> Understood, however, unlike SoftRoCE, qib and hfi currently share a lot of code > to drive the hardware. > > The underlying reason for the TODO item "Remove software processing of IB > protocol..." is because we have a large amount of duplicated code between these > drivers. _Some_ of which, at a high level, is sharable with SoftRoCE. > After studying the qib driver (briefly I must admit) I found that it has a lot in common with SoftRoCE driver and both can be redesigned to share a fair amount of code. > These patches (and more to follow), further differentiate the 2 drivers along > hardware lines. Accepting these patches will help us make sure that we don't > create some common code between qib and hfi which, because of our testing we > now know, needs to be separated out. > I'm sorry but I'm not sure that I understand the plan. What we had in mind is that we start following the idea which was presented by Deny, build a detailed design plan and implement it. All that can be done without fixing bugs, adding functionality and improving performance but I understand that you also need to move forward. Us, in Mellanox are willing to contribute to the effort and take responsibility over the Software Verbs Transport. > This is a separate issue from the higher level code sharing which will be done > with SoftRoCE. I'm not sure I agree. Can you explain the plan to remove code sharing between qib and hfi that is not part of the Software Verbs Transport module? > > Ira > > -- > To unsubscribe from this list: send the line "unsubscribe linux-rdma" in > the body of a message to majordomo@xxxxxxxxxxxxxxx > More majordomo info at http://vger.kernel.org/majordomo-info.html -- To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
