file.c

linux 内核源代码

		len = PAGE_CACHE_SIZE - ofs;
		if (len > bytes)
			len = bytes;
		addr = kmap_atomic(*pages, KM_USER0);
		left = __copy_from_user_inatomic(addr + ofs, buf, len);
		kunmap_atomic(addr, KM_USER0);
		if (unlikely(left)) {
			/* Do it the slow way. */
			addr = kmap(*pages);
			left = __copy_from_user(addr + ofs, buf, len);
			kunmap(*pages);
			if (unlikely(left))
				goto err_out;
		}
		total += len;
		bytes -= len;
		if (!bytes)
			break;
		buf += len;
		ofs = 0;
	} while (++pages < last_page);
out:
	return total;
err_out:
	total += len - left;
	/* Zero the rest of the target like __copy_from_user(). */
	while (++pages < last_page) {
		bytes -= len;
		if (!bytes)
			break;
		len = PAGE_CACHE_SIZE;
		if (len > bytes)
			len = bytes;
		zero_user_page(*pages, 0, len, KM_USER0);
	}
	goto out;
}

static size_t __ntfs_copy_from_user_iovec_inatomic(char *vaddr,
		const struct iovec *iov, size_t iov_ofs, size_t bytes)
{
	size_t total = 0;

	while (1) {
		const char __user *buf = iov->iov_base + iov_ofs;
		unsigned len;
		size_t left;

		len = iov->iov_len - iov_ofs;
		if (len > bytes)
			len = bytes;
		left = __copy_from_user_inatomic(vaddr, buf, len);
		total += len;
		bytes -= len;
		vaddr += len;
		if (unlikely(left)) {
			total -= left;
			break;
		}
		if (!bytes)
			break;
		iov++;
		iov_ofs = 0;
	}
	return total;
}

static inline void ntfs_set_next_iovec(const struct iovec **iovp,
		size_t *iov_ofsp, size_t bytes)
{
	const struct iovec *iov = *iovp;
	size_t iov_ofs = *iov_ofsp;

	while (bytes) {
		unsigned len;

		len = iov->iov_len - iov_ofs;
		if (len > bytes)
			len = bytes;
		bytes -= len;
		iov_ofs += len;
		if (iov->iov_len == iov_ofs) {
			iov++;
			iov_ofs = 0;
		}
	}
	*iovp = iov;
	*iov_ofsp = iov_ofs;
}

/*
 * This has the same side-effects and return value as ntfs_copy_from_user().
 * The difference is that on a fault we need to memset the remainder of the
 * pages (out to offset + bytes), to emulate ntfs_copy_from_user()'s
 * single-segment behaviour.
 *
 * We call the same helper (__ntfs_copy_from_user_iovec_inatomic()) both
 * when atomic and when not atomic.  This is ok because
 * __ntfs_copy_from_user_iovec_inatomic() calls __copy_from_user_inatomic()
 * and it is ok to call this when non-atomic.
 * Infact, the only difference between __copy_from_user_inatomic() and
 * __copy_from_user() is that the latter calls might_sleep() and the former
 * should not zero the tail of the buffer on error.  And on many
 * architectures __copy_from_user_inatomic() is just defined to
 * __copy_from_user() so it makes no difference at all on those architectures.
 */
static inline size_t ntfs_copy_from_user_iovec(struct page **pages,
		unsigned nr_pages, unsigned ofs, const struct iovec **iov,
		size_t *iov_ofs, size_t bytes)
{
	struct page **last_page = pages + nr_pages;
	char *addr;
	size_t copied, len, total = 0;

	do {
		len = PAGE_CACHE_SIZE - ofs;
		if (len > bytes)
			len = bytes;
		addr = kmap_atomic(*pages, KM_USER0);
		copied = __ntfs_copy_from_user_iovec_inatomic(addr + ofs,
				*iov, *iov_ofs, len);
		kunmap_atomic(addr, KM_USER0);
		if (unlikely(copied != len)) {
			/* Do it the slow way. */
			addr = kmap(*pages);
			copied = __ntfs_copy_from_user_iovec_inatomic(addr + ofs,
					*iov, *iov_ofs, len);
			/*
			 * Zero the rest of the target like __copy_from_user().
			 */
			memset(addr + ofs + copied, 0, len - copied);
			kunmap(*pages);
			if (unlikely(copied != len))
				goto err_out;
		}
		total += len;
		bytes -= len;
		if (!bytes)
			break;
		ntfs_set_next_iovec(iov, iov_ofs, len);
		ofs = 0;
	} while (++pages < last_page);
out:
	return total;
err_out:
	total += copied;
	/* Zero the rest of the target like __copy_from_user(). */
	while (++pages < last_page) {
		bytes -= len;
		if (!bytes)
			break;
		len = PAGE_CACHE_SIZE;
		if (len > bytes)
			len = bytes;
		zero_user_page(*pages, 0, len, KM_USER0);
	}
	goto out;
}

static inline void ntfs_flush_dcache_pages(struct page **pages,
		unsigned nr_pages)
{
	BUG_ON(!nr_pages);
	/*
	 * Warning: Do not do the decrement at the same time as the call to
	 * flush_dcache_page() because it is a NULL macro on i386 and hence the
	 * decrement never happens so the loop never terminates.
	 */
	do {
		--nr_pages;
		flush_dcache_page(pages[nr_pages]);
	} while (nr_pages > 0);
}

/**
 * ntfs_commit_pages_after_non_resident_write - commit the received data
 * @pages:	array of destination pages
 * @nr_pages:	number of pages in @pages
 * @pos:	byte position in file at which the write begins
 * @bytes:	number of bytes to be written
 *
 * See description of ntfs_commit_pages_after_write(), below.
 */
static inline int ntfs_commit_pages_after_non_resident_write(
		struct page **pages, const unsigned nr_pages,
		s64 pos, size_t bytes)
{
	s64 end, initialized_size;
	struct inode *vi;
	ntfs_inode *ni, *base_ni;
	struct buffer_head *bh, *head;
	ntfs_attr_search_ctx *ctx;
	MFT_RECORD *m;
	ATTR_RECORD *a;
	unsigned long flags;
	unsigned blocksize, u;
	int err;

	vi = pages[0]->mapping->host;
	ni = NTFS_I(vi);
	blocksize = vi->i_sb->s_blocksize;
	end = pos + bytes;
	u = 0;
	do {
		s64 bh_pos;
		struct page *page;
		bool partial;

		page = pages[u];
		bh_pos = (s64)page->index << PAGE_CACHE_SHIFT;
		bh = head = page_buffers(page);
		partial = false;
		do {
			s64 bh_end;

			bh_end = bh_pos + blocksize;
			if (bh_end <= pos || bh_pos >= end) {
				if (!buffer_uptodate(bh))
					partial = true;
			} else {
				set_buffer_uptodate(bh);
				mark_buffer_dirty(bh);
			}
		} while (bh_pos += blocksize, (bh = bh->b_this_page) != head);
		/*
		 * If all buffers are now uptodate but the page is not, set the
		 * page uptodate.
		 */
		if (!partial && !PageUptodate(page))
			SetPageUptodate(page);
	} while (++u < nr_pages);
	/*
	 * Finally, if we do not need to update initialized_size or i_size we
	 * are finished.
	 */
	read_lock_irqsave(&ni->size_lock, flags);
	initialized_size = ni->initialized_size;
	read_unlock_irqrestore(&ni->size_lock, flags);
	if (end <= initialized_size) {
		ntfs_debug("Done.");
		return 0;
	}
	/*
	 * Update initialized_size/i_size as appropriate, both in the inode and
	 * the mft record.
	 */
	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;
	}
	BUG_ON(!NInoNonResident(ni));
	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)) {
		if (err == -ENOENT)
			err = -EIO;
		goto err_out;
	}
	a = ctx->attr;
	BUG_ON(!a->non_resident);
	write_lock_irqsave(&ni->size_lock, flags);
	BUG_ON(end > ni->allocated_size);
	ni->initialized_size = end;
	a->data.non_resident.initialized_size = cpu_to_sle64(end);
	if (end > i_size_read(vi)) {
		i_size_write(vi, end);
		a->data.non_resident.data_size =
				a->data.non_resident.initialized_size;
	}
	write_unlock_irqrestore(&ni->size_lock, flags);
	/* Mark the mft record dirty, so it gets written back. */
	flush_dcache_mft_record_page(ctx->ntfs_ino);
	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 (ctx)
		ntfs_attr_put_search_ctx(ctx);
	if (m)
		unmap_mft_record(base_ni);
	ntfs_error(vi->i_sb, "Failed to update initialized_size/i_size (error "
			"code %i).", err);
	if (err != -ENOMEM)
		NVolSetErrors(ni->vol);
	return err;
}

/**
 * ntfs_commit_pages_after_write - commit the received data
 * @pages:	array of destination pages
 * @nr_pages:	number of pages in @pages
 * @pos:	byte position in file at which the write begins
 * @bytes:	number of bytes to be written
 *
 * This is called from ntfs_file_buffered_write() with i_mutex held on the inode
 * (@pages[0]->mapping->host).  There are @nr_pages pages in @pages which are
 * locked but not kmap()ped.  The source data has already been copied into the
 * @page.  ntfs_prepare_pages_for_non_resident_write() has been called before
 * the data was copied (for non-resident attributes only) and it returned
 * success.
 *
 * Need to set uptodate and mark dirty all buffers within the boundary of the
 * write.  If all buffers in a page are uptodate we set the page uptodate, too.
 *
 * Setting the buffers dirty ensures that they get written out later when
 * ntfs_writepage() is invoked by the VM.
 *
 * Finally, we need to update i_size and initialized_size as appropriate both
 * in the inode and the mft record.
 *
 * This is modelled after fs/buffer.c::generic_commit_write(), which 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.
 *
 * If things have gone as outlined in
 * ntfs_prepare_pages_for_non_resident_write(), we do not need to do any page
 * content modifications here for non-resident attributes.  For resident
 * attributes we need to do the uptodate bringing here which we combine with
 * the copying into the mft record which means we save one atomic kmap.
 *
 * Return 0 on success or -errno on error.
 */
static int ntfs_commit_pages_after_write(struct page **pages,
		const unsigned nr_pages, s64 pos, size_t bytes)
{
	s64 end, initialized_size;
	loff_t i_size;
	struct inode *vi;
	ntfs_inode *ni, *base_ni;
	struct page *page;
	ntfs_attr_search_ctx *ctx;
	MFT_RECORD *m;
	ATTR_RECORD *a;
	char *kattr, *kaddr;
	unsigned long flags;
	u32 attr_len;
	int err;

	BUG_ON(!nr_pages);
	BUG_ON(!pages);
	page = pages[0];
	BUG_ON(!page);
	vi = page->mapping->host;
	ni = NTFS_I(vi);
	ntfs_debug("Entering for inode 0x%lx, attribute type 0x%x, start page "
			"index 0x%lx, nr_pages 0x%x, pos 0x%llx, bytes 0x%zx.",
			vi->i_ino, ni->type, page->index, nr_pages,
			(long long)pos, bytes);
	if (NInoNonResident(ni))
		return ntfs_commit_pages_after_non_resident_write(pages,
				nr_pages, pos, bytes);
	BUG_ON(nr_pages > 1);
	/*
	 * Attribute is resident, implying it is not compressed, encrypted, or
	 * sparse.
	 */
	if (!NInoAttr(ni))
		base_ni = ni;
	else
		base_ni = ni->ext.base_ntfs_ino;
	BUG_ON(NInoNonResident(ni));
	/* 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)) {
		if (err == -ENOENT)
			err = -EIO;
		goto err_out;
	}
	a = ctx->attr;
	BUG_ON(a->non_resident);
	/* The total length of the attribute value. */
	attr_len = le32_to_cpu(a->data.resident.value_length);
	i_size = i_size_read(vi);
	BUG_ON(attr_len != i_size);
	BUG_ON(pos > attr_len);
	end = pos + bytes;
	BUG_ON(end > le32_to_cpu(a->length) -
			le16_to_cpu(a->data.resident.value_offset));
	kattr = (u8*)a + le16_to_cpu(a->data.resident.value_offset);
	kaddr = kmap_atomic(page, KM_USER0);
	/* Copy the received data from the page to the mft record. */
	memcpy(kattr + pos, kaddr + pos, bytes);
	/* Update the attribute length if necessary. */
	if (end > attr_len) {
		attr_len = end;
		a->data.resident.value_length = cpu_to_le32(attr_len);
	}
	/*
	 * If the page is not uptodate, bring the out of bounds area(s)
	 * uptodate by copying data from the mft record to the page.
	 */
	if (!PageUptodate(page)) {
		if (pos > 0)
			memcpy(kaddr, kattr, pos);
		if (end < attr_len)
			memcpy(kaddr + end, kattr + end, attr_len - end);
		/* Zero the region outside the end of the attribute value. */
		memset(kaddr + attr_len, 0, PAGE_CACHE_SIZE - attr_len);
		flush_dcache_page(page);
		SetPageUptodate(page);
	}
	kunmap_atomic(kaddr, KM_USER0);
	/* Update initialized_size/i_size if necessary. */
	read_lock_irqsave(&ni->size_lock, flags);