path: root/drivers/infiniband/ulp/ipoib/ipoib.h

/*
 * 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.
 */

#ifndef _IPOIB_H
#define _IPOIB_H

#include <linux/list.h>
#include <linux/skbuff.h>
#include <linux/netdevice.h>
#include <linux/workqueue.h>
#include <linux/kref.h>
#include <linux/if_infiniband.h>
#include <linux/mutex.h>

#include <net/neighbour.h>
#include <net/sch_generic.h>

#include <linux/atomic.h>

#include <rdma/ib_verbs.h>
#include <rdma/ib_pack.h>
#include <rdma/ib_sa.h>
#include <linux/sched.h>

/* constants */

enum ipoib_flush_level {
	IPOIB_FLUSH_LIGHT,
	IPOIB_FLUSH_NORMAL,
	IPOIB_FLUSH_HEAVY
};

enum {
	IPOIB_ENCAP_LEN		  = 4,

	IPOIB_UD_HEAD_SIZE	  = IB_GRH_BYTES + IPOIB_ENCAP_LEN,
	IPOIB_UD_RX_SG		  = 2, /* max buffer needed for 4K mtu */

	IPOIB_CM_MTU		  = 0x10000 - 0x10, /* padding to align header to 16 */
	IPOIB_CM_BUF_SIZE	  = IPOIB_CM_MTU  + IPOIB_ENCAP_LEN,
	IPOIB_CM_HEAD_SIZE	  = IPOIB_CM_BUF_SIZE % PAGE_SIZE,
	IPOIB_CM_RX_SG		  = ALIGN(IPOIB_CM_BUF_SIZE, PAGE_SIZE) / PAGE_SIZE,
	IPOIB_RX_RING_SIZE	  = 256,
	IPOIB_TX_RING_SIZE	  = 128,
	IPOIB_MAX_QUEUE_SIZE	  = 8192,
	IPOIB_MIN_QUEUE_SIZE	  = 2,
	IPOIB_CM_MAX_CONN_QP	  = 4096,

	IPOIB_NUM_WC		  = 4,

	IPOIB_MAX_PATH_REC_QUEUE  = 3,
	IPOIB_MAX_MCAST_QUEUE	  = 64,

	IPOIB_FLAG_OPER_UP	  = 0,
	IPOIB_FLAG_INITIALIZED	  = 1,
	IPOIB_FLAG_ADMIN_UP	  = 2,
	IPOIB_PKEY_ASSIGNED	  = 3,
	IPOIB_FLAG_SUBINTERFACE	  = 5,
	IPOIB_STOP_REAPER	  = 7,
	IPOIB_FLAG_ADMIN_CM	  = 9,
	IPOIB_FLAG_UMCAST	  = 10,
	IPOIB_STOP_NEIGH_GC	  = 11,
	IPOIB_NEIGH_TBL_FLUSH	  = 12,
	IPOIB_FLAG_DEV_ADDR_SET	  = 13,
	IPOIB_FLAG_DEV_ADDR_CTRL  = 14,

	IPOIB_MAX_BACKOFF_SECONDS = 16,

	IPOIB_MCAST_FLAG_FOUND	  = 0,	/* used in set_multicast_list */
	IPOIB_MCAST_FLAG_SENDONLY = 1,
	/*
	 * For IPOIB_MCAST_FLAG_BUSY
	 * When set, in flight join and mcast->mc is unreliable
	 * When clear and mcast->mc IS_ERR_OR_NULL, need to restart or
	 *   haven't started yet
	 * When clear and mcast->mc is valid pointer, join was successful
	 */
	IPOIB_MCAST_FLAG_BUSY	  = 2,
	IPOIB_MCAST_FLAG_ATTACHED = 3,

	MAX_SEND_CQE		  = 16,
	IPOIB_CM_COPYBREAK	  = 256,

	IPOIB_NON_CHILD		  = 0,
	IPOIB_LEGACY_CHILD	  = 1,
	IPOIB_RTNL_CHILD	  = 2,
};

#define	IPOIB_OP_RECV   (1ul << 31)
#ifdef CONFIG_INFINIBAND_IPOIB_CM
#define	IPOIB_OP_CM     (1ul << 30)
#else
#define	IPOIB_OP_CM     (0)
#endif

#define IPOIB_QPN_MASK ((__force u32) cpu_to_be32(0xFFFFFF))

/* structs */

struct ipoib_header {
	__be16	proto;
	u16	reserved;
};

struct ipoib_cb {
	struct qdisc_skb_cb	qdisc_cb;
	u8			hwaddr[INFINIBAND_ALEN];
};

static inline struct ipoib_cb *ipoib_skb_cb(const struct sk_buff *skb)
{
	BUILD_BUG_ON(sizeof(skb->cb) < sizeof(struct ipoib_cb));
	return (struct ipoib_cb *)skb->cb;
}

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

	struct rb_node    rb_node;
	struct list_head  list;

	unsigned long created;
	unsigned long backoff;
	unsigned long delay_until;

	unsigned long flags;
	unsigned char logcount;

	struct list_head  neigh_list;

	struct sk_buff_head pkt_queue;

	struct net_device *dev;
	struct completion done;
};

struct ipoib_rx_buf {
	struct sk_buff *skb;
	u64		mapping[IPOIB_UD_RX_SG];
};

struct ipoib_tx_buf {
	struct sk_buff *skb;
	u64		mapping[MAX_SKB_FRAGS + 1];
};

struct ipoib_cm_tx_buf {
	struct sk_buff *skb;
	u64		mapping;
};

struct ib_cm_id;

struct ipoib_cm_data {
	__be32 qpn; /* High byte MUST be ignored on receive */
	__be32 mtu;
};

/*
 * Quoting 10.3.1 Queue Pair and EE Context States:
 *
 * Note, for QPs that are associated with an SRQ, the Consumer should take the
 * QP through the Error State before invoking a Destroy QP or a Modify QP to the
 * Reset State.  The Consumer may invoke the Destroy QP without first performing
 * a Modify QP to the Error State and waiting for the Affiliated Asynchronous
 * Last WQE Reached Event. However, if the Consumer does not wait for the
 * Affiliated Asynchronous Last WQE Reached Event, then WQE and Data Segment
 * leakage may occur. Therefore, it is good programming practice to tear down a
 * QP that is associated with an SRQ by using the following process:
 *
 * - Put the QP in the Error State
 * - Wait for the Affiliated Asynchronous Last WQE Reached Event;
 * - either:
 *       drain the CQ by invoking the Poll CQ verb and either wait for CQ
 *       to be empty or the number of Poll CQ operations has exceeded
 *       CQ capacity size;
 * - or
 *       post another WR that completes on the same CQ and wait for this
 *       WR to return as a WC;
 * - and then invoke a Destroy QP or Reset QP.
 *
 * We use the second option and wait for a completion on the
 * same CQ before destroying QPs attached to our SRQ.
 */

enum ipoib_cm_state {
	IPOIB_CM_RX_LIVE,
	IPOIB_CM_RX_ERROR, /* Ignored by stale task */
	IPOIB_CM_RX_FLUSH  /* Last WQE Reached event observed */
};

struct ipoib_cm_rx {
	struct ib_cm_id	       *id;
	struct ib_qp	       *qp;
	struct ipoib_cm_rx_buf *rx_ring;
	struct list_head	list;
	struct net_device      *dev;
	unsigned long		jiffies;
	enum ipoib_cm_state	state;
	int			recv_count;
};

struct ipoib_cm_tx {
	struct ib_cm_id	    *id;
	struct ib_qp	    *qp;
	struct list_head     list;
	struct net_device   *dev;
	struct ipoib_neigh  *neigh;
	struct ipoib_path   *path;
	struct ipoib_tx_buf *tx_ring;
	unsigned	     tx_head;
	unsigned	     tx_tail;
	unsigned long	     flags;
	u32		     mtu;
	unsigned             max_send_sge;
};

struct ipoib_cm_rx_buf {
	struct sk_buff *skb;
	u64 mapping[IPOIB_CM_RX_SG];
};

struct ipoib_cm_dev_priv {
	struct ib_srq	       *srq;