Merge branch 'hfi1' into merge-test

3 files changed, 108 insertions, 25 deletions

diff --git a/include/rdma/rdma_vt.h b/include/rdma/rdma_vt.h
index e31502107a58..861e23eaebda 100644
--- a/include/rdma/rdma_vt.h
+++ b/include/rdma/rdma_vt.h
@@ -185,6 +185,27 @@ struct rvt_driver_provided {
 	 * check_support() for details.
 	 */
 
+	/* hot path calldowns in a single cacheline */
+
+	/*
+	 * Give the driver a notice that there is send work to do. It is up to
+	 * the driver to generally push the packets out, this just queues the
+	 * work with the driver. There are two variants here. The no_lock
+	 * version requires the s_lock not to be held. The other assumes the
+	 * s_lock is held.
+	 */
+	void (*schedule_send)(struct rvt_qp *qp);
+	void (*schedule_send_no_lock)(struct rvt_qp *qp);
+
+	/* Driver specific work request checking */
+	int (*check_send_wqe)(struct rvt_qp *qp, struct rvt_swqe *wqe);
+
+	/*
+	 * Sometimes rdmavt needs to kick the driver's send progress. That is
+	 * done by this call back.
+	 */
+	void (*do_send)(struct rvt_qp *qp);
+
 	/* Passed to ib core registration. Callback to create syfs files */
 	int (*port_callback)(struct ib_device *, u8, struct kobject *);
 
@@ -223,22 +244,6 @@ struct rvt_driver_provided {
 	void (*notify_qp_reset)(struct rvt_qp *qp);
 
 	/*
-	 * Give the driver a notice that there is send work to do. It is up to
-	 * the driver to generally push the packets out, this just queues the
-	 * work with the driver. There are two variants here. The no_lock
-	 * version requires the s_lock not to be held. The other assumes the
-	 * s_lock is held.
-	 */
-	void (*schedule_send)(struct rvt_qp *qp);
-	void (*schedule_send_no_lock)(struct rvt_qp *qp);
-
-	/*
-	 * Sometimes rdmavt needs to kick the driver's send progress. That is
-	 * done by this call back.
-	 */
-	void (*do_send)(struct rvt_qp *qp);
-
-	/*
 	 * Get a path mtu from the driver based on qp attributes.
 	 */
 	int (*get_pmtu_from_attr)(struct rvt_dev_info *rdi, struct rvt_qp *qp,
@@ -324,9 +329,6 @@ struct rvt_driver_provided {
 	void (*modify_qp)(struct rvt_qp *qp, struct ib_qp_attr *attr,
 			  int attr_mask, struct ib_udata *udata);
 
-	/* Driver specific work request checking */
-	int (*check_send_wqe)(struct rvt_qp *qp, struct rvt_swqe *wqe);
-
 	/* Notify driver a mad agent has been created */
 	void (*notify_create_mad_agent)(struct rvt_dev_info *rdi, int port_idx);
 
@@ -355,12 +357,12 @@ struct rvt_dev_info {
 	/* post send table */
 	const struct rvt_operation_params *post_parms;
 
-	struct rvt_mregion __rcu *dma_mr;
-	struct rvt_lkey_table lkey_table;
-
 	/* Driver specific helper functions */
 	struct rvt_driver_provided driver_f;
 
+	struct rvt_mregion __rcu *dma_mr;
+	struct rvt_lkey_table lkey_table;
+
 	/* Internal use */
 	int n_pds_allocated;
 	spinlock_t n_pds_lock; /* Protect pd allocated count */
diff --git a/include/rdma/rdmavt_mr.h b/include/rdma/rdmavt_mr.h
index 6b3c6c8b6b77..de59de28b6a2 100644
--- a/include/rdma/rdmavt_mr.h
+++ b/include/rdma/rdmavt_mr.h
@@ -90,11 +90,15 @@ struct rvt_mregion {
 #define RVT_MAX_LKEY_TABLE_BITS 23
 
 struct rvt_lkey_table {
-	spinlock_t lock; /* protect changes in this struct */
-	u32 next;               /* next unused index (speeds search) */
-	u32 gen;                /* generation count */
+	/* read mostly fields */
 	u32 max;                /* size of the table */
+	u32 shift;              /* lkey/rkey shift */
 	struct rvt_mregion __rcu **table;
+	/* writeable fields */
+	/* protect changes in this struct */
+	spinlock_t lock ____cacheline_aligned_in_smp;
+	u32 next;               /* next unused index (speeds search) */
+	u32 gen;                /* generation count */
 };
 
 /*
diff --git a/include/rdma/rdmavt_qp.h b/include/rdma/rdmavt_qp.h
index 2c5183ef0243..f3dbd157ae5c 100644
--- a/include/rdma/rdmavt_qp.h
+++ b/include/rdma/rdmavt_qp.h
@@ -51,6 +51,7 @@
 #include <rdma/rdma_vt.h>
 #include <rdma/ib_pack.h>
 #include <rdma/ib_verbs.h>
+#include <rdma/rdmavt_cq.h>
 /*
  * Atomic bit definitions for r_aflags.
  */
@@ -485,6 +486,23 @@ static inline void rvt_put_qp(struct rvt_qp *qp)
 }
 
 /**
+ * rvt_put_swqe - drop mr refs held by swqe
+ * @wqe - the send wqe
+ *
+ * This drops any mr references held by the swqe
+ */
+static inline void rvt_put_swqe(struct rvt_swqe *wqe)
+{
+	int i;
+
+	for (i = 0; i < wqe->wr.num_sge; i++) {
+		struct rvt_sge *sge = &wqe->sg_list[i];
+
+		rvt_put_mr(sge->mr);
+	}
+}
+
+/**
  * rvt_qp_wqe_reserve - reserve operation
  * @qp - the rvt qp
  * @wqe - the send wqe
@@ -527,6 +545,65 @@ static inline void rvt_qp_wqe_unreserve(
 	}
 }
 
+extern const enum ib_wc_opcode ib_rvt_wc_opcode[];
+
+/**
+ * rvt_qp_swqe_complete() - insert send completion
+ * @qp - the qp
+ * @wqe - the send wqe
+ * @status - completion status
+ *
+ * Insert a send completion into the completion
+ * queue if the qp indicates it should be done.
+ *
+ * See IBTA 10.7.3.1 for info on completion
+ * control.
+ */
+static inline void rvt_qp_swqe_complete(
+	struct rvt_qp *qp,
+	struct rvt_swqe *wqe,
+	enum ib_wc_status status)
+{
+	if (unlikely(wqe->wr.send_flags & RVT_SEND_RESERVE_USED))
+		return;
+	if (!(qp->s_flags & RVT_S_SIGNAL_REQ_WR) ||
+	    (wqe->wr.send_flags & IB_SEND_SIGNALED) ||
+	     status != IB_WC_SUCCESS) {
+		struct ib_wc wc;
+
+		memset(&wc, 0, sizeof(wc));
+		wc.wr_id = wqe->wr.wr_id;
+		wc.status = status;
+		wc.opcode = ib_rvt_wc_opcode[wqe->wr.opcode];
+		wc.qp = &qp->ibqp;
+		wc.byte_len = wqe->length;
+		rvt_cq_enter(ibcq_to_rvtcq(qp->ibqp.send_cq), &wc,
+			     status != IB_WC_SUCCESS);
+	}
+}
+
+/**
+ * @qp - the qp pair
+ * @len - the length
+ *
+ * Perform a shift based mtu round up divide
+ */
+static inline u32 rvt_div_round_up_mtu(struct rvt_qp *qp, u32 len)
+{
+	return (len + qp->pmtu - 1) >> qp->log_pmtu;
+}
+
+/**
+ * @qp - the qp pair
+ * @len - the length
+ *
+ * Perform a shift based mtu divide
+ */
+static inline u32 rvt_div_mtu(struct rvt_qp *qp, u32 len)
+{
+	return len >> qp->log_pmtu;
+}
+
 extern const int  ib_rvt_state_ops[];
 
 struct rvt_dev_info;