Merge tag 'v6.2' into iommufd.git for-next

Resolve conflicts from the signature change in iommu_map:

 - drivers/infiniband/hw/usnic/usnic_uiom.c
   Switch iommu_map_atomic() to iommu_map(.., GFP_ATOMIC)

 - drivers/vfio/vfio_iommu_type1.c
   Following indenting change for GFP_KERNEL

Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

28 files changed, 669 insertions, 245 deletions

diff --git a/tools/testing/selftests/amd-pstate/Makefile b/tools/testing/selftests/amd-pstate/Makefile
index 5f195ee756d6..5fd1424db37d 100644
--- a/tools/testing/selftests/amd-pstate/Makefile
+++ b/tools/testing/selftests/amd-pstate/Makefile
@@ -7,11 +7,6 @@ all:
 uname_M := $(shell uname -m 2>/dev/null || echo not)
 ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/)
 
-ifeq (x86,$(ARCH))
-TEST_GEN_FILES += ../../../power/x86/amd_pstate_tracer/amd_pstate_trace.py
-TEST_GEN_FILES += ../../../power/x86/intel_pstate_tracer/intel_pstate_tracer.py
-endif
-
 TEST_PROGS := run.sh
 TEST_FILES := basic.sh tbench.sh gitsource.sh
 
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
index 2cf0c7a3fe23..567e07c19ecc 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
@@ -30,6 +30,8 @@
 #define MAX_STRERR_LEN 256
 #define MAX_TEST_NAME 80
 
+#define __always_unused	__attribute__((__unused__))
+
 #define _FAIL(errnum, fmt...)                                                  \
 	({                                                                     \
 		error_at_line(0, (errnum), __func__, __LINE__, fmt);           \
@@ -321,7 +323,8 @@ static int socket_loopback(int family, int sotype)
 	return socket_loopback_reuseport(family, sotype, -1);
 }
 
-static void test_insert_invalid(int family, int sotype, int mapfd)
+static void test_insert_invalid(struct test_sockmap_listen *skel __always_unused,
+				int family, int sotype, int mapfd)
 {
 	u32 key = 0;
 	u64 value;
@@ -338,7 +341,8 @@ static void test_insert_invalid(int family, int sotype, int mapfd)
 		FAIL_ERRNO("map_update: expected EBADF");
 }
 
-static void test_insert_opened(int family, int sotype, int mapfd)
+static void test_insert_opened(struct test_sockmap_listen *skel __always_unused,
+			       int family, int sotype, int mapfd)
 {
 	u32 key = 0;
 	u64 value;
@@ -359,7 +363,8 @@ static void test_insert_opened(int family, int sotype, int mapfd)
 	xclose(s);
 }
 
-static void test_insert_bound(int family, int sotype, int mapfd)
+static void test_insert_bound(struct test_sockmap_listen *skel __always_unused,
+			      int family, int sotype, int mapfd)
 {
 	struct sockaddr_storage addr;
 	socklen_t len;
@@ -386,7 +391,8 @@ close:
 	xclose(s);
 }
 
-static void test_insert(int family, int sotype, int mapfd)
+static void test_insert(struct test_sockmap_listen *skel __always_unused,
+			int family, int sotype, int mapfd)
 {
 	u64 value;
 	u32 key;
@@ -402,7 +408,8 @@ static void test_insert(int family, int sotype, int mapfd)
 	xclose(s);
 }
 
-static void test_delete_after_insert(int family, int sotype, int mapfd)
+static void test_delete_after_insert(struct test_sockmap_listen *skel __always_unused,
+				     int family, int sotype, int mapfd)
 {
 	u64 value;
 	u32 key;
@@ -419,7 +426,8 @@ static void test_delete_after_insert(int family, int sotype, int mapfd)
 	xclose(s);
 }
 
-static void test_delete_after_close(int family, int sotype, int mapfd)
+static void test_delete_after_close(struct test_sockmap_listen *skel __always_unused,
+				    int family, int sotype, int mapfd)
 {
 	int err, s;
 	u64 value;
@@ -442,7 +450,8 @@ static void test_delete_after_close(int family, int sotype, int mapfd)
 		FAIL_ERRNO("map_delete: expected EINVAL/EINVAL");
 }
 
-static void test_lookup_after_insert(int family, int sotype, int mapfd)
+static void test_lookup_after_insert(struct test_sockmap_listen *skel __always_unused,
+				     int family, int sotype, int mapfd)
 {
 	u64 cookie, value;
 	socklen_t len;
@@ -470,7 +479,8 @@ static void test_lookup_after_insert(int family, int sotype, int mapfd)
 	xclose(s);
 }
 
-static void test_lookup_after_delete(int family, int sotype, int mapfd)
+static void test_lookup_after_delete(struct test_sockmap_listen *skel __always_unused,
+				     int family, int sotype, int mapfd)
 {
 	int err, s;
 	u64 value;
@@ -493,7 +503,8 @@ static void test_lookup_after_delete(int family, int sotype, int mapfd)
 	xclose(s);
 }
 
-static void test_lookup_32_bit_value(int family, int sotype, int mapfd)
+static void test_lookup_32_bit_value(struct test_sockmap_listen *skel __always_unused,
+				     int family, int sotype, int mapfd)
 {
 	u32 key, value32;
 	int err, s;
@@ -523,7 +534,8 @@ close:
 	xclose(s);
 }
 
-static void test_update_existing(int family, int sotype, int mapfd)
+static void test_update_existing(struct test_sockmap_listen *skel __always_unused,
+				 int family, int sotype, int mapfd)
 {
 	int s1, s2;
 	u64 value;
@@ -551,7 +563,7 @@ close_s1:
 /* Exercise the code path where we destroy child sockets that never
  * got accept()'ed, aka orphans, when parent socket gets closed.
  */
-static void test_destroy_orphan_child(int family, int sotype, int mapfd)
+static void do_destroy_orphan_child(int family, int sotype, int mapfd)
 {
 	struct sockaddr_storage addr;
 	socklen_t len;
@@ -582,10 +594,38 @@ close_srv:
 	xclose(s);
 }
 
+static void test_destroy_orphan_child(struct test_sockmap_listen *skel,
+				      int family, int sotype, int mapfd)
+{
+	int msg_verdict = bpf_program__fd(skel->progs.prog_msg_verdict);
+	int skb_verdict = bpf_program__fd(skel->progs.prog_skb_verdict);
+	const struct test {
+		int progfd;
+		enum bpf_attach_type atype;
+	} tests[] = {
+		{ -1, -1 },
+		{ msg_verdict, BPF_SK_MSG_VERDICT },
+		{ skb_verdict, BPF_SK_SKB_VERDICT },
+	};
+	const struct test *t;
+
+	for (t = tests; t < tests + ARRAY_SIZE(tests); t++) {
+		if (t->progfd != -1 &&
+		    xbpf_prog_attach(t->progfd, mapfd, t->atype, 0) != 0)
+			return;
+
+		do_destroy_orphan_child(family, sotype, mapfd);
+
+		if (t->progfd != -1)
+			xbpf_prog_detach2(t->progfd, mapfd, t->atype);
+	}
+}
+
 /* Perform a passive open after removing listening socket from SOCKMAP
  * to ensure that callbacks get restored properly.
  */
-static void test_clone_after_delete(int family, int sotype, int mapfd)
+static void test_clone_after_delete(struct test_sockmap_listen *skel __always_unused,
+				    int family, int sotype, int mapfd)
 {
 	struct sockaddr_storage addr;
 	socklen_t len;
@@ -621,7 +661,8 @@ close_srv:
  * SOCKMAP, but got accept()'ed only after the parent has been removed
  * from SOCKMAP, gets cloned without parent psock state or callbacks.
  */
-static void test_accept_after_delete(int family, int sotype, int mapfd)
+static void test_accept_after_delete(struct test_sockmap_listen *skel __always_unused,
+				     int family, int sotype, int mapfd)
 {
 	struct sockaddr_storage addr;
 	const u32 zero = 0;
@@ -675,7 +716,8 @@ close_srv:
 /* Check that child socket that got created and accepted while parent
  * was in a SOCKMAP is cloned without parent psock state or callbacks.
  */
-static void test_accept_before_delete(int family, int sotype, int mapfd)
+static void test_accept_before_delete(struct test_sockmap_listen *skel __always_unused,
+				      int family, int sotype, int mapfd)
 {
 	struct sockaddr_storage addr;
 	const u32 zero = 0, one = 1;
@@ -784,7 +826,8 @@ done:
 	return NULL;
 }
 
-static void test_syn_recv_insert_delete(int family, int sotype, int mapfd)
+static void test_syn_recv_insert_delete(struct test_sockmap_listen *skel __always_unused,
+					int family, int sotype, int mapfd)
 {
 	struct connect_accept_ctx ctx = { 0 };
 	struct sockaddr_storage addr;
@@ -847,7 +890,8 @@ static void *listen_thread(void *arg)
 	return NULL;
 }
 
-static void test_race_insert_listen(int family, int socktype, int mapfd)
+static void test_race_insert_listen(struct test_sockmap_listen *skel __always_unused,
+				    int family, int socktype, int mapfd)
 {
 	struct connect_accept_ctx ctx = { 0 };
 	const u32 zero = 0;
@@ -1473,7 +1517,8 @@ static void test_ops(struct test_sockmap_listen *skel, struct bpf_map *map,
 		     int family, int sotype)
 {
 	const struct op_test {
-		void (*fn)(int family, int sotype, int mapfd);
+		void (*fn)(struct test_sockmap_listen *skel,
+			   int family, int sotype, int mapfd);
 		const char *name;
 		int sotype;
 	} tests[] = {
@@ -1520,7 +1565,7 @@ static void test_ops(struct test_sockmap_listen *skel, struct bpf_map *map,
 		if (!test__start_subtest(s))
 			continue;
 
-		t->fn(family, sotype, map_fd);
+		t->fn(skel, family, sotype, map_fd);
 		test_ops_cleanup(map);
 	}
 }
diff --git a/tools/testing/selftests/bpf/verifier/search_pruning.c b/tools/testing/selftests/bpf/verifier/search_pruning.c
index 68b14fdfebdb..d63fd8991b03 100644
--- a/tools/testing/selftests/bpf/verifier/search_pruning.c
+++ b/tools/testing/selftests/bpf/verifier/search_pruning.c
@@ -225,3 +225,39 @@
 	.result_unpriv = ACCEPT,
 	.insn_processed = 15,
 },
+/* The test performs a conditional 64-bit write to a stack location
+ * fp[-8], this is followed by an unconditional 8-bit write to fp[-8],
+ * then data is read from fp[-8]. This sequence is unsafe.
+ *
+ * The test would be mistakenly marked as safe w/o dst register parent
+ * preservation in verifier.c:copy_register_state() function.
+ *
+ * Note the usage of BPF_F_TEST_STATE_FREQ to force creation of the
+ * checkpoint state after conditional 64-bit assignment.
+ */
+{
+	"write tracking and register parent chain bug",
+	.insns = {
+	/* r6 = ktime_get_ns() */
+	BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns),
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+	/* r0 = ktime_get_ns() */
+	BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns),
+	/* if r0 > r6 goto +1 */
+	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_6, 1),
+	/* *(u64 *)(r10 - 8) = 0xdeadbeef */
+	BPF_ST_MEM(BPF_DW, BPF_REG_FP, -8, 0xdeadbeef),
+	/* r1 = 42 */
+	BPF_MOV64_IMM(BPF_REG_1, 42),
+	/* *(u8 *)(r10 - 8) = r1 */
+	BPF_STX_MEM(BPF_B, BPF_REG_FP, BPF_REG_1, -8),
+	/* r2 = *(u64 *)(r10 - 8) */
+	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_FP, -8),
+	/* exit(0) */
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.flags = BPF_F_TEST_STATE_FREQ,
+	.errstr = "invalid read from stack off -8+1 size 8",
+	.result = REJECT,
+},
diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
index 186e1c26867e..75c100de90ff 100755
--- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh
+++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
@@ -268,6 +268,7 @@ TEST_MATRIX=(
 	# Taking away all CPUs from parent or itself if there are tasks
 	# will make the partition invalid.
 	"  S+ C2-3:P1:S+  C3:P1  .      .      T     C2-3    .      .     0 A1:2-3,A2:2-3 A1:P1,A2:P-1"
+	"  S+  C3:P1:S+    C3    .      .      T      P1     .      .     0 A1:3,A2:3 A1:P1,A2:P-1"
 	"  S+ $SETUP_A123_PARTITIONS    .    T:C2-3   .      .      .     0 A1:2-3,A2:2-3,A3:3 A1:P1,A2:P-1,A3:P-1"
 	"  S+ $SETUP_A123_PARTITIONS    . T:C2-3:C1-3 .      .      .     0 A1:1,A2:2,A3:3 A1:P1,A2:P1,A3:P1"
 
diff --git a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh
index 9c79bbcce5a8..aff0a59f92d9 100755
--- a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh
+++ b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh
@@ -246,7 +246,7 @@ test_vlan_ingress_modify()
 	bridge vlan add dev $swp2 vid 300
 
 	tc filter add dev $swp1 ingress chain $(IS1 2) pref 3 \
-		protocol 802.1Q flower skip_sw vlan_id 200 \
+		protocol 802.1Q flower skip_sw vlan_id 200 src_mac $h1_mac \
 		action vlan modify id 300 \
 		action goto chain $(IS2 0 0)
 
diff --git a/tools/testing/selftests/filesystems/fat/run_fat_tests.sh b/tools/testing/selftests/filesystems/fat/run_fat_tests.sh
index 7f35dc3d15df..7f35dc3d15df 100644..100755
--- a/tools/testing/selftests/filesystems/fat/run_fat_tests.sh
+++ b/tools/testing/selftests/filesystems/fat/run_fat_tests.sh
diff --git a/tools/testing/selftests/kvm/aarch64/page_fault_test.c b/tools/testing/selftests/kvm/aarch64/page_fault_test.c
index beb944fa6fd4..54680dc5887f 100644
--- a/tools/testing/selftests/kvm/aarch64/page_fault_test.c
+++ b/tools/testing/selftests/kvm/aarch64/page_fault_test.c
@@ -237,6 +237,11 @@ static void guest_check_s1ptw_wr_in_dirty_log(void)
 	GUEST_SYNC(CMD_CHECK_S1PTW_WR_IN_DIRTY_LOG);
 }
 
+static void guest_check_no_s1ptw_wr_in_dirty_log(void)
+{
+	GUEST_SYNC(CMD_CHECK_NO_S1PTW_WR_IN_DIRTY_LOG);
+}
+
 static void guest_exec(void)
 {
 	int (*code)(void) = (int (*)(void))TEST_EXEC_GVA;
@@ -304,7 +309,7 @@ static struct uffd_args {
 
 /* Returns true to continue the test, and false if it should be skipped. */
 static int uffd_generic_handler(int uffd_mode, int uffd, struct uffd_msg *msg,
-				struct uffd_args *args, bool expect_write)
+				struct uffd_args *args)
 {
 	uint64_t addr = msg->arg.pagefault.address;
 	uint64_t flags = msg->arg.pagefault.flags;
@@ -313,7 +318,6 @@ static int uffd_generic_handler(int uffd_mode, int uffd, struct uffd_msg *msg,
 
 	TEST_ASSERT(uffd_mode == UFFDIO_REGISTER_MODE_MISSING,
 		    "The only expected UFFD mode is MISSING");
-	ASSERT_EQ(!!(flags & UFFD_PAGEFAULT_FLAG_WRITE), expect_write);
 	ASSERT_EQ(addr, (uint64_t)args->hva);
 
 	pr_debug("uffd fault: addr=%p write=%d\n",
@@ -337,19 +341,14 @@ static int uffd_generic_handler(int uffd_mode, int uffd, struct uffd_msg *msg,
 	return 0;
 }
 
-static int uffd_pt_write_handler(int mode, int uffd, struct uffd_msg *msg)
-{
-	return uffd_generic_handler(mode, uffd, msg, &pt_args, true);
-}
-
-static int uffd_data_write_handler(int mode, int uffd, struct uffd_msg *msg)
+static int uffd_pt_handler(int mode, int uffd, struct uffd_msg *msg)
 {
-	return uffd_generic_handler(mode, uffd, msg, &data_args, true);
+	return uffd_generic_handler(mode, uffd, msg, &pt_args);
 }
 
-static int uffd_data_read_handler(int mode, int uffd, struct uffd_msg *msg)
+static int uffd_data_handler(int mode, int uffd, struct uffd_msg *msg)
 {
-	return uffd_generic_handler(mode, uffd, msg, &data_args, false);
+	return uffd_generic_handler(mode, uffd, msg, &data_args);
 }
 
 static void setup_uffd_args(struct userspace_mem_region *region,
@@ -471,9 +470,12 @@ static bool handle_cmd(struct kvm_vm *vm, int cmd)
 {
 	struct userspace_mem_region *data_region, *pt_region;
 	bool continue_test = true;
+	uint64_t pte_gpa, pte_pg;
 
 	data_region = vm_get_mem_region(vm, MEM_REGION_TEST_DATA);
 	pt_region = vm_get_mem_region(vm, MEM_REGION_PT);
+	pte_gpa = addr_hva2gpa(vm, virt_get_pte_hva(vm, TEST_GVA));
+	pte_pg = (pte_gpa - pt_region->region.guest_phys_addr) / getpagesize();
 
 	if (cmd == CMD_SKIP_TEST)
 		continue_test = false;
@@ -486,13 +488,13 @@ static bool handle_cmd(struct kvm_vm *vm, int cmd)
 		TEST_ASSERT(check_write_in_dirty_log(vm, data_region, 0),
 			    "Missing write in dirty log");
 	if (cmd & CMD_CHECK_S1PTW_WR_IN_DIRTY_LOG)
-		TEST_ASSERT(check_write_in_dirty_log(vm, pt_region, 0),
+		TEST_ASSERT(check_write_in_dirty_log(vm, pt_region, pte_pg),
 			    "Missing s1ptw write in dirty log");
 	if (cmd & CMD_CHECK_NO_WRITE_IN_DIRTY_LOG)
 		TEST_ASSERT(!check_write_in_dirty_log(vm, data_region, 0),
 			    "Unexpected write in dirty log");
 	if (cmd & CMD_CHECK_NO_S1PTW_WR_IN_DIRTY_LOG)
-		TEST_ASSERT(!check_write_in_dirty_log(vm, pt_region, 0),
+		TEST_ASSERT(!check_write_in_dirty_log(vm, pt_region, pte_pg),
 			    "Unexpected s1ptw write in dirty log");
 
 	return continue_test;
@@ -797,7 +799,7 @@ static void help(char *name)
 	.expected_events	= { .uffd_faults = _uffd_faults, },		\
 }
 
-#define TEST_DIRTY_LOG(_access, _with_af, _test_check)				\
+#define TEST_DIRTY_LOG(_access, _with_af, _test_check, _pt_check)		\
 {										\
 	.name			= SCAT3(dirty_log, _access, _with_af),		\
 	.data_memslot_flags	= KVM_MEM_LOG_DIRTY_PAGES,			\
@@ -805,13 +807,12 @@ static void help(char *name)
 	.guest_prepare		= { _PREPARE(_with_af),				\
 				    _PREPARE(_access) },			\
 	.guest_test		= _access,					\
-	.guest_test_check	= { _CHECK(_with_af), _test_check,		\
-				    guest_check_s1ptw_wr_in_dirty_log},		\
+	.guest_test_check	= { _CHECK(_with_af), _test_check, _pt_check },	\
 	.expected_events	= { 0 },					\
 }
 
 #define TEST_UFFD_AND_DIRTY_LOG(_access, _with_af, _uffd_data_handler,		\
-				_uffd_faults, _test_check)			\
+				_uffd_faults, _test_check, _pt_check)		\
 {										\
 	.name			= SCAT3(uffd_and_dirty_log, _access, _with_af),	\
 	.data_memslot_flags	= KVM_MEM_LOG_DIRTY_PAGES,			\
@@ -820,16 +821,17 @@ static void help(char *name)
 				    _PREPARE(_access) },			\
 	.guest_test		= _access,					\
 	.mem_mark_cmd		= CMD_HOLE_DATA | CMD_HOLE_PT,			\
-	.guest_test_check	= { _CHECK(_with_af), _test_check },		\
+	.guest_test_check	= { _CHECK(_with_af), _test_check, _pt_check },	\
 	.uffd_data_handler	= _uffd_data_handler,				\
-	.uffd_pt_handler	= uffd_pt_write_handler,			\
+	.uffd_pt_handler	= uffd_pt_handler,				\
 	.expected_events	= { .uffd_faults = _uffd_faults, },		\
 }
 
 #define TEST_RO_MEMSLOT(_access, _mmio_handler, _mmio_exits)			\
 {										\
-	.name			= SCAT3(ro_memslot, _access, _with_af),		\
+	.name			= SCAT2(ro_memslot, _access),			\
 	.data_memslot_flags	= KVM_MEM_READONLY,				\
+	.pt_memslot_flags	= KVM_MEM_READONLY,				\
 	.guest_prepare		= { _PREPARE(_access) },			\
 	.guest_test		= _access,					\
 	.mmio_handler		= _mmio_handler,				\
@@ -840,6 +842,7 @@ static void help(char *name)
 {										\
 	.name			= SCAT2(ro_memslot_no_syndrome, _access),	\
 	.data_memslot_flags	= KVM_MEM_READONLY,				\
+	.pt_memslot_flags	= KVM_MEM_READONLY,				\
 	.guest_test		= _access,					\
 	.fail_vcpu_run_handler	= fail_vcpu_run_mmio_no_syndrome_handler,	\
 	.expected_events	= { .fail_vcpu_runs = 1 },			\
@@ -848,9 +851,9 @@ static void help(char *name)
 #define TEST_RO_MEMSLOT_AND_DIRTY_LOG(_access, _mmio_handler, _mmio_exits,	\
 				      _test_check)				\
 {										\
-	.name			= SCAT3(ro_memslot, _access, _with_af),		\
+	.name			= SCAT2(ro_memslot, _access),			\
 	.data_memslot_flags	= KVM_MEM_READONLY | KVM_MEM_LOG_DIRTY_PAGES,	\
-	.pt_memslot_flags	= KVM_MEM_LOG_DIRTY_PAGES,			\
+	.pt_memslot_flags	= KVM_MEM_READONLY | KVM_MEM_LOG_DIRTY_PAGES,	\
 	.guest_prepare		= { _PREPARE(_access) },			\
 	.guest_test		= _access,					\
 	.guest_test_check	= { _test_check },				\
@@ -862,7 +865,7 @@ static void help(char *name)
 {										\
 	.name			= SCAT2(ro_memslot_no_syn_and_dlog, _access),	\
 	.data_memslot_flags	= KVM_MEM_READONLY | KVM_MEM_LOG_DIRTY_PAGES,	\
-	.pt_memslot_flags	= KVM_MEM_LOG_DIRTY_PAGES,			\
+	.pt_memslot_flags	= KVM_MEM_READONLY | KVM_MEM_LOG_DIRTY_PAGES,	\
 	.guest_test		= _access,					\
 	.guest_test_check	= { _test_check },				\
 	.fail_vcpu_run_handler	= fail_vcpu_run_mmio_no_syndrome_handler,	\
@@ -874,11 +877,12 @@ static void help(char *name)
 {										\
 	.name			= SCAT2(ro_memslot_uffd, _access),		\
 	.data_memslot_flags	= KVM_MEM_READONLY,				\
+	.pt_memslot_flags	= KVM_MEM_READONLY,				\
 	.mem_mark_cmd		= CMD_HOLE_DATA | CMD_HOLE_PT,			\
 	.guest_prepare		= { _PREPARE(_access) },			\
 	.guest_test		= _access,					\
 	.uffd_data_handler	= _uffd_data_handler,				\
-	.uffd_pt_handler	= uffd_pt_write_handler,			\
+	.uffd_pt_handler	= uffd_pt_handler,				\
 	.mmio_handler		= _mmio_handler,				\
 	.expected_events	= { .mmio_exits = _mmio_exits,			\
 				    .uffd_faults = _uffd_faults },		\
@@ -889,10 +893,11 @@ static void help(char *name)
 {										\
 	.name			= SCAT2(ro_memslot_no_syndrome, _access),	\
 	.data_memslot_flags	= KVM_MEM_READONLY,				\
+	.pt_memslot_flags	= KVM_MEM_READONLY,				\
 	.mem_mark_cmd		= CMD_HOLE_DATA | CMD_HOLE_PT,			\
 	.guest_test		= _access,					\
 	.uffd_data_handler	= _uffd_data_handler,				\
-	.uffd_pt_handler	= uffd_pt_write_handler,			\
+	.uffd_pt_handler	= uffd_pt_handler,			\
 	.fail_vcpu_run_handler	= fail_vcpu_run_mmio_no_syndrome_handler,	\
 	.expected_events	= { .fail_vcpu_runs = 1,			\
 				    .uffd_faults = _uffd_faults },		\
@@ -933,44 +938,51 @@ static struct test_desc tests[] = {
 	 * (S1PTW).
 	 */
 	TEST_UFFD(guest_read64, with_af, CMD_HOLE_DATA | CMD_HOLE_PT,
-		  uffd_data_read_handler, uffd_pt_write_handler, 2),
-	/* no_af should also lead to a PT write. */
+		  uffd_data_handler, uffd_pt_handler, 2),
 	TEST_UFFD(guest_read64, no_af, CMD_HOLE_DATA | CMD_HOLE_PT,
-		  uffd_data_read_handler, uffd_pt_write_handler, 2),
-	/* Note how that cas invokes the read handler. */
+		  uffd_data_handler, uffd_pt_handler, 2),
 	TEST_UFFD(guest_cas, with_af, CMD_HOLE_DATA | CMD_HOLE_PT,
-		  uffd_data_read_handler, uffd_pt_write_handler, 2),
+		  uffd_data_handler, uffd_pt_handler, 2),
 	/*
 	 * Can't test guest_at with_af as it's IMPDEF whether the AF is set.
 	 * The S1PTW fault should still be marked as a write.
 	 */
 	TEST_UFFD(guest_at, no_af, CMD_HOLE_DATA | CMD_HOLE_PT,
-		  uffd_data_read_handler, uffd_pt_write_handler, 1),
+		  uffd_no_handler, uffd_pt_handler, 1),
 	TEST_UFFD(guest_ld_preidx, with_af, CMD_HOLE_DATA | CMD_HOLE_PT,
-		  uffd_data_read_handler, uffd_pt_write_handler, 2),
+		  uffd_data_handler, uffd_pt_handler, 2),
 	TEST_UFFD(guest_write64, with_af, CMD_HOLE_DATA | CMD_HOLE_PT,
-		  uffd_data_write_handler, uffd_pt_write_handler, 2),
+		  uffd_data_handler, uffd_pt_handler, 2),
 	TEST_UFFD(guest_dc_zva, with_af, CMD_HOLE_DATA | CMD_HOLE_PT,
-		  uffd_data_write_handler, uffd_pt_write_handler, 2),
+		  uffd_data_handler, uffd_pt_handler, 2),
 	TEST_UFFD(guest_st_preidx, with_af, CMD_HOLE_DATA | CMD_HOLE_PT,
-		  uffd_data_write_handler, uffd_pt_write_handler, 2),
+		  uffd_data_handler, uffd_pt_handler, 2),
 	TEST_UFFD(guest_exec, with_af, CMD_HOLE_DATA | CMD_HOLE_PT,
-		  uffd_data_read_handler, uffd_pt_write_handler, 2),
+		  uffd_data_handler, uffd_pt_handler, 2),
 
 	/*
 	 * Try accesses when the data and PT memory regions are both
 	 * tracked for dirty logging.
 	 */
-	TEST_DIRTY_LOG(guest_read64, with_af, guest_check_no_write_in_dirty_log),
-	/* no_af should also lead to a PT write. */
-	TEST_DIRTY_LOG(guest_read64, no_af, guest_check_no_write_in_dirty_log),
-	TEST_DIRTY_LOG(guest_ld_preidx, with_af, guest_check_no_write_in_dirty_log),
-	TEST_DIRTY_LOG(guest_at, no_af, guest_check_no_write_in_dirty_log),
-	TEST_DIRTY_LOG(guest_exec, with_af, guest_check_no_write_in_dirty_log),
-	TEST_DIRTY_LOG(guest_write64, with_af, guest_check_write_in_dirty_log),
-	TEST_DIRTY_LOG(guest_cas, with_af, guest_check_write_in_dirty_log),
-	TEST_DIRTY_LOG(guest_dc_zva, with_af, guest_check_write_in_dirty_log),
-	TEST_DIRTY_LOG(guest_st_preidx, with_af, guest_check_write_in_dirty_log),
+	TEST_DIRTY_LOG(guest_read64, with_af, guest_check_no_write_in_dirty_log,
+		       guest_check_s1ptw_wr_in_dirty_log),
+	TEST_DIRTY_LOG(guest_read64, no_af, guest_check_no_write_in_dirty_log,
+		       guest_check_no_s1ptw_wr_in_dirty_log),
+	TEST_DIRTY_LOG(guest_ld_preidx, with_af,
+		       guest_check_no_write_in_dirty_log,
+		       guest_check_s1ptw_wr_in_dirty_log),
+	TEST_DIRTY_LOG(guest_at, no_af, guest_check_no_write_in_dirty_log,
+		       guest_check_no_s1ptw_wr_in_dirty_log),
+	TEST_DIRTY_LOG(guest_exec, with_af, guest_check_no_write_in_dirty_log,
+		       guest_check_s1ptw_wr_in_dirty_log),
+	TEST_DIRTY_LOG(guest_write64, with_af, guest_check_write_in_dirty_log,
+		       guest_check_s1ptw_wr_in_dirty_log),
+	TEST_DIRTY_LOG(guest_cas, with_af, guest_check_write_in_dirty_log,
+		       guest_check_s1ptw_wr_in_dirty_log),
+	TEST_DIRTY_LOG(guest_dc_zva, with_af, guest_check_write_in_dirty_log,
+		       guest_check_s1ptw_wr_in_dirty_log),
+	TEST_DIRTY_LOG(guest_st_preidx, with_af, guest_check_write_in_dirty_log,
+		       guest_check_s1ptw_wr_in_dirty_log),
 
 	/*
 	 * Access when the data and PT memory regions are both marked for
@@ -980,29 +992,43 @@ static struct test_desc tests[] = {
 	 * fault, and nothing in the dirty log.  Any S1PTW should result in
 	 * a write in the dirty log and a userfaultfd write.
 	 */
-	TEST_UFFD_AND_DIRTY_LOG(guest_read64, with_af, uffd_data_read_handler, 2,
-				guest_check_no_write_in_dirty_log),
-	/* no_af should also lead to a PT write. */
-	TEST_UFFD_AND_DIRTY_LOG(guest_read64, no_af, uffd_data_read_handler, 2,
-				guest_check_no_write_in_dirty_log),
-	TEST_UFFD_AND_DIRTY_LOG(guest_ld_preidx, with_af, uffd_data_read_handler,
-				2, guest_check_no_write_in_dirty_log),
-	TEST_UFFD_AND_DIRTY_LOG(guest_at, with_af, 0, 1,
-				guest_check_no_write_in_dirty_log),
-	TEST_UFFD_AND_DIRTY_LOG(guest_exec, with_af, uffd_data_read_handler, 2,
-				guest_check_no_write_in_dirty_log),
-	TEST_UFFD_AND_DIRTY_LOG(guest_write64, with_af, uffd_data_write_handler,
-				2, guest_check_write_in_dirty_log),
-	TEST_UFFD_AND_DIRTY_LOG(guest_cas, with_af, uffd_data_read_handler, 2,
-				guest_check_write_in_dirty_log),
-	TEST_UFFD_AND_DIRTY_LOG(guest_dc_zva, with_af, uffd_data_write_handler,
-				2, guest_check_write_in_dirty_log),
+	TEST_UFFD_AND_DIRTY_LOG(guest_read64, with_af,
+				uffd_data_handler, 2,
+				guest_check_no_write_in_dirty_log,
+				guest_check_s1ptw_wr_in_dirty_log),
+	TEST_UFFD_AND_DIRTY_LOG(guest_read64, no_af,
+				uffd_data_handler, 2,
+				guest_check_no_write_in_dirty_log,
+				guest_check_no_s1ptw_wr_in_dirty_log),
+	TEST_UFFD_AND_DIRTY_LOG(guest_ld_preidx, with_af,
+				uffd_data_handler,
+				2, guest_check_no_write_in_dirty_log,
+				guest_check_s1ptw_wr_in_dirty_log),
+	TEST_UFFD_AND_DIRTY_LOG(guest_at, with_af, uffd_no_handler, 1,
+				guest_check_no_write_in_dirty_log,
+				guest_check_s1ptw_wr_in_dirty_log),
+	TEST_UFFD_AND_DIRTY_LOG(guest_exec, with_af,
+				uffd_data_handler, 2,
+				guest_check_no_write_in_dirty_log,
+				guest_check_s1ptw_wr_in_dirty_log),
+	TEST_UFFD_AND_DIRTY_LOG(guest_write64, with_af,
+				uffd_data_handler,
+				2, guest_check_write_in_dirty_log,
+				guest_check_s1ptw_wr_in_dirty_log),
+	TEST_UFFD_AND_DIRTY_LOG(guest_cas, with_af,
+				uffd_data_handler, 2,
+				guest_check_write_in_dirty_log,
+				guest_check_s1ptw_wr_in_dirty_log),
+	TEST_UFFD_AND_DIRTY_LOG(guest_dc_zva, with_af,
+				uffd_data_handler,
+				2, guest_check_write_in_dirty_log,
+				guest_check_s1ptw_wr_in_dirty_log),
 	TEST_UFFD_AND_DIRTY_LOG(guest_st_preidx, with_af,
-				uffd_data_write_handler, 2,
-				guest_check_write_in_dirty_log),
-
+				uffd_data_handler, 2,
+				guest_check_write_in_dirty_log,
+				guest_check_s1ptw_wr_in_dirty_log),
 	/*
-	 * Try accesses when the data memory region is marked read-only
+	 * Access when both the PT and data regions are marked read-only
 	 * (with KVM_MEM_READONLY). Writes with a syndrome result in an
 	 * MMIO exit, writes with no syndrome (e.g., CAS) result in a
 	 * failed vcpu run, and reads/execs with and without syndroms do
@@ -1018,7 +1044,7 @@ static struct test_desc tests[] = {
 	TEST_RO_MEMSLOT_NO_SYNDROME(guest_st_preidx),
 
 	/*
-	 * Access when both the data region is both read-only and marked
+	 * The PT and data regions are both read-only and marked
 	 * for dirty logging at the same time. The expected result is that
 	 * for writes there should be no write in the dirty log. The
 	 * readonly handling is the same as if the memslot was not marked
@@ -1043,7 +1069,7 @@ static struct test_desc tests[] = {
 						  guest_check_no_write_in_dirty_log),
 
 	/*
-	 * Access when the data region is both read-only and punched with
+	 * The PT and data regions are both read-only and punched with
 	 * holes tracked with userfaultfd.  The expected result is the
 	 * union of both userfaultfd and read-only behaviors. For example,
 	 * write accesses result in a userfaultfd write fault and an MMIO
@@ -1051,22 +1077,15 @@ static struct test_desc tests[] = {
 	 * no userfaultfd write fault. Reads result in userfaultfd getting
 	 * triggered.
 	 */
-	TEST_RO_MEMSLOT_AND_UFFD(guest_read64, 0, 0,
-				 uffd_data_read_handler, 2),
-	TEST_RO_MEMSLOT_AND_UFFD(guest_ld_preidx, 0, 0,
-				 uffd_data_read_handler, 2),
-	TEST_RO_MEMSLOT_AND_UFFD(guest_at, 0, 0,
-				 uffd_no_handler, 1),
-	TEST_RO_MEMSLOT_AND_UFFD(guest_exec, 0, 0,
-				 uffd_data_read_handler, 2),
+	TEST_RO_MEMSLOT_AND_UFFD(guest_read64, 0, 0, uffd_data_handler, 2),
+	TEST_RO_MEMSLOT_AND_UFFD(guest_ld_preidx, 0, 0, uffd_data_handler, 2),
+	TEST_RO_MEMSLOT_AND_UFFD(guest_at, 0, 0, uffd_no_handler, 1),
+	TEST_RO_MEMSLOT_AND_UFFD(guest_exec, 0, 0, uffd_data_handler, 2),
 	TEST_RO_MEMSLOT_AND_UFFD(guest_write64, mmio_on_test_gpa_handler, 1,
-				 uffd_data_write_handler, 2),
-	TEST_RO_MEMSLOT_NO_SYNDROME_AND_UFFD(guest_cas,
-					     uffd_data_read_handler, 2),
-	TEST_RO_MEMSLOT_NO_SYNDROME_AND_UFFD(guest_dc_zva,
-					     uffd_no_handler, 1),
-	TEST_RO_MEMSLOT_NO_SYNDROME_AND_UFFD(guest_st_preidx,
-					     uffd_no_handler, 1),
+				 uffd_data_handler, 2),
+	TEST_RO_MEMSLOT_NO_SYNDROME_AND_UFFD(guest_cas, uffd_data_handler, 2),
+	TEST_RO_MEMSLOT_NO_SYNDROME_AND_UFFD(guest_dc_zva, uffd_no_handler, 1),
+	TEST_RO_MEMSLOT_NO_SYNDROME_AND_UFFD(guest_st_preidx, uffd_no_handler, 1),
 
 	{ 0 }
 };
diff --git a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c
index ea0978f22db8..251794f83719 100644
--- a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c
+++ b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c
@@ -241,7 +241,7 @@ int main(int argc, char **argv)
 	while ((opt = getopt(argc, argv, "hp:t:r")) != -1) {
 		switch (opt) {
 		case 'p':
-			reclaim_period_ms = atoi_non_negative("Reclaim period", optarg);
+			reclaim_period_ms = atoi_positive("Reclaim period", optarg);
 			break;
 		case 't':
 			token = atoi_paranoid(optarg);
diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
index dae510c263b4..13c75dc18c10 100644
--- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
@@ -434,6 +434,7 @@ static void *juggle_shinfo_state(void *arg)
 int main(int argc, char *argv[])
 {
 	struct timespec min_ts, max_ts, vm_ts;
+	struct kvm_xen_hvm_attr evt_reset;
 	struct kvm_vm *vm;
 	pthread_t thread;
 	bool verbose;
@@ -962,10 +963,8 @@ int main(int argc, char *argv[])
 	}
 
  done:
-	struct kvm_xen_hvm_attr evt_reset = {
-		.type = KVM_XEN_ATTR_TYPE_EVTCHN,
-		.u.evtchn.flags = KVM_XEN_EVTCHN_RESET,
-	};
+	evt_reset.type = KVM_XEN_ATTR_TYPE_EVTCHN;
+	evt_reset.u.evtchn.flags = KVM_XEN_EVTCHN_RESET;
 	vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &evt_reset);
 
 	alarm(0);
diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk
index 291144c284fb..f7900e75d230 100644
--- a/tools/testing/selftests/lib.mk
+++ b/tools/testing/selftests/lib.mk
@@ -20,7 +20,7 @@ CLANG_TARGET_FLAGS              := $(CLANG_TARGET_FLAGS_$(ARCH))
 
 ifeq ($(CROSS_COMPILE),)
 ifeq ($(CLANG_TARGET_FLAGS),)
-$(error Specify CROSS_COMPILE or add '--target=' option to lib.mk
+$(error Specify CROSS_COMPILE or add '--target=' option to lib.mk)
 else
 CLANG_FLAGS     += --target=$(CLANG_TARGET_FLAGS)
 endif # CLANG_TARGET_FLAGS
diff --git a/tools/testing/selftests/net/af_unix/test_unix_oob.c b/tools/testing/selftests/net/af_unix/test_unix_oob.c
index b57e91e1c3f2..532459a15067 100644
--- a/tools/testing/selftests/net/af_unix/test_unix_oob.c
+++ b/tools/testing/selftests/net/af_unix/test_unix_oob.c
@@ -124,7 +124,7 @@ void producer(struct sockaddr_un *consumer_addr)
 
 	wait_for_signal(pipefd[0]);
 	if (connect(cfd, (struct sockaddr *)consumer_addr,
-		     sizeof(struct sockaddr)) != 0) {
+		     sizeof(*consumer_addr)) != 0) {
 		perror("Connect failed");
 		kill(0, SIGTERM);
 		exit(1);
diff --git a/tools/testing/selftests/net/cmsg_ipv6.sh b/tools/testing/selftests/net/cmsg_ipv6.sh
index 2d89cb0ad288..330d0b1ceced 100755
--- a/tools/testing/selftests/net/cmsg_ipv6.sh
+++ b/tools/testing/selftests/net/cmsg_ipv6.sh
@@ -6,7 +6,7 @@ ksft_skip=4
 NS=ns
 IP6=2001:db8:1::1/64
 TGT6=2001:db8:1::2
-TMPF=`mktemp`
+TMPF=$(mktemp --suffix ".pcap")
 
 cleanup()
 {
diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh
index c245476fa29d..63c3eaec8d30 100755
--- a/tools/testing/selftests/net/fib_rule_tests.sh
+++ b/tools/testing/selftests/net/fib_rule_tests.sh
@@ -10,8 +10,10 @@ ret=0
 
 PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no}
 IP="ip -netns testns"
+IP_PEER="ip -netns peerns"
 
 RTABLE=100
+RTABLE_PEER=101
 GW_IP4=192.51.100.2
 SRC_IP=192.51.100.3
 GW_IP6=2001:db8:1::2
@@ -20,7 +22,9 @@ SRC_IP6=2001:db8:1::3
 DEV_ADDR=192.51.100.1
 DEV_ADDR6=2001:db8:1::1
 DEV=dummy0
-TESTS="fib_rule6 fib_rule4"
+TESTS="fib_rule6 fib_rule4 fib_rule6_connect fib_rule4_connect"
+
+SELFTEST_PATH=""
 
 log_test()
 {
@@ -52,6 +56,31 @@ log_section()
 	echo "######################################################################"
 }
 
+check_nettest()
+{
+	if which nettest > /dev/null 2>&1; then
+		return 0
+	fi
+
+	# Add the selftest directory to PATH if not already done
+	if [ "${SELFTEST_PATH}" = "" ]; then
+		SELFTEST_PATH="$(dirname $0)"
+		PATH="${PATH}:${SELFTEST_PATH}"
+
+		# Now retry with the new path
+		if which nettest > /dev/null 2>&1; then
+			return 0
+		fi
+
+		if [ "${ret}" -eq 0 ]; then
+			ret="${ksft_skip}"
+		fi
+		echo "nettest not found (try 'make -C ${SELFTEST_PATH} nettest')"
+	fi
+
+	return 1
+}
+
 setup()
 {
 	set -e
@@ -72,6 +101,39 @@ cleanup()
 	ip netns del testns
 }
 
+setup_peer()
+{
+	set -e
+
+	ip netns add peerns
+	$IP_PEER link set dev lo up
+
+	ip link add name veth0 netns testns type veth \
+		peer name veth1 netns peerns
+	$IP link set dev veth0 up
+	$IP_PEER link set dev veth1 up
+
+	$IP address add 192.0.2.10 peer 192.0.2.11/32 dev veth0
+	$IP_PEER address add 192.0.2.11 peer 192.0.2.10/32 dev veth1
+
+	$IP address add 2001:db8::10 peer 2001:db8::11/128 dev veth0 nodad
+	$IP_PEER address add 2001:db8::11 peer 2001:db8::10/128 dev veth1 nodad
+
+	$IP_PEER address add 198.51.100.11/32 dev lo
+	$IP route add table $RTABLE_PEER 198.51.100.11/32 via 192.0.2.11
+
+	$IP_PEER address add 2001:db8::1:11/128 dev lo
+	$IP route add table $RTABLE_PEER 2001:db8::1:11/128 via 2001:db8::11
+
+	set +e
+}
+
+cleanup_peer()
+{
+	$IP link del dev veth0
+	ip netns del peerns
+}
+
 fib_check_iproute_support()
 {
 	ip rule help 2>&1 | grep -q $1
@@ -190,6 +252,37 @@ fib_rule6_test()
 	fi
 }
 
+# Verify that the IPV6_TCLASS option of UDPv6 and TCPv6 sockets is properly
+# taken into account when connecting the socket and when sending packets.
+fib_rule6_connect_test()
+{
+	local dsfield
+
+	if ! check_nettest; then
+		echo "SKIP: Could not run test without nettest tool"
+		return
+	fi
+
+	setup_peer
+	$IP -6 rule add dsfield 0x04 table $RTABLE_PEER
+
+	# Combine the base DS Field value (0x04) with all possible ECN values
+	# (Not-ECT: 0, ECT(1): 1, ECT(0): 2, CE: 3).
+	# The ECN bits shouldn't influence the result of the test.
+	for dsfield in 0x04 0x05 0x06 0x07; do
+		nettest -q -6 -B -t 5 -N testns -O peerns -U -D \
+			-Q "${dsfield}" -l 2001:db8::1:11 -r 2001:db8::1:11
+		log_test $? 0 "rule6 dsfield udp connect (dsfield ${dsfield})"
+
+		nettest -q -6 -B -t 5 -N testns -O peerns -Q "${dsfield}" \
+			-l 2001:db8::1:11 -r 2001:db8::1:11
+		log_test $? 0 "rule6 dsfield tcp connect (dsfield ${dsfield})"
+	done
+
+	$IP -6 rule del dsfield 0x04 table $RTABLE_PEER
+	cleanup_peer
+}
+
 fib_rule4_del()
 {
 	$IP rule del $1
@@ -296,6 +389,37 @@ fib_rule4_test()
 	fi
 }
 
+# Verify that the IP_TOS option of UDPv4 and TCPv4 sockets is properly taken
+# into account when connecting the socket and when sending packets.
+fib_rule4_connect_test()
+{
+	local dsfield
+
+	if ! check_nettest; then
+		echo "SKIP: Could not run test without nettest tool"
+		return
+	fi
+
+	setup_peer
+	$IP -4 rule add dsfield 0x04 table $RTABLE_PEER
+
+	# Combine the base DS Field value (0x04) with all possible ECN values
+	# (Not-ECT: 0, ECT(1): 1, ECT(0): 2, CE: 3).
+	# The ECN bits shouldn't influence the result of the test.
+	for dsfield in 0x04 0x05 0x06 0x07; do
+		nettest -q -B -t 5 -N testns -O peerns -D -U -Q "${dsfield}" \
+			-l 198.51.100.11 -r 198.51.100.11
+		log_test $? 0 "rule4 dsfield udp connect (dsfield ${dsfield})"
+
+		nettest -q -B -t 5 -N testns -O peerns -Q "${dsfield}" \
+			-l 198.51.100.11 -r 198.51.100.11
+		log_test $? 0 "rule4 dsfield tcp connect (dsfield ${dsfield})"
+	done
+
+	$IP -4 rule del dsfield 0x04 table $RTABLE_PEER
+	cleanup_peer
+}
+
 run_fibrule_tests()
 {
 	log_section "IPv4 fib rule"
@@ -345,6 +469,8 @@ do
 	case $t in
 	fib_rule6_test|fib_rule6)		fib_rule6_test;;
 	fib_rule4_test|fib_rule4)		fib_rule4_test;;
+	fib_rule6_connect_test|fib_rule6_connect)	fib_rule6_connect_test;;
+	fib_rule4_connect_test|fib_rule4_connect)	fib_rule4_connect_test;;
 
 	help) echo "Test names: $TESTS"; exit 0;;
 
diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 1c4f866de7d7..3d8e4ebda1b6 100755
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -914,14 +914,14 @@ sysctl_set()
 	local value=$1; shift
 
 	SYSCTL_ORIG[$key]=$(sysctl -n $key)
-	sysctl -qw $key=$value
+	sysctl -qw $key="$value"
 }
 
 sysctl_restore()
 {
 	local key=$1; shift
 
-	sysctl -qw $key=${SYSCTL_ORIG["$key"]}
+	sysctl -qw $key="${SYSCTL_ORIG[$key]}"
 }
 
 forwarding_enable()
diff --git a/tools/testing/selftests/net/l2_tos_ttl_inherit.sh b/tools/testing/selftests/net/l2_tos_ttl_inherit.sh
index dca1e6f777a8..f11756e7df2f 100755
--- a/tools/testing/selftests/net/l2_tos_ttl_inherit.sh
+++ b/tools/testing/selftests/net/l2_tos_ttl_inherit.sh
@@ -12,19 +12,27 @@
 # In addition this script also checks if forcing a specific field in the
 # outer header is working.
 
+# Return 4 by default (Kselftest SKIP code)
+ERR=4
+
 if [ "$(id -u)" != "0" ]; then
 	echo "Please run as root."
-	exit 0
+	exit $ERR
 fi
 if ! which tcpdump > /dev/null 2>&1; then
 	echo "No tcpdump found. Required for this test."
-	exit 0
+	exit $ERR
 fi
 
 expected_tos="0x00"
 expected_ttl="0"
 failed=false
 
+readonly NS0=$(mktemp -u ns0-XXXXXXXX)
+readonly NS1=$(mktemp -u ns1-XXXXXXXX)
+
+RUN_NS0="ip netns exec ${NS0}"
+
 get_random_tos() {
 	# Get a random hex tos value between 0x00 and 0xfc, a multiple of 4
 	echo "0x$(tr -dc '0-9a-f' < /dev/urandom | head -c 1)\
@@ -61,7 +69,6 @@ setup() {
 	local vlan="$5"
 	local test_tos="0x00"
 	local test_ttl="0"
-	local ns="ip netns exec testing"
 
 	# We don't want a test-tos of 0x00,
 	# because this is the value that we get when no tos is set.
@@ -94,14 +101,15 @@ setup() {
 	printf "│%7s │%6s │%6s │%13s │%13s │%6s │" \
 	"$type" "$outer" "$inner" "$tos" "$ttl" "$vlan"
 
-	# Create 'testing' netns, veth pair and connect main ns with testing ns
-	ip netns add testing
-	ip link add type veth
-	ip link set veth1 netns testing
-	ip link set veth0 up
-	$ns ip link set veth1 up
-	ip addr flush dev veth0
-	$ns ip addr flush dev veth1
+	# Create netns NS0 and NS1 and connect them with a veth pair
+	ip netns add "${NS0}"
+	ip netns add "${NS1}"
+	ip link add name veth0 netns "${NS0}" type veth \
+		peer name veth1 netns "${NS1}"
+	ip -netns "${NS0}" link set dev veth0 up
+	ip -netns "${NS1}" link set dev veth1 up
+	ip -netns "${NS0}" address flush dev veth0
+	ip -netns "${NS1}" address flush dev veth1
 
 	local local_addr1=""
 	local local_addr2=""
@@ -127,51 +135,59 @@ setup() {
 		if [ "$type" = "gre" ]; then
 			type="gretap"
 		fi
-		ip addr add 198.18.0.1/24 dev veth0
-		$ns ip addr add 198.18.0.2/24 dev veth1
-		ip link add name tep0 type $type $local_addr1 remote \
-		198.18.0.2 tos $test_tos ttl $test_ttl $vxlan $geneve
-		$ns ip link add name tep1 type $type $local_addr2 remote \
-		198.18.0.1 tos $test_tos ttl $test_ttl $vxlan $geneve
+		ip -netns "${NS0}" address add 198.18.0.1/24 dev veth0
+		ip -netns "${NS1}" address add 198.18.0.2/24 dev veth1
+		ip -netns "${NS0}" link add name tep0 type $type $local_addr1 \
+			remote 198.18.0.2 tos $test_tos ttl $test_ttl         \
+			$vxlan $geneve
+		ip -netns "${NS1}" link add name tep1 type $type $local_addr2 \
+			remote 198.18.0.1 tos $test_tos ttl $test_ttl         \
+			$vxlan $geneve
 	elif [ "$outer" = "6" ]; then
 		if [ "$type" = "gre" ]; then
 			type="ip6gretap"
 		fi
-		ip addr add fdd1:ced0:5d88:3fce::1/64 dev veth0
-		$ns ip addr add fdd1:ced0:5d88:3fce::2/64 dev veth1
-		ip link add name tep0 type $type $local_addr1 \
-		remote fdd1:ced0:5d88:3fce::2 tos $test_tos ttl $test_ttl \
-		$vxlan $geneve
-		$ns ip link add name tep1 type $type $local_addr2 \
-		remote fdd1:ced0:5d88:3fce::1 tos $test_tos ttl $test_ttl \
-		$vxlan $geneve
+		ip -netns "${NS0}" address add fdd1:ced0:5d88:3fce::1/64 \
+			dev veth0 nodad
+		ip -netns "${NS1}" address add fdd1:ced0:5d88:3fce::2/64 \
+			dev veth1 nodad
+		ip -netns "${NS0}" link add name tep0 type $type $local_addr1 \
+			remote fdd1:ced0:5d88:3fce::2 tos $test_tos           \
+			ttl $test_ttl $vxlan $geneve
+		ip -netns "${NS1}" link add name tep1 type $type $local_addr2 \
+			remote fdd1:ced0:5d88:3fce::1 tos $test_tos           \
+			ttl $test_ttl $vxlan $geneve
 	fi
 
 	# Bring L2-tunnel link up and create VLAN on top
-	ip link set tep0 up
-	$ns ip link set tep1 up
-	ip addr flush dev tep0
-	$ns ip addr flush dev tep1
+	ip -netns "${NS0}" link set tep0 up
+	ip -netns "${NS1}" link set tep1 up
+	ip -netns "${NS0}" address flush dev tep0
+	ip -netns "${NS1}" address flush dev tep1
 	local parent
 	if $vlan; then
 		parent="vlan99-"
-		ip link add link tep0 name ${parent}0 type vlan id 99
-		$ns ip link add link tep1 name ${parent}1 type vlan id 99
-		ip link set ${parent}0 up
-		$ns ip link set ${parent}1 up
-		ip addr flush dev ${parent}0
-		$ns ip addr flush dev ${parent}1
+		ip -netns "${NS0}" link add link tep0 name ${parent}0 \
+			type vlan id 99
+		ip -netns "${NS1}" link add link tep1 name ${parent}1 \
+			type vlan id 99
+		ip -netns "${NS0}" link set dev ${parent}0 up
+		ip -netns "${NS1}" link set dev ${parent}1 up
+		ip -netns "${NS0}" address flush dev ${parent}0
+		ip -netns "${NS1}" address flush dev ${parent}1
 	else
 		parent="tep"
 	fi
 
 	# Assign inner IPv4/IPv6 addresses
 	if [ "$inner" = "4" ] || [ "$inner" = "other" ]; then
-		ip addr add 198.19.0.1/24 brd + dev ${parent}0
-		$ns ip addr add 198.19.0.2/24 brd + dev ${parent}1
+		ip -netns "${NS0}" address add 198.19.0.1/24 brd + dev ${parent}0
+		ip -netns "${NS1}" address add 198.19.0.2/24 brd + dev ${parent}1
 	elif [ "$inner" = "6" ]; then
-		ip addr add fdd4:96cf:4eae:443b::1/64 dev ${parent}0
-		$ns ip addr add fdd4:96cf:4eae:443b::2/64 dev ${parent}1
+		ip -netns "${NS0}" address add fdd4:96cf:4eae:443b::1/64 \
+			dev ${parent}0 nodad
+		ip -netns "${NS1}" address add fdd4:96cf:4eae:443b::2/64 \
+			dev ${parent}1 nodad
 	fi
 }
 
@@ -192,10 +208,10 @@ verify() {
 		ping_dst="198.19.0.3" # Generates ARPs which are not IPv4/IPv6
 	fi
 	if [ "$tos_ttl" = "inherit" ]; then
-		ping -i 0.1 $ping_dst -Q "$expected_tos" -t "$expected_ttl" \
-		2>/dev/null 1>&2 & ping_pid="$!"
+		${RUN_NS0} ping -i 0.1 $ping_dst -Q "$expected_tos"          \
+			 -t "$expected_ttl" 2>/dev/null 1>&2 & ping_pid="$!"
 	else
-		ping -i 0.1 $ping_dst 2>/dev/null 1>&2 & ping_pid="$!"
+		${RUN_NS0} ping -i 0.1 $ping_dst 2>/dev/null 1>&2 & ping_pid="$!"
 	fi
 	local tunnel_type_offset tunnel_type_proto req_proto_offset req_offset
 	if [ "$type" = "gre" ]; then
@@ -216,10 +232,12 @@ verify() {
 				req_proto_offset="$((req_proto_offset + 4))"
 				req_offset="$((req_offset + 4))"
 			fi
-			out="$(tcpdump --immediate-mode -p -c 1 -v -i veth0 -n \
-			ip[$tunnel_type_offset] = $tunnel_type_proto and \
-			ip[$req_proto_offset] = 0x01 and \
-			ip[$req_offset] = 0x08 2>/dev/null | head -n 1)"
+			out="$(${RUN_NS0} tcpdump --immediate-mode -p -c 1 -v \
+				-i veth0 -n                                   \
+				ip[$tunnel_type_offset] = $tunnel_type_proto and \
+				ip[$req_proto_offset] = 0x01 and              \
+				ip[$req_offset] = 0x08 2>/dev/null            \
+				| head -n 1)"
 		elif [ "$inner" = "6" ]; then
 			req_proto_offset="44"
 			req_offset="78"
@@ -231,10 +249,12 @@ verify() {
 				req_proto_offset="$((req_proto_offset + 4))"
 				req_offset="$((req_offset + 4))"
 			fi
-			out="$(tcpdump --immediate-mode -p -c 1 -v -i veth0 -n \
-			ip[$tunnel_type_offset] = $tunnel_type_proto and \
-			ip[$req_proto_offset] = 0x3a and \
-			ip[$req_offset] = 0x80 2>/dev/null | head -n 1)"
+			out="$(${RUN_NS0} tcpdump --immediate-mode -p -c 1 -v \
+				-i veth0 -n                                   \
+				ip[$tunnel_type_offset] = $tunnel_type_proto and \
+				ip[$req_proto_offset] = 0x3a and              \
+				ip[$req_offset] = 0x80 2>/dev/null            \
+				| head -n 1)"
 		elif [ "$inner" = "other" ]; then
 			req_proto_offset="36"
 			req_offset="45"
@@ -250,11 +270,13 @@ verify() {
 				expected_tos="0x00"
 				expected_ttl="64"
 			fi
-			out="$(tcpdump --immediate-mode -p -c 1 -v -i veth0 -n \
-			ip[$tunnel_type_offset] = $tunnel_type_proto and \
-			ip[$req_proto_offset] = 0x08 and \
-			ip[$((req_proto_offset + 1))] = 0x06 and \
-			ip[$req_offset] = 0x01 2>/dev/null | head -n 1)"
+			out="$(${RUN_NS0} tcpdump --immediate-mode -p -c 1 -v \
+				-i veth0 -n                                   \
+				ip[$tunnel_type_offset] = $tunnel_type_proto and \
+				ip[$req_proto_offset] = 0x08 and              \
+				ip[$((req_proto_offset + 1))] = 0x06 and      \
+				ip[$req_offset] = 0x01 2>/dev/null            \
+				| head -n 1)"
 		fi
 	elif [ "$outer" = "6" ]; then
 		if [ "$type" = "gre" ]; then
@@ -273,10 +295,12 @@ verify() {
 				req_proto_offset="$((req_proto_offset + 4))"
 				req_offset="$((req_offset + 4))"
 			fi
-			out="$(tcpdump --immediate-mode -p -c 1 -v -i veth0 -n \
-			ip6[$tunnel_type_offset] = $tunnel_type_proto and \
-			ip6[$req_proto_offset] = 0x01 and \
-			ip6[$req_offset] = 0x08 2>/dev/null | head -n 1)"
+			out="$(${RUN_NS0} tcpdump --immediate-mode -p -c 1 -v \
+				-i veth0 -n                                   \
+				ip6[$tunnel_type_offset] = $tunnel_type_proto and \
+				ip6[$req_proto_offset] = 0x01 and             \
+				ip6[$req_offset] = 0x08 2>/dev/null           \
+				| head -n 1)"
 		elif [ "$inner" = "6" ]; then
 			local req_proto_offset="72"
 			local req_offset="106"
@@ -288,10 +312,12 @@ verify() {
 				req_proto_offset="$((req_proto_offset + 4))"
 				req_offset="$((req_offset + 4))"
 			fi
-			out="$(tcpdump --immediate-mode -p -c 1 -v -i veth0 -n \
-			ip6[$tunnel_type_offset] = $tunnel_type_proto and \
-			ip6[$req_proto_offset] = 0x3a and \
-			ip6[$req_offset] = 0x80 2>/dev/null | head -n 1)"
+			out="$(${RUN_NS0} tcpdump --immediate-mode -p -c 1 -v \
+				-i veth0 -n                                   \
+				ip6[$tunnel_type_offset] = $tunnel_type_proto and \
+				ip6[$req_proto_offset] = 0x3a and             \
+				ip6[$req_offset] = 0x80 2>/dev/null           \
+				| head -n 1)"
 		elif [ "$inner" = "other" ]; then
 			local req_proto_offset="64"
 			local req_offset="73"
@@ -307,15 +333,17 @@ verify() {
 				expected_tos="0x00"
 				expected_ttl="64"
 			fi
-			out="$(tcpdump --immediate-mode -p -c 1 -v -i veth0 -n \
-			ip6[$tunnel_type_offset] = $tunnel_type_proto and \
-			ip6[$req_proto_offset] = 0x08 and \
-			ip6[$((req_proto_offset + 1))] = 0x06 and \
-			ip6[$req_offset] = 0x01 2>/dev/null | head -n 1)"
+			out="$(${RUN_NS0} tcpdump --immediate-mode -p -c 1 -v \
+				-i veth0 -n                                   \
+				ip6[$tunnel_type_offset] = $tunnel_type_proto and \
+				ip6[$req_proto_offset] = 0x08 and             \
+				ip6[$((req_proto_offset + 1))] = 0x06 and     \
+				ip6[$req_offset] = 0x01 2>/dev/null           \
+				| head -n 1)"
 		fi
 	fi
 	kill -9 $ping_pid
-	wait $ping_pid 2>/dev/null
+	wait $ping_pid 2>/dev/null || true
 	result="FAIL"
 	if [ "$outer" = "4" ]; then
 		captured_ttl="$(get_field "ttl" "$out")"
@@ -351,11 +379,35 @@ verify() {
 }
 
 cleanup() {
-	ip link del veth0 2>/dev/null
-	ip netns del testing 2>/dev/null
-	ip link del tep0 2>/dev/null
+	ip netns del "${NS0}" 2>/dev/null
+	ip netns del "${NS1}" 2>/dev/null
 }
 
+exit_handler() {
+	# Don't exit immediately if one of the intermediate commands fails.
+	# We might be called at the end of the script, when the network
+	# namespaces have already been deleted. So cleanup() may fail, but we
+	# still need to run until 'exit $ERR' or the script won't return the
+	# correct error code.
+	set +e
+
+	cleanup
+
+	exit $ERR
+}
+
+# Restore the default SIGINT handler (just in case) and exit.
+# The exit handler will take care of cleaning everything up.
+interrupted() {
+	trap - INT
+
+	exit $ERR
+}
+
+set -e
+trap exit_handler EXIT
+trap interrupted INT
+
 printf "┌────────┬───────┬───────┬──────────────┬"
 printf "──────────────┬───────┬────────┐\n"
 for type in gre vxlan geneve; do
@@ -385,6 +437,10 @@ done
 printf "└────────┴───────┴───────┴──────────────┴"
 printf "──────────────┴───────┴────────┘\n"
 
+# All tests done.
+# Set ERR appropriately: it will be returned by the exit handler.
 if $failed; then
-	exit 1
+	ERR=1
+else
+	ERR=0
 fi
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index d11d3d566608..079f8f46849d 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -498,6 +498,12 @@ kill_events_pids()
 	kill_wait $evts_ns2_pid
 }
 
+kill_tests_wait()
+{
+	kill -SIGUSR1 $(ip netns pids $ns2) $(ip netns pids $ns1)
+	wait
+}
+
 pm_nl_set_limits()
 {
 	local ns=$1
@@ -1694,6 +1700,7 @@ chk_subflow_nr()
 	local subflow_nr=$3
 	local cnt1
 	local cnt2
+	local dump_stats
 
 	if [ -n "${need_title}" ]; then
 		printf "%03u %-36s %s" "${TEST_COUNT}" "${TEST_NAME}" "${msg}"
@@ -1711,7 +1718,12 @@ chk_subflow_nr()
 		echo "[ ok ]"
 	fi
 
-	[ "${dump_stats}" = 1 ] && ( ss -N $ns1 -tOni ; ss -N $ns1 -tOni | grep token; ip -n $ns1 mptcp endpoint )
+	if [ "${dump_stats}" = 1 ]; then
+		ss -N $ns1 -tOni
+		ss -N $ns1 -tOni | grep token
+		ip -n $ns1 mptcp endpoint
+		dump_stats
+	fi
 }
 
 chk_link_usage()
@@ -3049,7 +3061,7 @@ endpoint_tests()
 		pm_nl_set_limits $ns1 2 2
 		pm_nl_set_limits $ns2 2 2
 		pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
-		run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow &
+		run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow 2>/dev/null &
 
 		wait_mpj $ns1
 		pm_nl_check_endpoint 1 "creation" \
@@ -3062,14 +3074,14 @@ endpoint_tests()
 		pm_nl_add_endpoint $ns2 10.0.2.2 flags signal
 		pm_nl_check_endpoint 0 "modif is allowed" \
 			$ns2 10.0.2.2 id 1 flags signal
-		wait
+		kill_tests_wait
 	fi
 
 	if reset "delete and re-add"; then
 		pm_nl_set_limits $ns1 1 1
 		pm_nl_set_limits $ns2 1 1
 		pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow
-		run_tests $ns1 $ns2 10.0.1.1 4 0 0 slow &
+		run_tests $ns1 $ns2 10.0.1.1 4 0 0 speed_20 2>/dev/null &
 
 		wait_mpj $ns2
 		pm_nl_del_endpoint $ns2 2 10.0.2.2
@@ -3079,7 +3091,7 @@ endpoint_tests()
 		pm_nl_add_endpoint $ns2 10.0.2.2 dev ns2eth2 flags subflow
 		wait_mpj $ns2
 		chk_subflow_nr "" "after re-add" 2
-		wait
+		kill_tests_wait
 	fi
 }
 
diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh
index a29deb9fa024..ab2d581f28a1 100755
--- a/tools/testing/selftests/net/mptcp/userspace_pm.sh
+++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh
@@ -752,6 +752,52 @@ test_subflows()
 	   "$server4_token" > /dev/null 2>&1
 }
 
+test_subflows_v4_v6_mix()
+{
+	# Attempt to add a listener at 10.0.2.1:<subflow-port>
+	ip netns exec "$ns1" ./pm_nl_ctl listen 10.0.2.1\
+	   $app6_port > /dev/null 2>&1 &
+	local listener_pid=$!
+
+	# ADD_ADDR4 from server to client machine reusing the subflow port on
+	# the established v6 connection
+	:>"$client_evts"
+	ip netns exec "$ns1" ./pm_nl_ctl ann 10.0.2.1 token "$server6_token" id\
+	   $server_addr_id dev ns1eth2 > /dev/null 2>&1
+	stdbuf -o0 -e0 printf "ADD_ADDR4 id:%d 10.0.2.1 (ns1) => ns2, reuse port\t\t" $server_addr_id
+	sleep 0.5
+	verify_announce_event "$client_evts" "$ANNOUNCED" "$client6_token" "10.0.2.1"\
+			      "$server_addr_id" "$app6_port"
+
+	# CREATE_SUBFLOW from client to server machine
+	:>"$client_evts"
+	ip netns exec "$ns2" ./pm_nl_ctl csf lip 10.0.2.2 lid 23 rip 10.0.2.1 rport\
+	   $app6_port token "$client6_token" > /dev/null 2>&1
+	sleep 0.5
+	verify_subflow_events "$client_evts" "$SUB_ESTABLISHED" "$client6_token"\
+			      "$AF_INET" "10.0.2.2" "10.0.2.1" "$app6_port" "23"\
+			      "$server_addr_id" "ns2" "ns1"
+
+	# Delete the listener from the server ns, if one was created
+	kill_wait $listener_pid
+
+	sport=$(sed --unbuffered -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q' "$client_evts")
+
+	# DESTROY_SUBFLOW from client to server machine
+	:>"$client_evts"
+	ip netns exec "$ns2" ./pm_nl_ctl dsf lip 10.0.2.2 lport "$sport" rip 10.0.2.1 rport\
+	   $app6_port token "$client6_token" > /dev/null 2>&1
+	sleep 0.5
+	verify_subflow_events "$client_evts" "$SUB_CLOSED" "$client6_token" \
+			      "$AF_INET" "10.0.2.2" "10.0.2.1" "$app6_port" "23"\
+			      "$server_addr_id" "ns2" "ns1"
+
+	# RM_ADDR from server to client machine
+	ip netns exec "$ns1" ./pm_nl_ctl rem id $server_addr_id token\
+	   "$server6_token" > /dev/null 2>&1
+	sleep 0.5
+}
+
 test_prio()
 {
 	local count
@@ -861,6 +907,7 @@ make_connection "v6"
 test_announce
 test_remove
 test_subflows
+test_subflows_v4_v6_mix
 test_prio
 test_listener
 
diff --git a/tools/testing/selftests/net/nettest.c b/tools/testing/selftests/net/nettest.c
index 7900fa98eccb..ee9a72982705 100644
--- a/tools/testing/selftests/net/nettest.c
+++ b/tools/testing/selftests/net/nettest.c
@@ -87,6 +87,7 @@ struct sock_args {
 	int use_setsockopt;
 	int use_freebind;
 	int use_cmsg;
+	uint8_t dsfield;
 	const char *dev;
 	const char *server_dev;
 	int ifindex;
@@ -580,6 +581,36 @@ static int set_reuseaddr(int sd)
 	return rc;
 }
 
+static int set_dsfield(int sd, int version, int dsfield)
+{
+	if (!dsfield)
+		return 0;
+
+	switch (version) {
+	case AF_INET:
+		if (setsockopt(sd, SOL_IP, IP_TOS, &dsfield,
+			       sizeof(dsfield)) < 0) {
+			log_err_errno("setsockopt(IP_TOS)");
+			return -1;
+		}
+		break;
+
+	case AF_INET6:
+		if (setsockopt(sd, SOL_IPV6, IPV6_TCLASS, &dsfield,
+			       sizeof(dsfield)) < 0) {
+			log_err_errno("setsockopt(IPV6_TCLASS)");
+			return -1;
+		}
+		break;
+
+	default:
+		log_error("Invalid address family\n");
+		return -1;
+	}
+
+	return 0;
+}
+
 static int str_to_uint(const char *str, int min, int max, unsigned int *value)
 {
 	int number;
@@ -1317,6 +1348,9 @@ static int msock_init(struct sock_args *args, int server)
 		       (char *)&one, sizeof(one)) < 0)
 		log_err_errno("Setting SO_BROADCAST error");
 
+	if (set_dsfield(sd, AF_INET, args->dsfield) != 0)
+		goto out_err;
+
 	if (args->dev && bind_to_device(sd, args->dev) != 0)
 		goto out_err;
 	else if (args->use_setsockopt &&
@@ -1445,6 +1479,9 @@ static int lsock_init(struct sock_args *args)
 	if (set_reuseport(sd) != 0)
 		goto err;
 
+	if (set_dsfield(sd, args->version, args->dsfield) != 0)
+		goto err;
+
 	if (args->dev && bind_to_device(sd, args->dev) != 0)
 		goto err;
 	else if (args->use_setsockopt &&
@@ -1658,6 +1695,9 @@ static int connectsock(void *addr, socklen_t alen, struct sock_args *args)
 	if (set_reuseport(sd) != 0)
 		goto err;
 
+	if (set_dsfield(sd, args->version, args->dsfield) != 0)
+		goto err;
+
 	if (args->dev && bind_to_device(sd, args->dev) != 0)
 		goto err;
 	else if (args->use_setsockopt &&
@@ -1862,7 +1902,7 @@ static int ipc_parent(int cpid, int fd, struct sock_args *args)
 	return client_status;
 }
 
-#define GETOPT_STR  "sr:l:c:p:t:g:P:DRn:M:X:m:d:I:BN:O:SUCi6xL:0:1:2:3:Fbqf"
+#define GETOPT_STR  "sr:l:c:Q:p:t:g:P:DRn:M:X:m:d:I:BN:O:SUCi6xL:0:1:2:3:Fbqf"
 #define OPT_FORCE_BIND_KEY_IFINDEX 1001
 #define OPT_NO_BIND_KEY_IFINDEX 1002
 
@@ -1893,6 +1933,8 @@ static void print_usage(char *prog)
 	"    -D|R          datagram (D) / raw (R) socket (default stream)\n"
 	"    -l addr       local address to bind to in server mode\n"
 	"    -c addr       local address to bind to in client mode\n"
+	"    -Q dsfield    DS Field value of the socket (the IP_TOS or\n"
+	"                  IPV6_TCLASS socket option)\n"
 	"    -x            configure XFRM policy on socket\n"
 	"\n"
 	"    -d dev        bind socket to given device name\n"
@@ -1971,6 +2013,13 @@ int main(int argc, char *argv[])
 			args.has_local_ip = 1;
 			args.client_local_addr_str = optarg;
 			break;
+		case 'Q':
+			if (str_to_uint(optarg, 0, 255, &tmp) != 0) {
+				fprintf(stderr, "Invalid DS Field\n");
+				return 1;
+			}
+			args.dsfield = tmp;
+			break;
 		case 'p':
 			if (str_to_uint(optarg, 1, 65535, &tmp) != 0) {
 				fprintf(stderr, "Invalid port\n");
diff --git a/tools/testing/selftests/net/test_vxlan_vnifiltering.sh b/tools/testing/selftests/net/test_vxlan_vnifiltering.sh
index 704997ffc244..8c3ac0a72545 100755
--- a/tools/testing/selftests/net/test_vxlan_vnifiltering.sh
+++ b/tools/testing/selftests/net/test_vxlan_vnifiltering.sh
@@ -293,19 +293,11 @@ setup-vm() {
 	elif [[ -n $vtype && $vtype == "vnifilterg" ]]; then
 	   # Add per vni group config with 'bridge vni' api
 	   if [ -n "$group" ]; then
-	      if [ "$family" == "v4" ]; then
-		 if [ $mcast -eq 1 ]; then
-		    bridge -netns hv-$hvid vni add dev $vxlandev vni $tid group $group
-		 else
-		    bridge -netns hv-$hvid vni add dev $vxlandev vni $tid remote $group
-		 fi
-	      else
-		 if [ $mcast -eq 1 ]; then
-		    bridge -netns hv-$hvid vni add dev $vxlandev vni $tid group6 $group
-		 else
-		    bridge -netns hv-$hvid vni add dev $vxlandev vni $tid remote6 $group
-		 fi
-	      fi
+		if [ $mcast -eq 1 ]; then
+			bridge -netns hv-$hvid vni add dev $vxlandev vni $tid group $group
+		else
+			bridge -netns hv-$hvid vni add dev $vxlandev vni $tid remote $group
+		fi
 	   fi
 	fi
 	done
diff --git a/tools/testing/selftests/net/toeplitz.c b/tools/testing/selftests/net/toeplitz.c
index 90026a27eac0..9ba03164d73a 100644
--- a/tools/testing/selftests/net/toeplitz.c
+++ b/tools/testing/selftests/net/toeplitz.c
@@ -215,7 +215,7 @@ static char *recv_frame(const struct ring_state *ring, char *frame)
 }
 
 /* A single TPACKET_V3 block can hold multiple frames */
-static void recv_block(struct ring_state *ring)
+static bool recv_block(struct ring_state *ring)
 {
 	struct tpacket_block_desc *block;
 	char *frame;
@@ -223,7 +223,7 @@ static void recv_block(struct ring_state *ring)
 
 	block = (void *)(ring->mmap + ring->idx * ring_block_sz);
 	if (!(block->hdr.bh1.block_status & TP_STATUS_USER))
-		return;
+		return false;
 
 	frame = (char *)block;
 	frame += block->hdr.bh1.offset_to_first_pkt;
@@ -235,6 +235,8 @@ static void recv_block(struct ring_state *ring)
 
 	block->hdr.bh1.block_status = TP_STATUS_KERNEL;
 	ring->idx = (ring->idx + 1) % ring_block_nr;
+
+	return true;
 }
 
 /* simple test: sleep once unconditionally and then process all rings */
@@ -245,7 +247,7 @@ static void process_rings(void)
 	usleep(1000 * cfg_timeout_msec);
 
 	for (i = 0; i < num_cpus; i++)
-		recv_block(&rings[i]);
+		do {} while (recv_block(&rings[i]));
 
 	fprintf(stderr, "count: pass=%u nohash=%u fail=%u\n",
 		frames_received - frames_nohash - frames_error,
@@ -257,12 +259,12 @@ static char *setup_ring(int fd)
 	struct tpacket_req3 req3 = {0};
 	void *ring;
 
-	req3.tp_retire_blk_tov = cfg_timeout_msec;
+	req3.tp_retire_blk_tov = cfg_timeout_msec / 8;
 	req3.tp_feature_req_word = TP_FT_REQ_FILL_RXHASH;
 
 	req3.tp_frame_size = 2048;
 	req3.tp_frame_nr = 1 << 10;
-	req3.tp_block_nr = 2;
+	req3.tp_block_nr = 16;
 
 	req3.tp_block_size = req3.tp_frame_size * req3.tp_frame_nr;
 	req3.tp_block_size /= req3.tp_block_nr;
diff --git a/tools/testing/selftests/net/udpgso_bench.sh b/tools/testing/selftests/net/udpgso_bench.sh
index dc932fd65363..640bc43452fa 100755
--- a/tools/testing/selftests/net/udpgso_bench.sh
+++ b/tools/testing/selftests/net/udpgso_bench.sh
@@ -7,6 +7,7 @@ readonly GREEN='\033[0;92m'
 readonly YELLOW='\033[0;33m'
 readonly RED='\033[0;31m'
 readonly NC='\033[0m' # No Color
+readonly TESTPORT=8000
 
 readonly KSFT_PASS=0
 readonly KSFT_FAIL=1
@@ -56,11 +57,26 @@ trap wake_children EXIT
 
 run_one() {
 	local -r args=$@
+	local nr_socks=0
+	local i=0
+	local -r timeout=10
+
+	./udpgso_bench_rx -p "$TESTPORT" &
+	./udpgso_bench_rx -p "$TESTPORT" -t &
+
+	# Wait for the above test program to get ready to receive connections.
+	while [ "$i" -lt "$timeout" ]; do
+		nr_socks="$(ss -lnHi | grep -c "\*:${TESTPORT}")"
+		[ "$nr_socks" -eq 2 ] && break
+		i=$((i + 1))
+		sleep 1
+	done
+	if [ "$nr_socks" -ne 2 ]; then
+		echo "timed out while waiting for udpgso_bench_rx"
+		exit 1
+	fi
 
-	./udpgso_bench_rx &
-	./udpgso_bench_rx -t &
-
-	./udpgso_bench_tx ${args}
+	./udpgso_bench_tx -p "$TESTPORT" ${args}
 }
 
 run_in_netns() {
diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c
index 6a193425c367..4058c7451e70 100644
--- a/tools/testing/selftests/net/udpgso_bench_rx.c
+++ b/tools/testing/selftests/net/udpgso_bench_rx.c
@@ -250,7 +250,7 @@ static int recv_msg(int fd, char *buf, int len, int *gso_size)
 static void do_flush_udp(int fd)
 {
 	static char rbuf[ETH_MAX_MTU];
-	int ret, len, gso_size, budget = 256;
+	int ret, len, gso_size = 0, budget = 256;
 
 	len = cfg_read_all ? sizeof(rbuf) : 0;
 	while (budget--) {
@@ -336,6 +336,8 @@ static void parse_opts(int argc, char **argv)
 			cfg_verify = true;
 			cfg_read_all = true;
 			break;
+		default:
+			exit(1);
 		}
 	}
 
diff --git a/tools/testing/selftests/net/udpgso_bench_tx.c b/tools/testing/selftests/net/udpgso_bench_tx.c
index f1fdaa270291..477392715a9a 100644
--- a/tools/testing/selftests/net/udpgso_bench_tx.c
+++ b/tools/testing/selftests/net/udpgso_bench_tx.c
@@ -62,6 +62,7 @@ static int	cfg_payload_len	= (1472 * 42);
 static int	cfg_port	= 8000;
 static int	cfg_runtime_ms	= -1;
 static bool	cfg_poll;
+static int	cfg_poll_loop_timeout_ms = 2000;
 static bool	cfg_segment;
 static bool	cfg_sendmmsg;
 static bool	cfg_tcp;
@@ -235,16 +236,17 @@ static void flush_errqueue_recv(int fd)
 	}
 }
 
-static void flush_errqueue(int fd, const bool do_poll)
+static void flush_errqueue(int fd, const bool do_poll,
+			   unsigned long poll_timeout, const bool poll_err)
 {
 	if (do_poll) {
 		struct pollfd fds = {0};
 		int ret;
 
 		fds.fd = fd;
-		ret = poll(&fds, 1, 500);
+		ret = poll(&fds, 1, poll_timeout);
 		if (ret == 0) {
-			if (cfg_verbose)
+			if ((cfg_verbose) && (poll_err))
 				fprintf(stderr, "poll timeout\n");
 		} else if (ret < 0) {
 			error(1, errno, "poll");
@@ -254,6 +256,20 @@ static void flush_errqueue(int fd, const bool do_poll)
 	flush_errqueue_recv(fd);
 }
 
+static void flush_errqueue_retry(int fd, unsigned long num_sends)
+{
+	unsigned long tnow, tstop;
+	bool first_try = true;
+
+	tnow = gettimeofday_ms();
+	tstop = tnow + cfg_poll_loop_timeout_ms;
+	do {
+		flush_errqueue(fd, true, tstop - tnow, first_try);
+		first_try = false;
+		tnow = gettimeofday_ms();
+	} while ((stat_zcopies != num_sends) && (tnow < tstop));
+}
+
 static int send_tcp(int fd, char *data)
 {
 	int ret, done = 0, count = 0;
@@ -413,7 +429,8 @@ static int send_udp_segment(int fd, char *data)
 
 static void usage(const char *filepath)
 {
-	error(1, 0, "Usage: %s [-46acmHPtTuvz] [-C cpu] [-D dst ip] [-l secs] [-M messagenr] [-p port] [-s sendsize] [-S gsosize]",
+	error(1, 0, "Usage: %s [-46acmHPtTuvz] [-C cpu] [-D dst ip] [-l secs] "
+		    "[-L secs] [-M messagenr] [-p port] [-s sendsize] [-S gsosize]",
 		    filepath);
 }
 
@@ -423,7 +440,7 @@ static void parse_opts(int argc, char **argv)
 	int max_len, hdrlen;
 	int c;
 
-	while ((c = getopt(argc, argv, "46acC:D:Hl:mM:p:s:PS:tTuvz")) != -1) {
+	while ((c = getopt(argc, argv, "46acC:D:Hl:L:mM:p:s:PS:tTuvz")) != -1) {
 		switch (c) {
 		case '4':
 			if (cfg_family != PF_UNSPEC)
@@ -452,6 +469,9 @@ static void parse_opts(int argc, char **argv)
 		case 'l':
 			cfg_runtime_ms = strtoul(optarg, NULL, 10) * 1000;
 			break;
+		case 'L':
+			cfg_poll_loop_timeout_ms = strtoul(optarg, NULL, 10) * 1000;
+			break;
 		case 'm':
 			cfg_sendmmsg = true;
 			break;
@@ -490,6 +510,8 @@ static void parse_opts(int argc, char **argv)
 		case 'z':
 			cfg_zerocopy = true;
 			break;
+		default:
+			exit(1);
 		}
 	}
 
@@ -677,7 +699,7 @@ int main(int argc, char **argv)
 			num_sends += send_udp(fd, buf[i]);
 		num_msgs++;
 		if ((cfg_zerocopy && ((num_msgs & 0xF) == 0)) || cfg_tx_tstamp)
-			flush_errqueue(fd, cfg_poll);
+			flush_errqueue(fd, cfg_poll, 500, true);
 
 		if (cfg_msg_nr && num_msgs >= cfg_msg_nr)
 			break;
@@ -696,7 +718,7 @@ int main(int argc, char **argv)
 	} while (!interrupted && (cfg_runtime_ms == -1 || tnow < tstop));
 
 	if (cfg_zerocopy || cfg_tx_tstamp)
-		flush_errqueue(fd, true);
+		flush_errqueue_retry(fd, num_sends);
 
 	if (close(fd))
 		error(1, errno, "close");
diff --git a/tools/testing/selftests/netfilter/nft_trans_stress.sh b/tools/testing/selftests/netfilter/nft_trans_stress.sh
index a7f62ad4f661..2ffba45a78bf 100755
--- a/tools/testing/selftests/netfilter/nft_trans_stress.sh
+++ b/tools/testing/selftests/netfilter/nft_trans_stress.sh
@@ -10,12 +10,20 @@
 ksft_skip=4
 
 testns=testns-$(mktemp -u "XXXXXXXX")
+tmp=""
 
 tables="foo bar baz quux"
 global_ret=0
 eret=0
 lret=0
 
+cleanup() {
+	ip netns pids "$testns" | xargs kill 2>/dev/null
+	ip netns del "$testns"
+
+	rm -f "$tmp"
+}
+
 check_result()
 {
 	local r=$1
@@ -43,6 +51,7 @@ if [ $? -ne 0 ];then
 	exit $ksft_skip
 fi
 
+trap cleanup EXIT
 tmp=$(mktemp)
 
 for table in $tables; do
@@ -139,11 +148,4 @@ done
 
 check_result $lret "add/delete with nftrace enabled"
 
-pkill -9 ping
-
-wait
-
-rm -f "$tmp"
-ip netns del "$testns"
-
 exit $global_ret
diff --git a/tools/testing/selftests/netfilter/settings b/tools/testing/selftests/netfilter/settings
new file mode 100644
index 000000000000..6091b45d226b
--- /dev/null
+++ b/tools/testing/selftests/netfilter/settings
@@ -0,0 +1 @@
+timeout=120
diff --git a/tools/testing/selftests/proc/proc-empty-vm.c b/tools/testing/selftests/proc/proc-empty-vm.c
index d95b1cb43d9d..7588428b8fcd 100644
--- a/tools/testing/selftests/proc/proc-empty-vm.c
+++ b/tools/testing/selftests/proc/proc-empty-vm.c
@@ -25,6 +25,7 @@
 #undef NDEBUG
 #include <assert.h>
 #include <errno.h>
+#include <stdint.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
@@ -41,7 +42,7 @@
  * 1: vsyscall VMA is --xp		vsyscall=xonly
  * 2: vsyscall VMA is r-xp		vsyscall=emulate
  */
-static int g_vsyscall;
+static volatile int g_vsyscall;
 static const char *g_proc_pid_maps_vsyscall;
 static const char *g_proc_pid_smaps_vsyscall;
 
@@ -147,11 +148,12 @@ static void vsyscall(void)
 
 		g_vsyscall = 0;
 		/* gettimeofday(NULL, NULL); */
+		uint64_t rax = 0xffffffffff600000;
 		asm volatile (
-			"call %P0"
-			:
-			: "i" (0xffffffffff600000), "D" (NULL), "S" (NULL)
-			: "rax", "rcx", "r11"
+			"call *%[rax]"
+			: [rax] "+a" (rax)
+			: "D" (NULL), "S" (NULL)
+			: "rcx", "r11"
 		);
 
 		g_vsyscall = 1;
diff --git a/tools/testing/selftests/proc/proc-pid-vm.c b/tools/testing/selftests/proc/proc-pid-vm.c
index 69551bfa215c..cacbd2a4aec9 100644
--- a/tools/testing/selftests/proc/proc-pid-vm.c
+++ b/tools/testing/selftests/proc/proc-pid-vm.c
@@ -257,11 +257,12 @@ static void vsyscall(void)
 
 		g_vsyscall = 0;
 		/* gettimeofday(NULL, NULL); */
+		uint64_t rax = 0xffffffffff600000;
 		asm volatile (
-			"call %P0"
-			:
-			: "i" (0xffffffffff600000), "D" (NULL), "S" (NULL)
-			: "rax", "rcx", "r11"
+			"call *%[rax]"
+			: [rax] "+a" (rax)
+			: "D" (NULL), "S" (NULL)
+			: "rcx", "r11"
 		);
 
 		g_vsyscall = 1;
diff --git a/tools/testing/selftests/vm/hugetlb-madvise.c b/tools/testing/selftests/vm/hugetlb-madvise.c
index a634f47d1e56..9a127a8fe176 100644
--- a/tools/testing/selftests/vm/hugetlb-madvise.c
+++ b/tools/testing/selftests/vm/hugetlb-madvise.c
@@ -17,7 +17,6 @@
 #include <stdio.h>
 #include <unistd.h>
 #include <sys/mman.h>
-#define __USE_GNU
 #include <fcntl.h>
 
 #define MIN_FREE_PAGES	20