[PATCHv2] io_uring: Support calling io_uring_register with a registered ring fd

From: Josh Triplett
Date: Tue Feb 14 2023 - 19:42:32 EST


Add a new flag IORING_REGISTER_USE_REGISTERED_RING (set via the high bit
of the opcode) to treat the fd as a registered index rather than a file
descriptor.

This makes it possible for a library to open an io_uring, register the
ring fd, close the ring fd, and subsequently use the ring entirely via
registered index.

Signed-off-by: Josh Triplett <josh@xxxxxxxxxxxxxxxx>
---

v2: Rebase. Change io_uring_register to extract the flag from the opcode first.

include/uapi/linux/io_uring.h | 6 +++++-
io_uring/io_uring.c | 34 +++++++++++++++++++++++++++-------
2 files changed, 32 insertions(+), 8 deletions(-)

diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 2780bce62faf..35e6f8046b9b 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -470,6 +470,7 @@ struct io_uring_params {
#define IORING_FEAT_RSRC_TAGS (1U << 10)
#define IORING_FEAT_CQE_SKIP (1U << 11)
#define IORING_FEAT_LINKED_FILE (1U << 12)
+#define IORING_FEAT_REG_REG_RING (1U << 13)

/*
* io_uring_register(2) opcodes and arguments
@@ -517,7 +518,10 @@ enum {
IORING_REGISTER_FILE_ALLOC_RANGE = 25,

/* this goes last */
- IORING_REGISTER_LAST
+ IORING_REGISTER_LAST,
+
+ /* flag added to the opcode to use a registered ring fd */
+ IORING_REGISTER_USE_REGISTERED_RING = 1U << 31
};

/* io-wq worker categories */
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index db623b3185c8..1fb743ecba5a 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -3663,7 +3663,7 @@ static __cold int io_uring_create(unsigned entries, struct io_uring_params *p,
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_LINKED_FILE;
+ IORING_FEAT_LINKED_FILE | IORING_FEAT_REG_REG_RING;

if (copy_to_user(params, p, sizeof(*p))) {
ret = -EFAULT;
@@ -4177,17 +4177,37 @@ SYSCALL_DEFINE4(io_uring_register, unsigned int, fd, unsigned int, opcode,
struct io_ring_ctx *ctx;
long ret = -EBADF;
struct fd f;
+ bool use_registered_ring;
+
+ use_registered_ring = !!(opcode & IORING_REGISTER_USE_REGISTERED_RING);
+ opcode &= ~IORING_REGISTER_USE_REGISTERED_RING;

if (opcode >= IORING_REGISTER_LAST)
return -EINVAL;

- f = fdget(fd);
- if (!f.file)
- return -EBADF;
+ if (use_registered_ring) {
+ /*
+ * Ring fd has been registered via IORING_REGISTER_RING_FDS, we
+ * need only dereference our task private array to find it.
+ */
+ struct io_uring_task *tctx = current->io_uring;

- ret = -EOPNOTSUPP;
- if (!io_is_uring_fops(f.file))
- goto out_fput;
+ if (unlikely(!tctx || fd >= IO_RINGFD_REG_MAX))
+ return -EINVAL;
+ fd = array_index_nospec(fd, IO_RINGFD_REG_MAX);
+ f.file = tctx->registered_rings[fd];
+ f.flags = 0;
+ if (unlikely(!f.file))
+ return -EBADF;
+ opcode &= ~IORING_REGISTER_USE_REGISTERED_RING;
+ } else {
+ f = fdget(fd);
+ if (unlikely(!f.file))
+ return -EBADF;
+ ret = -EOPNOTSUPP;
+ if (!io_is_uring_fops(f.file))
+ goto out_fput;
+ }

ctx = f.file->private_data;

--
2.39.1