1 files changed, 142 insertions, 82 deletions

diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c
index 0c9d2af15f3d..f63771207970 100644
--- a/drivers/infiniband/sw/rxe/rxe_req.c
+++ b/drivers/infiniband/sw/rxe/rxe_req.c
@@ -15,8 +15,7 @@ static int next_opcode(struct rxe_qp *qp, struct rxe_send_wqe *wqe,
 		       u32 opcode);
 
 static inline void retry_first_write_send(struct rxe_qp *qp,
-					  struct rxe_send_wqe *wqe,
-					  unsigned int mask, int npsn)
+					  struct rxe_send_wqe *wqe, int npsn)
 {
 	int i;
 
@@ -33,8 +32,6 @@ static inline void retry_first_write_send(struct rxe_qp *qp,
 		} else {
 			advance_dma_data(&wqe->dma, to_send);
 		}
-		if (mask & WR_WRITE_MASK)
-			wqe->iova += qp->mtu;
 	}
 }
 
@@ -85,7 +82,7 @@ static void req_retry(struct rxe_qp *qp)
 			if (mask & WR_WRITE_OR_SEND_MASK) {
 				npsn = (qp->comp.psn - wqe->first_psn) &
 					BTH_PSN_MASK;
-				retry_first_write_send(qp, wqe, mask, npsn);
+				retry_first_write_send(qp, wqe, npsn);
 			}
 
 			if (mask & WR_READ_MASK) {
@@ -103,14 +100,17 @@ void rnr_nak_timer(struct timer_list *t)
 {
 	struct rxe_qp *qp = from_timer(qp, t, rnr_nak_timer);
 
-	pr_debug("qp#%d rnr nak timer fired\n", qp_num(qp));
+	pr_debug("%s: fired for qp#%d\n", __func__, qp_num(qp));
+
+	/* request a send queue retry */
+	qp->req.need_retry = 1;
+	qp->req.wait_for_rnr_timer = 0;
 	rxe_run_task(&qp->req.task, 1);
 }
 
 static struct rxe_send_wqe *req_next_wqe(struct rxe_qp *qp)
 {
 	struct rxe_send_wqe *wqe;
-	unsigned long flags;
 	struct rxe_queue *q = qp->sq.queue;
 	unsigned int index = qp->req.wqe_index;
 	unsigned int cons;
@@ -124,25 +124,23 @@ static struct rxe_send_wqe *req_next_wqe(struct rxe_qp *qp)
 		/* check to see if we are drained;
 		 * state_lock used by requester and completer
 		 */
-		spin_lock_irqsave(&qp->state_lock, flags);
+		spin_lock_bh(&qp->state_lock);
 		do {
 			if (qp->req.state != QP_STATE_DRAIN) {
 				/* comp just finished */
-				spin_unlock_irqrestore(&qp->state_lock,
-						       flags);
+				spin_unlock_bh(&qp->state_lock);
 				break;
 			}
 
 			if (wqe && ((index != cons) ||
 				(wqe->state != wqe_state_posted))) {
 				/* comp not done yet */
-				spin_unlock_irqrestore(&qp->state_lock,
-						       flags);
+				spin_unlock_bh(&qp->state_lock);
 				break;
 			}
 
 			qp->req.state = QP_STATE_DRAINED;
-			spin_unlock_irqrestore(&qp->state_lock, flags);
+			spin_unlock_bh(&qp->state_lock);
 
 			if (qp->ibqp.event_handler) {
 				struct ib_event ev;
@@ -166,16 +164,36 @@ static struct rxe_send_wqe *req_next_wqe(struct rxe_qp *qp)
 		     (wqe->state != wqe_state_processing)))
 		return NULL;
 
-	if (unlikely((wqe->wr.send_flags & IB_SEND_FENCE) &&
-						     (index != cons))) {
-		qp->req.wait_fence = 1;
-		return NULL;
-	}
-
 	wqe->mask = wr_opcode_mask(wqe->wr.opcode, qp);
 	return wqe;
 }
 
+/**
+ * rxe_wqe_is_fenced - check if next wqe is fenced
+ * @qp: the queue pair
+ * @wqe: the next wqe
+ *
+ * Returns: 1 if wqe needs to wait
+ *	    0 if wqe is ready to go
+ */
+static int rxe_wqe_is_fenced(struct rxe_qp *qp, struct rxe_send_wqe *wqe)
+{
+	/* Local invalidate fence (LIF) see IBA 10.6.5.1
+	 * Requires ALL previous operations on the send queue
+	 * are complete. Make mandatory for the rxe driver.
+	 */
+	if (wqe->wr.opcode == IB_WR_LOCAL_INV)
+		return qp->req.wqe_index != queue_get_consumer(qp->sq.queue,
+						QUEUE_TYPE_FROM_CLIENT);
+
+	/* Fence see IBA 10.8.3.3
+	 * Requires that all previous read and atomic operations
+	 * are complete.
+	 */
+	return (wqe->wr.send_flags & IB_SEND_FENCE) &&
+		atomic_read(&qp->req.rd_atomic) != qp->attr.max_rd_atomic;
+}
+
 static int next_opcode_rc(struct rxe_qp *qp, u32 opcode, int fits)
 {
 	switch (opcode) {
@@ -311,7 +329,6 @@ static int next_opcode(struct rxe_qp *qp, struct rxe_send_wqe *wqe,
 	case IB_QPT_UC:
 		return next_opcode_uc(qp, opcode, fits);
 
-	case IB_QPT_SMI:
 	case IB_QPT_UD:
 	case IB_QPT_GSI:
 		switch (opcode) {
@@ -361,38 +378,25 @@ static inline int get_mtu(struct rxe_qp *qp)
 }
 
 static struct sk_buff *init_req_packet(struct rxe_qp *qp,
+				       struct rxe_av *av,
 				       struct rxe_send_wqe *wqe,
-				       int opcode, int payload,
+				       int opcode, u32 payload,
 				       struct rxe_pkt_info *pkt)
 {
 	struct rxe_dev		*rxe = to_rdev(qp->ibqp.device);
 	struct sk_buff		*skb;
 	struct rxe_send_wr	*ibwr = &wqe->wr;
-	struct rxe_av		*av;
 	int			pad = (-payload) & 0x3;
 	int			paylen;
 	int			solicited;
-	u16			pkey;
 	u32			qp_num;
 	int			ack_req;
 
 	/* length from start of bth to end of icrc */
 	paylen = rxe_opcode[opcode].length + payload + pad + RXE_ICRC_SIZE;
-
-	/* pkt->hdr, port_num and mask are initialized in ifc layer */
-	pkt->rxe	= rxe;
-	pkt->opcode	= opcode;
-	pkt->qp		= qp;
-	pkt->psn	= qp->req.psn;
-	pkt->mask	= rxe_opcode[opcode].mask;
-	pkt->paylen	= paylen;
-	pkt->wqe	= wqe;
+	pkt->paylen = paylen;
 
 	/* init skb */
-	av = rxe_get_av(pkt);
-	if (!av)
-		return NULL;
-
 	skb = rxe_init_packet(rxe, av, paylen, pkt);
 	if (unlikely(!skb))
 		return NULL;
@@ -404,8 +408,6 @@ static struct sk_buff *init_req_packet(struct rxe_qp *qp,
 			(pkt->mask & (RXE_WRITE_MASK | RXE_IMMDT_MASK)) ==
 			(RXE_WRITE_MASK | RXE_IMMDT_MASK));
 
-	pkey = IB_DEFAULT_PKEY_FULL;
-
 	qp_num = (pkt->mask & RXE_DETH_MASK) ? ibwr->wr.ud.remote_qpn :
 					 qp->attr.dest_qp_num;
 
@@ -414,7 +416,7 @@ static struct sk_buff *init_req_packet(struct rxe_qp *qp,
 	if (ack_req)
 		qp->req.noack_pkts = 0;
 
-	bth_init(pkt, pkt->opcode, solicited, 0, pad, pkey, qp_num,
+	bth_init(pkt, pkt->opcode, solicited, 0, pad, IB_DEFAULT_PKEY_FULL, qp_num,
 		 ack_req, pkt->psn);
 
 	/* init optional headers */
@@ -432,8 +434,7 @@ static struct sk_buff *init_req_packet(struct rxe_qp *qp,
 
 	if (pkt->mask & RXE_ATMETH_MASK) {
 		atmeth_set_va(pkt, wqe->iova);
-		if (opcode == IB_OPCODE_RC_COMPARE_SWAP ||
-		    opcode == IB_OPCODE_RD_COMPARE_SWAP) {
+		if (opcode == IB_OPCODE_RC_COMPARE_SWAP) {
 			atmeth_set_swap_add(pkt, ibwr->wr.atomic.swap);
 			atmeth_set_comp(pkt, ibwr->wr.atomic.compare_add);
 		} else {
@@ -453,13 +454,13 @@ static struct sk_buff *init_req_packet(struct rxe_qp *qp,
 	return skb;
 }
 
-static int finish_packet(struct rxe_qp *qp, struct rxe_send_wqe *wqe,
-		       struct rxe_pkt_info *pkt, struct sk_buff *skb,
-		       int paylen)
+static int finish_packet(struct rxe_qp *qp, struct rxe_av *av,
+			 struct rxe_send_wqe *wqe, struct rxe_pkt_info *pkt,
+			 struct sk_buff *skb, u32 payload)
 {
 	int err;
 
-	err = rxe_prepare(pkt, skb);
+	err = rxe_prepare(av, pkt, skb);
 	if (err)
 		return err;
 
@@ -467,19 +468,19 @@ static int finish_packet(struct rxe_qp *qp, struct rxe_send_wqe *wqe,
 		if (wqe->wr.send_flags & IB_SEND_INLINE) {
 			u8 *tmp = &wqe->dma.inline_data[wqe->dma.sge_offset];
 
-			memcpy(payload_addr(pkt), tmp, paylen);
+			memcpy(payload_addr(pkt), tmp, payload);
 
-			wqe->dma.resid -= paylen;
-			wqe->dma.sge_offset += paylen;
+			wqe->dma.resid -= payload;
+			wqe->dma.sge_offset += payload;
 		} else {
 			err = copy_data(qp->pd, 0, &wqe->dma,
-					payload_addr(pkt), paylen,
+					payload_addr(pkt), payload,
 					RXE_FROM_MR_OBJ);
 			if (err)
 				return err;
 		}
 		if (bth_pad(pkt)) {
-			u8 *pad = payload_addr(pkt) + paylen;
+			u8 *pad = payload_addr(pkt) + payload;
 
 			memset(pad, 0, bth_pad(pkt));
 		}
@@ -503,7 +504,7 @@ static void update_wqe_state(struct rxe_qp *qp,
 static void update_wqe_psn(struct rxe_qp *qp,
 			   struct rxe_send_wqe *wqe,
 			   struct rxe_pkt_info *pkt,
-			   int payload)
+			   u32 payload)
 {
 	/* number of packets left to send including current one */
 	int num_pkt = (wqe->dma.resid + payload + qp->mtu - 1) / qp->mtu;
@@ -545,8 +546,7 @@ static void rollback_state(struct rxe_send_wqe *wqe,
 	qp->req.psn    = rollback_psn;
 }
 
-static void update_state(struct rxe_qp *qp, struct rxe_send_wqe *wqe,
-			 struct rxe_pkt_info *pkt, int payload)
+static void update_state(struct rxe_qp *qp, struct rxe_pkt_info *pkt)
 {
 	qp->req.opcode = pkt->opcode;
 
@@ -604,9 +604,11 @@ static int rxe_do_local_ops(struct rxe_qp *qp, struct rxe_send_wqe *wqe)
 	wqe->status = IB_WC_SUCCESS;
 	qp->req.wqe_index = queue_next_index(qp->sq.queue, qp->req.wqe_index);
 
-	if ((wqe->wr.send_flags & IB_SEND_SIGNALED) ||
-	    qp->sq_sig_type == IB_SIGNAL_ALL_WR)
-		rxe_run_task(&qp->comp.task, 1);
+	/* There is no ack coming for local work requests
+	 * which can lead to a deadlock. So go ahead and complete
+	 * it now.
+	 */
+	rxe_run_task(&qp->comp.task, 1);
 
 	return 0;
 }
@@ -614,24 +616,39 @@ static int rxe_do_local_ops(struct rxe_qp *qp, struct rxe_send_wqe *wqe)
 int rxe_requester(void *arg)
 {
 	struct rxe_qp *qp = (struct rxe_qp *)arg;
+	struct rxe_dev *rxe = to_rdev(qp->ibqp.device);
 	struct rxe_pkt_info pkt;
 	struct sk_buff *skb;
 	struct rxe_send_wqe *wqe;
 	enum rxe_hdr_mask mask;
-	int payload;
+	u32 payload;
 	int mtu;
 	int opcode;
+	int err;
 	int ret;
 	struct rxe_send_wqe rollback_wqe;
 	u32 rollback_psn;
 	struct rxe_queue *q = qp->sq.queue;
+	struct rxe_ah *ah;
+	struct rxe_av *av;
 
-	rxe_add_ref(qp);
+	if (!rxe_get(qp))
+		return -EAGAIN;
 
-next_wqe:
-	if (unlikely(!qp->valid || qp->req.state == QP_STATE_ERROR))
+	if (unlikely(!qp->valid))
 		goto exit;
 
+	if (unlikely(qp->req.state == QP_STATE_ERROR)) {
+		wqe = req_next_wqe(qp);
+		if (wqe)
+			/*
+			 * Generate an error completion for error qp state
+			 */
+			goto err;
+		else
+			goto exit;
+	}
+
 	if (unlikely(qp->req.state == QP_STATE_RESET)) {
 		qp->req.wqe_index = queue_get_consumer(q,
 						QUEUE_TYPE_FROM_CLIENT);
@@ -639,10 +656,17 @@ next_wqe:
 		qp->req.need_rd_atomic = 0;
 		qp->req.wait_psn = 0;
 		qp->req.need_retry = 0;
+		qp->req.wait_for_rnr_timer = 0;
 		goto exit;
 	}
 
-	if (unlikely(qp->req.need_retry)) {
+	/* we come here if the retransmit timer has fired
+	 * or if the rnr timer has fired. If the retransmit
+	 * timer fires while we are processing an RNR NAK wait
+	 * until the rnr timer has fired before starting the
+	 * retry flow
+	 */
+	if (unlikely(qp->req.need_retry && !qp->req.wait_for_rnr_timer)) {
 		req_retry(qp);
 		qp->req.need_retry = 0;
 	}
@@ -651,12 +675,17 @@ next_wqe:
 	if (unlikely(!wqe))
 		goto exit;
 
+	if (rxe_wqe_is_fenced(qp, wqe)) {
+		qp->req.wait_fence = 1;
+		goto exit;
+	}
+
 	if (wqe->mask & WR_LOCAL_OP_MASK) {
-		ret = rxe_do_local_ops(qp, wqe);
-		if (unlikely(ret))
+		err = rxe_do_local_ops(qp, wqe);
+		if (unlikely(err))
 			goto err;
 		else
-			goto next_wqe;
+			goto done;
 	}
 
 	if (unlikely(qp_type(qp) == IB_QPT_RC &&
@@ -676,7 +705,7 @@ next_wqe:
 	opcode = next_opcode(qp, wqe, wqe->wr.opcode);
 	if (unlikely(opcode < 0)) {
 		wqe->status = IB_WC_LOC_QP_OP_ERR;
-		goto exit;
+		goto err;
 	}
 
 	mask = rxe_opcode[opcode].mask;
@@ -704,31 +733,51 @@ next_wqe:
 						       qp->req.wqe_index);
 			wqe->state = wqe_state_done;
 			wqe->status = IB_WC_SUCCESS;
-			__rxe_do_task(&qp->comp.task);
-			rxe_drop_ref(qp);
-			return 0;
+			rxe_run_task(&qp->comp.task, 0);
+			goto done;
 		}
 		payload = mtu;
 	}
 
-	skb = init_req_packet(qp, wqe, opcode, payload, &pkt);
+	pkt.rxe = rxe;
+	pkt.opcode = opcode;
+	pkt.qp = qp;
+	pkt.psn = qp->req.psn;
+	pkt.mask = rxe_opcode[opcode].mask;
+	pkt.wqe = wqe;
+
+	av = rxe_get_av(&pkt, &ah);
+	if (unlikely(!av)) {
+		pr_err("qp#%d Failed no address vector\n", qp_num(qp));
+		wqe->status = IB_WC_LOC_QP_OP_ERR;
+		goto err;
+	}
+
+	skb = init_req_packet(qp, av, wqe, opcode, payload, &pkt);
 	if (unlikely(!skb)) {
 		pr_err("qp#%d Failed allocating skb\n", qp_num(qp));
 		wqe->status = IB_WC_LOC_QP_OP_ERR;
+		if (ah)
+			rxe_put(ah);
 		goto err;
 	}
 
-	ret = finish_packet(qp, wqe, &pkt, skb, payload);
-	if (unlikely(ret)) {
+	err = finish_packet(qp, av, wqe, &pkt, skb, payload);
+	if (unlikely(err)) {
 		pr_debug("qp#%d Error during finish packet\n", qp_num(qp));
-		if (ret == -EFAULT)
+		if (err == -EFAULT)
 			wqe->status = IB_WC_LOC_PROT_ERR;
 		else
 			wqe->status = IB_WC_LOC_QP_OP_ERR;
 		kfree_skb(skb);
+		if (ah)
+			rxe_put(ah);
 		goto err;
 	}
 
+	if (ah)
+		rxe_put(ah);
+
 	/*
 	 * To prevent a race on wqe access between requester and completer,
 	 * wqe members state and psn need to be set before calling
@@ -738,13 +787,14 @@ next_wqe:
 	save_state(wqe, qp, &rollback_wqe, &rollback_psn);
 	update_wqe_state(qp, wqe, &pkt);
 	update_wqe_psn(qp, wqe, &pkt, payload);
-	ret = rxe_xmit_packet(qp, &pkt, skb);
-	if (ret) {
+
+	err = rxe_xmit_packet(qp, &pkt, skb);
+	if (err) {
 		qp->need_req_skb = 1;
 
 		rollback_state(wqe, qp, &rollback_wqe, rollback_psn);
 
-		if (ret == -EAGAIN) {
+		if (err == -EAGAIN) {
 			rxe_run_task(&qp->req.task, 1);
 			goto exit;
 		}
@@ -753,15 +803,25 @@ next_wqe:
 		goto err;
 	}
 
-	update_state(qp, wqe, &pkt, payload);
-
-	goto next_wqe;
+	update_state(qp, &pkt);
 
+	/* A non-zero return value will cause rxe_do_task to
+	 * exit its loop and end the tasklet. A zero return
+	 * will continue looping and return to rxe_requester
+	 */
+done:
+	ret = 0;
+	goto out;
 err:
+	/* update wqe_index for each wqe completion */
+	qp->req.wqe_index = queue_next_index(qp->sq.queue, qp->req.wqe_index);
 	wqe->state = wqe_state_error;
-	__rxe_do_task(&qp->comp.task);
-
+	qp->req.state = QP_STATE_ERROR;
+	rxe_run_task(&qp->comp.task, 0);
 exit:
-	rxe_drop_ref(qp);
-	return -EAGAIN;
+	ret = -EAGAIN;
+out:
+	rxe_put(qp);
+
+	return ret;
 }