summaryrefslogtreecommitdiffstats
path: root/net/bridge
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2023-02-22 03:24:12 +0100
committerLinus Torvalds <torvalds@linux-foundation.org>2023-02-22 03:24:12 +0100
commit5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 (patch)
treecc5c2d0a898769fd59549594fedb3ee6f84e59a0 /net/bridge
parentMerge tag 'v6.3-p1' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/... (diff)
parentMerge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net (diff)
downloadlinux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.tar.xz
linux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.zip
Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from Jakub Kicinski: "Core: - Add dedicated kmem_cache for typical/small skb->head, avoid having to access struct page at kfree time, and improve memory use. - Introduce sysctl to set default RPS configuration for new netdevs. - Define Netlink protocol specification format which can be used to describe messages used by each family and auto-generate parsers. Add tools for generating kernel data structures and uAPI headers. - Expose all net/core sysctls inside netns. - Remove 4s sleep in netpoll if carrier is instantly detected on boot. - Add configurable limit of MDB entries per port, and port-vlan. - Continue populating drop reasons throughout the stack. - Retire a handful of legacy Qdiscs and classifiers. Protocols: - Support IPv4 big TCP (TSO frames larger than 64kB). - Add IP_LOCAL_PORT_RANGE socket option, to control local port range on socket by socket basis. - Track and report in procfs number of MPTCP sockets used. - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path manager. - IPv6: don't check net.ipv6.route.max_size and rely on garbage collection to free memory (similarly to IPv4). - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986). - ICMP: add per-rate limit counters. - Add support for user scanning requests in ieee802154. - Remove static WEP support. - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate reporting. - WiFi 7 EHT channel puncturing support (client & AP). BPF: - Add a rbtree data structure following the "next-gen data structure" precedent set by recently added linked list, that is, by using kfunc + kptr instead of adding a new BPF map type. - Expose XDP hints via kfuncs with initial support for RX hash and timestamp metadata. - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to better support decap on GRE tunnel devices not operating in collect metadata. - Improve x86 JIT's codegen for PROBE_MEM runtime error checks. - Remove the need for trace_printk_lock for bpf_trace_printk and bpf_trace_vprintk helpers. - Extend libbpf's bpf_tracing.h support for tracing arguments of kprobes/uprobes and syscall as a special case. - Significantly reduce the search time for module symbols by livepatch and BPF. - Enable cpumasks to be used as kptrs, which is useful for tracing programs tracking which tasks end up running on which CPUs in different time intervals. - Add support for BPF trampoline on s390x and riscv64. - Add capability to export the XDP features supported by the NIC. - Add __bpf_kfunc tag for marking kernel functions as kfuncs. - Add cgroup.memory=nobpf kernel parameter option to disable BPF memory accounting for container environments. Netfilter: - Remove the CLUSTERIP target. It has been marked as obsolete for years, and we still have WARN splats wrt races of the out-of-band /proc interface installed by this target. - Add 'destroy' commands to nf_tables. They are identical to the existing 'delete' commands, but do not return an error if the referenced object (set, chain, rule...) did not exist. Driver API: - Improve cpumask_local_spread() locality to help NICs set the right IRQ affinity on AMD platforms. - Separate C22 and C45 MDIO bus transactions more clearly. - Introduce new DCB table to control DSCP rewrite on egress. - Support configuration of Physical Layer Collision Avoidance (PLCA) Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of shared medium Ethernet. - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing preemption of low priority frames by high priority frames. - Add support for controlling MACSec offload using netlink SET. - Rework devlink instance refcounts to allow registration and de-registration under the instance lock. Split the code into multiple files, drop some of the unnecessarily granular locks and factor out common parts of netlink operation handling. - Add TX frame aggregation parameters (for USB drivers). - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning messages with notifications for debug. - Allow offloading of UDP NEW connections via act_ct. - Add support for per action HW stats in TC. - Support hardware miss to TC action (continue processing in SW from a specific point in the action chain). - Warn if old Wireless Extension user space interface is used with modern cfg80211/mac80211 drivers. Do not support Wireless Extensions for Wi-Fi 7 devices at all. Everyone should switch to using nl80211 interface instead. - Improve the CAN bit timing configuration. Use extack to return error messages directly to user space, update the SJW handling, including the definition of a new default value that will benefit CAN-FD controllers, by increasing their oscillator tolerance. New hardware / drivers: - Ethernet: - nVidia BlueField-3 support (control traffic driver) - Ethernet support for imx93 SoCs - Motorcomm yt8531 gigabit Ethernet PHY - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA) - Microchip LAN8841 PHY (incl. cable diagnostics and PTP) - Amlogic gxl MDIO mux - WiFi: - RealTek RTL8188EU (rtl8xxxu) - Qualcomm Wi-Fi 7 devices (ath12k) - CAN: - Renesas R-Car V4H Drivers: - Bluetooth: - Set Per Platform Antenna Gain (PPAG) for Intel controllers. - Ethernet NICs: - Intel (1G, igc): - support TSN / Qbv / packet scheduling features of i226 model - Intel (100G, ice): - use GNSS subsystem instead of TTY - multi-buffer XDP support - extend support for GPIO pins to E823 devices - nVidia/Mellanox: - update the shared buffer configuration on PFC commands - implement PTP adjphase function for HW offset control - TC support for Geneve and GRE with VF tunnel offload - more efficient crypto key management method - multi-port eswitch support - Netronome/Corigine: - add DCB IEEE support - support IPsec offloading for NFP3800 - Freescale/NXP (enetc): - support XDP_REDIRECT for XDP non-linear buffers - improve reconfig, avoid link flap and waiting for idle - support MAC Merge layer - Other NICs: - sfc/ef100: add basic devlink support for ef100 - ionic: rx_push mode operation (writing descriptors via MMIO) - bnxt: use the auxiliary bus abstraction for RDMA - r8169: disable ASPM and reset bus in case of tx timeout - cpsw: support QSGMII mode for J721e CPSW9G - cpts: support pulse-per-second output - ngbe: add an mdio bus driver - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing - r8152: handle devices with FW with NCM support - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation - virtio-net: support multi buffer XDP - virtio/vsock: replace virtio_vsock_pkt with sk_buff - tsnep: XDP support - Ethernet high-speed switches: - nVidia/Mellanox (mlxsw): - add support for latency TLV (in FW control messages) - Microchip (sparx5): - separate explicit and implicit traffic forwarding rules, make the implicit rules always active - add support for egress DSCP rewrite - IS0 VCAP support (Ingress Classification) - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS etc.) - ES2 VCAP support (Egress Access Control) - support for Per-Stream Filtering and Policing (802.1Q, 8.6.5.1) - Ethernet embedded switches: - Marvell (mv88e6xxx): - add MAB (port auth) offload support - enable PTP receive for mv88e6390 - NXP (ocelot): - support MAC Merge layer - support for the the vsc7512 internal copper phys - Microchip: - lan9303: convert to PHYLINK - lan966x: support TC flower filter statistics - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x - lan937x: support Credit Based Shaper configuration - ksz9477: support Energy Efficient Ethernet - other: - qca8k: convert to regmap read/write API, use bulk operations - rswitch: Improve TX timestamp accuracy - Intel WiFi (iwlwifi): - EHT (Wi-Fi 7) rate reporting - STEP equalizer support: transfer some STEP (connection to radio on platforms with integrated wifi) related parameters from the BIOS to the firmware. - Qualcomm 802.11ax WiFi (ath11k): - IPQ5018 support - Fine Timing Measurement (FTM) responder role support - channel 177 support - MediaTek WiFi (mt76): - per-PHY LED support - mt7996: EHT (Wi-Fi 7) support - Wireless Ethernet Dispatch (WED) reset support - switch to using page pool allocator - RealTek WiFi (rtw89): - support new version of Bluetooth co-existance - Mobile: - rmnet: support TX aggregation" * tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits) page_pool: add a comment explaining the fragment counter usage net: ethtool: fix __ethtool_dev_mm_supported() implementation ethtool: pse-pd: Fix double word in comments xsk: add linux/vmalloc.h to xsk.c sefltests: netdevsim: wait for devlink instance after netns removal selftest: fib_tests: Always cleanup before exit net/mlx5e: Align IPsec ASO result memory to be as required by hardware net/mlx5e: TC, Set CT miss to the specific ct action instance net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG net/mlx5: Refactor tc miss handling to a single function net/mlx5: Kconfig: Make tc offload depend on tc skb extension net/sched: flower: Support hardware miss to tc action net/sched: flower: Move filter handle initialization earlier net/sched: cls_api: Support hardware miss to tc action net/sched: Rename user cookie and act cookie sfc: fix builds without CONFIG_RTC_LIB sfc: clean up some inconsistent indentings net/mlx4_en: Introduce flexible array to silence overflow warning net: lan966x: Fix possible deadlock inside PTP net/ulp: Remove redundant ->clone() test in inet_clone_ulp(). ...
Diffstat (limited to 'net/bridge')
-rw-r--r--net/bridge/br_if.c2
-rw-r--r--net/bridge/br_mdb.c66
-rw-r--r--net/bridge/br_multicast.c179
-rw-r--r--net/bridge/br_netfilter_hooks.c2
-rw-r--r--net/bridge/br_netlink.c19
-rw-r--r--net/bridge/br_netlink_tunnel.c3
-rw-r--r--net/bridge/br_private.h12
-rw-r--r--net/bridge/br_switchdev.c10
-rw-r--r--net/bridge/br_vlan.c11
-rw-r--r--net/bridge/br_vlan_options.c27
-rw-r--r--net/bridge/netfilter/nf_conntrack_bridge.c4
11 files changed, 280 insertions, 55 deletions
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index ad13b48e3e08..24f01ff113f0 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -269,7 +269,7 @@ static void brport_get_ownership(const struct kobject *kobj, kuid_t *uid, kgid_t
net_ns_get_ownership(dev_net(p->dev), uid, gid);
}
-static struct kobj_type brport_ktype = {
+static const struct kobj_type brport_ktype = {
#ifdef CONFIG_SYSFS
.sysfs_ops = &brport_sysfs_ops,
#endif
diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index 00e5743647b0..25c48d81a597 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -259,7 +259,7 @@ static int __mdb_fill_info(struct sk_buff *skb,
#endif
} else {
ether_addr_copy(e.addr.u.mac_addr, mp->addr.dst.mac_addr);
- e.state = MDB_PG_FLAGS_PERMANENT;
+ e.state = MDB_PERMANENT;
}
e.addr.proto = mp->addr.proto;
nest_ent = nla_nest_start_noflag(skb,
@@ -421,8 +421,6 @@ static int br_mdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
rcu_read_lock();
- cb->seq = net->dev_base_seq;
-
for_each_netdev_rcu(net, dev) {
if (netif_is_bridge_master(dev)) {
struct net_bridge *br = netdev_priv(dev);
@@ -685,51 +683,58 @@ static const struct nla_policy br_mdbe_attrs_pol[MDBE_ATTR_MAX + 1] = {
[MDBE_ATTR_RTPROT] = NLA_POLICY_MIN(NLA_U8, RTPROT_STATIC),
};
-static bool is_valid_mdb_entry(struct br_mdb_entry *entry,
- struct netlink_ext_ack *extack)
+static int 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_MOD(extack, "Invalid MDBA_SET_ENTRY attribute length");
+ return -EINVAL;
+ }
+
if (entry->ifindex == 0) {
NL_SET_ERR_MSG_MOD(extack, "Zero entry ifindex is not allowed");
- return false;
+ return -EINVAL;
}
if (entry->addr.proto == htons(ETH_P_IP)) {
if (!ipv4_is_multicast(entry->addr.u.ip4)) {
NL_SET_ERR_MSG_MOD(extack, "IPv4 entry group address is not multicast");
- return false;
+ return -EINVAL;
}
if (ipv4_is_local_multicast(entry->addr.u.ip4)) {
NL_SET_ERR_MSG_MOD(extack, "IPv4 entry group address is local multicast");
- return false;
+ 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_MOD(extack, "IPv6 entry group address is link-local all nodes");
- return false;
+ 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_MOD(extack, "L2 entry group is not multicast");
- return false;
+ return -EINVAL;
}
} else {
NL_SET_ERR_MSG_MOD(extack, "Unknown entry protocol");
- return false;
+ return -EINVAL;
}
if (entry->state != MDB_PERMANENT && entry->state != MDB_TEMPORARY) {
NL_SET_ERR_MSG_MOD(extack, "Unknown entry state");
- return false;
+ return -EINVAL;
}
if (entry->vid >= VLAN_VID_MASK) {
NL_SET_ERR_MSG_MOD(extack, "Invalid entry VLAN id");
- return false;
+ return -EINVAL;
}
- return true;
+ return 0;
}
static bool is_valid_mdb_source(struct nlattr *attr, __be16 proto,
@@ -849,11 +854,10 @@ static int br_mdb_add_group_sg(const struct br_mdb_config *cfg,
}
p = br_multicast_new_port_group(cfg->p, &cfg->group, *pp, flags, NULL,
- MCAST_INCLUDE, cfg->rt_protocol);
- if (unlikely(!p)) {
- NL_SET_ERR_MSG_MOD(extack, "Couldn't allocate new (S, G) port group");
+ MCAST_INCLUDE, cfg->rt_protocol, extack);
+ if (unlikely(!p))
return -ENOMEM;
- }
+
rcu_assign_pointer(*pp, p);
if (!(flags & MDB_PG_FLAGS_PERMANENT) && !cfg->src_entry)
mod_timer(&p->timer,
@@ -1075,11 +1079,10 @@ static int br_mdb_add_group_star_g(const struct br_mdb_config *cfg,
}
p = br_multicast_new_port_group(cfg->p, &cfg->group, *pp, flags, NULL,
- cfg->filter_mode, cfg->rt_protocol);
- if (unlikely(!p)) {
- NL_SET_ERR_MSG_MOD(extack, "Couldn't allocate new (*, G) port group");
+ cfg->filter_mode, cfg->rt_protocol,
+ extack);
+ if (unlikely(!p))
return -ENOMEM;
- }
err = br_mdb_add_group_srcs(cfg, p, brmctx, extack);
if (err)
@@ -1101,8 +1104,7 @@ static int br_mdb_add_group_star_g(const struct br_mdb_config *cfg,
return 0;
err_del_port_group:
- hlist_del_init(&p->mglist);
- kfree(p);
+ br_multicast_del_port_group(p);
return err;
}
@@ -1297,6 +1299,14 @@ static int br_mdb_config_attrs_init(struct nlattr *set_attrs,
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,
+ validate_mdb_entry,
+ sizeof(struct br_mdb_entry)),
+ [MDBA_SET_ENTRY_ATTRS] = { .type = NLA_NESTED },
+};
+
static int br_mdb_config_init(struct net *net, const struct nlmsghdr *nlh,
struct br_mdb_config *cfg,
struct netlink_ext_ack *extack)
@@ -1307,7 +1317,7 @@ static int br_mdb_config_init(struct net *net, const struct nlmsghdr *nlh,
int err;
err = nlmsg_parse_deprecated(nlh, sizeof(*bpm), tb,
- MDBA_SET_ENTRY_MAX, NULL, extack);
+ MDBA_SET_ENTRY_MAX, mdba_policy, extack);
if (err)
return err;
@@ -1349,14 +1359,8 @@ static int br_mdb_config_init(struct net *net, const struct nlmsghdr *nlh,
NL_SET_ERR_MSG_MOD(extack, "Missing MDBA_SET_ENTRY attribute");
return -EINVAL;
}
- if (nla_len(tb[MDBA_SET_ENTRY]) != sizeof(struct br_mdb_entry)) {
- NL_SET_ERR_MSG_MOD(extack, "Invalid MDBA_SET_ENTRY attribute length");
- return -EINVAL;
- }
cfg->entry = nla_data(tb[MDBA_SET_ENTRY]);
- if (!is_valid_mdb_entry(cfg->entry, extack))
- return -EINVAL;
if (cfg->entry->ifindex != cfg->br->dev->ifindex) {
struct net_device *pdev;
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index dea1ee1bd095..96d1fc78dd39 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -31,6 +31,7 @@
#include <net/ip6_checksum.h>
#include <net/addrconf.h>
#endif
+#include <trace/events/bridge.h>
#include "br_private.h"
#include "br_private_mcast_eht.h"
@@ -234,6 +235,29 @@ out:
return pmctx;
}
+static struct net_bridge_mcast_port *
+br_multicast_port_vid_to_port_ctx(struct net_bridge_port *port, u16 vid)
+{
+ struct net_bridge_mcast_port *pmctx = NULL;
+ struct net_bridge_vlan *vlan;
+
+ lockdep_assert_held_once(&port->br->multicast_lock);
+
+ if (!br_opt_get(port->br, BROPT_MCAST_VLAN_SNOOPING_ENABLED))
+ return NULL;
+
+ /* Take RCU to access the vlan. */
+ rcu_read_lock();
+
+ vlan = br_vlan_find(nbp_vlan_group_rcu(port), vid);
+ if (vlan && !br_multicast_port_ctx_vlan_disabled(&vlan->port_mcast_ctx))
+ pmctx = &vlan->port_mcast_ctx;
+
+ rcu_read_unlock();
+
+ return pmctx;
+}
+
/* when snooping we need to check if the contexts should be used
* in the following order:
* - if pmctx is non-NULL (port), check if it should be used
@@ -668,6 +692,101 @@ void br_multicast_del_group_src(struct net_bridge_group_src *src,
__br_multicast_del_group_src(src);
}
+static int
+br_multicast_port_ngroups_inc_one(struct net_bridge_mcast_port *pmctx,
+ struct netlink_ext_ack *extack,
+ const char *what)
+{
+ u32 max = READ_ONCE(pmctx->mdb_max_entries);
+ u32 n = READ_ONCE(pmctx->mdb_n_entries);
+
+ if (max && n >= max) {
+ NL_SET_ERR_MSG_FMT_MOD(extack, "%s is already in %u groups, and mcast_max_groups=%u",
+ what, n, max);
+ return -E2BIG;
+ }
+
+ WRITE_ONCE(pmctx->mdb_n_entries, n + 1);
+ return 0;
+}
+
+static void br_multicast_port_ngroups_dec_one(struct net_bridge_mcast_port *pmctx)
+{
+ u32 n = READ_ONCE(pmctx->mdb_n_entries);
+
+ WARN_ON_ONCE(n == 0);
+ WRITE_ONCE(pmctx->mdb_n_entries, n - 1);
+}
+
+static int br_multicast_port_ngroups_inc(struct net_bridge_port *port,
+ const struct br_ip *group,
+ struct netlink_ext_ack *extack)
+{
+ struct net_bridge_mcast_port *pmctx;
+ int err;
+
+ lockdep_assert_held_once(&port->br->multicast_lock);
+
+ /* Always count on the port context. */
+ err = br_multicast_port_ngroups_inc_one(&port->multicast_ctx, extack,
+ "Port");
+ if (err) {
+ trace_br_mdb_full(port->dev, group);
+ return err;
+ }
+
+ /* Only count on the VLAN context if VID is given, and if snooping on
+ * that VLAN is enabled.
+ */
+ if (!group->vid)
+ return 0;
+
+ pmctx = br_multicast_port_vid_to_port_ctx(port, group->vid);
+ if (!pmctx)
+ return 0;
+
+ err = br_multicast_port_ngroups_inc_one(pmctx, extack, "Port-VLAN");
+ if (err) {
+ trace_br_mdb_full(port->dev, group);
+ goto dec_one_out;
+ }
+
+ return 0;
+
+dec_one_out:
+ br_multicast_port_ngroups_dec_one(&port->multicast_ctx);
+ return err;
+}
+
+static void br_multicast_port_ngroups_dec(struct net_bridge_port *port, u16 vid)
+{
+ struct net_bridge_mcast_port *pmctx;
+
+ lockdep_assert_held_once(&port->br->multicast_lock);
+
+ if (vid) {
+ pmctx = br_multicast_port_vid_to_port_ctx(port, vid);
+ if (pmctx)
+ br_multicast_port_ngroups_dec_one(pmctx);
+ }
+ br_multicast_port_ngroups_dec_one(&port->multicast_ctx);
+}
+
+u32 br_multicast_ngroups_get(const struct net_bridge_mcast_port *pmctx)
+{
+ return READ_ONCE(pmctx->mdb_n_entries);
+}
+
+void br_multicast_ngroups_set_max(struct net_bridge_mcast_port *pmctx, u32 max)
+{
+ WRITE_ONCE(pmctx->mdb_max_entries, max);
+}
+
+u32 br_multicast_ngroups_get_max(const struct net_bridge_mcast_port *pmctx)
+{
+ return READ_ONCE(pmctx->mdb_max_entries);
+}
+
static void br_multicast_destroy_port_group(struct net_bridge_mcast_gc *gc)
{
struct net_bridge_port_group *pg;
@@ -702,6 +821,7 @@ void br_multicast_del_pg(struct net_bridge_mdb_entry *mp,
} else {
br_multicast_star_g_handle_mode(pg, MCAST_INCLUDE);
}
+ br_multicast_port_ngroups_dec(pg->key.port, pg->key.addr.vid);
hlist_add_head(&pg->mcast_gc.gc_node, &br->mcast_gc_list);
queue_work(system_long_wq, &br->mcast_gc_work);
@@ -1165,6 +1285,7 @@ struct net_bridge_mdb_entry *br_multicast_new_group(struct net_bridge *br,
return mp;
if (atomic_read(&br->mdb_hash_tbl.nelems) >= br->hash_max) {
+ trace_br_mdb_full(br->dev, group);
br_mc_disabled_update(br->dev, false, NULL);
br_opt_toggle(br, BROPT_MULTICAST_ENABLED, false);
return ERR_PTR(-E2BIG);
@@ -1284,14 +1405,22 @@ struct net_bridge_port_group *br_multicast_new_port_group(
unsigned char flags,
const unsigned char *src,
u8 filter_mode,
- u8 rt_protocol)
+ u8 rt_protocol,
+ struct netlink_ext_ack *extack)
{
struct net_bridge_port_group *p;
+ int err;
- p = kzalloc(sizeof(*p), GFP_ATOMIC);
- if (unlikely(!p))
+ err = br_multicast_port_ngroups_inc(port, group, extack);
+ if (err)
return NULL;
+ p = kzalloc(sizeof(*p), GFP_ATOMIC);
+ if (unlikely(!p)) {
+ NL_SET_ERR_MSG_MOD(extack, "Couldn't allocate new port group");
+ goto dec_out;
+ }
+
p->key.addr = *group;
p->key.port = port;
p->flags = flags;
@@ -1305,8 +1434,8 @@ struct net_bridge_port_group *br_multicast_new_port_group(
if (!br_multicast_is_star_g(group) &&
rhashtable_lookup_insert_fast(&port->br->sg_port_tbl, &p->rhnode,
br_sg_port_rht_params)) {
- kfree(p);
- return NULL;
+ NL_SET_ERR_MSG_MOD(extack, "Couldn't insert new port group");
+ goto free_out;
}
rcu_assign_pointer(p->next, next);
@@ -1320,6 +1449,25 @@ struct net_bridge_port_group *br_multicast_new_port_group(
eth_broadcast_addr(p->eth_addr);
return p;
+
+free_out:
+ kfree(p);
+dec_out:
+ br_multicast_port_ngroups_dec(port, group->vid);
+ return NULL;
+}
+
+void br_multicast_del_port_group(struct net_bridge_port_group *p)
+{
+ struct net_bridge_port *port = p->key.port;
+ __u16 vid = p->key.addr.vid;
+
+ hlist_del_init(&p->mglist);
+ if (!br_multicast_is_star_g(&p->key.addr))
+ rhashtable_remove_fast(&port->br->sg_port_tbl, &p->rhnode,
+ br_sg_port_rht_params);
+ kfree(p);
+ br_multicast_port_ngroups_dec(port, vid);
}
void br_multicast_host_join(const struct net_bridge_mcast *brmctx,
@@ -1387,7 +1535,7 @@ __br_multicast_add_group(struct net_bridge_mcast *brmctx,
}
p = br_multicast_new_port_group(pmctx->port, group, *pp, 0, src,
- filter_mode, RTPROT_KERNEL);
+ filter_mode, RTPROT_KERNEL, NULL);
if (unlikely(!p)) {
p = ERR_PTR(-ENOMEM);
goto out;
@@ -1933,6 +2081,25 @@ static void __br_multicast_enable_port_ctx(struct net_bridge_mcast_port *pmctx)
br_ip4_multicast_add_router(brmctx, pmctx);
br_ip6_multicast_add_router(brmctx, pmctx);
}
+
+ if (br_multicast_port_ctx_is_vlan(pmctx)) {
+ struct net_bridge_port_group *pg;
+ u32 n = 0;
+
+ /* The mcast_n_groups counter might be wrong. First,
+ * BR_VLFLAG_MCAST_ENABLED is toggled before temporary entries
+ * are flushed, thus mcast_n_groups after the toggle does not
+ * reflect the true values. And second, permanent entries added
+ * while BR_VLFLAG_MCAST_ENABLED was disabled, are not reflected
+ * either. Thus we have to refresh the counter.
+ */
+
+ hlist_for_each_entry(pg, &pmctx->port->mglist, mglist) {
+ if (pg->key.addr.vid == pmctx->vlan->vid)
+ n++;
+ }
+ WRITE_ONCE(pmctx->mdb_n_entries, n);
+ }
}
void br_multicast_enable_port(struct net_bridge_port *port)
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 9554abcfd5b4..638a4d5359db 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -214,7 +214,7 @@ static int br_validate_ipv4(struct net *net, struct sk_buff *skb)
if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl)))
goto csum_error;
- len = ntohs(iph->tot_len);
+ len = skb_ip_totlen(skb);
if (skb->len < len) {
__IP_INC_STATS(net, IPSTATS_MIB_INTRUNCATEDPKTS);
goto drop;
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 4316cc82ae17..9173e52b89e2 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -202,6 +202,8 @@ static inline size_t br_port_info_size(void)
+ nla_total_size_64bit(sizeof(u64)) /* IFLA_BRPORT_HOLD_TIMER */
#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
+ nla_total_size(sizeof(u8)) /* IFLA_BRPORT_MULTICAST_ROUTER */
+ + nla_total_size(sizeof(u32)) /* IFLA_BRPORT_MCAST_N_GROUPS */
+ + nla_total_size(sizeof(u32)) /* IFLA_BRPORT_MCAST_MAX_GROUPS */
#endif
+ nla_total_size(sizeof(u16)) /* IFLA_BRPORT_GROUP_FWD_MASK */
+ nla_total_size(sizeof(u8)) /* IFLA_BRPORT_MRP_RING_OPEN */
@@ -298,7 +300,11 @@ static int br_port_fill_attrs(struct sk_buff *skb,
nla_put_u32(skb, IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT,
p->multicast_eht_hosts_limit) ||
nla_put_u32(skb, IFLA_BRPORT_MCAST_EHT_HOSTS_CNT,
- p->multicast_eht_hosts_cnt))
+ p->multicast_eht_hosts_cnt) ||
+ nla_put_u32(skb, IFLA_BRPORT_MCAST_N_GROUPS,
+ br_multicast_ngroups_get(&p->multicast_ctx)) ||
+ nla_put_u32(skb, IFLA_BRPORT_MCAST_MAX_GROUPS,
+ br_multicast_ngroups_get_max(&p->multicast_ctx)))
return -EMSGSIZE;
#endif
@@ -858,6 +864,8 @@ static int br_afspec(struct net_bridge *br,
}
static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = {
+ [IFLA_BRPORT_UNSPEC] = { .strict_start_type =
+ IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT + 1 },
[IFLA_BRPORT_STATE] = { .type = NLA_U8 },
[IFLA_BRPORT_COST] = { .type = NLA_U32 },
[IFLA_BRPORT_PRIORITY] = { .type = NLA_U16 },
@@ -881,6 +889,8 @@ static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = {
[IFLA_BRPORT_MAB] = { .type = NLA_U8 },
[IFLA_BRPORT_BACKUP_PORT] = { .type = NLA_U32 },
[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 },
};
/* Change the state of the port and notify spanning tree */
@@ -1015,6 +1025,13 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[],
if (err)
return err;
}
+
+ if (tb[IFLA_BRPORT_MCAST_MAX_GROUPS]) {
+ u32 max_groups;
+
+ max_groups = nla_get_u32(tb[IFLA_BRPORT_MCAST_MAX_GROUPS]);
+ br_multicast_ngroups_set_max(&p->multicast_ctx, max_groups);
+ }
#endif
if (tb[IFLA_BRPORT_GROUP_FWD_MASK]) {
diff --git a/net/bridge/br_netlink_tunnel.c b/net/bridge/br_netlink_tunnel.c
index 8914290c75d4..17abf092f7ca 100644
--- a/net/bridge/br_netlink_tunnel.c
+++ b/net/bridge/br_netlink_tunnel.c
@@ -188,6 +188,9 @@ initvars:
}
static const struct nla_policy vlan_tunnel_policy[IFLA_BRIDGE_VLAN_TUNNEL_MAX + 1] = {
+ [IFLA_BRIDGE_VLAN_TUNNEL_UNSPEC] = {
+ .strict_start_type = IFLA_BRIDGE_VLAN_TUNNEL_FLAGS + 1
+ },
[IFLA_BRIDGE_VLAN_TUNNEL_ID] = { .type = NLA_U32 },
[IFLA_BRIDGE_VLAN_TUNNEL_VID] = { .type = NLA_U16 },
[IFLA_BRIDGE_VLAN_TUNNEL_FLAGS] = { .type = NLA_U16 },
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 15ef7fd508ee..cef5f6ea850c 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -126,6 +126,8 @@ struct net_bridge_mcast_port {
struct hlist_node ip6_rlist;
#endif /* IS_ENABLED(CONFIG_IPV6) */
unsigned char multicast_router;
+ u32 mdb_n_entries;
+ u32 mdb_max_entries;
#endif /* CONFIG_BRIDGE_IGMP_SNOOPING */
};
@@ -956,7 +958,9 @@ br_multicast_new_port_group(struct net_bridge_port *port,
const struct br_ip *group,
struct net_bridge_port_group __rcu *next,
unsigned char flags, const unsigned char *src,
- u8 filter_mode, u8 rt_protocol);
+ u8 filter_mode, u8 rt_protocol,
+ struct netlink_ext_ack *extack);
+void br_multicast_del_port_group(struct net_bridge_port_group *p);
int br_mdb_hash_init(struct net_bridge *br);
void br_mdb_hash_fini(struct net_bridge *br);
void br_mdb_notify(struct net_device *dev, struct net_bridge_mdb_entry *mp,
@@ -974,6 +978,9 @@ void br_multicast_uninit_stats(struct net_bridge *br);
void br_multicast_get_stats(const struct net_bridge *br,
const struct net_bridge_port *p,
struct br_mcast_stats *dest);
+u32 br_multicast_ngroups_get(const struct net_bridge_mcast_port *pmctx);
+void br_multicast_ngroups_set_max(struct net_bridge_mcast_port *pmctx, u32 max);
+u32 br_multicast_ngroups_get_max(const struct net_bridge_mcast_port *pmctx);
void br_mdb_init(void);
void br_mdb_uninit(void);
void br_multicast_host_join(const struct net_bridge_mcast *brmctx,
@@ -1757,7 +1764,8 @@ static inline u16 br_vlan_flags(const struct net_bridge_vlan *v, u16 pvid)
#ifdef CONFIG_BRIDGE_VLAN_FILTERING
bool br_vlan_opts_eq_range(const struct net_bridge_vlan *v_curr,
const struct net_bridge_vlan *range_end);
-bool br_vlan_opts_fill(struct sk_buff *skb, const struct net_bridge_vlan *v);
+bool br_vlan_opts_fill(struct sk_buff *skb, const struct net_bridge_vlan *v,
+ const struct net_bridge_port *p);
size_t br_vlan_opts_nl_size(void);
int br_vlan_process_options(const struct net_bridge *br,
const struct net_bridge_port *p,
diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c
index 7eb6fd5bb917..de18e9c1d7a7 100644
--- a/net/bridge/br_switchdev.c
+++ b/net/bridge/br_switchdev.c
@@ -104,9 +104,8 @@ int br_switchdev_set_port_flag(struct net_bridge_port *p,
return 0;
if (err) {
- if (extack && !extack->_msg)
- NL_SET_ERR_MSG_MOD(extack,
- "bridge flag offload is not supported");
+ NL_SET_ERR_MSG_WEAK_MOD(extack,
+ "bridge flag offload is not supported");
return -EOPNOTSUPP;
}
@@ -115,9 +114,8 @@ int br_switchdev_set_port_flag(struct net_bridge_port *p,
err = switchdev_port_attr_set(p->dev, &attr, extack);
if (err) {
- if (extack && !extack->_msg)
- NL_SET_ERR_MSG_MOD(extack,
- "error setting offload flag on port");
+ NL_SET_ERR_MSG_WEAK_MOD(extack,
+ "error setting offload flag on port");
return err;
}
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index bc75fa1e4666..8a3dbc09ba38 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -1816,6 +1816,7 @@ out_err:
/* v_opts is used to dump the options which must be equal in the whole range */
static bool br_vlan_fill_vids(struct sk_buff *skb, u16 vid, u16 vid_range,
const struct net_bridge_vlan *v_opts,
+ const struct net_bridge_port *p,
u16 flags,
bool dump_stats)
{
@@ -1842,7 +1843,7 @@ static bool br_vlan_fill_vids(struct sk_buff *skb, u16 vid, u16 vid_range,
goto out_err;
if (v_opts) {
- if (!br_vlan_opts_fill(skb, v_opts))
+ if (!br_vlan_opts_fill(skb, v_opts, p))
goto out_err;
if (dump_stats && !br_vlan_stats_fill(skb, v_opts))
@@ -1925,7 +1926,7 @@ void br_vlan_notify(const struct net_bridge *br,
goto out_kfree;
}
- if (!br_vlan_fill_vids(skb, vid, vid_range, v, flags, false))
+ if (!br_vlan_fill_vids(skb, vid, vid_range, v, p, flags, false))
goto out_err;
nlmsg_end(skb, nlh);
@@ -2030,7 +2031,7 @@ static int br_vlan_dump_dev(const struct net_device *dev,
if (!br_vlan_fill_vids(skb, range_start->vid,
range_end->vid, range_start,
- vlan_flags, dump_stats)) {
+ p, vlan_flags, dump_stats)) {
err = -EMSGSIZE;
break;
}
@@ -2056,7 +2057,7 @@ update_end:
else if (!dump_global &&
!br_vlan_fill_vids(skb, range_start->vid,
range_end->vid, range_start,
- br_vlan_flags(range_start, pvid),
+ p, br_vlan_flags(range_start, pvid),
dump_stats))
err = -EMSGSIZE;
}
@@ -2131,6 +2132,8 @@ static const struct nla_policy br_vlan_db_policy[BRIDGE_VLANDB_ENTRY_MAX + 1] =
[BRIDGE_VLANDB_ENTRY_STATE] = { .type = NLA_U8 },
[BRIDGE_VLANDB_ENTRY_TUNNEL_INFO] = { .type = NLA_NESTED },
[BRIDGE_VLANDB_ENTRY_MCAST_ROUTER] = { .type = NLA_U8 },
+ [BRIDGE_VLANDB_ENTRY_MCAST_N_GROUPS] = { .type = NLA_REJECT },
+ [BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS] = { .type = NLA_U32 },
};
static int br_vlan_rtm_process_one(struct net_device *dev,
diff --git a/net/bridge/br_vlan_options.c b/net/bridge/br_vlan_options.c
index a2724d03278c..e378c2f3a9e2 100644
--- a/net/bridge/br_vlan_options.c
+++ b/net/bridge/br_vlan_options.c
@@ -48,7 +48,8 @@ bool br_vlan_opts_eq_range(const struct net_bridge_vlan *v_curr,
curr_mc_rtr == range_mc_rtr;
}
-bool br_vlan_opts_fill(struct sk_buff *skb, const struct net_bridge_vlan *v)
+bool br_vlan_opts_fill(struct sk_buff *skb, const struct net_bridge_vlan *v,
+ const struct net_bridge_port *p)
{
if (nla_put_u8(skb, BRIDGE_VLANDB_ENTRY_STATE, br_vlan_get_state(v)) ||
!__vlan_tun_put(skb, v))
@@ -58,6 +59,12 @@ bool br_vlan_opts_fill(struct sk_buff *skb, const struct net_bridge_vlan *v)
if (nla_put_u8(skb, BRIDGE_VLANDB_ENTRY_MCAST_ROUTER,
br_vlan_multicast_router(v)))
return false;
+ if (p && !br_multicast_port_ctx_vlan_disabled(&v->port_mcast_ctx) &&
+ (nla_put_u32(skb, BRIDGE_VLANDB_ENTRY_MCAST_N_GROUPS,
+ br_multicast_ngroups_get(&v->port_mcast_ctx)) ||
+ nla_put_u32(skb, BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS,
+ br_multicast_ngroups_get_max(&v->port_mcast_ctx))))
+ return false;
#endif
return true;
@@ -70,6 +77,8 @@ size_t br_vlan_opts_nl_size(void)
+ nla_total_size(sizeof(u32)) /* BRIDGE_VLANDB_TINFO_ID */
#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
+ nla_total_size(sizeof(u8)) /* BRIDGE_VLANDB_ENTRY_MCAST_ROUTER */
+ + nla_total_size(sizeof(u32)) /* BRIDGE_VLANDB_ENTRY_MCAST_N_GROUPS */
+ + nla_total_size(sizeof(u32)) /* BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS */
#endif
+ 0;
}
@@ -212,6 +221,22 @@ static int br_vlan_process_one_opts(const struct net_bridge *br,
return err;
*changed = true;
}
+ if (tb[BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS]) {
+ u32 val;
+
+ if (!p) {
+ NL_SET_ERR_MSG_MOD(extack, "Can't set mcast_max_groups for non-port vlans");
+ return -EINVAL;
+ }
+ if (br_multicast_port_ctx_vlan_disabled(&v->port_mcast_ctx)) {
+ NL_SET_ERR_MSG_MOD(extack, "Multicast snooping disabled on this VLAN");
+ return -EINVAL;
+ }
+
+ val = nla_get_u32(tb[BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS]);
+ br_multicast_ngroups_set_max(&v->port_mcast_ctx, val);
+ *changed = true;
+ }
#endif
return 0;
diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c
index 5c5dd437f1c2..71056ee84773 100644
--- a/net/bridge/netfilter/nf_conntrack_bridge.c
+++ b/net/bridge/netfilter/nf_conntrack_bridge.c
@@ -212,7 +212,7 @@ static int nf_ct_br_ip_check(const struct sk_buff *skb)
iph->version != 4)
return -1;
- len = ntohs(iph->tot_len);
+ len = skb_ip_totlen(skb);
if (skb->len < nhoff + len ||
len < (iph->ihl * 4))
return -1;
@@ -256,7 +256,7 @@ static unsigned int nf_ct_bridge_pre(void *priv, struct sk_buff *skb,
if (!pskb_may_pull(skb, sizeof(struct iphdr)))
return NF_ACCEPT;
- len = ntohs(ip_hdr(skb)->tot_len);
+ len = skb_ip_totlen(skb);
if (pskb_trim_rcsum(skb, len))
return NF_ACCEPT;