vfio_pci.c 29.9 KB
Newer Older
Alex Williamson's avatar
Alex Williamson committed
1
2
3
4
5
6
7
8
9
10
11
12
13
/*
 * Copyright (C) 2012 Red Hat, Inc.  All rights reserved.
 *     Author: Alex Williamson <alex.williamson@redhat.com>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 *
 * Derived from original vfio:
 * Copyright 2010 Cisco Systems, Inc.  All rights reserved.
 * Author: Tom Lyon, pugs@cisco.com
 */

14
15
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

Alex Williamson's avatar
Alex Williamson committed
16
17
#include <linux/device.h>
#include <linux/eventfd.h>
18
#include <linux/file.h>
Alex Williamson's avatar
Alex Williamson committed
19
20
21
22
23
24
25
26
27
28
29
#include <linux/interrupt.h>
#include <linux/iommu.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/notifier.h>
#include <linux/pci.h>
#include <linux/pm_runtime.h>
#include <linux/slab.h>
#include <linux/types.h>
#include <linux/uaccess.h>
#include <linux/vfio.h>
30
#include <linux/vgaarb.h>
Alex Williamson's avatar
Alex Williamson committed
31
32
33
34
35
36
37

#include "vfio_pci_private.h"

#define DRIVER_VERSION  "0.2"
#define DRIVER_AUTHOR   "Alex Williamson <alex.williamson@redhat.com>"
#define DRIVER_DESC     "VFIO PCI - User Level meta-driver"

38
39
40
41
static char ids[1024] __initdata;
module_param_string(ids, ids, sizeof(ids), 0);
MODULE_PARM_DESC(ids, "Initial PCI IDs to add to the vfio driver, format is \"vendor:device[:subvendor[:subdevice[:class[:class_mask]]]]\" and multiple comma separated entries can be specified");

Alex Williamson's avatar
Alex Williamson committed
42
43
44
45
46
static bool nointxmask;
module_param_named(nointxmask, nointxmask, bool, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(nointxmask,
		  "Disable support for PCI 2.3 style INTx masking.  If this resolves problems for specific devices, report lspci -vvvxxx to linux-pci@vger.kernel.org so the device can be fixed automatically via the broken_intx_masking flag.");

47
48
49
50
51
52
#ifdef CONFIG_VFIO_PCI_VGA
static bool disable_vga;
module_param(disable_vga, bool, S_IRUGO);
MODULE_PARM_DESC(disable_vga, "Disable VGA resource access through vfio-pci");
#endif

53
54
55
56
57
static bool disable_idle_d3;
module_param(disable_idle_d3, bool, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(disable_idle_d3,
		 "Disable using the PCI D3 low power state for idle, unused devices");

58
59
static DEFINE_MUTEX(driver_lock);

60
61
62
63
64
65
66
67
68
static inline bool vfio_vga_disabled(void)
{
#ifdef CONFIG_VFIO_PCI_VGA
	return disable_vga;
#else
	return true;
#endif
}

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
/*
 * Our VGA arbiter participation is limited since we don't know anything
 * about the device itself.  However, if the device is the only VGA device
 * downstream of a bridge and VFIO VGA support is disabled, then we can
 * safely return legacy VGA IO and memory as not decoded since the user
 * has no way to get to it and routing can be disabled externally at the
 * bridge.
 */
static unsigned int vfio_pci_set_vga_decode(void *opaque, bool single_vga)
{
	struct vfio_pci_device *vdev = opaque;
	struct pci_dev *tmp = NULL, *pdev = vdev->pdev;
	unsigned char max_busnr;
	unsigned int decodes;

	if (single_vga || !vfio_vga_disabled() || pci_is_root_bus(pdev->bus))
		return VGA_RSRC_NORMAL_IO | VGA_RSRC_NORMAL_MEM |
		       VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM;

	max_busnr = pci_bus_max_busnr(pdev->bus);
	decodes = VGA_RSRC_NORMAL_IO | VGA_RSRC_NORMAL_MEM;

	while ((tmp = pci_get_class(PCI_CLASS_DISPLAY_VGA << 8, tmp)) != NULL) {
		if (tmp == pdev ||
		    pci_domain_nr(tmp->bus) != pci_domain_nr(pdev->bus) ||
		    pci_is_root_bus(tmp->bus))
			continue;

		if (tmp->bus->number >= pdev->bus->number &&
		    tmp->bus->number <= max_busnr) {
			pci_dev_put(tmp);
			decodes |= VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM;
			break;
		}
	}

	return decodes;
}

static inline bool vfio_pci_is_vga(struct pci_dev *pdev)
{
	return (pdev->class >> 8) == PCI_CLASS_DISPLAY_VGA;
}

113
114
static void vfio_pci_try_bus_reset(struct vfio_pci_device *vdev);

Alex Williamson's avatar
Alex Williamson committed
115
116
117
118
119
120
121
static int vfio_pci_enable(struct vfio_pci_device *vdev)
{
	struct pci_dev *pdev = vdev->pdev;
	int ret;
	u16 cmd;
	u8 msix_pos;

122
123
	pci_set_power_state(pdev, PCI_D0);

124
125
126
	/* Don't allow our initial saved state to include busmaster */
	pci_clear_master(pdev);

127
128
129
130
	ret = pci_enable_device(pdev);
	if (ret)
		return ret;

Alex Williamson's avatar
Alex Williamson committed
131
132
133
134
135
136
137
138
	vdev->reset_works = (pci_reset_function(pdev) == 0);
	pci_save_state(pdev);
	vdev->pci_saved_state = pci_store_saved_state(pdev);
	if (!vdev->pci_saved_state)
		pr_debug("%s: Couldn't store %s saved state\n",
			 __func__, dev_name(&pdev->dev));

	ret = vfio_config_init(vdev);
139
	if (ret) {
140
141
		kfree(vdev->pci_saved_state);
		vdev->pci_saved_state = NULL;
142
143
144
		pci_disable_device(pdev);
		return ret;
	}
Alex Williamson's avatar
Alex Williamson committed
145
146
147
148
149
150
151
152
153
154

	if (likely(!nointxmask))
		vdev->pci_2_3 = pci_intx_mask_supported(pdev);

	pci_read_config_word(pdev, PCI_COMMAND, &cmd);
	if (vdev->pci_2_3 && (cmd & PCI_COMMAND_INTX_DISABLE)) {
		cmd &= ~PCI_COMMAND_INTX_DISABLE;
		pci_write_config_word(pdev, PCI_COMMAND, cmd);
	}

155
	msix_pos = pdev->msix_cap;
Alex Williamson's avatar
Alex Williamson committed
156
157
158
159
160
161
162
	if (msix_pos) {
		u16 flags;
		u32 table;

		pci_read_config_word(pdev, msix_pos + PCI_MSIX_FLAGS, &flags);
		pci_read_config_dword(pdev, msix_pos + PCI_MSIX_TABLE, &table);

163
164
		vdev->msix_bar = table & PCI_MSIX_TABLE_BIR;
		vdev->msix_offset = table & PCI_MSIX_TABLE_OFFSET;
Alex Williamson's avatar
Alex Williamson committed
165
166
167
168
		vdev->msix_size = ((flags & PCI_MSIX_FLAGS_QSIZE) + 1) * 16;
	} else
		vdev->msix_bar = 0xFF;

169
	if (!vfio_vga_disabled() && vfio_pci_is_vga(pdev))
170
171
		vdev->has_vga = true;

172
	return 0;
Alex Williamson's avatar
Alex Williamson committed
173
174
175
176
}

static void vfio_pci_disable(struct vfio_pci_device *vdev)
{
177
	struct pci_dev *pdev = vdev->pdev;
Alex Williamson's avatar
Alex Williamson committed
178
179
	int bar;

180
181
	/* Stop the device from further DMA */
	pci_clear_master(pdev);
Alex Williamson's avatar
Alex Williamson committed
182
183
184
185
186
187
188
189
190
191
192
193

	vfio_pci_set_irqs_ioctl(vdev, VFIO_IRQ_SET_DATA_NONE |
				VFIO_IRQ_SET_ACTION_TRIGGER,
				vdev->irq_type, 0, 0, NULL);

	vdev->virq_disabled = false;

	vfio_config_free(vdev);

	for (bar = PCI_STD_RESOURCES; bar <= PCI_STD_RESOURCE_END; bar++) {
		if (!vdev->barmap[bar])
			continue;
194
195
		pci_iounmap(pdev, vdev->barmap[bar]);
		pci_release_selected_regions(pdev, 1 << bar);
Alex Williamson's avatar
Alex Williamson committed
196
197
		vdev->barmap[bar] = NULL;
	}
198

199
200
	vdev->needs_reset = true;

201
202
203
204
205
206
207
208
209
210
211
	/*
	 * If we have saved state, restore it.  If we can reset the device,
	 * even better.  Resetting with current state seems better than
	 * nothing, but saving and restoring current state without reset
	 * is just busy work.
	 */
	if (pci_load_and_free_saved_state(pdev, &vdev->pci_saved_state)) {
		pr_info("%s: Couldn't reload %s saved state\n",
			__func__, dev_name(&pdev->dev));

		if (!vdev->reset_works)
212
			goto out;
213
214
215
216
217
218
219
220
221
222

		pci_save_state(pdev);
	}

	/*
	 * Disable INTx and MSI, presumably to avoid spurious interrupts
	 * during reset.  Stolen from pci_reset_function()
	 */
	pci_write_config_word(pdev, PCI_COMMAND, PCI_COMMAND_INTX_DISABLE);

223
	/*
224
225
	 * Try to reset the device.  The success of this is dependent on
	 * being able to lock the device, which is not always possible.
226
	 */
227
228
	if (vdev->reset_works && !pci_try_reset_function(pdev))
		vdev->needs_reset = false;
229
230

	pci_restore_state(pdev);
231
232
out:
	pci_disable_device(pdev);
233
234

	vfio_pci_try_bus_reset(vdev);
235
236
237

	if (!disable_idle_d3)
		pci_set_power_state(pdev, PCI_D3hot);
Alex Williamson's avatar
Alex Williamson committed
238
239
240
241
242
243
}

static void vfio_pci_release(void *device_data)
{
	struct vfio_pci_device *vdev = device_data;

244
245
246
	mutex_lock(&driver_lock);

	if (!(--vdev->refcnt)) {
247
		vfio_spapr_pci_eeh_release(vdev->pdev);
Alex Williamson's avatar
Alex Williamson committed
248
		vfio_pci_disable(vdev);
249
	}
Alex Williamson's avatar
Alex Williamson committed
250

251
252
	mutex_unlock(&driver_lock);

Alex Williamson's avatar
Alex Williamson committed
253
254
255
256
257
258
	module_put(THIS_MODULE);
}

static int vfio_pci_open(void *device_data)
{
	struct vfio_pci_device *vdev = device_data;
259
	int ret = 0;
Alex Williamson's avatar
Alex Williamson committed
260
261
262
263

	if (!try_module_get(THIS_MODULE))
		return -ENODEV;

264
265
266
	mutex_lock(&driver_lock);

	if (!vdev->refcnt) {
267
268
269
270
		ret = vfio_pci_enable(vdev);
		if (ret)
			goto error;

271
		vfio_spapr_pci_eeh_open(vdev->pdev);
Alex Williamson's avatar
Alex Williamson committed
272
	}
273
	vdev->refcnt++;
274
error:
275
276
277
	mutex_unlock(&driver_lock);
	if (ret)
		module_put(THIS_MODULE);
278
	return ret;
Alex Williamson's avatar
Alex Williamson committed
279
280
281
282
283
284
285
}

static int vfio_pci_get_irq_count(struct vfio_pci_device *vdev, int irq_type)
{
	if (irq_type == VFIO_PCI_INTX_IRQ_INDEX) {
		u8 pin;
		pci_read_config_byte(vdev->pdev, PCI_INTERRUPT_PIN, &pin);
Frank Blaschka's avatar
Frank Blaschka committed
286
		if (IS_ENABLED(CONFIG_VFIO_PCI_INTX) && pin)
Alex Williamson's avatar
Alex Williamson committed
287
288
289
290
291
292
			return 1;

	} else if (irq_type == VFIO_PCI_MSI_IRQ_INDEX) {
		u8 pos;
		u16 flags;

293
		pos = vdev->pdev->msi_cap;
Alex Williamson's avatar
Alex Williamson committed
294
295
296
		if (pos) {
			pci_read_config_word(vdev->pdev,
					     pos + PCI_MSI_FLAGS, &flags);
297
			return 1 << ((flags & PCI_MSI_FLAGS_QMASK) >> 1);
Alex Williamson's avatar
Alex Williamson committed
298
299
300
301
302
		}
	} else if (irq_type == VFIO_PCI_MSIX_IRQ_INDEX) {
		u8 pos;
		u16 flags;

303
		pos = vdev->pdev->msix_cap;
Alex Williamson's avatar
Alex Williamson committed
304
305
306
307
308
309
		if (pos) {
			pci_read_config_word(vdev->pdev,
					     pos + PCI_MSIX_FLAGS, &flags);

			return (flags & PCI_MSIX_FLAGS_QSIZE) + 1;
		}
310
	} else if (irq_type == VFIO_PCI_ERR_IRQ_INDEX) {
311
312
		if (pci_is_pcie(vdev->pdev))
			return 1;
313
314
315
	} else if (irq_type == VFIO_PCI_REQ_IRQ_INDEX) {
		return 1;
	}
Alex Williamson's avatar
Alex Williamson committed
316
317
318
319

	return 0;
}

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
static int vfio_pci_count_devs(struct pci_dev *pdev, void *data)
{
	(*(int *)data)++;
	return 0;
}

struct vfio_pci_fill_info {
	int max;
	int cur;
	struct vfio_pci_dependent_device *devices;
};

static int vfio_pci_fill_devs(struct pci_dev *pdev, void *data)
{
	struct vfio_pci_fill_info *fill = data;
	struct iommu_group *iommu_group;

	if (fill->cur == fill->max)
		return -EAGAIN; /* Something changed, try again */

	iommu_group = iommu_group_get(&pdev->dev);
	if (!iommu_group)
		return -EPERM; /* Cannot reset non-isolated devices */

	fill->devices[fill->cur].group_id = iommu_group_id(iommu_group);
	fill->devices[fill->cur].segment = pci_domain_nr(pdev->bus);
	fill->devices[fill->cur].bus = pdev->bus->number;
	fill->devices[fill->cur].devfn = pdev->devfn;
	fill->cur++;
	iommu_group_put(iommu_group);
	return 0;
}

struct vfio_pci_group_entry {
	struct vfio_group *group;
	int id;
};

struct vfio_pci_group_info {
	int count;
	struct vfio_pci_group_entry *groups;
};

static int vfio_pci_validate_devs(struct pci_dev *pdev, void *data)
{
	struct vfio_pci_group_info *info = data;
	struct iommu_group *group;
	int id, i;

	group = iommu_group_get(&pdev->dev);
	if (!group)
		return -EPERM;

	id = iommu_group_id(group);

	for (i = 0; i < info->count; i++)
		if (info->groups[i].id == id)
			break;

	iommu_group_put(group);

	return (i == info->count) ? -EINVAL : 0;
}

static bool vfio_pci_dev_below_slot(struct pci_dev *pdev, struct pci_slot *slot)
{
	for (; pdev; pdev = pdev->bus->self)
		if (pdev->bus == slot->bus)
			return (pdev->slot == slot);
	return false;
}

struct vfio_pci_walk_info {
	int (*fn)(struct pci_dev *, void *data);
	void *data;
	struct pci_dev *pdev;
	bool slot;
	int ret;
};

static int vfio_pci_walk_wrapper(struct pci_dev *pdev, void *data)
{
	struct vfio_pci_walk_info *walk = data;

	if (!walk->slot || vfio_pci_dev_below_slot(pdev, walk->pdev->slot))
		walk->ret = walk->fn(pdev, walk->data);

	return walk->ret;
}

static int vfio_pci_for_each_slot_or_bus(struct pci_dev *pdev,
					 int (*fn)(struct pci_dev *,
						   void *data), void *data,
					 bool slot)
{
	struct vfio_pci_walk_info walk = {
		.fn = fn, .data = data, .pdev = pdev, .slot = slot, .ret = 0,
	};

	pci_walk_bus(pdev->bus, vfio_pci_walk_wrapper, &walk);

	return walk.ret;
}

Alex Williamson's avatar
Alex Williamson committed
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
static long vfio_pci_ioctl(void *device_data,
			   unsigned int cmd, unsigned long arg)
{
	struct vfio_pci_device *vdev = device_data;
	unsigned long minsz;

	if (cmd == VFIO_DEVICE_GET_INFO) {
		struct vfio_device_info info;

		minsz = offsetofend(struct vfio_device_info, num_irqs);

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

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

		info.flags = VFIO_DEVICE_FLAGS_PCI;

		if (vdev->reset_works)
			info.flags |= VFIO_DEVICE_FLAGS_RESET;

		info.num_regions = VFIO_PCI_NUM_REGIONS;
		info.num_irqs = VFIO_PCI_NUM_IRQS;

		return copy_to_user((void __user *)arg, &info, minsz);

	} else if (cmd == VFIO_DEVICE_GET_REGION_INFO) {
		struct pci_dev *pdev = vdev->pdev;
		struct vfio_region_info info;

		minsz = offsetofend(struct vfio_region_info, offset);

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

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

		switch (info.index) {
		case VFIO_PCI_CONFIG_REGION_INDEX:
			info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index);
			info.size = pdev->cfg_size;
			info.flags = VFIO_REGION_INFO_FLAG_READ |
				     VFIO_REGION_INFO_FLAG_WRITE;
			break;
		case VFIO_PCI_BAR0_REGION_INDEX ... VFIO_PCI_BAR5_REGION_INDEX:
			info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index);
			info.size = pci_resource_len(pdev, info.index);
			if (!info.size) {
				info.flags = 0;
				break;
			}

			info.flags = VFIO_REGION_INFO_FLAG_READ |
				     VFIO_REGION_INFO_FLAG_WRITE;
Frank Blaschka's avatar
Frank Blaschka committed
480
481
			if (IS_ENABLED(CONFIG_VFIO_PCI_MMAP) &&
			    pci_resource_flags(pdev, info.index) &
Alex Williamson's avatar
Alex Williamson committed
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
			    IORESOURCE_MEM && info.size >= PAGE_SIZE)
				info.flags |= VFIO_REGION_INFO_FLAG_MMAP;
			break;
		case VFIO_PCI_ROM_REGION_INDEX:
		{
			void __iomem *io;
			size_t size;

			info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index);
			info.flags = 0;

			/* Report the BAR size, not the ROM size */
			info.size = pci_resource_len(pdev, info.index);
			if (!info.size)
				break;

			/* Is it really there? */
			io = pci_map_rom(pdev, &size);
			if (!io || !size) {
				info.size = 0;
				break;
			}
			pci_unmap_rom(pdev, io);

			info.flags = VFIO_REGION_INFO_FLAG_READ;
			break;
		}
509
510
511
512
513
514
515
516
517
518
		case VFIO_PCI_VGA_REGION_INDEX:
			if (!vdev->has_vga)
				return -EINVAL;

			info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index);
			info.size = 0xc0000;
			info.flags = VFIO_REGION_INFO_FLAG_READ |
				     VFIO_REGION_INFO_FLAG_WRITE;

			break;
Alex Williamson's avatar
Alex Williamson committed
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
		default:
			return -EINVAL;
		}

		return copy_to_user((void __user *)arg, &info, minsz);

	} else if (cmd == VFIO_DEVICE_GET_IRQ_INFO) {
		struct vfio_irq_info info;

		minsz = offsetofend(struct vfio_irq_info, count);

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

		if (info.argsz < minsz || info.index >= VFIO_PCI_NUM_IRQS)
			return -EINVAL;

536
537
		switch (info.index) {
		case VFIO_PCI_INTX_IRQ_INDEX ... VFIO_PCI_MSIX_IRQ_INDEX:
538
		case VFIO_PCI_REQ_IRQ_INDEX:
539
540
541
542
543
544
545
546
547
			break;
		case VFIO_PCI_ERR_IRQ_INDEX:
			if (pci_is_pcie(vdev->pdev))
				break;
		/* pass thru to return error */
		default:
			return -EINVAL;
		}

Alex Williamson's avatar
Alex Williamson committed
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
		info.flags = VFIO_IRQ_INFO_EVENTFD;

		info.count = vfio_pci_get_irq_count(vdev, info.index);

		if (info.index == VFIO_PCI_INTX_IRQ_INDEX)
			info.flags |= (VFIO_IRQ_INFO_MASKABLE |
				       VFIO_IRQ_INFO_AUTOMASKED);
		else
			info.flags |= VFIO_IRQ_INFO_NORESIZE;

		return copy_to_user((void __user *)arg, &info, minsz);

	} else if (cmd == VFIO_DEVICE_SET_IRQS) {
		struct vfio_irq_set hdr;
		u8 *data = NULL;
		int ret = 0;

		minsz = offsetofend(struct vfio_irq_set, count);

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

		if (hdr.argsz < minsz || hdr.index >= VFIO_PCI_NUM_IRQS ||
		    hdr.flags & ~(VFIO_IRQ_SET_DATA_TYPE_MASK |
				  VFIO_IRQ_SET_ACTION_TYPE_MASK))
			return -EINVAL;

		if (!(hdr.flags & VFIO_IRQ_SET_DATA_NONE)) {
			size_t size;
577
			int max = vfio_pci_get_irq_count(vdev, hdr.index);
Alex Williamson's avatar
Alex Williamson committed
578
579
580
581
582
583
584
585
586

			if (hdr.flags & VFIO_IRQ_SET_DATA_BOOL)
				size = sizeof(uint8_t);
			else if (hdr.flags & VFIO_IRQ_SET_DATA_EVENTFD)
				size = sizeof(int32_t);
			else
				return -EINVAL;

			if (hdr.argsz - minsz < hdr.count * size ||
587
			    hdr.start >= max || hdr.start + hdr.count > max)
Alex Williamson's avatar
Alex Williamson committed
588
589
				return -EINVAL;

590
591
592
593
			data = memdup_user((void __user *)(arg + minsz),
					   hdr.count * size);
			if (IS_ERR(data))
				return PTR_ERR(data);
Alex Williamson's avatar
Alex Williamson committed
594
595
596
597
598
599
600
601
602
603
604
605
		}

		mutex_lock(&vdev->igate);

		ret = vfio_pci_set_irqs_ioctl(vdev, hdr.flags, hdr.index,
					      hdr.start, hdr.count, data);

		mutex_unlock(&vdev->igate);
		kfree(data);

		return ret;

606
	} else if (cmd == VFIO_DEVICE_RESET) {
Alex Williamson's avatar
Alex Williamson committed
607
		return vdev->reset_works ?
608
			pci_try_reset_function(vdev->pdev) : -EINVAL;
Alex Williamson's avatar
Alex Williamson committed
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
	} else if (cmd == VFIO_DEVICE_GET_PCI_HOT_RESET_INFO) {
		struct vfio_pci_hot_reset_info hdr;
		struct vfio_pci_fill_info fill = { 0 };
		struct vfio_pci_dependent_device *devices = NULL;
		bool slot = false;
		int ret = 0;

		minsz = offsetofend(struct vfio_pci_hot_reset_info, count);

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

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

		hdr.flags = 0;

		/* Can we do a slot or bus reset or neither? */
		if (!pci_probe_reset_slot(vdev->pdev->slot))
			slot = true;
		else if (pci_probe_reset_bus(vdev->pdev->bus))
			return -ENODEV;

		/* How many devices are affected? */
		ret = vfio_pci_for_each_slot_or_bus(vdev->pdev,
						    vfio_pci_count_devs,
						    &fill.max, slot);
		if (ret)
			return ret;

		WARN_ON(!fill.max); /* Should always be at least one */

		/*
		 * If there's enough space, fill it now, otherwise return
		 * -ENOSPC and the number of devices affected.
		 */
		if (hdr.argsz < sizeof(hdr) + (fill.max * sizeof(*devices))) {
			ret = -ENOSPC;
			hdr.count = fill.max;
			goto reset_info_exit;
		}

		devices = kcalloc(fill.max, sizeof(*devices), GFP_KERNEL);
		if (!devices)
			return -ENOMEM;

		fill.devices = devices;

		ret = vfio_pci_for_each_slot_or_bus(vdev->pdev,
						    vfio_pci_fill_devs,
						    &fill, slot);

		/*
		 * If a device was removed between counting and filling,
		 * we may come up short of fill.max.  If a device was
		 * added, we'll have a return of -EAGAIN above.
		 */
		if (!ret)
			hdr.count = fill.cur;

reset_info_exit:
		if (copy_to_user((void __user *)arg, &hdr, minsz))
			ret = -EFAULT;

		if (!ret) {
			if (copy_to_user((void __user *)(arg + minsz), devices,
					 hdr.count * sizeof(*devices)))
				ret = -EFAULT;
		}

		kfree(devices);
		return ret;

	} else if (cmd == VFIO_DEVICE_PCI_HOT_RESET) {
		struct vfio_pci_hot_reset hdr;
		int32_t *group_fds;
		struct vfio_pci_group_entry *groups;
		struct vfio_pci_group_info info;
		bool slot = false;
		int i, count = 0, ret = 0;

		minsz = offsetofend(struct vfio_pci_hot_reset, count);

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

		if (hdr.argsz < minsz || hdr.flags)
			return -EINVAL;

		/* Can we do a slot or bus reset or neither? */
		if (!pci_probe_reset_slot(vdev->pdev->slot))
			slot = true;
		else if (pci_probe_reset_bus(vdev->pdev->bus))
			return -ENODEV;

		/*
		 * We can't let userspace give us an arbitrarily large
		 * buffer to copy, so verify how many we think there
		 * could be.  Note groups can have multiple devices so
		 * one group per device is the max.
		 */
		ret = vfio_pci_for_each_slot_or_bus(vdev->pdev,
						    vfio_pci_count_devs,
						    &count, slot);
		if (ret)
			return ret;

		/* Somewhere between 1 and count is OK */
		if (!hdr.count || hdr.count > count)
			return -EINVAL;

		group_fds = kcalloc(hdr.count, sizeof(*group_fds), GFP_KERNEL);
		groups = kcalloc(hdr.count, sizeof(*groups), GFP_KERNEL);
		if (!group_fds || !groups) {
			kfree(group_fds);
			kfree(groups);
			return -ENOMEM;
		}

		if (copy_from_user(group_fds, (void __user *)(arg + minsz),
				   hdr.count * sizeof(*group_fds))) {
			kfree(group_fds);
			kfree(groups);
			return -EFAULT;
		}

		/*
		 * For each group_fd, get the group through the vfio external
		 * user interface and store the group and iommu ID.  This
		 * ensures the group is held across the reset.
		 */
		for (i = 0; i < hdr.count; i++) {
			struct vfio_group *group;
			struct fd f = fdget(group_fds[i]);
			if (!f.file) {
				ret = -EBADF;
				break;
			}

			group = vfio_group_get_external_user(f.file);
			fdput(f);
			if (IS_ERR(group)) {
				ret = PTR_ERR(group);
				break;
			}

			groups[i].group = group;
			groups[i].id = vfio_external_user_iommu_id(group);
		}

		kfree(group_fds);

		/* release reference to groups on error */
		if (ret)
			goto hot_reset_release;

		info.count = hdr.count;
		info.groups = groups;

		/*
		 * Test whether all the affected devices are contained
		 * by the set of groups provided by the user.
		 */
		ret = vfio_pci_for_each_slot_or_bus(vdev->pdev,
						    vfio_pci_validate_devs,
						    &info, slot);
		if (!ret)
			/* User has access, do the reset */
778
779
			ret = slot ? pci_try_reset_slot(vdev->pdev->slot) :
				     pci_try_reset_bus(vdev->pdev->bus);
780
781
782
783
784
785
786
787
788

hot_reset_release:
		for (i--; i >= 0; i--)
			vfio_group_put_external_user(groups[i].group);

		kfree(groups);
		return ret;
	}

Alex Williamson's avatar
Alex Williamson committed
789
790
791
	return -ENOTTY;
}

792
793
static ssize_t vfio_pci_rw(void *device_data, char __user *buf,
			   size_t count, loff_t *ppos, bool iswrite)
Alex Williamson's avatar
Alex Williamson committed
794
795
796
797
798
799
800
{
	unsigned int index = VFIO_PCI_OFFSET_TO_INDEX(*ppos);
	struct vfio_pci_device *vdev = device_data;

	if (index >= VFIO_PCI_NUM_REGIONS)
		return -EINVAL;

801
802
	switch (index) {
	case VFIO_PCI_CONFIG_REGION_INDEX:
Alex Williamson's avatar
Alex Williamson committed
803
804
		return vfio_pci_config_rw(vdev, buf, count, ppos, iswrite);

805
806
807
	case VFIO_PCI_ROM_REGION_INDEX:
		if (iswrite)
			return -EINVAL;
Alex Williamson's avatar
Alex Williamson committed
808
		return vfio_pci_bar_rw(vdev, buf, count, ppos, false);
Alex Williamson's avatar
Alex Williamson committed
809

810
	case VFIO_PCI_BAR0_REGION_INDEX ... VFIO_PCI_BAR5_REGION_INDEX:
Alex Williamson's avatar
Alex Williamson committed
811
		return vfio_pci_bar_rw(vdev, buf, count, ppos, iswrite);
812
813
814

	case VFIO_PCI_VGA_REGION_INDEX:
		return vfio_pci_vga_rw(vdev, buf, count, ppos, iswrite);
815
816
	}

Alex Williamson's avatar
Alex Williamson committed
817
818
819
	return -EINVAL;
}

820
821
822
static ssize_t vfio_pci_read(void *device_data, char __user *buf,
			     size_t count, loff_t *ppos)
{
Alex Williamson's avatar
Alex Williamson committed
823
824
825
	if (!count)
		return 0;

826
827
828
	return vfio_pci_rw(device_data, buf, count, ppos, false);
}

Alex Williamson's avatar
Alex Williamson committed
829
830
831
static ssize_t vfio_pci_write(void *device_data, const char __user *buf,
			      size_t count, loff_t *ppos)
{
Alex Williamson's avatar
Alex Williamson committed
832
833
834
835
	if (!count)
		return 0;

	return vfio_pci_rw(device_data, (char __user *)buf, count, ppos, true);
Alex Williamson's avatar
Alex Williamson committed
836
837
838
839
840
841
842
}

static int vfio_pci_mmap(void *device_data, struct vm_area_struct *vma)
{
	struct vfio_pci_device *vdev = device_data;
	struct pci_dev *pdev = vdev->pdev;
	unsigned int index;
843
	u64 phys_len, req_len, pgoff, req_start;
Alex Williamson's avatar
Alex Williamson committed
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
889
890
891
892
893
894
895
896
	int ret;

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

	if (vma->vm_end < vma->vm_start)
		return -EINVAL;
	if ((vma->vm_flags & VM_SHARED) == 0)
		return -EINVAL;
	if (index >= VFIO_PCI_ROM_REGION_INDEX)
		return -EINVAL;
	if (!(pci_resource_flags(pdev, index) & IORESOURCE_MEM))
		return -EINVAL;

	phys_len = pci_resource_len(pdev, index);
	req_len = vma->vm_end - vma->vm_start;
	pgoff = vma->vm_pgoff &
		((1U << (VFIO_PCI_OFFSET_SHIFT - PAGE_SHIFT)) - 1);
	req_start = pgoff << PAGE_SHIFT;

	if (phys_len < PAGE_SIZE || req_start + req_len > phys_len)
		return -EINVAL;

	if (index == vdev->msix_bar) {
		/*
		 * Disallow mmaps overlapping the MSI-X table; users don't
		 * get to touch this directly.  We could find somewhere
		 * else to map the overlap, but page granularity is only
		 * a recommendation, not a requirement, so the user needs
		 * to know which bits are real.  Requiring them to mmap
		 * around the table makes that clear.
		 */

		/* If neither entirely above nor below, then it overlaps */
		if (!(req_start >= vdev->msix_offset + vdev->msix_size ||
		      req_start + req_len <= vdev->msix_offset))
			return -EINVAL;
	}

	/*
	 * Even though we don't make use of the barmap for the mmap,
	 * we need to request the region and the barmap tracks that.
	 */
	if (!vdev->barmap[index]) {
		ret = pci_request_selected_regions(pdev,
						   1 << index, "vfio-pci");
		if (ret)
			return ret;

		vdev->barmap[index] = pci_iomap(pdev, index, 0);
	}

	vma->vm_private_data = vdev;
	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
897
	vma->vm_pgoff = (pci_resource_start(pdev, index) >> PAGE_SHIFT) + pgoff;
Alex Williamson's avatar
Alex Williamson committed
898

899
	return remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
Alex Williamson's avatar
Alex Williamson committed
900
901
902
			       req_len, vma->vm_page_prot);
}

903
904
905
906
907
908
909
static void vfio_pci_request(void *device_data, unsigned int count)
{
	struct vfio_pci_device *vdev = device_data;

	mutex_lock(&vdev->igate);

	if (vdev->req_trigger) {
910
911
912
913
		if (!(count % 10))
			dev_notice_ratelimited(&vdev->pdev->dev,
				"Relaying device request to user (#%u)\n",
				count);
914
		eventfd_signal(vdev->req_trigger, 1);
915
916
917
	} else if (count == 0) {
		dev_warn(&vdev->pdev->dev,
			"No device request channel registered, blocked until released by user\n");
918
919
920
921
922
	}

	mutex_unlock(&vdev->igate);
}

Alex Williamson's avatar
Alex Williamson committed
923
924
925
926
927
928
929
930
static const struct vfio_device_ops vfio_pci_ops = {
	.name		= "vfio-pci",
	.open		= vfio_pci_open,
	.release	= vfio_pci_release,
	.ioctl		= vfio_pci_ioctl,
	.read		= vfio_pci_read,
	.write		= vfio_pci_write,
	.mmap		= vfio_pci_mmap,
931
	.request	= vfio_pci_request,
Alex Williamson's avatar
Alex Williamson committed
932
933
934
935
936
937
938
939
};

static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
{
	struct vfio_pci_device *vdev;
	struct iommu_group *group;
	int ret;

940
	if (pdev->hdr_type != PCI_HEADER_TYPE_NORMAL)
Alex Williamson's avatar
Alex Williamson committed
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
		return -EINVAL;

	group = iommu_group_get(&pdev->dev);
	if (!group)
		return -EINVAL;

	vdev = kzalloc(sizeof(*vdev), GFP_KERNEL);
	if (!vdev) {
		iommu_group_put(group);
		return -ENOMEM;
	}

	vdev->pdev = pdev;
	vdev->irq_type = VFIO_PCI_NUM_IRQS;
	mutex_init(&vdev->igate);
	spin_lock_init(&vdev->irqlock);

	ret = vfio_add_group_dev(&pdev->dev, &vfio_pci_ops, vdev);
	if (ret) {
		iommu_group_put(group);
		kfree(vdev);
Alex Williamson's avatar
Alex Williamson committed
962
		return ret;
Alex Williamson's avatar
Alex Williamson committed
963
964
	}

965
966
967
968
969
970
	if (vfio_pci_is_vga(pdev)) {
		vga_client_register(pdev, vdev, NULL, vfio_pci_set_vga_decode);
		vga_set_legacy_decoding(pdev,
					vfio_pci_set_vga_decode(vdev, false));
	}

971
972
973
974
975
976
977
978
979
980
981
982
983
984
	if (!disable_idle_d3) {
		/*
		 * pci-core sets the device power state to an unknown value at
		 * bootup and after being removed from a driver.  The only
		 * transition it allows from this unknown state is to D0, which
		 * typically happens when a driver calls pci_enable_device().
		 * We're not ready to enable the device yet, but we do want to
		 * be able to get to D3.  Therefore first do a D0 transition
		 * before going to D3.
		 */
		pci_set_power_state(pdev, PCI_D0);
		pci_set_power_state(pdev, PCI_D3hot);
	}

Alex Williamson's avatar
Alex Williamson committed
985
986
987
988
989
990
991
992
	return ret;
}

static void vfio_pci_remove(struct pci_dev *pdev)
{
	struct vfio_pci_device *vdev;

	vdev = vfio_del_group_dev(&pdev->dev);
993
994
995
996
997
998
999
1000
1001
1002
1003
	if (!vdev)
		return;

	iommu_group_put(pdev->dev.iommu_group);
	kfree(vdev);

	if (vfio_pci_is_vga(pdev)) {
		vga_client_register(pdev, NULL, NULL, NULL);
		vga_set_legacy_decoding(pdev,
				VGA_RSRC_NORMAL_IO | VGA_RSRC_NORMAL_MEM |
				VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM);
1004
	}
1005
1006
1007

	if (!disable_idle_d3)
		pci_set_power_state(pdev, PCI_D0);
Alex Williamson's avatar
Alex Williamson committed
1008
1009
}

1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
static pci_ers_result_t vfio_pci_aer_err_detected(struct pci_dev *pdev,
						  pci_channel_state_t state)
{
	struct vfio_pci_device *vdev;
	struct vfio_device *device;

	device = vfio_device_get_from_dev(&pdev->dev);
	if (device == NULL)
		return PCI_ERS_RESULT_DISCONNECT;

	vdev = vfio_device_data(device);
	if (vdev == NULL) {
		vfio_device_put(device);
		return PCI_ERS_RESULT_DISCONNECT;
	}

1026
1027
	mutex_lock(&vdev->igate);

1028
1029
1030
	if (vdev->err_trigger)
		eventfd_signal(vdev->err_trigger, 1);

1031
1032
	mutex_unlock(&vdev->igate);

1033
1034
1035
1036
1037
1038
1039
1040
1041
	vfio_device_put(device);

	return PCI_ERS_RESULT_CAN_RECOVER;
}

static struct pci_error_handlers vfio_err_handlers = {
	.error_detected = vfio_pci_aer_err_detected,
};

Alex Williamson's avatar
Alex Williamson committed
1042
1043
1044
1045
1046
static struct pci_driver vfio_pci_driver = {
	.name		= "vfio-pci",
	.id_table	= NULL, /* only dynamic ids */
	.probe		= vfio_pci_probe,
	.remove		= vfio_pci_remove,
1047
	.err_handler	= &vfio_err_handlers,
Alex Williamson's avatar
Alex Williamson committed
1048
1049
};

1050
1051
1052
1053
1054
struct vfio_devices {
	struct vfio_device **devices;
	int cur_index;
	int max_index;
};
1055

1056
static int vfio_pci_get_devs(struct pci_dev *pdev, void *data)
1057
{
1058
	struct vfio_devices *devs = data;
1059
	struct vfio_device *device;
1060

1061
1062
	if (devs->cur_index == devs->max_index)
		return -ENOSPC;
1063

1064
1065
	device = vfio_device_get_from_dev(&pdev->dev);
	if (!device)
1066
		return -EINVAL;
1067

1068
1069
1070
1071
1072
1073
	if (pci_dev_driver(pdev) != &vfio_pci_driver) {
		vfio_device_put(device);
		return -EBUSY;
	}

	devs->devices[devs->cur_index++] = device;
1074
1075
1076
1077
1078
1079
	return 0;
}

/*
 * Attempt to do a bus/slot reset if there are devices affected by a reset for
 * this device that are needs_reset and all of the affected devices are unused
1080
1081
1082
1083
1084
1085
1086
1087
 * (!refcnt).  Callers are required to hold driver_lock when calling this to
 * prevent device opens and concurrent bus reset attempts.  We prevent device
 * unbinds by acquiring and holding a reference to the vfio_device.
 *
 * NB: vfio-core considers a group to be viable even if some devices are
 * bound to drivers like pci-stub or pcieport.  Here we require all devices
 * to be bound to vfio_pci since that's the only way we can be sure they
 * stay put.
1088
1089
1090
 */
static void vfio_pci_try_bus_reset(struct vfio_pci_device *vdev)
{
1091
1092
	struct vfio_devices devs = { .cur_index = 0 };
	int i = 0, ret = -EINVAL;
1093
	bool needs_reset = false, slot = false;
1094
	struct vfio_pci_device *tmp;
1095
1096
1097
1098
1099
1100

	if (!pci_probe_reset_slot(vdev->pdev->slot))
		slot = true;
	else if (pci_probe_reset_bus(vdev->pdev->bus))
		return;

1101
1102
	if (vfio_pci_for_each_slot_or_bus(vdev->pdev, vfio_pci_count_devs,
					  &i, slot) || !i)
1103
1104
		return;

1105
1106
1107
	devs.max_index = i;
	devs.devices = kcalloc(i, sizeof(struct vfio_device *), GFP_KERNEL);
	if (!devs.devices)
1108
1109
		return;

1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
	if (vfio_pci_for_each_slot_or_bus(vdev->pdev,
					  vfio_pci_get_devs, &devs, slot))
		goto put_devs;

	for (i = 0; i < devs.cur_index; i++) {
		tmp = vfio_device_data(devs.devices[i]);
		if (tmp->needs_reset)
			needs_reset = true;
		if (tmp->refcnt)
			goto put_devs;
	}

	if (needs_reset)
		ret = slot ? pci_try_reset_slot(vdev->pdev->slot) :
			     pci_try_reset_bus(vdev->pdev->bus);

put_devs:
	for (i = 0; i < devs.cur_index; i++) {
1128
1129
		tmp = vfio_device_data(devs.devices[i]);
		if (!ret)
1130
			tmp->needs_reset = false;
1131
1132
1133
1134

		if (!tmp->refcnt && !disable_idle_d3)
			pci_set_power_state(tmp->pdev, PCI_D3hot);

1135
1136
1137
1138
		vfio_device_put(devs.devices[i]);
	}

	kfree(devs.devices);
1139
1140
}

Alex Williamson's avatar
Alex Williamson committed
1141
1142
1143
1144
1145
1146
static void __exit vfio_pci_cleanup(void)
{
	pci_unregister_driver(&vfio_pci_driver);
	vfio_pci_uninit_perm_bits();
}

1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
static void __init vfio_pci_fill_ids(void)
{
	char *p, *id;
	int rc;

	/* no ids passed actually */
	if (ids[0] == '\0')
		return;

	/* add ids specified in the module parameter */
	p = ids;
	while ((id = strsep(&p, ","))) {
		unsigned int vendor, device, subvendor = PCI_ANY_ID,
			subdevice = PCI_ANY_ID, class = 0, class_mask = 0;
		int fields;

		if (!strlen(id))
			continue;

		fields = sscanf(id, "%x:%x:%x:%x:%x:%x",
				&vendor, &device, &subvendor, &subdevice,
				&class, &class_mask);

		if (fields < 2) {
			pr_warn("invalid id string \"%s\"\n", id);
			continue;
		}

		rc = pci_add_dynid(&vfio_pci_driver, vendor, device,
				   subvendor, subdevice, class, class_mask, 0);
		if (rc)
			pr_warn("failed to add dynamic id [%04hx:%04hx[%04hx:%04hx]] class %#08x/%08x (%d)\n",
				vendor, device, subvendor, subdevice,
				class, class_mask, rc);
		else
			pr_info("add [%04hx:%04hx[%04hx:%04hx]] class %#08x/%08x\n",
				vendor, device, subvendor, subdevice,
				class, class_mask);
	}
}

Alex Williamson's avatar
Alex Williamson committed
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
static int __init vfio_pci_init(void)
{
	int ret;

	/* Allocate shared config space permision data used by all devices */
	ret = vfio_pci_init_perm_bits();
	if (ret)
		return ret;

	/* Register and scan for devices */
	ret = pci_register_driver(&vfio_pci_driver);
	if (ret)
		goto out_driver;

1202
1203
	vfio_pci_fill_ids();

Alex Williamson's avatar
Alex Williamson committed
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
	return 0;

out_driver:
	vfio_pci_uninit_perm_bits();
	return ret;
}

module_init(vfio_pci_init);
module_exit(vfio_pci_cleanup);

MODULE_VERSION(DRIVER_VERSION);
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR(DRIVER_AUTHOR);
MODULE_DESCRIPTION(DRIVER_DESC);