Ipv6 flowlabels historically require a reservation before use.
Optionally in exclusive mode (e.g., user-private).
Commit 59c820b2317f ("ipv6: elide flowlabel check if no exclusive
leases exist") introduced a fastpath that avoids this check when no
exclusive leases exist in the system, and thus any flowlabel use
will be granted.
That allows skipping the control operation to reserve a flowlabel
entirely. Though with a warning if the fast path fails:
This is an optimization. Robust applications still have to revert to
requesting leases if the fast path fails due to an exclusive lease.
Still, this is subtle. Better isolate network namespaces from each
other. Flowlabels are per-netns. Also record per-netns whether
exclusive leases are in use. Then behavior does not change based on
activity in other netns.
Changes
v2
- wrap in IS_ENABLED(CONFIG_IPV6) to avoid breakage if disabled
Fixes: 59c820b2317f ("ipv6: elide flowlabel check if no exclusive leases exist")
Link: https://lore.kernel.org/netdev/MWHPR2201MB1072BCCCFCE779E4094837ACD0329@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx/
Reported-by: Congyu Liu <liu3101@xxxxxxxxxx>
Signed-off-by: Willem de Bruijn <willemb@xxxxxxxxxx>
Tested-by: Congyu Liu <liu3101@xxxxxxxxxx>
Link: https://lore.kernel.org/r/20220215160037.1976072-1-willemdebruijn.kernel@xxxxxxxxx
Signed-off-by: Jakub Kicinski <kuba@xxxxxxxxxx>
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 3afcb128e064..92eec13d1693 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -393,17 +393,20 @@ static inline void txopt_put(struct ipv6_txoptions *opt)
kfree_rcu(opt, rcu);
}
+#if IS_ENABLED(CONFIG_IPV6)
struct ip6_flowlabel *__fl6_sock_lookup(struct sock *sk, __be32 label);
extern struct static_key_false_deferred ipv6_flowlabel_exclusive;
static inline struct ip6_flowlabel *fl6_sock_lookup(struct sock *sk,
__be32 label)
{
- if (static_branch_unlikely(&ipv6_flowlabel_exclusive.key))
+ if (static_branch_unlikely(&ipv6_flowlabel_exclusive.key) &&
+ READ_ONCE(sock_net(sk)->ipv6.flowlabel_has_excl))
return __fl6_sock_lookup(sk, label) ? : ERR_PTR(-ENOENT);
return NULL;
}
+#endif
struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions *opt_space,
struct ip6_flowlabel *fl,
diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
index a4b550380316..6bd7e5a85ce7 100644
--- a/include/net/netns/ipv6.h
+++ b/include/net/netns/ipv6.h
@@ -77,9 +77,10 @@ struct netns_ipv6 {
spinlock_t fib6_gc_lock;
unsigned int ip6_rt_gc_expire;
unsigned long ip6_rt_last_gc;
+ unsigned char flowlabel_has_excl;
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
- unsigned int fib6_rules_require_fldissect;
bool fib6_has_custom_rules;
+ unsigned int fib6_rules_require_fldissect;
#ifdef CONFIG_IPV6_SUBTREES
unsigned int fib6_routes_require_src;
#endif
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index aa673a6a7e43..ceb85c67ce39 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -450,8 +450,10 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq,
err = -EINVAL;
goto done;
}
- if (fl_shared_exclusive(fl) || fl->opt)
+ if (fl_shared_exclusive(fl) || fl->opt) {
+ WRITE_ONCE(sock_net(sk)->ipv6.flowlabel_has_excl, 1);
static_branch_deferred_inc(&ipv6_flowlabel_exclusive);
+ }
return fl;
done:
