ipath_verbs.h

来自「linux 内核源代码」· C头文件 代码 · 共 864 行 · 第 1/2 页

/*
 * Copyright (c) 2006, 2007 QLogic Corporation. All rights reserved.
 * Copyright (c) 2005, 2006 PathScale, 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 IPATH_VERBS_H
#define IPATH_VERBS_H

#include <linux/types.h>
#include <linux/spinlock.h>
#include <linux/kernel.h>
#include <linux/interrupt.h>
#include <linux/kref.h>
#include <rdma/ib_pack.h>
#include <rdma/ib_user_verbs.h>

#include "ipath_kernel.h"

#define IPATH_MAX_RDMA_ATOMIC	4

#define QPN_MAX                 (1 << 24)
#define QPNMAP_ENTRIES          (QPN_MAX / PAGE_SIZE / BITS_PER_BYTE)

/*
 * Increment this value if any changes that break userspace ABI
 * compatibility are made.
 */
#define IPATH_UVERBS_ABI_VERSION       2

/*
 * Define an ib_cq_notify value that is not valid so we know when CQ
 * notifications are armed.
 */
#define IB_CQ_NONE	(IB_CQ_NEXT_COMP + 1)

/* AETH NAK opcode values */
#define IB_RNR_NAK			0x20
#define IB_NAK_PSN_ERROR		0x60
#define IB_NAK_INVALID_REQUEST		0x61
#define IB_NAK_REMOTE_ACCESS_ERROR	0x62
#define IB_NAK_REMOTE_OPERATIONAL_ERROR 0x63
#define IB_NAK_INVALID_RD_REQUEST	0x64

/* Flags for checking QP state (see ib_ipath_state_ops[]) */
#define IPATH_POST_SEND_OK		0x01
#define IPATH_POST_RECV_OK		0x02
#define IPATH_PROCESS_RECV_OK		0x04
#define IPATH_PROCESS_SEND_OK		0x08

/* IB Performance Manager status values */
#define IB_PMA_SAMPLE_STATUS_DONE	0x00
#define IB_PMA_SAMPLE_STATUS_STARTED	0x01
#define IB_PMA_SAMPLE_STATUS_RUNNING	0x02

/* Mandatory IB performance counter select values. */
#define IB_PMA_PORT_XMIT_DATA	__constant_htons(0x0001)
#define IB_PMA_PORT_RCV_DATA	__constant_htons(0x0002)
#define IB_PMA_PORT_XMIT_PKTS	__constant_htons(0x0003)
#define IB_PMA_PORT_RCV_PKTS	__constant_htons(0x0004)
#define IB_PMA_PORT_XMIT_WAIT	__constant_htons(0x0005)

struct ib_reth {
	__be64 vaddr;
	__be32 rkey;
	__be32 length;
} __attribute__ ((packed));

struct ib_atomic_eth {
	__be32 vaddr[2];	/* unaligned so access as 2 32-bit words */
	__be32 rkey;
	__be64 swap_data;
	__be64 compare_data;
} __attribute__ ((packed));

struct ipath_other_headers {
	__be32 bth[3];
	union {
		struct {
			__be32 deth[2];
			__be32 imm_data;
		} ud;
		struct {
			struct ib_reth reth;
			__be32 imm_data;
		} rc;
		struct {
			__be32 aeth;
			__be32 atomic_ack_eth[2];
		} at;
		__be32 imm_data;
		__be32 aeth;
		struct ib_atomic_eth atomic_eth;
	} u;
} __attribute__ ((packed));

/*
 * Note that UD packets with a GRH header are 8+40+12+8 = 68 bytes
 * long (72 w/ imm_data).  Only the first 56 bytes of the IB header
 * will be in the eager header buffer.  The remaining 12 or 16 bytes
 * are in the data buffer.
 */
struct ipath_ib_header {
	__be16 lrh[4];
	union {
		struct {
			struct ib_grh grh;
			struct ipath_other_headers oth;
		} l;
		struct ipath_other_headers oth;
	} u;
} __attribute__ ((packed));

/*
 * There is one struct ipath_mcast for each multicast GID.
 * All attached QPs are then stored as a list of
 * struct ipath_mcast_qp.
 */
struct ipath_mcast_qp {
	struct list_head list;
	struct ipath_qp *qp;
};

struct ipath_mcast {
	struct rb_node rb_node;
	union ib_gid mgid;
	struct list_head qp_list;
	wait_queue_head_t wait;
	atomic_t refcount;
	int n_attached;
};

/* Protection domain */
struct ipath_pd {
	struct ib_pd ibpd;
	int user;		/* non-zero if created from user space */
};

/* Address Handle */
struct ipath_ah {
	struct ib_ah ibah;
	struct ib_ah_attr attr;
};

/*
 * This structure is used by ipath_mmap() to validate an offset
 * when an mmap() request is made.  The vm_area_struct then uses
 * this as its vm_private_data.
 */
struct ipath_mmap_info {
	struct list_head pending_mmaps;
	struct ib_ucontext *context;
	void *obj;
	__u64 offset;
	struct kref ref;
	unsigned size;
};

/*
 * This structure is used to contain the head pointer, tail pointer,
 * and completion queue entries as a single memory allocation so
 * it can be mmap'ed into user space.
 */
struct ipath_cq_wc {
	u32 head;		/* index of next entry to fill */
	u32 tail;		/* index of next ib_poll_cq() entry */
	union {
		/* these are actually size ibcq.cqe + 1 */
		struct ib_uverbs_wc uqueue[0];
		struct ib_wc kqueue[0];
	};
};

/*
 * The completion queue structure.
 */
struct ipath_cq {
	struct ib_cq ibcq;
	struct tasklet_struct comptask;
	spinlock_t lock;
	u8 notify;
	u8 triggered;
	struct ipath_cq_wc *queue;
	struct ipath_mmap_info *ip;
};

/*
 * A segment is a linear region of low physical memory.
 * XXX Maybe we should use phys addr here and kmap()/kunmap().
 * Used by the verbs layer.
 */
struct ipath_seg {
	void *vaddr;
	size_t length;
};

/* The number of ipath_segs that fit in a page. */
#define IPATH_SEGSZ     (PAGE_SIZE / sizeof (struct ipath_seg))

struct ipath_segarray {
	struct ipath_seg segs[IPATH_SEGSZ];
};

struct ipath_mregion {
	struct ib_pd *pd;	/* shares refcnt of ibmr.pd */
	u64 user_base;		/* User's address for this region */
	u64 iova;		/* IB start address of this region */
	size_t length;
	u32 lkey;
	u32 offset;		/* offset (bytes) to start of region */
	int access_flags;
	u32 max_segs;		/* number of ipath_segs in all the arrays */
	u32 mapsz;		/* size of the map array */
	struct ipath_segarray *map[0];	/* the segments */
};

/*
 * These keep track of the copy progress within a memory region.
 * Used by the verbs layer.
 */
struct ipath_sge {
	struct ipath_mregion *mr;
	void *vaddr;		/* kernel virtual address of segment */
	u32 sge_length;		/* length of the SGE */
	u32 length;		/* remaining length of the segment */
	u16 m;			/* current index: mr->map[m] */
	u16 n;			/* current index: mr->map[m]->segs[n] */
};

/* Memory region */
struct ipath_mr {
	struct ib_mr ibmr;
	struct ib_umem *umem;
	struct ipath_mregion mr;	/* must be last */
};

/*
 * Send work request queue entry.
 * The size of the sg_list is determined when the QP is created and stored
 * in qp->s_max_sge.
 */
struct ipath_swqe {
	struct ib_send_wr wr;	/* don't use wr.sg_list */
	u32 psn;		/* first packet sequence number */
	u32 lpsn;		/* last packet sequence number */
	u32 ssn;		/* send sequence number */
	u32 length;		/* total length of data in sg_list */
	struct ipath_sge sg_list[0];
};

/*
 * Receive work request queue entry.
 * The size of the sg_list is determined when the QP (or SRQ) is created
 * and stored in qp->r_rq.max_sge (or srq->rq.max_sge).
 */
struct ipath_rwqe {
	u64 wr_id;
	u8 num_sge;
	struct ib_sge sg_list[0];
};

/*
 * This structure is used to contain the head pointer, tail pointer,
 * and receive work queue entries as a single memory allocation so
 * it can be mmap'ed into user space.
 * Note that the wq array elements are variable size so you can't
 * just index into the array to get the N'th element;
 * use get_rwqe_ptr() instead.
 */
struct ipath_rwq {
	u32 head;		/* new work requests posted to the head */
	u32 tail;		/* receives pull requests from here. */
	struct ipath_rwqe wq[0];
};

struct ipath_rq {
	struct ipath_rwq *wq;
	spinlock_t lock;
	u32 size;		/* size of RWQE array */
	u8 max_sge;
};

struct ipath_srq {
	struct ib_srq ibsrq;
	struct ipath_rq rq;
	struct ipath_mmap_info *ip;
	/* send signal when number of RWQEs < limit */
	u32 limit;
};

struct ipath_sge_state {
	struct ipath_sge *sg_list;      /* next SGE to be used if any */
	struct ipath_sge sge;   /* progress state for the current SGE */
	u8 num_sge;
};

/*
 * This structure holds the information that the send tasklet needs
 * to send a RDMA read response or atomic operation.
 */
struct ipath_ack_entry {
	u8 opcode;
	u8 sent;
	u32 psn;
	union {
		struct ipath_sge_state rdma_sge;
		u64 atomic_data;
	};
};

/*
 * Variables prefixed with s_ are for the requester (sender).
 * Variables prefixed with r_ are for the responder (receiver).
 * Variables prefixed with ack_ are for responder replies.
 *
 * Common variables are protected by both r_rq.lock and s_lock in that order
 * which only happens in modify_qp() or changing the QP 'state'.
 */
struct ipath_qp {
	struct ib_qp ibqp;
	struct ipath_qp *next;		/* link list for QPN hash table */
	struct ipath_qp *timer_next;	/* link list for ipath_ib_timer() */
	struct list_head piowait;	/* link for wait PIO buf */
	struct list_head timerwait;	/* link for waiting for timeouts */
	struct ib_ah_attr remote_ah_attr;
	struct ipath_ib_header s_hdr;	/* next packet header to send */
	atomic_t refcount;
	wait_queue_head_t wait;
	struct tasklet_struct s_task;
	struct ipath_mmap_info *ip;
	struct ipath_sge_state *s_cur_sge;
	struct ipath_sge_state s_sge;	/* current send request data */
	struct ipath_ack_entry s_ack_queue[IPATH_MAX_RDMA_ATOMIC + 1];
	struct ipath_sge_state s_ack_rdma_sge;
	struct ipath_sge_state s_rdma_read_sge;
	struct ipath_sge_state r_sge;	/* current receive data */
	spinlock_t s_lock;
	unsigned long s_busy;
	u32 s_hdrwords;		/* size of s_hdr in 32 bit words */
	u32 s_cur_size;		/* size of send packet in bytes */
	u32 s_len;		/* total length of s_sge */
	u32 s_rdma_read_len;	/* total length of s_rdma_read_sge */
	u32 s_next_psn;		/* PSN for next request */
	u32 s_last_psn;		/* last response PSN processed */
	u32 s_psn;		/* current packet sequence number */
	u32 s_ack_rdma_psn;	/* PSN for sending RDMA read responses */
	u32 s_ack_psn;		/* PSN for acking sends and RDMA writes */
	u32 s_rnr_timeout;	/* number of milliseconds for RNR timeout */
	u32 r_ack_psn;		/* PSN for next ACK or atomic ACK */
	u64 r_wr_id;		/* ID for current receive WQE */
	u32 r_len;		/* total length of r_sge */
	u32 r_rcv_len;		/* receive data len processed */
	u32 r_psn;		/* expected rcv packet sequence number */
	u32 r_msn;		/* message sequence number */
	u8 state;		/* QP state */
	u8 s_state;		/* opcode of last packet sent */
	u8 s_ack_state;		/* opcode of packet to ACK */
	u8 s_nak_state;		/* non-zero if NAK is pending */
	u8 r_state;		/* opcode of last packet received */
	u8 r_nak_state;		/* non-zero if NAK is pending */
	u8 r_min_rnr_timer;	/* retry timeout value for RNR NAKs */
	u8 r_reuse_sge;		/* for UC receive errors */
	u8 r_sge_inx;		/* current index into sg_list */
	u8 r_wrid_valid;	/* r_wrid set but CQ entry not yet made */
	u8 r_max_rd_atomic;	/* max number of RDMA read/atomic to receive */
	u8 r_head_ack_queue;	/* index into s_ack_queue[] */
	u8 qp_access_flags;
	u8 s_max_sge;		/* size of s_wq->sg_list */
	u8 s_retry_cnt;		/* number of times to retry */
	u8 s_rnr_retry_cnt;
	u8 s_retry;		/* requester retry counter */
	u8 s_rnr_retry;		/* requester RNR retry counter */
	u8 s_wait_credit;	/* limit number of unacked packets sent */
	u8 s_pkey_index;	/* PKEY index to use */
	u8 s_max_rd_atomic;	/* max number of RDMA read/atomic to send */
	u8 s_num_rd_atomic;	/* number of RDMA read/atomic pending */
	u8 s_tail_ack_queue;	/* index into s_ack_queue[] */
	u8 s_flags;
	u8 timeout;		/* Timeout for this QP */
	enum ib_mtu path_mtu;
	u32 remote_qpn;
	u32 qkey;		/* QKEY for this QP (for UD or RD) */
	u32 s_size;		/* send work queue size */
	u32 s_head;		/* new entries added here */
	u32 s_tail;		/* next entry to process */
	u32 s_cur;		/* current work queue entry */
	u32 s_last;		/* last un-ACK'ed entry */
	u32 s_ssn;		/* SSN of tail entry */
	u32 s_lsn;		/* limit sequence number (credit) */
	struct ipath_swqe *s_wq;	/* send work queue */
	struct ipath_swqe *s_wqe;
	struct ipath_rq r_rq;		/* receive work queue */
	struct ipath_sge r_sg_list[0];	/* verified SGEs */
};

/* Bit definition for s_busy. */
#define IPATH_S_BUSY		0

/*
 * Bit definitions for s_flags.
 */
#define IPATH_S_SIGNAL_REQ_WR	0x01
#define IPATH_S_FENCE_PENDING	0x02
#define IPATH_S_RDMAR_PENDING	0x04
#define IPATH_S_ACK_PENDING	0x08