[ofa-general] [PATCH/RFC 1/2] IB/core: Add support for "send with invalidate" work requests

[Steve Wise]

Roland Dreier wrote:
> Add an IB_SEND_INVALIDATE send flag that can be used to mark a "send
> with invalidate" work request as defined in the iWARP verbs and the
> InfiniBand base memory management extensions.  Also add a new
> "invalidate" structure to the struct ib_send_wr.wr union that can be
> used to pass in an R_Key/STag to be invalidated.  Add this new
> structure to struct ib_uverbs_send_wr and add code to copy the rkey
> field in ib_uverbs_post_send().
>
> Also, move the existing IB_DEVICE_SEND_W_INV flag to a new bit, since
> the iWARP drivers currently in the tree set the bit.  The amso1100
> driver at least will silently fail to honor the IB_SEND_INVALIDATE bit
> if passed in as part of userspace send requests (since it does not
> implement kernel bypass work request queueing).  Remove the flag from
> all existing drivers that set it until we know which ones are OK.
>
> The values chosen for the new flags are not consecutive to avoid
> clashing with flags defined in the IPoIB large send offload and XRC
> patches, which are not merged yet but which are already in use and are
> likely to be merged soon.
>
> This resurrects a patch sent long ago by Mikkel Hagen <mhagen at iol.unh.edu>.
>
> Signed-off-by: Roland Dreier <rolandd at cisco.com>
> ---
> I tried to avoid clashes with any flags values defined in OFED 1.3,
> just to make things a little simpler for users.  However a double
> check that I succeeded in avoiding already-used values would be good.
>
> Also I think redefining the IB_DEVICE_SEND_W_INV to a new value avoids
> all the backwards and forwards compatibility problems that were a
> sticking point when this idea originally appeared.
>
> Anyway if this looks good to people I will merge it for 2.6.26.
>
>   
Looks ok to me.

Steve.