mlx4: Implement QP paravirtualization and maintain phys_pkey_cache for smp_snoop

This requires:

1. Replacing the paravirtualized P_Key index (inserted by the guest)
   with the real P_Key index.

2. For UD QPs, placing the guest's true source GID index in the
   address path structure mgid field, and setting the ud_force_mgid
   bit so that the mgid is taken from the QP context and not from the
   WQE when posting sends.

3. For UC and RC QPs, placing the guest's true source GID index in the
   address path structure mgid field.

4. For tunnel and proxy QPs, setting the Q_Key value reserved for that
   proxy/tunnel pair.

Since not all the above adjustments occur in all the QP transitions,
the QP transitions require separate wrapper functions.

Secondly, initialize the P_Key virtualization table to its default
values: Master virtualized table is 1-1 with the real P_Key table,
guest virtualized table has P_Key index 0 mapped to the real P_Key
index 0, and all the other P_Key indices mapped to the reserved
(invalid) P_Key at index 127.

Finally, add logic in smp_snoop for maintaining the phys_P_Key_cache.
and generating events on the master only if a P_Key actually changed.

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <roland@purestorage.com>

2 files changed, 66 insertions, 2 deletions

diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index e98849338a9..318d5bcf821 100644
--- a/drivers/infiniband/hw/mlx4/mad.c
+++ b/drivers/infiniband/hw/mlx4/mad.c
@@ -185,6 +185,10 @@ static void smp_snoop(struct ib_device *ibdev, u8 port_num, struct ib_mad *mad,
 {
 	struct ib_port_info *pinfo;
 	u16 lid;
+	__be16 *base;
+	u32 bn, pkey_change_bitmap;
+	int i;
+
 
 	struct mlx4_ib_dev *dev = to_mdev(ibdev);
 	if ((mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_LID_ROUTED ||
@@ -209,8 +213,33 @@ static void smp_snoop(struct ib_device *ibdev, u8 port_num, struct ib_mad *mad,
 			break;
 
 		case IB_SMP_ATTR_PKEY_TABLE:
-			mlx4_ib_dispatch_event(dev, port_num,
-					       IB_EVENT_PKEY_CHANGE);
+			if (!mlx4_is_mfunc(dev->dev)) {
+				mlx4_ib_dispatch_event(dev, port_num,
+						       IB_EVENT_PKEY_CHANGE);
+				break;
+			}
+
+			bn  = be32_to_cpu(((struct ib_smp *)mad)->attr_mod) & 0xFFFF;
+			base = (__be16 *) &(((struct ib_smp *)mad)->data[0]);
+			pkey_change_bitmap = 0;
+			for (i = 0; i < 32; i++) {
+				pr_debug("PKEY[%d] = x%x\n",
+					 i + bn*32, be16_to_cpu(base[i]));
+				if (be16_to_cpu(base[i]) !=
+				    dev->pkeys.phys_pkey_cache[port_num - 1][i + bn*32]) {
+					pkey_change_bitmap |= (1 << i);
+					dev->pkeys.phys_pkey_cache[port_num - 1][i + bn*32] =
+						be16_to_cpu(base[i]);
+				}
+			}
+			pr_debug("PKEY Change event: port=%d, "
+				 "block=0x%x, change_bitmap=0x%x\n",
+				 port_num, bn, pkey_change_bitmap);
+
+			if (pkey_change_bitmap)
+				mlx4_ib_dispatch_event(dev, port_num,
+						       IB_EVENT_PKEY_CHANGE);
+
 			break;
 
 		case IB_SMP_ATTR_GUID_INFO:
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 3f7f77f93a1..8e10ec2af7b 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -1121,6 +1121,38 @@ static int mlx4_ib_netdev_event(struct notifier_block *this, unsigned long event
 	return NOTIFY_DONE;
 }
 
+static void init_pkeys(struct mlx4_ib_dev *ibdev)
+{
+	int port;
+	int slave;
+	int i;
+
+	if (mlx4_is_master(ibdev->dev)) {
+		for (slave = 0; slave <= ibdev->dev->num_vfs; ++slave) {
+			for (port = 1; port <= ibdev->dev->caps.num_ports; ++port) {
+				for (i = 0;
+				     i < ibdev->dev->phys_caps.pkey_phys_table_len[port];
+				     ++i) {
+					ibdev->pkeys.virt2phys_pkey[slave][port - 1][i] =
+					/* master has the identity virt2phys pkey mapping */
+						(slave == mlx4_master_func_num(ibdev->dev) || !i) ? i :
+							ibdev->dev->phys_caps.pkey_phys_table_len[port] - 1;
+					mlx4_sync_pkey_table(ibdev->dev, slave, port, i,
+							     ibdev->pkeys.virt2phys_pkey[slave][port - 1][i]);
+				}
+			}
+		}
+		/* initialize pkey cache */
+		for (port = 1; port <= ibdev->dev->caps.num_ports; ++port) {
+			for (i = 0;
+			     i < ibdev->dev->phys_caps.pkey_phys_table_len[port];
+			     ++i)
+				ibdev->pkeys.phys_pkey_cache[port-1][i] =
+					(i) ? 0 : 0xFFFF;
+		}
+	}
+}
+
 static void mlx4_ib_alloc_eqs(struct mlx4_dev *dev, struct mlx4_ib_dev *ibdev)
 {
 	char name[32];
@@ -1375,6 +1407,9 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 
 	ibdev->ib_active = true;
 
+	if (mlx4_is_mfunc(ibdev->dev))
+		init_pkeys(ibdev);
+
 	return ibdev;
 
 err_notif: