From: Dave Jiang <dave.jiang@intel.com>
To: Vinod Koul <vkoul@kernel.org>
Cc: Peter Ujfalusi <peter.ujfalusi@ti.com>,
dmaengine@vger.kernel.org, swathi.kovvuri@intel.com
Subject: Re: [PATCH v4] dmaengine: cookie bypass for out of order completion
Date: Tue, 19 May 2020 10:02:11 -0700 [thread overview]
Message-ID: <7a174bd3-b95f-ee45-c1ce-b738a709545f@intel.com> (raw)
In-Reply-To: <20200519165959.GR374218@vkoul-mobl.Dlink>
On 5/19/2020 9:59 AM, Vinod Koul wrote:
> On 15-05-20, 09:21, Dave Jiang wrote:
>>
>>
>> On 5/14/2020 11:48 PM, Vinod Koul wrote:
>>> On 13-05-20, 09:35, Dave Jiang wrote:
>>>>
>>>>
>>>> On 5/13/2020 12:30 AM, Peter Ujfalusi wrote:
>>>>>
>>>>>
>>>>> On 12/05/2020 2.47, Dave Jiang wrote:
>>>>>> The cookie tracking in dmaengine expects all submissions completed in
>>>>>> order. Some DMA devices like Intel DSA can complete submissions out of
>>>>>> order, especially if configured with a work queue sharing multiple DMA
>>>>>> engines. Add a status DMA_OUT_OF_ORDER that tx_status can be returned for
>>>>>> those DMA devices. The user should use callbacks to track the completion
>>>>>> rather than the DMA cookie. This would address the issue of dmatest
>>>>>> complaining that descriptors are "busy" when the cookie count goes
>>>>>> backwards due to out of order completion. Add DMA_COMPLETION_NO_ORDER
>>>>>> DMA capability to allow the driver to flag the device's ability to complete
>>>>>> operations out of order.
>>>>>
>>>>> I'm still a bit hesitant around this.
>>>>> If the DMA only support out of order completion then it is mandatory
>>>>> that each descriptor must have unique callback parameter in order the
>>>>> client could know which transfer has been completed.
>>>
>>> Maybe we can still use the cookie to indicate that, or leave it to users
>>> to manage? They can add an id in the callback params?
>>>
>>> Using former is easy, but still user needs to keep track... later can be
>>> possibly more suited here?
>>>
>>
>> Is there anything else I need to do with this patch?
>
> Not really atm, but i am going to defer this after merge window.
>
Fair enough. Thanks.
prev parent reply other threads:[~2020-05-19 17:03 UTC|newest]
Thread overview: 7+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-05-11 23:47 [PATCH v4] dmaengine: cookie bypass for out of order completion Dave Jiang
2020-05-13 7:30 ` Peter Ujfalusi
2020-05-13 16:35 ` Dave Jiang
2020-05-15 6:48 ` Vinod Koul
2020-05-15 16:21 ` Dave Jiang
2020-05-19 16:59 ` Vinod Koul
2020-05-19 17:02 ` Dave Jiang [this message]
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=7a174bd3-b95f-ee45-c1ce-b738a709545f@intel.com \
--to=dave.jiang@intel.com \
--cc=dmaengine@vger.kernel.org \
--cc=peter.ujfalusi@ti.com \
--cc=swathi.kovvuri@intel.com \
--cc=vkoul@kernel.org \
/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).