filemap.c

ARM 嵌入式 系统 设计与实例开发 实验教材 二源码

int file_read_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size)
{
	char *kaddr;
	unsigned long left, count = desc->count;

	if (size > count)
		size = count;

	kaddr = kmap(page);
	left = __copy_to_user(desc->buf, kaddr + offset, size);
	kunmap(page);
	
	if (left) {
		size -= left;
		desc->error = -EFAULT;
	}
	desc->count = count - size;
	desc->written += size;
	desc->buf += size;
	return size;
}

/*
 * This is the "read()" routine for all filesystems
 * that can use the page cache directly.
 */
ssize_t generic_file_read(struct file * filp, char * buf, size_t count, loff_t *ppos)
{
	ssize_t retval;

	if ((ssize_t) count < 0)
		return -EINVAL;

	if (filp->f_flags & O_DIRECT)
		goto o_direct;

	retval = -EFAULT;
	if (access_ok(VERIFY_WRITE, buf, count)) {
		retval = 0;

		if (count) {
			read_descriptor_t desc;

			desc.written = 0;
			desc.count = count;
			desc.buf = buf;
			desc.error = 0;
			do_generic_file_read(filp, ppos, &desc, file_read_actor);

			retval = desc.written;
			if (!retval)
				retval = desc.error;
		}
	}
 out:
	return retval;

 o_direct:
	{
		loff_t pos = *ppos, size;
		struct address_space *mapping = filp->f_dentry->d_inode->i_mapping;
		struct inode *inode = mapping->host;

		retval = 0;
		if (!count)
			goto out; /* skip atime */
		size = inode->i_size;
		if (pos < size) {
			if (pos + count > size)
				count = size - pos;
			retval = generic_file_direct_IO(READ, filp, buf, count, pos);
			if (retval > 0)
				*ppos = pos + retval;
		}
		UPDATE_ATIME(filp->f_dentry->d_inode);
		goto out;
	}
}

static int file_send_actor(read_descriptor_t * desc, struct page *page, unsigned long offset , unsigned long size)
{
	ssize_t written;
	unsigned long count = desc->count;
	struct file *file = (struct file *) desc->buf;

	if (size > count)
		size = count;

 	if (file->f_op->sendpage) {
 		written = file->f_op->sendpage(file, page, offset,
					       size, &file->f_pos, size<count);
	} else {
		char *kaddr;
		mm_segment_t old_fs;

		old_fs = get_fs();
		set_fs(KERNEL_DS);

		kaddr = kmap(page);
		written = file->f_op->write(file, kaddr + offset, size, &file->f_pos);
		kunmap(page);

		set_fs(old_fs);
	}
	if (written < 0) {
		desc->error = written;
		written = 0;
	}
	desc->count = count - written;
	desc->written += written;
	return written;
}

asmlinkage ssize_t sys_sendfile(int out_fd, int in_fd, off_t *offset, size_t count)
{
	ssize_t retval;
	struct file * in_file, * out_file;
	struct inode * in_inode, * out_inode;

	/*
	 * Get input file, and verify that it is ok..
	 */
	retval = -EBADF;
	in_file = fget(in_fd);
	if (!in_file)
		goto out;
	if (!(in_file->f_mode & FMODE_READ))
		goto fput_in;
	retval = -EINVAL;
	in_inode = in_file->f_dentry->d_inode;
	if (!in_inode)
		goto fput_in;
	if (!in_inode->i_mapping->a_ops->readpage)
		goto fput_in;
	retval = locks_verify_area(FLOCK_VERIFY_READ, in_inode, in_file, in_file->f_pos, count);
	if (retval)
		goto fput_in;

	/*
	 * Get output file, and verify that it is ok..
	 */
	retval = -EBADF;
	out_file = fget(out_fd);
	if (!out_file)
		goto fput_in;
	if (!(out_file->f_mode & FMODE_WRITE))
		goto fput_out;
	retval = -EINVAL;
	if (!out_file->f_op || !out_file->f_op->write)
		goto fput_out;
	out_inode = out_file->f_dentry->d_inode;
	retval = locks_verify_area(FLOCK_VERIFY_WRITE, out_inode, out_file, out_file->f_pos, count);
	if (retval)
		goto fput_out;

	retval = 0;
	if (count) {
		read_descriptor_t desc;
		loff_t pos = 0, *ppos;

		retval = -EFAULT;
		ppos = &in_file->f_pos;
		if (offset) {
			if (get_user(pos, offset))
				goto fput_out;
			ppos = &pos;
		}

		desc.written = 0;
		desc.count = count;
		desc.buf = (char *) out_file;
		desc.error = 0;
		do_generic_file_read(in_file, ppos, &desc, file_send_actor);

		retval = desc.written;
		if (!retval)
			retval = desc.error;
		if (offset)
			put_user(pos, offset);
	}

fput_out:
	fput(out_file);
fput_in:
	fput(in_file);
out:
	return retval;
}

static ssize_t do_readahead(struct file *file, unsigned long index, unsigned long nr)
{
	struct address_space *mapping = file->f_dentry->d_inode->i_mapping;
	unsigned long max;

	if (!mapping || !mapping->a_ops || !mapping->a_ops->readpage)
		return -EINVAL;

	/* Limit it to the size of the file.. */
	max = (mapping->host->i_size + ~PAGE_CACHE_MASK) >> PAGE_CACHE_SHIFT;
	if (index > max)
		return 0;
	max -= index;
	if (nr > max)
		nr = max;

	/* And limit it to a sane percentage of the inactive list.. */
	max = nr_inactive_pages / 2;
	if (nr > max)
		nr = max;

	while (nr) {
		page_cache_read(file, index);
		index++;
		nr--;
	}
	return 0;
}

asmlinkage ssize_t sys_readahead(int fd, loff_t offset, size_t count)
{
	ssize_t ret;
	struct file *file;

	ret = -EBADF;
	file = fget(fd);
	if (file) {
		if (file->f_mode & FMODE_READ) {
			unsigned long start = offset >> PAGE_CACHE_SHIFT;
			unsigned long len = (count + ((long)offset & ~PAGE_CACHE_MASK)) >> PAGE_CACHE_SHIFT;
			ret = do_readahead(file, start, len);
		}
		fput(file);
	}
	return ret;
}

/*
 * Read-ahead and flush behind for MADV_SEQUENTIAL areas.  Since we are
 * sure this is sequential access, we don't need a flexible read-ahead
 * window size -- we can always use a large fixed size window.
 */
static void nopage_sequential_readahead(struct vm_area_struct * vma,
	unsigned long pgoff, unsigned long filesize)
{
	unsigned long ra_window;

	ra_window = get_max_readahead(vma->vm_file->f_dentry->d_inode);
	ra_window = CLUSTER_OFFSET(ra_window + CLUSTER_PAGES - 1);

	/* vm_raend is zero if we haven't read ahead in this area yet.  */
	if (vma->vm_raend == 0)
		vma->vm_raend = vma->vm_pgoff + ra_window;

	/*
	 * If we've just faulted the page half-way through our window,
	 * then schedule reads for the next window, and release the
	 * pages in the previous window.
	 */
	if ((pgoff + (ra_window >> 1)) == vma->vm_raend) {
		unsigned long start = vma->vm_pgoff + vma->vm_raend;
		unsigned long end = start + ra_window;

		if (end > ((vma->vm_end >> PAGE_SHIFT) + vma->vm_pgoff))
			end = (vma->vm_end >> PAGE_SHIFT) + vma->vm_pgoff;
		if (start > end)
			return;

		while ((start < end) && (start < filesize)) {
			if (read_cluster_nonblocking(vma->vm_file,
							start, filesize) < 0)
				break;
			start += CLUSTER_PAGES;
		}
		run_task_queue(&tq_disk);

		/* if we're far enough past the beginning of this area,
		   recycle pages that are in the previous window. */
		if (vma->vm_raend > (vma->vm_pgoff + ra_window + ra_window)) {
			unsigned long window = ra_window << PAGE_SHIFT;

			end = vma->vm_start + (vma->vm_raend << PAGE_SHIFT);
			end -= window + window;
			filemap_sync(vma, end - window, window, MS_INVALIDATE);
		}

		vma->vm_raend += ra_window;
	}

	return;
}

/*
 * filemap_nopage() is invoked via the vma operations vector for a
 * mapped memory region to read in file data during a page fault.
 *
 * The goto's are kind of ugly, but this streamlines the normal case of having
 * it in the page cache, and handles the special cases reasonably without
 * having a lot of duplicated code.
 */
struct page * filemap_nopage(struct vm_area_struct * area, unsigned long address, int unused)
{
	int error;
	struct file *file = area->vm_file;
	struct address_space *mapping = file->f_dentry->d_inode->i_mapping;
	struct inode *inode = mapping->host;
	struct page *page, **hash;
	unsigned long size, pgoff, endoff;

	pgoff = ((address - area->vm_start) >> PAGE_CACHE_SHIFT) + area->vm_pgoff;
	endoff = ((area->vm_end - area->vm_start) >> PAGE_CACHE_SHIFT) + area->vm_pgoff;

retry_all:
	/*
	 * An external ptracer can access pages that normally aren't
	 * accessible..
	 */
	size = (inode->i_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
	if ((pgoff >= size) && (area->vm_mm == current->mm))
		return NULL;

	/* The "size" of the file, as far as mmap is concerned, isn't bigger than the mapping */
	if (size > endoff)
		size = endoff;

	/*
	 * Do we have something in the page cache already?
	 */
	hash = page_hash(mapping, pgoff);
retry_find:
	page = __find_get_page(mapping, pgoff, hash);
	if (!page)
		goto no_cached_page;

	/*
	 * Ok, found a page in the page cache, now we need to check
	 * that it's up-to-date.
	 */
	if (!Page_Uptodate(page))
		goto page_not_uptodate;

success:
 	/*
	 * Try read-ahead for sequential areas.
	 */
	if (VM_SequentialReadHint(area))
		nopage_sequential_readahead(area, pgoff, size);

	/*
	 * Found the page and have a reference on it, need to check sharing
	 * and possibly copy it over to another page..
	 */
	mark_page_accessed(page);
	flush_page_to_ram(page);
	return page;

no_cached_page:
	/*
	 * If the requested offset is within our file, try to read a whole 
	 * cluster of pages at once.
	 *
	 * Otherwise, we're off the end of a privately mapped file,
	 * so we need to map a zero page.
	 */
	if ((pgoff < size) && !VM_RandomReadHint(area))
		error = read_cluster_nonblocking(file, pgoff, size);
	else
		error = page_cache_read(file, pgoff);

	/*
	 * The page we want has now been added to the page cache.
	 * In the unlikely event that someone removed it in the
	 * meantime, we'll just come back here and read it again.
	 */
	if (error >= 0)
		goto retry_find;

	/*
	 * An error return from page_cache_read can result if the
	 * system is low on memory, or a problem occurs while trying
	 * to schedule I/O.
	 */
	if (error == -ENOMEM)
		return NOPAGE_OOM;
	return NULL;

page_not_uptodate:
	lock_page(page);

	/* Did it get unhashed while we waited for it? */
	if (!page->mapping) {
		UnlockPage(page);
		page_cache_release(page);
		goto retry_all;
	}

	/* Did somebody else get it up-to-date? */
	if (Page_Uptodate(page)) {
		UnlockPage(page);
		goto success;
	}

	if (!mapping->a_ops->readpage(file, page)) {
		wait_on_page(page);
		if (Page_Uptodate(page))
			goto success;
	}

	/*
	 * Umm, take care of errors if the page isn't up-to-date.
	 * Try to re-read it _once_. We do this synchronously,
	 * because there really aren't any performance issues here
	 * and we need to check for errors.
	 */
	lock_page(page);

	/* Somebody truncated the page on us? */
	if (!page->mapping) {
		UnlockPage(page);
		page_cache_release(page);
		goto retry_all;
	}

	/* Somebody else successfully read it in? */
	if (Page_Uptodate(page)) {
		UnlockPage(page);
		goto success;
	}
	ClearPageError(page);
	if (!mapping->a_ops->readpage(file, page)) {
		wait_on_page(page);
		if (Page_Uptodate(page))
			goto success;
	}

	/*
	 * Things didn't work out. Return zero to tell the
	 * mm layer so, possibly freeing the page cache page first.
	 */
	page_cache_release(page);
	return NULL;
}

/* Called with mm->page_table_lock held to protect against other
 * threads/the swapper from ripping pte's out from under us.
 */
static inline int filemap_sync_pte(pte_t * ptep, struct vm_area_struct *vma,
	unsigned long address, unsigned int flags)
{
	pte_t pte = *ptep;

	if (pte_present(pte)) {
		struct page *page = pte_page(pte);
		if (VALID_PAGE(page) && !PageReserved(page) && ptep_test_and_clear_dirty(ptep)) {
			flush_tlb_page(vma, address);
			set_page_dirty(page);
		}
	}
	return 0;
}

static inline int filemap_sync_pte_range(pmd_t * pmd,
	unsigned long address, unsigned long size, 
	struct vm_area_struct *vma, unsigned long offset, unsigned int flags)
{
	pte_t * pte;
	unsigned long end;
	int error;

	if (pmd_none(*pmd))
		return 0;
	if (pmd_bad(*pmd)) {
		pmd_ERROR(*pmd);
		pmd_clear(pmd);
		return 0;
	}
	pte = pte_offset(pmd, address);
	offset += address & PMD_MASK;
	address &= ~PMD_MASK;
	end = address + size;
	if (end > PMD_SIZE)
		end = PMD_SIZE;
	error = 0;
	do {
		error |= filemap_sync_pte(pte, vma, address + offset, flags);
		address += PAGE_SIZE;
		pte++;
	} while (address && (address < end));
	return error;
}

static inline int filemap_sync_pmd_range(pgd_t * pgd,
	unsigned long address, unsigned long size, 
	struct vm_area_struct *vma, unsigned int flags)
{
	pmd_t * pmd;
	unsigned long offset, end;
	int error;

	if (pgd_none(*pgd))
		return 0;
	if (pgd_bad(*pgd)) {
		pgd_ERROR(*pgd);
		pgd_clear(pgd);
		return 0;
	}
	pmd = pmd_offset(pgd, address);
	offset = address & PGDIR_MASK;
	address &= ~PGDIR_MASK;
	end = address + size;
	if (end > PGDIR_SIZE)
		end = PGDIR_SIZE;
	error = 0;
	do {
		error |= filemap_sync_pte_range(pmd, address, end - address, vma, offset, flags);