aboutsummaryrefslogblamecommitdiffstats
path: root/drivers/scsi/libfc/fc_exch.c
blob: 7af9bceb8aa9efa467c3ca58ed4da1694ec7d79c (plain) (tree)
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471

































                                                                               
























































































































































































































































                                                                               
                                                           














































































































































































































                                                                               
                                                 






































































































































                                                                                

























                                                                           










                                                                               

                                                                        




























































































































































































































































































































                                                                                


                                                             
































































































                                                                         
                                          












































































                                                                              



                                                     

















































































































































































































































































































                                                                                
                                                             


                             
                                         


























































































































                                                                               
                                                                  






















































































































































































































































                                                                               

                                              
















































































































                                                                             
/*
 * Copyright(c) 2007 Intel Corporation. All rights reserved.
 * Copyright(c) 2008 Red Hat, Inc.  All rights reserved.
 * Copyright(c) 2008 Mike Christie
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms and conditions of the GNU General Public License,
 * version 2, as published by the Free Software Foundation.
 *
 * This program is distributed in the hope it will be useful, but WITHOUT
 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
 * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
 * more details.
 *
 * You should have received a copy of the GNU General Public License along with
 * this program; if not, write to the Free Software Foundation, Inc.,
 * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
 *
 * Maintained at www.Open-FCoE.org
 */

/*
 * Fibre Channel exchange and sequence handling.
 */

#include <linux/timer.h>
#include <linux/gfp.h>
#include <linux/err.h>

#include <scsi/fc/fc_fc2.h>

#include <scsi/libfc.h>
#include <scsi/fc_encode.h>

/*
 * fc_exch_debug can be set in debugger or at compile time to get more logs.
 */
static int fc_exch_debug;

#define FC_DEBUG_EXCH(fmt...)			\
	do {					\
		if (fc_exch_debug)		\
			FC_DBG(fmt);		\
	} while (0)

static struct kmem_cache *fc_em_cachep;	/* cache for exchanges */

/*
 * Structure and function definitions for managing Fibre Channel Exchanges
 * and Sequences.
 *
 * The three primary structures used here are fc_exch_mgr, fc_exch, and fc_seq.
 *
 * fc_exch_mgr holds the exchange state for an N port
 *
 * fc_exch holds state for one exchange and links to its active sequence.
 *
 * fc_seq holds the state for an individual sequence.
 */

/*
 * Exchange manager.
 *
 * This structure is the center for creating exchanges and sequences.
 * It manages the allocation of exchange IDs.
 */
struct fc_exch_mgr {
	enum fc_class	class;		/* default class for sequences */
	spinlock_t	em_lock;	/* exchange manager lock,
					   must be taken before ex_lock */
	u16		last_xid;	/* last allocated exchange ID */
	u16		min_xid;	/* min exchange ID */
	u16		max_xid;	/* max exchange ID */
	u16		max_read;	/* max exchange ID for read */
	u16		last_read;	/* last xid allocated for read */
	u32	total_exches;		/* total allocated exchanges */
	struct list_head	ex_list;	/* allocated exchanges list */
	struct fc_lport	*lp;		/* fc device instance */
	mempool_t	*ep_pool;	/* reserve ep's */

	/*
	 * currently exchange mgr stats are updated but not used.
	 * either stats can be expose via sysfs or remove them
	 * all together if not used XXX
	 */
	struct {
		atomic_t no_free_exch;
		atomic_t no_free_exch_xid;
		atomic_t xid_not_found;
		atomic_t xid_busy;
		atomic_t seq_not_found;
		atomic_t non_bls_resp;
	} stats;
	struct fc_exch **exches;	/* for exch pointers indexed by xid */
};
#define	fc_seq_exch(sp) container_of(sp, struct fc_exch, seq)

static void fc_exch_rrq(struct fc_exch *);
static void fc_seq_ls_acc(struct fc_seq *);
static void fc_seq_ls_rjt(struct fc_seq *, enum fc_els_rjt_reason,
			  enum fc_els_rjt_explan);
static void fc_exch_els_rec(struct fc_seq *, struct fc_frame *);
static void fc_exch_els_rrq(struct fc_seq *, struct fc_frame *);
static struct fc_seq *fc_seq_start_next_locked(struct fc_seq *sp);

/*
 * Internal implementation notes.
 *
 * The exchange manager is one by default in libfc but LLD may choose
 * to have one per CPU. The sequence manager is one per exchange manager
 * and currently never separated.
 *
 * Section 9.8 in FC-FS-2 specifies:  "The SEQ_ID is a one-byte field
 * assigned by the Sequence Initiator that shall be unique for a specific
 * D_ID and S_ID pair while the Sequence is open."   Note that it isn't
 * qualified by exchange ID, which one might think it would be.
 * In practice this limits the number of open sequences and exchanges to 256
 * per session.	 For most targets we could treat this limit as per exchange.
 *
 * The exchange and its sequence are freed when the last sequence is received.
 * It's possible for the remote port to leave an exchange open without
 * sending any sequences.
 *
 * Notes on reference counts:
 *
 * Exchanges are reference counted and exchange gets freed when the reference
 * count becomes zero.
 *
 * Timeouts:
 * Sequences are timed out for E_D_TOV and R_A_TOV.
 *
 * Sequence event handling:
 *
 * The following events may occur on initiator sequences:
 *
 *	Send.
 *	    For now, the whole thing is sent.
 *	Receive ACK
 *	    This applies only to class F.
 *	    The sequence is marked complete.
 *	ULP completion.
 *	    The upper layer calls fc_exch_done() when done
 *	    with exchange and sequence tuple.
 *	RX-inferred completion.
 *	    When we receive the next sequence on the same exchange, we can
 *	    retire the previous sequence ID.  (XXX not implemented).
 *	Timeout.
 *	    R_A_TOV frees the sequence ID.  If we're waiting for ACK,
 *	    E_D_TOV causes abort and calls upper layer response handler
 *	    with FC_EX_TIMEOUT error.
 *	Receive RJT
 *	    XXX defer.
 *	Send ABTS
 *	    On timeout.
 *
 * The following events may occur on recipient sequences:
 *
 *	Receive
 *	    Allocate sequence for first frame received.
 *	    Hold during receive handler.
 *	    Release when final frame received.
 *	    Keep status of last N of these for the ELS RES command.  XXX TBD.
 *	Receive ABTS
 *	    Deallocate sequence
 *	Send RJT
 *	    Deallocate
 *
 * For now, we neglect conditions where only part of a sequence was
 * received or transmitted, or where out-of-order receipt is detected.
 */

/*
 * Locking notes:
 *
 * The EM code run in a per-CPU worker thread.
 *
 * To protect against concurrency between a worker thread code and timers,
 * sequence allocation and deallocation must be locked.
 *  - exchange refcnt can be done atomicly without locks.
 *  - sequence allocation must be locked by exch lock.
 *  - If the em_lock and ex_lock must be taken at the same time, then the
 *    em_lock must be taken before the ex_lock.
 */

/*
 * opcode names for debugging.
 */
static char *fc_exch_rctl_names[] = FC_RCTL_NAMES_INIT;

#define FC_TABLE_SIZE(x)   (sizeof(x) / sizeof(x[0]))

static inline const char *fc_exch_name_lookup(unsigned int op, char **table,
					      unsigned int max_index)
{
	const char *name = NULL;

	if (op < max_index)
		name = table[op];
	if (!name)
		name = "unknown";
	return name;
}

static const char *fc_exch_rctl_name(unsigned int op)
{
	return fc_exch_name_lookup(op, fc_exch_rctl_names,
				   FC_TABLE_SIZE(fc_exch_rctl_names));
}

/*
 * Hold an exchange - keep it from being freed.
 */
static void fc_exch_hold(struct fc_exch *ep)
{
	atomic_inc(&ep->ex_refcnt);
}

/*
 * setup fc hdr by initializing few more FC header fields and sof/eof.
 * Initialized fields by this func:
 *	- fh_ox_id, fh_rx_id, fh_seq_id, fh_seq_cnt
 *	- sof and eof
 */
static void fc_exch_setup_hdr(struct fc_exch *ep, struct fc_frame *fp,
			      u32 f_ctl)
{
	struct fc_frame_header *fh = fc_frame_header_get(fp);
	u16 fill;

	fr_sof(fp) = ep->class;
	if (ep->seq.cnt)
		fr_sof(fp) = fc_sof_normal(ep->class);

	if (f_ctl & FC_FC_END_SEQ) {
		fr_eof(fp) = FC_EOF_T;
		if (fc_sof_needs_ack(ep->class))
			fr_eof(fp) = FC_EOF_N;
		/*
		 * Form f_ctl.
		 * The number of fill bytes to make the length a 4-byte
		 * multiple is the low order 2-bits of the f_ctl.
		 * The fill itself will have been cleared by the frame
		 * allocation.
		 * After this, the length will be even, as expected by
		 * the transport.
		 */
		fill = fr_len(fp) & 3;
		if (fill) {
			fill = 4 - fill;
			/* TODO, this may be a problem with fragmented skb */
			skb_put(fp_skb(fp), fill);
			hton24(fh->fh_f_ctl, f_ctl | fill);
		}
	} else {
		WARN_ON(fr_len(fp) % 4 != 0);	/* no pad to non last frame */
		fr_eof(fp) = FC_EOF_N;
	}

	/*
	 * Initialize remainig fh fields
	 * from fc_fill_fc_hdr
	 */
	fh->fh_ox_id = htons(ep->oxid);
	fh->fh_rx_id = htons(ep->rxid);
	fh->fh_seq_id = ep->seq.id;
	fh->fh_seq_cnt = htons(ep->seq.cnt);
}


/*
 * Release a reference to an exchange.
 * If the refcnt goes to zero and the exchange is complete, it is freed.
 */
static void fc_exch_release(struct fc_exch *ep)
{
	struct fc_exch_mgr *mp;

	if (atomic_dec_and_test(&ep->ex_refcnt)) {
		mp = ep->em;
		if (ep->destructor)
			ep->destructor(&ep->seq, ep->arg);
		if (ep->lp->tt.exch_put)
			ep->lp->tt.exch_put(ep->lp, mp, ep->xid);
		WARN_ON(!(ep->esb_stat & ESB_ST_COMPLETE));
		mempool_free(ep, mp->ep_pool);
	}
}

static int fc_exch_done_locked(struct fc_exch *ep)
{
	int rc = 1;

	/*
	 * We must check for completion in case there are two threads
	 * tyring to complete this. But the rrq code will reuse the
	 * ep, and in that case we only clear the resp and set it as
	 * complete, so it can be reused by the timer to send the rrq.
	 */
	ep->resp = NULL;
	if (ep->state & FC_EX_DONE)
		return rc;
	ep->esb_stat |= ESB_ST_COMPLETE;

	if (!(ep->esb_stat & ESB_ST_REC_QUAL)) {
		ep->state |= FC_EX_DONE;
		if (cancel_delayed_work(&ep->timeout_work))
			atomic_dec(&ep->ex_refcnt); /* drop hold for timer */
		rc = 0;
	}
	return rc;
}

static void fc_exch_mgr_delete_ep(struct fc_exch *ep)
{
	struct fc_exch_mgr *mp;

	mp = ep->em;
	spin_lock_bh(&mp->em_lock);
	WARN_ON(mp->total_exches <= 0);
	mp->total_exches--;
	mp->exches[ep->xid - mp->min_xid] = NULL;
	list_del(&ep->ex_list);
	spin_unlock_bh(&mp->em_lock);
	fc_exch_release(ep);	/* drop hold for exch in mp */
}

/*
 * Internal version of fc_exch_timer_set - used with lock held.
 */
static inline void fc_exch_timer_set_locked(struct fc_exch *ep,
					    unsigned int timer_msec)
{
	if (ep->state & (FC_EX_RST_CLEANUP | FC_EX_DONE))
		return;

	FC_DEBUG_EXCH("Exchange (%4x) timed out, notifying the upper layer\n",
		      ep->xid);
	if (schedule_delayed_work(&ep->timeout_work,
				  msecs_to_jiffies(timer_msec)))
		fc_exch_hold(ep);		/* hold for timer */
}

/*
 * Set timer for an exchange.
 * The time is a minimum delay in milliseconds until the timer fires.
 * Used for upper level protocols to time out the exchange.
 * The timer is cancelled when it fires or when the exchange completes.
 * Returns non-zero if a timer couldn't be allocated.
 */
static void fc_exch_timer_set(struct fc_exch *ep, unsigned int timer_msec)
{
	spin_lock_bh(&ep->ex_lock);
	fc_exch_timer_set_locked(ep, timer_msec);
	spin_unlock_bh(&ep->ex_lock);
}

int fc_seq_exch_abort(const struct fc_seq *req_sp, unsigned int timer_msec)
{
	struct fc_seq *sp;
	struct fc_exch *ep;
	struct fc_frame *fp;
	int error;

	ep = fc_seq_exch(req_sp);

	spin_lock_bh(&ep->ex_lock);
	if (ep->esb_stat & (ESB_ST_COMPLETE | ESB_ST_ABNORMAL) ||
	    ep->state & (FC_EX_DONE | FC_EX_RST_CLEANUP)) {
		spin_unlock_bh(&ep->ex_lock);
		return -ENXIO;
	}

	/*
	 * Send the abort on a new sequence if possible.
	 */
	sp = fc_seq_start_next_locked(&ep->seq);
	if (!sp) {
		spin_unlock_bh(&ep->ex_lock);
		return -ENOMEM;
	}

	ep->esb_stat |= ESB_ST_SEQ_INIT | ESB_ST_ABNORMAL;
	if (timer_msec)
		fc_exch_timer_set_locked(ep, timer_msec);
	spin_unlock_bh(&ep->ex_lock);

	/*
	 * If not logged into the fabric, don't send ABTS but leave
	 * sequence active until next timeout.
	 */
	if (!ep->sid)
		return 0;

	/*
	 * Send an abort for the sequence that timed out.
	 */
	fp = fc_frame_alloc(ep->lp, 0);
	if (fp) {
		fc_fill_fc_hdr(fp, FC_RCTL_BA_ABTS, ep->did, ep->sid,
			       FC_TYPE_BLS, FC_FC_END_SEQ | FC_FC_SEQ_INIT, 0);
		error = fc_seq_send(ep->lp, sp, fp);
	} else
		error = -ENOBUFS;
	return error;
}
EXPORT_SYMBOL(fc_seq_exch_abort);

/*
 * Exchange timeout - handle exchange timer expiration.
 * The timer will have been cancelled before this is called.
 */
static void fc_exch_timeout(struct work_struct *work)
{
	struct fc_exch *ep = container_of(work, struct fc_exch,
					  timeout_work.work);
	struct fc_seq *sp = &ep->seq;
	void (*resp)(struct fc_seq *, struct fc_frame *fp, void *arg);
	void *arg;
	u32 e_stat;
	int rc = 1;

	spin_lock_bh(&ep->ex_lock);
	if (ep->state & (FC_EX_RST_CLEANUP | FC_EX_DONE))
		goto unlock;

	e_stat = ep->esb_stat;
	if (e_stat & ESB_ST_COMPLETE) {
		ep->esb_stat = e_stat & ~ESB_ST_REC_QUAL;
		if (e_stat & ESB_ST_REC_QUAL)
			fc_exch_rrq(ep);
		spin_unlock_bh(&ep->ex_lock);
		goto done;
	} else {
		resp = ep->resp;
		arg = ep->arg;
		ep->resp = NULL;
		if (e_stat & ESB_ST_ABNORMAL)
			rc = fc_exch_done_locked(ep);
		spin_unlock_bh(&ep->ex_lock);
		if (!rc)
			fc_exch_mgr_delete_ep(ep);
		if (resp)
			resp(sp, ERR_PTR(-FC_EX_TIMEOUT), arg);
		fc_seq_exch_abort(sp, 2 * ep->r_a_tov);
		goto done;
	}
unlock:
	spin_unlock_bh(&ep->ex_lock);
done:
	/*
	 * This release matches the hold taken when the timer was set.
	 */
	fc_exch_release(ep);
}

/*
 * Allocate a sequence.
 *
 * We don't support multiple originated sequences on the same exchange.
 * By implication, any previously originated sequence on this exchange
 * is complete, and we reallocate the same sequence.
 */
static struct fc_seq *fc_seq_alloc(struct fc_exch *ep, u8 seq_id)
{
	struct fc_seq *sp;

	sp = &ep->seq;
	sp->ssb_stat = 0;
	sp->cnt = 0;
	sp->id = seq_id;
	return sp;
}

/*
 * fc_em_alloc_xid - returns an xid based on request type
 * @lp : ptr to associated lport
 * @fp : ptr to the assocated frame
 *
 * check the associated fc_fsp_pkt to get scsi command type and
 * command direction to decide from which range this exch id
 * will be allocated from.
 *
 * Returns : 0 or an valid xid
 */
static u16 fc_em_alloc_xid(struct fc_exch_mgr *mp, const struct fc_frame *fp)
{
	u16 xid, min, max;
	u16 *plast;
	struct fc_exch *ep = NULL;

	if (mp->max_read) {
		if (fc_fcp_is_read(fr_fsp(fp))) {
			min = mp->min_xid;
			max = mp->max_read;
			plast = &mp->last_read;
		} else {
			min = mp->max_read + 1;
			max = mp->max_xid;
			plast = &mp->last_xid;
		}
	} else {
		min = mp->min_xid;
		max = mp->max_xid;
		plast = &mp->last_xid;
	}
	xid = *plast;
	do {
		xid = (xid == max) ? min : xid + 1;
		ep = mp->exches[xid - mp->min_xid];
	} while ((ep != NULL) && (xid != *plast));

	if (unlikely(ep))
		xid = 0;
	else
		*plast = xid;

	return xid;
}

/*
 * fc_exch_alloc - allocate an exchange.
 * @mp : ptr to the exchange manager
 * @xid: input xid
 *
 * if xid is supplied zero then assign next free exchange ID
 * from exchange manager, otherwise use supplied xid.
 * Returns with exch lock held.
 */
struct fc_exch *fc_exch_alloc(struct fc_exch_mgr *mp,
			      struct fc_frame *fp, u16 xid)
{
	struct fc_exch *ep;

	/* allocate memory for exchange */
	ep = mempool_alloc(mp->ep_pool, GFP_ATOMIC);
	if (!ep) {
		atomic_inc(&mp->stats.no_free_exch);
		goto out;
	}
	memset(ep, 0, sizeof(*ep));

	spin_lock_bh(&mp->em_lock);
	/* alloc xid if input xid 0 */
	if (!xid) {
		/* alloc a new xid */
		xid = fc_em_alloc_xid(mp, fp);
		if (!xid) {
			printk(KERN_ERR "fc_em_alloc_xid() failed\n");
			goto err;
		}
	}

	fc_exch_hold(ep);	/* hold for exch in mp */
	spin_lock_init(&ep->ex_lock);
	/*
	 * Hold exch lock for caller to prevent fc_exch_reset()
	 * from releasing exch	while fc_exch_alloc() caller is
	 * still working on exch.
	 */
	spin_lock_bh(&ep->ex_lock);

	mp->exches[xid - mp->min_xid] = ep;
	list_add_tail(&ep->ex_list, &mp->ex_list);
	fc_seq_alloc(ep, ep->seq_id++);
	mp->total_exches++;
	spin_unlock_bh(&mp->em_lock);

	/*
	 *  update exchange
	 */
	ep->oxid = ep->xid = xid;
	ep->em = mp;
	ep->lp = mp->lp;
	ep->f_ctl = FC_FC_FIRST_SEQ;	/* next seq is first seq */
	ep->rxid = FC_XID_UNKNOWN;
	ep->class = mp->class;
	INIT_DELAYED_WORK(&ep->timeout_work, fc_exch_timeout);
out:
	return ep;
err:
	spin_unlock_bh(&mp->em_lock);
	atomic_inc(&mp->stats.no_free_exch_xid);
	mempool_free(ep, mp->ep_pool);
	return NULL;
}
EXPORT_SYMBOL(fc_exch_alloc);

/*
 * Lookup and hold an exchange.
 */
static struct fc_exch *fc_exch_find(struct fc_exch_mgr *mp, u16 xid)
{
	struct fc_exch *ep = NULL;

	if ((xid >= mp->min_xid) && (xid <= mp->max_xid)) {
		spin_lock_bh(&mp->em_lock);
		ep = mp->exches[xid - mp->min_xid];
		if (ep) {
			fc_exch_hold(ep);
			WARN_ON(ep->xid != xid);
		}
		spin_unlock_bh(&mp->em_lock);
	}
	return ep;
}

void fc_exch_done(struct fc_seq *sp)
{
	struct fc_exch *ep = fc_seq_exch(sp);
	int rc;

	spin_lock_bh(&ep->ex_lock);
	rc = fc_exch_done_locked(ep);
	spin_unlock_bh(&ep->ex_lock);
	if (!rc)
		fc_exch_mgr_delete_ep(ep);
}
EXPORT_SYMBOL(fc_exch_done);

/*
 * Allocate a new exchange as responder.
 * Sets the responder ID in the frame header.
 */
static struct fc_exch *fc_exch_resp(struct fc_exch_mgr *mp, struct fc_frame *fp)
{
	struct fc_exch *ep;
	struct fc_frame_header *fh;

	ep = mp->lp->tt.exch_get(mp->lp, fp);
	if (ep) {
		ep->class = fc_frame_class(fp);

		/*
		 * Set EX_CTX indicating we're responding on this exchange.
		 */
		ep->f_ctl |= FC_FC_EX_CTX;	/* we're responding */
		ep->f_ctl &= ~FC_FC_FIRST_SEQ;	/* not new */
		fh = fc_frame_header_get(fp);
		ep->sid = ntoh24(fh->fh_d_id);
		ep->did = ntoh24(fh->fh_s_id);
		ep->oid = ep->did;

		/*
		 * Allocated exchange has placed the XID in the
		 * originator field. Move it to the responder field,
		 * and set the originator XID from the frame.
		 */
		ep->rxid = ep->xid;
		ep->oxid = ntohs(fh->fh_ox_id);
		ep->esb_stat |= ESB_ST_RESP | ESB_ST_SEQ_INIT;
		if ((ntoh24(fh->fh_f_ctl) & FC_FC_SEQ_INIT) == 0)
			ep->esb_stat &= ~ESB_ST_SEQ_INIT;

		fc_exch_hold(ep);	/* hold for caller */
		spin_unlock_bh(&ep->ex_lock);	/* lock from exch_get */
	}
	return ep;
}

/*
 * Find a sequence for receive where the other end is originating the sequence.
 * If fc_pf_rjt_reason is FC_RJT_NONE then this function will have a hold
 * on the ep that should be released by the caller.
 */
static enum fc_pf_rjt_reason fc_seq_lookup_recip(struct fc_exch_mgr *mp,
						 struct fc_frame *fp)
{
	struct fc_frame_header *fh = fc_frame_header_get(fp);
	struct fc_exch *ep = NULL;
	struct fc_seq *sp = NULL;
	enum fc_pf_rjt_reason reject = FC_RJT_NONE;
	u32 f_ctl;
	u16 xid;

	f_ctl = ntoh24(fh->fh_f_ctl);
	WARN_ON((f_ctl & FC_FC_SEQ_CTX) != 0);

	/*
	 * Lookup or create the exchange if we will be creating the sequence.
	 */
	if (f_ctl & FC_FC_EX_CTX) {
		xid = ntohs(fh->fh_ox_id);	/* we originated exch */
		ep = fc_exch_find(mp, xid);
		if (!ep) {
			atomic_inc(&mp->stats.xid_not_found);
			reject = FC_RJT_OX_ID;
			goto out;
		}
		if (ep->rxid == FC_XID_UNKNOWN)
			ep->rxid = ntohs(fh->fh_rx_id);
		else if (ep->rxid != ntohs(fh->fh_rx_id)) {
			reject = FC_RJT_OX_ID;
			goto rel;
		}
	} else {
		xid = ntohs(fh->fh_rx_id);	/* we are the responder */

		/*
		 * Special case for MDS issuing an ELS TEST with a
		 * bad rxid of 0.
		 * XXX take this out once we do the proper reject.
		 */
		if (xid == 0 && fh->fh_r_ctl == FC_RCTL_ELS_REQ &&
		    fc_frame_payload_op(fp) == ELS_TEST) {
			fh->fh_rx_id = htons(FC_XID_UNKNOWN);
			xid = FC_XID_UNKNOWN;
		}

		/*
		 * new sequence - find the exchange
		 */
		ep = fc_exch_find(mp, xid);
		if ((f_ctl & FC_FC_FIRST_SEQ) && fc_sof_is_init(fr_sof(fp))) {
			if (ep) {
				atomic_inc(&mp->stats.xid_busy);
				reject = FC_RJT_RX_ID;
				goto rel;
			}
			ep = fc_exch_resp(mp, fp);
			if (!ep) {
				reject = FC_RJT_EXCH_EST;	/* XXX */
				goto out;
			}
			xid = ep->xid;	/* get our XID */
		} else if (!ep) {
			atomic_inc(&mp->stats.xid_not_found);
			reject = FC_RJT_RX_ID;	/* XID not found */
			goto out;
		}
	}

	/*
	 * At this point, we have the exchange held.
	 * Find or create the sequence.
	 */
	if (fc_sof_is_init(fr_sof(fp))) {
		sp = fc_seq_start_next(&ep->seq);
		if (!sp) {
			reject = FC_RJT_SEQ_XS;	/* exchange shortage */
			goto rel;
		}
		sp->id = fh->fh_seq_id;
		sp->ssb_stat |= SSB_ST_RESP;
	} else {
		sp = &ep->seq;
		if (sp->id != fh->fh_seq_id) {
			atomic_inc(&mp->stats.seq_not_found);
			reject = FC_RJT_SEQ_ID;	/* sequence/exch should exist */
			goto rel;
		}
	}
	WARN_ON(ep != fc_seq_exch(sp));

	if (f_ctl & FC_FC_SEQ_INIT)
		ep->esb_stat |= ESB_ST_SEQ_INIT;

	fr_seq(fp) = sp;
out:
	return reject;
rel:
	fc_exch_done(&ep->seq);
	fc_exch_release(ep);	/* hold from fc_exch_find/fc_exch_resp */
	return reject;
}

/*
 * Find the sequence for a frame being received.
 * We originated the sequence, so it should be found.
 * We may or may not have originated the exchange.
 * Does not hold the sequence for the caller.
 */
static struct fc_seq *fc_seq_lookup_orig(struct fc_exch_mgr *mp,
					 struct fc_frame *fp)
{
	struct fc_frame_header *fh = fc_frame_header_get(fp);
	struct fc_exch *ep;
	struct fc_seq *sp = NULL;
	u32 f_ctl;
	u16 xid;

	f_ctl = ntoh24(fh->fh_f_ctl);
	WARN_ON((f_ctl & FC_FC_SEQ_CTX) != FC_FC_SEQ_CTX);
	xid = ntohs((f_ctl & FC_FC_EX_CTX) ? fh->fh_ox_id : fh->fh_rx_id);
	ep = fc_exch_find(mp, xid);
	if (!ep)
		return NULL;
	if (ep->seq.id == fh->fh_seq_id) {
		/*
		 * Save the RX_ID if we didn't previously know it.
		 */
		sp = &ep->seq;
		if ((f_ctl & FC_FC_EX_CTX) != 0 &&
		    ep->rxid == FC_XID_UNKNOWN) {
			ep->rxid = ntohs(fh->fh_rx_id);
		}
	}
	fc_exch_release(ep);
	return sp;
}

/*
 * Set addresses for an exchange.
 * Note this must be done before the first sequence of the exchange is sent.
 */
static void fc_exch_set_addr(struct fc_exch *ep,
			     u32 orig_id, u32 resp_id)
{
	ep->oid = orig_id;
	if (ep->esb_stat & ESB_ST_RESP) {
		ep->sid = resp_id;
		ep->did = orig_id;
	} else {
		ep->sid = orig_id;
		ep->did = resp_id;
	}
}

static struct fc_seq *fc_seq_start_next_locked(struct fc_seq *sp)
{
	struct fc_exch *ep = fc_seq_exch(sp);

	sp = fc_seq_alloc(ep, ep->seq_id++);
	FC_DEBUG_EXCH("exch %4x f_ctl %6x seq %2x\n",
		      ep->xid, ep->f_ctl, sp->id);
	return sp;
}
/*
 * Allocate a new sequence on the same exchange as the supplied sequence.
 * This will never return NULL.
 */
struct fc_seq *fc_seq_start_next(struct fc_seq *sp)
{
	struct fc_exch *ep = fc_seq_exch(sp);

	spin_lock_bh(&ep->ex_lock);
	WARN_ON((ep->esb_stat & ESB_ST_COMPLETE) != 0);
	sp = fc_seq_start_next_locked(sp);
	spin_unlock_bh(&ep->ex_lock);

	return sp;
}
EXPORT_SYMBOL(fc_seq_start_next);

int fc_seq_send(struct fc_lport *lp, struct fc_seq *sp, struct fc_frame *fp)
{
	struct fc_exch *ep;
	struct fc_frame_header *fh = fc_frame_header_get(fp);
	int error;
	u32	f_ctl;

	ep = fc_seq_exch(sp);
	WARN_ON((ep->esb_stat & ESB_ST_SEQ_INIT) != ESB_ST_SEQ_INIT);

	f_ctl = ntoh24(fh->fh_f_ctl);
	fc_exch_setup_hdr(ep, fp, f_ctl);

	/*
	 * update sequence count if this frame is carrying
	 * multiple FC frames when sequence offload is enabled
	 * by LLD.
	 */
	if (fr_max_payload(fp))
		sp->cnt += DIV_ROUND_UP((fr_len(fp) - sizeof(*fh)),
					fr_max_payload(fp));
	else
		sp->cnt++;

	/*
	 * Send the frame.
	 */
	error = lp->tt.frame_send(lp, fp);

	/*
	 * Update the exchange and sequence flags,
	 * assuming all frames for the sequence have been sent.
	 * We can only be called to send once for each sequence.
	 */
	spin_lock_bh(&ep->ex_lock);
	ep->f_ctl = f_ctl & ~FC_FC_FIRST_SEQ;	/* not first seq */
	if (f_ctl & (FC_FC_END_SEQ | FC_FC_SEQ_INIT))
		ep->esb_stat &= ~ESB_ST_SEQ_INIT;
	spin_unlock_bh(&ep->ex_lock);
	return error;
}
EXPORT_SYMBOL(fc_seq_send);

void fc_seq_els_rsp_send(struct fc_seq *sp, enum fc_els_cmd els_cmd,
			 struct fc_seq_els_data *els_data)
{
	switch (els_cmd) {
	case ELS_LS_RJT:
		fc_seq_ls_rjt(sp, els_data->reason, els_data->explan);
		break;
	case ELS_LS_ACC:
		fc_seq_ls_acc(sp);
		break;
	case ELS_RRQ:
		fc_exch_els_rrq(sp, els_data->fp);
		break;
	case ELS_REC:
		fc_exch_els_rec(sp, els_data->fp);
		break;
	default:
		FC_DBG("Invalid ELS CMD:%x\n", els_cmd);
	}
}
EXPORT_SYMBOL(fc_seq_els_rsp_send);

/*
 * Send a sequence, which is also the last sequence in the exchange.
 */
static void fc_seq_send_last(struct fc_seq *sp, struct fc_frame *fp,
			     enum fc_rctl rctl, enum fc_fh_type fh_type)
{
	u32 f_ctl;
	struct fc_exch *ep = fc_seq_exch(sp);

	f_ctl = FC_FC_LAST_SEQ | FC_FC_END_SEQ | FC_FC_SEQ_INIT;
	f_ctl |= ep->f_ctl;
	fc_fill_fc_hdr(fp, rctl, ep->did, ep->sid, fh_type, f_ctl, 0);
	fc_seq_send(ep->lp, sp, fp);
}

/*
 * Send ACK_1 (or equiv.) indicating we received something.
 * The frame we're acking is supplied.
 */
static void fc_seq_send_ack(struct fc_seq *sp, const struct fc_frame *rx_fp)
{
	struct fc_frame *fp;
	struct fc_frame_header *rx_fh;
	struct fc_frame_header *fh;
	struct fc_exch *ep = fc_seq_exch(sp);
	struct fc_lport *lp = ep->lp;
	unsigned int f_ctl;

	/*
	 * Don't send ACKs for class 3.
	 */
	if (fc_sof_needs_ack(fr_sof(rx_fp))) {
		fp = fc_frame_alloc(lp, 0);
		if (!fp)
			return;

		fh = fc_frame_header_get(fp);
		fh->fh_r_ctl = FC_RCTL_ACK_1;
		fh->fh_type = FC_TYPE_BLS;

		/*
		 * Form f_ctl by inverting EX_CTX and SEQ_CTX (bits 23, 22).
		 * Echo FIRST_SEQ, LAST_SEQ, END_SEQ, END_CONN, SEQ_INIT.
		 * Bits 9-8 are meaningful (retransmitted or unidirectional).
		 * Last ACK uses bits 7-6 (continue sequence),
		 * bits 5-4 are meaningful (what kind of ACK to use).
		 */
		rx_fh = fc_frame_header_get(rx_fp);
		f_ctl = ntoh24(rx_fh->fh_f_ctl);
		f_ctl &= FC_FC_EX_CTX | FC_FC_SEQ_CTX |
			FC_FC_FIRST_SEQ | FC_FC_LAST_SEQ |
			FC_FC_END_SEQ | FC_FC_END_CONN | FC_FC_SEQ_INIT |
			FC_FC_RETX_SEQ | FC_FC_UNI_TX;
		f_ctl ^= FC_FC_EX_CTX | FC_FC_SEQ_CTX;
		hton24(fh->fh_f_ctl, f_ctl);

		fc_exch_setup_hdr(ep, fp, f_ctl);
		fh->fh_seq_id = rx_fh->fh_seq_id;
		fh->fh_seq_cnt = rx_fh->fh_seq_cnt;
		fh->fh_parm_offset = htonl(1);	/* ack single frame */

		fr_sof(fp) = fr_sof(rx_fp);
		if (f_ctl & FC_FC_END_SEQ)
			fr_eof(fp) = FC_EOF_T;
		else
			fr_eof(fp) = FC_EOF_N;

		(void) lp->tt.frame_send(lp, fp);
	}
}

/*
 * Send BLS Reject.
 * This is for rejecting BA_ABTS only.
 */
static void fc_exch_send_ba_rjt(struct fc_frame *rx_fp,
				enum fc_ba_rjt_reason reason,
				enum fc_ba_rjt_explan explan)
{
	struct fc_frame *fp;
	struct fc_frame_header *rx_fh;
	struct fc_frame_header *fh;
	struct fc_ba_rjt *rp;
	struct fc_lport *lp;
	unsigned int f_ctl;

	lp = fr_dev(rx_fp);
	fp = fc_frame_alloc(lp, sizeof(*rp));
	if (!fp)
		return;
	fh = fc_frame_header_get(fp);
	rx_fh = fc_frame_header_get(rx_fp);

	memset(fh, 0, sizeof(*fh) + sizeof(*rp));

	rp = fc_frame_payload_get(fp, sizeof(*rp));
	rp->br_reason = reason;
	rp->br_explan = explan;

	/*
	 * seq_id, cs_ctl, df_ctl and param/offset are zero.
	 */
	memcpy(fh->fh_s_id, rx_fh->fh_d_id, 3);
	memcpy(fh->fh_d_id, rx_fh->fh_s_id, 3);
	fh->fh_ox_id = rx_fh->fh_rx_id;
	fh->fh_rx_id = rx_fh->fh_ox_id;
	fh->fh_seq_cnt = rx_fh->fh_seq_cnt;
	fh->fh_r_ctl = FC_RCTL_BA_RJT;
	fh->fh_type = FC_TYPE_BLS;

	/*
	 * Form f_ctl by inverting EX_CTX and SEQ_CTX (bits 23, 22).
	 * Echo FIRST_SEQ, LAST_SEQ, END_SEQ, END_CONN, SEQ_INIT.
	 * Bits 9-8 are meaningful (retransmitted or unidirectional).
	 * Last ACK uses bits 7-6 (continue sequence),
	 * bits 5-4 are meaningful (what kind of ACK to use).
	 * Always set LAST_SEQ, END_SEQ.
	 */
	f_ctl = ntoh24(rx_fh->fh_f_ctl);
	f_ctl &= FC_FC_EX_CTX | FC_FC_SEQ_CTX |
		FC_FC_END_CONN | FC_FC_SEQ_INIT |
		FC_FC_RETX_SEQ | FC_FC_UNI_TX;
	f_ctl ^= FC_FC_EX_CTX | FC_FC_SEQ_CTX;
	f_ctl |= FC_FC_LAST_SEQ | FC_FC_END_SEQ;
	f_ctl &= ~FC_FC_FIRST_SEQ;
	hton24(fh->fh_f_ctl, f_ctl);

	fr_sof(fp) = fc_sof_class(fr_sof(rx_fp));
	fr_eof(fp) = FC_EOF_T;
	if (fc_sof_needs_ack(fr_sof(fp)))
		fr_eof(fp) = FC_EOF_N;

	(void) lp->tt.frame_send(lp, fp);
}

/*
 * Handle an incoming ABTS.  This would be for target mode usually,
 * but could be due to lost FCP transfer ready, confirm or RRQ.
 * We always handle this as an exchange abort, ignoring the parameter.
 */
static void fc_exch_recv_abts(struct fc_exch *ep, struct fc_frame *rx_fp)
{
	struct fc_frame *fp;
	struct fc_ba_acc *ap;
	struct fc_frame_header *fh;
	struct fc_seq *sp;

	if (!ep)
		goto reject;
	spin_lock_bh(&ep->ex_lock);
	if (ep->esb_stat & ESB_ST_COMPLETE) {
		spin_unlock_bh(&ep->ex_lock);
		goto reject;
	}
	if (!(ep->esb_stat & ESB_ST_REC_QUAL))
		fc_exch_hold(ep);		/* hold for REC_QUAL */
	ep->esb_stat |= ESB_ST_ABNORMAL | ESB_ST_REC_QUAL;
	fc_exch_timer_set_locked(ep, ep->r_a_tov);

	fp = fc_frame_alloc(ep->lp, sizeof(*ap));
	if (!fp) {
		spin_unlock_bh(&ep->ex_lock);
		goto free;
	}
	fh = fc_frame_header_get(fp);
	ap = fc_frame_payload_get(fp, sizeof(*ap));
	memset(ap, 0, sizeof(*ap));
	sp = &ep->seq;
	ap->ba_high_seq_cnt = htons(0xffff);
	if (sp->ssb_stat & SSB_ST_RESP) {
		ap->ba_seq_id = sp->id;
		ap->ba_seq_id_val = FC_BA_SEQ_ID_VAL;
		ap->ba_high_seq_cnt = fh->fh_seq_cnt;
		ap->ba_low_seq_cnt = htons(sp->cnt);
	}
	sp = fc_seq_start_next_locked(sp);
	spin_unlock_bh(&ep->ex_lock);
	fc_seq_send_last(sp, fp, FC_RCTL_BA_ACC, FC_TYPE_BLS);
	fc_frame_free(rx_fp);
	return;

reject:
	fc_exch_send_ba_rjt(rx_fp, FC_BA_RJT_UNABLE, FC_BA_RJT_INV_XID);
free:
	fc_frame_free(rx_fp);
}

/*
 * Handle receive where the other end is originating the sequence.
 */
static void fc_exch_recv_req(struct fc_lport *lp, struct fc_exch_mgr *mp,
			     struct fc_frame *fp)
{
	struct fc_frame_header *fh = fc_frame_header_get(fp);
	struct fc_seq *sp = NULL;
	struct fc_exch *ep = NULL;
	enum fc_sof sof;
	enum fc_eof eof;
	u32 f_ctl;
	enum fc_pf_rjt_reason reject;

	fr_seq(fp) = NULL;
	reject = fc_seq_lookup_recip(mp, fp);
	if (reject == FC_RJT_NONE) {
		sp = fr_seq(fp);	/* sequence will be held */
		ep = fc_seq_exch(sp);
		sof = fr_sof(fp);
		eof = fr_eof(fp);
		f_ctl = ntoh24(fh->fh_f_ctl);
		fc_seq_send_ack(sp, fp);

		/*
		 * Call the receive function.
		 *
		 * The receive function may allocate a new sequence
		 * over the old one, so we shouldn't change the
		 * sequence after this.
		 *
		 * The frame will be freed by the receive function.
		 * If new exch resp handler is valid then call that
		 * first.
		 */
		if (ep->resp)
			ep->resp(sp, fp, ep->arg);
		else
			lp->tt.lport_recv(lp, sp, fp);
		fc_exch_release(ep);	/* release from lookup */
	} else {
		FC_DEBUG_EXCH("exch/seq lookup failed: reject %x\n", reject);
		fc_frame_free(fp);
	}
}

/*
 * Handle receive where the other end is originating the sequence in
 * response to our exchange.
 */
static void fc_exch_recv_seq_resp(struct fc_exch_mgr *mp, struct fc_frame *fp)
{
	struct fc_frame_header *fh = fc_frame_header_get(fp);
	struct fc_seq *sp;
	struct fc_exch *ep;
	enum fc_sof sof;
	u32 f_ctl;
	void (*resp)(struct fc_seq *, struct fc_frame *fp, void *arg);
	void *ex_resp_arg;
	int rc;

	ep = fc_exch_find(mp, ntohs(fh->fh_ox_id));
	if (!ep) {
		atomic_inc(&mp->stats.xid_not_found);
		goto out;
	}
	if (ep->esb_stat & ESB_ST_COMPLETE) {
		atomic_inc(&mp->stats.xid_not_found);
		goto out;
	}
	if (ep->rxid == FC_XID_UNKNOWN)
		ep->rxid = ntohs(fh->fh_rx_id);
	if (ep->sid != 0 && ep->sid != ntoh24(fh->fh_d_id)) {
		atomic_inc(&mp->stats.xid_not_found);
		goto rel;
	}
	if (ep->did != ntoh24(fh->fh_s_id) &&
	    ep->did != FC_FID_FLOGI) {
		atomic_inc(&mp->stats.xid_not_found);
		goto rel;
	}
	sof = fr_sof(fp);
	if (fc_sof_is_init(sof)) {
		sp = fc_seq_start_next(&ep->seq);
		sp->id = fh->fh_seq_id;
		sp->ssb_stat |= SSB_ST_RESP;
	} else {
		sp = &ep->seq;
		if (sp->id != fh->fh_seq_id) {
			atomic_inc(&mp->stats.seq_not_found);
			goto rel;
		}
	}
	f_ctl = ntoh24(fh->fh_f_ctl);
	fr_seq(fp) = sp;
	if (f_ctl & FC_FC_SEQ_INIT)
		ep->esb_stat |= ESB_ST_SEQ_INIT;

	if (fc_sof_needs_ack(sof))
		fc_seq_send_ack(sp, fp);
	resp = ep->resp;
	ex_resp_arg = ep->arg;

	if (fh->fh_type != FC_TYPE_FCP && fr_eof(fp) == FC_EOF_T &&
	    (f_ctl & (FC_FC_LAST_SEQ | FC_FC_END_SEQ)) ==
	    (FC_FC_LAST_SEQ | FC_FC_END_SEQ)) {
		spin_lock_bh(&ep->ex_lock);
		rc = fc_exch_done_locked(ep);
		WARN_ON(fc_seq_exch(sp) != ep);
		spin_unlock_bh(&ep->ex_lock);
		if (!rc)
			fc_exch_mgr_delete_ep(ep);
	}

	/*
	 * Call the receive function.
	 * The sequence is held (has a refcnt) for us,
	 * but not for the receive function.
	 *
	 * The receive function may allocate a new sequence
	 * over the old one, so we shouldn't change the
	 * sequence after this.
	 *
	 * The frame will be freed by the receive function.
	 * If new exch resp handler is valid then call that
	 * first.
	 */
	if (resp)
		resp(sp, fp, ex_resp_arg);
	else
		fc_frame_free(fp);
	fc_exch_release(ep);
	return;
rel:
	fc_exch_release(ep);
out:
	fc_frame_free(fp);
}

/*
 * Handle receive for a sequence where other end is responding to our sequence.
 */
static void fc_exch_recv_resp(struct fc_exch_mgr *mp, struct fc_frame *fp)
{
	struct fc_seq *sp;

	sp = fc_seq_lookup_orig(mp, fp);	/* doesn't hold sequence */
	if (!sp) {
		atomic_inc(&mp->stats.xid_not_found);
		FC_DEBUG_EXCH("seq lookup failed\n");
	} else {
		atomic_inc(&mp->stats.non_bls_resp);
		FC_DEBUG_EXCH("non-BLS response to sequence");
	}
	fc_frame_free(fp);
}

/*
 * Handle the response to an ABTS for exchange or sequence.
 * This can be BA_ACC or BA_RJT.
 */
static void fc_exch_abts_resp(struct fc_exch *ep, struct fc_frame *fp)
{
	void (*resp)(struct fc_seq *, struct fc_frame *fp, void *arg);
	void *ex_resp_arg;
	struct fc_frame_header *fh;
	struct fc_ba_acc *ap;
	struct fc_seq *sp;
	u16 low;
	u16 high;
	int rc = 1, has_rec = 0;

	fh = fc_frame_header_get(fp);
	FC_DEBUG_EXCH("exch: BLS rctl %x - %s\n",
		      fh->fh_r_ctl, fc_exch_rctl_name(fh->fh_r_ctl));

	if (cancel_delayed_work_sync(&ep->timeout_work))
		fc_exch_release(ep);	/* release from pending timer hold */

	spin_lock_bh(&ep->ex_lock);
	switch (fh->fh_r_ctl) {
	case FC_RCTL_BA_ACC:
		ap = fc_frame_payload_get(fp, sizeof(*ap));
		if (!ap)
			break;

		/*
		 * Decide whether to establish a Recovery Qualifier.
		 * We do this if there is a non-empty SEQ_CNT range and
		 * SEQ_ID is the same as the one we aborted.
		 */
		low = ntohs(ap->ba_low_seq_cnt);
		high = ntohs(ap->ba_high_seq_cnt);
		if ((ep->esb_stat & ESB_ST_REC_QUAL) == 0 &&
		    (ap->ba_seq_id_val != FC_BA_SEQ_ID_VAL ||
		     ap->ba_seq_id == ep->seq_id) && low != high) {
			ep->esb_stat |= ESB_ST_REC_QUAL;
			fc_exch_hold(ep);  /* hold for recovery qualifier */
			has_rec = 1;
		}
		break;
	case FC_RCTL_BA_RJT:
		break;
	default:
		break;
	}

	resp = ep->resp;
	ex_resp_arg = ep->arg;

	/* do we need to do some other checks here. Can we reuse more of
	 * fc_exch_recv_seq_resp
	 */
	sp = &ep->seq;
	/*
	 * do we want to check END_SEQ as well as LAST_SEQ here?
	 */
	if (ep->fh_type != FC_TYPE_FCP &&
	    ntoh24(fh->fh_f_ctl) & FC_FC_LAST_SEQ)
		rc = fc_exch_done_locked(ep);
	spin_unlock_bh(&ep->ex_lock);
	if (!rc)
		fc_exch_mgr_delete_ep(ep);

	if (resp)
		resp(sp, fp, ex_resp_arg);
	else
		fc_frame_free(fp);

	if (has_rec)
		fc_exch_timer_set(ep, ep->r_a_tov);

}

/*
 * Receive BLS sequence.
 * This is always a sequence initiated by the remote side.
 * We may be either the originator or recipient of the exchange.
 */
static void fc_exch_recv_bls(struct fc_exch_mgr *mp, struct fc_frame *fp)
{
	struct fc_frame_header *fh;
	struct fc_exch *ep;
	u32 f_ctl;

	fh = fc_frame_header_get(fp);
	f_ctl = ntoh24(fh->fh_f_ctl);
	fr_seq(fp) = NULL;

	ep = fc_exch_find(mp, (f_ctl & FC_FC_EX_CTX) ?
			  ntohs(fh->fh_ox_id) : ntohs(fh->fh_rx_id));
	if (ep && (f_ctl & FC_FC_SEQ_INIT)) {
		spin_lock_bh(&ep->ex_lock);
		ep->esb_stat |= ESB_ST_SEQ_INIT;
		spin_unlock_bh(&ep->ex_lock);
	}
	if (f_ctl & FC_FC_SEQ_CTX) {
		/*
		 * A response to a sequence we initiated.
		 * This should only be ACKs for class 2 or F.
		 */
		switch (fh->fh_r_ctl) {
		case FC_RCTL_ACK_1:
		case FC_RCTL_ACK_0:
			break;
		default:
			FC_DEBUG_EXCH("BLS rctl %x - %s received",
				      fh->fh_r_ctl,
				      fc_exch_rctl_name(fh->fh_r_ctl));
			break;
		}
		fc_frame_free(fp);
	} else {
		switch (fh->fh_r_ctl) {
		case FC_RCTL_BA_RJT:
		case FC_RCTL_BA_ACC:
			if (ep)
				fc_exch_abts_resp(ep, fp);
			else
				fc_frame_free(fp);
			break;
		case FC_RCTL_BA_ABTS:
			fc_exch_recv_abts(ep, fp);
			break;
		default:			/* ignore junk */
			fc_frame_free(fp);
			break;
		}
	}
	if (ep)
		fc_exch_release(ep);	/* release hold taken by fc_exch_find */
}

/*
 * Accept sequence with LS_ACC.
 * If this fails due to allocation or transmit congestion, assume the
 * originator will repeat the sequence.
 */
static void fc_seq_ls_acc(struct fc_seq *req_sp)
{
	struct fc_seq *sp;
	struct fc_els_ls_acc *acc;
	struct fc_frame *fp;

	sp = fc_seq_start_next(req_sp);
	fp = fc_frame_alloc(fc_seq_exch(sp)->lp, sizeof(*acc));
	if (fp) {
		acc = fc_frame_payload_get(fp, sizeof(*acc));
		memset(acc, 0, sizeof(*acc));
		acc->la_cmd = ELS_LS_ACC;
		fc_seq_send_last(sp, fp, FC_RCTL_ELS_REP, FC_TYPE_ELS);
	}
}

/*
 * Reject sequence with ELS LS_RJT.
 * If this fails due to allocation or transmit congestion, assume the
 * originator will repeat the sequence.
 */
static void fc_seq_ls_rjt(struct fc_seq *req_sp, enum fc_els_rjt_reason reason,
			  enum fc_els_rjt_explan explan)
{
	struct fc_seq *sp;
	struct fc_els_ls_rjt *rjt;
	struct fc_frame *fp;

	sp = fc_seq_start_next(req_sp);
	fp = fc_frame_alloc(fc_seq_exch(sp)->lp, sizeof(*rjt));
	if (fp) {
		rjt = fc_frame_payload_get(fp, sizeof(*rjt));
		memset(rjt, 0, sizeof(*rjt));
		rjt->er_cmd = ELS_LS_RJT;
		rjt->er_reason = reason;
		rjt->er_explan = explan;
		fc_seq_send_last(sp, fp, FC_RCTL_ELS_REP, FC_TYPE_ELS);
	}
}

static void fc_exch_reset(struct fc_exch *ep)
{
	struct fc_seq *sp;
	void (*resp)(struct fc_seq *, struct fc_frame *, void *);
	void *arg;
	int rc = 1;

	spin_lock_bh(&ep->ex_lock);
	ep->state |= FC_EX_RST_CLEANUP;
	/*
	 * we really want to call del_timer_sync, but cannot due
	 * to the lport calling with the lport lock held (some resp
	 * functions can also grab the lport lock which could cause
	 * a deadlock).
	 */
	if (cancel_delayed_work(&ep->timeout_work))
		atomic_dec(&ep->ex_refcnt);	/* drop hold for timer */
	resp = ep->resp;
	ep->resp = NULL;
	if (ep->esb_stat & ESB_ST_REC_QUAL)
		atomic_dec(&ep->ex_refcnt);	/* drop hold for rec_qual */
	ep->esb_stat &= ~ESB_ST_REC_QUAL;
	arg = ep->arg;
	sp = &ep->seq;
	rc = fc_exch_done_locked(ep);
	spin_unlock_bh(&ep->ex_lock);
	if (!rc)
		fc_exch_mgr_delete_ep(ep);

	if (resp)
		resp(sp, ERR_PTR(-FC_EX_CLOSED), arg);
}

/*
 * Reset an exchange manager, releasing all sequences and exchanges.
 * If sid is non-zero, reset only exchanges we source from that FID.
 * If did is non-zero, reset only exchanges destined to that FID.
 */
void fc_exch_mgr_reset(struct fc_lport *lp, u32 sid, u32 did)
{
	struct fc_exch *ep;
	struct fc_exch *next;
	struct fc_exch_mgr *mp = lp->emp;

	spin_lock_bh(&mp->em_lock);
restart:
	list_for_each_entry_safe(ep, next, &mp->ex_list, ex_list) {
		if ((sid == 0 || sid == ep->sid) &&
		    (did == 0 || did == ep->did)) {
			fc_exch_hold(ep);
			spin_unlock_bh(&mp->em_lock);

			fc_exch_reset(ep);

			fc_exch_release(ep);
			spin_lock_bh(&mp->em_lock);

			/*
			 * must restart loop incase while lock was down
			 * multiple eps were released.
			 */
			goto restart;
		}
	}
	spin_unlock_bh(&mp->em_lock);
}
EXPORT_SYMBOL(fc_exch_mgr_reset);

/*
 * Handle incoming ELS REC - Read Exchange Concise.
 * Note that the requesting port may be different than the S_ID in the request.
 */
static void fc_exch_els_rec(struct fc_seq *sp, struct fc_frame *rfp)
{
	struct fc_frame *fp;
	struct fc_exch *ep;
	struct fc_exch_mgr *em;
	struct fc_els_rec *rp;
	struct fc_els_rec_acc *acc;
	enum fc_els_rjt_reason reason = ELS_RJT_LOGIC;
	enum fc_els_rjt_explan explan;
	u32 sid;
	u16 rxid;
	u16 oxid;

	rp = fc_frame_payload_get(rfp, sizeof(*rp));
	explan = ELS_EXPL_INV_LEN;
	if (!rp)
		goto reject;
	sid = ntoh24(rp->rec_s_id);
	rxid = ntohs(rp->rec_rx_id);
	oxid = ntohs(rp->rec_ox_id);

	/*
	 * Currently it's hard to find the local S_ID from the exchange
	 * manager.  This will eventually be fixed, but for now it's easier
	 * to lookup the subject exchange twice, once as if we were
	 * the initiator, and then again if we weren't.
	 */
	em = fc_seq_exch(sp)->em;
	ep = fc_exch_find(em, oxid);
	explan = ELS_EXPL_OXID_RXID;
	if (ep && ep->oid == sid) {
		if (ep->rxid != FC_XID_UNKNOWN &&
		    rxid != FC_XID_UNKNOWN &&
		    ep->rxid != rxid)
			goto rel;
	} else {
		if (ep)
			fc_exch_release(ep);
		ep = NULL;
		if (rxid != FC_XID_UNKNOWN)
			ep = fc_exch_find(em, rxid);
		if (!ep)
			goto reject;
	}

	fp = fc_frame_alloc(fc_seq_exch(sp)->lp, sizeof(*acc));
	if (!fp) {
		fc_exch_done(sp);
		goto out;
	}
	sp = fc_seq_start_next(sp);
	acc = fc_frame_payload_get(fp, sizeof(*acc));
	memset(acc, 0, sizeof(*acc));
	acc->reca_cmd = ELS_LS_ACC;
	acc->reca_ox_id = rp->rec_ox_id;
	memcpy(acc->reca_ofid, rp->rec_s_id, 3);
	acc->reca_rx_id = htons(ep->rxid);
	if (ep->sid == ep->oid)
		hton24(acc->reca_rfid, ep->did);
	else
		hton24(acc->reca_rfid, ep->sid);
	acc->reca_fc4value = htonl(ep->seq.rec_data);
	acc->reca_e_stat = htonl(ep->esb_stat & (ESB_ST_RESP |
						 ESB_ST_SEQ_INIT |
						 ESB_ST_COMPLETE));
	sp = fc_seq_start_next(sp);
	fc_seq_send_last(sp, fp, FC_RCTL_ELS_REP, FC_TYPE_ELS);
out:
	fc_exch_release(ep);
	fc_frame_free(rfp);
	return;

rel:
	fc_exch_release(ep);
reject:
	fc_seq_ls_rjt(sp, reason, explan);
	fc_frame_free(rfp);
}

/*
 * Handle response from RRQ.
 * Not much to do here, really.
 * Should report errors.
 *
 * TODO: fix error handler.
 */
static void fc_exch_rrq_resp(struct fc_seq *sp, struct fc_frame *fp, void *arg)
{
	struct fc_exch *aborted_ep = arg;
	unsigned int op;

	if (IS_ERR(fp)) {
		int err = PTR_ERR(fp);

		if (err == -FC_EX_CLOSED || err == -FC_EX_TIMEOUT)
			goto cleanup;
		FC_DBG("Cannot process RRQ, because of frame error %d\n", err);
		return;
	}

	op = fc_frame_payload_op(fp);
	fc_frame_free(fp);

	switch (op) {
	case ELS_LS_RJT:
		FC_DBG("LS_RJT for RRQ");
		/* fall through */
	case ELS_LS_ACC:
		goto cleanup;
	default:
		FC_DBG("unexpected response op %x for RRQ", op);
		return;
	}

cleanup:
	fc_exch_done(&aborted_ep->seq);
	/* drop hold for rec qual */
	fc_exch_release(aborted_ep);
}

/*
 * Send ELS RRQ - Reinstate Recovery Qualifier.
 * This tells the remote port to stop blocking the use of
 * the exchange and the seq_cnt range.
 */
static void fc_exch_rrq(struct fc_exch *ep)
{
	struct fc_lport *lp;
	struct fc_els_rrq *rrq;
	struct fc_frame *fp;
	struct fc_seq *rrq_sp;
	u32 did;

	lp = ep->lp;

	fp = fc_frame_alloc(lp, sizeof(*rrq));
	if (!fp)
		return;
	rrq = fc_frame_payload_get(fp, sizeof(*rrq));
	memset(rrq, 0, sizeof(*rrq));
	rrq->rrq_cmd = ELS_RRQ;
	hton24(rrq->rrq_s_id, ep->sid);
	rrq->rrq_ox_id = htons(ep->oxid);
	rrq->rrq_rx_id = htons(ep->rxid);

	did = ep->did;
	if (ep->esb_stat & ESB_ST_RESP)
		did = ep->sid;

	fc_fill_fc_hdr(fp, FC_RCTL_ELS_REQ, did,
		       fc_host_port_id(lp->host), FC_TYPE_ELS,
		       FC_FC_FIRST_SEQ | FC_FC_END_SEQ | FC_FC_SEQ_INIT, 0);

	rrq_sp = fc_exch_seq_send(lp, fp, fc_exch_rrq_resp, NULL, ep,
				  lp->e_d_tov);
	if (!rrq_sp) {
		ep->esb_stat |= ESB_ST_REC_QUAL;
		fc_exch_timer_set_locked(ep, ep->r_a_tov);
		return;
	}
}


/*
 * Handle incoming ELS RRQ - Reset Recovery Qualifier.
 */
static void fc_exch_els_rrq(struct fc_seq *sp, struct fc_frame *fp)
{
	struct fc_exch *ep;		/* request or subject exchange */
	struct fc_els_rrq *rp;
	u32 sid;
	u16 xid;
	enum fc_els_rjt_explan explan;

	rp = fc_frame_payload_get(fp, sizeof(*rp));
	explan = ELS_EXPL_INV_LEN;
	if (!rp)
		goto reject;

	/*
	 * lookup subject exchange.
	 */
	ep = fc_seq_exch(sp);
	sid = ntoh24(rp->rrq_s_id);		/* subject source */
	xid = ep->did == sid ? ntohs(rp->rrq_ox_id) : ntohs(rp->rrq_rx_id);
	ep = fc_exch_find(ep->em, xid);

	explan = ELS_EXPL_OXID_RXID;
	if (!ep)
		goto reject;
	spin_lock_bh(&ep->ex_lock);
	if (ep->oxid != ntohs(rp->rrq_ox_id))
		goto unlock_reject;
	if (ep->rxid != ntohs(rp->rrq_rx_id) &&
	    ep->rxid != FC_XID_UNKNOWN)
		goto unlock_reject;
	explan = ELS_EXPL_SID;
	if (ep->sid != sid)
		goto unlock_reject;

	/*
	 * Clear Recovery Qualifier state, and cancel timer if complete.
	 */
	if (ep->esb_stat & ESB_ST_REC_QUAL) {
		ep->esb_stat &= ~ESB_ST_REC_QUAL;
		atomic_dec(&ep->ex_refcnt);	/* drop hold for rec qual */
	}
	if (ep->esb_stat & ESB_ST_COMPLETE) {
		if (cancel_delayed_work(&ep->timeout_work))
			atomic_dec(&ep->ex_refcnt);	/* drop timer hold */
	}

	spin_unlock_bh(&ep->ex_lock);

	/*
	 * Send LS_ACC.
	 */
	fc_seq_ls_acc(sp);
	fc_frame_free(fp);
	return;

unlock_reject:
	spin_unlock_bh(&ep->ex_lock);
	fc_exch_release(ep);	/* drop hold from fc_exch_find */
reject:
	fc_seq_ls_rjt(sp, ELS_RJT_LOGIC, explan);
	fc_frame_free(fp);
}

struct fc_exch_mgr *fc_exch_mgr_alloc(struct fc_lport *lp,
				      enum fc_class class,
				      u16 min_xid, u16 max_xid)
{
	struct fc_exch_mgr *mp;
	size_t len;

	if (max_xid <= min_xid || min_xid == 0 || max_xid == FC_XID_UNKNOWN) {
		FC_DBG("Invalid min_xid 0x:%x and max_xid 0x:%x\n",
		       min_xid, max_xid);
		return NULL;
	}

	/*
	 * Memory need for EM
	 */
#define xid_ok(i, m1, m2) (((i) >= (m1)) && ((i) <= (m2)))
	len = (max_xid - min_xid + 1) * (sizeof(struct fc_exch *));
	len += sizeof(struct fc_exch_mgr);

	mp = kzalloc(len, GFP_ATOMIC);
	if (!mp)
		return NULL;

	mp->class = class;
	mp->total_exches = 0;
	mp->exches = (struct fc_exch **)(mp + 1);
	mp->lp = lp;
	/* adjust em exch xid range for offload */
	mp->min_xid = min_xid;
	mp->max_xid = max_xid;
	mp->last_xid = min_xid - 1;
	mp->max_read = 0;
	mp->last_read = 0;
	if (lp->lro_enabled && xid_ok(lp->lro_xid, min_xid, max_xid)) {
		mp->max_read = lp->lro_xid;
		mp->last_read = min_xid - 1;
		mp->last_xid = mp->max_read;
	} else {
		/* disable lro if no xid control over read */
		lp->lro_enabled = 0;
	}

	INIT_LIST_HEAD(&mp->ex_list);
	spin_lock_init(&mp->em_lock);

	mp->ep_pool = mempool_create_slab_pool(2, fc_em_cachep);
	if (!mp->ep_pool)
		goto free_mp;

	return mp;

free_mp:
	kfree(mp);
	return NULL;
}
EXPORT_SYMBOL(fc_exch_mgr_alloc);

void fc_exch_mgr_free(struct fc_exch_mgr *mp)
{
	WARN_ON(!mp);
	/*
	 * The total exch count must be zero
	 * before freeing exchange manager.
	 */
	WARN_ON(mp->total_exches != 0);
	mempool_destroy(mp->ep_pool);
	kfree(mp);
}
EXPORT_SYMBOL(fc_exch_mgr_free);

struct fc_exch *fc_exch_get(struct fc_lport *lp, struct fc_frame *fp)
{
	if (!lp || !lp->emp)
		return NULL;

	return fc_exch_alloc(lp->emp, fp, 0);
}
EXPORT_SYMBOL(fc_exch_get);

struct fc_seq *fc_exch_seq_send(struct fc_lport *lp,
				struct fc_frame *fp,
				void (*resp)(struct fc_seq *,
					     struct fc_frame *fp,
					     void *arg),
				void (*destructor)(struct fc_seq *, void *),
				void *arg, u32 timer_msec)
{
	struct fc_exch *ep;
	struct fc_seq *sp = NULL;
	struct fc_frame_header *fh;
	int rc = 1;

	ep = lp->tt.exch_get(lp, fp);
	if (!ep) {
		fc_frame_free(fp);
		return NULL;
	}
	ep->esb_stat |= ESB_ST_SEQ_INIT;
	fh = fc_frame_header_get(fp);
	fc_exch_set_addr(ep, ntoh24(fh->fh_s_id), ntoh24(fh->fh_d_id));
	ep->resp = resp;
	ep->destructor = destructor;
	ep->arg = arg;
	ep->r_a_tov = FC_DEF_R_A_TOV;
	ep->lp = lp;
	sp = &ep->seq;

	ep->fh_type = fh->fh_type; /* save for possbile timeout handling */
	ep->f_ctl = ntoh24(fh->fh_f_ctl);
	fc_exch_setup_hdr(ep, fp, ep->f_ctl);
	sp->cnt++;

	fc_fcp_ddp_setup(fr_fsp(fp), ep->xid);

	if (unlikely(lp->tt.frame_send(lp, fp)))
		goto err;

	if (timer_msec)
		fc_exch_timer_set_locked(ep, timer_msec);
	ep->f_ctl &= ~FC_FC_FIRST_SEQ;	/* not first seq */

	if (ep->f_ctl & FC_FC_SEQ_INIT)
		ep->esb_stat &= ~ESB_ST_SEQ_INIT;
	spin_unlock_bh(&ep->ex_lock);
	return sp;
err:
	rc = fc_exch_done_locked(ep);
	spin_unlock_bh(&ep->ex_lock);
	if (!rc)
		fc_exch_mgr_delete_ep(ep);
	return NULL;
}
EXPORT_SYMBOL(fc_exch_seq_send);

/*
 * Receive a frame
 */
void fc_exch_recv(struct fc_lport *lp, struct fc_exch_mgr *mp,
		  struct fc_frame *fp)
{
	struct fc_frame_header *fh = fc_frame_header_get(fp);
	u32 f_ctl;

	/* lport lock ? */
	if (!lp || !mp || (lp->state == LPORT_ST_NONE)) {
		FC_DBG("fc_lport or EM is not allocated and configured");
		fc_frame_free(fp);
		return;
	}

	/*
	 * If frame is marked invalid, just drop it.
	 */
	f_ctl = ntoh24(fh->fh_f_ctl);
	switch (fr_eof(fp)) {
	case FC_EOF_T:
		if (f_ctl & FC_FC_END_SEQ)
			skb_trim(fp_skb(fp), fr_len(fp) - FC_FC_FILL(f_ctl));
		/* fall through */
	case FC_EOF_N:
		if (fh->fh_type == FC_TYPE_BLS)
			fc_exch_recv_bls(mp, fp);
		else if ((f_ctl & (FC_FC_EX_CTX | FC_FC_SEQ_CTX)) ==
			 FC_FC_EX_CTX)
			fc_exch_recv_seq_resp(mp, fp);
		else if (f_ctl & FC_FC_SEQ_CTX)
			fc_exch_recv_resp(mp, fp);
		else
			fc_exch_recv_req(lp, mp, fp);
		break;
	default:
		FC_DBG("dropping invalid frame (eof %x)", fr_eof(fp));
		fc_frame_free(fp);
		break;
	}
}
EXPORT_SYMBOL(fc_exch_recv);

int fc_exch_init(struct fc_lport *lp)
{
	if (!lp->tt.exch_get) {
		/*
		 *  exch_put() should be NULL if
		 *  exch_get() is NULL
		 */
		WARN_ON(lp->tt.exch_put);
		lp->tt.exch_get = fc_exch_get;
	}

	if (!lp->tt.seq_start_next)
		lp->tt.seq_start_next = fc_seq_start_next;

	if (!lp->tt.exch_seq_send)
		lp->tt.exch_seq_send = fc_exch_seq_send;

	if (!lp->tt.seq_send)
		lp->tt.seq_send = fc_seq_send;

	if (!lp->tt.seq_els_rsp_send)
		lp->tt.seq_els_rsp_send = fc_seq_els_rsp_send;

	if (!lp->tt.exch_done)
		lp->tt.exch_done = fc_exch_done;

	if (!lp->tt.exch_mgr_reset)
		lp->tt.exch_mgr_reset = fc_exch_mgr_reset;

	if (!lp->tt.seq_exch_abort)
		lp->tt.seq_exch_abort = fc_seq_exch_abort;

	return 0;
}
EXPORT_SYMBOL(fc_exch_init);

int fc_setup_exch_mgr(void)
{
	fc_em_cachep = kmem_cache_create("libfc_em", sizeof(struct fc_exch),
					 0, SLAB_HWCACHE_ALIGN, NULL);
	if (!fc_em_cachep)
		return -ENOMEM;
	return 0;
}

void fc_destroy_exch_mgr(void)
{
	kmem_cache_destroy(fc_em_cachep);
}