xdp: introduce xdp-feature support

From: Marek Majtyka <[email protected]>

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 <[email protected]>

Reviewed-by Simon Horman <[email protected]>

Acked-by Stanislav Fomichev <[email protected]>

Acked-by Jakub Kicinski <[email protected]>

Co-developed-by Kumar Kartikeya Dwivedi <[email protected]>

Signed-off-by Kumar Kartikeya Dwivedi <[email protected]>

Co-developed-by Lorenzo Bianconi <[email protected]>

Signed-off-by Lorenzo Bianconi <[email protected]>

Signed-off-by Marek Majtyka <[email protected]>

---
 drivers/net/ethernet/amazon/ena/ena_netdev.c   |  4 ++++
 .../net/ethernet/aquantia/atlantic/aq_nic.c    |  5 +++++
 drivers/net/ethernet/broadcom/bnxt/bnxt.c      |  3 +++
 drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c  |  2 ++
 .../net/ethernet/cavium/thunder/nicvf_main.c   |  2 ++
 drivers/net/ethernet/engleder/tsnep_main.c     |  4 ++++
 drivers/net/ethernet/freescale/dpaa/dpaa_eth.c |  4 ++++
 .../net/ethernet/freescale/dpaa2/dpaa2-eth.c   |  4 ++++
 .../net/ethernet/freescale/enetc/enetc_pf.c    |  3 +++
 .../net/ethernet/fungible/funeth/funeth_main.c |  6 ++++++
 drivers/net/ethernet/intel/i40e/i40e_main.c    | 10 ++++++++--
 drivers/net/ethernet/intel/ice/ice_main.c      |  5 +++++
 drivers/net/ethernet/intel/igb/igb_main.c      |  9 ++++++++-
 drivers/net/ethernet/intel/igc/igc_main.c      |  3 +++
 drivers/net/ethernet/intel/igc/igc_xdp.c       |  5 +++++
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c  |  6 ++++++
 .../net/ethernet/intel/ixgbevf/ixgbevf_main.c  |  1 +
 drivers/net/ethernet/marvell/mvneta.c          |  3 +++
 .../net/ethernet/marvell/mvpp2/mvpp2_main.c    |  4 ++++
 .../ethernet/marvell/octeontx2/nic/otx2_pf.c   |  8 ++++++--
 drivers/net/ethernet/mediatek/mtk_eth_soc.c    |  6 ++++++
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c |  2 ++
 .../net/ethernet/mellanox/mlx5/core/en_main.c  | 11 +++++++++++
 drivers/net/ethernet/microsoft/mana/mana_en.c  |  2 ++
 .../ethernet/netronome/nfp/nfp_net_common.c    |  5 +++++
 drivers/net/ethernet/qlogic/qede/qede_main.c   |  3 +++
 drivers/net/ethernet/sfc/efx.c                 |  4 ++++
 drivers/net/ethernet/sfc/siena/efx.c           |  4 ++++
 drivers/net/ethernet/socionext/netsec.c        |  3 +++
 .../net/ethernet/stmicro/stmmac/stmmac_main.c  |  2 ++
 drivers/net/ethernet/ti/cpsw.c                 |  4 ++++
 drivers/net/ethernet/ti/cpsw_new.c             |  4 ++++
 drivers/net/hyperv/netvsc_drv.c                |  2 ++
 drivers/net/netdevsim/netdev.c                 |  1 +
 drivers/net/tun.c                              |  5 +++++
 drivers/net/veth.c                             |  4 ++++
 drivers/net/virtio_net.c                       |  4 ++++
 drivers/net/xen-netfront.c                     |  2 ++
 include/net/xdp.h                              | 12 ++++++++++++
 net/core/xdp.c                                 | 18 ++++++++++++++++++
 40 files changed, 184 insertions(+), 5 deletions(-)

drivers/net/ethernet/amazon/ena/ena_netdev.c +4 -0

index e8ad5ea31aff..d3999db7c6a2 100644
@@ -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 +5 -0

index 06508eebb585..d6d6d5d37ff3 100644
@@ -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 +3 -0

index 240a7e8a7652..a1b4356dfb6c 100644
@@ -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 +2 -0

index 36d5202c0aee..5843c93b1711 100644
@@ -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 +2 -0

index f2f95493ec89..8b25313c7f6b 100644
@@ -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 +4 -0

index c3cf427a9409..6982aaa928b5 100644
@@ -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 +4 -0

index 027fff9f7db0..9318a2554056 100644
@@ -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 +4 -0

index 2e79d18fc3c7..746ccfde7255 100644
@@ -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 +3 -0

index 7facc7d5261e..6b54071d4ecc 100644
@@ -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 +6 -0

index b4cce30e526a..df86770731ad 100644
@@ -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 +8 -2

index 53d0083e35da..8a79cc18c428 100644
@@ -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 +5 -0

index fce86e8ff834..26b09e4ed0c8 100644
@@ -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;

@@ -2899,11 +2900,13 @@ 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");

@@ -3446,6 +3449,8 @@ 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 +8 -1

index 3c0c35ecea10..0e11a082f7a1 100644
@@ -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 +3 -0

index e86b15efaeb8..8b572cd2c350 100644
@@ -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 +5 -0

index aeeb34e64610..e27af72aada8 100644
@@ -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 +6 -0

index 43a44c1e1576..af4c12b6059f 100644
@@ -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 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	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 +1 -0

index ea0a230c1153..a44e4bd56142 100644
@@ -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 +3 -0

index f8925cac61e4..dc2989103a77 100644
@@ -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 +4 -0

index 4da45c5abba5..9b4ecbe4f36d 100644
@@ -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 +6 -2

index c1ea60bc2630..179433d0a54a 100644
@@ -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);

drivers/net/ethernet/mediatek/mtk_eth_soc.c +6 -0

index 801deac58bf7..ac54b6f2bb5c 100644
@@ -4447,6 +4447,12 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np)
 		register_netdevice_notifier(&mac->device_notifier);
 	}
 
+	if (mtk_page_pool_enabled(eth))
+		eth->netdev[id]->xdp_features = NETDEV_XDP_ACT_BASIC |
+						NETDEV_XDP_ACT_REDIRECT |
+						NETDEV_XDP_ACT_NDO_XMIT |
+						NETDEV_XDP_ACT_NDO_XMIT_SG;
+
 	return 0;
 
 free_netdev:

drivers/net/ethernet/mellanox/mlx4/en_netdev.c +2 -0

index af4c4858f397..e11bc0ac880e 100644
@@ -3416,6 +3416,8 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 		priv->rss_hash_fn = ETH_RSS_HASH_TOP;
 	}
 
+	dev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT;
+
 	/* MTU range: 68 - hw-specific max */
 	dev->min_mtu = ETH_MIN_MTU;
 	dev->max_mtu = priv->max_mtu;

drivers/net/ethernet/mellanox/mlx5/core/en_main.c +11 -0

index 0e87432ec6f1..e4996ef04d86 100644
@@ -4780,6 +4780,13 @@ 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;
 

@@ -5175,6 +5182,10 @@ 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);

drivers/net/ethernet/microsoft/mana/mana_en.c +2 -0

index 2f6a048dee90..6120f2b6684f 100644
@@ -2160,6 +2160,8 @@ static int mana_probe_port(struct mana_context *ac, int port_idx,
 	ndev->hw_features |= NETIF_F_RXHASH;
 	ndev->features = ndev->hw_features;
 	ndev->vlan_features = 0;
+	ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+			     NETDEV_XDP_ACT_NDO_XMIT;
 
 	err = register_netdev(ndev);
 	if (err) {

drivers/net/ethernet/netronome/nfp/nfp_net_common.c +5 -0

index 18fc9971f1c8..e4825d885560 100644
@@ -2529,10 +2529,15 @@ static void nfp_net_netdev_init(struct nfp_net *nn)
 	netdev->features &= ~NETIF_F_HW_VLAN_STAG_RX;
 	nn->dp.ctrl &= ~NFP_NET_CFG_CTRL_RXQINQ;
 
+	netdev->xdp_features = NETDEV_XDP_ACT_BASIC;
+	if (nn->app && nn->app->type->id == NFP_APP_BPF_NIC)
+		netdev->xdp_features |= NETDEV_XDP_ACT_HW_OFFLOAD;
+
 	/* Finalise the netdev setup */
 	switch (nn->dp.ops->version) {
 	case NFP_NFD_VER_NFD3:
 		netdev->netdev_ops = &nfp_nfd3_netdev_ops;
+		netdev->xdp_features |= NETDEV_XDP_ACT_XSK_ZEROCOPY;
 		break;
 	case NFP_NFD_VER_NFDK:
 		netdev->netdev_ops = &nfp_nfdk_netdev_ops;

drivers/net/ethernet/qlogic/qede/qede_main.c +3 -0

index 953f304b8588..b6d999927e86 100644
@@ -892,6 +892,9 @@ static void qede_init_ndev(struct qede_dev *edev)
 
 	ndev->hw_features = hw_features;
 
+	ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+			     NETDEV_XDP_ACT_NDO_XMIT;
+
 	/* MTU range: 46 - 9600 */
 	ndev->min_mtu = ETH_ZLEN - ETH_HLEN;
 	ndev->max_mtu = QEDE_MAX_JUMBO_PACKET_SIZE;

drivers/net/ethernet/sfc/efx.c +0 -0

index 0556542d7a6b..18ff8d8cff42 100644

drivers/net/ethernet/sfc/efx.c +0 -0

 	if (!efx->type->is_vf)
 		efx_probe_vpd_strings(efx);
 

drivers/net/ethernet/sfc/siena/efx.c +0 -0

index 60e5b7c8ccf9..a6ef21845224 100644

drivers/net/ethernet/sfc/siena/efx.c +0 -0

 	if (!efx->type->is_vf)
 		efx_probe_vpd_strings(efx);
 

drivers/net/ethernet/socionext/netsec.c +3 -0

index 9b46579b5a10..2d7347b71c41 100644
@@ -2104,6 +2104,9 @@ static int netsec_probe(struct platform_device *pdev)
 				NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
 	ndev->hw_features = ndev->features;
 
+	ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+			     NETDEV_XDP_ACT_NDO_XMIT;
+
 	priv->rx_cksum_offload_flag = true;
 
 	ret = netsec_register_mdio(priv, phy_addr);

drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +2 -0

index b7e5af58ab75..734d84263fd2 100644
@@ -7150,6 +7150,8 @@ int stmmac_dvr_probe(struct device *device,
 
 	ndev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
 			    NETIF_F_RXCSUM;
+	ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+			     NETDEV_XDP_ACT_NDO_XMIT;
 
 	ret = stmmac_tc_init(priv, priv);
 	if (!ret) {

drivers/net/ethernet/ti/cpsw.c +4 -0

index 13c9c2d6b79b..37f0b62ec5d6 100644
@@ -1458,6 +1458,8 @@ static int cpsw_probe_dual_emac(struct cpsw_priv *priv)
 	priv_sl2->emac_port = 1;
 	cpsw->slaves[1].ndev = ndev;
 	ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_CTAG_RX;
+	ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+			     NETDEV_XDP_ACT_NDO_XMIT;
 
 	ndev->netdev_ops = &cpsw_netdev_ops;
 	ndev->ethtool_ops = &cpsw_ethtool_ops;

@@ -1635,6 +1637,8 @@ static int cpsw_probe(struct platform_device *pdev)
 	cpsw->slaves[0].ndev = ndev;
 
 	ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_CTAG_RX;
+	ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+			     NETDEV_XDP_ACT_NDO_XMIT;
 
 	ndev->netdev_ops = &cpsw_netdev_ops;
 	ndev->ethtool_ops = &cpsw_ethtool_ops;

drivers/net/ethernet/ti/cpsw_new.c +4 -0

index 83596ec0c7cb..35128dd45ffc 100644
@@ -1405,6 +1405,10 @@ static int cpsw_create_ports(struct cpsw_common *cpsw)
 		ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER |
 				  NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_NETNS_LOCAL | NETIF_F_HW_TC;
 
+		ndev->xdp_features = NETDEV_XDP_ACT_BASIC |
+				     NETDEV_XDP_ACT_REDIRECT |
+				     NETDEV_XDP_ACT_NDO_XMIT;
+
 		ndev->netdev_ops = &cpsw_netdev_ops;
 		ndev->ethtool_ops = &cpsw_ethtool_ops;
 		SET_NETDEV_DEV(ndev, dev);

drivers/net/hyperv/netvsc_drv.c +2 -0

index f9b219e6cd58..a9b139bbdb2c 100644
@@ -2559,6 +2559,8 @@ static int netvsc_probe(struct hv_device *dev,
 
 	netdev_lockdep_set_classes(net);
 
+	net->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT;
+
 	/* MTU range: 68 - 1500 or 65521 */
 	net->min_mtu = NETVSC_MTU_MIN;
 	if (nvdev->nvsp_version >= NVSP_PROTOCOL_VERSION_2)

drivers/net/netdevsim/netdev.c +1 -0

index 6db6a75ff9b9..35fa1ca98671 100644
@@ -286,6 +286,7 @@ static void nsim_setup(struct net_device *dev)
 			 NETIF_F_TSO;
 	dev->hw_features |= NETIF_F_HW_TC;
 	dev->max_mtu = ETH_MAX_MTU;
+	dev->xdp_features = NETDEV_XDP_ACT_HW_OFFLOAD;
 }
 
 static int nsim_init_netdevsim(struct netdevsim *ns)

drivers/net/tun.c +5 -0

index a7d17c680f4a..36620afde373 100644
@@ -1401,6 +1401,11 @@ static void tun_net_initialize(struct net_device *dev)
 
 		eth_hw_addr_random(dev);
 
+		/* Currently tun does not support XDP, only tap does. */
+		dev->xdp_features = NETDEV_XDP_ACT_BASIC |
+				    NETDEV_XDP_ACT_REDIRECT |
+				    NETDEV_XDP_ACT_NDO_XMIT;
+
 		break;
 	}
 

drivers/net/veth.c +4 -0

index ba3e05832843..1bb54de7124d 100644
@@ -1686,6 +1686,10 @@ 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;
 }
 
 /*

drivers/net/virtio_net.c +4 -0

index 7e1a98430190..692dff071782 100644
@@ -3280,7 +3280,10 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 			if (i == 0 && !old_prog)
 				virtnet_clear_guest_offloads(vi);
 		}
+		if (!old_prog)
+			xdp_features_set_redirect_target(dev, false);
 	} else {
+		xdp_features_clear_redirect_target(dev);
 		vi->xdp_enabled = false;
 	}
 

@@ -3910,6 +3913,7 @@ static int virtnet_probe(struct virtio_device *vdev)
 		dev->hw_features |= NETIF_F_GRO_HW;
 
 	dev->vlan_features = dev->features;
+	dev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT;
 
 	/* MTU range: 68 - 65535 */
 	dev->min_mtu = MIN_MTU;

drivers/net/xen-netfront.c +2 -0

index 12b074286df9..47d54d8ea59d 100644
@@ -1741,6 +1741,8 @@ static struct net_device *xennet_create_dev(struct xenbus_device *dev)
          * negotiate with the backend regarding supported features.
          */
 	netdev->features |= netdev->hw_features;
+	netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+			       NETDEV_XDP_ACT_NDO_XMIT;
 
 	netdev->ethtool_ops = &xennet_ethtool_ops;
 	netdev->min_mtu = ETH_MIN_MTU;

include/net/xdp.h +12 -0

index 8d1c86914f4c..d517bfac937b 100644
@@ -428,9 +428,21 @@ 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_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_features_set_redirect_target(struct net_device *dev, bool support_sg)
+{
+}
+
+static inline void
+xdp_features_clear_redirect_target(struct net_device *dev)
+{
+}
 #endif
 
 #endif /* __LINUX_NET_XDP_H__ */

net/core/xdp.c +18 -0

index a5a7ecf6391c..82727b47259d 100644
@@ -773,3 +773,21 @@ static int __init xdp_metadata_init(void)
 	return register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &xdp_metadata_kfunc_set);
 }
 late_initcall(xdp_metadata_init);
+
+void xdp_features_set_redirect_target(struct net_device *dev, bool support_sg)
+{
+	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);
+}
+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 |
+			       NETDEV_XDP_ACT_NDO_XMIT_SG);
+	call_netdevice_notifiers(NETDEV_XDP_FEAT_CHANGE, dev);
+}
+EXPORT_SYMBOL_GPL(xdp_features_clear_redirect_target);

Signature · 1 line

2.39.1

Quoted 631 lines

From: Marek Majtyka <[email protected]>

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 <[email protected]>

Reviewed-by Simon Horman <[email protected]>

Acked-by Stanislav Fomichev <[email protected]>

Acked-by Jakub Kicinski <[email protected]>

Co-developed-by Kumar Kartikeya Dwivedi <[email protected]>

Signed-off-by Kumar Kartikeya Dwivedi <[email protected]>

Co-developed-by Lorenzo Bianconi <[email protected]>

Signed-off-by Lorenzo Bianconi <[email protected]>

Signed-off-by Marek Majtyka <[email protected]>

---
 drivers/net/ethernet/amazon/ena/ena_netdev.c   |  4 ++++
 .../net/ethernet/aquantia/atlantic/aq_nic.c    |  5 +++++
 drivers/net/ethernet/broadcom/bnxt/bnxt.c      |  3 +++
 drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c  |  2 ++
 .../net/ethernet/cavium/thunder/nicvf_main.c   |  2 ++
 drivers/net/ethernet/engleder/tsnep_main.c     |  4 ++++
 drivers/net/ethernet/freescale/dpaa/dpaa_eth.c |  4 ++++
 .../net/ethernet/freescale/dpaa2/dpaa2-eth.c   |  4 ++++
 .../net/ethernet/freescale/enetc/enetc_pf.c    |  3 +++
 .../net/ethernet/fungible/funeth/funeth_main.c |  6 ++++++
 drivers/net/ethernet/intel/i40e/i40e_main.c    | 10 ++++++++--
 drivers/net/ethernet/intel/ice/ice_main.c      |  5 +++++
 drivers/net/ethernet/intel/igb/igb_main.c      |  9 ++++++++-
 drivers/net/ethernet/intel/igc/igc_main.c      |  3 +++
 drivers/net/ethernet/intel/igc/igc_xdp.c       |  5 +++++
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c  |  6 ++++++
 .../net/ethernet/intel/ixgbevf/ixgbevf_main.c  |  1 +
 drivers/net/ethernet/marvell/mvneta.c          |  3 +++
 .../net/ethernet/marvell/mvpp2/mvpp2_main.c    |  4 ++++
 .../ethernet/marvell/octeontx2/nic/otx2_pf.c   |  8 ++++++--
 drivers/net/ethernet/mediatek/mtk_eth_soc.c    |  6 ++++++
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c |  2 ++
 .../net/ethernet/mellanox/mlx5/core/en_main.c  | 11 +++++++++++
 drivers/net/ethernet/microsoft/mana/mana_en.c  |  2 ++
 .../ethernet/netronome/nfp/nfp_net_common.c    |  5 +++++
 drivers/net/ethernet/qlogic/qede/qede_main.c   |  3 +++
 drivers/net/ethernet/sfc/efx.c                 |  4 ++++
 drivers/net/ethernet/sfc/siena/efx.c           |  4 ++++
 drivers/net/ethernet/socionext/netsec.c        |  3 +++
 .../net/ethernet/stmicro/stmmac/stmmac_main.c  |  2 ++
 drivers/net/ethernet/ti/cpsw.c                 |  4 ++++
 drivers/net/ethernet/ti/cpsw_new.c             |  4 ++++
 drivers/net/hyperv/netvsc_drv.c                |  2 ++
 drivers/net/netdevsim/netdev.c                 |  1 +
 drivers/net/tun.c                              |  5 +++++
 drivers/net/veth.c                             |  4 ++++
 drivers/net/virtio_net.c                       |  4 ++++
 drivers/net/xen-netfront.c                     |  2 ++
 include/net/xdp.h                              | 12 ++++++++++++
 net/core/xdp.c                                 | 18 ++++++++++++++++++
 40 files changed, 184 insertions(+), 5 deletions(-)

drivers/net/ethernet/amazon/ena/ena_netdev.c +4 -0

index e8ad5ea31aff..d3999db7c6a2 100644
@@ -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 +5 -0

index 06508eebb585..d6d6d5d37ff3 100644
@@ -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 +3 -0

index 240a7e8a7652..a1b4356dfb6c 100644
@@ -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 +2 -0

index 36d5202c0aee..5843c93b1711 100644
@@ -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 +2 -0

index f2f95493ec89..8b25313c7f6b 100644
@@ -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 +4 -0

index c3cf427a9409..6982aaa928b5 100644
@@ -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 +4 -0

index 027fff9f7db0..9318a2554056 100644
@@ -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 +4 -0

index 2e79d18fc3c7..746ccfde7255 100644
@@ -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 +3 -0

index 7facc7d5261e..6b54071d4ecc 100644
@@ -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 +6 -0

index b4cce30e526a..df86770731ad 100644
@@ -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 +8 -2

index 53d0083e35da..8a79cc18c428 100644
@@ -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 +5 -0

index fce86e8ff834..26b09e4ed0c8 100644
@@ -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;

@@ -2899,11 +2900,13 @@ 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");

@@ -3446,6 +3449,8 @@ 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 +8 -1

index 3c0c35ecea10..0e11a082f7a1 100644
@@ -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 +3 -0

index e86b15efaeb8..8b572cd2c350 100644
@@ -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 +5 -0

index aeeb34e64610..e27af72aada8 100644
@@ -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 +6 -0

index 43a44c1e1576..af4c12b6059f 100644
@@ -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 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	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 +1 -0

index ea0a230c1153..a44e4bd56142 100644
@@ -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 +3 -0

index f8925cac61e4..dc2989103a77 100644
@@ -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 +4 -0

index 4da45c5abba5..9b4ecbe4f36d 100644
@@ -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 +6 -2

index c1ea60bc2630..179433d0a54a 100644
@@ -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);

drivers/net/ethernet/mediatek/mtk_eth_soc.c +6 -0

index 801deac58bf7..ac54b6f2bb5c 100644
@@ -4447,6 +4447,12 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np)
 		register_netdevice_notifier(&mac->device_notifier);
 	}
 
+	if (mtk_page_pool_enabled(eth))
+		eth->netdev[id]->xdp_features = NETDEV_XDP_ACT_BASIC |
+						NETDEV_XDP_ACT_REDIRECT |
+						NETDEV_XDP_ACT_NDO_XMIT |
+						NETDEV_XDP_ACT_NDO_XMIT_SG;
+
 	return 0;
 
 free_netdev:

drivers/net/ethernet/mellanox/mlx4/en_netdev.c +2 -0

index af4c4858f397..e11bc0ac880e 100644
@@ -3416,6 +3416,8 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 		priv->rss_hash_fn = ETH_RSS_HASH_TOP;
 	}
 
+	dev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT;
+
 	/* MTU range: 68 - hw-specific max */
 	dev->min_mtu = ETH_MIN_MTU;
 	dev->max_mtu = priv->max_mtu;

drivers/net/ethernet/mellanox/mlx5/core/en_main.c +11 -0

index 0e87432ec6f1..e4996ef04d86 100644
@@ -4780,6 +4780,13 @@ 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;
 

@@ -5175,6 +5182,10 @@ 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);

drivers/net/ethernet/microsoft/mana/mana_en.c +2 -0

index 2f6a048dee90..6120f2b6684f 100644
@@ -2160,6 +2160,8 @@ static int mana_probe_port(struct mana_context *ac, int port_idx,
 	ndev->hw_features |= NETIF_F_RXHASH;
 	ndev->features = ndev->hw_features;
 	ndev->vlan_features = 0;
+	ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+			     NETDEV_XDP_ACT_NDO_XMIT;
 
 	err = register_netdev(ndev);
 	if (err) {

drivers/net/ethernet/netronome/nfp/nfp_net_common.c +5 -0

index 18fc9971f1c8..e4825d885560 100644
@@ -2529,10 +2529,15 @@ static void nfp_net_netdev_init(struct nfp_net *nn)
 	netdev->features &= ~NETIF_F_HW_VLAN_STAG_RX;
 	nn->dp.ctrl &= ~NFP_NET_CFG_CTRL_RXQINQ;
 
+	netdev->xdp_features = NETDEV_XDP_ACT_BASIC;
+	if (nn->app && nn->app->type->id == NFP_APP_BPF_NIC)
+		netdev->xdp_features |= NETDEV_XDP_ACT_HW_OFFLOAD;
+
 	/* Finalise the netdev setup */
 	switch (nn->dp.ops->version) {
 	case NFP_NFD_VER_NFD3:
 		netdev->netdev_ops = &nfp_nfd3_netdev_ops;
+		netdev->xdp_features |= NETDEV_XDP_ACT_XSK_ZEROCOPY;
 		break;
 	case NFP_NFD_VER_NFDK:
 		netdev->netdev_ops = &nfp_nfdk_netdev_ops;

drivers/net/ethernet/qlogic/qede/qede_main.c +3 -0

index 953f304b8588..b6d999927e86 100644
@@ -892,6 +892,9 @@ static void qede_init_ndev(struct qede_dev *edev)
 
 	ndev->hw_features = hw_features;
 
+	ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+			     NETDEV_XDP_ACT_NDO_XMIT;
+
 	/* MTU range: 46 - 9600 */
 	ndev->min_mtu = ETH_ZLEN - ETH_HLEN;
 	ndev->max_mtu = QEDE_MAX_JUMBO_PACKET_SIZE;

drivers/net/ethernet/sfc/efx.c +0 -0

index 0556542d7a6b..18ff8d8cff42 100644
@@ -1078,6 +1078,10 @@ static int efx_pci_probe(struct pci_dev *pci_dev,
 
 	pci_info(pci_dev, "Solarflare NIC detected\n");
 

drivers/net/ethernet/sfc/efx.c static int efx_pci_probe(struct pci_dev *pci_dev, · line 1084

Quoted 4 lines

drivers/net/ethernet/sfc/efx.c +4 -0

+	efx->net_dev->xdp_features = NETDEV_XDP_ACT_BASIC |
+				     NETDEV_XDP_ACT_REDIRECT |
+				     NETDEV_XDP_ACT_NDO_XMIT;
+

Put this in efx_pci_probe_post_io() please, that is where all the other basic netdev features are initialised.

Quoted 9 lines

drivers/net/ethernet/sfc/efx.c +0 -0

 	if (!efx->type->is_vf)
 		efx_probe_vpd_strings(efx);
 

drivers/net/ethernet/sfc/siena/efx.c +0 -0

index 60e5b7c8ccf9..a6ef21845224 100644

drivers/net/ethernet/sfc/siena/efx.c static int efx_pci_probe(struct pci_dev *pci_dev, · line 1054

Quoted 7 lines

drivers/net/ethernet/sfc/siena/efx.c +4 -0

@@ -1048,6 +1048,10 @@ static int efx_pci_probe(struct pci_dev *pci_dev,
 
 	pci_info(pci_dev, "Solarflare NIC detected\n");
 
+	efx->net_dev->xdp_features = NETDEV_XDP_ACT_BASIC |
+				     NETDEV_XDP_ACT_REDIRECT |
+				     NETDEV_XDP_ACT_NDO_XMIT;
+

Same comment here.

Martin

Quoted 213 lines

drivers/net/ethernet/sfc/siena/efx.c +0 -0

 	if (!efx->type->is_vf)
 		efx_probe_vpd_strings(efx);
 

drivers/net/ethernet/socionext/netsec.c +3 -0

index 9b46579b5a10..2d7347b71c41 100644
@@ -2104,6 +2104,9 @@ static int netsec_probe(struct platform_device *pdev)
 				NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
 	ndev->hw_features = ndev->features;
 
+	ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+			     NETDEV_XDP_ACT_NDO_XMIT;
+
 	priv->rx_cksum_offload_flag = true;
 
 	ret = netsec_register_mdio(priv, phy_addr);

drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +2 -0

index b7e5af58ab75..734d84263fd2 100644
@@ -7150,6 +7150,8 @@ int stmmac_dvr_probe(struct device *device,
 
 	ndev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
 			    NETIF_F_RXCSUM;
+	ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+			     NETDEV_XDP_ACT_NDO_XMIT;
 
 	ret = stmmac_tc_init(priv, priv);
 	if (!ret) {

drivers/net/ethernet/ti/cpsw.c +4 -0

index 13c9c2d6b79b..37f0b62ec5d6 100644
@@ -1458,6 +1458,8 @@ static int cpsw_probe_dual_emac(struct cpsw_priv *priv)
 	priv_sl2->emac_port = 1;
 	cpsw->slaves[1].ndev = ndev;
 	ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_CTAG_RX;
+	ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+			     NETDEV_XDP_ACT_NDO_XMIT;
 
 	ndev->netdev_ops = &cpsw_netdev_ops;
 	ndev->ethtool_ops = &cpsw_ethtool_ops;

@@ -1635,6 +1637,8 @@ static int cpsw_probe(struct platform_device *pdev)
 	cpsw->slaves[0].ndev = ndev;
 
 	ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_CTAG_RX;
+	ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+			     NETDEV_XDP_ACT_NDO_XMIT;
 
 	ndev->netdev_ops = &cpsw_netdev_ops;
 	ndev->ethtool_ops = &cpsw_ethtool_ops;

drivers/net/ethernet/ti/cpsw_new.c +4 -0

index 83596ec0c7cb..35128dd45ffc 100644
@@ -1405,6 +1405,10 @@ static int cpsw_create_ports(struct cpsw_common *cpsw)
 		ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER |
 				  NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_NETNS_LOCAL | NETIF_F_HW_TC;
 
+		ndev->xdp_features = NETDEV_XDP_ACT_BASIC |
+				     NETDEV_XDP_ACT_REDIRECT |
+				     NETDEV_XDP_ACT_NDO_XMIT;
+
 		ndev->netdev_ops = &cpsw_netdev_ops;
 		ndev->ethtool_ops = &cpsw_ethtool_ops;
 		SET_NETDEV_DEV(ndev, dev);

drivers/net/hyperv/netvsc_drv.c +2 -0

index f9b219e6cd58..a9b139bbdb2c 100644
@@ -2559,6 +2559,8 @@ static int netvsc_probe(struct hv_device *dev,
 
 	netdev_lockdep_set_classes(net);
 
+	net->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT;
+
 	/* MTU range: 68 - 1500 or 65521 */
 	net->min_mtu = NETVSC_MTU_MIN;
 	if (nvdev->nvsp_version >= NVSP_PROTOCOL_VERSION_2)

drivers/net/netdevsim/netdev.c +1 -0

index 6db6a75ff9b9..35fa1ca98671 100644
@@ -286,6 +286,7 @@ static void nsim_setup(struct net_device *dev)
 			 NETIF_F_TSO;
 	dev->hw_features |= NETIF_F_HW_TC;
 	dev->max_mtu = ETH_MAX_MTU;
+	dev->xdp_features = NETDEV_XDP_ACT_HW_OFFLOAD;
 }
 
 static int nsim_init_netdevsim(struct netdevsim *ns)

drivers/net/tun.c +5 -0

index a7d17c680f4a..36620afde373 100644
@@ -1401,6 +1401,11 @@ static void tun_net_initialize(struct net_device *dev)
 
 		eth_hw_addr_random(dev);
 
+		/* Currently tun does not support XDP, only tap does. */
+		dev->xdp_features = NETDEV_XDP_ACT_BASIC |
+				    NETDEV_XDP_ACT_REDIRECT |
+				    NETDEV_XDP_ACT_NDO_XMIT;
+
 		break;
 	}
 

drivers/net/veth.c +4 -0

index ba3e05832843..1bb54de7124d 100644
@@ -1686,6 +1686,10 @@ 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;
 }
 
 /*

drivers/net/virtio_net.c +4 -0

index 7e1a98430190..692dff071782 100644
@@ -3280,7 +3280,10 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 			if (i == 0 && !old_prog)
 				virtnet_clear_guest_offloads(vi);
 		}
+		if (!old_prog)
+			xdp_features_set_redirect_target(dev, false);
 	} else {
+		xdp_features_clear_redirect_target(dev);
 		vi->xdp_enabled = false;
 	}
 

@@ -3910,6 +3913,7 @@ static int virtnet_probe(struct virtio_device *vdev)
 		dev->hw_features |= NETIF_F_GRO_HW;
 
 	dev->vlan_features = dev->features;
+	dev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT;
 
 	/* MTU range: 68 - 65535 */
 	dev->min_mtu = MIN_MTU;

drivers/net/xen-netfront.c +2 -0

index 12b074286df9..47d54d8ea59d 100644
@@ -1741,6 +1741,8 @@ static struct net_device *xennet_create_dev(struct xenbus_device *dev)
          * negotiate with the backend regarding supported features.
          */
 	netdev->features |= netdev->hw_features;
+	netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+			       NETDEV_XDP_ACT_NDO_XMIT;
 
 	netdev->ethtool_ops = &xennet_ethtool_ops;
 	netdev->min_mtu = ETH_MIN_MTU;

include/net/xdp.h +12 -0

index 8d1c86914f4c..d517bfac937b 100644
@@ -428,9 +428,21 @@ 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_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_features_set_redirect_target(struct net_device *dev, bool support_sg)
+{
+}
+
+static inline void
+xdp_features_clear_redirect_target(struct net_device *dev)
+{
+}
 #endif
 
 #endif /* __LINUX_NET_XDP_H__ */

net/core/xdp.c +18 -0

index a5a7ecf6391c..82727b47259d 100644
@@ -773,3 +773,21 @@ static int __init xdp_metadata_init(void)
 	return register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &xdp_metadata_kfunc_set);
 }
 late_initcall(xdp_metadata_init);
+
+void xdp_features_set_redirect_target(struct net_device *dev, bool support_sg)
+{
+	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);
+}
+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 |
+			       NETDEV_XDP_ACT_NDO_XMIT_SG);
+	call_netdevice_notifiers(NETDEV_XDP_FEAT_CHANGE, dev);
+}
+EXPORT_SYMBOL_GPL(xdp_features_clear_redirect_target);

Signature · 1 line

2.39.1

Extend bpf_xdp_query routine in order to get XDP/XSK supported features of netdev over route netlink interface.
Extend libbpf netlink implementation in order to support netlink_generic protocol.

Co-developed-by Kumar Kartikeya Dwivedi <[email protected]>

Signed-off-by Kumar Kartikeya Dwivedi <[email protected]>

Co-developed-by Marek Majtyka <[email protected]>

Signed-off-by Marek Majtyka <[email protected]>

Signed-off-by Lorenzo Bianconi <[email protected]>

---
 tools/lib/bpf/libbpf.h  |  3 +-
 tools/lib/bpf/netlink.c | 96 +++++++++++++++++++++++++++++++++++++++++
 tools/lib/bpf/nlattr.h  | 12 ++++++
 3 files changed, 110 insertions(+), 1 deletion(-)

tools/lib/bpf/netlink.c +11 -0

@@ -366,6 +433,10 @@ int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts)
                .ifinfo.ifi_family = AF_PACKET,
        };
        struct xdp_id_md xdp_id = {};
+       struct xdp_features_md md = {
+               .ifindex = ifindex,
+       };
+       __u16 id;
        int err;
 
        if (!OPTS_VALID(opts, bpf_xdp_query_opts))

@@ -393,6 +464,31 @@ int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts)
        OPTS_SET(opts, skb_prog_id, xdp_id.info.skb_prog_id);
        OPTS_SET(opts, attach_mode, xdp_id.info.attach_mode);
 
+       if (!OPTS_HAS(opts, feature_flags))
+               return 0;
+
+       err = libbpf_netlink_resolve_genl_family_id("netdev", sizeof("netdev"), &id);
+       if (err < 0)
+               return libbpf_err(err);
+

tools/lib/bpf/netlink.c +8 -0

+
+       err = libbpf_netlink_send_recv(&req, NETLINK_GENERIC,
+                                      parse_xdp_features, NULL, &md);
+       if (err)
+               return libbpf_err(err);
+
+       opts->feature_flags = md.flags;
+
        return 0;
 }
 

Quoted 17 lines

Extend bpf_xdp_query routine in order to get XDP/XSK supported features of netdev over route netlink interface.
Extend libbpf netlink implementation in order to support netlink_generic protocol.

Co-developed-by Kumar Kartikeya Dwivedi <[email protected]>

Signed-off-by Kumar Kartikeya Dwivedi <[email protected]>

Co-developed-by Marek Majtyka <[email protected]>

Signed-off-by Marek Majtyka <[email protected]>

Signed-off-by Lorenzo Bianconi <[email protected]>

---
 tools/lib/bpf/libbpf.h  |  3 +-
 tools/lib/bpf/netlink.c | 96 +++++++++++++++++++++++++++++++++++++++++
 tools/lib/bpf/nlattr.h  | 12 ++++++
 3 files changed, 110 insertions(+), 1 deletion(-)

[...]

Quoted 27 lines

tools/lib/bpf/netlink.c +16 -0

@@ -366,6 +433,10 @@ int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts)
                .ifinfo.ifi_family = AF_PACKET,
        };
        struct xdp_id_md xdp_id = {};
+       struct xdp_features_md md = {
+               .ifindex = ifindex,
+       };
+       __u16 id;
        int err;
 
        if (!OPTS_VALID(opts, bpf_xdp_query_opts))

@@ -393,6 +464,31 @@ int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts)
        OPTS_SET(opts, skb_prog_id, xdp_id.info.skb_prog_id);
        OPTS_SET(opts, attach_mode, xdp_id.info.attach_mode);
 
+       if (!OPTS_HAS(opts, feature_flags))
+               return 0;
+
+       err = libbpf_netlink_resolve_genl_family_id("netdev", sizeof("netdev"), &id);
+       if (err < 0)
+               return libbpf_err(err);
+
+       memset(&req, 0, sizeof(req));
+       req.nh.nlmsg_len = NLMSG_LENGTH(GENL_HDRLEN);
+       req.nh.nlmsg_flags = NLM_F_REQUEST;
+       req.nh.nlmsg_type = id;
+       req.gnl.cmd = NETDEV_CMD_DEV_GET;

tools/lib/bpf/netlink.c int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts) · line 483

Quoted 5 lines

tools/lib/bpf/netlink.c +5 -0

+       req.gnl.version = 2;
+
+       err = nlattr_add(&req, NETDEV_A_DEV_IFINDEX, &ifindex, sizeof(ifindex));
+       if (err < 0)
+               return err;

just noticed this, we need to use libbpf_err(err) here like in other error cases to set errno properly. Can you please send a follow up?

Quoted 12 lines

tools/lib/bpf/netlink.c +8 -0

+
+       err = libbpf_netlink_send_recv(&req, NETLINK_GENERIC,
+                                      parse_xdp_features, NULL, &md);
+       if (err)
+               return libbpf_err(err);
+
+       opts->feature_flags = md.flags;
+
        return 0;
 }
 

[...]

Extend bpf_xdp_query routine in order to get XDP/XSK supported features of netdev over route netlink interface.
Extend libbpf netlink implementation in order to support netlink_generic protocol.

Co-developed-by Kumar Kartikeya Dwivedi <[email protected]>

Signed-off-by Kumar Kartikeya Dwivedi <[email protected]>

Co-developed-by Marek Majtyka <[email protected]>

Signed-off-by Marek Majtyka <[email protected]>

Signed-off-by Lorenzo Bianconi <[email protected]>

---
  tools/lib/bpf/libbpf.h  |  3 +-
  tools/lib/bpf/netlink.c | 96 +++++++++++++++++++++++++++++++++++++++++
  tools/lib/bpf/nlattr.h  | 12 ++++++
  3 files changed, 110 insertions(+), 1 deletion(-)

tools/lib/bpf/netlink.c +5 -0

+
  int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts)
  {
  	struct libbpf_nla_req req = {

@@ -366,6 +433,10 @@ int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts)
  		.ifinfo.ifi_family = AF_PACKET,
  	};
  	struct xdp_id_md xdp_id = {};
+	struct xdp_features_md md = {
+		.ifindex = ifindex,
+	};
+	__u16 id;
  	int err;
 
  	if (!OPTS_VALID(opts, bpf_xdp_query_opts))

tools/lib/bpf/netlink.c +19 -0

+
+	memset(&req, 0, sizeof(req));
+	req.nh.nlmsg_len = NLMSG_LENGTH(GENL_HDRLEN);
+	req.nh.nlmsg_flags = NLM_F_REQUEST;
+	req.nh.nlmsg_type = id;
+	req.gnl.cmd = NETDEV_CMD_DEV_GET;
+	req.gnl.version = 2;
+
+	err = nlattr_add(&req, NETDEV_A_DEV_IFINDEX, &ifindex, sizeof(ifindex));
+	if (err < 0)
+		return err;
+
+	err = libbpf_netlink_send_recv(&req, NETLINK_GENERIC,
+				       parse_xdp_features, NULL, &md);
+	if (err)
+		return libbpf_err(err);
+
+	opts->feature_flags = md.flags;
+
  	return 0;
  }
 

Quoted 16 lines · Lorenzo Bianconi

Extend bpf_xdp_query routine in order to get XDP/XSK supported features of netdev over route netlink interface.
Extend libbpf netlink implementation in order to support netlink_generic protocol.

Co-developed-by Kumar Kartikeya Dwivedi <[email protected]>

Signed-off-by Kumar Kartikeya Dwivedi <[email protected]>

Co-developed-by Marek Majtyka <[email protected]>

Signed-off-by Marek Majtyka <[email protected]>

Signed-off-by Lorenzo Bianconi <[email protected]>

---
  tools/lib/bpf/libbpf.h  |  3 +-
  tools/lib/bpf/netlink.c | 96 +++++++++++++++++++++++++++++++++++++++++
  tools/lib/bpf/nlattr.h  | 12 ++++++
  3 files changed, 110 insertions(+), 1 deletion(-)

[...]

Quoted 16 lines

tools/lib/bpf/netlink.c +5 -0

+
  int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts)
  {
      struct libbpf_nla_req req = {

@@ -366,6 +433,10 @@ int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts)
              .ifinfo.ifi_family = AF_PACKET,
      };
      struct xdp_id_md xdp_id = {};
+     struct xdp_features_md md = {
+             .ifindex = ifindex,
+     };
+     __u16 id;
      int err;
 
      if (!OPTS_VALID(opts, bpf_xdp_query_opts))

tools/lib/bpf/netlink.c int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts) · line 472

Quoted 9 lines

tools/lib/bpf/netlink.c +6 -0

@@ -393,6 +464,31 @@ int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts)
      OPTS_SET(opts, skb_prog_id, xdp_id.info.skb_prog_id);
      OPTS_SET(opts, attach_mode, xdp_id.info.attach_mode);
 
+     if (!OPTS_HAS(opts, feature_flags))
+             return 0;
+
+     err = libbpf_netlink_resolve_genl_family_id("netdev", sizeof("netdev"), &id);
+     if (err < 0)
+             return libbpf_err(err);

Hi, Lorenzo,

Using latest libbpf repo (https://github.com/libbpf/libbpf, sync'ed from source), looks like the above change won't work if the program is running on an old kernel, e.g., 5.12 kernel.

In this particular combination, in user space, bpf_xdp_query_opts does have 'feature_flags' member, so the control can reach libbpf_netlink_resolve_genl_family_id(). However, the family 'netdev' is only available in latest kernel (after this patch set). So the error will return in the above.

This breaks backward compatibility since old working application won't work any more with a refresh of libbpf.

I could not come up with an easy solution for this. One thing we could do is to treat 'libbpf_netlink_resolve_genl_family_id()' as a probe, so return 0 if probe fails.

err = libbpf_netlink_resolve_genl_family_id("netdev",

sizeof("netdev"), &id);
   if (err < 0)
        return 0;

Please let me know whether my suggestion makes sense or there could be a better solution.

Quoted 23 lines

tools/lib/bpf/netlink.c +19 -0

+
+     memset(&req, 0, sizeof(req));
+     req.nh.nlmsg_len = NLMSG_LENGTH(GENL_HDRLEN);
+     req.nh.nlmsg_flags = NLM_F_REQUEST;
+     req.nh.nlmsg_type = id;
+     req.gnl.cmd = NETDEV_CMD_DEV_GET;
+     req.gnl.version = 2;
+
+     err = nlattr_add(&req, NETDEV_A_DEV_IFINDEX, &ifindex, sizeof(ifindex));
+     if (err < 0)
+             return err;
+
+     err = libbpf_netlink_send_recv(&req, NETLINK_GENERIC,
+                                    parse_xdp_features, NULL, &md);
+     if (err)
+             return libbpf_err(err);
+
+     opts->feature_flags = md.flags;
+
      return 0;
  }
 

[...]

Quoted 66 lines · Yonghong Song

Quoted 16 lines · Lorenzo Bianconi

Extend bpf_xdp_query routine in order to get XDP/XSK supported features of netdev over route netlink interface.
Extend libbpf netlink implementation in order to support netlink_generic protocol.

Co-developed-by Kumar Kartikeya Dwivedi <[email protected]>

Signed-off-by Kumar Kartikeya Dwivedi <[email protected]>

Co-developed-by Marek Majtyka <[email protected]>

Signed-off-by Marek Majtyka <[email protected]>

Signed-off-by Lorenzo Bianconi <[email protected]>

---
   tools/lib/bpf/libbpf.h  |  3 +-
   tools/lib/bpf/netlink.c | 96 +++++++++++++++++++++++++++++++++++++++++
   tools/lib/bpf/nlattr.h  | 12 ++++++
   3 files changed, 110 insertions(+), 1 deletion(-)

[...]

Quoted 16 lines

tools/lib/bpf/netlink.c +5 -0

+
   int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts)
   {
       struct libbpf_nla_req req = {

@@ -366,6 +433,10 @@ int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts)
               .ifinfo.ifi_family = AF_PACKET,
       };
       struct xdp_id_md xdp_id = {};
+     struct xdp_features_md md = {
+             .ifindex = ifindex,
+     };
+     __u16 id;
       int err;
 
       if (!OPTS_VALID(opts, bpf_xdp_query_opts))

tools/lib/bpf/netlink.c int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts) · line 472

Quoted 9 lines

tools/lib/bpf/netlink.c +6 -0

@@ -393,6 +464,31 @@ int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts)
       OPTS_SET(opts, skb_prog_id, xdp_id.info.skb_prog_id);
       OPTS_SET(opts, attach_mode, xdp_id.info.attach_mode);
 
+     if (!OPTS_HAS(opts, feature_flags))
+             return 0;
+
+     err = libbpf_netlink_resolve_genl_family_id("netdev", sizeof("netdev"), &id);
+     if (err < 0)
+             return libbpf_err(err);

Hi, Lorenzo,

Using latest libbpf repo (https://github.com/libbpf/libbpf, sync'ed from source), looks like the above change won't work if the program is running on an old kernel, e.g., 5.12 kernel.

In this particular combination, in user space, bpf_xdp_query_opts does have 'feature_flags' member, so the control can reach libbpf_netlink_resolve_genl_family_id(). However, the family 'netdev' is only available in latest kernel (after this patch set). So the error will return in the above.

This breaks backward compatibility since old working application won't work any more with a refresh of libbpf.

I could not come up with an easy solution for this. One thing we could do is to treat 'libbpf_netlink_resolve_genl_family_id()' as a probe, so return 0 if probe fails.

Quoted 8 lines

err = libbpf_netlink_resolve_genl_family_id("netdev",

sizeof("netdev"), &id);
    if (err < 0)
         return 0;

Please let me know whether my suggestion makes sense or there could be a better solution.

feature_flags is an output parameter and if the "netdev" family doesn't exist then there are no feature flags to return, right?

Is there a specific error code that's returned when such a family doesn't exist? If yes, we should check for it and return 0 for feature_flags. If not, we'll have to do a generic < 0 check as Yonghong proposes.

Quoted 26 lines

Quoted 25 lines

tools/lib/bpf/netlink.c +19 -0

+
+     memset(&req, 0, sizeof(req));
+     req.nh.nlmsg_len = NLMSG_LENGTH(GENL_HDRLEN);
+     req.nh.nlmsg_flags = NLM_F_REQUEST;
+     req.nh.nlmsg_type = id;
+     req.gnl.cmd = NETDEV_CMD_DEV_GET;
+     req.gnl.version = 2;
+
+     err = nlattr_add(&req, NETDEV_A_DEV_IFINDEX, &ifindex, sizeof(ifindex));
+     if (err < 0)
+             return err;
+
+     err = libbpf_netlink_send_recv(&req, NETLINK_GENERIC,
+                                    parse_xdp_features, NULL, &md);
+     if (err)
+             return libbpf_err(err);
+
+     opts->feature_flags = md.flags;
+
       return 0;
   }
 

[...]

Quoted 76 lines · Andrii Nakryiko

Quoted 66 lines · Yonghong Song

Quoted 16 lines · Lorenzo Bianconi

Extend bpf_xdp_query routine in order to get XDP/XSK supported features of netdev over route netlink interface.
Extend libbpf netlink implementation in order to support netlink_generic protocol.

Co-developed-by Kumar Kartikeya Dwivedi <[email protected]>

Signed-off-by Kumar Kartikeya Dwivedi <[email protected]>

Co-developed-by Marek Majtyka <[email protected]>

Signed-off-by Marek Majtyka <[email protected]>

Signed-off-by Lorenzo Bianconi <[email protected]>

---
   tools/lib/bpf/libbpf.h  |  3 +-
   tools/lib/bpf/netlink.c | 96 +++++++++++++++++++++++++++++++++++++++++
   tools/lib/bpf/nlattr.h  | 12 ++++++
   3 files changed, 110 insertions(+), 1 deletion(-)

[...]

Quoted 16 lines

tools/lib/bpf/netlink.c +5 -0

+
   int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts)
   {
       struct libbpf_nla_req req = {

@@ -366,6 +433,10 @@ int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts)
               .ifinfo.ifi_family = AF_PACKET,
       };
       struct xdp_id_md xdp_id = {};
+     struct xdp_features_md md = {
+             .ifindex = ifindex,
+     };
+     __u16 id;
       int err;
 
       if (!OPTS_VALID(opts, bpf_xdp_query_opts))

tools/lib/bpf/netlink.c int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts) · line 472

Quoted 9 lines

tools/lib/bpf/netlink.c +6 -0

@@ -393,6 +464,31 @@ int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts)
       OPTS_SET(opts, skb_prog_id, xdp_id.info.skb_prog_id);
       OPTS_SET(opts, attach_mode, xdp_id.info.attach_mode);
 
+     if (!OPTS_HAS(opts, feature_flags))
+             return 0;
+
+     err = libbpf_netlink_resolve_genl_family_id("netdev", sizeof("netdev"), &id);
+     if (err < 0)
+             return libbpf_err(err);

Hi, Lorenzo,

Using latest libbpf repo (https://github.com/libbpf/libbpf, sync'ed from source), looks like the above change won't work if the program is running on an old kernel, e.g., 5.12 kernel.

In this particular combination, in user space, bpf_xdp_query_opts does have 'feature_flags' member, so the control can reach libbpf_netlink_resolve_genl_family_id(). However, the family 'netdev' is only available in latest kernel (after this patch set). So the error will return in the above.

This breaks backward compatibility since old working application won't work any more with a refresh of libbpf.

I could not come up with an easy solution for this. One thing we could do is to treat 'libbpf_netlink_resolve_genl_family_id()' as a probe, so return 0 if probe fails.

Quoted 8 lines

err = libbpf_netlink_resolve_genl_family_id("netdev",

sizeof("netdev"), &id);
    if (err < 0)
         return 0;

Please let me know whether my suggestion makes sense or there could be a better solution.

Quoted 7 lines

feature_flags is an output parameter and if the "netdev" family doesn't exist then there are no feature flags to return, right?

Is there a specific error code that's returned when such a family doesn't exist? If yes, we should check for it and return 0 for feature_flags. If not, we'll have to do a generic < 0 check as Yonghong proposes.

We can check -ENOENT.

err = libbpf_netlink_resolve_genl_family_id("netdev",
sizeof("netdev"), &id);

(quoted diff) +4 -1

-       if (err < 0)
+       if (err < 0) {
+               if (err == -ENOENT)
+                       return 0;
                 return libbpf_err(err);
+       }

Let me propose a patch for this.

Quoted 27 lines

Quoted 27 lines

Quoted 26 lines

tools/lib/bpf/netlink.c +19 -0

+
+     memset(&req, 0, sizeof(req));
+     req.nh.nlmsg_len = NLMSG_LENGTH(GENL_HDRLEN);
+     req.nh.nlmsg_flags = NLM_F_REQUEST;
+     req.nh.nlmsg_type = id;
+     req.gnl.cmd = NETDEV_CMD_DEV_GET;
+     req.gnl.version = 2;
+
+     err = nlattr_add(&req, NETDEV_A_DEV_IFINDEX, &ifindex, sizeof(ifindex));
+     if (err < 0)
+             return err;
+
+     err = libbpf_netlink_send_recv(&req, NETLINK_GENERIC,
+                                    parse_xdp_features, NULL, &md);
+     if (err)
+             return libbpf_err(err);
+
+     opts->feature_flags = md.flags;
+
       return 0;
   }
 

[...]

Introduce xdp_features tool in order to test XDP features supported by the NIC and match them against advertised ones.
In order to test supported/advertised XDP features, xdp_features must run on the Device Under Test (DUT) and on a Tester device. xdp_features opens a control TCP channel between DUT and Tester devices to send control commands from Tester to the DUT and a UDP data channel where the Tester sends UDP 'echo' packets and the DUT is expected to reply back with the same packet. DUT installs multiple XDP programs on the NIC to test XDP capabilities and reports back to the Tester some XDP stats. Currently xdp_features supports the following XDP features:
- XDP_DROP
- XDP_ABORTED
- XDP_PASS
- XDP_TX
- XDP_REDIRECT
- XDP_NDO_XMIT

Co-developed-by Kumar Kartikeya Dwivedi <[email protected]>

Signed-off-by Kumar Kartikeya Dwivedi <[email protected]>

Signed-off-by Lorenzo Bianconi <[email protected]>

---
  tools/testing/selftests/bpf/.gitignore        |   1 +
  tools/testing/selftests/bpf/Makefile          |  11 +-
  .../selftests/bpf/progs/xdp_features.c        | 269 +++++++
  .../selftests/bpf/test_xdp_features.sh        | 107 +++
  tools/testing/selftests/bpf/xdp_features.c    | 699 ++++++++++++++++++
  tools/testing/selftests/bpf/xdp_features.h    |  20 +
  6 files changed, 1105 insertions(+), 2 deletions(-)

create mode 100644 tools/testing/selftests/bpf/progs/xdp_features.c create mode 100755 tools/testing/selftests/bpf/test_xdp_features.sh create mode 100644 tools/testing/selftests/bpf/xdp_features.c create mode 100644 tools/testing/selftests/bpf/xdp_features.h

tools/testing/selftests/bpf/.gitignore +1 -0

index 4aa5bba956ff..116fecf80ca1 100644
@@ -48,3 +48,4 @@ xskxceiver
  xdp_redirect_multi
  xdp_synproxy
  xdp_hw_metadata
+xdp_features

tools/testing/selftests/bpf/Makefile +4 -2

index e79039726173..b2eb3201b85a 100644
@@ -73,7 +73,8 @@ TEST_PROGS := test_kmod.sh \
  	test_bpftool.sh \
  	test_bpftool_metadata.sh \
  	test_doc_build.sh \
-	test_xsk.sh
+	test_xsk.sh \
+	test_xdp_features.sh
 
  TEST_PROGS_EXTENDED := with_addr.sh \
  	with_tunnels.sh ima_setup.sh verify_sig_setup.sh \

@@ -83,7 +84,8 @@ TEST_PROGS_EXTENDED := with_addr.sh \
  TEST_GEN_PROGS_EXTENDED = test_sock_addr test_skb_cgroup_id_user \
  	flow_dissector_load test_flow_dissector test_tcp_check_syncookie_user \
  	test_lirc_mode2_user xdping test_cpp runqslower bench bpf_testmod.ko \
-	xskxceiver xdp_redirect_multi xdp_synproxy veristat xdp_hw_metadata
+	xskxceiver xdp_redirect_multi xdp_synproxy veristat xdp_hw_metadata \
+	xdp_features
 
  TEST_CUSTOM_PROGS = $(OUTPUT)/urandom_read $(OUTPUT)/sign-file
  TEST_GEN_FILES += liburandom_read.so

@@ -385,6 +387,7 @@ test_subskeleton_lib.skel.h-deps :=  

test_subskeleton_lib2.bpf.o test_subskeleton
test_usdt.skel.h-deps := test_usdt.bpf.o test_usdt_multispec.bpf.o xsk_xdp_progs.skel.h-deps := xsk_xdp_progs.bpf.o xdp_hw_metadata.skel.h-deps := xdp_hw_metadata.bpf.o
+xdp_features.skel.h-deps := xdp_features.bpf.o

LINKED_BPF_SRCS := $(patsubst %.bpf.o,%.c,$(foreach
skel,$(LINKED_SKELS),$($(skel)-deps)))

tools/testing/selftests/bpf/Makefile +0 -0

@@ -587,6 +590,10 @@ $(OUTPUT)/xdp_hw_metadata: xdp_hw_metadata.c  

$(OUTPUT)/network_helpers.o $(OUTPU
$(call msg,BINARY,,$@)
$(Q)$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@

+$(OUTPUT)/xdp_features: xdp_features.c $(OUTPUT)/network_helpers.o $(OUTPUT)/xdp_features.skel.h | $(OUTPUT)

tools/testing/selftests/bpf/Makefile +3 -0

+	$(call msg,BINARY,,$@)
+	$(Q)$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@
+
  # Make sure we are able to include and link libbpf against c++.
  $(OUTPUT)/test_cpp: test_cpp.cpp $(OUTPUT)/test_core_extern.skel.h  

$(BPFOBJ)
$(call msg,CXX,,$@)

tools/testing/selftests/bpf/progs/xdp_features.c new file +269 -0

new file mode 100644
index 000000000000..87c247d56f72
@@ -0,0 +1,269 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <stdbool.h>
+#include <linux/bpf.h>
+#include <linux/netdev.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+#include <bpf/bpf_tracing.h>
+#include <linux/if_ether.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <linux/udp.h>
+#include <asm-generic/errno-base.h>
+
+#include "xdp_features.h"
+
+#define ipv6_addr_equal(a, b)	((a).s6_addr32[0] == (b).s6_addr32[0] &&	\
+				 (a).s6_addr32[1] == (b).s6_addr32[1] &&	\
+				 (a).s6_addr32[2] == (b).s6_addr32[2] &&	\
+				 (a).s6_addr32[3] == (b).s6_addr32[3])
+
+struct net_device;
+struct bpf_prog;
+
+struct xdp_cpumap_stats {
+	unsigned int redirect;
+	unsigned int pass;
+	unsigned int drop;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, __u32);
+	__type(value, __u32);
+	__uint(max_entries, 1);
+} stats SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, __u32);
+	__type(value, __u32);
+	__uint(max_entries, 1);
+} dut_stats SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_CPUMAP);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(struct bpf_cpumap_val));
+	__uint(max_entries, 1);
+} cpu_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_DEVMAP);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(struct bpf_devmap_val));
+	__uint(max_entries, 1);
+} dev_map SEC(".maps");
+
+const volatile struct in6_addr tester_addr;
+const volatile struct in6_addr dut_addr;
+
+static __always_inline int
+xdp_process_echo_packet(struct xdp_md *xdp, bool dut)
+{
+	void *data_end = (void *)(long)xdp->data_end;
+	void *data = (void *)(long)xdp->data;
+	struct ethhdr *eh = data;
+	struct tlv_hdr *tlv;
+	struct udphdr *uh;
+	__be16 port;
+	__u8 *cmd;
+
+	if (eh + 1 > (struct ethhdr *)data_end)
+		return -EINVAL;
+
+	if (eh->h_proto == bpf_htons(ETH_P_IP)) {
+		struct iphdr *ih = (struct iphdr *)(eh + 1);
+		__be32 saddr = dut ? tester_addr.s6_addr32[3]
+				   : dut_addr.s6_addr32[3];
+		__be32 daddr = dut ? dut_addr.s6_addr32[3]
+				   : tester_addr.s6_addr32[3];
+
+		ih = (struct iphdr *)(eh + 1);
+		if (ih + 1 > (struct iphdr *)data_end)
+			return -EINVAL;
+
+		if (saddr != ih->saddr)
+			return -EINVAL;
+
+		if (daddr != ih->daddr)
+			return -EINVAL;
+
+		if (ih->protocol != IPPROTO_UDP)
+			return -EINVAL;
+
+		uh = (struct udphdr *)(ih + 1);
+	} else if (eh->h_proto == bpf_htons(ETH_P_IPV6)) {
+		struct in6_addr saddr = dut ? tester_addr : dut_addr;
+		struct in6_addr daddr = dut ? dut_addr : tester_addr;
+		struct ipv6hdr *ih6 = (struct ipv6hdr *)(eh + 1);
+
+		if (ih6 + 1 > (struct ipv6hdr *)data_end)
+			return -EINVAL;
+
+		if (!ipv6_addr_equal(saddr, ih6->saddr))
+			return -EINVAL;
+
+		if (!ipv6_addr_equal(daddr, ih6->daddr))
+			return -EINVAL;
+
+		if (ih6->nexthdr != IPPROTO_UDP)
+			return -EINVAL;
+
+		uh = (struct udphdr *)(ih6 + 1);
+	} else {
+		return -EINVAL;
+	}
+
+	if (uh + 1 > (struct udphdr *)data_end)
+		return -EINVAL;
+
+	port = dut ? uh->dest : uh->source;
+	if (port != bpf_htons(DUT_ECHO_PORT))
+		return -EINVAL;
+
+	tlv = (struct tlv_hdr *)(uh + 1);
+	if (tlv + 1 > data_end)
+		return -EINVAL;
+
+	return bpf_htons(tlv->type) == CMD_ECHO ? 0 : -EINVAL;
+}
+
+static __always_inline int
+xdp_update_stats(struct xdp_md *xdp, bool tx, bool dut)
+{
+	__u32 *val, key = 0;
+
+	if (xdp_process_echo_packet(xdp, tx))
+		return -EINVAL;
+
+	if (dut)
+		val = bpf_map_lookup_elem(&dut_stats, &key);
+	else
+		val = bpf_map_lookup_elem(&stats, &key);
+
+	if (val)
+		__sync_add_and_fetch(val, 1);
+
+	return 0;
+}
+
+/* Tester */
+
+SEC("xdp")
+int xdp_tester_check_tx(struct xdp_md *xdp)
+{
+	xdp_update_stats(xdp, true, false);
+
+	return XDP_PASS;
+}
+
+SEC("xdp")
+int xdp_tester_check_rx(struct xdp_md *xdp)
+{
+	xdp_update_stats(xdp, false, false);
+
+	return XDP_PASS;
+}
+
+/* DUT */
+
+SEC("xdp")
+int xdp_do_pass(struct xdp_md *xdp)
+{
+	xdp_update_stats(xdp, true, true);
+
+	return XDP_PASS;
+}
+
+SEC("xdp")
+int xdp_do_drop(struct xdp_md *xdp)
+{
+	if (xdp_update_stats(xdp, true, true))
+		return XDP_PASS;
+
+	return XDP_DROP;
+}
+
+SEC("xdp")
+int xdp_do_aborted(struct xdp_md *xdp)
+{
+	if (xdp_process_echo_packet(xdp, true))
+		return XDP_PASS;
+
+	return XDP_ABORTED;
+}
+
+SEC("xdp")
+int xdp_do_tx(struct xdp_md *xdp)
+{
+	void *data = (void *)(long)xdp->data;
+	struct ethhdr *eh = data;
+	__u8 tmp_mac[ETH_ALEN];
+
+	if (xdp_update_stats(xdp, true, true))
+		return XDP_PASS;
+
+	__builtin_memcpy(tmp_mac, eh->h_source, ETH_ALEN);
+	__builtin_memcpy(eh->h_source, eh->h_dest, ETH_ALEN);
+	__builtin_memcpy(eh->h_dest, tmp_mac, ETH_ALEN);
+
+	return XDP_TX;
+}
+
+SEC("xdp")
+int xdp_do_redirect(struct xdp_md *xdp)
+{
+	if (xdp_process_echo_packet(xdp, true))
+		return XDP_PASS;
+
+	return bpf_redirect_map(&cpu_map, 0, 0);
+}
+
+SEC("tp_btf/xdp_exception")
+int BPF_PROG(xdp_exception, const struct net_device *dev,
+	     const struct bpf_prog *xdp, __u32 act)
+{
+	__u32 *val, key = 0;
+
+	val = bpf_map_lookup_elem(&dut_stats, &key);
+	if (val)
+		__sync_add_and_fetch(val, 1);
+
+	return 0;
+}
+
+SEC("tp_btf/xdp_cpumap_kthread")
+int BPF_PROG(tp_xdp_cpumap_kthread, int map_id, unsigned int processed,
+	     unsigned int drops, int sched, struct xdp_cpumap_stats *xdp_stats)
+{
+	__u32 *val, key = 0;
+
+	val = bpf_map_lookup_elem(&dut_stats, &key);
+	if (val)
+		__sync_add_and_fetch(val, 1);
+
+	return 0;
+}
+
+SEC("xdp/cpumap")
+int xdp_do_redirect_cpumap(struct xdp_md *xdp)
+{
+	void *data = (void *)(long)xdp->data;
+	struct ethhdr *eh = data;
+	__u8 tmp_mac[ETH_ALEN];
+
+	if (xdp_process_echo_packet(xdp, true))
+		return XDP_PASS;
+
+	__builtin_memcpy(tmp_mac, eh->h_source, ETH_ALEN);
+	__builtin_memcpy(eh->h_source, eh->h_dest, ETH_ALEN);
+	__builtin_memcpy(eh->h_dest, tmp_mac, ETH_ALEN);
+
+	return bpf_redirect_map(&dev_map, 0, 0);
+}
+
+char _license[] SEC("license") = "GPL";

tools/testing/selftests/bpf/test_xdp_features.sh new file +36 -0

new file mode 100755
index 000000000000..0aa71c4455c0
@@ -0,0 +1,107 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+readonly NS="ns1-$(mktemp -u XXXXXX)"
+readonly V0_IP4=10.10.0.11
+readonly V1_IP4=10.10.0.1
+readonly V0_IP6=2001:db8::11
+readonly V1_IP6=2001:db8::1
+
+ret=1
+
+setup() {
+	{
+		ip netns add ${NS}
+
+		ip link add v1 type veth peer name v0 netns ${NS}
+
+		ip link set v1 up
+		ip addr add $V1_IP4/24 dev v1
+		ip addr add $V1_IP6/64 nodad dev v1
+		ip -n ${NS} link set dev v0 up
+		ip -n ${NS} addr add $V0_IP4/24 dev v0
+		ip -n ${NS} addr add $V0_IP6/64 nodad dev v0
+
+		# Enable XDP mode and disable checksum offload
+		ethtool -K v1 gro on
+		ethtool -K v1 tx-checksumming off
+		ip netns exec ${NS} ethtool -K v0 gro on
+		ip netns exec ${NS} ethtool -K v0 tx-checksumming off
+	} > /dev/null 2>&1
+}
+
+cleanup() {
+	ip link del v1 2> /dev/null
+	ip netns del ${NS} 2> /dev/null
+	[ "$(pidof xdp_features)" = "" ] || kill $(pidof xdp_features) 2>  

/dev/null

tools/testing/selftests/bpf/test_xdp_features.sh new file +71 -0

+}
+
+wait_for_dut_server() {
+	while sleep 1; do
+		ss -tlp | grep -q xdp_features
+		[ $? -eq 0 ] && break
+	done
+}
+
+test_xdp_features() {
+	setup
+
+	## XDP_PASS
+	./xdp_features -f XDP_PASS -D $V1_IP6 -T $V0_IP6 v1 &
+	wait_for_dut_server
+	ip netns exec ${NS} ./xdp_features -t -f XDP_PASS \
+					   -D $V1_IP6 -C $V1_IP6 \
+					   -T $V0_IP6 v0
+	[ $? -ne 0 ] && exit
+
+	## XDP_DROP
+	./xdp_features -f XDP_DROP -D ::ffff:$V1_IP4 -T ::ffff:$V0_IP4 v1 &
+	wait_for_dut_server
+	ip netns exec ${NS} ./xdp_features -t -f XDP_DROP \
+					   -D ::ffff:$V1_IP4 \
+					   -C ::ffff:$V1_IP4 \
+					   -T ::ffff:$V0_IP4 v0
+	[ $? -ne 0 ] && exit
+
+	## XDP_ABORTED
+	./xdp_features -f XDP_ABORTED -D $V1_IP6 -T $V0_IP6 v1 &
+	wait_for_dut_server
+	ip netns exec ${NS} ./xdp_features -t -f XDP_ABORTED \
+					   -D $V1_IP6 -C $V1_IP6 \
+					   -T $V0_IP6 v0
+	[ $? -ne 0 ] && exit
+
+	## XDP_TX
+	./xdp_features -f XDP_TX -D ::ffff:$V1_IP4 -T ::ffff:$V0_IP4 v1 &
+	wait_for_dut_server
+	ip netns exec ${NS} ./xdp_features -t -f XDP_TX \
+					   -D ::ffff:$V1_IP4 \
+					   -C ::ffff:$V1_IP4 \
+					   -T ::ffff:$V0_IP4 v0
+	[ $? -ne 0 ] && exit
+
+	## XDP_REDIRECT
+	./xdp_features -f XDP_REDIRECT -D $V1_IP6 -T $V0_IP6 v1 &
+	wait_for_dut_server
+	ip netns exec ${NS} ./xdp_features -t -f XDP_REDIRECT \
+					   -D $V1_IP6 -C $V1_IP6 \
+					   -T $V0_IP6 v0
+	[ $? -ne 0 ] && exit
+
+	## XDP_NDO_XMIT
+	./xdp_features -f XDP_NDO_XMIT -D ::ffff:$V1_IP4 -T ::ffff:$V0_IP4 v1 &
+	wait_for_dut_server
+	ip netns exec ${NS} ./xdp_features -t -f XDP_NDO_XMIT \
+					   -D ::ffff:$V1_IP4 \
+					   -C ::ffff:$V1_IP4 \
+					   -T ::ffff:$V0_IP4 v0
+	ret=$?
+	cleanup
+}
+
+set -e
+trap cleanup 2 3 6 9
+
+test_xdp_features
+
+exit $ret

tools/testing/selftests/bpf/xdp_features.c new file +62 -0

new file mode 100644
index 000000000000..10fad1243573
@@ -0,0 +1,699 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/netdev.h>
+#include <linux/if_link.h>
+#include <signal.h>
+#include <argp.h>
+#include <net/if.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <netinet/tcp.h>
+#include <unistd.h>
+#include <arpa/inet.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include <pthread.h>
+
+#include <network_helpers.h>
+
+#include "xdp_features.skel.h"
+#include "xdp_features.h"
+
+#define RED(str)	"\033[0;31m" str "\033[0m"
+#define GREEN(str)	"\033[0;32m" str "\033[0m"
+#define YELLOW(str)	"\033[0;33m" str "\033[0m"
+
+static struct env {
+	bool verbosity;
+	int ifindex;
+	bool is_tester;
+	struct {
+		enum netdev_xdp_act drv_feature;
+		enum xdp_action action;
+	} feature;
+	struct sockaddr_storage dut_ctrl_addr;
+	struct sockaddr_storage dut_addr;
+	struct sockaddr_storage tester_addr;
+} env;
+
+#define BUFSIZE		128
+
+void test__fail(void) { /* for network_helpers.c */ }
+
+static int libbpf_print_fn(enum libbpf_print_level level,
+			   const char *format, va_list args)
+{
+	if (level == LIBBPF_DEBUG && !env.verbosity)
+		return 0;
+	return vfprintf(stderr, format, args);
+}
+
+static volatile bool exiting;
+
+static void sig_handler(int sig)
+{
+	exiting = true;
+}
+
+const char *argp_program_version = "xdp-features 0.0";
+const char argp_program_doc[] =
+"XDP features detecion application.\n"
+"\n"
+"XDP features application checks the XDP advertised features match  

detected ones.\n"
+"\n"
+"USAGE: ./xdp-features [-vt] [-f <xdp-feature>] [-D <dut-data-ip>] [-T <tester-data-ip>] [-C <dut-ctrl-ip>] <iface-name>\n"
+"\n"
+"dut-data-ip, tester-data-ip, dut-ctrl-ip: IPv6 or IPv4-mapped-IPv6 addresses;\n"
+"\n"
+"XDP features\n:"
+"- XDP_PASS\n"
+"- XDP_DROP\n"
+"- XDP_ABORTED\n"
+"- XDP_REDIRECT\n"
+"- XDP_NDO_XMIT\n"
+"- XDP_TX\n";

tools/testing/selftests/bpf/xdp_features.c new file +8 -0

+
+static const struct argp_option opts[] = {
+	{ "verbose", 'v', NULL, 0, "Verbose debug output" },
+	{ "tester", 't', NULL, 0, "Tester mode" },
+	{ "feature", 'f', "XDP-FEATURE", 0, "XDP feature to test" },
+	{ "dut_data_ip", 'D', "DUT-DATA-IP", 0, "DUT IP data channel" },
+	{ "dut_ctrl_ip", 'C', "DUT-CTRL-IP", 0, "DUT IP control channel" },
+	{ "tester_data_ip", 'T', "TESTER-DATA-IP", 0, "Tester IP data channel"  

},

tools/testing/selftests/bpf/xdp_features.c new file +432 -0

+	{},
+};
+
+static int get_xdp_feature(const char *arg)
+{
+	if (!strcmp(arg, "XDP_PASS")) {
+		env.feature.action = XDP_PASS;
+		env.feature.drv_feature = NETDEV_XDP_ACT_BASIC;
+	} else if (!strcmp(arg, "XDP_DROP")) {
+		env.feature.drv_feature = NETDEV_XDP_ACT_BASIC;
+		env.feature.action = XDP_DROP;
+	} else if (!strcmp(arg, "XDP_ABORTED")) {
+		env.feature.drv_feature = NETDEV_XDP_ACT_BASIC;
+		env.feature.action = XDP_ABORTED;
+	} else if (!strcmp(arg, "XDP_TX")) {
+		env.feature.drv_feature = NETDEV_XDP_ACT_BASIC;
+		env.feature.action = XDP_TX;
+	} else if (!strcmp(arg, "XDP_REDIRECT")) {
+		env.feature.drv_feature = NETDEV_XDP_ACT_REDIRECT;
+		env.feature.action = XDP_REDIRECT;
+	} else if (!strcmp(arg, "XDP_NDO_XMIT")) {
+		env.feature.drv_feature = NETDEV_XDP_ACT_NDO_XMIT;
+	} else {
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static char *get_xdp_feature_str(void)
+{
+	switch (env.feature.action) {
+	case XDP_PASS:
+		return YELLOW("XDP_PASS");
+	case XDP_DROP:
+		return YELLOW("XDP_DROP");
+	case XDP_ABORTED:
+		return YELLOW("XDP_ABORTED");
+	case XDP_TX:
+		return YELLOW("XDP_TX");
+	case XDP_REDIRECT:
+		return YELLOW("XDP_REDIRECT");
+	default:
+		break;
+	}
+
+	if (env.feature.drv_feature == NETDEV_XDP_ACT_NDO_XMIT)
+		return YELLOW("XDP_NDO_XMIT");
+
+	return "";
+}
+
+static error_t parse_arg(int key, char *arg, struct argp_state *state)
+{
+	switch (key) {
+	case 'v':
+		env.verbosity = true;
+		break;
+	case 't':
+		env.is_tester = true;
+		break;
+	case 'f':
+		if (get_xdp_feature(arg) < 0) {
+			fprintf(stderr, "Invalid xdp feature: %s\n", arg);
+			argp_usage(state);
+			return ARGP_ERR_UNKNOWN;
+		}
+		break;
+	case 'D':
+		if (make_sockaddr(AF_INET6, arg, DUT_ECHO_PORT,
+				  &env.dut_addr, NULL)) {
+			fprintf(stderr, "Invalid DUT address: %s\n", arg);
+			return ARGP_ERR_UNKNOWN;
+		}
+		break;
+	case 'C':
+		if (make_sockaddr(AF_INET6, arg, DUT_CTRL_PORT,
+				  &env.dut_ctrl_addr, NULL)) {
+			fprintf(stderr, "Invalid DUT CTRL address: %s\n", arg);
+			return ARGP_ERR_UNKNOWN;
+		}
+		break;
+	case 'T':
+		if (make_sockaddr(AF_INET6, arg, 0, &env.tester_addr, NULL)) {
+			fprintf(stderr, "Invalid Tester address: %s\n", arg);
+			return ARGP_ERR_UNKNOWN;
+		}
+		break;
+	case ARGP_KEY_ARG:
+		errno = 0;
+		if (strlen(arg) >= IF_NAMESIZE) {
+			fprintf(stderr, "Invalid device name: %s\n", arg);
+			argp_usage(state);
+			return ARGP_ERR_UNKNOWN;
+		}
+
+		env.ifindex = if_nametoindex(arg);
+		if (!env.ifindex)
+			env.ifindex = strtoul(arg, NULL, 0);
+		if (!env.ifindex) {
+			fprintf(stderr,
+				"Bad interface index or name (%d): %s\n",
+				errno, strerror(errno));
+			argp_usage(state);
+			return ARGP_ERR_UNKNOWN;
+		}
+		break;
+	default:
+		return ARGP_ERR_UNKNOWN;
+	}
+
+	return 0;
+}
+
+static const struct argp argp = {
+	.options = opts,
+	.parser = parse_arg,
+	.doc = argp_program_doc,
+};
+
+static void set_env_default(void)
+{
+	env.feature.drv_feature = NETDEV_XDP_ACT_NDO_XMIT;
+	env.feature.action = -EINVAL;
+	env.ifindex = -ENODEV;
+	make_sockaddr(AF_INET6, "::ffff:127.0.0.1", DUT_CTRL_PORT,
+		      &env.dut_ctrl_addr, NULL);
+	make_sockaddr(AF_INET6, "::ffff:127.0.0.1", DUT_ECHO_PORT,
+		      &env.dut_addr, NULL);
+	make_sockaddr(AF_INET6, "::ffff:127.0.0.1", 0, &env.tester_addr, NULL);
+}
+
+static void *dut_echo_thread(void *arg)
+{
+	unsigned char buf[sizeof(struct tlv_hdr)];
+	int sockfd = *(int *)arg;
+
+	while (!exiting) {
+		struct tlv_hdr *tlv = (struct tlv_hdr *)buf;
+		struct sockaddr_storage addr;
+		socklen_t addrlen;
+		size_t n;
+
+		n = recvfrom(sockfd, buf, sizeof(buf), MSG_WAITALL,
+			     (struct sockaddr *)&addr, &addrlen);
+		if (n != ntohs(tlv->len))
+			continue;
+
+		if (ntohs(tlv->type) != CMD_ECHO)
+			continue;
+
+		sendto(sockfd, buf, sizeof(buf), MSG_NOSIGNAL | MSG_CONFIRM,
+		       (struct sockaddr *)&addr, addrlen);
+	}
+
+	pthread_exit((void *)0);
+	close(sockfd);
+
+	return NULL;
+}
+
+static int dut_run_echo_thread(pthread_t *t, int *sockfd)
+{
+	int err;
+
+	sockfd = start_reuseport_server(AF_INET6, SOCK_DGRAM, NULL,
+					DUT_ECHO_PORT, 0, 1);
+	if (!sockfd) {
+		fprintf(stderr, "Failed to create echo socket\n");
+		return -errno;
+	}
+
+	/* start echo channel */
+	err = pthread_create(t, NULL, dut_echo_thread, sockfd);
+	if (err) {
+		fprintf(stderr, "Failed creating dut_echo thread: %s\n",
+			strerror(-err));
+		free_fds(sockfd, 1);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int dut_attach_xdp_prog(struct xdp_features *skel, int flags)
+{
+	enum xdp_action action = env.feature.action;
+	struct bpf_program *prog;
+	unsigned int key = 0;
+	int err, fd = 0;
+
+	if (env.feature.drv_feature == NETDEV_XDP_ACT_NDO_XMIT) {
+		struct bpf_devmap_val entry = {
+			.ifindex = env.ifindex,
+		};
+
+		err = bpf_map__update_elem(skel->maps.dev_map,
+					   &key, sizeof(key),
+					   &entry, sizeof(entry), 0);
+		if (err < 0)
+			return err;
+
+		fd = bpf_program__fd(skel->progs.xdp_do_redirect_cpumap);
+		action = XDP_REDIRECT;
+	}
+
+	switch (action) {
+	case XDP_TX:
+		prog = skel->progs.xdp_do_tx;
+		break;
+	case XDP_DROP:
+		prog = skel->progs.xdp_do_drop;
+		break;
+	case XDP_ABORTED:
+		prog = skel->progs.xdp_do_aborted;
+		break;
+	case XDP_PASS:
+		prog = skel->progs.xdp_do_pass;
+		break;
+	case XDP_REDIRECT: {
+		struct bpf_cpumap_val entry = {
+			.qsize = 2048,
+			.bpf_prog.fd = fd,
+		};
+
+		err = bpf_map__update_elem(skel->maps.cpu_map,
+					   &key, sizeof(key),
+					   &entry, sizeof(entry), 0);
+		if (err < 0)
+			return err;
+
+		prog = skel->progs.xdp_do_redirect;
+		break;
+	}
+	default:
+		return -EINVAL;
+	}
+
+	err = bpf_xdp_attach(env.ifindex, bpf_program__fd(prog), flags, NULL);
+	if (err)
+		fprintf(stderr,
+			"Failed to attach XDP program to ifindex %d\n",
+			env.ifindex);
+	return err;
+}
+
+static int recv_msg(int sockfd, void *buf, size_t bufsize, void *val,
+		    size_t val_size)
+{
+	struct tlv_hdr *tlv = (struct tlv_hdr *)buf;
+	size_t len;
+
+	len = recv(sockfd, buf, bufsize, 0);
+	if (len != ntohs(tlv->len) || len < sizeof(*tlv))
+		return -EINVAL;
+
+	if (val) {
+		len -= sizeof(*tlv);
+		if (len > val_size)
+			return -ENOMEM;
+
+		memcpy(val, tlv->data, len);
+	}
+
+	return 0;
+}
+
+static int dut_run(struct xdp_features *skel)
+{
+	int flags = XDP_FLAGS_UPDATE_IF_NOEXIST | XDP_FLAGS_DRV_MODE;
+	int state, err, *sockfd, ctrl_sockfd, echo_sockfd;
+	struct sockaddr_storage ctrl_addr;
+	pthread_t dut_thread;
+	socklen_t addrlen;
+
+	sockfd = start_reuseport_server(AF_INET6, SOCK_STREAM, NULL,
+					DUT_CTRL_PORT, 0, 1);
+	if (!sockfd) {
+		fprintf(stderr, "Failed to create DUT socket\n");
+		return -errno;
+	}
+
+	ctrl_sockfd = accept(*sockfd, (struct sockaddr *)&ctrl_addr, &addrlen);
+	if (ctrl_sockfd < 0) {
+		fprintf(stderr, "Failed to accept connection on DUT socket\n");
+		free_fds(sockfd, 1);
+		return -errno;
+	}
+
+	/* CTRL loop */
+	while (!exiting) {
+		unsigned char buf[BUFSIZE] = {};
+		struct tlv_hdr *tlv = (struct tlv_hdr *)buf;
+
+		err = recv_msg(ctrl_sockfd, buf, BUFSIZE, NULL, 0);
+		if (err)
+			continue;
+
+		switch (ntohs(tlv->type)) {
+		case CMD_START: {
+			if (state == CMD_START)
+				continue;
+
+			state = CMD_START;
+			/* Load the XDP program on the DUT */
+			err = dut_attach_xdp_prog(skel, flags);
+			if (err)
+				goto out;
+
+			err = dut_run_echo_thread(&dut_thread, &echo_sockfd);
+			if (err < 0)
+				goto out;
+
+			tlv->type = htons(CMD_ACK);
+			tlv->len = htons(sizeof(*tlv));
+			err = send(ctrl_sockfd, buf, sizeof(*tlv), 0);
+			if (err < 0)
+				goto end_thread;
+			break;
+		}
+		case CMD_STOP:
+			if (state != CMD_START)
+				break;
+
+			state = CMD_STOP;
+
+			exiting = true;
+			bpf_xdp_detach(env.ifindex, flags, NULL);
+
+			tlv->type = htons(CMD_ACK);
+			tlv->len = htons(sizeof(*tlv));
+			err = send(ctrl_sockfd, buf, sizeof(*tlv), 0);
+			goto end_thread;
+		case CMD_GET_XDP_CAP: {
+			LIBBPF_OPTS(bpf_xdp_query_opts, opts);
+			unsigned long long val;
+			size_t n;
+
+			err = bpf_xdp_query(env.ifindex, XDP_FLAGS_DRV_MODE,
+					    &opts);
+			if (err) {
+				fprintf(stderr,
+					"Failed to query XDP cap for ifindex %d\n",
+					env.ifindex);
+				goto end_thread;
+			}
+
+			tlv->type = htons(CMD_ACK);
+			n = sizeof(*tlv) + sizeof(opts.feature_flags);
+			tlv->len = htons(n);
+
+			val = htobe64(opts.feature_flags);
+			memcpy(tlv->data, &val, sizeof(val));
+
+			err = send(ctrl_sockfd, buf, n, 0);
+			if (err < 0)
+				goto end_thread;
+			break;
+		}
+		case CMD_GET_STATS: {
+			unsigned int key = 0, val;
+			size_t n;
+
+			err = bpf_map__lookup_elem(skel->maps.dut_stats,
+						   &key, sizeof(key),
+						   &val, sizeof(val), 0);
+			if (err) {
+				fprintf(stderr, "bpf_map_lookup_elem failed\n");
+				goto end_thread;
+			}
+
+			tlv->type = htons(CMD_ACK);
+			n = sizeof(*tlv) + sizeof(val);
+			tlv->len = htons(n);
+
+			val = htonl(val);
+			memcpy(tlv->data, &val, sizeof(val));
+
+			err = send(ctrl_sockfd, buf, n, 0);
+			if (err < 0)
+				goto end_thread;
+			break;
+		}
+		default:
+			break;
+		}
+	}
+
+end_thread:
+	pthread_join(dut_thread, NULL);
+out:
+	bpf_xdp_detach(env.ifindex, flags, NULL);
+	close(ctrl_sockfd);
+	free_fds(sockfd, 1);
+
+	return err;
+}
+
+static bool tester_collect_detected_cap(struct xdp_features *skel,
+					unsigned int dut_stats)
+{
+	unsigned int err, key = 0, val;
+
+	if (!dut_stats)
+		return false;
+
+	err = bpf_map__lookup_elem(skel->maps.stats, &key, sizeof(key),
+				   &val, sizeof(val), 0);
+	if (err) {
+		fprintf(stderr, "bpf_map_lookup_elem failed\n");
+		return false;
+	}
+
+	switch (env.feature.action) {
+	case XDP_PASS:
+	case XDP_TX:
+	case XDP_REDIRECT:
+		return val > 0;
+	case XDP_DROP:
+	case XDP_ABORTED:
+		return val == 0;
+	default:
+		break;
+	}
+
+	if (env.feature.drv_feature == NETDEV_XDP_ACT_NDO_XMIT)
+		return val > 0;
+
+	return false;
+}
+
+static int send_and_recv_msg(int sockfd, enum test_commands cmd, void  

*val,

tools/testing/selftests/bpf/xdp_features.c new file +185 -0

+			     size_t val_size)
+{
+	unsigned char buf[BUFSIZE] = {};
+	struct tlv_hdr *tlv = (struct tlv_hdr *)buf;
+	int err;
+
+	tlv->type = htons(cmd);
+	tlv->len = htons(sizeof(*tlv));
+
+	err = send(sockfd, buf, sizeof(*tlv), 0);
+	if (err < 0)
+		return err;
+
+	err = recv_msg(sockfd, buf, BUFSIZE, val, val_size);
+	if (err < 0)
+		return err;
+
+	return ntohs(tlv->type) == CMD_ACK ? 0 : -EINVAL;
+}
+
+static int send_echo_msg(void)
+{
+	unsigned char buf[sizeof(struct tlv_hdr)];
+	struct tlv_hdr *tlv = (struct tlv_hdr *)buf;
+	int sockfd, n;
+
+	sockfd = socket(AF_INET6, SOCK_DGRAM, 0);
+	if (sockfd < 0) {
+		fprintf(stderr, "Failed to create echo socket\n");
+		return -errno;
+	}
+
+	tlv->type = htons(CMD_ECHO);
+	tlv->len = htons(sizeof(*tlv));
+
+	n = sendto(sockfd, buf, sizeof(*tlv), MSG_NOSIGNAL | MSG_CONFIRM,
+		   (struct sockaddr *)&env.dut_addr, sizeof(env.dut_addr));
+	close(sockfd);
+
+	return n == ntohs(tlv->len) ? 0 : -EINVAL;
+}
+
+static int tester_run(struct xdp_features *skel)
+{
+	int flags = XDP_FLAGS_UPDATE_IF_NOEXIST | XDP_FLAGS_DRV_MODE;
+	unsigned long long advertised_feature;
+	struct bpf_program *prog;
+	unsigned int stats;
+	int i, err, sockfd;
+	bool detected_cap;
+
+	sockfd = socket(AF_INET6, SOCK_STREAM, 0);
+	if (sockfd < 0) {
+		fprintf(stderr, "Failed to create tester socket\n");
+		return -errno;
+	}
+
+	if (settimeo(sockfd, 1000) < 0)
+		return -EINVAL;
+
+	err = connect(sockfd, (struct sockaddr *)&env.dut_ctrl_addr,
+		      sizeof(env.dut_ctrl_addr));
+	if (err) {
+		fprintf(stderr, "Failed to connect to the DUT\n");
+		return -errno;
+	}
+
+	err = send_and_recv_msg(sockfd, CMD_GET_XDP_CAP, &advertised_feature,
+				sizeof(advertised_feature));
+	if (err < 0) {
+		close(sockfd);
+		return err;
+	}
+
+	advertised_feature = be64toh(advertised_feature);
+
+	if (env.feature.drv_feature == NETDEV_XDP_ACT_NDO_XMIT ||
+	    env.feature.action == XDP_TX)
+		prog = skel->progs.xdp_tester_check_tx;
+	else
+		prog = skel->progs.xdp_tester_check_rx;
+
+	err = bpf_xdp_attach(env.ifindex, bpf_program__fd(prog), flags, NULL);
+	if (err) {
+		fprintf(stderr, "Failed to attach XDP program to ifindex %d\n",
+			env.ifindex);
+		goto out;
+	}
+
+	err = send_and_recv_msg(sockfd, CMD_START, NULL, 0);
+	if (err)
+		goto out;
+
+	for (i = 0; i < 10 && !exiting; i++) {
+		err = send_echo_msg();
+		if (err < 0)
+			goto out;
+
+		sleep(1);
+	}
+
+	err = send_and_recv_msg(sockfd, CMD_GET_STATS, &stats, sizeof(stats));
+	if (err)
+		goto out;
+
+	/* stop the test */
+	err = send_and_recv_msg(sockfd, CMD_STOP, NULL, 0);
+	/* send a new echo message to wake echo thread of the dut */
+	send_echo_msg();
+
+	detected_cap = tester_collect_detected_cap(skel, ntohl(stats));
+
+	fprintf(stdout, "Feature %s: [%s][%s]\n", get_xdp_feature_str(),
+		detected_cap ? GREEN("DETECTED") : RED("NOT DETECTED"),
+		env.feature.drv_feature & advertised_feature ? GREEN("ADVERTISED")
+							     : RED("NOT ADVERTISED"));
+out:
+	bpf_xdp_detach(env.ifindex, flags, NULL);
+	close(sockfd);
+	return err < 0 ? err : 0;
+}
+
+int main(int argc, char **argv)
+{
+	struct xdp_features *skel;
+	int err;
+
+	libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
+	libbpf_set_print(libbpf_print_fn);
+
+	signal(SIGINT, sig_handler);
+	signal(SIGTERM, sig_handler);
+
+	set_env_default();
+
+	/* Parse command line arguments */
+	err = argp_parse(&argp, argc, argv, 0, NULL, NULL);
+	if (err)
+		return err;
+
+	if (env.ifindex < 0) {
+		fprintf(stderr, "Invalid ifindex\n");
+		return -ENODEV;
+	}
+
+	/* Load and verify BPF application */
+	skel = xdp_features__open();
+	if (!skel) {
+		fprintf(stderr, "Failed to open and load BPF skeleton\n");
+		return -EINVAL;
+	}
+
+	skel->rodata->tester_addr =
+		((struct sockaddr_in6 *)&env.tester_addr)->sin6_addr;
+	skel->rodata->dut_addr =
+		((struct sockaddr_in6 *)&env.dut_addr)->sin6_addr;
+
+	/* Load & verify BPF programs */
+	err = xdp_features__load(skel);
+	if (err) {
+		fprintf(stderr, "Failed to load and verify BPF skeleton\n");
+		goto cleanup;
+	}
+
+	err = xdp_features__attach(skel);
+	if (err) {
+		fprintf(stderr, "Failed to attach BPF skeleton\n");
+		goto cleanup;
+	}
+
+	if (env.is_tester) {
+		/* Tester */
+		fprintf(stdout, "Starting tester on device %d\n", env.ifindex);
+		err = tester_run(skel);
+	} else {
+		/* DUT */
+		fprintf(stdout, "Starting DUT on device %d\n", env.ifindex);
+		err = dut_run(skel);
+	}
+
+cleanup:
+	xdp_features__destroy(skel);
+
+	return err < 0 ? -err : 0;
+}

tools/testing/selftests/bpf/xdp_features.h new file +20 -1

new file mode 100644
index 000000000000..2670c541713b
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/* test commands */
+enum test_commands {
+	CMD_STOP,		/* CMD */
+	CMD_START,		/* CMD */
+	CMD_ECHO,		/* CMD */
+	CMD_ACK,		/* CMD + data */
+	CMD_GET_XDP_CAP,	/* CMD */
+	CMD_GET_STATS,		/* CMD */
+};
+
+#define DUT_CTRL_PORT	12345
+#define DUT_ECHO_PORT	12346
+
+struct tlv_hdr {
+	__be16 type;
+	__be16 len;
+	__u8 data[];
+};
--