spi: spi-fsl-dspi: Target mode improvements

Merge series from James Clark <james.clark@linaro.org>:

Improve usability of target mode by reporting FIFO errors and increasing
the buffer size when DMA is used. While we're touching DMA stuff also
switch to non-coherent memory, although this is unrelated to target
mode.

With the combination of the commit to increase the DMA buffer size and
the commit to use non-coherent memory, the host mode performance figures
are as follows on S32G3:

  # spidev_test --device /dev/spidev1.0 --bpw 8 --size <test_size> --cpha --iter 10000000 --speed 10000000

  Coherent (4096 byte transfers): 6534 kbps
  Non-coherent:                   7347 kbps

  Coherent (16 byte transfers):    447 kbps
  Non-coherent:                    448 kbps

Just for comparison running the same test in XSPI mode:

  4096 byte transfers:            2143 kbps
  16 byte transfers:               637 kbps

These tests required hacking S32G3 to use DMA in host mode, although
the figures should be representative of target mode too where DMA is
used. And the other devices that use DMA in host mode should see similar
improvements.

34 files changed, 1148 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/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/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/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 d8cfcf9bb825..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;
@@ -2748,17 +3038,18 @@ TEST(data_steal) {
 	pid = fork();
 	ASSERT_GE(pid, 0);
 	if (!pid) {
-		EXPECT_EQ(recv(cfd, buf, sizeof(buf), MSG_WAITALL),
-			  sizeof(buf));
+		EXPECT_EQ(recv(cfd, buf, sizeof(buf) / 2, MSG_WAITALL),
+			  sizeof(buf) / 2);
 		exit(!__test_passed(_metadata));
 	}
 
-	usleep(2000);
+	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));
-	usleep(2000);
+	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.
@@ -2766,9 +3057,6 @@ TEST(data_steal) {
 
 	close(fd);
 	close(cfd);
-
-	EXPECT_EQ(wait(&status), pid);
-	EXPECT_EQ(status, 0);
 }
 
 static void __attribute__((constructor)) fips_check(void) {
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"