io_uring/zcrx: export zcrx via a file

Add an option to wrap a zcrx instance into a file and expose it to the
user space. Currently, users can't do anything meaningful with the file,
but it'll be used in a next patch to import it into another io_uring
instance. It's implemented as a new op called ZCRX_CTRL_EXPORT for the
IORING_REGISTER_ZCRX_CTRL registration opcode.

Signed-off-by: David Wei <dw@davidwei.uk>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

2 files changed, 72 insertions, 7 deletions

diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index db47fced2cc6..4bedc0310a55 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -1083,6 +1083,7 @@ struct io_uring_zcrx_ifq_reg {
 
 enum zcrx_ctrl_op {
 	ZCRX_CTRL_FLUSH_RQ,
+	ZCRX_CTRL_EXPORT,
 
 	__ZCRX_CTRL_LAST,
 };
@@ -1091,12 +1092,20 @@ struct zcrx_ctrl_flush_rq {
 	__u64		__resv[6];
 };
 
+struct zcrx_ctrl_export {
+	__u32		zcrx_fd;
+	__u32 		__resv1[11];
+};
+
 struct zcrx_ctrl {
 	__u32	zcrx_id;
 	__u32	op; /* see enum zcrx_ctrl_op */
 	__u64	__resv[2];
 
-	struct zcrx_ctrl_flush_rq	zc_flush;
+	union {
+		struct zcrx_ctrl_export		zc_export;
+		struct zcrx_ctrl_flush_rq	zc_flush;
+	};
 };
 
 #ifdef __cplusplus
diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c
index e60c5c00a611..815992aff246 100644
--- a/io_uring/zcrx.c
+++ b/io_uring/zcrx.c
@@ -8,6 +8,7 @@
 #include <linux/netdevice.h>
 #include <linux/rtnetlink.h>
 #include <linux/skbuff_ref.h>
+#include <linux/anon_inodes.h>
 
 #include <net/page_pool/helpers.h>
 #include <net/page_pool/memory_provider.h>
@@ -586,6 +587,15 @@ static void io_zcrx_scrub(struct io_zcrx_ifq *ifq)
 	}
 }
 
+static void zcrx_unregister(struct io_zcrx_ifq *ifq)
+{
+	if (refcount_dec_and_test(&ifq->user_refs)) {
+		io_close_queue(ifq);
+		io_zcrx_scrub(ifq);
+	}
+	io_put_zcrx_ifq(ifq);
+}
+
 struct io_mapped_region *io_zcrx_get_region(struct io_ring_ctx *ctx,
 					    unsigned int id)
 {
@@ -596,6 +606,55 @@ struct io_mapped_region *io_zcrx_get_region(struct io_ring_ctx *ctx,
 	return ifq ? &ifq->region : NULL;
 }
 
+static int zcrx_box_release(struct inode *inode, struct file *file)
+{
+	struct io_zcrx_ifq *ifq = file->private_data;
+
+	if (WARN_ON_ONCE(!ifq))
+		return -EFAULT;
+	zcrx_unregister(ifq);
+	return 0;
+}
+
+static const struct file_operations zcrx_box_fops = {
+	.owner		= THIS_MODULE,
+	.release	= zcrx_box_release,
+};
+
+static int zcrx_export(struct io_ring_ctx *ctx, struct io_zcrx_ifq *ifq,
+		       struct zcrx_ctrl *ctrl, void __user *arg)
+{
+	struct zcrx_ctrl_export *ce = &ctrl->zc_export;
+	struct file *file;
+	int fd = -1;
+
+	if (!mem_is_zero(ce, sizeof(*ce)))
+		return -EINVAL;
+	fd = get_unused_fd_flags(O_CLOEXEC);
+	if (fd < 0)
+		return fd;
+
+	ce->zcrx_fd = fd;
+	if (copy_to_user(arg, ctrl, sizeof(*ctrl))) {
+		put_unused_fd(fd);
+		return -EFAULT;
+	}
+
+	refcount_inc(&ifq->refs);
+	refcount_inc(&ifq->user_refs);
+
+	file = anon_inode_create_getfile("[zcrx]", &zcrx_box_fops,
+					 ifq, O_CLOEXEC, NULL);
+	if (IS_ERR(file)) {
+		put_unused_fd(fd);
+		zcrx_unregister(ifq);
+		return PTR_ERR(file);
+	}
+
+	fd_install(fd, file);
+	return 0;
+}
+
 int io_register_zcrx_ifq(struct io_ring_ctx *ctx,
 			  struct io_uring_zcrx_ifq_reg __user *arg)
 {
@@ -742,12 +801,7 @@ void io_unregister_zcrx_ifqs(struct io_ring_ctx *ctx)
 		}
 		if (!ifq)
 			break;
-
-		if (refcount_dec_and_test(&ifq->user_refs)) {
-			io_close_queue(ifq);
-			io_zcrx_scrub(ifq);
-		}
-		io_put_zcrx_ifq(ifq);
+		zcrx_unregister(ifq);
 	}
 
 	xa_destroy(&ctx->zcrx_ctxs);
@@ -1028,6 +1082,8 @@ int io_zcrx_ctrl(struct io_ring_ctx *ctx, void __user *arg, unsigned nr_args)
 	switch (ctrl.op) {
 	case ZCRX_CTRL_FLUSH_RQ:
 		return zcrx_flush_rq(ctx, zcrx, &ctrl);
+	case ZCRX_CTRL_EXPORT:
+		return zcrx_export(ctx, zcrx, &ctrl, arg);
 	}
 
 	return -EOPNOTSUPP;