IB/rdmavt: Add post send to rdmavt
Add in a post_send and post_one_send to rdmavt. The ULP will provide a WQE
to rdmavt which will then walk and queue each element. Rdmavt will then
queue the work to be done in the driver or kick the driver's progress
routine.
There needs to be a follow on patch which adds in another lock for the
head of the queue so that it can be added to and read from in parallel.
This will touch protocol handlers and require other changes in the
drivers. This will be done separately.
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
diff --git a/include/rdma/rdma_vt.h b/include/rdma/rdma_vt.h
index 79080e3..36e4fb4c 100644
--- a/include/rdma/rdma_vt.h
+++ b/include/rdma/rdma_vt.h
@@ -231,6 +231,8 @@
gfp_t gfp);
void (*qp_priv_free)(struct rvt_dev_info *rdi, struct rvt_qp *qp);
void (*notify_qp_reset)(struct rvt_qp *qp);
+ void (*schedule_send)(struct rvt_qp *qp);
+ void (*do_send)(struct rvt_qp *qp);
/*--------------------*/
/* Optional functions */
@@ -312,6 +314,11 @@
return container_of(ibsrq, struct rvt_srq, ibsrq);
}
+static inline struct rvt_qp *ibqp_to_rvtqp(struct ib_qp *ibqp)
+{
+ return container_of(ibqp, struct rvt_qp, ibqp);
+}
+
static inline unsigned rvt_get_npkeys(struct rvt_dev_info *rdi)
{
/*