From d072148a8631f102de60ed5a3a827e85d09d24f0 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 19 Aug 2025 10:25:00 +0200 Subject: [PATCH 1/2] fs: add a FMODE_ flag to indicate IOCB_HAS_METADATA availability Currently the kernel will happily route io_uring requests with metadata to file operations that don't support it. Add a FMODE_ flag to guard that. Fixes: 4de2ce04c862 ("fs: introduce IOCB_HAS_METADATA for metadata") Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/20250819082517.2038819-2-hch@lst.de Signed-off-by: Christian Brauner --- block/fops.c | 3 +++ include/linux/fs.h | 3 ++- io_uring/rw.c | 3 +++ 3 files changed, 8 insertions(+), 1 deletion(-) diff --git a/block/fops.c b/block/fops.c index 82451ac8ff25..08e7c21bd9f1 100644 --- a/block/fops.c +++ b/block/fops.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include #include @@ -687,6 +688,8 @@ static int blkdev_open(struct inode *inode, struct file *filp) if (bdev_can_atomic_write(bdev)) filp->f_mode |= FMODE_CAN_ATOMIC_WRITE; + if (blk_get_integrity(bdev->bd_disk)) + filp->f_mode |= FMODE_HAS_METADATA; ret = bdev_open(bdev, mode, filp->private_data, NULL, filp); if (ret) diff --git a/include/linux/fs.h b/include/linux/fs.h index d7ab4f96d705..601d036a6c78 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -149,7 +149,8 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* Expect random access pattern */ #define FMODE_RANDOM ((__force fmode_t)(1 << 12)) -/* FMODE_* bit 13 */ +/* Supports IOCB_HAS_METADATA */ +#define FMODE_HAS_METADATA ((__force fmode_t)(1 << 13)) /* File is opened with O_PATH; almost nothing can be done with it */ #define FMODE_PATH ((__force fmode_t)(1 << 14)) diff --git a/io_uring/rw.c b/io_uring/rw.c index 52a5b950b2e5..af5a54b5db12 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -886,6 +886,9 @@ static int io_rw_init_file(struct io_kiocb *req, fmode_t mode, int rw_type) if (req->flags & REQ_F_HAS_METADATA) { struct io_async_rw *io = req->async_data; + if (!(file->f_mode & FMODE_HAS_METADATA)) + return -EINVAL; + /* * We have a union of meta fields with wpq used for buffered-io * in io_async_rw, so fail it here. From 2729a60bbfb9215997f25372ebe9b7964f038296 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 19 Aug 2025 10:25:01 +0200 Subject: [PATCH 2/2] block: don't silently ignore metadata for sync read/write The block fops don't try to handle metadata for synchronous requests, probably because the completion handler looks at dio->iocb which is not valid for synchronous requests. But silently ignoring metadata (or warning in case of __blkdev_direct_IO_simple) is a really bad idea as that can cause silent data corruption if a user ever shows up. Instead simply handle metadata for synchronous requests as the completion handler can simply check for bio_integrity() as the block layer default integrity will already be freed at this point, and thus bio_integrity() will only return true for user mapped integrity. Fixes: 3d8b5a22d404 ("block: add support to pass user meta buffer") Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/20250819082517.2038819-3-hch@lst.de Reviewed-by: Martin K. Petersen Signed-off-by: Christian Brauner --- block/fops.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/block/fops.c b/block/fops.c index 08e7c21bd9f1..ddbc69c0922b 100644 --- a/block/fops.c +++ b/block/fops.c @@ -55,7 +55,6 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb, struct bio bio; ssize_t ret; - WARN_ON_ONCE(iocb->ki_flags & IOCB_HAS_METADATA); if (nr_pages <= DIO_INLINE_BIO_VECS) vecs = inline_vecs; else { @@ -132,7 +131,7 @@ static void blkdev_bio_end_io(struct bio *bio) if (bio->bi_status && !dio->bio.bi_status) dio->bio.bi_status = bio->bi_status; - if (!is_sync && (dio->iocb->ki_flags & IOCB_HAS_METADATA)) + if (bio_integrity(bio)) bio_integrity_unmap_user(bio); if (atomic_dec_and_test(&dio->ref)) { @@ -234,7 +233,7 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, } bio->bi_opf |= REQ_NOWAIT; } - if (!is_sync && (iocb->ki_flags & IOCB_HAS_METADATA)) { + if (iocb->ki_flags & IOCB_HAS_METADATA) { ret = bio_integrity_map_iter(bio, iocb->private); if (unlikely(ret)) goto fail; @@ -302,7 +301,7 @@ static void blkdev_bio_end_io_async(struct bio *bio) ret = blk_status_to_errno(bio->bi_status); } - if (iocb->ki_flags & IOCB_HAS_METADATA) + if (bio_integrity(bio)) bio_integrity_unmap_user(bio); iocb->ki_complete(iocb, ret); @@ -423,7 +422,8 @@ static ssize_t blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter) } nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS + 1); - if (likely(nr_pages <= BIO_MAX_VECS)) { + if (likely(nr_pages <= BIO_MAX_VECS && + !(iocb->ki_flags & IOCB_HAS_METADATA))) { if (is_sync_kiocb(iocb)) return __blkdev_direct_IO_simple(iocb, iter, bdev, nr_pages);