RDMA/rxe: Fix ref error in rxe_av.c

The commit referenced below can take a reference to the AH which is never
dropped. This only happens in the UD request path. This patch optionally
passes that AH back to the caller so that it can hold the reference while
the AV is being accessed and then drop it. Code to do this is added to
rxe_req.c. The AV is also passed to rxe_prepare in rxe_net.c as an
optimization.

Fixes: e2fe06c90806 ("RDMA/rxe: Lookup kernel AH from ah index in UD WQEs")
Link: https://lore.kernel.org/r/20220304000808.225811-2-rpearsonhpe@gmail.com
Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

1 files changed, 33 insertions, 22 deletions

diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c
index a3c78b4ac9f1..3520d55a124b 100644
--- a/drivers/infiniband/sw/rxe/rxe_req.c
+++ b/drivers/infiniband/sw/rxe/rxe_req.c
@@ -358,6 +358,7 @@ 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, u32 payload,
 				       struct rxe_pkt_info *pkt)
@@ -365,7 +366,6 @@ static struct sk_buff *init_req_packet(struct rxe_qp *qp,
 	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;
@@ -374,21 +374,9 @@ static struct sk_buff *init_req_packet(struct rxe_qp *qp,
 
 	/* 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;
@@ -447,13 +435,13 @@ 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,
-		       u32 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 paylen)
 {
 	int err;
 
-	err = rxe_prepare(pkt, skb);
+	err = rxe_prepare(av, pkt, skb);
 	if (err)
 		return err;
 
@@ -608,6 +596,7 @@ 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;
@@ -619,6 +608,8 @@ int rxe_requester(void *arg)
 	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);
 
@@ -705,14 +696,28 @@ next_wqe:
 		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_drop_ah;
+	}
+
+	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;
-		goto err;
+		goto err_drop_ah;
 	}
 
-	ret = finish_packet(qp, wqe, &pkt, skb, payload);
+	ret = finish_packet(qp, av, wqe, &pkt, skb, payload);
 	if (unlikely(ret)) {
 		pr_debug("qp#%d Error during finish packet\n", qp_num(qp));
 		if (ret == -EFAULT)
@@ -720,9 +725,12 @@ next_wqe:
 		else
 			wqe->status = IB_WC_LOC_QP_OP_ERR;
 		kfree_skb(skb);
-		goto err;
+		goto err_drop_ah;
 	}
 
+	if (ah)
+		rxe_drop_ref(ah);
+
 	/*
 	 * To prevent a race on wqe access between requester and completer,
 	 * wqe members state and psn need to be set before calling
@@ -751,6 +759,9 @@ next_wqe:
 
 	goto next_wqe;
 
+err_drop_ah:
+	if (ah)
+		rxe_drop_ref(ah);
 err:
 	wqe->state = wqe_state_error;
 	__rxe_do_task(&qp->comp.task);