From 282e5f8fe907dc3f2fbf9f2103b0e62ffc3a68a5 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 1 Jun 2022 10:47:35 +0200 Subject: netfilter: nat: really support inet nat without l3 address When no l3 address is given, priv->family is set to NFPROTO_INET and the evaluation function isn't called. Call it too so l4-only rewrite can work. Also add a test case for this. Fixes: a33f387ecd5aa ("netfilter: nft_nat: allow to specify layer 4 protocol NAT only") Reported-by: Yi Chen Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_nat.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index 4394df4bc99b..e5fd6995e4bf 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -335,7 +335,8 @@ static void nft_nat_inet_eval(const struct nft_expr *expr, { const struct nft_nat *priv = nft_expr_priv(expr); - if (priv->family == nft_pf(pkt)) + if (priv->family == nft_pf(pkt) || + priv->family == NFPROTO_INET) nft_nat_eval(expr, regs, pkt); } -- cgit v1.2.3 From ab5e5c062f67c5ae8cd07f0632ffa62dc0e7d169 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 1 Jun 2022 16:00:00 +0200 Subject: netfilter: nf_tables: use kfree_rcu(ptr, rcu) to release hooks in clean_net path Use kfree_rcu(ptr, rcu) variant instead as described by ae089831ff28 ("netfilter: nf_tables: prefer kfree_rcu(ptr, rcu) variant"). Fixes: f9a43007d3f7 ("netfilter: nf_tables: double hook unregistration in netns path") Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 746be13438ef..129d3ebd6ce5 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -7332,7 +7332,7 @@ static void __nft_unregister_flowtable_net_hooks(struct net *net, nf_unregister_net_hook(net, &hook->ops); if (release_netdev) { list_del(&hook->list); - kfree_rcu(hook); + kfree_rcu(hook, rcu); } } } -- cgit v1.2.3 From b6d9014a3335194590abdd2a2471ef5147a67645 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 30 May 2022 18:40:06 +0200 Subject: netfilter: nf_tables: delete flowtable hooks via transaction list Remove inactive bool field in nft_hook object that was introduced in abadb2f865d7 ("netfilter: nf_tables: delete devices from flowtable"). Move stale flowtable hooks to transaction list instead. Deleting twice the same device does not result in ENOENT. Fixes: abadb2f865d7 ("netfilter: nf_tables: delete devices from flowtable") Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 1 - net/netfilter/nf_tables_api.c | 31 ++++++------------------------- 2 files changed, 6 insertions(+), 26 deletions(-) (limited to 'net') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 20af9d3557b9..279ae0fff7ad 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1090,7 +1090,6 @@ struct nft_stats { struct nft_hook { struct list_head list; - bool inactive; struct nf_hook_ops ops; struct rcu_head rcu; }; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 129d3ebd6ce5..30588349f96c 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1914,7 +1914,6 @@ static struct nft_hook *nft_netdev_hook_alloc(struct net *net, goto err_hook_dev; } hook->ops.dev = dev; - hook->inactive = false; return hook; @@ -7618,6 +7617,7 @@ static int nft_delflowtable_hook(struct nft_ctx *ctx, { const struct nlattr * const *nla = ctx->nla; struct nft_flowtable_hook flowtable_hook; + LIST_HEAD(flowtable_del_list); struct nft_hook *this, *hook; struct nft_trans *trans; int err; @@ -7633,7 +7633,7 @@ static int nft_delflowtable_hook(struct nft_ctx *ctx, err = -ENOENT; goto err_flowtable_del_hook; } - hook->inactive = true; + list_move(&hook->list, &flowtable_del_list); } trans = nft_trans_alloc(ctx, NFT_MSG_DELFLOWTABLE, @@ -7646,6 +7646,7 @@ static int nft_delflowtable_hook(struct nft_ctx *ctx, nft_trans_flowtable(trans) = flowtable; nft_trans_flowtable_update(trans) = true; INIT_LIST_HEAD(&nft_trans_flowtable_hooks(trans)); + list_splice(&flowtable_del_list, &nft_trans_flowtable_hooks(trans)); nft_flowtable_hook_release(&flowtable_hook); nft_trans_commit_list_add_tail(ctx->net, trans); @@ -7653,13 +7654,7 @@ static int nft_delflowtable_hook(struct nft_ctx *ctx, return 0; err_flowtable_del_hook: - list_for_each_entry(this, &flowtable_hook.list, list) { - hook = nft_hook_list_find(&flowtable->hook_list, this); - if (!hook) - break; - - hook->inactive = false; - } + list_splice(&flowtable_del_list, &flowtable->hook_list); nft_flowtable_hook_release(&flowtable_hook); return err; @@ -8563,17 +8558,6 @@ void nft_chain_del(struct nft_chain *chain) list_del_rcu(&chain->list); } -static void nft_flowtable_hooks_del(struct nft_flowtable *flowtable, - struct list_head *hook_list) -{ - struct nft_hook *hook, *next; - - list_for_each_entry_safe(hook, next, &flowtable->hook_list, list) { - if (hook->inactive) - list_move(&hook->list, hook_list); - } -} - static void nf_tables_module_autoload_cleanup(struct net *net) { struct nftables_pernet *nft_net = nft_pernet(net); @@ -8918,8 +8902,6 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) break; case NFT_MSG_DELFLOWTABLE: if (nft_trans_flowtable_update(trans)) { - nft_flowtable_hooks_del(nft_trans_flowtable(trans), - &nft_trans_flowtable_hooks(trans)); nf_tables_flowtable_notify(&trans->ctx, nft_trans_flowtable(trans), &nft_trans_flowtable_hooks(trans), @@ -9000,7 +8982,6 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) struct nftables_pernet *nft_net = nft_pernet(net); struct nft_trans *trans, *next; struct nft_trans_elem *te; - struct nft_hook *hook; if (action == NFNL_ABORT_VALIDATE && nf_tables_validate(net) < 0) @@ -9131,8 +9112,8 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) break; case NFT_MSG_DELFLOWTABLE: if (nft_trans_flowtable_update(trans)) { - list_for_each_entry(hook, &nft_trans_flowtable(trans)->hook_list, list) - hook->inactive = false; + list_splice(&nft_trans_flowtable_hooks(trans), + &nft_trans_flowtable(trans)->hook_list); } else { trans->ctx.table->use++; nft_clear(trans->ctx.net, nft_trans_flowtable(trans)); -- cgit v1.2.3 From 2c9e4559773c261900c674a86b8e455911675d71 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 1 Jun 2022 17:49:36 +0200 Subject: netfilter: nf_tables: always initialize flowtable hook list in transaction The hook list is used if nft_trans_flowtable_update(trans) == true. However, initialize this list for other cases for safety reasons. Fixes: 78d9f48f7f44 ("netfilter: nf_tables: add devices to existing flowtable") Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net') diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 30588349f96c..2faa77cd2fe2 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -544,6 +544,7 @@ static int nft_trans_flowtable_add(struct nft_ctx *ctx, int msg_type, if (msg_type == NFT_MSG_NEWFLOWTABLE) nft_activate_next(ctx->net, flowtable); + INIT_LIST_HEAD(&nft_trans_flowtable_hooks(trans)); nft_trans_flowtable(trans) = flowtable; nft_trans_commit_list_add_tail(ctx->net, trans); -- cgit v1.2.3 From c271cc9febaaa1bcbc0842d1ee30466aa6148ea8 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sun, 5 Jun 2022 13:40:06 +0200 Subject: netfilter: nf_tables: release new hooks on unsupported flowtable flags Release the list of new hooks that are pending to be registered in case that unsupported flowtable flags are provided. Fixes: 78d9f48f7f44 ("netfilter: nf_tables: add devices to existing flowtable") Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'net') diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 2faa77cd2fe2..252796a99f5e 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -7433,11 +7433,15 @@ static int nft_flowtable_update(struct nft_ctx *ctx, const struct nlmsghdr *nlh, if (nla[NFTA_FLOWTABLE_FLAGS]) { flags = ntohl(nla_get_be32(nla[NFTA_FLOWTABLE_FLAGS])); - if (flags & ~NFT_FLOWTABLE_MASK) - return -EOPNOTSUPP; + if (flags & ~NFT_FLOWTABLE_MASK) { + err = -EOPNOTSUPP; + goto err_flowtable_update_hook; + } if ((flowtable->data.flags & NFT_FLOWTABLE_HW_OFFLOAD) ^ - (flags & NFT_FLOWTABLE_HW_OFFLOAD)) - return -EOPNOTSUPP; + (flags & NFT_FLOWTABLE_HW_OFFLOAD)) { + err = -EOPNOTSUPP; + goto err_flowtable_update_hook; + } } else { flags = flowtable->data.flags; } -- cgit v1.2.3 From 9dd732e0bdf538b1b76dc7c157e2b5e560ff30d3 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 6 Jun 2022 17:15:57 +0200 Subject: netfilter: nf_tables: memleak flow rule from commit path Abort path release flow rule object, however, commit path does not. Update code to destroy these objects before releasing the transaction. Fixes: c9626a2cbdb2 ("netfilter: nf_tables: add hardware offload support") Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'net') diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 252796a99f5e..1a6a21bfb18d 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -8329,6 +8329,9 @@ static void nft_commit_release(struct nft_trans *trans) nf_tables_chain_destroy(&trans->ctx); break; case NFT_MSG_DELRULE: + if (trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD) + nft_flow_rule_destroy(nft_trans_flow_rule(trans)); + nf_tables_rule_destroy(&trans->ctx, nft_trans_rule(trans)); break; case NFT_MSG_DELSET: @@ -8817,6 +8820,9 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nf_tables_rule_notify(&trans->ctx, nft_trans_rule(trans), NFT_MSG_NEWRULE); + if (trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD) + nft_flow_rule_destroy(nft_trans_flow_rule(trans)); + nft_trans_destroy(trans); break; case NFT_MSG_DELRULE: -- cgit v1.2.3 From 3a41c64d9c1185a2f3a184015e2a9b78bfc99c71 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 6 Jun 2022 17:31:29 +0200 Subject: netfilter: nf_tables: bail out early if hardware offload is not supported If user requests for NFT_CHAIN_HW_OFFLOAD, then check if either device provides the .ndo_setup_tc interface or there is an indirect flow block that has been registered. Otherwise, bail out early from the preparation phase. Moreover, validate that family == NFPROTO_NETDEV and hook is NF_NETDEV_INGRESS. Fixes: c9626a2cbdb2 ("netfilter: nf_tables: add hardware offload support") Signed-off-by: Pablo Neira Ayuso --- include/net/flow_offload.h | 1 + include/net/netfilter/nf_tables_offload.h | 2 +- net/core/flow_offload.c | 6 ++++++ net/netfilter/nf_tables_api.c | 2 +- net/netfilter/nf_tables_offload.c | 23 ++++++++++++++++++++++- 5 files changed, 31 insertions(+), 3 deletions(-) (limited to 'net') diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index 021778a7e1af..6484095a8c01 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -612,5 +612,6 @@ int flow_indr_dev_setup_offload(struct net_device *dev, struct Qdisc *sch, enum tc_setup_type type, void *data, struct flow_block_offload *bo, void (*cleanup)(struct flow_block_cb *block_cb)); +bool flow_indr_dev_exists(void); #endif /* _NET_FLOW_OFFLOAD_H */ diff --git a/include/net/netfilter/nf_tables_offload.h b/include/net/netfilter/nf_tables_offload.h index 797147843958..3568b6a2f5f0 100644 --- a/include/net/netfilter/nf_tables_offload.h +++ b/include/net/netfilter/nf_tables_offload.h @@ -92,7 +92,7 @@ int nft_flow_rule_offload_commit(struct net *net); NFT_OFFLOAD_MATCH(__key, __base, __field, __len, __reg) \ memset(&(__reg)->mask, 0xff, (__reg)->len); -int nft_chain_offload_priority(struct nft_base_chain *basechain); +bool nft_chain_offload_support(const struct nft_base_chain *basechain); int nft_offload_init(void); void nft_offload_exit(void); diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c index 73f68d4625f3..929f6379a279 100644 --- a/net/core/flow_offload.c +++ b/net/core/flow_offload.c @@ -595,3 +595,9 @@ int flow_indr_dev_setup_offload(struct net_device *dev, struct Qdisc *sch, return (bo && list_empty(&bo->cb_list)) ? -EOPNOTSUPP : count; } EXPORT_SYMBOL(flow_indr_dev_setup_offload); + +bool flow_indr_dev_exists(void) +{ + return !list_empty(&flow_block_indr_dev_list); +} +EXPORT_SYMBOL(flow_indr_dev_exists); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 1a6a21bfb18d..51144fc66889 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2166,7 +2166,7 @@ static int nft_basechain_init(struct nft_base_chain *basechain, u8 family, chain->flags |= NFT_CHAIN_BASE | flags; basechain->policy = NF_ACCEPT; if (chain->flags & NFT_CHAIN_HW_OFFLOAD && - nft_chain_offload_priority(basechain) < 0) + !nft_chain_offload_support(basechain)) return -EOPNOTSUPP; flow_block_init(&basechain->flow_block); diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c index 2d36952b1392..910ef881c3b8 100644 --- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -208,7 +208,7 @@ static int nft_setup_cb_call(enum tc_setup_type type, void *type_data, return 0; } -int nft_chain_offload_priority(struct nft_base_chain *basechain) +static int nft_chain_offload_priority(const struct nft_base_chain *basechain) { if (basechain->ops.priority <= 0 || basechain->ops.priority > USHRT_MAX) @@ -217,6 +217,27 @@ int nft_chain_offload_priority(struct nft_base_chain *basechain) return 0; } +bool nft_chain_offload_support(const struct nft_base_chain *basechain) +{ + struct net_device *dev; + struct nft_hook *hook; + + if (nft_chain_offload_priority(basechain) < 0) + return false; + + list_for_each_entry(hook, &basechain->hook_list, list) { + if (hook->ops.pf != NFPROTO_NETDEV || + hook->ops.hooknum != NF_NETDEV_INGRESS) + return false; + + dev = hook->ops.dev; + if (!dev->netdev_ops->ndo_setup_tc && !flow_indr_dev_exists()) + return false; + } + + return true; +} + static void nft_flow_cls_offload_setup(struct flow_cls_offload *cls_flow, const struct nft_base_chain *basechain, const struct nft_rule *rule, -- cgit v1.2.3 From 662a80946ce13633ae90a55379f1346c10f0c432 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Sun, 5 Jun 2022 16:23:25 -0700 Subject: af_unix: Fix a data-race in unix_dgram_peer_wake_me(). unix_dgram_poll() calls unix_dgram_peer_wake_me() without `other`'s lock held and check if its receive queue is full. Here we need to use unix_recvq_full_lockless() instead of unix_recvq_full(), otherwise KCSAN will report a data-race. Fixes: 7d267278a9ec ("unix: avoid use-after-free in ep_remove_wait_queue") Signed-off-by: Kuniyuki Iwashima Link: https://lore.kernel.org/r/20220605232325.11804-1-kuniyu@amazon.com Signed-off-by: Paolo Abeni --- net/unix/af_unix.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 654dcef7cfb3..2206e6f8902d 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -490,7 +490,7 @@ static int unix_dgram_peer_wake_me(struct sock *sk, struct sock *other) * -ECONNREFUSED. Otherwise, if we haven't queued any skbs * to other and its full, we will hang waiting for POLLOUT. */ - if (unix_recvq_full(other) && !sock_flag(other, SOCK_DEAD)) + if (unix_recvq_full_lockless(other) && !sock_flag(other, SOCK_DEAD)) return 1; if (connected) -- cgit v1.2.3 From d678cbd2f867a564a3c5b276c454e873f43f02f8 Mon Sep 17 00:00:00 2001 From: Maciej Fijalkowski Date: Tue, 7 Jun 2022 16:22:00 +0200 Subject: xsk: Fix handling of invalid descriptors in XSK TX batching API xdpxceiver run on a AF_XDP ZC enabled driver revealed a problem with XSK Tx batching API. There is a test that checks how invalid Tx descriptors are handled by AF_XDP. Each valid descriptor is followed by invalid one on Tx side whereas the Rx side expects only to receive a set of valid descriptors. In current xsk_tx_peek_release_desc_batch() function, the amount of available descriptors is hidden inside xskq_cons_peek_desc_batch(). This can be problematic in cases where invalid descriptors are present due to the fact that xskq_cons_peek_desc_batch() returns only a count of valid descriptors. This means that it is impossible to properly update XSK ring state when calling xskq_cons_release_n(). To address this issue, pull out the contents of xskq_cons_peek_desc_batch() so that callers (currently only xsk_tx_peek_release_desc_batch()) will always be able to update the state of ring properly, as total count of entries is now available and use this value as an argument in xskq_cons_release_n(). By doing so, xskq_cons_peek_desc_batch() can be dropped altogether. Fixes: 9349eb3a9d2a ("xsk: Introduce batched Tx descriptor interfaces") Signed-off-by: Maciej Fijalkowski Signed-off-by: Daniel Borkmann Acked-by: Magnus Karlsson Link: https://lore.kernel.org/bpf/20220607142200.576735-1-maciej.fijalkowski@intel.com --- net/xdp/xsk.c | 5 +++-- net/xdp/xsk_queue.h | 8 -------- 2 files changed, 3 insertions(+), 10 deletions(-) (limited to 'net') diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index e0a4526ab66b..19ac872a6624 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -373,7 +373,8 @@ u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, u32 max_entries) goto out; } - nb_pkts = xskq_cons_peek_desc_batch(xs->tx, pool, max_entries); + max_entries = xskq_cons_nb_entries(xs->tx, max_entries); + nb_pkts = xskq_cons_read_desc_batch(xs->tx, pool, max_entries); if (!nb_pkts) { xs->tx->queue_empty_descs++; goto out; @@ -389,7 +390,7 @@ u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, u32 max_entries) if (!nb_pkts) goto out; - xskq_cons_release_n(xs->tx, nb_pkts); + xskq_cons_release_n(xs->tx, max_entries); __xskq_cons_release(xs->tx); xs->sk.sk_write_space(&xs->sk); diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index a794410989cc..fb20bf7207cf 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -282,14 +282,6 @@ static inline bool xskq_cons_peek_desc(struct xsk_queue *q, return xskq_cons_read_desc(q, desc, pool); } -static inline u32 xskq_cons_peek_desc_batch(struct xsk_queue *q, struct xsk_buff_pool *pool, - u32 max) -{ - u32 entries = xskq_cons_nb_entries(q, max); - - return xskq_cons_read_desc_batch(q, pool, entries); -} - /* To improve performance in the xskq_cons_release functions, only update local state here. * Reflect this to global state when we get new entries from the ring in * xskq_cons_get_entries() and whenever Rx or Tx processing are completed in the NAPI loop. -- cgit v1.2.3 From 4a388f08d8784af48f352193d2b72aaf167a57a1 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 6 Jun 2022 13:53:54 +0900 Subject: net: xfrm: unexport __init-annotated xfrm4_protocol_init() EXPORT_SYMBOL and __init is a bad combination because the .init.text section is freed up after the initialization. Hence, modules cannot use symbols annotated __init. The access to a freed symbol may end up with kernel panic. modpost used to detect it, but it has been broken for a decade. Recently, I fixed modpost so it started to warn it again, then this showed up in linux-next builds. There are two ways to fix it: - Remove __init - Remove EXPORT_SYMBOL I chose the latter for this case because the only in-tree call-site, net/ipv4/xfrm4_policy.c is never compiled as modular. (CONFIG_XFRM is boolean) Fixes: 2f32b51b609f ("xfrm: Introduce xfrm_input_afinfo to access the the callbacks properly") Reported-by: Stephen Rothwell Signed-off-by: Masahiro Yamada Acked-by: Steffen Klassert Signed-off-by: Jakub Kicinski --- net/ipv4/xfrm4_protocol.c | 1 - 1 file changed, 1 deletion(-) (limited to 'net') diff --git a/net/ipv4/xfrm4_protocol.c b/net/ipv4/xfrm4_protocol.c index 2fe5860c21d6..b146ce88c5d0 100644 --- a/net/ipv4/xfrm4_protocol.c +++ b/net/ipv4/xfrm4_protocol.c @@ -304,4 +304,3 @@ void __init xfrm4_protocol_init(void) { xfrm_input_register_afinfo(&xfrm4_input_afinfo); } -EXPORT_SYMBOL(xfrm4_protocol_init); -- cgit v1.2.3 From 5801f064e35181c71857a80ff18af4dbec3c5f5c Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 6 Jun 2022 13:53:55 +0900 Subject: net: ipv6: unexport __init-annotated seg6_hmac_init() EXPORT_SYMBOL and __init is a bad combination because the .init.text section is freed up after the initialization. Hence, modules cannot use symbols annotated __init. The access to a freed symbol may end up with kernel panic. modpost used to detect it, but it has been broken for a decade. Recently, I fixed modpost so it started to warn it again, then this showed up in linux-next builds. There are two ways to fix it: - Remove __init - Remove EXPORT_SYMBOL I chose the latter for this case because the caller (net/ipv6/seg6.c) and the callee (net/ipv6/seg6_hmac.c) belong to the same module. It seems an internal function call in ipv6.ko. Fixes: bf355b8d2c30 ("ipv6: sr: add core files for SR HMAC support") Reported-by: Stephen Rothwell Signed-off-by: Masahiro Yamada Signed-off-by: Jakub Kicinski --- net/ipv6/seg6_hmac.c | 1 - 1 file changed, 1 deletion(-) (limited to 'net') diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c index 29bc4e7c3046..6de01185cc68 100644 --- a/net/ipv6/seg6_hmac.c +++ b/net/ipv6/seg6_hmac.c @@ -399,7 +399,6 @@ int __init seg6_hmac_init(void) { return seg6_hmac_init_algo(); } -EXPORT_SYMBOL(seg6_hmac_init); int __net_init seg6_hmac_net_init(struct net *net) { -- cgit v1.2.3 From f93431c86b631bbca5614c66f966bf3ddb3c2803 Mon Sep 17 00:00:00 2001 From: Wang Yufen Date: Tue, 7 Jun 2022 20:00:27 +0800 Subject: ipv6: Fix signed integer overflow in __ip6_append_data Resurrect ubsan overflow checks and ubsan report this warning, fix it by change the variable [length] type to size_t. UBSAN: signed-integer-overflow in net/ipv6/ip6_output.c:1489:19 2147479552 + 8567 cannot be represented in type 'int' CPU: 0 PID: 253 Comm: err Not tainted 5.16.0+ #1 Hardware name: linux,dummy-virt (DT) Call trace: dump_backtrace+0x214/0x230 show_stack+0x30/0x78 dump_stack_lvl+0xf8/0x118 dump_stack+0x18/0x30 ubsan_epilogue+0x18/0x60 handle_overflow+0xd0/0xf0 __ubsan_handle_add_overflow+0x34/0x44 __ip6_append_data.isra.48+0x1598/0x1688 ip6_append_data+0x128/0x260 udpv6_sendmsg+0x680/0xdd0 inet6_sendmsg+0x54/0x90 sock_sendmsg+0x70/0x88 ____sys_sendmsg+0xe8/0x368 ___sys_sendmsg+0x98/0xe0 __sys_sendmmsg+0xf4/0x3b8 __arm64_sys_sendmmsg+0x34/0x48 invoke_syscall+0x64/0x160 el0_svc_common.constprop.4+0x124/0x300 do_el0_svc+0x44/0xc8 el0_svc+0x3c/0x1e8 el0t_64_sync_handler+0x88/0xb0 el0t_64_sync+0x16c/0x170 Changes since v1: -Change the variable [length] type to unsigned, as Eric Dumazet suggested. Changes since v2: -Don't change exthdrlen type in ip6_make_skb, as Paolo Abeni suggested. Changes since v3: -Don't change ulen type in udpv6_sendmsg and l2tp_ip6_sendmsg, as Jakub Kicinski suggested. Reported-by: Hulk Robot Signed-off-by: Wang Yufen Link: https://lore.kernel.org/r/20220607120028.845916-1-wangyufen@huawei.com Signed-off-by: Jakub Kicinski --- include/net/ipv6.h | 4 ++-- net/ipv6/ip6_output.c | 6 +++--- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'net') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 5b38bf1a586b..de9dcc5652c4 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -1063,7 +1063,7 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr); int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), - void *from, int length, int transhdrlen, + void *from, size_t length, int transhdrlen, struct ipcm6_cookie *ipc6, struct flowi6 *fl6, struct rt6_info *rt, unsigned int flags); @@ -1079,7 +1079,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, struct sk_buff_head *queue, struct sk_buff *ip6_make_skb(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), - void *from, int length, int transhdrlen, + void *from, size_t length, int transhdrlen, struct ipcm6_cookie *ipc6, struct rt6_info *rt, unsigned int flags, struct inet_cork_full *cork); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 4081b12a01ff..77e3f5970ce4 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1450,7 +1450,7 @@ static int __ip6_append_data(struct sock *sk, struct page_frag *pfrag, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), - void *from, int length, int transhdrlen, + void *from, size_t length, int transhdrlen, unsigned int flags, struct ipcm6_cookie *ipc6) { struct sk_buff *skb, *skb_prev = NULL; @@ -1798,7 +1798,7 @@ error: int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), - void *from, int length, int transhdrlen, + void *from, size_t length, int transhdrlen, struct ipcm6_cookie *ipc6, struct flowi6 *fl6, struct rt6_info *rt, unsigned int flags) { @@ -1995,7 +1995,7 @@ EXPORT_SYMBOL_GPL(ip6_flush_pending_frames); struct sk_buff *ip6_make_skb(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), - void *from, int length, int transhdrlen, + void *from, size_t length, int transhdrlen, struct ipcm6_cookie *ipc6, struct rt6_info *rt, unsigned int flags, struct inet_cork_full *cork) { -- cgit v1.2.3 From f638a84afef3dfe10554c51820c16e39a278c915 Mon Sep 17 00:00:00 2001 From: Wang Yufen Date: Tue, 7 Jun 2022 20:00:28 +0800 Subject: ipv6: Fix signed integer overflow in l2tp_ip6_sendmsg When len >= INT_MAX - transhdrlen, ulen = len + transhdrlen will be overflow. To fix, we can follow what udpv6 does and subtract the transhdrlen from the max. Signed-off-by: Wang Yufen Link: https://lore.kernel.org/r/20220607120028.845916-2-wangyufen@huawei.com Signed-off-by: Jakub Kicinski --- net/l2tp/l2tp_ip6.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index c6ff8bf9b55f..9dbd801ddb98 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -504,14 +504,15 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) struct ipcm6_cookie ipc6; int addr_len = msg->msg_namelen; int transhdrlen = 4; /* zero session-id */ - int ulen = len + transhdrlen; + int ulen; int err; /* Rough check on arithmetic overflow, * better check is made in ip6_append_data(). */ - if (len > INT_MAX) + if (len > INT_MAX - transhdrlen) return -EMSGSIZE; + ulen = len + transhdrlen; /* Mirror BSD error message compatibility */ if (msg->msg_flags & MSG_OOB) -- cgit v1.2.3 From 8d21e9963bec1aad2280cdd034c8993033ef2948 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Mon, 6 Jun 2022 09:21:07 -0400 Subject: ip_gre: test csum_start instead of transport header GRE with TUNNEL_CSUM will apply local checksum offload on CHECKSUM_PARTIAL packets. ipgre_xmit must validate csum_start after an optional skb_pull, else lco_csum may trigger an overflow. The original check was if (csum && skb_checksum_start(skb) < skb->data) return -EINVAL; This had false positives when skb_checksum_start is undefined: when ip_summed is not CHECKSUM_PARTIAL. A discussed refinement was straightforward if (csum && skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_start(skb) < skb->data) return -EINVAL; But was eventually revised more thoroughly: - restrict the check to the only branch where needed, in an uncommon GRE path that uses header_ops and calls skb_pull. - test skb_transport_header, which is set along with csum_start in skb_partial_csum_set in the normal header_ops datapath. Turns out skbs can arrive in this branch without the transport header set, e.g., through BPF redirection. Revise the check back to check csum_start directly, and only if CHECKSUM_PARTIAL. Do leave the check in the updated location. Check field regardless of whether TUNNEL_CSUM is configured. Link: https://lore.kernel.org/netdev/YS+h%2FtqCJJiQei+W@shredder/ Link: https://lore.kernel.org/all/20210902193447.94039-2-willemdebruijn.kernel@gmail.com/T/#u Fixes: 8a0ed250f911 ("ip_gre: validate csum_start only on pull") Reported-by: syzbot Signed-off-by: Willem de Bruijn Reviewed-by: Eric Dumazet Reviewed-by: Alexander Duyck Link: https://lore.kernel.org/r/20220606132107.3582565-1-willemdebruijn.kernel@gmail.com Signed-off-by: Jakub Kicinski --- net/ipv4/ip_gre.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'net') diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 7e474a85deaf..3b9cd487075a 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -629,21 +629,20 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb, } if (dev->header_ops) { - const int pull_len = tunnel->hlen + sizeof(struct iphdr); - if (skb_cow_head(skb, 0)) goto free_skb; tnl_params = (const struct iphdr *)skb->data; - if (pull_len > skb_transport_offset(skb)) - goto free_skb; - /* Pull skb since ip_tunnel_xmit() needs skb->data pointing * to gre header. */ - skb_pull(skb, pull_len); + skb_pull(skb, tunnel->hlen + sizeof(struct iphdr)); skb_reset_mac_header(skb); + + if (skb->ip_summed == CHECKSUM_PARTIAL && + skb_checksum_start(skb) < skb->data) + goto free_skb; } else { if (skb_cow_head(skb, dev->needed_headroom)) goto free_skb; -- cgit v1.2.3 From 2061ecfdf2350994e5b61c43e50e98a7a70e95ee Mon Sep 17 00:00:00 2001 From: Ilya Maximets Date: Tue, 7 Jun 2022 00:11:40 +0200 Subject: net: openvswitch: fix misuse of the cached connection on tuple changes If packet headers changed, the cached nfct is no longer relevant for the packet and attempt to re-use it leads to the incorrect packet classification. This issue is causing broken connectivity in OpenStack deployments with OVS/OVN due to hairpin traffic being unexpectedly dropped. The setup has datapath flows with several conntrack actions and tuple changes between them: actions:ct(commit,zone=8,mark=0/0x1,nat(src)), set(eth(src=00:00:00:00:00:01,dst=00:00:00:00:00:06)), set(ipv4(src=172.18.2.10,dst=192.168.100.6,ttl=62)), ct(zone=8),recirc(0x4) After the first ct() action the packet headers are almost fully re-written. The next ct() tries to re-use the existing nfct entry and marks the packet as invalid, so it gets dropped later in the pipeline. Clearing the cached conntrack entry whenever packet tuple is changed to avoid the issue. The flow key should not be cleared though, because we should still be able to match on the ct_state if the recirculation happens after the tuple change but before the next ct() action. Cc: stable@vger.kernel.org Fixes: 7f8a436eaa2c ("openvswitch: Add conntrack action") Reported-by: Frode Nordahl Link: https://mail.openvswitch.org/pipermail/ovs-discuss/2022-May/051829.html Link: https://bugs.launchpad.net/ubuntu/+source/ovn/+bug/1967856 Signed-off-by: Ilya Maximets Link: https://lore.kernel.org/r/20220606221140.488984-1-i.maximets@ovn.org Signed-off-by: Jakub Kicinski --- net/openvswitch/actions.c | 6 ++++++ net/openvswitch/conntrack.c | 4 +++- 2 files changed, 9 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 1b5d73079dc9..868db4669a29 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -373,6 +373,7 @@ static void set_ip_addr(struct sk_buff *skb, struct iphdr *nh, update_ip_l4_checksum(skb, nh, *addr, new_addr); csum_replace4(&nh->check, *addr, new_addr); skb_clear_hash(skb); + ovs_ct_clear(skb, NULL); *addr = new_addr; } @@ -420,6 +421,7 @@ static void set_ipv6_addr(struct sk_buff *skb, u8 l4_proto, update_ipv6_checksum(skb, l4_proto, addr, new_addr); skb_clear_hash(skb); + ovs_ct_clear(skb, NULL); memcpy(addr, new_addr, sizeof(__be32[4])); } @@ -660,6 +662,7 @@ static int set_nsh(struct sk_buff *skb, struct sw_flow_key *flow_key, static void set_tp_port(struct sk_buff *skb, __be16 *port, __be16 new_port, __sum16 *check) { + ovs_ct_clear(skb, NULL); inet_proto_csum_replace2(check, skb, *port, new_port, false); *port = new_port; } @@ -699,6 +702,7 @@ static int set_udp(struct sk_buff *skb, struct sw_flow_key *flow_key, uh->dest = dst; flow_key->tp.src = src; flow_key->tp.dst = dst; + ovs_ct_clear(skb, NULL); } skb_clear_hash(skb); @@ -761,6 +765,8 @@ static int set_sctp(struct sk_buff *skb, struct sw_flow_key *flow_key, sh->checksum = old_csum ^ old_correct_csum ^ new_csum; skb_clear_hash(skb); + ovs_ct_clear(skb, NULL); + flow_key->tp.src = sh->source; flow_key->tp.dst = sh->dest; diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 4a947c13c813..4e70df91d0f2 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -1342,7 +1342,9 @@ int ovs_ct_clear(struct sk_buff *skb, struct sw_flow_key *key) nf_ct_put(ct); nf_ct_set(skb, NULL, IP_CT_UNTRACKED); - ovs_ct_fill_key(skb, key, false); + + if (key) + ovs_ct_fill_key(skb, key, false); return 0; } -- cgit v1.2.3 From e67b72b90b7e19a4be4d9c29f3feea6f58ab43f8 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Tue, 7 Jun 2022 15:02:14 +0800 Subject: tcp: use alloc_large_system_hash() to allocate table_perturb In our server, there may be no high order (>= 6) memory since we reserve lots of HugeTLB pages when booting. Then the system panic. So use alloc_large_system_hash() to allocate table_perturb. Fixes: e9261476184b ("tcp: dynamically allocate the perturb table used by source ports") Signed-off-by: Muchun Song Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20220607070214.94443-1-songmuchun@bytedance.com Signed-off-by: Jakub Kicinski --- net/ipv4/inet_hashtables.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'net') diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index e8de5e699b3f..545f91b6cb5e 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -1026,10 +1026,12 @@ void __init inet_hashinfo2_init(struct inet_hashinfo *h, const char *name, init_hashinfo_lhash2(h); /* this one is used for source ports of outgoing connections */ - table_perturb = kmalloc_array(INET_TABLE_PERTURB_SIZE, - sizeof(*table_perturb), GFP_KERNEL); - if (!table_perturb) - panic("TCP: failed to alloc table_perturb"); + table_perturb = alloc_large_system_hash("Table-perturb", + sizeof(*table_perturb), + INET_TABLE_PERTURB_SIZE, + 0, 0, NULL, NULL, + INET_TABLE_PERTURB_SIZE, + INET_TABLE_PERTURB_SIZE); } int inet_hashinfo2_init_mod(struct inet_hashinfo *h) -- cgit v1.2.3