summaryrefslogtreecommitdiffstats
path: root/arch/arm64/kernel/setup.c
blob: 6bab21f84a9ff38402e70345016ed50ae8e95e30 (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
/*
 * Based on arch/arm/kernel/setup.c
 *
 * Copyright (C) 1995-2001 Russell King
 * Copyright (C) 2012 ARM Ltd.
 *
 * 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.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program.  If not, see <http://www.gnu.org/licenses/>.
 */

#include <linux/acpi.h>
#include <linux/export.h>
#include <linux/kernel.h>
#include <linux/stddef.h>
#include <linux/ioport.h>
#include <linux/delay.h>
#include <linux/utsname.h>
#include <linux/initrd.h>
#include <linux/console.h>
#include <linux/cache.h>
#include <linux/bootmem.h>
#include <linux/seq_file.h>
#include <linux/screen_info.h>
#include <linux/init.h>
#include <linux/kexec.h>
#include <linux/crash_dump.h>
#include <linux/root_dev.h>
#include <linux/cpu.h>
#include <linux/interrupt.h>
#include <linux/smp.h>
#include <linux/fs.h>
#include <linux/proc_fs.h>
#include <linux/memblock.h>
#include <linux/of_iommu.h>
#include <linux/of_fdt.h>
#include <linux/of_platform.h>
#include <linux/efi.h>
#include <linux/personality.h>
#include <linux/psci.h>

#include <asm/acpi.h>
#include <asm/fixmap.h>
#include <asm/cpu.h>
#include <asm/cputype.h>
#include <asm/elf.h>
#include <asm/cpufeature.h>
#include <asm/cpu_ops.h>
#include <asm/sections.h>
#include <asm/setup.h>
#include <asm/smp_plat.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
#include <asm/traps.h>
#include <asm/memblock.h>
#include <asm/efi.h>
#include <asm/xen/hypervisor.h>

unsigned long elf_hwcap __read_mostly;
EXPORT_SYMBOL_GPL(elf_hwcap);

#ifdef CONFIG_COMPAT
#define COMPAT_ELF_HWCAP_DEFAULT	\
				(COMPAT_HWCAP_HALF|COMPAT_HWCAP_THUMB|\
				 COMPAT_HWCAP_FAST_MULT|COMPAT_HWCAP_EDSP|\
				 COMPAT_HWCAP_TLS|COMPAT_HWCAP_VFP|\
				 COMPAT_HWCAP_VFPv3|COMPAT_HWCAP_VFPv4|\
				 COMPAT_HWCAP_NEON|COMPAT_HWCAP_IDIV|\
				 COMPAT_HWCAP_LPAE)
unsigned int compat_elf_hwcap __read_mostly = COMPAT_ELF_HWCAP_DEFAULT;
unsigned int compat_elf_hwcap2 __read_mostly;
#endif

DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS);

phys_addr_t __fdt_pointer __initdata;

/*
 * Standard memory resources
 */
static struct resource mem_res[] = {
	{
		.name = "Kernel code",
		.start = 0,
		.end = 0,
		.flags = IORESOURCE_MEM
	},
	{
		.name = "Kernel data",
		.start = 0,
		.end = 0,
		.flags = IORESOURCE_MEM
	}
};

#define kernel_code mem_res[0]
#define kernel_data mem_res[1]

/*
 * The recorded values of x0 .. x3 upon kernel entry.
 */
u64 __cacheline_aligned boot_args[4];

void __init smp_setup_processor_id(void)
{
	u64 mpidr = read_cpuid_mpidr() & MPIDR_HWID_BITMASK;
	cpu_logical_map(0) = mpidr;

	/*
	 * clear __my_cpu_offset on boot CPU to avoid hang caused by
	 * using percpu variable early, for example, lockdep will
	 * access percpu variable inside lock_release
	 */
	set_my_cpu_offset(0);
	pr_info("Booting Linux on physical CPU 0x%lx\n", (unsigned long)mpidr);
}

bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
{
	return phys_id == cpu_logical_map(cpu);
}

struct mpidr_hash mpidr_hash;
/**
 * smp_build_mpidr_hash - Pre-compute shifts required at each affinity
 *			  level in order to build a linear index from an
 *			  MPIDR value. Resulting algorithm is a collision
 *			  free hash carried out through shifting and ORing
 */
static void __init smp_build_mpidr_hash(void)
{
	u32 i, affinity, fs[4], bits[4], ls;
	u64 mask = 0;
	/*
	 * Pre-scan the list of MPIDRS and filter out bits that do
	 * not contribute to affinity levels, ie they never toggle.
	 */
	for_each_possible_cpu(i)
		mask |= (cpu_logical_map(i) ^ cpu_logical_map(0));
	pr_debug("mask of set bits %#llx\n", mask);
	/*
	 * Find and stash the last and first bit set at all affinity levels to
	 * check how many bits are required to represent them.
	 */
	for (i = 0; i < 4; i++) {
		affinity = MPIDR_AFFINITY_LEVEL(mask, i);
		/*
		 * Find the MSB bit and LSB bits position
		 * to determine how many bits are required
		 * to express the affinity level.
		 */
		ls = fls(affinity);
		fs[i] = affinity ? ffs(affinity) - 1 : 0;
		bits[i] = ls - fs[i];
	}
	/*
	 * An index can be created from the MPIDR_EL1 by isolating the
	 * significant bits at each affinity level and by shifting
	 * them in order to compress the 32 bits values space to a
	 * compressed set of values. This is equivalent to hashing
	 * the MPIDR_EL1 through shifting and ORing. It is a collision free
	 * hash though not minimal since some levels might contain a number
	 * of CPUs that is not an exact power of 2 and their bit
	 * representation might contain holes, eg MPIDR_EL1[7:0] = {0x2, 0x80}.
	 */
	mpidr_hash.shift_aff[0] = MPIDR_LEVEL_SHIFT(0) + fs[0];
	mpidr_hash.shift_aff[1] = MPIDR_LEVEL_SHIFT(1) + fs[1] - bits[0];
	mpidr_hash.shift_aff[2] = MPIDR_LEVEL_SHIFT(2) + fs[2] -
						(bits[1] + bits[0]);
	mpidr_hash.shift_aff[3] = MPIDR_LEVEL_SHIFT(3) +
				  fs[3] - (bits[2] + bits[1] + bits[0]);
	mpidr_hash.mask = mask;
	mpidr_hash.bits = bits[3] + bits[2] + bits[1] + bits[0];
	pr_debug("MPIDR hash: aff0[%u] aff1[%u] aff2[%u] aff3[%u] mask[%#llx] bits[%u]\n",
		mpidr_hash.shift_aff[0],
		mpidr_hash.shift_aff[1],
		mpidr_hash.shift_aff[2],
		mpidr_hash.shift_aff[3],
		mpidr_hash.mask,
		mpidr_hash.bits);
	/*
	 * 4x is an arbitrary value used to warn on a hash table much bigger
	 * than expected on most systems.
	 */
	if (mpidr_hash_size() > 4 * num_possible_cpus())
		pr_warn("Large number of MPIDR hash buckets detected\n");
	__flush_dcache_area(&mpidr_hash, sizeof(struct mpidr_hash));
}

static void __init setup_processor(void)
{
	u64 features;
	s64 block;
	u32 cwg;
	int cls;

	printk("CPU: AArch64 Processor [%08x] revision %d\n",
	       read_cpuid_id(), read_cpuid_id() & 15);

	sprintf(init_utsname()->machine, ELF_PLATFORM);
	elf_hwcap = 0;

	cpuinfo_store_boot_cpu();

	/*
	 * Check for sane CTR_EL0.CWG value.
	 */
	cwg = cache_type_cwg();
	cls = cache_line_size();
	if (!cwg)
		pr_warn("No Cache Writeback Granule information, assuming cache line size %d\n",
			cls);
	if (L1_CACHE_BYTES < cls)
		pr_warn("L1_CACHE_BYTES smaller than the Cache Writeback Granule (%d < %d)\n",
			L1_CACHE_BYTES, cls);

	/*
	 * ID_AA64ISAR0_EL1 contains 4-bit wide signed feature blocks.
	 * The blocks we test below represent incremental functionality
	 * for non-negative values. Negative values are reserved.
	 */
	features = read_cpuid(ID_AA64ISAR0_EL1);
	block = cpuid_feature_extract_field(features, 4);
	if (block > 0) {
		switch (block) {
		default:
		case 2:
			elf_hwcap |= HWCAP_PMULL;
		case 1:
			elf_hwcap |= HWCAP_AES;
		case 0:
			break;
		}
	}

	if (cpuid_feature_extract_field(features, 8) > 0)
		elf_hwcap |= HWCAP_SHA1;

	if (cpuid_feature_extract_field(features, 12) > 0)
		elf_hwcap |= HWCAP_SHA2;

	if (cpuid_feature_extract_field(features, 16) > 0)
		elf_hwcap |= HWCAP_CRC32;

	block = cpuid_feature_extract_field(features, 20);
	if (block > 0) {
		switch (block) {
		default:
		case 2:
			elf_hwcap |= HWCAP_ATOMICS;
		case 1:
			/* RESERVED */
		case 0:
			break;
		}
	}

#ifdef CONFIG_COMPAT
	/*
	 * ID_ISAR5_EL1 carries similar information as above, but pertaining to
	 * the AArch32 32-bit execution state.
	 */
	features = read_cpuid(ID_ISAR5_EL1);
	block = cpuid_feature_extract_field(features, 4);
	if (block > 0) {
		switch (block) {
		default:
		case 2:
			compat_elf_hwcap2 |= COMPAT_HWCAP2_PMULL;
		case 1:
			compat_elf_hwcap2 |= COMPAT_HWCAP2_AES;
		case 0:
			break;
		}
	}

	if (cpuid_feature_extract_field(features, 8) > 0)
		compat_elf_hwcap2 |= COMPAT_HWCAP2_SHA1;

	if (cpuid_feature_extract_field(features, 12) > 0)
		compat_elf_hwcap2 |= COMPAT_HWCAP2_SHA2;

	if (cpuid_feature_extract_field(features, 16) > 0)
		compat_elf_hwcap2 |= COMPAT_HWCAP2_CRC32;
#endif
}

static void __init setup_machine_fdt(phys_addr_t dt_phys)
{
	void *dt_virt = fixmap_remap_fdt(dt_phys);

	if (!dt_virt || !early_init_dt_scan(dt_virt)) {
		pr_crit("\n"
			"Error: invalid device tree blob at physical address %pa (virtual address 0x%p)\n"
			"The dtb must be 8-byte aligned and must not exceed 2 MB in size\n"
			"\nPlease check your bootloader.",
			&dt_phys, dt_virt);

		while (true)
			cpu_relax();
	}

	dump_stack_set_arch_desc("%s (DT)", of_flat_dt_get_machine_name());
}

static void __init request_standard_resources(void)
{
	struct memblock_region *region;
	struct resource *res;

	kernel_code.start   = virt_to_phys(_text);
	kernel_code.end     = virt_to_phys(_etext - 1);
	kernel_data.start   = virt_to_phys(_sdata);
	kernel_data.end     = virt_to_phys(_end - 1);

	for_each_memblock(memory, region) {
		res = alloc_bootmem_low(sizeof(*res));
		res->name  = "System RAM";
		res->start = __pfn_to_phys(memblock_region_memory_base_pfn(region));
		res->end = __pfn_to_phys(memblock_region_memory_end_pfn(region)) - 1;
		res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;

		request_resource(&iomem_resource, res);

		if (kernel_code.start >= res->start &&
		    kernel_code.end <= res->end)
			request_resource(res, &kernel_code);
		if (kernel_data.start >= res->start &&
		    kernel_data.end <= res->end)
			request_resource(res, &kernel_data);
	}
}

#ifdef CONFIG_BLK_DEV_INITRD
/*
 * Relocate initrd if it is not completely within the linear mapping.
 * This would be the case if mem= cuts out all or part of it.
 */
static void __init relocate_initrd(void)
{
	phys_addr_t orig_start = __virt_to_phys(initrd_start);
	phys_addr_t orig_end = __virt_to_phys(initrd_end);
	phys_addr_t ram_end = memblock_end_of_DRAM();
	phys_addr_t new_start;
	unsigned long size, to_free = 0;
	void *dest;

	if (orig_end <= ram_end)
		return;

	/*
	 * Any of the original initrd which overlaps the linear map should
	 * be freed after relocating.
	 */
	if (orig_start < ram_end)
		to_free = ram_end - orig_start;

	size = orig_end - orig_start;

	/* initrd needs to be relocated completely inside linear mapping */
	new_start = memblock_find_in_range(0, PFN_PHYS(max_pfn),
					   size, PAGE_SIZE);
	if (!new_start)
		panic("Cannot relocate initrd of size %ld\n", size);
	memblock_reserve(new_start, size);

	initrd_start = __phys_to_virt(new_start);
	initrd_end   = initrd_start + size;

	pr_info("Moving initrd from [%llx-%llx] to [%llx-%llx]\n",
		orig_start, orig_start + size - 1,
		new_start, new_start + size - 1);

	dest = (void *)initrd_start;

	if (to_free) {
		memcpy(dest, (void *)__phys_to_virt(orig_start), to_free);
		dest += to_free;
	}

	copy_from_early_mem(dest, orig_start + to_free, size - to_free);

	if (to_free) {
		pr_info("Freeing original RAMDISK from [%llx-%llx]\n",
			orig_start, orig_start + to_free - 1);
		memblock_free(orig_start, to_free);
	}
}
#else
static inline void __init relocate_initrd(void)
{
}
#endif

u64 __cpu_logical_map[NR_CPUS] = { [0 ... NR_CPUS-1] = INVALID_HWID };

void __init setup_arch(char **cmdline_p)
{
	setup_processor();

	init_mm.start_code = (unsigned long) _text;
	init_mm.end_code   = (unsigned long) _etext;
	init_mm.end_data   = (unsigned long) _edata;
	init_mm.brk	   = (unsigned long) _end;

	*cmdline_p = boot_command_line;

	early_fixmap_init();
	early_ioremap_init();

	setup_machine_fdt(__fdt_pointer);

	parse_early_param();

	/*
	 *  Unmask asynchronous aborts after bringing up possible earlycon.
	 * (Report possible System Errors once we can report this occurred)
	 */
	local_async_enable();

	efi_init();
	arm64_memblock_init();

	/* Parse the ACPI tables for possible boot-time configuration */
	acpi_boot_table_init();

	paging_init();
	relocate_initrd();
	request_standard_resources();

	early_ioremap_reset();

	if (acpi_disabled) {
		unflatten_device_tree();
		psci_dt_init();
	} else {
		psci_acpi_init();
	}
	xen_early_init();

	cpu_read_bootcpu_ops();
	smp_init_cpus();
	smp_build_mpidr_hash();

#ifdef CONFIG_VT
#if defined(CONFIG_VGA_CONSOLE)
	conswitchp = &vga_con;
#elif defined(CONFIG_DUMMY_CONSOLE)
	conswitchp = &dummy_con;
#endif
#endif
	if (boot_args[1] || boot_args[2] || boot_args[3]) {
		pr_err("WARNING: x1-x3 nonzero in violation of boot protocol:\n"
			"\tx1: %016llx\n\tx2: %016llx\n\tx3: %016llx\n"
			"This indicates a broken bootloader or old kernel\n",
			boot_args[1], boot_args[2], boot_args[3]);
	}
}

static int __init arm64_device_init(void)
{
	if (of_have_populated_dt()) {
		of_iommu_init();
		of_platform_populate(NULL, of_default_bus_match_table,
				     NULL, NULL);
	} else if (acpi_disabled) {
		pr_crit("Device tree not populated\n");
	}
	return 0;
}
arch_initcall_sync(arm64_device_init);

static int __init topology_init(void)
{
	int i;

	for_each_possible_cpu(i) {
		struct cpu *cpu = &per_cpu(cpu_data.cpu, i);
		cpu->hotpluggable = 1;
		register_cpu(cpu, i);
	}

	return 0;
}
subsys_initcall(topology_init);

static const char *hwcap_str[] = {
	"fp",
	"asimd",
	"evtstrm",
	"aes",
	"pmull",
	"sha1",
	"sha2",
	"crc32",
	"atomics",
	NULL
};

#ifdef CONFIG_COMPAT
static const char *compat_hwcap_str[] = {
	"swp",
	"half",
	"thumb",
	"26bit",
	"fastmult",
	"fpa",
	"vfp",
	"edsp",
	"java",
	"iwmmxt",
	"crunch",
	"thumbee",
	"neon",
	"vfpv3",
	"vfpv3d16",
	"tls",
	"vfpv4",
	"idiva",
	"idivt",
	"vfpd32",
	"lpae",
	"evtstrm"
};

static const char *compat_hwcap2_str[] = {
	"aes",
	"pmull",
	"sha1",
	"sha2",
	"crc32",
	NULL
};
#endif /* CONFIG_COMPAT */

static int c_show(struct seq_file *m, void *v)
{
	int i, j;

	for_each_online_cpu(i) {
		struct cpuinfo_arm64 *cpuinfo = &per_cpu(cpu_data, i);
		u32 midr = cpuinfo->reg_midr;

		/*
		 * glibc reads /proc/cpuinfo to determine the number of
		 * online processors, looking for lines beginning with
		 * "processor".  Give glibc what it expects.
		 */
		seq_printf(m, "processor\t: %d\n", i);

		/*
		 * Dump out the common processor features in a single line.
		 * Userspace should read the hwcaps with getauxval(AT_HWCAP)
		 * rather than attempting to parse this, but there's a body of
		 * software which does already (at least for 32-bit).
		 */
		seq_puts(m, "Features\t:");
		if (personality(current->personality) == PER_LINUX32) {
#ifdef CONFIG_COMPAT
			for (j = 0; compat_hwcap_str[j]; j++)
				if (compat_elf_hwcap & (1 << j))
					seq_printf(m, " %s", compat_hwcap_str[j]);

			for (j = 0; compat_hwcap2_str[j]; j++)
				if (compat_elf_hwcap2 & (1 << j))
					seq_printf(m, " %s", compat_hwcap2_str[j]);
#endif /* CONFIG_COMPAT */
		} else {
			for (j = 0; hwcap_str[j]; j++)
				if (elf_hwcap & (1 << j))
					seq_printf(m, " %s", hwcap_str[j]);
		}
		seq_puts(m, "\n");

		seq_printf(m, "CPU implementer\t: 0x%02x\n",
			   MIDR_IMPLEMENTOR(midr));
		seq_printf(m, "CPU architecture: 8\n");
		seq_printf(m, "CPU variant\t: 0x%x\n", MIDR_VARIANT(midr));
		seq_printf(m, "CPU part\t: 0x%03x\n", MIDR_PARTNUM(midr));
		seq_printf(m, "CPU revision\t: %d\n\n", MIDR_REVISION(midr));
	}

	return 0;
}

static void *c_start(struct seq_file *m, loff_t *pos)
{
	return *pos < 1 ? (void *)1 : NULL;
}

static void *c_next(struct seq_file *m, void *v, loff_t *pos)
{
	++*pos;
	return NULL;
}

static void c_stop(struct seq_file *m, void *v)
{
}

const struct seq_operations cpuinfo_op = {
	.start	= c_start,
	.next	= c_next,
	.stop	= c_stop,
	.show	= c_show
};
OpenPOWER on IntegriCloud