rdma_rxe: Add memory access through MWs

Implement memory access through MWs.
Add rules checks from IBA.

Signed-off-by: Bob Pearson <rpearson@hpe.com>

drivers/infiniband/sw/rxe/rxe_loc.h

@@ -100,25 +100,28 @@ enum lookup_type {
 	lookup_remote,
 };
 
-struct rxe_mr *lookup_mr(struct rxe_pd *pd, int access, u32 key,
-			   enum lookup_type type);
+int advance_dma_data(struct rxe_dma_info *dma, unsigned int length);
 
-int mr_check_range(struct rxe_mr *mr, u64 iova, size_t length);
+int rxe_mr_check_access(struct rxe_qp *qp, struct rxe_mr *mr,
+			int access, u64 va, u32 resid);
 
 void rxe_mr_cleanup(struct rxe_pool_entry *arg);
 
-int advance_dma_data(struct rxe_dma_info *dma, unsigned int length);
-
 /* rxe_mw.c */
 struct ib_mw *rxe_alloc_mw(struct ib_pd *ibpd, enum ib_mw_type type,
 			   struct ib_udata *udata);
 
 int rxe_dealloc_mw(struct ib_mw *ibmw);
 
-void rxe_mw_cleanup(struct rxe_pool_entry *arg);
-
 int rxe_bind_mw(struct rxe_qp *qp, struct rxe_send_wqe *wqe);
 
+int rxe_invalidate_mw(struct rxe_qp *qp, struct rxe_mw *mw);
+
+int rxe_mw_check_access(struct rxe_qp *qp, struct rxe_mw *mw,
+			int access, u64 va, u32 resid);
+
+void rxe_mw_cleanup(struct rxe_pool_entry *arg);
+
 /* rxe_net.c */
 void rxe_loopback(struct sk_buff *skb);
 int rxe_send(struct rxe_pkt_info *pkt, struct sk_buff *skb);

drivers/infiniband/sw/rxe/rxe_mr.c

@@ -21,7 +21,7 @@ static void rxe_set_mr_lkey(struct rxe_mr *mr)
 	goto again;
 }
 
-int mr_check_range(struct rxe_mr *mr, u64 iova, size_t length)
+static int mr_check_range(struct rxe_mr *mr, u64 iova, size_t length)
 {
 	switch (mr->type) {
 	case RXE_MR_TYPE_DMA:
@@ -380,6 +380,25 @@ int rxe_mr_copy(struct rxe_mr *mr, u64 iova, void *addr, int length,
 	return err;
 }
 
+static struct rxe_mr *lookup_mr(struct rxe_pd *pd, int access, u32 lkey)
+{
+	struct rxe_mr *mr;
+	struct rxe_dev *rxe = to_rdev(pd->ibpd.device);
+
+	mr = rxe_pool_get_key(&rxe->mr_pool, &lkey);
+	if (!mr)
+		return NULL;
+
+	if (unlikely((mr->ibmr.lkey != lkey) || (mr->pd != pd) ||
+		     (access && !(access & mr->access)) ||
+		     (mr->state != RXE_MEM_STATE_VALID))) {
+		rxe_drop_ref(mr);
+		return NULL;
+	}
+
+	return mr;
+}
+
 /* copy data in or out of a wqe, i.e. sg list
  * under the control of a dma descriptor
  */
@@ -409,7 +428,7 @@ int copy_data(
 	}
 
 	if (sge->length && (offset < sge->length)) {
-		mr = lookup_mr(pd, access, sge->lkey, lookup_local);
+		mr = lookup_mr(pd, access, sge->lkey);
 		if (!mr) {
 			err = -EINVAL;
 			goto err1;
@@ -434,8 +453,7 @@ int copy_data(
 			}
 
 			if (sge->length) {
-				mr = lookup_mr(pd, access, sge->lkey,
-						 lookup_local);
+				mr = lookup_mr(pd, access, sge->lkey);
 				if (!mr) {
 					err = -EINVAL;
 					goto err1;
@@ -510,32 +528,38 @@ int advance_dma_data(struct rxe_dma_info *dma, unsigned int length)
 	return 0;
 }
 
-/* (1) find the mr corresponding to lkey/rkey
- *     depending on lookup_type
- * (2) verify that the (qp) pd matches the mr pd
- * (3) verify that the mr can support the requested access
- * (4) verify that mr state is valid
- */
-struct rxe_mr *lookup_mr(struct rxe_pd *pd, int access, u32 key,
-			   enum lookup_type type)
+int rxe_invalidate_mr(struct rxe_qp *qp, struct rxe_mr *mr)
 {
-	struct rxe_mr *mr;
-	struct rxe_dev *rxe = to_rdev(pd->ibpd.device);
+	mr->state = RXE_MEM_STATE_FREE;
+	return 0;
+}
 
-	mr = rxe_pool_get_key(&rxe->mr_pool, &key);
-	if (!mr)
-		return NULL;
+int rxe_mr_check_access(struct rxe_qp *qp, struct rxe_mr *mr,
+			int access, u64 va, u32 resid)
+{
+	int ret;
+	struct rxe_pd *pd = to_rpd(mr->ibmr.pd);
 
-	if (unlikely((type == lookup_local && mr->lkey != key) ||
-		     (type == lookup_remote && mr->rkey != key) ||
-		     mr->pd != pd ||
-		     (access && !(access & mr->access)) ||
-		     mr->state != RXE_MEM_STATE_VALID)) {
-		rxe_drop_ref(mr);
-		mr = NULL;
+	if (unlikely(mr->state != RXE_MEM_STATE_VALID)) {
+		pr_err("attempt to access a MR that is not in the valid state\n");
+		return -EINVAL;
 	}
 
-	return mr;
+	/* C10-56 */
+	if (unlikely(pd != qp->pd)) {
+		pr_err("attempt to access a MR with a different PD than the QP\n");
+		return -EINVAL;
+	}
+
+	/* C10-57 */
+	if (unlikely(access && !(access & mr->access))) {
+		pr_err("attempt to access a MR without required access rights\n");
+		return -EINVAL;
+	}
+
+	ret = mr_check_range(mr, va, resid);
+
+	return ret;
 }
 
 void rxe_mr_cleanup(struct rxe_pool_entry *arg)

drivers/infiniband/sw/rxe/rxe_mw.c

@@ -318,11 +318,6 @@ int rxe_bind_mw(struct rxe_qp *qp, struct rxe_send_wqe *wqe)
 
 static int check_invalidate_mw(struct rxe_qp *qp, struct rxe_mw *mw)
 {
-	if (unlikely(mw->state != RXE_MEM_STATE_VALID)) {
-		pr_err_once("attempt to invalidate a MW that is not valid\n");
-		return -EINVAL;
-	}
-
 	/* o10-37.2.26 */
 	if (unlikely(mw->ibmw.type == IB_MW_TYPE_1)) {
 		pr_err_once("attempt to invalidate a type 1 MW\n");
@@ -336,9 +331,11 @@ static void do_invalidate_mw(struct rxe_mw *mw)
 {
 	mw->qp = NULL;
 
-	rxe_drop_ref(mw->mr);
-	atomic_dec(&mw->mr->num_mw);
-	mw->mr = NULL;
+	if (mw->mr) {
+		atomic_dec(&mw->mr->num_mw);
+		mw->mr = NULL;
+		rxe_drop_ref(mw->mr);
+	}
 
 	mw->access = 0;
 	mw->addr = 0;
@@ -364,6 +361,50 @@ int rxe_invalidate_mw(struct rxe_qp *qp, struct rxe_mw *mw)
 	return ret;
 }
 
+int rxe_mw_check_access(struct rxe_qp *qp, struct rxe_mw *mw,
+			int access, u64 va, u32 resid)
+{
+	struct rxe_pd *pd = to_rpd(mw->ibmw.pd);
+
+	if (unlikely(mw->state != RXE_MEM_STATE_VALID)) {
+		pr_err_once("attempt to access a MW that is not valid\n");
+		return -EINVAL;
+	}
+
+	/* C10-76.2.1 */
+	if (unlikely((mw->ibmw.type == IB_MW_TYPE_1) && (pd != qp->pd))) {
+		pr_err_once("attempt to access a type 1 MW with a different PD than the QP\n");
+		return -EINVAL;
+	}
+
+	/* o10-37.2.43 */
+	if (unlikely((mw->ibmw.type == IB_MW_TYPE_2) && (mw->qp != qp))) {
+		pr_err_once("attempt to access a type 2 MW that is associated with a different QP\n");
+		return -EINVAL;
+	}
+
+	/* C10-77 */
+	if (unlikely(access && !(access & mw->access))) {
+		pr_err_once("attempt to access a MW without sufficient access\n");
+		return -EINVAL;
+	}
+
+	if (mw->access & IB_ZERO_BASED) {
+		if (unlikely((va + resid) > mw->length)) {
+			pr_err_once("attempt to access a ZB MW out of bounds\n");
+			return -EINVAL;
+		}
+	} else {
+		if (unlikely((va < mw->addr) ||
+			((va + resid) > (mw->addr + mw->length)))) {
+			pr_err_once("attempt to access a VA MW out of bounds\n");
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
 void rxe_mw_cleanup(struct rxe_pool_entry *arg)
 {
 	struct rxe_mw *mw = container_of(arg, typeof(*mw), pelem);

drivers/infiniband/sw/rxe/rxe_req.c

@@ -604,7 +604,6 @@ int rxe_requester(void *arg)
 			if (!mr) {
 				pr_err("No mr for key %#x\n",
 				       wqe->wr.ex.invalidate_rkey);
-				wqe->state = wqe_state_error;
 				wqe->status = IB_WC_MW_BIND_ERR;
 				goto err;
 			}
@@ -626,7 +625,6 @@ int rxe_requester(void *arg)
 		case IB_WR_BIND_MW:
 			ret = rxe_bind_mw(qp, wqe);
 			if (ret) {
-				wqe->state = wqe_state_done;
 				wqe->status = IB_WC_MW_BIND_ERR;
 				goto err;
 			}
@@ -636,6 +634,7 @@ int rxe_requester(void *arg)
 		default:
 			pr_err_once("unexpected LOCAL WR opcode = %d\n",
 					wqe->wr.opcode);
+			wqe->status = IB_WC_LOC_QP_OP_ERR;
 			goto err;
 		}
 
@@ -679,13 +678,7 @@ int rxe_requester(void *arg)
 	payload = (mask & RXE_WRITE_OR_SEND) ? wqe->dma.resid : 0;
 	if (payload > mtu) {
 		if (qp_type(qp) == IB_QPT_UD) {
-			/* C10-93.1.1: If the total sum of all the buffer lengths specified for a
-			 * UD message exceeds the MTU of the port as returned by QueryHCA, the CI
-			 * shall not emit any packets for this message. Further, the CI shall not
-			 * generate an error due to this condition.
-			 */
-
-			/* fake a successful UD send */
+			/* C10-93.1.1: fake a successful UD send */
 			wqe->first_psn = qp->req.psn;
 			wqe->last_psn = qp->req.psn;
 			qp->req.psn = (qp->req.psn + 1) & BTH_PSN_MASK;
@@ -750,6 +743,8 @@ int rxe_requester(void *arg)
 	 * to be called again
 	 */
 	wqe->state = wqe_state_error;
+	qp->req.wqe_index = next_index(qp->sq.queue,
+				       qp->req.wqe_index);
 	__rxe_do_task(&qp->comp.task);
 	ret = -EAGAIN;
 	goto done;
@@ -765,8 +760,7 @@ int rxe_requester(void *arg)
 
 again:
 	/* we come here if we are done with the current wqe but want to
-	 * get called again. Mostly we loop back to next wqe so should
-	 * be all one way or the other
+	 * get called again.
 	 */
 	ret = 0;
 	goto done;