From: Amir Goldstein <amir73il@gmail.com> mainline inclusion from mainline-v6.8-rc1 commit 6ae654392bb516a0baa47fed1f085d84e8cad739 category: feature bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBHLU4 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- In vfs code, sb_start_write() is usually called after the permission hook in rw_verify_area(). vfs_iocb_iter_write() is an exception to this rule, where kiocb_start_write() is called by its callers. Move kiocb_start_write() from the callers into vfs_iocb_iter_write() after the rw_verify_area() checks, to make them "start-write-safe". The semantics of vfs_iocb_iter_write() is changed, so that the caller is responsible for calling kiocb_end_write() on completion only if async iocb was queued. The completion handlers of both callers were adapted to this semantic change. This is needed for fanotify "pre content" events. Suggested-by: Jan Kara <jack@suse.cz> Suggested-by: Josef Bacik <josef@toxicpanda.com> Signed-off-by: Amir Goldstein <amir73il@gmail.com> Link: https://lore.kernel.org/r/20231122122715.2561213-14-amir73il@gmail.com Reviewed-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Christian Brauner <brauner@kernel.org> Signed-off-by: Yifan Qiao <qiaoyifan4@huawei.com> --- fs/cachefiles/io.c | 5 ++--- fs/overlayfs/file.c | 8 ++++---- fs/read_write.c | 7 +++++++ 3 files changed, 13 insertions(+), 7 deletions(-) diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c index e55c7cc6a997..f7a507ddd668 100644 --- a/fs/cachefiles/io.c +++ b/fs/cachefiles/io.c @@ -268,7 +268,8 @@ static void cachefiles_write_complete(struct kiocb *iocb, long ret) _enter("%ld", ret); - kiocb_end_write(iocb); + if (ki->was_async) + kiocb_end_write(iocb); if (ret < 0) trace_cachefiles_io_error(object, inode, ret, @@ -331,8 +332,6 @@ int __cachefiles_write(struct cachefiles_object *object, ki->iocb.ki_complete = cachefiles_write_complete; atomic_long_add(ki->b_writing, &cache->b_writing); - kiocb_start_write(&ki->iocb); - get_file(ki->iocb.ki_filp); cachefiles_grab_object(object, cachefiles_obj_get_ioreq); diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index 352836288943..0d0ba0240fa5 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -292,10 +292,8 @@ static void ovl_aio_cleanup_handler(struct ovl_aio_req *aio_req) struct kiocb *iocb = &aio_req->iocb; struct kiocb *orig_iocb = aio_req->orig_iocb; - if (iocb->ki_flags & IOCB_WRITE) { - kiocb_end_write(iocb); + if (iocb->ki_flags & IOCB_WRITE) ovl_file_modified(orig_iocb->ki_filp); - } orig_iocb->ki_pos = iocb->ki_pos; ovl_aio_put(aio_req); @@ -307,6 +305,9 @@ static void ovl_aio_rw_complete(struct kiocb *iocb, long res) struct ovl_aio_req, iocb); struct kiocb *orig_iocb = aio_req->orig_iocb; + if (iocb->ki_flags & IOCB_WRITE) + kiocb_end_write(iocb); + ovl_aio_cleanup_handler(aio_req); orig_iocb->ki_complete(orig_iocb, res); } @@ -453,7 +454,6 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter) aio_req->iocb.ki_flags = ifl; aio_req->iocb.ki_complete = ovl_aio_queue_completion; refcount_set(&aio_req->ref, 2); - kiocb_start_write(&aio_req->iocb); ret = vfs_iocb_iter_write(real.file, &aio_req->iocb, iter); ovl_aio_put(aio_req); if (ret != -EIOCBQUEUED) diff --git a/fs/read_write.c b/fs/read_write.c index a43dd3915c1a..efd4f0fd878b 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -831,6 +831,10 @@ ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos, } EXPORT_SYMBOL(vfs_iter_read); +/* + * Caller is responsible for calling kiocb_end_write() on completion + * if async iocb was queued. + */ ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb, struct iov_iter *iter) { @@ -851,7 +855,10 @@ ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb, if (ret < 0) return ret; + kiocb_start_write(iocb); ret = call_write_iter(file, iocb, iter); + if (ret != -EIOCBQUEUED) + kiocb_end_write(iocb); if (ret > 0) fsnotify_modify(file); -- 2.39.2