netfs: zero the tail of a short DIO/unbuffered readgrafted

The buffered read collector zero-fills the tail of a short read that
stops below the inode's i_size (netfs_clear_unread()), so a read that
races an extending write still returns the expected number of bytes.
The non-buffered collector path does no such thing: it just records
how much was transferred.

Add the same zero-fill for the non-buffered case, gated on
NETFS_SREQ_CLEAR_TAIL: a subreq's source sets that flag when a short
result from it is known to be safe to treat as a hole, as opposed to
NETFS_SREQ_HIT_EOF, which means the read genuinely ran off the end of
the file and should be reported short as-is. Only CLEAR_TAIL should
zero-fill here; a real EOF must stay a real short read.

No source currently sets CLEAR_TAIL on an unbuffered/DIO subrequest,
so this is inert on its own -- a following change teaches cifs to set
it in the one case that needs it.

Fixes: e2d46f2ec332 ("netfs: Change the read result collector to only use one work item")
Reviewed-by: David Howells <dhowells@redhat.com>
Reviewed-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Paulo Alcantara <pc@manguebit.org>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Ronnie Sahlberg <ronniesahlberg@gmail.com>
Cc: Shyam Prasad N <sprasad@microsoft.com>
Cc: Tom Talpey <tom@talpey.com>
Cc: Bharath SM <bharathsm@microsoft.com>
Cc: stable@vger.kernel.org

1 files changed, 114 insertions, 0 deletions

diff --git a/io_uring/sync.c b/io_uring/sync.c
new file mode 100644
index 000000000..ab7fa1cd7
--- /dev/null
+++ b/io_uring/sync.c
@@ -0,0 +1,114 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/namei.h>
+#include <linux/io_uring.h>
+#include <linux/fsnotify.h>
+
+#include <uapi/linux/io_uring.h>
+
+#include "io_uring.h"
+#include "sync.h"
+
+struct io_sync {
+	struct file			*file;
+	loff_t				len;
+	loff_t				off;
+	int				flags;
+	int				mode;
+};
+
+int io_sfr_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_sync *sync = io_kiocb_to_cmd(req, struct io_sync);
+
+	if (unlikely(sqe->addr || sqe->buf_index || sqe->splice_fd_in))
+		return -EINVAL;
+
+	sync->off = READ_ONCE(sqe->off);
+	sync->len = READ_ONCE(sqe->len);
+	sync->flags = READ_ONCE(sqe->sync_range_flags);
+	req->flags |= REQ_F_FORCE_ASYNC;
+
+	return 0;
+}
+
+int io_sync_file_range(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_sync *sync = io_kiocb_to_cmd(req, struct io_sync);
+	int ret;
+
+	/* sync_file_range always requires a blocking context */
+	WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK);
+
+	ret = sync_file_range(req->file, sync->off, sync->len, sync->flags);
+	io_req_set_res(req, ret, 0);
+	return IOU_COMPLETE;
+}
+
+int io_fsync_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_sync *sync = io_kiocb_to_cmd(req, struct io_sync);
+
+	if (unlikely(sqe->addr || sqe->buf_index || sqe->splice_fd_in))
+		return -EINVAL;
+
+	sync->flags = READ_ONCE(sqe->fsync_flags);
+	if (unlikely(sync->flags & ~IORING_FSYNC_DATASYNC))
+		return -EINVAL;
+
+	sync->off = READ_ONCE(sqe->off);
+	if (sync->off < 0)
+		return -EINVAL;
+	sync->len = READ_ONCE(sqe->len);
+	req->flags |= REQ_F_FORCE_ASYNC;
+	return 0;
+}
+
+int io_fsync(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_sync *sync = io_kiocb_to_cmd(req, struct io_sync);
+	loff_t end = sync->off + sync->len;
+	int ret;
+
+	/* fsync always requires a blocking context */
+	WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK);
+
+	ret = vfs_fsync_range(req->file, sync->off, end > 0 ? end : LLONG_MAX,
+				sync->flags & IORING_FSYNC_DATASYNC);
+	io_req_set_res(req, ret, 0);
+	return IOU_COMPLETE;
+}
+
+int io_fallocate_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_sync *sync = io_kiocb_to_cmd(req, struct io_sync);
+
+	if (sqe->buf_index || sqe->rw_flags || sqe->splice_fd_in)
+		return -EINVAL;
+
+	sync->off = READ_ONCE(sqe->off);
+	sync->len = READ_ONCE(sqe->addr);
+	sync->mode = READ_ONCE(sqe->len);
+	req->flags |= REQ_F_FORCE_ASYNC;
+	return 0;
+}
+
+int io_fallocate(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_sync *sync = io_kiocb_to_cmd(req, struct io_sync);
+	int ret;
+
+	/* fallocate always requiring blocking context */
+	WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK);
+
+	ret = vfs_fallocate(req->file, sync->mode, sync->off, sync->len);
+	if (ret >= 0)
+		fsnotify_modify(req->file);
+	io_req_set_res(req, ret, 0);
+	return IOU_COMPLETE;
+}