[ofa-general] rdma_create_qp fails with -12

[Roland Dreier]

 > Hi Galen, indeed, this was discussed on the list before with the
 > reason for the -ENOMEM failure being the kmalloc (and its such, as
 > mentioed in https://bugs.openfabrics.org/show_bug.cgi?id=331)
 > mentioned below.
 > 
 > Basically, I see it more of a missing questionable feature then a bug,
 > but you may want to get a response from Roland on that.

Yes, I agree with Or's assessment.  The work request ID auxiliary
array is allocated using contiguous memory in the kernel (it's not a
problem in userspace because userspace virtual memory need not be
physically contiguous).  Removing this limitation would make the code
more complex, and in general supporting huge queue depths hasn't
seemed that important.

 - R.