Merge tag 'net-6.13-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

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

  Current release - regressions:

   - rtnetlink: try the outer netns attribute in rtnl_get_peer_net()

   - rust: net::phy fix module autoloading

  Current release - new code bugs:

   - phy: avoid undefined behavior in *_led_polarity_set()

   - eth: octeontx2-pf: fix netdev memory leak in rvu_rep_create()

  Previous releases - regressions:

   - smc: check sndbuf_space again after NOSPACE flag is set in smc_poll

   - ipvs: fix clamp() of ip_vs_conn_tab on small memory systems

   - dsa: restore dsa_software_vlan_untag() ability to operate on
     VLAN-untagged traffic

   - eth:
       - tun: fix tun_napi_alloc_frags()
       - ionic: no double destroy workqueue
       - idpf: trigger SW interrupt when exiting wb_on_itr mode
       - rswitch: rework ts tags management
       - team: fix feature exposure when no ports are present

  Previous releases - always broken:

   - core: fix repeated netlink messages in queue dump

   - mdiobus: fix an OF node reference leak

   - smc: check iparea_offset and ipv6_prefixes_cnt when receiving
     proposal msg

   - can: fix missed interrupts with m_can_pci

   - eth: oa_tc6: fix infinite loop error when tx credits becomes 0"

* tag 'net-6.13-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (45 commits)
  net: mctp: handle skb cleanup on sock_queue failures
  net: mdiobus: fix an OF node reference leak
  octeontx2-pf: fix error handling of devlink port in rvu_rep_create()
  octeontx2-pf: fix netdev memory leak in rvu_rep_create()
  psample: adjust size if rate_as_probability is set
  netdev-genl: avoid empty messages in queue dump
  net: dsa: restore dsa_software_vlan_untag() ability to operate on VLAN-untagged traffic
  selftests: openvswitch: fix tcpdump execution
  net: usb: qmi_wwan: add Quectel RG255C
  net: phy: avoid undefined behavior in *_led_polarity_set()
  netfilter: ipset: Fix for recursive locking warning
  ipvs: Fix clamp() of ip_vs_conn_tab on small memory systems
  can: m_can: fix missed interrupts with m_can_pci
  can: m_can: set init flag earlier in probe
  rtnetlink: Try the outer netns attribute in rtnl_get_peer_net().
  net: netdevsim: fix nsim_pp_hold_write()
  idpf: trigger SW interrupt when exiting wb_on_itr mode
  idpf: add support for SW triggered interrupts
  qed: fix possible uninit pointer read in qed_mcp_nvm_info_populate()
  net: ethernet: bgmac-platform: fix an OF node reference leak
  ...

Author: torvalds

drivers/net/can/m_can/m_can.c

@@ -1220,20 +1220,32 @@ static void m_can_coalescing_update(struct m_can_classdev *cdev, u32 ir)
 static int m_can_interrupt_handler(struct m_can_classdev *cdev)
 {
 	struct net_device *dev = cdev->net;
-	u32 ir;
+	u32 ir = 0, ir_read;
 	int ret;
 
 	if (pm_runtime_suspended(cdev->dev))
 		return IRQ_NONE;
 
-	ir = m_can_read(cdev, M_CAN_IR);
+	/* The m_can controller signals its interrupt status as a level, but
+	 * depending in the integration the CPU may interpret the signal as
+	 * edge-triggered (for example with m_can_pci). For these
+	 * edge-triggered integrations, we must observe that IR is 0 at least
+	 * once to be sure that the next interrupt will generate an edge.
+	 */
+	while ((ir_read = m_can_read(cdev, M_CAN_IR)) != 0) {
+		ir |= ir_read;
+
+		/* ACK all irqs */
+		m_can_write(cdev, M_CAN_IR, ir);
+
+		if (!cdev->irq_edge_triggered)
+			break;
+	}
+
 	m_can_coalescing_update(cdev, ir);
 	if (!ir)
 		return IRQ_NONE;
 
-	/* ACK all irqs */
-	m_can_write(cdev, M_CAN_IR, ir);
-
 	if (cdev->ops->clear_interrupts)
 		cdev->ops->clear_interrupts(cdev);
 
@@ -1695,6 +1707,14 @@ static int m_can_dev_setup(struct m_can_classdev *cdev)
 		return -EINVAL;
 	}
 
+	/* Write the INIT bit, in case no hardware reset has happened before
+	 * the probe (for example, it was observed that the Intel Elkhart Lake
+	 * SoCs do not properly reset the CAN controllers on reboot)
+	 */
+	err = m_can_cccr_update_bits(cdev, CCCR_INIT, CCCR_INIT);
+	if (err)
+		return err;
+
 	if (!cdev->is_peripheral)
 		netif_napi_add(dev, &cdev->napi, m_can_poll);
 
@@ -1746,11 +1766,7 @@ static int m_can_dev_setup(struct m_can_classdev *cdev)
 		return -EINVAL;
 	}
 
-	/* Forcing standby mode should be redundant, as the chip should be in
-	 * standby after a reset. Write the INIT bit anyways, should the chip
-	 * be configured by previous stage.
-	 */
-	return m_can_cccr_update_bits(cdev, CCCR_INIT, CCCR_INIT);
+	return 0;
 }
 
 static void m_can_stop(struct net_device *dev)

drivers/net/can/m_can/m_can.h

@@ -99,6 +99,7 @@ struct m_can_classdev {
 	int pm_clock_support;
 	int pm_wake_source;
 	int is_peripheral;
+	bool irq_edge_triggered;
 
 	// Cached M_CAN_IE register content
 	u32 active_interrupts;

drivers/net/can/m_can/m_can_pci.c

@@ -127,6 +127,7 @@ static int m_can_pci_probe(struct pci_dev *pci, const struct pci_device_id *id)
 	mcan_class->pm_clock_support = 1;
 	mcan_class->pm_wake_source = 0;
 	mcan_class->can.clock.freq = id->driver_data;
+	mcan_class->irq_edge_triggered = true;
 	mcan_class->ops = &m_can_pci_ops;
 
 	pci_set_drvdata(pci, mcan_class);

drivers/net/ethernet/broadcom/bgmac-platform.c

@@ -171,6 +171,7 @@ static int platform_phy_connect(struct bgmac *bgmac)
 static int bgmac_probe(struct platform_device *pdev)
 {
 	struct device_node *np = pdev->dev.of_node;
+	struct device_node *phy_node;
 	struct bgmac *bgmac;
 	struct resource *regs;
 	int ret;
@@ -236,7 +237,9 @@ static int bgmac_probe(struct platform_device *pdev)
 	bgmac->cco_ctl_maskset = platform_bgmac_cco_ctl_maskset;
 	bgmac->get_bus_clock = platform_bgmac_get_bus_clock;
 	bgmac->cmn_maskset32 = platform_bgmac_cmn_maskset32;
-	if (of_parse_phandle(np, "phy-handle", 0)) {
+	phy_node = of_parse_phandle(np, "phy-handle", 0);
+	if (phy_node) {
+		of_node_put(phy_node);
 		bgmac->phy_connect = platform_phy_connect;
 	} else {
 		bgmac->phy_connect = bgmac_phy_connect_direct;

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

@@ -346,8 +346,9 @@ static struct sk_buff *copy_gl_to_skb_pkt(const struct pkt_gl *gl,
 	 * driver. Once driver synthesizes cpl_pass_accept_req the skb will go
 	 * through the regular cpl_pass_accept_req processing in TOM.
 	 */
-	skb = alloc_skb(gl->tot_len + sizeof(struct cpl_pass_accept_req)
-			- pktshift, GFP_ATOMIC);
+	skb = alloc_skb(size_add(gl->tot_len,
+				 sizeof(struct cpl_pass_accept_req)) -
+			pktshift, GFP_ATOMIC);
 	if (unlikely(!skb))
 		return NULL;
 	__skb_put(skb, gl->tot_len + sizeof(struct cpl_pass_accept_req)

drivers/net/ethernet/huawei/hinic/hinic_main.c

@@ -172,6 +172,7 @@ static int create_txqs(struct hinic_dev *nic_dev)
 	hinic_sq_dbgfs_uninit(nic_dev);
 
 	devm_kfree(&netdev->dev, nic_dev->txqs);
+	nic_dev->txqs = NULL;
 	return err;
 }
 
@@ -268,6 +269,7 @@ static int create_rxqs(struct hinic_dev *nic_dev)
 	hinic_rq_dbgfs_uninit(nic_dev);
 
 	devm_kfree(&netdev->dev, nic_dev->rxqs);
+	nic_dev->rxqs = NULL;
 	return err;
 }
 

drivers/net/ethernet/intel/idpf/idpf_dev.c

@@ -101,6 +101,9 @@ static int idpf_intr_reg_init(struct idpf_vport *vport)
 		intr->dyn_ctl_itridx_s = PF_GLINT_DYN_CTL_ITR_INDX_S;
 		intr->dyn_ctl_intrvl_s = PF_GLINT_DYN_CTL_INTERVAL_S;
 		intr->dyn_ctl_wb_on_itr_m = PF_GLINT_DYN_CTL_WB_ON_ITR_M;
+		intr->dyn_ctl_swint_trig_m = PF_GLINT_DYN_CTL_SWINT_TRIG_M;
+		intr->dyn_ctl_sw_itridx_ena_m =
+			PF_GLINT_DYN_CTL_SW_ITR_INDX_ENA_M;
 
 		spacing = IDPF_ITR_IDX_SPACING(reg_vals[vec_id].itrn_index_spacing,
 					       IDPF_PF_ITR_IDX_SPACING);

drivers/net/ethernet/intel/idpf/idpf_txrx.c

@@ -3604,21 +3604,31 @@ static void idpf_vport_intr_dis_irq_all(struct idpf_vport *vport)
 /**
  * idpf_vport_intr_buildreg_itr - Enable default interrupt generation settings
  * @q_vector: pointer to q_vector
- * @type: itr index
- * @itr: itr value
  */
-static u32 idpf_vport_intr_buildreg_itr(struct idpf_q_vector *q_vector,
-					const int type, u16 itr)
+static u32 idpf_vport_intr_buildreg_itr(struct idpf_q_vector *q_vector)
 {
-	u32 itr_val;
+	u32 itr_val = q_vector->intr_reg.dyn_ctl_intena_m;
+	int type = IDPF_NO_ITR_UPDATE_IDX;
+	u16 itr = 0;
+
+	if (q_vector->wb_on_itr) {
+		/*
+		 * Trigger a software interrupt when exiting wb_on_itr, to make
+		 * sure we catch any pending write backs that might have been
+		 * missed due to interrupt state transition.
+		 */
+		itr_val |= q_vector->intr_reg.dyn_ctl_swint_trig_m |
+			   q_vector->intr_reg.dyn_ctl_sw_itridx_ena_m;
+		type = IDPF_SW_ITR_UPDATE_IDX;
+		itr = IDPF_ITR_20K;
+	}
 
 	itr &= IDPF_ITR_MASK;
 	/* Don't clear PBA because that can cause lost interrupts that
 	 * came in while we were cleaning/polling
 	 */
-	itr_val = q_vector->intr_reg.dyn_ctl_intena_m |
-		  (type << q_vector->intr_reg.dyn_ctl_itridx_s) |
-		  (itr << (q_vector->intr_reg.dyn_ctl_intrvl_s - 1));
+	itr_val |= (type << q_vector->intr_reg.dyn_ctl_itridx_s) |
+		   (itr << (q_vector->intr_reg.dyn_ctl_intrvl_s - 1));
 
 	return itr_val;
 }
@@ -3716,9 +3726,8 @@ void idpf_vport_intr_update_itr_ena_irq(struct idpf_q_vector *q_vector)
 	/* net_dim() updates ITR out-of-band using a work item */
 	idpf_net_dim(q_vector);
 
+	intval = idpf_vport_intr_buildreg_itr(q_vector);
 	q_vector->wb_on_itr = false;
-	intval = idpf_vport_intr_buildreg_itr(q_vector,
-					      IDPF_NO_ITR_UPDATE_IDX, 0);
 
 	writel(intval, q_vector->intr_reg.dyn_ctl);
 }

drivers/net/ethernet/intel/idpf/idpf_txrx.h

@@ -354,6 +354,8 @@ struct idpf_vec_regs {
  * @dyn_ctl_itridx_m: Mask for ITR index
  * @dyn_ctl_intrvl_s: Register bit offset for ITR interval
  * @dyn_ctl_wb_on_itr_m: Mask for WB on ITR feature
+ * @dyn_ctl_sw_itridx_ena_m: Mask for SW ITR index
+ * @dyn_ctl_swint_trig_m: Mask for dyn_ctl SW triggered interrupt enable
  * @rx_itr: RX ITR register
  * @tx_itr: TX ITR register
  * @icr_ena: Interrupt cause register offset
@@ -367,6 +369,8 @@ struct idpf_intr_reg {
 	u32 dyn_ctl_itridx_m;
 	u32 dyn_ctl_intrvl_s;
 	u32 dyn_ctl_wb_on_itr_m;
+	u32 dyn_ctl_sw_itridx_ena_m;
+	u32 dyn_ctl_swint_trig_m;
 	void __iomem *rx_itr;
 	void __iomem *tx_itr;
 	void __iomem *icr_ena;
@@ -437,7 +441,7 @@ struct idpf_q_vector {
 	cpumask_var_t affinity_mask;
 	__cacheline_group_end_aligned(cold);
 };
-libeth_cacheline_set_assert(struct idpf_q_vector, 112,
+libeth_cacheline_set_assert(struct idpf_q_vector, 120,
 			    24 + sizeof(struct napi_struct) +
 			    2 * sizeof(struct dim),
 			    8 + sizeof(cpumask_var_t));
@@ -471,6 +475,8 @@ struct idpf_tx_queue_stats {
 #define IDPF_ITR_IS_DYNAMIC(itr_mode) (itr_mode)
 #define IDPF_ITR_TX_DEF		IDPF_ITR_20K
 #define IDPF_ITR_RX_DEF		IDPF_ITR_20K
+/* Index used for 'SW ITR' update in DYN_CTL register */
+#define IDPF_SW_ITR_UPDATE_IDX	2
 /* Index used for 'No ITR' update in DYN_CTL register */
 #define IDPF_NO_ITR_UPDATE_IDX	3
 #define IDPF_ITR_IDX_SPACING(spacing, dflt)	(spacing ? spacing : dflt)

drivers/net/ethernet/intel/idpf/idpf_vf_dev.c

@@ -101,6 +101,9 @@ static int idpf_vf_intr_reg_init(struct idpf_vport *vport)
 		intr->dyn_ctl_itridx_s = VF_INT_DYN_CTLN_ITR_INDX_S;
 		intr->dyn_ctl_intrvl_s = VF_INT_DYN_CTLN_INTERVAL_S;
 		intr->dyn_ctl_wb_on_itr_m = VF_INT_DYN_CTLN_WB_ON_ITR_M;
+		intr->dyn_ctl_swint_trig_m = VF_INT_DYN_CTLN_SWINT_TRIG_M;
+		intr->dyn_ctl_sw_itridx_ena_m =
+			VF_INT_DYN_CTLN_SW_ITR_INDX_ENA_M;
 
 		spacing = IDPF_ITR_IDX_SPACING(reg_vals[vec_id].itrn_index_spacing,
 					       IDPF_VF_ITR_IDX_SPACING);

drivers/net/ethernet/marvell/octeontx2/nic/rep.c

@@ -680,14 +680,17 @@ int rvu_rep_create(struct otx2_nic *priv, struct netlink_ext_ack *extack)
 		ndev->features |= ndev->hw_features;
 		eth_hw_addr_random(ndev);
 		err = rvu_rep_devlink_port_register(rep);
-		if (err)
+		if (err) {
+			free_netdev(ndev);
 			goto exit;
+		}
 
 		SET_NETDEV_DEVLINK_PORT(ndev, &rep->dl_port);
 		err = register_netdev(ndev);
 		if (err) {
 			NL_SET_ERR_MSG_MOD(extack,
 					   "PFVF representor registration failed");
+			rvu_rep_devlink_port_unregister(rep);
 			free_netdev(ndev);
 			goto exit;
 		}

drivers/net/ethernet/mscc/ocelot.c

@@ -1432,7 +1432,7 @@ void ocelot_ifh_set_basic(void *ifh, struct ocelot *ocelot, int port,
 
 	memset(ifh, 0, OCELOT_TAG_LEN);
 	ocelot_ifh_set_bypass(ifh, 1);
-	ocelot_ifh_set_src(ifh, BIT_ULL(ocelot->num_phys_ports));
+	ocelot_ifh_set_src(ifh, ocelot->num_phys_ports);
 	ocelot_ifh_set_dest(ifh, BIT_ULL(port));
 	ocelot_ifh_set_qos_class(ifh, qos_class);
 	ocelot_ifh_set_tag_type(ifh, tag_type);

drivers/net/ethernet/oa_tc6.c

@@ -113,6 +113,7 @@ struct oa_tc6 {
 	struct mii_bus *mdiobus;
 	struct spi_device *spi;
 	struct mutex spi_ctrl_lock; /* Protects spi control transfer */
+	spinlock_t tx_skb_lock; /* Protects tx skb handling */
 	void *spi_ctrl_tx_buf;
 	void *spi_ctrl_rx_buf;
 	void *spi_data_tx_buf;
@@ -1004,8 +1005,10 @@ static u16 oa_tc6_prepare_spi_tx_buf_for_tx_skbs(struct oa_tc6 *tc6)
 	for (used_tx_credits = 0; used_tx_credits < tc6->tx_credits;
 	     used_tx_credits++) {
 		if (!tc6->ongoing_tx_skb) {
+			spin_lock_bh(&tc6->tx_skb_lock);
 			tc6->ongoing_tx_skb = tc6->waiting_tx_skb;
 			tc6->waiting_tx_skb = NULL;
+			spin_unlock_bh(&tc6->tx_skb_lock);
 		}
 		if (!tc6->ongoing_tx_skb)
 			break;
@@ -1111,8 +1114,9 @@ static int oa_tc6_spi_thread_handler(void *data)
 		/* This kthread will be waken up if there is a tx skb or mac-phy
 		 * interrupt to perform spi transfer with tx chunks.
 		 */
-		wait_event_interruptible(tc6->spi_wq, tc6->waiting_tx_skb ||
-					 tc6->int_flag ||
+		wait_event_interruptible(tc6->spi_wq, tc6->int_flag ||
+					 (tc6->waiting_tx_skb &&
+					 tc6->tx_credits) ||
 					 kthread_should_stop());
 
 		if (kthread_should_stop())
@@ -1209,7 +1213,9 @@ netdev_tx_t oa_tc6_start_xmit(struct oa_tc6 *tc6, struct sk_buff *skb)
 		return NETDEV_TX_OK;
 	}
 
+	spin_lock_bh(&tc6->tx_skb_lock);
 	tc6->waiting_tx_skb = skb;
+	spin_unlock_bh(&tc6->tx_skb_lock);
 
 	/* Wake spi kthread to perform spi transfer */
 	wake_up_interruptible(&tc6->spi_wq);
@@ -1239,6 +1245,7 @@ struct oa_tc6 *oa_tc6_init(struct spi_device *spi, struct net_device *netdev)
 	tc6->netdev = netdev;
 	SET_NETDEV_DEV(netdev, &spi->dev);
 	mutex_init(&tc6->spi_ctrl_lock);
+	spin_lock_init(&tc6->tx_skb_lock);
 
 	/* Set the SPI controller to pump at realtime priority */
 	tc6->spi->rt = true;

drivers/net/ethernet/pensando/ionic/ionic_dev.c

@@ -277,7 +277,10 @@ void ionic_dev_teardown(struct ionic *ionic)
 	idev->phy_cmb_pages = 0;
 	idev->cmb_npages = 0;
 
-	destroy_workqueue(ionic->wq);
+	if (ionic->wq) {
+		destroy_workqueue(ionic->wq);
+		ionic->wq = NULL;
+	}
 	mutex_destroy(&idev->cmb_inuse_lock);
 }
 

drivers/net/ethernet/pensando/ionic/ionic_ethtool.c

@@ -961,8 +961,8 @@ static int ionic_get_module_eeprom(struct net_device *netdev,
 	len = min_t(u32, sizeof(xcvr->sprom), ee->len);
 
 	do {
-		memcpy(data, xcvr->sprom, len);
-		memcpy(tbuf, xcvr->sprom, len);
+		memcpy(data, &xcvr->sprom[ee->offset], len);
+		memcpy(tbuf, &xcvr->sprom[ee->offset], len);
 
 		/* Let's make sure we got a consistent copy */
 		if (!memcmp(data, tbuf, len))

drivers/net/ethernet/pensando/ionic/ionic_lif.c

@@ -3869,8 +3869,8 @@ int ionic_lif_register(struct ionic_lif *lif)
 	/* only register LIF0 for now */
 	err = register_netdev(lif->netdev);
 	if (err) {
-		dev_err(lif->ionic->dev, "Cannot register net device, aborting\n");
-		ionic_lif_unregister_phc(lif);
+		dev_err(lif->ionic->dev, "Cannot register net device: %d, aborting\n", err);
+		ionic_lif_unregister(lif);
 		return err;
 	}
 

drivers/net/ethernet/qlogic/qed/qed_mcp.c

@@ -3358,6 +3358,7 @@ int qed_mcp_nvm_info_populate(struct qed_hwfn *p_hwfn)
 					     p_ptt, &nvm_info.num_images);
 	if (rc == -EOPNOTSUPP) {
 		DP_INFO(p_hwfn, "DRV_MSG_CODE_BIST_TEST is not supported\n");
+		nvm_info.num_images = 0;
 		goto out;
 	} else if (rc || !nvm_info.num_images) {
 		DP_ERR(p_hwfn, "Failed getting number of images\n");