From 959d5c11601b2b337c364b2e3102d392365e3dd3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 22 Sep 2023 03:42:19 +0000 Subject: [PATCH] inet: implement lockless getsockopt(IP_UNICAST_IF) 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: Eric Dumazet Reviewed-by: David Ahern Signed-off-by: David S. Miller --- net/ipv4/datagram.c | 2 +- net/ipv4/ip_sockglue.c | 10 +++++----- net/ipv4/ping.c | 2 +- net/ipv4/raw.c | 13 +++++++------ net/ipv4/udp.c | 12 +++++++----- 5 files changed, 21 insertions(+), 18 deletions(-) diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index cb5dbee9e018..1480e9ebdfef 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -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, diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 04579e390ddd..58995526c6e9 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -1113,7 +1113,7 @@ 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; } @@ -1130,7 +1130,7 @@ 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; } @@ -1633,6 +1633,9 @@ 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) @@ -1640,9 +1643,6 @@ 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; diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 50d12b0c8d46..66ad1f95af49 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -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, diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index ade1aecd7c71..e2357d23202e 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -482,7 +482,7 @@ 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; @@ -576,24 +576,25 @@ 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; } } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 731a723dc808..1e0c3aba1e5a 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1055,6 +1055,7 @@ 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; @@ -1173,6 +1174,7 @@ 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; @@ -1180,18 +1182,18 @@ 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; } }