[INFINIBAND]: Add IPoIB (IP-over-InfiniBand) driver

Add a driver that implements the (IPoIB) IP-over-InfiniBand protocol.
This is a network device driver of type ARPHRD_INFINIBAND (and
addr_len INFINIBAND_ALEN bytes).

The ARP/ND implementation for this driver is not completely
straightforward, because InfiniBand requires an additional path lookup
be performed (through an IB-specific mechanism) after a remote
hardware address has been resolved.  We are very open to suggestions
of a better way to handle this than the current implementation.

Although IB has a special multicast group join mode intended to
support IP multicast routing (non member join), no means to identify
different multicast styles has yet been determined, so all joins by
the driver are currently full member joins.  We are looking for
guidance in how to solve this.

The IPoIB protocol/encapsulation is described in the Internet-Drafts
  http://www.ietf.org/internet-drafts/draft-ietf-ipoib-architecture-04.txt
  http://www.ietf.org/internet-drafts/draft-ietf-ipoib-ip-over-infiniband-08.txtSigned-off-by: Roland Dreier <roland@topspin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/infiniband/Kconfig

@@ -9,4 +9,6 @@ config INFINIBAND
 
 source "drivers/infiniband/hw/mthca/Kconfig"
 
+source "drivers/infiniband/ulp/ipoib/Kconfig"
+
 endmenu

drivers/infiniband/Makefile

 obj-$(CONFIG_INFINIBAND)		+= core/
 obj-$(CONFIG_INFINIBAND_MTHCA)		+= hw/mthca/
+obj-$(CONFIG_INFINIBAND_IPOIB)		+= ulp/ipoib/

drivers/infiniband/ulp/ipoib/Kconfig

+config INFINIBAND_IPOIB
+	tristate "IP-over-InfiniBand"
+	depends on INFINIBAND && NETDEVICES && INET
+	---help---
+	  Support for the IP-over-InfiniBand protocol (IPoIB). This
+	  transports IP packets over InfiniBand so you can use your IB
+	  device as a fancy NIC.
+
+	  The IPoIB protocol is defined by the IETF ipoib working
+	  group: <http://www.ietf.org/html.charters/ipoib-charter.html>.
+
+config INFINIBAND_IPOIB_DEBUG
+	bool "IP-over-InfiniBand debugging"
+	depends on INFINIBAND_IPOIB
+	---help---
+	  This option causes debugging code to be compiled into the
+	  IPoIB driver.  The output can be turned on via the
+	  debug_level and mcast_debug_level module parameters (which
+	  can also be set after the driver is loaded through sysfs).
+
+	  This option also creates an "ipoib_debugfs," which can be
+	  mounted to expose debugging information about IB multicast
+	  groups used by the IPoIB driver.
+
+config INFINIBAND_IPOIB_DEBUG_DATA
+	bool "IP-over-InfiniBand data path debugging"
+	depends on INFINIBAND_IPOIB_DEBUG
+	---help---
+	  This option compiles debugging code into the the data path
+	  of the IPoIB driver.  The output can be turned on via the
+	  data_debug_level module parameter; however, even with output
+	  turned off, this debugging code will have some performance
+	  impact.

drivers/infiniband/ulp/ipoib/Makefile

+EXTRA_CFLAGS += -Idrivers/infiniband/include
+
+obj-$(CONFIG_INFINIBAND_IPOIB)			+= ib_ipoib.o
+
+ib_ipoib-y					:= ipoib_main.o \
+						   ipoib_ib.o \
+						   ipoib_multicast.o \
+						   ipoib_verbs.o \
+						   ipoib_vlan.o
+ib_ipoib-$(CONFIG_INFINIBAND_IPOIB_DEBUG)	+= ipoib_fs.o
+

drivers/infiniband/ulp/ipoib/ipoib_fs.c

+/*
+ * Copyright (c) 2004 Topspin Communications.  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_fs.c 1389 2004-12-27 22:56:47Z roland $
+ */
+
+#include <linux/pagemap.h>
+#include <linux/seq_file.h>
+
+#include "ipoib.h"
+
+enum {
+	IPOIB_MAGIC = 0x49504942 /* "IPIB" */
+};
+
+static DECLARE_MUTEX(ipoib_fs_mutex);
+static struct dentry *ipoib_root;
+static struct super_block *ipoib_sb;
+static LIST_HEAD(ipoib_device_list);
+
+static void *ipoib_mcg_seq_start(struct seq_file *file, loff_t *pos)
+{
+	struct ipoib_mcast_iter *iter;
+	loff_t n = *pos;
+
+	iter = ipoib_mcast_iter_init(file->private);
+	if (!iter)
+		return NULL;
+
+	while (n--) {
+		if (ipoib_mcast_iter_next(iter)) {
+			ipoib_mcast_iter_free(iter);
+			return NULL;
+		}
+	}
+
+	return iter;
+}
+
+static void *ipoib_mcg_seq_next(struct seq_file *file, void *iter_ptr,
+				   loff_t *pos)
+{
+	struct ipoib_mcast_iter *iter = iter_ptr;
+
+	(*pos)++;
+
+	if (ipoib_mcast_iter_next(iter)) {
+		ipoib_mcast_iter_free(iter);
+		return NULL;
+	}
+
+	return iter;
+}
+
+static void ipoib_mcg_seq_stop(struct seq_file *file, void *iter_ptr)
+{
+	/* nothing for now */
+}
+
+static int ipoib_mcg_seq_show(struct seq_file *file, void *iter_ptr)
+{
+	struct ipoib_mcast_iter *iter = iter_ptr;
+	char gid_buf[sizeof "ffff:ffff:ffff:ffff:ffff:ffff:ffff:ffff"];
+	union ib_gid mgid;
+	int i, n;
+	unsigned long created;
+	unsigned int queuelen, complete, send_only;
+
+	if (iter) {
+		ipoib_mcast_iter_read(iter, &mgid, &created, &queuelen,
+				      &complete, &send_only);
+
+		for (n = 0, i = 0; i < sizeof mgid / 2; ++i) {
+			n += sprintf(gid_buf + n, "%x",
+				     be16_to_cpu(((u16 *)mgid.raw)[i]));
+			if (i < sizeof mgid / 2 - 1)
+				gid_buf[n++] = ':';
+		}
+	}
+
+	seq_printf(file, "GID: %*s", -(1 + (int) sizeof gid_buf), gid_buf);
+
+	seq_printf(file,
+		   " created: %10ld queuelen: %4d complete: %d send_only: %d\n",
+		   created, queuelen, complete, send_only);
+
+	return 0;
+}
+
+static struct seq_operations ipoib_seq_ops = {
+	.start = ipoib_mcg_seq_start,
+	.next  = ipoib_mcg_seq_next,
+	.stop  = ipoib_mcg_seq_stop,
+	.show  = ipoib_mcg_seq_show,
+};
+
+static int ipoib_mcg_open(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq;
+	int ret;
+
+	ret = seq_open(file, &ipoib_seq_ops);
+	if (ret)
+		return ret;
+
+	seq = file->private_data;
+	seq->private = inode->u.generic_ip;
+
+	return 0;
+}
+
+static struct file_operations ipoib_fops = {
+	.owner   = THIS_MODULE,
+	.open    = ipoib_mcg_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = seq_release
+};
+
+static struct inode *ipoib_get_inode(void)
+{
+	struct inode *inode = new_inode(ipoib_sb);
+
+	if (inode) {
+		inode->i_mode 	 = S_IFREG | S_IRUGO;
+		inode->i_uid 	 = 0;
+		inode->i_gid 	 = 0;
+		inode->i_blksize = PAGE_CACHE_SIZE;
+		inode->i_blocks  = 0;
+		inode->i_atime 	 = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+		inode->i_fop     = &ipoib_fops;
+	}
+
+	return inode;
+}
+
+static int __ipoib_create_debug_file(struct net_device *dev)
+{
+	struct ipoib_dev_priv *priv = netdev_priv(dev);
+	struct dentry *dentry;
+	struct inode *inode;
+	char name[IFNAMSIZ + sizeof "_mcg"];
+
+	snprintf(name, sizeof name, "%s_mcg", dev->name);
+
+	dentry = d_alloc_name(ipoib_root, name);
+	if (!dentry)
+		return -ENOMEM;
+
+	inode = ipoib_get_inode();
+	if (!inode) {
+		dput(dentry);
+		return -ENOMEM;
+	}
+
+	inode->u.generic_ip = dev;
+	priv->mcg_dentry = dentry;
+
+	d_add(dentry, inode);
+
+	return 0;
+}
+
+int ipoib_create_debug_file(struct net_device *dev)
+{
+	struct ipoib_dev_priv *priv = netdev_priv(dev);
+
+	down(&ipoib_fs_mutex);
+
+	list_add_tail(&priv->fs_list, &ipoib_device_list);
+
+	if (!ipoib_sb) {
+		up(&ipoib_fs_mutex);
+		return 0;
+	}
+
+	up(&ipoib_fs_mutex);
+
+	return __ipoib_create_debug_file(dev);
+}
+
+void ipoib_delete_debug_file(struct net_device *dev)
+{
+	struct ipoib_dev_priv *priv = netdev_priv(dev);
+
+	down(&ipoib_fs_mutex);
+	list_del(&priv->fs_list);
+	if (!ipoib_sb) {
+		up(&ipoib_fs_mutex);
+		return;
+	}
+	up(&ipoib_fs_mutex);
+
+	if (priv->mcg_dentry) {
+		d_drop(priv->mcg_dentry);
+		simple_unlink(ipoib_root->d_inode, priv->mcg_dentry);
+	}
+}
+
+static int ipoib_fill_super(struct super_block *sb, void *data, int silent)
+{
+	static struct tree_descr ipoib_files[] = {
+		{ "" }
+	};
+	struct ipoib_dev_priv *priv;
+	int ret;
+
+	ret = simple_fill_super(sb, IPOIB_MAGIC, ipoib_files);
+	if (ret)
+		return ret;
+
+	ipoib_root = sb->s_root;
+
+	down(&ipoib_fs_mutex);
+
+	ipoib_sb = sb;
+
+	list_for_each_entry(priv, &ipoib_device_list, fs_list) {
+		ret = __ipoib_create_debug_file(priv->dev);
+		if (ret)
+			break;
+	}
+
+	up(&ipoib_fs_mutex);
+
+	return ret;
+}
+
+static struct super_block *ipoib_get_sb(struct file_system_type *fs_type,
+	int flags, const char *dev_name, void *data)
+{
+	return get_sb_single(fs_type, flags, data, ipoib_fill_super);
+}
+
+static void ipoib_kill_sb(struct super_block *sb)
+{
+	down(&ipoib_fs_mutex);
+	ipoib_sb = NULL;
+	up(&ipoib_fs_mutex);
+
+	kill_litter_super(sb);
+}
+
+static struct file_system_type ipoib_fs_type = {
+	.owner		= THIS_MODULE,
+	.name		= "ipoib_debugfs",
+	.get_sb		= ipoib_get_sb,
+	.kill_sb	= ipoib_kill_sb,
+};
+
+int ipoib_register_debugfs(void)
+{
+	return register_filesystem(&ipoib_fs_type);
+}
+
+void ipoib_unregister_debugfs(void)
+{
+	unregister_filesystem(&ipoib_fs_type);
+}

drivers/infiniband/ulp/ipoib/ipoib_verbs.c

+/*
+ * Copyright (c) 2004 Topspin Communications.  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_verbs.c 1349 2004-12-16 21:09:43Z roland $
+ */
+
+#include <ib_cache.h>
+
+#include "ipoib.h"
+
+int ipoib_mcast_attach(struct net_device *dev, u16 mlid, union ib_gid *mgid)
+{
+	struct ipoib_dev_priv *priv = netdev_priv(dev);
+	struct ib_qp_attr *qp_attr;
+	int attr_mask;
+	int ret;
+	u16 pkey_index;
+
+	ret = -ENOMEM;
+	qp_attr = kmalloc(sizeof *qp_attr, GFP_KERNEL);
+	if (!qp_attr)
+		goto out;
+
+	if (ib_cached_pkey_find(priv->ca, priv->port, priv->pkey, &pkey_index)) {
+		clear_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);
+		ret = -ENXIO;
+		goto out;
+	}
+	set_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);
+
+	/* set correct QKey for QP */
+	qp_attr->qkey = priv->qkey;
+	attr_mask = IB_QP_QKEY;
+	ret = ib_modify_qp(priv->qp, qp_attr, attr_mask);
+	if (ret) {
+		ipoib_warn(priv, "failed to modify QP, ret = %d\n", ret);
+		goto out;
+	}
+
+	/* attach QP to multicast group */
+	down(&priv->mcast_mutex);
+	ret = ib_attach_mcast(priv->qp, mgid, mlid);
+	up(&priv->mcast_mutex);
+	if (ret)
+		ipoib_warn(priv, "failed to attach to multicast group, ret = %d\n", ret);
+
+out:
+	kfree(qp_attr);
+	return ret;
+}
+
+int ipoib_mcast_detach(struct net_device *dev, u16 mlid, union ib_gid *mgid)
+{
+	struct ipoib_dev_priv *priv = netdev_priv(dev);
+	int ret;
+
+	down(&priv->mcast_mutex);
+	ret = ib_detach_mcast(priv->qp, mgid, mlid);
+	up(&priv->mcast_mutex);
+	if (ret)
+		ipoib_warn(priv, "ib_detach_mcast failed (result = %d)\n", ret);
+
+	return ret;
+}
+
+int ipoib_qp_create(struct net_device *dev)
+{
+	struct ipoib_dev_priv *priv = netdev_priv(dev);
+	int ret;
+	u16 pkey_index;
+	struct ib_qp_attr qp_attr;
+	int attr_mask;
+
+	/*
+	 * Search through the port P_Key table for the requested pkey value.
+	 * The port has to be assigned to the respective IB partition in
+	 * advance.
+	 */
+	ret = ib_cached_pkey_find(priv->ca, priv->port, priv->pkey, &pkey_index);
+	if (ret) {
+		clear_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);
+		return ret;
+	}
+	set_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);
+
+	qp_attr.qp_state = IB_QPS_INIT;
+	qp_attr.qkey = 0;
+	qp_attr.port_num = priv->port;
+	qp_attr.pkey_index = pkey_index;
+	attr_mask =
+	    IB_QP_QKEY |
+	    IB_QP_PORT |
+	    IB_QP_PKEY_INDEX |
+	    IB_QP_STATE;
+	ret = ib_modify_qp(priv->qp, &qp_attr, attr_mask);
+	if (ret) {
+		ipoib_warn(priv, "failed to modify QP to init, ret = %d\n", ret);
+		goto out_fail;
+	}
+
+	qp_attr.qp_state = IB_QPS_RTR;
+	/* Can't set this in a INIT->RTR transition */
+	attr_mask &= ~IB_QP_PORT;
+	ret = ib_modify_qp(priv->qp, &qp_attr, attr_mask);
+	if (ret) {
+		ipoib_warn(priv, "failed to modify QP to RTR, ret = %d\n", ret);
+		goto out_fail;
+	}
+
+	qp_attr.qp_state = IB_QPS_RTS;
+	qp_attr.sq_psn = 0;
+	attr_mask |= IB_QP_SQ_PSN;
+	attr_mask &= ~IB_QP_PKEY_INDEX;
+	ret = ib_modify_qp(priv->qp, &qp_attr, attr_mask);
+	if (ret) {
+		ipoib_warn(priv, "failed to modify QP to RTS, ret = %d\n", ret);
+		goto out_fail;
+	}
+
+	return 0;
+
+out_fail:
+	ib_destroy_qp(priv->qp);
+	priv->qp = NULL;
+
+	return -EINVAL;
+}
+
+int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca)
+{
+	struct ipoib_dev_priv *priv = netdev_priv(dev);
+	struct ib_qp_init_attr init_attr = {
+		.cap = {
+			.max_send_wr  = IPOIB_TX_RING_SIZE,
+			.max_recv_wr  = IPOIB_RX_RING_SIZE,
+			.max_send_sge = 1,
+			.max_recv_sge = 1
+		},
+		.sq_sig_type = IB_SIGNAL_ALL_WR,
+		.rq_sig_type = IB_SIGNAL_ALL_WR,
+		.qp_type     = IB_QPT_UD
+	};
+
+	priv->pd = ib_alloc_pd(priv->ca);
+	if (IS_ERR(priv->pd)) {
+		printk(KERN_WARNING "%s: failed to allocate PD\n", ca->name);
+		return -ENODEV;
+	}
+
+	priv->cq = ib_create_cq(priv->ca, ipoib_ib_completion, NULL, dev,
+				IPOIB_TX_RING_SIZE + IPOIB_RX_RING_SIZE + 1);
+	if (IS_ERR(priv->cq)) {
+		printk(KERN_WARNING "%s: failed to create CQ\n", ca->name);
+		goto out_free_pd;
+	}
+
+	if (ib_req_notify_cq(priv->cq, IB_CQ_NEXT_COMP))
+		goto out_free_cq;
+
+	priv->mr = ib_get_dma_mr(priv->pd, IB_ACCESS_LOCAL_WRITE);
+	if (IS_ERR(priv->mr)) {
+		printk(KERN_WARNING "%s: ib_reg_phys_mr failed\n", ca->name);
+		goto out_free_cq;
+	}
+
+	init_attr.send_cq = priv->cq;
+	init_attr.recv_cq = priv->cq,
+
+	priv->qp = ib_create_qp(priv->pd, &init_attr);
+	if (IS_ERR(priv->qp)) {
+		printk(KERN_WARNING "%s: failed to create QP\n", ca->name);
+		goto out_free_mr;
+	}
+
+	priv->dev->dev_addr[1] = (priv->qp->qp_num >> 16) & 0xff;
+	priv->dev->dev_addr[2] = (priv->qp->qp_num >>  8) & 0xff;
+	priv->dev->dev_addr[3] = (priv->qp->qp_num      ) & 0xff;
+
+	return 0;
+
+out_free_mr:
+	ib_dereg_mr(priv->mr);
+
+out_free_cq:
+	ib_destroy_cq(priv->cq);
+
+out_free_pd:
+	ib_dealloc_pd(priv->pd);
+	return -ENODEV;
+}
+
+void ipoib_transport_dev_cleanup(struct net_device *dev)
+{
+	struct ipoib_dev_priv *priv = netdev_priv(dev);
+
+	if (priv->qp) {
+		if (ib_destroy_qp(priv->qp))
+			ipoib_warn(priv, "ib_qp_destroy failed\n");
+
+		priv->qp = NULL;
+		clear_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);
+	}
+
+	if (ib_dereg_mr(priv->mr))
+		ipoib_warn(priv, "ib_dereg_mr failed\n");
+
+	if (ib_destroy_cq(priv->cq))
+		ipoib_warn(priv, "ib_cq_destroy failed\n");
+
+	if (ib_dealloc_pd(priv->pd))
+		ipoib_warn(priv, "ib_dealloc_pd failed\n");
+}
+
+void ipoib_event(struct ib_event_handler *handler,
+		 struct ib_event *record)
+{
+	struct ipoib_dev_priv *priv =
+		container_of(handler, struct ipoib_dev_priv, event_handler);
+
+	if (record->event == IB_EVENT_PORT_ACTIVE ||
+	    record->event == IB_EVENT_LID_CHANGE  ||
+	    record->event == IB_EVENT_SM_CHANGE) {
+		ipoib_dbg(priv, "Port active event\n");
+		schedule_work(&priv->flush_task);
+	}
+}