From patchwork Fri Apr 21 23:01:52 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Pablo Neira Ayuso X-Patchwork-Id: 1772131 X-Patchwork-Delegate: pablo@netfilter.org Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@legolas.ozlabs.org Authentication-Results: legolas.ozlabs.org; spf=pass (sender SPF authorized) smtp.mailfrom=vger.kernel.org (client-ip=2620:137:e000::1:20; helo=out1.vger.email; envelope-from=netfilter-devel-owner@vger.kernel.org; receiver=) Received: from out1.vger.email (out1.vger.email [IPv6:2620:137:e000::1:20]) by legolas.ozlabs.org (Postfix) with ESMTP id 4Q395p0YTLz23tp for ; Sat, 22 Apr 2023 09:02:22 +1000 (AEST) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S233496AbjDUXCT (ORCPT ); Fri, 21 Apr 2023 19:02:19 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:52618 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S233239AbjDUXCS (ORCPT ); Fri, 21 Apr 2023 19:02:18 -0400 Received: from mail.netfilter.org (mail.netfilter.org [217.70.188.207]) by lindbergh.monkeyblade.net (Postfix) with ESMTP id 2CEA1E6E; Fri, 21 Apr 2023 16:02:17 -0700 (PDT) From: Pablo Neira Ayuso To: netfilter-devel@vger.kernel.org Cc: davem@davemloft.net, netdev@vger.kernel.org, kuba@kernel.org, pabeni@redhat.com, edumazet@google.com Subject: [PATCH net-next 01/20] netfilter: nft_exthdr: add boolean DCCP option matching Date: Sat, 22 Apr 2023 01:01:52 +0200 Message-Id: <20230421230211.214635-2-pablo@netfilter.org> X-Mailer: git-send-email 2.30.2 In-Reply-To: <20230421230211.214635-1-pablo@netfilter.org> References: <20230421230211.214635-1-pablo@netfilter.org> MIME-Version: 1.0 X-Spam-Status: No, score=-1.9 required=5.0 tests=BAYES_00,SPF_HELO_NONE, SPF_PASS,T_SCC_BODY_TEXT_LINE,URIBL_BLOCKED autolearn=ham autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on lindbergh.monkeyblade.net Precedence: bulk List-ID: X-Mailing-List: netfilter-devel@vger.kernel.org From: Jeremy Sowden The xt_dccp iptables module supports the matching of DCCP packets based on the presence or absence of DCCP options. Extend nft_exthdr to add this functionality to nftables. Link: https://bugzilla.netfilter.org/show_bug.cgi?id=930 Signed-off-by: Jeremy Sowden Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 2 + net/netfilter/nft_exthdr.c | 105 +++++++++++++++++++++++ 2 files changed, 107 insertions(+) diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index c4d4d8e42dc8..e059dc2644df 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -859,12 +859,14 @@ enum nft_exthdr_flags { * @NFT_EXTHDR_OP_TCP: match against tcp options * @NFT_EXTHDR_OP_IPV4: match against ipv4 options * @NFT_EXTHDR_OP_SCTP: match against sctp chunks + * @NFT_EXTHDR_OP_DCCP: match against dccp otions */ enum nft_exthdr_op { NFT_EXTHDR_OP_IPV6, NFT_EXTHDR_OP_TCPOPT, NFT_EXTHDR_OP_IPV4, NFT_EXTHDR_OP_SCTP, + NFT_EXTHDR_OP_DCCP, __NFT_EXTHDR_OP_MAX }; #define NFT_EXTHDR_OP_MAX (__NFT_EXTHDR_OP_MAX - 1) diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index a54a7f772cec..09b99a48e5c3 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -406,6 +407,81 @@ static void nft_exthdr_sctp_eval(const struct nft_expr *expr, regs->verdict.code = NFT_BREAK; } +static void nft_exthdr_dccp_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_exthdr *priv = nft_expr_priv(expr); + unsigned int thoff, dataoff, optoff, optlen, i; + u32 *dest = ®s->data[priv->dreg]; + const struct dccp_hdr *dh; + struct dccp_hdr _dh; + + if (pkt->tprot != IPPROTO_DCCP || pkt->fragoff) + goto err; + + thoff = nft_thoff(pkt); + + dh = skb_header_pointer(pkt->skb, thoff, sizeof(_dh), &_dh); + if (!dh) + goto err; + + dataoff = dh->dccph_doff * sizeof(u32); + optoff = __dccp_hdr_len(dh); + if (dataoff <= optoff) + goto err; + + optlen = dataoff - optoff; + + for (i = 0; i < optlen; ) { + /* Options 0 (DCCPO_PADDING) - 31 (DCCPO_MAX_RESERVED) are 1B in + * the length; the remaining options are at least 2B long. In + * all cases, the first byte contains the option type. In + * multi-byte options, the second byte contains the option + * length, which must be at least two: 1 for the type plus 1 for + * the length plus 0-253 for any following option data. We + * aren't interested in the option data, only the type and the + * length, so we don't need to read more than two bytes at a + * time. + */ + unsigned int buflen; + u8 buf[2], *bufp; + u8 type, len; + + buflen = optlen - i < sizeof(buf) ? optlen - i : sizeof(buf); + + bufp = skb_header_pointer(pkt->skb, thoff + optoff + i, buflen, + &buf); + if (!bufp) + goto err; + + type = bufp[0]; + + if (type == priv->type) { + *dest = 1; + return; + } + + if (type <= DCCPO_MAX_RESERVED) { + i++; + continue; + } + + if (buflen < 2) + goto err; + + len = bufp[1]; + + if (len < 2) + goto err; + + i += len; + } + +err: + *dest = 0; +} + static const struct nla_policy nft_exthdr_policy[NFTA_EXTHDR_MAX + 1] = { [NFTA_EXTHDR_DREG] = { .type = NLA_U32 }, [NFTA_EXTHDR_TYPE] = { .type = NLA_U8 }, @@ -557,6 +633,22 @@ static int nft_exthdr_ipv4_init(const struct nft_ctx *ctx, return 0; } +static int nft_exthdr_dccp_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_exthdr *priv = nft_expr_priv(expr); + int err = nft_exthdr_init(ctx, expr, tb); + + if (err < 0) + return err; + + if (!(priv->flags & NFT_EXTHDR_F_PRESENT)) + return -EOPNOTSUPP; + + return 0; +} + static int nft_exthdr_dump_common(struct sk_buff *skb, const struct nft_exthdr *priv) { if (nla_put_u8(skb, NFTA_EXTHDR_TYPE, priv->type)) @@ -686,6 +778,15 @@ static const struct nft_expr_ops nft_exthdr_sctp_ops = { .reduce = nft_exthdr_reduce, }; +static const struct nft_expr_ops nft_exthdr_dccp_ops = { + .type = &nft_exthdr_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_exthdr)), + .eval = nft_exthdr_dccp_eval, + .init = nft_exthdr_dccp_init, + .dump = nft_exthdr_dump, + .reduce = nft_exthdr_reduce, +}; + static const struct nft_expr_ops * nft_exthdr_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) @@ -720,6 +821,10 @@ nft_exthdr_select_ops(const struct nft_ctx *ctx, if (tb[NFTA_EXTHDR_DREG]) return &nft_exthdr_sctp_ops; break; + case NFT_EXTHDR_OP_DCCP: + if (tb[NFTA_EXTHDR_DREG]) + return &nft_exthdr_dccp_ops; + break; } return ERR_PTR(-EOPNOTSUPP); From patchwork Fri Apr 21 23:01:53 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Pablo Neira Ayuso X-Patchwork-Id: 1772132 X-Patchwork-Delegate: pablo@netfilter.org Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@legolas.ozlabs.org Authentication-Results: legolas.ozlabs.org; spf=pass (sender SPF authorized) smtp.mailfrom=vger.kernel.org (client-ip=2620:137:e000::1:20; helo=out1.vger.email; envelope-from=netfilter-devel-owner@vger.kernel.org; receiver=) Received: from out1.vger.email (out1.vger.email [IPv6:2620:137:e000::1:20]) by legolas.ozlabs.org (Postfix) with ESMTP id 4Q395p5zgwz23s0 for ; Sat, 22 Apr 2023 09:02:22 +1000 (AEST) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S233536AbjDUXCU (ORCPT ); Fri, 21 Apr 2023 19:02:20 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:52624 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S233465AbjDUXCT (ORCPT ); Fri, 21 Apr 2023 19:02:19 -0400 Received: from mail.netfilter.org (mail.netfilter.org [217.70.188.207]) by lindbergh.monkeyblade.net (Postfix) with ESMTP id DBDDCE73; Fri, 21 Apr 2023 16:02:17 -0700 (PDT) From: Pablo Neira Ayuso To: netfilter-devel@vger.kernel.org Cc: davem@davemloft.net, netdev@vger.kernel.org, kuba@kernel.org, pabeni@redhat.com, edumazet@google.com Subject: [PATCH net-next 02/20] netfilter: nf_tables: merge nft_rules_old structure and end of ruleblob marker Date: Sat, 22 Apr 2023 01:01:53 +0200 Message-Id: <20230421230211.214635-3-pablo@netfilter.org> X-Mailer: git-send-email 2.30.2 In-Reply-To: <20230421230211.214635-1-pablo@netfilter.org> References: <20230421230211.214635-1-pablo@netfilter.org> MIME-Version: 1.0 X-Spam-Status: No, score=-1.9 required=5.0 tests=BAYES_00,SPF_HELO_NONE, SPF_PASS,T_SCC_BODY_TEXT_LINE autolearn=ham autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on lindbergh.monkeyblade.net Precedence: bulk List-ID: X-Mailing-List: netfilter-devel@vger.kernel.org From: Florian Westphal In order to free the rules in a chain via call_rcu, the rule array used to stash a rcu_head and space for a pointer at the end of the rule array. When the current nft_rule_dp blob format got added in 2c865a8a28a1 ("netfilter: nf_tables: add rule blob layout"), this results in a double-trailer: size (unsigned long) struct nft_rule_dp struct nft_expr ... struct nft_rule_dp struct nft_expr ... struct nft_rule_dp (is_last=1) // Trailer The trailer, struct nft_rule_dp (is_last=1), is not accounted for in size, so it can be located via start_addr + size. Because the rcu_head is stored after 'start+size' as well this means the is_last trailer is *aliased* to the rcu_head (struct nft_rules_old). This is harmless, because at this time the nft_do_chain function never evaluates/accesses the trailer, it only checks the address boundary: for (; rule < last_rule; rule = nft_rule_next(rule)) { ... But this way the last_rule address has to be stashed in the jump structure to restore it after returning from a chain. nft_do_chain stack usage has become way too big, so put it on a diet. Without this patch is impossible to use for (; !rule->is_last; rule = nft_rule_next(rule)) { ... because on free, the needed update of the rcu_head will clobber the nft_rule_dp is_last bit. Furthermore, also stash the chain pointer in the trailer, this allows to recover the original chain structure from nf_tables_trace infra without a need to place them in the jump struct. After this patch it is trivial to diet the jump stack structure, done in the next two patches. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 55 +++++++++++++++++------------------ 1 file changed, 27 insertions(+), 28 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index e48ab8dfb541..79848a27e640 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2110,38 +2110,41 @@ static void nft_chain_release_hook(struct nft_chain_hook *hook) module_put(hook->type->owner); } -struct nft_rules_old { +struct nft_rule_dp_last { + struct nft_rule_dp end; /* end of nft_rule_blob marker */ struct rcu_head h; struct nft_rule_blob *blob; + const struct nft_chain *chain; /* for tracing */ }; -static void nft_last_rule(struct nft_rule_blob *blob, const void *ptr) +static void nft_last_rule(const struct nft_chain *chain, const void *ptr) { - struct nft_rule_dp *prule; + struct nft_rule_dp_last *lrule; + + BUILD_BUG_ON(offsetof(struct nft_rule_dp_last, end) != 0); - prule = (struct nft_rule_dp *)ptr; - prule->is_last = 1; + lrule = (struct nft_rule_dp_last *)ptr; + lrule->end.is_last = 1; + lrule->chain = chain; /* blob size does not include the trailer rule */ } -static struct nft_rule_blob *nf_tables_chain_alloc_rules(unsigned int size) +static struct nft_rule_blob *nf_tables_chain_alloc_rules(const struct nft_chain *chain, + unsigned int size) { struct nft_rule_blob *blob; - /* size must include room for the last rule */ - if (size < offsetof(struct nft_rule_dp, data)) - return NULL; - - size += sizeof(struct nft_rule_blob) + sizeof(struct nft_rules_old); if (size > INT_MAX) return NULL; + size += sizeof(struct nft_rule_blob) + sizeof(struct nft_rule_dp_last); + blob = kvmalloc(size, GFP_KERNEL_ACCOUNT); if (!blob) return NULL; blob->size = 0; - nft_last_rule(blob, blob->data); + nft_last_rule(chain, blob->data); return blob; } @@ -2220,7 +2223,6 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, struct nft_rule_blob *blob; struct nft_trans *trans; struct nft_chain *chain; - unsigned int data_size; int err; if (table->use == UINT_MAX) @@ -2308,8 +2310,7 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, chain->udlen = nla_len(nla[NFTA_CHAIN_USERDATA]); } - data_size = offsetof(struct nft_rule_dp, data); /* last rule */ - blob = nf_tables_chain_alloc_rules(data_size); + blob = nf_tables_chain_alloc_rules(chain, 0); if (!blob) { err = -ENOMEM; goto err_destroy_chain; @@ -8817,9 +8818,8 @@ static int nf_tables_commit_chain_prepare(struct net *net, struct nft_chain *cha return -ENOMEM; } } - data_size += offsetof(struct nft_rule_dp, data); /* last rule */ - chain->blob_next = nf_tables_chain_alloc_rules(data_size); + chain->blob_next = nf_tables_chain_alloc_rules(chain, data_size); if (!chain->blob_next) return -ENOMEM; @@ -8864,12 +8864,11 @@ static int nf_tables_commit_chain_prepare(struct net *net, struct nft_chain *cha chain->blob_next->size += (unsigned long)(data - (void *)prule); } - prule = (struct nft_rule_dp *)data; - data += offsetof(struct nft_rule_dp, data); if (WARN_ON_ONCE(data > data_boundary)) return -ENOMEM; - nft_last_rule(chain->blob_next, prule); + prule = (struct nft_rule_dp *)data; + nft_last_rule(chain, prule); return 0; } @@ -8890,22 +8889,22 @@ static void nf_tables_commit_chain_prepare_cancel(struct net *net) } } -static void __nf_tables_commit_chain_free_rules_old(struct rcu_head *h) +static void __nf_tables_commit_chain_free_rules(struct rcu_head *h) { - struct nft_rules_old *o = container_of(h, struct nft_rules_old, h); + struct nft_rule_dp_last *l = container_of(h, struct nft_rule_dp_last, h); - kvfree(o->blob); + kvfree(l->blob); } static void nf_tables_commit_chain_free_rules_old(struct nft_rule_blob *blob) { - struct nft_rules_old *old; + struct nft_rule_dp_last *last; - /* rcu_head is after end marker */ - old = (void *)blob + sizeof(*blob) + blob->size; - old->blob = blob; + /* last rule trailer is after end marker */ + last = (void *)blob + sizeof(*blob) + blob->size; + last->blob = blob; - call_rcu(&old->h, __nf_tables_commit_chain_free_rules_old); + call_rcu(&last->h, __nf_tables_commit_chain_free_rules); } static void nf_tables_commit_chain(struct net *net, struct nft_chain *chain) From patchwork Fri Apr 21 23:01:54 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Pablo Neira Ayuso X-Patchwork-Id: 1772133 X-Patchwork-Delegate: pablo@netfilter.org Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@legolas.ozlabs.org Authentication-Results: legolas.ozlabs.org; spf=pass (sender SPF authorized) smtp.mailfrom=vger.kernel.org (client-ip=2620:137:e000::1:20; helo=out1.vger.email; envelope-from=netfilter-devel-owner@vger.kernel.org; receiver=) Received: from out1.vger.email (out1.vger.email [IPv6:2620:137:e000::1:20]) by legolas.ozlabs.org (Postfix) with ESMTP id 4Q395q1vL2z23tp for ; Sat, 22 Apr 2023 09:02:23 +1000 (AEST) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S233577AbjDUXCU (ORCPT ); Fri, 21 Apr 2023 19:02:20 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:52626 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S233520AbjDUXCT (ORCPT ); Fri, 21 Apr 2023 19:02:19 -0400 Received: from mail.netfilter.org (mail.netfilter.org [217.70.188.207]) by lindbergh.monkeyblade.net (Postfix) with ESMTP id 92B8DE57; Fri, 21 Apr 2023 16:02:18 -0700 (PDT) From: Pablo Neira Ayuso To: netfilter-devel@vger.kernel.org Cc: davem@davemloft.net, netdev@vger.kernel.org, kuba@kernel.org, pabeni@redhat.com, edumazet@google.com Subject: [PATCH net-next 03/20] netfilter: nf_tables: don't store address of last rule on jump Date: Sat, 22 Apr 2023 01:01:54 +0200 Message-Id: <20230421230211.214635-4-pablo@netfilter.org> X-Mailer: git-send-email 2.30.2 In-Reply-To: <20230421230211.214635-1-pablo@netfilter.org> References: <20230421230211.214635-1-pablo@netfilter.org> MIME-Version: 1.0 X-Spam-Status: No, score=-1.9 required=5.0 tests=BAYES_00,SPF_HELO_NONE, SPF_PASS,T_SCC_BODY_TEXT_LINE autolearn=ham autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on lindbergh.monkeyblade.net Precedence: bulk List-ID: X-Mailing-List: netfilter-devel@vger.kernel.org From: Florian Westphal Walk the rule headers until the trailer one (last_bit flag set) instead of stopping at last_rule address. This avoids the need to store the address when jumping to another chain. This cuts size of jumpstack array by one third, on 64bit from 384 to 256 bytes. Still, stack usage is still quite large: scripts/stackusage: nf_tables_core.c:258 nft_do_chain 496 static Next patch will also remove chain pointer. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_core.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index 6ecd0ba2e546..ec3bab751092 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -205,7 +205,6 @@ static noinline void nft_update_chain_stats(const struct nft_chain *chain, struct nft_jumpstack { const struct nft_chain *chain; const struct nft_rule_dp *rule; - const struct nft_rule_dp *last_rule; }; static void expr_call_ops_eval(const struct nft_expr *expr, @@ -259,9 +258,9 @@ unsigned int nft_do_chain(struct nft_pktinfo *pkt, void *priv) { const struct nft_chain *chain = priv, *basechain = chain; - const struct nft_rule_dp *rule, *last_rule; const struct net *net = nft_net(pkt); const struct nft_expr *expr, *last; + const struct nft_rule_dp *rule; struct nft_regs regs = {}; unsigned int stackptr = 0; struct nft_jumpstack jumpstack[NFT_JUMP_STACK_SIZE]; @@ -279,10 +278,9 @@ nft_do_chain(struct nft_pktinfo *pkt, void *priv) blob = rcu_dereference(chain->blob_gen_0); rule = (struct nft_rule_dp *)blob->data; - last_rule = (void *)blob->data + blob->size; next_rule: regs.verdict.code = NFT_CONTINUE; - for (; rule < last_rule; rule = nft_rule_next(rule)) { + for (; !rule->is_last ; rule = nft_rule_next(rule)) { nft_rule_dp_for_each_expr(expr, last, rule) { if (expr->ops == &nft_cmp_fast_ops) nft_cmp_fast_eval(expr, ®s); @@ -327,7 +325,6 @@ nft_do_chain(struct nft_pktinfo *pkt, void *priv) return NF_DROP; jumpstack[stackptr].chain = chain; jumpstack[stackptr].rule = nft_rule_next(rule); - jumpstack[stackptr].last_rule = last_rule; stackptr++; fallthrough; case NFT_GOTO: @@ -344,7 +341,6 @@ nft_do_chain(struct nft_pktinfo *pkt, void *priv) stackptr--; chain = jumpstack[stackptr].chain; rule = jumpstack[stackptr].rule; - last_rule = jumpstack[stackptr].last_rule; goto next_rule; } From patchwork Fri Apr 21 23:01:55 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Pablo Neira Ayuso X-Patchwork-Id: 1772135 X-Patchwork-Delegate: pablo@netfilter.org Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@legolas.ozlabs.org Authentication-Results: legolas.ozlabs.org; spf=pass (sender SPF authorized) smtp.mailfrom=vger.kernel.org (client-ip=2620:137:e000::1:20; helo=out1.vger.email; envelope-from=netfilter-devel-owner@vger.kernel.org; receiver=) Received: from out1.vger.email (out1.vger.email [IPv6:2620:137:e000::1:20]) by legolas.ozlabs.org (Postfix) with ESMTP id 4Q395v3qJjz23s0 for ; Sat, 22 Apr 2023 09:02:27 +1000 (AEST) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S233748AbjDUXCZ (ORCPT ); Fri, 21 Apr 2023 19:02:25 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:52674 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S233609AbjDUXCV (ORCPT ); Fri, 21 Apr 2023 19:02:21 -0400 Received: from mail.netfilter.org (mail.netfilter.org [217.70.188.207]) by lindbergh.monkeyblade.net (Postfix) with ESMTP id 4530BE6E; Fri, 21 Apr 2023 16:02:19 -0700 (PDT) From: Pablo Neira Ayuso To: netfilter-devel@vger.kernel.org Cc: davem@davemloft.net, netdev@vger.kernel.org, kuba@kernel.org, pabeni@redhat.com, edumazet@google.com Subject: [PATCH net-next 04/20] netfilter: nf_tables: don't store chain address on jump Date: Sat, 22 Apr 2023 01:01:55 +0200 Message-Id: <20230421230211.214635-5-pablo@netfilter.org> X-Mailer: git-send-email 2.30.2 In-Reply-To: <20230421230211.214635-1-pablo@netfilter.org> References: <20230421230211.214635-1-pablo@netfilter.org> MIME-Version: 1.0 X-Spam-Status: No, score=-1.9 required=5.0 tests=BAYES_00,SPF_HELO_NONE, SPF_PASS,T_SCC_BODY_TEXT_LINE autolearn=ham autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on lindbergh.monkeyblade.net Precedence: bulk List-ID: X-Mailing-List: netfilter-devel@vger.kernel.org From: Florian Westphal Now that the rule trailer/end marker and the rcu head reside in the same structure, we no longer need to save/restore the chain pointer when performing/returning from a jump. We can simply let the trace infra walk the evaluated rule until it hits the end marker and then fetch the chain pointer from there. When the rule is NULL (policy tracing), then chain and basechain pointers were already identical, so just use the basechain. This cuts size of jumpstack in half, from 256 to 128 bytes in 64bit, scripts/stackusage says: nf_tables_core.c:251 nft_do_chain 328 static Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 14 ++++++++++++-- net/netfilter/nf_tables_api.c | 7 ------- net/netfilter/nf_tables_core.c | 21 ++++++--------------- net/netfilter/nf_tables_trace.c | 30 ++++++++++++++++++++++++++---- 4 files changed, 44 insertions(+), 28 deletions(-) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 1b8e305bb54a..f476fd030626 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1046,6 +1046,18 @@ struct nft_rule_dp { __attribute__((aligned(__alignof__(struct nft_expr)))); }; +struct nft_rule_dp_last { + struct nft_rule_dp end; /* end of nft_rule_blob marker */ + struct rcu_head h; /* call_rcu head */ + struct nft_rule_blob *blob; /* ptr to free via call_rcu */ + const struct nft_chain *chain; /* for nftables tracing */ +}; + +static inline const struct nft_rule_dp *nft_rule_next(const struct nft_rule_dp *rule) +{ + return (void *)rule + sizeof(*rule) + rule->dlen; +} + struct nft_rule_blob { unsigned long size; unsigned char data[] @@ -1396,7 +1408,6 @@ void nft_unregister_flowtable_type(struct nf_flowtable_type *type); * @packet_dumped: packet headers sent in a previous traceinfo message * @pkt: pktinfo currently processed * @basechain: base chain currently processed - * @chain: chain currently processed * @rule: rule that was evaluated * @verdict: verdict given by rule */ @@ -1408,7 +1419,6 @@ struct nft_traceinfo { u32 skbid; const struct nft_pktinfo *pkt; const struct nft_base_chain *basechain; - const struct nft_chain *chain; const struct nft_rule_dp *rule; const struct nft_verdict *verdict; }; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 79848a27e640..0e1c86bb51a2 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2110,13 +2110,6 @@ static void nft_chain_release_hook(struct nft_chain_hook *hook) module_put(hook->type->owner); } -struct nft_rule_dp_last { - struct nft_rule_dp end; /* end of nft_rule_blob marker */ - struct rcu_head h; - struct nft_rule_blob *blob; - const struct nft_chain *chain; /* for tracing */ -}; - static void nft_last_rule(const struct nft_chain *chain, const void *ptr) { struct nft_rule_dp_last *lrule; diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index ec3bab751092..89c05b64c2a2 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -42,13 +42,11 @@ static inline void nf_skip_indirect_calls_enable(void) { } #endif static noinline void __nft_trace_packet(struct nft_traceinfo *info, - const struct nft_chain *chain, enum nft_trace_types type) { if (!info->trace || !info->nf_trace) return; - info->chain = chain; info->type = type; nft_trace_notify(info); @@ -56,14 +54,13 @@ static noinline void __nft_trace_packet(struct nft_traceinfo *info, static inline void nft_trace_packet(const struct nft_pktinfo *pkt, struct nft_traceinfo *info, - const struct nft_chain *chain, const struct nft_rule_dp *rule, enum nft_trace_types type) { if (static_branch_unlikely(&nft_trace_enabled)) { info->nf_trace = pkt->skb->nf_trace; info->rule = rule; - __nft_trace_packet(info, chain, type); + __nft_trace_packet(info, type); } } @@ -111,7 +108,6 @@ static void nft_cmp16_fast_eval(const struct nft_expr *expr, } static noinline void __nft_trace_verdict(struct nft_traceinfo *info, - const struct nft_chain *chain, const struct nft_regs *regs) { enum nft_trace_types type; @@ -133,17 +129,16 @@ static noinline void __nft_trace_verdict(struct nft_traceinfo *info, break; } - __nft_trace_packet(info, chain, type); + __nft_trace_packet(info, type); } static inline void nft_trace_verdict(struct nft_traceinfo *info, - const struct nft_chain *chain, const struct nft_rule_dp *rule, const struct nft_regs *regs) { if (static_branch_unlikely(&nft_trace_enabled)) { info->rule = rule; - __nft_trace_verdict(info, chain, regs); + __nft_trace_verdict(info, regs); } } @@ -203,7 +198,6 @@ static noinline void nft_update_chain_stats(const struct nft_chain *chain, } struct nft_jumpstack { - const struct nft_chain *chain; const struct nft_rule_dp *rule; }; @@ -247,7 +241,6 @@ static void expr_call_ops_eval(const struct nft_expr *expr, #define nft_rule_expr_first(rule) (struct nft_expr *)&rule->data[0] #define nft_rule_expr_next(expr) ((void *)expr) + expr->ops->size #define nft_rule_expr_last(rule) (struct nft_expr *)&rule->data[rule->dlen] -#define nft_rule_next(rule) (void *)rule + sizeof(*rule) + rule->dlen #define nft_rule_dp_for_each_expr(expr, last, rule) \ for ((expr) = nft_rule_expr_first(rule), (last) = nft_rule_expr_last(rule); \ @@ -302,14 +295,14 @@ nft_do_chain(struct nft_pktinfo *pkt, void *priv) nft_trace_copy_nftrace(pkt, &info); continue; case NFT_CONTINUE: - nft_trace_packet(pkt, &info, chain, rule, + nft_trace_packet(pkt, &info, rule, NFT_TRACETYPE_RULE); continue; } break; } - nft_trace_verdict(&info, chain, rule, ®s); + nft_trace_verdict(&info, rule, ®s); switch (regs.verdict.code & NF_VERDICT_MASK) { case NF_ACCEPT: @@ -323,7 +316,6 @@ nft_do_chain(struct nft_pktinfo *pkt, void *priv) case NFT_JUMP: if (WARN_ON_ONCE(stackptr >= NFT_JUMP_STACK_SIZE)) return NF_DROP; - jumpstack[stackptr].chain = chain; jumpstack[stackptr].rule = nft_rule_next(rule); stackptr++; fallthrough; @@ -339,12 +331,11 @@ nft_do_chain(struct nft_pktinfo *pkt, void *priv) if (stackptr > 0) { stackptr--; - chain = jumpstack[stackptr].chain; rule = jumpstack[stackptr].rule; goto next_rule; } - nft_trace_packet(pkt, &info, basechain, NULL, NFT_TRACETYPE_POLICY); + nft_trace_packet(pkt, &info, NULL, NFT_TRACETYPE_POLICY); if (static_branch_unlikely(&nft_counters_enabled)) nft_update_chain_stats(basechain, pkt); diff --git a/net/netfilter/nf_tables_trace.c b/net/netfilter/nf_tables_trace.c index 1163ba9c1401..3d9b83d84a84 100644 --- a/net/netfilter/nf_tables_trace.c +++ b/net/netfilter/nf_tables_trace.c @@ -164,9 +164,29 @@ static bool nft_trace_have_verdict_chain(struct nft_traceinfo *info) return true; } +static const struct nft_chain *nft_trace_get_chain(const struct nft_traceinfo *info) +{ + const struct nft_rule_dp *rule = info->rule; + const struct nft_rule_dp_last *last; + + if (!rule) + return &info->basechain->chain; + + while (!rule->is_last) + rule = nft_rule_next(rule); + + last = (const struct nft_rule_dp_last *)rule; + + if (WARN_ON_ONCE(!last->chain)) + return &info->basechain->chain; + + return last->chain; +} + void nft_trace_notify(struct nft_traceinfo *info) { const struct nft_pktinfo *pkt = info->pkt; + const struct nft_chain *chain; struct nlmsghdr *nlh; struct sk_buff *skb; unsigned int size; @@ -176,9 +196,11 @@ void nft_trace_notify(struct nft_traceinfo *info) if (!nfnetlink_has_listeners(nft_net(pkt), NFNLGRP_NFTRACE)) return; + chain = nft_trace_get_chain(info); + size = nlmsg_total_size(sizeof(struct nfgenmsg)) + - nla_total_size(strlen(info->chain->table->name)) + - nla_total_size(strlen(info->chain->name)) + + nla_total_size(strlen(chain->table->name)) + + nla_total_size(strlen(chain->name)) + nla_total_size_64bit(sizeof(__be64)) + /* rule handle */ nla_total_size(sizeof(__be32)) + /* trace type */ nla_total_size(0) + /* VERDICT, nested */ @@ -217,10 +239,10 @@ void nft_trace_notify(struct nft_traceinfo *info) if (nla_put_u32(skb, NFTA_TRACE_ID, info->skbid)) goto nla_put_failure; - if (nla_put_string(skb, NFTA_TRACE_CHAIN, info->chain->name)) + if (nla_put_string(skb, NFTA_TRACE_CHAIN, chain->name)) goto nla_put_failure; - if (nla_put_string(skb, NFTA_TRACE_TABLE, info->chain->table->name)) + if (nla_put_string(skb, NFTA_TRACE_TABLE, chain->table->name)) goto nla_put_failure; if (nf_trace_fill_rule_info(skb, info)) From patchwork Fri Apr 21 23:01:56 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Pablo Neira Ayuso X-Patchwork-Id: 1772134 X-Patchwork-Delegate: pablo@netfilter.org Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@legolas.ozlabs.org Authentication-Results: legolas.ozlabs.org; spf=pass (sender SPF authorized) smtp.mailfrom=vger.kernel.org (client-ip=2620:137:e000::1:20; helo=out1.vger.email; envelope-from=netfilter-devel-owner@vger.kernel.org; receiver=) Received: from out1.vger.email (out1.vger.email [IPv6:2620:137:e000::1:20]) by legolas.ozlabs.org (Postfix) with ESMTP id 4Q395t0W7Fz23s0 for ; Sat, 22 Apr 2023 09:02:26 +1000 (AEST) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S233724AbjDUXCY (ORCPT ); Fri, 21 Apr 2023 19:02:24 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:52676 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S233605AbjDUXCV (ORCPT ); Fri, 21 Apr 2023 19:02:21 -0400 Received: from mail.netfilter.org (mail.netfilter.org [217.70.188.207]) by lindbergh.monkeyblade.net (Postfix) with ESMTP id 04B9B1984; Fri, 21 Apr 2023 16:02:19 -0700 (PDT) From: Pablo Neira Ayuso To: netfilter-devel@vger.kernel.org Cc: davem@davemloft.net, netdev@vger.kernel.org, kuba@kernel.org, pabeni@redhat.com, edumazet@google.com Subject: [PATCH net-next 05/20] netfilter: nf_tables: don't write table validation state without mutex Date: Sat, 22 Apr 2023 01:01:56 +0200 Message-Id: <20230421230211.214635-6-pablo@netfilter.org> X-Mailer: git-send-email 2.30.2 In-Reply-To: <20230421230211.214635-1-pablo@netfilter.org> References: <20230421230211.214635-1-pablo@netfilter.org> MIME-Version: 1.0 X-Spam-Status: No, score=-1.9 required=5.0 tests=BAYES_00,SPF_HELO_NONE, SPF_PASS,T_SCC_BODY_TEXT_LINE autolearn=ham autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on lindbergh.monkeyblade.net Precedence: bulk List-ID: X-Mailing-List: netfilter-devel@vger.kernel.org From: Florian Westphal The ->cleanup callback needs to be removed, this doesn't work anymore as the transaction mutex is already released in the ->abort function. Just do it after a successful validation pass, this either happens from commit or abort phases where transaction mutex is held. Fixes: f102d66b335a ("netfilter: nf_tables: use dedicated mutex to guard transactions") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nfnetlink.h | 1 - net/netfilter/nf_tables_api.c | 8 ++------ net/netfilter/nfnetlink.c | 2 -- 3 files changed, 2 insertions(+), 9 deletions(-) diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 241e005f290a..e9a9ab34a7cc 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -45,7 +45,6 @@ struct nfnetlink_subsystem { int (*commit)(struct net *net, struct sk_buff *skb); int (*abort)(struct net *net, struct sk_buff *skb, enum nfnl_abort_action action); - void (*cleanup)(struct net *net); bool (*valid_genid)(struct net *net, u32 genid); }; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 0e1c86bb51a2..21eb273d2740 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -8639,6 +8639,8 @@ static int nf_tables_validate(struct net *net) if (nft_table_validate(net, table) < 0) return -EAGAIN; } + + nft_validate_state_update(net, NFT_VALIDATE_SKIP); break; } @@ -9578,11 +9580,6 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) return 0; } -static void nf_tables_cleanup(struct net *net) -{ - nft_validate_state_update(net, NFT_VALIDATE_SKIP); -} - static int nf_tables_abort(struct net *net, struct sk_buff *skb, enum nfnl_abort_action action) { @@ -9616,7 +9613,6 @@ static const struct nfnetlink_subsystem nf_tables_subsys = { .cb = nf_tables_cb, .commit = nf_tables_commit, .abort = nf_tables_abort, - .cleanup = nf_tables_cleanup, .valid_genid = nf_tables_valid_genid, .owner = THIS_MODULE, }; diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 81c7737c803a..ae7146475d17 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -590,8 +590,6 @@ static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh, goto replay_abort; } } - if (ss->cleanup) - ss->cleanup(net); nfnl_err_deliver(&err_list, oskb); kfree_skb(skb); From patchwork Fri Apr 21 23:01:57 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Pablo Neira Ayuso X-Patchwork-Id: 1772136 X-Patchwork-Delegate: pablo@netfilter.org Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@legolas.ozlabs.org Authentication-Results: legolas.ozlabs.org; spf=pass (sender SPF authorized) smtp.mailfrom=vger.kernel.org (client-ip=2620:137:e000::1:20; helo=out1.vger.email; envelope-from=netfilter-devel-owner@vger.kernel.org; receiver=) Received: from out1.vger.email (out1.vger.email [IPv6:2620:137:e000::1:20]) by legolas.ozlabs.org (Postfix) with ESMTP id 4Q395v6tH3z23tp for ; Sat, 22 Apr 2023 09:02:27 +1000 (AEST) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S233605AbjDUXCZ (ORCPT ); Fri, 21 Apr 2023 19:02:25 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:52684 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S233618AbjDUXCV (ORCPT ); Fri, 21 Apr 2023 19:02:21 -0400 Received: from mail.netfilter.org (mail.netfilter.org [217.70.188.207]) by lindbergh.monkeyblade.net (Postfix) with ESMTP id 4DD111BCC; Fri, 21 Apr 2023 16:02:20 -0700 (PDT) From: Pablo Neira Ayuso To: netfilter-devel@vger.kernel.org Cc: davem@davemloft.net, netdev@vger.kernel.org, kuba@kernel.org, pabeni@redhat.com, edumazet@google.com Subject: [PATCH net-next 06/20] netfilter: nf_tables: make validation state per table Date: Sat, 22 Apr 2023 01:01:57 +0200 Message-Id: <20230421230211.214635-7-pablo@netfilter.org> X-Mailer: git-send-email 2.30.2 In-Reply-To: <20230421230211.214635-1-pablo@netfilter.org> References: <20230421230211.214635-1-pablo@netfilter.org> MIME-Version: 1.0 X-Spam-Status: No, score=-1.9 required=5.0 tests=BAYES_00,SPF_HELO_NONE, SPF_PASS,T_SCC_BODY_TEXT_LINE autolearn=ham autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on lindbergh.monkeyblade.net Precedence: bulk List-ID: X-Mailing-List: netfilter-devel@vger.kernel.org From: Florian Westphal We only need to validate tables that saw changes in the current transaction. The existing code revalidates all tables, but this isn't needed as cross-table jumps are not allowed (chains have table scope). Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 3 ++- net/netfilter/nf_tables_api.c | 38 +++++++++++++++---------------- 2 files changed, 20 insertions(+), 21 deletions(-) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index f476fd030626..ec347d9cff9e 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1209,6 +1209,7 @@ unsigned int nft_do_chain(struct nft_pktinfo *pkt, void *priv); * @genmask: generation mask * @afinfo: address family info * @name: name of the table + * @validate_state: internal, set when transaction adds jumps */ struct nft_table { struct list_head list; @@ -1227,6 +1228,7 @@ struct nft_table { char *name; u16 udlen; u8 *udata; + u8 validate_state; }; static inline bool nft_table_has_owner(const struct nft_table *table) @@ -1698,7 +1700,6 @@ struct nftables_pernet { struct mutex commit_mutex; u64 table_handle; unsigned int base_seq; - u8 validate_state; }; extern unsigned int nf_tables_net_id; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 21eb273d2740..44ebc5f9598e 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -102,11 +102,9 @@ static const u8 nft2audit_op[NFT_MSG_MAX] = { // enum nf_tables_msg_types [NFT_MSG_DELFLOWTABLE] = AUDIT_NFT_OP_FLOWTABLE_UNREGISTER, }; -static void nft_validate_state_update(struct net *net, u8 new_validate_state) +static void nft_validate_state_update(struct nft_table *table, u8 new_validate_state) { - struct nftables_pernet *nft_net = nft_pernet(net); - - switch (nft_net->validate_state) { + switch (table->validate_state) { case NFT_VALIDATE_SKIP: WARN_ON_ONCE(new_validate_state == NFT_VALIDATE_DO); break; @@ -117,7 +115,7 @@ static void nft_validate_state_update(struct net *net, u8 new_validate_state) return; } - nft_net->validate_state = new_validate_state; + table->validate_state = new_validate_state; } static void nf_tables_trans_destroy_work(struct work_struct *w); static DECLARE_WORK(trans_destroy_work, nf_tables_trans_destroy_work); @@ -1224,6 +1222,7 @@ static int nf_tables_newtable(struct sk_buff *skb, const struct nfnl_info *info, if (table == NULL) goto err_kzalloc; + table->validate_state = NFT_VALIDATE_SKIP; table->name = nla_strdup(attr, GFP_KERNEL_ACCOUNT); if (table->name == NULL) goto err_strdup; @@ -3660,7 +3659,7 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, } if (expr_info[i].ops->validate) - nft_validate_state_update(net, NFT_VALIDATE_NEED); + nft_validate_state_update(table, NFT_VALIDATE_NEED); expr_info[i].ops = NULL; expr = nft_expr_next(expr); @@ -3710,7 +3709,7 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, if (flow) nft_trans_flow_rule(trans) = flow; - if (nft_net->validate_state == NFT_VALIDATE_DO) + if (table->validate_state == NFT_VALIDATE_DO) return nft_table_validate(net, table); return 0; @@ -6312,7 +6311,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (desc.type == NFT_DATA_VERDICT && (elem.data.val.verdict.code == NFT_GOTO || elem.data.val.verdict.code == NFT_JUMP)) - nft_validate_state_update(ctx->net, + nft_validate_state_update(ctx->table, NFT_VALIDATE_NEED); } @@ -6437,7 +6436,6 @@ static int nf_tables_newsetelem(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - struct nftables_pernet *nft_net = nft_pernet(info->net); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); u8 family = info->nfmsg->nfgen_family; @@ -6476,7 +6474,7 @@ static int nf_tables_newsetelem(struct sk_buff *skb, } } - if (nft_net->validate_state == NFT_VALIDATE_DO) + if (table->validate_state == NFT_VALIDATE_DO) return nft_table_validate(net, table); return 0; @@ -8628,19 +8626,20 @@ static int nf_tables_validate(struct net *net) struct nftables_pernet *nft_net = nft_pernet(net); struct nft_table *table; - switch (nft_net->validate_state) { - case NFT_VALIDATE_SKIP: - break; - case NFT_VALIDATE_NEED: - nft_validate_state_update(net, NFT_VALIDATE_DO); - fallthrough; - case NFT_VALIDATE_DO: - list_for_each_entry(table, &nft_net->tables, list) { + list_for_each_entry(table, &nft_net->tables, list) { + switch (table->validate_state) { + case NFT_VALIDATE_SKIP: + continue; + case NFT_VALIDATE_NEED: + nft_validate_state_update(table, NFT_VALIDATE_DO); + fallthrough; + case NFT_VALIDATE_DO: if (nft_table_validate(net, table) < 0) return -EAGAIN; + + nft_validate_state_update(table, NFT_VALIDATE_SKIP); } - nft_validate_state_update(net, NFT_VALIDATE_SKIP); break; } @@ -10355,7 +10354,6 @@ static int __net_init nf_tables_init_net(struct net *net) INIT_LIST_HEAD(&nft_net->notify_list); mutex_init(&nft_net->commit_mutex); nft_net->base_seq = 1; - nft_net->validate_state = NFT_VALIDATE_SKIP; return 0; } From patchwork Fri Apr 21 23:01:58 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Pablo Neira Ayuso X-Patchwork-Id: 1772137 X-Patchwork-Delegate: pablo@netfilter.org Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@legolas.ozlabs.org Authentication-Results: legolas.ozlabs.org; spf=pass (sender SPF authorized) smtp.mailfrom=vger.kernel.org (client-ip=2620:137:e000::1:20; helo=out1.vger.email; envelope-from=netfilter-devel-owner@vger.kernel.org; receiver=) Received: from out1.vger.email (out1.vger.email [IPv6:2620:137:e000::1:20]) by legolas.ozlabs.org (Postfix) with ESMTP id 4Q395w4z90z23s0 for ; Sat, 22 Apr 2023 09:02:28 +1000 (AEST) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S233767AbjDUXC0 (ORCPT ); Fri, 21 Apr 2023 19:02:26 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:52698 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S233658AbjDUXCV (ORCPT ); Fri, 21 Apr 2023 19:02:21 -0400 Received: from mail.netfilter.org (mail.netfilter.org [217.70.188.207]) by lindbergh.monkeyblade.net (Postfix) with ESMTP id 323031FCF; Fri, 21 Apr 2023 16:02:21 -0700 (PDT) From: Pablo Neira Ayuso To: netfilter-devel@vger.kernel.org Cc: davem@davemloft.net, netdev@vger.kernel.org, kuba@kernel.org, pabeni@redhat.com, edumazet@google.com Subject: [PATCH net-next 07/20] netfilter: nf_tables: remove unneeded conditional Date: Sat, 22 Apr 2023 01:01:58 +0200 Message-Id: <20230421230211.214635-8-pablo@netfilter.org> X-Mailer: git-send-email 2.30.2 In-Reply-To: <20230421230211.214635-1-pablo@netfilter.org> References: <20230421230211.214635-1-pablo@netfilter.org> MIME-Version: 1.0 X-Spam-Status: No, score=-1.9 required=5.0 tests=BAYES_00,SPF_HELO_NONE, SPF_PASS,T_SCC_BODY_TEXT_LINE autolearn=ham autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on lindbergh.monkeyblade.net Precedence: bulk List-ID: X-Mailing-List: netfilter-devel@vger.kernel.org From: Florian Westphal This helper is inlined, so keep it as small as possible. If the static key is true, there is only a very small chance that info->trace is false: 1. tracing was enabled at this very moment, the static key was updated to active right after nft_do_table was called. 2. tracing was disabled at this very moment. trace->info is already false, the static key is about to be patched to false soon. In both cases, no event will be sent because info->trace is false (checked in noinline slowpath). info->nf_trace is irrelevant. The nf_trace update is redunant in this case, but this will only happen for short duration, when static key flips. text data bss dec hex filename old: 2980 192 32 3204 c84 nf_tables_core.o new: 2964 192 32 3188 c74i nf_tables_core.o Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_core.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index 89c05b64c2a2..bed855638050 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -67,10 +67,8 @@ static inline void nft_trace_packet(const struct nft_pktinfo *pkt, static inline void nft_trace_copy_nftrace(const struct nft_pktinfo *pkt, struct nft_traceinfo *info) { - if (static_branch_unlikely(&nft_trace_enabled)) { - if (info->trace) - info->nf_trace = pkt->skb->nf_trace; - } + if (static_branch_unlikely(&nft_trace_enabled)) + info->nf_trace = pkt->skb->nf_trace; } static void nft_bitwise_fast_eval(const struct nft_expr *expr, From patchwork Fri Apr 21 23:01:59 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Pablo Neira Ayuso X-Patchwork-Id: 1772138 X-Patchwork-Delegate: pablo@netfilter.org Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@legolas.ozlabs.org Authentication-Results: legolas.ozlabs.org; spf=pass (sender SPF authorized) smtp.mailfrom=vger.kernel.org (client-ip=2620:137:e000::1:20; helo=out1.vger.email; envelope-from=netfilter-devel-owner@vger.kernel.org; receiver=) Received: from out1.vger.email (out1.vger.email [IPv6:2620:137:e000::1:20]) by legolas.ozlabs.org (Postfix) with ESMTP id 4Q39604H5gz23s0 for ; Sat, 22 Apr 2023 09:02:32 +1000 (AEST) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S233796AbjDUXCa (ORCPT ); Fri, 21 Apr 2023 19:02:30 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:52720 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S231614AbjDUXCW (ORCPT ); Fri, 21 Apr 2023 19:02:22 -0400 Received: from mail.netfilter.org (mail.netfilter.org [217.70.188.207]) by lindbergh.monkeyblade.net (Postfix) with ESMTP id 7ECFA2109; Fri, 21 Apr 2023 16:02:21 -0700 (PDT) From: Pablo Neira Ayuso To: netfilter-devel@vger.kernel.org Cc: davem@davemloft.net, netdev@vger.kernel.org, kuba@kernel.org, pabeni@redhat.com, edumazet@google.com Subject: [PATCH net-next 08/20] netfilter: nf_tables: do not store pktinfo in traceinfo structure Date: Sat, 22 Apr 2023 01:01:59 +0200 Message-Id: <20230421230211.214635-9-pablo@netfilter.org> X-Mailer: git-send-email 2.30.2 In-Reply-To: <20230421230211.214635-1-pablo@netfilter.org> References: <20230421230211.214635-1-pablo@netfilter.org> MIME-Version: 1.0 X-Spam-Status: No, score=-1.9 required=5.0 tests=BAYES_00,SPF_HELO_NONE, SPF_PASS,T_SCC_BODY_TEXT_LINE autolearn=ham autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on lindbergh.monkeyblade.net Precedence: bulk List-ID: X-Mailing-List: netfilter-devel@vger.kernel.org From: Florian Westphal pass it as argument. No change in object size. stack usage decreases by 8 byte: nf_tables_core.c:254 nft_do_chain 320 static Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 5 ++--- net/netfilter/nf_tables_core.c | 21 ++++++++++++--------- net/netfilter/nf_tables_trace.c | 5 ++--- 3 files changed, 16 insertions(+), 15 deletions(-) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index ec347d9cff9e..cab351928cd2 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1408,7 +1408,6 @@ void nft_unregister_flowtable_type(struct nf_flowtable_type *type); * @type: event type (enum nft_trace_types) * @skbid: hash of skb to be used as trace id * @packet_dumped: packet headers sent in a previous traceinfo message - * @pkt: pktinfo currently processed * @basechain: base chain currently processed * @rule: rule that was evaluated * @verdict: verdict given by rule @@ -1419,7 +1418,6 @@ struct nft_traceinfo { bool packet_dumped; enum nft_trace_types type:8; u32 skbid; - const struct nft_pktinfo *pkt; const struct nft_base_chain *basechain; const struct nft_rule_dp *rule; const struct nft_verdict *verdict; @@ -1429,7 +1427,8 @@ void nft_trace_init(struct nft_traceinfo *info, const struct nft_pktinfo *pkt, const struct nft_verdict *verdict, const struct nft_chain *basechain); -void nft_trace_notify(struct nft_traceinfo *info); +void nft_trace_notify(const struct nft_pktinfo *pkt, + struct nft_traceinfo *info); #define MODULE_ALIAS_NFT_CHAIN(family, name) \ MODULE_ALIAS("nft-chain-" __stringify(family) "-" name) diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index bed855638050..776eb2b9f632 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -41,7 +41,8 @@ static inline bool nf_skip_indirect_calls(void) { return false; } static inline void nf_skip_indirect_calls_enable(void) { } #endif -static noinline void __nft_trace_packet(struct nft_traceinfo *info, +static noinline void __nft_trace_packet(const struct nft_pktinfo *pkt, + struct nft_traceinfo *info, enum nft_trace_types type) { if (!info->trace || !info->nf_trace) @@ -49,7 +50,7 @@ static noinline void __nft_trace_packet(struct nft_traceinfo *info, info->type = type; - nft_trace_notify(info); + nft_trace_notify(pkt, info); } static inline void nft_trace_packet(const struct nft_pktinfo *pkt, @@ -60,7 +61,7 @@ static inline void nft_trace_packet(const struct nft_pktinfo *pkt, if (static_branch_unlikely(&nft_trace_enabled)) { info->nf_trace = pkt->skb->nf_trace; info->rule = rule; - __nft_trace_packet(info, type); + __nft_trace_packet(pkt, info, type); } } @@ -105,7 +106,8 @@ static void nft_cmp16_fast_eval(const struct nft_expr *expr, regs->verdict.code = NFT_BREAK; } -static noinline void __nft_trace_verdict(struct nft_traceinfo *info, +static noinline void __nft_trace_verdict(const struct nft_pktinfo *pkt, + struct nft_traceinfo *info, const struct nft_regs *regs) { enum nft_trace_types type; @@ -123,20 +125,21 @@ static noinline void __nft_trace_verdict(struct nft_traceinfo *info, type = NFT_TRACETYPE_RULE; if (info->trace) - info->nf_trace = info->pkt->skb->nf_trace; + info->nf_trace = pkt->skb->nf_trace; break; } - __nft_trace_packet(info, type); + __nft_trace_packet(pkt, info, type); } -static inline void nft_trace_verdict(struct nft_traceinfo *info, +static inline void nft_trace_verdict(const struct nft_pktinfo *pkt, + struct nft_traceinfo *info, const struct nft_rule_dp *rule, const struct nft_regs *regs) { if (static_branch_unlikely(&nft_trace_enabled)) { info->rule = rule; - __nft_trace_verdict(info, regs); + __nft_trace_verdict(pkt, info, regs); } } @@ -300,7 +303,7 @@ nft_do_chain(struct nft_pktinfo *pkt, void *priv) break; } - nft_trace_verdict(&info, rule, ®s); + nft_trace_verdict(pkt, &info, rule, ®s); switch (regs.verdict.code & NF_VERDICT_MASK) { case NF_ACCEPT: diff --git a/net/netfilter/nf_tables_trace.c b/net/netfilter/nf_tables_trace.c index 3d9b83d84a84..0a0dcf2587fd 100644 --- a/net/netfilter/nf_tables_trace.c +++ b/net/netfilter/nf_tables_trace.c @@ -183,9 +183,9 @@ static const struct nft_chain *nft_trace_get_chain(const struct nft_traceinfo *i return last->chain; } -void nft_trace_notify(struct nft_traceinfo *info) +void nft_trace_notify(const struct nft_pktinfo *pkt, + struct nft_traceinfo *info) { - const struct nft_pktinfo *pkt = info->pkt; const struct nft_chain *chain; struct nlmsghdr *nlh; struct sk_buff *skb; @@ -305,7 +305,6 @@ void nft_trace_init(struct nft_traceinfo *info, const struct nft_pktinfo *pkt, info->trace = true; info->nf_trace = pkt->skb->nf_trace; info->packet_dumped = false; - info->pkt = pkt; info->verdict = verdict; net_get_random_once(&trace_key, sizeof(trace_key)); From patchwork Fri Apr 21 23:02:00 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Pablo Neira Ayuso X-Patchwork-Id: 1772139 X-Patchwork-Delegate: pablo@netfilter.org Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@legolas.ozlabs.org Authentication-Results: legolas.ozlabs.org; spf=pass (sender SPF authorized) smtp.mailfrom=vger.kernel.org (client-ip=2620:137:e000::1:20; helo=out1.vger.email; envelope-from=netfilter-devel-owner@vger.kernel.org; receiver=) Received: from out1.vger.email (out1.vger.email [IPv6:2620:137:e000::1:20]) by legolas.ozlabs.org (Postfix) with ESMTP id 4Q39610CHNz23tp for ; Sat, 22 Apr 2023 09:02:33 +1000 (AEST) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S233658AbjDUXCb (ORCPT ); Fri, 21 Apr 2023 19:02:31 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:52776 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S233714AbjDUXCY (ORCPT ); Fri, 21 Apr 2023 19:02:24 -0400 Received: from mail.netfilter.org (mail.netfilter.org [217.70.188.207]) by lindbergh.monkeyblade.net (Postfix) with ESMTP id 13513212F; Fri, 21 Apr 2023 16:02:22 -0700 (PDT) From: Pablo Neira Ayuso To: netfilter-devel@vger.kernel.org Cc: davem@davemloft.net, netdev@vger.kernel.org, kuba@kernel.org, pabeni@redhat.com, edumazet@google.com Subject: [PATCH net-next 09/20] netfilter: nf_tables: do not store verdict in traceinfo structure Date: Sat, 22 Apr 2023 01:02:00 +0200 Message-Id: <20230421230211.214635-10-pablo@netfilter.org> X-Mailer: git-send-email 2.30.2 In-Reply-To: <20230421230211.214635-1-pablo@netfilter.org> References: <20230421230211.214635-1-pablo@netfilter.org> MIME-Version: 1.0 X-Spam-Status: No, score=-1.9 required=5.0 tests=BAYES_00,SPF_HELO_NONE, SPF_PASS,T_SCC_BODY_TEXT_LINE autolearn=ham autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on lindbergh.monkeyblade.net Precedence: bulk List-ID: X-Mailing-List: netfilter-devel@vger.kernel.org From: Florian Westphal Just pass it as argument to nft_trace_notify. Stack is reduced by 8 bytes: nf_tables_core.c:256 nft_do_chain 312 static Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 4 +--- net/netfilter/nf_tables_core.c | 14 ++++++++------ net/netfilter/nf_tables_trace.c | 21 +++++++++++---------- 3 files changed, 20 insertions(+), 19 deletions(-) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index cab351928cd2..693469ecfa54 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1410,7 +1410,6 @@ void nft_unregister_flowtable_type(struct nf_flowtable_type *type); * @packet_dumped: packet headers sent in a previous traceinfo message * @basechain: base chain currently processed * @rule: rule that was evaluated - * @verdict: verdict given by rule */ struct nft_traceinfo { bool trace; @@ -1420,14 +1419,13 @@ struct nft_traceinfo { u32 skbid; const struct nft_base_chain *basechain; const struct nft_rule_dp *rule; - const struct nft_verdict *verdict; }; void nft_trace_init(struct nft_traceinfo *info, const struct nft_pktinfo *pkt, - const struct nft_verdict *verdict, const struct nft_chain *basechain); void nft_trace_notify(const struct nft_pktinfo *pkt, + const struct nft_verdict *verdict, struct nft_traceinfo *info); #define MODULE_ALIAS_NFT_CHAIN(family, name) \ diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index 776eb2b9f632..6debe8b2623f 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -42,6 +42,7 @@ static inline void nf_skip_indirect_calls_enable(void) { } #endif static noinline void __nft_trace_packet(const struct nft_pktinfo *pkt, + const struct nft_verdict *verdict, struct nft_traceinfo *info, enum nft_trace_types type) { @@ -50,10 +51,11 @@ static noinline void __nft_trace_packet(const struct nft_pktinfo *pkt, info->type = type; - nft_trace_notify(pkt, info); + nft_trace_notify(pkt, verdict, info); } static inline void nft_trace_packet(const struct nft_pktinfo *pkt, + struct nft_verdict *verdict, struct nft_traceinfo *info, const struct nft_rule_dp *rule, enum nft_trace_types type) @@ -61,7 +63,7 @@ static inline void nft_trace_packet(const struct nft_pktinfo *pkt, if (static_branch_unlikely(&nft_trace_enabled)) { info->nf_trace = pkt->skb->nf_trace; info->rule = rule; - __nft_trace_packet(pkt, info, type); + __nft_trace_packet(pkt, verdict, info, type); } } @@ -129,7 +131,7 @@ static noinline void __nft_trace_verdict(const struct nft_pktinfo *pkt, break; } - __nft_trace_packet(pkt, info, type); + __nft_trace_packet(pkt, ®s->verdict, info, type); } static inline void nft_trace_verdict(const struct nft_pktinfo *pkt, @@ -264,7 +266,7 @@ nft_do_chain(struct nft_pktinfo *pkt, void *priv) info.trace = false; if (static_branch_unlikely(&nft_trace_enabled)) - nft_trace_init(&info, pkt, ®s.verdict, basechain); + nft_trace_init(&info, pkt, basechain); do_chain: if (genbit) blob = rcu_dereference(chain->blob_gen_1); @@ -296,7 +298,7 @@ nft_do_chain(struct nft_pktinfo *pkt, void *priv) nft_trace_copy_nftrace(pkt, &info); continue; case NFT_CONTINUE: - nft_trace_packet(pkt, &info, rule, + nft_trace_packet(pkt, ®s.verdict, &info, rule, NFT_TRACETYPE_RULE); continue; } @@ -336,7 +338,7 @@ nft_do_chain(struct nft_pktinfo *pkt, void *priv) goto next_rule; } - nft_trace_packet(pkt, &info, NULL, NFT_TRACETYPE_POLICY); + nft_trace_packet(pkt, ®s.verdict, &info, NULL, NFT_TRACETYPE_POLICY); if (static_branch_unlikely(&nft_counters_enabled)) nft_update_chain_stats(basechain, pkt); diff --git a/net/netfilter/nf_tables_trace.c b/net/netfilter/nf_tables_trace.c index 0a0dcf2587fd..e635104a42be 100644 --- a/net/netfilter/nf_tables_trace.c +++ b/net/netfilter/nf_tables_trace.c @@ -124,6 +124,7 @@ static int nf_trace_fill_pkt_info(struct sk_buff *nlskb, } static int nf_trace_fill_rule_info(struct sk_buff *nlskb, + const struct nft_verdict *verdict, const struct nft_traceinfo *info) { if (!info->rule || info->rule->is_last) @@ -135,7 +136,7 @@ static int nf_trace_fill_rule_info(struct sk_buff *nlskb, * Since no rule matched, the ->rule pointer is invalid. */ if (info->type == NFT_TRACETYPE_RETURN && - info->verdict->code == NFT_CONTINUE) + verdict->code == NFT_CONTINUE) return 0; return nla_put_be64(nlskb, NFTA_TRACE_RULE_HANDLE, @@ -143,7 +144,8 @@ static int nf_trace_fill_rule_info(struct sk_buff *nlskb, NFTA_TRACE_PAD); } -static bool nft_trace_have_verdict_chain(struct nft_traceinfo *info) +static bool nft_trace_have_verdict_chain(const struct nft_verdict *verdict, + struct nft_traceinfo *info) { switch (info->type) { case NFT_TRACETYPE_RETURN: @@ -153,7 +155,7 @@ static bool nft_trace_have_verdict_chain(struct nft_traceinfo *info) return false; } - switch (info->verdict->code) { + switch (verdict->code) { case NFT_JUMP: case NFT_GOTO: break; @@ -184,6 +186,7 @@ static const struct nft_chain *nft_trace_get_chain(const struct nft_traceinfo *i } void nft_trace_notify(const struct nft_pktinfo *pkt, + const struct nft_verdict *verdict, struct nft_traceinfo *info) { const struct nft_chain *chain; @@ -217,8 +220,8 @@ void nft_trace_notify(const struct nft_pktinfo *pkt, nla_total_size(sizeof(u32)) + /* nfproto */ nla_total_size(sizeof(u32)); /* policy */ - if (nft_trace_have_verdict_chain(info)) - size += nla_total_size(strlen(info->verdict->chain->name)); /* jump target */ + if (nft_trace_have_verdict_chain(verdict, info)) + size += nla_total_size(strlen(verdict->chain->name)); /* jump target */ skb = nlmsg_new(size, GFP_ATOMIC); if (!skb) @@ -245,7 +248,7 @@ void nft_trace_notify(const struct nft_pktinfo *pkt, if (nla_put_string(skb, NFTA_TRACE_TABLE, chain->table->name)) goto nla_put_failure; - if (nf_trace_fill_rule_info(skb, info)) + if (nf_trace_fill_rule_info(skb, verdict, info)) goto nla_put_failure; switch (info->type) { @@ -254,11 +257,11 @@ void nft_trace_notify(const struct nft_pktinfo *pkt, break; case NFT_TRACETYPE_RETURN: case NFT_TRACETYPE_RULE: - if (nft_verdict_dump(skb, NFTA_TRACE_VERDICT, info->verdict)) + if (nft_verdict_dump(skb, NFTA_TRACE_VERDICT, verdict)) goto nla_put_failure; /* pkt->skb undefined iff NF_STOLEN, disable dump */ - if (info->verdict->code == NF_STOLEN) + if (verdict->code == NF_STOLEN) info->packet_dumped = true; else mark = pkt->skb->mark; @@ -295,7 +298,6 @@ void nft_trace_notify(const struct nft_pktinfo *pkt, } void nft_trace_init(struct nft_traceinfo *info, const struct nft_pktinfo *pkt, - const struct nft_verdict *verdict, const struct nft_chain *chain) { static siphash_key_t trace_key __read_mostly; @@ -305,7 +307,6 @@ void nft_trace_init(struct nft_traceinfo *info, const struct nft_pktinfo *pkt, info->trace = true; info->nf_trace = pkt->skb->nf_trace; info->packet_dumped = false; - info->verdict = verdict; net_get_random_once(&trace_key, sizeof(trace_key)); From patchwork Fri Apr 21 23:02:01 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Pablo Neira Ayuso X-Patchwork-Id: 1772140 X-Patchwork-Delegate: pablo@netfilter.org Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@legolas.ozlabs.org Authentication-Results: legolas.ozlabs.org; spf=pass (sender SPF authorized) smtp.mailfrom=vger.kernel.org (client-ip=2620:137:e000::1:20; helo=out1.vger.email; envelope-from=netfilter-devel-owner@vger.kernel.org; receiver=) Received: from out1.vger.email (out1.vger.email [IPv6:2620:137:e000::1:20]) by legolas.ozlabs.org (Postfix) with ESMTP id 4Q396J5FVPz23s0 for ; Sat, 22 Apr 2023 09:02:48 +1000 (AEST) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S233841AbjDUXCr (ORCPT ); Fri, 21 Apr 2023 19:02:47 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:52782 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S233722AbjDUXCY (ORCPT ); Fri, 21 Apr 2023 19:02:24 -0400 Received: from mail.netfilter.org (mail.netfilter.org [217.70.188.207]) by lindbergh.monkeyblade.net (Postfix) with ESMTP id A79F1E73; Fri, 21 Apr 2023 16:02:22 -0700 (PDT) From: Pablo Neira Ayuso To: netfilter-devel@vger.kernel.org Cc: davem@davemloft.net, netdev@vger.kernel.org, kuba@kernel.org, pabeni@redhat.com, edumazet@google.com Subject: [PATCH net-next 10/20] netfilter: nf_tables: do not store rule in traceinfo structure Date: Sat, 22 Apr 2023 01:02:01 +0200 Message-Id: <20230421230211.214635-11-pablo@netfilter.org> X-Mailer: git-send-email 2.30.2 In-Reply-To: <20230421230211.214635-1-pablo@netfilter.org> References: <20230421230211.214635-1-pablo@netfilter.org> MIME-Version: 1.0 X-Spam-Status: No, score=-1.9 required=5.0 tests=BAYES_00,SPF_HELO_NONE, SPF_PASS,T_SCC_BODY_TEXT_LINE autolearn=ham autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on lindbergh.monkeyblade.net Precedence: bulk List-ID: X-Mailing-List: netfilter-devel@vger.kernel.org From: Florian Westphal pass it as argument instead. This reduces size of traceinfo to 16 bytes. Total stack usage: nf_tables_core.c:252 nft_do_chain 304 static While its possible to also pass basechain as argument, doing so increases nft_do_chaininfo function size. Unlike pktinfo/verdict/rule the basechain info isn't used in the expression evaluation path. gcc places it on the stack, which results in extra push/pop when it gets passed to the trace helpers as argument rather than as part of the traceinfo structure. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 3 +-- net/netfilter/nf_tables_core.c | 15 +++++++-------- net/netfilter/nf_tables_trace.c | 14 ++++++++------ 3 files changed, 16 insertions(+), 16 deletions(-) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 693469ecfa54..58a4d217faaf 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1409,7 +1409,6 @@ void nft_unregister_flowtable_type(struct nf_flowtable_type *type); * @skbid: hash of skb to be used as trace id * @packet_dumped: packet headers sent in a previous traceinfo message * @basechain: base chain currently processed - * @rule: rule that was evaluated */ struct nft_traceinfo { bool trace; @@ -1418,7 +1417,6 @@ struct nft_traceinfo { enum nft_trace_types type:8; u32 skbid; const struct nft_base_chain *basechain; - const struct nft_rule_dp *rule; }; void nft_trace_init(struct nft_traceinfo *info, const struct nft_pktinfo *pkt, @@ -1426,6 +1424,7 @@ void nft_trace_init(struct nft_traceinfo *info, const struct nft_pktinfo *pkt, void nft_trace_notify(const struct nft_pktinfo *pkt, const struct nft_verdict *verdict, + const struct nft_rule_dp *rule, struct nft_traceinfo *info); #define MODULE_ALIAS_NFT_CHAIN(family, name) \ diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index 6debe8b2623f..4d0ce12221f6 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -43,6 +43,7 @@ static inline void nf_skip_indirect_calls_enable(void) { } static noinline void __nft_trace_packet(const struct nft_pktinfo *pkt, const struct nft_verdict *verdict, + const struct nft_rule_dp *rule, struct nft_traceinfo *info, enum nft_trace_types type) { @@ -51,7 +52,7 @@ static noinline void __nft_trace_packet(const struct nft_pktinfo *pkt, info->type = type; - nft_trace_notify(pkt, verdict, info); + nft_trace_notify(pkt, verdict, rule, info); } static inline void nft_trace_packet(const struct nft_pktinfo *pkt, @@ -62,8 +63,7 @@ static inline void nft_trace_packet(const struct nft_pktinfo *pkt, { if (static_branch_unlikely(&nft_trace_enabled)) { info->nf_trace = pkt->skb->nf_trace; - info->rule = rule; - __nft_trace_packet(pkt, verdict, info, type); + __nft_trace_packet(pkt, verdict, rule, info, type); } } @@ -110,6 +110,7 @@ static void nft_cmp16_fast_eval(const struct nft_expr *expr, static noinline void __nft_trace_verdict(const struct nft_pktinfo *pkt, struct nft_traceinfo *info, + const struct nft_rule_dp *rule, const struct nft_regs *regs) { enum nft_trace_types type; @@ -131,7 +132,7 @@ static noinline void __nft_trace_verdict(const struct nft_pktinfo *pkt, break; } - __nft_trace_packet(pkt, ®s->verdict, info, type); + __nft_trace_packet(pkt, ®s->verdict, rule, info, type); } static inline void nft_trace_verdict(const struct nft_pktinfo *pkt, @@ -139,10 +140,8 @@ static inline void nft_trace_verdict(const struct nft_pktinfo *pkt, const struct nft_rule_dp *rule, const struct nft_regs *regs) { - if (static_branch_unlikely(&nft_trace_enabled)) { - info->rule = rule; - __nft_trace_verdict(pkt, info, regs); - } + if (static_branch_unlikely(&nft_trace_enabled)) + __nft_trace_verdict(pkt, info, rule, regs); } static bool nft_payload_fast_eval(const struct nft_expr *expr, diff --git a/net/netfilter/nf_tables_trace.c b/net/netfilter/nf_tables_trace.c index e635104a42be..6d41c0bd3d78 100644 --- a/net/netfilter/nf_tables_trace.c +++ b/net/netfilter/nf_tables_trace.c @@ -125,9 +125,10 @@ static int nf_trace_fill_pkt_info(struct sk_buff *nlskb, static int nf_trace_fill_rule_info(struct sk_buff *nlskb, const struct nft_verdict *verdict, + const struct nft_rule_dp *rule, const struct nft_traceinfo *info) { - if (!info->rule || info->rule->is_last) + if (!rule || rule->is_last) return 0; /* a continue verdict with ->type == RETURN means that this is @@ -140,7 +141,7 @@ static int nf_trace_fill_rule_info(struct sk_buff *nlskb, return 0; return nla_put_be64(nlskb, NFTA_TRACE_RULE_HANDLE, - cpu_to_be64(info->rule->handle), + cpu_to_be64(rule->handle), NFTA_TRACE_PAD); } @@ -166,9 +167,9 @@ static bool nft_trace_have_verdict_chain(const struct nft_verdict *verdict, return true; } -static const struct nft_chain *nft_trace_get_chain(const struct nft_traceinfo *info) +static const struct nft_chain *nft_trace_get_chain(const struct nft_rule_dp *rule, + const struct nft_traceinfo *info) { - const struct nft_rule_dp *rule = info->rule; const struct nft_rule_dp_last *last; if (!rule) @@ -187,6 +188,7 @@ static const struct nft_chain *nft_trace_get_chain(const struct nft_traceinfo *i void nft_trace_notify(const struct nft_pktinfo *pkt, const struct nft_verdict *verdict, + const struct nft_rule_dp *rule, struct nft_traceinfo *info) { const struct nft_chain *chain; @@ -199,7 +201,7 @@ void nft_trace_notify(const struct nft_pktinfo *pkt, if (!nfnetlink_has_listeners(nft_net(pkt), NFNLGRP_NFTRACE)) return; - chain = nft_trace_get_chain(info); + chain = nft_trace_get_chain(rule, info); size = nlmsg_total_size(sizeof(struct nfgenmsg)) + nla_total_size(strlen(chain->table->name)) + @@ -248,7 +250,7 @@ void nft_trace_notify(const struct nft_pktinfo *pkt, if (nla_put_string(skb, NFTA_TRACE_TABLE, chain->table->name)) goto nla_put_failure; - if (nf_trace_fill_rule_info(skb, verdict, info)) + if (nf_trace_fill_rule_info(skb, verdict, rule, info)) goto nla_put_failure; switch (info->type) { From patchwork Fri Apr 21 23:02:02 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Pablo Neira Ayuso X-Patchwork-Id: 1772141 X-Patchwork-Delegate: pablo@netfilter.org Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@legolas.ozlabs.org Authentication-Results: legolas.ozlabs.org; spf=pass (sender SPF authorized) smtp.mailfrom=vger.kernel.org (client-ip=2620:137:e000::1:20; helo=out1.vger.email; envelope-from=netfilter-devel-owner@vger.kernel.org; receiver=) Received: from out1.vger.email (out1.vger.email [IPv6:2620:137:e000::1:20]) by legolas.ozlabs.org (Postfix) with ESMTP id 4Q396K2BpZz23s0 for ; Sat, 22 Apr 2023 09:02:49 +1000 (AEST) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S233860AbjDUXCr (ORCPT ); Fri, 21 Apr 2023 19:02:47 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:52794 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S233726AbjDUXCY (ORCPT ); Fri, 21 Apr 2023 19:02:24 -0400 Received: from mail.netfilter.org (mail.netfilter.org [217.70.188.207]) by lindbergh.monkeyblade.net (Postfix) with ESMTP id 3CAB61FCD; Fri, 21 Apr 2023 16:02:23 -0700 (PDT) From: Pablo Neira Ayuso To: netfilter-devel@vger.kernel.org Cc: davem@davemloft.net, netdev@vger.kernel.org, kuba@kernel.org, pabeni@redhat.com, edumazet@google.com Subject: [PATCH net-next 11/20] ipvs: Update width of source for ip_vs_sync_conn_options Date: Sat, 22 Apr 2023 01:02:02 +0200 Message-Id: <20230421230211.214635-12-pablo@netfilter.org> X-Mailer: git-send-email 2.30.2 In-Reply-To: <20230421230211.214635-1-pablo@netfilter.org> References: <20230421230211.214635-1-pablo@netfilter.org> MIME-Version: 1.0 X-Spam-Status: No, score=-1.9 required=5.0 tests=BAYES_00,SPF_HELO_NONE, SPF_PASS,T_SCC_BODY_TEXT_LINE autolearn=ham autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on lindbergh.monkeyblade.net Precedence: bulk List-ID: X-Mailing-List: netfilter-devel@vger.kernel.org From: Simon Horman In ip_vs_sync_conn_v0() copy is made to struct ip_vs_sync_conn_options. That structure looks like this: struct ip_vs_sync_conn_options { struct ip_vs_seq in_seq; struct ip_vs_seq out_seq; }; The source of the copy is the in_seq field of struct ip_vs_conn. Whose type is struct ip_vs_seq. Thus we can see that the source - is not as wide as the amount of data copied, which is the width of struct ip_vs_sync_conn_option. The copy is safe because the next field in is another struct ip_vs_seq. Make use of struct_group() to annotate this. Flagged by gcc-13 as: In file included from ./include/linux/string.h:254, from ./include/linux/bitmap.h:11, from ./include/linux/cpumask.h:12, from ./arch/x86/include/asm/paravirt.h:17, from ./arch/x86/include/asm/cpuid.h:62, from ./arch/x86/include/asm/processor.h:19, from ./arch/x86/include/asm/timex.h:5, from ./include/linux/timex.h:67, from ./include/linux/time32.h:13, from ./include/linux/time.h:60, from ./include/linux/stat.h:19, from ./include/linux/module.h:13, from net/netfilter/ipvs/ip_vs_sync.c:38: In function 'fortify_memcpy_chk', inlined from 'ip_vs_sync_conn_v0' at net/netfilter/ipvs/ip_vs_sync.c:606:3: ./include/linux/fortify-string.h:529:25: error: call to '__read_overflow2_field' declared with attribute warning: detected read beyond size of field (2nd parameter); maybe use struct_group()? [-Werror=attribute-warning] 529 | __read_overflow2_field(q_size_field, size); | Compile tested only. Signed-off-by: Simon Horman Reviewed-by: Horatiu Vultur Signed-off-by: Pablo Neira Ayuso --- include/net/ip_vs.h | 6 ++++-- net/netfilter/ipvs/ip_vs_sync.c | 2 +- 2 files changed, 5 insertions(+), 3 deletions(-) diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 6d71a5ff52df..e20f1f92066d 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -630,8 +630,10 @@ struct ip_vs_conn { */ struct ip_vs_app *app; /* bound ip_vs_app object */ void *app_data; /* Application private data */ - struct ip_vs_seq in_seq; /* incoming seq. struct */ - struct ip_vs_seq out_seq; /* outgoing seq. struct */ + struct_group(sync_conn_opt, + struct ip_vs_seq in_seq; /* incoming seq. struct */ + struct ip_vs_seq out_seq; /* outgoing seq. struct */ + ); const struct ip_vs_pe *pe; char *pe_data; diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 4963fec815da..d4fe7bb4f853 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -603,7 +603,7 @@ static void ip_vs_sync_conn_v0(struct netns_ipvs *ipvs, struct ip_vs_conn *cp, if (cp->flags & IP_VS_CONN_F_SEQ_MASK) { struct ip_vs_sync_conn_options *opt = (struct ip_vs_sync_conn_options *)&s[1]; - memcpy(opt, &cp->in_seq, sizeof(*opt)); + memcpy(opt, &cp->sync_conn_opt, sizeof(*opt)); } m->nr_conns++; From patchwork Fri Apr 21 23:02:03 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Pablo Neira Ayuso X-Patchwork-Id: 1772142 X-Patchwork-Delegate: pablo@netfilter.org Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@legolas.ozlabs.org Authentication-Results: legolas.ozlabs.org; spf=pass (sender SPF authorized) smtp.mailfrom=vger.kernel.org (client-ip=2620:137:e000::1:20; helo=out1.vger.email; envelope-from=netfilter-devel-owner@vger.kernel.org; receiver=) Received: from out1.vger.email (out1.vger.email [IPv6:2620:137:e000::1:20]) by legolas.ozlabs.org (Postfix) with ESMTP id 4Q396L0HFCz23s0 for ; Sat, 22 Apr 2023 09:02:50 +1000 (AEST) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S233786AbjDUXCs (ORCPT ); Fri, 21 Apr 2023 19:02:48 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:52816 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S233731AbjDUXCZ (ORCPT ); Fri, 21 Apr 2023 19:02:25 -0400 Received: from mail.netfilter.org (mail.netfilter.org [217.70.188.207]) by lindbergh.monkeyblade.net (Postfix) with ESMTP id D4D6926B2; Fri, 21 Apr 2023 16:02:23 -0700 (PDT) From: Pablo Neira Ayuso To: netfilter-devel@vger.kernel.org Cc: davem@davemloft.net, netdev@vger.kernel.org, kuba@kernel.org, pabeni@redhat.com, edumazet@google.com Subject: [PATCH net-next 12/20] ipvs: Consistently use array_size() in ip_vs_conn_init() Date: Sat, 22 Apr 2023 01:02:03 +0200 Message-Id: <20230421230211.214635-13-pablo@netfilter.org> X-Mailer: git-send-email 2.30.2 In-Reply-To: <20230421230211.214635-1-pablo@netfilter.org> References: <20230421230211.214635-1-pablo@netfilter.org> MIME-Version: 1.0 X-Spam-Status: No, score=-1.9 required=5.0 tests=BAYES_00,SPF_HELO_NONE, SPF_PASS,T_SCC_BODY_TEXT_LINE autolearn=ham autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on lindbergh.monkeyblade.net Precedence: bulk List-ID: X-Mailing-List: netfilter-devel@vger.kernel.org From: Simon Horman Consistently use array_size() to calculate the size of ip_vs_conn_tab in bytes. Flagged by Coccinelle: WARNING: array_size is already used (line 1498) to compute the same size No functional change intended. Compile tested only. Signed-off-by: Simon Horman Reviewed-by: Horatiu Vultur Signed-off-by: Pablo Neira Ayuso --- net/netfilter/ipvs/ip_vs_conn.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 13534e02346c..928e64653837 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1481,6 +1481,7 @@ void __net_exit ip_vs_conn_net_cleanup(struct netns_ipvs *ipvs) int __init ip_vs_conn_init(void) { + size_t tab_array_size; int idx; /* Compute size and mask */ @@ -1494,8 +1495,9 @@ int __init ip_vs_conn_init(void) /* * Allocate the connection hash table and initialize its list heads */ - ip_vs_conn_tab = vmalloc(array_size(ip_vs_conn_tab_size, - sizeof(*ip_vs_conn_tab))); + tab_array_size = array_size(ip_vs_conn_tab_size, + sizeof(*ip_vs_conn_tab)); + ip_vs_conn_tab = vmalloc(tab_array_size); if (!ip_vs_conn_tab) return -ENOMEM; @@ -1508,10 +1510,8 @@ int __init ip_vs_conn_init(void) return -ENOMEM; } - pr_info("Connection hash table configured " - "(size=%d, memory=%ldKbytes)\n", - ip_vs_conn_tab_size, - (long)(ip_vs_conn_tab_size*sizeof(*ip_vs_conn_tab))/1024); + pr_info("Connection hash table configured (size=%d, memory=%zdKbytes)\n", + ip_vs_conn_tab_size, tab_array_size / 1024); IP_VS_DBG(0, "Each connection entry needs %zd bytes at least\n", sizeof(struct ip_vs_conn)); From patchwork Fri Apr 21 23:02:04 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Pablo Neira Ayuso X-Patchwork-Id: 1772144 X-Patchwork-Delegate: pablo@netfilter.org Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@legolas.ozlabs.org Authentication-Results: legolas.ozlabs.org; spf=pass (sender SPF authorized) smtp.mailfrom=vger.kernel.org (client-ip=2620:137:e000::1:20; helo=out1.vger.email; envelope-from=netfilter-devel-owner@vger.kernel.org; receiver=) Received: from out1.vger.email (out1.vger.email [IPv6:2620:137:e000::1:20]) by legolas.ozlabs.org (Postfix) with ESMTP id 4Q396M2QgMz23s0 for ; Sat, 22 Apr 2023 09:02:51 +1000 (AEST) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S233554AbjDUXCt (ORCPT ); Fri, 21 Apr 2023 19:02:49 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:53034 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S233792AbjDUXCa (ORCPT ); Fri, 21 Apr 2023 19:02:30 -0400 Received: from mail.netfilter.org (mail.netfilter.org [217.70.188.207]) by lindbergh.monkeyblade.net (Postfix) with ESMTP id 8437F1BF0; Fri, 21 Apr 2023 16:02:24 -0700 (PDT) From: Pablo Neira Ayuso To: netfilter-devel@vger.kernel.org Cc: davem@davemloft.net, netdev@vger.kernel.org, kuba@kernel.org, pabeni@redhat.com, edumazet@google.com Subject: [PATCH net-next 13/20] ipvs: Remove {Enter,Leave}Function Date: Sat, 22 Apr 2023 01:02:04 +0200 Message-Id: <20230421230211.214635-14-pablo@netfilter.org> X-Mailer: git-send-email 2.30.2 In-Reply-To: <20230421230211.214635-1-pablo@netfilter.org> References: <20230421230211.214635-1-pablo@netfilter.org> MIME-Version: 1.0 X-Spam-Status: No, score=-1.9 required=5.0 tests=BAYES_00,SPF_HELO_NONE, SPF_PASS,T_SCC_BODY_TEXT_LINE autolearn=ham autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on lindbergh.monkeyblade.net Precedence: bulk List-ID: X-Mailing-List: netfilter-devel@vger.kernel.org From: Simon Horman Remove EnterFunction and LeaveFunction. These debugging macros seem well past their use-by date. And seem to have little value these days. Removing them allows some trivial cleanup of some exit paths for some functions. These are also included in this patch. There is likely scope for further cleanup of both debugging and unwind paths. But let's leave that for another day. Only intended to change debug output, and only when CONFIG_IP_VS_DEBUG is enabled. Compile tested only. Signed-off-by: Simon Horman Reviewed-by: Horatiu Vultur Signed-off-by: Pablo Neira Ayuso --- include/net/ip_vs.h | 20 ----------- net/netfilter/ipvs/ip_vs_core.c | 8 ----- net/netfilter/ipvs/ip_vs_ctl.c | 26 +------------- net/netfilter/ipvs/ip_vs_sync.c | 5 --- net/netfilter/ipvs/ip_vs_xmit.c | 62 +++++---------------------------- 5 files changed, 9 insertions(+), 112 deletions(-) diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index e20f1f92066d..a3adc246ee31 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -265,26 +265,6 @@ static inline const char *ip_vs_dbg_addr(int af, char *buf, size_t buf_len, pr_err(msg, ##__VA_ARGS__); \ } while (0) -#ifdef CONFIG_IP_VS_DEBUG -#define EnterFunction(level) \ - do { \ - if (level <= ip_vs_get_debug_level()) \ - printk(KERN_DEBUG \ - pr_fmt("Enter: %s, %s line %i\n"), \ - __func__, __FILE__, __LINE__); \ - } while (0) -#define LeaveFunction(level) \ - do { \ - if (level <= ip_vs_get_debug_level()) \ - printk(KERN_DEBUG \ - pr_fmt("Leave: %s, %s line %i\n"), \ - __func__, __FILE__, __LINE__); \ - } while (0) -#else -#define EnterFunction(level) do {} while (0) -#define LeaveFunction(level) do {} while (0) -#endif - /* The port number of FTP service (in network order). */ #define FTPPORT cpu_to_be16(21) #define FTPDATA cpu_to_be16(20) diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 2fcc26507d69..cb83ca506c5c 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1140,7 +1140,6 @@ struct ip_vs_conn *ip_vs_new_conn_out(struct ip_vs_service *svc, __be16 vport; unsigned int flags; - EnterFunction(12); vaddr = &svc->addr; vport = svc->port; daddr = &iph->saddr; @@ -1208,7 +1207,6 @@ struct ip_vs_conn *ip_vs_new_conn_out(struct ip_vs_service *svc, IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport), IP_VS_DBG_ADDR(cp->af, &cp->daddr), ntohs(cp->dport), cp->flags, refcount_read(&cp->refcnt)); - LeaveFunction(12); return cp; } @@ -1316,13 +1314,11 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, ip_vs_update_conntrack(skb, cp, 0); ip_vs_conn_put(cp); - LeaveFunction(11); return NF_ACCEPT; drop: ip_vs_conn_put(cp); kfree_skb(skb); - LeaveFunction(11); return NF_STOLEN; } @@ -1341,8 +1337,6 @@ ip_vs_out_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *stat int af = state->pf; struct sock *sk; - EnterFunction(11); - /* Already marked as IPVS request or reply? */ if (skb->ipvs_property) return NF_ACCEPT; @@ -2365,7 +2359,6 @@ static void __net_exit __ip_vs_dev_cleanup_batch(struct list_head *net_list) struct netns_ipvs *ipvs; struct net *net; - EnterFunction(2); list_for_each_entry(net, net_list, exit_list) { ipvs = net_ipvs(net); ip_vs_unregister_hooks(ipvs, AF_INET); @@ -2374,7 +2367,6 @@ static void __net_exit __ip_vs_dev_cleanup_batch(struct list_head *net_list) smp_wmb(); ip_vs_sync_net_cleanup(ipvs); } - LeaveFunction(2); } static struct pernet_operations ipvs_core_ops = { diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 2a5ed71c82c3..62606fb44d02 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -1061,8 +1061,6 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) unsigned int atype; int ret; - EnterFunction(2); - #ifdef CONFIG_IP_VS_IPV6 if (udest->af == AF_INET6) { atype = ipv6_addr_type(&udest->addr.in6); @@ -1111,7 +1109,6 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) spin_lock_init(&dest->dst_lock); __ip_vs_update_dest(svc, dest, udest, 1); - LeaveFunction(2); return 0; err_stats: @@ -1134,8 +1131,6 @@ ip_vs_add_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) __be16 dport = udest->port; int ret; - EnterFunction(2); - if (udest->weight < 0) { pr_err("%s(): server weight less than zero\n", __func__); return -ERANGE; @@ -1183,7 +1178,7 @@ ip_vs_add_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) ret = ip_vs_start_estimator(svc->ipvs, &dest->stats); if (ret < 0) - goto err; + return ret; __ip_vs_update_dest(svc, dest, udest, 1); } else { /* @@ -1192,9 +1187,6 @@ ip_vs_add_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) ret = ip_vs_new_dest(svc, udest); } -err: - LeaveFunction(2); - return ret; } @@ -1209,8 +1201,6 @@ ip_vs_edit_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) union nf_inet_addr daddr; __be16 dport = udest->port; - EnterFunction(2); - if (udest->weight < 0) { pr_err("%s(): server weight less than zero\n", __func__); return -ERANGE; @@ -1242,7 +1232,6 @@ ip_vs_edit_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) } __ip_vs_update_dest(svc, dest, udest, 0); - LeaveFunction(2); return 0; } @@ -1317,8 +1306,6 @@ ip_vs_del_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) struct ip_vs_dest *dest; __be16 dport = udest->port; - EnterFunction(2); - /* We use function that requires RCU lock */ rcu_read_lock(); dest = ip_vs_lookup_dest(svc, udest->af, &udest->addr, dport); @@ -1339,8 +1326,6 @@ ip_vs_del_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) */ __ip_vs_del_dest(svc->ipvs, dest, false); - LeaveFunction(2); - return 0; } @@ -1746,7 +1731,6 @@ void ip_vs_service_nets_cleanup(struct list_head *net_list) struct netns_ipvs *ipvs; struct net *net; - EnterFunction(2); /* Check for "full" addressed entries */ mutex_lock(&__ip_vs_mutex); list_for_each_entry(net, net_list, exit_list) { @@ -1754,7 +1738,6 @@ void ip_vs_service_nets_cleanup(struct list_head *net_list) ip_vs_flush(ipvs, true); } mutex_unlock(&__ip_vs_mutex); - LeaveFunction(2); } /* Put all references for device (dst_cache) */ @@ -1792,7 +1775,6 @@ static int ip_vs_dst_event(struct notifier_block *this, unsigned long event, if (event != NETDEV_DOWN || !ipvs) return NOTIFY_DONE; IP_VS_DBG(3, "%s() dev=%s\n", __func__, dev->name); - EnterFunction(2); mutex_lock(&__ip_vs_mutex); for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { hlist_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) { @@ -1821,7 +1803,6 @@ static int ip_vs_dst_event(struct notifier_block *this, unsigned long event, } spin_unlock_bh(&ipvs->dest_trash_lock); mutex_unlock(&__ip_vs_mutex); - LeaveFunction(2); return NOTIFY_DONE; } @@ -4537,8 +4518,6 @@ int __init ip_vs_control_init(void) int idx; int ret; - EnterFunction(2); - /* Initialize svc_table, ip_vs_svc_fwm_table */ for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { INIT_HLIST_HEAD(&ip_vs_svc_table[idx]); @@ -4551,15 +4530,12 @@ int __init ip_vs_control_init(void) if (ret < 0) return ret; - LeaveFunction(2); return 0; } void ip_vs_control_cleanup(void) { - EnterFunction(2); unregister_netdevice_notifier(&ip_vs_dst_notifier); /* relying on common rcu_barrier() in ip_vs_cleanup() */ - LeaveFunction(2); } diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index d4fe7bb4f853..264f2f87a437 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -1582,13 +1582,11 @@ ip_vs_send_async(struct socket *sock, const char *buffer, const size_t length) struct kvec iov; int len; - EnterFunction(7); iov.iov_base = (void *)buffer; iov.iov_len = length; len = kernel_sendmsg(sock, &msg, &iov, 1, (size_t)(length)); - LeaveFunction(7); return len; } @@ -1614,15 +1612,12 @@ ip_vs_receive(struct socket *sock, char *buffer, const size_t buflen) struct kvec iov = {buffer, buflen}; int len; - EnterFunction(7); - /* Receive a packet */ iov_iter_kvec(&msg.msg_iter, ITER_DEST, &iov, 1, buflen); len = sock_recvmsg(sock, &msg, MSG_DONTWAIT); if (len < 0) return len; - LeaveFunction(7); return len; } diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 99c349c0d968..feb1d7fcb09f 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -706,8 +706,6 @@ ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, { struct iphdr *iph = ip_hdr(skb); - EnterFunction(10); - if (__ip_vs_get_out_rt(cp->ipvs, cp->af, skb, NULL, iph->daddr, IP_VS_RT_MODE_NON_LOCAL, NULL, ipvsh) < 0) goto tx_error; @@ -719,12 +717,10 @@ ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, ip_vs_send_or_cont(NFPROTO_IPV4, skb, cp, 0); - LeaveFunction(10); return NF_STOLEN; tx_error: kfree_skb(skb); - LeaveFunction(10); return NF_STOLEN; } @@ -735,8 +731,6 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, { struct ipv6hdr *iph = ipv6_hdr(skb); - EnterFunction(10); - if (__ip_vs_get_out_rt_v6(cp->ipvs, cp->af, skb, NULL, &iph->daddr, NULL, ipvsh, 0, IP_VS_RT_MODE_NON_LOCAL) < 0) @@ -747,12 +741,10 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, ip_vs_send_or_cont(NFPROTO_IPV6, skb, cp, 0); - LeaveFunction(10); return NF_STOLEN; tx_error: kfree_skb(skb); - LeaveFunction(10); return NF_STOLEN; } #endif @@ -768,8 +760,6 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, struct rtable *rt; /* Route to the other host */ int local, rc, was_input; - EnterFunction(10); - /* check if it is a connection of no-client-port */ if (unlikely(cp->flags & IP_VS_CONN_F_NO_CPORT)) { __be16 _pt, *p; @@ -839,12 +829,10 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, rc = ip_vs_nat_send_or_cont(NFPROTO_IPV4, skb, cp, local); - LeaveFunction(10); return rc; tx_error: kfree_skb(skb); - LeaveFunction(10); return NF_STOLEN; } @@ -856,8 +844,6 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, struct rt6_info *rt; /* Route to the other host */ int local, rc; - EnterFunction(10); - /* check if it is a connection of no-client-port */ if (unlikely(cp->flags & IP_VS_CONN_F_NO_CPORT && !ipvsh->fragoffs)) { __be16 _pt, *p; @@ -927,11 +913,9 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, rc = ip_vs_nat_send_or_cont(NFPROTO_IPV6, skb, cp, local); - LeaveFunction(10); return rc; tx_error: - LeaveFunction(10); kfree_skb(skb); return NF_STOLEN; } @@ -1149,8 +1133,6 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, int tun_type, gso_type; int tun_flags; - EnterFunction(10); - local = __ip_vs_get_out_rt(ipvs, cp->af, skb, cp->dest, cp->daddr.ip, IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL | @@ -1199,7 +1181,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, &next_protocol, NULL, &dsfield, &ttl, dfp); if (IS_ERR(skb)) - goto tx_error; + return NF_STOLEN; gso_type = __tun_gso_type_mask(AF_INET, cp->af); if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) { @@ -1267,14 +1249,10 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, else if (ret == NF_DROP) kfree_skb(skb); - LeaveFunction(10); - return NF_STOLEN; tx_error: - if (!IS_ERR(skb)) - kfree_skb(skb); - LeaveFunction(10); + kfree_skb(skb); return NF_STOLEN; } @@ -1298,8 +1276,6 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, int tun_type, gso_type; int tun_flags; - EnterFunction(10); - local = __ip_vs_get_out_rt_v6(ipvs, cp->af, skb, cp->dest, &cp->daddr.in6, &saddr, ipvsh, 1, @@ -1347,7 +1323,7 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, &next_protocol, &payload_len, &dsfield, &ttl, NULL); if (IS_ERR(skb)) - goto tx_error; + return NF_STOLEN; gso_type = __tun_gso_type_mask(AF_INET6, cp->af); if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) { @@ -1414,14 +1390,10 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, else if (ret == NF_DROP) kfree_skb(skb); - LeaveFunction(10); - return NF_STOLEN; tx_error: - if (!IS_ERR(skb)) - kfree_skb(skb); - LeaveFunction(10); + kfree_skb(skb); return NF_STOLEN; } #endif @@ -1437,8 +1409,6 @@ ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, { int local; - EnterFunction(10); - local = __ip_vs_get_out_rt(cp->ipvs, cp->af, skb, cp->dest, cp->daddr.ip, IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL | @@ -1455,12 +1425,10 @@ ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, ip_vs_send_or_cont(NFPROTO_IPV4, skb, cp, 0); - LeaveFunction(10); return NF_STOLEN; tx_error: kfree_skb(skb); - LeaveFunction(10); return NF_STOLEN; } @@ -1471,8 +1439,6 @@ ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, { int local; - EnterFunction(10); - local = __ip_vs_get_out_rt_v6(cp->ipvs, cp->af, skb, cp->dest, &cp->daddr.in6, NULL, ipvsh, 0, @@ -1489,12 +1455,10 @@ ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, ip_vs_send_or_cont(NFPROTO_IPV6, skb, cp, 0); - LeaveFunction(10); return NF_STOLEN; tx_error: kfree_skb(skb); - LeaveFunction(10); return NF_STOLEN; } #endif @@ -1514,8 +1478,6 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, int local; int rt_mode, was_input; - EnterFunction(10); - /* The ICMP packet for VS/TUN, VS/DR and LOCALNODE will be forwarded directly here, because there is no need to translate address/port back */ @@ -1526,7 +1488,7 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, rc = NF_ACCEPT; /* do not touch skb anymore */ atomic_inc(&cp->in_pkts); - goto out; + return rc; } /* @@ -1582,14 +1544,11 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, /* Another hack: avoid icmp_send in ip_fragment */ skb->ignore_df = 1; - rc = ip_vs_nat_send_or_cont(NFPROTO_IPV4, skb, cp, local); - goto out; + return ip_vs_nat_send_or_cont(NFPROTO_IPV4, skb, cp, local); tx_error: kfree_skb(skb); rc = NF_STOLEN; - out: - LeaveFunction(10); return rc; } @@ -1604,8 +1563,6 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, int local; int rt_mode; - EnterFunction(10); - /* The ICMP packet for VS/TUN, VS/DR and LOCALNODE will be forwarded directly here, because there is no need to translate address/port back */ @@ -1616,7 +1573,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, rc = NF_ACCEPT; /* do not touch skb anymore */ atomic_inc(&cp->in_pkts); - goto out; + return rc; } /* @@ -1671,14 +1628,11 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, /* Another hack: avoid icmp_send in ip_fragment */ skb->ignore_df = 1; - rc = ip_vs_nat_send_or_cont(NFPROTO_IPV6, skb, cp, local); - goto out; + return ip_vs_nat_send_or_cont(NFPROTO_IPV6, skb, cp, local); tx_error: kfree_skb(skb); rc = NF_STOLEN; -out: - LeaveFunction(10); return rc; } #endif From patchwork Fri Apr 21 23:02:05 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Pablo Neira Ayuso X-Patchwork-Id: 1772143 X-Patchwork-Delegate: pablo@netfilter.org Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@legolas.ozlabs.org Authentication-Results: legolas.ozlabs.org; spf=pass (sender SPF authorized) smtp.mailfrom=vger.kernel.org (client-ip=2620:137:e000::1:20; helo=out1.vger.email; envelope-from=netfilter-devel-owner@vger.kernel.org; receiver=) Received: from out1.vger.email (out1.vger.email [IPv6:2620:137:e000::1:20]) by legolas.ozlabs.org (Postfix) with ESMTP id 4Q396L361Nz23tp for ; Sat, 22 Apr 2023 09:02:50 +1000 (AEST) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S233520AbjDUXCt (ORCPT ); Fri, 21 Apr 2023 19:02:49 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:53020 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S233784AbjDUXCa (ORCPT ); Fri, 21 Apr 2023 19:02:30 -0400 Received: from mail.netfilter.org (mail.netfilter.org [217.70.188.207]) by lindbergh.monkeyblade.net (Postfix) with ESMTP id 091092710; Fri, 21 Apr 2023 16:02:25 -0700 (PDT) From: Pablo Neira Ayuso To: netfilter-devel@vger.kernel.org Cc: davem@davemloft.net, netdev@vger.kernel.org, kuba@kernel.org, pabeni@redhat.com, edumazet@google.com Subject: [PATCH net-next 14/20] ipvs: Correct spelling in comments Date: Sat, 22 Apr 2023 01:02:05 +0200 Message-Id: <20230421230211.214635-15-pablo@netfilter.org> X-Mailer: git-send-email 2.30.2 In-Reply-To: <20230421230211.214635-1-pablo@netfilter.org> References: <20230421230211.214635-1-pablo@netfilter.org> MIME-Version: 1.0 X-Spam-Status: No, score=-1.9 required=5.0 tests=BAYES_00,SPF_HELO_NONE, SPF_PASS,T_SCC_BODY_TEXT_LINE autolearn=ham autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on lindbergh.monkeyblade.net Precedence: bulk List-ID: X-Mailing-List: netfilter-devel@vger.kernel.org From: Simon Horman Correct some spelling errors flagged by codespell and found by inspection. Signed-off-by: Simon Horman Reviewed-by: Horatiu Vultur Signed-off-by: Pablo Neira Ayuso --- include/net/ip_vs.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index a3adc246ee31..ff406ef4fd4a 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -584,7 +584,7 @@ struct ip_vs_conn { spinlock_t lock; /* lock for state transition */ volatile __u16 state; /* state info */ volatile __u16 old_state; /* old state, to be used for - * state transition triggerd + * state transition triggered * synchronization */ __u32 fwmark; /* Fire wall mark from skb */ @@ -635,7 +635,7 @@ struct ip_vs_service_user_kern { u16 protocol; union nf_inet_addr addr; /* virtual ip address */ __be16 port; - u32 fwmark; /* firwall mark of service */ + u32 fwmark; /* firewall mark of service */ /* virtual service options */ char *sched_name; @@ -1036,7 +1036,7 @@ struct netns_ipvs { struct ipvs_sync_daemon_cfg bcfg; /* Backup Configuration */ /* net name space ptr */ struct net *net; /* Needed by timer routines */ - /* Number of heterogeneous destinations, needed becaus heterogeneous + /* Number of heterogeneous destinations, needed because heterogeneous * are not supported when synchronization is enabled. */ unsigned int mixed_address_family_dests; From patchwork Fri Apr 21 23:02:06 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Pablo Neira Ayuso X-Patchwork-Id: 1772145 X-Patchwork-Delegate: pablo@netfilter.org Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@legolas.ozlabs.org Authentication-Results: legolas.ozlabs.org; spf=pass (sender SPF authorized) smtp.mailfrom=vger.kernel.org (client-ip=2620:137:e000::1:20; helo=out1.vger.email; envelope-from=netfilter-devel-owner@vger.kernel.org; receiver=) Received: from out1.vger.email (out1.vger.email [IPv6:2620:137:e000::1:20]) by legolas.ozlabs.org (Postfix) with ESMTP id 4Q396P5LYlz23s0 for ; Sat, 22 Apr 2023 09:02:53 +1000 (AEST) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S233726AbjDUXCu (ORCPT ); Fri, 21 Apr 2023 19:02:50 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:53062 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S233811AbjDUXCb (ORCPT ); Fri, 21 Apr 2023 19:02:31 -0400 Received: from mail.netfilter.org (mail.netfilter.org [217.70.188.207]) by lindbergh.monkeyblade.net (Postfix) with ESMTP id 981002D40; Fri, 21 Apr 2023 16:02:25 -0700 (PDT) From: Pablo Neira Ayuso To: netfilter-devel@vger.kernel.org Cc: davem@davemloft.net, netdev@vger.kernel.org, kuba@kernel.org, pabeni@redhat.com, edumazet@google.com Subject: [PATCH net-next 15/20] netfilter: nf_tables: extended netlink error reporting for netdevice Date: Sat, 22 Apr 2023 01:02:06 +0200 Message-Id: <20230421230211.214635-16-pablo@netfilter.org> X-Mailer: git-send-email 2.30.2 In-Reply-To: <20230421230211.214635-1-pablo@netfilter.org> References: <20230421230211.214635-1-pablo@netfilter.org> MIME-Version: 1.0 X-Spam-Status: No, score=-1.9 required=5.0 tests=BAYES_00,SPF_HELO_NONE, SPF_PASS,T_SCC_BODY_TEXT_LINE autolearn=ham autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on lindbergh.monkeyblade.net Precedence: bulk List-ID: X-Mailing-List: netfilter-devel@vger.kernel.org Flowtable and netdev chains are bound to one or several netdevice, extend netlink error reporting to specify the the netdevice that triggers the error. Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 38 ++++++++++++++++++++++------------- 1 file changed, 24 insertions(+), 14 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 44ebc5f9598e..0fd4e28fbb60 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1954,7 +1954,8 @@ static struct nft_hook *nft_hook_list_find(struct list_head *hook_list, static int nf_tables_parse_netdev_hooks(struct net *net, const struct nlattr *attr, - struct list_head *hook_list) + struct list_head *hook_list, + struct netlink_ext_ack *extack) { struct nft_hook *hook, *next; const struct nlattr *tmp; @@ -1968,10 +1969,12 @@ static int nf_tables_parse_netdev_hooks(struct net *net, hook = nft_netdev_hook_alloc(net, tmp); if (IS_ERR(hook)) { + NL_SET_BAD_ATTR(extack, tmp); err = PTR_ERR(hook); goto err_hook; } if (nft_hook_list_find(hook_list, hook)) { + NL_SET_BAD_ATTR(extack, tmp); kfree(hook); err = -EEXIST; goto err_hook; @@ -2004,20 +2007,23 @@ struct nft_chain_hook { static int nft_chain_parse_netdev(struct net *net, struct nlattr *tb[], - struct list_head *hook_list) + struct list_head *hook_list, + struct netlink_ext_ack *extack) { struct nft_hook *hook; int err; if (tb[NFTA_HOOK_DEV]) { hook = nft_netdev_hook_alloc(net, tb[NFTA_HOOK_DEV]); - if (IS_ERR(hook)) + if (IS_ERR(hook)) { + NL_SET_BAD_ATTR(extack, tb[NFTA_HOOK_DEV]); return PTR_ERR(hook); + } list_add_tail(&hook->list, hook_list); } else if (tb[NFTA_HOOK_DEVS]) { err = nf_tables_parse_netdev_hooks(net, tb[NFTA_HOOK_DEVS], - hook_list); + hook_list, extack); if (err < 0) return err; @@ -2085,7 +2091,7 @@ static int nft_chain_parse_hook(struct net *net, INIT_LIST_HEAD(&hook->list); if (nft_base_chain_netdev(family, hook->num)) { - err = nft_chain_parse_netdev(net, ha, &hook->list); + err = nft_chain_parse_netdev(net, ha, &hook->list, extack); if (err < 0) { module_put(type->owner); return err; @@ -7560,7 +7566,8 @@ static const struct nla_policy nft_flowtable_hook_policy[NFTA_FLOWTABLE_HOOK_MAX static int nft_flowtable_parse_hook(const struct nft_ctx *ctx, const struct nlattr *attr, struct nft_flowtable_hook *flowtable_hook, - struct nft_flowtable *flowtable, bool add) + struct nft_flowtable *flowtable, + struct netlink_ext_ack *extack, bool add) { struct nlattr *tb[NFTA_FLOWTABLE_HOOK_MAX + 1]; struct nft_hook *hook; @@ -7607,7 +7614,8 @@ static int nft_flowtable_parse_hook(const struct nft_ctx *ctx, if (tb[NFTA_FLOWTABLE_HOOK_DEVS]) { err = nf_tables_parse_netdev_hooks(ctx->net, tb[NFTA_FLOWTABLE_HOOK_DEVS], - &flowtable_hook->list); + &flowtable_hook->list, + extack); if (err < 0) return err; } @@ -7750,7 +7758,8 @@ static void nft_flowtable_hooks_destroy(struct list_head *hook_list) } static int nft_flowtable_update(struct nft_ctx *ctx, const struct nlmsghdr *nlh, - struct nft_flowtable *flowtable) + struct nft_flowtable *flowtable, + struct netlink_ext_ack *extack) { const struct nlattr * const *nla = ctx->nla; struct nft_flowtable_hook flowtable_hook; @@ -7761,7 +7770,7 @@ static int nft_flowtable_update(struct nft_ctx *ctx, const struct nlmsghdr *nlh, int err; err = nft_flowtable_parse_hook(ctx, nla[NFTA_FLOWTABLE_HOOK], - &flowtable_hook, flowtable, false); + &flowtable_hook, flowtable, extack, false); if (err < 0) return err; @@ -7866,7 +7875,7 @@ static int nf_tables_newflowtable(struct sk_buff *skb, nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); - return nft_flowtable_update(&ctx, info->nlh, flowtable); + return nft_flowtable_update(&ctx, info->nlh, flowtable, extack); } nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); @@ -7907,7 +7916,7 @@ static int nf_tables_newflowtable(struct sk_buff *skb, goto err3; err = nft_flowtable_parse_hook(&ctx, nla[NFTA_FLOWTABLE_HOOK], - &flowtable_hook, flowtable, true); + &flowtable_hook, flowtable, extack, true); if (err < 0) goto err4; @@ -7959,7 +7968,8 @@ static void nft_flowtable_hook_release(struct nft_flowtable_hook *flowtable_hook } static int nft_delflowtable_hook(struct nft_ctx *ctx, - struct nft_flowtable *flowtable) + struct nft_flowtable *flowtable, + struct netlink_ext_ack *extack) { const struct nlattr * const *nla = ctx->nla; struct nft_flowtable_hook flowtable_hook; @@ -7969,7 +7979,7 @@ static int nft_delflowtable_hook(struct nft_ctx *ctx, int err; err = nft_flowtable_parse_hook(ctx, nla[NFTA_FLOWTABLE_HOOK], - &flowtable_hook, flowtable, false); + &flowtable_hook, flowtable, extack, false); if (err < 0) return err; @@ -8051,7 +8061,7 @@ static int nf_tables_delflowtable(struct sk_buff *skb, nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); if (nla[NFTA_FLOWTABLE_HOOK]) - return nft_delflowtable_hook(&ctx, flowtable); + return nft_delflowtable_hook(&ctx, flowtable, extack); if (flowtable->use > 0) { NL_SET_BAD_ATTR(extack, attr); From patchwork Fri Apr 21 23:02:07 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Pablo Neira Ayuso X-Patchwork-Id: 1772147 X-Patchwork-Delegate: pablo@netfilter.org Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@legolas.ozlabs.org Authentication-Results: legolas.ozlabs.org; spf=pass (sender SPF authorized) smtp.mailfrom=vger.kernel.org (client-ip=2620:137:e000::1:20; helo=out1.vger.email; envelope-from=netfilter-devel-owner@vger.kernel.org; receiver=) Received: from out1.vger.email (out1.vger.email [IPv6:2620:137:e000::1:20]) by legolas.ozlabs.org (Postfix) with ESMTP id 4Q396X370Wz23s0 for ; Sat, 22 Apr 2023 09:03:00 +1000 (AEST) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S233811AbjDUXC6 (ORCPT ); Fri, 21 Apr 2023 19:02:58 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:52812 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S233844AbjDUXCr (ORCPT ); Fri, 21 Apr 2023 19:02:47 -0400 Received: from mail.netfilter.org (mail.netfilter.org [217.70.188.207]) by lindbergh.monkeyblade.net (Postfix) with ESMTP id 9984910E4; Fri, 21 Apr 2023 16:02:26 -0700 (PDT) From: Pablo Neira Ayuso To: netfilter-devel@vger.kernel.org Cc: davem@davemloft.net, netdev@vger.kernel.org, kuba@kernel.org, pabeni@redhat.com, edumazet@google.com Subject: [PATCH net-next 16/20] netfilter: nf_tables: do not send complete notification of deletions Date: Sat, 22 Apr 2023 01:02:07 +0200 Message-Id: <20230421230211.214635-17-pablo@netfilter.org> X-Mailer: git-send-email 2.30.2 In-Reply-To: <20230421230211.214635-1-pablo@netfilter.org> References: <20230421230211.214635-1-pablo@netfilter.org> MIME-Version: 1.0 X-Spam-Status: No, score=-1.9 required=5.0 tests=BAYES_00,SPF_HELO_NONE, SPF_PASS,T_SCC_BODY_TEXT_LINE autolearn=ham autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on lindbergh.monkeyblade.net Precedence: bulk List-ID: X-Mailing-List: netfilter-devel@vger.kernel.org In most cases, table, name and handle is sufficient for userspace to identify an object that has been deleted. Skipping unneeded fields in the netlink attributes in the message saves bandwidth (ie. less chances of hitting ENOBUFS). Rules are an exception: the existing userspace monitor code relies on the rule definition. This exception can be removed by implementing a rule cache in userspace, this is already supported by the tracing infrastructure. Regarding flowtables, incremental deletion of devices is possible. Skipping a full notification allows userspace to differentiate between flowtable removal and incremental removal of devices. Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 70 +++++++++++++++++++++++++---------- 1 file changed, 51 insertions(+), 19 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 0fd4e28fbb60..3f95fb24a0bc 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -819,12 +819,20 @@ static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net, goto nla_put_failure; if (nla_put_string(skb, NFTA_TABLE_NAME, table->name) || - nla_put_be32(skb, NFTA_TABLE_FLAGS, - htonl(table->flags & NFT_TABLE_F_MASK)) || nla_put_be32(skb, NFTA_TABLE_USE, htonl(table->use)) || nla_put_be64(skb, NFTA_TABLE_HANDLE, cpu_to_be64(table->handle), NFTA_TABLE_PAD)) goto nla_put_failure; + + if (event == NFT_MSG_DELTABLE) { + nlmsg_end(skb, nlh); + return 0; + } + + if (nla_put_be32(skb, NFTA_TABLE_FLAGS, + htonl(table->flags & NFT_TABLE_F_MASK))) + goto nla_put_failure; + if (nft_table_has_owner(table) && nla_put_be32(skb, NFTA_TABLE_OWNER, htonl(table->nlpid))) goto nla_put_failure; @@ -1626,13 +1634,16 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net, if (!nlh) goto nla_put_failure; - if (nla_put_string(skb, NFTA_CHAIN_TABLE, table->name)) - goto nla_put_failure; - if (nla_put_be64(skb, NFTA_CHAIN_HANDLE, cpu_to_be64(chain->handle), + if (nla_put_string(skb, NFTA_CHAIN_TABLE, table->name) || + nla_put_string(skb, NFTA_CHAIN_NAME, chain->name) || + nla_put_be64(skb, NFTA_CHAIN_HANDLE, cpu_to_be64(chain->handle), NFTA_CHAIN_PAD)) goto nla_put_failure; - if (nla_put_string(skb, NFTA_CHAIN_NAME, chain->name)) - goto nla_put_failure; + + if (event == NFT_MSG_DELCHAIN) { + nlmsg_end(skb, nlh); + return 0; + } if (nft_is_base_chain(chain)) { const struct nft_base_chain *basechain = nft_base_chain(chain); @@ -4150,6 +4161,12 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, if (nla_put_be64(skb, NFTA_SET_HANDLE, cpu_to_be64(set->handle), NFTA_SET_PAD)) goto nla_put_failure; + + if (event == NFT_MSG_DELSET) { + nlmsg_end(skb, nlh); + return 0; + } + if (set->flags != 0) if (nla_put_be32(skb, NFTA_SET_FLAGS, htonl(set->flags))) goto nla_put_failure; @@ -7154,13 +7171,20 @@ static int nf_tables_fill_obj_info(struct sk_buff *skb, struct net *net, if (nla_put_string(skb, NFTA_OBJ_TABLE, table->name) || nla_put_string(skb, NFTA_OBJ_NAME, obj->key.name) || - nla_put_be32(skb, NFTA_OBJ_TYPE, htonl(obj->ops->type->type)) || - nla_put_be32(skb, NFTA_OBJ_USE, htonl(obj->use)) || - nft_object_dump(skb, NFTA_OBJ_DATA, obj, reset) || nla_put_be64(skb, NFTA_OBJ_HANDLE, cpu_to_be64(obj->handle), NFTA_OBJ_PAD)) goto nla_put_failure; + if (event == NFT_MSG_DELOBJ) { + nlmsg_end(skb, nlh); + return 0; + } + + if (nla_put_be32(skb, NFTA_OBJ_TYPE, htonl(obj->ops->type->type)) || + nla_put_be32(skb, NFTA_OBJ_USE, htonl(obj->use)) || + nft_object_dump(skb, NFTA_OBJ_DATA, obj, reset)) + goto nla_put_failure; + if (obj->udata && nla_put(skb, NFTA_OBJ_USERDATA, obj->udlen, obj->udata)) goto nla_put_failure; @@ -8089,9 +8113,16 @@ static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net, if (nla_put_string(skb, NFTA_FLOWTABLE_TABLE, flowtable->table->name) || nla_put_string(skb, NFTA_FLOWTABLE_NAME, flowtable->name) || - nla_put_be32(skb, NFTA_FLOWTABLE_USE, htonl(flowtable->use)) || nla_put_be64(skb, NFTA_FLOWTABLE_HANDLE, cpu_to_be64(flowtable->handle), - NFTA_FLOWTABLE_PAD) || + NFTA_FLOWTABLE_PAD)) + goto nla_put_failure; + + if (event == NFT_MSG_DELFLOWTABLE && !hook_list) { + nlmsg_end(skb, nlh); + return 0; + } + + if (nla_put_be32(skb, NFTA_FLOWTABLE_USE, htonl(flowtable->use)) || nla_put_be32(skb, NFTA_FLOWTABLE_FLAGS, htonl(flowtable->data.flags))) goto nla_put_failure; @@ -8106,6 +8137,9 @@ static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net, if (!nest_devs) goto nla_put_failure; + if (!hook_list) + hook_list = &flowtable->hook_list; + list_for_each_entry_rcu(hook, hook_list, list) { if (nla_put_string(skb, NFTA_DEVICE_NAME, hook->ops.dev->name)) goto nla_put_failure; @@ -8162,8 +8196,7 @@ static int nf_tables_dump_flowtable(struct sk_buff *skb, NFT_MSG_NEWFLOWTABLE, NLM_F_MULTI | NLM_F_APPEND, table->family, - flowtable, - &flowtable->hook_list) < 0) + flowtable, NULL) < 0) goto done; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); @@ -8258,7 +8291,7 @@ static int nf_tables_getflowtable(struct sk_buff *skb, err = nf_tables_fill_flowtable_info(skb2, net, NETLINK_CB(skb).portid, info->nlh->nlmsg_seq, NFT_MSG_NEWFLOWTABLE, 0, family, - flowtable, &flowtable->hook_list); + flowtable, NULL); if (err < 0) goto err_fill_flowtable_info; @@ -8271,8 +8304,7 @@ static int nf_tables_getflowtable(struct sk_buff *skb, static void nf_tables_flowtable_notify(struct nft_ctx *ctx, struct nft_flowtable *flowtable, - struct list_head *hook_list, - int event) + struct list_head *hook_list, int event) { struct nftables_pernet *nft_net = nft_pernet(ctx->net); struct sk_buff *skb; @@ -9333,7 +9365,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nft_clear(net, nft_trans_flowtable(trans)); nf_tables_flowtable_notify(&trans->ctx, nft_trans_flowtable(trans), - &nft_trans_flowtable(trans)->hook_list, + NULL, NFT_MSG_NEWFLOWTABLE); } nft_trans_destroy(trans); @@ -9351,7 +9383,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) list_del_rcu(&nft_trans_flowtable(trans)->list); nf_tables_flowtable_notify(&trans->ctx, nft_trans_flowtable(trans), - &nft_trans_flowtable(trans)->hook_list, + NULL, trans->msg_type); nft_unregister_flowtable_net_hooks(net, &nft_trans_flowtable(trans)->hook_list); From patchwork Fri Apr 21 23:02:08 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Pablo Neira Ayuso X-Patchwork-Id: 1772146 X-Patchwork-Delegate: pablo@netfilter.org Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@legolas.ozlabs.org Authentication-Results: legolas.ozlabs.org; spf=pass (sender SPF authorized) smtp.mailfrom=vger.kernel.org (client-ip=2620:137:e000::1:20; helo=out1.vger.email; envelope-from=netfilter-devel-owner@vger.kernel.org; receiver=) Received: from out1.vger.email (out1.vger.email [IPv6:2620:137:e000::1:20]) by legolas.ozlabs.org (Postfix) with ESMTP id 4Q396W2vrpz23s0 for ; Sat, 22 Apr 2023 09:02:59 +1000 (AEST) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S233932AbjDUXC5 (ORCPT ); Fri, 21 Apr 2023 19:02:57 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:53558 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S233842AbjDUXCr (ORCPT ); Fri, 21 Apr 2023 19:02:47 -0400 Received: from mail.netfilter.org (mail.netfilter.org [217.70.188.207]) by lindbergh.monkeyblade.net (Postfix) with ESMTP id D25282728; Fri, 21 Apr 2023 16:02:26 -0700 (PDT) From: Pablo Neira Ayuso To: netfilter-devel@vger.kernel.org Cc: davem@davemloft.net, netdev@vger.kernel.org, kuba@kernel.org, pabeni@redhat.com, edumazet@google.com Subject: [PATCH net-next 17/20] netfilter: nf_tables: rename function to destroy hook list Date: Sat, 22 Apr 2023 01:02:08 +0200 Message-Id: <20230421230211.214635-18-pablo@netfilter.org> X-Mailer: git-send-email 2.30.2 In-Reply-To: <20230421230211.214635-1-pablo@netfilter.org> References: <20230421230211.214635-1-pablo@netfilter.org> MIME-Version: 1.0 X-Spam-Status: No, score=-1.9 required=5.0 tests=BAYES_00,SPF_HELO_NONE, SPF_PASS,T_SCC_BODY_TEXT_LINE autolearn=ham autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on lindbergh.monkeyblade.net Precedence: bulk List-ID: X-Mailing-List: netfilter-devel@vger.kernel.org Rename nft_flowtable_hooks_destroy() by nft_hooks_destroy() to prepare for netdev chain device updates. Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 3f95fb24a0bc..77975b4b0fdc 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -7771,7 +7771,7 @@ static int nft_register_flowtable_net_hooks(struct net *net, return err; } -static void nft_flowtable_hooks_destroy(struct list_head *hook_list) +static void nft_hooks_destroy(struct list_head *hook_list) { struct nft_hook *hook, *next; @@ -7952,7 +7952,7 @@ static int nf_tables_newflowtable(struct sk_buff *skb, &flowtable->hook_list, flowtable); if (err < 0) { - nft_flowtable_hooks_destroy(&flowtable->hook_list); + nft_hooks_destroy(&flowtable->hook_list); goto err4; } @@ -8789,7 +8789,7 @@ static void nft_commit_release(struct nft_trans *trans) case NFT_MSG_DELFLOWTABLE: case NFT_MSG_DESTROYFLOWTABLE: if (nft_trans_flowtable_update(trans)) - nft_flowtable_hooks_destroy(&nft_trans_flowtable_hooks(trans)); + nft_hooks_destroy(&nft_trans_flowtable_hooks(trans)); else nf_tables_flowtable_destroy(nft_trans_flowtable(trans)); break; @@ -9440,7 +9440,7 @@ static void nf_tables_abort_release(struct nft_trans *trans) break; case NFT_MSG_NEWFLOWTABLE: if (nft_trans_flowtable_update(trans)) - nft_flowtable_hooks_destroy(&nft_trans_flowtable_hooks(trans)); + nft_hooks_destroy(&nft_trans_flowtable_hooks(trans)); else nf_tables_flowtable_destroy(nft_trans_flowtable(trans)); break; From patchwork Fri Apr 21 23:02:09 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Pablo Neira Ayuso X-Patchwork-Id: 1772148 X-Patchwork-Delegate: pablo@netfilter.org Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@legolas.ozlabs.org Authentication-Results: legolas.ozlabs.org; spf=pass (sender SPF authorized) smtp.mailfrom=vger.kernel.org (client-ip=2620:137:e000::1:20; helo=out1.vger.email; envelope-from=netfilter-devel-owner@vger.kernel.org; receiver=) Received: from out1.vger.email (out1.vger.email [IPv6:2620:137:e000::1:20]) by legolas.ozlabs.org (Postfix) with ESMTP id 4Q396q0gw2z23s0 for ; Sat, 22 Apr 2023 09:03:15 +1000 (AEST) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S233857AbjDUXDN (ORCPT ); Fri, 21 Apr 2023 19:03:13 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:53564 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S233856AbjDUXCr (ORCPT ); Fri, 21 Apr 2023 19:02:47 -0400 Received: from mail.netfilter.org (mail.netfilter.org [217.70.188.207]) by lindbergh.monkeyblade.net (Postfix) with ESMTP id 4FE5330DA; Fri, 21 Apr 2023 16:02:27 -0700 (PDT) From: Pablo Neira Ayuso To: netfilter-devel@vger.kernel.org Cc: davem@davemloft.net, netdev@vger.kernel.org, kuba@kernel.org, pabeni@redhat.com, edumazet@google.com Subject: [PATCH net-next 18/20] netfilter: nf_tables: support for adding new devices to an existing netdev chain Date: Sat, 22 Apr 2023 01:02:09 +0200 Message-Id: <20230421230211.214635-19-pablo@netfilter.org> X-Mailer: git-send-email 2.30.2 In-Reply-To: <20230421230211.214635-1-pablo@netfilter.org> References: <20230421230211.214635-1-pablo@netfilter.org> MIME-Version: 1.0 X-Spam-Status: No, score=-1.9 required=5.0 tests=BAYES_00,SPF_HELO_NONE, SPF_PASS,T_SCC_BODY_TEXT_LINE,URIBL_BLOCKED autolearn=ham autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on lindbergh.monkeyblade.net Precedence: bulk List-ID: X-Mailing-List: netfilter-devel@vger.kernel.org This patch allows users to add devices to an existing netdev chain. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 6 + net/netfilter/nf_tables_api.c | 217 +++++++++++++++++++----------- 2 files changed, 142 insertions(+), 81 deletions(-) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 58a4d217faaf..3ed21d2d5659 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1609,6 +1609,8 @@ struct nft_trans_chain { struct nft_stats __percpu *stats; u8 policy; u32 chain_id; + struct nft_base_chain *basechain; + struct list_head hook_list; }; #define nft_trans_chain_update(trans) \ @@ -1621,6 +1623,10 @@ struct nft_trans_chain { (((struct nft_trans_chain *)trans->data)->policy) #define nft_trans_chain_id(trans) \ (((struct nft_trans_chain *)trans->data)->chain_id) +#define nft_trans_basechain(trans) \ + (((struct nft_trans_chain *)trans->data)->basechain) +#define nft_trans_chain_hooks(trans) \ + (((struct nft_trans_chain *)trans->data)->hook_list) struct nft_trans_table { bool update; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 77975b4b0fdc..f8d8cace0c7d 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1582,7 +1582,8 @@ static int nft_dump_stats(struct sk_buff *skb, struct nft_stats __percpu *stats) } static int nft_dump_basechain_hook(struct sk_buff *skb, int family, - const struct nft_base_chain *basechain) + const struct nft_base_chain *basechain, + const struct list_head *hook_list) { const struct nf_hook_ops *ops = &basechain->ops; struct nft_hook *hook, *first = NULL; @@ -1599,7 +1600,11 @@ static int nft_dump_basechain_hook(struct sk_buff *skb, int family, if (nft_base_chain_netdev(family, ops->hooknum)) { nest_devs = nla_nest_start_noflag(skb, NFTA_HOOK_DEVS); - list_for_each_entry(hook, &basechain->hook_list, list) { + + if (!hook_list) + hook_list = &basechain->hook_list; + + list_for_each_entry(hook, hook_list, list) { if (!first) first = hook; @@ -1624,7 +1629,8 @@ static int nft_dump_basechain_hook(struct sk_buff *skb, int family, static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net, u32 portid, u32 seq, int event, u32 flags, int family, const struct nft_table *table, - const struct nft_chain *chain) + const struct nft_chain *chain, + const struct list_head *hook_list) { struct nlmsghdr *nlh; @@ -1649,7 +1655,7 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net, const struct nft_base_chain *basechain = nft_base_chain(chain); struct nft_stats __percpu *stats; - if (nft_dump_basechain_hook(skb, family, basechain)) + if (nft_dump_basechain_hook(skb, family, basechain, hook_list)) goto nla_put_failure; if (nla_put_be32(skb, NFTA_CHAIN_POLICY, @@ -1684,7 +1690,8 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net, return -1; } -static void nf_tables_chain_notify(const struct nft_ctx *ctx, int event) +static void nf_tables_chain_notify(const struct nft_ctx *ctx, int event, + const struct list_head *hook_list) { struct nftables_pernet *nft_net; struct sk_buff *skb; @@ -1704,7 +1711,7 @@ static void nf_tables_chain_notify(const struct nft_ctx *ctx, int event) err = nf_tables_fill_chain_info(skb, ctx->net, ctx->portid, ctx->seq, event, flags, ctx->family, ctx->table, - ctx->chain); + ctx->chain, hook_list); if (err < 0) { kfree_skb(skb); goto err; @@ -1750,7 +1757,7 @@ static int nf_tables_dump_chains(struct sk_buff *skb, NFT_MSG_NEWCHAIN, NLM_F_MULTI, table->family, table, - chain) < 0) + chain, NULL) < 0) goto done; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); @@ -1804,7 +1811,7 @@ static int nf_tables_getchain(struct sk_buff *skb, const struct nfnl_info *info, err = nf_tables_fill_chain_info(skb2, net, NETLINK_CB(skb).portid, info->nlh->nlmsg_seq, NFT_MSG_NEWCHAIN, - 0, family, table, chain); + 0, family, table, chain, NULL); if (err < 0) goto err_fill_chain_info; @@ -2048,9 +2055,10 @@ static int nft_chain_parse_netdev(struct net *net, } static int nft_chain_parse_hook(struct net *net, + struct nft_base_chain *basechain, const struct nlattr * const nla[], struct nft_chain_hook *hook, u8 family, - struct netlink_ext_ack *extack, bool autoload) + struct netlink_ext_ack *extack) { struct nftables_pernet *nft_net = nft_pernet(net); struct nlattr *ha[NFTA_HOOK_MAX + 1]; @@ -2066,31 +2074,46 @@ static int nft_chain_parse_hook(struct net *net, if (err < 0) return err; - if (ha[NFTA_HOOK_HOOKNUM] == NULL || - ha[NFTA_HOOK_PRIORITY] == NULL) - return -EINVAL; + if (!basechain) { + if (!ha[NFTA_HOOK_HOOKNUM] || + !ha[NFTA_HOOK_PRIORITY]) + return -EINVAL; - hook->num = ntohl(nla_get_be32(ha[NFTA_HOOK_HOOKNUM])); - hook->priority = ntohl(nla_get_be32(ha[NFTA_HOOK_PRIORITY])); + hook->num = ntohl(nla_get_be32(ha[NFTA_HOOK_HOOKNUM])); + hook->priority = ntohl(nla_get_be32(ha[NFTA_HOOK_PRIORITY])); - type = __nft_chain_type_get(family, NFT_CHAIN_T_DEFAULT); - if (!type) - return -EOPNOTSUPP; + type = __nft_chain_type_get(family, NFT_CHAIN_T_DEFAULT); + if (!type) + return -EOPNOTSUPP; - if (nla[NFTA_CHAIN_TYPE]) { - type = nf_tables_chain_type_lookup(net, nla[NFTA_CHAIN_TYPE], - family, autoload); - if (IS_ERR(type)) { - NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TYPE]); - return PTR_ERR(type); + if (nla[NFTA_CHAIN_TYPE]) { + type = nf_tables_chain_type_lookup(net, nla[NFTA_CHAIN_TYPE], + family, true); + if (IS_ERR(type)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TYPE]); + return PTR_ERR(type); + } } - } - if (hook->num >= NFT_MAX_HOOKS || !(type->hook_mask & (1 << hook->num))) - return -EOPNOTSUPP; + if (hook->num >= NFT_MAX_HOOKS || !(type->hook_mask & (1 << hook->num))) + return -EOPNOTSUPP; - if (type->type == NFT_CHAIN_T_NAT && - hook->priority <= NF_IP_PRI_CONNTRACK) - return -EOPNOTSUPP; + if (type->type == NFT_CHAIN_T_NAT && + hook->priority <= NF_IP_PRI_CONNTRACK) + return -EOPNOTSUPP; + } else { + if (ha[NFTA_HOOK_HOOKNUM]) { + hook->num = ntohl(nla_get_be32(ha[NFTA_HOOK_HOOKNUM])); + if (hook->num != basechain->ops.hooknum) + return -EOPNOTSUPP; + } + if (ha[NFTA_HOOK_PRIORITY]) { + hook->priority = ntohl(nla_get_be32(ha[NFTA_HOOK_PRIORITY])); + if (hook->priority != basechain->ops.priority) + return -EOPNOTSUPP; + } + + type = basechain->type; + } if (!try_module_get(type->owner)) { if (nla[NFTA_CHAIN_TYPE]) @@ -2184,12 +2207,8 @@ static int nft_basechain_init(struct nft_base_chain *basechain, u8 family, list_splice_init(&hook->list, &basechain->hook_list); list_for_each_entry(h, &basechain->hook_list, list) nft_basechain_hook_init(&h->ops, family, hook, chain); - - basechain->ops.hooknum = hook->num; - basechain->ops.priority = hook->priority; - } else { - nft_basechain_hook_init(&basechain->ops, family, hook, chain); } + nft_basechain_hook_init(&basechain->ops, family, hook, chain); chain->flags |= NFT_CHAIN_BASE | flags; basechain->policy = NF_ACCEPT; @@ -2239,13 +2258,13 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, if (nla[NFTA_CHAIN_HOOK]) { struct nft_stats __percpu *stats = NULL; - struct nft_chain_hook hook; + struct nft_chain_hook hook = {}; if (flags & NFT_CHAIN_BINDING) return -EOPNOTSUPP; - err = nft_chain_parse_hook(net, nla, &hook, family, extack, - true); + err = nft_chain_parse_hook(net, NULL, nla, &hook, family, + extack); if (err < 0) return err; @@ -2359,65 +2378,57 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, return err; } -static bool nft_hook_list_equal(struct list_head *hook_list1, - struct list_head *hook_list2) -{ - struct nft_hook *hook; - int n = 0, m = 0; - - n = 0; - list_for_each_entry(hook, hook_list2, list) { - if (!nft_hook_list_find(hook_list1, hook)) - return false; - - n++; - } - list_for_each_entry(hook, hook_list1, list) - m++; - - return n == m; -} - static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, u32 flags, const struct nlattr *attr, struct netlink_ext_ack *extack) { const struct nlattr * const *nla = ctx->nla; + struct nft_base_chain *basechain = NULL; struct nft_table *table = ctx->table; struct nft_chain *chain = ctx->chain; - struct nft_base_chain *basechain; + struct nft_chain_hook hook = {}; struct nft_stats *stats = NULL; - struct nft_chain_hook hook; + struct nft_hook *h, *next; struct nf_hook_ops *ops; struct nft_trans *trans; + bool unregister = false; int err; if (chain->flags ^ flags) return -EOPNOTSUPP; + INIT_LIST_HEAD(&hook.list); + if (nla[NFTA_CHAIN_HOOK]) { if (!nft_is_base_chain(chain)) { NL_SET_BAD_ATTR(extack, attr); return -EEXIST; } - err = nft_chain_parse_hook(ctx->net, nla, &hook, ctx->family, - extack, false); + + basechain = nft_base_chain(chain); + err = nft_chain_parse_hook(ctx->net, basechain, nla, &hook, + ctx->family, extack); if (err < 0) return err; - basechain = nft_base_chain(chain); if (basechain->type != hook.type) { nft_chain_release_hook(&hook); NL_SET_BAD_ATTR(extack, attr); return -EEXIST; } - if (nft_base_chain_netdev(ctx->family, hook.num)) { - if (!nft_hook_list_equal(&basechain->hook_list, - &hook.list)) { - nft_chain_release_hook(&hook); - NL_SET_BAD_ATTR(extack, attr); - return -EEXIST; + if (nft_base_chain_netdev(ctx->family, basechain->ops.hooknum)) { + list_for_each_entry_safe(h, next, &hook.list, list) { + h->ops.pf = basechain->ops.pf; + h->ops.hooknum = basechain->ops.hooknum; + h->ops.priority = basechain->ops.priority; + h->ops.priv = basechain->ops.priv; + h->ops.hook = basechain->ops.hook; + + if (nft_hook_list_find(&basechain->hook_list, h)) { + list_del(&h->list); + kfree(h); + } } } else { ops = &basechain->ops; @@ -2428,7 +2439,6 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, return -EEXIST; } } - nft_chain_release_hook(&hook); } if (nla[NFTA_CHAIN_HANDLE] && @@ -2439,24 +2449,43 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, nla[NFTA_CHAIN_NAME], genmask); if (!IS_ERR(chain2)) { NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_NAME]); - return -EEXIST; + err = -EEXIST; + goto err_hooks; } } if (nla[NFTA_CHAIN_COUNTERS]) { - if (!nft_is_base_chain(chain)) - return -EOPNOTSUPP; + if (!nft_is_base_chain(chain)) { + err = -EOPNOTSUPP; + goto err_hooks; + } stats = nft_stats_alloc(nla[NFTA_CHAIN_COUNTERS]); - if (IS_ERR(stats)) - return PTR_ERR(stats); + if (IS_ERR(stats)) { + err = PTR_ERR(stats); + goto err_hooks; + } } + if (!(table->flags & NFT_TABLE_F_DORMANT) && + nft_is_base_chain(chain) && + !list_empty(&hook.list)) { + basechain = nft_base_chain(chain); + ops = &basechain->ops; + + if (nft_base_chain_netdev(table->family, basechain->ops.hooknum)) { + err = nft_netdev_register_hooks(ctx->net, &hook.list); + if (err < 0) + goto err_hooks; + } + } + + unregister = true; err = -ENOMEM; trans = nft_trans_alloc(ctx, NFT_MSG_NEWCHAIN, sizeof(struct nft_trans_chain)); if (trans == NULL) - goto err; + goto err_trans; nft_trans_chain_stats(trans) = stats; nft_trans_chain_update(trans) = true; @@ -2475,7 +2504,7 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, err = -ENOMEM; name = nla_strdup(nla[NFTA_CHAIN_NAME], GFP_KERNEL_ACCOUNT); if (!name) - goto err; + goto err_trans; err = -EEXIST; list_for_each_entry(tmp, &nft_net->commit_list, list) { @@ -2486,18 +2515,35 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, strcmp(name, nft_trans_chain_name(tmp)) == 0) { NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_NAME]); kfree(name); - goto err; + goto err_trans; } } nft_trans_chain_name(trans) = name; } + + nft_trans_basechain(trans) = basechain; + INIT_LIST_HEAD(&nft_trans_chain_hooks(trans)); + list_splice(&hook.list, &nft_trans_chain_hooks(trans)); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; -err: + +err_trans: free_percpu(stats); kfree(trans); +err_hooks: + if (nla[NFTA_CHAIN_HOOK]) { + list_for_each_entry_safe(h, next, &hook.list, list) { + if (unregister) + nf_unregister_net_hook(ctx->net, &h->ops); + list_del(&h->list); + kfree_rcu(h, rcu); + } + module_put(hook.type->owner); + } + return err; } @@ -9244,19 +9290,22 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) case NFT_MSG_NEWCHAIN: if (nft_trans_chain_update(trans)) { nft_chain_commit_update(trans); - nf_tables_chain_notify(&trans->ctx, NFT_MSG_NEWCHAIN); + nf_tables_chain_notify(&trans->ctx, NFT_MSG_NEWCHAIN, + &nft_trans_chain_hooks(trans)); + list_splice(&nft_trans_chain_hooks(trans), + &nft_trans_basechain(trans)->hook_list); /* trans destroyed after rcu grace period */ } else { nft_chain_commit_drop_policy(trans); nft_clear(net, trans->ctx.chain); - nf_tables_chain_notify(&trans->ctx, NFT_MSG_NEWCHAIN); + nf_tables_chain_notify(&trans->ctx, NFT_MSG_NEWCHAIN, NULL); nft_trans_destroy(trans); } break; case NFT_MSG_DELCHAIN: case NFT_MSG_DESTROYCHAIN: nft_chain_del(trans->ctx.chain); - nf_tables_chain_notify(&trans->ctx, trans->msg_type); + nf_tables_chain_notify(&trans->ctx, trans->msg_type, NULL); nf_tables_unregister_hook(trans->ctx.net, trans->ctx.table, trans->ctx.chain); @@ -9423,7 +9472,10 @@ static void nf_tables_abort_release(struct nft_trans *trans) nf_tables_table_destroy(&trans->ctx); break; case NFT_MSG_NEWCHAIN: - nf_tables_chain_destroy(&trans->ctx); + if (nft_trans_chain_update(trans)) + nft_hooks_destroy(&nft_trans_chain_hooks(trans)); + else + nf_tables_chain_destroy(&trans->ctx); break; case NFT_MSG_NEWRULE: nf_tables_rule_destroy(&trans->ctx, nft_trans_rule(trans)); @@ -9486,6 +9538,9 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) break; case NFT_MSG_NEWCHAIN: if (nft_trans_chain_update(trans)) { + nft_netdev_unregister_hooks(net, + &nft_trans_chain_hooks(trans), + true); free_percpu(nft_trans_chain_stats(trans)); kfree(nft_trans_chain_name(trans)); nft_trans_destroy(trans); From patchwork Fri Apr 21 23:02:10 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Pablo Neira Ayuso X-Patchwork-Id: 1772149 X-Patchwork-Delegate: pablo@netfilter.org Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@legolas.ozlabs.org Authentication-Results: legolas.ozlabs.org; spf=pass (sender SPF authorized) smtp.mailfrom=vger.kernel.org (client-ip=2620:137:e000::1:20; helo=out1.vger.email; envelope-from=netfilter-devel-owner@vger.kernel.org; receiver=) Received: from out1.vger.email (out1.vger.email [IPv6:2620:137:e000::1:20]) by legolas.ozlabs.org (Postfix) with ESMTP id 4Q396s511fz23s0 for ; Sat, 22 Apr 2023 09:03:17 +1000 (AEST) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S233971AbjDUXDQ (ORCPT ); Fri, 21 Apr 2023 19:03:16 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:53034 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S233782AbjDUXCs (ORCPT ); Fri, 21 Apr 2023 19:02:48 -0400 Received: from mail.netfilter.org (mail.netfilter.org [217.70.188.207]) by lindbergh.monkeyblade.net (Postfix) with ESMTP id 2AE7930EB; Fri, 21 Apr 2023 16:02:27 -0700 (PDT) From: Pablo Neira Ayuso To: netfilter-devel@vger.kernel.org Cc: davem@davemloft.net, netdev@vger.kernel.org, kuba@kernel.org, pabeni@redhat.com, edumazet@google.com Subject: [PATCH net-next 19/20] netfilter: nf_tables: support for deleting devices in an existing netdev chain Date: Sat, 22 Apr 2023 01:02:10 +0200 Message-Id: <20230421230211.214635-20-pablo@netfilter.org> X-Mailer: git-send-email 2.30.2 In-Reply-To: <20230421230211.214635-1-pablo@netfilter.org> References: <20230421230211.214635-1-pablo@netfilter.org> MIME-Version: 1.0 X-Spam-Status: No, score=-1.9 required=5.0 tests=BAYES_00,SPF_HELO_NONE, SPF_PASS,T_SCC_BODY_TEXT_LINE autolearn=ham autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on lindbergh.monkeyblade.net Precedence: bulk List-ID: X-Mailing-List: netfilter-devel@vger.kernel.org This patch allows for deleting devices in an existing netdev chain. Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 99 +++++++++++++++++++++++++++++++---- 1 file changed, 88 insertions(+), 11 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index f8d8cace0c7d..c55ac3d57c51 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1646,7 +1646,7 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net, NFTA_CHAIN_PAD)) goto nla_put_failure; - if (event == NFT_MSG_DELCHAIN) { + if (event == NFT_MSG_DELCHAIN && !hook_list) { nlmsg_end(skb, nlh); return 0; } @@ -2667,6 +2667,59 @@ static int nf_tables_newchain(struct sk_buff *skb, const struct nfnl_info *info, return nf_tables_addchain(&ctx, family, genmask, policy, flags, extack); } +static int nft_delchain_hook(struct nft_ctx *ctx, struct nft_chain *chain, + struct netlink_ext_ack *extack) +{ + const struct nlattr * const *nla = ctx->nla; + struct nft_chain_hook chain_hook = {}; + struct nft_base_chain *basechain; + struct nft_hook *this, *hook; + LIST_HEAD(chain_del_list); + struct nft_trans *trans; + int err; + + if (!nft_is_base_chain(chain)) + return -EOPNOTSUPP; + + basechain = nft_base_chain(chain); + err = nft_chain_parse_hook(ctx->net, basechain, nla, &chain_hook, + ctx->family, extack); + if (err < 0) + return err; + + list_for_each_entry(this, &chain_hook.list, list) { + hook = nft_hook_list_find(&basechain->hook_list, this); + if (!hook) { + err = -ENOENT; + goto err_chain_del_hook; + } + list_move(&hook->list, &chain_del_list); + } + + trans = nft_trans_alloc(ctx, NFT_MSG_DELCHAIN, + sizeof(struct nft_trans_chain)); + if (!trans) { + err = -ENOMEM; + goto err_chain_del_hook; + } + + nft_trans_basechain(trans) = basechain; + nft_trans_chain_update(trans) = true; + INIT_LIST_HEAD(&nft_trans_chain_hooks(trans)); + list_splice(&chain_del_list, &nft_trans_chain_hooks(trans)); + nft_chain_release_hook(&chain_hook); + + nft_trans_commit_list_add_tail(ctx->net, trans); + + return 0; + +err_chain_del_hook: + list_splice(&chain_del_list, &basechain->hook_list); + nft_chain_release_hook(&chain_hook); + + return err; +} + static int nf_tables_delchain(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { @@ -2707,12 +2760,19 @@ static int nf_tables_delchain(struct sk_buff *skb, const struct nfnl_info *info, return PTR_ERR(chain); } + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, chain, nla); + + if (nla[NFTA_CHAIN_HOOK]) { + if (chain->flags & NFT_CHAIN_HW_OFFLOAD) + return -EOPNOTSUPP; + + return nft_delchain_hook(&ctx, chain, extack); + } + if (info->nlh->nlmsg_flags & NLM_F_NONREC && chain->use > 0) return -EBUSY; - nft_ctx_init(&ctx, net, skb, info->nlh, family, table, chain, nla); - use = chain->use; list_for_each_entry(rule, &chain->rules, list) { if (!nft_is_active_next(net, rule)) @@ -8812,7 +8872,10 @@ static void nft_commit_release(struct nft_trans *trans) break; case NFT_MSG_DELCHAIN: case NFT_MSG_DESTROYCHAIN: - nf_tables_chain_destroy(&trans->ctx); + if (nft_trans_chain_update(trans)) + nft_hooks_destroy(&nft_trans_chain_hooks(trans)); + else + nf_tables_chain_destroy(&trans->ctx); break; case NFT_MSG_DELRULE: case NFT_MSG_DESTROYRULE: @@ -9304,11 +9367,20 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) break; case NFT_MSG_DELCHAIN: case NFT_MSG_DESTROYCHAIN: - nft_chain_del(trans->ctx.chain); - nf_tables_chain_notify(&trans->ctx, trans->msg_type, NULL); - nf_tables_unregister_hook(trans->ctx.net, - trans->ctx.table, - trans->ctx.chain); + if (nft_trans_chain_update(trans)) { + nf_tables_chain_notify(&trans->ctx, NFT_MSG_DELCHAIN, + &nft_trans_chain_hooks(trans)); + nft_netdev_unregister_hooks(net, + &nft_trans_chain_hooks(trans), + true); + } else { + nft_chain_del(trans->ctx.chain); + nf_tables_chain_notify(&trans->ctx, NFT_MSG_DELCHAIN, + NULL); + nf_tables_unregister_hook(trans->ctx.net, + trans->ctx.table, + trans->ctx.chain); + } break; case NFT_MSG_NEWRULE: nft_clear(trans->ctx.net, nft_trans_rule(trans)); @@ -9558,8 +9630,13 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) break; case NFT_MSG_DELCHAIN: case NFT_MSG_DESTROYCHAIN: - trans->ctx.table->use++; - nft_clear(trans->ctx.net, trans->ctx.chain); + if (nft_trans_chain_update(trans)) { + list_splice(&nft_trans_chain_hooks(trans), + &nft_trans_basechain(trans)->hook_list); + } else { + trans->ctx.table->use++; + nft_clear(trans->ctx.net, trans->ctx.chain); + } nft_trans_destroy(trans); break; case NFT_MSG_NEWRULE: From patchwork Fri Apr 21 23:02:11 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Pablo Neira Ayuso X-Patchwork-Id: 1772150 X-Patchwork-Delegate: pablo@netfilter.org Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@legolas.ozlabs.org Authentication-Results: legolas.ozlabs.org; spf=pass (sender SPF authorized) smtp.mailfrom=vger.kernel.org (client-ip=2620:137:e000::1:20; helo=out1.vger.email; envelope-from=netfilter-devel-owner@vger.kernel.org; receiver=) Received: from out1.vger.email (out1.vger.email [IPv6:2620:137:e000::1:20]) by legolas.ozlabs.org (Postfix) with ESMTP id 4Q396v1Bm7z23s0 for ; Sat, 22 Apr 2023 09:03:19 +1000 (AEST) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S233722AbjDUXDR (ORCPT ); Fri, 21 Apr 2023 19:03:17 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:52780 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S233880AbjDUXCs (ORCPT ); Fri, 21 Apr 2023 19:02:48 -0400 Received: from mail.netfilter.org (mail.netfilter.org [217.70.188.207]) by lindbergh.monkeyblade.net (Postfix) with ESMTP id DCE7530FF; Fri, 21 Apr 2023 16:02:28 -0700 (PDT) From: Pablo Neira Ayuso To: netfilter-devel@vger.kernel.org Cc: davem@davemloft.net, netdev@vger.kernel.org, kuba@kernel.org, pabeni@redhat.com, edumazet@google.com Subject: [PATCH net-next 20/20] netfilter: nf_tables: allow to create netdev chain without device Date: Sat, 22 Apr 2023 01:02:11 +0200 Message-Id: <20230421230211.214635-21-pablo@netfilter.org> X-Mailer: git-send-email 2.30.2 In-Reply-To: <20230421230211.214635-1-pablo@netfilter.org> References: <20230421230211.214635-1-pablo@netfilter.org> MIME-Version: 1.0 X-Spam-Status: No, score=-1.9 required=5.0 tests=BAYES_00,SPF_HELO_NONE, SPF_PASS,T_SCC_BODY_TEXT_LINE autolearn=ham autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on lindbergh.monkeyblade.net Precedence: bulk List-ID: X-Mailing-List: netfilter-devel@vger.kernel.org Relax netdev chain creation to allow for loading the ruleset, then adding/deleting devices at a later stage. Hardware offload does not support for this feature yet. Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 23 +++++++++++------------ 1 file changed, 11 insertions(+), 12 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index c55ac3d57c51..09542951656c 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2023,10 +2023,9 @@ struct nft_chain_hook { struct list_head list; }; -static int nft_chain_parse_netdev(struct net *net, - struct nlattr *tb[], +static int nft_chain_parse_netdev(struct net *net, struct nlattr *tb[], struct list_head *hook_list, - struct netlink_ext_ack *extack) + struct netlink_ext_ack *extack, u32 flags) { struct nft_hook *hook; int err; @@ -2045,12 +2044,12 @@ static int nft_chain_parse_netdev(struct net *net, if (err < 0) return err; - if (list_empty(hook_list)) - return -EINVAL; - } else { - return -EINVAL; } + if (flags & NFT_CHAIN_HW_OFFLOAD && + list_empty(hook_list)) + return -EINVAL; + return 0; } @@ -2058,7 +2057,7 @@ static int nft_chain_parse_hook(struct net *net, struct nft_base_chain *basechain, const struct nlattr * const nla[], struct nft_chain_hook *hook, u8 family, - struct netlink_ext_ack *extack) + u32 flags, struct netlink_ext_ack *extack) { struct nftables_pernet *nft_net = nft_pernet(net); struct nlattr *ha[NFTA_HOOK_MAX + 1]; @@ -2125,7 +2124,7 @@ static int nft_chain_parse_hook(struct net *net, INIT_LIST_HEAD(&hook->list); if (nft_base_chain_netdev(family, hook->num)) { - err = nft_chain_parse_netdev(net, ha, &hook->list, extack); + err = nft_chain_parse_netdev(net, ha, &hook->list, extack, flags); if (err < 0) { module_put(type->owner); return err; @@ -2263,7 +2262,7 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, if (flags & NFT_CHAIN_BINDING) return -EOPNOTSUPP; - err = nft_chain_parse_hook(net, NULL, nla, &hook, family, + err = nft_chain_parse_hook(net, NULL, nla, &hook, family, flags, extack); if (err < 0) return err; @@ -2407,7 +2406,7 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, basechain = nft_base_chain(chain); err = nft_chain_parse_hook(ctx->net, basechain, nla, &hook, - ctx->family, extack); + ctx->family, flags, extack); if (err < 0) return err; @@ -2683,7 +2682,7 @@ static int nft_delchain_hook(struct nft_ctx *ctx, struct nft_chain *chain, basechain = nft_base_chain(chain); err = nft_chain_parse_hook(ctx->net, basechain, nla, &chain_hook, - ctx->family, extack); + ctx->family, chain->flags, extack); if (err < 0) return err;