summaryrefslogtreecommitdiff
path: root/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
blob: 5968a568aae2afea4d8358c8ecfbb7c69dfaa296 (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Implementation of the IOMMU SVA API for the ARM SMMUv3
 */

#include <linux/mm.h>
#include <linux/mmu_context.h>
#include <linux/mmu_notifier.h>
#include <linux/sched/mm.h>
#include <linux/slab.h>

#include "arm-smmu-v3.h"
#include "../../iommu-sva-lib.h"
#include "../../io-pgtable-arm.h"

struct arm_smmu_mmu_notifier {
	struct mmu_notifier		mn;
	struct arm_smmu_ctx_desc	*cd;
	bool				cleared;
	refcount_t			refs;
	struct list_head		list;
	struct arm_smmu_domain		*domain;
};

#define mn_to_smmu(mn) container_of(mn, struct arm_smmu_mmu_notifier, mn)

struct arm_smmu_bond {
	struct iommu_sva		sva;
	struct mm_struct		*mm;
	struct arm_smmu_mmu_notifier	*smmu_mn;
	struct list_head		list;
	refcount_t			refs;
};

#define sva_to_bond(handle) \
	container_of(handle, struct arm_smmu_bond, sva)

static DEFINE_MUTEX(sva_lock);

/*
 * Check if the CPU ASID is available on the SMMU side. If a private context
 * descriptor is using it, try to replace it.
 */
static struct arm_smmu_ctx_desc *
arm_smmu_share_asid(struct mm_struct *mm, u16 asid)
{
	int ret;
	u32 new_asid;
	struct arm_smmu_ctx_desc *cd;
	struct arm_smmu_device *smmu;
	struct arm_smmu_domain *smmu_domain;

	cd = xa_load(&arm_smmu_asid_xa, asid);
	if (!cd)
		return NULL;

	if (cd->mm) {
		if (WARN_ON(cd->mm != mm))
			return ERR_PTR(-EINVAL);
		/* All devices bound to this mm use the same cd struct. */
		refcount_inc(&cd->refs);
		return cd;
	}

	smmu_domain = container_of(cd, struct arm_smmu_domain, s1_cfg.cd);
	smmu = smmu_domain->smmu;

	ret = xa_alloc(&arm_smmu_asid_xa, &new_asid, cd,
		       XA_LIMIT(1, (1 << smmu->asid_bits) - 1), GFP_KERNEL);
	if (ret)
		return ERR_PTR(-ENOSPC);
	/*
	 * Race with unmap: TLB invalidations will start targeting the new ASID,
	 * which isn't assigned yet. We'll do an invalidate-all on the old ASID
	 * later, so it doesn't matter.
	 */
	cd->asid = new_asid;
	/*
	 * Update ASID and invalidate CD in all associated masters. There will
	 * be some overlap between use of both ASIDs, until we invalidate the
	 * TLB.
	 */
	arm_smmu_write_ctx_desc(smmu_domain, 0, cd);

	/* Invalidate TLB entries previously associated with that context */
	arm_smmu_tlb_inv_asid(smmu, asid);

	xa_erase(&arm_smmu_asid_xa, asid);
	return NULL;
}

static struct arm_smmu_ctx_desc *arm_smmu_alloc_shared_cd(struct mm_struct *mm)
{
	u16 asid;
	int err = 0;
	u64 tcr, par, reg;
	struct arm_smmu_ctx_desc *cd;
	struct arm_smmu_ctx_desc *ret = NULL;

	/* Don't free the mm until we release the ASID */
	mmgrab(mm);

	asid = arm64_mm_context_get(mm);
	if (!asid) {
		err = -ESRCH;
		goto out_drop_mm;
	}

	cd = kzalloc(sizeof(*cd), GFP_KERNEL);
	if (!cd) {
		err = -ENOMEM;
		goto out_put_context;
	}

	refcount_set(&cd->refs, 1);

	mutex_lock(&arm_smmu_asid_lock);
	ret = arm_smmu_share_asid(mm, asid);
	if (ret) {
		mutex_unlock(&arm_smmu_asid_lock);
		goto out_free_cd;
	}

	err = xa_insert(&arm_smmu_asid_xa, asid, cd, GFP_KERNEL);
	mutex_unlock(&arm_smmu_asid_lock);

	if (err)
		goto out_free_asid;

	tcr = FIELD_PREP(CTXDESC_CD_0_TCR_T0SZ, 64ULL - vabits_actual) |
	      FIELD_PREP(CTXDESC_CD_0_TCR_IRGN0, ARM_LPAE_TCR_RGN_WBWA) |
	      FIELD_PREP(CTXDESC_CD_0_TCR_ORGN0, ARM_LPAE_TCR_RGN_WBWA) |
	      FIELD_PREP(CTXDESC_CD_0_TCR_SH0, ARM_LPAE_TCR_SH_IS) |
	      CTXDESC_CD_0_TCR_EPD1 | CTXDESC_CD_0_AA64;

	switch (PAGE_SIZE) {
	case SZ_4K:
		tcr |= FIELD_PREP(CTXDESC_CD_0_TCR_TG0, ARM_LPAE_TCR_TG0_4K);
		break;
	case SZ_16K:
		tcr |= FIELD_PREP(CTXDESC_CD_0_TCR_TG0, ARM_LPAE_TCR_TG0_16K);
		break;
	case SZ_64K:
		tcr |= FIELD_PREP(CTXDESC_CD_0_TCR_TG0, ARM_LPAE_TCR_TG0_64K);
		break;
	default:
		WARN_ON(1);
		err = -EINVAL;
		goto out_free_asid;
	}

	reg = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
	par = cpuid_feature_extract_unsigned_field(reg, ID_AA64MMFR0_EL1_PARANGE_SHIFT);
	tcr |= FIELD_PREP(CTXDESC_CD_0_TCR_IPS, par);

	cd->ttbr = virt_to_phys(mm->pgd);
	cd->tcr = tcr;
	/*
	 * MAIR value is pretty much constant and global, so we can just get it
	 * from the current CPU register
	 */
	cd->mair = read_sysreg(mair_el1);
	cd->asid = asid;
	cd->mm = mm;

	return cd;

out_free_asid:
	arm_smmu_free_asid(cd);
out_free_cd:
	kfree(cd);
out_put_context:
	arm64_mm_context_put(mm);
out_drop_mm:
	mmdrop(mm);
	return err < 0 ? ERR_PTR(err) : ret;
}

static void arm_smmu_free_shared_cd(struct arm_smmu_ctx_desc *cd)
{
	if (arm_smmu_free_asid(cd)) {
		/* Unpin ASID */
		arm64_mm_context_put(cd->mm);
		mmdrop(cd->mm);
		kfree(cd);
	}
}

static void arm_smmu_mm_invalidate_range(struct mmu_notifier *mn,
					 struct mm_struct *mm,
					 unsigned long start, unsigned long end)
{
	struct arm_smmu_mmu_notifier *smmu_mn = mn_to_smmu(mn);
	struct arm_smmu_domain *smmu_domain = smmu_mn->domain;
	size_t size;

	/*
	 * The mm_types defines vm_end as the first byte after the end address,
	 * different from IOMMU subsystem using the last address of an address
	 * range. So do a simple translation here by calculating size correctly.
	 */
	size = end - start;

	if (!(smmu_domain->smmu->features & ARM_SMMU_FEAT_BTM))
		arm_smmu_tlb_inv_range_asid(start, size, smmu_mn->cd->asid,
					    PAGE_SIZE, false, smmu_domain);
	arm_smmu_atc_inv_domain(smmu_domain, mm->pasid, start, size);
}

static void arm_smmu_mm_release(struct mmu_notifier *mn, struct mm_struct *mm)
{
	struct arm_smmu_mmu_notifier *smmu_mn = mn_to_smmu(mn);
	struct arm_smmu_domain *smmu_domain = smmu_mn->domain;

	mutex_lock(&sva_lock);
	if (smmu_mn->cleared) {
		mutex_unlock(&sva_lock);
		return;
	}

	/*
	 * DMA may still be running. Keep the cd valid to avoid C_BAD_CD events,
	 * but disable translation.
	 */
	arm_smmu_write_ctx_desc(smmu_domain, mm->pasid, &quiet_cd);

	arm_smmu_tlb_inv_asid(smmu_domain->smmu, smmu_mn->cd->asid);
	arm_smmu_atc_inv_domain(smmu_domain, mm->pasid, 0, 0);

	smmu_mn->cleared = true;
	mutex_unlock(&sva_lock);
}

static void arm_smmu_mmu_notifier_free(struct mmu_notifier *mn)
{
	kfree(mn_to_smmu(mn));
}

static const struct mmu_notifier_ops arm_smmu_mmu_notifier_ops = {
	.invalidate_range	= arm_smmu_mm_invalidate_range,
	.release		= arm_smmu_mm_release,
	.free_notifier		= arm_smmu_mmu_notifier_free,
};

/* Allocate or get existing MMU notifier for this {domain, mm} pair */
static struct arm_smmu_mmu_notifier *
arm_smmu_mmu_notifier_get(struct arm_smmu_domain *smmu_domain,
			  struct mm_struct *mm)
{
	int ret;
	struct arm_smmu_ctx_desc *cd;
	struct arm_smmu_mmu_notifier *smmu_mn;

	list_for_each_entry(smmu_mn, &smmu_domain->mmu_notifiers, list) {
		if (smmu_mn->mn.mm == mm) {
			refcount_inc(&smmu_mn->refs);
			return smmu_mn;
		}
	}

	cd = arm_smmu_alloc_shared_cd(mm);
	if (IS_ERR(cd))
		return ERR_CAST(cd);

	smmu_mn = kzalloc(sizeof(*smmu_mn), GFP_KERNEL);
	if (!smmu_mn) {
		ret = -ENOMEM;
		goto err_free_cd;
	}

	refcount_set(&smmu_mn->refs, 1);
	smmu_mn->cd = cd;
	smmu_mn->domain = smmu_domain;
	smmu_mn->mn.ops = &arm_smmu_mmu_notifier_ops;

	ret = mmu_notifier_register(&smmu_mn->mn, mm);
	if (ret) {
		kfree(smmu_mn);
		goto err_free_cd;
	}

	ret = arm_smmu_write_ctx_desc(smmu_domain, mm->pasid, cd);
	if (ret)
		goto err_put_notifier;

	list_add(&smmu_mn->list, &smmu_domain->mmu_notifiers);
	return smmu_mn;

err_put_notifier:
	/* Frees smmu_mn */
	mmu_notifier_put(&smmu_mn->mn);
err_free_cd:
	arm_smmu_free_shared_cd(cd);
	return ERR_PTR(ret);
}

static void arm_smmu_mmu_notifier_put(struct arm_smmu_mmu_notifier *smmu_mn)
{
	struct mm_struct *mm = smmu_mn->mn.mm;
	struct arm_smmu_ctx_desc *cd = smmu_mn->cd;
	struct arm_smmu_domain *smmu_domain = smmu_mn->domain;

	if (!refcount_dec_and_test(&smmu_mn->refs))
		return;

	list_del(&smmu_mn->list);
	arm_smmu_write_ctx_desc(smmu_domain, mm->pasid, NULL);

	/*
	 * If we went through clear(), we've already invalidated, and no
	 * new TLB entry can have been formed.
	 */
	if (!smmu_mn->cleared) {
		arm_smmu_tlb_inv_asid(smmu_domain->smmu, cd->asid);
		arm_smmu_atc_inv_domain(smmu_domain, mm->pasid, 0, 0);
	}

	/* Frees smmu_mn */
	mmu_notifier_put(&smmu_mn->mn);
	arm_smmu_free_shared_cd(cd);
}

static struct iommu_sva *
__arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm)
{
	int ret;
	struct arm_smmu_bond *bond;
	struct arm_smmu_master *master = dev_iommu_priv_get(dev);
	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);

	if (!master || !master->sva_enabled)
		return ERR_PTR(-ENODEV);

	/* If bind() was already called for this {dev, mm} pair, reuse it. */
	list_for_each_entry(bond, &master->bonds, list) {
		if (bond->mm == mm) {
			refcount_inc(&bond->refs);
			return &bond->sva;
		}
	}

	bond = kzalloc(sizeof(*bond), GFP_KERNEL);
	if (!bond)
		return ERR_PTR(-ENOMEM);

	/* Allocate a PASID for this mm if necessary */
	ret = iommu_sva_alloc_pasid(mm, 1, (1U << master->ssid_bits) - 1);
	if (ret)
		goto err_free_bond;

	bond->mm = mm;
	bond->sva.dev = dev;
	refcount_set(&bond->refs, 1);

	bond->smmu_mn = arm_smmu_mmu_notifier_get(smmu_domain, mm);
	if (IS_ERR(bond->smmu_mn)) {
		ret = PTR_ERR(bond->smmu_mn);
		goto err_free_bond;
	}

	list_add(&bond->list, &master->bonds);
	return &bond->sva;

err_free_bond:
	kfree(bond);
	return ERR_PTR(ret);
}

struct iommu_sva *
arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm, void *drvdata)
{
	struct iommu_sva *handle;
	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);

	if (smmu_domain->stage != ARM_SMMU_DOMAIN_S1)
		return ERR_PTR(-EINVAL);

	mutex_lock(&sva_lock);
	handle = __arm_smmu_sva_bind(dev, mm);
	mutex_unlock(&sva_lock);
	return handle;
}

void arm_smmu_sva_unbind(struct iommu_sva *handle)
{
	struct arm_smmu_bond *bond = sva_to_bond(handle);

	mutex_lock(&sva_lock);
	if (refcount_dec_and_test(&bond->refs)) {
		list_del(&bond->list);
		arm_smmu_mmu_notifier_put(bond->smmu_mn);
		kfree(bond);
	}
	mutex_unlock(&sva_lock);
}

u32 arm_smmu_sva_get_pasid(struct iommu_sva *handle)
{
	struct arm_smmu_bond *bond = sva_to_bond(handle);

	return bond->mm->pasid;
}

bool arm_smmu_sva_supported(struct arm_smmu_device *smmu)
{
	unsigned long reg, fld;
	unsigned long oas;
	unsigned long asid_bits;
	u32 feat_mask = ARM_SMMU_FEAT_COHERENCY;

	if (vabits_actual == 52)
		feat_mask |= ARM_SMMU_FEAT_VAX;

	if ((smmu->features & feat_mask) != feat_mask)
		return false;

	if (!(smmu->pgsize_bitmap & PAGE_SIZE))
		return false;

	/*
	 * Get the smallest PA size of all CPUs (sanitized by cpufeature). We're
	 * not even pretending to support AArch32 here. Abort if the MMU outputs
	 * addresses larger than what we support.
	 */
	reg = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
	fld = cpuid_feature_extract_unsigned_field(reg, ID_AA64MMFR0_EL1_PARANGE_SHIFT);
	oas = id_aa64mmfr0_parange_to_phys_shift(fld);
	if (smmu->oas < oas)
		return false;

	/* We can support bigger ASIDs than the CPU, but not smaller */
	fld = cpuid_feature_extract_unsigned_field(reg, ID_AA64MMFR0_EL1_ASIDBITS_SHIFT);
	asid_bits = fld ? 16 : 8;
	if (smmu->asid_bits < asid_bits)
		return false;

	/*
	 * See max_pinned_asids in arch/arm64/mm/context.c. The following is
	 * generally the maximum number of bindable processes.
	 */
	if (arm64_kernel_unmapped_at_el0())
		asid_bits--;
	dev_dbg(smmu->dev, "%d shared contexts\n", (1 << asid_bits) -
		num_possible_cpus() - 2);

	return true;
}

bool arm_smmu_master_iopf_supported(struct arm_smmu_master *master)
{
	/* We're not keeping track of SIDs in fault events */
	if (master->num_streams != 1)
		return false;

	return master->stall_enabled;
}

bool arm_smmu_master_sva_supported(struct arm_smmu_master *master)
{
	if (!(master->smmu->features & ARM_SMMU_FEAT_SVA))
		return false;

	/* SSID support is mandatory for the moment */
	return master->ssid_bits;
}

bool arm_smmu_master_sva_enabled(struct arm_smmu_master *master)
{
	bool enabled;

	mutex_lock(&sva_lock);
	enabled = master->sva_enabled;
	mutex_unlock(&sva_lock);
	return enabled;
}

static int arm_smmu_master_sva_enable_iopf(struct arm_smmu_master *master)
{
	int ret;
	struct device *dev = master->dev;

	/*
	 * Drivers for devices supporting PRI or stall should enable IOPF first.
	 * Others have device-specific fault handlers and don't need IOPF.
	 */
	if (!arm_smmu_master_iopf_supported(master))
		return 0;

	if (!master->iopf_enabled)
		return -EINVAL;

	ret = iopf_queue_add_device(master->smmu->evtq.iopf, dev);
	if (ret)
		return ret;

	ret = iommu_register_device_fault_handler(dev, iommu_queue_iopf, dev);
	if (ret) {
		iopf_queue_remove_device(master->smmu->evtq.iopf, dev);
		return ret;
	}
	return 0;
}

static void arm_smmu_master_sva_disable_iopf(struct arm_smmu_master *master)
{
	struct device *dev = master->dev;

	if (!master->iopf_enabled)
		return;

	iommu_unregister_device_fault_handler(dev);
	iopf_queue_remove_device(master->smmu->evtq.iopf, dev);
}

int arm_smmu_master_enable_sva(struct arm_smmu_master *master)
{
	int ret;

	mutex_lock(&sva_lock);
	ret = arm_smmu_master_sva_enable_iopf(master);
	if (!ret)
		master->sva_enabled = true;
	mutex_unlock(&sva_lock);

	return ret;
}

int arm_smmu_master_disable_sva(struct arm_smmu_master *master)
{
	mutex_lock(&sva_lock);
	if (!list_empty(&master->bonds)) {
		dev_err(master->dev, "cannot disable SVA, device is bound\n");
		mutex_unlock(&sva_lock);
		return -EBUSY;
	}
	arm_smmu_master_sva_disable_iopf(master);
	master->sva_enabled = false;
	mutex_unlock(&sva_lock);

	return 0;
}

void arm_smmu_sva_notifier_synchronize(void)
{
	/*
	 * Some MMU notifiers may still be waiting to be freed, using
	 * arm_smmu_mmu_notifier_free(). Wait for them.
	 */
	mmu_notifier_synchronize();
}