ipv4: remove get_rttos

Initialize the ip cookie tos field when initializing the cookie, in
ipcm_init_sk.

The existing code inverts the standard pattern for initializing cookie
fields. Default is to initialize the field from the sk, then possibly
overwrite that when parsing cmsgs (the unlikely case).

This field inverts that, setting the field to an illegal value and
after cmsg parsing checking whether the value is still illegal and
thus should be overridden.

Be careful to always apply mask INET_DSCP_MASK, as before.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20250214222720.3205500-5-willemdebruijn.kernel@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/include/net/ip.h b/include/net/ip.h
index 3c4ef5d..ce5e599 100644 (file)
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -92,7 +92,9 @@ static inline void ipcm_init(struct ipcm_cookie *ipcm)
 static inline void ipcm_init_sk(struct ipcm_cookie *ipcm,
                                const struct inet_sock *inet)
 {
-       ipcm_init(ipcm);
+       *ipcm = (struct ipcm_cookie) {
+               .tos = READ_ONCE(inet->tos),
+       };
 
        sockcm_init(&ipcm->sockc, &inet->sk);
 
@@ -256,13 +258,6 @@ static inline u8 ip_sendmsg_scope(const struct inet_sock *inet,
        return RT_SCOPE_UNIVERSE;
 }
 
-static inline __u8 get_rttos(struct ipcm_cookie* ipc, struct inet_sock *inet)
-{
-       u8 dsfield = ipc->tos != -1 ? ipc->tos : READ_ONCE(inet->tos);
-
-       return dsfield & INET_DSCP_MASK;
-}
-
 /* datagram.c */
 int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
 int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);

diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 619ddc0..85d09f2 100644 (file)
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -705,7 +705,7 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
        struct ip_options_data opt_copy;
        int free = 0;
        __be32 saddr, daddr, faddr;
-       u8 tos, scope;
+       u8 scope;
        int err;
 
        pr_debug("ping_v4_sendmsg(sk=%p,sk->num=%u)\n", inet, inet->inet_num);
@@ -768,7 +768,6 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
                }
                faddr = ipc.opt->opt.faddr;
        }
-       tos = get_rttos(&ipc, inet);
        scope = ip_sendmsg_scope(inet, &ipc, msg);
 
        if (ipv4_is_multicast(daddr)) {
@@ -779,7 +778,8 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
        } else if (!ipc.oif)
                ipc.oif = READ_ONCE(inet->uc_index);
 
-       flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos, scope,
+       flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark,
+                          ipc.tos & INET_DSCP_MASK, scope,
                           sk->sk_protocol, inet_sk_flowi_flags(sk), faddr,
                           saddr, 0, 0, sk->sk_uid);
 

diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 4304a68..6aace4d 100644 (file)
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -486,7 +486,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
        struct ipcm_cookie ipc;
        struct rtable *rt = NULL;
        struct flowi4 fl4;
-       u8 tos, scope;
+       u8 scope;
        int free = 0;
        __be32 daddr;
        __be32 saddr;
@@ -581,7 +581,6 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
                        daddr = ipc.opt->opt.faddr;
                }
        }
-       tos = get_rttos(&ipc, inet);
        scope = ip_sendmsg_scope(inet, &ipc, msg);
 
        uc_index = READ_ONCE(inet->uc_index);
@@ -606,7 +605,8 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
                }
        }
 
-       flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos, scope,
+       flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark,
+                          ipc.tos & INET_DSCP_MASK, scope,
                           hdrincl ? ipc.protocol : sk->sk_protocol,
                           inet_sk_flowi_flags(sk) |
                            (hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 3485989..17c7736 100644 (file)
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1280,7 +1280,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
        int free = 0;
        int connected = 0;
        __be32 daddr, faddr, saddr;
-       u8 tos, scope;
+       u8 scope;
        __be16 dport;
        int err, is_udplite = IS_UDPLITE(sk);
        int corkreq = udp_test_bit(CORK, sk) || msg->msg_flags & MSG_MORE;
@@ -1404,7 +1404,6 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
                faddr = ipc.opt->opt.faddr;
                connected = 0;
        }
-       tos = get_rttos(&ipc, inet);
        scope = ip_sendmsg_scope(inet, &ipc, msg);
        if (scope == RT_SCOPE_LINK)
                connected = 0;
@@ -1441,7 +1440,8 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
                fl4 = &fl4_stack;
 
-               flowi4_init_output(fl4, ipc.oif, ipc.sockc.mark, tos, scope,
+               flowi4_init_output(fl4, ipc.oif, ipc.sockc.mark,
+                                  ipc.tos & INET_DSCP_MASK, scope,
                                   sk->sk_protocol, flow_flags, faddr, saddr,
                                   dport, inet->inet_sport, sk->sk_uid);