From 8ecd06277a7664f4ef018abae3abd3451d64e7a6 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Mon, 17 Jun 2024 11:18:15 +0200 Subject: netfilter: ipset: Fix suspicious rcu_dereference_protected() When destroying all sets, we are either in pernet exit phase or are executing a "destroy all sets command" from userspace. The latter was taken into account in ip_set_dereference() (nfnetlink mutex is held), but the former was not. The patch adds the required check to rcu_dereference_protected() in ip_set_dereference(). Fixes: 4e7aaa6b82d6 ("netfilter: ipset: Fix race between namespace cleanup and gc in the list:set type") Reported-by: syzbot+b62c37cdd58103293a5a@syzkaller.appspotmail.com Reported-by: syzbot+cfbe1da5fdfc39efc293@syzkaller.appspotmail.com Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-lkp/202406141556.e0b6f17e-lkp@intel.com Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- net/netfilter/ipset/ip_set_core.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'net') diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index c7ae4d9bf3d2..61431690cbd5 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -53,12 +53,13 @@ MODULE_DESCRIPTION("core IP set support"); MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_IPSET); /* When the nfnl mutex or ip_set_ref_lock is held: */ -#define ip_set_dereference(p) \ - rcu_dereference_protected(p, \ +#define ip_set_dereference(inst) \ + rcu_dereference_protected((inst)->ip_set_list, \ lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET) || \ - lockdep_is_held(&ip_set_ref_lock)) + lockdep_is_held(&ip_set_ref_lock) || \ + (inst)->is_deleted) #define ip_set(inst, id) \ - ip_set_dereference((inst)->ip_set_list)[id] + ip_set_dereference(inst)[id] #define ip_set_ref_netlink(inst,id) \ rcu_dereference_raw((inst)->ip_set_list)[id] #define ip_set_dereference_nfnl(p) \ @@ -1133,7 +1134,7 @@ static int ip_set_create(struct sk_buff *skb, const struct nfnl_info *info, if (!list) goto cleanup; /* nfnl mutex is held, both lists are valid */ - tmp = ip_set_dereference(inst->ip_set_list); + tmp = ip_set_dereference(inst); memcpy(list, tmp, sizeof(struct ip_set *) * inst->ip_set_max); rcu_assign_pointer(inst->ip_set_list, list); /* Make sure all current packets have passed through */ -- cgit v1.2.3 From 9a3bc8d16e0aacd65c31aaf23a2bced3288a7779 Mon Sep 17 00:00:00 2001 From: Jianguo Wu Date: Thu, 13 Jun 2024 17:42:46 +0800 Subject: seg6: fix parameter passing when calling NF_HOOK() in End.DX4 and End.DX6 behaviors input_action_end_dx4() and input_action_end_dx6() are called NF_HOOK() for PREROUTING hook, in PREROUTING hook, we should passing a valid indev, and a NULL outdev to NF_HOOK(), otherwise may trigger a NULL pointer dereference, as below: [74830.647293] BUG: kernel NULL pointer dereference, address: 0000000000000090 [74830.655633] #PF: supervisor read access in kernel mode [74830.657888] #PF: error_code(0x0000) - not-present page [74830.659500] PGD 0 P4D 0 [74830.660450] Oops: 0000 [#1] PREEMPT SMP PTI ... [74830.664953] Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 [74830.666569] RIP: 0010:rpfilter_mt+0x44/0x15e [ipt_rpfilter] ... [74830.689725] Call Trace: [74830.690402] [74830.690953] ? show_trace_log_lvl+0x1c4/0x2df [74830.692020] ? show_trace_log_lvl+0x1c4/0x2df [74830.693095] ? ipt_do_table+0x286/0x710 [ip_tables] [74830.694275] ? __die_body.cold+0x8/0xd [74830.695205] ? page_fault_oops+0xac/0x140 [74830.696244] ? exc_page_fault+0x62/0x150 [74830.697225] ? asm_exc_page_fault+0x22/0x30 [74830.698344] ? rpfilter_mt+0x44/0x15e [ipt_rpfilter] [74830.699540] ipt_do_table+0x286/0x710 [ip_tables] [74830.700758] ? ip6_route_input+0x19d/0x240 [74830.701752] nf_hook_slow+0x3f/0xb0 [74830.702678] input_action_end_dx4+0x19b/0x1e0 [74830.703735] ? input_action_end_t+0xe0/0xe0 [74830.704734] seg6_local_input_core+0x2d/0x60 [74830.705782] lwtunnel_input+0x5b/0xb0 [74830.706690] __netif_receive_skb_one_core+0x63/0xa0 [74830.707825] process_backlog+0x99/0x140 [74830.709538] __napi_poll+0x2c/0x160 [74830.710673] net_rx_action+0x296/0x350 [74830.711860] __do_softirq+0xcb/0x2ac [74830.713049] do_softirq+0x63/0x90 input_action_end_dx4() passing a NULL indev to NF_HOOK(), and finally trigger a NULL dereference in rpfilter_mt()->rpfilter_is_loopback(): static bool rpfilter_is_loopback(const struct sk_buff *skb, const struct net_device *in) { // in is NULL return skb->pkt_type == PACKET_LOOPBACK || in->flags & IFF_LOOPBACK; } Fixes: 7a3f5b0de364 ("netfilter: add netfilter hooks to SRv6 data plane") Signed-off-by: Jianguo Wu Reviewed-by: Simon Horman Signed-off-by: Pablo Neira Ayuso --- net/ipv6/seg6_local.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'net') diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index 24e2b4b494cb..c434940131b1 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -941,8 +941,8 @@ static int input_action_end_dx6(struct sk_buff *skb, if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled)) return NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, - dev_net(skb->dev), NULL, skb, NULL, - skb_dst(skb)->dev, input_action_end_dx6_finish); + dev_net(skb->dev), NULL, skb, skb->dev, + NULL, input_action_end_dx6_finish); return input_action_end_dx6_finish(dev_net(skb->dev), NULL, skb); drop: @@ -991,8 +991,8 @@ static int input_action_end_dx4(struct sk_buff *skb, if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled)) return NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, - dev_net(skb->dev), NULL, skb, NULL, - skb_dst(skb)->dev, input_action_end_dx4_finish); + dev_net(skb->dev), NULL, skb, skb->dev, + NULL, input_action_end_dx4_finish); return input_action_end_dx4_finish(dev_net(skb->dev), NULL, skb); drop: -- cgit v1.2.3 From a2225e0250c5fa397dcebf6ce65a9f05a114e0cf Mon Sep 17 00:00:00 2001 From: Jianguo Wu Date: Thu, 13 Jun 2024 17:42:47 +0800 Subject: netfilter: move the sysctl nf_hooks_lwtunnel into the netfilter core Currently, the sysctl net.netfilter.nf_hooks_lwtunnel depends on the nf_conntrack module, but the nf_conntrack module is not always loaded. Therefore, accessing net.netfilter.nf_hooks_lwtunnel may have an error. Move sysctl nf_hooks_lwtunnel into the netfilter core. Fixes: 7a3f5b0de364 ("netfilter: add netfilter hooks to SRv6 data plane") Suggested-by: Pablo Neira Ayuso Signed-off-by: Jianguo Wu Signed-off-by: Pablo Neira Ayuso --- include/net/netns/netfilter.h | 3 ++ net/netfilter/core.c | 13 ++++++- net/netfilter/nf_conntrack_standalone.c | 15 -------- net/netfilter/nf_hooks_lwtunnel.c | 67 +++++++++++++++++++++++++++++++++ net/netfilter/nf_internals.h | 6 +++ 5 files changed, 87 insertions(+), 17 deletions(-) (limited to 'net') diff --git a/include/net/netns/netfilter.h b/include/net/netns/netfilter.h index 02bbdc577f8e..a6a0bf4a247e 100644 --- a/include/net/netns/netfilter.h +++ b/include/net/netns/netfilter.h @@ -15,6 +15,9 @@ struct netns_nf { const struct nf_logger __rcu *nf_loggers[NFPROTO_NUMPROTO]; #ifdef CONFIG_SYSCTL struct ctl_table_header *nf_log_dir_header; +#ifdef CONFIG_LWTUNNEL + struct ctl_table_header *nf_lwtnl_dir_header; +#endif #endif struct nf_hook_entries __rcu *hooks_ipv4[NF_INET_NUMHOOKS]; struct nf_hook_entries __rcu *hooks_ipv6[NF_INET_NUMHOOKS]; diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 3126911f5042..b00fc285b334 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -815,12 +815,21 @@ int __init netfilter_init(void) if (ret < 0) goto err; +#ifdef CONFIG_LWTUNNEL + ret = netfilter_lwtunnel_init(); + if (ret < 0) + goto err_lwtunnel_pernet; +#endif ret = netfilter_log_init(); if (ret < 0) - goto err_pernet; + goto err_log_pernet; return 0; -err_pernet: +err_log_pernet: +#ifdef CONFIG_LWTUNNEL + netfilter_lwtunnel_fini(); +err_lwtunnel_pernet: +#endif unregister_pernet_subsys(&netfilter_net_ops); err: return ret; diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 74112e9c5dab..6c40bdf8b05a 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -22,9 +22,6 @@ #include #include #include -#ifdef CONFIG_LWTUNNEL -#include -#endif #include static bool enable_hooks __read_mostly; @@ -612,9 +609,6 @@ enum nf_ct_sysctl_index { NF_SYSCTL_CT_PROTO_TIMEOUT_GRE, NF_SYSCTL_CT_PROTO_TIMEOUT_GRE_STREAM, #endif -#ifdef CONFIG_LWTUNNEL - NF_SYSCTL_CT_LWTUNNEL, -#endif NF_SYSCTL_CT_LAST_SYSCTL, }; @@ -946,15 +940,6 @@ static struct ctl_table nf_ct_sysctl_table[] = { .proc_handler = proc_dointvec_jiffies, }, #endif -#ifdef CONFIG_LWTUNNEL - [NF_SYSCTL_CT_LWTUNNEL] = { - .procname = "nf_hooks_lwtunnel", - .data = NULL, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = nf_hooks_lwtunnel_sysctl_handler, - }, -#endif }; static struct ctl_table nf_ct_netfilter_table[] = { diff --git a/net/netfilter/nf_hooks_lwtunnel.c b/net/netfilter/nf_hooks_lwtunnel.c index 00e89ffd78f6..7cdb59bb4459 100644 --- a/net/netfilter/nf_hooks_lwtunnel.c +++ b/net/netfilter/nf_hooks_lwtunnel.c @@ -3,6 +3,9 @@ #include #include #include +#include + +#include "nf_internals.h" static inline int nf_hooks_lwtunnel_get(void) { @@ -50,4 +53,68 @@ int nf_hooks_lwtunnel_sysctl_handler(struct ctl_table *table, int write, return ret; } EXPORT_SYMBOL_GPL(nf_hooks_lwtunnel_sysctl_handler); + +static struct ctl_table nf_lwtunnel_sysctl_table[] = { + { + .procname = "nf_hooks_lwtunnel", + .data = NULL, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = nf_hooks_lwtunnel_sysctl_handler, + }, +}; + +static int __net_init nf_lwtunnel_net_init(struct net *net) +{ + struct ctl_table_header *hdr; + struct ctl_table *table; + + table = nf_lwtunnel_sysctl_table; + if (!net_eq(net, &init_net)) { + table = kmemdup(nf_lwtunnel_sysctl_table, + sizeof(nf_lwtunnel_sysctl_table), + GFP_KERNEL); + if (!table) + goto err_alloc; + } + + hdr = register_net_sysctl_sz(net, "net/netfilter", table, + ARRAY_SIZE(nf_lwtunnel_sysctl_table)); + if (!hdr) + goto err_reg; + + net->nf.nf_lwtnl_dir_header = hdr; + + return 0; +err_reg: + if (!net_eq(net, &init_net)) + kfree(table); +err_alloc: + return -ENOMEM; +} + +static void __net_exit nf_lwtunnel_net_exit(struct net *net) +{ + const struct ctl_table *table; + + table = net->nf.nf_lwtnl_dir_header->ctl_table_arg; + unregister_net_sysctl_table(net->nf.nf_lwtnl_dir_header); + if (!net_eq(net, &init_net)) + kfree(table); +} + +static struct pernet_operations nf_lwtunnel_net_ops = { + .init = nf_lwtunnel_net_init, + .exit = nf_lwtunnel_net_exit, +}; + +int __init netfilter_lwtunnel_init(void) +{ + return register_pernet_subsys(&nf_lwtunnel_net_ops); +} + +void netfilter_lwtunnel_fini(void) +{ + unregister_pernet_subsys(&nf_lwtunnel_net_ops); +} #endif /* CONFIG_SYSCTL */ diff --git a/net/netfilter/nf_internals.h b/net/netfilter/nf_internals.h index 832ae64179f0..25403023060b 100644 --- a/net/netfilter/nf_internals.h +++ b/net/netfilter/nf_internals.h @@ -29,6 +29,12 @@ void nf_queue_nf_hook_drop(struct net *net); /* nf_log.c */ int __init netfilter_log_init(void); +#ifdef CONFIG_LWTUNNEL +/* nf_hooks_lwtunnel.c */ +int __init netfilter_lwtunnel_init(void); +void netfilter_lwtunnel_fini(void); +#endif + /* core.c */ void nf_hook_entries_delete_raw(struct nf_hook_entries __rcu **pp, const struct nf_hook_ops *reg); -- cgit v1.2.3