Resguardo inicial

linux-7.2.3/tools/testing/selftests/net/af_unix/.gitignore

@@ -0,0 +1,9 @@
+diag_uid
+msg_oob
+scm_inq
+scm_pidfd
+scm_rights
+so_peek_off
+unix_connect
+unix_connreset
+unix_listen

linux-7.2.3/tools/testing/selftests/net/af_unix/Makefile

@@ -0,0 +1,20 @@
+top_srcdir := ../../../../..
+include $(top_srcdir)/scripts/Makefile.compiler
+
+cc-option = $(call __cc-option, $(CC),,$(1),$(2))
+
+CFLAGS += $(KHDR_INCLUDES) -Wall $(call cc-option,-Wflex-array-member-not-at-end)
+
+TEST_GEN_PROGS := \
+	diag_uid \
+	msg_oob \
+	scm_inq \
+	scm_pidfd \
+	scm_rights \
+	so_peek_off \
+	unix_connect \
+	unix_connreset \
+	unix_listen \
+# end of TEST_GEN_PROGS
+
+include ../../lib.mk

linux-7.2.3/tools/testing/selftests/net/af_unix/config

@@ -0,0 +1,4 @@
+CONFIG_AF_UNIX_OOB=y
+CONFIG_UNIX=y
+CONFIG_UNIX_DIAG=m
+CONFIG_USER_NS=y

linux-7.2.3/tools/testing/selftests/net/af_unix/diag_uid.c

@@ -0,0 +1,177 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright Amazon.com Inc. or its affiliates. */
+
+#define _GNU_SOURCE
+#include <sched.h>
+
+#include <unistd.h>
+#include <linux/netlink.h>
+#include <linux/rtnetlink.h>
+#include <linux/sock_diag.h>
+#include <linux/unix_diag.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <sys/un.h>
+
+#include "kselftest_harness.h"
+
+FIXTURE(diag_uid)
+{
+	int netlink_fd;
+	int unix_fd;
+	__u32 inode;
+	__u64 cookie;
+};
+
+FIXTURE_VARIANT(diag_uid)
+{
+	int unshare;
+	int udiag_show;
+};
+
+FIXTURE_VARIANT_ADD(diag_uid, uid)
+{
+	.unshare = 0,
+	.udiag_show = UDIAG_SHOW_UID
+};
+
+FIXTURE_VARIANT_ADD(diag_uid, uid_unshare)
+{
+	.unshare = CLONE_NEWUSER,
+	.udiag_show = UDIAG_SHOW_UID
+};
+
+FIXTURE_SETUP(diag_uid)
+{
+	struct stat file_stat;
+	socklen_t optlen;
+	int ret;
+
+	if (variant->unshare)
+		ASSERT_EQ(unshare(variant->unshare), 0);
+
+	self->netlink_fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_SOCK_DIAG);
+	ASSERT_NE(self->netlink_fd, -1);
+
+	self->unix_fd = socket(AF_UNIX, SOCK_STREAM, 0);
+	ASSERT_NE(self->unix_fd, -1);
+
+	ret = fstat(self->unix_fd, &file_stat);
+	ASSERT_EQ(ret, 0);
+
+	self->inode = file_stat.st_ino;
+
+	optlen = sizeof(self->cookie);
+	ret = getsockopt(self->unix_fd, SOL_SOCKET, SO_COOKIE, &self->cookie, &optlen);
+	ASSERT_EQ(ret, 0);
+}
+
+FIXTURE_TEARDOWN(diag_uid)
+{
+	close(self->netlink_fd);
+	close(self->unix_fd);
+}
+
+int send_request(struct __test_metadata *_metadata,
+		 FIXTURE_DATA(diag_uid) *self,
+		 const FIXTURE_VARIANT(diag_uid) *variant)
+{
+	struct {
+		struct nlmsghdr nlh;
+		struct unix_diag_req udr;
+	} req = {
+		.nlh = {
+			.nlmsg_len = sizeof(req),
+			.nlmsg_type = SOCK_DIAG_BY_FAMILY,
+			.nlmsg_flags = NLM_F_REQUEST
+		},
+		.udr = {
+			.sdiag_family = AF_UNIX,
+			.udiag_ino = self->inode,
+			.udiag_cookie = {
+				(__u32)self->cookie,
+				(__u32)(self->cookie >> 32)
+			},
+			.udiag_show = variant->udiag_show
+		}
+	};
+	struct sockaddr_nl nladdr = {
+		.nl_family = AF_NETLINK
+	};
+	struct iovec iov = {
+		.iov_base = &req,
+		.iov_len = sizeof(req)
+	};
+	struct msghdr msg = {
+		.msg_name = &nladdr,
+		.msg_namelen = sizeof(nladdr),
+		.msg_iov = &iov,
+		.msg_iovlen = 1
+	};
+
+	return sendmsg(self->netlink_fd, &msg, 0);
+}
+
+void render_response(struct __test_metadata *_metadata,
+		     struct unix_diag_req *udr, __u32 len)
+{
+	unsigned int rta_len = len - NLMSG_LENGTH(sizeof(*udr));
+	struct rtattr *attr;
+	uid_t uid;
+
+	ASSERT_GT(len, sizeof(*udr));
+	ASSERT_EQ(udr->sdiag_family, AF_UNIX);
+
+	attr = (struct rtattr *)(udr + 1);
+	ASSERT_NE(RTA_OK(attr, rta_len), 0);
+	ASSERT_EQ(attr->rta_type, UNIX_DIAG_UID);
+
+	uid = *(uid_t *)RTA_DATA(attr);
+	ASSERT_EQ(uid, getuid());
+}
+
+void receive_response(struct __test_metadata *_metadata,
+		      FIXTURE_DATA(diag_uid) *self)
+{
+	long buf[8192 / sizeof(long)];
+	struct sockaddr_nl nladdr = {
+		.nl_family = AF_NETLINK
+	};
+	struct iovec iov = {
+		.iov_base = buf,
+		.iov_len = sizeof(buf)
+	};
+	struct msghdr msg = {
+		.msg_name = &nladdr,
+		.msg_namelen = sizeof(nladdr),
+		.msg_iov = &iov,
+		.msg_iovlen = 1
+	};
+	struct nlmsghdr *nlh;
+	int ret;
+
+	ret = recvmsg(self->netlink_fd, &msg, 0);
+	ASSERT_GT(ret, 0);
+
+	nlh = (struct nlmsghdr *)buf;
+	ASSERT_NE(NLMSG_OK(nlh, ret), 0);
+	ASSERT_EQ(nlh->nlmsg_type, SOCK_DIAG_BY_FAMILY);
+
+	render_response(_metadata, NLMSG_DATA(nlh), nlh->nlmsg_len);
+
+	nlh = NLMSG_NEXT(nlh, ret);
+	ASSERT_EQ(NLMSG_OK(nlh, ret), 0);
+}
+
+TEST_F(diag_uid, 1)
+{
+	int ret;
+
+	ret = send_request(_metadata, self, variant);
+	ASSERT_GT(ret, 0);
+
+	receive_response(_metadata, self);
+}
+
+TEST_HARNESS_MAIN

linux-7.2.3/tools/testing/selftests/net/af_unix/msg_oob.c

@@ -0,0 +1,891 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright Amazon.com Inc. or its affiliates. */
+
+#include <fcntl.h>
+#include <string.h>
+#include <unistd.h>
+
+#include <netinet/in.h>
+#include <sys/epoll.h>
+#include <sys/ioctl.h>
+#include <sys/signalfd.h>
+#include <sys/socket.h>
+
+#include "kselftest_harness.h"
+
+#define BUF_SZ	32
+
+FIXTURE(msg_oob)
+{
+	int fd[4];		/* 0: AF_UNIX sender
+				 * 1: AF_UNIX receiver
+				 * 2: TCP sender
+				 * 3: TCP receiver
+				 */
+	int signal_fd;
+	int epoll_fd[2];	/* 0: AF_UNIX receiver
+				 * 1: TCP receiver
+				 */
+	bool tcp_compliant;
+};
+
+FIXTURE_VARIANT(msg_oob)
+{
+	bool peek;
+};
+
+FIXTURE_VARIANT_ADD(msg_oob, no_peek)
+{
+	.peek = false,
+};
+
+FIXTURE_VARIANT_ADD(msg_oob, peek)
+{
+	.peek = true
+};
+
+static void create_unix_socketpair(struct __test_metadata *_metadata,
+				   FIXTURE_DATA(msg_oob) *self)
+{
+	int ret;
+
+	ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_NONBLOCK, 0, self->fd);
+	ASSERT_EQ(ret, 0);
+}
+
+static void create_tcp_socketpair(struct __test_metadata *_metadata,
+				  FIXTURE_DATA(msg_oob) *self)
+{
+	struct sockaddr_in addr;
+	socklen_t addrlen;
+	int listen_fd;
+	int ret;
+
+	listen_fd = socket(AF_INET, SOCK_STREAM, 0);
+	ASSERT_GE(listen_fd, 0);
+
+	ret = listen(listen_fd, -1);
+	ASSERT_EQ(ret, 0);
+
+	addrlen = sizeof(addr);
+	ret = getsockname(listen_fd, (struct sockaddr *)&addr, &addrlen);
+	ASSERT_EQ(ret, 0);
+
+	self->fd[2] = socket(AF_INET, SOCK_STREAM, 0);
+	ASSERT_GE(self->fd[2], 0);
+
+	ret = connect(self->fd[2], (struct sockaddr *)&addr, addrlen);
+	ASSERT_EQ(ret, 0);
+
+	self->fd[3] = accept(listen_fd, (struct sockaddr *)&addr, &addrlen);
+	ASSERT_GE(self->fd[3], 0);
+
+	ret = fcntl(self->fd[3], F_SETFL, O_NONBLOCK);
+	ASSERT_EQ(ret, 0);
+}
+
+static void setup_sigurg(struct __test_metadata *_metadata,
+			 FIXTURE_DATA(msg_oob) *self)
+{
+	struct signalfd_siginfo siginfo;
+	int pid = getpid();
+	sigset_t mask;
+	int i, ret;
+
+	for (i = 0; i < 2; i++) {
+		ret = ioctl(self->fd[i * 2 + 1], FIOSETOWN, &pid);
+		ASSERT_EQ(ret, 0);
+	}
+
+	ret = sigemptyset(&mask);
+	ASSERT_EQ(ret, 0);
+
+	ret = sigaddset(&mask, SIGURG);
+	ASSERT_EQ(ret, 0);
+
+	ret = sigprocmask(SIG_BLOCK, &mask, NULL);
+	ASSERT_EQ(ret, 0);
+
+	self->signal_fd = signalfd(-1, &mask, SFD_NONBLOCK);
+	ASSERT_GE(self->signal_fd, 0);
+
+	ret = read(self->signal_fd, &siginfo, sizeof(siginfo));
+	ASSERT_EQ(ret, -1);
+}
+
+static void setup_epollpri(struct __test_metadata *_metadata,
+			   FIXTURE_DATA(msg_oob) *self)
+{
+	struct epoll_event event = {
+		.events = EPOLLPRI,
+	};
+	int i;
+
+	for (i = 0; i < 2; i++) {
+		int ret;
+
+		self->epoll_fd[i] = epoll_create1(0);
+		ASSERT_GE(self->epoll_fd[i], 0);
+
+		ret = epoll_ctl(self->epoll_fd[i], EPOLL_CTL_ADD, self->fd[i * 2 + 1], &event);
+		ASSERT_EQ(ret, 0);
+	}
+}
+
+static void close_sockets(FIXTURE_DATA(msg_oob) *self)
+{
+	int i;
+
+	for (i = 0; i < 4; i++)
+		close(self->fd[i]);
+}
+
+FIXTURE_SETUP(msg_oob)
+{
+	create_unix_socketpair(_metadata, self);
+	create_tcp_socketpair(_metadata, self);
+
+	setup_sigurg(_metadata, self);
+	setup_epollpri(_metadata, self);
+
+	self->tcp_compliant = true;
+}
+
+FIXTURE_TEARDOWN(msg_oob)
+{
+	close_sockets(self);
+}
+
+static void __epollpair(struct __test_metadata *_metadata,
+			FIXTURE_DATA(msg_oob) *self,
+			bool oob_remaining)
+{
+	struct epoll_event event[2] = {};
+	int i, ret[2];
+
+	for (i = 0; i < 2; i++)
+		ret[i] = epoll_wait(self->epoll_fd[i], &event[i], 1, 0);
+
+	ASSERT_EQ(ret[0], oob_remaining);
+
+	if (self->tcp_compliant)
+		ASSERT_EQ(ret[0], ret[1]);
+
+	if (oob_remaining) {
+		ASSERT_EQ(event[0].events, EPOLLPRI);
+
+		if (self->tcp_compliant)
+			ASSERT_EQ(event[0].events, event[1].events);
+	}
+}
+
+static void __sendpair(struct __test_metadata *_metadata,
+		       FIXTURE_DATA(msg_oob) *self,
+		       const void *buf, size_t len, int flags)
+{
+	int i, ret[2];
+
+	for (i = 0; i < 2; i++) {
+		struct signalfd_siginfo siginfo = {};
+		int bytes;
+
+		ret[i] = send(self->fd[i * 2], buf, len, flags);
+
+		bytes = read(self->signal_fd, &siginfo, sizeof(siginfo));
+
+		if (flags & MSG_OOB) {
+			ASSERT_EQ(bytes, sizeof(siginfo));
+			ASSERT_EQ(siginfo.ssi_signo, SIGURG);
+
+			bytes = read(self->signal_fd, &siginfo, sizeof(siginfo));
+		}
+
+		ASSERT_EQ(bytes, -1);
+	}
+
+	ASSERT_EQ(ret[0], len);
+	ASSERT_EQ(ret[0], ret[1]);
+}
+
+static void __recvpair(struct __test_metadata *_metadata,
+		       FIXTURE_DATA(msg_oob) *self,
+		       const char *expected_buf, int expected_len,
+		       int buf_len, int flags, bool is_sender)
+{
+	int i, ret[2], recv_errno[2], expected_errno = 0;
+	char recv_buf[2][BUF_SZ] = {};
+	bool printed = false;
+
+	ASSERT_GE(BUF_SZ, buf_len);
+
+	errno = 0;
+
+	for (i = 0; i < 2; i++) {
+		int index = is_sender ? i * 2 : i * 2 + 1;
+
+		ret[i] = recv(self->fd[index], recv_buf[i], buf_len, flags);
+		recv_errno[i] = errno;
+	}
+
+	if (expected_len < 0) {
+		expected_errno = -expected_len;
+		expected_len = -1;
+	}
+
+	if (ret[0] != expected_len || recv_errno[0] != expected_errno) {
+		TH_LOG("AF_UNIX :%s", ret[0] < 0 ? strerror(recv_errno[0]) : recv_buf[0]);
+		TH_LOG("Expected:%s", expected_errno ? strerror(expected_errno) : expected_buf);
+
+		ASSERT_EQ(ret[0], expected_len);
+		ASSERT_EQ(recv_errno[0], expected_errno);
+	}
+
+	if (ret[0] != ret[1] || recv_errno[0] != recv_errno[1]) {
+		TH_LOG("AF_UNIX :%s", ret[0] < 0 ? strerror(recv_errno[0]) : recv_buf[0]);
+		TH_LOG("TCP     :%s", ret[1] < 0 ? strerror(recv_errno[1]) : recv_buf[1]);
+
+		printed = true;
+
+		if (self->tcp_compliant) {
+			ASSERT_EQ(ret[0], ret[1]);
+			ASSERT_EQ(recv_errno[0], recv_errno[1]);
+		}
+	}
+
+	if (expected_len >= 0) {
+		int cmp;
+
+		cmp = strncmp(expected_buf, recv_buf[0], expected_len);
+		if (cmp) {
+			TH_LOG("AF_UNIX :%s", ret[0] < 0 ? strerror(recv_errno[0]) : recv_buf[0]);
+			TH_LOG("Expected:%s", expected_errno ? strerror(expected_errno) : expected_buf);
+
+			ASSERT_EQ(cmp, 0);
+		}
+
+		cmp = strncmp(recv_buf[0], recv_buf[1], expected_len);
+		if (cmp) {
+			if (!printed) {
+				TH_LOG("AF_UNIX :%s", ret[0] < 0 ? strerror(recv_errno[0]) : recv_buf[0]);
+				TH_LOG("TCP     :%s", ret[1] < 0 ? strerror(recv_errno[1]) : recv_buf[1]);
+			}
+
+			if (self->tcp_compliant)
+				ASSERT_EQ(cmp, 0);
+		}
+	}
+}
+
+static void __setinlinepair(struct __test_metadata *_metadata,
+			    FIXTURE_DATA(msg_oob) *self)
+{
+	int i, oob_inline = 1;
+
+	for (i = 0; i < 2; i++) {
+		int ret;
+
+		ret = setsockopt(self->fd[i * 2 + 1], SOL_SOCKET, SO_OOBINLINE,
+				 &oob_inline, sizeof(oob_inline));
+		ASSERT_EQ(ret, 0);
+	}
+}
+
+static void __siocatmarkpair(struct __test_metadata *_metadata,
+			     FIXTURE_DATA(msg_oob) *self,
+			     bool oob_head)
+{
+	int answ[2] = {};
+	int i;
+
+	for (i = 0; i < 2; i++) {
+		int ret;
+
+		ret = ioctl(self->fd[i * 2 + 1], SIOCATMARK, &answ[i]);
+		ASSERT_EQ(ret, 0);
+	}
+
+	ASSERT_EQ(answ[0], oob_head);
+
+	if (self->tcp_compliant)
+		ASSERT_EQ(answ[0], answ[1]);
+}
+
+static void __resetpair(struct __test_metadata *_metadata,
+			FIXTURE_DATA(msg_oob) *self,
+			const FIXTURE_VARIANT(msg_oob) *variant,
+			bool reset)
+{
+	int i;
+
+	for (i = 0; i < 2; i++)
+		close(self->fd[i * 2 + 1]);
+
+	__recvpair(_metadata, self, "", reset ? -ECONNRESET : 0, 1,
+		   variant->peek ? MSG_PEEK : 0, true);
+}
+
+#define sendpair(buf, len, flags)					\
+	__sendpair(_metadata, self, buf, len, flags)
+
+#define recvpair(expected_buf, expected_len, buf_len, flags)		\
+	do {								\
+		if (variant->peek)					\
+			__recvpair(_metadata, self,			\
+				   expected_buf, expected_len,		\
+				   buf_len, (flags) | MSG_PEEK, false);	\
+		__recvpair(_metadata, self,				\
+			   expected_buf, expected_len,			\
+			   buf_len, flags, false);			\
+	} while (0)
+
+#define epollpair(oob_remaining)					\
+	__epollpair(_metadata, self, oob_remaining)
+
+#define siocatmarkpair(oob_head)					\
+	__siocatmarkpair(_metadata, self, oob_head)
+
+#define setinlinepair()							\
+	__setinlinepair(_metadata, self)
+
+#define resetpair(reset)						\
+	__resetpair(_metadata, self, variant, reset)
+
+#define tcp_incompliant							\
+	for (self->tcp_compliant = false;				\
+	     self->tcp_compliant == false;				\
+	     self->tcp_compliant = true)
+
+TEST_F(msg_oob, non_oob)
+{
+	sendpair("x", 1, 0);
+	epollpair(false);
+	siocatmarkpair(false);
+
+	recvpair("", -EINVAL, 1, MSG_OOB);
+	epollpair(false);
+	siocatmarkpair(false);
+
+	resetpair(true);
+}
+
+TEST_F(msg_oob, non_oob_no_reset)
+{
+	sendpair("x", 1, 0);
+	epollpair(false);
+	siocatmarkpair(false);
+
+	recvpair("x", 1, 1, 0);
+	epollpair(false);
+	siocatmarkpair(false);
+
+	resetpair(false);
+}
+
+TEST_F(msg_oob, oob)
+{
+	sendpair("x", 1, MSG_OOB);
+	epollpair(true);
+	siocatmarkpair(true);
+
+	recvpair("x", 1, 1, MSG_OOB);
+	epollpair(false);
+	siocatmarkpair(true);
+
+	tcp_incompliant {
+		resetpair(false);		/* TCP sets -ECONNRESET for ex-OOB. */
+	}
+}
+
+TEST_F(msg_oob, oob_reset)
+{
+	sendpair("x", 1, MSG_OOB);
+	epollpair(true);
+	siocatmarkpair(true);
+
+	resetpair(true);
+}
+
+TEST_F(msg_oob, oob_drop)
+{
+	sendpair("x", 1, MSG_OOB);
+	epollpair(true);
+	siocatmarkpair(true);
+
+	recvpair("", -EAGAIN, 1, 0);		/* Drop OOB. */
+	epollpair(false);
+	siocatmarkpair(false);
+
+	recvpair("", -EINVAL, 1, MSG_OOB);
+	epollpair(false);
+	siocatmarkpair(false);
+
+	resetpair(false);
+}
+
+TEST_F(msg_oob, oob_ahead)
+{
+	sendpair("hello", 5, MSG_OOB);
+	epollpair(true);
+	siocatmarkpair(false);
+
+	recvpair("o", 1, 1, MSG_OOB);
+	epollpair(false);
+	siocatmarkpair(false);
+
+	recvpair("hell", 4, 4, 0);
+	epollpair(false);
+	siocatmarkpair(true);
+
+	tcp_incompliant {
+		resetpair(false);		/* TCP sets -ECONNRESET for ex-OOB. */
+	}
+}
+
+TEST_F(msg_oob, oob_break)
+{
+	sendpair("hello", 5, MSG_OOB);
+	epollpair(true);
+	siocatmarkpair(false);
+
+	recvpair("hell", 4, 5, 0);		/* Break at OOB even with enough buffer. */
+	epollpair(true);
+	siocatmarkpair(true);
+
+	recvpair("o", 1, 1, MSG_OOB);
+	epollpair(false);
+	siocatmarkpair(true);
+
+	recvpair("", -EAGAIN, 1, 0);
+	siocatmarkpair(false);
+
+	resetpair(false);
+}
+
+TEST_F(msg_oob, oob_ahead_break)
+{
+	sendpair("hello", 5, MSG_OOB);
+	epollpair(true);
+	siocatmarkpair(false);
+
+	sendpair("world", 5, 0);
+	epollpair(true);
+	siocatmarkpair(false);
+
+	recvpair("o", 1, 1, MSG_OOB);
+	epollpair(false);
+	siocatmarkpair(false);
+
+	recvpair("hell", 4, 9, 0);		/* Break at OOB even after it's recv()ed. */
+	epollpair(false);
+	siocatmarkpair(true);
+
+	recvpair("world", 5, 5, 0);
+	epollpair(false);
+	siocatmarkpair(false);
+
+	resetpair(false);
+}
+
+TEST_F(msg_oob, oob_break_drop)
+{
+	sendpair("hello", 5, MSG_OOB);
+	epollpair(true);
+	siocatmarkpair(false);
+
+	sendpair("world", 5, 0);
+	epollpair(true);
+	siocatmarkpair(false);
+
+	recvpair("hell", 4, 10, 0);		/* Break at OOB even with enough buffer. */
+	epollpair(true);
+	siocatmarkpair(true);
+
+	recvpair("world", 5, 10, 0);		/* Drop OOB and recv() the next skb. */
+	epollpair(false);
+	siocatmarkpair(false);
+
+	recvpair("", -EINVAL, 1, MSG_OOB);
+	epollpair(false);
+	siocatmarkpair(false);
+
+	resetpair(false);
+}
+
+TEST_F(msg_oob, ex_oob_break)
+{
+	sendpair("hello", 5, MSG_OOB);
+	epollpair(true);
+	siocatmarkpair(false);
+
+	sendpair("wor", 3, MSG_OOB);
+	epollpair(true);
+	siocatmarkpair(false);
+
+	sendpair("ld", 2, 0);
+	epollpair(true);
+	siocatmarkpair(false);
+
+	recvpair("hellowo", 7, 10, 0);		/* Break at OOB but not at ex-OOB. */
+	epollpair(true);
+	siocatmarkpair(true);
+
+	recvpair("r", 1, 1, MSG_OOB);
+	epollpair(false);
+	siocatmarkpair(true);
+
+	recvpair("ld", 2, 2, 0);
+	epollpair(false);
+	siocatmarkpair(false);
+
+	resetpair(false);
+}
+
+TEST_F(msg_oob, ex_oob_drop)
+{
+	sendpair("x", 1, MSG_OOB);
+	epollpair(true);
+	siocatmarkpair(true);
+
+	sendpair("y", 1, MSG_OOB);		/* TCP drops "x" at this moment. */
+	epollpair(true);
+
+	tcp_incompliant {
+		siocatmarkpair(false);
+
+		recvpair("x", 1, 1, 0);		/* TCP drops "y" by passing through it. */
+		epollpair(true);
+		siocatmarkpair(true);
+
+		recvpair("y", 1, 1, MSG_OOB);	/* TCP returns -EINVAL. */
+		epollpair(false);
+		siocatmarkpair(true);
+	}
+
+	resetpair(false);
+}
+
+TEST_F(msg_oob, ex_oob_drop_2)
+{
+	sendpair("x", 1, MSG_OOB);
+	epollpair(true);
+	siocatmarkpair(true);
+
+	sendpair("y", 1, MSG_OOB);		/* TCP drops "x" at this moment. */
+	epollpair(true);
+
+	tcp_incompliant {
+		siocatmarkpair(false);
+	}
+
+	recvpair("y", 1, 1, MSG_OOB);
+	epollpair(false);
+
+	tcp_incompliant {
+		siocatmarkpair(false);
+
+		recvpair("x", 1, 1, 0);		/* TCP returns -EAGAIN. */
+		epollpair(false);
+		siocatmarkpair(true);
+	}
+
+	resetpair(false);
+}
+
+TEST_F(msg_oob, ex_oob_oob)
+{
+	sendpair("x", 1, MSG_OOB);
+	epollpair(true);
+	siocatmarkpair(true);
+
+	recvpair("x", 1, 1, MSG_OOB);
+	epollpair(false);
+	siocatmarkpair(true);
+
+	sendpair("y", 1, MSG_OOB);
+	epollpair(true);
+	siocatmarkpair(true);
+
+	recvpair("", -EAGAIN, 1, 0);
+	epollpair(false);
+	siocatmarkpair(false);
+
+	recvpair("", -EINVAL, 1, MSG_OOB);
+	epollpair(false);
+	siocatmarkpair(false);
+
+	resetpair(false);
+}
+
+TEST_F(msg_oob, ex_oob_ex_oob)
+{
+	sendpair("x", 1, MSG_OOB);
+	epollpair(true);
+	siocatmarkpair(true);
+
+	recvpair("x", 1, 1, MSG_OOB);
+	epollpair(false);
+	siocatmarkpair(true);
+
+	sendpair("y", 1, MSG_OOB);
+	epollpair(true);
+	siocatmarkpair(true);
+
+	recvpair("y", 1, 1, MSG_OOB);
+	epollpair(false);
+	siocatmarkpair(true);
+
+	tcp_incompliant {
+		resetpair(false);		/* TCP sets -ECONNRESET for ex-OOB. */
+	}
+}
+
+TEST_F(msg_oob, ex_oob_ex_oob_oob)
+{
+	sendpair("x", 1, MSG_OOB);
+	epollpair(true);
+	siocatmarkpair(true);
+
+	recvpair("x", 1, 1, MSG_OOB);
+	epollpair(false);
+	siocatmarkpair(true);
+
+	sendpair("y", 1, MSG_OOB);
+	epollpair(true);
+	siocatmarkpair(true);
+
+	recvpair("y", 1, 1, MSG_OOB);
+	epollpair(false);
+	siocatmarkpair(true);
+
+	sendpair("z", 1, MSG_OOB);
+	epollpair(true);
+	siocatmarkpair(true);
+}
+
+TEST_F(msg_oob, ex_oob_ahead_break)
+{
+	sendpair("hello", 5, MSG_OOB);
+	epollpair(true);
+	siocatmarkpair(false);
+
+	sendpair("wor", 3, MSG_OOB);
+	epollpair(true);
+	siocatmarkpair(false);
+
+	recvpair("r", 1, 1, MSG_OOB);
+	epollpair(false);
+	siocatmarkpair(false);
+
+	sendpair("ld", 2, MSG_OOB);
+	epollpair(true);
+	siocatmarkpair(false);
+
+	tcp_incompliant {
+		recvpair("hellowol", 8, 10, 0);	/* TCP recv()s "helloworl", why "r" ?? */
+	}
+
+	epollpair(true);
+	siocatmarkpair(true);
+
+	recvpair("d", 1, 1, MSG_OOB);
+	epollpair(false);
+	siocatmarkpair(true);
+
+	tcp_incompliant {
+		resetpair(false);		/* TCP sets -ECONNRESET for ex-OOB. */
+	}
+}
+
+TEST_F(msg_oob, ex_oob_siocatmark)
+{
+	sendpair("hello", 5, MSG_OOB);
+	epollpair(true);
+	siocatmarkpair(false);
+
+	recvpair("o", 1, 1, MSG_OOB);
+	epollpair(false);
+	siocatmarkpair(false);
+
+	sendpair("world", 5, MSG_OOB);
+	epollpair(true);
+	siocatmarkpair(false);
+
+	recvpair("hell", 4, 4, 0);		/* Intentionally stop at ex-OOB. */
+	epollpair(true);
+	siocatmarkpair(false);
+
+	resetpair(true);
+}
+
+TEST_F(msg_oob, inline_oob)
+{
+	setinlinepair();
+
+	sendpair("x", 1, MSG_OOB);
+	epollpair(true);
+	siocatmarkpair(true);
+
+	recvpair("", -EINVAL, 1, MSG_OOB);
+	epollpair(true);
+	siocatmarkpair(true);
+
+	recvpair("x", 1, 1, 0);
+	epollpair(false);
+	siocatmarkpair(false);
+
+	resetpair(false);
+}
+
+TEST_F(msg_oob, inline_oob_break)
+{
+	setinlinepair();
+
+	sendpair("hello", 5, MSG_OOB);
+	epollpair(true);
+	siocatmarkpair(false);
+
+	recvpair("", -EINVAL, 1, MSG_OOB);
+	epollpair(true);
+	siocatmarkpair(false);
+
+	recvpair("hell", 4, 5, 0);		/* Break at OOB but not at ex-OOB. */
+	epollpair(true);
+	siocatmarkpair(true);
+
+	recvpair("o", 1, 1, 0);
+	epollpair(false);
+	siocatmarkpair(false);
+
+	resetpair(false);
+}
+
+TEST_F(msg_oob, inline_oob_ahead_break)
+{
+	sendpair("hello", 5, MSG_OOB);
+	epollpair(true);
+	siocatmarkpair(false);
+
+	sendpair("world", 5, 0);
+	epollpair(true);
+	siocatmarkpair(false);
+
+	recvpair("o", 1, 1, MSG_OOB);
+	epollpair(false);
+	siocatmarkpair(false);
+
+	setinlinepair();
+
+	recvpair("hell", 4, 9, 0);		/* Break at OOB even with enough buffer. */
+	epollpair(false);
+	siocatmarkpair(true);
+
+	tcp_incompliant {
+		recvpair("world", 5, 6, 0);	/* TCP recv()s "oworld", ... "o" ??? */
+	}
+
+	epollpair(false);
+	siocatmarkpair(false);
+
+	resetpair(false);
+}
+
+TEST_F(msg_oob, inline_ex_oob_break)
+{
+	sendpair("hello", 5, MSG_OOB);
+	epollpair(true);
+	siocatmarkpair(false);
+
+	sendpair("wor", 3, MSG_OOB);
+	epollpair(true);
+	siocatmarkpair(false);
+
+	sendpair("ld", 2, 0);
+	epollpair(true);
+	siocatmarkpair(false);
+
+	setinlinepair();
+
+	recvpair("hellowo", 7, 10, 0);		/* Break at OOB but not at ex-OOB. */
+	epollpair(true);
+	siocatmarkpair(true);
+
+	recvpair("rld", 3, 3, 0);
+	epollpair(false);
+	siocatmarkpair(false);
+
+	resetpair(false);
+}
+
+TEST_F(msg_oob, inline_ex_oob_no_drop)
+{
+	sendpair("x", 1, MSG_OOB);
+	epollpair(true);
+	siocatmarkpair(true);
+
+	setinlinepair();
+
+	sendpair("y", 1, MSG_OOB);		/* TCP does NOT drops "x" at this moment. */
+	epollpair(true);
+	siocatmarkpair(false);
+
+	recvpair("x", 1, 1, 0);
+	epollpair(true);
+	siocatmarkpair(true);
+
+	recvpair("y", 1, 1, 0);
+	epollpair(false);
+	siocatmarkpair(false);
+
+	resetpair(false);
+}
+
+TEST_F(msg_oob, inline_ex_oob_drop)
+{
+	sendpair("x", 1, MSG_OOB);
+	epollpair(true);
+	siocatmarkpair(true);
+
+	sendpair("y", 1, MSG_OOB);		/* TCP drops "x" at this moment. */
+	epollpair(true);
+
+	setinlinepair();
+
+	tcp_incompliant {
+		siocatmarkpair(false);
+
+		recvpair("x", 1, 1, 0);		/* TCP recv()s "y". */
+		epollpair(true);
+		siocatmarkpair(true);
+
+		recvpair("y", 1, 1, 0);		/* TCP returns -EAGAIN. */
+		epollpair(false);
+		siocatmarkpair(false);
+	}
+
+	resetpair(false);
+}
+
+TEST_F(msg_oob, inline_ex_oob_siocatmark)
+{
+	sendpair("hello", 5, MSG_OOB);
+	epollpair(true);
+	siocatmarkpair(false);
+
+	recvpair("o", 1, 1, MSG_OOB);
+	epollpair(false);
+	siocatmarkpair(false);
+
+	setinlinepair();
+
+	sendpair("world", 5, MSG_OOB);
+	epollpair(true);
+	siocatmarkpair(false);
+
+	recvpair("hell", 4, 4, 0);		/* Intentionally stop at ex-OOB. */
+	epollpair(true);
+	siocatmarkpair(false);
+
+	resetpair(true);
+}
+
+TEST_HARNESS_MAIN

linux-7.2.3/tools/testing/selftests/net/af_unix/scm_inq.c

@@ -0,0 +1,173 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright 2025 Google LLC */
+
+#include <linux/sockios.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <sys/types.h>
+
+#include "kselftest_harness.h"
+
+#define NR_CHUNKS		100
+#define MSG_LEN			256
+#define NR_PARTIAL_READS	3
+
+FIXTURE(scm_inq)
+{
+	int fd[2];
+};
+
+FIXTURE_VARIANT(scm_inq)
+{
+	int type;
+};
+
+FIXTURE_VARIANT_ADD(scm_inq, stream)
+{
+	.type = SOCK_STREAM,
+};
+
+FIXTURE_VARIANT_ADD(scm_inq, dgram)
+{
+	.type = SOCK_DGRAM,
+};
+
+FIXTURE_VARIANT_ADD(scm_inq, seqpacket)
+{
+	.type = SOCK_SEQPACKET,
+};
+
+FIXTURE_SETUP(scm_inq)
+{
+	int err;
+
+	err = socketpair(AF_UNIX, variant->type | SOCK_NONBLOCK, 0, self->fd);
+	ASSERT_EQ(0, err);
+}
+
+FIXTURE_TEARDOWN(scm_inq)
+{
+	close(self->fd[0]);
+	close(self->fd[1]);
+}
+
+static void send_chunks(struct __test_metadata *_metadata,
+			FIXTURE_DATA(scm_inq) *self)
+{
+	char buf[MSG_LEN] = {};
+	int i, ret;
+
+	for (i = 0; i < NR_CHUNKS; i++) {
+		ret = send(self->fd[0], buf, sizeof(buf), 0);
+		ASSERT_EQ(sizeof(buf), ret);
+	}
+}
+
+static void recv_chunks(struct __test_metadata *_metadata,
+			FIXTURE_DATA(scm_inq) *self)
+{
+	char cmsg_buf[CMSG_SPACE(sizeof(int))];
+	struct msghdr msg = {};
+	struct iovec iov = {};
+	struct cmsghdr *cmsg;
+	char buf[MSG_LEN];
+	int i, ret;
+	int inq;
+
+	msg.msg_iov = &iov;
+	msg.msg_iovlen = 1;
+	msg.msg_control = cmsg_buf;
+	msg.msg_controllen = sizeof(cmsg_buf);
+
+	iov.iov_base = buf;
+	iov.iov_len = sizeof(buf);
+
+	for (i = 0; i < NR_CHUNKS; i++) {
+		memset(buf, 0, sizeof(buf));
+		memset(cmsg_buf, 0, sizeof(cmsg_buf));
+
+		ret = recvmsg(self->fd[1], &msg, 0);
+		ASSERT_EQ(MSG_LEN, ret);
+
+		cmsg = CMSG_FIRSTHDR(&msg);
+		ASSERT_NE(NULL, cmsg);
+		ASSERT_EQ(CMSG_LEN(sizeof(int)), cmsg->cmsg_len);
+		ASSERT_EQ(SOL_SOCKET, cmsg->cmsg_level);
+		ASSERT_EQ(SCM_INQ, cmsg->cmsg_type);
+
+		ret = ioctl(self->fd[1], SIOCINQ, &inq);
+		ASSERT_EQ(0, ret);
+		ASSERT_EQ(*(int *)CMSG_DATA(cmsg), inq);
+	}
+}
+
+TEST_F(scm_inq, basic)
+{
+	int err, inq;
+
+	err = setsockopt(self->fd[1], SOL_SOCKET, SO_INQ, &(int){1}, sizeof(int));
+	if (variant->type != SOCK_STREAM) {
+		ASSERT_EQ(-ENOPROTOOPT, -errno);
+		return;
+	}
+
+	ASSERT_EQ(0, err);
+
+	err = ioctl(self->fd[1], SIOCINQ, &inq);
+	ASSERT_EQ(0, err);
+	ASSERT_EQ(0, inq);
+
+	send_chunks(_metadata, self);
+	recv_chunks(_metadata, self);
+}
+
+TEST_F(scm_inq, partial_read)
+{
+	char buf[MSG_LEN * NR_PARTIAL_READS] = {};
+	char cmsg_buf[CMSG_SPACE(sizeof(int))];
+	struct msghdr msg = {};
+	struct iovec iov = {};
+	struct cmsghdr *cmsg;
+	int err, inq, ret, i;
+	int remain;
+
+	err = setsockopt(self->fd[1], SOL_SOCKET, SO_INQ, &(int){1}, sizeof(int));
+	if (variant->type != SOCK_STREAM) {
+		ASSERT_EQ(-ENOPROTOOPT, -errno);
+		return;
+	}
+	ASSERT_EQ(0, err);
+
+	ret = send(self->fd[0], buf, sizeof(buf), 0);
+	ASSERT_EQ(sizeof(buf), ret);
+
+	msg.msg_iov = &iov;
+	msg.msg_iovlen = 1;
+	msg.msg_control = cmsg_buf;
+	msg.msg_controllen = sizeof(cmsg_buf);
+
+	iov.iov_base = buf;
+	iov.iov_len = MSG_LEN;
+
+	for (i = 0; i < NR_PARTIAL_READS; i++) {
+		remain = MSG_LEN * (NR_PARTIAL_READS - 1 - i);
+
+		memset(buf, 0, MSG_LEN);
+		memset(cmsg_buf, 0, sizeof(cmsg_buf));
+		ret = recvmsg(self->fd[1], &msg, 0);
+		ASSERT_EQ(MSG_LEN, ret);
+
+		cmsg = CMSG_FIRSTHDR(&msg);
+		ASSERT_NE(NULL, cmsg);
+		ASSERT_EQ(CMSG_LEN(sizeof(int)), cmsg->cmsg_len);
+		ASSERT_EQ(SOL_SOCKET, cmsg->cmsg_level);
+		ASSERT_EQ(SCM_INQ, cmsg->cmsg_type);
+		ASSERT_EQ(remain, *(int *)CMSG_DATA(cmsg));
+
+		ret = ioctl(self->fd[1], SIOCINQ, &inq);
+		ASSERT_EQ(0, ret);
+		ASSERT_EQ(remain, inq);
+	}
+}
+
+TEST_HARNESS_MAIN

linux-7.2.3/tools/testing/selftests/net/af_unix/scm_pidfd.c

@@ -0,0 +1,556 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+#define _GNU_SOURCE
+#include <error.h>
+#include <limits.h>
+#include <stddef.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/socket.h>
+#include <linux/socket.h>
+#include <unistd.h>
+#include <string.h>
+#include <errno.h>
+#include <sys/un.h>
+#include <sys/signal.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+
+#include "../../pidfd/pidfd.h"
+#include "kselftest_harness.h"
+
+#define clean_errno() (errno == 0 ? "None" : strerror(errno))
+#define log_err(MSG, ...)                                                   \
+	fprintf(stderr, "(%s:%d: errno: %s) " MSG "\n", __FILE__, __LINE__, \
+		clean_errno(), ##__VA_ARGS__)
+
+#ifndef SCM_PIDFD
+#define SCM_PIDFD 0x04
+#endif
+
+#define CHILD_EXIT_CODE_OK 123
+
+static void child_die()
+{
+	exit(1);
+}
+
+static int safe_int(const char *numstr, int *converted)
+{
+	char *err = NULL;
+	long sli;
+
+	errno = 0;
+	sli = strtol(numstr, &err, 0);
+	if (errno == ERANGE && (sli == LONG_MAX || sli == LONG_MIN))
+		return -ERANGE;
+
+	if (errno != 0 && sli == 0)
+		return -EINVAL;
+
+	if (err == numstr || *err != '\0')
+		return -EINVAL;
+
+	if (sli > INT_MAX || sli < INT_MIN)
+		return -ERANGE;
+
+	*converted = (int)sli;
+	return 0;
+}
+
+static int char_left_gc(const char *buffer, size_t len)
+{
+	size_t i;
+
+	for (i = 0; i < len; i++) {
+		if (buffer[i] == ' ' || buffer[i] == '\t')
+			continue;
+
+		return i;
+	}
+
+	return 0;
+}
+
+static int char_right_gc(const char *buffer, size_t len)
+{
+	int i;
+
+	for (i = len - 1; i >= 0; i--) {
+		if (buffer[i] == ' ' || buffer[i] == '\t' ||
+		    buffer[i] == '\n' || buffer[i] == '\0')
+			continue;
+
+		return i + 1;
+	}
+
+	return 0;
+}
+
+static char *trim_whitespace_in_place(char *buffer)
+{
+	buffer += char_left_gc(buffer, strlen(buffer));
+	buffer[char_right_gc(buffer, strlen(buffer))] = '\0';
+	return buffer;
+}
+
+/* borrowed (with all helpers) from pidfd/pidfd_open_test.c */
+static pid_t get_pid_from_fdinfo_file(int pidfd, const char *key, size_t keylen)
+{
+	int ret;
+	char path[512];
+	FILE *f;
+	size_t n = 0;
+	pid_t result = -1;
+	char *line = NULL;
+
+	snprintf(path, sizeof(path), "/proc/self/fdinfo/%d", pidfd);
+
+	f = fopen(path, "re");
+	if (!f)
+		return -1;
+
+	while (getline(&line, &n, f) != -1) {
+		char *numstr;
+
+		if (strncmp(line, key, keylen))
+			continue;
+
+		numstr = trim_whitespace_in_place(line + 4);
+		ret = safe_int(numstr, &result);
+		if (ret < 0)
+			goto out;
+
+		break;
+	}
+
+out:
+	free(line);
+	fclose(f);
+	return result;
+}
+
+struct cmsg_data {
+	struct ucred *ucred;
+	int *pidfd;
+};
+
+static int parse_cmsg(struct msghdr *msg, struct cmsg_data *res)
+{
+	struct cmsghdr *cmsg;
+
+	if (msg->msg_flags & (MSG_TRUNC | MSG_CTRUNC)) {
+		log_err("recvmsg: truncated");
+		return 1;
+	}
+
+	for (cmsg = CMSG_FIRSTHDR(msg); cmsg != NULL;
+	     cmsg = CMSG_NXTHDR(msg, cmsg)) {
+		if (cmsg->cmsg_level == SOL_SOCKET &&
+		    cmsg->cmsg_type == SCM_PIDFD) {
+			if (cmsg->cmsg_len < sizeof(*res->pidfd)) {
+				log_err("CMSG parse: SCM_PIDFD wrong len");
+				return 1;
+			}
+
+			res->pidfd = (void *)CMSG_DATA(cmsg);
+		}
+
+		if (cmsg->cmsg_level == SOL_SOCKET &&
+		    cmsg->cmsg_type == SCM_CREDENTIALS) {
+			if (cmsg->cmsg_len < sizeof(*res->ucred)) {
+				log_err("CMSG parse: SCM_CREDENTIALS wrong len");
+				return 1;
+			}
+
+			res->ucred = (void *)CMSG_DATA(cmsg);
+		}
+	}
+
+	if (!res->pidfd) {
+		log_err("CMSG parse: SCM_PIDFD not found");
+		return 1;
+	}
+
+	if (!res->ucred) {
+		log_err("CMSG parse: SCM_CREDENTIALS not found");
+		return 1;
+	}
+
+	return 0;
+}
+
+static int cmsg_check(int fd)
+{
+	struct msghdr msg = { 0 };
+	struct cmsg_data res;
+	struct iovec iov;
+	int data = 0;
+	char control[CMSG_SPACE(sizeof(struct ucred)) +
+		     CMSG_SPACE(sizeof(int))] = { 0 };
+	pid_t parent_pid;
+	int err;
+
+	iov.iov_base = &data;
+	iov.iov_len = sizeof(data);
+
+	msg.msg_iov = &iov;
+	msg.msg_iovlen = 1;
+	msg.msg_control = control;
+	msg.msg_controllen = sizeof(control);
+
+	err = recvmsg(fd, &msg, 0);
+	if (err < 0) {
+		log_err("recvmsg");
+		return 1;
+	}
+
+	if (msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC)) {
+		log_err("recvmsg: truncated");
+		return 1;
+	}
+
+	/* send(pfd, "x", sizeof(char), 0) */
+	if (data != 'x') {
+		log_err("recvmsg: data corruption");
+		return 1;
+	}
+
+	if (parse_cmsg(&msg, &res)) {
+		log_err("CMSG parse: parse_cmsg() failed");
+		return 1;
+	}
+
+	/* pidfd from SCM_PIDFD should point to the parent process PID */
+	parent_pid =
+		get_pid_from_fdinfo_file(*res.pidfd, "Pid:", sizeof("Pid:") - 1);
+	if (parent_pid != getppid()) {
+		log_err("wrong SCM_PIDFD %d != %d", parent_pid, getppid());
+		close(*res.pidfd);
+		return 1;
+	}
+
+	close(*res.pidfd);
+	return 0;
+}
+
+static int cmsg_check_dead(int fd, int expected_pid)
+{
+	int err;
+	struct msghdr msg = { 0 };
+	struct cmsg_data res;
+	struct iovec iov;
+	int data = 0;
+	char control[CMSG_SPACE(sizeof(struct ucred)) +
+		     CMSG_SPACE(sizeof(int))] = { 0 };
+	struct pidfd_info info = {
+		.mask = PIDFD_INFO_EXIT,
+	};
+
+	iov.iov_base = &data;
+	iov.iov_len = sizeof(data);
+
+	msg.msg_iov = &iov;
+	msg.msg_iovlen = 1;
+	msg.msg_control = control;
+	msg.msg_controllen = sizeof(control);
+
+	err = recvmsg(fd, &msg, 0);
+	if (err < 0) {
+		log_err("recvmsg");
+		return 1;
+	}
+
+	if (msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC)) {
+		log_err("recvmsg: truncated");
+		return 1;
+	}
+
+	/* send(cfd, "y", sizeof(char), 0) */
+	if (data != 'y') {
+		log_err("recvmsg: data corruption");
+		return 1;
+	}
+
+	if (parse_cmsg(&msg, &res)) {
+		log_err("CMSG parse: parse_cmsg() failed");
+		return 1;
+	}
+
+	/*
+	 * pidfd from SCM_PIDFD should point to the client_pid.
+	 * Let's read exit information and check if it's what
+	 * we expect to see.
+	 */
+	if (ioctl(*res.pidfd, PIDFD_GET_INFO, &info)) {
+		log_err("%s: ioctl(PIDFD_GET_INFO) failed", __func__);
+		close(*res.pidfd);
+		return 1;
+	}
+
+	if (!(info.mask & PIDFD_INFO_EXIT)) {
+		log_err("%s: No exit information from ioctl(PIDFD_GET_INFO)", __func__);
+		close(*res.pidfd);
+		return 1;
+	}
+
+	err = WIFEXITED(info.exit_code) ? WEXITSTATUS(info.exit_code) : 1;
+	if (err != CHILD_EXIT_CODE_OK) {
+		log_err("%s: wrong exit_code %d != %d", __func__, err, CHILD_EXIT_CODE_OK);
+		close(*res.pidfd);
+		return 1;
+	}
+
+	close(*res.pidfd);
+	return 0;
+}
+
+struct sock_addr {
+	char sock_name[32];
+	struct sockaddr_un listen_addr;
+	socklen_t addrlen;
+};
+
+FIXTURE(scm_pidfd)
+{
+	int server;
+	pid_t client_pid;
+	int startup_pipe[2];
+	struct sock_addr server_addr;
+	struct sock_addr *client_addr;
+};
+
+FIXTURE_VARIANT(scm_pidfd)
+{
+	int type;
+	bool abstract;
+};
+
+FIXTURE_VARIANT_ADD(scm_pidfd, stream_pathname)
+{
+	.type = SOCK_STREAM,
+	.abstract = 0,
+};
+
+FIXTURE_VARIANT_ADD(scm_pidfd, stream_abstract)
+{
+	.type = SOCK_STREAM,
+	.abstract = 1,
+};
+
+FIXTURE_VARIANT_ADD(scm_pidfd, dgram_pathname)
+{
+	.type = SOCK_DGRAM,
+	.abstract = 0,
+};
+
+FIXTURE_VARIANT_ADD(scm_pidfd, dgram_abstract)
+{
+	.type = SOCK_DGRAM,
+	.abstract = 1,
+};
+
+FIXTURE_SETUP(scm_pidfd)
+{
+	self->client_addr = mmap(NULL, sizeof(*self->client_addr), PROT_READ | PROT_WRITE,
+				 MAP_SHARED | MAP_ANONYMOUS, -1, 0);
+	ASSERT_NE(MAP_FAILED, self->client_addr);
+}
+
+FIXTURE_TEARDOWN(scm_pidfd)
+{
+	close(self->server);
+
+	kill(self->client_pid, SIGKILL);
+	waitpid(self->client_pid, NULL, 0);
+
+	if (!variant->abstract) {
+		unlink(self->server_addr.sock_name);
+		unlink(self->client_addr->sock_name);
+	}
+}
+
+static void fill_sockaddr(struct sock_addr *addr, bool abstract)
+{
+	char *sun_path_buf = (char *)&addr->listen_addr.sun_path;
+
+	addr->listen_addr.sun_family = AF_UNIX;
+	addr->addrlen = offsetof(struct sockaddr_un, sun_path);
+	snprintf(addr->sock_name, sizeof(addr->sock_name), "scm_pidfd_%d", getpid());
+	addr->addrlen += strlen(addr->sock_name);
+	if (abstract) {
+		*sun_path_buf = '\0';
+		addr->addrlen++;
+		sun_path_buf++;
+	} else {
+		unlink(addr->sock_name);
+	}
+	memcpy(sun_path_buf, addr->sock_name, strlen(addr->sock_name));
+}
+
+static int sk_enable_cred_pass(int sk)
+{
+	int on = 0;
+
+	on = 1;
+	if (setsockopt(sk, SOL_SOCKET, SO_PASSCRED, &on, sizeof(on))) {
+		log_err("Failed to set SO_PASSCRED");
+		return 1;
+	}
+
+	if (setsockopt(sk, SOL_SOCKET, SO_PASSPIDFD, &on, sizeof(on))) {
+		log_err("Failed to set SO_PASSPIDFD");
+		return 1;
+	}
+
+	return 0;
+}
+
+static void client(FIXTURE_DATA(scm_pidfd) *self,
+		   const FIXTURE_VARIANT(scm_pidfd) *variant)
+{
+	int cfd;
+	socklen_t len;
+	struct ucred peer_cred;
+	int peer_pidfd;
+	pid_t peer_pid;
+
+	cfd = socket(AF_UNIX, variant->type, 0);
+	if (cfd < 0) {
+		log_err("socket");
+		child_die();
+	}
+
+	if (variant->type == SOCK_DGRAM) {
+		fill_sockaddr(self->client_addr, variant->abstract);
+
+		if (bind(cfd, (struct sockaddr *)&self->client_addr->listen_addr, self->client_addr->addrlen)) {
+			log_err("bind");
+			child_die();
+		}
+	}
+
+	if (connect(cfd, (struct sockaddr *)&self->server_addr.listen_addr,
+		    self->server_addr.addrlen) != 0) {
+		log_err("connect");
+		child_die();
+	}
+
+	if (sk_enable_cred_pass(cfd)) {
+		log_err("sk_enable_cred_pass() failed");
+		child_die();
+	}
+
+	close(self->startup_pipe[1]);
+
+	if (cmsg_check(cfd)) {
+		log_err("cmsg_check failed");
+		child_die();
+	}
+
+	/* send something to the parent so it can receive SCM_PIDFD too and validate it */
+	if (send(cfd, "y", sizeof(char), 0) == -1) {
+		log_err("Failed to send(cfd, \"y\", sizeof(char), 0)");
+		child_die();
+	}
+
+	/* skip further for SOCK_DGRAM as it's not applicable */
+	if (variant->type == SOCK_DGRAM)
+		return;
+
+	len = sizeof(peer_cred);
+	if (getsockopt(cfd, SOL_SOCKET, SO_PEERCRED, &peer_cred, &len)) {
+		log_err("Failed to get SO_PEERCRED");
+		child_die();
+	}
+
+	len = sizeof(peer_pidfd);
+	if (getsockopt(cfd, SOL_SOCKET, SO_PEERPIDFD, &peer_pidfd, &len)) {
+		log_err("Failed to get SO_PEERPIDFD");
+		child_die();
+	}
+
+	/* pid from SO_PEERCRED should point to the parent process PID */
+	if (peer_cred.pid != getppid()) {
+		log_err("peer_cred.pid != getppid(): %d != %d", peer_cred.pid, getppid());
+		child_die();
+	}
+
+	peer_pid = get_pid_from_fdinfo_file(peer_pidfd,
+					    "Pid:", sizeof("Pid:") - 1);
+	if (peer_pid != peer_cred.pid) {
+		log_err("peer_pid != peer_cred.pid: %d != %d", peer_pid, peer_cred.pid);
+		child_die();
+	}
+}
+
+TEST_F(scm_pidfd, test)
+{
+	int err;
+	int pfd;
+	int child_status = 0;
+
+	self->server = socket(AF_UNIX, variant->type, 0);
+	ASSERT_NE(-1, self->server);
+
+	fill_sockaddr(&self->server_addr, variant->abstract);
+
+	err = bind(self->server, (struct sockaddr *)&self->server_addr.listen_addr, self->server_addr.addrlen);
+	ASSERT_EQ(0, err);
+
+	if (variant->type == SOCK_STREAM) {
+		err = listen(self->server, 1);
+		ASSERT_EQ(0, err);
+	}
+
+	err = pipe(self->startup_pipe);
+	ASSERT_NE(-1, err);
+
+	self->client_pid = fork();
+	ASSERT_NE(-1, self->client_pid);
+	if (self->client_pid == 0) {
+		close(self->server);
+		close(self->startup_pipe[0]);
+		client(self, variant);
+
+		/*
+		 * It's a bit unusual, but in case of success we return non-zero
+		 * exit code (CHILD_EXIT_CODE_OK) and then we expect to read it
+		 * from ioctl(PIDFD_GET_INFO) in cmsg_check_dead().
+		 */
+		exit(CHILD_EXIT_CODE_OK);
+	}
+	close(self->startup_pipe[1]);
+
+	if (variant->type == SOCK_STREAM) {
+		pfd = accept(self->server, NULL, NULL);
+		ASSERT_NE(-1, pfd);
+	} else {
+		pfd = self->server;
+	}
+
+	/* wait until the child arrives at checkpoint */
+	read(self->startup_pipe[0], &err, sizeof(int));
+	close(self->startup_pipe[0]);
+
+	if (variant->type == SOCK_DGRAM) {
+		err = sendto(pfd, "x", sizeof(char), 0, (struct sockaddr *)&self->client_addr->listen_addr, self->client_addr->addrlen);
+		ASSERT_NE(-1, err);
+	} else {
+		err = send(pfd, "x", sizeof(char), 0);
+		ASSERT_NE(-1, err);
+	}
+
+	waitpid(self->client_pid, &child_status, 0);
+	/* see comment before exit(CHILD_EXIT_CODE_OK) */
+	ASSERT_EQ(CHILD_EXIT_CODE_OK, WIFEXITED(child_status) ? WEXITSTATUS(child_status) : 1);
+
+	err = sk_enable_cred_pass(pfd);
+	ASSERT_EQ(0, err);
+
+	err = cmsg_check_dead(pfd, self->client_pid);
+	ASSERT_EQ(0, err);
+
+	close(pfd);
+}
+
+TEST_HARNESS_MAIN

linux-7.2.3/tools/testing/selftests/net/af_unix/scm_rights.c

@@ -0,0 +1,381 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright Amazon.com Inc. or its affiliates. */
+#define _GNU_SOURCE
+#include <sched.h>
+
+#include <stdio.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <sys/un.h>
+
+#include "kselftest_harness.h"
+
+FIXTURE(scm_rights)
+{
+	int fd[32];
+};
+
+FIXTURE_VARIANT(scm_rights)
+{
+	char name[32];
+	int type;
+	int flags;
+	bool test_listener;
+	bool disabled;
+};
+
+FIXTURE_VARIANT_ADD(scm_rights, dgram)
+{
+	.name = "UNIX ",
+	.type = SOCK_DGRAM,
+	.flags = 0,
+	.test_listener = false,
+	.disabled = false,
+};
+
+FIXTURE_VARIANT_ADD(scm_rights, dgram_disabled)
+{
+	.name = "UNIX ",
+	.type = SOCK_DGRAM,
+	.flags = 0,
+	.test_listener = false,
+	.disabled = true,
+};
+
+FIXTURE_VARIANT_ADD(scm_rights, stream)
+{
+	.name = "UNIX-STREAM ",
+	.type = SOCK_STREAM,
+	.flags = 0,
+	.test_listener = false,
+	.disabled = false,
+};
+
+FIXTURE_VARIANT_ADD(scm_rights, stream_disabled)
+{
+	.name = "UNIX-STREAM ",
+	.type = SOCK_STREAM,
+	.flags = 0,
+	.test_listener = false,
+	.disabled = true,
+};
+
+FIXTURE_VARIANT_ADD(scm_rights, stream_oob)
+{
+	.name = "UNIX-STREAM ",
+	.type = SOCK_STREAM,
+	.flags = MSG_OOB,
+	.test_listener = false,
+	.disabled = false,
+};
+
+FIXTURE_VARIANT_ADD(scm_rights, stream_oob_disabled)
+{
+	.name = "UNIX-STREAM ",
+	.type = SOCK_STREAM,
+	.flags = MSG_OOB,
+	.test_listener = false,
+	.disabled = true,
+};
+
+FIXTURE_VARIANT_ADD(scm_rights, stream_listener)
+{
+	.name = "UNIX-STREAM ",
+	.type = SOCK_STREAM,
+	.flags = 0,
+	.test_listener = true,
+	.disabled = false,
+};
+
+FIXTURE_VARIANT_ADD(scm_rights, stream_listener_disabled)
+{
+	.name = "UNIX-STREAM ",
+	.type = SOCK_STREAM,
+	.flags = 0,
+	.test_listener = true,
+	.disabled = true,
+};
+
+FIXTURE_VARIANT_ADD(scm_rights, stream_listener_oob)
+{
+	.name = "UNIX-STREAM ",
+	.type = SOCK_STREAM,
+	.flags = MSG_OOB,
+	.test_listener = true,
+	.disabled = false,
+};
+
+FIXTURE_VARIANT_ADD(scm_rights, stream_listener_oob_disabled)
+{
+	.name = "UNIX-STREAM ",
+	.type = SOCK_STREAM,
+	.flags = MSG_OOB,
+	.test_listener = true,
+	.disabled = true,
+};
+
+static int count_sockets(struct __test_metadata *_metadata,
+			 const FIXTURE_VARIANT(scm_rights) *variant)
+{
+	int sockets = -1, len, ret;
+	char *line = NULL;
+	size_t unused;
+	FILE *f;
+
+	f = fopen("/proc/net/protocols", "r");
+	ASSERT_NE(NULL, f);
+
+	len = strlen(variant->name);
+
+	while (getline(&line, &unused, f) != -1) {
+		int unused2;
+
+		if (strncmp(line, variant->name, len))
+			continue;
+
+		ret = sscanf(line + len, "%d %d", &unused2, &sockets);
+		ASSERT_EQ(2, ret);
+
+		break;
+	}
+
+	free(line);
+
+	ret = fclose(f);
+	ASSERT_EQ(0, ret);
+
+	return sockets;
+}
+
+FIXTURE_SETUP(scm_rights)
+{
+	int ret;
+
+	ret = unshare(CLONE_NEWNET);
+	ASSERT_EQ(0, ret);
+
+	if (variant->disabled)
+		return;
+
+	ret = count_sockets(_metadata, variant);
+	ASSERT_EQ(0, ret);
+}
+
+FIXTURE_TEARDOWN(scm_rights)
+{
+	int ret;
+
+	if (variant->disabled)
+		return;
+
+	sleep(1);
+
+	ret = count_sockets(_metadata, variant);
+	ASSERT_EQ(0, ret);
+}
+
+static void create_listeners(struct __test_metadata *_metadata,
+			     FIXTURE_DATA(scm_rights) *self,
+			     const FIXTURE_VARIANT(scm_rights) *variant,
+			     int n)
+{
+	struct sockaddr_un addr = {
+		.sun_family = AF_UNIX,
+	};
+	socklen_t addrlen;
+	int i, ret;
+
+	for (i = 0; i < n * 2; i += 2) {
+		self->fd[i] = socket(AF_UNIX, SOCK_STREAM, 0);
+		ASSERT_LE(0, self->fd[i]);
+
+		addrlen = sizeof(addr.sun_family);
+		ret = bind(self->fd[i], (struct sockaddr *)&addr, addrlen);
+		ASSERT_EQ(0, ret);
+
+		ret = listen(self->fd[i], -1);
+		ASSERT_EQ(0, ret);
+
+		if (variant->disabled) {
+			ret = setsockopt(self->fd[i], SOL_SOCKET, SO_PASSRIGHTS,
+					 &(int){0}, sizeof(int));
+			ASSERT_EQ(0, ret);
+		}
+
+		addrlen = sizeof(addr);
+		ret = getsockname(self->fd[i], (struct sockaddr *)&addr, &addrlen);
+		ASSERT_EQ(0, ret);
+
+		self->fd[i + 1] = socket(AF_UNIX, SOCK_STREAM, 0);
+		ASSERT_LE(0, self->fd[i + 1]);
+
+		ret = connect(self->fd[i + 1], (struct sockaddr *)&addr, addrlen);
+		ASSERT_EQ(0, ret);
+	}
+}
+
+static void create_socketpairs(struct __test_metadata *_metadata,
+			       FIXTURE_DATA(scm_rights) *self,
+			       const FIXTURE_VARIANT(scm_rights) *variant,
+			       int n)
+{
+	int i, ret;
+
+	ASSERT_GE(sizeof(self->fd) / sizeof(int), n);
+
+	for (i = 0; i < n * 2; i += 2) {
+		ret = socketpair(AF_UNIX, variant->type, 0, self->fd + i);
+		ASSERT_EQ(0, ret);
+
+		if (variant->disabled) {
+			ret = setsockopt(self->fd[i], SOL_SOCKET, SO_PASSRIGHTS,
+					 &(int){0}, sizeof(int));
+			ASSERT_EQ(0, ret);
+		}
+	}
+}
+
+static void __create_sockets(struct __test_metadata *_metadata,
+			     FIXTURE_DATA(scm_rights) *self,
+			     const FIXTURE_VARIANT(scm_rights) *variant,
+			     int n)
+{
+	ASSERT_LE(n * 2, sizeof(self->fd) / sizeof(self->fd[0]));
+
+	if (variant->test_listener)
+		create_listeners(_metadata, self, variant, n);
+	else
+		create_socketpairs(_metadata, self, variant, n);
+}
+
+static void __close_sockets(struct __test_metadata *_metadata,
+			    FIXTURE_DATA(scm_rights) *self,
+			    int n)
+{
+	int i, ret;
+
+	ASSERT_GE(sizeof(self->fd) / sizeof(int), n);
+
+	for (i = 0; i < n * 2; i++) {
+		ret = close(self->fd[i]);
+		ASSERT_EQ(0, ret);
+	}
+}
+
+void __send_fd(struct __test_metadata *_metadata,
+	       const FIXTURE_DATA(scm_rights) *self,
+	       const FIXTURE_VARIANT(scm_rights) *variant,
+	       int inflight, int receiver)
+{
+#define MSG "x"
+#define MSGLEN 1
+	int fds[2] = {
+		self->fd[inflight * 2],
+		self->fd[inflight * 2],
+	};
+	char cmsg_buf[CMSG_SPACE(sizeof(fds))];
+	struct iovec iov = {
+		.iov_base = MSG,
+		.iov_len = MSGLEN,
+	};
+	struct msghdr msg = {
+		.msg_name = NULL,
+		.msg_namelen = 0,
+		.msg_iov = &iov,
+		.msg_iovlen = 1,
+		.msg_control = cmsg_buf,
+		.msg_controllen = sizeof(cmsg_buf),
+	};
+	struct cmsghdr *cmsg;
+	int ret;
+
+	cmsg = CMSG_FIRSTHDR(&msg);
+	cmsg->cmsg_level = SOL_SOCKET;
+	cmsg->cmsg_type = SCM_RIGHTS;
+	cmsg->cmsg_len = CMSG_LEN(sizeof(fds));
+	memcpy(CMSG_DATA(cmsg), fds, sizeof(fds));
+
+	ret = sendmsg(self->fd[receiver * 2 + 1], &msg, variant->flags);
+
+	if (variant->disabled) {
+		ASSERT_EQ(-1, ret);
+		ASSERT_EQ(-EPERM, -errno);
+	} else {
+		ASSERT_EQ(MSGLEN, ret);
+	}
+}
+
+#define create_sockets(n)					\
+	__create_sockets(_metadata, self, variant, n)
+#define close_sockets(n)					\
+	__close_sockets(_metadata, self, n)
+#define send_fd(inflight, receiver)				\
+	__send_fd(_metadata, self, variant, inflight, receiver)
+
+TEST_F(scm_rights, self_ref)
+{
+	create_sockets(2);
+
+	send_fd(0, 0);
+
+	send_fd(1, 1);
+
+	close_sockets(2);
+}
+
+TEST_F(scm_rights, triangle)
+{
+	create_sockets(6);
+
+	send_fd(0, 1);
+	send_fd(1, 2);
+	send_fd(2, 0);
+
+	send_fd(3, 4);
+	send_fd(4, 5);
+	send_fd(5, 3);
+
+	close_sockets(6);
+}
+
+TEST_F(scm_rights, cross_edge)
+{
+	create_sockets(8);
+
+	send_fd(0, 1);
+	send_fd(1, 2);
+	send_fd(2, 0);
+	send_fd(1, 3);
+	send_fd(3, 2);
+
+	send_fd(4, 5);
+	send_fd(5, 6);
+	send_fd(6, 4);
+	send_fd(5, 7);
+	send_fd(7, 6);
+
+	close_sockets(8);
+}
+
+TEST_F(scm_rights, backtrack_from_scc)
+{
+	create_sockets(10);
+
+	send_fd(0, 1);
+	send_fd(0, 4);
+	send_fd(1, 2);
+	send_fd(2, 3);
+	send_fd(3, 1);
+
+	send_fd(5, 6);
+	send_fd(5, 9);
+	send_fd(6, 7);
+	send_fd(7, 8);
+	send_fd(8, 6);
+
+	close_sockets(10);
+}
+
+TEST_HARNESS_MAIN

linux-7.2.3/tools/testing/selftests/net/af_unix/so_peek_off.c

@@ -0,0 +1,208 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright 2025 Google LLC */
+
+#include <stdlib.h>
+#include <unistd.h>
+
+#include <sys/socket.h>
+
+#include "../../kselftest_harness.h"
+
+FIXTURE(so_peek_off)
+{
+	int fd[2];	/* 0: sender, 1: receiver */
+};
+
+FIXTURE_VARIANT(so_peek_off)
+{
+	int type;
+};
+
+FIXTURE_VARIANT_ADD(so_peek_off, stream)
+{
+	.type = SOCK_STREAM,
+};
+
+FIXTURE_VARIANT_ADD(so_peek_off, dgram)
+{
+	.type = SOCK_DGRAM,
+};
+
+FIXTURE_VARIANT_ADD(so_peek_off, seqpacket)
+{
+	.type = SOCK_SEQPACKET,
+};
+
+FIXTURE_SETUP(so_peek_off)
+{
+	struct timeval timeout = {
+		.tv_sec = 5,
+		.tv_usec = 0,
+	};
+	int ret;
+
+	ret = socketpair(AF_UNIX, variant->type, 0, self->fd);
+	ASSERT_EQ(0, ret);
+
+	ret = setsockopt(self->fd[1], SOL_SOCKET, SO_RCVTIMEO_NEW,
+			 &timeout, sizeof(timeout));
+	ASSERT_EQ(0, ret);
+
+	ret = setsockopt(self->fd[1], SOL_SOCKET, SO_PEEK_OFF,
+			 &(int){0}, sizeof(int));
+	ASSERT_EQ(0, ret);
+}
+
+FIXTURE_TEARDOWN(so_peek_off)
+{
+	close_range(self->fd[0], self->fd[1], 0);
+}
+
+#define sendeq(fd, str, flags)					\
+	do {							\
+		int bytes, len = strlen(str);			\
+								\
+		bytes = send(fd, str, len, flags);		\
+		ASSERT_EQ(len, bytes);				\
+	} while (0)
+
+#define recveq(fd, str, buflen, flags)				\
+	do {							\
+		char buf[(buflen) + 1] = {};			\
+		int bytes;					\
+								\
+		bytes = recv(fd, buf, buflen, flags);		\
+		ASSERT_NE(-1, bytes);				\
+		ASSERT_STREQ(str, buf);				\
+	} while (0)
+
+#define peekoffeq(fd, expected)					\
+	do {							\
+		socklen_t optlen = sizeof(int);			\
+		int off = -1;					\
+		int ret;					\
+								\
+		ret = getsockopt(fd, SOL_SOCKET, SO_PEEK_OFF,	\
+				 &off, &optlen);		\
+		ASSERT_EQ(0, ret);				\
+		ASSERT_EQ((socklen_t)sizeof(off), optlen);	\
+		ASSERT_EQ(expected, off);			\
+	} while (0)
+
+#define async							\
+	for (pid_t pid = (pid = fork(),				\
+			  pid < 0 ?				\
+			  __TH_LOG("Failed to start async {}"),	\
+			  _metadata->exit_code = KSFT_FAIL,	\
+			  __bail(1, _metadata),			\
+			  0xdead :				\
+			  pid);					\
+	     !pid; exit(0))
+
+TEST_F(so_peek_off, single_chunk)
+{
+	sendeq(self->fd[0], "aaaabbbb", 0);
+
+	recveq(self->fd[1], "aaaa", 4, MSG_PEEK);
+	peekoffeq(self->fd[1], 4);
+	recveq(self->fd[1], "bbbb", 100, MSG_PEEK);
+	peekoffeq(self->fd[1], 8);
+
+	recveq(self->fd[1], "aaaabbbb", 8, 0);
+	peekoffeq(self->fd[1], 0);
+}
+
+TEST_F(so_peek_off, two_chunks)
+{
+	sendeq(self->fd[0], "aaaa", 0);
+	sendeq(self->fd[0], "bbbb", 0);
+
+	recveq(self->fd[1], "aaaa", 4, MSG_PEEK);
+	peekoffeq(self->fd[1], 4);
+	recveq(self->fd[1], "bbbb", 100, MSG_PEEK);
+	peekoffeq(self->fd[1], 8);
+
+	recveq(self->fd[1], "aaaa", 4, 0);
+	recveq(self->fd[1], "bbbb", 4, 0);
+	peekoffeq(self->fd[1], 0);
+}
+
+TEST_F(so_peek_off, two_chunks_blocking)
+{
+	async {
+		usleep(1000);
+		sendeq(self->fd[0], "aaaa", 0);
+	}
+
+	recveq(self->fd[1], "aaaa", 4, MSG_PEEK);
+	peekoffeq(self->fd[1], 4);
+
+	async {
+		usleep(1000);
+		sendeq(self->fd[0], "bbbb", 0);
+	}
+
+	/* goto again; -> goto redo; in unix_stream_read_generic(). */
+	recveq(self->fd[1], "bbbb", 100, MSG_PEEK);
+	peekoffeq(self->fd[1], 8);
+
+	recveq(self->fd[1], "aaaa", 4, 0);
+	recveq(self->fd[1], "bbbb", 4, 0);
+	peekoffeq(self->fd[1], 0);
+}
+
+TEST_F(so_peek_off, two_chunks_overlap)
+{
+	sendeq(self->fd[0], "aaaa", 0);
+	recveq(self->fd[1], "aa", 2, MSG_PEEK);
+	peekoffeq(self->fd[1], 2);
+
+	sendeq(self->fd[0], "bbbb", 0);
+
+	if (variant->type == SOCK_STREAM) {
+		/* SOCK_STREAM tries to fill the buffer. */
+		recveq(self->fd[1], "aabb", 4, MSG_PEEK);
+		peekoffeq(self->fd[1], 6);
+		recveq(self->fd[1], "bb", 100, MSG_PEEK);
+		peekoffeq(self->fd[1], 8);
+	} else {
+		/* SOCK_DGRAM and SOCK_SEQPACKET returns at the skb boundary. */
+		recveq(self->fd[1], "aa", 100, MSG_PEEK);
+		peekoffeq(self->fd[1], 4);
+		recveq(self->fd[1], "bbbb", 100, MSG_PEEK);
+		peekoffeq(self->fd[1], 8);
+	}
+
+	recveq(self->fd[1], "aaaa", 4, 0);
+	recveq(self->fd[1], "bbbb", 4, 0);
+	peekoffeq(self->fd[1], 0);
+}
+
+TEST_F(so_peek_off, two_chunks_overlap_blocking)
+{
+	async {
+		usleep(1000);
+		sendeq(self->fd[0], "aaaa", 0);
+	}
+
+	recveq(self->fd[1], "aa", 2, MSG_PEEK);
+	peekoffeq(self->fd[1], 2);
+
+	async {
+		usleep(1000);
+		sendeq(self->fd[0], "bbbb", 0);
+	}
+
+	/* Even SOCK_STREAM does not wait if at least one byte is read. */
+	recveq(self->fd[1], "aa", 100, MSG_PEEK);
+	peekoffeq(self->fd[1], 4);
+
+	recveq(self->fd[1], "bbbb", 100, MSG_PEEK);
+	peekoffeq(self->fd[1], 8);
+
+	recveq(self->fd[1], "aaaa", 4, 0);
+	recveq(self->fd[1], "bbbb", 4, 0);
+	peekoffeq(self->fd[1], 0);
+}
+
+TEST_HARNESS_MAIN

linux-7.2.3/tools/testing/selftests/net/af_unix/unix_connect.c

@@ -0,0 +1,148 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+#include <sched.h>
+
+#include <stddef.h>
+#include <stdio.h>
+#include <unistd.h>
+
+#include <sys/socket.h>
+#include <sys/un.h>
+
+#include "kselftest_harness.h"
+
+FIXTURE(unix_connect)
+{
+	int server, client;
+	int family;
+};
+
+FIXTURE_VARIANT(unix_connect)
+{
+	int type;
+	char sun_path[8];
+	int len;
+	int flags;
+	int err;
+};
+
+FIXTURE_VARIANT_ADD(unix_connect, stream_pathname)
+{
+	.type = SOCK_STREAM,
+	.sun_path = "test",
+	.len = 4 + 1,
+	.flags = 0,
+	.err = 0,
+};
+
+FIXTURE_VARIANT_ADD(unix_connect, stream_abstract)
+{
+	.type = SOCK_STREAM,
+	.sun_path = "\0test",
+	.len = 5,
+	.flags = 0,
+	.err = 0,
+};
+
+FIXTURE_VARIANT_ADD(unix_connect, stream_pathname_netns)
+{
+	.type = SOCK_STREAM,
+	.sun_path = "test",
+	.len = 4 + 1,
+	.flags = CLONE_NEWNET,
+	.err = 0,
+};
+
+FIXTURE_VARIANT_ADD(unix_connect, stream_abstract_netns)
+{
+	.type = SOCK_STREAM,
+	.sun_path = "\0test",
+	.len = 5,
+	.flags = CLONE_NEWNET,
+	.err = ECONNREFUSED,
+};
+
+FIXTURE_VARIANT_ADD(unix_connect, dgram_pathname)
+{
+	.type = SOCK_DGRAM,
+	.sun_path = "test",
+	.len = 4 + 1,
+	.flags = 0,
+	.err = 0,
+};
+
+FIXTURE_VARIANT_ADD(unix_connect, dgram_abstract)
+{
+	.type = SOCK_DGRAM,
+	.sun_path = "\0test",
+	.len = 5,
+	.flags = 0,
+	.err = 0,
+};
+
+FIXTURE_VARIANT_ADD(unix_connect, dgram_pathname_netns)
+{
+	.type = SOCK_DGRAM,
+	.sun_path = "test",
+	.len = 4 + 1,
+	.flags = CLONE_NEWNET,
+	.err = 0,
+};
+
+FIXTURE_VARIANT_ADD(unix_connect, dgram_abstract_netns)
+{
+	.type = SOCK_DGRAM,
+	.sun_path = "\0test",
+	.len = 5,
+	.flags = CLONE_NEWNET,
+	.err = ECONNREFUSED,
+};
+
+FIXTURE_SETUP(unix_connect)
+{
+	self->family = AF_UNIX;
+}
+
+FIXTURE_TEARDOWN(unix_connect)
+{
+	close(self->server);
+	close(self->client);
+
+	if (variant->sun_path[0])
+		remove("test");
+}
+
+TEST_F(unix_connect, test)
+{
+	socklen_t addrlen;
+	struct sockaddr_un addr = {
+		.sun_family = self->family,
+	};
+	int err;
+
+	self->server = socket(self->family, variant->type, 0);
+	ASSERT_NE(-1, self->server);
+
+	addrlen = offsetof(struct sockaddr_un, sun_path) + variant->len;
+	memcpy(&addr.sun_path, variant->sun_path, variant->len);
+
+	err = bind(self->server, (struct sockaddr *)&addr, addrlen);
+	ASSERT_EQ(0, err);
+
+	if (variant->type == SOCK_STREAM) {
+		err = listen(self->server, 32);
+		ASSERT_EQ(0, err);
+	}
+
+	err = unshare(variant->flags);
+	ASSERT_EQ(0, err);
+
+	self->client = socket(self->family, variant->type, 0);
+	ASSERT_LT(0, self->client);
+
+	err = connect(self->client, (struct sockaddr *)&addr, addrlen);
+	ASSERT_EQ(variant->err, err == -1 ? errno : 0);
+}
+
+TEST_HARNESS_MAIN

linux-7.2.3/tools/testing/selftests/net/af_unix/unix_connreset.c

@@ -0,0 +1,180 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Selftest for AF_UNIX socket close and ECONNRESET behaviour.
+ *
+ * This test verifies:
+ *  1. SOCK_STREAM returns EOF when the peer closes normally.
+ *  2. SOCK_STREAM returns ECONNRESET if peer closes with unread data.
+ *  3. SOCK_SEQPACKET returns EOF when the peer closes normally.
+ *  4. SOCK_SEQPACKET returns ECONNRESET if the peer closes with unread data.
+ *  5. SOCK_DGRAM does not return ECONNRESET when the peer closes.
+ *
+ * These tests document the intended Linux behaviour.
+ *
+ */
+
+#define _GNU_SOURCE
+#include <string.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include <errno.h>
+#include <sys/socket.h>
+#include <sys/un.h>
+#include "../../kselftest_harness.h"
+
+#define SOCK_PATH "/tmp/af_unix_connreset.sock"
+
+static void remove_socket_file(void)
+{
+	unlink(SOCK_PATH);
+}
+
+FIXTURE(unix_sock)
+{
+	int server;
+	int client;
+	int child;
+};
+
+FIXTURE_VARIANT(unix_sock)
+{
+	int socket_type;
+	const char *name;
+};
+
+FIXTURE_VARIANT_ADD(unix_sock, stream) {
+	.socket_type = SOCK_STREAM,
+	.name = "SOCK_STREAM",
+};
+
+FIXTURE_VARIANT_ADD(unix_sock, dgram) {
+	.socket_type = SOCK_DGRAM,
+	.name = "SOCK_DGRAM",
+};
+
+FIXTURE_VARIANT_ADD(unix_sock, seqpacket) {
+	.socket_type = SOCK_SEQPACKET,
+	.name = "SOCK_SEQPACKET",
+};
+
+FIXTURE_SETUP(unix_sock)
+{
+	struct sockaddr_un addr = {};
+	int err;
+
+	addr.sun_family = AF_UNIX;
+	strcpy(addr.sun_path, SOCK_PATH);
+	remove_socket_file();
+
+	self->server = socket(AF_UNIX, variant->socket_type, 0);
+	ASSERT_LT(-1, self->server);
+
+	err = bind(self->server, (struct sockaddr *)&addr, sizeof(addr));
+	ASSERT_EQ(0, err);
+
+	if (variant->socket_type == SOCK_STREAM ||
+	    variant->socket_type == SOCK_SEQPACKET) {
+		err = listen(self->server, 1);
+		ASSERT_EQ(0, err);
+	}
+
+	self->client = socket(AF_UNIX, variant->socket_type | SOCK_NONBLOCK, 0);
+	ASSERT_LT(-1, self->client);
+
+	err = connect(self->client, (struct sockaddr *)&addr, sizeof(addr));
+	ASSERT_EQ(0, err);
+}
+
+FIXTURE_TEARDOWN(unix_sock)
+{
+	if (variant->socket_type == SOCK_STREAM ||
+	    variant->socket_type == SOCK_SEQPACKET)
+		close(self->child);
+
+	close(self->client);
+	close(self->server);
+	remove_socket_file();
+}
+
+/* Test 1: peer closes normally */
+TEST_F(unix_sock, eof)
+{
+	char buf[16] = {};
+	ssize_t n;
+
+	if (variant->socket_type == SOCK_STREAM ||
+	    variant->socket_type == SOCK_SEQPACKET) {
+		self->child = accept(self->server, NULL, NULL);
+		ASSERT_LT(-1, self->child);
+
+		close(self->child);
+	} else {
+		close(self->server);
+	}
+
+	n = recv(self->client, buf, sizeof(buf), 0);
+
+	if (variant->socket_type == SOCK_STREAM ||
+	    variant->socket_type == SOCK_SEQPACKET) {
+		ASSERT_EQ(0, n);
+	} else {
+		ASSERT_EQ(-1, n);
+		ASSERT_EQ(EAGAIN, errno);
+	}
+}
+
+/* Test 2: peer closes with unread data */
+TEST_F(unix_sock, reset_unread_behavior)
+{
+	char buf[16] = {};
+	ssize_t n;
+
+	/* Send data that will remain unread */
+	send(self->client, "hello", 5, 0);
+
+	if (variant->socket_type == SOCK_DGRAM) {
+		/* No real connection, just close the server */
+		close(self->server);
+	} else {
+		self->child = accept(self->server, NULL, NULL);
+		ASSERT_LT(-1, self->child);
+
+		/* Peer closes before client reads */
+		close(self->child);
+	}
+
+	n = recv(self->client, buf, sizeof(buf), 0);
+	ASSERT_EQ(-1, n);
+
+	if (variant->socket_type == SOCK_STREAM ||
+	    variant->socket_type == SOCK_SEQPACKET) {
+		ASSERT_EQ(ECONNRESET, errno);
+	} else {
+		ASSERT_EQ(EAGAIN, errno);
+	}
+}
+
+/* Test 3: closing unaccepted (embryo) server socket should reset client. */
+TEST_F(unix_sock, reset_closed_embryo)
+{
+	char buf[16] = {};
+	ssize_t n;
+
+	if (variant->socket_type == SOCK_DGRAM) {
+		snprintf(_metadata->results->reason,
+			 sizeof(_metadata->results->reason),
+			 "Test only applies to SOCK_STREAM and SOCK_SEQPACKET");
+		exit(KSFT_XFAIL);
+	}
+
+	/* Close server without accept()ing */
+	close(self->server);
+
+	n = recv(self->client, buf, sizeof(buf), 0);
+
+	ASSERT_EQ(-1, n);
+	ASSERT_EQ(ECONNRESET, errno);
+}
+
+TEST_HARNESS_MAIN
+

linux-7.2.3/tools/testing/selftests/net/af_unix/unix_listen.c

@@ -0,0 +1,187 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Tests for the state checks in AF_UNIX listen().
+ *
+ * The central case is a regression test: listen() on a bound socket that
+ * is already connected (i.e. not in TCP_CLOSE or TCP_LISTEN state) must
+ * fail with EINVAL.  A prior change accidentally let it return success
+ * without doing anything, because a helper called in between reset the
+ * error code to 0.  The neighbouring checks (unbound, already listening)
+ * are tested too so they cannot silently regress the same way.
+ *
+ * Every case runs for both listenable socket types (SOCK_STREAM and
+ * SOCK_SEQPACKET) and both pathname and abstract addresses.
+ */
+#define _GNU_SOURCE
+
+#include <errno.h>
+#include <stddef.h>
+#include <stdio.h>
+#include <string.h>
+#include <unistd.h>
+
+#include <sys/socket.h>
+#include <sys/un.h>
+
+#include "kselftest_harness.h"
+
+#define SK_NAME		"unix_listen_sk"
+#define SRV_NAME	"unix_listen_srv"
+
+FIXTURE(unix_listen)
+{
+	int sk;			/* socket under test */
+	int server;		/* a listening peer, when a test needs one */
+	struct sockaddr_un addr, srv_addr;
+	socklen_t addrlen, srv_addrlen;
+};
+
+FIXTURE_VARIANT(unix_listen)
+{
+	int type;
+	int abstract;
+};
+
+FIXTURE_VARIANT_ADD(unix_listen, stream_pathname)
+{
+	.type = SOCK_STREAM,
+	.abstract = 0,
+};
+
+FIXTURE_VARIANT_ADD(unix_listen, stream_abstract)
+{
+	.type = SOCK_STREAM,
+	.abstract = 1,
+};
+
+FIXTURE_VARIANT_ADD(unix_listen, seqpacket_pathname)
+{
+	.type = SOCK_SEQPACKET,
+	.abstract = 0,
+};
+
+FIXTURE_VARIANT_ADD(unix_listen, seqpacket_abstract)
+{
+	.type = SOCK_SEQPACKET,
+	.abstract = 1,
+};
+
+/* Fill @addr with a pathname or abstract address named @name. */
+static socklen_t unix_set_addr(struct sockaddr_un *addr, const char *name,
+			       int abstract)
+{
+	size_t len = strlen(name);
+
+	memset(addr, 0, sizeof(*addr));
+	addr->sun_family = AF_UNIX;
+	/* An abstract address leads with a NUL and has no filesystem entry. */
+	memcpy(addr->sun_path + (abstract ? 1 : 0), name, len);
+
+	return offsetof(struct sockaddr_un, sun_path) + len + 1;
+}
+
+FIXTURE_SETUP(unix_listen)
+{
+	self->sk = -1;
+	self->server = -1;
+	self->addrlen = unix_set_addr(&self->addr, SK_NAME, variant->abstract);
+	self->srv_addrlen = unix_set_addr(&self->srv_addr, SRV_NAME,
+					  variant->abstract);
+}
+
+FIXTURE_TEARDOWN(unix_listen)
+{
+	if (self->sk >= 0)
+		close(self->sk);
+	if (self->server >= 0)
+		close(self->server);
+
+	/* Pathname sockets leave a filesystem entry behind; abstract ones do not. */
+	if (!variant->abstract) {
+		remove(SK_NAME);
+		remove(SRV_NAME);
+	}
+}
+
+/* A bound socket in TCP_CLOSE is the normal, allowed case. */
+TEST_F(unix_listen, bound_is_ok)
+{
+	int err;
+
+	self->sk = socket(AF_UNIX, variant->type, 0);
+	ASSERT_LE(0, self->sk);
+
+	err = bind(self->sk, (struct sockaddr *)&self->addr, self->addrlen);
+	ASSERT_EQ(0, err);
+
+	err = listen(self->sk, 8);
+	EXPECT_EQ(0, err);
+}
+
+/* Listening again on an already-listening socket (TCP_LISTEN) is allowed. */
+TEST_F(unix_listen, relisten_is_ok)
+{
+	int err;
+
+	self->sk = socket(AF_UNIX, variant->type, 0);
+	ASSERT_LE(0, self->sk);
+
+	err = bind(self->sk, (struct sockaddr *)&self->addr, self->addrlen);
+	ASSERT_EQ(0, err);
+
+	err = listen(self->sk, 8);
+	ASSERT_EQ(0, err);
+
+	err = listen(self->sk, 16);
+	EXPECT_EQ(0, err);
+}
+
+/* listen() on an unbound socket fails: there is nothing to listen on. */
+TEST_F(unix_listen, unbound_is_einval)
+{
+	int err;
+
+	self->sk = socket(AF_UNIX, variant->type, 0);
+	ASSERT_LE(0, self->sk);
+
+	err = listen(self->sk, 8);
+	EXPECT_EQ(-1, err);
+	EXPECT_EQ(EINVAL, errno);
+}
+
+/*
+ * The regression: a bound socket that has already been connected is not in
+ * TCP_CLOSE or TCP_LISTEN, so listen() must reject it with EINVAL rather
+ * than quietly succeeding.
+ */
+TEST_F(unix_listen, connected_is_einval)
+{
+	int err;
+
+	self->server = socket(AF_UNIX, variant->type, 0);
+	ASSERT_LE(0, self->server);
+
+	err = bind(self->server, (struct sockaddr *)&self->srv_addr,
+		   self->srv_addrlen);
+	ASSERT_EQ(0, err);
+
+	err = listen(self->server, 8);
+	ASSERT_EQ(0, err);
+
+	self->sk = socket(AF_UNIX, variant->type, 0);
+	ASSERT_LE(0, self->sk);
+
+	/* Bind first so the unbound check does not mask the state check. */
+	err = bind(self->sk, (struct sockaddr *)&self->addr, self->addrlen);
+	ASSERT_EQ(0, err);
+
+	err = connect(self->sk, (struct sockaddr *)&self->srv_addr,
+		      self->srv_addrlen);
+	ASSERT_EQ(0, err);
+
+	err = listen(self->sk, 8);
+	EXPECT_EQ(-1, err);
+	EXPECT_EQ(EINVAL, errno);
+}
+
+TEST_HARNESS_MAIN