From: msizanoen1 msizanoen@qtmlabs.xyz
commit cdef485217d30382f3bf6448c54b4401648fe3f1 upstream.
The kernel leaks memory when a `fib` rule is present in IPv6 nftables firewall rules and a suppress_prefix rule is present in the IPv6 routing rules (used by certain tools such as wg-quick). In such scenarios, every incoming packet will leak an allocation in `ip6_dst_cache` slab cache.
After some hours of `bpftrace`-ing and source code reading, I tracked down the issue to ca7a03c41753 ("ipv6: do not free rt if FIB_LOOKUP_NOREF is set on suppress rule").
The problem with that change is that the generic `args->flags` always have `FIB_LOOKUP_NOREF` set[1][2] but the IPv6-specific flag `RT6_LOOKUP_F_DST_NOREF` might not be, leading to `fib6_rule_suppress` not decreasing the refcount when needed.
How to reproduce: - Add the following nftables rule to a prerouting chain: meta nfproto ipv6 fib saddr . mark . iif oif missing drop This can be done with: sudo nft create table inet test sudo nft create chain inet test test_chain '{ type filter hook prerouting priority filter + 10; policy accept; }' sudo nft add rule inet test test_chain meta nfproto ipv6 fib saddr . mark . iif oif missing drop - Run: sudo ip -6 rule add table main suppress_prefixlength 0 - Watch `sudo slabtop -o | grep ip6_dst_cache` to see memory usage increase with every incoming ipv6 packet.
This patch exposes the protocol-specific flags to the protocol specific `suppress` function, and check the protocol-specific `flags` argument for RT6_LOOKUP_F_DST_NOREF instead of the generic FIB_LOOKUP_NOREF when decreasing the refcount, like this.
[1]: https://github.com/torvalds/linux/blob/ca7a03c4175366a92cee0ccc4fec0038c3266... [2]: https://github.com/torvalds/linux/blob/ca7a03c4175366a92cee0ccc4fec0038c3266...
Link: https://bugzilla.kernel.org/show_bug.cgi?id=215105 Fixes: ca7a03c41753 ("ipv6: do not free rt if FIB_LOOKUP_NOREF is set on suppress rule") Cc: stable@vger.kernel.org Signed-off-by: Jason A. Donenfeld Jason@zx2c4.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org
--- include/net/fib_rules.h | 2 +- net/core/fib_rules.c | 2 +- net/ipv4/fib_rules.c | 2 +- net/ipv6/fib6_rules.c | 5 ++--- 4 files changed, 5 insertions(+), 6 deletions(-)
--- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -68,7 +68,7 @@ struct fib_rules_ops { int (*action)(struct fib_rule *, struct flowi *, int, struct fib_lookup_arg *); - bool (*suppress)(struct fib_rule *, + bool (*suppress)(struct fib_rule *, int, struct fib_lookup_arg *); int (*match)(struct fib_rule *, struct flowi *, int); --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -300,7 +300,7 @@ jumped: else err = ops->action(rule, fl, flags, arg);
- if (!err && ops->suppress && ops->suppress(rule, arg)) + if (!err && ops->suppress && ops->suppress(rule, flags, arg)) continue;
if (err != -EAGAIN) { --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -137,7 +137,7 @@ static int fib4_rule_action(struct fib_r return err; }
-static bool fib4_rule_suppress(struct fib_rule *rule, struct fib_lookup_arg *arg) +static bool fib4_rule_suppress(struct fib_rule *rule, int flags, struct fib_lookup_arg *arg) { struct fib_result *result = (struct fib_result *) arg->result; struct net_device *dev = NULL; --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -260,7 +260,7 @@ static int fib6_rule_action(struct fib_r return __fib6_rule_action(rule, flp, flags, arg); }
-static bool fib6_rule_suppress(struct fib_rule *rule, struct fib_lookup_arg *arg) +static bool fib6_rule_suppress(struct fib_rule *rule, int flags, struct fib_lookup_arg *arg) { struct fib6_result *res = arg->result; struct rt6_info *rt = res->rt6; @@ -287,8 +287,7 @@ static bool fib6_rule_suppress(struct fi return false;
suppress_route: - if (!(arg->flags & FIB_LOOKUP_NOREF)) - ip6_rt_put(rt); + ip6_rt_put_flags(rt, flags); return true; }