Commit 38bd05d3 authored by Eric Dumazet's avatar Eric Dumazet Committed by Geliang Tang
Browse files

inet: implement lockless getsockopt(IP_UNICAST_IF) 

mainline inclusion
from mainline-v6.7-rc1
commit 959d5c11601b2b337c364b2e3102d392365e3dd3
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=959d5c11601b2b337c364b2e3102d392365e3dd3



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

Add missing READ_ONCE() annotations when reading inet->uc_index

Implementing getsockopt(IP_UNICAST_IF) locklessly seems possible,
the setsockopt() part might not be possible at the moment.

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 a18b2d1c

net/ipv4/datagram.c

+1 −1
Original line number Diff line number Diff line
@@ -43,7 +43,7 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len 
		if (!saddr)

			saddr = inet->mc_addr;

	} else if (!oif) {

		oif = inet->uc_index;

		oif = READ_ONCE(inet->uc_index);

	}

	fl4 = &inet->cork.fl.u.ip4;

	rt = ip_route_connect(fl4, usin->sin_addr.s_addr, saddr, oif,

net/ipv4/ip_sockglue.c

+5 −5
Original line number Diff line number Diff line
@@ -1120,7 +1120,7 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, 


		ifindex = (__force int)ntohl((__force __be32)val);

		if (ifindex == 0) {

			inet->uc_index = 0;

			WRITE_ONCE(inet->uc_index, 0);

			err = 0;

			break;

		}
@@ -1137,7 +1137,7 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, 
		if (sk->sk_bound_dev_if && midx != sk->sk_bound_dev_if)

			break;



		inet->uc_index = ifindex;

		WRITE_ONCE(inet->uc_index, ifindex);

		err = 0;

		break;

	}
@@ -1642,6 +1642,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, 
			return -ENOTCONN;

		goto copyval;

	}

	case IP_UNICAST_IF:

		val = (__force int)htonl((__u32) READ_ONCE(inet->uc_index));

		goto copyval;

	}



	if (needs_rtnl)
@@ -1649,9 +1652,6 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, 
	sockopt_lock_sock(sk);



	switch (optname) {

	case IP_UNICAST_IF:

		val = (__force int)htonl((__u32) inet->uc_index);

		break;

	case IP_MULTICAST_IF:

	{

		struct in_addr addr;

net/ipv4/ping.c

+1 −1
Original line number Diff line number Diff line
@@ -777,7 +777,7 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) 
		if (!saddr)

			saddr = inet->mc_addr;

	} else if (!ipc.oif)

		ipc.oif = inet->uc_index;

		ipc.oif = READ_ONCE(inet->uc_index);



	flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos, scope,

			   sk->sk_protocol, inet_sk_flowi_flags(sk), faddr,

net/ipv4/raw.c

+7 −6
Original line number Diff line number Diff line
@@ -483,7 +483,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) 
	int free = 0;

	__be32 daddr;

	__be32 saddr;

	int err;

	int uc_index, err;

	struct ip_options_data opt_copy;

	struct raw_frag_vec rfv;

	int hdrincl;
@@ -577,24 +577,25 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) 
	tos = get_rttos(&ipc, inet);

	scope = ip_sendmsg_scope(inet, &ipc, msg);



	uc_index = READ_ONCE(inet->uc_index);

	if (ipv4_is_multicast(daddr)) {

		if (!ipc.oif || netif_index_is_l3_master(sock_net(sk), ipc.oif))

			ipc.oif = inet->mc_index;

		if (!saddr)

			saddr = inet->mc_addr;

	} else if (!ipc.oif) {

		ipc.oif = inet->uc_index;

	} else if (ipv4_is_lbcast(daddr) && inet->uc_index) {

		ipc.oif = uc_index;

	} else if (ipv4_is_lbcast(daddr) && uc_index) {

		/* oif is set, packet is to local broadcast

		 * and uc_index is set. oif is most likely set

		 * by sk_bound_dev_if. If uc_index != oif check if the

		 * oif is an L3 master and uc_index is an L3 slave.

		 * If so, we want to allow the send using the uc_index.

		 */

		if (ipc.oif != inet->uc_index &&

		if (ipc.oif != uc_index &&

		    ipc.oif == l3mdev_master_ifindex_by_index(sock_net(sk),

							      inet->uc_index)) {

			ipc.oif = inet->uc_index;

							      uc_index)) {

			ipc.oif = uc_index;

		}

	}

net/ipv4/udp.c

+7 −5
Original line number Diff line number Diff line
@@ -1063,6 +1063,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) 
	int (*getfrag)(void *, char *, int, int, int, struct sk_buff *);

	struct sk_buff *skb;

	struct ip_options_data opt_copy;

	int uc_index;



	if (len > 0xFFFF)

		return -EMSGSIZE;
@@ -1184,6 +1185,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) 
	if (scope == RT_SCOPE_LINK)

		connected = 0;



	uc_index = READ_ONCE(inet->uc_index);

	if (ipv4_is_multicast(daddr)) {

		if (!ipc.oif || netif_index_is_l3_master(sock_net(sk), ipc.oif))

			ipc.oif = inet->mc_index;
@@ -1191,18 +1193,18 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) 
			saddr = inet->mc_addr;

		connected = 0;

	} else if (!ipc.oif) {

		ipc.oif = inet->uc_index;

	} else if (ipv4_is_lbcast(daddr) && inet->uc_index) {

		ipc.oif = uc_index;

	} else if (ipv4_is_lbcast(daddr) && uc_index) {

		/* oif is set, packet is to local broadcast and

		 * uc_index is set. oif is most likely set

		 * by sk_bound_dev_if. If uc_index != oif check if the

		 * oif is an L3 master and uc_index is an L3 slave.

		 * If so, we want to allow the send using the uc_index.

		 */

		if (ipc.oif != inet->uc_index &&

		if (ipc.oif != uc_index &&

		    ipc.oif == l3mdev_master_ifindex_by_index(sock_net(sk),

							      inet->uc_index)) {

			ipc.oif = inet->uc_index;

							      uc_index)) {

			ipc.oif = uc_index;

		}

	}