summaryrefslogtreecommitdiffstats
path: root/drivers/misc/habanalabs/common/mmu_v1.c
blob: 8d1eb5265419d9bda13159dd6cb332b6fb9a72ca (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
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
// SPDX-License-Identifier: GPL-2.0

/*
 * Copyright 2016-2019 HabanaLabs, Ltd.
 * All Rights Reserved.
 */

#include "habanalabs.h"
#include "../include/hw_ip/mmu/mmu_general.h"

#include <linux/genalloc.h>
#include <linux/slab.h>

static inline u64 get_phys_addr(struct hl_ctx *ctx, u64 shadow_addr);

static struct pgt_info *get_pgt_info(struct hl_ctx *ctx, u64 hop_addr)
{
	struct pgt_info *pgt_info = NULL;

	hash_for_each_possible(ctx->mmu_shadow_hash, pgt_info, node,
				(unsigned long) hop_addr)
		if (hop_addr == pgt_info->shadow_addr)
			break;

	return pgt_info;
}

static void _free_hop(struct hl_ctx *ctx, struct pgt_info *pgt_info)
{
	struct hl_device *hdev = ctx->hdev;

	gen_pool_free(hdev->mmu_priv.mmu_pgt_pool, pgt_info->phys_addr,
			hdev->asic_prop.mmu_hop_table_size);
	hash_del(&pgt_info->node);
	kfree((u64 *) (uintptr_t) pgt_info->shadow_addr);
	kfree(pgt_info);
}

static void free_hop(struct hl_ctx *ctx, u64 hop_addr)
{
	struct pgt_info *pgt_info = get_pgt_info(ctx, hop_addr);

	_free_hop(ctx, pgt_info);
}

static u64 alloc_hop(struct hl_ctx *ctx)
{
	struct hl_device *hdev = ctx->hdev;
	struct asic_fixed_properties *prop = &hdev->asic_prop;
	struct pgt_info *pgt_info;
	u64 phys_addr, shadow_addr;

	pgt_info = kmalloc(sizeof(*pgt_info), GFP_KERNEL);
	if (!pgt_info)
		return ULLONG_MAX;

	phys_addr = (u64) gen_pool_alloc(hdev->mmu_priv.mmu_pgt_pool,
					prop->mmu_hop_table_size);
	if (!phys_addr) {
		dev_err(hdev->dev, "failed to allocate page\n");
		goto pool_add_err;
	}

	shadow_addr = (u64) (uintptr_t) kzalloc(prop->mmu_hop_table_size,
						GFP_KERNEL);
	if (!shadow_addr)
		goto shadow_err;

	pgt_info->phys_addr = phys_addr;
	pgt_info->shadow_addr = shadow_addr;
	pgt_info->ctx = ctx;
	pgt_info->num_of_ptes = 0;
	hash_add(ctx->mmu_shadow_hash, &pgt_info->node, shadow_addr);

	return shadow_addr;

shadow_err:
	gen_pool_free(hdev->mmu_priv.mmu_pgt_pool, phys_addr,
			prop->mmu_hop_table_size);
pool_add_err:
	kfree(pgt_info);

	return ULLONG_MAX;
}

static inline u64 get_phys_hop0_addr(struct hl_ctx *ctx)
{
	return ctx->hdev->asic_prop.mmu_pgt_addr +
			(ctx->asid * ctx->hdev->asic_prop.mmu_hop_table_size);
}

static inline u64 get_hop0_addr(struct hl_ctx *ctx)
{
	return (u64) (uintptr_t) ctx->hdev->mmu_priv.mmu_shadow_hop0 +
			(ctx->asid * ctx->hdev->asic_prop.mmu_hop_table_size);
}

static void flush(struct hl_ctx *ctx)
{
	/* flush all writes from all cores to reach PCI */
	mb();
	ctx->hdev->asic_funcs->read_pte(ctx->hdev, get_phys_hop0_addr(ctx));
}

/* transform the value to physical address when writing to H/W */
static inline void write_pte(struct hl_ctx *ctx, u64 shadow_pte_addr, u64 val)
{
	/*
	 * The value to write is actually the address of the next shadow hop +
	 * flags at the 12 LSBs.
	 * Hence in order to get the value to write to the physical PTE, we
	 * clear the 12 LSBs and translate the shadow hop to its associated
	 * physical hop, and add back the original 12 LSBs.
	 */
	u64 phys_val = get_phys_addr(ctx, val & HOP_PHYS_ADDR_MASK) |
				(val & FLAGS_MASK);

	ctx->hdev->asic_funcs->write_pte(ctx->hdev,
					get_phys_addr(ctx, shadow_pte_addr),
					phys_val);

	*(u64 *) (uintptr_t) shadow_pte_addr = val;
}

/* do not transform the value to physical address when writing to H/W */
static inline void write_final_pte(struct hl_ctx *ctx, u64 shadow_pte_addr,
					u64 val)
{
	ctx->hdev->asic_funcs->write_pte(ctx->hdev,
					get_phys_addr(ctx, shadow_pte_addr),
					val);
	*(u64 *) (uintptr_t) shadow_pte_addr = val;
}

/* clear the last and present bits */
static inline void clear_pte(struct hl_ctx *ctx, u64 pte_addr)
{
	/* no need to transform the value to physical address */
	write_final_pte(ctx, pte_addr, 0);
}

static inline void get_pte(struct hl_ctx *ctx, u64 hop_addr)
{
	get_pgt_info(ctx, hop_addr)->num_of_ptes++;
}

/*
 * put_pte - decrement the num of ptes and free the hop if possible
 *
 * @ctx: pointer to the context structure
 * @hop_addr: addr of the hop
 *
 * This function returns the number of ptes left on this hop. If the number is
 * 0, it means the pte was freed.
 */
static inline int put_pte(struct hl_ctx *ctx, u64 hop_addr)
{
	struct pgt_info *pgt_info = get_pgt_info(ctx, hop_addr);
	int num_of_ptes_left;

	pgt_info->num_of_ptes--;

	/*
	 * Need to save the number of ptes left because free_hop might free
	 * the pgt_info
	 */
	num_of_ptes_left = pgt_info->num_of_ptes;
	if (!num_of_ptes_left)
		_free_hop(ctx, pgt_info);

	return num_of_ptes_left;
}

static inline u64 get_hopN_pte_addr(struct hl_ctx *ctx, u64 hop_addr,
					u64 virt_addr, u64 mask, u64 shift)
{
	return hop_addr + ctx->hdev->asic_prop.mmu_pte_size *
			((virt_addr & mask) >> shift);
}

static inline u64 get_hop0_pte_addr(struct hl_ctx *ctx,
					struct hl_mmu_properties *mmu_prop,
					u64 hop_addr, u64 vaddr)
{
	return get_hopN_pte_addr(ctx, hop_addr, vaddr, mmu_prop->hop0_mask,
					mmu_prop->hop0_shift);
}

static inline u64 get_hop1_pte_addr(struct hl_ctx *ctx,
					struct hl_mmu_properties *mmu_prop,
					u64 hop_addr, u64 vaddr)
{
	return get_hopN_pte_addr(ctx, hop_addr, vaddr, mmu_prop->hop1_mask,
					mmu_prop->hop1_shift);
}

static inline u64 get_hop2_pte_addr(struct hl_ctx *ctx,
					struct hl_mmu_properties *mmu_prop,
					u64 hop_addr, u64 vaddr)
{
	return get_hopN_pte_addr(ctx, hop_addr, vaddr, mmu_prop->hop2_mask,
					mmu_prop->hop2_shift);
}

static inline u64 get_hop3_pte_addr(struct hl_ctx *ctx,
					struct hl_mmu_properties *mmu_prop,
					u64 hop_addr, u64 vaddr)
{
	return get_hopN_pte_addr(ctx, hop_addr, vaddr, mmu_prop->hop3_mask,
					mmu_prop->hop3_shift);
}

static inline u64 get_hop4_pte_addr(struct hl_ctx *ctx,
					struct hl_mmu_properties *mmu_prop,
					u64 hop_addr, u64 vaddr)
{
	return get_hopN_pte_addr(ctx, hop_addr, vaddr, mmu_prop->hop4_mask,
					mmu_prop->hop4_shift);
}

static inline u64 get_next_hop_addr(struct hl_ctx *ctx, u64 curr_pte)
{
	if (curr_pte & PAGE_PRESENT_MASK)
		return curr_pte & HOP_PHYS_ADDR_MASK;
	else
		return ULLONG_MAX;
}

static inline u64 get_alloc_next_hop_addr(struct hl_ctx *ctx, u64 curr_pte,
						bool *is_new_hop)
{
	u64 hop_addr = get_next_hop_addr(ctx, curr_pte);

	if (hop_addr == ULLONG_MAX) {
		hop_addr = alloc_hop(ctx);
		*is_new_hop = (hop_addr != ULLONG_MAX);
	}

	return hop_addr;
}

/* translates shadow address inside hop to a physical address */
static inline u64 get_phys_addr(struct hl_ctx *ctx, u64 shadow_addr)
{
	u64 page_mask = (ctx->hdev->asic_prop.mmu_hop_table_size - 1);
	u64 shadow_hop_addr = shadow_addr & ~page_mask;
	u64 pte_offset = shadow_addr & page_mask;
	u64 phys_hop_addr;

	if (shadow_hop_addr != get_hop0_addr(ctx))
		phys_hop_addr = get_pgt_info(ctx, shadow_hop_addr)->phys_addr;
	else
		phys_hop_addr = get_phys_hop0_addr(ctx);

	return phys_hop_addr + pte_offset;
}

static int dram_default_mapping_init(struct hl_ctx *ctx)
{
	struct hl_device *hdev = ctx->hdev;
	struct asic_fixed_properties *prop = &hdev->asic_prop;
	u64 num_of_hop3, total_hops, hop0_addr, hop1_addr, hop2_addr,
		hop2_pte_addr, hop3_pte_addr, pte_val;
	int rc, i, j, hop3_allocated = 0;

	if ((!hdev->dram_supports_virtual_memory) ||
			(!hdev->dram_default_page_mapping) ||
			(ctx->asid == HL_KERNEL_ASID_ID))
		return 0;

	num_of_hop3 = prop->dram_size_for_default_page_mapping;
	do_div(num_of_hop3, prop->dram_page_size);
	do_div(num_of_hop3, PTE_ENTRIES_IN_HOP);

	/* add hop1 and hop2 */
	total_hops = num_of_hop3 + 2;

	ctx->dram_default_hops = kzalloc(HL_PTE_SIZE * total_hops,  GFP_KERNEL);
	if (!ctx->dram_default_hops)
		return -ENOMEM;

	hop0_addr = get_hop0_addr(ctx);

	hop1_addr = alloc_hop(ctx);
	if (hop1_addr == ULLONG_MAX) {
		dev_err(hdev->dev, "failed to alloc hop 1\n");
		rc = -ENOMEM;
		goto hop1_err;
	}

	ctx->dram_default_hops[total_hops - 1] = hop1_addr;

	hop2_addr = alloc_hop(ctx);
	if (hop2_addr == ULLONG_MAX) {
		dev_err(hdev->dev, "failed to alloc hop 2\n");
		rc = -ENOMEM;
		goto hop2_err;
	}

	ctx->dram_default_hops[total_hops - 2] = hop2_addr;

	for (i = 0 ; i < num_of_hop3 ; i++) {
		ctx->dram_default_hops[i] = alloc_hop(ctx);
		if (ctx->dram_default_hops[i] == ULLONG_MAX) {
			dev_err(hdev->dev, "failed to alloc hop 3, i: %d\n", i);
			rc = -ENOMEM;
			goto hop3_err;
		}
		hop3_allocated++;
	}

	/* need only pte 0 in hops 0 and 1 */
	pte_val = (hop1_addr & HOP_PHYS_ADDR_MASK) | PAGE_PRESENT_MASK;
	write_pte(ctx, hop0_addr, pte_val);

	pte_val = (hop2_addr & HOP_PHYS_ADDR_MASK) | PAGE_PRESENT_MASK;
	write_pte(ctx, hop1_addr, pte_val);
	get_pte(ctx, hop1_addr);

	hop2_pte_addr = hop2_addr;
	for (i = 0 ; i < num_of_hop3 ; i++) {
		pte_val = (ctx->dram_default_hops[i] & HOP_PHYS_ADDR_MASK) |
				PAGE_PRESENT_MASK;
		write_pte(ctx, hop2_pte_addr, pte_val);
		get_pte(ctx, hop2_addr);
		hop2_pte_addr += HL_PTE_SIZE;
	}

	pte_val = (prop->mmu_dram_default_page_addr & HOP_PHYS_ADDR_MASK) |
			LAST_MASK | PAGE_PRESENT_MASK;

	for (i = 0 ; i < num_of_hop3 ; i++) {
		hop3_pte_addr = ctx->dram_default_hops[i];
		for (j = 0 ; j < PTE_ENTRIES_IN_HOP ; j++) {
			write_final_pte(ctx, hop3_pte_addr, pte_val);
			get_pte(ctx, ctx->dram_default_hops[i]);
			hop3_pte_addr += HL_PTE_SIZE;
		}
	}

	flush(ctx);

	return 0;

hop3_err:
	for (i = 0 ; i < hop3_allocated ; i++)
		free_hop(ctx, ctx->dram_default_hops[i]);

	free_hop(ctx, hop2_addr);
hop2_err:
	free_hop(ctx, hop1_addr);
hop1_err:
	kfree(ctx->dram_default_hops);

	return rc;
}

static void dram_default_mapping_fini(struct hl_ctx *ctx)
{
	struct hl_device *hdev = ctx->hdev;
	struct asic_fixed_properties *prop = &hdev->asic_prop;
	u64 num_of_hop3, total_hops, hop0_addr, hop1_addr, hop2_addr,
		hop2_pte_addr, hop3_pte_addr;
	int i, j;

	if ((!hdev->dram_supports_virtual_memory) ||
			(!hdev->dram_default_page_mapping) ||
			(ctx->asid == HL_KERNEL_ASID_ID))
		return;

	num_of_hop3 = prop->dram_size_for_default_page_mapping;
	do_div(num_of_hop3, prop->dram_page_size);
	do_div(num_of_hop3, PTE_ENTRIES_IN_HOP);

	hop0_addr = get_hop0_addr(ctx);
	/* add hop1 and hop2 */
	total_hops = num_of_hop3 + 2;
	hop1_addr = ctx->dram_default_hops[total_hops - 1];
	hop2_addr = ctx->dram_default_hops[total_hops - 2];

	for (i = 0 ; i < num_of_hop3 ; i++) {
		hop3_pte_addr = ctx->dram_default_hops[i];
		for (j = 0 ; j < PTE_ENTRIES_IN_HOP ; j++) {
			clear_pte(ctx, hop3_pte_addr);
			put_pte(ctx, ctx->dram_default_hops[i]);
			hop3_pte_addr += HL_PTE_SIZE;
		}
	}

	hop2_pte_addr = hop2_addr;
	hop2_pte_addr = hop2_addr;
	for (i = 0 ; i < num_of_hop3 ; i++) {
		clear_pte(ctx, hop2_pte_addr);
		put_pte(ctx, hop2_addr);
		hop2_pte_addr += HL_PTE_SIZE;
	}

	clear_pte(ctx, hop1_addr);
	put_pte(ctx, hop1_addr);
	clear_pte(ctx, hop0_addr);

	kfree(ctx->dram_default_hops);

	flush(ctx);
}

/**
 * hl_mmu_v1_init() - initialize the MMU module.
 * @hdev: habanalabs device structure.
 *
 * This function does the following:
 * - Create a pool of pages for pgt_infos.
 * - Create a shadow table for pgt
 *
 * Return: 0 for success, non-zero for failure.
 */
static int hl_mmu_v1_init(struct hl_device *hdev)
{
	struct asic_fixed_properties *prop = &hdev->asic_prop;
	int rc;

	hdev->mmu_priv.mmu_pgt_pool =
			gen_pool_create(__ffs(prop->mmu_hop_table_size), -1);

	if (!hdev->mmu_priv.mmu_pgt_pool) {
		dev_err(hdev->dev, "Failed to create page gen pool\n");
		return -ENOMEM;
	}

	rc = gen_pool_add(hdev->mmu_priv.mmu_pgt_pool, prop->mmu_pgt_addr +
			prop->mmu_hop0_tables_total_size,
			prop->mmu_pgt_size - prop->mmu_hop0_tables_total_size,
			-1);
	if (rc) {
		dev_err(hdev->dev, "Failed to add memory to page gen pool\n");
		goto err_pool_add;
	}

	hdev->mmu_priv.mmu_shadow_hop0 = kvmalloc_array(prop->max_asid,
						prop->mmu_hop_table_size,
						GFP_KERNEL | __GFP_ZERO);
	if (ZERO_OR_NULL_PTR(hdev->mmu_priv.mmu_shadow_hop0)) {
		rc = -ENOMEM;
		goto err_pool_add;
	}

	/* MMU H/W init will be done in device hw_init() */

	return 0;

err_pool_add:
	gen_pool_destroy(hdev->mmu_priv.mmu_pgt_pool);

	return rc;
}

/**
 * hl_mmu_fini() - release the MMU module.
 * @hdev: habanalabs device structure.
 *
 * This function does the following:
 * - Disable MMU in H/W.
 * - Free the pgt_infos pool.
 *
 * All contexts should be freed before calling this function.
 */
static void hl_mmu_v1_fini(struct hl_device *hdev)
{
	/* MMU H/W fini was already done in device hw_fini() */

	kvfree(hdev->mmu_priv.mmu_shadow_hop0);
	gen_pool_destroy(hdev->mmu_priv.mmu_pgt_pool);
}

/**
 * hl_mmu_ctx_init() - initialize a context for using the MMU module.
 * @ctx: pointer to the context structure to initialize.
 *
 * Initialize a mutex to protect the concurrent mapping flow, a hash to hold all
 * page tables hops related to this context.
 * Return: 0 on success, non-zero otherwise.
 */
static int hl_mmu_v1_ctx_init(struct hl_ctx *ctx)
{
	mutex_init(&ctx->mmu_lock);
	hash_init(ctx->mmu_shadow_hash);

	return dram_default_mapping_init(ctx);
}

/*
 * hl_mmu_ctx_fini - disable a ctx from using the mmu module
 *
 * @ctx: pointer to the context structure
 *
 * This function does the following:
 * - Free any pgts which were not freed yet
 * - Free the mutex
 * - Free DRAM default page mapping hops
 */
static void hl_mmu_v1_ctx_fini(struct hl_ctx *ctx)
{
	struct hl_device *hdev = ctx->hdev;
	struct pgt_info *pgt_info;
	struct hlist_node *tmp;
	int i;

	dram_default_mapping_fini(ctx);

	if (!hash_empty(ctx->mmu_shadow_hash))
		dev_err(hdev->dev, "ctx %d is freed while it has pgts in use\n",
			ctx->asid);

	hash_for_each_safe(ctx->mmu_shadow_hash, i, tmp, pgt_info, node) {
		dev_err_ratelimited(hdev->dev,
			"pgt_info of addr 0x%llx of asid %d was not destroyed, num_ptes: %d\n",
			pgt_info->phys_addr, ctx->asid, pgt_info->num_of_ptes);
		_free_hop(ctx, pgt_info);
	}

	mutex_destroy(&ctx->mmu_lock);
}

static int _hl_mmu_v1_unmap(struct hl_ctx *ctx,
				u64 virt_addr, bool is_dram_addr)
{
	struct hl_device *hdev = ctx->hdev;
	struct asic_fixed_properties *prop = &hdev->asic_prop;
	struct hl_mmu_properties *mmu_prop;
	u64 hop0_addr = 0, hop0_pte_addr = 0,
		hop1_addr = 0, hop1_pte_addr = 0,
		hop2_addr = 0, hop2_pte_addr = 0,
		hop3_addr = 0, hop3_pte_addr = 0,
		hop4_addr = 0, hop4_pte_addr = 0,
		curr_pte;
	bool is_huge, clear_hop3 = true;

	/* shifts and masks are the same in PMMU and HPMMU, use one of them */
	mmu_prop = is_dram_addr ? &prop->dmmu : &prop->pmmu;

	hop0_addr = get_hop0_addr(ctx);
	hop0_pte_addr = get_hop0_pte_addr(ctx, mmu_prop, hop0_addr, virt_addr);

	curr_pte = *(u64 *) (uintptr_t) hop0_pte_addr;

	hop1_addr = get_next_hop_addr(ctx, curr_pte);

	if (hop1_addr == ULLONG_MAX)
		goto not_mapped;

	hop1_pte_addr = get_hop1_pte_addr(ctx, mmu_prop, hop1_addr, virt_addr);

	curr_pte = *(u64 *) (uintptr_t) hop1_pte_addr;

	hop2_addr = get_next_hop_addr(ctx, curr_pte);

	if (hop2_addr == ULLONG_MAX)
		goto not_mapped;

	hop2_pte_addr = get_hop2_pte_addr(ctx, mmu_prop, hop2_addr, virt_addr);

	curr_pte = *(u64 *) (uintptr_t) hop2_pte_addr;

	hop3_addr = get_next_hop_addr(ctx, curr_pte);

	if (hop3_addr == ULLONG_MAX)
		goto not_mapped;

	hop3_pte_addr = get_hop3_pte_addr(ctx, mmu_prop, hop3_addr, virt_addr);

	curr_pte = *(u64 *) (uintptr_t) hop3_pte_addr;

	is_huge = curr_pte & LAST_MASK;

	if (is_dram_addr && !is_huge) {
		dev_err(hdev->dev,
				"DRAM unmapping should use huge pages only\n");
		return -EFAULT;
	}

	if (!is_huge) {
		hop4_addr = get_next_hop_addr(ctx, curr_pte);

		if (hop4_addr == ULLONG_MAX)
			goto not_mapped;

		hop4_pte_addr = get_hop4_pte_addr(ctx, mmu_prop, hop4_addr,
							virt_addr);

		curr_pte = *(u64 *) (uintptr_t) hop4_pte_addr;

		clear_hop3 = false;
	}

	if (hdev->dram_default_page_mapping && is_dram_addr) {
		u64 default_pte = (prop->mmu_dram_default_page_addr &
				HOP_PHYS_ADDR_MASK) | LAST_MASK |
					PAGE_PRESENT_MASK;
		if (curr_pte == default_pte) {
			dev_err(hdev->dev,
				"DRAM: hop3 PTE points to zero page, can't unmap, va: 0x%llx\n",
					virt_addr);
			goto not_mapped;
		}

		if (!(curr_pte & PAGE_PRESENT_MASK)) {
			dev_err(hdev->dev,
				"DRAM: hop3 PTE is cleared! can't unmap, va: 0x%llx\n",
					virt_addr);
			goto not_mapped;
		}

		write_final_pte(ctx, hop3_pte_addr, default_pte);
		put_pte(ctx, hop3_addr);
	} else {
		if (!(curr_pte & PAGE_PRESENT_MASK))
			goto not_mapped;

		if (hop4_addr)
			clear_pte(ctx, hop4_pte_addr);
		else
			clear_pte(ctx, hop3_pte_addr);

		if (hop4_addr && !put_pte(ctx, hop4_addr))
			clear_hop3 = true;

		if (!clear_hop3)
			goto mapped;

		clear_pte(ctx, hop3_pte_addr);

		if (put_pte(ctx, hop3_addr))
			goto mapped;

		clear_pte(ctx, hop2_pte_addr);

		if (put_pte(ctx, hop2_addr))
			goto mapped;

		clear_pte(ctx, hop1_pte_addr);

		if (put_pte(ctx, hop1_addr))
			goto mapped;

		clear_pte(ctx, hop0_pte_addr);
	}

mapped:
	return 0;

not_mapped:
	dev_err(hdev->dev, "virt addr 0x%llx is not mapped to phys addr\n",
		virt_addr);

	return -EINVAL;
}

static int _hl_mmu_v1_map(struct hl_ctx *ctx, u64 virt_addr, u64 phys_addr,
			u32 page_size, bool is_dram_addr)
{
	struct hl_device *hdev = ctx->hdev;
	struct asic_fixed_properties *prop = &hdev->asic_prop;
	struct hl_mmu_properties *mmu_prop;
	u64 hop0_addr = 0, hop0_pte_addr = 0,
		hop1_addr = 0, hop1_pte_addr = 0,
		hop2_addr = 0, hop2_pte_addr = 0,
		hop3_addr = 0, hop3_pte_addr = 0,
		hop4_addr = 0, hop4_pte_addr = 0,
		curr_pte = 0;
	bool hop1_new = false, hop2_new = false, hop3_new = false,
		hop4_new = false, is_huge;
	int rc = -ENOMEM;

	/*
	 * This mapping function can map a page or a huge page. For huge page
	 * there are only 3 hops rather than 4. Currently the DRAM allocation
	 * uses huge pages only but user memory could have been allocated with
	 * one of the two page sizes. Since this is a common code for all the
	 * three cases, we need this hugs page check.
	 */
	if (is_dram_addr) {
		mmu_prop = &prop->dmmu;
		is_huge = true;
	} else if (page_size == prop->pmmu_huge.page_size) {
		mmu_prop = &prop->pmmu_huge;
		is_huge = true;
	} else {
		mmu_prop = &prop->pmmu;
		is_huge = false;
	}

	hop0_addr = get_hop0_addr(ctx);
	hop0_pte_addr = get_hop0_pte_addr(ctx, mmu_prop, hop0_addr, virt_addr);
	curr_pte = *(u64 *) (uintptr_t) hop0_pte_addr;

	hop1_addr = get_alloc_next_hop_addr(ctx, curr_pte, &hop1_new);
	if (hop1_addr == ULLONG_MAX)
		goto err;

	hop1_pte_addr = get_hop1_pte_addr(ctx, mmu_prop, hop1_addr, virt_addr);
	curr_pte = *(u64 *) (uintptr_t) hop1_pte_addr;

	hop2_addr = get_alloc_next_hop_addr(ctx, curr_pte, &hop2_new);
	if (hop2_addr == ULLONG_MAX)
		goto err;

	hop2_pte_addr = get_hop2_pte_addr(ctx, mmu_prop, hop2_addr, virt_addr);
	curr_pte = *(u64 *) (uintptr_t) hop2_pte_addr;

	hop3_addr = get_alloc_next_hop_addr(ctx, curr_pte, &hop3_new);
	if (hop3_addr == ULLONG_MAX)
		goto err;

	hop3_pte_addr = get_hop3_pte_addr(ctx, mmu_prop, hop3_addr, virt_addr);
	curr_pte = *(u64 *) (uintptr_t) hop3_pte_addr;

	if (!is_huge) {
		hop4_addr = get_alloc_next_hop_addr(ctx, curr_pte, &hop4_new);
		if (hop4_addr == ULLONG_MAX)
			goto err;

		hop4_pte_addr = get_hop4_pte_addr(ctx, mmu_prop, hop4_addr,
							virt_addr);
		curr_pte = *(u64 *) (uintptr_t) hop4_pte_addr;
	}

	if (hdev->dram_default_page_mapping && is_dram_addr) {
		u64 default_pte = (prop->mmu_dram_default_page_addr &
					HOP_PHYS_ADDR_MASK) | LAST_MASK |
						PAGE_PRESENT_MASK;

		if (curr_pte != default_pte) {
			dev_err(hdev->dev,
				"DRAM: mapping already exists for virt_addr 0x%llx\n",
					virt_addr);
			rc = -EINVAL;
			goto err;
		}

		if (hop1_new || hop2_new || hop3_new || hop4_new) {
			dev_err(hdev->dev,
				"DRAM mapping should not allocate more hops\n");
			rc = -EFAULT;
			goto err;
		}
	} else if (curr_pte & PAGE_PRESENT_MASK) {
		dev_err(hdev->dev,
			"mapping already exists for virt_addr 0x%llx\n",
				virt_addr);

		dev_dbg(hdev->dev, "hop0 pte: 0x%llx (0x%llx)\n",
			*(u64 *) (uintptr_t) hop0_pte_addr, hop0_pte_addr);
		dev_dbg(hdev->dev, "hop1 pte: 0x%llx (0x%llx)\n",
			*(u64 *) (uintptr_t) hop1_pte_addr, hop1_pte_addr);
		dev_dbg(hdev->dev, "hop2 pte: 0x%llx (0x%llx)\n",
			*(u64 *) (uintptr_t) hop2_pte_addr, hop2_pte_addr);
		dev_dbg(hdev->dev, "hop3 pte: 0x%llx (0x%llx)\n",
			*(u64 *) (uintptr_t) hop3_pte_addr, hop3_pte_addr);

		if (!is_huge)
			dev_dbg(hdev->dev, "hop4 pte: 0x%llx (0x%llx)\n",
				*(u64 *) (uintptr_t) hop4_pte_addr,
				hop4_pte_addr);

		rc = -EINVAL;
		goto err;
	}

	curr_pte = (phys_addr & HOP_PHYS_ADDR_MASK) | LAST_MASK
			| PAGE_PRESENT_MASK;

	if (is_huge)
		write_final_pte(ctx, hop3_pte_addr, curr_pte);
	else
		write_final_pte(ctx, hop4_pte_addr, curr_pte);

	if (hop1_new) {
		curr_pte =
			(hop1_addr & HOP_PHYS_ADDR_MASK) | PAGE_PRESENT_MASK;
		write_pte(ctx, hop0_pte_addr, curr_pte);
	}
	if (hop2_new) {
		curr_pte =
			(hop2_addr & HOP_PHYS_ADDR_MASK) | PAGE_PRESENT_MASK;
		write_pte(ctx, hop1_pte_addr, curr_pte);
		get_pte(ctx, hop1_addr);
	}
	if (hop3_new) {
		curr_pte =
			(hop3_addr & HOP_PHYS_ADDR_MASK) | PAGE_PRESENT_MASK;
		write_pte(ctx, hop2_pte_addr, curr_pte);
		get_pte(ctx, hop2_addr);
	}

	if (!is_huge) {
		if (hop4_new) {
			curr_pte = (hop4_addr & HOP_PHYS_ADDR_MASK) |
					PAGE_PRESENT_MASK;
			write_pte(ctx, hop3_pte_addr, curr_pte);
			get_pte(ctx, hop3_addr);
		}

		get_pte(ctx, hop4_addr);
	} else {
		get_pte(ctx, hop3_addr);
	}

	return 0;

err:
	if (hop4_new)
		free_hop(ctx, hop4_addr);
	if (hop3_new)
		free_hop(ctx, hop3_addr);
	if (hop2_new)
		free_hop(ctx, hop2_addr);
	if (hop1_new)
		free_hop(ctx, hop1_addr);

	return rc;
}

/*
 * hl_mmu_v1_swap_out - marks all mapping of the given ctx as swapped out
 *
 * @ctx: pointer to the context structure
 *
 */
static void hl_mmu_v1_swap_out(struct hl_ctx *ctx)
{

}

/*
 * hl_mmu_v1_swap_in - marks all mapping of the given ctx as swapped in
 *
 * @ctx: pointer to the context structure
 *
 */
static void hl_mmu_v1_swap_in(struct hl_ctx *ctx)
{

}

/*
 * hl_mmu_v1_prepare - prepare mmu  for working with mmu v1
 *
 * @hdev: pointer to the device structure
 */
void hl_mmu_v1_set_funcs(struct hl_device *hdev)
{
	struct hl_mmu_funcs *mmu = &hdev->mmu_func;

	mmu->init = hl_mmu_v1_init;
	mmu->fini = hl_mmu_v1_fini;
	mmu->ctx_init = hl_mmu_v1_ctx_init;
	mmu->ctx_fini = hl_mmu_v1_ctx_fini;
	mmu->map = _hl_mmu_v1_map;
	mmu->unmap = _hl_mmu_v1_unmap;
	mmu->flush = flush;
	mmu->swap_out = hl_mmu_v1_swap_out;
	mmu->swap_in = hl_mmu_v1_swap_in;
}