ipoib.h

linux内核源码

/*
 * 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.h 1358 2004-12-17 22:00:11Z roland $
 */

#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 <asm/atomic.h>

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

/* constants */

enum {
	IPOIB_PACKET_SIZE         = 2048,
	IPOIB_BUF_SIZE 		  = IPOIB_PACKET_SIZE + IB_GRH_BYTES,

	IPOIB_ENCAP_LEN 	  = 4,

	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 	  = 128,
	IPOIB_TX_RING_SIZE 	  = 64,
	IPOIB_MAX_QUEUE_SIZE	  = 8192,
	IPOIB_MIN_QUEUE_SIZE	  = 2,

	IPOIB_NUM_WC 		  = 4,

	IPOIB_MAX_PATH_REC_QUEUE  = 3,
	IPOIB_MAX_MCAST_QUEUE     = 3,

	IPOIB_FLAG_OPER_UP 	  = 0,
	IPOIB_FLAG_INITIALIZED    = 1,
	IPOIB_FLAG_ADMIN_UP 	  = 2,
	IPOIB_PKEY_ASSIGNED 	  = 3,
	IPOIB_PKEY_STOP 	  = 4,
	IPOIB_FLAG_SUBINTERFACE   = 5,
	IPOIB_MCAST_RUN 	  = 6,
	IPOIB_STOP_REAPER         = 7,
	IPOIB_MCAST_STARTED       = 8,
	IPOIB_FLAG_ADMIN_CM 	  = 9,
	IPOIB_FLAG_UMCAST	  = 10,

	IPOIB_MAX_BACKOFF_SECONDS = 16,

	IPOIB_MCAST_FLAG_FOUND 	  = 0,	/* used in set_multicast_list */
	IPOIB_MCAST_FLAG_SENDONLY = 1,
	IPOIB_MCAST_FLAG_BUSY 	  = 2,	/* joining or already joined */
	IPOIB_MCAST_FLAG_ATTACHED = 3,
};

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

/* structs */

struct ipoib_header {
	__be16	proto;
	u16	reserved;
};

struct ipoib_pseudoheader {
	u8  hwaddr[INFINIBAND_ALEN];
};

/* 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 flags;
	unsigned char logcount;

	struct list_head  neigh_list;

	struct sk_buff_head pkt_queue;

	struct net_device *dev;
};

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

struct ipoib_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 list_head     list;
	struct net_device   *dev;
	unsigned long        jiffies;
	enum ipoib_cm_state  state;
};

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;
	struct ib_wc         ibwc[IPOIB_NUM_WC];
};

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

struct ipoib_cm_dev_priv {
	struct ib_srq  	       *srq;
	struct ipoib_cm_rx_buf *srq_ring;
	struct ib_cm_id        *id;
	struct list_head        passive_ids;   /* state: LIVE */
	struct list_head        rx_error_list; /* state: ERROR */
	struct list_head        rx_flush_list; /* state: FLUSH, drain not started */
	struct list_head        rx_drain_list; /* state: FLUSH, drain started */
	struct list_head        rx_reap_list;  /* state: FLUSH, drain done */
	struct work_struct      start_task;
	struct work_struct      reap_task;
	struct work_struct      skb_task;
	struct work_struct      rx_reap_task;
	struct delayed_work     stale_task;
	struct sk_buff_head     skb_queue;
	struct list_head        start_list;
	struct list_head        reap_list;
	struct ib_wc            ibwc[IPOIB_NUM_WC];
	struct ib_sge           rx_sge[IPOIB_CM_RX_SG];
	struct ib_recv_wr       rx_wr;
};

/*
 * Device private locking: tx_lock protects members used in TX fast
 * path (and we use LLTX so upper layers don't do extra locking).
 * lock protects everything else.  lock nests inside of tx_lock (ie
 * tx_lock must be acquired first if needed).
 */
struct ipoib_dev_priv {
	spinlock_t lock;

	struct net_device *dev;

	struct napi_struct napi;

	unsigned long flags;

	struct mutex mcast_mutex;
	struct mutex vlan_mutex;

	struct rb_root  path_tree;
	struct list_head path_list;

	struct ipoib_mcast *broadcast;
	struct list_head multicast_list;
	struct rb_root multicast_tree;

	struct delayed_work pkey_poll_task;
	struct delayed_work mcast_task;
	struct work_struct flush_task;
	struct work_struct restart_task;
	struct delayed_work ah_reap_task;
	struct work_struct pkey_event_task;

	struct ib_device *ca;
	u8            	  port;
	u16           	  pkey;
	u16               pkey_index;
	struct ib_pd  	 *pd;
	struct ib_mr  	 *mr;
	struct ib_cq  	 *cq;
	struct ib_qp  	 *qp;
	u32           	  qkey;

	union ib_gid local_gid;
	u16          local_lid;

	unsigned int admin_mtu;
	unsigned int mcast_mtu;

	struct ipoib_rx_buf *rx_ring;

	spinlock_t           tx_lock;
	struct ipoib_tx_buf *tx_ring;
	unsigned             tx_head;
	unsigned             tx_tail;
	struct ib_sge        tx_sge;
	struct ib_send_wr    tx_wr;
	unsigned             tx_outstanding;

	struct ib_wc ibwc[IPOIB_NUM_WC];

	struct list_head dead_ahs;

	struct ib_event_handler event_handler;

	struct net_device *parent;
	struct list_head child_intfs;
	struct list_head list;

#ifdef CONFIG_INFINIBAND_IPOIB_CM
	struct ipoib_cm_dev_priv cm;
#endif

#ifdef CONFIG_INFINIBAND_IPOIB_DEBUG
	struct list_head fs_list;
	struct dentry *mcg_dentry;
	struct dentry *path_dentry;
#endif
};

struct ipoib_ah {
	struct net_device *dev;
	struct ib_ah      *ah;
	struct list_head   list;
	struct kref        ref;
	unsigned           last_send;
};

struct ipoib_path {
	struct net_device    *dev;
	struct ib_sa_path_rec pathrec;
	struct ipoib_ah      *ah;
	struct sk_buff_head   queue;

	struct list_head      neigh_list;

	int                   query_id;
	struct ib_sa_query   *query;
	struct completion     done;

	struct rb_node        rb_node;
	struct list_head      list;
};