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, 841 insertions, 0 deletions

diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h
new file mode 100644
index 000000000..56189e425
--- /dev/null
+++ b/include/net/mana/gdma.h
@@ -0,0 +1,841 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/* Copyright (c) 2021, Microsoft Corporation. */
+
+#ifndef _GDMA_H
+#define _GDMA_H
+
+#include <linux/dma-mapping.h>
+#include <linux/netdevice.h>
+
+#include "shm_channel.h"
+
+#define GDMA_STATUS_MORE_ENTRIES	0x00000105
+
+/* Structures labeled with "HW DATA" are exchanged with the hardware. All of
+ * them are naturally aligned and hence don't need __packed.
+ */
+
+enum gdma_request_type {
+	GDMA_VERIFY_VF_DRIVER_VERSION	= 1,
+	GDMA_QUERY_MAX_RESOURCES	= 2,
+	GDMA_LIST_DEVICES		= 3,
+	GDMA_REGISTER_DEVICE		= 4,
+	GDMA_DEREGISTER_DEVICE		= 5,
+	GDMA_GENERATE_TEST_EQE		= 10,
+	GDMA_CREATE_QUEUE		= 12,
+	GDMA_DISABLE_QUEUE		= 13,
+	GDMA_ALLOCATE_RESOURCE_RANGE	= 22,
+	GDMA_DESTROY_RESOURCE_RANGE	= 24,
+	GDMA_CREATE_DMA_REGION		= 25,
+	GDMA_DMA_REGION_ADD_PAGES	= 26,
+	GDMA_DESTROY_DMA_REGION		= 27,
+	GDMA_CREATE_PD			= 29,
+	GDMA_DESTROY_PD			= 30,
+	GDMA_CREATE_MR			= 31,
+	GDMA_DESTROY_MR			= 32,
+};
+
+#define GDMA_RESOURCE_DOORBELL_PAGE	27
+
+enum gdma_queue_type {
+	GDMA_INVALID_QUEUE,
+	GDMA_SQ,
+	GDMA_RQ,
+	GDMA_CQ,
+	GDMA_EQ,
+};
+
+enum gdma_work_request_flags {
+	GDMA_WR_NONE			= 0,
+	GDMA_WR_OOB_IN_SGL		= BIT(0),
+	GDMA_WR_PAD_BY_SGE0		= BIT(1),
+};
+
+enum gdma_eqe_type {
+	GDMA_EQE_COMPLETION		= 3,
+	GDMA_EQE_TEST_EVENT		= 64,
+	GDMA_EQE_HWC_INIT_EQ_ID_DB	= 129,
+	GDMA_EQE_HWC_INIT_DATA		= 130,
+	GDMA_EQE_HWC_INIT_DONE		= 131,
+};
+
+enum {
+	GDMA_DEVICE_NONE	= 0,
+	GDMA_DEVICE_HWC		= 1,
+	GDMA_DEVICE_MANA	= 2,
+};
+
+struct gdma_resource {
+	/* Protect the bitmap */
+	spinlock_t lock;
+
+	/* The bitmap size in bits. */
+	u32 size;
+
+	/* The bitmap tracks the resources. */
+	unsigned long *map;
+};
+
+union gdma_doorbell_entry {
+	u64	as_uint64;
+
+	struct {
+		u64 id		: 24;
+		u64 reserved	: 8;
+		u64 tail_ptr	: 31;
+		u64 arm		: 1;
+	} cq;
+
+	struct {
+		u64 id		: 24;
+		u64 wqe_cnt	: 8;
+		u64 tail_ptr	: 32;
+	} rq;
+
+	struct {
+		u64 id		: 24;
+		u64 reserved	: 8;
+		u64 tail_ptr	: 32;
+	} sq;
+
+	struct {
+		u64 id		: 16;
+		u64 reserved	: 16;
+		u64 tail_ptr	: 31;
+		u64 arm		: 1;
+	} eq;
+}; /* HW DATA */
+
+struct gdma_msg_hdr {
+	u32 hdr_type;
+	u32 msg_type;
+	u16 msg_version;
+	u16 hwc_msg_id;
+	u32 msg_size;
+}; /* HW DATA */
+
+struct gdma_dev_id {
+	union {
+		struct {
+			u16 type;
+			u16 instance;
+		};
+
+		u32 as_uint32;
+	};
+}; /* HW DATA */
+
+struct gdma_req_hdr {
+	struct gdma_msg_hdr req;
+	struct gdma_msg_hdr resp; /* The expected response */
+	struct gdma_dev_id dev_id;
+	u32 activity_id;
+}; /* HW DATA */
+
+struct gdma_resp_hdr {
+	struct gdma_msg_hdr response;
+	struct gdma_dev_id dev_id;
+	u32 activity_id;
+	u32 status;
+	u32 reserved;
+}; /* HW DATA */
+
+struct gdma_general_req {
+	struct gdma_req_hdr hdr;
+}; /* HW DATA */
+
+#define GDMA_MESSAGE_V1 1
+
+struct gdma_general_resp {
+	struct gdma_resp_hdr hdr;
+}; /* HW DATA */
+
+#define GDMA_STANDARD_HEADER_TYPE 0
+
+static inline void mana_gd_init_req_hdr(struct gdma_req_hdr *hdr, u32 code,
+					u32 req_size, u32 resp_size)
+{
+	hdr->req.hdr_type = GDMA_STANDARD_HEADER_TYPE;
+	hdr->req.msg_type = code;
+	hdr->req.msg_version = GDMA_MESSAGE_V1;
+	hdr->req.msg_size = req_size;
+
+	hdr->resp.hdr_type = GDMA_STANDARD_HEADER_TYPE;
+	hdr->resp.msg_type = code;
+	hdr->resp.msg_version = GDMA_MESSAGE_V1;
+	hdr->resp.msg_size = resp_size;
+}
+
+/* The 16-byte struct is part of the GDMA work queue entry (WQE). */
+struct gdma_sge {
+	u64 address;
+	u32 mem_key;
+	u32 size;
+}; /* HW DATA */
+
+struct gdma_wqe_request {
+	struct gdma_sge *sgl;
+	u32 num_sge;
+
+	u32 inline_oob_size;
+	const void *inline_oob_data;
+
+	u32 flags;
+	u32 client_data_unit;
+};
+
+enum gdma_page_type {
+	GDMA_PAGE_TYPE_4K,
+};
+
+#define GDMA_INVALID_DMA_REGION 0
+
+struct gdma_mem_info {
+	struct device *dev;
+
+	dma_addr_t dma_handle;
+	void *virt_addr;
+	u64 length;
+
+	/* Allocated by the PF driver */
+	u64 dma_region_handle;
+};
+
+#define REGISTER_ATB_MST_MKEY_LOWER_SIZE 8
+
+struct gdma_dev {
+	struct gdma_context *gdma_context;
+
+	struct gdma_dev_id dev_id;
+
+	u32 pdid;
+	u32 doorbell;
+	u32 gpa_mkey;
+
+	/* GDMA driver specific pointer */
+	void *driver_data;
+
+	struct auxiliary_device *adev;
+};
+
+#define MINIMUM_SUPPORTED_PAGE_SIZE PAGE_SIZE
+
+#define GDMA_CQE_SIZE 64
+#define GDMA_EQE_SIZE 16
+#define GDMA_MAX_SQE_SIZE 512
+#define GDMA_MAX_RQE_SIZE 256
+
+#define GDMA_COMP_DATA_SIZE 0x3C
+
+#define GDMA_EVENT_DATA_SIZE 0xC
+
+/* The WQE size must be a multiple of the Basic Unit, which is 32 bytes. */
+#define GDMA_WQE_BU_SIZE 32
+
+#define INVALID_PDID		UINT_MAX
+#define INVALID_DOORBELL	UINT_MAX
+#define INVALID_MEM_KEY		UINT_MAX
+#define INVALID_QUEUE_ID	UINT_MAX
+#define INVALID_PCI_MSIX_INDEX  UINT_MAX
+
+struct gdma_comp {
+	u32 cqe_data[GDMA_COMP_DATA_SIZE / 4];
+	u32 wq_num;
+	bool is_sq;
+};
+
+struct gdma_event {
+	u32 details[GDMA_EVENT_DATA_SIZE / 4];
+	u8  type;
+};
+
+struct gdma_queue;
+
+struct mana_eq {
+	struct gdma_queue *eq;
+};
+
+typedef void gdma_eq_callback(void *context, struct gdma_queue *q,
+			      struct gdma_event *e);
+
+typedef void gdma_cq_callback(void *context, struct gdma_queue *q);
+
+/* The 'head' is the producer index. For SQ/RQ, when the driver posts a WQE
+ * (Note: the WQE size must be a multiple of the 32-byte Basic Unit), the
+ * driver increases the 'head' in BUs rather than in bytes, and notifies
+ * the HW of the updated head. For EQ/CQ, the driver uses the 'head' to track
+ * the HW head, and increases the 'head' by 1 for every processed EQE/CQE.
+ *
+ * The 'tail' is the consumer index for SQ/RQ. After the CQE of the SQ/RQ is
+ * processed, the driver increases the 'tail' to indicate that WQEs have
+ * been consumed by the HW, so the driver can post new WQEs into the SQ/RQ.
+ *
+ * The driver doesn't use the 'tail' for EQ/CQ, because the driver ensures
+ * that the EQ/CQ is big enough so they can't overflow, and the driver uses
+ * the owner bits mechanism to detect if the queue has become empty.
+ */
+struct gdma_queue {
+	struct gdma_dev *gdma_dev;
+
+	enum gdma_queue_type type;
+	u32 id;
+
+	struct gdma_mem_info mem_info;
+
+	void *queue_mem_ptr;
+	u32 queue_size;
+
+	bool monitor_avl_buf;
+
+	u32 head;
+	u32 tail;
+
+	/* Extra fields specific to EQ/CQ. */
+	union {
+		struct {
+			bool disable_needed;
+
+			gdma_eq_callback *callback;
+			void *context;
+
+			unsigned int msix_index;
+
+			u32 log2_throttle_limit;
+		} eq;
+
+		struct {
+			gdma_cq_callback *callback;
+			void *context;
+
+			struct gdma_queue *parent; /* For CQ/EQ relationship */
+		} cq;
+	};
+};
+
+struct gdma_queue_spec {
+	enum gdma_queue_type type;
+	bool monitor_avl_buf;
+	unsigned int queue_size;
+
+	/* Extra fields specific to EQ/CQ. */
+	union {
+		struct {
+			gdma_eq_callback *callback;
+			void *context;
+
+			unsigned long log2_throttle_limit;
+		} eq;
+
+		struct {
+			gdma_cq_callback *callback;
+			void *context;
+
+			struct gdma_queue *parent_eq;
+
+		} cq;
+	};
+};
+
+#define MANA_IRQ_NAME_SZ 32
+
+struct gdma_irq_context {
+	void (*handler)(void *arg);
+	void *arg;
+	char name[MANA_IRQ_NAME_SZ];
+};
+
+struct gdma_context {
+	struct device		*dev;
+
+	/* Per-vPort max number of queues */
+	unsigned int		max_num_queues;
+	unsigned int		max_num_msix;
+	unsigned int		num_msix_usable;
+	struct gdma_resource	msix_resource;
+	struct gdma_irq_context	*irq_contexts;
+
+	/* This maps a CQ index to the queue structure. */
+	unsigned int		max_num_cqs;
+	struct gdma_queue	**cq_table;
+
+	/* Protect eq_test_event and test_event_eq_id  */
+	struct mutex		eq_test_event_mutex;
+	struct completion	eq_test_event;
+	u32			test_event_eq_id;
+
+	bool			is_pf;
+	phys_addr_t		bar0_pa;
+	void __iomem		*bar0_va;
+	void __iomem		*shm_base;
+	void __iomem		*db_page_base;
+	phys_addr_t		phys_db_page_base;
+	u32 db_page_size;
+	int                     numa_node;
+
+	/* Shared memory chanenl (used to bootstrap HWC) */
+	struct shm_channel	shm_channel;
+
+	/* Hardware communication channel (HWC) */
+	struct gdma_dev		hwc;
+
+	/* Azure network adapter */
+	struct gdma_dev		mana;
+};
+
+#define MAX_NUM_GDMA_DEVICES	4
+
+static inline bool mana_gd_is_mana(struct gdma_dev *gd)
+{
+	return gd->dev_id.type == GDMA_DEVICE_MANA;
+}
+
+static inline bool mana_gd_is_hwc(struct gdma_dev *gd)
+{
+	return gd->dev_id.type == GDMA_DEVICE_HWC;
+}
+
+u8 *mana_gd_get_wqe_ptr(const struct gdma_queue *wq, u32 wqe_offset);
+u32 mana_gd_wq_avail_space(struct gdma_queue *wq);
+
+int mana_gd_test_eq(struct gdma_context *gc, struct gdma_queue *eq);
+
+int mana_gd_create_hwc_queue(struct gdma_dev *gd,
+			     const struct gdma_queue_spec *spec,
+			     struct gdma_queue **queue_ptr);
+
+int mana_gd_create_mana_eq(struct gdma_dev *gd,
+			   const struct gdma_queue_spec *spec,
+			   struct gdma_queue **queue_ptr);
+
+int mana_gd_create_mana_wq_cq(struct gdma_dev *gd,
+			      const struct gdma_queue_spec *spec,
+			      struct gdma_queue **queue_ptr);
+
+void mana_gd_destroy_queue(struct gdma_context *gc, struct gdma_queue *queue);
+
+int mana_gd_poll_cq(struct gdma_queue *cq, struct gdma_comp *comp, int num_cqe);
+
+void mana_gd_ring_cq(struct gdma_queue *cq, u8 arm_bit);
+
+struct gdma_wqe {
+	u32 reserved	:24;
+	u32 last_vbytes	:8;
+
+	union {
+		u32 flags;
+
+		struct {
+			u32 num_sge		:8;
+			u32 inline_oob_size_div4:3;
+			u32 client_oob_in_sgl	:1;
+			u32 reserved1		:4;
+			u32 client_data_unit	:14;
+			u32 reserved2		:2;
+		};
+	};
+}; /* HW DATA */
+
+#define INLINE_OOB_SMALL_SIZE 8
+#define INLINE_OOB_LARGE_SIZE 24
+
+#define MAX_TX_WQE_SIZE 512
+#define MAX_RX_WQE_SIZE 256
+
+#define MAX_TX_WQE_SGL_ENTRIES	((GDMA_MAX_SQE_SIZE -			   \
+			sizeof(struct gdma_sge) - INLINE_OOB_SMALL_SIZE) / \
+			sizeof(struct gdma_sge))
+
+#define MAX_RX_WQE_SGL_ENTRIES	((GDMA_MAX_RQE_SIZE -			   \
+			sizeof(struct gdma_sge)) / sizeof(struct gdma_sge))
+
+struct gdma_cqe {
+	u32 cqe_data[GDMA_COMP_DATA_SIZE / 4];
+
+	union {
+		u32 as_uint32;
+
+		struct {
+			u32 wq_num	: 24;
+			u32 is_sq	: 1;
+			u32 reserved	: 4;
+			u32 owner_bits	: 3;
+		};
+	} cqe_info;
+}; /* HW DATA */
+
+#define GDMA_CQE_OWNER_BITS 3
+
+#define GDMA_CQE_OWNER_MASK ((1 << GDMA_CQE_OWNER_BITS) - 1)
+
+#define SET_ARM_BIT 1
+
+#define GDMA_EQE_OWNER_BITS 3
+
+union gdma_eqe_info {
+	u32 as_uint32;
+
+	struct {
+		u32 type	: 8;
+		u32 reserved1	: 8;
+		u32 client_id	: 2;
+		u32 reserved2	: 11;
+		u32 owner_bits	: 3;
+	};
+}; /* HW DATA */
+
+#define GDMA_EQE_OWNER_MASK ((1 << GDMA_EQE_OWNER_BITS) - 1)
+#define INITIALIZED_OWNER_BIT(log2_num_entries) (1UL << (log2_num_entries))
+
+struct gdma_eqe {
+	u32 details[GDMA_EVENT_DATA_SIZE / 4];
+	u32 eqe_info;
+}; /* HW DATA */
+
+#define GDMA_REG_DB_PAGE_OFFSET	8
+#define GDMA_REG_DB_PAGE_SIZE	0x10
+#define GDMA_REG_SHM_OFFSET	0x18
+
+#define GDMA_PF_REG_DB_PAGE_SIZE	0xD0
+#define GDMA_PF_REG_DB_PAGE_OFF		0xC8
+#define GDMA_PF_REG_SHM_OFF		0x70
+
+#define GDMA_SRIOV_REG_CFG_BASE_OFF	0x108
+
+#define MANA_PF_DEVICE_ID 0x00B9
+#define MANA_VF_DEVICE_ID 0x00BA
+
+struct gdma_posted_wqe_info {
+	u32 wqe_size_in_bu;
+};
+
+/* GDMA_GENERATE_TEST_EQE */
+struct gdma_generate_test_event_req {
+	struct gdma_req_hdr hdr;
+	u32 queue_index;
+}; /* HW DATA */
+
+/* GDMA_VERIFY_VF_DRIVER_VERSION */
+enum {
+	GDMA_PROTOCOL_V1	= 1,
+	GDMA_PROTOCOL_FIRST	= GDMA_PROTOCOL_V1,
+	GDMA_PROTOCOL_LAST	= GDMA_PROTOCOL_V1,
+};
+
+#define GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT BIT(0)
+
+/* Advertise to the NIC firmware: the NAPI work_done variable race is fixed,
+ * so the driver is able to reliably support features like busy_poll.
+ */
+#define GDMA_DRV_CAP_FLAG_1_NAPI_WKDONE_FIX BIT(2)
+
+#define GDMA_DRV_CAP_FLAGS1 \
+	(GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT | \
+	 GDMA_DRV_CAP_FLAG_1_NAPI_WKDONE_FIX)
+
+#define GDMA_DRV_CAP_FLAGS2 0
+
+#define GDMA_DRV_CAP_FLAGS3 0
+
+#define GDMA_DRV_CAP_FLAGS4 0
+
+struct gdma_verify_ver_req {
+	struct gdma_req_hdr hdr;
+
+	/* Mandatory fields required for protocol establishment */
+	u64 protocol_ver_min;
+	u64 protocol_ver_max;
+
+	/* Gdma Driver Capability Flags */
+	u64 gd_drv_cap_flags1;
+	u64 gd_drv_cap_flags2;
+	u64 gd_drv_cap_flags3;
+	u64 gd_drv_cap_flags4;
+
+	/* Advisory fields */
+	u64 drv_ver;
+	u32 os_type; /* Linux = 0x10; Windows = 0x20; Other = 0x30 */
+	u32 reserved;
+	u32 os_ver_major;
+	u32 os_ver_minor;
+	u32 os_ver_build;
+	u32 os_ver_platform;
+	u64 reserved_2;
+	u8 os_ver_str1[128];
+	u8 os_ver_str2[128];
+	u8 os_ver_str3[128];
+	u8 os_ver_str4[128];
+}; /* HW DATA */
+
+struct gdma_verify_ver_resp {
+	struct gdma_resp_hdr hdr;
+	u64 gdma_protocol_ver;
+	u64 pf_cap_flags1;
+	u64 pf_cap_flags2;
+	u64 pf_cap_flags3;
+	u64 pf_cap_flags4;
+}; /* HW DATA */
+
+/* GDMA_QUERY_MAX_RESOURCES */
+struct gdma_query_max_resources_resp {
+	struct gdma_resp_hdr hdr;
+	u32 status;
+	u32 max_sq;
+	u32 max_rq;
+	u32 max_cq;
+	u32 max_eq;
+	u32 max_db;
+	u32 max_mst;
+	u32 max_cq_mod_ctx;
+	u32 max_mod_cq;
+	u32 max_msix;
+}; /* HW DATA */
+
+/* GDMA_LIST_DEVICES */
+struct gdma_list_devices_resp {
+	struct gdma_resp_hdr hdr;
+	u32 num_of_devs;
+	u32 reserved;
+	struct gdma_dev_id devs[64];
+}; /* HW DATA */
+
+/* GDMA_REGISTER_DEVICE */
+struct gdma_register_device_resp {
+	struct gdma_resp_hdr hdr;
+	u32 pdid;
+	u32 gpa_mkey;
+	u32 db_id;
+}; /* HW DATA */
+
+struct gdma_allocate_resource_range_req {
+	struct gdma_req_hdr hdr;
+	u32 resource_type;
+	u32 num_resources;
+	u32 alignment;
+	u32 allocated_resources;
+};
+
+struct gdma_allocate_resource_range_resp {
+	struct gdma_resp_hdr hdr;
+	u32 allocated_resources;
+};
+
+struct gdma_destroy_resource_range_req {
+	struct gdma_req_hdr hdr;
+	u32 resource_type;
+	u32 num_resources;
+	u32 allocated_resources;
+};
+
+/* GDMA_CREATE_QUEUE */
+struct gdma_create_queue_req {
+	struct gdma_req_hdr hdr;
+	u32 type;
+	u32 reserved1;
+	u32 pdid;
+	u32 doolbell_id;
+	u64 gdma_region;
+	u32 reserved2;
+	u32 queue_size;
+	u32 log2_throttle_limit;
+	u32 eq_pci_msix_index;
+	u32 cq_mod_ctx_id;
+	u32 cq_parent_eq_id;
+	u8  rq_drop_on_overrun;
+	u8  rq_err_on_wqe_overflow;
+	u8  rq_chain_rec_wqes;
+	u8  sq_hw_db;
+	u32 reserved3;
+}; /* HW DATA */
+
+struct gdma_create_queue_resp {
+	struct gdma_resp_hdr hdr;
+	u32 queue_index;
+}; /* HW DATA */
+
+/* GDMA_DISABLE_QUEUE */
+struct gdma_disable_queue_req {
+	struct gdma_req_hdr hdr;
+	u32 type;
+	u32 queue_index;
+	u32 alloc_res_id_on_creation;
+}; /* HW DATA */
+
+enum atb_page_size {
+	ATB_PAGE_SIZE_4K,
+	ATB_PAGE_SIZE_8K,
+	ATB_PAGE_SIZE_16K,
+	ATB_PAGE_SIZE_32K,
+	ATB_PAGE_SIZE_64K,
+	ATB_PAGE_SIZE_128K,
+	ATB_PAGE_SIZE_256K,
+	ATB_PAGE_SIZE_512K,
+	ATB_PAGE_SIZE_1M,
+	ATB_PAGE_SIZE_2M,
+	ATB_PAGE_SIZE_MAX,
+};
+
+enum gdma_mr_access_flags {
+	GDMA_ACCESS_FLAG_LOCAL_READ = BIT_ULL(0),
+	GDMA_ACCESS_FLAG_LOCAL_WRITE = BIT_ULL(1),
+	GDMA_ACCESS_FLAG_REMOTE_READ = BIT_ULL(2),
+	GDMA_ACCESS_FLAG_REMOTE_WRITE = BIT_ULL(3),
+	GDMA_ACCESS_FLAG_REMOTE_ATOMIC = BIT_ULL(4),
+};
+
+/* GDMA_CREATE_DMA_REGION */
+struct gdma_create_dma_region_req {
+	struct gdma_req_hdr hdr;
+
+	/* The total size of the DMA region */
+	u64 length;
+
+	/* The offset in the first page */
+	u32 offset_in_page;
+
+	/* enum gdma_page_type */
+	u32 gdma_page_type;
+
+	/* The total number of pages */
+	u32 page_count;
+
+	/* If page_addr_list_len is smaller than page_count,
+	 * the remaining page addresses will be added via the
+	 * message GDMA_DMA_REGION_ADD_PAGES.
+	 */
+	u32 page_addr_list_len;
+	u64 page_addr_list[];
+}; /* HW DATA */
+
+struct gdma_create_dma_region_resp {
+	struct gdma_resp_hdr hdr;
+	u64 dma_region_handle;
+}; /* HW DATA */
+
+/* GDMA_DMA_REGION_ADD_PAGES */
+struct gdma_dma_region_add_pages_req {
+	struct gdma_req_hdr hdr;
+
+	u64 dma_region_handle;
+
+	u32 page_addr_list_len;
+	u32 reserved3;
+
+	u64 page_addr_list[];
+}; /* HW DATA */
+
+/* GDMA_DESTROY_DMA_REGION */
+struct gdma_destroy_dma_region_req {
+	struct gdma_req_hdr hdr;
+
+	u64 dma_region_handle;
+}; /* HW DATA */
+
+enum gdma_pd_flags {
+	GDMA_PD_FLAG_INVALID = 0,
+};
+
+struct gdma_create_pd_req {
+	struct gdma_req_hdr hdr;
+	enum gdma_pd_flags flags;
+	u32 reserved;
+};/* HW DATA */
+
+struct gdma_create_pd_resp {
+	struct gdma_resp_hdr hdr;
+	u64 pd_handle;
+	u32 pd_id;
+	u32 reserved;
+};/* HW DATA */
+
+struct gdma_destroy_pd_req {
+	struct gdma_req_hdr hdr;
+	u64 pd_handle;
+};/* HW DATA */
+
+struct gdma_destory_pd_resp {
+	struct gdma_resp_hdr hdr;
+};/* HW DATA */
+
+enum gdma_mr_type {
+	/* Guest Virtual Address - MRs of this type allow access
+	 * to memory mapped by PTEs associated with this MR using a virtual
+	 * address that is set up in the MST
+	 */
+	GDMA_MR_TYPE_GVA = 2,
+};
+
+struct gdma_create_mr_params {
+	u64 pd_handle;
+	enum gdma_mr_type mr_type;
+	union {
+		struct {
+			u64 dma_region_handle;
+			u64 virtual_address;
+			enum gdma_mr_access_flags access_flags;
+		} gva;
+	};
+};
+
+struct gdma_create_mr_request {
+	struct gdma_req_hdr hdr;
+	u64 pd_handle;
+	enum gdma_mr_type mr_type;
+	u32 reserved_1;
+
+	union {
+		struct {
+			u64 dma_region_handle;
+			u64 virtual_address;
+			enum gdma_mr_access_flags access_flags;
+		} gva;
+
+	};
+	u32 reserved_2;
+};/* HW DATA */
+
+struct gdma_create_mr_response {
+	struct gdma_resp_hdr hdr;
+	u64 mr_handle;
+	u32 lkey;
+	u32 rkey;
+};/* HW DATA */
+
+struct gdma_destroy_mr_request {
+	struct gdma_req_hdr hdr;
+	u64 mr_handle;
+};/* HW DATA */
+
+struct gdma_destroy_mr_response {
+	struct gdma_resp_hdr hdr;
+};/* HW DATA */
+
+int mana_gd_verify_vf_version(struct pci_dev *pdev);
+
+int mana_gd_register_device(struct gdma_dev *gd);
+int mana_gd_deregister_device(struct gdma_dev *gd);
+
+int mana_gd_post_work_request(struct gdma_queue *wq,
+			      const struct gdma_wqe_request *wqe_req,
+			      struct gdma_posted_wqe_info *wqe_info);
+
+int mana_gd_post_and_ring(struct gdma_queue *queue,
+			  const struct gdma_wqe_request *wqe,
+			  struct gdma_posted_wqe_info *wqe_info);
+
+int mana_gd_alloc_res_map(u32 res_avail, struct gdma_resource *r);
+void mana_gd_free_res_map(struct gdma_resource *r);
+
+void mana_gd_wq_ring_doorbell(struct gdma_context *gc,
+			      struct gdma_queue *queue);
+
+int mana_gd_alloc_memory(struct gdma_context *gc, unsigned int length,
+			 struct gdma_mem_info *gmi);
+
+void mana_gd_free_memory(struct gdma_mem_info *gmi);
+
+int mana_gd_send_request(struct gdma_context *gc, u32 req_len, const void *req,
+			 u32 resp_len, void *resp);
+
+int mana_gd_destroy_dma_region(struct gdma_context *gc, u64 dma_region_handle);
+
+#endif /* _GDMA_H */