net/mlx4_en: Add resilience in low memory systems

This patch fixes the lost of Ethernet port on low memory system,
when driver frees its resources and fails to allocate new resources.
Issue could happen while changing number of channels, rings size or
changing the timestamp configuration.
This fix is necessary because of removing vmap use in the code.
When vmap was in use driver could allocate non-contiguous memory
and make it contiguous with vmap. Now it could fail to allocate
a large chunk of contiguous memory and lose the port.
Current code tries to allocate new resources and then upon success
frees the old resources.

Fixes: 73898db0 ('net/mlx4: Avoid wrong virtual mappings')
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/mellanox/mlx4/en_ethtool.c

@@ -1042,6 +1042,8 @@ static int mlx4_en_set_ringparam(struct net_device *dev,
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_en_dev *mdev = priv->mdev;
+	struct mlx4_en_port_profile new_prof;
+	struct mlx4_en_priv *tmp;
 	u32 rx_size, tx_size;
 	int port_up = 0;
 	int err = 0;
@@ -1061,22 +1063,25 @@ static int mlx4_en_set_ringparam(struct net_device *dev,
 	    tx_size == priv->tx_ring[0]->size)
 		return 0;
 
+	tmp = kzalloc(sizeof(*tmp), GFP_KERNEL);
+	if (!tmp)
+		return -ENOMEM;
+
 	mutex_lock(&mdev->state_lock);
+	memcpy(&new_prof, priv->prof, sizeof(struct mlx4_en_port_profile));
+	new_prof.tx_ring_size = tx_size;
+	new_prof.rx_ring_size = rx_size;
+	err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof);
+	if (err)
+		goto out;
+
 	if (priv->port_up) {
 		port_up = 1;
 		mlx4_en_stop_port(dev, 1);
 	}
 
-	mlx4_en_free_resources(priv);
-
-	priv->prof->tx_ring_size = tx_size;
-	priv->prof->rx_ring_size = rx_size;
+	mlx4_en_safe_replace_resources(priv, tmp);
 
-	err = mlx4_en_alloc_resources(priv);
-	if (err) {
-		en_err(priv, "Failed reallocating port resources\n");
-		goto out;
-	}
 	if (port_up) {
 		err = mlx4_en_start_port(dev);
 		if (err)
@@ -1084,8 +1089,8 @@ static int mlx4_en_set_ringparam(struct net_device *dev,
 	}
 
 	err = mlx4_en_moderation_update(priv);
-
 out:
+	kfree(tmp);
 	mutex_unlock(&mdev->state_lock);
 	return err;
 }
@@ -1714,6 +1719,8 @@ static int mlx4_en_set_channels(struct net_device *dev,
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_en_dev *mdev = priv->mdev;
+	struct mlx4_en_port_profile new_prof;
+	struct mlx4_en_priv *tmp;
 	int port_up = 0;
 	int err = 0;
 
@@ -1723,23 +1730,26 @@ static int mlx4_en_set_channels(struct net_device *dev,
 	    !channel->tx_count || !channel->rx_count)
 		return -EINVAL;
 
+	tmp = kzalloc(sizeof(*tmp), GFP_KERNEL);
+	if (!tmp)
+		return -ENOMEM;
+
 	mutex_lock(&mdev->state_lock);
+	memcpy(&new_prof, priv->prof, sizeof(struct mlx4_en_port_profile));
+	new_prof.num_tx_rings_p_up = channel->tx_count;
+	new_prof.tx_ring_num = channel->tx_count * MLX4_EN_NUM_UP;
+	new_prof.rx_ring_num = channel->rx_count;
+
+	err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof);
+	if (err)
+		goto out;
+
 	if (priv->port_up) {
 		port_up = 1;
 		mlx4_en_stop_port(dev, 1);
 	}
 
-	mlx4_en_free_resources(priv);
-
-	priv->num_tx_rings_p_up = channel->tx_count;
-	priv->tx_ring_num = channel->tx_count * MLX4_EN_NUM_UP;
-	priv->rx_ring_num = channel->rx_count;
-
-	err = mlx4_en_alloc_resources(priv);
-	if (err) {
-		en_err(priv, "Failed reallocating port resources\n");
-		goto out;
-	}
+	mlx4_en_safe_replace_resources(priv, tmp);
 
 	netif_set_real_num_tx_queues(dev, priv->tx_ring_num);
 	netif_set_real_num_rx_queues(dev, priv->rx_ring_num);
@@ -1757,8 +1767,8 @@ static int mlx4_en_set_channels(struct net_device *dev,
 	}
 
 	err = mlx4_en_moderation_update(priv);
-
 out:
+	kfree(tmp);
 	mutex_unlock(&mdev->state_lock);
 	return err;
 }

drivers/net/ethernet/mellanox/mlx4/en_netdev.c

@@ -1954,7 +1954,7 @@ static int mlx4_en_close(struct net_device *dev)
 	return 0;
 }
 
-void mlx4_en_free_resources(struct mlx4_en_priv *priv)
+static void mlx4_en_free_resources(struct mlx4_en_priv *priv)
 {
 	int i;
 
@@ -1979,7 +1979,7 @@ void mlx4_en_free_resources(struct mlx4_en_priv *priv)
 
 }
 
-int mlx4_en_alloc_resources(struct mlx4_en_priv *priv)
+static int mlx4_en_alloc_resources(struct mlx4_en_priv *priv)
 {
 	struct mlx4_en_port_profile *prof = priv->prof;
 	int i;
@@ -2044,6 +2044,77 @@ static void mlx4_en_shutdown(struct net_device *dev)
 	rtnl_unlock();
 }
 
+static int mlx4_en_copy_priv(struct mlx4_en_priv *dst,
+			     struct mlx4_en_priv *src,
+			     struct mlx4_en_port_profile *prof)
+{
+	memcpy(&dst->hwtstamp_config, &prof->hwtstamp_config,
+	       sizeof(dst->hwtstamp_config));
+	dst->num_tx_rings_p_up = src->mdev->profile.num_tx_rings_p_up;
+	dst->tx_ring_num = prof->tx_ring_num;
+	dst->rx_ring_num = prof->rx_ring_num;
+	dst->flags = prof->flags;
+	dst->mdev = src->mdev;
+	dst->port = src->port;
+	dst->dev = src->dev;
+	dst->prof = prof;
+	dst->stride = roundup_pow_of_two(sizeof(struct mlx4_en_rx_desc) +
+					 DS_SIZE * MLX4_EN_MAX_RX_FRAGS);
+
+	dst->tx_ring = kzalloc(sizeof(struct mlx4_en_tx_ring *) * MAX_TX_RINGS,
+				GFP_KERNEL);
+	if (!dst->tx_ring)
+		return -ENOMEM;
+
+	dst->tx_cq = kzalloc(sizeof(struct mlx4_en_cq *) * MAX_TX_RINGS,
+			      GFP_KERNEL);
+	if (!dst->tx_cq) {
+		kfree(dst->tx_ring);
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+static void mlx4_en_update_priv(struct mlx4_en_priv *dst,
+				struct mlx4_en_priv *src)
+{
+	memcpy(dst->rx_ring, src->rx_ring,
+	       sizeof(struct mlx4_en_rx_ring *) * src->rx_ring_num);
+	memcpy(dst->rx_cq, src->rx_cq,
+	       sizeof(struct mlx4_en_cq *) * src->rx_ring_num);
+	memcpy(&dst->hwtstamp_config, &src->hwtstamp_config,
+	       sizeof(dst->hwtstamp_config));
+	dst->tx_ring_num = src->tx_ring_num;
+	dst->rx_ring_num = src->rx_ring_num;
+	dst->tx_ring = src->tx_ring;
+	dst->tx_cq = src->tx_cq;
+	memcpy(dst->prof, src->prof, sizeof(struct mlx4_en_port_profile));
+}
+
+int mlx4_en_try_alloc_resources(struct mlx4_en_priv *priv,
+				struct mlx4_en_priv *tmp,
+				struct mlx4_en_port_profile *prof)
+{
+	mlx4_en_copy_priv(tmp, priv, prof);
+
+	if (mlx4_en_alloc_resources(tmp)) {
+		en_warn(priv,
+			"%s: Resource allocation failed, using previous configuration\n",
+			__func__);
+		kfree(tmp->tx_ring);
+		kfree(tmp->tx_cq);
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+void mlx4_en_safe_replace_resources(struct mlx4_en_priv *priv,
+				    struct mlx4_en_priv *tmp)
+{
+	mlx4_en_free_resources(priv);
+	mlx4_en_update_priv(priv, tmp);
+}
+
 void mlx4_en_destroy_netdev(struct net_device *dev)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
@@ -3128,6 +3199,8 @@ int mlx4_en_reset_config(struct net_device *dev,
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_en_dev *mdev = priv->mdev;
+	struct mlx4_en_port_profile new_prof;
+	struct mlx4_en_priv *tmp;
 	int port_up = 0;
 	int err = 0;
 
@@ -3144,19 +3217,29 @@ int mlx4_en_reset_config(struct net_device *dev,
 		return -EINVAL;
 	}
 
+	tmp = kzalloc(sizeof(*tmp), GFP_KERNEL);
+	if (!tmp)
+		return -ENOMEM;
+
 	mutex_lock(&mdev->state_lock);
+
+	memcpy(&new_prof, priv->prof, sizeof(struct mlx4_en_port_profile));
+	memcpy(&new_prof.hwtstamp_config, &ts_config, sizeof(ts_config));
+
+	err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof);
+	if (err)
+		goto out;
+
 	if (priv->port_up) {
 		port_up = 1;
 		mlx4_en_stop_port(dev, 1);
 	}
 
-	mlx4_en_free_resources(priv);
-
 	en_warn(priv, "Changing device configuration rx filter(%x) rx vlan(%x)\n",
-		ts_config.rx_filter, !!(features & NETIF_F_HW_VLAN_CTAG_RX));
+		ts_config.rx_filter,
+		!!(features & NETIF_F_HW_VLAN_CTAG_RX));
 
-	priv->hwtstamp_config.tx_type = ts_config.tx_type;
-	priv->hwtstamp_config.rx_filter = ts_config.rx_filter;
+	mlx4_en_safe_replace_resources(priv, tmp);
 
 	if (DEV_FEATURE_CHANGED(dev, features, NETIF_F_HW_VLAN_CTAG_RX)) {
 		if (features & NETIF_F_HW_VLAN_CTAG_RX)
@@ -3190,11 +3273,6 @@ int mlx4_en_reset_config(struct net_device *dev,
 		dev->features &= ~NETIF_F_HW_VLAN_CTAG_RX;
 	}
 
-	err = mlx4_en_alloc_resources(priv);
-	if (err) {
-		en_err(priv, "Failed reallocating port resources\n");
-		goto out;
-	}
 	if (port_up) {
 		err = mlx4_en_start_port(dev);
 		if (err)
@@ -3203,6 +3281,8 @@ int mlx4_en_reset_config(struct net_device *dev,
 
 out:
 	mutex_unlock(&mdev->state_lock);
-	netdev_features_change(dev);
+	kfree(tmp);
+	if (!err)
+		netdev_features_change(dev);
 	return err;
 }

drivers/net/ethernet/mellanox/mlx4/mlx4_en.h

@@ -353,12 +353,14 @@ struct mlx4_en_port_profile {
 	u32 rx_ring_num;
 	u32 tx_ring_size;
 	u32 rx_ring_size;
+	u8 num_tx_rings_p_up;
 	u8 rx_pause;
 	u8 rx_ppp;
 	u8 tx_pause;
 	u8 tx_ppp;
 	int rss_rings;
 	int inline_thold;
+	struct hwtstamp_config hwtstamp_config;
 };
 
 struct mlx4_en_profile {
@@ -623,8 +625,11 @@ void mlx4_en_set_stats_bitmap(struct mlx4_dev *dev,
 			      u8 rx_ppp, u8 rx_pause,
 			      u8 tx_ppp, u8 tx_pause);
 
-void mlx4_en_free_resources(struct mlx4_en_priv *priv);
-int mlx4_en_alloc_resources(struct mlx4_en_priv *priv);
+int mlx4_en_try_alloc_resources(struct mlx4_en_priv *priv,
+				struct mlx4_en_priv *tmp,
+				struct mlx4_en_port_profile *prof);
+void mlx4_en_safe_replace_resources(struct mlx4_en_priv *priv,
+				    struct mlx4_en_priv *tmp);
 
 int mlx4_en_create_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq **pcq,
 		      int entries, int ring, enum cq_type mode, int node);