Merge tag 'net-next-7.4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Paolo Abeni:
 "This includes a significant number of low-priority fixes - especially
  in the NIC drivers area - that we deferred from the last few RCs in
  the previous cycle, which can't be easily outlined in the synopsis
  below.

  Core & protocols:

   - Continue the work on removing rtnl_lock dependencies:
      - per-netns ARP and ND neighbour tables, with the default settings
        now configurable per netns (inheritance from init_net is
        controlled by the new net.core.neigh_inherit_init_net sysctl)
      - RCU-protected configuration and rtnl_lock-less fill_info() for
        hsr, netkit, sit, vlan and vxlan devices
      - per-netns device unregistration for ip tunnel and gre devices
      - use the netdev instance lock instead of rtnl_lock when reading
        speed and duplex via sysfs
      - batch the flushing of uncached routes at device unregistration
        time, relieving rtnl_lock contention on netns dismantle.

   - Add hardware pacing offload support, admin-controlled via a new
     rtnetlink attribute, with sch_fq integration (implemented in idpf).

   - Re-segment BIG TCP GSO packets into GSO packets fitting the egress
     device limits instead of plain MSS-sized segments, improving
     throughput for mixed BIG TCP / non-BIG TCP paths by up to 70%.

   - Generate RSS keys that spread flows over all the RX queues; the
     previous random keys could leave some queues unused.

   - Optimize the bridge VLAN forwarding paths: cache the port-VLAN in
     fdb entries and consider only VLAN members when flooding, for ~10%
     more Mpps in the fdb forwarding path.

   - A few TCP/IP performance improvements aimed at efficient cache
     usage and reducing contention.

   - Add the TCP ROCCET congestion control, a CUBIC variant aimed at
     avoiding bufferbloat in cellular networks.

   - Continue the conversion of getsockopt callbacks to sockopt_t.

   - Add an ethtool command to list the front-facing ports of an
     interface, including SFP cages and modules, using the phy_port
     representation.

   - Enable BIG TCP support for bareudp tunnels.

   - Remove the IPV6_ADDRFORM socket option and disallow buggy TCP state
     transitions (listen() + shutdown() + connect() and connect() +
     connect(AF_UNSPEC) + listen()).

   - Remove most BUG_ON()s from core packet processing, replacing them
     with error paths.

  Wireless:

   - Latency improvements, including lockless station get/dump and
     beacon updates, plus RTNL reduction and locking cleanups.

   - Infrastructure for non-station TX/RX with MLO.

   - NAN (Wi-Fi Aware) Instant Communication support and other NAN
     improvements.

   - Control frame Integrity Protocol (CIP) and protected TWT support.

   - Improvements for AP regulatory checks.

  Netfilter:

   - Disable br_netfilter in user namespaces and schedule it for removal
     in 2027.

   - Restrict the raw table in nft_compat to the specific family, hook
     and priority.

   - Prepare the flowtable for mixed IPv4-over-IPv6 tunneling (and vice
     versa).

   - Use GFP_KERNEL_ACCOUNT for most netfilter allocations, for better
     integration with memcg.

   - Allow discovering conntrack zone filtering support in ctnetlink
     dumps, and fix nfnetlink_hook handling of large dumps.

  Deletions:

   - Move the LLC type 2 sockets out of tree. There are no known users
     and the code attracts a never-ending stream of LLM-driven fixes.

  Device drivers:

   - New drivers:
      - Meta Platforms NIC (mpnic), the second-generation NIC from Meta
      - initial skeleton of the Nebula-matrix NICs driver (nbl)
      - X-Powers AC200/AC300 Fast Ethernet PHYs

   - Ethernet high-speed NICs:
      - Intel:
         - i40e: XDP metadata support for RX hash and VLAN tag
         - ice: expose the E825 TSPLL state via the DPLL subsystem
      - nVidia/Mellanox:
         - move the data direct infrastructure from IB to core, in
           preparation for netdev support.
         - reduce the memory used per offloaded TC rule
      - Meta (fbnic):
         - support large io_uring zero-copy RX buffers
      - Microsoft vNIC (mana):
         - add BQL support

   - Ethernet NICs consumer, and embedded:
      - Airoha:
         - LRO offload support
      - Cadence (macb):
         - context swapping for ringparam and MTU changes, avoiding
           buffer loss under memory pressure
      - Mucse (rnpgbe):
         - TX/RX and link status support
      - NXP (enetc):
         - SR-IOV improvements and VF support for ENETC v4
      - Qualcomm (ppe):
         - IPQ5424 support
      - Realtek PCI (r8169):
         - phylink support
         - RSS support for RTL8127
      - Renesas (ravb):
         - gPTP support for R-Car Gen4
      - Synopsys (stmmac):
         - XDP multi-buffer support on the TX side
         - tc mqprio hw queue priority offload
         - support for RK3568 SGMII, Allwinner H616 EMAC1, UltraRISC
           DP1000 and Qualcomm sa8255p

   - Ethernet switches:
      - Mediatek (mt7530):
         - fast age and change conduit support
      - Microchip (ksz):
         - support for KSZ8995XA/KS8995XA
      - Microchip (lan966x):
         - PCIe FDMA support, ~20x throughput increase in PCIe endpoint
      - Microchip (sparx5):
         - Time Aware Shaper (taprio) offload
      - Motorcomm (yt921x):
         - LED and SerDes PCS support
      - Realtek (rtl8365mb):
         - EEE support

   - Ethernet PHYs:
      - Broadcom:
         - enable jumbo frames on BCM54xx
      - Realtek:
         - support for RTL8261CE_CG and RTL8261D_VM
         - MDIO support for RTL838x and RTL839x

   - WiFi drivers:
      - Broadcom (brcmfmac):
         - FT/OKC roaming offload
      - Intel (iwlwifi):
         - UHR sniffer support
         - support for newer UEFI/BIOS tables
      - MediaTek (mt76):
         - mt7925 NAN improvements
         - offchannel/scan improvements and MLO fixes
      - Morse Micro (mm81x):
         - monitor mode support
      - Qualcomm (ath12k):
         - IPQ5332 platform infrastructure
      - Realtek (rtw88):
         - RTL8723BS support
         - SDIO TX performance improvements
      - Realtek (rtw89):
         - P2P_DEVICE support
         - BT-coex updates for RTL8922D

   - Bluetooth:
      - move H:4 reassembly into the Bluetooth core
      - add generic support for vendor packets
      - MGMT: add security level changed event

   - Bluetooth drivers:
      - btusb: support Bulk Serialization Mode
      - Intel: support Draco and Titan Lake, allow unsigned firmware
      - Mediatek: MT7928 support
      - Qualcomm: QCC2072 support
      - Broadcom: Synaptics 4384 support"

* tag 'net-next-7.4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2126 commits)
  Bluetooth: btusb: disable by default Qualcomm multi-subsystem
  tipc: fix broadcast sender hang on last acker departure
  tipc: fix use-after-free of broadcast reception link at node release
  r8169: clear TX LPI on RTL8168h at link up after phylink conversion
  tun: Require CAP_NET_ADMIN to attach to an ownerless device
  net/sched/sch_cake: drop dead nla_nest_end() error check
  net/sched/sch_cake: widen buffer_used to u64
  net/sched/sch_cake: reduce parent backlog when clearing a tin
  net/sched/sch_cake: serialize reconfiguration with the datapath
  tg3: Add Datto SIRIS 5 1U Server to restart AER quirk table
  net/mlx5e: Stop asserting for RTNL when closing channels
  net: shrink the payload-only part of skb dataref to one bit
  net: wwan: iosm: validate msg_head before indexing msg_ring
  net: bgmac: rate limit RX error messages
  selftests: net: veth: test XDP_TX to a peer with GRO enabled
  veth: schedule the peer's NAPI after XDP_TX when only GRO is enabled
  pppoe: delete session hash entries by pointer match
  net: lan969x: don't disable hardirqs in fdma tx clear
  net: sparx5/lan969x: do not clobber the PSFP cycle timer update period
  net: lan969x: fix DSM calendar for empty taxis
  ...

3 files changed, 104 insertions, 12 deletions

diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h
index 2a28fcaa637d..0b52582118e8 100644
--- a/include/net/mana/gdma.h
+++ b/include/net/mana/gdma.h
@@ -427,14 +427,74 @@ enum gdma_context_flags {
 	GC_IN_SERVICE		= 1,
 };
 
+struct gdma_context;
+
+/**
+ * struct gdma_bus_ops - transport-specific operations
+ *
+ * Lets the bus-agnostic GDMA core drive PCI and CDX devices without
+ * testing configuration symbols. Each bus driver installs its own
+ * instance in gdma_context.bus_ops at probe time.
+ *
+ * @bus_name: Bus token used to build the per-vector IRQ names.
+ * @adev_prefix: Prefix used for auxiliary-device match names.
+ * @msix_can_alloc_dyn: True if the bus can allocate MSI-X vectors after
+ *	probe time. Buses that size their vector pool at probe and cannot
+ *	grow it later leave this NULL.
+ * @msix_virq: Return the Linux IRQ number backing an MSI vector, or
+ *	-EINVAL if the vector has not been allocated yet.
+ * @msix_alloc_at: Allocate an MSI vector on demand and return its IRQ
+ *	number, updating @msi with the index actually assigned. Buses that
+ *	allocate their whole pool up front leave this NULL.
+ * @msix_free: Release a vector obtained from @msix_alloc_at. Only needed
+ *	by buses that implement @msix_alloc_at.
+ * @msix_vec_count: Return the number of entries in the device MSI-X table,
+ *	used to clamp the vector count the core asks for. Buses that cannot
+ *	report a table size leave this NULL and the clamp is skipped.
+ * @setup_hwc_irqs: Set up the interrupts the hardware channel needs before
+ *	it is created.
+ * @setup_remaining_irqs: Set up the remaining interrupts once the device
+ *	resource limits are known.
+ * @remove_irqs: Release the interrupts set up by @setup_hwc_irqs and
+ *	@setup_remaining_irqs.
+ * @dev_reset: Reset the device using the bus-level reset mechanism.
+ * @schedule_serv_work: Queue device servicing or recovery. Buses without
+ *	a servicing path leave this NULL.
+ * @drv_cap_flags1: Extra capability bits this transport can honour, OR'ed
+ *	into GDMA_DRV_CAP_FLAGS1 when the driver version is negotiated.
+ */
+struct gdma_bus_ops {
+	const char *bus_name;
+	const char *adev_prefix;
+	bool (*msix_can_alloc_dyn)(struct gdma_context *gc);
+	int (*msix_virq)(struct gdma_context *gc, int msi);
+	int (*msix_alloc_at)(struct gdma_context *gc, int *msi);
+	void (*msix_free)(struct gdma_context *gc, int msi, int irq);
+	int (*msix_vec_count)(struct gdma_context *gc);
+	int (*setup_hwc_irqs)(struct gdma_context *gc);
+	int (*setup_remaining_irqs)(struct gdma_context *gc);
+	void (*remove_irqs)(struct gdma_context *gc);
+	int (*dev_reset)(struct gdma_context *gc);
+	int (*schedule_serv_work)(struct gdma_context *gc,
+				  enum gdma_eqe_type type);
+	u64 drv_cap_flags1;
+};
+
 struct gdma_context {
 	struct device		*dev;
 	struct dentry		*mana_pci_debugfs;
 
+	/* Transport-specific operations, installed by the bus driver */
+	const struct gdma_bus_ops *bus_ops;
+
 	/* Hardware max number of queues */
 	unsigned int		max_num_queues;
 	/* Per-vPort max number of queues */
 	unsigned int		max_num_queues_vport;
+	/* Number of vPorts reported by the device, capped at
+	 * MAX_PORTS_IN_MANA_DEV
+	 */
+	u16			num_ports;
 	unsigned int		max_num_msix;
 	unsigned int		num_msix_usable;
 	struct xarray		irq_contexts;
@@ -534,6 +594,10 @@ ssize_t mana_gd_read_ring(struct gdma_queue *q, char __user *buf,
 
 int mana_schedule_serv_work(struct gdma_context *gc, enum gdma_eqe_type type);
 
+int mana_gd_alloc_service_wq(struct gdma_context *gc);
+
+void mana_gd_free_service_wq(struct gdma_context *gc);
+
 void mana_gd_ring_dim(struct gdma_queue *cq, u32 mod_usec, bool mod_usec_vld,
 		      u32 mod_comps, bool mod_comps_vld);
 
@@ -628,6 +692,8 @@ struct gdma_eqe {
 #define MANA_PF2_DEVICE_ID 0x00C1
 #define MANA_VF_DEVICE_ID 0x00BA
 
+#define MANA_CDX_DEVICE_ID 0x00C2
+
 struct gdma_posted_wqe_info {
 	u32 wqe_size_in_bu;
 	/* Unmasked WQE start offset in GDMA basic units. */
@@ -694,21 +760,28 @@ enum {
 /* Driver supports non-contiguous queue buffers */
 #define GDMA_DRV_CAP_FLAG_1_NON_CONTIGUOUS_BUFFERS BIT(30)
 
+/* Capabilities in the PCI-only group below rely on dynamic MSI-X allocation
+ * and on the servicing and reset paths reached through
+ * mana_schedule_serv_work(). Transports that provide neither leave
+ * gdma_bus_ops.drv_cap_flags1 unset so the group is not advertised.
+ */
+#define GDMA_DRV_CAP_FLAGS1_PCI \
+	(GDMA_DRV_CAP_FLAG_1_DYNAMIC_IRQ_ALLOC_SUPPORT | \
+	 GDMA_DRV_CAP_FLAG_1_SELF_RESET_ON_EQE | \
+	 GDMA_DRV_CAP_FLAG_1_HANDLE_RECONFIG_EQE | \
+	 GDMA_DRV_CAP_FLAG_1_PROBE_RECOVERY | \
+	 GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECOVERY)
+
 #define GDMA_DRV_CAP_FLAGS1 \
 	(GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT | \
 	 GDMA_DRV_CAP_FLAG_1_NAPI_WKDONE_FIX | \
 	 GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECONFIG | \
 	 GDMA_DRV_CAP_FLAG_1_VARIABLE_INDIRECTION_TABLE_SUPPORT | \
 	 GDMA_DRV_CAP_FLAG_1_DEV_LIST_HOLES_SUP | \
-	 GDMA_DRV_CAP_FLAG_1_DYNAMIC_IRQ_ALLOC_SUPPORT | \
-	 GDMA_DRV_CAP_FLAG_1_SELF_RESET_ON_EQE | \
-	 GDMA_DRV_CAP_FLAG_1_HANDLE_RECONFIG_EQE | \
 	 GDMA_DRV_CAP_FLAG_1_HW_VPORT_LINK_AWARE | \
 	 GDMA_DRV_CAP_FLAG_1_PERIODIC_STATS_QUERY | \
 	 GDMA_DRV_CAP_FLAG_1_SKB_LINEARIZE | \
-	 GDMA_DRV_CAP_FLAG_1_PROBE_RECOVERY | \
 	 GDMA_DRV_CAP_FLAG_1_HANDLE_STALL_SQ_RECOVERY | \
-	 GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECOVERY | \
 	 GDMA_DRV_CAP_FLAG_1_EQ_MSI_UNSHARE_MULTI_VPORT | \
 	 GDMA_DRV_CAP_FLAG_1_DYN_INTERRUPT_MODERATION | \
 	 GDMA_DRV_CAP_FLAG_1_NON_CONTIGUOUS_BUFFERS)
@@ -1052,7 +1125,24 @@ struct gdma_destroy_dm_resp {
 	struct gdma_resp_hdr hdr;
 }; /* HW Data */
 
-int mana_gd_verify_vf_version(struct pci_dev *pdev);
+int mana_gd_verify_vf_version(struct gdma_context *gc);
+int mana_gd_query_max_resources(struct gdma_context *gc);
+int mana_gd_setup(struct gdma_context *gc);
+void mana_gd_cleanup(struct gdma_context *gc);
+int mana_gd_detect_devices(struct gdma_context *gc);
+int mana_gd_init_registers(struct gdma_context *gc);
+irqreturn_t mana_gd_intr(int irq, void *arg);
+void mana_gd_process_eq_events(void *arg);
+
+static inline u32 mana_gd_r32(struct gdma_context *g, u64 offset)
+{
+	return readl(g->bar0_va + offset);
+}
+
+static inline u64 mana_gd_r64(struct gdma_context *g, u64 offset)
+{
+	return readq(g->bar0_va + offset);
+}
 
 int mana_gd_register_device(struct gdma_dev *gd);
 int mana_gd_deregister_device(struct gdma_dev *gd);
@@ -1087,8 +1177,6 @@ void mana_unregister_debugfs(void);
 
 int mana_rdma_service_event(struct gdma_context *gc, enum gdma_service_type event);
 
-int mana_gd_suspend(struct pci_dev *pdev, pm_message_t state);
-int mana_gd_resume(struct pci_dev *pdev);
 
 bool mana_need_log(struct gdma_context *gc, int err);
 
@@ -1099,4 +1187,6 @@ void mana_gd_put_gic(struct gdma_context *gc, bool use_msi_bitmap, int msi);
 int mana_gd_query_device_cfg(struct gdma_context *gc, u32 proto_major_ver,
 			     u32 proto_minor_ver, u32 proto_micro_ver,
 			     u16 *max_num_vports, u8 *bm_hostmode);
+int mana_gd_dev_reset(struct gdma_context *gc);
+
 #endif /* _GDMA_H */
diff --git a/include/net/mana/hw_channel.h b/include/net/mana/hw_channel.h
index 16feb39616c1..1ab2d66c891e 100644
--- a/include/net/mana/hw_channel.h
+++ b/include/net/mana/hw_channel.h
@@ -20,8 +20,8 @@
 #define HWC_INIT_DATA_MAX_NUM_CQS	7
 #define HWC_INIT_DATA_PDID		8
 #define HWC_INIT_DATA_GPA_MKEY		9
-#define HWC_INIT_DATA_PF_DEST_RQ_ID	10
-#define HWC_INIT_DATA_PF_DEST_CQ_ID	11
+#define HWC_INIT_DATA_DEST_RQ_ID	10
+#define HWC_INIT_DATA_DEST_CQ_ID	11
 
 #define HWC_DATA_CFG_HWC_TIMEOUT 1
 #define HWC_DATA_HW_LINK_CONNECT 2
@@ -195,8 +195,8 @@ struct hw_channel_context {
 	struct semaphore sema;
 	struct gdma_resource inflight_msg_res;
 
-	u32 pf_dest_vrq_id;
-	u32 pf_dest_vrcq_id;
+	u32 dest_vrq_id;
+	u32 dest_vrcq_id;
 	u32 hwc_timeout;
 
 	struct hwc_caller_ctx *caller_ctx;
diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
index 8c3dc9d0b299..e1fa9131c490 100644
--- a/include/net/mana/mana.h
+++ b/include/net/mana/mana.h
@@ -672,6 +672,8 @@ struct mana_port_context {
 	u32 steer_cqe_coalescing;
 };
 
+netdev_tx_t __mana_start_xmit(struct sk_buff *skb, struct net_device *ndev,
+			      bool xdp);
 netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev);
 int mana_config_rss(struct mana_port_context *ac, enum TRI_STATE rx,
 		    bool update_hash, bool update_tab);