From 735e4ae5ba28c886d249ad04d3c8cc097dad6336 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Mon, 1 Jun 2020 21:45:36 -0700 Subject: vfs: track per-sb writeback errors and report them to syncfs Patch series "vfs: have syncfs() return error when there are writeback errors", v6. Currently, syncfs does not return errors when one of the inodes fails to be written back. It will return errors based on the legacy AS_EIO and AS_ENOSPC flags when syncing out the block device fails, but that's not particularly helpful for filesystems that aren't backed by a blockdev. It's also possible for a stray sync to lose those errors. The basic idea in this set is to track writeback errors at the superblock level, so that we can quickly and easily check whether something bad happened without having to fsync each file individually. syncfs is then changed to reliably report writeback errors after they occur, much in the same fashion as fsync does now. This patch (of 2): Usually we suggest that applications call fsync when they want to ensure that all data written to the file has made it to the backing store, but that can be inefficient when there are a lot of open files. Calling syncfs on the filesystem can be more efficient in some situations, but the error reporting doesn't currently work the way most people expect. If a single inode on a filesystem reports a writeback error, syncfs won't necessarily return an error. syncfs only returns an error if __sync_blockdev fails, and on some filesystems that's a no-op. It would be better if syncfs reported an error if there were any writeback failures. Then applications could call syncfs to see if there are any errors on any open files, and could then call fsync on all of the other descriptors to figure out which one failed. This patch adds a new errseq_t to struct super_block, and has mapping_set_error also record writeback errors there. To report those errors, we also need to keep an errseq_t in struct file to act as a cursor. This patch adds a dedicated field for that purpose, which slots nicely into 4 bytes of padding at the end of struct file on x86_64. An earlier version of this patch used an O_PATH file descriptor to cue the kernel that the open file should track the superblock error and not the inode's writeback error. I think that API is just too weird though. This is simpler and should make syncfs error reporting "just work" even if someone is multiplexing fsync and syncfs on the same fds. Signed-off-by: Jeff Layton Signed-off-by: Andrew Morton Reviewed-by: Jan Kara Cc: Andres Freund Cc: Matthew Wilcox Cc: Al Viro Cc: Christoph Hellwig Cc: Dave Chinner Cc: David Howells Link: http://lkml.kernel.org/r/20200428135155.19223-1-jlayton@kernel.org Link: http://lkml.kernel.org/r/20200428135155.19223-2-jlayton@kernel.org Signed-off-by: Linus Torvalds --- include/linux/fs.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index 45cc10cdf6dd..f2fb5b7406b9 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -976,6 +976,7 @@ struct file { #endif /* #ifdef CONFIG_EPOLL */ struct address_space *f_mapping; errseq_t f_wb_err; + errseq_t f_sb_err; /* for syncfs */ } __randomize_layout __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */ @@ -1520,6 +1521,9 @@ struct super_block { /* Being remounted read-only */ int s_readonly_remount; + /* per-sb errseq_t for reporting writeback errors via syncfs */ + errseq_t s_wb_err; + /* AIO completions deferred from interrupt context */ struct workqueue_struct *s_dio_done_wq; struct hlist_head s_pins; @@ -2827,6 +2831,18 @@ static inline errseq_t filemap_sample_wb_err(struct address_space *mapping) return errseq_sample(&mapping->wb_err); } +/** + * file_sample_sb_err - sample the current errseq_t to test for later errors + * @mapping: mapping to be sampled + * + * Grab the most current superblock-level errseq_t value for the given + * struct file. + */ +static inline errseq_t file_sample_sb_err(struct file *file) +{ + return errseq_sample(&file->f_path.dentry->d_sb->s_wb_err); +} + static inline int filemap_nr_thps(struct address_space *mapping) { #ifdef CONFIG_READ_ONLY_THP_FOR_FS -- cgit v1.2.3 From 8151b4c8bee43cea7a28cb0300123df90880e60c Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 1 Jun 2020 21:46:44 -0700 Subject: mm: add readahead address space operation This replaces ->readpages with a saner interface: - Return void instead of an ignored error code. - Page cache is already populated with locked pages when ->readahead is called. - New arguments can be passed to the implementation without changing all the filesystems that use a common helper function like mpage_readahead(). Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Reviewed-by: John Hubbard Reviewed-by: Christoph Hellwig Reviewed-by: William Kucharski Cc: Chao Yu Cc: Cong Wang Cc: Darrick J. Wong Cc: Dave Chinner Cc: Eric Biggers Cc: Gao Xiang Cc: Jaegeuk Kim Cc: Joseph Qi Cc: Junxiao Bi Cc: Michal Hocko Cc: Zi Yan Cc: Johannes Thumshirn Cc: Miklos Szeredi Link: http://lkml.kernel.org/r/20200414150233.24495-12-willy@infradead.org Signed-off-by: Linus Torvalds --- Documentation/filesystems/locking.rst | 6 +++++- Documentation/filesystems/vfs.rst | 15 +++++++++++++++ include/linux/fs.h | 2 ++ mm/readahead.c | 12 ++++++++++-- 4 files changed, 32 insertions(+), 3 deletions(-) (limited to 'include/linux/fs.h') diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst index 5057e4d9dcd1..0af2e0e11461 100644 --- a/Documentation/filesystems/locking.rst +++ b/Documentation/filesystems/locking.rst @@ -239,6 +239,7 @@ prototypes:: int (*readpage)(struct file *, struct page *); int (*writepages)(struct address_space *, struct writeback_control *); int (*set_page_dirty)(struct page *page); + void (*readahead)(struct readahead_control *); int (*readpages)(struct file *filp, struct address_space *mapping, struct list_head *pages, unsigned nr_pages); int (*write_begin)(struct file *, struct address_space *mapping, @@ -271,7 +272,8 @@ writepage: yes, unlocks (see below) readpage: yes, unlocks writepages: set_page_dirty no -readpages: +readahead: yes, unlocks +readpages: no write_begin: locks the page exclusive write_end: yes, unlocks exclusive bmap: @@ -295,6 +297,8 @@ the request handler (/dev/loop). ->readpage() unlocks the page, either synchronously or via I/O completion. +->readahead() unlocks the pages that I/O is attempted on like ->readpage(). + ->readpages() populates the pagecache with the passed pages and starts I/O against them. They come unlocked upon I/O completion. diff --git a/Documentation/filesystems/vfs.rst b/Documentation/filesystems/vfs.rst index 7d4d09dd5e6d..ed17771c212b 100644 --- a/Documentation/filesystems/vfs.rst +++ b/Documentation/filesystems/vfs.rst @@ -706,6 +706,7 @@ cache in your filesystem. The following members are defined: int (*readpage)(struct file *, struct page *); int (*writepages)(struct address_space *, struct writeback_control *); int (*set_page_dirty)(struct page *page); + void (*readahead)(struct readahead_control *); int (*readpages)(struct file *filp, struct address_space *mapping, struct list_head *pages, unsigned nr_pages); int (*write_begin)(struct file *, struct address_space *mapping, @@ -781,12 +782,26 @@ cache in your filesystem. The following members are defined: If defined, it should set the PageDirty flag, and the PAGECACHE_TAG_DIRTY tag in the radix tree. +``readahead`` + Called by the VM to read pages associated with the address_space + object. The pages are consecutive in the page cache and are + locked. The implementation should decrement the page refcount + after starting I/O on each page. Usually the page will be + unlocked by the I/O completion handler. If the filesystem decides + to stop attempting I/O before reaching the end of the readahead + window, it can simply return. The caller will decrement the page + refcount and unlock the remaining pages for you. Set PageUptodate + if the I/O completes successfully. Setting PageError on any page + will be ignored; simply unlock the page if an I/O error occurs. + ``readpages`` called by the VM to read pages associated with the address_space object. This is essentially just a vector version of readpage. Instead of just one page, several pages are requested. readpages is only used for read-ahead, so read errors are ignored. If anything goes wrong, feel free to give up. + This interface is deprecated and will be removed by the end of + 2020; implement readahead instead. ``write_begin`` Called by the generic buffered write code to ask the filesystem diff --git a/include/linux/fs.h b/include/linux/fs.h index f2fb5b7406b9..1434ed801b80 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -292,6 +292,7 @@ enum positive_aop_returns { struct page; struct address_space; struct writeback_control; +struct readahead_control; /* * Write life time hint values. @@ -375,6 +376,7 @@ struct address_space_operations { */ int (*readpages)(struct file *filp, struct address_space *mapping, struct list_head *pages, unsigned nr_pages); + void (*readahead)(struct readahead_control *); int (*write_begin)(struct file *, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, diff --git a/mm/readahead.c b/mm/readahead.c index e52b3a7b9da5..d01531ef9f3c 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -125,7 +125,14 @@ static void read_pages(struct readahead_control *rac, struct list_head *pages, blk_start_plug(&plug); - if (aops->readpages) { + if (aops->readahead) { + aops->readahead(rac); + /* Clean up the remaining pages */ + while ((page = readahead_page(rac))) { + unlock_page(page); + put_page(page); + } + } else if (aops->readpages) { aops->readpages(rac->file, rac->mapping, pages, readahead_count(rac)); /* Clean up the remaining pages */ @@ -233,7 +240,8 @@ void force_page_cache_readahead(struct address_space *mapping, struct file_ra_state *ra = &filp->f_ra; unsigned long max_pages; - if (unlikely(!mapping->a_ops->readpage && !mapping->a_ops->readpages)) + if (unlikely(!mapping->a_ops->readpage && !mapping->a_ops->readpages && + !mapping->a_ops->readahead)) return; /* -- cgit v1.2.3