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, 743 insertions, 0 deletions

diff --git a/drivers/infiniband/ulp/iser/iser_initiator.c b/drivers/infiniband/ulp/iser/iser_initiator.c
new file mode 100644
index 000000000..7b83f48f6
--- /dev/null
+++ b/drivers/infiniband/ulp/iser/iser_initiator.c
@@ -0,0 +1,743 @@
+/*
+ * Copyright (c) 2004, 2005, 2006 Voltaire, Inc. All rights reserved.
+ * Copyright (c) 2013-2014 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 <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
+#include <linux/scatterlist.h>
+#include <linux/kfifo.h>
+#include <scsi/scsi_cmnd.h>
+#include <scsi/scsi_host.h>
+
+#include "iscsi_iser.h"
+
+/* Register user buffer memory and initialize passive rdma
+ *  dto descriptor. Data size is stored in
+ *  task->data[ISER_DIR_IN].data_len, Protection size
+ *  os stored in task->prot[ISER_DIR_IN].data_len
+ */
+static int iser_prepare_read_cmd(struct iscsi_task *task)
+
+{
+	struct iscsi_iser_task *iser_task = task->dd_data;
+	struct iser_mem_reg *mem_reg;
+	int err;
+	struct iser_ctrl *hdr = &iser_task->desc.iser_header;
+
+	err = iser_dma_map_task_data(iser_task,
+				     ISER_DIR_IN,
+				     DMA_FROM_DEVICE);
+	if (err)
+		return err;
+
+	err = iser_reg_mem_fastreg(iser_task, ISER_DIR_IN, false);
+	if (err) {
+		iser_err("Failed to set up Data-IN RDMA\n");
+		goto out_err;
+	}
+	mem_reg = &iser_task->rdma_reg[ISER_DIR_IN];
+
+	hdr->flags    |= ISER_RSV;
+	hdr->read_stag = cpu_to_be32(mem_reg->rkey);
+	hdr->read_va   = cpu_to_be64(mem_reg->sge.addr);
+
+	iser_dbg("Cmd itt:%d READ tags RKEY:%#.4X VA:%#llX\n",
+		 task->itt, mem_reg->rkey,
+		 (unsigned long long)mem_reg->sge.addr);
+
+	return 0;
+
+out_err:
+	iser_dma_unmap_task_data(iser_task, ISER_DIR_IN, DMA_FROM_DEVICE);
+	return err;
+}
+
+/* Register user buffer memory and initialize passive rdma
+ *  dto descriptor. Data size is stored in
+ *  task->data[ISER_DIR_OUT].data_len, Protection size
+ *  is stored at task->prot[ISER_DIR_OUT].data_len
+ */
+static int iser_prepare_write_cmd(struct iscsi_task *task, unsigned int imm_sz,
+				  unsigned int unsol_sz, unsigned int edtl)
+{
+	struct iscsi_iser_task *iser_task = task->dd_data;
+	struct iser_mem_reg *mem_reg;
+	int err;
+	struct iser_ctrl *hdr = &iser_task->desc.iser_header;
+	struct iser_data_buf *buf_out = &iser_task->data[ISER_DIR_OUT];
+	struct ib_sge *tx_dsg = &iser_task->desc.tx_sg[1];
+
+	err = iser_dma_map_task_data(iser_task,
+				     ISER_DIR_OUT,
+				     DMA_TO_DEVICE);
+	if (err)
+		return err;
+
+	err = iser_reg_mem_fastreg(iser_task, ISER_DIR_OUT,
+				   buf_out->data_len == imm_sz);
+	if (err) {
+		iser_err("Failed to register write cmd RDMA mem\n");
+		goto out_err;
+	}
+
+	mem_reg = &iser_task->rdma_reg[ISER_DIR_OUT];
+
+	if (unsol_sz < edtl) {
+		hdr->flags     |= ISER_WSV;
+		if (buf_out->data_len > imm_sz) {
+			hdr->write_stag = cpu_to_be32(mem_reg->rkey);
+			hdr->write_va = cpu_to_be64(mem_reg->sge.addr + unsol_sz);
+		}
+
+		iser_dbg("Cmd itt:%d, WRITE tags, RKEY:%#.4X VA:%#llX + unsol:%d\n",
+			 task->itt, mem_reg->rkey,
+			 (unsigned long long)mem_reg->sge.addr, unsol_sz);
+	}
+
+	if (imm_sz > 0) {
+		iser_dbg("Cmd itt:%d, WRITE, adding imm.data sz: %d\n",
+			 task->itt, imm_sz);
+		tx_dsg->addr = mem_reg->sge.addr;
+		tx_dsg->length = imm_sz;
+		tx_dsg->lkey = mem_reg->sge.lkey;
+		iser_task->desc.num_sge = 2;
+	}
+
+	return 0;
+
+out_err:
+	iser_dma_unmap_task_data(iser_task, ISER_DIR_OUT, DMA_TO_DEVICE);
+	return err;
+}
+
+/* creates a new tx descriptor and adds header regd buffer */
+static void iser_create_send_desc(struct iser_conn *iser_conn,
+				  struct iser_tx_desc *tx_desc)
+{
+	struct iser_device *device = iser_conn->ib_conn.device;
+
+	ib_dma_sync_single_for_cpu(device->ib_device,
+		tx_desc->dma_addr, ISER_HEADERS_LEN, DMA_TO_DEVICE);
+
+	memset(&tx_desc->iser_header, 0, sizeof(struct iser_ctrl));
+	tx_desc->iser_header.flags = ISER_VER;
+	tx_desc->num_sge = 1;
+}
+
+static void iser_free_login_buf(struct iser_conn *iser_conn)
+{
+	struct iser_device *device = iser_conn->ib_conn.device;
+	struct iser_login_desc *desc = &iser_conn->login_desc;
+
+	if (!desc->req)
+		return;
+
+	ib_dma_unmap_single(device->ib_device, desc->req_dma,
+			    ISCSI_DEF_MAX_RECV_SEG_LEN, DMA_TO_DEVICE);
+
+	ib_dma_unmap_single(device->ib_device, desc->rsp_dma,
+			    ISER_RX_LOGIN_SIZE, DMA_FROM_DEVICE);
+
+	kfree(desc->req);
+	kfree(desc->rsp);
+
+	/* make sure we never redo any unmapping */
+	desc->req = NULL;
+	desc->rsp = NULL;
+}
+
+static int iser_alloc_login_buf(struct iser_conn *iser_conn)
+{
+	struct iser_device *device = iser_conn->ib_conn.device;
+	struct iser_login_desc *desc = &iser_conn->login_desc;
+
+	desc->req = kmalloc(ISCSI_DEF_MAX_RECV_SEG_LEN, GFP_KERNEL);
+	if (!desc->req)
+		return -ENOMEM;
+
+	desc->req_dma = ib_dma_map_single(device->ib_device, desc->req,
+					  ISCSI_DEF_MAX_RECV_SEG_LEN,
+					  DMA_TO_DEVICE);
+	if (ib_dma_mapping_error(device->ib_device,
+				desc->req_dma))
+		goto free_req;
+
+	desc->rsp = kmalloc(ISER_RX_LOGIN_SIZE, GFP_KERNEL);
+	if (!desc->rsp)
+		goto unmap_req;
+
+	desc->rsp_dma = ib_dma_map_single(device->ib_device, desc->rsp,
+					   ISER_RX_LOGIN_SIZE,
+					   DMA_FROM_DEVICE);
+	if (ib_dma_mapping_error(device->ib_device,
+				desc->rsp_dma))
+		goto free_rsp;
+
+	return 0;
+
+free_rsp:
+	kfree(desc->rsp);
+unmap_req:
+	ib_dma_unmap_single(device->ib_device, desc->req_dma,
+			    ISCSI_DEF_MAX_RECV_SEG_LEN,
+			    DMA_TO_DEVICE);
+free_req:
+	kfree(desc->req);
+
+	return -ENOMEM;
+}
+
+int iser_alloc_rx_descriptors(struct iser_conn *iser_conn,
+			      struct iscsi_session *session)
+{
+	int i, j;
+	u64 dma_addr;
+	struct iser_rx_desc *rx_desc;
+	struct ib_sge       *rx_sg;
+	struct ib_conn *ib_conn = &iser_conn->ib_conn;
+	struct iser_device *device = ib_conn->device;
+
+	iser_conn->qp_max_recv_dtos = session->cmds_max;
+
+	if (iser_alloc_fastreg_pool(ib_conn, session->scsi_cmds_max,
+				    iser_conn->pages_per_mr))
+		goto create_rdma_reg_res_failed;
+
+	if (iser_alloc_login_buf(iser_conn))
+		goto alloc_login_buf_fail;
+
+	iser_conn->num_rx_descs = session->cmds_max;
+	iser_conn->rx_descs = kmalloc_array(iser_conn->num_rx_descs,
+					    sizeof(struct iser_rx_desc),
+					    GFP_KERNEL);
+	if (!iser_conn->rx_descs)
+		goto rx_desc_alloc_fail;
+
+	rx_desc = iser_conn->rx_descs;
+
+	for (i = 0; i < iser_conn->qp_max_recv_dtos; i++, rx_desc++)  {
+		dma_addr = ib_dma_map_single(device->ib_device, (void *)rx_desc,
+					ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE);
+		if (ib_dma_mapping_error(device->ib_device, dma_addr))
+			goto rx_desc_dma_map_failed;
+
+		rx_desc->dma_addr = dma_addr;
+		rx_desc->cqe.done = iser_task_rsp;
+		rx_sg = &rx_desc->rx_sg;
+		rx_sg->addr = rx_desc->dma_addr;
+		rx_sg->length = ISER_RX_PAYLOAD_SIZE;
+		rx_sg->lkey = device->pd->local_dma_lkey;
+	}
+
+	return 0;
+
+rx_desc_dma_map_failed:
+	rx_desc = iser_conn->rx_descs;
+	for (j = 0; j < i; j++, rx_desc++)
+		ib_dma_unmap_single(device->ib_device, rx_desc->dma_addr,
+				    ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE);
+	kfree(iser_conn->rx_descs);
+	iser_conn->rx_descs = NULL;
+rx_desc_alloc_fail:
+	iser_free_login_buf(iser_conn);
+alloc_login_buf_fail:
+	iser_free_fastreg_pool(ib_conn);
+create_rdma_reg_res_failed:
+	iser_err("failed allocating rx descriptors / data buffers\n");
+	return -ENOMEM;
+}
+
+void iser_free_rx_descriptors(struct iser_conn *iser_conn)
+{
+	int i;
+	struct iser_rx_desc *rx_desc;
+	struct ib_conn *ib_conn = &iser_conn->ib_conn;
+	struct iser_device *device = ib_conn->device;
+
+	iser_free_fastreg_pool(ib_conn);
+
+	rx_desc = iser_conn->rx_descs;
+	for (i = 0; i < iser_conn->qp_max_recv_dtos; i++, rx_desc++)
+		ib_dma_unmap_single(device->ib_device, rx_desc->dma_addr,
+				    ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE);
+	kfree(iser_conn->rx_descs);
+	/* make sure we never redo any unmapping */
+	iser_conn->rx_descs = NULL;
+
+	iser_free_login_buf(iser_conn);
+}
+
+static int iser_post_rx_bufs(struct iscsi_conn *conn, struct iscsi_hdr *req)
+{
+	struct iser_conn *iser_conn = conn->dd_data;
+	struct iscsi_session *session = conn->session;
+	int err = 0;
+	int i;
+
+	iser_dbg("req op %x flags %x\n", req->opcode, req->flags);
+	/* check if this is the last login - going to full feature phase */
+	if ((req->flags & ISCSI_FULL_FEATURE_PHASE) != ISCSI_FULL_FEATURE_PHASE)
+		goto out;
+
+	if (session->discovery_sess) {
+		iser_info("Discovery session, re-using login RX buffer\n");
+		goto out;
+	}
+
+	iser_info("Normal session, posting batch of RX %d buffers\n",
+		  iser_conn->qp_max_recv_dtos - 1);
+
+	/*
+	 * Initial post receive buffers.
+	 * There is one already posted recv buffer (for the last login
+	 * response). Therefore, the first recv buffer is skipped here.
+	 */
+	for (i = 1; i < iser_conn->qp_max_recv_dtos; i++) {
+		err = iser_post_recvm(iser_conn, &iser_conn->rx_descs[i]);
+		if (err)
+			goto out;
+	}
+out:
+	return err;
+}
+
+/**
+ * iser_send_command - send command PDU
+ * @conn: link to matching iscsi connection
+ * @task: SCSI command task
+ */
+int iser_send_command(struct iscsi_conn *conn, struct iscsi_task *task)
+{
+	struct iser_conn *iser_conn = conn->dd_data;
+	struct iscsi_iser_task *iser_task = task->dd_data;
+	unsigned long edtl;
+	int err;
+	struct iser_data_buf *data_buf, *prot_buf;
+	struct iscsi_scsi_req *hdr = (struct iscsi_scsi_req *)task->hdr;
+	struct scsi_cmnd *sc  =  task->sc;
+	struct iser_tx_desc *tx_desc = &iser_task->desc;
+
+	edtl = ntohl(hdr->data_length);
+
+	/* build the tx desc regd header and add it to the tx desc dto */
+	tx_desc->type = ISCSI_TX_SCSI_COMMAND;
+	tx_desc->cqe.done = iser_cmd_comp;
+	iser_create_send_desc(iser_conn, tx_desc);
+
+	if (hdr->flags & ISCSI_FLAG_CMD_READ) {
+		data_buf = &iser_task->data[ISER_DIR_IN];
+		prot_buf = &iser_task->prot[ISER_DIR_IN];
+	} else {
+		data_buf = &iser_task->data[ISER_DIR_OUT];
+		prot_buf = &iser_task->prot[ISER_DIR_OUT];
+	}
+
+	if (scsi_sg_count(sc)) { /* using a scatter list */
+		data_buf->sg = scsi_sglist(sc);
+		data_buf->size = scsi_sg_count(sc);
+	}
+	data_buf->data_len = scsi_bufflen(sc);
+
+	if (scsi_prot_sg_count(sc)) {
+		prot_buf->sg  = scsi_prot_sglist(sc);
+		prot_buf->size = scsi_prot_sg_count(sc);
+		prot_buf->data_len = (data_buf->data_len >>
+				     ilog2(sc->device->sector_size)) * 8;
+	}
+
+	if (hdr->flags & ISCSI_FLAG_CMD_READ) {
+		err = iser_prepare_read_cmd(task);
+		if (err)
+			goto send_command_error;
+	}
+	if (hdr->flags & ISCSI_FLAG_CMD_WRITE) {
+		err = iser_prepare_write_cmd(task,
+					     task->imm_count,
+				             task->imm_count +
+					     task->unsol_r2t.data_length,
+					     edtl);
+		if (err)
+			goto send_command_error;
+	}
+
+	iser_task->status = ISER_TASK_STATUS_STARTED;
+
+	err = iser_post_send(&iser_conn->ib_conn, tx_desc);
+	if (!err)
+		return 0;
+
+send_command_error:
+	iser_err("conn %p failed task->itt %d err %d\n",conn, task->itt, err);
+	return err;
+}
+
+/**
+ * iser_send_data_out - send data out PDU
+ * @conn: link to matching iscsi connection
+ * @task: SCSI command task
+ * @hdr: pointer to the LLD's iSCSI message header
+ */
+int iser_send_data_out(struct iscsi_conn *conn, struct iscsi_task *task,
+		       struct iscsi_data *hdr)
+{
+	struct iser_conn *iser_conn = conn->dd_data;
+	struct iscsi_iser_task *iser_task = task->dd_data;
+	struct iser_tx_desc *tx_desc;
+	struct iser_mem_reg *mem_reg;
+	unsigned long buf_offset;
+	unsigned long data_seg_len;
+	uint32_t itt;
+	int err;
+	struct ib_sge *tx_dsg;
+
+	itt = (__force uint32_t)hdr->itt;
+	data_seg_len = ntoh24(hdr->dlength);
+	buf_offset   = ntohl(hdr->offset);
+
+	iser_dbg("%s itt %d dseg_len %d offset %d\n",
+		 __func__,(int)itt,(int)data_seg_len,(int)buf_offset);
+
+	tx_desc = kmem_cache_zalloc(ig.desc_cache, GFP_ATOMIC);
+	if (!tx_desc)
+		return -ENOMEM;
+
+	tx_desc->type = ISCSI_TX_DATAOUT;
+	tx_desc->cqe.done = iser_dataout_comp;
+	tx_desc->iser_header.flags = ISER_VER;
+	memcpy(&tx_desc->iscsi_header, hdr, sizeof(struct iscsi_hdr));
+
+	/* build the tx desc */
+	err = iser_initialize_task_headers(task, tx_desc);
+	if (err)
+		goto send_data_out_error;
+
+	mem_reg = &iser_task->rdma_reg[ISER_DIR_OUT];
+	tx_dsg = &tx_desc->tx_sg[1];
+	tx_dsg->addr = mem_reg->sge.addr + buf_offset;
+	tx_dsg->length = data_seg_len;
+	tx_dsg->lkey = mem_reg->sge.lkey;
+	tx_desc->num_sge = 2;
+
+	if (buf_offset + data_seg_len > iser_task->data[ISER_DIR_OUT].data_len) {
+		iser_err("Offset:%ld & DSL:%ld in Data-Out inconsistent with total len:%ld, itt:%d\n",
+			 buf_offset, data_seg_len,
+			 iser_task->data[ISER_DIR_OUT].data_len, itt);
+		err = -EINVAL;
+		goto send_data_out_error;
+	}
+	iser_dbg("data-out itt: %d, offset: %ld, sz: %ld\n",
+		 itt, buf_offset, data_seg_len);
+
+
+	err = iser_post_send(&iser_conn->ib_conn, tx_desc);
+	if (!err)
+		return 0;
+
+send_data_out_error:
+	kmem_cache_free(ig.desc_cache, tx_desc);
+	iser_err("conn %p failed err %d\n", conn, err);
+	return err;
+}
+
+int iser_send_control(struct iscsi_conn *conn, struct iscsi_task *task)
+{
+	struct iser_conn *iser_conn = conn->dd_data;
+	struct iscsi_iser_task *iser_task = task->dd_data;
+	struct iser_tx_desc *mdesc = &iser_task->desc;
+	unsigned long data_seg_len;
+	int err = 0;
+	struct iser_device *device;
+
+	/* build the tx desc regd header and add it to the tx desc dto */
+	mdesc->type = ISCSI_TX_CONTROL;
+	mdesc->cqe.done = iser_ctrl_comp;
+	iser_create_send_desc(iser_conn, mdesc);
+
+	device = iser_conn->ib_conn.device;
+
+	data_seg_len = ntoh24(task->hdr->dlength);
+
+	if (data_seg_len > 0) {
+		struct iser_login_desc *desc = &iser_conn->login_desc;
+		struct ib_sge *tx_dsg = &mdesc->tx_sg[1];
+
+		if (task != conn->login_task) {
+			iser_err("data present on non login task!!!\n");
+			goto send_control_error;
+		}
+
+		ib_dma_sync_single_for_cpu(device->ib_device, desc->req_dma,
+					   task->data_count, DMA_TO_DEVICE);
+
+		memcpy(desc->req, task->data, task->data_count);
+
+		ib_dma_sync_single_for_device(device->ib_device, desc->req_dma,
+					      task->data_count, DMA_TO_DEVICE);
+
+		tx_dsg->addr = desc->req_dma;
+		tx_dsg->length = task->data_count;
+		tx_dsg->lkey = device->pd->local_dma_lkey;
+		mdesc->num_sge = 2;
+	}
+
+	if (task == conn->login_task) {
+		iser_dbg("op %x dsl %lx, posting login rx buffer\n",
+			 task->hdr->opcode, data_seg_len);
+		err = iser_post_recvl(iser_conn);
+		if (err)
+			goto send_control_error;
+		err = iser_post_rx_bufs(conn, task->hdr);
+		if (err)
+			goto send_control_error;
+	}
+
+	err = iser_post_send(&iser_conn->ib_conn, mdesc);
+	if (!err)
+		return 0;
+
+send_control_error:
+	iser_err("conn %p failed err %d\n",conn, err);
+	return err;
+}
+
+void iser_login_rsp(struct ib_cq *cq, struct ib_wc *wc)
+{
+	struct ib_conn *ib_conn = wc->qp->qp_context;
+	struct iser_conn *iser_conn = to_iser_conn(ib_conn);
+	struct iser_login_desc *desc = iser_login(wc->wr_cqe);
+	struct iscsi_hdr *hdr;
+	char *data;
+	int length;
+	bool full_feature_phase;
+
+	if (unlikely(wc->status != IB_WC_SUCCESS)) {
+		iser_err_comp(wc, "login_rsp");
+		return;
+	}
+
+	ib_dma_sync_single_for_cpu(ib_conn->device->ib_device,
+				   desc->rsp_dma, ISER_RX_LOGIN_SIZE,
+				   DMA_FROM_DEVICE);
+
+	hdr = desc->rsp + sizeof(struct iser_ctrl);
+	data = desc->rsp + ISER_HEADERS_LEN;
+	length = wc->byte_len - ISER_HEADERS_LEN;
+	full_feature_phase = ((hdr->flags & ISCSI_FULL_FEATURE_PHASE) ==
+			      ISCSI_FULL_FEATURE_PHASE) &&
+			     (hdr->flags & ISCSI_FLAG_CMD_FINAL);
+
+	iser_dbg("op 0x%x itt 0x%x dlen %d\n", hdr->opcode,
+		 hdr->itt, length);
+
+	iscsi_iser_recv(iser_conn->iscsi_conn, hdr, data, length);
+
+	ib_dma_sync_single_for_device(ib_conn->device->ib_device,
+				      desc->rsp_dma, ISER_RX_LOGIN_SIZE,
+				      DMA_FROM_DEVICE);
+
+	if (!full_feature_phase ||
+	    iser_conn->iscsi_conn->session->discovery_sess)
+		return;
+
+	/* Post the first RX buffer that is skipped in iser_post_rx_bufs() */
+	iser_post_recvm(iser_conn, iser_conn->rx_descs);
+}
+
+static inline int iser_inv_desc(struct iser_fr_desc *desc, u32 rkey)
+{
+	if (unlikely((!desc->sig_protected && rkey != desc->rsc.mr->rkey) ||
+		     (desc->sig_protected && rkey != desc->rsc.sig_mr->rkey))) {
+		iser_err("Bogus remote invalidation for rkey %#x\n", rkey);
+		return -EINVAL;
+	}
+
+	desc->rsc.mr_valid = 0;
+
+	return 0;
+}
+
+static int iser_check_remote_inv(struct iser_conn *iser_conn, struct ib_wc *wc,
+				 struct iscsi_hdr *hdr)
+{
+	if (wc->wc_flags & IB_WC_WITH_INVALIDATE) {
+		struct iscsi_task *task;
+		u32 rkey = wc->ex.invalidate_rkey;
+
+		iser_dbg("conn %p: remote invalidation for rkey %#x\n",
+			 iser_conn, rkey);
+
+		if (unlikely(!iser_conn->snd_w_inv)) {
+			iser_err("conn %p: unexpected remote invalidation, terminating connection\n",
+				 iser_conn);
+			return -EPROTO;
+		}
+
+		task = iscsi_itt_to_ctask(iser_conn->iscsi_conn, hdr->itt);
+		if (likely(task)) {
+			struct iscsi_iser_task *iser_task = task->dd_data;
+			struct iser_fr_desc *desc;
+
+			if (iser_task->dir[ISER_DIR_IN]) {
+				desc = iser_task->rdma_reg[ISER_DIR_IN].desc;
+				if (unlikely(iser_inv_desc(desc, rkey)))
+					return -EINVAL;
+			}
+
+			if (iser_task->dir[ISER_DIR_OUT]) {
+				desc = iser_task->rdma_reg[ISER_DIR_OUT].desc;
+				if (unlikely(iser_inv_desc(desc, rkey)))
+					return -EINVAL;
+			}
+		} else {
+			iser_err("failed to get task for itt=%d\n", hdr->itt);
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+
+void iser_task_rsp(struct ib_cq *cq, struct ib_wc *wc)
+{
+	struct ib_conn *ib_conn = wc->qp->qp_context;
+	struct iser_conn *iser_conn = to_iser_conn(ib_conn);
+	struct iser_rx_desc *desc = iser_rx(wc->wr_cqe);
+	struct iscsi_hdr *hdr;
+	int length, err;
+
+	if (unlikely(wc->status != IB_WC_SUCCESS)) {
+		iser_err_comp(wc, "task_rsp");
+		return;
+	}
+
+	ib_dma_sync_single_for_cpu(ib_conn->device->ib_device,
+				   desc->dma_addr, ISER_RX_PAYLOAD_SIZE,
+				   DMA_FROM_DEVICE);
+
+	hdr = &desc->iscsi_header;
+	length = wc->byte_len - ISER_HEADERS_LEN;
+
+	iser_dbg("op 0x%x itt 0x%x dlen %d\n", hdr->opcode,
+		 hdr->itt, length);
+
+	if (iser_check_remote_inv(iser_conn, wc, hdr)) {
+		iscsi_conn_failure(iser_conn->iscsi_conn,
+				   ISCSI_ERR_CONN_FAILED);
+		return;
+	}
+
+	iscsi_iser_recv(iser_conn->iscsi_conn, hdr, desc->data, length);
+
+	ib_dma_sync_single_for_device(ib_conn->device->ib_device,
+				      desc->dma_addr, ISER_RX_PAYLOAD_SIZE,
+				      DMA_FROM_DEVICE);
+
+	err = iser_post_recvm(iser_conn, desc);
+	if (err)
+		iser_err("posting rx buffer err %d\n", err);
+}
+
+void iser_cmd_comp(struct ib_cq *cq, struct ib_wc *wc)
+{
+	if (unlikely(wc->status != IB_WC_SUCCESS))
+		iser_err_comp(wc, "command");
+}
+
+void iser_ctrl_comp(struct ib_cq *cq, struct ib_wc *wc)
+{
+	struct iser_tx_desc *desc = iser_tx(wc->wr_cqe);
+	struct iscsi_task *task;
+
+	if (unlikely(wc->status != IB_WC_SUCCESS)) {
+		iser_err_comp(wc, "control");
+		return;
+	}
+
+	/* this arithmetic is legal by libiscsi dd_data allocation */
+	task = (void *)desc - sizeof(struct iscsi_task);
+	if (task->hdr->itt == RESERVED_ITT)
+		iscsi_put_task(task);
+}
+
+void iser_dataout_comp(struct ib_cq *cq, struct ib_wc *wc)
+{
+	struct iser_tx_desc *desc = iser_tx(wc->wr_cqe);
+	struct ib_conn *ib_conn = wc->qp->qp_context;
+	struct iser_device *device = ib_conn->device;
+
+	if (unlikely(wc->status != IB_WC_SUCCESS))
+		iser_err_comp(wc, "dataout");
+
+	ib_dma_unmap_single(device->ib_device, desc->dma_addr,
+			    ISER_HEADERS_LEN, DMA_TO_DEVICE);
+	kmem_cache_free(ig.desc_cache, desc);
+}
+
+void iser_task_rdma_init(struct iscsi_iser_task *iser_task)
+
+{
+	iser_task->status = ISER_TASK_STATUS_INIT;
+
+	iser_task->dir[ISER_DIR_IN] = 0;
+	iser_task->dir[ISER_DIR_OUT] = 0;
+
+	iser_task->data[ISER_DIR_IN].data_len  = 0;
+	iser_task->data[ISER_DIR_OUT].data_len = 0;
+
+	iser_task->prot[ISER_DIR_IN].data_len  = 0;
+	iser_task->prot[ISER_DIR_OUT].data_len = 0;
+
+	iser_task->prot[ISER_DIR_IN].dma_nents = 0;
+	iser_task->prot[ISER_DIR_OUT].dma_nents = 0;
+
+	memset(&iser_task->rdma_reg[ISER_DIR_IN], 0,
+	       sizeof(struct iser_mem_reg));
+	memset(&iser_task->rdma_reg[ISER_DIR_OUT], 0,
+	       sizeof(struct iser_mem_reg));
+}
+
+void iser_task_rdma_finalize(struct iscsi_iser_task *iser_task)
+{
+
+	if (iser_task->dir[ISER_DIR_IN]) {
+		iser_unreg_mem_fastreg(iser_task, ISER_DIR_IN);
+		iser_dma_unmap_task_data(iser_task, ISER_DIR_IN,
+					 DMA_FROM_DEVICE);
+	}
+
+	if (iser_task->dir[ISER_DIR_OUT]) {
+		iser_unreg_mem_fastreg(iser_task, ISER_DIR_OUT);
+		iser_dma_unmap_task_data(iser_task, ISER_DIR_OUT,
+					 DMA_TO_DEVICE);
+	}
+}