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, 605 insertions, 0 deletions

diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
new file mode 100644
index 000000000..5e5ff6784
--- /dev/null
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -0,0 +1,605 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/*
+ * Copyright (c) 2014-2017 Oracle.  All rights reserved.
+ * Copyright (c) 2003-2007 Network Appliance, Inc. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the BSD-type
+ * license below:
+ *
+ * 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 the Network Appliance, Inc. 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_SUNRPC_XPRT_RDMA_H
+#define _LINUX_SUNRPC_XPRT_RDMA_H
+
+#include <linux/wait.h> 		/* wait_queue_head_t, etc */
+#include <linux/spinlock.h> 		/* spinlock_t, etc */
+#include <linux/atomic.h>		/* atomic_t, etc */
+#include <linux/kref.h>			/* struct kref */
+#include <linux/workqueue.h>		/* struct work_struct */
+#include <linux/llist.h>
+
+#include <rdma/rdma_cm.h>		/* RDMA connection api */
+#include <rdma/ib_verbs.h>		/* RDMA verbs api */
+
+#include <linux/sunrpc/clnt.h> 		/* rpc_xprt */
+#include <linux/sunrpc/rpc_rdma_cid.h> 	/* completion IDs */
+#include <linux/sunrpc/rpc_rdma.h> 	/* RPC/RDMA protocol */
+#include <linux/sunrpc/xprtrdma.h> 	/* xprt parameters */
+
+#define RDMA_RESOLVE_TIMEOUT	(5000)	/* 5 seconds */
+#define RDMA_CONNECT_RETRY_MAX	(2)	/* retries if no listener backlog */
+
+#define RPCRDMA_BIND_TO		(60U * HZ)
+#define RPCRDMA_INIT_REEST_TO	(5U * HZ)
+#define RPCRDMA_MAX_REEST_TO	(30U * HZ)
+#define RPCRDMA_IDLE_DISC_TO	(5U * 60 * HZ)
+
+/*
+ * RDMA Endpoint -- connection endpoint details
+ */
+struct rpcrdma_mr;
+struct rpcrdma_ep {
+	struct kref		re_kref;
+	struct rdma_cm_id 	*re_id;
+	struct ib_pd		*re_pd;
+	unsigned int		re_max_rdma_segs;
+	unsigned int		re_max_fr_depth;
+	struct rpcrdma_mr	*re_write_pad_mr;
+	enum ib_mr_type		re_mrtype;
+	struct completion	re_done;
+	unsigned int		re_send_count;
+	unsigned int		re_send_batch;
+	unsigned int		re_max_inline_send;
+	unsigned int		re_max_inline_recv;
+	int			re_async_rc;
+	int			re_connect_status;
+	atomic_t		re_receiving;
+	atomic_t		re_force_disconnect;
+	struct ib_qp_init_attr	re_attr;
+	wait_queue_head_t       re_connect_wait;
+	struct rpc_xprt		*re_xprt;
+	struct rpcrdma_connect_private
+				re_cm_private;
+	struct rdma_conn_param	re_remote_cma;
+	int			re_receive_count;
+	unsigned int		re_max_requests; /* depends on device */
+	unsigned int		re_inline_send;	/* negotiated */
+	unsigned int		re_inline_recv;	/* negotiated */
+
+	atomic_t		re_completion_ids;
+
+	char			re_write_pad[XDR_UNIT];
+};
+
+/* Pre-allocate extra Work Requests for handling reverse-direction
+ * Receives and Sends. This is a fixed value because the Work Queues
+ * are allocated when the forward channel is set up, long before the
+ * backchannel is provisioned. This value is two times
+ * NFS4_DEF_CB_SLOT_TABLE_SIZE.
+ */
+#if defined(CONFIG_SUNRPC_BACKCHANNEL)
+#define RPCRDMA_BACKWARD_WRS (32)
+#else
+#define RPCRDMA_BACKWARD_WRS (0)
+#endif
+
+/* Registered buffer -- registered kmalloc'd memory for RDMA SEND/RECV
+ */
+
+struct rpcrdma_regbuf {
+	struct ib_sge		rg_iov;
+	struct ib_device	*rg_device;
+	enum dma_data_direction	rg_direction;
+	void			*rg_data;
+};
+
+static inline u64 rdmab_addr(struct rpcrdma_regbuf *rb)
+{
+	return rb->rg_iov.addr;
+}
+
+static inline u32 rdmab_length(struct rpcrdma_regbuf *rb)
+{
+	return rb->rg_iov.length;
+}
+
+static inline u32 rdmab_lkey(struct rpcrdma_regbuf *rb)
+{
+	return rb->rg_iov.lkey;
+}
+
+static inline struct ib_device *rdmab_device(struct rpcrdma_regbuf *rb)
+{
+	return rb->rg_device;
+}
+
+static inline void *rdmab_data(const struct rpcrdma_regbuf *rb)
+{
+	return rb->rg_data;
+}
+
+/* Do not use emergency memory reserves, and fail quickly if memory
+ * cannot be allocated easily. These flags may be used wherever there
+ * is robust logic to handle a failure to allocate.
+ */
+#define XPRTRDMA_GFP_FLAGS  (__GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN)
+
+/* To ensure a transport can always make forward progress,
+ * the number of RDMA segments allowed in header chunk lists
+ * is capped at 16. This prevents less-capable devices from
+ * overrunning the Send buffer while building chunk lists.
+ *
+ * Elements of the Read list take up more room than the
+ * Write list or Reply chunk. 16 read segments means the
+ * chunk lists cannot consume more than
+ *
+ * ((16 + 2) * read segment size) + 1 XDR words,
+ *
+ * or about 400 bytes. The fixed part of the header is
+ * another 24 bytes. Thus when the inline threshold is
+ * 1024 bytes, at least 600 bytes are available for RPC
+ * message bodies.
+ */
+enum {
+	RPCRDMA_MAX_HDR_SEGS = 16,
+};
+
+/*
+ * struct rpcrdma_rep -- this structure encapsulates state required
+ * to receive and complete an RPC Reply, asychronously. It needs
+ * several pieces of state:
+ *
+ *   o receive buffer and ib_sge (donated to provider)
+ *   o status of receive (success or not, length, inv rkey)
+ *   o bookkeeping state to get run by reply handler (XDR stream)
+ *
+ * These structures are allocated during transport initialization.
+ * N of these are associated with a transport instance, managed by
+ * struct rpcrdma_buffer. N is the max number of outstanding RPCs.
+ */
+
+struct rpcrdma_rep {
+	struct ib_cqe		rr_cqe;
+	struct rpc_rdma_cid	rr_cid;
+
+	__be32			rr_xid;
+	__be32			rr_vers;
+	__be32			rr_proc;
+	int			rr_wc_flags;
+	u32			rr_inv_rkey;
+	bool			rr_temp;
+	struct rpcrdma_regbuf	*rr_rdmabuf;
+	struct rpcrdma_xprt	*rr_rxprt;
+	struct rpc_rqst		*rr_rqst;
+	struct xdr_buf		rr_hdrbuf;
+	struct xdr_stream	rr_stream;
+	struct llist_node	rr_node;
+	struct ib_recv_wr	rr_recv_wr;
+	struct list_head	rr_all;
+};
+
+/* To reduce the rate at which a transport invokes ib_post_recv
+ * (and thus the hardware doorbell rate), xprtrdma posts Receive
+ * WRs in batches.
+ *
+ * Setting this to zero disables Receive post batching.
+ */
+enum {
+	RPCRDMA_MAX_RECV_BATCH = 7,
+};
+
+/* struct rpcrdma_sendctx - DMA mapped SGEs to unmap after Send completes
+ */
+struct rpcrdma_req;
+struct rpcrdma_sendctx {
+	struct ib_cqe		sc_cqe;
+	struct rpc_rdma_cid	sc_cid;
+	struct rpcrdma_req	*sc_req;
+	unsigned int		sc_unmap_count;
+	struct ib_sge		sc_sges[];
+};
+
+/*
+ * struct rpcrdma_mr - external memory region metadata
+ *
+ * An external memory region is any buffer or page that is registered
+ * on the fly (ie, not pre-registered).
+ */
+struct rpcrdma_req;
+struct rpcrdma_mr {
+	struct list_head	mr_list;
+	struct rpcrdma_req	*mr_req;
+
+	struct ib_mr		*mr_ibmr;
+	struct ib_device	*mr_device;
+	struct scatterlist	*mr_sg;
+	int			mr_nents;
+	enum dma_data_direction	mr_dir;
+	struct ib_cqe		mr_cqe;
+	struct completion	mr_linv_done;
+	union {
+		struct ib_reg_wr	mr_regwr;
+		struct ib_send_wr	mr_invwr;
+	};
+	struct rpcrdma_xprt	*mr_xprt;
+	u32			mr_handle;
+	u32			mr_length;
+	u64			mr_offset;
+	struct list_head	mr_all;
+	struct rpc_rdma_cid	mr_cid;
+};
+
+/*
+ * struct rpcrdma_req -- structure central to the request/reply sequence.
+ *
+ * N of these are associated with a transport instance, and stored in
+ * struct rpcrdma_buffer. N is the max number of outstanding requests.
+ *
+ * It includes pre-registered buffer memory for send AND recv.
+ * The recv buffer, however, is not owned by this structure, and
+ * is "donated" to the hardware when a recv is posted. When a
+ * reply is handled, the recv buffer used is given back to the
+ * struct rpcrdma_req associated with the request.
+ *
+ * In addition to the basic memory, this structure includes an array
+ * of iovs for send operations. The reason is that the iovs passed to
+ * ib_post_{send,recv} must not be modified until the work request
+ * completes.
+ */
+
+/* Maximum number of page-sized "segments" per chunk list to be
+ * registered or invalidated. Must handle a Reply chunk:
+ */
+enum {
+	RPCRDMA_MAX_IOV_SEGS	= 3,
+	RPCRDMA_MAX_DATA_SEGS	= ((1 * 1024 * 1024) / PAGE_SIZE) + 1,
+	RPCRDMA_MAX_SEGS	= RPCRDMA_MAX_DATA_SEGS +
+				  RPCRDMA_MAX_IOV_SEGS,
+};
+
+/* Arguments for DMA mapping and registration */
+struct rpcrdma_mr_seg {
+	u32		mr_len;		/* length of segment */
+	struct page	*mr_page;	/* underlying struct page */
+	u64		mr_offset;	/* IN: page offset, OUT: iova */
+};
+
+/* The Send SGE array is provisioned to send a maximum size
+ * inline request:
+ * - RPC-over-RDMA header
+ * - xdr_buf head iovec
+ * - RPCRDMA_MAX_INLINE bytes, in pages
+ * - xdr_buf tail iovec
+ *
+ * The actual number of array elements consumed by each RPC
+ * depends on the device's max_sge limit.
+ */
+enum {
+	RPCRDMA_MIN_SEND_SGES = 3,
+	RPCRDMA_MAX_PAGE_SGES = RPCRDMA_MAX_INLINE >> PAGE_SHIFT,
+	RPCRDMA_MAX_SEND_SGES = 1 + 1 + RPCRDMA_MAX_PAGE_SGES + 1,
+};
+
+struct rpcrdma_buffer;
+struct rpcrdma_req {
+	struct list_head	rl_list;
+	struct rpc_rqst		rl_slot;
+	struct rpcrdma_rep	*rl_reply;
+	struct xdr_stream	rl_stream;
+	struct xdr_buf		rl_hdrbuf;
+	struct ib_send_wr	rl_wr;
+	struct rpcrdma_sendctx	*rl_sendctx;
+	struct rpcrdma_regbuf	*rl_rdmabuf;	/* xprt header */
+	struct rpcrdma_regbuf	*rl_sendbuf;	/* rq_snd_buf */
+	struct rpcrdma_regbuf	*rl_recvbuf;	/* rq_rcv_buf */
+
+	struct list_head	rl_all;
+	struct kref		rl_kref;
+
+	struct list_head	rl_free_mrs;
+	struct list_head	rl_registered;
+	struct rpcrdma_mr_seg	rl_segments[RPCRDMA_MAX_SEGS];
+};
+
+static inline struct rpcrdma_req *
+rpcr_to_rdmar(const struct rpc_rqst *rqst)
+{
+	return container_of(rqst, struct rpcrdma_req, rl_slot);
+}
+
+static inline void
+rpcrdma_mr_push(struct rpcrdma_mr *mr, struct list_head *list)
+{
+	list_add(&mr->mr_list, list);
+}
+
+static inline struct rpcrdma_mr *
+rpcrdma_mr_pop(struct list_head *list)
+{
+	struct rpcrdma_mr *mr;
+
+	mr = list_first_entry_or_null(list, struct rpcrdma_mr, mr_list);
+	if (mr)
+		list_del_init(&mr->mr_list);
+	return mr;
+}
+
+/*
+ * struct rpcrdma_buffer -- holds list/queue of pre-registered memory for
+ * inline requests/replies, and client/server credits.
+ *
+ * One of these is associated with a transport instance
+ */
+struct rpcrdma_buffer {
+	spinlock_t		rb_lock;
+	struct list_head	rb_send_bufs;
+	struct list_head	rb_mrs;
+
+	unsigned long		rb_sc_head;
+	unsigned long		rb_sc_tail;
+	unsigned long		rb_sc_last;
+	struct rpcrdma_sendctx	**rb_sc_ctxs;
+
+	struct list_head	rb_allreqs;
+	struct list_head	rb_all_mrs;
+	struct list_head	rb_all_reps;
+
+	struct llist_head	rb_free_reps;
+
+	__be32			rb_max_requests;
+	u32			rb_credits;	/* most recent credit grant */
+
+	u32			rb_bc_srv_max_requests;
+	u32			rb_bc_max_requests;
+
+	struct work_struct	rb_refresh_worker;
+};
+
+/*
+ * Statistics for RPCRDMA
+ */
+struct rpcrdma_stats {
+	/* accessed when sending a call */
+	unsigned long		read_chunk_count;
+	unsigned long		write_chunk_count;
+	unsigned long		reply_chunk_count;
+	unsigned long long	total_rdma_request;
+
+	/* rarely accessed error counters */
+	unsigned long long	pullup_copy_count;
+	unsigned long		hardway_register_count;
+	unsigned long		failed_marshal_count;
+	unsigned long		bad_reply_count;
+	unsigned long		mrs_recycled;
+	unsigned long		mrs_orphaned;
+	unsigned long		mrs_allocated;
+	unsigned long		empty_sendctx_q;
+
+	/* accessed when receiving a reply */
+	unsigned long long	total_rdma_reply;
+	unsigned long long	fixup_copy_count;
+	unsigned long		reply_waits_for_send;
+	unsigned long		local_inv_needed;
+	unsigned long		nomsg_call_count;
+	unsigned long		bcall_count;
+};
+
+/*
+ * RPCRDMA transport -- encapsulates the structures above for
+ * integration with RPC.
+ *
+ * The contained structures are embedded, not pointers,
+ * for convenience. This structure need not be visible externally.
+ *
+ * It is allocated and initialized during mount, and released
+ * during unmount.
+ */
+struct rpcrdma_xprt {
+	struct rpc_xprt		rx_xprt;
+	struct rpcrdma_ep	*rx_ep;
+	struct rpcrdma_buffer	rx_buf;
+	struct delayed_work	rx_connect_worker;
+	struct rpc_timeout	rx_timeout;
+	struct rpcrdma_stats	rx_stats;
+};
+
+#define rpcx_to_rdmax(x) container_of(x, struct rpcrdma_xprt, rx_xprt)
+
+static inline const char *
+rpcrdma_addrstr(const struct rpcrdma_xprt *r_xprt)
+{
+	return r_xprt->rx_xprt.address_strings[RPC_DISPLAY_ADDR];
+}
+
+static inline const char *
+rpcrdma_portstr(const struct rpcrdma_xprt *r_xprt)
+{
+	return r_xprt->rx_xprt.address_strings[RPC_DISPLAY_PORT];
+}
+
+/* Setting this to 0 ensures interoperability with early servers.
+ * Setting this to 1 enhances certain unaligned read/write performance.
+ * Default is 0, see sysctl entry and rpc_rdma.c rpcrdma_convert_iovs() */
+extern int xprt_rdma_pad_optimize;
+
+/* This setting controls the hunt for a supported memory
+ * registration strategy.
+ */
+extern unsigned int xprt_rdma_memreg_strategy;
+
+/*
+ * Endpoint calls - xprtrdma/verbs.c
+ */
+void rpcrdma_force_disconnect(struct rpcrdma_ep *ep);
+void rpcrdma_flush_disconnect(struct rpcrdma_xprt *r_xprt, struct ib_wc *wc);
+int rpcrdma_xprt_connect(struct rpcrdma_xprt *r_xprt);
+void rpcrdma_xprt_disconnect(struct rpcrdma_xprt *r_xprt);
+
+void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, int needed, bool temp);
+
+/*
+ * Buffer calls - xprtrdma/verbs.c
+ */
+struct rpcrdma_req *rpcrdma_req_create(struct rpcrdma_xprt *r_xprt,
+				       size_t size);
+int rpcrdma_req_setup(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req);
+void rpcrdma_req_destroy(struct rpcrdma_req *req);
+int rpcrdma_buffer_create(struct rpcrdma_xprt *);
+void rpcrdma_buffer_destroy(struct rpcrdma_buffer *);
+struct rpcrdma_sendctx *rpcrdma_sendctx_get_locked(struct rpcrdma_xprt *r_xprt);
+
+struct rpcrdma_mr *rpcrdma_mr_get(struct rpcrdma_xprt *r_xprt);
+void rpcrdma_mrs_refresh(struct rpcrdma_xprt *r_xprt);
+
+struct rpcrdma_req *rpcrdma_buffer_get(struct rpcrdma_buffer *);
+void rpcrdma_buffer_put(struct rpcrdma_buffer *buffers,
+			struct rpcrdma_req *req);
+void rpcrdma_rep_put(struct rpcrdma_buffer *buf, struct rpcrdma_rep *rep);
+void rpcrdma_reply_put(struct rpcrdma_buffer *buffers, struct rpcrdma_req *req);
+
+bool rpcrdma_regbuf_realloc(struct rpcrdma_regbuf *rb, size_t size,
+			    gfp_t flags);
+bool __rpcrdma_regbuf_dma_map(struct rpcrdma_xprt *r_xprt,
+			      struct rpcrdma_regbuf *rb);
+
+/**
+ * rpcrdma_regbuf_is_mapped - check if buffer is DMA mapped
+ *
+ * Returns true if the buffer is now mapped to rb->rg_device.
+ */
+static inline bool rpcrdma_regbuf_is_mapped(struct rpcrdma_regbuf *rb)
+{
+	return rb->rg_device != NULL;
+}
+
+/**
+ * rpcrdma_regbuf_dma_map - DMA-map a regbuf
+ * @r_xprt: controlling transport instance
+ * @rb: regbuf to be mapped
+ *
+ * Returns true if the buffer is currently DMA mapped.
+ */
+static inline bool rpcrdma_regbuf_dma_map(struct rpcrdma_xprt *r_xprt,
+					  struct rpcrdma_regbuf *rb)
+{
+	if (likely(rpcrdma_regbuf_is_mapped(rb)))
+		return true;
+	return __rpcrdma_regbuf_dma_map(r_xprt, rb);
+}
+
+/*
+ * Wrappers for chunk registration, shared by read/write chunk code.
+ */
+
+static inline enum dma_data_direction
+rpcrdma_data_dir(bool writing)
+{
+	return writing ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
+}
+
+/* Memory registration calls xprtrdma/frwr_ops.c
+ */
+void frwr_reset(struct rpcrdma_req *req);
+int frwr_query_device(struct rpcrdma_ep *ep, const struct ib_device *device);
+int frwr_mr_init(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr *mr);
+void frwr_mr_release(struct rpcrdma_mr *mr);
+struct rpcrdma_mr_seg *frwr_map(struct rpcrdma_xprt *r_xprt,
+				struct rpcrdma_mr_seg *seg,
+				int nsegs, bool writing, __be32 xid,
+				struct rpcrdma_mr *mr);
+int frwr_send(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req);
+void frwr_reminv(struct rpcrdma_rep *rep, struct list_head *mrs);
+void frwr_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req);
+void frwr_unmap_async(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req);
+int frwr_wp_create(struct rpcrdma_xprt *r_xprt);
+
+/*
+ * RPC/RDMA protocol calls - xprtrdma/rpc_rdma.c
+ */
+
+enum rpcrdma_chunktype {
+	rpcrdma_noch = 0,
+	rpcrdma_noch_pullup,
+	rpcrdma_noch_mapped,
+	rpcrdma_readch,
+	rpcrdma_areadch,
+	rpcrdma_writech,
+	rpcrdma_replych
+};
+
+int rpcrdma_prepare_send_sges(struct rpcrdma_xprt *r_xprt,
+			      struct rpcrdma_req *req, u32 hdrlen,
+			      struct xdr_buf *xdr,
+			      enum rpcrdma_chunktype rtype);
+void rpcrdma_sendctx_unmap(struct rpcrdma_sendctx *sc);
+int rpcrdma_marshal_req(struct rpcrdma_xprt *r_xprt, struct rpc_rqst *rqst);
+void rpcrdma_set_max_header_sizes(struct rpcrdma_ep *ep);
+void rpcrdma_reset_cwnd(struct rpcrdma_xprt *r_xprt);
+void rpcrdma_complete_rqst(struct rpcrdma_rep *rep);
+void rpcrdma_unpin_rqst(struct rpcrdma_rep *rep);
+void rpcrdma_reply_handler(struct rpcrdma_rep *rep);
+
+static inline void rpcrdma_set_xdrlen(struct xdr_buf *xdr, size_t len)
+{
+	xdr->head[0].iov_len = len;
+	xdr->len = len;
+}
+
+/* RPC/RDMA module init - xprtrdma/transport.c
+ */
+extern unsigned int xprt_rdma_max_inline_read;
+extern unsigned int xprt_rdma_max_inline_write;
+void xprt_rdma_format_addresses(struct rpc_xprt *xprt, struct sockaddr *sap);
+void xprt_rdma_free_addresses(struct rpc_xprt *xprt);
+void xprt_rdma_close(struct rpc_xprt *xprt);
+void xprt_rdma_print_stats(struct rpc_xprt *xprt, struct seq_file *seq);
+int xprt_rdma_init(void);
+void xprt_rdma_cleanup(void);
+
+/* Backchannel calls - xprtrdma/backchannel.c
+ */
+#if defined(CONFIG_SUNRPC_BACKCHANNEL)
+int xprt_rdma_bc_setup(struct rpc_xprt *, unsigned int);
+size_t xprt_rdma_bc_maxpayload(struct rpc_xprt *);
+unsigned int xprt_rdma_bc_max_slots(struct rpc_xprt *);
+int rpcrdma_bc_post_recv(struct rpcrdma_xprt *, unsigned int);
+void rpcrdma_bc_receive_call(struct rpcrdma_xprt *, struct rpcrdma_rep *);
+int xprt_rdma_bc_send_reply(struct rpc_rqst *rqst);
+void xprt_rdma_bc_free_rqst(struct rpc_rqst *);
+void xprt_rdma_bc_destroy(struct rpc_xprt *, unsigned int);
+#endif	/* CONFIG_SUNRPC_BACKCHANNEL */
+
+extern struct xprt_class xprt_rdma_bc;
+
+#endif				/* _LINUX_SUNRPC_XPRT_RDMA_H */