Give applications a way to tell if the kernel supports sane linked files,
as in files being assigned at the right time to be able to reliably
do <open file direct into slot X><read file from slot X> while using
IOSQE_IO_LINK to order them.
Not really a bug fix, but flag it as such so that it gets pulled in with
backports of the deferred file assignment.
Fixes: 6bf9c47a3989 ("io_uring: defer file assignment")
Signed-off-by: Jens Axboe <axboe@xxxxxxxxx>
---
fs/io_uring.c | 3 ++-
include/uapi/linux/io_uring.h | 1 +
2 files changed, 3 insertions(+), 1 deletion(-)
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 659f8ecba5b7..f060ad018ba4 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -11178,7 +11178,8 @@ static __cold int io_uring_create(unsigned entries, struct io_uring_params *p,
IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL |
IORING_FEAT_POLL_32BITS | IORING_FEAT_SQPOLL_NONFIXED |
IORING_FEAT_EXT_ARG | IORING_FEAT_NATIVE_WORKERS |
- IORING_FEAT_RSRC_TAGS | IORING_FEAT_CQE_SKIP;
+ IORING_FEAT_RSRC_TAGS | IORING_FEAT_CQE_SKIP |
+ IORING_FEAT_LINKED_FILE;
if (copy_to_user(params, p, sizeof(*p))) {
ret = -EFAULT;
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 784adc6f6ed2..1845cf7c80ba 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -296,6 +296,7 @@ struct io_uring_params {
#define IORING_FEAT_NATIVE_WORKERS (1U << 9)
#define IORING_FEAT_RSRC_TAGS (1U << 10)
#define IORING_FEAT_CQE_SKIP (1U << 11)
+#define IORING_FEAT_LINKED_FILE (1U << 12)
/*
* io_uring_register(2) opcodes and arguments
--
2.35.1
