[openib-general][PATCH][SRP] bug fixes & fmr supported,

[Vu Pham]

Christoph Hellwig wrote:

>>I think it makes more sense to handle this the same way I handled
>>max_sectors: make it a per-target parameter passed in when connecting
>>to the target.  We could make cmds_per_lun a similar parameter, but
>>are there likely to be any SRP targets that need this to be limited?
>>Also, what is max_targets?
> 
> 
> Why do we need a limited max_luns at all?  I hope all SRP targets
> propetly support REPORT_LUNS in which case we couldn't care less about
> a maximum LUN limit.  And even if they don't I hope they handle scanning
> the first non-existant LUN gracefully.
> 

I aggreed. However, we need to override the default value of 
the scsi_host->max_lun with some big number ie. 1024