From 1f5c23e2c10d642a23aa3ebb449670a5184b6aab Mon Sep 17 00:00:00 2001
From: Arthur Kepner <akepner@sgi.com>
Date: Mon, 16 Oct 2006 20:22:35 -0700
Subject: [PATCH] IB/mthca: Use mmiowb after doorbell ring

We discovered a problem when running IPoIB applications on multiple
CPUs on an Altix system. Many messages such as:

ib_mthca 0002:01:00.0: SQ 000014 full (19941644 head, 19941707 tail, 64 max, 0 nreq)

appear in syslog, and the driver wedges up.

Apparently this is because writes to the doorbells from different CPUs
reach the device out of order. The following patch adds mmiowb() calls
after doorbell rings to ensure the doorbell writes are ordered.

Signed-off-by: Arthur Kepner <akepner@sgi.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
---
 drivers/infiniband/hw/mthca/mthca_cq.c  |  7 +++++++
 drivers/infiniband/hw/mthca/mthca_qp.c  | 19 +++++++++++++++++++
 drivers/infiniband/hw/mthca/mthca_srq.c |  8 ++++++++
 3 files changed, 34 insertions(+)

diff --git a/drivers/infiniband/hw/mthca/mthca_cq.c b/drivers/infiniband/hw/mthca/mthca_cq.c
index e393681ba7d4..149b36901239 100644
--- a/drivers/infiniband/hw/mthca/mthca_cq.c
+++ b/drivers/infiniband/hw/mthca/mthca_cq.c
@@ -39,6 +39,8 @@
 #include <linux/init.h>
 #include <linux/hardirq.h>
 
+#include <asm/io.h>
+
 #include <rdma/ib_pack.h>
 
 #include "mthca_dev.h"
@@ -210,6 +212,11 @@ static inline void update_cons_index(struct mthca_dev *dev, struct mthca_cq *cq,
 		mthca_write64(doorbell,
 			      dev->kar + MTHCA_CQ_DOORBELL,
 			      MTHCA_GET_DOORBELL_LOCK(&dev->doorbell_lock));
+		/*
+		 * Make sure doorbells don't leak out of CQ spinlock
+		 * and reach the HCA out of order:
+		 */
+		mmiowb();
 	}
 }
 
diff --git a/drivers/infiniband/hw/mthca/mthca_qp.c b/drivers/infiniband/hw/mthca/mthca_qp.c
index 5e5c58b9920b..6a7822e0fc19 100644
--- a/drivers/infiniband/hw/mthca/mthca_qp.c
+++ b/drivers/infiniband/hw/mthca/mthca_qp.c
@@ -39,6 +39,8 @@
 #include <linux/string.h>
 #include <linux/slab.h>
 
+#include <asm/io.h>
+
 #include <rdma/ib_verbs.h>
 #include <rdma/ib_cache.h>
 #include <rdma/ib_pack.h>
@@ -1732,6 +1734,11 @@ out:
 		mthca_write64(doorbell,
 			      dev->kar + MTHCA_SEND_DOORBELL,
 			      MTHCA_GET_DOORBELL_LOCK(&dev->doorbell_lock));
+		/*
+		 * Make sure doorbells don't leak out of SQ spinlock
+		 * and reach the HCA out of order:
+		 */
+		mmiowb();
 	}
 
 	qp->sq.next_ind = ind;
@@ -1851,6 +1858,12 @@ out:
 	qp->rq.next_ind = ind;
 	qp->rq.head    += nreq;
 
+	/*
+	 * Make sure doorbells don't leak out of RQ spinlock and reach
+	 * the HCA out of order:
+	 */
+	mmiowb();
+
 	spin_unlock_irqrestore(&qp->rq.lock, flags);
 	return err;
 }
@@ -2112,6 +2125,12 @@ out:
 			      MTHCA_GET_DOORBELL_LOCK(&dev->doorbell_lock));
 	}
 
+	/*
+	 * Make sure doorbells don't leak out of SQ spinlock and reach
+	 * the HCA out of order:
+	 */
+	mmiowb();
+
 	spin_unlock_irqrestore(&qp->sq.lock, flags);
 	return err;
 }
diff --git a/drivers/infiniband/hw/mthca/mthca_srq.c b/drivers/infiniband/hw/mthca/mthca_srq.c
index 92a72f521528..f5d7677d1079 100644
--- a/drivers/infiniband/hw/mthca/mthca_srq.c
+++ b/drivers/infiniband/hw/mthca/mthca_srq.c
@@ -35,6 +35,8 @@
 #include <linux/slab.h>
 #include <linux/string.h>
 
+#include <asm/io.h>
+
 #include "mthca_dev.h"
 #include "mthca_cmd.h"
 #include "mthca_memfree.h"
@@ -595,6 +597,12 @@ int mthca_tavor_post_srq_recv(struct ib_srq *ibsrq, struct ib_recv_wr *wr,
 			      MTHCA_GET_DOORBELL_LOCK(&dev->doorbell_lock));
 	}
 
+	/*
+	 * Make sure doorbells don't leak out of SRQ spinlock and
+	 * reach the HCA out of order:
+	 */
+	mmiowb();
+
 	spin_unlock_irqrestore(&srq->lock, flags);
 	return err;
 }
-- 
2.20.1