net/mlx4_core: Port aggregation upper layer interface

Supply interface functions to bond and unbond ports of a mlx4 internal
interfaces. Example for such an interface is the one registered by the
mlx4 IB driver under RoCE.

There are

1. Functions to go in/out to/from bonded mode
2. Function to remap virtual ports to physical ports

The bond_mutex prevents simultaneous access to data that keep status of
the device in bonded mode.

The upper mlx4 interface marks to the mlx4 core module that they
want to be subject for such bonding by setting the MLX4_INTFF_BONDING
flag. Interface which goes to/from bonded mode is re-created.

The mlx4 Ethernet driver does not set this flag when registering the
interface, the IB driver does.

Signed-off-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

6 files changed, 157 insertions, 2 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_resources.c b/drivers/net/ethernet/mellanox/mlx4/en_resources.c
index f1a5500ff72d..34f2fdf4fe5d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_resources.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_resources.c
@@ -50,10 +50,14 @@ void mlx4_en_fill_qp_context(struct mlx4_en_priv *priv, int size, int stride,
 	context->mtu_msgmax = 0xff;
 	if (!is_tx && !rss)
 		context->rq_size_stride = ilog2(size) << 3 | (ilog2(stride) - 4);
-	if (is_tx)
+	if (is_tx) {
 		context->sq_size_stride = ilog2(size) << 3 | (ilog2(stride) - 4);
-	else
+		if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_PORT_REMAP)
+			context->params2 |= MLX4_QP_BIT_FPP;
+
+	} else {
 		context->sq_size_stride = ilog2(TXBB_SIZE) - 4;
+	}
 	context->usr_page = cpu_to_be32(mdev->priv_uar.index);
 	context->local_qpn = cpu_to_be32(qpn);
 	context->pri_path.ackto = 1 & 0x07;
diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c
index 68d2bad325d5..6fce58718837 100644
--- a/drivers/net/ethernet/mellanox/mlx4/intf.c
+++ b/drivers/net/ethernet/mellanox/mlx4/intf.c
@@ -33,11 +33,13 @@
 
 #include <linux/slab.h>
 #include <linux/export.h>
+#include <linux/errno.h>
 
 #include "mlx4.h"
 
 struct mlx4_device_context {
 	struct list_head	list;
+	struct list_head	bond_list;
 	struct mlx4_interface  *intf;
 	void		       *context;
 };
@@ -115,6 +117,58 @@ void mlx4_unregister_interface(struct mlx4_interface *intf)
 }
 EXPORT_SYMBOL_GPL(mlx4_unregister_interface);
 
+int mlx4_do_bond(struct mlx4_dev *dev, bool enable)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_device_context *dev_ctx = NULL, *temp_dev_ctx;
+	unsigned long flags;
+	int ret;
+	LIST_HEAD(bond_list);
+
+	if (!(dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_PORT_REMAP))
+		return -ENOTSUPP;
+
+	ret = mlx4_disable_rx_port_check(dev, enable);
+	if (ret) {
+		mlx4_err(dev, "Fail to %s rx port check\n",
+			 enable ? "enable" : "disable");
+		return ret;
+	}
+	if (enable) {
+		dev->flags |= MLX4_FLAG_BONDED;
+	} else {
+		 ret = mlx4_virt2phy_port_map(dev, 1, 2);
+		if (ret) {
+			mlx4_err(dev, "Fail to reset port map\n");
+			return ret;
+		}
+		dev->flags &= ~MLX4_FLAG_BONDED;
+	}
+
+	spin_lock_irqsave(&priv->ctx_lock, flags);
+	list_for_each_entry_safe(dev_ctx, temp_dev_ctx, &priv->ctx_list, list) {
+		if (dev_ctx->intf->flags & MLX4_INTFF_BONDING) {
+			list_add_tail(&dev_ctx->bond_list, &bond_list);
+			list_del(&dev_ctx->list);
+		}
+	}
+	spin_unlock_irqrestore(&priv->ctx_lock, flags);
+
+	list_for_each_entry(dev_ctx, &bond_list, bond_list) {
+		dev_ctx->intf->remove(dev, dev_ctx->context);
+		dev_ctx->context =  dev_ctx->intf->add(dev);
+
+		spin_lock_irqsave(&priv->ctx_lock, flags);
+		list_add_tail(&dev_ctx->list, &priv->ctx_list);
+		spin_unlock_irqrestore(&priv->ctx_lock, flags);
+
+		mlx4_dbg(dev, "Inrerface for protocol %d restarted with when bonded mode is %s\n",
+			 dev_ctx->intf->protocol, enable ?
+			 "enabled" : "disabled");
+	}
+	return 0;
+}
+
 void mlx4_dispatch_event(struct mlx4_dev *dev, enum mlx4_dev_event type,
 			 unsigned long param)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index cc9f48439244..f3245fe0f442 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -1160,6 +1160,91 @@ err_set_port:
 	return err ? err : count;
 }
 
+int mlx4_bond(struct mlx4_dev *dev)
+{
+	int ret = 0;
+	struct mlx4_priv *priv = mlx4_priv(dev);
+
+	mutex_lock(&priv->bond_mutex);
+
+	if (!mlx4_is_bonded(dev))
+		ret = mlx4_do_bond(dev, true);
+	else
+		ret = 0;
+
+	mutex_unlock(&priv->bond_mutex);
+	if (ret)
+		mlx4_err(dev, "Failed to bond device: %d\n", ret);
+	else
+		mlx4_dbg(dev, "Device is bonded\n");
+	return ret;
+}
+EXPORT_SYMBOL_GPL(mlx4_bond);
+
+int mlx4_unbond(struct mlx4_dev *dev)
+{
+	int ret = 0;
+	struct mlx4_priv *priv = mlx4_priv(dev);
+
+	mutex_lock(&priv->bond_mutex);
+
+	if (mlx4_is_bonded(dev))
+		ret = mlx4_do_bond(dev, false);
+
+	mutex_unlock(&priv->bond_mutex);
+	if (ret)
+		mlx4_err(dev, "Failed to unbond device: %d\n", ret);
+	else
+		mlx4_dbg(dev, "Device is unbonded\n");
+	return ret;
+}
+EXPORT_SYMBOL_GPL(mlx4_unbond);
+
+
+int mlx4_port_map_set(struct mlx4_dev *dev, struct mlx4_port_map *v2p)
+{
+	u8 port1 = v2p->port1;
+	u8 port2 = v2p->port2;
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	int err;
+
+	if (!(dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_PORT_REMAP))
+		return -ENOTSUPP;
+
+	mutex_lock(&priv->bond_mutex);
+
+	/* zero means keep current mapping for this port */
+	if (port1 == 0)
+		port1 = priv->v2p.port1;
+	if (port2 == 0)
+		port2 = priv->v2p.port2;
+
+	if ((port1 < 1) || (port1 > MLX4_MAX_PORTS) ||
+	    (port2 < 1) || (port2 > MLX4_MAX_PORTS) ||
+	    (port1 == 2 && port2 == 1)) {
+		/* besides boundary checks cross mapping makes
+		 * no sense and therefore not allowed */
+		err = -EINVAL;
+	} else if ((port1 == priv->v2p.port1) &&
+		 (port2 == priv->v2p.port2)) {
+		err = 0;
+	} else {
+		err = mlx4_virt2phy_port_map(dev, port1, port2);
+		if (!err) {
+			mlx4_dbg(dev, "port map changed: [%d][%d]\n",
+				 port1, port2);
+			priv->v2p.port1 = port1;
+			priv->v2p.port2 = port2;
+		} else {
+			mlx4_err(dev, "Failed to change port mape: %d\n", err);
+		}
+	}
+
+	mutex_unlock(&priv->bond_mutex);
+	return err;
+}
+EXPORT_SYMBOL_GPL(mlx4_port_map_set);
+
 static int mlx4_load_fw(struct mlx4_dev *dev)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
@@ -2638,6 +2723,7 @@ static int mlx4_load_one(struct pci_dev *pdev, int pci_dev_data,
 	spin_lock_init(&priv->ctx_lock);
 
 	mutex_init(&priv->port_mutex);
+	mutex_init(&priv->bond_mutex);
 
 	INIT_LIST_HEAD(&priv->pgdir_list);
 	mutex_init(&priv->pgdir_mutex);
@@ -2934,6 +3020,9 @@ slave_start:
 			goto err_port;
 	}
 
+	priv->v2p.port1 = 1;
+	priv->v2p.port2 = 2;
+
 	err = mlx4_register_device(dev);
 	if (err)
 		goto err_port;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 148dc0945aab..803f17653da7 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -885,6 +885,8 @@ struct mlx4_priv {
 	int			reserved_mtts;
 	int			fs_hash_mode;
 	u8 virt2phys_pkey[MLX4_MFUNC_MAX][MLX4_MAX_PORTS][MLX4_MAX_PORT_PKEYS];
+	struct mlx4_port_map	v2p; /* cached port mapping configuration */
+	struct mutex		bond_mutex; /* for bond mode */
 	__be64			slave_node_guids[MLX4_MFUNC_MAX];
 
 	atomic_t		opreq_count;
@@ -1364,6 +1366,7 @@ int mlx4_get_slave_num_gids(struct mlx4_dev *dev, int slave, int port);
 /* Returns the VF index of slave */
 int mlx4_get_vf_indx(struct mlx4_dev *dev, int slave);
 int mlx4_config_mad_demux(struct mlx4_dev *dev);
+int mlx4_do_bond(struct mlx4_dev *dev, bool enable);
 
 enum mlx4_zone_flags {
 	MLX4_ZONE_ALLOW_ALLOC_FROM_LOWER_PRIO	= 1UL << 0,
diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c
index 1586ecce13c7..2bb8553bd905 100644
--- a/drivers/net/ethernet/mellanox/mlx4/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx4/qp.c
@@ -882,6 +882,8 @@ int mlx4_qp_to_ready(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
 	for (i = 0; i < ARRAY_SIZE(states) - 1; i++) {
 		context->flags &= cpu_to_be32(~(0xf << 28));
 		context->flags |= cpu_to_be32(states[i + 1] << 28);
+		if (states[i + 1] != MLX4_QP_STATE_RTR)
+			context->params2 &= ~MLX4_QP_BIT_FPP;
 		err = mlx4_qp_modify(dev, mtt, states[i], states[i + 1],
 				     context, 0, 0, qp);
 		if (err) {
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index 79feeb6b0d87..c5f3dfca226b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -2944,6 +2944,9 @@ static int verify_qp_parameters(struct mlx4_dev *dev,
 	qp_type	= (be32_to_cpu(qp_ctx->flags) >> 16) & 0xff;
 	optpar	= be32_to_cpu(*(__be32 *) inbox->buf);
 
+	if (slave != mlx4_master_func_num(dev))
+		qp_ctx->params2 &= ~MLX4_QP_BIT_FPP;
+
 	switch (qp_type) {
 	case MLX4_QP_ST_RC:
 	case MLX4_QP_ST_XRC: