summaryrefslogtreecommitdiffstats
path: root/arch/arm64/kernel/setup.c
blob: a096e2451044d35bad506ecb67edcf3f2d30b87c (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Based on arch/arm/kernel/setup.c
 *
 * Copyright (C) 1995-2001 Russell King
 * Copyright (C) 2012 ARM Ltd.
 */

#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/initrd.h>
#include <linux/console.h>
#include <linux/cache.h>
#include <linux/screen_info.h>
#include <linux/init.h>
#include <linux/kexec.h>
#include <linux/root_dev.h>
#include <linux/cpu.h>
#include <linux/interrupt.h>
#include <linux/smp.h>
#include <linux/fs.h>
#include <linux/panic_notifier.h>
#include <linux/proc_fs.h>
#include <linux/memblock.h>
#include <linux/of_fdt.h>
#include <linux/efi.h>
#include <linux/psci.h>
#include <linux/sched/task.h>
#include <linux/scs.h>
#include <linux/mm.h>

#include <asm/acpi.h>
#include <asm/fixmap.h>
#include <asm/cpu.h>
#include <asm/cputype.h>
#include <asm/daifflags.h>
#include <asm/elf.h>
#include <asm/cpufeature.h>
#include <asm/cpu_ops.h>
#include <asm/kasan.h>
#include <asm/numa.h>
#include <asm/scs.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/efi.h>
#include <asm/xen/hypervisor.h>
#include <asm/mmu_context.h>

static int num_standard_resources;
static struct resource *standard_resources;

phys_addr_t __fdt_pointer __initdata;
u64 mmu_enabled_at_boot __initdata;

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

#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;
	set_cpu_logical_map(0, mpidr);

	pr_info("Booting Linux on physical CPU 0x%010lx [0x%08x]\n",
		(unsigned long)mpidr, read_cpuid_id());
}

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");
}

static void __init setup_machine_fdt(phys_addr_t dt_phys)
{
	int size;
	void *dt_virt = fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL);
	const char *name;

	if (dt_virt)
		memblock_reserve(dt_phys, size);

	if (!dt_virt || !early_init_dt_scan(dt_virt)) {
		pr_crit("\n"
			"Error: invalid device tree blob at physical address %pa (virtual address 0x%px)\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);

		/*
		 * Note that in this _really_ early stage we cannot even BUG()
		 * or oops, so the least terrible thing to do is cpu_relax(),
		 * or else we could end-up printing non-initialized data, etc.
		 */
		while (true)
			cpu_relax();
	}

	/* Early fixups are done, map the FDT as read-only now */
	fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL_RO);

	name = of_flat_dt_get_machine_name();
	if (!name)
		return;

	pr_info("Machine model: %s\n", name);
	dump_stack_set_arch_desc("%s (DT)", name);
}

static void __init request_standard_resources(void)
{
	struct memblock_region *region;
	struct resource *res;
	unsigned long i = 0;
	size_t res_size;

	kernel_code.start   = __pa_symbol(_stext);
	kernel_code.end     = __pa_symbol(__init_begin - 1);
	kernel_data.start   = __pa_symbol(_sdata);
	kernel_data.end     = __pa_symbol(_end - 1);
	insert_resource(&iomem_resource, &kernel_code);
	insert_resource(&iomem_resource, &kernel_data);

	num_standard_resources = memblock.memory.cnt;
	res_size = num_standard_resources * sizeof(*standard_resources);
	standard_resources = memblock_alloc(res_size, SMP_CACHE_BYTES);
	if (!standard_resources)
		panic("%s: Failed to allocate %zu bytes\n", __func__, res_size);

	for_each_mem_region(region) {
		res = &standard_resources[i++];
		if (memblock_is_nomap(region)) {
			res->name  = "reserved";
			res->flags = IORESOURCE_MEM;
			res->start = __pfn_to_phys(memblock_region_reserved_base_pfn(region));
			res->end = __pfn_to_phys(memblock_region_reserved_end_pfn(region)) - 1;
		} else {
			res->name  = "System RAM";
			res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
			res->start = __pfn_to_phys(memblock_region_memory_base_pfn(region));
			res->end = __pfn_to_phys(memblock_region_memory_end_pfn(region)) - 1;
		}

		insert_resource(&iomem_resource, res);
	}
}

static int __init reserve_memblock_reserved_regions(void)
{
	u64 i, j;

	for (i = 0; i < num_standard_resources; ++i) {
		struct resource *mem = &standard_resources[i];
		phys_addr_t r_start, r_end, mem_size = resource_size(mem);

		if (!memblock_is_region_reserved(mem->start, mem_size))
			continue;

		for_each_reserved_mem_range(j, &r_start, &r_end) {
			resource_size_t start, end;

			start = max(PFN_PHYS(PFN_DOWN(r_start)), mem->start);
			end = min(PFN_PHYS(PFN_UP(r_end)) - 1, mem->end);

			if (start > mem->end || end < mem->start)
				continue;

			reserve_region_with_split(mem, start, end, "reserved");
		}
	}

	return 0;
}
arch_initcall(reserve_memblock_reserved_regions);

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

u64 cpu_logical_map(unsigned int cpu)
{
	return __cpu_logical_map[cpu];
}

void __init __no_sanitize_address setup_arch(char **cmdline_p)
{
	setup_initial_init_mm(_stext, _etext, _edata, _end);

	*cmdline_p = boot_command_line;

	kaslr_init();

	early_fixmap_init();
	early_ioremap_init();

	setup_machine_fdt(__fdt_pointer);

	/*
	 * Initialise the static keys early as they may be enabled by the
	 * cpufeature code and early parameters.
	 */
	jump_label_init();
	parse_early_param();

	dynamic_scs_init();

	/*
	 * The primary CPU enters the kernel with all DAIF exceptions masked.
	 *
	 * We must unmask Debug and SError before preemption or scheduling is
	 * possible to ensure that these are consistently unmasked across
	 * threads, and we want to unmask SError as soon as possible after
	 * initializing earlycon so that we can report any SErrors immediately.
	 *
	 * IRQ and FIQ will be unmasked after the root irqchip has been
	 * detected and initialized.
	 */
	local_daif_restore(DAIF_PROCCTX_NOIRQ);

	/*
	 * TTBR0 is only used for the identity mapping at this stage. Make it
	 * point to zero page to avoid speculatively fetching new entries.
	 */
	cpu_uninstall_idmap();

	xen_early_init();
	efi_init();

	if (!efi_enabled(EFI_BOOT)) {
		if ((u64)_text % MIN_KIMG_ALIGN)
			pr_warn(FW_BUG "Kernel image misaligned at boot, please fix your bootloader!");
		WARN_TAINT(mmu_enabled_at_boot, TAINT_FIRMWARE_WORKAROUND,
			   FW_BUG "Booted with MMU enabled!");
	}

	arm64_memblock_init();

	paging_init();

	acpi_table_upgrade();

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

	if (acpi_disabled)
		unflatten_device_tree();

	bootmem_init();

	kasan_init();

	request_standard_resources();

	early_ioremap_reset();

	if (acpi_disabled)
		psci_dt_init();
	else
		psci_acpi_init();

	init_bootcpu_ops();
	smp_init_cpus();
	smp_build_mpidr_hash();

	/* Init percpu seeds for random tags after cpus are set up. */
	kasan_init_sw_tags();

#ifdef CONFIG_ARM64_SW_TTBR0_PAN
	/*
	 * Make sure init_thread_info.ttbr0 always generates translation
	 * faults in case uaccess_enable() is inadvertently called by the init
	 * thread.
	 */
	init_task.thread_info.ttbr0 = phys_to_ttbr(__pa_symbol(reserved_pg_dir));
#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 inline bool cpu_can_disable(unsigned int cpu)
{
#ifdef CONFIG_HOTPLUG_CPU
	const struct cpu_operations *ops = get_cpu_ops(cpu);

	if (ops && ops->cpu_can_disable)
		return ops->cpu_can_disable(cpu);
#endif
	return false;
}

bool arch_cpu_is_hotpluggable(int num)
{
	return cpu_can_disable(num);
}

static void dump_kernel_offset(void)
{
	const unsigned long offset = kaslr_offset();

	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && offset > 0) {
		pr_emerg("Kernel Offset: 0x%lx from 0x%lx\n",
			 offset, KIMAGE_VADDR);
		pr_emerg("PHYS_OFFSET: 0x%llx\n", PHYS_OFFSET);
	} else {
		pr_emerg("Kernel Offset: disabled\n");
	}
}

static int arm64_panic_block_dump(struct notifier_block *self,
				  unsigned long v, void *p)
{
	dump_kernel_offset();
	dump_cpu_features();
	dump_mem_limit();
	return 0;
}

static struct notifier_block arm64_panic_block = {
	.notifier_call = arm64_panic_block_dump
};

static int __init register_arm64_panic_block(void)
{
	atomic_notifier_chain_register(&panic_notifier_list,
				       &arm64_panic_block);
	return 0;
}
device_initcall(register_arm64_panic_block);

static int __init check_mmu_enabled_at_boot(void)
{
	if (!efi_enabled(EFI_BOOT) && mmu_enabled_at_boot)
		panic("Non-EFI boot detected with MMU and caches enabled");
	return 0;
}
device_initcall_sync(check_mmu_enabled_at_boot);