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().
  ...

2 files changed, 442 insertions, 0 deletions

diff --git a/include/uapi/rdma/hfi/hfi1_ioctl.h b/include/uapi/rdma/hfi/hfi1_ioctl.h
new file mode 100644
index 000000000..8f3d9fe7b
--- /dev/null
+++ b/include/uapi/rdma/hfi/hfi1_ioctl.h
@@ -0,0 +1,174 @@
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/*
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2015 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2015 Intel Corporation.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *  - Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ *  - Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *  - Neither the name of Intel Corporation nor the names of its
+ *    contributors may be used to endorse or promote products derived
+ *    from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ */
+
+#ifndef _LINUX__HFI1_IOCTL_H
+#define _LINUX__HFI1_IOCTL_H
+#include <linux/types.h>
+
+/*
+ * This structure is passed to the driver to tell it where
+ * user code buffers are, sizes, etc.   The offsets and sizes of the
+ * fields must remain unchanged, for binary compatibility.  It can
+ * be extended, if userversion is changed so user code can tell, if needed
+ */
+struct hfi1_user_info {
+	/*
+	 * version of user software, to detect compatibility issues.
+	 * Should be set to HFI1_USER_SWVERSION.
+	 */
+	__u32 userversion;
+	__u32 pad;
+	/*
+	 * If two or more processes wish to share a context, each process
+	 * must set the subcontext_cnt and subcontext_id to the same
+	 * values.  The only restriction on the subcontext_id is that
+	 * it be unique for a given node.
+	 */
+	__u16 subctxt_cnt;
+	__u16 subctxt_id;
+	/* 128bit UUID passed in by PSM. */
+	__u8 uuid[16];
+};
+
+struct hfi1_ctxt_info {
+	__aligned_u64 runtime_flags;    /* chip/drv runtime flags (HFI1_CAP_*) */
+	__u32 rcvegr_size;      /* size of each eager buffer */
+	__u16 num_active;       /* number of active units */
+	__u16 unit;             /* unit (chip) assigned to caller */
+	__u16 ctxt;             /* ctxt on unit assigned to caller */
+	__u16 subctxt;          /* subctxt on unit assigned to caller */
+	__u16 rcvtids;          /* number of Rcv TIDs for this context */
+	__u16 credits;          /* number of PIO credits for this context */
+	__u16 numa_node;        /* NUMA node of the assigned device */
+	__u16 rec_cpu;          /* cpu # for affinity (0xffff if none) */
+	__u16 send_ctxt;        /* send context in use by this user context */
+	__u16 egrtids;          /* number of RcvArray entries for Eager Rcvs */
+	__u16 rcvhdrq_cnt;      /* number of RcvHdrQ entries */
+	__u16 rcvhdrq_entsize;  /* size (in bytes) for each RcvHdrQ entry */
+	__u16 sdma_ring_size;   /* number of entries in SDMA request ring */
+};
+
+struct hfi1_tid_info {
+	/* virtual address of first page in transfer */
+	__aligned_u64 vaddr;
+	/* pointer to tid array. this array is big enough */
+	__aligned_u64 tidlist;
+	/* number of tids programmed by this request */
+	__u32 tidcnt;
+	/* length of transfer buffer programmed by this request */
+	__u32 length;
+};
+
+/*
+ * This structure is returned by the driver immediately after
+ * open to get implementation-specific info, and info specific to this
+ * instance.
+ *
+ * This struct must have explicit pad fields where type sizes
+ * may result in different alignments between 32 and 64 bit
+ * programs, since the 64 bit * bit kernel requires the user code
+ * to have matching offsets
+ */
+struct hfi1_base_info {
+	/* version of hardware, for feature checking. */
+	__u32 hw_version;
+	/* version of software, for feature checking. */
+	__u32 sw_version;
+	/* Job key */
+	__u16 jkey;
+	__u16 padding1;
+	/*
+	 * The special QP (queue pair) value that identifies PSM
+	 * protocol packet from standard IB packets.
+	 */
+	__u32 bthqp;
+	/* PIO credit return address, */
+	__aligned_u64 sc_credits_addr;
+	/*
+	 * Base address of write-only pio buffers for this process.
+	 * Each buffer has sendpio_credits*64 bytes.
+	 */
+	__aligned_u64 pio_bufbase_sop;
+	/*
+	 * Base address of write-only pio buffers for this process.
+	 * Each buffer has sendpio_credits*64 bytes.
+	 */
+	__aligned_u64 pio_bufbase;
+	/* address where receive buffer queue is mapped into */
+	__aligned_u64 rcvhdr_bufbase;
+	/* base address of Eager receive buffers. */
+	__aligned_u64 rcvegr_bufbase;
+	/* base address of SDMA completion ring */
+	__aligned_u64 sdma_comp_bufbase;
+	/*
+	 * User register base for init code, not to be used directly by
+	 * protocol or applications.  Always maps real chip register space.
+	 * the register addresses are:
+	 * ur_rcvhdrhead, ur_rcvhdrtail, ur_rcvegrhead, ur_rcvegrtail,
+	 * ur_rcvtidflow
+	 */
+	__aligned_u64 user_regbase;
+	/* notification events */
+	__aligned_u64 events_bufbase;
+	/* status page */
+	__aligned_u64 status_bufbase;
+	/* rcvhdrtail update */
+	__aligned_u64 rcvhdrtail_base;
+	/*
+	 * shared memory pages for subctxts if ctxt is shared; these cover
+	 * all the processes in the group sharing a single context.
+	 * all have enough space for the num_subcontexts value on this job.
+	 */
+	__aligned_u64 subctxt_uregbase;
+	__aligned_u64 subctxt_rcvegrbuf;
+	__aligned_u64 subctxt_rcvhdrbuf;
+};
+#endif /* _LINIUX__HFI1_IOCTL_H */
diff --git a/include/uapi/rdma/hfi/hfi1_user.h b/include/uapi/rdma/hfi/hfi1_user.h
new file mode 100644
index 000000000..1106a7c90
--- /dev/null
+++ b/include/uapi/rdma/hfi/hfi1_user.h
@@ -0,0 +1,268 @@
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/*
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2015 - 2020 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2015 Intel Corporation.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *  - Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ *  - Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *  - Neither the name of Intel Corporation nor the names of its
+ *    contributors may be used to endorse or promote products derived
+ *    from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ */
+
+/*
+ * This file contains defines, structures, etc. that are used
+ * to communicate between kernel and user code.
+ */
+
+#ifndef _LINUX__HFI1_USER_H
+#define _LINUX__HFI1_USER_H
+
+#include <linux/types.h>
+#include <rdma/rdma_user_ioctl.h>
+
+/*
+ * This version number is given to the driver by the user code during
+ * initialization in the spu_userversion field of hfi1_user_info, so
+ * the driver can check for compatibility with user code.
+ *
+ * The major version changes when data structures change in an incompatible
+ * way. The driver must be the same for initialization to succeed.
+ */
+#define HFI1_USER_SWMAJOR 6
+
+/*
+ * Minor version differences are always compatible
+ * a within a major version, however if user software is larger
+ * than driver software, some new features and/or structure fields
+ * may not be implemented; the user code must deal with this if it
+ * cares, or it must abort after initialization reports the difference.
+ */
+#define HFI1_USER_SWMINOR 3
+
+/*
+ * We will encode the major/minor inside a single 32bit version number.
+ */
+#define HFI1_SWMAJOR_SHIFT 16
+
+/*
+ * Set of HW and driver capability/feature bits.
+ * These bit values are used to configure enabled/disabled HW and
+ * driver features. The same set of bits are communicated to user
+ * space.
+ */
+#define HFI1_CAP_DMA_RTAIL        (1UL <<  0) /* Use DMA'ed RTail value */
+#define HFI1_CAP_SDMA             (1UL <<  1) /* Enable SDMA support */
+#define HFI1_CAP_SDMA_AHG         (1UL <<  2) /* Enable SDMA AHG support */
+#define HFI1_CAP_EXTENDED_PSN     (1UL <<  3) /* Enable Extended PSN support */
+#define HFI1_CAP_HDRSUPP          (1UL <<  4) /* Enable Header Suppression */
+#define HFI1_CAP_TID_RDMA         (1UL <<  5) /* Enable TID RDMA operations */
+#define HFI1_CAP_USE_SDMA_HEAD    (1UL <<  6) /* DMA Hdr Q tail vs. use CSR */
+#define HFI1_CAP_MULTI_PKT_EGR    (1UL <<  7) /* Enable multi-packet Egr buffs*/
+#define HFI1_CAP_NODROP_RHQ_FULL  (1UL <<  8) /* Don't drop on Hdr Q full */
+#define HFI1_CAP_NODROP_EGR_FULL  (1UL <<  9) /* Don't drop on EGR buffs full */
+#define HFI1_CAP_TID_UNMAP        (1UL << 10) /* Disable Expected TID caching */
+#define HFI1_CAP_PRINT_UNIMPL     (1UL << 11) /* Show for unimplemented feats */
+#define HFI1_CAP_ALLOW_PERM_JKEY  (1UL << 12) /* Allow use of permissive JKEY */
+#define HFI1_CAP_NO_INTEGRITY     (1UL << 13) /* Enable ctxt integrity checks */
+#define HFI1_CAP_PKEY_CHECK       (1UL << 14) /* Enable ctxt PKey checking */
+#define HFI1_CAP_STATIC_RATE_CTRL (1UL << 15) /* Allow PBC.StaticRateControl */
+#define HFI1_CAP_OPFN             (1UL << 16) /* Enable the OPFN protocol */
+#define HFI1_CAP_SDMA_HEAD_CHECK  (1UL << 17) /* SDMA head checking */
+#define HFI1_CAP_EARLY_CREDIT_RETURN (1UL << 18) /* early credit return */
+#define HFI1_CAP_AIP              (1UL << 19) /* Enable accelerated IP */
+
+#define HFI1_RCVHDR_ENTSIZE_2    (1UL << 0)
+#define HFI1_RCVHDR_ENTSIZE_16   (1UL << 1)
+#define HFI1_RCVDHR_ENTSIZE_32   (1UL << 2)
+
+#define _HFI1_EVENT_FROZEN_BIT         0
+#define _HFI1_EVENT_LINKDOWN_BIT       1
+#define _HFI1_EVENT_LID_CHANGE_BIT     2
+#define _HFI1_EVENT_LMC_CHANGE_BIT     3
+#define _HFI1_EVENT_SL2VL_CHANGE_BIT   4
+#define _HFI1_EVENT_TID_MMU_NOTIFY_BIT 5
+#define _HFI1_MAX_EVENT_BIT _HFI1_EVENT_TID_MMU_NOTIFY_BIT
+
+#define HFI1_EVENT_FROZEN            (1UL << _HFI1_EVENT_FROZEN_BIT)
+#define HFI1_EVENT_LINKDOWN          (1UL << _HFI1_EVENT_LINKDOWN_BIT)
+#define HFI1_EVENT_LID_CHANGE        (1UL << _HFI1_EVENT_LID_CHANGE_BIT)
+#define HFI1_EVENT_LMC_CHANGE        (1UL << _HFI1_EVENT_LMC_CHANGE_BIT)
+#define HFI1_EVENT_SL2VL_CHANGE      (1UL << _HFI1_EVENT_SL2VL_CHANGE_BIT)
+#define HFI1_EVENT_TID_MMU_NOTIFY    (1UL << _HFI1_EVENT_TID_MMU_NOTIFY_BIT)
+
+/*
+ * These are the status bits readable (in ASCII form, 64bit value)
+ * from the "status" sysfs file.  For binary compatibility, values
+ * must remain as is; removed states can be reused for different
+ * purposes.
+ */
+#define HFI1_STATUS_INITTED       0x1    /* basic initialization done */
+/* Chip has been found and initialized */
+#define HFI1_STATUS_CHIP_PRESENT 0x20
+/* IB link is at ACTIVE, usable for data traffic */
+#define HFI1_STATUS_IB_READY     0x40
+/* link is configured, LID, MTU, etc. have been set */
+#define HFI1_STATUS_IB_CONF      0x80
+/* A Fatal hardware error has occurred. */
+#define HFI1_STATUS_HWERROR     0x200
+
+/*
+ * Number of supported shared contexts.
+ * This is the maximum number of software contexts that can share
+ * a hardware send/receive context.
+ */
+#define HFI1_MAX_SHARED_CTXTS 8
+
+/*
+ * Poll types
+ */
+#define HFI1_POLL_TYPE_ANYRCV     0x0
+#define HFI1_POLL_TYPE_URGENT     0x1
+
+enum hfi1_sdma_comp_state {
+	FREE = 0,
+	QUEUED,
+	COMPLETE,
+	ERROR
+};
+
+/*
+ * SDMA completion ring entry
+ */
+struct hfi1_sdma_comp_entry {
+	__u32 status;
+	__u32 errcode;
+};
+
+/*
+ * Device status and notifications from driver to user-space.
+ */
+struct hfi1_status {
+	__aligned_u64 dev;      /* device/hw status bits */
+	__aligned_u64 port;     /* port state and status bits */
+	char freezemsg[];
+};
+
+enum sdma_req_opcode {
+	EXPECTED = 0,
+	EAGER
+};
+
+#define HFI1_SDMA_REQ_VERSION_MASK 0xF
+#define HFI1_SDMA_REQ_VERSION_SHIFT 0x0
+#define HFI1_SDMA_REQ_OPCODE_MASK 0xF
+#define HFI1_SDMA_REQ_OPCODE_SHIFT 0x4
+#define HFI1_SDMA_REQ_IOVCNT_MASK 0xFF
+#define HFI1_SDMA_REQ_IOVCNT_SHIFT 0x8
+
+struct sdma_req_info {
+	/*
+	 * bits 0-3 - version (currently unused)
+	 * bits 4-7 - opcode (enum sdma_req_opcode)
+	 * bits 8-15 - io vector count
+	 */
+	__u16 ctrl;
+	/*
+	 * Number of fragments contained in this request.
+	 * User-space has already computed how many
+	 * fragment-sized packet the user buffer will be
+	 * split into.
+	 */
+	__u16 npkts;
+	/*
+	 * Size of each fragment the user buffer will be
+	 * split into.
+	 */
+	__u16 fragsize;
+	/*
+	 * Index of the slot in the SDMA completion ring
+	 * this request should be using. User-space is
+	 * in charge of managing its own ring.
+	 */
+	__u16 comp_idx;
+} __attribute__((__packed__));
+
+/*
+ * SW KDETH header.
+ * swdata is SW defined portion.
+ */
+struct hfi1_kdeth_header {
+	__le32 ver_tid_offset;
+	__le16 jkey;
+	__le16 hcrc;
+	__le32 swdata[7];
+}  __attribute__((__packed__));
+
+/*
+ * Structure describing the headers that User space uses. The
+ * structure above is a subset of this one.
+ */
+struct hfi1_pkt_header {
+	__le16 pbc[4];
+	__be16 lrh[4];
+	__be32 bth[3];
+	struct hfi1_kdeth_header kdeth;
+}  __attribute__((__packed__));
+
+
+/*
+ * The list of usermode accessible registers.
+ */
+enum hfi1_ureg {
+	/* (RO)  DMA RcvHdr to be used next. */
+	ur_rcvhdrtail = 0,
+	/* (RW)  RcvHdr entry to be processed next by host. */
+	ur_rcvhdrhead = 1,
+	/* (RO)  Index of next Eager index to use. */
+	ur_rcvegrindextail = 2,
+	/* (RW)  Eager TID to be processed next */
+	ur_rcvegrindexhead = 3,
+	/* (RO)  Receive Eager Offset Tail */
+	ur_rcvegroffsettail = 4,
+	/* For internal use only; max register number. */
+	ur_maxreg,
+	/* (RW)  Receive TID flow table */
+	ur_rcvtidflowtable = 256
+};
+
+#endif /* _LINIUX__HFI1_USER_H */