io_uring: Support calling io_uring_register with a registered ring fd

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@joshtriplett.org>
Link: https://lore.kernel.org/r/f2396369e638284586b069dbddffb8c992afba95.1676419314.git.josh@joshtriplett.org
[axboe: remove extra high bit clear]
Signed-off-by: Jens Axboe <axboe@kernel.dk>

include/uapi/linux/io_uring.h

@@ -472,6 +472,7 @@ 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
@@ -519,7 +520,10 @@ 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 */

io_uring/io_uring.c

@@ -3785,7 +3785,7 @@ 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;
@@ -4306,17 +4306,36 @@ 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;
 
+	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;
+
+		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;
+	} else {
 		f = fdget(fd);
-	if (!f.file)
+		if (unlikely(!f.file))
 			return -EBADF;
-
 		ret = -EOPNOTSUPP;
 		if (!io_is_uring_fops(f.file))
 			goto out_fput;
+	}
 
 	ctx = f.file->private_data;