From bcbb7bf6ccde7cb969a5642879832bc84ebf06a3 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 10 Mar 2022 12:59:35 -0700
Subject: [PATCH] io_uring: allow submissions to continue on error
Git-commit: bcbb7bf6ccde7cb969a5642879832bc84ebf06a3
Patch-mainline: v5.18-rc1
References: bsc#1205205

By default, io_uring will stop submitting a batch of requests if we run
into an error submitting a request. This isn't strictly necessary, as
the error result is passed out-of-band via a CQE anyway. And it can be
a bit confusing for some applications.

Provide a way to setup a ring that will continue submitting on error,
when the error CQE has been posted.

There's still one case that will break out of submission. If we fail
allocating a request, then we'll still return -ENOMEM. We could in theory
post a CQE for that condition too even if we never got a request. Leave
that for a potential followup.

Reported-by: Dylan Yudaken <dylany@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Gabriel Krisman Bertazi <krisman@suse.de>
---
 fs/io_uring.c                 | 12 +++++++++---
 include/uapi/linux/io_uring.h |  1 +
 2 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 3145c9cacee0..229b31d644ef 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -7801,8 +7801,14 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr)
 		}
 		/* will complete beyond this point, count as submitted */
 		submitted++;
-		if (io_submit_sqe(ctx, req, sqe))
-			break;
+		if (io_submit_sqe(ctx, req, sqe)) {
+			/*
+			 * Continue submitting even for sqe failure if the
+			 * ring was setup with IORING_SETUP_SUBMIT_ALL
+			 */
+			if (!(ctx->flags & IORING_SETUP_SUBMIT_ALL))
+				break;
+		}
 	} while (submitted < nr);
 
 	if (unlikely(submitted != nr)) {
@@ -11265,7 +11271,7 @@ static long io_uring_setup(u32 entries, struct io_uring_params __user *params)
 	if (p.flags & ~(IORING_SETUP_IOPOLL | IORING_SETUP_SQPOLL |
 			IORING_SETUP_SQ_AFF | IORING_SETUP_CQSIZE |
 			IORING_SETUP_CLAMP | IORING_SETUP_ATTACH_WQ |
-			IORING_SETUP_R_DISABLED))
+			IORING_SETUP_R_DISABLED | IORING_SETUP_SUBMIT_ALL))
 		return -EINVAL;
 
 	return  io_uring_create(entries, &p, params);
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 8bd4bfdd9a89..d2be4eb22008 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -101,6 +101,7 @@ enum {
 #define IORING_SETUP_CLAMP	(1U << 4)	/* clamp SQ/CQ ring sizes */
 #define IORING_SETUP_ATTACH_WQ	(1U << 5)	/* attach to existing wq */
 #define IORING_SETUP_R_DISABLED	(1U << 6)	/* start with ring disabled */
+#define IORING_SETUP_SUBMIT_ALL	(1U << 7)	/* continue submit on error */
 
 enum {
 	IORING_OP_NOP,
-- 
2.35.3