ipv4: Convert ->flowi4_tos to dscp_t.

Convert the ->flowic_tos field of struct flowi_common from __u8 to
dscp_t, rename it ->flowic_dscp and propagate these changes to struct
flowi and struct flowi4.

We've had several bugs in the past where ECN bits could interfere with
IPv4 routing, because these bits were not properly cleared when setting
->flowi4_tos. These bugs should be fixed now and the dscp_t type has
been introduced to ensure that variables carrying DSCP values don't
accidentally have any ECN bits set. Several variables and structure
fields have been converted to dscp_t already, but the main IPv4 routing
structure, struct flowi4, is still using a __u8. To avoid any future
regression, this patch converts it to dscp_t.

There are many users to convert at once. Fortunately, around half of
->flowi4_tos users already have a dscp_t value at hand, which they
currently convert to __u8 using inet_dscp_to_dsfield(). For all of
these users, we just need to drop that conversion.

But, although we try to do the __u8 <-> dscp_t conversions at the
boundaries of the network or of user space, some places still store
TOS/DSCP variables as __u8 in core networking code. Those can hardly be
converted either because the data structure is part of UAPI or because
the same variable or field is also used for handling ECN in other parts
of the code. In all of these cases where we don't have a dscp_t
variable at hand, we need to use inet_dsfield_to_dscp() when
interacting with ->flowi4_dscp.

Changes since v1:
  * Fix space alignment in __bpf_redirect_neigh_v4() (Ido).

Signed-off-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Link: https://patch.msgid.link/29acecb45e911d17446b9a3dbdb1ab7b821ea371.1756128932.git.gnault@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

2 files changed, 4 insertions, 4 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index 5da1cad66be2..b005363f482c 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2373,7 +2373,7 @@ static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev,
 		struct flowi4 fl4 = {
 			.flowi4_flags = FLOWI_FLAG_ANYSRC,
 			.flowi4_mark  = skb->mark,
-			.flowi4_tos   = inet_dscp_to_dsfield(ip4h_dscp(ip4h)),
+			.flowi4_dscp  = ip4h_dscp(ip4h),
 			.flowi4_oif   = dev->ifindex,
 			.flowi4_proto = ip4h->protocol,
 			.daddr	      = ip4h->daddr,
@@ -6020,7 +6020,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 		fl4.flowi4_iif = params->ifindex;
 		fl4.flowi4_oif = 0;
 	}
-	fl4.flowi4_tos = params->tos & INET_DSCP_MASK;
+	fl4.flowi4_dscp = inet_dsfield_to_dscp(params->tos);
 	fl4.flowi4_scope = RT_SCOPE_UNIVERSE;
 	fl4.flowi4_flags = 0;
 
diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c
index ae74634310a3..9f40be0c3e71 100644
--- a/net/core/lwt_bpf.c
+++ b/net/core/lwt_bpf.c
@@ -8,12 +8,12 @@
 #include <linux/skbuff.h>
 #include <linux/types.h>
 #include <linux/bpf.h>
+#include <net/flow.h>
 #include <net/lwtunnel.h>
 #include <net/gre.h>
 #include <net/ip.h>
 #include <net/ip6_route.h>
 #include <net/ipv6_stubs.h>
-#include <net/inet_dscp.h>
 
 struct bpf_lwt_prog {
 	struct bpf_prog *prog;
@@ -209,7 +209,7 @@ static int bpf_lwt_xmit_reroute(struct sk_buff *skb)
 		fl4.flowi4_oif = oif;
 		fl4.flowi4_mark = skb->mark;
 		fl4.flowi4_uid = sock_net_uid(net, sk);
-		fl4.flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(iph));
+		fl4.flowi4_dscp = ip4h_dscp(iph);
 		fl4.flowi4_flags = FLOWI_FLAG_ANYSRC;
 		fl4.flowi4_proto = iph->protocol;
 		fl4.daddr = iph->daddr;