ipv6: Define dscp_t and stop taking ECN bits into account in fib6-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 struct fib6_rule, so
that fib6-rules don't get influenced by ECN bits anymore.

Before this patch, fib6-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 fib6-rules only compare the DSCP bits. ECN doesn't
influence the result anymore. Also, fib6-rules now must have the ECN
bits cleared or they will be rejected.

Signed-off-by: Guillaume Nault <gnault@redhat.com>
Acked-by: David Ahern <dsahern@kernel.org>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

2 files changed, 63 insertions, 0 deletions

diff --git a/include/net/inet_dscp.h b/include/net/inet_dscp.h
new file mode 100644
index 000000000000..72f250dffada
--- /dev/null
+++ b/include/net/inet_dscp.h
@@ -0,0 +1,57 @@
+/* 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 DS field with the CU (ECN) bits cleared.
+ * Using dscp_t allows to strictly separate DSCP and ECN bits, thus avoiding
+ * bugs where ECN bits are erroneously taken into account during FIB lookups
+ * or policy routing.
+ *
+ * Note: to get the real DSCP value contained in a dscp_t variable one would
+ * have to do a bit shift after calling inet_dscp_to_dsfield(). We could have
+ * a helper for that, but there's currently no users.
+ */
+typedef u8 __bitwise dscp_t;
+
+#define INET_DSCP_MASK 0xfc
+
+static inline dscp_t inet_dsfield_to_dscp(__u8 dsfield)
+{
+	return (__force dscp_t)(dsfield & INET_DSCP_MASK);
+}
+
+static inline __u8 inet_dscp_to_dsfield(dscp_t dscp)
+{
+	return (__force __u8)dscp;
+}
+
+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 cda1f205f391..f693784e1419 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -17,6 +17,7 @@
 #include <net/if_inet6.h>
 #include <net/flow.h>
 #include <net/flow_dissector.h>
+#include <net/inet_dscp.h>
 #include <net/snmp.h>
 #include <net/netns/hash.h>
 
@@ -974,6 +975,11 @@ 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;