Re: [PATCH net v5] ipv6: flowlabel: enforce per-netns limit for unprivileged callers

[Willem de Bruijn <willemdebruijn.kernel@gmail.com>]

Maoyi Xie wrote:
> fl_size, fl_ht and ip6_fl_lock in net/ipv6/ip6_flowlabel.c are file
> scope and shared across netns. mem_check() reads fl_size to decide
> whether to deny non-CAP_NET_ADMIN callers; capable() runs against
> init_user_ns, so an unprivileged user in any non-init userns can
> push fl_size past FL_MAX_SIZE - FL_MAX_SIZE/4 and starve every
> other unprivileged userns on the host.
> 
> Add struct netns_ipv6::flowlabel_count, bumped and decremented next
> to fl_size in fl_intern, ip6_fl_gc and ip6_fl_purge. The new field
> is placed in the existing 4-byte hole after ipmr_seq, so struct
> netns_ipv6 stays the same size on 64-bit builds.
> 
> Bump FL_MAX_SIZE from 4096 to 8192. It has been 4096 since the file
> was added; machines and connection counts have grown.
> 
> mem_check() folds an extra per-netns ceiling into the existing
> non-CAP_NET_ADMIN conditional. The ceiling is half of the total
> budget that unprivileged callers have ever been able to use, i.e.
> (FL_MAX_SIZE - FL_MAX_SIZE/4) / 2 = 3072 entries. With FL_MAX_SIZE
> doubled, this preserves the original per-user reach (~3K, what an
> unprivileged caller could already obtain before this change) while
> forcing an attacker to spread allocations across at least two
> netns to exhaust the global non-CAP_NET_ADMIN budget.
> 
> CAP_NET_ADMIN against init_user_ns still bypasses both caps.
> 
> Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
> Suggested-by: Willem de Bruijn <willemb@google.com>
> Cc: stable@vger.kernel.org # v5.15+
> Signed-off-by: Maoyi Xie <maoyi.xie@ntu.edu.sg>

No longer applies cleanly to net. Conflict on
include/net/netns/ipv6.h. Please update your tree.

> ---
> v5 (this submission, addressing v4 review by Willem):
>     - Replaced the per-netns ceiling FL_MAX_SIZE/8 with the
>       computed unpriv_user_limit = (FL_MAX_SIZE - FL_MAX_SIZE/4)/2,
>       which evaluates to 3072. v4's FL_MAX_SIZE/8 = 1024 would have
>       reduced the per-user budget below the ~3K an unprivileged
>       caller could already obtain before any of this work, defeating
>       the reason FL_MAX_SIZE was doubled in the first place. The new
>       ceiling preserves the original per-user reach while still
>       requiring an attacker to spread across at least two netns to
>       drain the global non-CAP_NET_ADMIN budget.
>     - Reworded the corresponding paragraph in the commit body.
> v4: addressed Willem's v3 review on netdev. Dropped the
>     flowlabel_has_excl cacheline argument in favour of "fills the
>     existing 4-byte hole after ipmr_seq", and reordered
>     atomic_dec(&...flowlabel_count) to sit immediately after
>     atomic_dec(&fl_size) in ip6_fl_gc and ip6_fl_purge.
> v3: addressed Willem's review on the private security@ thread.
>     Merged FL_MAX_SIZE doubling, dropped test data, moved
>     flowlabel_count near ipmr_seq, inlined fl->fl_net in ip6_fl_gc.
> v2: per-netns counter + cap, sent to security@ as a 2-patch series.
> v1: fix-shape sketch in original disclosure.
> 
>  include/net/netns/ipv6.h |  1 +
>  net/ipv6/ip6_flowlabel.c | 16 ++++++++++++----
>  2 files changed, 13 insertions(+), 4 deletions(-)
> 
> diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
> index 34bdb1308..329482373 100644
> --- a/include/net/netns/ipv6.h
> +++ b/include/net/netns/ipv6.h
> @@ -119,6 +119,7 @@ struct netns_ipv6 {
>  	struct fib_notifier_ops	*notifier_ops;
>  	struct fib_notifier_ops	*ip6mr_notifier_ops;
>  	unsigned int ipmr_seq; /* protected by rtnl_mutex */
> +	atomic_t		flowlabel_count;
>  	struct {
>  		struct hlist_head head;
>  		spinlock_t	lock;
> diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
> index c92f98c6f..758a2fc4d 100644
> --- a/net/ipv6/ip6_flowlabel.c
> +++ b/net/ipv6/ip6_flowlabel.c
> @@ -36,7 +36,7 @@
>  /* FL hash table */
>  
>  #define FL_MAX_PER_SOCK	32
> -#define FL_MAX_SIZE	4096
> +#define FL_MAX_SIZE	8192
>  #define FL_HASH_MASK	255
>  #define FL_HASH(l)	(ntohl(l)&FL_HASH_MASK)
>  
> @@ -162,8 +162,9 @@ static void ip6_fl_gc(struct timer_list *unused)
>  				ttd = fl->expires;
>  				if (time_after_eq(now, ttd)) {
>  					*flp = fl->next;
> -					fl_free(fl);
>  					atomic_dec(&fl_size);
> +					atomic_dec(&fl->fl_net->ipv6.flowlabel_count);
> +					fl_free(fl);

Do not touch fl_free (here and below)
>  					continue;
>  				}
>  				if (!sched || time_before(ttd, sched))
> @@ -195,8 +196,9 @@ static void __net_exit ip6_fl_purge(struct net *net)
>  			if (net_eq(fl->fl_net, net) &&
>  			    atomic_read(&fl->users) == 0) {
>  				*flp = fl->next;
> -				fl_free(fl);
>  				atomic_dec(&fl_size);
> +				atomic_dec(&net->ipv6.flowlabel_count);
> +				fl_free(fl);
>  				continue;
>  			}
>  			flp = &fl->next;
> @@ -245,6 +247,7 @@ static struct ip6_flowlabel *fl_intern(struct net *net,
>  	fl->next = fl_ht[FL_HASH(fl->label)];
>  	rcu_assign_pointer(fl_ht[FL_HASH(fl->label)], fl);
>  	atomic_inc(&fl_size);
> +	atomic_inc(&net->ipv6.flowlabel_count);
>  	spin_unlock_bh(&ip6_fl_lock);
>  	rcu_read_unlock();
>  	return NULL;
> @@ -464,6 +467,9 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq,
>  
>  static int mem_check(struct sock *sk)
>  {
> +	const int unpriv_total_limit = FL_MAX_SIZE - (FL_MAX_SIZE / 4);
> +	const int unpriv_user_limit = unpriv_total_limit / 2;
> +	struct net *net = sock_net(sk);
>  	int room = FL_MAX_SIZE - atomic_read(&fl_size);
>  	struct ipv6_fl_socklist *sfl;
>  	int count = 0;
> @@ -478,7 +484,9 @@ static int mem_check(struct sock *sk)
>  
>  	if (room <= 0 ||
>  	    ((count >= FL_MAX_PER_SOCK ||
> -	      (count > 0 && room < FL_MAX_SIZE/2) || room < FL_MAX_SIZE/4) &&
> +	      (count > 0 && room < FL_MAX_SIZE/2) ||
> +	      room < FL_MAX_SIZE/4 ||
> +	      atomic_read(&net->ipv6.flowlabel_count) >= unpriv_user_limit) &&
>  	     !capable(CAP_NET_ADMIN)))
>  		return -ENOBUFS;
>  
> -- 
> 2.34.1
>