init.c 20.4 KB
Newer Older
1
// SPDX-License-Identifier: GPL-2.0-only
C
Catalin Marinas 已提交
2 3 4 5 6 7 8 9 10 11 12 13
/*
 * 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>
14
#include <linux/cache.h>
C
Catalin Marinas 已提交
15 16 17 18 19 20
#include <linux/mman.h>
#include <linux/nodemask.h>
#include <linux/initrd.h>
#include <linux/gfp.h>
#include <linux/memblock.h>
#include <linux/sort.h>
21
#include <linux/of.h>
C
Catalin Marinas 已提交
22
#include <linux/of_fdt.h>
23
#include <linux/dma-direct.h>
24
#include <linux/dma-map-ops.h>
25
#include <linux/efi.h>
26
#include <linux/swiotlb.h>
27
#include <linux/vmalloc.h>
28
#include <linux/mm.h>
29
#include <linux/kexec.h>
30
#include <linux/crash_dump.h>
31
#include <linux/hugetlb.h>
32
#include <linux/acpi_iort.h>
33 34 35
#ifdef CONFIG_PIN_MEMORY
#include <linux/pin_mem.h>
#endif
C
Catalin Marinas 已提交
36

37
#include <asm/boot.h>
38
#include <asm/fixmap.h>
39
#include <asm/kasan.h>
40
#include <asm/kernel-pgtable.h>
41
#include <asm/kexec.h>
42
#include <asm/memory.h>
43
#include <asm/numa.h>
C
Catalin Marinas 已提交
44 45
#include <asm/sections.h>
#include <asm/setup.h>
46
#include <linux/sizes.h>
C
Catalin Marinas 已提交
47
#include <asm/tlb.h>
48
#include <asm/alternative.h>
C
Catalin Marinas 已提交
49

50 51 52 53 54 55
/*
 * 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.
 */
56
s64 memstart_addr __ro_after_init = -1;
57 58
EXPORT_SYMBOL(memstart_addr);

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
#ifdef CONFIG_PIN_MEMORY
struct resource pin_memory_resource = {
	.name = "Pin memory",
	.start = 0,
	.end = 0,
	.flags = IORESOURCE_MEM,
	.desc = IORES_DESC_RESERVED
};

static void __init reserve_pin_memory_res(void)
{
	unsigned long long mem_start, mem_len;
	int ret;

	ret = parse_pin_memory(boot_command_line, memblock_phys_mem_size(),
		&mem_len, &mem_start);
	if (ret || !mem_len)
		return;

	mem_len = PAGE_ALIGN(mem_len);

	if (!memblock_is_region_memory(mem_start, mem_len)) {
		pr_warn("cannot reserve for pin memory: region is not memory!\n");
		return;
	}

	if (memblock_is_region_reserved(mem_start, mem_len)) {
		pr_warn("cannot reserve for pin memory: region overlaps reserved memory!\n");
		return;
	}

	if (!IS_ALIGNED(mem_start, SZ_2M)) {
		pr_warn("cannot reserve for pin memory: base address is not 2MB aligned\n");
		return;
	}

	memblock_reserve(mem_start, mem_len);
	pin_memory_resource.start = mem_start;
	pin_memory_resource.end = mem_start + mem_len - 1;
}
#else
static void __init reserve_pin_memory_res(void)
{
}
#endif /* CONFIG_PIN_MEMORY */

105
/*
106 107 108 109 110
 * 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.
111
 */
112
phys_addr_t arm64_dma_phys_limit __ro_after_init;
C
Catalin Marinas 已提交
113

114
#ifndef CONFIG_KEXEC_CORE
115 116 117
static void __init reserve_crashkernel(void)
{
}
118
#endif
119

120 121 122 123 124 125 126 127 128
/*
 * The main usage of linux,usable-memory-range is for crash dump kernel.
 * Originally, the number of usable-memory regions is one. Now there may
 * be two regions, low region and high region.
 * To make compatibility with existing user-space and older kdump, the low
 * region is always the last range of linux,usable-memory-range if exist.
 */
#define MAX_USABLE_RANGES	2

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
#ifdef CONFIG_CRASH_DUMP
static int __init early_init_dt_scan_elfcorehdr(unsigned long node,
		const char *uname, int depth, void *data)
{
	const __be32 *reg;
	int len;

	if (depth != 1 || strcmp(uname, "chosen") != 0)
		return 0;

	reg = of_get_flat_dt_prop(node, "linux,elfcorehdr", &len);
	if (!reg || (len < (dt_root_addr_cells + dt_root_size_cells)))
		return 1;

	elfcorehdr_addr = dt_mem_next_cell(dt_root_addr_cells, &reg);
	elfcorehdr_size = dt_mem_next_cell(dt_root_size_cells, &reg);

	return 1;
}

/*
 * reserve_elfcorehdr() - reserves memory for elf core header
 *
 * This function reserves the memory occupied by an elf core header
 * described in the device tree. This region contains all the
 * information about primary kernel's core image and is used by a dump
 * capture kernel to access the system memory on primary kernel.
 */
static void __init reserve_elfcorehdr(void)
{
	of_scan_flat_dt(early_init_dt_scan_elfcorehdr, NULL);

	if (!elfcorehdr_size)
		return;

	if (memblock_is_region_reserved(elfcorehdr_addr, elfcorehdr_size)) {
		pr_warn("elfcorehdr is overlapped\n");
		return;
	}

	memblock_reserve(elfcorehdr_addr, elfcorehdr_size);

	pr_info("Reserving %lldKB of memory at 0x%llx for elfcorehdr\n",
		elfcorehdr_size >> 10, elfcorehdr_addr);
}
#else
static void __init reserve_elfcorehdr(void)
{
}
#endif /* CONFIG_CRASH_DUMP */
179

S
Sang Yan 已提交
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
#ifdef CONFIG_QUICK_KEXEC
static int __init parse_quick_kexec(char *p)
{
	if (!p)
		return 0;

	quick_kexec_res.end = PAGE_ALIGN(memparse(p, NULL));

	return 0;
}
early_param("quickkexec", parse_quick_kexec);

static void __init reserve_quick_kexec(void)
{
	unsigned long long mem_start, mem_len;

	mem_len = quick_kexec_res.end;
	if (mem_len == 0)
		return;

	/* Current arm64 boot protocol requires 2MB alignment */
	mem_start = memblock_find_in_range(0, arm64_dma_phys_limit,
			mem_len, SZ_2M);
	if (mem_start == 0) {
		pr_warn("cannot allocate quick kexec mem (size:0x%llx)\n",
			mem_len);
		quick_kexec_res.end = 0;
		return;
	}

	memblock_reserve(mem_start, mem_len);
	pr_info("quick kexec mem reserved: 0x%016llx - 0x%016llx (%lld MB)\n",
		mem_start, mem_start + mem_len,	mem_len >> 20);

	quick_kexec_res.start = mem_start;
	quick_kexec_res.end = mem_start + mem_len - 1;
}
#endif

219
/*
220 221 222
 * 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.
223
 */
224
static phys_addr_t __init max_zone_phys(unsigned int zone_bits)
225
{
226 227 228 229 230 231 232 233 234
	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;
235 236
}

237 238 239
static void __init zone_sizes_init(unsigned long min, unsigned long max)
{
	unsigned long max_zone_pfns[MAX_NR_ZONES]  = {0};
240
	unsigned int __maybe_unused acpi_zone_dma_bits;
241
	unsigned int __maybe_unused dt_zone_dma_bits;
242
	phys_addr_t __maybe_unused dma32_phys_limit = max_zone_phys(32);
243

244
#ifdef CONFIG_ZONE_DMA
245
	acpi_zone_dma_bits = fls64(acpi_iort_dma_get_max_cpu_address());
246
	dt_zone_dma_bits = fls64(of_dma_get_max_cpu_address(NULL));
247
	zone_dma_bits = min3(32U, dt_zone_dma_bits, acpi_zone_dma_bits);
248
	arm64_dma_phys_limit = max_zone_phys(zone_dma_bits);
249 250
	max_zone_pfns[ZONE_DMA] = PFN_DOWN(arm64_dma_phys_limit);
#endif
251
#ifdef CONFIG_ZONE_DMA32
252 253 254
	max_zone_pfns[ZONE_DMA32] = PFN_DOWN(dma32_phys_limit);
	if (!arm64_dma_phys_limit)
		arm64_dma_phys_limit = dma32_phys_limit;
255
#endif
256 257
	if (!arm64_dma_phys_limit)
		arm64_dma_phys_limit = PHYS_MASK + 1;
258 259
	max_zone_pfns[ZONE_NORMAL] = max;

260
	free_area_init(max_zone_pfns);
261 262
}

C
Catalin Marinas 已提交
263 264
int pfn_valid(unsigned long pfn)
{
265 266 267 268
	phys_addr_t addr = pfn << PAGE_SHIFT;

	if ((addr >> PAGE_SHIFT) != pfn)
		return 0;
R
Robin Murphy 已提交
269 270 271 272 273

#ifdef CONFIG_SPARSEMEM
	if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS)
		return 0;

274
	if (!valid_section(__pfn_to_section(pfn)))
R
Robin Murphy 已提交
275
		return 0;
276 277 278 279 280 281 282 283 284 285 286 287

	/*
	 * ZONE_DEVICE memory does not have the memblock entries.
	 * memblock_is_map_memory() check for ZONE_DEVICE based
	 * addresses will always fail. Even the normal hotplugged
	 * memory will never have MEMBLOCK_NOMAP flag set in their
	 * memblock entries. Skip memblock search for all non early
	 * memory sections covering all of hotplug memory including
	 * both normal and ZONE_DEVICE based.
	 */
	if (!early_section(__pfn_to_section(pfn)))
		return pfn_section_valid(__pfn_to_section(pfn), pfn);
R
Robin Murphy 已提交
288
#endif
289
	return memblock_is_map_memory(addr);
C
Catalin Marinas 已提交
290 291 292
}
EXPORT_SYMBOL(pfn_valid);

293
static phys_addr_t memory_limit = PHYS_ADDR_MAX;
M
Mark Rutland 已提交
294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309

/*
 * 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);

310 311 312
static int __init early_init_dt_scan_usablemem(unsigned long node,
		const char *uname, int depth, void *data)
{
313 314 315
	struct memblock_region *usable_rgns = data;
	const __be32 *reg, *endp;
	int len, nr = 0;
316 317 318 319 320 321 322 323

	if (depth != 1 || strcmp(uname, "chosen") != 0)
		return 0;

	reg = of_get_flat_dt_prop(node, "linux,usable-memory-range", &len);
	if (!reg || (len < (dt_root_addr_cells + dt_root_size_cells)))
		return 1;

324 325 326 327 328 329 330 331
	endp = reg + (len / sizeof(__be32));
	while ((endp - reg) >= (dt_root_addr_cells + dt_root_size_cells)) {
		usable_rgns[nr].base = dt_mem_next_cell(dt_root_addr_cells, &reg);
		usable_rgns[nr].size = dt_mem_next_cell(dt_root_size_cells, &reg);

		if (++nr >= MAX_USABLE_RANGES)
			break;
	}
332 333 334 335 336 337

	return 1;
}

static void __init fdt_enforce_memory_region(void)
{
338 339 340
	struct memblock_region usable_rgns[MAX_USABLE_RANGES] = {
		{ .size = 0 },
		{ .size = 0 }
341 342
	};

343 344 345 346 347 348 349 350 351 352 353
	of_scan_flat_dt(early_init_dt_scan_usablemem, &usable_rgns);

	/*
	 * The first range of usable-memory regions is for crash dump
	 * kernel with only one region or for high region with two regions,
	 * the second range is dedicated for low region if exist.
	 */
	if (usable_rgns[0].size)
		memblock_cap_memory_range(usable_rgns[0].base, usable_rgns[0].size);
	if (usable_rgns[1].size)
		memblock_add(usable_rgns[1].base, usable_rgns[1].size);
354 355
}

S
Sang Yan 已提交
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
#ifdef CONFIG_ARM64_CPU_PARK
struct cpu_park_info park_info = {
	.start = 0,
	.len = PARK_SECTION_SIZE * NR_CPUS,
	.start_v = 0,
};

static int __init parse_park_mem(char *p)
{
	if (!p)
		return 0;

	park_info.start = PAGE_ALIGN(memparse(p, NULL));
	if (park_info.start == 0)
		pr_info("cpu park mem params[%s]", p);

	return 0;
}
early_param("cpuparkmem", parse_park_mem);

static int __init reserve_park_mem(void)
{
	if (park_info.start == 0 || park_info.len == 0)
		return 0;

	park_info.start = PAGE_ALIGN(park_info.start);
	park_info.len = PAGE_ALIGN(park_info.len);

	if (!memblock_is_region_memory(park_info.start, park_info.len)) {
		pr_warn("cannot reserve park mem: region is not memory!");
		goto out;
	}

	if (memblock_is_region_reserved(park_info.start, park_info.len)) {
		pr_warn("cannot reserve park mem: region overlaps reserved memory!");
		goto out;
	}

	memblock_remove(park_info.start, park_info.len);
	pr_info("cpu park mem reserved: 0x%016lx - 0x%016lx (%ld MB)",
		park_info.start, park_info.start + park_info.len,
		park_info.len >> 20);

	return 0;
out:
	park_info.start = 0;
	park_info.len = 0;
	return -EINVAL;
}
#endif

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
static int need_remove_real_memblock __initdata;

static int __init parse_memmap_one(char *p)
{
	char *oldp;
	u64 start_at, mem_size;

	if (!p)
		return -EINVAL;

	if (!strncmp(p, "exactmap", 8)) {
		need_remove_real_memblock = 1;
		return -EINVAL;
	}

	oldp = p;
	mem_size = memparse(p, &p);
	if (p == oldp)
		return -EINVAL;

	if (!mem_size)
		return -EINVAL;

	if (*p == '@') {
		start_at = memparse(p + 1, &p);
		/*
		 * use the exactmap defined by nn[KMG]@ss[KMG], remove
		 * memblock populated by DT etc.
		 */
		if (need_remove_real_memblock) {
			need_remove_real_memblock = 0;
			memblock_remove(0, ULLONG_MAX);
		}
		memblock_add(start_at, mem_size);
	} else if (*p == '$') {
		start_at = memparse(p + 1, &p);
		memblock_reserve(start_at, mem_size);
	} else
		pr_info("Unrecognized memmap option, please check the parameter.\n");

	return *p == '\0' ? 0 : -EINVAL;
}

static int __init parse_memmap_opt(char *str)
{
	while (str) {
		char *k = strchr(str, ',');

		if (k)
			*k++ = 0;

		parse_memmap_one(str);
		str = k;
	}

	return 0;
}
early_param("memmap", parse_memmap_opt);

C
Catalin Marinas 已提交
466 467
void __init arm64_memblock_init(void)
{
468
	const s64 linear_region_size = BIT(vabits_actual - 1);
469

470 471 472
	/* Handle linux,usable-memory-range property */
	fdt_enforce_memory_region();

473 474 475
	/* Remove memory above our supported physical address size */
	memblock_remove(1ULL << PHYS_MASK_SHIFT, ULLONG_MAX);

476 477 478 479 480 481 482 483 484 485 486
	/*
	 * Select a suitable value for the base of physical memory.
	 */
	memstart_addr = round_down(memblock_start_of_DRAM(),
				   ARM64_MEMSTART_ALIGN);

	/*
	 * 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.
	 */
487 488
	memblock_remove(max_t(u64, memstart_addr + linear_region_size,
			__pa_symbol(_end)), ULLONG_MAX);
489 490 491 492 493 494
	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);
	}
495

496 497 498 499 500 501 502 503 504 505
	/*
	 * 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);

506 507 508 509 510
	/*
	 * 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.
	 */
511
	if (memory_limit != PHYS_ADDR_MAX) {
512
		memblock_mem_limit_remove_map(memory_limit);
513
		memblock_add(__pa_symbol(_text), (u64)(_end - _text));
514
	}
M
Mark Rutland 已提交
515

516
	if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && phys_initrd_size) {
517 518 519 520 521
		/*
		 * 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
		 */
522
		u64 base = phys_initrd_start & PAGE_MASK;
523
		u64 size = PAGE_ALIGN(phys_initrd_start + phys_initrd_size) - base;
524 525 526 527 528 529 530 531 532 533 534 535 536

		/*
		 * 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")) {
537
			phys_initrd_size = 0;
538 539 540 541 542 543 544
		} else {
			memblock_remove(base, size); /* clear MEMBLOCK_ flags */
			memblock_add(base, size);
			memblock_reserve(base, size);
		}
	}

545 546
	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
		extern u16 memstart_offset_seed;
547 548
		u64 range = linear_region_size -
			    (memblock_end_of_DRAM() - memblock_start_of_DRAM());
549 550 551

		/*
		 * If the size of the linear region exceeds, by a sufficient
552 553
		 * margin, the size of the region that the available physical
		 * memory spans, randomize the linear region as well.
554
		 */
555
		if (memstart_offset_seed > 0 && range >= ARM64_MEMSTART_ALIGN) {
556
			range /= ARM64_MEMSTART_ALIGN;
557 558 559 560
			memstart_addr -= ARM64_MEMSTART_ALIGN *
					 ((range * memstart_offset_seed) >> 16);
		}
	}
M
Mark Rutland 已提交
561

562 563 564 565
	/*
	 * Register the kernel text, kernel data, initrd, and initial
	 * pagetables with memblock.
	 */
566
	memblock_reserve(__pa_symbol(_text), _end - _text);
567
	if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && phys_initrd_size) {
568
		/* the generic initrd code expects virtual addresses */
569 570
		initrd_start = __phys_to_virt(phys_initrd_start);
		initrd_end = initrd_start + phys_initrd_size;
571
	}
C
Catalin Marinas 已提交
572

573
	early_init_fdt_scan_reserved_mem();
574

575 576
	reserve_elfcorehdr();

577
	high_memory = __va(memblock_end_of_DRAM() - 1) + 1;
C
Catalin Marinas 已提交
578 579 580 581 582 583 584 585 586
}

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

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

V
Vladimir Murzin 已提交
587 588
	early_memtest(min << PAGE_SHIFT, max << PAGE_SHIFT);

589
	max_pfn = max_low_pfn = max;
M
Miles Chen 已提交
590
	min_low_pfn = min;
591 592

	arm64_numa_init();
593 594 595 596 597 598

	/*
	 * must be done after arm64_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.
	 */
599 600
#if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_CMA)
	arm64_hugetlb_cma_reserve();
601 602
#endif

603 604
	dma_pernuma_cma_reserve();

C
Catalin Marinas 已提交
605
	/*
606 607
	 * sparse_init() tries to allocate memory from memblock, so must be
	 * done after the fixed reservations
C
Catalin Marinas 已提交
608 609 610 611
	 */
	sparse_init();
	zone_sizes_init(min, max);

612 613 614 615 616
	/*
	 * Reserve the CMA area after arm64_dma_phys_limit was initialised.
	 */
	dma_contiguous_reserve(arm64_dma_phys_limit);

S
Sang Yan 已提交
617 618 619 620 621 622 623 624 625 626 627 628 629
	/*
	 * Reserve park memory before crashkernel and quick kexec.
	 * Because park memory must be specified by address, but
	 * crashkernel and quickkexec may be specified by memory length,
	 * then find one sutiable memory region to reserve.
	 *
	 * So reserve park memory firstly is better, but it may cause
	 * crashkernel or quickkexec reserving failed.
	 */
#ifdef CONFIG_ARM64_CPU_PARK
	reserve_park_mem();
#endif

630 631 632 633 634 635
	/*
	 * request_standard_resources() depends on crashkernel's memory being
	 * reserved, so do it here.
	 */
	reserve_crashkernel();

S
Sang Yan 已提交
636 637 638
#ifdef CONFIG_QUICK_KEXEC
	reserve_quick_kexec();
#endif
639

640 641
	reserve_pin_memory_res();

642
	memblock_dump_all();
C
Catalin Marinas 已提交
643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668
}

#ifndef CONFIG_SPARSEMEM_VMEMMAP
static inline void free_memmap(unsigned long start_pfn, unsigned long end_pfn)
{
	struct page *start_pg, *end_pg;
	unsigned long pg, pgend;

	/*
	 * Convert start_pfn/end_pfn to a struct page pointer.
	 */
	start_pg = pfn_to_page(start_pfn - 1) + 1;
	end_pg = pfn_to_page(end_pfn - 1) + 1;

	/*
	 * Convert to physical addresses, and round start upwards and end
	 * downwards.
	 */
	pg = (unsigned long)PAGE_ALIGN(__pa(start_pg));
	pgend = (unsigned long)__pa(end_pg) & PAGE_MASK;

	/*
	 * If there are free pages between these, free the section of the
	 * memmap array.
	 */
	if (pg < pgend)
669
		memblock_free(pg, pgend - pg);
C
Catalin Marinas 已提交
670 671 672 673 674 675 676
}

/*
 * The mem_map array can get very big. Free the unused area of the memory map.
 */
static void __init free_unused_memmap(void)
{
677 678
	unsigned long start, end, prev_end = 0;
	int i;
C
Catalin Marinas 已提交
679

680
	for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, NULL) {
C
Catalin Marinas 已提交
681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699
#ifdef CONFIG_SPARSEMEM
		/*
		 * Take care not to free memmap entries that don't exist due
		 * to SPARSEMEM sections which aren't present.
		 */
		start = min(start, ALIGN(prev_end, PAGES_PER_SECTION));
#endif
		/*
		 * If we had a previous bank, and there is a space between the
		 * current bank and the previous, free it.
		 */
		if (prev_end && prev_end < start)
			free_memmap(prev_end, start);

		/*
		 * Align up here since the VM subsystem insists that the
		 * memmap entries are valid from the bank end aligned to
		 * MAX_ORDER_NR_PAGES.
		 */
700
		prev_end = ALIGN(end, MAX_ORDER_NR_PAGES);
C
Catalin Marinas 已提交
701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716
	}

#ifdef CONFIG_SPARSEMEM
	if (!IS_ALIGNED(prev_end, PAGES_PER_SECTION))
		free_memmap(prev_end, ALIGN(prev_end, PAGES_PER_SECTION));
#endif
}
#endif	/* !CONFIG_SPARSEMEM_VMEMMAP */

/*
 * 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)
{
717
	if (swiotlb_force == SWIOTLB_FORCE ||
718
	    max_pfn > PFN_DOWN(arm64_dma_phys_limit))
719
		swiotlb_init(1);
720 721
	else
		swiotlb_force = SWIOTLB_NO_FORCE;
722

723
	set_max_mapnr(max_pfn - PHYS_PFN_OFFSET);
C
Catalin Marinas 已提交
724 725 726 727

#ifndef CONFIG_SPARSEMEM_VMEMMAP
	free_unused_memmap();
#endif
728
	/* this will put all unused low memory onto the freelists */
729
	memblock_free_all();
C
Catalin Marinas 已提交
730

731 732 733 734 735 736
#ifdef CONFIG_PIN_MEMORY
	/* pre alloc the pages for pin memory */
	init_reserve_page_map((unsigned long)pin_memory_resource.start,
		(unsigned long)(pin_memory_resource.end - pin_memory_resource.start));
#endif

737
	mem_init_print_info(NULL);
C
Catalin Marinas 已提交
738 739 740 741 742 743

	/*
	 * Check boundaries twice: Some fundamental inconsistencies can be
	 * detected at build time already.
	 */
#ifdef CONFIG_COMPAT
744
	BUILD_BUG_ON(TASK_SIZE_32 > DEFAULT_MAP_WINDOW_64);
C
Catalin Marinas 已提交
745 746
#endif

747
	if (PAGE_SIZE >= 16384 && get_num_physpages() <= 128) {
C
Catalin Marinas 已提交
748 749 750 751 752 753 754 755 756 757 758
		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)
{
759 760
	free_reserved_area(lm_alias(__init_begin),
			   lm_alias(__init_end),
761
			   POISON_FREE_INITMEM, "unused kernel");
762 763 764 765 766 767
	/*
	 * 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.
	 */
	unmap_kernel_range((u64)__init_begin, (u64)(__init_end - __init_begin));
C
Catalin Marinas 已提交
768 769
}

770
void dump_mem_limit(void)
771
{
772
	if (memory_limit != PHYS_ADDR_MAX) {
773 774 775 776 777
		pr_emerg("Memory Limit: %llu MB\n", memory_limit >> 20);
	} else {
		pr_emerg("Memory Limit: none\n");
	}
}