[v7,14/24] btrfs: Convert from readpages to readahead

Message ID	20200219210103.32400-15-willy@infradead.org (mailing list archive)
State	New, archived
Headers	show Return-Path: <SRS0=PNgT=4H=vger.kernel.org=linux-btrfs-owner@kernel.org> From: Matthew Wilcox <willy@infradead.org> To: linux-fsdevel@vger.kernel.org Cc: "Matthew Wilcox (Oracle)" <willy@infradead.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 Subject: [PATCH v7 14/24] btrfs: Convert from readpages to readahead Date: Wed, 19 Feb 2020 13:00:53 -0800 Message-Id: <20200219210103.32400-15-willy@infradead.org> In-Reply-To: <20200219210103.32400-1-willy@infradead.org> References: <20200219210103.32400-1-willy@infradead.org> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Sender: linux-btrfs-owner@vger.kernel.org Precedence: bulk
Series	Change readahead API \| expand [v7,00/23] Change readahead API [v7,01/24] mm: Move readahead prototypes from mm.h [v7,02/24] mm: Return void from various readahead functions [v7,03/24] mm: Ignore return value of ->readpages [v7,04/24] mm: Move readahead nr_pages check into read_pages [v7,05/24] mm: Use readahead_control to pass arguments [v7,06/24] mm: Rename various 'offset' parameters to 'index' [v7,07/24] mm: rename readahead loop variable to 'i' [v7,08/24] mm: Remove 'page_offset' from readahead loop [v7,09/24] mm: Put readahead pages in cache earlier [v7,10/24] mm: Add readahead address space operation [v7,11/24] mm: Move end_index check out of readahead loop [v7,12/24] mm: Add page_cache_readahead_unbounded [v7,13/24] fs: Convert mpage_readpages to mpage_readahead [v7,14/24] btrfs: Convert from readpages to readahead [v7,15/24] erofs: Convert uncompressed files from readpages to readahead [v7,16/24] erofs: Convert compressed files from readpages to readahead [v7,17/24] ext4: Convert from readpages to readahead [v7,18/24] ext4: Pass the inode to ext4_mpage_readpages [v7,19/24] f2fs: Convert from readpages to readahead [v7,20/24] fuse: Convert from readpages to readahead [v7,21/24] iomap: Restructure iomap_readpages_actor [v7,22/24] iomap: Convert from readpages to readahead [v7,23/24] mm: Document why we don't set PageReadahead [v7,24/24] mm: Use memalloc_nofs_save in readahead path

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index c0f202741e09..e70f14c1de60 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -4278,52 +4278,34 @@ int extent_writepages(struct address_space *mapping, return ret; } -int extent_readpages(struct address_space *mapping, struct list_head *pages, - unsigned nr_pages) +void extent_readahead(struct readahead_control *rac) { struct bio *bio = NULL; unsigned long bio_flags = 0; struct page *pagepool[16]; struct extent_map *em_cached = NULL; - struct extent_io_tree *tree = &BTRFS_I(mapping->host)->io_tree; - int nr = 0; + struct extent_io_tree *tree = &BTRFS_I(rac->mapping->host)->io_tree; u64 prev_em_start = (u64)-1; + int nr; - while (!list_empty(pages)) { - u64 contig_end = 0; - - for (nr = 0; nr < ARRAY_SIZE(pagepool) && !list_empty(pages);) { - struct page *page = lru_to_page(pages); - - prefetchw(&page->flags); - list_del(&page->lru); - if (add_to_page_cache_lru(page, mapping, page->index, - readahead_gfp_mask(mapping))) { - put_page(page); - break; - } - - pagepool[nr++] = page; - contig_end = page_offset(page) + PAGE_SIZE - 1; - } + while ((nr = readahead_page_batch(rac, pagepool))) { + u64 contig_start = page_offset(pagepool[0]); + u64 contig_end = page_offset(pagepool[nr - 1]) + PAGE_SIZE - 1; - if (nr) { - u64 contig_start = page_offset(pagepool[0]); + ASSERT(contig_start + nr * PAGE_SIZE - 1 == contig_end); - ASSERT(contig_start + nr * PAGE_SIZE - 1 == contig_end); - - contiguous_readpages(tree, pagepool, nr, contig_start, - contig_end, &em_cached, &bio, &bio_flags, - &prev_em_start); - } + contiguous_readpages(tree, pagepool, nr, contig_start, + contig_end, &em_cached, &bio, &bio_flags, + &prev_em_start); } if (em_cached) free_extent_map(em_cached); - if (bio) - return submit_one_bio(bio, 0, bio_flags); - return 0; + if (bio) { + if (submit_one_bio(bio, 0, bio_flags)) + return; + } } /* diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 5d205bbaafdc..bddac32948c7 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -198,8 +198,7 @@ int extent_writepages(struct address_space *mapping, struct writeback_control *wbc); int btree_write_cache_pages(struct address_space *mapping, struct writeback_control *wbc); -int extent_readpages(struct address_space *mapping, struct list_head *pages, - unsigned nr_pages); +void extent_readahead(struct readahead_control *rac); int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len); void set_page_extent_mapped(struct page *page); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 7d26b4bfb2c6..61d5137ce4e9 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4802,8 +4802,8 @@ static void evict_inode_truncate_pages(struct inode *inode) /* * Keep looping until we have no more ranges in the io tree. - * We can have ongoing bios started by readpages (called from readahead) - * that have their endio callback (extent_io.c:end_bio_extent_readpage) + * We can have ongoing bios started by readahead that have + * their endio callback (extent_io.c:end_bio_extent_readpage) * still in progress (unlocked the pages in the bio but did not yet * unlocked the ranges in the io tree). Therefore this means some * ranges can still be locked and eviction started because before @@ -7004,11 +7004,11 @@ static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend, * for it to complete) and then invalidate the pages for * this range (through invalidate_inode_pages2_range()), * but that can lead us to a deadlock with a concurrent - * call to readpages() (a buffered read or a defrag call + * call to readahead (a buffered read or a defrag call * triggered a readahead) on a page lock due to an * ordered dio extent we created before but did not have * yet a corresponding bio submitted (whence it can not - * complete), which makes readpages() wait for that + * complete), which makes readahead wait for that * ordered extent to complete while holding a lock on * that page. */ @@ -8247,11 +8247,9 @@ static int btrfs_writepages(struct address_space *mapping, return extent_writepages(mapping, wbc); } -static int -btrfs_readpages(struct file *file, struct address_space *mapping, - struct list_head *pages, unsigned nr_pages) +static void btrfs_readahead(struct readahead_control *rac) { - return extent_readpages(mapping, pages, nr_pages); + extent_readahead(rac); } static int __btrfs_releasepage(struct page *page, gfp_t gfp_flags) @@ -10456,7 +10454,7 @@ static const struct address_space_operations btrfs_aops = { .readpage = btrfs_readpage, .writepage = btrfs_writepage, .writepages = btrfs_writepages, - .readpages = btrfs_readpages, + .readahead = btrfs_readahead, .direct_IO = btrfs_direct_IO, .invalidatepage = btrfs_invalidatepage, .releasepage = btrfs_releasepage, diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 60f9b8d4da6c..dadf6ed11e71 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -672,6 +672,43 @@ static inline struct page *readahead_page(struct readahead_control *rac) 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, rac->_index); + 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_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; + } + + return i; +} + +#define readahead_page_batch(rac, array) \ + __readahead_batch(rac, array, ARRAY_SIZE(array)) + /* The byte offset into the file of this readahead block */ static inline loff_t readahead_pos(struct readahead_control *rac) {

[v7,14/24] btrfs: Convert from readpages to readahead

Commit Message

Comments

Patch