Merge tag 'net-5.14-rc7' of git://git.kernel.org/pub/scm/linux/kernel…

…/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Networking fixes, including fixes from bpf, wireless and mac80211
  trees.

  Current release - regressions:

   - tipc: call tipc_wait_for_connect only when dlen is not 0

   - mac80211: fix locking in ieee80211_restart_work()

  Current release - new code bugs:

   - bpf: add rcu_read_lock in bpf_get_current_[ancestor_]cgroup_id()

   - ethernet: ice: fix perout start time rounding

   - wwan: iosm: prevent underflow in ipc_chnl_cfg_get()

  Previous releases - regressions:

   - bpf: clear zext_dst of dead insns

   - sch_cake: fix srchost/dsthost hashing mode

   - vrf: reset skb conntrack connection on VRF rcv

   - net/rds: dma_map_sg is entitled to merge entries

  Previous releases - always broken:

   - ethernet: bnxt: fix Tx path locking and races, add Rx path
     barriers"

* tag 'net-5.14-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (42 commits)
  net: dpaa2-switch: disable the control interface on error path
  Revert "flow_offload: action should not be NULL when it is referenced"
  iavf: Fix ping is lost after untrusted VF had tried to change MAC
  i40e: Fix ATR queue selection
  r8152: fix the maximum number of PLA bp for RTL8153C
  r8152: fix writing USB_BP2_EN
  mptcp: full fully established support after ADD_ADDR
  mptcp: fix memory leak on address flush
  net/rds: dma_map_sg is entitled to merge entries
  net: mscc: ocelot: allow forwarding from bridge ports to the tag_8021q CPU port
  net: asix: fix uninit value bugs
  ovs: clear skb->tstamp in forwarding path
  net: mdio-mux: Handle -EPROBE_DEFER correctly
  net: mdio-mux: Don't ignore memory allocation errors
  net: mdio-mux: Delete unnecessary devm_kfree
  net: dsa: sja1105: fix use-after-free after calling of_find_compatible_node, or worse
  sch_cake: fix srchost/dsthost hashing mode
  ixgbe, xsk: clean up the resources in ixgbe_xsk_pool_enable error path
  net: qlcnic: add missed unlock in qlcnic_83xx_flash_read32
  mac80211: fix locking in ieee80211_restart_work()
  ...

drivers/net/dsa/sja1105/sja1105_mdio.c

@@ -284,8 +284,7 @@ static int sja1105_mdiobus_base_tx_register(struct sja1105_private *priv,
 	struct mii_bus *bus;
 	int rc = 0;
 
-	np = of_find_compatible_node(mdio_node, NULL,
-				     "nxp,sja1110-base-tx-mdio");
+	np = of_get_compatible_child(mdio_node, "nxp,sja1110-base-tx-mdio");
 	if (!np)
 		return 0;
 
@@ -339,8 +338,7 @@ static int sja1105_mdiobus_base_t1_register(struct sja1105_private *priv,
 	struct mii_bus *bus;
 	int rc = 0;
 
-	np = of_find_compatible_node(mdio_node, NULL,
-				     "nxp,sja1110-base-t1-mdio");
+	np = of_get_compatible_child(mdio_node, "nxp,sja1110-base-t1-mdio");
 	if (!np)
 		return 0;
 

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

@@ -72,7 +72,8 @@
 #include "bnxt_debugfs.h"
 
 #define BNXT_TX_TIMEOUT		(5 * HZ)
-#define BNXT_DEF_MSG_ENABLE	(NETIF_MSG_DRV | NETIF_MSG_HW)
+#define BNXT_DEF_MSG_ENABLE	(NETIF_MSG_DRV | NETIF_MSG_HW | \
+				 NETIF_MSG_TX_ERR)
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Broadcom BCM573xx network driver");
@@ -365,6 +366,33 @@ static u16 bnxt_xmit_get_cfa_action(struct sk_buff *skb)
 	return md_dst->u.port_info.port_id;
 }
 
+static void bnxt_txr_db_kick(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
+			     u16 prod)
+{
+	bnxt_db_write(bp, &txr->tx_db, prod);
+	txr->kick_pending = 0;
+}
+
+static bool bnxt_txr_netif_try_stop_queue(struct bnxt *bp,
+					  struct bnxt_tx_ring_info *txr,
+					  struct netdev_queue *txq)
+{
+	netif_tx_stop_queue(txq);
+
+	/* netif_tx_stop_queue() must be done before checking
+	 * tx index in bnxt_tx_avail() below, because in
+	 * bnxt_tx_int(), we update tx index before checking for
+	 * netif_tx_queue_stopped().
+	 */
+	smp_mb();
+	if (bnxt_tx_avail(bp, txr) > bp->tx_wake_thresh) {
+		netif_tx_wake_queue(txq);
+		return false;
+	}
+
+	return true;
+}
+
 static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct bnxt *bp = netdev_priv(dev);
@@ -384,6 +412,7 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	i = skb_get_queue_mapping(skb);
 	if (unlikely(i >= bp->tx_nr_rings)) {
 		dev_kfree_skb_any(skb);
+		atomic_long_inc(&dev->tx_dropped);
 		return NETDEV_TX_OK;
 	}
 
@@ -393,8 +422,12 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	free_size = bnxt_tx_avail(bp, txr);
 	if (unlikely(free_size < skb_shinfo(skb)->nr_frags + 2)) {
-		netif_tx_stop_queue(txq);
-		return NETDEV_TX_BUSY;
+		/* We must have raced with NAPI cleanup */
+		if (net_ratelimit() && txr->kick_pending)
+			netif_warn(bp, tx_err, dev,
+				   "bnxt: ring busy w/ flush pending!\n");
+		if (bnxt_txr_netif_try_stop_queue(bp, txr, txq))
+			return NETDEV_TX_BUSY;
 	}
 
 	length = skb->len;
@@ -517,21 +550,16 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 normal_tx:
 	if (length < BNXT_MIN_PKT_SIZE) {
 		pad = BNXT_MIN_PKT_SIZE - length;
-		if (skb_pad(skb, pad)) {
+		if (skb_pad(skb, pad))
 			/* SKB already freed. */
-			tx_buf->skb = NULL;
-			return NETDEV_TX_OK;
-		}
+			goto tx_kick_pending;
 		length = BNXT_MIN_PKT_SIZE;
 	}
 
 	mapping = dma_map_single(&pdev->dev, skb->data, len, DMA_TO_DEVICE);
 
-	if (unlikely(dma_mapping_error(&pdev->dev, mapping))) {
-		dev_kfree_skb_any(skb);
-		tx_buf->skb = NULL;
-		return NETDEV_TX_OK;
-	}
+	if (unlikely(dma_mapping_error(&pdev->dev, mapping)))
+		goto tx_free;
 
 	dma_unmap_addr_set(tx_buf, mapping, mapping);
 	flags = (len << TX_BD_LEN_SHIFT) | TX_BD_TYPE_LONG_TX_BD |
@@ -618,24 +646,17 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	txr->tx_prod = prod;
 
 	if (!netdev_xmit_more() || netif_xmit_stopped(txq))
-		bnxt_db_write(bp, &txr->tx_db, prod);
+		bnxt_txr_db_kick(bp, txr, prod);
+	else
+		txr->kick_pending = 1;
 
 tx_done:
 
 	if (unlikely(bnxt_tx_avail(bp, txr) <= MAX_SKB_FRAGS + 1)) {
 		if (netdev_xmit_more() && !tx_buf->is_push)
-			bnxt_db_write(bp, &txr->tx_db, prod);
-
-		netif_tx_stop_queue(txq);
+			bnxt_txr_db_kick(bp, txr, prod);
 
-		/* netif_tx_stop_queue() must be done before checking
-		 * tx index in bnxt_tx_avail() below, because in
-		 * bnxt_tx_int(), we update tx index before checking for
-		 * netif_tx_queue_stopped().
-		 */
-		smp_mb();
-		if (bnxt_tx_avail(bp, txr) > bp->tx_wake_thresh)
-			netif_tx_wake_queue(txq);
+		bnxt_txr_netif_try_stop_queue(bp, txr, txq);
 	}
 	return NETDEV_TX_OK;
 
@@ -648,7 +669,6 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	/* start back at beginning and unmap skb */
 	prod = txr->tx_prod;
 	tx_buf = &txr->tx_buf_ring[prod];
-	tx_buf->skb = NULL;
 	dma_unmap_single(&pdev->dev, dma_unmap_addr(tx_buf, mapping),
 			 skb_headlen(skb), PCI_DMA_TODEVICE);
 	prod = NEXT_TX(prod);
@@ -662,7 +682,13 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 			       PCI_DMA_TODEVICE);
 	}
 
+tx_free:
 	dev_kfree_skb_any(skb);
+tx_kick_pending:
+	if (txr->kick_pending)
+		bnxt_txr_db_kick(bp, txr, txr->tx_prod);
+	txr->tx_buf_ring[txr->tx_prod].skb = NULL;
+	atomic_long_inc(&dev->tx_dropped);
 	return NETDEV_TX_OK;
 }
 
@@ -732,14 +758,9 @@ static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts)
 	smp_mb();
 
 	if (unlikely(netif_tx_queue_stopped(txq)) &&
-	    (bnxt_tx_avail(bp, txr) > bp->tx_wake_thresh)) {
-		__netif_tx_lock(txq, smp_processor_id());
-		if (netif_tx_queue_stopped(txq) &&
-		    bnxt_tx_avail(bp, txr) > bp->tx_wake_thresh &&
-		    txr->dev_state != BNXT_DEV_STATE_CLOSING)
-			netif_tx_wake_queue(txq);
-		__netif_tx_unlock(txq);
-	}
+	    bnxt_tx_avail(bp, txr) > bp->tx_wake_thresh &&
+	    READ_ONCE(txr->dev_state) != BNXT_DEV_STATE_CLOSING)
+		netif_tx_wake_queue(txq);
 }
 
 static struct page *__bnxt_alloc_rx_page(struct bnxt *bp, dma_addr_t *mapping,
@@ -1767,6 +1788,10 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	if (!RX_CMP_VALID(rxcmp1, tmp_raw_cons))
 		return -EBUSY;
 
+	/* The valid test of the entry must be done first before
+	 * reading any further.
+	 */
+	dma_rmb();
 	prod = rxr->rx_prod;
 
 	if (cmp_type == CMP_TYPE_RX_L2_TPA_START_CMP) {
@@ -1989,6 +2014,10 @@ static int bnxt_force_rx_discard(struct bnxt *bp,
 	if (!RX_CMP_VALID(rxcmp1, tmp_raw_cons))
 		return -EBUSY;
 
+	/* The valid test of the entry must be done first before
+	 * reading any further.
+	 */
+	dma_rmb();
 	cmp_type = RX_CMP_TYPE(rxcmp);
 	if (cmp_type == CMP_TYPE_RX_L2_CMP) {
 		rxcmp1->rx_cmp_cfa_code_errors_v2 |=
@@ -2454,6 +2483,10 @@ static int bnxt_poll_nitroa0(struct napi_struct *napi, int budget)
 		if (!TX_CMP_VALID(txcmp, raw_cons))
 			break;
 
+		/* The valid test of the entry must be done first before
+		 * reading any further.
+		 */
+		dma_rmb();
 		if ((TX_CMP_TYPE(txcmp) & 0x30) == 0x10) {
 			tmp_raw_cons = NEXT_RAW_CMP(raw_cons);
 			cp_cons = RING_CMP(tmp_raw_cons);
@@ -9128,10 +9161,9 @@ static void bnxt_disable_napi(struct bnxt *bp)
 	for (i = 0; i < bp->cp_nr_rings; i++) {
 		struct bnxt_cp_ring_info *cpr = &bp->bnapi[i]->cp_ring;
 
+		napi_disable(&bp->bnapi[i]->napi);
 		if (bp->bnapi[i]->rx_ring)
 			cancel_work_sync(&cpr->dim.work);
-
-		napi_disable(&bp->bnapi[i]->napi);
 	}
 }
 
@@ -9165,9 +9197,11 @@ void bnxt_tx_disable(struct bnxt *bp)
 	if (bp->tx_ring) {
 		for (i = 0; i < bp->tx_nr_rings; i++) {
 			txr = &bp->tx_ring[i];
-			txr->dev_state = BNXT_DEV_STATE_CLOSING;
+			WRITE_ONCE(txr->dev_state, BNXT_DEV_STATE_CLOSING);
 		}
 	}
+	/* Make sure napi polls see @dev_state change */
+	synchronize_net();
 	/* Drop carrier first to prevent TX timeout */
 	netif_carrier_off(bp->dev);
 	/* Stop all TX queues */
@@ -9181,8 +9215,10 @@ void bnxt_tx_enable(struct bnxt *bp)
 
 	for (i = 0; i < bp->tx_nr_rings; i++) {
 		txr = &bp->tx_ring[i];
-		txr->dev_state = 0;
+		WRITE_ONCE(txr->dev_state, 0);
 	}
+	/* Make sure napi polls see @dev_state change */
+	synchronize_net();
 	netif_tx_wake_all_queues(bp->dev);
 	if (bp->link_info.link_up)
 		netif_carrier_on(bp->dev);
@@ -10768,6 +10804,9 @@ static bool bnxt_rfs_supported(struct bnxt *bp)
 			return true;
 		return false;
 	}
+	/* 212 firmware is broken for aRFS */
+	if (BNXT_FW_MAJ(bp) == 212)
+		return false;
 	if (BNXT_PF(bp) && !BNXT_CHIP_TYPE_NITRO_A0(bp))
 		return true;
 	if (bp->flags & BNXT_FLAG_NEW_RSS_CAP)

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

@@ -786,6 +786,7 @@ struct bnxt_tx_ring_info {
 	u16			tx_prod;
 	u16			tx_cons;
 	u16			txq_index;
+	u8			kick_pending;
 	struct bnxt_db_info	tx_db;
 
 	struct tx_bd		*tx_desc_ring[MAX_TX_PAGES];

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

@@ -3038,26 +3038,30 @@ static int dpaa2_switch_port_init(struct ethsw_port_priv *port_priv, u16 port)
 	return err;
 }
 
-static void dpaa2_switch_takedown(struct fsl_mc_device *sw_dev)
+static void dpaa2_switch_ctrl_if_teardown(struct ethsw_core *ethsw)
+{
+	dpsw_ctrl_if_disable(ethsw->mc_io, 0, ethsw->dpsw_handle);
+	dpaa2_switch_free_dpio(ethsw);
+	dpaa2_switch_destroy_rings(ethsw);
+	dpaa2_switch_drain_bp(ethsw);
+	dpaa2_switch_free_dpbp(ethsw);
+}
+
+static void dpaa2_switch_teardown(struct fsl_mc_device *sw_dev)
 {
 	struct device *dev = &sw_dev->dev;
 	struct ethsw_core *ethsw = dev_get_drvdata(dev);
 	int err;
 
+	dpaa2_switch_ctrl_if_teardown(ethsw);
+
+	destroy_workqueue(ethsw->workqueue);
+
 	err = dpsw_close(ethsw->mc_io, 0, ethsw->dpsw_handle);
 	if (err)
 		dev_warn(dev, "dpsw_close err %d\n", err);
 }
 
-static void dpaa2_switch_ctrl_if_teardown(struct ethsw_core *ethsw)
-{
-	dpsw_ctrl_if_disable(ethsw->mc_io, 0, ethsw->dpsw_handle);
-	dpaa2_switch_free_dpio(ethsw);
-	dpaa2_switch_destroy_rings(ethsw);
-	dpaa2_switch_drain_bp(ethsw);
-	dpaa2_switch_free_dpbp(ethsw);
-}
-
 static int dpaa2_switch_remove(struct fsl_mc_device *sw_dev)
 {
 	struct ethsw_port_priv *port_priv;
@@ -3068,8 +3072,6 @@ static int dpaa2_switch_remove(struct fsl_mc_device *sw_dev)
 	dev = &sw_dev->dev;
 	ethsw = dev_get_drvdata(dev);
 
-	dpaa2_switch_ctrl_if_teardown(ethsw);
-
 	dpaa2_switch_teardown_irqs(sw_dev);
 
 	dpsw_disable(ethsw->mc_io, 0, ethsw->dpsw_handle);
@@ -3084,9 +3086,7 @@ static int dpaa2_switch_remove(struct fsl_mc_device *sw_dev)
 	kfree(ethsw->acls);
 	kfree(ethsw->ports);
 
-	dpaa2_switch_takedown(sw_dev);
-
-	destroy_workqueue(ethsw->workqueue);
+	dpaa2_switch_teardown(sw_dev);
 
 	fsl_mc_portal_free(ethsw->mc_io);
 
@@ -3199,7 +3199,7 @@ static int dpaa2_switch_probe(struct fsl_mc_device *sw_dev)
 			       GFP_KERNEL);
 	if (!(ethsw->ports)) {
 		err = -ENOMEM;
-		goto err_takedown;
+		goto err_teardown;
 	}
 
 	ethsw->fdbs = kcalloc(ethsw->sw_attr.num_ifs, sizeof(*ethsw->fdbs),
@@ -3270,8 +3270,8 @@ static int dpaa2_switch_probe(struct fsl_mc_device *sw_dev)
 err_free_ports:
 	kfree(ethsw->ports);
 
-err_takedown:
-	dpaa2_switch_takedown(sw_dev);
+err_teardown:
+	dpaa2_switch_teardown(sw_dev);
 
 err_free_cmdport:
 	fsl_mc_portal_free(ethsw->mc_io);

drivers/net/ethernet/intel/i40e/i40e_txrx.c

@@ -3663,8 +3663,7 @@ u16 i40e_lan_select_queue(struct net_device *netdev,
 
 	/* is DCB enabled at all? */
 	if (vsi->tc_config.numtc == 1)
-		return i40e_swdcb_skb_tx_hash(netdev, skb,
-					      netdev->real_num_tx_queues);
+		return netdev_pick_tx(netdev, skb, sb_dev);
 
 	prio = skb->priority;
 	hw = &vsi->back->hw;

drivers/net/ethernet/intel/iavf/iavf.h

@@ -136,6 +136,7 @@ struct iavf_q_vector {
 struct iavf_mac_filter {
 	struct list_head list;
 	u8 macaddr[ETH_ALEN];
+	bool is_new_mac;	/* filter is new, wait for PF decision */
 	bool remove;		/* filter needs to be removed */
 	bool add;		/* filter needs to be added */
 };

drivers/net/ethernet/intel/iavf/iavf_main.c

@@ -751,6 +751,7 @@ struct iavf_mac_filter *iavf_add_filter(struct iavf_adapter *adapter,
 
 		list_add_tail(&f->list, &adapter->mac_filter_list);
 		f->add = true;
+		f->is_new_mac = true;
 		adapter->aq_required |= IAVF_FLAG_AQ_ADD_MAC_FILTER;
 	} else {
 		f->remove = false;