[sync] PR-66: 1. Fix the sge num problem of atomic op; 2. Fix sge tail_len overflow; 3. Disable local invalidate operation · Pull Request !67 · src-openEuler/rdma-core

### 1. Origin pull request:
https://gitee.com/src-openeuler/rdma-core/pulls/66

### 2. Original pull request related issue(s):
https://gitee.com/src-openeuler/rdma-core/issues/I72EWP
https://gitee.com/src-openeuler/rdma-core/issues/I72F0C
https://gitee.com/src-openeuler/rdma-core/issues/I72F0U

### 3. Original pull request related commit(s):
| Sha | Datetime | Message |
|---|---|---|
|[43c14b73](https://gitee.com/src-openeuler/rdma-core/commits/43c14b73409cf6e63278d5ff68e2694e592e9015)|2023-05-11 20:11:44 +0800 CST|Fix the sge number related errors and remove local invalidate operation 1. The hns hardware logic requires wr->num_sge to be 1 when performing atomic operations. The code does not judge this condition, and the current patch adds this constraint. 2. In the sq inline scenario, when num_sge in post_send is not 1, sge array appears in the for loop without rotation and directly copy out of bounds. 3. Currently local invalidate operation don't work properly. Disable it for the time being. HIP08 and HIP09 hardware does not support this feature, so delete the associated code. Signed-off-by: Juan Zhou <zhoujuan51@h-partners.com> |

src-openEuler/rdma-core .gitee-modal { width: 500px !important; }

搜索帮助

src-openEuler/rdma-core