fs: move kiocb_start_write() into vfs_iocb_iter_write()

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>

diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c
index 009d23cd435b544d2b7176c86a0f42eb4d2e2a4a..5857241c59181674ef8dafcfc9b6216d65db75a0 100644 (file)
--- a/fs/cachefiles/io.c
+++ b/fs/cachefiles/io.c
@@ -259,7 +259,8 @@ 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,
@@ -319,8 +320,6 @@ 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 690b173f34fc458fa121144f7043766eb7a5c905..4e46420c8fdd621b9472111815a668d93c065712 100644 (file)
--- a/fs/overlayfs/file.c
+++ b/fs/overlayfs/file.c
@@ -295,10 +295,8 @@ 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);
@@ -310,6 +308,9 @@ 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);
 }
@@ -456,7 +457,6 @@ 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 9fce8d6968df6fccf6feaaf812bb6b6e9b31f949..92c68ab4f2212821c6f5aefe821267bcbb2e9f55 100644 (file)
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -829,6 +829,10 @@ out:
 }
 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)
 {
@@ -849,7 +853,10 @@ 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);