From 034dd340b08be1f2f0477ad16131d609f9dbd53c Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 30 Aug 2026 09:22:00 -0700 Subject: Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace Pull tracing fixes from Steven Rostedt: - Fix error output of boot instance creation failure Currently if a boot instance creation fails, instead of printing out the name of the instance that failed, it prints "(null)". That is because it prints "cur_str" that had already been processed by strsep(). Print the saved name instead. While at it, print the error code of the failure. - Fix use-after-free for same named historgrams Histograms can be named so that they can be used in multiple events. But if the named histogram has a variable attached, the second event that uses the named histogram which duplicates it and needs to free the original after duplication leaves the old variable in place and still visible. If another histogram uses than variable, it will use the stale one which will try to reference the freed duplicate histogram and crash the kernel. Free the duplicate variables along with the duplicated histogram data. - Check return value of kthread_run() in event self test The events self tests uses a kthread for testing but does not check if it succeeded in creating a kthread. If the kthread creation were to fail, the code will still try to call kthread_stop() on the error returned. - Fix race between reading trace_pipe and updating subbuffer size If a user is reading the trace_pipe file at the same time they update the ring buffer sub-buffer size, can cause the trace_pipe read to read stale data. Add trace_access_lock() around updating the ring buffer sub-buffer size. - Fix eventfs_inode on failure path in creation of the events directory In the creation of the "events" directory, if after allocating the eventfs_inode a failure is detected, it calls cleanup_ei() which calls free_ei(). The free_ei() will test if eventfs_inode being freed has no children. It is a bug if it does. But on the failure case of the creation of the "events" directory, the children lists have not yet been initialized and the free will trigger a warning because list_empty() on an uninitialized list returns false. Move the initialization into init_ei() where it makes more sense and makes sure that a created eventfs_inode has its lists initialized upon creation. - Check return value of kthread_run() in ftrace direct sample code The sample code that shows how to use the ftrace direct calls does not test the return of kthread_run() to see if it succeeds. Return a failure if the kthread_run() doesn't succeed. - Clear user events state on fork in case of alloc failure On fork, the child gets a pointer to the parent's user events state. It makes a copy of it then updates the child's pointer to it. But if the allocation fails, the duplication function leaves the child with a pointer to its parent's descriptor. When the child cleans up its data, it will free the parent's descriptor while the parent is still using it. In the duplication function, set the child's user_event_mm to NULL before testing if the allocation succeeded, and when it exits it will not free the parent's descriptor. - Fix retry exhaustion in simple ring buffer reader swap simple_ring_buffer_swap_reader_page() starts with retry set to 8 and post-decrements it only after a failed link replacement. On the final attempt, a successful replacement leaves retry at zero, while a failed replacement leaves it at -1. But the check for success expects the retry value to be non-zero and exits with an error on zero. This is the opposite result. Fix it. - Fail nicely when the remote swap_reader_page() returns an error Currently, if the swap_reader_page() of a remote buffer fails, it triggers a WARN_ON_ONCE() and continues normally. Instead, have it exit with an error and a pr_warn() print instead of a full WARNING. * tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: ring-buffer: Stop remote reader update when page swap fails tracing: Fix retry exhaustion in simple ring buffer reader swap tracing/user_events: Clear copied tracing state before fork duplication samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify eventfs: Initialize ei->children and ei->list in init_ei() tracing: Fix use-after-free in trace_pipe read on sub-buffer order change tracing: Fix crash passing ERR_PTR to kthread_stop() tracing: Fix use-after-free with same-name named triggers tracing: Fix logged instance name on creation failure --- net/bridge/br_input.c | 485 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 485 insertions(+) create mode 100644 net/bridge/br_input.c (limited to 'net/bridge/br_input.c') diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c new file mode 100644 index 000000000..d87a5f9fa --- /dev/null +++ b/net/bridge/br_input.c @@ -0,0 +1,485 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Handle incoming frames + * Linux ethernet bridge + * + * Authors: + * Lennert Buytenhek + */ + +#include +#include +#include +#include +#include +#ifdef CONFIG_NETFILTER_FAMILY_BRIDGE +#include +#endif +#include +#include +#include +#include +#include +#include "br_private.h" +#include "br_private_tunnel.h" + +static int +br_netif_receive_skb(struct net *net, struct sock *sk, struct sk_buff *skb) +{ + br_drop_fake_rtable(skb); + return netif_receive_skb(skb); +} + +static int br_pass_frame_up(struct sk_buff *skb, bool promisc) +{ + struct net_device *indev, *brdev = BR_INPUT_SKB_CB(skb)->brdev; + struct net_bridge *br = netdev_priv(brdev); + struct net_bridge_vlan_group *vg; + + dev_sw_netstats_rx_add(brdev, skb->len); + + vg = br_vlan_group_rcu(br); + + /* Reset the offload_fwd_mark because there could be a stacked + * bridge above, and it should not think this bridge it doing + * that bridge's work forwarding out its ports. + */ + br_switchdev_frame_unmark(skb); + + /* Bridge is just like any other port. Make sure the + * packet is allowed except in promisc mode when someone + * may be running packet capture. + */ + if (!(brdev->flags & IFF_PROMISC) && + !br_allowed_egress(vg, skb)) { + kfree_skb(skb); + return NET_RX_DROP; + } + + indev = skb->dev; + skb->dev = brdev; + skb = br_handle_vlan(br, NULL, vg, skb); + if (!skb) + return NET_RX_DROP; + /* update the multicast stats if the packet is IGMP/MLD */ + br_multicast_count(br, NULL, skb, br_multicast_igmp_type(skb), + BR_MCAST_DIR_TX); + + BR_INPUT_SKB_CB(skb)->promisc = promisc; + + return NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, + dev_net(indev), NULL, skb, indev, NULL, + br_netif_receive_skb); +} + +/* note: already called with rcu_read_lock */ +int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb) +{ + enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED; + struct net_bridge_port *p = br_port_get_rcu(skb->dev); + enum br_pkt_type pkt_type = BR_PKT_UNICAST; + struct net_bridge_fdb_entry *dst = NULL; + struct net_bridge_mcast_port *pmctx; + struct net_bridge_mdb_entry *mdst; + bool local_rcv, mcast_hit = false; + struct net_bridge_mcast *brmctx; + struct net_bridge_vlan *vlan; + struct net_bridge *br; + bool promisc; + u16 vid = 0; + u8 state; + + if (!p) + goto drop; + + br = p->br; + + if (br_mst_is_enabled(p)) { + state = BR_STATE_FORWARDING; + } else { + if (p->state == BR_STATE_DISABLED) { + reason = SKB_DROP_REASON_BRIDGE_INGRESS_STP_STATE; + goto drop; + } + + state = p->state; + } + + brmctx = &p->br->multicast_ctx; + pmctx = &p->multicast_ctx; + if (!br_allowed_ingress(p->br, nbp_vlan_group_rcu(p), skb, &vid, + &state, &vlan)) + goto out; + + if (test_bit(BR_PORT_LOCKED_BIT, &p->flags)) { + struct net_bridge_fdb_entry *fdb_src = + br_fdb_find_rcu(br, eth_hdr(skb)->h_source, vid); + + if (!fdb_src) { + /* FDB miss. Create locked FDB entry if MAB is enabled + * and drop the packet. + */ + if (test_bit(BR_PORT_MAB_BIT, &p->flags)) + br_fdb_update(br, p, eth_hdr(skb)->h_source, + vid, BIT(BR_FDB_LOCKED)); + goto drop; + } else if (READ_ONCE(fdb_src->dst) != p || + test_bit(BR_FDB_LOCAL, &fdb_src->flags)) { + /* FDB mismatch. Drop the packet without roaming. */ + goto drop; + } else if (test_bit(BR_FDB_LOCKED, &fdb_src->flags)) { + /* FDB match, but entry is locked. Refresh it and drop + * the packet. + */ + br_fdb_update(br, p, eth_hdr(skb)->h_source, vid, + BIT(BR_FDB_LOCKED)); + goto drop; + } + } + + nbp_switchdev_frame_mark(p, skb); + + /* insert into forwarding database after filtering to avoid spoofing */ + if (test_bit(BR_LEARNING_BIT, &p->flags)) + br_fdb_update(br, p, eth_hdr(skb)->h_source, vid, 0); + + promisc = !!(br->dev->flags & IFF_PROMISC); + local_rcv = promisc; + + if (is_multicast_ether_addr(eth_hdr(skb)->h_dest)) { + /* by definition the broadcast is also a multicast address */ + if (is_broadcast_ether_addr(eth_hdr(skb)->h_dest)) { + pkt_type = BR_PKT_BROADCAST; + local_rcv = true; + } else { + pkt_type = BR_PKT_MULTICAST; + if (br_multicast_rcv(&brmctx, &pmctx, vlan, skb, vid)) + goto drop; + } + } + + if (state == BR_STATE_LEARNING) { + reason = SKB_DROP_REASON_BRIDGE_INGRESS_STP_STATE; + goto drop; + } + + BR_INPUT_SKB_CB(skb)->brdev = br->dev; + BR_INPUT_SKB_CB(skb)->src_port_isolated = test_bit(BR_ISOLATED_BIT, &p->flags); + + if (IS_ENABLED(CONFIG_INET) && + (skb->protocol == htons(ETH_P_ARP) || + skb->protocol == htons(ETH_P_RARP))) { + br_do_proxy_suppress_arp(skb, br, vid, p); + } else if (ipv6_mod_enabled() && + skb->protocol == htons(ETH_P_IPV6) && + br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED) && + pskb_may_pull(skb, sizeof(struct ipv6hdr) + + sizeof(struct nd_msg)) && + ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) { + struct nd_msg *msg; + + msg = br_is_nd_neigh_msg(skb); + if (msg) + br_do_suppress_nd(skb, br, vid, p, msg); + } + + switch (pkt_type) { + case BR_PKT_MULTICAST: + mdst = br_mdb_entry_skb_get(brmctx, skb, vid); + if ((mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) && + br_multicast_querier_exists(brmctx, eth_hdr(skb), mdst)) { + if ((mdst && mdst->host_joined) || + br_multicast_is_router(brmctx, skb) || + br->dev->flags & IFF_ALLMULTI) { + local_rcv = true; + DEV_STATS_INC(br->dev, multicast); + } + mcast_hit = true; + } else { + local_rcv = true; + DEV_STATS_INC(br->dev, multicast); + } + break; + case BR_PKT_UNICAST: + dst = br_fdb_find_rcu(br, eth_hdr(skb)->h_dest, vid); + if (unlikely(!dst && vid && + br_opt_get(br, BROPT_FDB_LOCAL_VLAN_0))) { + dst = br_fdb_find_rcu(br, eth_hdr(skb)->h_dest, 0); + if (dst && + (!test_bit(BR_FDB_LOCAL, &dst->flags) || + test_bit(BR_FDB_ADDED_BY_USER, &dst->flags))) + dst = NULL; + } + break; + default: + break; + } + + if (dst) { + unsigned long now = jiffies; + + if (test_bit(BR_FDB_LOCAL, &dst->flags)) + return br_pass_frame_up(skb, false); + + if (now != READ_ONCE(dst->used)) + WRITE_ONCE(dst->used, now); + br_forward(READ_ONCE(dst->dst), skb, local_rcv, false); + } else { + if (!mcast_hit) + br_flood(br, skb, pkt_type, local_rcv, false, vid); + else + br_multicast_flood(mdst, skb, brmctx, local_rcv, false); + } + + if (local_rcv) + return br_pass_frame_up(skb, promisc); + +out: + return 0; +drop: + kfree_skb_reason(skb, reason); + goto out; +} +EXPORT_SYMBOL_GPL(br_handle_frame_finish); + +static void __br_handle_local_finish(struct sk_buff *skb) +{ + struct net_bridge_port *p = br_port_get_rcu(skb->dev); + u16 vid = 0; + + /* check if vlan is allowed, to avoid spoofing */ + if (test_bit(BR_LEARNING_BIT, &p->flags) && + nbp_state_should_learn(p) && + !br_opt_get(p->br, BROPT_NO_LL_LEARN) && + br_should_learn(p, skb, &vid)) + br_fdb_update(p->br, p, eth_hdr(skb)->h_source, vid, 0); +} + +/* note: already called with rcu_read_lock */ +static int br_handle_local_finish(struct net *net, struct sock *sk, struct sk_buff *skb) +{ + __br_handle_local_finish(skb); + + /* return 1 to signal the okfn() was called so it's ok to use the skb */ + return 1; +} + +static int nf_hook_bridge_pre(struct sk_buff *skb, struct sk_buff **pskb) +{ +#ifdef CONFIG_NETFILTER_FAMILY_BRIDGE + struct nf_hook_entries *e = NULL; + struct nf_hook_state state; + unsigned int verdict, i; + struct net *net; + int ret; + + net = dev_net(skb->dev); +#ifdef CONFIG_JUMP_LABEL + if (!static_key_false(&nf_hooks_needed[NFPROTO_BRIDGE][NF_BR_PRE_ROUTING])) + goto frame_finish; +#endif + + e = rcu_dereference(net->nf.hooks_bridge[NF_BR_PRE_ROUTING]); + if (!e) + goto frame_finish; + + nf_hook_state_init(&state, NF_BR_PRE_ROUTING, + NFPROTO_BRIDGE, skb->dev, NULL, NULL, + net, br_handle_frame_finish); + + for (i = 0; i < e->num_hook_entries; i++) { + verdict = nf_hook_entry_hookfn(&e->hooks[i], skb, &state); + switch (verdict & NF_VERDICT_MASK) { + case NF_ACCEPT: + if (BR_INPUT_SKB_CB(skb)->br_netfilter_broute) { + *pskb = skb; + return RX_HANDLER_PASS; + } + break; + case NF_DROP: + kfree_skb(skb); + return RX_HANDLER_CONSUMED; + case NF_QUEUE: + ret = nf_queue(skb, &state, i, verdict); + if (ret == 1) + continue; + return RX_HANDLER_CONSUMED; + default: /* STOLEN */ + return RX_HANDLER_CONSUMED; + } + } +frame_finish: + net = dev_net(skb->dev); + br_handle_frame_finish(net, NULL, skb); +#else + br_handle_frame_finish(dev_net(skb->dev), NULL, skb); +#endif + return RX_HANDLER_CONSUMED; +} + +/* Return 0 if the frame was not processed otherwise 1 + * note: already called with rcu_read_lock + */ +static int br_process_frame_type(struct net_bridge_port *p, + struct sk_buff *skb) +{ + struct br_frame_type *tmp; + + hlist_for_each_entry_rcu(tmp, &p->br->frame_type_list, list) + if (unlikely(tmp->type == skb->protocol)) + return tmp->frame_handler(p, skb); + + return 0; +} + +/* + * Return NULL if skb is handled + * note: already called with rcu_read_lock + */ +static rx_handler_result_t br_handle_frame(struct sk_buff **pskb) +{ + enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED; + struct net_bridge_port *p; + struct sk_buff *skb = *pskb; + const unsigned char *dest = eth_hdr(skb)->h_dest; + + if (unlikely(skb->pkt_type == PACKET_LOOPBACK)) + return RX_HANDLER_PASS; + + if (!is_valid_ether_addr(eth_hdr(skb)->h_source)) { + reason = SKB_DROP_REASON_MAC_INVALID_SOURCE; + goto drop; + } + + skb = skb_share_check(skb, GFP_ATOMIC); + if (!skb) + return RX_HANDLER_CONSUMED; + + memset(skb->cb, 0, sizeof(struct br_input_skb_cb)); + br_tc_skb_miss_set(skb, false); + + p = br_port_get_rcu(skb->dev); + if (test_bit(BR_VLAN_TUNNEL_BIT, &p->flags)) + br_handle_ingress_vlan_tunnel(skb, p, nbp_vlan_group_rcu(p)); + + if (unlikely(is_link_local_ether_addr(dest))) { + u16 fwd_mask = p->br->group_fwd_mask_required; + + /* + * See IEEE 802.1D Table 7-10 Reserved addresses + * + * Assignment Value + * Bridge Group Address 01-80-C2-00-00-00 + * (MAC Control) 802.3 01-80-C2-00-00-01 + * (Link Aggregation) 802.3 01-80-C2-00-00-02 + * 802.1X PAE address 01-80-C2-00-00-03 + * + * 802.1AB LLDP 01-80-C2-00-00-0E + * + * Others reserved for future standardization + */ + fwd_mask |= p->group_fwd_mask; + switch (dest[5]) { + case 0x00: /* Bridge Group Address */ + /* If STP is turned off, + then must forward to keep loop detection */ + if (p->br->stp_enabled == BR_NO_STP || + fwd_mask & (1u << dest[5])) + goto forward; + *pskb = skb; + __br_handle_local_finish(skb); + return RX_HANDLER_PASS; + + case 0x01: /* IEEE MAC (Pause) */ + reason = SKB_DROP_REASON_MAC_IEEE_MAC_CONTROL; + goto drop; + + case 0x0E: /* 802.1AB LLDP */ + fwd_mask |= p->br->group_fwd_mask; + if (fwd_mask & (1u << dest[5])) + goto forward; + *pskb = skb; + __br_handle_local_finish(skb); + return RX_HANDLER_PASS; + + default: + /* Allow selective forwarding for most other protocols */ + fwd_mask |= p->br->group_fwd_mask; + if (fwd_mask & (1u << dest[5])) + goto forward; + } + + BR_INPUT_SKB_CB(skb)->promisc = false; + + /* The else clause should be hit when nf_hook(): + * - returns < 0 (drop/error) + * - returns = 0 (stolen/nf_queue) + * Thus return 1 from the okfn() to signal the skb is ok to pass + */ + if (NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, + dev_net(skb->dev), NULL, skb, skb->dev, NULL, + br_handle_local_finish) == 1) { + return RX_HANDLER_PASS; + } else { + return RX_HANDLER_CONSUMED; + } + } + + if (unlikely(br_process_frame_type(p, skb))) + return RX_HANDLER_PASS; + +forward: + if (br_mst_is_enabled(p)) + goto defer_stp_filtering; + + switch (p->state) { + case BR_STATE_FORWARDING: + case BR_STATE_LEARNING: +defer_stp_filtering: + if (ether_addr_equal(p->br->dev->dev_addr, dest)) + skb->pkt_type = PACKET_HOST; + + return nf_hook_bridge_pre(skb, pskb); + default: + reason = SKB_DROP_REASON_BRIDGE_INGRESS_STP_STATE; +drop: + kfree_skb_reason(skb, reason); + } + return RX_HANDLER_CONSUMED; +} + +/* This function has no purpose other than to appease the br_port_get_rcu/rtnl + * helpers which identify bridged ports according to the rx_handler installed + * on them (so there _needs_ to be a bridge rx_handler even if we don't need it + * to do anything useful). This bridge won't support traffic to/from the stack, + * but only hardware bridging. So return RX_HANDLER_PASS so we don't steal + * frames from the ETH_P_XDSA packet_type handler. + */ +static rx_handler_result_t br_handle_frame_dummy(struct sk_buff **pskb) +{ + return RX_HANDLER_PASS; +} + +rx_handler_func_t *br_get_rx_handler(const struct net_device *dev) +{ + if (netdev_uses_dsa(dev)) + return br_handle_frame_dummy; + + return br_handle_frame; +} + +void br_add_frame(struct net_bridge *br, struct br_frame_type *ft) +{ + hlist_add_head_rcu(&ft->list, &br->frame_type_list); +} + +void br_del_frame(struct net_bridge *br, struct br_frame_type *ft) +{ + struct br_frame_type *tmp; + + hlist_for_each_entry(tmp, &br->frame_type_list, list) + if (ft == tmp) { + hlist_del_rcu(&ft->list); + return; + } +} -- cgit v1.3.1