[ofa-general] Re: [RFC][PATCH] last wqe event handler patch

[Roland Dreier]

 > Thanks for the clarification. Another question, after the QP entered an
 > error state, the HCA can generate a cqe for post_send drain WRs?

Yes, this is required by the spec.

 > I saw some panic in Mellanox HCAs, I thought this senarios could cause a
 > panic. ehca doesn't support post_send() drain WRs after such an event. So
 > it can't be a problem for ehca.

This is just the bug in ehca rejecting send WRs in error state that only
was in some 2.6.26-rc kernels, right?