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, 487 insertions, 0 deletions

diff --git a/drivers/infiniband/hw/hfi1/verbs.h b/drivers/infiniband/hw/hfi1/verbs.h
new file mode 100644
index 000000000..7f30f32b3
--- /dev/null
+++ b/drivers/infiniband/hw/hfi1/verbs.h
@@ -0,0 +1,487 @@
+/* SPDX-License-Identifier: GPL-2.0 or BSD-3-Clause */
+/*
+ * Copyright(c) 2015 - 2018 Intel Corporation.
+ */
+
+#ifndef HFI1_VERBS_H
+#define HFI1_VERBS_H
+
+#include <linux/types.h>
+#include <linux/seqlock.h>
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/kref.h>
+#include <linux/workqueue.h>
+#include <linux/kthread.h>
+#include <linux/completion.h>
+#include <linux/slab.h>
+#include <rdma/ib_pack.h>
+#include <rdma/ib_user_verbs.h>
+#include <rdma/ib_mad.h>
+#include <rdma/ib_hdrs.h>
+#include <rdma/rdma_vt.h>
+#include <rdma/rdmavt_qp.h>
+#include <rdma/rdmavt_cq.h>
+
+struct hfi1_ctxtdata;
+struct hfi1_pportdata;
+struct hfi1_devdata;
+struct hfi1_packet;
+
+#include "iowait.h"
+#include "tid_rdma.h"
+#include "opfn.h"
+
+#define HFI1_MAX_RDMA_ATOMIC     16
+
+/*
+ * Increment this value if any changes that break userspace ABI
+ * compatibility are made.
+ */
+#define HFI1_UVERBS_ABI_VERSION       2
+
+/* IB Performance Manager status values */
+#define IB_PMA_SAMPLE_STATUS_DONE       0x00
+#define IB_PMA_SAMPLE_STATUS_STARTED    0x01
+#define IB_PMA_SAMPLE_STATUS_RUNNING    0x02
+
+/* Mandatory IB performance counter select values. */
+#define IB_PMA_PORT_XMIT_DATA   cpu_to_be16(0x0001)
+#define IB_PMA_PORT_RCV_DATA    cpu_to_be16(0x0002)
+#define IB_PMA_PORT_XMIT_PKTS   cpu_to_be16(0x0003)
+#define IB_PMA_PORT_RCV_PKTS    cpu_to_be16(0x0004)
+#define IB_PMA_PORT_XMIT_WAIT   cpu_to_be16(0x0005)
+
+#define HFI1_VENDOR_IPG		cpu_to_be16(0xFFA0)
+
+#define IB_DEFAULT_GID_PREFIX	cpu_to_be64(0xfe80000000000000ULL)
+#define OPA_BTH_MIG_REQ		BIT(31)
+
+#define RC_OP(x) IB_OPCODE_RC_##x
+#define UC_OP(x) IB_OPCODE_UC_##x
+
+/* flags passed by hfi1_ib_rcv() */
+enum {
+	HFI1_HAS_GRH = (1 << 0),
+};
+
+#define LRH_16B_BYTES (sizeof_field(struct hfi1_16b_header, lrh))
+#define LRH_16B_DWORDS (LRH_16B_BYTES / sizeof(u32))
+#define LRH_9B_BYTES (sizeof_field(struct ib_header, lrh))
+#define LRH_9B_DWORDS (LRH_9B_BYTES / sizeof(u32))
+
+/* 24Bits for qpn, upper 8Bits reserved */
+struct opa_16b_mgmt {
+	__be32 dest_qpn;
+	__be32 src_qpn;
+};
+
+struct hfi1_16b_header {
+	u32 lrh[4];
+	union {
+		struct {
+			struct ib_grh grh;
+			struct ib_other_headers oth;
+		} l;
+		struct ib_other_headers oth;
+		struct opa_16b_mgmt mgmt;
+	} u;
+} __packed;
+
+struct hfi1_opa_header {
+	union {
+		struct ib_header ibh; /* 9B header */
+		struct hfi1_16b_header opah; /* 16B header */
+	};
+	u8 hdr_type; /* 9B or 16B */
+} __packed;
+
+struct hfi1_ahg_info {
+	u32 ahgdesc[2];
+	u16 tx_flags;
+	u8 ahgcount;
+	u8 ahgidx;
+};
+
+struct hfi1_sdma_header {
+	__le64 pbc;
+	struct hfi1_opa_header hdr;
+} __packed;
+
+/*
+ * hfi1 specific data structures that will be hidden from rvt after the queue
+ * pair is made common
+ */
+struct hfi1_qp_priv {
+	struct hfi1_ahg_info *s_ahg;              /* ahg info for next header */
+	struct sdma_engine *s_sde;                /* current sde */
+	struct send_context *s_sendcontext;       /* current sendcontext */
+	struct hfi1_ctxtdata *rcd;                /* QP's receive context */
+	struct page **pages;                      /* for TID page scan */
+	u32 tid_enqueue;                          /* saved when tid waited */
+	u8 s_sc;		                  /* SC[0..4] for next packet */
+	struct iowait s_iowait;
+	struct timer_list s_tid_timer;            /* for timing tid wait */
+	struct timer_list s_tid_retry_timer;      /* for timing tid ack */
+	struct list_head tid_wait;                /* for queueing tid space */
+	struct hfi1_opfn_data opfn;
+	struct tid_flow_state flow_state;
+	struct tid_rdma_qp_params tid_rdma;
+	struct rvt_qp *owner;
+	u16 s_running_pkt_size;
+	u8 hdr_type; /* 9B or 16B */
+	struct rvt_sge_state tid_ss;       /* SGE state pointer for 2nd leg */
+	atomic_t n_requests;               /* # of TID RDMA requests in the */
+					   /* queue */
+	atomic_t n_tid_requests;            /* # of sent TID RDMA requests */
+	unsigned long tid_timer_timeout_jiffies;
+	unsigned long tid_retry_timeout_jiffies;
+
+	/* variables for the TID RDMA SE state machine */
+	u8 s_state;
+	u8 s_retry;
+	u8 rnr_nak_state;       /* RNR NAK state */
+	u8 s_nak_state;
+	u32 s_nak_psn;
+	u32 s_flags;
+	u32 s_tid_cur;
+	u32 s_tid_head;
+	u32 s_tid_tail;
+	u32 r_tid_head;     /* Most recently added TID RDMA request */
+	u32 r_tid_tail;     /* the last completed TID RDMA request */
+	u32 r_tid_ack;      /* the TID RDMA request to be ACK'ed */
+	u32 r_tid_alloc;    /* Request for which we are allocating resources */
+	u32 pending_tid_w_segs; /* Num of pending tid write segments */
+	u32 pending_tid_w_resp; /* Num of pending tid write responses */
+	u32 alloc_w_segs;       /* Number of segments for which write */
+			       /* resources have been allocated for this QP */
+
+	/* For TID RDMA READ */
+	u32 tid_r_reqs;         /* Num of tid reads requested */
+	u32 tid_r_comp;         /* Num of tid reads completed */
+	u32 pending_tid_r_segs; /* Num of pending tid read segments */
+	u16 pkts_ps;            /* packets per segment */
+	u8 timeout_shift;       /* account for number of packets per segment */
+
+	u32 r_next_psn_kdeth;
+	u32 r_next_psn_kdeth_save;
+	u32 s_resync_psn;
+	u8 sync_pt;           /* Set when QP reaches sync point */
+	u8 resync;
+};
+
+#define HFI1_QP_WQE_INVALID   ((u32)-1)
+
+struct hfi1_swqe_priv {
+	struct tid_rdma_request tid_req;
+	struct rvt_sge_state ss;  /* Used for TID RDMA READ Request */
+};
+
+struct hfi1_ack_priv {
+	struct rvt_sge_state ss;               /* used for TID WRITE RESP */
+	struct tid_rdma_request tid_req;
+};
+
+/*
+ * This structure is used to hold commonly lookedup and computed values during
+ * the send engine progress.
+ */
+struct iowait_work;
+struct hfi1_pkt_state {
+	struct hfi1_ibdev *dev;
+	struct hfi1_ibport *ibp;
+	struct hfi1_pportdata *ppd;
+	struct verbs_txreq *s_txreq;
+	struct iowait_work *wait;
+	unsigned long flags;
+	unsigned long timeout;
+	unsigned long timeout_int;
+	int cpu;
+	u8 opcode;
+	bool in_thread;
+	bool pkts_sent;
+};
+
+#define HFI1_PSN_CREDIT  16
+
+struct hfi1_opcode_stats {
+	u64 n_packets;          /* number of packets */
+	u64 n_bytes;            /* total number of bytes */
+};
+
+struct hfi1_opcode_stats_perctx {
+	struct hfi1_opcode_stats stats[256];
+};
+
+static inline void inc_opstats(
+	u32 tlen,
+	struct hfi1_opcode_stats *stats)
+{
+#ifdef CONFIG_DEBUG_FS
+	stats->n_bytes += tlen;
+	stats->n_packets++;
+#endif
+}
+
+struct hfi1_ibport {
+	struct rvt_qp __rcu *qp[2];
+	struct rvt_ibport rvp;
+
+	/* the first 16 entries are sl_to_vl for !OPA */
+	u8 sl_to_sc[32];
+	u8 sc_to_sl[32];
+};
+
+struct hfi1_ibdev {
+	struct rvt_dev_info rdi; /* Must be first */
+
+	/* QP numbers are shared by all IB ports */
+	/* protect txwait list */
+	seqlock_t txwait_lock ____cacheline_aligned_in_smp;
+	struct list_head txwait;        /* list for wait verbs_txreq */
+	struct list_head memwait;       /* list for wait kernel memory */
+	struct kmem_cache *verbs_txreq_cache;
+	u64 n_txwait;
+	u64 n_kmem_wait;
+	u64 n_tidwait;
+
+	/* protect iowait lists */
+	seqlock_t iowait_lock ____cacheline_aligned_in_smp;
+	u64 n_piowait;
+	u64 n_piodrain;
+	struct timer_list mem_timer;
+
+#ifdef CONFIG_DEBUG_FS
+	/* per HFI debugfs */
+	struct dentry *hfi1_ibdev_dbg;
+	/* per HFI symlinks to above */
+	struct dentry *hfi1_ibdev_link;
+#ifdef CONFIG_FAULT_INJECTION
+	struct fault *fault;
+#endif
+#endif
+};
+
+static inline struct hfi1_ibdev *to_idev(struct ib_device *ibdev)
+{
+	struct rvt_dev_info *rdi;
+
+	rdi = container_of(ibdev, struct rvt_dev_info, ibdev);
+	return container_of(rdi, struct hfi1_ibdev, rdi);
+}
+
+static inline struct rvt_qp *iowait_to_qp(struct iowait *s_iowait)
+{
+	struct hfi1_qp_priv *priv;
+
+	priv = container_of(s_iowait, struct hfi1_qp_priv, s_iowait);
+	return priv->owner;
+}
+
+/*
+ * This must be called with s_lock held.
+ */
+void hfi1_bad_pkey(struct hfi1_ibport *ibp, u32 key, u32 sl,
+		   u32 qp1, u32 qp2, u32 lid1, u32 lid2);
+void hfi1_cap_mask_chg(struct rvt_dev_info *rdi, u32 port_num);
+void hfi1_sys_guid_chg(struct hfi1_ibport *ibp);
+void hfi1_node_desc_chg(struct hfi1_ibport *ibp);
+int hfi1_process_mad(struct ib_device *ibdev, int mad_flags, u32 port,
+		     const struct ib_wc *in_wc, const struct ib_grh *in_grh,
+		     const struct ib_mad *in_mad, struct ib_mad *out_mad,
+		     size_t *out_mad_size, u16 *out_mad_pkey_index);
+
+/*
+ * The PSN_MASK and PSN_SHIFT allow for
+ * 1) comparing two PSNs
+ * 2) returning the PSN with any upper bits masked
+ * 3) returning the difference between to PSNs
+ *
+ * The number of significant bits in the PSN must
+ * necessarily be at least one bit less than
+ * the container holding the PSN.
+ */
+#define PSN_MASK 0x7FFFFFFF
+#define PSN_SHIFT 1
+#define PSN_MODIFY_MASK 0xFFFFFF
+
+/*
+ * Compare two PSNs
+ * Returns an integer <, ==, or > than zero.
+ */
+static inline int cmp_psn(u32 a, u32 b)
+{
+	return (((int)a) - ((int)b)) << PSN_SHIFT;
+}
+
+/*
+ * Return masked PSN
+ */
+static inline u32 mask_psn(u32 a)
+{
+	return a & PSN_MASK;
+}
+
+/*
+ * Return delta between two PSNs
+ */
+static inline u32 delta_psn(u32 a, u32 b)
+{
+	return (((int)a - (int)b) << PSN_SHIFT) >> PSN_SHIFT;
+}
+
+static inline struct tid_rdma_request *wqe_to_tid_req(struct rvt_swqe *wqe)
+{
+	return &((struct hfi1_swqe_priv *)wqe->priv)->tid_req;
+}
+
+static inline struct tid_rdma_request *ack_to_tid_req(struct rvt_ack_entry *e)
+{
+	return &((struct hfi1_ack_priv *)e->priv)->tid_req;
+}
+
+/*
+ * Look through all the active flows for a TID RDMA request and find
+ * the one (if it exists) that contains the specified PSN.
+ */
+static inline u32 __full_flow_psn(struct flow_state *state, u32 psn)
+{
+	return mask_psn((state->generation << HFI1_KDETH_BTH_SEQ_SHIFT) |
+			(psn & HFI1_KDETH_BTH_SEQ_MASK));
+}
+
+static inline u32 full_flow_psn(struct tid_rdma_flow *flow, u32 psn)
+{
+	return __full_flow_psn(&flow->flow_state, psn);
+}
+
+struct verbs_txreq;
+void hfi1_put_txreq(struct verbs_txreq *tx);
+
+int hfi1_verbs_send(struct rvt_qp *qp, struct hfi1_pkt_state *ps);
+
+void hfi1_cnp_rcv(struct hfi1_packet *packet);
+
+void hfi1_uc_rcv(struct hfi1_packet *packet);
+
+void hfi1_rc_rcv(struct hfi1_packet *packet);
+
+void hfi1_rc_hdrerr(
+	struct hfi1_ctxtdata *rcd,
+	struct hfi1_packet *packet,
+	struct rvt_qp *qp);
+
+u8 ah_to_sc(struct ib_device *ibdev, struct rdma_ah_attr *ah_attr);
+
+void hfi1_rc_verbs_aborted(struct rvt_qp *qp, struct hfi1_opa_header *opah);
+void hfi1_rc_send_complete(struct rvt_qp *qp, struct hfi1_opa_header *opah);
+
+void hfi1_ud_rcv(struct hfi1_packet *packet);
+
+int hfi1_lookup_pkey_idx(struct hfi1_ibport *ibp, u16 pkey);
+
+void hfi1_migrate_qp(struct rvt_qp *qp);
+
+int hfi1_check_modify_qp(struct rvt_qp *qp, struct ib_qp_attr *attr,
+			 int attr_mask, struct ib_udata *udata);
+
+void hfi1_modify_qp(struct rvt_qp *qp, struct ib_qp_attr *attr,
+		    int attr_mask, struct ib_udata *udata);
+void hfi1_restart_rc(struct rvt_qp *qp, u32 psn, int wait);
+int hfi1_setup_wqe(struct rvt_qp *qp, struct rvt_swqe *wqe,
+		   bool *call_send);
+
+int hfi1_ruc_check_hdr(struct hfi1_ibport *ibp, struct hfi1_packet *packet);
+
+u32 hfi1_make_grh(struct hfi1_ibport *ibp, struct ib_grh *hdr,
+		  const struct ib_global_route *grh, u32 hwords, u32 nwords);
+
+void hfi1_make_ruc_header(struct rvt_qp *qp, struct ib_other_headers *ohdr,
+			  u32 bth0, u32 bth1, u32 bth2, int middle,
+			  struct hfi1_pkt_state *ps);
+
+bool hfi1_schedule_send_yield(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
+			      bool tid);
+
+void _hfi1_do_send(struct work_struct *work);
+
+void hfi1_do_send_from_rvt(struct rvt_qp *qp);
+
+void hfi1_do_send(struct rvt_qp *qp, bool in_thread);
+
+void hfi1_send_rc_ack(struct hfi1_packet *packet, bool is_fecn);
+
+int hfi1_make_rc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps);
+
+int hfi1_make_uc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps);
+
+int hfi1_make_ud_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps);
+
+int hfi1_register_ib_device(struct hfi1_devdata *);
+
+void hfi1_unregister_ib_device(struct hfi1_devdata *);
+
+void hfi1_kdeth_eager_rcv(struct hfi1_packet *packet);
+
+void hfi1_kdeth_expected_rcv(struct hfi1_packet *packet);
+
+void hfi1_ib_rcv(struct hfi1_packet *packet);
+
+void hfi1_16B_rcv(struct hfi1_packet *packet);
+
+unsigned hfi1_get_npkeys(struct hfi1_devdata *);
+
+int hfi1_verbs_send_dma(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
+			u64 pbc);
+
+int hfi1_verbs_send_pio(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
+			u64 pbc);
+
+static inline bool opa_bth_is_migration(struct ib_other_headers *ohdr)
+{
+	return ohdr->bth[1] & cpu_to_be32(OPA_BTH_MIG_REQ);
+}
+
+void hfi1_wait_kmem(struct rvt_qp *qp);
+
+static inline void hfi1_trdma_send_complete(struct rvt_qp *qp,
+					    struct rvt_swqe *wqe,
+					    enum ib_wc_status status)
+{
+	trdma_clean_swqe(qp, wqe);
+	rvt_send_complete(qp, wqe, status);
+}
+
+extern const enum ib_wc_opcode ib_hfi1_wc_opcode[];
+
+extern const u8 hdr_len_by_opcode[];
+
+extern const int ib_rvt_state_ops[];
+
+extern __be64 ib_hfi1_sys_image_guid;    /* in network order */
+
+extern unsigned int hfi1_max_cqes;
+
+extern unsigned int hfi1_max_cqs;
+
+extern unsigned int hfi1_max_qp_wrs;
+
+extern unsigned int hfi1_max_qps;
+
+extern unsigned int hfi1_max_sges;
+
+extern unsigned int hfi1_max_mcast_grps;
+
+extern unsigned int hfi1_max_mcast_qp_attached;
+
+extern unsigned int hfi1_max_srqs;
+
+extern unsigned int hfi1_max_srq_sges;
+
+extern unsigned int hfi1_max_srq_wrs;
+
+extern unsigned short piothreshold;
+
+extern const u32 ib_hfi1_rnr_table[];
+
+#endif                          /* HFI1_VERBS_H */