Commit f5518257 authored by Geliang Tang's avatar Geliang Tang
Browse files

inet: implement lockless IP_TOS 

mainline inclusion
from mainline-v6.7-rc1
commit e08d0b3d172311e2bb500865c0d0038533d0ff11
category: feature
bugzilla: https://gitee.com/openeuler/kernel/issues/I9VYQ9
CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git/commit/?id=e08d0b3d172311e2bb500865c0d0038533d0ff11



--------------------------------

Some reads of inet->tos are racy.

Add needed READ_ONCE() annotations and convert IP_TOS option lockless.

v2: missing changes in include/net/route.h (David Ahern)
rebased: on "mptcp: fix setsockopt(IP_TOS) subflow locking" (Geliang)

Signed-off-by: default avatarEric Dumazet <edumazet@google.com>
Reviewed-by: default avatarDavid Ahern <dsahern@kernel.org>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
Reviewed-by: default avatarJackie Liu <liuyun01@kylinos.cn>
Signed-off-by: default avatarGeliang Tang <tanggeliang@kylinos.cn>
parent 86cc03e9

net/ipv4/ip_sockglue.c

+11 −9
Original line number Diff line number Diff line
@@ -587,12 +587,14 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) 


void __ip_sock_set_tos(struct sock *sk, int val)

{

	u8 old_tos = inet_sk(sk)->tos;



	if (sk->sk_type == SOCK_STREAM) {

		val &= ~INET_ECN_MASK;

		val |= inet_sk(sk)->tos & INET_ECN_MASK;

		val |= old_tos & INET_ECN_MASK;

	}

	if (inet_sk(sk)->tos != val) {

		inet_sk(sk)->tos = val;

	if (old_tos != val) {

		WRITE_ONCE(inet_sk(sk)->tos, val);

		WRITE_ONCE(sk->sk_priority, rt_tos2priority(val));

		sk_dst_reset(sk);

	}
@@ -1050,6 +1052,9 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, 
		return 0;

	case IP_MTU_DISCOVER:

		return ip_sock_set_mtu_discover(sk, val);

	case IP_TOS:	/* This sets both TOS and Precedence */

		ip_sock_set_tos(sk, val);

		return 0;

	}



	err = 0;
@@ -1104,9 +1109,6 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, 
			}

		}

		break;

	case IP_TOS:	/* This sets both TOS and Precedence */

		__ip_sock_set_tos(sk, val);

		break;

	case IP_UNICAST_IF:

	{

		struct net_device *dev = NULL;
@@ -1595,6 +1597,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, 
	case IP_MTU_DISCOVER:

		val = READ_ONCE(inet->pmtudisc);

		goto copyval;

	case IP_TOS:

		val = READ_ONCE(inet->tos);

		goto copyval;

	}



	if (needs_rtnl)
@@ -1631,9 +1636,6 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, 
			return -EFAULT;

		return 0;

	}

	case IP_TOS:

		val = inet->tos;

		break;

	case IP_MTU:

	{

		struct dst_entry *dst;

net/ipv4/tcp_ipv4.c

+5 −4
Original line number Diff line number Diff line
@@ -1024,10 +1024,11 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst, 
	if (skb) {

		__tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr);



		tos = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) ?

				(tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) |

				(inet_sk(sk)->tos & INET_ECN_MASK) :

				inet_sk(sk)->tos;

		tos = READ_ONCE(inet_sk(sk)->tos);



		if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos))

			tos = (tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) |

			      (tos & INET_ECN_MASK);



		if (!INET_ECN_is_capable(tos) &&

		    tcp_bpf_ca_needs_ecn((struct sock *)req))