Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Date:   Mon, 4 May 2020 12:01:11 -0700
From:   Kees Cook <keescook@chromium.org>
To:     Christoph Hellwig <hch@lst.de>
Cc:     Iurii Zaikin <yzaikin@google.com>,
        Alexei Starovoitov <ast@kernel.org>,
        Daniel Borkmann <daniel@iogearbox.net>,
        linux-kernel@vger.kernel.org, linux-mm@kvack.org,
        linux-fsdevel@vger.kernel.org, netdev@vger.kernel.org,
        bpf@vger.kernel.org, Andrey Ignatov <rdna@fb.com>
Subject: Re: [PATCH 5/5] sysctl: pass kernel pointers to ->proc_handler
Message-ID: <202005041154.CC19F03@keescook>
References: <20200424064338.538313-1-hch@lst.de>
 <20200424064338.538313-6-hch@lst.de>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20200424064338.538313-6-hch@lst.de>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Fri, Apr 24, 2020 at 08:43:38AM +0200, Christoph Hellwig wrote:
> Instead of having all the sysctl handlers deal with user pointers, which
> is rather hairy in terms of the BPF interaction, copy the input to and
> from  userspace in common code.  This also means that the strings are
> always NUL-terminated by the common code, making the API a little bit
> safer.
> 
> As most handler just pass through the data to one of the common handlers
> a lot of the changes are mechnical.

This is a lovely cleanup; thank you!

Tiny notes below...

> diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
> index b6f5d459b087d..df2143e05c571 100644
> --- a/fs/proc/proc_sysctl.c
> +++ b/fs/proc/proc_sysctl.c
> @@ -539,13 +539,13 @@ static struct dentry *proc_sys_lookup(struct inode *dir, struct dentry *dentry,
>  	return err;
>  }
>  
> -static ssize_t proc_sys_call_handler(struct file *filp, void __user *buf,
> +static ssize_t proc_sys_call_handler(struct file *filp, void __user *ubuf,
>  		size_t count, loff_t *ppos, int write)
>  {
>  	struct inode *inode = file_inode(filp);
>  	struct ctl_table_header *head = grab_header(inode);
>  	struct ctl_table *table = PROC_I(inode)->sysctl_entry;
> -	void *new_buf = NULL;
> +	void *kbuf;
>  	ssize_t error;
>  
>  	if (IS_ERR(head))
> @@ -564,27 +564,38 @@ static ssize_t proc_sys_call_handler(struct file *filp, void __user *buf,
>  	if (!table->proc_handler)
>  		goto out;
>  
> -	error = BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, buf, &count,
> -					   ppos, &new_buf);
> +	if (write) {
> +		kbuf = memdup_user_nul(ubuf, count);
> +		if (IS_ERR(kbuf)) {
> +			error = PTR_ERR(kbuf);
> +			goto out;
> +		}
> +	} else {
> +		error = -ENOMEM;
> +		kbuf = kzalloc(count, GFP_KERNEL);
> +		if (!kbuf)
> +			goto out;
> +	}
> +
> +	error = BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, &kbuf, &count,
> +					   ppos);
>  	if (error)
> -		goto out;
> +		goto out_free_buf;
>  
>  	/* careful: calling conventions are nasty here */

Is this comment still valid after doing these cleanups?

> -	if (new_buf) {
> -		mm_segment_t old_fs;
> -
> -		old_fs = get_fs();
> -		set_fs(KERNEL_DS);
> -		error = table->proc_handler(table, write, (void __user *)new_buf,
> -					    &count, ppos);
> -		set_fs(old_fs);
> -		kfree(new_buf);
> -	} else {
> -		error = table->proc_handler(table, write, buf, &count, ppos);
> +	error = table->proc_handler(table, write, kbuf, &count, ppos);
> +	if (error)
> +		goto out_free_buf;
> +
> +	if (!write) {
> +		error = -EFAULT;
> +		if (copy_to_user(ubuf, kbuf, count))
> +			goto out_free_buf;
>  	}

Something I noticed here that existed in the original code, but might be
nice to improve while we're here is to make sure that the "count"
returned from proc_handler() cannot grow _larger_, since then we might
expose heap memory beyond the end of the allocation.

I'll send a patch for this...

>  
> -	if (!error)
> -		error = count;
> +	error = count;
> +out_free_buf:
> +	kfree(kbuf);
>  out:
>  	sysctl_head_finish(head);
>  
> [...]
> diff --git a/kernel/sysctl.c b/kernel/sysctl.c
> index 511543d238794..e26fe7e8e19d7 100644
> --- a/kernel/sysctl.c
> +++ b/kernel/sysctl.c
> [...]
> @@ -682,7 +661,6 @@ static int do_proc_douintvec_w(unsigned int *tbl_data,
>  		left -= proc_skip_spaces(&p);
>  
>  out_free:
> -	kfree(kbuf);
>  	if (err)
>  		return -EINVAL;

This label name isn't accurate any more... *shrug*

-- 
Kees Cook