[ofa-general] [PATCH RFC] rds: add iwarp support

[Steve Wise]

Jon Mason wrote:
> On Mon, Jul 07, 2008 at 04:10:09PM -0500, Steve Wise wrote:
>   
>> Sean Hefty wrote:
>>     
>>>> Maybe there's a better way?
>>>>     
>>>>         
>>> I would look at using rdma_resolve_ip, or using rdma_resolve_addr as is.
>>>
>>> The rdma_cm_id ensures that there's a reference on the ib_device for the pointer
>>> that's returned.  The proposed interface returns a pointer without any way to
>>> verify that it's still valid, or know when it is no longer usable.
>>>
>>>   
>>>       
>> The rds module already _has_ cm_id's bound to these devices. So they  
>> won't "go away" without rds getting an event. The service in question  
>> was just a quick way to map an ip address to its associated struct  
>> ib_device. Perhaps this just needs to be a function inside the rds  
>> module as opposed to something exported from the cma proper...
>>     
>
> Unfortunately, this cannot be rds only.  All the data structs are local
> to cma.c.  
>
> The question is, if given only a u32 ipaddr, is there a way to turn this
> into a struct ib_device *?
>
> Thanks,
> Jon
>
>   
Ah yes. The cma dev list is static. But ib_find_cached_gid() is 
exported. If you only really ever need to do this on active connections, 
then you could walk your list of connected cm_ids and get the struct 
ib_device for each and call ib_find_cached_gid() to see if its a match. 
Would that work? It would handle setting up new connections, but maybe 
that is a different path?


steve.