From: "Matthew Wilcox (Oracle)" <willy@xxxxxxxxxxxxx> Subject: btrfs: convert from readpages to readahead Implement the new readahead method in btrfs using the new readahead_page_batch() function. Link: http://lkml.kernel.org/r/20200414150233.24495-18-willy@xxxxxxxxxxxxx Signed-off-by: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx> Reviewed-by: William Kucharski <william.kucharski@xxxxxxxxxx> Cc: Chao Yu <yuchao0@xxxxxxxxxx> Cc: Christoph Hellwig <hch@xxxxxx> Cc: Cong Wang <xiyou.wangcong@xxxxxxxxx> Cc: Darrick J. Wong <darrick.wong@xxxxxxxxxx> Cc: Dave Chinner <dchinner@xxxxxxxxxx> Cc: Eric Biggers <ebiggers@xxxxxxxxxx> Cc: Gao Xiang <gaoxiang25@xxxxxxxxxx> Cc: Jaegeuk Kim <jaegeuk@xxxxxxxxxx> Cc: John Hubbard <jhubbard@xxxxxxxxxx> Cc: Joseph Qi <joseph.qi@xxxxxxxxxxxxxxxxx> Cc: Junxiao Bi <junxiao.bi@xxxxxxxxxx> Cc: Michal Hocko <mhocko@xxxxxxxx> Cc: Zi Yan <ziy@xxxxxxxxxx> Cc: Johannes Thumshirn <johannes.thumshirn@xxxxxxx> Cc: Miklos Szeredi <mszeredi@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- fs/btrfs/extent_io.c | 43 +++++++++++------------------------------ fs/btrfs/extent_io.h | 3 -- fs/btrfs/inode.c | 16 ++++++--------- 3 files changed, 20 insertions(+), 42 deletions(-) --- a/fs/btrfs/extent_io.c~btrfs-convert-from-readpages-to-readahead +++ a/fs/btrfs/extent_io.c @@ -4367,51 +4367,32 @@ int extent_writepages(struct address_spa 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; - int nr = 0; u64 prev_em_start = (u64)-1; + int nr; - while (!list_empty(pages)) { - u64 contig_end = 0; + 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; - for (nr = 0; nr < ARRAY_SIZE(pagepool) && !list_empty(pages);) { - struct page *page = lru_to_page(pages); + ASSERT(contig_start + nr * PAGE_SIZE - 1 == contig_end); - 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; - } - - if (nr) { - u64 contig_start = page_offset(pagepool[0]); - - ASSERT(contig_start + nr * PAGE_SIZE - 1 == contig_end); - - contiguous_readpages(pagepool, nr, contig_start, - contig_end, &em_cached, &bio, &bio_flags, - &prev_em_start); - } + contiguous_readpages(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; + } } /* --- a/fs/btrfs/extent_io.h~btrfs-convert-from-readpages-to-readahead +++ a/fs/btrfs/extent_io.h @@ -198,8 +198,7 @@ int extent_writepages(struct address_spa 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); --- a/fs/btrfs/inode.c~btrfs-convert-from-readpages-to-readahead +++ a/fs/btrfs/inode.c @@ -4856,8 +4856,8 @@ static void evict_inode_truncate_pages(s /* * 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 @@ -7050,11 +7050,11 @@ static int lock_extent_direct(struct ino * 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. */ @@ -8293,11 +8293,9 @@ static int btrfs_writepages(struct addre 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) @@ -10553,7 +10551,7 @@ static const struct address_space_operat .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, _
