Merge tag 'net-7.2-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni:
 "Including fixes from netfilter, Bluetooth and batman-adv.

  Current release - regressions:

   - bluetooth: fix using chan->conn as indication to no remote netdev

  Current release - new code bugs:

   - netfilter: cap to maximum number of expectation per master on
     updates

  Previous releases - regressions:

   - bluetooth:
      - fix UAF of hci_conn_params in add_device_complete
      - fix null ptr deref in hci_abort_conn()

   - igmp: remove multicast group from hash table on device destruction

   - batman-adv: prevent TVLV OOB check overflow

   - eth: mlx5/mlx5e:
      - fix off-by-one in single-FDB error rollback
      - skip peer flow cleanup when LAG seq is unavailable
      - fix crashes in dynamic per-channel stats and HV VHCA agent

   - eth: mana: Sync page pool RX frags for CPU

  Previous releases - always broken:

   - netfilter:
      - mark malformed IPv6 extension headers for hotdrop
      - terminate table name before find_table_lock()
      - ipvs: use parsed transport offset in TCP state lookup

   - sched: act_pedit: fix TOCTOU heap OOB write in tc offload

   - ethtool: rss: fix hfunc and input_xfrm parsing on big endian

   - ipv4/ipv6: fix UAF and memory leak in IGMP/MLD

   - tls: consume empty data records in tls_sw_read_sock()

   - eth:
      - octeontx2-af: fix VF bringup affecting PF promiscuous state
      - gue: validate REMCSUM private option length"

* tag 'net-7.2-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (94 commits)
  macsec: don't read an unset MAC header in macsec_encrypt()
  dibs: loopback: validate offset and size in move_data()
  octeontx2-af: fix VF bringup affecting PF promiscuous state
  ethtool: rss: Fix hfunc and input_xfrm parsing on big endian
  net/mlx5: Fix L3 tunnel entropy refcount leak
  net: macb: drop in-flight Tx SKBs on close
  net: mana: Sync page pool RX frags for CPU
  net: mana: Validate the packet length reported by the NIC
  selftests/net: fix EVP_MD_CTX leak in tcp_mmap
  ipvs: ensure inner headers in ICMP errors are in headroom
  ipvs: use parsed transport offset in SCTP state lookup
  ipvs: use parsed transport offset in TCP state lookup
  ipvs: pass parsed transport offset to state handlers
  netfilter: handle unreadable frags
  netfilter: flowtable: support IPIP tunnel with direct xmit
  netfilter: flowtable: IPIP tunnel hardware offload is not yet support
  netfilter: flowtable: use dst in this direction when pushing IPIP header
  netfilter: ipset: allocate the proper memory for the generic hash structure
  netfilter: ipset: cleanup the add/del backlog when resize failed
  netfilter: ipset: exclude gc when resize is in progress
  ...

drivers/bluetooth/bpa10x.c

@@ -255,9 +255,13 @@ static int bpa10x_setup(struct hci_dev *hdev)
 	if (IS_ERR(skb))
 		return PTR_ERR(skb);
 
-	bt_dev_info(hdev, "%s", (char *)(skb->data + 1));
+	/* Bounded print: the device controls skb->len. */
+	if (skb->len > 1) {
+		int len = skb->len - 1;
 
-	hci_set_fw_info(hdev, "%s", skb->data + 1);
+		bt_dev_info(hdev, "%.*s", len, (char *)(skb->data + 1));
+		hci_set_fw_info(hdev, "%.*s", len, skb->data + 1);
+	}
 
 	kfree_skb(skb);
 	return 0;

drivers/bluetooth/btintel_pcie.c

@@ -2127,6 +2127,9 @@ static int btintel_pcie_send_frame(struct hci_dev *hdev,
 	if (test_bit(BTINTEL_PCIE_CORE_HALTED, &data->flags))
 		return -ENODEV;
 
+	if (test_bit(BTINTEL_PCIE_RECOVERY_IN_PROGRESS, &data->flags))
+		return -ENODEV;
+
 	/* Due to the fw limitation, the type header of the packet should be
 	 * 4 bytes unlike 1 byte for UART. In UART, the firmware can read
 	 * the first byte to get the packet type and redirect the rest of data
@@ -2485,7 +2488,6 @@ static void btintel_pcie_inc_recovery_count(struct pci_dev *pdev,
 	}
 }
 
-static int btintel_pcie_setup_hdev(struct btintel_pcie_data *data);
 static void btintel_pcie_reset(struct hci_dev *hdev);
 
 static int btintel_pcie_acpi_reset_method(struct btintel_pcie_data *data)
@@ -2596,12 +2598,45 @@ static void btintel_pcie_perform_pldr(struct btintel_pcie_data *data)
 	}
 }
 
+/*
+ * Issue a Function Level Reset and hand teardown/re-init off to the PCI
+ * core via device_reprobe(), mirroring the PLDR path's contract.
+ *
+ * Caller must hold pci_lock_rescan_remove() and must have already
+ * disabled interrupts and drained both rx_work and coredump_work.
+ */
+static int btintel_pcie_perform_flr(struct btintel_pcie_data *data)
+{
+	struct pci_dev *pdev = data->pdev;
+	int err;
+
+	/* pci_try_reset_function() avoids the device_lock ABBA against
+	 * btintel_pcie_remove(): .remove() runs with device_lock held and
+	 * then waits for this work via disable_work_sync(); the blocking
+	 * pci_reset_function() would deadlock by trying to re-acquire
+	 * device_lock here.
+	 */
+	err = pci_try_reset_function(pdev);
+	if (err) {
+		BT_ERR("Failed resetting the pcie device (%d)", err);
+		return err;
+	}
+
+	/* device_reprobe() always detaches the driver first (running
+	 * .remove(), which frees 'data'); any re-probe failure leaves the
+	 * device unbound but 'data' is already gone, so just log it.
+	 */
+	if (device_reprobe(&pdev->dev))
+		BT_ERR("BT reprobe failed for BDF:%s", pci_name(pdev));
+
+	return 0;
+}
+
 static void btintel_pcie_reset_work(struct work_struct *wk)
 {
 	struct btintel_pcie_data *data =
 		container_of(wk, struct btintel_pcie_data, reset_work);
 	struct pci_dev *pdev = data->pdev;
-	int err;
 
 	pci_lock_rescan_remove();
 
@@ -2621,60 +2656,27 @@ static void btintel_pcie_reset_work(struct work_struct *wk)
 	disable_work_sync(&data->coredump_work);
 
 	bt_dev_dbg(data->hdev, "Release bluetooth interface");
+
+	/* Both reset paths follow the same contract: on success they
+	 * destroy 'data' via device_reprobe() (a fresh probe re-INIT_WORKs
+	 * the coredump_work with disable count 0), so enable_work() must
+	 * NOT be called on the success path. Only the FLR path can fail
+	 * with 'data' still alive, in which case we balance the
+	 * disable_work_sync() above so a later successful reset is not
+	 * permanently blocked.
+	 *
+	 * pci_lock_rescan_remove() (held above) serializes against PCI
+	 * device addition/removal (hotplug), so no device can be added to
+	 * or removed from the bus list while this code runs.
+	 */
 	if (data->reset_type == BTINTEL_PCIE_IOSF_PRR_PLDR) {
-		/* This function holds pci_lock_rescan_remove(), which acquires
-		 * pci_rescan_remove_lock. This mutex serializes against PCI device
-		 * addition/removal (hotplug), so no device can be added to or
-		 * removed from the bus list while this code runs.
-		 *
-		 * device_reprobe() inside btintel_pcie_perform_pldr() destroys
-		 * 'data' via .remove(); a fresh probe re-INIT_WORKs the
-		 * coredump_work with disable count 0, so we must not call
-		 * enable_work() on this path.
-		 */
 		btintel_pcie_perform_pldr(data);
 		goto out;
 	}
-	btintel_pcie_release_hdev(data);
 
-	/* Use pci_try_reset_function() rather than pci_reset_function() to
-	 * avoid an ABBA deadlock against btintel_pcie_remove(): the PCI core
-	 * calls .remove() with device_lock held, and remove() then waits for
-	 * this work via cancel_work_sync(); pci_reset_function() would in
-	 * turn try to acquire the same device_lock, deadlocking both paths.
-	 */
-	err = pci_try_reset_function(pdev);
-	if (err) {
-		BT_ERR("Failed resetting the pcie device (%d)", err);
-		goto out_enable;
-	}
+	if (btintel_pcie_perform_flr(data))
+		enable_work(&data->coredump_work);
 
-	btintel_pcie_enable_interrupts(data);
-	btintel_pcie_config_msix(data);
-
-	err = btintel_pcie_enable_bt(data);
-	if (err) {
-		BT_ERR("Failed to enable bluetooth hardware after reset (%d)",
-		       err);
-		goto out_enable;
-	}
-
-	btintel_pcie_reset_ia(data);
-	btintel_pcie_start_rx(data);
-	data->flags = 0;
-
-	err = btintel_pcie_setup_hdev(data);
-	if (err) {
-		BT_ERR("Failed registering hdev (%d)", err);
-		goto out_enable;
-	}
-
-out_enable:
-	/* Balance disable_work_sync() above on every exit. Leaving the
-	 * counter incremented on a failed reset would permanently disable
-	 * coredump_work even after a later successful reset.
-	 */
-	enable_work(&data->coredump_work);
 out:
 	pci_dev_put(pdev);
 	pci_unlock_rescan_remove();

drivers/bluetooth/btnxpuart.c

@@ -1267,6 +1267,12 @@ static int nxp_recv_fw_req_v3(struct hci_dev *hdev, struct sk_buff *skb)
 	}
 
 	nxpdev->fw_dnld_v3_offset = offset - nxpdev->fw_v3_offset_correction;
+	if (nxpdev->fw_dnld_v3_offset >= nxpdev->fw->size ||
+	    len > nxpdev->fw->size - nxpdev->fw_dnld_v3_offset) {
+		bt_dev_err(hdev, "FW download out of bounds, ignoring request");
+		len = 0;
+		goto free_skb;
+	}
 	serdev_device_write_buf(nxpdev->serdev, nxpdev->fw->data +
 				nxpdev->fw_dnld_v3_offset, len);
 

drivers/bluetooth/hci_ldisc.c

@@ -239,6 +239,8 @@ static int hci_uart_flush(struct hci_dev *hdev)
 
 	BT_DBG("hdev %p tty %p", hdev, tty);
 
+	disable_work_sync(&hu->write_work);
+
 	if (hu->tx_skb) {
 		kfree_skb(hu->tx_skb); hu->tx_skb = NULL;
 	}
@@ -254,6 +256,14 @@ static int hci_uart_flush(struct hci_dev *hdev)
 
 	percpu_up_read(&hu->proto_lock);
 
+	/* Resume TX. Also reschedule in case work was queued concurrently;
+	 * this may schedule write_work although there's nothing to do.
+	 */
+	enable_work(&hu->write_work);
+	clear_bit(HCI_UART_SENDING, &hu->tx_state);
+	if (test_bit(HCI_UART_TX_WAKEUP, &hu->tx_state))
+		hci_uart_tx_wakeup(hu);
+
 	return 0;
 }
 
@@ -271,12 +281,8 @@ static int hci_uart_open(struct hci_dev *hdev)
 /* Close device */
 static int hci_uart_close(struct hci_dev *hdev)
 {
-	struct hci_uart *hu = hci_get_drvdata(hdev);
-
 	BT_DBG("hdev %p", hdev);
 
-	cancel_work_sync(&hu->write_work);
-
 	hci_uart_flush(hdev);
 	hdev->flush = NULL;
 	return 0;

drivers/dibs/dibs_loopback.c

@@ -254,6 +254,11 @@ static int dibs_lo_move_data(struct dibs_dev *dibs, u64 dmb_tok,
 		read_unlock_bh(&ldev->dmb_ht_lock);
 		return -EINVAL;
 	}
+	if ((u64)offset + size > rmb_node->len) {
+		read_unlock_bh(&ldev->dmb_ht_lock);
+		return -EINVAL;
+	}
+
 	memcpy((char *)rmb_node->cpu_addr + offset, data, size);
 	sba_idx = rmb_node->sba_idx;
 	read_unlock_bh(&ldev->dmb_ht_lock);

drivers/net/amt.c

@@ -3301,9 +3301,9 @@ static size_t amt_get_size(const struct net_device *dev)
 	       nla_total_size(sizeof(__u16)) + /* IFLA_AMT_GATEWAY_PORT */
 	       nla_total_size(sizeof(__u32)) + /* IFLA_AMT_LINK */
 	       nla_total_size(sizeof(__u32)) + /* IFLA_MAX_TUNNELS */
-	       nla_total_size(sizeof(struct iphdr)) + /* IFLA_AMT_DISCOVERY_IP */
-	       nla_total_size(sizeof(struct iphdr)) + /* IFLA_AMT_REMOTE_IP */
-	       nla_total_size(sizeof(struct iphdr)); /* IFLA_AMT_LOCAL_IP */
+	       nla_total_size(sizeof(__be32)) + /* IFLA_AMT_DISCOVERY_IP */
+	       nla_total_size(sizeof(__be32)) + /* IFLA_AMT_REMOTE_IP */
+	       nla_total_size(sizeof(__be32)); /* IFLA_AMT_LOCAL_IP */
 }
 
 static int amt_fill_info(struct sk_buff *skb, const struct net_device *dev)

drivers/net/ethernet/cadence/macb_main.c

@@ -2668,8 +2668,25 @@ static void macb_free_consistent(struct macb *bp)
 	dma_free_coherent(dev, size, bp->queues[0].rx_ring, bp->queues[0].rx_ring_dma);
 
 	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
-		kfree(queue->tx_skb);
-		queue->tx_skb = NULL;
+		if (queue->tx_skb) {
+			unsigned int dropped = 0, tail;
+
+			for (tail = queue->tx_tail; tail != queue->tx_head;
+			     tail++) {
+				if (macb_tx_skb(queue, tail)->skb)
+					dropped++;
+				macb_tx_unmap(bp, macb_tx_skb(queue, tail), 0);
+			}
+
+			queue->stats.tx_dropped += dropped;
+			bp->dev->stats.tx_dropped += dropped;
+
+			kfree(queue->tx_skb);
+			queue->tx_skb = NULL;
+		}
+
+		queue->tx_head = 0;
+		queue->tx_tail = 0;
 		queue->tx_ring = NULL;
 		queue->rx_ring = NULL;
 	}

drivers/net/ethernet/cavium/liquidio/lio_main.c

@@ -3779,9 +3779,7 @@ setup_nic_dev_done:
 static int octeon_enable_sriov(struct octeon_device *oct)
 {
 	unsigned int num_vfs_alloced = oct->sriov_info.num_vfs_alloced;
-	struct pci_dev *vfdev;
 	int err;
-	u32 u;
 
 	if (OCTEON_CN23XX_PF(oct) && num_vfs_alloced) {
 		err = pci_enable_sriov(oct->pci_dev,
@@ -3794,23 +3792,6 @@ static int octeon_enable_sriov(struct octeon_device *oct)
 			return err;
 		}
 		oct->sriov_info.sriov_enabled = 1;
-
-		/* init lookup table that maps DPI ring number to VF pci_dev
-		 * struct pointer
-		 */
-		u = 0;
-		vfdev = pci_get_device(PCI_VENDOR_ID_CAVIUM,
-				       OCTEON_CN23XX_VF_VID, NULL);
-		while (vfdev) {
-			if (vfdev->is_virtfn &&
-			    (vfdev->physfn == oct->pci_dev)) {
-				oct->sriov_info.dpiring_to_vfpcidev_lut[u] =
-					vfdev;
-				u += oct->sriov_info.rings_per_vf;
-			}
-			vfdev = pci_get_device(PCI_VENDOR_ID_CAVIUM,
-					       OCTEON_CN23XX_VF_VID, vfdev);
-		}
 	}
 
 	return num_vfs_alloced;
@@ -3818,8 +3799,6 @@ static int octeon_enable_sriov(struct octeon_device *oct)
 
 static int lio_pci_sriov_disable(struct octeon_device *oct)
 {
-	int u;
-
 	if (pci_vfs_assigned(oct->pci_dev)) {
 		dev_err(&oct->pci_dev->dev, "VFs are still assigned to VMs.\n");
 		return -EPERM;
@@ -3827,12 +3806,6 @@ static int lio_pci_sriov_disable(struct octeon_device *oct)
 
 	pci_disable_sriov(oct->pci_dev);
 
-	u = 0;
-	while (u < MAX_POSSIBLE_VFS) {
-		oct->sriov_info.dpiring_to_vfpcidev_lut[u] = NULL;
-		u += oct->sriov_info.rings_per_vf;
-	}
-
 	oct->sriov_info.num_vfs_alloced = 0;
 	dev_info(&oct->pci_dev->dev, "oct->pf_num:%d disabled VFs\n",
 		 oct->pf_num);

drivers/net/ethernet/cavium/liquidio/octeon_device.h

@@ -390,9 +390,6 @@ struct octeon_sriov_info {
 
 	struct lio_trusted_vf	trusted_vf;
 
-	/*lookup table that maps DPI ring number to VF pci_dev struct pointer*/
-	struct pci_dev *dpiring_to_vfpcidev_lut[MAX_POSSIBLE_VFS];
-
 	u64	vf_macaddr[MAX_POSSIBLE_VFS];
 
 	u16	vf_vlantci[MAX_POSSIBLE_VFS];

drivers/net/ethernet/cavium/liquidio/octeon_mailbox.c

@@ -26,6 +26,31 @@
 #include "octeon_mailbox.h"
 #include "cn23xx_pf_device.h"
 
+static struct pci_dev *lio_vf_pci_dev_by_qno(struct octeon_device *oct, u32 q_no)
+{
+	struct pci_dev *vfdev = NULL;
+	int vfidx;
+
+	if (!oct->sriov_info.rings_per_vf)
+		return NULL;
+
+	if (q_no % oct->sriov_info.rings_per_vf)
+		return NULL;
+
+	vfidx = q_no / oct->sriov_info.rings_per_vf;
+	if (vfidx >= oct->sriov_info.num_vfs_alloced)
+		return NULL;
+
+	while ((vfdev = pci_get_device(PCI_VENDOR_ID_CAVIUM,
+				       OCTEON_CN23XX_VF_VID, vfdev))) {
+		if (pci_physfn(vfdev) && pci_physfn(vfdev) == oct->pci_dev &&
+		    pci_iov_vf_id(vfdev) == vfidx)
+			return vfdev;
+	}
+
+	return NULL;
+}
+
 /**
  * octeon_mbox_read:
  * @mbox: Pointer mailbox
@@ -237,6 +262,7 @@ static int octeon_mbox_process_cmd(struct octeon_mbox *mbox,
 				   struct octeon_mbox_cmd *mbox_cmd)
 {
 	struct octeon_device *oct = mbox->oct_dev;
+	struct pci_dev *vfdev;
 
 	switch (mbox_cmd->msg.s.cmd) {
 	case OCTEON_VF_ACTIVE:
@@ -260,7 +286,12 @@ static int octeon_mbox_process_cmd(struct octeon_mbox *mbox,
 		dev_info(&oct->pci_dev->dev,
 			 "got a request for FLR from VF that owns DPI ring %u\n",
 			 mbox->q_no);
-		pcie_flr(oct->sriov_info.dpiring_to_vfpcidev_lut[mbox->q_no]);
+		vfdev = lio_vf_pci_dev_by_qno(oct, mbox->q_no);
+		if (!vfdev)
+			break;
+
+		pcie_flr(vfdev);
+		pci_dev_put(vfdev);
 		break;
 
 	case OCTEON_PF_CHANGED_VF_MACADDR:

drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c

@@ -4580,7 +4580,7 @@ int rvu_mbox_handler_nix_set_rx_mode(struct rvu *rvu, struct nix_rx_mode *req,
 		rvu_npc_install_allmulti_entry(rvu, pcifunc, nixlf,
 					       pfvf->rx_chan_base);
 	} else {
-		if (!nix_rx_multicast)
+		if (!nix_rx_multicast && !is_vf(pcifunc))
 			rvu_npc_enable_allmulti_entry(rvu, pcifunc, nixlf, false);
 	}
 
@@ -4590,7 +4590,7 @@ int rvu_mbox_handler_nix_set_rx_mode(struct rvu *rvu, struct nix_rx_mode *req,
 					      pfvf->rx_chan_base,
 					      pfvf->rx_chan_cnt);
 	else
-		if (!nix_rx_multicast)
+		if (!nix_rx_multicast && !is_vf(pcifunc))
 			rvu_npc_enable_promisc_entry(rvu, pcifunc, nixlf, false);
 
 	return 0;

drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c

@@ -1568,15 +1568,15 @@ static void otx2_free_sq_res(struct otx2_nic *pf)
 	otx2_sq_free_sqbs(pf);
 	for (qidx = 0; qidx < otx2_get_total_tx_queues(pf); qidx++) {
 		sq = &qset->sq[qidx];
-		/* Skip freeing Qos queues if they are not initialized */
-		if (!sq->sqe)
-			continue;
-		qmem_free(pf->dev, sq->sqe);
-		qmem_free(pf->dev, sq->sqe_ring);
-		qmem_free(pf->dev, sq->cpt_resp);
-		qmem_free(pf->dev, sq->tso_hdrs);
-		qmem_free(pf->dev, sq->timestamps);
-		kfree(sq->sg);
+		/* sq->sqe is not initialized for unused QoS queues */
+		if (sq->sqe) {
+			qmem_free(pf->dev, sq->sqe);
+			qmem_free(pf->dev, sq->sqe_ring);
+			qmem_free(pf->dev, sq->cpt_resp);
+			qmem_free(pf->dev, sq->tso_hdrs);
+			qmem_free(pf->dev, sq->timestamps);
+			kfree(sq->sg);
+		}
 		kfree(sq->sqb_ptrs);
 	}
 }
@@ -1711,13 +1711,12 @@ int otx2_init_hw_resources(struct otx2_nic *pf)
 	return err;
 
 err_free_nix_queues:
-	otx2_free_sq_res(pf);
 	otx2_free_cq_res(pf);
 	otx2_ctx_disable(mbox, NIX_AQ_CTYPE_RQ, false);
 err_free_txsch:
 	otx2_txschq_stop(pf);
 err_free_sq_ptrs:
-	otx2_sq_free_sqbs(pf);
+	otx2_free_sq_res(pf);
 err_free_rq_ptrs:
 	otx2_free_aura_ptr(pf, AURA_NIX_RQ);
 	otx2_ctx_disable(mbox, NPA_AQ_CTYPE_POOL, true);
@@ -2517,10 +2516,42 @@ EXPORT_SYMBOL(otx2_config_hwtstamp_set);
 
 static int otx2_do_set_vf_mac(struct otx2_nic *pf, int vf, const u8 *mac)
 {
+	struct npc_get_field_status_req *freq;
+	struct npc_get_field_status_rsp *frsp;
 	struct npc_install_flow_req *req;
 	int err;
 
 	mutex_lock(&pf->mbox.lock);
+
+	/* Skip installing the DMAC filter if the hardware parser profile
+	 * does not support DMAC extraction.
+	 */
+	freq = otx2_mbox_alloc_msg_npc_get_field_status(&pf->mbox);
+	if (!freq) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	freq->field = NPC_DMAC;
+	err = otx2_sync_mbox_msg(&pf->mbox);
+	if (err)
+		goto out;
+
+	frsp = (struct npc_get_field_status_rsp *)otx2_mbox_get_rsp
+	       (&pf->mbox.mbox, 0, &freq->hdr);
+	if (IS_ERR(frsp)) {
+		err = PTR_ERR(frsp);
+		goto out;
+	}
+
+	if (!frsp->enable) {
+		netdev_warn(pf->netdev,
+			    "VF %d MAC filter not installed: DMAC extraction not supported by parser profile\n",
+			    vf);
+		err = -EOPNOTSUPP;
+		goto out;
+	}
+
 	req = otx2_mbox_alloc_msg_npc_install_flow(&pf->mbox);
 	if (!req) {
 		err = -ENOMEM;
@@ -2559,13 +2590,12 @@ static int otx2_set_vf_mac(struct net_device *netdev, int vf, u8 *mac)
 	if (!is_valid_ether_addr(mac))
 		return -EINVAL;
 
-	config = &pf->vf_configs[vf];
-	ether_addr_copy(config->mac, mac);
-
 	ret = otx2_do_set_vf_mac(pf, vf, mac);
-	if (ret == 0)
-		dev_info(&pdev->dev,
-			 "Load/Reload VF driver\n");
+	if (ret == 0) {
+		config = &pf->vf_configs[vf];
+		ether_addr_copy(config->mac, mac);
+		dev_info(&pdev->dev, "Load/Reload VF driver\n");
+	}
 
 	return ret;
 }

drivers/net/ethernet/mellanox/mlx5/core/en.h

@@ -987,6 +987,18 @@ struct mlx5e_priv {
 	struct ethtool_fec_hist_range *fec_ranges;
 };
 
+static inline u16 mlx5e_stats_nch_read(const struct mlx5e_priv *priv)
+{
+	/* Pairs with smp_store_release in mlx5e_stats_nch_write(). */
+	return smp_load_acquire(&priv->stats_nch);
+}
+
+static inline void mlx5e_stats_nch_write(struct mlx5e_priv *priv, u16 n)
+{
+	/* Pairs with smp_load_acquire in mlx5e_stats_nch_read(). */
+	smp_store_release(&priv->stats_nch, n);
+}
+
 struct mlx5e_dev {
 	struct net_device *netdev;
 	struct devlink_port dl_port;

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

@@ -33,9 +33,10 @@ mlx5e_hv_vhca_fill_ring_stats(struct mlx5e_priv *priv, int ch,
 static void mlx5e_hv_vhca_fill_stats(struct mlx5e_priv *priv, void *data,
 				     int buf_len)
 {
+	u16 nch = mlx5e_stats_nch_read(priv);
 	int ch, i = 0;
 
-	for (ch = 0; ch < priv->stats_nch; ch++) {
+	for (ch = 0; ch < nch; ch++) {
 		void *buf = data + i;
 
 		if (WARN_ON_ONCE(buf +
@@ -49,9 +50,16 @@ static void mlx5e_hv_vhca_fill_stats(struct mlx5e_priv *priv, void *data,
 }
 
 static int mlx5e_hv_vhca_stats_buf_size(struct mlx5e_priv *priv)
+{
+	u16 nch = mlx5e_stats_nch_read(priv);
+
+	return sizeof(struct mlx5e_hv_vhca_per_ring_stats) * nch;
+}
+
+static int mlx5e_hv_vhca_stats_buf_max_size(struct mlx5e_priv *priv)
 {
 	return (sizeof(struct mlx5e_hv_vhca_per_ring_stats) *
-		priv->stats_nch);
+		max(priv->max_nch, priv->stats_nch));
 }
 
 static void mlx5e_hv_vhca_stats_work(struct work_struct *work)
@@ -67,7 +75,7 @@ static void mlx5e_hv_vhca_stats_work(struct work_struct *work)
 	sagent = container_of(dwork, struct mlx5e_hv_vhca_stats_agent, work);
 	priv = container_of(sagent, struct mlx5e_priv, stats_agent);
 	buf_len = mlx5e_hv_vhca_stats_buf_size(priv);
-	agent = sagent->agent;
+	agent = READ_ONCE(sagent->agent);
 	buf = sagent->buf;
 
 	memset(buf, 0, buf_len);
@@ -100,7 +108,7 @@ static void mlx5e_hv_vhca_stats_control(struct mlx5_hv_vhca_agent *agent,
 	sagent = &priv->stats_agent;
 
 	block->version = MLX5_HV_VHCA_STATS_VERSION;
-	block->rings   = priv->stats_nch;
+	block->rings   = mlx5e_stats_nch_read(priv);
 
 	if (!block->command) {
 		cancel_delayed_work_sync(&priv->stats_agent.work);
@@ -122,18 +130,21 @@ static void mlx5e_hv_vhca_stats_cleanup(struct mlx5_hv_vhca_agent *agent)
 
 void mlx5e_hv_vhca_stats_create(struct mlx5e_priv *priv)
 {
-	int buf_len = mlx5e_hv_vhca_stats_buf_size(priv);
+	int buf_len = mlx5e_hv_vhca_stats_buf_max_size(priv);
 	struct mlx5_hv_vhca_agent *agent;
 
 	priv->stats_agent.buf = kvzalloc(buf_len, GFP_KERNEL);
 	if (!priv->stats_agent.buf)
 		return;
 
+	INIT_DELAYED_WORK(&priv->stats_agent.work, mlx5e_hv_vhca_stats_work);
+
 	agent = mlx5_hv_vhca_agent_create(priv->mdev->hv_vhca,
 					  MLX5_HV_VHCA_AGENT_STATS,
 					  mlx5e_hv_vhca_stats_control, NULL,
 					  mlx5e_hv_vhca_stats_cleanup,
-					  priv);
+					  priv,
+					  &priv->stats_agent.agent);
 
 	if (IS_ERR_OR_NULL(agent)) {
 		if (IS_ERR(agent))
@@ -142,18 +153,20 @@ void mlx5e_hv_vhca_stats_create(struct mlx5e_priv *priv)
 				    agent);
 
 		kvfree(priv->stats_agent.buf);
-		return;
+		priv->stats_agent.buf = NULL;
 	}
-
-	priv->stats_agent.agent = agent;
-	INIT_DELAYED_WORK(&priv->stats_agent.work, mlx5e_hv_vhca_stats_work);
 }
 
 void mlx5e_hv_vhca_stats_destroy(struct mlx5e_priv *priv)
 {
-	if (IS_ERR_OR_NULL(priv->stats_agent.agent))
+	struct mlx5_hv_vhca_agent *agent;
+
+	agent = READ_ONCE(priv->stats_agent.agent);
+	if (IS_ERR_OR_NULL(agent))
 		return;
 
-	mlx5_hv_vhca_agent_destroy(priv->stats_agent.agent);
+	mlx5_hv_vhca_agent_destroy(agent);
+	WRITE_ONCE(priv->stats_agent.agent, NULL);
 	kvfree(priv->stats_agent.buf);
+	priv->stats_agent.buf = NULL;
 }

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

@@ -2773,7 +2773,7 @@ static int mlx5e_channel_stats_alloc(struct mlx5e_priv *priv, int ix, int cpu)
 						GFP_KERNEL, cpu_to_node(cpu));
 	if (!priv->channel_stats[ix])
 		return -ENOMEM;
-	priv->stats_nch++;
+	mlx5e_stats_nch_write(priv, priv->stats_nch + 1);
 
 	return 0;
 }
@@ -4040,9 +4040,10 @@ static int mlx5e_setup_tc(struct net_device *dev, enum tc_setup_type type,
 
 void mlx5e_fold_sw_stats64(struct mlx5e_priv *priv, struct rtnl_link_stats64 *s)
 {
+	u16 nch = mlx5e_stats_nch_read(priv);
 	int i;
 
-	for (i = 0; i < priv->stats_nch; i++) {
+	for (i = 0; i < nch; i++) {
 		struct mlx5e_channel_stats *channel_stats = priv->channel_stats[i];
 		struct mlx5e_rq_stats *xskrq_stats = &channel_stats->xskrq;
 		struct mlx5e_rq_stats *rq_stats = &channel_stats->rq;
@@ -5488,7 +5489,7 @@ static void mlx5e_get_queue_stats_rx(struct net_device *dev, int i,
 	struct mlx5e_rq_stats *xskrq_stats;
 	struct mlx5e_rq_stats *rq_stats;
 
-	if (mlx5e_is_uplink_rep(priv) || !priv->stats_nch)
+	if (mlx5e_is_uplink_rep(priv) || !mlx5e_stats_nch_read(priv))
 		return;
 
 	channel_stats = priv->channel_stats[i];
@@ -5512,7 +5513,7 @@ static void mlx5e_get_queue_stats_tx(struct net_device *dev, int i,
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5e_sq_stats *sq_stats;
 
-	if (!priv->stats_nch)
+	if (!mlx5e_stats_nch_read(priv))
 		return;
 
 	/* no special case needed for ptp htb etc since txq2sq_stats is kept up
@@ -5538,6 +5539,7 @@ static void mlx5e_get_base_stats(struct net_device *dev,
 				 struct netdev_queue_stats_tx *tx)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
+	u16 nch = mlx5e_stats_nch_read(priv);
 	struct mlx5e_ptp *ptp_channel;
 	int i, tc;
 
@@ -5549,7 +5551,7 @@ static void mlx5e_get_base_stats(struct net_device *dev,
 		rx->hw_gro_wire_packets = 0;
 		rx->hw_gro_wire_bytes = 0;
 
-		for (i = priv->channels.params.num_channels; i < priv->stats_nch; i++) {
+		for (i = priv->channels.params.num_channels; i < nch; i++) {
 			struct netdev_queue_stats_rx rx_i = {0};
 
 			mlx5e_get_queue_stats_rx(dev, i, &rx_i);
@@ -5585,7 +5587,7 @@ static void mlx5e_get_base_stats(struct net_device *dev,
 	tx->stop = 0;
 	tx->wake = 0;
 
-	for (i = 0; i < priv->stats_nch; i++) {
+	for (i = 0; i < nch; i++) {
 		struct mlx5e_channel_stats *channel_stats = priv->channel_stats[i];
 
 		/* handle two cases:

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

@@ -515,6 +515,7 @@ static void mlx5e_stats_update_stats_rq_page_pool(struct mlx5e_channel *c)
 static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(sw)
 {
 	struct mlx5e_sw_stats *s = &priv->stats.sw;
+	u16 nch = mlx5e_stats_nch_read(priv);
 	int i;
 
 	memset(s, 0, sizeof(*s));
@@ -522,7 +523,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(sw)
 	for (i = 0; i < priv->channels.num; i++) /* for active channels only */
 		mlx5e_stats_update_stats_rq_page_pool(priv->channels.c[i]);
 
-	for (i = 0; i < priv->stats_nch; i++) {
+	for (i = 0; i < nch; i++) {
 		struct mlx5e_channel_stats *channel_stats =
 			priv->channel_stats[i];
 
@@ -2614,7 +2615,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(ptp) { return; }
 
 static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(channels)
 {
-	int max_nch = priv->stats_nch;
+	int max_nch = mlx5e_stats_nch_read(priv);
 
 	return (NUM_RQ_STATS * max_nch) +
 	       (NUM_CH_STATS * max_nch) +
@@ -2627,8 +2628,8 @@ static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(channels)
 
 static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(channels)
 {
+	int max_nch = mlx5e_stats_nch_read(priv);
 	bool is_xsk = priv->xsk.ever_used;
-	int max_nch = priv->stats_nch;
 	int i, j, tc;
 
 	for (i = 0; i < max_nch; i++)
@@ -2660,8 +2661,8 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(channels)
 
 static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(channels)
 {
+	int max_nch = mlx5e_stats_nch_read(priv);
 	bool is_xsk = priv->xsk.ever_used;
-	int max_nch = priv->stats_nch;
 	int i, j, tc;
 
 	for (i = 0; i < max_nch; i++)

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

@@ -5547,6 +5547,9 @@ void mlx5e_tc_clean_fdb_peer_flows(struct mlx5_eswitch *esw)
 
 	mlx5_devcom_for_each_peer_entry(devcom, peer_esw, pos) {
 		i = mlx5_lag_get_dev_seq(peer_esw->dev);
+		if (i < 0)
+			continue;
+
 		list_for_each_entry_safe(flow, tmp, &esw->offloads.peer_flows[i], peer[i])
 			mlx5e_tc_del_fdb_peers_flow(flow);
 	}

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

@@ -135,10 +135,11 @@ void mlx5i_cleanup(struct mlx5e_priv *priv)
 
 static void mlx5i_grp_sw_update_stats(struct mlx5e_priv *priv)
 {
+	u16 nch = mlx5e_stats_nch_read(priv);
 	struct rtnl_link_stats64 s = {};
 	int i, j;
 
-	for (i = 0; i < priv->stats_nch; i++) {
+	for (i = 0; i < nch; i++) {
 		struct mlx5e_channel_stats *channel_stats;
 		struct mlx5e_rq_stats *rq_stats;
 

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

@@ -194,8 +194,10 @@ static void mlx5_mpesw_work(struct work_struct *work)
 	struct mlx5_lag *ldev = mpesww->lag;
 
 	devcom = mlx5_lag_get_devcom_comp(ldev);
-	if (!devcom)
-		return;
+	if (!devcom) {
+		mpesww->result = -ENODEV;
+		goto complete;
+	}
 
 	mlx5_devcom_comp_lock(devcom);
 	mlx5_mpesw_sd_devcoms_lock(ldev);
@@ -213,6 +215,7 @@ unlock:
 	mutex_unlock(&ldev->lock);
 	mlx5_mpesw_sd_devcoms_unlock(ldev);
 	mlx5_devcom_comp_unlock(devcom);
+complete:
 	complete(&mpesww->comp);
 }
 

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

@@ -78,7 +78,7 @@ static int mlx5_lag_create_single_fdb_filter(struct mlx5_lag *ldev, u32 filter)
 	}
 	return 0;
 err:
-	mlx5_lag_for_each_reverse(j, i, 0, ldev, filter) {
+	mlx5_lag_for_each_reverse(j, i - 1, 0, ldev, filter) {
 		struct mlx5_eswitch *slave_esw;
 
 		if (j == master_idx)