memory.c

最新最稳定的Linux内存管理模块源代码

 * unmap_vmas - unmap a range of memory covered by a list of vma's
 * @tlbp: address of the caller's struct mmu_gather
 * @vma: the starting vma
 * @start_addr: virtual address at which to start unmapping
 * @end_addr: virtual address at which to end unmapping
 * @nr_accounted: Place number of unmapped pages in vm-accountable vma's here
 * @details: details of nonlinear truncation or shared cache invalidation
 *
 * Returns the end address of the unmapping (restart addr if interrupted).
 *
 * Unmap all pages in the vma list.
 *
 * We aim to not hold locks for too long (for scheduling latency reasons).
 * So zap pages in ZAP_BLOCK_SIZE bytecounts.  This means we need to
 * return the ending mmu_gather to the caller.
 *
 * Only addresses between `start' and `end' will be unmapped.
 *
 * The VMA list must be sorted in ascending virtual address order.
 *
 * unmap_vmas() assumes that the caller will flush the whole unmapped address
 * range after unmap_vmas() returns.  So the only responsibility here is to
 * ensure that any thus-far unmapped pages are flushed before unmap_vmas()
 * drops the lock and schedules.
 */
unsigned long unmap_vmas(struct mmu_gather **tlbp,
		struct vm_area_struct *vma, unsigned long start_addr,
		unsigned long end_addr, unsigned long *nr_accounted,
		struct zap_details *details)
{
	long zap_work = ZAP_BLOCK_SIZE;
	unsigned long tlb_start = 0;	/* For tlb_finish_mmu */
	int tlb_start_valid = 0;
	unsigned long start = start_addr;
	spinlock_t *i_mmap_lock = details? details->i_mmap_lock: NULL;
	int fullmm = (*tlbp)->fullmm;
	struct mm_struct *mm = vma->vm_mm;

	mmu_notifier_invalidate_range_start(mm, start_addr, end_addr);
	for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next) {
		unsigned long end;

		start = max(vma->vm_start, start_addr);
		if (start >= vma->vm_end)
			continue;
		end = min(vma->vm_end, end_addr);
		if (end <= vma->vm_start)
			continue;

		if (vma->vm_flags & VM_ACCOUNT)
			*nr_accounted += (end - start) >> PAGE_SHIFT;

		if (unlikely(is_pfn_mapping(vma)))
			untrack_pfn_vma(vma, 0, 0);

		while (start != end) {
			if (!tlb_start_valid) {
				tlb_start = start;
				tlb_start_valid = 1;
			}

			if (unlikely(is_vm_hugetlb_page(vma))) {
				/*
				 * It is undesirable to test vma->vm_file as it
				 * should be non-null for valid hugetlb area.
				 * However, vm_file will be NULL in the error
				 * cleanup path of do_mmap_pgoff. When
				 * hugetlbfs ->mmap method fails,
				 * do_mmap_pgoff() nullifies vma->vm_file
				 * before calling this function to clean up.
				 * Since no pte has actually been setup, it is
				 * safe to do nothing in this case.
				 */
				if (vma->vm_file) {
					unmap_hugepage_range(vma, start, end, NULL);
					zap_work -= (end - start) /
					pages_per_huge_page(hstate_vma(vma));
				}

				start = end;
			} else
				start = unmap_page_range(*tlbp, vma,
						start, end, &zap_work, details);

			if (zap_work > 0) {
				BUG_ON(start != end);
				break;
			}

			tlb_finish_mmu(*tlbp, tlb_start, start);

			if (need_resched() ||
				(i_mmap_lock && spin_needbreak(i_mmap_lock))) {
				if (i_mmap_lock) {
					*tlbp = NULL;
					goto out;
				}
				cond_resched();
			}

			*tlbp = tlb_gather_mmu(vma->vm_mm, fullmm);
			tlb_start_valid = 0;
			zap_work = ZAP_BLOCK_SIZE;
		}
	}
out:
	mmu_notifier_invalidate_range_end(mm, start_addr, end_addr);
	return start;	/* which is now the end (or restart) address */
}

/**
 * zap_page_range - remove user pages in a given range
 * @vma: vm_area_struct holding the applicable pages
 * @address: starting address of pages to zap
 * @size: number of bytes to zap
 * @details: details of nonlinear truncation or shared cache invalidation
 */
unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address,
		unsigned long size, struct zap_details *details)
{
	struct mm_struct *mm = vma->vm_mm;
	struct mmu_gather *tlb;
	unsigned long end = address + size;
	unsigned long nr_accounted = 0;

	lru_add_drain();
	tlb = tlb_gather_mmu(mm, 0);
	update_hiwater_rss(mm);
	end = unmap_vmas(&tlb, vma, address, end, &nr_accounted, details);
	if (tlb)
		tlb_finish_mmu(tlb, address, end);
	return end;
}

/**
 * zap_vma_ptes - remove ptes mapping the vma
 * @vma: vm_area_struct holding ptes to be zapped
 * @address: starting address of pages to zap
 * @size: number of bytes to zap
 *
 * This function only unmaps ptes assigned to VM_PFNMAP vmas.
 *
 * The entire address range must be fully contained within the vma.
 *
 * Returns 0 if successful.
 */
int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address,
		unsigned long size)
{
	if (address < vma->vm_start || address + size > vma->vm_end ||
	    		!(vma->vm_flags & VM_PFNMAP))
		return -1;
	zap_page_range(vma, address, size, NULL);
	return 0;
}
EXPORT_SYMBOL_GPL(zap_vma_ptes);

/*
 * Do a quick page-table lookup for a single page.
 */
struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
			unsigned int flags)
{
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *ptep, pte;
	spinlock_t *ptl;
	struct page *page;
	struct mm_struct *mm = vma->vm_mm;

	page = follow_huge_addr(mm, address, flags & FOLL_WRITE);
	if (!IS_ERR(page)) {
		BUG_ON(flags & FOLL_GET);
		goto out;
	}

	page = NULL;
	pgd = pgd_offset(mm, address);
	if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
		goto no_page_table;

	pud = pud_offset(pgd, address);
	if (pud_none(*pud))
		goto no_page_table;
	if (pud_huge(*pud)) {
		BUG_ON(flags & FOLL_GET);
		page = follow_huge_pud(mm, address, pud, flags & FOLL_WRITE);
		goto out;
	}
	if (unlikely(pud_bad(*pud)))
		goto no_page_table;

	pmd = pmd_offset(pud, address);
	if (pmd_none(*pmd))
		goto no_page_table;
	if (pmd_huge(*pmd)) {
		BUG_ON(flags & FOLL_GET);
		page = follow_huge_pmd(mm, address, pmd, flags & FOLL_WRITE);
		goto out;
	}
	if (unlikely(pmd_bad(*pmd)))
		goto no_page_table;

	ptep = pte_offset_map_lock(mm, pmd, address, &ptl);

	pte = *ptep;
	if (!pte_present(pte))
		goto no_page;
	if ((flags & FOLL_WRITE) && !pte_write(pte))
		goto unlock;
	page = vm_normal_page(vma, address, pte);
	if (unlikely(!page))
		goto bad_page;

	if (flags & FOLL_GET)
		get_page(page);
	if (flags & FOLL_TOUCH) {
		if ((flags & FOLL_WRITE) &&
		    !pte_dirty(pte) && !PageDirty(page))
			set_page_dirty(page);
		mark_page_accessed(page);
	}
unlock:
	pte_unmap_unlock(ptep, ptl);
out:
	return page;

bad_page:
	pte_unmap_unlock(ptep, ptl);
	return ERR_PTR(-EFAULT);

no_page:
	pte_unmap_unlock(ptep, ptl);
	if (!pte_none(pte))
		return page;
	/* Fall through to ZERO_PAGE handling */
no_page_table:
	/*
	 * When core dumping an enormous anonymous area that nobody
	 * has touched so far, we don't want to allocate page tables.
	 */
	if (flags & FOLL_ANON) {
		page = ZERO_PAGE(0);
		if (flags & FOLL_GET)
			get_page(page);
		BUG_ON(flags & FOLL_WRITE);
	}
	return page;
}

/* Can we do the FOLL_ANON optimization? */
static inline int use_zero_page(struct vm_area_struct *vma)
{
	/*
	 * We don't want to optimize FOLL_ANON for make_pages_present()
	 * when it tries to page in a VM_LOCKED region. As to VM_SHARED,
	 * we want to get the page from the page tables to make sure
	 * that we serialize and update with any other user of that
	 * mapping.
	 */
	if (vma->vm_flags & (VM_LOCKED | VM_SHARED))
		return 0;
	/*
	 * And if we have a fault routine, it's not an anonymous region.
	 */
	return !vma->vm_ops || !vma->vm_ops->fault;
}



int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
		     unsigned long start, int len, int flags,
		struct page **pages, struct vm_area_struct **vmas)
{
	int i;
	unsigned int vm_flags = 0;
	int write = !!(flags & GUP_FLAGS_WRITE);
	int force = !!(flags & GUP_FLAGS_FORCE);
	int ignore = !!(flags & GUP_FLAGS_IGNORE_VMA_PERMISSIONS);
	int ignore_sigkill = !!(flags & GUP_FLAGS_IGNORE_SIGKILL);

	if (len <= 0)
		return 0;
	/* 
	 * Require read or write permissions.
	 * If 'force' is set, we only require the "MAY" flags.
	 */
	vm_flags  = write ? (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD);
	vm_flags &= force ? (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE);
	i = 0;

	do {
		struct vm_area_struct *vma;
		unsigned int foll_flags;

		vma = find_extend_vma(mm, start);
		if (!vma && in_gate_area(tsk, start)) {
			unsigned long pg = start & PAGE_MASK;
			struct vm_area_struct *gate_vma = get_gate_vma(tsk);
			pgd_t *pgd;
			pud_t *pud;
			pmd_t *pmd;
			pte_t *pte;

			/* user gate pages are read-only */
			if (!ignore && write)
				return i ? : -EFAULT;
			if (pg > TASK_SIZE)
				pgd = pgd_offset_k(pg);
			else
				pgd = pgd_offset_gate(mm, pg);
			BUG_ON(pgd_none(*pgd));
			pud = pud_offset(pgd, pg);
			BUG_ON(pud_none(*pud));
			pmd = pmd_offset(pud, pg);
			if (pmd_none(*pmd))
				return i ? : -EFAULT;
			pte = pte_offset_map(pmd, pg);
			if (pte_none(*pte)) {
				pte_unmap(pte);
				return i ? : -EFAULT;
			}
			if (pages) {
				struct page *page = vm_normal_page(gate_vma, start, *pte);
				pages[i] = page;
				if (page)
					get_page(page);
			}
			pte_unmap(pte);
			if (vmas)
				vmas[i] = gate_vma;
			i++;
			start += PAGE_SIZE;
			len--;
			continue;
		}

		if (!vma ||
		    (vma->vm_flags & (VM_IO | VM_PFNMAP)) ||
		    (!ignore && !(vm_flags & vma->vm_flags)))
			return i ? : -EFAULT;

		if (is_vm_hugetlb_page(vma)) {
			i = follow_hugetlb_page(mm, vma, pages, vmas,
						&start, &len, i, write);
			continue;
		}

		foll_flags = FOLL_TOUCH;
		if (pages)
			foll_flags |= FOLL_GET;
		if (!write && use_zero_page(vma))
			foll_flags |= FOLL_ANON;

		do {
			struct page *page;

			/*
			 * If we have a pending SIGKILL, don't keep faulting
			 * pages and potentially allocating memory, unless
			 * current is handling munlock--e.g., on exit. In
			 * that case, we are not allocating memory.  Rather,
			 * we're only unlocking already resident/mapped pages.
			 */
			if (unlikely(!ignore_sigkill &&
					fatal_signal_pending(current)))
				return i ? i : -ERESTARTSYS;

			if (write)
				foll_flags |= FOLL_WRITE;

			cond_resched();
			while (!(page = follow_page(vma, start, foll_flags))) {
				int ret;
				ret = handle_mm_fault(mm, vma, start,
						foll_flags & FOLL_WRITE);
				if (ret & VM_FAULT_ERROR) {
					if (ret & VM_FAULT_OOM)
						return i ? i : -ENOMEM;
					else if (ret & VM_FAULT_SIGBUS)
						return i ? i : -EFAULT;
					BUG();
				}
				if (ret & VM_FAULT_MAJOR)
					tsk->maj_flt++;
				else
					tsk->min_flt++;

				/*
				 * The VM_FAULT_WRITE bit tells us that
				 * do_wp_page has broken COW when necessary,
				 * even if maybe_mkwrite decided not to set
				 * pte_write. We can thus safely do subsequent
				 * page lookups as if they were reads. But only
				 * do so when looping for pte_write is futile:
				 * in some cases userspace may also be wanting
				 * to write to the gotten user page, which a
				 * read fault here might prevent (a readonly
				 * page might get reCOWed by userspace write).
				 */
				if ((ret & VM_FAULT_WRITE) &&
				    !(vma->vm_flags & VM_WRITE))
					foll_flags &= ~FOLL_WRITE;

				cond_resched();
			}
			if (IS_ERR(page))
				return i ? i : PTR_ERR(page);
			if (pages) {
				pages[i] = page;

				flush_anon_page(vma, page, start);
				flush_dcache_page(page);
			}
			if (vmas)
				vmas[i] = vma;
			i++;
			start += PAGE_SIZE;
			len--;
		} while (len && start < vma->vm_end);
	} while (len);
	return i;
}

int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
		unsigned long start, int len, int write, int force,
		struct page **pages, struct vm_area_struct **vmas)
{
	int flags = 0;

	if (write)
		flags |= GUP_FLAGS_WRITE;
	if (force)
		flags |= GUP_FLAGS_FORCE;

	return __get_user_pages(tsk, mm,
				start, len, flags,
				pages, vmas);
}

EXPORT_SYMBOL(get_user_pages);

pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr,
			spinlock_t **ptl)
{
	pgd_t * pgd = pgd_offset(mm, addr);
	pud_t * pud = pud_alloc(mm, pgd, addr);
	if (pud) {
		pmd_t * pmd = pmd_alloc(mm, pud, addr);
		if (pmd)
			return pte_alloc_map_lock(mm, pmd, addr, ptl);
	}
	return NULL;
}

/*
 * This is the old fallback for page remapping.
 *
 * For historical reasons, it only allows reserved pages. Only
 * old drivers should use this, and they needed to mark their
 * pages reserved for the old functions anyway.
 */
static int insert_page(struct vm_area_struct *vma, unsigned long addr,
			struct page *page, pgprot_t prot)
{