1 files changed, 279 insertions, 50 deletions

diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c
index 693081e813ec..7a60c7709da0 100644
--- a/drivers/infiniband/sw/rxe/rxe_resp.c
+++ b/drivers/infiniband/sw/rxe/rxe_resp.c
@@ -22,6 +22,8 @@ enum resp_states {
 	RESPST_EXECUTE,
 	RESPST_READ_REPLY,
 	RESPST_ATOMIC_REPLY,
+	RESPST_ATOMIC_WRITE_REPLY,
+	RESPST_PROCESS_FLUSH,
 	RESPST_COMPLETE,
 	RESPST_ACKNOWLEDGE,
 	RESPST_CLEANUP,
@@ -57,6 +59,8 @@ static char *resp_state_name[] = {
 	[RESPST_EXECUTE]			= "EXECUTE",
 	[RESPST_READ_REPLY]			= "READ_REPLY",
 	[RESPST_ATOMIC_REPLY]			= "ATOMIC_REPLY",
+	[RESPST_ATOMIC_WRITE_REPLY]		= "ATOMIC_WRITE_REPLY",
+	[RESPST_PROCESS_FLUSH]			= "PROCESS_FLUSH",
 	[RESPST_COMPLETE]			= "COMPLETE",
 	[RESPST_ACKNOWLEDGE]			= "ACKNOWLEDGE",
 	[RESPST_CLEANUP]			= "CLEANUP",
@@ -91,7 +95,10 @@ void rxe_resp_queue_pkt(struct rxe_qp *qp, struct sk_buff *skb)
 	must_sched = (pkt->opcode == IB_OPCODE_RC_RDMA_READ_REQUEST) ||
 			(skb_queue_len(&qp->req_pkts) > 1);
 
-	rxe_run_task(&qp->resp.task, must_sched);
+	if (must_sched)
+		rxe_sched_task(&qp->resp.task);
+	else
+		rxe_run_task(&qp->resp.task);
 }
 
 static inline enum resp_states get_req(struct rxe_qp *qp,
@@ -253,19 +260,37 @@ static enum resp_states check_op_seq(struct rxe_qp *qp,
 	}
 }
 
+static bool check_qp_attr_access(struct rxe_qp *qp,
+				 struct rxe_pkt_info *pkt)
+{
+	if (((pkt->mask & RXE_READ_MASK) &&
+	     !(qp->attr.qp_access_flags & IB_ACCESS_REMOTE_READ)) ||
+	    ((pkt->mask & (RXE_WRITE_MASK | RXE_ATOMIC_WRITE_MASK)) &&
+	     !(qp->attr.qp_access_flags & IB_ACCESS_REMOTE_WRITE)) ||
+	    ((pkt->mask & RXE_ATOMIC_MASK) &&
+	     !(qp->attr.qp_access_flags & IB_ACCESS_REMOTE_ATOMIC)))
+		return false;
+
+	if (pkt->mask & RXE_FLUSH_MASK) {
+		u32 flush_type = feth_plt(pkt);
+
+		if ((flush_type & IB_FLUSH_GLOBAL &&
+		     !(qp->attr.qp_access_flags & IB_ACCESS_FLUSH_GLOBAL)) ||
+		    (flush_type & IB_FLUSH_PERSISTENT &&
+		     !(qp->attr.qp_access_flags & IB_ACCESS_FLUSH_PERSISTENT)))
+			return false;
+	}
+
+	return true;
+}
+
 static enum resp_states check_op_valid(struct rxe_qp *qp,
 				       struct rxe_pkt_info *pkt)
 {
 	switch (qp_type(qp)) {
 	case IB_QPT_RC:
-		if (((pkt->mask & RXE_READ_MASK) &&
-		     !(qp->attr.qp_access_flags & IB_ACCESS_REMOTE_READ)) ||
-		    ((pkt->mask & RXE_WRITE_MASK) &&
-		     !(qp->attr.qp_access_flags & IB_ACCESS_REMOTE_WRITE)) ||
-		    ((pkt->mask & RXE_ATOMIC_MASK) &&
-		     !(qp->attr.qp_access_flags & IB_ACCESS_REMOTE_ATOMIC))) {
+		if (!check_qp_attr_access(qp, pkt))
 			return RESPST_ERR_UNSUPPORTED_OPCODE;
-		}
 
 		break;
 
@@ -314,7 +339,7 @@ static enum resp_states get_srq_wqe(struct rxe_qp *qp)
 	/* don't trust user space data */
 	if (unlikely(wqe->dma.num_sge > srq->rq.max_sge)) {
 		spin_unlock_irqrestore(&srq->rq.consumer_lock, flags);
-		pr_warn("%s: invalid num_sge in SRQ entry\n", __func__);
+		rxe_dbg_qp(qp, "invalid num_sge in SRQ entry\n");
 		return RESPST_ERR_MALFORMED_WQE;
 	}
 	size = sizeof(*wqe) + wqe->dma.num_sge*sizeof(struct rxe_sge);
@@ -364,7 +389,7 @@ static enum resp_states check_resource(struct rxe_qp *qp,
 		}
 	}
 
-	if (pkt->mask & RXE_READ_OR_ATOMIC_MASK) {
+	if (pkt->mask & (RXE_READ_OR_ATOMIC_MASK | RXE_ATOMIC_WRITE_MASK)) {
 		/* it is the requesters job to not send
 		 * too many read/atomic ops, we just
 		 * recycle the responder resource queue
@@ -387,19 +412,66 @@ static enum resp_states check_resource(struct rxe_qp *qp,
 	return RESPST_CHK_LENGTH;
 }
 
-static enum resp_states check_length(struct rxe_qp *qp,
-				     struct rxe_pkt_info *pkt)
+static enum resp_states rxe_resp_check_length(struct rxe_qp *qp,
+					      struct rxe_pkt_info *pkt)
 {
-	switch (qp_type(qp)) {
-	case IB_QPT_RC:
-		return RESPST_CHK_RKEY;
-
-	case IB_QPT_UC:
-		return RESPST_CHK_RKEY;
+	/*
+	 * See IBA C9-92
+	 * For UD QPs we only check if the packet will fit in the
+	 * receive buffer later. For rmda operations additional
+	 * length checks are performed in check_rkey.
+	 */
+	if (pkt->mask & RXE_PAYLOAD_MASK && ((qp_type(qp) == IB_QPT_RC) ||
+					     (qp_type(qp) == IB_QPT_UC))) {
+		unsigned int mtu = qp->mtu;
+		unsigned int payload = payload_size(pkt);
+
+		if ((pkt->mask & RXE_START_MASK) &&
+		    (pkt->mask & RXE_END_MASK)) {
+			if (unlikely(payload > mtu)) {
+				rxe_dbg_qp(qp, "only packet too long");
+				return RESPST_ERR_LENGTH;
+			}
+		} else if ((pkt->mask & RXE_START_MASK) ||
+			   (pkt->mask & RXE_MIDDLE_MASK)) {
+			if (unlikely(payload != mtu)) {
+				rxe_dbg_qp(qp, "first or middle packet not mtu");
+				return RESPST_ERR_LENGTH;
+			}
+		} else if (pkt->mask & RXE_END_MASK) {
+			if (unlikely((payload == 0) || (payload > mtu))) {
+				rxe_dbg_qp(qp, "last packet zero or too long");
+				return RESPST_ERR_LENGTH;
+			}
+		}
+	}
 
-	default:
-		return RESPST_CHK_RKEY;
+	/* See IBA C9-94 */
+	if (pkt->mask & RXE_RETH_MASK) {
+		if (reth_len(pkt) > (1U << 31)) {
+			rxe_dbg_qp(qp, "dma length too long");
+			return RESPST_ERR_LENGTH;
+		}
 	}
+
+	return RESPST_CHK_RKEY;
+}
+
+static void qp_resp_from_reth(struct rxe_qp *qp, struct rxe_pkt_info *pkt)
+{
+	qp->resp.va = reth_va(pkt);
+	qp->resp.offset = 0;
+	qp->resp.rkey = reth_rkey(pkt);
+	qp->resp.resid = reth_len(pkt);
+	qp->resp.length = reth_len(pkt);
+}
+
+static void qp_resp_from_atmeth(struct rxe_qp *qp, struct rxe_pkt_info *pkt)
+{
+	qp->resp.va = atmeth_va(pkt);
+	qp->resp.offset = 0;
+	qp->resp.rkey = atmeth_rkey(pkt);
+	qp->resp.resid = sizeof(u64);
 }
 
 static enum resp_states check_rkey(struct rxe_qp *qp,
@@ -413,29 +485,32 @@ static enum resp_states check_rkey(struct rxe_qp *qp,
 	u32 pktlen;
 	int mtu = qp->mtu;
 	enum resp_states state;
-	int access;
-
-	if (pkt->mask & RXE_READ_OR_WRITE_MASK) {
-		if (pkt->mask & RXE_RETH_MASK) {
-			qp->resp.va = reth_va(pkt);
-			qp->resp.offset = 0;
-			qp->resp.rkey = reth_rkey(pkt);
-			qp->resp.resid = reth_len(pkt);
-			qp->resp.length = reth_len(pkt);
-		}
+	int access = 0;
+
+	if (pkt->mask & (RXE_READ_OR_WRITE_MASK | RXE_ATOMIC_WRITE_MASK)) {
+		if (pkt->mask & RXE_RETH_MASK)
+			qp_resp_from_reth(qp, pkt);
+
 		access = (pkt->mask & RXE_READ_MASK) ? IB_ACCESS_REMOTE_READ
 						     : IB_ACCESS_REMOTE_WRITE;
+	} else if (pkt->mask & RXE_FLUSH_MASK) {
+		u32 flush_type = feth_plt(pkt);
+
+		if (pkt->mask & RXE_RETH_MASK)
+			qp_resp_from_reth(qp, pkt);
+
+		if (flush_type & IB_FLUSH_GLOBAL)
+			access |= IB_ACCESS_FLUSH_GLOBAL;
+		if (flush_type & IB_FLUSH_PERSISTENT)
+			access |= IB_ACCESS_FLUSH_PERSISTENT;
 	} else if (pkt->mask & RXE_ATOMIC_MASK) {
-		qp->resp.va = atmeth_va(pkt);
-		qp->resp.offset = 0;
-		qp->resp.rkey = atmeth_rkey(pkt);
-		qp->resp.resid = sizeof(u64);
+		qp_resp_from_atmeth(qp, pkt);
 		access = IB_ACCESS_REMOTE_ATOMIC;
 	} else {
 		return RESPST_EXECUTE;
 	}
 
-	/* A zero-byte op is not required to set an addr or rkey. */
+	/* A zero-byte op is not required to set an addr or rkey. See C9-88 */
 	if ((pkt->mask & RXE_READ_OR_WRITE_MASK) &&
 	    (pkt->mask & RXE_RETH_MASK) &&
 	    reth_len(pkt) == 0) {
@@ -450,15 +525,14 @@ static enum resp_states check_rkey(struct rxe_qp *qp,
 	if (rkey_is_mw(rkey)) {
 		mw = rxe_lookup_mw(qp, access, rkey);
 		if (!mw) {
-			pr_debug("%s: no MW matches rkey %#x\n",
-					__func__, rkey);
+			rxe_dbg_qp(qp, "no MW matches rkey %#x\n", rkey);
 			state = RESPST_ERR_RKEY_VIOLATION;
 			goto err;
 		}
 
 		mr = mw->mr;
 		if (!mr) {
-			pr_err("%s: MW doesn't have an MR\n", __func__);
+			rxe_dbg_qp(qp, "MW doesn't have an MR\n");
 			state = RESPST_ERR_RKEY_VIOLATION;
 			goto err;
 		}
@@ -471,19 +545,27 @@ static enum resp_states check_rkey(struct rxe_qp *qp,
 	} else {
 		mr = lookup_mr(qp->pd, access, rkey, RXE_LOOKUP_REMOTE);
 		if (!mr) {
-			pr_debug("%s: no MR matches rkey %#x\n",
-					__func__, rkey);
+			rxe_dbg_qp(qp, "no MR matches rkey %#x\n", rkey);
 			state = RESPST_ERR_RKEY_VIOLATION;
 			goto err;
 		}
 	}
 
+	if (pkt->mask & RXE_FLUSH_MASK) {
+		/* FLUSH MR may not set va or resid
+		 * no need to check range since we will flush whole mr
+		 */
+		if (feth_sel(pkt) == IB_FLUSH_MR)
+			goto skip_check_range;
+	}
+
 	if (mr_check_range(mr, va + qp->resp.offset, resid)) {
 		state = RESPST_ERR_RKEY_VIOLATION;
 		goto err;
 	}
 
-	if (pkt->mask & RXE_WRITE_MASK)	 {
+skip_check_range:
+	if (pkt->mask & (RXE_WRITE_MASK | RXE_ATOMIC_WRITE_MASK)) {
 		if (resid > mtu) {
 			if (pktlen != mtu || bth_pad(pkt)) {
 				state = RESPST_ERR_LENGTH;
@@ -583,15 +665,66 @@ static struct resp_res *rxe_prepare_res(struct rxe_qp *qp,
 		res->state = rdatm_res_state_new;
 		break;
 	case RXE_ATOMIC_MASK:
+	case RXE_ATOMIC_WRITE_MASK:
 		res->first_psn = pkt->psn;
 		res->last_psn = pkt->psn;
 		res->cur_psn = pkt->psn;
 		break;
+	case RXE_FLUSH_MASK:
+		res->flush.va = qp->resp.va + qp->resp.offset;
+		res->flush.length = qp->resp.length;
+		res->flush.type = feth_plt(pkt);
+		res->flush.level = feth_sel(pkt);
 	}
 
 	return res;
 }
 
+static enum resp_states process_flush(struct rxe_qp *qp,
+				       struct rxe_pkt_info *pkt)
+{
+	u64 length, start;
+	struct rxe_mr *mr = qp->resp.mr;
+	struct resp_res *res = qp->resp.res;
+
+	/* oA19-14, oA19-15 */
+	if (res && res->replay)
+		return RESPST_ACKNOWLEDGE;
+	else if (!res) {
+		res = rxe_prepare_res(qp, pkt, RXE_FLUSH_MASK);
+		qp->resp.res = res;
+	}
+
+	if (res->flush.level == IB_FLUSH_RANGE) {
+		start = res->flush.va;
+		length = res->flush.length;
+	} else { /* level == IB_FLUSH_MR */
+		start = mr->ibmr.iova;
+		length = mr->ibmr.length;
+	}
+
+	if (res->flush.type & IB_FLUSH_PERSISTENT) {
+		if (rxe_flush_pmem_iova(mr, start, length))
+			return RESPST_ERR_RKEY_VIOLATION;
+		/* Make data persistent. */
+		wmb();
+	} else if (res->flush.type & IB_FLUSH_GLOBAL) {
+		/* Make data global visibility. */
+		wmb();
+	}
+
+	qp->resp.msn++;
+
+	/* next expected psn, read handles this separately */
+	qp->resp.psn = (pkt->psn + 1) & BTH_PSN_MASK;
+	qp->resp.ack_psn = qp->resp.psn;
+
+	qp->resp.opcode = pkt->opcode;
+	qp->resp.status = IB_WC_SUCCESS;
+
+	return RESPST_ACKNOWLEDGE;
+}
+
 /* Guarantee atomicity of atomic operations at the machine level. */
 static DEFINE_SPINLOCK(atomic_ops_lock);
 
@@ -652,6 +785,55 @@ out:
 	return ret;
 }
 
+static enum resp_states atomic_write_reply(struct rxe_qp *qp,
+						struct rxe_pkt_info *pkt)
+{
+	u64 src, *dst;
+	struct resp_res *res = qp->resp.res;
+	struct rxe_mr *mr = qp->resp.mr;
+	int payload = payload_size(pkt);
+
+	if (!res) {
+		res = rxe_prepare_res(qp, pkt, RXE_ATOMIC_WRITE_MASK);
+		qp->resp.res = res;
+	}
+
+	if (!res->replay) {
+#ifdef CONFIG_64BIT
+		if (mr->state != RXE_MR_STATE_VALID)
+			return RESPST_ERR_RKEY_VIOLATION;
+
+		memcpy(&src, payload_addr(pkt), payload);
+
+		dst = iova_to_vaddr(mr, qp->resp.va + qp->resp.offset, payload);
+		/* check vaddr is 8 bytes aligned. */
+		if (!dst || (uintptr_t)dst & 7)
+			return RESPST_ERR_MISALIGNED_ATOMIC;
+
+		/* Do atomic write after all prior operations have completed */
+		smp_store_release(dst, src);
+
+		/* decrease resp.resid to zero */
+		qp->resp.resid -= sizeof(payload);
+
+		qp->resp.msn++;
+
+		/* next expected psn, read handles this separately */
+		qp->resp.psn = (pkt->psn + 1) & BTH_PSN_MASK;
+		qp->resp.ack_psn = qp->resp.psn;
+
+		qp->resp.opcode = pkt->opcode;
+		qp->resp.status = IB_WC_SUCCESS;
+
+		return RESPST_ACKNOWLEDGE;
+#else
+		return RESPST_ERR_UNSUPPORTED_OPCODE;
+#endif /* CONFIG_64BIT */
+	}
+
+	return RESPST_ACKNOWLEDGE;
+}
+
 static struct sk_buff *prepare_ack_packet(struct rxe_qp *qp,
 					  struct rxe_pkt_info *ack,
 					  int opcode,
@@ -807,14 +989,19 @@ static enum resp_states read_reply(struct rxe_qp *qp,
 	skb = prepare_ack_packet(qp, &ack_pkt, opcode, payload,
 				 res->cur_psn, AETH_ACK_UNLIMITED);
 	if (!skb) {
-		rxe_put(mr);
+		if (mr)
+			rxe_put(mr);
 		return RESPST_ERR_RNR;
 	}
 
-	rxe_mr_copy(mr, res->read.va, payload_addr(&ack_pkt),
-		    payload, RXE_FROM_MR_OBJ);
+	err = rxe_mr_copy(mr, res->read.va, payload_addr(&ack_pkt),
+			  payload, RXE_FROM_MR_OBJ);
 	if (mr)
 		rxe_put(mr);
+	if (err) {
+		kfree_skb(skb);
+		return RESPST_ERR_RKEY_VIOLATION;
+	}
 
 	if (bth_pad(&ack_pkt)) {
 		u8 *pad = payload_addr(&ack_pkt) + payload;
@@ -890,6 +1077,10 @@ static enum resp_states execute(struct rxe_qp *qp, struct rxe_pkt_info *pkt)
 		return RESPST_READ_REPLY;
 	} else if (pkt->mask & RXE_ATOMIC_MASK) {
 		return RESPST_ATOMIC_REPLY;
+	} else if (pkt->mask & RXE_ATOMIC_WRITE_MASK) {
+		return RESPST_ATOMIC_WRITE_REPLY;
+	} else if (pkt->mask & RXE_FLUSH_MASK) {
+		return RESPST_PROCESS_FLUSH;
 	} else {
 		/* Unreachable */
 		WARN_ON_ONCE(1);
@@ -1040,7 +1231,7 @@ static int send_common_ack(struct rxe_qp *qp, u8 syndrome, u32 psn,
 
 	err = rxe_xmit_packet(qp, &ack_pkt, skb);
 	if (err)
-		pr_err_ratelimited("Failed sending %s\n", msg);
+		rxe_dbg_qp(qp, "Failed sending %s\n", msg);
 
 	return err;
 }
@@ -1063,6 +1254,19 @@ static int send_atomic_ack(struct rxe_qp *qp, u8 syndrome, u32 psn)
 	return ret;
 }
 
+static int send_read_response_ack(struct rxe_qp *qp, u8 syndrome, u32 psn)
+{
+	int ret = send_common_ack(qp, syndrome, psn,
+			IB_OPCODE_RC_RDMA_READ_RESPONSE_ONLY,
+			"RDMA READ response of length zero ACK");
+
+	/* have to clear this since it is used to trigger
+	 * long read replies
+	 */
+	qp->resp.res = NULL;
+	return ret;
+}
+
 static enum resp_states acknowledge(struct rxe_qp *qp,
 				    struct rxe_pkt_info *pkt)
 {
@@ -1073,6 +1277,8 @@ static enum resp_states acknowledge(struct rxe_qp *qp,
 		send_ack(qp, qp->resp.aeth_syndrome, pkt->psn);
 	else if (pkt->mask & RXE_ATOMIC_MASK)
 		send_atomic_ack(qp, AETH_ACK_UNLIMITED, pkt->psn);
+	else if (pkt->mask & (RXE_FLUSH_MASK | RXE_ATOMIC_WRITE_MASK))
+		send_read_response_ack(qp, AETH_ACK_UNLIMITED, pkt->psn);
 	else if (bth_ack(pkt))
 		send_ack(qp, AETH_ACK_UNLIMITED, pkt->psn);
 
@@ -1129,6 +1335,22 @@ static enum resp_states duplicate_request(struct rxe_qp *qp,
 		/* SEND. Ack again and cleanup. C9-105. */
 		send_ack(qp, AETH_ACK_UNLIMITED, prev_psn);
 		return RESPST_CLEANUP;
+	} else if (pkt->mask & RXE_FLUSH_MASK) {
+		struct resp_res *res;
+
+		/* Find the operation in our list of responder resources. */
+		res = find_resource(qp, pkt->psn);
+		if (res) {
+			res->replay = 1;
+			res->cur_psn = pkt->psn;
+			qp->resp.res = res;
+			rc = RESPST_PROCESS_FLUSH;
+			goto out;
+		}
+
+		/* Resource not found. Class D error. Drop the request. */
+		rc = RESPST_CLEANUP;
+		goto out;
 	} else if (pkt->mask & RXE_READ_MASK) {
 		struct resp_res *res;
 
@@ -1184,7 +1406,9 @@ static enum resp_states duplicate_request(struct rxe_qp *qp,
 			res->replay = 1;
 			res->cur_psn = pkt->psn;
 			qp->resp.res = res;
-			rc = RESPST_ATOMIC_REPLY;
+			rc = pkt->mask & RXE_ATOMIC_MASK ?
+					RESPST_ATOMIC_REPLY :
+					RESPST_ATOMIC_WRITE_REPLY;
 			goto out;
 		}
 
@@ -1286,8 +1510,7 @@ int rxe_responder(void *arg)
 	}
 
 	while (1) {
-		pr_debug("qp#%d state = %s\n", qp_num(qp),
-			 resp_state_name[state]);
+		rxe_dbg_qp(qp, "state = %s\n", resp_state_name[state]);
 		switch (state) {
 		case RESPST_GET_REQ:
 			state = get_req(qp, &pkt);
@@ -1305,7 +1528,7 @@ int rxe_responder(void *arg)
 			state = check_resource(qp, pkt);
 			break;
 		case RESPST_CHK_LENGTH:
-			state = check_length(qp, pkt);
+			state = rxe_resp_check_length(qp, pkt);
 			break;
 		case RESPST_CHK_RKEY:
 			state = check_rkey(qp, pkt);
@@ -1322,6 +1545,12 @@ int rxe_responder(void *arg)
 		case RESPST_ATOMIC_REPLY:
 			state = atomic_reply(qp, pkt);
 			break;
+		case RESPST_ATOMIC_WRITE_REPLY:
+			state = atomic_write_reply(qp, pkt);
+			break;
+		case RESPST_PROCESS_FLUSH:
+			state = process_flush(qp, pkt);
+			break;
 		case RESPST_ACKNOWLEDGE:
 			state = acknowledge(qp, pkt);
 			break;
@@ -1444,7 +1673,7 @@ int rxe_responder(void *arg)
 
 		case RESPST_ERROR:
 			qp->resp.goto_error = 0;
-			pr_debug("qp#%d moved to error state\n", qp_num(qp));
+			rxe_dbg_qp(qp, "moved to error state\n");
 			rxe_qp_error(qp);
 			goto exit;