Merge tag 'net-6.5-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni:
"Including fixes from wifi, can and netfilter.

Fixes to fixes:

- nf_tables:
- GC transaction race with abort path
- defer gc run if previous batch is still pending

Previous releases - regressions:

- ipv4: fix data-races around inet->inet_id

- phy: fix deadlocking in phy_error() invocation

- mdio: fix C45 read/write protocol

- ipvlan: fix a reference count leak warning in ipvlan_ns_exit()

- ice: fix NULL pointer deref during VF reset

- i40e: fix potential NULL pointer dereferencing of pf->vf in
i40e_sync_vsi_filters()

- tg3: use slab_build_skb() when needed

- mtk_eth_soc: fix NULL pointer on hw reset

Previous releases - always broken:

- core: validate veth and vxcan peer ifindexes

- sched: fix a qdisc modification with ambiguous command request

- devlink: add missing unregister linecard notification

- wifi: mac80211: limit reorder_buf_filtered to avoid UBSAN warning

- batman:
- do not get eth header before batadv_check_management_packet
- fix batadv_v_ogm_aggr_send memory leak

- bonding: fix macvlan over alb bond support

- mlxsw: set time stamp fields also when its type is MIRROR_UTC"

* tag 'net-6.5-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (54 commits)
selftests: bonding: add macvlan over bond testing
selftest: bond: add new topo bond_topo_2d1c.sh
bonding: fix macvlan over alb bond support
rtnetlink: Reject negative ifindexes in RTM_NEWLINK
netfilter: nf_tables: defer gc run if previous batch is still pending
netfilter: nf_tables: fix out of memory error handling
netfilter: nf_tables: use correct lock to protect gc_list
netfilter: nf_tables: GC transaction race with abort path
netfilter: nf_tables: flush pending destroy work before netlink notifier
netfilter: nf_tables: validate all pending tables
ibmveth: Use dcbf rather than dcbfl
i40e: fix potential NULL pointer dereferencing of pf->vf i40e_sync_vsi_filters()
net/sched: fix a qdisc modification with ambiguous command request
igc: Fix the typo in the PTM Control macro
batman-adv: Hold rtnl lock during MTU update via netlink
igb: Avoid starting unnecessary workqueues
can: raw: add missing refcount for memory leak fix
can: isotp: fix support for transmission of SF without flow control
bnx2x: new flag for track HW resource allocation
sfc: allocate a big enough SKB for loopback selftest packet
...

Documentation/ABI/testing/sysfs-class-led-trigger-netdev

···
 		Specifies the duration of the LED blink in milliseconds.
 		Defaults to 50 ms.
 
-		With hw_control ON, the interval value MUST be set to the
+		When offloaded is true, the interval value MUST be set to the
 		default value and cannot be changed.
 		Trying to set any value in this specific mode will return
 		an EINVAL error.
···
 		If set to 1, the LED will blink for the milliseconds specified
 		in interval to signal transmission.
 
-		With hw_control ON, the blink interval is controlled by hardware
-		and won't reflect the value set in interval.
+		When offloaded is true, the blink interval is controlled by
+		hardware and won't reflect the value set in interval.
 
 What:		/sys/class/leds/<led>/rx
 Date:		Dec 2017
···
 		If set to 1, the LED will blink for the milliseconds specified
 		in interval to signal reception.
 
-		With hw_control ON, the blink interval is controlled by hardware
-		and won't reflect the value set in interval.
+		When offloaded is true, the blink interval is controlled by
+		hardware and won't reflect the value set in interval.
 
-What:		/sys/class/leds/<led>/hw_control
+What:		/sys/class/leds/<led>/offloaded
 Date:		Jun 2023
 KernelVersion:	6.5
 Contact:	[e-mail]
 Description:
-		Communicate whether the LED trigger modes are driven by hardware
-		or software fallback is used.
+		Communicate whether the LED trigger modes are offloaded to
+		hardware or whether software fallback is used.
 
 		If 0, the LED is using software fallback to blink.
 
-		If 1, the LED is using hardware control to blink and signal the
-		requested modes.
+		If 1, the LED blinking in requested mode is offloaded to
+		hardware.
 
 What:		/sys/class/leds/<led>/link_10
 Date:		Jun 2023

MAINTAINERS

···
 F:	net/netfilter/xt_SECMARK.c
 F:	net/netlabel/
 
+NETWORKING [MACSEC]
+M:	Sabrina Dubroca <[e-mail]>
+L:	[e-mail]
+S:	Maintained
+F:	drivers/net/macsec.c
+F:	include/net/macsec.h
+F:	include/uapi/linux/if_macsec.h
+K:	macsec
+K:	\bmdo_
+
 NETWORKING [MPTCP]
 M:	Matthieu Baerts <[e-mail]>
 M:	Mat Martineau <[e-mail]>

drivers/leds/trigger/ledtrig-netdev.c

···
 
 static DEVICE_ATTR_RW(interval);
 
-static ssize_t hw_control_show(struct device *dev,
-			       struct device_attribute *attr, char *buf)
+static ssize_t offloaded_show(struct device *dev,
+			      struct device_attribute *attr, char *buf)
 {
 	struct led_netdev_data *trigger_data = led_trigger_get_drvdata(dev);
 
 	return sprintf(buf, "%d\n", trigger_data->hw_control);
 }
 
-static DEVICE_ATTR_RO(hw_control);
+static DEVICE_ATTR_RO(offloaded);
 
 static struct attribute *netdev_trig_attrs[] = {
 	&dev_attr_device_name.attr,
···
 	&dev_attr_rx.attr,
 	&dev_attr_tx.attr,
 	&dev_attr_interval.attr,
-	&dev_attr_hw_control.attr,
+	&dev_attr_offloaded.attr,
 	NULL
 };
 ATTRIBUTE_GROUPS(netdev_trig);

drivers/net/bonding/bond_alb.c

···
 		return NULL;
 	arp = (struct arp_pkt *)skb_network_header(skb);
 
-	/* Don't modify or load balance ARPs that do not originate locally
-	 * (e.g.,arrive via a bridge).
+	/* Don't modify or load balance ARPs that do not originate
+	 * from the bond itself or a VLAN directly above the bond.
 	 */
-	if (!bond_slave_has_mac_rx(bond, arp->mac_src))
+	if (!bond_slave_has_mac_rcu(bond, arp->mac_src))
 		return NULL;
 
 	dev = ip_dev_find(dev_net(bond->dev), arp->ip_src);

drivers/net/can/vxcan.c

···
 
 		nla_peer = data[VXCAN_INFO_PEER];
 		ifmp = nla_data(nla_peer);
-		err = rtnl_nla_parse_ifla(peer_tb,
-					  nla_data(nla_peer) +
-					  sizeof(struct ifinfomsg),
-					  nla_len(nla_peer) -
-					  sizeof(struct ifinfomsg),
-					  NULL);
+		err = rtnl_nla_parse_ifinfomsg(peer_tb, nla_peer, extack);
 		if (err < 0)
 			return err;
 

drivers/net/dsa/mt7530.c

···
 	mt7530_rmw(priv, MT753X_BPC, MT753X_BPDU_PORT_FW_MASK,
 		   MT753X_BPDU_CPU_ONLY);
 
+	/* Trap 802.1X PAE frames to the CPU port(s) */
+	mt7530_rmw(priv, MT753X_BPC, MT753X_PAE_PORT_FW_MASK,
+		   MT753X_PAE_PORT_FW(MT753X_BPDU_CPU_ONLY));
+
 	/* Trap LLDP frames with :0E MAC DA to the CPU port(s) */
 	mt7530_rmw(priv, MT753X_RGAC2, MT753X_R0E_PORT_FW_MASK,
 		   MT753X_R0E_PORT_FW(MT753X_BPDU_CPU_ONLY));

drivers/net/dsa/mt7530.h

···
 /* Registers for BPDU and PAE frame control*/
 #define MT753X_BPC			0x24
 #define  MT753X_BPDU_PORT_FW_MASK	GENMASK(2, 0)
+#define  MT753X_PAE_PORT_FW_MASK	GENMASK(18, 16)
+#define  MT753X_PAE_PORT_FW(x)		FIELD_PREP(MT753X_PAE_PORT_FW_MASK, x)
 
 /* Register for :03 and :0E MAC DA frame control */
 #define MT753X_RGAC2			0x2c

drivers/net/dsa/ocelot/felix_vsc9959.c

···
 	if (gate_len_ns == U64_MAX)
 		return U64_MAX;
 
+	if (gate_len_ns < VSC9959_TAS_MIN_GATE_LEN_NS)
+		return 0;
+
 	return (gate_len_ns - VSC9959_TAS_MIN_GATE_LEN_NS) * PSEC_PER_NSEC;
 }
 

drivers/net/ethernet/broadcom/bgmac.c

···
 	int err;
 
 	phy_dev = fixed_phy_register(PHY_POLL, &fphy_status, NULL);
-	if (!phy_dev || IS_ERR(phy_dev)) {
+	if (IS_ERR(phy_dev)) {
 		dev_err(bgmac->dev, "Failed to register fixed PHY device\n");
 		return -ENODEV;
 	}

drivers/net/ethernet/broadcom/bnx2x/bnx2x.h

···
 	bool			cnic_loaded;
 	struct cnic_eth_dev	*(*cnic_probe)(struct net_device *);
 
+	bool                    nic_stopped;
+
 	/* Flag that indicates that we can start looking for FCoE L2 queue
 	 * completions in the default status block.
 	 */

drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c

···
 	bnx2x_add_all_napi(bp);
 	DP(NETIF_MSG_IFUP, "napi added\n");
 	bnx2x_napi_enable(bp);
+	bp->nic_stopped = false;
 
 	if (IS_PF(bp)) {
 		/* set pf load just before approaching the MCP */
···
 load_error1:
 	bnx2x_napi_disable(bp);
 	bnx2x_del_all_napi(bp);
+	bp->nic_stopped = true;
 
 	/* clear pf_load status, as it was already set */
 	if (IS_PF(bp))
···
 		if (!CHIP_IS_E1x(bp))
 			bnx2x_pf_disable(bp);
 
-		/* Disable HW interrupts, NAPI */
-		bnx2x_netif_stop(bp, 1);
-		/* Delete all NAPI objects */
-		bnx2x_del_all_napi(bp);
-		if (CNIC_LOADED(bp))
-			bnx2x_del_all_napi_cnic(bp);
-		/* Release IRQs */
-		bnx2x_free_irq(bp);
+		if (!bp->nic_stopped) {
+			/* Disable HW interrupts, NAPI */
+			bnx2x_netif_stop(bp, 1);
+			/* Delete all NAPI objects */
+			bnx2x_del_all_napi(bp);
+			if (CNIC_LOADED(bp))
+				bnx2x_del_all_napi_cnic(bp);
+			/* Release IRQs */
+			bnx2x_free_irq(bp);
+			bp->nic_stopped = true;
+		}
 
 		/* Report UNLOAD_DONE to MCP */
 		bnx2x_send_unload_done(bp, false);

drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c

···
 		}
 	}
 
-	/* Disable HW interrupts, NAPI */
-	bnx2x_netif_stop(bp, 1);
-	/* Delete all NAPI objects */
-	bnx2x_del_all_napi(bp);
-	if (CNIC_LOADED(bp))
-		bnx2x_del_all_napi_cnic(bp);
+	if (!bp->nic_stopped) {
+		/* Disable HW interrupts, NAPI */
+		bnx2x_netif_stop(bp, 1);
+		/* Delete all NAPI objects */
+		bnx2x_del_all_napi(bp);
+		if (CNIC_LOADED(bp))
+			bnx2x_del_all_napi_cnic(bp);
 
-	/* Release IRQs */
-	bnx2x_free_irq(bp);
+		/* Release IRQs */
+		bnx2x_free_irq(bp);
+		bp->nic_stopped = true;
+	}
 
 	/* Reset the chip, unless PCI function is offline. If we reach this
 	 * point following a PCI error handling, it means device is really
···
 		}
 		bnx2x_drain_tx_queues(bp);
 		bnx2x_send_unload_req(bp, UNLOAD_RECOVERY);
-		bnx2x_netif_stop(bp, 1);
-		bnx2x_del_all_napi(bp);
+		if (!bp->nic_stopped) {
+			bnx2x_netif_stop(bp, 1);
+			bnx2x_del_all_napi(bp);
 
-		if (CNIC_LOADED(bp))
-			bnx2x_del_all_napi_cnic(bp);
+			if (CNIC_LOADED(bp))
+				bnx2x_del_all_napi_cnic(bp);
 
-		bnx2x_free_irq(bp);
+			bnx2x_free_irq(bp);
+			bp->nic_stopped = true;
+		}
 
 		/* Report UNLOAD_DONE to MCP */
 		bnx2x_send_unload_done(bp, true);

drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c

···
 	bnx2x_vfpf_finalize(bp, &req->first_tlv);
 
 free_irq:
-	/* Disable HW interrupts, NAPI */
-	bnx2x_netif_stop(bp, 0);
-	/* Delete all NAPI objects */
-	bnx2x_del_all_napi(bp);
+	if (!bp->nic_stopped) {
+		/* Disable HW interrupts, NAPI */
+		bnx2x_netif_stop(bp, 0);
+		/* Delete all NAPI objects */
+		bnx2x_del_all_napi(bp);
 
-	/* Release IRQs */
-	bnx2x_free_irq(bp);
+		/* Release IRQs */
+		bnx2x_free_irq(bp);
+		bp->nic_stopped = true;
+	}
 }
 
 static void bnx2x_leading_vfq_init(struct bnx2x *bp, struct bnx2x_virtf *vf,

drivers/net/ethernet/broadcom/genet/bcmmii.c

···
 		};
 
 		phydev = fixed_phy_register(PHY_POLL, &fphy_status, NULL);
-		if (!phydev || IS_ERR(phydev)) {
+		if (IS_ERR(phydev)) {
 			dev_err(kdev, "failed to register fixed PHY device\n");
 			return -ENODEV;
 		}

drivers/net/ethernet/broadcom/tg3.c

···
 
 			ri->data = NULL;
 
-			skb = build_skb(data, frag_size);
+			if (frag_size)
+				skb = build_skb(data, frag_size);
+			else
+				skb = slab_build_skb(data);
 			if (!skb) {
 				tg3_frag_free(frag_size != 0, data);
 				goto drop_it_no_recycle;

drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c

···
 	tp->write_seq = snd_isn;
 	tp->snd_nxt = snd_isn;
 	tp->snd_una = snd_isn;
-	inet_sk(sk)->inet_id = get_random_u16();
+	atomic_set(&inet_sk(sk)->inet_id, get_random_u16());
 	assign_rxopt(sk, opt);
 
 	if (tp->rcv_wnd > (RCV_BUFSIZ_M << 10))

drivers/net/ethernet/ibm/ibmveth.c

···
 	unsigned long offset;
 
 	for (offset = 0; offset < length; offset += SMP_CACHE_BYTES)
-		asm("dcbfl %0,%1" :: "b" (addr), "r" (offset));
+		asm("dcbf %0,%1,1" :: "b" (addr), "r" (offset));
 }
 
 /* replenish the buffers for a pool.  note that we don't need to

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

···
 			retval = i40e_correct_mac_vlan_filters
 				(vsi, &tmp_add_list, &tmp_del_list,
 				 vlan_filters);
-		else
+		else if (pf->vf)
 			retval = i40e_correct_vf_mac_vlan_filters
 				(vsi, &tmp_add_list, &tmp_del_list,
 				 vlan_filters, pf->vf[vsi->vf_id].trusted);
···
 	}
 
 	/* if the VF is not trusted do not do promisc */
-	if ((vsi->type == I40E_VSI_SRIOV) && !pf->vf[vsi->vf_id].trusted) {
+	if (vsi->type == I40E_VSI_SRIOV && pf->vf &&
+	    !pf->vf[vsi->vf_id].trusted) {
 		clear_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state);
 		goto out;
 	}

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

···
 	/* Receive Packet Data Buffer Size.
 	 * The Packet Data Buffer Size is defined in 128 byte units.
 	 */
-	rlan_ctx.dbuf = ring->rx_buf_len >> ICE_RLAN_CTX_DBUF_S;
+	rlan_ctx.dbuf = DIV_ROUND_UP(ring->rx_buf_len,
+				     BIT_ULL(ICE_RLAN_CTX_DBUF_S));
 
 	/* use 32 byte descriptors */
 	rlan_ctx.dsize = 1;

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

···
 	if (!vf)
 		return -EINVAL;
 
-	ret = ice_check_vf_ready_for_reset(vf);
+	ret = ice_check_vf_ready_for_cfg(vf);
 	if (ret)
 		goto out_put_vf;
 
···
 		goto out_put_vf;
 	}
 
-	ret = ice_check_vf_ready_for_reset(vf);
+	ret = ice_check_vf_ready_for_cfg(vf);
 	if (ret)
 		goto out_put_vf;
 
···
 		return -EOPNOTSUPP;
 	}
 
-	ret = ice_check_vf_ready_for_reset(vf);
+	ret = ice_check_vf_ready_for_cfg(vf);
 	if (ret)
 		goto out_put_vf;
 
···
 	if (!vf)
 		return -EINVAL;
 
-	ret = ice_check_vf_ready_for_reset(vf);
+	ret = ice_check_vf_ready_for_cfg(vf);
 	if (ret)
 		goto out_put_vf;
 

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

···
 }
 
 /**
- * ice_check_vf_ready_for_reset - check if VF is ready to be reset
- * @vf: VF to check if it's ready to be reset
- *
- * The purpose of this function is to ensure that the VF is not in reset,
- * disabled, and is both initialized and active, thus enabling us to safely
- * initialize another reset.
- */
-int ice_check_vf_ready_for_reset(struct ice_vf *vf)
-{
-	int ret;
-
-	ret = ice_check_vf_ready_for_cfg(vf);
-	if (!ret && !test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states))
-		ret = -EAGAIN;
-
-	return ret;
-}
-
-/**
  * ice_trigger_vf_reset - Reset a VF on HW
  * @vf: pointer to the VF structure
  * @is_vflr: true if VFLR was issued, false if not
···
 		return 0;
 	}
 
+	if (flags & ICE_VF_RESET_LOCK)
+		mutex_lock(&vf->cfg_lock);
+	else
+		lockdep_assert_held(&vf->cfg_lock);
+
 	if (ice_is_vf_disabled(vf)) {
 		vsi = ice_get_vf_vsi(vf);
 		if (!vsi) {
 			dev_dbg(dev, "VF is already removed\n");
-			return -EINVAL;
+			err = -EINVAL;
+			goto out_unlock;
 		}
 		ice_vsi_stop_lan_tx_rings(vsi, ICE_NO_RESET, vf->vf_id);
 
···
 
 		dev_dbg(dev, "VF is already disabled, there is no need for resetting it, telling VM, all is fine %d\n",
 			vf->vf_id);
-		return 0;
+		goto out_unlock;
 	}
-
-	if (flags & ICE_VF_RESET_LOCK)
-		mutex_lock(&vf->cfg_lock);
-	else
-		lockdep_assert_held(&vf->cfg_lock);
 
 	/* Set VF disable bit state here, before triggering reset */
 	set_bit(ICE_VF_STATE_DIS, vf->vf_states);

drivers/net/ethernet/intel/ice/ice_vf_lib.h

···
 struct ice_vsi *ice_get_vf_vsi(struct ice_vf *vf);
 bool ice_is_vf_disabled(struct ice_vf *vf);
 int ice_check_vf_ready_for_cfg(struct ice_vf *vf);
-int ice_check_vf_ready_for_reset(struct ice_vf *vf);
 void ice_set_vf_state_dis(struct ice_vf *vf);
 bool ice_is_any_vf_in_unicast_promisc(struct ice_pf *pf);
 void

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

···
 		ice_vc_notify_vf_link_state(vf);
 		break;
 	case VIRTCHNL_OP_RESET_VF:
-		clear_bit(ICE_VF_STATE_ACTIVE, vf->vf_states);
 		ops->reset_vf(vf);
 		break;
 	case VIRTCHNL_OP_ADD_ETH_ADDR:

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

···
 		return;
 	}
 
-	spin_lock_init(&adapter->tmreg_lock);
-	INIT_WORK(&adapter->ptp_tx_work, igb_ptp_tx_work);
-
-	if (adapter->ptp_flags & IGB_PTP_OVERFLOW_CHECK)
-		INIT_DELAYED_WORK(&adapter->ptp_overflow_work,
-				  igb_ptp_overflow_check);
-
-	adapter->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE;
-	adapter->tstamp_config.tx_type = HWTSTAMP_TX_OFF;
-
-	igb_ptp_reset(adapter);
-
 	adapter->ptp_clock = ptp_clock_register(&adapter->ptp_caps,
 						&adapter->pdev->dev);
 	if (IS_ERR(adapter->ptp_clock)) {
···
 		dev_info(&adapter->pdev->dev, "added PHC on %s\n",
 			 adapter->netdev->name);
 		adapter->ptp_flags |= IGB_PTP_ENABLED;
+
+		spin_lock_init(&adapter->tmreg_lock);
+		INIT_WORK(&adapter->ptp_tx_work, igb_ptp_tx_work);
+
+		if (adapter->ptp_flags & IGB_PTP_OVERFLOW_CHECK)
+			INIT_DELAYED_WORK(&adapter->ptp_overflow_work,
+					  igb_ptp_overflow_check);
+
+		adapter->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE;
+		adapter->tstamp_config.tx_type = HWTSTAMP_TX_OFF;
+
+		igb_ptp_reset(adapter);
 	}
 }
 

drivers/net/ethernet/intel/igc/igc_defines.h

···
 #define IGC_PTM_CTRL_START_NOW	BIT(29) /* Start PTM Now */
 #define IGC_PTM_CTRL_EN		BIT(30) /* Enable PTM */
 #define IGC_PTM_CTRL_TRIG	BIT(31) /* PTM Cycle trigger */
-#define IGC_PTM_CTRL_SHRT_CYC(usec)	(((usec) & 0x2f) << 2)
+#define IGC_PTM_CTRL_SHRT_CYC(usec)	(((usec) & 0x3f) << 2)
 #define IGC_PTM_CTRL_PTM_TO(usec)	(((usec) & 0xff) << 8)
 
 #define IGC_PTM_SHORT_CYC_DEFAULT	10  /* Default Short/interrupted cycle interval */

drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c

···
 	if (link < 0)
 		return NIX_AF_ERR_RX_LINK_INVALID;
 
-	nix_find_link_frs(rvu, req, pcifunc);
 
 linkcfg:
+	nix_find_link_frs(rvu, req, pcifunc);
+
 	cfg = rvu_read64(rvu, blkaddr, NIX_AF_RX_LINKX_CFG(link));
 	cfg = (cfg & ~(0xFFFFULL << 16)) | ((u64)req->maxlen << 16);
 	if (req->update_minlen)

drivers/net/ethernet/mediatek/mtk_wed.c

···
 
 	for (i = 0; i < ARRAY_SIZE(hw_list); i++) {
 		struct mtk_wed_hw *hw = hw_list[i];
-		struct mtk_wed_device *dev = hw->wed_dev;
+		struct mtk_wed_device *dev;
 		int err;
 
+		if (!hw)
+			break;
+
+		dev = hw->wed_dev;
 		if (!dev || !dev->wlan.reset)
 			continue;
 
···
 
 	for (i = 0; i < ARRAY_SIZE(hw_list); i++) {
 		struct mtk_wed_hw *hw = hw_list[i];
-		struct mtk_wed_device *dev = hw->wed_dev;
+		struct mtk_wed_device *dev;
 
+		if (!hw)
+			break;
+
+		dev = hw->wed_dev;
 		if (!dev || !dev->wlan.reset_complete)
 			continue;
 

drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c

···
 	MLXSW_AFK_ELEMENT_INFO_U32(IP_TTL_, 0x18, 0, 8),
 	MLXSW_AFK_ELEMENT_INFO_U32(IP_ECN, 0x18, 9, 2),
 	MLXSW_AFK_ELEMENT_INFO_U32(IP_DSCP, 0x18, 11, 6),
-	MLXSW_AFK_ELEMENT_INFO_U32(VIRT_ROUTER_MSB, 0x18, 17, 3),
-	MLXSW_AFK_ELEMENT_INFO_U32(VIRT_ROUTER_LSB, 0x18, 20, 8),
+	MLXSW_AFK_ELEMENT_INFO_U32(VIRT_ROUTER_MSB, 0x18, 17, 4),
+	MLXSW_AFK_ELEMENT_INFO_U32(VIRT_ROUTER_LSB, 0x18, 21, 8),
 	MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP_96_127, 0x20, 4),
 	MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP_64_95, 0x24, 4),
 	MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP_32_63, 0x28, 4),

drivers/net/ethernet/mellanox/mlxsw/pci.c

···
 				    struct sk_buff *skb,
 				    enum mlxsw_pci_cqe_v cqe_v, char *cqe)
 {
+	u8 ts_type;
+
 	if (cqe_v != MLXSW_PCI_CQE_V2)
 		return;
 
-	if (mlxsw_pci_cqe2_time_stamp_type_get(cqe) !=
-	    MLXSW_PCI_CQE_TIME_STAMP_TYPE_UTC)
+	ts_type = mlxsw_pci_cqe2_time_stamp_type_get(cqe);
+
+	if (ts_type != MLXSW_PCI_CQE_TIME_STAMP_TYPE_UTC &&
+	    ts_type != MLXSW_PCI_CQE_TIME_STAMP_TYPE_MIRROR_UTC)
 		return;
 
 	mlxsw_skb_cb(skb)->cqe_ts.sec = mlxsw_pci_cqe2_time_stamp_sec_get(cqe);

drivers/net/ethernet/mellanox/mlxsw/reg.h

···
  */
 MLXSW_ITEM32_LP(reg, sspr, 0x00, 16, 0x00, 12);
 
-/* reg_sspr_sub_port
- * Virtual port within the physical port.
- * Should be set to 0 when virtual ports are not enabled on the port.
- *
- * Access: RW
- */
-MLXSW_ITEM32(reg, sspr, sub_port, 0x00, 8, 8);
-
 /* reg_sspr_system_port
  * Unique identifier within the stacking domain that represents all the ports
  * that are available in the system (external ports).
···
 	MLXSW_REG_ZERO(sspr, payload);
 	mlxsw_reg_sspr_m_set(payload, 1);
 	mlxsw_reg_sspr_local_port_set(payload, local_port);
-	mlxsw_reg_sspr_sub_port_set(payload, 0);
 	mlxsw_reg_sspr_system_port_set(payload, local_port);
 }
 

drivers/net/ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c

···
 				       key->vrid, GENMASK(7, 0));
 	mlxsw_sp_acl_rulei_keymask_u32(rulei,
 				       MLXSW_AFK_ELEMENT_VIRT_ROUTER_MSB,
-				       key->vrid >> 8, GENMASK(2, 0));
+				       key->vrid >> 8, GENMASK(3, 0));
 	switch (key->proto) {
 	case MLXSW_SP_L3_PROTO_IPV4:
 		return mlxsw_sp2_mr_tcam_rule_parse4(rulei, key);

drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c

···
 
 static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_4[] = {
 	MLXSW_AFK_ELEMENT_INST_U32(VIRT_ROUTER_LSB, 0x04, 24, 8),
-	MLXSW_AFK_ELEMENT_INST_U32(VIRT_ROUTER_MSB, 0x00, 0, 3),
+	MLXSW_AFK_ELEMENT_INST_EXT_U32(VIRT_ROUTER_MSB, 0x00, 0, 3, 0, true),
 };
 
 static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_0[] = {
···
 
 static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_4b[] = {
 	MLXSW_AFK_ELEMENT_INST_U32(VIRT_ROUTER_LSB, 0x04, 13, 8),
-	MLXSW_AFK_ELEMENT_INST_EXT_U32(VIRT_ROUTER_MSB, 0x04, 21, 4, 0, true),
+	MLXSW_AFK_ELEMENT_INST_U32(VIRT_ROUTER_MSB, 0x04, 21, 4),
 };
 
 static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_2b[] = {

drivers/net/ethernet/sfc/falcon/selftest.c

···
 	for (i = 0; i < state->packet_count; i++) {
 		/* Allocate an skb, holding an extra reference for
 		 * transmit completion counting */
-		skb = alloc_skb(EF4_LOOPBACK_PAYLOAD_LEN, GFP_KERNEL);
+		skb = alloc_skb(sizeof(state->payload), GFP_KERNEL);
 		if (!skb)
 			return -ENOMEM;
 		state->skbs[i] = skb;

drivers/net/ethernet/sfc/selftest.c

···
 	for (i = 0; i < state->packet_count; i++) {
 		/* Allocate an skb, holding an extra reference for
 		 * transmit completion counting */
-		skb = alloc_skb(EFX_LOOPBACK_PAYLOAD_LEN, GFP_KERNEL);
+		skb = alloc_skb(sizeof(state->payload), GFP_KERNEL);
 		if (!skb)
 			return -ENOMEM;
 		state->skbs[i] = skb;

drivers/net/ethernet/sfc/siena/selftest.c

···
 	for (i = 0; i < state->packet_count; i++) {
 		/* Allocate an skb, holding an extra reference for
 		 * transmit completion counting */
-		skb = alloc_skb(EFX_LOOPBACK_PAYLOAD_LEN, GFP_KERNEL);
+		skb = alloc_skb(sizeof(state->payload), GFP_KERNEL);
 		if (!skb)
 			return -ENOMEM;
 		state->skbs[i] = skb;

drivers/net/ipvlan/ipvlan_main.c

···
 
 		write_pnet(&port->pnet, newnet);
 
-		ipvlan_migrate_l3s_hook(oldnet, newnet);
+		if (port->mode == IPVLAN_MODE_L3S)
+			ipvlan_migrate_l3s_hook(oldnet, newnet);
 		break;
 	}
 	case NETDEV_UNREGISTER:

drivers/net/mdio/mdio-bitbang.c

···
 	struct mdiobb_ctrl *ctrl = bus->priv;
 
 	mdiobb_cmd_addr(ctrl, phy, devad, reg);
-	mdiobb_cmd(ctrl, MDIO_C45_READ, phy, reg);
+	mdiobb_cmd(ctrl, MDIO_C45_READ, phy, devad);
 
 	return mdiobb_read_common(bus, phy);
 }
···
 	struct mdiobb_ctrl *ctrl = bus->priv;
 
 	mdiobb_cmd_addr(ctrl, phy, devad, reg);
-	mdiobb_cmd(ctrl, MDIO_C45_WRITE, phy, reg);
+	mdiobb_cmd(ctrl, MDIO_C45_WRITE, phy, devad);
 
 	return mdiobb_write_common(bus, val);
 }

drivers/net/phy/phy.c

···
 
 static void phy_process_error(struct phy_device *phydev)
 {
-	mutex_lock(&phydev->lock);
+	/* phydev->lock must be held for the state change to be safe */
+	if (!mutex_is_locked(&phydev->lock))
+		phydev_err(phydev, "PHY-device data unsafe context\n");
+
 	phydev->state = PHY_ERROR;
-	mutex_unlock(&phydev->lock);
 
 	phy_trigger_machine(phydev);
 }
···
 			      const void *func, int err)
 {
 	WARN(1, "%pS: returned: %d\n", func, err);
+	mutex_lock(&phydev->lock);
 	phy_process_error(phydev);
+	mutex_unlock(&phydev->lock);
 }
 
 /**
···
  *
  * Moves the PHY to the ERROR state in response to a read
  * or write error, and tells the controller the link is down.
- * Must not be called from interrupt context, or while the
- * phydev->lock is held.
+ * Must be called with phydev->lock held.
  */
 void phy_error(struct phy_device *phydev)
 {

drivers/net/phy/sfp-bus.c

···
 	switch (id->base.extended_cc) {
 	case SFF8024_ECC_UNSPEC:
 		break;
+	case SFF8024_ECC_100G_25GAUI_C2M_AOC:
+		if (br_min <= 28000 && br_max >= 25000) {
+			/* 25GBASE-R, possibly with FEC */
+			__set_bit(PHY_INTERFACE_MODE_25GBASER, interfaces);
+			/* There is currently no link mode for 25000base
+			 * with unspecified range, reuse SR.
+			 */
+			phylink_set(modes, 25000baseSR_Full);
+		}
+		break;
 	case SFF8024_ECC_100GBASE_SR4_25GBASE_SR:
 		phylink_set(modes, 100000baseSR4_Full);
 		phylink_set(modes, 25000baseSR_Full);

drivers/net/veth.c

···
 
 		nla_peer = data[VETH_INFO_PEER];
 		ifmp = nla_data(nla_peer);
-		err = rtnl_nla_parse_ifla(peer_tb,
-					  nla_data(nla_peer) + sizeof(struct ifinfomsg),
-					  nla_len(nla_peer) - sizeof(struct ifinfomsg),
-					  NULL);
+		err = rtnl_nla_parse_ifinfomsg(peer_tb, nla_peer, extack);
 		if (err < 0)
 			return err;
 

drivers/net/wireless/intel/iwlwifi/Kconfig

···
 	tristate "Intel Wireless WiFi MVM Firmware support"
 	select WANT_DEV_COREDUMP
 	depends on MAC80211
+	depends on PTP_1588_CLOCK_OPTIONAL
 	help
 	  This is the driver that supports the MVM firmware. The list
 	  of the devices that use this firmware is available here:

include/net/bonding.h

···
 }
 
 /* Caller must hold rcu_read_lock() for read */
-static inline bool bond_slave_has_mac_rx(struct bonding *bond, const u8 *mac)
+static inline bool bond_slave_has_mac_rcu(struct bonding *bond, const u8 *mac)
 {
 	struct list_head *iter;
 	struct slave *tmp;
-	struct netdev_hw_addr *ha;
 
 	bond_for_each_slave_rcu(bond, tmp, iter)
 		if (ether_addr_equal_64bits(mac, tmp->dev->dev_addr))
 			return true;
-
-	if (netdev_uc_empty(bond->dev))
-		return false;
-
-	netdev_for_each_uc_addr(ha, bond->dev)
-		if (ether_addr_equal_64bits(mac, ha->addr))
-			return true;
-
 	return false;
 }
 

include/net/inet_sock.h

···
 	__s16			uc_ttl;
 	__u16			cmsg_flags;
 	struct ip_options_rcu __rcu	*inet_opt;
+	atomic_t		inet_id;
 	__be16			inet_sport;
-	__u16			inet_id;
 
 	__u8			tos;
 	__u8			min_ttl;

include/net/ip.h

···
 	 * generator as much as we can.
 	 */
 	if (sk && inet_sk(sk)->inet_daddr) {
-		iph->id = htons(inet_sk(sk)->inet_id);
-		inet_sk(sk)->inet_id += segs;
+		int val;
+
+		/* avoid atomic operations for TCP,
+		 * as we hold socket lock at this point.
+		 */
+		if (sk_is_tcp(sk)) {
+			sock_owned_by_me(sk);
+			val = atomic_read(&inet_sk(sk)->inet_id);
+			atomic_set(&inet_sk(sk)->inet_id, val + segs);
+		} else {
+			val = atomic_add_return(segs, &inet_sk(sk)->inet_id);
+		}
+		iph->id = htons(val);
 		return;
 	}
 	if ((iph->frag_off & htons(IP_DF)) && !skb->ignore_df) {

include/net/mac80211.h

···
  * marks frames marked in the bitmap as having been filtered. Afterwards, it
  * checks if any frames in the window starting from @ssn can now be released
  * (in case they were only waiting for frames that were filtered.)
+ * (Only work correctly if @max_rx_aggregation_subframes <= 64 frames)
  */
 void ieee80211_mark_rx_ba_filtered_frames(struct ieee80211_sta *pubsta, u8 tid,
 					  u16 ssn, u64 filtered,

include/net/netfilter/nf_tables.h

···
 	return (void *)set->data;
 }
 
+static inline bool nft_set_gc_is_pending(const struct nft_set *s)
+{
+	return refcount_read(&s->refs) != 1;
+}
+
 static inline struct nft_set *nft_set_container_of(const void *priv)
 {
 	return (void *)priv - offsetof(struct nft_set, data);
···
 	u64			table_handle;
 	unsigned int		base_seq;
 	unsigned int		gc_seq;
+	u8			validate_state;
 };
 
 extern unsigned int nf_tables_net_id;

include/net/rtnetlink.h

···
 int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm,
 			u32 portid, const struct nlmsghdr *nlh);
 
-int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len,
-			struct netlink_ext_ack *exterr);
+int rtnl_nla_parse_ifinfomsg(struct nlattr **tb, const struct nlattr *nla_peer,
+			     struct netlink_ext_ack *exterr);
 struct net *rtnl_get_net_ns_capable(struct sock *sk, int netnsid);
 
 #define MODULE_ALIAS_RTNL_LINK(kind) MODULE_ALIAS("rtnl-link-" kind)

include/net/sock.h

···
 	/*
 	 * Pressure flag: try to collapse.
 	 * Technical note: it is used by multiple contexts non atomically.
+	 * Make sure to use READ_ONCE()/WRITE_ONCE() for all reads/writes.
 	 * All the __sk_mem_schedule() is of this nature: accounting
 	 * is strict, actions are advisory and have some latency.
 	 */
···
 static inline bool sk_under_global_memory_pressure(const struct sock *sk)
 {
 	return sk->sk_prot->memory_pressure &&
-		!!*sk->sk_prot->memory_pressure;
+		!!READ_ONCE(*sk->sk_prot->memory_pressure);
 }
 
 static inline bool sk_under_memory_pressure(const struct sock *sk)
···
 	    mem_cgroup_under_socket_pressure(sk->sk_memcg))
 		return true;
 
-	return !!*sk->sk_prot->memory_pressure;
+	return !!READ_ONCE(*sk->sk_prot->memory_pressure);
 }
 
 static inline long
···
 {
 	if (!prot->memory_pressure)
 		return false;
-	return !!*prot->memory_pressure;
+	return !!READ_ONCE(*prot->memory_pressure);
 }
 
 

net/batman-adv/bat_v_elp.c

···
 	struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface);
 	struct batadv_elp_packet *elp_packet;
 	struct batadv_hard_iface *primary_if;
-	struct ethhdr *ethhdr = (struct ethhdr *)skb_mac_header(skb);
+	struct ethhdr *ethhdr;
 	bool res;
 	int ret = NET_RX_DROP;
 
···
 	if (!res)
 		goto free_skb;
 
+	ethhdr = eth_hdr(skb);
 	if (batadv_is_my_mac(bat_priv, ethhdr->h_source))
 		goto free_skb;
 

net/batman-adv/bat_v_ogm.c

···
 {
 	struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface);
 
-	if (hard_iface->if_status != BATADV_IF_ACTIVE)
+	if (hard_iface->if_status != BATADV_IF_ACTIVE) {
+		kfree_skb(skb);
 		return;
+	}
 
 	batadv_inc_counter(bat_priv, BATADV_CNT_MGMT_TX);
 	batadv_add_counter(bat_priv, BATADV_CNT_MGMT_TX_BYTES,
···
 {
 	struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface);
 	struct batadv_ogm2_packet *ogm_packet;
-	struct ethhdr *ethhdr = eth_hdr(skb);
+	struct ethhdr *ethhdr;
 	int ogm_offset;
 	u8 *packet_pos;
 	int ret = NET_RX_DROP;
···
 	if (!batadv_check_management_packet(skb, if_incoming, BATADV_OGM2_HLEN))
 		goto free_skb;
 
+	ethhdr = eth_hdr(skb);
 	if (batadv_is_my_mac(bat_priv, ethhdr->h_source))
 		goto free_skb;
 

net/batman-adv/hard-interface.c

···
  */
 void batadv_update_min_mtu(struct net_device *soft_iface)
 {
-	soft_iface->mtu = batadv_hardif_min_mtu(soft_iface);
+	struct batadv_priv *bat_priv = netdev_priv(soft_iface);
+	int limit_mtu;
+	int mtu;
+
+	mtu = batadv_hardif_min_mtu(soft_iface);
+
+	if (bat_priv->mtu_set_by_user)
+		limit_mtu = bat_priv->mtu_set_by_user;
+	else
+		limit_mtu = ETH_DATA_LEN;
+
+	mtu = min(mtu, limit_mtu);
+	dev_set_mtu(soft_iface, mtu);
 
 	/* Check if the local translate table should be cleaned up to match a
 	 * new (and smaller) MTU.

net/batman-adv/netlink.c

···
 		attr = info->attrs[BATADV_ATTR_FRAGMENTATION_ENABLED];
 
 		atomic_set(&bat_priv->fragmentation, !!nla_get_u8(attr));
+
+		rtnl_lock();
 		batadv_update_min_mtu(bat_priv->soft_iface);
+		rtnl_unlock();
 	}
 
 	if (info->attrs[BATADV_ATTR_GW_BANDWIDTH_DOWN]) {

net/batman-adv/soft-interface.c

···
 
 static int batadv_interface_change_mtu(struct net_device *dev, int new_mtu)
 {
+	struct batadv_priv *bat_priv = netdev_priv(dev);
+
 	/* check ranges */
 	if (new_mtu < 68 || new_mtu > batadv_hardif_min_mtu(dev))
 		return -EINVAL;
 
 	dev->mtu = new_mtu;
+	bat_priv->mtu_set_by_user = new_mtu;
 
 	return 0;
 }

net/batman-adv/translation-table.c

···
 		if (roamed_back) {
 			batadv_tt_global_free(bat_priv, tt_global,
 					      "Roaming canceled");
-			tt_global = NULL;
 		} else {
 			/* The global entry has to be marked as ROAMING and
 			 * has to be kept for consistency purpose

net/batman-adv/types.h

···
 	struct net_device *soft_iface;
 
 	/**
+	 * @mtu_set_by_user: MTU was set once by user
+	 * protected by rtnl_lock
+	 */
+	int mtu_set_by_user;
+
+	/**
 	 * @bat_counters: mesh internal traffic statistic counters (see
 	 *  batadv_counters)
 	 */

net/can/isotp.c

···
 	return (isotp_bc_flags(so) == 0);
 }
 
-static bool isotp_register_txecho(struct isotp_sock *so)
-{
-	/* all modes but SF_BROADCAST register for tx echo skbs */
-	return (isotp_bc_flags(so) != CAN_ISOTP_SF_BROADCAST);
-}
-
 static enum hrtimer_restart isotp_rx_timer_handler(struct hrtimer *hrtimer)
 {
 	struct isotp_sock *so = container_of(hrtimer, struct isotp_sock,
···
 	lock_sock(sk);
 
 	/* remove current filters & unregister */
-	if (so->bound && isotp_register_txecho(so)) {
+	if (so->bound) {
 		if (so->ifindex) {
 			struct net_device *dev;
 
···
 		can_rx_register(net, dev, rx_id, SINGLE_MASK(rx_id),
 				isotp_rcv, sk, "isotp", sk);
 
-	if (isotp_register_txecho(so)) {
-		/* no consecutive frame echo skb in flight */
-		so->cfecho = 0;
+	/* no consecutive frame echo skb in flight */
+	so->cfecho = 0;
 
-		/* register for echo skb's */
-		can_rx_register(net, dev, tx_id, SINGLE_MASK(tx_id),
-				isotp_rcv_echo, sk, "isotpe", sk);
-	}
+	/* register for echo skb's */
+	can_rx_register(net, dev, tx_id, SINGLE_MASK(tx_id),
+			isotp_rcv_echo, sk, "isotpe", sk);
 
 	dev_put(dev);
 
···
 	case NETDEV_UNREGISTER:
 		lock_sock(sk);
 		/* remove current filters & unregister */
-		if (so->bound && isotp_register_txecho(so)) {
+		if (so->bound) {
 			if (isotp_register_rxid(so))
 				can_rx_unregister(dev_net(dev), dev, so->rxid,
 						  SINGLE_MASK(so->rxid),

net/can/raw.c

···
 	int bound;
 	int ifindex;
 	struct net_device *dev;
+	netdevice_tracker dev_tracker;
 	struct list_head notifier;
 	int loopback;
 	int recv_own_msgs;
···
 	case NETDEV_UNREGISTER:
 		lock_sock(sk);
 		/* remove current filters & unregister */
-		if (ro->bound)
+		if (ro->bound) {
 			raw_disable_allfilters(dev_net(dev), dev, sk);
+			netdev_put(dev, &ro->dev_tracker);
+		}
 
 		if (ro->count > 1)
 			kfree(ro->filter);
···
 
 	/* remove current filters & unregister */
 	if (ro->bound) {
-		if (ro->dev)
+		if (ro->dev) {
 			raw_disable_allfilters(dev_net(ro->dev), ro->dev, sk);
-		else
+			netdev_put(ro->dev, &ro->dev_tracker);
+		} else {
 			raw_disable_allfilters(sock_net(sk), NULL, sk);
+		}
 	}
 
 	if (ro->count > 1)
···
 			goto out;
 		}
 		if (dev->type != ARPHRD_CAN) {
-			dev_put(dev);
 			err = -ENODEV;
-			goto out;
+			goto out_put_dev;
 		}
+
 		if (!(dev->flags & IFF_UP))
 			notify_enetdown = 1;
 
···
 
 		/* filters set by default/setsockopt */
 		err = raw_enable_allfilters(sock_net(sk), dev, sk);
-		dev_put(dev);
+		if (err)
+			goto out_put_dev;
+
 	} else {
 		ifindex = 0;
 
···
 	if (!err) {
 		if (ro->bound) {
 			/* unregister old filters */
-			if (ro->dev)
+			if (ro->dev) {
 				raw_disable_allfilters(dev_net(ro->dev),
 						       ro->dev, sk);
-			else
+				/* drop reference to old ro->dev */
+				netdev_put(ro->dev, &ro->dev_tracker);
+			} else {
 				raw_disable_allfilters(sock_net(sk), NULL, sk);
+			}
 		}
 		ro->ifindex = ifindex;
 		ro->bound = 1;
+		/* bind() ok -> hold a reference for new ro->dev */
 		ro->dev = dev;
+		if (ro->dev)
+			netdev_hold(ro->dev, &ro->dev_tracker, GFP_KERNEL);
 	}
 
- out:
+out_put_dev:
+	/* remove potential reference from dev_get_by_index() */
+	if (dev)
+		dev_put(dev);
+out:
 	release_sock(sk);
 	rtnl_unlock();
 

net/core/rtnetlink.c

···
 	return err;
 }
 
-int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len,
-			struct netlink_ext_ack *exterr)
+int rtnl_nla_parse_ifinfomsg(struct nlattr **tb, const struct nlattr *nla_peer,
+			     struct netlink_ext_ack *exterr)
 {
-	return nla_parse_deprecated(tb, IFLA_MAX, head, len, ifla_policy,
+	const struct ifinfomsg *ifmp;
+	const struct nlattr *attrs;
+	size_t len;
+
+	ifmp = nla_data(nla_peer);
+	attrs = nla_data(nla_peer) + sizeof(struct ifinfomsg);
+	len = nla_len(nla_peer) - sizeof(struct ifinfomsg);
+
+	if (ifmp->ifi_index < 0) {
+		NL_SET_ERR_MSG_ATTR(exterr, nla_peer,
+				    "ifindex can't be negative");
+		return -EINVAL;
+	}
+
+	return nla_parse_deprecated(tb, IFLA_MAX, attrs, len, ifla_policy,
 				    exterr);
 }
-EXPORT_SYMBOL(rtnl_nla_parse_ifla);
+EXPORT_SYMBOL(rtnl_nla_parse_ifinfomsg);
 
 struct net *rtnl_link_get_net(struct net *src_net, struct nlattr *tb[])
 {
···
 	if (ifm->ifi_index > 0) {
 		link_specified = true;
 		dev = __dev_get_by_index(net, ifm->ifi_index);
+	} else if (ifm->ifi_index < 0) {
+		NL_SET_ERR_MSG(extack, "ifindex can't be negative");
+		return -EINVAL;
 	} else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME]) {
 		link_specified = true;
 		dev = rtnl_dev_get(net, tb);

net/dccp/ipv4.c

···
 						    inet->inet_daddr,
 						    inet->inet_sport,
 						    inet->inet_dport);
-	inet->inet_id = get_random_u16();
+	atomic_set(&inet->inet_id, get_random_u16());
 
 	err = dccp_connect(sk);
 	rt = NULL;
···
 	RCU_INIT_POINTER(newinet->inet_opt, rcu_dereference(ireq->ireq_opt));
 	newinet->mc_index  = inet_iif(skb);
 	newinet->mc_ttl	   = ip_hdr(skb)->ttl;
-	newinet->inet_id   = get_random_u16();
+	atomic_set(&newinet->inet_id, get_random_u16());
 
 	if (dst == NULL && (dst = inet_csk_route_child_sock(sk, newsk, req)) == NULL)
 		goto put_and_exit;

net/dccp/proto.c

···
 __poll_t dccp_poll(struct file *file, struct socket *sock,
 		       poll_table *wait)
 {
-	__poll_t mask;
 	struct sock *sk = sock->sk;
+	__poll_t mask;
+	u8 shutdown;
+	int state;
 
 	sock_poll_wait(file, sock, wait);
-	if (sk->sk_state == DCCP_LISTEN)
+
+	state = inet_sk_state_load(sk);
+	if (state == DCCP_LISTEN)
 		return inet_csk_listen_poll(sk);
 
 	/* Socket is not locked. We are protected from async events
···
 	 */
 
 	mask = 0;
-	if (sk->sk_err)
+	if (READ_ONCE(sk->sk_err))
 		mask = EPOLLERR;
+	shutdown = READ_ONCE(sk->sk_shutdown);
 
-	if (sk->sk_shutdown == SHUTDOWN_MASK || sk->sk_state == DCCP_CLOSED)
+	if (shutdown == SHUTDOWN_MASK || state == DCCP_CLOSED)
 		mask |= EPOLLHUP;
-	if (sk->sk_shutdown & RCV_SHUTDOWN)
+	if (shutdown & RCV_SHUTDOWN)
 		mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP;
 
 	/* Connected? */
-	if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_RESPOND)) {
+	if ((1 << state) & ~(DCCPF_REQUESTING | DCCPF_RESPOND)) {
 		if (atomic_read(&sk->sk_rmem_alloc) > 0)
 			mask |= EPOLLIN | EPOLLRDNORM;
 
-		if (!(sk->sk_shutdown & SEND_SHUTDOWN)) {
+		if (!(shutdown & SEND_SHUTDOWN)) {
 			if (sk_stream_is_writeable(sk)) {
 				mask |= EPOLLOUT | EPOLLWRNORM;
 			} else {  /* send SIGIO later */
···
 	}
 	return mask;
 }
-
 EXPORT_SYMBOL_GPL(dccp_poll);
 
 int dccp_ioctl(struct sock *sk, int cmd, int *karg)

net/devlink/leftover.c

···
 	struct devlink_param_item *param_item;
 	struct devlink_trap_item *trap_item;
 	struct devlink_port *devlink_port;
+	struct devlink_linecard *linecard;
 	struct devlink_rate *rate_node;
 	struct devlink_region *region;
 	unsigned long port_index;
···
 
 	xa_for_each(&devlink->ports, port_index, devlink_port)
 		devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_DEL);
+	list_for_each_entry_reverse(linecard, &devlink->linecard_list, list)
+		devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_DEL);
 	devlink_notify(devlink, DEVLINK_CMD_DEL);
 }
 

net/ipv4/af_inet.c

···
 	else
 		inet->pmtudisc = IP_PMTUDISC_WANT;
 
-	inet->inet_id = 0;
+	atomic_set(&inet->inet_id, 0);
 
 	sock_init_data(sock, sk);
 

net/ipv4/datagram.c

···
 	reuseport_has_conns_set(sk);
 	sk->sk_state = TCP_ESTABLISHED;
 	sk_set_txhash(sk);
-	inet->inet_id = get_random_u16();
+	atomic_set(&inet->inet_id, get_random_u16());
 
 	sk_dst_set(sk, &rt->dst);
 	err = 0;

net/ipv4/tcp_ipv4.c

···
 					     inet->inet_daddr));
 	}
 
-	inet->inet_id = get_random_u16();
+	atomic_set(&inet->inet_id, get_random_u16());
 
 	if (tcp_fastopen_defer_connect(sk, &err))
 		return err;
···
 	inet_csk(newsk)->icsk_ext_hdr_len = 0;
 	if (inet_opt)
 		inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen;
-	newinet->inet_id = get_random_u16();
+	atomic_set(&newinet->inet_id, get_random_u16());
 
 	/* Set ToS of the new socket based upon the value of incoming SYN.
 	 * ECT bits are set later in tcp_init_transfer().

net/mac80211/rx.c

···
 	struct sk_buff *tail = skb_peek_tail(frames);
 	struct ieee80211_rx_status *status;
 
-	if (tid_agg_rx->reorder_buf_filtered & BIT_ULL(index))
+	if (tid_agg_rx->reorder_buf_filtered &&
+	    tid_agg_rx->reorder_buf_filtered & BIT_ULL(index))
 		return true;
 
 	if (!tail)
···
 	}
 
 no_frame:
-	tid_agg_rx->reorder_buf_filtered &= ~BIT_ULL(index);
+	if (tid_agg_rx->reorder_buf_filtered)
+		tid_agg_rx->reorder_buf_filtered &= ~BIT_ULL(index);
 	tid_agg_rx->head_seq_num = ieee80211_sn_inc(tid_agg_rx->head_seq_num);
 }
 
···
 					  u16 ssn, u64 filtered,
 					  u16 received_mpdus)
 {
+	struct ieee80211_local *local;
 	struct sta_info *sta;
 	struct tid_ampdu_rx *tid_agg_rx;
 	struct sk_buff_head frames;
···
 	__skb_queue_head_init(&frames);
 
 	sta = container_of(pubsta, struct sta_info, sta);
+
+	local = sta->sdata->local;
+	WARN_ONCE(local->hw.max_rx_aggregation_subframes > 64,
+		  "RX BA marker can't support max_rx_aggregation_subframes %u > 64\n",
+		  local->hw.max_rx_aggregation_subframes);
 
 	if (!ieee80211_rx_data_set_sta(&rx, sta, -1))
 		return;

net/netfilter/nf_tables_api.c

···
 	if (table == NULL)
 		goto err_kzalloc;
 
-	table->validate_state = NFT_VALIDATE_SKIP;
+	table->validate_state = nft_net->validate_state;
 	table->name = nla_strdup(attr, GFP_KERNEL_ACCOUNT);
 	if (table->name == NULL)
 		goto err_strdup;
···
 				return -EAGAIN;
 
 			nft_validate_state_update(table, NFT_VALIDATE_SKIP);
+			break;
 		}
-
-		break;
 	}
 
 	return 0;
···
 	struct nft_trans_gc *trans, *next;
 	LIST_HEAD(trans_gc_list);
 
-	spin_lock(&nf_tables_destroy_list_lock);
+	spin_lock(&nf_tables_gc_list_lock);
 	list_splice_init(&nf_tables_gc_list, &trans_gc_list);
-	spin_unlock(&nf_tables_destroy_list_lock);
+	spin_unlock(&nf_tables_gc_list_lock);
 
 	list_for_each_entry_safe(trans, next, &trans_gc_list, list) {
 		list_del(&trans->list);
···
 	}
 
 	/* 0. Validate ruleset, otherwise roll back for error reporting. */
-	if (nf_tables_validate(net) < 0)
+	if (nf_tables_validate(net) < 0) {
+		nft_net->validate_state = NFT_VALIDATE_DO;
 		return -EAGAIN;
+	}
 
 	err = nft_flow_rule_offload_commit(net);
 	if (err < 0)
···
 	nf_tables_commit_audit_log(&adl, nft_net->base_seq);
 
 	nft_gc_seq_end(nft_net, gc_seq);
+	nft_net->validate_state = NFT_VALIDATE_SKIP;
 	nf_tables_commit_release(net);
 
 	return 0;
···
 			   enum nfnl_abort_action action)
 {
 	struct nftables_pernet *nft_net = nft_pernet(net);
-	int ret = __nf_tables_abort(net, action);
+	unsigned int gc_seq;
+	int ret;
 
+	gc_seq = nft_gc_seq_begin(nft_net);
+	ret = __nf_tables_abort(net, action);
+	nft_gc_seq_end(nft_net, gc_seq);
 	mutex_unlock(&nft_net->commit_mutex);
 
 	return ret;
···
 	gc_seq = nft_gc_seq_begin(nft_net);
 
 	if (!list_empty(&nf_tables_destroy_list))
-		rcu_barrier();
+		nf_tables_trans_destroy_flush_work();
 again:
 	list_for_each_entry(table, &nft_net->tables, list) {
 		if (nft_table_has_owner(table) &&
···
 	mutex_init(&nft_net->commit_mutex);
 	nft_net->base_seq = 1;
 	nft_net->gc_seq = 0;
+	nft_net->validate_state = NFT_VALIDATE_SKIP;
 
 	return 0;
 }

net/netfilter/nft_set_hash.c

···
 	nft_net = nft_pernet(net);
 	gc_seq = READ_ONCE(nft_net->gc_seq);
 
+	if (nft_set_gc_is_pending(set))
+		goto done;
+
 	gc = nft_trans_gc_alloc(set, gc_seq, GFP_KERNEL);
 	if (!gc)
 		goto done;

net/netfilter/nft_set_pipapo.c

···
 static int pipapo_insert(struct nft_pipapo_field *f, const uint8_t *k,
 			 int mask_bits)
 {
-	int rule = f->rules++, group, ret, bit_offset = 0;
+	int rule = f->rules, group, ret, bit_offset = 0;
 
-	ret = pipapo_resize(f, f->rules - 1, f->rules);
+	ret = pipapo_resize(f, f->rules, f->rules + 1);
 	if (ret)
 		return ret;
+
+	f->rules++;
 
 	for (group = 0; group < f->groups; group++) {
 		int i, v;
···
 			step++;
 			if (step >= len) {
 				if (!masks) {
-					pipapo_insert(f, base, 0);
+					err = pipapo_insert(f, base, 0);
+					if (err < 0)
+						return err;
 					masks = 1;
 				}
 				goto out;
···
 			ret = pipapo_insert(f, start, f->groups * f->bb);
 		else
 			ret = pipapo_expand(f, start, end, f->groups * f->bb);
+
+		if (ret < 0)
+			return ret;
 
 		if (f->bsize > bsize_max)
 			bsize_max = f->bsize;

net/netfilter/nft_set_rbtree.c

···
 	nft_net = nft_pernet(net);
 	gc_seq  = READ_ONCE(nft_net->gc_seq);
 
+	if (nft_set_gc_is_pending(set))
+		goto done;
+
 	gc = nft_trans_gc_alloc(set, gc_seq, GFP_KERNEL);
 	if (!gc)
 		goto done;

net/sched/sch_api.c

···
 	return 0;
 }
 
+static bool req_create_or_replace(struct nlmsghdr *n)
+{
+	return (n->nlmsg_flags & NLM_F_CREATE &&
+		n->nlmsg_flags & NLM_F_REPLACE);
+}
+
+static bool req_create_exclusive(struct nlmsghdr *n)
+{
+	return (n->nlmsg_flags & NLM_F_CREATE &&
+		n->nlmsg_flags & NLM_F_EXCL);
+}
+
+static bool req_change(struct nlmsghdr *n)
+{
+	return (!(n->nlmsg_flags & NLM_F_CREATE) &&
+		!(n->nlmsg_flags & NLM_F_REPLACE) &&
+		!(n->nlmsg_flags & NLM_F_EXCL));
+}
+
 /*
  * Create/change qdisc.
  */
-
 static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n,
 			   struct netlink_ext_ack *extack)
 {
···
 				 *
 				 *   We know, that some child q is already
 				 *   attached to this parent and have choice:
-				 *   either to change it or to create/graft new one.
+				 *   1) change it or 2) create/graft new one.
+				 *   If the requested qdisc kind is different
+				 *   than the existing one, then we choose graft.
+				 *   If they are the same then this is "change"
+				 *   operation - just let it fallthrough..
 				 *
 				 *   1. We are allowed to create/graft only
-				 *   if CREATE and REPLACE flags are set.
+				 *   if the request is explicitly stating
+				 *   "please create if it doesn't exist".
 				 *
-				 *   2. If EXCL is set, requestor wanted to say,
-				 *   that qdisc tcm_handle is not expected
+				 *   2. If the request is to exclusive create
+				 *   then the qdisc tcm_handle is not expected
 				 *   to exist, so that we choose create/graft too.
 				 *
 				 *   3. The last case is when no flags are set.
+				 *   This will happen when for example tc
+				 *   utility issues a "change" command.
 				 *   Alas, it is sort of hole in API, we
 				 *   cannot decide what to do unambiguously.
-				 *   For now we select create/graft, if
-				 *   user gave KIND, which does not match existing.
+				 *   For now we select create/graft.
 				 */
-				if ((n->nlmsg_flags & NLM_F_CREATE) &&
-				    (n->nlmsg_flags & NLM_F_REPLACE) &&
-				    ((n->nlmsg_flags & NLM_F_EXCL) ||
-				     (tca[TCA_KIND] &&
-				      nla_strcmp(tca[TCA_KIND], q->ops->id))))
-					goto create_n_graft;
+				if (tca[TCA_KIND] &&
+				    nla_strcmp(tca[TCA_KIND], q->ops->id)) {
+					if (req_create_or_replace(n) ||
+					    req_create_exclusive(n))
+						goto create_n_graft;
+					else if (req_change(n))
+						goto create_n_graft2;
+				}
 			}
 		}
 	} else {
···
 		NL_SET_ERR_MSG(extack, "Qdisc not found. To create specify NLM_F_CREATE flag");
 		return -ENOENT;
 	}
+create_n_graft2:
 	if (clid == TC_H_INGRESS) {
 		if (dev_ingress_queue(dev)) {
 			q = qdisc_create(dev, dev_ingress_queue(dev),

net/sctp/socket.c

···
 
 static void sctp_enter_memory_pressure(struct sock *sk)
 {
-	sctp_memory_pressure = 1;
+	WRITE_ONCE(sctp_memory_pressure, 1);
 }
 
 
···
 	newinet->inet_rcv_saddr = inet->inet_rcv_saddr;
 	newinet->inet_dport = htons(asoc->peer.port);
 	newinet->pmtudisc = inet->pmtudisc;
-	newinet->inet_id = get_random_u16();
+	atomic_set(&newinet->inet_id, get_random_u16());
 
 	newinet->uc_ttl = inet->uc_ttl;
 	newinet->mc_loop = 1;

tools/testing/selftests/drivers/net/bonding/Makefile

···
 	mode-1-recovery-updelay.sh \
 	mode-2-recovery-updelay.sh \
 	bond_options.sh \
-	bond-eth-type-change.sh
+	bond-eth-type-change.sh \
+	bond_macvlan.sh
 
 TEST_FILES := \
 	lag_lib.sh \
+	bond_topo_2d1c.sh \
 	bond_topo_3d1c.sh \
 	net_forwarding_lib.sh
 

tools/testing/selftests/drivers/net/bonding/bond-break-lacpdu-tx.sh

···
 
 # add ports
 ip link set fbond master fab-br0
-ip link set veth1-bond down master fbond
-ip link set veth2-bond down master fbond
+ip link set veth1-bond master fbond
+ip link set veth2-bond master fbond
 
 # bring up
 ip link set veth1-end up

tools/testing/selftests/drivers/net/bonding/bond_macvlan.sh

···
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test macvlan over balance-alb
+
+lib_dir=$(dirname "$0")
+source ${lib_dir}/bond_topo_2d1c.sh
+
+m1_ns="m1-$(mktemp -u XXXXXX)"
+m2_ns="m1-$(mktemp -u XXXXXX)"
+m1_ip4="192.0.2.11"
+m1_ip6="2001:db8::11"
+m2_ip4="192.0.2.12"
+m2_ip6="2001:db8::12"
+
+cleanup()
+{
+	ip -n ${m1_ns} link del macv0
+	ip netns del ${m1_ns}
+	ip -n ${m2_ns} link del macv0
+	ip netns del ${m2_ns}
+
+	client_destroy
+	server_destroy
+	gateway_destroy
+}
+
+check_connection()
+{
+	local ns=${1}
+	local target=${2}
+	local message=${3:-"macvlan_over_bond"}
+	RET=0
+
+
+	ip netns exec ${ns} ping ${target} -c 4 -i 0.1 &>/dev/null
+	check_err $? "ping failed"
+	log_test "$mode: $message"
+}
+
+macvlan_over_bond()
+{
+	local param="$1"
+	RET=0
+
+	# setup new bond mode
+	bond_reset "${param}"
+
+	ip -n ${s_ns} link add link bond0 name macv0 type macvlan mode bridge
+	ip -n ${s_ns} link set macv0 netns ${m1_ns}
+	ip -n ${m1_ns} link set dev macv0 up
+	ip -n ${m1_ns} addr add ${m1_ip4}/24 dev macv0
+	ip -n ${m1_ns} addr add ${m1_ip6}/24 dev macv0
+
+	ip -n ${s_ns} link add link bond0 name macv0 type macvlan mode bridge
+	ip -n ${s_ns} link set macv0 netns ${m2_ns}
+	ip -n ${m2_ns} link set dev macv0 up
+	ip -n ${m2_ns} addr add ${m2_ip4}/24 dev macv0
+	ip -n ${m2_ns} addr add ${m2_ip6}/24 dev macv0
+
+	sleep 2
+
+	check_connection "${c_ns}" "${s_ip4}" "IPv4: client->server"
+	check_connection "${c_ns}" "${s_ip6}" "IPv6: client->server"
+	check_connection "${c_ns}" "${m1_ip4}" "IPv4: client->macvlan_1"
+	check_connection "${c_ns}" "${m1_ip6}" "IPv6: client->macvlan_1"
+	check_connection "${c_ns}" "${m2_ip4}" "IPv4: client->macvlan_2"
+	check_connection "${c_ns}" "${m2_ip6}" "IPv6: client->macvlan_2"
+	check_connection "${m1_ns}" "${m2_ip4}" "IPv4: macvlan_1->macvlan_2"
+	check_connection "${m1_ns}" "${m2_ip6}" "IPv6: macvlan_1->macvlan_2"
+
+
+	sleep 5
+
+	check_connection "${s_ns}" "${c_ip4}" "IPv4: server->client"
+	check_connection "${s_ns}" "${c_ip6}" "IPv6: server->client"
+	check_connection "${m1_ns}" "${c_ip4}" "IPv4: macvlan_1->client"
+	check_connection "${m1_ns}" "${c_ip6}" "IPv6: macvlan_1->client"
+	check_connection "${m2_ns}" "${c_ip4}" "IPv4: macvlan_2->client"
+	check_connection "${m2_ns}" "${c_ip6}" "IPv6: macvlan_2->client"
+	check_connection "${m2_ns}" "${m1_ip4}" "IPv4: macvlan_2->macvlan_2"
+	check_connection "${m2_ns}" "${m1_ip6}" "IPv6: macvlan_2->macvlan_2"
+
+	ip -n ${c_ns} neigh flush dev eth0
+}
+
+trap cleanup EXIT
+
+setup_prepare
+ip netns add ${m1_ns}
+ip netns add ${m2_ns}
+
+modes="active-backup balance-tlb balance-alb"
+
+for mode in $modes; do
+	macvlan_over_bond "mode $mode"
+done
+
+exit $EXIT_STATUS

tools/testing/selftests/drivers/net/bonding/bond_options.sh

···
 	num_grat_arp
 "
 
-REQUIRE_MZ=no
-NUM_NETIFS=0
 lib_dir=$(dirname "$0")
-source ${lib_dir}/net_forwarding_lib.sh
 source ${lib_dir}/bond_topo_3d1c.sh
 
 skip_prio()

tools/testing/selftests/drivers/net/bonding/bond_topo_2d1c.sh

···
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Topology for Bond mode 1,5,6 testing
+#
+#  +-------------------------+
+#  |          bond0          |  Server
+#  |            +            |  192.0.2.1/24
+#  |      eth0  |  eth1      |  2001:db8::1/24
+#  |        +---+---+        |
+#  |        |       |        |
+#  +-------------------------+
+#           |       |
+#  +-------------------------+
+#  |        |       |        |
+#  |    +---+-------+---+    |  Gateway
+#  |    |      br0      |    |  192.0.2.254/24
+#  |    +-------+-------+    |  2001:db8::254/24
+#  |            |            |
+#  +-------------------------+
+#               |
+#  +-------------------------+
+#  |            |            |  Client
+#  |            +            |  192.0.2.10/24
+#  |          eth0           |  2001:db8::10/24
+#  +-------------------------+
+
+REQUIRE_MZ=no
+NUM_NETIFS=0
+lib_dir=$(dirname "$0")
+source ${lib_dir}/net_forwarding_lib.sh
+
+s_ns="s-$(mktemp -u XXXXXX)"
+c_ns="c-$(mktemp -u XXXXXX)"
+g_ns="g-$(mktemp -u XXXXXX)"
+s_ip4="192.0.2.1"
+c_ip4="192.0.2.10"
+g_ip4="192.0.2.254"
+s_ip6="2001:db8::1"
+c_ip6="2001:db8::10"
+g_ip6="2001:db8::254"
+
+gateway_create()
+{
+	ip netns add ${g_ns}
+	ip -n ${g_ns} link add br0 type bridge
+	ip -n ${g_ns} link set br0 up
+	ip -n ${g_ns} addr add ${g_ip4}/24 dev br0
+	ip -n ${g_ns} addr add ${g_ip6}/24 dev br0
+}
+
+gateway_destroy()
+{
+	ip -n ${g_ns} link del br0
+	ip netns del ${g_ns}
+}
+
+server_create()
+{
+	ip netns add ${s_ns}
+	ip -n ${s_ns} link add bond0 type bond mode active-backup miimon 100
+
+	for i in $(seq 0 1); do
+		ip -n ${s_ns} link add eth${i} type veth peer name s${i} netns ${g_ns}
+
+		ip -n ${g_ns} link set s${i} up
+		ip -n ${g_ns} link set s${i} master br0
+		ip -n ${s_ns} link set eth${i} master bond0
+
+		tc -n ${g_ns} qdisc add dev s${i} clsact
+	done
+
+	ip -n ${s_ns} link set bond0 up
+	ip -n ${s_ns} addr add ${s_ip4}/24 dev bond0
+	ip -n ${s_ns} addr add ${s_ip6}/24 dev bond0
+	sleep 2
+}
+
+# Reset bond with new mode and options
+bond_reset()
+{
+	# Count the eth link number in real-time as this function
+	# maybe called from other topologies.
+	local link_num=$(ip -n ${s_ns} -br link show | grep -c "^eth")
+	local param="$1"
+	link_num=$((link_num -1))
+
+	ip -n ${s_ns} link set bond0 down
+	ip -n ${s_ns} link del bond0
+
+	ip -n ${s_ns} link add bond0 type bond $param
+	for i in $(seq 0 ${link_num}); do
+		ip -n ${s_ns} link set eth$i master bond0
+	done
+
+	ip -n ${s_ns} link set bond0 up
+	ip -n ${s_ns} addr add ${s_ip4}/24 dev bond0
+	ip -n ${s_ns} addr add ${s_ip6}/24 dev bond0
+	sleep 2
+}
+
+server_destroy()
+{
+	# Count the eth link number in real-time as this function
+	# maybe called from other topologies.
+	local link_num=$(ip -n ${s_ns} -br link show | grep -c "^eth")
+	link_num=$((link_num -1))
+	for i in $(seq 0 ${link_num}); do
+		ip -n ${s_ns} link del eth${i}
+	done
+	ip netns del ${s_ns}
+}
+
+client_create()
+{
+	ip netns add ${c_ns}
+	ip -n ${c_ns} link add eth0 type veth peer name c0 netns ${g_ns}
+
+	ip -n ${g_ns} link set c0 up
+	ip -n ${g_ns} link set c0 master br0
+
+	ip -n ${c_ns} link set eth0 up
+	ip -n ${c_ns} addr add ${c_ip4}/24 dev eth0
+	ip -n ${c_ns} addr add ${c_ip6}/24 dev eth0
+}
+
+client_destroy()
+{
+	ip -n ${c_ns} link del eth0
+	ip netns del ${c_ns}
+}
+
+setup_prepare()
+{
+	gateway_create
+	server_create
+	client_create
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	client_destroy
+	server_destroy
+	gateway_destroy
+}
+
+bond_check_connection()
+{
+	local msg=${1:-"check connection"}
+
+	sleep 2
+	ip netns exec ${s_ns} ping ${c_ip4} -c5 -i 0.1 &>/dev/null
+	check_err $? "${msg}: ping failed"
+	ip netns exec ${s_ns} ping6 ${c_ip6} -c5 -i 0.1 &>/dev/null
+	check_err $? "${msg}: ping6 failed"
+}

tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh

···
 #  |                eth0                 |  2001:db8::10/24
 #  +-------------------------------------+
 
-s_ns="s-$(mktemp -u XXXXXX)"
-c_ns="c-$(mktemp -u XXXXXX)"
-g_ns="g-$(mktemp -u XXXXXX)"
-s_ip4="192.0.2.1"
-c_ip4="192.0.2.10"
-g_ip4="192.0.2.254"
-s_ip6="2001:db8::1"
-c_ip6="2001:db8::10"
-g_ip6="2001:db8::254"
-
-gateway_create()
-{
-	ip netns add ${g_ns}
-	ip -n ${g_ns} link add br0 type bridge
-	ip -n ${g_ns} link set br0 up
-	ip -n ${g_ns} addr add ${g_ip4}/24 dev br0
-	ip -n ${g_ns} addr add ${g_ip6}/24 dev br0
-}
-
-gateway_destroy()
-{
-	ip -n ${g_ns} link del br0
-	ip netns del ${g_ns}
-}
-
-server_create()
-{
-	ip netns add ${s_ns}
-	ip -n ${s_ns} link add bond0 type bond mode active-backup miimon 100
-
-	for i in $(seq 0 2); do
-		ip -n ${s_ns} link add eth${i} type veth peer name s${i} netns ${g_ns}
-
-		ip -n ${g_ns} link set s${i} up
-		ip -n ${g_ns} link set s${i} master br0
-		ip -n ${s_ns} link set eth${i} master bond0
-
-		tc -n ${g_ns} qdisc add dev s${i} clsact
-	done
-
-	ip -n ${s_ns} link set bond0 up
-	ip -n ${s_ns} addr add ${s_ip4}/24 dev bond0
-	ip -n ${s_ns} addr add ${s_ip6}/24 dev bond0
-	sleep 2
-}
-
-# Reset bond with new mode and options
-bond_reset()
-{
-	local param="$1"
-
-	ip -n ${s_ns} link set bond0 down
-	ip -n ${s_ns} link del bond0
-
-	ip -n ${s_ns} link add bond0 type bond $param
-	for i in $(seq 0 2); do
-		ip -n ${s_ns} link set eth$i master bond0
-	done
-
-	ip -n ${s_ns} link set bond0 up
-	ip -n ${s_ns} addr add ${s_ip4}/24 dev bond0
-	ip -n ${s_ns} addr add ${s_ip6}/24 dev bond0
-	sleep 2
-}
-
-server_destroy()
-{
-	for i in $(seq 0 2); do
-		ip -n ${s_ns} link del eth${i}
-	done
-	ip netns del ${s_ns}
-}
-
-client_create()
-{
-	ip netns add ${c_ns}
-	ip -n ${c_ns} link add eth0 type veth peer name c0 netns ${g_ns}
-
-	ip -n ${g_ns} link set c0 up
-	ip -n ${g_ns} link set c0 master br0
-
-	ip -n ${c_ns} link set eth0 up
-	ip -n ${c_ns} addr add ${c_ip4}/24 dev eth0
-	ip -n ${c_ns} addr add ${c_ip6}/24 dev eth0
-}
-
-client_destroy()
-{
-	ip -n ${c_ns} link del eth0
-	ip netns del ${c_ns}
-}
+source bond_topo_2d1c.sh
 
 setup_prepare()
 {
 	gateway_create
 	server_create
 	client_create
-}
 
-cleanup()
-{
-	pre_cleanup
-
-	client_destroy
-	server_destroy
-	gateway_destroy
-}
-
-bond_check_connection()
-{
-	local msg=${1:-"check connection"}
-
-	sleep 2
-	ip netns exec ${s_ns} ping ${c_ip4} -c5 -i 0.1 &>/dev/null
-	check_err $? "${msg}: ping failed"
-	ip netns exec ${s_ns} ping6 ${c_ip6} -c5 -i 0.1 &>/dev/null
-	check_err $? "${msg}: ping6 failed"
+	# Add the extra device as we use 3 down links for bond0
+	local i=2
+	ip -n ${s_ns} link add eth${i} type veth peer name s${i} netns ${g_ns}
+	ip -n ${g_ns} link set s${i} up
+	ip -n ${g_ns} link set s${i} master br0
+	ip -n ${s_ns} link set eth${i} master bond0
+	tc -n ${g_ns} qdisc add dev s${i} clsact
 }

tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh

···
 
 port_pool_test()
 {
-	local exp_max_occ=288
+	local exp_max_occ=$(devlink_cell_size_get)
 	local max_occ
 
 	devlink sb occupancy clearmax $DEVLINK_DEV
 
-	$MZ $h1 -c 1 -p 160 -a $h1mac -b $h2mac -A 192.0.1.1 -B 192.0.1.2 \
+	$MZ $h1 -c 1 -p 10 -a $h1mac -b $h2mac -A 192.0.1.1 -B 192.0.1.2 \
 		-t ip -q
 
 	devlink sb occupancy snapshot $DEVLINK_DEV
···
 
 port_tc_ip_test()
 {
-	local exp_max_occ=288
+	local exp_max_occ=$(devlink_cell_size_get)
 	local max_occ
 
 	devlink sb occupancy clearmax $DEVLINK_DEV
 
-	$MZ $h1 -c 1 -p 160 -a $h1mac -b $h2mac -A 192.0.1.1 -B 192.0.1.2 \
+	$MZ $h1 -c 1 -p 10 -a $h1mac -b $h2mac -A 192.0.1.1 -B 192.0.1.2 \
 		-t ip -q
 
 	devlink sb occupancy snapshot $DEVLINK_DEV
···
 
 port_tc_arp_test()
 {
-	local exp_max_occ=96
+	local exp_max_occ=$(devlink_cell_size_get)
 	local max_occ
-
-	if [[ $MLXSW_CHIP != "mlxsw_spectrum" ]]; then
-		exp_max_occ=144
-	fi
 
 	devlink sb occupancy clearmax $DEVLINK_DEV
 
-	$MZ $h1 -c 1 -p 160 -a $h1mac -A 192.0.1.1 -t arp -q
+	$MZ $h1 -c 1 -p 10 -a $h1mac -A 192.0.1.1 -t arp -q
 
 	devlink sb occupancy snapshot $DEVLINK_DEV
 

tools/testing/selftests/net/.gitignore

···
 ipsec
 ipv6_flowlabel
 ipv6_flowlabel_mgr
+log.txt
 msg_zerocopy
 nettest
 psock_fanout
···
 timestamping
 tls
 toeplitz
+tools
 tun
 txring_overwrite
 txtimestamp