Merge tag 'net-6.16-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from bluetooth and wireless.

  Current release - regressions:

   - af_unix: allow passing cred for embryo without SO_PASSCRED/SO_PASSPIDFD

  Current release - new code bugs:

   - eth: airoha: correct enable mask for RX queues 16-31

   - veth: prevent NULL pointer dereference in veth_xdp_rcv when peer
     disappears under traffic

   - ipv6: move fib6_config_validate() to ip6_route_add(), prevent
     invalid routes

  Previous releases - regressions:

   - phy: phy_caps: don't skip better duplex match on non-exact match

   - dsa: b53: fix untagged traffic sent via cpu tagged with VID 0

   - Revert "wifi: mwifiex: Fix HT40 bandwidth issue.", it caused
     transient packet loss, exact reason not fully understood, yet

  Previous releases - always broken:

   - net: clear the dst when BPF is changing skb protocol (IPv4 <> IPv6)

   - sched: sfq: fix a potential crash on gso_skb handling

   - Bluetooth: intel: improve rx buffer posting to avoid causing issues
     in the firmware

   - eth: intel: i40e: make reset handling robust against multiple
     requests

   - eth: mlx5: ensure FW pages are always allocated on the local NUMA
     node, even when device is configure to 'serve' another node

   - wifi: ath12k: fix GCC_GCC_PCIE_HOT_RST definition for WCN7850,
     prevent kernel crashes

   - wifi: ath11k: avoid burning CPU in ath11k_debugfs_fw_stats_request()
     for 3 sec if fw_stats_done is not set"

* tag 'net-6.16-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (70 commits)
  selftests: drv-net: rss_ctx: Add test for ntuple rules targeting default RSS context
  net: ethtool: Don't check if RSS context exists in case of context 0
  af_unix: Allow passing cred for embryo without SO_PASSCRED/SO_PASSPIDFD.
  ipv6: Move fib6_config_validate() to ip6_route_add().
  net: drv: netdevsim: don't napi_complete() from netpoll
  net/mlx5: HWS, Add error checking to hws_bwc_rule_complex_hash_node_get()
  veth: prevent NULL pointer dereference in veth_xdp_rcv
  net_sched: remove qdisc_tree_flush_backlog()
  net_sched: ets: fix a race in ets_qdisc_change()
  net_sched: tbf: fix a race in tbf_change()
  net_sched: red: fix a race in __red_change()
  net_sched: prio: fix a race in prio_tune()
  net_sched: sch_sfq: reject invalid perturb period
  net: phy: phy_caps: Don't skip better duplex macth on non-exact match
  MAINTAINERS: Update Kuniyuki Iwashima's email address.
  selftests: net: add test case for NAT46 looping back dst
  net: clear the dst when changing skb protocol
  net/mlx5e: Fix number of lanes to UNKNOWN when using data_rate_oper
  net/mlx5e: Fix leak of Geneve TLV option object
  net/mlx5: HWS, make sure the uplink is the last destination
  ...

Author: torvalds

.mailmap

@@ -426,6 +426,9 @@ Krzysztof Wilczyński <kwilczynski@kernel.org> <krzysztof.wilczynski@linux.com>
 Krzysztof Wilczyński <kwilczynski@kernel.org> <kw@linux.com>
 Kshitiz Godara <quic_kgodara@quicinc.com> <kgodara@codeaurora.org>
 Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+Kuniyuki Iwashima <kuniyu@google.com> <kuniyu@amazon.com>
+Kuniyuki Iwashima <kuniyu@google.com> <kuniyu@amazon.co.jp>
+Kuniyuki Iwashima <kuniyu@google.com> <kuni1840@gmail.com>
 Kuogee Hsieh <quic_khsieh@quicinc.com> <khsieh@codeaurora.org>
 Lee Jones <lee@kernel.org> <joneslee@google.com>
 Lee Jones <lee@kernel.org> <lee.jones@canonical.com>

MAINTAINERS

@@ -17494,7 +17494,7 @@ F:	tools/testing/selftests/net/srv6*
 NETWORKING [TCP]
 M:	Eric Dumazet <edumazet@google.com>
 M:	Neal Cardwell <ncardwell@google.com>
-R:	Kuniyuki Iwashima <kuniyu@amazon.com>
+R:	Kuniyuki Iwashima <kuniyu@google.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	Documentation/networking/net_cachelines/tcp_sock.rst
@@ -17524,7 +17524,7 @@ F:	net/tls/*
 
 NETWORKING [SOCKETS]
 M:	Eric Dumazet <edumazet@google.com>
-M:	Kuniyuki Iwashima <kuniyu@amazon.com>
+M:	Kuniyuki Iwashima <kuniyu@google.com>
 M:	Paolo Abeni <pabeni@redhat.com>
 M:	Willem de Bruijn <willemb@google.com>
 S:	Maintained
@@ -17539,7 +17539,7 @@ F:	net/core/scm.c
 F:	net/socket.c
 
 NETWORKING [UNIX SOCKETS]
-M:	Kuniyuki Iwashima <kuniyu@amazon.com>
+M:	Kuniyuki Iwashima <kuniyu@google.com>
 S:	Maintained
 F:	include/net/af_unix.h
 F:	include/net/netns/unix.h

drivers/bluetooth/btintel_pcie.c

@@ -396,8 +396,13 @@ static int btintel_pcie_submit_rx(struct btintel_pcie_data *data)
 static int btintel_pcie_start_rx(struct btintel_pcie_data *data)
 {
 	int i, ret;
+	struct rxq *rxq = &data->rxq;
+
+	/* Post (BTINTEL_PCIE_RX_DESCS_COUNT - 3) buffers to overcome the
+	 * hardware issues leading to race condition at the firmware.
+	 */
 
-	for (i = 0; i < BTINTEL_PCIE_RX_MAX_QUEUE; i++) {
+	for (i = 0; i < rxq->count - 3; i++) {
 		ret = btintel_pcie_submit_rx(data);
 		if (ret)
 			return ret;
@@ -1782,8 +1787,8 @@ static int btintel_pcie_alloc(struct btintel_pcie_data *data)
 	 *  + size of index * Number of queues(2) * type of index array(4)
 	 *  + size of context information
 	 */
-	total = (sizeof(struct tfd) + sizeof(struct urbd0) + sizeof(struct frbd)
-		+ sizeof(struct urbd1)) * BTINTEL_DESCS_COUNT;
+	total = (sizeof(struct tfd) + sizeof(struct urbd0)) * BTINTEL_PCIE_TX_DESCS_COUNT;
+	total += (sizeof(struct frbd) + sizeof(struct urbd1)) * BTINTEL_PCIE_RX_DESCS_COUNT;
 
 	/* Add the sum of size of index array and size of ci struct */
 	total += (sizeof(u16) * BTINTEL_PCIE_NUM_QUEUES * 4) + sizeof(struct ctx_info);
@@ -1808,36 +1813,36 @@ static int btintel_pcie_alloc(struct btintel_pcie_data *data)
 	data->dma_v_addr = v_addr;
 
 	/* Setup descriptor count */
-	data->txq.count = BTINTEL_DESCS_COUNT;
-	data->rxq.count = BTINTEL_DESCS_COUNT;
+	data->txq.count = BTINTEL_PCIE_TX_DESCS_COUNT;
+	data->rxq.count = BTINTEL_PCIE_RX_DESCS_COUNT;
 
 	/* Setup tfds */
 	data->txq.tfds_p_addr = p_addr;
 	data->txq.tfds = v_addr;
 
-	p_addr += (sizeof(struct tfd) * BTINTEL_DESCS_COUNT);
-	v_addr += (sizeof(struct tfd) * BTINTEL_DESCS_COUNT);
+	p_addr += (sizeof(struct tfd) * BTINTEL_PCIE_TX_DESCS_COUNT);
+	v_addr += (sizeof(struct tfd) * BTINTEL_PCIE_TX_DESCS_COUNT);
 
 	/* Setup urbd0 */
 	data->txq.urbd0s_p_addr = p_addr;
 	data->txq.urbd0s = v_addr;
 
-	p_addr += (sizeof(struct urbd0) * BTINTEL_DESCS_COUNT);
-	v_addr += (sizeof(struct urbd0) * BTINTEL_DESCS_COUNT);
+	p_addr += (sizeof(struct urbd0) * BTINTEL_PCIE_TX_DESCS_COUNT);
+	v_addr += (sizeof(struct urbd0) * BTINTEL_PCIE_TX_DESCS_COUNT);
 
 	/* Setup FRBD*/
 	data->rxq.frbds_p_addr = p_addr;
 	data->rxq.frbds = v_addr;
 
-	p_addr += (sizeof(struct frbd) * BTINTEL_DESCS_COUNT);
-	v_addr += (sizeof(struct frbd) * BTINTEL_DESCS_COUNT);
+	p_addr += (sizeof(struct frbd) * BTINTEL_PCIE_RX_DESCS_COUNT);
+	v_addr += (sizeof(struct frbd) * BTINTEL_PCIE_RX_DESCS_COUNT);
 
 	/* Setup urbd1 */
 	data->rxq.urbd1s_p_addr = p_addr;
 	data->rxq.urbd1s = v_addr;
 
-	p_addr += (sizeof(struct urbd1) * BTINTEL_DESCS_COUNT);
-	v_addr += (sizeof(struct urbd1) * BTINTEL_DESCS_COUNT);
+	p_addr += (sizeof(struct urbd1) * BTINTEL_PCIE_RX_DESCS_COUNT);
+	v_addr += (sizeof(struct urbd1) * BTINTEL_PCIE_RX_DESCS_COUNT);
 
 	/* Setup data buffers for txq */
 	err = btintel_pcie_setup_txq_bufs(data, &data->txq);

drivers/bluetooth/btintel_pcie.h

@@ -154,8 +154,11 @@ enum msix_mbox_int_causes {
 /* Default interrupt timeout in msec */
 #define BTINTEL_DEFAULT_INTR_TIMEOUT_MS	3000
 
-/* The number of descriptors in TX/RX queues */
-#define BTINTEL_DESCS_COUNT	16
+/* The number of descriptors in TX queues */
+#define BTINTEL_PCIE_TX_DESCS_COUNT	32
+
+/* The number of descriptors in RX queues */
+#define BTINTEL_PCIE_RX_DESCS_COUNT	64
 
 /* Number of Queue for TX and RX
  * It indicates the index of the IA(Index Array)
@@ -177,9 +180,6 @@ enum {
 /* Doorbell vector for TFD */
 #define BTINTEL_PCIE_TX_DB_VEC	0
 
-/* Number of pending RX requests for downlink */
-#define BTINTEL_PCIE_RX_MAX_QUEUE	6
-
 /* Doorbell vector for FRBD */
 #define BTINTEL_PCIE_RX_DB_VEC	513
 

drivers/net/dsa/b53/b53_common.c

@@ -2034,9 +2034,6 @@ int b53_br_join(struct dsa_switch *ds, int port, struct dsa_bridge bridge,
 
 		b53_get_vlan_entry(dev, pvid, vl);
 		vl->members &= ~BIT(port);
-		if (vl->members == BIT(cpu_port))
-			vl->members &= ~BIT(cpu_port);
-		vl->untag = vl->members;
 		b53_set_vlan_entry(dev, pvid, vl);
 	}
 
@@ -2115,8 +2112,7 @@ void b53_br_leave(struct dsa_switch *ds, int port, struct dsa_bridge bridge)
 		}
 
 		b53_get_vlan_entry(dev, pvid, vl);
-		vl->members |= BIT(port) | BIT(cpu_port);
-		vl->untag |= BIT(port) | BIT(cpu_port);
+		vl->members |= BIT(port);
 		b53_set_vlan_entry(dev, pvid, vl);
 	}
 }

drivers/net/ethernet/airoha/airoha_regs.h

@@ -614,8 +614,9 @@
 	 RX19_DONE_INT_MASK | RX18_DONE_INT_MASK |	\
 	 RX17_DONE_INT_MASK | RX16_DONE_INT_MASK)
 
-#define RX_DONE_INT_MASK	(RX_DONE_HIGH_INT_MASK | RX_DONE_LOW_INT_MASK)
 #define RX_DONE_HIGH_OFFSET	fls(RX_DONE_HIGH_INT_MASK)
+#define RX_DONE_INT_MASK	\
+	((RX_DONE_HIGH_INT_MASK << RX_DONE_HIGH_OFFSET) | RX_DONE_LOW_INT_MASK)
 
 #define INT_RX2_MASK(_n)				\
 	((RX_NO_CPU_DSCP_HIGH_INT_MASK & (_n)) |	\

drivers/net/ethernet/freescale/enetc/Kconfig

@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 config FSL_ENETC_CORE
 	tristate
+	select NXP_NETC_LIB if NXP_NTMP
 	help
 	  This module supports common functionality between the PF and VF
 	  drivers for the NXP ENETC controller.
@@ -22,6 +23,9 @@ config NXP_NETC_LIB
 	  Switch, such as NETC Table Management Protocol (NTMP) 2.0, common tc
 	  flower and debugfs interfaces and so on.
 
+config NXP_NTMP
+	bool
+
 config FSL_ENETC
 	tristate "ENETC PF driver"
 	depends on PCI_MSI
@@ -45,7 +49,7 @@ config NXP_ENETC4
 	select FSL_ENETC_CORE
 	select FSL_ENETC_MDIO
 	select NXP_ENETC_PF_COMMON
-	select NXP_NETC_LIB
+	select NXP_NTMP
 	select PHYLINK
 	select DIMLIB
 	help

drivers/net/ethernet/intel/e1000/e1000_main.c

@@ -477,10 +477,6 @@ static void e1000_down_and_stop(struct e1000_adapter *adapter)
 
 	cancel_delayed_work_sync(&adapter->phy_info_task);
 	cancel_delayed_work_sync(&adapter->fifo_stall_task);
-
-	/* Only kill reset task if adapter is not resetting */
-	if (!test_bit(__E1000_RESETTING, &adapter->flags))
-		cancel_work_sync(&adapter->reset_task);
 }
 
 void e1000_down(struct e1000_adapter *adapter)
@@ -1266,6 +1262,10 @@ static void e1000_remove(struct pci_dev *pdev)
 
 	unregister_netdev(netdev);
 
+	/* Only kill reset task if adapter is not resetting */
+	if (!test_bit(__E1000_RESETTING, &adapter->flags))
+		cancel_work_sync(&adapter->reset_task);
+
 	e1000_phy_hw_reset(hw);
 
 	kfree(adapter->tx_ring);

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

@@ -1546,8 +1546,8 @@ static void i40e_cleanup_reset_vf(struct i40e_vf *vf)
  * @vf: pointer to the VF structure
  * @flr: VFLR was issued or not
  *
- * Returns true if the VF is in reset, resets successfully, or resets
- * are disabled and false otherwise.
+ * Return: True if reset was performed successfully or if resets are disabled.
+ * False if reset is already in progress.
  **/
 bool i40e_reset_vf(struct i40e_vf *vf, bool flr)
 {
@@ -1566,7 +1566,7 @@ bool i40e_reset_vf(struct i40e_vf *vf, bool flr)
 
 	/* If VF is being reset already we don't need to continue. */
 	if (test_and_set_bit(I40E_VF_STATE_RESETTING, &vf->vf_states))
-		return true;
+		return false;
 
 	i40e_trigger_vf_reset(vf, flr);
 
@@ -4328,7 +4328,10 @@ int i40e_vc_process_vflr_event(struct i40e_pf *pf)
 		reg = rd32(hw, I40E_GLGEN_VFLRSTAT(reg_idx));
 		if (reg & BIT(bit_idx))
 			/* i40e_reset_vf will clear the bit in GLGEN_VFLRSTAT */
-			i40e_reset_vf(vf, true);
+			if (!i40e_reset_vf(vf, true)) {
+				/* At least one VF did not finish resetting, retry next time */
+				set_bit(__I40E_VFLR_EVENT_PENDING, pf->state);
+			}
 	}
 
 	return 0;

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

@@ -3209,6 +3209,17 @@ static void iavf_reset_task(struct work_struct *work)
 	}
 
 continue_reset:
+	/* If we are still early in the state machine, just restart. */
+	if (adapter->state <= __IAVF_INIT_FAILED) {
+		iavf_shutdown_adminq(hw);
+		iavf_change_state(adapter, __IAVF_STARTUP);
+		iavf_startup(adapter);
+		queue_delayed_work(adapter->wq, &adapter->watchdog_task,
+				   msecs_to_jiffies(30));
+		netdev_unlock(netdev);
+		return;
+	}
+
 	/* We don't use netif_running() because it may be true prior to
 	 * ndo_open() returning, so we can't assume it means all our open
 	 * tasks have finished, since we're not holding the rtnl_lock here.