Merge tag 'net-6.6-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from bluetooth, netfilter, WiFi.

  Feels like an up-tick in regression fixes, mostly for older releases.
  The hfsc fix, tcp_disconnect() and Intel WWAN fixes stand out as
  fairly clear-cut user reported regressions. The mlx5 DMA bug was
  causing strife for 390x folks. The fixes themselves are not
  particularly scary, tho. No open investigations / outstanding reports
  at the time of writing.

  Current release - regressions:

   - eth: mlx5: perform DMA operations in the right locations, make
     devices usable on s390x, again

   - sched: sch_hfsc: upgrade 'rt' to 'sc' when it becomes a inner
     curve, previous fix of rejecting invalid config broke some scripts

   - rfkill: reduce data->mtx scope in rfkill_fop_open, avoid deadlock

   - revert "ethtool: Fix mod state of verbose no_mask bitset", needs
     more work

  Current release - new code bugs:

   - tcp: fix listen() warning with v4-mapped-v6 address

  Previous releases - regressions:

   - tcp: allow tcp_disconnect() again when threads are waiting, it was
     denied to plug a constant source of bugs but turns out .NET depends
     on it

   - eth: mlx5: fix double-free if buffer refill fails under OOM

   - revert "net: wwan: iosm: enable runtime pm support for 7560", it's
     causing regressions and the WWAN team at Intel disappeared

   - tcp: tsq: relax tcp_small_queue_check() when rtx queue contains a
     single skb, fix single-stream perf regression on some devices

  Previous releases - always broken:

   - Bluetooth:
      - fix issues in legacy BR/EDR PIN code pairing
      - correctly bounds check and pad HCI_MON_NEW_INDEX name

   - netfilter:
      - more fixes / follow ups for the large "commit protocol" rework,
        which went in as a fix to 6.5
      - fix null-derefs on netlink attrs which user may not pass in

   - tcp: fix excessive TLP and RACK timeouts from HZ rounding (bless
     Debian for keeping HZ=250 alive)

   - net: more strict VIRTIO_NET_HDR_GSO_UDP_L4 validation, prevent
     letting frankenstein UDP super-frames from getting into the stack

   - net: fix interface altnames when ifc moves to a new namespace

   - eth: qed: fix the size of the RX buffers

   - mptcp: avoid sending RST when closing the initial subflow"

* tag 'net-6.6-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (94 commits)
  Revert "ethtool: Fix mod state of verbose no_mask bitset"
  selftests: mptcp: join: no RST when rm subflow/addr
  mptcp: avoid sending RST when closing the initial subflow
  mptcp: more conservative check for zero probes
  tcp: check mptcp-level constraints for backlog coalescing
  selftests: mptcp: join: correctly check for no RST
  net: ti: icssg-prueth: Fix r30 CMDs bitmasks
  selftests: net: add very basic test for netdev names and namespaces
  net: move altnames together with the netdevice
  net: avoid UAF on deleted altname
  net: check for altname conflicts when changing netdev's netns
  net: fix ifname in netlink ntf during netns move
  net: ethernet: ti: Fix mixed module-builtin object
  net: phy: bcm7xxx: Add missing 16nm EPHY statistics
  ipv4: fib: annotate races around nh->nh_saddr_genid and nh->nh_saddr
  tcp_bpf: properly release resources on error paths
  net/sched: sch_hfsc: upgrade 'rt' to 'sc' when it becomes a inner curve
  net: mdio-mux: fix C45 access returning -EIO after API change
  tcp: tsq: relax tcp_small_queue_check() when rtx queue contains a single skb
  octeon_ep: update BQL sent bytes before ringing doorbell
  ...

Documentation/netlink/specs/devlink.yaml

@@ -323,7 +323,7 @@ operations:
             - dev-name
             - sb-index
         reply: &sb-get-reply
-          value: 11
+          value: 13
           attributes: *sb-id-attrs
       dump:
         request:
@@ -350,7 +350,7 @@ operations:
             - sb-index
             - sb-pool-index
         reply: &sb-pool-get-reply
-          value: 15
+          value: 17
           attributes: *sb-pool-id-attrs
       dump:
         request:
@@ -378,7 +378,7 @@ operations:
             - sb-index
             - sb-pool-index
         reply: &sb-port-pool-get-reply
-          value: 19
+          value: 21
           attributes: *sb-port-pool-id-attrs
       dump:
         request:
@@ -407,7 +407,7 @@ operations:
             - sb-pool-type
             - sb-tc-index
         reply: &sb-tc-pool-bind-get-reply
-          value: 23
+          value: 25
           attributes: *sb-tc-pool-bind-id-attrs
       dump:
         request:
@@ -538,7 +538,7 @@ operations:
             - dev-name
             - trap-name
         reply: &trap-get-reply
-          value: 61
+          value: 63
           attributes: *trap-id-attrs
       dump:
         request:
@@ -564,7 +564,7 @@ operations:
             - dev-name
             - trap-group-name
         reply: &trap-group-get-reply
-          value: 65
+          value: 67
           attributes: *trap-group-id-attrs
       dump:
         request:
@@ -590,7 +590,7 @@ operations:
             - dev-name
             - trap-policer-id
         reply: &trap-policer-get-reply
-          value: 69
+          value: 71
           attributes: *trap-policer-id-attrs
       dump:
         request:
@@ -617,7 +617,7 @@ operations:
             - port-index
             - rate-node-name
         reply: &rate-get-reply
-          value: 74
+          value: 76
           attributes: *rate-id-attrs
       dump:
         request:
@@ -643,7 +643,7 @@ operations:
             - dev-name
             - linecard-index
         reply: &linecard-get-reply
-          value: 78
+          value: 80
           attributes: *linecard-id-attrs
       dump:
         request:

Documentation/networking/representors.rst

@@ -162,9 +162,11 @@ How are representors identified?
 The representor netdevice should *not* directly refer to a PCIe device (e.g.
 through ``net_dev->dev.parent`` / ``SET_NETDEV_DEV()``), either of the
 representee or of the switchdev function.
-Instead, it should implement the ``ndo_get_devlink_port()`` netdevice op, which
-the kernel uses to provide the ``phys_switch_id`` and ``phys_port_name`` sysfs
-nodes.  (Some legacy drivers implement ``ndo_get_port_parent_id()`` and
+Instead, the driver should use the ``SET_NETDEV_DEVLINK_PORT`` macro to
+assign a devlink port instance to the netdevice before registering the
+netdevice; the kernel uses the devlink port to provide the ``phys_switch_id``
+and ``phys_port_name`` sysfs nodes.
+(Some legacy drivers implement ``ndo_get_port_parent_id()`` and
 ``ndo_get_phys_port_name()`` directly, but this is deprecated.)  See
 :ref:`Documentation/networking/devlink/devlink-port.rst <devlink_port>` for the
 details of this API.

drivers/bluetooth/btrtl.c

@@ -962,13 +962,10 @@ static void btrtl_dmp_hdr(struct hci_dev *hdev, struct sk_buff *skb)
 	skb_put_data(skb, buf, strlen(buf));
 }
 
-static int btrtl_register_devcoredump_support(struct hci_dev *hdev)
+static void btrtl_register_devcoredump_support(struct hci_dev *hdev)
 {
-	int err;
+	hci_devcd_register(hdev, btrtl_coredump, btrtl_dmp_hdr, NULL);
 
-	err = hci_devcd_register(hdev, btrtl_coredump, btrtl_dmp_hdr, NULL);
-
-	return err;
 }
 
 void btrtl_set_driver_name(struct hci_dev *hdev, const char *driver_name)
@@ -1255,8 +1252,7 @@ int btrtl_download_firmware(struct hci_dev *hdev,
 	}
 
 done:
-	if (!err)
-		err = btrtl_register_devcoredump_support(hdev);
+	btrtl_register_devcoredump_support(hdev);
 
 	return err;
 }

drivers/bluetooth/hci_vhci.c

@@ -74,7 +74,10 @@ static int vhci_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
 	struct vhci_data *data = hci_get_drvdata(hdev);
 
 	memcpy(skb_push(skb, 1), &hci_skb_pkt_type(skb), 1);
+
+	mutex_lock(&data->open_mutex);
 	skb_queue_tail(&data->readq, skb);
+	mutex_unlock(&data->open_mutex);
 
 	wake_up_interruptible(&data->read_wait);
 	return 0;

drivers/net/bonding/bond_main.c

@@ -4023,7 +4023,7 @@ static inline const void *bond_pull_data(struct sk_buff *skb,
 	if (likely(n <= hlen))
 		return data;
 	else if (skb && likely(pskb_may_pull(skb, n)))
-		return skb->head;
+		return skb->data;
 
 	return NULL;
 }

drivers/net/dsa/bcm_sf2.c

@@ -617,17 +617,16 @@ static int bcm_sf2_mdio_register(struct dsa_switch *ds)
 	dn = of_find_compatible_node(NULL, NULL, "brcm,unimac-mdio");
 	priv->master_mii_bus = of_mdio_find_bus(dn);
 	if (!priv->master_mii_bus) {
-		of_node_put(dn);
-		return -EPROBE_DEFER;
+		err = -EPROBE_DEFER;
+		goto err_of_node_put;
 	}
 
-	get_device(&priv->master_mii_bus->dev);
 	priv->master_mii_dn = dn;
 
 	priv->slave_mii_bus = mdiobus_alloc();
 	if (!priv->slave_mii_bus) {
-		of_node_put(dn);
-		return -ENOMEM;
+		err = -ENOMEM;
+		goto err_put_master_mii_bus_dev;
 	}
 
 	priv->slave_mii_bus->priv = priv;
@@ -684,11 +683,17 @@ static int bcm_sf2_mdio_register(struct dsa_switch *ds)
 	}
 
 	err = mdiobus_register(priv->slave_mii_bus);
-	if (err && dn) {
-		mdiobus_free(priv->slave_mii_bus);
-		of_node_put(dn);
-	}
+	if (err && dn)
+		goto err_free_slave_mii_bus;
 
+	return 0;
+
+err_free_slave_mii_bus:
+	mdiobus_free(priv->slave_mii_bus);
+err_put_master_mii_bus_dev:
+	put_device(&priv->master_mii_bus->dev);
+err_of_node_put:
+	of_node_put(dn);
 	return err;
 }
 
@@ -696,6 +701,7 @@ static void bcm_sf2_mdio_unregister(struct bcm_sf2_priv *priv)
 {
 	mdiobus_unregister(priv->slave_mii_bus);
 	mdiobus_free(priv->slave_mii_bus);
+	put_device(&priv->master_mii_bus->dev);
 	of_node_put(priv->master_mii_dn);
 }
 

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

@@ -911,7 +911,7 @@ static int csk_wait_memory(struct chtls_dev *cdev,
 			   struct sock *sk, long *timeo_p)
 {
 	DEFINE_WAIT_FUNC(wait, woken_wake_function);
-	int err = 0;
+	int ret, err = 0;
 	long current_timeo;
 	long vm_wait = 0;
 	bool noblock;
@@ -942,10 +942,13 @@ static int csk_wait_memory(struct chtls_dev *cdev,
 
 		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 		sk->sk_write_pending++;
-		sk_wait_event(sk, &current_timeo, sk->sk_err ||
-			      (sk->sk_shutdown & SEND_SHUTDOWN) ||
-			      (csk_mem_free(cdev, sk) && !vm_wait), &wait);
+		ret = sk_wait_event(sk, &current_timeo, sk->sk_err ||
+				    (sk->sk_shutdown & SEND_SHUTDOWN) ||
+				    (csk_mem_free(cdev, sk) && !vm_wait),
+				    &wait);
 		sk->sk_write_pending--;
+		if (ret < 0)
+			goto do_error;
 
 		if (vm_wait) {
 			vm_wait -= current_timeo;
@@ -1348,6 +1351,7 @@ static int chtls_pt_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 	int copied = 0;
 	int target;
 	long timeo;
+	int ret;
 
 	buffers_freed = 0;
 
@@ -1423,7 +1427,11 @@ static int chtls_pt_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		if (copied >= target)
 			break;
 		chtls_cleanup_rbuf(sk, copied);
-		sk_wait_data(sk, &timeo, NULL);
+		ret = sk_wait_data(sk, &timeo, NULL);
+		if (ret < 0) {
+			copied = copied ? : ret;
+			goto unlock;
+		}
 		continue;
 found_ok_skb:
 		if (!skb->len) {
@@ -1518,6 +1526,8 @@ skip_copy:
 
 	if (buffers_freed)
 		chtls_cleanup_rbuf(sk, copied);
+
+unlock:
 	release_sock(sk);
 	return copied;
 }
@@ -1534,6 +1544,7 @@ static int peekmsg(struct sock *sk, struct msghdr *msg,
 	int copied = 0;
 	size_t avail;          /* amount of available data in current skb */
 	long timeo;
+	int ret;
 
 	lock_sock(sk);
 	timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
@@ -1585,7 +1596,12 @@ static int peekmsg(struct sock *sk, struct msghdr *msg,
 			release_sock(sk);
 			lock_sock(sk);
 		} else {
-			sk_wait_data(sk, &timeo, NULL);
+			ret = sk_wait_data(sk, &timeo, NULL);
+			if (ret < 0) {
+				/* here 'copied' is 0 due to previous checks */
+				copied = ret;
+				break;
+			}
 		}
 
 		if (unlikely(peek_seq != tp->copied_seq)) {
@@ -1656,6 +1672,7 @@ int chtls_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 	int copied = 0;
 	long timeo;
 	int target;             /* Read at least this many bytes */
+	int ret;
 
 	buffers_freed = 0;
 
@@ -1747,7 +1764,11 @@ int chtls_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		if (copied >= target)
 			break;
 		chtls_cleanup_rbuf(sk, copied);
-		sk_wait_data(sk, &timeo, NULL);
+		ret = sk_wait_data(sk, &timeo, NULL);
+		if (ret < 0) {
+			copied = copied ? : ret;
+			goto unlock;
+		}
 		continue;
 
 found_ok_skb:
@@ -1816,6 +1837,7 @@ skip_copy:
 	if (buffers_freed)
 		chtls_cleanup_rbuf(sk, copied);
 
+unlock:
 	release_sock(sk);
 	return copied;
 }

drivers/net/ethernet/google/gve/gve_rx.c

@@ -146,7 +146,7 @@ static int gve_prefill_rx_pages(struct gve_rx_ring *rx)
 		err = gve_rx_alloc_buffer(priv, &priv->pdev->dev, &rx->data.page_info[i],
 					  &rx->data.data_ring[i]);
 		if (err)
-			goto alloc_err;
+			goto alloc_err_rda;
 	}
 
 	if (!rx->data.raw_addressing) {
@@ -171,12 +171,26 @@ static int gve_prefill_rx_pages(struct gve_rx_ring *rx)
 	return slots;
 
 alloc_err_qpl:
+	/* Fully free the copy pool pages. */
 	while (j--) {
 		page_ref_sub(rx->qpl_copy_pool[j].page,
 			     rx->qpl_copy_pool[j].pagecnt_bias - 1);
 		put_page(rx->qpl_copy_pool[j].page);
 	}
-alloc_err:
+
+	/* Do not fully free QPL pages - only remove the bias added in this
+	 * function with gve_setup_rx_buffer.
+	 */
+	while (i--)
+		page_ref_sub(rx->data.page_info[i].page,
+			     rx->data.page_info[i].pagecnt_bias - 1);
+
+	gve_unassign_qpl(priv, rx->data.qpl->id);
+	rx->data.qpl = NULL;
+
+	return err;
+
+alloc_err_rda:
 	while (i--)
 		gve_rx_free_buffer(&priv->pdev->dev,
 				   &rx->data.page_info[i],

drivers/net/ethernet/intel/i40e/i40e_common.c

@@ -1082,7 +1082,7 @@ void i40e_clear_hw(struct i40e_hw *hw)
 		     I40E_PFLAN_QALLOC_FIRSTQ_SHIFT;
 	j = (val & I40E_PFLAN_QALLOC_LASTQ_MASK) >>
 	    I40E_PFLAN_QALLOC_LASTQ_SHIFT;
-	if (val & I40E_PFLAN_QALLOC_VALID_MASK)
+	if (val & I40E_PFLAN_QALLOC_VALID_MASK && j >= base_queue)
 		num_queues = (j - base_queue) + 1;
 	else
 		num_queues = 0;
@@ -1092,7 +1092,7 @@ void i40e_clear_hw(struct i40e_hw *hw)
 	    I40E_PF_VT_PFALLOC_FIRSTVF_SHIFT;
 	j = (val & I40E_PF_VT_PFALLOC_LASTVF_MASK) >>
 	    I40E_PF_VT_PFALLOC_LASTVF_SHIFT;
-	if (val & I40E_PF_VT_PFALLOC_VALID_MASK)
+	if (val & I40E_PF_VT_PFALLOC_VALID_MASK && j >= i)
 		num_vfs = (j - i) + 1;
 	else
 		num_vfs = 0;

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

@@ -1201,8 +1201,7 @@ static void ice_set_rss_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi)
 
 	ctxt->info.q_opt_rss = ((lut_type << ICE_AQ_VSI_Q_OPT_RSS_LUT_S) &
 				ICE_AQ_VSI_Q_OPT_RSS_LUT_M) |
-				((hash_type << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) &
-				 ICE_AQ_VSI_Q_OPT_RSS_HASH_M);
+				(hash_type & ICE_AQ_VSI_Q_OPT_RSS_HASH_M);
 }
 
 static void

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

@@ -6,6 +6,7 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <generated/utsrelease.h>
+#include <linux/crash_dump.h>
 #include "ice.h"
 #include "ice_base.h"
 #include "ice_lib.h"
@@ -4683,6 +4684,9 @@ static void ice_init_features(struct ice_pf *pf)
 
 static void ice_deinit_features(struct ice_pf *pf)
 {
+	if (ice_is_safe_mode(pf))
+		return;
+
 	ice_deinit_lag(pf);
 	if (test_bit(ICE_FLAG_DCB_CAPABLE, pf->flags))
 		ice_cfg_lldp_mib_change(&pf->hw, false);
@@ -5014,6 +5018,20 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 		return -EINVAL;
 	}
 
+	/* when under a kdump kernel initiate a reset before enabling the
+	 * device in order to clear out any pending DMA transactions. These
+	 * transactions can cause some systems to machine check when doing
+	 * the pcim_enable_device() below.
+	 */
+	if (is_kdump_kernel()) {
+		pci_save_state(pdev);
+		pci_clear_master(pdev);
+		err = pcie_flr(pdev);
+		if (err)
+			return err;
+		pci_restore_state(pdev);
+	}
+
 	/* this driver uses devres, see
 	 * Documentation/driver-api/driver-model/devres.rst
 	 */

drivers/net/ethernet/marvell/octeon_ep/octep_main.c

@@ -715,20 +715,19 @@ static netdev_tx_t octep_start_xmit(struct sk_buff *skb,
 		hw_desc->dptr = tx_buffer->sglist_dma;
 	}
 
-	/* Flush the hw descriptor before writing to doorbell */
-	wmb();
-
-	/* Ring Doorbell to notify the NIC there is a new packet */
-	writel(1, iq->doorbell_reg);
+	netdev_tx_sent_queue(iq->netdev_q, skb->len);
+	skb_tx_timestamp(skb);
 	atomic_inc(&iq->instr_pending);
 	wi++;
 	if (wi == iq->max_count)
 		wi = 0;
 	iq->host_write_index = wi;
+	/* Flush the hw descriptor before writing to doorbell */
+	wmb();
 
-	netdev_tx_sent_queue(iq->netdev_q, skb->len);
+	/* Ring Doorbell to notify the NIC there is a new packet */
+	writel(1, iq->doorbell_reg);
 	iq->stats.instr_posted++;
-	skb_tx_timestamp(skb);
 	return NETDEV_TX_OK;
 
 dma_map_sg_err:

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

@@ -2186,52 +2186,23 @@ static u16 cmdif_rev(struct mlx5_core_dev *dev)
 
 int mlx5_cmd_init(struct mlx5_core_dev *dev)
 {
-	int size = sizeof(struct mlx5_cmd_prot_block);
-	int align = roundup_pow_of_two(size);
 	struct mlx5_cmd *cmd = &dev->cmd;
-	u32 cmd_l;
-	int err;
 
-	cmd->pool = dma_pool_create("mlx5_cmd", mlx5_core_dma_dev(dev), size, align, 0);
-	if (!cmd->pool)
-		return -ENOMEM;
-
-	err = alloc_cmd_page(dev, cmd);
-	if (err)
-		goto err_free_pool;
-
-	cmd_l = (u32)(cmd->dma);
-	if (cmd_l & 0xfff) {
-		mlx5_core_err(dev, "invalid command queue address\n");
-		err = -ENOMEM;
-		goto err_cmd_page;
-	}
 	cmd->checksum_disabled = 1;
 
 	spin_lock_init(&cmd->alloc_lock);
 	spin_lock_init(&cmd->token_lock);
 
-	create_msg_cache(dev);
-
 	set_wqname(dev);
 	cmd->wq = create_singlethread_workqueue(cmd->wq_name);
 	if (!cmd->wq) {
 		mlx5_core_err(dev, "failed to create command workqueue\n");
-		err = -ENOMEM;
-		goto err_cache;
+		return -ENOMEM;
 	}
 
 	mlx5_cmdif_debugfs_init(dev);
 
 	return 0;
-
-err_cache:
-	destroy_msg_cache(dev);
-err_cmd_page:
-	free_cmd_page(dev, cmd);
-err_free_pool:
-	dma_pool_destroy(cmd->pool);
-	return err;
 }
 
 void mlx5_cmd_cleanup(struct mlx5_core_dev *dev)
@@ -2240,15 +2211,15 @@ void mlx5_cmd_cleanup(struct mlx5_core_dev *dev)
 
 	mlx5_cmdif_debugfs_cleanup(dev);
 	destroy_workqueue(cmd->wq);
-	destroy_msg_cache(dev);
-	free_cmd_page(dev, cmd);
-	dma_pool_destroy(cmd->pool);
 }
 
 int mlx5_cmd_enable(struct mlx5_core_dev *dev)
 {
+	int size = sizeof(struct mlx5_cmd_prot_block);
+	int align = roundup_pow_of_two(size);
 	struct mlx5_cmd *cmd = &dev->cmd;
 	u32 cmd_h, cmd_l;
+	int err;
 
 	memset(&cmd->vars, 0, sizeof(cmd->vars));
 	cmd->vars.cmdif_rev = cmdif_rev(dev);
@@ -2281,10 +2252,21 @@ int mlx5_cmd_enable(struct mlx5_core_dev *dev)
 	sema_init(&cmd->vars.pages_sem, 1);
 	sema_init(&cmd->vars.throttle_sem, DIV_ROUND_UP(cmd->vars.max_reg_cmds, 2));
 
+	cmd->pool = dma_pool_create("mlx5_cmd", mlx5_core_dma_dev(dev), size, align, 0);
+	if (!cmd->pool)
+		return -ENOMEM;
+
+	err = alloc_cmd_page(dev, cmd);
+	if (err)
+		goto err_free_pool;
+
 	cmd_h = (u32)((u64)(cmd->dma) >> 32);
 	cmd_l = (u32)(cmd->dma);
-	if (WARN_ON(cmd_l & 0xfff))
-		return -EINVAL;
+	if (cmd_l & 0xfff) {
+		mlx5_core_err(dev, "invalid command queue address\n");
+		err = -ENOMEM;
+		goto err_cmd_page;
+	}
 
 	iowrite32be(cmd_h, &dev->iseg->cmdq_addr_h);
 	iowrite32be(cmd_l, &dev->iseg->cmdq_addr_l_sz);
@@ -2297,17 +2279,27 @@ int mlx5_cmd_enable(struct mlx5_core_dev *dev)
 	cmd->mode = CMD_MODE_POLLING;
 	cmd->allowed_opcode = CMD_ALLOWED_OPCODE_ALL;
 
+	create_msg_cache(dev);
 	create_debugfs_files(dev);
 
 	return 0;
+
+err_cmd_page:
+	free_cmd_page(dev, cmd);
+err_free_pool:
+	dma_pool_destroy(cmd->pool);
+	return err;
 }
 
 void mlx5_cmd_disable(struct mlx5_core_dev *dev)
 {
 	struct mlx5_cmd *cmd = &dev->cmd;
 
-	clean_debug_files(dev);
 	flush_workqueue(cmd->wq);
+	clean_debug_files(dev);
+	destroy_msg_cache(dev);
+	free_cmd_page(dev, cmd);
+	dma_pool_destroy(cmd->pool);
 }
 
 void mlx5_cmd_set_state(struct mlx5_core_dev *dev,

drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c

@@ -848,7 +848,7 @@ static void mlx5_fw_tracer_ownership_change(struct work_struct *work)
 
 	mlx5_core_dbg(tracer->dev, "FWTracer: ownership changed, current=(%d)\n", tracer->owner);
 	if (tracer->owner) {
-		tracer->owner = false;
+		mlx5_fw_tracer_ownership_acquire(tracer);
 		return;
 	}
 

drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c

@@ -467,6 +467,17 @@ static int mlx5_esw_bridge_switchdev_event(struct notifier_block *nb,
 		/* only handle the event on peers */
 		if (mlx5_esw_bridge_is_local(dev, rep, esw))
 			break;
+
+		fdb_info = container_of(info,
+					struct switchdev_notifier_fdb_info,
+					info);
+		/* Mark for deletion to prevent the update wq task from
+		 * spuriously refreshing the entry which would mark it again as
+		 * offloaded in SW bridge. After this fallthrough to regular
+		 * async delete code.
+		 */
+		mlx5_esw_bridge_fdb_mark_deleted(dev, vport_num, esw_owner_vhca_id, br_offloads,
+						 fdb_info);
 		fallthrough;
 	case SWITCHDEV_FDB_ADD_TO_DEVICE:
 	case SWITCHDEV_FDB_DEL_TO_DEVICE:

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

@@ -24,7 +24,8 @@ static int mlx5e_set_int_port_tunnel(struct mlx5e_priv *priv,
 
 	route_dev = dev_get_by_index(dev_net(e->out_dev), e->route_dev_ifindex);
 
-	if (!route_dev || !netif_is_ovs_master(route_dev))
+	if (!route_dev || !netif_is_ovs_master(route_dev) ||
+	    attr->parse_attr->filter_dev == e->out_dev)
 		goto out;
 
 	err = mlx5e_set_fwd_to_int_port_actions(priv, attr, e->route_dev_ifindex,

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

@@ -874,11 +874,11 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 	}
 
 out:
-	if (flags & XDP_XMIT_FLUSH) {
-		if (sq->mpwqe.wqe)
-			mlx5e_xdp_mpwqe_complete(sq);
+	if (sq->mpwqe.wqe)
+		mlx5e_xdp_mpwqe_complete(sq);
+
+	if (flags & XDP_XMIT_FLUSH)
 		mlx5e_xmit_xdp_doorbell(sq);
-	}
 
 	return nxmit;
 }

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

@@ -701,7 +701,7 @@ mlx5e_rep_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
 
 	/* update HW stats in background for next time */
 	mlx5e_queue_update_stats(priv);
-	memcpy(stats, &priv->stats.vf_vport, sizeof(*stats));
+	mlx5e_stats_copy_rep_stats(stats, &priv->stats.rep_stats);
 }
 
 static int mlx5e_rep_change_mtu(struct net_device *netdev, int new_mtu)
@@ -769,6 +769,7 @@ static int mlx5e_rep_max_nch_limit(struct mlx5_core_dev *mdev)
 
 static void mlx5e_build_rep_params(struct net_device *netdev)
 {
+	const bool take_rtnl = netdev->reg_state == NETREG_REGISTERED;
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 	struct mlx5_eswitch_rep *rep = rpriv->rep;
@@ -794,8 +795,15 @@ static void mlx5e_build_rep_params(struct net_device *netdev)
 	/* RQ */
 	mlx5e_build_rq_params(mdev, params);
 
+	/* If netdev is already registered (e.g. move from nic profile to uplink,
+	 * RTNL lock must be held before triggering netdev notifiers.
+	 */
+	if (take_rtnl)
+		rtnl_lock();
 	/* update XDP supported features */
 	mlx5e_set_xdp_feature(netdev);
+	if (take_rtnl)
+		rtnl_unlock();
 
 	/* CQ moderation params */
 	params->rx_dim_enabled = MLX5_CAP_GEN(mdev, cq_moderation);

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

@@ -457,26 +457,41 @@ static int mlx5e_alloc_rx_wqes(struct mlx5e_rq *rq, u16 ix, int wqe_bulk)
 static int mlx5e_refill_rx_wqes(struct mlx5e_rq *rq, u16 ix, int wqe_bulk)
 {
 	int remaining = wqe_bulk;
-	int i = 0;
+	int total_alloc = 0;
+	int refill_alloc;
+	int refill;
 
 	/* The WQE bulk is split into smaller bulks that are sized
 	 * according to the page pool cache refill size to avoid overflowing
 	 * the page pool cache due to too many page releases at once.
 	 */
 	do {
-		int refill = min_t(u16, rq->wqe.info.refill_unit, remaining);
-		int alloc_count;
+		refill = min_t(u16, rq->wqe.info.refill_unit, remaining);
 
-		mlx5e_free_rx_wqes(rq, ix + i, refill);
-		alloc_count = mlx5e_alloc_rx_wqes(rq, ix + i, refill);
-		i += alloc_count;
-		if (unlikely(alloc_count != refill))
-			break;
+		mlx5e_free_rx_wqes(rq, ix + total_alloc, refill);
+		refill_alloc = mlx5e_alloc_rx_wqes(rq, ix + total_alloc, refill);
+		if (unlikely(refill_alloc != refill))
+			goto err_free;
 
+		total_alloc += refill_alloc;
 		remaining -= refill;
 	} while (remaining);
 
-	return i;
+	return total_alloc;
+
+err_free:
+	mlx5e_free_rx_wqes(rq, ix, total_alloc + refill_alloc);
+
+	for (int i = 0; i < total_alloc + refill; i++) {
+		int j = mlx5_wq_cyc_ctr2ix(&rq->wqe.wq, ix + i);
+		struct mlx5e_wqe_frag_info *frag;
+
+		frag = get_frag(rq, j);
+		for (int k = 0; k < rq->wqe.info.num_frags; k++, frag++)
+			frag->flags |= BIT(MLX5E_WQE_FRAG_SKIP_RELEASE);
+	}
+
+	return 0;
 }
 
 static void
@@ -816,6 +831,8 @@ err_unmap:
 		mlx5e_page_release_fragmented(rq, frag_page);
 	}
 
+	bitmap_fill(wi->skip_release_bitmap, rq->mpwqe.pages_per_wqe);
+
 err:
 	rq->stats->buff_alloc_err++;
 

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

@@ -484,11 +484,20 @@ struct mlx5e_stats {
 	struct mlx5e_vnic_env_stats vnic;
 	struct mlx5e_vport_stats vport;
 	struct mlx5e_pport_stats pport;
-	struct rtnl_link_stats64 vf_vport;
 	struct mlx5e_pcie_stats pcie;
 	struct mlx5e_rep_stats rep_stats;
 };
 
+static inline void mlx5e_stats_copy_rep_stats(struct rtnl_link_stats64 *vf_vport,
+					      struct mlx5e_rep_stats *rep_stats)
+{
+	memset(vf_vport, 0, sizeof(*vf_vport));
+	vf_vport->rx_packets = rep_stats->vport_rx_packets;
+	vf_vport->tx_packets = rep_stats->vport_tx_packets;
+	vf_vport->rx_bytes = rep_stats->vport_rx_bytes;
+	vf_vport->tx_bytes = rep_stats->vport_tx_bytes;
+}
+
 extern mlx5e_stats_grp_t mlx5e_nic_stats_grps[];
 unsigned int mlx5e_nic_stats_grps_num(struct mlx5e_priv *priv);