Current release - regressions:

- core: avoid CFI problems with sock priv helpers
 
   - xsk: bring back busy polling support
 
   - netpoll: ensure skb_pool list is always initialized
 
 Current release - new code bugs:
 
   - core: make page_pool_ref_netmem work with net iovs
 
   - ipv4: route: fix drop reason being overridden in ip_route_input_slow
 
   - udp: make rehash4 independent in udp_lib_rehash()
 
 Previous releases - regressions:
 
   - bpf: fix bpf_sk_select_reuseport() memory leak
 
   - openvswitch: fix lockup on tx to unregistering netdev with carrier
 
   - mptcp: be sure to send ack when mptcp-level window re-opens
 
   - eth: bnxt: always recalculate features after XDP clearing, fix null-deref
 
   - eth: mlx5: fix sub-function add port error handling
 
   - eth: fec: handle page_pool_dev_alloc_pages error
 
 Previous releases - always broken:
 
   - vsock: some fixes due to transport de-assignment
 
   - eth: ice: fix E825 initialization
 
   - eth: mlx5e: fix inversion dependency warning while enabling IPsec tunnel
 
   - eth: gtp: destroy device along with udp socket's netns dismantle.
 
   - eth: xilinx: axienet: Fix IRQ coalescing packet count overflow
 
 Signed-off-by: Paolo Abeni <pabeni@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 
 iQJGBAABCAAwFiEEg1AjqC77wbdLX2LbKSR5jcyPE6QFAmeJGOISHHBhYmVuaUBy
 ZWRoYXQuY29tAAoJECkkeY3MjxOkfLwP/1XaeyEtSifDiF+bj7f3M6gd8RC2wkNq
 8DvHadl+uPx1RWv0F2UH9fsVz17A3Gg3oF2Agl4tMP5p9F0e489pNjm2QXOl1zac
 hpJdV0VdNJHKEfWhKODRfLap6fNtPoEQP5r3scbFYuzkdMw6sYZujdQUmFNghPYe
 Y6GKZIrQ96vYLpSTrLCAQt/2EEt608b3ESFFhqTkvB8voB2cODNxxBoTJ5K+jMa0
 +fVW46siGKc8HSaUJCWS5YkAW/Tu3AXJmYgKGQg9PaErVclwImsQFXggIki80P7W
 747Gkuc3kZm3Mt91d6kK1s5Sxr/FAaaJlOOE2iHpZld6cN+Y6niJ+knFdkaX5rCE
 T/aLq8cdegwSdct6CIJ7YZp3v1AVv21erWf7OpbY9KGTWPV9d2yzh3fYin87tAzs
 YYo0H1OqqbxpnKThgGREpu+LqEkCbMzsKmwn/5wTAZZl28ySZWZin2ukzTMRqla0
 Y8JJvBYvcHn/ekb4gJNaDhJF7ZBuLjrXlG1SXAyO+GS4TwToqrK/luPRf0tkbI/Z
 QVNBNCukdRTy/IeZQJsc1gtE1tlQmRXNlTbAILPIkWWdxgjdpd/wBbP8/qG9184l
 Ut4gu7AVF+LLH5nhgRVHAcfrO3i/kbRFC3ErQw06YLyqLInyss8GPULP7tWeFfE3
 iM/DsTHjjr04
 =EtnO
 -----END PGP SIGNATURE-----

Merge tag 'net-6.13-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni:
 "Notably this includes fixes for a few regressions spotted very
  recently. No known outstanding ones.

  Current release - regressions:

   - core: avoid CFI problems with sock priv helpers

   - xsk: bring back busy polling support

   - netpoll: ensure skb_pool list is always initialized

  Current release - new code bugs:

   - core: make page_pool_ref_netmem work with net iovs

   - ipv4: route: fix drop reason being overridden in
     ip_route_input_slow

   - udp: make rehash4 independent in udp_lib_rehash()

  Previous releases - regressions:

   - bpf: fix bpf_sk_select_reuseport() memory leak

   - openvswitch: fix lockup on tx to unregistering netdev with carrier

   - mptcp: be sure to send ack when mptcp-level window re-opens

   - eth:
      - bnxt: always recalculate features after XDP clearing, fix
        null-deref
      - mlx5: fix sub-function add port error handling
      - fec: handle page_pool_dev_alloc_pages error

  Previous releases - always broken:

   - vsock: some fixes due to transport de-assignment

   - eth:
      - ice: fix E825 initialization
      - mlx5e: fix inversion dependency warning while enabling IPsec
        tunnel
      - gtp: destroy device along with udp socket's netns dismantle.
      - xilinx: axienet: Fix IRQ coalescing packet count overflow"

* tag 'net-6.13-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (44 commits)
  netdev: avoid CFI problems with sock priv helpers
  net/mlx5e: Always start IPsec sequence number from 1
  net/mlx5e: Rely on reqid in IPsec tunnel mode
  net/mlx5e: Fix inversion dependency warning while enabling IPsec tunnel
  net/mlx5: Clear port select structure when fail to create
  net/mlx5: SF, Fix add port error handling
  net/mlx5: Fix a lockdep warning as part of the write combining test
  net/mlx5: Fix RDMA TX steering prio
  net: make page_pool_ref_netmem work with net iovs
  net: ethernet: xgbe: re-add aneg to supported features in PHY quirks
  net: pcs: xpcs: actively unset DW_VR_MII_DIG_CTRL1_2G5_EN for 1G SGMII
  net: pcs: xpcs: fix DW_VR_MII_DIG_CTRL1_2G5_EN bit being set for 1G SGMII w/o inband
  selftests: net: Adapt ethtool mq tests to fix in qdisc graft
  net: fec: handle page_pool_dev_alloc_pages error
  net: netpoll: ensure skb_pool list is always initialized
  net: xilinx: axienet: Fix IRQ coalescing packet count overflow
  nfp: bpf: prevent integer overflow in nfp_bpf_event_output()
  selftests: mptcp: avoid spurious errors on disconnect
  mptcp: fix spurious wake-up on under memory pressure
  mptcp: be sure to send ack when mptcp-level window re-opens
  ...

drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c

@@ -923,7 +923,6 @@ static void xgbe_phy_free_phy_device(struct xgbe_prv_data *pdata)
 
 static bool xgbe_phy_finisar_phy_quirks(struct xgbe_prv_data *pdata)
 {
-	__ETHTOOL_DECLARE_LINK_MODE_MASK(supported) = { 0, };
 	struct xgbe_phy_data *phy_data = pdata->phy_data;
 	unsigned int phy_id = phy_data->phydev->phy_id;
 
@@ -945,14 +944,7 @@ static bool xgbe_phy_finisar_phy_quirks(struct xgbe_prv_data *pdata)
 	phy_write(phy_data->phydev, 0x04, 0x0d01);
 	phy_write(phy_data->phydev, 0x00, 0x9140);
 
-	linkmode_set_bit_array(phy_10_100_features_array,
+	linkmode_copy(phy_data->phydev->supported, PHY_GBIT_FEATURES);
-			       ARRAY_SIZE(phy_10_100_features_array),
-			       supported);
-	linkmode_set_bit_array(phy_gbit_features_array,
-			       ARRAY_SIZE(phy_gbit_features_array),
-			       supported);
-
-	linkmode_copy(phy_data->phydev->supported, supported);
 
 	phy_support_asym_pause(phy_data->phydev);
 
@@ -964,7 +956,6 @@ static bool xgbe_phy_finisar_phy_quirks(struct xgbe_prv_data *pdata)
 
 static bool xgbe_phy_belfuse_phy_quirks(struct xgbe_prv_data *pdata)
 {
-	__ETHTOOL_DECLARE_LINK_MODE_MASK(supported) = { 0, };
 	struct xgbe_phy_data *phy_data = pdata->phy_data;
 	struct xgbe_sfp_eeprom *sfp_eeprom = &phy_data->sfp_eeprom;
 	unsigned int phy_id = phy_data->phydev->phy_id;
@@ -1028,13 +1019,7 @@ static bool xgbe_phy_belfuse_phy_quirks(struct xgbe_prv_data *pdata)
 	reg = phy_read(phy_data->phydev, 0x00);
 	phy_write(phy_data->phydev, 0x00, reg & ~0x00800);
 
-	linkmode_set_bit_array(phy_10_100_features_array,
+	linkmode_copy(phy_data->phydev->supported, PHY_GBIT_FEATURES);
-			       ARRAY_SIZE(phy_10_100_features_array),
-			       supported);
-	linkmode_set_bit_array(phy_gbit_features_array,
-			       ARRAY_SIZE(phy_gbit_features_array),
-			       supported);
-	linkmode_copy(phy_data->phydev->supported, supported);
 	phy_support_asym_pause(phy_data->phydev);
 
 	netif_dbg(pdata, drv, pdata->netdev,

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

@@ -4708,7 +4708,7 @@ void bnxt_set_ring_params(struct bnxt *bp)
 /* Changing allocation mode of RX rings.
  * TODO: Update when extending xdp_rxq_info to support allocation modes.
  */
-int bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode)
+static void __bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode)
 {
 	struct net_device *dev = bp->dev;
 
@@ -4729,15 +4729,30 @@ int bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode)
 			bp->rx_skb_func = bnxt_rx_page_skb;
 		}
 		bp->rx_dir = DMA_BIDIRECTIONAL;
-		/* Disable LRO or GRO_HW */
-		netdev_update_features(dev);
 	} else {
 		dev->max_mtu = bp->max_mtu;
 		bp->flags &= ~BNXT_FLAG_RX_PAGE_MODE;
 		bp->rx_dir = DMA_FROM_DEVICE;
 		bp->rx_skb_func = bnxt_rx_skb;
 	}
-	return 0;
+}
+
+void bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode)
+{
+	__bnxt_set_rx_skb_mode(bp, page_mode);
+
+	if (!page_mode) {
+		int rx, tx;
+
+		bnxt_get_max_rings(bp, &rx, &tx, true);
+		if (rx > 1) {
+			bp->flags &= ~BNXT_FLAG_NO_AGG_RINGS;
+			bp->dev->hw_features |= NETIF_F_LRO;
+		}
+	}
+
+	/* Update LRO and GRO_HW availability */
+	netdev_update_features(bp->dev);
 }
 
 static void bnxt_free_vnic_attributes(struct bnxt *bp)
@@ -16214,7 +16229,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (bp->max_fltr < BNXT_MAX_FLTR)
 		bp->max_fltr = BNXT_MAX_FLTR;
 	bnxt_init_l2_fltr_tbl(bp);
-	bnxt_set_rx_skb_mode(bp, false);
+	__bnxt_set_rx_skb_mode(bp, false);
 	bnxt_set_tpa_flags(bp);
 	bnxt_set_ring_params(bp);
 	bnxt_rdma_aux_device_init(bp);

drivers/net/ethernet/broadcom/bnxt/bnxt.h

@@ -2846,7 +2846,7 @@ u32 bnxt_fw_health_readl(struct bnxt *bp, int reg_idx);
 bool bnxt_bs_trace_avail(struct bnxt *bp, u16 type);
 void bnxt_set_tpa_flags(struct bnxt *bp);
 void bnxt_set_ring_params(struct bnxt *);
-int bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode);
+void bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode);
 void bnxt_insert_usr_fltr(struct bnxt *bp, struct bnxt_filter_base *fltr);
 void bnxt_del_one_usr_fltr(struct bnxt *bp, struct bnxt_filter_base *fltr);
 int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp, unsigned long *bmap,

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

@@ -422,15 +422,8 @@ static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *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) {
-			bp->flags &= ~BNXT_FLAG_NO_AGG_RINGS;
-			bp->dev->hw_features |= NETIF_F_LRO;
-		}
 	}
 	bp->tx_nr_rings_xdp = tx_xdp;
 	bp->tx_nr_rings = bp->tx_nr_rings_per_tc * tc + tx_xdp;

drivers/net/ethernet/freescale/fec_main.c

@@ -1591,19 +1591,22 @@ static void fec_enet_tx(struct net_device *ndev, int budget)
 		fec_enet_tx_queue(ndev, i, budget);
 }
 
-static void fec_enet_update_cbd(struct fec_enet_priv_rx_q *rxq,
+static int fec_enet_update_cbd(struct fec_enet_priv_rx_q *rxq,
 				struct bufdesc *bdp, int index)
 {
 	struct page *new_page;
 	dma_addr_t phys_addr;
 
 	new_page = page_pool_dev_alloc_pages(rxq->page_pool);
-	WARN_ON(!new_page);
+	if (unlikely(!new_page))
-	rxq->rx_skb_info[index].page = new_page;
+		return -ENOMEM;
 
+	rxq->rx_skb_info[index].page = new_page;
 	rxq->rx_skb_info[index].offset = FEC_ENET_XDP_HEADROOM;
 	phys_addr = page_pool_get_dma_addr(new_page) + FEC_ENET_XDP_HEADROOM;
 	bdp->cbd_bufaddr = cpu_to_fec32(phys_addr);
+
+	return 0;
 }
 
 static u32
@@ -1698,6 +1701,7 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id)
 	int cpu = smp_processor_id();
 	struct xdp_buff xdp;
 	struct page *page;
+	__fec32 cbd_bufaddr;
 	u32 sub_len = 4;
 
 #if !defined(CONFIG_M5272)
@@ -1766,12 +1770,17 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id)
 
 		index = fec_enet_get_bd_index(bdp, &rxq->bd);
 		page = rxq->rx_skb_info[index].page;
+		cbd_bufaddr = bdp->cbd_bufaddr;
+		if (fec_enet_update_cbd(rxq, bdp, index)) {
+			ndev->stats.rx_dropped++;
+			goto rx_processing_done;
+		}
+
 		dma_sync_single_for_cpu(&fep->pdev->dev,
-					fec32_to_cpu(bdp->cbd_bufaddr),
+					fec32_to_cpu(cbd_bufaddr),
 					pkt_len,
 					DMA_FROM_DEVICE);
 		prefetch(page_address(page));
-		fec_enet_update_cbd(rxq, bdp, index);
 
 		if (xdp_prog) {
 			xdp_buff_clear_frags_flag(&xdp);

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

@@ -1665,6 +1665,7 @@ struct ice_aqc_get_port_options_elem {
 #define ICE_AQC_PORT_OPT_MAX_LANE_25G	5
 #define ICE_AQC_PORT_OPT_MAX_LANE_50G	6
 #define ICE_AQC_PORT_OPT_MAX_LANE_100G	7
+#define ICE_AQC_PORT_OPT_MAX_LANE_200G	8
 
 	u8 global_scid[2];
 	u8 phy_scid[2];

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

@@ -4095,6 +4095,57 @@ ice_aq_set_port_option(struct ice_hw *hw, u8 lport, u8 lport_valid,
 	return ice_aq_send_cmd(hw, &desc, NULL, 0, NULL);
 }
 
+/**
+ * ice_get_phy_lane_number - Get PHY lane number for current adapter
+ * @hw: pointer to the hw struct
+ *
+ * Return: PHY lane number on success, negative error code otherwise.
+ */
+int ice_get_phy_lane_number(struct ice_hw *hw)
+{
+	struct ice_aqc_get_port_options_elem *options;
+	unsigned int lport = 0;
+	unsigned int lane;
+	int err;
+
+	options = kcalloc(ICE_AQC_PORT_OPT_MAX, sizeof(*options), GFP_KERNEL);
+	if (!options)
+		return -ENOMEM;
+
+	for (lane = 0; lane < ICE_MAX_PORT_PER_PCI_DEV; lane++) {
+		u8 options_count = ICE_AQC_PORT_OPT_MAX;
+		u8 speed, active_idx, pending_idx;
+		bool active_valid, pending_valid;
+
+		err = ice_aq_get_port_options(hw, options, &options_count, lane,
+					      true, &active_idx, &active_valid,
+					      &pending_idx, &pending_valid);
+		if (err)
+			goto err;
+
+		if (!active_valid)
+			continue;
+
+		speed = options[active_idx].max_lane_speed;
+		/* If we don't get speed for this lane, it's unoccupied */
+		if (speed > ICE_AQC_PORT_OPT_MAX_LANE_200G)
+			continue;
+
+		if (hw->pf_id == lport) {
+			kfree(options);
+			return lane;
+		}
+
+		lport++;
+	}
+
+	/* PHY lane not found */
+	err = -ENXIO;
+err:
+	kfree(options);
+	return err;
+}
+
 /**
  * ice_aq_sff_eeprom
  * @hw: pointer to the HW struct

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

@@ -193,6 +193,7 @@ ice_aq_get_port_options(struct ice_hw *hw,
 int
 ice_aq_set_port_option(struct ice_hw *hw, u8 lport, u8 lport_valid,
 		       u8 new_option);
+int ice_get_phy_lane_number(struct ice_hw *hw);
 int
 ice_aq_sff_eeprom(struct ice_hw *hw, u16 lport, u8 bus_addr,
 		  u16 mem_addr, u8 page, u8 set_page, u8 *data, u8 length,

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

@@ -1144,7 +1144,7 @@ ice_link_event(struct ice_pf *pf, struct ice_port_info *pi, bool link_up,
 	if (link_up == old_link && link_speed == old_link_speed)
 		return 0;
 
-	ice_ptp_link_change(pf, pf->hw.pf_id, link_up);
+	ice_ptp_link_change(pf, link_up);
 
 	if (ice_is_dcb_active(pf)) {
 		if (test_bit(ICE_FLAG_DCB_ENA, pf->flags))
@@ -6790,7 +6790,7 @@ static int ice_up_complete(struct ice_vsi *vsi)
 		ice_print_link_msg(vsi, true);
 		netif_tx_start_all_queues(vsi->netdev);
 		netif_carrier_on(vsi->netdev);
-		ice_ptp_link_change(pf, pf->hw.pf_id, true);
+		ice_ptp_link_change(pf, true);
 	}
 
 	/* Perform an initial read of the statistics registers now to
@@ -7260,7 +7260,7 @@ int ice_down(struct ice_vsi *vsi)
 
 	if (vsi->netdev) {
 		vlan_err = ice_vsi_del_vlan_zero(vsi);
-		ice_ptp_link_change(vsi->back, vsi->back->hw.pf_id, false);
+		ice_ptp_link_change(vsi->back, false);
 		netif_carrier_off(vsi->netdev);
 		netif_tx_disable(vsi->netdev);
 	}

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

@@ -1388,10 +1388,9 @@ ice_ptp_port_phy_restart(struct ice_ptp_port *ptp_port)
 /**
  * ice_ptp_link_change - Reconfigure PTP after link status change
  * @pf: Board private structure
- * @port: Port for which the PHY start is set
  * @linkup: Link is up or down
  */
-void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup)
+void ice_ptp_link_change(struct ice_pf *pf, bool linkup)
 {
 	struct ice_ptp_port *ptp_port;
 	struct ice_hw *hw = &pf->hw;
@@ -1399,14 +1398,7 @@ void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup)
 	if (pf->ptp.state != ICE_PTP_READY)
 		return;
 
-	if (WARN_ON_ONCE(port >= hw->ptp.num_lports))
-		return;
-
 	ptp_port = &pf->ptp.port;
-	if (ice_is_e825c(hw) && hw->ptp.is_2x50g_muxed_topo)
-		port *= 2;
-	if (WARN_ON_ONCE(ptp_port->port_num != port))
-		return;
 
 	/* Update cached link status for this port immediately */
 	ptp_port->link_up = linkup;
@@ -3164,10 +3156,17 @@ void ice_ptp_init(struct ice_pf *pf)
 {
 	struct ice_ptp *ptp = &pf->ptp;
 	struct ice_hw *hw = &pf->hw;
-	int err;
+	int lane_num, err;
 
 	ptp->state = ICE_PTP_INITIALIZING;
 
+	lane_num = ice_get_phy_lane_number(hw);
+	if (lane_num < 0) {
+		err = lane_num;
+		goto err_exit;
+	}
+
+	ptp->port.port_num = (u8)lane_num;
 	ice_ptp_init_hw(hw);
 
 	ice_ptp_init_tx_interrupt_mode(pf);
@@ -3188,10 +3187,6 @@ void ice_ptp_init(struct ice_pf *pf)
 	if (err)
 		goto err_exit;
 
-	ptp->port.port_num = hw->pf_id;
-	if (ice_is_e825c(hw) && hw->ptp.is_2x50g_muxed_topo)
-		ptp->port.port_num = hw->pf_id * 2;
-
 	err = ice_ptp_init_port(pf, &ptp->port);
 	if (err)
 		goto err_exit;

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

@@ -310,7 +310,7 @@ void ice_ptp_prepare_for_reset(struct ice_pf *pf,
 			       enum ice_reset_req reset_type);
 void ice_ptp_init(struct ice_pf *pf);
 void ice_ptp_release(struct ice_pf *pf);
-void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup);
+void ice_ptp_link_change(struct ice_pf *pf, bool linkup);
 #else /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */
 static inline int ice_ptp_set_ts_config(struct ice_pf *pf, struct ifreq *ifr)
 {
@@ -358,7 +358,7 @@ static inline void ice_ptp_prepare_for_reset(struct ice_pf *pf,
 }
 static inline void ice_ptp_init(struct ice_pf *pf) { }
 static inline void ice_ptp_release(struct ice_pf *pf) { }
-static inline void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup)
+static inline void ice_ptp_link_change(struct ice_pf *pf, bool linkup)
 {
 }
 

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

@@ -131,7 +131,7 @@ struct ice_eth56g_mac_reg_cfg eth56g_mac_cfg[NUM_ICE_ETH56G_LNK_SPD] = {
 		.rx_offset = {
 			.serdes = 0xffffeb27, /* -10.42424 */
 			.no_fec = 0xffffcccd, /* -25.6 */
-			.fc = 0xfffe0014, /* -255.96 */
+			.fc = 0xfffc557b, /* -469.26 */
 			.sfd = 0x4a4, /* 2.32 */
 			.bs_ds = 0x32 /* 0.0969697 */
 		}

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

@@ -900,31 +900,46 @@ static void ice_ptp_exec_tmr_cmd(struct ice_hw *hw)
  * The following functions operate on devices with the ETH 56G PHY.
  */
 
+/**
+ * ice_ptp_get_dest_dev_e825 - get destination PHY for given port number
+ * @hw: pointer to the HW struct
+ * @port: destination port
+ *
+ * Return: destination sideband queue PHY device.
+ */
+static enum ice_sbq_msg_dev ice_ptp_get_dest_dev_e825(struct ice_hw *hw,
+						      u8 port)
+{
+	/* On a single complex E825, PHY 0 is always destination device phy_0
+	 * and PHY 1 is phy_0_peer.
+	 */
+	if (port >= hw->ptp.ports_per_phy)
+		return eth56g_phy_1;
+	else
+		return eth56g_phy_0;
+}
+
 /**
  * ice_write_phy_eth56g - Write a PHY port register
  * @hw: pointer to the HW struct
- * @phy_idx: PHY index
+ * @port: destination port
  * @addr: PHY register address
  * @val: Value to write
  *
  * Return: 0 on success, other error codes when failed to write to PHY
  */
-static int ice_write_phy_eth56g(struct ice_hw *hw, u8 phy_idx, u32 addr,
+static int ice_write_phy_eth56g(struct ice_hw *hw, u8 port, u32 addr, u32 val)
-				u32 val)
 {
-	struct ice_sbq_msg_input phy_msg;
+	struct ice_sbq_msg_input msg = {
+		.dest_dev = ice_ptp_get_dest_dev_e825(hw, port),
+		.opcode = ice_sbq_msg_wr,
+		.msg_addr_low = lower_16_bits(addr),
+		.msg_addr_high = upper_16_bits(addr),
+		.data = val
+	};
 	int err;
 
-	phy_msg.opcode = ice_sbq_msg_wr;
+	err = ice_sbq_rw_reg(hw, &msg, ICE_AQ_FLAG_RD);
-
-	phy_msg.msg_addr_low = lower_16_bits(addr);
-	phy_msg.msg_addr_high = upper_16_bits(addr);
-
-	phy_msg.data = val;
-	phy_msg.dest_dev = hw->ptp.phy.eth56g.phy_addr[phy_idx];
-
-	err = ice_sbq_rw_reg(hw, &phy_msg, ICE_AQ_FLAG_RD);
-
 	if (err)
 		ice_debug(hw, ICE_DBG_PTP, "PTP failed to send msg to phy %d\n",
 			  err);
@@ -935,41 +950,36 @@ static int ice_write_phy_eth56g(struct ice_hw *hw, u8 phy_idx, u32 addr,
 /**
  * ice_read_phy_eth56g - Read a PHY port register
  * @hw: pointer to the HW struct
- * @phy_idx: PHY index
+ * @port: destination port
  * @addr: PHY register address
  * @val: Value to write
  *
  * Return: 0 on success, other error codes when failed to read from PHY
  */
-static int ice_read_phy_eth56g(struct ice_hw *hw, u8 phy_idx, u32 addr,
+static int ice_read_phy_eth56g(struct ice_hw *hw, u8 port, u32 addr, u32 *val)
-			       u32 *val)
 {
-	struct ice_sbq_msg_input phy_msg;
+	struct ice_sbq_msg_input msg = {
+		.dest_dev = ice_ptp_get_dest_dev_e825(hw, port),
+		.opcode = ice_sbq_msg_rd,
+		.msg_addr_low = lower_16_bits(addr),
+		.msg_addr_high = upper_16_bits(addr)
+	};
 	int err;
 
-	phy_msg.opcode = ice_sbq_msg_rd;
+	err = ice_sbq_rw_reg(hw, &msg, ICE_AQ_FLAG_RD);
-
+	if (err)
-	phy_msg.msg_addr_low = lower_16_bits(addr);
-	phy_msg.msg_addr_high = upper_16_bits(addr);
-
-	phy_msg.data = 0;
-	phy_msg.dest_dev = hw->ptp.phy.eth56g.phy_addr[phy_idx];
-
-	err = ice_sbq_rw_reg(hw, &phy_msg, ICE_AQ_FLAG_RD);
-	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "PTP failed to send msg to phy %d\n",
 			  err);
-		return err;
+	else
-	}
+		*val = msg.data;
 
-	*val = phy_msg.data;
+	return err;
-
-	return 0;
 }
 
 /**
  * ice_phy_res_address_eth56g - Calculate a PHY port register address
- * @port: Port number to be written
+ * @hw: pointer to the HW struct
+ * @lane: Lane number to be written
  * @res_type: resource type (register/memory)
  * @offset: Offset from PHY port register base
  * @addr: The result address
@@ -978,17 +988,19 @@ static int ice_read_phy_eth56g(struct ice_hw *hw, u8 phy_idx, u32 addr,
  * * %0      - success
  * * %EINVAL - invalid port number or resource type
  */
-static int ice_phy_res_address_eth56g(u8 port, enum eth56g_res_type res_type,
+static int ice_phy_res_address_eth56g(struct ice_hw *hw, u8 lane,
-				      u32 offset, u32 *addr)
+				      enum eth56g_res_type res_type,
+				      u32 offset,
+				      u32 *addr)
 {
-	u8 lane = port % ICE_PORTS_PER_QUAD;
-	u8 phy = ICE_GET_QUAD_NUM(port);
-
 	if (res_type >= NUM_ETH56G_PHY_RES)
 		return -EINVAL;
 
-	*addr = eth56g_phy_res[res_type].base[phy] +
+	/* Lanes 4..7 are in fact 0..3 on a second PHY */
+	lane %= hw->ptp.ports_per_phy;
+	*addr = eth56g_phy_res[res_type].base[0] +
 		lane * eth56g_phy_res[res_type].step + offset;
+
 	return 0;
 }
 
@@ -1008,19 +1020,17 @@ static int ice_phy_res_address_eth56g(u8 port, enum eth56g_res_type res_type,
 static int ice_write_port_eth56g(struct ice_hw *hw, u8 port, u32 offset,
 				 u32 val, enum eth56g_res_type res_type)
 {
-	u8 phy_port = port % hw->ptp.ports_per_phy;
-	u8 phy_idx = port / hw->ptp.ports_per_phy;
 	u32 addr;
 	int err;
 
 	if (port >= hw->ptp.num_lports)
 		return -EINVAL;
 
-	err = ice_phy_res_address_eth56g(phy_port, res_type, offset, &addr);
+	err = ice_phy_res_address_eth56g(hw, port, res_type, offset, &addr);
 	if (err)
 		return err;
 
-	return ice_write_phy_eth56g(hw, phy_idx, addr, val);
+	return ice_write_phy_eth56g(hw, port, addr, val);
 }
 
 /**
@@ -1039,19 +1049,17 @@ static int ice_write_port_eth56g(struct ice_hw *hw, u8 port, u32 offset,
 static int ice_read_port_eth56g(struct ice_hw *hw, u8 port, u32 offset,
 				u32 *val, enum eth56g_res_type res_type)
 {
-	u8 phy_port = port % hw->ptp.ports_per_phy;
-	u8 phy_idx = port / hw->ptp.ports_per_phy;
 	u32 addr;
 	int err;
 
 	if (port >= hw->ptp.num_lports)
 		return -EINVAL;
 
-	err = ice_phy_res_address_eth56g(phy_port, res_type, offset, &addr);
+	err = ice_phy_res_address_eth56g(hw, port, res_type, offset, &addr);
 	if (err)
 		return err;
 
-	return ice_read_phy_eth56g(hw, phy_idx, addr, val);
+	return ice_read_phy_eth56g(hw, port, addr, val);
 }
 
 /**
@@ -1200,6 +1208,56 @@ static int ice_write_port_mem_eth56g(struct ice_hw *hw, u8 port, u16 offset,
 	return ice_write_port_eth56g(hw, port, offset, val, ETH56G_PHY_MEM_PTP);
 }
 
+/**
+ * ice_write_quad_ptp_reg_eth56g - Write a PHY quad register
+ * @hw: pointer to the HW struct
+ * @offset: PHY register offset
+ * @port: Port number
+ * @val: Value to write
+ *
+ * Return:
+ * * %0     - success
+ * * %EIO  - invalid port number or resource type
+ * * %other - failed to write to PHY
+ */
+static int ice_write_quad_ptp_reg_eth56g(struct ice_hw *hw, u8 port,
+					 u32 offset, u32 val)
+{
+	u32 addr;
+
+	if (port >= hw->ptp.num_lports)
+		return -EIO;
+
+	addr = eth56g_phy_res[ETH56G_PHY_REG_PTP].base[0] + offset;
+
+	return ice_write_phy_eth56g(hw, port, addr, val);
+}
+
+/**
+ * ice_read_quad_ptp_reg_eth56g - Read a PHY quad register
+ * @hw: pointer to the HW struct
+ * @offset: PHY register offset
+ * @port: Port number
+ * @val: Value to read
+ *
+ * Return:
+ * * %0     - success
+ * * %EIO  - invalid port number or resource type
+ * * %other - failed to read from PHY
+ */
+static int ice_read_quad_ptp_reg_eth56g(struct ice_hw *hw, u8 port,
+					u32 offset, u32 *val)
+{
+	u32 addr;
+
+	if (port >= hw->ptp.num_lports)
+		return -EIO;
+
+	addr = eth56g_phy_res[ETH56G_PHY_REG_PTP].base[0] + offset;
+
+	return ice_read_phy_eth56g(hw, port, addr, val);
+}
+
 /**
  * ice_is_64b_phy_reg_eth56g - Check if this is a 64bit PHY register
  * @low_addr: the low address to check
@@ -1919,7 +1977,6 @@ ice_phy_get_speed_eth56g(struct ice_link_status *li)
  */
 static int ice_phy_cfg_parpcs_eth56g(struct ice_hw *hw, u8 port)
 {
-	u8 port_blk = port & ~(ICE_PORTS_PER_QUAD - 1);
 	u32 val;
 	int err;
 
@@ -1934,8 +1991,8 @@ static int ice_phy_cfg_parpcs_eth56g(struct ice_hw *hw, u8 port)
 	switch (ice_phy_get_speed_eth56g(&hw->port_info->phy.link_info)) {
 	case ICE_ETH56G_LNK_SPD_1G:
 	case ICE_ETH56G_LNK_SPD_2_5G:
-		err = ice_read_ptp_reg_eth56g(hw, port_blk,
+		err = ice_read_quad_ptp_reg_eth56g(hw, port,
-					      PHY_GPCS_CONFIG_REG0, &val);
+						   PHY_GPCS_CONFIG_REG0, &val);
 		if (err) {
 			ice_debug(hw, ICE_DBG_PTP, "Failed to read PHY_GPCS_CONFIG_REG0, status: %d",
 				  err);
@@ -1946,8 +2003,8 @@ static int ice_phy_cfg_parpcs_eth56g(struct ice_hw *hw, u8 port)
 		val |= FIELD_PREP(PHY_GPCS_CONFIG_REG0_TX_THR_M,
 				  ICE_ETH56G_NOMINAL_TX_THRESH);
 
-		err = ice_write_ptp_reg_eth56g(hw, port_blk,
+		err = ice_write_quad_ptp_reg_eth56g(hw, port,
-					       PHY_GPCS_CONFIG_REG0, val);
+						    PHY_GPCS_CONFIG_REG0, val);
 		if (err) {
 			ice_debug(hw, ICE_DBG_PTP, "Failed to write PHY_GPCS_CONFIG_REG0, status: %d",
 				  err);
@@ -1988,50 +2045,47 @@ static int ice_phy_cfg_parpcs_eth56g(struct ice_hw *hw, u8 port)
  */
 int ice_phy_cfg_ptp_1step_eth56g(struct ice_hw *hw, u8 port)
 {
-	u8 port_blk = port & ~(ICE_PORTS_PER_QUAD - 1);
+	u8 quad_lane = port % ICE_PORTS_PER_QUAD;
-	u8 blk_port = port & (ICE_PORTS_PER_QUAD - 1);
+	u32 addr, val, peer_delay;
 	bool enable, sfd_ena;
-	u32 val, peer_delay;
 	int err;
 
 	enable = hw->ptp.phy.eth56g.onestep_ena;
 	peer_delay = hw->ptp.phy.eth56g.peer_delay;
 	sfd_ena = hw->ptp.phy.eth56g.sfd_ena;
 
-	/* PHY_PTP_1STEP_CONFIG */
+	addr = PHY_PTP_1STEP_CONFIG;
-	err = ice_read_ptp_reg_eth56g(hw, port_blk, PHY_PTP_1STEP_CONFIG, &val);
+	err = ice_read_quad_ptp_reg_eth56g(hw, port, addr, &val);
 	if (err)
 		return err;
 
 	if (enable)
-		val |= blk_port;
+		val |= BIT(quad_lane);
 	else
-		val &= ~blk_port;
+		val &= ~BIT(quad_lane);
 
 	val &= ~(PHY_PTP_1STEP_T1S_UP64_M | PHY_PTP_1STEP_T1S_DELTA_M);
 
-	err = ice_write_ptp_reg_eth56g(hw, port_blk, PHY_PTP_1STEP_CONFIG, val);
+	err = ice_write_quad_ptp_reg_eth56g(hw, port, addr, val);
 	if (err)
 		return err;
 
-	/* PHY_PTP_1STEP_PEER_DELAY */
+	addr = PHY_PTP_1STEP_PEER_DELAY(quad_lane);
 	val = FIELD_PREP(PHY_PTP_1STEP_PD_DELAY_M, peer_delay);
 	if (peer_delay)
 		val |= PHY_PTP_1STEP_PD_ADD_PD_M;
 	val |= PHY_PTP_1STEP_PD_DLY_V_M;
-	err = ice_write_ptp_reg_eth56g(hw, port_blk,
+	err = ice_write_quad_ptp_reg_eth56g(hw, port, addr, val);
-				       PHY_PTP_1STEP_PEER_DELAY(blk_port), val);
 	if (err)
 		return err;
 
 	val &= ~PHY_PTP_1STEP_PD_DLY_V_M;
-	err = ice_write_ptp_reg_eth56g(hw, port_blk,
+	err = ice_write_quad_ptp_reg_eth56g(hw, port, addr, val);
-				       PHY_PTP_1STEP_PEER_DELAY(blk_port), val);
 	if (err)
 		return err;
 
-	/* PHY_MAC_XIF_MODE */
+	addr = PHY_MAC_XIF_MODE;
-	err = ice_read_mac_reg_eth56g(hw, port, PHY_MAC_XIF_MODE, &val);
+	err = ice_read_mac_reg_eth56g(hw, port, addr, &val);
 	if (err)
 		return err;
 
@@ -2051,7 +2105,7 @@ int ice_phy_cfg_ptp_1step_eth56g(struct ice_hw *hw, u8 port)
 	       FIELD_PREP(PHY_MAC_XIF_TS_BIN_MODE_M, enable) |
 	       FIELD_PREP(PHY_MAC_XIF_TS_SFD_ENA_M, sfd_ena);
 
-	return ice_write_mac_reg_eth56g(hw, port, PHY_MAC_XIF_MODE, val);
+	return ice_write_mac_reg_eth56g(hw, port, addr, val);
 }
 
 /**
@@ -2093,21 +2147,22 @@ static u32 ice_ptp_calc_bitslip_eth56g(struct ice_hw *hw, u8 port, u32 bs,
 				       bool fc, bool rs,
 				       enum ice_eth56g_link_spd spd)
 {
-	u8 port_offset = port & (ICE_PORTS_PER_QUAD - 1);
-	u8 port_blk = port & ~(ICE_PORTS_PER_QUAD - 1);
 	u32 bitslip;
 	int err;
 
 	if (!bs || rs)
 		return 0;
 
-	if (spd == ICE_ETH56G_LNK_SPD_1G || spd == ICE_ETH56G_LNK_SPD_2_5G)
+	if (spd == ICE_ETH56G_LNK_SPD_1G || spd == ICE_ETH56G_LNK_SPD_2_5G) {
 		err = ice_read_gpcs_reg_eth56g(hw, port, PHY_GPCS_BITSLIP,
 					       &bitslip);
-	else
+	} else {
-		err = ice_read_ptp_reg_eth56g(hw, port_blk,
+		u8 quad_lane = port % ICE_PORTS_PER_QUAD;
-					      PHY_REG_SD_BIT_SLIP(port_offset),
+		u32 addr;
-					      &bitslip);
+
+		addr = PHY_REG_SD_BIT_SLIP(quad_lane);
+		err = ice_read_quad_ptp_reg_eth56g(hw, port, addr, &bitslip);
+	}
 	if (err)
 		return 0;
 
@@ -2667,59 +2722,29 @@ static int ice_get_phy_tx_tstamp_ready_eth56g(struct ice_hw *hw, u8 port,
 }
 
 /**
- * ice_is_muxed_topo - detect breakout 2x50G topology for E825C
+ * ice_ptp_init_phy_e825 - initialize PHY parameters
- * @hw: pointer to the HW struct
- *
- * Return: true if it's 2x50 breakout topology, false otherwise
- */
-static bool ice_is_muxed_topo(struct ice_hw *hw)
-{
-	u8 link_topo;
-	bool mux;
-	u32 val;
-
-	val = rd32(hw, GLGEN_SWITCH_MODE_CONFIG);
-	mux = FIELD_GET(GLGEN_SWITCH_MODE_CONFIG_25X4_QUAD_M, val);
-	val = rd32(hw, GLGEN_MAC_LINK_TOPO);
-	link_topo = FIELD_GET(GLGEN_MAC_LINK_TOPO_LINK_TOPO_M, val);
-
-	return (mux && link_topo == ICE_LINK_TOPO_UP_TO_2_LINKS);
-}
-
-/**
- * ice_ptp_init_phy_e825c - initialize PHY parameters
  * @hw: pointer to the HW struct
  */
-static void ice_ptp_init_phy_e825c(struct ice_hw *hw)
+static void ice_ptp_init_phy_e825(struct ice_hw *hw)
 {
 	struct ice_ptp_hw *ptp = &hw->ptp;
 	struct ice_eth56g_params *params;
-	u8 phy;
+	u32 phy_rev;
+	int err;
 
 	ptp->phy_model = ICE_PHY_ETH56G;
 	params = &ptp->phy.eth56g;
 	params->onestep_ena = false;
 	params->peer_delay = 0;
 	params->sfd_ena = false;
-	params->phy_addr[0] = eth56g_phy_0;
-	params->phy_addr[1] = eth56g_phy_1;
 	params->num_phys = 2;
 	ptp->ports_per_phy = 4;
 	ptp->num_lports = params->num_phys * ptp->ports_per_phy;
 
 	ice_sb_access_ena_eth56g(hw, true);
-	for (phy = 0; phy < params->num_phys; phy++) {
+	err = ice_read_phy_eth56g(hw, hw->pf_id, PHY_REG_REVISION, &phy_rev);
-		u32 phy_rev;
+	if (err || phy_rev != PHY_REVISION_ETH56G)
-		int err;
+		ptp->phy_model = ICE_PHY_UNSUP;
-
-		err = ice_read_phy_eth56g(hw, phy, PHY_REG_REVISION, &phy_rev);
-		if (err || phy_rev != PHY_REVISION_ETH56G) {
-			ptp->phy_model = ICE_PHY_UNSUP;
-			return;
-		}
-	}
-
-	ptp->is_2x50g_muxed_topo = ice_is_muxed_topo(hw);
 }
 
 /* E822 family functions
@@ -2738,10 +2763,9 @@ static void ice_fill_phy_msg_e82x(struct ice_hw *hw,
 				  struct ice_sbq_msg_input *msg, u8 port,
 				  u16 offset)
 {
-	int phy_port, phy, quadtype;
+	int phy_port, quadtype;
 
 	phy_port = port % hw->ptp.ports_per_phy;
-	phy = port / hw->ptp.ports_per_phy;
 	quadtype = ICE_GET_QUAD_NUM(port) %
 		   ICE_GET_QUAD_NUM(hw->ptp.ports_per_phy);
 
@@ -2753,12 +2777,7 @@ static void ice_fill_phy_msg_e82x(struct ice_hw *hw,
 		msg->msg_addr_high = P_Q1_H(P_4_BASE + offset, phy_port);
 	}
 
-	if (phy == 0)
+	msg->dest_dev = rmn_0;
-		msg->dest_dev = rmn_0;
-	else if (phy == 1)
-		msg->dest_dev = rmn_1;
-	else
-		msg->dest_dev = rmn_2;
 }
 
 /**
@@ -5478,7 +5497,7 @@ void ice_ptp_init_hw(struct ice_hw *hw)
 	else if (ice_is_e810(hw))
 		ice_ptp_init_phy_e810(ptp);
 	else if (ice_is_e825c(hw))
-		ice_ptp_init_phy_e825c(hw);
+		ice_ptp_init_phy_e825(hw);
 	else
 		ptp->phy_model = ICE_PHY_UNSUP;
 }

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

@@ -850,7 +850,6 @@ struct ice_mbx_data {
 
 struct ice_eth56g_params {
 	u8 num_phys;
-	u8 phy_addr[2];
 	bool onestep_ena;
 	bool sfd_ena;
 	u32 peer_delay;
@@ -881,7 +880,6 @@ struct ice_ptp_hw {
 	union ice_phy_params phy;
 	u8 num_lports;
 	u8 ports_per_phy;
-	bool is_2x50g_muxed_topo;
 };
 
 /* Port hardware description */

drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c

@@ -724,6 +724,12 @@ static int mlx5e_xfrm_add_state(struct xfrm_state *x,
 	/* check esn */
 	if (x->props.flags & XFRM_STATE_ESN)
 		mlx5e_ipsec_update_esn_state(sa_entry);
+	else
+		/* According to RFC4303, section "3.3.3. Sequence Number Generation",
+		 * the first packet sent using a given SA will contain a sequence
+		 * number of 1.
+		 */
+		sa_entry->esn_state.esn = 1;
 
 	mlx5e_ipsec_build_accel_xfrm_attrs(sa_entry, &sa_entry->attrs);
 
@@ -768,9 +774,12 @@ static int mlx5e_xfrm_add_state(struct xfrm_state *x,
 				   MLX5_IPSEC_RESCHED);
 
 	if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET &&
-	    x->props.mode == XFRM_MODE_TUNNEL)
+	    x->props.mode == XFRM_MODE_TUNNEL) {
-		xa_set_mark(&ipsec->sadb, sa_entry->ipsec_obj_id,
+		xa_lock_bh(&ipsec->sadb);
-			    MLX5E_IPSEC_TUNNEL_SA);
+		__xa_set_mark(&ipsec->sadb, sa_entry->ipsec_obj_id,
+			      MLX5E_IPSEC_TUNNEL_SA);
+		xa_unlock_bh(&ipsec->sadb);
+	}
 
 out:
 	x->xso.offload_handle = (unsigned long)sa_entry;
@@ -797,7 +806,6 @@ err_xfrm:
 static void mlx5e_xfrm_del_state(struct xfrm_state *x)
 {
 	struct mlx5e_ipsec_sa_entry *sa_entry = to_ipsec_sa_entry(x);
-	struct mlx5_accel_esp_xfrm_attrs *attrs = &sa_entry->attrs;
 	struct mlx5e_ipsec *ipsec = sa_entry->ipsec;
 	struct mlx5e_ipsec_sa_entry *old;
 
@@ -806,12 +814,6 @@ static void mlx5e_xfrm_del_state(struct xfrm_state *x)
 
 	old = xa_erase_bh(&ipsec->sadb, sa_entry->ipsec_obj_id);
 	WARN_ON(old != sa_entry);
-
-	if (attrs->mode == XFRM_MODE_TUNNEL &&
-	    attrs->type == XFRM_DEV_OFFLOAD_PACKET)
-		/* Make sure that no ARP requests are running in parallel */
-		flush_workqueue(ipsec->wq);
-
 }
 
 static void mlx5e_xfrm_free_state(struct xfrm_state *x)

drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c

@@ -1718,23 +1718,21 @@ static int tx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 		goto err_alloc;
 	}
 
-	if (attrs->family == AF_INET)
-		setup_fte_addr4(spec, &attrs->saddr.a4, &attrs->daddr.a4);
-	else
-		setup_fte_addr6(spec, attrs->saddr.a6, attrs->daddr.a6);
-
 	setup_fte_no_frags(spec);
 	setup_fte_upper_proto_match(spec, &attrs->upspec);
 
 	switch (attrs->type) {
 	case XFRM_DEV_OFFLOAD_CRYPTO:
+		if (attrs->family == AF_INET)
+			setup_fte_addr4(spec, &attrs->saddr.a4, &attrs->daddr.a4);
+		else
+			setup_fte_addr6(spec, attrs->saddr.a6, attrs->daddr.a6);
 		setup_fte_spi(spec, attrs->spi, false);
 		setup_fte_esp(spec);
 		setup_fte_reg_a(spec);
 		break;
 	case XFRM_DEV_OFFLOAD_PACKET:
-		if (attrs->reqid)
+		setup_fte_reg_c4(spec, attrs->reqid);
-			setup_fte_reg_c4(spec, attrs->reqid);
 		err = setup_pkt_reformat(ipsec, attrs, &flow_act);
 		if (err)
 			goto err_pkt_reformat;

drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c

@@ -91,8 +91,9 @@ u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev)
 EXPORT_SYMBOL_GPL(mlx5_ipsec_device_caps);
 
 static void mlx5e_ipsec_packet_setup(void *obj, u32 pdn,
-				     struct mlx5_accel_esp_xfrm_attrs *attrs)
+				     struct mlx5e_ipsec_sa_entry *sa_entry)
 {
+	struct mlx5_accel_esp_xfrm_attrs *attrs = &sa_entry->attrs;
 	void *aso_ctx;
 
 	aso_ctx = MLX5_ADDR_OF(ipsec_obj, obj, ipsec_aso);
@@ -120,8 +121,12 @@ static void mlx5e_ipsec_packet_setup(void *obj, u32 pdn,
 	 * active.
 	 */
 	MLX5_SET(ipsec_obj, obj, aso_return_reg, MLX5_IPSEC_ASO_REG_C_4_5);
-	if (attrs->dir == XFRM_DEV_OFFLOAD_OUT)
+	if (attrs->dir == XFRM_DEV_OFFLOAD_OUT) {
 		MLX5_SET(ipsec_aso, aso_ctx, mode, MLX5_IPSEC_ASO_INC_SN);
+		if (!attrs->replay_esn.trigger)
+			MLX5_SET(ipsec_aso, aso_ctx, mode_parameter,
+				 sa_entry->esn_state.esn);
+	}
 
 	if (attrs->lft.hard_packet_limit != XFRM_INF) {
 		MLX5_SET(ipsec_aso, aso_ctx, remove_flow_pkt_cnt,
@@ -175,7 +180,7 @@ static int mlx5_create_ipsec_obj(struct mlx5e_ipsec_sa_entry *sa_entry)
 
 	res = &mdev->mlx5e_res.hw_objs;
 	if (attrs->type == XFRM_DEV_OFFLOAD_PACKET)
-		mlx5e_ipsec_packet_setup(obj, res->pdn, attrs);
+		mlx5e_ipsec_packet_setup(obj, res->pdn, sa_entry);
 
 	err = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
 	if (!err)

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

@@ -2709,6 +2709,7 @@ struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev,
 		break;
 	case MLX5_FLOW_NAMESPACE_RDMA_TX:
 		root_ns = steering->rdma_tx_root_ns;
+		prio = RDMA_TX_BYPASS_PRIO;
 		break;
 	case MLX5_FLOW_NAMESPACE_RDMA_RX_COUNTERS:
 		root_ns = steering->rdma_rx_root_ns;

drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c

@@ -530,7 +530,7 @@ int mlx5_lag_port_sel_create(struct mlx5_lag *ldev,
 	set_tt_map(port_sel, hash_type);
 	err = mlx5_lag_create_definers(ldev, hash_type, ports);
 	if (err)
-		return err;
+		goto clear_port_sel;
 
 	if (port_sel->tunnel) {
 		err = mlx5_lag_create_inner_ttc_table(ldev);
@@ -549,6 +549,8 @@ destroy_inner:
 		mlx5_destroy_ttc_table(port_sel->inner.ttc);
 destroy_definers:
 	mlx5_lag_destroy_definers(ldev);
+clear_port_sel:
+	memset(port_sel, 0, sizeof(*port_sel));
 	return err;
 }
 

drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c

@@ -257,6 +257,7 @@ static int mlx5_sf_add(struct mlx5_core_dev *dev, struct mlx5_sf_table *table,
 	return 0;
 
 esw_err:
+	mlx5_sf_function_id_erase(table, sf);
 	mlx5_sf_free(table, sf);
 	return err;
 }

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

@@ -382,6 +382,7 @@ err_alloc_bfreg:
 
 bool mlx5_wc_support_get(struct mlx5_core_dev *mdev)
 {
+	struct mutex *wc_state_lock = &mdev->wc_state_lock;
 	struct mlx5_core_dev *parent = NULL;
 
 	if (!MLX5_CAP_GEN(mdev, bf)) {
@@ -400,32 +401,31 @@ bool mlx5_wc_support_get(struct mlx5_core_dev *mdev)
 		 */
 		goto out;
 
-	mutex_lock(&mdev->wc_state_lock);
+#ifdef CONFIG_MLX5_SF
+	if (mlx5_core_is_sf(mdev)) {
+		parent = mdev->priv.parent_mdev;
+		wc_state_lock = &parent->wc_state_lock;
+	}
+#endif
+
+	mutex_lock(wc_state_lock);
 
 	if (mdev->wc_state != MLX5_WC_STATE_UNINITIALIZED)
 		goto unlock;
 
-#ifdef CONFIG_MLX5_SF
-	if (mlx5_core_is_sf(mdev))
-		parent = mdev->priv.parent_mdev;
-#endif
-
 	if (parent) {
-		mutex_lock(&parent->wc_state_lock);
-
 		mlx5_core_test_wc(parent);
 
 		mlx5_core_dbg(mdev, "parent set wc_state=%d\n",
 			      parent->wc_state);
 		mdev->wc_state = parent->wc_state;
 
-		mutex_unlock(&parent->wc_state_lock);
+	} else {
+		mlx5_core_test_wc(mdev);
 	}
 
-	mlx5_core_test_wc(mdev);
-
 unlock:
-	mutex_unlock(&mdev->wc_state_lock);
+	mutex_unlock(wc_state_lock);
 out:
 	mlx5_core_dbg(mdev, "wc_state=%d\n", mdev->wc_state);
 

drivers/net/ethernet/microsoft/mana/gdma_main.c

@@ -1656,9 +1656,9 @@ static int __init mana_driver_init(void)
 
 static void __exit mana_driver_exit(void)
 {
-	debugfs_remove(mana_debugfs_root);
-
 	pci_unregister_driver(&mana_driver);
+
+	debugfs_remove(mana_debugfs_root);
 }
 
 module_init(mana_driver_init);

drivers/net/ethernet/netronome/nfp/bpf/offload.c

@@ -458,7 +458,8 @@ int nfp_bpf_event_output(struct nfp_app_bpf *bpf, const void *data,
 	map_id_full = be64_to_cpu(cbe->map_ptr);
 	map_id = map_id_full;
 
-	if (len < sizeof(struct cmsg_bpf_event) + pkt_size + data_size)
+	if (size_add(pkt_size, data_size) > INT_MAX ||
+	    len < sizeof(struct cmsg_bpf_event) + pkt_size + data_size)
 		return -EINVAL;
 	if (cbe->hdr.ver != NFP_CCM_ABI_VERSION)
 		return -EINVAL;

drivers/net/ethernet/realtek/r8169_main.c

@@ -16,7 +16,6 @@
 #include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/ethtool.h>
-#include <linux/hwmon.h>
 #include <linux/phy.h>
 #include <linux/if_vlan.h>
 #include <linux/in.h>
@@ -5347,43 +5346,6 @@ static bool rtl_aspm_is_safe(struct rtl8169_private *tp)
 	return false;
 }
 
-static umode_t r8169_hwmon_is_visible(const void *drvdata,
-				      enum hwmon_sensor_types type,
-				      u32 attr, int channel)
-{
-	return 0444;
-}
-
-static int r8169_hwmon_read(struct device *dev, enum hwmon_sensor_types type,
-			    u32 attr, int channel, long *val)
-{
-	struct rtl8169_private *tp = dev_get_drvdata(dev);
-	int val_raw;
-
-	val_raw = phy_read_paged(tp->phydev, 0xbd8, 0x12) & 0x3ff;
-	if (val_raw >= 512)
-		val_raw -= 1024;
-
-	*val = 1000 * val_raw / 2;
-
-	return 0;
-}
-
-static const struct hwmon_ops r8169_hwmon_ops = {
-	.is_visible =  r8169_hwmon_is_visible,
-	.read = r8169_hwmon_read,
-};
-
-static const struct hwmon_channel_info * const r8169_hwmon_info[] = {
-	HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT),
-	NULL
-};
-
-static const struct hwmon_chip_info r8169_hwmon_chip_info = {
-	.ops = &r8169_hwmon_ops,
-	.info = r8169_hwmon_info,
-};
-
 static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	struct rtl8169_private *tp;
@@ -5563,12 +5525,6 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (rc)
 		return rc;
 
-	/* The temperature sensor is available from RTl8125B */
-	if (IS_REACHABLE(CONFIG_HWMON) && tp->mac_version >= RTL_GIGA_MAC_VER_63)
-		/* ignore errors */
-		devm_hwmon_device_register_with_info(&pdev->dev, "nic_temp", tp,
-						     &r8169_hwmon_chip_info,
-						     NULL);
 	rc = register_netdev(dev);
 	if (rc)
 		return rc;

drivers/net/ethernet/renesas/ravb_main.c

@@ -2763,6 +2763,7 @@ static const struct ravb_hw_info ravb_rzv2m_hw_info = {
 	.net_features = NETIF_F_RXCSUM,
 	.stats_len = ARRAY_SIZE(ravb_gstrings_stats),
 	.tccr_mask = TCCR_TSRQ0 | TCCR_TSRQ1 | TCCR_TSRQ2 | TCCR_TSRQ3,
+	.tx_max_frame_size = SZ_2K,
 	.rx_max_frame_size = SZ_2K,
 	.rx_buffer_size = SZ_2K +
 			  SKB_DATA_ALIGN(sizeof(struct skb_shared_info)),

drivers/net/ethernet/ti/cpsw_ale.c

@@ -127,15 +127,15 @@ struct cpsw_ale_dev_id {
 
 static inline int cpsw_ale_get_field(u32 *ale_entry, u32 start, u32 bits)
 {
-	int idx, idx2;
+	int idx, idx2, index;
 	u32 hi_val = 0;
 
 	idx    = start / 32;
 	idx2 = (start + bits - 1) / 32;
 	/* Check if bits to be fetched exceed a word */
 	if (idx != idx2) {
-		idx2 = 2 - idx2; /* flip */
+		index = 2 - idx2; /* flip */
-		hi_val = ale_entry[idx2] << ((idx2 * 32) - start);
+		hi_val = ale_entry[index] << ((idx2 * 32) - start);
 	}
 	start -= idx * 32;
 	idx    = 2 - idx; /* flip */
@@ -145,16 +145,16 @@ static inline int cpsw_ale_get_field(u32 *ale_entry, u32 start, u32 bits)
 static inline void cpsw_ale_set_field(u32 *ale_entry, u32 start, u32 bits,
 				      u32 value)
 {
-	int idx, idx2;
+	int idx, idx2, index;
 
 	value &= BITMASK(bits);
 	idx = start / 32;
 	idx2 = (start + bits - 1) / 32;
 	/* Check if bits to be set exceed a word */
 	if (idx != idx2) {
-		idx2 = 2 - idx2; /* flip */
+		index = 2 - idx2; /* flip */
-		ale_entry[idx2] &= ~(BITMASK(bits + start - (idx2 * 32)));
+		ale_entry[index] &= ~(BITMASK(bits + start - (idx2 * 32)));
-		ale_entry[idx2] |= (value >> ((idx2 * 32) - start));
+		ale_entry[index] |= (value >> ((idx2 * 32) - start));
 	}
 	start -= idx * 32;
 	idx = 2 - idx; /* flip */

drivers/net/ethernet/xilinx/xilinx_axienet_main.c

@@ -2056,6 +2056,12 @@ axienet_ethtools_set_coalesce(struct net_device *ndev,
 		return -EBUSY;
 	}
 
+	if (ecoalesce->rx_max_coalesced_frames > 255 ||
+	    ecoalesce->tx_max_coalesced_frames > 255) {
+		NL_SET_ERR_MSG(extack, "frames must be less than 256");
+		return -EINVAL;
+	}
+
 	if (ecoalesce->rx_max_coalesced_frames)
 		lp->coalesce_count_rx = ecoalesce->rx_max_coalesced_frames;
 	if (ecoalesce->rx_coalesce_usecs)

drivers/net/gtp.c

@@ -1524,8 +1524,8 @@ static int gtp_newlink(struct net *src_net, struct net_device *dev,
 		goto out_encap;
 	}
 
-	gn = net_generic(dev_net(dev), gtp_net_id);
+	gn = net_generic(src_net, gtp_net_id);
-	list_add_rcu(&gtp->list, &gn->gtp_dev_list);
+	list_add(&gtp->list, &gn->gtp_dev_list);
 	dev->priv_destructor = gtp_destructor;
 
 	netdev_dbg(dev, "registered new GTP interface\n");
@@ -1551,7 +1551,7 @@ static void gtp_dellink(struct net_device *dev, struct list_head *head)
 		hlist_for_each_entry_safe(pctx, next, &gtp->tid_hash[i], hlist_tid)
 			pdp_context_delete(pctx);
 
-	list_del_rcu(&gtp->list);
+	list_del(&gtp->list);
 	unregister_netdevice_queue(dev, head);
 }
 
@@ -2271,16 +2271,19 @@ static int gtp_genl_dump_pdp(struct sk_buff *skb,
 	struct gtp_dev *last_gtp = (struct gtp_dev *)cb->args[2], *gtp;
 	int i, j, bucket = cb->args[0], skip = cb->args[1];
 	struct net *net = sock_net(skb->sk);
+	struct net_device *dev;
 	struct pdp_ctx *pctx;
-	struct gtp_net *gn;
-
-	gn = net_generic(net, gtp_net_id);
 
 	if (cb->args[4])
 		return 0;
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(gtp, &gn->gtp_dev_list, list) {
+	for_each_netdev_rcu(net, dev) {
+		if (dev->rtnl_link_ops != &gtp_link_ops)
+			continue;
+
+		gtp = netdev_priv(dev);
+
 		if (last_gtp && last_gtp != gtp)
 			continue;
 		else
@@ -2475,9 +2478,14 @@ static void __net_exit gtp_net_exit_batch_rtnl(struct list_head *net_list,
 
 	list_for_each_entry(net, net_list, exit_list) {
 		struct gtp_net *gn = net_generic(net, gtp_net_id);
-		struct gtp_dev *gtp;
+		struct gtp_dev *gtp, *gtp_next;
+		struct net_device *dev;
 
-		list_for_each_entry(gtp, &gn->gtp_dev_list, list)
+		for_each_netdev(net, dev)
+			if (dev->rtnl_link_ops == &gtp_link_ops)
+				gtp_dellink(dev, dev_to_kill);
+
+		list_for_each_entry_safe(gtp, gtp_next, &gn->gtp_dev_list, list)
 			gtp_dellink(gtp->dev, dev_to_kill);
 	}
 }

drivers/net/pcs/pcs-xpcs.c

@@ -684,7 +684,9 @@ static int xpcs_config_aneg_c37_sgmii(struct dw_xpcs *xpcs,
 	if (ret < 0)
 		return ret;
 
-	mask = DW_VR_MII_DIG_CTRL1_MAC_AUTO_SW;
+	val = 0;
+	mask = DW_VR_MII_DIG_CTRL1_2G5_EN | DW_VR_MII_DIG_CTRL1_MAC_AUTO_SW;
+
 	if (neg_mode == PHYLINK_PCS_NEG_INBAND_ENABLED)
 		val = DW_VR_MII_DIG_CTRL1_MAC_AUTO_SW;
 

drivers/net/pfcp.c

@@ -206,8 +206,8 @@ static int pfcp_newlink(struct net *net, struct net_device *dev,
 		goto exit_del_pfcp_sock;
 	}
 
-	pn = net_generic(dev_net(dev), pfcp_net_id);
+	pn = net_generic(net, pfcp_net_id);
-	list_add_rcu(&pfcp->list, &pn->pfcp_dev_list);
+	list_add(&pfcp->list, &pn->pfcp_dev_list);
 
 	netdev_dbg(dev, "registered new PFCP interface\n");
 
@@ -224,7 +224,7 @@ static void pfcp_dellink(struct net_device *dev, struct list_head *head)
 {
 	struct pfcp_dev *pfcp = netdev_priv(dev);
 
-	list_del_rcu(&pfcp->list);
+	list_del(&pfcp->list);
 	unregister_netdevice_queue(dev, head);
 }
 
@@ -247,11 +247,16 @@ static int __net_init pfcp_net_init(struct net *net)
 static void __net_exit pfcp_net_exit(struct net *net)
 {
 	struct pfcp_net *pn = net_generic(net, pfcp_net_id);
-	struct pfcp_dev *pfcp;
+	struct pfcp_dev *pfcp, *pfcp_next;
+	struct net_device *dev;
 	LIST_HEAD(list);
 
 	rtnl_lock();
-	list_for_each_entry(pfcp, &pn->pfcp_dev_list, list)
+	for_each_netdev(net, dev)
+		if (dev->rtnl_link_ops == &pfcp_link_ops)
+			pfcp_dellink(dev, &list);
+
+	list_for_each_entry_safe(pfcp, pfcp_next, &pn->pfcp_dev_list, list)
 		pfcp_dellink(pfcp->dev, &list);
 
 	unregister_netdevice_many(&list);

include/net/busy_poll.h

@@ -174,12 +174,4 @@ static inline void sk_mark_napi_id_once(struct sock *sk,
 #endif
 }
 
-static inline void sk_mark_napi_id_once_xdp(struct sock *sk,
-					    const struct xdp_buff *xdp)
-{
-#ifdef CONFIG_NET_RX_BUSY_POLL
-	__sk_mark_napi_id_once(sk, xdp->rxq->napi_id);
-#endif
-}
-
 #endif /* _LINUX_NET_BUSY_POLL_H */

include/net/page_pool/helpers.h

@@ -294,7 +294,7 @@ static inline long page_pool_unref_page(struct page *page, long nr)
 
 static inline void page_pool_ref_netmem(netmem_ref netmem)
 {
-	atomic_long_inc(&netmem_to_page(netmem)->pp_ref_count);
+	atomic_long_inc(netmem_get_pp_ref_count_ref(netmem));
 }
 
 static inline void page_pool_ref_page(struct page *page)

include/net/xdp.h

@@ -62,7 +62,6 @@ struct xdp_rxq_info {
 	u32 queue_index;
 	u32 reg_state;
 	struct xdp_mem_info mem;
-	unsigned int napi_id;
 	u32 frag_size;
 } ____cacheline_aligned; /* perf critical, avoid false-sharing */
 

include/net/xdp_sock_drv.h

@@ -59,15 +59,6 @@ static inline void xsk_pool_fill_cb(struct xsk_buff_pool *pool,
 	xp_fill_cb(pool, desc);
 }
 
-static inline unsigned int xsk_pool_get_napi_id(struct xsk_buff_pool *pool)
-{
-#ifdef CONFIG_NET_RX_BUSY_POLL
-	return pool->heads[0].xdp.rxq->napi_id;
-#else
-	return 0;
-#endif
-}
-
 static inline void xsk_pool_dma_unmap(struct xsk_buff_pool *pool,
 				      unsigned long attrs)
 {
@@ -306,11 +297,6 @@ static inline void xsk_pool_fill_cb(struct xsk_buff_pool *pool,
 {
 }
 
-static inline unsigned int xsk_pool_get_napi_id(struct xsk_buff_pool *pool)
-{
-	return 0;
-}
-
 static inline void xsk_pool_dma_unmap(struct xsk_buff_pool *pool,
 				      unsigned long attrs)
 {

net/core/filter.c

@@ -11251,6 +11251,7 @@ BPF_CALL_4(sk_select_reuseport, struct sk_reuseport_kern *, reuse_kern,
 	bool is_sockarray = map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY;
 	struct sock_reuseport *reuse;
 	struct sock *selected_sk;
+	int err;
 
 	selected_sk = map->ops->map_lookup_elem(map, key);
 	if (!selected_sk)
@@ -11258,10 +11259,6 @@ BPF_CALL_4(sk_select_reuseport, struct sk_reuseport_kern *, reuse_kern,
 
 	reuse = rcu_dereference(selected_sk->sk_reuseport_cb);
 	if (!reuse) {
-		/* Lookup in sock_map can return TCP ESTABLISHED sockets. */
-		if (sk_is_refcounted(selected_sk))
-			sock_put(selected_sk);
-
 		/* reuseport_array has only sk with non NULL sk_reuseport_cb.
 		 * The only (!reuse) case here is - the sk has already been
 		 * unhashed (e.g. by close()), so treat it as -ENOENT.
@@ -11269,24 +11266,33 @@ BPF_CALL_4(sk_select_reuseport, struct sk_reuseport_kern *, reuse_kern,
 		 * Other maps (e.g. sock_map) do not provide this guarantee and
 		 * the sk may never be in the reuseport group to begin with.
 		 */
-		return is_sockarray ? -ENOENT : -EINVAL;
+		err = is_sockarray ? -ENOENT : -EINVAL;
+		goto error;
 	}
 
 	if (unlikely(reuse->reuseport_id != reuse_kern->reuseport_id)) {
 		struct sock *sk = reuse_kern->sk;
 
-		if (sk->sk_protocol != selected_sk->sk_protocol)
+		if (sk->sk_protocol != selected_sk->sk_protocol) {
-			return -EPROTOTYPE;
+			err = -EPROTOTYPE;
-		else if (sk->sk_family != selected_sk->sk_family)
+		} else if (sk->sk_family != selected_sk->sk_family) {
-			return -EAFNOSUPPORT;
+			err = -EAFNOSUPPORT;
-
+		} else {
-		/* Catch all. Likely bound to a different sockaddr. */
+			/* Catch all. Likely bound to a different sockaddr. */
-		return -EBADFD;
+			err = -EBADFD;
+		}
+		goto error;
 	}
 
 	reuse_kern->selected_sk = selected_sk;
 
 	return 0;
+error:
+	/* Lookup in sock_map can return TCP ESTABLISHED sockets. */
+	if (sk_is_refcounted(selected_sk))
+		sock_put(selected_sk);
+
+	return err;
 }
 
 static const struct bpf_func_proto sk_select_reuseport_proto = {

net/core/netdev-genl-gen.c

@@ -197,6 +197,16 @@ static const struct genl_multicast_group netdev_nl_mcgrps[] = {
 	[NETDEV_NLGRP_PAGE_POOL] = { "page-pool", },
 };
 
+static void __netdev_nl_sock_priv_init(void *priv)
+{
+	netdev_nl_sock_priv_init(priv);
+}
+
+static void __netdev_nl_sock_priv_destroy(void *priv)
+{
+	netdev_nl_sock_priv_destroy(priv);
+}
+
 struct genl_family netdev_nl_family __ro_after_init = {
 	.name		= NETDEV_FAMILY_NAME,
 	.version	= NETDEV_FAMILY_VERSION,
@@ -208,6 +218,6 @@ struct genl_family netdev_nl_family __ro_after_init = {
 	.mcgrps		= netdev_nl_mcgrps,
 	.n_mcgrps	= ARRAY_SIZE(netdev_nl_mcgrps),
 	.sock_priv_size	= sizeof(struct list_head),
-	.sock_priv_init	= (void *)netdev_nl_sock_priv_init,
+	.sock_priv_init	= __netdev_nl_sock_priv_init,
-	.sock_priv_destroy = (void *)netdev_nl_sock_priv_destroy,
+	.sock_priv_destroy = __netdev_nl_sock_priv_destroy,
 };

net/core/netpoll.c

@@ -627,6 +627,8 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev)
 	const struct net_device_ops *ops;
 	int err;
 
+	skb_queue_head_init(&np->skb_pool);
+
 	if (ndev->priv_flags & IFF_DISABLE_NETPOLL) {
 		np_err(np, "%s doesn't support polling, aborting\n",
 		       ndev->name);
@@ -662,6 +664,9 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev)
 	strscpy(np->dev_name, ndev->name, IFNAMSIZ);
 	npinfo->netpoll = np;
 
+	/* fill up the skb queue */
+	refill_skbs(np);
+
 	/* last thing to do is link it to the net device structure */
 	rcu_assign_pointer(ndev->npinfo, npinfo);
 
@@ -681,8 +686,6 @@ int netpoll_setup(struct netpoll *np)
 	struct in_device *in_dev;
 	int err;
 
-	skb_queue_head_init(&np->skb_pool);
-
 	rtnl_lock();
 	if (np->dev_name[0]) {
 		struct net *net = current->nsproxy->net_ns;
@@ -782,9 +785,6 @@ put_noaddr:
 		}
 	}
 
-	/* fill up the skb queue */
-	refill_skbs(np);
-
 	err = __netpoll_setup(np, ndev);
 	if (err)
 		goto flush;

net/core/pktgen.c

@@ -851,6 +851,9 @@ static ssize_t get_imix_entries(const char __user *buffer,
 		unsigned long weight;
 		unsigned long size;
 
+		if (pkt_dev->n_imix_entries >= MAX_IMIX_ENTRIES)
+			return -E2BIG;
+
 		len = num_arg(&buffer[i], max_digits, &size);
 		if (len < 0)
 			return len;
@@ -880,9 +883,6 @@ static ssize_t get_imix_entries(const char __user *buffer,
 
 		i++;
 		pkt_dev->n_imix_entries++;
-
-		if (pkt_dev->n_imix_entries > MAX_IMIX_ENTRIES)
-			return -E2BIG;
 	} while (c == ' ');
 
 	return i;

net/core/xdp.c

@@ -186,7 +186,6 @@ int __xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq,
 	xdp_rxq_info_init(xdp_rxq);
 	xdp_rxq->dev = dev;
 	xdp_rxq->queue_index = queue_index;
-	xdp_rxq->napi_id = napi_id;
 	xdp_rxq->frag_size = frag_size;
 
 	xdp_rxq->reg_state = REG_STATE_REGISTERED;

net/ipv4/route.c

@@ -2445,6 +2445,7 @@ martian_destination:
 		net_warn_ratelimited("martian destination %pI4 from %pI4, dev %s\n",
 				     &daddr, &saddr, dev->name);
 #endif
+	goto out;
 
 e_nobufs:
 	reason = SKB_DROP_REASON_NOMEM;

net/ipv4/udp.c

@@ -533,7 +533,7 @@ begin:
 	return NULL;
 }
 
-/* In hash4, rehash can happen in connect(), where hash4_cnt keeps unchanged. */
+/* udp_rehash4() only checks hslot4, and hash4_cnt is not processed. */
 static void udp_rehash4(struct udp_table *udptable, struct sock *sk,
 			u16 newhash4)
 {
@@ -582,15 +582,13 @@ void udp_lib_hash4(struct sock *sk, u16 hash)
 	struct net *net = sock_net(sk);
 	struct udp_table *udptable;
 
-	/* Connected udp socket can re-connect to another remote address,
+	/* Connected udp socket can re-connect to another remote address, which
-	 * so rehash4 is needed.
+	 * will be handled by rehash. Thus no need to redo hash4 here.
 	 */
-	udptable = net->ipv4.udp_table;
+	if (udp_hashed4(sk))
-	if (udp_hashed4(sk)) {
-		udp_rehash4(udptable, sk, hash);
 		return;
-	}
 
+	udptable = net->ipv4.udp_table;
 	hslot = udp_hashslot(udptable, net, udp_sk(sk)->udp_port_hash);
 	hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash);
 	hslot4 = udp_hashslot4(udptable, hash);
@@ -2173,14 +2171,14 @@ void udp_lib_rehash(struct sock *sk, u16 newhash, u16 newhash4)
 		struct udp_table *udptable = udp_get_table_prot(sk);
 		struct udp_hslot *hslot, *hslot2, *nhslot2;
 
+		hslot = udp_hashslot(udptable, sock_net(sk),
+				     udp_sk(sk)->udp_port_hash);
 		hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash);
 		nhslot2 = udp_hashslot2(udptable, newhash);
 		udp_sk(sk)->udp_portaddr_hash = newhash;
 
 		if (hslot2 != nhslot2 ||
 		    rcu_access_pointer(sk->sk_reuseport_cb)) {
-			hslot = udp_hashslot(udptable, sock_net(sk),
-					     udp_sk(sk)->udp_port_hash);
 			/* we must lock primary chain too */
 			spin_lock_bh(&hslot->lock);
 			if (rcu_access_pointer(sk->sk_reuseport_cb))
@@ -2199,19 +2197,29 @@ void udp_lib_rehash(struct sock *sk, u16 newhash, u16 newhash4)
 				spin_unlock(&nhslot2->lock);
 			}
 
-			if (udp_hashed4(sk)) {
+			spin_unlock_bh(&hslot->lock);
-				udp_rehash4(udptable, sk, newhash4);
+		}
 
-				if (hslot2 != nhslot2) {
+		/* Now process hash4 if necessary:
-					spin_lock(&hslot2->lock);
+		 * (1) update hslot4;
-					udp_hash4_dec(hslot2);
+		 * (2) update hslot2->hash4_cnt.
-					spin_unlock(&hslot2->lock);
+		 * Note that hslot2/hslot4 should be checked separately, as
+		 * either of them may change with the other unchanged.
+		 */
+		if (udp_hashed4(sk)) {
+			spin_lock_bh(&hslot->lock);
 
-					spin_lock(&nhslot2->lock);
+			udp_rehash4(udptable, sk, newhash4);
-					udp_hash4_inc(nhslot2);
+			if (hslot2 != nhslot2) {
-					spin_unlock(&nhslot2->lock);
+				spin_lock(&hslot2->lock);
-				}
+				udp_hash4_dec(hslot2);
+				spin_unlock(&hslot2->lock);
+
+				spin_lock(&nhslot2->lock);
+				udp_hash4_inc(nhslot2);
+				spin_unlock(&nhslot2->lock);
 			}
+
 			spin_unlock_bh(&hslot->lock);
 		}
 	}

net/mptcp/options.c

@@ -607,7 +607,6 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb,
 	}
 	opts->ext_copy.use_ack = 1;
 	opts->suboptions = OPTION_MPTCP_DSS;
-	WRITE_ONCE(msk->old_wspace, __mptcp_space((struct sock *)msk));
 
 	/* Add kind/length/subtype/flag overhead if mapping is not populated */
 	if (dss_size == 0)
@@ -1288,7 +1287,7 @@ static void mptcp_set_rwin(struct tcp_sock *tp, struct tcphdr *th)
 			}
 			MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_RCVWNDCONFLICT);
 		}
-		return;
+		goto update_wspace;
 	}
 
 	if (rcv_wnd_new != rcv_wnd_old) {
@@ -1313,6 +1312,9 @@ raise_win:
 		th->window = htons(new_win);
 		MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_RCVWNDSHARED);
 	}
+
+update_wspace:
+	WRITE_ONCE(msk->old_wspace, tp->rcv_wnd);
 }
 
 __sum16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum)

net/mptcp/protocol.h

@@ -760,10 +760,15 @@ static inline u64 mptcp_data_avail(const struct mptcp_sock *msk)
 
 static inline bool mptcp_epollin_ready(const struct sock *sk)
 {
+	u64 data_avail = mptcp_data_avail(mptcp_sk(sk));
+
+	if (!data_avail)
+		return false;
+
 	/* mptcp doesn't have to deal with small skbs in the receive queue,
-	 * at it can always coalesce them
+	 * as it can always coalesce them
 	 */
-	return (mptcp_data_avail(mptcp_sk(sk)) >= sk->sk_rcvlowat) ||
+	return (data_avail >= sk->sk_rcvlowat) ||
 	       (mem_cgroup_sockets_enabled && sk->sk_memcg &&
 		mem_cgroup_under_socket_pressure(sk->sk_memcg)) ||
 	       READ_ONCE(tcp_memory_pressure);

net/ncsi/internal.h

@@ -289,6 +289,7 @@ enum {
 	ncsi_dev_state_config_sp	= 0x0301,
 	ncsi_dev_state_config_cis,
 	ncsi_dev_state_config_oem_gma,
+	ncsi_dev_state_config_apply_mac,
 	ncsi_dev_state_config_clear_vids,
 	ncsi_dev_state_config_svf,
 	ncsi_dev_state_config_ev,
@@ -322,6 +323,7 @@ struct ncsi_dev_priv {
 #define NCSI_DEV_RESHUFFLE	4
 #define NCSI_DEV_RESET		8            /* Reset state of NC          */
 	unsigned int        gma_flag;        /* OEM GMA flag               */
+	struct sockaddr     pending_mac;     /* MAC address received from GMA */
 	spinlock_t          lock;            /* Protect the NCSI device    */
 	unsigned int        package_probe_id;/* Current ID during probe    */
 	unsigned int        package_num;     /* Number of packages         */

net/ncsi/ncsi-manage.c

@@ -1038,7 +1038,7 @@ static void ncsi_configure_channel(struct ncsi_dev_priv *ndp)
 			  : ncsi_dev_state_config_clear_vids;
 		break;
 	case ncsi_dev_state_config_oem_gma:
-		nd->state = ncsi_dev_state_config_clear_vids;
+		nd->state = ncsi_dev_state_config_apply_mac;
 
 		nca.package = np->id;
 		nca.channel = nc->id;
@@ -1050,10 +1050,22 @@ static void ncsi_configure_channel(struct ncsi_dev_priv *ndp)
 			nca.type = NCSI_PKT_CMD_OEM;
 			ret = ncsi_gma_handler(&nca, nc->version.mf_id);
 		}
-		if (ret < 0)
+		if (ret < 0) {
+			nd->state = ncsi_dev_state_config_clear_vids;
 			schedule_work(&ndp->work);
+		}
 
 		break;
+	case ncsi_dev_state_config_apply_mac:
+		rtnl_lock();
+		ret = dev_set_mac_address(dev, &ndp->pending_mac, NULL);
+		rtnl_unlock();
+		if (ret < 0)
+			netdev_warn(dev, "NCSI: 'Writing MAC address to device failed\n");
+
+		nd->state = ncsi_dev_state_config_clear_vids;
+
+		fallthrough;
 	case ncsi_dev_state_config_clear_vids:
 	case ncsi_dev_state_config_svf:
 	case ncsi_dev_state_config_ev:

net/ncsi/ncsi-rsp.c

@@ -628,16 +628,14 @@ static int ncsi_rsp_handler_snfc(struct ncsi_request *nr)
 static int ncsi_rsp_handler_oem_gma(struct ncsi_request *nr, int mfr_id)
 {
 	struct ncsi_dev_priv *ndp = nr->ndp;
+	struct sockaddr *saddr = &ndp->pending_mac;
 	struct net_device *ndev = ndp->ndev.dev;
 	struct ncsi_rsp_oem_pkt *rsp;
-	struct sockaddr saddr;
 	u32 mac_addr_off = 0;
-	int ret = 0;
 
 	/* Get the response header */
 	rsp = (struct ncsi_rsp_oem_pkt *)skb_network_header(nr->rsp);
 
-	saddr.sa_family = ndev->type;
 	ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 	if (mfr_id == NCSI_OEM_MFR_BCM_ID)
 		mac_addr_off = BCM_MAC_ADDR_OFFSET;
@@ -646,22 +644,17 @@ static int ncsi_rsp_handler_oem_gma(struct ncsi_request *nr, int mfr_id)
 	else if (mfr_id == NCSI_OEM_MFR_INTEL_ID)
 		mac_addr_off = INTEL_MAC_ADDR_OFFSET;
 
-	memcpy(saddr.sa_data, &rsp->data[mac_addr_off], ETH_ALEN);
+	saddr->sa_family = ndev->type;
+	memcpy(saddr->sa_data, &rsp->data[mac_addr_off], ETH_ALEN);
 	if (mfr_id == NCSI_OEM_MFR_BCM_ID || mfr_id == NCSI_OEM_MFR_INTEL_ID)
-		eth_addr_inc((u8 *)saddr.sa_data);
+		eth_addr_inc((u8 *)saddr->sa_data);
-	if (!is_valid_ether_addr((const u8 *)saddr.sa_data))
+	if (!is_valid_ether_addr((const u8 *)saddr->sa_data))
 		return -ENXIO;
 
 	/* Set the flag for GMA command which should only be called once */
 	ndp->gma_flag = 1;
 
-	rtnl_lock();
+	return 0;
-	ret = dev_set_mac_address(ndev, &saddr, NULL);
-	rtnl_unlock();
-	if (ret < 0)
-		netdev_warn(ndev, "NCSI: 'Writing mac address to device failed\n");
-
-	return ret;
 }
 
 /* Response handler for Mellanox card */

net/openvswitch/actions.c

@@ -934,7 +934,9 @@ static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port,
 {
 	struct vport *vport = ovs_vport_rcu(dp, out_port);
 
-	if (likely(vport && netif_carrier_ok(vport->dev))) {
+	if (likely(vport &&
+		   netif_running(vport->dev) &&
+		   netif_carrier_ok(vport->dev))) {
 		u16 mru = OVS_CB(skb)->mru;
 		u32 cutlen = OVS_CB(skb)->cutlen;
 

net/vmw_vsock/af_vsock.c

@@ -491,6 +491,15 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
 		 */
 		vsk->transport->release(vsk);
 		vsock_deassign_transport(vsk);
+
+		/* transport's release() and destruct() can touch some socket
+		 * state, since we are reassigning the socket to a new transport
+		 * during vsock_connect(), let's reset these fields to have a
+		 * clean state.
+		 */
+		sock_reset_flag(sk, SOCK_DONE);
+		sk->sk_state = TCP_CLOSE;
+		vsk->peer_shutdown = 0;
 	}
 
 	/* We increase the module refcnt to prevent the transport unloading
@@ -870,6 +879,9 @@ EXPORT_SYMBOL_GPL(vsock_create_connected);
 
 s64 vsock_stream_has_data(struct vsock_sock *vsk)
 {
+	if (WARN_ON(!vsk->transport))
+		return 0;
+
 	return vsk->transport->stream_has_data(vsk);
 }
 EXPORT_SYMBOL_GPL(vsock_stream_has_data);
@@ -878,6 +890,9 @@ s64 vsock_connectible_has_data(struct vsock_sock *vsk)
 {
 	struct sock *sk = sk_vsock(vsk);
 
+	if (WARN_ON(!vsk->transport))
+		return 0;
+
 	if (sk->sk_type == SOCK_SEQPACKET)
 		return vsk->transport->seqpacket_has_data(vsk);
 	else
@@ -887,6 +902,9 @@ EXPORT_SYMBOL_GPL(vsock_connectible_has_data);
 
 s64 vsock_stream_has_space(struct vsock_sock *vsk)
 {
+	if (WARN_ON(!vsk->transport))
+		return 0;
+
 	return vsk->transport->stream_has_space(vsk);
 }
 EXPORT_SYMBOL_GPL(vsock_stream_has_space);

net/vmw_vsock/virtio_transport_common.c

@@ -26,6 +26,9 @@
 /* Threshold for detecting small packets to copy */
 #define GOOD_COPY_LEN  128
 
+static void virtio_transport_cancel_close_work(struct vsock_sock *vsk,
+					       bool cancel_timeout);
+
 static const struct virtio_transport *
 virtio_transport_get_ops(struct vsock_sock *vsk)
 {
@@ -1109,6 +1112,8 @@ void virtio_transport_destruct(struct vsock_sock *vsk)
 {
 	struct virtio_vsock_sock *vvs = vsk->trans;
 
+	virtio_transport_cancel_close_work(vsk, true);
+
 	kfree(vvs);
 	vsk->trans = NULL;
 }
@@ -1204,6 +1209,22 @@ static void virtio_transport_wait_close(struct sock *sk, long timeout)
 	}
 }
 
+static void virtio_transport_cancel_close_work(struct vsock_sock *vsk,
+					       bool cancel_timeout)
+{
+	struct sock *sk = sk_vsock(vsk);
+
+	if (vsk->close_work_scheduled &&
+	    (!cancel_timeout || cancel_delayed_work(&vsk->close_work))) {
+		vsk->close_work_scheduled = false;
+
+		virtio_transport_remove_sock(vsk);
+
+		/* Release refcnt obtained when we scheduled the timeout */
+		sock_put(sk);
+	}
+}
+
 static void virtio_transport_do_close(struct vsock_sock *vsk,
 				      bool cancel_timeout)
 {
@@ -1215,15 +1236,7 @@ static void virtio_transport_do_close(struct vsock_sock *vsk,
 		sk->sk_state = TCP_CLOSING;
 	sk->sk_state_change(sk);
 
-	if (vsk->close_work_scheduled &&
+	virtio_transport_cancel_close_work(vsk, cancel_timeout);
-	    (!cancel_timeout || cancel_delayed_work(&vsk->close_work))) {
-		vsk->close_work_scheduled = false;
-
-		virtio_transport_remove_sock(vsk);
-
-		/* Release refcnt obtained when we scheduled the timeout */
-		sock_put(sk);
-	}
 }
 
 static void virtio_transport_close_timeout(struct work_struct *work)
@@ -1628,8 +1641,11 @@ void virtio_transport_recv_pkt(struct virtio_transport *t,
 
 	lock_sock(sk);
 
-	/* Check if sk has been closed before lock_sock */
+	/* Check if sk has been closed or assigned to another transport before
-	if (sock_flag(sk, SOCK_DONE)) {
+	 * lock_sock (note: listener sockets are not assigned to any transport)
+	 */
+	if (sock_flag(sk, SOCK_DONE) ||
+	    (sk->sk_state != TCP_LISTEN && vsk->transport != &t->transport)) {
 		(void)virtio_transport_reset_no_sock(t, skb);
 		release_sock(sk);
 		sock_put(sk);

net/vmw_vsock/vsock_bpf.c

@@ -77,6 +77,7 @@ static int vsock_bpf_recvmsg(struct sock *sk, struct msghdr *msg,
 			     size_t len, int flags, int *addr_len)
 {
 	struct sk_psock *psock;
+	struct vsock_sock *vsk;
 	int copied;
 
 	psock = sk_psock_get(sk);
@@ -84,6 +85,13 @@ static int vsock_bpf_recvmsg(struct sock *sk, struct msghdr *msg,
 		return __vsock_recvmsg(sk, msg, len, flags);
 
 	lock_sock(sk);
+	vsk = vsock_sk(sk);
+
+	if (!vsk->transport) {
+		copied = -ENODEV;
+		goto out;
+	}
+
 	if (vsock_has_data(sk, psock) && sk_psock_queue_empty(psock)) {
 		release_sock(sk);
 		sk_psock_put(sk, psock);
@@ -108,6 +116,7 @@ static int vsock_bpf_recvmsg(struct sock *sk, struct msghdr *msg,
 		copied = sk_msg_recvmsg(sk, psock, msg, len, flags);
 	}
 
+out:
 	release_sock(sk);
 	sk_psock_put(sk, psock);
 

net/xdp/xsk.c

@@ -322,7 +322,6 @@ static int xsk_rcv_check(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
 		return -ENOSPC;
 	}
 
-	sk_mark_napi_id_once_xdp(&xs->sk, xdp);
 	return 0;
 }
 
@@ -908,11 +907,8 @@ static int __xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len
 	if (unlikely(!xs->tx))
 		return -ENOBUFS;
 
-	if (sk_can_busy_loop(sk)) {
+	if (sk_can_busy_loop(sk))
-		if (xs->zc)
-			__sk_mark_napi_id_once(sk, xsk_pool_get_napi_id(xs->pool));
 		sk_busy_loop(sk, 1); /* only support non-blocking sockets */
-	}
 
 	if (xs->zc && xsk_no_wakeup(sk))
 		return 0;
@@ -1298,6 +1294,14 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 	xs->queue_id = qid;
 	xp_add_xsk(xs->pool, xs);
 
+	if (xs->zc && qid < dev->real_num_rx_queues) {
+		struct netdev_rx_queue *rxq;
+
+		rxq = __netif_get_rx_queue(dev, qid);
+		if (rxq->napi)
+			__sk_mark_napi_id_once(sk, rxq->napi->napi_id);
+	}
+
 out_unlock:
 	if (err) {
 		dev_put(dev);

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

@@ -2384,6 +2384,17 @@ def print_kernel_family_struct_src(family, cw):
     if not kernel_can_gen_family_struct(family):
         return
 
+    if 'sock-priv' in family.kernel_family:
+        # Generate "trampolines" to make CFI happy
+        cw.write_func("static void", f"__{family.c_name}_nl_sock_priv_init",
+                      [f"{family.c_name}_nl_sock_priv_init(priv);"],
+                      ["void *priv"])
+        cw.nl()
+        cw.write_func("static void", f"__{family.c_name}_nl_sock_priv_destroy",
+                      [f"{family.c_name}_nl_sock_priv_destroy(priv);"],
+                      ["void *priv"])
+        cw.nl()
+
     cw.block_start(f"struct genl_family {family.ident_name}_nl_family __ro_after_init =")
     cw.p('.name\t\t= ' + family.fam_key + ',')
     cw.p('.version\t= ' + family.ver_key + ',')
@@ -2401,9 +2412,8 @@ def print_kernel_family_struct_src(family, cw):
         cw.p(f'.n_mcgrps\t= ARRAY_SIZE({family.c_name}_nl_mcgrps),')
     if 'sock-priv' in family.kernel_family:
         cw.p(f'.sock_priv_size\t= sizeof({family.kernel_family["sock-priv"]}),')
-        # Force cast here, actual helpers take pointer to the real type.
+        cw.p(f'.sock_priv_init\t= __{family.c_name}_nl_sock_priv_init,')
-        cw.p(f'.sock_priv_init\t= (void *){family.c_name}_nl_sock_priv_init,')
+        cw.p(f'.sock_priv_destroy = __{family.c_name}_nl_sock_priv_destroy,')
-        cw.p(f'.sock_priv_destroy = (void *){family.c_name}_nl_sock_priv_destroy,')
     cw.block_end(';')
 
 

tools/testing/selftests/drivers/net/netdevsim/tc-mq-visibility.sh

@@ -58,9 +58,12 @@ for root in mq mqprio; do
     ethtool -L $NDEV combined 4
     n_child_assert 4 "One real queue, rest default"
 
-    # Graft some
+    # Remove real one
-    tcq replace parent 100:1 handle 204:
+    tcq del parent 100:4 handle 204:
-    n_child_assert 3 "Grafted"
+
+    # Replace default with pfifo
+    tcq replace parent 100:1 handle 205: pfifo limit 1000
+    n_child_assert 3 "Deleting real one, replacing default one with pfifo"
 
     ethtool -L $NDEV combined 1
     n_child_assert 1 "Grafted, one"

tools/testing/selftests/net/mptcp/mptcp_connect.c

@@ -25,6 +25,8 @@
 #include <sys/types.h>
 #include <sys/mman.h>
 
+#include <arpa/inet.h>
+
 #include <netdb.h>
 #include <netinet/in.h>
 
@@ -1211,23 +1213,42 @@ static void parse_setsock_options(const char *name)
 	exit(1);
 }
 
-void xdisconnect(int fd, int addrlen)
+void xdisconnect(int fd)
 {
-	struct sockaddr_storage empty;
+	socklen_t addrlen = sizeof(struct sockaddr_storage);
+	struct sockaddr_storage addr, empty;
 	int msec_sleep = 10;
-	int queued = 1;
+	void *raw_addr;
-	int i;
+	int i, cmdlen;
+	char cmd[128];
+
+	/* get the local address and convert it to string */
+	if (getsockname(fd, (struct sockaddr *)&addr, &addrlen) < 0)
+		xerror("getsockname");
+
+	if (addr.ss_family == AF_INET)
+		raw_addr = &(((struct sockaddr_in *)&addr)->sin_addr);
+	else if (addr.ss_family == AF_INET6)
+		raw_addr = &(((struct sockaddr_in6 *)&addr)->sin6_addr);
+	else
+		xerror("bad family");
+
+	strcpy(cmd, "ss -M | grep -q ");
+	cmdlen = strlen(cmd);
+	if (!inet_ntop(addr.ss_family, raw_addr, &cmd[cmdlen],
+		       sizeof(cmd) - cmdlen))
+		xerror("inet_ntop");
 
 	shutdown(fd, SHUT_WR);
 
-	/* while until the pending data is completely flushed, the later
+	/*
+	 * wait until the pending data is completely flushed and all
+	 * the MPTCP sockets reached the closed status.
 	 * disconnect will bypass/ignore/drop any pending data.
 	 */
 	for (i = 0; ; i += msec_sleep) {
-		if (ioctl(fd, SIOCOUTQ, &queued) < 0)
+		/* closed socket are not listed by 'ss' */
-			xerror("can't query out socket queue: %d", errno);
+		if (system(cmd) != 0)
-
-		if (!queued)
 			break;
 
 		if (i > poll_timeout)
@@ -1281,9 +1302,9 @@ again:
 		return ret;
 
 	if (cfg_truncate > 0) {
-		xdisconnect(fd, peer->ai_addrlen);
+		xdisconnect(fd);
 	} else if (--cfg_repeat > 0) {
-		xdisconnect(fd, peer->ai_addrlen);
+		xdisconnect(fd);
 
 		/* the socket could be unblocking at this point, we need the
 		 * connect to be blocking