io_uring: add support for passing fixed file descriptors

With IORING_OP_MSG_RING, one ring can send a message to another ring.
Extend that support to also allow sending a fixed file descriptor to
that ring, enabling one ring to pass a registered descriptor to another
one.

Arguments are extended to pass in:

sqe->addr3	fixed file slot in source ring
sqe->file_index	fixed file slot in destination ring

IORING_OP_MSG_RING is extended to take a command argument in sqe->addr.
If set to zero (or IORING_MSG_DATA), it sends just a message like before.
If set to IORING_MSG_SEND_FD, a fixed file descriptor is sent according
to the above arguments.

Two common use cases for this are:

1) Server needs to be shutdown or restarted, pass file descriptors to
   another onei

2) Backend is split, and one accepts connections, while others then get
  the fd passed and handle the actual connection.

Both of those are classic SCM_RIGHTS use cases, and it's not possible to
support them with direct descriptors today.

By default, this will post a CQE to the target ring, similarly to how
IORING_MSG_DATA does it. If IORING_MSG_RING_CQE_SKIP is set, no message
is posted to the target ring. The issuer is expected to notify the
receiver side separately.

Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 123 insertions, 7 deletions

diff --git a/io_uring/msg_ring.c b/io_uring/msg_ring.c
index b02be2349652..939205b30c8b 100644
--- a/io_uring/msg_ring.c
+++ b/io_uring/msg_ring.c
@@ -3,46 +3,162 @@
 #include <linux/errno.h>
 #include <linux/file.h>
 #include <linux/slab.h>
+#include <linux/nospec.h>
 #include <linux/io_uring.h>
 
 #include <uapi/linux/io_uring.h>
 
 #include "io_uring.h"
+#include "rsrc.h"
+#include "filetable.h"
 #include "msg_ring.h"
 
 struct io_msg {
 	struct file			*file;
 	u64 user_data;
 	u32 len;
+	u32 cmd;
+	u32 src_fd;
+	u32 dst_fd;
+	u32 flags;
 };
 
+static int io_msg_ring_data(struct io_kiocb *req)
+{
+	struct io_ring_ctx *target_ctx = req->file->private_data;
+	struct io_msg *msg = io_kiocb_to_cmd(req);
+
+	if (msg->src_fd || msg->dst_fd || msg->flags)
+		return -EINVAL;
+
+	if (io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0))
+		return 0;
+
+	return -EOVERFLOW;
+}
+
+static void io_double_unlock_ctx(struct io_ring_ctx *ctx,
+				 struct io_ring_ctx *octx,
+				 unsigned int issue_flags)
+{
+	if (issue_flags & IO_URING_F_UNLOCKED)
+		mutex_unlock(&ctx->uring_lock);
+	mutex_unlock(&octx->uring_lock);
+}
+
+static int io_double_lock_ctx(struct io_ring_ctx *ctx,
+			      struct io_ring_ctx *octx,
+			      unsigned int issue_flags)
+{
+	/*
+	 * To ensure proper ordering between the two ctxs, we can only
+	 * attempt a trylock on the target. If that fails and we already have
+	 * the source ctx lock, punt to io-wq.
+	 */
+	if (!(issue_flags & IO_URING_F_UNLOCKED)) {
+		if (!mutex_trylock(&octx->uring_lock))
+			return -EAGAIN;
+		return 0;
+	}
+
+	/* Always grab smallest value ctx first. We know ctx != octx. */
+	if (ctx < octx) {
+		mutex_lock(&ctx->uring_lock);
+		mutex_lock(&octx->uring_lock);
+	} else {
+		mutex_lock(&octx->uring_lock);
+		mutex_lock(&ctx->uring_lock);
+	}
+
+	return 0;
+}
+
+static int io_msg_send_fd(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_ring_ctx *target_ctx = req->file->private_data;
+	struct io_msg *msg = io_kiocb_to_cmd(req);
+	struct io_ring_ctx *ctx = req->ctx;
+	unsigned long file_ptr;
+	struct file *src_file;
+	int ret;
+
+	if (target_ctx == ctx)
+		return -EINVAL;
+
+	ret = io_double_lock_ctx(ctx, target_ctx, issue_flags);
+	if (unlikely(ret))
+		return ret;
+
+	ret = -EBADF;
+	if (unlikely(msg->src_fd >= ctx->nr_user_files))
+		goto out_unlock;
+
+	msg->src_fd = array_index_nospec(msg->src_fd, ctx->nr_user_files);
+	file_ptr = io_fixed_file_slot(&ctx->file_table, msg->src_fd)->file_ptr;
+	src_file = (struct file *) (file_ptr & FFS_MASK);
+	get_file(src_file);
+
+	ret = __io_fixed_fd_install(target_ctx, src_file, msg->dst_fd);
+	if (ret < 0) {
+		fput(src_file);
+		goto out_unlock;
+	}
+
+	if (msg->flags & IORING_MSG_RING_CQE_SKIP)
+		goto out_unlock;
+
+	/*
+	 * If this fails, the target still received the file descriptor but
+	 * wasn't notified of the fact. This means that if this request
+	 * completes with -EOVERFLOW, then the sender must ensure that a
+	 * later IORING_OP_MSG_RING delivers the message.
+	 */
+	if (!io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0))
+		ret = -EOVERFLOW;
+out_unlock:
+	io_double_unlock_ctx(ctx, target_ctx, issue_flags);
+	return ret;
+}
+
 int io_msg_ring_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	struct io_msg *msg = io_kiocb_to_cmd(req);
 
-	if (unlikely(sqe->addr || sqe->rw_flags || sqe->splice_fd_in ||
-		     sqe->buf_index || sqe->personality))
+	if (unlikely(sqe->buf_index || sqe->personality))
 		return -EINVAL;
 
 	msg->user_data = READ_ONCE(sqe->off);
 	msg->len = READ_ONCE(sqe->len);
+	msg->cmd = READ_ONCE(sqe->addr);
+	msg->src_fd = READ_ONCE(sqe->addr3);
+	msg->dst_fd = READ_ONCE(sqe->file_index);
+	msg->flags = READ_ONCE(sqe->msg_ring_flags);
+	if (msg->flags & ~IORING_MSG_RING_CQE_SKIP)
+		return -EINVAL;
+
 	return 0;
 }
 
 int io_msg_ring(struct io_kiocb *req, unsigned int issue_flags)
 {
 	struct io_msg *msg = io_kiocb_to_cmd(req);
-	struct io_ring_ctx *target_ctx;
 	int ret;
 
 	ret = -EBADFD;
 	if (!io_is_uring_fops(req->file))
 		goto done;
 
-	ret = -EOVERFLOW;
-	target_ctx = req->file->private_data;
-	if (io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0))
-		ret = 0;
+	switch (msg->cmd) {
+	case IORING_MSG_DATA:
+		ret = io_msg_ring_data(req);
+		break;
+	case IORING_MSG_SEND_FD:
+		ret = io_msg_send_fd(req, issue_flags);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
 
 done:
 	if (ret < 0)