summaryrefslogtreecommitdiffstats
path: root/arch/arm64/kernel/acpi.c
blob: f3851724fe35611eb9d113e9e4aec6ee395b456f (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 *  ARM64 Specific Low-Level ACPI Boot Support
 *
 *  Copyright (C) 2013-2014, Linaro Ltd.
 *	Author: Al Stone <al.stone@linaro.org>
 *	Author: Graeme Gregory <graeme.gregory@linaro.org>
 *	Author: Hanjun Guo <hanjun.guo@linaro.org>
 *	Author: Tomasz Nowicki <tomasz.nowicki@linaro.org>
 *	Author: Naresh Bhat <naresh.bhat@linaro.org>
 */

#define pr_fmt(fmt) "ACPI: " fmt

#include <linux/acpi.h>
#include <linux/cpumask.h>
#include <linux/efi.h>
#include <linux/efi-bgrt.h>
#include <linux/init.h>
#include <linux/irq.h>
#include <linux/irqdomain.h>
#include <linux/irq_work.h>
#include <linux/memblock.h>
#include <linux/of_fdt.h>
#include <linux/smp.h>
#include <linux/serial_core.h>
#include <linux/pgtable.h>

#include <acpi/ghes.h>
#include <asm/cputype.h>
#include <asm/cpu_ops.h>
#include <asm/daifflags.h>
#include <asm/smp_plat.h>

int acpi_noirq = 1;		/* skip ACPI IRQ initialization */
int acpi_disabled = 1;
EXPORT_SYMBOL(acpi_disabled);

int acpi_pci_disabled = 1;	/* skip ACPI PCI scan and IRQ initialization */
EXPORT_SYMBOL(acpi_pci_disabled);

static bool param_acpi_off __initdata;
static bool param_acpi_on __initdata;
static bool param_acpi_force __initdata;

static int __init parse_acpi(char *arg)
{
	if (!arg)
		return -EINVAL;

	/* "acpi=off" disables both ACPI table parsing and interpreter */
	if (strcmp(arg, "off") == 0)
		param_acpi_off = true;
	else if (strcmp(arg, "on") == 0) /* prefer ACPI over DT */
		param_acpi_on = true;
	else if (strcmp(arg, "force") == 0) /* force ACPI to be enabled */
		param_acpi_force = true;
	else
		return -EINVAL;	/* Core will print when we return error */

	return 0;
}
early_param("acpi", parse_acpi);

static int __init dt_scan_depth1_nodes(unsigned long node,
				       const char *uname, int depth,
				       void *data)
{
	/*
	 * Ignore anything not directly under the root node; we'll
	 * catch its parent instead.
	 */
	if (depth != 1)
		return 0;

	if (strcmp(uname, "chosen") == 0)
		return 0;

	if (strcmp(uname, "hypervisor") == 0 &&
	    of_flat_dt_is_compatible(node, "xen,xen"))
		return 0;

	/*
	 * This node at depth 1 is neither a chosen node nor a xen node,
	 * which we do not expect.
	 */
	return 1;
}

/*
 * __acpi_map_table() will be called before page_init(), so early_ioremap()
 * or early_memremap() should be called here to for ACPI table mapping.
 */
void __init __iomem *__acpi_map_table(unsigned long phys, unsigned long size)
{
	if (!size)
		return NULL;

	return early_memremap(phys, size);
}

void __init __acpi_unmap_table(void __iomem *map, unsigned long size)
{
	if (!map || !size)
		return;

	early_memunmap(map, size);
}

bool __init acpi_psci_present(void)
{
	return acpi_gbl_FADT.arm_boot_flags & ACPI_FADT_PSCI_COMPLIANT;
}

/* Whether HVC must be used instead of SMC as the PSCI conduit */
bool acpi_psci_use_hvc(void)
{
	return acpi_gbl_FADT.arm_boot_flags & ACPI_FADT_PSCI_USE_HVC;
}

/*
 * acpi_fadt_sanity_check() - Check FADT presence and carry out sanity
 *			      checks on it
 *
 * Return 0 on success,  <0 on failure
 */
static int __init acpi_fadt_sanity_check(void)
{
	struct acpi_table_header *table;
	struct acpi_table_fadt *fadt;
	acpi_status status;
	int ret = 0;

	/*
	 * FADT is required on arm64; retrieve it to check its presence
	 * and carry out revision and ACPI HW reduced compliancy tests
	 */
	status = acpi_get_table(ACPI_SIG_FADT, 0, &table);
	if (ACPI_FAILURE(status)) {
		const char *msg = acpi_format_exception(status);

		pr_err("Failed to get FADT table, %s\n", msg);
		return -ENODEV;
	}

	fadt = (struct acpi_table_fadt *)table;

	/*
	 * Revision in table header is the FADT Major revision, and there
	 * is a minor revision of FADT which was introduced by ACPI 5.1,
	 * we only deal with ACPI 5.1 or newer revision to get GIC and SMP
	 * boot protocol configuration data.
	 */
	if (table->revision < 5 ||
	   (table->revision == 5 && fadt->minor_revision < 1)) {
		pr_err(FW_BUG "Unsupported FADT revision %d.%d, should be 5.1+\n",
		       table->revision, fadt->minor_revision);

		if (!fadt->arm_boot_flags) {
			ret = -EINVAL;
			goto out;
		}
		pr_err("FADT has ARM boot flags set, assuming 5.1\n");
	}

	if (!(fadt->flags & ACPI_FADT_HW_REDUCED)) {
		pr_err("FADT not ACPI hardware reduced compliant\n");
		ret = -EINVAL;
	}

out:
	/*
	 * acpi_get_table() creates FADT table mapping that
	 * should be released after parsing and before resuming boot
	 */
	acpi_put_table(table);
	return ret;
}

/*
 * acpi_boot_table_init() called from setup_arch(), always.
 *	1. find RSDP and get its address, and then find XSDT
 *	2. extract all tables and checksums them all
 *	3. check ACPI FADT revision
 *	4. check ACPI FADT HW reduced flag
 *
 * We can parse ACPI boot-time tables such as MADT after
 * this function is called.
 *
 * On return ACPI is enabled if either:
 *
 * - ACPI tables are initialized and sanity checks passed
 * - acpi=force was passed in the command line and ACPI was not disabled
 *   explicitly through acpi=off command line parameter
 *
 * ACPI is disabled on function return otherwise
 */
void __init acpi_boot_table_init(void)
{
	/*
	 * Enable ACPI instead of device tree unless
	 * - ACPI has been disabled explicitly (acpi=off), or
	 * - the device tree is not empty (it has more than just a /chosen node,
	 *   and a /hypervisor node when running on Xen)
	 *   and ACPI has not been [force] enabled (acpi=on|force)
	 */
	if (param_acpi_off ||
	    (!param_acpi_on && !param_acpi_force &&
	     of_scan_flat_dt(dt_scan_depth1_nodes, NULL)))
		goto done;

	/*
	 * ACPI is disabled at this point. Enable it in order to parse
	 * the ACPI tables and carry out sanity checks
	 */
	enable_acpi();

	/*
	 * If ACPI tables are initialized and FADT sanity checks passed,
	 * leave ACPI enabled and carry on booting; otherwise disable ACPI
	 * on initialization error.
	 * If acpi=force was passed on the command line it forces ACPI
	 * to be enabled even if its initialization failed.
	 */
	if (acpi_table_init() || acpi_fadt_sanity_check()) {
		pr_err("Failed to init ACPI tables\n");
		if (!param_acpi_force)
			disable_acpi();
	}

done:
	if (acpi_disabled) {
		if (earlycon_acpi_spcr_enable)
			early_init_dt_scan_chosen_stdout();
	} else {
		acpi_parse_spcr(earlycon_acpi_spcr_enable, true);
		if (IS_ENABLED(CONFIG_ACPI_BGRT))
			acpi_table_parse(ACPI_SIG_BGRT, acpi_parse_bgrt);
	}
}

static pgprot_t __acpi_get_writethrough_mem_attribute(void)
{
	/*
	 * Although UEFI specifies the use of Normal Write-through for
	 * EFI_MEMORY_WT, it is seldom used in practice and not implemented
	 * by most (all?) CPUs. Rather than allocate a MAIR just for this
	 * purpose, emit a warning and use Normal Non-cacheable instead.
	 */
	pr_warn_once("No MAIR allocation for EFI_MEMORY_WT; treating as Normal Non-cacheable\n");
	return __pgprot(PROT_NORMAL_NC);
}

pgprot_t __acpi_get_mem_attribute(phys_addr_t addr)
{
	/*
	 * According to "Table 8 Map: EFI memory types to AArch64 memory
	 * types" of UEFI 2.5 section 2.3.6.1, each EFI memory type is
	 * mapped to a corresponding MAIR attribute encoding.
	 * The EFI memory attribute advises all possible capabilities
	 * of a memory region.
	 */

	u64 attr;

	attr = efi_mem_attributes(addr);
	if (attr & EFI_MEMORY_WB)
		return PAGE_KERNEL;
	if (attr & EFI_MEMORY_WC)
		return __pgprot(PROT_NORMAL_NC);
	if (attr & EFI_MEMORY_WT)
		return __acpi_get_writethrough_mem_attribute();
	return __pgprot(PROT_DEVICE_nGnRnE);
}

void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size)
{
	efi_memory_desc_t *md, *region = NULL;
	pgprot_t prot;

	if (WARN_ON_ONCE(!efi_enabled(EFI_MEMMAP)))
		return NULL;

	for_each_efi_memory_desc(md) {
		u64 end = md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT);

		if (phys < md->phys_addr || phys >= end)
			continue;

		if (phys + size > end) {
			pr_warn(FW_BUG "requested region covers multiple EFI memory regions\n");
			return NULL;
		}
		region = md;
		break;
	}

	/*
	 * It is fine for AML to remap regions that are not represented in the
	 * EFI memory map at all, as it only describes normal memory, and MMIO
	 * regions that require a virtual mapping to make them accessible to
	 * the EFI runtime services.
	 */
	prot = __pgprot(PROT_DEVICE_nGnRnE);
	if (region) {
		switch (region->type) {
		case EFI_LOADER_CODE:
		case EFI_LOADER_DATA:
		case EFI_BOOT_SERVICES_CODE:
		case EFI_BOOT_SERVICES_DATA:
		case EFI_CONVENTIONAL_MEMORY:
		case EFI_PERSISTENT_MEMORY:
			if (memblock_is_map_memory(phys) ||
			    !memblock_is_region_memory(phys, size)) {
				pr_warn(FW_BUG "requested region covers kernel memory @ %pa\n", &phys);
				return NULL;
			}
			/*
			 * Mapping kernel memory is permitted if the region in
			 * question is covered by a single memblock with the
			 * NOMAP attribute set: this enables the use of ACPI
			 * table overrides passed via initramfs, which are
			 * reserved in memory using arch_reserve_mem_area()
			 * below. As this particular use case only requires
			 * read access, fall through to the R/O mapping case.
			 */
			fallthrough;

		case EFI_RUNTIME_SERVICES_CODE:
			/*
			 * This would be unusual, but not problematic per se,
			 * as long as we take care not to create a writable
			 * mapping for executable code.
			 */
			prot = PAGE_KERNEL_RO;
			break;

		case EFI_ACPI_RECLAIM_MEMORY:
			/*
			 * ACPI reclaim memory is used to pass firmware tables
			 * and other data that is intended for consumption by
			 * the OS only, which may decide it wants to reclaim
			 * that memory and use it for something else. We never
			 * do that, but we usually add it to the linear map
			 * anyway, in which case we should use the existing
			 * mapping.
			 */
			if (memblock_is_map_memory(phys))
				return (void __iomem *)__phys_to_virt(phys);
			fallthrough;

		default:
			if (region->attribute & EFI_MEMORY_WB)
				prot = PAGE_KERNEL;
			else if (region->attribute & EFI_MEMORY_WC)
				prot = __pgprot(PROT_NORMAL_NC);
			else if (region->attribute & EFI_MEMORY_WT)
				prot = __acpi_get_writethrough_mem_attribute();
		}
	}
	return __ioremap(phys, size, prot);
}

/*
 * Claim Synchronous External Aborts as a firmware first notification.
 *
 * Used by KVM and the arch do_sea handler.
 * @regs may be NULL when called from process context.
 */
int apei_claim_sea(struct pt_regs *regs)
{
	int err = -ENOENT;
	bool return_to_irqs_enabled;
	unsigned long current_flags;

	if (!IS_ENABLED(CONFIG_ACPI_APEI_GHES))
		return err;

	current_flags = local_daif_save_flags();

	/* current_flags isn't useful here as daif doesn't tell us about pNMI */
	return_to_irqs_enabled = !irqs_disabled_flags(arch_local_save_flags());

	if (regs)
		return_to_irqs_enabled = interrupts_enabled(regs);

	/*
	 * SEA can interrupt SError, mask it and describe this as an NMI so
	 * that APEI defers the handling.
	 */
	local_daif_restore(DAIF_ERRCTX);
	nmi_enter();
	err = ghes_notify_sea();
	nmi_exit();

	/*
	 * APEI NMI-like notifications are deferred to irq_work. Unless
	 * we interrupted irqs-masked code, we can do that now.
	 */
	if (!err) {
		if (return_to_irqs_enabled) {
			local_daif_restore(DAIF_PROCCTX_NOIRQ);
			__irq_enter();
			irq_work_run();
			__irq_exit();
		} else {
			pr_warn_ratelimited("APEI work queued but not completed");
			err = -EINPROGRESS;
		}
	}

	local_daif_restore(current_flags);

	return err;
}

void arch_reserve_mem_area(acpi_physical_address addr, size_t size)
{
	memblock_mark_nomap(addr, size);
}