linux-kernel - [PATCH v6] ipvs: inspect reply packets from DR/TUN real servers

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [day] [month] [year] [list]

Message-Id: <20201004150716.83274-1-bigclouds@163.com>
Date:   Sun,  4 Oct 2020 23:07:16 +0800
From:   "longguang.yue" <bigclouds@....com>
To:     unlisted-recipients:; (no To-header on input)
Cc:     ja@....bg, kuba@...nel.org, wensong@...ux-vs.org,
        horms@...ge.net.au, pablo@...filter.org, kadlec@...filter.org,
        fw@...len.de, davem@...emloft.net, lvs-devel@...r.kernel.org,
        netfilter-devel@...r.kernel.org, coreteam@...filter.org,
        linux-kernel@...r.kernel.org, yuelongguang@...il.com,
        "longguang.yue" <bigclouds@....com>
Subject: [PATCH v6] ipvs: inspect reply packets from DR/TUN real servers

Just like for MASQ, inspect the reply packets coming from DR/TUN
real servers and alter the connection's state and timeout
according to the protocol.

It's ipvs's duty to do traffic statistic if packets get hit,
no matter what mode it is.

---
Changes in v1: support DR/TUN mode statistic
Changes in v2: ip_vs_conn_out_get handles DR/TUN mode's conn
Changes in v3: fix checkpatch
Changes in v4, v5: restructure and optimise this feature
Changes in v6: rewrite subject and patch description

Signed-off-by: longguang.yue <bigclouds@....com>
---
 net/netfilter/ipvs/ip_vs_conn.c | 18 +++++++++++++++---
 net/netfilter/ipvs/ip_vs_core.c | 17 ++++++-----------
 2 files changed, 21 insertions(+), 14 deletions(-)

diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index a90b8eac16ac..af08ca2d9174 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -401,6 +401,8 @@ struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p)
 struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p)
 {
 	unsigned int hash;
+	__be16 sport;
+	const union nf_inet_addr *saddr;
 	struct ip_vs_conn *cp, *ret=NULL;
 
 	/*
@@ -411,10 +413,20 @@ struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p)
 	rcu_read_lock();
 
 	hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[hash], c_list) {
-		if (p->vport == cp->cport && p->cport == cp->dport &&
-		    cp->af == p->af &&
+		if (p->vport != cp->cport)
+			continue;
+
+		if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) {
+			sport = cp->vport;
+			saddr = &cp->vaddr;
+		} else {
+			sport = cp->dport;
+			saddr = &cp->daddr;
+		}
+
+		if (p->cport == sport && cp->af == p->af &&
 		    ip_vs_addr_equal(p->af, p->vaddr, &cp->caddr) &&
-		    ip_vs_addr_equal(p->af, p->caddr, &cp->daddr) &&
+		    ip_vs_addr_equal(p->af, p->caddr, saddr) &&
 		    p->protocol == cp->protocol &&
 		    cp->ipvs == p->ipvs) {
 			if (!__ip_vs_conn_get(cp))
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index e3668a6e54e4..494ea1fcf4d8 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -875,7 +875,7 @@ static int handle_response_icmp(int af, struct sk_buff *skb,
 	unsigned int verdict = NF_DROP;
 
 	if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ)
-		goto ignore_cp;
+		goto after_nat;
 
 	/* Ensure the checksum is correct */
 	if (!skb_csum_unnecessary(skb) && ip_vs_checksum_complete(skb, ihl)) {
@@ -900,7 +900,7 @@ static int handle_response_icmp(int af, struct sk_buff *skb,
 
 	if (ip_vs_route_me_harder(cp->ipvs, af, skb, hooknum))
 		goto out;
-
+after_nat:
 	/* do the statistics and put it back */
 	ip_vs_out_stats(cp, skb);
 
@@ -909,8 +909,6 @@ static int handle_response_icmp(int af, struct sk_buff *skb,
 		ip_vs_notrack(skb);
 	else
 		ip_vs_update_conntrack(skb, cp, 0);
-
-ignore_cp:
 	verdict = NF_ACCEPT;
 
 out:
@@ -1276,6 +1274,9 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 {
 	struct ip_vs_protocol *pp = pd->pp;
 
+	if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ)
+		goto after_nat;
+
 	IP_VS_DBG_PKT(11, af, pp, skb, iph->off, "Outgoing packet");
 
 	if (skb_ensure_writable(skb, iph->len))
@@ -1316,6 +1317,7 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 
 	IP_VS_DBG_PKT(10, af, pp, skb, iph->off, "After SNAT");
 
+after_nat:
 	ip_vs_out_stats(cp, skb);
 	ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pd);
 	skb->ipvs_property = 1;
@@ -1413,8 +1415,6 @@ ip_vs_out(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, in
 			     ipvs, af, skb, &iph);
 
 	if (likely(cp)) {
-		if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ)
-			goto ignore_cp;
 		return handle_response(af, skb, pd, cp, &iph, hooknum);
 	}
 
@@ -1475,14 +1475,9 @@ ip_vs_out(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, in
 		}
 	}
 
-out:
 	IP_VS_DBG_PKT(12, af, pp, skb, iph.off,
 		      "ip_vs_out: packet continues traversal as normal");
 	return NF_ACCEPT;
-
-ignore_cp:
-	__ip_vs_conn_put(cp);
-	goto out;
 }
 
 /*
-- 
2.20.1 (Apple Git-117)