summaryrefslogtreecommitdiffstats
path: root/arch/arm64/mm/init.c
blob: b9af30be813eefa89d8385fc90d098175e102cd8 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Based on arch/arm/mm/init.c
 *
 * Copyright (C) 1995-2005 Russell King
 * Copyright (C) 2012 ARM Ltd.
 */

#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/errno.h>
#include <linux/swap.h>
#include <linux/init.h>
#include <linux/cache.h>
#include <linux/mman.h>
#include <linux/nodemask.h>
#include <linux/initrd.h>
#include <linux/gfp.h>
#include <linux/memblock.h>
#include <linux/sort.h>
#include <linux/of.h>
#include <linux/of_fdt.h>
#include <linux/dma-direct.h>
#include <linux/dma-map-ops.h>
#include <linux/efi.h>
#include <linux/swiotlb.h>
#include <linux/vmalloc.h>
#include <linux/mm.h>
#include <linux/kexec.h>
#include <linux/crash_dump.h>
#include <linux/hugetlb.h>
#include <linux/acpi_iort.h>
#include <linux/kmemleak.h>

#include <asm/boot.h>
#include <asm/fixmap.h>
#include <asm/kasan.h>
#include <asm/kernel-pgtable.h>
#include <asm/kvm_host.h>
#include <asm/memory.h>
#include <asm/numa.h>
#include <asm/sections.h>
#include <asm/setup.h>
#include <linux/sizes.h>
#include <asm/tlb.h>
#include <asm/alternative.h>
#include <asm/xen/swiotlb-xen.h>

/*
 * We need to be able to catch inadvertent references to memstart_addr
 * that occur (potentially in generic code) before arm64_memblock_init()
 * executes, which assigns it its actual value. So use a default value
 * that cannot be mistaken for a real physical address.
 */
s64 memstart_addr __ro_after_init = -1;
EXPORT_SYMBOL(memstart_addr);

/*
 * If the corresponding config options are enabled, we create both ZONE_DMA
 * and ZONE_DMA32. By default ZONE_DMA covers the 32-bit addressable memory
 * unless restricted on specific platforms (e.g. 30-bit on Raspberry Pi 4).
 * In such case, ZONE_DMA32 covers the rest of the 32-bit addressable memory,
 * otherwise it is empty.
 *
 * Memory reservation for crash kernel either done early or deferred
 * depending on DMA memory zones configs (ZONE_DMA) --
 *
 * In absence of ZONE_DMA configs arm64_dma_phys_limit initialized
 * here instead of max_zone_phys().  This lets early reservation of
 * crash kernel memory which has a dependency on arm64_dma_phys_limit.
 * Reserving memory early for crash kernel allows linear creation of block
 * mappings (greater than page-granularity) for all the memory bank rangs.
 * In this scheme a comparatively quicker boot is observed.
 *
 * If ZONE_DMA configs are defined, crash kernel memory reservation
 * is delayed until DMA zone memory range size initialization performed in
 * zone_sizes_init().  The defer is necessary to steer clear of DMA zone
 * memory range to avoid overlap allocation.  So crash kernel memory boundaries
 * are not known when mapping all bank memory ranges, which otherwise means
 * not possible to exclude crash kernel range from creating block mappings
 * so page-granularity mappings are created for the entire memory range.
 * Hence a slightly slower boot is observed.
 *
 * Note: Page-granularity mappings are necessary for crash kernel memory
 * range for shrinking its size via /sys/kernel/kexec_crash_size interface.
 */
#if IS_ENABLED(CONFIG_ZONE_DMA) || IS_ENABLED(CONFIG_ZONE_DMA32)
phys_addr_t __ro_after_init arm64_dma_phys_limit;
#else
phys_addr_t __ro_after_init arm64_dma_phys_limit = PHYS_MASK + 1;
#endif

/* Current arm64 boot protocol requires 2MB alignment */
#define CRASH_ALIGN			SZ_2M

#define CRASH_ADDR_LOW_MAX		arm64_dma_phys_limit
#define CRASH_ADDR_HIGH_MAX		(PHYS_MASK + 1)

static int __init reserve_crashkernel_low(unsigned long long low_size)
{
	unsigned long long low_base;

	low_base = memblock_phys_alloc_range(low_size, CRASH_ALIGN, 0, CRASH_ADDR_LOW_MAX);
	if (!low_base) {
		pr_err("cannot allocate crashkernel low memory (size:0x%llx).\n", low_size);
		return -ENOMEM;
	}

	pr_info("crashkernel low memory reserved: 0x%08llx - 0x%08llx (%lld MB)\n",
		low_base, low_base + low_size, low_size >> 20);

	crashk_low_res.start = low_base;
	crashk_low_res.end   = low_base + low_size - 1;
	insert_resource(&iomem_resource, &crashk_low_res);

	return 0;
}

/*
 * reserve_crashkernel() - reserves memory for crash kernel
 *
 * This function reserves memory area given in "crashkernel=" kernel command
 * line parameter. The memory reserved is used by dump capture kernel when
 * primary kernel is crashing.
 */
static void __init reserve_crashkernel(void)
{
	unsigned long long crash_base, crash_size;
	unsigned long long crash_low_size = 0;
	unsigned long long crash_max = CRASH_ADDR_LOW_MAX;
	char *cmdline = boot_command_line;
	int ret;

	if (!IS_ENABLED(CONFIG_KEXEC_CORE))
		return;

	/* crashkernel=X[@offset] */
	ret = parse_crashkernel(cmdline, memblock_phys_mem_size(),
				&crash_size, &crash_base);
	if (ret == -ENOENT) {
		ret = parse_crashkernel_high(cmdline, 0, &crash_size, &crash_base);
		if (ret || !crash_size)
			return;

		/*
		 * crashkernel=Y,low can be specified or not, but invalid value
		 * is not allowed.
		 */
		ret = parse_crashkernel_low(cmdline, 0, &crash_low_size, &crash_base);
		if (ret && (ret != -ENOENT))
			return;

		crash_max = CRASH_ADDR_HIGH_MAX;
	} else if (ret || !crash_size) {
		/* The specified value is invalid */
		return;
	}

	crash_size = PAGE_ALIGN(crash_size);

	/* User specifies base address explicitly. */
	if (crash_base)
		crash_max = crash_base + crash_size;

	crash_base = memblock_phys_alloc_range(crash_size, CRASH_ALIGN,
					       crash_base, crash_max);
	if (!crash_base) {
		pr_warn("cannot allocate crashkernel (size:0x%llx)\n",
			crash_size);
		return;
	}

	if ((crash_base >= CRASH_ADDR_LOW_MAX) &&
	     crash_low_size && reserve_crashkernel_low(crash_low_size)) {
		memblock_phys_free(crash_base, crash_size);
		return;
	}

	pr_info("crashkernel reserved: 0x%016llx - 0x%016llx (%lld MB)\n",
		crash_base, crash_base + crash_size, crash_size >> 20);

	/*
	 * The crashkernel memory will be removed from the kernel linear
	 * map. Inform kmemleak so that it won't try to access it.
	 */
	kmemleak_ignore_phys(crash_base);
	if (crashk_low_res.end)
		kmemleak_ignore_phys(crashk_low_res.start);

	crashk_res.start = crash_base;
	crashk_res.end = crash_base + crash_size - 1;
	insert_resource(&iomem_resource, &crashk_res);
}

/*
 * Return the maximum physical address for a zone accessible by the given bits
 * limit. If DRAM starts above 32-bit, expand the zone to the maximum
 * available memory, otherwise cap it at 32-bit.
 */
static phys_addr_t __init max_zone_phys(unsigned int zone_bits)
{
	phys_addr_t zone_mask = DMA_BIT_MASK(zone_bits);
	phys_addr_t phys_start = memblock_start_of_DRAM();

	if (phys_start > U32_MAX)
		zone_mask = PHYS_ADDR_MAX;
	else if (phys_start > zone_mask)
		zone_mask = U32_MAX;

	return min(zone_mask, memblock_end_of_DRAM() - 1) + 1;
}

static void __init zone_sizes_init(void)
{
	unsigned long max_zone_pfns[MAX_NR_ZONES]  = {0};
	unsigned int __maybe_unused acpi_zone_dma_bits;
	unsigned int __maybe_unused dt_zone_dma_bits;
	phys_addr_t __maybe_unused dma32_phys_limit = max_zone_phys(32);

#ifdef CONFIG_ZONE_DMA
	acpi_zone_dma_bits = fls64(acpi_iort_dma_get_max_cpu_address());
	dt_zone_dma_bits = fls64(of_dma_get_max_cpu_address(NULL));
	zone_dma_bits = min3(32U, dt_zone_dma_bits, acpi_zone_dma_bits);
	arm64_dma_phys_limit = max_zone_phys(zone_dma_bits);
	max_zone_pfns[ZONE_DMA] = PFN_DOWN(arm64_dma_phys_limit);
#endif
#ifdef CONFIG_ZONE_DMA32
	max_zone_pfns[ZONE_DMA32] = PFN_DOWN(dma32_phys_limit);
	if (!arm64_dma_phys_limit)
		arm64_dma_phys_limit = dma32_phys_limit;
#endif
	max_zone_pfns[ZONE_NORMAL] = max_pfn;

	free_area_init(max_zone_pfns);
}

int pfn_is_map_memory(unsigned long pfn)
{
	phys_addr_t addr = PFN_PHYS(pfn);

	/* avoid false positives for bogus PFNs, see comment in pfn_valid() */
	if (PHYS_PFN(addr) != pfn)
		return 0;

	return memblock_is_map_memory(addr);
}
EXPORT_SYMBOL(pfn_is_map_memory);

static phys_addr_t memory_limit __ro_after_init = PHYS_ADDR_MAX;

/*
 * Limit the memory size that was specified via FDT.
 */
static int __init early_mem(char *p)
{
	if (!p)
		return 1;

	memory_limit = memparse(p, &p) & PAGE_MASK;
	pr_notice("Memory limited to %lldMB\n", memory_limit >> 20);

	return 0;
}
early_param("mem", early_mem);

void __init arm64_memblock_init(void)
{
	s64 linear_region_size = PAGE_END - _PAGE_OFFSET(vabits_actual);

	/*
	 * Corner case: 52-bit VA capable systems running KVM in nVHE mode may
	 * be limited in their ability to support a linear map that exceeds 51
	 * bits of VA space, depending on the placement of the ID map. Given
	 * that the placement of the ID map may be randomized, let's simply
	 * limit the kernel's linear map to 51 bits as well if we detect this
	 * configuration.
	 */
	if (IS_ENABLED(CONFIG_KVM) && vabits_actual == 52 &&
	    is_hyp_mode_available() && !is_kernel_in_hyp_mode()) {
		pr_info("Capping linear region to 51 bits for KVM in nVHE mode on LVA capable hardware.\n");
		linear_region_size = min_t(u64, linear_region_size, BIT(51));
	}

	/* Remove memory above our supported physical address size */
	memblock_remove(1ULL << PHYS_MASK_SHIFT, ULLONG_MAX);

	/*
	 * Select a suitable value for the base of physical memory.
	 */
	memstart_addr = round_down(memblock_start_of_DRAM(),
				   ARM64_MEMSTART_ALIGN);

	if ((memblock_end_of_DRAM() - memstart_addr) > linear_region_size)
		pr_warn("Memory doesn't fit in the linear mapping, VA_BITS too small\n");

	/*
	 * Remove the memory that we will not be able to cover with the
	 * linear mapping. Take care not to clip the kernel which may be
	 * high in memory.
	 */
	memblock_remove(max_t(u64, memstart_addr + linear_region_size,
			__pa_symbol(_end)), ULLONG_MAX);
	if (memstart_addr + linear_region_size < memblock_end_of_DRAM()) {
		/* ensure that memstart_addr remains sufficiently aligned */
		memstart_addr = round_up(memblock_end_of_DRAM() - linear_region_size,
					 ARM64_MEMSTART_ALIGN);
		memblock_remove(0, memstart_addr);
	}

	/*
	 * If we are running with a 52-bit kernel VA config on a system that
	 * does not support it, we have to place the available physical
	 * memory in the 48-bit addressable part of the linear region, i.e.,
	 * we have to move it upward. Since memstart_addr represents the
	 * physical address of PAGE_OFFSET, we have to *subtract* from it.
	 */
	if (IS_ENABLED(CONFIG_ARM64_VA_BITS_52) && (vabits_actual != 52))
		memstart_addr -= _PAGE_OFFSET(48) - _PAGE_OFFSET(52);

	/*
	 * Apply the memory limit if it was set. Since the kernel may be loaded
	 * high up in memory, add back the kernel region that must be accessible
	 * via the linear mapping.
	 */
	if (memory_limit != PHYS_ADDR_MAX) {
		memblock_mem_limit_remove_map(memory_limit);
		memblock_add(__pa_symbol(_text), (u64)(_end - _text));
	}

	if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && phys_initrd_size) {
		/*
		 * Add back the memory we just removed if it results in the
		 * initrd to become inaccessible via the linear mapping.
		 * Otherwise, this is a no-op
		 */
		u64 base = phys_initrd_start & PAGE_MASK;
		u64 size = PAGE_ALIGN(phys_initrd_start + phys_initrd_size) - base;

		/*
		 * We can only add back the initrd memory if we don't end up
		 * with more memory than we can address via the linear mapping.
		 * It is up to the bootloader to position the kernel and the
		 * initrd reasonably close to each other (i.e., within 32 GB of
		 * each other) so that all granule/#levels combinations can
		 * always access both.
		 */
		if (WARN(base < memblock_start_of_DRAM() ||
			 base + size > memblock_start_of_DRAM() +
				       linear_region_size,
			"initrd not fully accessible via the linear mapping -- please check your bootloader ...\n")) {
			phys_initrd_size = 0;
		} else {
			memblock_add(base, size);
			memblock_clear_nomap(base, size);
			memblock_reserve(base, size);
		}
	}

	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
		extern u16 memstart_offset_seed;
		u64 mmfr0 = read_cpuid(ID_AA64MMFR0_EL1);
		int parange = cpuid_feature_extract_unsigned_field(
					mmfr0, ID_AA64MMFR0_PARANGE_SHIFT);
		s64 range = linear_region_size -
			    BIT(id_aa64mmfr0_parange_to_phys_shift(parange));

		/*
		 * If the size of the linear region exceeds, by a sufficient
		 * margin, the size of the region that the physical memory can
		 * span, randomize the linear region as well.
		 */
		if (memstart_offset_seed > 0 && range >= (s64)ARM64_MEMSTART_ALIGN) {
			range /= ARM64_MEMSTART_ALIGN;
			memstart_addr -= ARM64_MEMSTART_ALIGN *
					 ((range * memstart_offset_seed) >> 16);
		}
	}

	/*
	 * Register the kernel text, kernel data, initrd, and initial
	 * pagetables with memblock.
	 */
	memblock_reserve(__pa_symbol(_stext), _end - _stext);
	if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && phys_initrd_size) {
		/* the generic initrd code expects virtual addresses */
		initrd_start = __phys_to_virt(phys_initrd_start);
		initrd_end = initrd_start + phys_initrd_size;
	}

	early_init_fdt_scan_reserved_mem();

	if (!defer_reserve_crashkernel())
		reserve_crashkernel();

	high_memory = __va(memblock_end_of_DRAM() - 1) + 1;
}

void __init bootmem_init(void)
{
	unsigned long min, max;

	min = PFN_UP(memblock_start_of_DRAM());
	max = PFN_DOWN(memblock_end_of_DRAM());

	early_memtest(min << PAGE_SHIFT, max << PAGE_SHIFT);

	max_pfn = max_low_pfn = max;
	min_low_pfn = min;

	arch_numa_init();

	/*
	 * must be done after arch_numa_init() which calls numa_init() to
	 * initialize node_online_map that gets used in hugetlb_cma_reserve()
	 * while allocating required CMA size across online nodes.
	 */
#if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_CMA)
	arm64_hugetlb_cma_reserve();
#endif

	dma_pernuma_cma_reserve();

	kvm_hyp_reserve();

	/*
	 * sparse_init() tries to allocate memory from memblock, so must be
	 * done after the fixed reservations
	 */
	sparse_init();
	zone_sizes_init();

	/*
	 * Reserve the CMA area after arm64_dma_phys_limit was initialised.
	 */
	dma_contiguous_reserve(arm64_dma_phys_limit);

	/*
	 * request_standard_resources() depends on crashkernel's memory being
	 * reserved, so do it here.
	 */
	if (defer_reserve_crashkernel())
		reserve_crashkernel();

	memblock_dump_all();
}

/*
 * mem_init() marks the free areas in the mem_map and tells us how much memory
 * is free.  This is done after various parts of the system have claimed their
 * memory after the kernel image.
 */
void __init mem_init(void)
{
	swiotlb_init(max_pfn > PFN_DOWN(arm64_dma_phys_limit), SWIOTLB_VERBOSE);

	/* this will put all unused low memory onto the freelists */
	memblock_free_all();

	/*
	 * Check boundaries twice: Some fundamental inconsistencies can be
	 * detected at build time already.
	 */
#ifdef CONFIG_COMPAT
	BUILD_BUG_ON(TASK_SIZE_32 > DEFAULT_MAP_WINDOW_64);
#endif

	/*
	 * Selected page table levels should match when derived from
	 * scratch using the virtual address range and page size.
	 */
	BUILD_BUG_ON(ARM64_HW_PGTABLE_LEVELS(CONFIG_ARM64_VA_BITS) !=
		     CONFIG_PGTABLE_LEVELS);

	if (PAGE_SIZE >= 16384 && get_num_physpages() <= 128) {
		extern int sysctl_overcommit_memory;
		/*
		 * On a machine this small we won't get anywhere without
		 * overcommit, so turn it on by default.
		 */
		sysctl_overcommit_memory = OVERCOMMIT_ALWAYS;
	}
}

void free_initmem(void)
{
	free_reserved_area(lm_alias(__init_begin),
			   lm_alias(__init_end),
			   POISON_FREE_INITMEM, "unused kernel");
	/*
	 * Unmap the __init region but leave the VM area in place. This
	 * prevents the region from being reused for kernel modules, which
	 * is not supported by kallsyms.
	 */
	vunmap_range((u64)__init_begin, (u64)__init_end);
}

void dump_mem_limit(void)
{
	if (memory_limit != PHYS_ADDR_MAX) {
		pr_emerg("Memory Limit: %llu MB\n", memory_limit >> 20);
	} else {
		pr_emerg("Memory Limit: none\n");
	}
}