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>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <7430f57f0949081f54e633c69f2800ae577e8605.1638814614.git.gnault@redhat.com>
Date:   Mon, 6 Dec 2021 19:22:06 +0100
From:   Guillaume Nault <gnault@...hat.com>
To:     David Miller <davem@...emloft.net>,
        Jakub Kicinski <kuba@...nel.org>
Cc:     netdev@...r.kernel.org,
        Hideaki YOSHIFUJI <yoshfuji@...ux-ipv6.org>,
        David Ahern <dsahern@...nel.org>,
        Toke Høiland-Jørgensen <toke@...hat.com>,
        Russell Strong <russell@...ong.id.au>
Subject: [PATCH net-next 1/4] ipv6: Define dscp_t and stop taking ECN bits
 into account in ip6-rules

Define a dscp_t type and its appropriate helpers that ensure ECN bits
are not taken into account when handling DSCP.

Use this new type to replace the tclass field of fib6_rule, so that
ip6-rules don't get influenced by ECN bits anymore.

Before this patch, ip6-rules didn't make any distinction between the
DSCP and ECN bits. Therefore, rules specifying a DSCP (tos or dsfield
options in iproute2) stopped working as soon a packets had at least one
of its ECN bits set (as a work around one could create four rules for
each DSCP value to match, one for each possible ECN value).

After this patch ip6-rules only compare the DSCP bits. ECN doesn't
influence the result anymore. Also, ip6-rules now must have the ECN
bits cleared or they will be rejected.

Signed-off-by: Guillaume Nault <gnault@...hat.com>
---
 include/net/inet_dscp.h | 54 +++++++++++++++++++++++++++++++++++++++++
 include/net/ipv6.h      |  6 +++++
 net/ipv6/fib6_rules.c   | 18 +++++++++-----
 3 files changed, 72 insertions(+), 6 deletions(-)
 create mode 100644 include/net/inet_dscp.h

diff --git a/include/net/inet_dscp.h b/include/net/inet_dscp.h
new file mode 100644
index 000000000000..e7f7e182529c
--- /dev/null
+++ b/include/net/inet_dscp.h
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * inet_dscp.h: helpers for handling differentiated services codepoints (DSCP)
+ *
+ * DSCP is defined in RFC 2474:
+ *
+ *        0   1   2   3   4   5   6   7
+ *      +---+---+---+---+---+---+---+---+
+ *      |         DSCP          |  CU   |
+ *      +---+---+---+---+---+---+---+---+
+ *
+ *        DSCP: differentiated services codepoint
+ *        CU:   currently unused
+ *
+ * The whole DSCP + CU bits form the DS field.
+ * The DS field is also commonly called TOS or Traffic Class (for IPv6).
+ *
+ * Note: the CU bits are now used for Explicit Congestion Notification
+ *       (RFC 3168).
+ */
+
+#ifndef _INET_DSCP_H
+#define _INET_DSCP_H
+
+#include <linux/types.h>
+
+/* Special type for storing DSCP values.
+ *
+ * A dscp_t variable stores a DSCP value, without the CU (or ECN) bits.
+ * Using dscp_t allows to strictly separate DSCP and ECN bits, thus avoid bugs
+ * where ECN bits are erroneously taken into account during FIB lookups or
+ * policy routing.
+ */
+typedef u8 __bitwise dscp_t;
+
+#define INET_DSCP_MASK 0xfc
+#define INET_DSCP_SHIFT 2
+
+static inline dscp_t inet_dsfield_to_dscp(__u8 dsfield)
+{
+	return (__force dscp_t)(dsfield >> INET_DSCP_SHIFT);
+}
+
+static inline __u8 inet_dscp_to_dsfield(dscp_t dscp)
+{
+	return (__force __u8)dscp << INET_DSCP_SHIFT;
+}
+
+static inline bool inet_validate_dscp(__u8 val)
+{
+	return !(val & ~INET_DSCP_MASK);
+}
+
+#endif /* _INET_DSCP_H */
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 53ac7707ca70..3a457db7a4f6 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -18,6 +18,7 @@
 #include <net/ndisc.h>
 #include <net/flow.h>
 #include <net/flow_dissector.h>
+#include <net/inet_dscp.h>
 #include <net/snmp.h>
 #include <net/netns/hash.h>
 
@@ -965,6 +966,11 @@ static inline u8 ip6_tclass(__be32 flowinfo)
 	return ntohl(flowinfo & IPV6_TCLASS_MASK) >> IPV6_TCLASS_SHIFT;
 }
 
+static inline dscp_t ip6_dscp(__be32 flowinfo)
+{
+	return inet_dsfield_to_dscp(ip6_tclass(flowinfo));
+}
+
 static inline __be32 ip6_make_flowinfo(unsigned int tclass, __be32 flowlabel)
 {
 	return htonl(tclass << IPV6_TCLASS_SHIFT) | flowlabel;
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index dcedfe29d9d9..82d95d00214c 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -16,6 +16,7 @@
 #include <linux/indirect_call_wrapper.h>
 
 #include <net/fib_rules.h>
+#include <net/inet_dscp.h>
 #include <net/ipv6.h>
 #include <net/addrconf.h>
 #include <net/ip6_route.h>
@@ -25,14 +26,14 @@ struct fib6_rule {
 	struct fib_rule		common;
 	struct rt6key		src;
 	struct rt6key		dst;
-	u8			tclass;
+	dscp_t			dscp;
 };
 
 static bool fib6_rule_matchall(const struct fib_rule *rule)
 {
 	struct fib6_rule *r = container_of(rule, struct fib6_rule, common);
 
-	if (r->dst.plen || r->src.plen || r->tclass)
+	if (r->dst.plen || r->src.plen || r->dscp)
 		return false;
 	return fib_rule_matchall(rule);
 }
@@ -323,7 +324,7 @@ INDIRECT_CALLABLE_SCOPE int fib6_rule_match(struct fib_rule *rule,
 			return 0;
 	}
 
-	if (r->tclass && r->tclass != ip6_tclass(fl6->flowlabel))
+	if (r->dscp && r->dscp != ip6_dscp(fl6->flowlabel))
 		return 0;
 
 	if (rule->ip_proto && (rule->ip_proto != fl6->flowi6_proto))
@@ -353,6 +354,12 @@ static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
 	struct net *net = sock_net(skb->sk);
 	struct fib6_rule *rule6 = (struct fib6_rule *) rule;
 
+	if (!inet_validate_dscp(frh->tos)) {
+		NL_SET_ERR_MSG(extack, "Invalid dsfield (tos): ECN bits must be 0");
+		goto errout;
+	}
+	rule6->dscp = inet_dsfield_to_dscp(frh->tos);
+
 	if (rule->action == FR_ACT_TO_TBL && !rule->l3mdev) {
 		if (rule->table == RT6_TABLE_UNSPEC) {
 			NL_SET_ERR_MSG(extack, "Invalid table");
@@ -373,7 +380,6 @@ static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
 
 	rule6->src.plen = frh->src_len;
 	rule6->dst.plen = frh->dst_len;
-	rule6->tclass = frh->tos;
 
 	if (fib_rule_requires_fldissect(rule))
 		net->ipv6.fib6_rules_require_fldissect++;
@@ -406,7 +412,7 @@ static int fib6_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh,
 	if (frh->dst_len && (rule6->dst.plen != frh->dst_len))
 		return 0;
 
-	if (frh->tos && (rule6->tclass != frh->tos))
+	if (frh->tos && inet_dscp_to_dsfield(rule6->dscp) != frh->tos)
 		return 0;
 
 	if (frh->src_len &&
@@ -427,7 +433,7 @@ static int fib6_rule_fill(struct fib_rule *rule, struct sk_buff *skb,
 
 	frh->dst_len = rule6->dst.plen;
 	frh->src_len = rule6->src.plen;
-	frh->tos = rule6->tclass;
+	frh->tos = inet_dscp_to_dsfield(rule6->dscp);
 
 	if ((rule6->dst.plen &&
 	     nla_put_in6_addr(skb, FRA_DST, &rule6->dst.addr)) ||
-- 
2.21.3

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ