From dc489f86257cab5056e747344f17a164f63bff4b Mon Sep 17 00:00:00 2001 From: Tobias Waldekranz Date: Wed, 14 Feb 2024 22:40:03 +0100 Subject: net: bridge: switchdev: Skip MDB replays of deferred events on offload Before this change, generation of the list of MDB events to replay would race against the creation of new group memberships, either from the IGMP/MLD snooping logic or from user configuration. While new memberships are immediately visible to walkers of br->mdb_list, the notification of their existence to switchdev event subscribers is deferred until a later point in time. So if a replay list was generated during a time that overlapped with such a window, it would also contain a replay of the not-yet-delivered event. The driver would thus receive two copies of what the bridge internally considered to be one single event. On destruction of the bridge, only a single membership deletion event was therefore sent. As a consequence of this, drivers which reference count memberships (at least DSA), would be left with orphan groups in their hardware database when the bridge was destroyed. This is only an issue when replaying additions. While deletion events may still be pending on the deferred queue, they will already have been removed from br->mdb_list, so no duplicates can be generated in that scenario. To a user this meant that old group memberships, from a bridge in which a port was previously attached, could be reanimated (in hardware) when the port joined a new bridge, without the new bridge's knowledge. For example, on an mv88e6xxx system, create a snooping bridge and immediately add a port to it: root@infix-06-0b-00:~$ ip link add dev br0 up type bridge mcast_snooping 1 && \ > ip link set dev x3 up master br0 And then destroy the bridge: root@infix-06-0b-00:~$ ip link del dev br0 root@infix-06-0b-00:~$ mvls atu ADDRESS FID STATE Q F 0 1 2 3 4 5 6 7 8 9 a DEV:0 Marvell 88E6393X 33:33:00:00:00:6a 1 static - - 0 . . . . . . . . . . 33:33:ff:87:e4:3f 1 static - - 0 . . . . . . . . . . ff:ff:ff:ff:ff:ff 1 static - - 0 1 2 3 4 5 6 7 8 9 a root@infix-06-0b-00:~$ The two IPv6 groups remain in the hardware database because the port (x3) is notified of the host's membership twice: once via the original event and once via a replay. Since only a single delete notification is sent, the count remains at 1 when the bridge is destroyed. Then add the same port (or another port belonging to the same hardware domain) to a new bridge, this time with snooping disabled: root@infix-06-0b-00:~$ ip link add dev br1 up type bridge mcast_snooping 0 && \ > ip link set dev x3 up master br1 All multicast, including the two IPv6 groups from br0, should now be flooded, according to the policy of br1. But instead the old memberships are still active in the hardware database, causing the switch to only forward traffic to those groups towards the CPU (port 0). Eliminate the race in two steps: 1. Grab the write-side lock of the MDB while generating the replay list. This prevents new memberships from showing up while we are generating the replay list. But it leaves the scenario in which a deferred event was already generated, but not delivered, before we grabbed the lock. Therefore: 2. Make sure that no deferred version of a replay event is already enqueued to the switchdev deferred queue, before adding it to the replay list, when replaying additions. Fixes: 4f2673b3a2b6 ("net: bridge: add helper to replay port and host-joined mdb entries") Signed-off-by: Tobias Waldekranz Reviewed-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/net/switchdev.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index a43062d4c734..8346b0d29542 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -308,6 +308,9 @@ void switchdev_deferred_process(void); int switchdev_port_attr_set(struct net_device *dev, const struct switchdev_attr *attr, struct netlink_ext_ack *extack); +bool switchdev_port_obj_act_is_deferred(struct net_device *dev, + enum switchdev_notifier_type nt, + const struct switchdev_obj *obj); int switchdev_port_obj_add(struct net_device *dev, const struct switchdev_obj *obj, struct netlink_ext_ack *extack); -- cgit v1.2.3 From b8adb69a7d29c2d33eb327bca66476fb6066516b Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 15 Feb 2024 19:25:30 +0100 Subject: mptcp: fix lockless access in subflow ULP diag Since the introduction of the subflow ULP diag interface, the dump callback accessed all the subflow data with lockless. We need either to annotate all the read and write operation accordingly, or acquire the subflow socket lock. Let's do latter, even if slower, to avoid a diffstat havoc. Fixes: 5147dfb50832 ("mptcp: allow dumping subflow context to userspace") Cc: stable@vger.kernel.org Signed-off-by: Paolo Abeni Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Signed-off-by: David S. Miller --- include/net/tcp.h | 2 +- net/mptcp/diag.c | 6 +++++- net/tls/tls_main.c | 2 +- 3 files changed, 7 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index dd78a1181031..f6eba9652d01 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2506,7 +2506,7 @@ struct tcp_ulp_ops { /* cleanup ulp */ void (*release)(struct sock *sk); /* diagnostic */ - int (*get_info)(const struct sock *sk, struct sk_buff *skb); + int (*get_info)(struct sock *sk, struct sk_buff *skb); size_t (*get_info_size)(const struct sock *sk); /* clone ulp */ void (*clone)(const struct request_sock *req, struct sock *newsk, diff --git a/net/mptcp/diag.c b/net/mptcp/diag.c index a536586742f2..e57c5f47f035 100644 --- a/net/mptcp/diag.c +++ b/net/mptcp/diag.c @@ -13,17 +13,19 @@ #include #include "protocol.h" -static int subflow_get_info(const struct sock *sk, struct sk_buff *skb) +static int subflow_get_info(struct sock *sk, struct sk_buff *skb) { struct mptcp_subflow_context *sf; struct nlattr *start; u32 flags = 0; + bool slow; int err; start = nla_nest_start_noflag(skb, INET_ULP_INFO_MPTCP); if (!start) return -EMSGSIZE; + slow = lock_sock_fast(sk); rcu_read_lock(); sf = rcu_dereference(inet_csk(sk)->icsk_ulp_data); if (!sf) { @@ -69,11 +71,13 @@ static int subflow_get_info(const struct sock *sk, struct sk_buff *skb) } rcu_read_unlock(); + unlock_sock_fast(sk, slow); nla_nest_end(skb, start); return 0; nla_failure: rcu_read_unlock(); + unlock_sock_fast(sk, slow); nla_nest_cancel(skb, start); return err; } diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 1c2c6800949d..b4674f03d71a 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -1003,7 +1003,7 @@ static u16 tls_user_config(struct tls_context *ctx, bool tx) return 0; } -static int tls_get_info(const struct sock *sk, struct sk_buff *skb) +static int tls_get_info(struct sock *sk, struct sk_buff *skb) { u16 version, cipher_type; struct tls_context *ctx; -- cgit v1.2.3 From 9e0f0430389be7696396c62f037be4bf72cf93e3 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 21 Feb 2024 12:32:58 +0100 Subject: netfilter: nft_flow_offload: reset dst in route object after setting up flow dst is transferred to the flow object, route object does not own it anymore. Reset dst in route object, otherwise if flow_offload_add() fails, error path releases dst twice, leading to a refcount underflow. Fixes: a3c90f7a2323 ("netfilter: nf_tables: flow offload expression") Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_flow_table.h | 2 +- net/netfilter/nf_flow_table_core.c | 16 +++++++++++++--- 2 files changed, 14 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index 956c752ceb31..a763dd327c6e 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -276,7 +276,7 @@ nf_flow_table_offload_del_cb(struct nf_flowtable *flow_table, } void flow_offload_route_init(struct flow_offload *flow, - const struct nf_flow_route *route); + struct nf_flow_route *route); int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow); void flow_offload_refresh(struct nf_flowtable *flow_table, diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 920a5a29ae1d..7502d6d73a60 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -87,12 +87,22 @@ static u32 flow_offload_dst_cookie(struct flow_offload_tuple *flow_tuple) return 0; } +static struct dst_entry *nft_route_dst_fetch(struct nf_flow_route *route, + enum flow_offload_tuple_dir dir) +{ + struct dst_entry *dst = route->tuple[dir].dst; + + route->tuple[dir].dst = NULL; + + return dst; +} + static int flow_offload_fill_route(struct flow_offload *flow, - const struct nf_flow_route *route, + struct nf_flow_route *route, enum flow_offload_tuple_dir dir) { struct flow_offload_tuple *flow_tuple = &flow->tuplehash[dir].tuple; - struct dst_entry *dst = route->tuple[dir].dst; + struct dst_entry *dst = nft_route_dst_fetch(route, dir); int i, j = 0; switch (flow_tuple->l3proto) { @@ -146,7 +156,7 @@ static void nft_flow_dst_release(struct flow_offload *flow, } void flow_offload_route_init(struct flow_offload *flow, - const struct nf_flow_route *route) + struct nf_flow_route *route) { flow_offload_fill_route(flow, route, FLOW_OFFLOAD_DIR_ORIGINAL); flow_offload_fill_route(flow, route, FLOW_OFFLOAD_DIR_REPLY); -- cgit v1.2.3