IB/ipoib: Increase ipoib Datagram mode MTU's upper limit

Currently the ipoib UD mtu is restricted to 4K bytes. Remove this
limitation so that the IPOIB module can potentially use an MTU (in UD
mode) that is bounded by the MTU of the underlying device. A field is
added to the ib_port_attr structure to indicate the maximum physical
MTU the underlying device supports.

Link: https://lore.kernel.org/r/20200511160618.173205.23053.stgit@awfm-01.aw.intel.com
Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Sadanand Warrier <sadanand.warrier@intel.com>
Signed-off-by: Kaike Wan <kaike.wan@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

4 files changed, 10 insertions, 23 deletions

diff --git a/drivers/infiniband/hw/hfi1/qp.c b/drivers/infiniband/hw/hfi1/qp.c
index f8e733aa3bb8..0c2ae9f7b3e8 100644
--- a/drivers/infiniband/hw/hfi1/qp.c
+++ b/drivers/infiniband/hw/hfi1/qp.c
@@ -1,5 +1,5 @@
 /*
- * Copyright(c) 2015 - 2019 Intel Corporation.
+ * Copyright(c) 2015 - 2020 Intel Corporation.
  *
  * This file is provided under a dual BSD/GPLv2 license.  When using or
  * redistributing this file, you may do so under either license.
@@ -186,15 +186,6 @@ static void flush_iowait(struct rvt_qp *qp)
 	write_sequnlock_irqrestore(lock, flags);
 }
 
-static inline int opa_mtu_enum_to_int(int mtu)
-{
-	switch (mtu) {
-	case OPA_MTU_8192:  return 8192;
-	case OPA_MTU_10240: return 10240;
-	default:            return -1;
-	}
-}
-
 /**
  * This function is what we would push to the core layer if we wanted to be a
  * "first class citizen".  Instead we hide this here and rely on Verbs ULPs
@@ -202,15 +193,10 @@ static inline int opa_mtu_enum_to_int(int mtu)
  */
 static inline int verbs_mtu_enum_to_int(struct ib_device *dev, enum ib_mtu mtu)
 {
-	int val;
-
 	/* Constraining 10KB packets to 8KB packets */
 	if (mtu == (enum ib_mtu)OPA_MTU_10240)
 		mtu = OPA_MTU_8192;
-	val = opa_mtu_enum_to_int((int)mtu);
-	if (val > 0)
-		return val;
-	return ib_mtu_enum_to_int(mtu);
+	return opa_mtu_enum_to_int((enum opa_mtu)mtu);
 }
 
 int hfi1_check_modify_qp(struct rvt_qp *qp, struct ib_qp_attr *attr,
diff --git a/drivers/infiniband/hw/hfi1/verbs.c b/drivers/infiniband/hw/hfi1/verbs.c
index c61b2916d420..19d5d0061b01 100644
--- a/drivers/infiniband/hw/hfi1/verbs.c
+++ b/drivers/infiniband/hw/hfi1/verbs.c
@@ -1439,6 +1439,8 @@ static int query_port(struct rvt_dev_info *rdi, u8 port_num,
 				      4096 : hfi1_max_mtu), IB_MTU_4096);
 	props->active_mtu = !valid_ib_mtu(ppd->ibmtu) ? props->max_mtu :
 		mtu_to_enum(ppd->ibmtu, IB_MTU_4096);
+	props->phys_mtu = HFI1_CAP_IS_KSET(AIP) ? hfi1_max_mtu :
+				ib_mtu_enum_to_int(props->max_mtu);
 
 	return 0;
 }
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index d4c6a97ce4c0..22216f181b24 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -1855,7 +1855,7 @@ static int ipoib_parent_init(struct net_device *ndev)
 			priv->port);
 		return result;
 	}
-	priv->max_ib_mtu = ib_mtu_enum_to_int(attr.max_mtu);
+	priv->max_ib_mtu = rdma_mtu_from_attr(priv->ca, priv->port, &attr);
 
 	result = ib_query_pkey(priv->ca, priv->port, 0, &priv->pkey);
 	if (result) {
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index b9e9562f5034..7166ee9b7a25 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -218,6 +218,7 @@ static int ipoib_mcast_join_finish(struct ipoib_mcast *mcast,
 	struct rdma_ah_attr av;
 	int ret;
 	int set_qkey = 0;
+	int mtu;
 
 	mcast->mcmember = *mcmember;
 
@@ -240,13 +241,11 @@ static int ipoib_mcast_join_finish(struct ipoib_mcast *mcast,
 		priv->broadcast->mcmember.flow_label = mcmember->flow_label;
 		priv->broadcast->mcmember.hop_limit = mcmember->hop_limit;
 		/* assume if the admin and the mcast are the same both can be changed */
+		mtu = rdma_mtu_enum_to_int(priv->ca,  priv->port,
+					   priv->broadcast->mcmember.mtu);
 		if (priv->mcast_mtu == priv->admin_mtu)
-			priv->admin_mtu =
-			priv->mcast_mtu =
-			IPOIB_UD_MTU(ib_mtu_enum_to_int(priv->broadcast->mcmember.mtu));
-		else
-			priv->mcast_mtu =
-			IPOIB_UD_MTU(ib_mtu_enum_to_int(priv->broadcast->mcmember.mtu));
+			priv->admin_mtu = IPOIB_UD_MTU(mtu);
+		priv->mcast_mtu = IPOIB_UD_MTU(mtu);
 
 		priv->qkey = be32_to_cpu(priv->broadcast->mcmember.qkey);
 		spin_unlock_irq(&priv->lock);