drivers: net: turn on XDP features

A summary of the flags being set for various drivers is given below.
Note that XDP_F_REDIRECT_TARGET and XDP_F_FRAG_TARGET are features
that can be turned off and on at runtime. This means that these flags
may be set and unset under RTNL lock protection by the driver. Hence,
READ_ONCE must be used by code loading the flag value.

Also, these flags are not used for synchronization against the availability
of XDP resources on a device. It is merely a hint, and hence the read
may race with the actual teardown of XDP resources on the device. This
may change in the future, e.g. operations taking a reference on the XDP
resources of the driver, and in turn inhibiting turning off this flag.
However, for now, it can only be used as a hint to check whether device
supports becoming a redirection target.

Turn 'hw-offload' feature flag on for:
 - netronome (nfp)
 - netdevsim.

Turn 'native' and 'zerocopy' features flags on for:
 - intel (i40e, ice, ixgbe, igc)
 - mellanox (mlx5).
 - stmmac
 - netronome (nfp)

Turn 'native' features flags on for:
 - amazon (ena)
 - broadcom (bnxt)
 - freescale (dpaa, dpaa2, enetc)
 - funeth
 - intel (igb)
 - marvell (mvneta, mvpp2, octeontx2)
 - mellanox (mlx4)
 - mtk_eth_soc
 - qlogic (qede)
 - sfc
 - socionext (netsec)
 - ti (cpsw)
 - tap
 - tsnep
 - veth
 - xen
 - virtio_net.

Turn 'basic' (tx, pass, aborted and drop) features flags on for:
 - netronome (nfp)
 - cavium (thunder)
 - hyperv.

Turn 'redirect_target' feature flag on for:
 - amanzon (ena)
 - broadcom (bnxt)
 - freescale (dpaa, dpaa2)
 - intel (i40e, ice, igb, ixgbe)
 - ti (cpsw)
 - marvell (mvneta, mvpp2)
 - sfc
 - socionext (netsec)
 - qlogic (qede)
 - mellanox (mlx5)
 - tap
 - veth
 - virtio_net
 - xen

Reviewed-by: Gerhard Engleder <gerhard@engleder-embedded.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Co-developed-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Co-developed-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Marek Majtyka <alardam@gmail.com>
Link: https://lore.kernel.org/r/3eca9fafb308462f7edb1f58e451d59209aa07eb.1675245258.git.lorenzo@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

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

@@ -597,7 +597,9 @@ static int ena_xdp_set(struct net_device *netdev, struct netdev_bpf *bpf)
 				if (rc)
 					return rc;
 			}
+			xdp_features_set_redirect_target(netdev, false);
 		} else if (old_bpf_prog) {
+			xdp_features_clear_redirect_target(netdev);
 			rc = ena_destroy_and_free_all_xdp_queues(adapter);
 			if (rc)
 				return rc;
@@ -4103,6 +4105,8 @@ 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;

drivers/net/ethernet/aquantia/atlantic/aq_nic.c

@@ -384,6 +384,11 @@ void aq_nic_ndev_init(struct aq_nic_s *self)
 	self->ndev->mtu = aq_nic_cfg->mtu - ETH_HLEN;
 	self->ndev->max_mtu = aq_hw_caps->mtu - ETH_FCS_LEN - ETH_HLEN;
 
+	self->ndev->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;
 }
 
 void aq_nic_set_tx_ring(struct aq_nic_s *self, unsigned int idx,

drivers/net/ethernet/broadcom/bnxt/bnxt.c

@@ -13686,6 +13686,9 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	netif_set_tso_max_size(dev, GSO_MAX_SIZE);
 
+	dev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+			    NETDEV_XDP_ACT_RX_SG;
+
 #ifdef CONFIG_BNXT_SRIOV
 	init_waitqueue_head(&bp->sriov_cfg_wait);
 #endif

drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c

@@ -422,9 +422,11 @@ static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *prog)
 
 	if (prog) {
 		bnxt_set_rx_skb_mode(bp, true);
+		xdp_features_set_redirect_target(dev, true);
 	} else {
 		int rx, tx;
 
+		xdp_features_clear_redirect_target(dev);
 		bnxt_set_rx_skb_mode(bp, false);
 		bnxt_get_max_rings(bp, &rx, &tx, true);
 		if (rx > 1) {

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

@@ -2218,6 +2218,8 @@ 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;
+
 	/* MTU range: 64 - 9200 */
 	netdev->min_mtu = NIC_HW_MIN_FRS;
 	netdev->max_mtu = NIC_HW_MAX_FRS;

drivers/net/ethernet/engleder/tsnep_main.c

@@ -1926,6 +1926,10 @@ static int tsnep_probe(struct platform_device *pdev)
 	netdev->features = NETIF_F_SG;
 	netdev->hw_features = netdev->features | NETIF_F_LOOPBACK;
 
+	netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+			       NETDEV_XDP_ACT_NDO_XMIT |
+			       NETDEV_XDP_ACT_NDO_XMIT_SG;
+
 	/* carrier off reporting is important to ethtool even BEFORE open */
 	netif_carrier_off(netdev);
 

drivers/net/ethernet/freescale/dpaa/dpaa_eth.c

@@ -244,6 +244,10 @@ static int dpaa_netdev_init(struct net_device *net_dev,
 	net_dev->features |= net_dev->hw_features;
 	net_dev->vlan_features = net_dev->features;
 
+	net_dev->xdp_features = NETDEV_XDP_ACT_BASIC |
+				NETDEV_XDP_ACT_REDIRECT |
+				NETDEV_XDP_ACT_NDO_XMIT;
+
 	if (is_valid_ether_addr(mac_addr)) {
 		memcpy(net_dev->perm_addr, mac_addr, net_dev->addr_len);
 		eth_hw_addr_set(net_dev, mac_addr);

drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c

@@ -4596,6 +4596,10 @@ static int dpaa2_eth_netdev_init(struct net_device *net_dev)
 			    NETIF_F_LLTX | NETIF_F_HW_TC | NETIF_F_TSO;
 	net_dev->gso_max_segs = DPAA2_ETH_ENQUEUE_MAX_FDS;
 	net_dev->hw_features = net_dev->features;
+	net_dev->xdp_features = NETDEV_XDP_ACT_BASIC |
+				NETDEV_XDP_ACT_REDIRECT |
+				NETDEV_XDP_ACT_XSK_ZEROCOPY |
+				NETDEV_XDP_ACT_NDO_XMIT;
 
 	if (priv->dpni_attrs.vlan_filter_entries)
 		net_dev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER;

drivers/net/ethernet/freescale/enetc/enetc_pf.c

@@ -807,6 +807,9 @@ static void enetc_pf_netdev_setup(struct enetc_si *si, struct net_device *ndev,
 		ndev->hw_features |= NETIF_F_RXHASH;
 
 	ndev->priv_flags |= IFF_UNICAST_FLT;
+	ndev->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;
 
 	if (si->hw_features & ENETC_SI_F_PSFP && !enetc_psfp_enable(priv)) {
 		priv->active_offloads |= ENETC_F_QCI;

drivers/net/ethernet/fungible/funeth/funeth_main.c

@@ -1160,6 +1160,11 @@ static int fun_xdp_setup(struct net_device *dev, struct netdev_bpf *xdp)
 			WRITE_ONCE(rxqs[i]->xdp_prog, prog);
 	}
 
+	if (prog)
+		xdp_features_set_redirect_target(dev, true);
+	else
+		xdp_features_clear_redirect_target(dev);
+
 	dev->max_mtu = prog ? XDP_MAX_MTU : FUN_MAX_MTU;
 	old_prog = xchg(&fp->xdp_prog, prog);
 	if (old_prog)
@@ -1765,6 +1770,7 @@ static int fun_create_netdev(struct fun_ethdev *ed, unsigned int portid)
 	netdev->vlan_features = netdev->features & VLAN_FEAT;
 	netdev->mpls_features = netdev->vlan_features;
 	netdev->hw_enc_features = netdev->hw_features;
+	netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT;
 
 	netdev->min_mtu = ETH_MIN_MTU;
 	netdev->max_mtu = FUN_MAX_MTU;

drivers/net/ethernet/intel/i40e/i40e_main.c

@@ -13339,9 +13339,11 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi, struct bpf_prog *prog,
 	old_prog = xchg(&vsi->xdp_prog, prog);
 
 	if (need_reset) {
-		if (!prog)
+		if (!prog) {
+			xdp_features_clear_redirect_target(vsi->netdev);
 			/* Wait until ndo_xsk_wakeup completes. */
 			synchronize_rcu();
+		}
 		i40e_reset_and_rebuild(pf, true, true);
 	}
 
@@ -13362,11 +13364,13 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi, struct bpf_prog *prog,
 	/* Kick start the NAPI context if there is an AF_XDP socket open
 	 * on that queue id. This so that receiving will start.
 	 */
-	if (need_reset && prog)
+	if (need_reset && prog) {
 		for (i = 0; i < vsi->num_queue_pairs; i++)
 			if (vsi->xdp_rings[i]->xsk_pool)
 				(void)i40e_xsk_wakeup(vsi->netdev, i,
 						      XDP_WAKEUP_RX);
+		xdp_features_set_redirect_target(vsi->netdev, true);
+	}
 
 	return 0;
 }
@@ -13783,6 +13787,8 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
 	netdev->hw_enc_features |= NETIF_F_TSO_MANGLEID;
 
 	netdev->features &= ~NETIF_F_HW_TC;
+	netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+			       NETDEV_XDP_ACT_XSK_ZEROCOPY;
 
 	if (vsi->type == I40E_VSI_MAIN) {
 		SET_NETDEV_DEV(netdev, &pf->pdev->dev);

drivers/net/ethernet/intel/ice/ice_main.c

@@ -22,6 +22,7 @@
 #include "ice_eswitch.h"
 #include "ice_tc_lib.h"
 #include "ice_vsi_vlan_ops.h"
+#include <net/xdp_sock_drv.h>
 
 #define DRV_SUMMARY	"Intel(R) Ethernet Connection E800 Series Linux Driver"
 static const char ice_driver_string[] = DRV_SUMMARY;
@@ -2912,11 +2913,13 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog,
 			if (xdp_ring_err)
 				NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Tx resources failed");
 		}
+		xdp_features_set_redirect_target(vsi->netdev, false);
 		/* reallocate Rx queues that are used for zero-copy */
 		xdp_ring_err = ice_realloc_zc_buf(vsi, true);
 		if (xdp_ring_err)
 			NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Rx resources failed");
 	} else if (ice_is_xdp_ena_vsi(vsi) && !prog) {
+		xdp_features_clear_redirect_target(vsi->netdev);
 		xdp_ring_err = ice_destroy_xdp_rings(vsi);
 		if (xdp_ring_err)
 			NL_SET_ERR_MSG_MOD(extack, "Freeing XDP Tx resources failed");
@@ -3459,6 +3462,8 @@ static int ice_cfg_netdev(struct ice_vsi *vsi)
 	np->vsi = vsi;
 
 	ice_set_netdev_features(netdev);
+	netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+			       NETDEV_XDP_ACT_XSK_ZEROCOPY;
 
 	ice_set_ops(netdev);
 

drivers/net/ethernet/intel/igb/igb_main.c

@@ -2871,8 +2871,14 @@ static int igb_xdp_setup(struct net_device *dev, struct netdev_bpf *bpf)
 		bpf_prog_put(old_prog);
 
 	/* bpf is just replaced, RXQ and MTU are already setup */
-	if (!need_reset)
+	if (!need_reset) {
 		return 0;
+	} else {
+		if (prog)
+			xdp_features_set_redirect_target(dev, true);
+		else
+			xdp_features_clear_redirect_target(dev);
+	}
 
 	if (running)
 		igb_open(dev);
@@ -3317,6 +3323,7 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	netdev->priv_flags |= IFF_SUPP_NOFCS;
 
 	netdev->priv_flags |= IFF_UNICAST_FLT;
+	netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT;
 
 	/* MTU range: 68 - 9216 */
 	netdev->min_mtu = ETH_MIN_MTU;

drivers/net/ethernet/intel/igc/igc_main.c

@@ -6533,6 +6533,9 @@ static int igc_probe(struct pci_dev *pdev,
 	netdev->mpls_features |= NETIF_F_HW_CSUM;
 	netdev->hw_enc_features |= netdev->vlan_features;
 
+	netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+			       NETDEV_XDP_ACT_XSK_ZEROCOPY;
+
 	/* MTU range: 68 - 9216 */
 	netdev->min_mtu = ETH_MIN_MTU;
 	netdev->max_mtu = MAX_STD_JUMBO_FRAME_SIZE;

drivers/net/ethernet/intel/igc/igc_xdp.c

@@ -29,6 +29,11 @@ int igc_xdp_set_prog(struct igc_adapter *adapter, struct bpf_prog *prog,
 	if (old_prog)
 		bpf_prog_put(old_prog);
 
+	if (prog)
+		xdp_features_set_redirect_target(dev, true);
+	else
+		xdp_features_clear_redirect_target(dev);
+
 	if (if_running)
 		igc_open(dev);
 

drivers/net/ethernet/intel/ixgbe/ixgbe_main.c

@@ -10301,6 +10301,8 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog)
 
 		if (err)
 			return -EINVAL;
+		if (!prog)
+			xdp_features_clear_redirect_target(dev);
 	} else {
 		for (i = 0; i < adapter->num_rx_queues; i++) {
 			WRITE_ONCE(adapter->rx_ring[i]->xdp_prog,
@@ -10321,6 +10323,7 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog)
 			if (adapter->xdp_ring[i]->xsk_pool)
 				(void)ixgbe_xsk_wakeup(adapter->netdev, i,
 						       XDP_WAKEUP_RX);
+		xdp_features_set_redirect_target(dev, true);
 	}
 
 	return 0;
@@ -11018,6 +11021,9 @@ skip_sriov:
 	netdev->priv_flags |= IFF_UNICAST_FLT;
 	netdev->priv_flags |= IFF_SUPP_NOFCS;
 
+	netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+			       NETDEV_XDP_ACT_XSK_ZEROCOPY;
+
 	/* MTU range: 68 - 9710 */
 	netdev->min_mtu = ETH_MIN_MTU;
 	netdev->max_mtu = IXGBE_MAX_JUMBO_FRAME_SIZE - (ETH_HLEN + ETH_FCS_LEN);

drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c

@@ -4634,6 +4634,7 @@ static int ixgbevf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 			    NETIF_F_HW_VLAN_CTAG_TX;
 
 	netdev->priv_flags |= IFF_UNICAST_FLT;
+	netdev->xdp_features = NETDEV_XDP_ACT_BASIC;
 
 	/* MTU range: 68 - 1504 or 9710 */
 	netdev->min_mtu = ETH_MIN_MTU;

drivers/net/ethernet/marvell/mvneta.c

@@ -5612,6 +5612,9 @@ static int mvneta_probe(struct platform_device *pdev)
 			NETIF_F_TSO | NETIF_F_RXCSUM;
 	dev->hw_features |= dev->features;
 	dev->vlan_features |= dev->features;
+	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;
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 	netif_set_tso_max_segs(dev, MVNETA_MAX_TSO_SEGS);
 

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

@@ -6866,6 +6866,10 @@ static int mvpp2_port_probe(struct platform_device *pdev,
 
 	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/marvell/octeontx2/nic/otx2_pf.c

@@ -2512,10 +2512,13 @@ static int otx2_xdp_setup(struct otx2_nic *pf, struct bpf_prog *prog)
 	/* Network stack and XDP shared same rx queues.
 	 * Use separate tx queues for XDP and network stack.
 	 */
-	if (pf->xdp_prog)
+	if (pf->xdp_prog) {
 		pf->hw.xdp_queues = pf->hw.rx_queues;
-	else
+		xdp_features_set_redirect_target(dev, false);
+	} else {
 		pf->hw.xdp_queues = 0;
+		xdp_features_clear_redirect_target(dev);
+	}
 
 	pf->hw.tot_tx_queues += pf->hw.xdp_queues;
 
@@ -2878,6 +2881,7 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	netdev->watchdog_timeo = OTX2_TX_TIMEOUT;
 
 	netdev->netdev_ops = &otx2_netdev_ops;
+	netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT;
 
 	netdev->min_mtu = OTX2_MIN_MTU;
 	netdev->max_mtu = otx2_get_max_mtu(pf);