Merge branch 'af_unix-fix-so_peek_off-bug-in-unix_stream_read_generic'

Kuniyuki Iwashima says:

====================
af_unix: Fix SO_PEEK_OFF bug in unix_stream_read_generic().

Miao Wang reported a bug of SO_PEEK_OFF on AF_UNIX SOCK_STREAM socket.

Patch 1 fixes the bug and Patch 2 adds a new selftest to cover the case.
====================

Link: https://patch.msgid.link/20251117174740.3684604-1-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

Author: kuba-moo

net/unix/af_unix.c

@@ -2954,6 +2954,7 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state,
 
 	u = unix_sk(sk);
 
+redo:
 	/* Lock the socket to prevent queue disordering
 	 * while sleeps in memcpy_tomsg
 	 */
@@ -2965,7 +2966,6 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state,
 		struct sk_buff *skb, *last;
 		int chunk;
 
-redo:
 		unix_state_lock(sk);
 		if (sock_flag(sk, SOCK_DEAD)) {
 			err = -ECONNRESET;
@@ -3015,7 +3015,6 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state,
 				goto out;
 			}
 
-			mutex_lock(&u->iolock);
 			goto redo;
 unlock:
 			unix_state_unlock(sk);

tools/testing/selftests/net/.gitignore

@@ -45,6 +45,7 @@ skf_net_off
 socket
 so_incoming_cpu
 so_netns_cookie
+so_peek_off
 so_txtime
 so_rcv_listener
 stress_reuseport_listen

tools/testing/selftests/net/af_unix/Makefile

@@ -6,6 +6,7 @@ TEST_GEN_PROGS := \
 	scm_inq \
 	scm_pidfd \
 	scm_rights \
+	so_peek_off \
 	unix_connect \
 # end of TEST_GEN_PROGS
 

tools/testing/selftests/net/af_unix/so_peek_off.c

@@ -0,0 +1,162 @@
+// 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 = 0,
+		.tv_usec = 3000,
+	};
+	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 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);
+	recveq(self->fd[1], "bbbb", 100, MSG_PEEK);
+}
+
+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);
+	recveq(self->fd[1], "bbbb", 100, MSG_PEEK);
+}
+
+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);
+
+	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);
+}
+
+TEST_F(so_peek_off, two_chunks_overlap)
+{
+	sendeq(self->fd[0], "aaaa", 0);
+	recveq(self->fd[1], "aa", 2, MSG_PEEK);
+
+	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);
+		recveq(self->fd[1], "bb", 100, MSG_PEEK);
+	} else {
+		/* SOCK_DGRAM and SOCK_SEQPACKET returns at the skb boundary. */
+		recveq(self->fd[1], "aa", 100, MSG_PEEK);
+		recveq(self->fd[1], "bbbb", 100, MSG_PEEK);
+	}
+}
+
+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);
+
+	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);
+
+	recveq(self->fd[1], "bbbb", 100, MSG_PEEK);
+}
+
+TEST_HARNESS_MAIN