init.c

linux-2.6.15.6

	} else {
		/*
		 * For AP's, zap the low identity mappings by changing the cr3
		 * to init_level4_pgt and doing local flush tlb all
		 */
		asm volatile("movq %0,%%cr3" :: "r" (__pa_symbol(&init_level4_pgt)));
	}
	__flush_tlb_all();
}

/* Compute zone sizes for the DMA and DMA32 zones in a node. */
__init void
size_zones(unsigned long *z, unsigned long *h,
	   unsigned long start_pfn, unsigned long end_pfn)
{
 	int i;
 	unsigned long w;

 	for (i = 0; i < MAX_NR_ZONES; i++)
 		z[i] = 0;

 	if (start_pfn < MAX_DMA_PFN)
 		z[ZONE_DMA] = MAX_DMA_PFN - start_pfn;
 	if (start_pfn < MAX_DMA32_PFN) {
 		unsigned long dma32_pfn = MAX_DMA32_PFN;
 		if (dma32_pfn > end_pfn)
 			dma32_pfn = end_pfn;
 		z[ZONE_DMA32] = dma32_pfn - start_pfn;
 	}
 	z[ZONE_NORMAL] = end_pfn - start_pfn;

 	/* Remove lower zones from higher ones. */
 	w = 0;
 	for (i = 0; i < MAX_NR_ZONES; i++) {
 		if (z[i])
 			z[i] -= w;
 	        w += z[i];
	}

	/* Compute holes */
	w = start_pfn;
	for (i = 0; i < MAX_NR_ZONES; i++) {
		unsigned long s = w;
		w += z[i];
		h[i] = e820_hole_size(s, w);
	}

	/* Add the space pace needed for mem_map to the holes too. */
	for (i = 0; i < MAX_NR_ZONES; i++)
		h[i] += (z[i] * sizeof(struct page)) / PAGE_SIZE;

	/* The 16MB DMA zone has the kernel and other misc mappings.
 	   Account them too */
	if (h[ZONE_DMA]) {
		h[ZONE_DMA] += dma_reserve;
		if (h[ZONE_DMA] >= z[ZONE_DMA]) {
			printk(KERN_WARNING
				"Kernel too large and filling up ZONE_DMA?\n");
			h[ZONE_DMA] = z[ZONE_DMA];
		}
	}
}

#ifndef CONFIG_NUMA
void __init paging_init(void)
{
	unsigned long zones[MAX_NR_ZONES], holes[MAX_NR_ZONES];
	size_zones(zones, holes, 0, end_pfn);
	free_area_init_node(0, NODE_DATA(0), zones,
			    __pa(PAGE_OFFSET) >> PAGE_SHIFT, holes);
}
#endif

/* Unmap a kernel mapping if it exists. This is useful to avoid prefetches
   from the CPU leading to inconsistent cache lines. address and size
   must be aligned to 2MB boundaries. 
   Does nothing when the mapping doesn't exist. */
void __init clear_kernel_mapping(unsigned long address, unsigned long size) 
{
	unsigned long end = address + size;

	BUG_ON(address & ~LARGE_PAGE_MASK);
	BUG_ON(size & ~LARGE_PAGE_MASK); 
	
	for (; address < end; address += LARGE_PAGE_SIZE) { 
		pgd_t *pgd = pgd_offset_k(address);
		pud_t *pud;
		pmd_t *pmd;
		if (pgd_none(*pgd))
			continue;
		pud = pud_offset(pgd, address);
		if (pud_none(*pud))
			continue; 
		pmd = pmd_offset(pud, address);
		if (!pmd || pmd_none(*pmd))
			continue; 
		if (0 == (pmd_val(*pmd) & _PAGE_PSE)) { 
			/* Could handle this, but it should not happen currently. */
			printk(KERN_ERR 
	       "clear_kernel_mapping: mapping has been split. will leak memory\n"); 
			pmd_ERROR(*pmd); 
		}
		set_pmd(pmd, __pmd(0)); 		
	}
	__flush_tlb_all();
} 

static struct kcore_list kcore_mem, kcore_vmalloc, kcore_kernel, kcore_modules,
			 kcore_vsyscall;

void __init mem_init(void)
{
	long codesize, reservedpages, datasize, initsize;

#ifdef CONFIG_SWIOTLB
	if (!iommu_aperture &&
	    (end_pfn >= 0xffffffff>>PAGE_SHIFT || force_iommu))
	       swiotlb = 1;
	if (swiotlb)
		swiotlb_init();	
#endif

	/* How many end-of-memory variables you have, grandma! */
	max_low_pfn = end_pfn;
	max_pfn = end_pfn;
	num_physpages = end_pfn;
	high_memory = (void *) __va(end_pfn * PAGE_SIZE);

	/* clear the zero-page */
	memset(empty_zero_page, 0, PAGE_SIZE);

	reservedpages = 0;

	/* this will put all low memory onto the freelists */
#ifdef CONFIG_NUMA
	totalram_pages = numa_free_all_bootmem();
#else
	totalram_pages = free_all_bootmem();
#endif
	reservedpages = end_pfn - totalram_pages - e820_hole_size(0, end_pfn);

	after_bootmem = 1;

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

	/* Register memory areas for /proc/kcore */
	kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT); 
	kclist_add(&kcore_vmalloc, (void *)VMALLOC_START, 
		   VMALLOC_END-VMALLOC_START);
	kclist_add(&kcore_kernel, &_stext, _end - _stext);
	kclist_add(&kcore_modules, (void *)MODULES_VADDR, MODULES_LEN);
	kclist_add(&kcore_vsyscall, (void *)VSYSCALL_START, 
				 VSYSCALL_END - VSYSCALL_START);

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

#ifdef CONFIG_SMP
	/*
	 * Sync boot_level4_pgt mappings with the init_level4_pgt
	 * except for the low identity mappings which are already zapped
	 * in init_level4_pgt. This sync-up is essential for AP's bringup
	 */
	memcpy(boot_level4_pgt+1, init_level4_pgt+1, (PTRS_PER_PGD-1)*sizeof(pgd_t));
#endif
}

void free_initmem(void)
{
	unsigned long addr;

	addr = (unsigned long)(&__init_begin);
	for (; addr < (unsigned long)(&__init_end); addr += PAGE_SIZE) {
		ClearPageReserved(virt_to_page(addr));
		set_page_count(virt_to_page(addr), 1);
		memset((void *)(addr & ~(PAGE_SIZE-1)), 0xcc, PAGE_SIZE); 
		free_page(addr);
		totalram_pages++;
	}
	memset(__initdata_begin, 0xba, __initdata_end - __initdata_begin);
	printk ("Freeing unused kernel memory: %luk freed\n", (__init_end - __init_begin) >> 10);
}

#ifdef CONFIG_BLK_DEV_INITRD
void free_initrd_mem(unsigned long start, unsigned long end)
{
	if (start < (unsigned long)&_end)
		return;
	printk ("Freeing initrd memory: %ldk freed\n", (end - start) >> 10);
	for (; start < end; start += PAGE_SIZE) {
		ClearPageReserved(virt_to_page(start));
		set_page_count(virt_to_page(start), 1);
		free_page(start);
		totalram_pages++;
	}
}
#endif

void __init reserve_bootmem_generic(unsigned long phys, unsigned len) 
{ 
	/* Should check here against the e820 map to avoid double free */ 
#ifdef CONFIG_NUMA
	int nid = phys_to_nid(phys);
  	reserve_bootmem_node(NODE_DATA(nid), phys, len);
#else       		
	reserve_bootmem(phys, len);    
#endif
	if (phys+len <= MAX_DMA_PFN*PAGE_SIZE)
		dma_reserve += len / PAGE_SIZE;
}

int kern_addr_valid(unsigned long addr) 
{ 
	unsigned long above = ((long)addr) >> __VIRTUAL_MASK_SHIFT;
       pgd_t *pgd;
       pud_t *pud;
       pmd_t *pmd;
       pte_t *pte;

	if (above != 0 && above != -1UL)
		return 0; 
	
	pgd = pgd_offset_k(addr);
	if (pgd_none(*pgd))
		return 0;

	pud = pud_offset(pgd, addr);
	if (pud_none(*pud))
		return 0; 

	pmd = pmd_offset(pud, addr);
	if (pmd_none(*pmd))
		return 0;
	if (pmd_large(*pmd))
		return pfn_valid(pmd_pfn(*pmd));

	pte = pte_offset_kernel(pmd, addr);
	if (pte_none(*pte))
		return 0;
	return pfn_valid(pte_pfn(*pte));
}

#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>

extern int exception_trace, page_fault_trace;

static ctl_table debug_table2[] = {
	{ 99, "exception-trace", &exception_trace, sizeof(int), 0644, NULL,
	  proc_dointvec },
	{ 0, }
}; 

static ctl_table debug_root_table2[] = { 
	{ .ctl_name = CTL_DEBUG, .procname = "debug", .mode = 0555, 
	   .child = debug_table2 }, 
	{ 0 }, 
}; 

static __init int x8664_sysctl_init(void)
{ 
	register_sysctl_table(debug_root_table2, 1);
	return 0;
}
__initcall(x8664_sysctl_init);
#endif

/* A pseudo VMAs to allow ptrace access for the vsyscall page.   This only
   covers the 64bit vsyscall page now. 32bit has a real VMA now and does
   not need special handling anymore. */

static struct vm_area_struct gate_vma = {
	.vm_start = VSYSCALL_START,
	.vm_end = VSYSCALL_END,
	.vm_page_prot = PAGE_READONLY
};

struct vm_area_struct *get_gate_vma(struct task_struct *tsk)
{
#ifdef CONFIG_IA32_EMULATION
	if (test_tsk_thread_flag(tsk, TIF_IA32))
		return NULL;
#endif
	return &gate_vma;
}

int in_gate_area(struct task_struct *task, unsigned long addr)
{
	struct vm_area_struct *vma = get_gate_vma(task);
	if (!vma)
		return 0;
	return (addr >= vma->vm_start) && (addr < vma->vm_end);
}

/* Use this when you have no reliable task/vma, typically from interrupt
 * context.  It is less reliable than using the task's vma and may give
 * false positives.
 */
int in_gate_area_no_task(unsigned long addr)
{
	return (addr >= VSYSCALL_START) && (addr < VSYSCALL_END);
}