aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/misc/sgi-xp/xpc_partition.c
blob: 4e14effdeddb9016431f41ac29f225a4bce46895 (plain) (blame)
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
/*
 * This file is subject to the terms and conditions of the GNU General Public
 * License.  See the file "COPYING" in the main directory of this archive
 * for more details.
 *
 * Copyright (c) 2004-2008 Silicon Graphics, Inc.  All Rights Reserved.
 */

/*
 * Cross Partition Communication (XPC) partition support.
 *
 *	This is the part of XPC that detects the presence/absence of
 *	other partitions. It provides a heartbeat and monitors the
 *	heartbeats of other partitions.
 *
 */

#include <linux/kernel.h>
#include <linux/sysctl.h>
#include <linux/cache.h>
#include <linux/mmzone.h>
#include <linux/nodemask.h>
#include <asm/sn/intr.h>
#include <asm/sn/sn_sal.h>
#include <asm/sn/nodepda.h>
#include <asm/sn/addrs.h>
#include "xpc.h"

/* XPC is exiting flag */
int xpc_exiting;

/* SH_IPI_ACCESS shub register value on startup */
static u64 xpc_sh1_IPI_access;
static u64 xpc_sh2_IPI_access0;
static u64 xpc_sh2_IPI_access1;
static u64 xpc_sh2_IPI_access2;
static u64 xpc_sh2_IPI_access3;

/* original protection values for each node */
u64 xpc_prot_vec[MAX_NUMNODES];

/* this partition's reserved page pointers */
struct xpc_rsvd_page *xpc_rsvd_page;
static u64 *xpc_part_nasids;
u64 *xpc_mach_nasids;

/* >>> next two variables should be 'xpc_' if they remain here */
static int xp_sizeof_nasid_mask;	/* actual size in bytes of nasid mask */
int xp_nasid_mask_words;	/* actual size in words of nasid mask */

struct xpc_partition *xpc_partitions;

/*
 * Generic buffer used to store a local copy of portions of a remote
 * partition's reserved page (either its header and part_nasids mask,
 * or its vars).
 */
char *xpc_remote_copy_buffer;
void *xpc_remote_copy_buffer_base;

/*
 * Guarantee that the kmalloc'd memory is cacheline aligned.
 */
void *
xpc_kmalloc_cacheline_aligned(size_t size, gfp_t flags, void **base)
{
	/* see if kmalloc will give us cachline aligned memory by default */
	*base = kmalloc(size, flags);
	if (*base == NULL)
		return NULL;

	if ((u64)*base == L1_CACHE_ALIGN((u64)*base))
		return *base;

	kfree(*base);

	/* nope, we'll have to do it ourselves */
	*base = kmalloc(size + L1_CACHE_BYTES, flags);
	if (*base == NULL)
		return NULL;

	return (void *)L1_CACHE_ALIGN((u64)*base);
}

/*
 * Given a nasid, get the physical address of the  partition's reserved page
 * for that nasid. This function returns 0 on any error.
 */
static u64
xpc_get_rsvd_page_pa(int nasid)
{
	enum xp_retval ret;
	s64 status;
	u64 cookie = 0;
	u64 rp_pa = nasid;	/* seed with nasid */
	u64 len = 0;
	u64 buf = buf;
	u64 buf_len = 0;
	void *buf_base = NULL;

	while (1) {

		status = sn_partition_reserved_page_pa(buf, &cookie, &rp_pa,
						       &len);

		dev_dbg(xpc_part, "SAL returned with status=%li, cookie="
			"0x%016lx, address=0x%016lx, len=0x%016lx\n",
			status, cookie, rp_pa, len);

		if (status != SALRET_MORE_PASSES)
			break;

		/* >>> L1_CACHE_ALIGN() is only a sn2-bte_copy requirement */
		if (L1_CACHE_ALIGN(len) > buf_len) {
			kfree(buf_base);
			buf_len = L1_CACHE_ALIGN(len);
			buf = (u64)xpc_kmalloc_cacheline_aligned(buf_len,
								 GFP_KERNEL,
								 &buf_base);
			if (buf_base == NULL) {
				dev_err(xpc_part, "unable to kmalloc "
					"len=0x%016lx\n", buf_len);
				status = SALRET_ERROR;
				break;
			}
		}

		ret = xp_remote_memcpy((void *)buf, (void *)rp_pa, buf_len);
		if (ret != xpSuccess) {
			dev_dbg(xpc_part, "xp_remote_memcpy failed %d\n", ret);
			status = SALRET_ERROR;
			break;
		}
	}

	kfree(buf_base);

	if (status != SALRET_OK)
		rp_pa = 0;

	dev_dbg(xpc_part, "reserved page at phys address 0x%016lx\n", rp_pa);
	return rp_pa;
}

/*
 * Fill the partition reserved page with the information needed by
 * other partitions to discover we are alive and establish initial
 * communications.
 */
struct xpc_rsvd_page *
xpc_setup_rsvd_page(void)
{
	struct xpc_rsvd_page *rp;
	u64 rp_pa;

	/* get the local reserved page's address */

	preempt_disable();
	rp_pa = xpc_get_rsvd_page_pa(cpuid_to_nasid(smp_processor_id()));
	preempt_enable();
	if (rp_pa == 0) {
		dev_err(xpc_part, "SAL failed to locate the reserved page\n");
		return NULL;
	}
	rp = (struct xpc_rsvd_page *)__va(rp_pa);

	if (rp->SAL_version < 3) {
		/* SAL_versions < 3 had a SAL_partid defined as a u8 */
		rp->SAL_partid &= 0xff;
	}
	BUG_ON(rp->SAL_partid != sn_partition_id);

	if (rp->SAL_partid < 0 || rp->SAL_partid >= xp_max_npartitions) {
		dev_err(xpc_part, "the reserved page's partid of %d is outside "
			"supported range (< 0 || >= %d)\n", rp->SAL_partid,
			xp_max_npartitions);
		return NULL;
	}

	rp->version = XPC_RP_VERSION;
	rp->max_npartitions = xp_max_npartitions;

	/* establish the actual sizes of the nasid masks */
	if (rp->SAL_version == 1) {
		/* SAL_version 1 didn't set the nasids_size field */
		rp->SAL_nasids_size = 128;
	}
	xp_sizeof_nasid_mask = rp->SAL_nasids_size;
	xp_nasid_mask_words = DIV_ROUND_UP(xp_sizeof_nasid_mask,
					   BYTES_PER_WORD);

	/* setup the pointers to the various items in the reserved page */
	xpc_part_nasids = XPC_RP_PART_NASIDS(rp);
	xpc_mach_nasids = XPC_RP_MACH_NASIDS(rp);

	if (xpc_rsvd_page_init(rp) != xpSuccess)
		return NULL;

	/*
	 * Set timestamp of when reserved page was setup by XPC.
	 * This signifies to the remote partition that our reserved
	 * page is initialized.
	 */
	rp->stamp = CURRENT_TIME;

	return rp;
}

/*
 * Change protections to allow IPI operations (and AMO operations on
 * Shub 1.1 systems).
 */
void
xpc_allow_IPI_ops(void)
{
	int node;
	int nasid;

	/* >>> Change SH_IPI_ACCESS code to use SAL call once it is available */

	if (is_shub2()) {
		xpc_sh2_IPI_access0 =
		    (u64)HUB_L((u64 *)LOCAL_MMR_ADDR(SH2_IPI_ACCESS0));
		xpc_sh2_IPI_access1 =
		    (u64)HUB_L((u64 *)LOCAL_MMR_ADDR(SH2_IPI_ACCESS1));
		xpc_sh2_IPI_access2 =
		    (u64)HUB_L((u64 *)LOCAL_MMR_ADDR(SH2_IPI_ACCESS2));
		xpc_sh2_IPI_access3 =
		    (u64)HUB_L((u64 *)LOCAL_MMR_ADDR(SH2_IPI_ACCESS3));

		for_each_online_node(node) {
			nasid = cnodeid_to_nasid(node);
			HUB_S((u64 *)GLOBAL_MMR_ADDR(nasid, SH2_IPI_ACCESS0),
			      -1UL);
			HUB_S((u64 *)GLOBAL_MMR_ADDR(nasid, SH2_IPI_ACCESS1),
			      -1UL);
			HUB_S((u64 *)GLOBAL_MMR_ADDR(nasid, SH2_IPI_ACCESS2),
			      -1UL);
			HUB_S((u64 *)GLOBAL_MMR_ADDR(nasid, SH2_IPI_ACCESS3),
			      -1UL);
		}

	} else {
		xpc_sh1_IPI_access =
		    (u64)HUB_L((u64 *)LOCAL_MMR_ADDR(SH1_IPI_ACCESS));

		for_each_online_node(node) {
			nasid = cnodeid_to_nasid(node);
			HUB_S((u64 *)GLOBAL_MMR_ADDR(nasid, SH1_IPI_ACCESS),
			      -1UL);

			/*
			 * Since the BIST collides with memory operations on
			 * SHUB 1.1 sn_change_memprotect() cannot be used.
			 */
			if (enable_shub_wars_1_1()) {
				/* open up everything */
				xpc_prot_vec[node] = (u64)HUB_L((u64 *)
								GLOBAL_MMR_ADDR
								(nasid,
						  SH1_MD_DQLP_MMR_DIR_PRIVEC0));
				HUB_S((u64 *)
				      GLOBAL_MMR_ADDR(nasid,
						   SH1_MD_DQLP_MMR_DIR_PRIVEC0),
				      -1UL);
				HUB_S((u64 *)
				      GLOBAL_MMR_ADDR(nasid,
						   SH1_MD_DQRP_MMR_DIR_PRIVEC0),
				      -1UL);
			}
		}
	}
}

/*
 * Restrict protections to disallow IPI operations (and AMO operations on
 * Shub 1.1 systems).
 */
void
xpc_restrict_IPI_ops(void)
{
	int node;
	int nasid;

	/* >>> Change SH_IPI_ACCESS code to use SAL call once it is available */

	if (is_shub2()) {

		for_each_online_node(node) {
			nasid = cnodeid_to_nasid(node);
			HUB_S((u64 *)GLOBAL_MMR_ADDR(nasid, SH2_IPI_ACCESS0),
			      xpc_sh2_IPI_access0);
			HUB_S((u64 *)GLOBAL_MMR_ADDR(nasid, SH2_IPI_ACCESS1),
			      xpc_sh2_IPI_access1);
			HUB_S((u64 *)GLOBAL_MMR_ADDR(nasid, SH2_IPI_ACCESS2),
			      xpc_sh2_IPI_access2);
			HUB_S((u64 *)GLOBAL_MMR_ADDR(nasid, SH2_IPI_ACCESS3),
			      xpc_sh2_IPI_access3);
		}

	} else {

		for_each_online_node(node) {
			nasid = cnodeid_to_nasid(node);
			HUB_S((u64 *)GLOBAL_MMR_ADDR(nasid, SH1_IPI_ACCESS),
			      xpc_sh1_IPI_access);

			if (enable_shub_wars_1_1()) {
				HUB_S((u64 *)GLOBAL_MMR_ADDR(nasid,
						   SH1_MD_DQLP_MMR_DIR_PRIVEC0),
				      xpc_prot_vec[node]);
				HUB_S((u64 *)GLOBAL_MMR_ADDR(nasid,
						   SH1_MD_DQRP_MMR_DIR_PRIVEC0),
				      xpc_prot_vec[node]);
			}
		}
	}
}

/*
 * Get a copy of a portion of the remote partition's rsvd page.
 *
 * remote_rp points to a buffer that is cacheline aligned for BTE copies and
 * is large enough to contain a copy of their reserved page header and
 * part_nasids mask.
 */
enum xp_retval
xpc_get_remote_rp(int nasid, u64 *discovered_nasids,
		  struct xpc_rsvd_page *remote_rp, u64 *remote_rp_pa)
{
	int i;
	enum xp_retval ret;

	/* get the reserved page's physical address */

	*remote_rp_pa = xpc_get_rsvd_page_pa(nasid);
	if (*remote_rp_pa == 0)
		return xpNoRsvdPageAddr;

	/* pull over the reserved page header and part_nasids mask */
	ret = xp_remote_memcpy(remote_rp, (void *)*remote_rp_pa,
			       XPC_RP_HEADER_SIZE + xp_sizeof_nasid_mask);
	if (ret != xpSuccess)
		return ret;

	if (discovered_nasids != NULL) {
		u64 *remote_part_nasids = XPC_RP_PART_NASIDS(remote_rp);

		for (i = 0; i < xp_nasid_mask_words; i++)
			discovered_nasids[i] |= remote_part_nasids[i];
	}

	/* check that the partid is valid and is for another partition */

	if (remote_rp->SAL_partid < 0 ||
	    remote_rp->SAL_partid >= xp_max_npartitions) {
		return xpInvalidPartid;
	}

	if (remote_rp->SAL_partid == sn_partition_id)
		return xpLocalPartid;

	/* see if the rest of the reserved page has been set up by XPC */
	if (timespec_equal(&remote_rp->stamp, &ZERO_STAMP))
		return xpRsvdPageNotSet;

	if (XPC_VERSION_MAJOR(remote_rp->version) !=
	    XPC_VERSION_MAJOR(XPC_RP_VERSION)) {
		return xpBadVersion;
	}

	if (remote_rp->max_npartitions <= sn_partition_id)
		return xpInvalidPartid;

	return xpSuccess;
}

/*
 * See if the other side has responded to a partition disengage request
 * from us.
 */
int
xpc_partition_disengaged(struct xpc_partition *part)
{
	short partid = XPC_PARTID(part);
	int disengaged;

	disengaged = (xpc_partition_engaged(1UL << partid) == 0);
	if (part->disengage_request_timeout) {
		if (!disengaged) {
			if (time_before(jiffies,
			    part->disengage_request_timeout)) {
				/* timelimit hasn't been reached yet */
				return 0;
			}

			/*
			 * Other side hasn't responded to our disengage
			 * request in a timely fashion, so assume it's dead.
			 */

			dev_info(xpc_part, "disengage from remote partition %d "
				 "timed out\n", partid);
			xpc_disengage_request_timedout = 1;
			xpc_clear_partition_engaged(1UL << partid);
			disengaged = 1;
		}
		part->disengage_request_timeout = 0;

		/* cancel the timer function, provided it's not us */
		if (!in_interrupt()) {
			del_singleshot_timer_sync(&part->
						  disengage_request_timer);
		}

		DBUG_ON(part->act_state != XPC_P_DEACTIVATING &&
			part->act_state != XPC_P_INACTIVE);
		if (part->act_state != XPC_P_INACTIVE)
			xpc_wakeup_channel_mgr(part);

		if (XPC_SUPPORTS_DISENGAGE_REQUEST(part->remote_vars_version))
			xpc_cancel_partition_disengage_request(part);
	}
	return disengaged;
}

/*
 * Mark specified partition as active.
 */
enum xp_retval
xpc_mark_partition_active(struct xpc_partition *part)
{
	unsigned long irq_flags;
	enum xp_retval ret;

	dev_dbg(xpc_part, "setting partition %d to ACTIVE\n", XPC_PARTID(part));

	spin_lock_irqsave(&part->act_lock, irq_flags);
	if (part->act_state == XPC_P_ACTIVATING) {
		part->act_state = XPC_P_ACTIVE;
		ret = xpSuccess;
	} else {
		DBUG_ON(part->reason == xpSuccess);
		ret = part->reason;
	}
	spin_unlock_irqrestore(&part->act_lock, irq_flags);

	return ret;
}

/*
 * Notify XPC that the partition is down.
 */
void
xpc_deactivate_partition(const int line, struct xpc_partition *part,
			 enum xp_retval reason)
{
	unsigned long irq_flags;

	spin_lock_irqsave(&part->act_lock, irq_flags);

	if (part->act_state == XPC_P_INACTIVE) {
		XPC_SET_REASON(part, reason, line);
		spin_unlock_irqrestore(&part->act_lock, irq_flags);
		if (reason == xpReactivating) {
			/* we interrupt ourselves to reactivate partition */
			xpc_IPI_send_local_reactivate(part->reactivate_nasid);
		}
		return;
	}
	if (part->act_state == XPC_P_DEACTIVATING) {
		if ((part->reason == xpUnloading && reason != xpUnloading) ||
		    reason == xpReactivating) {
			XPC_SET_REASON(part, reason, line);
		}
		spin_unlock_irqrestore(&part->act_lock, irq_flags);
		return;
	}

	part->act_state = XPC_P_DEACTIVATING;
	XPC_SET_REASON(part, reason, line);

	spin_unlock_irqrestore(&part->act_lock, irq_flags);

	if (XPC_SUPPORTS_DISENGAGE_REQUEST(part->remote_vars_version)) {
		xpc_request_partition_disengage(part);
		xpc_IPI_send_disengage(part);

		/* set a timelimit on the disengage request */
		part->disengage_request_timeout = jiffies +
		    (xpc_disengage_request_timelimit * HZ);
		part->disengage_request_timer.expires =
		    part->disengage_request_timeout;
		add_timer(&part->disengage_request_timer);
	}

	dev_dbg(xpc_part, "bringing partition %d down, reason = %d\n",
		XPC_PARTID(part), reason);

	xpc_partition_going_down(part, reason);
}

/*
 * Mark specified partition as inactive.
 */
void
xpc_mark_partition_inactive(struct xpc_partition *part)
{
	unsigned long irq_flags;

	dev_dbg(xpc_part, "setting partition %d to INACTIVE\n",
		XPC_PARTID(part));

	spin_lock_irqsave(&part->act_lock, irq_flags);
	part->act_state = XPC_P_INACTIVE;
	spin_unlock_irqrestore(&part->act_lock, irq_flags);
	part->remote_rp_pa = 0;
}

/*
 * SAL has provided a partition and machine mask.  The partition mask
 * contains a bit for each even nasid in our partition.  The machine
 * mask contains a bit for each even nasid in the entire machine.
 *
 * Using those two bit arrays, we can determine which nasids are
 * known in the machine.  Each should also have a reserved page
 * initialized if they are available for partitioning.
 */
void
xpc_discovery(void)
{
	void *remote_rp_base;
	struct xpc_rsvd_page *remote_rp;
	u64 remote_rp_pa;
	int region;
	int region_size;
	int max_regions;
	int nasid;
	struct xpc_rsvd_page *rp;
	u64 *discovered_nasids;
	enum xp_retval ret;

	remote_rp = xpc_kmalloc_cacheline_aligned(XPC_RP_HEADER_SIZE +
						  xp_sizeof_nasid_mask,
						  GFP_KERNEL, &remote_rp_base);
	if (remote_rp == NULL)
		return;

	discovered_nasids = kzalloc(sizeof(u64) * xp_nasid_mask_words,
				    GFP_KERNEL);
	if (discovered_nasids == NULL) {
		kfree(remote_rp_base);
		return;
	}

	rp = (struct xpc_rsvd_page *)xpc_rsvd_page;

	/*
	 * The term 'region' in this context refers to the minimum number of
	 * nodes that can comprise an access protection grouping. The access
	 * protection is in regards to memory, IOI and IPI.
	 */
	max_regions = 64;
	region_size = sn_region_size;

	switch (region_size) {
	case 128:
		max_regions *= 2;
	case 64:
		max_regions *= 2;
	case 32:
		max_regions *= 2;
		region_size = 16;
		DBUG_ON(!is_shub2());
	}

	for (region = 0; region < max_regions; region++) {

		if (xpc_exiting)
			break;

		dev_dbg(xpc_part, "searching region %d\n", region);

		for (nasid = (region * region_size * 2);
		     nasid < ((region + 1) * region_size * 2); nasid += 2) {

			if (xpc_exiting)
				break;

			dev_dbg(xpc_part, "checking nasid %d\n", nasid);

			if (XPC_NASID_IN_ARRAY(nasid, xpc_part_nasids)) {
				dev_dbg(xpc_part, "PROM indicates Nasid %d is "
					"part of the local partition; skipping "
					"region\n", nasid);
				break;
			}

			if (!(XPC_NASID_IN_ARRAY(nasid, xpc_mach_nasids))) {
				dev_dbg(xpc_part, "PROM indicates Nasid %d was "
					"not on Numa-Link network at reset\n",
					nasid);
				continue;
			}

			if (XPC_NASID_IN_ARRAY(nasid, discovered_nasids)) {
				dev_dbg(xpc_part, "Nasid %d is part of a "
					"partition which was previously "
					"discovered\n", nasid);
				continue;
			}

			/* pull over the rsvd page header & part_nasids mask */

			ret = xpc_get_remote_rp(nasid, discovered_nasids,
						remote_rp, &remote_rp_pa);
			if (ret != xpSuccess) {
				dev_dbg(xpc_part, "unable to get reserved page "
					"from nasid %d, reason=%d\n", nasid,
					ret);

				if (ret == xpLocalPartid)
					break;

				continue;
			}

			xpc_initiate_partition_activation(remote_rp,
							  remote_rp_pa, nasid);
		}
	}

	kfree(discovered_nasids);
	kfree(remote_rp_base);
}

/*
 * Given a partid, get the nasids owned by that partition from the
 * remote partition's reserved page.
 */
enum xp_retval
xpc_initiate_partid_to_nasids(short partid, void *nasid_mask)
{
	struct xpc_partition *part;
	u64 part_nasid_pa;

	part = &xpc_partitions[partid];
	if (part->remote_rp_pa == 0)
		return xpPartitionDown;

	memset(nasid_mask, 0, XP_NASID_MASK_BYTES);

	part_nasid_pa = (u64)XPC_RP_PART_NASIDS(part->remote_rp_pa);

	return xp_remote_memcpy(nasid_mask, (void *)part_nasid_pa,
				xp_sizeof_nasid_mask);
}