RDS: IB: split the mr registration and invalidation path

MR invalidation in RDS is done in background thread and not in
data path like registration. So break the dependency between them
which helps to remove the performance bottleneck.
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>

net/rds/ib.h

@@ -14,7 +14,8 @@
 
 #define RDS_IB_DEFAULT_RECV_WR		1024
 #define RDS_IB_DEFAULT_SEND_WR		256
-#define RDS_IB_DEFAULT_FR_WR		512
+#define RDS_IB_DEFAULT_FR_WR		256
+#define RDS_IB_DEFAULT_FR_INV_WR	256
 
 #define RDS_IB_DEFAULT_RETRY_COUNT	1
 
@@ -125,6 +126,7 @@ struct rds_ib_connection {
 
 	/* To control the number of wrs from fastreg */
 	atomic_t		i_fastreg_wrs;
+	atomic_t		i_fastunreg_wrs;
 
 	/* interrupt handling */
 	struct tasklet_struct	i_send_tasklet;

net/rds/ib_cm.c

@@ -382,7 +382,10 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
 	 * completion queue and send queue. This extra space is used for FRMR
 	 * registration and invalidation work requests
 	 */
-	fr_queue_space = (rds_ibdev->use_fastreg ? RDS_IB_DEFAULT_FR_WR : 0);
+	fr_queue_space = rds_ibdev->use_fastreg ?
+			 (RDS_IB_DEFAULT_FR_WR + 1) +
+			 (RDS_IB_DEFAULT_FR_INV_WR + 1)
+			 : 0;
 
 	/* add the conn now so that connection establishment has the dev */
 	rds_ib_add_conn(rds_ibdev, conn);
@@ -444,6 +447,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
 	attr.send_cq = ic->i_send_cq;
 	attr.recv_cq = ic->i_recv_cq;
 	atomic_set(&ic->i_fastreg_wrs, RDS_IB_DEFAULT_FR_WR);
+	atomic_set(&ic->i_fastunreg_wrs, RDS_IB_DEFAULT_FR_INV_WR);
 
 	/*
 	 * XXX this can fail if max_*_wr is too large?  Are we supposed
@@ -766,7 +770,8 @@ void rds_ib_conn_path_shutdown(struct rds_conn_path *cp)
 		wait_event(rds_ib_ring_empty_wait,
 			   rds_ib_ring_empty(&ic->i_recv_ring) &&
 			   (atomic_read(&ic->i_signaled_sends) == 0) &&
-			   (atomic_read(&ic->i_fastreg_wrs) == RDS_IB_DEFAULT_FR_WR));
+			   (atomic_read(&ic->i_fastreg_wrs) == RDS_IB_DEFAULT_FR_WR) &&
+			   (atomic_read(&ic->i_fastunreg_wrs) == RDS_IB_DEFAULT_FR_INV_WR));
 		tasklet_kill(&ic->i_send_tasklet);
 		tasklet_kill(&ic->i_recv_tasklet);
 

net/rds/ib_frmr.c

@@ -241,8 +241,8 @@ static int rds_ib_post_inv(struct rds_ib_mr *ibmr)
 	if (frmr->fr_state != FRMR_IS_INUSE)
 		goto out;
 
-	while (atomic_dec_return(&ibmr->ic->i_fastreg_wrs) <= 0) {
-		atomic_inc(&ibmr->ic->i_fastreg_wrs);
+	while (atomic_dec_return(&ibmr->ic->i_fastunreg_wrs) <= 0) {
+		atomic_inc(&ibmr->ic->i_fastunreg_wrs);
 		cpu_relax();
 	}
 
@@ -261,7 +261,7 @@ static int rds_ib_post_inv(struct rds_ib_mr *ibmr)
 	if (unlikely(ret)) {
 		frmr->fr_state = FRMR_IS_STALE;
 		frmr->fr_inv = false;
-		atomic_inc(&ibmr->ic->i_fastreg_wrs);
+		atomic_inc(&ibmr->ic->i_fastunreg_wrs);
 		pr_err("RDS/IB: %s returned error(%d)\n", __func__, ret);
 		goto out;
 	}
@@ -289,9 +289,10 @@ void rds_ib_mr_cqe_handler(struct rds_ib_connection *ic, struct ib_wc *wc)
 	if (frmr->fr_inv) {
 		frmr->fr_state = FRMR_IS_FREE;
 		frmr->fr_inv = false;
+		atomic_inc(&ic->i_fastreg_wrs);
+	} else {
+		atomic_inc(&ic->i_fastunreg_wrs);
 	}
-
-	atomic_inc(&ic->i_fastreg_wrs);
 }
 
 void rds_ib_unreg_frmr(struct list_head *list, unsigned int *nfreed,