summaryrefslogtreecommitdiffstats
path: root/mm/slab.c
diff options
context:
space:
mode:
authorManfred Spraul <manfred@colorfullife.com>2005-09-03 18:55:07 -0400
committerLinus Torvalds <torvalds@evo.osdl.org>2005-09-05 03:05:49 -0400
commit00e145b6d59a16dd7740197a18f7abdb3af004a9 (patch)
tree7b081ccfa6a34e5a17f4f1d6925d4945df2a97c1 /mm/slab.c
parent34342e863c3143640c031760140d640a06c6a5f8 (diff)
[PATCH] slab: removes local_irq_save()/local_irq_restore() pair
Proposed by and based on a patch from Eric Dumazet <dada1@cosmosbay.com>: This patch removes unnecessary critical section in ksize() function, as cli/sti are rather expensive on modern CPUS. It additionally adds a docbook entry for ksize() and further simplifies the code. Signed-Off-By: Manfred Spraul <manfred@colorfullife.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Diffstat (limited to 'mm/slab.c')
-rw-r--r--mm/slab.c26
1 files changed, 15 insertions, 11 deletions
diff --git a/mm/slab.c b/mm/slab.c
index 75127a6f1fd9..a9ff4f7f9860 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -3076,20 +3076,24 @@ ssize_t slabinfo_write(struct file *file, const char __user *buffer,
3076} 3076}
3077#endif 3077#endif
3078 3078
3079/**
3080 * ksize - get the actual amount of memory allocated for a given object
3081 * @objp: Pointer to the object
3082 *
3083 * kmalloc may internally round up allocations and return more memory
3084 * than requested. ksize() can be used to determine the actual amount of
3085 * memory allocated. The caller may use this additional memory, even though
3086 * a smaller amount of memory was initially specified with the kmalloc call.
3087 * The caller must guarantee that objp points to a valid object previously
3088 * allocated with either kmalloc() or kmem_cache_alloc(). The object
3089 * must not be freed during the duration of the call.
3090 */
3079unsigned int ksize(const void *objp) 3091unsigned int ksize(const void *objp)
3080{ 3092{
3081 kmem_cache_t *c; 3093 if (unlikely(objp == NULL))
3082 unsigned long flags; 3094 return 0;
3083 unsigned int size = 0;
3084
3085 if (likely(objp != NULL)) {
3086 local_irq_save(flags);
3087 c = GET_PAGE_CACHE(virt_to_page(objp));
3088 size = kmem_cache_size(c);
3089 local_irq_restore(flags);
3090 }
3091 3095
3092 return size; 3096 return obj_reallen(GET_PAGE_CACHE(virt_to_page(objp)));
3093} 3097}
3094 3098
3095 3099
generated by cgit v1.2.2 (git 2.25.0) at 2025-09-17 03:25:13 -0400
4' href='#n304'>304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 
/*
 *  linux/arch/i386/mm/init.c
 *
 *  Copyright (C) 1995  Linus Torvalds
 *
 *  Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
 */

#include <linux/module.h>
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/ptrace.h>
#include <linux/mman.h>
#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/swap.h>
#include <linux/smp.h>
#include <linux/init.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
#include <linux/pfn.h>
#include <linux/poison.h>
#include <linux/bootmem.h>
#include <linux/slab.h>
#include <linux/proc_fs.h>
#include <linux/memory_hotplug.h>
#include <linux/initrd.h>
#include <linux/cpumask.h>

#include <asm/asm.h>
#include <asm/processor.h>
#include <asm/system.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
#include <asm/dma.h>
#include <asm/fixmap.h>
#include <asm/e820.h>
#include <asm/apic.h>
#include <asm/bugs.h>
#include <asm/tlb.h>
#include <asm/tlbflush.h>
#include <asm/pgalloc.h>
#include <asm/sections.h>
#include <asm/paravirt.h>

unsigned int __VMALLOC_RESERVE = 128 << 20;

DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
unsigned long highstart_pfn, highend_pfn;

static noinline int do_test_wp_bit(void);

/*
 * Creates a middle page table and puts a pointer to it in the
 * given global directory entry. This only returns the gd entry
 * in non-PAE compilation mode, since the middle layer is folded.
 */
static pmd_t * __init one_md_table_init(pgd_t *pgd)
{
	pud_t *pud;
	pmd_t *pmd_table;

#ifdef CONFIG_X86_PAE
	if (!(pgd_val(*pgd) & _PAGE_PRESENT)) {
		pmd_table = (pmd_t *) alloc_bootmem_low_pages(PAGE_SIZE);

		paravirt_alloc_pd(&init_mm, __pa(pmd_table) >> PAGE_SHIFT);
		set_pgd(pgd, __pgd(__pa(pmd_table) | _PAGE_PRESENT));
		pud = pud_offset(pgd, 0);
		BUG_ON(pmd_table != pmd_offset(pud, 0));
	}
#endif
	pud = pud_offset(pgd, 0);
	pmd_table = pmd_offset(pud, 0);

	return pmd_table;
}

/*
 * Create a page table and place a pointer to it in a middle page
 * directory entry:
 */
static pte_t * __init one_page_table_init(pmd_t *pmd)
{
	if (!(pmd_val(*pmd) & _PAGE_PRESENT)) {
		pte_t *page_table = NULL;

#ifdef CONFIG_DEBUG_PAGEALLOC
		page_table = (pte_t *) alloc_bootmem_pages(PAGE_SIZE);
#endif
		if (!page_table) {
			page_table =
				(pte_t *)alloc_bootmem_low_pages(PAGE_SIZE);
		}

		paravirt_alloc_pt(&init_mm, __pa(page_table) >> PAGE_SHIFT);
		set_pmd(pmd, __pmd(__pa(page_table) | _PAGE_TABLE));
		BUG_ON(page_table != pte_offset_kernel(pmd, 0));
	}

	return pte_offset_kernel(pmd, 0);
}

/*
 * This function initializes a certain range of kernel virtual memory
 * with new bootmem page tables, everywhere page tables are missing in
 * the given range.
 *
 * NOTE: The pagetables are allocated contiguous on the physical space
 * so we can cache the place of the first one and move around without
 * checking the pgd every time.
 */
static void __init
page_table_range_init(unsigned long start, unsigned long end, pgd_t *pgd_base)
{
	int pgd_idx, pmd_idx;
	unsigned long vaddr;
	pgd_t *pgd;
	pmd_t *pmd;

	vaddr = start;
	pgd_idx = pgd_index(vaddr);
	pmd_idx = pmd_index(vaddr);
	pgd = pgd_base + pgd_idx;

	for ( ; (pgd_idx < PTRS_PER_PGD) && (vaddr != end); pgd++, pgd_idx++) {
		pmd = one_md_table_init(pgd);
		pmd = pmd + pmd_index(vaddr);
		for (; (pmd_idx < PTRS_PER_PMD) && (vaddr != end);
							pmd++, pmd_idx++) {
			one_page_table_init(pmd);

			vaddr += PMD_SIZE;
		}
		pmd_idx = 0;
	}
}

static inline int is_kernel_text(unsigned long addr)
{
	if (addr >= PAGE_OFFSET && addr <= (unsigned long)__init_end)
		return 1;
	return 0;
}

/*
 * This maps the physical memory to kernel virtual address space, a total
 * of max_low_pfn pages, by creating page tables starting from address
 * PAGE_OFFSET:
 */
static void __init kernel_physical_mapping_init(pgd_t *pgd_base)
{
	int pgd_idx, pmd_idx, pte_ofs;
	unsigned long pfn;
	pgd_t *pgd;
	pmd_t *pmd;
	pte_t *pte;

	pgd_idx = pgd_index(PAGE_OFFSET);
	pgd = pgd_base + pgd_idx;
	pfn = 0;

	for (; pgd_idx < PTRS_PER_PGD; pgd++, pgd_idx++) {
		pmd = one_md_table_init(pgd);
		if (pfn >= max_low_pfn)
			continue;

		for (pmd_idx = 0;
		     pmd_idx < PTRS_PER_PMD && pfn < max_low_pfn;
		     pmd++, pmd_idx++) {
			unsigned int addr = pfn * PAGE_SIZE + PAGE_OFFSET;

			/*
			 * Map with big pages if possible, otherwise
			 * create normal page tables:
			 */
			if (cpu_has_pse) {
				unsigned int addr2;
				pgprot_t prot = PAGE_KERNEL_LARGE;

				addr2 = (pfn + PTRS_PER_PTE-1) * PAGE_SIZE +
					PAGE_OFFSET + PAGE_SIZE-1;

				if (is_kernel_text(addr) ||
				    is_kernel_text(addr2))
					prot = PAGE_KERNEL_LARGE_EXEC;

				set_pmd(pmd, pfn_pmd(pfn, prot));

				pfn += PTRS_PER_PTE;
				continue;
			}
			pte = one_page_table_init(pmd);

			for (pte_ofs = 0;
			     pte_ofs < PTRS_PER_PTE && pfn < max_low_pfn;
			     pte++, pfn++, pte_ofs++, addr += PAGE_SIZE) {
				pgprot_t prot = PAGE_KERNEL;

				if (is_kernel_text(addr))
					prot = PAGE_KERNEL_EXEC;

				set_pte(pte, pfn_pte(pfn, prot));
			}
		}
	}
}

static inline int page_kills_ppro(unsigned long pagenr)
{
	if (pagenr >= 0x70000 && pagenr <= 0x7003F)
		return 1;
	return 0;
}

#ifdef CONFIG_HIGHMEM
pte_t *kmap_pte;
pgprot_t kmap_prot;

static inline pte_t *kmap_get_fixmap_pte(unsigned long vaddr)
{
	return pte_offset_kernel(pmd_offset(pud_offset(pgd_offset_k(vaddr),
			vaddr), vaddr), vaddr);
}

static void __init kmap_init(void)
{
	unsigned long kmap_vstart;

	/*
	 * Cache the first kmap pte:
	 */
	kmap_vstart = __fix_to_virt(FIX_KMAP_BEGIN);
	kmap_pte = kmap_get_fixmap_pte(kmap_vstart);

	kmap_prot = PAGE_KERNEL;
}

static void __init permanent_kmaps_init(pgd_t *pgd_base)
{
	unsigned long vaddr;
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *pte;

	vaddr = PKMAP_BASE;
	page_table_range_init(vaddr, vaddr + PAGE_SIZE*LAST_PKMAP, pgd_base);

	pgd = swapper_pg_dir + pgd_index(vaddr);
	pud = pud_offset(pgd, vaddr);
	pmd = pmd_offset(pud, vaddr);
	pte = pte_offset_kernel(pmd, vaddr);
	pkmap_page_table = pte;
}

static void __meminit free_new_highpage(struct page *page)
{
	init_page_count(page);
	__free_page(page);
	totalhigh_pages++;
}

void __init add_one_highpage_init(struct page *page, int pfn, int bad_ppro)
{
	if (page_is_ram(pfn) && !(bad_ppro && page_kills_ppro(pfn))) {
		ClearPageReserved(page);
		free_new_highpage(page);
	} else
		SetPageReserved(page);
}

static int __meminit
add_one_highpage_hotplug(struct page *page, unsigned long pfn)
{
	free_new_highpage(page);
	totalram_pages++;
#ifdef CONFIG_FLATMEM
	max_mapnr = max(pfn, max_mapnr);
#endif
	num_physpages++;

	return 0;
}

/*
 * Not currently handling the NUMA case.
 * Assuming single node and all memory that
 * has been added dynamically that would be
 * onlined here is in HIGHMEM.
 */
void __meminit online_page(struct page *page)
{
	ClearPageReserved(page);
	add_one_highpage_hotplug(page, page_to_pfn(page));
}

#ifndef CONFIG_NUMA
static void __init set_highmem_pages_init(int bad_ppro)
{
	int pfn;

	for (pfn = highstart_pfn; pfn < highend_pfn; pfn++) {
		/*
		 * Holes under sparsemem might not have no mem_map[]:
		 */
		if (pfn_valid(pfn))
			add_one_highpage_init(pfn_to_page(pfn), pfn, bad_ppro);
	}
	totalram_pages += totalhigh_pages;
}
#endif /* !CONFIG_NUMA */

#else
# define kmap_init()				do { } while (0)
# define permanent_kmaps_init(pgd_base)		do { } while (0)
# define set_highmem_pages_init(bad_ppro)	do { } while (0)
#endif /* CONFIG_HIGHMEM */

pteval_t __PAGE_KERNEL = _PAGE_KERNEL;
EXPORT_SYMBOL(__PAGE_KERNEL);

pteval_t __PAGE_KERNEL_EXEC = _PAGE_KERNEL_EXEC;

void __init native_pagetable_setup_start(pgd_t *base)
{
#ifdef CONFIG_X86_PAE
	int i;

	/*
	 * Init entries of the first-level page table to the
	 * zero page, if they haven't already been set up.
	 *
	 * In a normal native boot, we'll be running on a
	 * pagetable rooted in swapper_pg_dir, but not in PAE
	 * mode, so this will end up clobbering the mappings
	 * for the lower 24Mbytes of the address space,
	 * without affecting the kernel address space.
	 */
	for (i = 0; i < USER_PTRS_PER_PGD; i++)
		set_pgd(&base[i],
			__pgd(__pa(empty_zero_page) | _PAGE_PRESENT));

	/* Make sure kernel address space is empty so that a pagetable
	   will be allocated for it. */
	memset(&base[USER_PTRS_PER_PGD], 0,
	       KERNEL_PGD_PTRS * sizeof(pgd_t));
#else
	paravirt_alloc_pd(&init_mm, __pa(base) >> PAGE_SHIFT);
#endif
}

void __init native_pagetable_setup_done(pgd_t *base)
{
#ifdef CONFIG_X86_PAE
	/*
	 * Add low memory identity-mappings - SMP needs it when
	 * starting up on an AP from real-mode. In the non-PAE
	 * case we already have these mappings through head.S.
	 * All user-space mappings are explicitly cleared after
	 * SMP startup.
	 */
	set_pgd(&base[0], base[USER_PTRS_PER_PGD]);
#endif
}

/*
 * Build a proper pagetable for the kernel mappings.  Up until this
 * point, we've been running on some set of pagetables constructed by
 * the boot process.
 *
 * If we're booting on native hardware, this will be a pagetable
 * constructed in arch/i386/kernel/head.S, and not running in PAE mode
 * (even if we'll end up running in PAE).  The root of the pagetable
 * will be swapper_pg_dir.
 *
 * If we're booting paravirtualized under a hypervisor, then there are
 * more options: we may already be running PAE, and the pagetable may
 * or may not be based in swapper_pg_dir.  In any case,
 * paravirt_pagetable_setup_start() will set up swapper_pg_dir
 * appropriately for the rest of the initialization to work.
 *
 * In general, pagetable_init() assumes that the pagetable may already
 * be partially populated, and so it avoids stomping on any existing
 * mappings.
 */
static void __init pagetable_init(void)
{
	pgd_t *pgd_base = swapper_pg_dir;
	unsigned long vaddr, end;

	paravirt_pagetable_setup_start(pgd_base);

	/* Enable PSE if available */
	if (cpu_has_pse)
		set_in_cr4(X86_CR4_PSE);

	/* Enable PGE if available */
	if (cpu_has_pge) {
		set_in_cr4(X86_CR4_PGE);
		__PAGE_KERNEL |= _PAGE_GLOBAL;
		__PAGE_KERNEL_EXEC |= _PAGE_GLOBAL;
	}

	kernel_physical_mapping_init(pgd_base);
	remap_numa_kva();

	/*
	 * Fixed mappings, only the page table structure has to be
	 * created - mappings will be set by set_fixmap():
	 */
	early_ioremap_clear();
	vaddr = __fix_to_virt(__end_of_fixed_addresses - 1) & PMD_MASK;
	end = (FIXADDR_TOP + PMD_SIZE - 1) & PMD_MASK;
	page_table_range_init(vaddr, end, pgd_base);
	early_ioremap_reset();

	permanent_kmaps_init(pgd_base);

	paravirt_pagetable_setup_done(pgd_base);
}

#ifdef CONFIG_ACPI_SLEEP
/*
 * ACPI suspend needs this for resume, because things like the intel-agp
 * driver might have split up a kernel 4MB mapping.
 */
char swsusp_pg_dir[PAGE_SIZE]
	__attribute__ ((aligned(PAGE_SIZE)));

static inline void save_pg_dir(void)
{
	memcpy(swsusp_pg_dir, swapper_pg_dir, PAGE_SIZE);
}
#else /* !CONFIG_ACPI_SLEEP */
static inline void save_pg_dir(void)
{
}
#endif /* !CONFIG_ACPI_SLEEP */

void zap_low_mappings(void)
{
	int i;

	save_pg_dir();

	/*
	 * Zap initial low-memory mappings.
	 *
	 * Note that "pgd_clear()" doesn't do it for
	 * us, because pgd_clear() is a no-op on i386.
	 */
	for (i = 0; i < USER_PTRS_PER_PGD; i++) {
#ifdef CONFIG_X86_PAE
		set_pgd(swapper_pg_dir+i, __pgd(1 + __pa(empty_zero_page)));
#else
		set_pgd(swapper_pg_dir+i, __pgd(0));
#endif
	}
	flush_tlb_all();
}

int nx_enabled;

pteval_t __supported_pte_mask __read_mostly = ~_PAGE_NX;
EXPORT_SYMBOL_GPL(__supported_pte_mask);

#ifdef CONFIG_X86_PAE

static int disable_nx __initdata;

/*
 * noexec = on|off
 *
 * Control non executable mappings.
 *
 * on      Enable
 * off     Disable
 */
static int __init noexec_setup(char *str)
{
	if (!str || !strcmp(str, "on")) {
		if (cpu_has_nx) {
			__supported_pte_mask |= _PAGE_NX;
			disable_nx = 0;
		}
	} else {
		if (!strcmp(str, "off")) {
			disable_nx = 1;
			__supported_pte_mask &= ~_PAGE_NX;
		} else {
			return -EINVAL;
		}
	}

	return 0;
}
early_param("noexec", noexec_setup);

static void __init set_nx(void)
{
	unsigned int v[4], l, h;

	if (cpu_has_pae && (cpuid_eax(0x80000000) > 0x80000001)) {
		cpuid(0x80000001, &v[0], &v[1], &v[2], &v[3]);

		if ((v[3] & (1 << 20)) && !disable_nx) {
			rdmsr(MSR_EFER, l, h);
			l |= EFER_NX;
			wrmsr(MSR_EFER, l, h);
			nx_enabled = 1;
			__supported_pte_mask |= _PAGE_NX;
		}
	}
}
#endif

/*
 * paging_init() sets up the page tables - note that the first 8MB are
 * already mapped by head.S.
 *
 * This routines also unmaps the page at virtual kernel address 0, so
 * that we can trap those pesky NULL-reference errors in the kernel.
 */
void __init paging_init(void)
{
#ifdef CONFIG_X86_PAE
	set_nx();
	if (nx_enabled)
		printk(KERN_INFO "NX (Execute Disable) protection: active\n");
#endif
	pagetable_init();

	load_cr3(swapper_pg_dir);

#ifdef CONFIG_X86_PAE
	/*
	 * We will bail out later - printk doesn't work right now so
	 * the user would just see a hanging kernel.
	 */
	if (cpu_has_pae)
		set_in_cr4(X86_CR4_PAE);
#endif
	__flush_tlb_all();

	kmap_init();
}

/*
 * Test if the WP bit works in supervisor mode. It isn't supported on 386's
 * and also on some strange 486's (NexGen etc.). All 586+'s are OK. This
 * used to involve black magic jumps to work around some nasty CPU bugs,
 * but fortunately the switch to using exceptions got rid of all that.
 */
static void __init test_wp_bit(void)
{
	printk(KERN_INFO
  "Checking if this processor honours the WP bit even in supervisor mode...");

	/* Any page-aligned address will do, the test is non-destructive */
	__set_fixmap(FIX_WP_TEST, __pa(&swapper_pg_dir), PAGE_READONLY);
	boot_cpu_data.wp_works_ok = do_test_wp_bit();
	clear_fixmap(FIX_WP_TEST);

	if (!boot_cpu_data.wp_works_ok) {
		printk(KERN_CONT "No.\n");
#ifdef CONFIG_X86_WP_WORKS_OK
		panic(
  "This kernel doesn't support CPU's with broken WP. Recompile it for a 386!");
#endif
	} else {
		printk(KERN_CONT "Ok.\n");
	}
}

static struct kcore_list kcore_mem, kcore_vmalloc;

void __init mem_init(void)
{
	int codesize, reservedpages, datasize, initsize;
	int tmp, bad_ppro;

#ifdef CONFIG_FLATMEM
	BUG_ON(!mem_map);
#endif
	bad_ppro = ppro_with_ram_bug();

#ifdef CONFIG_HIGHMEM
	/* check that fixmap and pkmap do not overlap */
	if (PKMAP_BASE + LAST_PKMAP*PAGE_SIZE >= FIXADDR_START) {
		printk(KERN_ERR
			"fixmap and kmap areas overlap - this will crash\n");
		printk(KERN_ERR "pkstart: %lxh pkend: %lxh fixstart %lxh\n",
				PKMAP_BASE, PKMAP_BASE + LAST_PKMAP*PAGE_SIZE,
				FIXADDR_START);
		BUG();
	}
#endif
	/* this will put all low memory onto the freelists */
	totalram_pages += free_all_bootmem();

	reservedpages = 0;
	for (tmp = 0; tmp < max_low_pfn; tmp++)
		/*
		 * Only count reserved RAM pages:
		 */
		if (page_is_ram(tmp) && PageReserved(pfn_to_page(tmp)))
			reservedpages++;

	set_highmem_pages_init(bad_ppro);

	codesize =  (unsigned long) &_etext - (unsigned long) &_text;
	datasize =  (unsigned long) &_edata - (unsigned long) &_etext;
	initsize =  (unsigned long) &__init_end - (unsigned long) &__init_begin;

	kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT);
	kclist_add(&kcore_vmalloc, (void *)VMALLOC_START,
		   VMALLOC_END-VMALLOC_START);

	printk(KERN_INFO "Memory: %luk/%luk available (%dk kernel code, "
			"%dk reserved, %dk data, %dk init, %ldk highmem)\n",
		(unsigned long) nr_free_pages() << (PAGE_SHIFT-10),
		num_physpages << (PAGE_SHIFT-10),
		codesize >> 10,
		reservedpages << (PAGE_SHIFT-10),
		datasize >> 10,
		initsize >> 10,
		(unsigned long) (totalhigh_pages << (PAGE_SHIFT-10))
	       );

#if 1 /* double-sanity-check paranoia */
	printk(KERN_INFO "virtual kernel memory layout:\n"
		"    fixmap  : 0x%08lx - 0x%08lx   (%4ld kB)\n"
#ifdef CONFIG_HIGHMEM
		"    pkmap   : 0x%08lx - 0x%08lx   (%4ld kB)\n"
#endif
		"    vmalloc : 0x%08lx - 0x%08lx   (%4ld MB)\n"
		"    lowmem  : 0x%08lx - 0x%08lx   (%4ld MB)\n"
		"      .init : 0x%08lx - 0x%08lx   (%4ld kB)\n"
		"      .data : 0x%08lx - 0x%08lx   (%4ld kB)\n"
		"      .text : 0x%08lx - 0x%08lx   (%4ld kB)\n",
		FIXADDR_START, FIXADDR_TOP,
		(FIXADDR_TOP - FIXADDR_START) >> 10,

#ifdef CONFIG_HIGHMEM
		PKMAP_BASE, PKMAP_BASE+LAST_PKMAP*PAGE_SIZE,
		(LAST_PKMAP*PAGE_SIZE) >> 10,
#endif

		VMALLOC_START, VMALLOC_END,
		(VMALLOC_END - VMALLOC_START) >> 20,

		(unsigned long)__va(0), (unsigned long)high_memory,
		((unsigned long)high_memory - (unsigned long)__va(0)) >> 20,

		(unsigned long)&__init_begin, (unsigned long)&__init_end,
		((unsigned long)&__init_end -
		 (unsigned long)&__init_begin) >> 10,

		(unsigned long)&_etext, (unsigned long)&_edata,
		((unsigned long)&_edata - (unsigned long)&_etext) >> 10,

		(unsigned long)&_text, (unsigned long)&_etext,
		((unsigned long)&_etext - (unsigned long)&_text) >> 10);

#ifdef CONFIG_HIGHMEM
	BUG_ON(PKMAP_BASE + LAST_PKMAP*PAGE_SIZE	> FIXADDR_START);
	BUG_ON(VMALLOC_END				> PKMAP_BASE);
#endif
	BUG_ON(VMALLOC_START				> VMALLOC_END);
	BUG_ON((unsigned long)high_memory		> VMALLOC_START);
#endif /* double-sanity-check paranoia */

#ifdef CONFIG_X86_PAE
	if (!cpu_has_pae)
		panic("cannot execute a PAE-enabled kernel on a PAE-less CPU!");
#endif
	if (boot_cpu_data.wp_works_ok < 0)
		test_wp_bit();

	/*
	 * Subtle. SMP is doing it's boot stuff late (because it has to
	 * fork idle threads) - but it also needs low mappings for the
	 * protected-mode entry to work. We zap these entries only after
	 * the WP-bit has been tested.
	 */
#ifndef CONFIG_SMP
	zap_low_mappings();
#endif
}

#ifdef CONFIG_MEMORY_HOTPLUG
int arch_add_memory(int nid, u64 start, u64 size)
{
	struct pglist_data *pgdata = NODE_DATA(nid);
	struct zone *zone = pgdata->node_zones + ZONE_HIGHMEM;
	unsigned long start_pfn = start >> PAGE_SHIFT;
	unsigned long nr_pages = size >> PAGE_SHIFT;

	return __add_pages(zone, start_pfn, nr_pages);
}
#endif

/*
 * This function cannot be __init, since exceptions don't work in that
 * section.  Put this after the callers, so that it cannot be inlined.
 */
static noinline int do_test_wp_bit(void)
{
	char tmp_reg;
	int flag;

	__asm__ __volatile__(
		"	movb %0, %1	\n"
		"1:	movb %1, %0	\n"
		"	xorl %2, %2	\n"
		"2:			\n"
		_ASM_EXTABLE(1b,2b)
		:"=m" (*(char *)fix_to_virt(FIX_WP_TEST)),
		 "=q" (tmp_reg),
		 "=r" (flag)
		:"2" (1)
		:"memory");

	return flag;
}

#ifdef CONFIG_DEBUG_RODATA
const int rodata_test_data = 0xC3;
EXPORT_SYMBOL_GPL(rodata_test_data);

void mark_rodata_ro(void)
{
	unsigned long start = PFN_ALIGN(_text);
	unsigned long size = PFN_ALIGN(_etext) - start;

#ifndef CONFIG_KPROBES
#ifdef CONFIG_HOTPLUG_CPU
	/* It must still be possible to apply SMP alternatives. */
	if (num_possible_cpus() <= 1)
#endif
	{
		set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
		printk(KERN_INFO "Write protecting the kernel text: %luk\n",
			size >> 10);

#ifdef CONFIG_CPA_DEBUG
		printk(KERN_INFO "Testing CPA: Reverting %lx-%lx\n",
			start, start+size);
		set_pages_rw(virt_to_page(start), size>>PAGE_SHIFT);

		printk(KERN_INFO "Testing CPA: write protecting again\n");
		set_pages_ro(virt_to_page(start), size>>PAGE_SHIFT);
#endif
	}
#endif
	start += size;
	size = (unsigned long)__end_rodata - start;
	set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
	printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n",
		size >> 10);
	rodata_test();

#ifdef CONFIG_CPA_DEBUG
	printk(KERN_INFO "Testing CPA: undo %lx-%lx\n", start, start + size);
	set_pages_rw(virt_to_page(start), size >> PAGE_SHIFT);

	printk(KERN_INFO "Testing CPA: write protecting again\n");
	set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
#endif
}
#endif

void free_init_pages(char *what, unsigned long begin, unsigned long end)
{
#ifdef CONFIG_DEBUG_PAGEALLOC
	/*
	 * If debugging page accesses then do not free this memory but
	 * mark them not present - any buggy init-section access will
	 * create a kernel page fault:
	 */
	printk(KERN_INFO "debug: unmapping init memory %08lx..%08lx\n",
		begin, PAGE_ALIGN(end));
	set_memory_np(begin, (end - begin) >> PAGE_SHIFT);
#else
	unsigned long addr;

	/*
	 * We just marked the kernel text read only above, now that
	 * we are going to free part of that, we need to make that
	 * writeable first.
	 */
	set_memory_rw(begin, (end - begin) >> PAGE_SHIFT);

	for (addr = begin; addr < end; addr += PAGE_SIZE) {
		ClearPageReserved(virt_to_page(addr));
		init_page_count(virt_to_page(addr));
		memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE);
		free_page(addr);
		totalram_pages++;
	}
	printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10);
#endif
}

void free_initmem(void)
{
	free_init_pages("unused kernel memory",
			(unsigned long)(&__init_begin),
			(unsigned long)(&__init_end));
}

#ifdef CONFIG_BLK_DEV_INITRD
void free_initrd_mem(unsigned long start, unsigned long end)
{
	free_init_pages("initrd memory", start, end);
}
#endif
generated by cgit v1.2.2 (git 2.25.0) at 2025-09-17 03:25:13 -0400