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, 521 insertions, 0 deletions

diff --git a/drivers/infiniband/hw/qib/qib_uc.c b/drivers/infiniband/hw/qib/qib_uc.c
new file mode 100644
index 000000000..8e2bda77d
--- /dev/null
+++ b/drivers/infiniband/hw/qib/qib_uc.c
@@ -0,0 +1,521 @@
+/*
+ * Copyright (c) 2006, 2007, 2008, 2009, 2010 QLogic Corporation.
+ * All rights reserved.
+ * Copyright (c) 2005, 2006 PathScale, 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
+ * OpenIB.org BSD 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.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include "qib.h"
+
+/* cut down ridiculously long IB macro names */
+#define OP(x) IB_OPCODE_UC_##x
+
+/**
+ * qib_make_uc_req - construct a request packet (SEND, RDMA write)
+ * @qp: a pointer to the QP
+ * @flags: unused
+ *
+ * Assumes the s_lock is held.
+ *
+ * Return 1 if constructed; otherwise, return 0.
+ */
+int qib_make_uc_req(struct rvt_qp *qp, unsigned long *flags)
+{
+	struct qib_qp_priv *priv = qp->priv;
+	struct ib_other_headers *ohdr;
+	struct rvt_swqe *wqe;
+	u32 hwords;
+	u32 bth0;
+	u32 len;
+	u32 pmtu = qp->pmtu;
+	int ret = 0;
+
+	if (!(ib_rvt_state_ops[qp->state] & RVT_PROCESS_SEND_OK)) {
+		if (!(ib_rvt_state_ops[qp->state] & RVT_FLUSH_SEND))
+			goto bail;
+		/* We are in the error state, flush the work request. */
+		if (qp->s_last == READ_ONCE(qp->s_head))
+			goto bail;
+		/* If DMAs are in progress, we can't flush immediately. */
+		if (atomic_read(&priv->s_dma_busy)) {
+			qp->s_flags |= RVT_S_WAIT_DMA;
+			goto bail;
+		}
+		wqe = rvt_get_swqe_ptr(qp, qp->s_last);
+		rvt_send_complete(qp, wqe, IB_WC_WR_FLUSH_ERR);
+		goto done;
+	}
+
+	ohdr = &priv->s_hdr->u.oth;
+	if (rdma_ah_get_ah_flags(&qp->remote_ah_attr) & IB_AH_GRH)
+		ohdr = &priv->s_hdr->u.l.oth;
+
+	/* header size in 32-bit words LRH+BTH = (8+12)/4. */
+	hwords = 5;
+	bth0 = 0;
+
+	/* Get the next send request. */
+	wqe = rvt_get_swqe_ptr(qp, qp->s_cur);
+	qp->s_wqe = NULL;
+	switch (qp->s_state) {
+	default:
+		if (!(ib_rvt_state_ops[qp->state] &
+		    RVT_PROCESS_NEXT_SEND_OK))
+			goto bail;
+		/* Check if send work queue is empty. */
+		if (qp->s_cur == READ_ONCE(qp->s_head))
+			goto bail;
+		/*
+		 * Start a new request.
+		 */
+		qp->s_psn = wqe->psn;
+		qp->s_sge.sge = wqe->sg_list[0];
+		qp->s_sge.sg_list = wqe->sg_list + 1;
+		qp->s_sge.num_sge = wqe->wr.num_sge;
+		qp->s_sge.total_len = wqe->length;
+		len = wqe->length;
+		qp->s_len = len;
+		switch (wqe->wr.opcode) {
+		case IB_WR_SEND:
+		case IB_WR_SEND_WITH_IMM:
+			if (len > pmtu) {
+				qp->s_state = OP(SEND_FIRST);
+				len = pmtu;
+				break;
+			}
+			if (wqe->wr.opcode == IB_WR_SEND)
+				qp->s_state = OP(SEND_ONLY);
+			else {
+				qp->s_state =
+					OP(SEND_ONLY_WITH_IMMEDIATE);
+				/* Immediate data comes after the BTH */
+				ohdr->u.imm_data = wqe->wr.ex.imm_data;
+				hwords += 1;
+			}
+			if (wqe->wr.send_flags & IB_SEND_SOLICITED)
+				bth0 |= IB_BTH_SOLICITED;
+			qp->s_wqe = wqe;
+			if (++qp->s_cur >= qp->s_size)
+				qp->s_cur = 0;
+			break;
+
+		case IB_WR_RDMA_WRITE:
+		case IB_WR_RDMA_WRITE_WITH_IMM:
+			ohdr->u.rc.reth.vaddr =
+				cpu_to_be64(wqe->rdma_wr.remote_addr);
+			ohdr->u.rc.reth.rkey =
+				cpu_to_be32(wqe->rdma_wr.rkey);
+			ohdr->u.rc.reth.length = cpu_to_be32(len);
+			hwords += sizeof(struct ib_reth) / 4;
+			if (len > pmtu) {
+				qp->s_state = OP(RDMA_WRITE_FIRST);
+				len = pmtu;
+				break;
+			}
+			if (wqe->wr.opcode == IB_WR_RDMA_WRITE)
+				qp->s_state = OP(RDMA_WRITE_ONLY);
+			else {
+				qp->s_state =
+					OP(RDMA_WRITE_ONLY_WITH_IMMEDIATE);
+				/* Immediate data comes after the RETH */
+				ohdr->u.rc.imm_data = wqe->wr.ex.imm_data;
+				hwords += 1;
+				if (wqe->wr.send_flags & IB_SEND_SOLICITED)
+					bth0 |= IB_BTH_SOLICITED;
+			}
+			qp->s_wqe = wqe;
+			if (++qp->s_cur >= qp->s_size)
+				qp->s_cur = 0;
+			break;
+
+		default:
+			goto bail;
+		}
+		break;
+
+	case OP(SEND_FIRST):
+		qp->s_state = OP(SEND_MIDDLE);
+		fallthrough;
+	case OP(SEND_MIDDLE):
+		len = qp->s_len;
+		if (len > pmtu) {
+			len = pmtu;
+			break;
+		}
+		if (wqe->wr.opcode == IB_WR_SEND)
+			qp->s_state = OP(SEND_LAST);
+		else {
+			qp->s_state = OP(SEND_LAST_WITH_IMMEDIATE);
+			/* Immediate data comes after the BTH */
+			ohdr->u.imm_data = wqe->wr.ex.imm_data;
+			hwords += 1;
+		}
+		if (wqe->wr.send_flags & IB_SEND_SOLICITED)
+			bth0 |= IB_BTH_SOLICITED;
+		qp->s_wqe = wqe;
+		if (++qp->s_cur >= qp->s_size)
+			qp->s_cur = 0;
+		break;
+
+	case OP(RDMA_WRITE_FIRST):
+		qp->s_state = OP(RDMA_WRITE_MIDDLE);
+		fallthrough;
+	case OP(RDMA_WRITE_MIDDLE):
+		len = qp->s_len;
+		if (len > pmtu) {
+			len = pmtu;
+			break;
+		}
+		if (wqe->wr.opcode == IB_WR_RDMA_WRITE)
+			qp->s_state = OP(RDMA_WRITE_LAST);
+		else {
+			qp->s_state =
+				OP(RDMA_WRITE_LAST_WITH_IMMEDIATE);
+			/* Immediate data comes after the BTH */
+			ohdr->u.imm_data = wqe->wr.ex.imm_data;
+			hwords += 1;
+			if (wqe->wr.send_flags & IB_SEND_SOLICITED)
+				bth0 |= IB_BTH_SOLICITED;
+		}
+		qp->s_wqe = wqe;
+		if (++qp->s_cur >= qp->s_size)
+			qp->s_cur = 0;
+		break;
+	}
+	qp->s_len -= len;
+	qp->s_hdrwords = hwords;
+	qp->s_cur_sge = &qp->s_sge;
+	qp->s_cur_size = len;
+	qib_make_ruc_header(qp, ohdr, bth0 | (qp->s_state << 24),
+			    qp->s_psn++ & QIB_PSN_MASK);
+done:
+	return 1;
+bail:
+	qp->s_flags &= ~RVT_S_BUSY;
+	return ret;
+}
+
+/**
+ * qib_uc_rcv - handle an incoming UC packet
+ * @ibp: the port the packet came in on
+ * @hdr: the header of the packet
+ * @has_grh: true if the packet has a GRH
+ * @data: the packet data
+ * @tlen: the length of the packet
+ * @qp: the QP for this packet.
+ *
+ * This is called from qib_qp_rcv() to process an incoming UC packet
+ * for the given QP.
+ * Called at interrupt level.
+ */
+void qib_uc_rcv(struct qib_ibport *ibp, struct ib_header *hdr,
+		int has_grh, void *data, u32 tlen, struct rvt_qp *qp)
+{
+	struct ib_other_headers *ohdr;
+	u32 opcode;
+	u32 hdrsize;
+	u32 psn;
+	u32 pad;
+	struct ib_wc wc;
+	u32 pmtu = qp->pmtu;
+	struct ib_reth *reth;
+	int ret;
+
+	/* Check for GRH */
+	if (!has_grh) {
+		ohdr = &hdr->u.oth;
+		hdrsize = 8 + 12;       /* LRH + BTH */
+	} else {
+		ohdr = &hdr->u.l.oth;
+		hdrsize = 8 + 40 + 12;  /* LRH + GRH + BTH */
+	}
+
+	opcode = be32_to_cpu(ohdr->bth[0]);
+	if (qib_ruc_check_hdr(ibp, hdr, has_grh, qp, opcode))
+		return;
+
+	psn = be32_to_cpu(ohdr->bth[2]);
+	opcode >>= 24;
+
+	/* Compare the PSN verses the expected PSN. */
+	if (unlikely(qib_cmp24(psn, qp->r_psn) != 0)) {
+		/*
+		 * Handle a sequence error.
+		 * Silently drop any current message.
+		 */
+		qp->r_psn = psn;
+inv:
+		if (qp->r_state == OP(SEND_FIRST) ||
+		    qp->r_state == OP(SEND_MIDDLE)) {
+			set_bit(RVT_R_REWIND_SGE, &qp->r_aflags);
+			qp->r_sge.num_sge = 0;
+		} else
+			rvt_put_ss(&qp->r_sge);
+		qp->r_state = OP(SEND_LAST);
+		switch (opcode) {
+		case OP(SEND_FIRST):
+		case OP(SEND_ONLY):
+		case OP(SEND_ONLY_WITH_IMMEDIATE):
+			goto send_first;
+
+		case OP(RDMA_WRITE_FIRST):
+		case OP(RDMA_WRITE_ONLY):
+		case OP(RDMA_WRITE_ONLY_WITH_IMMEDIATE):
+			goto rdma_first;
+
+		default:
+			goto drop;
+		}
+	}
+
+	/* Check for opcode sequence errors. */
+	switch (qp->r_state) {
+	case OP(SEND_FIRST):
+	case OP(SEND_MIDDLE):
+		if (opcode == OP(SEND_MIDDLE) ||
+		    opcode == OP(SEND_LAST) ||
+		    opcode == OP(SEND_LAST_WITH_IMMEDIATE))
+			break;
+		goto inv;
+
+	case OP(RDMA_WRITE_FIRST):
+	case OP(RDMA_WRITE_MIDDLE):
+		if (opcode == OP(RDMA_WRITE_MIDDLE) ||
+		    opcode == OP(RDMA_WRITE_LAST) ||
+		    opcode == OP(RDMA_WRITE_LAST_WITH_IMMEDIATE))
+			break;
+		goto inv;
+
+	default:
+		if (opcode == OP(SEND_FIRST) ||
+		    opcode == OP(SEND_ONLY) ||
+		    opcode == OP(SEND_ONLY_WITH_IMMEDIATE) ||
+		    opcode == OP(RDMA_WRITE_FIRST) ||
+		    opcode == OP(RDMA_WRITE_ONLY) ||
+		    opcode == OP(RDMA_WRITE_ONLY_WITH_IMMEDIATE))
+			break;
+		goto inv;
+	}
+
+	if (qp->state == IB_QPS_RTR && !(qp->r_flags & RVT_R_COMM_EST))
+		rvt_comm_est(qp);
+
+	/* OK, process the packet. */
+	switch (opcode) {
+	case OP(SEND_FIRST):
+	case OP(SEND_ONLY):
+	case OP(SEND_ONLY_WITH_IMMEDIATE):
+send_first:
+		if (test_and_clear_bit(RVT_R_REWIND_SGE, &qp->r_aflags))
+			qp->r_sge = qp->s_rdma_read_sge;
+		else {
+			ret = rvt_get_rwqe(qp, false);
+			if (ret < 0)
+				goto op_err;
+			if (!ret)
+				goto drop;
+			/*
+			 * qp->s_rdma_read_sge will be the owner
+			 * of the mr references.
+			 */
+			qp->s_rdma_read_sge = qp->r_sge;
+		}
+		qp->r_rcv_len = 0;
+		if (opcode == OP(SEND_ONLY))
+			goto no_immediate_data;
+		else if (opcode == OP(SEND_ONLY_WITH_IMMEDIATE))
+			goto send_last_imm;
+		fallthrough;
+	case OP(SEND_MIDDLE):
+		/* Check for invalid length PMTU or posted rwqe len. */
+		if (unlikely(tlen != (hdrsize + pmtu + 4)))
+			goto rewind;
+		qp->r_rcv_len += pmtu;
+		if (unlikely(qp->r_rcv_len > qp->r_len))
+			goto rewind;
+		rvt_copy_sge(qp, &qp->r_sge, data, pmtu, false, false);
+		break;
+
+	case OP(SEND_LAST_WITH_IMMEDIATE):
+send_last_imm:
+		wc.ex.imm_data = ohdr->u.imm_data;
+		hdrsize += 4;
+		wc.wc_flags = IB_WC_WITH_IMM;
+		goto send_last;
+	case OP(SEND_LAST):
+no_immediate_data:
+		wc.ex.imm_data = 0;
+		wc.wc_flags = 0;
+send_last:
+		/* Get the number of bytes the message was padded by. */
+		pad = (be32_to_cpu(ohdr->bth[0]) >> 20) & 3;
+		/* Check for invalid length. */
+		/* XXX LAST len should be >= 1 */
+		if (unlikely(tlen < (hdrsize + pad + 4)))
+			goto rewind;
+		/* Don't count the CRC. */
+		tlen -= (hdrsize + pad + 4);
+		wc.byte_len = tlen + qp->r_rcv_len;
+		if (unlikely(wc.byte_len > qp->r_len))
+			goto rewind;
+		wc.opcode = IB_WC_RECV;
+		rvt_copy_sge(qp, &qp->r_sge, data, tlen, false, false);
+		rvt_put_ss(&qp->s_rdma_read_sge);
+last_imm:
+		wc.wr_id = qp->r_wr_id;
+		wc.status = IB_WC_SUCCESS;
+		wc.qp = &qp->ibqp;
+		wc.src_qp = qp->remote_qpn;
+		wc.slid = rdma_ah_get_dlid(&qp->remote_ah_attr);
+		wc.sl = rdma_ah_get_sl(&qp->remote_ah_attr);
+		/* zero fields that are N/A */
+		wc.vendor_err = 0;
+		wc.pkey_index = 0;
+		wc.dlid_path_bits = 0;
+		wc.port_num = 0;
+		/* Signal completion event if the solicited bit is set. */
+		rvt_recv_cq(qp, &wc, ib_bth_is_solicited(ohdr));
+		break;
+
+	case OP(RDMA_WRITE_FIRST):
+	case OP(RDMA_WRITE_ONLY):
+	case OP(RDMA_WRITE_ONLY_WITH_IMMEDIATE): /* consume RWQE */
+rdma_first:
+		if (unlikely(!(qp->qp_access_flags &
+			       IB_ACCESS_REMOTE_WRITE))) {
+			goto drop;
+		}
+		reth = &ohdr->u.rc.reth;
+		hdrsize += sizeof(*reth);
+		qp->r_len = be32_to_cpu(reth->length);
+		qp->r_rcv_len = 0;
+		qp->r_sge.sg_list = NULL;
+		if (qp->r_len != 0) {
+			u32 rkey = be32_to_cpu(reth->rkey);
+			u64 vaddr = be64_to_cpu(reth->vaddr);
+			int ok;
+
+			/* Check rkey */
+			ok = rvt_rkey_ok(qp, &qp->r_sge.sge, qp->r_len,
+					 vaddr, rkey, IB_ACCESS_REMOTE_WRITE);
+			if (unlikely(!ok))
+				goto drop;
+			qp->r_sge.num_sge = 1;
+		} else {
+			qp->r_sge.num_sge = 0;
+			qp->r_sge.sge.mr = NULL;
+			qp->r_sge.sge.vaddr = NULL;
+			qp->r_sge.sge.length = 0;
+			qp->r_sge.sge.sge_length = 0;
+		}
+		if (opcode == OP(RDMA_WRITE_ONLY))
+			goto rdma_last;
+		else if (opcode == OP(RDMA_WRITE_ONLY_WITH_IMMEDIATE)) {
+			wc.ex.imm_data = ohdr->u.rc.imm_data;
+			goto rdma_last_imm;
+		}
+		fallthrough;
+	case OP(RDMA_WRITE_MIDDLE):
+		/* Check for invalid length PMTU or posted rwqe len. */
+		if (unlikely(tlen != (hdrsize + pmtu + 4)))
+			goto drop;
+		qp->r_rcv_len += pmtu;
+		if (unlikely(qp->r_rcv_len > qp->r_len))
+			goto drop;
+		rvt_copy_sge(qp, &qp->r_sge, data, pmtu, true, false);
+		break;
+
+	case OP(RDMA_WRITE_LAST_WITH_IMMEDIATE):
+		wc.ex.imm_data = ohdr->u.imm_data;
+rdma_last_imm:
+		hdrsize += 4;
+		wc.wc_flags = IB_WC_WITH_IMM;
+
+		/* Get the number of bytes the message was padded by. */
+		pad = (be32_to_cpu(ohdr->bth[0]) >> 20) & 3;
+		/* Check for invalid length. */
+		/* XXX LAST len should be >= 1 */
+		if (unlikely(tlen < (hdrsize + pad + 4)))
+			goto drop;
+		/* Don't count the CRC. */
+		tlen -= (hdrsize + pad + 4);
+		if (unlikely(tlen + qp->r_rcv_len != qp->r_len))
+			goto drop;
+		if (test_and_clear_bit(RVT_R_REWIND_SGE, &qp->r_aflags))
+			rvt_put_ss(&qp->s_rdma_read_sge);
+		else {
+			ret = rvt_get_rwqe(qp, true);
+			if (ret < 0)
+				goto op_err;
+			if (!ret)
+				goto drop;
+		}
+		wc.byte_len = qp->r_len;
+		wc.opcode = IB_WC_RECV_RDMA_WITH_IMM;
+		rvt_copy_sge(qp, &qp->r_sge, data, tlen, true, false);
+		rvt_put_ss(&qp->r_sge);
+		goto last_imm;
+
+	case OP(RDMA_WRITE_LAST):
+rdma_last:
+		/* Get the number of bytes the message was padded by. */
+		pad = (be32_to_cpu(ohdr->bth[0]) >> 20) & 3;
+		/* Check for invalid length. */
+		/* XXX LAST len should be >= 1 */
+		if (unlikely(tlen < (hdrsize + pad + 4)))
+			goto drop;
+		/* Don't count the CRC. */
+		tlen -= (hdrsize + pad + 4);
+		if (unlikely(tlen + qp->r_rcv_len != qp->r_len))
+			goto drop;
+		rvt_copy_sge(qp, &qp->r_sge, data, tlen, true, false);
+		rvt_put_ss(&qp->r_sge);
+		break;
+
+	default:
+		/* Drop packet for unknown opcodes. */
+		goto drop;
+	}
+	qp->r_psn++;
+	qp->r_state = opcode;
+	return;
+
+rewind:
+	set_bit(RVT_R_REWIND_SGE, &qp->r_aflags);
+	qp->r_sge.num_sge = 0;
+drop:
+	ibp->rvp.n_pkt_drops++;
+	return;
+
+op_err:
+	rvt_rc_error(qp, IB_WC_LOC_QP_OP_ERR);
+	return;
+
+}