Re: [PATCH 19/26] net/ipv6: switch ipv6_flowlabel_opt to sockptr_t

[Ido Schimmel <idosch@idosch.org>]

On Thu, Jul 23, 2020 at 08:09:01AM +0200, Christoph Hellwig wrote:
> Pass a sockptr_t to prepare for set_fs-less handling of the kernel
> pointer from bpf-cgroup.
> 
> Note that the get case is pretty weird in that it actually copies data
> back to userspace from setsockopt.
> 
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> ---
>  include/net/ipv6.h       |  2 +-
>  net/ipv6/ip6_flowlabel.c | 16 +++++++++-------
>  net/ipv6/ipv6_sockglue.c |  2 +-
>  3 files changed, 11 insertions(+), 9 deletions(-)
> 
> diff --git a/include/net/ipv6.h b/include/net/ipv6.h
> index 262fc88dbd7e2f..4c9d89b5d73268 100644
> --- a/include/net/ipv6.h
> +++ b/include/net/ipv6.h
> @@ -406,7 +406,7 @@ struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions *opt_space,
>  					 struct ip6_flowlabel *fl,
>  					 struct ipv6_txoptions *fopt);
>  void fl6_free_socklist(struct sock *sk);
> -int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen);
> +int ipv6_flowlabel_opt(struct sock *sk, sockptr_t optval, int optlen);
>  int ipv6_flowlabel_opt_get(struct sock *sk, struct in6_flowlabel_req *freq,
>  			   int flags);
>  int ip6_flowlabel_init(void);
> diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
> index 27ee6de9beffc4..6b3c315f3d461a 100644
> --- a/net/ipv6/ip6_flowlabel.c
> +++ b/net/ipv6/ip6_flowlabel.c
> @@ -371,7 +371,7 @@ static int fl6_renew(struct ip6_flowlabel *fl, unsigned long linger, unsigned lo
>  
>  static struct ip6_flowlabel *
>  fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq,
> -	  char __user *optval, int optlen, int *err_p)
> +	  sockptr_t optval, int optlen, int *err_p)
>  {
>  	struct ip6_flowlabel *fl = NULL;
>  	int olen;
> @@ -401,7 +401,8 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq,
>  		memset(fl->opt, 0, sizeof(*fl->opt));
>  		fl->opt->tot_len = sizeof(*fl->opt) + olen;
>  		err = -EFAULT;
> -		if (copy_from_user(fl->opt+1, optval+CMSG_ALIGN(sizeof(*freq)), olen))
> +		sockptr_advance(optval, CMSG_ALIGN(sizeof(*freq)));
> +		if (copy_from_sockptr(fl->opt + 1, optval, olen))
>  			goto done;
>  
>  		msg.msg_controllen = olen;
> @@ -604,7 +605,7 @@ static int ipv6_flowlabel_renew(struct sock *sk, struct in6_flowlabel_req *freq)
>  }
>  
>  static int ipv6_flowlabel_get(struct sock *sk, struct in6_flowlabel_req *freq,
> -		void __user *optval, int optlen)
> +		sockptr_t optval, int optlen)
>  {
>  	struct ipv6_fl_socklist *sfl, *sfl1 = NULL;
>  	struct ip6_flowlabel *fl, *fl1 = NULL;
> @@ -702,8 +703,9 @@ static int ipv6_flowlabel_get(struct sock *sk, struct in6_flowlabel_req *freq,
>  		goto recheck;
>  
>  	if (!freq->flr_label) {
> -		if (copy_to_user(&((struct in6_flowlabel_req __user *) optval)->flr_label,
> -				 &fl->label, sizeof(fl->label))) {
> +		sockptr_advance(optval,
> +				offsetof(struct in6_flowlabel_req, flr_label));

Christoph,

I see a regression with IPv6 flowlabel that I bisected to this patch.
When passing '-F 0' to 'ping' the flow label should be random, yet it's
the same every time after this patch.

It seems that the pointer is never advanced after the call to
sockptr_advance() because it is passed by value and not by reference.
Even if you were to pass it by reference I think you would later need to
call sockptr_decrease() or something similar. Otherwise it is very
error-prone.

Maybe adding an offset to copy_to_sockptr() and copy_from_sockptr() is
better?

Thanks

> +		if (copy_to_sockptr(optval, &fl->label, sizeof(fl->label))) {
>  			/* Intentionally ignore fault. */
>  		}
>  	}
> @@ -716,13 +718,13 @@ static int ipv6_flowlabel_get(struct sock *sk, struct in6_flowlabel_req *freq,
>  	return err;
>  }
>  
> -int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen)
> +int ipv6_flowlabel_opt(struct sock *sk, sockptr_t optval, int optlen)
>  {
>  	struct in6_flowlabel_req freq;
>  
>  	if (optlen < sizeof(freq))
>  		return -EINVAL;
> -	if (copy_from_user(&freq, optval, sizeof(freq)))
> +	if (copy_from_sockptr(&freq, optval, sizeof(freq)))
>  		return -EFAULT;
>  
>  	switch (freq.flr_action) {
> diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
> index 119dfaf5f4bb26..3897fb55372d38 100644
> --- a/net/ipv6/ipv6_sockglue.c
> +++ b/net/ipv6/ipv6_sockglue.c
> @@ -929,7 +929,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
>  		retv = 0;
>  		break;
>  	case IPV6_FLOWLABEL_MGR:
> -		retv = ipv6_flowlabel_opt(sk, optval, optlen);
> +		retv = ipv6_flowlabel_opt(sk, USER_SOCKPTR(optval), optlen);
>  		break;
>  	case IPV6_IPSEC_POLICY:
>  	case IPV6_XFRM_POLICY:
> -- 
> 2.27.0
>