diff mbox

[v1] IB/cma: Use inner P_Key to determine netdev

Message ID 1445323981-28582-1-git-send-email-haggaie@mellanox.com (mailing list archive)
State Accepted
Headers show

Commit Message

Haggai Eran Oct. 20, 2015, 6:53 a.m. UTC
When discussing the patches to demux ids in rdma_cm instead of ib_cm, it
was decided that it is best to use the P_Key value in the packet headers.
However, the mlx5 and ipath drivers are currently unable to send correct
P_Key values in GMP headers. They always send using a single P_Key that is
set during the GSI QP initialization.

Change the rdma_cm code to look at the P_Key value that is part of the
packet payload as a workaround. Once the drivers are fixed this patch can
be reverted.

Fixes: 4c21b5bcef73 ("IB/cma: Add net_dev and private data checks to
RDMA CM")
Signed-off-by: Haggai Eran <haggaie@mellanox.com>
---
Changes from v0:
- improve commit message

 drivers/infiniband/core/cma.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

Comments

Doug Ledford Oct. 20, 2015, 7:20 a.m. UTC | #1
On 10/20/2015 02:53 AM, Haggai Eran wrote:
> When discussing the patches to demux ids in rdma_cm instead of ib_cm, it
> was decided that it is best to use the P_Key value in the packet headers.
> However, the mlx5 and ipath drivers are currently unable to send correct
> P_Key values in GMP headers. They always send using a single P_Key that is
> set during the GSI QP initialization.
> 
> Change the rdma_cm code to look at the P_Key value that is part of the
> packet payload as a workaround. Once the drivers are fixed this patch can
> be reverted.
> 
> Fixes: 4c21b5bcef73 ("IB/cma: Add net_dev and private data checks to
> RDMA CM")
> Signed-off-by: Haggai Eran <haggaie@mellanox.com>
> ---
> Changes from v0:
> - improve commit message
> 
>  drivers/infiniband/core/cma.c | 4 ++--
>  1 file changed, 2 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
> index 59a2dafc8c57..e8324543e085 100644
> --- a/drivers/infiniband/core/cma.c
> +++ b/drivers/infiniband/core/cma.c
> @@ -1067,14 +1067,14 @@ static int cma_save_req_info(const struct ib_cm_event *ib_event,
>  		       sizeof(req->local_gid));
>  		req->has_gid	= true;
>  		req->service_id	= req_param->primary_path->service_id;
> -		req->pkey	= req_param->bth_pkey;
> +		req->pkey	= be16_to_cpu(req_param->primary_path->pkey);
>  		break;
>  	case IB_CM_SIDR_REQ_RECEIVED:
>  		req->device	= sidr_param->listen_id->device;
>  		req->port	= sidr_param->port;
>  		req->has_gid	= false;
>  		req->service_id	= sidr_param->service_id;
> -		req->pkey	= sidr_param->bth_pkey;
> +		req->pkey	= sidr_param->pkey;
>  		break;
>  	default:
>  		return -EINVAL;
> 

And, to be clear, you are looking for this to be part of 4.3-rc updates,
yes?
Haggai Eran Oct. 20, 2015, 8:35 a.m. UTC | #2
On 20/10/2015 10:20, Doug Ledford wrote:
> On 10/20/2015 02:53 AM, Haggai Eran wrote:
>> When discussing the patches to demux ids in rdma_cm instead of ib_cm, it
>> was decided that it is best to use the P_Key value in the packet headers.
>> However, the mlx5 and ipath drivers are currently unable to send correct
>> P_Key values in GMP headers. They always send using a single P_Key that is
>> set during the GSI QP initialization.
>>
>> Change the rdma_cm code to look at the P_Key value that is part of the
>> packet payload as a workaround. Once the drivers are fixed this patch can
>> be reverted.
>>
>> Fixes: 4c21b5bcef73 ("IB/cma: Add net_dev and private data checks to
>> RDMA CM")
>> Signed-off-by: Haggai Eran <haggaie@mellanox.com>
>> ---
>> Changes from v0:
>> - improve commit message
>>
>>  drivers/infiniband/core/cma.c | 4 ++--
>>  1 file changed, 2 insertions(+), 2 deletions(-)
>>
>> diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
>> index 59a2dafc8c57..e8324543e085 100644
>> --- a/drivers/infiniband/core/cma.c
>> +++ b/drivers/infiniband/core/cma.c
>> @@ -1067,14 +1067,14 @@ static int cma_save_req_info(const struct ib_cm_event *ib_event,
>>  		       sizeof(req->local_gid));
>>  		req->has_gid	= true;
>>  		req->service_id	= req_param->primary_path->service_id;
>> -		req->pkey	= req_param->bth_pkey;
>> +		req->pkey	= be16_to_cpu(req_param->primary_path->pkey);
>>  		break;
>>  	case IB_CM_SIDR_REQ_RECEIVED:
>>  		req->device	= sidr_param->listen_id->device;
>>  		req->port	= sidr_param->port;
>>  		req->has_gid	= false;
>>  		req->service_id	= sidr_param->service_id;
>> -		req->pkey	= sidr_param->bth_pkey;
>> +		req->pkey	= sidr_param->pkey;
>>  		break;
>>  	default:
>>  		return -EINVAL;
>>
> 
> And, to be clear, you are looking for this to be part of 4.3-rc updates,
> yes?

Yes, the issue was introduced in 4.3 in my cma demux patch.

Haggai

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Doug Ledford Oct. 20, 2015, 8:46 p.m. UTC | #3
On 10/20/2015 04:35 AM, Haggai Eran wrote:
> On 20/10/2015 10:20, Doug Ledford wrote:
>> On 10/20/2015 02:53 AM, Haggai Eran wrote:
>>> When discussing the patches to demux ids in rdma_cm instead of ib_cm, it
>>> was decided that it is best to use the P_Key value in the packet headers.
>>> However, the mlx5 and ipath drivers are currently unable to send correct
>>> P_Key values in GMP headers. They always send using a single P_Key that is
>>> set during the GSI QP initialization.
>>>
>>> Change the rdma_cm code to look at the P_Key value that is part of the
>>> packet payload as a workaround. Once the drivers are fixed this patch can
>>> be reverted.
>>>
>>> Fixes: 4c21b5bcef73 ("IB/cma: Add net_dev and private data checks to
>>> RDMA CM")
>>> Signed-off-by: Haggai Eran <haggaie@mellanox.com>
>>> ---
>>> Changes from v0:
>>> - improve commit message
>>>
>>>  drivers/infiniband/core/cma.c | 4 ++--
>>>  1 file changed, 2 insertions(+), 2 deletions(-)
>>>
>>> diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
>>> index 59a2dafc8c57..e8324543e085 100644
>>> --- a/drivers/infiniband/core/cma.c
>>> +++ b/drivers/infiniband/core/cma.c
>>> @@ -1067,14 +1067,14 @@ static int cma_save_req_info(const struct ib_cm_event *ib_event,
>>>  		       sizeof(req->local_gid));
>>>  		req->has_gid	= true;
>>>  		req->service_id	= req_param->primary_path->service_id;
>>> -		req->pkey	= req_param->bth_pkey;
>>> +		req->pkey	= be16_to_cpu(req_param->primary_path->pkey);
>>>  		break;
>>>  	case IB_CM_SIDR_REQ_RECEIVED:
>>>  		req->device	= sidr_param->listen_id->device;
>>>  		req->port	= sidr_param->port;
>>>  		req->has_gid	= false;
>>>  		req->service_id	= sidr_param->service_id;
>>> -		req->pkey	= sidr_param->bth_pkey;
>>> +		req->pkey	= sidr_param->pkey;
>>>  		break;
>>>  	default:
>>>  		return -EINVAL;
>>>
>>
>> And, to be clear, you are looking for this to be part of 4.3-rc updates,
>> yes?
> 
> Yes, the issue was introduced in 4.3 in my cma demux patch.

Applied, thanks.
diff mbox

Patch

diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 59a2dafc8c57..e8324543e085 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -1067,14 +1067,14 @@  static int cma_save_req_info(const struct ib_cm_event *ib_event,
 		       sizeof(req->local_gid));
 		req->has_gid	= true;
 		req->service_id	= req_param->primary_path->service_id;
-		req->pkey	= req_param->bth_pkey;
+		req->pkey	= be16_to_cpu(req_param->primary_path->pkey);
 		break;
 	case IB_CM_SIDR_REQ_RECEIVED:
 		req->device	= sidr_param->listen_id->device;
 		req->port	= sidr_param->port;
 		req->has_gid	= false;
 		req->service_id	= sidr_param->service_id;
-		req->pkey	= sidr_param->bth_pkey;
+		req->pkey	= sidr_param->pkey;
 		break;
 	default:
 		return -EINVAL;