new file mode 100644
@@ -0,0 +1,2184 @@
+/*
+ * Software iWARP device driver
+ *
+ * Authors: Bernard Metzler <bmt@zurich.ibm.com>
+ * Fredy Neeser <nfd@zurich.ibm.com>
+ * Greg Joyce <greg@opengridcomputing.com>
+ *
+ * Copyright (c) 2008-2017, IBM Corporation
+ * Copyright (c) 2017, Open Grid Computing, Inc.
+ *
+ * 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 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 IBM nor the names of its contributors may be
+ * used to endorse or promote products derived from this software without
+ * specific prior written permission.
+ *
+ * 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/errno.h>
+#include <linux/types.h>
+#include <linux/net.h>
+#include <linux/inetdevice.h>
+#include <linux/workqueue.h>
+#include <net/sock.h>
+#include <net/tcp.h>
+#include <linux/tcp.h>
+
+#include <rdma/iw_cm.h>
+#include <rdma/ib_verbs.h>
+#include <rdma/ib_smi.h>
+#include <rdma/ib_user_verbs.h>
+
+#include "siw.h"
+#include "siw_cm.h"
+#include "siw_obj.h"
+
+/*
+ * Set to any combination of
+ * MPA_V2_RDMA_NO_RTR, MPA_V2_RDMA_READ_RTR, MPA_V2_RDMA_WRITE_RTR
+ */
+static __be16 rtr_type = MPA_V2_RDMA_READ_RTR|MPA_V2_RDMA_WRITE_RTR;
+static const bool relaxed_ird_negotiation = 1;
+
+/*
+ * siw_sock_nodelay() - Disable Nagle algorithm and/or set pingpong
+ */
+static int siw_sock_nodelay(struct socket *sock)
+{
+ int val = 1, rv = 0;
+
+ if (siw_lowdelay)
+ rv = kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY,
+ (char *)&val, sizeof(val));
+
+ if (!rv && tcp_quickack)
+ rv = kernel_setsockopt(sock, SOL_TCP, TCP_QUICKACK,
+ (char *)&val, sizeof(val));
+ return rv;
+}
+
+static void siw_cm_llp_state_change(struct sock *s);
+static void siw_cm_llp_data_ready(struct sock *s);
+static void siw_cm_llp_write_space(struct sock *s);
+static void siw_cm_llp_error_report(struct sock *s);
+static int siw_cm_upcall(struct siw_cep *cep, enum iw_cm_event_type reson,
+ int status);
+
+static void siw_sk_assign_cm_upcalls(struct sock *sk)
+{
+ write_lock_bh(&sk->sk_callback_lock);
+ sk->sk_state_change = siw_cm_llp_state_change;
+ sk->sk_data_ready = siw_cm_llp_data_ready;
+ sk->sk_write_space = siw_cm_llp_write_space;
+ sk->sk_error_report = siw_cm_llp_error_report;
+ write_unlock_bh(&sk->sk_callback_lock);
+}
+
+static void siw_sk_save_upcalls(struct sock *sk)
+{
+ struct siw_cep *cep = sk_to_cep(sk);
+
+ write_lock_bh(&sk->sk_callback_lock);
+ cep->sk_state_change = sk->sk_state_change;
+ cep->sk_data_ready = sk->sk_data_ready;
+ cep->sk_write_space = sk->sk_write_space;
+ cep->sk_error_report = sk->sk_error_report;
+ write_unlock_bh(&sk->sk_callback_lock);
+}
+
+static void siw_sk_restore_upcalls(struct sock *sk, struct siw_cep *cep)
+{
+ sk->sk_state_change = cep->sk_state_change;
+ sk->sk_data_ready = cep->sk_data_ready;
+ sk->sk_write_space = cep->sk_write_space;
+ sk->sk_error_report = cep->sk_error_report;
+ sk->sk_user_data = NULL;
+}
+
+static void siw_qp_socket_assoc(struct siw_cep *cep, struct siw_qp *qp)
+{
+ struct socket *s = cep->llp.sock;
+ struct sock *sk = s->sk;
+
+ write_lock_bh(&sk->sk_callback_lock);
+
+ qp->attrs.llp_stream_handle = s;
+ sk->sk_data_ready = siw_qp_llp_data_ready;
+ sk->sk_write_space = siw_qp_llp_write_space;
+
+ write_unlock_bh(&sk->sk_callback_lock);
+}
+
+static void siw_socket_disassoc(struct socket *s)
+{
+ struct sock *sk = s->sk;
+ struct siw_cep *cep;
+
+ if (sk) {
+ write_lock_bh(&sk->sk_callback_lock);
+ cep = sk_to_cep(sk);
+ if (cep) {
+ siw_sk_restore_upcalls(sk, cep);
+ siw_cep_put(cep);
+ } else
+ pr_warn("SIW: cannot restore sk callbacks: no ep\n");
+ write_unlock_bh(&sk->sk_callback_lock);
+ } else {
+ pr_warn("SIW: cannot restore sk callbacks: no sk\n");
+ }
+}
+
+static void siw_rtr_data_ready(struct sock *sk)
+{
+ struct siw_cep *cep;
+ struct siw_qp *qp = NULL;
+ read_descriptor_t rd_desc;
+
+ read_lock(&sk->sk_callback_lock);
+
+ cep = sk_to_cep(sk);
+ if (!cep) {
+ WARN(1, "No connection endpoint\n");
+ goto out;
+ }
+ qp = sk_to_qp(sk);
+
+ memset(&rd_desc, 0, sizeof(rd_desc));
+ rd_desc.arg.data = qp;
+ rd_desc.count = 1;
+
+ tcp_read_sock(sk, &rd_desc, siw_tcp_rx_data);
+ /*
+ * Check if first frame was successfully processed.
+ * Signal connection full establishment if yes.
+ * Failed data processing would have already scheduled
+ * connection drop.
+ */
+ if (!qp->rx_ctx.rx_suspend)
+ siw_cm_upcall(cep, IW_CM_EVENT_ESTABLISHED, 0);
+out:
+ read_unlock(&sk->sk_callback_lock);
+ if (qp)
+ siw_qp_socket_assoc(cep, qp);
+}
+
+static void siw_sk_assign_rtr_upcalls(struct siw_cep *cep)
+{
+ struct sock *sk = cep->llp.sock->sk;
+
+ write_lock_bh(&sk->sk_callback_lock);
+ sk->sk_data_ready = siw_rtr_data_ready;
+ sk->sk_write_space = siw_qp_llp_write_space;
+ write_unlock_bh(&sk->sk_callback_lock);
+}
+
+static inline int kernel_peername(struct socket *s, struct sockaddr_in *addr)
+{
+ int addr_len;
+
+ return s->ops->getname(s, (struct sockaddr *)addr, &addr_len, 1);
+}
+
+static inline int kernel_localname(struct socket *s, struct sockaddr_in *addr)
+{
+ int addr_len;
+
+ return s->ops->getname(s, (struct sockaddr *)addr, &addr_len, 0);
+}
+
+static void siw_cep_socket_assoc(struct siw_cep *cep, struct socket *s)
+{
+ cep->llp.sock = s;
+ siw_cep_get(cep);
+ s->sk->sk_user_data = cep;
+
+ siw_sk_save_upcalls(s->sk);
+ siw_sk_assign_cm_upcalls(s->sk);
+}
+
+static struct siw_cep *siw_cep_alloc(struct siw_device *sdev)
+{
+ struct siw_cep *cep = kzalloc(sizeof(*cep), GFP_KERNEL);
+
+ if (cep) {
+ unsigned long flags;
+
+ INIT_LIST_HEAD(&cep->listenq);
+ INIT_LIST_HEAD(&cep->devq);
+ INIT_LIST_HEAD(&cep->work_freelist);
+
+ kref_init(&cep->ref);
+ cep->state = SIW_EPSTATE_IDLE;
+ init_waitqueue_head(&cep->waitq);
+ spin_lock_init(&cep->lock);
+ cep->sdev = sdev;
+ cep->enhanced_rdma_conn_est = false;
+
+ spin_lock_irqsave(&sdev->idr_lock, flags);
+ list_add_tail(&cep->devq, &sdev->cep_list);
+ spin_unlock_irqrestore(&sdev->idr_lock, flags);
+ atomic_inc(&sdev->num_cep);
+
+ siw_dbg_cep(cep, "new object\n");
+ }
+ return cep;
+}
+
+static void siw_cm_free_work(struct siw_cep *cep)
+{
+ struct list_head *w, *tmp;
+ struct siw_cm_work *work;
+
+ list_for_each_safe(w, tmp, &cep->work_freelist) {
+ work = list_entry(w, struct siw_cm_work, list);
+ list_del(&work->list);
+ kfree(work);
+ }
+}
+
+static void siw_cancel_mpatimer(struct siw_cep *cep)
+{
+ spin_lock_bh(&cep->lock);
+ if (cep->mpa_timer) {
+ if (cancel_delayed_work(&cep->mpa_timer->work)) {
+ siw_cep_put(cep);
+ kfree(cep->mpa_timer); /* not needed again */
+ }
+ cep->mpa_timer = NULL;
+ }
+ spin_unlock_bh(&cep->lock);
+}
+
+static void siw_put_work(struct siw_cm_work *work)
+{
+ INIT_LIST_HEAD(&work->list);
+ spin_lock_bh(&work->cep->lock);
+ list_add(&work->list, &work->cep->work_freelist);
+ spin_unlock_bh(&work->cep->lock);
+}
+
+static void siw_cep_set_inuse(struct siw_cep *cep)
+{
+ unsigned long flags;
+ int rv;
+retry:
+ siw_dbg_cep(cep, "current in_use %d\n", cep->in_use);
+
+ spin_lock_irqsave(&cep->lock, flags);
+
+ if (cep->in_use) {
+ spin_unlock_irqrestore(&cep->lock, flags);
+ rv = wait_event_interruptible(cep->waitq, !cep->in_use);
+ if (signal_pending(current))
+ flush_signals(current);
+ goto retry;
+ } else {
+ cep->in_use = 1;
+ spin_unlock_irqrestore(&cep->lock, flags);
+ }
+}
+
+static void siw_cep_set_free(struct siw_cep *cep)
+{
+ unsigned long flags;
+
+ siw_dbg_cep(cep, "current in_use %d\n", cep->in_use);
+
+ spin_lock_irqsave(&cep->lock, flags);
+ cep->in_use = 0;
+ spin_unlock_irqrestore(&cep->lock, flags);
+
+ wake_up(&cep->waitq);
+}
+
+static void __siw_cep_dealloc(struct kref *ref)
+{
+ struct siw_cep *cep = container_of(ref, struct siw_cep, ref);
+ struct siw_device *sdev = cep->sdev;
+ unsigned long flags;
+
+ siw_dbg_cep(cep, "free object\n");
+
+ WARN_ON(cep->listen_cep);
+
+ /* kfree(NULL) is safe */
+ kfree(cep->mpa.pdata);
+ spin_lock_bh(&cep->lock);
+ if (!list_empty(&cep->work_freelist))
+ siw_cm_free_work(cep);
+ spin_unlock_bh(&cep->lock);
+
+ spin_lock_irqsave(&sdev->idr_lock, flags);
+ list_del(&cep->devq);
+ spin_unlock_irqrestore(&sdev->idr_lock, flags);
+ atomic_dec(&sdev->num_cep);
+ kfree(cep);
+}
+
+static struct siw_cm_work *siw_get_work(struct siw_cep *cep)
+{
+ struct siw_cm_work *work = NULL;
+
+ spin_lock_bh(&cep->lock);
+ if (!list_empty(&cep->work_freelist)) {
+ work = list_entry(cep->work_freelist.next, struct siw_cm_work,
+ list);
+ list_del_init(&work->list);
+ }
+ spin_unlock_bh(&cep->lock);
+ return work;
+}
+
+static int siw_cm_alloc_work(struct siw_cep *cep, int num)
+{
+ struct siw_cm_work *work;
+
+ while (num--) {
+ work = kmalloc(sizeof(*work), GFP_KERNEL);
+ if (!work) {
+ if (!(list_empty(&cep->work_freelist)))
+ siw_cm_free_work(cep);
+ return -ENOMEM;
+ }
+ work->cep = cep;
+ INIT_LIST_HEAD(&work->list);
+ list_add(&work->list, &cep->work_freelist);
+ }
+ return 0;
+}
+
+/*
+ * siw_cm_upcall()
+ *
+ * Upcall to IWCM to inform about async connection events
+ */
+static int siw_cm_upcall(struct siw_cep *cep, enum iw_cm_event_type reason,
+ int status)
+{
+ struct iw_cm_event event;
+ struct iw_cm_id *cm_id;
+
+ memset(&event, 0, sizeof(event));
+ event.status = status;
+ event.event = reason;
+
+ if (reason == IW_CM_EVENT_CONNECT_REQUEST) {
+ event.provider_data = cep;
+ cm_id = cep->listen_cep->cm_id;
+ } else {
+ cm_id = cep->cm_id;
+ }
+ /* Signal private data and address information */
+ if (reason == IW_CM_EVENT_CONNECT_REQUEST ||
+ reason == IW_CM_EVENT_CONNECT_REPLY) {
+ u16 pd_len = be16_to_cpu(cep->mpa.hdr.params.pd_len);
+
+ if (pd_len && cep->enhanced_rdma_conn_est)
+ pd_len -= sizeof(struct mpa_v2_data);
+
+ if (pd_len) {
+ /*
+ * hand over MPA private data
+ */
+ event.private_data_len = pd_len;
+ event.private_data = cep->mpa.pdata;
+ /* Hide MPA V2 IRD/ORD control */
+ if (cep->enhanced_rdma_conn_est)
+ event.private_data +=
+ sizeof(struct mpa_v2_data);
+ }
+ to_sockaddr_in(event.local_addr) = cep->llp.laddr;
+ to_sockaddr_in(event.remote_addr) = cep->llp.raddr;
+ }
+ /* Signal IRD and ORD */
+ if (reason == IW_CM_EVENT_ESTABLISHED ||
+ reason == IW_CM_EVENT_CONNECT_REPLY) {
+ /* Signal negotiated IRD/ORD values we will use */
+ event.ird = cep->ird;
+ event.ord = cep->ord;
+ } else if (reason == IW_CM_EVENT_CONNECT_REQUEST) {
+ event.ird = cep->ord;
+ event.ord = cep->ird;
+ }
+ siw_dbg_cep(cep, "[QP %d]: id 0x%p, reason=%d, status=%d\n",
+ cep->qp ? QP_ID(cep->qp) : -1, cm_id, reason, status);
+
+ return cm_id->event_handler(cm_id, &event);
+}
+
+/*
+ * siw_qp_cm_drop()
+ *
+ * Drops established LLP connection if present and not already
+ * scheduled for dropping. Called from user context, SQ workqueue
+ * or receive IRQ. Caller signals if socket can be immediately
+ * closed (basically, if not in IRQ).
+ */
+void siw_qp_cm_drop(struct siw_qp *qp, int schedule)
+{
+ struct siw_cep *cep = qp->cep;
+
+ qp->rx_ctx.rx_suspend = 1;
+ qp->tx_ctx.tx_suspend = 1;
+
+ if (!qp->cep)
+ return;
+
+ if (schedule) {
+ siw_cm_queue_work(cep, SIW_CM_WORK_CLOSE_LLP);
+ } else {
+ siw_cep_set_inuse(cep);
+
+ if (cep->state == SIW_EPSTATE_CLOSED) {
+ siw_dbg_cep(cep, "already closed\n");
+ goto out;
+ }
+ siw_dbg_cep(cep, "immediate close, state %d\n", cep->state);
+
+ if (qp->term_info.valid)
+ siw_send_terminate(qp);
+
+ if (cep->cm_id) {
+ switch (cep->state) {
+
+ case SIW_EPSTATE_AWAIT_MPAREP:
+ siw_cm_upcall(cep, IW_CM_EVENT_CONNECT_REPLY,
+ -EINVAL);
+ break;
+
+ case SIW_EPSTATE_RDMA_MODE:
+ siw_cm_upcall(cep, IW_CM_EVENT_CLOSE, 0);
+
+ break;
+
+ case SIW_EPSTATE_IDLE:
+ case SIW_EPSTATE_LISTENING:
+ case SIW_EPSTATE_CONNECTING:
+ case SIW_EPSTATE_AWAIT_MPAREQ:
+ case SIW_EPSTATE_RECVD_MPAREQ:
+ case SIW_EPSTATE_CLOSED:
+ default:
+
+ break;
+ }
+ cep->cm_id->rem_ref(cep->cm_id);
+ cep->cm_id = NULL;
+ siw_cep_put(cep);
+ }
+ cep->state = SIW_EPSTATE_CLOSED;
+
+ if (cep->llp.sock) {
+ siw_socket_disassoc(cep->llp.sock);
+ /*
+ * Immediately close socket
+ */
+ sock_release(cep->llp.sock);
+ cep->llp.sock = NULL;
+ }
+ if (cep->qp) {
+ cep->qp = NULL;
+ siw_qp_put(qp);
+ }
+out:
+ siw_cep_set_free(cep);
+ }
+}
+
+void siw_cep_put(struct siw_cep *cep)
+{
+ siw_dbg_cep(cep, "new refcount: %d\n", refcount_read(&cep->ref) - 1);
+
+ WARN_ON(refcount_read(&cep->ref) < 1);
+ kref_put(&cep->ref, __siw_cep_dealloc);
+}
+
+void siw_cep_get(struct siw_cep *cep)
+{
+ kref_get(&cep->ref);
+ siw_dbg_cep(cep, "new refcount: %d\n", refcount_read(&cep->ref));
+}
+
+static inline int ksock_recv(struct socket *sock, char *buf, size_t size,
+ int flags)
+{
+ struct kvec iov = {buf, size};
+ struct msghdr msg = {.msg_name = NULL, .msg_flags = flags};
+
+ return kernel_recvmsg(sock, &msg, &iov, 1, size, flags);
+}
+
+/*
+ * Expects params->pd_len in host byte order
+ */
+static int siw_send_mpareqrep(struct siw_cep *cep, const void *pdata,
+ u8 pd_len)
+{
+ struct socket *s = cep->llp.sock;
+ struct mpa_rr *rr = &cep->mpa.hdr;
+ struct kvec iov[3];
+ struct msghdr msg;
+ int rv;
+ int iovec_num = 0;
+ int mpa_len;
+
+ memset(&msg, 0, sizeof(msg));
+
+ iov[iovec_num].iov_base = rr;
+ iov[iovec_num].iov_len = sizeof(*rr);
+ mpa_len = sizeof(*rr);
+
+ if (cep->enhanced_rdma_conn_est) {
+ iovec_num++;
+ iov[iovec_num].iov_base = &cep->mpa.v2_ctrl;
+ iov[iovec_num].iov_len = sizeof(cep->mpa.v2_ctrl);
+ mpa_len += sizeof(cep->mpa.v2_ctrl);
+ }
+ if (pd_len) {
+ iovec_num++;
+ iov[iovec_num].iov_base = (char *)pdata;
+ iov[iovec_num].iov_len = pd_len;
+ mpa_len += pd_len;
+ }
+ if (cep->enhanced_rdma_conn_est)
+ pd_len += sizeof(cep->mpa.v2_ctrl);
+
+ rr->params.pd_len = cpu_to_be16(pd_len);
+
+ rv = kernel_sendmsg(s, &msg, iov, iovec_num + 1, mpa_len);
+
+ return rv < 0 ? rv : 0;
+}
+
+/*
+ * Receive MPA Request/Reply header.
+ *
+ * Returns 0 if complete MPA Request/Reply haeder including
+ * eventual private data was received. Returns -EAGAIN if
+ * header was partially received or negative error code otherwise.
+ *
+ * Context: May be called in process context only
+ */
+static int siw_recv_mpa_rr(struct siw_cep *cep)
+{
+ struct mpa_rr *hdr = &cep->mpa.hdr;
+ struct socket *s = cep->llp.sock;
+ u16 pd_len;
+ int rcvd, to_rcv;
+
+ if (cep->mpa.bytes_rcvd < sizeof(struct mpa_rr)) {
+
+ rcvd = ksock_recv(s, (char *)hdr + cep->mpa.bytes_rcvd,
+ sizeof(struct mpa_rr) -
+ cep->mpa.bytes_rcvd, 0);
+
+ if (rcvd <= 0)
+ return -ECONNABORTED;
+
+ cep->mpa.bytes_rcvd += rcvd;
+
+ if (cep->mpa.bytes_rcvd < sizeof(struct mpa_rr))
+ return -EAGAIN;
+
+ if (be16_to_cpu(hdr->params.pd_len) > MPA_MAX_PRIVDATA)
+ return -EPROTO;
+ }
+ pd_len = be16_to_cpu(hdr->params.pd_len);
+
+ /*
+ * At least the MPA Request/Reply header (frame not including
+ * private data) has been received.
+ * Receive (or continue receiving) any private data.
+ */
+ to_rcv = pd_len - (cep->mpa.bytes_rcvd - sizeof(struct mpa_rr));
+
+ if (!to_rcv) {
+ /*
+ * We must have hdr->params.pd_len == 0 and thus received a
+ * complete MPA Request/Reply frame.
+ * Check against peer protocol violation.
+ */
+ u32 word;
+
+ rcvd = ksock_recv(s, (char *)&word, sizeof(word), MSG_DONTWAIT);
+ if (rcvd == -EAGAIN)
+ return 0;
+
+ if (rcvd == 0) {
+ siw_dbg_cep(cep, "peer EOF\n");
+ return -EPIPE;
+ }
+ if (rcvd < 0) {
+ siw_dbg_cep(cep, "error: %d\n", rcvd);
+ return rcvd;
+ }
+ siw_dbg_cep(cep, "peer sent extra data: %d\n", rcvd);
+
+ return -EPROTO;
+ }
+
+ /*
+ * At this point, we must have hdr->params.pd_len != 0.
+ * A private data buffer gets allocated if hdr->params.pd_len != 0.
+ */
+ if (!cep->mpa.pdata) {
+ cep->mpa.pdata = kmalloc(pd_len + 4, GFP_KERNEL);
+ if (!cep->mpa.pdata)
+ return -ENOMEM;
+ }
+ rcvd = ksock_recv(s, cep->mpa.pdata + cep->mpa.bytes_rcvd
+ - sizeof(struct mpa_rr), to_rcv + 4, MSG_DONTWAIT);
+
+ if (rcvd < 0)
+ return rcvd;
+
+ if (rcvd > to_rcv)
+ return -EPROTO;
+
+ cep->mpa.bytes_rcvd += rcvd;
+
+ if (to_rcv == rcvd) {
+ siw_dbg_cep(cep, "%d bytes private data received\n", pd_len);
+ return 0;
+ }
+ return -EAGAIN;
+}
+
+/*
+ * siw_proc_mpareq()
+ *
+ * Read MPA Request from socket and signal new connection to IWCM
+ * if success. Caller must hold lock on corresponding listening CEP.
+ */
+static int siw_proc_mpareq(struct siw_cep *cep)
+{
+ struct mpa_rr *req;
+ int version, rv;
+ u16 pd_len;
+
+ rv = siw_recv_mpa_rr(cep);
+ if (rv)
+ return rv;
+
+ req = &cep->mpa.hdr;
+
+ version = __mpa_rr_revision(req->params.bits);
+ pd_len = be16_to_cpu(req->params.pd_len);
+
+ if (version > MPA_REVISION_2)
+ /* allow for 0, 1, and 2 only */
+ return -EPROTO;
+
+ if (memcmp(req->key, MPA_KEY_REQ, 16))
+ return -EPROTO;
+
+ /* Prepare for sending MPA reply */
+ memcpy(req->key, MPA_KEY_REP, 16);
+
+ if (version == MPA_REVISION_2 &&
+ (req->params.bits & MPA_RR_FLAG_ENHANCED)) {
+ /*
+ * MPA version 2 must signal IRD/ORD values and P2P mode
+ * in private data if header flag MPA_RR_FLAG_ENHANCED
+ * is set.
+ */
+ if (pd_len < sizeof(struct mpa_v2_data))
+ goto reject_conn;
+
+ cep->enhanced_rdma_conn_est = true;
+ }
+
+ /* MPA Markers: currently not supported. Marker TX to be added. */
+ if (req->params.bits & MPA_RR_FLAG_MARKERS)
+ goto reject_conn;
+
+ if (req->params.bits & MPA_RR_FLAG_CRC) {
+ /*
+ * RFC 5044, page 27: CRC MUST be used if peer requests it.
+ * siw specific: 'mpa_crc_strict' parameter to reject
+ * connection with CRC if local CRC off enforced by
+ * 'mpa_crc_strict' module parameter.
+ */
+ if (!mpa_crc_required && mpa_crc_strict)
+ goto reject_conn;
+
+ /* Enable CRC if requested by module parameter */
+ if (mpa_crc_required)
+ req->params.bits |= MPA_RR_FLAG_CRC;
+ }
+
+ if (cep->enhanced_rdma_conn_est) {
+ struct mpa_v2_data *v2 = (struct mpa_v2_data *)cep->mpa.pdata;
+
+ /*
+ * Peer requested ORD becomes requested local IRD,
+ * peer requested IRD becomes requested local ORD.
+ * IRD and ORD get limited by global maximum values.
+ */
+ cep->ord = ntohs(v2->ird) & MPA_IRD_ORD_MASK;
+ cep->ord = min(cep->ord, SIW_MAX_ORD_QP);
+ cep->ird = ntohs(v2->ord) & MPA_IRD_ORD_MASK;
+ cep->ird = min(cep->ird, SIW_MAX_IRD_QP);
+
+ /* May get overwritten by locally negotiated values */
+ cep->mpa.v2_ctrl.ird = htons(cep->ird);
+ cep->mpa.v2_ctrl.ord = htons(cep->ord);
+
+ /*
+ * Support for peer sent zero length Write or Read to
+ * let local side enter RTS. Writes are preferred.
+ * Sends would require pre-posting a Receive and are
+ * not supported.
+ * Propose zero length Write if none of Read and Write
+ * is indicated.
+ */
+ if (v2->ird & MPA_V2_PEER_TO_PEER) {
+ cep->mpa.v2_ctrl.ird |= MPA_V2_PEER_TO_PEER;
+
+ if (v2->ord & MPA_V2_RDMA_WRITE_RTR)
+ cep->mpa.v2_ctrl.ord |= MPA_V2_RDMA_WRITE_RTR;
+ else if (v2->ord & MPA_V2_RDMA_READ_RTR)
+ cep->mpa.v2_ctrl.ord |= MPA_V2_RDMA_READ_RTR;
+ else
+ cep->mpa.v2_ctrl.ord |= MPA_V2_RDMA_WRITE_RTR;
+ }
+ }
+
+ cep->state = SIW_EPSTATE_RECVD_MPAREQ;
+
+ /* Keep reference until IWCM accepts/rejects */
+ siw_cep_get(cep);
+ rv = siw_cm_upcall(cep, IW_CM_EVENT_CONNECT_REQUEST, 0);
+ if (rv)
+ siw_cep_put(cep);
+
+ return rv;
+
+reject_conn:
+ siw_dbg_cep(cep, "reject: crc %d:%d:%d, m %d:%d\n",
+ req->params.bits & MPA_RR_FLAG_CRC ? 1 : 0,
+ mpa_crc_required, mpa_crc_strict,
+ req->params.bits & MPA_RR_FLAG_MARKERS ? 1 : 0, 0);
+
+ req->params.bits &= ~MPA_RR_FLAG_MARKERS;
+ req->params.bits |= MPA_RR_FLAG_REJECT;
+
+ if (!mpa_crc_required && mpa_crc_strict)
+ req->params.bits &= ~MPA_RR_FLAG_CRC;
+
+ if (pd_len)
+ kfree(cep->mpa.pdata);
+
+ cep->mpa.pdata = NULL;
+
+ (void)siw_send_mpareqrep(cep, NULL, 0);
+
+ return -EOPNOTSUPP;
+}
+
+static int siw_proc_mpareply(struct siw_cep *cep)
+{
+ struct siw_qp_attrs qp_attrs;
+ enum siw_qp_attr_mask qp_attr_mask;
+ struct siw_qp *qp = cep->qp;
+ struct mpa_rr *rep;
+ int rv;
+ u16 rep_ord;
+ u16 rep_ird;
+ bool ird_insufficient = false;
+ enum mpa_v2_ctrl mpa_p2p_mode = MPA_V2_RDMA_NO_RTR;
+
+ rv = siw_recv_mpa_rr(cep);
+ if (rv != -EAGAIN)
+ siw_cancel_mpatimer(cep);
+ if (rv)
+ goto out_err;
+
+ rep = &cep->mpa.hdr;
+
+ if (__mpa_rr_revision(rep->params.bits) > MPA_REVISION_2) {
+ /* allow for 0, 1, and 2 only */
+ rv = -EPROTO;
+ goto out_err;
+ }
+ if (memcmp(rep->key, MPA_KEY_REP, 16)) {
+ siw_init_terminate(qp, TERM_ERROR_LAYER_LLP,
+ LLP_ETYPE_MPA,
+ LLP_ECODE_INVALID_REQ_RESP, 0);
+ siw_send_terminate(qp);
+ rv = -EPROTO;
+ goto out_err;
+ }
+ if (rep->params.bits & MPA_RR_FLAG_REJECT) {
+ siw_dbg_cep(cep, "got mpa reject\n");
+ (void)siw_cm_upcall(cep, IW_CM_EVENT_CONNECT_REPLY,
+ -ECONNRESET);
+
+ return -ECONNRESET;
+ }
+ if ((rep->params.bits & MPA_RR_FLAG_MARKERS)
+ || (mpa_crc_required && !(rep->params.bits & MPA_RR_FLAG_CRC))
+ || (mpa_crc_strict && !mpa_crc_required
+ && (rep->params.bits & MPA_RR_FLAG_CRC))) {
+
+ siw_dbg_cep(cep, "reply unsupp: crc %d:%d:%d, m %d:%d\n",
+ rep->params.bits & MPA_RR_FLAG_CRC ? 1 : 0,
+ mpa_crc_required, mpa_crc_strict,
+ rep->params.bits & MPA_RR_FLAG_MARKERS ? 1 : 0, 0);
+
+ (void)siw_cm_upcall(cep, IW_CM_EVENT_CONNECT_REPLY,
+ -ECONNREFUSED);
+ return -EINVAL;
+ }
+
+ if (cep->enhanced_rdma_conn_est) {
+ struct mpa_v2_data *v2;
+
+ if (__mpa_rr_revision(rep->params.bits) < MPA_REVISION_2 ||
+ !(rep->params.bits & MPA_RR_FLAG_ENHANCED)) {
+ /*
+ * Protocol failure: The responder MUST reply with
+ * MPA version 2 and MUST set MPA_RR_FLAG_ENHANCED.
+ */
+ siw_dbg_cep(cep, "mpa reply error: vers %d, enhcd %d\n",
+ __mpa_rr_revision(rep->params.bits),
+ rep->params.bits & MPA_RR_FLAG_ENHANCED ? 1:0);
+
+ (void)siw_cm_upcall(cep, IW_CM_EVENT_CONNECT_REPLY,
+ -ECONNRESET);
+ return -EINVAL;
+ }
+ v2 = (struct mpa_v2_data *)cep->mpa.pdata;
+ rep_ird = ntohs(v2->ird) & MPA_IRD_ORD_MASK;
+ rep_ord = ntohs(v2->ord) & MPA_IRD_ORD_MASK;
+
+ if (cep->ird < rep_ord &&
+ (relaxed_ird_negotiation == false ||
+ rep_ord > cep->sdev->attrs.max_ird)) {
+ siw_dbg_cep(cep, "ird %d, rep_ord %d, max_ord %d\n",
+ cep->ird, rep_ord,
+ cep->sdev->attrs.max_ord);
+ ird_insufficient = true;
+ }
+ if (cep->ord > rep_ird && relaxed_ird_negotiation == false) {
+ siw_dbg_cep(cep, "ord %d, rep_ird %d\n",
+ cep->ord, rep_ird);
+ ird_insufficient = true;
+ }
+ /*
+ * Always report negotiated peer values to user,
+ * even if IRD/ORD negotiation failed
+ */
+ cep->ird = rep_ord;
+ cep->ord = rep_ird;
+
+ if (ird_insufficient) {
+ /*
+ * If the initiator IRD is insuffient for the
+ * responder ORD, send a TERM.
+ */
+ siw_init_terminate(qp, TERM_ERROR_LAYER_LLP,
+ LLP_ETYPE_MPA,
+ LLP_ECODE_INSUFFICIENT_IRD, 0);
+ siw_send_terminate(qp);
+ rv = -ENOMEM;
+ goto out_err;
+ }
+
+ if (cep->mpa.v2_ctrl_req.ird & MPA_V2_PEER_TO_PEER)
+ mpa_p2p_mode = cep->mpa.v2_ctrl_req.ord &
+ (MPA_V2_RDMA_WRITE_RTR | MPA_V2_RDMA_READ_RTR);
+
+ /*
+ * Check if we requested P2P mode, and if peer agrees
+ */
+ if (mpa_p2p_mode != MPA_V2_RDMA_NO_RTR) {
+ if ((mpa_p2p_mode & v2->ord) == 0) {
+ /*
+ * We requested RTR mode(s), but the peer
+ * did not pick any mode we support.
+ */
+ siw_dbg_cep(cep,
+ "rtr mode: req %2x, got %2x\n",
+ mpa_p2p_mode,
+ v2->ord & (MPA_V2_RDMA_WRITE_RTR |
+ MPA_V2_RDMA_READ_RTR));
+
+ siw_init_terminate(qp, TERM_ERROR_LAYER_LLP,
+ LLP_ETYPE_MPA,
+ LLP_ECODE_NO_MATCHING_RTR,
+ 0);
+ siw_send_terminate(qp);
+ rv = -EPROTO;
+ goto out_err;
+ }
+ mpa_p2p_mode = v2->ord &
+ (MPA_V2_RDMA_WRITE_RTR | MPA_V2_RDMA_READ_RTR);
+ }
+ }
+
+ memset(&qp_attrs, 0, sizeof(qp_attrs));
+
+ if (rep->params.bits & MPA_RR_FLAG_CRC)
+ qp_attrs.flags = SIW_MPA_CRC;
+
+ qp_attrs.irq_size = cep->ird;
+ qp_attrs.orq_size = cep->ord;
+ qp_attrs.llp_stream_handle = cep->llp.sock;
+ qp_attrs.state = SIW_QP_STATE_RTS;
+
+ qp_attr_mask = SIW_QP_ATTR_STATE | SIW_QP_ATTR_LLP_HANDLE |
+ SIW_QP_ATTR_ORD | SIW_QP_ATTR_IRD | SIW_QP_ATTR_MPA;
+
+ /* Move socket RX/TX under QP control */
+ down_write(&qp->state_lock);
+ if (qp->attrs.state > SIW_QP_STATE_RTR) {
+ rv = -EINVAL;
+ up_write(&qp->state_lock);
+ goto out_err;
+ }
+ rv = siw_qp_modify(qp, &qp_attrs, qp_attr_mask);
+
+ siw_qp_socket_assoc(cep, qp);
+
+ up_write(&qp->state_lock);
+
+ /* Send extra RDMA frame to trigger peer RTS if negotiated */
+ if (mpa_p2p_mode != MPA_V2_RDMA_NO_RTR) {
+ rv = siw_qp_mpa_rts(qp, mpa_p2p_mode);
+ if (rv)
+ goto out_err;
+ }
+
+ if (!rv) {
+ rv = siw_cm_upcall(cep, IW_CM_EVENT_CONNECT_REPLY, 0);
+ if (!rv)
+ cep->state = SIW_EPSTATE_RDMA_MODE;
+
+ return 0;
+ }
+
+out_err:
+ (void)siw_cm_upcall(cep, IW_CM_EVENT_CONNECT_REPLY, -EINVAL);
+
+ return rv;
+}
+
+/*
+ * siw_accept_newconn - accept an incoming pending connection
+ *
+ */
+static void siw_accept_newconn(struct siw_cep *cep)
+{
+ struct socket *s = cep->llp.sock;
+ struct socket *new_s = NULL;
+ struct siw_cep *new_cep = NULL;
+ int rv = 0; /* debug only. should disappear */
+
+ if (cep->state != SIW_EPSTATE_LISTENING)
+ goto error;
+
+ new_cep = siw_cep_alloc(cep->sdev);
+ if (!new_cep)
+ goto error;
+
+ /*
+ * 4: Allocate a sufficient number of work elements
+ * to allow concurrent handling of local + peer close
+ * events, MPA header processing + MPA timeout.
+ */
+ if (siw_cm_alloc_work(new_cep, 4) != 0)
+ goto error;
+
+ /*
+ * Copy saved socket callbacks from listening CEP
+ * and assign new socket with new CEP
+ */
+ new_cep->sk_state_change = cep->sk_state_change;
+ new_cep->sk_data_ready = cep->sk_data_ready;
+ new_cep->sk_write_space = cep->sk_write_space;
+ new_cep->sk_error_report = cep->sk_error_report;
+
+ rv = kernel_accept(s, &new_s, O_NONBLOCK);
+ if (rv != 0) {
+ /*
+ * Connection already aborted by peer..?
+ */
+ siw_dbg_cep(cep, "kernel_accept() error: %d\n", rv);
+ goto error;
+ }
+ new_cep->llp.sock = new_s;
+ siw_cep_get(new_cep);
+ new_s->sk->sk_user_data = new_cep;
+
+ siw_dbg_cep(cep, "listen socket 0x%p, new 0x%p\n", s, new_s);
+
+ rv = siw_sock_nodelay(new_s);
+ if (rv) {
+ siw_dbg_cep(cep, "siw_sock_nodelay() error: %d\n", rv);
+ goto error;
+ }
+
+ rv = kernel_peername(new_s, &new_cep->llp.raddr);
+ if (rv) {
+ siw_dbg_cep(cep, "kernel_peername() error: %d\n", rv);
+ goto error;
+ }
+ rv = kernel_localname(new_s, &new_cep->llp.laddr);
+ if (rv) {
+ siw_dbg_cep(cep, "kernel_localname() error: %d\n", rv);
+ goto error;
+ }
+
+ new_cep->state = SIW_EPSTATE_AWAIT_MPAREQ;
+
+ rv = siw_cm_queue_work(new_cep, SIW_CM_WORK_MPATIMEOUT);
+ if (rv)
+ goto error;
+ /*
+ * See siw_proc_mpareq() etc. for the use of new_cep->listen_cep.
+ */
+ new_cep->listen_cep = cep;
+ siw_cep_get(cep);
+
+ if (atomic_read(&new_s->sk->sk_rmem_alloc)) {
+ /*
+ * MPA REQ already queued
+ */
+ siw_dbg_cep(cep, "immediate mpa request\n");
+
+ siw_cep_set_inuse(new_cep);
+ rv = siw_proc_mpareq(new_cep);
+ siw_cep_set_free(new_cep);
+
+ if (rv != -EAGAIN) {
+ siw_cep_put(cep);
+ new_cep->listen_cep = NULL;
+ if (rv)
+ goto error;
+ }
+ }
+ return;
+
+error:
+ if (new_cep)
+ siw_cep_put(new_cep);
+
+ if (new_s) {
+ siw_socket_disassoc(new_s);
+ sock_release(new_s);
+ new_cep->llp.sock = NULL;
+ }
+ siw_dbg_cep(cep, "error %d\n", rv);
+}
+
+static void siw_cm_work_handler(struct work_struct *w)
+{
+ struct siw_cm_work *work;
+ struct siw_cep *cep;
+ int release_cep = 0, rv = 0;
+
+ work = container_of(w, struct siw_cm_work, work.work);
+ cep = work->cep;
+
+ siw_dbg_cep(cep, "[QP %d]: work type: %d, state %d\n",
+ cep->qp ? QP_ID(cep->qp) : -1, work->type, cep->state);
+
+ siw_cep_set_inuse(cep);
+
+ switch (work->type) {
+
+ case SIW_CM_WORK_ACCEPT:
+
+ siw_accept_newconn(cep);
+ break;
+
+ case SIW_CM_WORK_READ_MPAHDR:
+
+ switch (cep->state) {
+
+ case SIW_EPSTATE_AWAIT_MPAREQ:
+
+ if (cep->listen_cep) {
+ siw_cep_set_inuse(cep->listen_cep);
+
+ if (cep->listen_cep->state ==
+ SIW_EPSTATE_LISTENING)
+ rv = siw_proc_mpareq(cep);
+ else
+ rv = -EFAULT;
+
+ siw_cep_set_free(cep->listen_cep);
+
+ if (rv != -EAGAIN) {
+ siw_cep_put(cep->listen_cep);
+ cep->listen_cep = NULL;
+ if (rv)
+ siw_cep_put(cep);
+ }
+ }
+ break;
+
+ case SIW_EPSTATE_AWAIT_MPAREP:
+
+ rv = siw_proc_mpareply(cep);
+ break;
+
+ default:
+ /*
+ * CEP already moved out of MPA handshake.
+ * any connection management already done.
+ * silently ignore the mpa packet.
+ */
+ if (cep->state == SIW_EPSTATE_RDMA_MODE) {
+ cep->llp.sock->sk->sk_data_ready(
+ cep->llp.sock->sk);
+ siw_dbg_cep(cep, "already in RDMA mode");
+ } else {
+ siw_dbg_cep(cep, "out of state: %d\n",
+ cep->state);
+ }
+ }
+ if (rv && rv != EAGAIN)
+ release_cep = 1;
+
+ break;
+
+ case SIW_CM_WORK_CLOSE_LLP:
+ /*
+ * QP scheduled LLP close
+ */
+ siw_dbg_cep(cep, "work close_llp, state=%d\n", cep->state);
+
+ if (cep->qp && cep->qp->term_info.valid)
+ siw_send_terminate(cep->qp);
+
+ if (cep->cm_id)
+ siw_cm_upcall(cep, IW_CM_EVENT_CLOSE, 0);
+
+ release_cep = 1;
+
+ break;
+
+ case SIW_CM_WORK_PEER_CLOSE:
+
+ siw_dbg_cep(cep, "work peer_close, state=%d\n", cep->state);
+
+ if (cep->cm_id) {
+ switch (cep->state) {
+
+ case SIW_EPSTATE_AWAIT_MPAREP:
+ /*
+ * MPA reply not received, but connection drop
+ */
+ siw_cm_upcall(cep, IW_CM_EVENT_CONNECT_REPLY,
+ -ECONNRESET);
+ break;
+
+ case SIW_EPSTATE_RDMA_MODE:
+ /*
+ * NOTE: IW_CM_EVENT_DISCONNECT is given just
+ * to transition IWCM into CLOSING.
+ */
+ siw_cm_upcall(cep, IW_CM_EVENT_DISCONNECT, 0);
+ siw_cm_upcall(cep, IW_CM_EVENT_CLOSE, 0);
+
+ break;
+
+ default:
+
+ break;
+ /*
+ * for these states there is no connection
+ * known to the IWCM.
+ */
+ }
+ } else {
+ switch (cep->state) {
+
+ case SIW_EPSTATE_RECVD_MPAREQ:
+ /*
+ * Wait for the ulp/CM to call accept/reject
+ */
+ siw_dbg_cep(cep,
+ "mpa req recvd, wait for ULP\n");
+ break;
+
+ case SIW_EPSTATE_AWAIT_MPAREQ:
+ /*
+ * Socket close before MPA request received.
+ */
+ siw_dbg_cep(cep, "no mpareq: drop listener\n");
+ siw_cep_put(cep->listen_cep);
+ cep->listen_cep = NULL;
+
+ break;
+
+ default:
+ break;
+ }
+ }
+ release_cep = 1;
+
+ break;
+
+ case SIW_CM_WORK_MPATIMEOUT:
+
+ cep->mpa_timer = NULL;
+
+ if (cep->state == SIW_EPSTATE_AWAIT_MPAREP) {
+ /*
+ * MPA request timed out:
+ * Hide any partially received private data and signal
+ * timeout
+ */
+ cep->mpa.hdr.params.pd_len = 0;
+
+ if (cep->cm_id)
+ siw_cm_upcall(cep, IW_CM_EVENT_CONNECT_REPLY,
+ -ETIMEDOUT);
+ release_cep = 1;
+
+ } else if (cep->state == SIW_EPSTATE_AWAIT_MPAREQ) {
+ /*
+ * No MPA request received after peer TCP stream setup.
+ */
+ if (cep->listen_cep) {
+ siw_cep_put(cep->listen_cep);
+ cep->listen_cep = NULL;
+ }
+ release_cep = 1;
+ }
+ break;
+
+ default:
+ WARN(1, "Undefined CM work type: %d\n", work->type);
+ }
+
+ if (release_cep) {
+ siw_dbg_cep(cep,
+ "release: timer=%s, sock=0x%p, QP %d, id 0x%p\n",
+ cep->mpa_timer ? "y" : "n", cep->llp.sock,
+ cep->qp ? QP_ID(cep->qp) : -1, cep->cm_id);
+
+ siw_cancel_mpatimer(cep);
+
+ cep->state = SIW_EPSTATE_CLOSED;
+
+ if (cep->qp) {
+ struct siw_qp *qp = cep->qp;
+ /*
+ * Serialize a potential race with application
+ * closing the QP and calling siw_qp_cm_drop()
+ */
+ siw_qp_get(qp);
+ siw_cep_set_free(cep);
+
+ siw_qp_llp_close(qp);
+ siw_qp_put(qp);
+
+ siw_cep_set_inuse(cep);
+ cep->qp = NULL;
+ siw_qp_put(qp);
+ }
+ if (cep->llp.sock) {
+ siw_socket_disassoc(cep->llp.sock);
+ sock_release(cep->llp.sock);
+ cep->llp.sock = NULL;
+ }
+ if (cep->cm_id) {
+ cep->cm_id->rem_ref(cep->cm_id);
+ cep->cm_id = NULL;
+ siw_cep_put(cep);
+ }
+ }
+
+ siw_cep_set_free(cep);
+ siw_dbg_cep(cep, "Exit: work type: %d\n", work->type);
+
+ siw_put_work(work);
+ siw_cep_put(cep);
+}
+
+static struct workqueue_struct *siw_cm_wq;
+
+int siw_cm_queue_work(struct siw_cep *cep, enum siw_work_type type)
+{
+ struct siw_cm_work *work = siw_get_work(cep);
+ unsigned long delay = 0;
+
+ if (!work) {
+ siw_dbg_cep(cep, "failed with no work available\n");
+ return -ENOMEM;
+ }
+ work->type = type;
+ work->cep = cep;
+
+ siw_cep_get(cep);
+
+ INIT_DELAYED_WORK(&work->work, siw_cm_work_handler);
+
+ if (type == SIW_CM_WORK_MPATIMEOUT) {
+ cep->mpa_timer = work;
+
+ if (cep->state == SIW_EPSTATE_AWAIT_MPAREP)
+ delay = MPAREQ_TIMEOUT;
+ else
+ delay = MPAREP_TIMEOUT;
+ }
+ siw_dbg_cep(cep, "[QP %d]: work type: %d, work 0x%p, timeout %lu\n",
+ cep->qp ? QP_ID(cep->qp) : -1, type, work, delay);
+
+ queue_delayed_work(siw_cm_wq, &work->work, delay);
+
+ return 0;
+}
+
+static void siw_cm_llp_data_ready(struct sock *sk)
+{
+ struct siw_cep *cep;
+
+ read_lock(&sk->sk_callback_lock);
+
+ cep = sk_to_cep(sk);
+ if (!cep) {
+ WARN_ON(1);
+ goto out;
+ }
+
+ siw_dbg_cep(cep, "state: %d\n", cep->state);
+
+ switch (cep->state) {
+
+ case SIW_EPSTATE_RDMA_MODE:
+ /* fall through */
+ case SIW_EPSTATE_LISTENING:
+
+ break;
+
+ case SIW_EPSTATE_AWAIT_MPAREQ:
+ /* fall through */
+ case SIW_EPSTATE_AWAIT_MPAREP:
+
+ siw_cm_queue_work(cep, SIW_CM_WORK_READ_MPAHDR);
+ break;
+
+ default:
+ siw_dbg_cep(cep, "unexpected data, state %d\n", cep->state);
+ break;
+ }
+out:
+ read_unlock(&sk->sk_callback_lock);
+}
+
+static void siw_cm_llp_write_space(struct sock *sk)
+{
+ struct siw_cep *cep = sk_to_cep(sk);
+
+ if (cep)
+ siw_dbg_cep(cep, "state: %d\n", cep->state);
+}
+
+static void siw_cm_llp_error_report(struct sock *sk)
+{
+ struct siw_cep *cep = sk_to_cep(sk);
+
+ if (cep) {
+ siw_dbg_cep(cep, "error %d, socket state: %d, cep state: %d\n",
+ sk->sk_err, sk->sk_state, cep->state);
+ cep->sk_error = sk->sk_err;
+ cep->sk_error_report(sk);
+ }
+}
+
+static void siw_cm_llp_state_change(struct sock *sk)
+{
+ struct siw_cep *cep;
+ struct socket *s;
+ void (*orig_state_change)(struct sock *);
+
+ read_lock(&sk->sk_callback_lock);
+
+ cep = sk_to_cep(sk);
+ if (!cep) {
+ /* endpoint already disassociated */
+ read_unlock(&sk->sk_callback_lock);
+ return;
+ }
+ orig_state_change = cep->sk_state_change;
+
+ s = sk->sk_socket;
+
+ siw_dbg_cep(cep, "state: %d\n", cep->state);
+
+ switch (sk->sk_state) {
+
+ case TCP_ESTABLISHED:
+ /*
+ * handle accepting socket as special case where only
+ * new connection is possible
+ */
+ siw_cm_queue_work(cep, SIW_CM_WORK_ACCEPT);
+
+ break;
+
+ case TCP_CLOSE:
+ case TCP_CLOSE_WAIT:
+
+ if (cep->qp)
+ cep->qp->tx_ctx.tx_suspend = 1;
+ siw_cm_queue_work(cep, SIW_CM_WORK_PEER_CLOSE);
+
+ break;
+
+ default:
+ siw_dbg_cep(cep, "unexpected socket state %d\n", sk->sk_state);
+ }
+ read_unlock(&sk->sk_callback_lock);
+ orig_state_change(sk);
+}
+
+static int kernel_bindconnect(struct socket *s,
+ struct sockaddr *laddr, int laddrlen,
+ struct sockaddr *raddr, int raddrlen, int flags)
+{
+ int rv, s_val = 1;
+
+ /*
+ * Make address available again asap.
+ */
+ rv = kernel_setsockopt(s, SOL_SOCKET, SO_REUSEADDR, (char *)&s_val,
+ sizeof(s_val));
+ if (rv < 0)
+ return rv;
+
+ rv = s->ops->bind(s, laddr, laddrlen);
+ if (rv < 0)
+ return rv;
+
+ rv = s->ops->connect(s, raddr, raddrlen, flags);
+ if (rv < 0)
+ return rv;
+
+ return s->ops->getname(s, laddr, &s_val, 0);
+}
+
+int siw_connect(struct iw_cm_id *id, struct iw_cm_conn_param *params)
+{
+ struct siw_device *sdev = siw_dev_base2siw(id->device);
+ struct siw_qp *qp;
+ struct siw_cep *cep = NULL;
+ struct socket *s = NULL;
+ struct sockaddr *laddr, *raddr;
+ bool p2p_mode = peer_to_peer;
+
+ u16 pd_len = params->private_data_len;
+ int version = mpa_version, rv;
+
+ if (pd_len > MPA_MAX_PRIVDATA)
+ return -EINVAL;
+
+ if (params->ird > sdev->attrs.max_ird ||
+ params->ord > sdev->attrs.max_ord)
+ return -ENOMEM;
+
+ qp = siw_qp_id2obj(sdev, params->qpn);
+ if (!qp) {
+ WARN(1, "[QP %u] does not exist\n", params->qpn);
+ rv = -EINVAL;
+ goto error;
+ }
+
+ siw_dbg_qp(qp, "id 0x%p, pd_len %d, laddr 0x%x:%d, raddr 0x%x:%d\n",
+ id, pd_len,
+ ntohl(to_sockaddr_in(id->local_addr).sin_addr.s_addr),
+ ntohs(to_sockaddr_in(id->local_addr).sin_port),
+ ntohl(to_sockaddr_in(id->remote_addr).sin_addr.s_addr),
+ ntohs(to_sockaddr_in(id->remote_addr).sin_port));
+
+ laddr = (struct sockaddr *)&id->local_addr;
+ raddr = (struct sockaddr *)&id->remote_addr;
+
+ rv = sock_create(AF_INET, SOCK_STREAM, IPPROTO_TCP, &s);
+ if (rv < 0)
+ goto error;
+
+ /*
+ * NOTE: For simplification, connect() is called in blocking
+ * mode. Might be reconsidered for async connection setup at
+ * TCP level.
+ */
+ rv = kernel_bindconnect(s, laddr, sizeof(*laddr), raddr,
+ sizeof(*raddr), 0);
+ if (rv != 0) {
+ siw_dbg_qp(qp, "id 0x%p: kernel_bindconnect: rv %d\n", id, rv);
+ goto error;
+ }
+ rv = siw_sock_nodelay(s);
+ if (rv != 0) {
+ siw_dbg_qp(qp, "siw_sock_nodelay() error: %d\n", rv);
+ goto error;
+ }
+ cep = siw_cep_alloc(sdev);
+ if (!cep) {
+ rv = -ENOMEM;
+ goto error;
+ }
+ siw_cep_set_inuse(cep);
+
+ /* Associate QP with CEP */
+ siw_cep_get(cep);
+ qp->cep = cep;
+
+ /* siw_qp_get(qp) already done by QP lookup */
+ cep->qp = qp;
+
+ id->add_ref(id);
+ cep->cm_id = id;
+
+ /*
+ * 4: Allocate a sufficient number of work elements
+ * to allow concurrent handling of local + peer close
+ * events, MPA header processing + MPA timeout.
+ */
+ rv = siw_cm_alloc_work(cep, 4);
+ if (rv != 0) {
+ rv = -ENOMEM;
+ goto error;
+ }
+ cep->ird = params->ird;
+ cep->ord = params->ord;
+
+ if (p2p_mode && cep->ord == 0)
+ cep->ord = 1;
+
+ cep->state = SIW_EPSTATE_CONNECTING;
+
+ rv = kernel_peername(s, &cep->llp.raddr);
+ if (rv)
+ goto error;
+
+ rv = kernel_localname(s, &cep->llp.laddr);
+ if (rv)
+ goto error;
+
+ /*
+ * Associate CEP with socket
+ */
+ siw_cep_socket_assoc(cep, s);
+
+ cep->state = SIW_EPSTATE_AWAIT_MPAREP;
+
+ /*
+ * Set MPA Request bits: CRC if required, no MPA Markers,
+ * MPA Rev. according to module parameter 'mpa_version', Key 'Request'.
+ */
+ cep->mpa.hdr.params.bits = 0;
+ if (version > MPA_REVISION_2) {
+ pr_warn("Setting MPA version to %u\n", MPA_REVISION_2);
+ version = MPA_REVISION_2;
+ /* Adjust also module parameter */
+ mpa_version = MPA_REVISION_2;
+ }
+ __mpa_rr_set_revision(&cep->mpa.hdr.params.bits, version);
+
+ if (mpa_crc_required)
+ cep->mpa.hdr.params.bits |= MPA_RR_FLAG_CRC;
+
+ /*
+ * If MPA version == 2:
+ * o Include ORD and IRD.
+ * o Indicate peer-to-peer mode, if required by module
+ * parameter 'peer_to_peer'.
+ */
+ if (version == MPA_REVISION_2) {
+ cep->enhanced_rdma_conn_est = true;
+ cep->mpa.hdr.params.bits |= MPA_RR_FLAG_ENHANCED;
+
+ cep->mpa.v2_ctrl.ird = htons(cep->ird);
+ cep->mpa.v2_ctrl.ord = htons(cep->ord);
+
+ if (p2p_mode) {
+ cep->mpa.v2_ctrl.ird |= MPA_V2_PEER_TO_PEER;
+ cep->mpa.v2_ctrl.ord |= rtr_type;
+ }
+ /* Remember own P2P mode requested */
+ cep->mpa.v2_ctrl_req.ird = cep->mpa.v2_ctrl.ird;
+ cep->mpa.v2_ctrl_req.ord = cep->mpa.v2_ctrl.ord;
+ }
+
+ memcpy(cep->mpa.hdr.key, MPA_KEY_REQ, 16);
+
+ rv = siw_send_mpareqrep(cep, params->private_data, pd_len);
+ /*
+ * Reset private data.
+ */
+ cep->mpa.hdr.params.pd_len = 0;
+
+ if (rv >= 0) {
+ rv = siw_cm_queue_work(cep, SIW_CM_WORK_MPATIMEOUT);
+ if (!rv) {
+ siw_dbg_cep(cep, "id 0x%p, [QP %d]: exit\n",
+ id, QP_ID(qp));
+ siw_cep_set_free(cep);
+ return 0;
+ }
+ }
+error:
+ siw_dbg_qp(qp, "failed: %d\n", rv);
+
+ if (cep) {
+ siw_socket_disassoc(s);
+ sock_release(s);
+ cep->llp.sock = NULL;
+
+ cep->qp = NULL;
+
+ cep->cm_id = NULL;
+ id->rem_ref(id);
+ siw_cep_put(cep);
+
+ qp->cep = NULL;
+ siw_cep_put(cep);
+
+ cep->state = SIW_EPSTATE_CLOSED;
+
+ siw_cep_set_free(cep);
+
+ siw_cep_put(cep);
+
+ } else if (s) {
+ sock_release(s);
+ }
+ siw_qp_put(qp);
+
+ return rv;
+}
+
+/*
+ * siw_accept - Let SoftiWARP accept an RDMA connection request
+ *
+ * @id: New connection management id to be used for accepted
+ * connection request
+ * @params: Connection parameters provided by ULP for accepting connection
+ *
+ * Transition QP to RTS state, associate new CM id @id with accepted CEP
+ * and get prepared for TCP input by installing socket callbacks.
+ * Then send MPA Reply and generate the "connection established" event.
+ * Socket callbacks must be installed before sending MPA Reply, because
+ * the latter may cause a first RDMA message to arrive from the RDMA Initiator
+ * side very quickly, at which time the socket callbacks must be ready.
+ */
+int siw_accept(struct iw_cm_id *id, struct iw_cm_conn_param *params)
+{
+ struct siw_device *sdev = siw_dev_base2siw(id->device);
+ struct siw_cep *cep = (struct siw_cep *)id->provider_data;
+ struct siw_qp *qp;
+ struct siw_qp_attrs qp_attrs;
+ int rv, max_priv_data = MPA_MAX_PRIVDATA;
+ bool wait_for_peer_rts = false;
+
+ siw_cep_set_inuse(cep);
+ siw_cep_put(cep);
+
+ /* Free lingering inbound private data */
+ if (cep->mpa.hdr.params.pd_len) {
+ cep->mpa.hdr.params.pd_len = 0;
+ kfree(cep->mpa.pdata);
+ cep->mpa.pdata = NULL;
+ }
+ siw_cancel_mpatimer(cep);
+
+ if (cep->state != SIW_EPSTATE_RECVD_MPAREQ) {
+ siw_dbg_cep(cep, "id 0x%p: out of state\n", id);
+
+ siw_cep_set_free(cep);
+ siw_cep_put(cep);
+
+ return -ECONNRESET;
+ }
+
+ qp = siw_qp_id2obj(sdev, params->qpn);
+ if (!qp) {
+ WARN(1, "[QP %d] does not exist\n", params->qpn);
+ siw_cep_set_free(cep);
+ siw_cep_put(cep);
+
+ return -EINVAL;
+ }
+
+ down_write(&qp->state_lock);
+ if (qp->attrs.state > SIW_QP_STATE_RTR) {
+ rv = -EINVAL;
+ up_write(&qp->state_lock);
+ goto error;
+ }
+
+ siw_dbg_cep(cep, "id 0x%p\n", id);
+
+ if (params->ord > sdev->attrs.max_ord ||
+ params->ird > sdev->attrs.max_ird) {
+ siw_dbg_cep(cep,
+ "id 0x%p, [QP %d]: ord %d (max %d), ird %d (max %d)\n",
+ id, QP_ID(qp),
+ params->ord, sdev->attrs.max_ord,
+ params->ird, sdev->attrs.max_ird);
+ rv = -EINVAL;
+ up_write(&qp->state_lock);
+ goto error;
+ }
+ if (cep->enhanced_rdma_conn_est)
+ max_priv_data -= sizeof(struct mpa_v2_data);
+
+ if (params->private_data_len > max_priv_data) {
+ siw_dbg_cep(cep,
+ "id 0x%p, [QP %d]: private data length: %d (max %d)\n",
+ id, QP_ID(qp),
+ params->private_data_len, max_priv_data);
+ rv = -EINVAL;
+ up_write(&qp->state_lock);
+ goto error;
+ }
+
+ if (cep->enhanced_rdma_conn_est) {
+ if (params->ord > cep->ord) {
+ if (relaxed_ird_negotiation)
+ params->ord = cep->ord;
+ else {
+ cep->ird = params->ird;
+ cep->ord = params->ord;
+ rv = -EINVAL;
+ up_write(&qp->state_lock);
+ goto error;
+ }
+ }
+ if (params->ird < cep->ird) {
+ if (relaxed_ird_negotiation &&
+ cep->ird <= sdev->attrs.max_ird)
+ params->ird = cep->ird;
+ else {
+ rv = -ENOMEM;
+ up_write(&qp->state_lock);
+ goto error;
+ }
+ }
+ if (cep->mpa.v2_ctrl.ord &
+ (MPA_V2_RDMA_WRITE_RTR | MPA_V2_RDMA_READ_RTR))
+ wait_for_peer_rts = true;
+ /*
+ * Signal back negotiated IRD and ORD values
+ */
+ cep->mpa.v2_ctrl.ord = htons(params->ord & MPA_IRD_ORD_MASK) |
+ (cep->mpa.v2_ctrl.ord & ~MPA_V2_MASK_IRD_ORD);
+ cep->mpa.v2_ctrl.ird = htons(params->ird & MPA_IRD_ORD_MASK) |
+ (cep->mpa.v2_ctrl.ird & ~MPA_V2_MASK_IRD_ORD);
+ }
+ cep->ird = params->ird;
+ cep->ord = params->ord;
+
+ cep->cm_id = id;
+ id->add_ref(id);
+
+ memset(&qp_attrs, 0, sizeof(qp_attrs));
+ qp_attrs.orq_size = cep->ord;
+ qp_attrs.irq_size = cep->ird;
+ qp_attrs.llp_stream_handle = cep->llp.sock;
+ if (cep->mpa.hdr.params.bits & MPA_RR_FLAG_CRC)
+ qp_attrs.flags = SIW_MPA_CRC;
+ qp_attrs.state = SIW_QP_STATE_RTS;
+
+ siw_dbg_cep(cep, "id 0x%p, [QP%d]: moving to rts\n", id, QP_ID(qp));
+
+ /* Associate QP with CEP */
+ siw_cep_get(cep);
+ qp->cep = cep;
+
+ /* siw_qp_get(qp) already done by QP lookup */
+ cep->qp = qp;
+
+ cep->state = SIW_EPSTATE_RDMA_MODE;
+
+ /* Move socket RX/TX under QP control */
+ rv = siw_qp_modify(qp, &qp_attrs, SIW_QP_ATTR_STATE|
+ SIW_QP_ATTR_LLP_HANDLE|
+ SIW_QP_ATTR_ORD|
+ SIW_QP_ATTR_IRD|
+ SIW_QP_ATTR_MPA);
+ up_write(&qp->state_lock);
+
+ if (rv)
+ goto error;
+
+ siw_dbg_cep(cep, "id 0x%p, [QP %d]: send mpa reply, %d byte pdata\n",
+ id, QP_ID(qp), params->private_data_len);
+
+ rv = siw_send_mpareqrep(cep, params->private_data,
+ params->private_data_len);
+ if (rv != 0)
+ goto error;
+
+ if (wait_for_peer_rts) {
+ siw_sk_assign_rtr_upcalls(cep);
+ } else {
+ siw_qp_socket_assoc(cep, qp);
+ rv = siw_cm_upcall(cep, IW_CM_EVENT_ESTABLISHED, 0);
+ if (rv)
+ goto error;
+ }
+ siw_cep_set_free(cep);
+
+ return 0;
+error:
+ siw_socket_disassoc(cep->llp.sock);
+ sock_release(cep->llp.sock);
+ cep->llp.sock = NULL;
+
+ cep->state = SIW_EPSTATE_CLOSED;
+
+ if (cep->cm_id) {
+ cep->cm_id->rem_ref(id);
+ cep->cm_id = NULL;
+ }
+ if (qp->cep) {
+ siw_cep_put(cep);
+ qp->cep = NULL;
+ }
+ cep->qp = NULL;
+ siw_qp_put(qp);
+
+ siw_cep_set_free(cep);
+ siw_cep_put(cep);
+
+ return rv;
+}
+
+/*
+ * siw_reject()
+ *
+ * Local connection reject case. Send private data back to peer,
+ * close connection and dereference connection id.
+ */
+int siw_reject(struct iw_cm_id *id, const void *pdata, u8 pd_len)
+{
+ struct siw_cep *cep = (struct siw_cep *)id->provider_data;
+
+ siw_cep_set_inuse(cep);
+ siw_cep_put(cep);
+
+ siw_cancel_mpatimer(cep);
+
+ if (cep->state != SIW_EPSTATE_RECVD_MPAREQ) {
+
+ siw_dbg_cep(cep, "id 0x%p: out of state\n", id);
+
+ siw_cep_set_free(cep);
+ siw_cep_put(cep); /* put last reference */
+
+ return -ECONNRESET;
+ }
+ siw_dbg_cep(cep, "id 0x%p, cep->state %d, pd_len %d\n",
+ id, cep->state, pd_len);
+
+ if (__mpa_rr_revision(cep->mpa.hdr.params.bits) >= MPA_REVISION_1) {
+ cep->mpa.hdr.params.bits |= MPA_RR_FLAG_REJECT; /* reject */
+ (void)siw_send_mpareqrep(cep, pdata, pd_len);
+ }
+ siw_socket_disassoc(cep->llp.sock);
+ sock_release(cep->llp.sock);
+ cep->llp.sock = NULL;
+
+ cep->state = SIW_EPSTATE_CLOSED;
+
+ siw_cep_set_free(cep);
+ siw_cep_put(cep);
+
+ return 0;
+}
+
+static int siw_listen_address(struct iw_cm_id *id, int backlog,
+ struct sockaddr *laddr)
+{
+ struct socket *s;
+ struct siw_cep *cep = NULL;
+ struct siw_device *sdev = siw_dev_base2siw(id->device);
+ int rv = 0, s_val;
+
+ rv = sock_create(AF_INET, SOCK_STREAM, IPPROTO_TCP, &s);
+ if (rv < 0)
+ return rv;
+
+ /*
+ * Probably to be removed later. Allows binding
+ * local port when still in TIME_WAIT from last close.
+ */
+ s_val = 1;
+ rv = kernel_setsockopt(s, SOL_SOCKET, SO_REUSEADDR, (char *)&s_val,
+ sizeof(s_val));
+ if (rv) {
+ siw_dbg(sdev, "id 0x%p: setsockopt error: %d\n", id, rv);
+ goto error;
+ }
+ rv = s->ops->bind(s, laddr, sizeof(*laddr));
+ if (rv != 0) {
+ siw_dbg(sdev, "id 0x%p: socket bind error: %d\n", id, rv);
+ goto error;
+ }
+ cep = siw_cep_alloc(sdev);
+ if (!cep) {
+ rv = -ENOMEM;
+ goto error;
+ }
+ siw_cep_socket_assoc(cep, s);
+
+ rv = siw_cm_alloc_work(cep, backlog);
+ if (rv != 0) {
+ siw_dbg(sdev, "id 0x%p: alloc_work error %d, backlog %d\n",
+ id, rv, backlog);
+ goto error;
+ }
+ rv = s->ops->listen(s, backlog);
+ if (rv != 0) {
+ siw_dbg(sdev, "id 0x%p: listen error %d\n", id, rv);
+ goto error;
+ }
+ memcpy(&cep->llp.laddr, &id->local_addr, sizeof(cep->llp.laddr));
+ memcpy(&cep->llp.raddr, &id->remote_addr, sizeof(cep->llp.raddr));
+
+ cep->cm_id = id;
+ id->add_ref(id);
+
+ /*
+ * In case of a wildcard rdma_listen on a multi-homed device,
+ * a listener's IWCM id is associated with more than one listening CEP.
+ *
+ * We currently use id->provider_data in three different ways:
+ *
+ * o For a listener's IWCM id, id->provider_data points to
+ * the list_head of the list of listening CEPs.
+ * Uses: siw_create_listen(), siw_destroy_listen()
+ *
+ * o For a passive-side IWCM id, id->provider_data points to
+ * the CEP itself. This is a consequence of
+ * - siw_cm_upcall() setting event.provider_data = cep and
+ * - the IWCM's cm_conn_req_handler() setting provider_data of the
+ * new passive-side IWCM id equal to event.provider_data
+ * Uses: siw_accept(), siw_reject()
+ *
+ * o For an active-side IWCM id, id->provider_data is not used at all.
+ *
+ */
+ if (!id->provider_data) {
+ id->provider_data = kmalloc(sizeof(struct list_head),
+ GFP_KERNEL);
+ if (!id->provider_data) {
+ rv = -ENOMEM;
+ goto error;
+ }
+ INIT_LIST_HEAD((struct list_head *)id->provider_data);
+ }
+
+ siw_dbg(sdev, "id 0x%p: provider_data 0x%p, cep 0x%p\n",
+ id, id->provider_data, cep);
+
+ list_add_tail(&cep->listenq, (struct list_head *)id->provider_data);
+ cep->state = SIW_EPSTATE_LISTENING;
+
+ return 0;
+
+error:
+ siw_dbg(sdev, "failed: %d\n", rv);
+
+ if (cep) {
+ siw_cep_set_inuse(cep);
+
+ if (cep->cm_id) {
+ cep->cm_id->rem_ref(cep->cm_id);
+ cep->cm_id = NULL;
+ }
+ cep->llp.sock = NULL;
+ siw_socket_disassoc(s);
+ cep->state = SIW_EPSTATE_CLOSED;
+
+ siw_cep_set_free(cep);
+ siw_cep_put(cep);
+ }
+ sock_release(s);
+
+ return rv;
+}
+
+static void siw_drop_listeners(struct iw_cm_id *id)
+{
+ struct list_head *p, *tmp;
+
+ /*
+ * In case of a wildcard rdma_listen on a multi-homed device,
+ * a listener's IWCM id is associated with more than one listening CEP.
+ */
+ list_for_each_safe(p, tmp, (struct list_head *)id->provider_data) {
+ struct siw_cep *cep = list_entry(p, struct siw_cep, listenq);
+
+ list_del(p);
+
+ siw_dbg_cep(cep, "id 0x%p: drop cep, state %d\n",
+ id, cep->state);
+
+ siw_cep_set_inuse(cep);
+
+ if (cep->cm_id) {
+ cep->cm_id->rem_ref(cep->cm_id);
+ cep->cm_id = NULL;
+ }
+ if (cep->llp.sock) {
+ siw_socket_disassoc(cep->llp.sock);
+ sock_release(cep->llp.sock);
+ cep->llp.sock = NULL;
+ }
+ cep->state = SIW_EPSTATE_CLOSED;
+ siw_cep_set_free(cep);
+ siw_cep_put(cep);
+ }
+}
+
+/*
+ * siw_create_listen - Create resources for a listener's IWCM ID @id
+ *
+ * Listens on the socket addresses id->local_addr and id->remote_addr.
+ *
+ * If the listener's @id provides a specific local IP address, at most one
+ * listening socket is created and associated with @id.
+ *
+ * If the listener's @id provides the wildcard (zero) local IP address,
+ * a separate listen is performed for each local IP address of the device
+ * by creating a listening socket and binding to that local IP address.
+ *
+ */
+int siw_create_listen(struct iw_cm_id *id, int backlog)
+{
+ struct ib_device *base_dev = id->device;
+ struct siw_device *sdev = siw_dev_base2siw(base_dev);
+ int rv = 0;
+
+ siw_dbg(sdev, "id 0x%p: backlog %d\n", id, backlog);
+
+ if (to_sockaddr_in(id->local_addr).sin_family == AF_INET) {
+ /* IPv4 */
+ struct sockaddr_in laddr = to_sockaddr_in(id->local_addr);
+ u8 *l_ip, *r_ip;
+ struct in_device *in_dev;
+
+ l_ip = (u8 *) &to_sockaddr_in(id->local_addr).sin_addr.s_addr;
+ r_ip = (u8 *) &to_sockaddr_in(id->remote_addr).sin_addr.s_addr;
+ siw_dbg(sdev,
+ "id 0x%p: laddr %d.%d.%d.%d:%d, raddr %d.%d.%d.%d:%d\n",
+ id, l_ip[0], l_ip[1], l_ip[2], l_ip[3],
+ ntohs(to_sockaddr_in(id->local_addr).sin_port),
+ r_ip[0], r_ip[1], r_ip[2], r_ip[3],
+ ntohs(to_sockaddr_in(id->remote_addr).sin_port));
+
+ in_dev = in_dev_get(sdev->netdev);
+ if (!in_dev) {
+ siw_dbg(sdev, "id 0x%p: netdev w/o in_device\n", id);
+ return -ENODEV;
+ }
+
+ for_ifa(in_dev) {
+ /*
+ * Create a listening socket if id->local_addr
+ * contains the wildcard IP address OR
+ * the IP address of the interface.
+ */
+ if (ipv4_is_zeronet(
+ to_sockaddr_in(id->local_addr).sin_addr.s_addr) ||
+ to_sockaddr_in(id->local_addr).sin_addr.s_addr ==
+ ifa->ifa_address) {
+ laddr.sin_addr.s_addr = ifa->ifa_address;
+
+ l_ip = (u8 *) &laddr.sin_addr.s_addr;
+ siw_dbg(sdev,
+ "id 0x%p: bind: %d.%d.%d.%d:%d\n",
+ id, l_ip[0], l_ip[1], l_ip[2],
+ l_ip[3], ntohs(laddr.sin_port));
+
+ rv = siw_listen_address(id, backlog,
+ (struct sockaddr *)&laddr);
+ if (rv)
+ break;
+ }
+ }
+ endfor_ifa(in_dev);
+ in_dev_put(in_dev);
+
+ if (rv && id->provider_data)
+ siw_drop_listeners(id);
+
+ } else {
+ /* IPv6 */
+ rv = -EAFNOSUPPORT;
+ siw_dbg(sdev, "id 0x%p: TODO: IPv6 support\n", id);
+ }
+ if (!rv)
+ siw_dbg(sdev, "id 0x%p: success\n", id);
+
+ return rv;
+}
+
+int siw_destroy_listen(struct iw_cm_id *id)
+{
+ struct siw_device *sdev = siw_dev_base2siw(id->device);
+
+ siw_dbg(sdev, "id 0x%p\n", id);
+
+ if (!id->provider_data) {
+ siw_dbg(sdev, "id 0x%p: no cep(s)\n", id);
+ return 0;
+ }
+ siw_drop_listeners(id);
+ kfree(id->provider_data);
+ id->provider_data = NULL;
+
+ return 0;
+}
+
+int siw_cm_init(void)
+{
+ /*
+ * create_single_workqueue for strict ordering
+ */
+ siw_cm_wq = create_singlethread_workqueue("siw_cm_wq");
+ if (!siw_cm_wq)
+ return -ENOMEM;
+
+ return 0;
+}
+
+void siw_cm_exit(void)
+{
+ if (siw_cm_wq) {
+ flush_workqueue(siw_cm_wq);
+ destroy_workqueue(siw_cm_wq);
+ }
+}
new file mode 100644
@@ -0,0 +1,156 @@
+/*
+ * Software iWARP device driver
+ *
+ * Authors: Bernard Metzler <bmt@zurich.ibm.com>
+ * Greg Joyce <greg@opengridcomputing.com>
+ *
+ * Copyright (c) 2008-2017, IBM Corporation
+ * Copyright (c) 2017, Open Grid Computing, Inc.
+ *
+ * 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 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 IBM nor the names of its contributors may be
+ * used to endorse or promote products derived from this software without
+ * specific prior written permission.
+ *
+ * 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.
+ */
+
+#ifndef _SIW_CM_H
+#define _SIW_CM_H
+
+#include <net/sock.h>
+#include <linux/tcp.h>
+
+#include <rdma/iw_cm.h>
+
+
+enum siw_cep_state {
+ SIW_EPSTATE_IDLE = 1,
+ SIW_EPSTATE_LISTENING,
+ SIW_EPSTATE_CONNECTING,
+ SIW_EPSTATE_AWAIT_MPAREQ,
+ SIW_EPSTATE_RECVD_MPAREQ,
+ SIW_EPSTATE_AWAIT_MPAREP,
+ SIW_EPSTATE_RDMA_MODE,
+ SIW_EPSTATE_CLOSED
+};
+
+struct siw_mpa_info {
+ struct mpa_rr hdr; /* peer mpa hdr in host byte order */
+ struct mpa_v2_data v2_ctrl;
+ struct mpa_v2_data v2_ctrl_req;
+ char *pdata;
+ int bytes_rcvd;
+};
+
+struct siw_llp_info {
+ struct socket *sock;
+ struct sockaddr_in laddr; /* redundant with socket info above */
+ struct sockaddr_in raddr; /* dito, consider removal */
+ struct siw_sk_upcalls sk_def_upcalls;
+};
+
+struct siw_device;
+
+struct siw_cep {
+ struct iw_cm_id *cm_id;
+ struct siw_device *sdev;
+
+ struct list_head devq;
+ /*
+ * The provider_data element of a listener IWCM ID
+ * refers to a list of one or more listener CEPs
+ */
+ struct list_head listenq;
+ struct siw_cep *listen_cep;
+ struct siw_qp *qp;
+ spinlock_t lock;
+ wait_queue_head_t waitq;
+ struct kref ref;
+ enum siw_cep_state state;
+ short in_use;
+ struct siw_cm_work *mpa_timer;
+ struct list_head work_freelist;
+ struct siw_llp_info llp;
+ struct siw_mpa_info mpa;
+ int ord;
+ int ird;
+ bool enhanced_rdma_conn_est;
+ int sk_error; /* not (yet) used XXX */
+
+ /* Saved upcalls of socket llp.sock */
+ void (*sk_state_change)(struct sock *sk);
+ void (*sk_data_ready)(struct sock *sk);
+ void (*sk_write_space)(struct sock *sk);
+ void (*sk_error_report)(struct sock *sk);
+};
+
+/*
+ * Connection initiator waits 10 seconds to receive an
+ * MPA reply after sending out MPA request. Reponder waits for
+ * 5 seconds for MPA request to arrive if new TCP connection
+ * was set up.
+ */
+#define MPAREQ_TIMEOUT (HZ*10)
+#define MPAREP_TIMEOUT (HZ*5)
+
+enum siw_work_type {
+ SIW_CM_WORK_ACCEPT = 1,
+ SIW_CM_WORK_READ_MPAHDR,
+ SIW_CM_WORK_CLOSE_LLP, /* close socket */
+ SIW_CM_WORK_PEER_CLOSE, /* socket indicated peer close */
+ SIW_CM_WORK_MPATIMEOUT
+};
+
+struct siw_cm_work {
+ struct delayed_work work;
+ struct list_head list;
+ enum siw_work_type type;
+ struct siw_cep *cep;
+};
+
+#define to_sockaddr_in(a) (*(struct sockaddr_in *)(&(a)))
+
+extern int siw_connect(struct iw_cm_id *id, struct iw_cm_conn_param *parm);
+extern int siw_accept(struct iw_cm_id *id, struct iw_cm_conn_param *param);
+extern int siw_reject(struct iw_cm_id *id, const void *data, u8 len);
+extern int siw_create_listen(struct iw_cm_id *id, int backlog);
+extern int siw_destroy_listen(struct iw_cm_id *id);
+
+extern void siw_cep_get(struct siw_cep *cep);
+extern void siw_cep_put(struct siw_cep *cep);
+extern int siw_cm_queue_work(struct siw_cep *cep, enum siw_work_type type);
+
+extern int siw_cm_init(void);
+extern void siw_cm_exit(void);
+
+/*
+ * TCP socket interface
+ */
+#define sk_to_qp(sk) (((struct siw_cep *)((sk)->sk_user_data))->qp)
+#define sk_to_cep(sk) ((struct siw_cep *)((sk)->sk_user_data))
+
+#endif
Signed-off-by: Bernard Metzler <bmt@zurich.ibm.com> --- drivers/infiniband/sw/siw/siw_cm.c | 2184 ++++++++++++++++++++++++++++++++++++ drivers/infiniband/sw/siw/siw_cm.h | 156 +++ 2 files changed, 2340 insertions(+) create mode 100644 drivers/infiniband/sw/siw/siw_cm.c create mode 100644 drivers/infiniband/sw/siw/siw_cm.h