Linux-XFS Archive on lore.kernel.org
 help / color / Atom feed
From: Matthew Wilcox <willy@infradead.org>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>,
	linux-fsdevel@vger.kernel.org, linux-mm@kvack.org,
	linux-kernel@vger.kernel.org, linux-btrfs@vger.kernel.org,
	linux-erofs@lists.ozlabs.org, linux-ext4@vger.kernel.org,
	linux-f2fs-devel@lists.sourceforge.net, cluster-devel@redhat.com,
	ocfs2-devel@oss.oracle.com, linux-xfs@vger.kernel.org,
	Christoph Hellwig <hch@lst.de>,
	William Kucharski <william.kucharski@oracle.com>
Subject: [PATCH v10 05/25] mm: Add new readahead_control API
Date: Mon, 23 Mar 2020 13:22:39 -0700
Message-ID: <20200323202259.13363-6-willy@infradead.org> (raw)
In-Reply-To: <20200323202259.13363-1-willy@infradead.org>

From: "Matthew Wilcox (Oracle)" <willy@infradead.org>

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>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: William Kucharski <william.kucharski@oracle.com>
---
 include/linux/pagemap.h | 140 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 140 insertions(+)

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 7d43a464b2a4..89fd6a62bfa5 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -636,6 +636,146 @@ 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) >>
-- 
2.25.1


  parent reply index

Thread overview: 34+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-03-23 20:22 [PATCH v10 00/25] Change readahead API Matthew Wilcox
2020-03-23 20:22 ` [PATCH v10 01/25] mm: Move readahead prototypes from mm.h Matthew Wilcox
2020-03-23 20:22 ` [PATCH v10 02/25] mm: Return void from various readahead functions Matthew Wilcox
2020-03-23 20:22 ` [PATCH v10 03/25] mm: Ignore return value of ->readpages Matthew Wilcox
2020-03-23 20:22 ` [PATCH v10 04/25] mm: Move readahead nr_pages check into read_pages Matthew Wilcox
2020-03-23 20:22 ` Matthew Wilcox [this message]
2020-03-23 20:22 ` [PATCH v10 06/25] mm: Use readahead_control to pass arguments Matthew Wilcox
2020-03-23 20:22 ` [PATCH v10 07/25] mm: Rename various 'offset' parameters to 'index' Matthew Wilcox
2020-03-23 20:22 ` [PATCH v10 08/25] mm: rename readahead loop variable to 'i' Matthew Wilcox
2020-03-23 20:22 ` [PATCH v10 09/25] mm: Remove 'page_offset' from readahead loop Matthew Wilcox
2020-03-23 20:22 ` [PATCH v10 10/25] mm: Put readahead pages in cache earlier Matthew Wilcox
2020-03-23 20:22 ` [PATCH v10 11/25] mm: Add readahead address space operation Matthew Wilcox
2020-03-23 20:22 ` [PATCH v10 12/25] mm: Move end_index check out of readahead loop Matthew Wilcox
2020-03-23 20:49   ` Eric Biggers
2020-03-24  8:40   ` Christoph Hellwig
2020-03-23 20:22 ` [PATCH v10 13/25] mm: Add page_cache_readahead_unbounded Matthew Wilcox
2020-03-23 20:22 ` [PATCH v10 14/25] mm: Document why we don't set PageReadahead Matthew Wilcox
2020-03-23 20:22 ` [PATCH v10 15/25] mm: Use memalloc_nofs_save in readahead path Matthew Wilcox
2020-03-23 20:22 ` [PATCH v10 16/25] fs: Convert mpage_readpages to mpage_readahead Matthew Wilcox
2020-03-23 20:22 ` [PATCH v10 17/25] btrfs: Convert from readpages to readahead Matthew Wilcox
2020-03-26 16:53   ` David Sterba
2020-03-23 20:22 ` [PATCH v10 18/25] erofs: Convert uncompressed files " Matthew Wilcox
2020-03-23 20:22 ` [PATCH v10 19/25] erofs: Convert compressed " Matthew Wilcox
2020-03-23 20:22 ` [PATCH v10 20/25] ext4: Convert " Matthew Wilcox
2020-03-23 20:22 ` [PATCH v10 21/25] ext4: Pass the inode to ext4_mpage_readpages Matthew Wilcox
2020-03-23 20:22 ` [PATCH v10 22/25] f2fs: Convert from readpages to readahead Matthew Wilcox
2020-03-23 20:22 ` [PATCH v10 23/25] f2fs: Pass the inode to f2fs_mpage_readpages Matthew Wilcox
2020-03-23 20:22 ` [PATCH v10 24/25] fuse: Convert from readpages to readahead Matthew Wilcox
2020-03-25  9:42   ` Miklos Szeredi
2020-03-25 12:02     ` Matthew Wilcox
2020-03-25 14:43       ` Miklos Szeredi
2020-03-25 15:32         ` Matthew Wilcox
2020-03-25 15:54           ` Miklos Szeredi
2020-03-23 20:22 ` [PATCH v10 25/25] iomap: " Matthew Wilcox

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200323202259.13363-6-willy@infradead.org \
    --to=willy@infradead.org \
    --cc=akpm@linux-foundation.org \
    --cc=cluster-devel@redhat.com \
    --cc=hch@lst.de \
    --cc=linux-btrfs@vger.kernel.org \
    --cc=linux-erofs@lists.ozlabs.org \
    --cc=linux-ext4@vger.kernel.org \
    --cc=linux-f2fs-devel@lists.sourceforge.net \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-xfs@vger.kernel.org \
    --cc=ocfs2-devel@oss.oracle.com \
    --cc=william.kucharski@oracle.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Linux-XFS Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-xfs/0 linux-xfs/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-xfs linux-xfs/ https://lore.kernel.org/linux-xfs \
		linux-xfs@vger.kernel.org
	public-inbox-index linux-xfs

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-xfs


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git