Merge branch 'net-convert-af_netlink-and-af_vsock-to-getsockopt_iter-api'

Breno Leitao says:

====================
net: Convert AF_NETLINK and AF_VSOCK to getsockopt_iter API

Continue the work to convert protocols to the new getsockopt_iter API.

Convert AF_NETLINK and AF_VSOCK getsockopt implementations to the new
sockopt_t/getsockopt_iter API, and add kselftests that verify the size
and errno semantics are preserved across the conversion.

I chose these two socket families because they are probably one of the
most used  protocols,, ensuring that any potential bugs will be
discovered and reported quickly.
====================

Link: https://patch.msgid.link/20260501-getsock_one-v1-0-810ce23ea70e@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

4 files changed, 232 insertions, 19 deletions

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 2aeb0680807d..db3be485b480 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -39,6 +39,7 @@
 #include <linux/fs.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
+#include <linux/uio.h>
 #include <linux/skbuff.h>
 #include <linux/netdevice.h>
 #include <linux/rtnetlink.h>
@@ -1716,18 +1717,18 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
 }
 
 static int netlink_getsockopt(struct socket *sock, int level, int optname,
-			      char __user *optval, int __user *optlen)
+			      sockopt_t *opt)
 {
 	struct sock *sk = sock->sk;
 	struct netlink_sock *nlk = nlk_sk(sk);
 	unsigned int flag;
 	int len, val;
+	u32 group;
 
 	if (level != SOL_NETLINK)
 		return -ENOPROTOOPT;
 
-	if (get_user(len, optlen))
-		return -EFAULT;
+	len = opt->optlen;
 	if (len < 0)
 		return -EINVAL;
 
@@ -1751,14 +1752,14 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname,
 
 			idx = pos / sizeof(unsigned long);
 			shift = (pos % sizeof(unsigned long)) * 8;
-			if (put_user((u32)(nlk->groups[idx] >> shift),
-				     (u32 __user *)(optval + pos))) {
+			group = (u32)(nlk->groups[idx] >> shift);
+			if (copy_to_iter(&group, sizeof(u32),
+					 &opt->iter_out) != sizeof(u32)) {
 				err = -EFAULT;
 				break;
 			}
 		}
-		if (put_user(ALIGN(BITS_TO_BYTES(nlk->ngroups), sizeof(u32)), optlen))
-			err = -EFAULT;
+		opt->optlen = ALIGN(BITS_TO_BYTES(nlk->ngroups), sizeof(u32));
 		netlink_unlock_table();
 		return err;
 	}
@@ -1784,8 +1785,8 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname,
 	len = sizeof(int);
 	val = test_bit(flag, &nlk->flags);
 
-	if (put_user(len, optlen) ||
-	    copy_to_user(optval, &val, len))
+	opt->optlen = len;
+	if (copy_to_iter(&val, len, &opt->iter_out) != len)
 		return -EFAULT;
 
 	return 0;
@@ -2813,7 +2814,7 @@ static const struct proto_ops netlink_ops = {
 	.listen =	sock_no_listen,
 	.shutdown =	sock_no_shutdown,
 	.setsockopt =	netlink_setsockopt,
-	.getsockopt =	netlink_getsockopt,
+	.getsockopt_iter = netlink_getsockopt,
 	.sendmsg =	netlink_sendmsg,
 	.recvmsg =	netlink_recvmsg,
 	.mmap =		sock_no_mmap,
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 44037b066a5f..d4a97eeb596e 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -155,6 +155,7 @@
 #include <linux/random.h>
 #include <linux/skbuff.h>
 #include <linux/smp.h>
+#include <linux/uio.h>
 #include <linux/socket.h>
 #include <linux/stddef.h>
 #include <linux/sysctl.h>
@@ -2091,8 +2092,7 @@ exit:
 
 static int vsock_connectible_getsockopt(struct socket *sock,
 					int level, int optname,
-					char __user *optval,
-					int __user *optlen)
+					sockopt_t *opt)
 {
 	struct sock *sk = sock->sk;
 	struct vsock_sock *vsk = vsock_sk(sk);
@@ -2110,8 +2110,7 @@ static int vsock_connectible_getsockopt(struct socket *sock,
 	if (level != AF_VSOCK)
 		return -ENOPROTOOPT;
 
-	if (get_user(len, optlen))
-		return -EFAULT;
+	len = opt->optlen;
 
 	memset(&v, 0, sizeof(v));
 
@@ -2142,11 +2141,10 @@ static int vsock_connectible_getsockopt(struct socket *sock,
 		return -EINVAL;
 	if (len > lv)
 		len = lv;
-	if (copy_to_user(optval, &v, len))
+	if (copy_to_iter(&v, len, &opt->iter_out) != len)
 		return -EFAULT;
 
-	if (put_user(len, optlen))
-		return -EFAULT;
+	opt->optlen = len;
 
 	return 0;
 }
@@ -2631,7 +2629,7 @@ static const struct proto_ops vsock_stream_ops = {
 	.listen = vsock_listen,
 	.shutdown = vsock_shutdown,
 	.setsockopt = vsock_connectible_setsockopt,
-	.getsockopt = vsock_connectible_getsockopt,
+	.getsockopt_iter = vsock_connectible_getsockopt,
 	.sendmsg = vsock_connectible_sendmsg,
 	.recvmsg = vsock_connectible_recvmsg,
 	.mmap = sock_no_mmap,
@@ -2653,7 +2651,7 @@ static const struct proto_ops vsock_seqpacket_ops = {
 	.listen = vsock_listen,
 	.shutdown = vsock_shutdown,
 	.setsockopt = vsock_connectible_setsockopt,
-	.getsockopt = vsock_connectible_getsockopt,
+	.getsockopt_iter = vsock_connectible_getsockopt,
 	.sendmsg = vsock_connectible_sendmsg,
 	.recvmsg = vsock_connectible_recvmsg,
 	.mmap = sock_no_mmap,
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index a275ed584026..baa30287cf22 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -176,6 +176,7 @@ TEST_GEN_PROGS := \
 	bind_timewait \
 	bind_wildcard \
 	epoll_busy_poll \
+	getsockopt_iter \
 	icmp_rfc4884 \
 	ipv6_fragmentation \
 	proc_net_pktgen \
diff --git a/tools/testing/selftests/net/getsockopt_iter.c b/tools/testing/selftests/net/getsockopt_iter.c
new file mode 100644
index 000000000000..179f9e84926f
--- /dev/null
+++ b/tools/testing/selftests/net/getsockopt_iter.c
@@ -0,0 +1,213 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Quick test for getsockopt{_iter} tests.
+ *
+ * Each fixture targets one converted protocol and pins down the
+ * returned-length / errno semantics across buffer-size variations,
+ * an unknown optname and a bogus level.
+ *
+ * - netlink: NETLINK_PKTINFO covers the flag-style int path; the
+ *   NETLINK_LIST_MEMBERSHIPS cases cover the size-discovery path
+ *   that always reports the required buffer length back via optlen,
+ *   even when the user buffer is too small to receive any group bits.
+ * - vsock:   SO_VM_SOCKETS_BUFFER_SIZE covers the u64 path.
+ *
+ * Author: Breno Leitao <leitao@debian.org>
+ */
+
+#include <errno.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <string.h>
+#include <unistd.h>
+#include <linux/netlink.h>
+#include <linux/rtnetlink.h>
+#include <linux/vm_sockets.h>
+#include <sys/socket.h>
+#include "kselftest_harness.h"
+
+#ifndef AF_VSOCK
+#define AF_VSOCK 40
+#endif
+
+/* ---------- netlink ---------- */
+
+FIXTURE(netlink)
+{
+	int fd;
+};
+
+FIXTURE_SETUP(netlink)
+{
+	int group = RTNLGRP_LINK;
+
+	self->fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
+	if (self->fd < 0)
+		SKIP(return, "AF_NETLINK socket: %s", strerror(errno));
+
+	/* Joining a multicast group grows nlk->ngroups so the
+	 * NETLINK_LIST_MEMBERSHIPS path has a non-zero size to report.
+	 */
+	if (setsockopt(self->fd, SOL_NETLINK, NETLINK_ADD_MEMBERSHIP,
+		       &group, sizeof(group)) < 0)
+		SKIP(return, "NETLINK_ADD_MEMBERSHIP: %s", strerror(errno));
+}
+
+FIXTURE_TEARDOWN(netlink)
+{
+	if (self->fd >= 0)
+		close(self->fd);
+}
+
+TEST_F(netlink, pktinfo_exact)
+{
+	int val = -1;
+	socklen_t optlen = sizeof(val);
+
+	ASSERT_EQ(0, getsockopt(self->fd, SOL_NETLINK, NETLINK_PKTINFO,
+				&val, &optlen));
+	ASSERT_EQ(sizeof(int), optlen);
+	ASSERT_TRUE(val == 0 || val == 1);
+}
+
+TEST_F(netlink, pktinfo_oversize_clamped)
+{
+	char buf[16] = {};
+	socklen_t optlen = sizeof(buf);
+
+	ASSERT_EQ(0, getsockopt(self->fd, SOL_NETLINK, NETLINK_PKTINFO,
+				buf, &optlen));
+	ASSERT_EQ(sizeof(int), optlen);
+}
+
+TEST_F(netlink, pktinfo_undersize)
+{
+	char buf[2] = {};
+	socklen_t optlen = sizeof(buf);
+
+	ASSERT_EQ(-1, getsockopt(self->fd, SOL_NETLINK, NETLINK_PKTINFO,
+				 buf, &optlen));
+	ASSERT_EQ(EINVAL, errno);
+}
+
+TEST_F(netlink, list_memberships_size_discovery)
+{
+	socklen_t optlen = 0;
+	char dummy;
+
+	ASSERT_EQ(0, getsockopt(self->fd, SOL_NETLINK,
+				NETLINK_LIST_MEMBERSHIPS,
+				&dummy, &optlen));
+	ASSERT_GT(optlen, 0);
+	ASSERT_EQ(0, optlen % sizeof(__u32));
+}
+
+TEST_F(netlink, list_memberships_full_read)
+{
+	__u32 buf[64] = {};
+	socklen_t optlen = sizeof(buf);
+
+	ASSERT_EQ(0, getsockopt(self->fd, SOL_NETLINK,
+				NETLINK_LIST_MEMBERSHIPS,
+				buf, &optlen));
+	ASSERT_GT(optlen, 0);
+	ASSERT_LE(optlen, sizeof(buf));
+	ASSERT_EQ(0, optlen % sizeof(__u32));
+}
+
+TEST_F(netlink, bad_level)
+{
+	int val;
+	socklen_t optlen = sizeof(val);
+
+	ASSERT_EQ(-1, getsockopt(self->fd, SOL_SOCKET + 1, NETLINK_PKTINFO,
+				 &val, &optlen));
+	ASSERT_EQ(ENOPROTOOPT, errno);
+}
+
+TEST_F(netlink, bad_optname)
+{
+	int val;
+	socklen_t optlen = sizeof(val);
+
+	ASSERT_EQ(-1, getsockopt(self->fd, SOL_NETLINK, 0x7fff,
+				 &val, &optlen));
+	ASSERT_EQ(ENOPROTOOPT, errno);
+}
+
+/* ---------- vsock ---------- */
+
+FIXTURE(vsock)
+{
+	int fd;
+};
+
+FIXTURE_SETUP(vsock)
+{
+	self->fd = socket(AF_VSOCK, SOCK_STREAM, 0);
+	if (self->fd < 0)
+		SKIP(return, "AF_VSOCK socket: %s", strerror(errno));
+}
+
+FIXTURE_TEARDOWN(vsock)
+{
+	if (self->fd >= 0)
+		close(self->fd);
+}
+
+TEST_F(vsock, buffer_size_exact)
+{
+	uint64_t val = 0;
+	socklen_t optlen = sizeof(val);
+
+	ASSERT_EQ(0, getsockopt(self->fd, AF_VSOCK,
+				SO_VM_SOCKETS_BUFFER_SIZE,
+				&val, &optlen));
+	ASSERT_EQ(sizeof(uint64_t), optlen);
+	ASSERT_GT(val, 0);
+}
+
+TEST_F(vsock, buffer_size_oversize_clamped)
+{
+	char buf[16] = {};
+	socklen_t optlen = sizeof(buf);
+
+	ASSERT_EQ(0, getsockopt(self->fd, AF_VSOCK,
+				SO_VM_SOCKETS_BUFFER_SIZE,
+				buf, &optlen));
+	ASSERT_EQ(sizeof(uint64_t), optlen);
+}
+
+TEST_F(vsock, buffer_size_undersize)
+{
+	char buf[4] = {};
+	socklen_t optlen = sizeof(buf);
+
+	ASSERT_EQ(-1, getsockopt(self->fd, AF_VSOCK,
+				 SO_VM_SOCKETS_BUFFER_SIZE,
+				 buf, &optlen));
+	ASSERT_EQ(EINVAL, errno);
+}
+
+TEST_F(vsock, bad_level)
+{
+	uint64_t val;
+	socklen_t optlen = sizeof(val);
+
+	ASSERT_EQ(-1, getsockopt(self->fd, SOL_SOCKET + 1,
+				 SO_VM_SOCKETS_BUFFER_SIZE,
+				 &val, &optlen));
+	ASSERT_EQ(ENOPROTOOPT, errno);
+}
+
+TEST_F(vsock, bad_optname)
+{
+	uint64_t val;
+	socklen_t optlen = sizeof(val);
+
+	ASSERT_EQ(-1, getsockopt(self->fd, AF_VSOCK, 0x7fff,
+				 &val, &optlen));
+	ASSERT_EQ(ENOPROTOOPT, errno);
+}
+
+TEST_HARNESS_MAIN