All of lore.kernel.org
 help / color / mirror / Atom feed
From: Christoph Hellwig <hch@lst.de>
To: Robin Murphy <robin.murphy@arm.com>
Cc: Christoph Hellwig <hch@lst.de>, Tony Luck <tony.luck@intel.com>,
	Fenghua Yu <fenghua.yu@intel.com>,
	Thomas Bogendoerfer <tsbogend@alpha.franken.de>,
	iommu@lists.linux-foundation.org,
	Tomasz Figa <tfiga@chromium.org>, Joerg Roedel <joro@8bytes.org>,
	linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-ia64@vger.kernel.org, linux-mips@vger.kernel.org
Subject: Re: [PATCH 12/12] dma-mapping: move the dma_declare_coherent_memory documentation
Date: Fri, 11 Sep 2020 09:17:51 +0200	[thread overview]
Message-ID: <20200911071751.GG22394@lst.de> (raw)
In-Reply-To: <07c51b70-fb7d-cf44-b5c3-54e3148c11ae@arm.com>

On Thu, Sep 10, 2020 at 02:51:47PM +0100, Robin Murphy wrote:
> On 2020-09-08 17:47, Christoph Hellwig wrote:
>> dma_declare_coherent_memory should not be in a DMA API guide aimed
>> at driver writers (that is consumers of the API).  Move it to a comment
>> near the function instead.
>
> I still think there might be an occasional valid use for device-local 
> memory outside the scope of platform code without the driver having to go 
> full ZONE_DEVICE/HMM/TTM, e.g. with stuff like PCIe-based FPGA prototyping 
> cards, but the kind of driver I'm imagining for that case would never be 
> upstream anyway (if it were even written, rather than just using hard-coded 
> hacks), so meh.

And I'm not sure this would be the right interface for it.  E.g. NVMe
has the concept of a Controller Memory buffer (and a similar persistent
variant not supported by Linux), where the device can do this local DMA
(in a completely broken way that relies on correlating addresses seen
by the device and those by the host, but that's another disgression).
But that memory obviously can also be addresses by other devices using
PCIe P2P transactions which would also be useful for any HMM-ish devices,
so we'd need to expose it as P2P memory anyay..

WARNING: multiple messages have this Message-ID (diff)
From: Christoph Hellwig <hch@lst.de>
To: Robin Murphy <robin.murphy@arm.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>,
	Tony Luck <tony.luck@intel.com>,
	linux-ia64@vger.kernel.org, linux-doc@vger.kernel.org,
	linux-kernel@vger.kernel.org, iommu@lists.linux-foundation.org,
	Thomas Bogendoerfer <tsbogend@alpha.franken.de>,
	linux-mips@vger.kernel.org, Christoph Hellwig <hch@lst.de>
Subject: Re: [PATCH 12/12] dma-mapping: move the dma_declare_coherent_memory documentation
Date: Fri, 11 Sep 2020 09:17:51 +0200	[thread overview]
Message-ID: <20200911071751.GG22394@lst.de> (raw)
In-Reply-To: <07c51b70-fb7d-cf44-b5c3-54e3148c11ae@arm.com>

On Thu, Sep 10, 2020 at 02:51:47PM +0100, Robin Murphy wrote:
> On 2020-09-08 17:47, Christoph Hellwig wrote:
>> dma_declare_coherent_memory should not be in a DMA API guide aimed
>> at driver writers (that is consumers of the API).  Move it to a comment
>> near the function instead.
>
> I still think there might be an occasional valid use for device-local 
> memory outside the scope of platform code without the driver having to go 
> full ZONE_DEVICE/HMM/TTM, e.g. with stuff like PCIe-based FPGA prototyping 
> cards, but the kind of driver I'm imagining for that case would never be 
> upstream anyway (if it were even written, rather than just using hard-coded 
> hacks), so meh.

And I'm not sure this would be the right interface for it.  E.g. NVMe
has the concept of a Controller Memory buffer (and a similar persistent
variant not supported by Linux), where the device can do this local DMA
(in a completely broken way that relies on correlating addresses seen
by the device and those by the host, but that's another disgression).
But that memory obviously can also be addresses by other devices using
PCIe P2P transactions which would also be useful for any HMM-ish devices,
so we'd need to expose it as P2P memory anyay..
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

WARNING: multiple messages have this Message-ID (diff)
From: Christoph Hellwig <hch@lst.de>
To: Robin Murphy <robin.murphy@arm.com>
Cc: Christoph Hellwig <hch@lst.de>, Tony Luck <tony.luck@intel.com>,
	Fenghua Yu <fenghua.yu@intel.com>,
	Thomas Bogendoerfer <tsbogend@alpha.franken.de>,
	iommu@lists.linux-foundation.org,
	Tomasz Figa <tfiga@chromium.org>, Joerg Roedel <joro@8bytes.org>,
	linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-ia64@vger.kernel.org, linux-mips@vger.kernel.org
Subject: Re: [PATCH 12/12] dma-mapping: move the dma_declare_coherent_memory documentation
Date: Fri, 11 Sep 2020 07:17:51 +0000	[thread overview]
Message-ID: <20200911071751.GG22394@lst.de> (raw)
In-Reply-To: <07c51b70-fb7d-cf44-b5c3-54e3148c11ae@arm.com>

On Thu, Sep 10, 2020 at 02:51:47PM +0100, Robin Murphy wrote:
> On 2020-09-08 17:47, Christoph Hellwig wrote:
>> dma_declare_coherent_memory should not be in a DMA API guide aimed
>> at driver writers (that is consumers of the API).  Move it to a comment
>> near the function instead.
>
> I still think there might be an occasional valid use for device-local 
> memory outside the scope of platform code without the driver having to go 
> full ZONE_DEVICE/HMM/TTM, e.g. with stuff like PCIe-based FPGA prototyping 
> cards, but the kind of driver I'm imagining for that case would never be 
> upstream anyway (if it were even written, rather than just using hard-coded 
> hacks), so meh.

And I'm not sure this would be the right interface for it.  E.g. NVMe
has the concept of a Controller Memory buffer (and a similar persistent
variant not supported by Linux), where the device can do this local DMA
(in a completely broken way that relies on correlating addresses seen
by the device and those by the host, but that's another disgression).
But that memory obviously can also be addresses by other devices using
PCIe P2P transactions which would also be useful for any HMM-ish devices,
so we'd need to expose it as P2P memory anyay..

  reply	other threads:[~2020-09-11  7:18 UTC|newest]

Thread overview: 85+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-09-08 16:47 dma-mapping cleanups Christoph Hellwig
2020-09-08 16:47 ` Christoph Hellwig
2020-09-08 16:47 ` Christoph Hellwig
2020-09-08 16:47 ` [PATCH 01/12] MIPS: make dma_sync_*_for_cpu a little less overzealous Christoph Hellwig
2020-09-08 16:47   ` Christoph Hellwig
2020-09-08 16:47   ` Christoph Hellwig
2020-09-08 16:47 ` [PATCH 02/12] MIPS/jazzdma: remove the unused vdma_remap function Christoph Hellwig
2020-09-08 16:47   ` Christoph Hellwig
2020-09-08 16:47   ` Christoph Hellwig
2020-09-08 16:47 ` [PATCH 03/12] MIPS/jazzdma: decouple from dma-direct Christoph Hellwig
2020-09-08 16:47   ` Christoph Hellwig
2020-09-08 16:47   ` Christoph Hellwig
2020-09-08 16:47 ` [PATCH 04/12] dma-mapping: fix DMA_OPS dependencies Christoph Hellwig
2020-09-08 16:47   ` Christoph Hellwig
2020-09-08 16:47   ` Christoph Hellwig
2020-09-08 18:04   ` Sergei Shtylyov
2020-09-08 18:04     ` Sergei Shtylyov
2020-09-08 18:04     ` Sergei Shtylyov
2020-09-11  7:10     ` Christoph Hellwig
2020-09-11  7:10       ` Christoph Hellwig
2020-09-11  7:10       ` Christoph Hellwig
2020-09-10 12:55   ` Robin Murphy
2020-09-10 12:55     ` Robin Murphy
2020-09-10 12:55     ` Robin Murphy
2020-09-11  7:09     ` Christoph Hellwig
2020-09-11  7:09       ` Christoph Hellwig
2020-09-11  7:09       ` Christoph Hellwig
2020-09-08 16:47 ` [PATCH 05/12] dma-mapping: add (back) arch_dma_mark_clean for ia64 Christoph Hellwig
2020-09-08 16:47   ` Christoph Hellwig
2020-09-08 16:47   ` Christoph Hellwig
2020-09-08 16:47 ` [PATCH 06/12] dma-direct: remove dma_direct_{alloc,free}_pages Christoph Hellwig
2020-09-08 16:47   ` Christoph Hellwig
2020-09-08 16:47   ` Christoph Hellwig
2020-09-10 12:57   ` Robin Murphy
2020-09-10 12:57     ` Robin Murphy
2020-09-10 12:57     ` Robin Murphy
2020-09-08 16:47 ` [PATCH 07/12] dma-direct: lift gfp_t manipulation out of__dma_direct_alloc_pages Christoph Hellwig
2020-09-08 16:47   ` Christoph Hellwig
2020-09-08 16:47   ` Christoph Hellwig
2020-09-10 13:02   ` Robin Murphy
2020-09-10 13:02     ` Robin Murphy
2020-09-10 13:02     ` Robin Murphy
2020-09-08 16:47 ` [PATCH 08/12] dma-direct: use phys_to_dma_direct in dma_direct_alloc Christoph Hellwig
2020-09-08 16:47   ` Christoph Hellwig
2020-09-08 16:47   ` Christoph Hellwig
2020-09-10 13:03   ` Robin Murphy
2020-09-10 13:03     ` Robin Murphy
2020-09-10 13:03     ` Robin Murphy
2020-09-08 16:47 ` [PATCH 09/12] dma-direct: remove __dma_to_phys Christoph Hellwig
2020-09-08 16:47   ` Christoph Hellwig
2020-09-08 16:47   ` Christoph Hellwig
2020-09-10  9:45   ` Dan Carpenter
2020-09-10  9:45     ` Dan Carpenter
2020-09-11  7:12     ` Christoph Hellwig
2020-09-10 13:26   ` Robin Murphy
2020-09-10 13:26     ` Robin Murphy
2020-09-10 13:26     ` Robin Murphy
2020-09-11  7:14     ` Christoph Hellwig
2020-09-11  7:14       ` Christoph Hellwig
2020-09-11  7:14       ` Christoph Hellwig
2020-09-08 16:47 ` [PATCH 10/12] dma-direct: rename and cleanup __phys_to_dma Christoph Hellwig
2020-09-08 16:47   ` Christoph Hellwig
2020-09-08 16:47   ` Christoph Hellwig
2020-09-10 13:30   ` Robin Murphy
2020-09-10 13:30     ` Robin Murphy
2020-09-10 13:30     ` Robin Murphy
2020-09-08 16:47 ` [PATCH 11/12] dma-mapping: move dma_common_{mmap,get_sgtable} out of mapping.c Christoph Hellwig
2020-09-08 16:47   ` Christoph Hellwig
2020-09-08 16:47   ` [PATCH 11/12] dma-mapping: move dma_common_{mmap, get_sgtable} " Christoph Hellwig
2020-09-10 13:34   ` [PATCH 11/12] dma-mapping: move dma_common_{mmap,get_sgtable} " Robin Murphy
2020-09-10 13:34     ` Robin Murphy
2020-09-10 13:34     ` [PATCH 11/12] dma-mapping: move dma_common_{mmap, get_sgtable} " Robin Murphy
2020-09-11  7:15     ` [PATCH 11/12] dma-mapping: move dma_common_{mmap,get_sgtable} " Christoph Hellwig
2020-09-11  7:15       ` Christoph Hellwig
2020-09-11  7:15       ` Christoph Hellwig
2020-09-08 16:47 ` [PATCH 12/12] dma-mapping: move the dma_declare_coherent_memory documentation Christoph Hellwig
2020-09-08 16:47   ` Christoph Hellwig
2020-09-08 16:47   ` Christoph Hellwig
2020-09-10 13:51   ` Robin Murphy
2020-09-10 13:51     ` Robin Murphy
2020-09-10 13:51     ` Robin Murphy
2020-09-11  7:17     ` Christoph Hellwig [this message]
2020-09-11  7:17       ` Christoph Hellwig
2020-09-11  7:17       ` Christoph Hellwig
     [not found] ` <20200910141233.10768-1-hdanton@sina.com>
2020-09-11  7:07   ` [PATCH 03/12] MIPS/jazzdma: decouple from dma-direct Christoph Hellwig

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=20200911071751.GG22394@lst.de \
    --to=hch@lst.de \
    --cc=fenghua.yu@intel.com \
    --cc=iommu@lists.linux-foundation.org \
    --cc=joro@8bytes.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-ia64@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mips@vger.kernel.org \
    --cc=robin.murphy@arm.com \
    --cc=tfiga@chromium.org \
    --cc=tony.luck@intel.com \
    --cc=tsbogend@alpha.franken.de \
    /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: link
Be 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.