From 11bb9d392c1d5b63e2b9a0c8cc8a64cf49808757 Mon Sep 17 00:00:00 2001
From: Arthur Kepner <akepner@sgi.com>
Date: Sun, 11 Mar 2007 07:35:15 +0100
Subject: 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>
Signed-off-by: Adrian Bunk <bunk@stusta.de>
---
 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 96f1a86bf049..e8662467ddf6 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"
@@ -205,6 +207,11 @@ 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 fba608ed7df2..ac9ff2a35f62 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>
@@ -1724,6 +1726,11 @@ 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;
@@ -1842,6 +1849,12 @@ 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;
 }
@@ -2099,6 +2112,12 @@ 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 e7e153d9c4c6..a818c319f2a1 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"
@@ -528,6 +530,12 @@ 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;
 }
-- 
cgit v1.2.3