[PATCH for-next 5/7] io_uring: post msg_ring CQE in task context

[Pavel Begunkov <asml.silence@xxxxxxxxx>]

We want to limit post_aux_cqe() to the task context when ->task_complete
is set, and so we can't just deliver a IORING_OP_MSG_RING CQE to another
thread. Instead of trying to invent a new delayed CQE posting mechanism
push them into the overflow list.

Signed-off-by: Pavel Begunkov <asml.silence@xxxxxxxxx>
---
 io_uring/io_uring.c | 12 ++++++++++++
 io_uring/io_uring.h |  2 ++
 io_uring/msg_ring.c | 14 ++++++++++++--
 3 files changed, 26 insertions(+), 2 deletions(-)

diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 0c86df7112fb..7fda57dc0e8c 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -860,6 +860,18 @@ bool io_post_aux_cqe(struct io_ring_ctx *ctx, u64 user_data, s32 res, u32 cflags
 	return __io_post_aux_cqe(ctx, user_data, res, cflags, true);
 }
 
+bool io_post_aux_cqe_overflow(struct io_ring_ctx *ctx,
+			      u64 user_data, s32 res, u32 cflags)
+{
+	bool filled;
+
+	io_cq_lock(ctx);
+	ctx->cq_extra++;
+	filled = io_cqring_event_overflow(ctx, user_data, res, cflags, 0, 0);
+	io_cq_unlock_post(ctx);
+	return filled;
+}
+
 bool io_aux_cqe(struct io_ring_ctx *ctx, bool defer, u64 user_data, s32 res, u32 cflags,
 		bool allow_overflow)
 {
diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h
index 62227ec3260c..a0b11a631e29 100644
--- a/io_uring/io_uring.h
+++ b/io_uring/io_uring.h
@@ -36,6 +36,8 @@ bool io_post_aux_cqe(struct io_ring_ctx *ctx, u64 user_data, s32 res, u32 cflags
 bool io_aux_cqe(struct io_ring_ctx *ctx, bool defer, u64 user_data, s32 res, u32 cflags,
 		bool allow_overflow);
 void __io_commit_cqring_flush(struct io_ring_ctx *ctx);
+bool io_post_aux_cqe_overflow(struct io_ring_ctx *ctx,
+			      u64 user_data, s32 res, u32 cflags);
 
 struct page **io_pin_pages(unsigned long ubuf, unsigned long len, int *npages);
 
diff --git a/io_uring/msg_ring.c b/io_uring/msg_ring.c
index afb543aab9f6..7717fe519b07 100644
--- a/io_uring/msg_ring.c
+++ b/io_uring/msg_ring.c
@@ -23,6 +23,16 @@ struct io_msg {
 	u32 flags;
 };
 
+/* post cqes to another ring */
+static int io_msg_post_cqe(struct io_ring_ctx *ctx,
+			   u64 user_data, s32 res, u32 cflags)
+{
+	if (!ctx->task_complete || current == ctx->submitter_task)
+		return io_post_aux_cqe(ctx, user_data, res, cflags);
+	else
+		return io_post_aux_cqe_overflow(ctx, user_data, res, cflags);
+}
+
 static int io_msg_ring_data(struct io_kiocb *req)
 {
 	struct io_ring_ctx *target_ctx = req->file->private_data;
@@ -31,7 +41,7 @@ static int io_msg_ring_data(struct io_kiocb *req)
 	if (msg->src_fd || msg->dst_fd || msg->flags)
 		return -EINVAL;
 
-	if (io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0))
+	if (io_msg_post_cqe(target_ctx, msg->user_data, msg->len, 0))
 		return 0;
 
 	return -EOVERFLOW;
@@ -116,7 +126,7 @@ static int io_msg_send_fd(struct io_kiocb *req, unsigned int issue_flags)
 	 * completes with -EOVERFLOW, then the sender must ensure that a
 	 * later IORING_OP_MSG_RING delivers the message.
 	 */
-	if (!io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0))
+	if (!io_msg_post_cqe(target_ctx, msg->user_data, msg->len, 0))
 		ret = -EOVERFLOW;
 out_unlock:
 	io_double_unlock_ctx(ctx, target_ctx, issue_flags);
-- 
2.38.1