Re: [PATCH v6] io_uring/register: add IORING_REGISTER_CLONE_FILES opcode

[Gabriel Krisman Bertazi <krisman@suse.de>]

Harshal Chavan <harshal24.chavan@gmail.com> writes:

> Currently, if an application wants to duplicate registered file
> descriptors from one io_uring instance to another, it must manually
> unregister and re-register them, incurring unnecessary overhead.
>
> Add IORING_REGISTER_CLONE_FILES to allow direct cloning of the file
> table from a source ring to a destination ring. This implementation
> strictly mirrors the io_clone_buffers UAPI, supporting partial offsets
> and the IORING_REGISTER_DST_REPLACE flag.
>
> To ensure lock synchronization safety, destination nodes are strictly
> allocated as new, private io_rsrc_nodes rather than sharing references
> across rings.
>
> Signed-off-by: Harshal Chavan <harshal24.chavan@gmail.com>
>
> ---
> Sorry for the noise on the previous email! I accidentally sent the patch 
> before running checkpatch and missed a whitespace error. This v6 corrects it.
>
> v6:
>   - Fixed trailing whitespace checkpatch error.
> v5:
>   - Added missing spacing in comment (Gabriel).
>   - Removed ctx->user and mm_account checks (Gabriel).
>   - Used !! for boolean conversion (Gabriel).
>   - Moved mutex_unlock unconditionally above the out label (Gabriel).
>   - liburing implementation and tests: https://github.com/axboe/liburing/pull/1606
> v4:
>   - Updated Signed-off-by to use real name and moved above the scissors line (Greg KH).
> v3:
>   - Rewrote the cloning loop to allocate private destination nodes via io_rsrc_node_alloc to fix non-atomic ref lock synchronization (Jens).
>   - Maintained partial offset/copy support to mirror io_clone_buffers UAPI (Jens).
>   - Gated the replacement free check on ctx->file_table.data.nr (Gabriel).
>   - Prevented self-cloning by checking ctx == src_ctx (Gabriel).
>   - Removed submitter_task check to allow cross-thread pooling setups (Gabriel).
> v2:
>   - Dropped unrelated whitespace formatting changes from v1

> +static int io_clone_file_node(struct io_ring_ctx *ctx,
> +			      struct io_rsrc_node *src_node,
> +			      int dst_index,
> +			      struct io_file_table *new_table)
> +{
> +	struct io_rsrc_node *dst_node;
> +	struct file *file;
> +
> +	dst_node = io_rsrc_node_alloc(ctx, IORING_RSRC_FILE);
> +	if (!dst_node)
> +		return -ENOMEM;
> +
> +	file = io_slot_file(src_node);
> +	get_file(file);
> +	io_fixed_file_set(dst_node, file);

don't you need to copy the src_node->tag here as well?

I didn't get a chance to run it yet, sorry.  I'd suggest you wait for
Jens feedback before pushing the v7 too, so you don't need to keep
iterating drop by drop :)

> +
> +	new_table->data.nodes[dst_index] = dst_node;
> +	io_file_bitmap_set(new_table, dst_index);
> +
> +	return 0;
> +}
> +
> +static int io_clone_files(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx,
> +			  struct io_uring_clone_files *arg)
> +{
> +	struct io_file_table new_file_table;
> +	unsigned int dst_nr = ctx->file_table.data.nr;
> +	unsigned int src_nr = src_ctx->file_table.data.nr;
> +	unsigned int new_nr, i;
> +
> +	lockdep_assert_held(&ctx->uring_lock);
> +	lockdep_assert_held(&src_ctx->uring_lock);
> +
> +	if (dst_nr && !(arg->flags & IORING_REGISTER_DST_REPLACE))
> +		return -EBUSY;
> +
> +	if (!src_nr)
> +		return -ENXIO;
> +
> +	if (!arg->nr)
> +		arg->nr = src_nr;
> +	else if (arg->nr > src_nr)
> +		return -EINVAL;
> +
> +	if (check_add_overflow(arg->src_off, arg->nr, &i) || i > src_nr)
> +		return -EINVAL;
> +	if (check_add_overflow(arg->dst_off, arg->nr, &i))
> +		return -EINVAL;
> +
> +	new_nr = max(dst_nr, arg->dst_off + arg->nr);
> +	if (new_nr > IORING_MAX_FIXED_FILES)
> +		return -EINVAL;
> +
> +	memset(&new_file_table, 0, sizeof(new_file_table));
> +	if (!io_alloc_file_tables(ctx, &new_file_table, new_nr))
> +		return -ENOMEM;
> +
> +	/* Copy original nodes from before the cloned range */
> +	for (i = 0; i < min(arg->dst_off, dst_nr); i++) {
> +		struct io_rsrc_node *src_node = io_rsrc_node_lookup(&ctx->file_table.data, i);
> +
> +		if (!src_node)
> +			continue;
> +		if (io_clone_file_node(ctx, src_node, i, &new_file_table))
> +			goto out;
> +	}
> +
> +	/* Copy the actual cloned range from the source ring */
> +	for (i = 0; i < arg->nr; i++) {
> +		struct io_rsrc_node *src_node = io_rsrc_node_lookup(&src_ctx->file_table.data,
> +				arg->src_off + i);
> +
> +		if (!src_node)
> +			continue;
> +		if (io_clone_file_node(ctx, src_node, arg->dst_off + i, &new_file_table))
> +			goto out;
> +	}
> +
> +	/* Copy original nodes from after the cloned range */
> +	for (i = arg->dst_off + arg->nr; i < dst_nr; i++) {
> +		struct io_rsrc_node *src_node = io_rsrc_node_lookup(&ctx->file_table.data, i);
> +
> +		if (!src_node)
> +			continue;
> +		if (io_clone_file_node(ctx, src_node, i, &new_file_table))
> +			goto out;
> +	}
> +
> +	/* free the old file table if there is any data present */
> +	if (dst_nr)
> +		io_free_file_tables(ctx, &ctx->file_table);
> +
> +	WARN_ON_ONCE(ctx->file_table.data.nr);
> +	ctx->file_table = new_file_table;
> +	io_file_table_set_alloc_range(ctx, 0, ctx->file_table.data.nr);
> +	return 0;
> +
> +out:
> +	/* Error Path: Safely destroy whatever we partially built */
> +	io_free_file_tables(ctx, &new_file_table);
> +	return -ENOMEM;
> +}
> +
> +int io_register_clone_files(struct io_ring_ctx *ctx, void __user *arg)
> +{
> +	struct io_uring_clone_files clone_arg;
> +	struct io_ring_ctx *src_ctx;
> +	bool registered_src;
> +	struct file *file;
> +	int ret;
> +
> +	if (copy_from_user(&clone_arg, arg, sizeof(clone_arg)))
> +		return -EFAULT;
> +	if (clone_arg.flags &
> +	    ~(IORING_REGISTER_SRC_REGISTERED | IORING_REGISTER_DST_REPLACE))
> +		return -EINVAL;
> +
> +	if (memchr_inv(clone_arg.pad, 0, sizeof(clone_arg.pad)))
> +		return -EINVAL;
> +
> +	registered_src = !!(clone_arg.flags & IORING_REGISTER_SRC_REGISTERED);
> +	file = io_uring_ctx_get_file(clone_arg.src_fd, registered_src);
> +	if (IS_ERR(file))
> +		return PTR_ERR(file);
> +
> +	src_ctx = file->private_data;
> +	/* Same ring clone is not allowed */
> +	if (src_ctx == ctx) {
> +		ret = -EINVAL;
> +		goto out;
> +	}
> +
> +	mutex_unlock(&ctx->uring_lock);
> +	lock_two_rings(ctx, src_ctx);
> +
> +	ret = io_clone_files(ctx, src_ctx, &clone_arg);
> +
> +	mutex_unlock(&src_ctx->uring_lock);
> +
> +out:
> +	if (!registered_src)
> +		fput(file);
> +	return ret;
> +}
> +
>  void io_vec_free(struct iou_vec *iv)
>  {
>  	if (!iv->iovec)
> diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h
> index 44e3386f7c1c..32f5c47c46af 100644
> --- a/io_uring/rsrc.h
> +++ b/io_uring/rsrc.h
> @@ -75,6 +75,7 @@ int io_prep_reg_iovec(struct io_kiocb *req, struct iou_vec *iv,
>  			const struct iovec __user *uvec, size_t uvec_segs);
>  
>  int io_register_clone_buffers(struct io_ring_ctx *ctx, void __user *arg);
> +int io_register_clone_files(struct io_ring_ctx *ctx, void __user *arg);
>  int io_sqe_buffers_unregister(struct io_ring_ctx *ctx);
>  int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg,
>  			    unsigned int nr_args, u64 __user *tags);
> -- 
> 2.54.0
>

-- 
Gabriel Krisman Bertazi