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, 489 insertions, 0 deletions

diff --git a/drivers/infiniband/hw/mlx5/gsi.c b/drivers/infiniband/hw/mlx5/gsi.c
new file mode 100644
index 000000000..b804f2dd5
--- /dev/null
+++ b/drivers/infiniband/hw/mlx5/gsi.c
@@ -0,0 +1,489 @@
+/*
+ * Copyright (c) 2016, Mellanox Technologies. 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 "mlx5_ib.h"
+
+struct mlx5_ib_gsi_wr {
+	struct ib_cqe cqe;
+	struct ib_wc wc;
+	bool completed:1;
+};
+
+static bool mlx5_ib_deth_sqpn_cap(struct mlx5_ib_dev *dev)
+{
+	return MLX5_CAP_GEN(dev->mdev, set_deth_sqpn);
+}
+
+/* Call with gsi->lock locked */
+static void generate_completions(struct mlx5_ib_qp *mqp)
+{
+	struct mlx5_ib_gsi_qp *gsi = &mqp->gsi;
+	struct ib_cq *gsi_cq = mqp->ibqp.send_cq;
+	struct mlx5_ib_gsi_wr *wr;
+	u32 index;
+
+	for (index = gsi->outstanding_ci; index != gsi->outstanding_pi;
+	     index++) {
+		wr = &gsi->outstanding_wrs[index % gsi->cap.max_send_wr];
+
+		if (!wr->completed)
+			break;
+
+		WARN_ON_ONCE(mlx5_ib_generate_wc(gsi_cq, &wr->wc));
+		wr->completed = false;
+	}
+
+	gsi->outstanding_ci = index;
+}
+
+static void handle_single_completion(struct ib_cq *cq, struct ib_wc *wc)
+{
+	struct mlx5_ib_gsi_qp *gsi = cq->cq_context;
+	struct mlx5_ib_gsi_wr *wr =
+		container_of(wc->wr_cqe, struct mlx5_ib_gsi_wr, cqe);
+	struct mlx5_ib_qp *mqp = container_of(gsi, struct mlx5_ib_qp, gsi);
+	u64 wr_id;
+	unsigned long flags;
+
+	spin_lock_irqsave(&gsi->lock, flags);
+	wr->completed = true;
+	wr_id = wr->wc.wr_id;
+	wr->wc = *wc;
+	wr->wc.wr_id = wr_id;
+	wr->wc.qp = &mqp->ibqp;
+
+	generate_completions(mqp);
+	spin_unlock_irqrestore(&gsi->lock, flags);
+}
+
+int mlx5_ib_create_gsi(struct ib_pd *pd, struct mlx5_ib_qp *mqp,
+		       struct ib_qp_init_attr *attr)
+{
+	struct mlx5_ib_dev *dev = to_mdev(pd->device);
+	struct mlx5_ib_gsi_qp *gsi;
+	struct ib_qp_init_attr hw_init_attr = *attr;
+	const u8 port_num = attr->port_num;
+	int num_qps = 0;
+	int ret;
+
+	if (mlx5_ib_deth_sqpn_cap(dev)) {
+		if (MLX5_CAP_GEN(dev->mdev,
+				 port_type) == MLX5_CAP_PORT_TYPE_IB)
+			num_qps = pd->device->attrs.max_pkeys;
+		else if (dev->lag_active)
+			num_qps = dev->lag_ports;
+	}
+
+	gsi = &mqp->gsi;
+	gsi->tx_qps = kcalloc(num_qps, sizeof(*gsi->tx_qps), GFP_KERNEL);
+	if (!gsi->tx_qps)
+		return -ENOMEM;
+
+	gsi->outstanding_wrs =
+		kcalloc(attr->cap.max_send_wr, sizeof(*gsi->outstanding_wrs),
+			GFP_KERNEL);
+	if (!gsi->outstanding_wrs) {
+		ret = -ENOMEM;
+		goto err_free_tx;
+	}
+
+	if (dev->devr.ports[port_num - 1].gsi) {
+		mlx5_ib_warn(dev, "GSI QP already exists on port %d\n",
+			     port_num);
+		ret = -EBUSY;
+		goto err_free_wrs;
+	}
+	gsi->num_qps = num_qps;
+	spin_lock_init(&gsi->lock);
+
+	gsi->cap = attr->cap;
+	gsi->port_num = port_num;
+
+	gsi->cq = ib_alloc_cq(pd->device, gsi, attr->cap.max_send_wr, 0,
+			      IB_POLL_SOFTIRQ);
+	if (IS_ERR(gsi->cq)) {
+		mlx5_ib_warn(dev, "unable to create send CQ for GSI QP. error %ld\n",
+			     PTR_ERR(gsi->cq));
+		ret = PTR_ERR(gsi->cq);
+		goto err_free_wrs;
+	}
+
+	hw_init_attr.qp_type = MLX5_IB_QPT_HW_GSI;
+	hw_init_attr.send_cq = gsi->cq;
+	if (num_qps) {
+		hw_init_attr.cap.max_send_wr = 0;
+		hw_init_attr.cap.max_send_sge = 0;
+		hw_init_attr.cap.max_inline_data = 0;
+	}
+
+	gsi->rx_qp = ib_create_qp(pd, &hw_init_attr);
+	if (IS_ERR(gsi->rx_qp)) {
+		mlx5_ib_warn(dev, "unable to create hardware GSI QP. error %ld\n",
+			     PTR_ERR(gsi->rx_qp));
+		ret = PTR_ERR(gsi->rx_qp);
+		goto err_destroy_cq;
+	}
+
+	dev->devr.ports[attr->port_num - 1].gsi = gsi;
+	return 0;
+
+err_destroy_cq:
+	ib_free_cq(gsi->cq);
+err_free_wrs:
+	kfree(gsi->outstanding_wrs);
+err_free_tx:
+	kfree(gsi->tx_qps);
+	return ret;
+}
+
+int mlx5_ib_destroy_gsi(struct mlx5_ib_qp *mqp)
+{
+	struct mlx5_ib_dev *dev = to_mdev(mqp->ibqp.device);
+	struct mlx5_ib_gsi_qp *gsi = &mqp->gsi;
+	const int port_num = gsi->port_num;
+	int qp_index;
+	int ret;
+
+	ret = ib_destroy_qp(gsi->rx_qp);
+	if (ret) {
+		mlx5_ib_warn(dev, "unable to destroy hardware GSI QP. error %d\n",
+			     ret);
+		return ret;
+	}
+	dev->devr.ports[port_num - 1].gsi = NULL;
+	gsi->rx_qp = NULL;
+
+	for (qp_index = 0; qp_index < gsi->num_qps; ++qp_index) {
+		if (!gsi->tx_qps[qp_index])
+			continue;
+		WARN_ON_ONCE(ib_destroy_qp(gsi->tx_qps[qp_index]));
+		gsi->tx_qps[qp_index] = NULL;
+	}
+
+	ib_free_cq(gsi->cq);
+
+	kfree(gsi->outstanding_wrs);
+	kfree(gsi->tx_qps);
+	return 0;
+}
+
+static struct ib_qp *create_gsi_ud_qp(struct mlx5_ib_gsi_qp *gsi)
+{
+	struct ib_pd *pd = gsi->rx_qp->pd;
+	struct ib_qp_init_attr init_attr = {
+		.event_handler = gsi->rx_qp->event_handler,
+		.qp_context = gsi->rx_qp->qp_context,
+		.send_cq = gsi->cq,
+		.recv_cq = gsi->rx_qp->recv_cq,
+		.cap = {
+			.max_send_wr = gsi->cap.max_send_wr,
+			.max_send_sge = gsi->cap.max_send_sge,
+			.max_inline_data = gsi->cap.max_inline_data,
+		},
+		.qp_type = IB_QPT_UD,
+		.create_flags = MLX5_IB_QP_CREATE_SQPN_QP1,
+	};
+
+	return ib_create_qp(pd, &init_attr);
+}
+
+static int modify_to_rts(struct mlx5_ib_gsi_qp *gsi, struct ib_qp *qp,
+			 u16 pkey_index)
+{
+	struct mlx5_ib_dev *dev = to_mdev(qp->device);
+	struct ib_qp_attr attr;
+	int mask;
+	int ret;
+
+	mask = IB_QP_STATE | IB_QP_PKEY_INDEX | IB_QP_QKEY | IB_QP_PORT;
+	attr.qp_state = IB_QPS_INIT;
+	attr.pkey_index = pkey_index;
+	attr.qkey = IB_QP1_QKEY;
+	attr.port_num = gsi->port_num;
+	ret = ib_modify_qp(qp, &attr, mask);
+	if (ret) {
+		mlx5_ib_err(dev, "could not change QP%d state to INIT: %d\n",
+			    qp->qp_num, ret);
+		return ret;
+	}
+
+	attr.qp_state = IB_QPS_RTR;
+	ret = ib_modify_qp(qp, &attr, IB_QP_STATE);
+	if (ret) {
+		mlx5_ib_err(dev, "could not change QP%d state to RTR: %d\n",
+			    qp->qp_num, ret);
+		return ret;
+	}
+
+	attr.qp_state = IB_QPS_RTS;
+	attr.sq_psn = 0;
+	ret = ib_modify_qp(qp, &attr, IB_QP_STATE | IB_QP_SQ_PSN);
+	if (ret) {
+		mlx5_ib_err(dev, "could not change QP%d state to RTS: %d\n",
+			    qp->qp_num, ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void setup_qp(struct mlx5_ib_gsi_qp *gsi, u16 qp_index)
+{
+	struct ib_device *device = gsi->rx_qp->device;
+	struct mlx5_ib_dev *dev = to_mdev(device);
+	int pkey_index = qp_index;
+	struct mlx5_ib_qp *mqp;
+	struct ib_qp *qp;
+	unsigned long flags;
+	u16 pkey;
+	int ret;
+
+	if (MLX5_CAP_GEN(dev->mdev,  port_type) != MLX5_CAP_PORT_TYPE_IB)
+		pkey_index = 0;
+
+	ret = ib_query_pkey(device, gsi->port_num, pkey_index, &pkey);
+	if (ret) {
+		mlx5_ib_warn(dev, "unable to read P_Key at port %d, index %d\n",
+			     gsi->port_num, qp_index);
+		return;
+	}
+
+	if (!pkey) {
+		mlx5_ib_dbg(dev, "invalid P_Key at port %d, index %d.  Skipping.\n",
+			    gsi->port_num, qp_index);
+		return;
+	}
+
+	spin_lock_irqsave(&gsi->lock, flags);
+	qp = gsi->tx_qps[qp_index];
+	spin_unlock_irqrestore(&gsi->lock, flags);
+	if (qp) {
+		mlx5_ib_dbg(dev, "already existing GSI TX QP at port %d, index %d. Skipping\n",
+			    gsi->port_num, qp_index);
+		return;
+	}
+
+	qp = create_gsi_ud_qp(gsi);
+	if (IS_ERR(qp)) {
+		mlx5_ib_warn(dev, "unable to create hardware UD QP for GSI: %ld\n",
+			     PTR_ERR(qp));
+		return;
+	}
+
+	mqp = to_mqp(qp);
+	if (dev->lag_active)
+		mqp->gsi_lag_port = qp_index + 1;
+	ret = modify_to_rts(gsi, qp, pkey_index);
+	if (ret)
+		goto err_destroy_qp;
+
+	spin_lock_irqsave(&gsi->lock, flags);
+	WARN_ON_ONCE(gsi->tx_qps[qp_index]);
+	gsi->tx_qps[qp_index] = qp;
+	spin_unlock_irqrestore(&gsi->lock, flags);
+
+	return;
+
+err_destroy_qp:
+	WARN_ON_ONCE(qp);
+}
+
+int mlx5_ib_gsi_modify_qp(struct ib_qp *qp, struct ib_qp_attr *attr,
+			  int attr_mask)
+{
+	struct mlx5_ib_dev *dev = to_mdev(qp->device);
+	struct mlx5_ib_qp *mqp = to_mqp(qp);
+	struct mlx5_ib_gsi_qp *gsi = &mqp->gsi;
+	u16 qp_index;
+	int ret;
+
+	mlx5_ib_dbg(dev, "modifying GSI QP to state %d\n", attr->qp_state);
+
+	ret = ib_modify_qp(gsi->rx_qp, attr, attr_mask);
+	if (ret) {
+		mlx5_ib_warn(dev, "unable to modify GSI rx QP: %d\n", ret);
+		return ret;
+	}
+
+	if (to_mqp(gsi->rx_qp)->state != IB_QPS_RTS)
+		return 0;
+
+	for (qp_index = 0; qp_index < gsi->num_qps; ++qp_index)
+		setup_qp(gsi, qp_index);
+	return 0;
+}
+
+int mlx5_ib_gsi_query_qp(struct ib_qp *qp, struct ib_qp_attr *qp_attr,
+			 int qp_attr_mask,
+			 struct ib_qp_init_attr *qp_init_attr)
+{
+	struct mlx5_ib_qp *mqp = to_mqp(qp);
+	struct mlx5_ib_gsi_qp *gsi = &mqp->gsi;
+	int ret;
+
+	ret = ib_query_qp(gsi->rx_qp, qp_attr, qp_attr_mask, qp_init_attr);
+	qp_init_attr->cap = gsi->cap;
+	return ret;
+}
+
+/* Call with gsi->lock locked */
+static int mlx5_ib_add_outstanding_wr(struct mlx5_ib_qp *mqp,
+				      struct ib_ud_wr *wr, struct ib_wc *wc)
+{
+	struct mlx5_ib_gsi_qp *gsi = &mqp->gsi;
+	struct mlx5_ib_dev *dev = to_mdev(gsi->rx_qp->device);
+	struct mlx5_ib_gsi_wr *gsi_wr;
+
+	if (gsi->outstanding_pi == gsi->outstanding_ci + gsi->cap.max_send_wr) {
+		mlx5_ib_warn(dev, "no available GSI work request.\n");
+		return -ENOMEM;
+	}
+
+	gsi_wr = &gsi->outstanding_wrs[gsi->outstanding_pi %
+				       gsi->cap.max_send_wr];
+	gsi->outstanding_pi++;
+
+	if (!wc) {
+		memset(&gsi_wr->wc, 0, sizeof(gsi_wr->wc));
+		gsi_wr->wc.pkey_index = wr->pkey_index;
+		gsi_wr->wc.wr_id = wr->wr.wr_id;
+	} else {
+		gsi_wr->wc = *wc;
+		gsi_wr->completed = true;
+	}
+
+	gsi_wr->cqe.done = &handle_single_completion;
+	wr->wr.wr_cqe = &gsi_wr->cqe;
+
+	return 0;
+}
+
+/* Call with gsi->lock locked */
+static int mlx5_ib_gsi_silent_drop(struct mlx5_ib_qp *mqp, struct ib_ud_wr *wr)
+{
+	struct ib_wc wc = {
+		{ .wr_id = wr->wr.wr_id },
+		.status = IB_WC_SUCCESS,
+		.opcode = IB_WC_SEND,
+		.qp = &mqp->ibqp,
+	};
+	int ret;
+
+	ret = mlx5_ib_add_outstanding_wr(mqp, wr, &wc);
+	if (ret)
+		return ret;
+
+	generate_completions(mqp);
+
+	return 0;
+}
+
+/* Call with gsi->lock locked */
+static struct ib_qp *get_tx_qp(struct mlx5_ib_gsi_qp *gsi, struct ib_ud_wr *wr)
+{
+	struct mlx5_ib_dev *dev = to_mdev(gsi->rx_qp->device);
+	struct mlx5_ib_ah *ah = to_mah(wr->ah);
+	int qp_index = wr->pkey_index;
+
+	if (!gsi->num_qps)
+		return gsi->rx_qp;
+
+	if (dev->lag_active && ah->xmit_port)
+		qp_index = ah->xmit_port - 1;
+
+	if (qp_index >= gsi->num_qps)
+		return NULL;
+
+	return gsi->tx_qps[qp_index];
+}
+
+int mlx5_ib_gsi_post_send(struct ib_qp *qp, const struct ib_send_wr *wr,
+			  const struct ib_send_wr **bad_wr)
+{
+	struct mlx5_ib_qp *mqp = to_mqp(qp);
+	struct mlx5_ib_gsi_qp *gsi = &mqp->gsi;
+	struct ib_qp *tx_qp;
+	unsigned long flags;
+	int ret;
+
+	for (; wr; wr = wr->next) {
+		struct ib_ud_wr cur_wr = *ud_wr(wr);
+
+		cur_wr.wr.next = NULL;
+
+		spin_lock_irqsave(&gsi->lock, flags);
+		tx_qp = get_tx_qp(gsi, &cur_wr);
+		if (!tx_qp) {
+			ret = mlx5_ib_gsi_silent_drop(mqp, &cur_wr);
+			if (ret)
+				goto err;
+			spin_unlock_irqrestore(&gsi->lock, flags);
+			continue;
+		}
+
+		ret = mlx5_ib_add_outstanding_wr(mqp, &cur_wr, NULL);
+		if (ret)
+			goto err;
+
+		ret = ib_post_send(tx_qp, &cur_wr.wr, bad_wr);
+		if (ret) {
+			/* Undo the effect of adding the outstanding wr */
+			gsi->outstanding_pi--;
+			goto err;
+		}
+		spin_unlock_irqrestore(&gsi->lock, flags);
+	}
+
+	return 0;
+
+err:
+	spin_unlock_irqrestore(&gsi->lock, flags);
+	*bad_wr = wr;
+	return ret;
+}
+
+int mlx5_ib_gsi_post_recv(struct ib_qp *qp, const struct ib_recv_wr *wr,
+			  const struct ib_recv_wr **bad_wr)
+{
+	struct mlx5_ib_qp *mqp = to_mqp(qp);
+	struct mlx5_ib_gsi_qp *gsi = &mqp->gsi;
+
+	return ib_post_recv(gsi->rx_qp, wr, bad_wr);
+}
+
+void mlx5_ib_gsi_pkey_change(struct mlx5_ib_gsi_qp *gsi)
+{
+	u16 qp_index;
+
+	for (qp_index = 0; qp_index < gsi->num_qps; ++qp_index)
+		setup_qp(gsi, qp_index);
+}