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
|
// SPDX-License-Identifier: GPL-2.0
/* Copyright 2019 Linaro, Ltd, Rob Herring <robh@kernel.org> */
#include <linux/atomic.h>
#include <linux/bitfield.h>
#include <linux/delay.h>
#include <linux/dma-mapping.h>
#include <linux/interrupt.h>
#include <linux/io.h>
#include <linux/iopoll.h>
#include <linux/io-pgtable.h>
#include <linux/iommu.h>
#include <linux/platform_device.h>
#include <linux/pm_runtime.h>
#include <linux/shmem_fs.h>
#include <linux/sizes.h>
#include "panfrost_device.h"
#include "panfrost_mmu.h"
#include "panfrost_gem.h"
#include "panfrost_features.h"
#include "panfrost_regs.h"
#define mmu_write(dev, reg, data) writel(data, dev->iomem + reg)
#define mmu_read(dev, reg) readl(dev->iomem + reg)
static int wait_ready(struct panfrost_device *pfdev, u32 as_nr)
{
int ret;
u32 val;
/* Wait for the MMU status to indicate there is no active command, in
* case one is pending. */
ret = readl_relaxed_poll_timeout_atomic(pfdev->iomem + AS_STATUS(as_nr),
val, !(val & AS_STATUS_AS_ACTIVE), 10, 1000);
if (ret)
dev_err(pfdev->dev, "AS_ACTIVE bit stuck\n");
return ret;
}
static int write_cmd(struct panfrost_device *pfdev, u32 as_nr, u32 cmd)
{
int status;
/* write AS_COMMAND when MMU is ready to accept another command */
status = wait_ready(pfdev, as_nr);
if (!status)
mmu_write(pfdev, AS_COMMAND(as_nr), cmd);
return status;
}
static void lock_region(struct panfrost_device *pfdev, u32 as_nr,
u64 iova, size_t size)
{
u8 region_width;
u64 region = iova & PAGE_MASK;
/*
* fls returns:
* 1 .. 32
*
* 10 + fls(num_pages)
* results in the range (11 .. 42)
*/
size = round_up(size, PAGE_SIZE);
region_width = 10 + fls(size >> PAGE_SHIFT);
if ((size >> PAGE_SHIFT) != (1ul << (region_width - 11))) {
/* not pow2, so must go up to the next pow2 */
region_width += 1;
}
region |= region_width;
/* Lock the region that needs to be updated */
mmu_write(pfdev, AS_LOCKADDR_LO(as_nr), region & 0xFFFFFFFFUL);
mmu_write(pfdev, AS_LOCKADDR_HI(as_nr), (region >> 32) & 0xFFFFFFFFUL);
write_cmd(pfdev, as_nr, AS_COMMAND_LOCK);
}
static int mmu_hw_do_operation_locked(struct panfrost_device *pfdev, int as_nr,
u64 iova, size_t size, u32 op)
{
if (as_nr < 0)
return 0;
if (op != AS_COMMAND_UNLOCK)
lock_region(pfdev, as_nr, iova, size);
/* Run the MMU operation */
write_cmd(pfdev, as_nr, op);
/* Wait for the flush to complete */
return wait_ready(pfdev, as_nr);
}
static int mmu_hw_do_operation(struct panfrost_device *pfdev,
struct panfrost_mmu *mmu,
u64 iova, size_t size, u32 op)
{
int ret;
spin_lock(&pfdev->as_lock);
ret = mmu_hw_do_operation_locked(pfdev, mmu->as, iova, size, op);
spin_unlock(&pfdev->as_lock);
return ret;
}
static void panfrost_mmu_enable(struct panfrost_device *pfdev, struct panfrost_mmu *mmu)
{
int as_nr = mmu->as;
struct io_pgtable_cfg *cfg = &mmu->pgtbl_cfg;
u64 transtab = cfg->arm_mali_lpae_cfg.transtab;
u64 memattr = cfg->arm_mali_lpae_cfg.memattr;
mmu_hw_do_operation_locked(pfdev, as_nr, 0, ~0UL, AS_COMMAND_FLUSH_MEM);
mmu_write(pfdev, AS_TRANSTAB_LO(as_nr), transtab & 0xffffffffUL);
mmu_write(pfdev, AS_TRANSTAB_HI(as_nr), transtab >> 32);
/* Need to revisit mem attrs.
* NC is the default, Mali driver is inner WT.
*/
mmu_write(pfdev, AS_MEMATTR_LO(as_nr), memattr & 0xffffffffUL);
mmu_write(pfdev, AS_MEMATTR_HI(as_nr), memattr >> 32);
write_cmd(pfdev, as_nr, AS_COMMAND_UPDATE);
}
static void panfrost_mmu_disable(struct panfrost_device *pfdev, u32 as_nr)
{
mmu_hw_do_operation_locked(pfdev, as_nr, 0, ~0UL, AS_COMMAND_FLUSH_MEM);
mmu_write(pfdev, AS_TRANSTAB_LO(as_nr), 0);
mmu_write(pfdev, AS_TRANSTAB_HI(as_nr), 0);
mmu_write(pfdev, AS_MEMATTR_LO(as_nr), 0);
mmu_write(pfdev, AS_MEMATTR_HI(as_nr), 0);
write_cmd(pfdev, as_nr, AS_COMMAND_UPDATE);
}
u32 panfrost_mmu_as_get(struct panfrost_device *pfdev, struct panfrost_mmu *mmu)
{
int as;
spin_lock(&pfdev->as_lock);
as = mmu->as;
if (as >= 0) {
int en = atomic_inc_return(&mmu->as_count);
WARN_ON(en >= NUM_JOB_SLOTS);
list_move(&mmu->list, &pfdev->as_lru_list);
goto out;
}
/* Check for a free AS */
as = ffz(pfdev->as_alloc_mask);
if (!(BIT(as) & pfdev->features.as_present)) {
struct panfrost_mmu *lru_mmu;
list_for_each_entry_reverse(lru_mmu, &pfdev->as_lru_list, list) {
if (!atomic_read(&lru_mmu->as_count))
break;
}
WARN_ON(&lru_mmu->list == &pfdev->as_lru_list);
list_del_init(&lru_mmu->list);
as = lru_mmu->as;
WARN_ON(as < 0);
lru_mmu->as = -1;
}
/* Assign the free or reclaimed AS to the FD */
mmu->as = as;
set_bit(as, &pfdev->as_alloc_mask);
atomic_set(&mmu->as_count, 1);
list_add(&mmu->list, &pfdev->as_lru_list);
dev_dbg(pfdev->dev, "Assigned AS%d to mmu %p, alloc_mask=%lx", as, mmu, pfdev->as_alloc_mask);
panfrost_mmu_enable(pfdev, mmu);
out:
spin_unlock(&pfdev->as_lock);
return as;
}
void panfrost_mmu_as_put(struct panfrost_device *pfdev, struct panfrost_mmu *mmu)
{
atomic_dec(&mmu->as_count);
WARN_ON(atomic_read(&mmu->as_count) < 0);
}
void panfrost_mmu_reset(struct panfrost_device *pfdev)
{
struct panfrost_mmu *mmu, *mmu_tmp;
spin_lock(&pfdev->as_lock);
pfdev->as_alloc_mask = 0;
list_for_each_entry_safe(mmu, mmu_tmp, &pfdev->as_lru_list, list) {
mmu->as = -1;
atomic_set(&mmu->as_count, 0);
list_del_init(&mmu->list);
}
spin_unlock(&pfdev->as_lock);
mmu_write(pfdev, MMU_INT_CLEAR, ~0);
mmu_write(pfdev, MMU_INT_MASK, ~0);
}
static size_t get_pgsize(u64 addr, size_t size)
{
if (addr & (SZ_2M - 1) || size < SZ_2M)
return SZ_4K;
return SZ_2M;
}
void panfrost_mmu_flush_range(struct panfrost_device *pfdev,
struct panfrost_mmu *mmu,
u64 iova, size_t size)
{
if (mmu->as < 0)
return;
pm_runtime_get_noresume(pfdev->dev);
/* Flush the PTs only if we're already awake */
if (pm_runtime_active(pfdev->dev))
mmu_hw_do_operation(pfdev, mmu, iova, size, AS_COMMAND_FLUSH_PT);
pm_runtime_put_sync_autosuspend(pfdev->dev);
}
static int mmu_map_sg(struct panfrost_device *pfdev, struct panfrost_mmu *mmu,
u64 iova, int prot, struct sg_table *sgt)
{
unsigned int count;
struct scatterlist *sgl;
struct io_pgtable_ops *ops = mmu->pgtbl_ops;
u64 start_iova = iova;
for_each_sg(sgt->sgl, sgl, sgt->nents, count) {
unsigned long paddr = sg_dma_address(sgl);
size_t len = sg_dma_len(sgl);
dev_dbg(pfdev->dev, "map: as=%d, iova=%llx, paddr=%lx, len=%zx", mmu->as, iova, paddr, len);
while (len) {
size_t pgsize = get_pgsize(iova | paddr, len);
ops->map(ops, iova, paddr, pgsize, prot);
iova += pgsize;
paddr += pgsize;
len -= pgsize;
}
}
panfrost_mmu_flush_range(pfdev, mmu, start_iova, iova - start_iova);
return 0;
}
int panfrost_mmu_map(struct panfrost_gem_object *bo)
{
struct drm_gem_object *obj = &bo->base.base;
struct panfrost_device *pfdev = to_panfrost_device(obj->dev);
struct sg_table *sgt;
int prot = IOMMU_READ | IOMMU_WRITE;
if (WARN_ON(bo->is_mapped))
return 0;
if (bo->noexec)
prot |= IOMMU_NOEXEC;
sgt = drm_gem_shmem_get_pages_sgt(obj);
if (WARN_ON(IS_ERR(sgt)))
return PTR_ERR(sgt);
mmu_map_sg(pfdev, bo->mmu, bo->node.start << PAGE_SHIFT, prot, sgt);
bo->is_mapped = true;
return 0;
}
void panfrost_mmu_unmap(struct panfrost_gem_object *bo)
{
struct drm_gem_object *obj = &bo->base.base;
struct panfrost_device *pfdev = to_panfrost_device(obj->dev);
struct io_pgtable_ops *ops = bo->mmu->pgtbl_ops;
u64 iova = bo->node.start << PAGE_SHIFT;
size_t len = bo->node.size << PAGE_SHIFT;
size_t unmapped_len = 0;
if (WARN_ON(!bo->is_mapped))
return;
dev_dbg(pfdev->dev, "unmap: as=%d, iova=%llx, len=%zx", bo->mmu->as, iova, len);
while (unmapped_len < len) {
size_t unmapped_page;
size_t pgsize = get_pgsize(iova, len - unmapped_len);
if (ops->iova_to_phys(ops, iova)) {
unmapped_page = ops->unmap(ops, iova, pgsize, NULL);
WARN_ON(unmapped_page != pgsize);
}
iova += pgsize;
unmapped_len += pgsize;
}
panfrost_mmu_flush_range(pfdev, bo->mmu, bo->node.start << PAGE_SHIFT, len);
bo->is_mapped = false;
}
static void mmu_tlb_inv_context_s1(void *cookie)
{}
static void mmu_tlb_sync_context(void *cookie)
{
//struct panfrost_device *pfdev = cookie;
// TODO: Wait 1000 GPU cycles for HW_ISSUE_6367/T60X
}
static void mmu_tlb_flush_walk(unsigned long iova, size_t size, size_t granule,
void *cookie)
{
mmu_tlb_sync_context(cookie);
}
static void mmu_tlb_flush_leaf(unsigned long iova, size_t size, size_t granule,
void *cookie)
{
mmu_tlb_sync_context(cookie);
}
static const struct iommu_flush_ops mmu_tlb_ops = {
.tlb_flush_all = mmu_tlb_inv_context_s1,
.tlb_flush_walk = mmu_tlb_flush_walk,
.tlb_flush_leaf = mmu_tlb_flush_leaf,
};
int panfrost_mmu_pgtable_alloc(struct panfrost_file_priv *priv)
{
struct panfrost_mmu *mmu = &priv->mmu;
struct panfrost_device *pfdev = priv->pfdev;
INIT_LIST_HEAD(&mmu->list);
mmu->as = -1;
mmu->pgtbl_cfg = (struct io_pgtable_cfg) {
.pgsize_bitmap = SZ_4K | SZ_2M,
.ias = FIELD_GET(0xff, pfdev->features.mmu_features),
.oas = FIELD_GET(0xff00, pfdev->features.mmu_features),
.tlb = &mmu_tlb_ops,
.iommu_dev = pfdev->dev,
};
mmu->pgtbl_ops = alloc_io_pgtable_ops(ARM_MALI_LPAE, &mmu->pgtbl_cfg,
priv);
if (!mmu->pgtbl_ops)
return -EINVAL;
return 0;
}
void panfrost_mmu_pgtable_free(struct panfrost_file_priv *priv)
{
struct panfrost_device *pfdev = priv->pfdev;
struct panfrost_mmu *mmu = &priv->mmu;
spin_lock(&pfdev->as_lock);
if (mmu->as >= 0) {
pm_runtime_get_noresume(pfdev->dev);
if (pm_runtime_active(pfdev->dev))
panfrost_mmu_disable(pfdev, mmu->as);
pm_runtime_put_autosuspend(pfdev->dev);
clear_bit(mmu->as, &pfdev->as_alloc_mask);
clear_bit(mmu->as, &pfdev->as_in_use_mask);
list_del(&mmu->list);
}
spin_unlock(&pfdev->as_lock);
free_io_pgtable_ops(mmu->pgtbl_ops);
}
static struct panfrost_gem_object *
addr_to_drm_mm_node(struct panfrost_device *pfdev, int as, u64 addr)
{
struct panfrost_gem_object *bo = NULL;
struct panfrost_file_priv *priv;
struct drm_mm_node *node;
u64 offset = addr >> PAGE_SHIFT;
struct panfrost_mmu *mmu;
spin_lock(&pfdev->as_lock);
list_for_each_entry(mmu, &pfdev->as_lru_list, list) {
if (as == mmu->as)
break;
}
if (as != mmu->as)
goto out;
priv = container_of(mmu, struct panfrost_file_priv, mmu);
spin_lock(&priv->mm_lock);
drm_mm_for_each_node(node, &priv->mm) {
if (offset >= node->start &&
offset < (node->start + node->size)) {
bo = drm_mm_node_to_panfrost_bo(node);
drm_gem_object_get(&bo->base.base);
break;
}
}
spin_unlock(&priv->mm_lock);
out:
spin_unlock(&pfdev->as_lock);
return bo;
}
#define NUM_FAULT_PAGES (SZ_2M / PAGE_SIZE)
int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as, u64 addr)
{
int ret, i;
struct panfrost_gem_object *bo;
struct address_space *mapping;
pgoff_t page_offset;
struct sg_table *sgt;
struct page **pages;
bo = addr_to_drm_mm_node(pfdev, as, addr);
if (!bo)
return -ENOENT;
if (!bo->is_heap) {
dev_WARN(pfdev->dev, "matching BO is not heap type (GPU VA = %llx)",
bo->node.start << PAGE_SHIFT);
ret = -EINVAL;
goto err_bo;
}
WARN_ON(bo->mmu->as != as);
/* Assume 2MB alignment and size multiple */
addr &= ~((u64)SZ_2M - 1);
page_offset = addr >> PAGE_SHIFT;
page_offset -= bo->node.start;
mutex_lock(&bo->base.pages_lock);
if (!bo->base.pages) {
bo->sgts = kvmalloc_array(bo->base.base.size / SZ_2M,
sizeof(struct sg_table), GFP_KERNEL | __GFP_ZERO);
if (!bo->sgts) {
mutex_unlock(&bo->base.pages_lock);
ret = -ENOMEM;
goto err_bo;
}
pages = kvmalloc_array(bo->base.base.size >> PAGE_SHIFT,
sizeof(struct page *), GFP_KERNEL | __GFP_ZERO);
if (!pages) {
kfree(bo->sgts);
bo->sgts = NULL;
mutex_unlock(&bo->base.pages_lock);
ret = -ENOMEM;
goto err_bo;
}
bo->base.pages = pages;
bo->base.pages_use_count = 1;
} else
pages = bo->base.pages;
mapping = bo->base.base.filp->f_mapping;
mapping_set_unevictable(mapping);
for (i = page_offset; i < page_offset + NUM_FAULT_PAGES; i++) {
pages[i] = shmem_read_mapping_page(mapping, i);
if (IS_ERR(pages[i])) {
mutex_unlock(&bo->base.pages_lock);
ret = PTR_ERR(pages[i]);
goto err_pages;
}
}
mutex_unlock(&bo->base.pages_lock);
sgt = &bo->sgts[page_offset / (SZ_2M / PAGE_SIZE)];
ret = sg_alloc_table_from_pages(sgt, pages + page_offset,
NUM_FAULT_PAGES, 0, SZ_2M, GFP_KERNEL);
if (ret)
goto err_pages;
if (!dma_map_sg(pfdev->dev, sgt->sgl, sgt->nents, DMA_BIDIRECTIONAL)) {
ret = -EINVAL;
goto err_map;
}
mmu_map_sg(pfdev, bo->mmu, addr, IOMMU_WRITE | IOMMU_READ | IOMMU_NOEXEC, sgt);
bo->is_mapped = true;
dev_dbg(pfdev->dev, "mapped page fault @ AS%d %llx", as, addr);
drm_gem_object_put_unlocked(&bo->base.base);
return 0;
err_map:
sg_free_table(sgt);
err_pages:
drm_gem_shmem_put_pages(&bo->base);
err_bo:
drm_gem_object_put_unlocked(&bo->base.base);
return ret;
}
static const char *access_type_name(struct panfrost_device *pfdev,
u32 fault_status)
{
switch (fault_status & AS_FAULTSTATUS_ACCESS_TYPE_MASK) {
case AS_FAULTSTATUS_ACCESS_TYPE_ATOMIC:
if (panfrost_has_hw_feature(pfdev, HW_FEATURE_AARCH64_MMU))
return "ATOMIC";
else
return "UNKNOWN";
case AS_FAULTSTATUS_ACCESS_TYPE_READ:
return "READ";
case AS_FAULTSTATUS_ACCESS_TYPE_WRITE:
return "WRITE";
case AS_FAULTSTATUS_ACCESS_TYPE_EX:
return "EXECUTE";
default:
WARN_ON(1);
return NULL;
}
}
static irqreturn_t panfrost_mmu_irq_handler(int irq, void *data)
{
struct panfrost_device *pfdev = data;
if (!mmu_read(pfdev, MMU_INT_STAT))
return IRQ_NONE;
mmu_write(pfdev, MMU_INT_MASK, 0);
return IRQ_WAKE_THREAD;
}
static irqreturn_t panfrost_mmu_irq_handler_thread(int irq, void *data)
{
struct panfrost_device *pfdev = data;
u32 status = mmu_read(pfdev, MMU_INT_RAWSTAT);
int i, ret;
for (i = 0; status; i++) {
u32 mask = BIT(i) | BIT(i + 16);
u64 addr;
u32 fault_status;
u32 exception_type;
u32 access_type;
u32 source_id;
if (!(status & mask))
continue;
fault_status = mmu_read(pfdev, AS_FAULTSTATUS(i));
addr = mmu_read(pfdev, AS_FAULTADDRESS_LO(i));
addr |= (u64)mmu_read(pfdev, AS_FAULTADDRESS_HI(i)) << 32;
/* decode the fault status */
exception_type = fault_status & 0xFF;
access_type = (fault_status >> 8) & 0x3;
source_id = (fault_status >> 16);
/* Page fault only */
if ((status & mask) == BIT(i)) {
WARN_ON(exception_type < 0xC1 || exception_type > 0xC4);
ret = panfrost_mmu_map_fault_addr(pfdev, i, addr);
if (!ret) {
mmu_write(pfdev, MMU_INT_CLEAR, BIT(i));
status &= ~mask;
continue;
}
}
/* terminal fault, print info about the fault */
dev_err(pfdev->dev,
"Unhandled Page fault in AS%d at VA 0x%016llX\n"
"Reason: %s\n"
"raw fault status: 0x%X\n"
"decoded fault status: %s\n"
"exception type 0x%X: %s\n"
"access type 0x%X: %s\n"
"source id 0x%X\n",
i, addr,
"TODO",
fault_status,
(fault_status & (1 << 10) ? "DECODER FAULT" : "SLAVE FAULT"),
exception_type, panfrost_exception_name(pfdev, exception_type),
access_type, access_type_name(pfdev, fault_status),
source_id);
mmu_write(pfdev, MMU_INT_CLEAR, mask);
status &= ~mask;
}
mmu_write(pfdev, MMU_INT_MASK, ~0);
return IRQ_HANDLED;
};
int panfrost_mmu_init(struct panfrost_device *pfdev)
{
int err, irq;
irq = platform_get_irq_byname(to_platform_device(pfdev->dev), "mmu");
if (irq <= 0)
return -ENODEV;
err = devm_request_threaded_irq(pfdev->dev, irq, panfrost_mmu_irq_handler,
panfrost_mmu_irq_handler_thread,
IRQF_SHARED, "mmu", pfdev);
if (err) {
dev_err(pfdev->dev, "failed to request mmu irq");
return err;
}
return 0;
}
void panfrost_mmu_fini(struct panfrost_device *pfdev)
{
mmu_write(pfdev, MMU_INT_MASK, 0);
}
|