mm: add new readahead_control API

Filesystems which implement the upcoming ->readahead method will get
their pages by calling readahead_page() or readahead_page_batch().
These functions support large pages, even though none of the filesystems
to be converted do yet.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: William Kucharski <william.kucharski@oracle.com>
Cc: Chao Yu <yuchao0@huawei.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Darrick J. Wong <darrick.wong@oracle.com>
Cc: Dave Chinner <dchinner@redhat.com>
Cc: Eric Biggers <ebiggers@google.com>
Cc: Gao Xiang <gaoxiang25@huawei.com>
Cc: Jaegeuk Kim <jaegeuk@kernel.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Joseph Qi <joseph.qi@linux.alibaba.com>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Cc: Miklos Szeredi <mszeredi@redhat.com>
Link: http://lkml.kernel.org/r/20200414150233.24495-6-willy@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/linux/pagemap.h

@@ -642,6 +642,146 @@ static inline int add_to_page_cache(struct page *page,
 	return error;
 }
 
+/**
+ * struct readahead_control - Describes a readahead request.
+ *
+ * A readahead request is for consecutive pages.  Filesystems which
+ * implement the ->readahead method should call readahead_page() or
+ * readahead_page_batch() in a loop and attempt to start I/O against
+ * each page in the request.
+ *
+ * Most of the fields in this struct are private and should be accessed
+ * by the functions below.
+ *
+ * @file: The file, used primarily by network filesystems for authentication.
+ *	  May be NULL if invoked internally by the filesystem.
+ * @mapping: Readahead this filesystem object.
+ */
+struct readahead_control {
+	struct file *file;
+	struct address_space *mapping;
+/* private: use the readahead_* accessors instead */
+	pgoff_t _index;
+	unsigned int _nr_pages;
+	unsigned int _batch_count;
+};
+
+/**
+ * readahead_page - Get the next page to read.
+ * @rac: The current readahead request.
+ *
+ * Context: The page is locked and has an elevated refcount.  The caller
+ * should decreases the refcount once the page has been submitted for I/O
+ * and unlock the page once all I/O to that page has completed.
+ * Return: A pointer to the next page, or %NULL if we are done.
+ */
+static inline struct page *readahead_page(struct readahead_control *rac)
+{
+	struct page *page;
+
+	BUG_ON(rac->_batch_count > rac->_nr_pages);
+	rac->_nr_pages -= rac->_batch_count;
+	rac->_index += rac->_batch_count;
+
+	if (!rac->_nr_pages) {
+		rac->_batch_count = 0;
+		return NULL;
+	}
+
+	page = xa_load(&rac->mapping->i_pages, rac->_index);
+	VM_BUG_ON_PAGE(!PageLocked(page), page);
+	rac->_batch_count = hpage_nr_pages(page);
+
+	return page;
+}
+
+static inline unsigned int __readahead_batch(struct readahead_control *rac,
+		struct page **array, unsigned int array_sz)
+{
+	unsigned int i = 0;
+	XA_STATE(xas, &rac->mapping->i_pages, 0);
+	struct page *page;
+
+	BUG_ON(rac->_batch_count > rac->_nr_pages);
+	rac->_nr_pages -= rac->_batch_count;
+	rac->_index += rac->_batch_count;
+	rac->_batch_count = 0;
+
+	xas_set(&xas, rac->_index);
+	rcu_read_lock();
+	xas_for_each(&xas, page, rac->_index + rac->_nr_pages - 1) {
+		VM_BUG_ON_PAGE(!PageLocked(page), page);
+		VM_BUG_ON_PAGE(PageTail(page), page);
+		array[i++] = page;
+		rac->_batch_count += hpage_nr_pages(page);
+
+		/*
+		 * The page cache isn't using multi-index entries yet,
+		 * so the xas cursor needs to be manually moved to the
+		 * next index.  This can be removed once the page cache
+		 * is converted.
+		 */
+		if (PageHead(page))
+			xas_set(&xas, rac->_index + rac->_batch_count);
+
+		if (i == array_sz)
+			break;
+	}
+	rcu_read_unlock();
+
+	return i;
+}
+
+/**
+ * readahead_page_batch - Get a batch of pages to read.
+ * @rac: The current readahead request.
+ * @array: An array of pointers to struct page.
+ *
+ * Context: The pages are locked and have an elevated refcount.  The caller
+ * should decreases the refcount once the page has been submitted for I/O
+ * and unlock the page once all I/O to that page has completed.
+ * Return: The number of pages placed in the array.  0 indicates the request
+ * is complete.
+ */
+#define readahead_page_batch(rac, array)				\
+	__readahead_batch(rac, array, ARRAY_SIZE(array))
+
+/**
+ * readahead_pos - The byte offset into the file of this readahead request.
+ * @rac: The readahead request.
+ */
+static inline loff_t readahead_pos(struct readahead_control *rac)
+{
+	return (loff_t)rac->_index * PAGE_SIZE;
+}
+
+/**
+ * readahead_length - The number of bytes in this readahead request.
+ * @rac: The readahead request.
+ */
+static inline loff_t readahead_length(struct readahead_control *rac)
+{
+	return (loff_t)rac->_nr_pages * PAGE_SIZE;
+}
+
+/**
+ * readahead_index - The index of the first page in this readahead request.
+ * @rac: The readahead request.
+ */
+static inline pgoff_t readahead_index(struct readahead_control *rac)
+{
+	return rac->_index;
+}
+
+/**
+ * readahead_count - The number of pages in this readahead request.
+ * @rac: The readahead request.
+ */
+static inline unsigned int readahead_count(struct readahead_control *rac)
+{
+	return rac->_nr_pages;
+}
+
 static inline unsigned long dir_pages(struct inode *inode)
 {
 	return (unsigned long)(inode->i_size + PAGE_SIZE - 1) >>