IB/mlx4: Fix possible vl/sl field mismatch in LRH header in QP1 packets

In MLX qp packets, the LRH (built by the driver) has both a VL field
and an SL field. When building a QP1 packet, the VL field should
reflect the SLtoVL mapping and not arbitrarily contain zero (as is
done now). This bug causes credit problems in IB switches at
high rates of QP1 packets.

The fix is to cache the SL to VL mapping in the driver, and look up
the VL mapped to the SL provided in the send request when sending
QP1 packets.

For FW versions which support generating a port_management_config_change
event with subtype sl-to-vl-table-change, the driver uses that event
to update its sl-to-vl mapping cache.  Otherwise, the driver snoops
incoming SMP mads to update the cache.

There remains the case where the FW is running in secure-host mode
(so no QP0 packets are delivered to the driver), and the FW does not
generate the sl2vl mapping change event. To support this case, the
driver updates (via querying the FW) its sl2vl mapping cache when
running in secure-host mode when it receives either a Port Up event
or a client-reregister event (where the port is still up, but there
may have been an opensm failover).
OpenSM modifies the sl2vl mapping before Port Up and Client-reregister
events occur, so if there is a mapping change the driver's cache will
be properly updated.

Fixes: 225c7b1feef1 ("IB/mlx4: Add a driver Mellanox ConnectX InfiniBand adapters")
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>

1 files changed, 62 insertions, 2 deletions

diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index d8886d051d4b..1301a1db958c 100644
--- a/drivers/infiniband/hw/mlx4/mad.c
+++ b/drivers/infiniband/hw/mlx4/mad.c
@@ -230,6 +230,8 @@ static void smp_snoop(struct ib_device *ibdev, u8 port_num, const struct ib_mad
 	    mad->mad_hdr.method == IB_MGMT_METHOD_SET)
 		switch (mad->mad_hdr.attr_id) {
 		case IB_SMP_ATTR_PORT_INFO:
+			if (dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_PORT_MNG_CHG_EV)
+				return;
 			pinfo = (struct ib_port_info *) ((struct ib_smp *) mad)->data;
 			lid = be16_to_cpu(pinfo->lid);
 
@@ -245,6 +247,8 @@ static void smp_snoop(struct ib_device *ibdev, u8 port_num, const struct ib_mad
 			break;
 
 		case IB_SMP_ATTR_PKEY_TABLE:
+			if (dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_PORT_MNG_CHG_EV)
+				return;
 			if (!mlx4_is_mfunc(dev->dev)) {
 				mlx4_ib_dispatch_event(dev, port_num,
 						       IB_EVENT_PKEY_CHANGE);
@@ -281,6 +285,8 @@ static void smp_snoop(struct ib_device *ibdev, u8 port_num, const struct ib_mad
 			break;
 
 		case IB_SMP_ATTR_GUID_INFO:
+			if (dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_PORT_MNG_CHG_EV)
+				return;
 			/* paravirtualized master's guid is guid 0 -- does not change */
 			if (!mlx4_is_master(dev->dev))
 				mlx4_ib_dispatch_event(dev, port_num,
@@ -296,6 +302,26 @@ static void smp_snoop(struct ib_device *ibdev, u8 port_num, const struct ib_mad
 			}
 			break;
 
+		case IB_SMP_ATTR_SL_TO_VL_TABLE:
+			/* cache sl to vl mapping changes for use in
+			 * filling QP1 LRH VL field when sending packets
+			 */
+			if (dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_PORT_MNG_CHG_EV &&
+			    dev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_SL_TO_VL_CHANGE_EVENT)
+				return;
+			if (!mlx4_is_slave(dev->dev)) {
+				union sl2vl_tbl_to_u64 sl2vl64;
+				int jj;
+
+				for (jj = 0; jj < 8; jj++) {
+					sl2vl64.sl8[jj] = ((struct ib_smp *)mad)->data[jj];
+					pr_debug("port %u, sl2vl[%d] = %02x\n",
+						 port_num, jj, sl2vl64.sl8[jj]);
+				}
+				atomic64_set(&dev->sl2vl[port_num - 1], sl2vl64.sl64);
+			}
+			break;
+
 		default:
 			break;
 		}
@@ -806,8 +832,7 @@ static int ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 		return IB_MAD_RESULT_FAILURE;
 
 	if (!out_mad->mad_hdr.status) {
-		if (!(to_mdev(ibdev)->dev->caps.flags & MLX4_DEV_CAP_FLAG_PORT_MNG_CHG_EV))
-			smp_snoop(ibdev, port_num, in_mad, prev_lid);
+		smp_snoop(ibdev, port_num, in_mad, prev_lid);
 		/* slaves get node desc from FW */
 		if (!mlx4_is_slave(to_mdev(ibdev)->dev))
 			node_desc_override(ibdev, out_mad);
@@ -1038,6 +1063,23 @@ static void handle_client_rereg_event(struct mlx4_ib_dev *dev, u8 port_num)
 						    MLX4_EQ_PORT_INFO_CLIENT_REREG_MASK);
 		}
 	}
+
+	/* Update the sl to vl table from inside client rereg
+	 * only if in secure-host mode (snooping is not possible)
+	 * and the sl-to-vl change event is not generated by FW.
+	 */
+	if (!mlx4_is_slave(dev->dev) &&
+	    dev->dev->flags & MLX4_FLAG_SECURE_HOST &&
+	    !(dev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_SL_TO_VL_CHANGE_EVENT)) {
+		if (mlx4_is_master(dev->dev))
+			/* already in work queue from mlx4_ib_event queueing
+			 * mlx4_handle_port_mgmt_change_event, which calls
+			 * this procedure. Therefore, call sl2vl_update directly.
+			 */
+			mlx4_ib_sl2vl_update(dev, port_num);
+		else
+			mlx4_sched_ib_sl2vl_update_work(dev, port_num);
+	}
 	mlx4_ib_dispatch_event(dev, port_num, IB_EVENT_CLIENT_REREGISTER);
 }
 
@@ -1156,6 +1198,24 @@ void handle_port_mgmt_change_event(struct work_struct *work)
 			handle_slaves_guid_change(dev, port, tbl_block, change_bitmap);
 		}
 		break;
+
+	case MLX4_DEV_PMC_SUBTYPE_SL_TO_VL_MAP:
+		/* cache sl to vl mapping changes for use in
+		 * filling QP1 LRH VL field when sending packets
+		 */
+		if (!mlx4_is_slave(dev->dev)) {
+			union sl2vl_tbl_to_u64 sl2vl64;
+			int jj;
+
+			for (jj = 0; jj < 8; jj++) {
+				sl2vl64.sl8[jj] =
+					eqe->event.port_mgmt_change.params.sl2vl_tbl_change_info.sl2vl_table[jj];
+				pr_debug("port %u, sl2vl[%d] = %02x\n",
+					 port, jj, sl2vl64.sl8[jj]);
+			}
+			atomic64_set(&dev->sl2vl[port - 1], sl2vl64.sl64);
+		}
+		break;
 	default:
 		pr_warn("Unsupported subtype 0x%x for "
 			"Port Management Change event\n", eqe->subtype);