C++ pgd_offset_k函数代码示例

static void shmedia_mapioaddr(unsigned long pa, unsigned long va)
{
	pgd_t *pgdp;
	pmd_t *pmdp;
	pte_t *ptep;

	unsigned long flags = 1; /* 1 = CB0-1 device */


	DEBUG_IOREMAP(("shmedia_mapiopage pa %08x va %08x\n",  pa, va));

	pgdp = pgd_offset_k(va);
	if (pgd_none(*pgdp)) {
		pmdp = alloc_bootmem_low_pages(PTRS_PER_PMD * sizeof(pmd_t));
		if (pmdp == NULL) panic("No memory for pmd\n");
		memset(pmdp, 0, PTRS_PER_PGD * sizeof(pmd_t));
		set_pgd(pgdp, __pgd((unsigned long)pmdp | _KERNPG_TABLE));
	}

	pmdp = pmd_offset(pgdp, va);
	if (pmd_none(*pmdp)) {
		ptep = alloc_bootmem_low_pages(PTRS_PER_PTE * sizeof(pte_t));
		if (ptep == NULL) panic("No memory for pte\n");
		clear_page((void *)ptep);
		set_pmd(pmdp, __pmd((unsigned long)ptep + _PAGE_TABLE));
	}

	ptep = pte_offset(pmdp, va);
	set_pte(ptep, mk_pte_phys(pa, __pgprot(_PAGE_PRESENT |
			_PAGE_READ | _PAGE_WRITE | 
			_PAGE_DIRTY | _PAGE_ACCESSED |_PAGE_SHARED | flags)));
}

static int remap_area_pages(unsigned long address, unsigned long phys_addr,
				 unsigned long size, unsigned long flags)
{
	int error;
	pgd_t * dir;
	unsigned long end = address + size;

	phys_addr -= address;
	dir = pgd_offset_k(address);
	flush_cache_all();
	if (address >= end)
		BUG();
	spin_lock(&init_mm.page_table_lock);
	do {
		pmd_t *pmd;
		pmd = pmd_alloc(&init_mm, dir, address);
		error = -ENOMEM;
		if (!pmd)
			break;
		if (remap_area_pmd(pmd, address, end - address,
					 phys_addr + address, flags))
			break;
		error = 0;
		address = (address + PGDIR_SIZE) & PGDIR_MASK;
		dir++;
	} while (address && (address < end));
	spin_unlock(&init_mm.page_table_lock);
	flush_tlb_all();
	return error;
}

/*
 * Section support is unsafe on SMP - If you iounmap and ioremap a region,
 * the other CPUs will not see this change until their next context switch.
 * Meanwhile, (eg) if an interrupt comes in on one of those other CPUs
 * which requires the new ioremap'd region to be referenced, the CPU will
 * reference the _old_ region.
 *
 * Note that get_vm_area_caller() allocates a guard 4K page, so we need to
 * mask the size back to 4MB aligned or we will overflow in the loop below.
 */
static void unmap_area_sections(unsigned long virt, unsigned long size)
{
	unsigned long addr = virt, end = virt + (size & ~(SZ_4M - 1));
	pgd_t *pgd;

	flush_cache_vunmap(addr, end);
	pgd = pgd_offset_k(addr);
	do {
		pmd_t pmd, *pmdp = pmd_offset((pud_t *)pgd, addr);

		pmd = *pmdp;
		if (!pmd_none(pmd)) {
			/*
			 * Clear the PMD from the page table, and
			 * increment the kvm sequence so others
			 * notice this change.
			 *
			 * Note: this is still racy on SMP machines.
			 */
			pmd_clear(pmdp);

			/*
			 * Free the page table, if there was one.
			 */
			if ((pmd_val(pmd) & PMD_TYPE_MASK) == PMD_TYPE_TABLE)
				pte_free_kernel(&init_mm, pmd_page_vaddr(pmd));
		}

		addr += PGDIR_SIZE;
		pgd++;
	} while (addr < end);

	flush_tlb_kernel_range(virt, end);
}

int ioremap_page_range(unsigned long addr,
		       unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
{
	pgd_t *pgd;
	unsigned long start;
	unsigned long next;
	int err;

	might_sleep();
	BUG_ON(addr >= end);

	start = addr;
	phys_addr -= addr;
	pgd = pgd_offset_k(addr);
	do {
		next = pgd_addr_end(addr, end);
		err = ioremap_p4d_range(pgd, addr, next, phys_addr+addr, prot);
		if (err)
			break;
	} while (pgd++, addr = next, addr != end);

	flush_cache_vmap(start, end);

	return err;
}

/*
 * kernel virtual address is required to implement vmalloc/pkmap/fixmap
 * Refer to asm/processor.h for System Memory Map
 *
 * It simply copies the PMD entry (pointer to 2nd level page table or hugepage)
 * from swapper pgdir to task pgdir. The 2nd level table/page is thus shared
 */
noinline static int handle_kernel_vaddr_fault(unsigned long address)
{
	/*
	 * Synchronize this task's top level page-table
	 * with the 'reference' page table.
	 */
	pgd_t *pgd, *pgd_k;
	pud_t *pud, *pud_k;
	pmd_t *pmd, *pmd_k;

	pgd = pgd_offset_fast(current->active_mm, address);
	pgd_k = pgd_offset_k(address);

	if (!pgd_present(*pgd_k))
		goto bad_area;

	pud = pud_offset(pgd, address);
	pud_k = pud_offset(pgd_k, address);
	if (!pud_present(*pud_k))
		goto bad_area;

	pmd = pmd_offset(pud, address);
	pmd_k = pmd_offset(pud_k, address);
	if (!pmd_present(*pmd_k))
		goto bad_area;

	set_pmd(pmd, *pmd_k);

	/* XXX: create the TLB entry here */
	return 0;

bad_area:
	return 1;
}

static void shmedia_unmapioaddr(unsigned long vaddr)
{
	pgd_t *pgdp;
	pud_t *pudp;
	pmd_t *pmdp;
	pte_t *ptep;

	pgdp = pgd_offset_k(vaddr);
	if (pgd_none(*pgdp) || pgd_bad(*pgdp))
		return;

	pudp = pud_offset(pgdp, vaddr);
	if (pud_none(*pudp) || pud_bad(*pudp))
		return;

	pmdp = pmd_offset(pudp, vaddr);
	if (pmd_none(*pmdp) || pmd_bad(*pmdp))
		return;

	ptep = pte_offset_kernel(pmdp, vaddr);

	if (pte_none(*ptep) || !pte_present(*ptep))
		return;

	clear_page((void *)ptep);
	pte_clear(&init_mm, vaddr, ptep);
}

static void * __init init_pmd(unsigned long vaddr, unsigned long n_pages)
{
	pgd_t *pgd = pgd_offset_k(vaddr);
	pmd_t *pmd = pmd_offset(pgd, vaddr);
	pte_t *pte;
	unsigned long i;

	n_pages = ALIGN(n_pages, PTRS_PER_PTE);

	pr_debug("%s: vaddr: 0x%08lx, n_pages: %ld\n",
		 __func__, vaddr, n_pages);

	pte = memblock_alloc_low(n_pages * sizeof(pte_t), PAGE_SIZE);

	for (i = 0; i < n_pages; ++i)
		pte_clear(NULL, 0, pte + i);

	for (i = 0; i < n_pages; i += PTRS_PER_PTE, ++pmd) {
		pte_t *cur_pte = pte + i;

		BUG_ON(!pmd_none(*pmd));
		set_pmd(pmd, __pmd(((unsigned long)cur_pte) & PAGE_MASK));
		BUG_ON(cur_pte != pte_offset_kernel(pmd, 0));
		pr_debug("%s: pmd: 0x%p, pte: 0x%p\n",
			 __func__, pmd, cur_pte);
	}
	return pte;
}

static int
remap_area_sections(unsigned long virt, unsigned long pfn,
                    size_t size, const struct mem_type *type)
{
    unsigned long addr = virt, end = virt + size;
    pgd_t *pgd;
    pud_t *pud;
    pmd_t *pmd;

    unmap_area_sections(virt, size);

    pgd = pgd_offset_k(addr);
    pud = pud_offset(pgd, addr);
    pmd = pmd_offset(pud, addr);
    do {
        pmd[0] = __pmd(__pfn_to_phys(pfn) | type->prot_sect);
        pfn += SZ_1M >> PAGE_SHIFT;
        pmd[1] = __pmd(__pfn_to_phys(pfn) | type->prot_sect);
        pfn += SZ_1M >> PAGE_SHIFT;
        flush_pmd_entry(pmd);

        addr += PMD_SIZE;
        pmd += 2;
    } while (addr < end);

    return 0;
}

/* Ensure all existing pages follow the policy. */
static int
verify_pages(unsigned long addr, unsigned long end, unsigned long *nodes)
{
	while (addr < end) {
		struct page *p;
		pte_t *pte;
		pmd_t *pmd;
		pgd_t *pgd = pgd_offset_k(addr);
		if (pgd_none(*pgd)) {
			addr = (addr + PGDIR_SIZE) & PGDIR_MASK;
			continue;
		}
		pmd = pmd_offset(pgd, addr);
		if (pmd_none(*pmd)) {
			addr = (addr + PMD_SIZE) & PMD_MASK;
			continue;
		}
		p = NULL;
		pte = pte_offset_map(pmd, addr);
		if (pte_present(*pte))
			p = pte_page(*pte);
		pte_unmap(pte);
		if (p) {
			unsigned nid = page_to_nid(p);
			if (!test_bit(nid, nodes))
				return -EIO;
		}
		addr += PAGE_SIZE;
	}
	return 0;
}

/*
 * When built with CONFIG_DEBUG_PAGEALLOC and CONFIG_HIBERNATION, this function
 * is used to determine if a linear map page has been marked as not-valid by
 * CONFIG_DEBUG_PAGEALLOC. Walk the page table and check the PTE_VALID bit.
 * This is based on kern_addr_valid(), which almost does what we need.
 *
 * Because this is only called on the kernel linear map,  p?d_sect() implies
 * p?d_present(). When debug_pagealloc is enabled, sections mappings are
 * disabled.
 */
bool kernel_page_present(struct page *page)
{
	pgd_t *pgdp;
	pud_t *pudp, pud;
	pmd_t *pmdp, pmd;
	pte_t *ptep;
	unsigned long addr = (unsigned long)page_address(page);

	pgdp = pgd_offset_k(addr);
	if (pgd_none(READ_ONCE(*pgdp)))
		return false;

	pudp = pud_offset(pgdp, addr);
	pud = READ_ONCE(*pudp);
	if (pud_none(pud))
		return false;
	if (pud_sect(pud))
		return true;

	pmdp = pmd_offset(pudp, addr);
	pmd = READ_ONCE(*pmdp);
	if (pmd_none(pmd))
		return false;
	if (pmd_sect(pmd))
		return true;

	ptep = pte_offset_kernel(pmdp, addr);
	return pte_valid(READ_ONCE(*ptep));
}

/*
 * copy_user_page
 * @to: P1 address
 * @from: P1 address
 * @address: U0 address to be mapped
 * @page: page (virt_to_page(to))
 */
void copy_user_page(void *to, void *from, unsigned long address, 
		    struct page *page)
{
	__set_bit(PG_mapped, &page->flags);
	if (((address ^ (unsigned long)to) & CACHE_ALIAS) == 0)
		copy_page(to, from);
	else {
		pgprot_t pgprot = __pgprot(_PAGE_PRESENT | 
					   _PAGE_RW | _PAGE_CACHABLE |
					   _PAGE_DIRTY | _PAGE_ACCESSED | 
					   _PAGE_HW_SHARED | _PAGE_FLAGS_HARD);
		unsigned long phys_addr = PHYSADDR(to);
		unsigned long p3_addr = P3SEG + (address & CACHE_ALIAS);
		pgd_t *dir = pgd_offset_k(p3_addr);
		pmd_t *pmd = pmd_offset(dir, p3_addr);
		pte_t *pte = pte_offset_kernel(pmd, p3_addr);
		pte_t entry;
		unsigned long flags;

		entry = pfn_pte(phys_addr >> PAGE_SHIFT, pgprot);
		down(&p3map_sem[(address & CACHE_ALIAS)>>12]);
		set_pte(pte, entry);
		local_irq_save(flags);
		__flush_tlb_page(get_asid(), p3_addr);
		local_irq_restore(flags);
		update_mmu_cache(NULL, p3_addr, entry);
		__copy_user_page((void *)p3_addr, from, to);
		pte_clear(&init_mm, p3_addr, pte);
		up(&p3map_sem[(address & CACHE_ALIAS)>>12]);
	}
}

/*From: http://www.scs.ch/~frey/linux/memorymap.html*/
volatile void *virt_to_kseg(volatile void *address) {
    pgd_t *pgd; pmd_t *pmd; pte_t *ptep, pte;
    unsigned long va, ret = 0UL;
    va=VMALLOC_VMADDR((unsigned long)address);
    /* get the page directory. Use the kernel memory map. */
    pgd = pgd_offset_k(va);
    /* check whether we found an entry */
    if (!pgd_none(*pgd)) {
         /*I'm not sure if we need this, or the line for 2.4*/
            /*above will work reliably too*/
         /*If you know, please email me :-)*/
        pud_t *pud = pud_offset(pgd, va);       
        pmd = pmd_offset(pud, va);
        /* check whether we found an entry */
        if (!pmd_none(*pmd)) {
            /* get a pointer to the page table entry */
            ptep = pte_offset_map(pmd, va);
            pte = *ptep;
            /* check for a valid page */
            if (pte_present(pte)) {
                /* get the address the page is refering to */
                ret = (unsigned long)page_address(pte_page(pte));
                /* add the offset within the page to the page address */
                ret |= (va & (PAGE_SIZE -1));
            }
        }
    }
    return((volatile void *)ret);
}

/*
 * map_kernel_page currently only called by __ioremap
 * map_kernel_page adds an entry to the ioremap page table
 * and adds an entry to the HPT, possibly bolting it
 */
int hash__map_kernel_page(unsigned long ea, unsigned long pa, unsigned long flags)
{
	pgd_t *pgdp;
	pud_t *pudp;
	pmd_t *pmdp;
	pte_t *ptep;

	BUILD_BUG_ON(TASK_SIZE_USER64 > H_PGTABLE_RANGE);
	if (slab_is_available()) {
		pgdp = pgd_offset_k(ea);
		pudp = pud_alloc(&init_mm, pgdp, ea);
		if (!pudp)
			return -ENOMEM;
		pmdp = pmd_alloc(&init_mm, pudp, ea);
		if (!pmdp)
			return -ENOMEM;
		ptep = pte_alloc_kernel(pmdp, ea);
		if (!ptep)
			return -ENOMEM;
		set_pte_at(&init_mm, ea, ptep, pfn_pte(pa >> PAGE_SHIFT,
							  __pgprot(flags)));
	} else {
		/*
		 * If the mm subsystem is not fully up, we cannot create a
		 * linux page table entry for this mapping.  Simply bolt an
		 * entry in the hardware page table.
		 *
		 */
		if (htab_bolt_mapping(ea, ea + PAGE_SIZE, pa, flags,

static void unmap_area_sections(unsigned long virt, unsigned long size)
{
    unsigned long addr = virt, end = virt + (size & ~(SZ_1M - 1));
    pgd_t *pgd;
    pud_t *pud;
    pmd_t *pmdp;

    flush_cache_vunmap(addr, end);
    pgd = pgd_offset_k(addr);
    pud = pud_offset(pgd, addr);
    pmdp = pmd_offset(pud, addr);
    do {
        pmd_t pmd = *pmdp;

        if (!pmd_none(pmd)) {
            pmd_clear(pmdp);
            init_mm.context.kvm_seq++;

            if ((pmd_val(pmd) & PMD_TYPE_MASK) == PMD_TYPE_TABLE)
                pte_free_kernel(&init_mm, pmd_page_vaddr(pmd));
        }

        addr += PMD_SIZE;
        pmdp += 2;
    } while (addr < end);

    if (current->active_mm->context.kvm_seq != init_mm.context.kvm_seq)
        __check_kvm_seq(current->active_mm);

    flush_tlb_kernel_range(virt, end);
}

static int
remap_area_supersections(unsigned long virt, unsigned long pfn,
                         size_t size, const struct mem_type *type)
{
    unsigned long addr = virt, end = virt + size;
    pgd_t *pgd;
    pud_t *pud;
    pmd_t *pmd;

    unmap_area_sections(virt, size);

    pgd = pgd_offset_k(virt);
    pud = pud_offset(pgd, addr);
    pmd = pmd_offset(pud, addr);
    do {
        unsigned long super_pmd_val, i;

        super_pmd_val = __pfn_to_phys(pfn) | type->prot_sect |
                        PMD_SECT_SUPER;
        super_pmd_val |= ((pfn >> (32 - PAGE_SHIFT)) & 0xf) << 20;

        for (i = 0; i < 8; i++) {
            pmd[0] = __pmd(super_pmd_val);
            pmd[1] = __pmd(super_pmd_val);
            flush_pmd_entry(pmd);

            addr += PMD_SIZE;
            pmd += 2;
        }

        pfn += SUPERSECTION_SIZE >> PAGE_SHIFT;
    } while (addr < end);

    return 0;
}