On 19/11/2019 21:56, Jason Gunthorpe wrote:
> On Tue, Nov 12, 2019 at 11:17:37AM +0200, Gal Pressman wrote:
>> diff --git a/include/uapi/rdma/efa-abi.h b/include/uapi/rdma/efa-abi.h
>> index 9599a2a62be8..442804572118 100644
>> +++ b/include/uapi/rdma/efa-abi.h
>> @@ -90,12 +90,21 @@ struct efa_ibv_create_ah_resp {
>> __u8 reserved_30[2];
>> };
>>
>> +enum {
>> + EFA_QUERY_DEVICE_CAPS_RDMA_READ = 1 << 0,
>> +};
>
> This doesn't seem needed, caps should only be used if a zero filled
> reply from an old kernel is not OK.
This isn't a compatibility mask, it's our way to indicate the userspace whether
the device supports RDMA read. Old kernel/lack of support will return 0, new
kernel will return 0/1 according to the device support.
>> struct efa_ibv_ex_query_device_resp {
>> __u32 comp_mask;
>> __u32 max_sq_wr;
>> __u32 max_rq_wr;
>> __u16 max_sq_sge;
>> __u16 max_rq_sge;
>> + __u32 max_rdma_size;
>> + __u16 max_wr_rdma_sge;
>> + __u8 reserved_b0[2];
>> + __u32 device_caps;
>> + __u8 reserved_e0[4];
>> };
>
> This has the same problem as we talked about in userspace, the
> max_wr_rdma_sge duplicates the field in the normal query_device
> response
Sure, will remove from both.
