summaryrefslogtreecommitdiffstats
path: root/arch/x86/platform/efi/quirks.c
blob: cdfe8c62895981029b8f69218b717b05d0b8961a (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
#define pr_fmt(fmt) "efi: " fmt

#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/time.h>
#include <linux/types.h>
#include <linux/efi.h>
#include <linux/slab.h>
#include <linux/memblock.h>
#include <linux/bootmem.h>
#include <linux/acpi.h>
#include <linux/dmi.h>
#include <asm/efi.h>
#include <asm/uv/uv.h>

#define EFI_MIN_RESERVE 5120

#define EFI_DUMMY_GUID \
	EFI_GUID(0x4424ac57, 0xbe4b, 0x47dd, 0x9e, 0x97, 0xed, 0x50, 0xf0, 0x9f, 0x92, 0xa9)

static efi_char16_t efi_dummy_name[6] = { 'D', 'U', 'M', 'M', 'Y', 0 };

static bool efi_no_storage_paranoia;

/*
 * Some firmware implementations refuse to boot if there's insufficient
 * space in the variable store. The implementation of garbage collection
 * in some FW versions causes stale (deleted) variables to take up space
 * longer than intended and space is only freed once the store becomes
 * almost completely full.
 *
 * Enabling this option disables the space checks in
 * efi_query_variable_store() and forces garbage collection.
 *
 * Only enable this option if deleting EFI variables does not free up
 * space in your variable store, e.g. if despite deleting variables
 * you're unable to create new ones.
 */
static int __init setup_storage_paranoia(char *arg)
{
	efi_no_storage_paranoia = true;
	return 0;
}
early_param("efi_no_storage_paranoia", setup_storage_paranoia);

/*
 * Deleting the dummy variable which kicks off garbage collection
*/
void efi_delete_dummy_variable(void)
{
	efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID,
			 EFI_VARIABLE_NON_VOLATILE |
			 EFI_VARIABLE_BOOTSERVICE_ACCESS |
			 EFI_VARIABLE_RUNTIME_ACCESS,
			 0, NULL);
}

/*
 * In the nonblocking case we do not attempt to perform garbage
 * collection if we do not have enough free space. Rather, we do the
 * bare minimum check and give up immediately if the available space
 * is below EFI_MIN_RESERVE.
 *
 * This function is intended to be small and simple because it is
 * invoked from crash handler paths.
 */
static efi_status_t
query_variable_store_nonblocking(u32 attributes, unsigned long size)
{
	efi_status_t status;
	u64 storage_size, remaining_size, max_size;

	status = efi.query_variable_info_nonblocking(attributes, &storage_size,
						     &remaining_size,
						     &max_size);
	if (status != EFI_SUCCESS)
		return status;

	if (remaining_size - size < EFI_MIN_RESERVE)
		return EFI_OUT_OF_RESOURCES;

	return EFI_SUCCESS;
}

/*
 * Some firmware implementations refuse to boot if there's insufficient space
 * in the variable store. Ensure that we never use more than a safe limit.
 *
 * Return EFI_SUCCESS if it is safe to write 'size' bytes to the variable
 * store.
 */
efi_status_t efi_query_variable_store(u32 attributes, unsigned long size,
				      bool nonblocking)
{
	efi_status_t status;
	u64 storage_size, remaining_size, max_size;

	if (!(attributes & EFI_VARIABLE_NON_VOLATILE))
		return 0;

	if (nonblocking)
		return query_variable_store_nonblocking(attributes, size);

	status = efi.query_variable_info(attributes, &storage_size,
					 &remaining_size, &max_size);
	if (status != EFI_SUCCESS)
		return status;

	/*
	 * We account for that by refusing the write if permitting it would
	 * reduce the available space to under 5KB. This figure was provided by
	 * Samsung, so should be safe.
	 */
	if ((remaining_size - size < EFI_MIN_RESERVE) &&
		!efi_no_storage_paranoia) {

		/*
		 * Triggering garbage collection may require that the firmware
		 * generate a real EFI_OUT_OF_RESOURCES error. We can force
		 * that by attempting to use more space than is available.
		 */
		unsigned long dummy_size = remaining_size + 1024;
		void *dummy = kzalloc(dummy_size, GFP_ATOMIC);

		if (!dummy)
			return EFI_OUT_OF_RESOURCES;

		status = efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID,
					  EFI_VARIABLE_NON_VOLATILE |
					  EFI_VARIABLE_BOOTSERVICE_ACCESS |
					  EFI_VARIABLE_RUNTIME_ACCESS,
					  dummy_size, dummy);

		if (status == EFI_SUCCESS) {
			/*
			 * This should have failed, so if it didn't make sure
			 * that we delete it...
			 */
			efi_delete_dummy_variable();
		}

		kfree(dummy);

		/*
		 * The runtime code may now have triggered a garbage collection
		 * run, so check the variable info again
		 */
		status = efi.query_variable_info(attributes, &storage_size,
						 &remaining_size, &max_size);

		if (status != EFI_SUCCESS)
			return status;

		/*
		 * There still isn't enough room, so return an error
		 */
		if (remaining_size - size < EFI_MIN_RESERVE)
			return EFI_OUT_OF_RESOURCES;
	}

	return EFI_SUCCESS;
}
EXPORT_SYMBOL_GPL(efi_query_variable_store);

/*
 * The UEFI specification makes it clear that the operating system is
 * free to do whatever it wants with boot services code after
 * ExitBootServices() has been called. Ignoring this recommendation a
 * significant bunch of EFI implementations continue calling into boot
 * services code (SetVirtualAddressMap). In order to work around such
 * buggy implementations we reserve boot services region during EFI
 * init and make sure it stays executable. Then, after
 * SetVirtualAddressMap(), it is discarded.
 *
 * However, some boot services regions contain data that is required
 * by drivers, so we need to track which memory ranges can never be
 * freed. This is done by tagging those regions with the
 * EFI_MEMORY_RUNTIME attribute.
 *
 * Any driver that wants to mark a region as reserved must use
 * efi_mem_reserve() which will insert a new EFI memory descriptor
 * into efi.memmap (splitting existing regions if necessary) and tag
 * it with EFI_MEMORY_RUNTIME.
 */
void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size)
{
	phys_addr_t new_phys, new_size;
	struct efi_mem_range mr;
	efi_memory_desc_t md;
	int num_entries;
	void *new;

	if (efi_mem_desc_lookup(addr, &md)) {
		pr_err("Failed to lookup EFI memory descriptor for %pa\n", &addr);
		return;
	}

	if (addr + size > md.phys_addr + (md.num_pages << EFI_PAGE_SHIFT)) {
		pr_err("Region spans EFI memory descriptors, %pa\n", &addr);
		return;
	}

	/* No need to reserve regions that will never be freed. */
	if (md.attribute & EFI_MEMORY_RUNTIME)
		return;

	size += addr % EFI_PAGE_SIZE;
	size = round_up(size, EFI_PAGE_SIZE);
	addr = round_down(addr, EFI_PAGE_SIZE);

	mr.range.start = addr;
	mr.range.end = addr + size - 1;
	mr.attribute = md.attribute | EFI_MEMORY_RUNTIME;

	num_entries = efi_memmap_split_count(&md, &mr.range);
	num_entries += efi.memmap.nr_map;

	new_size = efi.memmap.desc_size * num_entries;

	new_phys = efi_memmap_alloc(num_entries);
	if (!new_phys) {
		pr_err("Could not allocate boot services memmap\n");
		return;
	}

	new = early_memremap(new_phys, new_size);
	if (!new) {
		pr_err("Failed to map new boot services memmap\n");
		return;
	}

	efi_memmap_insert(&efi.memmap, new, &mr);
	early_memunmap(new, new_size);

	efi_memmap_install(new_phys, num_entries);
}

/*
 * Helper function for efi_reserve_boot_services() to figure out if we
 * can free regions in efi_free_boot_services().
 *
 * Use this function to ensure we do not free regions owned by somebody
 * else. We must only reserve (and then free) regions:
 *
 * - Not within any part of the kernel
 * - Not the BIOS reserved area (E820_RESERVED, E820_NVS, etc)
 */
static bool can_free_region(u64 start, u64 size)
{
	if (start + size > __pa_symbol(_text) && start <= __pa_symbol(_end))
		return false;

	if (!e820_all_mapped(start, start+size, E820_RAM))
		return false;

	return true;
}

void __init efi_reserve_boot_services(void)
{
	efi_memory_desc_t *md;

	for_each_efi_memory_desc(md) {
		u64 start = md->phys_addr;
		u64 size = md->num_pages << EFI_PAGE_SHIFT;
		bool already_reserved;

		if (md->type != EFI_BOOT_SERVICES_CODE &&
		    md->type != EFI_BOOT_SERVICES_DATA)
			continue;

		already_reserved = memblock_is_region_reserved(start, size);

		/*
		 * Because the following memblock_reserve() is paired
		 * with free_bootmem_late() for this region in
		 * efi_free_boot_services(), we must be extremely
		 * careful not to reserve, and subsequently free,
		 * critical regions of memory (like the kernel image) or
		 * those regions that somebody else has already
		 * reserved.
		 *
		 * A good example of a critical region that must not be
		 * freed is page zero (first 4Kb of memory), which may
		 * contain boot services code/data but is marked
		 * E820_RESERVED by trim_bios_range().
		 */
		if (!already_reserved) {
			memblock_reserve(start, size);

			/*
			 * If we are the first to reserve the region, no
			 * one else cares about it. We own it and can
			 * free it later.
			 */
			if (can_free_region(start, size))
				continue;
		}

		/*
		 * We don't own the region. We must not free it.
		 *
		 * Setting this bit for a boot services region really
		 * doesn't make sense as far as the firmware is
		 * concerned, but it does provide us with a way to tag
		 * those regions that must not be paired with
		 * free_bootmem_late().
		 */
		md->attribute |= EFI_MEMORY_RUNTIME;
	}
}

void __init efi_free_boot_services(void)
{
	phys_addr_t new_phys, new_size;
	efi_memory_desc_t *md;
	int num_entries = 0;
	void *new, *new_md;

	for_each_efi_memory_desc(md) {
		unsigned long long start = md->phys_addr;
		unsigned long long size = md->num_pages << EFI_PAGE_SHIFT;
		size_t rm_size;

		if (md->type != EFI_BOOT_SERVICES_CODE &&
		    md->type != EFI_BOOT_SERVICES_DATA) {
			num_entries++;
			continue;
		}

		/* Do not free, someone else owns it: */
		if (md->attribute & EFI_MEMORY_RUNTIME) {
			num_entries++;
			continue;
		}

		/*
		 * Nasty quirk: if all sub-1MB memory is used for boot
		 * services, we can get here without having allocated the
		 * real mode trampoline.  It's too late to hand boot services
		 * memory back to the memblock allocator, so instead
		 * try to manually allocate the trampoline if needed.
		 *
		 * I've seen this on a Dell XPS 13 9350 with firmware
		 * 1.4.4 with SGX enabled booting Linux via Fedora 24's
		 * grub2-efi on a hard disk.  (And no, I don't know why
		 * this happened, but Linux should still try to boot rather
		 * panicing early.)
		 */
		rm_size = real_mode_size_needed();
		if (rm_size && (start + rm_size) < (1<<20) && size >= rm_size) {
			set_real_mode_mem(start, rm_size);
			start += rm_size;
			size -= rm_size;
		}

		free_bootmem_late(start, size);
	}

	new_size = efi.memmap.desc_size * num_entries;
	new_phys = efi_memmap_alloc(num_entries);
	if (!new_phys) {
		pr_err("Failed to allocate new EFI memmap\n");
		return;
	}

	new = memremap(new_phys, new_size, MEMREMAP_WB);
	if (!new) {
		pr_err("Failed to map new EFI memmap\n");
		return;
	}

	/*
	 * Build a new EFI memmap that excludes any boot services
	 * regions that are not tagged EFI_MEMORY_RUNTIME, since those
	 * regions have now been freed.
	 */
	new_md = new;
	for_each_efi_memory_desc(md) {
		if (!(md->attribute & EFI_MEMORY_RUNTIME) &&
		    (md->type == EFI_BOOT_SERVICES_CODE ||
		     md->type == EFI_BOOT_SERVICES_DATA))
			continue;

		memcpy(new_md, md, efi.memmap.desc_size);
		new_md += efi.memmap.desc_size;
	}

	memunmap(new);

	if (efi_memmap_install(new_phys, num_entries)) {
		pr_err("Could not install new EFI memmap\n");
		return;
	}
}

/*
 * A number of config table entries get remapped to virtual addresses
 * after entering EFI virtual mode. However, the kexec kernel requires
 * their physical addresses therefore we pass them via setup_data and
 * correct those entries to their respective physical addresses here.
 *
 * Currently only handles smbios which is necessary for some firmware
 * implementation.
 */
int __init efi_reuse_config(u64 tables, int nr_tables)
{
	int i, sz, ret = 0;
	void *p, *tablep;
	struct efi_setup_data *data;

	if (!efi_setup)
		return 0;

	if (!efi_enabled(EFI_64BIT))
		return 0;

	data = early_memremap(efi_setup, sizeof(*data));
	if (!data) {
		ret = -ENOMEM;
		goto out;
	}

	if (!data->smbios)
		goto out_memremap;

	sz = sizeof(efi_config_table_64_t);

	p = tablep = early_memremap(tables, nr_tables * sz);
	if (!p) {
		pr_err("Could not map Configuration table!\n");
		ret = -ENOMEM;
		goto out_memremap;
	}

	for (i = 0; i < efi.systab->nr_tables; i++) {
		efi_guid_t guid;

		guid = ((efi_config_table_64_t *)p)->guid;

		if (!efi_guidcmp(guid, SMBIOS_TABLE_GUID))
			((efi_config_table_64_t *)p)->table = data->smbios;
		p += sz;
	}
	early_memunmap(tablep, nr_tables * sz);

out_memremap:
	early_memunmap(data, sizeof(*data));
out:
	return ret;
}

static const struct dmi_system_id sgi_uv1_dmi[] = {
	{ NULL, "SGI UV1",
		{	DMI_MATCH(DMI_PRODUCT_NAME,	"Stoutland Platform"),
			DMI_MATCH(DMI_PRODUCT_VERSION,	"1.0"),
			DMI_MATCH(DMI_BIOS_VENDOR,	"SGI.COM"),
		}
	},
	{ } /* NULL entry stops DMI scanning */
};

void __init efi_apply_memmap_quirks(void)
{
	/*
	 * Once setup is done earlier, unmap the EFI memory map on mismatched
	 * firmware/kernel architectures since there is no support for runtime
	 * services.
	 */
	if (!efi_runtime_supported()) {
		pr_info("Setup done, disabling due to 32/64-bit mismatch\n");
		efi_memmap_unmap();
	}

	/* UV2+ BIOS has a fix for this issue.  UV1 still needs the quirk. */
	if (dmi_check_system(sgi_uv1_dmi))
		set_bit(EFI_OLD_MEMMAP, &efi.flags);
}

/*
 * For most modern platforms the preferred method of powering off is via
 * ACPI. However, there are some that are known to require the use of
 * EFI runtime services and for which ACPI does not work at all.
 *
 * Using EFI is a last resort, to be used only if no other option
 * exists.
 */
bool efi_reboot_required(void)
{
	if (!acpi_gbl_reduced_hardware)
		return false;

	efi_reboot_quirk_mode = EFI_RESET_WARM;
	return true;
}

bool efi_poweroff_required(void)
{
	return acpi_gbl_reduced_hardware || acpi_no_s5;
}