From: Christoph Hellwig hch@lst.de
commit 44fff0fa08ec5a6d9d5fb05443a36d854d0ece4d upstream.
Add a helper dealing with handling the syncing of a buffered write fallback for direct I/O.
Link: https://lkml.kernel.org/r/20230601145904.1385409-10-hch@lst.de Signed-off-by: Christoph Hellwig hch@lst.de Reviewed-by: Damien Le Moal dlemoal@kernel.org Reviewed-by: Miklos Szeredi mszeredi@redhat.com Reviewed-by: Darrick J. Wong djwong@kernel.org Cc: Al Viro viro@zeniv.linux.org.uk Cc: Andreas Gruenbacher agruenba@redhat.com Cc: Anna Schumaker anna@kernel.org Cc: Chao Yu chao@kernel.org Cc: Christian Brauner brauner@kernel.org Cc: Hannes Reinecke hare@suse.de Cc: Ilya Dryomov idryomov@gmail.com Cc: Jaegeuk Kim jaegeuk@kernel.org Cc: Jens Axboe axboe@kernel.dk Cc: Johannes Thumshirn johannes.thumshirn@wdc.com Cc: Matthew Wilcox willy@infradead.org Cc: Miklos Szeredi miklos@szeredi.hu Cc: Theodore Ts'o tytso@mit.edu Cc: Trond Myklebust trond.myklebust@hammerspace.com Cc: Xiubo Li xiubli@redhat.com Signed-off-by: Andrew Morton akpm@linux-foundation.org [backing_dev_info still being used here. do small changes to the patch to keep the out label. Which means replacing all returns to goto out.] Signed-off-by: Mahmoud Adam mngyadam@amazon.de --- fs/libfs.c | 41 +++++++++++++++++++++++++++++++ include/linux/fs.h | 2 ++ mm/filemap.c | 61 +++++++++++----------------------------------- 3 files changed, 57 insertions(+), 47 deletions(-)
diff --git a/fs/libfs.c b/fs/libfs.c index cbd42d76fbd018..a5bbe8e31d6616 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -1582,3 +1582,44 @@ bool inode_maybe_inc_iversion(struct inode *inode, bool force) return true; } EXPORT_SYMBOL(inode_maybe_inc_iversion); + +ssize_t direct_write_fallback(struct kiocb *iocb, struct iov_iter *iter, + ssize_t direct_written, ssize_t buffered_written) +{ + struct address_space *mapping = iocb->ki_filp->f_mapping; + loff_t pos = iocb->ki_pos - buffered_written; + loff_t end = iocb->ki_pos - 1; + int err; + + /* + * If the buffered write fallback returned an error, we want to return + * the number of bytes which were written by direct I/O, or the error + * code if that was zero. + * + * Note that this differs from normal direct-io semantics, which will + * return -EFOO even if some bytes were written. + */ + if (unlikely(buffered_written < 0)) { + if (direct_written) + return direct_written; + return buffered_written; + } + + /* + * We need to ensure that the page cache pages are written to disk and + * invalidated to preserve the expected O_DIRECT semantics. + */ + err = filemap_write_and_wait_range(mapping, pos, end); + if (err < 0) { + /* + * We don't know how much we wrote, so just return the number of + * bytes which were direct-written + */ + if (direct_written) + return direct_written; + return err; + } + invalidate_mapping_pages(mapping, pos >> PAGE_SHIFT, end >> PAGE_SHIFT); + return direct_written + buffered_written; +} +EXPORT_SYMBOL_GPL(direct_write_fallback); diff --git a/include/linux/fs.h b/include/linux/fs.h index 4e8a3e4f894c0f..02c83cd07d4f20 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3278,6 +3278,8 @@ extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_direct_write(struct kiocb *, struct iov_iter *); ssize_t generic_perform_write(struct kiocb *, struct iov_iter *); +ssize_t direct_write_fallback(struct kiocb *iocb, struct iov_iter *iter, + ssize_t direct_written, ssize_t buffered_written);
ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags); diff --git a/mm/filemap.c b/mm/filemap.c index e2045266d2f2c9..b77f534dfad35a 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -3923,25 +3923,21 @@ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; - struct inode *inode = mapping->host; - ssize_t written = 0; - ssize_t err; - ssize_t status; + struct inode *inode = mapping->host; + ssize_t ret;
/* We can write back this queue in page reclaim */ current->backing_dev_info = inode_to_bdi(inode); - err = file_remove_privs(file); - if (err) + ret = file_remove_privs(file); + if (ret) goto out;
- err = file_update_time(file); - if (err) + ret = file_update_time(file); + if (ret) goto out;
if (iocb->ki_flags & IOCB_DIRECT) { - loff_t pos, endbyte; - - written = generic_file_direct_write(iocb, from); + ret = generic_file_direct_write(iocb, from); /* * If the write stopped short of completing, fall back to * buffered writes. Some filesystems do this for writes to @@ -3949,46 +3945,17 @@ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) * not succeed (even if it did, DAX does not handle dirty * page-cache pages correctly). */ - if (written < 0 || !iov_iter_count(from) || IS_DAX(inode)) + if (ret < 0 || !iov_iter_count(from) || IS_DAX(inode)) goto out; - - pos = iocb->ki_pos; - status = generic_perform_write(iocb, from); - /* - * If generic_perform_write() returned a synchronous error - * then we want to return the number of bytes which were - * direct-written, or the error code if that was zero. Note - * that this differs from normal direct-io semantics, which - * will return -EFOO even if some bytes were written. - */ - if (unlikely(status < 0)) { - err = status; - goto out; - } - /* - * We need to ensure that the page cache pages are written to - * disk and invalidated to preserve the expected O_DIRECT - * semantics. - */ - endbyte = pos + status - 1; - err = filemap_write_and_wait_range(mapping, pos, endbyte); - if (err == 0) { - written += status; - invalidate_mapping_pages(mapping, - pos >> PAGE_SHIFT, - endbyte >> PAGE_SHIFT); - } else { - /* - * We don't know how much we wrote, so just return - * the number of bytes which were direct-written - */ - } - } else { - written = generic_perform_write(iocb, from); + ret = direct_write_fallback(iocb, from, ret, + generic_perform_write(iocb, from)); + goto out; } + + ret = generic_perform_write(iocb, from); out: current->backing_dev_info = NULL; - return written ? written : err; + return ret; } EXPORT_SYMBOL(__generic_file_write_iter);