From 2874b7911132f6975e668f6849c8ac93bc4e1f35 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sat, 12 Feb 2022 00:44:11 +0100 Subject: netfilter: xt_socket: missing ifdef CONFIG_IP6_NF_IPTABLES dependency nf_defrag_ipv6_disable() requires CONFIG_IP6_NF_IPTABLES. Fixes: 75063c9294fb ("netfilter: xt_socket: fix a typo in socket_mt_destroy()") Reported-by: kernel test robot Reviewed-by: Eric Dumazet Signed-off-by: Pablo Neira Ayuso --- net/netfilter/xt_socket.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net/netfilter') diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index 662e5eb1cc39..7013f55f05d1 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -220,8 +220,10 @@ static void socket_mt_destroy(const struct xt_mtdtor_param *par) { if (par->family == NFPROTO_IPV4) nf_defrag_ipv4_disable(par->net); +#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) else if (par->family == NFPROTO_IPV6) nf_defrag_ipv6_disable(par->net); +#endif } static struct xt_match socket_mt_reg[] __read_mostly = { -- cgit v1.2.3 From b1a5983f56e371046dcf164f90bfaf704d2b89f6 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 17 Feb 2022 23:41:20 +0100 Subject: netfilter: nf_tables_offload: incorrect flow offload action array size immediate verdict expression needs to allocate one slot in the flow offload action array, however, immediate data expression does not need to do so. fwd and dup expression need to allocate one slot, this is missing. Add a new offload_action interface to report if this expression needs to allocate one slot in the flow offload action array. Fixes: be2861dc36d7 ("netfilter: nft_{fwd,dup}_netdev: add offload support") Reported-and-tested-by: Nick Gregory Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 2 +- include/net/netfilter/nf_tables_offload.h | 2 -- net/netfilter/nf_tables_offload.c | 3 ++- net/netfilter/nft_dup_netdev.c | 6 ++++++ net/netfilter/nft_fwd_netdev.c | 6 ++++++ net/netfilter/nft_immediate.c | 12 +++++++++++- 6 files changed, 26 insertions(+), 5 deletions(-) (limited to 'net/netfilter') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index eaf55da9a205..c4c0861deac1 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -905,9 +905,9 @@ struct nft_expr_ops { int (*offload)(struct nft_offload_ctx *ctx, struct nft_flow_rule *flow, const struct nft_expr *expr); + bool (*offload_action)(const struct nft_expr *expr); void (*offload_stats)(struct nft_expr *expr, const struct flow_stats *stats); - u32 offload_flags; const struct nft_expr_type *type; void *data; }; diff --git a/include/net/netfilter/nf_tables_offload.h b/include/net/netfilter/nf_tables_offload.h index f9d95ff82df8..797147843958 100644 --- a/include/net/netfilter/nf_tables_offload.h +++ b/include/net/netfilter/nf_tables_offload.h @@ -67,8 +67,6 @@ struct nft_flow_rule { struct flow_rule *rule; }; -#define NFT_OFFLOAD_F_ACTION (1 << 0) - void nft_flow_rule_set_addr_type(struct nft_flow_rule *flow, enum flow_dissector_key_id addr_type); diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c index 9656c1646222..2d36952b1392 100644 --- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -94,7 +94,8 @@ struct nft_flow_rule *nft_flow_rule_create(struct net *net, expr = nft_expr_first(rule); while (nft_expr_more(rule, expr)) { - if (expr->ops->offload_flags & NFT_OFFLOAD_F_ACTION) + if (expr->ops->offload_action && + expr->ops->offload_action(expr)) num_actions++; expr = nft_expr_next(expr); diff --git a/net/netfilter/nft_dup_netdev.c b/net/netfilter/nft_dup_netdev.c index bbf3fcba3df4..5b5c607fbf83 100644 --- a/net/netfilter/nft_dup_netdev.c +++ b/net/netfilter/nft_dup_netdev.c @@ -67,6 +67,11 @@ static int nft_dup_netdev_offload(struct nft_offload_ctx *ctx, return nft_fwd_dup_netdev_offload(ctx, flow, FLOW_ACTION_MIRRED, oif); } +static bool nft_dup_netdev_offload_action(const struct nft_expr *expr) +{ + return true; +} + static struct nft_expr_type nft_dup_netdev_type; static const struct nft_expr_ops nft_dup_netdev_ops = { .type = &nft_dup_netdev_type, @@ -75,6 +80,7 @@ static const struct nft_expr_ops nft_dup_netdev_ops = { .init = nft_dup_netdev_init, .dump = nft_dup_netdev_dump, .offload = nft_dup_netdev_offload, + .offload_action = nft_dup_netdev_offload_action, }; static struct nft_expr_type nft_dup_netdev_type __read_mostly = { diff --git a/net/netfilter/nft_fwd_netdev.c b/net/netfilter/nft_fwd_netdev.c index fa9301ca6033..619e394a91de 100644 --- a/net/netfilter/nft_fwd_netdev.c +++ b/net/netfilter/nft_fwd_netdev.c @@ -79,6 +79,11 @@ static int nft_fwd_netdev_offload(struct nft_offload_ctx *ctx, return nft_fwd_dup_netdev_offload(ctx, flow, FLOW_ACTION_REDIRECT, oif); } +static bool nft_fwd_netdev_offload_action(const struct nft_expr *expr) +{ + return true; +} + struct nft_fwd_neigh { u8 sreg_dev; u8 sreg_addr; @@ -222,6 +227,7 @@ static const struct nft_expr_ops nft_fwd_netdev_ops = { .dump = nft_fwd_netdev_dump, .validate = nft_fwd_validate, .offload = nft_fwd_netdev_offload, + .offload_action = nft_fwd_netdev_offload_action, }; static const struct nft_expr_ops * diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index 90c64d27ae53..d0f67d325bdf 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -213,6 +213,16 @@ static int nft_immediate_offload(struct nft_offload_ctx *ctx, return 0; } +static bool nft_immediate_offload_action(const struct nft_expr *expr) +{ + const struct nft_immediate_expr *priv = nft_expr_priv(expr); + + if (priv->dreg == NFT_REG_VERDICT) + return true; + + return false; +} + static const struct nft_expr_ops nft_imm_ops = { .type = &nft_imm_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_immediate_expr)), @@ -224,7 +234,7 @@ static const struct nft_expr_ops nft_imm_ops = { .dump = nft_immediate_dump, .validate = nft_immediate_validate, .offload = nft_immediate_offload, - .offload_flags = NFT_OFFLOAD_F_ACTION, + .offload_action = nft_immediate_offload_action, }; struct nft_expr_type nft_imm_type __read_mostly = { -- cgit v1.2.3 From 6069da443bf65f513bb507bb21e2f87cfb1ad0b6 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 18 Feb 2022 12:45:32 +0100 Subject: netfilter: nf_tables: unregister flowtable hooks on netns exit Unregister flowtable hooks before they are releases via nf_tables_flowtable_destroy() otherwise hook core reports UAF. BUG: KASAN: use-after-free in nf_hook_entries_grow+0x5a7/0x700 net/netfilter/core.c:142 net/netfilter/core.c:142 Read of size 4 at addr ffff8880736f7438 by task syz-executor579/3666 CPU: 0 PID: 3666 Comm: syz-executor579 Not tainted 5.16.0-rc5-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] __dump_stack lib/dump_stack.c:88 [inline] lib/dump_stack.c:106 dump_stack_lvl+0x1dc/0x2d8 lib/dump_stack.c:106 lib/dump_stack.c:106 print_address_description+0x65/0x380 mm/kasan/report.c:247 mm/kasan/report.c:247 __kasan_report mm/kasan/report.c:433 [inline] __kasan_report mm/kasan/report.c:433 [inline] mm/kasan/report.c:450 kasan_report+0x19a/0x1f0 mm/kasan/report.c:450 mm/kasan/report.c:450 nf_hook_entries_grow+0x5a7/0x700 net/netfilter/core.c:142 net/netfilter/core.c:142 __nf_register_net_hook+0x27e/0x8d0 net/netfilter/core.c:429 net/netfilter/core.c:429 nf_register_net_hook+0xaa/0x180 net/netfilter/core.c:571 net/netfilter/core.c:571 nft_register_flowtable_net_hooks+0x3c5/0x730 net/netfilter/nf_tables_api.c:7232 net/netfilter/nf_tables_api.c:7232 nf_tables_newflowtable+0x2022/0x2cf0 net/netfilter/nf_tables_api.c:7430 net/netfilter/nf_tables_api.c:7430 nfnetlink_rcv_batch net/netfilter/nfnetlink.c:513 [inline] nfnetlink_rcv_skb_batch net/netfilter/nfnetlink.c:634 [inline] nfnetlink_rcv_batch net/netfilter/nfnetlink.c:513 [inline] net/netfilter/nfnetlink.c:652 nfnetlink_rcv_skb_batch net/netfilter/nfnetlink.c:634 [inline] net/netfilter/nfnetlink.c:652 nfnetlink_rcv+0x10e6/0x2550 net/netfilter/nfnetlink.c:652 net/netfilter/nfnetlink.c:652 __nft_release_hook() calls nft_unregister_flowtable_net_hooks() which only unregisters the hooks, then after RCU grace period, it is guaranteed that no packets add new entries to the flowtable (no flow offload rules and flowtable hooks are reachable from packet path), so it is safe to call nf_flow_table_free() which cleans up the remaining entries from the flowtable (both software and hardware) and it unbinds the flow_block. Fixes: ff4bf2f42a40 ("netfilter: nf_tables: add nft_unregister_flowtable_hook()") Reported-by: syzbot+e918523f77e62790d6d9@syzkaller.appspotmail.com Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'net/netfilter') diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 5fa16990da95..3081c4399f10 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -9636,10 +9636,13 @@ EXPORT_SYMBOL_GPL(__nft_release_basechain); static void __nft_release_hook(struct net *net, struct nft_table *table) { + struct nft_flowtable *flowtable; struct nft_chain *chain; list_for_each_entry(chain, &table->chains, list) nf_tables_unregister_hook(net, table, chain); + list_for_each_entry(flowtable, &table->flowtables, list) + nft_unregister_flowtable_net_hooks(net, &flowtable->hook_list); } static void __nft_release_hooks(struct net *net) -- cgit v1.2.3 From 1a58f84ea5df7f026bf92a0009f931bf547fe965 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 18 Feb 2022 13:17:05 +0100 Subject: netfilter: nft_limit: fix stateful object memory leak We need to provide a destroy callback to release the extra fields. Fixes: 3b9e2ea6c11b ("netfilter: nft_limit: move stateful fields out of expression data") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_limit.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'net/netfilter') diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c index c4f308460dd1..a726b623963d 100644 --- a/net/netfilter/nft_limit.c +++ b/net/netfilter/nft_limit.c @@ -340,11 +340,20 @@ static int nft_limit_obj_pkts_dump(struct sk_buff *skb, return nft_limit_dump(skb, &priv->limit, NFT_LIMIT_PKTS); } +static void nft_limit_obj_pkts_destroy(const struct nft_ctx *ctx, + struct nft_object *obj) +{ + struct nft_limit_priv_pkts *priv = nft_obj_data(obj); + + nft_limit_destroy(ctx, &priv->limit); +} + static struct nft_object_type nft_limit_obj_type; static const struct nft_object_ops nft_limit_obj_pkts_ops = { .type = &nft_limit_obj_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_limit_priv_pkts)), .init = nft_limit_obj_pkts_init, + .destroy = nft_limit_obj_pkts_destroy, .eval = nft_limit_obj_pkts_eval, .dump = nft_limit_obj_pkts_dump, }; @@ -378,11 +387,20 @@ static int nft_limit_obj_bytes_dump(struct sk_buff *skb, return nft_limit_dump(skb, priv, NFT_LIMIT_PKT_BYTES); } +static void nft_limit_obj_bytes_destroy(const struct nft_ctx *ctx, + struct nft_object *obj) +{ + struct nft_limit_priv *priv = nft_obj_data(obj); + + nft_limit_destroy(ctx, priv); +} + static struct nft_object_type nft_limit_obj_type; static const struct nft_object_ops nft_limit_obj_bytes_ops = { .type = &nft_limit_obj_type, .size = sizeof(struct nft_limit_priv), .init = nft_limit_obj_bytes_init, + .destroy = nft_limit_obj_bytes_destroy, .eval = nft_limit_obj_bytes_eval, .dump = nft_limit_obj_bytes_dump, }; -- cgit v1.2.3 From dad3bdeef45f81a6e90204bcc85360bb76eccec7 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 21 Feb 2022 13:31:49 +0100 Subject: netfilter: nf_tables: fix memory leak during stateful obj update stateful objects can be updated from the control plane. The transaction logic allocates a temporary object for this purpose. The ->init function was called for this object, so plain kfree() leaks resources. We must call ->destroy function of the object. nft_obj_destroy does this, but it also decrements the module refcount, but the update path doesn't increment it. To avoid special-casing the update object release, do module_get for the update case too and release it via nft_obj_destroy(). Fixes: d62d0ba97b58 ("netfilter: nf_tables: Introduce stateful object update operation") Cc: Fernando Fernandez Mancera Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 3081c4399f10..9cd1d7a62804 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -6551,12 +6551,15 @@ static int nf_tables_updobj(const struct nft_ctx *ctx, { struct nft_object *newobj; struct nft_trans *trans; - int err; + int err = -ENOMEM; + + if (!try_module_get(type->owner)) + return -ENOENT; trans = nft_trans_alloc(ctx, NFT_MSG_NEWOBJ, sizeof(struct nft_trans_obj)); if (!trans) - return -ENOMEM; + goto err_trans; newobj = nft_obj_init(ctx, type, attr); if (IS_ERR(newobj)) { @@ -6573,6 +6576,8 @@ static int nf_tables_updobj(const struct nft_ctx *ctx, err_free_trans: kfree(trans); +err_trans: + module_put(type->owner); return err; } @@ -8185,7 +8190,7 @@ static void nft_obj_commit_update(struct nft_trans *trans) if (obj->ops->update) obj->ops->update(obj, newobj); - kfree(newobj); + nft_obj_destroy(&trans->ctx, newobj); } static void nft_commit_release(struct nft_trans *trans) @@ -8976,7 +8981,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) break; case NFT_MSG_NEWOBJ: if (nft_trans_obj_update(trans)) { - kfree(nft_trans_obj_newobj(trans)); + nft_obj_destroy(&trans->ctx, nft_trans_obj_newobj(trans)); nft_trans_destroy(trans); } else { trans->ctx.table->use--; -- cgit v1.2.3 From ae089831ff28a115908b8d796f667c2dadef1637 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 22 Feb 2022 10:13:31 -0800 Subject: netfilter: nf_tables: prefer kfree_rcu(ptr, rcu) variant While kfree_rcu(ptr) _is_ supported, it has some limitations. Given that 99.99% of kfree_rcu() users [1] use the legacy two parameters variant, and @catchall objects do have an rcu head, simply use it. Choice of kfree_rcu(ptr) variant was probably not intentional. [1] including calls from net/netfilter/nf_tables_api.c Fixes: aaa31047a6d2 ("netfilter: nftables: add catch-all set element support") Signed-off-by: Eric Dumazet Reviewed-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 9cd1d7a62804..c86748b3873b 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -4502,7 +4502,7 @@ static void nft_set_catchall_destroy(const struct nft_ctx *ctx, list_for_each_entry_safe(catchall, next, &set->catchall_list, list) { list_del_rcu(&catchall->list); nft_set_elem_destroy(set, catchall->elem, true); - kfree_rcu(catchall); + kfree_rcu(catchall, rcu); } } @@ -5669,7 +5669,7 @@ static void nft_setelem_catchall_remove(const struct net *net, list_for_each_entry_safe(catchall, next, &set->catchall_list, list) { if (catchall->elem == elem->priv) { list_del_rcu(&catchall->list); - kfree_rcu(catchall); + kfree_rcu(catchall, rcu); break; } } -- cgit v1.2.3 From 56763f12b0f02706576a088e85ef856deacc98a0 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 27 Feb 2022 10:01:41 -0800 Subject: netfilter: fix use-after-free in __nf_register_net_hook() We must not dereference @new_hooks after nf_hook_mutex has been released, because other threads might have freed our allocated hooks already. BUG: KASAN: use-after-free in nf_hook_entries_get_hook_ops include/linux/netfilter.h:130 [inline] BUG: KASAN: use-after-free in hooks_validate net/netfilter/core.c:171 [inline] BUG: KASAN: use-after-free in __nf_register_net_hook+0x77a/0x820 net/netfilter/core.c:438 Read of size 2 at addr ffff88801c1a8000 by task syz-executor237/4430 CPU: 1 PID: 4430 Comm: syz-executor237 Not tainted 5.17.0-rc5-syzkaller-00306-g2293be58d6a1 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:106 print_address_description.constprop.0.cold+0x8d/0x336 mm/kasan/report.c:255 __kasan_report mm/kasan/report.c:442 [inline] kasan_report.cold+0x83/0xdf mm/kasan/report.c:459 nf_hook_entries_get_hook_ops include/linux/netfilter.h:130 [inline] hooks_validate net/netfilter/core.c:171 [inline] __nf_register_net_hook+0x77a/0x820 net/netfilter/core.c:438 nf_register_net_hook+0x114/0x170 net/netfilter/core.c:571 nf_register_net_hooks+0x59/0xc0 net/netfilter/core.c:587 nf_synproxy_ipv6_init+0x85/0xe0 net/netfilter/nf_synproxy_core.c:1218 synproxy_tg6_check+0x30d/0x560 net/ipv6/netfilter/ip6t_SYNPROXY.c:81 xt_check_target+0x26c/0x9e0 net/netfilter/x_tables.c:1038 check_target net/ipv6/netfilter/ip6_tables.c:530 [inline] find_check_entry.constprop.0+0x7f1/0x9e0 net/ipv6/netfilter/ip6_tables.c:573 translate_table+0xc8b/0x1750 net/ipv6/netfilter/ip6_tables.c:735 do_replace net/ipv6/netfilter/ip6_tables.c:1153 [inline] do_ip6t_set_ctl+0x56e/0xb90 net/ipv6/netfilter/ip6_tables.c:1639 nf_setsockopt+0x83/0xe0 net/netfilter/nf_sockopt.c:101 ipv6_setsockopt+0x122/0x180 net/ipv6/ipv6_sockglue.c:1024 rawv6_setsockopt+0xd3/0x6a0 net/ipv6/raw.c:1084 __sys_setsockopt+0x2db/0x610 net/socket.c:2180 __do_sys_setsockopt net/socket.c:2191 [inline] __se_sys_setsockopt net/socket.c:2188 [inline] __x64_sys_setsockopt+0xba/0x150 net/socket.c:2188 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7f65a1ace7d9 Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 71 15 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f65a1a7f308 EFLAGS: 00000246 ORIG_RAX: 0000000000000036 RAX: ffffffffffffffda RBX: 0000000000000006 RCX: 00007f65a1ace7d9 RDX: 0000000000000040 RSI: 0000000000000029 RDI: 0000000000000003 RBP: 00007f65a1b574c8 R08: 0000000000000001 R09: 0000000000000000 R10: 0000000020000000 R11: 0000000000000246 R12: 00007f65a1b55130 R13: 00007f65a1b574c0 R14: 00007f65a1b24090 R15: 0000000000022000 The buggy address belongs to the page: page:ffffea0000706a00 refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x1c1a8 flags: 0xfff00000000000(node=0|zone=1|lastcpupid=0x7ff) raw: 00fff00000000000 ffffea0001c1b108 ffffea000046dd08 0000000000000000 raw: 0000000000000000 0000000000000000 00000000ffffffff 0000000000000000 page dumped because: kasan: bad access detected page_owner tracks the page as freed page last allocated via order 2, migratetype Unmovable, gfp_mask 0x52dc0(GFP_KERNEL|__GFP_NOWARN|__GFP_NORETRY|__GFP_COMP|__GFP_ZERO), pid 4430, ts 1061781545818, free_ts 1061791488993 prep_new_page mm/page_alloc.c:2434 [inline] get_page_from_freelist+0xa72/0x2f50 mm/page_alloc.c:4165 __alloc_pages+0x1b2/0x500 mm/page_alloc.c:5389 __alloc_pages_node include/linux/gfp.h:572 [inline] alloc_pages_node include/linux/gfp.h:595 [inline] kmalloc_large_node+0x62/0x130 mm/slub.c:4438 __kmalloc_node+0x35a/0x4a0 mm/slub.c:4454 kmalloc_node include/linux/slab.h:604 [inline] kvmalloc_node+0x97/0x100 mm/util.c:580 kvmalloc include/linux/slab.h:731 [inline] kvzalloc include/linux/slab.h:739 [inline] allocate_hook_entries_size net/netfilter/core.c:61 [inline] nf_hook_entries_grow+0x140/0x780 net/netfilter/core.c:128 __nf_register_net_hook+0x144/0x820 net/netfilter/core.c:429 nf_register_net_hook+0x114/0x170 net/netfilter/core.c:571 nf_register_net_hooks+0x59/0xc0 net/netfilter/core.c:587 nf_synproxy_ipv6_init+0x85/0xe0 net/netfilter/nf_synproxy_core.c:1218 synproxy_tg6_check+0x30d/0x560 net/ipv6/netfilter/ip6t_SYNPROXY.c:81 xt_check_target+0x26c/0x9e0 net/netfilter/x_tables.c:1038 check_target net/ipv6/netfilter/ip6_tables.c:530 [inline] find_check_entry.constprop.0+0x7f1/0x9e0 net/ipv6/netfilter/ip6_tables.c:573 translate_table+0xc8b/0x1750 net/ipv6/netfilter/ip6_tables.c:735 do_replace net/ipv6/netfilter/ip6_tables.c:1153 [inline] do_ip6t_set_ctl+0x56e/0xb90 net/ipv6/netfilter/ip6_tables.c:1639 nf_setsockopt+0x83/0xe0 net/netfilter/nf_sockopt.c:101 page last free stack trace: reset_page_owner include/linux/page_owner.h:24 [inline] free_pages_prepare mm/page_alloc.c:1352 [inline] free_pcp_prepare+0x374/0x870 mm/page_alloc.c:1404 free_unref_page_prepare mm/page_alloc.c:3325 [inline] free_unref_page+0x19/0x690 mm/page_alloc.c:3404 kvfree+0x42/0x50 mm/util.c:613 rcu_do_batch kernel/rcu/tree.c:2527 [inline] rcu_core+0x7b1/0x1820 kernel/rcu/tree.c:2778 __do_softirq+0x29b/0x9c2 kernel/softirq.c:558 Memory state around the buggy address: ffff88801c1a7f00: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ffff88801c1a7f80: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff >ffff88801c1a8000: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ^ ffff88801c1a8080: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ffff88801c1a8100: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff Fixes: 2420b79f8c18 ("netfilter: debug: check for sorted array") Signed-off-by: Eric Dumazet Reported-by: syzbot Acked-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/core.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 354cb472f386..8a77a3fd69bc 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -428,14 +428,15 @@ static int __nf_register_net_hook(struct net *net, int pf, p = nf_entry_dereference(*pp); new_hooks = nf_hook_entries_grow(p, reg); - if (!IS_ERR(new_hooks)) + if (!IS_ERR(new_hooks)) { + hooks_validate(new_hooks); rcu_assign_pointer(*pp, new_hooks); + } mutex_unlock(&nf_hook_mutex); if (IS_ERR(new_hooks)) return PTR_ERR(new_hooks); - hooks_validate(new_hooks); #ifdef CONFIG_NETFILTER_INGRESS if (nf_ingress_hook(reg, pf)) net_inc_ingress_queue(); -- cgit v1.2.3 From 747670fd9a2d1b7774030dba65ca022ba442ce71 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 25 Feb 2022 14:02:41 +0100 Subject: netfilter: nf_queue: don't assume sk is full socket There is no guarantee that state->sk refers to a full socket. If refcount transitions to 0, sock_put calls sk_free which then ends up with garbage fields. I'd like to thank Oleksandr Natalenko and Jiri Benc for considerable debug work and pointing out state->sk oddities. Fixes: ca6fb0651883 ("tcp: attach SYNACK messages to request sockets instead of listener") Tested-by: Oleksandr Natalenko Signed-off-by: Florian Westphal --- net/netfilter/nf_queue.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'net/netfilter') diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index 6d12afabfe8a..5ab0680db445 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -46,6 +46,15 @@ void nf_unregister_queue_handler(void) } EXPORT_SYMBOL(nf_unregister_queue_handler); +static void nf_queue_sock_put(struct sock *sk) +{ +#ifdef CONFIG_INET + sock_gen_put(sk); +#else + sock_put(sk); +#endif +} + static void nf_queue_entry_release_refs(struct nf_queue_entry *entry) { struct nf_hook_state *state = &entry->state; @@ -54,7 +63,7 @@ static void nf_queue_entry_release_refs(struct nf_queue_entry *entry) dev_put(state->in); dev_put(state->out); if (state->sk) - sock_put(state->sk); + nf_queue_sock_put(state->sk); #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) dev_put(entry->physin); -- cgit v1.2.3 From c3873070247d9e3c7a6b0cf9bf9b45e8018427b1 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 28 Feb 2022 06:22:22 +0100 Subject: netfilter: nf_queue: fix possible use-after-free Eric Dumazet says: The sock_hold() side seems suspect, because there is no guarantee that sk_refcnt is not already 0. On failure, we cannot queue the packet and need to indicate an error. The packet will be dropped by the caller. v2: split skb prefetch hunk into separate change Fixes: 271b72c7fa82c ("udp: RCU handling for Unicast packets.") Reported-by: Eric Dumazet Reviewed-by: Eric Dumazet Signed-off-by: Florian Westphal --- include/net/netfilter/nf_queue.h | 2 +- net/netfilter/nf_queue.c | 13 +++++++++---- net/netfilter/nfnetlink_queue.c | 12 +++++++++--- 3 files changed, 19 insertions(+), 8 deletions(-) (limited to 'net/netfilter') diff --git a/include/net/netfilter/nf_queue.h b/include/net/netfilter/nf_queue.h index 9eed51e920e8..980daa6e1e3a 100644 --- a/include/net/netfilter/nf_queue.h +++ b/include/net/netfilter/nf_queue.h @@ -37,7 +37,7 @@ void nf_register_queue_handler(const struct nf_queue_handler *qh); void nf_unregister_queue_handler(void); void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict); -void nf_queue_entry_get_refs(struct nf_queue_entry *entry); +bool nf_queue_entry_get_refs(struct nf_queue_entry *entry); void nf_queue_entry_free(struct nf_queue_entry *entry); static inline void init_hashrandom(u32 *jhash_initval) diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index 5ab0680db445..e39549c55945 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -96,19 +96,21 @@ static void __nf_queue_entry_init_physdevs(struct nf_queue_entry *entry) } /* Bump dev refs so they don't vanish while packet is out */ -void nf_queue_entry_get_refs(struct nf_queue_entry *entry) +bool nf_queue_entry_get_refs(struct nf_queue_entry *entry) { struct nf_hook_state *state = &entry->state; + if (state->sk && !refcount_inc_not_zero(&state->sk->sk_refcnt)) + return false; + dev_hold(state->in); dev_hold(state->out); - if (state->sk) - sock_hold(state->sk); #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) dev_hold(entry->physin); dev_hold(entry->physout); #endif + return true; } EXPORT_SYMBOL_GPL(nf_queue_entry_get_refs); @@ -196,7 +198,10 @@ static int __nf_queue(struct sk_buff *skb, const struct nf_hook_state *state, __nf_queue_entry_init_physdevs(entry); - nf_queue_entry_get_refs(entry); + if (!nf_queue_entry_get_refs(entry)) { + kfree(entry); + return -ENOTCONN; + } switch (entry->state.pf) { case AF_INET: diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index ea2d9c2a44cf..64a6acb6aeae 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -710,9 +710,15 @@ static struct nf_queue_entry * nf_queue_entry_dup(struct nf_queue_entry *e) { struct nf_queue_entry *entry = kmemdup(e, e->size, GFP_ATOMIC); - if (entry) - nf_queue_entry_get_refs(entry); - return entry; + + if (!entry) + return NULL; + + if (nf_queue_entry_get_refs(entry)) + return entry; + + kfree(entry); + return NULL; } #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) -- cgit v1.2.3 From 3b836da4081fa585cf6c392f62557496f2cb0efe Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 1 Mar 2022 00:46:19 +0100 Subject: netfilter: nf_queue: handle socket prefetch In case someone combines bpf socket assign and nf_queue, then we will queue an skb who references a struct sock that did not have its reference count incremented. As we leave rcu protection, there is no guarantee that skb->sk is still valid. For refcount-less skb->sk case, try to increment the reference count and then override the destructor. In case of failure we have two choices: orphan the skb and 'delete' preselect or let nf_queue() drop the packet. Do the latter, it should not happen during normal operation. Fixes: cf7fbe660f2d ("bpf: Add socket assign support") Acked-by: Joe Stringer Signed-off-by: Florian Westphal --- net/netfilter/nf_queue.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'net/netfilter') diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index e39549c55945..63d1516816b1 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -180,6 +180,18 @@ static int __nf_queue(struct sk_buff *skb, const struct nf_hook_state *state, break; } + if (skb_sk_is_prefetched(skb)) { + struct sock *sk = skb->sk; + + if (!sk_is_refcounted(sk)) { + if (!refcount_inc_not_zero(&sk->sk_refcnt)) + return -ENOTCONN; + + /* drop refcount on skb_orphan */ + skb->destructor = sock_edemux; + } + } + entry = kmalloc(sizeof(*entry) + route_key_size, GFP_ATOMIC); if (!entry) return -ENOMEM; -- cgit v1.2.3 From db6140e5e35a48405e669353bd54042c1d4c3841 Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Mon, 28 Feb 2022 11:23:49 +0200 Subject: net/sched: act_ct: Fix flow table lookup failure with no originating ifindex After cited commit optimizted hw insertion, flow table entries are populated with ifindex information which was intended to only be used for HW offload. This tuple ifindex is hashed in the flow table key, so it must be filled for lookup to be successful. But tuple ifindex is only relevant for the netfilter flowtables (nft), so it's not filled in act_ct flow table lookup, resulting in lookup failure, and no SW offload and no offload teardown for TCP connection FIN/RST packets. To fix this, add new tc ifindex field to tuple, which will only be used for offloading, not for lookup, as it will not be part of the tuple hash. Fixes: 9795ded7f924 ("net/sched: act_ct: Fill offloading tuple iifidx") Signed-off-by: Paul Blakey Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_flow_table.h | 6 +++++- net/netfilter/nf_flow_table_offload.c | 6 +++++- net/sched/act_ct.c | 13 +++++++++---- 3 files changed, 19 insertions(+), 6 deletions(-) (limited to 'net/netfilter') diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index a3647fadf1cc..bd59e950f4d6 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -96,6 +96,7 @@ enum flow_offload_xmit_type { FLOW_OFFLOAD_XMIT_NEIGH, FLOW_OFFLOAD_XMIT_XFRM, FLOW_OFFLOAD_XMIT_DIRECT, + FLOW_OFFLOAD_XMIT_TC, }; #define NF_FLOW_TABLE_ENCAP_MAX 2 @@ -127,7 +128,7 @@ struct flow_offload_tuple { struct { } __hash; u8 dir:2, - xmit_type:2, + xmit_type:3, encap_num:2, in_vlan_ingress:2; u16 mtu; @@ -142,6 +143,9 @@ struct flow_offload_tuple { u8 h_source[ETH_ALEN]; u8 h_dest[ETH_ALEN]; } out; + struct { + u32 iifidx; + } tc; }; }; diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index b561e0a44a45..fc4265acd9c4 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -110,7 +110,11 @@ static int nf_flow_rule_match(struct nf_flow_match *match, nf_flow_rule_lwt_match(match, tun_info); } - key->meta.ingress_ifindex = tuple->iifidx; + if (tuple->xmit_type == FLOW_OFFLOAD_XMIT_TC) + key->meta.ingress_ifindex = tuple->tc.iifidx; + else + key->meta.ingress_ifindex = tuple->iifidx; + mask->meta.ingress_ifindex = 0xffffffff; if (tuple->encap_num > 0 && !(tuple->in_vlan_ingress & BIT(0)) && diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 33e70d60f0bf..ec19f625863a 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -361,6 +361,13 @@ static void tcf_ct_flow_table_put(struct tcf_ct_params *params) } } +static void tcf_ct_flow_tc_ifidx(struct flow_offload *entry, + struct nf_conn_act_ct_ext *act_ct_ext, u8 dir) +{ + entry->tuplehash[dir].tuple.xmit_type = FLOW_OFFLOAD_XMIT_TC; + entry->tuplehash[dir].tuple.tc.iifidx = act_ct_ext->ifindex[dir]; +} + static void tcf_ct_flow_table_add(struct tcf_ct_flow_table *ct_ft, struct nf_conn *ct, bool tcp) @@ -385,10 +392,8 @@ static void tcf_ct_flow_table_add(struct tcf_ct_flow_table *ct_ft, act_ct_ext = nf_conn_act_ct_ext_find(ct); if (act_ct_ext) { - entry->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.iifidx = - act_ct_ext->ifindex[IP_CT_DIR_ORIGINAL]; - entry->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.iifidx = - act_ct_ext->ifindex[IP_CT_DIR_REPLY]; + tcf_ct_flow_tc_ifidx(entry, act_ct_ext, FLOW_OFFLOAD_DIR_ORIGINAL); + tcf_ct_flow_tc_ifidx(entry, act_ct_ext, FLOW_OFFLOAD_DIR_REPLY); } err = flow_offload_add(&ct_ft->nf_ft, entry); -- cgit v1.2.3