summaryrefslogtreecommitdiff
path: root/drivers/firmware/qemu_fw_cfg.c
blob: f08e056ed0ae4506db5f6336534b4095ea4cc388 (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
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
/*
 * drivers/firmware/qemu_fw_cfg.c
 *
 * Copyright 2015 Carnegie Mellon University
 *
 * Expose entries from QEMU's firmware configuration (fw_cfg) device in
 * sysfs (read-only, under "/sys/firmware/qemu_fw_cfg/...").
 *
 * The fw_cfg device may be instantiated via either an ACPI node (on x86
 * and select subsets of aarch64), a Device Tree node (on arm), or using
 * a kernel module (or command line) parameter with the following syntax:
 *
 *      [qemu_fw_cfg.]ioport=<size>@<base>[:<ctrl_off>:<data_off>[:<dma_off>]]
 * or
 *      [qemu_fw_cfg.]mmio=<size>@<base>[:<ctrl_off>:<data_off>[:<dma_off>]]
 *
 * where:
 *      <size>     := size of ioport or mmio range
 *      <base>     := physical base address of ioport or mmio range
 *      <ctrl_off> := (optional) offset of control register
 *      <data_off> := (optional) offset of data register
 *      <dma_off> := (optional) offset of dma register
 *
 * e.g.:
 *      qemu_fw_cfg.ioport=12@0x510:0:1:4	(the default on x86)
 * or
 *      qemu_fw_cfg.mmio=16@0x9020000:8:0:16	(the default on arm)
 */

#include <linux/module.h>
#include <linux/mod_devicetable.h>
#include <linux/platform_device.h>
#include <linux/acpi.h>
#include <linux/slab.h>
#include <linux/io.h>
#include <linux/ioport.h>
#include <uapi/linux/qemu_fw_cfg.h>
#include <linux/delay.h>
#include <linux/crash_dump.h>
#include <linux/crash_core.h>

MODULE_AUTHOR("Gabriel L. Somlo <somlo@cmu.edu>");
MODULE_DESCRIPTION("QEMU fw_cfg sysfs support");
MODULE_LICENSE("GPL");

/* fw_cfg revision attribute, in /sys/firmware/qemu_fw_cfg top-level dir. */
static u32 fw_cfg_rev;

/* fw_cfg device i/o register addresses */
static bool fw_cfg_is_mmio;
static phys_addr_t fw_cfg_p_base;
static resource_size_t fw_cfg_p_size;
static void __iomem *fw_cfg_dev_base;
static void __iomem *fw_cfg_reg_ctrl;
static void __iomem *fw_cfg_reg_data;
static void __iomem *fw_cfg_reg_dma;

/* atomic access to fw_cfg device (potentially slow i/o, so using mutex) */
static DEFINE_MUTEX(fw_cfg_dev_lock);

/* pick appropriate endianness for selector key */
static void fw_cfg_sel_endianness(u16 key)
{
	if (fw_cfg_is_mmio)
		iowrite16be(key, fw_cfg_reg_ctrl);
	else
		iowrite16(key, fw_cfg_reg_ctrl);
}

#ifdef CONFIG_CRASH_CORE
static inline bool fw_cfg_dma_enabled(void)
{
	return (fw_cfg_rev & FW_CFG_VERSION_DMA) && fw_cfg_reg_dma;
}

/* qemu fw_cfg device is sync today, but spec says it may become async */
static void fw_cfg_wait_for_control(struct fw_cfg_dma_access *d)
{
	for (;;) {
		u32 ctrl = be32_to_cpu(READ_ONCE(d->control));

		/* do not reorder the read to d->control */
		rmb();
		if ((ctrl & ~FW_CFG_DMA_CTL_ERROR) == 0)
			return;

		cpu_relax();
	}
}

static ssize_t fw_cfg_dma_transfer(void *address, u32 length, u32 control)
{
	phys_addr_t dma;
	struct fw_cfg_dma_access *d = NULL;
	ssize_t ret = length;

	d = kmalloc(sizeof(*d), GFP_KERNEL);
	if (!d) {
		ret = -ENOMEM;
		goto end;
	}

	/* fw_cfg device does not need IOMMU protection, so use physical addresses */
	*d = (struct fw_cfg_dma_access) {
		.address = cpu_to_be64(address ? virt_to_phys(address) : 0),
		.length = cpu_to_be32(length),
		.control = cpu_to_be32(control)
	};

	dma = virt_to_phys(d);

	iowrite32be((u64)dma >> 32, fw_cfg_reg_dma);
	/* force memory to sync before notifying device via MMIO */
	wmb();
	iowrite32be(dma, fw_cfg_reg_dma + 4);

	fw_cfg_wait_for_control(d);

	if (be32_to_cpu(READ_ONCE(d->control)) & FW_CFG_DMA_CTL_ERROR) {
		ret = -EIO;
	}

end:
	kfree(d);

	return ret;
}
#endif

/* read chunk of given fw_cfg blob (caller responsible for sanity-check) */
static ssize_t fw_cfg_read_blob(u16 key,
				void *buf, loff_t pos, size_t count)
{
	u32 glk = -1U;
	acpi_status status;

	/* If we have ACPI, ensure mutual exclusion against any potential
	 * device access by the firmware, e.g. via AML methods:
	 */
	status = acpi_acquire_global_lock(ACPI_WAIT_FOREVER, &glk);
	if (ACPI_FAILURE(status) && status != AE_NOT_CONFIGURED) {
		/* Should never get here */
		WARN(1, "fw_cfg_read_blob: Failed to lock ACPI!\n");
		memset(buf, 0, count);
		return -EINVAL;
	}

	mutex_lock(&fw_cfg_dev_lock);
	fw_cfg_sel_endianness(key);
	while (pos-- > 0)
		ioread8(fw_cfg_reg_data);
	ioread8_rep(fw_cfg_reg_data, buf, count);
	mutex_unlock(&fw_cfg_dev_lock);

	acpi_release_global_lock(glk);
	return count;
}

#ifdef CONFIG_CRASH_CORE
/* write chunk of given fw_cfg blob (caller responsible for sanity-check) */
static ssize_t fw_cfg_write_blob(u16 key,
				 void *buf, loff_t pos, size_t count)
{
	u32 glk = -1U;
	acpi_status status;
	ssize_t ret = count;

	/* If we have ACPI, ensure mutual exclusion against any potential
	 * device access by the firmware, e.g. via AML methods:
	 */
	status = acpi_acquire_global_lock(ACPI_WAIT_FOREVER, &glk);
	if (ACPI_FAILURE(status) && status != AE_NOT_CONFIGURED) {
		/* Should never get here */
		WARN(1, "%s: Failed to lock ACPI!\n", __func__);
		return -EINVAL;
	}

	mutex_lock(&fw_cfg_dev_lock);
	if (pos == 0) {
		ret = fw_cfg_dma_transfer(buf, count, key << 16
					  | FW_CFG_DMA_CTL_SELECT
					  | FW_CFG_DMA_CTL_WRITE);
	} else {
		fw_cfg_sel_endianness(key);
		ret = fw_cfg_dma_transfer(NULL, pos, FW_CFG_DMA_CTL_SKIP);
		if (ret < 0)
			goto end;
		ret = fw_cfg_dma_transfer(buf, count, FW_CFG_DMA_CTL_WRITE);
	}

end:
	mutex_unlock(&fw_cfg_dev_lock);

	acpi_release_global_lock(glk);

	return ret;
}
#endif /* CONFIG_CRASH_CORE */

/* clean up fw_cfg device i/o */
static void fw_cfg_io_cleanup(void)
{
	if (fw_cfg_is_mmio) {
		iounmap(fw_cfg_dev_base);
		release_mem_region(fw_cfg_p_base, fw_cfg_p_size);
	} else {
		ioport_unmap(fw_cfg_dev_base);
		release_region(fw_cfg_p_base, fw_cfg_p_size);
	}
}

/* arch-specific ctrl & data register offsets are not available in ACPI, DT */
#if !(defined(FW_CFG_CTRL_OFF) && defined(FW_CFG_DATA_OFF))
# if (defined(CONFIG_ARM) || defined(CONFIG_ARM64))
#  define FW_CFG_CTRL_OFF 0x08
#  define FW_CFG_DATA_OFF 0x00
#  define FW_CFG_DMA_OFF 0x10
# elif defined(CONFIG_PARISC)	/* parisc */
#  define FW_CFG_CTRL_OFF 0x00
#  define FW_CFG_DATA_OFF 0x04
# elif (defined(CONFIG_PPC_PMAC) || defined(CONFIG_SPARC32)) /* ppc/mac,sun4m */
#  define FW_CFG_CTRL_OFF 0x00
#  define FW_CFG_DATA_OFF 0x02
# elif (defined(CONFIG_X86) || defined(CONFIG_SPARC64)) /* x86, sun4u */
#  define FW_CFG_CTRL_OFF 0x00
#  define FW_CFG_DATA_OFF 0x01
#  define FW_CFG_DMA_OFF 0x04
# else
#  error "QEMU FW_CFG not available on this architecture!"
# endif
#endif

/* initialize fw_cfg device i/o from platform data */
static int fw_cfg_do_platform_probe(struct platform_device *pdev)
{
	char sig[FW_CFG_SIG_SIZE];
	struct resource *range, *ctrl, *data, *dma;

	/* acquire i/o range details */
	fw_cfg_is_mmio = false;
	range = platform_get_resource(pdev, IORESOURCE_IO, 0);
	if (!range) {
		fw_cfg_is_mmio = true;
		range = platform_get_resource(pdev, IORESOURCE_MEM, 0);
		if (!range)
			return -EINVAL;
	}
	fw_cfg_p_base = range->start;
	fw_cfg_p_size = resource_size(range);

	if (fw_cfg_is_mmio) {
		if (!request_mem_region(fw_cfg_p_base,
					fw_cfg_p_size, "fw_cfg_mem"))
			return -EBUSY;
		fw_cfg_dev_base = ioremap(fw_cfg_p_base, fw_cfg_p_size);
		if (!fw_cfg_dev_base) {
			release_mem_region(fw_cfg_p_base, fw_cfg_p_size);
			return -EFAULT;
		}
	} else {
		if (!request_region(fw_cfg_p_base,
				    fw_cfg_p_size, "fw_cfg_io"))
			return -EBUSY;
		fw_cfg_dev_base = ioport_map(fw_cfg_p_base, fw_cfg_p_size);
		if (!fw_cfg_dev_base) {
			release_region(fw_cfg_p_base, fw_cfg_p_size);
			return -EFAULT;
		}
	}

	/* were custom register offsets provided (e.g. on the command line)? */
	ctrl = platform_get_resource_byname(pdev, IORESOURCE_REG, "ctrl");
	data = platform_get_resource_byname(pdev, IORESOURCE_REG, "data");
	dma = platform_get_resource_byname(pdev, IORESOURCE_REG, "dma");
	if (ctrl && data) {
		fw_cfg_reg_ctrl = fw_cfg_dev_base + ctrl->start;
		fw_cfg_reg_data = fw_cfg_dev_base + data->start;
	} else {
		/* use architecture-specific offsets */
		fw_cfg_reg_ctrl = fw_cfg_dev_base + FW_CFG_CTRL_OFF;
		fw_cfg_reg_data = fw_cfg_dev_base + FW_CFG_DATA_OFF;
	}

	if (dma)
		fw_cfg_reg_dma = fw_cfg_dev_base + dma->start;
#ifdef FW_CFG_DMA_OFF
	else
		fw_cfg_reg_dma = fw_cfg_dev_base + FW_CFG_DMA_OFF;
#endif

	/* verify fw_cfg device signature */
	if (fw_cfg_read_blob(FW_CFG_SIGNATURE, sig,
				0, FW_CFG_SIG_SIZE) < 0 ||
		memcmp(sig, "QEMU", FW_CFG_SIG_SIZE) != 0) {
		fw_cfg_io_cleanup();
		return -ENODEV;
	}

	return 0;
}

static ssize_t fw_cfg_showrev(struct kobject *k, struct kobj_attribute *a,
			      char *buf)
{
	return sprintf(buf, "%u\n", fw_cfg_rev);
}

static const struct kobj_attribute fw_cfg_rev_attr = {
	.attr = { .name = "rev", .mode = S_IRUSR },
	.show = fw_cfg_showrev,
};

/* fw_cfg_sysfs_entry type */
struct fw_cfg_sysfs_entry {
	struct kobject kobj;
	u32 size;
	u16 select;
	char name[FW_CFG_MAX_FILE_PATH];
	struct list_head list;
};

#ifdef CONFIG_CRASH_CORE
static ssize_t fw_cfg_write_vmcoreinfo(const struct fw_cfg_file *f)
{
	static struct fw_cfg_vmcoreinfo *data;
	ssize_t ret;

	data = kmalloc(sizeof(struct fw_cfg_vmcoreinfo), GFP_KERNEL);
	if (!data)
		return -ENOMEM;

	*data = (struct fw_cfg_vmcoreinfo) {
		.guest_format = cpu_to_le16(FW_CFG_VMCOREINFO_FORMAT_ELF),
		.size = cpu_to_le32(VMCOREINFO_NOTE_SIZE),
		.paddr = cpu_to_le64(paddr_vmcoreinfo_note())
	};
	/* spare ourself reading host format support for now since we
	 * don't know what else to format - host may ignore ours
	 */
	ret = fw_cfg_write_blob(be16_to_cpu(f->select), data,
				0, sizeof(struct fw_cfg_vmcoreinfo));

	kfree(data);
	return ret;
}
#endif /* CONFIG_CRASH_CORE */

/* get fw_cfg_sysfs_entry from kobject member */
static inline struct fw_cfg_sysfs_entry *to_entry(struct kobject *kobj)
{
	return container_of(kobj, struct fw_cfg_sysfs_entry, kobj);
}

/* fw_cfg_sysfs_attribute type */
struct fw_cfg_sysfs_attribute {
	struct attribute attr;
	ssize_t (*show)(struct fw_cfg_sysfs_entry *entry, char *buf);
};

/* get fw_cfg_sysfs_attribute from attribute member */
static inline struct fw_cfg_sysfs_attribute *to_attr(struct attribute *attr)
{
	return container_of(attr, struct fw_cfg_sysfs_attribute, attr);
}

/* global cache of fw_cfg_sysfs_entry objects */
static LIST_HEAD(fw_cfg_entry_cache);

/* kobjects removed lazily by kernel, mutual exclusion needed */
static DEFINE_SPINLOCK(fw_cfg_cache_lock);

static inline void fw_cfg_sysfs_cache_enlist(struct fw_cfg_sysfs_entry *entry)
{
	spin_lock(&fw_cfg_cache_lock);
	list_add_tail(&entry->list, &fw_cfg_entry_cache);
	spin_unlock(&fw_cfg_cache_lock);
}

static inline void fw_cfg_sysfs_cache_delist(struct fw_cfg_sysfs_entry *entry)
{
	spin_lock(&fw_cfg_cache_lock);
	list_del(&entry->list);
	spin_unlock(&fw_cfg_cache_lock);
}

static void fw_cfg_sysfs_cache_cleanup(void)
{
	struct fw_cfg_sysfs_entry *entry, *next;

	list_for_each_entry_safe(entry, next, &fw_cfg_entry_cache, list) {
		fw_cfg_sysfs_cache_delist(entry);
		kobject_put(&entry->kobj);
	}
}

/* default_attrs: per-entry attributes and show methods */

#define FW_CFG_SYSFS_ATTR(_attr) \
struct fw_cfg_sysfs_attribute fw_cfg_sysfs_attr_##_attr = { \
	.attr = { .name = __stringify(_attr), .mode = S_IRUSR }, \
	.show = fw_cfg_sysfs_show_##_attr, \
}

static ssize_t fw_cfg_sysfs_show_size(struct fw_cfg_sysfs_entry *e, char *buf)
{
	return sprintf(buf, "%u\n", e->size);
}

static ssize_t fw_cfg_sysfs_show_key(struct fw_cfg_sysfs_entry *e, char *buf)
{
	return sprintf(buf, "%u\n", e->select);
}

static ssize_t fw_cfg_sysfs_show_name(struct fw_cfg_sysfs_entry *e, char *buf)
{
	return sprintf(buf, "%s\n", e->name);
}

static FW_CFG_SYSFS_ATTR(size);
static FW_CFG_SYSFS_ATTR(key);
static FW_CFG_SYSFS_ATTR(name);

static struct attribute *fw_cfg_sysfs_entry_attrs[] = {
	&fw_cfg_sysfs_attr_size.attr,
	&fw_cfg_sysfs_attr_key.attr,
	&fw_cfg_sysfs_attr_name.attr,
	NULL,
};

/* sysfs_ops: find fw_cfg_[entry, attribute] and call appropriate show method */
static ssize_t fw_cfg_sysfs_attr_show(struct kobject *kobj, struct attribute *a,
				      char *buf)
{
	struct fw_cfg_sysfs_entry *entry = to_entry(kobj);
	struct fw_cfg_sysfs_attribute *attr = to_attr(a);

	return attr->show(entry, buf);
}

static const struct sysfs_ops fw_cfg_sysfs_attr_ops = {
	.show = fw_cfg_sysfs_attr_show,
};

/* release: destructor, to be called via kobject_put() */
static void fw_cfg_sysfs_release_entry(struct kobject *kobj)
{
	struct fw_cfg_sysfs_entry *entry = to_entry(kobj);

	kfree(entry);
}

/* kobj_type: ties together all properties required to register an entry */
static struct kobj_type fw_cfg_sysfs_entry_ktype = {
	.default_attrs = fw_cfg_sysfs_entry_attrs,
	.sysfs_ops = &fw_cfg_sysfs_attr_ops,
	.release = fw_cfg_sysfs_release_entry,
};

/* raw-read method and attribute */
static ssize_t fw_cfg_sysfs_read_raw(struct file *filp, struct kobject *kobj,
				     struct bin_attribute *bin_attr,
				     char *buf, loff_t pos, size_t count)
{
	struct fw_cfg_sysfs_entry *entry = to_entry(kobj);

	if (pos > entry->size)
		return -EINVAL;

	if (count > entry->size - pos)
		count = entry->size - pos;

	return fw_cfg_read_blob(entry->select, buf, pos, count);
}

static struct bin_attribute fw_cfg_sysfs_attr_raw = {
	.attr = { .name = "raw", .mode = S_IRUSR },
	.read = fw_cfg_sysfs_read_raw,
};

/*
 * Create a kset subdirectory matching each '/' delimited dirname token
 * in 'name', starting with sysfs kset/folder 'dir'; At the end, create
 * a symlink directed at the given 'target'.
 * NOTE: We do this on a best-effort basis, since 'name' is not guaranteed
 * to be a well-behaved path name. Whenever a symlink vs. kset directory
 * name collision occurs, the kernel will issue big scary warnings while
 * refusing to add the offending link or directory. We follow up with our
 * own, slightly less scary error messages explaining the situation :)
 */
static int fw_cfg_build_symlink(struct kset *dir,
				struct kobject *target, const char *name)
{
	int ret;
	struct kset *subdir;
	struct kobject *ko;
	char *name_copy, *p, *tok;

	if (!dir || !target || !name || !*name)
		return -EINVAL;

	/* clone a copy of name for parsing */
	name_copy = p = kstrdup(name, GFP_KERNEL);
	if (!name_copy)
		return -ENOMEM;

	/* create folders for each dirname token, then symlink for basename */
	while ((tok = strsep(&p, "/")) && *tok) {

		/* last (basename) token? If so, add symlink here */
		if (!p || !*p) {
			ret = sysfs_create_link(&dir->kobj, target, tok);
			break;
		}

		/* does the current dir contain an item named after tok ? */
		ko = kset_find_obj(dir, tok);
		if (ko) {
			/* drop reference added by kset_find_obj */
			kobject_put(ko);

			/* ko MUST be a kset - we're about to use it as one ! */
			if (ko->ktype != dir->kobj.ktype) {
				ret = -EINVAL;
				break;
			}

			/* descend into already existing subdirectory */
			dir = to_kset(ko);
		} else {
			/* create new subdirectory kset */
			subdir = kzalloc(sizeof(struct kset), GFP_KERNEL);
			if (!subdir) {
				ret = -ENOMEM;
				break;
			}
			subdir->kobj.kset = dir;
			subdir->kobj.ktype = dir->kobj.ktype;
			ret = kobject_set_name(&subdir->kobj, "%s", tok);
			if (ret) {
				kfree(subdir);
				break;
			}
			ret = kset_register(subdir);
			if (ret) {
				kfree(subdir);
				break;
			}

			/* descend into newly created subdirectory */
			dir = subdir;
		}
	}

	/* we're done with cloned copy of name */
	kfree(name_copy);
	return ret;
}

/* recursively unregister fw_cfg/by_name/ kset directory tree */
static void fw_cfg_kset_unregister_recursive(struct kset *kset)
{
	struct kobject *k, *next;

	list_for_each_entry_safe(k, next, &kset->list, entry)
		/* all set members are ksets too, but check just in case... */
		if (k->ktype == kset->kobj.ktype)
			fw_cfg_kset_unregister_recursive(to_kset(k));

	/* symlinks are cleanly and automatically removed with the directory */
	kset_unregister(kset);
}

/* kobjects & kset representing top-level, by_key, and by_name folders */
static struct kobject *fw_cfg_top_ko;
static struct kobject *fw_cfg_sel_ko;
static struct kset *fw_cfg_fname_kset;

/* register an individual fw_cfg file */
static int fw_cfg_register_file(const struct fw_cfg_file *f)
{
	int err;
	struct fw_cfg_sysfs_entry *entry;

#ifdef CONFIG_CRASH_CORE
	if (fw_cfg_dma_enabled() &&
		strcmp(f->name, FW_CFG_VMCOREINFO_FILENAME) == 0 &&
		!is_kdump_kernel()) {
		if (fw_cfg_write_vmcoreinfo(f) < 0)
			pr_warn("fw_cfg: failed to write vmcoreinfo");
	}
#endif

	/* allocate new entry */
	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
	if (!entry)
		return -ENOMEM;

	/* set file entry information */
	entry->size = be32_to_cpu(f->size);
	entry->select = be16_to_cpu(f->select);
	strscpy(entry->name, f->name, FW_CFG_MAX_FILE_PATH);

	/* register entry under "/sys/firmware/qemu_fw_cfg/by_key/" */
	err = kobject_init_and_add(&entry->kobj, &fw_cfg_sysfs_entry_ktype,
				   fw_cfg_sel_ko, "%d", entry->select);
	if (err)
		goto err_put_entry;

	/* add raw binary content access */
	err = sysfs_create_bin_file(&entry->kobj, &fw_cfg_sysfs_attr_raw);
	if (err)
		goto err_del_entry;

	/* try adding "/sys/firmware/qemu_fw_cfg/by_name/" symlink */
	fw_cfg_build_symlink(fw_cfg_fname_kset, &entry->kobj, entry->name);

	/* success, add entry to global cache */
	fw_cfg_sysfs_cache_enlist(entry);
	return 0;

err_del_entry:
	kobject_del(&entry->kobj);
err_put_entry:
	kobject_put(&entry->kobj);
	return err;
}

/* iterate over all fw_cfg directory entries, registering each one */
static int fw_cfg_register_dir_entries(void)
{
	int ret = 0;
	__be32 files_count;
	u32 count, i;
	struct fw_cfg_file *dir;
	size_t dir_size;

	ret = fw_cfg_read_blob(FW_CFG_FILE_DIR, &files_count,
			0, sizeof(files_count));
	if (ret < 0)
		return ret;

	count = be32_to_cpu(files_count);
	dir_size = count * sizeof(struct fw_cfg_file);

	dir = kmalloc(dir_size, GFP_KERNEL);
	if (!dir)
		return -ENOMEM;

	ret = fw_cfg_read_blob(FW_CFG_FILE_DIR, dir,
			sizeof(files_count), dir_size);
	if (ret < 0)
		goto end;

	for (i = 0; i < count; i++) {
		ret = fw_cfg_register_file(&dir[i]);
		if (ret)
			break;
	}

end:
	kfree(dir);
	return ret;
}

/* unregister top-level or by_key folder */
static inline void fw_cfg_kobj_cleanup(struct kobject *kobj)
{
	kobject_del(kobj);
	kobject_put(kobj);
}

static int fw_cfg_sysfs_probe(struct platform_device *pdev)
{
	int err;
	__le32 rev;

	/* NOTE: If we supported multiple fw_cfg devices, we'd first create
	 * a subdirectory named after e.g. pdev->id, then hang per-device
	 * by_key (and by_name) subdirectories underneath it. However, only
	 * one fw_cfg device exist system-wide, so if one was already found
	 * earlier, we might as well stop here.
	 */
	if (fw_cfg_sel_ko)
		return -EBUSY;

	/* create by_key and by_name subdirs of /sys/firmware/qemu_fw_cfg/ */
	err = -ENOMEM;
	fw_cfg_sel_ko = kobject_create_and_add("by_key", fw_cfg_top_ko);
	if (!fw_cfg_sel_ko)
		goto err_sel;
	fw_cfg_fname_kset = kset_create_and_add("by_name", NULL, fw_cfg_top_ko);
	if (!fw_cfg_fname_kset)
		goto err_name;

	/* initialize fw_cfg device i/o from platform data */
	err = fw_cfg_do_platform_probe(pdev);
	if (err)
		goto err_probe;

	/* get revision number, add matching top-level attribute */
	err = fw_cfg_read_blob(FW_CFG_ID, &rev, 0, sizeof(rev));
	if (err < 0)
		goto err_probe;

	fw_cfg_rev = le32_to_cpu(rev);
	err = sysfs_create_file(fw_cfg_top_ko, &fw_cfg_rev_attr.attr);
	if (err)
		goto err_rev;

	/* process fw_cfg file directory entry, registering each file */
	err = fw_cfg_register_dir_entries();
	if (err)
		goto err_dir;

	/* success */
	pr_debug("fw_cfg: loaded.\n");
	return 0;

err_dir:
	fw_cfg_sysfs_cache_cleanup();
	sysfs_remove_file(fw_cfg_top_ko, &fw_cfg_rev_attr.attr);
err_rev:
	fw_cfg_io_cleanup();
err_probe:
	fw_cfg_kset_unregister_recursive(fw_cfg_fname_kset);
err_name:
	fw_cfg_kobj_cleanup(fw_cfg_sel_ko);
err_sel:
	return err;
}

static int fw_cfg_sysfs_remove(struct platform_device *pdev)
{
	pr_debug("fw_cfg: unloading.\n");
	fw_cfg_sysfs_cache_cleanup();
	sysfs_remove_file(fw_cfg_top_ko, &fw_cfg_rev_attr.attr);
	fw_cfg_io_cleanup();
	fw_cfg_kset_unregister_recursive(fw_cfg_fname_kset);
	fw_cfg_kobj_cleanup(fw_cfg_sel_ko);
	return 0;
}

static const struct of_device_id fw_cfg_sysfs_mmio_match[] = {
	{ .compatible = "qemu,fw-cfg-mmio", },
	{},
};
MODULE_DEVICE_TABLE(of, fw_cfg_sysfs_mmio_match);

#ifdef CONFIG_ACPI
static const struct acpi_device_id fw_cfg_sysfs_acpi_match[] = {
	{ FW_CFG_ACPI_DEVICE_ID, },
	{},
};
MODULE_DEVICE_TABLE(acpi, fw_cfg_sysfs_acpi_match);
#endif

static struct platform_driver fw_cfg_sysfs_driver = {
	.probe = fw_cfg_sysfs_probe,
	.remove = fw_cfg_sysfs_remove,
	.driver = {
		.name = "fw_cfg",
		.of_match_table = fw_cfg_sysfs_mmio_match,
		.acpi_match_table = ACPI_PTR(fw_cfg_sysfs_acpi_match),
	},
};

#ifdef CONFIG_FW_CFG_SYSFS_CMDLINE

static struct platform_device *fw_cfg_cmdline_dev;

/* this probably belongs in e.g. include/linux/types.h,
 * but right now we are the only ones doing it...
 */
#ifdef CONFIG_PHYS_ADDR_T_64BIT
#define __PHYS_ADDR_PREFIX "ll"
#else
#define __PHYS_ADDR_PREFIX ""
#endif

/* use special scanf/printf modifier for phys_addr_t, resource_size_t */
#define PH_ADDR_SCAN_FMT "@%" __PHYS_ADDR_PREFIX "i%n" \
			 ":%" __PHYS_ADDR_PREFIX "i" \
			 ":%" __PHYS_ADDR_PREFIX "i%n" \
			 ":%" __PHYS_ADDR_PREFIX "i%n"

#define PH_ADDR_PR_1_FMT "0x%" __PHYS_ADDR_PREFIX "x@" \
			 "0x%" __PHYS_ADDR_PREFIX "x"

#define PH_ADDR_PR_3_FMT PH_ADDR_PR_1_FMT \
			 ":%" __PHYS_ADDR_PREFIX "u" \
			 ":%" __PHYS_ADDR_PREFIX "u"

#define PH_ADDR_PR_4_FMT PH_ADDR_PR_3_FMT \
			 ":%" __PHYS_ADDR_PREFIX "u"

static int fw_cfg_cmdline_set(const char *arg, const struct kernel_param *kp)
{
	struct resource res[4] = {};
	char *str;
	phys_addr_t base;
	resource_size_t size, ctrl_off, data_off, dma_off;
	int processed, consumed = 0;

	/* only one fw_cfg device can exist system-wide, so if one
	 * was processed on the command line already, we might as
	 * well stop here.
	 */
	if (fw_cfg_cmdline_dev) {
		/* avoid leaking previously registered device */
		platform_device_unregister(fw_cfg_cmdline_dev);
		return -EINVAL;
	}

	/* consume "<size>" portion of command line argument */
	size = memparse(arg, &str);

	/* get "@<base>[:<ctrl_off>:<data_off>[:<dma_off>]]" chunks */
	processed = sscanf(str, PH_ADDR_SCAN_FMT,
			   &base, &consumed,
			   &ctrl_off, &data_off, &consumed,
			   &dma_off, &consumed);

	/* sscanf() must process precisely 1, 3 or 4 chunks:
	 * <base> is mandatory, optionally followed by <ctrl_off>
	 * and <data_off>, and <dma_off>;
	 * there must be no extra characters after the last chunk,
	 * so str[consumed] must be '\0'.
	 */
	if (str[consumed] ||
	    (processed != 1 && processed != 3 && processed != 4))
		return -EINVAL;

	res[0].start = base;
	res[0].end = base + size - 1;
	res[0].flags = !strcmp(kp->name, "mmio") ? IORESOURCE_MEM :
						   IORESOURCE_IO;

	/* insert register offsets, if provided */
	if (processed > 1) {
		res[1].name = "ctrl";
		res[1].start = ctrl_off;
		res[1].flags = IORESOURCE_REG;
		res[2].name = "data";
		res[2].start = data_off;
		res[2].flags = IORESOURCE_REG;
	}
	if (processed > 3) {
		res[3].name = "dma";
		res[3].start = dma_off;
		res[3].flags = IORESOURCE_REG;
	}

	/* "processed" happens to nicely match the number of resources
	 * we need to pass in to this platform device.
	 */
	fw_cfg_cmdline_dev = platform_device_register_simple("fw_cfg",
					PLATFORM_DEVID_NONE, res, processed);

	return PTR_ERR_OR_ZERO(fw_cfg_cmdline_dev);
}

static int fw_cfg_cmdline_get(char *buf, const struct kernel_param *kp)
{
	/* stay silent if device was not configured via the command
	 * line, or if the parameter name (ioport/mmio) doesn't match
	 * the device setting
	 */
	if (!fw_cfg_cmdline_dev ||
	    (!strcmp(kp->name, "mmio") ^
	     (fw_cfg_cmdline_dev->resource[0].flags == IORESOURCE_MEM)))
		return 0;

	switch (fw_cfg_cmdline_dev->num_resources) {
	case 1:
		return snprintf(buf, PAGE_SIZE, PH_ADDR_PR_1_FMT,
				resource_size(&fw_cfg_cmdline_dev->resource[0]),
				fw_cfg_cmdline_dev->resource[0].start);
	case 3:
		return snprintf(buf, PAGE_SIZE, PH_ADDR_PR_3_FMT,
				resource_size(&fw_cfg_cmdline_dev->resource[0]),
				fw_cfg_cmdline_dev->resource[0].start,
				fw_cfg_cmdline_dev->resource[1].start,
				fw_cfg_cmdline_dev->resource[2].start);
	case 4:
		return snprintf(buf, PAGE_SIZE, PH_ADDR_PR_4_FMT,
				resource_size(&fw_cfg_cmdline_dev->resource[0]),
				fw_cfg_cmdline_dev->resource[0].start,
				fw_cfg_cmdline_dev->resource[1].start,
				fw_cfg_cmdline_dev->resource[2].start,
				fw_cfg_cmdline_dev->resource[3].start);
	}

	/* Should never get here */
	WARN(1, "Unexpected number of resources: %d\n",
		fw_cfg_cmdline_dev->num_resources);
	return 0;
}

static const struct kernel_param_ops fw_cfg_cmdline_param_ops = {
	.set = fw_cfg_cmdline_set,
	.get = fw_cfg_cmdline_get,
};

device_param_cb(ioport, &fw_cfg_cmdline_param_ops, NULL, S_IRUSR);
device_param_cb(mmio, &fw_cfg_cmdline_param_ops, NULL, S_IRUSR);

#endif /* CONFIG_FW_CFG_SYSFS_CMDLINE */

static int __init fw_cfg_sysfs_init(void)
{
	int ret;

	/* create /sys/firmware/qemu_fw_cfg/ top level directory */
	fw_cfg_top_ko = kobject_create_and_add("qemu_fw_cfg", firmware_kobj);
	if (!fw_cfg_top_ko)
		return -ENOMEM;

	ret = platform_driver_register(&fw_cfg_sysfs_driver);
	if (ret)
		fw_cfg_kobj_cleanup(fw_cfg_top_ko);

	return ret;
}

static void __exit fw_cfg_sysfs_exit(void)
{
	platform_driver_unregister(&fw_cfg_sysfs_driver);

#ifdef CONFIG_FW_CFG_SYSFS_CMDLINE
	platform_device_unregister(fw_cfg_cmdline_dev);
#endif

	/* clean up /sys/firmware/qemu_fw_cfg/ */
	fw_cfg_kobj_cleanup(fw_cfg_top_ko);
}

module_init(fw_cfg_sysfs_init);
module_exit(fw_cfg_sysfs_exit);