net/mlx5e: Fix concurrency issues between config flow and XSK

After disabling resources necessary for XSK (the XDP program, channels,
XSK queues), use synchronize_rcu to wait until the XSK wakeup function
finishes, before freeing the resources.

Suspend XSK wakeups during switching channels. If the XDP program is
being removed, synchronize_rcu before closing the old channels to allow
XSK wakeup to complete.

Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20191217162023.16011-3-maximmi@mellanox.com

5 files changed, 13 insertions, 33 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 2c16add0b642..9c8427698238 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -760,7 +760,7 @@ enum {
 	MLX5E_STATE_OPENED,
 	MLX5E_STATE_DESTROYING,
 	MLX5E_STATE_XDP_TX_ENABLED,
-	MLX5E_STATE_XDP_OPEN,
+	MLX5E_STATE_XDP_ACTIVE,
 };
 
 struct mlx5e_rqt {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
index 36ac1e3816b9..d7587f40ecae 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
@@ -75,12 +75,18 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 static inline void mlx5e_xdp_tx_enable(struct mlx5e_priv *priv)
 {
 	set_bit(MLX5E_STATE_XDP_TX_ENABLED, &priv->state);
+
+	if (priv->channels.params.xdp_prog)
+		set_bit(MLX5E_STATE_XDP_ACTIVE, &priv->state);
 }
 
 static inline void mlx5e_xdp_tx_disable(struct mlx5e_priv *priv)
 {
+	if (priv->channels.params.xdp_prog)
+		clear_bit(MLX5E_STATE_XDP_ACTIVE, &priv->state);
+
 	clear_bit(MLX5E_STATE_XDP_TX_ENABLED, &priv->state);
-	/* let other device's napi(s) see our new state */
+	/* Let other device's napi(s) and XSK wakeups see our new state. */
 	synchronize_rcu();
 }
 
@@ -89,19 +95,9 @@ static inline bool mlx5e_xdp_tx_is_enabled(struct mlx5e_priv *priv)
 	return test_bit(MLX5E_STATE_XDP_TX_ENABLED, &priv->state);
 }
 
-static inline void mlx5e_xdp_set_open(struct mlx5e_priv *priv)
-{
-	set_bit(MLX5E_STATE_XDP_OPEN, &priv->state);
-}
-
-static inline void mlx5e_xdp_set_closed(struct mlx5e_priv *priv)
-{
-	clear_bit(MLX5E_STATE_XDP_OPEN, &priv->state);
-}
-
-static inline bool mlx5e_xdp_is_open(struct mlx5e_priv *priv)
+static inline bool mlx5e_xdp_is_active(struct mlx5e_priv *priv)
 {
-	return test_bit(MLX5E_STATE_XDP_OPEN, &priv->state);
+	return test_bit(MLX5E_STATE_XDP_ACTIVE, &priv->state);
 }
 
 static inline void mlx5e_xmit_xdp_doorbell(struct mlx5e_xdpsq *sq)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
index 631af8dee517..c28cbae42331 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
@@ -144,6 +144,7 @@ void mlx5e_close_xsk(struct mlx5e_channel *c)
 {
 	clear_bit(MLX5E_CHANNEL_STATE_XSK, c->state);
 	napi_synchronize(&c->napi);
+	synchronize_rcu(); /* Sync with the XSK wakeup. */
 
 	mlx5e_close_rq(&c->xskrq);
 	mlx5e_close_cq(&c->xskrq.cq);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
index 87827477d38c..fe2d596cb361 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
@@ -14,7 +14,7 @@ int mlx5e_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags)
 	struct mlx5e_channel *c;
 	u16 ix;
 
-	if (unlikely(!mlx5e_xdp_is_open(priv)))
+	if (unlikely(!mlx5e_xdp_is_active(priv)))
 		return -ENETDOWN;
 
 	if (unlikely(!mlx5e_qid_get_ch_if_in_group(params, qid, MLX5E_RQ_GROUP_XSK, &ix)))
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 4980e80a5e85..4997b8a51994 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3000,12 +3000,9 @@ void mlx5e_timestamp_init(struct mlx5e_priv *priv)
 int mlx5e_open_locked(struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
-	bool is_xdp = priv->channels.params.xdp_prog;
 	int err;
 
 	set_bit(MLX5E_STATE_OPENED, &priv->state);
-	if (is_xdp)
-		mlx5e_xdp_set_open(priv);
 
 	err = mlx5e_open_channels(priv, &priv->channels);
 	if (err)
@@ -3020,8 +3017,6 @@ int mlx5e_open_locked(struct net_device *netdev)
 	return 0;
 
 err_clear_state_opened_flag:
-	if (is_xdp)
-		mlx5e_xdp_set_closed(priv);
 	clear_bit(MLX5E_STATE_OPENED, &priv->state);
 	return err;
 }
@@ -3053,8 +3048,6 @@ int mlx5e_close_locked(struct net_device *netdev)
 	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
 		return 0;
 
-	if (priv->channels.params.xdp_prog)
-		mlx5e_xdp_set_closed(priv);
 	clear_bit(MLX5E_STATE_OPENED, &priv->state);
 
 	netif_carrier_off(priv->netdev);
@@ -4371,16 +4364,6 @@ static int mlx5e_xdp_allowed(struct mlx5e_priv *priv, struct bpf_prog *prog)
 	return 0;
 }
 
-static int mlx5e_xdp_update_state(struct mlx5e_priv *priv)
-{
-	if (priv->channels.params.xdp_prog)
-		mlx5e_xdp_set_open(priv);
-	else
-		mlx5e_xdp_set_closed(priv);
-
-	return 0;
-}
-
 static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
@@ -4415,7 +4398,7 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
 		mlx5e_set_rq_type(priv->mdev, &new_channels.params);
 		old_prog = priv->channels.params.xdp_prog;
 
-		err = mlx5e_safe_switch_channels(priv, &new_channels, mlx5e_xdp_update_state);
+		err = mlx5e_safe_switch_channels(priv, &new_channels, NULL);
 		if (err)
 			goto unlock;
 	} else {