From 78dcdffe0418ac8f3f057f26fe71ccf4d8ed851f Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Fri, 20 Jan 2023 18:01:39 +0100 Subject: [PATCH 1/2] net/sched: act_mirred: better wording on protection against excessive stack growth with commit e2ca070f89ec ("net: sched: protect against stack overflow in TC act_mirred"), act_mirred protected itself against excessive stack growth using per_cpu counter of nested calls to tcf_mirred_act(), and capping it to MIRRED_RECURSION_LIMIT. However, such protection does not detect recursion/loops in case the packet is enqueued to the backlog (for example, when the mirred target device has RPS or skb timestamping enabled). Change the wording from "recursion" to "nesting" to make it more clear to readers. CC: Jamal Hadi Salim Signed-off-by: Davide Caratti Reviewed-by: Marcelo Ricardo Leitner Acked-by: Jamal Hadi Salim Signed-off-by: Paolo Abeni --- net/sched/act_mirred.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 7284bcea7b0b..c8abb5136491 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -29,8 +29,8 @@ static LIST_HEAD(mirred_list); static DEFINE_SPINLOCK(mirred_list_lock); -#define MIRRED_RECURSION_LIMIT 4 -static DEFINE_PER_CPU(unsigned int, mirred_rec_level); +#define MIRRED_NEST_LIMIT 4 +static DEFINE_PER_CPU(unsigned int, mirred_nest_level); static bool tcf_mirred_is_act_redirect(int action) { @@ -226,7 +226,7 @@ TC_INDIRECT_SCOPE int tcf_mirred_act(struct sk_buff *skb, struct sk_buff *skb2 = skb; bool m_mac_header_xmit; struct net_device *dev; - unsigned int rec_level; + unsigned int nest_level; int retval, err = 0; bool use_reinsert; bool want_ingress; @@ -237,11 +237,11 @@ TC_INDIRECT_SCOPE int tcf_mirred_act(struct sk_buff *skb, int mac_len; bool at_nh; - rec_level = __this_cpu_inc_return(mirred_rec_level); - if (unlikely(rec_level > MIRRED_RECURSION_LIMIT)) { + nest_level = __this_cpu_inc_return(mirred_nest_level); + if (unlikely(nest_level > MIRRED_NEST_LIMIT)) { net_warn_ratelimited("Packet exceeded mirred recursion limit on dev %s\n", netdev_name(skb->dev)); - __this_cpu_dec(mirred_rec_level); + __this_cpu_dec(mirred_nest_level); return TC_ACT_SHOT; } @@ -310,7 +310,7 @@ TC_INDIRECT_SCOPE int tcf_mirred_act(struct sk_buff *skb, err = tcf_mirred_forward(want_ingress, skb); if (err) tcf_action_inc_overlimit_qstats(&m->common); - __this_cpu_dec(mirred_rec_level); + __this_cpu_dec(mirred_nest_level); return TC_ACT_CONSUMED; } } @@ -322,7 +322,7 @@ out: if (tcf_mirred_is_act_redirect(m_eaction)) retval = TC_ACT_SHOT; } - __this_cpu_dec(mirred_rec_level); + __this_cpu_dec(mirred_nest_level); return retval; } From ca22da2fbd693b54dc8e3b7b54ccc9f7e9ba3640 Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Fri, 20 Jan 2023 18:01:40 +0100 Subject: [PATCH 2/2] act_mirred: use the backlog for nested calls to mirred ingress William reports kernel soft-lockups on some OVS topologies when TC mirred egress->ingress action is hit by local TCP traffic [1]. The same can also be reproduced with SCTP (thanks Xin for verifying), when client and server reach themselves through mirred egress to ingress, and one of the two peers sends a "heartbeat" packet (from within a timer). Enqueueing to backlog proved to fix this soft lockup; however, as Cong noticed [2], we should preserve - when possible - the current mirred behavior that counts as "overlimits" any eventual packet drop subsequent to the mirred forwarding action [3]. A compromise solution might use the backlog only when tcf_mirred_act() has a nest level greater than one: change tcf_mirred_forward() accordingly. Also, add a kselftest that can reproduce the lockup and verifies TC mirred ability to account for further packet drops after TC mirred egress->ingress (when the nest level is 1). [1] https://lore.kernel.org/netdev/33dc43f587ec1388ba456b4915c75f02a8aae226.1663945716.git.dcaratti@redhat.com/ [2] https://lore.kernel.org/netdev/Y0w%2FWWY60gqrtGLp@pop-os.localdomain/ [3] such behavior is not guaranteed: for example, if RPS or skb RX timestamping is enabled on the mirred target device, the kernel can defer receiving the skb and return NET_RX_SUCCESS inside tcf_mirred_forward(). Reported-by: William Zhao CC: Xin Long Signed-off-by: Davide Caratti Reviewed-by: Marcelo Ricardo Leitner Acked-by: Jamal Hadi Salim Signed-off-by: Paolo Abeni --- net/sched/act_mirred.c | 7 +++ .../selftests/net/forwarding/tc_actions.sh | 49 ++++++++++++++++++- 2 files changed, 55 insertions(+), 1 deletion(-) diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index c8abb5136491..8037ec9b1d31 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -206,12 +206,19 @@ release_idr: return err; } +static bool is_mirred_nested(void) +{ + return unlikely(__this_cpu_read(mirred_nest_level) > 1); +} + static int tcf_mirred_forward(bool want_ingress, struct sk_buff *skb) { int err; if (!want_ingress) err = tcf_dev_queue_xmit(skb, dev_queue_xmit); + else if (is_mirred_nested()) + err = netif_rx(skb); else err = netif_receive_skb(skb); diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh index 1e0a62f638fe..919c0dd9fe4b 100755 --- a/tools/testing/selftests/net/forwarding/tc_actions.sh +++ b/tools/testing/selftests/net/forwarding/tc_actions.sh @@ -3,7 +3,8 @@ ALL_TESTS="gact_drop_and_ok_test mirred_egress_redirect_test \ mirred_egress_mirror_test matchall_mirred_egress_mirror_test \ - gact_trap_test mirred_egress_to_ingress_test" + gact_trap_test mirred_egress_to_ingress_test \ + mirred_egress_to_ingress_tcp_test" NUM_NETIFS=4 source tc_common.sh source lib.sh @@ -198,6 +199,52 @@ mirred_egress_to_ingress_test() log_test "mirred_egress_to_ingress ($tcflags)" } +mirred_egress_to_ingress_tcp_test() +{ + local tmpfile=$(mktemp) tmpfile1=$(mktemp) + + RET=0 + dd conv=sparse status=none if=/dev/zero bs=1M count=2 of=$tmpfile + tc filter add dev $h1 protocol ip pref 100 handle 100 egress flower \ + $tcflags ip_proto tcp src_ip 192.0.2.1 dst_ip 192.0.2.2 \ + action ct commit nat src addr 192.0.2.2 pipe \ + action ct clear pipe \ + action ct commit nat dst addr 192.0.2.1 pipe \ + action ct clear pipe \ + action skbedit ptype host pipe \ + action mirred ingress redirect dev $h1 + tc filter add dev $h1 protocol ip pref 101 handle 101 egress flower \ + $tcflags ip_proto icmp \ + action mirred ingress redirect dev $h1 + tc filter add dev $h1 protocol ip pref 102 handle 102 ingress flower \ + ip_proto icmp \ + action drop + + ip vrf exec v$h1 nc --recv-only -w10 -l -p 12345 -o $tmpfile1 & + local rpid=$! + ip vrf exec v$h1 nc -w1 --send-only 192.0.2.2 12345 <$tmpfile + wait -n $rpid + cmp -s $tmpfile $tmpfile1 + check_err $? "server output check failed" + + $MZ $h1 -c 10 -p 64 -a $h1mac -b $h1mac -A 192.0.2.1 -B 192.0.2.1 \ + -t icmp "ping,id=42,seq=5" -q + tc_check_packets "dev $h1 egress" 101 10 + check_err $? "didn't mirred redirect ICMP" + tc_check_packets "dev $h1 ingress" 102 10 + check_err $? "didn't drop mirred ICMP" + local overlimits=$(tc_rule_stats_get ${h1} 101 egress .overlimits) + test ${overlimits} = 10 + check_err $? "wrong overlimits, expected 10 got ${overlimits}" + + tc filter del dev $h1 egress protocol ip pref 100 handle 100 flower + tc filter del dev $h1 egress protocol ip pref 101 handle 101 flower + tc filter del dev $h1 ingress protocol ip pref 102 handle 102 flower + + rm -f $tmpfile $tmpfile1 + log_test "mirred_egress_to_ingress_tcp ($tcflags)" +} + setup_prepare() { h1=${NETIFS[p1]}