[ewg] OFED-1.5.1 failure over iWarp

[Steve Wise]

Eli Cohen wrote:
> On Wed, Feb 03, 2010 at 02:28:05PM -0600, Steve Wise wrote:
>   
>> Here is the patched cma_acquire_dev() function.  Where does it
>> "build the gid in the pre rocee patches fashion and search again"
>> for the iwarp case?  Maybe I'm missing it?
>>
>> ---------------
>> static int cma_acquire_dev(struct rdma_id_private *id_priv)
>> {
>>        struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr;
>>        struct cma_device *cma_dev;
>>        union ib_gid gid;
>>        int ret = -ENODEV;
>>
>>        if (dev_addr->dev_type != ARPHRD_INFINIBAND) {
>>                rocee_addr_get_sgid(dev_addr, &gid);
>>                list_for_each_entry(cma_dev, &dev_list, list) {
>>                        ret = ib_find_cached_gid(cma_dev->device, &gid,
>>                                                 &id_priv->id.port_num,
>> NULL);
>>                        if (!ret)
>>                                break;
>>                }
>>        } else {
>>     
>
> here it is - it's the memcpy below:
>
>   
How does it get here if it was already in the above block?  IE it won't 
fall into this block, right?

>>                memcpy(&gid, dev_addr->src_dev_addr +
>>                       rdma_addr_gid_offset(dev_addr), sizeof gid);
>>                list_for_each_entry(cma_dev, &dev_list, list) {
>>                        ret = ib_find_cached_gid(cma_dev->device, &gid,
>>                                                 &id_priv->id.port_num,
>> NULL);
>>                        if (!ret)
>>                                break;
>>                }
>>        }
>>
>>        if (!ret)
>>                cma_attach_to_dev(id_priv, cma_dev);
>>
>>        return ret;
>> }
>> ----------------
>>
>>
>>
>> Eli Cohen wrote:
>>     
>>> On Wed, Feb 03, 2010 at 09:20:05AM -0600, Steve Wise wrote:
>>>       
>>>>> diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
>>>>> index a2d5aad..76dce2b 100644
>>>>> --- a/drivers/infiniband/core/cma.c
>>>>> +++ b/drivers/infiniband/core/cma.c
>>>>> @@ -348,15 +348,28 @@ static int cma_acquire_dev(struct rdma_id_private *id_priv)
>>>>> 	union ib_gid gid;
>>>>> 	int ret = -ENODEV;
>>>>> -	rdma_addr_get_sgid(dev_addr, &gid);
>>>>> -	list_for_each_entry(cma_dev, &dev_list, list) {
>>>>> -		ret = ib_find_cached_gid(cma_dev->device, &gid,
>>>>> -					 &id_priv->id.port_num, NULL);
>>>>> -		if (!ret) {
>>>>> -			cma_attach_to_dev(id_priv, cma_dev);
>>>>> -			break;
>>>>> +	if (dev_addr->dev_type != ARPHRD_INFINIBAND) {
>>>>> +		rocee_addr_get_sgid(dev_addr, &gid);
>>>>> +		list_for_each_entry(cma_dev, &dev_list, list) {
>>>>> +			ret = ib_find_cached_gid(cma_dev->device, &gid,
>>>>> +						 &id_priv->id.port_num, NULL);
>>>>> +			if (!ret)
>>>>> +				break;
>>>>> +		}
>>>>>           
>>>> The above if statement is true for iwarp devices, so this patch is
>>>> just wrong.   rocee__addr_get_sgid() should only be used for ROCEE
>>>> interfaces, correct?
>>>>         
>>> No, the idea is this: for non ARPHRD_INFINIBAND devices (e.g. rocee or
>>> iwarp) I assume first this rocee, get the rocee gid, and check if this
>>> gid appears in any device's gid table. It the mac address belongs to a
>>> rocee device then it will be found; if it belongs to an iwarp device
>>> then it won't be found. In the later case I build the gid in the pre
>>> rocee patches fashion and search again.
>>>       
>>>>> +	} else {
>>>>> +		memcpy(&gid, dev_addr->src_dev_addr +
>>>>> +		       rdma_addr_gid_offset(dev_addr), sizeof gid);
>>>>> +		list_for_each_entry(cma_dev, &dev_list, list) {
>>>>> +			ret = ib_find_cached_gid(cma_dev->device, &gid,
>>>>> +						 &id_priv->id.port_num, NULL);
>>>>> +			if (!ret)
>>>>> +				break;
>>>>> 		}
>>>>> 	}
>>>>> +
>>>>> +	if (!ret)
>>>>> +		cma_attach_to_dev(id_priv, cma_dev);
>>>>> +
>>>>> 	return ret;
>>>>> }
>>>>>