From: Bernard Metzler <bmt@zurich.ibm.com>
Date: Sun, 30 Jan 2022 18:08:15 +0100
Subject: RDMA/siw: Fix broken RDMA Read Fence/Resume logic.
Patch-mainline: v5.17-rc3
Git-commit: b43a76f423aa304037603fd6165c4a534d2c09a7
References: git-fixes

Code unconditionally resumed fenced SQ processing after next RDMA Read
completion, even if other RDMA Read responses are still outstanding, or
ORQ is full. Also adds comments for better readability of fence
processing, and removes orq_get_tail() helper, which is not needed
anymore.

Fixes: 8b6a361b8c48 ("rdma/siw: receive path")
Fixes: a531975279f3 ("rdma/siw: main include file")
Link: https://lore.kernel.org/r/20220130170815.1940-1-bmt@zurich.ibm.com
Reported-by: Jared Holzman <jared.holzman@excelero.com>
Signed-off-by: Bernard Metzler <bmt@zurich.ibm.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Acked-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
---
 drivers/infiniband/sw/siw/siw.h       |    7 +------
 drivers/infiniband/sw/siw/siw_qp_rx.c |   20 +++++++++++---------
 2 files changed, 12 insertions(+), 15 deletions(-)

--- a/drivers/infiniband/sw/siw/siw.h
+++ b/drivers/infiniband/sw/siw/siw.h
@@ -644,14 +644,9 @@ static inline struct siw_sqe *orq_get_cu
 	return &qp->orq[qp->orq_get % qp->attrs.orq_size];
 }
 
-static inline struct siw_sqe *orq_get_tail(struct siw_qp *qp)
-{
-	return &qp->orq[qp->orq_put % qp->attrs.orq_size];
-}
-
 static inline struct siw_sqe *orq_get_free(struct siw_qp *qp)
 {
-	struct siw_sqe *orq_e = orq_get_tail(qp);
+	struct siw_sqe *orq_e = &qp->orq[qp->orq_put % qp->attrs.orq_size];
 
 	if (READ_ONCE(orq_e->flags) == 0)
 		return orq_e;
--- a/drivers/infiniband/sw/siw/siw_qp_rx.c
+++ b/drivers/infiniband/sw/siw/siw_qp_rx.c
@@ -1153,11 +1153,12 @@ static int siw_check_tx_fence(struct siw
 
 	spin_lock_irqsave(&qp->orq_lock, flags);
 
-	rreq = orq_get_current(qp);
-
 	/* free current orq entry */
+	rreq = orq_get_current(qp);
 	WRITE_ONCE(rreq->flags, 0);
 
+	qp->orq_get++;
+
 	if (qp->tx_ctx.orq_fence) {
 		if (unlikely(tx_waiting->wr_status != SIW_WR_QUEUED)) {
 			pr_warn("siw: [QP %u]: fence resume: bad status %d\n",
@@ -1165,10 +1166,12 @@ static int siw_check_tx_fence(struct siw
 			rv = -EPROTO;
 			goto out;
 		}
-		/* resume SQ processing */
+		/* resume SQ processing, if possible */
 		if (tx_waiting->sqe.opcode == SIW_OP_READ ||
 		    tx_waiting->sqe.opcode == SIW_OP_READ_LOCAL_INV) {
-			rreq = orq_get_tail(qp);
+
+			/* SQ processing was stopped because of a full ORQ */
+			rreq = orq_get_free(qp);
 			if (unlikely(!rreq)) {
 				pr_warn("siw: [QP %u]: no ORQE\n", qp_id(qp));
 				rv = -EPROTO;
@@ -1181,15 +1184,14 @@ static int siw_check_tx_fence(struct siw
 			resume_tx = 1;
 
 		} else if (siw_orq_empty(qp)) {
+			/*
+			 * SQ processing was stopped by fenced work request.
+			 * Resume since all previous Read's are now completed.
+			 */
 			qp->tx_ctx.orq_fence = 0;
 			resume_tx = 1;
-		} else {
-			pr_warn("siw: [QP %u]: fence resume: orq idx: %d:%d\n",
-				qp_id(qp), qp->orq_get, qp->orq_put);
-			rv = -EPROTO;
 		}
 	}
-	qp->orq_get++;
 out:
 	spin_unlock_irqrestore(&qp->orq_lock, flags);