[PATCH 0/2] fix dmadev incomplete ABI validation

[PATCH 0/2] fix dmadev incomplete ABI validation

[datshan]

From: datshan <datshan@qq.com>

Fix dmadev incomplete ABI validation.

Chengwen Feng (2):
  dmadev: fix incomplete configuration validation
  test/dmadev: add config and vchan validation tests

 app/test/test_dmadev_api.c | 186 ++++++++++++++++++++++++++++++++++---
 lib/dmadev/rte_dmadev.c    | 156 +++++++++++++++++++++----------
 2 files changed, 283 insertions(+), 59 deletions(-)

-- 
2.54.0

[PATCH 0/2] fix dmadev incomplete ABI validation

[datshan]

From: datshan <datshan@qq.com>

Fix dmadev incomplete ABI validation.

Chengwen Feng (2):
  dmadev: fix incomplete configuration validation
  test/dmadev: add config and vchan validation tests

 app/test/test_dmadev_api.c | 186 ++++++++++++++++++++++++++++++++++---
 lib/dmadev/rte_dmadev.c    | 156 +++++++++++++++++++++----------
 2 files changed, 283 insertions(+), 59 deletions(-)

-- 
2.54.0

Re: [PATCH 0/2] fix dmadev incomplete ABI validation

[David Marchand]

Hello,

On Tue, 30 Jun 2026 at 15:24, <datshan@qq.com> wrote:
>
> From: datshan <datshan@qq.com>
>
> Fix dmadev incomplete ABI validation.
>
> Chengwen Feng (2):
>   dmadev: fix incomplete configuration validation
>   test/dmadev: add config and vchan validation tests
>
>  app/test/test_dmadev_api.c | 186 ++++++++++++++++++++++++++++++++++---
>  lib/dmadev/rte_dmadev.c    | 156 +++++++++++++++++++++----------
>  2 files changed, 283 insertions(+), 59 deletions(-)
>

This series is not versionned, but I guess this is a new revision.
Don't forget to flag your submissions with a version number in the future.
I marked the previous patches as superseded in patchwork.

Also provide a high level summary of the differences between versions.

All of those steps are listed in the contributing guide, I suggest
(re-)reading the whole guide, with a highlight on:
https://doc.dpdk.org/guides/contributing/patches.html#steps-to-getting-your-patch-merged

Thanks, I'll try to find some time to review this week.


-- 
David Marchand

Re: [PATCH 0/2] fix dmadev incomplete ABI validation

[David Marchand]

On Wed, 1 Jul 2026 at 10:11, David Marchand <david.marchand@redhat.com> wrote:
> On Tue, 30 Jun 2026 at 15:24, <datshan@qq.com> wrote:
> >
> > From: datshan <datshan@qq.com>
> >
> > Fix dmadev incomplete ABI validation.
> >
> > Chengwen Feng (2):
> >   dmadev: fix incomplete configuration validation
> >   test/dmadev: add config and vchan validation tests
> >
> >  app/test/test_dmadev_api.c | 186 ++++++++++++++++++++++++++++++++++---
> >  lib/dmadev/rte_dmadev.c    | 156 +++++++++++++++++++++----------
> >  2 files changed, 283 insertions(+), 59 deletions(-)
> >
>
> This series is not versionned, but I guess this is a new revision.
> Don't forget to flag your submissions with a version number in the future.
> I marked the previous patches as superseded in patchwork.
>
> Also provide a high level summary of the differences between versions.
>
> All of those steps are listed in the contributing guide, I suggest
> (re-)reading the whole guide, with a highlight on:
> https://doc.dpdk.org/guides/contributing/patches.html#steps-to-getting-your-patch-merged
>
> Thanks, I'll try to find some time to review this week.

Well, enforcing *now* that some fields are 0 is actually breaking ABI
for existing applications.
This change should be deferred to 26.11, and backporting to a LTS is
not possible.

Opinions?


-- 
David Marchand

Re: [PATCH 0/2] fix dmadev incomplete ABI validation

[fengchengwen]

On 7/2/2026 1:01 AM, David Marchand wrote:
> On Wed, 1 Jul 2026 at 10:11, David Marchand <david.marchand@redhat.com> wrote:
>> On Tue, 30 Jun 2026 at 15:24, <datshan@qq.com> wrote:
>>>
>>> From: datshan <datshan@qq.com>
>>>
>>> Fix dmadev incomplete ABI validation.
>>>
>>> Chengwen Feng (2):
>>>   dmadev: fix incomplete configuration validation
>>>   test/dmadev: add config and vchan validation tests
>>>
>>>  app/test/test_dmadev_api.c | 186 ++++++++++++++++++++++++++++++++++---
>>>  lib/dmadev/rte_dmadev.c    | 156 +++++++++++++++++++++----------
>>>  2 files changed, 283 insertions(+), 59 deletions(-)
>>>
>>
>> This series is not versionned, but I guess this is a new revision.
>> Don't forget to flag your submissions with a version number in the future.
>> I marked the previous patches as superseded in patchwork.
>>
>> Also provide a high level summary of the differences between versions.
>>
>> All of those steps are listed in the contributing guide, I suggest
>> (re-)reading the whole guide, with a highlight on:
>> https://doc.dpdk.org/guides/contributing/patches.html#steps-to-getting-your-patch-merged
>>
>> Thanks, I'll try to find some time to review this week.
> 
> Well, enforcing *now* that some fields are 0 is actually breaking ABI
> for existing applications.
> This change should be deferred to 26.11, and backporting to a LTS is
> not possible.

OK
BTW: Should I submit another version in 26.11 cycle or do nothing?

> 
> Opinions?
> 
> 

Re: [PATCH 0/2] fix dmadev incomplete ABI validation

[David Marchand]

On Thu, 2 Jul 2026 at 03:35, fengchengwen <fengchengwen@huawei.com> wrote:
>
> On 7/2/2026 1:01 AM, David Marchand wrote:
> > On Wed, 1 Jul 2026 at 10:11, David Marchand <david.marchand@redhat.com> wrote:
> >> On Tue, 30 Jun 2026 at 15:24, <datshan@qq.com> wrote:
> >>>
> >>> From: datshan <datshan@qq.com>
> >>>
> >>> Fix dmadev incomplete ABI validation.
> >>>
> >>> Chengwen Feng (2):
> >>>   dmadev: fix incomplete configuration validation
> >>>   test/dmadev: add config and vchan validation tests
> >>>
> >>>  app/test/test_dmadev_api.c | 186 ++++++++++++++++++++++++++++++++++---
> >>>  lib/dmadev/rte_dmadev.c    | 156 +++++++++++++++++++++----------
> >>>  2 files changed, 283 insertions(+), 59 deletions(-)
> >>>
> >>
> >> This series is not versionned, but I guess this is a new revision.
> >> Don't forget to flag your submissions with a version number in the future.
> >> I marked the previous patches as superseded in patchwork.
> >>
> >> Also provide a high level summary of the differences between versions.
> >>
> >> All of those steps are listed in the contributing guide, I suggest
> >> (re-)reading the whole guide, with a highlight on:
> >> https://doc.dpdk.org/guides/contributing/patches.html#steps-to-getting-your-patch-merged
> >>
> >> Thanks, I'll try to find some time to review this week.
> >
> > Well, enforcing *now* that some fields are 0 is actually breaking ABI
> > for existing applications.
> > This change should be deferred to 26.11, and backporting to a LTS is
> > not possible.
>
> OK
> BTW: Should I submit another version in 26.11 cycle or do nothing?

I'll mark those patches as Deferred in patchwork.
That's enough, I will apply them after 26.11-rc0.


-- 
David Marchand

Re: [PATCH 0/2] fix dmadev incomplete ABI validation

[fengchengwen]

On 7/2/2026 2:52 PM, David Marchand wrote:
> On Thu, 2 Jul 2026 at 03:35, fengchengwen <fengchengwen@huawei.com> wrote:
>>
>> On 7/2/2026 1:01 AM, David Marchand wrote:
>>> On Wed, 1 Jul 2026 at 10:11, David Marchand <david.marchand@redhat.com> wrote:
>>>> On Tue, 30 Jun 2026 at 15:24, <datshan@qq.com> wrote:
>>>>>
>>>>> From: datshan <datshan@qq.com>
>>>>>
>>>>> Fix dmadev incomplete ABI validation.
>>>>>
>>>>> Chengwen Feng (2):
>>>>>   dmadev: fix incomplete configuration validation
>>>>>   test/dmadev: add config and vchan validation tests
>>>>>
>>>>>  app/test/test_dmadev_api.c | 186 ++++++++++++++++++++++++++++++++++---
>>>>>  lib/dmadev/rte_dmadev.c    | 156 +++++++++++++++++++++----------
>>>>>  2 files changed, 283 insertions(+), 59 deletions(-)
>>>>>
>>>>
>>>> This series is not versionned, but I guess this is a new revision.
>>>> Don't forget to flag your submissions with a version number in the future.
>>>> I marked the previous patches as superseded in patchwork.
>>>>
>>>> Also provide a high level summary of the differences between versions.
>>>>
>>>> All of those steps are listed in the contributing guide, I suggest
>>>> (re-)reading the whole guide, with a highlight on:
>>>> https://doc.dpdk.org/guides/contributing/patches.html#steps-to-getting-your-patch-merged
>>>>
>>>> Thanks, I'll try to find some time to review this week.
>>>
>>> Well, enforcing *now* that some fields are 0 is actually breaking ABI
>>> for existing applications.
>>> This change should be deferred to 26.11, and backporting to a LTS is
>>> not possible.
>>
>> OK
>> BTW: Should I submit another version in 26.11 cycle or do nothing?
> 
> I'll mark those patches as Deferred in patchwork.
> That's enough, I will apply them after 26.11-rc0.

Thanks

> 
>