cregit-Linux how code gets into the kernel

Release 4.14 net/rds/ib_cm.c

Directory: net/rds
/*
 * Copyright (c) 2006 Oracle.  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/in.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/ratelimit.h>

#include "rds_single_path.h"
#include "rds.h"
#include "ib.h"

/*
 * Set the selected protocol version
 */



static void rds_ib_set_protocol(struct rds_connection *conn, unsigned int version)
{
	conn->c_version = version;
}


Contributors
PersonTokensPropCommitsCommitProp
Andy Grover21100.00%1100.00%


Total21100.00%1100.00%



/*
 * Set up flow control
 */



static void rds_ib_set_flow_control(struct rds_connection *conn, u32 credits)
{
	struct rds_ib_connection *ic = conn->c_transport_data;

	if (rds_ib_sysctl_flow_control && credits != 0) {
		/* We're doing flow control */
		ic->i_flowctl = 1;
		rds_ib_send_add_credits(conn, credits);
	} else {
		ic->i_flowctl = 0;
	}
}


Contributors
PersonTokensPropCommitsCommitProp
Andy Grover56100.00%1100.00%


Total56100.00%1100.00%



/*
 * Tune RNR behavior. Without flow control, we use a rather
 * low timeout, but not the absolute minimum - this should
 * be tunable.
 *
 * We already set the RNR retry count to 7 (which is the
 * smallest infinite number :-) above.
 * If flow control is off, we want to change this back to 0
 * so that we learn quickly when our credit accounting is
 * buggy.
 *
 * Caller passes in a qp_attr pointer - don't waste stack spacv
 * by allocation this twice.
 */


static void

rds_ib_tune_rnr(struct rds_ib_connection *ic, struct ib_qp_attr *attr)
{
	int ret;

	attr->min_rnr_timer = IB_RNR_TIMER_000_32;
	ret = ib_modify_qp(ic->i_cm_id->qp, attr, IB_QP_MIN_RNR_TIMER);
	if (ret)
		printk(KERN_NOTICE "ib_modify_qp(IB_QP_MIN_RNR_TIMER): err=%d\n", -ret);
}


Contributors
PersonTokensPropCommitsCommitProp
Andy Grover53100.00%1100.00%


Total53100.00%1100.00%



/*
 * Connection established.
 * We get here for both outgoing and incoming connection.
 */



void rds_ib_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_event *event)
{
	const struct rds_ib_connect_private *dp = NULL;
	struct rds_ib_connection *ic = conn->c_transport_data;
	struct ib_qp_attr qp_attr;
	int err;

	if (event->param.conn.private_data_len >= sizeof(*dp)) {
		dp = event->param.conn.private_data;

		/* make sure it isn't empty data */
		if (dp->dp_protocol_major) {
			rds_ib_set_protocol(conn,
				RDS_PROTOCOL(dp->dp_protocol_major,
				dp->dp_protocol_minor));
			rds_ib_set_flow_control(conn, be32_to_cpu(dp->dp_credit));
		}
	}

	if (conn->c_version < RDS_PROTOCOL(3, 1)) {
		pr_notice("RDS/IB: Connection <%pI4,%pI4> version %u.%u no longer supported\n",
			  &conn->c_laddr, &conn->c_faddr,
			  RDS_PROTOCOL_MAJOR(conn->c_version),
			  RDS_PROTOCOL_MINOR(conn->c_version));
		rds_conn_destroy(conn);
		return;
	} else {
		pr_notice("RDS/IB: %s conn connected <%pI4,%pI4> version %u.%u%s\n",
			  ic->i_active_side ? "Active" : "Passive",
			  &conn->c_laddr, &conn->c_faddr,
			  RDS_PROTOCOL_MAJOR(conn->c_version),
			  RDS_PROTOCOL_MINOR(conn->c_version),
			  ic->i_flowctl ? ", flow control" : "");
	}

	atomic_set(&ic->i_cq_quiesce, 0);

	/* Init rings and fill recv. this needs to wait until protocol
         * negotiation is complete, since ring layout is different
         * from 3.1 to 4.1.
         */
	rds_ib_send_init_ring(ic);
	rds_ib_recv_init_ring(ic);
	/* Post receive buffers - as a side effect, this will update
         * the posted credit count. */
	rds_ib_recv_refill(conn, 1, GFP_KERNEL);

	/* Tune RNR behavior */
	rds_ib_tune_rnr(ic, &qp_attr);

	qp_attr.qp_state = IB_QPS_RTS;
	err = ib_modify_qp(ic->i_cm_id->qp, &qp_attr, IB_QP_STATE);
	if (err)
		printk(KERN_NOTICE "ib_modify_qp(IB_QP_STATE, RTS): err=%d\n", err);

	/* update ib_device with this local ipaddr */
	err = rds_ib_update_ipaddr(ic->rds_ibdev, conn->c_laddr);
	if (err)
		printk(KERN_ERR "rds_ib_update_ipaddr failed (%d)\n",
			err);

	/* If the peer gave us the last packet it saw, process this as if
         * we had received a regular ACK. */
	if (dp) {
		/* dp structure start is not guaranteed to be 8 bytes aligned.
                 * Since dp_ack_seq is 64-bit extended load operations can be
                 * used so go through get_unaligned to avoid unaligned errors.
                 */
		__be64 dp_ack_seq = get_unaligned(&dp->dp_ack_seq);

		if (dp_ack_seq)
			rds_send_drop_acked(conn, be64_to_cpu(dp_ack_seq),
					    NULL);
	}

	rds_connect_complete(conn);
}


Contributors
PersonTokensPropCommitsCommitProp
Andy Grover28984.50%646.15%


Santosh Shilimkar3510.23%430.77%


shamir rabinovitch144.09%17.69%


Zach Brown30.88%17.69%


David Ahern10.29%17.69%


Total342100.00%13100.00%






static void rds_ib_cm_fill_conn_param(struct rds_connection *conn,
			struct rdma_conn_param *conn_param,
			struct rds_ib_connect_private *dp,
			u32 protocol_version,
			u32 max_responder_resources,
			u32 max_initiator_depth)
{
	struct rds_ib_connection *ic = conn->c_transport_data;
	struct rds_ib_device *rds_ibdev = ic->rds_ibdev;

	memset(conn_param, 0, sizeof(struct rdma_conn_param));

	conn_param->responder_resources =
		min_t(u32, rds_ibdev->max_responder_resources, max_responder_resources);
	conn_param->initiator_depth =
		min_t(u32, rds_ibdev->max_initiator_depth, max_initiator_depth);
	conn_param->retry_count = min_t(unsigned int, rds_ib_retry_count, 7);
	conn_param->rnr_retry_count = 7;

	if (dp) {
		memset(dp, 0, sizeof(*dp));
		dp->dp_saddr = conn->c_laddr;
		dp->dp_daddr = conn->c_faddr;
		dp->dp_protocol_major = RDS_PROTOCOL_MAJOR(protocol_version);
		dp->dp_protocol_minor = RDS_PROTOCOL_MINOR(protocol_version);
		dp->dp_protocol_minor_mask = cpu_to_be16(RDS_IB_SUPPORTED_PROTOCOLS);
		dp->dp_ack_seq = cpu_to_be64(rds_ib_piggyb_ack(ic));

		/* Advertise flow control */
		if (ic->i_flowctl) {
			unsigned int credits;

			credits = IB_GET_POST_CREDITS(atomic_read(&ic->i_credits));
			dp->dp_credit = cpu_to_be32(credits);
			atomic_sub(IB_SET_POST_CREDITS(credits), &ic->i_credits);
		}

		conn_param->private_data = dp;
		conn_param->private_data_len = sizeof(*dp);
	}
}


Contributors
PersonTokensPropCommitsCommitProp
Andy Grover24197.18%360.00%


Zach Brown41.61%120.00%


Qing Huang31.21%120.00%


Total248100.00%5100.00%






static void rds_ib_cq_event_handler(struct ib_event *event, void *data)
{
	rdsdebug("event %u (%s) data %p\n",
		 event->event, ib_event_msg(event->event), data);
}


Contributors
PersonTokensPropCommitsCommitProp
Andy Grover2575.76%133.33%


Zach Brown721.21%133.33%


Sagi Grimberg13.03%133.33%


Total33100.00%3100.00%



/* Plucking the oldest entry from the ring can be done concurrently with
 * the thread refilling the ring.  Each ring operation is protected by
 * spinlocks and the transient state of refilling doesn't change the
 * recording of which entry is oldest.
 *
 * This relies on IB only calling one cq comp_handler for each cq so that
 * there will only be one caller of rds_recv_incoming() per RDS connection.
 */



static void rds_ib_cq_comp_handler_recv(struct ib_cq *cq, void *context)
{
	struct rds_connection *conn = context;
	struct rds_ib_connection *ic = conn->c_transport_data;

	rdsdebug("conn %p cq %p\n", conn, cq);

	rds_ib_stats_inc(s_ib_evt_handler_call);

	tasklet_schedule(&ic->i_recv_tasklet);
}


Contributors
PersonTokensPropCommitsCommitProp
Santosh Shilimkar53100.00%1100.00%


Total53100.00%1100.00%






static void poll_scq(struct rds_ib_connection *ic, struct ib_cq *cq,
		     struct ib_wc *wcs)
{
	int nr, i;
	struct ib_wc *wc;

	while ((nr = ib_poll_cq(cq, RDS_IB_WC_MAX, wcs)) > 0) {
		for (i = 0; i < nr; i++) {
			wc = wcs + i;
			rdsdebug("wc wr_id 0x%llx status %u byte_len %u imm_data %u\n",
				 (unsigned long long)wc->wr_id, wc->status,
				 wc->byte_len, be32_to_cpu(wc->ex.imm_data));

			if (wc->wr_id <= ic->i_send_ring.w_nr ||
			    wc->wr_id == RDS_IB_ACK_WR_ID)
				rds_ib_send_cqe_handler(ic, wc);
			else
				rds_ib_mr_cqe_handler(ic, wc);

		}
	}
}


Contributors
PersonTokensPropCommitsCommitProp
Santosh Shilimkar10980.74%375.00%


Avinash Repaka2619.26%125.00%


Total135100.00%4100.00%






static void rds_ib_tasklet_fn_send(unsigned long data)
{
	struct rds_ib_connection *ic = (struct rds_ib_connection *)data;
	struct rds_connection *conn = ic->conn;

	rds_ib_stats_inc(s_ib_tasklet_call);

	/* if cq has been already reaped, ignore incoming cq event */
	if (atomic_read(&ic->i_cq_quiesce))
		return;

	poll_scq(ic, ic->i_send_cq, ic->i_send_wc);
	ib_req_notify_cq(ic->i_send_cq, IB_CQ_NEXT_COMP);
	poll_scq(ic, ic->i_send_cq, ic->i_send_wc);

	if (rds_conn_up(conn) &&
	    (!test_bit(RDS_LL_SEND_FULL, &conn->c_flags) ||
	    test_bit(0, &conn->c_map_queued)))
		rds_send_xmit(&ic->conn->c_path[0]);
}


Contributors
PersonTokensPropCommitsCommitProp
Santosh Shilimkar12095.24%375.00%


Sowmini Varadhan64.76%125.00%


Total126100.00%4100.00%






static void poll_rcq(struct rds_ib_connection *ic, struct ib_cq *cq,
		     struct ib_wc *wcs,
		     struct rds_ib_ack_state *ack_state)
{
	int nr, i;
	struct ib_wc *wc;

	while ((nr = ib_poll_cq(cq, RDS_IB_WC_MAX, wcs)) > 0) {
		for (i = 0; i < nr; i++) {
			wc = wcs + i;
			rdsdebug("wc wr_id 0x%llx status %u byte_len %u imm_data %u\n",
				 (unsigned long long)wc->wr_id, wc->status,
				 wc->byte_len, be32_to_cpu(wc->ex.imm_data));

			rds_ib_recv_cqe_handler(ic, wc, ack_state);
		}
	}
}


Contributors
PersonTokensPropCommitsCommitProp
Santosh Shilimkar116100.00%1100.00%


Total116100.00%1100.00%






static void rds_ib_tasklet_fn_recv(unsigned long data)
{
	struct rds_ib_connection *ic = (struct rds_ib_connection *)data;
	struct rds_connection *conn = ic->conn;
	struct rds_ib_device *rds_ibdev = ic->rds_ibdev;
	struct rds_ib_ack_state state;

	if (!rds_ibdev)
		rds_conn_drop(conn);

	rds_ib_stats_inc(s_ib_tasklet_call);

	/* if cq has been already reaped, ignore incoming cq event */
	if (atomic_read(&ic->i_cq_quiesce))
		return;

	memset(&state, 0, sizeof(state));
	poll_rcq(ic, ic->i_recv_cq, ic->i_recv_wc, &state);
	ib_req_notify_cq(ic->i_recv_cq, IB_CQ_SOLICITED);
	poll_rcq(ic, ic->i_recv_cq, ic->i_recv_wc, &state);

	if (state.ack_next_valid)
		rds_ib_set_ack(ic, state.ack_next, state.ack_required);
	if (state.ack_recv_valid && state.ack_recv > ic->i_ack_recv) {
		rds_send_drop_acked(conn, state.ack_recv, NULL);
		ic->i_ack_recv = state.ack_recv;
	}

	if (rds_conn_up(conn))
		rds_ib_attempt_ack(ic);
}


Contributors
PersonTokensPropCommitsCommitProp
Santosh Shilimkar191100.00%4100.00%


Total191100.00%4100.00%






static void rds_ib_qp_event_handler(struct ib_event *event, void *data)
{
	struct rds_connection *conn = data;
	struct rds_ib_connection *ic = conn->c_transport_data;

	rdsdebug("conn %p ic %p event %u (%s)\n", conn, ic, event->event,
		 ib_event_msg(event->event));

	switch (event->event) {
	case IB_EVENT_COMM_EST:
		rdma_notify(ic->i_cm_id, IB_EVENT_COMM_EST);
		break;
	default:
		rdsdebug("Fatal QP Event %u (%s) "
			"- connection %pI4->%pI4, reconnecting\n",
			event->event, ib_event_msg(event->event),
			&conn->c_laddr, &conn->c_faddr);
		rds_conn_drop(conn);
		break;
	}
}


Contributors
PersonTokensPropCommitsCommitProp
Andy Grover9084.91%360.00%


Zach Brown1413.21%120.00%


Sagi Grimberg21.89%120.00%


Total106100.00%5100.00%






static void rds_ib_cq_comp_handler_send(struct ib_cq *cq, void *context)
{
	struct rds_connection *conn = context;
	struct rds_ib_connection *ic = conn->c_transport_data;

	rdsdebug("conn %p cq %p\n", conn, cq);

	rds_ib_stats_inc(s_ib_evt_handler_call);

	tasklet_schedule(&ic->i_send_tasklet);
}


Contributors
PersonTokensPropCommitsCommitProp
Santosh Shilimkar53100.00%1100.00%


Total53100.00%1100.00%






static inline int ibdev_get_unused_vector(struct rds_ib_device *rds_ibdev)
{
	int min = rds_ibdev->vector_load[rds_ibdev->dev->num_comp_vectors - 1];
	int index = rds_ibdev->dev->num_comp_vectors - 1;
	int i;

	for (i = rds_ibdev->dev->num_comp_vectors - 1; i >= 0; i--) {
		if (rds_ibdev->vector_load[i] < min) {
			index = i;
			min = rds_ibdev->vector_load[i];
		}
	}

	rds_ibdev->vector_load[index]++;
	return index;
}


Contributors
PersonTokensPropCommitsCommitProp
Santosh Shilimkar100100.00%1100.00%


Total100100.00%1100.00%






static inline void ibdev_put_vector(struct rds_ib_device *rds_ibdev, int index)
{
	rds_ibdev->vector_load[index]--;
}


Contributors
PersonTokensPropCommitsCommitProp
Santosh Shilimkar23100.00%1100.00%


Total23100.00%1100.00%



/*
 * This needs to be very careful to not leave IS_ERR pointers around for
 * cleanup to trip over.
 */



static int rds_ib_setup_qp(struct rds_connection *conn)
{
	struct rds_ib_connection *ic = conn->c_transport_data;
	struct ib_device *dev = ic->i_cm_id->device;
	struct ib_qp_init_attr attr;
	struct ib_cq_init_attr cq_attr = {};
	struct rds_ib_device *rds_ibdev;
	int ret, fr_queue_space;

	/*
         * It's normal to see a null device if an incoming connection races
         * with device removal, so we don't print a warning.
         */
	rds_ibdev = rds_ib_get_client_data(dev);
	if (!rds_ibdev)
		return -EOPNOTSUPP;

	/* The fr_queue_space is currently set to 512, to add extra space on
         * completion queue and send queue. This extra space is used for FRMR
         * registration and invalidation work requests
         */
	fr_queue_space = rds_ibdev->use_fastreg ?
			 (RDS_IB_DEFAULT_FR_WR + 1) +
			 (RDS_IB_DEFAULT_FR_INV_WR + 1)
			 : 0;

	/* add the conn now so that connection establishment has the dev */
	rds_ib_add_conn(rds_ibdev, conn);

	if (rds_ibdev->max_wrs < ic->i_send_ring.w_nr + 1)
		rds_ib_ring_resize(&ic->i_send_ring, rds_ibdev->max_wrs - 1);
	if (rds_ibdev->max_wrs < ic->i_recv_ring.w_nr + 1)
		rds_ib_ring_resize(&ic->i_recv_ring, rds_ibdev->max_wrs - 1);

	/* Protection domain and memory range */
	ic->i_pd = rds_ibdev->pd;

	ic->i_scq_vector = ibdev_get_unused_vector(rds_ibdev);
	cq_attr.cqe = ic->i_send_ring.w_nr + fr_queue_space + 1;
	cq_attr.comp_vector = ic->i_scq_vector;
	ic->i_send_cq = ib_create_cq(dev, rds_ib_cq_comp_handler_send,
				     rds_ib_cq_event_handler, conn,
				     &cq_attr);
	if (IS_ERR(ic->i_send_cq)) {
		ret = PTR_ERR(ic->i_send_cq);
		ic->i_send_cq = NULL;
		ibdev_put_vector(rds_ibdev, ic->i_scq_vector);
		rdsdebug("ib_create_cq send failed: %d\n", ret);
		goto rds_ibdev_out;
	}

	ic->i_rcq_vector = ibdev_get_unused_vector(rds_ibdev);
	cq_attr.cqe = ic->i_recv_ring.w_nr;
	cq_attr.comp_vector = ic->i_rcq_vector;
	ic->i_recv_cq = ib_create_cq(dev, rds_ib_cq_comp_handler_recv,
				     rds_ib_cq_event_handler, conn,
				     &cq_attr);
	if (IS_ERR(ic->i_recv_cq)) {
		ret = PTR_ERR(ic->i_recv_cq);
		ic->i_recv_cq = NULL;
		ibdev_put_vector(rds_ibdev, ic->i_rcq_vector);
		rdsdebug("ib_create_cq recv failed: %d\n", ret);
		goto send_cq_out;
	}

	ret = ib_req_notify_cq(ic->i_send_cq, IB_CQ_NEXT_COMP);
	if (ret) {
		rdsdebug("ib_req_notify_cq send failed: %d\n", ret);
		goto recv_cq_out;
	}

	ret = ib_req_notify_cq(ic->i_recv_cq, IB_CQ_SOLICITED);
	if (ret) {
		rdsdebug("ib_req_notify_cq recv failed: %d\n", ret);
		goto recv_cq_out;
	}

	/* XXX negotiate max send/recv with remote? */
	memset(&attr, 0, sizeof(attr));
	attr.event_handler = rds_ib_qp_event_handler;
	attr.qp_context = conn;
	/* + 1 to allow for the single ack message */
	attr.cap.max_send_wr = ic->i_send_ring.w_nr + fr_queue_space + 1;
	attr.cap.max_recv_wr = ic->i_recv_ring.w_nr + 1;
	attr.cap.max_send_sge = rds_ibdev->max_sge;
	attr.cap.max_recv_sge = RDS_IB_RECV_SGE;
	attr.sq_sig_type = IB_SIGNAL_REQ_WR;
	attr.qp_type = IB_QPT_RC;
	attr.send_cq = ic->i_send_cq;
	attr.recv_cq = ic->i_recv_cq;
	atomic_set(&ic->i_fastreg_wrs, RDS_IB_DEFAULT_FR_WR);
	atomic_set(&ic->i_fastunreg_wrs, RDS_IB_DEFAULT_FR_INV_WR);

	/*
         * XXX this can fail if max_*_wr is too large?  Are we supposed
         * to back off until we get a value that the hardware can support?
         */
	ret = rdma_create_qp(ic->i_cm_id, ic->i_pd, &attr);
	if (ret) {
		rdsdebug("rdma_create_qp failed: %d\n", ret);
		goto recv_cq_out;
	}

	ic->i_send_hdrs = ib_dma_alloc_coherent(dev,
					   ic->i_send_ring.w_nr *
						sizeof(struct rds_header),
					   &ic->i_send_hdrs_dma, GFP_KERNEL);
	if (!ic->i_send_hdrs) {
		ret = -ENOMEM;
		rdsdebug("ib_dma_alloc_coherent send failed\n");
		goto qp_out;
	}

	ic->i_recv_hdrs = ib_dma_alloc_coherent(dev,
					   ic->i_recv_ring.w_nr *
						sizeof(struct rds_header),
					   &ic->i_recv_hdrs_dma, GFP_KERNEL);
	if (!ic->i_recv_hdrs) {
		ret = -ENOMEM;
		rdsdebug("ib_dma_alloc_coherent recv failed\n");
		goto send_hdrs_dma_out;
	}

	ic->i_ack = ib_dma_alloc_coherent(dev, sizeof(struct rds_header),
				       &ic->i_ack_dma, GFP_KERNEL);
	if (!ic->i_ack) {
		ret = -ENOMEM;
		rdsdebug("ib_dma_alloc_coherent ack failed\n");
		goto recv_hdrs_dma_out;
	}

	ic->i_sends = vzalloc_node(ic->i_send_ring.w_nr * sizeof(struct rds_ib_send_work),
				   ibdev_to_node(dev));
	if (!ic->i_sends) {
		ret = -ENOMEM;
		rdsdebug("send allocation failed\n");
		goto ack_dma_out;
	}

	ic->i_recvs = vzalloc_node(ic->i_recv_ring.w_nr * sizeof(struct rds_ib_recv_work),
				   ibdev_to_node(dev));
	if (!ic->i_recvs) {
		ret = -ENOMEM;
		rdsdebug("recv allocation failed\n");
		goto sends_out;
	}

	rds_ib_recv_init_ack(ic);

	rdsdebug("conn %p pd %p cq %p %p\n", conn, ic->i_pd,
		 ic->i_send_cq, ic->i_recv_cq);

	return ret;

sends_out:
	vfree(ic->i_sends);
ack_dma_out:
	ib_dma_free_coherent(dev, sizeof(struct rds_header),
			     ic->i_ack, ic->i_ack_dma);
recv_hdrs_dma_out:
	ib_dma_free_coherent(dev, ic->i_recv_ring.w_nr *
					sizeof(struct rds_header),
					ic->i_recv_hdrs, ic->i_recv_hdrs_dma);
send_hdrs_dma_out:
	ib_dma_free_coherent(dev, ic->i_send_ring.w_nr *
					sizeof(struct rds_header),
					ic->i_send_hdrs, ic->i_send_hdrs_dma);
qp_out:
	rdma_destroy_qp(ic->i_cm_id);
recv_cq_out:
	if (!ib_destroy_cq(ic->i_recv_cq))
		ic->i_recv_cq = NULL;
send_cq_out:
	if (!ib_destroy_cq(ic->i_send_cq))
		ic->i_send_cq = NULL;
rds_ibdev_out:
	rds_ib_remove_conn(rds_ibdev, conn);
	rds_ib_dev_put(rds_ibdev);

	return ret;
}


Contributors
PersonTokensPropCommitsCommitProp
Andy Grover66468.81%323.08%


Zhu Yanjun15015.54%17.69%


Santosh Shilimkar10110.47%538.46%


Matan Barak323.32%17.69%


Zach Brown151.55%17.69%


Joe Perches20.21%17.69%


Jason Gunthorpe10.10%17.69%


Total965100.00%13100.00%






static u32 rds_ib_protocol_compatible(struct rdma_cm_event *event)
{
	const struct rds_ib_connect_private *dp = event->param.conn.private_data;
	u16 common;
	u32 version = 0;

	/*
         * rdma_cm private data is odd - when there is any private data in the
         * request, we will be given a pretty large buffer without telling us the
         * original size. The only way to tell the difference is by looking at
         * the contents, which are initialized to zero.
         * If the protocol version fields aren't set, this is a connection attempt
         * from an older version. This could could be 3.0 or 2.0 - we can't tell.
         * We really should have changed this for OFED 1.3 :-(
         */

	/* Be paranoid. RDS always has privdata */
	if (!event->param.conn.private_data_len) {
		printk(KERN_NOTICE "RDS incoming connection has no private data, "
			"rejecting\n");
		return 0;
	}

	/* Even if len is crap *now* I still want to check it. -ASG */
	if (event->param.conn.private_data_len < sizeof (*dp) ||
	    dp->dp_protocol_major == 0)
		return RDS_PROTOCOL_3_0;

	common = be16_to_cpu(dp->dp_protocol_minor_mask) & RDS_IB_SUPPORTED_PROTOCOLS;
	if (dp->dp_protocol_major == 3 && common) {
		version = RDS_PROTOCOL_3_0;
		while ((common >>= 1) != 0)
			version++;
	} else
		printk_ratelimited(KERN_NOTICE "RDS: Connection from %pI4 using incompatible protocol version %u.%u\n",
				&dp->dp_saddr,
				dp->dp_protocol_major,
				dp->dp_protocol_minor);
	return version;
}


Contributors
PersonTokensPropCommitsCommitProp
Andy Grover14497.96%250.00%


Mike Marciniszyn21.36%125.00%


Manuel Zerpies10.68%125.00%


Total147100.00%4100.00%






int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id,
				    struct rdma_cm_event *event)
{
	__be64 lguid = cm_id->route.path_rec->sgid.global.interface_id;
	__be64 fguid = cm_id->route.path_rec->dgid.global.interface_id;
	const struct rds_ib_connect_private *dp = event->param.conn.private_data;
	struct rds_ib_connect_private dp_rep;
	struct rds_connection *conn = NULL;
	struct rds_ib_connection *ic = NULL;
	struct rdma_conn_param conn_param;
	u32 version;
	int err = 1, destroy = 1;

	/* Check whether the remote protocol version matches ours. */
	version = rds_ib_protocol_compatible(event);
	if (!version)
		goto out;

	rdsdebug("saddr %pI4 daddr %pI4 RDSv%u.%u lguid 0x%llx fguid "
		 "0x%llx\n", &dp->dp_saddr, &dp->dp_daddr,
		 RDS_PROTOCOL_MAJOR(version), RDS_PROTOCOL_MINOR(version),
		 (unsigned long long)be64_to_cpu(lguid),
		 (unsigned long long)be64_to_cpu(fguid));

	/* RDS/IB is not currently netns aware, thus init_net */
	conn = rds_conn_create(&init_net, dp->dp_daddr, dp->dp_saddr,
			       &rds_ib_transport, GFP_KERNEL);
	if (IS_ERR(conn)) {
		rdsdebug("rds_conn_create failed (%ld)\n", PTR_ERR(conn));
		conn = NULL;
		goto out;
	}

	/*
         * The connection request may occur while the
         * previous connection exist, e.g. in case of failover.
         * But as connections may be initiated simultaneously
         * by both hosts, we have a random backoff mechanism -
         * see the comment above rds_queue_reconnect()
         */
	mutex_lock(&conn->c_cm_lock);
	if (!rds_conn_transition(conn, RDS_CONN_DOWN, RDS_CONN_CONNECTING)) {
		if (rds_conn_state(conn) == RDS_CONN_UP) {
			rdsdebug("incoming connect while connecting\n");
			rds_conn_drop(conn);
			rds_ib_stats_inc(s_ib_listen_closed_stale);
		} else
		if (rds_conn_state(conn) == RDS_CONN_CONNECTING) {
			/* Wait and see - our connect may still be succeeding */
			rds_ib_stats_inc(s_ib_connect_raced);
		}
		goto out;
	}

	ic = conn->c_transport_data;

	rds_ib_set_protocol(conn, version);
	rds_ib_set_flow_control(conn, be32_to_cpu(dp->dp_credit));

	/* If the peer gave us the last packet it saw, process this as if
         * we had received a regular ACK. */
	if (dp->dp_ack_seq)
		rds_send_drop_acked(