aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorEric Dumazet <edumazet@google.com>2023-08-16 08:15:46 +0000
committerDavid S. Miller <davem@davemloft.net>2023-08-16 11:09:18 +0100
commit10f42426e5bcea728d7fae96609b29b4fb1f7518 (patch)
tree96616c34b54ec1557e0b65ed307efd6f060141a4
parent08e39c0dfa29f233f5a621f7d274b793a080c769 (diff)
downloadnf-next-10f42426e5bcea728d7fae96609b29b4fb1f7518.tar.gz
inet: implement lockless IP_TTL
ip_select_ttl() is racy, because it reads inet->uc_ttl without proper locking. Add READ_ONCE()/WRITE_ONCE() annotations while allowing IP_TTL socket option to be set/read without holding the socket lock. Signed-off-by: Eric Dumazet <edumazet@google.com> Acked-by: Soheil Hassas Yeganeh <soheil@google.com> Reviewed-by: Simon Horman <horms@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
-rw-r--r--net/ipv4/ip_output.c2
-rw-r--r--net/ipv4/ip_sockglue.c27
2 files changed, 13 insertions, 16 deletions
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 8f396eada1b6e..ce6257860a401 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -133,7 +133,7 @@ EXPORT_SYMBOL_GPL(ip_local_out);
static inline int ip_select_ttl(const struct inet_sock *inet,
const struct dst_entry *dst)
{
- int ttl = inet->uc_ttl;
+ int ttl = READ_ONCE(inet->uc_ttl);
if (ttl < 0)
ttl = ip4_dst_hoplimit(dst);
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index cfa65a0b0900f..dbb2d2342ebf0 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -1023,6 +1023,13 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
case IP_BIND_ADDRESS_NO_PORT:
inet_assign_bit(BIND_ADDRESS_NO_PORT, sk, val);
return 0;
+ case IP_TTL:
+ if (optlen < 1)
+ return -EINVAL;
+ if (val != -1 && (val < 1 || val > 255))
+ return -EINVAL;
+ WRITE_ONCE(inet->uc_ttl, val);
+ return 0;
}
err = 0;
@@ -1080,13 +1087,6 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
case IP_TOS: /* This sets both TOS and Precedence */
__ip_sock_set_tos(sk, val);
break;
- case IP_TTL:
- if (optlen < 1)
- goto e_inval;
- if (val != -1 && (val < 1 || val > 255))
- goto e_inval;
- inet->uc_ttl = val;
- break;
case IP_MTU_DISCOVER:
if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_OMIT)
goto e_inval;
@@ -1590,6 +1590,11 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
case IP_BIND_ADDRESS_NO_PORT:
val = inet_test_bit(BIND_ADDRESS_NO_PORT, sk);
goto copyval;
+ case IP_TTL:
+ val = READ_ONCE(inet->uc_ttl);
+ if (val < 0)
+ val = READ_ONCE(sock_net(sk)->ipv4.sysctl_ip_default_ttl);
+ goto copyval;
}
if (needs_rtnl)
@@ -1629,14 +1634,6 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
case IP_TOS:
val = inet->tos;
break;
- case IP_TTL:
- {
- struct net *net = sock_net(sk);
- val = (inet->uc_ttl == -1 ?
- READ_ONCE(net->ipv4.sysctl_ip_default_ttl) :
- inet->uc_ttl);
- break;
- }
case IP_MTU_DISCOVER:
val = inet->pmtudisc;
break;