[for-next,00/11] Some misc fixes for hns

Message ID	1538042511-43966-1-git-send-email-oulijun@huawei.com (mailing list archive)
Headers	show Return-Path: <linux-rdma-owner@kernel.org> From: Lijun Ou <oulijun@huawei.com> To: <dledford@redhat.com>, <jgg@ziepe.ca> CC: <leon@kernel.org>, <linux-rdma@vger.kernel.org> Subject: [PATCH for-next 00/11] Some misc fixes for hns Date: Thu, 27 Sep 2018 18:01:40 +0800 Message-ID: <1538042511-43966-1-git-send-email-oulijun@huawei.com> MIME-Version: 1.0 Content-Type: text/plain Sender: linux-rdma-owner@vger.kernel.org Precedence: bulk
Series	Some misc fixes for hns \| expand [for-next,00/11] Some misc fixes for hns [for-next,01/11] RDMA/hns: Bugfix for reserved qp number [for-next,02/11] RDMA/hns: Submit bad wr when post send wr exception [for-next,03/11] RDMA/hns: Bugfix for CM test [for-next,04/11] RDMA/hns: Limit the size of extend sge of sq [for-next,05/11] RDMA/hns: Configure ecn field of ip header [for-next,06/11] RDMA/hns: Update some attributes of the RoCE device [for-next,07/11] RDMA/hns: Limit extend sq sge num [for-next,08/11] RDMA/hns: Update some fields of qp context [for-next,09/11] RDMA/hns: Support local invalidate for hip08 in kernel space [for-next,10/11] RDMA/hns: Add vlan enable bit for hip08 [for-next,11/11] RDMA/hns: Bugfix for atomic operation

Message ID

1538042511-43966-1-git-send-email-oulijun@huawei.com (mailing list archive)

Headers

From: Lijun Ou <oulijun@huawei.com>
To: <dledford@redhat.com>, <jgg@ziepe.ca>
CC: <leon@kernel.org>, <linux-rdma@vger.kernel.org>
Subject: [PATCH for-next 00/11] Some misc fixes for hns
Date: Thu, 27 Sep 2018 18:01:40 +0800
Message-ID: <1538042511-43966-1-git-send-email-oulijun@huawei.com>
MIME-Version: 1.0
Content-Type: text/plain
Sender: linux-rdma-owner@vger.kernel.org
Precedence: bulk

Series

Some misc fixes for hns | expand

Message

Lijun Ou Sept. 27, 2018, 10:01 a.m. UTC

This patch series includes bug fixes and a small
feature for hns.

Lijun Ou (11):
  RDMA/hns: Bugfix for reserved qp number
  RDMA/hns: Submit bad wr when post send wr exception
  RDMA/hns: Bugfix for CM test
  RDMA/hns: Limit the size of extend sge of sq
  RDMA/hns: Configure ecn field of ip header
  RDMA/hns: Update some attributes of the RoCE device
  RDMA/hns: Limit extend sq sge num
  RDMA/hns: Update some fields of qp context
  RDMA/hns: Support local invalidate for hip08 in kernel space
  RDMA/hns: Add vlan enable bit for hip08
  RDMA/hns: Bugfix for atomic operation

 drivers/infiniband/hw/hns/hns_roce_device.h |   3 +
 drivers/infiniband/hw/hns/hns_roce_hw_v2.c  | 163 +++++++++++++++++-----------
 drivers/infiniband/hw/hns/hns_roce_hw_v2.h  |  52 +++++----
 drivers/infiniband/hw/hns/hns_roce_main.c   |   1 +
 drivers/infiniband/hw/hns/hns_roce_qp.c     |  37 ++++++-
 5 files changed, 166 insertions(+), 90 deletions(-)

Comments

Jason Gunthorpe Sept. 28, 2018, 5:34 p.m. UTC | #1

On Thu, Sep 27, 2018 at 06:01:40PM +0800, Lijun Ou wrote:
> This patch series includes bug fixes and a small
> feature for hns.
> 
> Lijun Ou (11):
>   RDMA/hns: Bugfix for reserved qp number
>   RDMA/hns: Submit bad wr when post send wr exception
>   RDMA/hns: Bugfix for CM test
>   RDMA/hns: Limit the size of extend sge of sq
>   RDMA/hns: Configure ecn field of ip header
>   RDMA/hns: Update some attributes of the RoCE device
>   RDMA/hns: Limit extend sq sge num
>   RDMA/hns: Update some fields of qp context
>   RDMA/hns: Support local invalidate for hip08 in kernel space
>   RDMA/hns: Add vlan enable bit for hip08
>   RDMA/hns: Bugfix for atomic operation

These looked OK, but they don't apply the current tree:

Applying: RDMA/hns: Bugfix for reserved qp number
Applying: RDMA/hns: Submit bad wr when post send wr exception
Applying: RDMA/hns: Bugfix for CM test
Applying: RDMA/hns: Limit the size of extend sge of sq
Applying: RDMA/hns: Configure ecn field of ip header
Applying: RDMA/hns: Update some attributes of the RoCE device
Applying: RDMA/hns: Limit extend sq sge num
Applying: RDMA/hns: Update some fields of qp context
Applying: RDMA/hns: Support local invalidate for hip08 in kernel space
Applying: RDMA/hns: Add vlan enable bit for hip08
Applying: RDMA/hns: Bugfix for atomic operation
error: sha1 information is lacking or useless (drivers/infiniband/hw/hns/hns_roce_hw_v2.c).
error: could not build fake ancestor
Patch failed at 0011 RDMA/hns: Bugfix for atomic operation
hint: Use 'git am --show-current-patch' to see the failed patch
When you have resolved this problem, run "git am --continue".
If you prefer to skip this patch, run "git am --skip" instead.
To restore the original branch and stop patching, run "git am --abort".

Please rebase and resend.

If you list a git URL in pull requests that exactly matches that git
tree that was used to make the git send-email I can resolve trivial
rebases myself, but if git am fails I prefer to give up :)

Jason

Lijun Ou Sept. 30, 2018, 8:11 a.m. UTC | #2

在 2018/9/29 1:34, Jason Gunthorpe 写道:
> On Thu, Sep 27, 2018 at 06:01:40PM +0800, Lijun Ou wrote:
>> This patch series includes bug fixes and a small
>> feature for hns.
>>
>> Lijun Ou (11):
>>   RDMA/hns: Bugfix for reserved qp number
>>   RDMA/hns: Submit bad wr when post send wr exception
>>   RDMA/hns: Bugfix for CM test
>>   RDMA/hns: Limit the size of extend sge of sq
>>   RDMA/hns: Configure ecn field of ip header
>>   RDMA/hns: Update some attributes of the RoCE device
>>   RDMA/hns: Limit extend sq sge num
>>   RDMA/hns: Update some fields of qp context
>>   RDMA/hns: Support local invalidate for hip08 in kernel space
>>   RDMA/hns: Add vlan enable bit for hip08
>>   RDMA/hns: Bugfix for atomic operation
> 
> These looked OK, but they don't apply the current tree:
> 
> Applying: RDMA/hns: Bugfix for reserved qp number
> Applying: RDMA/hns: Submit bad wr when post send wr exception
> Applying: RDMA/hns: Bugfix for CM test
> Applying: RDMA/hns: Limit the size of extend sge of sq
> Applying: RDMA/hns: Configure ecn field of ip header
> Applying: RDMA/hns: Update some attributes of the RoCE device
> Applying: RDMA/hns: Limit extend sq sge num
> Applying: RDMA/hns: Update some fields of qp context
> Applying: RDMA/hns: Support local invalidate for hip08 in kernel space
> Applying: RDMA/hns: Add vlan enable bit for hip08
> Applying: RDMA/hns: Bugfix for atomic operation
> error: sha1 information is lacking or useless (drivers/infiniband/hw/hns/hns_roce_hw_v2.c).
> error: could not build fake ancestor
> Patch failed at 0011 RDMA/hns: Bugfix for atomic operation
> hint: Use 'git am --show-current-patch' to see the failed patch
> When you have resolved this problem, run "git am --continue".
> If you prefer to skip this patch, run "git am --skip" instead.
> To restore the original branch and stop patching, run "git am --abort".
> 
> Please rebase and resend.
> 
> If you list a git URL in pull requests that exactly matches that git
> tree that was used to make the git send-email I can resolve trivial
> rebases myself, but if git am fails I prefer to give up :)
> 
> Jason
> 
> .
> 
Thanks. I will rebase on jgg-for-next and resend it.

Lijun Ou Sept. 30, 2018, 8:32 a.m. UTC | #3

在 2018/9/29 1:34, Jason Gunthorpe 写道:
> On Thu, Sep 27, 2018 at 06:01:40PM +0800, Lijun Ou wrote:
>> This patch series includes bug fixes and a small
>> feature for hns.
>>
>> Lijun Ou (11):
>>   RDMA/hns: Bugfix for reserved qp number
>>   RDMA/hns: Submit bad wr when post send wr exception
>>   RDMA/hns: Bugfix for CM test
>>   RDMA/hns: Limit the size of extend sge of sq
>>   RDMA/hns: Configure ecn field of ip header
>>   RDMA/hns: Update some attributes of the RoCE device
>>   RDMA/hns: Limit extend sq sge num
>>   RDMA/hns: Update some fields of qp context
>>   RDMA/hns: Support local invalidate for hip08 in kernel space
>>   RDMA/hns: Add vlan enable bit for hip08
>>   RDMA/hns: Bugfix for atomic operation
> 
> These looked OK, but they don't apply the current tree:
> 
> Applying: RDMA/hns: Bugfix for reserved qp number
> Applying: RDMA/hns: Submit bad wr when post send wr exception
> Applying: RDMA/hns: Bugfix for CM test
> Applying: RDMA/hns: Limit the size of extend sge of sq
> Applying: RDMA/hns: Configure ecn field of ip header
> Applying: RDMA/hns: Update some attributes of the RoCE device
> Applying: RDMA/hns: Limit extend sq sge num
> Applying: RDMA/hns: Update some fields of qp context
> Applying: RDMA/hns: Support local invalidate for hip08 in kernel space
> Applying: RDMA/hns: Add vlan enable bit for hip08
> Applying: RDMA/hns: Bugfix for atomic operation
> error: sha1 information is lacking or useless (drivers/infiniband/hw/hns/hns_roce_hw_v2.c).
> error: could not build fake ancestor
> Patch failed at 0011 RDMA/hns: Bugfix for atomic operation
> hint: Use 'git am --show-current-patch' to see the failed patch
> When you have resolved this problem, run "git am --continue".
> If you prefer to skip this patch, run "git am --skip" instead.
> To restore the original branch and stop patching, run "git am --abort".
> 
> Please rebase and resend.
> 
> If you list a git URL in pull requests that exactly matches that git
> tree that was used to make the git send-email I can resolve trivial
> rebases myself, but if git am fails I prefer to give up :)
> 
> Jason
> 
Hi， Jason
  First， sorry for my careless. the patch set is generated on jgg-for-next. because the dependent patch only
exist in this branch.
  I have sendt the next patchset.

Thanks
Lijun Ou

> .
>