* Issue in "Introduce create/destroy QP commands over ioctl"?
@ 2020-05-27 12:34 Gal Pressman
2020-05-27 12:53 ` Jason Gunthorpe
0 siblings, 1 reply; 3+ messages in thread
From: Gal Pressman @ 2020-05-27 12:34 UTC (permalink / raw)
To: Yishai Hadas, Leon Romanovsky; +Cc: linux-rdma, Leybovich, Yossi
Hi,
The recent transition of create/destroy QP commands to ioctl broke the EFA
provider in [1].
With the new ioctl the 'ibv_resp' part of the response is all zero'd, opposed to
the write method.
Any idea what went wrong? Is that an intended change?
Thanks,
Gal
[1]
https://github.com/linux-rdma/rdma-core/blob/a02ba0449c1409742261d68bd251fe0ad0662b15/providers/efa/verbs.c#L562
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: Issue in "Introduce create/destroy QP commands over ioctl"?
2020-05-27 12:34 Issue in "Introduce create/destroy QP commands over ioctl"? Gal Pressman
@ 2020-05-27 12:53 ` Jason Gunthorpe
2020-05-27 13:18 ` Gal Pressman
0 siblings, 1 reply; 3+ messages in thread
From: Jason Gunthorpe @ 2020-05-27 12:53 UTC (permalink / raw)
To: Gal Pressman; +Cc: Yishai Hadas, Leon Romanovsky, linux-rdma, Leybovich, Yossi
On Wed, May 27, 2020 at 03:34:33PM +0300, Gal Pressman wrote:
> Hi,
>
> The recent transition of create/destroy QP commands to ioctl broke the EFA
> provider in [1].
> With the new ioctl the 'ibv_resp' part of the response is all zero'd, opposed to
> the write method.
It is a bug in the efa provider. It is not allowed to touch the
'ibv_resp' parts of the structure from a provider.
Something like this
diff --git a/providers/efa/verbs.c b/providers/efa/verbs.c
index 5f8e7b800210bb..92bb7432a92a2b 100644
--- a/providers/efa/verbs.c
+++ b/providers/efa/verbs.c
@@ -541,7 +541,9 @@ static void efa_sq_terminate(struct efa_qp *qp)
efa_wq_terminate(&qp->sq.wq);
}
-static int efa_sq_initialize(struct efa_qp *qp, struct efa_create_qp_resp *resp)
+static int efa_sq_initialize(struct efa_qp *qp,
+ const struct ibv_qp_init_attr_ex *attr,
+ struct efa_create_qp_resp *resp)
{
struct efa_dev *dev = to_efa_dev(qp->verbs_qp.qp.context->device);
size_t desc_ring_size;
@@ -559,7 +561,7 @@ static int efa_sq_initialize(struct efa_qp *qp, struct efa_create_qp_resp *resp)
desc_ring_size = qp->sq.wq.wqe_cnt * sizeof(struct efa_io_tx_wqe);
qp->sq.desc_ring_mmap_size = align(desc_ring_size + qp->sq.desc_offset,
qp->page_size);
- qp->sq.max_inline_data = resp->ibv_resp.max_inline_data;
+ qp->sq.max_inline_data = attr->cap.max_inline_data;
qp->sq.local_queue = malloc(desc_ring_size);
if (!qp->sq.local_queue) {
@@ -840,7 +842,7 @@ static struct ibv_qp *create_qp(struct ibv_context *ibvctx,
if (err)
goto err_destroy_qp;
- err = efa_sq_initialize(qp, &resp);
+ err = efa_sq_initialize(qp, attr, &resp);
if (err)
goto err_terminate_rq;
^ permalink raw reply related [flat|nested] 3+ messages in thread
* Re: Issue in "Introduce create/destroy QP commands over ioctl"?
2020-05-27 12:53 ` Jason Gunthorpe
@ 2020-05-27 13:18 ` Gal Pressman
0 siblings, 0 replies; 3+ messages in thread
From: Gal Pressman @ 2020-05-27 13:18 UTC (permalink / raw)
To: Jason Gunthorpe
Cc: Yishai Hadas, Leon Romanovsky, linux-rdma, Leybovich, Yossi
On 27/05/2020 15:53, Jason Gunthorpe wrote:
> On Wed, May 27, 2020 at 03:34:33PM +0300, Gal Pressman wrote:
>> Hi,
>>
>> The recent transition of create/destroy QP commands to ioctl broke the EFA
>> provider in [1].
>> With the new ioctl the 'ibv_resp' part of the response is all zero'd, opposed to
>> the write method.
>
> It is a bug in the efa provider. It is not allowed to touch the
> 'ibv_resp' parts of the structure from a provider.
Thanks Jason, I did not know that.
> Something like this
>
> diff --git a/providers/efa/verbs.c b/providers/efa/verbs.c
> index 5f8e7b800210bb..92bb7432a92a2b 100644
> --- a/providers/efa/verbs.c
> +++ b/providers/efa/verbs.c
> @@ -541,7 +541,9 @@ static void efa_sq_terminate(struct efa_qp *qp)
> efa_wq_terminate(&qp->sq.wq);
> }
>
> -static int efa_sq_initialize(struct efa_qp *qp, struct efa_create_qp_resp *resp)
> +static int efa_sq_initialize(struct efa_qp *qp,
> + const struct ibv_qp_init_attr_ex *attr,
> + struct efa_create_qp_resp *resp)
> {
> struct efa_dev *dev = to_efa_dev(qp->verbs_qp.qp.context->device);
> size_t desc_ring_size;
> @@ -559,7 +561,7 @@ static int efa_sq_initialize(struct efa_qp *qp, struct efa_create_qp_resp *resp)
> desc_ring_size = qp->sq.wq.wqe_cnt * sizeof(struct efa_io_tx_wqe);
> qp->sq.desc_ring_mmap_size = align(desc_ring_size + qp->sq.desc_offset,
> qp->page_size);
> - qp->sq.max_inline_data = resp->ibv_resp.max_inline_data;
> + qp->sq.max_inline_data = attr->cap.max_inline_data;
>
> qp->sq.local_queue = malloc(desc_ring_size);
> if (!qp->sq.local_queue) {
> @@ -840,7 +842,7 @@ static struct ibv_qp *create_qp(struct ibv_context *ibvctx,
> if (err)
> goto err_destroy_qp;
>
> - err = efa_sq_initialize(qp, &resp);
> + err = efa_sq_initialize(qp, attr, &resp);
> if (err)
> goto err_terminate_rq;
>
>
I'll send a PR.
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2020-05-27 13:19 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2020-05-27 12:34 Issue in "Introduce create/destroy QP commands over ioctl"? Gal Pressman
2020-05-27 12:53 ` Jason Gunthorpe
2020-05-27 13:18 ` Gal Pressman
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).