init.c 19.5 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9 10 11 12
/*
 * Initialize MMU support.
 *
 * Copyright (C) 1998-2003 Hewlett-Packard Co
 *	David Mosberger-Tang <davidm@hpl.hp.com>
 */
#include <linux/kernel.h>
#include <linux/init.h>

#include <linux/bootmem.h>
#include <linux/efi.h>
#include <linux/elf.h>
T
Tejun Heo 已提交
13
#include <linux/memblock.h>
L
Linus Torvalds 已提交
14 15 16 17 18 19 20 21 22
#include <linux/mm.h>
#include <linux/mmzone.h>
#include <linux/module.h>
#include <linux/personality.h>
#include <linux/reboot.h>
#include <linux/slab.h>
#include <linux/swap.h>
#include <linux/proc_fs.h>
#include <linux/bitops.h>
23
#include <linux/kexec.h>
L
Linus Torvalds 已提交
24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42

#include <asm/dma.h>
#include <asm/io.h>
#include <asm/machvec.h>
#include <asm/numa.h>
#include <asm/patch.h>
#include <asm/pgalloc.h>
#include <asm/sal.h>
#include <asm/sections.h>
#include <asm/tlb.h>
#include <asm/uaccess.h>
#include <asm/unistd.h>
#include <asm/mca.h>

extern void ia64_tlb_init (void);

unsigned long MAX_DMA_ADDRESS = PAGE_OFFSET + 0x100000000UL;

#ifdef CONFIG_VIRTUAL_MEM_MAP
43 44
unsigned long VMALLOC_END = VMALLOC_END_INIT;
EXPORT_SYMBOL(VMALLOC_END);
L
Linus Torvalds 已提交
45 46 47 48
struct page *vmem_map;
EXPORT_SYMBOL(vmem_map);
#endif

49
struct page *zero_page_memmap_ptr;	/* map entry for zero page */
L
Linus Torvalds 已提交
50 51 52
EXPORT_SYMBOL(zero_page_memmap_ptr);

void
53
__ia64_sync_icache_dcache (pte_t pte)
L
Linus Torvalds 已提交
54 55 56 57 58 59 60 61 62 63
{
	unsigned long addr;
	struct page *page;

	page = pte_page(pte);
	addr = (unsigned long) page_address(page);

	if (test_bit(PG_arch_1, &page->flags))
		return;				/* i-cache is already coherent with d-cache */

64
	flush_icache_range(addr, addr + (PAGE_SIZE << compound_order(page)));
L
Linus Torvalds 已提交
65 66 67
	set_bit(PG_arch_1, &page->flags);	/* mark page as clean */
}

J
Jan Beulich 已提交
68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86
/*
 * Since DMA is i-cache coherent, any (complete) pages that were written via
 * DMA can be marked as "clean" so that lazy_mmu_prot_update() doesn't have to
 * flush them when they get mapped into an executable vm-area.
 */
void
dma_mark_clean(void *addr, size_t size)
{
	unsigned long pg_addr, end;

	pg_addr = PAGE_ALIGN((unsigned long) addr);
	end = (unsigned long) addr + size;
	while (pg_addr + PAGE_SIZE <= end) {
		struct page *page = virt_to_page(pg_addr);
		set_bit(PG_arch_1, &page->flags);
		pg_addr += PAGE_SIZE;
	}
}

L
Linus Torvalds 已提交
87 88 89
inline void
ia64_set_rbs_bot (void)
{
J
Jiri Slaby 已提交
90
	unsigned long stack_size = rlimit_max(RLIMIT_STACK) & -16;
L
Linus Torvalds 已提交
91 92 93

	if (stack_size > MAX_USER_STACK_SIZE)
		stack_size = MAX_USER_STACK_SIZE;
94
	current->thread.rbs_bot = PAGE_ALIGN(current->mm->start_stack - stack_size);
L
Linus Torvalds 已提交
95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114
}

/*
 * This performs some platform-dependent address space initialization.
 * On IA-64, we want to setup the VM area for the register backing
 * store (which grows upwards) and install the gateway page which is
 * used for signal trampolines, etc.
 */
void
ia64_init_addr_space (void)
{
	struct vm_area_struct *vma;

	ia64_set_rbs_bot();

	/*
	 * If we're out of memory and kmem_cache_alloc() returns NULL, we simply ignore
	 * the problem.  When the process attempts to write to the register backing store
	 * for the first time, it will get a SEGFAULT in this case.
	 */
115
	vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
L
Linus Torvalds 已提交
116
	if (vma) {
117
		INIT_LIST_HEAD(&vma->anon_vma_chain);
L
Linus Torvalds 已提交
118 119 120
		vma->vm_mm = current->mm;
		vma->vm_start = current->thread.rbs_bot & PAGE_MASK;
		vma->vm_end = vma->vm_start + PAGE_SIZE;
H
Hugh Dickins 已提交
121
		vma->vm_flags = VM_DATA_DEFAULT_FLAGS|VM_GROWSUP|VM_ACCOUNT;
122
		vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
L
Linus Torvalds 已提交
123 124 125 126 127 128 129 130 131 132 133
		down_write(&current->mm->mmap_sem);
		if (insert_vm_struct(current->mm, vma)) {
			up_write(&current->mm->mmap_sem);
			kmem_cache_free(vm_area_cachep, vma);
			return;
		}
		up_write(&current->mm->mmap_sem);
	}

	/* map NaT-page at address zero to speed up speculative dereferencing of NULL: */
	if (!(current->personality & MMAP_PAGE_ZERO)) {
134
		vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
L
Linus Torvalds 已提交
135
		if (vma) {
136
			INIT_LIST_HEAD(&vma->anon_vma_chain);
L
Linus Torvalds 已提交
137 138 139
			vma->vm_mm = current->mm;
			vma->vm_end = PAGE_SIZE;
			vma->vm_page_prot = __pgprot(pgprot_val(PAGE_READONLY) | _PAGE_MA_NAT);
140 141
			vma->vm_flags = VM_READ | VM_MAYREAD | VM_IO |
					VM_DONTEXPAND | VM_DONTDUMP;
L
Linus Torvalds 已提交
142 143 144 145 146 147 148 149 150 151 152 153 154 155
			down_write(&current->mm->mmap_sem);
			if (insert_vm_struct(current->mm, vma)) {
				up_write(&current->mm->mmap_sem);
				kmem_cache_free(vm_area_cachep, vma);
				return;
			}
			up_write(&current->mm->mmap_sem);
		}
	}
}

void
free_initmem (void)
{
156
	free_reserved_area(ia64_imva(__init_begin), ia64_imva(__init_end),
157
			   -1, "unused kernel");
L
Linus Torvalds 已提交
158 159
}

160
void __init
L
Linus Torvalds 已提交
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
free_initrd_mem (unsigned long start, unsigned long end)
{
	/*
	 * EFI uses 4KB pages while the kernel can use 4KB or bigger.
	 * Thus EFI and the kernel may have different page sizes. It is
	 * therefore possible to have the initrd share the same page as
	 * the end of the kernel (given current setup).
	 *
	 * To avoid freeing/using the wrong page (kernel sized) we:
	 *	- align up the beginning of initrd
	 *	- align down the end of initrd
	 *
	 *  |             |
	 *  |=============| a000
	 *  |             |
	 *  |             |
	 *  |             | 9000
	 *  |/////////////|
	 *  |/////////////|
	 *  |=============| 8000
	 *  |///INITRD////|
	 *  |/////////////|
	 *  |/////////////| 7000
	 *  |             |
	 *  |KKKKKKKKKKKKK|
	 *  |=============| 6000
	 *  |KKKKKKKKKKKKK|
	 *  |KKKKKKKKKKKKK|
	 *  K=kernel using 8KB pages
	 *
	 * In this example, we must free page 8000 ONLY. So we must align up
	 * initrd_start and keep initrd_end as is.
	 */
	start = PAGE_ALIGN(start);
	end = end & PAGE_MASK;

	if (start < end)
		printk(KERN_INFO "Freeing initrd memory: %ldkB freed\n", (end - start) >> 10);

	for (; start < end; start += PAGE_SIZE) {
		if (!virt_addr_valid(start))
			continue;
203
		free_reserved_page(virt_to_page(start));
L
Linus Torvalds 已提交
204 205 206 207 208 209
	}
}

/*
 * This installs a clean page in the kernel's page table.
 */
210
static struct page * __init
L
Linus Torvalds 已提交
211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230
put_kernel_page (struct page *page, unsigned long address, pgprot_t pgprot)
{
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *pte;

	if (!PageReserved(page))
		printk(KERN_ERR "put_kernel_page: page at 0x%p not in reserved memory\n",
		       page_address(page));

	pgd = pgd_offset_k(address);		/* note: this is NOT pgd_offset()! */

	{
		pud = pud_alloc(&init_mm, pgd, address);
		if (!pud)
			goto out;
		pmd = pmd_alloc(&init_mm, pud, address);
		if (!pmd)
			goto out;
H
Hugh Dickins 已提交
231
		pte = pte_alloc_kernel(pmd, address);
L
Linus Torvalds 已提交
232 233
		if (!pte)
			goto out;
H
Hugh Dickins 已提交
234
		if (!pte_none(*pte))
L
Linus Torvalds 已提交
235 236 237
			goto out;
		set_pte(pte, mk_pte(page, pgprot));
	}
H
Hugh Dickins 已提交
238
  out:
L
Linus Torvalds 已提交
239 240 241 242
	/* no need for flush_tlb */
	return page;
}

243
static void __init
L
Linus Torvalds 已提交
244 245 246 247 248
setup_gate (void)
{
	struct page *page;

	/*
249 250 251
	 * Map the gate page twice: once read-only to export the ELF
	 * headers etc. and once execute-only page to enable
	 * privilege-promotion via "epc":
L
Linus Torvalds 已提交
252
	 */
L
Luis R. Rodriguez 已提交
253
	page = virt_to_page(ia64_imva(__start_gate_section));
L
Linus Torvalds 已提交
254 255
	put_kernel_page(page, GATE_ADDR, PAGE_READONLY);
#ifdef HAVE_BUGGY_SEGREL
L
Luis R. Rodriguez 已提交
256
	page = virt_to_page(ia64_imva(__start_gate_section + PAGE_SIZE));
L
Linus Torvalds 已提交
257 258 259
	put_kernel_page(page, GATE_ADDR + PAGE_SIZE, PAGE_GATE);
#else
	put_kernel_page(page, GATE_ADDR + PERCPU_PAGE_SIZE, PAGE_GATE);
260 261 262 263 264 265 266 267 268 269 270 271 272 273
	/* Fill in the holes (if any) with read-only zero pages: */
	{
		unsigned long addr;

		for (addr = GATE_ADDR + PAGE_SIZE;
		     addr < GATE_ADDR + PERCPU_PAGE_SIZE;
		     addr += PAGE_SIZE)
		{
			put_kernel_page(ZERO_PAGE(0), addr,
					PAGE_READONLY);
			put_kernel_page(ZERO_PAGE(0), addr + PERCPU_PAGE_SIZE,
					PAGE_READONLY);
		}
	}
L
Linus Torvalds 已提交
274 275 276 277
#endif
	ia64_patch_gate();
}

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
static struct vm_area_struct gate_vma;

static int __init gate_vma_init(void)
{
	gate_vma.vm_mm = NULL;
	gate_vma.vm_start = FIXADDR_USER_START;
	gate_vma.vm_end = FIXADDR_USER_END;
	gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC;
	gate_vma.vm_page_prot = __P101;

	return 0;
}
__initcall(gate_vma_init);

struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
{
	return &gate_vma;
}

int in_gate_area_no_mm(unsigned long addr)
{
	if ((addr >= FIXADDR_USER_START) && (addr < FIXADDR_USER_END))
		return 1;
	return 0;
}

int in_gate_area(struct mm_struct *mm, unsigned long addr)
{
	return in_gate_area_no_mm(addr);
}

309
void ia64_mmu_init(void *my_cpu_data)
L
Linus Torvalds 已提交
310
{
311
	unsigned long pta, impl_va_bits;
312
	extern void tlb_init(void);
L
Linus Torvalds 已提交
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

#ifdef CONFIG_DISABLE_VHPT
#	define VHPT_ENABLE_BIT	0
#else
#	define VHPT_ENABLE_BIT	1
#endif

	/*
	 * Check if the virtually mapped linear page table (VMLPT) overlaps with a mapped
	 * address space.  The IA-64 architecture guarantees that at least 50 bits of
	 * virtual address space are implemented but if we pick a large enough page size
	 * (e.g., 64KB), the mapped address space is big enough that it will overlap with
	 * VMLPT.  I assume that once we run on machines big enough to warrant 64KB pages,
	 * IMPL_VA_MSB will be significantly bigger, so this is unlikely to become a
	 * problem in practice.  Alternatively, we could truncate the top of the mapped
	 * address space to not permit mappings that would overlap with the VMLPT.
	 * --davidm 00/12/06
	 */
#	define pte_bits			3
#	define mapped_space_bits	(3*(PAGE_SHIFT - pte_bits) + PAGE_SHIFT)
	/*
	 * The virtual page table has to cover the entire implemented address space within
	 * a region even though not all of this space may be mappable.  The reason for
	 * this is that the Access bit and Dirty bit fault handlers perform
	 * non-speculative accesses to the virtual page table, so the address range of the
	 * virtual page table itself needs to be covered by virtual page table.
	 */
#	define vmlpt_bits		(impl_va_bits - PAGE_SHIFT + pte_bits)
#	define POW2(n)			(1ULL << (n))

	impl_va_bits = ffz(~(local_cpu_data->unimpl_va_mask | (7UL << 61)));

	if (impl_va_bits < 51 || impl_va_bits > 61)
		panic("CPU has bogus IMPL_VA_MSB value of %lu!\n", impl_va_bits - 1);
P
Peter Chubb 已提交
347 348 349 350 351 352 353 354 355 356 357 358
	/*
	 * mapped_space_bits - PAGE_SHIFT is the total number of ptes we need,
	 * which must fit into "vmlpt_bits - pte_bits" slots. Second half of
	 * the test makes sure that our mapped space doesn't overlap the
	 * unimplemented hole in the middle of the region.
	 */
	if ((mapped_space_bits - PAGE_SHIFT > vmlpt_bits - pte_bits) ||
	    (mapped_space_bits > impl_va_bits - 1))
		panic("Cannot build a big enough virtual-linear page table"
		      " to cover mapped address space.\n"
		      " Try using a smaller page size.\n");

L
Linus Torvalds 已提交
359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379

	/* place the VMLPT at the end of each page-table mapped region: */
	pta = POW2(61) - POW2(vmlpt_bits);

	/*
	 * Set the (virtually mapped linear) page table address.  Bit
	 * 8 selects between the short and long format, bits 2-7 the
	 * size of the table, and bit 0 whether the VHPT walker is
	 * enabled.
	 */
	ia64_set_pta(pta | (0 << 8) | (vmlpt_bits << 2) | VHPT_ENABLE_BIT);

	ia64_tlb_init();

#ifdef	CONFIG_HUGETLB_PAGE
	ia64_set_rr(HPAGE_REGION_BASE, HPAGE_SHIFT << 2);
	ia64_srlz_d();
#endif
}

#ifdef CONFIG_VIRTUAL_MEM_MAP
380 381 382 383 384 385 386 387
int vmemmap_find_next_valid_pfn(int node, int i)
{
	unsigned long end_address, hole_next_pfn;
	unsigned long stop_address;
	pg_data_t *pgdat = NODE_DATA(node);

	end_address = (unsigned long) &vmem_map[pgdat->node_start_pfn + i];
	end_address = PAGE_ALIGN(end_address);
388
	stop_address = (unsigned long) &vmem_map[pgdat_end_pfn(pgdat)];
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

	do {
		pgd_t *pgd;
		pud_t *pud;
		pmd_t *pmd;
		pte_t *pte;

		pgd = pgd_offset_k(end_address);
		if (pgd_none(*pgd)) {
			end_address += PGDIR_SIZE;
			continue;
		}

		pud = pud_offset(pgd, end_address);
		if (pud_none(*pud)) {
			end_address += PUD_SIZE;
			continue;
		}

		pmd = pmd_offset(pud, end_address);
		if (pmd_none(*pmd)) {
			end_address += PMD_SIZE;
			continue;
		}

		pte = pte_offset_kernel(pmd, end_address);
retry_pte:
		if (pte_none(*pte)) {
			end_address += PAGE_SIZE;
			pte++;
			if ((end_address < stop_address) &&
			    (end_address != ALIGN(end_address, 1UL << PMD_SHIFT)))
				goto retry_pte;
			continue;
		}
		/* Found next valid vmem_map page */
		break;
	} while (end_address < stop_address);

	end_address = min(end_address, stop_address);
	end_address = end_address - (unsigned long) vmem_map + sizeof(struct page) - 1;
	hole_next_pfn = end_address / sizeof(struct page);
	return hole_next_pfn - pgdat->node_start_pfn;
}
L
Linus Torvalds 已提交
433

434
int __init create_mem_map_page_table(u64 start, u64 end, void *arg)
L
Linus Torvalds 已提交
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
{
	unsigned long address, start_page, end_page;
	struct page *map_start, *map_end;
	int node;
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *pte;

	map_start = vmem_map + (__pa(start) >> PAGE_SHIFT);
	map_end   = vmem_map + (__pa(end) >> PAGE_SHIFT);

	start_page = (unsigned long) map_start & PAGE_MASK;
	end_page = PAGE_ALIGN((unsigned long) map_end);
	node = paddr_to_nid(__pa(start));

	for (address = start_page; address < end_page; address += PAGE_SIZE) {
		pgd = pgd_offset_k(address);
		if (pgd_none(*pgd))
			pgd_populate(&init_mm, pgd, alloc_bootmem_pages_node(NODE_DATA(node), PAGE_SIZE));
		pud = pud_offset(pgd, address);

		if (pud_none(*pud))
			pud_populate(&init_mm, pud, alloc_bootmem_pages_node(NODE_DATA(node), PAGE_SIZE));
		pmd = pmd_offset(pud, address);

		if (pmd_none(*pmd))
			pmd_populate_kernel(&init_mm, pmd, alloc_bootmem_pages_node(NODE_DATA(node), PAGE_SIZE));
		pte = pte_offset_kernel(pmd, address);

		if (pte_none(*pte))
			set_pte(pte, pfn_pte(__pa(alloc_bootmem_pages_node(NODE_DATA(node), PAGE_SIZE)) >> PAGE_SHIFT,
					     PAGE_KERNEL));
	}
	return 0;
}

struct memmap_init_callback_data {
	struct page *start;
	struct page *end;
	int nid;
	unsigned long zone;
};

479
static int __meminit
480
virtual_memmap_init(u64 start, u64 end, void *arg)
L
Linus Torvalds 已提交
481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504
{
	struct memmap_init_callback_data *args;
	struct page *map_start, *map_end;

	args = (struct memmap_init_callback_data *) arg;
	map_start = vmem_map + (__pa(start) >> PAGE_SHIFT);
	map_end   = vmem_map + (__pa(end) >> PAGE_SHIFT);

	if (map_start < args->start)
		map_start = args->start;
	if (map_end > args->end)
		map_end = args->end;

	/*
	 * We have to initialize "out of bounds" struct page elements that fit completely
	 * on the same pages that were allocated for the "in bounds" elements because they
	 * may be referenced later (and found to be "reserved").
	 */
	map_start -= ((unsigned long) map_start & (PAGE_SIZE - 1)) / sizeof(struct page);
	map_end += ((PAGE_ALIGN((unsigned long) map_end) - (unsigned long) map_end)
		    / sizeof(struct page));

	if (map_start < map_end)
		memmap_init_zone((unsigned long)(map_end - map_start),
D
Dave Hansen 已提交
505 506
				 args->nid, args->zone, page_to_pfn(map_start),
				 MEMMAP_EARLY);
L
Linus Torvalds 已提交
507 508 509
	return 0;
}

510
void __meminit
L
Linus Torvalds 已提交
511 512 513 514
memmap_init (unsigned long size, int nid, unsigned long zone,
	     unsigned long start_pfn)
{
	if (!vmem_map)
D
Dave Hansen 已提交
515
		memmap_init_zone(size, nid, zone, start_pfn, MEMMAP_EARLY);
L
Linus Torvalds 已提交
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
	else {
		struct page *start;
		struct memmap_init_callback_data args;

		start = pfn_to_page(start_pfn);
		args.start = start;
		args.end = start + size;
		args.nid = nid;
		args.zone = zone;

		efi_memmap_walk(virtual_memmap_init, &args);
	}
}

int
ia64_pfn_valid (unsigned long pfn)
{
	char byte;
	struct page *pg = pfn_to_page(pfn);

	return     (__get_user(byte, (char __user *) pg) == 0)
		&& ((((u64)pg & PAGE_MASK) == (((u64)(pg + 1) - 1) & PAGE_MASK))
			|| (__get_user(byte, (char __user *) (pg + 1) - 1) == 0));
}
EXPORT_SYMBOL(ia64_pfn_valid);

542
int __init find_largest_hole(u64 start, u64 end, void *arg)
L
Linus Torvalds 已提交
543 544 545 546 547 548 549 550 551 552 553 554
{
	u64 *max_gap = arg;

	static u64 last_end = PAGE_OFFSET;

	/* NOTE: this algorithm assumes efi memmap table is ordered */

	if (*max_gap < (start - last_end))
		*max_gap = start - last_end;
	last_end = end;
	return 0;
}
555

556 557
#endif /* CONFIG_VIRTUAL_MEM_MAP */

558
int __init register_active_ranges(u64 start, u64 len, int nid)
559
{
560
	u64 end = start + len;
561 562 563 564 565 566 567 568 569

#ifdef CONFIG_KEXEC
	if (start > crashk_res.start && start < crashk_res.end)
		start = crashk_res.end;
	if (end > crashk_res.start && end < crashk_res.end)
		end = crashk_res.start;
#endif

	if (start < end)
T
Tejun Heo 已提交
570
		memblock_add_node(__pa(start), end - start, nid);
571 572
	return 0;
}
L
Linus Torvalds 已提交
573

574
int
575
find_max_min_low_pfn (u64 start, u64 end, void *arg)
576 577 578 579 580 581 582 583 584 585 586 587 588 589
{
	unsigned long pfn_start, pfn_end;
#ifdef CONFIG_FLATMEM
	pfn_start = (PAGE_ALIGN(__pa(start))) >> PAGE_SHIFT;
	pfn_end = (PAGE_ALIGN(__pa(end - 1))) >> PAGE_SHIFT;
#else
	pfn_start = GRANULEROUNDDOWN(__pa(start)) >> PAGE_SHIFT;
	pfn_end = GRANULEROUNDUP(__pa(end - 1)) >> PAGE_SHIFT;
#endif
	min_low_pfn = min(min_low_pfn, pfn_start);
	max_low_pfn = max(max_low_pfn, pfn_end);
	return 0;
}

L
Linus Torvalds 已提交
590 591 592 593 594 595 596 597
/*
 * Boot command-line option "nolwsys" can be used to disable the use of any light-weight
 * system call handler.  When this option is in effect, all fsyscalls will end up bubbling
 * down into the kernel and calling the normal (heavy-weight) syscall handler.  This is
 * useful for performance testing, but conceivably could also come in handy for debugging
 * purposes.
 */

598
static int nolwsys __initdata;
L
Linus Torvalds 已提交
599 600 601 602 603 604 605 606 607 608

static int __init
nolwsys_setup (char *s)
{
	nolwsys = 1;
	return 1;
}

__setup("nolwsys", nolwsys_setup);

609
void __init
L
Linus Torvalds 已提交
610 611 612 613
mem_init (void)
{
	int i;

614 615 616 617
	BUG_ON(PTRS_PER_PGD * sizeof(pgd_t) != PAGE_SIZE);
	BUG_ON(PTRS_PER_PMD * sizeof(pmd_t) != PAGE_SIZE);
	BUG_ON(PTRS_PER_PTE * sizeof(pte_t) != PAGE_SIZE);

L
Linus Torvalds 已提交
618 619 620 621 622 623 624 625 626
#ifdef CONFIG_PCI
	/*
	 * This needs to be called _after_ the command line has been parsed but _before_
	 * any drivers that may need the PCI DMA interface are initialized or bootmem has
	 * been freed.
	 */
	platform_dma_init();
#endif

627
#ifdef CONFIG_FLATMEM
S
Stoyan Gaydarov 已提交
628
	BUG_ON(!mem_map);
L
Linus Torvalds 已提交
629 630
#endif

631
	set_max_mapnr(max_low_pfn);
L
Linus Torvalds 已提交
632
	high_memory = __va(max_low_pfn * PAGE_SIZE);
633
	free_all_bootmem();
634
	mem_init_print_info(NULL);
L
Linus Torvalds 已提交
635 636 637 638 639 640 641

	/*
	 * For fsyscall entrpoints with no light-weight handler, use the ordinary
	 * (heavy-weight) handler, but mark it by setting bit 0, so the fsyscall entry
	 * code can tell them apart.
	 */
	for (i = 0; i < NR_syscalls; ++i) {
L
Luis R. Rodriguez 已提交
642
		extern unsigned long fsyscall_table[NR_syscalls];
L
Linus Torvalds 已提交
643 644 645 646 647 648 649
		extern unsigned long sys_call_table[NR_syscalls];

		if (!fsyscall_table[i] || nolwsys)
			fsyscall_table[i] = sys_call_table[i] | 1;
	}
	setup_gate();
}
650 651

#ifdef CONFIG_MEMORY_HOTPLUG
652
int arch_add_memory(int nid, u64 start, u64 size)
653 654 655 656 657 658 659
{
	pg_data_t *pgdat;
	struct zone *zone;
	unsigned long start_pfn = start >> PAGE_SHIFT;
	unsigned long nr_pages = size >> PAGE_SHIFT;
	int ret;

660
	pgdat = NODE_DATA(nid);
661

662 663
	zone = pgdat->node_zones +
		zone_for_memory(nid, start, size, ZONE_NORMAL);
664
	ret = __add_pages(nid, zone, start_pfn, nr_pages);
665 666 667

	if (ret)
		printk("%s: Problem encountered in __add_pages() as ret=%d\n",
668
		       __func__,  ret);
669 670 671

	return ret;
}
672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689

#ifdef CONFIG_MEMORY_HOTREMOVE
int arch_remove_memory(u64 start, u64 size)
{
	unsigned long start_pfn = start >> PAGE_SHIFT;
	unsigned long nr_pages = size >> PAGE_SHIFT;
	struct zone *zone;
	int ret;

	zone = page_zone(pfn_to_page(start_pfn));
	ret = __remove_pages(zone, start_pfn, nr_pages);
	if (ret)
		pr_warn("%s: Problem encountered in __remove_pages() as"
			" ret=%d\n", __func__,  ret);

	return ret;
}
#endif
690
#endif
691

692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738
/**
 * show_mem - give short summary of memory stats
 *
 * Shows a simple page count of reserved and used pages in the system.
 * For discontig machines, it does this on a per-pgdat basis.
 */
void show_mem(unsigned int filter)
{
	int total_reserved = 0;
	unsigned long total_present = 0;
	pg_data_t *pgdat;

	printk(KERN_INFO "Mem-info:\n");
	show_free_areas(filter);
	printk(KERN_INFO "Node memory in pages:\n");
	for_each_online_pgdat(pgdat) {
		unsigned long present;
		unsigned long flags;
		int reserved = 0;
		int nid = pgdat->node_id;
		int zoneid;

		if (skip_free_areas_node(filter, nid))
			continue;
		pgdat_resize_lock(pgdat, &flags);

		for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) {
			struct zone *zone = &pgdat->node_zones[zoneid];
			if (!populated_zone(zone))
				continue;

			reserved += zone->present_pages - zone->managed_pages;
		}
		present = pgdat->node_present_pages;

		pgdat_resize_unlock(pgdat, &flags);
		total_present += present;
		total_reserved += reserved;
		printk(KERN_INFO "Node %4d:  RAM: %11ld, rsvd: %8d, ",
		       nid, present, reserved);
	}
	printk(KERN_INFO "%ld pages of RAM\n", total_present);
	printk(KERN_INFO "%d reserved pages\n", total_reserved);
	printk(KERN_INFO "Total of %ld pages in page table cache\n",
	       quicklist_total_size());
	printk(KERN_INFO "%ld free buffer pages\n", nr_free_buffer_pages());
}