netfilter: nf_tables: extend tracing infrastructure

nft monitor mode can then decode and display this trace data.

Parts of LL/Network/Transport headers are provided as separate
attributes.

Otherwise, printing IP address data becomes virtually impossible
for userspace since in the case of the netdev family we really don't
want userspace to have to know all the possible link layer types
and/or sizes just to display/print an ip address.

We also don't want userspace to have to follow ipv6 header chains
to get the s/dport info, the kernel already did this work for us.

To avoid bloating nft_do_chain all data required for tracing is
encapsulated in nft_traceinfo.

The structure is initialized unconditionally(!) for each nft_do_chain
invocation.

This unconditionall call will be moved under a static key in a
followup patch.

With lots of help from Patrick McHardy and Pablo Neira.

Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

1 files changed, 33 insertions, 12 deletions

diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
index f3695a497408..2395de7c8ab2 100644
--- a/net/netfilter/nf_tables_core.c
+++ b/net/netfilter/nf_tables_core.c
@@ -44,22 +44,36 @@ static struct nf_loginfo trace_loginfo = {
 	},
 };
 
-static void __nft_trace_packet(const struct nft_pktinfo *pkt,
-			       const struct nft_chain *chain,
-			       int rulenum, enum nft_trace type)
+static noinline void __nft_trace_packet(struct nft_traceinfo *info,
+					const struct nft_chain *chain,
+					int rulenum, enum nft_trace type)
 {
+	const struct nft_pktinfo *pkt = info->pkt;
+
+	if (!pkt->skb->nf_trace)
+		return;
+
+	info->chain = chain;
+	info->type = type;
+
+	nft_trace_notify(info);
+
 	nf_log_trace(pkt->net, pkt->pf, pkt->hook, pkt->skb, pkt->in,
 		     pkt->out, &trace_loginfo, "TRACE: %s:%s:%s:%u ",
 		     chain->table->name, chain->name, comments[type],
 		     rulenum);
 }
 
-static inline void nft_trace_packet(const struct nft_pktinfo *pkt,
+static inline void nft_trace_packet(struct nft_traceinfo *info,
 				    const struct nft_chain *chain,
-				    int rulenum, enum nft_trace type)
+				    const struct nft_rule *rule,
+				    int rulenum,
+				    enum nft_trace_types type)
 {
-	if (unlikely(pkt->skb->nf_trace))
-		__nft_trace_packet(pkt, chain, rulenum, type);
+	if (unlikely(info->trace)) {
+		info->rule = rule;
+		__nft_trace_packet(info, chain, rulenum, type);
+	}
 }
 
 static void nft_cmp_fast_eval(const struct nft_expr *expr,
@@ -121,7 +135,9 @@ nft_do_chain(struct nft_pktinfo *pkt, void *priv)
 	struct nft_stats *stats;
 	int rulenum;
 	unsigned int gencursor = nft_genmask_cur(net);
+	struct nft_traceinfo info;
 
+	nft_trace_init(&info, pkt, &regs.verdict, basechain);
 do_chain:
 	rulenum = 0;
 	rule = list_entry(&chain->rules, struct nft_rule, list);
@@ -151,7 +167,8 @@ next_rule:
 			regs.verdict.code = NFT_CONTINUE;
 			continue;
 		case NFT_CONTINUE:
-			nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RULE);
+			nft_trace_packet(&info, chain, rule,
+					 rulenum, NFT_TRACETYPE_RULE);
 			continue;
 		}
 		break;
@@ -161,7 +178,8 @@ next_rule:
 	case NF_ACCEPT:
 	case NF_DROP:
 	case NF_QUEUE:
-		nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RULE);
+		nft_trace_packet(&info, chain, rule,
+				 rulenum, NFT_TRACETYPE_RULE);
 		return regs.verdict.code;
 	}
 
@@ -174,7 +192,8 @@ next_rule:
 		stackptr++;
 		/* fall through */
 	case NFT_GOTO:
-		nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RULE);
+		nft_trace_packet(&info, chain, rule,
+				 rulenum, NFT_TRACETYPE_RULE);
 
 		chain = regs.verdict.chain;
 		goto do_chain;
@@ -182,7 +201,8 @@ next_rule:
 		rulenum++;
 		/* fall through */
 	case NFT_RETURN:
-		nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RETURN);
+		nft_trace_packet(&info, chain, rule,
+				 rulenum, NFT_TRACETYPE_RETURN);
 		break;
 	default:
 		WARN_ON(1);
@@ -196,7 +216,8 @@ next_rule:
 		goto next_rule;
 	}
 
-	nft_trace_packet(pkt, basechain, -1, NFT_TRACE_POLICY);
+	nft_trace_packet(&info, basechain, NULL, -1,
+			 NFT_TRACETYPE_POLICY);
 
 	rcu_read_lock_bh();
 	stats = this_cpu_ptr(rcu_dereference(nft_base_chain(basechain)->stats));