file.c

Linux内核自带的cifs模块

	if (wbc->start || wbc->end) {
		index = wbc->start >> PAGE_CACHE_SHIFT;
		end = wbc->end >> PAGE_CACHE_SHIFT;
		is_range = 1;
		scanned = 1;
	}
#endif /* 2.6.17 */
retry:
	while (!done && (index <= end) &&
	       (nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
			PAGECACHE_TAG_DIRTY,
			min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1))) {
		int first;
		unsigned int i;

		first = -1;
		next = 0;
		n_iov = 0;
		bytes_to_write = 0;

		for (i = 0; i < nr_pages; i++) {
			page = pvec.pages[i];
			/*
			 * At this point we hold neither mapping->tree_lock nor
			 * lock on the page itself: the page may be truncated or
			 * invalidated (changing page->mapping to NULL), or even
			 * swizzled back from swapper_space to tmpfs file
			 * mapping
			 */

			if (first < 0)
				lock_page(page);
			else if (TestSetPageLocked(page))
				break;

			if (unlikely(page->mapping != mapping)) {
				unlock_page(page);
				break;
			}

#if LINUX_VERSION_CODE > KERNEL_VERSION(2, 6, 17)
			if (!wbc->range_cyclic && page->index > end) {
#else
			if (unlikely(is_range) && (page->index > end)) {
#endif /* 2.6.17 */
				done = 1;
				unlock_page(page);
				break;
			}

			if (next && (page->index != next)) {
				/* Not next consecutive page */
				unlock_page(page);
				break;
			}

			if (wbc->sync_mode != WB_SYNC_NONE)
				wait_on_page_writeback(page);

			if (PageWriteback(page) ||
					!clear_page_dirty_for_io(page)) {
				unlock_page(page);
				break;
			}

			/*
			 * This actually clears the dirty bit in the radix tree.
			 * See cifs_writepage() for more commentary.
			 */
			set_page_writeback(page);

			if (page_offset(page) >= mapping->host->i_size) {
				done = 1;
				unlock_page(page);
				end_page_writeback(page);
				break;
			}

			/*
			 * BB can we get rid of this?  pages are held by pvec
			 */
			page_cache_get(page);

			len = min(mapping->host->i_size - page_offset(page),
				  (loff_t)PAGE_CACHE_SIZE);

			/* reserve iov[0] for the smb header */
			n_iov++;
			iov[n_iov].iov_base = kmap(page);
			iov[n_iov].iov_len = len;
			bytes_to_write += len;

			if (first < 0) {
				first = i;
				offset = page_offset(page);
			}
			next = page->index + 1;
			if (bytes_to_write + PAGE_CACHE_SIZE > cifs_sb->wsize)
				break;
		}
		if (n_iov) {
			/* Search for a writable handle every time we call
			 * CIFSSMBWrite2.  We can't rely on the last handle
			 * we used to still be valid
			 */
			open_file = find_writable_file(CIFS_I(mapping->host));
			if (!open_file) {
				cERROR(1, ("No writable handles for inode"));
				rc = -EBADF;
			} else {
				rc = CIFSSMBWrite2(xid, cifs_sb->tcon,
						   open_file->netfid,
						   bytes_to_write, offset,
						   &bytes_written, iov, n_iov,
						   1);
				atomic_dec(&open_file->wrtPending);
				if (rc || bytes_written < bytes_to_write) {
					cERROR(1, ("Write2 ret %d, wrote %d",
						  rc, bytes_written));
					/* BB what if continued retry is
					   requested via mount flags? */
					set_bit(AS_EIO, &mapping->flags);
				} else {
					cifs_stats_bytes_written(cifs_sb->tcon,
								 bytes_written);
				}
			}
			for (i = 0; i < n_iov; i++) {
				page = pvec.pages[first + i];
				/* Should we also set page error on
				success rc but too little data written? */
				/* BB investigate retry logic on temporary
				server crash cases and how recovery works
				when page marked as error */
				if (rc)
					SetPageError(page);
				kunmap(page);
				unlock_page(page);
				end_page_writeback(page);
				page_cache_release(page);
			}
			if ((wbc->nr_to_write -= n_iov) <= 0)
				done = 1;
			index = next;
		}
		pagevec_release(&pvec);
	}
	if (!scanned && !done) {
		/*
		 * We hit the last page and there is more work to be done: wrap
		 * back to the start of the file
		 */
		scanned = 1;
		index = 0;
		goto retry;
	}
#if LINUX_VERSION_CODE > KERNEL_VERSION(2, 6, 17)
	if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
#else
	if (!is_range)
#endif /* 2.6.17 */
		mapping->writeback_index = index;

	FreeXid(xid);
	kfree(iov);
	return rc;
}
#endif /* KERNEL_VERSION > 2.6.14 */

#if LINUX_VERSION_CODE < KERNEL_VERSION(2,5,0)
static int cifs_writepage(struct page* page)
#else
static int cifs_writepage(struct page *page, struct writeback_control *wbc)
#endif
{
	int rc = -EFAULT;
	int xid;

	xid = GetXid();
/* BB add check for wbc flags */
	page_cache_get(page);
	if (!PageUptodate(page)) {
		cFYI(1, ("ppw - page not up to date"));
	}

	/*
	 * Set the "writeback" flag, and clear "dirty" in the radix tree.
	 *
	 * A writepage() implementation always needs to do either this,
	 * or re-dirty the page with "redirty_page_for_writepage()" in
	 * the case of a failure.
	 *
	 * Just unlocking the page will cause the radix tree tag-bits
	 * to fail to update with the state of the page correctly.
	 */
	set_page_writeback(page);
	rc = cifs_partialpagewrite(page, 0, PAGE_CACHE_SIZE);
	SetPageUptodate(page); /* BB add check for error and Clearuptodate? */
	unlock_page(page);
	end_page_writeback(page);
	page_cache_release(page);
	FreeXid(xid);
	return rc;
}

static int cifs_commit_write(struct file *file, struct page *page,
	unsigned offset, unsigned to)
{
	int xid;
	int rc = 0;
	struct inode *inode = page->mapping->host;
	loff_t position = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to;
	char *page_data;

	xid = GetXid();
	cFYI(1, ("commit write for page %p up to position %lld for %d",
		 page, position, to));
	spin_lock(&inode->i_lock);
	if (position > inode->i_size) {
		i_size_write(inode, position);
	}
	spin_unlock(&inode->i_lock);
	if (!PageUptodate(page)) {
		position =  ((loff_t)page->index << PAGE_CACHE_SHIFT) + offset;
		/* can not rely on (or let) writepage write this data */
		if (to < offset) {
			cFYI(1, ("Illegal offsets, can not copy from %d to %d",
				offset, to));
			FreeXid(xid);
			return rc;
		}
		/* this is probably better than directly calling
		   partialpage_write since in this function the file handle is
		   known which we might as well	leverage */
		/* BB check if anything else missing out of ppw
		   such as updating last write time */
		page_data = kmap(page);
		rc = cifs_write(file, page_data + offset, to-offset,
				&position);
		if (rc > 0)
			rc = 0;
		/* else if (rc < 0) should we set writebehind rc? */
		kunmap(page);
	} else {
		set_page_dirty(page);
	}

	FreeXid(xid);
	return rc;
}

int cifs_fsync(struct file *file, struct dentry *dentry, int datasync)
{
	int xid;
	int rc = 0;
#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 20)
	struct inode *inode = file->f_dentry->d_inode;
#else
	struct inode *inode = file->f_path.dentry->d_inode;
#endif

	xid = GetXid();

	cFYI(1, ("Sync file - name: %s datasync: 0x%x",
		dentry->d_name.name, datasync));

	rc = filemap_fdatawrite(inode->i_mapping);
	if (rc == 0)
		CIFS_I(inode)->write_behind_rc = 0;
	FreeXid(xid);
	return rc;
}

/* static void cifs_sync_page(struct page *page)
{
	struct address_space *mapping;
	struct inode *inode;
	unsigned long index = page->index;
	unsigned int rpages = 0;
	int rc = 0;

	cFYI(1, ("sync page %p",page));
	mapping = page->mapping;
	if (!mapping)
		return 0;
	inode = mapping->host;
	if (!inode)
		return; */

/*	fill in rpages then
	result = cifs_pagein_inode(inode, index, rpages); */ /* BB finish */

/*	cFYI(1, ("rpages is %d for sync page of Index %ld", rpages, index));

#if 0
	if (rc < 0)
		return rc;
	return 0;
#endif
} */

/*
 * As file closes, flush all cached write data for this inode checking
 * for write behind errors.
 */
#if LINUX_VERSION_CODE > KERNEL_VERSION(2, 6, 17)
int cifs_flush(struct file *file, fl_owner_t id)
#else
int cifs_flush(struct file *file)
#endif /* 2.6.17 */
{
#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 20)
	struct inode *inode = file->f_dentry->d_inode;
#else
	struct inode *inode = file->f_path.dentry->d_inode;
#endif
	int rc = 0;

	/* Rather than do the steps manually:
	   lock the inode for writing
	   loop through pages looking for write behind data (dirty pages)
	   coalesce into contiguous 16K (or smaller) chunks to write to server
	   send to server (prefer in parallel)
	   deal with writebehind errors
	   unlock inode for writing
	   filemapfdatawrite appears easier for the time being */

	rc = filemap_fdatawrite(inode->i_mapping);
	if (!rc) /* reset wb rc if we were able to write out dirty pages */
		CIFS_I(inode)->write_behind_rc = 0;

	cFYI(1, ("Flush inode %p file %p rc %d", inode, file, rc));

	return rc;
}

ssize_t cifs_user_read(struct file *file, char __user *read_data,
	size_t read_size, loff_t *poffset)
{
	int rc = -EACCES;
	unsigned int bytes_read = 0;
	unsigned int total_read = 0;
	unsigned int current_read_size;
	struct cifs_sb_info *cifs_sb;
	struct cifsTconInfo *pTcon;
	int xid;
	struct cifsFileInfo *open_file;
	char *smb_read_data;
	char __user *current_offset;
	struct smb_com_read_rsp *pSMBr;

	xid = GetXid();
#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 20)
	cifs_sb = CIFS_SB(file->f_dentry->d_sb);
#else
	cifs_sb = CIFS_SB(file->f_path.dentry->d_sb);
#endif
	pTcon = cifs_sb->tcon;

	if (file->private_data == NULL) {
		FreeXid(xid);
		return -EBADF;
	}
	open_file = (struct cifsFileInfo *)file->private_data;

	if ((file->f_flags & O_ACCMODE) == O_WRONLY) {
		cFYI(1, ("attempting read on write only file instance"));
	}
	for (total_read = 0, current_offset = read_data;
	     read_size > total_read;
	     total_read += bytes_read, current_offset += bytes_read) {
		current_read_size = min_t(const int, read_size - total_read,
					  cifs_sb->rsize);
		rc = -EAGAIN;
		smb_read_data = NULL;
		while (rc == -EAGAIN) {
			int buf_type = CIFS_NO_BUFFER;
			if ((open_file->invalidHandle) &&
			    (!open_file->closePend)) {
				rc = cifs_reopen_file(file, TRUE);
				if (rc != 0)
					break;
			}
			rc = CIFSSMBRead(xid, pTcon,
					 open_file->netfid,
					 current_read_size, *poffset,
					 &bytes_read, &smb_read_data,
					 &buf_type);
			pSMBr = (struct smb_com_read_rsp *)smb_read_data;
			if (smb_read_data) {
				if (copy_to_user(current_offset,
						smb_read_data +
						4 /* RFC1001 length field */ +
						le16_to_cpu(pSMBr->DataOffset),
						bytes_read)) {
					rc = -EFAULT;
				}

				if (buf_type == CIFS_SMALL_BUFFER)
					cifs_small_buf_release(smb_read_data);
				else if (buf_type == CIFS_LARGE_BUFFER)
					cifs_buf_release(smb_read_data);
				smb_read_data = NULL;
			}
		}
		if (rc || (bytes_read == 0)) {
			if (total_read) {
				break;
			} else {
				FreeXid(xid);
				return rc;
			}
		} else {
			cifs_stats_bytes_read(pTcon, bytes_read);
			*poffset += bytes_read;
		}
	}
	FreeXid(xid);
	return total_read;
}


static ssize_t cifs_read(struct file *file, char *read_data, size_t read_size,
	loff_t *poffset)
{
	int rc = -EACCES;
	unsigned int bytes_read = 0;
	unsigned int total_read;
	unsigned int current_read_size;
	struct cifs_sb_info *cifs_sb;
	struct cifsTconInfo *pTcon;
	int xid;
	char *current_offset;
	struct cifsFileInfo *open_file;
	int buf_type = CIFS_NO_BUFFER;

	xid = GetXid();
#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 20)
	cifs_sb = CIFS_SB(file->f_dentry->d_sb);
#else
	cifs_sb = CIFS_SB(file->f_path.dentry->d_sb);
#endif
	pTcon = cifs_sb->tcon;

	if (file->private_data == NULL) {
		FreeXid(xid);
		return -EBADF;
	}
	open_file = (struct cifsFileInfo *)file->private_data;

	if ((file->f_flags & O_ACCMODE) == O_WRONLY)
		cFYI(1, ("attempting read on write only file instance"));

	for (total_read = 0, current_offset = read_data;
	     read_size > total_read;
	     total_read += bytes_read, current_offset += bytes_read) {
		current_read_size = min_t(const int, read_size - total_read,
					  cifs_sb->rsize);
		/* For windows me and 9x we do not want to request more
		than it negotiated since it will refuse the read then */
		if ((pTcon->ses) &&
			!(pTcon->ses->capabilities & CAP_LARGE_FILES)) {
			current_read_size = min_t(const int, current_read_size,