Merge patch series "ns: support file handles"

Christian Brauner <brauner@kernel.org> says:

For a while now we have supported file handles for pidfds. This has
proven to be very useful.

Extend the concept to cover namespaces as well. After this patchset it
is possible to encode and decode namespace file handles using the
commong name_to_handle_at() and open_by_handle_at() apis.

Namespaces file descriptors can already be derived from pidfds which
means they aren't subject to overmount protection bugs. IOW, it's
irrelevant if the caller would not have access to an appropriate
/proc/<pid>/ns/ directory as they could always just derive the namespace
based on a pidfd already.

It has the same advantage as pidfds. It's possible to reliably and for
the lifetime of the system refer to a namespace without pinning any
resources and to compare them.

Permission checking is kept simple. If the caller is located in the
namespace the file handle refers to they are able to open it otherwise
they must hold privilege over the owning namespace of the relevant
namespace.

Both the network namespace and the mount namespace already have an
associated cookie that isn't recycled and is fully exposed to userspace.
Move this into ns_common and use the same id space for all namespaces so
they can trivially and reliably be compared.

There's more coming based on the iterator infrastructure but the series
is large enough and focuses on file handles.

Extensive selftests included.

* patches from https://lore.kernel.org/20250912-work-namespace-v2-0-1a247645cef5@kernel.org: (33 commits)
  selftests/namespaces: add file handle selftests
  selftests/namespaces: add identifier selftests
  tools: update nsfs.h uapi header
  nsfs: add missing id retrieval support
  nsfs: support exhaustive file handles
  nsfs: support file handles
  nsfs: add current_in_namespace()
  ns: add to_<type>_ns() to respective headers
  uts: support ns lookup
  user: support ns lookup
  time: support ns lookup
  pid: support ns lookup
  net: support ns lookup
  ipc: support ns lookup
  cgroup: support ns lookup
  mnt: support ns lookup
  nstree: make iterator generic
  ns: remove ns_alloc_inum()
  uts: use ns_common_init()
  user: use ns_common_init()
  ...

Signed-off-by: Christian Brauner <brauner@kernel.org>

43 files changed, 3653 insertions, 99 deletions

diff --git a/tools/testing/selftests/arm64/fp/fp-ptrace.c b/tools/testing/selftests/arm64/fp/fp-ptrace.c
index 124bc883365e..cdd7a45c045d 100644
--- a/tools/testing/selftests/arm64/fp/fp-ptrace.c
+++ b/tools/testing/selftests/arm64/fp/fp-ptrace.c
@@ -1187,7 +1187,7 @@ static void sve_write_sve(pid_t child, struct test_config *config)
 	if (!vl)
 		return;
 
-	iov.iov_len = SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, SVE_PT_REGS_SVE);
+	iov.iov_len = SVE_PT_SIZE(vq, SVE_PT_REGS_SVE);
 	iov.iov_base = malloc(iov.iov_len);
 	if (!iov.iov_base) {
 		ksft_print_msg("Failed allocating %lu byte SVE write buffer\n",
@@ -1234,8 +1234,7 @@ static void sve_write_fpsimd(pid_t child, struct test_config *config)
 	if (!vl)
 		return;
 
-	iov.iov_len = SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq,
-							  SVE_PT_REGS_FPSIMD);
+	iov.iov_len = SVE_PT_SIZE(vq, SVE_PT_REGS_FPSIMD);
 	iov.iov_base = malloc(iov.iov_len);
 	if (!iov.iov_base) {
 		ksft_print_msg("Failed allocating %lu byte SVE write buffer\n",
diff --git a/tools/testing/selftests/coredump/stackdump_test.c b/tools/testing/selftests/coredump/stackdump_test.c
index 5a5a7a5f7e1d..a4ac80bb1003 100644
--- a/tools/testing/selftests/coredump/stackdump_test.c
+++ b/tools/testing/selftests/coredump/stackdump_test.c
@@ -446,9 +446,6 @@ TEST_F(coredump, socket_detect_userspace_client)
 		if (info.coredump_mask & PIDFD_COREDUMPED)
 			goto out;
 
-		if (read(fd_coredump, &c, 1) < 1)
-			goto out;
-
 		exit_code = EXIT_SUCCESS;
 out:
 		if (fd_peer_pidfd >= 0)
diff --git a/tools/testing/selftests/damon/Makefile b/tools/testing/selftests/damon/Makefile
index 5b230deb19e8..9a3499827d4b 100644
--- a/tools/testing/selftests/damon/Makefile
+++ b/tools/testing/selftests/damon/Makefile
@@ -4,6 +4,7 @@
 TEST_GEN_FILES += access_memory access_memory_even
 
 TEST_FILES = _damon_sysfs.py
+TEST_FILES += drgn_dump_damon_status.py
 
 # functionality tests
 TEST_PROGS += sysfs.sh
diff --git a/tools/testing/selftests/drivers/net/bonding/Makefile b/tools/testing/selftests/drivers/net/bonding/Makefile
index 2b10854e4b1e..44b98f17f8ff 100644
--- a/tools/testing/selftests/drivers/net/bonding/Makefile
+++ b/tools/testing/selftests/drivers/net/bonding/Makefile
@@ -10,7 +10,8 @@ TEST_PROGS := \
 	mode-2-recovery-updelay.sh \
 	bond_options.sh \
 	bond-eth-type-change.sh \
-	bond_macvlan_ipvlan.sh
+	bond_macvlan_ipvlan.sh \
+	bond_passive_lacp.sh
 
 TEST_FILES := \
 	lag_lib.sh \
diff --git a/tools/testing/selftests/drivers/net/bonding/bond_passive_lacp.sh b/tools/testing/selftests/drivers/net/bonding/bond_passive_lacp.sh
new file mode 100755
index 000000000000..9c3b089813df
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/bonding/bond_passive_lacp.sh
@@ -0,0 +1,105 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test if a bond interface works with lacp_active=off.
+
+# shellcheck disable=SC2034
+REQUIRE_MZ=no
+NUM_NETIFS=0
+lib_dir=$(dirname "$0")
+# shellcheck disable=SC1091
+source "$lib_dir"/../../../net/forwarding/lib.sh
+
+# shellcheck disable=SC2317
+check_port_state()
+{
+	local netns=$1
+	local port=$2
+	local state=$3
+
+	ip -n "${netns}" -d -j link show "$port" | \
+		jq -e ".[].linkinfo.info_slave_data.ad_actor_oper_port_state_str | index(\"${state}\") != null" > /dev/null
+}
+
+check_pkt_count()
+{
+	RET=0
+	local ns="$1"
+	local iface="$2"
+
+	# wait 65s, one per 30s
+	slowwait_for_counter 65 2 tc_rule_handle_stats_get \
+		"dev ${iface} egress" 101 ".packets" "-n ${ns}" &> /dev/null
+}
+
+setup() {
+	setup_ns c_ns s_ns
+
+	# shellcheck disable=SC2154
+	ip -n "${c_ns}" link add eth0 type veth peer name eth0 netns "${s_ns}"
+	ip -n "${c_ns}" link add eth1 type veth peer name eth1 netns "${s_ns}"
+
+	# Add tc filter to count the pkts
+	tc -n "${c_ns}" qdisc add dev eth0 clsact
+	tc -n "${c_ns}" filter add dev eth0 egress handle 101 protocol 0x8809 matchall action pass
+	tc -n "${s_ns}" qdisc add dev eth1 clsact
+	tc -n "${s_ns}" filter add dev eth1 egress handle 101 protocol 0x8809 matchall action pass
+
+	ip -n "${s_ns}" link add bond0 type bond mode 802.3ad lacp_active on lacp_rate fast
+	ip -n "${s_ns}" link set eth0 master bond0
+	ip -n "${s_ns}" link set eth1 master bond0
+
+	ip -n "${c_ns}" link add bond0 type bond mode 802.3ad lacp_active off lacp_rate fast
+	ip -n "${c_ns}" link set eth0 master bond0
+	ip -n "${c_ns}" link set eth1 master bond0
+
+}
+
+trap cleanup_all_ns EXIT
+setup
+
+# The bond will send 2 lacpdu pkts during init time, let's wait at least 2s
+# after interface up
+ip -n "${c_ns}" link set bond0 up
+sleep 2
+
+# 1. The passive side shouldn't send LACPDU.
+check_pkt_count "${c_ns}" "eth0" && RET=1
+log_test "802.3ad lacp_active off" "init port"
+
+ip -n "${s_ns}" link set bond0 up
+# 2. The passive side should not have the 'active' flag.
+RET=0
+slowwait 2 check_port_state "${c_ns}" "eth0" "active" && RET=1
+log_test "802.3ad lacp_active off" "port state active"
+
+# 3. The active side should have the 'active' flag.
+RET=0
+slowwait 2 check_port_state "${s_ns}" "eth0" "active" || RET=1
+log_test "802.3ad lacp_active on" "port state active"
+
+# 4. Make sure the connection is not expired.
+RET=0
+slowwait 5 check_port_state "${s_ns}" "eth0" "distributing"
+slowwait 10 check_port_state "${s_ns}" "eth0" "expired" && RET=1
+log_test "bond 802.3ad lacp_active off" "port connection"
+
+# After testing, disconnect one port on each side to check the state.
+ip -n "${s_ns}" link set eth0 nomaster
+ip -n "${s_ns}" link set eth0 up
+ip -n "${c_ns}" link set eth1 nomaster
+ip -n "${c_ns}" link set eth1 up
+# Due to Periodic Machine and Rx Machine state change, the bond will still
+# send lacpdu pkts in a few seconds. sleep at lease 5s to make sure
+# negotiation finished
+sleep 5
+
+# 5. The active side should keep sending LACPDU.
+check_pkt_count "${s_ns}" "eth1" || RET=1
+log_test "bond 802.3ad lacp_active on" "port pkt after disconnect"
+
+# 6. The passive side shouldn't send LACPDU anymore.
+check_pkt_count "${c_ns}" "eth0" && RET=1
+log_test "bond 802.3ad lacp_active off" "port pkt after disconnect"
+
+exit "$EXIT_STATUS"
diff --git a/tools/testing/selftests/drivers/net/bonding/config b/tools/testing/selftests/drivers/net/bonding/config
index dad4e5fda4db..4d16a69ffc65 100644
--- a/tools/testing/selftests/drivers/net/bonding/config
+++ b/tools/testing/selftests/drivers/net/bonding/config
@@ -6,6 +6,7 @@ CONFIG_MACVLAN=y
 CONFIG_IPVLAN=y
 CONFIG_NET_ACT_GACT=y
 CONFIG_NET_CLS_FLOWER=y
+CONFIG_NET_CLS_MATCHALL=m
 CONFIG_NET_SCH_INGRESS=y
 CONFIG_NLMON=y
 CONFIG_VETH=y
diff --git a/tools/testing/selftests/drivers/net/napi_threaded.py b/tools/testing/selftests/drivers/net/napi_threaded.py
index b2698db39817..9699a100a87d 100755
--- a/tools/testing/selftests/drivers/net/napi_threaded.py
+++ b/tools/testing/selftests/drivers/net/napi_threaded.py
@@ -35,6 +35,8 @@ def _setup_deferred_cleanup(cfg) -> None:
     threaded = cmd(f"cat /sys/class/net/{cfg.ifname}/threaded").stdout
     defer(_set_threaded_state, cfg, threaded)
 
+    return combined
+
 
 def enable_dev_threaded_disable_napi_threaded(cfg, nl) -> None:
     """
@@ -49,7 +51,7 @@ def enable_dev_threaded_disable_napi_threaded(cfg, nl) -> None:
     napi0_id = napis[0]['id']
     napi1_id = napis[1]['id']
 
-    _setup_deferred_cleanup(cfg)
+    qcnt = _setup_deferred_cleanup(cfg)
 
     # set threaded
     _set_threaded_state(cfg, 1)
@@ -62,7 +64,7 @@ def enable_dev_threaded_disable_napi_threaded(cfg, nl) -> None:
     nl.napi_set({'id': napi1_id, 'threaded': 'disabled'})
 
     cmd(f"ethtool -L {cfg.ifname} combined 1")
-    cmd(f"ethtool -L {cfg.ifname} combined 2")
+    cmd(f"ethtool -L {cfg.ifname} combined {qcnt}")
     _assert_napi_threaded_enabled(nl, napi0_id)
     _assert_napi_threaded_disabled(nl, napi1_id)
 
@@ -80,7 +82,7 @@ def change_num_queues(cfg, nl) -> None:
     napi0_id = napis[0]['id']
     napi1_id = napis[1]['id']
 
-    _setup_deferred_cleanup(cfg)
+    qcnt = _setup_deferred_cleanup(cfg)
 
     # set threaded
     _set_threaded_state(cfg, 1)
@@ -90,7 +92,7 @@ def change_num_queues(cfg, nl) -> None:
     _assert_napi_threaded_enabled(nl, napi1_id)
 
     cmd(f"ethtool -L {cfg.ifname} combined 1")
-    cmd(f"ethtool -L {cfg.ifname} combined 2")
+    cmd(f"ethtool -L {cfg.ifname} combined {qcnt}")
 
     # check napi threaded is set for both napis
     _assert_napi_threaded_enabled(nl, napi0_id)
diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h
index 2925e47db995..8516e8434bc4 100644
--- a/tools/testing/selftests/kselftest_harness.h
+++ b/tools/testing/selftests/kselftest_harness.h
@@ -751,7 +751,7 @@
 	for (; _metadata->trigger; _metadata->trigger = \
 			__bail(_assert, _metadata))
 
-#define is_signed_type(var)       (!!(((__typeof__(var))(-1)) < (__typeof__(var))1))
+#define is_signed_var(var)	(!!(((__typeof__(var))(-1)) < (__typeof__(var))1))
 
 #define __EXPECT(_expected, _expected_str, _seen, _seen_str, _t, _assert) do { \
 	/* Avoid multiple evaluation of the cases */ \
@@ -759,7 +759,7 @@
 	__typeof__(_seen) __seen = (_seen); \
 	if (!(__exp _t __seen)) { \
 		/* Report with actual signedness to avoid weird output. */ \
-		switch (is_signed_type(__exp) * 2 + is_signed_type(__seen)) { \
+		switch (is_signed_var(__exp) * 2 + is_signed_var(__seen)) { \
 		case 0: { \
 			uintmax_t __exp_print = (uintmax_t)__exp; \
 			uintmax_t __seen_print = (uintmax_t)__seen; \
diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm
index f6fe7a07a0a2..41b40c676d7f 100644
--- a/tools/testing/selftests/kvm/Makefile.kvm
+++ b/tools/testing/selftests/kvm/Makefile.kvm
@@ -169,6 +169,7 @@ TEST_GEN_PROGS_arm64 += arm64/vgic_irq
 TEST_GEN_PROGS_arm64 += arm64/vgic_lpi_stress
 TEST_GEN_PROGS_arm64 += arm64/vpmu_counter_access
 TEST_GEN_PROGS_arm64 += arm64/no-vgic-v3
+TEST_GEN_PROGS_arm64 += arm64/kvm-uuid
 TEST_GEN_PROGS_arm64 += access_tracking_perf_test
 TEST_GEN_PROGS_arm64 += arch_timer
 TEST_GEN_PROGS_arm64 += coalesced_io_test
diff --git a/tools/testing/selftests/kvm/arm64/aarch32_id_regs.c b/tools/testing/selftests/kvm/arm64/aarch32_id_regs.c
index cef8f7323ceb..713005b6f508 100644
--- a/tools/testing/selftests/kvm/arm64/aarch32_id_regs.c
+++ b/tools/testing/selftests/kvm/arm64/aarch32_id_regs.c
@@ -146,7 +146,7 @@ static bool vcpu_aarch64_only(struct kvm_vcpu *vcpu)
 
 	val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1));
 
-	el0 = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_EL0), val);
+	el0 = FIELD_GET(ID_AA64PFR0_EL1_EL0, val);
 	return el0 == ID_AA64PFR0_EL1_EL0_IMP;
 }
 
diff --git a/tools/testing/selftests/kvm/arm64/debug-exceptions.c b/tools/testing/selftests/kvm/arm64/debug-exceptions.c
index e34963956fbc..1d431de8729c 100644
--- a/tools/testing/selftests/kvm/arm64/debug-exceptions.c
+++ b/tools/testing/selftests/kvm/arm64/debug-exceptions.c
@@ -116,12 +116,12 @@ static void reset_debug_state(void)
 
 	/* Reset all bcr/bvr/wcr/wvr registers */
 	dfr0 = read_sysreg(id_aa64dfr0_el1);
-	brps = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_BRPs), dfr0);
+	brps = FIELD_GET(ID_AA64DFR0_EL1_BRPs, dfr0);
 	for (i = 0; i <= brps; i++) {
 		write_dbgbcr(i, 0);
 		write_dbgbvr(i, 0);
 	}
-	wrps = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_WRPs), dfr0);
+	wrps = FIELD_GET(ID_AA64DFR0_EL1_WRPs, dfr0);
 	for (i = 0; i <= wrps; i++) {
 		write_dbgwcr(i, 0);
 		write_dbgwvr(i, 0);
@@ -418,7 +418,7 @@ static void guest_code_ss(int test_cnt)
 
 static int debug_version(uint64_t id_aa64dfr0)
 {
-	return FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_DebugVer), id_aa64dfr0);
+	return FIELD_GET(ID_AA64DFR0_EL1_DebugVer, id_aa64dfr0);
 }
 
 static void test_guest_debug_exceptions(uint8_t bpn, uint8_t wpn, uint8_t ctx_bpn)
@@ -539,14 +539,14 @@ void test_guest_debug_exceptions_all(uint64_t aa64dfr0)
 	int b, w, c;
 
 	/* Number of breakpoints */
-	brp_num = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_BRPs), aa64dfr0) + 1;
+	brp_num = FIELD_GET(ID_AA64DFR0_EL1_BRPs, aa64dfr0) + 1;
 	__TEST_REQUIRE(brp_num >= 2, "At least two breakpoints are required");
 
 	/* Number of watchpoints */
-	wrp_num = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_WRPs), aa64dfr0) + 1;
+	wrp_num = FIELD_GET(ID_AA64DFR0_EL1_WRPs, aa64dfr0) + 1;
 
 	/* Number of context aware breakpoints */
-	ctx_brp_num = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_CTX_CMPs), aa64dfr0) + 1;
+	ctx_brp_num = FIELD_GET(ID_AA64DFR0_EL1_CTX_CMPs, aa64dfr0) + 1;
 
 	pr_debug("%s brp_num:%d, wrp_num:%d, ctx_brp_num:%d\n", __func__,
 		 brp_num, wrp_num, ctx_brp_num);
diff --git a/tools/testing/selftests/kvm/arm64/kvm-uuid.c b/tools/testing/selftests/kvm/arm64/kvm-uuid.c
new file mode 100644
index 000000000000..af9581b860f1
--- /dev/null
+++ b/tools/testing/selftests/kvm/arm64/kvm-uuid.c
@@ -0,0 +1,70 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// Check that nobody has tampered with KVM's UID
+
+#include <errno.h>
+#include <linux/arm-smccc.h>
+#include <asm/kvm.h>
+#include <kvm_util.h>
+
+#include "processor.h"
+
+/*
+ * Do NOT redefine these constants, or try to replace them with some
+ * "common" version. They are hardcoded here to detect any potential
+ * breakage happening in the rest of the kernel.
+ *
+ * KVM UID value: 28b46fb6-2ec5-11e9-a9ca-4b564d003a74
+ */
+#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_0	0xb66fb428U
+#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_1	0xe911c52eU
+#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_2	0x564bcaa9U
+#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_3	0x743a004dU
+
+static void guest_code(void)
+{
+	struct arm_smccc_res res = {};
+
+	smccc_hvc(ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID, 0, 0, 0, 0, 0, 0, 0, &res);
+
+	__GUEST_ASSERT(res.a0 == ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_0 &&
+		       res.a1 == ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_1 &&
+		       res.a2 == ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_2 &&
+		       res.a3 == ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_3,
+		       "Unexpected KVM-specific UID %lx %lx %lx %lx\n", res.a0, res.a1, res.a2, res.a3);
+	GUEST_DONE();
+}
+
+int main (int argc, char *argv[])
+{
+	struct kvm_vcpu *vcpu;
+	struct kvm_vm *vm;
+	struct ucall uc;
+	bool guest_done = false;
+
+	vm = vm_create_with_one_vcpu(&vcpu, guest_code);
+
+	while (!guest_done) {
+		vcpu_run(vcpu);
+
+		switch (get_ucall(vcpu, &uc)) {
+		case UCALL_SYNC:
+			break;
+		case UCALL_DONE:
+			guest_done = true;
+			break;
+		case UCALL_ABORT:
+			REPORT_GUEST_ASSERT(uc);
+			break;
+		case UCALL_PRINTF:
+			printf("%s", uc.buffer);
+			break;
+		default:
+			TEST_FAIL("Unexpected guest exit");
+		}
+	}
+
+	kvm_vm_free(vm);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/arm64/no-vgic-v3.c b/tools/testing/selftests/kvm/arm64/no-vgic-v3.c
index ebd70430c89d..f222538e6084 100644
--- a/tools/testing/selftests/kvm/arm64/no-vgic-v3.c
+++ b/tools/testing/selftests/kvm/arm64/no-vgic-v3.c
@@ -54,7 +54,7 @@ static void guest_code(void)
 	 * Check that we advertise that ID_AA64PFR0_EL1.GIC == 0, having
 	 * hidden the feature at runtime without any other userspace action.
 	 */
-	__GUEST_ASSERT(FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_GIC),
+	__GUEST_ASSERT(FIELD_GET(ID_AA64PFR0_EL1_GIC,
 				 read_sysreg(id_aa64pfr0_el1)) == 0,
 		       "GICv3 wrongly advertised");
 
@@ -165,7 +165,7 @@ int main(int argc, char *argv[])
 
 	vm = vm_create_with_one_vcpu(&vcpu, NULL);
 	pfr0 = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1));
-	__TEST_REQUIRE(FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_GIC), pfr0),
+	__TEST_REQUIRE(FIELD_GET(ID_AA64PFR0_EL1_GIC, pfr0),
 		       "GICv3 not supported.");
 	kvm_vm_free(vm);
 
diff --git a/tools/testing/selftests/kvm/arm64/page_fault_test.c b/tools/testing/selftests/kvm/arm64/page_fault_test.c
index dc6559dad9d8..4ccbd389d133 100644
--- a/tools/testing/selftests/kvm/arm64/page_fault_test.c
+++ b/tools/testing/selftests/kvm/arm64/page_fault_test.c
@@ -95,14 +95,14 @@ static bool guest_check_lse(void)
 	uint64_t isar0 = read_sysreg(id_aa64isar0_el1);
 	uint64_t atomic;
 
-	atomic = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_ATOMIC), isar0);
+	atomic = FIELD_GET(ID_AA64ISAR0_EL1_ATOMIC, isar0);
 	return atomic >= 2;
 }
 
 static bool guest_check_dc_zva(void)
 {
 	uint64_t dczid = read_sysreg(dczid_el0);
-	uint64_t dzp = FIELD_GET(ARM64_FEATURE_MASK(DCZID_EL0_DZP), dczid);
+	uint64_t dzp = FIELD_GET(DCZID_EL0_DZP, dczid);
 
 	return dzp == 0;
 }
@@ -195,7 +195,7 @@ static bool guest_set_ha(void)
 	uint64_t hadbs, tcr;
 
 	/* Skip if HA is not supported. */
-	hadbs = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR1_EL1_HAFDBS), mmfr1);
+	hadbs = FIELD_GET(ID_AA64MMFR1_EL1_HAFDBS, mmfr1);
 	if (hadbs == 0)
 		return false;
 
diff --git a/tools/testing/selftests/kvm/arm64/set_id_regs.c b/tools/testing/selftests/kvm/arm64/set_id_regs.c
index d3bf9204409c..189321e96925 100644
--- a/tools/testing/selftests/kvm/arm64/set_id_regs.c
+++ b/tools/testing/selftests/kvm/arm64/set_id_regs.c
@@ -243,6 +243,7 @@ static void guest_code(void)
 	GUEST_REG_SYNC(SYS_ID_AA64MMFR0_EL1);
 	GUEST_REG_SYNC(SYS_ID_AA64MMFR1_EL1);
 	GUEST_REG_SYNC(SYS_ID_AA64MMFR2_EL1);
+	GUEST_REG_SYNC(SYS_ID_AA64MMFR3_EL1);
 	GUEST_REG_SYNC(SYS_ID_AA64ZFR0_EL1);
 	GUEST_REG_SYNC(SYS_CTR_EL0);
 	GUEST_REG_SYNC(SYS_MIDR_EL1);
@@ -594,8 +595,8 @@ static void test_user_set_mte_reg(struct kvm_vcpu *vcpu)
 	 */
 	val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR1_EL1));
 
-	mte = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE), val);
-	mte_frac = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE_frac), val);
+	mte = FIELD_GET(ID_AA64PFR1_EL1_MTE, val);
+	mte_frac = FIELD_GET(ID_AA64PFR1_EL1_MTE_frac, val);
 	if (mte != ID_AA64PFR1_EL1_MTE_MTE2 ||
 	    mte_frac != ID_AA64PFR1_EL1_MTE_frac_NI) {
 		ksft_test_result_skip("MTE_ASYNC or MTE_ASYMM are supported, nothing to test\n");
@@ -612,7 +613,7 @@ static void test_user_set_mte_reg(struct kvm_vcpu *vcpu)
 	}
 
 	val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR1_EL1));
-	mte_frac = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE_frac), val);
+	mte_frac = FIELD_GET(ID_AA64PFR1_EL1_MTE_frac, val);
 	if (mte_frac == ID_AA64PFR1_EL1_MTE_frac_NI)
 		ksft_test_result_pass("ID_AA64PFR1_EL1.MTE_frac=0 accepted and still 0xF\n");
 	else
@@ -774,7 +775,7 @@ int main(void)
 
 	/* Check for AARCH64 only system */
 	val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1));
-	el0 = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_EL0), val);
+	el0 = FIELD_GET(ID_AA64PFR0_EL1_EL0, val);
 	aarch64_only = (el0 == ID_AA64PFR0_EL1_EL0_IMP);
 
 	ksft_print_header();
diff --git a/tools/testing/selftests/kvm/arm64/vpmu_counter_access.c b/tools/testing/selftests/kvm/arm64/vpmu_counter_access.c
index f16b3b27e32e..a0c4ab839155 100644
--- a/tools/testing/selftests/kvm/arm64/vpmu_counter_access.c
+++ b/tools/testing/selftests/kvm/arm64/vpmu_counter_access.c
@@ -441,7 +441,7 @@ static void create_vpmu_vm(void *guest_code)
 
 	/* Make sure that PMUv3 support is indicated in the ID register */
 	dfr0 = vcpu_get_reg(vpmu_vm.vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64DFR0_EL1));
-	pmuver = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer), dfr0);
+	pmuver = FIELD_GET(ID_AA64DFR0_EL1_PMUVer, dfr0);
 	TEST_ASSERT(pmuver != ID_AA64DFR0_EL1_PMUVer_IMP_DEF &&
 		    pmuver >= ID_AA64DFR0_EL1_PMUVer_IMP,
 		    "Unexpected PMUVER (0x%x) on the vCPU with PMUv3", pmuver);
diff --git a/tools/testing/selftests/kvm/lib/arm64/processor.c b/tools/testing/selftests/kvm/lib/arm64/processor.c
index 9d69904cb608..eb115123d741 100644
--- a/tools/testing/selftests/kvm/lib/arm64/processor.c
+++ b/tools/testing/selftests/kvm/lib/arm64/processor.c
@@ -573,15 +573,15 @@ void aarch64_get_supported_page_sizes(uint32_t ipa, uint32_t *ipa4k,
 	err = ioctl(vcpu_fd, KVM_GET_ONE_REG, &reg);
 	TEST_ASSERT(err == 0, KVM_IOCTL_ERROR(KVM_GET_ONE_REG, vcpu_fd));
 
-	gran = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_TGRAN4), val);
+	gran = FIELD_GET(ID_AA64MMFR0_EL1_TGRAN4, val);
 	*ipa4k = max_ipa_for_page_size(ipa, gran, ID_AA64MMFR0_EL1_TGRAN4_NI,
 					ID_AA64MMFR0_EL1_TGRAN4_52_BIT);
 
-	gran = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_TGRAN64), val);
+	gran = FIELD_GET(ID_AA64MMFR0_EL1_TGRAN64, val);
 	*ipa64k = max_ipa_for_page_size(ipa, gran, ID_AA64MMFR0_EL1_TGRAN64_NI,
 					ID_AA64MMFR0_EL1_TGRAN64_IMP);
 
-	gran = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_TGRAN16), val);
+	gran = FIELD_GET(ID_AA64MMFR0_EL1_TGRAN16, val);
 	*ipa16k = max_ipa_for_page_size(ipa, gran, ID_AA64MMFR0_EL1_TGRAN16_NI,
 					ID_AA64MMFR0_EL1_TGRAN16_52_BIT);
 
diff --git a/tools/testing/selftests/mm/mremap_test.c b/tools/testing/selftests/mm/mremap_test.c
index fccf9e797a0c..5bd52a951cbd 100644
--- a/tools/testing/selftests/mm/mremap_test.c
+++ b/tools/testing/selftests/mm/mremap_test.c
@@ -5,10 +5,14 @@
 #define _GNU_SOURCE
 
 #include <errno.h>
+#include <fcntl.h>
+#include <linux/userfaultfd.h>
 #include <stdlib.h>
 #include <stdio.h>
 #include <string.h>
+#include <sys/ioctl.h>
 #include <sys/mman.h>
+#include <syscall.h>
 #include <time.h>
 #include <stdbool.h>
 
@@ -168,6 +172,7 @@ static bool is_range_mapped(FILE *maps_fp, unsigned long start,
 
 		if (first_val <= start && second_val >= end) {
 			success = true;
+			fflush(maps_fp);
 			break;
 		}
 	}
@@ -175,6 +180,15 @@ static bool is_range_mapped(FILE *maps_fp, unsigned long start,
 	return success;
 }
 
+/* Check if [ptr, ptr + size) mapped in /proc/self/maps. */
+static bool is_ptr_mapped(FILE *maps_fp, void *ptr, unsigned long size)
+{
+	unsigned long start = (unsigned long)ptr;
+	unsigned long end = start + size;
+
+	return is_range_mapped(maps_fp, start, end);
+}
+
 /*
  * Returns the start address of the mapping on success, else returns
  * NULL on failure.
@@ -733,6 +747,249 @@ out:
 				      dont_unmap ? " [dontunnmap]" : "");
 }
 
+#ifdef __NR_userfaultfd
+static void mremap_move_multi_invalid_vmas(FILE *maps_fp,
+		unsigned long page_size)
+{
+	char *test_name = "mremap move multiple invalid vmas";
+	const size_t size = 10 * page_size;
+	bool success = true;
+	char *ptr, *tgt_ptr;
+	int uffd, err, i;
+	void *res;
+	struct uffdio_api api = {
+		.api = UFFD_API,
+		.features = UFFD_EVENT_PAGEFAULT,
+	};
+
+	uffd = syscall(__NR_userfaultfd, O_NONBLOCK);
+	if (uffd == -1) {
+		err = errno;
+		perror("userfaultfd");
+		if (err == EPERM) {
+			ksft_test_result_skip("%s - missing uffd", test_name);
+			return;
+		}
+		success = false;
+		goto out;
+	}
+	if (ioctl(uffd, UFFDIO_API, &api)) {
+		perror("ioctl UFFDIO_API");
+		success = false;
+		goto out_close_uffd;
+	}
+
+	ptr = mmap(NULL, size, PROT_READ | PROT_WRITE,
+		   MAP_PRIVATE | MAP_ANON, -1, 0);
+	if (ptr == MAP_FAILED) {
+		perror("mmap");
+		success = false;
+		goto out_close_uffd;
+	}
+
+	tgt_ptr = mmap(NULL, size, PROT_NONE, MAP_PRIVATE | MAP_ANON, -1, 0);
+	if (tgt_ptr == MAP_FAILED) {
+		perror("mmap");
+		success = false;
+		goto out_close_uffd;
+	}
+	if (munmap(tgt_ptr, size)) {
+		perror("munmap");
+		success = false;
+		goto out_unmap;
+	}
+
+	/*
+	 * Unmap so we end up with:
+	 *
+	 *  0   2   4   6   8   10 offset in buffer
+	 * |*| |*| |*| |*| |*|
+	 * |*| |*| |*| |*| |*|
+	 *
+	 * Additionally, register each with UFFD.
+	 */
+	for (i = 0; i < 10; i += 2) {
+		void *unmap_ptr = &ptr[(i + 1) * page_size];
+		unsigned long start = (unsigned long)&ptr[i * page_size];
+		struct uffdio_register reg = {
+			.range = {
+				.start = start,
+				.len = page_size,
+			},
+			.mode = UFFDIO_REGISTER_MODE_MISSING,
+		};
+
+		if (ioctl(uffd, UFFDIO_REGISTER, &reg) == -1) {
+			perror("ioctl UFFDIO_REGISTER");
+			success = false;
+			goto out_unmap;
+		}
+		if (munmap(unmap_ptr, page_size)) {
+			perror("munmap");
+			success = false;
+			goto out_unmap;
+		}
+	}
+
+	/*
+	 * Now try to move the entire range which is invalid for multi VMA move.
+	 *
+	 * This will fail, and no VMA should be moved, as we check this ahead of
+	 * time.
+	 */
+	res = mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_FIXED, tgt_ptr);
+	err = errno;
+	if (res != MAP_FAILED) {
+		fprintf(stderr, "mremap() succeeded for multi VMA uffd armed\n");
+		success = false;
+		goto out_unmap;
+	}
+	if (err != EFAULT) {
+		errno = err;
+		perror("mrmeap() unexpected error");
+		success = false;
+		goto out_unmap;
+	}
+	if (is_ptr_mapped(maps_fp, tgt_ptr, page_size)) {
+		fprintf(stderr,
+			"Invalid uffd-armed VMA at start of multi range moved\n");
+		success = false;
+		goto out_unmap;
+	}
+
+	/*
+	 * Now try to move a single VMA, this should succeed as not multi VMA
+	 * move.
+	 */
+	res = mremap(ptr, page_size, page_size,
+		     MREMAP_MAYMOVE | MREMAP_FIXED, tgt_ptr);
+	if (res == MAP_FAILED) {
+		perror("mremap single invalid-multi VMA");
+		success = false;
+		goto out_unmap;
+	}
+
+	/*
+	 * Unmap the VMA, and remap a non-uffd registered (therefore, multi VMA
+	 * move valid) VMA at the start of ptr range.
+	 */
+	if (munmap(tgt_ptr, page_size)) {
+		perror("munmap");
+		success = false;
+		goto out_unmap;
+	}
+	res = mmap(ptr, page_size, PROT_READ | PROT_WRITE,
+		   MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0);
+	if (res == MAP_FAILED) {
+		perror("mmap");
+		success = false;
+		goto out_unmap;
+	}
+
+	/*
+	 * Now try to move the entire range, we should succeed in moving the
+	 * first VMA, but no others, and report a failure.
+	 */
+	res = mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_FIXED, tgt_ptr);
+	err = errno;
+	if (res != MAP_FAILED) {
+		fprintf(stderr, "mremap() succeeded for multi VMA uffd armed\n");
+		success = false;
+		goto out_unmap;
+	}
+	if (err != EFAULT) {
+		errno = err;
+		perror("mrmeap() unexpected error");
+		success = false;
+		goto out_unmap;
+	}
+	if (!is_ptr_mapped(maps_fp, tgt_ptr, page_size)) {
+		fprintf(stderr, "Valid VMA not moved\n");
+		success = false;
+		goto out_unmap;
+	}
+
+	/*
+	 * Unmap the VMA, and map valid VMA at start of ptr range, and replace
+	 * all existing multi-move invalid VMAs, except the last, with valid
+	 * multi-move VMAs.
+	 */
+	if (munmap(tgt_ptr, page_size)) {
+		perror("munmap");
+		success = false;
+		goto out_unmap;
+	}
+	if (munmap(ptr, size - 2 * page_size)) {
+		perror("munmap");
+		success = false;
+		goto out_unmap;
+	}
+	for (i = 0; i < 8; i += 2) {
+		res = mmap(&ptr[i * page_size], page_size,
+			   PROT_READ | PROT_WRITE,
+			   MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0);
+		if (res == MAP_FAILED) {
+			perror("mmap");
+			success = false;
+			goto out_unmap;
+		}
+	}
+
+	/*
+	 * Now try to move the entire range, we should succeed in moving all but
+	 * the last VMA, and report a failure.
+	 */
+	res = mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_FIXED, tgt_ptr);
+	err = errno;
+	if (res != MAP_FAILED) {
+		fprintf(stderr, "mremap() succeeded for multi VMA uffd armed\n");
+		success = false;
+		goto out_unmap;
+	}
+	if (err != EFAULT) {
+		errno = err;
+		perror("mrmeap() unexpected error");
+		success = false;
+		goto out_unmap;
+	}
+
+	for (i = 0; i < 10; i += 2) {
+		bool is_mapped = is_ptr_mapped(maps_fp,
+				&tgt_ptr[i * page_size], page_size);
+
+		if (i < 8 && !is_mapped) {
+			fprintf(stderr, "Valid VMA not moved at %d\n", i);
+			success = false;
+			goto out_unmap;
+		} else if (i == 8 && is_mapped) {
+			fprintf(stderr, "Invalid VMA moved at %d\n", i);
+			success = false;
+			goto out_unmap;
+		}
+	}
+
+out_unmap:
+	if (munmap(tgt_ptr, size))
+		perror("munmap tgt");
+	if (munmap(ptr, size))
+		perror("munmap src");
+out_close_uffd:
+	close(uffd);
+out:
+	if (success)
+		ksft_test_result_pass("%s\n", test_name);
+	else
+		ksft_test_result_fail("%s\n", test_name);
+}
+#else
+static void mremap_move_multi_invalid_vmas(FILE *maps_fp, unsigned long page_size)
+{
+	char *test_name = "mremap move multiple invalid vmas";
+
+	ksft_test_result_skip("%s - missing uffd", test_name);
+}
+#endif /* __NR_userfaultfd */
+
 /* Returns the time taken for the remap on success else returns -1. */
 static long long remap_region(struct config c, unsigned int threshold_mb,
 			      char *rand_addr)
@@ -1074,7 +1331,7 @@ int main(int argc, char **argv)
 	char *rand_addr;
 	size_t rand_size;
 	int num_expand_tests = 2;
-	int num_misc_tests = 8;
+	int num_misc_tests = 9;
 	struct test test_cases[MAX_TEST] = {};
 	struct test perf_test_cases[MAX_PERF_TEST];
 	int page_size;
@@ -1197,8 +1454,6 @@ int main(int argc, char **argv)
 	mremap_expand_merge(maps_fp, page_size);
 	mremap_expand_merge_offset(maps_fp, page_size);
 
-	fclose(maps_fp);
-
 	mremap_move_within_range(pattern_seed, rand_addr);
 	mremap_move_1mb_from_start(pattern_seed, rand_addr);
 	mremap_shrink_multiple_vmas(page_size, /* inplace= */true);
@@ -1207,6 +1462,9 @@ int main(int argc, char **argv)
 	mremap_move_multiple_vmas(pattern_seed, page_size, /* dontunmap= */ true);
 	mremap_move_multiple_vmas_split(pattern_seed, page_size, /* dontunmap= */ false);
 	mremap_move_multiple_vmas_split(pattern_seed, page_size, /* dontunmap= */ true);
+	mremap_move_multi_invalid_vmas(maps_fp, page_size);
+
+	fclose(maps_fp);
 
 	if (run_perf_tests) {
 		ksft_print_msg("\n%s\n",
diff --git a/tools/testing/selftests/mount_setattr/mount_setattr_test.c b/tools/testing/selftests/mount_setattr/mount_setattr_test.c
index b1e4618399be..a688871a98eb 100644
--- a/tools/testing/selftests/mount_setattr/mount_setattr_test.c
+++ b/tools/testing/selftests/mount_setattr/mount_setattr_test.c
@@ -107,6 +107,26 @@
 	#endif
 #endif
 
+#ifndef __NR_open_tree_attr
+	#if defined __alpha__
+		#define __NR_open_tree_attr 577
+	#elif defined _MIPS_SIM
+		#if _MIPS_SIM == _MIPS_SIM_ABI32	/* o32 */
+			#define __NR_open_tree_attr (467 + 4000)
+		#endif
+		#if _MIPS_SIM == _MIPS_SIM_NABI32	/* n32 */
+			#define __NR_open_tree_attr (467 + 6000)
+		#endif
+		#if _MIPS_SIM == _MIPS_SIM_ABI64	/* n64 */
+			#define __NR_open_tree_attr (467 + 5000)
+		#endif
+	#elif defined __ia64__
+		#define __NR_open_tree_attr (467 + 1024)
+	#else
+		#define __NR_open_tree_attr 467
+	#endif
+#endif
+
 #ifndef MOUNT_ATTR_IDMAP
 #define MOUNT_ATTR_IDMAP 0x00100000
 #endif
@@ -121,6 +141,12 @@ static inline int sys_mount_setattr(int dfd, const char *path, unsigned int flag
 	return syscall(__NR_mount_setattr, dfd, path, flags, attr, size);
 }
 
+static inline int sys_open_tree_attr(int dfd, const char *path, unsigned int flags,
+				     struct mount_attr *attr, size_t size)
+{
+	return syscall(__NR_open_tree_attr, dfd, path, flags, attr, size);
+}
+
 static ssize_t write_nointr(int fd, const void *buf, size_t count)
 {
 	ssize_t ret;
@@ -1222,6 +1248,12 @@ TEST_F(mount_setattr_idmapped, attached_mount_inside_current_mount_namespace)
 	attr.userns_fd	= get_userns_fd(0, 10000, 10000);
 	ASSERT_GE(attr.userns_fd, 0);
 	ASSERT_NE(sys_mount_setattr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0);
+	/*
+	 * Make sure that open_tree_attr() without OPEN_TREE_CLONE is not a way
+	 * to bypass this mount_setattr() restriction.
+	 */
+	ASSERT_LT(sys_open_tree_attr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0);
+
 	ASSERT_EQ(close(attr.userns_fd), 0);
 	ASSERT_EQ(close(open_tree_fd), 0);
 }
@@ -1255,6 +1287,12 @@ TEST_F(mount_setattr_idmapped, attached_mount_outside_current_mount_namespace)
 	ASSERT_GE(attr.userns_fd, 0);
 	ASSERT_NE(sys_mount_setattr(open_tree_fd, "", AT_EMPTY_PATH, &attr,
 				    sizeof(attr)), 0);
+	/*
+	 * Make sure that open_tree_attr() without OPEN_TREE_CLONE is not a way
+	 * to bypass this mount_setattr() restriction.
+	 */
+	ASSERT_LT(sys_open_tree_attr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0);
+
 	ASSERT_EQ(close(attr.userns_fd), 0);
 	ASSERT_EQ(close(open_tree_fd), 0);
 }
@@ -1321,6 +1359,19 @@ TEST_F(mount_setattr_idmapped, detached_mount_outside_current_mount_namespace)
 	ASSERT_EQ(close(open_tree_fd), 0);
 }
 
+static bool expected_uid_gid(int dfd, const char *path, int flags,
+			     uid_t expected_uid, gid_t expected_gid)
+{
+	int ret;
+	struct stat st;
+
+	ret = fstatat(dfd, path, &st, flags);
+	if (ret < 0)
+		return false;
+
+	return st.st_uid == expected_uid && st.st_gid == expected_gid;
+}
+
 /**
  * Validate that currently changing the idmapping of an idmapped mount fails.
  */
@@ -1331,6 +1382,8 @@ TEST_F(mount_setattr_idmapped, change_idmapping)
 		.attr_set = MOUNT_ATTR_IDMAP,
 	};
 
+	ASSERT_TRUE(expected_uid_gid(-EBADF, "/mnt/D", 0, 0, 0));
+
 	if (!mount_setattr_supported())
 		SKIP(return, "mount_setattr syscall not supported");
 
@@ -1348,27 +1401,25 @@ TEST_F(mount_setattr_idmapped, change_idmapping)
 				    AT_EMPTY_PATH, &attr, sizeof(attr)), 0);
 	ASSERT_EQ(close(attr.userns_fd), 0);
 
+	EXPECT_FALSE(expected_uid_gid(open_tree_fd, ".", 0, 0, 0));
+	EXPECT_TRUE(expected_uid_gid(open_tree_fd, ".", 0, 10000, 10000));
+
 	/* Change idmapping on a detached mount that is already idmapped. */
 	attr.userns_fd	= get_userns_fd(0, 20000, 10000);
 	ASSERT_GE(attr.userns_fd, 0);
 	ASSERT_NE(sys_mount_setattr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0);
+	/*
+	 * Make sure that open_tree_attr() without OPEN_TREE_CLONE is not a way
+	 * to bypass this mount_setattr() restriction.
+	 */
+	EXPECT_LT(sys_open_tree_attr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0);
+	EXPECT_FALSE(expected_uid_gid(open_tree_fd, ".", 0, 20000, 20000));
+	EXPECT_TRUE(expected_uid_gid(open_tree_fd, ".", 0, 10000, 10000));
+
 	ASSERT_EQ(close(attr.userns_fd), 0);
 	ASSERT_EQ(close(open_tree_fd), 0);
 }
 
-static bool expected_uid_gid(int dfd, const char *path, int flags,
-			     uid_t expected_uid, gid_t expected_gid)
-{
-	int ret;
-	struct stat st;
-
-	ret = fstatat(dfd, path, &st, flags);
-	if (ret < 0)
-		return false;
-
-	return st.st_uid == expected_uid && st.st_gid == expected_gid;
-}
-
 TEST_F(mount_setattr_idmapped, idmap_mount_tree_invalid)
 {
 	int open_tree_fd = -EBADF;
diff --git a/tools/testing/selftests/namespaces/.gitignore b/tools/testing/selftests/namespaces/.gitignore
new file mode 100644
index 000000000000..7639dbf58bbf
--- /dev/null
+++ b/tools/testing/selftests/namespaces/.gitignore
@@ -0,0 +1,2 @@
+nsid_test
+file_handle_test
diff --git a/tools/testing/selftests/namespaces/Makefile b/tools/testing/selftests/namespaces/Makefile
new file mode 100644
index 000000000000..f6c117ce2c2b
--- /dev/null
+++ b/tools/testing/selftests/namespaces/Makefile
@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0-only
+CFLAGS += -Wall -O0 -g $(KHDR_INCLUDES) $(TOOLS_INCLUDES)
+
+TEST_GEN_PROGS := nsid_test file_handle_test
+
+include ../lib.mk
+
diff --git a/tools/testing/selftests/namespaces/config b/tools/testing/selftests/namespaces/config
new file mode 100644
index 000000000000..d09836260262
--- /dev/null
+++ b/tools/testing/selftests/namespaces/config
@@ -0,0 +1,7 @@
+CONFIG_UTS_NS=y
+CONFIG_TIME_NS=y
+CONFIG_IPC_NS=y
+CONFIG_USER_NS=y
+CONFIG_PID_NS=y
+CONFIG_NET_NS=y
+CONFIG_CGROUPS=y
diff --git a/tools/testing/selftests/namespaces/file_handle_test.c b/tools/testing/selftests/namespaces/file_handle_test.c
new file mode 100644
index 000000000000..f1bc5773f552
--- /dev/null
+++ b/tools/testing/selftests/namespaces/file_handle_test.c
@@ -0,0 +1,1429 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <grp.h>
+#include <limits.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/mount.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include <linux/unistd.h>
+#include "../kselftest_harness.h"
+
+#ifndef FD_NSFS_ROOT
+#define FD_NSFS_ROOT -10003 /* Root of the nsfs filesystem */
+#endif
+
+TEST(nsfs_net_handle)
+{
+	struct file_handle *handle;
+	int mount_id;
+	int ret;
+	int fd;
+	int ns_fd;
+	struct stat st1, st2;
+
+	/* Drop to unprivileged uid/gid */
+	ASSERT_EQ(setresgid(65534, 65534, 65534), 0); /* nogroup */
+	ASSERT_EQ(setresuid(65534, 65534, 65534), 0); /* nobody */
+
+	handle = malloc(sizeof(*handle) + MAX_HANDLE_SZ);
+	ASSERT_NE(handle, NULL);
+
+	/* Open a namespace file descriptor */
+	ns_fd = open("/proc/self/ns/net", O_RDONLY);
+	ASSERT_GE(ns_fd, 0);
+
+	/* Get handle for the namespace */
+	handle->handle_bytes = MAX_HANDLE_SZ;
+	ret = name_to_handle_at(ns_fd, "", handle, &mount_id, AT_EMPTY_PATH);
+	if (ret < 0 && errno == EOPNOTSUPP) {
+		SKIP(free(handle); close(ns_fd);
+		     return, "nsfs doesn't support file handles");
+	}
+	ASSERT_EQ(ret, 0);
+	ASSERT_GT(handle->handle_bytes, 0);
+
+	/* Try to open using FD_NSFS_ROOT as unprivileged user */
+	fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+	if (fd < 0 && (errno == EINVAL || errno == EOPNOTSUPP)) {
+		SKIP(free(handle); close(ns_fd);
+		     return,
+			   "open_by_handle_at with FD_NSFS_ROOT not supported");
+	}
+	if (fd < 0 && errno == EPERM) {
+		SKIP(free(handle); close(ns_fd);
+		     return,
+			   "Permission denied for unprivileged user (expected)");
+	}
+	ASSERT_GE(fd, 0);
+
+	/* Verify we opened the correct namespace */
+	ASSERT_EQ(fstat(ns_fd, &st1), 0);
+	ASSERT_EQ(fstat(fd, &st2), 0);
+	ASSERT_EQ(st1.st_ino, st2.st_ino);
+	ASSERT_EQ(st1.st_dev, st2.st_dev);
+
+	close(fd);
+	close(ns_fd);
+	free(handle);
+}
+
+TEST(nsfs_uts_handle)
+{
+	struct file_handle *handle;
+	int mount_id;
+	int ret;
+	int fd;
+	int ns_fd;
+	struct stat st1, st2;
+
+	/* Drop to unprivileged uid/gid */
+	ASSERT_EQ(setresgid(65534, 65534, 65534), 0); /* nogroup */
+	ASSERT_EQ(setresuid(65534, 65534, 65534), 0); /* nobody */
+
+	handle = malloc(sizeof(*handle) + MAX_HANDLE_SZ);
+	ASSERT_NE(handle, NULL);
+
+	/* Open UTS namespace file descriptor */
+	ns_fd = open("/proc/self/ns/uts", O_RDONLY);
+	ASSERT_GE(ns_fd, 0);
+
+	/* Get handle for the namespace */
+	handle->handle_bytes = MAX_HANDLE_SZ;
+	ret = name_to_handle_at(ns_fd, "", handle, &mount_id, AT_EMPTY_PATH);
+	if (ret < 0 && errno == EOPNOTSUPP) {
+		SKIP(free(handle); close(ns_fd);
+		     return, "nsfs doesn't support file handles");
+	}
+	ASSERT_EQ(ret, 0);
+	ASSERT_GT(handle->handle_bytes, 0);
+
+	/* Try to open using FD_NSFS_ROOT */
+	fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+	if (fd < 0 && (errno == EINVAL || errno == EOPNOTSUPP)) {
+		SKIP(free(handle); close(ns_fd);
+		     return,
+			   "open_by_handle_at with FD_NSFS_ROOT not supported");
+	}
+	ASSERT_GE(fd, 0);
+
+	/* Verify we opened the correct namespace */
+	ASSERT_EQ(fstat(ns_fd, &st1), 0);
+	ASSERT_EQ(fstat(fd, &st2), 0);
+	ASSERT_EQ(st1.st_ino, st2.st_ino);
+	ASSERT_EQ(st1.st_dev, st2.st_dev);
+
+	close(fd);
+	close(ns_fd);
+	free(handle);
+}
+
+TEST(nsfs_ipc_handle)
+{
+	struct file_handle *handle;
+	int mount_id;
+	int ret;
+	int fd;
+	int ns_fd;
+	struct stat st1, st2;
+
+	/* Drop to unprivileged uid/gid */
+	ASSERT_EQ(setresgid(65534, 65534, 65534), 0); /* nogroup */
+	ASSERT_EQ(setresuid(65534, 65534, 65534), 0); /* nobody */
+
+	handle = malloc(sizeof(*handle) + MAX_HANDLE_SZ);
+	ASSERT_NE(handle, NULL);
+
+	/* Open IPC namespace file descriptor */
+	ns_fd = open("/proc/self/ns/ipc", O_RDONLY);
+	ASSERT_GE(ns_fd, 0);
+
+	/* Get handle for the namespace */
+	handle->handle_bytes = MAX_HANDLE_SZ;
+	ret = name_to_handle_at(ns_fd, "", handle, &mount_id, AT_EMPTY_PATH);
+	if (ret < 0 && errno == EOPNOTSUPP) {
+		SKIP(free(handle); close(ns_fd);
+		     return, "nsfs doesn't support file handles");
+	}
+	ASSERT_EQ(ret, 0);
+	ASSERT_GT(handle->handle_bytes, 0);
+
+	/* Try to open using FD_NSFS_ROOT */
+	fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+	if (fd < 0 && (errno == EINVAL || errno == EOPNOTSUPP)) {
+		SKIP(free(handle); close(ns_fd);
+		     return,
+			   "open_by_handle_at with FD_NSFS_ROOT not supported");
+	}
+	ASSERT_GE(fd, 0);
+
+	/* Verify we opened the correct namespace */
+	ASSERT_EQ(fstat(ns_fd, &st1), 0);
+	ASSERT_EQ(fstat(fd, &st2), 0);
+	ASSERT_EQ(st1.st_ino, st2.st_ino);
+	ASSERT_EQ(st1.st_dev, st2.st_dev);
+
+	close(fd);
+	close(ns_fd);
+	free(handle);
+}
+
+TEST(nsfs_pid_handle)
+{
+	struct file_handle *handle;
+	int mount_id;
+	int ret;
+	int fd;
+	int ns_fd;
+	struct stat st1, st2;
+
+	/* Drop to unprivileged uid/gid */
+	ASSERT_EQ(setresgid(65534, 65534, 65534), 0); /* nogroup */
+	ASSERT_EQ(setresuid(65534, 65534, 65534), 0); /* nobody */
+
+	handle = malloc(sizeof(*handle) + MAX_HANDLE_SZ);
+	ASSERT_NE(handle, NULL);
+
+	/* Open PID namespace file descriptor */
+	ns_fd = open("/proc/self/ns/pid", O_RDONLY);
+	ASSERT_GE(ns_fd, 0);
+
+	/* Get handle for the namespace */
+	handle->handle_bytes = MAX_HANDLE_SZ;
+	ret = name_to_handle_at(ns_fd, "", handle, &mount_id, AT_EMPTY_PATH);
+	if (ret < 0 && errno == EOPNOTSUPP) {
+		SKIP(free(handle); close(ns_fd);
+		     return, "nsfs doesn't support file handles");
+	}
+	ASSERT_EQ(ret, 0);
+	ASSERT_GT(handle->handle_bytes, 0);
+
+	/* Try to open using FD_NSFS_ROOT */
+	fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+	if (fd < 0 && (errno == EINVAL || errno == EOPNOTSUPP)) {
+		SKIP(free(handle); close(ns_fd);
+		     return,
+			   "open_by_handle_at with FD_NSFS_ROOT not supported");
+	}
+	ASSERT_GE(fd, 0);
+
+	/* Verify we opened the correct namespace */
+	ASSERT_EQ(fstat(ns_fd, &st1), 0);
+	ASSERT_EQ(fstat(fd, &st2), 0);
+	ASSERT_EQ(st1.st_ino, st2.st_ino);
+	ASSERT_EQ(st1.st_dev, st2.st_dev);
+
+	close(fd);
+	close(ns_fd);
+	free(handle);
+}
+
+TEST(nsfs_mnt_handle)
+{
+	struct file_handle *handle;
+	int mount_id;
+	int ret;
+	int fd;
+	int ns_fd;
+	struct stat st1, st2;
+
+	/* Drop to unprivileged uid/gid */
+	ASSERT_EQ(setresgid(65534, 65534, 65534), 0); /* nogroup */
+	ASSERT_EQ(setresuid(65534, 65534, 65534), 0); /* nobody */
+
+	handle = malloc(sizeof(*handle) + MAX_HANDLE_SZ);
+	ASSERT_NE(handle, NULL);
+
+	/* Open mount namespace file descriptor */
+	ns_fd = open("/proc/self/ns/mnt", O_RDONLY);
+	ASSERT_GE(ns_fd, 0);
+
+	/* Get handle for the namespace */
+	handle->handle_bytes = MAX_HANDLE_SZ;
+	ret = name_to_handle_at(ns_fd, "", handle, &mount_id, AT_EMPTY_PATH);
+	if (ret < 0 && errno == EOPNOTSUPP) {
+		SKIP(free(handle); close(ns_fd);
+		     return, "nsfs doesn't support file handles");
+	}
+	ASSERT_EQ(ret, 0);
+	ASSERT_GT(handle->handle_bytes, 0);
+
+	/* Try to open using FD_NSFS_ROOT */
+	fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+	if (fd < 0 && (errno == EINVAL || errno == EOPNOTSUPP)) {
+		SKIP(free(handle); close(ns_fd);
+		     return,
+			   "open_by_handle_at with FD_NSFS_ROOT not supported");
+	}
+	ASSERT_GE(fd, 0);
+
+	/* Verify we opened the correct namespace */
+	ASSERT_EQ(fstat(ns_fd, &st1), 0);
+	ASSERT_EQ(fstat(fd, &st2), 0);
+	ASSERT_EQ(st1.st_ino, st2.st_ino);
+	ASSERT_EQ(st1.st_dev, st2.st_dev);
+
+	close(fd);
+	close(ns_fd);
+	free(handle);
+}
+
+TEST(nsfs_user_handle)
+{
+	struct file_handle *handle;
+	int mount_id;
+	int ret;
+	int fd;
+	int ns_fd;
+	struct stat st1, st2;
+
+	/* Drop to unprivileged uid/gid */
+	ASSERT_EQ(setresgid(65534, 65534, 65534), 0); /* nogroup */
+	ASSERT_EQ(setresuid(65534, 65534, 65534), 0); /* nobody */
+
+	handle = malloc(sizeof(*handle) + MAX_HANDLE_SZ);
+	ASSERT_NE(handle, NULL);
+
+	/* Open user namespace file descriptor */
+	ns_fd = open("/proc/self/ns/user", O_RDONLY);
+	ASSERT_GE(ns_fd, 0);
+
+	/* Get handle for the namespace */
+	handle->handle_bytes = MAX_HANDLE_SZ;
+	ret = name_to_handle_at(ns_fd, "", handle, &mount_id, AT_EMPTY_PATH);
+	if (ret < 0 && errno == EOPNOTSUPP) {
+		SKIP(free(handle); close(ns_fd);
+		     return, "nsfs doesn't support file handles");
+	}
+	ASSERT_EQ(ret, 0);
+	ASSERT_GT(handle->handle_bytes, 0);
+
+	/* Try to open using FD_NSFS_ROOT */
+	fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+	if (fd < 0 && (errno == EINVAL || errno == EOPNOTSUPP)) {
+		SKIP(free(handle); close(ns_fd);
+		     return,
+			   "open_by_handle_at with FD_NSFS_ROOT not supported");
+	}
+	ASSERT_GE(fd, 0);
+
+	/* Verify we opened the correct namespace */
+	ASSERT_EQ(fstat(ns_fd, &st1), 0);
+	ASSERT_EQ(fstat(fd, &st2), 0);
+	ASSERT_EQ(st1.st_ino, st2.st_ino);
+	ASSERT_EQ(st1.st_dev, st2.st_dev);
+
+	close(fd);
+	close(ns_fd);
+	free(handle);
+}
+
+TEST(nsfs_cgroup_handle)
+{
+	struct file_handle *handle;
+	int mount_id;
+	int ret;
+	int fd;
+	int ns_fd;
+	struct stat st1, st2;
+
+	/* Drop to unprivileged uid/gid */
+	ASSERT_EQ(setresgid(65534, 65534, 65534), 0); /* nogroup */
+	ASSERT_EQ(setresuid(65534, 65534, 65534), 0); /* nobody */
+
+	handle = malloc(sizeof(*handle) + MAX_HANDLE_SZ);
+	ASSERT_NE(handle, NULL);
+
+	/* Open cgroup namespace file descriptor */
+	ns_fd = open("/proc/self/ns/cgroup", O_RDONLY);
+	if (ns_fd < 0) {
+		SKIP(free(handle); return, "cgroup namespace not available");
+	}
+
+	/* Get handle for the namespace */
+	handle->handle_bytes = MAX_HANDLE_SZ;
+	ret = name_to_handle_at(ns_fd, "", handle, &mount_id, AT_EMPTY_PATH);
+	if (ret < 0 && errno == EOPNOTSUPP) {
+		SKIP(free(handle); close(ns_fd);
+		     return, "nsfs doesn't support file handles");
+	}
+	ASSERT_EQ(ret, 0);
+	ASSERT_GT(handle->handle_bytes, 0);
+
+	/* Try to open using FD_NSFS_ROOT */
+	fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+	if (fd < 0 && (errno == EINVAL || errno == EOPNOTSUPP)) {
+		SKIP(free(handle); close(ns_fd);
+		     return,
+			   "open_by_handle_at with FD_NSFS_ROOT not supported");
+	}
+	ASSERT_GE(fd, 0);
+
+	/* Verify we opened the correct namespace */
+	ASSERT_EQ(fstat(ns_fd, &st1), 0);
+	ASSERT_EQ(fstat(fd, &st2), 0);
+	ASSERT_EQ(st1.st_ino, st2.st_ino);
+	ASSERT_EQ(st1.st_dev, st2.st_dev);
+
+	close(fd);
+	close(ns_fd);
+	free(handle);
+}
+
+TEST(nsfs_time_handle)
+{
+	struct file_handle *handle;
+	int mount_id;
+	int ret;
+	int fd;
+	int ns_fd;
+	struct stat st1, st2;
+
+	/* Drop to unprivileged uid/gid */
+	ASSERT_EQ(setresgid(65534, 65534, 65534), 0); /* nogroup */
+	ASSERT_EQ(setresuid(65534, 65534, 65534), 0); /* nobody */
+
+	handle = malloc(sizeof(*handle) + MAX_HANDLE_SZ);
+	ASSERT_NE(handle, NULL);
+
+	/* Open time namespace file descriptor */
+	ns_fd = open("/proc/self/ns/time", O_RDONLY);
+	if (ns_fd < 0) {
+		SKIP(free(handle); return, "time namespace not available");
+	}
+
+	/* Get handle for the namespace */
+	handle->handle_bytes = MAX_HANDLE_SZ;
+	ret = name_to_handle_at(ns_fd, "", handle, &mount_id, AT_EMPTY_PATH);
+	if (ret < 0 && errno == EOPNOTSUPP) {
+		SKIP(free(handle); close(ns_fd);
+		     return, "nsfs doesn't support file handles");
+	}
+	ASSERT_EQ(ret, 0);
+	ASSERT_GT(handle->handle_bytes, 0);
+
+	/* Try to open using FD_NSFS_ROOT */
+	fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+	if (fd < 0 && (errno == EINVAL || errno == EOPNOTSUPP)) {
+		SKIP(free(handle); close(ns_fd);
+		     return,
+			   "open_by_handle_at with FD_NSFS_ROOT not supported");
+	}
+	ASSERT_GE(fd, 0);
+
+	/* Verify we opened the correct namespace */
+	ASSERT_EQ(fstat(ns_fd, &st1), 0);
+	ASSERT_EQ(fstat(fd, &st2), 0);
+	ASSERT_EQ(st1.st_ino, st2.st_ino);
+	ASSERT_EQ(st1.st_dev, st2.st_dev);
+
+	close(fd);
+	close(ns_fd);
+	free(handle);
+}
+
+TEST(nsfs_user_net_namespace_isolation)
+{
+	struct file_handle *handle;
+	int mount_id;
+	int ret;
+	int fd;
+	int ns_fd;
+	pid_t pid;
+	int status;
+	int pipefd[2];
+	char result;
+
+	handle = malloc(sizeof(*handle) + MAX_HANDLE_SZ);
+	ASSERT_NE(handle, NULL);
+
+	/* Create pipe for communication */
+	ASSERT_EQ(pipe(pipefd), 0);
+
+	/* Get handle for current network namespace */
+	ns_fd = open("/proc/self/ns/net", O_RDONLY);
+	ASSERT_GE(ns_fd, 0);
+
+	handle->handle_bytes = MAX_HANDLE_SZ;
+	ret = name_to_handle_at(ns_fd, "", handle, &mount_id, AT_EMPTY_PATH);
+	if (ret < 0 && errno == EOPNOTSUPP) {
+		SKIP(free(handle); close(ns_fd); close(pipefd[0]);
+		     close(pipefd[1]);
+		     return, "nsfs doesn't support file handles");
+	}
+	ASSERT_EQ(ret, 0);
+	close(ns_fd);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+
+	if (pid == 0) {
+		/* Child process */
+		close(pipefd[0]);
+
+		/* First create new user namespace to drop privileges */
+		ret = unshare(CLONE_NEWUSER);
+		if (ret < 0) {
+			write(pipefd[1], "U",
+			      1); /* Unable to create user namespace */
+			close(pipefd[1]);
+			exit(0);
+		}
+
+		/* Write uid/gid mappings to maintain some capabilities */
+		int uid_map_fd = open("/proc/self/uid_map", O_WRONLY);
+		int gid_map_fd = open("/proc/self/gid_map", O_WRONLY);
+		int setgroups_fd = open("/proc/self/setgroups", O_WRONLY);
+
+		if (uid_map_fd < 0 || gid_map_fd < 0 || setgroups_fd < 0) {
+			write(pipefd[1], "M", 1); /* Unable to set mappings */
+			close(pipefd[1]);
+			exit(0);
+		}
+
+		/* Disable setgroups to allow gid mapping */
+		write(setgroups_fd, "deny", 4);
+		close(setgroups_fd);
+
+		/* Map current uid/gid to root in the new namespace */
+		char mapping[64];
+		snprintf(mapping, sizeof(mapping), "0 %d 1", getuid());
+		write(uid_map_fd, mapping, strlen(mapping));
+		close(uid_map_fd);
+
+		snprintf(mapping, sizeof(mapping), "0 %d 1", getgid());
+		write(gid_map_fd, mapping, strlen(mapping));
+		close(gid_map_fd);
+
+		/* Now create new network namespace */
+		ret = unshare(CLONE_NEWNET);
+		if (ret < 0) {
+			write(pipefd[1], "N",
+			      1); /* Unable to create network namespace */
+			close(pipefd[1]);
+			exit(0);
+		}
+
+		/* Try to open parent's network namespace handle from new user+net namespace */
+		fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+
+		if (fd >= 0) {
+			/* Should NOT succeed - we're in a different user namespace */
+			write(pipefd[1], "S", 1); /* Unexpected success */
+			close(fd);
+		} else if (errno == ESTALE) {
+			/* Expected: Stale file handle */
+			write(pipefd[1], "P", 1);
+		} else {
+			/* Other error */
+			write(pipefd[1], "F", 1);
+		}
+
+		close(pipefd[1]);
+		exit(0);
+	}
+
+	/* Parent process */
+	close(pipefd[1]);
+	ASSERT_EQ(read(pipefd[0], &result, 1), 1);
+
+	waitpid(pid, &status, 0);
+	ASSERT_TRUE(WIFEXITED(status));
+	ASSERT_EQ(WEXITSTATUS(status), 0);
+
+	if (result == 'U') {
+		SKIP(free(handle); close(pipefd[0]);
+		     return, "Cannot create new user namespace");
+	}
+	if (result == 'M') {
+		SKIP(free(handle); close(pipefd[0]);
+		     return, "Cannot set uid/gid mappings");
+	}
+	if (result == 'N') {
+		SKIP(free(handle); close(pipefd[0]);
+		     return, "Cannot create new network namespace");
+	}
+
+	/* Should fail with permission denied since we're in a different user namespace */
+	ASSERT_EQ(result, 'P');
+
+	close(pipefd[0]);
+	free(handle);
+}
+
+TEST(nsfs_user_uts_namespace_isolation)
+{
+	struct file_handle *handle;
+	int mount_id;
+	int ret;
+	int fd;
+	int ns_fd;
+	pid_t pid;
+	int status;
+	int pipefd[2];
+	char result;
+
+	handle = malloc(sizeof(*handle) + MAX_HANDLE_SZ);
+	ASSERT_NE(handle, NULL);
+
+	/* Create pipe for communication */
+	ASSERT_EQ(pipe(pipefd), 0);
+
+	/* Get handle for current UTS namespace */
+	ns_fd = open("/proc/self/ns/uts", O_RDONLY);
+	ASSERT_GE(ns_fd, 0);
+
+	handle->handle_bytes = MAX_HANDLE_SZ;
+	ret = name_to_handle_at(ns_fd, "", handle, &mount_id, AT_EMPTY_PATH);
+	if (ret < 0 && errno == EOPNOTSUPP) {
+		SKIP(free(handle); close(ns_fd); close(pipefd[0]);
+		     close(pipefd[1]);
+		     return, "nsfs doesn't support file handles");
+	}
+	ASSERT_EQ(ret, 0);
+	close(ns_fd);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+
+	if (pid == 0) {
+		/* Child process */
+		close(pipefd[0]);
+
+		/* First create new user namespace to drop privileges */
+		ret = unshare(CLONE_NEWUSER);
+		if (ret < 0) {
+			write(pipefd[1], "U",
+			      1); /* Unable to create user namespace */
+			close(pipefd[1]);
+			exit(0);
+		}
+
+		/* Write uid/gid mappings to maintain some capabilities */
+		int uid_map_fd = open("/proc/self/uid_map", O_WRONLY);
+		int gid_map_fd = open("/proc/self/gid_map", O_WRONLY);
+		int setgroups_fd = open("/proc/self/setgroups", O_WRONLY);
+
+		if (uid_map_fd < 0 || gid_map_fd < 0 || setgroups_fd < 0) {
+			write(pipefd[1], "M", 1); /* Unable to set mappings */
+			close(pipefd[1]);
+			exit(0);
+		}
+
+		/* Disable setgroups to allow gid mapping */
+		write(setgroups_fd, "deny", 4);
+		close(setgroups_fd);
+
+		/* Map current uid/gid to root in the new namespace */
+		char mapping[64];
+		snprintf(mapping, sizeof(mapping), "0 %d 1", getuid());
+		write(uid_map_fd, mapping, strlen(mapping));
+		close(uid_map_fd);
+
+		snprintf(mapping, sizeof(mapping), "0 %d 1", getgid());
+		write(gid_map_fd, mapping, strlen(mapping));
+		close(gid_map_fd);
+
+		/* Now create new UTS namespace */
+		ret = unshare(CLONE_NEWUTS);
+		if (ret < 0) {
+			write(pipefd[1], "N",
+			      1); /* Unable to create UTS namespace */
+			close(pipefd[1]);
+			exit(0);
+		}
+
+		/* Try to open parent's UTS namespace handle from new user+uts namespace */
+		fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+
+		if (fd >= 0) {
+			/* Should NOT succeed - we're in a different user namespace */
+			write(pipefd[1], "S", 1); /* Unexpected success */
+			close(fd);
+		} else if (errno == ESTALE) {
+			/* Expected: Stale file handle */
+			write(pipefd[1], "P", 1);
+		} else {
+			/* Other error */
+			write(pipefd[1], "F", 1);
+		}
+
+		close(pipefd[1]);
+		exit(0);
+	}
+
+	/* Parent process */
+	close(pipefd[1]);
+	ASSERT_EQ(read(pipefd[0], &result, 1), 1);
+
+	waitpid(pid, &status, 0);
+	ASSERT_TRUE(WIFEXITED(status));
+	ASSERT_EQ(WEXITSTATUS(status), 0);
+
+	if (result == 'U') {
+		SKIP(free(handle); close(pipefd[0]);
+		     return, "Cannot create new user namespace");
+	}
+	if (result == 'M') {
+		SKIP(free(handle); close(pipefd[0]);
+		     return, "Cannot set uid/gid mappings");
+	}
+	if (result == 'N') {
+		SKIP(free(handle); close(pipefd[0]);
+		     return, "Cannot create new UTS namespace");
+	}
+
+	/* Should fail with ESTALE since we're in a different user namespace */
+	ASSERT_EQ(result, 'P');
+
+	close(pipefd[0]);
+	free(handle);
+}
+
+TEST(nsfs_user_ipc_namespace_isolation)
+{
+	struct file_handle *handle;
+	int mount_id;
+	int ret;
+	int fd;
+	int ns_fd;
+	pid_t pid;
+	int status;
+	int pipefd[2];
+	char result;
+
+	handle = malloc(sizeof(*handle) + MAX_HANDLE_SZ);
+	ASSERT_NE(handle, NULL);
+
+	/* Create pipe for communication */
+	ASSERT_EQ(pipe(pipefd), 0);
+
+	/* Get handle for current IPC namespace */
+	ns_fd = open("/proc/self/ns/ipc", O_RDONLY);
+	ASSERT_GE(ns_fd, 0);
+
+	handle->handle_bytes = MAX_HANDLE_SZ;
+	ret = name_to_handle_at(ns_fd, "", handle, &mount_id, AT_EMPTY_PATH);
+	if (ret < 0 && errno == EOPNOTSUPP) {
+		SKIP(free(handle); close(ns_fd); close(pipefd[0]);
+		     close(pipefd[1]);
+		     return, "nsfs doesn't support file handles");
+	}
+	ASSERT_EQ(ret, 0);
+	close(ns_fd);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+
+	if (pid == 0) {
+		/* Child process */
+		close(pipefd[0]);
+
+		/* First create new user namespace to drop privileges */
+		ret = unshare(CLONE_NEWUSER);
+		if (ret < 0) {
+			write(pipefd[1], "U",
+			      1); /* Unable to create user namespace */
+			close(pipefd[1]);
+			exit(0);
+		}
+
+		/* Write uid/gid mappings to maintain some capabilities */
+		int uid_map_fd = open("/proc/self/uid_map", O_WRONLY);
+		int gid_map_fd = open("/proc/self/gid_map", O_WRONLY);
+		int setgroups_fd = open("/proc/self/setgroups", O_WRONLY);
+
+		if (uid_map_fd < 0 || gid_map_fd < 0 || setgroups_fd < 0) {
+			write(pipefd[1], "M", 1); /* Unable to set mappings */
+			close(pipefd[1]);
+			exit(0);
+		}
+
+		/* Disable setgroups to allow gid mapping */
+		write(setgroups_fd, "deny", 4);
+		close(setgroups_fd);
+
+		/* Map current uid/gid to root in the new namespace */
+		char mapping[64];
+		snprintf(mapping, sizeof(mapping), "0 %d 1", getuid());
+		write(uid_map_fd, mapping, strlen(mapping));
+		close(uid_map_fd);
+
+		snprintf(mapping, sizeof(mapping), "0 %d 1", getgid());
+		write(gid_map_fd, mapping, strlen(mapping));
+		close(gid_map_fd);
+
+		/* Now create new IPC namespace */
+		ret = unshare(CLONE_NEWIPC);
+		if (ret < 0) {
+			write(pipefd[1], "N",
+			      1); /* Unable to create IPC namespace */
+			close(pipefd[1]);
+			exit(0);
+		}
+
+		/* Try to open parent's IPC namespace handle from new user+ipc namespace */
+		fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+
+		if (fd >= 0) {
+			/* Should NOT succeed - we're in a different user namespace */
+			write(pipefd[1], "S", 1); /* Unexpected success */
+			close(fd);
+		} else if (errno == ESTALE) {
+			/* Expected: Stale file handle */
+			write(pipefd[1], "P", 1);
+		} else {
+			/* Other error */
+			write(pipefd[1], "F", 1);
+		}
+
+		close(pipefd[1]);
+		exit(0);
+	}
+
+	/* Parent process */
+	close(pipefd[1]);
+	ASSERT_EQ(read(pipefd[0], &result, 1), 1);
+
+	waitpid(pid, &status, 0);
+	ASSERT_TRUE(WIFEXITED(status));
+	ASSERT_EQ(WEXITSTATUS(status), 0);
+
+	if (result == 'U') {
+		SKIP(free(handle); close(pipefd[0]);
+		     return, "Cannot create new user namespace");
+	}
+	if (result == 'M') {
+		SKIP(free(handle); close(pipefd[0]);
+		     return, "Cannot set uid/gid mappings");
+	}
+	if (result == 'N') {
+		SKIP(free(handle); close(pipefd[0]);
+		     return, "Cannot create new IPC namespace");
+	}
+
+	/* Should fail with ESTALE since we're in a different user namespace */
+	ASSERT_EQ(result, 'P');
+
+	close(pipefd[0]);
+	free(handle);
+}
+
+TEST(nsfs_user_mnt_namespace_isolation)
+{
+	struct file_handle *handle;
+	int mount_id;
+	int ret;
+	int fd;
+	int ns_fd;
+	pid_t pid;
+	int status;
+	int pipefd[2];
+	char result;
+
+	handle = malloc(sizeof(*handle) + MAX_HANDLE_SZ);
+	ASSERT_NE(handle, NULL);
+
+	/* Create pipe for communication */
+	ASSERT_EQ(pipe(pipefd), 0);
+
+	/* Get handle for current mount namespace */
+	ns_fd = open("/proc/self/ns/mnt", O_RDONLY);
+	ASSERT_GE(ns_fd, 0);
+
+	handle->handle_bytes = MAX_HANDLE_SZ;
+	ret = name_to_handle_at(ns_fd, "", handle, &mount_id, AT_EMPTY_PATH);
+	if (ret < 0 && errno == EOPNOTSUPP) {
+		SKIP(free(handle); close(ns_fd); close(pipefd[0]);
+		     close(pipefd[1]);
+		     return, "nsfs doesn't support file handles");
+	}
+	ASSERT_EQ(ret, 0);
+	close(ns_fd);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+
+	if (pid == 0) {
+		/* Child process */
+		close(pipefd[0]);
+
+		/* First create new user namespace to drop privileges */
+		ret = unshare(CLONE_NEWUSER);
+		if (ret < 0) {
+			write(pipefd[1], "U",
+			      1); /* Unable to create user namespace */
+			close(pipefd[1]);
+			exit(0);
+		}
+
+		/* Write uid/gid mappings to maintain some capabilities */
+		int uid_map_fd = open("/proc/self/uid_map", O_WRONLY);
+		int gid_map_fd = open("/proc/self/gid_map", O_WRONLY);
+		int setgroups_fd = open("/proc/self/setgroups", O_WRONLY);
+
+		if (uid_map_fd < 0 || gid_map_fd < 0 || setgroups_fd < 0) {
+			write(pipefd[1], "M", 1); /* Unable to set mappings */
+			close(pipefd[1]);
+			exit(0);
+		}
+
+		/* Disable setgroups to allow gid mapping */
+		write(setgroups_fd, "deny", 4);
+		close(setgroups_fd);
+
+		/* Map current uid/gid to root in the new namespace */
+		char mapping[64];
+		snprintf(mapping, sizeof(mapping), "0 %d 1", getuid());
+		write(uid_map_fd, mapping, strlen(mapping));
+		close(uid_map_fd);
+
+		snprintf(mapping, sizeof(mapping), "0 %d 1", getgid());
+		write(gid_map_fd, mapping, strlen(mapping));
+		close(gid_map_fd);
+
+		/* Now create new mount namespace */
+		ret = unshare(CLONE_NEWNS);
+		if (ret < 0) {
+			write(pipefd[1], "N",
+			      1); /* Unable to create mount namespace */
+			close(pipefd[1]);
+			exit(0);
+		}
+
+		/* Try to open parent's mount namespace handle from new user+mnt namespace */
+		fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+
+		if (fd >= 0) {
+			/* Should NOT succeed - we're in a different user namespace */
+			write(pipefd[1], "S", 1); /* Unexpected success */
+			close(fd);
+		} else if (errno == ESTALE) {
+			/* Expected: Stale file handle */
+			write(pipefd[1], "P", 1);
+		} else {
+			/* Other error */
+			write(pipefd[1], "F", 1);
+		}
+
+		close(pipefd[1]);
+		exit(0);
+	}
+
+	/* Parent process */
+	close(pipefd[1]);
+	ASSERT_EQ(read(pipefd[0], &result, 1), 1);
+
+	waitpid(pid, &status, 0);
+	ASSERT_TRUE(WIFEXITED(status));
+	ASSERT_EQ(WEXITSTATUS(status), 0);
+
+	if (result == 'U') {
+		SKIP(free(handle); close(pipefd[0]);
+		     return, "Cannot create new user namespace");
+	}
+	if (result == 'M') {
+		SKIP(free(handle); close(pipefd[0]);
+		     return, "Cannot set uid/gid mappings");
+	}
+	if (result == 'N') {
+		SKIP(free(handle); close(pipefd[0]);
+		     return, "Cannot create new mount namespace");
+	}
+
+	/* Should fail with ESTALE since we're in a different user namespace */
+	ASSERT_EQ(result, 'P');
+
+	close(pipefd[0]);
+	free(handle);
+}
+
+TEST(nsfs_user_cgroup_namespace_isolation)
+{
+	struct file_handle *handle;
+	int mount_id;
+	int ret;
+	int fd;
+	int ns_fd;
+	pid_t pid;
+	int status;
+	int pipefd[2];
+	char result;
+
+	handle = malloc(sizeof(*handle) + MAX_HANDLE_SZ);
+	ASSERT_NE(handle, NULL);
+
+	/* Create pipe for communication */
+	ASSERT_EQ(pipe(pipefd), 0);
+
+	/* Get handle for current cgroup namespace */
+	ns_fd = open("/proc/self/ns/cgroup", O_RDONLY);
+	if (ns_fd < 0) {
+		SKIP(free(handle); close(pipefd[0]); close(pipefd[1]);
+		     return, "cgroup namespace not available");
+	}
+
+	handle->handle_bytes = MAX_HANDLE_SZ;
+	ret = name_to_handle_at(ns_fd, "", handle, &mount_id, AT_EMPTY_PATH);
+	if (ret < 0 && errno == EOPNOTSUPP) {
+		SKIP(free(handle); close(ns_fd); close(pipefd[0]);
+		     close(pipefd[1]);
+		     return, "nsfs doesn't support file handles");
+	}
+	ASSERT_EQ(ret, 0);
+	close(ns_fd);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+
+	if (pid == 0) {
+		/* Child process */
+		close(pipefd[0]);
+
+		/* First create new user namespace to drop privileges */
+		ret = unshare(CLONE_NEWUSER);
+		if (ret < 0) {
+			write(pipefd[1], "U",
+			      1); /* Unable to create user namespace */
+			close(pipefd[1]);
+			exit(0);
+		}
+
+		/* Write uid/gid mappings to maintain some capabilities */
+		int uid_map_fd = open("/proc/self/uid_map", O_WRONLY);
+		int gid_map_fd = open("/proc/self/gid_map", O_WRONLY);
+		int setgroups_fd = open("/proc/self/setgroups", O_WRONLY);
+
+		if (uid_map_fd < 0 || gid_map_fd < 0 || setgroups_fd < 0) {
+			write(pipefd[1], "M", 1); /* Unable to set mappings */
+			close(pipefd[1]);
+			exit(0);
+		}
+
+		/* Disable setgroups to allow gid mapping */
+		write(setgroups_fd, "deny", 4);
+		close(setgroups_fd);
+
+		/* Map current uid/gid to root in the new namespace */
+		char mapping[64];
+		snprintf(mapping, sizeof(mapping), "0 %d 1", getuid());
+		write(uid_map_fd, mapping, strlen(mapping));
+		close(uid_map_fd);
+
+		snprintf(mapping, sizeof(mapping), "0 %d 1", getgid());
+		write(gid_map_fd, mapping, strlen(mapping));
+		close(gid_map_fd);
+
+		/* Now create new cgroup namespace */
+		ret = unshare(CLONE_NEWCGROUP);
+		if (ret < 0) {
+			write(pipefd[1], "N",
+			      1); /* Unable to create cgroup namespace */
+			close(pipefd[1]);
+			exit(0);
+		}
+
+		/* Try to open parent's cgroup namespace handle from new user+cgroup namespace */
+		fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+
+		if (fd >= 0) {
+			/* Should NOT succeed - we're in a different user namespace */
+			write(pipefd[1], "S", 1); /* Unexpected success */
+			close(fd);
+		} else if (errno == ESTALE) {
+			/* Expected: Stale file handle */
+			write(pipefd[1], "P", 1);
+		} else {
+			/* Other error */
+			write(pipefd[1], "F", 1);
+		}
+
+		close(pipefd[1]);
+		exit(0);
+	}
+
+	/* Parent process */
+	close(pipefd[1]);
+	ASSERT_EQ(read(pipefd[0], &result, 1), 1);
+
+	waitpid(pid, &status, 0);
+	ASSERT_TRUE(WIFEXITED(status));
+	ASSERT_EQ(WEXITSTATUS(status), 0);
+
+	if (result == 'U') {
+		SKIP(free(handle); close(pipefd[0]);
+		     return, "Cannot create new user namespace");
+	}
+	if (result == 'M') {
+		SKIP(free(handle); close(pipefd[0]);
+		     return, "Cannot set uid/gid mappings");
+	}
+	if (result == 'N') {
+		SKIP(free(handle); close(pipefd[0]);
+		     return, "Cannot create new cgroup namespace");
+	}
+
+	/* Should fail with ESTALE since we're in a different user namespace */
+	ASSERT_EQ(result, 'P');
+
+	close(pipefd[0]);
+	free(handle);
+}
+
+TEST(nsfs_user_pid_namespace_isolation)
+{
+	struct file_handle *handle;
+	int mount_id;
+	int ret;
+	int fd;
+	int ns_fd;
+	pid_t pid;
+	int status;
+	int pipefd[2];
+	char result;
+
+	handle = malloc(sizeof(*handle) + MAX_HANDLE_SZ);
+	ASSERT_NE(handle, NULL);
+
+	/* Create pipe for communication */
+	ASSERT_EQ(pipe(pipefd), 0);
+
+	/* Get handle for current PID namespace */
+	ns_fd = open("/proc/self/ns/pid", O_RDONLY);
+	ASSERT_GE(ns_fd, 0);
+
+	handle->handle_bytes = MAX_HANDLE_SZ;
+	ret = name_to_handle_at(ns_fd, "", handle, &mount_id, AT_EMPTY_PATH);
+	if (ret < 0 && errno == EOPNOTSUPP) {
+		SKIP(free(handle); close(ns_fd); close(pipefd[0]);
+		     close(pipefd[1]);
+		     return, "nsfs doesn't support file handles");
+	}
+	ASSERT_EQ(ret, 0);
+	close(ns_fd);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+
+	if (pid == 0) {
+		/* Child process */
+		close(pipefd[0]);
+
+		/* First create new user namespace to drop privileges */
+		ret = unshare(CLONE_NEWUSER);
+		if (ret < 0) {
+			write(pipefd[1], "U",
+			      1); /* Unable to create user namespace */
+			close(pipefd[1]);
+			exit(0);
+		}
+
+		/* Write uid/gid mappings to maintain some capabilities */
+		int uid_map_fd = open("/proc/self/uid_map", O_WRONLY);
+		int gid_map_fd = open("/proc/self/gid_map", O_WRONLY);
+		int setgroups_fd = open("/proc/self/setgroups", O_WRONLY);
+
+		if (uid_map_fd < 0 || gid_map_fd < 0 || setgroups_fd < 0) {
+			write(pipefd[1], "M", 1); /* Unable to set mappings */
+			close(pipefd[1]);
+			exit(0);
+		}
+
+		/* Disable setgroups to allow gid mapping */
+		write(setgroups_fd, "deny", 4);
+		close(setgroups_fd);
+
+		/* Map current uid/gid to root in the new namespace */
+		char mapping[64];
+		snprintf(mapping, sizeof(mapping), "0 %d 1", getuid());
+		write(uid_map_fd, mapping, strlen(mapping));
+		close(uid_map_fd);
+
+		snprintf(mapping, sizeof(mapping), "0 %d 1", getgid());
+		write(gid_map_fd, mapping, strlen(mapping));
+		close(gid_map_fd);
+
+		/* Now create new PID namespace - requires fork to take effect */
+		ret = unshare(CLONE_NEWPID);
+		if (ret < 0) {
+			write(pipefd[1], "N",
+			      1); /* Unable to create PID namespace */
+			close(pipefd[1]);
+			exit(0);
+		}
+
+		/* Fork again for PID namespace to take effect */
+		pid_t child_pid = fork();
+		if (child_pid < 0) {
+			write(pipefd[1], "N",
+			      1); /* Unable to fork in PID namespace */
+			close(pipefd[1]);
+			exit(0);
+		}
+
+		if (child_pid == 0) {
+			/* Grandchild in new PID namespace */
+			/* Try to open parent's PID namespace handle from new user+pid namespace */
+			fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+
+			if (fd >= 0) {
+				/* Should NOT succeed - we're in a different user namespace */
+				write(pipefd[1], "S",
+				      1); /* Unexpected success */
+				close(fd);
+			} else if (errno == ESTALE) {
+				/* Expected: Stale file handle */
+				write(pipefd[1], "P", 1);
+			} else {
+				/* Other error */
+				write(pipefd[1], "F", 1);
+			}
+
+			close(pipefd[1]);
+			exit(0);
+		}
+
+		/* Wait for grandchild */
+		waitpid(child_pid, NULL, 0);
+		exit(0);
+	}
+
+	/* Parent process */
+	close(pipefd[1]);
+	ASSERT_EQ(read(pipefd[0], &result, 1), 1);
+
+	waitpid(pid, &status, 0);
+	ASSERT_TRUE(WIFEXITED(status));
+	ASSERT_EQ(WEXITSTATUS(status), 0);
+
+	if (result == 'U') {
+		SKIP(free(handle); close(pipefd[0]);
+		     return, "Cannot create new user namespace");
+	}
+	if (result == 'M') {
+		SKIP(free(handle); close(pipefd[0]);
+		     return, "Cannot set uid/gid mappings");
+	}
+	if (result == 'N') {
+		SKIP(free(handle); close(pipefd[0]);
+		     return, "Cannot create new PID namespace");
+	}
+
+	/* Should fail with ESTALE since we're in a different user namespace */
+	ASSERT_EQ(result, 'P');
+
+	close(pipefd[0]);
+	free(handle);
+}
+
+TEST(nsfs_user_time_namespace_isolation)
+{
+	struct file_handle *handle;
+	int mount_id;
+	int ret;
+	int fd;
+	int ns_fd;
+	pid_t pid;
+	int status;
+	int pipefd[2];
+	char result;
+
+	handle = malloc(sizeof(*handle) + MAX_HANDLE_SZ);
+	ASSERT_NE(handle, NULL);
+
+	/* Create pipe for communication */
+	ASSERT_EQ(pipe(pipefd), 0);
+
+	/* Get handle for current time namespace */
+	ns_fd = open("/proc/self/ns/time", O_RDONLY);
+	if (ns_fd < 0) {
+		SKIP(free(handle); close(pipefd[0]); close(pipefd[1]);
+		     return, "time namespace not available");
+	}
+
+	handle->handle_bytes = MAX_HANDLE_SZ;
+	ret = name_to_handle_at(ns_fd, "", handle, &mount_id, AT_EMPTY_PATH);
+	if (ret < 0 && errno == EOPNOTSUPP) {
+		SKIP(free(handle); close(ns_fd); close(pipefd[0]);
+		     close(pipefd[1]);
+		     return, "nsfs doesn't support file handles");
+	}
+	ASSERT_EQ(ret, 0);
+	close(ns_fd);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+
+	if (pid == 0) {
+		/* Child process */
+		close(pipefd[0]);
+
+		/* First create new user namespace to drop privileges */
+		ret = unshare(CLONE_NEWUSER);
+		if (ret < 0) {
+			write(pipefd[1], "U",
+			      1); /* Unable to create user namespace */
+			close(pipefd[1]);
+			exit(0);
+		}
+
+		/* Write uid/gid mappings to maintain some capabilities */
+		int uid_map_fd = open("/proc/self/uid_map", O_WRONLY);
+		int gid_map_fd = open("/proc/self/gid_map", O_WRONLY);
+		int setgroups_fd = open("/proc/self/setgroups", O_WRONLY);
+
+		if (uid_map_fd < 0 || gid_map_fd < 0 || setgroups_fd < 0) {
+			write(pipefd[1], "M", 1); /* Unable to set mappings */
+			close(pipefd[1]);
+			exit(0);
+		}
+
+		/* Disable setgroups to allow gid mapping */
+		write(setgroups_fd, "deny", 4);
+		close(setgroups_fd);
+
+		/* Map current uid/gid to root in the new namespace */
+		char mapping[64];
+		snprintf(mapping, sizeof(mapping), "0 %d 1", getuid());
+		write(uid_map_fd, mapping, strlen(mapping));
+		close(uid_map_fd);
+
+		snprintf(mapping, sizeof(mapping), "0 %d 1", getgid());
+		write(gid_map_fd, mapping, strlen(mapping));
+		close(gid_map_fd);
+
+		/* Now create new time namespace - requires fork to take effect */
+		ret = unshare(CLONE_NEWTIME);
+		if (ret < 0) {
+			write(pipefd[1], "N",
+			      1); /* Unable to create time namespace */
+			close(pipefd[1]);
+			exit(0);
+		}
+
+		/* Fork again for time namespace to take effect */
+		pid_t child_pid = fork();
+		if (child_pid < 0) {
+			write(pipefd[1], "N",
+			      1); /* Unable to fork in time namespace */
+			close(pipefd[1]);
+			exit(0);
+		}
+
+		if (child_pid == 0) {
+			/* Grandchild in new time namespace */
+			/* Try to open parent's time namespace handle from new user+time namespace */
+			fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+
+			if (fd >= 0) {
+				/* Should NOT succeed - we're in a different user namespace */
+				write(pipefd[1], "S",
+				      1); /* Unexpected success */
+				close(fd);
+			} else if (errno == ESTALE) {
+				/* Expected: Stale file handle */
+				write(pipefd[1], "P", 1);
+			} else {
+				/* Other error */
+				write(pipefd[1], "F", 1);
+			}
+
+			close(pipefd[1]);
+			exit(0);
+		}
+
+		/* Wait for grandchild */
+		waitpid(child_pid, NULL, 0);
+		exit(0);
+	}
+
+	/* Parent process */
+	close(pipefd[1]);
+	ASSERT_EQ(read(pipefd[0], &result, 1), 1);
+
+	waitpid(pid, &status, 0);
+	ASSERT_TRUE(WIFEXITED(status));
+	ASSERT_EQ(WEXITSTATUS(status), 0);
+
+	if (result == 'U') {
+		SKIP(free(handle); close(pipefd[0]);
+		     return, "Cannot create new user namespace");
+	}
+	if (result == 'M') {
+		SKIP(free(handle); close(pipefd[0]);
+		     return, "Cannot set uid/gid mappings");
+	}
+	if (result == 'N') {
+		SKIP(free(handle); close(pipefd[0]);
+		     return, "Cannot create new time namespace");
+	}
+
+	/* Should fail with ESTALE since we're in a different user namespace */
+	ASSERT_EQ(result, 'P');
+
+	close(pipefd[0]);
+	free(handle);
+}
+
+TEST(nsfs_open_flags)
+{
+	struct file_handle *handle;
+	int mount_id;
+	int ret;
+	int fd;
+	int ns_fd;
+
+	handle = malloc(sizeof(*handle) + MAX_HANDLE_SZ);
+	ASSERT_NE(handle, NULL);
+
+	/* Open a namespace file descriptor */
+	ns_fd = open("/proc/self/ns/net", O_RDONLY);
+	ASSERT_GE(ns_fd, 0);
+
+	/* Get handle for the namespace */
+	handle->handle_bytes = MAX_HANDLE_SZ;
+	ret = name_to_handle_at(ns_fd, "", handle, &mount_id, AT_EMPTY_PATH);
+	if (ret < 0 && errno == EOPNOTSUPP) {
+		SKIP(free(handle); close(ns_fd);
+		     return, "nsfs doesn't support file handles");
+	}
+	ASSERT_EQ(ret, 0);
+	ASSERT_GT(handle->handle_bytes, 0);
+
+	/* Test invalid flags that should fail */
+	fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_WRONLY);
+	ASSERT_LT(fd, 0);
+	ASSERT_EQ(errno, EPERM);
+
+	fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDWR);
+	ASSERT_LT(fd, 0);
+	ASSERT_EQ(errno, EPERM);
+
+	fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_TRUNC);
+	ASSERT_LT(fd, 0);
+	ASSERT_EQ(errno, EPERM);
+
+	fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_DIRECT);
+	ASSERT_LT(fd, 0);
+	ASSERT_EQ(errno, EINVAL);
+
+	fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_TMPFILE);
+	ASSERT_LT(fd, 0);
+	ASSERT_EQ(errno, EINVAL);
+
+	fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_DIRECTORY);
+	ASSERT_LT(fd, 0);
+	ASSERT_EQ(errno, ENOTDIR);
+
+	close(ns_fd);
+	free(handle);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/namespaces/nsid_test.c b/tools/testing/selftests/namespaces/nsid_test.c
new file mode 100644
index 000000000000..e28accd74a57
--- /dev/null
+++ b/tools/testing/selftests/namespaces/nsid_test.c
@@ -0,0 +1,986 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <assert.h>
+#include <fcntl.h>
+#include <inttypes.h>
+#include <libgen.h>
+#include <limits.h>
+#include <pthread.h>
+#include <string.h>
+#include <sys/mount.h>
+#include <poll.h>
+#include <sys/epoll.h>
+#include <sys/resource.h>
+#include <sys/stat.h>
+#include <sys/socket.h>
+#include <sys/un.h>
+#include <unistd.h>
+#include <linux/fs.h>
+#include <linux/limits.h>
+#include <linux/nsfs.h>
+#include "../kselftest_harness.h"
+
+TEST(nsid_mntns_basic)
+{
+	__u64 mnt_ns_id = 0;
+	int fd_mntns;
+	int ret;
+
+	/* Open the current mount namespace */
+	fd_mntns = open("/proc/self/ns/mnt", O_RDONLY);
+	ASSERT_GE(fd_mntns, 0);
+
+	/* Get the mount namespace ID */
+	ret = ioctl(fd_mntns, NS_GET_MNTNS_ID, &mnt_ns_id);
+	ASSERT_EQ(ret, 0);
+	ASSERT_NE(mnt_ns_id, 0);
+
+	/* Verify we can get the same ID again */
+	__u64 mnt_ns_id2 = 0;
+	ret = ioctl(fd_mntns, NS_GET_ID, &mnt_ns_id2);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(mnt_ns_id, mnt_ns_id2);
+
+	close(fd_mntns);
+}
+
+TEST(nsid_mntns_separate)
+{
+	__u64 parent_mnt_ns_id = 0;
+	__u64 child_mnt_ns_id = 0;
+	int fd_parent_mntns, fd_child_mntns;
+	int ret;
+	pid_t pid;
+	int pipefd[2];
+
+	/* Get parent's mount namespace ID */
+	fd_parent_mntns = open("/proc/self/ns/mnt", O_RDONLY);
+	ASSERT_GE(fd_parent_mntns, 0);
+	ret = ioctl(fd_parent_mntns, NS_GET_ID, &parent_mnt_ns_id);
+	ASSERT_EQ(ret, 0);
+	ASSERT_NE(parent_mnt_ns_id, 0);
+
+	/* Create a pipe for synchronization */
+	ASSERT_EQ(pipe(pipefd), 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+
+	if (pid == 0) {
+		/* Child process */
+		close(pipefd[0]);
+
+		/* Create new mount namespace */
+		ret = unshare(CLONE_NEWNS);
+		if (ret != 0) {
+			/* Skip test if we don't have permission */
+			if (errno == EPERM || errno == EACCES) {
+				write(pipefd[1], "S", 1); /* Signal skip */
+				_exit(0);
+			}
+			_exit(1);
+		}
+
+		/* Signal success */
+		write(pipefd[1], "Y", 1);
+		close(pipefd[1]);
+
+		/* Keep namespace alive */
+		pause();
+		_exit(0);
+	}
+
+	/* Parent process */
+	close(pipefd[1]);
+
+	char buf;
+	ASSERT_EQ(read(pipefd[0], &buf, 1), 1);
+	close(pipefd[0]);
+
+	if (buf == 'S') {
+		/* Child couldn't create namespace, skip test */
+		kill(pid, SIGTERM);
+		waitpid(pid, NULL, 0);
+		close(fd_parent_mntns);
+		SKIP(return, "No permission to create mount namespace");
+	}
+
+	ASSERT_EQ(buf, 'Y');
+
+	/* Open child's mount namespace */
+	char path[256];
+	snprintf(path, sizeof(path), "/proc/%d/ns/mnt", pid);
+	fd_child_mntns = open(path, O_RDONLY);
+	ASSERT_GE(fd_child_mntns, 0);
+
+	/* Get child's mount namespace ID */
+	ret = ioctl(fd_child_mntns, NS_GET_ID, &child_mnt_ns_id);
+	ASSERT_EQ(ret, 0);
+	ASSERT_NE(child_mnt_ns_id, 0);
+
+	/* Parent and child should have different mount namespace IDs */
+	ASSERT_NE(parent_mnt_ns_id, child_mnt_ns_id);
+
+	close(fd_parent_mntns);
+	close(fd_child_mntns);
+
+	/* Clean up child process */
+	kill(pid, SIGTERM);
+	waitpid(pid, NULL, 0);
+}
+
+TEST(nsid_cgroupns_basic)
+{
+	__u64 cgroup_ns_id = 0;
+	int fd_cgroupns;
+	int ret;
+
+	/* Open the current cgroup namespace */
+	fd_cgroupns = open("/proc/self/ns/cgroup", O_RDONLY);
+	ASSERT_GE(fd_cgroupns, 0);
+
+	/* Get the cgroup namespace ID */
+	ret = ioctl(fd_cgroupns, NS_GET_ID, &cgroup_ns_id);
+	ASSERT_EQ(ret, 0);
+	ASSERT_NE(cgroup_ns_id, 0);
+
+	/* Verify we can get the same ID again */
+	__u64 cgroup_ns_id2 = 0;
+	ret = ioctl(fd_cgroupns, NS_GET_ID, &cgroup_ns_id2);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(cgroup_ns_id, cgroup_ns_id2);
+
+	close(fd_cgroupns);
+}
+
+TEST(nsid_cgroupns_separate)
+{
+	__u64 parent_cgroup_ns_id = 0;
+	__u64 child_cgroup_ns_id = 0;
+	int fd_parent_cgroupns, fd_child_cgroupns;
+	int ret;
+	pid_t pid;
+	int pipefd[2];
+
+	/* Get parent's cgroup namespace ID */
+	fd_parent_cgroupns = open("/proc/self/ns/cgroup", O_RDONLY);
+	ASSERT_GE(fd_parent_cgroupns, 0);
+	ret = ioctl(fd_parent_cgroupns, NS_GET_ID, &parent_cgroup_ns_id);
+	ASSERT_EQ(ret, 0);
+	ASSERT_NE(parent_cgroup_ns_id, 0);
+
+	/* Create a pipe for synchronization */
+	ASSERT_EQ(pipe(pipefd), 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+
+	if (pid == 0) {
+		/* Child process */
+		close(pipefd[0]);
+
+		/* Create new cgroup namespace */
+		ret = unshare(CLONE_NEWCGROUP);
+		if (ret != 0) {
+			/* Skip test if we don't have permission */
+			if (errno == EPERM || errno == EACCES) {
+				write(pipefd[1], "S", 1); /* Signal skip */
+				_exit(0);
+			}
+			_exit(1);
+		}
+
+		/* Signal success */
+		write(pipefd[1], "Y", 1);
+		close(pipefd[1]);
+
+		/* Keep namespace alive */
+		pause();
+		_exit(0);
+	}
+
+	/* Parent process */
+	close(pipefd[1]);
+
+	char buf;
+	ASSERT_EQ(read(pipefd[0], &buf, 1), 1);
+	close(pipefd[0]);
+
+	if (buf == 'S') {
+		/* Child couldn't create namespace, skip test */
+		kill(pid, SIGTERM);
+		waitpid(pid, NULL, 0);
+		close(fd_parent_cgroupns);
+		SKIP(return, "No permission to create cgroup namespace");
+	}
+
+	ASSERT_EQ(buf, 'Y');
+
+	/* Open child's cgroup namespace */
+	char path[256];
+	snprintf(path, sizeof(path), "/proc/%d/ns/cgroup", pid);
+	fd_child_cgroupns = open(path, O_RDONLY);
+	ASSERT_GE(fd_child_cgroupns, 0);
+
+	/* Get child's cgroup namespace ID */
+	ret = ioctl(fd_child_cgroupns, NS_GET_ID, &child_cgroup_ns_id);
+	ASSERT_EQ(ret, 0);
+	ASSERT_NE(child_cgroup_ns_id, 0);
+
+	/* Parent and child should have different cgroup namespace IDs */
+	ASSERT_NE(parent_cgroup_ns_id, child_cgroup_ns_id);
+
+	close(fd_parent_cgroupns);
+	close(fd_child_cgroupns);
+
+	/* Clean up child process */
+	kill(pid, SIGTERM);
+	waitpid(pid, NULL, 0);
+}
+
+TEST(nsid_ipcns_basic)
+{
+	__u64 ipc_ns_id = 0;
+	int fd_ipcns;
+	int ret;
+
+	/* Open the current IPC namespace */
+	fd_ipcns = open("/proc/self/ns/ipc", O_RDONLY);
+	ASSERT_GE(fd_ipcns, 0);
+
+	/* Get the IPC namespace ID */
+	ret = ioctl(fd_ipcns, NS_GET_ID, &ipc_ns_id);
+	ASSERT_EQ(ret, 0);
+	ASSERT_NE(ipc_ns_id, 0);
+
+	/* Verify we can get the same ID again */
+	__u64 ipc_ns_id2 = 0;
+	ret = ioctl(fd_ipcns, NS_GET_ID, &ipc_ns_id2);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(ipc_ns_id, ipc_ns_id2);
+
+	close(fd_ipcns);
+}
+
+TEST(nsid_ipcns_separate)
+{
+	__u64 parent_ipc_ns_id = 0;
+	__u64 child_ipc_ns_id = 0;
+	int fd_parent_ipcns, fd_child_ipcns;
+	int ret;
+	pid_t pid;
+	int pipefd[2];
+
+	/* Get parent's IPC namespace ID */
+	fd_parent_ipcns = open("/proc/self/ns/ipc", O_RDONLY);
+	ASSERT_GE(fd_parent_ipcns, 0);
+	ret = ioctl(fd_parent_ipcns, NS_GET_ID, &parent_ipc_ns_id);
+	ASSERT_EQ(ret, 0);
+	ASSERT_NE(parent_ipc_ns_id, 0);
+
+	/* Create a pipe for synchronization */
+	ASSERT_EQ(pipe(pipefd), 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+
+	if (pid == 0) {
+		/* Child process */
+		close(pipefd[0]);
+
+		/* Create new IPC namespace */
+		ret = unshare(CLONE_NEWIPC);
+		if (ret != 0) {
+			/* Skip test if we don't have permission */
+			if (errno == EPERM || errno == EACCES) {
+				write(pipefd[1], "S", 1); /* Signal skip */
+				_exit(0);
+			}
+			_exit(1);
+		}
+
+		/* Signal success */
+		write(pipefd[1], "Y", 1);
+		close(pipefd[1]);
+
+		/* Keep namespace alive */
+		pause();
+		_exit(0);
+	}
+
+	/* Parent process */
+	close(pipefd[1]);
+
+	char buf;
+	ASSERT_EQ(read(pipefd[0], &buf, 1), 1);
+	close(pipefd[0]);
+
+	if (buf == 'S') {
+		/* Child couldn't create namespace, skip test */
+		kill(pid, SIGTERM);
+		waitpid(pid, NULL, 0);
+		close(fd_parent_ipcns);
+		SKIP(return, "No permission to create IPC namespace");
+	}
+
+	ASSERT_EQ(buf, 'Y');
+
+	/* Open child's IPC namespace */
+	char path[256];
+	snprintf(path, sizeof(path), "/proc/%d/ns/ipc", pid);
+	fd_child_ipcns = open(path, O_RDONLY);
+	ASSERT_GE(fd_child_ipcns, 0);
+
+	/* Get child's IPC namespace ID */
+	ret = ioctl(fd_child_ipcns, NS_GET_ID, &child_ipc_ns_id);
+	ASSERT_EQ(ret, 0);
+	ASSERT_NE(child_ipc_ns_id, 0);
+
+	/* Parent and child should have different IPC namespace IDs */
+	ASSERT_NE(parent_ipc_ns_id, child_ipc_ns_id);
+
+	close(fd_parent_ipcns);
+	close(fd_child_ipcns);
+
+	/* Clean up child process */
+	kill(pid, SIGTERM);
+	waitpid(pid, NULL, 0);
+}
+
+TEST(nsid_utsns_basic)
+{
+	__u64 uts_ns_id = 0;
+	int fd_utsns;
+	int ret;
+
+	/* Open the current UTS namespace */
+	fd_utsns = open("/proc/self/ns/uts", O_RDONLY);
+	ASSERT_GE(fd_utsns, 0);
+
+	/* Get the UTS namespace ID */
+	ret = ioctl(fd_utsns, NS_GET_ID, &uts_ns_id);
+	ASSERT_EQ(ret, 0);
+	ASSERT_NE(uts_ns_id, 0);
+
+	/* Verify we can get the same ID again */
+	__u64 uts_ns_id2 = 0;
+	ret = ioctl(fd_utsns, NS_GET_ID, &uts_ns_id2);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(uts_ns_id, uts_ns_id2);
+
+	close(fd_utsns);
+}
+
+TEST(nsid_utsns_separate)
+{
+	__u64 parent_uts_ns_id = 0;
+	__u64 child_uts_ns_id = 0;
+	int fd_parent_utsns, fd_child_utsns;
+	int ret;
+	pid_t pid;
+	int pipefd[2];
+
+	/* Get parent's UTS namespace ID */
+	fd_parent_utsns = open("/proc/self/ns/uts", O_RDONLY);
+	ASSERT_GE(fd_parent_utsns, 0);
+	ret = ioctl(fd_parent_utsns, NS_GET_ID, &parent_uts_ns_id);
+	ASSERT_EQ(ret, 0);
+	ASSERT_NE(parent_uts_ns_id, 0);
+
+	/* Create a pipe for synchronization */
+	ASSERT_EQ(pipe(pipefd), 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+
+	if (pid == 0) {
+		/* Child process */
+		close(pipefd[0]);
+
+		/* Create new UTS namespace */
+		ret = unshare(CLONE_NEWUTS);
+		if (ret != 0) {
+			/* Skip test if we don't have permission */
+			if (errno == EPERM || errno == EACCES) {
+				write(pipefd[1], "S", 1); /* Signal skip */
+				_exit(0);
+			}
+			_exit(1);
+		}
+
+		/* Signal success */
+		write(pipefd[1], "Y", 1);
+		close(pipefd[1]);
+
+		/* Keep namespace alive */
+		pause();
+		_exit(0);
+	}
+
+	/* Parent process */
+	close(pipefd[1]);
+
+	char buf;
+	ASSERT_EQ(read(pipefd[0], &buf, 1), 1);
+	close(pipefd[0]);
+
+	if (buf == 'S') {
+		/* Child couldn't create namespace, skip test */
+		kill(pid, SIGTERM);
+		waitpid(pid, NULL, 0);
+		close(fd_parent_utsns);
+		SKIP(return, "No permission to create UTS namespace");
+	}
+
+	ASSERT_EQ(buf, 'Y');
+
+	/* Open child's UTS namespace */
+	char path[256];
+	snprintf(path, sizeof(path), "/proc/%d/ns/uts", pid);
+	fd_child_utsns = open(path, O_RDONLY);
+	ASSERT_GE(fd_child_utsns, 0);
+
+	/* Get child's UTS namespace ID */
+	ret = ioctl(fd_child_utsns, NS_GET_ID, &child_uts_ns_id);
+	ASSERT_EQ(ret, 0);
+	ASSERT_NE(child_uts_ns_id, 0);
+
+	/* Parent and child should have different UTS namespace IDs */
+	ASSERT_NE(parent_uts_ns_id, child_uts_ns_id);
+
+	close(fd_parent_utsns);
+	close(fd_child_utsns);
+
+	/* Clean up child process */
+	kill(pid, SIGTERM);
+	waitpid(pid, NULL, 0);
+}
+
+TEST(nsid_userns_basic)
+{
+	__u64 user_ns_id = 0;
+	int fd_userns;
+	int ret;
+
+	/* Open the current user namespace */
+	fd_userns = open("/proc/self/ns/user", O_RDONLY);
+	ASSERT_GE(fd_userns, 0);
+
+	/* Get the user namespace ID */
+	ret = ioctl(fd_userns, NS_GET_ID, &user_ns_id);
+	ASSERT_EQ(ret, 0);
+	ASSERT_NE(user_ns_id, 0);
+
+	/* Verify we can get the same ID again */
+	__u64 user_ns_id2 = 0;
+	ret = ioctl(fd_userns, NS_GET_ID, &user_ns_id2);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(user_ns_id, user_ns_id2);
+
+	close(fd_userns);
+}
+
+TEST(nsid_userns_separate)
+{
+	__u64 parent_user_ns_id = 0;
+	__u64 child_user_ns_id = 0;
+	int fd_parent_userns, fd_child_userns;
+	int ret;
+	pid_t pid;
+	int pipefd[2];
+
+	/* Get parent's user namespace ID */
+	fd_parent_userns = open("/proc/self/ns/user", O_RDONLY);
+	ASSERT_GE(fd_parent_userns, 0);
+	ret = ioctl(fd_parent_userns, NS_GET_ID, &parent_user_ns_id);
+	ASSERT_EQ(ret, 0);
+	ASSERT_NE(parent_user_ns_id, 0);
+
+	/* Create a pipe for synchronization */
+	ASSERT_EQ(pipe(pipefd), 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+
+	if (pid == 0) {
+		/* Child process */
+		close(pipefd[0]);
+
+		/* Create new user namespace */
+		ret = unshare(CLONE_NEWUSER);
+		if (ret != 0) {
+			/* Skip test if we don't have permission */
+			if (errno == EPERM || errno == EACCES) {
+				write(pipefd[1], "S", 1); /* Signal skip */
+				_exit(0);
+			}
+			_exit(1);
+		}
+
+		/* Signal success */
+		write(pipefd[1], "Y", 1);
+		close(pipefd[1]);
+
+		/* Keep namespace alive */
+		pause();
+		_exit(0);
+	}
+
+	/* Parent process */
+	close(pipefd[1]);
+
+	char buf;
+	ASSERT_EQ(read(pipefd[0], &buf, 1), 1);
+	close(pipefd[0]);
+
+	if (buf == 'S') {
+		/* Child couldn't create namespace, skip test */
+		kill(pid, SIGTERM);
+		waitpid(pid, NULL, 0);
+		close(fd_parent_userns);
+		SKIP(return, "No permission to create user namespace");
+	}
+
+	ASSERT_EQ(buf, 'Y');
+
+	/* Open child's user namespace */
+	char path[256];
+	snprintf(path, sizeof(path), "/proc/%d/ns/user", pid);
+	fd_child_userns = open(path, O_RDONLY);
+	ASSERT_GE(fd_child_userns, 0);
+
+	/* Get child's user namespace ID */
+	ret = ioctl(fd_child_userns, NS_GET_ID, &child_user_ns_id);
+	ASSERT_EQ(ret, 0);
+	ASSERT_NE(child_user_ns_id, 0);
+
+	/* Parent and child should have different user namespace IDs */
+	ASSERT_NE(parent_user_ns_id, child_user_ns_id);
+
+	close(fd_parent_userns);
+	close(fd_child_userns);
+
+	/* Clean up child process */
+	kill(pid, SIGTERM);
+	waitpid(pid, NULL, 0);
+}
+
+TEST(nsid_timens_basic)
+{
+	__u64 time_ns_id = 0;
+	int fd_timens;
+	int ret;
+
+	/* Open the current time namespace */
+	fd_timens = open("/proc/self/ns/time", O_RDONLY);
+	if (fd_timens < 0) {
+		SKIP(return, "Time namespaces not supported");
+	}
+
+	/* Get the time namespace ID */
+	ret = ioctl(fd_timens, NS_GET_ID, &time_ns_id);
+	ASSERT_EQ(ret, 0);
+	ASSERT_NE(time_ns_id, 0);
+
+	/* Verify we can get the same ID again */
+	__u64 time_ns_id2 = 0;
+	ret = ioctl(fd_timens, NS_GET_ID, &time_ns_id2);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(time_ns_id, time_ns_id2);
+
+	close(fd_timens);
+}
+
+TEST(nsid_timens_separate)
+{
+	__u64 parent_time_ns_id = 0;
+	__u64 child_time_ns_id = 0;
+	int fd_parent_timens, fd_child_timens;
+	int ret;
+	pid_t pid;
+	int pipefd[2];
+
+	/* Open the current time namespace */
+	fd_parent_timens = open("/proc/self/ns/time", O_RDONLY);
+	if (fd_parent_timens < 0) {
+		SKIP(return, "Time namespaces not supported");
+	}
+
+	/* Get parent's time namespace ID */
+	ret = ioctl(fd_parent_timens, NS_GET_ID, &parent_time_ns_id);
+	ASSERT_EQ(ret, 0);
+	ASSERT_NE(parent_time_ns_id, 0);
+
+	/* Create a pipe for synchronization */
+	ASSERT_EQ(pipe(pipefd), 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+
+	if (pid == 0) {
+		/* Child process */
+		close(pipefd[0]);
+
+		/* Create new time namespace */
+		ret = unshare(CLONE_NEWTIME);
+		if (ret != 0) {
+			/* Skip test if we don't have permission */
+			if (errno == EPERM || errno == EACCES || errno == EINVAL) {
+				write(pipefd[1], "S", 1); /* Signal skip */
+				_exit(0);
+			}
+			_exit(1);
+		}
+
+		/* Fork a grandchild to actually enter the new namespace */
+		pid_t grandchild = fork();
+		if (grandchild == 0) {
+			/* Grandchild is in the new namespace */
+			write(pipefd[1], "Y", 1);
+			close(pipefd[1]);
+			pause();
+			_exit(0);
+		} else if (grandchild > 0) {
+			/* Child writes grandchild PID and waits */
+			write(pipefd[1], "Y", 1);
+			write(pipefd[1], &grandchild, sizeof(grandchild));
+			close(pipefd[1]);
+			pause(); /* Keep the parent alive to maintain the grandchild */
+			_exit(0);
+		} else {
+			_exit(1);
+		}
+	}
+
+	/* Parent process */
+	close(pipefd[1]);
+
+	char buf;
+	ASSERT_EQ(read(pipefd[0], &buf, 1), 1);
+
+	if (buf == 'S') {
+		/* Child couldn't create namespace, skip test */
+		kill(pid, SIGTERM);
+		waitpid(pid, NULL, 0);
+		close(fd_parent_timens);
+		close(pipefd[0]);
+		SKIP(return, "Cannot create time namespace");
+	}
+
+	ASSERT_EQ(buf, 'Y');
+
+	pid_t grandchild_pid;
+	ASSERT_EQ(read(pipefd[0], &grandchild_pid, sizeof(grandchild_pid)), sizeof(grandchild_pid));
+	close(pipefd[0]);
+
+	/* Open grandchild's time namespace */
+	char path[256];
+	snprintf(path, sizeof(path), "/proc/%d/ns/time", grandchild_pid);
+	fd_child_timens = open(path, O_RDONLY);
+	ASSERT_GE(fd_child_timens, 0);
+
+	/* Get child's time namespace ID */
+	ret = ioctl(fd_child_timens, NS_GET_ID, &child_time_ns_id);
+	ASSERT_EQ(ret, 0);
+	ASSERT_NE(child_time_ns_id, 0);
+
+	/* Parent and child should have different time namespace IDs */
+	ASSERT_NE(parent_time_ns_id, child_time_ns_id);
+
+	close(fd_parent_timens);
+	close(fd_child_timens);
+
+	/* Clean up child process */
+	kill(pid, SIGTERM);
+	waitpid(pid, NULL, 0);
+}
+
+TEST(nsid_pidns_basic)
+{
+	__u64 pid_ns_id = 0;
+	int fd_pidns;
+	int ret;
+
+	/* Open the current PID namespace */
+	fd_pidns = open("/proc/self/ns/pid", O_RDONLY);
+	ASSERT_GE(fd_pidns, 0);
+
+	/* Get the PID namespace ID */
+	ret = ioctl(fd_pidns, NS_GET_ID, &pid_ns_id);
+	ASSERT_EQ(ret, 0);
+	ASSERT_NE(pid_ns_id, 0);
+
+	/* Verify we can get the same ID again */
+	__u64 pid_ns_id2 = 0;
+	ret = ioctl(fd_pidns, NS_GET_ID, &pid_ns_id2);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(pid_ns_id, pid_ns_id2);
+
+	close(fd_pidns);
+}
+
+TEST(nsid_pidns_separate)
+{
+	__u64 parent_pid_ns_id = 0;
+	__u64 child_pid_ns_id = 0;
+	int fd_parent_pidns, fd_child_pidns;
+	int ret;
+	pid_t pid;
+	int pipefd[2];
+
+	/* Get parent's PID namespace ID */
+	fd_parent_pidns = open("/proc/self/ns/pid", O_RDONLY);
+	ASSERT_GE(fd_parent_pidns, 0);
+	ret = ioctl(fd_parent_pidns, NS_GET_ID, &parent_pid_ns_id);
+	ASSERT_EQ(ret, 0);
+	ASSERT_NE(parent_pid_ns_id, 0);
+
+	/* Create a pipe for synchronization */
+	ASSERT_EQ(pipe(pipefd), 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+
+	if (pid == 0) {
+		/* Child process */
+		close(pipefd[0]);
+
+		/* Create new PID namespace */
+		ret = unshare(CLONE_NEWPID);
+		if (ret != 0) {
+			/* Skip test if we don't have permission */
+			if (errno == EPERM || errno == EACCES) {
+				write(pipefd[1], "S", 1); /* Signal skip */
+				_exit(0);
+			}
+			_exit(1);
+		}
+
+		/* Fork a grandchild to actually enter the new namespace */
+		pid_t grandchild = fork();
+		if (grandchild == 0) {
+			/* Grandchild is in the new namespace */
+			write(pipefd[1], "Y", 1);
+			close(pipefd[1]);
+			pause();
+			_exit(0);
+		} else if (grandchild > 0) {
+			/* Child writes grandchild PID and waits */
+			write(pipefd[1], "Y", 1);
+			write(pipefd[1], &grandchild, sizeof(grandchild));
+			close(pipefd[1]);
+			pause(); /* Keep the parent alive to maintain the grandchild */
+			_exit(0);
+		} else {
+			_exit(1);
+		}
+	}
+
+	/* Parent process */
+	close(pipefd[1]);
+
+	char buf;
+	ASSERT_EQ(read(pipefd[0], &buf, 1), 1);
+
+	if (buf == 'S') {
+		/* Child couldn't create namespace, skip test */
+		kill(pid, SIGTERM);
+		waitpid(pid, NULL, 0);
+		close(fd_parent_pidns);
+		close(pipefd[0]);
+		SKIP(return, "No permission to create PID namespace");
+	}
+
+	ASSERT_EQ(buf, 'Y');
+
+	pid_t grandchild_pid;
+	ASSERT_EQ(read(pipefd[0], &grandchild_pid, sizeof(grandchild_pid)), sizeof(grandchild_pid));
+	close(pipefd[0]);
+
+	/* Open grandchild's PID namespace */
+	char path[256];
+	snprintf(path, sizeof(path), "/proc/%d/ns/pid", grandchild_pid);
+	fd_child_pidns = open(path, O_RDONLY);
+	ASSERT_GE(fd_child_pidns, 0);
+
+	/* Get child's PID namespace ID */
+	ret = ioctl(fd_child_pidns, NS_GET_ID, &child_pid_ns_id);
+	ASSERT_EQ(ret, 0);
+	ASSERT_NE(child_pid_ns_id, 0);
+
+	/* Parent and child should have different PID namespace IDs */
+	ASSERT_NE(parent_pid_ns_id, child_pid_ns_id);
+
+	close(fd_parent_pidns);
+	close(fd_child_pidns);
+
+	/* Clean up child process */
+	kill(pid, SIGTERM);
+	waitpid(pid, NULL, 0);
+}
+
+TEST(nsid_netns_basic)
+{
+	__u64 net_ns_id = 0;
+	__u64 netns_cookie = 0;
+	int fd_netns;
+	int sock;
+	socklen_t optlen;
+	int ret;
+
+	/* Open the current network namespace */
+	fd_netns = open("/proc/self/ns/net", O_RDONLY);
+	ASSERT_GE(fd_netns, 0);
+
+	/* Get the network namespace ID via ioctl */
+	ret = ioctl(fd_netns, NS_GET_ID, &net_ns_id);
+	ASSERT_EQ(ret, 0);
+	ASSERT_NE(net_ns_id, 0);
+
+	/* Create a socket to get the SO_NETNS_COOKIE */
+	sock = socket(AF_UNIX, SOCK_STREAM, 0);
+	ASSERT_GE(sock, 0);
+
+	/* Get the network namespace cookie via socket option */
+	optlen = sizeof(netns_cookie);
+	ret = getsockopt(sock, SOL_SOCKET, SO_NETNS_COOKIE, &netns_cookie, &optlen);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(optlen, sizeof(netns_cookie));
+
+	/* The namespace ID and cookie should be identical */
+	ASSERT_EQ(net_ns_id, netns_cookie);
+
+	/* Verify we can get the same ID again */
+	__u64 net_ns_id2 = 0;
+	ret = ioctl(fd_netns, NS_GET_ID, &net_ns_id2);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(net_ns_id, net_ns_id2);
+
+	close(sock);
+	close(fd_netns);
+}
+
+TEST(nsid_netns_separate)
+{
+	__u64 parent_net_ns_id = 0;
+	__u64 parent_netns_cookie = 0;
+	__u64 child_net_ns_id = 0;
+	__u64 child_netns_cookie = 0;
+	int fd_parent_netns, fd_child_netns;
+	int parent_sock, child_sock;
+	socklen_t optlen;
+	int ret;
+	pid_t pid;
+	int pipefd[2];
+
+	/* Get parent's network namespace ID */
+	fd_parent_netns = open("/proc/self/ns/net", O_RDONLY);
+	ASSERT_GE(fd_parent_netns, 0);
+	ret = ioctl(fd_parent_netns, NS_GET_ID, &parent_net_ns_id);
+	ASSERT_EQ(ret, 0);
+	ASSERT_NE(parent_net_ns_id, 0);
+
+	/* Get parent's network namespace cookie */
+	parent_sock = socket(AF_UNIX, SOCK_STREAM, 0);
+	ASSERT_GE(parent_sock, 0);
+	optlen = sizeof(parent_netns_cookie);
+	ret = getsockopt(parent_sock, SOL_SOCKET, SO_NETNS_COOKIE, &parent_netns_cookie, &optlen);
+	ASSERT_EQ(ret, 0);
+
+	/* Verify parent's ID and cookie match */
+	ASSERT_EQ(parent_net_ns_id, parent_netns_cookie);
+
+	/* Create a pipe for synchronization */
+	ASSERT_EQ(pipe(pipefd), 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+
+	if (pid == 0) {
+		/* Child process */
+		close(pipefd[0]);
+
+		/* Create new network namespace */
+		ret = unshare(CLONE_NEWNET);
+		if (ret != 0) {
+			/* Skip test if we don't have permission */
+			if (errno == EPERM || errno == EACCES) {
+				write(pipefd[1], "S", 1); /* Signal skip */
+				_exit(0);
+			}
+			_exit(1);
+		}
+
+		/* Signal success */
+		write(pipefd[1], "Y", 1);
+		close(pipefd[1]);
+
+		/* Keep namespace alive */
+		pause();
+		_exit(0);
+	}
+
+	/* Parent process */
+	close(pipefd[1]);
+
+	char buf;
+	ASSERT_EQ(read(pipefd[0], &buf, 1), 1);
+	close(pipefd[0]);
+
+	if (buf == 'S') {
+		/* Child couldn't create namespace, skip test */
+		kill(pid, SIGTERM);
+		waitpid(pid, NULL, 0);
+		close(fd_parent_netns);
+		close(parent_sock);
+		SKIP(return, "No permission to create network namespace");
+	}
+
+	ASSERT_EQ(buf, 'Y');
+
+	/* Open child's network namespace */
+	char path[256];
+	snprintf(path, sizeof(path), "/proc/%d/ns/net", pid);
+	fd_child_netns = open(path, O_RDONLY);
+	ASSERT_GE(fd_child_netns, 0);
+
+	/* Get child's network namespace ID */
+	ret = ioctl(fd_child_netns, NS_GET_ID, &child_net_ns_id);
+	ASSERT_EQ(ret, 0);
+	ASSERT_NE(child_net_ns_id, 0);
+
+	/* Create socket in child's namespace to get cookie */
+	ret = setns(fd_child_netns, CLONE_NEWNET);
+	if (ret == 0) {
+		child_sock = socket(AF_UNIX, SOCK_STREAM, 0);
+		ASSERT_GE(child_sock, 0);
+
+		optlen = sizeof(child_netns_cookie);
+		ret = getsockopt(child_sock, SOL_SOCKET, SO_NETNS_COOKIE, &child_netns_cookie, &optlen);
+		ASSERT_EQ(ret, 0);
+
+		/* Verify child's ID and cookie match */
+		ASSERT_EQ(child_net_ns_id, child_netns_cookie);
+
+		close(child_sock);
+
+		/* Return to parent namespace */
+		setns(fd_parent_netns, CLONE_NEWNET);
+	}
+
+	/* Parent and child should have different network namespace IDs */
+	ASSERT_NE(parent_net_ns_id, child_net_ns_id);
+	if (child_netns_cookie != 0) {
+		ASSERT_NE(parent_netns_cookie, child_netns_cookie);
+	}
+
+	close(fd_parent_netns);
+	close(fd_child_netns);
+	close(parent_sock);
+
+	/* Clean up child process */
+	kill(pid, SIGTERM);
+	waitpid(pid, NULL, 0);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/net/forwarding/router.sh b/tools/testing/selftests/net/forwarding/router.sh
index b98ea9449b8b..dfb6646cb97b 100755
--- a/tools/testing/selftests/net/forwarding/router.sh
+++ b/tools/testing/selftests/net/forwarding/router.sh
@@ -18,6 +18,8 @@
 # | 2001:db8:1::1/64                             2001:db8:2::1/64   |
 # |                                                                 |
 # +-----------------------------------------------------------------+
+#
+#shellcheck disable=SC2034 # SC doesn't see our uses of global variables
 
 ALL_TESTS="
 	ping_ipv4
@@ -27,6 +29,7 @@ ALL_TESTS="
 	ipv4_sip_equal_dip
 	ipv6_sip_equal_dip
 	ipv4_dip_link_local
+	ipv4_sip_link_local
 "
 
 NUM_NETIFS=4
@@ -330,6 +333,32 @@ ipv4_dip_link_local()
 	tc filter del dev $rp2 egress protocol ip pref 1 handle 101 flower
 }
 
+ipv4_sip_link_local()
+{
+	local sip=169.254.1.1
+
+	RET=0
+
+	# Disable rpfilter to prevent packets to be dropped because of it.
+	sysctl_set net.ipv4.conf.all.rp_filter 0
+	sysctl_set net.ipv4.conf."$rp1".rp_filter 0
+
+	tc filter add dev "$rp2" egress protocol ip pref 1 handle 101 \
+		flower src_ip "$sip" action pass
+
+	$MZ "$h1" -t udp "sp=54321,dp=12345" -c 5 -d 1msec -b "$rp1mac" \
+		-A "$sip" -B 198.51.100.2 -q
+
+	tc_check_packets "dev $rp2 egress" 101 5
+	check_err $? "Packets were dropped"
+
+	log_test "IPv4 source IP is link-local"
+
+	tc filter del dev "$rp2" egress protocol ip pref 1 handle 101 flower
+	sysctl_restore net.ipv4.conf."$rp1".rp_filter
+	sysctl_restore net.ipv4.conf.all.rp_filter
+}
+
 trap cleanup EXIT
 
 setup_prepare
diff --git a/tools/testing/selftests/net/forwarding/sch_ets.sh b/tools/testing/selftests/net/forwarding/sch_ets.sh
index 1f6f53e284b5..6269d5e23487 100755
--- a/tools/testing/selftests/net/forwarding/sch_ets.sh
+++ b/tools/testing/selftests/net/forwarding/sch_ets.sh
@@ -11,6 +11,7 @@ ALL_TESTS="
 	ets_test_strict
 	ets_test_mixed
 	ets_test_dwrr
+	ets_test_plug
 	classifier_mode
 	ets_test_strict
 	ets_test_mixed
diff --git a/tools/testing/selftests/net/forwarding/sch_ets_tests.sh b/tools/testing/selftests/net/forwarding/sch_ets_tests.sh
index 08240d3e3c87..79d837a2868a 100644
--- a/tools/testing/selftests/net/forwarding/sch_ets_tests.sh
+++ b/tools/testing/selftests/net/forwarding/sch_ets_tests.sh
@@ -224,3 +224,11 @@ ets_test_dwrr()
 	ets_set_dwrr_two_bands
 	xfail_on_slow ets_dwrr_test_01
 }
+
+ets_test_plug()
+{
+	ets_change_qdisc $put 2 "3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3" "1514 1514"
+	tc qdisc add dev $put handle 20: parent 10:4 plug
+	start_traffic_pktsize 100 $h1.10 192.0.2.1 192.0.2.2 00:c1:a0:c1:a0:00 "-c 1"
+	ets_qdisc_setup $put 2
+}
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c
index ac1349c4b9e5..4f07ac9fa207 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c
@@ -183,9 +183,10 @@ static void xgetaddrinfo(const char *node, const char *service,
 			 struct addrinfo *hints,
 			 struct addrinfo **res)
 {
-again:
-	int err = getaddrinfo(node, service, hints, res);
+	int err;
 
+again:
+	err = getaddrinfo(node, service, hints, res);
 	if (err) {
 		const char *errstr;
 
diff --git a/tools/testing/selftests/net/mptcp/mptcp_inq.c b/tools/testing/selftests/net/mptcp/mptcp_inq.c
index 3cf1e2a612ce..f3bcaa48df8f 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_inq.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_inq.c
@@ -75,9 +75,10 @@ static void xgetaddrinfo(const char *node, const char *service,
 			 struct addrinfo *hints,
 			 struct addrinfo **res)
 {
-again:
-	int err = getaddrinfo(node, service, hints, res);
+	int err;
 
+again:
+	err = getaddrinfo(node, service, hints, res);
 	if (err) {
 		const char *errstr;
 
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index b8af65373b3a..82cae37d9c20 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -3842,6 +3842,7 @@ endpoint_tests()
 	# remove and re-add
 	if reset_with_events "delete re-add signal" &&
 	   mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then
+		ip netns exec $ns1 sysctl -q net.mptcp.add_addr_timeout=0
 		pm_nl_set_limits $ns1 0 3
 		pm_nl_set_limits $ns2 3 3
 		pm_nl_add_endpoint $ns1 10.0.2.1 id 1 flags signal
diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
index 9934a68df237..e934dd26a59d 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
@@ -162,9 +162,10 @@ static void xgetaddrinfo(const char *node, const char *service,
 			 struct addrinfo *hints,
 			 struct addrinfo **res)
 {
-again:
-	int err = getaddrinfo(node, service, hints, res);
+	int err;
 
+again:
+	err = getaddrinfo(node, service, hints, res);
 	if (err) {
 		const char *errstr;
 
diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh
index 2e6648a2b2c0..ac7ec6f94023 100755
--- a/tools/testing/selftests/net/mptcp/pm_netlink.sh
+++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh
@@ -198,6 +198,7 @@ set_limits 1 9 2>/dev/null
 check "get_limits" "${default_limits}" "subflows above hard limit"
 
 set_limits 8 8
+flush_endpoint  ## to make sure it doesn't affect the limits
 check "get_limits" "$(format_limits 8 8)" "set limits"
 
 flush_endpoint
diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 5ded3b3a7538..0f5640d8dc7f 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -181,13 +181,12 @@ static int tls_send_cmsg(int fd, unsigned char record_type,
 	return sendmsg(fd, &msg, flags);
 }
 
-static int tls_recv_cmsg(struct __test_metadata *_metadata,
-			 int fd, unsigned char record_type,
-			 void *data, size_t len, int flags)
+static int __tls_recv_cmsg(struct __test_metadata *_metadata,
+			   int fd, unsigned char *ctype,
+			   void *data, size_t len, int flags)
 {
 	char cbuf[CMSG_SPACE(sizeof(char))];
 	struct cmsghdr *cmsg;
-	unsigned char ctype;
 	struct msghdr msg;
 	struct iovec vec;
 	int n;
@@ -206,7 +205,20 @@ static int tls_recv_cmsg(struct __test_metadata *_metadata,
 	EXPECT_NE(cmsg, NULL);
 	EXPECT_EQ(cmsg->cmsg_level, SOL_TLS);
 	EXPECT_EQ(cmsg->cmsg_type, TLS_GET_RECORD_TYPE);
-	ctype = *((unsigned char *)CMSG_DATA(cmsg));
+	if (ctype)
+		*ctype = *((unsigned char *)CMSG_DATA(cmsg));
+
+	return n;
+}
+
+static int tls_recv_cmsg(struct __test_metadata *_metadata,
+			 int fd, unsigned char record_type,
+			 void *data, size_t len, int flags)
+{
+	unsigned char ctype;
+	int n;
+
+	n = __tls_recv_cmsg(_metadata, fd, &ctype, data, len, flags);
 	EXPECT_EQ(ctype, record_type);
 
 	return n;
@@ -2164,6 +2176,284 @@ TEST_F(tls, rekey_poll_delay)
 	}
 }
 
+struct raw_rec {
+	unsigned int plain_len;
+	unsigned char plain_data[100];
+	unsigned int cipher_len;
+	unsigned char cipher_data[128];
+};
+
+/* TLS 1.2, AES_CCM, data, seqno:0, plaintext: 'Hello world' */
+static const struct raw_rec id0_data_l11 = {
+	.plain_len = 11,
+	.plain_data = {
+		0x48, 0x65, 0x6c, 0x6c, 0x6f, 0x20, 0x77, 0x6f,
+		0x72, 0x6c, 0x64,
+	},
+	.cipher_len = 40,
+	.cipher_data = {
+		0x17, 0x03, 0x03, 0x00, 0x23, 0x00, 0x00, 0x00,
+		0x00, 0x00, 0x00, 0x00, 0x00, 0x26, 0xa2, 0x33,
+		0xde, 0x8d, 0x94, 0xf0, 0x29, 0x6c, 0xb1, 0xaf,
+		0x6a, 0x75, 0xb2, 0x93, 0xad, 0x45, 0xd5, 0xfd,
+		0x03, 0x51, 0x57, 0x8f, 0xf9, 0xcc, 0x3b, 0x42,
+	},
+};
+
+/* TLS 1.2, AES_CCM, ctrl, seqno:0, plaintext: '' */
+static const struct raw_rec id0_ctrl_l0 = {
+	.plain_len = 0,
+	.plain_data = {
+	},
+	.cipher_len = 29,
+	.cipher_data = {
+		0x16, 0x03, 0x03, 0x00, 0x18, 0x00, 0x00, 0x00,
+		0x00, 0x00, 0x00, 0x00, 0x00, 0x13, 0x38, 0x7b,
+		0xa6, 0x1c, 0xdd, 0xa7, 0x19, 0x33, 0xab, 0xae,
+		0x88, 0xe1, 0xd2, 0x08, 0x4f,
+	},
+};
+
+/* TLS 1.2, AES_CCM, data, seqno:0, plaintext: '' */
+static const struct raw_rec id0_data_l0 = {
+	.plain_len = 0,
+	.plain_data = {
+	},
+	.cipher_len = 29,
+	.cipher_data = {
+		0x17, 0x03, 0x03, 0x00, 0x18, 0x00, 0x00, 0x00,
+		0x00, 0x00, 0x00, 0x00, 0x00, 0xc5, 0x37, 0x90,
+		0x70, 0x45, 0x89, 0xfb, 0x5c, 0xc7, 0x89, 0x03,
+		0x68, 0x80, 0xd3, 0xd8, 0xcc,
+	},
+};
+
+/* TLS 1.2, AES_CCM, data, seqno:1, plaintext: 'Hello world' */
+static const struct raw_rec id1_data_l11 = {
+	.plain_len = 11,
+	.plain_data = {
+		0x48, 0x65, 0x6c, 0x6c, 0x6f, 0x20, 0x77, 0x6f,
+		0x72, 0x6c, 0x64,
+	},
+	.cipher_len = 40,
+	.cipher_data = {
+		0x17, 0x03, 0x03, 0x00, 0x23, 0x00, 0x00, 0x00,
+		0x00, 0x00, 0x00, 0x00, 0x01, 0x3a, 0x1a, 0x9c,
+		0xd0, 0xa8, 0x9a, 0xd6, 0x69, 0xd6, 0x1a, 0xe3,
+		0xb5, 0x1f, 0x0d, 0x2c, 0xe2, 0x97, 0x46, 0xff,
+		0x2b, 0xcc, 0x5a, 0xc4, 0xa3, 0xb9, 0xef, 0xba,
+	},
+};
+
+/* TLS 1.2, AES_CCM, ctrl, seqno:1, plaintext: '' */
+static const struct raw_rec id1_ctrl_l0 = {
+	.plain_len = 0,
+	.plain_data = {
+	},
+	.cipher_len = 29,
+	.cipher_data = {
+		0x16, 0x03, 0x03, 0x00, 0x18, 0x00, 0x00, 0x00,
+		0x00, 0x00, 0x00, 0x00, 0x01, 0x3e, 0xf0, 0xfe,
+		0xee, 0xd9, 0xe2, 0x5d, 0xc7, 0x11, 0x4c, 0xe6,
+		0xb4, 0x7e, 0xef, 0x40, 0x2b,
+	},
+};
+
+/* TLS 1.2, AES_CCM, data, seqno:1, plaintext: '' */
+static const struct raw_rec id1_data_l0 = {
+	.plain_len = 0,
+	.plain_data = {
+	},
+	.cipher_len = 29,
+	.cipher_data = {
+		0x17, 0x03, 0x03, 0x00, 0x18, 0x00, 0x00, 0x00,
+		0x00, 0x00, 0x00, 0x00, 0x01, 0xce, 0xfc, 0x86,
+		0xc8, 0xf0, 0x55, 0xf9, 0x47, 0x3f, 0x74, 0xdc,
+		0xc9, 0xbf, 0xfe, 0x5b, 0xb1,
+	},
+};
+
+/* TLS 1.2, AES_CCM, ctrl, seqno:2, plaintext: 'Hello world' */
+static const struct raw_rec id2_ctrl_l11 = {
+	.plain_len = 11,
+	.plain_data = {
+		0x48, 0x65, 0x6c, 0x6c, 0x6f, 0x20, 0x77, 0x6f,
+		0x72, 0x6c, 0x64,
+	},
+	.cipher_len = 40,
+	.cipher_data = {
+		0x16, 0x03, 0x03, 0x00, 0x23, 0x00, 0x00, 0x00,
+		0x00, 0x00, 0x00, 0x00, 0x02, 0xe5, 0x3d, 0x19,
+		0x3d, 0xca, 0xb8, 0x16, 0xb6, 0xff, 0x79, 0x87,
+		0x2a, 0x04, 0x11, 0x3d, 0xf8, 0x64, 0x5f, 0x36,
+		0x8b, 0xa8, 0xee, 0x4c, 0x6d, 0x62, 0xa5, 0x00,
+	},
+};
+
+/* TLS 1.2, AES_CCM, data, seqno:2, plaintext: 'Hello world' */
+static const struct raw_rec id2_data_l11 = {
+	.plain_len = 11,
+	.plain_data = {
+		0x48, 0x65, 0x6c, 0x6c, 0x6f, 0x20, 0x77, 0x6f,
+		0x72, 0x6c, 0x64,
+	},
+	.cipher_len = 40,
+	.cipher_data = {
+		0x17, 0x03, 0x03, 0x00, 0x23, 0x00, 0x00, 0x00,
+		0x00, 0x00, 0x00, 0x00, 0x02, 0xe5, 0x3d, 0x19,
+		0x3d, 0xca, 0xb8, 0x16, 0xb6, 0xff, 0x79, 0x87,
+		0x8e, 0xa1, 0xd0, 0xcd, 0x33, 0xb5, 0x86, 0x2b,
+		0x17, 0xf1, 0x52, 0x2a, 0x55, 0x62, 0x65, 0x11,
+	},
+};
+
+/* TLS 1.2, AES_CCM, ctrl, seqno:2, plaintext: '' */
+static const struct raw_rec id2_ctrl_l0 = {
+	.plain_len = 0,
+	.plain_data = {
+	},
+	.cipher_len = 29,
+	.cipher_data = {
+		0x16, 0x03, 0x03, 0x00, 0x18, 0x00, 0x00, 0x00,
+		0x00, 0x00, 0x00, 0x00, 0x02, 0xdc, 0x5c, 0x0e,
+		0x41, 0xdd, 0xba, 0xd3, 0xcc, 0xcf, 0x6d, 0xd9,
+		0x06, 0xdb, 0x79, 0xe5, 0x5d,
+	},
+};
+
+/* TLS 1.2, AES_CCM, data, seqno:2, plaintext: '' */
+static const struct raw_rec id2_data_l0 = {
+	.plain_len = 0,
+	.plain_data = {
+	},
+	.cipher_len = 29,
+	.cipher_data = {
+		0x17, 0x03, 0x03, 0x00, 0x18, 0x00, 0x00, 0x00,
+		0x00, 0x00, 0x00, 0x00, 0x02, 0xc3, 0xca, 0x26,
+		0x22, 0xe4, 0x25, 0xfb, 0x5f, 0x6d, 0xbf, 0x83,
+		0x30, 0x48, 0x69, 0x1a, 0x47,
+	},
+};
+
+FIXTURE(zero_len)
+{
+	int fd, cfd;
+	bool notls;
+};
+
+FIXTURE_VARIANT(zero_len)
+{
+	const struct raw_rec *recs[4];
+	ssize_t recv_ret[4];
+};
+
+FIXTURE_VARIANT_ADD(zero_len, data_data_data)
+{
+	.recs = { &id0_data_l11, &id1_data_l11, &id2_data_l11, },
+	.recv_ret = { 33, -EAGAIN, },
+};
+
+FIXTURE_VARIANT_ADD(zero_len, data_0ctrl_data)
+{
+	.recs = { &id0_data_l11, &id1_ctrl_l0, &id2_data_l11, },
+	.recv_ret = { 11, 0, 11, -EAGAIN, },
+};
+
+FIXTURE_VARIANT_ADD(zero_len, 0data_0data_0data)
+{
+	.recs = { &id0_data_l0, &id1_data_l0, &id2_data_l0, },
+	.recv_ret = { -EAGAIN, },
+};
+
+FIXTURE_VARIANT_ADD(zero_len, 0data_0data_ctrl)
+{
+	.recs = { &id0_data_l0, &id1_data_l0, &id2_ctrl_l11, },
+	.recv_ret = { 0, 11, -EAGAIN, },
+};
+
+FIXTURE_VARIANT_ADD(zero_len, 0data_0data_0ctrl)
+{
+	.recs = { &id0_data_l0, &id1_data_l0, &id2_ctrl_l0, },
+	.recv_ret = { 0, 0, -EAGAIN, },
+};
+
+FIXTURE_VARIANT_ADD(zero_len, 0ctrl_0ctrl_0ctrl)
+{
+	.recs = { &id0_ctrl_l0, &id1_ctrl_l0, &id2_ctrl_l0, },
+	.recv_ret = { 0, 0, 0, -EAGAIN, },
+};
+
+FIXTURE_VARIANT_ADD(zero_len, 0data_0data_data)
+{
+	.recs = { &id0_data_l0, &id1_data_l0, &id2_data_l11, },
+	.recv_ret = { 11, -EAGAIN, },
+};
+
+FIXTURE_VARIANT_ADD(zero_len, data_0data_0data)
+{
+	.recs = { &id0_data_l11, &id1_data_l0, &id2_data_l0, },
+	.recv_ret = { 11, -EAGAIN, },
+};
+
+FIXTURE_SETUP(zero_len)
+{
+	struct tls_crypto_info_keys tls12;
+	int ret;
+
+	tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_CCM_128,
+			     &tls12, 0);
+
+	ulp_sock_pair(_metadata, &self->fd, &self->cfd, &self->notls);
+	if (self->notls)
+		return;
+
+	/* Don't install keys on fd, we'll send raw records */
+	ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len);
+	ASSERT_EQ(ret, 0);
+}
+
+FIXTURE_TEARDOWN(zero_len)
+{
+	close(self->fd);
+	close(self->cfd);
+}
+
+TEST_F(zero_len, test)
+{
+	const struct raw_rec *const *rec;
+	unsigned char buf[128];
+	int rec_off;
+	int i;
+
+	for (i = 0; i < 4 && variant->recs[i]; i++)
+		EXPECT_EQ(send(self->fd, variant->recs[i]->cipher_data,
+			       variant->recs[i]->cipher_len, 0),
+			  variant->recs[i]->cipher_len);
+
+	rec = &variant->recs[0];
+	rec_off = 0;
+	for (i = 0; i < 4; i++) {
+		int j, ret;
+
+		ret = variant->recv_ret[i] >= 0 ? variant->recv_ret[i] : -1;
+		EXPECT_EQ(__tls_recv_cmsg(_metadata, self->cfd, NULL,
+					  buf, sizeof(buf), MSG_DONTWAIT), ret);
+		if (ret == -1)
+			EXPECT_EQ(errno, -variant->recv_ret[i]);
+		if (variant->recv_ret[i] == -EAGAIN)
+			break;
+
+		for (j = 0; j < ret; j++) {
+			while (rec_off == (*rec)->plain_len) {
+				rec++;
+				rec_off = 0;
+			}
+			EXPECT_EQ(buf[j], (*rec)->plain_data[rec_off]);
+			rec_off++;
+		}
+	}
+};
+
 FIXTURE(tls_err)
 {
 	int fd, cfd;
@@ -2708,6 +2998,67 @@ TEST(prequeue) {
 	close(cfd);
 }
 
+TEST(data_steal) {
+	struct tls_crypto_info_keys tls;
+	char buf[20000], buf2[20000];
+	struct sockaddr_in addr;
+	int sfd, cfd, ret, fd;
+	int pid, status;
+	socklen_t len;
+
+	len = sizeof(addr);
+	memrnd(buf, sizeof(buf));
+
+	tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_GCM_256, &tls, 0);
+
+	addr.sin_family = AF_INET;
+	addr.sin_addr.s_addr = htonl(INADDR_ANY);
+	addr.sin_port = 0;
+
+	fd = socket(AF_INET, SOCK_STREAM, 0);
+	sfd = socket(AF_INET, SOCK_STREAM, 0);
+
+	ASSERT_EQ(bind(sfd, &addr, sizeof(addr)), 0);
+	ASSERT_EQ(listen(sfd, 10), 0);
+	ASSERT_EQ(getsockname(sfd, &addr, &len), 0);
+	ASSERT_EQ(connect(fd, &addr, sizeof(addr)), 0);
+	ASSERT_GE(cfd = accept(sfd, &addr, &len), 0);
+	close(sfd);
+
+	ret = setsockopt(fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls"));
+	if (ret) {
+		ASSERT_EQ(errno, ENOENT);
+		SKIP(return, "no TLS support");
+	}
+	ASSERT_EQ(setsockopt(cfd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")), 0);
+
+	/* Spawn a child and get it into the read wait path of the underlying
+	 * TCP socket.
+	 */
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (!pid) {
+		EXPECT_EQ(recv(cfd, buf, sizeof(buf) / 2, MSG_WAITALL),
+			  sizeof(buf) / 2);
+		exit(!__test_passed(_metadata));
+	}
+
+	usleep(10000);
+	ASSERT_EQ(setsockopt(fd, SOL_TLS, TLS_TX, &tls, tls.len), 0);
+	ASSERT_EQ(setsockopt(cfd, SOL_TLS, TLS_RX, &tls, tls.len), 0);
+
+	EXPECT_EQ(send(fd, buf, sizeof(buf), 0), sizeof(buf));
+	EXPECT_EQ(wait(&status), pid);
+	EXPECT_EQ(status, 0);
+	EXPECT_EQ(recv(cfd, buf2, sizeof(buf2), MSG_DONTWAIT), -1);
+	/* Don't check errno, the error will be different depending
+	 * on what random bytes TLS interpreted as the record length.
+	 */
+
+	close(fd);
+	close(cfd);
+}
+
 static void __attribute__((constructor)) fips_check(void) {
 	int res;
 	FILE *f;
diff --git a/tools/testing/selftests/proc/proc-maps-race.c b/tools/testing/selftests/proc/proc-maps-race.c
index 66773685a047..94bba4553130 100644
--- a/tools/testing/selftests/proc/proc-maps-race.c
+++ b/tools/testing/selftests/proc/proc-maps-race.c
@@ -202,11 +202,11 @@ static void print_first_lines(char *text, int nr)
 		int offs = end - text;
 
 		text[offs] = '\0';
-		printf(text);
+		printf("%s", text);
 		text[offs] = '\n';
 		printf("\n");
 	} else {
-		printf(text);
+		printf("%s", text);
 	}
 }
 
@@ -221,7 +221,7 @@ static void print_last_lines(char *text, int nr)
 		nr--;
 		start--;
 	}
-	printf(start);
+	printf("%s", start);
 }
 
 static void print_boundaries(const char *title, FIXTURE_DATA(proc_maps_race) *self)
diff --git a/tools/testing/selftests/sched_ext/hotplug.c b/tools/testing/selftests/sched_ext/hotplug.c
index 1c9ceb661c43..0cfbb111a2d0 100644
--- a/tools/testing/selftests/sched_ext/hotplug.c
+++ b/tools/testing/selftests/sched_ext/hotplug.c
@@ -6,7 +6,6 @@
 #include <bpf/bpf.h>
 #include <sched.h>
 #include <scx/common.h>
-#include <sched.h>
 #include <sys/wait.h>
 #include <unistd.h>
 
diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
index 23a61e5b99d0..998e5a2f4579 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
@@ -186,6 +186,204 @@
         ]
     },
     {
+        "id": "34c0",
+        "name": "Test TBF with HHF Backlog Accounting in gso_skb case against underflow",
+        "category": [
+            "qdisc",
+            "tbf",
+            "hhf"
+        ],
+        "plugins": {
+            "requires": [
+                "nsPlugin"
+            ]
+        },
+        "setup": [
+            "$IP link set dev $DUMMY up || true",
+            "$IP addr add 10.10.11.10/24 dev $DUMMY || true",
+            "$TC qdisc add dev $DUMMY root handle 1: tbf rate 8bit burst 100b latency 100ms",
+            "$TC qdisc replace dev $DUMMY handle 2: parent 1:1 hhf limit 1000",
+            [
+                "ping -I $DUMMY -c2 10.10.11.11",
+                1
+            ],
+            "$TC qdisc change dev $DUMMY handle 2: parent 1:1 hhf limit 1"
+        ],
+        "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 2: parent 1:1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -s qdisc show dev $DUMMY",
+        "matchPattern": "backlog 0b 0p",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY handle 1: root"
+        ]
+    },
+    {
+        "id": "fd68",
+        "name": "Test TBF with CODEL Backlog Accounting in gso_skb case against underflow",
+        "category": [
+            "qdisc",
+            "tbf",
+            "codel"
+        ],
+        "plugins": {
+            "requires": [
+                "nsPlugin"
+            ]
+        },
+        "setup": [
+            "$IP link set dev $DUMMY up || true",
+            "$IP addr add 10.10.11.10/24 dev $DUMMY || true",
+            "$TC qdisc add dev $DUMMY root handle 1: tbf rate 8bit burst 100b latency 100ms",
+            "$TC qdisc replace dev $DUMMY handle 2: parent 1:1 codel limit 1000",
+            [
+                "ping -I $DUMMY -c2 10.10.11.11",
+                1
+            ],
+            "$TC qdisc change dev $DUMMY handle 2: parent 1:1 codel limit 1"
+        ],
+        "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 2: parent 1:1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -s qdisc show dev $DUMMY",
+        "matchPattern": "backlog 0b 0p",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY handle 1: root"
+        ]
+    },
+    {
+        "id": "514e",
+        "name": "Test TBF with PIE Backlog Accounting in gso_skb case against underflow",
+        "category": [
+            "qdisc",
+            "tbf",
+            "pie"
+        ],
+        "plugins": {
+            "requires": [
+                "nsPlugin"
+            ]
+        },
+        "setup": [
+            "$IP link set dev $DUMMY up || true",
+            "$IP addr add 10.10.11.10/24 dev $DUMMY || true",
+            "$TC qdisc add dev $DUMMY root handle 1: tbf rate 8bit burst 100b latency 100ms",
+            "$TC qdisc replace dev $DUMMY handle 2: parent 1:1 pie limit 1000",
+            [
+                "ping -I $DUMMY -c2 10.10.11.11",
+                1
+            ],
+            "$TC qdisc change dev $DUMMY handle 2: parent 1:1 pie limit 1"
+        ],
+        "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 2: parent 1:1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -s qdisc show dev $DUMMY",
+        "matchPattern": "backlog 0b 0p",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY handle 1: root"
+        ]
+    },
+    {
+        "id": "6c97",
+        "name": "Test TBF with FQ Backlog Accounting in gso_skb case against underflow",
+        "category": [
+            "qdisc",
+            "tbf",
+            "fq"
+        ],
+        "plugins": {
+            "requires": [
+                "nsPlugin"
+            ]
+        },
+        "setup": [
+            "$IP link set dev $DUMMY up || true",
+            "$IP addr add 10.10.11.10/24 dev $DUMMY || true",
+            "$TC qdisc add dev $DUMMY root handle 1: tbf rate 8bit burst 100b latency 100ms",
+            "$TC qdisc replace dev $DUMMY handle 2: parent 1:1 fq limit 1000",
+            [
+                "ping -I $DUMMY -c2 10.10.11.11",
+                1
+            ],
+            "$TC qdisc change dev $DUMMY handle 2: parent 1:1 fq limit 1"
+        ],
+        "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 2: parent 1:1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -s qdisc show dev $DUMMY",
+        "matchPattern": "backlog 0b 0p",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY handle 1: root"
+        ]
+    },
+    {
+        "id": "5d0b",
+        "name": "Test TBF with FQ_CODEL Backlog Accounting in gso_skb case against underflow",
+        "category": [
+            "qdisc",
+            "tbf",
+            "fq_codel"
+        ],
+        "plugins": {
+            "requires": [
+                "nsPlugin"
+            ]
+        },
+        "setup": [
+            "$IP link set dev $DUMMY up || true",
+            "$IP addr add 10.10.11.10/24 dev $DUMMY || true",
+            "$TC qdisc add dev $DUMMY root handle 1: tbf rate 8bit burst 100b latency 100ms",
+            "$TC qdisc replace dev $DUMMY handle 2: parent 1:1 fq_codel limit 1000",
+            [
+                "ping -I $DUMMY -c2 10.10.11.11",
+                1
+            ],
+            "$TC qdisc change dev $DUMMY handle 2: parent 1:1 fq_codel limit 1"
+        ],
+        "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 2: parent 1:1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -s qdisc show dev $DUMMY",
+        "matchPattern": "backlog 0b 0p",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY handle 1: root"
+        ]
+    },
+    {
+        "id": "21c3",
+        "name": "Test TBF with FQ_PIE Backlog Accounting in gso_skb case against underflow",
+        "category": [
+            "qdisc",
+            "tbf",
+            "fq_pie"
+        ],
+        "plugins": {
+            "requires": [
+                "nsPlugin"
+            ]
+        },
+        "setup": [
+            "$IP link set dev $DUMMY up || true",
+            "$IP addr add 10.10.11.10/24 dev $DUMMY || true",
+            "$TC qdisc add dev $DUMMY root handle 1: tbf rate 8bit burst 100b latency 100ms",
+            "$TC qdisc replace dev $DUMMY handle 2: parent 1:1 fq_pie limit 1000",
+            [
+                "ping -I $DUMMY -c2 10.10.11.11",
+                1
+            ],
+            "$TC qdisc change dev $DUMMY handle 2: parent 1:1 fq_pie limit 1"
+        ],
+        "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 2: parent 1:1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -s qdisc show dev $DUMMY",
+        "matchPattern": "backlog 0b 0p",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY handle 1: root"
+        ]
+    },
+    {
         "id": "a4bb",
         "name": "Test FQ_CODEL with HTB parent - force packet drop with empty queue",
         "category": [
diff --git a/tools/testing/selftests/ublk/file_backed.c b/tools/testing/selftests/ublk/file_backed.c
index 2d93ac860bd5..cd9fe69ecce2 100644
--- a/tools/testing/selftests/ublk/file_backed.c
+++ b/tools/testing/selftests/ublk/file_backed.c
@@ -20,7 +20,7 @@ static int loop_queue_flush_io(struct ublk_thread *t, struct ublk_queue *q,
 	struct io_uring_sqe *sqe[1];
 
 	ublk_io_alloc_sqes(t, sqe, 1);
-	io_uring_prep_fsync(sqe[0], 1 /*fds[1]*/, IORING_FSYNC_DATASYNC);
+	io_uring_prep_fsync(sqe[0], ublk_get_registered_fd(q, 1) /*fds[1]*/, IORING_FSYNC_DATASYNC);
 	io_uring_sqe_set_flags(sqe[0], IOSQE_FIXED_FILE);
 	/* bit63 marks us as tgt io */
 	sqe[0]->user_data = build_user_data(tag, ublk_op, 0, q->q_id, 1);
@@ -42,7 +42,7 @@ static int loop_queue_tgt_rw_io(struct ublk_thread *t, struct ublk_queue *q,
 		if (!sqe[0])
 			return -ENOMEM;
 
-		io_uring_prep_rw(op, sqe[0], 1 /*fds[1]*/,
+		io_uring_prep_rw(op, sqe[0], ublk_get_registered_fd(q, 1) /*fds[1]*/,
 				addr,
 				iod->nr_sectors << 9,
 				iod->start_sector << 9);
@@ -56,19 +56,19 @@ static int loop_queue_tgt_rw_io(struct ublk_thread *t, struct ublk_queue *q,
 
 	ublk_io_alloc_sqes(t, sqe, 3);
 
-	io_uring_prep_buf_register(sqe[0], 0, tag, q->q_id, ublk_get_io(q, tag)->buf_index);
+	io_uring_prep_buf_register(sqe[0], q, tag, q->q_id, ublk_get_io(q, tag)->buf_index);
 	sqe[0]->flags |= IOSQE_CQE_SKIP_SUCCESS | IOSQE_IO_HARDLINK;
 	sqe[0]->user_data = build_user_data(tag,
 			ublk_cmd_op_nr(sqe[0]->cmd_op), 0, q->q_id, 1);
 
-	io_uring_prep_rw(op, sqe[1], 1 /*fds[1]*/, 0,
+	io_uring_prep_rw(op, sqe[1], ublk_get_registered_fd(q, 1) /*fds[1]*/, 0,
 		iod->nr_sectors << 9,
 		iod->start_sector << 9);
 	sqe[1]->buf_index = tag;
 	sqe[1]->flags |= IOSQE_FIXED_FILE | IOSQE_IO_HARDLINK;
 	sqe[1]->user_data = build_user_data(tag, ublk_op, 0, q->q_id, 1);
 
-	io_uring_prep_buf_unregister(sqe[2], 0, tag, q->q_id, ublk_get_io(q, tag)->buf_index);
+	io_uring_prep_buf_unregister(sqe[2], q, tag, q->q_id, ublk_get_io(q, tag)->buf_index);
 	sqe[2]->user_data = build_user_data(tag, ublk_cmd_op_nr(sqe[2]->cmd_op), 0, q->q_id, 1);
 
 	return 2;
diff --git a/tools/testing/selftests/ublk/kublk.c b/tools/testing/selftests/ublk/kublk.c
index 95188065b2e9..b71faba86c3b 100644
--- a/tools/testing/selftests/ublk/kublk.c
+++ b/tools/testing/selftests/ublk/kublk.c
@@ -432,7 +432,7 @@ static void ublk_thread_deinit(struct ublk_thread *t)
 	}
 }
 
-static int ublk_queue_init(struct ublk_queue *q, unsigned extra_flags)
+static int ublk_queue_init(struct ublk_queue *q, unsigned long long extra_flags)
 {
 	struct ublk_dev *dev = q->dev;
 	int depth = dev->dev_info.queue_depth;
@@ -446,6 +446,9 @@ static int ublk_queue_init(struct ublk_queue *q, unsigned extra_flags)
 	q->flags = dev->dev_info.flags;
 	q->flags |= extra_flags;
 
+	/* Cache fd in queue for fast path access */
+	q->ublk_fd = dev->fds[0];
+
 	cmd_buf_size = ublk_queue_cmd_buf_sz(q);
 	off = UBLKSRV_CMD_BUF_OFFSET + q->q_id * ublk_queue_max_cmd_buf_sz();
 	q->io_cmd_buf = mmap(0, cmd_buf_size, PROT_READ,
@@ -481,9 +484,10 @@ static int ublk_queue_init(struct ublk_queue *q, unsigned extra_flags)
 	return -ENOMEM;
 }
 
-static int ublk_thread_init(struct ublk_thread *t)
+static int ublk_thread_init(struct ublk_thread *t, unsigned long long extra_flags)
 {
 	struct ublk_dev *dev = t->dev;
+	unsigned long long flags = dev->dev_info.flags | extra_flags;
 	int ring_depth = dev->tgt.sq_depth, cq_depth = dev->tgt.cq_depth;
 	int ret;
 
@@ -512,7 +516,17 @@ static int ublk_thread_init(struct ublk_thread *t)
 
 	io_uring_register_ring_fd(&t->ring);
 
-	ret = io_uring_register_files(&t->ring, dev->fds, dev->nr_fds);
+	if (flags & UBLKS_Q_NO_UBLK_FIXED_FD) {
+		/* Register only backing files starting from index 1, exclude ublk control device */
+		if (dev->nr_fds > 1) {
+			ret = io_uring_register_files(&t->ring, &dev->fds[1], dev->nr_fds - 1);
+		} else {
+			/* No backing files to register, skip file registration */
+			ret = 0;
+		}
+	} else {
+		ret = io_uring_register_files(&t->ring, dev->fds, dev->nr_fds);
+	}
 	if (ret) {
 		ublk_err("ublk dev %d thread %d register files failed %d\n",
 				t->dev->dev_info.dev_id, t->idx, ret);
@@ -626,9 +640,12 @@ int ublk_queue_io_cmd(struct ublk_thread *t, struct ublk_io *io)
 
 	/* These fields should be written once, never change */
 	ublk_set_sqe_cmd_op(sqe[0], cmd_op);
-	sqe[0]->fd		= 0;	/* dev->fds[0] */
+	sqe[0]->fd	= ublk_get_registered_fd(q, 0);	/* dev->fds[0] */
 	sqe[0]->opcode	= IORING_OP_URING_CMD;
-	sqe[0]->flags	= IOSQE_FIXED_FILE;
+	if (q->flags & UBLKS_Q_NO_UBLK_FIXED_FD)
+		sqe[0]->flags	= 0;  /* Use raw FD, not fixed file */
+	else
+		sqe[0]->flags	= IOSQE_FIXED_FILE;
 	sqe[0]->rw_flags	= 0;
 	cmd->tag	= io->tag;
 	cmd->q_id	= q->q_id;
@@ -832,6 +849,7 @@ struct ublk_thread_info {
 	unsigned		idx;
 	sem_t 			*ready;
 	cpu_set_t 		*affinity;
+	unsigned long long	extra_flags;
 };
 
 static void *ublk_io_handler_fn(void *data)
@@ -844,7 +862,7 @@ static void *ublk_io_handler_fn(void *data)
 	t->dev = info->dev;
 	t->idx = info->idx;
 
-	ret = ublk_thread_init(t);
+	ret = ublk_thread_init(t, info->extra_flags);
 	if (ret) {
 		ublk_err("ublk dev %d thread %u init failed\n",
 				dev_id, t->idx);
@@ -934,6 +952,8 @@ static int ublk_start_daemon(const struct dev_ctx *ctx, struct ublk_dev *dev)
 
 	if (ctx->auto_zc_fallback)
 		extra_flags = UBLKS_Q_AUTO_BUF_REG_FALLBACK;
+	if (ctx->no_ublk_fixed_fd)
+		extra_flags |= UBLKS_Q_NO_UBLK_FIXED_FD;
 
 	for (i = 0; i < dinfo->nr_hw_queues; i++) {
 		dev->q[i].dev = dev;
@@ -951,6 +971,7 @@ static int ublk_start_daemon(const struct dev_ctx *ctx, struct ublk_dev *dev)
 		tinfo[i].dev = dev;
 		tinfo[i].idx = i;
 		tinfo[i].ready = &ready;
+		tinfo[i].extra_flags = extra_flags;
 
 		/*
 		 * If threads are not tied 1:1 to queues, setting thread
@@ -1400,7 +1421,7 @@ static int cmd_dev_get_features(void)
 
 			if (!((1ULL << i)  & features))
 				continue;
-			if (i < sizeof(feat_map) / sizeof(feat_map[0]))
+			if (i < ARRAY_SIZE(feat_map))
 				feat = feat_map[i];
 			else
 				feat = "unknown";
@@ -1471,13 +1492,13 @@ static void __cmd_create_help(char *exe, bool recovery)
 	printf("%s %s -t [null|loop|stripe|fault_inject] [-q nr_queues] [-d depth] [-n dev_id]\n",
 			exe, recovery ? "recover" : "add");
 	printf("\t[--foreground] [--quiet] [-z] [--auto_zc] [--auto_zc_fallback] [--debug_mask mask] [-r 0|1 ] [-g]\n");
-	printf("\t[-e 0|1 ] [-i 0|1]\n");
+	printf("\t[-e 0|1 ] [-i 0|1] [--no_ublk_fixed_fd]\n");
 	printf("\t[--nthreads threads] [--per_io_tasks]\n");
 	printf("\t[target options] [backfile1] [backfile2] ...\n");
 	printf("\tdefault: nr_queues=2(max 32), depth=128(max 1024), dev_id=-1(auto allocation)\n");
 	printf("\tdefault: nthreads=nr_queues");
 
-	for (i = 0; i < sizeof(tgt_ops_list) / sizeof(tgt_ops_list[0]); i++) {
+	for (i = 0; i < ARRAY_SIZE(tgt_ops_list); i++) {
 		const struct ublk_tgt_ops *ops = tgt_ops_list[i];
 
 		if (ops->usage)
@@ -1534,6 +1555,7 @@ int main(int argc, char *argv[])
 		{ "size",		1,	NULL, 's'},
 		{ "nthreads",		1,	NULL,  0 },
 		{ "per_io_tasks",	0,	NULL,  0 },
+		{ "no_ublk_fixed_fd",	0,	NULL,  0 },
 		{ 0, 0, 0, 0 }
 	};
 	const struct ublk_tgt_ops *ops = NULL;
@@ -1613,6 +1635,8 @@ int main(int argc, char *argv[])
 				ctx.nthreads = strtol(optarg, NULL, 10);
 			if (!strcmp(longopts[option_idx].name, "per_io_tasks"))
 				ctx.per_io_tasks = 1;
+			if (!strcmp(longopts[option_idx].name, "no_ublk_fixed_fd"))
+				ctx.no_ublk_fixed_fd = 1;
 			break;
 		case '?':
 			/*
diff --git a/tools/testing/selftests/ublk/kublk.h b/tools/testing/selftests/ublk/kublk.h
index 219233f8a053..5e55484fb0aa 100644
--- a/tools/testing/selftests/ublk/kublk.h
+++ b/tools/testing/selftests/ublk/kublk.h
@@ -77,6 +77,7 @@ struct dev_ctx {
 	unsigned int	recovery:1;
 	unsigned int	auto_zc_fallback:1;
 	unsigned int	per_io_tasks:1;
+	unsigned int	no_ublk_fixed_fd:1;
 
 	int _evtfd;
 	int _shmid;
@@ -166,7 +167,9 @@ struct ublk_queue {
 
 /* borrow one bit of ublk uapi flags, which may never be used */
 #define UBLKS_Q_AUTO_BUF_REG_FALLBACK	(1ULL << 63)
+#define UBLKS_Q_NO_UBLK_FIXED_FD	(1ULL << 62)
 	__u64 flags;
+	int ublk_fd;	/* cached ublk char device fd */
 	struct ublk_io ios[UBLK_QUEUE_DEPTH];
 };
 
@@ -273,34 +276,48 @@ static inline int ublk_io_alloc_sqes(struct ublk_thread *t,
 	return nr_sqes;
 }
 
-static inline void io_uring_prep_buf_register(struct io_uring_sqe *sqe,
-		int dev_fd, int tag, int q_id, __u64 index)
+static inline int ublk_get_registered_fd(struct ublk_queue *q, int fd_index)
+{
+	if (q->flags & UBLKS_Q_NO_UBLK_FIXED_FD) {
+		if (fd_index == 0)
+			/* Return the raw ublk FD for index 0 */
+			return q->ublk_fd;
+		/* Adjust index for backing files (index 1 becomes 0, etc.) */
+		return fd_index - 1;
+	}
+	return fd_index;
+}
+
+static inline void __io_uring_prep_buf_reg_unreg(struct io_uring_sqe *sqe,
+		struct ublk_queue *q, int tag, int q_id, __u64 index)
 {
 	struct ublksrv_io_cmd *cmd = (struct ublksrv_io_cmd *)sqe->cmd;
+	int dev_fd = ublk_get_registered_fd(q, 0);
 
 	io_uring_prep_read(sqe, dev_fd, 0, 0, 0);
 	sqe->opcode		= IORING_OP_URING_CMD;
-	sqe->flags		|= IOSQE_FIXED_FILE;
-	sqe->cmd_op		= UBLK_U_IO_REGISTER_IO_BUF;
+	if (q->flags & UBLKS_Q_NO_UBLK_FIXED_FD)
+		sqe->flags	&= ~IOSQE_FIXED_FILE;
+	else
+		sqe->flags	|= IOSQE_FIXED_FILE;
 
 	cmd->tag		= tag;
 	cmd->addr		= index;
 	cmd->q_id		= q_id;
 }
 
-static inline void io_uring_prep_buf_unregister(struct io_uring_sqe *sqe,
-		int dev_fd, int tag, int q_id, __u64 index)
+static inline void io_uring_prep_buf_register(struct io_uring_sqe *sqe,
+		struct ublk_queue *q, int tag, int q_id, __u64 index)
 {
-	struct ublksrv_io_cmd *cmd = (struct ublksrv_io_cmd *)sqe->cmd;
+	__io_uring_prep_buf_reg_unreg(sqe, q, tag, q_id, index);
+	sqe->cmd_op		= UBLK_U_IO_REGISTER_IO_BUF;
+}
 
-	io_uring_prep_read(sqe, dev_fd, 0, 0, 0);
-	sqe->opcode		= IORING_OP_URING_CMD;
-	sqe->flags		|= IOSQE_FIXED_FILE;
+static inline void io_uring_prep_buf_unregister(struct io_uring_sqe *sqe,
+		struct ublk_queue *q, int tag, int q_id, __u64 index)
+{
+	__io_uring_prep_buf_reg_unreg(sqe, q, tag, q_id, index);
 	sqe->cmd_op		= UBLK_U_IO_UNREGISTER_IO_BUF;
-
-	cmd->tag		= tag;
-	cmd->addr		= index;
-	cmd->q_id		= q_id;
 }
 
 static inline void *ublk_get_sqe_cmd(const struct io_uring_sqe *sqe)
diff --git a/tools/testing/selftests/ublk/null.c b/tools/testing/selftests/ublk/null.c
index f0e0003a4860..280043f6b689 100644
--- a/tools/testing/selftests/ublk/null.c
+++ b/tools/testing/selftests/ublk/null.c
@@ -63,7 +63,7 @@ static int null_queue_zc_io(struct ublk_thread *t, struct ublk_queue *q,
 
 	ublk_io_alloc_sqes(t, sqe, 3);
 
-	io_uring_prep_buf_register(sqe[0], 0, tag, q->q_id, ublk_get_io(q, tag)->buf_index);
+	io_uring_prep_buf_register(sqe[0], q, tag, q->q_id, ublk_get_io(q, tag)->buf_index);
 	sqe[0]->user_data = build_user_data(tag,
 			ublk_cmd_op_nr(sqe[0]->cmd_op), 0, q->q_id, 1);
 	sqe[0]->flags |= IOSQE_CQE_SKIP_SUCCESS | IOSQE_IO_HARDLINK;
@@ -71,7 +71,7 @@ static int null_queue_zc_io(struct ublk_thread *t, struct ublk_queue *q,
 	__setup_nop_io(tag, iod, sqe[1], q->q_id);
 	sqe[1]->flags |= IOSQE_IO_HARDLINK;
 
-	io_uring_prep_buf_unregister(sqe[2], 0, tag, q->q_id, ublk_get_io(q, tag)->buf_index);
+	io_uring_prep_buf_unregister(sqe[2], q, tag, q->q_id, ublk_get_io(q, tag)->buf_index);
 	sqe[2]->user_data = build_user_data(tag, ublk_cmd_op_nr(sqe[2]->cmd_op), 0, q->q_id, 1);
 
 	// buf register is marked as IOSQE_CQE_SKIP_SUCCESS
diff --git a/tools/testing/selftests/ublk/stripe.c b/tools/testing/selftests/ublk/stripe.c
index 1fb9b7cc281b..791fa8dc1651 100644
--- a/tools/testing/selftests/ublk/stripe.c
+++ b/tools/testing/selftests/ublk/stripe.c
@@ -142,7 +142,7 @@ static int stripe_queue_tgt_rw_io(struct ublk_thread *t, struct ublk_queue *q,
 	ublk_io_alloc_sqes(t, sqe, s->nr + extra);
 
 	if (zc) {
-		io_uring_prep_buf_register(sqe[0], 0, tag, q->q_id, io->buf_index);
+		io_uring_prep_buf_register(sqe[0], q, tag, q->q_id, io->buf_index);
 		sqe[0]->flags |= IOSQE_CQE_SKIP_SUCCESS | IOSQE_IO_HARDLINK;
 		sqe[0]->user_data = build_user_data(tag,
 			ublk_cmd_op_nr(sqe[0]->cmd_op), 0, q->q_id, 1);
@@ -168,7 +168,7 @@ static int stripe_queue_tgt_rw_io(struct ublk_thread *t, struct ublk_queue *q,
 	if (zc) {
 		struct io_uring_sqe *unreg = sqe[s->nr + 1];
 
-		io_uring_prep_buf_unregister(unreg, 0, tag, q->q_id, io->buf_index);
+		io_uring_prep_buf_unregister(unreg, q, tag, q->q_id, io->buf_index);
 		unreg->user_data = build_user_data(
 			tag, ublk_cmd_op_nr(unreg->cmd_op), 0, q->q_id, 1);
 	}
diff --git a/tools/testing/selftests/ublk/test_stress_04.sh b/tools/testing/selftests/ublk/test_stress_04.sh
index 40d1437ca298..3f901db4d09d 100755
--- a/tools/testing/selftests/ublk/test_stress_04.sh
+++ b/tools/testing/selftests/ublk/test_stress_04.sh
@@ -28,14 +28,14 @@ _create_backfile 0 256M
 _create_backfile 1 128M
 _create_backfile 2 128M
 
-ublk_io_and_kill_daemon 8G -t null -q 4 -z &
-ublk_io_and_kill_daemon 256M -t loop -q 4 -z "${UBLK_BACKFILES[0]}" &
+ublk_io_and_kill_daemon 8G -t null -q 4 -z --no_ublk_fixed_fd &
+ublk_io_and_kill_daemon 256M -t loop -q 4 -z --no_ublk_fixed_fd "${UBLK_BACKFILES[0]}" &
 ublk_io_and_kill_daemon 256M -t stripe -q 4 -z "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
 
 if _have_feature "AUTO_BUF_REG"; then
 	ublk_io_and_kill_daemon 8G -t null -q 4 --auto_zc &
 	ublk_io_and_kill_daemon 256M -t loop -q 4 --auto_zc "${UBLK_BACKFILES[0]}" &
-	ublk_io_and_kill_daemon 256M -t stripe -q 4 --auto_zc "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
+	ublk_io_and_kill_daemon 256M -t stripe -q 4 --auto_zc --no_ublk_fixed_fd "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
 	ublk_io_and_kill_daemon 8G -t null -q 4 -z --auto_zc --auto_zc_fallback &
 fi
 
diff --git a/tools/testing/shared/linux/idr.h b/tools/testing/shared/linux/idr.h
index 4e342f2e37cf..676c5564e33f 100644
--- a/tools/testing/shared/linux/idr.h
+++ b/tools/testing/shared/linux/idr.h
@@ -1 +1,5 @@
+/* Avoid duplicate definitions due to system headers. */
+#ifdef __CONCAT
+#undef __CONCAT
+#endif
 #include "../../../../include/linux/idr.h"