From 47afa284b96c62bda127604e6091fd5c9fd7e42c Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 29 Aug 2024 09:54:48 +0300 Subject: [PATCH 01/12] ipv4: Unmask upper DSCP bits in RTM_GETROUTE output route lookup Unmask the upper DSCP bits when looking up an output route via the RTM_GETROUTE netlink message so that in the future the lookup could be performed according to the full DSCP value. No functional changes intended since the upper DSCP bits are masked when comparing against the TOS selectors in FIB rules and routes. Signed-off-by: Ido Schimmel Reviewed-by: Guillaume Nault Signed-off-by: David S. Miller --- net/ipv4/route.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index f6972b24664a..e4b45aa18470 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -3261,7 +3261,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, fl4.daddr = dst; fl4.saddr = src; - fl4.flowi4_tos = rtm->rtm_tos & IPTOS_RT_MASK; + fl4.flowi4_tos = rtm->rtm_tos & INET_DSCP_MASK; fl4.flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0; fl4.flowi4_mark = mark; fl4.flowi4_uid = uid; From a63cef46adcbedd4f4ea7401773a310edca53131 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 29 Aug 2024 09:54:49 +0300 Subject: [PATCH 02/12] ipv4: Unmask upper DSCP bits in ip_route_output_key_hash() Unmask the upper DSCP bits so that in the future output routes could be looked up according to the full DSCP value. Signed-off-by: Ido Schimmel Reviewed-by: Guillaume Nault Signed-off-by: David S. Miller --- net/ipv4/route.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index e4b45aa18470..5a77dc6d9c72 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2618,7 +2618,7 @@ struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, struct rtable *rth; fl4->flowi4_iif = LOOPBACK_IFINDEX; - fl4->flowi4_tos &= IPTOS_RT_MASK; + fl4->flowi4_tos &= INET_DSCP_MASK; rcu_read_lock(); rth = ip_route_output_key_hash_rcu(net, fl4, &res, skb); From 4805646c42e51d2fbf142864d281473ad453ad5d Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 29 Aug 2024 09:54:50 +0300 Subject: [PATCH 03/12] ipv4: icmp: Unmask upper DSCP bits in icmp_route_lookup() The function is called to resolve a route for an ICMP message that is sent in response to a situation. Based on the type of the generated ICMP message, the function is either passed the DS field of the packet that generated the ICMP message or a DS field that is derived from it. Unmask the upper DSCP bits before resolving and output route via ip_route_output_key_hash() so that in the future the lookup could be performed according to the full DSCP value. Signed-off-by: Ido Schimmel Reviewed-by: Guillaume Nault Signed-off-by: David S. Miller --- net/ipv4/icmp.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 1ed88883e1f2..d2463b6e390e 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -93,6 +93,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS #include @@ -497,7 +498,7 @@ static struct rtable *icmp_route_lookup(struct net *net, fl4->saddr = saddr; fl4->flowi4_mark = mark; fl4->flowi4_uid = sock_net_uid(net, NULL); - fl4->flowi4_tos = RT_TOS(tos); + fl4->flowi4_tos = tos & INET_DSCP_MASK; fl4->flowi4_proto = IPPROTO_ICMP; fl4->fl4_icmp_type = type; fl4->fl4_icmp_code = code; From ff95cb5e521b60d046e6571ada697a0977b189c3 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 29 Aug 2024 09:54:51 +0300 Subject: [PATCH 04/12] ipv4: Unmask upper DSCP bits in ip_sock_rt_tos() The function is used to read the DS field that was stored in IPv4 sockets via the IP_TOS socket option so that it could be used to initialize the flowi4_tos field before resolving an output route. Unmask the upper DSCP bits so that in the future the output route lookup could be performed according to the full DSCP value. Signed-off-by: Ido Schimmel Reviewed-by: Guillaume Nault Signed-off-by: David S. Miller --- include/net/route.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/include/net/route.h b/include/net/route.h index 93833cfe9c96..b896f086ec8e 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include @@ -45,7 +46,7 @@ static inline __u8 ip_sock_rt_scope(const struct sock *sk) static inline __u8 ip_sock_rt_tos(const struct sock *sk) { - return RT_TOS(READ_ONCE(inet_sk(sk)->tos)); + return READ_ONCE(inet_sk(sk)->tos) & INET_DSCP_MASK; } struct ip_tunnel_info; From 356d054a4967e6190ee558b8e839fad3e9db35ec Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 29 Aug 2024 09:54:52 +0300 Subject: [PATCH 05/12] ipv4: Unmask upper DSCP bits in get_rttos() The function is used by a few socket types to retrieve the TOS value with which to perform the FIB lookup for packets sent through the socket (flowi4_tos). If a DS field was passed using the IP_TOS control message, then it is used. Otherwise the one specified via the IP_TOS socket option. Unmask the upper DSCP bits so that in the future the lookup could be performed according to the full DSCP value. Signed-off-by: Ido Schimmel Reviewed-by: Guillaume Nault Signed-off-by: David S. Miller --- include/net/ip.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/include/net/ip.h b/include/net/ip.h index 1ee472fa8b37..d92d3bc3ec0e 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -33,6 +33,7 @@ #include #include #include +#include #define IPV4_MAX_PMTU 65535U /* RFC 2675, Section 5.1 */ #define IPV4_MIN_MTU 68 /* RFC 791 */ @@ -258,7 +259,9 @@ static inline u8 ip_sendmsg_scope(const struct inet_sock *inet, static inline __u8 get_rttos(struct ipcm_cookie* ipc, struct inet_sock *inet) { - return (ipc->tos != -1) ? RT_TOS(ipc->tos) : RT_TOS(READ_ONCE(inet->tos)); + u8 dsfield = ipc->tos != -1 ? ipc->tos : READ_ONCE(inet->tos); + + return dsfield & INET_DSCP_MASK; } /* datagram.c */ From f6c89e95555ace0cb10d01b07756bfa5db5ee7fa Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 29 Aug 2024 09:54:53 +0300 Subject: [PATCH 06/12] ipv4: Unmask upper DSCP bits when building flow key build_sk_flow_key() and __build_flow_key() are used to build an IPv4 flow key before calling one of the FIB lookup APIs. Unmask the upper DSCP bits so that in the future the lookup could be performed according to the full DSCP value. Signed-off-by: Ido Schimmel Reviewed-by: Guillaume Nault Signed-off-by: David S. Miller --- net/ipv4/route.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 5a77dc6d9c72..723ac9181558 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -512,7 +512,7 @@ static void __build_flow_key(const struct net *net, struct flowi4 *fl4, sk->sk_protocol; } - flowi4_init_output(fl4, oif, mark, tos & IPTOS_RT_MASK, scope, + flowi4_init_output(fl4, oif, mark, tos & INET_DSCP_MASK, scope, prot, flow_flags, iph->daddr, iph->saddr, 0, 0, sock_net_uid(net, sk)); } @@ -541,7 +541,7 @@ static void build_sk_flow_key(struct flowi4 *fl4, const struct sock *sk) if (inet_opt && inet_opt->opt.srr) daddr = inet_opt->opt.faddr; flowi4_init_output(fl4, sk->sk_bound_dev_if, READ_ONCE(sk->sk_mark), - ip_sock_rt_tos(sk) & IPTOS_RT_MASK, + ip_sock_rt_tos(sk), ip_sock_rt_scope(sk), inet_test_bit(HDRINCL, sk) ? IPPROTO_RAW : sk->sk_protocol, From b261b2c6c18bcb81d69de011fd991bdfb97259f7 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 29 Aug 2024 09:54:54 +0300 Subject: [PATCH 07/12] xfrm: Unmask upper DSCP bits in xfrm_get_tos() The function returns a value that is used to initialize 'flowi4_tos' before being passed to the FIB lookup API in the following call chain: xfrm_bundle_create() tos = xfrm_get_tos(fl, family) xfrm_dst_lookup(..., tos, ...) __xfrm_dst_lookup(..., tos, ...) xfrm4_dst_lookup(..., tos, ...) __xfrm4_dst_lookup(..., tos, ...) fl4->flowi4_tos = tos __ip_route_output_key(net, fl4) Unmask the upper DSCP bits so that in the future the output route lookup could be performed according to the full DSCP value. Remove IPTOS_RT_MASK since it is no longer used. Signed-off-by: Ido Schimmel Reviewed-by: Guillaume Nault Signed-off-by: David S. Miller --- include/net/route.h | 2 -- net/xfrm/xfrm_policy.c | 3 ++- 2 files changed, 2 insertions(+), 3 deletions(-) diff --git a/include/net/route.h b/include/net/route.h index b896f086ec8e..1789f1e6640b 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -266,8 +266,6 @@ static inline void ip_rt_put(struct rtable *rt) dst_release(&rt->dst); } -#define IPTOS_RT_MASK (IPTOS_TOS_MASK & ~3) - extern const __u8 ip_tos2prio[16]; static inline char rt_tos2priority(u8 tos) diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index c56c61b0c12e..b22767c0c078 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -45,6 +45,7 @@ #ifdef CONFIG_XFRM_ESPINTCP #include #endif +#include #include "xfrm_hash.h" @@ -2561,7 +2562,7 @@ xfrm_tmpl_resolve(struct xfrm_policy **pols, int npols, const struct flowi *fl, static int xfrm_get_tos(const struct flowi *fl, int family) { if (family == AF_INET) - return IPTOS_RT_MASK & fl->u.ip4.flowi4_tos; + return fl->u.ip4.flowi4_tos & INET_DSCP_MASK; return 0; } From 13f6538de2b845650e68996621489de547b0337e Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 29 Aug 2024 09:54:55 +0300 Subject: [PATCH 08/12] ipv4: Unmask upper DSCP bits in ip_send_unicast_reply() The function calls flowi4_init_output() to initialize an IPv4 flow key with which it then performs a FIB lookup using ip_route_output_flow(). 'arg->tos' with which the TOS value in the IPv4 flow key (flowi4_tos) is initialized contains the full DS field. Unmask the upper DSCP bits so that in the future the FIB lookup could be performed according to the full DSCP value. Signed-off-by: Ido Schimmel Reviewed-by: Guillaume Nault Signed-off-by: David S. Miller --- net/ipv4/ip_output.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index b90d0f78ac80..eea443b7f65e 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -77,6 +77,7 @@ #include #include #include +#include #include #include #include @@ -1621,7 +1622,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, flowi4_init_output(&fl4, oif, IP4_REPLY_MARK(net, skb->mark) ?: sk->sk_mark, - RT_TOS(arg->tos), + arg->tos & INET_DSCP_MASK, RT_SCOPE_UNIVERSE, ip_hdr(skb)->protocol, ip_reply_arg_flowi_flags(arg), daddr, saddr, From 6a59526628ad6dadf389f45ddb3f75db44930897 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 29 Aug 2024 09:54:56 +0300 Subject: [PATCH 09/12] ipv6: sit: Unmask upper DSCP bits in ipip6_tunnel_xmit() The function calls flowi4_init_output() to initialize an IPv4 flow key with which it then performs a FIB lookup using ip_route_output_flow(). The 'tos' variable with which the TOS value in the IPv4 flow key (flowi4_tos) is initialized contains the full DS field. Unmask the upper DSCP bits so that in the future the FIB lookup could be performed according to the full DSCP value. Signed-off-by: Ido Schimmel Reviewed-by: Guillaume Nault Signed-off-by: David S. Miller --- net/ipv6/sit.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 83b195f09561..3b2eed7fc765 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -51,6 +51,7 @@ #include #include #include +#include /* This version of net/ipv6/sit.c is cloned of net/ipv4/ip_gre.c @@ -935,8 +936,8 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, } flowi4_init_output(&fl4, tunnel->parms.link, tunnel->fwmark, - RT_TOS(tos), RT_SCOPE_UNIVERSE, IPPROTO_IPV6, - 0, dst, tiph->saddr, 0, 0, + tos & INET_DSCP_MASK, RT_SCOPE_UNIVERSE, + IPPROTO_IPV6, 0, dst, tiph->saddr, 0, 0, sock_net_uid(tunnel->net, NULL)); rt = dst_cache_get_ip4(&tunnel->dst_cache, &fl4.saddr); From 939cd1abf080c629552a9c5e6db4c0509d13e4c7 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 29 Aug 2024 09:54:57 +0300 Subject: [PATCH 10/12] ipvlan: Unmask upper DSCP bits in ipvlan_process_v4_outbound() Unmask the upper DSCP bits when calling ip_route_output_flow() so that in the future it could perform the FIB lookup according to the full DSCP value. Signed-off-by: Ido Schimmel Reviewed-by: Guillaume Nault Signed-off-by: David S. Miller --- drivers/net/ipvlan/ipvlan_core.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index fef4eff7753a..b1afcb8740de 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -2,6 +2,8 @@ /* Copyright (c) 2014 Mahesh Bandewar */ +#include + #include "ipvlan.h" static u32 ipvlan_jhash_secret __read_mostly; @@ -420,7 +422,7 @@ static noinline_for_stack int ipvlan_process_v4_outbound(struct sk_buff *skb) int err, ret = NET_XMIT_DROP; struct flowi4 fl4 = { .flowi4_oif = dev->ifindex, - .flowi4_tos = RT_TOS(ip4h->tos), + .flowi4_tos = ip4h->tos & INET_DSCP_MASK, .flowi4_flags = FLOWI_FLAG_ANYSRC, .flowi4_mark = skb->mark, .daddr = ip4h->daddr, From c5d8ffe29cf2873b62e4bc008ca48d045b6cde88 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 29 Aug 2024 09:54:58 +0300 Subject: [PATCH 11/12] vrf: Unmask upper DSCP bits in vrf_process_v4_outbound() Unmask the upper DSCP bits when calling ip_route_output_flow() so that in the future it could perform the FIB lookup according to the full DSCP value. Signed-off-by: Ido Schimmel Reviewed-by: Guillaume Nault Signed-off-by: David S. Miller --- drivers/net/vrf.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 040f0bb36c0e..a900908eb24a 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -37,6 +37,7 @@ #include #include #include +#include #define DRV_NAME "vrf" #define DRV_VERSION "1.1" @@ -520,7 +521,7 @@ static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb, /* needed to match OIF rule */ fl4.flowi4_l3mdev = vrf_dev->ifindex; fl4.flowi4_iif = LOOPBACK_IFINDEX; - fl4.flowi4_tos = RT_TOS(ip4h->tos); + fl4.flowi4_tos = ip4h->tos & INET_DSCP_MASK; fl4.flowi4_flags = FLOWI_FLAG_ANYSRC; fl4.flowi4_proto = ip4h->protocol; fl4.daddr = ip4h->daddr; From 50033400fc3a4744ea3ef6b7ec6443c5ec15a797 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 29 Aug 2024 09:54:59 +0300 Subject: [PATCH 12/12] bpf: Unmask upper DSCP bits in __bpf_redirect_neigh_v4() Unmask the upper DSCP bits when calling ip_route_output_flow() so that in the future it could perform the FIB lookup according to the full DSCP value. Signed-off-by: Ido Schimmel Reviewed-by: Guillaume Nault Signed-off-by: David S. Miller --- net/core/filter.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/core/filter.c b/net/core/filter.c index f09d875cc053..8569cd2482ee 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2372,7 +2372,7 @@ 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 = RT_TOS(ip4h->tos), + .flowi4_tos = ip4h->tos & INET_DSCP_MASK, .flowi4_oif = dev->ifindex, .flowi4_proto = ip4h->protocol, .daddr = ip4h->daddr,