Merge branch 'net/rds-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/ssantosh/linux

Santosh Shilimkar says:

====================
rds fixes

Few rds fixes which makes rds rdma transport reliably working on mainline

First two fixes are applicable to v4.11+ stable versions and last
three patches applies to only v5.1 stable and current mainline.

Patchset is re-based against 'net' and also available on below tree
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

net/rds/connection.c

@@ -736,6 +736,7 @@ static int rds_conn_info_visitor(struct rds_conn_path *cp, void *buffer)
 	cinfo->next_rx_seq = cp->cp_next_rx_seq;
 	cinfo->laddr = conn->c_laddr.s6_addr32[3];
 	cinfo->faddr = conn->c_faddr.s6_addr32[3];
+	cinfo->tos = conn->c_tos;
 	strncpy(cinfo->transport, conn->c_trans->t_name,
 		sizeof(cinfo->transport));
 	cinfo->flags = 0;

net/rds/ib.h

@@ -15,8 +15,7 @@
 
 #define RDS_IB_DEFAULT_RECV_WR		1024
 #define RDS_IB_DEFAULT_SEND_WR		256
-#define RDS_IB_DEFAULT_FR_WR		256
-#define RDS_IB_DEFAULT_FR_INV_WR	256
+#define RDS_IB_DEFAULT_FR_WR		512
 
 #define RDS_IB_DEFAULT_RETRY_COUNT	1
 
@@ -157,7 +156,6 @@ 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

@@ -460,10 +460,7 @@ 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 + 1) +
-			 (RDS_IB_DEFAULT_FR_INV_WR + 1)
-			 : 0;
+	fr_queue_space = (rds_ibdev->use_fastreg ? RDS_IB_DEFAULT_FR_WR : 0);
 
 	/* add the conn now so that connection establishment has the dev */
 	rds_ib_add_conn(rds_ibdev, conn);
@@ -530,7 +527,6 @@ 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
@@ -1009,8 +1005,7 @@ 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_fastunreg_wrs) == RDS_IB_DEFAULT_FR_INV_WR));
+			   (atomic_read(&ic->i_fastreg_wrs) == RDS_IB_DEFAULT_FR_WR));
 		tasklet_kill(&ic->i_send_tasklet);
 		tasklet_kill(&ic->i_recv_tasklet);
 

net/rds/ib_frmr.c

@@ -239,8 +239,8 @@ 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_fastunreg_wrs) <= 0) {
-		atomic_inc(&ibmr->ic->i_fastunreg_wrs);
+	while (atomic_dec_return(&ibmr->ic->i_fastreg_wrs) <= 0) {
+		atomic_inc(&ibmr->ic->i_fastreg_wrs);
 		cpu_relax();
 	}
 
@@ -257,7 +257,7 @@ 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_fastunreg_wrs);
+		atomic_inc(&ibmr->ic->i_fastreg_wrs);
 		pr_err("RDS/IB: %s returned error(%d)\n", __func__, ret);
 		goto out;
 	}
@@ -285,10 +285,9 @@ 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,

net/rds/ib_send.c

@@ -69,6 +69,16 @@ static void rds_ib_send_complete(struct rds_message *rm,
 	complete(rm, notify_status);
 }
 
+static void rds_ib_send_unmap_data(struct rds_ib_connection *ic,
+				   struct rm_data_op *op,
+				   int wc_status)
+{
+	if (op->op_nents)
+		ib_dma_unmap_sg(ic->i_cm_id->device,
+				op->op_sg, op->op_nents,
+				DMA_TO_DEVICE);
+}
+
 static void rds_ib_send_unmap_rdma(struct rds_ib_connection *ic,
 				   struct rm_rdma_op *op,
 				   int wc_status)
@@ -129,21 +139,6 @@ static void rds_ib_send_unmap_atomic(struct rds_ib_connection *ic,
 		rds_ib_stats_inc(s_ib_atomic_fadd);
 }
 
-static void rds_ib_send_unmap_data(struct rds_ib_connection *ic,
-				   struct rm_data_op *op,
-				   int wc_status)
-{
-	struct rds_message *rm = container_of(op, struct rds_message, data);
-
-	if (op->op_nents)
-		ib_dma_unmap_sg(ic->i_cm_id->device,
-				op->op_sg, op->op_nents,
-				DMA_TO_DEVICE);
-
-	if (rm->rdma.op_active && rm->data.op_notify)
-		rds_ib_send_unmap_rdma(ic, &rm->rdma, wc_status);
-}
-
 /*
  * Unmap the resources associated with a struct send_work.
  *
@@ -902,7 +897,9 @@ int rds_ib_xmit_rdma(struct rds_connection *conn, struct rm_rdma_op *op)
 		send->s_queued = jiffies;
 		send->s_op = NULL;
 
-		nr_sig += rds_ib_set_wr_signal_state(ic, send, op->op_notify);
+		if (!op->op_notify)
+			nr_sig += rds_ib_set_wr_signal_state(ic, send,
+							     op->op_notify);
 
 		send->s_wr.opcode = op->op_write ? IB_WR_RDMA_WRITE : IB_WR_RDMA_READ;
 		send->s_rdma_wr.remote_addr = remote_addr;

net/rds/rdma.c

@@ -641,16 +641,6 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm,
 		}
 		op->op_notifier->n_user_token = args->user_token;
 		op->op_notifier->n_status = RDS_RDMA_SUCCESS;
-
-		/* Enable rmda notification on data operation for composite
-		 * rds messages and make sure notification is enabled only
-		 * for the data operation which follows it so that application
-		 * gets notified only after full message gets delivered.
-		 */
-		if (rm->data.op_sg) {
-			rm->rdma.op_notify = 0;
-			rm->data.op_notify = !!(args->flags & RDS_RDMA_NOTIFY_ME);
-		}
 	}
 
 	/* The cookie contains the R_Key of the remote memory region, and

net/rds/rdma_transport.c

@@ -112,17 +112,20 @@ static int rds_rdma_cm_event_handler_cmn(struct rdma_cm_id *cm_id,
 		if (!conn)
 			break;
 		err = (int *)rdma_consumer_reject_data(cm_id, event, &len);
-		if (!err || (err && ((*err) == RDS_RDMA_REJ_INCOMPAT))) {
+		if (!err ||
+		    (err && len >= sizeof(*err) &&
+		     ((*err) <= RDS_RDMA_REJ_INCOMPAT))) {
 			pr_warn("RDS/RDMA: conn <%pI6c, %pI6c> rejected, dropping connection\n",
 				&conn->c_laddr, &conn->c_faddr);
-			conn->c_proposed_version = RDS_PROTOCOL_COMPAT_VERSION;
-			conn->c_tos = 0;
+
+			if (!conn->c_tos)
+				conn->c_proposed_version = RDS_PROTOCOL_COMPAT_VERSION;
+
 			rds_conn_drop(conn);
 		}
 		rdsdebug("Connection rejected: %s\n",
 			 rdma_reject_msg(cm_id, event->status));
 		break;
-		/* FALLTHROUGH */
 	case RDMA_CM_EVENT_ADDR_ERROR:
 	case RDMA_CM_EVENT_ROUTE_ERROR:
 	case RDMA_CM_EVENT_CONNECT_ERROR:

net/rds/rds.h

@@ -476,7 +476,6 @@ struct rds_message {
 		} rdma;
 		struct rm_data_op {
 			unsigned int		op_active:1;
-			unsigned int		op_notify:1;
 			unsigned int		op_nents;
 			unsigned int		op_count;
 			unsigned int		op_dmasg;

net/rds/send.c

@@ -491,14 +491,12 @@ void rds_rdma_send_complete(struct rds_message *rm, int status)
 	struct rm_rdma_op *ro;
 	struct rds_notifier *notifier;
 	unsigned long flags;
-	unsigned int notify = 0;
 
 	spin_lock_irqsave(&rm->m_rs_lock, flags);
 
-	notify =  rm->rdma.op_notify | rm->data.op_notify;
 	ro = &rm->rdma;
 	if (test_bit(RDS_MSG_ON_SOCK, &rm->m_flags) &&
-	    ro->op_active && notify && ro->op_notifier) {
+	    ro->op_active && ro->op_notify && ro->op_notifier) {
 		notifier = ro->op_notifier;
 		rs = rm->m_rs;
 		sock_hold(rds_rs_to_sk(rs));