Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Cross-merge networking fixes after downstream PR.

Conflicts:

Documentation/devicetree/bindings/net/fsl,qoriq-mc-dpmac.yaml
  c25504a0ba36 ("dt-bindings: net: fsl,qoriq-mc-dpmac: add missed property phys")
  be034ee6c33d ("dt-bindings: net: fsl,qoriq-mc-dpmac: using unevaluatedProperties")
https://lore.kernel.org/20240815110934.56ae623a@canb.auug.org.au

drivers/net/dsa/vitesse-vsc73xx-core.c
  5b9eebc2c7a5 ("net: dsa: vsc73xx: pass value in phy_write operation")
  fa63c6434b6f ("net: dsa: vsc73xx: check busy flag in MDIO operations")
  2524d6c28bdc ("net: dsa: vsc73xx: use defined values in phy operations")
https://lore.kernel.org/20240813104039.429b9fe6@canb.auug.org.au
Resolve by using FIELD_PREP(), Stephen's resolution is simpler.

Adjacent changes:

net/vmw_vsock/af_vsock.c
  69139d2919dd ("vsock: fix recursive ->recvmsg calls")
  744500d81f81 ("vsock: add support for SIOCOUTQ ioctl")

Link: https://patch.msgid.link/20240815141149.33862-1-pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

9 files changed, 224 insertions, 4 deletions

diff --git a/tools/testing/selftests/bpf/progs/iters.c b/tools/testing/selftests/bpf/progs/iters.c
index 16bdc3e25591..ef70b88bccb2 100644
--- a/tools/testing/selftests/bpf/progs/iters.c
+++ b/tools/testing/selftests/bpf/progs/iters.c
@@ -1432,4 +1432,58 @@ int iter_arr_with_actual_elem_count(const void *ctx)
 	return sum;
 }
 
+__u32 upper, select_n, result;
+__u64 global;
+
+static __noinline bool nest_2(char *str)
+{
+	/* some insns (including branch insns) to ensure stacksafe() is triggered
+	 * in nest_2(). This way, stacksafe() can compare frame associated with nest_1().
+	 */
+	if (str[0] == 't')
+		return true;
+	if (str[1] == 'e')
+		return true;
+	if (str[2] == 's')
+		return true;
+	if (str[3] == 't')
+		return true;
+	return false;
+}
+
+static __noinline bool nest_1(int n)
+{
+	/* case 0: allocate stack, case 1: no allocate stack */
+	switch (n) {
+	case 0: {
+		char comm[16];
+
+		if (bpf_get_current_comm(comm, 16))
+			return false;
+		return nest_2(comm);
+	}
+	case 1:
+		return nest_2((char *)&global);
+	default:
+		return false;
+	}
+}
+
+SEC("raw_tp")
+__success
+int iter_subprog_check_stacksafe(const void *ctx)
+{
+	long i;
+
+	bpf_for(i, 0, upper) {
+		if (!nest_1(select_n)) {
+			result = 1;
+			return 0;
+		}
+	}
+
+	result = 2;
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/core/close_range_test.c b/tools/testing/selftests/core/close_range_test.c
index 991c473e3859..12b4eb9d0434 100644
--- a/tools/testing/selftests/core/close_range_test.c
+++ b/tools/testing/selftests/core/close_range_test.c
@@ -589,4 +589,39 @@ TEST(close_range_cloexec_unshare_syzbot)
 	EXPECT_EQ(close(fd3), 0);
 }
 
+TEST(close_range_bitmap_corruption)
+{
+	pid_t pid;
+	int status;
+	struct __clone_args args = {
+		.flags = CLONE_FILES,
+		.exit_signal = SIGCHLD,
+	};
+
+	/* get the first 128 descriptors open */
+	for (int i = 2; i < 128; i++)
+		EXPECT_GE(dup2(0, i), 0);
+
+	/* get descriptor table shared */
+	pid = sys_clone3(&args, sizeof(args));
+	ASSERT_GE(pid, 0);
+
+	if (pid == 0) {
+		/* unshare and truncate descriptor table down to 64 */
+		if (sys_close_range(64, ~0U, CLOSE_RANGE_UNSHARE))
+			exit(EXIT_FAILURE);
+
+		ASSERT_EQ(fcntl(64, F_GETFD), -1);
+		/* ... and verify that the range 64..127 is not
+		   stuck "fully used" according to secondary bitmap */
+		EXPECT_EQ(dup(0), 64)
+			exit(EXIT_FAILURE);
+		exit(EXIT_SUCCESS);
+	}
+
+	EXPECT_EQ(waitpid(pid, &status, 0), pid);
+	EXPECT_EQ(true, WIFEXITED(status));
+	EXPECT_EQ(0, WEXITSTATUS(status));
+}
+
 TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
index 709d7d721760..4abebde78187 100644
--- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c
+++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
@@ -32,13 +32,13 @@ static struct feature_id_reg feat_id_regs[] = {
 	{
 		ARM64_SYS_REG(3, 0, 10, 2, 2),	/* PIRE0_EL1 */
 		ARM64_SYS_REG(3, 0, 0, 7, 3),	/* ID_AA64MMFR3_EL1 */
-		4,
+		8,
 		1
 	},
 	{
 		ARM64_SYS_REG(3, 0, 10, 2, 3),	/* PIR_EL1 */
 		ARM64_SYS_REG(3, 0, 0, 7, 3),	/* ID_AA64MMFR3_EL1 */
-		4,
+		8,
 		1
 	}
 };
diff --git a/tools/testing/selftests/kvm/x86_64/xapic_state_test.c b/tools/testing/selftests/kvm/x86_64/xapic_state_test.c
index 69849acd95b0..618cd2442390 100644
--- a/tools/testing/selftests/kvm/x86_64/xapic_state_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xapic_state_test.c
@@ -184,6 +184,33 @@ static void test_apic_id(void)
 	kvm_vm_free(vm);
 }
 
+static void test_x2apic_id(void)
+{
+	struct kvm_lapic_state lapic = {};
+	struct kvm_vcpu *vcpu;
+	struct kvm_vm *vm;
+	int i;
+
+	vm = vm_create_with_one_vcpu(&vcpu, NULL);
+	vcpu_set_msr(vcpu, MSR_IA32_APICBASE, MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE);
+
+	/*
+	 * Try stuffing a modified x2APIC ID, KVM should ignore the value and
+	 * always return the vCPU's default/readonly x2APIC ID.
+	 */
+	for (i = 0; i <= 0xff; i++) {
+		*(u32 *)(lapic.regs + APIC_ID) = i << 24;
+		*(u32 *)(lapic.regs + APIC_SPIV) = APIC_SPIV_APIC_ENABLED;
+		vcpu_ioctl(vcpu, KVM_SET_LAPIC, &lapic);
+
+		vcpu_ioctl(vcpu, KVM_GET_LAPIC, &lapic);
+		TEST_ASSERT(*((u32 *)&lapic.regs[APIC_ID]) == vcpu->id << 24,
+			    "x2APIC ID should be fully readonly");
+	}
+
+	kvm_vm_free(vm);
+}
+
 int main(int argc, char *argv[])
 {
 	struct xapic_vcpu x = {
@@ -211,4 +238,5 @@ int main(int argc, char *argv[])
 	kvm_vm_free(vm);
 
 	test_apic_id();
+	test_x2apic_id();
 }
diff --git a/tools/testing/selftests/net/af_unix/msg_oob.c b/tools/testing/selftests/net/af_unix/msg_oob.c
index 16d0c172eaeb..535eb2c3d7d1 100644
--- a/tools/testing/selftests/net/af_unix/msg_oob.c
+++ b/tools/testing/selftests/net/af_unix/msg_oob.c
@@ -209,7 +209,7 @@ static void __sendpair(struct __test_metadata *_metadata,
 
 static void __recvpair(struct __test_metadata *_metadata,
 		       FIXTURE_DATA(msg_oob) *self,
-		       const void *expected_buf, int expected_len,
+		       const char *expected_buf, int expected_len,
 		       int buf_len, int flags)
 {
 	int i, ret[2], recv_errno[2], expected_errno = 0;
diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh
index d0219032f773..8ee4489238ca 100644
--- a/tools/testing/selftests/net/lib.sh
+++ b/tools/testing/selftests/net/lib.sh
@@ -146,6 +146,7 @@ cleanup_ns()
 
 	for ns in "$@"; do
 		[ -z "${ns}" ] && continue
+		ip netns pids "${ns}" 2> /dev/null | xargs -r kill || true
 		ip netns delete "${ns}" &> /dev/null || true
 		if ! busywait $BUSYWAIT_TIMEOUT ip netns list \| grep -vq "^$ns$" &> /dev/null; then
 			echo "Warn: Failed to remove namespace $ns"
diff --git a/tools/testing/selftests/net/netfilter/Makefile b/tools/testing/selftests/net/netfilter/Makefile
index 47945b2b3f92..d13fb5ea3e89 100644
--- a/tools/testing/selftests/net/netfilter/Makefile
+++ b/tools/testing/selftests/net/netfilter/Makefile
@@ -7,6 +7,7 @@ MNL_CFLAGS := $(shell $(HOSTPKG_CONFIG) --cflags libmnl 2>/dev/null)
 MNL_LDLIBS := $(shell $(HOSTPKG_CONFIG) --libs libmnl 2>/dev/null || echo -lmnl)
 
 TEST_PROGS := br_netfilter.sh bridge_brouter.sh
+TEST_PROGS += br_netfilter_queue.sh
 TEST_PROGS += conntrack_icmp_related.sh
 TEST_PROGS += conntrack_ipip_mtu.sh
 TEST_PROGS += conntrack_tcp_unreplied.sh
diff --git a/tools/testing/selftests/net/netfilter/br_netfilter_queue.sh b/tools/testing/selftests/net/netfilter/br_netfilter_queue.sh
new file mode 100755
index 000000000000..6a764d70ab06
--- /dev/null
+++ b/tools/testing/selftests/net/netfilter/br_netfilter_queue.sh
@@ -0,0 +1,78 @@
+#!/bin/bash
+
+source lib.sh
+
+checktool "nft --version" "run test without nft tool"
+
+cleanup() {
+	cleanup_all_ns
+}
+
+setup_ns c1 c2 c3 sender
+
+trap cleanup EXIT
+
+nf_queue_wait()
+{
+	grep -q "^ *$1 " "/proc/self/net/netfilter/nfnetlink_queue"
+}
+
+port_add() {
+	ns="$1"
+	dev="$2"
+	a="$3"
+
+	ip link add name "$dev" type veth peer name "$dev" netns "$ns"
+
+	ip -net "$ns" addr add 192.168.1."$a"/24 dev "$dev"
+	ip -net "$ns" link set "$dev" up
+
+	ip link set "$dev" master br0
+	ip link set "$dev" up
+}
+
+[ "${1}" != "run" ] && { unshare -n "${0}" run; exit $?; }
+
+ip link add br0 type bridge
+ip addr add 192.168.1.254/24 dev br0
+
+port_add "$c1" "c1" 1
+port_add "$c2" "c2" 2
+port_add "$c3" "c3" 3
+port_add "$sender" "sender" 253
+
+ip link set br0 up
+
+modprobe -q br_netfilter
+
+sysctl net.bridge.bridge-nf-call-iptables=1 || exit 1
+
+ip netns exec "$sender" ping -I sender -c1 192.168.1.1 || exit 1
+ip netns exec "$sender" ping -I sender -c1 192.168.1.2 || exit 2
+ip netns exec "$sender" ping -I sender -c1 192.168.1.3 || exit 3
+
+nft -f /dev/stdin <<EOF
+table ip filter {
+	chain forward {
+		type filter hook forward priority 0; policy accept;
+		ct state new counter
+		ip protocol icmp counter queue num 0 bypass
+	}
+}
+EOF
+./nf_queue -t 5 > /dev/null &
+
+busywait 5000 nf_queue_wait
+
+for i in $(seq 1 5); do conntrack -F > /dev/null 2> /dev/null; sleep 0.1 ; done &
+ip netns exec "$sender" ping -I sender -f -c 50 -b 192.168.1.255
+
+read t < /proc/sys/kernel/tainted
+if [ "$t" -eq 0 ];then
+	echo PASS: kernel not tainted
+else
+	echo ERROR: kernel is tainted
+	exit 1
+fi
+
+exit 0
diff --git a/tools/testing/selftests/net/udpgso.c b/tools/testing/selftests/net/udpgso.c
index 3e74cfa1a2bf..3f2fca02fec5 100644
--- a/tools/testing/selftests/net/udpgso.c
+++ b/tools/testing/selftests/net/udpgso.c
@@ -67,6 +67,7 @@ struct testcase {
 	int gso_len;		/* mss after applying gso */
 	int r_num_mss;		/* recv(): number of calls of full mss */
 	int r_len_last;		/* recv(): size of last non-mss dgram, if any */
+	bool v6_ext_hdr;	/* send() dgrams with IPv6 extension headers */
 };
 
 const struct in6_addr addr6 = {
@@ -77,6 +78,8 @@ const struct in_addr addr4 = {
 	__constant_htonl(0x0a000001), /* 10.0.0.1 */
 };
 
+static const char ipv6_hopopts_pad1[8] = { 0 };
+
 struct testcase testcases_v4[] = {
 	{
 		/* no GSO: send a single byte */
@@ -256,6 +259,13 @@ struct testcase testcases_v6[] = {
 		.r_num_mss = 2,
 	},
 	{
+		/* send 2 1B segments with extension headers */
+		.tlen = 2,
+		.gso_len = 1,
+		.r_num_mss = 2,
+		.v6_ext_hdr = true,
+	},
+	{
 		/* send 2B + 2B + 1B segments */
 		.tlen = 5,
 		.gso_len = 2,
@@ -396,11 +406,18 @@ static void run_one(struct testcase *test, int fdt, int fdr,
 	int i, ret, val, mss;
 	bool sent;
 
-	fprintf(stderr, "ipv%d tx:%d gso:%d %s\n",
+	fprintf(stderr, "ipv%d tx:%d gso:%d %s%s\n",
 			addr->sa_family == AF_INET ? 4 : 6,
 			test->tlen, test->gso_len,
+			test->v6_ext_hdr ? "ext-hdr " : "",
 			test->tfail ? "(fail)" : "");
 
+	if (test->v6_ext_hdr) {
+		if (setsockopt(fdt, IPPROTO_IPV6, IPV6_HOPOPTS,
+			       ipv6_hopopts_pad1, sizeof(ipv6_hopopts_pad1)))
+			error(1, errno, "setsockopt ipv6 hopopts");
+	}
+
 	val = test->gso_len;
 	if (cfg_do_setsockopt) {
 		if (setsockopt(fdt, SOL_UDP, UDP_SEGMENT, &val, sizeof(val)))
@@ -412,6 +429,12 @@ static void run_one(struct testcase *test, int fdt, int fdr,
 		error(1, 0, "send succeeded while expecting failure");
 	if (!sent && !test->tfail)
 		error(1, 0, "send failed while expecting success");
+
+	if (test->v6_ext_hdr) {
+		if (setsockopt(fdt, IPPROTO_IPV6, IPV6_HOPOPTS, NULL, 0))
+			error(1, errno, "setsockopt ipv6 hopopts clear");
+	}
+
 	if (!sent)
 		return;