Merge branch 'update-xdp_features-flag-according-to-nic-re-configuration'

Lorenzo Bianconi says:

====================
update xdp_features flag according to NIC re-configuration

Changes since v1:
- rebase on top of net tree
- remove NETDEV_XDP_ACT_NDO_XMIT_SG support in mlx5e driver
- always enable NETDEV_XDP_ACT_NDO_XMIT support in mlx5e driver
====================

Link: https://lore.kernel.org/r/cover.1678364612.git.lorenzo@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

Documentation/netlink/specs/netdev.yaml

@@ -9,6 +9,7 @@ definitions:
   -
     type: flags
     name: xdp-act
+    render-max: true
     entries:
       -
         name: basic

drivers/net/ethernet/amazon/ena/ena_ethtool.c

@@ -850,11 +850,20 @@ static int ena_set_channels(struct net_device *netdev,
 	struct ena_adapter *adapter = netdev_priv(netdev);
 	u32 count = channels->combined_count;
 	/* The check for max value is already done in ethtool */
-	if (count < ENA_MIN_NUM_IO_QUEUES ||
+	if (count < ENA_MIN_NUM_IO_QUEUES)
-	    (ena_xdp_present(adapter) &&
-	    !ena_xdp_legal_queue_count(adapter, count)))
 		return -EINVAL;
 
+	if (!ena_xdp_legal_queue_count(adapter, count)) {
+		if (ena_xdp_present(adapter))
+			return -EINVAL;
+
+		xdp_clear_features_flag(netdev);
+	} else {
+		xdp_set_features_flag(netdev,
+				      NETDEV_XDP_ACT_BASIC |
+				      NETDEV_XDP_ACT_REDIRECT);
+	}
+
 	return ena_update_queue_count(adapter, count);
 }
 

drivers/net/ethernet/amazon/ena/ena_netdev.c

@@ -4105,8 +4105,6 @@ static void ena_set_conf_feat_params(struct ena_adapter *adapter,
 	/* Set offload features */
 	ena_set_dev_offloads(feat, netdev);
 
-	netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT;
-
 	adapter->max_mtu = feat->dev_attr.max_mtu;
 	netdev->max_mtu = adapter->max_mtu;
 	netdev->min_mtu = ENA_MIN_MTU;
@@ -4393,6 +4391,10 @@ static int ena_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	ena_config_debug_area(adapter);
 
+	if (ena_xdp_legal_queue_count(adapter, adapter->num_io_queues))
+		netdev->xdp_features = NETDEV_XDP_ACT_BASIC |
+				       NETDEV_XDP_ACT_REDIRECT;
+
 	memcpy(adapter->netdev->perm_addr, adapter->mac_addr, netdev->addr_len);
 
 	netif_carrier_off(netdev);

drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c

@@ -735,12 +735,17 @@ static int nicvf_set_channels(struct net_device *dev,
 	if (channel->tx_count > nic->max_queues)
 		return -EINVAL;
 
-	if (nic->xdp_prog &&
+	if (channel->tx_count + channel->rx_count > nic->max_queues) {
-	    ((channel->tx_count + channel->rx_count) > nic->max_queues)) {
+		if (nic->xdp_prog) {
-		netdev_err(nic->netdev,
+			netdev_err(nic->netdev,
-			   "XDP mode, RXQs + TXQs > Max %d\n",
+				   "XDP mode, RXQs + TXQs > Max %d\n",
-			   nic->max_queues);
+				   nic->max_queues);
-		return -EINVAL;
+			return -EINVAL;
+		}
+
+		xdp_clear_features_flag(nic->netdev);
+	} else if (!pass1_silicon(nic->pdev)) {
+		xdp_set_features_flag(dev, NETDEV_XDP_ACT_BASIC);
 	}
 
 	if (if_up)

drivers/net/ethernet/cavium/thunder/nicvf_main.c

@@ -2218,7 +2218,9 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	netdev->netdev_ops = &nicvf_netdev_ops;
 	netdev->watchdog_timeo = NICVF_TX_TIMEOUT;
 
-	netdev->xdp_features = NETDEV_XDP_ACT_BASIC;
+	if (!pass1_silicon(nic->pdev) &&
+	    nic->rx_queues + nic->tx_queues <= nic->max_queues)
+		netdev->xdp_features = NETDEV_XDP_ACT_BASIC;
 
 	/* MTU range: 64 - 9200 */
 	netdev->min_mtu = NIC_HW_MIN_FRS;

drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c

@@ -4996,6 +4996,14 @@ static int mvpp2_bm_switch_buffers(struct mvpp2 *priv, bool percpu)
 
 	for (i = 0; i < priv->port_count; i++) {
 		port = priv->port_list[i];
+		if (percpu && port->ntxqs >= num_possible_cpus() * 2)
+			xdp_set_features_flag(port->dev,
+					      NETDEV_XDP_ACT_BASIC |
+					      NETDEV_XDP_ACT_REDIRECT |
+					      NETDEV_XDP_ACT_NDO_XMIT);
+		else
+			xdp_clear_features_flag(port->dev);
+
 		mvpp2_swf_bm_pool_init(port);
 		if (status[i])
 			mvpp2_open(port->dev);
@@ -6863,13 +6871,14 @@ static int mvpp2_port_probe(struct platform_device *pdev,
 
 	if (!port->priv->percpu_pools)
 		mvpp2_set_hw_csum(port, port->pool_long->id);
+	else if (port->ntxqs >= num_possible_cpus() * 2)
+		dev->xdp_features = NETDEV_XDP_ACT_BASIC |
+				    NETDEV_XDP_ACT_REDIRECT |
+				    NETDEV_XDP_ACT_NDO_XMIT;
 
 	dev->vlan_features |= features;
 	netif_set_tso_max_segs(dev, MVPP2_MAX_TSO_SEGS);
 
-	dev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
-			    NETDEV_XDP_ACT_NDO_XMIT;
-
 	dev->priv_flags |= IFF_UNICAST_FLT;
 
 	/* MTU range: 68 - 9704 */

drivers/net/ethernet/mellanox/mlx5/core/en.h

@@ -1243,6 +1243,7 @@ void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16
 void mlx5e_rx_dim_work(struct work_struct *work);
 void mlx5e_tx_dim_work(struct work_struct *work);
 
+void mlx5e_set_xdp_feature(struct net_device *netdev);
 netdev_features_t mlx5e_features_check(struct sk_buff *skb,
 				       struct net_device *netdev,
 				       netdev_features_t features);

drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c

@@ -1985,6 +1985,7 @@ static int set_pflag_rx_striding_rq(struct net_device *netdev, bool enable)
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5e_params new_params;
+	int err;
 
 	if (enable) {
 		/* Checking the regular RQ here; mlx5e_validate_xsk_param called
@@ -2005,7 +2006,14 @@ static int set_pflag_rx_striding_rq(struct net_device *netdev, bool enable)
 	MLX5E_SET_PFLAG(&new_params, MLX5E_PFLAG_RX_STRIDING_RQ, enable);
 	mlx5e_set_rq_type(mdev, &new_params);
 
-	return mlx5e_safe_switch_params(priv, &new_params, NULL, NULL, true);
+	err = mlx5e_safe_switch_params(priv, &new_params, NULL, NULL, true);
+	if (err)
+		return err;
+
+	/* update XDP supported features */
+	mlx5e_set_xdp_feature(netdev);
+
+	return 0;
 }
 
 static int set_pflag_rx_no_csum_complete(struct net_device *netdev, bool enable)

drivers/net/ethernet/mellanox/mlx5/core/en_main.c

@@ -4004,6 +4004,25 @@ static int mlx5e_handle_feature(struct net_device *netdev,
 	return 0;
 }
 
+void mlx5e_set_xdp_feature(struct net_device *netdev)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct mlx5e_params *params = &priv->channels.params;
+	xdp_features_t val;
+
+	if (params->packet_merge.type != MLX5E_PACKET_MERGE_NONE) {
+		xdp_clear_features_flag(netdev);
+		return;
+	}
+
+	val = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+	      NETDEV_XDP_ACT_XSK_ZEROCOPY |
+	      NETDEV_XDP_ACT_NDO_XMIT;
+	if (params->rq_wq_type == MLX5_WQ_TYPE_CYCLIC)
+		val |= NETDEV_XDP_ACT_RX_SG;
+	xdp_set_features_flag(netdev, val);
+}
+
 int mlx5e_set_features(struct net_device *netdev, netdev_features_t features)
 {
 	netdev_features_t oper_features = features;
@@ -4030,6 +4049,9 @@ int mlx5e_set_features(struct net_device *netdev, netdev_features_t features)
 		return -EINVAL;
 	}
 
+	/* update XDP supported features */
+	mlx5e_set_xdp_feature(netdev);
+
 	return 0;
 }
 
@@ -4761,13 +4783,6 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
 	if (old_prog)
 		bpf_prog_put(old_prog);
 
-	if (reset) {
-		if (prog)
-			xdp_features_set_redirect_target(netdev, true);
-		else
-			xdp_features_clear_redirect_target(netdev);
-	}
-
 	if (!test_bit(MLX5E_STATE_OPENED, &priv->state) || reset)
 		goto unlock;
 
@@ -5163,13 +5178,10 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 	netdev->features         |= NETIF_F_HIGHDMA;
 	netdev->features         |= NETIF_F_HW_VLAN_STAG_FILTER;
 
-	netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
-			       NETDEV_XDP_ACT_XSK_ZEROCOPY |
-			       NETDEV_XDP_ACT_RX_SG;
-
 	netdev->priv_flags       |= IFF_UNICAST_FLT;
 
 	netif_set_tso_max_size(netdev, GSO_MAX_SIZE);
+	mlx5e_set_xdp_feature(netdev);
 	mlx5e_set_netdev_dev_addr(netdev);
 	mlx5e_macsec_build_netdev(priv);
 	mlx5e_ipsec_build_netdev(priv);
@@ -5241,6 +5253,9 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev,
 		mlx5_core_err(mdev, "TLS initialization failed, %d\n", err);
 
 	mlx5e_health_create_reporters(priv);
+	/* update XDP supported features */
+	mlx5e_set_xdp_feature(netdev);
+
 	return 0;
 }
 

drivers/net/ethernet/mellanox/mlx5/core/en_rep.c

@@ -747,6 +747,9 @@ static void mlx5e_build_rep_params(struct net_device *netdev)
 	/* RQ */
 	mlx5e_build_rq_params(mdev, params);
 
+	/* update XDP supported features */
+	mlx5e_set_xdp_feature(netdev);
+
 	/* CQ moderation params */
 	params->rx_dim_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
 	mlx5e_set_rx_cq_mode_params(params, cq_period_mode);

drivers/net/veth.c

@@ -1257,6 +1257,26 @@ static int veth_enable_range_safe(struct net_device *dev, int start, int end)
 	return 0;
 }
 
+static void veth_set_xdp_features(struct net_device *dev)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+	struct net_device *peer;
+
+	peer = rcu_dereference(priv->peer);
+	if (peer && peer->real_num_tx_queues <= dev->real_num_rx_queues) {
+		xdp_features_t val = NETDEV_XDP_ACT_BASIC |
+				     NETDEV_XDP_ACT_REDIRECT |
+				     NETDEV_XDP_ACT_RX_SG;
+
+		if (priv->_xdp_prog || veth_gro_requested(dev))
+			val |= NETDEV_XDP_ACT_NDO_XMIT |
+			       NETDEV_XDP_ACT_NDO_XMIT_SG;
+		xdp_set_features_flag(dev, val);
+	} else {
+		xdp_clear_features_flag(dev);
+	}
+}
+
 static int veth_set_channels(struct net_device *dev,
 			     struct ethtool_channels *ch)
 {
@@ -1323,6 +1343,12 @@ out:
 		if (peer)
 			netif_carrier_on(peer);
 	}
+
+	/* update XDP supported features */
+	veth_set_xdp_features(dev);
+	if (peer)
+		veth_set_xdp_features(peer);
+
 	return err;
 
 revert:
@@ -1489,7 +1515,10 @@ static int veth_set_features(struct net_device *dev,
 		err = veth_napi_enable(dev);
 		if (err)
 			return err;
+
+		xdp_features_set_redirect_target(dev, true);
 	} else {
+		xdp_features_clear_redirect_target(dev);
 		veth_napi_del(dev);
 	}
 	return 0;
@@ -1570,10 +1599,15 @@ static int veth_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 			peer->hw_features &= ~NETIF_F_GSO_SOFTWARE;
 			peer->max_mtu = max_mtu;
 		}
+
+		xdp_features_set_redirect_target(dev, true);
 	}
 
 	if (old_prog) {
 		if (!prog) {
+			if (!veth_gro_requested(dev))
+				xdp_features_clear_redirect_target(dev);
+
 			if (dev->flags & IFF_UP)
 				veth_disable_xdp(dev);
 
@@ -1686,10 +1720,6 @@ static void veth_setup(struct net_device *dev)
 	dev->hw_enc_features = VETH_FEATURES;
 	dev->mpls_features = NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE;
 	netif_set_tso_max_size(dev, GSO_MAX_SIZE);
-
-	dev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
-			    NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_RX_SG |
-			    NETDEV_XDP_ACT_NDO_XMIT_SG;
 }
 
 /*
@@ -1857,6 +1887,10 @@ static int veth_newlink(struct net *src_net, struct net_device *dev,
 		goto err_queues;
 
 	veth_disable_gro(dev);
+	/* update XDP supported features */
+	veth_set_xdp_features(dev);
+	veth_set_xdp_features(peer);
+
 	return 0;
 
 err_queues:

include/net/xdp.h

@@ -428,12 +428,18 @@ MAX_XDP_METADATA_KFUNC,
 #ifdef CONFIG_NET
 u32 bpf_xdp_metadata_kfunc_id(int id);
 bool bpf_dev_bound_kfunc_id(u32 btf_id);
+void xdp_set_features_flag(struct net_device *dev, xdp_features_t val);
 void xdp_features_set_redirect_target(struct net_device *dev, bool support_sg);
 void xdp_features_clear_redirect_target(struct net_device *dev);
 #else
 static inline u32 bpf_xdp_metadata_kfunc_id(int id) { return 0; }
 static inline bool bpf_dev_bound_kfunc_id(u32 btf_id) { return false; }
 
+static inline void
+xdp_set_features_flag(struct net_device *dev, xdp_features_t val)
+{
+}
+
 static inline void
 xdp_features_set_redirect_target(struct net_device *dev, bool support_sg)
 {
@@ -445,4 +451,9 @@ xdp_features_clear_redirect_target(struct net_device *dev)
 }
 #endif
 
+static inline void xdp_clear_features_flag(struct net_device *dev)
+{
+	xdp_set_features_flag(dev, 0);
+}
+
 #endif /* __LINUX_NET_XDP_H__ */

include/uapi/linux/netdev.h

@@ -33,6 +33,8 @@ enum netdev_xdp_act {
 	NETDEV_XDP_ACT_HW_OFFLOAD = 16,
 	NETDEV_XDP_ACT_RX_SG = 32,
 	NETDEV_XDP_ACT_NDO_XMIT_SG = 64,
+
+	NETDEV_XDP_ACT_MASK = 127,
 };
 
 enum {

net/core/xdp.c

@@ -774,20 +774,32 @@ static int __init xdp_metadata_init(void)
 }
 late_initcall(xdp_metadata_init);
 
+void xdp_set_features_flag(struct net_device *dev, xdp_features_t val)
+{
+	val &= NETDEV_XDP_ACT_MASK;
+	if (dev->xdp_features == val)
+		return;
+
+	dev->xdp_features = val;
+	call_netdevice_notifiers(NETDEV_XDP_FEAT_CHANGE, dev);
+}
+EXPORT_SYMBOL_GPL(xdp_set_features_flag);
+
 void xdp_features_set_redirect_target(struct net_device *dev, bool support_sg)
 {
-	dev->xdp_features |= NETDEV_XDP_ACT_NDO_XMIT;
+	xdp_features_t val = (dev->xdp_features | NETDEV_XDP_ACT_NDO_XMIT);
-	if (support_sg)
-		dev->xdp_features |= NETDEV_XDP_ACT_NDO_XMIT_SG;
 
-	call_netdevice_notifiers(NETDEV_XDP_FEAT_CHANGE, dev);
+	if (support_sg)
+		val |= NETDEV_XDP_ACT_NDO_XMIT_SG;
+	xdp_set_features_flag(dev, val);
 }
 EXPORT_SYMBOL_GPL(xdp_features_set_redirect_target);
 
 void xdp_features_clear_redirect_target(struct net_device *dev)
 {
-	dev->xdp_features &= ~(NETDEV_XDP_ACT_NDO_XMIT |
+	xdp_features_t val = dev->xdp_features;
-			       NETDEV_XDP_ACT_NDO_XMIT_SG);
+
-	call_netdevice_notifiers(NETDEV_XDP_FEAT_CHANGE, dev);
+	val &= ~(NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_NDO_XMIT_SG);
+	xdp_set_features_flag(dev, val);
 }
 EXPORT_SYMBOL_GPL(xdp_features_clear_redirect_target);

tools/include/uapi/linux/netdev.h

@@ -33,6 +33,8 @@ enum netdev_xdp_act {
 	NETDEV_XDP_ACT_HW_OFFLOAD = 16,
 	NETDEV_XDP_ACT_RX_SG = 32,
 	NETDEV_XDP_ACT_NDO_XMIT_SG = 64,
+
+	NETDEV_XDP_ACT_MASK = 127,
 };
 
 enum {

tools/net/ynl/lib/nlspec.py

@@ -138,10 +138,8 @@ class SpecEnumSet(SpecElement):
 
     def get_mask(self):
         mask = 0
-        idx = self.yaml.get('value-start', 0)
+        for e in self.entries.values():
-        for _ in self.entries.values():
+            mask += e.user_value()
-            mask |= 1 << idx
-            idx += 1
         return mask
 
 

tools/net/ynl/ynl-gen-c.py

@@ -1931,9 +1931,14 @@ def render_uapi(family, cw):
 
             if const.get('render-max', False):
                 cw.nl()
-                max_name = c_upper(name_pfx + 'max')
+                if const['type'] == 'flags':
-                cw.p('__' + max_name + ',')
+                    max_name = c_upper(name_pfx + 'mask')
-                cw.p(max_name + ' = (__' + max_name + ' - 1)')
+                    max_val = f' = {enum.get_mask()},'
+                    cw.p(max_name + max_val)
+                else:
+                    max_name = c_upper(name_pfx + 'max')
+                    cw.p('__' + max_name + ',')
+                    cw.p(max_name + ' = (__' + max_name + ' - 1)')
             cw.block_end(line=';')
             cw.nl()
         elif const['type'] == 'const':