summaryrefslogtreecommitdiffstats
path: root/drivers/vfio/pci/nvgrace-gpu/main.c
blob: a7fd018aa5483681a987d4fa4c95408f32247993 (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
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (c) 2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved
 */

#include <linux/sizes.h>
#include <linux/vfio_pci_core.h>

/*
 * The device memory usable to the workloads running in the VM is cached
 * and showcased as a 64b device BAR (comprising of BAR4 and BAR5 region)
 * to the VM and is represented as usemem.
 * Moreover, the VM GPU device driver needs a non-cacheable region to
 * support the MIG feature. This region is also exposed as a 64b BAR
 * (comprising of BAR2 and BAR3 region) and represented as resmem.
 */
#define RESMEM_REGION_INDEX VFIO_PCI_BAR2_REGION_INDEX
#define USEMEM_REGION_INDEX VFIO_PCI_BAR4_REGION_INDEX

/* Memory size expected as non cached and reserved by the VM driver */
#define RESMEM_SIZE SZ_1G

/* A hardwired and constant ABI value between the GPU FW and VFIO driver. */
#define MEMBLK_SIZE SZ_512M

/*
 * The state of the two device memory region - resmem and usemem - is
 * saved as struct mem_region.
 */
struct mem_region {
	phys_addr_t memphys;    /* Base physical address of the region */
	size_t memlength;       /* Region size */
	size_t bar_size;        /* Reported region BAR size */
	__le64 bar_val;         /* Emulated BAR offset registers */
	union {
		void *memaddr;
		void __iomem *ioaddr;
	};                      /* Base virtual address of the region */
};

struct nvgrace_gpu_pci_core_device {
	struct vfio_pci_core_device core_device;
	/* Cached and usable memory for the VM. */
	struct mem_region usemem;
	/* Non cached memory carved out from the end of device memory */
	struct mem_region resmem;
	/* Lock to control device memory kernel mapping */
	struct mutex remap_lock;
};

static void nvgrace_gpu_init_fake_bar_emu_regs(struct vfio_device *core_vdev)
{
	struct nvgrace_gpu_pci_core_device *nvdev =
		container_of(core_vdev, struct nvgrace_gpu_pci_core_device,
			     core_device.vdev);

	nvdev->resmem.bar_val = 0;
	nvdev->usemem.bar_val = 0;
}

/* Choose the structure corresponding to the fake BAR with a given index. */
static struct mem_region *
nvgrace_gpu_memregion(int index,
		      struct nvgrace_gpu_pci_core_device *nvdev)
{
	if (index == USEMEM_REGION_INDEX)
		return &nvdev->usemem;

	if (index == RESMEM_REGION_INDEX)
		return &nvdev->resmem;

	return NULL;
}

static int nvgrace_gpu_open_device(struct vfio_device *core_vdev)
{
	struct vfio_pci_core_device *vdev =
		container_of(core_vdev, struct vfio_pci_core_device, vdev);
	struct nvgrace_gpu_pci_core_device *nvdev =
		container_of(core_vdev, struct nvgrace_gpu_pci_core_device,
			     core_device.vdev);
	int ret;

	ret = vfio_pci_core_enable(vdev);
	if (ret)
		return ret;

	if (nvdev->usemem.memlength) {
		nvgrace_gpu_init_fake_bar_emu_regs(core_vdev);
		mutex_init(&nvdev->remap_lock);
	}

	vfio_pci_core_finish_enable(vdev);

	return 0;
}

static void nvgrace_gpu_close_device(struct vfio_device *core_vdev)
{
	struct nvgrace_gpu_pci_core_device *nvdev =
		container_of(core_vdev, struct nvgrace_gpu_pci_core_device,
			     core_device.vdev);

	/* Unmap the mapping to the device memory cached region */
	if (nvdev->usemem.memaddr) {
		memunmap(nvdev->usemem.memaddr);
		nvdev->usemem.memaddr = NULL;
	}

	/* Unmap the mapping to the device memory non-cached region */
	if (nvdev->resmem.ioaddr) {
		iounmap(nvdev->resmem.ioaddr);
		nvdev->resmem.ioaddr = NULL;
	}

	mutex_destroy(&nvdev->remap_lock);

	vfio_pci_core_close_device(core_vdev);
}

static int nvgrace_gpu_mmap(struct vfio_device *core_vdev,
			    struct vm_area_struct *vma)
{
	struct nvgrace_gpu_pci_core_device *nvdev =
		container_of(core_vdev, struct nvgrace_gpu_pci_core_device,
			     core_device.vdev);
	struct mem_region *memregion;
	unsigned long start_pfn;
	u64 req_len, pgoff, end;
	unsigned int index;
	int ret = 0;

	index = vma->vm_pgoff >> (VFIO_PCI_OFFSET_SHIFT - PAGE_SHIFT);

	memregion = nvgrace_gpu_memregion(index, nvdev);
	if (!memregion)
		return vfio_pci_core_mmap(core_vdev, vma);

	/*
	 * Request to mmap the BAR. Map to the CPU accessible memory on the
	 * GPU using the memory information gathered from the system ACPI
	 * tables.
	 */
	pgoff = vma->vm_pgoff &
		((1U << (VFIO_PCI_OFFSET_SHIFT - PAGE_SHIFT)) - 1);

	if (check_sub_overflow(vma->vm_end, vma->vm_start, &req_len) ||
	    check_add_overflow(PHYS_PFN(memregion->memphys), pgoff, &start_pfn) ||
	    check_add_overflow(PFN_PHYS(pgoff), req_len, &end))
		return -EOVERFLOW;

	/*
	 * Check that the mapping request does not go beyond available device
	 * memory size
	 */
	if (end > memregion->memlength)
		return -EINVAL;

	/*
	 * The carved out region of the device memory needs the NORMAL_NC
	 * property. Communicate as such to the hypervisor.
	 */
	if (index == RESMEM_REGION_INDEX) {
		/*
		 * The nvgrace-gpu module has no issues with uncontained
		 * failures on NORMAL_NC accesses. VM_ALLOW_ANY_UNCACHED is
		 * set to communicate to the KVM to S2 map as NORMAL_NC.
		 * This opens up guest usage of NORMAL_NC for this mapping.
		 */
		vm_flags_set(vma, VM_ALLOW_ANY_UNCACHED);

		vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
	}

	/*
	 * Perform a PFN map to the memory and back the device BAR by the
	 * GPU memory.
	 *
	 * The available GPU memory size may not be power-of-2 aligned. The
	 * remainder is only backed by vfio_device_ops read/write handlers.
	 *
	 * During device reset, the GPU is safely disconnected to the CPU
	 * and access to the BAR will be immediately returned preventing
	 * machine check.
	 */
	ret = remap_pfn_range(vma, vma->vm_start, start_pfn,
			      req_len, vma->vm_page_prot);
	if (ret)
		return ret;

	vma->vm_pgoff = start_pfn;

	return 0;
}

static long
nvgrace_gpu_ioctl_get_region_info(struct vfio_device *core_vdev,
				  unsigned long arg)
{
	struct nvgrace_gpu_pci_core_device *nvdev =
		container_of(core_vdev, struct nvgrace_gpu_pci_core_device,
			     core_device.vdev);
	unsigned long minsz = offsetofend(struct vfio_region_info, offset);
	struct vfio_info_cap caps = { .buf = NULL, .size = 0 };
	struct vfio_region_info_cap_sparse_mmap *sparse;
	struct vfio_region_info info;
	struct mem_region *memregion;
	u32 size;
	int ret;

	if (copy_from_user(&info, (void __user *)arg, minsz))
		return -EFAULT;

	if (info.argsz < minsz)
		return -EINVAL;

	/*
	 * Request to determine the BAR region information. Send the
	 * GPU memory information.
	 */
	memregion = nvgrace_gpu_memregion(info.index, nvdev);
	if (!memregion)
		return vfio_pci_core_ioctl(core_vdev,
					   VFIO_DEVICE_GET_REGION_INFO, arg);

	size = struct_size(sparse, areas, 1);

	/*
	 * Setup for sparse mapping for the device memory. Only the
	 * available device memory on the hardware is shown as a
	 * mappable region.
	 */
	sparse = kzalloc(size, GFP_KERNEL);
	if (!sparse)
		return -ENOMEM;

	sparse->nr_areas = 1;
	sparse->areas[0].offset = 0;
	sparse->areas[0].size = memregion->memlength;
	sparse->header.id = VFIO_REGION_INFO_CAP_SPARSE_MMAP;
	sparse->header.version = 1;

	ret = vfio_info_add_capability(&caps, &sparse->header, size);
	kfree(sparse);
	if (ret)
		return ret;

	info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index);
	/*
	 * The region memory size may not be power-of-2 aligned.
	 * Given that the memory  as a BAR and may not be
	 * aligned, roundup to the next power-of-2.
	 */
	info.size = memregion->bar_size;
	info.flags = VFIO_REGION_INFO_FLAG_READ |
		     VFIO_REGION_INFO_FLAG_WRITE |
		     VFIO_REGION_INFO_FLAG_MMAP;

	if (caps.size) {
		info.flags |= VFIO_REGION_INFO_FLAG_CAPS;
		if (info.argsz < sizeof(info) + caps.size) {
			info.argsz = sizeof(info) + caps.size;
			info.cap_offset = 0;
		} else {
			vfio_info_cap_shift(&caps, sizeof(info));
			if (copy_to_user((void __user *)arg +
					 sizeof(info), caps.buf,
					 caps.size)) {
				kfree(caps.buf);
				return -EFAULT;
			}
			info.cap_offset = sizeof(info);
		}
		kfree(caps.buf);
	}
	return copy_to_user((void __user *)arg, &info, minsz) ?
			    -EFAULT : 0;
}

static long nvgrace_gpu_ioctl(struct vfio_device *core_vdev,
			      unsigned int cmd, unsigned long arg)
{
	switch (cmd) {
	case VFIO_DEVICE_GET_REGION_INFO:
		return nvgrace_gpu_ioctl_get_region_info(core_vdev, arg);
	case VFIO_DEVICE_IOEVENTFD:
		return -ENOTTY;
	case VFIO_DEVICE_RESET:
		nvgrace_gpu_init_fake_bar_emu_regs(core_vdev);
		fallthrough;
	default:
		return vfio_pci_core_ioctl(core_vdev, cmd, arg);
	}
}

static __le64
nvgrace_gpu_get_read_value(size_t bar_size, u64 flags, __le64 val64)
{
	u64 tmp_val;

	tmp_val = le64_to_cpu(val64);
	tmp_val &= ~(bar_size - 1);
	tmp_val |= flags;

	return cpu_to_le64(tmp_val);
}

/*
 * Both the usable (usemem) and the reserved (resmem) device memory region
 * are exposed as a 64b fake device BARs in the VM. These fake BARs must
 * respond to the accesses on their respective PCI config space offsets.
 *
 * resmem BAR owns PCI_BASE_ADDRESS_2 & PCI_BASE_ADDRESS_3.
 * usemem BAR owns PCI_BASE_ADDRESS_4 & PCI_BASE_ADDRESS_5.
 */
static ssize_t
nvgrace_gpu_read_config_emu(struct vfio_device *core_vdev,
			    char __user *buf, size_t count, loff_t *ppos)
{
	struct nvgrace_gpu_pci_core_device *nvdev =
		container_of(core_vdev, struct nvgrace_gpu_pci_core_device,
			     core_device.vdev);
	u64 pos = *ppos & VFIO_PCI_OFFSET_MASK;
	struct mem_region *memregion = NULL;
	__le64 val64;
	size_t register_offset;
	loff_t copy_offset;
	size_t copy_count;
	int ret;

	ret = vfio_pci_core_read(core_vdev, buf, count, ppos);
	if (ret < 0)
		return ret;

	if (vfio_pci_core_range_intersect_range(pos, count, PCI_BASE_ADDRESS_2,
						sizeof(val64),
						&copy_offset, &copy_count,
						&register_offset))
		memregion = nvgrace_gpu_memregion(RESMEM_REGION_INDEX, nvdev);
	else if (vfio_pci_core_range_intersect_range(pos, count,
						     PCI_BASE_ADDRESS_4,
						     sizeof(val64),
						     &copy_offset, &copy_count,
						     &register_offset))
		memregion = nvgrace_gpu_memregion(USEMEM_REGION_INDEX, nvdev);

	if (memregion) {
		val64 = nvgrace_gpu_get_read_value(memregion->bar_size,
						   PCI_BASE_ADDRESS_MEM_TYPE_64 |
						   PCI_BASE_ADDRESS_MEM_PREFETCH,
						   memregion->bar_val);
		if (copy_to_user(buf + copy_offset,
				 (void *)&val64 + register_offset, copy_count)) {
			/*
			 * The position has been incremented in
			 * vfio_pci_core_read. Reset the offset back to the
			 * starting position.
			 */
			*ppos -= count;
			return -EFAULT;
		}
	}

	return count;
}

static ssize_t
nvgrace_gpu_write_config_emu(struct vfio_device *core_vdev,
			     const char __user *buf, size_t count, loff_t *ppos)
{
	struct nvgrace_gpu_pci_core_device *nvdev =
		container_of(core_vdev, struct nvgrace_gpu_pci_core_device,
			     core_device.vdev);
	u64 pos = *ppos & VFIO_PCI_OFFSET_MASK;
	struct mem_region *memregion = NULL;
	size_t register_offset;
	loff_t copy_offset;
	size_t copy_count;

	if (vfio_pci_core_range_intersect_range(pos, count, PCI_BASE_ADDRESS_2,
						sizeof(u64), &copy_offset,
						&copy_count, &register_offset))
		memregion = nvgrace_gpu_memregion(RESMEM_REGION_INDEX, nvdev);
	else if (vfio_pci_core_range_intersect_range(pos, count, PCI_BASE_ADDRESS_4,
						     sizeof(u64), &copy_offset,
						     &copy_count, &register_offset))
		memregion = nvgrace_gpu_memregion(USEMEM_REGION_INDEX, nvdev);

	if (memregion) {
		if (copy_from_user((void *)&memregion->bar_val + register_offset,
				   buf + copy_offset, copy_count))
			return -EFAULT;
		*ppos += copy_count;
		return copy_count;
	}

	return vfio_pci_core_write(core_vdev, buf, count, ppos);
}

/*
 * Ad hoc map the device memory in the module kernel VA space. Primarily needed
 * as vfio does not require the userspace driver to only perform accesses through
 * mmaps of the vfio-pci BAR regions and such accesses should be supported using
 * vfio_device_ops read/write implementations.
 *
 * The usemem region is cacheable memory and hence is memremaped.
 * The resmem region is non-cached and is mapped using ioremap_wc (NORMAL_NC).
 */
static int
nvgrace_gpu_map_device_mem(int index,
			   struct nvgrace_gpu_pci_core_device *nvdev)
{
	struct mem_region *memregion;
	int ret = 0;

	memregion = nvgrace_gpu_memregion(index, nvdev);
	if (!memregion)
		return -EINVAL;

	mutex_lock(&nvdev->remap_lock);

	if (memregion->memaddr)
		goto unlock;

	if (index == USEMEM_REGION_INDEX)
		memregion->memaddr = memremap(memregion->memphys,
					      memregion->memlength,
					      MEMREMAP_WB);
	else
		memregion->ioaddr = ioremap_wc(memregion->memphys,
					       memregion->memlength);

	if (!memregion->memaddr)
		ret = -ENOMEM;

unlock:
	mutex_unlock(&nvdev->remap_lock);

	return ret;
}

/*
 * Read the data from the device memory (mapped either through ioremap
 * or memremap) into the user buffer.
 */
static int
nvgrace_gpu_map_and_read(struct nvgrace_gpu_pci_core_device *nvdev,
			 char __user *buf, size_t mem_count, loff_t *ppos)
{
	unsigned int index = VFIO_PCI_OFFSET_TO_INDEX(*ppos);
	u64 offset = *ppos & VFIO_PCI_OFFSET_MASK;
	int ret;

	if (!mem_count)
		return 0;

	/*
	 * Handle read on the BAR regions. Map to the target device memory
	 * physical address and copy to the request read buffer.
	 */
	ret = nvgrace_gpu_map_device_mem(index, nvdev);
	if (ret)
		return ret;

	if (index == USEMEM_REGION_INDEX) {
		if (copy_to_user(buf,
				 (u8 *)nvdev->usemem.memaddr + offset,
				 mem_count))
			ret = -EFAULT;
	} else {
		/*
		 * The hardware ensures that the system does not crash when
		 * the device memory is accessed with the memory enable
		 * turned off. It synthesizes ~0 on such read. So there is
		 * no need to check or support the disablement/enablement of
		 * BAR through PCI_COMMAND config space register. Pass
		 * test_mem flag as false.
		 */
		ret = vfio_pci_core_do_io_rw(&nvdev->core_device, false,
					     nvdev->resmem.ioaddr,
					     buf, offset, mem_count,
					     0, 0, false);
	}

	return ret;
}

/*
 * Read count bytes from the device memory at an offset. The actual device
 * memory size (available) may not be a power-of-2. So the driver fakes
 * the size to a power-of-2 (reported) when exposing to a user space driver.
 *
 * Reads starting beyond the reported size generate -EINVAL; reads extending
 * beyond the actual device size is filled with ~0; reads extending beyond
 * the reported size are truncated.
 */
static ssize_t
nvgrace_gpu_read_mem(struct nvgrace_gpu_pci_core_device *nvdev,
		     char __user *buf, size_t count, loff_t *ppos)
{
	u64 offset = *ppos & VFIO_PCI_OFFSET_MASK;
	unsigned int index = VFIO_PCI_OFFSET_TO_INDEX(*ppos);
	struct mem_region *memregion;
	size_t mem_count, i;
	u8 val = 0xFF;
	int ret;

	/* No need to do NULL check as caller does. */
	memregion = nvgrace_gpu_memregion(index, nvdev);

	if (offset >= memregion->bar_size)
		return -EINVAL;

	/* Clip short the read request beyond reported BAR size */
	count = min(count, memregion->bar_size - (size_t)offset);

	/*
	 * Determine how many bytes to be actually read from the device memory.
	 * Read request beyond the actual device memory size is filled with ~0,
	 * while those beyond the actual reported size is skipped.
	 */
	if (offset >= memregion->memlength)
		mem_count = 0;
	else
		mem_count = min(count, memregion->memlength - (size_t)offset);

	ret = nvgrace_gpu_map_and_read(nvdev, buf, mem_count, ppos);
	if (ret)
		return ret;

	/*
	 * Only the device memory present on the hardware is mapped, which may
	 * not be power-of-2 aligned. A read to an offset beyond the device memory
	 * size is filled with ~0.
	 */
	for (i = mem_count; i < count; i++) {
		ret = put_user(val, (unsigned char __user *)(buf + i));
		if (ret)
			return ret;
	}

	*ppos += count;
	return count;
}

static ssize_t
nvgrace_gpu_read(struct vfio_device *core_vdev,
		 char __user *buf, size_t count, loff_t *ppos)
{
	unsigned int index = VFIO_PCI_OFFSET_TO_INDEX(*ppos);
	struct nvgrace_gpu_pci_core_device *nvdev =
		container_of(core_vdev, struct nvgrace_gpu_pci_core_device,
			     core_device.vdev);

	if (nvgrace_gpu_memregion(index, nvdev))
		return nvgrace_gpu_read_mem(nvdev, buf, count, ppos);

	if (index == VFIO_PCI_CONFIG_REGION_INDEX)
		return nvgrace_gpu_read_config_emu(core_vdev, buf, count, ppos);

	return vfio_pci_core_read(core_vdev, buf, count, ppos);
}

/*
 * Write the data to the device memory (mapped either through ioremap
 * or memremap) from the user buffer.
 */
static int
nvgrace_gpu_map_and_write(struct nvgrace_gpu_pci_core_device *nvdev,
			  const char __user *buf, size_t mem_count,
			  loff_t *ppos)
{
	unsigned int index = VFIO_PCI_OFFSET_TO_INDEX(*ppos);
	loff_t pos = *ppos & VFIO_PCI_OFFSET_MASK;
	int ret;

	if (!mem_count)
		return 0;

	ret = nvgrace_gpu_map_device_mem(index, nvdev);
	if (ret)
		return ret;

	if (index == USEMEM_REGION_INDEX) {
		if (copy_from_user((u8 *)nvdev->usemem.memaddr + pos,
				   buf, mem_count))
			return -EFAULT;
	} else {
		/*
		 * The hardware ensures that the system does not crash when
		 * the device memory is accessed with the memory enable
		 * turned off. It drops such writes. So there is no need to
		 * check or support the disablement/enablement of BAR
		 * through PCI_COMMAND config space register. Pass test_mem
		 * flag as false.
		 */
		ret = vfio_pci_core_do_io_rw(&nvdev->core_device, false,
					     nvdev->resmem.ioaddr,
					     (char __user *)buf, pos, mem_count,
					     0, 0, true);
	}

	return ret;
}

/*
 * Write count bytes to the device memory at a given offset. The actual device
 * memory size (available) may not be a power-of-2. So the driver fakes the
 * size to a power-of-2 (reported) when exposing to a user space driver.
 *
 * Writes extending beyond the reported size are truncated; writes starting
 * beyond the reported size generate -EINVAL.
 */
static ssize_t
nvgrace_gpu_write_mem(struct nvgrace_gpu_pci_core_device *nvdev,
		      size_t count, loff_t *ppos, const char __user *buf)
{
	unsigned int index = VFIO_PCI_OFFSET_TO_INDEX(*ppos);
	u64 offset = *ppos & VFIO_PCI_OFFSET_MASK;
	struct mem_region *memregion;
	size_t mem_count;
	int ret = 0;

	/* No need to do NULL check as caller does. */
	memregion = nvgrace_gpu_memregion(index, nvdev);

	if (offset >= memregion->bar_size)
		return -EINVAL;

	/* Clip short the write request beyond reported BAR size */
	count = min(count, memregion->bar_size - (size_t)offset);

	/*
	 * Determine how many bytes to be actually written to the device memory.
	 * Do not write to the offset beyond available size.
	 */
	if (offset >= memregion->memlength)
		goto exitfn;

	/*
	 * Only the device memory present on the hardware is mapped, which may
	 * not be power-of-2 aligned. Drop access outside the available device
	 * memory on the hardware.
	 */
	mem_count = min(count, memregion->memlength - (size_t)offset);

	ret = nvgrace_gpu_map_and_write(nvdev, buf, mem_count, ppos);
	if (ret)
		return ret;

exitfn:
	*ppos += count;
	return count;
}

static ssize_t
nvgrace_gpu_write(struct vfio_device *core_vdev,
		  const char __user *buf, size_t count, loff_t *ppos)
{
	struct nvgrace_gpu_pci_core_device *nvdev =
		container_of(core_vdev, struct nvgrace_gpu_pci_core_device,
			     core_device.vdev);
	unsigned int index = VFIO_PCI_OFFSET_TO_INDEX(*ppos);

	if (nvgrace_gpu_memregion(index, nvdev))
		return nvgrace_gpu_write_mem(nvdev, count, ppos, buf);

	if (index == VFIO_PCI_CONFIG_REGION_INDEX)
		return nvgrace_gpu_write_config_emu(core_vdev, buf, count, ppos);

	return vfio_pci_core_write(core_vdev, buf, count, ppos);
}

static const struct vfio_device_ops nvgrace_gpu_pci_ops = {
	.name		= "nvgrace-gpu-vfio-pci",
	.init		= vfio_pci_core_init_dev,
	.release	= vfio_pci_core_release_dev,
	.open_device	= nvgrace_gpu_open_device,
	.close_device	= nvgrace_gpu_close_device,
	.ioctl		= nvgrace_gpu_ioctl,
	.device_feature	= vfio_pci_core_ioctl_feature,
	.read		= nvgrace_gpu_read,
	.write		= nvgrace_gpu_write,
	.mmap		= nvgrace_gpu_mmap,
	.request	= vfio_pci_core_request,
	.match		= vfio_pci_core_match,
	.bind_iommufd	= vfio_iommufd_physical_bind,
	.unbind_iommufd	= vfio_iommufd_physical_unbind,
	.attach_ioas	= vfio_iommufd_physical_attach_ioas,
	.detach_ioas	= vfio_iommufd_physical_detach_ioas,
};

static const struct vfio_device_ops nvgrace_gpu_pci_core_ops = {
	.name		= "nvgrace-gpu-vfio-pci-core",
	.init		= vfio_pci_core_init_dev,
	.release	= vfio_pci_core_release_dev,
	.open_device	= nvgrace_gpu_open_device,
	.close_device	= vfio_pci_core_close_device,
	.ioctl		= vfio_pci_core_ioctl,
	.device_feature	= vfio_pci_core_ioctl_feature,
	.read		= vfio_pci_core_read,
	.write		= vfio_pci_core_write,
	.mmap		= vfio_pci_core_mmap,
	.request	= vfio_pci_core_request,
	.match		= vfio_pci_core_match,
	.bind_iommufd	= vfio_iommufd_physical_bind,
	.unbind_iommufd	= vfio_iommufd_physical_unbind,
	.attach_ioas	= vfio_iommufd_physical_attach_ioas,
	.detach_ioas	= vfio_iommufd_physical_detach_ioas,
};

static int
nvgrace_gpu_fetch_memory_property(struct pci_dev *pdev,
				  u64 *pmemphys, u64 *pmemlength)
{
	int ret;

	/*
	 * The memory information is present in the system ACPI tables as DSD
	 * properties nvidia,gpu-mem-base-pa and nvidia,gpu-mem-size.
	 */
	ret = device_property_read_u64(&pdev->dev, "nvidia,gpu-mem-base-pa",
				       pmemphys);
	if (ret)
		return ret;

	if (*pmemphys > type_max(phys_addr_t))
		return -EOVERFLOW;

	ret = device_property_read_u64(&pdev->dev, "nvidia,gpu-mem-size",
				       pmemlength);
	if (ret)
		return ret;

	if (*pmemlength > type_max(size_t))
		return -EOVERFLOW;

	/*
	 * If the C2C link is not up due to an error, the coherent device
	 * memory size is returned as 0. Fail in such case.
	 */
	if (*pmemlength == 0)
		return -ENOMEM;

	return ret;
}

static int
nvgrace_gpu_init_nvdev_struct(struct pci_dev *pdev,
			      struct nvgrace_gpu_pci_core_device *nvdev,
			      u64 memphys, u64 memlength)
{
	int ret = 0;

	/*
	 * The VM GPU device driver needs a non-cacheable region to support
	 * the MIG feature. Since the device memory is mapped as NORMAL cached,
	 * carve out a region from the end with a different NORMAL_NC
	 * property (called as reserved memory and represented as resmem). This
	 * region then is exposed as a 64b BAR (region 2 and 3) to the VM, while
	 * exposing the rest (termed as usable memory and represented using usemem)
	 * as cacheable 64b BAR (region 4 and 5).
	 *
	 *               devmem (memlength)
	 * |-------------------------------------------------|
	 * |                                           |
	 * usemem.memphys                              resmem.memphys
	 */
	nvdev->usemem.memphys = memphys;

	/*
	 * The device memory exposed to the VM is added to the kernel by the
	 * VM driver module in chunks of memory block size. Only the usable
	 * memory (usemem) is added to the kernel for usage by the VM
	 * workloads. Make the usable memory size memblock aligned.
	 */
	if (check_sub_overflow(memlength, RESMEM_SIZE,
			       &nvdev->usemem.memlength)) {
		ret = -EOVERFLOW;
		goto done;
	}

	/*
	 * The USEMEM part of the device memory has to be MEMBLK_SIZE
	 * aligned. This is a hardwired ABI value between the GPU FW and
	 * VFIO driver. The VM device driver is also aware of it and make
	 * use of the value for its calculation to determine USEMEM size.
	 */
	nvdev->usemem.memlength = round_down(nvdev->usemem.memlength,
					     MEMBLK_SIZE);
	if (nvdev->usemem.memlength == 0) {
		ret = -EINVAL;
		goto done;
	}

	if ((check_add_overflow(nvdev->usemem.memphys,
				nvdev->usemem.memlength,
				&nvdev->resmem.memphys)) ||
	    (check_sub_overflow(memlength, nvdev->usemem.memlength,
				&nvdev->resmem.memlength))) {
		ret = -EOVERFLOW;
		goto done;
	}

	/*
	 * The memory regions are exposed as BARs. Calculate and save
	 * the BAR size for them.
	 */
	nvdev->usemem.bar_size = roundup_pow_of_two(nvdev->usemem.memlength);
	nvdev->resmem.bar_size = roundup_pow_of_two(nvdev->resmem.memlength);
done:
	return ret;
}

static int nvgrace_gpu_probe(struct pci_dev *pdev,
			     const struct pci_device_id *id)
{
	const struct vfio_device_ops *ops = &nvgrace_gpu_pci_core_ops;
	struct nvgrace_gpu_pci_core_device *nvdev;
	u64 memphys, memlength;
	int ret;

	ret = nvgrace_gpu_fetch_memory_property(pdev, &memphys, &memlength);
	if (!ret)
		ops = &nvgrace_gpu_pci_ops;

	nvdev = vfio_alloc_device(nvgrace_gpu_pci_core_device, core_device.vdev,
				  &pdev->dev, ops);
	if (IS_ERR(nvdev))
		return PTR_ERR(nvdev);

	dev_set_drvdata(&pdev->dev, &nvdev->core_device);

	if (ops == &nvgrace_gpu_pci_ops) {
		/*
		 * Device memory properties are identified in the host ACPI
		 * table. Set the nvgrace_gpu_pci_core_device structure.
		 */
		ret = nvgrace_gpu_init_nvdev_struct(pdev, nvdev,
						    memphys, memlength);
		if (ret)
			goto out_put_vdev;
	}

	ret = vfio_pci_core_register_device(&nvdev->core_device);
	if (ret)
		goto out_put_vdev;

	return ret;

out_put_vdev:
	vfio_put_device(&nvdev->core_device.vdev);
	return ret;
}

static void nvgrace_gpu_remove(struct pci_dev *pdev)
{
	struct vfio_pci_core_device *core_device = dev_get_drvdata(&pdev->dev);

	vfio_pci_core_unregister_device(core_device);
	vfio_put_device(&core_device->vdev);
}

static const struct pci_device_id nvgrace_gpu_vfio_pci_table[] = {
	/* GH200 120GB */
	{ PCI_DRIVER_OVERRIDE_DEVICE_VFIO(PCI_VENDOR_ID_NVIDIA, 0x2342) },
	/* GH200 480GB */
	{ PCI_DRIVER_OVERRIDE_DEVICE_VFIO(PCI_VENDOR_ID_NVIDIA, 0x2345) },
	{}
};

MODULE_DEVICE_TABLE(pci, nvgrace_gpu_vfio_pci_table);

static struct pci_driver nvgrace_gpu_vfio_pci_driver = {
	.name = KBUILD_MODNAME,
	.id_table = nvgrace_gpu_vfio_pci_table,
	.probe = nvgrace_gpu_probe,
	.remove = nvgrace_gpu_remove,
	.err_handler = &vfio_pci_core_err_handlers,
	.driver_managed_dma = true,
};

module_pci_driver(nvgrace_gpu_vfio_pci_driver);

MODULE_LICENSE("GPL");
MODULE_AUTHOR("Ankit Agrawal <ankita@nvidia.com>");
MODULE_AUTHOR("Aniket Agashe <aniketa@nvidia.com>");
MODULE_DESCRIPTION("VFIO NVGRACE GPU PF - User Level driver for NVIDIA devices with CPU coherently accessible device memory");