summaryrefslogtreecommitdiffstats
path: root/drivers/misc/sgi-gru/grufault.c
blob: 6d0681236db5ea4bae4e1b8e0da7822d512f93c3 (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
/*
 * SN Platform GRU Driver
 *
 *              FAULT HANDLER FOR GRU DETECTED TLB MISSES
 *
 * This file contains code that handles TLB misses within the GRU.
 * These misses are reported either via interrupts or user polling of
 * the user CB.
 *
 *  Copyright (c) 2008 Silicon Graphics, Inc.  All Rights Reserved.
 *
 *  This program is free software; you can redistribute it and/or modify
 *  it under the terms of the GNU General Public License as published by
 *  the Free Software Foundation; either version 2 of the License, or
 *  (at your option) any later version.
 *
 *  This program is distributed in the hope that 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., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
 */

#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/spinlock.h>
#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/device.h>
#include <linux/io.h>
#include <linux/uaccess.h>
#include <linux/security.h>
#include <asm/pgtable.h>
#include "gru.h"
#include "grutables.h"
#include "grulib.h"
#include "gru_instructions.h"
#include <asm/uv/uv_hub.h>

/*
 * Test if a physical address is a valid GRU GSEG address
 */
static inline int is_gru_paddr(unsigned long paddr)
{
	return paddr >= gru_start_paddr && paddr < gru_end_paddr;
}

/*
 * Find the vma of a GRU segment. Caller must hold mmap_sem.
 */
struct vm_area_struct *gru_find_vma(unsigned long vaddr)
{
	struct vm_area_struct *vma;

	vma = find_vma(current->mm, vaddr);
	if (vma && vma->vm_start <= vaddr && vma->vm_ops == &gru_vm_ops)
		return vma;
	return NULL;
}

/*
 * Find and lock the gts that contains the specified user vaddr.
 *
 * Returns:
 * 	- *gts with the mmap_sem locked for read and the GTS locked.
 *	- NULL if vaddr invalid OR is not a valid GSEG vaddr.
 */

static struct gru_thread_state *gru_find_lock_gts(unsigned long vaddr)
{
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma;
	struct gru_thread_state *gts = NULL;

	down_read(&mm->mmap_sem);
	vma = gru_find_vma(vaddr);
	if (vma)
		gts = gru_find_thread_state(vma, TSID(vaddr, vma));
	if (gts)
		mutex_lock(&gts->ts_ctxlock);
	else
		up_read(&mm->mmap_sem);
	return gts;
}

static struct gru_thread_state *gru_alloc_locked_gts(unsigned long vaddr)
{
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma;
	struct gru_thread_state *gts = NULL;

	down_write(&mm->mmap_sem);
	vma = gru_find_vma(vaddr);
	if (vma)
		gts = gru_alloc_thread_state(vma, TSID(vaddr, vma));
	if (gts) {
		mutex_lock(&gts->ts_ctxlock);
		downgrade_write(&mm->mmap_sem);
	} else {
		up_write(&mm->mmap_sem);
	}

	return gts;
}

/*
 * Unlock a GTS that was previously locked with gru_find_lock_gts().
 */
static void gru_unlock_gts(struct gru_thread_state *gts)
{
	mutex_unlock(&gts->ts_ctxlock);
	up_read(&current->mm->mmap_sem);
}

/*
 * Set a CB.istatus to active using a user virtual address. This must be done
 * just prior to a TFH RESTART. The new cb.istatus is an in-cache status ONLY.
 * If the line is evicted, the status may be lost. The in-cache update
 * is necessary to prevent the user from seeing a stale cb.istatus that will
 * change as soon as the TFH restart is complete. Races may cause an
 * occasional failure to clear the cb.istatus, but that is ok.
 *
 * If the cb address is not valid (should not happen, but...), nothing
 * bad will happen.. The get_user()/put_user() will fail but there
 * are no bad side-effects.
 */
static void gru_cb_set_istatus_active(unsigned long __user *cb)
{
	union {
		struct gru_instruction_bits bits;
		unsigned long dw;
	} u;

	if (cb) {
		get_user(u.dw, cb);
		u.bits.istatus = CBS_ACTIVE;
		put_user(u.dw, cb);
	}
}

/*
 * Convert a interrupt IRQ to a pointer to the GRU GTS that caused the
 * interrupt. Interrupts are always sent to a cpu on the blade that contains the
 * GRU (except for headless blades which are not currently supported). A blade
 * has N grus; a block of N consecutive IRQs is assigned to the GRUs. The IRQ
 * number uniquely identifies the GRU chiplet on the local blade that caused the
 * interrupt. Always called in interrupt context.
 */
static inline struct gru_state *irq_to_gru(int irq)
{
	return &gru_base[uv_numa_blade_id()]->bs_grus[irq - IRQ_GRU];
}

/*
 * Read & clear a TFM
 *
 * The GRU has an array of fault maps. A map is private to a cpu
 * Only one cpu will be accessing a cpu's fault map.
 *
 * This function scans the cpu-private fault map & clears all bits that
 * are set. The function returns a bitmap that indicates the bits that
 * were cleared. Note that sense the maps may be updated asynchronously by
 * the GRU, atomic operations must be used to clear bits.
 */
static void get_clear_fault_map(struct gru_state *gru,
				struct gru_tlb_fault_map *imap,
				struct gru_tlb_fault_map *dmap)
{
	unsigned long i, k;
	struct gru_tlb_fault_map *tfm;

	tfm = get_tfm_for_cpu(gru, gru_cpu_fault_map_id());
	prefetchw(tfm);		/* Helps on hardware, required for emulator */
	for (i = 0; i < BITS_TO_LONGS(GRU_NUM_CBE); i++) {
		k = tfm->fault_bits[i];
		if (k)
			k = xchg(&tfm->fault_bits[i], 0UL);
		imap->fault_bits[i] = k;
		k = tfm->done_bits[i];
		if (k)
			k = xchg(&tfm->done_bits[i], 0UL);
		dmap->fault_bits[i] = k;
	}

	/*
	 * Not functionally required but helps performance. (Required
	 * on emulator)
	 */
	gru_flush_cache(tfm);
}

/*
 * Atomic (interrupt context) & non-atomic (user context) functions to
 * convert a vaddr into a physical address. The size of the page
 * is returned in pageshift.
 * 	returns:
 * 		  0 - successful
 * 		< 0 - error code
 * 		  1 - (atomic only) try again in non-atomic context
 */
static int non_atomic_pte_lookup(struct vm_area_struct *vma,
				 unsigned long vaddr, int write,
				 unsigned long *paddr, int *pageshift)
{
	struct page *page;

	/* ZZZ Need to handle HUGE pages */
	if (is_vm_hugetlb_page(vma))
		return -EFAULT;
	*pageshift = PAGE_SHIFT;
	if (get_user_pages
	    (current, current->mm, vaddr, 1, write, 0, &page, NULL) <= 0)
		return -EFAULT;
	*paddr = page_to_phys(page);
	put_page(page);
	return 0;
}

/*
 * atomic_pte_lookup
 *
 * Convert a user virtual address to a physical address
 * Only supports Intel large pages (2MB only) on x86_64.
 *	ZZZ - hugepage support is incomplete
 *
 * NOTE: mmap_sem is already held on entry to this function. This
 * guarantees existence of the page tables.
 */
static int atomic_pte_lookup(struct vm_area_struct *vma, unsigned long vaddr,
	int write, unsigned long *paddr, int *pageshift)
{
	pgd_t *pgdp;
	pmd_t *pmdp;
	pud_t *pudp;
	pte_t pte;

	pgdp = pgd_offset(vma->vm_mm, vaddr);
	if (unlikely(pgd_none(*pgdp)))
		goto err;

	pudp = pud_offset(pgdp, vaddr);
	if (unlikely(pud_none(*pudp)))
		goto err;

	pmdp = pmd_offset(pudp, vaddr);
	if (unlikely(pmd_none(*pmdp)))
		goto err;
#ifdef CONFIG_X86_64
	if (unlikely(pmd_large(*pmdp)))
		pte = *(pte_t *) pmdp;
	else
#endif
		pte = *pte_offset_kernel(pmdp, vaddr);

	if (unlikely(!pte_present(pte) ||
		     (write && (!pte_write(pte) || !pte_dirty(pte)))))
		return 1;

	*paddr = pte_pfn(pte) << PAGE_SHIFT;
#ifdef CONFIG_HUGETLB_PAGE
	*pageshift = is_vm_hugetlb_page(vma) ? HPAGE_SHIFT : PAGE_SHIFT;
#else
	*pageshift = PAGE_SHIFT;
#endif
	return 0;

err:
	local_irq_enable();
	return 1;
}

static int gru_vtop(struct gru_thread_state *gts, unsigned long vaddr,
		    int write, int atomic, unsigned long *gpa, int *pageshift)
{
	struct mm_struct *mm = gts->ts_mm;
	struct vm_area_struct *vma;
	unsigned long paddr;
	int ret, ps;

	vma = find_vma(mm, vaddr);
	if (!vma)
		goto inval;

	/*
	 * Atomic lookup is faster & usually works even if called in non-atomic
	 * context.
	 */
	rmb();	/* Must/check ms_range_active before loading PTEs */
	ret = atomic_pte_lookup(vma, vaddr, write, &paddr, &ps);
	if (ret) {
		if (atomic)
			goto upm;
		if (non_atomic_pte_lookup(vma, vaddr, write, &paddr, &ps))
			goto inval;
	}
	if (is_gru_paddr(paddr))
		goto inval;
	paddr = paddr & ~((1UL << ps) - 1);
	*gpa = uv_soc_phys_ram_to_gpa(paddr);
	*pageshift = ps;
	return 0;

inval:
	return -1;
upm:
	return -2;
}


/*
 * Drop a TLB entry into the GRU. The fault is described by info in an TFH.
 *	Input:
 *		cb    Address of user CBR. Null if not running in user context
 * 	Return:
 * 		  0 = dropin, exception, or switch to UPM successful
 * 		  1 = range invalidate active
 * 		< 0 = error code
 *
 */
static int gru_try_dropin(struct gru_thread_state *gts,
			  struct gru_tlb_fault_handle *tfh,
			  unsigned long __user *cb)
{
	int pageshift = 0, asid, write, ret, atomic = !cb;
	unsigned long gpa = 0, vaddr = 0;

	/*
	 * NOTE: The GRU contains magic hardware that eliminates races between
	 * TLB invalidates and TLB dropins. If an invalidate occurs
	 * in the window between reading the TFH and the subsequent TLB dropin,
	 * the dropin is ignored. This eliminates the need for additional locks.
	 */

	/*
	 * Error if TFH state is IDLE or FMM mode & the user issuing a UPM call.
	 * Might be a hardware race OR a stupid user. Ignore FMM because FMM
	 * is a transient state.
	 */
	if (tfh->status != TFHSTATUS_EXCEPTION) {
		gru_flush_cache(tfh);
		if (tfh->status != TFHSTATUS_EXCEPTION)
			goto failnoexception;
		STAT(tfh_stale_on_fault);
	}
	if (tfh->state == TFHSTATE_IDLE)
		goto failidle;
	if (tfh->state == TFHSTATE_MISS_FMM && cb)
		goto failfmm;

	write = (tfh->cause & TFHCAUSE_TLB_MOD) != 0;
	vaddr = tfh->missvaddr;
	asid = tfh->missasid;
	if (asid == 0)
		goto failnoasid;

	rmb();	/* TFH must be cache resident before reading ms_range_active */

	/*
	 * TFH is cache resident - at least briefly. Fail the dropin
	 * if a range invalidate is active.
	 */
	if (atomic_read(&gts->ts_gms->ms_range_active))
		goto failactive;

	ret = gru_vtop(gts, vaddr, write, atomic, &gpa, &pageshift);
	if (ret == -1)
		goto failinval;
	if (ret == -2)
		goto failupm;

	if (!(gts->ts_sizeavail & GRU_SIZEAVAIL(pageshift))) {
		gts->ts_sizeavail |= GRU_SIZEAVAIL(pageshift);
		if (atomic || !gru_update_cch(gts, 0)) {
			gts->ts_force_cch_reload = 1;
			goto failupm;
		}
	}
	gru_cb_set_istatus_active(cb);
	tfh_write_restart(tfh, gpa, GAA_RAM, vaddr, asid, write,
			  GRU_PAGESIZE(pageshift));
	STAT(tlb_dropin);
	gru_dbg(grudev,
		"%s: tfh 0x%p, vaddr 0x%lx, asid 0x%x, ps %d, gpa 0x%lx\n",
		ret ? "non-atomic" : "atomic", tfh, vaddr, asid,
		pageshift, gpa);
	return 0;

failnoasid:
	/* No asid (delayed unload). */
	STAT(tlb_dropin_fail_no_asid);
	gru_dbg(grudev, "FAILED no_asid tfh: 0x%p, vaddr 0x%lx\n", tfh, vaddr);
	if (!cb)
		tfh_user_polling_mode(tfh);
	else
		gru_flush_cache(tfh);
	return -EAGAIN;

failupm:
	/* Atomic failure switch CBR to UPM */
	tfh_user_polling_mode(tfh);
	STAT(tlb_dropin_fail_upm);
	gru_dbg(grudev, "FAILED upm tfh: 0x%p, vaddr 0x%lx\n", tfh, vaddr);
	return 1;

failfmm:
	/* FMM state on UPM call */
	gru_flush_cache(tfh);
	STAT(tlb_dropin_fail_fmm);
	gru_dbg(grudev, "FAILED fmm tfh: 0x%p, state %d\n", tfh, tfh->state);
	return 0;

failnoexception:
	/* TFH status did not show exception pending */
	gru_flush_cache(tfh);
	if (cb)
		gru_flush_cache(cb);
	STAT(tlb_dropin_fail_no_exception);
	gru_dbg(grudev, "FAILED non-exception tfh: 0x%p, status %d, state %d\n", tfh, tfh->status, tfh->state);
	return 0;

failidle:
	/* TFH state was idle  - no miss pending */
	gru_flush_cache(tfh);
	if (cb)
		gru_flush_cache(cb);
	STAT(tlb_dropin_fail_idle);
	gru_dbg(grudev, "FAILED idle tfh: 0x%p, state %d\n", tfh, tfh->state);
	return 0;

failinval:
	/* All errors (atomic & non-atomic) switch CBR to EXCEPTION state */
	tfh_exception(tfh);
	STAT(tlb_dropin_fail_invalid);
	gru_dbg(grudev, "FAILED inval tfh: 0x%p, vaddr 0x%lx\n", tfh, vaddr);
	return -EFAULT;

failactive:
	/* Range invalidate active. Switch to UPM iff atomic */
	if (!cb)
		tfh_user_polling_mode(tfh);
	else
		gru_flush_cache(tfh);
	STAT(tlb_dropin_fail_range_active);
	gru_dbg(grudev, "FAILED range active: tfh 0x%p, vaddr 0x%lx\n",
		tfh, vaddr);
	return 1;
}

/*
 * Process an external interrupt from the GRU. This interrupt is
 * caused by a TLB miss.
 * Note that this is the interrupt handler that is registered with linux
 * interrupt handlers.
 */
irqreturn_t gru_intr(int irq, void *dev_id)
{
	struct gru_state *gru;
	struct gru_tlb_fault_map imap, dmap;
	struct gru_thread_state *gts;
	struct gru_tlb_fault_handle *tfh = NULL;
	int cbrnum, ctxnum;

	STAT(intr);

	gru = irq_to_gru(irq);
	if (!gru) {
		dev_err(grudev, "GRU: invalid interrupt: cpu %d, irq %d\n",
			raw_smp_processor_id(), irq);
		return IRQ_NONE;
	}
	get_clear_fault_map(gru, &imap, &dmap);

	for_each_cbr_in_tfm(cbrnum, dmap.fault_bits) {
		complete(gru->gs_blade->bs_async_wq);
		gru_dbg(grudev, "gid %d, cbr_done %d, done %d\n",
			gru->gs_gid, cbrnum, gru->gs_blade->bs_async_wq->done);
	}

	for_each_cbr_in_tfm(cbrnum, imap.fault_bits) {
		tfh = get_tfh_by_index(gru, cbrnum);
		prefetchw(tfh);	/* Helps on hdw, required for emulator */

		/*
		 * When hardware sets a bit in the faultmap, it implicitly
		 * locks the GRU context so that it cannot be unloaded.
		 * The gts cannot change until a TFH start/writestart command
		 * is issued.
		 */
		ctxnum = tfh->ctxnum;
		gts = gru->gs_gts[ctxnum];

		/*
		 * This is running in interrupt context. Trylock the mmap_sem.
		 * If it fails, retry the fault in user context.
		 */
		if (!gts->ts_force_cch_reload &&
					down_read_trylock(&gts->ts_mm->mmap_sem)) {
			gru_try_dropin(gts, tfh, NULL);
			up_read(&gts->ts_mm->mmap_sem);
		} else {
			tfh_user_polling_mode(tfh);
			STAT(intr_mm_lock_failed);
		}
	}
	return IRQ_HANDLED;
}


static int gru_user_dropin(struct gru_thread_state *gts,
			   struct gru_tlb_fault_handle *tfh,
			   unsigned long __user *cb)
{
	struct gru_mm_struct *gms = gts->ts_gms;
	int ret;

	while (1) {
		wait_event(gms->ms_wait_queue,
			   atomic_read(&gms->ms_range_active) == 0);
		prefetchw(tfh);	/* Helps on hdw, required for emulator */
		ret = gru_try_dropin(gts, tfh, cb);
		if (ret <= 0)
			return ret;
		STAT(call_os_wait_queue);
	}
}

/*
 * This interface is called as a result of a user detecting a "call OS" bit
 * in a user CB. Normally means that a TLB fault has occurred.
 * 	cb - user virtual address of the CB
 */
int gru_handle_user_call_os(unsigned long cb)
{
	struct gru_tlb_fault_handle *tfh;
	struct gru_thread_state *gts;
	unsigned long __user *cbp;
	int ucbnum, cbrnum, ret = -EINVAL;

	STAT(call_os);
	gru_dbg(grudev, "address 0x%lx\n", cb);

	/* sanity check the cb pointer */
	ucbnum = get_cb_number((void *)cb);
	if ((cb & (GRU_HANDLE_STRIDE - 1)) || ucbnum >= GRU_NUM_CB)
		return -EINVAL;
	cbp = (unsigned long *)cb;

	gts = gru_find_lock_gts(cb);
	if (!gts)
		return -EINVAL;

	if (ucbnum >= gts->ts_cbr_au_count * GRU_CBR_AU_SIZE)
		goto exit;

	/*
	 * If force_unload is set, the UPM TLB fault is phony. The task
	 * has migrated to another node and the GSEG must be moved. Just
	 * unload the context. The task will page fault and assign a new
	 * context.
	 */
	if (gts->ts_tgid_owner == current->tgid && gts->ts_blade >= 0 &&
				gts->ts_blade != uv_numa_blade_id()) {
		STAT(call_os_offnode_reference);
		gts->ts_force_unload = 1;
	}

	/*
	 * CCH may contain stale data if ts_force_cch_reload is set.
	 */
	if (gts->ts_gru && gts->ts_force_cch_reload) {
		gts->ts_force_cch_reload = 0;
		gru_update_cch(gts, 0);
	}

	ret = -EAGAIN;
	cbrnum = thread_cbr_number(gts, ucbnum);
	if (gts->ts_force_unload) {
		gru_unload_context(gts, 1);
	} else if (gts->ts_gru) {
		tfh = get_tfh_by_index(gts->ts_gru, cbrnum);
		ret = gru_user_dropin(gts, tfh, cbp);
	}
exit:
	gru_unlock_gts(gts);
	return ret;
}

/*
 * Fetch the exception detail information for a CB that terminated with
 * an exception.
 */
int gru_get_exception_detail(unsigned long arg)
{
	struct control_block_extended_exc_detail excdet;
	struct gru_control_block_extended *cbe;
	struct gru_thread_state *gts;
	int ucbnum, cbrnum, ret;

	STAT(user_exception);
	if (copy_from_user(&excdet, (void __user *)arg, sizeof(excdet)))
		return -EFAULT;

	gru_dbg(grudev, "address 0x%lx\n", excdet.cb);
	gts = gru_find_lock_gts(excdet.cb);
	if (!gts)
		return -EINVAL;

	ucbnum = get_cb_number((void *)excdet.cb);
	if (ucbnum >= gts->ts_cbr_au_count * GRU_CBR_AU_SIZE) {
		ret = -EINVAL;
	} else if (gts->ts_gru) {
		cbrnum = thread_cbr_number(gts, ucbnum);
		cbe = get_cbe_by_index(gts->ts_gru, cbrnum);
		gru_flush_cache(cbe);	/* CBE not coherent */
		excdet.opc = cbe->opccpy;
		excdet.exopc = cbe->exopccpy;
		excdet.ecause = cbe->ecause;
		excdet.exceptdet0 = cbe->idef1upd;
		excdet.exceptdet1 = cbe->idef3upd;
		excdet.cbrstate = cbe->cbrstate;
		excdet.cbrexecstatus = cbe->cbrexecstatus;
		gru_flush_cache(cbe);
		ret = 0;
	} else {
		ret = -EAGAIN;
	}
	gru_unlock_gts(gts);

	gru_dbg(grudev,
		"cb 0x%lx, op %d, exopc %d, cbrstate %d, cbrexecstatus 0x%x, ecause 0x%x, "
		"exdet0 0x%lx, exdet1 0x%x\n",
		excdet.cb, excdet.opc, excdet.exopc, excdet.cbrstate, excdet.cbrexecstatus,
		excdet.ecause, excdet.exceptdet0, excdet.exceptdet1);
	if (!ret && copy_to_user((void __user *)arg, &excdet, sizeof(excdet)))
		ret = -EFAULT;
	return ret;
}

/*
 * User request to unload a context. Content is saved for possible reload.
 */
static int gru_unload_all_contexts(void)
{
	struct gru_thread_state *gts;
	struct gru_state *gru;
	int gid, ctxnum;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;
	foreach_gid(gid) {
		gru = GID_TO_GRU(gid);
		spin_lock(&gru->gs_lock);
		for (ctxnum = 0; ctxnum < GRU_NUM_CCH; ctxnum++) {
			gts = gru->gs_gts[ctxnum];
			if (gts && mutex_trylock(&gts->ts_ctxlock)) {
				spin_unlock(&gru->gs_lock);
				gru_unload_context(gts, 1);
				mutex_unlock(&gts->ts_ctxlock);
				spin_lock(&gru->gs_lock);
			}
		}
		spin_unlock(&gru->gs_lock);
	}
	return 0;
}

int gru_user_unload_context(unsigned long arg)
{
	struct gru_thread_state *gts;
	struct gru_unload_context_req req;

	STAT(user_unload_context);
	if (copy_from_user(&req, (void __user *)arg, sizeof(req)))
		return -EFAULT;

	gru_dbg(grudev, "gseg 0x%lx\n", req.gseg);

	if (!req.gseg)
		return gru_unload_all_contexts();

	gts = gru_find_lock_gts(req.gseg);
	if (!gts)
		return -EINVAL;

	if (gts->ts_gru)
		gru_unload_context(gts, 1);
	gru_unlock_gts(gts);

	return 0;
}

/*
 * User request to flush a range of virtual addresses from the GRU TLB
 * (Mainly for testing).
 */
int gru_user_flush_tlb(unsigned long arg)
{
	struct gru_thread_state *gts;
	struct gru_flush_tlb_req req;

	STAT(user_flush_tlb);
	if (copy_from_user(&req, (void __user *)arg, sizeof(req)))
		return -EFAULT;

	gru_dbg(grudev, "gseg 0x%lx, vaddr 0x%lx, len 0x%lx\n", req.gseg,
		req.vaddr, req.len);

	gts = gru_find_lock_gts(req.gseg);
	if (!gts)
		return -EINVAL;

	gru_flush_tlb_range(gts->ts_gms, req.vaddr, req.len);
	gru_unlock_gts(gts);

	return 0;
}

/*
 * Register the current task as the user of the GSEG slice.
 * Needed for TLB fault interrupt targeting.
 */
int gru_set_task_slice(long address)
{
	struct gru_thread_state *gts;

	STAT(set_task_slice);
	gru_dbg(grudev, "address 0x%lx\n", address);
	gts = gru_alloc_locked_gts(address);
	if (!gts)
		return -EINVAL;

	gts->ts_tgid_owner = current->tgid;
	gru_unlock_gts(gts);

	return 0;
}
OpenPOWER on IntegriCloud