summaryrefslogtreecommitdiffstats
path: root/drivers/infiniband/hw/qib/qib_driver.c
blob: 5423edcab51f4404905e47674957cb32e5f33b9f (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
/*
 * Copyright (c) 2006, 2007, 2008, 2009 QLogic Corporation. All rights reserved.
 * Copyright (c) 2003, 2004, 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.
 */

#include <linux/spinlock.h>
#include <linux/pci.h>
#include <linux/io.h>
#include <linux/delay.h>
#include <linux/netdevice.h>
#include <linux/vmalloc.h>
#include <linux/module.h>
#include <linux/prefetch.h>

#include "qib.h"

/*
 * The size has to be longer than this string, so we can append
 * board/chip information to it in the init code.
 */
const char ib_qib_version[] = QIB_DRIVER_VERSION "\n";

DEFINE_SPINLOCK(qib_devs_lock);
LIST_HEAD(qib_dev_list);
DEFINE_MUTEX(qib_mutex);	/* general driver use */

unsigned qib_ibmtu;
module_param_named(ibmtu, qib_ibmtu, uint, S_IRUGO);
MODULE_PARM_DESC(ibmtu, "Set max IB MTU (0=2KB, 1=256, 2=512, ... 5=4096");

unsigned qib_compat_ddr_negotiate = 1;
module_param_named(compat_ddr_negotiate, qib_compat_ddr_negotiate, uint,
		   S_IWUSR | S_IRUGO);
MODULE_PARM_DESC(compat_ddr_negotiate,
		 "Attempt pre-IBTA 1.2 DDR speed negotiation");

MODULE_LICENSE("Dual BSD/GPL");
MODULE_AUTHOR("QLogic <support@qlogic.com>");
MODULE_DESCRIPTION("QLogic IB driver");
MODULE_VERSION(QIB_DRIVER_VERSION);

/*
 * QIB_PIO_MAXIBHDR is the max IB header size allowed for in our
 * PIO send buffers.  This is well beyond anything currently
 * defined in the InfiniBand spec.
 */
#define QIB_PIO_MAXIBHDR 128

/*
 * QIB_MAX_PKT_RCV is the max # if packets processed per receive interrupt.
 */
#define QIB_MAX_PKT_RECV 64

struct qlogic_ib_stats qib_stats;

const char *qib_get_unit_name(int unit)
{
	static char iname[16];

	snprintf(iname, sizeof iname, "infinipath%u", unit);
	return iname;
}

/*
 * Return count of units with at least one port ACTIVE.
 */
int qib_count_active_units(void)
{
	struct qib_devdata *dd;
	struct qib_pportdata *ppd;
	unsigned long flags;
	int pidx, nunits_active = 0;

	spin_lock_irqsave(&qib_devs_lock, flags);
	list_for_each_entry(dd, &qib_dev_list, list) {
		if (!(dd->flags & QIB_PRESENT) || !dd->kregbase)
			continue;
		for (pidx = 0; pidx < dd->num_pports; ++pidx) {
			ppd = dd->pport + pidx;
			if (ppd->lid && (ppd->lflags & (QIBL_LINKINIT |
					 QIBL_LINKARMED | QIBL_LINKACTIVE))) {
				nunits_active++;
				break;
			}
		}
	}
	spin_unlock_irqrestore(&qib_devs_lock, flags);
	return nunits_active;
}

/*
 * Return count of all units, optionally return in arguments
 * the number of usable (present) units, and the number of
 * ports that are up.
 */
int qib_count_units(int *npresentp, int *nupp)
{
	int nunits = 0, npresent = 0, nup = 0;
	struct qib_devdata *dd;
	unsigned long flags;
	int pidx;
	struct qib_pportdata *ppd;

	spin_lock_irqsave(&qib_devs_lock, flags);

	list_for_each_entry(dd, &qib_dev_list, list) {
		nunits++;
		if ((dd->flags & QIB_PRESENT) && dd->kregbase)
			npresent++;
		for (pidx = 0; pidx < dd->num_pports; ++pidx) {
			ppd = dd->pport + pidx;
			if (ppd->lid && (ppd->lflags & (QIBL_LINKINIT |
					 QIBL_LINKARMED | QIBL_LINKACTIVE)))
				nup++;
		}
	}

	spin_unlock_irqrestore(&qib_devs_lock, flags);

	if (npresentp)
		*npresentp = npresent;
	if (nupp)
		*nupp = nup;

	return nunits;
}

/**
 * qib_wait_linkstate - wait for an IB link state change to occur
 * @dd: the qlogic_ib device
 * @state: the state to wait for
 * @msecs: the number of milliseconds to wait
 *
 * wait up to msecs milliseconds for IB link state change to occur for
 * now, take the easy polling route.  Currently used only by
 * qib_set_linkstate.  Returns 0 if state reached, otherwise
 * -ETIMEDOUT state can have multiple states set, for any of several
 * transitions.
 */
int qib_wait_linkstate(struct qib_pportdata *ppd, u32 state, int msecs)
{
	int ret;
	unsigned long flags;

	spin_lock_irqsave(&ppd->lflags_lock, flags);
	if (ppd->state_wanted) {
		spin_unlock_irqrestore(&ppd->lflags_lock, flags);
		ret = -EBUSY;
		goto bail;
	}
	ppd->state_wanted = state;
	spin_unlock_irqrestore(&ppd->lflags_lock, flags);
	wait_event_interruptible_timeout(ppd->state_wait,
					 (ppd->lflags & state),
					 msecs_to_jiffies(msecs));
	spin_lock_irqsave(&ppd->lflags_lock, flags);
	ppd->state_wanted = 0;
	spin_unlock_irqrestore(&ppd->lflags_lock, flags);

	if (!(ppd->lflags & state))
		ret = -ETIMEDOUT;
	else
		ret = 0;
bail:
	return ret;
}

int qib_set_linkstate(struct qib_pportdata *ppd, u8 newstate)
{
	u32 lstate;
	int ret;
	struct qib_devdata *dd = ppd->dd;
	unsigned long flags;

	switch (newstate) {
	case QIB_IB_LINKDOWN_ONLY:
		dd->f_set_ib_cfg(ppd, QIB_IB_CFG_LSTATE,
				 IB_LINKCMD_DOWN | IB_LINKINITCMD_NOP);
		/* don't wait */
		ret = 0;
		goto bail;

	case QIB_IB_LINKDOWN:
		dd->f_set_ib_cfg(ppd, QIB_IB_CFG_LSTATE,
				 IB_LINKCMD_DOWN | IB_LINKINITCMD_POLL);
		/* don't wait */
		ret = 0;
		goto bail;

	case QIB_IB_LINKDOWN_SLEEP:
		dd->f_set_ib_cfg(ppd, QIB_IB_CFG_LSTATE,
				 IB_LINKCMD_DOWN | IB_LINKINITCMD_SLEEP);
		/* don't wait */
		ret = 0;
		goto bail;

	case QIB_IB_LINKDOWN_DISABLE:
		dd->f_set_ib_cfg(ppd, QIB_IB_CFG_LSTATE,
				 IB_LINKCMD_DOWN | IB_LINKINITCMD_DISABLE);
		/* don't wait */
		ret = 0;
		goto bail;

	case QIB_IB_LINKARM:
		if (ppd->lflags & QIBL_LINKARMED) {
			ret = 0;
			goto bail;
		}
		if (!(ppd->lflags & (QIBL_LINKINIT | QIBL_LINKACTIVE))) {
			ret = -EINVAL;
			goto bail;
		}
		/*
		 * Since the port can be ACTIVE when we ask for ARMED,
		 * clear QIBL_LINKV so we can wait for a transition.
		 * If the link isn't ARMED, then something else happened
		 * and there is no point waiting for ARMED.
		 */
		spin_lock_irqsave(&ppd->lflags_lock, flags);
		ppd->lflags &= ~QIBL_LINKV;
		spin_unlock_irqrestore(&ppd->lflags_lock, flags);
		dd->f_set_ib_cfg(ppd, QIB_IB_CFG_LSTATE,
				 IB_LINKCMD_ARMED | IB_LINKINITCMD_NOP);
		lstate = QIBL_LINKV;
		break;

	case QIB_IB_LINKACTIVE:
		if (ppd->lflags & QIBL_LINKACTIVE) {
			ret = 0;
			goto bail;
		}
		if (!(ppd->lflags & QIBL_LINKARMED)) {
			ret = -EINVAL;
			goto bail;
		}
		dd->f_set_ib_cfg(ppd, QIB_IB_CFG_LSTATE,
				 IB_LINKCMD_ACTIVE | IB_LINKINITCMD_NOP);
		lstate = QIBL_LINKACTIVE;
		break;

	default:
		ret = -EINVAL;
		goto bail;
	}
	ret = qib_wait_linkstate(ppd, lstate, 10);

bail:
	return ret;
}

/*
 * Get address of eager buffer from it's index (allocated in chunks, not
 * contiguous).
 */
static inline void *qib_get_egrbuf(const struct qib_ctxtdata *rcd, u32 etail)
{
	const u32 chunk = etail >> rcd->rcvegrbufs_perchunk_shift;
	const u32 idx =  etail & ((u32)rcd->rcvegrbufs_perchunk - 1);

	return rcd->rcvegrbuf[chunk] + (idx << rcd->dd->rcvegrbufsize_shift);
}

/*
 * Returns 1 if error was a CRC, else 0.
 * Needed for some chip's synthesized error counters.
 */
static u32 qib_rcv_hdrerr(struct qib_ctxtdata *rcd, struct qib_pportdata *ppd,
			  u32 ctxt, u32 eflags, u32 l, u32 etail,
			  __le32 *rhf_addr, struct qib_message_header *rhdr)
{
	u32 ret = 0;

	if (eflags & (QLOGIC_IB_RHF_H_ICRCERR | QLOGIC_IB_RHF_H_VCRCERR))
		ret = 1;
	else if (eflags == QLOGIC_IB_RHF_H_TIDERR) {
		/* For TIDERR and RC QPs premptively schedule a NAK */
		struct qib_ib_header *hdr = (struct qib_ib_header *) rhdr;
		struct qib_other_headers *ohdr = NULL;
		struct qib_ibport *ibp = &ppd->ibport_data;
		struct qib_qp *qp = NULL;
		u32 tlen = qib_hdrget_length_in_bytes(rhf_addr);
		u16 lid  = be16_to_cpu(hdr->lrh[1]);
		int lnh = be16_to_cpu(hdr->lrh[0]) & 3;
		u32 qp_num;
		u32 opcode;
		u32 psn;
		int diff;

		/* Sanity check packet */
		if (tlen < 24)
			goto drop;

		if (lid < QIB_MULTICAST_LID_BASE) {
			lid &= ~((1 << ppd->lmc) - 1);
			if (unlikely(lid != ppd->lid))
				goto drop;
		}

		/* Check for GRH */
		if (lnh == QIB_LRH_BTH)
			ohdr = &hdr->u.oth;
		else if (lnh == QIB_LRH_GRH) {
			u32 vtf;

			ohdr = &hdr->u.l.oth;
			if (hdr->u.l.grh.next_hdr != IB_GRH_NEXT_HDR)
				goto drop;
			vtf = be32_to_cpu(hdr->u.l.grh.version_tclass_flow);
			if ((vtf >> IB_GRH_VERSION_SHIFT) != IB_GRH_VERSION)
				goto drop;
		} else
			goto drop;

		/* Get opcode and PSN from packet */
		opcode = be32_to_cpu(ohdr->bth[0]);
		opcode >>= 24;
		psn = be32_to_cpu(ohdr->bth[2]);

		/* Get the destination QP number. */
		qp_num = be32_to_cpu(ohdr->bth[1]) & QIB_QPN_MASK;
		if (qp_num != QIB_MULTICAST_QPN) {
			int ruc_res;
			qp = qib_lookup_qpn(ibp, qp_num);
			if (!qp)
				goto drop;

			/*
			 * Handle only RC QPs - for other QP types drop error
			 * packet.
			 */
			spin_lock(&qp->r_lock);

			/* Check for valid receive state. */
			if (!(ib_qib_state_ops[qp->state] &
			      QIB_PROCESS_RECV_OK)) {
				ibp->n_pkt_drops++;
				goto unlock;
			}

			switch (qp->ibqp.qp_type) {
			case IB_QPT_RC:
				ruc_res =
					qib_ruc_check_hdr(
						ibp, hdr,
						lnh == QIB_LRH_GRH,
						qp,
						be32_to_cpu(ohdr->bth[0]));
				if (ruc_res)
					goto unlock;

				/* Only deal with RDMA Writes for now */
				if (opcode <
				    IB_OPCODE_RC_RDMA_READ_RESPONSE_FIRST) {
					diff = qib_cmp24(psn, qp->r_psn);
					if (!qp->r_nak_state && diff >= 0) {
						ibp->n_rc_seqnak++;
						qp->r_nak_state =
							IB_NAK_PSN_ERROR;
						/* Use the expected PSN. */
						qp->r_ack_psn = qp->r_psn;
						/*
						 * Wait to send the sequence
						 * NAK until all packets
						 * in the receive queue have
						 * been processed.
						 * Otherwise, we end up
						 * propagating congestion.
						 */
						if (list_empty(&qp->rspwait)) {
							qp->r_flags |=
								QIB_R_RSP_NAK;
							atomic_inc(
								&qp->refcount);
							list_add_tail(
							 &qp->rspwait,
							 &rcd->qp_wait_list);
						}
					} /* Out of sequence NAK */
				} /* QP Request NAKs */
				break;
			case IB_QPT_SMI:
			case IB_QPT_GSI:
			case IB_QPT_UD:
			case IB_QPT_UC:
			default:
				/* For now don't handle any other QP types */
				break;
			}

unlock:
			spin_unlock(&qp->r_lock);
			/*
			 * Notify qib_destroy_qp() if it is waiting
			 * for us to finish.
			 */
			if (atomic_dec_and_test(&qp->refcount))
				wake_up(&qp->wait);
		} /* Unicast QP */
	} /* Valid packet with TIDErr */

drop:
	return ret;
}

/*
 * qib_kreceive - receive a packet
 * @rcd: the qlogic_ib context
 * @llic: gets count of good packets needed to clear lli,
 *          (used with chips that need need to track crcs for lli)
 *
 * called from interrupt handler for errors or receive interrupt
 * Returns number of CRC error packets, needed by some chips for
 * local link integrity tracking.   crcs are adjusted down by following
 * good packets, if any, and count of good packets is also tracked.
 */
u32 qib_kreceive(struct qib_ctxtdata *rcd, u32 *llic, u32 *npkts)
{
	struct qib_devdata *dd = rcd->dd;
	struct qib_pportdata *ppd = rcd->ppd;
	__le32 *rhf_addr;
	void *ebuf;
	const u32 rsize = dd->rcvhdrentsize;        /* words */
	const u32 maxcnt = dd->rcvhdrcnt * rsize;   /* words */
	u32 etail = -1, l, hdrqtail;
	struct qib_message_header *hdr;
	u32 eflags, etype, tlen, i = 0, updegr = 0, crcs = 0;
	int last;
	u64 lval;
	struct qib_qp *qp, *nqp;

	l = rcd->head;
	rhf_addr = (__le32 *) rcd->rcvhdrq + l + dd->rhf_offset;
	if (dd->flags & QIB_NODMA_RTAIL) {
		u32 seq = qib_hdrget_seq(rhf_addr);
		if (seq != rcd->seq_cnt)
			goto bail;
		hdrqtail = 0;
	} else {
		hdrqtail = qib_get_rcvhdrtail(rcd);
		if (l == hdrqtail)
			goto bail;
		smp_rmb();  /* prevent speculative reads of dma'ed hdrq */
	}

	for (last = 0, i = 1; !last; i += !last) {
		hdr = dd->f_get_msgheader(dd, rhf_addr);
		eflags = qib_hdrget_err_flags(rhf_addr);
		etype = qib_hdrget_rcv_type(rhf_addr);
		/* total length */
		tlen = qib_hdrget_length_in_bytes(rhf_addr);
		ebuf = NULL;
		if ((dd->flags & QIB_NODMA_RTAIL) ?
		    qib_hdrget_use_egr_buf(rhf_addr) :
		    (etype != RCVHQ_RCV_TYPE_EXPECTED)) {
			etail = qib_hdrget_index(rhf_addr);
			updegr = 1;
			if (tlen > sizeof(*hdr) ||
			    etype >= RCVHQ_RCV_TYPE_NON_KD) {
				ebuf = qib_get_egrbuf(rcd, etail);
				prefetch_range(ebuf, tlen - sizeof(*hdr));
			}
		}
		if (!eflags) {
			u16 lrh_len = be16_to_cpu(hdr->lrh[2]) << 2;

			if (lrh_len != tlen) {
				qib_stats.sps_lenerrs++;
				goto move_along;
			}
		}
		if (etype == RCVHQ_RCV_TYPE_NON_KD && !eflags &&
		    ebuf == NULL &&
		    tlen > (dd->rcvhdrentsize - 2 + 1 -
				qib_hdrget_offset(rhf_addr)) << 2) {
			goto move_along;
		}

		/*
		 * Both tiderr and qibhdrerr are set for all plain IB
		 * packets; only qibhdrerr should be set.
		 */
		if (unlikely(eflags))
			crcs += qib_rcv_hdrerr(rcd, ppd, rcd->ctxt, eflags, l,
					       etail, rhf_addr, hdr);
		else if (etype == RCVHQ_RCV_TYPE_NON_KD) {
			qib_ib_rcv(rcd, hdr, ebuf, tlen);
			if (crcs)
				crcs--;
			else if (llic && *llic)
				--*llic;
		}
move_along:
		l += rsize;
		if (l >= maxcnt)
			l = 0;
		if (i == QIB_MAX_PKT_RECV)
			last = 1;

		rhf_addr = (__le32 *) rcd->rcvhdrq + l + dd->rhf_offset;
		if (dd->flags & QIB_NODMA_RTAIL) {
			u32 seq = qib_hdrget_seq(rhf_addr);

			if (++rcd->seq_cnt > 13)
				rcd->seq_cnt = 1;
			if (seq != rcd->seq_cnt)
				last = 1;
		} else if (l == hdrqtail)
			last = 1;
		/*
		 * Update head regs etc., every 16 packets, if not last pkt,
		 * to help prevent rcvhdrq overflows, when many packets
		 * are processed and queue is nearly full.
		 * Don't request an interrupt for intermediate updates.
		 */
		lval = l;
		if (!last && !(i & 0xf)) {
			dd->f_update_usrhead(rcd, lval, updegr, etail, i);
			updegr = 0;
		}
	}
	/*
	 * Notify qib_destroy_qp() if it is waiting
	 * for lookaside_qp to finish.
	 */
	if (rcd->lookaside_qp) {
		if (atomic_dec_and_test(&rcd->lookaside_qp->refcount))
			wake_up(&rcd->lookaside_qp->wait);
		rcd->lookaside_qp = NULL;
	}

	rcd->head = l;
	rcd->pkt_count += i;

	/*
	 * Iterate over all QPs waiting to respond.
	 * The list won't change since the IRQ is only run on one CPU.
	 */
	list_for_each_entry_safe(qp, nqp, &rcd->qp_wait_list, rspwait) {
		list_del_init(&qp->rspwait);
		if (qp->r_flags & QIB_R_RSP_NAK) {
			qp->r_flags &= ~QIB_R_RSP_NAK;
			qib_send_rc_ack(qp);
		}
		if (qp->r_flags & QIB_R_RSP_SEND) {
			unsigned long flags;

			qp->r_flags &= ~QIB_R_RSP_SEND;
			spin_lock_irqsave(&qp->s_lock, flags);
			if (ib_qib_state_ops[qp->state] &
					QIB_PROCESS_OR_FLUSH_SEND)
				qib_schedule_send(qp);
			spin_unlock_irqrestore(&qp->s_lock, flags);
		}
		if (atomic_dec_and_test(&qp->refcount))
			wake_up(&qp->wait);
	}

bail:
	/* Report number of packets consumed */
	if (npkts)
		*npkts = i;

	/*
	 * Always write head at end, and setup rcv interrupt, even
	 * if no packets were processed.
	 */
	lval = (u64)rcd->head | dd->rhdrhead_intr_off;
	dd->f_update_usrhead(rcd, lval, updegr, etail, i);
	return crcs;
}

/**
 * qib_set_mtu - set the MTU
 * @ppd: the perport data
 * @arg: the new MTU
 *
 * We can handle "any" incoming size, the issue here is whether we
 * need to restrict our outgoing size.   For now, we don't do any
 * sanity checking on this, and we don't deal with what happens to
 * programs that are already running when the size changes.
 * NOTE: changing the MTU will usually cause the IBC to go back to
 * link INIT state...
 */
int qib_set_mtu(struct qib_pportdata *ppd, u16 arg)
{
	u32 piosize;
	int ret, chk;

	if (arg != 256 && arg != 512 && arg != 1024 && arg != 2048 &&
	    arg != 4096) {
		ret = -EINVAL;
		goto bail;
	}
	chk = ib_mtu_enum_to_int(qib_ibmtu);
	if (chk > 0 && arg > chk) {
		ret = -EINVAL;
		goto bail;
	}

	piosize = ppd->ibmaxlen;
	ppd->ibmtu = arg;

	if (arg >= (piosize - QIB_PIO_MAXIBHDR)) {
		/* Only if it's not the initial value (or reset to it) */
		if (piosize != ppd->init_ibmaxlen) {
			if (arg > piosize && arg <= ppd->init_ibmaxlen)
				piosize = ppd->init_ibmaxlen - 2 * sizeof(u32);
			ppd->ibmaxlen = piosize;
		}
	} else if ((arg + QIB_PIO_MAXIBHDR) != ppd->ibmaxlen) {
		piosize = arg + QIB_PIO_MAXIBHDR - 2 * sizeof(u32);
		ppd->ibmaxlen = piosize;
	}

	ppd->dd->f_set_ib_cfg(ppd, QIB_IB_CFG_MTU, 0);

	ret = 0;

bail:
	return ret;
}

int qib_set_lid(struct qib_pportdata *ppd, u32 lid, u8 lmc)
{
	struct qib_devdata *dd = ppd->dd;
	ppd->lid = lid;
	ppd->lmc = lmc;

	dd->f_set_ib_cfg(ppd, QIB_IB_CFG_LIDLMC,
			 lid | (~((1U << lmc) - 1)) << 16);

	qib_devinfo(dd->pcidev, "IB%u:%u got a lid: 0x%x\n",
		    dd->unit, ppd->port, lid);

	return 0;
}

/*
 * Following deal with the "obviously simple" task of overriding the state
 * of the LEDS, which normally indicate link physical and logical status.
 * The complications arise in dealing with different hardware mappings
 * and the board-dependent routine being called from interrupts.
 * and then there's the requirement to _flash_ them.
 */
#define LED_OVER_FREQ_SHIFT 8
#define LED_OVER_FREQ_MASK (0xFF<<LED_OVER_FREQ_SHIFT)
/* Below is "non-zero" to force override, but both actual LEDs are off */
#define LED_OVER_BOTH_OFF (8)

static void qib_run_led_override(unsigned long opaque)
{
	struct qib_pportdata *ppd = (struct qib_pportdata *)opaque;
	struct qib_devdata *dd = ppd->dd;
	int timeoff;
	int ph_idx;

	if (!(dd->flags & QIB_INITTED))
		return;

	ph_idx = ppd->led_override_phase++ & 1;
	ppd->led_override = ppd->led_override_vals[ph_idx];
	timeoff = ppd->led_override_timeoff;

	dd->f_setextled(ppd, 1);
	/*
	 * don't re-fire the timer if user asked for it to be off; we let
	 * it fire one more time after they turn it off to simplify
	 */
	if (ppd->led_override_vals[0] || ppd->led_override_vals[1])
		mod_timer(&ppd->led_override_timer, jiffies + timeoff);
}

void qib_set_led_override(struct qib_pportdata *ppd, unsigned int val)
{
	struct qib_devdata *dd = ppd->dd;
	int timeoff, freq;

	if (!(dd->flags & QIB_INITTED))
		return;

	/* First check if we are blinking. If not, use 1HZ polling */
	timeoff = HZ;
	freq = (val & LED_OVER_FREQ_MASK) >> LED_OVER_FREQ_SHIFT;

	if (freq) {
		/* For blink, set each phase from one nybble of val */
		ppd->led_override_vals[0] = val & 0xF;
		ppd->led_override_vals[1] = (val >> 4) & 0xF;
		timeoff = (HZ << 4)/freq;
	} else {
		/* Non-blink set both phases the same. */
		ppd->led_override_vals[0] = val & 0xF;
		ppd->led_override_vals[1] = val & 0xF;
	}
	ppd->led_override_timeoff = timeoff;

	/*
	 * If the timer has not already been started, do so. Use a "quick"
	 * timeout so the function will be called soon, to look at our request.
	 */
	if (atomic_inc_return(&ppd->led_override_timer_active) == 1) {
		/* Need to start timer */
		init_timer(&ppd->led_override_timer);
		ppd->led_override_timer.function = qib_run_led_override;
		ppd->led_override_timer.data = (unsigned long) ppd;
		ppd->led_override_timer.expires = jiffies + 1;
		add_timer(&ppd->led_override_timer);
	} else {
		if (ppd->led_override_vals[0] || ppd->led_override_vals[1])
			mod_timer(&ppd->led_override_timer, jiffies + 1);
		atomic_dec(&ppd->led_override_timer_active);
	}
}

/**
 * qib_reset_device - reset the chip if possible
 * @unit: the device to reset
 *
 * Whether or not reset is successful, we attempt to re-initialize the chip
 * (that is, much like a driver unload/reload).  We clear the INITTED flag
 * so that the various entry points will fail until we reinitialize.  For
 * now, we only allow this if no user contexts are open that use chip resources
 */
int qib_reset_device(int unit)
{
	int ret, i;
	struct qib_devdata *dd = qib_lookup(unit);
	struct qib_pportdata *ppd;
	unsigned long flags;
	int pidx;

	if (!dd) {
		ret = -ENODEV;
		goto bail;
	}

	qib_devinfo(dd->pcidev, "Reset on unit %u requested\n", unit);

	if (!dd->kregbase || !(dd->flags & QIB_PRESENT)) {
		qib_devinfo(dd->pcidev,
			"Invalid unit number %u or not initialized or not present\n",
			unit);
		ret = -ENXIO;
		goto bail;
	}

	spin_lock_irqsave(&dd->uctxt_lock, flags);
	if (dd->rcd)
		for (i = dd->first_user_ctxt; i < dd->cfgctxts; i++) {
			if (!dd->rcd[i] || !dd->rcd[i]->cnt)
				continue;
			spin_unlock_irqrestore(&dd->uctxt_lock, flags);
			ret = -EBUSY;
			goto bail;
		}
	spin_unlock_irqrestore(&dd->uctxt_lock, flags);

	for (pidx = 0; pidx < dd->num_pports; ++pidx) {
		ppd = dd->pport + pidx;
		if (atomic_read(&ppd->led_override_timer_active)) {
			/* Need to stop LED timer, _then_ shut off LEDs */
			del_timer_sync(&ppd->led_override_timer);
			atomic_set(&ppd->led_override_timer_active, 0);
		}

		/* Shut off LEDs after we are sure timer is not running */
		ppd->led_override = LED_OVER_BOTH_OFF;
		dd->f_setextled(ppd, 0);
		if (dd->flags & QIB_HAS_SEND_DMA)
			qib_teardown_sdma(ppd);
	}

	ret = dd->f_reset(dd);
	if (ret == 1)
		ret = qib_init(dd, 1);
	else
		ret = -EAGAIN;
	if (ret)
		qib_dev_err(dd,
			"Reinitialize unit %u after reset failed with %d\n",
			unit, ret);
	else
		qib_devinfo(dd->pcidev,
			"Reinitialized unit %u after resetting\n",
			unit);

bail:
	return ret;
}
OpenPOWER on IntegriCloud