net/mlx5e: XDP, fix redirect resources availability check

Currently mlx5 driver creates xdp redirect hw queues unconditionally on
netdevice open, This is great until someone starts redirecting XDP traffic
via ndo_xdp_xmit on mlx5 device and changes the device configuration at
the same time, this might cause crashes, since the other device's napi
is not aware of the mlx5 state change (resources un-availability).

To fix this we must synchronize with other devices napi's on the system.
Added a new flag under mlx5e_priv to determine XDP TX resources are
available, set/clear it up when necessary and use synchronize_rcu()
when the flag is turned off, so other napi's are in-sync with it, before
we actually cleanup the hw resources.

The flag is tested prior to committing to transmit on mlx5e_xdp_xmit, and
it is sufficient to determine if it safe to transmit or not. The other
two internal flags (MLX5E_STATE_OPENED and MLX5E_SQ_STATE_ENABLED) become
unnecessary. Thus, they are removed from data path.

Fixes: 58b99ee3e3eb ("net/mlx5e: Add support for XDP_REDIRECT in device-out side")
Reported-by: Toke Høiland-Jørgensen <toke@redhat.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

4 files changed, 22 insertions, 4 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 8fa8fdd30b85..448a92561567 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -657,6 +657,7 @@ struct mlx5e_channel_stats {
 enum {
 	MLX5E_STATE_OPENED,
 	MLX5E_STATE_DESTROYING,
+	MLX5E_STATE_XDP_TX_ENABLED,
 };
 
 struct mlx5e_rqt {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 3740177eed09..03b2a9f9c589 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -365,7 +365,8 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 	int sq_num;
 	int i;
 
-	if (unlikely(!test_bit(MLX5E_STATE_OPENED, &priv->state)))
+	/* this flag is sufficient, no need to test internal sq state */
+	if (unlikely(!mlx5e_xdp_tx_is_enabled(priv)))
 		return -ENETDOWN;
 
 	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
@@ -378,9 +379,6 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 
 	sq = &priv->channels.c[sq_num]->xdpsq;
 
-	if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state)))
-		return -ENETDOWN;
-
 	for (i = 0; i < n; i++) {
 		struct xdp_frame *xdpf = frames[i];
 		struct mlx5e_xdp_info xdpi;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
index 3a67cb3cd179..ee27a7c8cd87 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
@@ -50,6 +50,23 @@ void mlx5e_xdp_rx_poll_complete(struct mlx5e_rq *rq);
 int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 		   u32 flags);
 
+static inline void mlx5e_xdp_tx_enable(struct mlx5e_priv *priv)
+{
+	set_bit(MLX5E_STATE_XDP_TX_ENABLED, &priv->state);
+}
+
+static inline void mlx5e_xdp_tx_disable(struct mlx5e_priv *priv)
+{
+	clear_bit(MLX5E_STATE_XDP_TX_ENABLED, &priv->state);
+	/* let other device's napi(s) see our new state */
+	synchronize_rcu();
+}
+
+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_xmit_xdp_doorbell(struct mlx5e_xdpsq *sq)
 {
 	if (sq->doorbell_cseg) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 01819e5c9975..93e50ccd44c3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2938,6 +2938,7 @@ void mlx5e_activate_priv_channels(struct mlx5e_priv *priv)
 
 	mlx5e_build_tx2sq_maps(priv);
 	mlx5e_activate_channels(&priv->channels);
+	mlx5e_xdp_tx_enable(priv);
 	netif_tx_start_all_queues(priv->netdev);
 
 	if (mlx5e_is_vport_rep(priv))
@@ -2959,6 +2960,7 @@ void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv)
 	 */
 	netif_tx_stop_all_queues(priv->netdev);
 	netif_tx_disable(priv->netdev);
+	mlx5e_xdp_tx_disable(priv);
 	mlx5e_deactivate_channels(&priv->channels);
 }