Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Date:   Mon, 24 Jul 2023 18:58:04 -0400
From:   Willem de Bruijn <willemdebruijn.kernel@gmail.com>
To:     Breno Leitao <leitao@debian.org>, asml.silence@gmail.com,
        axboe@kernel.dk
Cc:     io-uring@vger.kernel.org, netdev@vger.kernel.org,
        davem@davemloft.net, kuba@kernel.org, edumazet@google.com,
        pabeni@redhat.com, linux-kernel@vger.kernel.org, leit@meta.com
Message-ID: <64bf01fc80d67_3b637629452@willemb.c.googlers.com.notmuch>
In-Reply-To: <20230724142237.358769-3-leitao@debian.org>
References: <20230724142237.358769-1-leitao@debian.org>
 <20230724142237.358769-3-leitao@debian.org>
Subject: RE: [PATCH 2/4] io_uring/cmd: Introduce SOCKET_URING_OP_GETSOCKOPT
Mime-Version: 1.0
Content-Type: text/plain;
 charset=utf-8
Content-Transfer-Encoding: 7bit
Precedence: bulk

Breno Leitao wrote:
> Add support for getsockopt command (SOCKET_URING_OP_GETSOCKOPT), where
> level is SOL_SOCKET. This is leveraging the sockptr_t infrastructure,
> where a sockptr_t is either userspace or kernel space, and handled as
> such.
> 
> Function io_uring_cmd_getsockopt() is inspired by __sys_getsockopt().
> 
> Differently from the getsockopt(2), the optlen field is not a userspace
> pointers. In getsockopt(2), userspace provides optlen pointer, which is
> overwritten by the kernel.  In this implementation, userspace passes a
> u32, and the new value is returned in cqe->res. I.e., optlen is not a
> pointer.
> 
> Important to say that userspace needs to keep the pointer alive until
> the CQE is completed.
> 
> Signed-off-by: Breno Leitao <leitao@debian.org>
> ---
>  include/uapi/linux/io_uring.h |  7 ++++++
>  io_uring/uring_cmd.c          | 43 +++++++++++++++++++++++++++++++++++
>  2 files changed, 50 insertions(+)
> 
> diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
> index 9fc7195f25df..8152151080db 100644
> --- a/include/uapi/linux/io_uring.h
> +++ b/include/uapi/linux/io_uring.h
> @@ -43,6 +43,10 @@ struct io_uring_sqe {
>  	union {
>  		__u64	addr;	/* pointer to buffer or iovecs */
>  		__u64	splice_off_in;
> +		struct {
> +			__u32	level;
> +			__u32	optname;
> +		};
>  	};
>  	__u32	len;		/* buffer size or number of iovecs */
>  	union {
> @@ -79,6 +83,7 @@ struct io_uring_sqe {
>  	union {
>  		__s32	splice_fd_in;
>  		__u32	file_index;
> +		__u32	optlen;
>  		struct {
>  			__u16	addr_len;
>  			__u16	__pad3[1];
> @@ -89,6 +94,7 @@ struct io_uring_sqe {
>  			__u64	addr3;
>  			__u64	__pad2[1];
>  		};
> +		__u64	optval;
>  		/*
>  		 * If the ring is initialized with IORING_SETUP_SQE128, then
>  		 * this field is used for 80 bytes of arbitrary command data
> @@ -729,6 +735,7 @@ struct io_uring_recvmsg_out {
>  enum {
>  	SOCKET_URING_OP_SIOCINQ		= 0,
>  	SOCKET_URING_OP_SIOCOUTQ,
> +	SOCKET_URING_OP_GETSOCKOPT,
>  };
>  
>  #ifdef __cplusplus
> diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c
> index 8e7a03c1b20e..16c857cbf3b0 100644
> --- a/io_uring/uring_cmd.c
> +++ b/io_uring/uring_cmd.c
> @@ -166,6 +166,47 @@ int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
>  }
>  EXPORT_SYMBOL_GPL(io_uring_cmd_import_fixed);
>  
> +static inline int io_uring_cmd_getsockopt(struct socket *sock,
> +					  struct io_uring_cmd *cmd)
> +{
> +	void __user *optval = u64_to_user_ptr(READ_ONCE(cmd->sqe->optval));
> +	int optname = READ_ONCE(cmd->sqe->optname);
> +	int optlen = READ_ONCE(cmd->sqe->optlen);
> +	int level = READ_ONCE(cmd->sqe->level);
> +	void *koptval;
> +	int err;
> +
> +	err = security_socket_getsockopt(sock, level, optname);
> +	if (err)
> +		return err;
> +
> +	koptval = kmalloc(optlen, GFP_KERNEL);
> +	if (!koptval)
> +		return -ENOMEM;

This will try to kmalloc any length that userspace passes?

That is unnecessary ..

> +
> +	err = copy_from_user(koptval, optval, optlen);
> +	if (err)
> +		goto fail;
> +
> +	err = -EOPNOTSUPP;
> +	if (level == SOL_SOCKET) {
> +		err = sk_getsockopt(sock->sk, level, optname,
> +				    KERNEL_SOCKPTR(koptval),
> +				    KERNEL_SOCKPTR(&optlen));

.. sk_getsockopt defines a union of acceptable fields, which
are all fairly small.

I notice that BPF added BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN to
work around the issue of pre-allocating for the worst case.

But that also needs to deal woth other getsockopt levels.


> +		if (err)
> +			goto fail;
> +	}
> +
> +	err = copy_to_user(optval, koptval, optlen);
> +
> +fail:
> +	kfree(koptval);
> +	if (err)
> +		return err;
> +	else
> +		return optlen;
> +}
> +
>  int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags)
>  {
>  	struct socket *sock = cmd->file->private_data;
> @@ -187,6 +228,8 @@ int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags)
>  		if (ret)
>  			return ret;
>  		return arg;
> +	case SOCKET_URING_OP_GETSOCKOPT:
> +		return io_uring_cmd_getsockopt(sock, cmd);
>  	default:
>  		return -EOPNOTSUPP;
>  	}
> -- 
> 2.34.1
>