io_uring: Add io_uring_setup flag to pre-register ring fd and never install it

With IORING_REGISTER_USE_REGISTERED_RING, an application can register
the ring fd and use it via registered index rather than installed fd.
This allows using a registered ring for everything *except* the initial
mmap.

With IORING_SETUP_NO_MMAP, io_uring_setup uses buffers allocated by the
user, rather than requiring a subsequent mmap.

The combination of the two allows a user to operate *entirely* via a
registered ring fd, making it unnecessary to ever install the fd in the
first place. So, add a flag IORING_SETUP_REGISTERED_FD_ONLY to make
io_uring_setup register the fd and return a registered index, without
installing the fd.

This allows an application to avoid touching the fd table at all, and
allows a library to never even momentarily install a file descriptor.

This splits out an io_ring_add_registered_file helper from
io_ring_add_registered_fd, for use by io_uring_setup.

Signed-off-by: Josh Triplett <[email protected]>
Link: https://lore.kernel.org/r/bc8f431bada371c183b95a83399628b605e978a3.1682699803.git.josh@joshtriplett.org
Signed-off-by: Jens Axboe <[email protected]>

Author: joshtriplett

include/uapi/linux/io_uring.h

@@ -178,6 +178,13 @@ enum {
  */
 #define IORING_SETUP_NO_MMAP		(1U << 14)
 
+/*
+ * Register the ring fd in itself for use with
+ * IORING_REGISTER_USE_REGISTERED_RING; return a registered fd index rather
+ * than an fd.
+ */
+#define IORING_SETUP_REGISTERED_FD_ONLY	(1U << 15)
+
 enum io_uring_op {
 	IORING_OP_NOP,
 	IORING_OP_READV,

io_uring/io_uring.c

@@ -3788,19 +3788,13 @@ static __cold int io_allocate_scq_urings(struct io_ring_ctx *ctx,
 	return 0;
 }
 
-static int io_uring_install_fd(struct io_ring_ctx *ctx, struct file *file)
+static int io_uring_install_fd(struct file *file)
 {
-	int ret, fd;
+	int fd;
 
 	fd = get_unused_fd_flags(O_RDWR | O_CLOEXEC);
 	if (fd < 0)
 		return fd;
-
-	ret = __io_uring_add_tctx_node(ctx);
-	if (ret) {
-		put_unused_fd(fd);
-		return ret;
-	}
 	fd_install(fd, file);
 	return fd;
 }
@@ -3840,6 +3834,7 @@ static __cold int io_uring_create(unsigned entries, struct io_uring_params *p,
 				  struct io_uring_params __user *params)
 {
 	struct io_ring_ctx *ctx;
+	struct io_uring_task *tctx;
 	struct file *file;
 	int ret;
 
@@ -3851,6 +3846,10 @@ static __cold int io_uring_create(unsigned entries, struct io_uring_params *p,
 		entries = IORING_MAX_ENTRIES;
 	}
 
+	if ((p->flags & IORING_SETUP_REGISTERED_FD_ONLY)
+	    && !(p->flags & IORING_SETUP_NO_MMAP))
+		return -EINVAL;
+
 	/*
 	 * Use twice as many entries for the CQ ring. It's possible for the
 	 * application to drive a higher depth than the size of the SQ ring,
@@ -4007,22 +4006,30 @@ static __cold int io_uring_create(unsigned entries, struct io_uring_params *p,
 		goto err;
 	}
 
+	ret = __io_uring_add_tctx_node(ctx);
+	if (ret)
+		goto err_fput;
+	tctx = current->io_uring;
+
 	/*
 	 * Install ring fd as the very last thing, so we don't risk someone
 	 * having closed it before we finish setup
 	 */
-	ret = io_uring_install_fd(ctx, file);
-	if (ret < 0) {
-		/* fput will clean it up */
-		fput(file);
-		return ret;
-	}
+	if (p->flags & IORING_SETUP_REGISTERED_FD_ONLY)
+		ret = io_ring_add_registered_file(tctx, file, 0, IO_RINGFD_REG_MAX);
+	else
+		ret = io_uring_install_fd(file);
+	if (ret < 0)
+		goto err_fput;
 
 	trace_io_uring_create(ret, ctx, p->sq_entries, p->cq_entries, p->flags);
 	return ret;
 err:
 	io_ring_ctx_wait_and_kill(ctx);
 	return ret;
+err_fput:
+	fput(file);
+	return ret;
 }
 
 /*
@@ -4049,7 +4056,7 @@ static long io_uring_setup(u32 entries, struct io_uring_params __user *params)
 			IORING_SETUP_COOP_TASKRUN | IORING_SETUP_TASKRUN_FLAG |
 			IORING_SETUP_SQE128 | IORING_SETUP_CQE32 |
 			IORING_SETUP_SINGLE_ISSUER | IORING_SETUP_DEFER_TASKRUN |
-			IORING_SETUP_NO_MMAP))
+			IORING_SETUP_NO_MMAP | IORING_SETUP_REGISTERED_FD_ONLY))
 		return -EINVAL;
 
 	return io_uring_create(entries, &p, params);

io_uring/io_uring.h

@@ -75,6 +75,9 @@ __cold void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd);
 int io_uring_alloc_task_context(struct task_struct *task,
 				struct io_ring_ctx *ctx);
 
+int io_ring_add_registered_file(struct io_uring_task *tctx, struct file *file,
+				     int start, int end);
+
 int io_poll_issue(struct io_kiocb *req, struct io_tw_state *ts);
 int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr);
 int io_do_iopoll(struct io_ring_ctx *ctx, bool force_nonspin);

io_uring/tctx.c

@@ -208,31 +208,40 @@ void io_uring_unreg_ringfd(void)
 	}
 }
 
-static int io_ring_add_registered_fd(struct io_uring_task *tctx, int fd,
+int io_ring_add_registered_file(struct io_uring_task *tctx, struct file *file,
 				     int start, int end)
 {
-	struct file *file;
 	int offset;
-
 	for (offset = start; offset < end; offset++) {
 		offset = array_index_nospec(offset, IO_RINGFD_REG_MAX);
 		if (tctx->registered_rings[offset])
 			continue;
 
-		file = fget(fd);
-		if (!file) {
-			return -EBADF;
-		} else if (!io_is_uring_fops(file)) {
-			fput(file);
-			return -EOPNOTSUPP;
-		}
 		tctx->registered_rings[offset] = file;
 		return offset;
 	}
-
 	return -EBUSY;
 }
 
+static int io_ring_add_registered_fd(struct io_uring_task *tctx, int fd,
+				     int start, int end)
+{
+	struct file *file;
+	int offset;
+
+	file = fget(fd);
+	if (!file) {
+		return -EBADF;
+	} else if (!io_is_uring_fops(file)) {
+		fput(file);
+		return -EOPNOTSUPP;
+	}
+	offset = io_ring_add_registered_file(tctx, file, start, end);
+	if (offset < 0)
+		fput(file);
+	return offset;
+}
+
 /*
  * Register a ring fd to avoid fdget/fdput for each io_uring_enter()
  * invocation. User passes in an array of struct io_uring_rsrc_update