aops.c

来自「Linux Kernel 2.6.9 for OMAP1710」· C语言 代码 · 共 2,031 行 · 第 1/4 页

		}
	} while (block++, block_start = block_end,
			(bh = bh->b_this_page) != head);

	/* Release the lock if we took it. */
	if (rl) {
		up_read(&ni->runlist.lock);
		rl = NULL;
	}

	/* If we issued read requests, let them complete. */
	while (wait_bh > wait) {
		wait_on_buffer(*--wait_bh);
		if (!buffer_uptodate(*wait_bh))
			return -EIO;
	}

	ntfs_debug("Done.");
	return 0;
err_out:
	/*
	 * Zero out any newly allocated blocks to avoid exposing stale data.
	 * If BH_New is set, we know that the block was newly allocated in the
	 * above loop.
	 * FIXME: What about initialized_size increments? Have we done all the
	 * required zeroing above? If not this error handling is broken, and
	 * in particular the if (block_end <= from) check is completely bogus.
	 */
	bh = head;
	block_start = 0;
	is_retry = FALSE;
	do {
		block_end = block_start + blocksize;
		if (block_end <= from)
			continue;
		if (block_start >= to)
			break;
		if (buffer_new(bh)) {
			void *kaddr;

			clear_buffer_new(bh);
			kaddr = kmap_atomic(page, KM_USER0);
			memset(kaddr + block_start, 0, bh->b_size);
			kunmap_atomic(kaddr, KM_USER0);
			set_buffer_uptodate(bh);
			mark_buffer_dirty(bh);
			is_retry = TRUE;
		}
	} while (block_start = block_end, (bh = bh->b_this_page) != head);
	if (is_retry)
		flush_dcache_page(page);
	if (rl)
		up_read(&ni->runlist.lock);
	return err;
}

/**
 * ntfs_prepare_write - prepare a page for receiving data
 *
 * This is called from generic_file_write() with i_sem held on the inode
 * (@page->mapping->host). The @page is locked and kmap()ped so page_address()
 * can simply be used. The source data has not yet been copied into the @page.
 *
 * Need to extend the attribute/fill in holes if necessary, create blocks and
 * make partially overwritten blocks uptodate,
 *
 * i_size is not to be modified yet.
 *
 * Return 0 on success or -errno on error.
 *
 * Should be using block_prepare_write() [support for sparse files] or
 * cont_prepare_write() [no support for sparse files]. Can't do that due to
 * ntfs specifics but can look at them for implementation guidancea.
 *
 * Note: In the range, @from is inclusive and @to is exclusive, i.e. @from is
 * the first byte in the page that will be written to and @to is the first byte
 * after the last byte that will be written to.
 */
static int ntfs_prepare_write(struct file *file, struct page *page,
		unsigned from, unsigned to)
{
	struct inode *vi = page->mapping->host;
	ntfs_inode   *ni = NTFS_I(vi);

	ntfs_debug("Entering for inode 0x%lx, attribute type 0x%x, page index "
			"0x%lx, from = %u, to = %u.", vi->i_ino, ni->type,
			page->index, from, to);

	BUG_ON(!PageLocked(page));
	BUG_ON(from > PAGE_CACHE_SIZE);
	BUG_ON(to > PAGE_CACHE_SIZE);
	BUG_ON(from > to);

	if (NInoNonResident(ni)) {
		/*
		 * Only unnamed $DATA attributes can be compressed, encrypted,
		 * and/or sparse.
		 */
		if (ni->type == AT_DATA && !ni->name_len) {
			/* If file is encrypted, deny access, just like NT4. */
			if (NInoEncrypted(ni)) {
				ntfs_debug("Denying write access to encrypted "
						"file.");
				return -EACCES;
			}
			/* Compressed data streams are handled in compress.c. */
			if (NInoCompressed(ni)) {
				// TODO: Implement and replace this check with
				// return ntfs_write_compressed_block(page);
				ntfs_error(vi->i_sb, "Writing to compressed "
						"files is not supported yet. "
						"Sorry.");
				return -EOPNOTSUPP;
			}
			// TODO: Implement and remove this check.
			if (NInoSparse(ni)) {
				ntfs_error(vi->i_sb, "Writing to sparse files "
						"is not supported yet. Sorry.");
				return -EOPNOTSUPP;
			}
		}

		// TODO: Implement and remove this check.
		if (NInoMstProtected(ni)) {
			ntfs_error(vi->i_sb, "Writing to MST protected "
					"attributes is not supported yet. "
					"Sorry.");
			return -EOPNOTSUPP;
		}

		/* Normal data stream. */
		return ntfs_prepare_nonresident_write(page, from, to);
	}

	/*
	 * Attribute is resident, implying it is not compressed, encrypted, or
	 * mst protected.
	 */
	BUG_ON(page_has_buffers(page));

	/* Do we need to resize the attribute? */
	if (((s64)page->index << PAGE_CACHE_SHIFT) + to > vi->i_size) {
		// TODO: Implement resize...
		ntfs_error(vi->i_sb, "Writing beyond the existing file size is "
				"not supported yet. Sorry.");
		return -EOPNOTSUPP;
	}

	/*
	 * Because resident attributes are handled by memcpy() to/from the
	 * corresponding MFT record, and because this form of i/o is byte
	 * aligned rather than block aligned, there is no need to bring the
	 * page uptodate here as in the non-resident case where we need to
	 * bring the buffers straddled by the write uptodate before
	 * generic_file_write() does the copying from userspace.
	 *
	 * We thus defer the uptodate bringing of the page region outside the
	 * region written to to ntfs_commit_write(). The reason for doing this
	 * is that we save one round of:
	 *	map_mft_record(), ntfs_attr_get_search_ctx(),
	 *	ntfs_attr_lookup(), kmap_atomic(), kunmap_atomic(),
	 *	ntfs_attr_put_search_ctx(), unmap_mft_record().
	 * Which is obviously a very worthwhile save.
	 *
	 * Thus we just return success now...
	 */
	ntfs_debug("Done.");
	return 0;
}

/*
 * NOTES: There is a disparity between the apparent need to extend the
 * attribute in prepare write but to update i_size only in commit write.
 * Need to make sure i_sem protection is sufficient. And if not will need to
 * handle this in some way or another.
 */

/**
 * ntfs_commit_nonresident_write -
 *
 */
static int ntfs_commit_nonresident_write(struct page *page,
		unsigned from, unsigned to)
{
	s64 pos = ((s64)page->index << PAGE_CACHE_SHIFT) + to;
	struct inode *vi;
	struct buffer_head *bh, *head;
	unsigned int block_start, block_end, blocksize;
	BOOL partial;

	vi = page->mapping->host;

	ntfs_debug("Entering for inode 0x%lx, attribute type 0x%x, page index "
			"0x%lx, from = %u, to = %u.", vi->i_ino,
			NTFS_I(vi)->type, page->index, from, to);

	blocksize = 1 << vi->i_blkbits;

	// FIXME: We need a whole slew of special cases in here for MST
	// protected attributes for example. For compressed files, too...
	// For now, we know ntfs_prepare_write() would have failed so we can't
	// get here in any of the cases which we have to special case, so we
	// are just a ripped off unrolled generic_commit_write() at present.

	bh = head = page_buffers(page);
	block_start = 0;
	partial = FALSE;
	do {
		block_end = block_start + blocksize;
		if (block_end <= from || block_start >= to) {
			if (!buffer_uptodate(bh))
				partial = TRUE;
		} else {
			set_buffer_uptodate(bh);
			mark_buffer_dirty(bh);
		}
	} while (block_start = block_end, (bh = bh->b_this_page) != head);

	/*
	 * If this is a partial write which happened to make all buffers
	 * uptodate then we can optimize away a bogus ->readpage() for the next
	 * read(). Here we 'discover' whether the page went uptodate as a
	 * result of this (potentially partial) write.
	 */
	if (!partial)
		SetPageUptodate(page);

	/*
	 * Not convinced about this at all. See disparity comment above. For
	 * now we know ntfs_prepare_write() would have failed in the write
	 * exceeds i_size case, so this will never trigger which is fine.
	 */
	if (pos > vi->i_size) {
		ntfs_error(vi->i_sb, "Writing beyond the existing file size is "
				"not supported yet. Sorry.");
		return -EOPNOTSUPP;
		// vi->i_size = pos;
		// mark_inode_dirty(vi);
	}
	ntfs_debug("Done.");
	return 0;
}

/**
 * ntfs_commit_write - commit the received data
 *
 * This is called from generic_file_write() with i_sem held on the inode
 * (@page->mapping->host). The @page is locked and kmap()ped so page_address()
 * can simply be used. The source data has already been copied into the @page.
 *
 * Need to mark modified blocks dirty so they get written out later when
 * ntfs_writepage() is invoked by the VM.
 *
 * Return 0 on success or -errno on error.
 *
 * Should be using generic_commit_write(). This marks buffers uptodate and
 * dirty, sets the page uptodate if all buffers in the page are uptodate, and
 * updates i_size if the end of io is beyond i_size. In that case, it also
 * marks the inode dirty. - We could still use this (obviously except for
 * NInoMstProtected() attributes, where we will need to duplicate the core code
 * because we need our own async_io completion handler) but we could just do
 * the i_size update in prepare write, when we resize the attribute. Then
 * we would avoid the i_size update and mark_inode_dirty() happening here.
 *
 * Can't use generic_commit_write() due to ntfs specialities but can look at
 * it for implementation guidance.
 *
 * If things have gone as outlined in ntfs_prepare_write(), then we do not
 * need to do any page content modifications here at all, except in the write
 * to resident attribute case, where we need to do the uptodate bringing here
 * which we combine with the copying into the mft record which means we only
 * need to map the mft record and find the attribute record in it only once.
 */
static int ntfs_commit_write(struct file *file, struct page *page,
		unsigned from, unsigned to)
{
	s64 attr_pos;
	struct inode *vi;
	ntfs_inode *ni, *base_ni;
	char *kaddr, *kattr;
	ntfs_attr_search_ctx *ctx;
	MFT_RECORD *m;
	u32 attr_len, bytes;
	int err;

	vi = page->mapping->host;
	ni = NTFS_I(vi);

	ntfs_debug("Entering for inode 0x%lx, attribute type 0x%x, page index "
			"0x%lx, from = %u, to = %u.", vi->i_ino, ni->type,
			page->index, from, to);

	if (NInoNonResident(ni)) {
		/*
		 * Only unnamed $DATA attributes can be compressed, encrypted,
		 * and/or sparse.
		 */
		if (ni->type == AT_DATA && !ni->name_len) {
			/* If file is encrypted, deny access, just like NT4. */
			if (NInoEncrypted(ni)) {
				// Should never get here!
				ntfs_debug("Denying write access to encrypted "
						"file.");
				return -EACCES;
			}
			/* Compressed data streams are handled in compress.c. */
			if (NInoCompressed(ni)) {
				// TODO: Implement and replace this check with
				// return ntfs_write_compressed_block(page);
				// Should never get here!
				ntfs_error(vi->i_sb, "Writing to compressed "
						"files is not supported yet. "
						"Sorry.");
				return -EOPNOTSUPP;
			}
			// TODO: Implement and remove this check.
			if (NInoSparse(ni)) {
				// Should never get here!
				ntfs_error(vi->i_sb, "Writing to sparse files "
						"is not supported yet. Sorry.");
				return -EOPNOTSUPP;
			}
		}

		// TODO: Implement and remove this check.
		if (NInoMstProtected(ni)) {
			// Should never get here!
			ntfs_error(vi->i_sb, "Writing to MST protected "
					"attributes is not supported yet. "
					"Sorry.");
			return -EOPNOTSUPP;
		}

		/* Normal data stream. */
		return ntfs_commit_nonresident_write(page, from, to);
	}

	/*
	 * Attribute is resident, implying it is not compressed, encrypted, or
	 * mst protected.
	 */

	/* Do we need to resize the attribute? */
	if (((s64)page->index << PAGE_CACHE_SHIFT) + to > vi->i_size) {
		// TODO: Implement resize...
		// pos = ((s64)page->index << PAGE_CACHE_SHIFT) + to;
		// vi->i_size = pos;
		// mark_inode_dirty(vi);
		// Should never get here!
		ntfs_error(vi->i_sb, "Writing beyond the existing file size is "
				"not supported yet. Sorry.");
		return -EOPNOTSUPP;
	}

	if (!NInoAttr(ni))
		base_ni = ni;
	else
		base_ni = ni->ext.base_ntfs_ino;

	/* Map, pin, and lock the mft record. */
	m = map_mft_record(base_ni);
	if (IS_ERR(m)) {
		err = PTR_ERR(m);
		m = NULL;
		ctx = NULL;
		goto err_out;
	}
	ctx = ntfs_attr_get_search_ctx(base_ni, m);
	if (unlikely(!ctx)) {
		err = -ENOMEM;
		goto err_out;
	}
	err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
			CASE_SENSITIVE, 0, NULL, 0, ctx);
	if (unlikely(err))
		goto err_out;

	/* Starting position of the page within the attribute value. */
	attr_pos = page->index << PAGE_CACHE_SHIFT;

	/* The total length of the attribute value. */
	attr_len = le32_to_cpu(ctx->attr->data.resident.value_length);

	if (unlikely(vi->i_size != attr_len)) {
		ntfs_error(vi->i_sb, "BUG()! i_size (0x%llx) doesn't match "
				"attr_len (0x%x). Aborting write.", vi->i_size,
				attr_len);
		err = -EIO;
		goto err_out;
	}
	if (unlikely(attr_pos >= attr_len)) {
		ntfs_error(vi->i_sb, "BUG()! attr_pos (0x%llx) > attr_len "
				"(0x%x). Aborting write.",
				(unsigned long long)attr_pos, attr_len);
		err = -EIO;
		goto err_out;
	}

	bytes = attr_len - attr_pos;
	if (unlikely(bytes > PAGE_CACHE_SIZE))
		bytes = PAGE_CACHE_SIZE;

	/*
	 * Calculate the address of the attribute value corresponding to the
	 * beginning of the current data @page.
	 */
	kattr = (u8*)ctx->attr + le16_to_cpu(
			ctx->attr->data.resident.value_offset) + attr_pos;

	kaddr = kmap_atomic(page, KM_USER0);

	/* Copy the received data from the page to the mft record. */
	memcpy(kattr + from, kaddr + from, to - from);
	flush_dcache_mft_record_page(ctx->ntfs_ino);

	if (!PageUptodate(page)) {
		/*
		 * Bring the out of bounds area(s) uptodate by copying data
		 * from the mft record to the page.
		 */
		if (from > 0)
			memcpy(kaddr, kattr, from);
		if (to < bytes)
			memcpy(kaddr + to, kattr + to, bytes - to);

		/* Zero the region outside the end of the attribute value. */
		if (likely(bytes < PAGE_CACHE_SIZE))
			memset(kaddr + bytes, 0, PAGE_CACHE_SIZE - bytes);

		/*
		 * The probability of not having done any of the above is
		 * extremely small, so we just flush unconditionally.
		 */
		flush_dcache_page(page);
		SetPageUptodate(page);
	}
	kunmap_atomic(kaddr, KM_USER0);

	/* Mark the mft record dirty, so it gets written back. */
	mark_mft_record_dirty(ctx->ntfs_ino);

	ntfs_attr_put_search_ctx(ctx);
	unmap_mft_record(base_ni);
	ntfs_debug("Done.");
	return 0;
err_out:
	if (err == -ENOMEM) {
		ntfs_warning(vi->i_sb, "Error allocating memory required to "
				"commit the write.");
		if (PageUptodate(page)) {
			ntfs_warning(vi->i_sb, "Page is uptodate, setting "
					"dirty so the write will be retried "
					"later on by the VM.");
			/*
			 * Put the page on mapping->dirty_pages, but leave its
			 * buffer's dirty state as-is.
			 */
			__set_page_dirty_nobuffers(page);
			err = 0;
		} else
			ntfs_error(vi->i_sb, "Page is not uptodate. Written "
					"data has been lost. )-:");
	} else {
		ntfs_error(vi->i_sb, "Resident attribute write failed with "
				"error %i. Setting page error flag.", -err);
		SetPageError(page);
	}
	if (ctx)
		ntfs_attr_put_search_ctx(ctx);
	if (m)
		unmap_mft_record(base_ni);
	return err;
}

#endif	/* NTFS_RW */

/**
 * ntfs_aops - general address space operations for inodes and attributes
 */
struct address_space_operations ntfs_aops = {
	.readpage	= ntfs_readpage,	/* Fill page with data. */
	.sync_page	= block_sync_page,	/* Currently, just unplugs the
						   disk request queue. */
#ifdef NTFS_RW
	.writepage	= ntfs_writepage,	/* Write dirty page to disk. */
	.prepare_write	= ntfs_prepare_write,	/* Prepare page and buffers
						   ready to receive data. */
	.commit_write	= ntfs_commit_write,	/* Commit received data. */
#endif /* NTFS_RW */
};

/**
 * ntfs_mst_aops - general address space operations for mst protecteed inodes
 *		   and attributes
 */
struct address_space_operations ntfs_mst_aops = {
	.readpage	= ntfs_readpage,	/* Fill page with data. */
	.sync_page	= block_sync_page,	/* Currently, just unplugs the
						   disk request queue. */
#ifdef NTFS_RW
	.writepage	= ntfs_writepage,	/* Write dirty page to disk. */
	.set_page_dirty	= __set_page_dirty_nobuffers,	/* Set the page dirty
						   without touching the buffers
						   belonging to the page. */
#endif /* NTFS_RW */
};