ipoib_multicast.c

linux-2.6.15.6

/*
 * Copyright (c) 2004, 2005 Topspin Communications.  All rights reserved.
 * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved.
 * Copyright (c) 2004 Voltaire, Inc. All rights reserved.
 *
 * This software is available to you under a choice of one of two
 * licenses.  You may choose to be licensed under the terms of the GNU
 * General Public License (GPL) Version 2, available from the file
 * COPYING in the main directory of this source tree, or the
 * OpenIB.org BSD license below:
 *
 *     Redistribution and use in source and binary forms, with or
 *     without modification, are permitted provided that the following
 *     conditions are met:
 *
 *      - Redistributions of source code must retain the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer.
 *
 *      - Redistributions in binary form must reproduce the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer in the documentation and/or other materials
 *        provided with the distribution.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
 * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
 * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
 * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 * SOFTWARE.
 *
 * $Id: ipoib_multicast.c 1362 2004-12-18 15:56:29Z roland $
 */

#include <linux/skbuff.h>
#include <linux/rtnetlink.h>
#include <linux/ip.h>
#include <linux/in.h>
#include <linux/igmp.h>
#include <linux/inetdevice.h>
#include <linux/delay.h>
#include <linux/completion.h>

#include "ipoib.h"

#ifdef CONFIG_INFINIBAND_IPOIB_DEBUG
static int mcast_debug_level;

module_param(mcast_debug_level, int, 0644);
MODULE_PARM_DESC(mcast_debug_level,
		 "Enable multicast debug tracing if > 0");
#endif

static DECLARE_MUTEX(mcast_mutex);

/* Used for all multicast joins (broadcast, IPv4 mcast and IPv6 mcast) */
struct ipoib_mcast {
	struct ib_sa_mcmember_rec mcmember;
	struct ipoib_ah          *ah;

	struct rb_node    rb_node;
	struct list_head  list;
	struct completion done;

	int                 query_id;
	struct ib_sa_query *query;

	unsigned long created;
	unsigned long backoff;

	unsigned long flags;
	unsigned char logcount;

	struct list_head  neigh_list;

	struct sk_buff_head pkt_queue;

	struct net_device *dev;
};

struct ipoib_mcast_iter {
	struct net_device *dev;
	union ib_gid       mgid;
	unsigned long      created;
	unsigned int       queuelen;
	unsigned int       complete;
	unsigned int       send_only;
};

static void ipoib_mcast_free(struct ipoib_mcast *mcast)
{
	struct net_device *dev = mcast->dev;
	struct ipoib_dev_priv *priv = netdev_priv(dev);
	struct ipoib_neigh *neigh, *tmp;
	unsigned long flags;
	LIST_HEAD(ah_list);
	struct ipoib_ah *ah, *tah;

	ipoib_dbg_mcast(netdev_priv(dev),
			"deleting multicast group " IPOIB_GID_FMT "\n",
			IPOIB_GID_ARG(mcast->mcmember.mgid));

	spin_lock_irqsave(&priv->lock, flags);

	list_for_each_entry_safe(neigh, tmp, &mcast->neigh_list, list) {
		if (neigh->ah)
			list_add_tail(&neigh->ah->list, &ah_list);
		*to_ipoib_neigh(neigh->neighbour) = NULL;
		neigh->neighbour->ops->destructor = NULL;
		kfree(neigh);
	}

	spin_unlock_irqrestore(&priv->lock, flags);

	list_for_each_entry_safe(ah, tah, &ah_list, list)
		ipoib_put_ah(ah);

	if (mcast->ah)
		ipoib_put_ah(mcast->ah);

	while (!skb_queue_empty(&mcast->pkt_queue))
		dev_kfree_skb_any(skb_dequeue(&mcast->pkt_queue));

	kfree(mcast);
}

static struct ipoib_mcast *ipoib_mcast_alloc(struct net_device *dev,
					     int can_sleep)
{
	struct ipoib_mcast *mcast;

	mcast = kzalloc(sizeof *mcast, can_sleep ? GFP_KERNEL : GFP_ATOMIC);
	if (!mcast)
		return NULL;

	mcast->dev = dev;
	mcast->created = jiffies;
	mcast->backoff = 1;

	INIT_LIST_HEAD(&mcast->list);
	INIT_LIST_HEAD(&mcast->neigh_list);
	skb_queue_head_init(&mcast->pkt_queue);

	return mcast;
}

static struct ipoib_mcast *__ipoib_mcast_find(struct net_device *dev, union ib_gid *mgid)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);
	struct rb_node *n = priv->multicast_tree.rb_node;

	while (n) {
		struct ipoib_mcast *mcast;
		int ret;

		mcast = rb_entry(n, struct ipoib_mcast, rb_node);

		ret = memcmp(mgid->raw, mcast->mcmember.mgid.raw,
			     sizeof (union ib_gid));
		if (ret < 0)
			n = n->rb_left;
		else if (ret > 0)
			n = n->rb_right;
		else
			return mcast;
	}

	return NULL;
}

static int __ipoib_mcast_add(struct net_device *dev, struct ipoib_mcast *mcast)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);
	struct rb_node **n = &priv->multicast_tree.rb_node, *pn = NULL;

	while (*n) {
		struct ipoib_mcast *tmcast;
		int ret;

		pn = *n;
		tmcast = rb_entry(pn, struct ipoib_mcast, rb_node);

		ret = memcmp(mcast->mcmember.mgid.raw, tmcast->mcmember.mgid.raw,
			     sizeof (union ib_gid));
		if (ret < 0)
			n = &pn->rb_left;
		else if (ret > 0)
			n = &pn->rb_right;
		else
			return -EEXIST;
	}

	rb_link_node(&mcast->rb_node, pn, n);
	rb_insert_color(&mcast->rb_node, &priv->multicast_tree);

	return 0;
}

static int ipoib_mcast_join_finish(struct ipoib_mcast *mcast,
				   struct ib_sa_mcmember_rec *mcmember)
{
	struct net_device *dev = mcast->dev;
	struct ipoib_dev_priv *priv = netdev_priv(dev);
	int ret;

	mcast->mcmember = *mcmember;

	/* Set the cached Q_Key before we attach if it's the broadcast group */
	if (!memcmp(mcast->mcmember.mgid.raw, priv->dev->broadcast + 4,
		    sizeof (union ib_gid))) {
		priv->qkey = be32_to_cpu(priv->broadcast->mcmember.qkey);
		priv->tx_wr.wr.ud.remote_qkey = priv->qkey;
	}

	if (!test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags)) {
		if (test_and_set_bit(IPOIB_MCAST_FLAG_ATTACHED, &mcast->flags)) {
			ipoib_warn(priv, "multicast group " IPOIB_GID_FMT
				   " already attached\n",
				   IPOIB_GID_ARG(mcast->mcmember.mgid));

			return 0;
		}

		ret = ipoib_mcast_attach(dev, be16_to_cpu(mcast->mcmember.mlid),
					 &mcast->mcmember.mgid);
		if (ret < 0) {
			ipoib_warn(priv, "couldn't attach QP to multicast group "
				   IPOIB_GID_FMT "\n",
				   IPOIB_GID_ARG(mcast->mcmember.mgid));

			clear_bit(IPOIB_MCAST_FLAG_ATTACHED, &mcast->flags);
			return ret;
		}
	}

	{
		struct ib_ah_attr av = {
			.dlid	       = be16_to_cpu(mcast->mcmember.mlid),
			.port_num      = priv->port,
			.sl	       = mcast->mcmember.sl,
			.ah_flags      = IB_AH_GRH,
			.grh	       = {
				.flow_label    = be32_to_cpu(mcast->mcmember.flow_label),
				.hop_limit     = mcast->mcmember.hop_limit,
				.sgid_index    = 0,
				.traffic_class = mcast->mcmember.traffic_class
			}
		};
		int path_rate = ib_sa_rate_enum_to_int(mcast->mcmember.rate);

		av.grh.dgid = mcast->mcmember.mgid;

		if (path_rate > 0 && priv->local_rate > path_rate)
			av.static_rate = (priv->local_rate - 1) / path_rate;

		ipoib_dbg_mcast(priv, "static_rate %d for local port %dX, mcmember %dX\n",
				av.static_rate, priv->local_rate,
				ib_sa_rate_enum_to_int(mcast->mcmember.rate));

		mcast->ah = ipoib_create_ah(dev, priv->pd, &av);
		if (!mcast->ah) {
			ipoib_warn(priv, "ib_address_create failed\n");
		} else {
			ipoib_dbg_mcast(priv, "MGID " IPOIB_GID_FMT
					" AV %p, LID 0x%04x, SL %d\n",
					IPOIB_GID_ARG(mcast->mcmember.mgid),
					mcast->ah->ah,
					be16_to_cpu(mcast->mcmember.mlid),
					mcast->mcmember.sl);
		}
	}

	/* actually send any queued packets */
	while (!skb_queue_empty(&mcast->pkt_queue)) {
		struct sk_buff *skb = skb_dequeue(&mcast->pkt_queue);

		skb->dev = dev;

		if (!skb->dst || !skb->dst->neighbour) {
			/* put pseudoheader back on for next time */
			skb_push(skb, sizeof (struct ipoib_pseudoheader));
		}

		if (dev_queue_xmit(skb))
			ipoib_warn(priv, "dev_queue_xmit failed to requeue packet\n");
	}

	return 0;
}

static void
ipoib_mcast_sendonly_join_complete(int status,
				   struct ib_sa_mcmember_rec *mcmember,
				   void *mcast_ptr)
{
	struct ipoib_mcast *mcast = mcast_ptr;
	struct net_device *dev = mcast->dev;

	if (!status)
		ipoib_mcast_join_finish(mcast, mcmember);
	else {
		if (mcast->logcount++ < 20)
			ipoib_dbg_mcast(netdev_priv(dev), "multicast join failed for "
					IPOIB_GID_FMT ", status %d\n",
					IPOIB_GID_ARG(mcast->mcmember.mgid), status);

		/* Flush out any queued packets */
		while (!skb_queue_empty(&mcast->pkt_queue))
			dev_kfree_skb_any(skb_dequeue(&mcast->pkt_queue));

		/* Clear the busy flag so we try again */
		clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);
	}

	complete(&mcast->done);
}

static int ipoib_mcast_sendonly_join(struct ipoib_mcast *mcast)
{
	struct net_device *dev = mcast->dev;
	struct ipoib_dev_priv *priv = netdev_priv(dev);
	struct ib_sa_mcmember_rec rec = {
#if 0				/* Some SMs don't support send-only yet */
		.join_state = 4
#else
		.join_state = 1
#endif
	};
	int ret = 0;

	if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags)) {
		ipoib_dbg_mcast(priv, "device shutting down, no multicast joins\n");
		return -ENODEV;
	}

	if (test_and_set_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags)) {
		ipoib_dbg_mcast(priv, "multicast entry busy, skipping\n");
		return -EBUSY;
	}

	rec.mgid     = mcast->mcmember.mgid;
	rec.port_gid = priv->local_gid;
	rec.pkey     = cpu_to_be16(priv->pkey);

	init_completion(&mcast->done);

	ret = ib_sa_mcmember_rec_set(priv->ca, priv->port, &rec,
				     IB_SA_MCMEMBER_REC_MGID		|
				     IB_SA_MCMEMBER_REC_PORT_GID	|
				     IB_SA_MCMEMBER_REC_PKEY		|
				     IB_SA_MCMEMBER_REC_JOIN_STATE,
				     1000, GFP_ATOMIC,
				     ipoib_mcast_sendonly_join_complete,
				     mcast, &mcast->query);
	if (ret < 0) {
		ipoib_warn(priv, "ib_sa_mcmember_rec_set failed (ret = %d)\n",
			   ret);
	} else {
		ipoib_dbg_mcast(priv, "no multicast record for " IPOIB_GID_FMT
				", starting join\n",
				IPOIB_GID_ARG(mcast->mcmember.mgid));

		mcast->query_id = ret;
	}

	return ret;
}

static void ipoib_mcast_join_complete(int status,
				      struct ib_sa_mcmember_rec *mcmember,
				      void *mcast_ptr)
{
	struct ipoib_mcast *mcast = mcast_ptr;
	struct net_device *dev = mcast->dev;
	struct ipoib_dev_priv *priv = netdev_priv(dev);

	ipoib_dbg_mcast(priv, "join completion for " IPOIB_GID_FMT
			" (status %d)\n",
			IPOIB_GID_ARG(mcast->mcmember.mgid), status);

	if (!status && !ipoib_mcast_join_finish(mcast, mcmember)) {
		mcast->backoff = 1;
		down(&mcast_mutex);
		if (test_bit(IPOIB_MCAST_RUN, &priv->flags))
			queue_work(ipoib_workqueue, &priv->mcast_task);
		up(&mcast_mutex);
		complete(&mcast->done);
		return;
	}

	if (status == -EINTR) {
		complete(&mcast->done);
		return;
	}

	if (status && mcast->logcount++ < 20) {
		if (status == -ETIMEDOUT || status == -EINTR) {
			ipoib_dbg_mcast(priv, "multicast join failed for " IPOIB_GID_FMT
					", status %d\n",
					IPOIB_GID_ARG(mcast->mcmember.mgid),
					status);
		} else {
			ipoib_warn(priv, "multicast join failed for "
				   IPOIB_GID_FMT ", status %d\n",
				   IPOIB_GID_ARG(mcast->mcmember.mgid),
				   status);
		}
	}

	mcast->backoff *= 2;
	if (mcast->backoff > IPOIB_MAX_BACKOFF_SECONDS)
		mcast->backoff = IPOIB_MAX_BACKOFF_SECONDS;

	mcast->query = NULL;

	down(&mcast_mutex);
	if (test_bit(IPOIB_MCAST_RUN, &priv->flags)) {
		if (status == -ETIMEDOUT)
			queue_work(ipoib_workqueue, &priv->mcast_task);
		else
			queue_delayed_work(ipoib_workqueue, &priv->mcast_task,
					   mcast->backoff * HZ);
	} else
		complete(&mcast->done);
	up(&mcast_mutex);

	return;
}

static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast,
			     int create)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);
	struct ib_sa_mcmember_rec rec = {
		.join_state = 1
	};
	ib_sa_comp_mask comp_mask;
	int ret = 0;

	ipoib_dbg_mcast(priv, "joining MGID " IPOIB_GID_FMT "\n",
			IPOIB_GID_ARG(mcast->mcmember.mgid));

	rec.mgid     = mcast->mcmember.mgid;
	rec.port_gid = priv->local_gid;
	rec.pkey     = cpu_to_be16(priv->pkey);

	comp_mask =
		IB_SA_MCMEMBER_REC_MGID		|
		IB_SA_MCMEMBER_REC_PORT_GID	|
		IB_SA_MCMEMBER_REC_PKEY		|
		IB_SA_MCMEMBER_REC_JOIN_STATE;

	if (create) {
		comp_mask |=
			IB_SA_MCMEMBER_REC_QKEY		|
			IB_SA_MCMEMBER_REC_SL		|
			IB_SA_MCMEMBER_REC_FLOW_LABEL	|
			IB_SA_MCMEMBER_REC_TRAFFIC_CLASS;

		rec.qkey	  = priv->broadcast->mcmember.qkey;
		rec.sl		  = priv->broadcast->mcmember.sl;
		rec.flow_label	  = priv->broadcast->mcmember.flow_label;
		rec.traffic_class = priv->broadcast->mcmember.traffic_class;
	}

	init_completion(&mcast->done);

	ret = ib_sa_mcmember_rec_set(priv->ca, priv->port, &rec, comp_mask,
				     mcast->backoff * 1000, GFP_ATOMIC,
				     ipoib_mcast_join_complete,
				     mcast, &mcast->query);

	if (ret < 0) {
		ipoib_warn(priv, "ib_sa_mcmember_rec_set failed, status %d\n", ret);

		mcast->backoff *= 2;
		if (mcast->backoff > IPOIB_MAX_BACKOFF_SECONDS)
			mcast->backoff = IPOIB_MAX_BACKOFF_SECONDS;

		down(&mcast_mutex);
		if (test_bit(IPOIB_MCAST_RUN, &priv->flags))
			queue_delayed_work(ipoib_workqueue,
					   &priv->mcast_task,
					   mcast->backoff * HZ);
		up(&mcast_mutex);
	} else
		mcast->query_id = ret;
}