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>, "Darrick J . Wong" <darrick.wong@oracle.com>, William Kucharski <william.kucharski@oracle.com> Subject: [PATCH v11 25/25] iomap: Convert from readpages to readahead Date: Tue, 14 Apr 2020 08:02:33 -0700 Message-ID: <20200414150233.24495-26-willy@infradead.org> (raw) In-Reply-To: <20200414150233.24495-1-willy@infradead.org> From: "Matthew Wilcox (Oracle)" <willy@infradead.org> Use the new readahead operation in iomap. Convert XFS and ZoneFS to use it. Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: William Kucharski <william.kucharski@oracle.com> --- fs/iomap/buffered-io.c | 90 +++++++++++++++--------------------------- fs/iomap/trace.h | 2 +- fs/xfs/xfs_aops.c | 13 +++--- fs/zonefs/super.c | 7 ++-- include/linux/iomap.h | 3 +- 5 files changed, 41 insertions(+), 74 deletions(-) diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 075db1e71b14..890c8fcda4f3 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -214,9 +214,8 @@ iomap_read_end_io(struct bio *bio) struct iomap_readpage_ctx { struct page *cur_page; bool cur_page_in_bio; - bool is_readahead; struct bio *bio; - struct list_head *pages; + struct readahead_control *rac; }; static void @@ -308,7 +307,7 @@ iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data, if (ctx->bio) submit_bio(ctx->bio); - if (ctx->is_readahead) /* same as readahead_gfp_mask */ + if (ctx->rac) /* same as readahead_gfp_mask */ gfp |= __GFP_NORETRY | __GFP_NOWARN; ctx->bio = bio_alloc(gfp, min(BIO_MAX_PAGES, nr_vecs)); /* @@ -319,7 +318,7 @@ iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data, if (!ctx->bio) ctx->bio = bio_alloc(orig_gfp, 1); ctx->bio->bi_opf = REQ_OP_READ; - if (ctx->is_readahead) + if (ctx->rac) ctx->bio->bi_opf |= REQ_RAHEAD; ctx->bio->bi_iter.bi_sector = sector; bio_set_dev(ctx->bio, iomap->bdev); @@ -375,36 +374,8 @@ iomap_readpage(struct page *page, const struct iomap_ops *ops) } EXPORT_SYMBOL_GPL(iomap_readpage); -static struct page * -iomap_next_page(struct inode *inode, struct list_head *pages, loff_t pos, - loff_t length, loff_t *done) -{ - while (!list_empty(pages)) { - struct page *page = lru_to_page(pages); - - if (page_offset(page) >= (u64)pos + length) - break; - - list_del(&page->lru); - if (!add_to_page_cache_lru(page, inode->i_mapping, page->index, - GFP_NOFS)) - return page; - - /* - * If we already have a page in the page cache at index we are - * done. Upper layers don't care if it is uptodate after the - * readpages call itself as every page gets checked again once - * actually needed. - */ - *done += PAGE_SIZE; - put_page(page); - } - - return NULL; -} - static loff_t -iomap_readpages_actor(struct inode *inode, loff_t pos, loff_t length, +iomap_readahead_actor(struct inode *inode, loff_t pos, loff_t length, void *data, struct iomap *iomap, struct iomap *srcmap) { struct iomap_readpage_ctx *ctx = data; @@ -418,10 +389,7 @@ iomap_readpages_actor(struct inode *inode, loff_t pos, loff_t length, ctx->cur_page = NULL; } if (!ctx->cur_page) { - ctx->cur_page = iomap_next_page(inode, ctx->pages, - pos, length, &done); - if (!ctx->cur_page) - break; + ctx->cur_page = readahead_page(ctx->rac); ctx->cur_page_in_bio = false; } ret = iomap_readpage_actor(inode, pos + done, length - done, @@ -431,32 +399,43 @@ iomap_readpages_actor(struct inode *inode, loff_t pos, loff_t length, return done; } -int -iomap_readpages(struct address_space *mapping, struct list_head *pages, - unsigned nr_pages, const struct iomap_ops *ops) +/** + * iomap_readahead - Attempt to read pages from a file. + * @rac: Describes the pages to be read. + * @ops: The operations vector for the filesystem. + * + * This function is for filesystems to call to implement their readahead + * address_space operation. + * + * Context: The @ops callbacks may submit I/O (eg to read the addresses of + * blocks from disc), and may wait for it. The caller may be trying to + * access a different page, and so sleeping excessively should be avoided. + * It may allocate memory, but should avoid costly allocations. This + * function is called with memalloc_nofs set, so allocations will not cause + * the filesystem to be reentered. + */ +void iomap_readahead(struct readahead_control *rac, const struct iomap_ops *ops) { + struct inode *inode = rac->mapping->host; + loff_t pos = readahead_pos(rac); + loff_t length = readahead_length(rac); struct iomap_readpage_ctx ctx = { - .pages = pages, - .is_readahead = true, + .rac = rac, }; - loff_t pos = page_offset(list_entry(pages->prev, struct page, lru)); - loff_t last = page_offset(list_entry(pages->next, struct page, lru)); - loff_t length = last - pos + PAGE_SIZE, ret = 0; - trace_iomap_readpages(mapping->host, nr_pages); + trace_iomap_readahead(inode, readahead_count(rac)); while (length > 0) { - ret = iomap_apply(mapping->host, pos, length, 0, ops, - &ctx, iomap_readpages_actor); + loff_t ret = iomap_apply(inode, pos, length, 0, ops, + &ctx, iomap_readahead_actor); if (ret <= 0) { WARN_ON_ONCE(ret == 0); - goto done; + break; } pos += ret; length -= ret; } - ret = 0; -done: + if (ctx.bio) submit_bio(ctx.bio); if (ctx.cur_page) { @@ -464,15 +443,8 @@ iomap_readpages(struct address_space *mapping, struct list_head *pages, unlock_page(ctx.cur_page); put_page(ctx.cur_page); } - - /* - * Check that we didn't lose a page due to the arcance calling - * conventions.. - */ - WARN_ON_ONCE(!ret && !list_empty(ctx.pages)); - return ret; } -EXPORT_SYMBOL_GPL(iomap_readpages); +EXPORT_SYMBOL_GPL(iomap_readahead); /* * iomap_is_partially_uptodate checks whether blocks within a page are diff --git a/fs/iomap/trace.h b/fs/iomap/trace.h index 4df19c66f597..5693a39d52fb 100644 --- a/fs/iomap/trace.h +++ b/fs/iomap/trace.h @@ -39,7 +39,7 @@ DEFINE_EVENT(iomap_readpage_class, name, \ TP_PROTO(struct inode *inode, int nr_pages), \ TP_ARGS(inode, nr_pages)) DEFINE_READPAGE_EVENT(iomap_readpage); -DEFINE_READPAGE_EVENT(iomap_readpages); +DEFINE_READPAGE_EVENT(iomap_readahead); DECLARE_EVENT_CLASS(iomap_range_class, TP_PROTO(struct inode *inode, unsigned long off, unsigned int len), diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 9d9cebf18726..1fd4fb7a607c 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -621,14 +621,11 @@ xfs_vm_readpage( return iomap_readpage(page, &xfs_read_iomap_ops); } -STATIC int -xfs_vm_readpages( - struct file *unused, - struct address_space *mapping, - struct list_head *pages, - unsigned nr_pages) +STATIC void +xfs_vm_readahead( + struct readahead_control *rac) { - return iomap_readpages(mapping, pages, nr_pages, &xfs_read_iomap_ops); + iomap_readahead(rac, &xfs_read_iomap_ops); } static int @@ -644,7 +641,7 @@ xfs_iomap_swapfile_activate( const struct address_space_operations xfs_address_space_operations = { .readpage = xfs_vm_readpage, - .readpages = xfs_vm_readpages, + .readahead = xfs_vm_readahead, .writepage = xfs_vm_writepage, .writepages = xfs_vm_writepages, .set_page_dirty = iomap_set_page_dirty, diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index 3ce9829a6936..dba874a61fc5 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -78,10 +78,9 @@ static int zonefs_readpage(struct file *unused, struct page *page) return iomap_readpage(page, &zonefs_iomap_ops); } -static int zonefs_readpages(struct file *unused, struct address_space *mapping, - struct list_head *pages, unsigned int nr_pages) +static void zonefs_readahead(struct readahead_control *rac) { - return iomap_readpages(mapping, pages, nr_pages, &zonefs_iomap_ops); + iomap_readahead(rac, &zonefs_iomap_ops); } /* @@ -128,7 +127,7 @@ static int zonefs_writepages(struct address_space *mapping, static const struct address_space_operations zonefs_file_aops = { .readpage = zonefs_readpage, - .readpages = zonefs_readpages, + .readahead = zonefs_readahead, .writepage = zonefs_writepage, .writepages = zonefs_writepages, .set_page_dirty = iomap_set_page_dirty, diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 8b09463dae0d..bc20bd04c2a2 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -155,8 +155,7 @@ loff_t iomap_apply(struct inode *inode, loff_t pos, loff_t length, ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from, const struct iomap_ops *ops); int iomap_readpage(struct page *page, const struct iomap_ops *ops); -int iomap_readpages(struct address_space *mapping, struct list_head *pages, - unsigned nr_pages, const struct iomap_ops *ops); +void iomap_readahead(struct readahead_control *, const struct iomap_ops *ops); int iomap_set_page_dirty(struct page *page); int iomap_is_partially_uptodate(struct page *page, unsigned long from, unsigned long count); -- 2.25.1
prev parent reply index Thread overview: 47+ messages / expand[flat|nested] mbox.gz Atom feed top 2020-04-14 15:02 [PATCH v11 00/25] Change readahead API Matthew Wilcox 2020-04-14 15:02 ` [PATCH v11 01/25] mm: Move readahead prototypes from mm.h Matthew Wilcox 2020-04-15 9:10 ` Johannes Thumshirn 2020-04-14 15:02 ` [PATCH v11 02/25] mm: Return void from various readahead functions Matthew Wilcox 2020-04-14 15:02 ` [PATCH v11 03/25] mm: Ignore return value of ->readpages Matthew Wilcox 2020-04-15 9:17 ` Johannes Thumshirn 2020-04-14 15:02 ` [PATCH v11 04/25] mm: Move readahead nr_pages check into read_pages Matthew Wilcox 2020-04-15 9:19 ` Johannes Thumshirn 2020-04-14 15:02 ` [PATCH v11 05/25] mm: Add new readahead_control API Matthew Wilcox 2020-04-15 1:17 ` Andrew Morton 2020-04-15 2:18 ` Matthew Wilcox 2020-04-15 4:56 ` Andrew Morton 2020-04-15 11:22 ` Matthew Wilcox 2020-04-14 15:02 ` [PATCH v11 06/25] mm: Use readahead_control to pass arguments Matthew Wilcox 2020-04-15 9:30 ` Johannes Thumshirn 2020-04-14 15:02 ` [PATCH v11 07/25] mm: Rename various 'offset' parameters to 'index' Matthew Wilcox 2020-04-14 15:02 ` [PATCH v11 08/25] mm: rename readahead loop variable to 'i' Matthew Wilcox 2020-04-15 9:31 ` Johannes Thumshirn 2020-04-14 15:02 ` [PATCH v11 09/25] mm: Remove 'page_offset' from readahead loop Matthew Wilcox 2020-04-14 15:02 ` [PATCH v11 10/25] mm: Put readahead pages in cache earlier Matthew Wilcox 2020-04-14 15:02 ` [PATCH v11 11/25] mm: Add readahead address space operation Matthew Wilcox 2020-04-14 15:02 ` [PATCH v11 12/25] mm: Move end_index check out of readahead loop Matthew Wilcox 2020-04-14 15:02 ` [PATCH v11 13/25] mm: Add page_cache_readahead_unbounded Matthew Wilcox 2020-04-14 15:02 ` [PATCH v11 14/25] mm: Document why we don't set PageReadahead Matthew Wilcox 2020-04-14 15:02 ` [PATCH v11 15/25] mm: Use memalloc_nofs_save in readahead path Matthew Wilcox 2020-04-14 15:02 ` [PATCH v11 16/25] fs: Convert mpage_readpages to mpage_readahead Matthew Wilcox 2020-06-16 22:36 ` [Cluster-devel] " Andreas Gruenbacher 2020-06-17 0:32 ` Matthew Wilcox 2020-06-17 0:57 ` Andreas Grünbacher 2020-06-17 2:21 ` Matthew Wilcox 2020-06-18 12:46 ` Andreas Gruenbacher 2020-06-18 15:03 ` Matthew Wilcox 2020-06-18 16:40 ` Andreas Gruenbacher 2020-04-14 15:02 ` [PATCH v11 17/25] btrfs: Convert from readpages to readahead Matthew Wilcox 2020-04-14 15:02 ` [PATCH v11 18/25] erofs: Convert uncompressed files " Matthew Wilcox 2020-04-14 15:02 ` [PATCH v11 19/25] erofs: Convert compressed " Matthew Wilcox 2020-04-21 5:42 ` Andrew Morton 2020-04-21 7:28 ` Gao Xiang 2020-04-14 15:02 ` [PATCH v11 20/25] ext4: Convert " Matthew Wilcox 2020-04-14 15:02 ` [PATCH v11 21/25] ext4: Pass the inode to ext4_mpage_readpages Matthew Wilcox 2020-04-14 15:02 ` [PATCH v11 22/25] f2fs: Convert from readpages to readahead Matthew Wilcox 2020-04-14 15:02 ` [PATCH v11 23/25] f2fs: Pass the inode to f2fs_mpage_readpages Matthew Wilcox 2020-04-14 15:02 ` [PATCH v11 24/25] fuse: Convert from readpages to readahead Matthew Wilcox 2020-04-20 11:14 ` Miklos Szeredi 2020-04-20 11:43 ` Matthew Wilcox 2020-04-20 11:54 ` Miklos Szeredi 2020-04-14 15:02 ` Matthew Wilcox [this message]
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=20200414150233.24495-26-willy@infradead.org \ --to=willy@infradead.org \ --cc=akpm@linux-foundation.org \ --cc=cluster-devel@redhat.com \ --cc=darrick.wong@oracle.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-BTRFS Archive on lore.kernel.org Archives are clonable: git clone --mirror https://lore.kernel.org/linux-btrfs/0 linux-btrfs/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-btrfs linux-btrfs/ https://lore.kernel.org/linux-btrfs \ linux-btrfs@vger.kernel.org public-inbox-index linux-btrfs Example config snippet for mirrors Newsgroup available over NNTP: nntp://nntp.lore.kernel.org/org.kernel.vger.linux-btrfs AGPL code for this site: git clone https://public-inbox.org/public-inbox.git