io_uring: don't pass restart error codes to userspace

-ERESTARTSYS and friends are instructions for the system call exit code,
which either restarts the call or turns them into -EINTR. They are not
supposed to be seen by applications. A request isn't a system call,
nobody looks at what it returns before that is put into a CQE.

The read/write and the networking opcodes convert these codes to -EINTR
by hand. The others don't. An io-wq worker that is blocked in the open of
a FIFO, a tty or some other device, or in a splice from an empty pipe,
and that gets interrupted because the request is cancelled, completes it
with -512:

  IORING_OP_OPENAT, IOSQE_ASYNC       // FIFO without a writer
  IORING_OP_ASYNC_CANCEL              // -EALREADY, worker is signalled
  CQE of the open: res == -512

There are more candidates, like whatever a file system or driver returns
from ->flush(), ->fsync(), ->fallocate() or ->uring_cmd(), or breaking a
lease or delegation.

Take care of it in io_issue_sqe(), which all of them go through. The
helper is moved from rw.c as is. The cost is a compare and a branch that
is not taken per request.

Fixes: 15b71abe7b52 ("io_uring: add support for IORING_OP_OPENAT")
Assisted-by: LLM
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Link: https://patch.msgid.link/20261015-b4-io-uring-fixes-v1-39-c1556f5d7bf5@toxicpanda.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

3 files changed, 23 insertions, 18 deletions

diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 7092efc22dd2..2fa720160e8f 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -1457,6 +1457,9 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
 	ret = __io_issue_sqe(req, issue_flags, def);
 
 	if (ret == IOU_COMPLETE) {
+		/* not all handlers take care of the internal restart codes */
+		if (unlikely(req->cqe.res <= -ERESTARTSYS))
+			req->cqe.res = io_fixup_restart_res(req->cqe.res);
 		if (issue_flags & IO_URING_F_COMPLETE_DEFER)
 			io_req_complete_defer(req);
 		else
@@ -1471,6 +1474,8 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
 		if (req->flags & REQ_F_IOPOLL)
 			io_iopoll_req_issued(req, issue_flags);
 	}
+	if (unlikely(ret <= -ERESTARTSYS))
+		ret = io_fixup_restart_res(ret);
 	return ret;
 }
 
diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h
index 36d0d67fcb9f..203bf019e931 100644
--- a/io_uring/io_uring.h
+++ b/io_uring/io_uring.h
@@ -319,6 +319,24 @@ static __always_inline bool io_fill_cqe_req(struct io_ring_ctx *ctx,
 	return true;
 }
 
+static inline ssize_t io_fixup_restart_res(ssize_t ret)
+{
+	switch (ret) {
+	case -ERESTARTSYS:
+	case -ERESTARTNOINTR:
+	case -ERESTARTNOHAND:
+	case -ERESTART_RESTARTBLOCK:
+		/*
+		 * We can't just restart the syscall, since previously
+		 * submitted sqes may already be in progress. Just fail
+		 * this IO with EINTR.
+		 */
+		return -EINTR;
+	default:
+		return ret;
+	}
+}
+
 static inline void *io_uring_alloc_async_data(struct io_alloc_cache *cache,
 					      struct io_kiocb *req)
 {
diff --git a/io_uring/rw.c b/io_uring/rw.c
index 999d9a1cc5a5..ac211badbe9a 100644
--- a/io_uring/rw.c
+++ b/io_uring/rw.c
@@ -605,24 +605,6 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res)
 	smp_store_release(&req->iopoll_completed, 1);
 }
 
-static inline ssize_t io_fixup_restart_res(ssize_t ret)
-{
-	switch (ret) {
-	case -ERESTARTSYS:
-	case -ERESTARTNOINTR:
-	case -ERESTARTNOHAND:
-	case -ERESTART_RESTARTBLOCK:
-		/*
-		 * We can't just restart the syscall, since previously
-		 * submitted sqes may already be in progress. Just fail
-		 * this IO with EINTR.
-		 */
-		return -EINTR;
-	default:
-		return ret;
-	}
-}
-
 static inline void io_rw_done(struct io_kiocb *req, ssize_t ret)
 {
 	struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw);