Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted

Pull networking updates from Jakub Kicinski:
 "Core:

   - Add dedicated kmem_cache for typical/small skb->head, avoid having
     to access struct page at kfree time, and improve memory use.

   - Introduce sysctl to set default RPS configuration for new netdevs.

   - Define Netlink protocol specification format which can be used to
     describe messages used by each family and auto-generate parsers.
     Add tools for generating kernel data structures and uAPI headers.

   - Expose all net/core sysctls inside netns.

   - Remove 4s sleep in netpoll if carrier is instantly detected on
     boot.

   - Add configurable limit of MDB entries per port, and port-vlan.

   - Continue populating drop reasons throughout the stack.

   - Retire a handful of legacy Qdiscs and classifiers.

  Protocols:

   - Support IPv4 big TCP (TSO frames larger than 64kB).

   - Add IP_LOCAL_PORT_RANGE socket option, to control local port range
     on socket by socket basis.

   - Track and report in procfs number of MPTCP sockets used.

   - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
     manager.

   - IPv6: don't check net.ipv6.route.max_size and rely on garbage
     collection to free memory (similarly to IPv4).

   - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).

   - ICMP: add per-rate limit counters.

   - Add support for user scanning requests in ieee802154.

   - Remove static WEP support.

   - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
     reporting.

   - WiFi 7 EHT channel puncturing support (client & AP).

  BPF:

   - Add a rbtree data structure following the "next-gen data structure"
     precedent set by recently added linked list, that is, by using
     kfunc + kptr instead of adding a new BPF map type.

   - Expose XDP hints via kfuncs with initial support for RX hash and
     timestamp metadata.

   - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
     better support decap on GRE tunnel devices not operating in collect
     metadata.

   - Improve x86 JIT's codegen for PROBE_MEM runtime error checks.

   - Remove the need for trace_printk_lock for bpf_trace_printk and
     bpf_trace_vprintk helpers.

   - Extend libbpf's bpf_tracing.h support for tracing arguments of
     kprobes/uprobes and syscall as a special case.

   - Significantly reduce the search time for module symbols by
     livepatch and BPF.

   - Enable cpumasks to be used as kptrs, which is useful for tracing
     programs tracking which tasks end up running on which CPUs in
     different time intervals.

   - Add support for BPF trampoline on s390x and riscv64.

   - Add capability to export the XDP features supported by the NIC.

   - Add __bpf_kfunc tag for marking kernel functions as kfuncs.

   - Add cgroup.memory=nobpf kernel parameter option to disable BPF
     memory accounting for container environments.

  Netfilter:

   - Remove the CLUSTERIP target. It has been marked as obsolete for
     years, and we still have WARN splats wrt races of the out-of-band
     /proc interface installed by this target.

   - Add 'destroy' commands to nf_tables. They are identical to the
     existing 'delete' commands, but do not return an error if the
     referenced object (set, chain, rule...) did not exist.

  Driver API:

   - Improve cpumask_local_spread() locality to help NICs set the right
     IRQ affinity on AMD platforms.

   - Separate C22 and C45 MDIO bus transactions more clearly.

   - Introduce new DCB table to control DSCP rewrite on egress.

   - Support configuration of Physical Layer Collision Avoidance (PLCA)
     Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
     shared medium Ethernet.

   - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
     preemption of low priority frames by high priority frames.

   - Add support for controlling MACSec offload using netlink SET.

   - Rework devlink instance refcounts to allow registration and
     de-registration under the instance lock. Split the code into
     multiple files, drop some of the unnecessarily granular locks and
     factor out common parts of netlink operation handling.

   - Add TX frame aggregation parameters (for USB drivers).

   - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
     messages with notifications for debug.

   - Allow offloading of UDP NEW connections via act_ct.

   - Add support for per action HW stats in TC.

   - Support hardware miss to TC action (continue processing in SW from
     a specific point in the action chain).

   - Warn if old Wireless Extension user space interface is used with
     modern cfg80211/mac80211 drivers. Do not support Wireless
     Extensions for Wi-Fi 7 devices at all. Everyone should switch to
     using nl80211 interface instead.

   - Improve the CAN bit timing configuration. Use extack to return
     error messages directly to user space, update the SJW handling,
     including the definition of a new default value that will benefit
     CAN-FD controllers, by increasing their oscillator tolerance.

  New hardware / drivers:

   - Ethernet:
      - nVidia BlueField-3 support (control traffic driver)
      - Ethernet support for imx93 SoCs
      - Motorcomm yt8531 gigabit Ethernet PHY
      - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
      - Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
      - Amlogic gxl MDIO mux

   - WiFi:
      - RealTek RTL8188EU (rtl8xxxu)
      - Qualcomm Wi-Fi 7 devices (ath12k)

   - CAN:
      - Renesas R-Car V4H

  Drivers:

   - Bluetooth:
      - Set Per Platform Antenna Gain (PPAG) for Intel controllers.

   - Ethernet NICs:
      - Intel (1G, igc):
         - support TSN / Qbv / packet scheduling features of i226 model
      - Intel (100G, ice):
         - use GNSS subsystem instead of TTY
         - multi-buffer XDP support
         - extend support for GPIO pins to E823 devices
      - nVidia/Mellanox:
         - update the shared buffer configuration on PFC commands
         - implement PTP adjphase function for HW offset control
         - TC support for Geneve and GRE with VF tunnel offload
         - more efficient crypto key management method
         - multi-port eswitch support
      - Netronome/Corigine:
         - add DCB IEEE support
         - support IPsec offloading for NFP3800
      - Freescale/NXP (enetc):
         - support XDP_REDIRECT for XDP non-linear buffers
         - improve reconfig, avoid link flap and waiting for idle
         - support MAC Merge layer
      - Other NICs:
         - sfc/ef100: add basic devlink support for ef100
         - ionic: rx_push mode operation (writing descriptors via MMIO)
         - bnxt: use the auxiliary bus abstraction for RDMA
         - r8169: disable ASPM and reset bus in case of tx timeout
         - cpsw: support QSGMII mode for J721e CPSW9G
         - cpts: support pulse-per-second output
         - ngbe: add an mdio bus driver
         - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
         - r8152: handle devices with FW with NCM support
         - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
         - virtio-net: support multi buffer XDP
         - virtio/vsock: replace virtio_vsock_pkt with sk_buff
         - tsnep: XDP support

   - Ethernet high-speed switches:
      - nVidia/Mellanox (mlxsw):
         - add support for latency TLV (in FW control messages)
      - Microchip (sparx5):
         - separate explicit and implicit traffic forwarding rules, make
           the implicit rules always active
         - add support for egress DSCP rewrite
         - IS0 VCAP support (Ingress Classification)
         - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
           etc.)
         - ES2 VCAP support (Egress Access Control)
         - support for Per-Stream Filtering and Policing (802.1Q,
           8.6.5.1)

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - add MAB (port auth) offload support
         - enable PTP receive for mv88e6390
      - NXP (ocelot):
         - support MAC Merge layer
         - support for the the vsc7512 internal copper phys
      - Microchip:
         - lan9303: convert to PHYLINK
         - lan966x: support TC flower filter statistics
         - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
         - lan937x: support Credit Based Shaper configuration
         - ksz9477: support Energy Efficient Ethernet
      - other:
         - qca8k: convert to regmap read/write API, use bulk operations
         - rswitch: Improve TX timestamp accuracy

   - Intel WiFi (iwlwifi):
      - EHT (Wi-Fi 7) rate reporting
      - STEP equalizer support: transfer some STEP (connection to radio
        on platforms with integrated wifi) related parameters from the
        BIOS to the firmware.

   - Qualcomm 802.11ax WiFi (ath11k):
      - IPQ5018 support
      - Fine Timing Measurement (FTM) responder role support
      - channel 177 support

   - MediaTek WiFi (mt76):
      - per-PHY LED support
      - mt7996: EHT (Wi-Fi 7) support
      - Wireless Ethernet Dispatch (WED) reset support
      - switch to using page pool allocator

   - RealTek WiFi (rtw89):
      - support new version of Bluetooth co-existance

   - Mobile:
      - rmnet: support TX aggregation"

* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
  page_pool: add a comment explaining the fragment counter usage
  net: ethtool: fix __ethtool_dev_mm_supported() implementation
  ethtool: pse-pd: Fix double word in comments
  xsk: add linux/vmalloc.h to xsk.c
  sefltests: netdevsim: wait for devlink instance after netns removal
  selftest: fib_tests: Always cleanup before exit
  net/mlx5e: Align IPsec ASO result memory to be as required by hardware
  net/mlx5e: TC, Set CT miss to the specific ct action instance
  net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
  net/mlx5: Refactor tc miss handling to a single function
  net/mlx5: Kconfig: Make tc offload depend on tc skb extension
  net/sched: flower: Support hardware miss to tc action
  net/sched: flower: Move filter handle initialization earlier
  net/sched: cls_api: Support hardware miss to tc action
  net/sched: Rename user cookie and act cookie
  sfc: fix builds without CONFIG_RTC_LIB
  sfc: clean up some inconsistent indentings
  net/mlx4_en: Introduce flexible array to silence overflow warning
  net: lan966x: Fix possible deadlock inside PTP
  net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
  ...

1 files changed, 651 insertions, 0 deletions

diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
new file mode 100644
index 000000000..3bb579962
--- /dev/null
+++ b/include/net/mana/mana.h
@@ -0,0 +1,651 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/* Copyright (c) 2021, Microsoft Corporation. */
+
+#ifndef _MANA_H
+#define _MANA_H
+
+#include "gdma.h"
+#include "hw_channel.h"
+
+/* Microsoft Azure Network Adapter (MANA)'s definitions
+ *
+ * Structures labeled with "HW DATA" are exchanged with the hardware. All of
+ * them are naturally aligned and hence don't need __packed.
+ */
+
+/* MANA protocol version */
+#define MANA_MAJOR_VERSION	0
+#define MANA_MINOR_VERSION	1
+#define MANA_MICRO_VERSION	1
+
+typedef u64 mana_handle_t;
+#define INVALID_MANA_HANDLE ((mana_handle_t)-1)
+
+enum TRI_STATE {
+	TRI_STATE_UNKNOWN = -1,
+	TRI_STATE_FALSE = 0,
+	TRI_STATE_TRUE = 1
+};
+
+/* Number of entries for hardware indirection table must be in power of 2 */
+#define MANA_INDIRECT_TABLE_SIZE 64
+#define MANA_INDIRECT_TABLE_MASK (MANA_INDIRECT_TABLE_SIZE - 1)
+
+/* The Toeplitz hash key's length in bytes: should be multiple of 8 */
+#define MANA_HASH_KEY_SIZE 40
+
+#define COMP_ENTRY_SIZE 64
+
+#define ADAPTER_MTU_SIZE 1500
+#define MAX_FRAME_SIZE (ADAPTER_MTU_SIZE + 14)
+
+#define RX_BUFFERS_PER_QUEUE 512
+
+#define MAX_SEND_BUFFERS_PER_QUEUE 256
+
+#define EQ_SIZE (8 * PAGE_SIZE)
+#define LOG2_EQ_THROTTLE 3
+
+#define MAX_PORTS_IN_MANA_DEV 256
+
+struct mana_stats_rx {
+	u64 packets;
+	u64 bytes;
+	u64 xdp_drop;
+	u64 xdp_tx;
+	u64 xdp_redirect;
+	struct u64_stats_sync syncp;
+};
+
+struct mana_stats_tx {
+	u64 packets;
+	u64 bytes;
+	u64 xdp_xmit;
+	struct u64_stats_sync syncp;
+};
+
+struct mana_txq {
+	struct gdma_queue *gdma_sq;
+
+	union {
+		u32 gdma_txq_id;
+		struct {
+			u32 reserved1	: 10;
+			u32 vsq_frame	: 14;
+			u32 reserved2	: 8;
+		};
+	};
+
+	u16 vp_offset;
+
+	struct net_device *ndev;
+
+	/* The SKBs are sent to the HW and we are waiting for the CQEs. */
+	struct sk_buff_head pending_skbs;
+	struct netdev_queue *net_txq;
+
+	atomic_t pending_sends;
+
+	struct mana_stats_tx stats;
+};
+
+/* skb data and frags dma mappings */
+struct mana_skb_head {
+	dma_addr_t dma_handle[MAX_SKB_FRAGS + 1];
+
+	u32 size[MAX_SKB_FRAGS + 1];
+};
+
+#define MANA_HEADROOM sizeof(struct mana_skb_head)
+
+enum mana_tx_pkt_format {
+	MANA_SHORT_PKT_FMT	= 0,
+	MANA_LONG_PKT_FMT	= 1,
+};
+
+struct mana_tx_short_oob {
+	u32 pkt_fmt		: 2;
+	u32 is_outer_ipv4	: 1;
+	u32 is_outer_ipv6	: 1;
+	u32 comp_iphdr_csum	: 1;
+	u32 comp_tcp_csum	: 1;
+	u32 comp_udp_csum	: 1;
+	u32 supress_txcqe_gen	: 1;
+	u32 vcq_num		: 24;
+
+	u32 trans_off		: 10; /* Transport header offset */
+	u32 vsq_frame		: 14;
+	u32 short_vp_offset	: 8;
+}; /* HW DATA */
+
+struct mana_tx_long_oob {
+	u32 is_encap		: 1;
+	u32 inner_is_ipv6	: 1;
+	u32 inner_tcp_opt	: 1;
+	u32 inject_vlan_pri_tag : 1;
+	u32 reserved1		: 12;
+	u32 pcp			: 3;  /* 802.1Q */
+	u32 dei			: 1;  /* 802.1Q */
+	u32 vlan_id		: 12; /* 802.1Q */
+
+	u32 inner_frame_offset	: 10;
+	u32 inner_ip_rel_offset : 6;
+	u32 long_vp_offset	: 12;
+	u32 reserved2		: 4;
+
+	u32 reserved3;
+	u32 reserved4;
+}; /* HW DATA */
+
+struct mana_tx_oob {
+	struct mana_tx_short_oob s_oob;
+	struct mana_tx_long_oob l_oob;
+}; /* HW DATA */
+
+enum mana_cq_type {
+	MANA_CQ_TYPE_RX,
+	MANA_CQ_TYPE_TX,
+};
+
+enum mana_cqe_type {
+	CQE_INVALID			= 0,
+	CQE_RX_OKAY			= 1,
+	CQE_RX_COALESCED_4		= 2,
+	CQE_RX_OBJECT_FENCE		= 3,
+	CQE_RX_TRUNCATED		= 4,
+
+	CQE_TX_OKAY			= 32,
+	CQE_TX_SA_DROP			= 33,
+	CQE_TX_MTU_DROP			= 34,
+	CQE_TX_INVALID_OOB		= 35,
+	CQE_TX_INVALID_ETH_TYPE		= 36,
+	CQE_TX_HDR_PROCESSING_ERROR	= 37,
+	CQE_TX_VF_DISABLED		= 38,
+	CQE_TX_VPORT_IDX_OUT_OF_RANGE	= 39,
+	CQE_TX_VPORT_DISABLED		= 40,
+	CQE_TX_VLAN_TAGGING_VIOLATION	= 41,
+};
+
+#define MANA_CQE_COMPLETION 1
+
+struct mana_cqe_header {
+	u32 cqe_type	: 6;
+	u32 client_type	: 2;
+	u32 vendor_err	: 24;
+}; /* HW DATA */
+
+/* NDIS HASH Types */
+#define NDIS_HASH_IPV4		BIT(0)
+#define NDIS_HASH_TCP_IPV4	BIT(1)
+#define NDIS_HASH_UDP_IPV4	BIT(2)
+#define NDIS_HASH_IPV6		BIT(3)
+#define NDIS_HASH_TCP_IPV6	BIT(4)
+#define NDIS_HASH_UDP_IPV6	BIT(5)
+#define NDIS_HASH_IPV6_EX	BIT(6)
+#define NDIS_HASH_TCP_IPV6_EX	BIT(7)
+#define NDIS_HASH_UDP_IPV6_EX	BIT(8)
+
+#define MANA_HASH_L3 (NDIS_HASH_IPV4 | NDIS_HASH_IPV6 | NDIS_HASH_IPV6_EX)
+#define MANA_HASH_L4                                                         \
+	(NDIS_HASH_TCP_IPV4 | NDIS_HASH_UDP_IPV4 | NDIS_HASH_TCP_IPV6 |      \
+	 NDIS_HASH_UDP_IPV6 | NDIS_HASH_TCP_IPV6_EX | NDIS_HASH_UDP_IPV6_EX)
+
+struct mana_rxcomp_perpkt_info {
+	u32 pkt_len	: 16;
+	u32 reserved1	: 16;
+	u32 reserved2;
+	u32 pkt_hash;
+}; /* HW DATA */
+
+#define MANA_RXCOMP_OOB_NUM_PPI 4
+
+/* Receive completion OOB */
+struct mana_rxcomp_oob {
+	struct mana_cqe_header cqe_hdr;
+
+	u32 rx_vlan_id			: 12;
+	u32 rx_vlantag_present		: 1;
+	u32 rx_outer_iphdr_csum_succeed	: 1;
+	u32 rx_outer_iphdr_csum_fail	: 1;
+	u32 reserved1			: 1;
+	u32 rx_hashtype			: 9;
+	u32 rx_iphdr_csum_succeed	: 1;
+	u32 rx_iphdr_csum_fail		: 1;
+	u32 rx_tcp_csum_succeed		: 1;
+	u32 rx_tcp_csum_fail		: 1;
+	u32 rx_udp_csum_succeed		: 1;
+	u32 rx_udp_csum_fail		: 1;
+	u32 reserved2			: 1;
+
+	struct mana_rxcomp_perpkt_info ppi[MANA_RXCOMP_OOB_NUM_PPI];
+
+	u32 rx_wqe_offset;
+}; /* HW DATA */
+
+struct mana_tx_comp_oob {
+	struct mana_cqe_header cqe_hdr;
+
+	u32 tx_data_offset;
+
+	u32 tx_sgl_offset	: 5;
+	u32 tx_wqe_offset	: 27;
+
+	u32 reserved[12];
+}; /* HW DATA */
+
+struct mana_rxq;
+
+#define CQE_POLLING_BUFFER 512
+
+struct mana_cq {
+	struct gdma_queue *gdma_cq;
+
+	/* Cache the CQ id (used to verify if each CQE comes to the right CQ. */
+	u32 gdma_id;
+
+	/* Type of the CQ: TX or RX */
+	enum mana_cq_type type;
+
+	/* Pointer to the mana_rxq that is pushing RX CQEs to the queue.
+	 * Only and must be non-NULL if type is MANA_CQ_TYPE_RX.
+	 */
+	struct mana_rxq *rxq;
+
+	/* Pointer to the mana_txq that is pushing TX CQEs to the queue.
+	 * Only and must be non-NULL if type is MANA_CQ_TYPE_TX.
+	 */
+	struct mana_txq *txq;
+
+	/* Buffer which the CQ handler can copy the CQE's into. */
+	struct gdma_comp gdma_comp_buf[CQE_POLLING_BUFFER];
+
+	/* NAPI data */
+	struct napi_struct napi;
+	int work_done;
+	int budget;
+};
+
+struct mana_recv_buf_oob {
+	/* A valid GDMA work request representing the data buffer. */
+	struct gdma_wqe_request wqe_req;
+
+	void *buf_va;
+	dma_addr_t buf_dma_addr;
+
+	/* SGL of the buffer going to be sent has part of the work request. */
+	u32 num_sge;
+	struct gdma_sge sgl[MAX_RX_WQE_SGL_ENTRIES];
+
+	/* Required to store the result of mana_gd_post_work_request.
+	 * gdma_posted_wqe_info.wqe_size_in_bu is required for progressing the
+	 * work queue when the WQE is consumed.
+	 */
+	struct gdma_posted_wqe_info wqe_inf;
+};
+
+struct mana_rxq {
+	struct gdma_queue *gdma_rq;
+	/* Cache the gdma receive queue id */
+	u32 gdma_id;
+
+	/* Index of RQ in the vPort, not gdma receive queue id */
+	u32 rxq_idx;
+
+	u32 datasize;
+
+	mana_handle_t rxobj;
+
+	struct mana_cq rx_cq;
+
+	struct completion fence_event;
+
+	struct net_device *ndev;
+
+	/* Total number of receive buffers to be allocated */
+	u32 num_rx_buf;
+
+	u32 buf_index;
+
+	struct mana_stats_rx stats;
+
+	struct bpf_prog __rcu *bpf_prog;
+	struct xdp_rxq_info xdp_rxq;
+	struct page *xdp_save_page;
+	bool xdp_flush;
+	int xdp_rc; /* XDP redirect return code */
+
+	/* MUST BE THE LAST MEMBER:
+	 * Each receive buffer has an associated mana_recv_buf_oob.
+	 */
+	struct mana_recv_buf_oob rx_oobs[];
+};
+
+struct mana_tx_qp {
+	struct mana_txq txq;
+
+	struct mana_cq tx_cq;
+
+	mana_handle_t tx_object;
+};
+
+struct mana_ethtool_stats {
+	u64 stop_queue;
+	u64 wake_queue;
+};
+
+struct mana_context {
+	struct gdma_dev *gdma_dev;
+
+	u16 num_ports;
+
+	struct mana_eq *eqs;
+
+	struct net_device *ports[MAX_PORTS_IN_MANA_DEV];
+};
+
+struct mana_port_context {
+	struct mana_context *ac;
+	struct net_device *ndev;
+
+	u8 mac_addr[ETH_ALEN];
+
+	enum TRI_STATE rss_state;
+
+	mana_handle_t default_rxobj;
+	bool tx_shortform_allowed;
+	u16 tx_vp_offset;
+
+	struct mana_tx_qp *tx_qp;
+
+	/* Indirection Table for RX & TX. The values are queue indexes */
+	u32 indir_table[MANA_INDIRECT_TABLE_SIZE];
+
+	/* Indirection table containing RxObject Handles */
+	mana_handle_t rxobj_table[MANA_INDIRECT_TABLE_SIZE];
+
+	/*  Hash key used by the NIC */
+	u8 hashkey[MANA_HASH_KEY_SIZE];
+
+	/* This points to an array of num_queues of RQ pointers. */
+	struct mana_rxq **rxqs;
+
+	struct bpf_prog *bpf_prog;
+
+	/* Create num_queues EQs, SQs, SQ-CQs, RQs and RQ-CQs, respectively. */
+	unsigned int max_queues;
+	unsigned int num_queues;
+
+	mana_handle_t port_handle;
+	mana_handle_t pf_filter_handle;
+
+	/* Mutex for sharing access to vport_use_count */
+	struct mutex vport_mutex;
+	int vport_use_count;
+
+	u16 port_idx;
+
+	bool port_is_up;
+	bool port_st_save; /* Saved port state */
+
+	struct mana_ethtool_stats eth_stats;
+};
+
+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);
+
+int mana_alloc_queues(struct net_device *ndev);
+int mana_attach(struct net_device *ndev);
+int mana_detach(struct net_device *ndev, bool from_close);
+
+int mana_probe(struct gdma_dev *gd, bool resuming);
+void mana_remove(struct gdma_dev *gd, bool suspending);
+
+void mana_xdp_tx(struct sk_buff *skb, struct net_device *ndev);
+int mana_xdp_xmit(struct net_device *ndev, int n, struct xdp_frame **frames,
+		  u32 flags);
+u32 mana_run_xdp(struct net_device *ndev, struct mana_rxq *rxq,
+		 struct xdp_buff *xdp, void *buf_va, uint pkt_len);
+struct bpf_prog *mana_xdp_get(struct mana_port_context *apc);
+void mana_chn_setxdp(struct mana_port_context *apc, struct bpf_prog *prog);
+int mana_bpf(struct net_device *ndev, struct netdev_bpf *bpf);
+
+extern const struct ethtool_ops mana_ethtool_ops;
+
+/* A CQ can be created not associated with any EQ */
+#define GDMA_CQ_NO_EQ  0xffff
+
+struct mana_obj_spec {
+	u32 queue_index;
+	u64 gdma_region;
+	u32 queue_size;
+	u32 attached_eq;
+	u32 modr_ctx_id;
+};
+
+enum mana_command_code {
+	MANA_QUERY_DEV_CONFIG	= 0x20001,
+	MANA_QUERY_GF_STAT	= 0x20002,
+	MANA_CONFIG_VPORT_TX	= 0x20003,
+	MANA_CREATE_WQ_OBJ	= 0x20004,
+	MANA_DESTROY_WQ_OBJ	= 0x20005,
+	MANA_FENCE_RQ		= 0x20006,
+	MANA_CONFIG_VPORT_RX	= 0x20007,
+	MANA_QUERY_VPORT_CONFIG	= 0x20008,
+
+	/* Privileged commands for the PF mode */
+	MANA_REGISTER_FILTER	= 0x28000,
+	MANA_DEREGISTER_FILTER	= 0x28001,
+	MANA_REGISTER_HW_PORT	= 0x28003,
+	MANA_DEREGISTER_HW_PORT	= 0x28004,
+};
+
+/* Query Device Configuration */
+struct mana_query_device_cfg_req {
+	struct gdma_req_hdr hdr;
+
+	/* MANA Nic Driver Capability flags */
+	u64 mn_drv_cap_flags1;
+	u64 mn_drv_cap_flags2;
+	u64 mn_drv_cap_flags3;
+	u64 mn_drv_cap_flags4;
+
+	u32 proto_major_ver;
+	u32 proto_minor_ver;
+	u32 proto_micro_ver;
+
+	u32 reserved;
+}; /* HW DATA */
+
+struct mana_query_device_cfg_resp {
+	struct gdma_resp_hdr hdr;
+
+	u64 pf_cap_flags1;
+	u64 pf_cap_flags2;
+	u64 pf_cap_flags3;
+	u64 pf_cap_flags4;
+
+	u16 max_num_vports;
+	u16 reserved;
+	u32 max_num_eqs;
+}; /* HW DATA */
+
+/* Query vPort Configuration */
+struct mana_query_vport_cfg_req {
+	struct gdma_req_hdr hdr;
+	u32 vport_index;
+}; /* HW DATA */
+
+struct mana_query_vport_cfg_resp {
+	struct gdma_resp_hdr hdr;
+	u32 max_num_sq;
+	u32 max_num_rq;
+	u32 num_indirection_ent;
+	u32 reserved1;
+	u8 mac_addr[6];
+	u8 reserved2[2];
+	mana_handle_t vport;
+}; /* HW DATA */
+
+/* Configure vPort */
+struct mana_config_vport_req {
+	struct gdma_req_hdr hdr;
+	mana_handle_t vport;
+	u32 pdid;
+	u32 doorbell_pageid;
+}; /* HW DATA */
+
+struct mana_config_vport_resp {
+	struct gdma_resp_hdr hdr;
+	u16 tx_vport_offset;
+	u8 short_form_allowed;
+	u8 reserved;
+}; /* HW DATA */
+
+/* Create WQ Object */
+struct mana_create_wqobj_req {
+	struct gdma_req_hdr hdr;
+	mana_handle_t vport;
+	u32 wq_type;
+	u32 reserved;
+	u64 wq_gdma_region;
+	u64 cq_gdma_region;
+	u32 wq_size;
+	u32 cq_size;
+	u32 cq_moderation_ctx_id;
+	u32 cq_parent_qid;
+}; /* HW DATA */
+
+struct mana_create_wqobj_resp {
+	struct gdma_resp_hdr hdr;
+	u32 wq_id;
+	u32 cq_id;
+	mana_handle_t wq_obj;
+}; /* HW DATA */
+
+/* Destroy WQ Object */
+struct mana_destroy_wqobj_req {
+	struct gdma_req_hdr hdr;
+	u32 wq_type;
+	u32 reserved;
+	mana_handle_t wq_obj_handle;
+}; /* HW DATA */
+
+struct mana_destroy_wqobj_resp {
+	struct gdma_resp_hdr hdr;
+}; /* HW DATA */
+
+/* Fence RQ */
+struct mana_fence_rq_req {
+	struct gdma_req_hdr hdr;
+	mana_handle_t wq_obj_handle;
+}; /* HW DATA */
+
+struct mana_fence_rq_resp {
+	struct gdma_resp_hdr hdr;
+}; /* HW DATA */
+
+/* Configure vPort Rx Steering */
+struct mana_cfg_rx_steer_req {
+	struct gdma_req_hdr hdr;
+	mana_handle_t vport;
+	u16 num_indir_entries;
+	u16 indir_tab_offset;
+	u32 rx_enable;
+	u32 rss_enable;
+	u8 update_default_rxobj;
+	u8 update_hashkey;
+	u8 update_indir_tab;
+	u8 reserved;
+	mana_handle_t default_rxobj;
+	u8 hashkey[MANA_HASH_KEY_SIZE];
+}; /* HW DATA */
+
+struct mana_cfg_rx_steer_resp {
+	struct gdma_resp_hdr hdr;
+}; /* HW DATA */
+
+/* Register HW vPort */
+struct mana_register_hw_vport_req {
+	struct gdma_req_hdr hdr;
+	u16 attached_gfid;
+	u8 is_pf_default_vport;
+	u8 reserved1;
+	u8 allow_all_ether_types;
+	u8 reserved2;
+	u8 reserved3;
+	u8 reserved4;
+}; /* HW DATA */
+
+struct mana_register_hw_vport_resp {
+	struct gdma_resp_hdr hdr;
+	mana_handle_t hw_vport_handle;
+}; /* HW DATA */
+
+/* Deregister HW vPort */
+struct mana_deregister_hw_vport_req {
+	struct gdma_req_hdr hdr;
+	mana_handle_t hw_vport_handle;
+}; /* HW DATA */
+
+struct mana_deregister_hw_vport_resp {
+	struct gdma_resp_hdr hdr;
+}; /* HW DATA */
+
+/* Register filter */
+struct mana_register_filter_req {
+	struct gdma_req_hdr hdr;
+	mana_handle_t vport;
+	u8 mac_addr[6];
+	u8 reserved1;
+	u8 reserved2;
+	u8 reserved3;
+	u8 reserved4;
+	u16 reserved5;
+	u32 reserved6;
+	u32 reserved7;
+	u32 reserved8;
+}; /* HW DATA */
+
+struct mana_register_filter_resp {
+	struct gdma_resp_hdr hdr;
+	mana_handle_t filter_handle;
+}; /* HW DATA */
+
+/* Deregister filter */
+struct mana_deregister_filter_req {
+	struct gdma_req_hdr hdr;
+	mana_handle_t filter_handle;
+}; /* HW DATA */
+
+struct mana_deregister_filter_resp {
+	struct gdma_resp_hdr hdr;
+}; /* HW DATA */
+
+#define MANA_MAX_NUM_QUEUES 64
+
+#define MANA_SHORT_VPORT_OFFSET_MAX ((1U << 8) - 1)
+
+struct mana_tx_package {
+	struct gdma_wqe_request wqe_req;
+	struct gdma_sge sgl_array[5];
+	struct gdma_sge *sgl_ptr;
+
+	struct mana_tx_oob tx_oob;
+
+	struct gdma_posted_wqe_info wqe_info;
+};
+
+int mana_create_wq_obj(struct mana_port_context *apc,
+		       mana_handle_t vport,
+		       u32 wq_type, struct mana_obj_spec *wq_spec,
+		       struct mana_obj_spec *cq_spec,
+		       mana_handle_t *wq_obj);
+
+void mana_destroy_wq_obj(struct mana_port_context *apc, u32 wq_type,
+			 mana_handle_t wq_obj);
+
+int mana_cfg_vport(struct mana_port_context *apc, u32 protection_dom_id,
+		   u32 doorbell_pg_id);
+void mana_uncfg_vport(struct mana_port_context *apc);
+#endif /* _MANA_H */