From cc7f5022f810cf7bf4f1826dd620656c35942a13 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 15 Mar 2023 15:11:47 +0200 Subject: rtnetlink: bridge: mcast: Move MDB handlers out of bridge driver Currently, the bridge driver registers handlers for MDB netlink messages, making it impossible for other drivers to implement MDB support. As a preparation for VXLAN MDB support, move the MDB handlers out of the bridge driver to the core rtnetlink code. The rtnetlink code will call into individual drivers by invoking their previously added MDB net device operations. Note that while the diffstat is large, the change is mechanical. It moves code out of the bridge driver to rtnetlink code. Also note that a similar change was made in 2012 with commit 77162022ab26 ("net: add generic PF_BRIDGE:RTM_ FDB hooks") that moved FDB handlers out of the bridge driver to the core rtnetlink code. Signed-off-by: Ido Schimmel Reviewed-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 217 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 217 insertions(+) (limited to 'net/core/rtnetlink.c') diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 5d8eb57867a9..f347d9fa78c7 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -54,6 +54,9 @@ #include #include #include +#if IS_ENABLED(CONFIG_IPV6) +#include +#endif #include "dev.h" @@ -6063,6 +6066,216 @@ static int rtnl_stats_set(struct sk_buff *skb, struct nlmsghdr *nlh, return 0; } +static int rtnl_mdb_valid_dump_req(const struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + struct br_port_msg *bpm; + + if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*bpm))) { + NL_SET_ERR_MSG(extack, "Invalid header for mdb dump request"); + return -EINVAL; + } + + bpm = nlmsg_data(nlh); + if (bpm->ifindex) { + NL_SET_ERR_MSG(extack, "Filtering by device index is not supported for mdb dump request"); + return -EINVAL; + } + if (nlmsg_attrlen(nlh, sizeof(*bpm))) { + NL_SET_ERR_MSG(extack, "Invalid data after header in mdb dump request"); + return -EINVAL; + } + + return 0; +} + +struct rtnl_mdb_dump_ctx { + long idx; +}; + +static int rtnl_mdb_dump(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct rtnl_mdb_dump_ctx *ctx = (void *)cb->ctx; + struct net *net = sock_net(skb->sk); + struct net_device *dev; + int idx, s_idx; + int err; + + NL_ASSERT_DUMP_CTX_FITS(struct rtnl_mdb_dump_ctx); + + if (cb->strict_check) { + err = rtnl_mdb_valid_dump_req(cb->nlh, cb->extack); + if (err) + return err; + } + + s_idx = ctx->idx; + idx = 0; + + for_each_netdev(net, dev) { + if (idx < s_idx) + goto skip; + if (!dev->netdev_ops->ndo_mdb_dump) + goto skip; + + err = dev->netdev_ops->ndo_mdb_dump(dev, skb, cb); + if (err == -EMSGSIZE) + goto out; + /* Moving on to next device, reset markers and sequence + * counters since they are all maintained per-device. + */ + memset(cb->ctx, 0, sizeof(cb->ctx)); + cb->prev_seq = 0; + cb->seq = 0; +skip: + idx++; + } + +out: + ctx->idx = idx; + return skb->len; +} + +static int rtnl_validate_mdb_entry(const struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + struct br_mdb_entry *entry = nla_data(attr); + + if (nla_len(attr) != sizeof(struct br_mdb_entry)) { + NL_SET_ERR_MSG_ATTR(extack, attr, "Invalid attribute length"); + return -EINVAL; + } + + if (entry->ifindex == 0) { + NL_SET_ERR_MSG(extack, "Zero entry ifindex is not allowed"); + return -EINVAL; + } + + if (entry->addr.proto == htons(ETH_P_IP)) { + if (!ipv4_is_multicast(entry->addr.u.ip4)) { + NL_SET_ERR_MSG(extack, "IPv4 entry group address is not multicast"); + return -EINVAL; + } + if (ipv4_is_local_multicast(entry->addr.u.ip4)) { + NL_SET_ERR_MSG(extack, "IPv4 entry group address is local multicast"); + return -EINVAL; + } +#if IS_ENABLED(CONFIG_IPV6) + } else if (entry->addr.proto == htons(ETH_P_IPV6)) { + if (ipv6_addr_is_ll_all_nodes(&entry->addr.u.ip6)) { + NL_SET_ERR_MSG(extack, "IPv6 entry group address is link-local all nodes"); + return -EINVAL; + } +#endif + } else if (entry->addr.proto == 0) { + /* L2 mdb */ + if (!is_multicast_ether_addr(entry->addr.u.mac_addr)) { + NL_SET_ERR_MSG(extack, "L2 entry group is not multicast"); + return -EINVAL; + } + } else { + NL_SET_ERR_MSG(extack, "Unknown entry protocol"); + return -EINVAL; + } + + if (entry->state != MDB_PERMANENT && entry->state != MDB_TEMPORARY) { + NL_SET_ERR_MSG(extack, "Unknown entry state"); + return -EINVAL; + } + if (entry->vid >= VLAN_VID_MASK) { + NL_SET_ERR_MSG(extack, "Invalid entry VLAN id"); + return -EINVAL; + } + + return 0; +} + +static const struct nla_policy mdba_policy[MDBA_SET_ENTRY_MAX + 1] = { + [MDBA_SET_ENTRY_UNSPEC] = { .strict_start_type = MDBA_SET_ENTRY_ATTRS + 1 }, + [MDBA_SET_ENTRY] = NLA_POLICY_VALIDATE_FN(NLA_BINARY, + rtnl_validate_mdb_entry, + sizeof(struct br_mdb_entry)), + [MDBA_SET_ENTRY_ATTRS] = { .type = NLA_NESTED }, +}; + +static int rtnl_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[MDBA_SET_ENTRY_MAX + 1]; + struct net *net = sock_net(skb->sk); + struct br_port_msg *bpm; + struct net_device *dev; + int err; + + err = nlmsg_parse_deprecated(nlh, sizeof(*bpm), tb, + MDBA_SET_ENTRY_MAX, mdba_policy, extack); + if (err) + return err; + + bpm = nlmsg_data(nlh); + if (!bpm->ifindex) { + NL_SET_ERR_MSG(extack, "Invalid ifindex"); + return -EINVAL; + } + + dev = __dev_get_by_index(net, bpm->ifindex); + if (!dev) { + NL_SET_ERR_MSG(extack, "Device doesn't exist"); + return -ENODEV; + } + + if (NL_REQ_ATTR_CHECK(extack, NULL, tb, MDBA_SET_ENTRY)) { + NL_SET_ERR_MSG(extack, "Missing MDBA_SET_ENTRY attribute"); + return -EINVAL; + } + + if (!dev->netdev_ops->ndo_mdb_add) { + NL_SET_ERR_MSG(extack, "Device does not support MDB operations"); + return -EOPNOTSUPP; + } + + return dev->netdev_ops->ndo_mdb_add(dev, tb, nlh->nlmsg_flags, extack); +} + +static int rtnl_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[MDBA_SET_ENTRY_MAX + 1]; + struct net *net = sock_net(skb->sk); + struct br_port_msg *bpm; + struct net_device *dev; + int err; + + err = nlmsg_parse_deprecated(nlh, sizeof(*bpm), tb, + MDBA_SET_ENTRY_MAX, mdba_policy, extack); + if (err) + return err; + + bpm = nlmsg_data(nlh); + if (!bpm->ifindex) { + NL_SET_ERR_MSG(extack, "Invalid ifindex"); + return -EINVAL; + } + + dev = __dev_get_by_index(net, bpm->ifindex); + if (!dev) { + NL_SET_ERR_MSG(extack, "Device doesn't exist"); + return -ENODEV; + } + + if (NL_REQ_ATTR_CHECK(extack, NULL, tb, MDBA_SET_ENTRY)) { + NL_SET_ERR_MSG(extack, "Missing MDBA_SET_ENTRY attribute"); + return -EINVAL; + } + + if (!dev->netdev_ops->ndo_mdb_del) { + NL_SET_ERR_MSG(extack, "Device does not support MDB operations"); + return -EOPNOTSUPP; + } + + return dev->netdev_ops->ndo_mdb_del(dev, tb, extack); +} + /* Process one rtnetlink message. */ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, @@ -6297,4 +6510,8 @@ void __init rtnetlink_init(void) rtnl_register(PF_UNSPEC, RTM_GETSTATS, rtnl_stats_get, rtnl_stats_dump, 0); rtnl_register(PF_UNSPEC, RTM_SETSTATS, rtnl_stats_set, NULL, 0); + + rtnl_register(PF_BRIDGE, RTM_GETMDB, NULL, rtnl_mdb_dump, 0); + rtnl_register(PF_BRIDGE, RTM_NEWMDB, rtnl_mdb_add, NULL, 0); + rtnl_register(PF_BRIDGE, RTM_DELMDB, rtnl_mdb_del, NULL, 0); } -- cgit v1.2.3 From da654c80a0ebba2e2a0614e017c9bbe57f643fe2 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 15 Mar 2023 15:11:48 +0200 Subject: rtnetlink: bridge: mcast: Relax group address validation in common code In the upcoming VXLAN MDB implementation, the 0.0.0.0 and :: MDB entries will act as catchall entries for unregistered IP multicast traffic in a similar fashion to the 00:00:00:00:00:00 VXLAN FDB entry that is used to transmit BUM traffic. In deployments where inter-subnet multicast forwarding is used, not all the VTEPs in a tenant domain are members in all the broadcast domains. It is therefore advantageous to transmit BULL (broadcast, unknown unicast and link-local multicast) and unregistered IP multicast traffic on different tunnels. If the same tunnel was used, a VTEP only interested in IP multicast traffic would also pull all the BULL traffic and drop it as it is not a member in the originating broadcast domain [1]. Prepare for this change by allowing the 0.0.0.0 group address in the common rtnetlink MDB code and forbid it in the bridge driver. A similar change is not needed for IPv6 because the common code only validates that the group address is not the all-nodes address. [1] https://datatracker.ietf.org/doc/html/draft-ietf-bess-evpn-irb-mcast#section-2.6 Signed-off-by: Ido Schimmel Reviewed-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- net/bridge/br_mdb.c | 6 ++++++ net/core/rtnetlink.c | 5 +++-- 2 files changed, 9 insertions(+), 2 deletions(-) (limited to 'net/core/rtnetlink.c') diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index 76636c61db21..7305f5f8215c 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -1246,6 +1246,12 @@ static int br_mdb_config_init(struct br_mdb_config *cfg, struct net_device *dev, } } + if (cfg->entry->addr.proto == htons(ETH_P_IP) && + ipv4_is_zeronet(cfg->entry->addr.u.ip4)) { + NL_SET_ERR_MSG_MOD(extack, "IPv4 entry group address 0.0.0.0 is not allowed"); + return -EINVAL; + } + if (tb[MDBA_SET_ENTRY_ATTRS]) return br_mdb_config_attrs_init(tb[MDBA_SET_ENTRY_ATTRS], cfg, extack); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index f347d9fa78c7..b7b1661d0d56 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -6152,8 +6152,9 @@ static int rtnl_validate_mdb_entry(const struct nlattr *attr, } if (entry->addr.proto == htons(ETH_P_IP)) { - if (!ipv4_is_multicast(entry->addr.u.ip4)) { - NL_SET_ERR_MSG(extack, "IPv4 entry group address is not multicast"); + if (!ipv4_is_multicast(entry->addr.u.ip4) && + !ipv4_is_zeronet(entry->addr.u.ip4)) { + NL_SET_ERR_MSG(extack, "IPv4 entry group address is not multicast or 0.0.0.0"); return -EINVAL; } if (ipv4_is_local_multicast(entry->addr.u.ip4)) { -- cgit v1.2.3 From bc9d3a9f2afca189a6ae40225b6985e3c775375e Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 23 Mar 2023 21:55:32 +0100 Subject: net: dst: Switch to rcuref_t reference counting Under high contention dst_entry::__refcnt becomes a significant bottleneck. atomic_inc_not_zero() is implemented with a cmpxchg() loop, which goes into high retry rates on contention. Switch the reference count to rcuref_t which results in a significant performance gain. Rename the reference count member to __rcuref to reflect the change. The gain depends on the micro-architecture and the number of concurrent operations and has been measured in the range of +25% to +130% with a localhost memtier/memcached benchmark which amplifies the problem massively. Running the memtier/memcached benchmark over a real (1Gb) network connection the conversion on top of the false sharing fix for struct dst_entry::__refcnt results in a total gain in the 2%-5% range over the upstream baseline. Reported-by: Wangyang Guo Reported-by: Arjan Van De Ven Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20230307125538.989175656@linutronix.de Link: https://lore.kernel.org/r/20230323102800.215027837@linutronix.de Signed-off-by: Jakub Kicinski --- include/net/dst.h | 19 ++++++++++--------- include/net/sock.h | 2 +- net/bridge/br_nf_core.c | 2 +- net/core/dst.c | 26 +++++--------------------- net/core/rtnetlink.c | 2 +- net/ipv6/route.c | 6 +++--- net/netfilter/ipvs/ip_vs_xmit.c | 4 ++-- 7 files changed, 23 insertions(+), 38 deletions(-) (limited to 'net/core/rtnetlink.c') diff --git a/include/net/dst.h b/include/net/dst.h index 81f2279ea911..78884429deed 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include @@ -61,11 +62,11 @@ struct dst_entry { unsigned short trailer_len; /* space to reserve at tail */ /* - * __refcnt wants to be on a different cache line from + * __rcuref wants to be on a different cache line from * input/output/ops or performance tanks badly */ #ifdef CONFIG_64BIT - atomic_t __refcnt; /* 64-bit offset 64 */ + rcuref_t __rcuref; /* 64-bit offset 64 */ #endif int __use; unsigned long lastuse; @@ -75,16 +76,16 @@ struct dst_entry { __u32 tclassid; #ifndef CONFIG_64BIT struct lwtunnel_state *lwtstate; - atomic_t __refcnt; /* 32-bit offset 64 */ + rcuref_t __rcuref; /* 32-bit offset 64 */ #endif netdevice_tracker dev_tracker; /* * Used by rtable and rt6_info. Moves lwtstate into the next cache * line on 64bit so that lwtstate does not cause false sharing with - * __refcnt under contention of __refcnt. This also puts the + * __rcuref under contention of __rcuref. This also puts the * frequently accessed members of rtable and rt6_info out of the - * __refcnt cache line. + * __rcuref cache line. */ struct list_head rt_uncached; struct uncached_list *rt_uncached_list; @@ -238,10 +239,10 @@ static inline void dst_hold(struct dst_entry *dst) { /* * If your kernel compilation stops here, please check - * the placement of __refcnt in struct dst_entry + * the placement of __rcuref in struct dst_entry */ - BUILD_BUG_ON(offsetof(struct dst_entry, __refcnt) & 63); - WARN_ON(atomic_inc_not_zero(&dst->__refcnt) == 0); + BUILD_BUG_ON(offsetof(struct dst_entry, __rcuref) & 63); + WARN_ON(!rcuref_get(&dst->__rcuref)); } static inline void dst_use_noref(struct dst_entry *dst, unsigned long time) @@ -305,7 +306,7 @@ static inline void skb_dst_copy(struct sk_buff *nskb, const struct sk_buff *oskb */ static inline bool dst_hold_safe(struct dst_entry *dst) { - return atomic_inc_not_zero(&dst->__refcnt); + return rcuref_get(&dst->__rcuref); } /** diff --git a/include/net/sock.h b/include/net/sock.h index 573f2bf7e0de..5edf0038867c 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2131,7 +2131,7 @@ sk_dst_get(struct sock *sk) rcu_read_lock(); dst = rcu_dereference(sk->sk_dst_cache); - if (dst && !atomic_inc_not_zero(&dst->__refcnt)) + if (dst && !rcuref_get(&dst->__rcuref)) dst = NULL; rcu_read_unlock(); return dst; diff --git a/net/bridge/br_nf_core.c b/net/bridge/br_nf_core.c index 8c69f0c95a8e..98aea5485aae 100644 --- a/net/bridge/br_nf_core.c +++ b/net/bridge/br_nf_core.c @@ -73,7 +73,7 @@ void br_netfilter_rtable_init(struct net_bridge *br) { struct rtable *rt = &br->fake_rtable; - atomic_set(&rt->dst.__refcnt, 1); + rcuref_init(&rt->dst.__rcuref, 1); rt->dst.dev = br->dev; dst_init_metrics(&rt->dst, br_dst_default_metrics, true); rt->dst.flags = DST_NOXFRM | DST_FAKE_RTABLE; diff --git a/net/core/dst.c b/net/core/dst.c index 31c08a3386d3..3247e84045ca 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -66,7 +66,7 @@ void dst_init(struct dst_entry *dst, struct dst_ops *ops, dst->tclassid = 0; #endif dst->lwtstate = NULL; - atomic_set(&dst->__refcnt, initial_ref); + rcuref_init(&dst->__rcuref, initial_ref); dst->__use = 0; dst->lastuse = jiffies; dst->flags = flags; @@ -162,31 +162,15 @@ EXPORT_SYMBOL(dst_dev_put); void dst_release(struct dst_entry *dst) { - if (dst) { - int newrefcnt; - - newrefcnt = atomic_dec_return(&dst->__refcnt); - if (WARN_ONCE(newrefcnt < 0, "dst_release underflow")) - net_warn_ratelimited("%s: dst:%p refcnt:%d\n", - __func__, dst, newrefcnt); - if (!newrefcnt) - call_rcu_hurry(&dst->rcu_head, dst_destroy_rcu); - } + if (dst && rcuref_put(&dst->__rcuref)) + call_rcu_hurry(&dst->rcu_head, dst_destroy_rcu); } EXPORT_SYMBOL(dst_release); void dst_release_immediate(struct dst_entry *dst) { - if (dst) { - int newrefcnt; - - newrefcnt = atomic_dec_return(&dst->__refcnt); - if (WARN_ONCE(newrefcnt < 0, "dst_release_immediate underflow")) - net_warn_ratelimited("%s: dst:%p refcnt:%d\n", - __func__, dst, newrefcnt); - if (!newrefcnt) - dst_destroy(dst); - } + if (dst && rcuref_put(&dst->__rcuref)) + dst_destroy(dst); } EXPORT_SYMBOL(dst_release_immediate); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index b7b1661d0d56..906aebdc566b 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -843,7 +843,7 @@ int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id, if (dst) { ci.rta_lastuse = jiffies_delta_to_clock_t(jiffies - dst->lastuse); ci.rta_used = dst->__use; - ci.rta_clntref = atomic_read(&dst->__refcnt); + ci.rta_clntref = rcuref_read(&dst->__rcuref); } if (expires) { unsigned long clock; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 12e163dec34e..35085fc0cf15 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -293,7 +293,7 @@ static const struct fib6_info fib6_null_entry_template = { static const struct rt6_info ip6_null_entry_template = { .dst = { - .__refcnt = ATOMIC_INIT(1), + .__rcuref = RCUREF_INIT(1), .__use = 1, .obsolete = DST_OBSOLETE_FORCE_CHK, .error = -ENETUNREACH, @@ -307,7 +307,7 @@ static const struct rt6_info ip6_null_entry_template = { static const struct rt6_info ip6_prohibit_entry_template = { .dst = { - .__refcnt = ATOMIC_INIT(1), + .__rcuref = RCUREF_INIT(1), .__use = 1, .obsolete = DST_OBSOLETE_FORCE_CHK, .error = -EACCES, @@ -319,7 +319,7 @@ static const struct rt6_info ip6_prohibit_entry_template = { static const struct rt6_info ip6_blk_hole_entry_template = { .dst = { - .__refcnt = ATOMIC_INIT(1), + .__rcuref = RCUREF_INIT(1), .__use = 1, .obsolete = DST_OBSOLETE_FORCE_CHK, .error = -EINVAL, diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 80448885c3d7..99c349c0d968 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -339,7 +339,7 @@ __ip_vs_get_out_rt(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb, spin_unlock_bh(&dest->dst_lock); IP_VS_DBG(10, "new dst %pI4, src %pI4, refcnt=%d\n", &dest->addr.ip, &dest_dst->dst_saddr.ip, - atomic_read(&rt->dst.__refcnt)); + rcuref_read(&rt->dst.__rcuref)); } if (ret_saddr) *ret_saddr = dest_dst->dst_saddr.ip; @@ -507,7 +507,7 @@ __ip_vs_get_out_rt_v6(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb, spin_unlock_bh(&dest->dst_lock); IP_VS_DBG(10, "new dst %pI6, src %pI6, refcnt=%d\n", &dest->addr.in6, &dest_dst->dst_saddr.in6, - atomic_read(&rt->dst.__refcnt)); + rcuref_read(&rt->dst.__rcuref)); } if (ret_saddr) *ret_saddr = dest_dst->dst_saddr.in6; -- cgit v1.2.3 From 59d3efd27c11c59b32291e5ebc307bed2edb65ee Mon Sep 17 00:00:00 2001 From: Martin Willi Date: Tue, 11 Apr 2023 09:43:19 +0200 Subject: rtnetlink: Restore RTM_NEW/DELLINK notification behavior The commits referenced below allows userspace to use the NLM_F_ECHO flag for RTM_NEW/DELLINK operations to receive unicast notifications for the affected link. Prior to these changes, applications may have relied on multicast notifications to learn the same information without specifying the NLM_F_ECHO flag. For such applications, the mentioned commits changed the behavior for requests not using NLM_F_ECHO. Multicast notifications are still received, but now use the portid of the requester and the sequence number of the request instead of zero values used previously. For the application, this message may be unexpected and likely handled as a response to the NLM_F_ACKed request, especially if it uses the same socket to handle requests and notifications. To fix existing applications relying on the old notification behavior, set the portid and sequence number in the notification only if the request included the NLM_F_ECHO flag. This restores the old behavior for applications not using it, but allows unicasted notifications for others. Fixes: f3a63cce1b4f ("rtnetlink: Honour NLM_F_ECHO flag in rtnl_delete_link") Fixes: d88e136cab37 ("rtnetlink: Honour NLM_F_ECHO flag in rtnl_newlink_create") Signed-off-by: Martin Willi Acked-by: Guillaume Nault Acked-by: Hangbin Liu Link: https://lore.kernel.org/r/20230411074319.24133-1-martin@strongswan.org Signed-off-by: Jakub Kicinski --- include/linux/rtnetlink.h | 3 ++- net/core/dev.c | 2 +- net/core/rtnetlink.c | 11 +++++++++-- 3 files changed, 12 insertions(+), 4 deletions(-) (limited to 'net/core/rtnetlink.c') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 92ad75549e9c..b6e6378dcbbd 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -25,7 +25,8 @@ void rtmsg_ifinfo_newnet(int type, struct net_device *dev, unsigned int change, struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, unsigned change, u32 event, gfp_t flags, int *new_nsid, - int new_ifindex, u32 portid, u32 seq); + int new_ifindex, u32 portid, + const struct nlmsghdr *nlh); void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev, gfp_t flags, u32 portid, const struct nlmsghdr *nlh); diff --git a/net/core/dev.c b/net/core/dev.c index 48067321c0db..1488f700bf81 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -10847,7 +10847,7 @@ void unregister_netdevice_many_notify(struct list_head *head, dev->rtnl_link_state == RTNL_LINK_INITIALIZED) skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, 0, GFP_KERNEL, NULL, 0, - portid, nlmsg_seq(nlh)); + portid, nlh); /* * Flush the unicast and multicast chains diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 5d8eb57867a9..6e44e92ebdf5 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3972,16 +3972,23 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, unsigned int change, u32 event, gfp_t flags, int *new_nsid, - int new_ifindex, u32 portid, u32 seq) + int new_ifindex, u32 portid, + const struct nlmsghdr *nlh) { struct net *net = dev_net(dev); struct sk_buff *skb; int err = -ENOBUFS; + u32 seq = 0; skb = nlmsg_new(if_nlmsg_size(dev, 0), flags); if (skb == NULL) goto errout; + if (nlmsg_report(nlh)) + seq = nlmsg_seq(nlh); + else + portid = 0; + err = rtnl_fill_ifinfo(skb, dev, dev_net(dev), type, portid, seq, change, 0, 0, event, new_nsid, new_ifindex, -1, flags); @@ -4017,7 +4024,7 @@ static void rtmsg_ifinfo_event(int type, struct net_device *dev, return; skb = rtmsg_ifinfo_build_skb(type, dev, change, event, flags, new_nsid, - new_ifindex, portid, nlmsg_seq(nlh)); + new_ifindex, portid, nlh); if (skb) rtmsg_ifinfo_send(skb, dev, flags, portid, nlh); } -- cgit v1.2.3 From 160656d7201d861a1f2a0bf279a765e8cda2317a Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 19 Apr 2023 18:34:59 +0300 Subject: bridge: Allow setting per-{Port, VLAN} neighbor suppression state Add a new bridge port attribute that allows user space to enable per-{Port, VLAN} neighbor suppression. Example: # bridge -d -j -p link show dev swp1 | jq '.[]["neigh_vlan_suppress"]' false # bridge link set dev swp1 neigh_vlan_suppress on # bridge -d -j -p link show dev swp1 | jq '.[]["neigh_vlan_suppress"]' true # bridge link set dev swp1 neigh_vlan_suppress off # bridge -d -j -p link show dev swp1 | jq '.[]["neigh_vlan_suppress"]' false Signed-off-by: Ido Schimmel Acked-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_netlink.c | 8 +++++++- net/core/rtnetlink.c | 2 +- 3 files changed, 9 insertions(+), 2 deletions(-) (limited to 'net/core/rtnetlink.c') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 8d679688efe0..4ac1000b0ef2 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -569,6 +569,7 @@ enum { IFLA_BRPORT_MAB, IFLA_BRPORT_MCAST_N_GROUPS, IFLA_BRPORT_MCAST_MAX_GROUPS, + IFLA_BRPORT_NEIGH_VLAN_SUPPRESS, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index fefb1c0e248b..05c5863d2e20 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -189,6 +189,7 @@ static inline size_t br_port_info_size(void) + nla_total_size(1) /* IFLA_BRPORT_ISOLATED */ + nla_total_size(1) /* IFLA_BRPORT_LOCKED */ + nla_total_size(1) /* IFLA_BRPORT_MAB */ + + nla_total_size(1) /* IFLA_BRPORT_NEIGH_VLAN_SUPPRESS */ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_ROOT_ID */ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_BRIDGE_ID */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_DESIGNATED_PORT */ @@ -278,7 +279,9 @@ static int br_port_fill_attrs(struct sk_buff *skb, !!(p->flags & BR_MRP_LOST_IN_CONT)) || nla_put_u8(skb, IFLA_BRPORT_ISOLATED, !!(p->flags & BR_ISOLATED)) || nla_put_u8(skb, IFLA_BRPORT_LOCKED, !!(p->flags & BR_PORT_LOCKED)) || - nla_put_u8(skb, IFLA_BRPORT_MAB, !!(p->flags & BR_PORT_MAB))) + nla_put_u8(skb, IFLA_BRPORT_MAB, !!(p->flags & BR_PORT_MAB)) || + nla_put_u8(skb, IFLA_BRPORT_NEIGH_VLAN_SUPPRESS, + !!(p->flags & BR_NEIGH_VLAN_SUPPRESS))) return -EMSGSIZE; timerval = br_timer_value(&p->message_age_timer); @@ -891,6 +894,7 @@ static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = { [IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT] = { .type = NLA_U32 }, [IFLA_BRPORT_MCAST_N_GROUPS] = { .type = NLA_REJECT }, [IFLA_BRPORT_MCAST_MAX_GROUPS] = { .type = NLA_U32 }, + [IFLA_BRPORT_NEIGH_VLAN_SUPPRESS] = NLA_POLICY_MAX(NLA_U8, 1), }; /* Change the state of the port and notify spanning tree */ @@ -957,6 +961,8 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[], br_set_port_flag(p, tb, IFLA_BRPORT_ISOLATED, BR_ISOLATED); br_set_port_flag(p, tb, IFLA_BRPORT_LOCKED, BR_PORT_LOCKED); br_set_port_flag(p, tb, IFLA_BRPORT_MAB, BR_PORT_MAB); + br_set_port_flag(p, tb, IFLA_BRPORT_NEIGH_VLAN_SUPPRESS, + BR_NEIGH_VLAN_SUPPRESS); if ((p->flags & BR_PORT_MAB) && (!(p->flags & BR_PORT_LOCKED) || !(p->flags & BR_LEARNING))) { diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index e844d75220fb..653901a1bf75 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -61,7 +61,7 @@ #include "dev.h" #define RTNL_MAX_TYPE 50 -#define RTNL_SLAVE_MAX_TYPE 42 +#define RTNL_SLAVE_MAX_TYPE 43 struct rtnl_link { rtnl_doit_func doit; -- cgit v1.2.3 From b0ad3c179059089d809b477a1d445c1183a7b8fe Mon Sep 17 00:00:00 2001 From: Xin Long Date: Wed, 31 May 2023 12:01:42 -0400 Subject: rtnetlink: call validate_linkmsg in rtnl_create_link validate_linkmsg() was introduced by commit 1840bb13c22f5b ("[RTNL]: Validate hardware and broadcast address attribute for RTM_NEWLINK") to validate tb[IFLA_ADDRESS/BROADCAST] for existing links. The same check should also be done for newly created links. This patch adds validate_linkmsg() call in rtnl_create_link(), to avoid the invalid address set when creating some devices like: # ip link add dummy0 type dummy # ip link add link dummy0 name mac0 address 01:02 type macsec Fixes: 0e06877c6fdb ("[RTNETLINK]: rtnl_link: allow specifying initial device address") Signed-off-by: Xin Long Reviewed-by: Simon Horman Signed-off-by: Jakub Kicinski --- net/core/rtnetlink.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'net/core/rtnetlink.c') diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 653901a1bf75..824688edb722 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3285,6 +3285,7 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname, struct net_device *dev; unsigned int num_tx_queues = 1; unsigned int num_rx_queues = 1; + int err; if (tb[IFLA_NUM_TX_QUEUES]) num_tx_queues = nla_get_u32(tb[IFLA_NUM_TX_QUEUES]); @@ -3320,13 +3321,18 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname, if (!dev) return ERR_PTR(-ENOMEM); + err = validate_linkmsg(dev, tb, extack); + if (err < 0) { + free_netdev(dev); + return ERR_PTR(err); + } + dev_net_set(dev, net); dev->rtnl_link_ops = ops; dev->rtnl_link_state = RTNL_LINK_INITIALIZING; if (tb[IFLA_MTU]) { u32 mtu = nla_get_u32(tb[IFLA_MTU]); - int err; err = dev_validate_mtu(dev, mtu, extack); if (err) { -- cgit v1.2.3 From fef5b228dd38378148bc850f7e69a7783f3b95a4 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Wed, 31 May 2023 12:01:43 -0400 Subject: rtnetlink: move IFLA_GSO_ tb check to validate_linkmsg These IFLA_GSO_* tb check should also be done for the new created link, otherwise, they can be set to a huge value when creating links: # ip link add dummy1 gso_max_size 4294967295 type dummy # ip -d link show dummy1 dummy addrgenmode eui64 ... gso_max_size 4294967295 Fixes: 46e6b992c250 ("rtnetlink: allow GSO maximums to be set on device creation") Fixes: 9eefedd58ae1 ("net: add gso_ipv4_max_size and gro_ipv4_max_size per device") Signed-off-by: Xin Long Reviewed-by: Simon Horman Signed-off-by: Jakub Kicinski --- net/core/rtnetlink.c | 34 +++++++++++++++++++--------------- 1 file changed, 19 insertions(+), 15 deletions(-) (limited to 'net/core/rtnetlink.c') diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 824688edb722..bc068a857219 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2385,6 +2385,25 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[], if (tb[IFLA_BROADCAST] && nla_len(tb[IFLA_BROADCAST]) < dev->addr_len) return -EINVAL; + + if (tb[IFLA_GSO_MAX_SIZE] && + nla_get_u32(tb[IFLA_GSO_MAX_SIZE]) > dev->tso_max_size) { + NL_SET_ERR_MSG(extack, "too big gso_max_size"); + return -EINVAL; + } + + if (tb[IFLA_GSO_MAX_SEGS] && + (nla_get_u32(tb[IFLA_GSO_MAX_SEGS]) > GSO_MAX_SEGS || + nla_get_u32(tb[IFLA_GSO_MAX_SEGS]) > dev->tso_max_segs)) { + NL_SET_ERR_MSG(extack, "too big gso_max_segs"); + return -EINVAL; + } + + if (tb[IFLA_GSO_IPV4_MAX_SIZE] && + nla_get_u32(tb[IFLA_GSO_IPV4_MAX_SIZE]) > dev->tso_max_size) { + NL_SET_ERR_MSG(extack, "too big gso_ipv4_max_size"); + return -EINVAL; + } } if (tb[IFLA_AF_SPEC]) { @@ -2858,11 +2877,6 @@ static int do_setlink(const struct sk_buff *skb, if (tb[IFLA_GSO_MAX_SIZE]) { u32 max_size = nla_get_u32(tb[IFLA_GSO_MAX_SIZE]); - if (max_size > dev->tso_max_size) { - err = -EINVAL; - goto errout; - } - if (dev->gso_max_size ^ max_size) { netif_set_gso_max_size(dev, max_size); status |= DO_SETLINK_MODIFIED; @@ -2872,11 +2886,6 @@ static int do_setlink(const struct sk_buff *skb, if (tb[IFLA_GSO_MAX_SEGS]) { u32 max_segs = nla_get_u32(tb[IFLA_GSO_MAX_SEGS]); - if (max_segs > GSO_MAX_SEGS || max_segs > dev->tso_max_segs) { - err = -EINVAL; - goto errout; - } - if (dev->gso_max_segs ^ max_segs) { netif_set_gso_max_segs(dev, max_segs); status |= DO_SETLINK_MODIFIED; @@ -2895,11 +2904,6 @@ static int do_setlink(const struct sk_buff *skb, if (tb[IFLA_GSO_IPV4_MAX_SIZE]) { u32 max_size = nla_get_u32(tb[IFLA_GSO_IPV4_MAX_SIZE]); - if (max_size > dev->tso_max_size) { - err = -EINVAL; - goto errout; - } - if (dev->gso_ipv4_max_size ^ max_size) { netif_set_gso_ipv4_max_size(dev, max_size); status |= DO_SETLINK_MODIFIED; -- cgit v1.2.3 From 65d6914e253f3d83b724a9bbfc889ae95711e512 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Wed, 31 May 2023 12:01:44 -0400 Subject: rtnetlink: add the missing IFLA_GRO_ tb check in validate_linkmsg This fixes the issue that dev gro_max_size and gso_ipv4_max_size can be set to a huge value: # ip link add dummy1 type dummy # ip link set dummy1 gro_max_size 4294967295 # ip -d link show dummy1 dummy addrgenmode eui64 ... gro_max_size 4294967295 Fixes: 0fe79f28bfaf ("net: allow gro_max_size to exceed 65536") Fixes: 9eefedd58ae1 ("net: add gso_ipv4_max_size and gro_ipv4_max_size per device") Reported-by: Xiumei Mu Signed-off-by: Xin Long Reviewed-by: Simon Horman Signed-off-by: Jakub Kicinski --- net/core/rtnetlink.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'net/core/rtnetlink.c') diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index bc068a857219..41de3a2f29e1 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2399,11 +2399,23 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[], return -EINVAL; } + if (tb[IFLA_GRO_MAX_SIZE] && + nla_get_u32(tb[IFLA_GRO_MAX_SIZE]) > GRO_MAX_SIZE) { + NL_SET_ERR_MSG(extack, "too big gro_max_size"); + return -EINVAL; + } + if (tb[IFLA_GSO_IPV4_MAX_SIZE] && nla_get_u32(tb[IFLA_GSO_IPV4_MAX_SIZE]) > dev->tso_max_size) { NL_SET_ERR_MSG(extack, "too big gso_ipv4_max_size"); return -EINVAL; } + + if (tb[IFLA_GRO_IPV4_MAX_SIZE] && + nla_get_u32(tb[IFLA_GRO_IPV4_MAX_SIZE]) > GRO_MAX_SIZE) { + NL_SET_ERR_MSG(extack, "too big gro_ipv4_max_size"); + return -EINVAL; + } } if (tb[IFLA_AF_SPEC]) { -- cgit v1.2.3