Merge tag 'net-6.11-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni:
"Including fixes from wireless, bleutooth, BPF and netfilter.

Current release - regressions:

- core: drop bad gso csum_start and offset in virtio_net_hdr

- wifi: mt76: fix null pointer access in mt792x_mac_link_bss_remove

- eth: tun: add missing bpf_net_ctx_clear() in do_xdp_generic()

- phy: aquantia: only poll GLOBAL_CFG regs on aqr113, aqr113c and
aqr115c

Current release - new code bugs:

- smc: prevent UAF in inet_create()

- bluetooth: btmtk: fix kernel crash when entering btmtk_usb_suspend

- eth: bnxt: reject unsupported hash functions

Previous releases - regressions:

- sched: act_ct: take care of padding in struct zones_ht_key

- netfilter: fix null-ptr-deref in iptable_nat_table_init().

- tcp: adjust clamping window for applications specifying SO_RCVBUF

Previous releases - always broken:

- ethtool: rss: small fixes to spec and GET

- mptcp:
- fix signal endpoint re-add
- pm: fix backup support in signal endpoints

- wifi: ath12k: fix soft lockup on suspend

- eth: bnxt_en: fix RSS logic in __bnxt_reserve_rings()

- eth: ice: fix AF_XDP ZC timeout and concurrency issues

- eth: mlx5:
- fix missing lock on sync reset reload
- fix error handling in irq_pool_request_irq"

* tag 'net-6.11-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (76 commits)
mptcp: fix duplicate data handling
mptcp: fix bad RCVPRUNED mib accounting
ipv6: fix ndisc_is_useropt() handling for PIO
igc: Fix double reset adapter triggered from a single taprio cmd
net: MAINTAINERS: Demote Qualcomm IPA to "maintained"
net: wan: fsl_qmc_hdlc: Discard received CRC
net: wan: fsl_qmc_hdlc: Convert carrier_lock spinlock to a mutex
net/mlx5e: Add a check for the return value from mlx5_port_set_eth_ptys
net/mlx5e: Fix CT entry update leaks of modify header context
net/mlx5e: Require mlx5 tc classifier action support for IPsec prio capability
net/mlx5: Fix missing lock on sync reset reload
net/mlx5: Lag, don't use the hardcoded value of the first port
net/mlx5: DR, Fix 'stack guard page was hit' error in dr_rule
net/mlx5: Fix error handling in irq_pool_request_irq
net/mlx5: Always drain health in shutdown callback
net: Add skbuff.h to MAINTAINERS
r8169: don't increment tx_dropped in case of NETDEV_TX_BUSY
netfilter: iptables: Fix potential null-ptr-deref in ip6table_nat_table_init().
netfilter: iptables: Fix null-ptr-deref in iptable_nat_table_init().
net: drop bad gso csum_start and offset in virtio_net_hdr
...

Documentation/netlink/specs/ethtool.yaml

···
         request:
           attributes:
             - header
+            - context
         reply:
           attributes:
             - header
···
             - indir
             - hkey
             - input_xfrm
-      dump: *rss-get-op
     -
       name: plca-get-cfg
       doc: Get PLCA params.

Documentation/networking/ethtool-netlink.rst

···
 
 =====================================  ======  ==========================
   ``ETHTOOL_A_RSS_HEADER``             nested  reply header
+  ``ETHTOOL_A_RSS_CONTEXT``            u32     context number
   ``ETHTOOL_A_RSS_HFUNC``              u32     RSS hash func
   ``ETHTOOL_A_RSS_INDIR``              binary  Indir table bytes
   ``ETHTOOL_A_RSS_HKEY``               binary  Hash key bytes

MAINTAINERS

···
 F:	include/linux/indirect_call_wrapper.h
 F:	include/linux/net.h
 F:	include/linux/netdevice.h
+F:	include/linux/skbuff.h
 F:	include/net/
 F:	include/uapi/linux/in.h
 F:	include/uapi/linux/net.h
···
 QCOM IPA DRIVER
 M:	Alex Elder <[e-mail]>
 L:	[e-mail]
-S:	Supported
+S:	Maintained
 F:	drivers/net/ipa/
 
 QEMU MACHINE EMULATOR AND VIRTUALIZER SUPPORT

drivers/bluetooth/Kconfig

···
 config BT_MTKSDIO
 	tristate "MediaTek HCI SDIO driver"
 	depends on MMC
+	depends on USB || !BT_HCIBTUSB_MTK
 	select BT_MTK
 	help
 	  MediaTek Bluetooth HCI SDIO driver.
···
 config BT_MTKUART
 	tristate "MediaTek HCI UART driver"
 	depends on SERIAL_DEV_BUS
+	depends on USB || !BT_HCIBTUSB_MTK
 	select BT_MTK
 	help
 	  MediaTek Bluetooth HCI UART driver.

drivers/bluetooth/btintel.c

···
 		btintel_set_dsm_reset_method(hdev, &ver_tlv);
 
 		err = btintel_bootloader_setup_tlv(hdev, &ver_tlv);
+		if (err)
+			goto exit_error;
+
 		btintel_register_devcoredump_support(hdev);
 		btintel_print_fseq_info(hdev);
 		break;

drivers/bluetooth/btmtk.c

···
 }
 EXPORT_SYMBOL_GPL(btmtk_process_coredump);
 
+#if IS_ENABLED(CONFIG_BT_HCIBTUSB_MTK)
 static void btmtk_usb_wmt_recv(struct urb *urb)
 {
 	struct hci_dev *hdev = urb->context;
···
 	struct btmtk_data *btmtk_data = hci_get_priv(hdev);
 
 	/* Stop urb anchor for iso data transmission */
-	usb_kill_anchored_urbs(&btmtk_data->isopkt_anchor);
+	if (test_bit(BTMTK_ISOPKT_RUNNING, &btmtk_data->flags))
+		usb_kill_anchored_urbs(&btmtk_data->isopkt_anchor);
 
 	return 0;
 }
···
 	return 0;
 }
 EXPORT_SYMBOL_GPL(btmtk_usb_shutdown);
+#endif
 
 MODULE_AUTHOR("Sean Wang <[e-mail]>");
 MODULE_AUTHOR("Mark Chen <[e-mail]>");

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

···
 static int __bnxt_reserve_rings(struct bnxt *bp)
 {
 	struct bnxt_hw_rings hwr = {0};
+	int rx_rings, old_rx_rings, rc;
 	int cp = bp->cp_nr_rings;
-	int rx_rings, rc;
 	int ulp_msix = 0;
 	bool sh = false;
 	int tx_cp;
···
 	hwr.grp = bp->rx_nr_rings;
 	hwr.rss_ctx = bnxt_get_total_rss_ctxs(bp, &hwr);
 	hwr.stat = bnxt_get_func_stat_ctxs(bp);
+	old_rx_rings = bp->hw_resc.resv_rx_rings;
 
 	rc = bnxt_hwrm_reserve_rings(bp, &hwr);
 	if (rc)
···
 	if (!bnxt_rings_ok(bp, &hwr))
 		return -ENOMEM;
 
-	if (!netif_is_rxfh_configured(bp->dev))
+	if (old_rx_rings != bp->hw_resc.resv_rx_rings &&
+	    !netif_is_rxfh_configured(bp->dev))
 		bnxt_set_dflt_rss_indir_tbl(bp, NULL);
 
 	if (!bnxt_ulp_registered(bp->edev) && BNXT_NEW_RM(bp)) {

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

···
 }
 
 static int bnxt_rxfh_context_check(struct bnxt *bp,
+				   const struct ethtool_rxfh_param *rxfh,
 				   struct netlink_ext_ack *extack)
 {
+	if (rxfh->hfunc && rxfh->hfunc != ETH_RSS_HASH_TOP) {
+		NL_SET_ERR_MSG_MOD(extack, "RSS hash function not supported");
+		return -EOPNOTSUPP;
+	}
+
 	if (!BNXT_SUPPORTS_MULTI_RSS_CTX(bp)) {
 		NL_SET_ERR_MSG_MOD(extack, "RSS contexts not supported");
 		return -EOPNOTSUPP;
···
 	struct bnxt_vnic_info *vnic;
 	int rc;
 
-	rc = bnxt_rxfh_context_check(bp, extack);
+	rc = bnxt_rxfh_context_check(bp, rxfh, extack);
 	if (rc)
 		return rc;
 
···
 	if (rc)
 		goto out;
 
+	/* Populate defaults in the context */
 	bnxt_set_dflt_rss_indir_tbl(bp, ctx);
+	ctx->hfunc = ETH_RSS_HASH_TOP;
 	memcpy(vnic->rss_hash_key, bp->rss_hash_key, HW_HASH_KEY_SIZE);
+	memcpy(ethtool_rxfh_context_key(ctx),
+	       bp->rss_hash_key, HW_HASH_KEY_SIZE);
 
 	rc = bnxt_hwrm_vnic_alloc(bp, vnic, 0, bp->rx_nr_rings);
 	if (rc) {
···
 	struct bnxt_rss_ctx *rss_ctx;
 	int rc;
 
-	rc = bnxt_rxfh_context_check(bp, extack);
+	rc = bnxt_rxfh_context_check(bp, rxfh, extack);
 	if (rc)
 		return rc;
 

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

···
 }
 
 /**
- * ice_xsk_pool - get XSK buffer pool bound to a ring
+ * ice_rx_xsk_pool - assign XSK buff pool to Rx ring
  * @ring: Rx ring to use
  *
- * Returns a pointer to xsk_buff_pool structure if there is a buffer pool
- * present, NULL otherwise.
+ * Sets XSK buff pool pointer on Rx ring.
  */
-static inline struct xsk_buff_pool *ice_xsk_pool(struct ice_rx_ring *ring)
+static inline void ice_rx_xsk_pool(struct ice_rx_ring *ring)
 {
 	struct ice_vsi *vsi = ring->vsi;
 	u16 qid = ring->q_index;
 
-	return ice_get_xp_from_qid(vsi, qid);
+	WRITE_ONCE(ring->xsk_pool, ice_get_xp_from_qid(vsi, qid));
 }
 
 /**
···
 	if (!ring)
 		return;
 
-	ring->xsk_pool = ice_get_xp_from_qid(vsi, qid);
+	WRITE_ONCE(ring->xsk_pool, ice_get_xp_from_qid(vsi, qid));
 }
 
 /**

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

···
 				return err;
 		}
 
-		ring->xsk_pool = ice_xsk_pool(ring);
+		ice_rx_xsk_pool(ring);
 		if (ring->xsk_pool) {
 			xdp_rxq_info_unreg(&ring->xdp_rxq);
 
···
 			return 0;
 		}
 
-		ok = ice_alloc_rx_bufs_zc(ring, num_bufs);
+		ok = ice_alloc_rx_bufs_zc(ring, ring->xsk_pool, num_bufs);
 		if (!ok) {
 			u16 pf_q = ring->vsi->rxq_map[ring->q_index];
 

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

···
 	ice_for_each_rxq(vsi, i) {
 		struct ice_rx_ring *rx_ring = vsi->rx_rings[i];
 
-		if (rx_ring->xsk_pool)
+		if (READ_ONCE(rx_ring->xsk_pool))
 			napi_schedule(&rx_ring->q_vector->napi);
 	}
 }

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

···
 	if (rx_ring->vsi->type == ICE_VSI_PF)
 		if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq))
 			xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
-	rx_ring->xdp_prog = NULL;
+	WRITE_ONCE(rx_ring->xdp_prog, NULL);
 	if (rx_ring->xsk_pool) {
 		kfree(rx_ring->xdp_buf);
 		rx_ring->xdp_buf = NULL;
···
 	 * budget and be more aggressive about cleaning up the Tx descriptors.
 	 */
 	ice_for_each_tx_ring(tx_ring, q_vector->tx) {
+		struct xsk_buff_pool *xsk_pool = READ_ONCE(tx_ring->xsk_pool);
 		bool wd;
 
-		if (tx_ring->xsk_pool)
-			wd = ice_xmit_zc(tx_ring);
+		if (xsk_pool)
+			wd = ice_xmit_zc(tx_ring, xsk_pool);
 		else if (ice_ring_is_xdp(tx_ring))
 			wd = true;
 		else
···
 		budget_per_ring = budget;
 
 	ice_for_each_rx_ring(rx_ring, q_vector->rx) {
+		struct xsk_buff_pool *xsk_pool = READ_ONCE(rx_ring->xsk_pool);
 		int cleaned;
 
 		/* A dedicated path for zero-copy allows making a single
···
 		 * ice_clean_rx_irq function and makes the codebase cleaner.
 		 */
 		cleaned = rx_ring->xsk_pool ?
-			  ice_clean_rx_irq_zc(rx_ring, budget_per_ring) :
+			  ice_clean_rx_irq_zc(rx_ring, xsk_pool, budget_per_ring) :
 			  ice_clean_rx_irq(rx_ring, budget_per_ring);
 		work_done += cleaned;
 		/* if we clean as many as budgeted, we must not be done */

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

···
 static void ice_qp_clean_rings(struct ice_vsi *vsi, u16 q_idx)
 {
 	ice_clean_tx_ring(vsi->tx_rings[q_idx]);
-	if (ice_is_xdp_ena_vsi(vsi)) {
-		synchronize_rcu();
+	if (ice_is_xdp_ena_vsi(vsi))
 		ice_clean_tx_ring(vsi->xdp_rings[q_idx]);
-	}
 	ice_clean_rx_ring(vsi->rx_rings[q_idx]);
 }
 
···
  * ice_qvec_cfg_msix - Enable IRQ for given queue vector
  * @vsi: the VSI that contains queue vector
  * @q_vector: queue vector
+ * @qid: queue index
  */
 static void
-ice_qvec_cfg_msix(struct ice_vsi *vsi, struct ice_q_vector *q_vector)
+ice_qvec_cfg_msix(struct ice_vsi *vsi, struct ice_q_vector *q_vector, u16 qid)
 {
 	u16 reg_idx = q_vector->reg_idx;
 	struct ice_pf *pf = vsi->back;
 	struct ice_hw *hw = &pf->hw;
-	struct ice_tx_ring *tx_ring;
-	struct ice_rx_ring *rx_ring;
+	int q, _qid = qid;
 
 	ice_cfg_itr(hw, q_vector);
 
-	ice_for_each_tx_ring(tx_ring, q_vector->tx)
-		ice_cfg_txq_interrupt(vsi, tx_ring->reg_idx, reg_idx,
-				      q_vector->tx.itr_idx);
+	for (q = 0; q < q_vector->num_ring_tx; q++) {
+		ice_cfg_txq_interrupt(vsi, _qid, reg_idx, q_vector->tx.itr_idx);
+		_qid++;
+	}
 
-	ice_for_each_rx_ring(rx_ring, q_vector->rx)
-		ice_cfg_rxq_interrupt(vsi, rx_ring->reg_idx, reg_idx,
-				      q_vector->rx.itr_idx);
+	_qid = qid;
+
+	for (q = 0; q < q_vector->num_ring_rx; q++) {
+		ice_cfg_rxq_interrupt(vsi, _qid, reg_idx, q_vector->rx.itr_idx);
+		_qid++;
+	}
 
 	ice_flush(hw);
 }
···
 	struct ice_tx_ring *tx_ring;
 	struct ice_rx_ring *rx_ring;
 	int timeout = 50;
+	int fail = 0;
 	int err;
 
 	if (q_idx >= vsi->num_rxq || q_idx >= vsi->num_txq)
···
 		usleep_range(1000, 2000);
 	}
 
+	synchronize_net();
+	netif_carrier_off(vsi->netdev);
+	netif_tx_stop_queue(netdev_get_tx_queue(vsi->netdev, q_idx));
+
 	ice_qvec_dis_irq(vsi, rx_ring, q_vector);
 	ice_qvec_toggle_napi(vsi, q_vector, false);
 
-	netif_tx_stop_queue(netdev_get_tx_queue(vsi->netdev, q_idx));
-
 	ice_fill_txq_meta(vsi, tx_ring, &txq_meta);
 	err = ice_vsi_stop_tx_ring(vsi, ICE_NO_RESET, 0, tx_ring, &txq_meta);
-	if (err)
-		return err;
+	if (!fail)
+		fail = err;
 	if (ice_is_xdp_ena_vsi(vsi)) {
 		struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_idx];
 
···
 		ice_fill_txq_meta(vsi, xdp_ring, &txq_meta);
 		err = ice_vsi_stop_tx_ring(vsi, ICE_NO_RESET, 0, xdp_ring,
 					   &txq_meta);
-		if (err)
-			return err;
+		if (!fail)
+			fail = err;
 	}
-	err = ice_vsi_ctrl_one_rx_ring(vsi, false, q_idx, true);
-	if (err)
-		return err;
 
+	ice_vsi_ctrl_one_rx_ring(vsi, false, q_idx, false);
 	ice_qp_clean_rings(vsi, q_idx);
 	ice_qp_reset_stats(vsi, q_idx);
 
-	return 0;
+	return fail;
 }
 
 /**
···
 static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx)
 {
 	struct ice_q_vector *q_vector;
+	int fail = 0;
+	bool link_up;
 	int err;
 
 	err = ice_vsi_cfg_single_txq(vsi, vsi->tx_rings, q_idx);
-	if (err)
-		return err;
+	if (!fail)
+		fail = err;
 
 	if (ice_is_xdp_ena_vsi(vsi)) {
 		struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_idx];
 
 		err = ice_vsi_cfg_single_txq(vsi, vsi->xdp_rings, q_idx);
-		if (err)
-			return err;
+		if (!fail)
+			fail = err;
 		ice_set_ring_xdp(xdp_ring);
 		ice_tx_xsk_pool(vsi, q_idx);
 	}
 
 	err = ice_vsi_cfg_single_rxq(vsi, q_idx);
-	if (err)
-		return err;
+	if (!fail)
+		fail = err;
 
 	q_vector = vsi->rx_rings[q_idx]->q_vector;
-	ice_qvec_cfg_msix(vsi, q_vector);
+	ice_qvec_cfg_msix(vsi, q_vector, q_idx);
 
 	err = ice_vsi_ctrl_one_rx_ring(vsi, true, q_idx, true);
-	if (err)
-		return err;
+	if (!fail)
+		fail = err;
 
 	ice_qvec_toggle_napi(vsi, q_vector, true);
 	ice_qvec_ena_irq(vsi, q_vector);
 
-	netif_tx_start_queue(netdev_get_tx_queue(vsi->netdev, q_idx));
+	/* make sure NAPI sees updated ice_{t,x}_ring::xsk_pool */
+	synchronize_net();
+	ice_get_link_status(vsi->port_info, &link_up);
+	if (link_up) {
+		netif_tx_start_queue(netdev_get_tx_queue(vsi->netdev, q_idx));
+		netif_carrier_on(vsi->netdev);
+	}
 	clear_bit(ICE_CFG_BUSY, vsi->state);
 
-	return 0;
+	return fail;
 }
 
 /**
···
 /**
  * __ice_alloc_rx_bufs_zc - allocate a number of Rx buffers
  * @rx_ring: Rx ring
+ * @xsk_pool: XSK buffer pool to pick buffers to be filled by HW
  * @count: The number of buffers to allocate
  *
  * Place the @count of descriptors onto Rx ring. Handle the ring wrap
···
  *
  * Returns true if all allocations were successful, false if any fail.
  */
-static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
+static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring,
+				   struct xsk_buff_pool *xsk_pool, u16 count)
 {
 	u32 nb_buffs_extra = 0, nb_buffs = 0;
 	union ice_32b_rx_flex_desc *rx_desc;
···
 	xdp = ice_xdp_buf(rx_ring, ntu);
 
 	if (ntu + count >= rx_ring->count) {
-		nb_buffs_extra = ice_fill_rx_descs(rx_ring->xsk_pool, xdp,
-						   rx_desc,
+		nb_buffs_extra = ice_fill_rx_descs(xsk_pool, xdp, rx_desc,
 						   rx_ring->count - ntu);
 		if (nb_buffs_extra != rx_ring->count - ntu) {
 			ntu += nb_buffs_extra;
···
 		ice_release_rx_desc(rx_ring, 0);
 	}
 
-	nb_buffs = ice_fill_rx_descs(rx_ring->xsk_pool, xdp, rx_desc, count);
+	nb_buffs = ice_fill_rx_descs(xsk_pool, xdp, rx_desc, count);
 
 	ntu += nb_buffs;
 	if (ntu == rx_ring->count)
···
 /**
  * ice_alloc_rx_bufs_zc - allocate a number of Rx buffers
  * @rx_ring: Rx ring
+ * @xsk_pool: XSK buffer pool to pick buffers to be filled by HW
  * @count: The number of buffers to allocate
  *
  * Wrapper for internal allocation routine; figure out how many tail
···
  *
  * Returns true if all calls to internal alloc routine succeeded
  */
-bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
+bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring,
+			  struct xsk_buff_pool *xsk_pool, u16 count)
 {
 	u16 rx_thresh = ICE_RING_QUARTER(rx_ring);
 	u16 leftover, i, tail_bumps;
···
 	leftover = count - (tail_bumps * rx_thresh);
 
 	for (i = 0; i < tail_bumps; i++)
-		if (!__ice_alloc_rx_bufs_zc(rx_ring, rx_thresh))
+		if (!__ice_alloc_rx_bufs_zc(rx_ring, xsk_pool, rx_thresh))
 			return false;
-	return __ice_alloc_rx_bufs_zc(rx_ring, leftover);
+	return __ice_alloc_rx_bufs_zc(rx_ring, xsk_pool, leftover);
 }
 
 /**
···
 /**
  * ice_clean_xdp_irq_zc - produce AF_XDP descriptors to CQ
  * @xdp_ring: XDP Tx ring
+ * @xsk_pool: AF_XDP buffer pool pointer
  */
-static u32 ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring)
+static u32 ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring,
+				struct xsk_buff_pool *xsk_pool)
 {
 	u16 ntc = xdp_ring->next_to_clean;
 	struct ice_tx_desc *tx_desc;
···
 	if (xdp_ring->next_to_clean >= cnt)
 		xdp_ring->next_to_clean -= cnt;
 	if (xsk_frames)
-		xsk_tx_completed(xdp_ring->xsk_pool, xsk_frames);
+		xsk_tx_completed(xsk_pool, xsk_frames);
 
 	return completed_frames;
 }
···
  * ice_xmit_xdp_tx_zc - AF_XDP ZC handler for XDP_TX
  * @xdp: XDP buffer to xmit
  * @xdp_ring: XDP ring to produce descriptor onto
+ * @xsk_pool: AF_XDP buffer pool pointer
  *
  * note that this function works directly on xdp_buff, no need to convert
  * it to xdp_frame. xdp_buff pointer is stored to ice_tx_buf so that cleaning
···
  * was not enough space on XDP ring
  */
 static int ice_xmit_xdp_tx_zc(struct xdp_buff *xdp,
-			      struct ice_tx_ring *xdp_ring)
+			      struct ice_tx_ring *xdp_ring,
+			      struct xsk_buff_pool *xsk_pool)
 {
 	struct skb_shared_info *sinfo = NULL;
 	u32 size = xdp->data_end - xdp->data;
···
 
 	free_space = ICE_DESC_UNUSED(xdp_ring);
 	if (free_space < ICE_RING_QUARTER(xdp_ring))
-		free_space += ice_clean_xdp_irq_zc(xdp_ring);
+		free_space += ice_clean_xdp_irq_zc(xdp_ring, xsk_pool);
 
 	if (unlikely(!free_space))
 		goto busy;
···
 		dma_addr_t dma;
 
 		dma = xsk_buff_xdp_get_dma(xdp);
-		xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, size);
+		xsk_buff_raw_dma_sync_for_device(xsk_pool, dma, size);
 
 		tx_buf->xdp = xdp;
 		tx_buf->type = ICE_TX_BUF_XSK_TX;
···
  * @xdp: xdp_buff used as input to the XDP program
  * @xdp_prog: XDP program to run
  * @xdp_ring: ring to be used for XDP_TX action
+ * @xsk_pool: AF_XDP buffer pool pointer
  *
  * Returns any of ICE_XDP_{PASS, CONSUMED, TX, REDIR}
  */
 static int
 ice_run_xdp_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
-	       struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring)
+	       struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring,
+	       struct xsk_buff_pool *xsk_pool)
 {
 	int err, result = ICE_XDP_PASS;
 	u32 act;
···
 		err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
 		if (!err)
 			return ICE_XDP_REDIR;
-		if (xsk_uses_need_wakeup(rx_ring->xsk_pool) && err == -ENOBUFS)
+		if (xsk_uses_need_wakeup(xsk_pool) && err == -ENOBUFS)
 			result = ICE_XDP_EXIT;
 		else
 			result = ICE_XDP_CONSUMED;
···
 	case XDP_PASS:
 		break;
 	case XDP_TX:
-		result = ice_xmit_xdp_tx_zc(xdp, xdp_ring);
+		result = ice_xmit_xdp_tx_zc(xdp, xdp_ring, xsk_pool);
 		if (result == ICE_XDP_CONSUMED)
 			goto out_failure;
 		break;
···
 /**
  * ice_clean_rx_irq_zc - consumes packets from the hardware ring
  * @rx_ring: AF_XDP Rx ring
+ * @xsk_pool: AF_XDP buffer pool pointer
  * @budget: NAPI budget
  *
  * Returns number of processed packets on success, remaining budget on failure.
  */
-int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
+int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring,
+			struct xsk_buff_pool *xsk_pool,
+			int budget)
 {
 	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
-	struct xsk_buff_pool *xsk_pool = rx_ring->xsk_pool;
 	u32 ntc = rx_ring->next_to_clean;
 	u32 ntu = rx_ring->next_to_use;
 	struct xdp_buff *first = NULL;
···
 		if (ice_is_non_eop(rx_ring, rx_desc))
 			continue;
 
-		xdp_res = ice_run_xdp_zc(rx_ring, first, xdp_prog, xdp_ring);
+		xdp_res = ice_run_xdp_zc(rx_ring, first, xdp_prog, xdp_ring,
+					 xsk_pool);
 		if (likely(xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR))) {
 			xdp_xmit |= xdp_res;
 		} else if (xdp_res == ICE_XDP_EXIT) {
···
 	rx_ring->next_to_clean = ntc;
 	entries_to_alloc = ICE_RX_DESC_UNUSED(rx_ring);
 	if (entries_to_alloc > ICE_RING_QUARTER(rx_ring))
-		failure |= !ice_alloc_rx_bufs_zc(rx_ring, entries_to_alloc);
+		failure |= !ice_alloc_rx_bufs_zc(rx_ring, xsk_pool,
+						 entries_to_alloc);
 
 	ice_finalize_xdp_rx(xdp_ring, xdp_xmit, 0);
 	ice_update_rx_ring_stats(rx_ring, total_rx_packets, total_rx_bytes);
···
 /**
  * ice_xmit_pkt - produce a single HW Tx descriptor out of AF_XDP descriptor
  * @xdp_ring: XDP ring to produce the HW Tx descriptor on
+ * @xsk_pool: XSK buffer pool to pick buffers to be consumed by HW
  * @desc: AF_XDP descriptor to pull the DMA address and length from
  * @total_bytes: bytes accumulator that will be used for stats update
  */
-static void ice_xmit_pkt(struct ice_tx_ring *xdp_ring, struct xdp_desc *desc,
+static void ice_xmit_pkt(struct ice_tx_ring *xdp_ring,
+			 struct xsk_buff_pool *xsk_pool, struct xdp_desc *desc,
 			 unsigned int *total_bytes)
 {
 	struct ice_tx_desc *tx_desc;
 	dma_addr_t dma;
 
-	dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, desc->addr);
-	xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, desc->len);
+	dma = xsk_buff_raw_get_dma(xsk_pool, desc->addr);
+	xsk_buff_raw_dma_sync_for_device(xsk_pool, dma, desc->len);
 
 	tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_to_use++);
 	tx_desc->buf_addr = cpu_to_le64(dma);
···
 /**
  * ice_xmit_pkt_batch - produce a batch of HW Tx descriptors out of AF_XDP descriptors
  * @xdp_ring: XDP ring to produce the HW Tx descriptors on
+ * @xsk_pool: XSK buffer pool to pick buffers to be consumed by HW
  * @descs: AF_XDP descriptors to pull the DMA addresses and lengths from
  * @total_bytes: bytes accumulator that will be used for stats update
  */
-static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *descs,
+static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring,
+			       struct xsk_buff_pool *xsk_pool,
+			       struct xdp_desc *descs,
 			       unsigned int *total_bytes)
 {
 	u16 ntu = xdp_ring->next_to_use;
···
 	loop_unrolled_for(i = 0; i < PKTS_PER_BATCH; i++) {
 		dma_addr_t dma;
 
-		dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, descs[i].addr);
-		xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, descs[i].len);
+		dma = xsk_buff_raw_get_dma(xsk_pool, descs[i].addr);
+		xsk_buff_raw_dma_sync_for_device(xsk_pool, dma, descs[i].len);
 
 		tx_desc = ICE_TX_DESC(xdp_ring, ntu++);
 		tx_desc->buf_addr = cpu_to_le64(dma);
···
 /**
  * ice_fill_tx_hw_ring - produce the number of Tx descriptors onto ring
  * @xdp_ring: XDP ring to produce the HW Tx descriptors on
+ * @xsk_pool: XSK buffer pool to pick buffers to be consumed by HW
  * @descs: AF_XDP descriptors to pull the DMA addresses and lengths from
  * @nb_pkts: count of packets to be send
  * @total_bytes: bytes accumulator that will be used for stats update
  */
-static void ice_fill_tx_hw_ring(struct ice_tx_ring *xdp_ring, struct xdp_desc *descs,
-				u32 nb_pkts, unsigned int *total_bytes)
+static void ice_fill_tx_hw_ring(struct ice_tx_ring *xdp_ring,
+				struct xsk_buff_pool *xsk_pool,
+				struct xdp_desc *descs, u32 nb_pkts,
+				unsigned int *total_bytes)
 {
 	u32 batched, leftover, i;
 
 	batched = ALIGN_DOWN(nb_pkts, PKTS_PER_BATCH);
 	leftover = nb_pkts & (PKTS_PER_BATCH - 1);
 	for (i = 0; i < batched; i += PKTS_PER_BATCH)
-		ice_xmit_pkt_batch(xdp_ring, &descs[i], total_bytes);
+		ice_xmit_pkt_batch(xdp_ring, xsk_pool, &descs[i], total_bytes);
 	for (; i < batched + leftover; i++)
-		ice_xmit_pkt(xdp_ring, &descs[i], total_bytes);
+		ice_xmit_pkt(xdp_ring, xsk_pool, &descs[i], total_bytes);
 }
 
 /**
  * ice_xmit_zc - take entries from XSK Tx ring and place them onto HW Tx ring
  * @xdp_ring: XDP ring to produce the HW Tx descriptors on
+ * @xsk_pool: AF_XDP buffer pool pointer
  *
  * Returns true if there is no more work that needs to be done, false otherwise
  */
-bool ice_xmit_zc(struct ice_tx_ring *xdp_ring)
+bool ice_xmit_zc(struct ice_tx_ring *xdp_ring, struct xsk_buff_pool *xsk_pool)
 {
-	struct xdp_desc *descs = xdp_ring->xsk_pool->tx_descs;
+	struct xdp_desc *descs = xsk_pool->tx_descs;
 	u32 nb_pkts, nb_processed = 0;
 	unsigned int total_bytes = 0;
 	int budget;
 
-	ice_clean_xdp_irq_zc(xdp_ring);
+	ice_clean_xdp_irq_zc(xdp_ring, xsk_pool);
+
+	if (!netif_carrier_ok(xdp_ring->vsi->netdev) ||
+	    !netif_running(xdp_ring->vsi->netdev))
+		return true;
 
 	budget = ICE_DESC_UNUSED(xdp_ring);
 	budget = min_t(u16, budget, ICE_RING_QUARTER(xdp_ring));
 
-	nb_pkts = xsk_tx_peek_release_desc_batch(xdp_ring->xsk_pool, budget);
+	nb_pkts = xsk_tx_peek_release_desc_batch(xsk_pool, budget);
 	if (!nb_pkts)
 		return true;
 
 	if (xdp_ring->next_to_use + nb_pkts >= xdp_ring->count) {
 		nb_processed = xdp_ring->count - xdp_ring->next_to_use;
-		ice_fill_tx_hw_ring(xdp_ring, descs, nb_processed, &total_bytes);
+		ice_fill_tx_hw_ring(xdp_ring, xsk_pool, descs, nb_processed,
+				    &total_bytes);
 		xdp_ring->next_to_use = 0;
 	}
 
-	ice_fill_tx_hw_ring(xdp_ring, &descs[nb_processed], nb_pkts - nb_processed,
-			    &total_bytes);
+	ice_fill_tx_hw_ring(xdp_ring, xsk_pool, &descs[nb_processed],
+			    nb_pkts - nb_processed, &total_bytes);
 
 	ice_set_rs_bit(xdp_ring);
 	ice_xdp_ring_update_tail(xdp_ring);
 	ice_update_tx_ring_stats(xdp_ring, nb_pkts, total_bytes);
 
-	if (xsk_uses_need_wakeup(xdp_ring->xsk_pool))
-		xsk_set_tx_need_wakeup(xdp_ring->xsk_pool);
+	if (xsk_uses_need_wakeup(xsk_pool))
+		xsk_set_tx_need_wakeup(xsk_pool);
 
 	return nb_pkts < budget;
 }
···
 	struct ice_vsi *vsi = np->vsi;
 	struct ice_tx_ring *ring;
 
-	if (test_bit(ICE_VSI_DOWN, vsi->state))
+	if (test_bit(ICE_VSI_DOWN, vsi->state) || !netif_carrier_ok(netdev))
 		return -ENETDOWN;
 
 	if (!ice_is_xdp_ena_vsi(vsi))
···
 
 	ring = vsi->rx_rings[queue_id]->xdp_ring;
 
-	if (!ring->xsk_pool)
+	if (!READ_ONCE(ring->xsk_pool))
 		return -EINVAL;
 
 	/* The idea here is that if NAPI is running, mark a miss, so

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

···
 #ifdef CONFIG_XDP_SOCKETS
 int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool,
 		       u16 qid);
-int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget);
+int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring,
+			struct xsk_buff_pool *xsk_pool,
+			int budget);
 int ice_xsk_wakeup(struct net_device *netdev, u32 queue_id, u32 flags);
-bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count);
+bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring,
+			  struct xsk_buff_pool *xsk_pool, u16 count);
 bool ice_xsk_any_rx_ring_ena(struct ice_vsi *vsi);
 void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring);
 void ice_xsk_clean_xdp_ring(struct ice_tx_ring *xdp_ring);
-bool ice_xmit_zc(struct ice_tx_ring *xdp_ring);
+bool ice_xmit_zc(struct ice_tx_ring *xdp_ring, struct xsk_buff_pool *xsk_pool);
 int ice_realloc_zc_buf(struct ice_vsi *vsi, bool zc);
 #else
-static inline bool ice_xmit_zc(struct ice_tx_ring __always_unused *xdp_ring)
+static inline bool ice_xmit_zc(struct ice_tx_ring __always_unused *xdp_ring,
+			       struct xsk_buff_pool __always_unused *xsk_pool)
 {
 	return false;
 }
···
 
 static inline int
 ice_clean_rx_irq_zc(struct ice_rx_ring __always_unused *rx_ring,
+		    struct xsk_buff_pool __always_unused *xsk_pool,
 		    int __always_unused budget)
 {
 	return 0;
···
 
 static inline bool
 ice_alloc_rx_bufs_zc(struct ice_rx_ring __always_unused *rx_ring,
+		     struct xsk_buff_pool __always_unused *xsk_pool,
 		     u16 __always_unused count)
 {
 	return false;

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

···
 	size_t n;
 	int i;
 
-	switch (qopt->cmd) {
-	case TAPRIO_CMD_REPLACE:
-		break;
-	case TAPRIO_CMD_DESTROY:
-		return igc_tsn_clear_schedule(adapter);
-	case TAPRIO_CMD_STATS:
-		igc_taprio_stats(adapter->netdev, &qopt->stats);
-		return 0;
-	case TAPRIO_CMD_QUEUE_STATS:
-		igc_taprio_queue_stats(adapter->netdev, &qopt->queue_stats);
-		return 0;
-	default:
-		return -EOPNOTSUPP;
-	}
-
 	if (qopt->base_time < 0)
 		return -ERANGE;
 
···
 	if (hw->mac.type != igc_i225)
 		return -EOPNOTSUPP;
 
-	err = igc_save_qbv_schedule(adapter, qopt);
+	switch (qopt->cmd) {
+	case TAPRIO_CMD_REPLACE:
+		err = igc_save_qbv_schedule(adapter, qopt);
+		break;
+	case TAPRIO_CMD_DESTROY:
+		err = igc_tsn_clear_schedule(adapter);
+		break;
+	case TAPRIO_CMD_STATS:
+		igc_taprio_stats(adapter->netdev, &qopt->stats);
+		return 0;
+	case TAPRIO_CMD_QUEUE_STATS:
+		igc_taprio_queue_stats(adapter->netdev, &qopt->queue_stats);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+
 	if (err)
 		return err;
 

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

···
 static void mvpp2_bm_pool_update_priv_fc(struct mvpp2 *priv, bool en)
 {
 	struct mvpp2_port *port;
-	int i;
+	int i, j;
 
 	for (i = 0; i < priv->port_count; i++) {
 		port = priv->port_list[i];
 		if (port->priv->percpu_pools) {
-			for (i = 0; i < port->nrxqs; i++)
-				mvpp2_bm_pool_update_fc(port, &port->priv->bm_pools[i],
+			for (j = 0; j < port->nrxqs; j++)
+				mvpp2_bm_pool_update_fc(port, &port->priv->bm_pools[j],
 							port->tx_fc & en);
 		} else {
 			mvpp2_bm_pool_update_fc(port, port->pool_long, port->tx_fc & en);

drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c

···
 	mlx5_tc_ct_entry_destroy_mod_hdr(ct_priv, zone_rule->attr, mh);
 	mlx5_put_label_mapping(ct_priv, attr->ct_attr.ct_labels_id);
 err_mod_hdr:
+	*attr = *old_attr;
 	kfree(old_attr);
 err_attr:
 	kvfree(spec);

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

···
 		    MLX5_CAP_FLOWTABLE_NIC_RX(mdev, decap))
 			caps |= MLX5_IPSEC_CAP_PACKET_OFFLOAD;
 
-		if ((MLX5_CAP_FLOWTABLE_NIC_TX(mdev, ignore_flow_level) &&
-		     MLX5_CAP_FLOWTABLE_NIC_RX(mdev, ignore_flow_level)) ||
-		    MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, ignore_flow_level))
+		if (IS_ENABLED(CONFIG_MLX5_CLS_ACT) &&
+		    ((MLX5_CAP_FLOWTABLE_NIC_TX(mdev, ignore_flow_level) &&
+		      MLX5_CAP_FLOWTABLE_NIC_RX(mdev, ignore_flow_level)) ||
+		     MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, ignore_flow_level)))
 			caps |= MLX5_IPSEC_CAP_PRIO;
 
 		if (MLX5_CAP_FLOWTABLE_NIC_TX(mdev,

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

···
 	if (!an_changes && link_modes == eproto.admin)
 		goto out;
 
-	mlx5_port_set_eth_ptys(mdev, an_disable, link_modes, ext);
+	err = mlx5_port_set_eth_ptys(mdev, an_disable, link_modes, ext);
+	if (err) {
+		netdev_err(priv->netdev, "%s: failed to set ptys reg: %d\n", __func__, err);
+		goto out;
+	}
+
 	mlx5_toggle_port_link(mdev);
 
 out:

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

···
 static void mlx5_fw_reset_complete_reload(struct mlx5_core_dev *dev, bool unloaded)
 {
 	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
+	struct devlink *devlink = priv_to_devlink(dev);
 
 	/* if this is the driver that initiated the fw reset, devlink completed the reload */
 	if (test_bit(MLX5_FW_RESET_FLAGS_PENDING_COMP, &fw_reset->reset_flags)) {
···
 			mlx5_core_err(dev, "reset reload flow aborted, PCI reads still not working\n");
 		else
 			mlx5_load_one(dev, true);
-		devlink_remote_reload_actions_performed(priv_to_devlink(dev), 0,
+		devl_lock(devlink);
+		devlink_remote_reload_actions_performed(devlink, 0,
 							BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT) |
 							BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE));
+		devl_unlock(devlink);
 	}
 }
 

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

···
 irq_pool_request_irq(struct mlx5_irq_pool *pool, struct irq_affinity_desc *af_desc)
 {
 	struct irq_affinity_desc auto_desc = {};
+	struct mlx5_irq *irq;
 	u32 irq_index;
 	int err;
 
···
 		else
 			cpu_get(pool, cpumask_first(&af_desc->mask));
 	}
-	return mlx5_irq_alloc(pool, irq_index,
-			      cpumask_empty(&auto_desc.mask) ? af_desc : &auto_desc,
-			      NULL);
+	irq = mlx5_irq_alloc(pool, irq_index,
+			     cpumask_empty(&auto_desc.mask) ? af_desc : &auto_desc,
+			     NULL);
+	if (IS_ERR(irq))
+		xa_erase(&pool->irqs, irq_index);
+	return irq;
 }
 
 /* Looking for the IRQ with the smallest refcount that fits req_mask.

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

···
 		goto unlock;
 
 	for (i = 0; i < ldev->ports; i++) {
-		if (ldev->pf[MLX5_LAG_P1].netdev == slave) {
+		if (ldev->pf[i].netdev == slave) {
 			port = i;
 			break;
 		}

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

···
 	/* Panic tear down fw command will stop the PCI bus communication
 	 * with the HCA, so the health poll is no longer needed.
 	 */
-	mlx5_drain_health_wq(dev);
 	mlx5_stop_health_poll(dev, false);
 
 	ret = mlx5_cmd_fast_teardown_hca(dev);
···
 
 	mlx5_core_info(dev, "Shutdown was called\n");
 	set_bit(MLX5_BREAK_FW_WAIT, &dev->intf_state);
+	mlx5_drain_health_wq(dev);
 	err = mlx5_try_fast_unload(dev);
 	if (err)
 		mlx5_unload_one(dev, false);

drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c

···
 	struct mlx5_core_dev *mdev = sf_dev->mdev;
 
 	set_bit(MLX5_BREAK_FW_WAIT, &mdev->intf_state);
+	mlx5_drain_health_wq(mdev);
 	mlx5_unload_one(mdev, false);
 }
 

drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c

···
 /* don't try to optimize STE allocation if the stack is too constaraining */
 #define DR_RULE_MAX_STES_OPTIMIZED 0
 #else
-#define DR_RULE_MAX_STES_OPTIMIZED 5
+#define DR_RULE_MAX_STES_OPTIMIZED 2
 #endif
 #define DR_RULE_MAX_STE_CHAIN_OPTIMIZED (DR_RULE_MAX_STES_OPTIMIZED + DR_ACTION_MAX_STES)
 

drivers/net/ethernet/meta/Kconfig

···
 config FBNIC
 	tristate "Meta Platforms Host Network Interface"
 	depends on X86_64 || COMPILE_TEST
-	depends on S390=n
+	depends on !S390
 	depends on MAX_SKB_FRAGS < 22
 	depends on PCI_MSI
 	select PHYLINK

drivers/net/ethernet/realtek/r8169_main.c

···
 	if (unlikely(!rtl_tx_slots_avail(tp))) {
 		if (net_ratelimit())
 			netdev_err(dev, "BUG! Tx Ring full when queue awake!\n");
-		goto err_stop_0;
+		netif_stop_queue(dev);
+		return NETDEV_TX_BUSY;
 	}
 
 	opts[1] = rtl8169_tx_vlan_tag(skb);
···
 	dev_kfree_skb_any(skb);
 	dev->stats.tx_dropped++;
 	return NETDEV_TX_OK;
-
-err_stop_0:
-	netif_stop_queue(dev);
-	dev->stats.tx_dropped++;
-	return NETDEV_TX_BUSY;
 }
 
 static unsigned int rtl_last_frag_len(struct sk_buff *skb)

drivers/net/ethernet/xilinx/xilinx_axienet_main.c

···
 			   ~(XAE_OPTION_TXEN | XAE_OPTION_RXEN));
 	axienet_set_mac_address(ndev, NULL);
 	axienet_set_multicast_list(ndev);
-	axienet_setoptions(ndev, lp->options);
 	napi_enable(&lp->napi_rx);
 	napi_enable(&lp->napi_tx);
+	axienet_setoptions(ndev, lp->options);
 }
 
 /**

drivers/net/phy/aquantia/aquantia_main.c

···
 	unsigned long *possible = phydev->possible_interfaces;
 	unsigned int serdes_mode, rate_adapt;
 	phy_interface_t interface;
-	int i, val, ret;
-
-	ret = phy_read_mmd_poll_timeout(phydev, MDIO_MMD_VEND1,
-					VEND1_GLOBAL_CFG_10M, val, val != 0,
-					1000, 100000, false);
-	if (ret)
-		return ret;
+	int i, val;
 
 	/* Walk the media-speed configuration registers to determine which
 	 * host-side serdes modes may be used by the PHY depending on the
···
 	return 0;
 }
 
+static int aqr113c_fill_interface_modes(struct phy_device *phydev)
+{
+	int val, ret;
+
+	/* It's been observed on some models that - when coming out of suspend
+	 * - the FW signals that the PHY is ready but the GLOBAL_CFG registers
+	 * continue on returning zeroes for some time. Let's poll the 100M
+	 * register until it returns a real value as both 113c and 115c support
+	 * this mode.
+	 */
+	ret = phy_read_mmd_poll_timeout(phydev, MDIO_MMD_VEND1,
+					VEND1_GLOBAL_CFG_100M, val, val != 0,
+					1000, 100000, false);
+	if (ret)
+		return ret;
+
+	return aqr107_fill_interface_modes(phydev);
+}
+
 static int aqr113c_config_init(struct phy_device *phydev)
 {
 	int ret;
···
 	if (ret)
 		return ret;
 
-	return aqr107_fill_interface_modes(phydev);
+	return aqr113c_fill_interface_modes(phydev);
 }
 
 static int aqr107_probe(struct phy_device *phydev)

drivers/net/phy/micrel.c

···
 	const struct device *dev_walker;
 	int ret;
 
+	phydev->mdix_ctrl = ETH_TP_MDI_AUTO;
+
 	dev_walker = &phydev->mdio.dev;
 	do {
 		of_node = dev_walker->of_node;
···
 #define MII_KSZ9131_AUTO_MDIX		0x1C
 #define MII_KSZ9131_AUTO_MDI_SET	BIT(7)
 #define MII_KSZ9131_AUTO_MDIX_SWAP_OFF	BIT(6)
+#define MII_KSZ9131_DIG_AXAN_STS	0x14
+#define MII_KSZ9131_DIG_AXAN_STS_LINK_DET	BIT(14)
+#define MII_KSZ9131_DIG_AXAN_STS_A_SELECT	BIT(12)
 
 static int ksz9131_mdix_update(struct phy_device *phydev)
 {
 	int ret;
 
-	ret = phy_read(phydev, MII_KSZ9131_AUTO_MDIX);
-	if (ret < 0)
-		return ret;
-
-	if (ret & MII_KSZ9131_AUTO_MDIX_SWAP_OFF) {
-		if (ret & MII_KSZ9131_AUTO_MDI_SET)
-			phydev->mdix_ctrl = ETH_TP_MDI;
-		else
-			phydev->mdix_ctrl = ETH_TP_MDI_X;
+	if (phydev->mdix_ctrl != ETH_TP_MDI_AUTO) {
+		phydev->mdix = phydev->mdix_ctrl;
 	} else {
-		phydev->mdix_ctrl = ETH_TP_MDI_AUTO;
-	}
+		ret = phy_read(phydev, MII_KSZ9131_DIG_AXAN_STS);
+		if (ret < 0)
+			return ret;
 
-	if (ret & MII_KSZ9131_AUTO_MDI_SET)
-		phydev->mdix = ETH_TP_MDI;
-	else
-		phydev->mdix = ETH_TP_MDI_X;
+		if (ret & MII_KSZ9131_DIG_AXAN_STS_LINK_DET) {
+			if (ret & MII_KSZ9131_DIG_AXAN_STS_A_SELECT)
+				phydev->mdix = ETH_TP_MDI;
+			else
+				phydev->mdix = ETH_TP_MDI_X;
+		} else {
+			phydev->mdix = ETH_TP_MDI_INVALID;
+		}
+	}
 
 	return 0;
 }

drivers/net/phy/realtek.c

···
 		.handle_interrupt = genphy_handle_interrupt_no_ack,
 		.suspend	= genphy_suspend,
 		.resume		= genphy_resume,
+	}, {
+		PHY_ID_MATCH_EXACT(0x001cc960),
+		.name		= "RTL8366S Gigabit Ethernet",
+		.suspend	= genphy_suspend,
+		.resume		= genphy_resume,
+		.read_mmd	= genphy_read_mmd_unsupported,
+		.write_mmd	= genphy_write_mmd_unsupported,
 	},
 };
 

drivers/net/usb/sr9700.c

···
 	struct usbnet *dev = netdev_priv(netdev);
 	__le16 res;
 	int rc = 0;
+	int err;
 
 	if (phy_id) {
 		netdev_dbg(netdev, "Only internal phy supported\n");
···
 	if (loc == MII_BMSR) {
 		u8 value;
 
-		sr_read_reg(dev, SR_NSR, &value);
+		err = sr_read_reg(dev, SR_NSR, &value);
+		if (err < 0)
+			return err;
+
 		if (value & NSR_LINKST)
 			rc = 1;
 	}
-	sr_share_read_word(dev, 1, loc, &res);
+	err = sr_share_read_word(dev, 1, loc, &res);
+	if (err < 0)
+		return err;
+
 	if (rc == 1)
 		res = le16_to_cpu(res) | BMSR_LSTATUS;
 	else

drivers/net/wan/fsl_qmc_hdlc.c

···
 #include <linux/hdlc.h>
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
+#include <linux/mutex.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
···
 	struct qmc_chan *qmc_chan;
 	struct net_device *netdev;
 	struct framer *framer;
-	spinlock_t carrier_lock; /* Protect carrier detection */
+	struct mutex carrier_lock; /* Protect carrier detection */
 	struct notifier_block nb;
 	bool is_crc32;
 	spinlock_t tx_lock; /* Protect tx descriptors */
···
 	if (!qmc_hdlc->framer)
 		return 0;
 
-	guard(spinlock_irqsave)(&qmc_hdlc->carrier_lock);
+	guard(mutex)(&qmc_hdlc->carrier_lock);
 
 	ret = framer_get_status(qmc_hdlc->framer, &framer_status);
 	if (ret) {
···
 	struct qmc_hdlc_desc *desc = context;
 	struct net_device *netdev;
 	struct qmc_hdlc *qmc_hdlc;
+	size_t crc_size;
 	int ret;
 
 	netdev = desc->netdev;
···
 		if (flags & QMC_RX_FLAG_HDLC_CRC) /* CRC error */
 			netdev->stats.rx_crc_errors++;
 		kfree_skb(desc->skb);
-	} else {
-		netdev->stats.rx_packets++;
-		netdev->stats.rx_bytes += length;
-
-		skb_put(desc->skb, length);
-		desc->skb->protocol = hdlc_type_trans(desc->skb, netdev);
-		netif_rx(desc->skb);
+		goto re_queue;
 	}
 
+	/* Discard the CRC */
+	crc_size = qmc_hdlc->is_crc32 ? 4 : 2;
+	if (length < crc_size) {
+		netdev->stats.rx_length_errors++;
+		kfree_skb(desc->skb);
+		goto re_queue;
+	}
+	length -= crc_size;
+
+	netdev->stats.rx_packets++;
+	netdev->stats.rx_bytes += length;
+
+	skb_put(desc->skb, length);
+	desc->skb->protocol = hdlc_type_trans(desc->skb, netdev);
+	netif_rx(desc->skb);
+
+re_queue:
 	/* Re-queue a transfer using the same descriptor */
 	ret = qmc_hdlc_recv_queue(qmc_hdlc, desc, desc->dma_size);
 	if (ret) {
···
 
 	qmc_hdlc->dev = dev;
 	spin_lock_init(&qmc_hdlc->tx_lock);
-	spin_lock_init(&qmc_hdlc->carrier_lock);
+	mutex_init(&qmc_hdlc->carrier_lock);
 
 	qmc_hdlc->qmc_chan = devm_qmc_chan_get_bychild(dev, dev->of_node);
 	if (IS_ERR(qmc_hdlc->qmc_chan))

drivers/net/wireless/ath/ath12k/pci.c

···
 {
 	int i;
 
-	clear_bit(ATH12K_FLAG_EXT_IRQ_ENABLED, &ab->dev_flags);
+	if (!test_and_clear_bit(ATH12K_FLAG_EXT_IRQ_ENABLED, &ab->dev_flags))
+		return;
 
 	for (i = 0; i < ATH12K_EXT_IRQ_GRP_NUM_MAX; i++) {
 		struct ath12k_ext_irq_grp *irq_grp = &ab->ext_irq_grp[i];

drivers/net/wireless/ath/ath12k/wow.c

···
 	struct ath12k *ar = arvif->ar;
 	unsigned long wow_mask = 0;
 	int pattern_id = 0;
-	int ret, i;
+	int ret, i, j;
 
 	/* Setup requested WOW features */
 	switch (arvif->vdev_type) {
···
 			       eth_pattern->pattern_len);
 
 			/* convert bitmask to bytemask */
-			for (i = 0; i < eth_pattern->pattern_len; i++)
-				if (eth_pattern->mask[i / 8] & BIT(i % 8))
-					new_pattern.bytemask[i] = 0xff;
+			for (j = 0; j < eth_pattern->pattern_len; j++)
+				if (eth_pattern->mask[j / 8] & BIT(j % 8))
+					new_pattern.bytemask[j] = 0xff;
 
 			new_pattern.pattern_len = eth_pattern->pattern_len;
 			new_pattern.pkt_offset = eth_pattern->pkt_offset;

drivers/net/wireless/mediatek/mt76/mt7921/main.c

···
 
 	mvif->bss_conf.mt76.omac_idx = mvif->bss_conf.mt76.idx;
 	mvif->phy = phy;
+	mvif->bss_conf.vif = mvif;
 	mvif->bss_conf.mt76.band_idx = 0;
 	mvif->bss_conf.mt76.wmm_idx = mvif->bss_conf.mt76.idx % MT76_CONNAC_MAX_WMM_SETS;
 

include/linux/virtio_net.h

···
 	unsigned int thlen = 0;
 	unsigned int p_off = 0;
 	unsigned int ip_proto;
-	u64 ret, remainder, gso_size;
 
 	if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
 		switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
···
 		u32 start = __virtio16_to_cpu(little_endian, hdr->csum_start);
 		u32 off = __virtio16_to_cpu(little_endian, hdr->csum_offset);
 		u32 needed = start + max_t(u32, thlen, off + sizeof(__sum16));
-
-		if (hdr->gso_size) {
-			gso_size = __virtio16_to_cpu(little_endian, hdr->gso_size);
-			ret = div64_u64_rem(skb->len, gso_size, &remainder);
-			if (!(ret && (hdr->gso_size > needed) &&
-						((remainder > needed) || (remainder == 0)))) {
-				return -EINVAL;
-			}
-			skb_shinfo(skb)->tx_flags |= SKBFL_SHARED_FRAG;
-		}
 
 		if (!pskb_may_pull(skb, needed))
 			return -EINVAL;
···
 			if (skb->len - p_off > gso_size * UDP_MAX_SEGMENTS)
 				return -EINVAL;
 			if (gso_type != SKB_GSO_UDP_L4)
+				return -EINVAL;
+			break;
+		case SKB_GSO_TCPV4:
+		case SKB_GSO_TCPV6:
+			if (skb->csum_offset != offsetof(struct tcphdr, check))
 				return -EINVAL;
 			break;
 		}

include/trace/events/mptcp.h

···
 		struct sock *ssk;
 
 		__entry->active = mptcp_subflow_active(subflow);
-		__entry->backup = subflow->backup;
+		__entry->backup = subflow->backup || subflow->request_bkup;
 
 		if (subflow->tcp_sock && sk_fullsock(subflow->tcp_sock))
 			__entry->free = sk_stream_memory_free(subflow->tcp_sock);

net/bluetooth/hci_core.c

···
 	case DISCOVERY_STARTING:
 		break;
 	case DISCOVERY_FINDING:
-		/* If discovery was not started then it was initiated by the
-		 * MGMT interface so no MGMT event shall be generated either
-		 */
-		if (old_state != DISCOVERY_STARTING) {
-			hdev->discovery.state = old_state;
-			return;
-		}
 		mgmt_discovering(hdev, 1);
 		break;
 	case DISCOVERY_RESOLVING:

net/bluetooth/hci_event.c

···
 	switch (enable) {
 	case LE_SCAN_ENABLE:
 		hci_dev_set_flag(hdev, HCI_LE_SCAN);
-		if (hdev->le_scan_type == LE_SCAN_ACTIVE)
+		if (hdev->le_scan_type == LE_SCAN_ACTIVE) {
 			clear_pending_adv_report(hdev);
-		hci_discovery_set_state(hdev, DISCOVERY_FINDING);
+			hci_discovery_set_state(hdev, DISCOVERY_FINDING);
+		}
 		break;
 
 	case LE_SCAN_DISABLE:

net/bluetooth/hci_sync.c

···
 	 */
 	filter_policy = hci_update_accept_list_sync(hdev);
 
+	/* If suspended and filter_policy set to 0x00 (no acceptlist) then
+	 * passive scanning cannot be started since that would require the host
+	 * to be woken up to process the reports.
+	 */
+	if (hdev->suspended && !filter_policy) {
+		/* Check if accept list is empty then there is no need to scan
+		 * while suspended.
+		 */
+		if (list_empty(&hdev->le_accept_list))
+			return 0;
+
+		/* If there are devices is the accept_list that means some
+		 * devices could not be programmed which in non-suspended case
+		 * means filter_policy needs to be set to 0x00 so the host needs
+		 * to filter, but since this is treating suspended case we
+		 * can ignore device needing host to filter to allow devices in
+		 * the acceptlist to be able to wakeup the system.
+		 */
+		filter_policy = 0x01;
+	}
+
 	/* When the controller is using random resolvable addresses and
 	 * with that having LE privacy enabled, then controllers with
 	 * Extended Scanner Filter Policies support can now enable support

net/core/dev.c

···
 			bpf_net_ctx_clear(bpf_net_ctx);
 			return XDP_DROP;
 		}
+		bpf_net_ctx_clear(bpf_net_ctx);
 	}
 	return XDP_PASS;
 out_redir:

net/core/rtnetlink.c

···
 	if (ifm->ifi_index > 0)
 		dev = __dev_get_by_index(tgt_net, ifm->ifi_index);
 	else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME])
-		dev = rtnl_dev_get(net, tb);
+		dev = rtnl_dev_get(tgt_net, tb);
 	else if (tb[IFLA_GROUP])
 		err = rtnl_group_dellink(tgt_net, nla_get_u32(tb[IFLA_GROUP]));
 	else

net/ethtool/ioctl.c

···
 	u32 rss_cfg_offset = offsetof(struct ethtool_rxfh, rss_config[0]);
 	const struct ethtool_ops *ops = dev->ethtool_ops;
 	u32 dev_indir_size = 0, dev_key_size = 0, i;
+	u32 user_indir_len = 0, indir_bytes = 0;
 	struct ethtool_rxfh_param rxfh_dev = {};
 	struct ethtool_rxfh_context *ctx = NULL;
 	struct netlink_ext_ack *extack = NULL;
 	struct ethtool_rxnfc rx_rings;
 	struct ethtool_rxfh rxfh;
 	bool locked = false; /* dev->ethtool->rss_lock taken */
-	u32 indir_bytes = 0;
 	bool create = false;
 	u8 *rss_config;
 	int ret;
···
 	     rxfh.input_xfrm == RXH_XFRM_NO_CHANGE))
 		return -EINVAL;
 
-	if (rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE)
-		indir_bytes = dev_indir_size * sizeof(rxfh_dev.indir[0]);
+	indir_bytes = dev_indir_size * sizeof(rxfh_dev.indir[0]);
 
-	rss_config = kzalloc(indir_bytes + rxfh.key_size, GFP_USER);
+	rss_config = kzalloc(indir_bytes + dev_key_size, GFP_USER);
 	if (!rss_config)
 		return -ENOMEM;
 
···
 	 */
 	if (rxfh.indir_size &&
 	    rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE) {
+		user_indir_len = indir_bytes;
 		rxfh_dev.indir = (u32 *)rss_config;
 		rxfh_dev.indir_size = dev_indir_size;
 		ret = ethtool_copy_validate_indir(rxfh_dev.indir,
···
 		rxfh_dev.key_size = dev_key_size;
 		rxfh_dev.key = rss_config + indir_bytes;
 		if (copy_from_user(rxfh_dev.key,
-				   useraddr + rss_cfg_offset + indir_bytes,
+				   useraddr + rss_cfg_offset + user_indir_len,
 				   rxfh.key_size)) {
 			ret = -EFAULT;
 			goto out;
···
 	rxfh_dev.input_xfrm = rxfh.input_xfrm;
 
 	if (rxfh.rss_context && ops->create_rxfh_context) {
-		if (create)
+		if (create) {
 			ret = ops->create_rxfh_context(dev, ctx, &rxfh_dev,
 						       extack);
-		else if (rxfh_dev.rss_delete)
+			/* Make sure driver populates defaults */
+			WARN_ON_ONCE(!ret && !rxfh_dev.key &&
+				     !memchr_inv(ethtool_rxfh_context_key(ctx),
+						 0, ctx->key_size));
+		} else if (rxfh_dev.rss_delete) {
 			ret = ops->remove_rxfh_context(dev, ctx,
 						       rxfh.rss_context,
 						       extack);
-		else
+		} else {
 			ret = ops->modify_rxfh_context(dev, ctx, &rxfh_dev,
 						       extack);
+		}
 	} else {
 		ret = ops->set_rxfh(dev, &rxfh_dev, extack);
 	}
···
 			kfree(ctx);
 			goto out;
 		}
+
+		/* Fetch the defaults for the old API, in the new API drivers
+		 * should write defaults into ctx themselves.
+		 */
+		rxfh_dev.indir = (u32 *)rss_config;
+		rxfh_dev.indir_size = dev_indir_size;
+
+		rxfh_dev.key = rss_config + indir_bytes;
+		rxfh_dev.key_size = dev_key_size;
+
+		ret = ops->get_rxfh(dev, &rxfh_dev);
+		if (WARN_ON(ret)) {
+			xa_erase(&dev->ethtool->rss_ctx, rxfh.rss_context);
+			kfree(ctx);
+			goto out;
+		}
 	}
 	if (rxfh_dev.rss_delete) {
 		WARN_ON(xa_erase(&dev->ethtool->rss_ctx, rxfh.rss_context) != ctx);
···
 		if (rxfh_dev.indir) {
 			for (i = 0; i < dev_indir_size; i++)
 				ethtool_rxfh_context_indir(ctx)[i] = rxfh_dev.indir[i];
-			ctx->indir_configured = 1;
+			ctx->indir_configured =
+				rxfh.indir_size &&
+				rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE;
 		}
 		if (rxfh_dev.key) {
 			memcpy(ethtool_rxfh_context_key(ctx), rxfh_dev.key,
 			       dev_key_size);
-			ctx->key_configured = 1;
+			ctx->key_configured = !!rxfh.key_size;
 		}
 		if (rxfh_dev.hfunc != ETH_RSS_HASH_NO_CHANGE)
 			ctx->hfunc = rxfh_dev.hfunc;

net/ethtool/rss.c

···
 	const struct rss_reply_data *data = RSS_REPDATA(reply_base);
 	int len;
 
-	len = nla_total_size(sizeof(u32)) +	/* _RSS_HFUNC */
+	len = nla_total_size(sizeof(u32)) +	/* _RSS_CONTEXT */
+	      nla_total_size(sizeof(u32)) +	/* _RSS_HFUNC */
 	      nla_total_size(sizeof(u32)) +	/* _RSS_INPUT_XFRM */
 	      nla_total_size(sizeof(u32) * data->indir_size) + /* _RSS_INDIR */
 	      nla_total_size(data->hkey_size);	/* _RSS_HKEY */
···
 	       const struct ethnl_reply_data *reply_base)
 {
 	const struct rss_reply_data *data = RSS_REPDATA(reply_base);
+	struct rss_req_info *request = RSS_REQINFO(req_base);
+
+	if (request->rss_context &&
+	    nla_put_u32(skb, ETHTOOL_A_RSS_CONTEXT, request->rss_context))
+		return -EMSGSIZE;
 
 	if ((data->hfunc &&
 	     nla_put_u32(skb, ETHTOOL_A_RSS_HFUNC, data->hfunc)) ||

net/ipv4/netfilter/iptable_nat.c

···
 
 static int __init iptable_nat_init(void)
 {
-	int ret = xt_register_template(&nf_nat_ipv4_table,
-				       iptable_nat_table_init);
+	int ret;
 
+	/* net->gen->ptr[iptable_nat_net_id] must be allocated
+	 * before calling iptable_nat_table_init().
+	 */
+	ret = register_pernet_subsys(&iptable_nat_net_ops);
 	if (ret < 0)
 		return ret;
 
-	ret = register_pernet_subsys(&iptable_nat_net_ops);
-	if (ret < 0) {
-		xt_unregister_template(&nf_nat_ipv4_table);
-		return ret;
-	}
+	ret = xt_register_template(&nf_nat_ipv4_table,
+				   iptable_nat_table_init);
+	if (ret < 0)
+		unregister_pernet_subsys(&iptable_nat_net_ops);
 
 	return ret;
 }
 
 static void __exit iptable_nat_exit(void)
 {
-	unregister_pernet_subsys(&iptable_nat_net_ops);
 	xt_unregister_template(&nf_nat_ipv4_table);
+	unregister_pernet_subsys(&iptable_nat_net_ops);
 }
 
 module_init(iptable_nat_init);

net/ipv4/tcp_input.c

···
 	 * <prev RTT . ><current RTT .. ><next RTT .... >
 	 */
 
-	if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) &&
-	    !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
+	if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf)) {
 		u64 rcvwin, grow;
 		int rcvbuf;
 
···
 
 		rcvbuf = min_t(u64, tcp_space_from_win(sk, rcvwin),
 			       READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
-		if (rcvbuf > sk->sk_rcvbuf) {
-			WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);
+		if (!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
+			if (rcvbuf > sk->sk_rcvbuf) {
+				WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);
 
-			/* Make the window clamp follow along.  */
-			WRITE_ONCE(tp->window_clamp,
-				   tcp_win_from_space(sk, rcvbuf));
+				/* Make the window clamp follow along.  */
+				WRITE_ONCE(tp->window_clamp,
+					   tcp_win_from_space(sk, rcvbuf));
+			}
+		} else {
+			/* Make the window clamp follow along while being bounded
+			 * by SO_RCVBUF.
+			 */
+			int clamp = tcp_win_from_space(sk, min(rcvbuf, sk->sk_rcvbuf));
+
+			if (clamp > tp->window_clamp)
+				WRITE_ONCE(tp->window_clamp, clamp);
 		}
 	}
 	tp->rcvq_space.space = copied;

net/ipv4/tcp_offload.c

···
 	if (thlen < sizeof(*th))
 		goto out;
 
+	if (unlikely(skb_checksum_start(skb) != skb_transport_header(skb)))
+		goto out;
+
 	if (!pskb_may_pull(skb, thlen))
 		goto out;
 

net/ipv4/udp_offload.c

···
 	if (gso_skb->len <= sizeof(*uh) + mss)
 		return ERR_PTR(-EINVAL);
 
+	if (unlikely(skb_checksum_start(gso_skb) !=
+		     skb_transport_header(gso_skb)))
+		return ERR_PTR(-EINVAL);
+
 	if (skb_gso_ok(gso_skb, features | NETIF_F_GSO_ROBUST)) {
 		/* Packet is from an untrusted source, reset gso_segs. */
 		skb_shinfo(gso_skb)->gso_segs = DIV_ROUND_UP(gso_skb->len - sizeof(*uh),

net/ipv6/ndisc.c

···
 		return NULL;
 	memset(ndopts, 0, sizeof(*ndopts));
 	while (opt_len) {
+		bool unknown = false;
 		int l;
 		if (opt_len < sizeof(struct nd_opt_hdr))
 			return NULL;
···
 			break;
 #endif
 		default:
-			if (ndisc_is_useropt(dev, nd_opt)) {
-				ndopts->nd_useropts_end = nd_opt;
-				if (!ndopts->nd_useropts)
-					ndopts->nd_useropts = nd_opt;
-			} else {
-				/*
-				 * Unknown options must be silently ignored,
-				 * to accommodate future extension to the
-				 * protocol.
-				 */
-				ND_PRINTK(2, notice,
-					  "%s: ignored unsupported option; type=%d, len=%d\n",
-					  __func__,
-					  nd_opt->nd_opt_type,
-					  nd_opt->nd_opt_len);
-			}
+			unknown = true;
+		}
+		if (ndisc_is_useropt(dev, nd_opt)) {
+			ndopts->nd_useropts_end = nd_opt;
+			if (!ndopts->nd_useropts)
+				ndopts->nd_useropts = nd_opt;
+		} else if (unknown) {
+			/*
+			 * Unknown options must be silently ignored,
+			 * to accommodate future extension to the
+			 * protocol.
+			 */
+			ND_PRINTK(2, notice,
+				  "%s: ignored unsupported option; type=%d, len=%d\n",
+				  __func__,
+				  nd_opt->nd_opt_type,
+				  nd_opt->nd_opt_len);
 		}
 next_opt:
 		opt_len -= l;

net/ipv6/netfilter/ip6table_nat.c

···
 
 static int __init ip6table_nat_init(void)
 {
-	int ret = xt_register_template(&nf_nat_ipv6_table,
-				       ip6table_nat_table_init);
+	int ret;
 
+	/* net->gen->ptr[ip6table_nat_net_id] must be allocated
+	 * before calling ip6t_nat_register_lookups().
+	 */
+	ret = register_pernet_subsys(&ip6table_nat_net_ops);
 	if (ret < 0)
 		return ret;
 
-	ret = register_pernet_subsys(&ip6table_nat_net_ops);
+	ret = xt_register_template(&nf_nat_ipv6_table,
+				   ip6table_nat_table_init);
 	if (ret)
-		xt_unregister_template(&nf_nat_ipv6_table);
+		unregister_pernet_subsys(&ip6table_nat_net_ops);
 
 	return ret;
 }
 
 static void __exit ip6table_nat_exit(void)
 {
-	unregister_pernet_subsys(&ip6table_nat_net_ops);
 	xt_unregister_template(&nf_nat_ipv6_table);
+	unregister_pernet_subsys(&ip6table_nat_net_ops);
 }
 
 module_init(ip6table_nat_init);

net/iucv/af_iucv.c

···
 	struct iucv_sock *iucv = iucv_sk(sk);
 	struct iucv_path *path = iucv->path;
 
-	if (iucv->path) {
-		iucv->path = NULL;
+	/* Whoever resets the path pointer, must sever and free it. */
+	if (xchg(&iucv->path, NULL)) {
 		if (with_user_data) {
 			low_nmcpy(user_data, iucv->src_name);
 			high_nmcpy(user_data, iucv->dst_name);

net/mac80211/cfg.c

···
 
 	/* apply all changes now - no failures allowed */
 
-	if (monitor_sdata)
+	if (monitor_sdata && ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF))
 		ieee80211_set_mu_mimo_follow(monitor_sdata, params);
 
 	if (params->flags) {
···
 		sdata = IEEE80211_WDEV_TO_SUB_IF(wdev);
 
 		if (sdata->vif.type == NL80211_IFTYPE_MONITOR) {
+			if (!ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF))
+				return -EOPNOTSUPP;
+
 			sdata = wiphy_dereference(local->hw.wiphy,
 						  local->monitor_sdata);
 			if (!sdata)
···
 	if (has_monitor) {
 		sdata = wiphy_dereference(local->hw.wiphy,
 					  local->monitor_sdata);
-		if (sdata) {
+		if (sdata && ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) {
 			sdata->deflink.user_power_level = local->user_power_level;
 			if (txp_type != sdata->vif.bss_conf.txpower_type)
 				update_txp_type = true;

net/mac80211/tx.c

···
 			break;
 		}
 		sdata = rcu_dereference(local->monitor_sdata);
-		if (sdata) {
+		if (sdata && ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) {
 			vif = &sdata->vif;
 			info->hw_queue =
 				vif->hw_queue[skb_get_queue_mapping(skb)];
···
 			break;
 		}
 		tx.sdata = rcu_dereference(local->monitor_sdata);
-		if (tx.sdata) {
+		if (tx.sdata &&
+		    ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) {
 			vif = &tx.sdata->vif;
 			info->hw_queue =
 				vif->hw_queue[skb_get_queue_mapping(skb)];

net/mac80211/util.c

···
 	sdata = rcu_dereference_check(local->monitor_sdata,
 				      lockdep_is_held(&local->iflist_mtx) ||
 				      lockdep_is_held(&local->hw.wiphy->mtx));
-	if (sdata &&
+	if (sdata && ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF) &&
 	    (iter_flags & IEEE80211_IFACE_ITER_RESUME_ALL || !active_only ||
 	     sdata->flags & IEEE80211_SDATA_IN_DRIVER))
 		iterator(data, sdata->vif.addr, &sdata->vif);

net/mptcp/mib.c

···
 	SNMP_MIB_ITEM("MPTCPRetrans", MPTCP_MIB_RETRANSSEGS),
 	SNMP_MIB_ITEM("MPJoinNoTokenFound", MPTCP_MIB_JOINNOTOKEN),
 	SNMP_MIB_ITEM("MPJoinSynRx", MPTCP_MIB_JOINSYNRX),
+	SNMP_MIB_ITEM("MPJoinSynBackupRx", MPTCP_MIB_JOINSYNBACKUPRX),
 	SNMP_MIB_ITEM("MPJoinSynAckRx", MPTCP_MIB_JOINSYNACKRX),
+	SNMP_MIB_ITEM("MPJoinSynAckBackupRx", MPTCP_MIB_JOINSYNACKBACKUPRX),
 	SNMP_MIB_ITEM("MPJoinSynAckHMacFailure", MPTCP_MIB_JOINSYNACKMAC),
 	SNMP_MIB_ITEM("MPJoinAckRx", MPTCP_MIB_JOINACKRX),
 	SNMP_MIB_ITEM("MPJoinAckHMacFailure", MPTCP_MIB_JOINACKMAC),

net/mptcp/mib.h

···
 	MPTCP_MIB_RETRANSSEGS,		/* Segments retransmitted at the MPTCP-level */
 	MPTCP_MIB_JOINNOTOKEN,		/* Received MP_JOIN but the token was not found */
 	MPTCP_MIB_JOINSYNRX,		/* Received a SYN + MP_JOIN */
+	MPTCP_MIB_JOINSYNBACKUPRX,	/* Received a SYN + MP_JOIN + backup flag */
 	MPTCP_MIB_JOINSYNACKRX,		/* Received a SYN/ACK + MP_JOIN */
+	MPTCP_MIB_JOINSYNACKBACKUPRX,	/* Received a SYN/ACK + MP_JOIN + backup flag */
 	MPTCP_MIB_JOINSYNACKMAC,	/* HMAC was wrong on SYN/ACK + MP_JOIN */
 	MPTCP_MIB_JOINACKRX,		/* Received an ACK + MP_JOIN */
 	MPTCP_MIB_JOINACKMAC,		/* HMAC was wrong on ACK + MP_JOIN */

net/mptcp/options.c

···
 		return true;
 	} else if (subflow_req->mp_join) {
 		opts->suboptions = OPTION_MPTCP_MPJ_SYNACK;
-		opts->backup = subflow_req->backup;
+		opts->backup = subflow_req->request_bkup;
 		opts->join_id = subflow_req->local_id;
 		opts->thmac = subflow_req->thmac;
 		opts->nonce = subflow_req->local_nonce;

net/mptcp/pm.c

···
 	return mptcp_pm_nl_get_local_id(msk, &skc_local);
 }
 
+bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc)
+{
+	struct mptcp_addr_info skc_local;
+
+	mptcp_local_address((struct sock_common *)skc, &skc_local);
+
+	if (mptcp_pm_is_userspace(msk))
+		return mptcp_userspace_pm_is_backup(msk, &skc_local);
+
+	return mptcp_pm_nl_is_backup(msk, &skc_local);
+}
+
 int mptcp_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id,
 					 u8 *flags, int *ifindex)
 {

net/mptcp/pm_netlink.c

···
 	slow = lock_sock_fast(ssk);
 	if (prio) {
 		subflow->send_mp_prio = 1;
-		subflow->backup = backup;
 		subflow->request_bkup = backup;
 	}
 
···
 	return ret;
 }
 
+bool mptcp_pm_nl_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc)
+{
+	struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);
+	struct mptcp_pm_addr_entry *entry;
+	bool backup = false;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) {
+		if (mptcp_addresses_equal(&entry->addr, skc, entry->addr.port)) {
+			backup = !!(entry->flags & MPTCP_PM_ADDR_FLAG_BACKUP);
+			break;
+		}
+	}
+	rcu_read_unlock();
+
+	return backup;
+}
+
 #define MPTCP_PM_CMD_GRP_OFFSET       0
 #define MPTCP_PM_EV_GRP_OFFSET        1
 
···
 	ret = remove_anno_list_by_saddr(msk, addr);
 	if (ret || force) {
 		spin_lock_bh(&msk->pm.lock);
+		msk->pm.add_addr_signaled -= ret;
 		mptcp_pm_remove_addr(msk, &list);
 		spin_unlock_bh(&msk->pm.lock);
 	}
···
 {
 	struct mptcp_rm_list alist = { .nr = 0 };
 	struct mptcp_pm_addr_entry *entry;
+	int anno_nr = 0;
 
 	list_for_each_entry(entry, rm_list, list) {
-		if ((remove_anno_list_by_saddr(msk, &entry->addr) ||
-		     lookup_subflow_by_saddr(&msk->conn_list, &entry->addr)) &&
-		    alist.nr < MPTCP_RM_IDS_MAX)
-			alist.ids[alist.nr++] = entry->addr.id;
+		if (alist.nr >= MPTCP_RM_IDS_MAX)
+			break;
+
+		/* only delete if either announced or matching a subflow */
+		if (remove_anno_list_by_saddr(msk, &entry->addr))
+			anno_nr++;
+		else if (!lookup_subflow_by_saddr(&msk->conn_list,
+						  &entry->addr))
+			continue;
+
+		alist.ids[alist.nr++] = entry->addr.id;
 	}
 
 	if (alist.nr) {
 		spin_lock_bh(&msk->pm.lock);
+		msk->pm.add_addr_signaled -= anno_nr;
 		mptcp_pm_remove_addr(msk, &alist);
 		spin_unlock_bh(&msk->pm.lock);
 	}
···
 	struct mptcp_pm_addr_entry *entry;
 
 	list_for_each_entry(entry, rm_list, list) {
-		if (lookup_subflow_by_saddr(&msk->conn_list, &entry->addr) &&
-		    slist.nr < MPTCP_RM_IDS_MAX)
+		if (slist.nr < MPTCP_RM_IDS_MAX &&
+		    lookup_subflow_by_saddr(&msk->conn_list, &entry->addr))
 			slist.ids[slist.nr++] = entry->addr.id;
 
-		if (remove_anno_list_by_saddr(msk, &entry->addr) &&
-		    alist.nr < MPTCP_RM_IDS_MAX)
+		if (alist.nr < MPTCP_RM_IDS_MAX &&
+		    remove_anno_list_by_saddr(msk, &entry->addr))
 			alist.ids[alist.nr++] = entry->addr.id;
 	}
 
 	if (alist.nr) {
 		spin_lock_bh(&msk->pm.lock);
+		msk->pm.add_addr_signaled -= alist.nr;
 		mptcp_pm_remove_addr(msk, &alist);
 		spin_unlock_bh(&msk->pm.lock);
 	}

net/mptcp/pm_userspace.c

···
 	return mptcp_userspace_pm_append_new_local_addr(msk, &new_entry, true);
 }
 
+bool mptcp_userspace_pm_is_backup(struct mptcp_sock *msk,
+				  struct mptcp_addr_info *skc)
+{
+	struct mptcp_pm_addr_entry *entry;
+	bool backup = false;
+
+	spin_lock_bh(&msk->pm.lock);
+	list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) {
+		if (mptcp_addresses_equal(&entry->addr, skc, false)) {
+			backup = !!(entry->flags & MPTCP_PM_ADDR_FLAG_BACKUP);
+			break;
+		}
+	}
+	spin_unlock_bh(&msk->pm.lock);
+
+	return backup;
+}
+
 int mptcp_pm_nl_announce_doit(struct sk_buff *skb, struct genl_info *info)
 {
 	struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN];

net/mptcp/protocol.c

···
 	skb_orphan(skb);
 
 	/* try to fetch required memory from subflow */
-	if (!mptcp_rmem_schedule(sk, ssk, skb->truesize))
+	if (!mptcp_rmem_schedule(sk, ssk, skb->truesize)) {
+		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED);
 		goto drop;
+	}
 
 	has_rxtstamp = TCP_SKB_CB(skb)->has_rxtstamp;
 
···
 		sk_rbuf = ssk_rbuf;
 
 	/* over limit? can't append more skbs to msk, Also, no need to wake-up*/
-	if (__mptcp_rmem(sk) > sk_rbuf) {
-		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED);
+	if (__mptcp_rmem(sk) > sk_rbuf)
 		return;
-	}
 
 	/* Wake-up the reader only for in-sequence data */
 	mptcp_data_lock(sk);
···
 	}
 
 	mptcp_for_each_subflow(msk, subflow) {
+		bool backup = subflow->backup || subflow->request_bkup;
+
 		trace_mptcp_subflow_get_send(subflow);
 		ssk =  mptcp_subflow_tcp_sock(subflow);
 		if (!mptcp_subflow_active(subflow))
 			continue;
 
 		tout = max(tout, mptcp_timeout_from_subflow(subflow));
-		nr_active += !subflow->backup;
+		nr_active += !backup;
 		pace = subflow->avg_pacing_rate;
 		if (unlikely(!pace)) {
 			/* init pacing rate from socket */
···
 		}
 
 		linger_time = div_u64((u64)READ_ONCE(ssk->sk_wmem_queued) << 32, pace);
-		if (linger_time < send_info[subflow->backup].linger_time) {
-			send_info[subflow->backup].ssk = ssk;
-			send_info[subflow->backup].linger_time = linger_time;
+		if (linger_time < send_info[backup].linger_time) {
+			send_info[backup].ssk = ssk;
+			send_info[backup].linger_time = linger_time;
 		}
 	}
 	__mptcp_set_timeout(sk, tout);

net/mptcp/protocol.h

···
 	u16	mp_capable : 1,
 		mp_join : 1,
 		backup : 1,
+		request_bkup : 1,
 		csum_reqd : 1,
 		allow_join_id0 : 1;
 	u8	local_id;
···
 int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc);
 int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc);
 int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc);
+bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc);
+bool mptcp_pm_nl_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc);
+bool mptcp_userspace_pm_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc);
 int mptcp_pm_dump_addr(struct sk_buff *msg, struct netlink_callback *cb);
 int mptcp_pm_nl_dump_addr(struct sk_buff *msg,
 			  struct netlink_callback *cb);

net/mptcp/subflow.c

···
 		return NULL;
 	}
 	subflow_req->local_id = local_id;
+	subflow_req->request_bkup = mptcp_pm_is_backup(msk, (struct sock_common *)req);
 
 	return msk;
 }
···
 			return 0;
 	} else if (opt_mp_join) {
 		SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNRX);
+
+		if (mp_opt.backup)
+			SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNBACKUPRX);
 	}
 
 	if (opt_mp_capable && listener->request_mptcp) {
···
 		subflow->mp_join = 1;
 		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKRX);
 
+		if (subflow->backup)
+			MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKBACKUPRX);
+
 		if (subflow_use_different_dport(msk, sk)) {
 			pr_debug("synack inet_dport=%d %d",
 				 ntohs(inet_sk(sk)->inet_dport),
···
 		return err;
 
 	subflow_set_local_id(subflow, err);
+	subflow->request_bkup = mptcp_pm_is_backup(msk, (struct sock_common *)sk);
+
 	return 0;
 }
 
···
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
 	bool fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN;
-	u32 incr;
+	struct tcp_sock *tp = tcp_sk(ssk);
+	u32 offset, incr, avail_len;
 
-	incr = limit >= skb->len ? skb->len + fin : limit;
+	offset = tp->copied_seq - TCP_SKB_CB(skb)->seq;
+	if (WARN_ON_ONCE(offset > skb->len))
+		goto out;
 
-	pr_debug("discarding=%d len=%d seq=%d", incr, skb->len,
-		 subflow->map_subflow_seq);
+	avail_len = skb->len - offset;
+	incr = limit >= avail_len ? avail_len + fin : limit;
+
+	pr_debug("discarding=%d len=%d offset=%d seq=%d", incr, skb->len,
+		 offset, subflow->map_subflow_seq);
 	MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DUPDATA);
 	tcp_sk(ssk)->copied_seq += incr;
+
+out:
 	if (!before(tcp_sk(ssk)->copied_seq, TCP_SKB_CB(skb)->end_seq))
 		sk_eat_skb(ssk, skb);
 	if (mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len)
···
 		new_ctx->fully_established = 1;
 		new_ctx->remote_key_valid = 1;
 		new_ctx->backup = subflow_req->backup;
+		new_ctx->request_bkup = subflow_req->request_bkup;
 		WRITE_ONCE(new_ctx->remote_id, subflow_req->remote_id);
 		new_ctx->token = subflow_req->token;
 		new_ctx->thmac = subflow_req->thmac;

net/sched/act_ct.c

···
 struct zones_ht_key {
 	struct net *net;
 	u16 zone;
+	/* Note : pad[] must be the last field. */
+	u8  pad[];
 };
 
 struct tcf_ct_flow_table {
···
 static const struct rhashtable_params zones_params = {
 	.head_offset = offsetof(struct tcf_ct_flow_table, node),
 	.key_offset = offsetof(struct tcf_ct_flow_table, key),
-	.key_len = sizeof_field(struct tcf_ct_flow_table, key),
+	.key_len = offsetof(struct zones_ht_key, pad),
 	.automatic_shrinking = true,
 };
 

net/smc/af_smc.c

···
 
 	rc = sock_create_kern(net, family, SOCK_STREAM, IPPROTO_TCP,
 			      &smc->clcsock);
-	if (rc) {
-		sk_common_release(sk);
+	if (rc)
 		return rc;
-	}
 
 	/* smc_clcsock_release() does not wait smc->clcsock->sk's
 	 * destruction;  its sk_state might not be TCP_CLOSE after
···
 		smc->clcsock = clcsock;
 	else
 		rc = smc_create_clcsk(net, sk, family);
+
+	if (rc)
+		sk_common_release(sk);
 out:
 	return rc;
 }

net/wireless/scan.c

···
 			       struct ieee80211_mgmt *mgmt, size_t len,
 			       gfp_t gfp)
 {
-	size_t min_hdr_len = offsetof(struct ieee80211_mgmt,
-				      u.probe_resp.variable);
+	size_t min_hdr_len;
 	struct ieee80211_ext *ext = NULL;
 	enum cfg80211_bss_frame_type ftype;
 	u16 beacon_interval;
···
 
 	if (ieee80211_is_s1g_beacon(mgmt->frame_control)) {
 		ext = (void *) mgmt;
-		min_hdr_len = offsetof(struct ieee80211_ext, u.s1g_beacon);
 		if (ieee80211_is_s1g_short_beacon(mgmt->frame_control))
 			min_hdr_len = offsetof(struct ieee80211_ext,
 					       u.s1g_short_beacon.variable);
+		else
+			min_hdr_len = offsetof(struct ieee80211_ext,
+					       u.s1g_beacon.variable);
+	} else {
+		/* same for beacons */
+		min_hdr_len = offsetof(struct ieee80211_mgmt,
+				       u.probe_resp.variable);
 	}
 
 	if (WARN_ON(len < min_hdr_len))

net/wireless/sme.c

···
 			cfg80211_hold_bss(
 				bss_from_pub(params->links[link].bss));
 		ev->cr.links[link].bss = params->links[link].bss;
+		ev->cr.links[link].status = params->links[link].status;
 
 		if (params->links[link].addr) {
 			ev->cr.links[link].addr = next;

tools/testing/selftests/bpf/Makefile

···
 # Make sure we are able to include and link libbpf against c++.
 $(OUTPUT)/test_cpp: test_cpp.cpp $(OUTPUT)/test_core_extern.skel.h $(BPFOBJ)
 	$(call msg,CXX,,$@)
-	$(Q)$(CXX) $(CFLAGS) $(filter %.a %.o %.cpp,$^) $(LDLIBS) -o $@
+	$(Q)$(CXX) $(subst -D_GNU_SOURCE=,,$(CFLAGS)) $(filter %.a %.o %.cpp,$^) $(LDLIBS) -o $@
 
 # Benchmark runner
 $(OUTPUT)/bench_%.o: benchs/bench_%.c bench.h $(BPFOBJ)

tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c

···
 	struct uprobe_syscall_executed *skel;
 	int pid, status, err, go[2], c;
 
-	if (ASSERT_OK(pipe(go), "pipe"))
+	if (!ASSERT_OK(pipe(go), "pipe"))
 		return;
 
 	skel = uprobe_syscall_executed__open_and_load();

tools/testing/selftests/drivers/net/hw/rss_ctx.py

···
     return [random.randint(0, 255) for _ in range(length)]
 
 
+def _rss_key_check(cfg, data=None, context=0):
+    if data is None:
+        data = get_rss(cfg, context=context)
+    if 'rss-hash-key' not in data:
+        return
+    non_zero = [x for x in data['rss-hash-key'] if x != 0]
+    ksft_eq(bool(non_zero), True, comment=f"RSS key is all zero {data['rss-hash-key']}")
+
+
 def get_rss(cfg, context=0):
     return ethtool(f"-x {cfg.ifname} context {context}", json=True)[0]
 
···
 def test_rss_key_indir(cfg):
     """Test basics like updating the main RSS key and indirection table."""
 
-    if len(_get_rx_cnts(cfg)) < 2:
-        KsftSkipEx("Device has only one queue (or doesn't support queue stats)")
+    qcnt = len(_get_rx_cnts(cfg))
+    if qcnt < 3:
+        KsftSkipEx("Device has fewer than 3 queues (or doesn't support queue stats)")
 
     data = get_rss(cfg)
     want_keys = ['rss-hash-key', 'rss-hash-function', 'rss-indirection-table']
···
         if not data[k]:
             raise KsftFailEx(f"ethtool results empty for '{k}': {data[k]}")
 
+    _rss_key_check(cfg, data=data)
     key_len = len(data['rss-hash-key'])
 
     # Set the key
···
     data = get_rss(cfg)
     ksft_eq(key, data['rss-hash-key'])
 
+    # Set the indirection table and the key together
+    key = _rss_key_rand(key_len)
+    ethtool(f"-X {cfg.ifname} equal 3 hkey " + _rss_key_str(key))
+    reset_indir = defer(ethtool, f"-X {cfg.ifname} default")
+
+    data = get_rss(cfg)
+    _rss_key_check(cfg, data=data)
+    ksft_eq(0, min(data['rss-indirection-table']))
+    ksft_eq(2, max(data['rss-indirection-table']))
+
+    # Reset indirection table and set the key
+    key = _rss_key_rand(key_len)
+    ethtool(f"-X {cfg.ifname} default hkey " + _rss_key_str(key))
+    data = get_rss(cfg)
+    _rss_key_check(cfg, data=data)
+    ksft_eq(0, min(data['rss-indirection-table']))
+    ksft_eq(qcnt - 1, max(data['rss-indirection-table']))
+
     # Set the indirection table
     ethtool(f"-X {cfg.ifname} equal 2")
-    reset_indir = defer(ethtool, f"-X {cfg.ifname} default")
     data = get_rss(cfg)
     ksft_eq(0, min(data['rss-indirection-table']))
     ksft_eq(1, max(data['rss-indirection-table']))
···
             ctx_cnt = i
             break
 
+        _rss_key_check(cfg, context=ctx_id)
+
         if not create_with_cfg:
             ethtool(f"-X {cfg.ifname} context {ctx_id} {want_cfg}")
+            _rss_key_check(cfg, context=ctx_id)
 
         # Sanity check the context we just created
         data = get_rss(cfg, ctx_id)

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

···
 		return 1;
 	}
 
-	if (--cfg_repeat > 0) {
-		if (cfg_input)
-			close(fd);
+	if (cfg_input)
+		close(fd);
+
+	if (--cfg_repeat > 0)
 		goto again;
-	}
 
 	return 0;
 }

tools/testing/selftests/net/mptcp/mptcp_join.sh

···
 	done
 
 	if [ -z "${id}" ]; then
-		test_fail "bad test - missing endpoint id"
+		fail_test "bad test - missing endpoint id"
 		return
 	fi
 
···
 {
 	local mp_prio_nr_tx=$1
 	local mp_prio_nr_rx=$2
+	local mpj_syn=$3
+	local mpj_syn_ack=$4
 	local count
 
 	print_check "ptx"
···
 		print_skip
 	elif [ "$count" != "$mp_prio_nr_rx" ]; then
 		fail_test "got $count MP_PRIO[s] RX expected $mp_prio_nr_rx"
+	else
+		print_ok
+	fi
+
+	print_check "syn backup"
+	count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPJoinSynBackupRx")
+	if [ -z "$count" ]; then
+		print_skip
+	elif [ "$count" != "$mpj_syn" ]; then
+		fail_test "got $count JOIN[s] syn with Backup expected $mpj_syn"
+	else
+		print_ok
+	fi
+
+	print_check "synack backup"
+	count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtMPJoinSynAckBackupRx")
+	if [ -z "$count" ]; then
+		print_skip
+	elif [ "$count" != "$mpj_syn_ack" ]; then
+		fail_test "got $count JOIN[s] synack with Backup expected $mpj_syn_ack"
 	else
 		print_ok
 	fi
···
 		sflags=nobackup speed=slow \
 			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 1 1 1
-		chk_prio_nr 0 1
+		chk_prio_nr 0 1 1 0
 	fi
 
 	# single address, backup
 	if reset "single address, backup" &&
+	   continue_if mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then
+		pm_nl_set_limits $ns1 0 1
+		pm_nl_add_endpoint $ns1 10.0.2.1 flags signal,backup
+		pm_nl_set_limits $ns2 1 1
+		sflags=nobackup speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
+		chk_join_nr 1 1 1
+		chk_add_nr 1 1
+		chk_prio_nr 1 0 0 1
+	fi
+
+	# single address, switch to backup
+	if reset "single address, switch to backup" &&
 	   continue_if mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then
 		pm_nl_set_limits $ns1 0 1
 		pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
···
 			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 1 1 1
 		chk_add_nr 1 1
-		chk_prio_nr 1 1
+		chk_prio_nr 1 1 0 0
 	fi
 
 	# single address with port, backup
 	if reset "single address with port, backup" &&
 	   continue_if mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then
 		pm_nl_set_limits $ns1 0 1
-		pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100
+		pm_nl_add_endpoint $ns1 10.0.2.1 flags signal,backup port 10100
 		pm_nl_set_limits $ns2 1 1
-		sflags=backup speed=slow \
+		sflags=nobackup speed=slow \
 			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 1 1 1
 		chk_add_nr 1 1
-		chk_prio_nr 1 1
+		chk_prio_nr 1 0 0 1
 	fi
 
 	if reset "mpc backup" &&
···
 		speed=slow \
 			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 0 0 0
-		chk_prio_nr 0 1
+		chk_prio_nr 0 1 0 0
 	fi
 
 	if reset "mpc backup both sides" &&
 	   continue_if mptcp_lib_kallsyms_doesnt_have "T mptcp_subflow_send_ack$"; then
-		pm_nl_add_endpoint $ns1 10.0.1.1 flags subflow,backup
+		pm_nl_set_limits $ns1 0 2
+		pm_nl_set_limits $ns2 1 2
+		pm_nl_add_endpoint $ns1 10.0.1.1 flags signal,backup
 		pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,backup
+
+		# 10.0.2.2 (non-backup) -> 10.0.1.1 (backup)
+		pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow
+		# 10.0.1.2 (backup) -> 10.0.2.1 (non-backup)
+		pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
+		ip -net "$ns2" route add 10.0.2.1 via 10.0.1.1 dev ns2eth1 # force this path
+
 		speed=slow \
 			run_tests $ns1 $ns2 10.0.1.1
-		chk_join_nr 0 0 0
-		chk_prio_nr 1 1
+		chk_join_nr 2 2 2
+		chk_prio_nr 1 1 1 1
 	fi
 
 	if reset "mpc switch to backup" &&
···
 		sflags=backup speed=slow \
 			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 0 0 0
-		chk_prio_nr 0 1
+		chk_prio_nr 0 1 0 0
 	fi
 
 	if reset "mpc switch to backup both sides" &&
···
 		sflags=backup speed=slow \
 			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 0 0 0
-		chk_prio_nr 1 1
+		chk_prio_nr 1 1 0 0
 	fi
 }
 
···
 		addr_nr_ns2=1 sflags=backup,fullmesh speed=slow \
 			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 2 2 2
-		chk_prio_nr 0 1
+		chk_prio_nr 0 1 1 0
 		chk_rm_nr 0 1
 	fi
 
···
 		sflags=nobackup,nofullmesh speed=slow \
 			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 2 2 2
-		chk_prio_nr 0 1
+		chk_prio_nr 0 1 1 0
 		chk_rm_nr 0 1
 	fi
 }
···
 		sflags=backup speed=slow \
 			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 1 1 0
-		chk_prio_nr 0 0
+		chk_prio_nr 0 0 0 0
 	fi
 
 	# userspace pm type prevents rm_addr
···
 		chk_mptcp_info subflows 1 subflows 1
 		mptcp_lib_kill_wait $tests_pid
 	fi
+
+	# remove and re-add
+	if reset "delete re-add signal" &&
+	   mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then
+		pm_nl_set_limits $ns1 1 1
+		pm_nl_set_limits $ns2 1 1
+		pm_nl_add_endpoint $ns1 10.0.2.1 id 1 flags signal
+		test_linkfail=4 speed=20 \
+			run_tests $ns1 $ns2 10.0.1.1 &
+		local tests_pid=$!
+
+		wait_mpj $ns2
+		pm_nl_check_endpoint "creation" \
+			$ns1 10.0.2.1 id 1 flags signal
+		chk_subflow_nr "before delete" 2
+		chk_mptcp_info subflows 1 subflows 1
+
+		pm_nl_del_endpoint $ns1 1 10.0.2.1
+		sleep 0.5
+		chk_subflow_nr "after delete" 1
+		chk_mptcp_info subflows 0 subflows 0
+
+		pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
+		wait_mpj $ns2
+		chk_subflow_nr "after re-add" 2
+		chk_mptcp_info subflows 1 subflows 1
+		mptcp_lib_kill_wait $tests_pid
+	fi
+
 }
 
 # [$1: error message]