netdev - [PATCH net-next 7/8] inet: lockless IP

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date: Thu, 21 Sep 2023 13:30:20 +0000
From: Eric Dumazet <edumazet@...gle.com>
To: "David S . Miller" <davem@...emloft.net>, Jakub Kicinski <kuba@...nel.org>, 
	Paolo Abeni <pabeni@...hat.com>
Cc: David Ahern <dsahern@...nel.org>, netdev@...r.kernel.org, eric.dumazet@...il.com, 
	Eric Dumazet <edumazet@...gle.com>
Subject: [PATCH net-next 7/8] inet: lockless IP_PKTOPTIONS implementation

Current implementation is already lockless, because the socket
lock is released before reading socket fields.

Add missing READ_ONCE() annotations.

Note that corresponding WRITE_ONCE() are needed, the order
of the patches do not really matter.

Signed-off-by: Eric Dumazet <edumazet@...gle.com>
---
 net/ipv4/ip_sockglue.c | 76 ++++++++++++++++++++----------------------
 1 file changed, 37 insertions(+), 39 deletions(-)

diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 58995526c6e965d613b8cdea61b84916d608a6fb..1ee01ff64171c94b6b244589518a53ce807a212d 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -1633,6 +1633,43 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
 			return -ENOTCONN;
 		goto copyval;
 	}
+	case IP_PKTOPTIONS:
+	{
+		struct msghdr msg;
+
+		if (sk->sk_type != SOCK_STREAM)
+			return -ENOPROTOOPT;
+
+		if (optval.is_kernel) {
+			msg.msg_control_is_user = false;
+			msg.msg_control = optval.kernel;
+		} else {
+			msg.msg_control_is_user = true;
+			msg.msg_control_user = optval.user;
+		}
+		msg.msg_controllen = len;
+		msg.msg_flags = in_compat_syscall() ? MSG_CMSG_COMPAT : 0;
+
+		if (inet_test_bit(PKTINFO, sk)) {
+			struct in_pktinfo info;
+
+			info.ipi_addr.s_addr = READ_ONCE(inet->inet_rcv_saddr);
+			info.ipi_spec_dst.s_addr = READ_ONCE(inet->inet_rcv_saddr);
+			info.ipi_ifindex = READ_ONCE(inet->mc_index);
+			put_cmsg(&msg, SOL_IP, IP_PKTINFO, sizeof(info), &info);
+		}
+		if (inet_test_bit(TTL, sk)) {
+			int hlim = READ_ONCE(inet->mc_ttl);
+
+			put_cmsg(&msg, SOL_IP, IP_TTL, sizeof(hlim), &hlim);
+		}
+		if (inet_test_bit(TOS, sk)) {
+			int tos = READ_ONCE(inet->rcv_tos);
+			put_cmsg(&msg, SOL_IP, IP_TOS, sizeof(tos), &tos);
+		}
+		len -= msg.msg_controllen;
+		return copy_to_sockptr(optlen, &len, sizeof(int));
+	}
 	case IP_UNICAST_IF:
 		val = (__force int)htonl((__u32) READ_ONCE(inet->uc_index));
 		goto copyval;
@@ -1678,45 +1715,6 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
 		else
 			err = ip_get_mcast_msfilter(sk, optval, optlen, len);
 		goto out;
-	case IP_PKTOPTIONS:
-	{
-		struct msghdr msg;
-
-		sockopt_release_sock(sk);
-
-		if (sk->sk_type != SOCK_STREAM)
-			return -ENOPROTOOPT;
-
-		if (optval.is_kernel) {
-			msg.msg_control_is_user = false;
-			msg.msg_control = optval.kernel;
-		} else {
-			msg.msg_control_is_user = true;
-			msg.msg_control_user = optval.user;
-		}
-		msg.msg_controllen = len;
-		msg.msg_flags = in_compat_syscall() ? MSG_CMSG_COMPAT : 0;
-
-		if (inet_test_bit(PKTINFO, sk)) {
-			struct in_pktinfo info;
-
-			info.ipi_addr.s_addr = inet->inet_rcv_saddr;
-			info.ipi_spec_dst.s_addr = inet->inet_rcv_saddr;
-			info.ipi_ifindex = inet->mc_index;
-			put_cmsg(&msg, SOL_IP, IP_PKTINFO, sizeof(info), &info);
-		}
-		if (inet_test_bit(TTL, sk)) {
-			int hlim = READ_ONCE(inet->mc_ttl);
-
-			put_cmsg(&msg, SOL_IP, IP_TTL, sizeof(hlim), &hlim);
-		}
-		if (inet_test_bit(TOS, sk)) {
-			int tos = inet->rcv_tos;
-			put_cmsg(&msg, SOL_IP, IP_TOS, sizeof(tos), &tos);
-		}
-		len -= msg.msg_controllen;
-		return copy_to_sockptr(optlen, &len, sizeof(int));
-	}
 	case IP_LOCAL_PORT_RANGE:
 		val = inet->local_port_range.hi << 16 | inet->local_port_range.lo;
 		break;
-- 
2.42.0.459.ge4e396fd5e-goog