diff mbox series

[net-next,14/15] inet: implement lockless IP_TTL

Message ID 20230810103927.1705940-15-edumazet@google.com (mailing list archive)
State Superseded
Delegated to: Netdev Maintainers
Headers show
Series inet: socket lock and data-races avoidance | expand

Checks

Context Check Description
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Clearly marked for net-next, async
netdev/fixes_present success Fixes tag not required for -next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit fail Errors and warnings before: 17 this patch: 17
netdev/cc_maintainers warning 1 maintainers not CCed: dsahern@kernel.org
netdev/build_clang fail Errors and warnings before: 18 this patch: 18
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn fail Errors and warnings before: 17 this patch: 17
netdev/checkpatch warning WARNING: line length of 82 exceeds 80 columns
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0

Commit Message

Eric Dumazet Aug. 10, 2023, 10:39 a.m. UTC 
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>
---
 net/ipv4/ip_output.c   |  2 +-
 net/ipv4/ip_sockglue.c | 27 ++++++++++++---------------
 2 files changed, 13 insertions(+), 16 deletions(-)
diff mbox series

Patch

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 8f396eada1b6e61ab174473e9859bc62a10a0d1c..ce6257860a4019d01e28d57d3ce4981fe79d0a0e 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 cfa65a0b0900f2f77bfd800f105ea079e2afff7c..dbb2d2342ebf0c1f1366ee6b6b2158a6118b2659 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;