.freedesktop.org>, Chenbo Feng <fengc@google.com>, lkml <linux-kernel@vger.kernel.org>, Liam Mark <lmark@codeaurora.org>, "Xiaqing (A)" <saberlily.xia@hisilicon.com>, Sudipto Paul <Sudipto.Paul@arm.com>, Pratik Patel <pratikp@codeaurora.org>, butao <butao@hisilicon.com> Subject: Re: [PATCH v6 4/5] dma-buf: heaps: Add CMA heap to dmabuf heaps Date: Thu, 25 Jul 2019 09:47:11 -0400 [thread overview] Message-ID: <18975c1a-7e4e-fab3-eec8-387fbf9dcfe5@ti.com> (raw) In-Reply-To: <20190725124820.GC20286@infradead.org> On 7/25/19 8:48 AM, Christoph Hellwig wrote: > On Wed, Jul 24, 2019 at 07:38:07AM -0400, Laura Abbott wrote: >> It's not just an optimization for Ion though. Ion was designed to >> let the callers choose between system and multiple CMA heaps. > > Who cares about ion? That some out of tree android crap that should > not be relevant for upstream except as an example for how not to design > things.. > Tell us how you really feel about ION :) >> On other >> systems there may be multiple CMA regions dedicated to a specific >> purpose or placed at a specific address. The callers need to >> be able to choose exactly whether they want a particular CMA region >> or discontiguous regions. > > At least in cma is only used either with the global pool or a per-device > cma pool. I think if you want to make this new dma-buf API fit in with > the rest with the kernel you follow that model, and pass in a struct > device to select the particular cma area, similar how the DMA allocator > works. > This is a central allocator, it is not tied to any one device. If we knew the one device ahead of time we would just use the existing dma_alloc. We might be able to solve some of that with late mapping after all the devices attach to the buffer, but even then, which device's CMA area would we chose to use from all the attached devices? I can agree that allocating from per-device CMA using Heaps doesn't make much sense, but for global pools I'm not sure I see any way to allow devices to select which pool is right for a specific use. They don't have the full use-case information like the application does, the selection needs to be made from the application. Andrew _______________________________________________ dri-devel mailing list dri-devel@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/dri-devel
next prev parent reply other threads:[~2019-07-25 13:47 UTC|newest] Thread overview: 53+ messages / expand[flat|nested] mbox.gz Atom feed top 2019-06-24 19:49 [PATCH v6 0/5] DMA-BUF Heaps (destaging ION) John Stultz 2019-06-24 19:49 ` [PATCH v6 1/5] dma-buf: Add dma-buf heaps framework John Stultz 2019-06-24 19:49 ` [PATCH v6 2/5] dma-buf: heaps: Add heap helpers John Stultz 2019-06-24 19:49 ` John Stultz 2019-07-18 10:06 ` Christoph Hellwig 2019-07-23 4:09 ` John Stultz 2019-07-23 4:09 ` John Stultz 2019-07-23 20:09 ` Rob Clark 2019-07-23 20:09 ` Rob Clark 2019-07-24 6:55 ` Christoph Hellwig 2019-07-24 6:55 ` Christoph Hellwig 2019-07-24 15:20 ` Andrew F. Davis 2019-07-24 15:20 ` Andrew F. Davis 2019-07-25 12:41 ` Christoph Hellwig 2019-07-25 12:41 ` Christoph Hellwig 2019-07-25 15:23 ` Rob Clark 2019-07-25 15:23 ` Rob Clark 2019-07-24 6:58 ` Christoph Hellwig 2019-07-24 6:58 ` Christoph Hellwig 2019-06-24 19:49 ` [PATCH v6 3/5] dma-buf: heaps: Add system heap to dmabuf heaps John Stultz 2019-06-24 19:49 ` [PATCH v6 4/5] dma-buf: heaps: Add CMA " John Stultz 2019-07-18 10:08 ` Christoph Hellwig 2019-07-23 5:04 ` John Stultz 2019-07-23 5:04 ` John Stultz 2019-07-24 6:59 ` Christoph Hellwig 2019-07-24 8:08 ` Benjamin Gaignard 2019-07-25 12:45 ` Christoph Hellwig 2019-07-24 11:38 ` Laura Abbott 2019-07-25 12:48 ` Christoph Hellwig 2019-07-25 13:47 ` Andrew F. Davis [this message] 2019-07-25 13:47 ` Andrew F. Davis 2019-07-25 14:05 ` Christoph Hellwig 2019-07-24 15:46 ` Andrew F. Davis 2019-07-25 12:50 ` Christoph Hellwig 2019-07-25 13:31 ` Andrew F. Davis 2019-07-25 13:31 ` Andrew F. Davis 2019-07-25 14:04 ` Christoph Hellwig 2019-07-25 14:10 ` Andrew F. Davis 2019-07-25 14:11 ` Christoph Hellwig 2019-07-25 14:25 ` Andrew F. Davis 2019-07-25 14:30 ` Christoph Hellwig 2019-07-25 14:51 ` Andrew F. Davis 2019-07-25 14:51 ` Andrew F. Davis 2019-07-24 18:46 ` John Stultz 2019-07-24 18:46 ` John Stultz 2019-07-25 12:52 ` Christoph Hellwig 2019-07-25 13:20 ` Benjamin Gaignard 2019-07-25 14:33 ` Christoph Hellwig 2019-07-25 14:46 ` Benjamin Gaignard 2019-06-24 19:49 ` [PATCH v6 5/5] kselftests: Add dma-heap test John Stultz 2019-06-24 19:49 ` John Stultz 2019-07-01 21:45 ` [PATCH v6 0/5] DMA-BUF Heaps (destaging ION) Laura Abbott 2019-07-01 21:55 ` John Stultz
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=18975c1a-7e4e-fab3-eec8-387fbf9dcfe5@ti.com \ --to=afd@ti.com \ --cc=Brian.Starkey@arm.com \ --cc=Sudipto.Paul@arm.com \ --cc=Vincent.Donnefort@arm.com \ --cc=astrachan@google.com \ --cc=benjamin.gaignard@linaro.org \ --cc=butao@hisilicon.com \ --cc=dri-devel@lists.freedesktop.org \ --cc=fengc@google.com \ --cc=hch@infradead.org \ --cc=john.stultz@linaro.org \ --cc=labbott@redhat.com \ --cc=linux-kernel@vger.kernel.org \ --cc=lmark@codeaurora.org \ --cc=pratikp@codeaurora.org \ --cc=puck.chen@hisilicon.com \ --cc=saberlily.xia@hisilicon.com \ --cc=sumit.semwal@linaro.org \ --cc=xuyiping@hisilicon.com \ --cc=yudongbin@hisilicon.com \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.