From: Alexey Kardashevskiy <aik@ozlabs.ru>
To: Christoph Hellwig <hch@lst.de>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
linuxppc-dev@lists.ozlabs.org, linux-kernel@vger.kernel.org,
iommu@lists.linux-foundation.org,
"Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>,
Robin Murphy <robin.murphy@arm.com>
Subject: Re: [PATCH 1/2] dma-mapping: add a dma_ops_bypass flag to struct device
Date: Mon, 23 Mar 2020 19:58:01 +1100 [thread overview]
Message-ID: <37ce1b7e-264d-292d-32b1-093b24b3525c@ozlabs.ru> (raw)
In-Reply-To: <20200323083705.GA31245@lst.de>
On 23/03/2020 19:37, Christoph Hellwig wrote:
> On Mon, Mar 23, 2020 at 12:28:34PM +1100, Alexey Kardashevskiy wrote:
>
> [full quote deleted, please follow proper quoting rules]
>
>>> +static bool dma_alloc_direct(struct device *dev, const struct dma_map_ops *ops)
>>> +{
>>> + if (!ops)
>>> + return true;
>>> +
>>> + /*
>>> + * Allows IOMMU drivers to bypass dynamic translations if the DMA mask
>>> + * is large enough.
>>> + */
>>> + if (dev->dma_ops_bypass) {
>>> + if (min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit) >=
>>> + dma_direct_get_required_mask(dev))
>>> + return true;
>>> + }
>>
>>
>> Why not do this in dma_map_direct() as well?
>
> Mostly beacuse it is a relatively expensive operation, including a
> fls64.
Ah, ok.
>> Or simply have just one dma_map_direct()?
>
> What do you mean with that?
I mean use dma_alloc_direct() instead of dma_map_direct() everywhere,
you explained just above.
>
>> And one more general question - we need a way to use non-direct IOMMU
>> for RAM above certain limit.
>>
>> Let's say we have a system with:
>> 0 .. 0x1.0000.0000
>> 0x100.0000.0000 .. 0x101.0000.0000
>>
>> 2x4G, each is 1TB aligned. And we can map directly only the first 4GB
>> (because of the maximum IOMMU table size) but not the other. And 1:1 on
>> that "pseries" is done with offset=0x0800.0000.0000.0000.
>>
>> So we want to check every bus address against dev->bus_dma_limit, not
>> dev->coherent_dma_mask. In the example above I'd set bus_dma_limit to
>> 0x0800.0001.0000.0000 and 1:1 mapping for the second 4GB would not be
>> tried. Does this sound reasonable? Thanks,
>
> bus_dma_limit is just another limiting factor applied on top of
> coherent_dma_mask or dma_mask respectively.
This is not enough for the task: in my example, I'd set bus limit to
0x0800.0001.0000.0000 but this would disable bypass for all RAM
addresses - the first and the second 4GB blocks.
--
Alexey
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
next prev parent reply other threads:[~2020-03-23 9:05 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-03-20 14:16 generic DMA bypass flag v2 Christoph Hellwig
2020-03-20 14:16 ` [PATCH 1/2] dma-mapping: add a dma_ops_bypass flag to struct device Christoph Hellwig
2020-03-20 15:02 ` Greg Kroah-Hartman
2020-03-23 1:28 ` Alexey Kardashevskiy
2020-03-23 8:37 ` Christoph Hellwig
2020-03-23 8:50 ` Christoph Hellwig
2020-03-23 15:37 ` Aneesh Kumar K.V
2020-03-23 17:22 ` Christoph Hellwig
2020-03-24 3:05 ` Alexey Kardashevskiy
2020-03-24 6:30 ` Aneesh Kumar K.V
2020-03-24 7:55 ` Christoph Hellwig
2020-03-24 7:54 ` Christoph Hellwig
2020-03-25 4:51 ` Alexey Kardashevskiy
2020-03-25 8:37 ` Christoph Hellwig
2020-03-26 1:26 ` Alexey Kardashevskiy
2020-04-03 8:38 ` Alexey Kardashevskiy
2020-04-06 11:50 ` Christoph Hellwig
2020-04-06 13:25 ` Alexey Kardashevskiy
2020-04-06 17:17 ` Christoph Hellwig
2020-04-07 10:12 ` Alexey Kardashevskiy
2020-04-14 6:21 ` Alexey Kardashevskiy
2020-04-14 6:30 ` Christoph Hellwig
2020-03-23 8:58 ` Alexey Kardashevskiy [this message]
2020-03-23 17:20 ` Christoph Hellwig
2020-03-24 3:37 ` Alexey Kardashevskiy
2020-03-24 4:55 ` Alexey Kardashevskiy
2020-03-24 7:52 ` Christoph Hellwig
2020-03-23 12:14 ` Robin Murphy
2020-03-23 12:55 ` Christoph Hellwig
2020-03-20 14:16 ` [PATCH 2/2] powerpc: use the generic dma_ops_bypass mode Christoph Hellwig
-- strict thread matches above, loose matches on Subject: below --
2019-11-13 13:37 generic DMA bypass flag Christoph Hellwig
2019-11-13 13:37 ` [PATCH 1/2] dma-mapping: add a dma_ops_bypass flag to struct device 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=37ce1b7e-264d-292d-32b1-093b24b3525c@ozlabs.ru \
--to=aik@ozlabs.ru \
--cc=aneesh.kumar@linux.ibm.com \
--cc=gregkh@linuxfoundation.org \
--cc=hch@lst.de \
--cc=iommu@lists.linux-foundation.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=robin.murphy@arm.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: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).