Merge tag 'net-5.11-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Networking fixes for 5.11-rc7, including fixes from bpf and mac80211
  trees.

  Current release - regressions:

   - ip_tunnel: fix mtu calculation

   - mlx5: fix function calculation for page trees

  Previous releases - regressions:

   - vsock: fix the race conditions in multi-transport support

   - neighbour: prevent a dead entry from updating gc_list

   - dsa: mv88e6xxx: override existent unicast portvec in port_fdb_add

  Previous releases - always broken:

   - bpf, cgroup: two copy_{from,to}_user() warn_on_once splats for BPF
     cgroup getsockopt infra when user space is trying to race against
     optlen, from Loris Reiff.

   - bpf: add missing fput() in BPF inode storage map update helper

   - udp: ipv4: manipulate network header of NATed UDP GRO fraglist

   - mac80211: fix station rate table updates on assoc

   - r8169: work around RTL8125 UDP HW bug

   - igc: report speed and duplex as unknown when device is runtime
     suspended

   - rxrpc: fix deadlock around release of dst cached on udp tunnel"

* tag 'net-5.11-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (36 commits)
  net: hsr: align sup_multicast_addr in struct hsr_priv to u16 boundary
  net: ipa: fix two format specifier errors
  net: ipa: use the right accessor in ipa_endpoint_status_skip()
  net: ipa: be explicit about endianness
  net: ipa: add a missing __iomem attribute
  net: ipa: pass correct dma_handle to dma_free_coherent()
  r8169: fix WoL on shutdown if CONFIG_DEBUG_SHIRQ is set
  net/rds: restrict iovecs length for RDS_CMSG_RDMA_ARGS
  net: mvpp2: TCAM entry enable should be written after SRAM data
  net: lapb: Copy the skb before sending a packet
  net/mlx5e: Release skb in case of failure in tc update skb
  net/mlx5e: Update max_opened_tc also when channels are closed
  net/mlx5: Fix leak upon failure of rule creation
  net/mlx5: Fix function calculation for page trees
  docs: networking: swap words in icmp_errors_use_inbound_ifaddr doc
  udp: ipv4: manipulate network header of NATed UDP GRO fraglist
  net: ip_tunnel: fix mtu calculation
  vsock: fix the race conditions in multi-transport support
  net: sched: replaced invalid qdisc tree flush helper in qdisc_replace
  ibmvnic: device remove has higher precedence over reset
  ...

Documentation/networking/ip-sysctl.rst

@@ -1196,7 +1196,7 @@ icmp_errors_use_inbound_ifaddr - BOOLEAN
 
 	If non-zero, the message will be sent with the primary address of
 	the interface that received the packet that caused the icmp error.
-	This is the behaviour network many administrators will expect from
+	This is the behaviour many network administrators will expect from
 	a router. And it can make debugging complicated network layouts
 	much easier.
 

drivers/net/arcnet/arc-rimi.c

@@ -332,7 +332,7 @@ static int __init arc_rimi_init(void)
 		dev->irq = 9;
 
 	if (arcrimi_probe(dev)) {
-		free_netdev(dev);
+		free_arcdev(dev);
 		return -EIO;
 	}
 
@@ -349,7 +349,7 @@ static void __exit arc_rimi_exit(void)
 	iounmap(lp->mem_start);
 	release_mem_region(dev->mem_start, dev->mem_end - dev->mem_start + 1);
 	free_irq(dev->irq, dev);
-	free_netdev(dev);
+	free_arcdev(dev);
 }
 
 #ifndef MODULE

drivers/net/arcnet/arcdevice.h

@@ -298,6 +298,10 @@ struct arcnet_local {
 
 	int excnak_pending;    /* We just got an excesive nak interrupt */
 
+	/* RESET flag handling */
+	int reset_in_progress;
+	struct work_struct reset_work;
+
 	struct {
 		uint16_t sequence;	/* sequence number (incs with each packet) */
 		__be16 aborted_seq;
@@ -350,7 +354,9 @@ void arcnet_dump_skb(struct net_device *dev, struct sk_buff *skb, char *desc)
 
 void arcnet_unregister_proto(struct ArcProto *proto);
 irqreturn_t arcnet_interrupt(int irq, void *dev_id);
+
 struct net_device *alloc_arcdev(const char *name);
+void free_arcdev(struct net_device *dev);
 
 int arcnet_open(struct net_device *dev);
 int arcnet_close(struct net_device *dev);

drivers/net/arcnet/arcnet.c

@@ -387,10 +387,44 @@ static void arcnet_timer(struct timer_list *t)
 	struct arcnet_local *lp = from_timer(lp, t, timer);
 	struct net_device *dev = lp->dev;
 
-	if (!netif_carrier_ok(dev)) {
+	spin_lock_irq(&lp->lock);
+
+	if (!lp->reset_in_progress && !netif_carrier_ok(dev)) {
 		netif_carrier_on(dev);
 		netdev_info(dev, "link up\n");
 	}
+
+	spin_unlock_irq(&lp->lock);
+}
+
+static void reset_device_work(struct work_struct *work)
+{
+	struct arcnet_local *lp;
+	struct net_device *dev;
+
+	lp = container_of(work, struct arcnet_local, reset_work);
+	dev = lp->dev;
+
+	/* Do not bring the network interface back up if an ifdown
+	 * was already done.
+	 */
+	if (!netif_running(dev) || !lp->reset_in_progress)
+		return;
+
+	rtnl_lock();
+
+	/* Do another check, in case of an ifdown that was triggered in
+	 * the small race window between the exit condition above and
+	 * acquiring RTNL.
+	 */
+	if (!netif_running(dev) || !lp->reset_in_progress)
+		goto out;
+
+	dev_close(dev);
+	dev_open(dev, NULL);
+
+out:
+	rtnl_unlock();
 }
 
 static void arcnet_reply_tasklet(unsigned long data)
@@ -452,12 +486,25 @@ struct net_device *alloc_arcdev(const char *name)
 		lp->dev = dev;
 		spin_lock_init(&lp->lock);
 		timer_setup(&lp->timer, arcnet_timer, 0);
+		INIT_WORK(&lp->reset_work, reset_device_work);
 	}
 
 	return dev;
 }
 EXPORT_SYMBOL(alloc_arcdev);
 
+void free_arcdev(struct net_device *dev)
+{
+	struct arcnet_local *lp = netdev_priv(dev);
+
+	/* Do not cancel this at ->ndo_close(), as the workqueue itself
+	 * indirectly calls the ifdown path through dev_close().
+	 */
+	cancel_work_sync(&lp->reset_work);
+	free_netdev(dev);
+}
+EXPORT_SYMBOL(free_arcdev);
+
 /* Open/initialize the board.  This is called sometime after booting when
  * the 'ifconfig' program is run.
  *
@@ -587,6 +634,10 @@ int arcnet_close(struct net_device *dev)
 
 	/* shut down the card */
 	lp->hw.close(dev);
+
+	/* reset counters */
+	lp->reset_in_progress = 0;
+
 	module_put(lp->hw.owner);
 	return 0;
 }
@@ -820,6 +871,9 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id)
 
 	spin_lock_irqsave(&lp->lock, flags);
 
+	if (lp->reset_in_progress)
+		goto out;
+
 	/* RESET flag was enabled - if device is not running, we must
 	 * clear it right away (but nothing else).
 	 */
@@ -852,11 +906,14 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id)
 		if (status & RESETflag) {
 			arc_printk(D_NORMAL, dev, "spurious reset (status=%Xh)\n",
 				   status);
-			arcnet_close(dev);
-			arcnet_open(dev);
+
+			lp->reset_in_progress = 1;
+			netif_stop_queue(dev);
+			netif_carrier_off(dev);
+			schedule_work(&lp->reset_work);
 
 			/* get out of the interrupt handler! */
-			break;
+			goto out;
 		}
 		/* RX is inhibited - we must have received something.
 		 * Prepare to receive into the next buffer.
@@ -1052,6 +1109,7 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id)
 	udelay(1);
 	lp->hw.intmask(dev, lp->intmask);
 
+out:
 	spin_unlock_irqrestore(&lp->lock, flags);
 	return retval;
 }

drivers/net/arcnet/com20020-isa.c

@@ -169,7 +169,7 @@ static int __init com20020_init(void)
 		dev->irq = 9;
 
 	if (com20020isa_probe(dev)) {
-		free_netdev(dev);
+		free_arcdev(dev);
 		return -EIO;
 	}
 
@@ -182,7 +182,7 @@ static void __exit com20020_exit(void)
 	unregister_netdev(my_dev);
 	free_irq(my_dev->irq, my_dev);
 	release_region(my_dev->base_addr, ARCNET_TOTAL_SIZE);
-	free_netdev(my_dev);
+	free_arcdev(my_dev);
 }
 
 #ifndef MODULE

drivers/net/arcnet/com20020-pci.c

@@ -291,7 +291,7 @@ static void com20020pci_remove(struct pci_dev *pdev)
 
 		unregister_netdev(dev);
 		free_irq(dev->irq, dev);
-		free_netdev(dev);
+		free_arcdev(dev);
 	}
 }
 

drivers/net/arcnet/com20020_cs.c

@@ -177,7 +177,7 @@ static void com20020_detach(struct pcmcia_device *link)
 		dev = info->dev;
 		if (dev) {
 			dev_dbg(&link->dev, "kfree...\n");
-			free_netdev(dev);
+			free_arcdev(dev);
 		}
 		dev_dbg(&link->dev, "kfree2...\n");
 		kfree(info);

drivers/net/arcnet/com90io.c

@@ -396,7 +396,7 @@ static int __init com90io_init(void)
 	err = com90io_probe(dev);
 
 	if (err) {
-		free_netdev(dev);
+		free_arcdev(dev);
 		return err;
 	}
 
@@ -419,7 +419,7 @@ static void __exit com90io_exit(void)
 
 	free_irq(dev->irq, dev);
 	release_region(dev->base_addr, ARCNET_TOTAL_SIZE);
-	free_netdev(dev);
+	free_arcdev(dev);
 }
 
 module_init(com90io_init)

drivers/net/arcnet/com90xx.c

@@ -554,7 +554,7 @@ err_free_irq:
 err_release_mem:
 	release_mem_region(dev->mem_start, dev->mem_end - dev->mem_start + 1);
 err_free_dev:
-	free_netdev(dev);
+	free_arcdev(dev);
 	return -EIO;
 }
 
@@ -672,7 +672,7 @@ static void __exit com90xx_exit(void)
 		release_region(dev->base_addr, ARCNET_TOTAL_SIZE);
 		release_mem_region(dev->mem_start,
 				   dev->mem_end - dev->mem_start + 1);
-		free_netdev(dev);
+		free_arcdev(dev);
 	}
 }
 

drivers/net/dsa/mv88e6xxx/chip.c

@@ -1676,7 +1676,11 @@ static int mv88e6xxx_port_db_load_purge(struct mv88e6xxx_chip *chip, int port,
 		if (!entry.portvec)
 			entry.state = 0;
 	} else {
-		entry.portvec |= BIT(port);
+		if (state == MV88E6XXX_G1_ATU_DATA_STATE_UC_STATIC)
+			entry.portvec = BIT(port);
+		else
+			entry.portvec |= BIT(port);
+
 		entry.state = state;
 	}
 

drivers/net/ethernet/ibm/ibmvnic.c

@@ -5444,11 +5444,6 @@ static int ibmvnic_remove(struct vio_dev *dev)
 	unsigned long flags;
 
 	spin_lock_irqsave(&adapter->state_lock, flags);
-	if (test_bit(0, &adapter->resetting)) {
-		spin_unlock_irqrestore(&adapter->state_lock, flags);
-		return -EBUSY;
-	}
-
 	adapter->state = VNIC_REMOVING;
 	spin_unlock_irqrestore(&adapter->state_lock, flags);
 

drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c

@@ -55,12 +55,7 @@ static void i40e_vc_notify_vf_link_state(struct i40e_vf *vf)
 
 	pfe.event = VIRTCHNL_EVENT_LINK_CHANGE;
 	pfe.severity = PF_EVENT_SEVERITY_INFO;
-
-	/* Always report link is down if the VF queues aren't enabled */
-	if (!vf->queues_enabled) {
-		pfe.event_data.link_event.link_status = false;
-		pfe.event_data.link_event.link_speed = 0;
-	} else if (vf->link_forced) {
+	if (vf->link_forced) {
 		pfe.event_data.link_event.link_status = vf->link_up;
 		pfe.event_data.link_event.link_speed =
 			(vf->link_up ? i40e_virtchnl_link_speed(ls->link_speed) : 0);
@@ -70,7 +65,6 @@ static void i40e_vc_notify_vf_link_state(struct i40e_vf *vf)
 		pfe.event_data.link_event.link_speed =
 			i40e_virtchnl_link_speed(ls->link_speed);
 	}
-
 	i40e_aq_send_msg_to_vf(hw, abs_vf_id, VIRTCHNL_OP_EVENT,
 			       0, (u8 *)&pfe, sizeof(pfe), NULL);
 }
@@ -2443,8 +2437,6 @@ static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg)
 		}
 	}
 
-	vf->queues_enabled = true;
-
 error_param:
 	/* send the response to the VF */
 	return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_ENABLE_QUEUES,
@@ -2466,9 +2458,6 @@ static int i40e_vc_disable_queues_msg(struct i40e_vf *vf, u8 *msg)
 	struct i40e_pf *pf = vf->pf;
 	i40e_status aq_ret = 0;
 
-	/* Immediately mark queues as disabled */
-	vf->queues_enabled = false;
-
 	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
 		aq_ret = I40E_ERR_PARAM;
 		goto error_param;

drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h

@@ -98,7 +98,6 @@ struct i40e_vf {
 	unsigned int tx_rate;	/* Tx bandwidth limit in Mbps */
 	bool link_forced;
 	bool link_up;		/* only valid if VF link is forced */
-	bool queues_enabled;	/* true if the VF queues are enabled */
 	bool spoofchk;
 	u16 num_vlan;
 

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

@@ -1714,7 +1714,8 @@ static int igc_ethtool_get_link_ksettings(struct net_device *netdev,
 						     Asym_Pause);
 	}
 
-	status = rd32(IGC_STATUS);
+	status = pm_runtime_suspended(&adapter->pdev->dev) ?
+		 0 : rd32(IGC_STATUS);
 
 	if (status & IGC_STATUS_LU) {
 		if (status & IGC_STATUS_SPEED_1000) {

drivers/net/ethernet/intel/igc/igc_i225.c

@@ -219,9 +219,9 @@ static s32 igc_write_nvm_srwr(struct igc_hw *hw, u16 offset, u16 words,
 			      u16 *data)
 {
 	struct igc_nvm_info *nvm = &hw->nvm;
+	s32 ret_val = -IGC_ERR_NVM;
 	u32 attempts = 100000;
 	u32 i, k, eewr = 0;
-	s32 ret_val = 0;
 
 	/* A check for invalid values:  offset too large, too many words,
 	 * too many words for the offset, and not enough words.
@@ -229,7 +229,6 @@ static s32 igc_write_nvm_srwr(struct igc_hw *hw, u16 offset, u16 words,
 	if (offset >= nvm->word_size || (words > (nvm->word_size - offset)) ||
 	    words == 0) {
 		hw_dbg("nvm parameter(s) out of bounds\n");
-		ret_val = -IGC_ERR_NVM;
 		goto out;
 	}
 

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

@@ -638,7 +638,7 @@ s32 igc_config_fc_after_link_up(struct igc_hw *hw)
 	}
 
 out:
-	return 0;
+	return ret_val;
 }
 
 /**

drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c

@@ -29,16 +29,16 @@ static int mvpp2_prs_hw_write(struct mvpp2 *priv, struct mvpp2_prs_entry *pe)
 	/* Clear entry invalidation bit */
 	pe->tcam[MVPP2_PRS_TCAM_INV_WORD] &= ~MVPP2_PRS_TCAM_INV_MASK;
 
-	/* Write tcam index - indirect access */
-	mvpp2_write(priv, MVPP2_PRS_TCAM_IDX_REG, pe->index);
-	for (i = 0; i < MVPP2_PRS_TCAM_WORDS; i++)
-		mvpp2_write(priv, MVPP2_PRS_TCAM_DATA_REG(i), pe->tcam[i]);
-
 	/* Write sram index - indirect access */
 	mvpp2_write(priv, MVPP2_PRS_SRAM_IDX_REG, pe->index);
 	for (i = 0; i < MVPP2_PRS_SRAM_WORDS; i++)
 		mvpp2_write(priv, MVPP2_PRS_SRAM_DATA_REG(i), pe->sram[i]);
 
+	/* Write tcam index - indirect access */
+	mvpp2_write(priv, MVPP2_PRS_TCAM_IDX_REG, pe->index);
+	for (i = 0; i < MVPP2_PRS_TCAM_WORDS; i++)
+		mvpp2_write(priv, MVPP2_PRS_TCAM_DATA_REG(i), pe->tcam[i]);
+
 	return 0;
 }
 

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

@@ -3627,12 +3627,10 @@ static int mlx5e_setup_tc_mqprio(struct mlx5e_priv *priv,
 
 	err = mlx5e_safe_switch_channels(priv, &new_channels,
 					 mlx5e_num_channels_changed_ctx, NULL);
-	if (err)
-		goto out;
 
-	priv->max_opened_tc = max_t(u8, priv->max_opened_tc,
-				    new_channels.params.num_tc);
 out:
+	priv->max_opened_tc = max_t(u8, priv->max_opened_tc,
+				    priv->channels.params.num_tc);
 	mutex_unlock(&priv->state_lock);
 	return err;
 }

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

@@ -1262,8 +1262,10 @@ static void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 	mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
 
 	if (mlx5e_cqe_regb_chain(cqe))
-		if (!mlx5e_tc_update_skb(cqe, skb))
+		if (!mlx5e_tc_update_skb(cqe, skb)) {
+			dev_kfree_skb_any(skb);
 			goto free_wqe;
+		}
 
 	napi_gro_receive(rq->cq.napi, skb);
 
@@ -1316,8 +1318,10 @@ static void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 	if (rep->vlan && skb_vlan_tag_present(skb))
 		skb_vlan_pop(skb);
 
-	if (!mlx5e_rep_tc_update_skb(cqe, skb, &tc_priv))
+	if (!mlx5e_rep_tc_update_skb(cqe, skb, &tc_priv)) {
+		dev_kfree_skb_any(skb);
 		goto free_wqe;
+	}
 
 	napi_gro_receive(rq->cq.napi, skb);
 
@@ -1371,8 +1375,10 @@ static void mlx5e_handle_rx_cqe_mpwrq_rep(struct mlx5e_rq *rq, struct mlx5_cqe64
 
 	mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
 
-	if (!mlx5e_rep_tc_update_skb(cqe, skb, &tc_priv))
+	if (!mlx5e_rep_tc_update_skb(cqe, skb, &tc_priv)) {
+		dev_kfree_skb_any(skb);
 		goto mpwrq_cqe_out;
+	}
 
 	napi_gro_receive(rq->cq.napi, skb);
 
@@ -1528,8 +1534,10 @@ static void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cq
 	mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
 
 	if (mlx5e_cqe_regb_chain(cqe))
-		if (!mlx5e_tc_update_skb(cqe, skb))
+		if (!mlx5e_tc_update_skb(cqe, skb)) {
+			dev_kfree_skb_any(skb);
 			goto mpwrq_cqe_out;
+		}
 
 	napi_gro_receive(rq->cq.napi, skb);
 

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

@@ -1760,6 +1760,7 @@ search_again_locked:
 		if (!fte_tmp)
 			continue;
 		rule = add_rule_fg(g, spec, flow_act, dest, dest_num, fte_tmp);
+		/* No error check needed here, because insert_fte() is not called */
 		up_write_ref_node(&fte_tmp->node, false);
 		tree_put_node(&fte_tmp->node, false);
 		kmem_cache_free(steering->ftes_cache, fte);
@@ -1812,6 +1813,8 @@ skip_search:
 		up_write_ref_node(&g->node, false);
 		rule = add_rule_fg(g, spec, flow_act, dest, dest_num, fte);
 		up_write_ref_node(&fte->node, false);
+		if (IS_ERR(rule))
+			tree_put_node(&fte->node, false);
 		return rule;
 	}
 	rule = ERR_PTR(-ENOENT);
@@ -1910,6 +1913,8 @@ search_again_locked:
 	up_write_ref_node(&g->node, false);
 	rule = add_rule_fg(g, spec, flow_act, dest, dest_num, fte);
 	up_write_ref_node(&fte->node, false);
+	if (IS_ERR(rule))
+		tree_put_node(&fte->node, false);
 	tree_put_node(&g->node, false);
 	return rule;