init.c

linux-2.4.29操作系统的源码

/*
 * Initialize MMU support.
 *
 * Copyright (C) 1998-2002 Hewlett-Packard Co
 *	David Mosberger-Tang <[e-mail]>
 */
#include <linux/config.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/init.h>

#include <linux/bootmem.h>
#include <linux/mm.h>
#include <linux/personality.h>
#include <linux/reboot.h>
#include <linux/slab.h>
#include <linux/swap.h>
#include <linux/efi.h>
#include <linux/mmzone.h>

#include <asm/bitops.h>
#include <asm/dma.h>
#include <asm/ia32.h>
#include <asm/io.h>
#include <asm/machvec.h>
#include <asm/numa.h>
#include <asm/pgalloc.h>
#include <asm/sal.h>
#include <asm/system.h>
#include <asm/uaccess.h>
#include <asm/mca.h>

/* References to section boundaries: */
extern char _stext, _etext, _edata, __init_begin, __init_end;

extern void ia64_tlb_init (void);
extern int  filter_rsvd_memory (unsigned long, unsigned long, void *);

/* Note - may be changed by platform_setup */
unsigned long MAX_DMA_ADDRESS = PAGE_OFFSET + 0x100000000UL;
#define LARGE_GAP 0x40000000 /* Use virtual mem map if a hole is > than this */

static unsigned long totalram_pages, reserved_pages;
struct page *zero_page_memmap_ptr;		/* map entry for zero page */

unsigned long vmalloc_end = VMALLOC_END_INIT;

static struct page *vmem_map;
static unsigned long num_dma_physpages;

int
do_check_pgt_cache (int low, int high)
{
	int freed = 0;

	if (pgtable_cache_size > high) {
		do {
			if (pgd_quicklist)
				free_page((unsigned long)pgd_alloc_one_fast(0)), ++freed;
			if (pmd_quicklist)
				free_page((unsigned long)pmd_alloc_one_fast(0, 0)), ++freed;
			if (pte_quicklist)
				free_page((unsigned long)pte_alloc_one_fast(0, 0)), ++freed;
		} while (pgtable_cache_size > low);
	}
	return freed;
}

inline void
ia64_set_rbs_bot (void)
{
	unsigned long stack_size = current->rlim[RLIMIT_STACK].rlim_max & -16;

	if (stack_size > MAX_USER_STACK_SIZE)
		stack_size = MAX_USER_STACK_SIZE;
	current->thread.rbs_bot = STACK_TOP - stack_size;
}

/*
 * 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.
	 */
	vma = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
	if (vma) {
		vma->vm_mm = current->mm;
		vma->vm_start = current->thread.rbs_bot & PAGE_MASK;
		vma->vm_end = vma->vm_start + PAGE_SIZE;
		vma->vm_page_prot = PAGE_COPY;
		vma->vm_flags = VM_READ|VM_WRITE|VM_MAYREAD|VM_MAYWRITE|VM_GROWSUP;
		vma->vm_ops = NULL;
		vma->vm_pgoff = 0;
		vma->vm_file = NULL;
		vma->vm_private_data = NULL;
		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)) {
		vma = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
		if (vma) {
			memset(vma, 0, sizeof(*vma));
			vma->vm_mm = current->mm;
			vma->vm_end = PAGE_SIZE;
			vma->vm_page_prot = __pgprot(pgprot_val(PAGE_READONLY) | _PAGE_MA_NAT);
			vma->vm_flags = VM_READ | VM_MAYREAD | VM_IO | VM_RESERVED;
			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)
{
	unsigned long addr, eaddr;

	addr = (unsigned long) ia64_imva(&__init_begin);
	eaddr = (unsigned long) ia64_imva(&__init_end);
	for (; addr < eaddr; addr += PAGE_SIZE) {
		clear_bit(PG_reserved, &virt_to_page((void *)addr)->flags);
		set_page_count(virt_to_page((void *)addr), 1);
		free_page(addr);
		++totalram_pages;
	}
	printk(KERN_INFO "Freeing unused kernel memory: %ldkB freed\n",
		(&__init_end - &__init_begin) >> 10);
}

void
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 (!VALID_PAGE(virt_to_page((void *)start)))
			continue;
		clear_bit(PG_reserved, &virt_to_page((void *)start)->flags);
		set_page_count(virt_to_page((void *)start), 1);
		free_page(start);
		++totalram_pages;
	}
}

void
si_meminfo (struct sysinfo *val)
{
	val->totalram = totalram_pages;
	val->sharedram = 0;
	val->freeram = nr_free_pages();
	val->bufferram = atomic_read(&buffermem_pages);
	val->totalhigh = 0;
	val->freehigh = 0;
	val->mem_unit = PAGE_SIZE;
	return;
}

void
show_mem(void)
{
	int i, reserved;
	int shared, cached;
	pg_data_t *pgdat;
	char *tchar = (numnodes > 1) ? "\t" : "";

	printk("Mem-info:\n");
	show_free_areas();

	printk("Free swap:       %6dkB\n", nr_swap_pages<<(PAGE_SHIFT-10));
	for_each_pgdat(pgdat) {
		reserved=0;
		cached=0;
		shared=0;
		if (numnodes > 1)
			printk("Node ID: %d\n", pgdat->node_id);
		for(i = 0; i < pgdat->node_size; i++) {
			if (!VALID_PAGE(pgdat->node_mem_map+i))
				continue;
			if (PageReserved(pgdat->node_mem_map+i))
				reserved++;
			else if (PageSwapCache(pgdat->node_mem_map+i))
				cached++;
			else if (page_count(pgdat->node_mem_map + i))
				shared += page_count(pgdat->node_mem_map + i) - 1;
		}
		printk("%s%ld pages of RAM\n", tchar, pgdat->node_size);
		printk("%s%d reserved pages\n", tchar, reserved);
		printk("%s%d pages shared\n", tchar, shared);
		printk("%s%d pages swap cached\n", tchar, cached);
	}
	printk("Total of %ld pages in page table cache\n", pgtable_cache_size);
	show_buffers();
	printk("%d free buffer pages\n", nr_free_buffer_pages());
}

/*
 * This is like put_dirty_page() but installs a clean page with PAGE_GATE protection
 * (execute-only, typically).
 */
struct page *
put_gate_page (struct page *page, unsigned long address)
{
	pgd_t *pgd;
	pmd_t *pmd;
	pte_t *pte;

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

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

	spin_lock(&init_mm.page_table_lock);
	{
		pmd = pmd_alloc(&init_mm, pgd, address);
		if (!pmd)
			goto out;
		pte = pte_alloc(&init_mm, pmd, address);
		if (!pte)
			goto out;
		if (!pte_none(*pte)) {
			pte_ERROR(*pte);
			goto out;
		}
		flush_page_to_ram(page);
		set_pte(pte, mk_pte(page, PAGE_GATE));
	}
  out:	spin_unlock(&init_mm.page_table_lock);
	/* no need for flush_tlb */
	return page;
}

void __init
ia64_mmu_init (void *my_cpu_data)
{
	unsigned long psr, rid, pta, impl_va_bits;
	extern void __init tlb_init (void);
#ifdef CONFIG_IA64_MCA
	int cpu;
#endif

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

	/*
	 * Set up the kernel identity mapping for regions 6 and 5.  The mapping for region
	 * 7 is setup up in _start().
	 */
	psr = ia64_clear_ic();

	rid = ia64_rid(IA64_REGION_ID_KERNEL, __IA64_UNCACHED_OFFSET);
	ia64_set_rr(__IA64_UNCACHED_OFFSET, (rid << 8) | (IA64_GRANULE_SHIFT << 2));

	rid = ia64_rid(IA64_REGION_ID_KERNEL, VMALLOC_START);
	ia64_set_rr(VMALLOC_START, (rid << 8) | (PAGE_SHIFT << 2) | 1);

	/* ensure rr6 is up-to-date before inserting the PERCPU_ADDR translation: */
	ia64_srlz_d();

	ia64_itr(0x2, IA64_TR_PERCPU_DATA, PERCPU_ADDR,
		 pte_val(mk_pte_phys(__pa(my_cpu_data), PAGE_KERNEL)), PAGE_SHIFT);

	ia64_set_psr(psr);
	ia64_srlz_i();

	/*
	 * 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)));