Merge tag 'bpf-next-6.15' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Pull bpf updates from Alexei Starovoitov:
 "For this merge window we're splitting BPF pull request into three for
  higher visibility: main changes, res_spin_lock, try_alloc_pages.

  These are the main BPF changes:

   - Add DFA-based live registers analysis to improve verification of
     programs with loops (Eduard Zingerman)

   - Introduce load_acquire and store_release BPF instructions and add
     x86, arm64 JIT support (Peilin Ye)

   - Fix loop detection logic in the verifier (Eduard Zingerman)

   - Drop unnecesary lock in bpf_map_inc_not_zero() (Eric Dumazet)

   - Add kfunc for populating cpumask bits (Emil Tsalapatis)

   - Convert various shell based tests to selftests/bpf/test_progs
     format (Bastien Curutchet)

   - Allow passing referenced kptrs into struct_ops callbacks (Amery
     Hung)

   - Add a flag to LSM bpf hook to facilitate bpf program signing
     (Blaise Boscaccy)

   - Track arena arguments in kfuncs (Ihor Solodrai)

   - Add copy_remote_vm_str() helper for reading strings from remote VM
     and bpf_copy_from_user_task_str() kfunc (Jordan Rome)

   - Add support for timed may_goto instruction (Kumar Kartikeya
     Dwivedi)

   - Allow bpf_get_netns_cookie() int cgroup_skb programs (Mahe Tardy)

   - Reduce bpf_cgrp_storage_busy false positives when accessing cgroup
     local storage (Martin KaFai Lau)

   - Introduce bpf_dynptr_copy() kfunc (Mykyta Yatsenko)

   - Allow retrieving BTF data with BTF token (Mykyta Yatsenko)

   - Add BPF kfuncs to set and get xattrs with 'security.bpf.' prefix
     (Song Liu)

   - Reject attaching programs to noreturn functions (Yafang Shao)

   - Introduce pre-order traversal of cgroup bpf programs (Yonghong
     Song)"

* tag 'bpf-next-6.15' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (186 commits)
  selftests/bpf: Add selftests for load-acquire/store-release when register number is invalid
  bpf: Fix out-of-bounds read in check_atomic_load/store()
  libbpf: Add namespace for errstr making it libbpf_errstr
  bpf: Add struct_ops context information to struct bpf_prog_aux
  selftests/bpf: Sanitize pointer prior fclose()
  selftests/bpf: Migrate test_xdp_vlan.sh into test_progs
  selftests/bpf: test_xdp_vlan: Rename BPF sections
  bpf: clarify a misleading verifier error message
  selftests/bpf: Add selftest for attaching fexit to __noreturn functions
  bpf: Reject attaching fexit/fmod_ret to __noreturn functions
  bpf: Only fails the busy counter check in bpf_cgrp_storage_get if it creates storage
  bpf: Make perf_event_read_output accessible in all program types.
  bpftool: Using the right format specifiers
  bpftool: Add -Wformat-signedness flag to detect format errors
  selftests/bpf: Test freplace from user namespace
  libbpf: Pass BPF token from find_prog_btf_id to BPF_BTF_GET_FD_BY_ID
  bpf: Return prog btf_id without capable check
  bpf: BPF token support for BPF_BTF_GET_FD_BY_ID
  bpf, x86: Fix objtool warning for timed may_goto
  bpf: Check map->record at the beginning of check_and_free_fields()
  ...

tools/testing/selftests/bpf/DENYLIST.aarch64

@@ -1,12 +1,3 @@
-bpf_cookie/multi_kprobe_attach_api               # kprobe_multi_link_api_subtest:FAIL:fentry_raw_skel_load unexpected error: -3
-bpf_cookie/multi_kprobe_link_api                 # kprobe_multi_link_api_subtest:FAIL:fentry_raw_skel_load unexpected error: -3
-kprobe_multi_bench_attach                        # needs CONFIG_FPROBE
-kprobe_multi_test                                # needs CONFIG_FPROBE
-module_attach                                    # prog 'kprobe_multi': failed to auto-attach: -95
 fentry_test/fentry_many_args                     # fentry_many_args:FAIL:fentry_many_args_attach unexpected error: -524
 fexit_test/fexit_many_args                       # fexit_many_args:FAIL:fexit_many_args_attach unexpected error: -524
 tracing_struct/struct_many_args                  # struct_many_args:FAIL:tracing_struct_many_args__attach unexpected error: -524
-fill_link_info/kprobe_multi_link_info            # bpf_program__attach_kprobe_multi_opts unexpected error: -95
-fill_link_info/kretprobe_multi_link_info         # bpf_program__attach_kprobe_multi_opts unexpected error: -95
-fill_link_info/kprobe_multi_invalid_ubuff        # bpf_program__attach_kprobe_multi_opts unexpected error: -95
-missed/kprobe_recursion                          # missed_kprobe_recursion__attach unexpected error: -95 (errno 95)

tools/testing/selftests/bpf/Makefile

@@ -95,18 +95,12 @@ TEST_GEN_PROGS += test_progs-cpuv4
 TEST_INST_SUBDIRS += cpuv4
 endif
 
-TEST_GEN_FILES = test_lwt_ip_encap.bpf.o test_tc_edt.bpf.o
+TEST_GEN_FILES = test_tc_edt.bpf.o
 TEST_FILES = xsk_prereqs.sh $(wildcard progs/btf_dump_test_case_*.c)
 
 # Order correspond to 'make run_tests' order
 TEST_PROGS := test_kmod.sh \
-	test_xdp_redirect_multi.sh \
-	test_tunnel.sh \
-	test_lwt_seg6local.sh \
 	test_lirc_mode2.sh \
-	test_xdp_vlan_mode_generic.sh \
-	test_xdp_vlan_mode_native.sh \
-	test_lwt_ip_encap.sh \
 	test_tc_tunnel.sh \
 	test_tc_edt.sh \
 	test_xdping.sh \
@@ -117,9 +111,9 @@ TEST_PROGS := test_kmod.sh \
 	test_xsk.sh \
 	test_xdp_features.sh
 
-TEST_PROGS_EXTENDED := with_addr.sh \
-	with_tunnels.sh ima_setup.sh verify_sig_setup.sh \
-	test_xdp_vlan.sh test_bpftool.py
+TEST_PROGS_EXTENDED := \
+	ima_setup.sh verify_sig_setup.sh \
+	test_bpftool.py
 
 TEST_KMODS := bpf_testmod.ko bpf_test_no_cfi.ko bpf_test_modorder_x.ko \
 	bpf_test_modorder_y.ko
@@ -135,7 +129,6 @@ TEST_GEN_PROGS_EXTENDED = \
 	veristat \
 	xdp_features \
 	xdp_hw_metadata \
-	xdp_redirect_multi \
 	xdp_synproxy \
 	xdping \
 	xskxceiver
@@ -184,9 +177,14 @@ ifeq ($(feature-llvm),1)
   LLVM_CONFIG_LIB_COMPONENTS := mcdisassembler all-targets
   # both llvm-config and lib.mk add -D_GNU_SOURCE, which ends up as conflict
   LLVM_CFLAGS  += $(filter-out -D_GNU_SOURCE,$(shell $(LLVM_CONFIG) --cflags))
-  LLVM_LDLIBS  += $(shell $(LLVM_CONFIG) --link-static --libs $(LLVM_CONFIG_LIB_COMPONENTS))
-  LLVM_LDLIBS  += $(shell $(LLVM_CONFIG) --link-static --system-libs $(LLVM_CONFIG_LIB_COMPONENTS))
-  LLVM_LDLIBS  += -lstdc++
+  # Prefer linking statically if it's available, otherwise fallback to shared
+  ifeq ($(shell $(LLVM_CONFIG) --link-static --libs >/dev/null 2>&1 && echo static),static)
+    LLVM_LDLIBS  += $(shell $(LLVM_CONFIG) --link-static --libs $(LLVM_CONFIG_LIB_COMPONENTS))
+    LLVM_LDLIBS  += $(shell $(LLVM_CONFIG) --link-static --system-libs $(LLVM_CONFIG_LIB_COMPONENTS))
+    LLVM_LDLIBS  += -lstdc++
+  else
+    LLVM_LDLIBS  += $(shell $(LLVM_CONFIG) --link-shared --libs $(LLVM_CONFIG_LIB_COMPONENTS))
+  endif
   LLVM_LDFLAGS += $(shell $(LLVM_CONFIG) --ldflags)
 endif
 
@@ -306,6 +304,7 @@ $(OUTPUT)/runqslower: $(BPFOBJ) | $(DEFAULT_BPFTOOL) $(RUNQSLOWER_OUTPUT)
 		    BPFTOOL_OUTPUT=$(HOST_BUILD_DIR)/bpftool/		       \
 		    BPFOBJ_OUTPUT=$(BUILD_DIR)/libbpf/			       \
 		    BPFOBJ=$(BPFOBJ) BPF_INCLUDE=$(INCLUDE_DIR)		       \
+		    BPF_TARGET_ENDIAN=$(BPF_TARGET_ENDIAN)		       \
 		    EXTRA_CFLAGS='-g $(OPT_FLAGS) $(SAN_CFLAGS) $(EXTRA_CFLAGS)' \
 		    EXTRA_LDFLAGS='$(SAN_LDFLAGS) $(EXTRA_LDFLAGS)' &&	       \
 		    cp $(RUNQSLOWER_OUTPUT)runqslower $@
@@ -684,6 +683,7 @@ $(OUTPUT)/$(TRUNNER_BINARY): $(TRUNNER_TEST_OBJS)			\
 			     $(TRUNNER_EXTRA_OBJS) $$(BPFOBJ)		\
 			     $(RESOLVE_BTFIDS)				\
 			     $(TRUNNER_BPFTOOL)				\
+			     $(OUTPUT)/veristat				\
 			     | $(TRUNNER_BINARY)-extras
 	$$(call msg,BINARY,,$$@)
 	$(Q)$$(CC) $$(CFLAGS) $$(filter %.a %.o,$$^) $$(LDLIBS) $$(LDFLAGS) -o $$@

tools/testing/selftests/bpf/bpf_arena_spin_lock.h

@@ -0,0 +1,533 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#ifndef BPF_ARENA_SPIN_LOCK_H
+#define BPF_ARENA_SPIN_LOCK_H
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_atomic.h"
+
+#define arch_mcs_spin_lock_contended_label(l, label) smp_cond_load_acquire_label(l, VAL, label)
+#define arch_mcs_spin_unlock_contended(l) smp_store_release((l), 1)
+
+#if defined(ENABLE_ATOMICS_TESTS) && defined(__BPF_FEATURE_ADDR_SPACE_CAST)
+
+#define EBUSY 16
+#define EOPNOTSUPP 95
+#define ETIMEDOUT 110
+
+#ifndef __arena
+#define __arena __attribute__((address_space(1)))
+#endif
+
+extern unsigned long CONFIG_NR_CPUS __kconfig;
+
+/*
+ * Typically, we'd just rely on the definition in vmlinux.h for qspinlock, but
+ * PowerPC overrides the definition to define lock->val as u32 instead of
+ * atomic_t, leading to compilation errors.  Import a local definition below so
+ * that we don't depend on the vmlinux.h version.
+ */
+
+struct __qspinlock {
+	union {
+		atomic_t val;
+		struct {
+			u8 locked;
+			u8 pending;
+		};
+		struct {
+			u16 locked_pending;
+			u16 tail;
+		};
+	};
+};
+
+#define arena_spinlock_t struct __qspinlock
+/* FIXME: Using typedef causes CO-RE relocation error */
+/* typedef struct qspinlock arena_spinlock_t; */
+
+struct arena_mcs_spinlock {
+	struct arena_mcs_spinlock __arena *next;
+	int locked;
+	int count;
+};
+
+struct arena_qnode {
+	struct arena_mcs_spinlock mcs;
+};
+
+#define _Q_MAX_NODES		4
+#define _Q_PENDING_LOOPS	1
+
+/*
+ * Bitfields in the atomic value:
+ *
+ *  0- 7: locked byte
+ *     8: pending
+ *  9-15: not used
+ * 16-17: tail index
+ * 18-31: tail cpu (+1)
+ */
+#define _Q_MAX_CPUS		1024
+
+#define	_Q_SET_MASK(type)	(((1U << _Q_ ## type ## _BITS) - 1)\
+				      << _Q_ ## type ## _OFFSET)
+#define _Q_LOCKED_OFFSET	0
+#define _Q_LOCKED_BITS		8
+#define _Q_LOCKED_MASK		_Q_SET_MASK(LOCKED)
+
+#define _Q_PENDING_OFFSET	(_Q_LOCKED_OFFSET + _Q_LOCKED_BITS)
+#define _Q_PENDING_BITS		8
+#define _Q_PENDING_MASK		_Q_SET_MASK(PENDING)
+
+#define _Q_TAIL_IDX_OFFSET	(_Q_PENDING_OFFSET + _Q_PENDING_BITS)
+#define _Q_TAIL_IDX_BITS	2
+#define _Q_TAIL_IDX_MASK	_Q_SET_MASK(TAIL_IDX)
+
+#define _Q_TAIL_CPU_OFFSET	(_Q_TAIL_IDX_OFFSET + _Q_TAIL_IDX_BITS)
+#define _Q_TAIL_CPU_BITS	(32 - _Q_TAIL_CPU_OFFSET)
+#define _Q_TAIL_CPU_MASK	_Q_SET_MASK(TAIL_CPU)
+
+#define _Q_TAIL_OFFSET		_Q_TAIL_IDX_OFFSET
+#define _Q_TAIL_MASK		(_Q_TAIL_IDX_MASK | _Q_TAIL_CPU_MASK)
+
+#define _Q_LOCKED_VAL		(1U << _Q_LOCKED_OFFSET)
+#define _Q_PENDING_VAL		(1U << _Q_PENDING_OFFSET)
+
+#define likely(x) __builtin_expect(!!(x), 1)
+#define unlikely(x) __builtin_expect(!!(x), 0)
+
+struct arena_qnode __arena qnodes[_Q_MAX_CPUS][_Q_MAX_NODES];
+
+static inline u32 encode_tail(int cpu, int idx)
+{
+	u32 tail;
+
+	tail  = (cpu + 1) << _Q_TAIL_CPU_OFFSET;
+	tail |= idx << _Q_TAIL_IDX_OFFSET; /* assume < 4 */
+
+	return tail;
+}
+
+static inline struct arena_mcs_spinlock __arena *decode_tail(u32 tail)
+{
+	u32 cpu = (tail >> _Q_TAIL_CPU_OFFSET) - 1;
+	u32 idx = (tail &  _Q_TAIL_IDX_MASK) >> _Q_TAIL_IDX_OFFSET;
+
+	return &qnodes[cpu][idx].mcs;
+}
+
+static inline
+struct arena_mcs_spinlock __arena *grab_mcs_node(struct arena_mcs_spinlock __arena *base, int idx)
+{
+	return &((struct arena_qnode __arena *)base + idx)->mcs;
+}
+
+#define _Q_LOCKED_PENDING_MASK (_Q_LOCKED_MASK | _Q_PENDING_MASK)
+
+/**
+ * xchg_tail - Put in the new queue tail code word & retrieve previous one
+ * @lock : Pointer to queued spinlock structure
+ * @tail : The new queue tail code word
+ * Return: The previous queue tail code word
+ *
+ * xchg(lock, tail)
+ *
+ * p,*,* -> n,*,* ; prev = xchg(lock, node)
+ */
+static __always_inline u32 xchg_tail(arena_spinlock_t __arena *lock, u32 tail)
+{
+	u32 old, new;
+
+	old = atomic_read(&lock->val);
+	do {
+		new = (old & _Q_LOCKED_PENDING_MASK) | tail;
+		/*
+		 * We can use relaxed semantics since the caller ensures that
+		 * the MCS node is properly initialized before updating the
+		 * tail.
+		 */
+		/* These loops are not expected to stall, but we still need to
+		 * prove to the verifier they will terminate eventually.
+		 */
+		cond_break_label(out);
+	} while (!atomic_try_cmpxchg_relaxed(&lock->val, &old, new));
+
+	return old;
+out:
+	bpf_printk("RUNTIME ERROR: %s unexpected cond_break exit!!!", __func__);
+	return old;
+}
+
+/**
+ * clear_pending - clear the pending bit.
+ * @lock: Pointer to queued spinlock structure
+ *
+ * *,1,* -> *,0,*
+ */
+static __always_inline void clear_pending(arena_spinlock_t __arena *lock)
+{
+	WRITE_ONCE(lock->pending, 0);
+}
+
+/**
+ * clear_pending_set_locked - take ownership and clear the pending bit.
+ * @lock: Pointer to queued spinlock structure
+ *
+ * *,1,0 -> *,0,1
+ *
+ * Lock stealing is not allowed if this function is used.
+ */
+static __always_inline void clear_pending_set_locked(arena_spinlock_t __arena *lock)
+{
+	WRITE_ONCE(lock->locked_pending, _Q_LOCKED_VAL);
+}
+
+/**
+ * set_locked - Set the lock bit and own the lock
+ * @lock: Pointer to queued spinlock structure
+ *
+ * *,*,0 -> *,0,1
+ */
+static __always_inline void set_locked(arena_spinlock_t __arena *lock)
+{
+	WRITE_ONCE(lock->locked, _Q_LOCKED_VAL);
+}
+
+static __always_inline
+u32 arena_fetch_set_pending_acquire(arena_spinlock_t __arena *lock)
+{
+	u32 old, new;
+
+	old = atomic_read(&lock->val);
+	do {
+		new = old | _Q_PENDING_VAL;
+		/*
+		 * These loops are not expected to stall, but we still need to
+		 * prove to the verifier they will terminate eventually.
+		 */
+		cond_break_label(out);
+	} while (!atomic_try_cmpxchg_acquire(&lock->val, &old, new));
+
+	return old;
+out:
+	bpf_printk("RUNTIME ERROR: %s unexpected cond_break exit!!!", __func__);
+	return old;
+}
+
+/**
+ * arena_spin_trylock - try to acquire the queued spinlock
+ * @lock : Pointer to queued spinlock structure
+ * Return: 1 if lock acquired, 0 if failed
+ */
+static __always_inline int arena_spin_trylock(arena_spinlock_t __arena *lock)
+{
+	int val = atomic_read(&lock->val);
+
+	if (unlikely(val))
+		return 0;
+
+	return likely(atomic_try_cmpxchg_acquire(&lock->val, &val, _Q_LOCKED_VAL));
+}
+
+__noinline
+int arena_spin_lock_slowpath(arena_spinlock_t __arena __arg_arena *lock, u32 val)
+{
+	struct arena_mcs_spinlock __arena *prev, *next, *node0, *node;
+	int ret = -ETIMEDOUT;
+	u32 old, tail;
+	int idx;
+
+	/*
+	 * Wait for in-progress pending->locked hand-overs with a bounded
+	 * number of spins so that we guarantee forward progress.
+	 *
+	 * 0,1,0 -> 0,0,1
+	 */
+	if (val == _Q_PENDING_VAL) {
+		int cnt = _Q_PENDING_LOOPS;
+		val = atomic_cond_read_relaxed_label(&lock->val,
+						     (VAL != _Q_PENDING_VAL) || !cnt--,
+						     release_err);
+	}
+
+	/*
+	 * If we observe any contention; queue.
+	 */
+	if (val & ~_Q_LOCKED_MASK)
+		goto queue;
+
+	/*
+	 * trylock || pending
+	 *
+	 * 0,0,* -> 0,1,* -> 0,0,1 pending, trylock
+	 */
+	val = arena_fetch_set_pending_acquire(lock);
+
+	/*
+	 * If we observe contention, there is a concurrent locker.
+	 *
+	 * Undo and queue; our setting of PENDING might have made the
+	 * n,0,0 -> 0,0,0 transition fail and it will now be waiting
+	 * on @next to become !NULL.
+	 */
+	if (unlikely(val & ~_Q_LOCKED_MASK)) {
+
+		/* Undo PENDING if we set it. */
+		if (!(val & _Q_PENDING_MASK))
+			clear_pending(lock);
+
+		goto queue;
+	}
+
+	/*
+	 * We're pending, wait for the owner to go away.
+	 *
+	 * 0,1,1 -> *,1,0
+	 *
+	 * this wait loop must be a load-acquire such that we match the
+	 * store-release that clears the locked bit and create lock
+	 * sequentiality; this is because not all
+	 * clear_pending_set_locked() implementations imply full
+	 * barriers.
+	 */
+	if (val & _Q_LOCKED_MASK)
+		smp_cond_load_acquire_label(&lock->locked, !VAL, release_err);
+
+	/*
+	 * take ownership and clear the pending bit.
+	 *
+	 * 0,1,0 -> 0,0,1
+	 */
+	clear_pending_set_locked(lock);
+	return 0;
+
+	/*
+	 * End of pending bit optimistic spinning and beginning of MCS
+	 * queuing.
+	 */
+queue:
+	node0 = &(qnodes[bpf_get_smp_processor_id()])[0].mcs;
+	idx = node0->count++;
+	tail = encode_tail(bpf_get_smp_processor_id(), idx);
+
+	/*
+	 * 4 nodes are allocated based on the assumption that there will not be
+	 * nested NMIs taking spinlocks. That may not be true in some
+	 * architectures even though the chance of needing more than 4 nodes
+	 * will still be extremely unlikely. When that happens, we simply return
+	 * an error. Original qspinlock has a trylock fallback in this case.
+	 */
+	if (unlikely(idx >= _Q_MAX_NODES)) {
+		ret = -EBUSY;
+		goto release_node_err;
+	}
+
+	node = grab_mcs_node(node0, idx);
+
+	/*
+	 * Ensure that we increment the head node->count before initialising
+	 * the actual node. If the compiler is kind enough to reorder these
+	 * stores, then an IRQ could overwrite our assignments.
+	 */
+	barrier();
+
+	node->locked = 0;
+	node->next = NULL;
+
+	/*
+	 * We touched a (possibly) cold cacheline in the per-cpu queue node;
+	 * attempt the trylock once more in the hope someone let go while we
+	 * weren't watching.
+	 */
+	if (arena_spin_trylock(lock))
+		goto release;
+
+	/*
+	 * Ensure that the initialisation of @node is complete before we
+	 * publish the updated tail via xchg_tail() and potentially link
+	 * @node into the waitqueue via WRITE_ONCE(prev->next, node) below.
+	 */
+	smp_wmb();
+
+	/*
+	 * Publish the updated tail.
+	 * We have already touched the queueing cacheline; don't bother with
+	 * pending stuff.
+	 *
+	 * p,*,* -> n,*,*
+	 */
+	old = xchg_tail(lock, tail);
+	next = NULL;
+
+	/*
+	 * if there was a previous node; link it and wait until reaching the
+	 * head of the waitqueue.
+	 */
+	if (old & _Q_TAIL_MASK) {
+		prev = decode_tail(old);
+
+		/* Link @node into the waitqueue. */
+		WRITE_ONCE(prev->next, node);
+
+		arch_mcs_spin_lock_contended_label(&node->locked, release_node_err);
+
+		/*
+		 * While waiting for the MCS lock, the next pointer may have
+		 * been set by another lock waiter. We cannot prefetch here
+		 * due to lack of equivalent instruction in BPF ISA.
+		 */
+		next = READ_ONCE(node->next);
+	}
+
+	/*
+	 * we're at the head of the waitqueue, wait for the owner & pending to
+	 * go away.
+	 *
+	 * *,x,y -> *,0,0
+	 *
+	 * this wait loop must use a load-acquire such that we match the
+	 * store-release that clears the locked bit and create lock
+	 * sequentiality; this is because the set_locked() function below
+	 * does not imply a full barrier.
+	 */
+	val = atomic_cond_read_acquire_label(&lock->val, !(VAL & _Q_LOCKED_PENDING_MASK),
+					     release_node_err);
+
+	/*
+	 * claim the lock:
+	 *
+	 * n,0,0 -> 0,0,1 : lock, uncontended
+	 * *,*,0 -> *,*,1 : lock, contended
+	 *
+	 * If the queue head is the only one in the queue (lock value == tail)
+	 * and nobody is pending, clear the tail code and grab the lock.
+	 * Otherwise, we only need to grab the lock.
+	 */
+
+	/*
+	 * In the PV case we might already have _Q_LOCKED_VAL set, because
+	 * of lock stealing; therefore we must also allow:
+	 *
+	 * n,0,1 -> 0,0,1
+	 *
+	 * Note: at this point: (val & _Q_PENDING_MASK) == 0, because of the
+	 *       above wait condition, therefore any concurrent setting of
+	 *       PENDING will make the uncontended transition fail.
+	 */
+	if ((val & _Q_TAIL_MASK) == tail) {
+		if (atomic_try_cmpxchg_relaxed(&lock->val, &val, _Q_LOCKED_VAL))
+			goto release; /* No contention */
+	}
+
+	/*
+	 * Either somebody is queued behind us or _Q_PENDING_VAL got set
+	 * which will then detect the remaining tail and queue behind us
+	 * ensuring we'll see a @next.
+	 */
+	set_locked(lock);
+
+	/*
+	 * contended path; wait for next if not observed yet, release.
+	 */
+	if (!next)
+		next = smp_cond_load_relaxed_label(&node->next, (VAL), release_node_err);
+
+	arch_mcs_spin_unlock_contended(&next->locked);
+
+release:;
+	/*
+	 * release the node
+	 *
+	 * Doing a normal dec vs this_cpu_dec is fine. An upper context always
+	 * decrements count it incremented before returning, thus we're fine.
+	 * For contexts interrupting us, they either observe our dec or not.
+	 * Just ensure the compiler doesn't reorder this statement, as a
+	 * this_cpu_dec implicitly implied that.
+	 */
+	barrier();
+	node0->count--;
+	return 0;
+release_node_err:
+	barrier();
+	node0->count--;
+	goto release_err;
+release_err:
+	return ret;
+}
+
+/**
+ * arena_spin_lock - acquire a queued spinlock
+ * @lock: Pointer to queued spinlock structure
+ *
+ * On error, returned value will be negative.
+ * On success, zero is returned.
+ *
+ * The return value _must_ be tested against zero for success,
+ * instead of checking it against negative, for passing the
+ * BPF verifier.
+ *
+ * The user should do:
+ *	if (arena_spin_lock(...) != 0) // failure
+ *		or
+ *	if (arena_spin_lock(...) == 0) // success
+ *		or
+ *	if (arena_spin_lock(...)) // failure
+ *		or
+ *	if (!arena_spin_lock(...)) // success
+ * instead of:
+ *	if (arena_spin_lock(...) < 0) // failure
+ *
+ * The return value can still be inspected later.
+ */
+static __always_inline int arena_spin_lock(arena_spinlock_t __arena *lock)
+{
+	int val = 0;
+
+	if (CONFIG_NR_CPUS > 1024)
+		return -EOPNOTSUPP;
+
+	bpf_preempt_disable();
+	if (likely(atomic_try_cmpxchg_acquire(&lock->val, &val, _Q_LOCKED_VAL)))
+		return 0;
+
+	val = arena_spin_lock_slowpath(lock, val);
+	/* FIXME: bpf_assert_range(-MAX_ERRNO, 0) once we have it working for all cases. */
+	if (val)
+		bpf_preempt_enable();
+	return val;
+}
+
+/**
+ * arena_spin_unlock - release a queued spinlock
+ * @lock : Pointer to queued spinlock structure
+ */
+static __always_inline void arena_spin_unlock(arena_spinlock_t __arena *lock)
+{
+	/*
+	 * unlock() needs release semantics:
+	 */
+	smp_store_release(&lock->locked, 0);
+	bpf_preempt_enable();
+}
+
+#define arena_spin_lock_irqsave(lock, flags)             \
+	({                                               \
+		int __ret;                               \
+		bpf_local_irq_save(&(flags));            \
+		__ret = arena_spin_lock((lock));         \
+		if (__ret)                               \
+			bpf_local_irq_restore(&(flags)); \
+		(__ret);                                 \
+	})
+
+#define arena_spin_unlock_irqrestore(lock, flags) \
+	({                                        \
+		arena_spin_unlock((lock));        \
+		bpf_local_irq_restore(&(flags));  \
+	})
+
+#endif
+
+#endif /* BPF_ARENA_SPIN_LOCK_H */

tools/testing/selftests/bpf/bpf_atomic.h

@@ -0,0 +1,140 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#ifndef BPF_ATOMIC_H
+#define BPF_ATOMIC_H
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_experimental.h"
+
+extern bool CONFIG_X86_64 __kconfig __weak;
+
+/*
+ * __unqual_typeof(x) - Declare an unqualified scalar type, leaving
+ *			non-scalar types unchanged,
+ *
+ * Prefer C11 _Generic for better compile-times and simpler code. Note: 'char'
+ * is not type-compatible with 'signed char', and we define a separate case.
+ *
+ * This is copied verbatim from kernel's include/linux/compiler_types.h, but
+ * with default expression (for pointers) changed from (x) to (typeof(x)0).
+ *
+ * This is because LLVM has a bug where for lvalue (x), it does not get rid of
+ * an extra address_space qualifier, but does in case of rvalue (typeof(x)0).
+ * Hence, for pointers, we need to create an rvalue expression to get the
+ * desired type. See https://github.com/llvm/llvm-project/issues/53400.
+ */
+#define __scalar_type_to_expr_cases(type) \
+	unsigned type : (unsigned type)0, signed type : (signed type)0
+
+#define __unqual_typeof(x)                              \
+	typeof(_Generic((x),                            \
+		char: (char)0,                          \
+		__scalar_type_to_expr_cases(char),      \
+		__scalar_type_to_expr_cases(short),     \
+		__scalar_type_to_expr_cases(int),       \
+		__scalar_type_to_expr_cases(long),      \
+		__scalar_type_to_expr_cases(long long), \
+		default: (typeof(x))0))
+
+/* No-op for BPF */
+#define cpu_relax() ({})
+
+#define READ_ONCE(x) (*(volatile typeof(x) *)&(x))
+
+#define WRITE_ONCE(x, val) ((*(volatile typeof(x) *)&(x)) = (val))
+
+#define cmpxchg(p, old, new) __sync_val_compare_and_swap((p), old, new)
+
+#define try_cmpxchg(p, pold, new)                                 \
+	({                                                        \
+		__unqual_typeof(*(pold)) __o = *(pold);           \
+		__unqual_typeof(*(p)) __r = cmpxchg(p, __o, new); \
+		if (__r != __o)                                   \
+			*(pold) = __r;                            \
+		__r == __o;                                       \
+	})
+
+#define try_cmpxchg_relaxed(p, pold, new) try_cmpxchg(p, pold, new)
+
+#define try_cmpxchg_acquire(p, pold, new) try_cmpxchg(p, pold, new)
+
+#define smp_mb()                                 \
+	({                                       \
+		unsigned long __val;             \
+		__sync_fetch_and_add(&__val, 0); \
+	})
+
+#define smp_rmb()                   \
+	({                          \
+		if (!CONFIG_X86_64) \
+			smp_mb();   \
+		else                \
+			barrier();  \
+	})
+
+#define smp_wmb()                   \
+	({                          \
+		if (!CONFIG_X86_64) \
+			smp_mb();   \
+		else                \
+			barrier();  \
+	})
+
+/* Control dependency provides LOAD->STORE, provide LOAD->LOAD */
+#define smp_acquire__after_ctrl_dep() ({ smp_rmb(); })
+
+#define smp_load_acquire(p)                                  \
+	({                                                   \
+		__unqual_typeof(*(p)) __v = READ_ONCE(*(p)); \
+		if (!CONFIG_X86_64)                          \
+			smp_mb();                            \
+		barrier();                                   \
+		__v;                                         \
+	})
+
+#define smp_store_release(p, val)      \
+	({                             \
+		if (!CONFIG_X86_64)    \
+			smp_mb();      \
+		barrier();             \
+		WRITE_ONCE(*(p), val); \
+	})
+
+#define smp_cond_load_relaxed_label(p, cond_expr, label)                \
+	({                                                              \
+		typeof(p) __ptr = (p);                                  \
+		__unqual_typeof(*(p)) VAL;                              \
+		for (;;) {                                              \
+			VAL = (__unqual_typeof(*(p)))READ_ONCE(*__ptr); \
+			if (cond_expr)                                  \
+				break;                                  \
+			cond_break_label(label);                        \
+			cpu_relax();                                    \
+		}                                                       \
+		(typeof(*(p)))VAL;                                      \
+	})
+
+#define smp_cond_load_acquire_label(p, cond_expr, label)                  \
+	({                                                                \
+		__unqual_typeof(*p) __val =                               \
+			smp_cond_load_relaxed_label(p, cond_expr, label); \
+		smp_acquire__after_ctrl_dep();                            \
+		(typeof(*(p)))__val;                                      \
+	})
+
+#define atomic_read(p) READ_ONCE((p)->counter)
+
+#define atomic_cond_read_relaxed_label(p, cond_expr, label) \
+	smp_cond_load_relaxed_label(&(p)->counter, cond_expr, label)
+
+#define atomic_cond_read_acquire_label(p, cond_expr, label) \
+	smp_cond_load_acquire_label(&(p)->counter, cond_expr, label)
+
+#define atomic_try_cmpxchg_relaxed(p, pold, new) \
+	try_cmpxchg_relaxed(&(p)->counter, pold, new)
+
+#define atomic_try_cmpxchg_acquire(p, pold, new) \
+	try_cmpxchg_acquire(&(p)->counter, pold, new)
+
+#endif /* BPF_ATOMIC_H */

tools/testing/selftests/bpf/bpf_experimental.h

@@ -368,12 +368,12 @@ l_true:												\
 	ret;						\
 	})
 
-#define cond_break					\
+#define __cond_break(expr)				\
 	({ __label__ l_break, l_continue;		\
 	asm volatile goto("may_goto %l[l_break]"	\
 		      :::: l_break);			\
 	goto l_continue;				\
-	l_break: break;					\
+	l_break: expr;					\
 	l_continue:;					\
 	})
 #else
@@ -392,7 +392,7 @@ l_true:												\
 	ret;						\
 	})
 
-#define cond_break					\
+#define __cond_break(expr)				\
 	({ __label__ l_break, l_continue;		\
 	asm volatile goto("1:.byte 0xe5;		\
 		      .byte 0;				\
@@ -400,7 +400,7 @@ l_true:												\
 		      .short 0"				\
 		      :::: l_break);			\
 	goto l_continue;				\
-	l_break: break;					\
+	l_break: expr;					\
 	l_continue:;					\
 	})
 #else
@@ -418,7 +418,7 @@ l_true:												\
 	ret;						\
 	})
 
-#define cond_break					\
+#define __cond_break(expr)				\
 	({ __label__ l_break, l_continue;		\
 	asm volatile goto("1:.byte 0xe5;		\
 		      .byte 0;				\
@@ -426,12 +426,15 @@ l_true:												\
 		      .short 0"				\
 		      :::: l_break);			\
 	goto l_continue;				\
-	l_break: break;					\
+	l_break: expr;					\
 	l_continue:;					\
 	})
 #endif
 #endif
 
+#define cond_break __cond_break(break)
+#define cond_break_label(label) __cond_break(goto label)
+
 #ifndef bpf_nop_mov
 #define bpf_nop_mov(var) \
 	asm volatile("%[reg]=%[reg]"::[reg]"r"((short)var))

tools/testing/selftests/bpf/bpf_kfuncs.h

@@ -87,4 +87,9 @@ struct dentry;
  */
 extern int bpf_get_dentry_xattr(struct dentry *dentry, const char *name,
 			      struct bpf_dynptr *value_ptr) __ksym __weak;
+
+extern int bpf_set_dentry_xattr(struct dentry *dentry, const char *name__str,
+				const struct bpf_dynptr *value_p, int flags) __ksym __weak;
+extern int bpf_remove_dentry_xattr(struct dentry *dentry, const char *name__str) __ksym __weak;
+
 #endif

tools/testing/selftests/bpf/cap_helpers.c

@@ -19,7 +19,7 @@ int cap_enable_effective(__u64 caps, __u64 *old_caps)
 
 	err = capget(&hdr, data);
 	if (err)
-		return err;
+		return -errno;
 
 	if (old_caps)
 		*old_caps = (__u64)(data[1].effective) << 32 | data[0].effective;
@@ -32,7 +32,7 @@ int cap_enable_effective(__u64 caps, __u64 *old_caps)
 	data[1].effective |= cap1;
 	err = capset(&hdr, data);
 	if (err)
-		return err;
+		return -errno;
 
 	return 0;
 }
@@ -49,7 +49,7 @@ int cap_disable_effective(__u64 caps, __u64 *old_caps)
 
 	err = capget(&hdr, data);
 	if (err)
-		return err;
+		return -errno;
 
 	if (old_caps)
 		*old_caps = (__u64)(data[1].effective) << 32 | data[0].effective;
@@ -61,7 +61,7 @@ int cap_disable_effective(__u64 caps, __u64 *old_caps)
 	data[1].effective &= ~cap1;
 	err = capset(&hdr, data);
 	if (err)
-		return err;
+		return -errno;
 
 	return 0;
 }

tools/testing/selftests/bpf/cap_helpers.h

@@ -4,6 +4,7 @@
 
 #include <linux/types.h>
 #include <linux/capability.h>
+#include <errno.h>
 
 #ifndef CAP_PERFMON
 #define CAP_PERFMON		38

tools/testing/selftests/bpf/network_helpers.c

@@ -446,6 +446,23 @@ char *ping_command(int family)
 	return "ping";
 }
 
+int append_tid(char *str, size_t sz)
+{
+	size_t end;
+
+	if (!str)
+		return -1;
+
+	end = strlen(str);
+	if (end + 8 > sz)
+		return -1;
+
+	sprintf(&str[end], "%07d", gettid());
+	str[end + 7] = '\0';
+
+	return 0;
+}
+
 int remove_netns(const char *name)
 {
 	char *cmd;
@@ -761,6 +778,36 @@ struct tmonitor_ctx {
 	int pcap_fd;
 };
 
+static int __base_pr(const char *format, va_list args)
+{
+	return vfprintf(stdout, format, args);
+}
+
+static tm_print_fn_t __tm_pr = __base_pr;
+
+tm_print_fn_t traffic_monitor_set_print(tm_print_fn_t fn)
+{
+	tm_print_fn_t old_print_fn;
+
+	old_print_fn = __atomic_exchange_n(&__tm_pr, fn, __ATOMIC_RELAXED);
+
+	return old_print_fn;
+}
+
+void tm_print(const char *format, ...)
+{
+	tm_print_fn_t print_fn;
+	va_list args;
+
+	print_fn = __atomic_load_n(&__tm_pr, __ATOMIC_RELAXED);
+	if (!print_fn)
+		return;
+
+	va_start(args, format);
+	print_fn(format, args);
+	va_end(args);
+}
+
 /* Is this packet captured with a Ethernet protocol type? */
 static bool is_ethernet(const u_char *packet)
 {
@@ -778,7 +825,7 @@ static bool is_ethernet(const u_char *packet)
 	case 770: /* ARPHRD_FRAD */
 	case 778: /* ARPHDR_IPGRE */
 	case 803: /* ARPHRD_IEEE80211_RADIOTAP */
-		printf("Packet captured: arphdr_type=%d\n", arphdr_type);
+		tm_print("Packet captured: arphdr_type=%d\n", arphdr_type);
 		return false;
 	}
 	return true;
@@ -799,12 +846,13 @@ static const char *pkt_type_str(u16 pkt_type)
 	return "Unknown";
 }
 
+#define MAX_FLAGS_STRLEN 21
 /* Show the information of the transport layer in the packet */
 static void show_transport(const u_char *packet, u16 len, u32 ifindex,
 			   const char *src_addr, const char *dst_addr,
 			   u16 proto, bool ipv6, u8 pkt_type)
 {
-	char *ifname, _ifname[IF_NAMESIZE];
+	char *ifname, _ifname[IF_NAMESIZE], flags[MAX_FLAGS_STRLEN] = "";
 	const char *transport_str;
 	u16 src_port, dst_port;
 	struct udphdr *udp;
@@ -827,47 +875,39 @@ static void show_transport(const u_char *packet, u16 len, u32 ifindex,
 		dst_port = ntohs(tcp->dest);
 		transport_str = "TCP";
 	} else if (proto == IPPROTO_ICMP) {
-		printf("%-7s %-3s IPv4 %s > %s: ICMP, length %d, type %d, code %d\n",
-		       ifname, pkt_type_str(pkt_type), src_addr, dst_addr, len,
-		       packet[0], packet[1]);
+		tm_print("%-7s %-3s IPv4 %s > %s: ICMP, length %d, type %d, code %d\n",
+			 ifname, pkt_type_str(pkt_type), src_addr, dst_addr, len,
+			 packet[0], packet[1]);
 		return;
 	} else if (proto == IPPROTO_ICMPV6) {
-		printf("%-7s %-3s IPv6 %s > %s: ICMPv6, length %d, type %d, code %d\n",
-		       ifname, pkt_type_str(pkt_type), src_addr, dst_addr, len,
-		       packet[0], packet[1]);
+		tm_print("%-7s %-3s IPv6 %s > %s: ICMPv6, length %d, type %d, code %d\n",
+			 ifname, pkt_type_str(pkt_type), src_addr, dst_addr, len,
+			 packet[0], packet[1]);
 		return;
 	} else {
-		printf("%-7s %-3s %s %s > %s: protocol %d\n",
-		       ifname, pkt_type_str(pkt_type), ipv6 ? "IPv6" : "IPv4",
-		       src_addr, dst_addr, proto);
+		tm_print("%-7s %-3s %s %s > %s: protocol %d\n",
+			 ifname, pkt_type_str(pkt_type), ipv6 ? "IPv6" : "IPv4",
+			 src_addr, dst_addr, proto);
 		return;
 	}
 
 	/* TCP or UDP*/
 
-	flockfile(stdout);
+	if (proto == IPPROTO_TCP)
+		snprintf(flags, MAX_FLAGS_STRLEN, "%s%s%s%s",
+			 tcp->fin ? ", FIN" : "",
+			 tcp->syn ? ", SYN" : "",
+			 tcp->rst ? ", RST" : "",
+			 tcp->ack ? ", ACK" : "");
+
 	if (ipv6)
-		printf("%-7s %-3s IPv6 %s.%d > %s.%d: %s, length %d",
-		       ifname, pkt_type_str(pkt_type), src_addr, src_port,
-		       dst_addr, dst_port, transport_str, len);
+		tm_print("%-7s %-3s IPv6 %s.%d > %s.%d: %s, length %d%s\n",
+			 ifname, pkt_type_str(pkt_type), src_addr, src_port,
+			 dst_addr, dst_port, transport_str, len, flags);
 	else
-		printf("%-7s %-3s IPv4 %s:%d > %s:%d: %s, length %d",
-		       ifname, pkt_type_str(pkt_type), src_addr, src_port,
-		       dst_addr, dst_port, transport_str, len);
-
-	if (proto == IPPROTO_TCP) {
-		if (tcp->fin)
-			printf(", FIN");
-		if (tcp->syn)
-			printf(", SYN");
-		if (tcp->rst)
-			printf(", RST");
-		if (tcp->ack)
-			printf(", ACK");
-	}
-
-	printf("\n");
-	funlockfile(stdout);
+		tm_print("%-7s %-3s IPv4 %s:%d > %s:%d: %s, length %d%s\n",
+			 ifname, pkt_type_str(pkt_type), src_addr, src_port,
+			 dst_addr, dst_port, transport_str, len, flags);
 }
 
 static void show_ipv6_packet(const u_char *packet, u32 ifindex, u8 pkt_type)
@@ -982,8 +1022,8 @@ static void *traffic_monitor_thread(void *arg)
 				ifname = _ifname;
 			}
 
-			printf("%-7s %-3s Unknown network protocol type 0x%x\n",
-			       ifname, pkt_type_str(ptype), proto);
+			tm_print("%-7s %-3s Unknown network protocol type 0x%x\n",
+				 ifname, pkt_type_str(ptype), proto);
 		}
 	}
 
@@ -1183,8 +1223,9 @@ void traffic_monitor_stop(struct tmonitor_ctx *ctx)
 	write(ctx->wake_fd, &w, sizeof(w));
 	pthread_join(ctx->thread, NULL);
 
-	printf("Packet file: %s\n", strrchr(ctx->pkt_fname, '/') + 1);
+	tm_print("Packet file: %s\n", strrchr(ctx->pkt_fname, '/') + 1);
 
 	traffic_monitor_release(ctx);
 }
+
 #endif /* TRAFFIC_MONITOR */

tools/testing/selftests/bpf/network_helpers.h

@@ -18,6 +18,7 @@ typedef __u16 __sum16;
 #include <netinet/udp.h>
 #include <bpf/bpf_endian.h>
 #include <net/if.h>
+#include <stdio.h>
 
 #define MAGIC_VAL 0x1234
 #define NUM_ITER 100000
@@ -101,6 +102,18 @@ int send_recv_data(int lfd, int fd, uint32_t total_bytes);
 int make_netns(const char *name);
 int remove_netns(const char *name);
 
+/**
+ * append_tid() - Append thread ID to the given string.
+ *
+ * @str: string to extend
+ * @sz: string's size
+ *
+ * 8 characters are used to append the thread ID (7 digits + '\0')
+ *
+ * Returns -1 on errors, 0 otherwise
+ */
+int append_tid(char *str, size_t sz);
+
 static __u16 csum_fold(__u32 csum)
 {
 	csum = (csum & 0xffff) + (csum >> 16);
@@ -240,10 +253,13 @@ static inline __sum16 build_udp_v6_csum(const struct ipv6hdr *ip6h,
 
 struct tmonitor_ctx;
 
+typedef int (*tm_print_fn_t)(const char *format, va_list args);
+
 #ifdef TRAFFIC_MONITOR
 struct tmonitor_ctx *traffic_monitor_start(const char *netns, const char *test_name,
 					   const char *subtest_name);
 void traffic_monitor_stop(struct tmonitor_ctx *ctx);
+tm_print_fn_t traffic_monitor_set_print(tm_print_fn_t fn);
 #else
 static inline struct tmonitor_ctx *traffic_monitor_start(const char *netns, const char *test_name,
 							 const char *subtest_name)
@@ -254,6 +270,11 @@ static inline struct tmonitor_ctx *traffic_monitor_start(const char *netns, cons
 static inline void traffic_monitor_stop(struct tmonitor_ctx *ctx)
 {
 }
+
+static inline tm_print_fn_t traffic_monitor_set_print(tm_print_fn_t fn)
+{
+	return NULL;
+}
 #endif
 
 #endif

tools/testing/selftests/bpf/prog_tests/align.c

@@ -610,9 +610,11 @@ static int do_test_single(struct bpf_align_test *test)
 		.log_size = sizeof(bpf_vlog),
 		.log_level = 2,
 	);
+	const char *main_pass_start = "0: R1=ctx() R10=fp0";
 	const char *line_ptr;
 	int cur_line = -1;
 	int prog_len, i;
+	char *start;
 	int fd_prog;
 	int ret;
 
@@ -632,7 +634,13 @@ static int do_test_single(struct bpf_align_test *test)
 		ret = 0;
 		/* We make a local copy so that we can strtok() it */
 		strncpy(bpf_vlog_copy, bpf_vlog, sizeof(bpf_vlog_copy));
-		line_ptr = strtok(bpf_vlog_copy, "\n");
+		start = strstr(bpf_vlog_copy, main_pass_start);
+		if (!start) {
+			ret = 1;
+			printf("Can't find initial line '%s'\n", main_pass_start);
+			goto out;
+		}
+		line_ptr = strtok(start, "\n");
 		for (i = 0; i < MAX_MATCHES; i++) {
 			struct bpf_reg_match m = test->matches[i];
 			const char *p;
@@ -682,6 +690,7 @@ static int do_test_single(struct bpf_align_test *test)
 				break;
 			}
 		}
+out:
 		if (fd_prog >= 0)
 			close(fd_prog);
 	}

tools/testing/selftests/bpf/prog_tests/arena_atomics.c

@@ -162,6 +162,66 @@ static void test_uaf(struct arena_atomics *skel)
 	ASSERT_EQ(skel->arena->uaf_recovery_fails, 0, "uaf_recovery_fails");
 }
 
+static void test_load_acquire(struct arena_atomics *skel)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+	int err, prog_fd;
+
+	if (skel->data->skip_lacq_srel_tests) {
+		printf("%s:SKIP: ENABLE_ATOMICS_TESTS not defined, Clang doesn't support addr_space_cast, and/or JIT doesn't support load-acquire\n",
+		       __func__);
+		test__skip();
+		return;
+	}
+
+	/* No need to attach it, just run it directly */
+	prog_fd = bpf_program__fd(skel->progs.load_acquire);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	if (!ASSERT_OK(err, "test_run_opts err"))
+		return;
+	if (!ASSERT_OK(topts.retval, "test_run_opts retval"))
+		return;
+
+	ASSERT_EQ(skel->arena->load_acquire8_result, 0x12,
+		  "load_acquire8_result");
+	ASSERT_EQ(skel->arena->load_acquire16_result, 0x1234,
+		  "load_acquire16_result");
+	ASSERT_EQ(skel->arena->load_acquire32_result, 0x12345678,
+		  "load_acquire32_result");
+	ASSERT_EQ(skel->arena->load_acquire64_result, 0x1234567890abcdef,
+		  "load_acquire64_result");
+}
+
+static void test_store_release(struct arena_atomics *skel)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+	int err, prog_fd;
+
+	if (skel->data->skip_lacq_srel_tests) {
+		printf("%s:SKIP: ENABLE_ATOMICS_TESTS not defined, Clang doesn't support addr_space_cast, and/or JIT doesn't support store-release\n",
+		       __func__);
+		test__skip();
+		return;
+	}
+
+	/* No need to attach it, just run it directly */
+	prog_fd = bpf_program__fd(skel->progs.store_release);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	if (!ASSERT_OK(err, "test_run_opts err"))
+		return;
+	if (!ASSERT_OK(topts.retval, "test_run_opts retval"))
+		return;
+
+	ASSERT_EQ(skel->arena->store_release8_result, 0x12,
+		  "store_release8_result");
+	ASSERT_EQ(skel->arena->store_release16_result, 0x1234,
+		  "store_release16_result");
+	ASSERT_EQ(skel->arena->store_release32_result, 0x12345678,
+		  "store_release32_result");
+	ASSERT_EQ(skel->arena->store_release64_result, 0x1234567890abcdef,
+		  "store_release64_result");
+}
+
 void test_arena_atomics(void)
 {
 	struct arena_atomics *skel;
@@ -171,7 +231,7 @@ void test_arena_atomics(void)
 	if (!ASSERT_OK_PTR(skel, "arena atomics skeleton open"))
 		return;
 
-	if (skel->data->skip_tests) {
+	if (skel->data->skip_all_tests) {
 		printf("%s:SKIP:no ENABLE_ATOMICS_TESTS or no addr_space_cast support in clang",
 		       __func__);
 		test__skip();
@@ -198,6 +258,10 @@ void test_arena_atomics(void)
 		test_xchg(skel);
 	if (test__start_subtest("uaf"))
 		test_uaf(skel);
+	if (test__start_subtest("load_acquire"))
+		test_load_acquire(skel);
+	if (test__start_subtest("store_release"))
+		test_store_release(skel);
 
 cleanup:
 	arena_atomics__destroy(skel);

tools/testing/selftests/bpf/prog_tests/arena_spin_lock.c

@@ -0,0 +1,108 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include <network_helpers.h>
+#include <sys/sysinfo.h>
+
+struct __qspinlock { int val; };
+typedef struct __qspinlock arena_spinlock_t;
+
+struct arena_qnode {
+	unsigned long next;
+	int count;
+	int locked;
+};
+
+#include "arena_spin_lock.skel.h"
+
+static long cpu;
+static int repeat;
+
+pthread_barrier_t barrier;
+
+static void *spin_lock_thread(void *arg)
+{
+	int err, prog_fd = *(u32 *)arg;
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		.data_in = &pkt_v4,
+		.data_size_in = sizeof(pkt_v4),
+		.repeat = repeat,
+	);
+	cpu_set_t cpuset;
+
+	CPU_ZERO(&cpuset);
+	CPU_SET(__sync_fetch_and_add(&cpu, 1), &cpuset);
+	ASSERT_OK(pthread_setaffinity_np(pthread_self(), sizeof(cpuset), &cpuset), "cpu affinity");
+
+	err = pthread_barrier_wait(&barrier);
+	if (err != PTHREAD_BARRIER_SERIAL_THREAD && err != 0)
+		ASSERT_FALSE(true, "pthread_barrier");
+
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	ASSERT_OK(err, "test_run err");
+	ASSERT_EQ((int)topts.retval, 0, "test_run retval");
+
+	pthread_exit(arg);
+}
+
+static void test_arena_spin_lock_size(int size)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+	struct arena_spin_lock *skel;
+	pthread_t thread_id[16];
+	int prog_fd, i, err;
+	void *ret;
+
+	if (get_nprocs() < 2) {
+		test__skip();
+		return;
+	}
+
+	skel = arena_spin_lock__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "arena_spin_lock__open_and_load"))
+		return;
+	if (skel->data->test_skip == 2) {
+		test__skip();
+		goto end;
+	}
+	skel->bss->cs_count = size;
+	skel->bss->limit = repeat * 16;
+
+	ASSERT_OK(pthread_barrier_init(&barrier, NULL, 16), "barrier init");
+
+	prog_fd = bpf_program__fd(skel->progs.prog);
+	for (i = 0; i < 16; i++) {
+		err = pthread_create(&thread_id[i], NULL, &spin_lock_thread, &prog_fd);
+		if (!ASSERT_OK(err, "pthread_create"))
+			goto end_barrier;
+	}
+
+	for (i = 0; i < 16; i++) {
+		if (!ASSERT_OK(pthread_join(thread_id[i], &ret), "pthread_join"))
+			goto end_barrier;
+		if (!ASSERT_EQ(ret, &prog_fd, "ret == prog_fd"))
+			goto end_barrier;
+	}
+
+	ASSERT_EQ(skel->bss->counter, repeat * 16, "check counter value");
+
+end_barrier:
+	pthread_barrier_destroy(&barrier);
+end:
+	arena_spin_lock__destroy(skel);
+	return;
+}
+
+void test_arena_spin_lock(void)
+{
+	repeat = 1000;
+	if (test__start_subtest("arena_spin_lock_1"))
+		test_arena_spin_lock_size(1);
+	cpu = 0;
+	if (test__start_subtest("arena_spin_lock_1000"))
+		test_arena_spin_lock_size(1000);
+	cpu = 0;
+	repeat = 100;
+	if (test__start_subtest("arena_spin_lock_50000"))
+		test_arena_spin_lock_size(50000);
+}

tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c

@@ -6,6 +6,10 @@
 #include <test_progs.h>
 #include "bloom_filter_map.skel.h"
 
+#ifndef NUMA_NO_NODE
+#define NUMA_NO_NODE	(-1)
+#endif
+
 static void test_fail_cases(void)
 {
 	LIBBPF_OPTS(bpf_map_create_opts, opts);
@@ -69,6 +73,7 @@ static void test_success_cases(void)
 
 	/* Create a map */
 	opts.map_flags = BPF_F_ZERO_SEED | BPF_F_NUMA_NODE;
+	opts.numa_node = NUMA_NO_NODE;
 	fd = bpf_map_create(BPF_MAP_TYPE_BLOOM_FILTER, NULL, 0, sizeof(value), 100, &opts);
 	if (!ASSERT_GE(fd, 0, "bpf_map_create bloom filter success case"))
 		return;

tools/testing/selftests/bpf/prog_tests/bpf_iter.c

@@ -323,19 +323,87 @@ static void test_task_pidfd(void)
 static void test_task_sleepable(void)
 {
 	struct bpf_iter_tasks *skel;
+	int pid, status, err, data_pipe[2], finish_pipe[2], c;
+	char *test_data = NULL;
+	char *test_data_long = NULL;
+	char *data[2];
+
+	if (!ASSERT_OK(pipe(data_pipe), "data_pipe") ||
+	    !ASSERT_OK(pipe(finish_pipe), "finish_pipe"))
+		return;
 
 	skel = bpf_iter_tasks__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "bpf_iter_tasks__open_and_load"))
 		return;
 
+	pid = fork();
+	if (!ASSERT_GE(pid, 0, "fork"))
+		return;
+
+	if (pid == 0) {
+		/* child */
+		close(data_pipe[0]);
+		close(finish_pipe[1]);
+
+		test_data = malloc(sizeof(char) * 10);
+		strncpy(test_data, "test_data", 10);
+		test_data[9] = '\0';
+
+		test_data_long = malloc(sizeof(char) * 5000);
+		for (int i = 0; i < 5000; ++i) {
+			if (i % 2 == 0)
+				test_data_long[i] = 'b';
+			else
+				test_data_long[i] = 'a';
+		}
+		test_data_long[4999] = '\0';
+
+		data[0] = test_data;
+		data[1] = test_data_long;
+
+		write(data_pipe[1], &data, sizeof(data));
+
+		/* keep child alive until after the test */
+		err = read(finish_pipe[0], &c, 1);
+		if (err != 1)
+			exit(-1);
+
+		close(data_pipe[1]);
+		close(finish_pipe[0]);
+		_exit(0);
+	}
+
+	/* parent */
+	close(data_pipe[1]);
+	close(finish_pipe[0]);
+
+	err = read(data_pipe[0], &data, sizeof(data));
+	ASSERT_EQ(err, sizeof(data), "read_check");
+
+	skel->bss->user_ptr = data[0];
+	skel->bss->user_ptr_long = data[1];
+	skel->bss->pid = pid;
+
 	do_dummy_read(skel->progs.dump_task_sleepable);
 
 	ASSERT_GT(skel->bss->num_expected_failure_copy_from_user_task, 0,
 		  "num_expected_failure_copy_from_user_task");
 	ASSERT_GT(skel->bss->num_success_copy_from_user_task, 0,
 		  "num_success_copy_from_user_task");
+	ASSERT_GT(skel->bss->num_expected_failure_copy_from_user_task_str, 0,
+		  "num_expected_failure_copy_from_user_task_str");
+	ASSERT_GT(skel->bss->num_success_copy_from_user_task_str, 0,
+		  "num_success_copy_from_user_task_str");
 
 	bpf_iter_tasks__destroy(skel);
+
+	write(finish_pipe[1], &c, 1);
+	err = waitpid(pid, &status, 0);
+	ASSERT_EQ(err, pid, "waitpid");
+	ASSERT_EQ(status, 0, "zero_child_exit");
+
+	close(data_pipe[0]);
+	close(finish_pipe[1]);
 }
 
 static void test_task_stack(void)

tools/testing/selftests/bpf/prog_tests/bpf_nf.c

@@ -72,11 +72,14 @@ static void test_bpf_nf_ct(int mode)
 	if (!ASSERT_OK(system(cmd), cmd))
 		goto end;
 
-	srv_port = (mode == TEST_XDP) ? 5005 : 5006;
-	srv_fd = start_server(AF_INET, SOCK_STREAM, "127.0.0.1", srv_port, TIMEOUT_MS);
+	srv_fd = start_server(AF_INET, SOCK_STREAM, "127.0.0.1", 0, TIMEOUT_MS);
 	if (!ASSERT_GE(srv_fd, 0, "start_server"))
 		goto end;
 
+	srv_port = get_socket_local_port(srv_fd);
+	if (!ASSERT_GE(srv_port, 0, "get_sock_local_port"))
+		goto end;
+
 	client_fd = connect_to_server(srv_fd);
 	if (!ASSERT_GE(client_fd, 0, "connect_to_server"))
 		goto end;
@@ -91,7 +94,7 @@ static void test_bpf_nf_ct(int mode)
 	skel->bss->saddr = peer_addr.sin_addr.s_addr;
 	skel->bss->sport = peer_addr.sin_port;
 	skel->bss->daddr = peer_addr.sin_addr.s_addr;
-	skel->bss->dport = htons(srv_port);
+	skel->bss->dport = srv_port;
 
 	if (mode == TEST_XDP)
 		prog_fd = bpf_program__fd(skel->progs.nf_xdp_ct_test);

tools/testing/selftests/bpf/prog_tests/btf.c

@@ -3866,11 +3866,11 @@ static struct btf_raw_test raw_tests[] = {
 	.err_str = "vlen != 0",
 },
 {
-	.descr = "decl_tag test #8, invalid kflag",
+	.descr = "decl_tag test #8, tag with kflag",
 	.raw_types = {
 		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
 		BTF_VAR_ENC(NAME_TBD, 1, 0),			/* [2] */
-		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DECL_TAG, 1, 0), 2), (-1),
+		BTF_DECL_ATTR_ENC(NAME_TBD, 2, -1),
 		BTF_END_RAW,
 	},
 	BTF_STR_SEC("\0local\0tag1"),
@@ -3881,8 +3881,6 @@ static struct btf_raw_test raw_tests[] = {
 	.key_type_id = 1,
 	.value_type_id = 1,
 	.max_entries = 1,
-	.btf_load_err = true,
-	.err_str = "Invalid btf_info kind_flag",
 },
 {
 	.descr = "decl_tag test #9, var, invalid component_idx",
@@ -4206,6 +4204,23 @@ static struct btf_raw_test raw_tests[] = {
 	.btf_load_err = true,
 	.err_str = "Type tags don't precede modifiers",
 },
+{
+	.descr = "type_tag test #7, tag with kflag",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_ATTR_ENC(NAME_TBD, 1),			/* [2] */
+		BTF_PTR_ENC(2),					/* [3] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0tag"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "tag_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = 4,
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 1,
+},
 {
 	.descr = "enum64 test #1, unsigned, size 8",
 	.raw_types = {

tools/testing/selftests/bpf/prog_tests/btf_dump.c

@@ -126,25 +126,68 @@ done:
 	return err;
 }
 
-static char *dump_buf;
-static size_t dump_buf_sz;
-static FILE *dump_buf_file;
+struct test_ctx {
+	struct btf *btf;
+	struct btf_dump *d;
+	char *dump_buf;
+	size_t dump_buf_sz;
+	FILE *dump_buf_file;
+};
+
+static void test_ctx__free(struct test_ctx *t)
+{
+	fclose(t->dump_buf_file);
+	free(t->dump_buf);
+	btf_dump__free(t->d);
+	btf__free(t->btf);
+}
+
+static int test_ctx__init(struct test_ctx *t)
+{
+	t->dump_buf_file = open_memstream(&t->dump_buf, &t->dump_buf_sz);
+	if (!ASSERT_OK_PTR(t->dump_buf_file, "dump_memstream"))
+		return -1;
+	t->btf = btf__new_empty();
+	if (!ASSERT_OK_PTR(t->btf, "new_empty"))
+		goto err_out;
+	t->d = btf_dump__new(t->btf, btf_dump_printf, t->dump_buf_file, NULL);
+	if (!ASSERT_OK(libbpf_get_error(t->d), "btf_dump__new"))
+		goto err_out;
+
+	return 0;
+
+err_out:
+	test_ctx__free(t);
+	return -1;
+}
+
+static void test_ctx__dump_and_compare(struct test_ctx *t,
+				       const char *expected_output,
+				       const char *message)
+{
+	int i, err;
+
+	for (i = 1; i < btf__type_cnt(t->btf); i++) {
+		err = btf_dump__dump_type(t->d, i);
+		ASSERT_OK(err, "dump_type_ok");
+	}
+
+	fflush(t->dump_buf_file);
+	t->dump_buf[t->dump_buf_sz] = 0; /* some libc implementations don't do this */
+
+	ASSERT_STREQ(t->dump_buf, expected_output, message);
+}
 
 static void test_btf_dump_incremental(void)
 {
-	struct btf *btf = NULL;
-	struct btf_dump *d = NULL;
-	int id, err, i;
+	struct test_ctx t = {};
+	struct btf *btf;
+	int id, err;
 
-	dump_buf_file = open_memstream(&dump_buf, &dump_buf_sz);
-	if (!ASSERT_OK_PTR(dump_buf_file, "dump_memstream"))
+	if (test_ctx__init(&t))
 		return;
-	btf = btf__new_empty();
-	if (!ASSERT_OK_PTR(btf, "new_empty"))
-		goto err_out;
-	d = btf_dump__new(btf, btf_dump_printf, dump_buf_file, NULL);
-	if (!ASSERT_OK(libbpf_get_error(d), "btf_dump__new"))
-		goto err_out;
+
+	btf = t.btf;
 
 	/* First, generate BTF corresponding to the following C code:
 	 *
@@ -182,15 +225,7 @@ static void test_btf_dump_incremental(void)
 	err = btf__add_field(btf, "x", 4, 0, 0);
 	ASSERT_OK(err, "field_ok");
 
-	for (i = 1; i < btf__type_cnt(btf); i++) {
-		err = btf_dump__dump_type(d, i);
-		ASSERT_OK(err, "dump_type_ok");
-	}
-
-	fflush(dump_buf_file);
-	dump_buf[dump_buf_sz] = 0; /* some libc implementations don't do this */
-
-	ASSERT_STREQ(dump_buf,
+	test_ctx__dump_and_compare(&t,
 "enum x;\n"
 "\n"
 "enum x {\n"
@@ -221,7 +256,7 @@ static void test_btf_dump_incremental(void)
 	 * enum values don't conflict;
 	 *
 	 */
-	fseek(dump_buf_file, 0, SEEK_SET);
+	fseek(t.dump_buf_file, 0, SEEK_SET);
 
 	id = btf__add_struct(btf, "s", 4);
 	ASSERT_EQ(id, 7, "struct_id");
@@ -232,14 +267,7 @@ static void test_btf_dump_incremental(void)
 	err = btf__add_field(btf, "s", 6, 64, 0);
 	ASSERT_OK(err, "field_ok");
 
-	for (i = 1; i < btf__type_cnt(btf); i++) {
-		err = btf_dump__dump_type(d, i);
-		ASSERT_OK(err, "dump_type_ok");
-	}
-
-	fflush(dump_buf_file);
-	dump_buf[dump_buf_sz] = 0; /* some libc implementations don't do this */
-	ASSERT_STREQ(dump_buf,
+	test_ctx__dump_and_compare(&t,
 "struct s___2 {\n"
 "	enum x x;\n"
 "	enum {\n"
@@ -248,11 +276,53 @@ static void test_btf_dump_incremental(void)
 "	struct s s;\n"
 "};\n\n" , "c_dump1");
 
-err_out:
-	fclose(dump_buf_file);
-	free(dump_buf);
-	btf_dump__free(d);
-	btf__free(btf);
+	test_ctx__free(&t);
+}
+
+static void test_btf_dump_type_tags(void)
+{
+	struct test_ctx t = {};
+	struct btf *btf;
+	int id, err;
+
+	if (test_ctx__init(&t))
+		return;
+
+	btf = t.btf;
+
+	/* Generate BTF corresponding to the following C code:
+	 *
+	 * struct s {
+	 *   void __attribute__((btf_type_tag(\"void_tag\"))) *p1;
+	 *   void __attribute__((void_attr)) *p2;
+	 * };
+	 *
+	 */
+
+	id = btf__add_type_tag(btf, "void_tag", 0);
+	ASSERT_EQ(id, 1, "type_tag_id");
+	id = btf__add_ptr(btf, id);
+	ASSERT_EQ(id, 2, "void_ptr_id1");
+
+	id = btf__add_type_attr(btf, "void_attr", 0);
+	ASSERT_EQ(id, 3, "type_attr_id");
+	id = btf__add_ptr(btf, id);
+	ASSERT_EQ(id, 4, "void_ptr_id2");
+
+	id = btf__add_struct(btf, "s", 8);
+	ASSERT_EQ(id, 5, "struct_id");
+	err = btf__add_field(btf, "p1", 2, 0, 0);
+	ASSERT_OK(err, "field_ok1");
+	err = btf__add_field(btf, "p2", 4, 0, 0);
+	ASSERT_OK(err, "field_ok2");
+
+	test_ctx__dump_and_compare(&t,
+"struct s {\n"
+"	void __attribute__((btf_type_tag(\"void_tag\"))) *p1;\n"
+"	void __attribute__((void_attr)) *p2;\n"
+"};\n\n", "dump_and_compare");
+
+	test_ctx__free(&t);
 }
 
 #define STRSIZE				4096
@@ -874,6 +944,9 @@ void test_btf_dump() {
 	if (test__start_subtest("btf_dump: incremental"))
 		test_btf_dump_incremental();
 
+	if (test__start_subtest("btf_dump: type_tags"))
+		test_btf_dump_type_tags();
+
 	btf = libbpf_find_kernel_btf();
 	if (!ASSERT_OK_PTR(btf, "no kernel BTF found"))
 		return;

tools/testing/selftests/bpf/prog_tests/cgroup_preorder.c

@@ -0,0 +1,128 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include "cgroup_helpers.h"
+#include "cgroup_preorder.skel.h"
+
+static int run_getsockopt_test(int cg_parent, int cg_child, int sock_fd, bool all_preorder)
+{
+	LIBBPF_OPTS(bpf_prog_attach_opts, opts);
+	enum bpf_attach_type prog_c_atype, prog_c2_atype, prog_p_atype, prog_p2_atype;
+	int prog_c_fd, prog_c2_fd, prog_p_fd, prog_p2_fd;
+	struct cgroup_preorder *skel = NULL;
+	struct bpf_program *prog;
+	__u8 *result, buf;
+	socklen_t optlen;
+	int err = 0;
+
+	skel = cgroup_preorder__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "cgroup_preorder__open_and_load"))
+		return 0;
+
+	buf = 0x00;
+	err = setsockopt(sock_fd, SOL_IP, IP_TOS, &buf, 1);
+	if (!ASSERT_OK(err, "setsockopt"))
+		goto close_skel;
+
+	opts.flags = BPF_F_ALLOW_MULTI;
+	if (all_preorder)
+		opts.flags |= BPF_F_PREORDER;
+	prog = skel->progs.child;
+	prog_c_fd = bpf_program__fd(prog);
+	prog_c_atype = bpf_program__expected_attach_type(prog);
+	err = bpf_prog_attach_opts(prog_c_fd, cg_child, prog_c_atype, &opts);
+	if (!ASSERT_OK(err, "bpf_prog_attach_opts-child"))
+		goto close_skel;
+
+	opts.flags = BPF_F_ALLOW_MULTI | BPF_F_PREORDER;
+	prog = skel->progs.child_2;
+	prog_c2_fd = bpf_program__fd(prog);
+	prog_c2_atype = bpf_program__expected_attach_type(prog);
+	err = bpf_prog_attach_opts(prog_c2_fd, cg_child, prog_c2_atype, &opts);
+	if (!ASSERT_OK(err, "bpf_prog_attach_opts-child_2"))
+		goto detach_child;
+
+	optlen = 1;
+	err = getsockopt(sock_fd, SOL_IP, IP_TOS, &buf, &optlen);
+	if (!ASSERT_OK(err, "getsockopt"))
+		goto detach_child_2;
+
+	result = skel->bss->result;
+	if (all_preorder)
+		ASSERT_TRUE(result[0] == 1 && result[1] == 2, "child only");
+	else
+		ASSERT_TRUE(result[0] == 2 && result[1] == 1, "child only");
+
+	skel->bss->idx = 0;
+	memset(result, 0, 4);
+
+	opts.flags = BPF_F_ALLOW_MULTI;
+	if (all_preorder)
+		opts.flags |= BPF_F_PREORDER;
+	prog = skel->progs.parent;
+	prog_p_fd = bpf_program__fd(prog);
+	prog_p_atype = bpf_program__expected_attach_type(prog);
+	err = bpf_prog_attach_opts(prog_p_fd, cg_parent, prog_p_atype, &opts);
+	if (!ASSERT_OK(err, "bpf_prog_attach_opts-parent"))
+		goto detach_child_2;
+
+	opts.flags = BPF_F_ALLOW_MULTI | BPF_F_PREORDER;
+	prog = skel->progs.parent_2;
+	prog_p2_fd = bpf_program__fd(prog);
+	prog_p2_atype = bpf_program__expected_attach_type(prog);
+	err = bpf_prog_attach_opts(prog_p2_fd, cg_parent, prog_p2_atype, &opts);
+	if (!ASSERT_OK(err, "bpf_prog_attach_opts-parent_2"))
+		goto detach_parent;
+
+	err = getsockopt(sock_fd, SOL_IP, IP_TOS, &buf, &optlen);
+	if (!ASSERT_OK(err, "getsockopt"))
+		goto detach_parent_2;
+
+	if (all_preorder)
+		ASSERT_TRUE(result[0] == 3 && result[1] == 4 && result[2] == 1 && result[3] == 2,
+			    "parent and child");
+	else
+		ASSERT_TRUE(result[0] == 4 && result[1] == 2 && result[2] == 1 && result[3] == 3,
+			    "parent and child");
+
+detach_parent_2:
+	ASSERT_OK(bpf_prog_detach2(prog_p2_fd, cg_parent, prog_p2_atype),
+		  "bpf_prog_detach2-parent_2");
+detach_parent:
+	ASSERT_OK(bpf_prog_detach2(prog_p_fd, cg_parent, prog_p_atype),
+		  "bpf_prog_detach2-parent");
+detach_child_2:
+	ASSERT_OK(bpf_prog_detach2(prog_c2_fd, cg_child, prog_c2_atype),
+		  "bpf_prog_detach2-child_2");
+detach_child:
+	ASSERT_OK(bpf_prog_detach2(prog_c_fd, cg_child, prog_c_atype),
+		  "bpf_prog_detach2-child");
+close_skel:
+	cgroup_preorder__destroy(skel);
+	return err;
+}
+
+void test_cgroup_preorder(void)
+{
+	int cg_parent = -1, cg_child = -1, sock_fd = -1;
+
+	cg_parent = test__join_cgroup("/parent");
+	if (!ASSERT_GE(cg_parent, 0, "join_cgroup /parent"))
+		goto out;
+
+	cg_child = test__join_cgroup("/parent/child");
+	if (!ASSERT_GE(cg_child, 0, "join_cgroup /parent/child"))
+		goto out;
+
+	sock_fd = socket(AF_INET, SOCK_STREAM, 0);
+	if (!ASSERT_GE(sock_fd, 0, "socket"))
+		goto out;
+
+	ASSERT_OK(run_getsockopt_test(cg_parent, cg_child, sock_fd, false), "getsockopt_test_1");
+	ASSERT_OK(run_getsockopt_test(cg_parent, cg_child, sock_fd, true), "getsockopt_test_2");
+
+out:
+	close(sock_fd);
+	close(cg_child);
+	close(cg_parent);
+}

tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c

@@ -10,12 +10,18 @@
 static int run_test(int cgroup_fd, int server_fd, bool classid)
 {
 	struct connect4_dropper *skel;
-	int fd, err = 0;
+	int fd, err = 0, port;
 
 	skel = connect4_dropper__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "skel_open"))
 		return -1;
 
+	port = get_socket_local_port(server_fd);
+	if (!ASSERT_GE(port, 0, "get_socket_local_port"))
+		return -1;
+
+	skel->bss->port = ntohs(port);
+
 	skel->links.connect_v4_dropper =
 		bpf_program__attach_cgroup(skel->progs.connect_v4_dropper,
 					   cgroup_fd);
@@ -48,10 +54,9 @@ void test_cgroup_v1v2(void)
 {
 	struct network_helper_opts opts = {};
 	int server_fd, client_fd, cgroup_fd;
-	static const int port = 60120;
 
 	/* Step 1: Check base connectivity works without any BPF. */
-	server_fd = start_server(AF_INET, SOCK_STREAM, NULL, port, 0);
+	server_fd = start_server(AF_INET, SOCK_STREAM, NULL, 0, 0);
 	if (!ASSERT_GE(server_fd, 0, "server_fd"))
 		return;
 	client_fd = connect_to_fd_opts(server_fd, &opts);
@@ -66,7 +71,7 @@ void test_cgroup_v1v2(void)
 	cgroup_fd = test__join_cgroup("/connect_dropper");
 	if (!ASSERT_GE(cgroup_fd, 0, "cgroup_fd"))
 		return;
-	server_fd = start_server(AF_INET, SOCK_STREAM, NULL, port, 0);
+	server_fd = start_server(AF_INET, SOCK_STREAM, NULL, 0, 0);
 	if (!ASSERT_GE(server_fd, 0, "server_fd")) {
 		close(cgroup_fd);
 		return;

tools/testing/selftests/bpf/prog_tests/changes_pkt_data.c

@@ -1,107 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include "bpf/libbpf.h"
-#include "changes_pkt_data_freplace.skel.h"
-#include "changes_pkt_data.skel.h"
-#include <test_progs.h>
-
-static void print_verifier_log(const char *log)
-{
-	if (env.verbosity >= VERBOSE_VERY)
-		fprintf(stdout, "VERIFIER LOG:\n=============\n%s=============\n", log);
-}
-
-static void test_aux(const char *main_prog_name,
-		     const char *to_be_replaced,
-		     const char *replacement,
-		     bool expect_load)
-{
-	struct changes_pkt_data_freplace *freplace = NULL;
-	struct bpf_program *freplace_prog = NULL;
-	struct bpf_program *main_prog = NULL;
-	LIBBPF_OPTS(bpf_object_open_opts, opts);
-	struct changes_pkt_data *main = NULL;
-	char log[16*1024];
-	int err;
-
-	opts.kernel_log_buf = log;
-	opts.kernel_log_size = sizeof(log);
-	if (env.verbosity >= VERBOSE_SUPER)
-		opts.kernel_log_level = 1 | 2 | 4;
-	main = changes_pkt_data__open_opts(&opts);
-	if (!ASSERT_OK_PTR(main, "changes_pkt_data__open"))
-		goto out;
-	main_prog = bpf_object__find_program_by_name(main->obj, main_prog_name);
-	if (!ASSERT_OK_PTR(main_prog, "main_prog"))
-		goto out;
-	bpf_program__set_autoload(main_prog, true);
-	err = changes_pkt_data__load(main);
-	print_verifier_log(log);
-	if (!ASSERT_OK(err, "changes_pkt_data__load"))
-		goto out;
-	freplace = changes_pkt_data_freplace__open_opts(&opts);
-	if (!ASSERT_OK_PTR(freplace, "changes_pkt_data_freplace__open"))
-		goto out;
-	freplace_prog = bpf_object__find_program_by_name(freplace->obj, replacement);
-	if (!ASSERT_OK_PTR(freplace_prog, "freplace_prog"))
-		goto out;
-	bpf_program__set_autoload(freplace_prog, true);
-	bpf_program__set_autoattach(freplace_prog, true);
-	bpf_program__set_attach_target(freplace_prog,
-				       bpf_program__fd(main_prog),
-				       to_be_replaced);
-	err = changes_pkt_data_freplace__load(freplace);
-	print_verifier_log(log);
-	if (expect_load) {
-		ASSERT_OK(err, "changes_pkt_data_freplace__load");
-	} else {
-		ASSERT_ERR(err, "changes_pkt_data_freplace__load");
-		ASSERT_HAS_SUBSTR(log, "Extension program changes packet data", "error log");
-	}
-
-out:
-	changes_pkt_data_freplace__destroy(freplace);
-	changes_pkt_data__destroy(main);
-}
-
-/* There are two global subprograms in both changes_pkt_data.skel.h:
- * - one changes packet data;
- * - another does not.
- * It is ok to freplace subprograms that change packet data with those
- * that either do or do not. It is only ok to freplace subprograms
- * that do not change packet data with those that do not as well.
- * The below tests check outcomes for each combination of such freplace.
- * Also test a case when main subprogram itself is replaced and is a single
- * subprogram in a program.
- */
-void test_changes_pkt_data_freplace(void)
-{
-	struct {
-		const char *main;
-		const char *to_be_replaced;
-		bool changes;
-	} mains[] = {
-		{ "main_with_subprogs",   "changes_pkt_data",         true },
-		{ "main_with_subprogs",   "does_not_change_pkt_data", false },
-		{ "main_changes",         "main_changes",             true },
-		{ "main_does_not_change", "main_does_not_change",     false },
-	};
-	struct {
-		const char *func;
-		bool changes;
-	} replacements[] = {
-		{ "changes_pkt_data",         true },
-		{ "does_not_change_pkt_data", false }
-	};
-	char buf[64];
-
-	for (int i = 0; i < ARRAY_SIZE(mains); ++i) {
-		for (int j = 0; j < ARRAY_SIZE(replacements); ++j) {
-			snprintf(buf, sizeof(buf), "%s_with_%s",
-				 mains[i].to_be_replaced, replacements[j].func);
-			if (!test__start_subtest(buf))
-				continue;
-			test_aux(mains[i].main, mains[i].to_be_replaced, replacements[j].func,
-				 mains[i].changes || !replacements[j].changes);
-		}
-	}
-}

tools/testing/selftests/bpf/prog_tests/compute_live_registers.c

@@ -0,0 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "compute_live_registers.skel.h"
+#include "test_progs.h"
+
+void test_compute_live_registers(void)
+{
+	RUN_TESTS(compute_live_registers);
+}

tools/testing/selftests/bpf/prog_tests/core_reloc.c

@@ -85,11 +85,11 @@ static int duration = 0;
 #define NESTING_ERR_CASE(name) {					\
 	NESTING_CASE_COMMON(name),					\
 	.fails = true,							\
-	.run_btfgen_fails = true,							\
+	.run_btfgen_fails = true,					\
 }
 
 #define ARRAYS_DATA(struct_name) STRUCT_TO_CHAR_PTR(struct_name) {	\
-	.a = { [2] = 1 },						\
+	.a = { [2] = 1, [3] = 11 },					\
 	.b = { [1] = { [2] = { [3] = 2 } } },				\
 	.c = { [1] = { .c =  3 } },					\
 	.d = { [0] = { [0] = { .d = 4 } } },				\
@@ -108,6 +108,7 @@ static int duration = 0;
 	.input_len = sizeof(struct core_reloc_##name),			\
 	.output = STRUCT_TO_CHAR_PTR(core_reloc_arrays_output) {	\
 		.a2   = 1,						\
+		.a3   = 12,						\
 		.b123 = 2,						\
 		.c1c  = 3,						\
 		.d00d = 4,						\
@@ -602,6 +603,7 @@ static const struct core_reloc_test_case test_cases[] = {
 	ARRAYS_ERR_CASE(arrays___err_non_array),
 	ARRAYS_ERR_CASE(arrays___err_wrong_val_type),
 	ARRAYS_ERR_CASE(arrays___err_bad_zero_sz_arr),
+	ARRAYS_ERR_CASE(arrays___err_bad_signed_arr_elem_sz),
 
 	/* enum/ptr/int handling scenarios */
 	PRIMITIVES_CASE(primitives),

tools/testing/selftests/bpf/prog_tests/cpumask.c

@@ -25,6 +25,10 @@ static const char * const cpumask_success_testcases[] = {
 	"test_global_mask_nested_deep_rcu",
 	"test_global_mask_nested_deep_array_rcu",
 	"test_cpumask_weight",
+	"test_refcount_null_tracking",
+	"test_populate_reject_small_mask",
+	"test_populate_reject_unaligned",
+	"test_populate",
 };
 
 static void verify_success(const char *prog_name)
@@ -78,6 +82,5 @@ void test_cpumask(void)
 		verify_success(cpumask_success_testcases[i]);
 	}
 
-	RUN_TESTS(cpumask_success);
 	RUN_TESTS(cpumask_failure);
 }

tools/testing/selftests/bpf/prog_tests/dynptr.c

@@ -10,6 +10,7 @@ enum test_setup_type {
 	SETUP_SYSCALL_SLEEP,
 	SETUP_SKB_PROG,
 	SETUP_SKB_PROG_TP,
+	SETUP_XDP_PROG,
 };
 
 static struct {
@@ -18,6 +19,8 @@ static struct {
 } success_tests[] = {
 	{"test_read_write", SETUP_SYSCALL_SLEEP},
 	{"test_dynptr_data", SETUP_SYSCALL_SLEEP},
+	{"test_dynptr_copy", SETUP_SYSCALL_SLEEP},
+	{"test_dynptr_copy_xdp", SETUP_XDP_PROG},
 	{"test_ringbuf", SETUP_SYSCALL_SLEEP},
 	{"test_skb_readonly", SETUP_SKB_PROG},
 	{"test_dynptr_skb_data", SETUP_SKB_PROG},
@@ -120,6 +123,24 @@ static void verify_success(const char *prog_name, enum test_setup_type setup_typ
 
 		break;
 	}
+	case SETUP_XDP_PROG:
+	{
+		char data[5000];
+		int err, prog_fd;
+		LIBBPF_OPTS(bpf_test_run_opts, opts,
+			    .data_in = &data,
+			    .data_size_in = sizeof(data),
+			    .repeat = 1,
+		);
+
+		prog_fd = bpf_program__fd(prog);
+		err = bpf_prog_test_run_opts(prog_fd, &opts);
+
+		if (!ASSERT_OK(err, "test_run"))
+			goto cleanup;
+
+		break;
+	}
 	}
 
 	ASSERT_EQ(skel->bss->err, 0, "err");

tools/testing/selftests/bpf/prog_tests/fd_array.c

@@ -83,8 +83,8 @@ static inline int bpf_prog_get_map_ids(int prog_fd, __u32 *nr_map_ids, __u32 *ma
 	int err;
 
 	memset(&info, 0, len);
-	info.nr_map_ids = *nr_map_ids,
-	info.map_ids = ptr_to_u64(map_ids),
+	info.nr_map_ids = *nr_map_ids;
+	info.map_ids = ptr_to_u64(map_ids);
 
 	err = bpf_prog_get_info_by_fd(prog_fd, &info, &len);
 	if (!ASSERT_OK(err, "bpf_prog_get_info_by_fd"))

tools/testing/selftests/bpf/prog_tests/fexit_noreturns.c

@@ -0,0 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include "fexit_noreturns.skel.h"
+
+void test_fexit_noreturns(void)
+{
+	RUN_TESTS(fexit_noreturns);
+}

tools/testing/selftests/bpf/prog_tests/fs_kfuncs.c

@@ -8,11 +8,12 @@
 #include <unistd.h>
 #include <test_progs.h>
 #include "test_get_xattr.skel.h"
+#include "test_set_remove_xattr.skel.h"
 #include "test_fsverity.skel.h"
 
 static const char testfile[] = "/tmp/test_progs_fs_kfuncs";
 
-static void test_xattr(void)
+static void test_get_xattr(const char *name, const char *value, bool allow_access)
 {
 	struct test_get_xattr *skel = NULL;
 	int fd = -1, err;
@@ -25,7 +26,7 @@ static void test_xattr(void)
 	close(fd);
 	fd = -1;
 
-	err = setxattr(testfile, "user.kfuncs", "hello", sizeof("hello"), 0);
+	err = setxattr(testfile, name, value, strlen(value) + 1, 0);
 	if (err && errno == EOPNOTSUPP) {
 		printf("%s:SKIP:local fs doesn't support xattr (%d)\n"
 		       "To run this test, make sure /tmp filesystem supports xattr.\n",
@@ -48,16 +49,23 @@ static void test_xattr(void)
 		goto out;
 
 	fd = open(testfile, O_RDONLY, 0644);
+
 	if (!ASSERT_GE(fd, 0, "open_file"))
 		goto out;
 
-	ASSERT_EQ(skel->bss->found_xattr_from_file, 1, "found_xattr_from_file");
-
 	/* Trigger security_inode_getxattr */
-	err = getxattr(testfile, "user.kfuncs", v, sizeof(v));
-	ASSERT_EQ(err, -1, "getxattr_return");
-	ASSERT_EQ(errno, EINVAL, "getxattr_errno");
-	ASSERT_EQ(skel->bss->found_xattr_from_dentry, 1, "found_xattr_from_dentry");
+	err = getxattr(testfile, name, v, sizeof(v));
+
+	if (allow_access) {
+		ASSERT_EQ(err, -1, "getxattr_return");
+		ASSERT_EQ(errno, EINVAL, "getxattr_errno");
+		ASSERT_EQ(skel->bss->found_xattr_from_file, 1, "found_xattr_from_file");
+		ASSERT_EQ(skel->bss->found_xattr_from_dentry, 1, "found_xattr_from_dentry");
+	} else {
+		ASSERT_EQ(err, strlen(value) + 1, "getxattr_return");
+		ASSERT_EQ(skel->bss->found_xattr_from_file, 0, "found_xattr_from_file");
+		ASSERT_EQ(skel->bss->found_xattr_from_dentry, 0, "found_xattr_from_dentry");
+	}
 
 out:
 	close(fd);
@@ -65,6 +73,127 @@ out:
 	remove(testfile);
 }
 
+/* xattr value we will set to security.bpf.foo */
+static const char value_foo[] = "hello";
+
+static void read_and_validate_foo(struct test_set_remove_xattr *skel)
+{
+	char value_out[32];
+	int err;
+
+	err = getxattr(testfile, skel->rodata->xattr_foo, value_out, sizeof(value_out));
+	ASSERT_EQ(err, sizeof(value_foo), "getxattr size foo");
+	ASSERT_EQ(strncmp(value_out, value_foo, sizeof(value_foo)), 0, "strncmp value_foo");
+}
+
+static void set_foo(struct test_set_remove_xattr *skel)
+{
+	ASSERT_OK(setxattr(testfile, skel->rodata->xattr_foo, value_foo, strlen(value_foo) + 1, 0),
+		  "setxattr foo");
+}
+
+static void validate_bar_match(struct test_set_remove_xattr *skel)
+{
+	char value_out[32];
+	int err;
+
+	err = getxattr(testfile, skel->rodata->xattr_bar, value_out, sizeof(value_out));
+	ASSERT_EQ(err, sizeof(skel->data->value_bar), "getxattr size bar");
+	ASSERT_EQ(strncmp(value_out, skel->data->value_bar, sizeof(skel->data->value_bar)), 0,
+		  "strncmp value_bar");
+}
+
+static void validate_bar_removed(struct test_set_remove_xattr *skel)
+{
+	char value_out[32];
+	int err;
+
+	err = getxattr(testfile, skel->rodata->xattr_bar, value_out, sizeof(value_out));
+	ASSERT_LT(err, 0, "getxattr size bar should fail");
+}
+
+static void test_set_remove_xattr(void)
+{
+	struct test_set_remove_xattr *skel = NULL;
+	int fd = -1, err;
+
+	fd = open(testfile, O_CREAT | O_RDONLY, 0644);
+	if (!ASSERT_GE(fd, 0, "create_file"))
+		return;
+
+	close(fd);
+	fd = -1;
+
+	skel = test_set_remove_xattr__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_set_remove_xattr__open_and_load"))
+		return;
+
+	/* Set security.bpf.foo to "hello" */
+	err = setxattr(testfile, skel->rodata->xattr_foo, value_foo, strlen(value_foo) + 1, 0);
+	if (err && errno == EOPNOTSUPP) {
+		printf("%s:SKIP:local fs doesn't support xattr (%d)\n"
+		       "To run this test, make sure /tmp filesystem supports xattr.\n",
+		       __func__, errno);
+		test__skip();
+		goto out;
+	}
+
+	if (!ASSERT_OK(err, "setxattr"))
+		goto out;
+
+	skel->bss->monitored_pid = getpid();
+	err = test_set_remove_xattr__attach(skel);
+	if (!ASSERT_OK(err, "test_set_remove_xattr__attach"))
+		goto out;
+
+	/* First, test not _locked version of the kfuncs with getxattr. */
+
+	/* Read security.bpf.foo and trigger test_inode_getxattr. This
+	 * bpf program will set security.bpf.bar to "world".
+	 */
+	read_and_validate_foo(skel);
+	validate_bar_match(skel);
+
+	/* Read security.bpf.foo and trigger test_inode_getxattr again.
+	 * This will remove xattr security.bpf.bar.
+	 */
+	read_and_validate_foo(skel);
+	validate_bar_removed(skel);
+
+	ASSERT_TRUE(skel->bss->set_security_bpf_bar_success, "set_security_bpf_bar_success");
+	ASSERT_TRUE(skel->bss->remove_security_bpf_bar_success, "remove_security_bpf_bar_success");
+	ASSERT_TRUE(skel->bss->set_security_selinux_fail, "set_security_selinux_fail");
+	ASSERT_TRUE(skel->bss->remove_security_selinux_fail, "remove_security_selinux_fail");
+
+	/* Second, test _locked version of the kfuncs, with setxattr */
+
+	/* Set security.bpf.foo and trigger test_inode_setxattr. This
+	 * bpf program will set security.bpf.bar to "world".
+	 */
+	set_foo(skel);
+	validate_bar_match(skel);
+
+	/* Set security.bpf.foo and trigger test_inode_setxattr again.
+	 * This will remove xattr security.bpf.bar.
+	 */
+	set_foo(skel);
+	validate_bar_removed(skel);
+
+	ASSERT_TRUE(skel->bss->locked_set_security_bpf_bar_success,
+		    "locked_set_security_bpf_bar_success");
+	ASSERT_TRUE(skel->bss->locked_remove_security_bpf_bar_success,
+		    "locked_remove_security_bpf_bar_success");
+	ASSERT_TRUE(skel->bss->locked_set_security_selinux_fail,
+		    "locked_set_security_selinux_fail");
+	ASSERT_TRUE(skel->bss->locked_remove_security_selinux_fail,
+		    "locked_remove_security_selinux_fail");
+
+out:
+	close(fd);
+	test_set_remove_xattr__destroy(skel);
+	remove(testfile);
+}
+
 #ifndef SHA256_DIGEST_SIZE
 #define SHA256_DIGEST_SIZE      32
 #endif
@@ -141,8 +270,21 @@ out:
 
 void test_fs_kfuncs(void)
 {
-	if (test__start_subtest("xattr"))
-		test_xattr();
+	/* Matches xattr_names in progs/test_get_xattr.c */
+	if (test__start_subtest("user_xattr"))
+		test_get_xattr("user.kfuncs", "hello", true);
+
+	if (test__start_subtest("security_bpf_xattr"))
+		test_get_xattr("security.bpf.xxx", "hello", true);
+
+	if (test__start_subtest("security_bpf_xattr_error"))
+		test_get_xattr("security.bpf", "hello", false);
+
+	if (test__start_subtest("security_selinux_xattr_error"))
+		test_get_xattr("security.selinux", "hello", false);
+
+	if (test__start_subtest("set_remove_xattr"))
+		test_set_remove_xattr();
 
 	if (test__start_subtest("fsverity"))
 		test_fsverity();

tools/testing/selftests/bpf/prog_tests/kernel_flag.c

@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Microsoft */
+#include <test_progs.h>
+#include "kfunc_call_test.skel.h"
+#include "kfunc_call_test.lskel.h"
+#include "test_kernel_flag.skel.h"
+
+void test_kernel_flag(void)
+{
+	struct test_kernel_flag *lsm_skel;
+	struct kfunc_call_test *skel = NULL;
+	struct kfunc_call_test_lskel *lskel = NULL;
+	int ret;
+
+	lsm_skel = test_kernel_flag__open_and_load();
+	if (!ASSERT_OK_PTR(lsm_skel, "lsm_skel"))
+		return;
+
+	lsm_skel->bss->monitored_tid = gettid();
+
+	ret = test_kernel_flag__attach(lsm_skel);
+	if (!ASSERT_OK(ret, "test_kernel_flag__attach"))
+		goto close_prog;
+
+	/* Test with skel. This should pass the gatekeeper */
+	skel = kfunc_call_test__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel"))
+		goto close_prog;
+
+	/* Test with lskel. This should fail due to blocking kernel-based bpf() invocations */
+	lskel = kfunc_call_test_lskel__open_and_load();
+	if (!ASSERT_ERR_PTR(lskel, "lskel"))
+		goto close_prog;
+
+close_prog:
+	if (skel)
+		kfunc_call_test__destroy(skel);
+	if (lskel)
+		kfunc_call_test_lskel__destroy(lskel);
+
+	lsm_skel->bss->monitored_tid = 0;
+	test_kernel_flag__destroy(lsm_skel);
+}

tools/testing/selftests/bpf/prog_tests/lwt_ip_encap.c

@@ -0,0 +1,540 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <netinet/in.h>
+
+#include "network_helpers.h"
+#include "test_progs.h"
+
+#define BPF_FILE "test_lwt_ip_encap.bpf.o"
+
+#define NETNS_NAME_SIZE	32
+#define NETNS_BASE	"ns-lwt-ip-encap"
+
+#define IP4_ADDR_1 "172.16.1.100"
+#define IP4_ADDR_2 "172.16.2.100"
+#define IP4_ADDR_3 "172.16.3.100"
+#define IP4_ADDR_4 "172.16.4.100"
+#define IP4_ADDR_5 "172.16.5.100"
+#define IP4_ADDR_6 "172.16.6.100"
+#define IP4_ADDR_7 "172.16.7.100"
+#define IP4_ADDR_8 "172.16.8.100"
+#define IP4_ADDR_GRE "172.16.16.100"
+
+#define IP4_ADDR_SRC IP4_ADDR_1
+#define IP4_ADDR_DST IP4_ADDR_4
+
+#define IP6_ADDR_1 "fb01::1"
+#define IP6_ADDR_2 "fb02::1"
+#define IP6_ADDR_3 "fb03::1"
+#define IP6_ADDR_4 "fb04::1"
+#define IP6_ADDR_5 "fb05::1"
+#define IP6_ADDR_6 "fb06::1"
+#define IP6_ADDR_7 "fb07::1"
+#define IP6_ADDR_8 "fb08::1"
+#define IP6_ADDR_GRE "fb10::1"
+
+#define IP6_ADDR_SRC IP6_ADDR_1
+#define IP6_ADDR_DST IP6_ADDR_4
+
+/* Setup/topology:
+ *
+ *    NS1             NS2             NS3
+ *   veth1 <---> veth2   veth3 <---> veth4 (the top route)
+ *   veth5 <---> veth6   veth7 <---> veth8 (the bottom route)
+ *
+ *   Each vethN gets IP[4|6]_ADDR_N address.
+ *
+ *   IP*_ADDR_SRC = IP*_ADDR_1
+ *   IP*_ADDR_DST = IP*_ADDR_4
+ *
+ *   All tests test pings from IP*_ADDR__SRC to IP*_ADDR_DST.
+ *
+ *   By default, routes are configured to allow packets to go
+ *   IP*_ADDR_1 <=> IP*_ADDR_2 <=> IP*_ADDR_3 <=> IP*_ADDR_4 (the top route).
+ *
+ *   A GRE device is installed in NS3 with IP*_ADDR_GRE, and
+ *   NS1/NS2 are configured to route packets to IP*_ADDR_GRE via IP*_ADDR_8
+ *   (the bottom route).
+ *
+ * Tests:
+ *
+ *   1. Routes NS2->IP*_ADDR_DST are brought down, so the only way a ping
+ *      from IP*_ADDR_SRC to IP*_ADDR_DST can work is via IP*_ADDR_GRE.
+ *
+ *   2a. In an egress test, a bpf LWT_XMIT program is installed on veth1
+ *       that encaps the packets with an IP/GRE header to route to IP*_ADDR_GRE.
+ *
+ *       ping: SRC->[encap at veth1:egress]->GRE:decap->DST
+ *       ping replies go DST->SRC directly
+ *
+ *   2b. In an ingress test, a bpf LWT_IN program is installed on veth2
+ *       that encaps the packets with an IP/GRE header to route to IP*_ADDR_GRE.
+ *
+ *       ping: SRC->[encap at veth2:ingress]->GRE:decap->DST
+ *       ping replies go DST->SRC directly
+ */
+
+static int create_ns(char *name, size_t name_sz)
+{
+	if (!name)
+		goto fail;
+
+	if (!ASSERT_OK(append_tid(name, name_sz), "append TID"))
+		goto fail;
+
+	SYS(fail, "ip netns add %s", name);
+
+	/* rp_filter gets confused by what these tests are doing, so disable it */
+	SYS(fail, "ip netns exec %s sysctl -wq net.ipv4.conf.all.rp_filter=0", name);
+	SYS(fail, "ip netns exec %s sysctl -wq net.ipv4.conf.default.rp_filter=0", name);
+	/* Disable IPv6 DAD because it sometimes takes too long and fails tests */
+	SYS(fail, "ip netns exec %s sysctl -wq net.ipv6.conf.all.accept_dad=0", name);
+	SYS(fail, "ip netns exec %s sysctl -wq net.ipv6.conf.default.accept_dad=0", name);
+
+	return 0;
+fail:
+	return -1;
+}
+
+static int set_top_addr(const char *ns1, const char *ns2, const char *ns3)
+{
+	SYS(fail, "ip -n %s    a add %s/24  dev veth1", ns1, IP4_ADDR_1);
+	SYS(fail, "ip -n %s    a add %s/24  dev veth2", ns2, IP4_ADDR_2);
+	SYS(fail, "ip -n %s    a add %s/24  dev veth3", ns2, IP4_ADDR_3);
+	SYS(fail, "ip -n %s    a add %s/24  dev veth4", ns3, IP4_ADDR_4);
+	SYS(fail, "ip -n %s -6 a add %s/128 dev veth1", ns1, IP6_ADDR_1);
+	SYS(fail, "ip -n %s -6 a add %s/128 dev veth2", ns2, IP6_ADDR_2);
+	SYS(fail, "ip -n %s -6 a add %s/128 dev veth3", ns2, IP6_ADDR_3);
+	SYS(fail, "ip -n %s -6 a add %s/128 dev veth4", ns3, IP6_ADDR_4);
+
+	SYS(fail, "ip -n %s link set dev veth1 up", ns1);
+	SYS(fail, "ip -n %s link set dev veth2 up", ns2);
+	SYS(fail, "ip -n %s link set dev veth3 up", ns2);
+	SYS(fail, "ip -n %s link set dev veth4 up", ns3);
+
+	return 0;
+fail:
+	return 1;
+}
+
+static int set_bottom_addr(const char *ns1, const char *ns2, const char *ns3)
+{
+	SYS(fail, "ip -n %s    a add %s/24  dev veth5", ns1, IP4_ADDR_5);
+	SYS(fail, "ip -n %s    a add %s/24  dev veth6", ns2, IP4_ADDR_6);
+	SYS(fail, "ip -n %s    a add %s/24  dev veth7", ns2, IP4_ADDR_7);
+	SYS(fail, "ip -n %s    a add %s/24  dev veth8", ns3, IP4_ADDR_8);
+	SYS(fail, "ip -n %s -6 a add %s/128 dev veth5", ns1, IP6_ADDR_5);
+	SYS(fail, "ip -n %s -6 a add %s/128 dev veth6", ns2, IP6_ADDR_6);
+	SYS(fail, "ip -n %s -6 a add %s/128 dev veth7", ns2, IP6_ADDR_7);
+	SYS(fail, "ip -n %s -6 a add %s/128 dev veth8", ns3, IP6_ADDR_8);
+
+	SYS(fail, "ip -n %s link set dev veth5 up", ns1);
+	SYS(fail, "ip -n %s link set dev veth6 up", ns2);
+	SYS(fail, "ip -n %s link set dev veth7 up", ns2);
+	SYS(fail, "ip -n %s link set dev veth8 up", ns3);
+
+	return 0;
+fail:
+	return 1;
+}
+
+static int configure_vrf(const char *ns1, const char *ns2)
+{
+	if (!ns1 || !ns2)
+		goto fail;
+
+	SYS(fail, "ip -n %s link add red type vrf table 1001", ns1);
+	SYS(fail, "ip -n %s link set red up", ns1);
+	SYS(fail, "ip -n %s route add table 1001 unreachable default metric 8192", ns1);
+	SYS(fail, "ip -n %s -6 route add table 1001 unreachable default metric 8192", ns1);
+	SYS(fail, "ip -n %s link set veth1 vrf red", ns1);
+	SYS(fail, "ip -n %s link set veth5 vrf red", ns1);
+
+	SYS(fail, "ip -n %s link add red type vrf table 1001", ns2);
+	SYS(fail, "ip -n %s link set red up", ns2);
+	SYS(fail, "ip -n %s route add table 1001 unreachable default metric 8192", ns2);
+	SYS(fail, "ip -n %s -6 route add table 1001 unreachable default metric 8192", ns2);
+	SYS(fail, "ip -n %s link set veth2 vrf red", ns2);
+	SYS(fail, "ip -n %s link set veth3 vrf red", ns2);
+	SYS(fail, "ip -n %s link set veth6 vrf red", ns2);
+	SYS(fail, "ip -n %s link set veth7 vrf red", ns2);
+
+	return 0;
+fail:
+	return -1;
+}
+
+static int configure_ns1(const char *ns1, const char *vrf)
+{
+	struct nstoken *nstoken = NULL;
+
+	if (!ns1 || !vrf)
+		goto fail;
+
+	nstoken = open_netns(ns1);
+	if (!ASSERT_OK_PTR(nstoken, "open ns1"))
+		goto fail;
+
+	/* Top route */
+	SYS(fail, "ip    route add %s/32  dev veth1 %s", IP4_ADDR_2, vrf);
+	SYS(fail, "ip    route add default dev veth1 via %s %s", IP4_ADDR_2, vrf);
+	SYS(fail, "ip -6 route add %s/128 dev veth1 %s", IP6_ADDR_2, vrf);
+	SYS(fail, "ip -6 route add default dev veth1 via %s %s", IP6_ADDR_2, vrf);
+	/* Bottom route */
+	SYS(fail, "ip    route add %s/32  dev veth5 %s", IP4_ADDR_6, vrf);
+	SYS(fail, "ip    route add %s/32  dev veth5 via  %s %s", IP4_ADDR_7, IP4_ADDR_6, vrf);
+	SYS(fail, "ip    route add %s/32  dev veth5 via  %s %s", IP4_ADDR_8, IP4_ADDR_6, vrf);
+	SYS(fail, "ip -6 route add %s/128 dev veth5 %s", IP6_ADDR_6, vrf);
+	SYS(fail, "ip -6 route add %s/128 dev veth5 via  %s %s", IP6_ADDR_7, IP6_ADDR_6, vrf);
+	SYS(fail, "ip -6 route add %s/128 dev veth5 via  %s %s", IP6_ADDR_8, IP6_ADDR_6, vrf);
+
+	close_netns(nstoken);
+	return 0;
+fail:
+	close_netns(nstoken);
+	return -1;
+}
+
+static int configure_ns2(const char *ns2, const char *vrf)
+{
+	struct nstoken *nstoken = NULL;
+
+	if (!ns2 || !vrf)
+		goto fail;
+
+	nstoken = open_netns(ns2);
+	if (!ASSERT_OK_PTR(nstoken, "open ns2"))
+		goto fail;
+
+	SYS(fail, "ip netns exec %s sysctl -wq net.ipv4.ip_forward=1", ns2);
+	SYS(fail, "ip netns exec %s sysctl -wq net.ipv6.conf.all.forwarding=1", ns2);
+
+	/* Top route */
+	SYS(fail, "ip    route add %s/32  dev veth2 %s", IP4_ADDR_1, vrf);
+	SYS(fail, "ip    route add %s/32  dev veth3 %s", IP4_ADDR_4, vrf);
+	SYS(fail, "ip -6 route add %s/128 dev veth2 %s", IP6_ADDR_1, vrf);
+	SYS(fail, "ip -6 route add %s/128 dev veth3 %s", IP6_ADDR_4, vrf);
+	/* Bottom route */
+	SYS(fail, "ip    route add %s/32  dev veth6 %s", IP4_ADDR_5, vrf);
+	SYS(fail, "ip    route add %s/32  dev veth7 %s", IP4_ADDR_8, vrf);
+	SYS(fail, "ip -6 route add %s/128 dev veth6 %s", IP6_ADDR_5, vrf);
+	SYS(fail, "ip -6 route add %s/128 dev veth7 %s", IP6_ADDR_8, vrf);
+
+	close_netns(nstoken);
+	return 0;
+fail:
+	close_netns(nstoken);
+	return -1;
+}
+
+static int configure_ns3(const char *ns3)
+{
+	struct nstoken *nstoken = NULL;
+
+	if (!ns3)
+		goto fail;
+
+	nstoken = open_netns(ns3);
+	if (!ASSERT_OK_PTR(nstoken, "open ns3"))
+		goto fail;
+
+	/* Top route */
+	SYS(fail, "ip    route add %s/32  dev veth4", IP4_ADDR_3);
+	SYS(fail, "ip    route add %s/32  dev veth4 via  %s", IP4_ADDR_1, IP4_ADDR_3);
+	SYS(fail, "ip    route add %s/32  dev veth4 via  %s", IP4_ADDR_2, IP4_ADDR_3);
+	SYS(fail, "ip -6 route add %s/128 dev veth4", IP6_ADDR_3);
+	SYS(fail, "ip -6 route add %s/128 dev veth4 via  %s", IP6_ADDR_1, IP6_ADDR_3);
+	SYS(fail, "ip -6 route add %s/128 dev veth4 via  %s", IP6_ADDR_2, IP6_ADDR_3);
+	/* Bottom route */
+	SYS(fail, "ip    route add %s/32  dev veth8", IP4_ADDR_7);
+	SYS(fail, "ip    route add %s/32  dev veth8 via  %s", IP4_ADDR_5, IP4_ADDR_7);
+	SYS(fail, "ip    route add %s/32  dev veth8 via  %s", IP4_ADDR_6, IP4_ADDR_7);
+	SYS(fail, "ip -6 route add %s/128 dev veth8", IP6_ADDR_7);
+	SYS(fail, "ip -6 route add %s/128 dev veth8 via  %s", IP6_ADDR_5, IP6_ADDR_7);
+	SYS(fail, "ip -6 route add %s/128 dev veth8 via  %s", IP6_ADDR_6, IP6_ADDR_7);
+
+	/* Configure IPv4 GRE device */
+	SYS(fail, "ip tunnel add gre_dev mode gre remote %s local %s ttl 255",
+	    IP4_ADDR_1, IP4_ADDR_GRE);
+	SYS(fail, "ip link set gre_dev up");
+	SYS(fail, "ip a add %s dev gre_dev", IP4_ADDR_GRE);
+
+	/* Configure IPv6 GRE device */
+	SYS(fail, "ip tunnel add gre6_dev mode ip6gre remote %s local %s ttl 255",
+	    IP6_ADDR_1, IP6_ADDR_GRE);
+	SYS(fail, "ip link set gre6_dev up");
+	SYS(fail, "ip a add %s dev gre6_dev", IP6_ADDR_GRE);
+
+	close_netns(nstoken);
+	return 0;
+fail:
+	close_netns(nstoken);
+	return -1;
+}
+
+static int setup_network(char *ns1, char *ns2, char *ns3, const char *vrf)
+{
+	if (!ns1 || !ns2 || !ns3 || !vrf)
+		goto fail;
+
+	SYS(fail, "ip -n %s link add veth1 type veth peer name veth2 netns %s", ns1, ns2);
+	SYS(fail, "ip -n %s link add veth3 type veth peer name veth4 netns %s", ns2, ns3);
+	SYS(fail, "ip -n %s link add veth5 type veth peer name veth6 netns %s", ns1, ns2);
+	SYS(fail, "ip -n %s link add veth7 type veth peer name veth8 netns %s", ns2, ns3);
+
+	if (vrf[0]) {
+		if (!ASSERT_OK(configure_vrf(ns1, ns2), "configure vrf"))
+			goto fail;
+	}
+	if (!ASSERT_OK(set_top_addr(ns1, ns2, ns3), "set top addresses"))
+		goto fail;
+
+	if (!ASSERT_OK(set_bottom_addr(ns1, ns2, ns3), "set bottom addresses"))
+		goto fail;
+
+	if (!ASSERT_OK(configure_ns1(ns1, vrf), "configure ns1 routes"))
+		goto fail;
+
+	if (!ASSERT_OK(configure_ns2(ns2, vrf), "configure ns2 routes"))
+		goto fail;
+
+	if (!ASSERT_OK(configure_ns3(ns3), "configure ns3 routes"))
+		goto fail;
+
+	/* Link bottom route to the GRE tunnels */
+	SYS(fail, "ip -n %s route add %s/32 dev veth5 via %s %s",
+	    ns1, IP4_ADDR_GRE, IP4_ADDR_6, vrf);
+	SYS(fail, "ip -n %s route add %s/32 dev veth7 via %s %s",
+	    ns2, IP4_ADDR_GRE, IP4_ADDR_8, vrf);
+	SYS(fail, "ip -n %s -6 route add %s/128 dev veth5 via %s %s",
+	    ns1, IP6_ADDR_GRE, IP6_ADDR_6, vrf);
+	SYS(fail, "ip -n %s -6 route add %s/128 dev veth7 via %s %s",
+	    ns2, IP6_ADDR_GRE, IP6_ADDR_8, vrf);
+
+	return 0;
+fail:
+	return -1;
+}
+
+static int remove_routes_to_gredev(const char *ns1, const char *ns2, const char *vrf)
+{
+	SYS(fail, "ip -n %s route del %s dev veth5 %s", ns1, IP4_ADDR_GRE, vrf);
+	SYS(fail, "ip -n %s route del %s dev veth7 %s", ns2, IP4_ADDR_GRE, vrf);
+	SYS(fail, "ip -n %s -6 route del %s/128 dev veth5 %s", ns1, IP6_ADDR_GRE, vrf);
+	SYS(fail, "ip -n %s -6 route del %s/128 dev veth7 %s", ns2, IP6_ADDR_GRE, vrf);
+
+	return 0;
+fail:
+	return -1;
+}
+
+static int add_unreachable_routes_to_gredev(const char *ns1, const char *ns2, const char *vrf)
+{
+	SYS(fail, "ip -n %s route add unreachable %s/32 %s", ns1, IP4_ADDR_GRE, vrf);
+	SYS(fail, "ip -n %s route add unreachable %s/32 %s", ns2, IP4_ADDR_GRE, vrf);
+	SYS(fail, "ip -n %s -6 route add unreachable %s/128 %s", ns1, IP6_ADDR_GRE, vrf);
+	SYS(fail, "ip -n %s -6 route add unreachable %s/128 %s", ns2, IP6_ADDR_GRE, vrf);
+
+	return 0;
+fail:
+	return -1;
+}
+
+#define GSO_SIZE 5000
+#define GSO_TCP_PORT 9000
+/* This tests the fix from commit ea0371f78799 ("net: fix GSO in bpf_lwt_push_ip_encap") */
+static int test_gso_fix(const char *ns1, const char *ns3, int family)
+{
+	const char *ip_addr = family == AF_INET ? IP4_ADDR_DST : IP6_ADDR_DST;
+	char gso_packet[GSO_SIZE] = {};
+	struct nstoken *nstoken = NULL;
+	int sfd, cfd, afd;
+	ssize_t bytes;
+	int ret = -1;
+
+	if (!ns1 || !ns3)
+		return ret;
+
+	nstoken = open_netns(ns3);
+	if (!ASSERT_OK_PTR(nstoken, "open ns3"))
+		return ret;
+
+	sfd = start_server_str(family, SOCK_STREAM, ip_addr, GSO_TCP_PORT, NULL);
+	if (!ASSERT_OK_FD(sfd, "start server"))
+		goto close_netns;
+
+	close_netns(nstoken);
+
+	nstoken = open_netns(ns1);
+	if (!ASSERT_OK_PTR(nstoken, "open ns1"))
+		goto close_server;
+
+	cfd = connect_to_addr_str(family, SOCK_STREAM, ip_addr, GSO_TCP_PORT, NULL);
+	if (!ASSERT_OK_FD(cfd, "connect to server"))
+		goto close_server;
+
+	close_netns(nstoken);
+	nstoken = NULL;
+
+	afd = accept(sfd, NULL, NULL);
+	if (!ASSERT_OK_FD(afd, "accept"))
+		goto close_client;
+
+	/* Send a packet larger than MTU */
+	bytes = send(cfd, gso_packet, GSO_SIZE, 0);
+	if (!ASSERT_EQ(bytes, GSO_SIZE, "send packet"))
+		goto close_accept;
+
+	/* Verify we received all expected bytes */
+	bytes = read(afd, gso_packet, GSO_SIZE);
+	if (!ASSERT_EQ(bytes, GSO_SIZE, "receive packet"))
+		goto close_accept;
+
+	ret = 0;
+
+close_accept:
+	close(afd);
+close_client:
+	close(cfd);
+close_server:
+	close(sfd);
+close_netns:
+	close_netns(nstoken);
+
+	return ret;
+}
+
+static int check_ping_ok(const char *ns1)
+{
+	SYS(fail, "ip netns exec %s ping -c 1 -W1 -I veth1 %s > /dev/null", ns1, IP4_ADDR_DST);
+	SYS(fail, "ip netns exec %s ping6 -c 1 -W1 -I veth1 %s > /dev/null", ns1, IP6_ADDR_DST);
+	return 0;
+fail:
+	return -1;
+}
+
+static int check_ping_fails(const char *ns1)
+{
+	int ret;
+
+	ret = SYS_NOFAIL("ip netns exec %s ping -c 1 -W1 -I veth1 %s", ns1, IP4_ADDR_DST);
+	if (!ret)
+		return -1;
+
+	ret = SYS_NOFAIL("ip netns exec %s ping6 -c 1 -W1 -I veth1 %s", ns1, IP6_ADDR_DST);
+	if (!ret)
+		return -1;
+
+	return 0;
+}
+
+#define EGRESS true
+#define INGRESS false
+#define IPV4_ENCAP true
+#define IPV6_ENCAP false
+static void lwt_ip_encap(bool ipv4_encap, bool egress, const char *vrf)
+{
+	char ns1[NETNS_NAME_SIZE] = NETNS_BASE "-1-";
+	char ns2[NETNS_NAME_SIZE] = NETNS_BASE "-2-";
+	char ns3[NETNS_NAME_SIZE] = NETNS_BASE "-3-";
+	char *sec = ipv4_encap ?  "encap_gre" : "encap_gre6";
+
+	if (!vrf)
+		return;
+
+	if (!ASSERT_OK(create_ns(ns1, NETNS_NAME_SIZE), "create ns1"))
+		goto out;
+	if (!ASSERT_OK(create_ns(ns2, NETNS_NAME_SIZE), "create ns2"))
+		goto out;
+	if (!ASSERT_OK(create_ns(ns3, NETNS_NAME_SIZE), "create ns3"))
+		goto out;
+
+	if (!ASSERT_OK(setup_network(ns1, ns2, ns3, vrf), "setup network"))
+		goto out;
+
+	/* By default, pings work */
+	if (!ASSERT_OK(check_ping_ok(ns1), "ping OK"))
+		goto out;
+
+	/* Remove NS2->DST routes, ping fails */
+	SYS(out, "ip -n %s    route del %s/32  dev veth3 %s", ns2, IP4_ADDR_DST, vrf);
+	SYS(out, "ip -n %s -6 route del %s/128 dev veth3 %s", ns2, IP6_ADDR_DST, vrf);
+	if (!ASSERT_OK(check_ping_fails(ns1), "ping expected fail"))
+		goto out;
+
+	/* Install replacement routes (LWT/eBPF), pings succeed */
+	if (egress) {
+		SYS(out, "ip -n %s route add %s encap bpf xmit obj %s sec %s dev veth1 %s",
+		    ns1, IP4_ADDR_DST, BPF_FILE, sec, vrf);
+		SYS(out, "ip -n %s -6 route add %s encap bpf xmit obj %s sec %s dev veth1 %s",
+		    ns1, IP6_ADDR_DST, BPF_FILE, sec, vrf);
+	} else {
+		SYS(out, "ip -n %s route add %s encap bpf in obj %s sec %s dev veth2 %s",
+		    ns2, IP4_ADDR_DST, BPF_FILE, sec, vrf);
+		SYS(out, "ip -n %s -6 route add %s encap bpf in obj %s sec %s dev veth2 %s",
+		    ns2, IP6_ADDR_DST, BPF_FILE, sec, vrf);
+	}
+
+	if (!ASSERT_OK(check_ping_ok(ns1), "ping OK"))
+		goto out;
+
+	/* Skip GSO tests with VRF: VRF routing needs properly assigned
+	 * source IP/device, which is easy to do with ping but hard with TCP.
+	 */
+	if (egress && !vrf[0]) {
+		if (!ASSERT_OK(test_gso_fix(ns1, ns3, AF_INET), "test GSO"))
+			goto out;
+	}
+
+	/* Negative test: remove routes to GRE devices: ping fails */
+	if (!ASSERT_OK(remove_routes_to_gredev(ns1, ns2, vrf), "remove routes to gredev"))
+		goto out;
+	if (!ASSERT_OK(check_ping_fails(ns1), "ping expected fail"))
+		goto out;
+
+	/* Another negative test */
+	if (!ASSERT_OK(add_unreachable_routes_to_gredev(ns1, ns2, vrf),
+		       "add unreachable routes"))
+		goto out;
+	ASSERT_OK(check_ping_fails(ns1), "ping expected fail");
+
+out:
+	SYS_NOFAIL("ip netns del %s", ns1);
+	SYS_NOFAIL("ip netns del %s", ns2);
+	SYS_NOFAIL("ip netns del %s", ns3);
+}
+
+void test_lwt_ip_encap_vrf_ipv6(void)
+{
+	if (test__start_subtest("egress"))
+		lwt_ip_encap(IPV6_ENCAP, EGRESS, "vrf red");
+
+	if (test__start_subtest("ingress"))
+		lwt_ip_encap(IPV6_ENCAP, INGRESS, "vrf red");
+}
+
+void test_lwt_ip_encap_vrf_ipv4(void)
+{
+	if (test__start_subtest("egress"))
+		lwt_ip_encap(IPV4_ENCAP, EGRESS, "vrf red");
+
+	if (test__start_subtest("ingress"))
+		lwt_ip_encap(IPV4_ENCAP, INGRESS, "vrf red");
+}
+
+void test_lwt_ip_encap_ipv6(void)
+{
+	if (test__start_subtest("egress"))
+		lwt_ip_encap(IPV6_ENCAP, EGRESS, "");
+
+	if (test__start_subtest("ingress"))
+		lwt_ip_encap(IPV6_ENCAP, INGRESS, "");
+}
+
+void test_lwt_ip_encap_ipv4(void)
+{
+	if (test__start_subtest("egress"))
+		lwt_ip_encap(IPV4_ENCAP, EGRESS, "");
+
+	if (test__start_subtest("ingress"))
+		lwt_ip_encap(IPV4_ENCAP, INGRESS, "");
+}

tools/testing/selftests/bpf/prog_tests/lwt_seg6local.c

@@ -0,0 +1,176 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+/* Connects 6 network namespaces through veths.
+ * Each NS may have different IPv6 global scope addresses :
+ *
+ *          NS1            NS2             NS3              NS4               NS5             NS6
+ *      lo  veth1 <-> veth2 veth3 <-> veth4 veth5 <-> veth6 lo veth7 <-> veth8 veth9 <-> veth10 lo
+ * fb00 ::1  ::12      ::21  ::34      ::43  ::56      ::65     ::78      ::87  ::910     ::109  ::6
+ * fd00                                                                                          ::4
+ * fc42                                                     ::1
+ *
+ * All IPv6 packets going to fb00::/16 through NS2 will be encapsulated in a
+ * IPv6 header with a Segment Routing Header, with segments :
+ *	fd00::1 -> fd00::2 -> fd00::3 -> fd00::4
+ *
+ * 3 fd00::/16 IPv6 addresses are binded to seg6local End.BPF actions :
+ * - fd00::1 : add a TLV, change the flags and apply a End.X action to fc42::1
+ * - fd00::2 : remove the TLV, change the flags, add a tag
+ * - fd00::3 : apply an End.T action to fd00::4, through routing table 117
+ *
+ * fd00::4 is a simple Segment Routing node decapsulating the inner IPv6 packet.
+ * Each End.BPF action will validate the operations applied on the SRH by the
+ * previous BPF program in the chain, otherwise the packet is dropped.
+ *
+ * An UDP datagram is sent from fb00::1 to fb00::6. The test succeeds if this
+ * datagram can be read on NS6 when binding to fb00::6.
+ */
+
+#include "network_helpers.h"
+#include "test_progs.h"
+
+#define NETNS_BASE "lwt-seg6local-"
+#define BPF_FILE "test_lwt_seg6local.bpf.o"
+
+static void cleanup(void)
+{
+	int ns;
+
+	for (ns = 1; ns < 7; ns++)
+		SYS_NOFAIL("ip netns del %s%d", NETNS_BASE, ns);
+}
+
+static int setup(void)
+{
+	int ns;
+
+	for (ns = 1; ns < 7; ns++)
+		SYS(fail, "ip netns add %s%d", NETNS_BASE, ns);
+
+	SYS(fail, "ip -n %s6 link set dev lo up", NETNS_BASE);
+
+	for (ns = 1; ns < 6; ns++) {
+		int local_id = ns * 2 - 1;
+		int peer_id = ns * 2;
+		int next_ns = ns + 1;
+
+		SYS(fail, "ip -n %s%d link add veth%d type veth peer name veth%d netns %s%d",
+		    NETNS_BASE, ns, local_id, peer_id, NETNS_BASE, next_ns);
+
+		SYS(fail, "ip -n %s%d link set dev veth%d up", NETNS_BASE, ns, local_id);
+		SYS(fail, "ip -n %s%d link set dev veth%d up", NETNS_BASE, next_ns, peer_id);
+
+		/* All link scope addresses to veths */
+		SYS(fail, "ip -n %s%d -6 addr add fb00::%d%d/16 dev veth%d scope link",
+		    NETNS_BASE, ns, local_id, peer_id, local_id);
+		SYS(fail, "ip -n %s%d -6 addr add fb00::%d%d/16 dev veth%d scope link",
+		    NETNS_BASE, next_ns, peer_id, local_id, peer_id);
+	}
+
+
+	SYS(fail, "ip -n %s5 -6 route add fb00::109 table 117 dev veth9 scope link", NETNS_BASE);
+
+	SYS(fail, "ip -n %s1 -6 addr add fb00::1/16 dev lo", NETNS_BASE);
+	SYS(fail, "ip -n %s1 -6 route add fb00::6 dev veth1 via fb00::21", NETNS_BASE);
+
+	SYS(fail, "ip -n %s2 -6 route add fb00::6 encap bpf in obj %s sec encap_srh dev veth2",
+	    NETNS_BASE, BPF_FILE);
+	SYS(fail, "ip -n %s2 -6 route add fd00::1 dev veth3 via fb00::43 scope link", NETNS_BASE);
+
+	SYS(fail, "ip -n %s3 -6 route add fc42::1 dev veth5 via fb00::65", NETNS_BASE);
+	SYS(fail,
+	    "ip -n %s3 -6 route add fd00::1 encap seg6local action End.BPF endpoint obj %s sec add_egr_x dev veth4",
+	    NETNS_BASE, BPF_FILE);
+
+	SYS(fail,
+	    "ip -n %s4 -6 route add fd00::2 encap seg6local action End.BPF endpoint obj %s sec pop_egr dev veth6",
+	    NETNS_BASE, BPF_FILE);
+	SYS(fail, "ip -n %s4 -6 addr add fc42::1 dev lo", NETNS_BASE);
+	SYS(fail, "ip -n %s4 -6 route add fd00::3 dev veth7 via fb00::87", NETNS_BASE);
+
+	SYS(fail, "ip -n %s5 -6 route add fd00::4 table 117 dev veth9 via fb00::109", NETNS_BASE);
+	SYS(fail,
+	    "ip -n %s5 -6 route add fd00::3 encap seg6local action End.BPF endpoint obj %s sec inspect_t dev veth8",
+	    NETNS_BASE, BPF_FILE);
+
+	SYS(fail, "ip -n %s6 -6 addr add fb00::6/16 dev lo", NETNS_BASE);
+	SYS(fail, "ip -n %s6 -6 addr add fd00::4/16 dev lo", NETNS_BASE);
+
+	for (ns = 1; ns < 6; ns++)
+		SYS(fail, "ip netns exec %s%d sysctl -wq net.ipv6.conf.all.forwarding=1",
+		    NETNS_BASE, ns);
+
+	SYS(fail, "ip netns exec %s6 sysctl -wq net.ipv6.conf.all.seg6_enabled=1", NETNS_BASE);
+	SYS(fail, "ip netns exec %s6 sysctl -wq net.ipv6.conf.lo.seg6_enabled=1", NETNS_BASE);
+	SYS(fail, "ip netns exec %s6 sysctl -wq net.ipv6.conf.veth10.seg6_enabled=1", NETNS_BASE);
+
+	return 0;
+fail:
+	return -1;
+}
+
+#define SERVER_PORT 7330
+#define CLIENT_PORT 2121
+void test_lwt_seg6local(void)
+{
+	struct sockaddr_in6 server_addr = {};
+	const char *ns1 = NETNS_BASE "1";
+	const char *ns6 = NETNS_BASE "6";
+	struct nstoken *nstoken = NULL;
+	const char *foobar = "foobar";
+	ssize_t bytes;
+	int sfd, cfd;
+	char buf[7];
+
+	if (!ASSERT_OK(setup(), "setup"))
+		goto out;
+
+	nstoken = open_netns(ns6);
+	if (!ASSERT_OK_PTR(nstoken, "open ns6"))
+		goto out;
+
+	sfd = start_server_str(AF_INET6, SOCK_DGRAM, "fb00::6", SERVER_PORT, NULL);
+	if (!ASSERT_OK_FD(sfd, "start server"))
+		goto close_netns;
+
+	close_netns(nstoken);
+
+	nstoken = open_netns(ns1);
+	if (!ASSERT_OK_PTR(nstoken, "open ns1"))
+		goto close_server;
+
+	cfd = start_server_str(AF_INET6, SOCK_DGRAM, "fb00::1", CLIENT_PORT, NULL);
+	if (!ASSERT_OK_FD(cfd, "start client"))
+		goto close_server;
+
+	close_netns(nstoken);
+	nstoken = NULL;
+
+	/* Send a packet larger than MTU */
+	server_addr.sin6_family = AF_INET6;
+	server_addr.sin6_port = htons(SERVER_PORT);
+	if (!ASSERT_EQ(inet_pton(AF_INET6, "fb00::6", &server_addr.sin6_addr), 1,
+		       "build target addr"))
+		goto close_client;
+
+	bytes = sendto(cfd, foobar, sizeof(foobar), 0,
+		       (struct sockaddr *)&server_addr, sizeof(server_addr));
+	if (!ASSERT_EQ(bytes, sizeof(foobar), "send packet"))
+		goto close_client;
+
+	/* Verify we received all expected bytes */
+	bytes = read(sfd, buf, sizeof(buf));
+	if (!ASSERT_EQ(bytes, sizeof(buf), "receive packet"))
+		goto close_client;
+	ASSERT_STREQ(buf, foobar, "check udp packet");
+
+close_client:
+	close(cfd);
+close_server:
+	close(sfd);
+close_netns:
+	close_netns(nstoken);
+
+out:
+	cleanup();
+}

tools/testing/selftests/bpf/prog_tests/netns_cookie.c

@@ -33,20 +33,25 @@ void test_netns_cookie(void)
 
 	skel->links.get_netns_cookie_sockops = bpf_program__attach_cgroup(
 		skel->progs.get_netns_cookie_sockops, cgroup_fd);
-	if (!ASSERT_OK_PTR(skel->links.get_netns_cookie_sockops, "prog_attach"))
+	if (!ASSERT_OK_PTR(skel->links.get_netns_cookie_sockops, "prog_attach_sockops"))
 		goto done;
 
 	verdict = bpf_program__fd(skel->progs.get_netns_cookie_sk_msg);
 	map = bpf_map__fd(skel->maps.sock_map);
 	err = bpf_prog_attach(verdict, map, BPF_SK_MSG_VERDICT, 0);
-	if (!ASSERT_OK(err, "prog_attach"))
+	if (!ASSERT_OK(err, "prog_attach_sk_msg"))
 		goto done;
 
 	tc_fd = bpf_program__fd(skel->progs.get_netns_cookie_tcx);
 	err = bpf_prog_attach_opts(tc_fd, loopback, BPF_TCX_INGRESS, &opta);
-	if (!ASSERT_OK(err, "prog_attach"))
+	if (!ASSERT_OK(err, "prog_attach_tcx"))
 		goto done;
 
+	skel->links.get_netns_cookie_cgroup_skb = bpf_program__attach_cgroup(
+		skel->progs.get_netns_cookie_cgroup_skb, cgroup_fd);
+	if (!ASSERT_OK_PTR(skel->links.get_netns_cookie_cgroup_skb, "prog_attach_cgroup_skb"))
+		goto cleanup_tc;
+
 	server_fd = start_server(AF_INET6, SOCK_STREAM, "::1", 0, 0);
 	if (CHECK(server_fd < 0, "start_server", "errno %d\n", errno))
 		goto cleanup_tc;
@@ -69,16 +74,18 @@ void test_netns_cookie(void)
 	if (!ASSERT_OK(err, "getsockopt"))
 		goto cleanup_tc;
 
-	ASSERT_EQ(val, cookie_expected_value, "cookie_value");
+	ASSERT_EQ(val, cookie_expected_value, "cookie_value_sockops");
 
 	err = bpf_map_lookup_elem(bpf_map__fd(skel->maps.sk_msg_netns_cookies),
 				  &client_fd, &val);
 	if (!ASSERT_OK(err, "map_lookup(sk_msg_netns_cookies)"))
 		goto cleanup_tc;
 
-	ASSERT_EQ(val, cookie_expected_value, "cookie_value");
-	ASSERT_EQ(skel->bss->tcx_init_netns_cookie, cookie_expected_value, "cookie_value");
-	ASSERT_EQ(skel->bss->tcx_netns_cookie, cookie_expected_value, "cookie_value");
+	ASSERT_EQ(val, cookie_expected_value, "cookie_value_sk_msg");
+	ASSERT_EQ(skel->bss->tcx_init_netns_cookie, cookie_expected_value, "cookie_value_init_tcx");
+	ASSERT_EQ(skel->bss->tcx_netns_cookie, cookie_expected_value, "cookie_value_tcx");
+	ASSERT_EQ(skel->bss->cgroup_skb_init_netns_cookie, cookie_expected_value, "cookie_value_init_cgroup_skb");
+	ASSERT_EQ(skel->bss->cgroup_skb_netns_cookie, cookie_expected_value, "cookie_value_cgroup_skb");
 
 cleanup_tc:
 	err = bpf_prog_detach_opts(tc_fd, loopback, BPF_TCX_INGRESS, &optd);

tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c

@@ -200,41 +200,28 @@ static void test_ns_current_pid_tgid_new_ns(int (*fn)(void *), void *arg)
 		return;
 }
 
-static void test_in_netns(int (*fn)(void *), void *arg)
-{
-	struct nstoken *nstoken = NULL;
-
-	SYS(cleanup, "ip netns add ns_current_pid_tgid");
-	SYS(cleanup, "ip -net ns_current_pid_tgid link set dev lo up");
-
-	nstoken = open_netns("ns_current_pid_tgid");
-	if (!ASSERT_OK_PTR(nstoken, "open_netns"))
-		goto cleanup;
-
-	test_ns_current_pid_tgid_new_ns(fn, arg);
-
-cleanup:
-	if (nstoken)
-		close_netns(nstoken);
-	SYS_NOFAIL("ip netns del ns_current_pid_tgid");
-}
-
 /* TODO: use a different tracepoint */
-void serial_test_ns_current_pid_tgid(void)
+void serial_test_current_pid_tgid(void)
 {
 	if (test__start_subtest("root_ns_tp"))
 		test_current_pid_tgid_tp(NULL);
 	if (test__start_subtest("new_ns_tp"))
 		test_ns_current_pid_tgid_new_ns(test_current_pid_tgid_tp, NULL);
-	if (test__start_subtest("new_ns_cgrp")) {
-		int cgroup_fd = -1;
-
-		cgroup_fd = test__join_cgroup("/sock_addr");
-		if (ASSERT_GE(cgroup_fd, 0, "join_cgroup")) {
-			test_in_netns(test_current_pid_tgid_cgrp, &cgroup_fd);
-			close(cgroup_fd);
-		}
-	}
-	if (test__start_subtest("new_ns_sk_msg"))
-		test_in_netns(test_current_pid_tgid_sk_msg, NULL);
 }
+
+void test_ns_current_pid_tgid_cgrp(void)
+{
+	int cgroup_fd = test__join_cgroup("/sock_addr");
+
+	if (ASSERT_OK_FD(cgroup_fd, "join_cgroup")) {
+		test_ns_current_pid_tgid_new_ns(test_current_pid_tgid_cgrp, &cgroup_fd);
+		close(cgroup_fd);
+	}
+}
+
+void test_ns_current_pid_tgid_sk_msg(void)
+{
+	test_ns_current_pid_tgid_new_ns(test_current_pid_tgid_sk_msg, NULL);
+}
+
+

tools/testing/selftests/bpf/prog_tests/prepare.c

@@ -0,0 +1,99 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta */
+
+#include <test_progs.h>
+#include <network_helpers.h>
+#include "prepare.skel.h"
+
+static bool check_prepared(struct bpf_object *obj)
+{
+	bool is_prepared = true;
+	const struct bpf_map *map;
+
+	bpf_object__for_each_map(map, obj) {
+		if (bpf_map__fd(map) < 0)
+			is_prepared = false;
+	}
+
+	return is_prepared;
+}
+
+static void test_prepare_no_load(void)
+{
+	struct prepare *skel;
+	int err;
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		    .data_in = &pkt_v4,
+		    .data_size_in = sizeof(pkt_v4),
+	);
+
+	skel = prepare__open();
+	if (!ASSERT_OK_PTR(skel, "prepare__open"))
+		return;
+
+	if (!ASSERT_FALSE(check_prepared(skel->obj), "not check_prepared"))
+		goto cleanup;
+
+	err = bpf_object__prepare(skel->obj);
+
+	if (!ASSERT_TRUE(check_prepared(skel->obj), "check_prepared"))
+		goto cleanup;
+
+	if (!ASSERT_OK(err, "bpf_object__prepare"))
+		goto cleanup;
+
+cleanup:
+	prepare__destroy(skel);
+}
+
+static void test_prepare_load(void)
+{
+	struct prepare *skel;
+	int err, prog_fd;
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		    .data_in = &pkt_v4,
+		    .data_size_in = sizeof(pkt_v4),
+	);
+
+	skel = prepare__open();
+	if (!ASSERT_OK_PTR(skel, "prepare__open"))
+		return;
+
+	if (!ASSERT_FALSE(check_prepared(skel->obj), "not check_prepared"))
+		goto cleanup;
+
+	err = bpf_object__prepare(skel->obj);
+	if (!ASSERT_OK(err, "bpf_object__prepare"))
+		goto cleanup;
+
+	err = prepare__load(skel);
+	if (!ASSERT_OK(err, "prepare__load"))
+		goto cleanup;
+
+	if (!ASSERT_TRUE(check_prepared(skel->obj), "check_prepared"))
+		goto cleanup;
+
+	prog_fd = bpf_program__fd(skel->progs.program);
+	if (!ASSERT_GE(prog_fd, 0, "prog_fd"))
+		goto cleanup;
+
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	if (!ASSERT_OK(err, "test_run_opts err"))
+		goto cleanup;
+
+	if (!ASSERT_OK(topts.retval, "test_run_opts retval"))
+		goto cleanup;
+
+	ASSERT_EQ(skel->bss->err, 0, "err");
+
+cleanup:
+	prepare__destroy(skel);
+}
+
+void test_prepare(void)
+{
+	if (test__start_subtest("prepare_load"))
+		test_prepare_load();
+	if (test__start_subtest("prepare_no_load"))
+		test_prepare_no_load();
+}

tools/testing/selftests/bpf/prog_tests/pro_epilogue.c

@@ -6,6 +6,7 @@
 #include "epilogue_tailcall.skel.h"
 #include "pro_epilogue_goto_start.skel.h"
 #include "epilogue_exit.skel.h"
+#include "pro_epilogue_with_kfunc.skel.h"
 
 struct st_ops_args {
 	__u64 a;
@@ -55,6 +56,7 @@ void test_pro_epilogue(void)
 	RUN_TESTS(pro_epilogue);
 	RUN_TESTS(pro_epilogue_goto_start);
 	RUN_TESTS(epilogue_exit);
+	RUN_TESTS(pro_epilogue_with_kfunc);
 	if (test__start_subtest("tailcall"))
 		test_tailcall();
 }

tools/testing/selftests/bpf/prog_tests/rcu_read_lock.c

@@ -81,6 +81,9 @@ static const char * const inproper_region_tests[] = {
 	"nested_rcu_region",
 	"rcu_read_lock_global_subprog_lock",
 	"rcu_read_lock_global_subprog_unlock",
+	"rcu_read_lock_sleepable_helper_global_subprog",
+	"rcu_read_lock_sleepable_kfunc_global_subprog",
+	"rcu_read_lock_sleepable_global_subprog_indirect",
 };
 
 static void test_inproper_region(void)

tools/testing/selftests/bpf/prog_tests/read_vsyscall.c

@@ -24,6 +24,7 @@ struct read_ret_desc {
 	{ .name = "copy_from_user", .ret = -EFAULT },
 	{ .name = "copy_from_user_task", .ret = -EFAULT },
 	{ .name = "copy_from_user_str", .ret = -EFAULT },
+	{ .name = "copy_from_user_task_str", .ret = -EFAULT },
 };
 
 void test_read_vsyscall(void)

tools/testing/selftests/bpf/prog_tests/setget_sockopt.c

@@ -202,7 +202,7 @@ err_out:
 void test_setget_sockopt(void)
 {
 	cg_fd = test__join_cgroup(CG_NAME);
-	if (cg_fd < 0)
+	if (!ASSERT_OK_FD(cg_fd, "join cgroup"))
 		return;
 
 	if (create_netns())

tools/testing/selftests/bpf/prog_tests/spin_lock.c

@@ -50,6 +50,9 @@ static struct {
 	{ "lock_id_mismatch_innermapval_mapval", "bpf_spin_unlock of different lock" },
 	{ "lock_global_subprog_call1", "global function calls are not allowed while holding a lock" },
 	{ "lock_global_subprog_call2", "global function calls are not allowed while holding a lock" },
+	{ "lock_global_sleepable_helper_subprog", "global function calls are not allowed while holding a lock" },
+	{ "lock_global_sleepable_kfunc_subprog", "global function calls are not allowed while holding a lock" },
+	{ "lock_global_sleepable_subprog_indirect", "global function calls are not allowed while holding a lock" },
 };
 
 static int match_regex(const char *pattern, const char *string)

tools/testing/selftests/bpf/prog_tests/summarization.c

@@ -0,0 +1,144 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "bpf/libbpf.h"
+#include "summarization_freplace.skel.h"
+#include "summarization.skel.h"
+#include <test_progs.h>
+
+static void print_verifier_log(const char *log)
+{
+	if (env.verbosity >= VERBOSE_VERY)
+		fprintf(stdout, "VERIFIER LOG:\n=============\n%s=============\n", log);
+}
+
+static void test_aux(const char *main_prog_name,
+		     const char *to_be_replaced,
+		     const char *replacement,
+		     bool expect_load,
+		     const char *err_msg)
+{
+	struct summarization_freplace *freplace = NULL;
+	struct bpf_program *freplace_prog = NULL;
+	struct bpf_program *main_prog = NULL;
+	LIBBPF_OPTS(bpf_object_open_opts, opts);
+	struct summarization *main = NULL;
+	char log[16*1024];
+	int err;
+
+	opts.kernel_log_buf = log;
+	opts.kernel_log_size = sizeof(log);
+	if (env.verbosity >= VERBOSE_SUPER)
+		opts.kernel_log_level = 1 | 2 | 4;
+	main = summarization__open_opts(&opts);
+	if (!ASSERT_OK_PTR(main, "summarization__open"))
+		goto out;
+	main_prog = bpf_object__find_program_by_name(main->obj, main_prog_name);
+	if (!ASSERT_OK_PTR(main_prog, "main_prog"))
+		goto out;
+	bpf_program__set_autoload(main_prog, true);
+	err = summarization__load(main);
+	print_verifier_log(log);
+	if (!ASSERT_OK(err, "summarization__load"))
+		goto out;
+	freplace = summarization_freplace__open_opts(&opts);
+	if (!ASSERT_OK_PTR(freplace, "summarization_freplace__open"))
+		goto out;
+	freplace_prog = bpf_object__find_program_by_name(freplace->obj, replacement);
+	if (!ASSERT_OK_PTR(freplace_prog, "freplace_prog"))
+		goto out;
+	bpf_program__set_autoload(freplace_prog, true);
+	bpf_program__set_autoattach(freplace_prog, true);
+	bpf_program__set_attach_target(freplace_prog,
+				       bpf_program__fd(main_prog),
+				       to_be_replaced);
+	err = summarization_freplace__load(freplace);
+	print_verifier_log(log);
+
+	/* The might_sleep extension doesn't work yet as sleepable calls are not
+	 * allowed, but preserve the check in case it's supported later and then
+	 * this particular combination can be enabled.
+	 */
+	if (!strcmp("might_sleep", replacement) && err) {
+		ASSERT_HAS_SUBSTR(log, "helper call might sleep in a non-sleepable prog", "error log");
+		ASSERT_EQ(err, -EINVAL, "err");
+		test__skip();
+		goto out;
+	}
+
+	if (expect_load) {
+		ASSERT_OK(err, "summarization_freplace__load");
+	} else {
+		ASSERT_ERR(err, "summarization_freplace__load");
+		ASSERT_HAS_SUBSTR(log, err_msg, "error log");
+	}
+
+out:
+	summarization_freplace__destroy(freplace);
+	summarization__destroy(main);
+}
+
+/* There are two global subprograms in both summarization.skel.h:
+ * - one changes packet data;
+ * - another does not.
+ * It is ok to freplace subprograms that change packet data with those
+ * that either do or do not. It is only ok to freplace subprograms
+ * that do not change packet data with those that do not as well.
+ * The below tests check outcomes for each combination of such freplace.
+ * Also test a case when main subprogram itself is replaced and is a single
+ * subprogram in a program.
+ *
+ * This holds for might_sleep programs. It is ok to replace might_sleep with
+ * might_sleep and with does_not_sleep, but does_not_sleep cannot be replaced
+ * with might_sleep.
+ */
+void test_summarization_freplace(void)
+{
+	struct {
+		const char *main;
+		const char *to_be_replaced;
+		bool has_side_effect;
+	} mains[2][4] = {
+		{
+			{ "main_changes_with_subprogs",		"changes_pkt_data",	    true },
+			{ "main_changes_with_subprogs",		"does_not_change_pkt_data", false },
+			{ "main_changes",			"main_changes",             true },
+			{ "main_does_not_change",		"main_does_not_change",     false },
+		},
+		{
+			{ "main_might_sleep_with_subprogs",	"might_sleep",		    true },
+			{ "main_might_sleep_with_subprogs",	"does_not_sleep",	    false },
+			{ "main_might_sleep",			"main_might_sleep",	    true },
+			{ "main_does_not_sleep",		"main_does_not_sleep",	    false },
+		},
+	};
+	const char *pkt_err = "Extension program changes packet data";
+	const char *slp_err = "Extension program may sleep";
+	struct {
+		const char *func;
+		bool has_side_effect;
+		const char *err_msg;
+	} replacements[2][2] = {
+		{
+			{ "changes_pkt_data",	      true,	pkt_err },
+			{ "does_not_change_pkt_data", false,	pkt_err },
+		},
+		{
+			{ "might_sleep",	      true,	slp_err },
+			{ "does_not_sleep",	      false,	slp_err },
+		},
+	};
+	char buf[64];
+
+	for (int t = 0; t < 2; t++) {
+		for (int i = 0; i < ARRAY_SIZE(mains); ++i) {
+			for (int j = 0; j < ARRAY_SIZE(replacements); ++j) {
+				snprintf(buf, sizeof(buf), "%s_with_%s",
+					 mains[t][i].to_be_replaced, replacements[t][j].func);
+				if (!test__start_subtest(buf))
+					continue;
+				test_aux(mains[t][i].main, mains[t][i].to_be_replaced, replacements[t][j].func,
+					 mains[t][i].has_side_effect || !replacements[t][j].has_side_effect,
+					 replacements[t][j].err_msg);
+			}
+		}
+	}
+}

tools/testing/selftests/bpf/prog_tests/tailcalls.c

@@ -1600,6 +1600,7 @@ static void test_tailcall_bpf2bpf_freplace(void)
 		goto out;
 
 	err = bpf_link__destroy(freplace_link);
+	freplace_link = NULL;
 	if (!ASSERT_OK(err, "destroy link"))
 		goto out;
 

tools/testing/selftests/bpf/prog_tests/tc_links.c

@@ -13,7 +13,7 @@
 #include "netlink_helpers.h"
 #include "tc_helpers.h"
 
-void serial_test_tc_links_basic(void)
+void test_ns_tc_links_basic(void)
 {
 	LIBBPF_OPTS(bpf_prog_query_opts, optq);
 	LIBBPF_OPTS(bpf_tcx_opts, optl);
@@ -260,7 +260,7 @@ cleanup:
 	assert_mprog_count(target, 0);
 }
 
-void serial_test_tc_links_before(void)
+void test_ns_tc_links_before(void)
 {
 	test_tc_links_before_target(BPF_TCX_INGRESS);
 	test_tc_links_before_target(BPF_TCX_EGRESS);
@@ -414,7 +414,7 @@ cleanup:
 	assert_mprog_count(target, 0);
 }
 
-void serial_test_tc_links_after(void)
+void test_ns_tc_links_after(void)
 {
 	test_tc_links_after_target(BPF_TCX_INGRESS);
 	test_tc_links_after_target(BPF_TCX_EGRESS);
@@ -514,7 +514,7 @@ cleanup:
 	assert_mprog_count(target, 0);
 }
 
-void serial_test_tc_links_revision(void)
+void test_ns_tc_links_revision(void)
 {
 	test_tc_links_revision_target(BPF_TCX_INGRESS);
 	test_tc_links_revision_target(BPF_TCX_EGRESS);
@@ -618,7 +618,7 @@ cleanup:
 	assert_mprog_count(target, 0);
 }
 
-void serial_test_tc_links_chain_classic(void)
+void test_ns_tc_links_chain_classic(void)
 {
 	test_tc_chain_classic(BPF_TCX_INGRESS, false);
 	test_tc_chain_classic(BPF_TCX_EGRESS, false);
@@ -846,7 +846,7 @@ cleanup:
 	assert_mprog_count(target, 0);
 }
 
-void serial_test_tc_links_replace(void)
+void test_ns_tc_links_replace(void)
 {
 	test_tc_links_replace_target(BPF_TCX_INGRESS);
 	test_tc_links_replace_target(BPF_TCX_EGRESS);
@@ -1158,7 +1158,7 @@ cleanup:
 	assert_mprog_count(target, 0);
 }
 
-void serial_test_tc_links_invalid(void)
+void test_ns_tc_links_invalid(void)
 {
 	test_tc_links_invalid_target(BPF_TCX_INGRESS);
 	test_tc_links_invalid_target(BPF_TCX_EGRESS);
@@ -1314,7 +1314,7 @@ cleanup:
 	assert_mprog_count(target, 0);
 }
 
-void serial_test_tc_links_prepend(void)
+void test_ns_tc_links_prepend(void)
 {
 	test_tc_links_prepend_target(BPF_TCX_INGRESS);
 	test_tc_links_prepend_target(BPF_TCX_EGRESS);
@@ -1470,7 +1470,7 @@ cleanup:
 	assert_mprog_count(target, 0);
 }
 
-void serial_test_tc_links_append(void)
+void test_ns_tc_links_append(void)
 {
 	test_tc_links_append_target(BPF_TCX_INGRESS);
 	test_tc_links_append_target(BPF_TCX_EGRESS);
@@ -1568,7 +1568,7 @@ cleanup:
 	ASSERT_EQ(if_nametoindex("tcx_opts2"), 0, "dev2_removed");
 }
 
-void serial_test_tc_links_dev_cleanup(void)
+void test_ns_tc_links_dev_cleanup(void)
 {
 	test_tc_links_dev_cleanup_target(BPF_TCX_INGRESS);
 	test_tc_links_dev_cleanup_target(BPF_TCX_EGRESS);
@@ -1672,7 +1672,7 @@ cleanup:
 	test_tc_link__destroy(skel);
 }
 
-void serial_test_tc_links_chain_mixed(void)
+void test_ns_tc_links_chain_mixed(void)
 {
 	test_tc_chain_mixed(BPF_TCX_INGRESS);
 	test_tc_chain_mixed(BPF_TCX_EGRESS);
@@ -1782,7 +1782,7 @@ cleanup:
 	assert_mprog_count(target, 0);
 }
 
-void serial_test_tc_links_ingress(void)
+void test_ns_tc_links_ingress(void)
 {
 	test_tc_links_ingress(BPF_TCX_INGRESS, true, true);
 	test_tc_links_ingress(BPF_TCX_INGRESS, true, false);
@@ -1823,7 +1823,7 @@ static int qdisc_replace(int ifindex, const char *kind, bool block)
 	return err;
 }
 
-void serial_test_tc_links_dev_chain0(void)
+void test_ns_tc_links_dev_chain0(void)
 {
 	int err, ifindex;
 
@@ -1955,7 +1955,7 @@ cleanup:
 	ASSERT_EQ(if_nametoindex("tcx_opts2"), 0, "dev2_removed");
 }
 
-void serial_test_tc_links_dev_mixed(void)
+void test_ns_tc_links_dev_mixed(void)
 {
 	test_tc_links_dev_mixed(BPF_TCX_INGRESS);
 	test_tc_links_dev_mixed(BPF_TCX_EGRESS);

tools/testing/selftests/bpf/prog_tests/tc_opts.c

@@ -10,7 +10,7 @@
 #include "test_tc_link.skel.h"
 #include "tc_helpers.h"
 
-void serial_test_tc_opts_basic(void)
+void test_ns_tc_opts_basic(void)
 {
 	LIBBPF_OPTS(bpf_prog_attach_opts, opta);
 	LIBBPF_OPTS(bpf_prog_detach_opts, optd);
@@ -254,7 +254,7 @@ cleanup:
 	test_tc_link__destroy(skel);
 }
 
-void serial_test_tc_opts_before(void)
+void test_ns_tc_opts_before(void)
 {
 	test_tc_opts_before_target(BPF_TCX_INGRESS);
 	test_tc_opts_before_target(BPF_TCX_EGRESS);
@@ -445,7 +445,7 @@ cleanup:
 	test_tc_link__destroy(skel);
 }
 
-void serial_test_tc_opts_after(void)
+void test_ns_tc_opts_after(void)
 {
 	test_tc_opts_after_target(BPF_TCX_INGRESS);
 	test_tc_opts_after_target(BPF_TCX_EGRESS);
@@ -554,7 +554,7 @@ cleanup:
 	test_tc_link__destroy(skel);
 }
 
-void serial_test_tc_opts_revision(void)
+void test_ns_tc_opts_revision(void)
 {
 	test_tc_opts_revision_target(BPF_TCX_INGRESS);
 	test_tc_opts_revision_target(BPF_TCX_EGRESS);
@@ -655,7 +655,7 @@ cleanup:
 	assert_mprog_count(target, 0);
 }
 
-void serial_test_tc_opts_chain_classic(void)
+void test_ns_tc_opts_chain_classic(void)
 {
 	test_tc_chain_classic(BPF_TCX_INGRESS, false);
 	test_tc_chain_classic(BPF_TCX_EGRESS, false);
@@ -864,7 +864,7 @@ cleanup:
 	test_tc_link__destroy(skel);
 }
 
-void serial_test_tc_opts_replace(void)
+void test_ns_tc_opts_replace(void)
 {
 	test_tc_opts_replace_target(BPF_TCX_INGRESS);
 	test_tc_opts_replace_target(BPF_TCX_EGRESS);
@@ -1017,7 +1017,7 @@ cleanup:
 	test_tc_link__destroy(skel);
 }
 
-void serial_test_tc_opts_invalid(void)
+void test_ns_tc_opts_invalid(void)
 {
 	test_tc_opts_invalid_target(BPF_TCX_INGRESS);
 	test_tc_opts_invalid_target(BPF_TCX_EGRESS);
@@ -1157,7 +1157,7 @@ cleanup:
 	test_tc_link__destroy(skel);
 }
 
-void serial_test_tc_opts_prepend(void)
+void test_ns_tc_opts_prepend(void)
 {
 	test_tc_opts_prepend_target(BPF_TCX_INGRESS);
 	test_tc_opts_prepend_target(BPF_TCX_EGRESS);
@@ -1297,7 +1297,7 @@ cleanup:
 	test_tc_link__destroy(skel);
 }
 
-void serial_test_tc_opts_append(void)
+void test_ns_tc_opts_append(void)
 {
 	test_tc_opts_append_target(BPF_TCX_INGRESS);
 	test_tc_opts_append_target(BPF_TCX_EGRESS);
@@ -1387,7 +1387,7 @@ cleanup:
 	ASSERT_EQ(if_nametoindex("tcx_opts2"), 0, "dev2_removed");
 }
 
-void serial_test_tc_opts_dev_cleanup(void)
+void test_ns_tc_opts_dev_cleanup(void)
 {
 	test_tc_opts_dev_cleanup_target(BPF_TCX_INGRESS);
 	test_tc_opts_dev_cleanup_target(BPF_TCX_EGRESS);
@@ -1563,7 +1563,7 @@ cleanup:
 	assert_mprog_count(target, 0);
 }
 
-void serial_test_tc_opts_mixed(void)
+void test_ns_tc_opts_mixed(void)
 {
 	test_tc_opts_mixed_target(BPF_TCX_INGRESS);
 	test_tc_opts_mixed_target(BPF_TCX_EGRESS);
@@ -1642,7 +1642,7 @@ cleanup:
 	assert_mprog_count(target, 0);
 }
 
-void serial_test_tc_opts_demixed(void)
+void test_ns_tc_opts_demixed(void)
 {
 	test_tc_opts_demixed_target(BPF_TCX_INGRESS);
 	test_tc_opts_demixed_target(BPF_TCX_EGRESS);
@@ -1813,7 +1813,7 @@ cleanup:
 	test_tc_link__destroy(skel);
 }
 
-void serial_test_tc_opts_detach(void)
+void test_ns_tc_opts_detach(void)
 {
 	test_tc_opts_detach_target(BPF_TCX_INGRESS);
 	test_tc_opts_detach_target(BPF_TCX_EGRESS);
@@ -2020,7 +2020,7 @@ cleanup:
 	test_tc_link__destroy(skel);
 }
 
-void serial_test_tc_opts_detach_before(void)
+void test_ns_tc_opts_detach_before(void)
 {
 	test_tc_opts_detach_before_target(BPF_TCX_INGRESS);
 	test_tc_opts_detach_before_target(BPF_TCX_EGRESS);
@@ -2236,7 +2236,7 @@ cleanup:
 	test_tc_link__destroy(skel);
 }
 
-void serial_test_tc_opts_detach_after(void)
+void test_ns_tc_opts_detach_after(void)
 {
 	test_tc_opts_detach_after_target(BPF_TCX_INGRESS);
 	test_tc_opts_detach_after_target(BPF_TCX_EGRESS);
@@ -2265,7 +2265,7 @@ static void test_tc_opts_delete_empty(int target, bool chain_tc_old)
 	assert_mprog_count(target, 0);
 }
 
-void serial_test_tc_opts_delete_empty(void)
+void test_ns_tc_opts_delete_empty(void)
 {
 	test_tc_opts_delete_empty(BPF_TCX_INGRESS, false);
 	test_tc_opts_delete_empty(BPF_TCX_EGRESS, false);
@@ -2372,7 +2372,7 @@ cleanup:
 	test_tc_link__destroy(skel);
 }
 
-void serial_test_tc_opts_chain_mixed(void)
+void test_ns_tc_opts_chain_mixed(void)
 {
 	test_tc_chain_mixed(BPF_TCX_INGRESS);
 	test_tc_chain_mixed(BPF_TCX_EGRESS);
@@ -2446,7 +2446,7 @@ cleanup:
 	ASSERT_EQ(if_nametoindex("tcx_opts2"), 0, "dev2_removed");
 }
 
-void serial_test_tc_opts_max(void)
+void test_ns_tc_opts_max(void)
 {
 	test_tc_opts_max_target(BPF_TCX_INGRESS, 0, false);
 	test_tc_opts_max_target(BPF_TCX_EGRESS, 0, false);
@@ -2748,7 +2748,7 @@ cleanup:
 	test_tc_link__destroy(skel);
 }
 
-void serial_test_tc_opts_query(void)
+void test_ns_tc_opts_query(void)
 {
 	test_tc_opts_query_target(BPF_TCX_INGRESS);
 	test_tc_opts_query_target(BPF_TCX_EGRESS);
@@ -2807,7 +2807,7 @@ cleanup:
 	test_tc_link__destroy(skel);
 }
 
-void serial_test_tc_opts_query_attach(void)
+void test_ns_tc_opts_query_attach(void)
 {
 	test_tc_opts_query_attach_target(BPF_TCX_INGRESS);
 	test_tc_opts_query_attach_target(BPF_TCX_EGRESS);

tools/testing/selftests/bpf/prog_tests/test_struct_ops_kptr_return.c

@@ -0,0 +1,16 @@
+#include <test_progs.h>
+
+#include "struct_ops_kptr_return.skel.h"
+#include "struct_ops_kptr_return_fail__wrong_type.skel.h"
+#include "struct_ops_kptr_return_fail__invalid_scalar.skel.h"
+#include "struct_ops_kptr_return_fail__nonzero_offset.skel.h"
+#include "struct_ops_kptr_return_fail__local_kptr.skel.h"
+
+void test_struct_ops_kptr_return(void)
+{
+	RUN_TESTS(struct_ops_kptr_return);
+	RUN_TESTS(struct_ops_kptr_return_fail__wrong_type);
+	RUN_TESTS(struct_ops_kptr_return_fail__invalid_scalar);
+	RUN_TESTS(struct_ops_kptr_return_fail__nonzero_offset);
+	RUN_TESTS(struct_ops_kptr_return_fail__local_kptr);
+}

tools/testing/selftests/bpf/prog_tests/test_struct_ops_refcounted.c

@@ -0,0 +1,14 @@
+#include <test_progs.h>
+
+#include "struct_ops_refcounted.skel.h"
+#include "struct_ops_refcounted_fail__ref_leak.skel.h"
+#include "struct_ops_refcounted_fail__global_subprog.skel.h"
+#include "struct_ops_refcounted_fail__tail_call.skel.h"
+
+void test_struct_ops_refcounted(void)
+{
+	RUN_TESTS(struct_ops_refcounted);
+	RUN_TESTS(struct_ops_refcounted_fail__ref_leak);
+	RUN_TESTS(struct_ops_refcounted_fail__global_subprog);
+	RUN_TESTS(struct_ops_refcounted_fail__tail_call);
+}

tools/testing/selftests/bpf/prog_tests/test_tunnel.c

@@ -71,6 +71,8 @@
 #define IP4_ADDR2_VETH1 "172.16.1.20"
 #define IP4_ADDR_TUNL_DEV0 "10.1.1.100"
 #define IP4_ADDR_TUNL_DEV1 "10.1.1.200"
+#define IP6_ADDR_TUNL_DEV0 "fc80::100"
+#define IP6_ADDR_TUNL_DEV1 "fc80::200"
 
 #define IP6_ADDR_VETH0 "::11"
 #define IP6_ADDR1_VETH1 "::22"
@@ -98,6 +100,27 @@
 #define XFRM_SPI_IN_TO_OUT 0x1
 #define XFRM_SPI_OUT_TO_IN 0x2
 
+#define GRE_TUNL_DEV0 "gre00"
+#define GRE_TUNL_DEV1 "gre11"
+
+#define IP6GRE_TUNL_DEV0 "ip6gre00"
+#define IP6GRE_TUNL_DEV1 "ip6gre11"
+
+#define ERSPAN_TUNL_DEV0 "erspan00"
+#define ERSPAN_TUNL_DEV1 "erspan11"
+
+#define IP6ERSPAN_TUNL_DEV0 "ip6erspan00"
+#define IP6ERSPAN_TUNL_DEV1 "ip6erspan11"
+
+#define GENEVE_TUNL_DEV0 "geneve00"
+#define GENEVE_TUNL_DEV1 "geneve11"
+
+#define IP6GENEVE_TUNL_DEV0 "ip6geneve00"
+#define IP6GENEVE_TUNL_DEV1 "ip6geneve11"
+
+#define IP6TNL_TUNL_DEV0 "ip6tnl00"
+#define IP6TNL_TUNL_DEV1 "ip6tnl11"
+
 #define PING_ARGS "-i 0.01 -c 3 -w 10 -q"
 
 static int config_device(void)
@@ -216,6 +239,18 @@ fail:
 	return -1;
 }
 
+static int set_ipv4_addr(const char *dev0, const char *dev1)
+{
+	SYS(fail, "ip -n at_ns0 link set dev %s up", dev0);
+	SYS(fail, "ip -n at_ns0 addr add dev %s %s/24", dev0, IP4_ADDR_TUNL_DEV0);
+	SYS(fail, "ip link set dev %s up", dev1);
+	SYS(fail, "ip addr add dev %s %s/24", dev1, IP4_ADDR_TUNL_DEV1);
+
+	return 0;
+fail:
+	return 1;
+}
+
 static int add_ipip_tunnel(enum ipip_encap encap)
 {
 	int err;
@@ -356,6 +391,99 @@ static void delete_xfrm_tunnel(void)
 		   IP4_ADDR1_VETH1, IP4_ADDR_VETH0, XFRM_SPI_OUT_TO_IN);
 }
 
+static int add_ipv4_tunnel(const char *dev0, const char *dev1,
+			   const char *type, const char *opt)
+{
+	if (!type || !opt || !dev0 || !dev1)
+		return -1;
+
+	SYS(fail, "ip -n at_ns0 link add dev %s type %s %s local %s remote %s",
+	    dev0, type, opt, IP4_ADDR_VETH0, IP4_ADDR1_VETH1);
+
+	SYS(fail, "ip link add dev %s type %s external", dev1, type);
+
+	return set_ipv4_addr(dev0, dev1);
+fail:
+	return -1;
+}
+
+static void delete_tunnel(const char *dev0, const char *dev1)
+{
+	if (!dev0 || !dev1)
+		return;
+
+	SYS_NOFAIL("ip netns exec at_ns0 ip link delete dev %s", dev0);
+	SYS_NOFAIL("ip link delete dev %s", dev1);
+}
+
+static int set_ipv6_addr(const char *dev0, const char *dev1)
+{
+	/* disable IPv6 DAD because it might take too long and fail tests */
+	SYS(fail, "ip -n at_ns0 addr add %s/96 dev veth0 nodad", IP6_ADDR_VETH0);
+	SYS(fail, "ip -n at_ns0 link set dev veth0 up");
+	SYS(fail, "ip addr add %s/96 dev veth1 nodad", IP6_ADDR1_VETH1);
+	SYS(fail, "ip link set dev veth1 up");
+
+	SYS(fail, "ip -n at_ns0 addr add dev %s %s/24", dev0, IP4_ADDR_TUNL_DEV0);
+	SYS(fail, "ip -n at_ns0 addr add dev %s %s/96 nodad", dev0, IP6_ADDR_TUNL_DEV0);
+	SYS(fail, "ip -n at_ns0 link set dev %s up", dev0);
+
+	SYS(fail, "ip addr add dev %s %s/24", dev1, IP4_ADDR_TUNL_DEV1);
+	SYS(fail, "ip addr add dev %s %s/96 nodad", dev1, IP6_ADDR_TUNL_DEV1);
+	SYS(fail, "ip link set dev %s up", dev1);
+	return 0;
+fail:
+	return 1;
+}
+
+static int add_ipv6_tunnel(const char *dev0, const char *dev1,
+			   const char *type, const char *opt)
+{
+	if (!type || !opt || !dev0 || !dev1)
+		return -1;
+
+	SYS(fail, "ip -n at_ns0 link add dev %s type %s %s local %s remote %s",
+	    dev0, type, opt, IP6_ADDR_VETH0, IP6_ADDR1_VETH1);
+
+	SYS(fail, "ip link add dev %s type %s external", dev1, type);
+
+	return set_ipv6_addr(dev0, dev1);
+fail:
+	return -1;
+}
+
+static int add_geneve_tunnel(const char *dev0, const char *dev1,
+			     const char *type, const char *opt)
+{
+	if (!type || !opt || !dev0 || !dev1)
+		return -1;
+
+	SYS(fail, "ip -n at_ns0 link add dev %s type %s id 2 %s remote %s",
+	    dev0, type, opt, IP4_ADDR1_VETH1);
+
+	SYS(fail, "ip link add dev %s type %s %s external", dev1, type, opt);
+
+	return set_ipv4_addr(dev0, dev1);
+fail:
+	return -1;
+}
+
+static int add_ip6geneve_tunnel(const char *dev0, const char *dev1,
+			     const char *type, const char *opt)
+{
+	if (!type || !opt || !dev0 || !dev1)
+		return -1;
+
+	SYS(fail, "ip -n at_ns0 link add dev %s type %s id 22 %s remote %s",
+	    dev0, type, opt, IP6_ADDR1_VETH1);
+
+	SYS(fail, "ip link add dev %s type %s %s external", dev1, type, opt);
+
+	return set_ipv6_addr(dev0, dev1);
+fail:
+	return -1;
+}
+
 static int test_ping(int family, const char *addr)
 {
 	SYS(fail, "%s %s %s > /dev/null", ping_command(family), PING_ARGS, addr);
@@ -364,32 +492,76 @@ fail:
 	return -1;
 }
 
-static int attach_tc_prog(struct bpf_tc_hook *hook, int igr_fd, int egr_fd)
+static void ping_dev0(void)
 {
+	/* ping from root namespace test */
+	test_ping(AF_INET, IP4_ADDR_TUNL_DEV0);
+}
+
+static void ping_dev1(void)
+{
+	struct nstoken *nstoken;
+
+	/* ping from at_ns0 namespace test */
+	nstoken = open_netns("at_ns0");
+	if (!ASSERT_OK_PTR(nstoken, "setns"))
+		return;
+
+	test_ping(AF_INET, IP4_ADDR_TUNL_DEV1);
+	close_netns(nstoken);
+}
+
+static void ping6_veth0(void)
+{
+	test_ping(AF_INET6, IP6_ADDR_VETH0);
+}
+
+static void ping6_dev0(void)
+{
+	test_ping(AF_INET6, IP6_ADDR_TUNL_DEV0);
+}
+
+static void ping6_dev1(void)
+{
+	struct nstoken *nstoken;
+
+	/* ping from at_ns0 namespace test */
+	nstoken = open_netns("at_ns0");
+	if (!ASSERT_OK_PTR(nstoken, "setns"))
+		return;
+
+	test_ping(AF_INET, IP6_ADDR_TUNL_DEV1);
+	close_netns(nstoken);
+}
+
+static int attach_tc_prog(int ifindex, int igr_fd, int egr_fd)
+{
+	DECLARE_LIBBPF_OPTS(bpf_tc_hook, hook, .ifindex = ifindex,
+			    .attach_point = BPF_TC_INGRESS | BPF_TC_EGRESS);
 	DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts1, .handle = 1,
 			    .priority = 1, .prog_fd = igr_fd);
 	DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts2, .handle = 1,
 			    .priority = 1, .prog_fd = egr_fd);
 	int ret;
 
-	ret = bpf_tc_hook_create(hook);
+	ret = bpf_tc_hook_create(&hook);
 	if (!ASSERT_OK(ret, "create tc hook"))
 		return ret;
 
 	if (igr_fd >= 0) {
-		hook->attach_point = BPF_TC_INGRESS;
-		ret = bpf_tc_attach(hook, &opts1);
+		hook.attach_point = BPF_TC_INGRESS;
+		ret = bpf_tc_attach(&hook, &opts1);
 		if (!ASSERT_OK(ret, "bpf_tc_attach")) {
-			bpf_tc_hook_destroy(hook);
+			bpf_tc_hook_destroy(&hook);
 			return ret;
 		}
 	}
 
 	if (egr_fd >= 0) {
-		hook->attach_point = BPF_TC_EGRESS;
-		ret = bpf_tc_attach(hook, &opts2);
+		hook.attach_point = BPF_TC_EGRESS;
+		ret = bpf_tc_attach(&hook, &opts2);
 		if (!ASSERT_OK(ret, "bpf_tc_attach")) {
-			bpf_tc_hook_destroy(hook);
+			bpf_tc_hook_destroy(&hook);
 			return ret;
 		}
 	}
@@ -397,6 +569,50 @@ static int attach_tc_prog(struct bpf_tc_hook *hook, int igr_fd, int egr_fd)
 	return 0;
 }
 
+static int generic_attach(const char *dev, int igr_fd, int egr_fd)
+{
+	int ifindex;
+
+	if (!ASSERT_OK_FD(igr_fd, "check ingress fd"))
+		return -1;
+	if (!ASSERT_OK_FD(egr_fd, "check egress fd"))
+		return -1;
+
+	ifindex = if_nametoindex(dev);
+	if (!ASSERT_NEQ(ifindex, 0, "get ifindex"))
+		return -1;
+
+	return attach_tc_prog(ifindex, igr_fd, egr_fd);
+}
+
+static int generic_attach_igr(const char *dev, int igr_fd)
+{
+	int ifindex;
+
+	if (!ASSERT_OK_FD(igr_fd, "check ingress fd"))
+		return -1;
+
+	ifindex = if_nametoindex(dev);
+	if (!ASSERT_NEQ(ifindex, 0, "get ifindex"))
+		return -1;
+
+	return attach_tc_prog(ifindex, igr_fd, -1);
+}
+
+static int generic_attach_egr(const char *dev, int egr_fd)
+{
+	int ifindex;
+
+	if (!ASSERT_OK_FD(egr_fd, "check egress fd"))
+		return -1;
+
+	ifindex = if_nametoindex(dev);
+	if (!ASSERT_NEQ(ifindex, 0, "get ifindex"))
+		return -1;
+
+	return attach_tc_prog(ifindex, -1, egr_fd);
+}
+
 static void test_vxlan_tunnel(void)
 {
 	struct test_tunnel_kern *skel = NULL;
@@ -404,11 +620,9 @@ static void test_vxlan_tunnel(void)
 	int local_ip_map_fd = -1;
 	int set_src_prog_fd, get_src_prog_fd;
 	int set_dst_prog_fd;
-	int key = 0, ifindex = -1;
+	int key = 0;
 	uint local_ip;
 	int err;
-	DECLARE_LIBBPF_OPTS(bpf_tc_hook, tc_hook,
-			    .attach_point = BPF_TC_INGRESS);
 
 	/* add vxlan tunnel */
 	err = add_vxlan_tunnel();
@@ -419,42 +633,22 @@ static void test_vxlan_tunnel(void)
 	skel = test_tunnel_kern__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load"))
 		goto done;
-	ifindex = if_nametoindex(VXLAN_TUNL_DEV1);
-	if (!ASSERT_NEQ(ifindex, 0, "vxlan11 ifindex"))
-		goto done;
-	tc_hook.ifindex = ifindex;
 	get_src_prog_fd = bpf_program__fd(skel->progs.vxlan_get_tunnel_src);
 	set_src_prog_fd = bpf_program__fd(skel->progs.vxlan_set_tunnel_src);
-	if (!ASSERT_GE(get_src_prog_fd, 0, "bpf_program__fd"))
-		goto done;
-	if (!ASSERT_GE(set_src_prog_fd, 0, "bpf_program__fd"))
-		goto done;
-	if (attach_tc_prog(&tc_hook, get_src_prog_fd, set_src_prog_fd))
+	if (generic_attach(VXLAN_TUNL_DEV1, get_src_prog_fd, set_src_prog_fd))
 		goto done;
 
 	/* load and attach bpf prog to veth dev tc hook point */
-	ifindex = if_nametoindex("veth1");
-	if (!ASSERT_NEQ(ifindex, 0, "veth1 ifindex"))
-		goto done;
-	tc_hook.ifindex = ifindex;
 	set_dst_prog_fd = bpf_program__fd(skel->progs.veth_set_outer_dst);
-	if (!ASSERT_GE(set_dst_prog_fd, 0, "bpf_program__fd"))
-		goto done;
-	if (attach_tc_prog(&tc_hook, set_dst_prog_fd, -1))
+	if (generic_attach_igr("veth1", set_dst_prog_fd))
 		goto done;
 
 	/* load and attach prog set_md to tunnel dev tc hook point at_ns0 */
 	nstoken = open_netns("at_ns0");
 	if (!ASSERT_OK_PTR(nstoken, "setns src"))
 		goto done;
-	ifindex = if_nametoindex(VXLAN_TUNL_DEV0);
-	if (!ASSERT_NEQ(ifindex, 0, "vxlan00 ifindex"))
-		goto done;
-	tc_hook.ifindex = ifindex;
 	set_dst_prog_fd = bpf_program__fd(skel->progs.vxlan_set_tunnel_dst);
-	if (!ASSERT_GE(set_dst_prog_fd, 0, "bpf_program__fd"))
-		goto done;
-	if (attach_tc_prog(&tc_hook, -1, set_dst_prog_fd))
+	if (generic_attach_egr(VXLAN_TUNL_DEV0, set_dst_prog_fd))
 		goto done;
 	close_netns(nstoken);
 
@@ -468,9 +662,7 @@ static void test_vxlan_tunnel(void)
 		goto done;
 
 	/* ping test */
-	err = test_ping(AF_INET, IP4_ADDR_TUNL_DEV0);
-	if (!ASSERT_OK(err, "test_ping"))
-		goto done;
+	ping_dev0();
 
 done:
 	/* delete vxlan tunnel */
@@ -488,11 +680,9 @@ static void test_ip6vxlan_tunnel(void)
 	int local_ip_map_fd = -1;
 	int set_src_prog_fd, get_src_prog_fd;
 	int set_dst_prog_fd;
-	int key = 0, ifindex = -1;
+	int key = 0;
 	uint local_ip;
 	int err;
-	DECLARE_LIBBPF_OPTS(bpf_tc_hook, tc_hook,
-			    .attach_point = BPF_TC_INGRESS);
 
 	/* add vxlan tunnel */
 	err = add_ip6vxlan_tunnel();
@@ -503,31 +693,17 @@ static void test_ip6vxlan_tunnel(void)
 	skel = test_tunnel_kern__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load"))
 		goto done;
-	ifindex = if_nametoindex(IP6VXLAN_TUNL_DEV1);
-	if (!ASSERT_NEQ(ifindex, 0, "ip6vxlan11 ifindex"))
-		goto done;
-	tc_hook.ifindex = ifindex;
 	get_src_prog_fd = bpf_program__fd(skel->progs.ip6vxlan_get_tunnel_src);
 	set_src_prog_fd = bpf_program__fd(skel->progs.ip6vxlan_set_tunnel_src);
-	if (!ASSERT_GE(set_src_prog_fd, 0, "bpf_program__fd"))
-		goto done;
-	if (!ASSERT_GE(get_src_prog_fd, 0, "bpf_program__fd"))
-		goto done;
-	if (attach_tc_prog(&tc_hook, get_src_prog_fd, set_src_prog_fd))
+	if (generic_attach(IP6VXLAN_TUNL_DEV1, get_src_prog_fd, set_src_prog_fd))
 		goto done;
 
 	/* load and attach prog set_md to tunnel dev tc hook point at_ns0 */
 	nstoken = open_netns("at_ns0");
 	if (!ASSERT_OK_PTR(nstoken, "setns src"))
 		goto done;
-	ifindex = if_nametoindex(IP6VXLAN_TUNL_DEV0);
-	if (!ASSERT_NEQ(ifindex, 0, "ip6vxlan00 ifindex"))
-		goto done;
-	tc_hook.ifindex = ifindex;
 	set_dst_prog_fd = bpf_program__fd(skel->progs.ip6vxlan_set_tunnel_dst);
-	if (!ASSERT_GE(set_dst_prog_fd, 0, "bpf_program__fd"))
-		goto done;
-	if (attach_tc_prog(&tc_hook, -1, set_dst_prog_fd))
+	if (generic_attach_egr(IP6VXLAN_TUNL_DEV0, set_dst_prog_fd))
 		goto done;
 	close_netns(nstoken);
 
@@ -541,9 +717,7 @@ static void test_ip6vxlan_tunnel(void)
 		goto done;
 
 	/* ping test */
-	err = test_ping(AF_INET, IP4_ADDR_TUNL_DEV0);
-	if (!ASSERT_OK(err, "test_ping"))
-		goto done;
+	ping_dev0();
 
 done:
 	/* delete ipv6 vxlan tunnel */
@@ -557,12 +731,8 @@ done:
 static void test_ipip_tunnel(enum ipip_encap encap)
 {
 	struct test_tunnel_kern *skel = NULL;
-	struct nstoken *nstoken;
 	int set_src_prog_fd, get_src_prog_fd;
-	int ifindex = -1;
 	int err;
-	DECLARE_LIBBPF_OPTS(bpf_tc_hook, tc_hook,
-			    .attach_point = BPF_TC_INGRESS);
 
 	/* add ipip tunnel */
 	err = add_ipip_tunnel(encap);
@@ -573,10 +743,6 @@ static void test_ipip_tunnel(enum ipip_encap encap)
 	skel = test_tunnel_kern__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load"))
 		goto done;
-	ifindex = if_nametoindex(IPIP_TUNL_DEV1);
-	if (!ASSERT_NEQ(ifindex, 0, "ipip11 ifindex"))
-		goto done;
-	tc_hook.ifindex = ifindex;
 
 	switch (encap) {
 	case FOU:
@@ -598,26 +764,11 @@ static void test_ipip_tunnel(enum ipip_encap encap)
 			skel->progs.ipip_set_tunnel);
 	}
 
-	if (!ASSERT_GE(set_src_prog_fd, 0, "bpf_program__fd"))
-		goto done;
-	if (!ASSERT_GE(get_src_prog_fd, 0, "bpf_program__fd"))
-		goto done;
-	if (attach_tc_prog(&tc_hook, get_src_prog_fd, set_src_prog_fd))
+	if (generic_attach(IPIP_TUNL_DEV1, get_src_prog_fd, set_src_prog_fd))
 		goto done;
 
-	/* ping from root namespace test */
-	err = test_ping(AF_INET, IP4_ADDR_TUNL_DEV0);
-	if (!ASSERT_OK(err, "test_ping"))
-		goto done;
-
-	/* ping from at_ns0 namespace test */
-	nstoken = open_netns("at_ns0");
-	if (!ASSERT_OK_PTR(nstoken, "setns"))
-		goto done;
-	err = test_ping(AF_INET, IP4_ADDR_TUNL_DEV1);
-	if (!ASSERT_OK(err, "test_ping"))
-		goto done;
-	close_netns(nstoken);
+	ping_dev0();
+	ping_dev1();
 
 done:
 	/* delete ipip tunnel */
@@ -628,11 +779,8 @@ done:
 
 static void test_xfrm_tunnel(void)
 {
-	DECLARE_LIBBPF_OPTS(bpf_tc_hook, tc_hook,
-			    .attach_point = BPF_TC_INGRESS);
 	LIBBPF_OPTS(bpf_xdp_attach_opts, opts);
 	struct test_tunnel_kern *skel = NULL;
-	struct nstoken *nstoken;
 	int xdp_prog_fd;
 	int tc_prog_fd;
 	int ifindex;
@@ -646,19 +794,16 @@ static void test_xfrm_tunnel(void)
 	if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load"))
 		goto done;
 
-	ifindex = if_nametoindex("veth1");
-	if (!ASSERT_NEQ(ifindex, 0, "veth1 ifindex"))
-		goto done;
 
 	/* attach tc prog to tunnel dev */
-	tc_hook.ifindex = ifindex;
 	tc_prog_fd = bpf_program__fd(skel->progs.xfrm_get_state);
-	if (!ASSERT_GE(tc_prog_fd, 0, "bpf_program__fd"))
-		goto done;
-	if (attach_tc_prog(&tc_hook, tc_prog_fd, -1))
+	if (generic_attach_igr("veth1", tc_prog_fd))
 		goto done;
 
 	/* attach xdp prog to tunnel dev */
+	ifindex = if_nametoindex("veth1");
+	if (!ASSERT_NEQ(ifindex, 0, "veth1 ifindex"))
+		goto done;
 	xdp_prog_fd = bpf_program__fd(skel->progs.xfrm_get_state_xdp);
 	if (!ASSERT_GE(xdp_prog_fd, 0, "bpf_program__fd"))
 		goto done;
@@ -666,14 +811,7 @@ static void test_xfrm_tunnel(void)
 	if (!ASSERT_OK(err, "bpf_xdp_attach"))
 		goto done;
 
-	/* ping from at_ns0 namespace test */
-	nstoken = open_netns("at_ns0");
-	if (!ASSERT_OK_PTR(nstoken, "setns"))
-		goto done;
-	err = test_ping(AF_INET, IP4_ADDR_TUNL_DEV1);
-	close_netns(nstoken);
-	if (!ASSERT_OK(err, "test_ping"))
-		goto done;
+	ping_dev1();
 
 	if (!ASSERT_EQ(skel->bss->xfrm_reqid, 1, "req_id"))
 		goto done;
@@ -690,6 +828,281 @@ done:
 		test_tunnel_kern__destroy(skel);
 }
 
+enum gre_test {
+	GRE,
+	GRE_NOKEY,
+	GRETAP,
+	GRETAP_NOKEY,
+};
+
+static void test_gre_tunnel(enum gre_test test)
+{
+	struct test_tunnel_kern *skel;
+	int set_fd, get_fd;
+	int err;
+
+	skel = test_tunnel_kern__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load"))
+		return;
+
+	switch (test) {
+	case GRE:
+		err = add_ipv4_tunnel(GRE_TUNL_DEV0, GRE_TUNL_DEV1, "gre", "seq");
+		set_fd = bpf_program__fd(skel->progs.gre_set_tunnel_no_key);
+		get_fd = bpf_program__fd(skel->progs.gre_get_tunnel);
+		break;
+	case GRE_NOKEY:
+		err = add_ipv4_tunnel(GRE_TUNL_DEV0, GRE_TUNL_DEV1, "gre", "seq key 2");
+		set_fd = bpf_program__fd(skel->progs.gre_set_tunnel);
+		get_fd = bpf_program__fd(skel->progs.gre_get_tunnel);
+		break;
+	case GRETAP:
+		err = add_ipv4_tunnel(GRE_TUNL_DEV0, GRE_TUNL_DEV1, "gretap", "seq");
+		set_fd = bpf_program__fd(skel->progs.gre_set_tunnel_no_key);
+		get_fd = bpf_program__fd(skel->progs.gre_get_tunnel);
+		break;
+	case GRETAP_NOKEY:
+		err = add_ipv4_tunnel(GRE_TUNL_DEV0, GRE_TUNL_DEV1, "gretap", "seq key 2");
+		set_fd = bpf_program__fd(skel->progs.gre_set_tunnel);
+		get_fd = bpf_program__fd(skel->progs.gre_get_tunnel);
+		break;
+	}
+	if (!ASSERT_OK(err, "add tunnel"))
+		goto done;
+
+	if (generic_attach(GRE_TUNL_DEV1, get_fd, set_fd))
+		goto done;
+
+	ping_dev0();
+	ping_dev1();
+
+done:
+	delete_tunnel(GRE_TUNL_DEV0, GRE_TUNL_DEV1);
+	test_tunnel_kern__destroy(skel);
+}
+
+enum ip6gre_test {
+	IP6GRE,
+	IP6GRETAP
+};
+
+static void test_ip6gre_tunnel(enum ip6gre_test test)
+{
+	struct test_tunnel_kern *skel;
+	int set_fd, get_fd;
+	int err;
+
+	skel = test_tunnel_kern__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load"))
+		return;
+
+	switch (test) {
+	case IP6GRE:
+		err = add_ipv6_tunnel(IP6GRE_TUNL_DEV0, IP6GRE_TUNL_DEV1,
+				      "ip6gre", "flowlabel 0xbcdef key 2");
+		break;
+	case IP6GRETAP:
+		err = add_ipv6_tunnel(IP6GRE_TUNL_DEV0, IP6GRE_TUNL_DEV1,
+				      "ip6gretap", "flowlabel 0xbcdef key 2");
+		break;
+	}
+	if (!ASSERT_OK(err, "add tunnel"))
+		goto done;
+
+	set_fd = bpf_program__fd(skel->progs.ip6gretap_set_tunnel);
+	get_fd = bpf_program__fd(skel->progs.ip6gretap_get_tunnel);
+	if (generic_attach(IP6GRE_TUNL_DEV1, get_fd, set_fd))
+		goto done;
+
+	ping6_veth0();
+	ping6_dev1();
+	ping_dev0();
+	ping_dev1();
+done:
+	delete_tunnel(IP6GRE_TUNL_DEV0, IP6GRE_TUNL_DEV1);
+	test_tunnel_kern__destroy(skel);
+}
+
+enum erspan_test {
+	V1,
+	V2
+};
+
+static void test_erspan_tunnel(enum erspan_test test)
+{
+	struct test_tunnel_kern *skel;
+	int set_fd, get_fd;
+	int err;
+
+	skel = test_tunnel_kern__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load"))
+		return;
+
+	switch (test) {
+	case V1:
+		err = add_ipv4_tunnel(ERSPAN_TUNL_DEV0, ERSPAN_TUNL_DEV1,
+				      "erspan", "seq key 2 erspan_ver 1 erspan 123");
+		break;
+	case V2:
+		err = add_ipv4_tunnel(ERSPAN_TUNL_DEV0, ERSPAN_TUNL_DEV1,
+				      "erspan",
+				      "seq key 2 erspan_ver 2 erspan_dir egress erspan_hwid 3");
+		break;
+	}
+	if (!ASSERT_OK(err, "add tunnel"))
+		goto done;
+
+	set_fd = bpf_program__fd(skel->progs.erspan_set_tunnel);
+	get_fd = bpf_program__fd(skel->progs.erspan_get_tunnel);
+	if (generic_attach(ERSPAN_TUNL_DEV1, get_fd, set_fd))
+		goto done;
+
+	ping_dev0();
+	ping_dev1();
+done:
+	delete_tunnel(ERSPAN_TUNL_DEV0, ERSPAN_TUNL_DEV1);
+	test_tunnel_kern__destroy(skel);
+}
+
+static void test_ip6erspan_tunnel(enum erspan_test test)
+{
+	struct test_tunnel_kern *skel;
+	int set_fd, get_fd;
+	int err;
+
+	skel = test_tunnel_kern__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load"))
+		return;
+
+	switch (test) {
+	case V1:
+		err = add_ipv6_tunnel(IP6ERSPAN_TUNL_DEV0, IP6ERSPAN_TUNL_DEV1,
+				      "ip6erspan", "seq key 2 erspan_ver 1 erspan 123");
+		break;
+	case V2:
+		err = add_ipv6_tunnel(IP6ERSPAN_TUNL_DEV0, IP6ERSPAN_TUNL_DEV1,
+				      "ip6erspan",
+				      "seq key 2 erspan_ver 2 erspan_dir egress erspan_hwid 7");
+		break;
+	}
+	if (!ASSERT_OK(err, "add tunnel"))
+		goto done;
+
+	set_fd = bpf_program__fd(skel->progs.ip4ip6erspan_set_tunnel);
+	get_fd = bpf_program__fd(skel->progs.ip4ip6erspan_get_tunnel);
+	if (generic_attach(IP6ERSPAN_TUNL_DEV1, get_fd, set_fd))
+		goto done;
+
+	ping6_veth0();
+	ping_dev1();
+done:
+	delete_tunnel(IP6ERSPAN_TUNL_DEV0, IP6ERSPAN_TUNL_DEV1);
+	test_tunnel_kern__destroy(skel);
+}
+
+static void test_geneve_tunnel(void)
+{
+	struct test_tunnel_kern *skel;
+	int set_fd, get_fd;
+	int err;
+
+	skel = test_tunnel_kern__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load"))
+		return;
+
+	err = add_geneve_tunnel(GENEVE_TUNL_DEV0, GENEVE_TUNL_DEV1,
+				"geneve", "dstport 6081");
+	if (!ASSERT_OK(err, "add tunnel"))
+		goto done;
+
+	set_fd = bpf_program__fd(skel->progs.geneve_set_tunnel);
+	get_fd = bpf_program__fd(skel->progs.geneve_get_tunnel);
+	if (generic_attach(GENEVE_TUNL_DEV1, get_fd, set_fd))
+		goto done;
+
+	ping_dev0();
+	ping_dev1();
+done:
+	delete_tunnel(GENEVE_TUNL_DEV0, GENEVE_TUNL_DEV1);
+	test_tunnel_kern__destroy(skel);
+}
+
+static void test_ip6geneve_tunnel(void)
+{
+	struct test_tunnel_kern *skel;
+	int set_fd, get_fd;
+	int err;
+
+	skel = test_tunnel_kern__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load"))
+		return;
+
+	err = add_ip6geneve_tunnel(IP6GENEVE_TUNL_DEV0, IP6GENEVE_TUNL_DEV1,
+				   "geneve", "");
+	if (!ASSERT_OK(err, "add tunnel"))
+		goto done;
+
+	set_fd = bpf_program__fd(skel->progs.ip6geneve_set_tunnel);
+	get_fd = bpf_program__fd(skel->progs.ip6geneve_get_tunnel);
+	if (generic_attach(IP6GENEVE_TUNL_DEV1, get_fd, set_fd))
+		goto done;
+
+	ping_dev0();
+	ping_dev1();
+done:
+	delete_tunnel(IP6GENEVE_TUNL_DEV0, IP6GENEVE_TUNL_DEV1);
+	test_tunnel_kern__destroy(skel);
+}
+
+enum ip6tnl_test {
+	IPIP6,
+	IP6IP6
+};
+
+static void test_ip6tnl_tunnel(enum ip6tnl_test test)
+{
+	struct test_tunnel_kern *skel;
+	int set_fd, get_fd;
+	int err;
+
+	skel = test_tunnel_kern__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load"))
+		return;
+
+	err = add_ipv6_tunnel(IP6TNL_TUNL_DEV0, IP6TNL_TUNL_DEV1, "ip6tnl", "");
+	if (!ASSERT_OK(err, "add tunnel"))
+		goto done;
+
+	switch (test) {
+	case IPIP6:
+		set_fd = bpf_program__fd(skel->progs.ipip6_set_tunnel);
+		get_fd = bpf_program__fd(skel->progs.ipip6_get_tunnel);
+		break;
+	case IP6IP6:
+		set_fd = bpf_program__fd(skel->progs.ip6ip6_set_tunnel);
+		get_fd = bpf_program__fd(skel->progs.ip6ip6_get_tunnel);
+		break;
+	}
+	if (generic_attach(IP6TNL_TUNL_DEV1, get_fd, set_fd))
+		goto done;
+
+	ping6_veth0();
+	switch (test) {
+	case IPIP6:
+		ping_dev0();
+		ping_dev1();
+		break;
+	case IP6IP6:
+		ping6_dev0();
+		ping6_dev1();
+		break;
+	}
+
+done:
+	delete_tunnel(IP6TNL_TUNL_DEV0, IP6TNL_TUNL_DEV1);
+	test_tunnel_kern__destroy(skel);
+}
+
 #define RUN_TEST(name, ...)						\
 	({								\
 		if (test__start_subtest(#name)) {			\
@@ -707,6 +1120,20 @@ static void *test_tunnel_run_tests(void *arg)
 	RUN_TEST(ipip_tunnel, FOU);
 	RUN_TEST(ipip_tunnel, GUE);
 	RUN_TEST(xfrm_tunnel);
+	RUN_TEST(gre_tunnel, GRE);
+	RUN_TEST(gre_tunnel, GRE_NOKEY);
+	RUN_TEST(gre_tunnel, GRETAP);
+	RUN_TEST(gre_tunnel, GRETAP_NOKEY);
+	RUN_TEST(ip6gre_tunnel, IP6GRE);
+	RUN_TEST(ip6gre_tunnel, IP6GRETAP);
+	RUN_TEST(erspan_tunnel, V1);
+	RUN_TEST(erspan_tunnel, V2);
+	RUN_TEST(ip6erspan_tunnel, V1);
+	RUN_TEST(ip6erspan_tunnel, V2);
+	RUN_TEST(geneve_tunnel);
+	RUN_TEST(ip6geneve_tunnel);
+	RUN_TEST(ip6tnl_tunnel, IPIP6);
+	RUN_TEST(ip6tnl_tunnel, IP6IP6);
 
 	return NULL;
 }

tools/testing/selftests/bpf/prog_tests/test_veristat.c

@@ -0,0 +1,139 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include <string.h>
+#include <stdio.h>
+
+#define __CHECK_STR(str, name)					    \
+	do {							    \
+		if (!ASSERT_HAS_SUBSTR(fix->output, (str), (name))) \
+			goto out;				    \
+	} while (0)
+
+struct fixture {
+	char tmpfile[80];
+	int fd;
+	char *output;
+	size_t sz;
+	char veristat[80];
+};
+
+static struct fixture *init_fixture(void)
+{
+	struct fixture *fix = malloc(sizeof(struct fixture));
+
+	/* for no_alu32 and cpuv4 veristat is in parent folder */
+	if (access("./veristat", F_OK) == 0)
+		strcpy(fix->veristat, "./veristat");
+	else if (access("../veristat", F_OK) == 0)
+		strcpy(fix->veristat, "../veristat");
+	else
+		PRINT_FAIL("Can't find veristat binary");
+
+	snprintf(fix->tmpfile, sizeof(fix->tmpfile), "/tmp/test_veristat.XXXXXX");
+	fix->fd = mkstemp(fix->tmpfile);
+	fix->sz = 1000000;
+	fix->output = malloc(fix->sz);
+	return fix;
+}
+
+static void teardown_fixture(struct fixture *fix)
+{
+	free(fix->output);
+	close(fix->fd);
+	remove(fix->tmpfile);
+	free(fix);
+}
+
+static void test_set_global_vars_succeeds(void)
+{
+	struct fixture *fix = init_fixture();
+
+	SYS(out,
+	    "%s set_global_vars.bpf.o"\
+	    " -G \"var_s64 = 0xf000000000000001\" "\
+	    " -G \"var_u64 = 0xfedcba9876543210\" "\
+	    " -G \"var_s32 = -0x80000000\" "\
+	    " -G \"var_u32 = 0x76543210\" "\
+	    " -G \"var_s16 = -32768\" "\
+	    " -G \"var_u16 = 60652\" "\
+	    " -G \"var_s8 = -128\" "\
+	    " -G \"var_u8 = 255\" "\
+	    " -G \"var_ea = EA2\" "\
+	    " -G \"var_eb = EB2\" "\
+	    " -G \"var_ec = EC2\" "\
+	    " -G \"var_b = 1\" "\
+	    "-vl2 > %s", fix->veristat, fix->tmpfile);
+
+	read(fix->fd, fix->output, fix->sz);
+	__CHECK_STR("_w=0xf000000000000001 ", "var_s64 = 0xf000000000000001");
+	__CHECK_STR("_w=0xfedcba9876543210 ", "var_u64 = 0xfedcba9876543210");
+	__CHECK_STR("_w=0x80000000 ", "var_s32 = -0x80000000");
+	__CHECK_STR("_w=0x76543210 ", "var_u32 = 0x76543210");
+	__CHECK_STR("_w=0x8000 ", "var_s16 = -32768");
+	__CHECK_STR("_w=0xecec ", "var_u16 = 60652");
+	__CHECK_STR("_w=128 ", "var_s8 = -128");
+	__CHECK_STR("_w=255 ", "var_u8 = 255");
+	__CHECK_STR("_w=11 ", "var_ea = EA2");
+	__CHECK_STR("_w=12 ", "var_eb = EB2");
+	__CHECK_STR("_w=13 ", "var_ec = EC2");
+	__CHECK_STR("_w=1 ", "var_b = 1");
+
+out:
+	teardown_fixture(fix);
+}
+
+static void test_set_global_vars_from_file_succeeds(void)
+{
+	struct fixture *fix = init_fixture();
+	char input_file[80];
+	const char *vars = "var_s16 = -32768\nvar_u16 = 60652";
+	int fd;
+
+	snprintf(input_file, sizeof(input_file), "/tmp/veristat_input.XXXXXX");
+	fd = mkstemp(input_file);
+	if (!ASSERT_GE(fd, 0, "valid fd"))
+		goto out;
+
+	write(fd, vars, strlen(vars));
+	syncfs(fd);
+	SYS(out, "%s set_global_vars.bpf.o -G \"@%s\" -vl2 > %s",
+	    fix->veristat, input_file, fix->tmpfile);
+	read(fix->fd, fix->output, fix->sz);
+	__CHECK_STR("_w=0x8000 ", "var_s16 = -32768");
+	__CHECK_STR("_w=0xecec ", "var_u16 = 60652");
+
+out:
+	close(fd);
+	remove(input_file);
+	teardown_fixture(fix);
+}
+
+static void test_set_global_vars_out_of_range(void)
+{
+	struct fixture *fix = init_fixture();
+
+	SYS_FAIL(out,
+		 "%s set_global_vars.bpf.o -G \"var_s32 = 2147483648\" -vl2 2> %s",
+		 fix->veristat, fix->tmpfile);
+
+	read(fix->fd, fix->output, fix->sz);
+	__CHECK_STR("is out of range [-2147483648; 2147483647]", "out of range");
+
+out:
+	teardown_fixture(fix);
+}
+
+void test_veristat(void)
+{
+	if (test__start_subtest("set_global_vars_succeeds"))
+		test_set_global_vars_succeeds();
+
+	if (test__start_subtest("set_global_vars_out_of_range"))
+		test_set_global_vars_out_of_range();
+
+	if (test__start_subtest("set_global_vars_from_file_succeeds"))
+		test_set_global_vars_from_file_succeeds();
+}
+
+#undef __CHECK_STR

tools/testing/selftests/bpf/prog_tests/test_xdp_veth.c

@@ -3,17 +3,50 @@
 /* Create 3 namespaces with 3 veth peers, and forward packets in-between using
  * native XDP
  *
- *                      XDP_TX
- * NS1(veth11)        NS2(veth22)        NS3(veth33)
- *      |                  |                  |
- *      |                  |                  |
- *   (veth1,            (veth2,            (veth3,
- *   id:111)            id:122)            id:133)
- *     ^ |                ^ |                ^ |
- *     | |  XDP_REDIRECT  | |  XDP_REDIRECT  | |
- *     | ------------------ ------------------ |
- *     -----------------------------------------
- *                    XDP_REDIRECT
+ * Network topology:
+ *  ----------        ----------       ----------
+ *  |  NS1   |        |  NS2   |       |  NS3   |
+ *  | veth11 |        | veth22 |       | veth33 |
+ *  ----|-----        -----|----       -----|----
+ *      |                  |                |
+ *  ----|------------------|----------------|----
+ *  | veth1              veth2            veth3 |
+ *  |                                           |
+ *  |                     NSO                   |
+ *  ---------------------------------------------
+ *
+ * Test cases:
+ *  - [test_xdp_veth_redirect] : ping veth33 from veth11
+ *
+ *    veth11             veth22              veth33
+ *  (XDP_PASS)          (XDP_TX)           (XDP_PASS)
+ *       |                  |                  |
+ *       |                  |                  |
+ *     veth1             veth2              veth3
+ * (XDP_REDIRECT)     (XDP_REDIRECT)     (XDP_REDIRECT)
+ *      ^ |                ^ |                ^ |
+ *      | |                | |                | |
+ *      | ------------------ ------------------ |
+ *      -----------------------------------------
+ *
+ * - [test_xdp_veth_broadcast_redirect]: broadcast from veth11
+ *     - IPv4 ping : BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS
+ *          -> echo request received by all except veth11
+ *     - IPv4 ping : BPF_F_BROADCAST
+ *          -> echo request received by all veth
+ * - [test_xdp_veth_egress]:
+ *     - all src mac should be the magic mac
+ *
+ *    veth11             veth22              veth33
+ *  (XDP_PASS)         (XDP_PASS)          (XDP_PASS)
+ *       |                  |                  |
+ *       |                  |                  |
+ *     veth1		  veth2              veth3
+ * (XDP_REDIRECT)     (XDP_REDIRECT)     (XDP_REDIRECT)
+ *      |                   ^                  ^
+ *      |                   |                  |
+ *      ----------------------------------------
+ *
  */
 
 #define _GNU_SOURCE
@@ -22,192 +55,545 @@
 #include "network_helpers.h"
 #include "xdp_dummy.skel.h"
 #include "xdp_redirect_map.skel.h"
+#include "xdp_redirect_multi_kern.skel.h"
 #include "xdp_tx.skel.h"
+#include <uapi/linux/if_link.h>
 
 #define VETH_PAIRS_COUNT	3
-#define NS_SUFFIX_LEN		6
-#define VETH_NAME_MAX_LEN	16
+#define VETH_NAME_MAX_LEN	32
+#define IP_MAX_LEN		16
 #define IP_SRC				"10.1.1.11"
 #define IP_DST				"10.1.1.33"
-#define IP_CMD_MAX_LEN		128
-
-struct skeletons {
-	struct xdp_dummy *xdp_dummy;
-	struct xdp_tx *xdp_tx;
-	struct xdp_redirect_map *xdp_redirect_maps;
-};
+#define IP_NEIGH			"10.1.1.253"
+#define PROG_NAME_MAX_LEN	128
+#define NS_NAME_MAX_LEN		32
 
 struct veth_configuration {
 	char local_veth[VETH_NAME_MAX_LEN]; /* Interface in main namespace */
 	char remote_veth[VETH_NAME_MAX_LEN]; /* Peer interface in dedicated namespace*/
-	const char *namespace; /* Namespace for the remote veth */
-	char next_veth[VETH_NAME_MAX_LEN]; /* Local interface to redirect traffic to */
-	char *remote_addr; /* IP address of the remote veth */
+	char namespace[NS_NAME_MAX_LEN]; /* Namespace for the remote veth */
+	int next_veth; /* Local interface to redirect traffic to */
+	char remote_addr[IP_MAX_LEN]; /* IP address of the remote veth */
 };
 
-static struct veth_configuration config[VETH_PAIRS_COUNT] = {
+struct net_configuration {
+	char ns0_name[NS_NAME_MAX_LEN];
+	struct veth_configuration veth_cfg[VETH_PAIRS_COUNT];
+};
+
+static const struct net_configuration default_config = {
+	.ns0_name = "ns0-",
 	{
-		.local_veth = "veth1",
-		.remote_veth = "veth11",
-		.next_veth = "veth2",
-		.remote_addr = IP_SRC,
-		.namespace = "ns-veth11"
-	},
-	{
-		.local_veth = "veth2",
-		.remote_veth = "veth22",
-		.next_veth = "veth3",
-		.remote_addr = NULL,
-		.namespace = "ns-veth22"
-	},
-	{
-		.local_veth = "veth3",
-		.remote_veth = "veth33",
-		.next_veth = "veth1",
-		.remote_addr = IP_DST,
-		.namespace = "ns-veth33"
+		{
+			.local_veth = "veth1-",
+			.remote_veth = "veth11",
+			.next_veth = 1,
+			.remote_addr = IP_SRC,
+			.namespace = "ns-veth11-"
+		},
+		{
+			.local_veth = "veth2-",
+			.remote_veth = "veth22",
+			.next_veth = 2,
+			.remote_addr = "",
+			.namespace = "ns-veth22-"
+		},
+		{
+			.local_veth = "veth3-",
+			.remote_veth = "veth33",
+			.next_veth = 0,
+			.remote_addr = IP_DST,
+			.namespace = "ns-veth33-"
+		}
 	}
 };
 
-static int attach_programs_to_veth_pair(struct skeletons *skeletons, int index)
+struct prog_configuration {
+	char local_name[PROG_NAME_MAX_LEN]; /* BPF prog to attach to local_veth */
+	char remote_name[PROG_NAME_MAX_LEN]; /* BPF prog to attach to remote_veth */
+	u32 local_flags; /* XDP flags to use on local_veth */
+	u32 remote_flags; /* XDP flags to use on remote_veth */
+};
+
+static int attach_programs_to_veth_pair(struct bpf_object **objs, size_t nb_obj,
+					struct net_configuration *net_config,
+					struct prog_configuration *prog, int index)
 {
 	struct bpf_program *local_prog, *remote_prog;
-	struct bpf_link **local_link, **remote_link;
 	struct nstoken *nstoken;
-	struct bpf_link *link;
-	int interface;
+	int interface, ret, i;
 
-	switch (index) {
-	case 0:
-		local_prog = skeletons->xdp_redirect_maps->progs.xdp_redirect_map_0;
-		local_link = &skeletons->xdp_redirect_maps->links.xdp_redirect_map_0;
-		remote_prog = skeletons->xdp_dummy->progs.xdp_dummy_prog;
-		remote_link = &skeletons->xdp_dummy->links.xdp_dummy_prog;
-		break;
-	case 1:
-		local_prog = skeletons->xdp_redirect_maps->progs.xdp_redirect_map_1;
-		local_link = &skeletons->xdp_redirect_maps->links.xdp_redirect_map_1;
-		remote_prog = skeletons->xdp_tx->progs.xdp_tx;
-		remote_link = &skeletons->xdp_tx->links.xdp_tx;
-		break;
-	case 2:
-		local_prog = skeletons->xdp_redirect_maps->progs.xdp_redirect_map_2;
-		local_link = &skeletons->xdp_redirect_maps->links.xdp_redirect_map_2;
-		remote_prog = skeletons->xdp_dummy->progs.xdp_dummy_prog;
-		remote_link = &skeletons->xdp_dummy->links.xdp_dummy_prog;
-		break;
+	for (i = 0; i < nb_obj; i++) {
+		local_prog = bpf_object__find_program_by_name(objs[i], prog[index].local_name);
+		if (local_prog)
+			break;
 	}
-	interface = if_nametoindex(config[index].local_veth);
+	if (!ASSERT_OK_PTR(local_prog, "find local program"))
+		return -1;
+
+	for (i = 0; i < nb_obj; i++) {
+		remote_prog = bpf_object__find_program_by_name(objs[i], prog[index].remote_name);
+		if (remote_prog)
+			break;
+	}
+	if (!ASSERT_OK_PTR(remote_prog, "find remote program"))
+		return -1;
+
+	interface = if_nametoindex(net_config->veth_cfg[index].local_veth);
 	if (!ASSERT_NEQ(interface, 0, "non zero interface index"))
 		return -1;
-	link = bpf_program__attach_xdp(local_prog, interface);
-	if (!ASSERT_OK_PTR(link, "attach xdp program to local veth"))
+
+	ret = bpf_xdp_attach(interface, bpf_program__fd(local_prog),
+			     prog[index].local_flags, NULL);
+	if (!ASSERT_OK(ret, "attach xdp program to local veth"))
 		return -1;
-	*local_link = link;
-	nstoken = open_netns(config[index].namespace);
+
+	nstoken = open_netns(net_config->veth_cfg[index].namespace);
 	if (!ASSERT_OK_PTR(nstoken, "switch to remote veth namespace"))
 		return -1;
-	interface = if_nametoindex(config[index].remote_veth);
+
+	interface = if_nametoindex(net_config->veth_cfg[index].remote_veth);
 	if (!ASSERT_NEQ(interface, 0, "non zero interface index")) {
 		close_netns(nstoken);
 		return -1;
 	}
-	link = bpf_program__attach_xdp(remote_prog, interface);
-	*remote_link = link;
-	close_netns(nstoken);
-	if (!ASSERT_OK_PTR(link, "attach xdp program to remote veth"))
-		return -1;
 
+	ret = bpf_xdp_attach(interface, bpf_program__fd(remote_prog),
+			     prog[index].remote_flags, NULL);
+	if (!ASSERT_OK(ret, "attach xdp program to remote veth")) {
+		close_netns(nstoken);
+		return -1;
+	}
+
+	close_netns(nstoken);
 	return 0;
 }
 
-static int configure_network(struct skeletons *skeletons)
+static int create_network(struct net_configuration *net_config)
 {
-	int interface_id;
-	int map_fd;
-	int err;
-	int i = 0;
+	struct nstoken *nstoken = NULL;
+	int i, err;
 
-	/* First create and configure all interfaces */
-	for (i = 0; i < VETH_PAIRS_COUNT; i++) {
-		SYS(fail, "ip netns add %s", config[i].namespace);
-		SYS(fail, "ip link add %s type veth peer name %s netns %s",
-		    config[i].local_veth, config[i].remote_veth, config[i].namespace);
-		SYS(fail, "ip link set dev %s up", config[i].local_veth);
-		if (config[i].remote_addr)
-			SYS(fail, "ip -n %s addr add %s/24 dev %s",	config[i].namespace,
-			    config[i].remote_addr, config[i].remote_veth);
-		SYS(fail, "ip -n %s link set dev %s up", config[i].namespace,
-		    config[i].remote_veth);
-	}
+	memcpy(net_config, &default_config, sizeof(struct net_configuration));
 
-	/* Then configure the redirect map and attach programs to interfaces */
-	map_fd = bpf_map__fd(skeletons->xdp_redirect_maps->maps.tx_port);
-	if (!ASSERT_GE(map_fd, 0, "open redirect map"))
+	/* Create unique namespaces */
+	err = append_tid(net_config->ns0_name, NS_NAME_MAX_LEN);
+	if (!ASSERT_OK(err, "append TID to ns0 name"))
 		goto fail;
+	SYS(fail, "ip netns add %s", net_config->ns0_name);
+
 	for (i = 0; i < VETH_PAIRS_COUNT; i++) {
-		interface_id = if_nametoindex(config[i].next_veth);
-		if (!ASSERT_NEQ(interface_id, 0, "non zero interface index"))
-			goto fail;
-		err = bpf_map_update_elem(map_fd, &i, &interface_id, BPF_ANY);
-		if (!ASSERT_OK(err, "configure interface redirection through map"))
-			goto fail;
-		if (attach_programs_to_veth_pair(skeletons, i))
+		err = append_tid(net_config->veth_cfg[i].namespace, NS_NAME_MAX_LEN);
+		if (!ASSERT_OK(err, "append TID to ns name"))
 			goto fail;
+		SYS(fail, "ip netns add %s", net_config->veth_cfg[i].namespace);
 	}
 
+	/* Create interfaces */
+	nstoken = open_netns(net_config->ns0_name);
+	if (!nstoken)
+		goto fail;
+
+	for (i = 0; i < VETH_PAIRS_COUNT; i++) {
+		SYS(fail, "ip link add %s type veth peer name %s netns %s",
+		    net_config->veth_cfg[i].local_veth, net_config->veth_cfg[i].remote_veth,
+		    net_config->veth_cfg[i].namespace);
+		SYS(fail, "ip link set dev %s up", net_config->veth_cfg[i].local_veth);
+		if (net_config->veth_cfg[i].remote_addr[0])
+			SYS(fail, "ip -n %s addr add %s/24 dev %s",
+			    net_config->veth_cfg[i].namespace,
+			    net_config->veth_cfg[i].remote_addr,
+			    net_config->veth_cfg[i].remote_veth);
+		SYS(fail, "ip -n %s link set dev %s up", net_config->veth_cfg[i].namespace,
+		    net_config->veth_cfg[i].remote_veth);
+	}
+
+	close_netns(nstoken);
 	return 0;
 
 fail:
+	close_netns(nstoken);
 	return -1;
 }
 
-static void cleanup_network(void)
+static void cleanup_network(struct net_configuration *net_config)
 {
 	int i;
 
-	/* Deleting namespaces is enough to automatically remove veth pairs as well
-	 */
+	SYS_NOFAIL("ip netns del %s", net_config->ns0_name);
 	for (i = 0; i < VETH_PAIRS_COUNT; i++)
-		SYS_NOFAIL("ip netns del %s", config[i].namespace);
+		SYS_NOFAIL("ip netns del %s", net_config->veth_cfg[i].namespace);
 }
 
-static int check_ping(struct skeletons *skeletons)
+#define VETH_REDIRECT_SKEL_NB	3
+static void xdp_veth_redirect(u32 flags)
 {
+	struct prog_configuration ping_config[VETH_PAIRS_COUNT] = {
+		{
+			.local_name = "xdp_redirect_map_0",
+			.remote_name = "xdp_dummy_prog",
+			.local_flags = flags,
+			.remote_flags = flags,
+		},
+		{
+			.local_name = "xdp_redirect_map_1",
+			.remote_name = "xdp_tx",
+			.local_flags = flags,
+			.remote_flags = flags,
+		},
+		{
+			.local_name = "xdp_redirect_map_2",
+			.remote_name = "xdp_dummy_prog",
+			.local_flags = flags,
+			.remote_flags = flags,
+		}
+	};
+	struct bpf_object *bpf_objs[VETH_REDIRECT_SKEL_NB];
+	struct xdp_redirect_map *xdp_redirect_map;
+	struct net_configuration net_config;
+	struct nstoken *nstoken = NULL;
+	struct xdp_dummy *xdp_dummy;
+	struct xdp_tx *xdp_tx;
+	int map_fd;
+	int i;
+
+	xdp_dummy = xdp_dummy__open_and_load();
+	if (!ASSERT_OK_PTR(xdp_dummy, "xdp_dummy__open_and_load"))
+		return;
+
+	xdp_tx = xdp_tx__open_and_load();
+	if (!ASSERT_OK_PTR(xdp_tx, "xdp_tx__open_and_load"))
+		goto destroy_xdp_dummy;
+
+	xdp_redirect_map = xdp_redirect_map__open_and_load();
+	if (!ASSERT_OK_PTR(xdp_redirect_map, "xdp_redirect_map__open_and_load"))
+		goto destroy_xdp_tx;
+
+	if (!ASSERT_OK(create_network(&net_config), "create network"))
+		goto destroy_xdp_redirect_map;
+
+	/* Then configure the redirect map and attach programs to interfaces */
+	map_fd = bpf_map__fd(xdp_redirect_map->maps.tx_port);
+	if (!ASSERT_OK_FD(map_fd, "open redirect map"))
+		goto destroy_xdp_redirect_map;
+
+	bpf_objs[0] = xdp_dummy->obj;
+	bpf_objs[1] = xdp_tx->obj;
+	bpf_objs[2] = xdp_redirect_map->obj;
+
+	nstoken = open_netns(net_config.ns0_name);
+	if (!ASSERT_OK_PTR(nstoken, "open NS0"))
+		goto destroy_xdp_redirect_map;
+
+	for (i = 0; i < VETH_PAIRS_COUNT; i++) {
+		int next_veth = net_config.veth_cfg[i].next_veth;
+		int interface_id;
+		int err;
+
+		interface_id = if_nametoindex(net_config.veth_cfg[next_veth].local_veth);
+		if (!ASSERT_NEQ(interface_id, 0, "non zero interface index"))
+			goto destroy_xdp_redirect_map;
+		err = bpf_map_update_elem(map_fd, &i, &interface_id, BPF_ANY);
+		if (!ASSERT_OK(err, "configure interface redirection through map"))
+			goto destroy_xdp_redirect_map;
+		if (attach_programs_to_veth_pair(bpf_objs, VETH_REDIRECT_SKEL_NB,
+						 &net_config, ping_config, i))
+			goto destroy_xdp_redirect_map;
+	}
+
 	/* Test: if all interfaces are properly configured, we must be able to ping
 	 * veth33 from veth11
 	 */
-	return SYS_NOFAIL("ip netns exec %s ping -c 1 -W 1 %s > /dev/null",
-					  config[0].namespace, IP_DST);
+	ASSERT_OK(SYS_NOFAIL("ip netns exec %s ping -c 1 -W 1 %s > /dev/null",
+			     net_config.veth_cfg[0].namespace, IP_DST), "ping");
+
+destroy_xdp_redirect_map:
+	close_netns(nstoken);
+	xdp_redirect_map__destroy(xdp_redirect_map);
+destroy_xdp_tx:
+	xdp_tx__destroy(xdp_tx);
+destroy_xdp_dummy:
+	xdp_dummy__destroy(xdp_dummy);
+
+	cleanup_network(&net_config);
+}
+
+#define BROADCAST_REDIRECT_SKEL_NB	2
+static void xdp_veth_broadcast_redirect(u32 attach_flags, u64 redirect_flags)
+{
+	struct prog_configuration prog_cfg[VETH_PAIRS_COUNT] = {
+		{
+			.local_name = "xdp_redirect_map_multi_prog",
+			.remote_name = "xdp_count_0",
+			.local_flags = attach_flags,
+			.remote_flags = attach_flags,
+		},
+		{
+			.local_name = "xdp_redirect_map_multi_prog",
+			.remote_name = "xdp_count_1",
+			.local_flags = attach_flags,
+			.remote_flags = attach_flags,
+		},
+		{
+			.local_name = "xdp_redirect_map_multi_prog",
+			.remote_name = "xdp_count_2",
+			.local_flags = attach_flags,
+			.remote_flags = attach_flags,
+		}
+	};
+	struct bpf_object *bpf_objs[BROADCAST_REDIRECT_SKEL_NB];
+	struct xdp_redirect_multi_kern *xdp_redirect_multi_kern;
+	struct xdp_redirect_map *xdp_redirect_map;
+	struct bpf_devmap_val devmap_val = {};
+	struct net_configuration net_config;
+	struct nstoken *nstoken = NULL;
+	u16 protocol = ETH_P_IP;
+	int group_map;
+	int flags_map;
+	int cnt_map;
+	u64 cnt = 0;
+	int i, err;
+
+	xdp_redirect_multi_kern = xdp_redirect_multi_kern__open_and_load();
+	if (!ASSERT_OK_PTR(xdp_redirect_multi_kern, "xdp_redirect_multi_kern__open_and_load"))
+		return;
+
+	xdp_redirect_map = xdp_redirect_map__open_and_load();
+	if (!ASSERT_OK_PTR(xdp_redirect_map, "xdp_redirect_map__open_and_load"))
+		goto destroy_xdp_redirect_multi_kern;
+
+	if (!ASSERT_OK(create_network(&net_config), "create network"))
+		goto destroy_xdp_redirect_map;
+
+	group_map = bpf_map__fd(xdp_redirect_multi_kern->maps.map_all);
+	if (!ASSERT_OK_FD(group_map, "open map_all"))
+		goto destroy_xdp_redirect_map;
+
+	flags_map = bpf_map__fd(xdp_redirect_multi_kern->maps.redirect_flags);
+	if (!ASSERT_OK_FD(group_map, "open map_all"))
+		goto destroy_xdp_redirect_map;
+
+	err = bpf_map_update_elem(flags_map, &protocol, &redirect_flags, BPF_NOEXIST);
+	if (!ASSERT_OK(err, "init IP count"))
+		goto destroy_xdp_redirect_map;
+
+	cnt_map = bpf_map__fd(xdp_redirect_map->maps.rxcnt);
+	if (!ASSERT_OK_FD(cnt_map, "open rxcnt map"))
+		goto destroy_xdp_redirect_map;
+
+	bpf_objs[0] = xdp_redirect_multi_kern->obj;
+	bpf_objs[1] = xdp_redirect_map->obj;
+
+	nstoken = open_netns(net_config.ns0_name);
+	if (!ASSERT_OK_PTR(nstoken, "open NS0"))
+		goto destroy_xdp_redirect_map;
+
+	for (i = 0; i < VETH_PAIRS_COUNT; i++) {
+		int ifindex = if_nametoindex(net_config.veth_cfg[i].local_veth);
+
+		if (attach_programs_to_veth_pair(bpf_objs, BROADCAST_REDIRECT_SKEL_NB,
+						 &net_config, prog_cfg, i))
+			goto destroy_xdp_redirect_map;
+
+		SYS(destroy_xdp_redirect_map,
+		    "ip -n %s neigh add %s lladdr 00:00:00:00:00:01 dev %s",
+		    net_config.veth_cfg[i].namespace, IP_NEIGH, net_config.veth_cfg[i].remote_veth);
+
+		devmap_val.ifindex = ifindex;
+		err = bpf_map_update_elem(group_map, &ifindex, &devmap_val, 0);
+		if (!ASSERT_OK(err, "bpf_map_update_elem"))
+			goto destroy_xdp_redirect_map;
+
+	}
+
+	SYS_NOFAIL("ip netns exec %s ping %s -i 0.1 -c 4 -W1 > /dev/null ",
+		    net_config.veth_cfg[0].namespace, IP_NEIGH);
+
+	for (i = 0; i < VETH_PAIRS_COUNT; i++) {
+		err =  bpf_map_lookup_elem(cnt_map, &i, &cnt);
+		if (!ASSERT_OK(err, "get IP cnt"))
+			goto destroy_xdp_redirect_map;
+
+		if (redirect_flags & BPF_F_EXCLUDE_INGRESS)
+			/* veth11 shouldn't receive the ICMP requests;
+			 * others should
+			 */
+			ASSERT_EQ(cnt, i ? 4 : 0, "compare IP cnt");
+		else
+			/* All remote veth should receive the ICMP requests */
+			ASSERT_EQ(cnt, 4, "compare IP cnt");
+	}
+
+destroy_xdp_redirect_map:
+	close_netns(nstoken);
+	xdp_redirect_map__destroy(xdp_redirect_map);
+destroy_xdp_redirect_multi_kern:
+	xdp_redirect_multi_kern__destroy(xdp_redirect_multi_kern);
+
+	cleanup_network(&net_config);
+}
+
+#define VETH_EGRESS_SKEL_NB	3
+static void xdp_veth_egress(u32 flags)
+{
+	struct prog_configuration prog_cfg[VETH_PAIRS_COUNT] = {
+		{
+			.local_name = "xdp_redirect_map_all_prog",
+			.remote_name = "xdp_dummy_prog",
+			.local_flags = flags,
+			.remote_flags = flags,
+		},
+		{
+			.local_name = "xdp_redirect_map_all_prog",
+			.remote_name = "store_mac_1",
+			.local_flags = flags,
+			.remote_flags = flags,
+		},
+		{
+			.local_name = "xdp_redirect_map_all_prog",
+			.remote_name = "store_mac_2",
+			.local_flags = flags,
+			.remote_flags = flags,
+		}
+	};
+	const char magic_mac[6] = { 0xAA, 0xBB, 0xCC, 0xDD, 0xEE, 0xFF};
+	struct xdp_redirect_multi_kern *xdp_redirect_multi_kern;
+	struct bpf_object *bpf_objs[VETH_EGRESS_SKEL_NB];
+	struct xdp_redirect_map *xdp_redirect_map;
+	struct bpf_devmap_val devmap_val = {};
+	struct net_configuration net_config;
+	int mac_map, egress_map, res_map;
+	struct nstoken *nstoken = NULL;
+	struct xdp_dummy *xdp_dummy;
+	int err;
+	int i;
+
+	xdp_dummy = xdp_dummy__open_and_load();
+	if (!ASSERT_OK_PTR(xdp_dummy, "xdp_dummy__open_and_load"))
+		return;
+
+	xdp_redirect_multi_kern = xdp_redirect_multi_kern__open_and_load();
+	if (!ASSERT_OK_PTR(xdp_redirect_multi_kern, "xdp_redirect_multi_kern__open_and_load"))
+		goto destroy_xdp_dummy;
+
+	xdp_redirect_map = xdp_redirect_map__open_and_load();
+	if (!ASSERT_OK_PTR(xdp_redirect_map, "xdp_redirect_map__open_and_load"))
+		goto destroy_xdp_redirect_multi_kern;
+
+	if (!ASSERT_OK(create_network(&net_config), "create network"))
+		goto destroy_xdp_redirect_map;
+
+	mac_map = bpf_map__fd(xdp_redirect_multi_kern->maps.mac_map);
+	if (!ASSERT_OK_FD(mac_map, "open mac_map"))
+		goto destroy_xdp_redirect_map;
+
+	egress_map = bpf_map__fd(xdp_redirect_multi_kern->maps.map_egress);
+	if (!ASSERT_OK_FD(egress_map, "open map_egress"))
+		goto destroy_xdp_redirect_map;
+
+	devmap_val.bpf_prog.fd = bpf_program__fd(xdp_redirect_multi_kern->progs.xdp_devmap_prog);
+
+	bpf_objs[0] = xdp_dummy->obj;
+	bpf_objs[1] = xdp_redirect_multi_kern->obj;
+	bpf_objs[2] = xdp_redirect_map->obj;
+
+	nstoken = open_netns(net_config.ns0_name);
+	if (!ASSERT_OK_PTR(nstoken, "open NS0"))
+		goto destroy_xdp_redirect_map;
+
+	for (i = 0; i < VETH_PAIRS_COUNT; i++) {
+		int ifindex = if_nametoindex(net_config.veth_cfg[i].local_veth);
+
+		SYS(destroy_xdp_redirect_map,
+		    "ip -n %s neigh add %s lladdr 00:00:00:00:00:01 dev %s",
+		    net_config.veth_cfg[i].namespace, IP_NEIGH, net_config.veth_cfg[i].remote_veth);
+
+		if (attach_programs_to_veth_pair(bpf_objs, VETH_REDIRECT_SKEL_NB,
+						 &net_config, prog_cfg, i))
+			goto destroy_xdp_redirect_map;
+
+		err = bpf_map_update_elem(mac_map, &ifindex, magic_mac, 0);
+		if (!ASSERT_OK(err, "bpf_map_update_elem"))
+			goto destroy_xdp_redirect_map;
+
+		devmap_val.ifindex = ifindex;
+		err = bpf_map_update_elem(egress_map, &ifindex, &devmap_val, 0);
+		if (!ASSERT_OK(err, "bpf_map_update_elem"))
+			goto destroy_xdp_redirect_map;
+	}
+
+	SYS_NOFAIL("ip netns exec %s ping %s -i 0.1 -c 4 -W1 > /dev/null ",
+		    net_config.veth_cfg[0].namespace, IP_NEIGH);
+
+	res_map = bpf_map__fd(xdp_redirect_map->maps.rx_mac);
+	if (!ASSERT_OK_FD(res_map, "open rx_map"))
+		goto destroy_xdp_redirect_map;
+
+	for (i = 0; i < 2; i++) {
+		u32 key = i;
+		u64 res;
+
+		err = bpf_map_lookup_elem(res_map, &key, &res);
+		if (!ASSERT_OK(err, "get MAC res"))
+			goto destroy_xdp_redirect_map;
+
+		ASSERT_STRNEQ((const char *)&res, magic_mac, ETH_ALEN, "compare mac");
+	}
+
+destroy_xdp_redirect_map:
+	close_netns(nstoken);
+	xdp_redirect_map__destroy(xdp_redirect_map);
+destroy_xdp_redirect_multi_kern:
+	xdp_redirect_multi_kern__destroy(xdp_redirect_multi_kern);
+destroy_xdp_dummy:
+	xdp_dummy__destroy(xdp_dummy);
+
+	cleanup_network(&net_config);
 }
 
 void test_xdp_veth_redirect(void)
 {
-	struct skeletons skeletons = {};
+	if (test__start_subtest("0"))
+		xdp_veth_redirect(0);
 
-	skeletons.xdp_dummy = xdp_dummy__open_and_load();
-	if (!ASSERT_OK_PTR(skeletons.xdp_dummy, "xdp_dummy__open_and_load"))
-		return;
+	if (test__start_subtest("DRV_MODE"))
+		xdp_veth_redirect(XDP_FLAGS_DRV_MODE);
 
-	skeletons.xdp_tx = xdp_tx__open_and_load();
-	if (!ASSERT_OK_PTR(skeletons.xdp_tx, "xdp_tx__open_and_load"))
-		goto destroy_xdp_dummy;
-
-	skeletons.xdp_redirect_maps = xdp_redirect_map__open_and_load();
-	if (!ASSERT_OK_PTR(skeletons.xdp_redirect_maps, "xdp_redirect_map__open_and_load"))
-		goto destroy_xdp_tx;
-
-	if (configure_network(&skeletons))
-		goto destroy_xdp_redirect_map;
-
-	ASSERT_OK(check_ping(&skeletons), "ping");
-
-destroy_xdp_redirect_map:
-	xdp_redirect_map__destroy(skeletons.xdp_redirect_maps);
-destroy_xdp_tx:
-	xdp_tx__destroy(skeletons.xdp_tx);
-destroy_xdp_dummy:
-	xdp_dummy__destroy(skeletons.xdp_dummy);
-
-	cleanup_network();
+	if (test__start_subtest("SKB_MODE"))
+		xdp_veth_redirect(XDP_FLAGS_SKB_MODE);
+}
+
+void test_xdp_veth_broadcast_redirect(void)
+{
+	if (test__start_subtest("0/BROADCAST"))
+		xdp_veth_broadcast_redirect(0, BPF_F_BROADCAST);
+
+	if (test__start_subtest("0/(BROADCAST | EXCLUDE_INGRESS)"))
+		xdp_veth_broadcast_redirect(0, BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS);
+
+	if (test__start_subtest("DRV_MODE/BROADCAST"))
+		xdp_veth_broadcast_redirect(XDP_FLAGS_DRV_MODE, BPF_F_BROADCAST);
+
+	if (test__start_subtest("DRV_MODE/(BROADCAST | EXCLUDE_INGRESS)"))
+		xdp_veth_broadcast_redirect(XDP_FLAGS_DRV_MODE,
+					    BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS);
+
+	if (test__start_subtest("SKB_MODE/BROADCAST"))
+		xdp_veth_broadcast_redirect(XDP_FLAGS_SKB_MODE, BPF_F_BROADCAST);
+
+	if (test__start_subtest("SKB_MODE/(BROADCAST | EXCLUDE_INGRESS)"))
+		xdp_veth_broadcast_redirect(XDP_FLAGS_SKB_MODE,
+					    BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS);
+}
+
+void test_xdp_veth_egress(void)
+{
+	if (test__start_subtest("0/egress"))
+		xdp_veth_egress(0);
+
+	if (test__start_subtest("DRV_MODE/egress"))
+		xdp_veth_egress(XDP_FLAGS_DRV_MODE);
+
+	if (test__start_subtest("SKB_MODE/egress"))
+		xdp_veth_egress(XDP_FLAGS_SKB_MODE);
 }

tools/testing/selftests/bpf/prog_tests/token.c

@@ -19,6 +19,7 @@
 #include "priv_prog.skel.h"
 #include "dummy_st_ops_success.skel.h"
 #include "token_lsm.skel.h"
+#include "priv_freplace_prog.skel.h"
 
 static inline int sys_mount(const char *dev_name, const char *dir_name,
 			    const char *type, unsigned long flags,
@@ -788,6 +789,84 @@ static int userns_obj_priv_prog(int mnt_fd, struct token_lsm *lsm_skel)
 	return 0;
 }
 
+static int userns_obj_priv_freplace_setup(int mnt_fd, struct priv_freplace_prog **fr_skel,
+					  struct priv_prog **skel, int *tgt_fd)
+{
+	LIBBPF_OPTS(bpf_object_open_opts, opts);
+	int err;
+	char buf[256];
+
+	/* use bpf_token_path to provide BPF FS path */
+	snprintf(buf, sizeof(buf), "/proc/self/fd/%d", mnt_fd);
+	opts.bpf_token_path = buf;
+	*skel = priv_prog__open_opts(&opts);
+	if (!ASSERT_OK_PTR(*skel, "priv_prog__open_opts"))
+		return -EINVAL;
+	err = priv_prog__load(*skel);
+	if (!ASSERT_OK(err, "priv_prog__load"))
+		return -EINVAL;
+
+	*fr_skel = priv_freplace_prog__open_opts(&opts);
+	if (!ASSERT_OK_PTR(*skel, "priv_freplace_prog__open_opts"))
+		return -EINVAL;
+
+	*tgt_fd = bpf_program__fd((*skel)->progs.xdp_prog1);
+	return 0;
+}
+
+/* Verify that freplace works from user namespace, because bpf token is loaded
+ * in bpf_object__prepare
+ */
+static int userns_obj_priv_freplace_prog(int mnt_fd, struct token_lsm *lsm_skel)
+{
+	struct priv_freplace_prog *fr_skel = NULL;
+	struct priv_prog *skel = NULL;
+	int err, tgt_fd;
+
+	err = userns_obj_priv_freplace_setup(mnt_fd, &fr_skel, &skel, &tgt_fd);
+	if (!ASSERT_OK(err, "setup"))
+		goto out;
+
+	err = bpf_object__prepare(fr_skel->obj);
+	if (!ASSERT_OK(err, "freplace__prepare"))
+		goto out;
+
+	err = bpf_program__set_attach_target(fr_skel->progs.new_xdp_prog2, tgt_fd, "xdp_prog1");
+	if (!ASSERT_OK(err, "set_attach_target"))
+		goto out;
+
+	err = priv_freplace_prog__load(fr_skel);
+	ASSERT_OK(err, "priv_freplace_prog__load");
+
+out:
+	priv_freplace_prog__destroy(fr_skel);
+	priv_prog__destroy(skel);
+	return err;
+}
+
+/* Verify that replace fails to set attach target from user namespace without bpf token */
+static int userns_obj_priv_freplace_prog_fail(int mnt_fd, struct token_lsm *lsm_skel)
+{
+	struct priv_freplace_prog *fr_skel = NULL;
+	struct priv_prog *skel = NULL;
+	int err, tgt_fd;
+
+	err = userns_obj_priv_freplace_setup(mnt_fd, &fr_skel, &skel, &tgt_fd);
+	if (!ASSERT_OK(err, "setup"))
+		goto out;
+
+	err = bpf_program__set_attach_target(fr_skel->progs.new_xdp_prog2, tgt_fd, "xdp_prog1");
+	if (ASSERT_ERR(err, "attach fails"))
+		err = 0;
+	else
+		err = -EINVAL;
+
+out:
+	priv_freplace_prog__destroy(fr_skel);
+	priv_prog__destroy(skel);
+	return err;
+}
+
 /* this test is called with BPF FS that doesn't delegate BPF_BTF_LOAD command,
  * which should cause struct_ops application to fail, as BTF won't be uploaded
  * into the kernel, even if STRUCT_OPS programs themselves are allowed
@@ -1004,12 +1083,28 @@ void test_token(void)
 	if (test__start_subtest("obj_priv_prog")) {
 		struct bpffs_opts opts = {
 			.cmds = bit(BPF_PROG_LOAD),
-			.progs = bit(BPF_PROG_TYPE_KPROBE),
+			.progs = bit(BPF_PROG_TYPE_XDP),
 			.attachs = ~0ULL,
 		};
 
 		subtest_userns(&opts, userns_obj_priv_prog);
 	}
+	if (test__start_subtest("obj_priv_freplace_prog")) {
+		struct bpffs_opts opts = {
+			.cmds = bit(BPF_BTF_LOAD) | bit(BPF_PROG_LOAD) | bit(BPF_BTF_GET_FD_BY_ID),
+			.progs = bit(BPF_PROG_TYPE_EXT) | bit(BPF_PROG_TYPE_XDP),
+			.attachs = ~0ULL,
+		};
+		subtest_userns(&opts, userns_obj_priv_freplace_prog);
+	}
+	if (test__start_subtest("obj_priv_freplace_prog_fail")) {
+		struct bpffs_opts opts = {
+			.cmds = bit(BPF_BTF_LOAD) | bit(BPF_PROG_LOAD) | bit(BPF_BTF_GET_FD_BY_ID),
+			.progs = bit(BPF_PROG_TYPE_EXT) | bit(BPF_PROG_TYPE_XDP),
+			.attachs = ~0ULL,
+		};
+		subtest_userns(&opts, userns_obj_priv_freplace_prog_fail);
+	}
 	if (test__start_subtest("obj_priv_btf_fail")) {
 		struct bpffs_opts opts = {
 			/* disallow BTF loading */

tools/testing/selftests/bpf/prog_tests/usdt.c

@@ -45,7 +45,7 @@ static void subtest_basic_usdt(void)
 	LIBBPF_OPTS(bpf_usdt_opts, opts);
 	struct test_usdt *skel;
 	struct test_usdt__bss *bss;
-	int err;
+	int err, i;
 
 	skel = test_usdt__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "skel_open"))
@@ -75,6 +75,7 @@ static void subtest_basic_usdt(void)
 	ASSERT_EQ(bss->usdt0_cookie, 0xcafedeadbeeffeed, "usdt0_cookie");
 	ASSERT_EQ(bss->usdt0_arg_cnt, 0, "usdt0_arg_cnt");
 	ASSERT_EQ(bss->usdt0_arg_ret, -ENOENT, "usdt0_arg_ret");
+	ASSERT_EQ(bss->usdt0_arg_size, -ENOENT, "usdt0_arg_size");
 
 	/* auto-attached usdt3 gets default zero cookie value */
 	ASSERT_EQ(bss->usdt3_cookie, 0, "usdt3_cookie");
@@ -86,6 +87,9 @@ static void subtest_basic_usdt(void)
 	ASSERT_EQ(bss->usdt3_args[0], 1, "usdt3_arg1");
 	ASSERT_EQ(bss->usdt3_args[1], 42, "usdt3_arg2");
 	ASSERT_EQ(bss->usdt3_args[2], (uintptr_t)&bla, "usdt3_arg3");
+	ASSERT_EQ(bss->usdt3_arg_sizes[0], 4, "usdt3_arg1_size");
+	ASSERT_EQ(bss->usdt3_arg_sizes[1], 8, "usdt3_arg2_size");
+	ASSERT_EQ(bss->usdt3_arg_sizes[2], 8, "usdt3_arg3_size");
 
 	/* auto-attached usdt12 gets default zero cookie value */
 	ASSERT_EQ(bss->usdt12_cookie, 0, "usdt12_cookie");
@@ -104,6 +108,11 @@ static void subtest_basic_usdt(void)
 	ASSERT_EQ(bss->usdt12_args[10], nums[idx], "usdt12_arg11");
 	ASSERT_EQ(bss->usdt12_args[11], t1.y, "usdt12_arg12");
 
+	int usdt12_expected_arg_sizes[12] = { 4, 4, 8, 8, 4, 8, 8, 8, 4, 2, 2, 1 };
+
+	for (i = 0; i < 12; i++)
+		ASSERT_EQ(bss->usdt12_arg_sizes[i], usdt12_expected_arg_sizes[i], "usdt12_arg_size");
+
 	/* trigger_func() is marked __always_inline, so USDT invocations will be
 	 * inlined in two different places, meaning that each USDT will have
 	 * at least 2 different places to be attached to. This verifies that

tools/testing/selftests/bpf/prog_tests/verifier.c

@@ -45,6 +45,7 @@
 #include "verifier_ldsx.skel.h"
 #include "verifier_leak_ptr.skel.h"
 #include "verifier_linked_scalars.skel.h"
+#include "verifier_load_acquire.skel.h"
 #include "verifier_loops1.skel.h"
 #include "verifier_lwt.skel.h"
 #include "verifier_map_in_map.skel.h"
@@ -80,6 +81,7 @@
 #include "verifier_spill_fill.skel.h"
 #include "verifier_spin_lock.skel.h"
 #include "verifier_stack_ptr.skel.h"
+#include "verifier_store_release.skel.h"
 #include "verifier_subprog_precision.skel.h"
 #include "verifier_subreg.skel.h"
 #include "verifier_tailcall_jit.skel.h"
@@ -121,7 +123,7 @@ static void run_tests_aux(const char *skel_name,
 	/* test_verifier tests are executed w/o CAP_SYS_ADMIN, do the same here */
 	err = cap_disable_effective(1ULL << CAP_SYS_ADMIN, &old_caps);
 	if (err) {
-		PRINT_FAIL("failed to drop CAP_SYS_ADMIN: %i, %s\n", err, strerror(err));
+		PRINT_FAIL("failed to drop CAP_SYS_ADMIN: %i, %s\n", err, strerror(-err));
 		return;
 	}
 
@@ -131,7 +133,7 @@ static void run_tests_aux(const char *skel_name,
 
 	err = cap_enable_effective(old_caps, NULL);
 	if (err)
-		PRINT_FAIL("failed to restore CAP_SYS_ADMIN: %i, %s\n", err, strerror(err));
+		PRINT_FAIL("failed to restore CAP_SYS_ADMIN: %i, %s\n", err, strerror(-err));
 }
 
 #define RUN(skel) run_tests_aux(#skel, skel##__elf_bytes, NULL)
@@ -173,6 +175,7 @@ void test_verifier_int_ptr(void)              { RUN(verifier_int_ptr); }
 void test_verifier_iterating_callbacks(void)  { RUN(verifier_iterating_callbacks); }
 void test_verifier_jeq_infer_not_null(void)   { RUN(verifier_jeq_infer_not_null); }
 void test_verifier_jit_convergence(void)      { RUN(verifier_jit_convergence); }
+void test_verifier_load_acquire(void)         { RUN(verifier_load_acquire); }
 void test_verifier_ld_ind(void)               { RUN(verifier_ld_ind); }
 void test_verifier_ldsx(void)                  { RUN(verifier_ldsx); }
 void test_verifier_leak_ptr(void)             { RUN(verifier_leak_ptr); }
@@ -211,6 +214,7 @@ void test_verifier_sockmap_mutate(void)       { RUN(verifier_sockmap_mutate); }
 void test_verifier_spill_fill(void)           { RUN(verifier_spill_fill); }
 void test_verifier_spin_lock(void)            { RUN(verifier_spin_lock); }
 void test_verifier_stack_ptr(void)            { RUN(verifier_stack_ptr); }
+void test_verifier_store_release(void)        { RUN(verifier_store_release); }
 void test_verifier_subprog_precision(void)    { RUN(verifier_subprog_precision); }
 void test_verifier_subreg(void)               { RUN(verifier_subreg); }
 void test_verifier_tailcall_jit(void)         { RUN(verifier_tailcall_jit); }

tools/testing/selftests/bpf/prog_tests/xdp_vlan.c

@@ -0,0 +1,175 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Network topology:
+ *  -----------        -----------
+ *  |  NS1    |        |   NS2   |
+ *  | veth0  -|--------|- veth0  |
+ *  -----------        -----------
+ *
+ */
+
+#define _GNU_SOURCE
+#include <net/if.h>
+#include <uapi/linux/if_link.h>
+
+#include "network_helpers.h"
+#include "test_progs.h"
+#include "test_xdp_vlan.skel.h"
+
+
+#define VETH_NAME	"veth0"
+#define NS_MAX_SIZE	32
+#define NS1_NAME	"ns-xdp-vlan-1-"
+#define NS2_NAME	"ns-xdp-vlan-2-"
+#define NS1_IP_ADDR	"100.64.10.1"
+#define NS2_IP_ADDR	"100.64.10.2"
+#define VLAN_ID		4011
+
+static int setup_network(char *ns1, char *ns2)
+{
+	if (!ASSERT_OK(append_tid(ns1, NS_MAX_SIZE), "create ns1 name"))
+		goto fail;
+	if (!ASSERT_OK(append_tid(ns2, NS_MAX_SIZE), "create ns2 name"))
+		goto fail;
+
+	SYS(fail, "ip netns add %s", ns1);
+	SYS(fail, "ip netns add %s", ns2);
+	SYS(fail, "ip -n %s link add %s type veth peer name %s netns %s",
+	    ns1, VETH_NAME, VETH_NAME, ns2);
+
+	/* NOTICE: XDP require VLAN header inside packet payload
+	 *  - Thus, disable VLAN offloading driver features
+	 */
+	SYS(fail, "ip netns exec %s ethtool -K %s rxvlan off txvlan off", ns1, VETH_NAME);
+	SYS(fail, "ip netns exec %s ethtool -K %s rxvlan off txvlan off", ns2, VETH_NAME);
+
+	/* NS1 configuration */
+	SYS(fail, "ip -n %s addr add %s/24 dev %s", ns1, NS1_IP_ADDR, VETH_NAME);
+	SYS(fail, "ip -n %s link set %s up", ns1, VETH_NAME);
+
+	/* NS2 configuration */
+	SYS(fail, "ip -n %s link add link %s name %s.%d type vlan id %d",
+	    ns2, VETH_NAME, VETH_NAME, VLAN_ID, VLAN_ID);
+	SYS(fail, "ip -n %s addr add %s/24 dev %s.%d", ns2, NS2_IP_ADDR, VETH_NAME, VLAN_ID);
+	SYS(fail, "ip -n %s link set %s up", ns2, VETH_NAME);
+	SYS(fail, "ip -n %s link set %s.%d up", ns2, VETH_NAME, VLAN_ID);
+
+	/* At this point ping should fail because VLAN tags are only used by NS2 */
+	return !SYS_NOFAIL("ip netns exec %s ping -W 1 -c1 %s", ns2, NS1_IP_ADDR);
+
+fail:
+	return -1;
+}
+
+static void cleanup_network(const char *ns1, const char *ns2)
+{
+	SYS_NOFAIL("ip netns del %s", ns1);
+	SYS_NOFAIL("ip netns del %s", ns2);
+}
+
+static void xdp_vlan(struct bpf_program *xdp, struct bpf_program *tc, u32 flags)
+{
+	LIBBPF_OPTS(bpf_tc_hook, tc_hook, .attach_point = BPF_TC_EGRESS);
+	LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1);
+	char ns1[NS_MAX_SIZE] = NS1_NAME;
+	char ns2[NS_MAX_SIZE] = NS2_NAME;
+	struct nstoken *nstoken = NULL;
+	int interface;
+	int ret;
+
+	if (!ASSERT_OK(setup_network(ns1, ns2), "setup network"))
+		goto cleanup;
+
+	nstoken = open_netns(ns1);
+	if (!ASSERT_OK_PTR(nstoken, "open NS1"))
+		goto cleanup;
+
+	interface = if_nametoindex(VETH_NAME);
+	if (!ASSERT_NEQ(interface, 0, "get interface index"))
+		goto cleanup;
+
+	ret = bpf_xdp_attach(interface, bpf_program__fd(xdp), flags, NULL);
+	if (!ASSERT_OK(ret, "attach xdp_vlan_change"))
+		goto cleanup;
+
+	tc_hook.ifindex = interface;
+	ret = bpf_tc_hook_create(&tc_hook);
+	if (!ASSERT_OK(ret, "bpf_tc_hook_create"))
+		goto detach_xdp;
+
+	/* Now we'll use BPF programs to pop/push the VLAN tags */
+	tc_opts.prog_fd = bpf_program__fd(tc);
+	ret = bpf_tc_attach(&tc_hook, &tc_opts);
+	if (!ASSERT_OK(ret, "bpf_tc_attach"))
+		goto detach_xdp;
+
+	close_netns(nstoken);
+	nstoken = NULL;
+
+	/* Now the namespaces can reach each-other, test with pings */
+	SYS(detach_tc, "ip netns exec %s ping -i 0.2 -W 2 -c 2 %s > /dev/null", ns1, NS2_IP_ADDR);
+	SYS(detach_tc, "ip netns exec %s ping -i 0.2 -W 2 -c 2 %s > /dev/null", ns2, NS1_IP_ADDR);
+
+
+detach_tc:
+	bpf_tc_detach(&tc_hook, &tc_opts);
+detach_xdp:
+	bpf_xdp_detach(interface, flags, NULL);
+cleanup:
+	close_netns(nstoken);
+	cleanup_network(ns1, ns2);
+}
+
+/* First test: Remove VLAN by setting VLAN ID 0, using "xdp_vlan_change"
+ * egress use TC to add back VLAN tag 4011
+ */
+void test_xdp_vlan_change(void)
+{
+	struct test_xdp_vlan *skel;
+
+	skel = test_xdp_vlan__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "xdp_vlan__open_and_load"))
+		return;
+
+	if (test__start_subtest("0"))
+		xdp_vlan(skel->progs.xdp_vlan_change, skel->progs.tc_vlan_push, 0);
+
+	if (test__start_subtest("DRV_MODE"))
+		xdp_vlan(skel->progs.xdp_vlan_change, skel->progs.tc_vlan_push,
+			 XDP_FLAGS_DRV_MODE);
+
+	if (test__start_subtest("SKB_MODE"))
+		xdp_vlan(skel->progs.xdp_vlan_change, skel->progs.tc_vlan_push,
+			 XDP_FLAGS_SKB_MODE);
+
+	test_xdp_vlan__destroy(skel);
+}
+
+/* Second test: XDP prog fully remove vlan header
+ *
+ * Catch kernel bug for generic-XDP, that doesn't allow us to
+ * remove a VLAN header, because skb->protocol still contain VLAN
+ * ETH_P_8021Q indication, and this cause overwriting of our changes.
+ */
+void test_xdp_vlan_remove(void)
+{
+	struct test_xdp_vlan *skel;
+
+	skel = test_xdp_vlan__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "xdp_vlan__open_and_load"))
+		return;
+
+	if (test__start_subtest("0"))
+		xdp_vlan(skel->progs.xdp_vlan_remove_outer2, skel->progs.tc_vlan_push, 0);
+
+	if (test__start_subtest("DRV_MODE"))
+		xdp_vlan(skel->progs.xdp_vlan_remove_outer2, skel->progs.tc_vlan_push,
+			 XDP_FLAGS_DRV_MODE);
+
+	if (test__start_subtest("SKB_MODE"))
+		xdp_vlan(skel->progs.xdp_vlan_remove_outer2, skel->progs.tc_vlan_push,
+			 XDP_FLAGS_SKB_MODE);
+
+	test_xdp_vlan__destroy(skel);
+}

tools/testing/selftests/bpf/progs/arena_atomics.c

@@ -6,6 +6,8 @@
 #include <stdbool.h>
 #include <stdatomic.h>
 #include "bpf_arena_common.h"
+#include "../../../include/linux/filter.h"
+#include "bpf_misc.h"
 
 struct {
 	__uint(type, BPF_MAP_TYPE_ARENA);
@@ -19,9 +21,17 @@ struct {
 } arena SEC(".maps");
 
 #if defined(ENABLE_ATOMICS_TESTS) && defined(__BPF_FEATURE_ADDR_SPACE_CAST)
-bool skip_tests __attribute((__section__(".data"))) = false;
+bool skip_all_tests __attribute((__section__(".data"))) = false;
 #else
-bool skip_tests = true;
+bool skip_all_tests = true;
+#endif
+
+#if defined(ENABLE_ATOMICS_TESTS) &&		  \
+	defined(__BPF_FEATURE_ADDR_SPACE_CAST) && \
+	(defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86))
+bool skip_lacq_srel_tests __attribute((__section__(".data"))) = false;
+#else
+bool skip_lacq_srel_tests = true;
 #endif
 
 __u32 pid = 0;
@@ -274,4 +284,111 @@ int uaf(const void *ctx)
 	return 0;
 }
 
+#if __clang_major__ >= 18
+__u8 __arena_global load_acquire8_value = 0x12;
+__u16 __arena_global load_acquire16_value = 0x1234;
+__u32 __arena_global load_acquire32_value = 0x12345678;
+__u64 __arena_global load_acquire64_value = 0x1234567890abcdef;
+
+__u8 __arena_global load_acquire8_result = 0;
+__u16 __arena_global load_acquire16_result = 0;
+__u32 __arena_global load_acquire32_result = 0;
+__u64 __arena_global load_acquire64_result = 0;
+#else
+/* clang-17 crashes if the .addr_space.1 ELF section has holes. Work around
+ * this issue by defining the below variables as 64-bit.
+ */
+__u64 __arena_global load_acquire8_value;
+__u64 __arena_global load_acquire16_value;
+__u64 __arena_global load_acquire32_value;
+__u64 __arena_global load_acquire64_value;
+
+__u64 __arena_global load_acquire8_result;
+__u64 __arena_global load_acquire16_result;
+__u64 __arena_global load_acquire32_result;
+__u64 __arena_global load_acquire64_result;
+#endif
+
+SEC("raw_tp/sys_enter")
+int load_acquire(const void *ctx)
+{
+#if defined(ENABLE_ATOMICS_TESTS) &&		  \
+	defined(__BPF_FEATURE_ADDR_SPACE_CAST) && \
+	(defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86))
+
+#define LOAD_ACQUIRE_ARENA(SIZEOP, SIZE, SRC, DST)	\
+	{ asm volatile (				\
+	"r1 = %[" #SRC "] ll;"				\
+	"r1 = addr_space_cast(r1, 0x0, 0x1);"		\
+	".8byte %[load_acquire_insn];"			\
+	"r3 = %[" #DST "] ll;"				\
+	"r3 = addr_space_cast(r3, 0x0, 0x1);"		\
+	"*(" #SIZE " *)(r3 + 0) = r2;"			\
+	:						\
+	: __imm_addr(SRC),				\
+	  __imm_insn(load_acquire_insn,			\
+		     BPF_ATOMIC_OP(BPF_##SIZEOP, BPF_LOAD_ACQ,	\
+				   BPF_REG_2, BPF_REG_1, 0)),	\
+	  __imm_addr(DST)				\
+	: __clobber_all); }				\
+
+	LOAD_ACQUIRE_ARENA(B, u8, load_acquire8_value, load_acquire8_result)
+	LOAD_ACQUIRE_ARENA(H, u16, load_acquire16_value,
+			   load_acquire16_result)
+	LOAD_ACQUIRE_ARENA(W, u32, load_acquire32_value,
+			   load_acquire32_result)
+	LOAD_ACQUIRE_ARENA(DW, u64, load_acquire64_value,
+			   load_acquire64_result)
+#undef LOAD_ACQUIRE_ARENA
+
+#endif
+	return 0;
+}
+
+#if __clang_major__ >= 18
+__u8 __arena_global store_release8_result = 0;
+__u16 __arena_global store_release16_result = 0;
+__u32 __arena_global store_release32_result = 0;
+__u64 __arena_global store_release64_result = 0;
+#else
+/* clang-17 crashes if the .addr_space.1 ELF section has holes. Work around
+ * this issue by defining the below variables as 64-bit.
+ */
+__u64 __arena_global store_release8_result;
+__u64 __arena_global store_release16_result;
+__u64 __arena_global store_release32_result;
+__u64 __arena_global store_release64_result;
+#endif
+
+SEC("raw_tp/sys_enter")
+int store_release(const void *ctx)
+{
+#if defined(ENABLE_ATOMICS_TESTS) &&		  \
+	defined(__BPF_FEATURE_ADDR_SPACE_CAST) && \
+	(defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86))
+
+#define STORE_RELEASE_ARENA(SIZEOP, DST, VAL)	\
+	{ asm volatile (			\
+	"r1 = " VAL ";"				\
+	"r2 = %[" #DST "] ll;"			\
+	"r2 = addr_space_cast(r2, 0x0, 0x1);"	\
+	".8byte %[store_release_insn];"		\
+	:					\
+	: __imm_addr(DST),			\
+	  __imm_insn(store_release_insn,	\
+		     BPF_ATOMIC_OP(BPF_##SIZEOP, BPF_STORE_REL,	\
+				   BPF_REG_2, BPF_REG_1, 0))	\
+	: __clobber_all); }			\
+
+	STORE_RELEASE_ARENA(B, store_release8_result, "0x12")
+	STORE_RELEASE_ARENA(H, store_release16_result, "0x1234")
+	STORE_RELEASE_ARENA(W, store_release32_result, "0x12345678")
+	STORE_RELEASE_ARENA(DW, store_release64_result,
+			    "0x1234567890abcdef ll")
+#undef STORE_RELEASE_ARENA
+
+#endif
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";

tools/testing/selftests/bpf/progs/arena_spin_lock.c

@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+#include "bpf_arena_spin_lock.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARENA);
+	__uint(map_flags, BPF_F_MMAPABLE);
+	__uint(max_entries, 100); /* number of pages */
+#ifdef __TARGET_ARCH_arm64
+	__ulong(map_extra, 0x1ull << 32); /* start of mmap() region */
+#else
+	__ulong(map_extra, 0x1ull << 44); /* start of mmap() region */
+#endif
+} arena SEC(".maps");
+
+int cs_count;
+
+#if defined(ENABLE_ATOMICS_TESTS) && defined(__BPF_FEATURE_ADDR_SPACE_CAST)
+arena_spinlock_t __arena lock;
+int test_skip = 1;
+#else
+int test_skip = 2;
+#endif
+
+int counter;
+int limit;
+
+SEC("tc")
+int prog(void *ctx)
+{
+	int ret = -2;
+
+#if defined(ENABLE_ATOMICS_TESTS) && defined(__BPF_FEATURE_ADDR_SPACE_CAST)
+	unsigned long flags;
+
+	if ((ret = arena_spin_lock_irqsave(&lock, flags)))
+		return ret;
+	if (counter != limit)
+		counter++;
+	bpf_repeat(cs_count);
+	ret = 0;
+	arena_spin_unlock_irqrestore(&lock, flags);
+#endif
+	return ret;
+}
+
+char _license[] SEC("license") = "GPL";

tools/testing/selftests/bpf/progs/bpf_iter_tasks.c

@@ -9,6 +9,13 @@ char _license[] SEC("license") = "GPL";
 uint32_t tid = 0;
 int num_unknown_tid = 0;
 int num_known_tid = 0;
+void *user_ptr = 0;
+void *user_ptr_long = 0;
+uint32_t pid = 0;
+
+static char big_str1[5000];
+static char big_str2[5005];
+static char big_str3[4996];
 
 SEC("iter/task")
 int dump_task(struct bpf_iter__task *ctx)
@@ -35,7 +42,9 @@ int dump_task(struct bpf_iter__task *ctx)
 }
 
 int num_expected_failure_copy_from_user_task = 0;
+int num_expected_failure_copy_from_user_task_str = 0;
 int num_success_copy_from_user_task = 0;
+int num_success_copy_from_user_task_str = 0;
 
 SEC("iter.s/task")
 int dump_task_sleepable(struct bpf_iter__task *ctx)
@@ -44,6 +53,9 @@ int dump_task_sleepable(struct bpf_iter__task *ctx)
 	struct task_struct *task = ctx->task;
 	static const char info[] = "    === END ===";
 	struct pt_regs *regs;
+	char task_str1[10] = "aaaaaaaaaa";
+	char task_str2[10], task_str3[10];
+	char task_str4[20] = "aaaaaaaaaaaaaaaaaaaa";
 	void *ptr;
 	uint32_t user_data = 0;
 	int ret;
@@ -78,8 +90,106 @@ int dump_task_sleepable(struct bpf_iter__task *ctx)
 		BPF_SEQ_PRINTF(seq, "%s\n", info);
 		return 0;
 	}
+
 	++num_success_copy_from_user_task;
 
+	/* Read an invalid pointer and ensure we get an error */
+	ptr = NULL;
+	ret = bpf_copy_from_user_task_str((char *)task_str1, sizeof(task_str1), ptr, task, 0);
+	if (ret >= 0 || task_str1[9] != 'a' || task_str1[0] != '\0') {
+		BPF_SEQ_PRINTF(seq, "%s\n", info);
+		return 0;
+	}
+
+	/* Read an invalid pointer and ensure we get error with pad zeros flag */
+	ptr = NULL;
+	ret = bpf_copy_from_user_task_str((char *)task_str1, sizeof(task_str1),
+					  ptr, task, BPF_F_PAD_ZEROS);
+	if (ret >= 0 || task_str1[9] != '\0' || task_str1[0] != '\0') {
+		BPF_SEQ_PRINTF(seq, "%s\n", info);
+		return 0;
+	}
+
+	++num_expected_failure_copy_from_user_task_str;
+
+	/* Same length as the string */
+	ret = bpf_copy_from_user_task_str((char *)task_str2, 10, user_ptr, task, 0);
+	/* only need to do the task pid check once */
+	if (bpf_strncmp(task_str2, 10, "test_data\0") != 0 || ret != 10 || task->tgid != pid) {
+		BPF_SEQ_PRINTF(seq, "%s\n", info);
+		return 0;
+	}
+
+	/* Shorter length than the string */
+	ret = bpf_copy_from_user_task_str((char *)task_str3, 2, user_ptr, task, 0);
+	if (bpf_strncmp(task_str3, 2, "t\0") != 0 || ret != 2) {
+		BPF_SEQ_PRINTF(seq, "%s\n", info);
+		return 0;
+	}
+
+	/* Longer length than the string */
+	ret = bpf_copy_from_user_task_str((char *)task_str4, 20, user_ptr, task, 0);
+	if (bpf_strncmp(task_str4, 10, "test_data\0") != 0 || ret != 10
+	    || task_str4[sizeof(task_str4) - 1] != 'a') {
+		BPF_SEQ_PRINTF(seq, "%s\n", info);
+		return 0;
+	}
+
+	/* Longer length than the string with pad zeros flag */
+	ret = bpf_copy_from_user_task_str((char *)task_str4, 20, user_ptr, task, BPF_F_PAD_ZEROS);
+	if (bpf_strncmp(task_str4, 10, "test_data\0") != 0 || ret != 10
+	    || task_str4[sizeof(task_str4) - 1] != '\0') {
+		BPF_SEQ_PRINTF(seq, "%s\n", info);
+		return 0;
+	}
+
+	/* Longer length than the string past a page boundary */
+	ret = bpf_copy_from_user_task_str(big_str1, 5000, user_ptr, task, 0);
+	if (bpf_strncmp(big_str1, 10, "test_data\0") != 0 || ret != 10) {
+		BPF_SEQ_PRINTF(seq, "%s\n", info);
+		return 0;
+	}
+
+	/* String that crosses a page boundary */
+	ret = bpf_copy_from_user_task_str(big_str1, 5000, user_ptr_long, task, BPF_F_PAD_ZEROS);
+	if (bpf_strncmp(big_str1, 4, "baba") != 0 || ret != 5000
+	    || bpf_strncmp(big_str1 + 4996, 4, "bab\0") != 0) {
+		BPF_SEQ_PRINTF(seq, "%s\n", info);
+		return 0;
+	}
+
+	for (int i = 0; i < 4999; ++i) {
+		if (i % 2 == 0) {
+			if (big_str1[i] != 'b') {
+				BPF_SEQ_PRINTF(seq, "%s\n", info);
+				return 0;
+			}
+		} else {
+			if (big_str1[i] != 'a') {
+				BPF_SEQ_PRINTF(seq, "%s\n", info);
+				return 0;
+			}
+		}
+	}
+
+	/* Longer length than the string that crosses a page boundary */
+	ret = bpf_copy_from_user_task_str(big_str2, 5005, user_ptr_long, task, BPF_F_PAD_ZEROS);
+	if (bpf_strncmp(big_str2, 4, "baba") != 0 || ret != 5000
+	    || bpf_strncmp(big_str2 + 4996, 5, "bab\0\0") != 0) {
+		BPF_SEQ_PRINTF(seq, "%s\n", info);
+		return 0;
+	}
+
+	/* Shorter length than the string that crosses a page boundary */
+	ret = bpf_copy_from_user_task_str(big_str3, 4996, user_ptr_long, task, 0);
+	if (bpf_strncmp(big_str3, 4, "baba") != 0 || ret != 4996
+	    || bpf_strncmp(big_str3 + 4992, 4, "bab\0") != 0) {
+		BPF_SEQ_PRINTF(seq, "%s\n", info);
+		return 0;
+	}
+
+	++num_success_copy_from_user_task_str;
+
 	if (ctx->meta->seq_num == 0)
 		BPF_SEQ_PRINTF(seq, "    tgid      gid     data\n");
 

tools/testing/selftests/bpf/progs/bpf_misc.h

@@ -135,6 +135,8 @@
 #define __arch_arm64		__arch("ARM64")
 #define __arch_riscv64		__arch("RISCV64")
 #define __caps_unpriv(caps)	__attribute__((btf_decl_tag("comment:test_caps_unpriv=" EXPAND_QUOTE(caps))))
+#define __load_if_JITed()	__attribute__((btf_decl_tag("comment:load_mode=jited")))
+#define __load_if_no_JITed()	__attribute__((btf_decl_tag("comment:load_mode=no_jited")))
 
 /* Define common capabilities tested using __caps_unpriv */
 #define CAP_NET_ADMIN		12
@@ -172,6 +174,9 @@
 #elif defined(__TARGET_ARCH_riscv)
 #define SYSCALL_WRAPPER 1
 #define SYS_PREFIX "__riscv_"
+#elif defined(__TARGET_ARCH_powerpc)
+#define SYSCALL_WRAPPER 1
+#define SYS_PREFIX ""
 #else
 #define SYSCALL_WRAPPER 0
 #define SYS_PREFIX "__se_"
@@ -208,4 +213,21 @@
 #define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
 #endif
 
+#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) ||	\
+     (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) ||		\
+     defined(__TARGET_ARCH_arm) || defined(__TARGET_ARCH_s390) ||	\
+     defined(__TARGET_ARCH_loongarch)) &&				\
+	__clang_major__ >= 18
+#define CAN_USE_GOTOL
+#endif
+
+#if _clang_major__ >= 18
+#define CAN_USE_BPF_ST
+#endif
+
+#if __clang_major__ >= 18 && defined(ENABLE_ATOMICS_TESTS) && \
+	(defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86))
+#define CAN_USE_LOAD_ACQ_STORE_REL
+#endif
+
 #endif

tools/testing/selftests/bpf/progs/bpf_tracing_net.h

@@ -15,7 +15,11 @@
 #define SO_KEEPALIVE		9
 #define SO_PRIORITY		12
 #define SO_REUSEPORT		15
+#if defined(__TARGET_ARCH_powerpc)
+#define SO_RCVLOWAT		16
+#else
 #define SO_RCVLOWAT		18
+#endif
 #define SO_BINDTODEVICE		25
 #define SO_MARK			36
 #define SO_MAX_PACING_RATE	47

tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_bad_signed_arr_elem_sz.c

@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_arrays___err_bad_signed_arr_elem_sz x) {}

tools/testing/selftests/bpf/progs/cgroup_preorder.c

@@ -0,0 +1,41 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+unsigned int idx;
+__u8 result[4];
+
+SEC("cgroup/getsockopt")
+int child(struct bpf_sockopt *ctx)
+{
+	if (idx < 4)
+		result[idx++] = 1;
+	return 1;
+}
+
+SEC("cgroup/getsockopt")
+int child_2(struct bpf_sockopt *ctx)
+{
+	if (idx < 4)
+		result[idx++] = 2;
+	return 1;
+}
+
+SEC("cgroup/getsockopt")
+int parent(struct bpf_sockopt *ctx)
+{
+	if (idx < 4)
+		result[idx++] = 3;
+	return 1;
+}
+
+SEC("cgroup/getsockopt")
+int parent_2(struct bpf_sockopt *ctx)
+{
+	if (idx < 4)
+		result[idx++] = 4;
+	return 1;
+}

tools/testing/selftests/bpf/progs/changes_pkt_data.c

@@ -1,39 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-
-#include <linux/bpf.h>
-#include <bpf/bpf_helpers.h>
-
-__noinline
-long changes_pkt_data(struct __sk_buff *sk)
-{
-	return bpf_skb_pull_data(sk, 0);
-}
-
-__noinline __weak
-long does_not_change_pkt_data(struct __sk_buff *sk)
-{
-	return 0;
-}
-
-SEC("?tc")
-int main_with_subprogs(struct __sk_buff *sk)
-{
-	changes_pkt_data(sk);
-	does_not_change_pkt_data(sk);
-	return 0;
-}
-
-SEC("?tc")
-int main_changes(struct __sk_buff *sk)
-{
-	bpf_skb_pull_data(sk, 0);
-	return 0;
-}
-
-SEC("?tc")
-int main_does_not_change(struct __sk_buff *sk)
-{
-	return 0;
-}
-
-char _license[] SEC("license") = "GPL";

tools/testing/selftests/bpf/progs/compute_live_registers.c

@@ -0,0 +1,424 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "../../../include/linux/filter.h"
+#include "bpf_arena_common.h"
+#include "bpf_misc.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, __u64);
+} test_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARENA);
+	__uint(map_flags, BPF_F_MMAPABLE);
+	__uint(max_entries, 1);
+} arena SEC(".maps");
+
+SEC("socket")
+__log_level(2)
+__msg(" 0: .......... (b7) r0 = 42")
+__msg(" 1: 0......... (bf) r1 = r0")
+__msg(" 2: .1........ (bf) r2 = r1")
+__msg(" 3: ..2....... (bf) r3 = r2")
+__msg(" 4: ...3...... (bf) r4 = r3")
+__msg(" 5: ....4..... (bf) r5 = r4")
+__msg(" 6: .....5.... (bf) r6 = r5")
+__msg(" 7: ......6... (bf) r7 = r6")
+__msg(" 8: .......7.. (bf) r8 = r7")
+__msg(" 9: ........8. (bf) r9 = r8")
+__msg("10: .........9 (bf) r0 = r9")
+__msg("11: 0......... (95) exit")
+__naked void assign_chain(void)
+{
+	asm volatile (
+		"r0 = 42;"
+		"r1 = r0;"
+		"r2 = r1;"
+		"r3 = r2;"
+		"r4 = r3;"
+		"r5 = r4;"
+		"r6 = r5;"
+		"r7 = r6;"
+		"r8 = r7;"
+		"r9 = r8;"
+		"r0 = r9;"
+		"exit;"
+		::: __clobber_all);
+}
+
+SEC("socket")
+__log_level(2)
+__msg("0: .......... (b7) r1 = 7")
+__msg("1: .1........ (07) r1 += 7")
+__msg("2: .......... (b7) r2 = 7")
+__msg("3: ..2....... (b7) r3 = 42")
+__msg("4: ..23...... (0f) r2 += r3")
+__msg("5: .......... (b7) r0 = 0")
+__msg("6: 0......... (95) exit")
+__naked void arithmetics(void)
+{
+	asm volatile (
+		"r1 = 7;"
+		"r1 += 7;"
+		"r2 = 7;"
+		"r3 = 42;"
+		"r2 += r3;"
+		"r0 = 0;"
+		"exit;"
+		::: __clobber_all);
+}
+
+#ifdef CAN_USE_BPF_ST
+SEC("socket")
+__log_level(2)
+__msg("  1: .1........ (07) r1 += -8")
+__msg("  2: .1........ (7a) *(u64 *)(r1 +0) = 7")
+__msg("  3: .1........ (b7) r2 = 42")
+__msg("  4: .12....... (7b) *(u64 *)(r1 +0) = r2")
+__msg("  5: .12....... (7b) *(u64 *)(r1 +0) = r2")
+__msg("  6: .......... (b7) r0 = 0")
+__naked void store(void)
+{
+	asm volatile (
+		"r1 = r10;"
+		"r1 += -8;"
+		"*(u64 *)(r1 +0) = 7;"
+		"r2 = 42;"
+		"*(u64 *)(r1 +0) = r2;"
+		"*(u64 *)(r1 +0) = r2;"
+		"r0 = 0;"
+		"exit;"
+		::: __clobber_all);
+}
+#endif
+
+SEC("socket")
+__log_level(2)
+__msg("1: ....4..... (07) r4 += -8")
+__msg("2: ....4..... (79) r5 = *(u64 *)(r4 +0)")
+__msg("3: ....45.... (07) r4 += -8")
+__naked void load(void)
+{
+	asm volatile (
+		"r4 = r10;"
+		"r4 += -8;"
+		"r5 = *(u64 *)(r4 +0);"
+		"r4 += -8;"
+		"r0 = r5;"
+		"exit;"
+		::: __clobber_all);
+}
+
+SEC("socket")
+__log_level(2)
+__msg("0: .1........ (61) r2 = *(u32 *)(r1 +0)")
+__msg("1: ..2....... (d4) r2 = le64 r2")
+__msg("2: ..2....... (bf) r0 = r2")
+__naked void endian(void)
+{
+	asm volatile (
+		"r2 = *(u32 *)(r1 +0);"
+		"r2 = le64 r2;"
+		"r0 = r2;"
+		"exit;"
+		::: __clobber_all);
+}
+
+SEC("socket")
+__log_level(2)
+__msg(" 8: 0......... (b7) r1 = 1")
+__msg(" 9: 01........ (db) r1 = atomic64_fetch_add((u64 *)(r0 +0), r1)")
+__msg("10: 01........ (c3) lock *(u32 *)(r0 +0) += r1")
+__msg("11: 01........ (db) r1 = atomic64_xchg((u64 *)(r0 +0), r1)")
+__msg("12: 01........ (bf) r2 = r0")
+__msg("13: .12....... (bf) r0 = r1")
+__msg("14: 012....... (db) r0 = atomic64_cmpxchg((u64 *)(r2 +0), r0, r1)")
+__naked void atomic(void)
+{
+	asm volatile (
+		"r2 = r10;"
+		"r2 += -8;"
+		"r1 = 0;"
+		"*(u64 *)(r2 +0) = r1;"
+		"r1 = %[test_map] ll;"
+		"call %[bpf_map_lookup_elem];"
+		"if r0 == 0 goto 1f;"
+		"r1 = 1;"
+		"r1 = atomic_fetch_add((u64 *)(r0 +0), r1);"
+		".8byte %[add_nofetch];" /* same as "lock *(u32 *)(r0 +0) += r1;" */
+		"r1 = xchg_64(r0 + 0, r1);"
+		"r2 = r0;"
+		"r0 = r1;"
+		"r0 = cmpxchg_64(r2 + 0, r0, r1);"
+		"1: exit;"
+		:
+		: __imm(bpf_map_lookup_elem),
+		  __imm_addr(test_map),
+		  __imm_insn(add_nofetch, BPF_ATOMIC_OP(BPF_W, BPF_ADD, BPF_REG_0, BPF_REG_1, 0))
+		: __clobber_all);
+}
+
+#ifdef CAN_USE_LOAD_ACQ_STORE_REL
+
+SEC("socket")
+__log_level(2)
+__msg("2: .12....... (db) store_release((u64 *)(r2 -8), r1)")
+__msg("3: .......... (bf) r3 = r10")
+__msg("4: ...3...... (db) r4 = load_acquire((u64 *)(r3 -8))")
+__naked void atomic_load_acq_store_rel(void)
+{
+	asm volatile (
+		"r1 = 42;"
+		"r2 = r10;"
+		".8byte %[store_release_insn];" /* store_release((u64 *)(r2 - 8), r1); */
+		"r3 = r10;"
+		".8byte %[load_acquire_insn];" /* r4 = load_acquire((u64 *)(r3 + 0)); */
+		"r0 = r4;"
+		"exit;"
+		:
+		: __imm_insn(store_release_insn,
+			     BPF_ATOMIC_OP(BPF_DW, BPF_STORE_REL, BPF_REG_2, BPF_REG_1, -8)),
+		  __imm_insn(load_acquire_insn,
+			     BPF_ATOMIC_OP(BPF_DW, BPF_LOAD_ACQ, BPF_REG_4, BPF_REG_3, -8))
+		: __clobber_all);
+}
+
+#endif /* CAN_USE_LOAD_ACQ_STORE_REL */
+
+SEC("socket")
+__log_level(2)
+__msg("4: .12....7.. (85) call bpf_trace_printk#6")
+__msg("5: 0......7.. (0f) r0 += r7")
+__naked void regular_call(void)
+{
+	asm volatile (
+		"r7 = 1;"
+		"r1 = r10;"
+		"r1 += -8;"
+		"r2 = 1;"
+		"call %[bpf_trace_printk];"
+		"r0 += r7;"
+		"exit;"
+		:
+		: __imm(bpf_trace_printk)
+		: __clobber_all);
+}
+
+SEC("socket")
+__log_level(2)
+__msg("2: 012....... (25) if r1 > 0x7 goto pc+1")
+__msg("3: ..2....... (bf) r0 = r2")
+__naked void if1(void)
+{
+	asm volatile (
+		"r0 = 1;"
+		"r2 = 2;"
+		"if r1 > 0x7 goto +1;"
+		"r0 = r2;"
+		"exit;"
+		::: __clobber_all);
+}
+
+SEC("socket")
+__log_level(2)
+__msg("3: 0123...... (2d) if r1 > r3 goto pc+1")
+__msg("4: ..2....... (bf) r0 = r2")
+__naked void if2(void)
+{
+	asm volatile (
+		"r0 = 1;"
+		"r2 = 2;"
+		"r3 = 7;"
+		"if r1 > r3 goto +1;"
+		"r0 = r2;"
+		"exit;"
+		::: __clobber_all);
+}
+
+SEC("socket")
+__log_level(2)
+__msg("0: .......... (b7) r1 = 0")
+__msg("1: .1........ (b7) r2 = 7")
+__msg("2: .12....... (25) if r1 > 0x7 goto pc+4")
+__msg("3: .12....... (07) r1 += 1")
+__msg("4: .12....... (27) r2 *= 2")
+__msg("5: .12....... (05) goto pc+0")
+__msg("6: .12....... (05) goto pc-5")
+__msg("7: .......... (b7) r0 = 0")
+__msg("8: 0......... (95) exit")
+__naked void loop(void)
+{
+	asm volatile (
+		"r1 = 0;"
+		"r2 = 7;"
+		"if r1 > 0x7 goto +4;"
+		"r1 += 1;"
+		"r2 *= 2;"
+		"goto +0;"
+		"goto -5;"
+		"r0 = 0;"
+		"exit;"
+		:
+		: __imm(bpf_trace_printk)
+		: __clobber_all);
+}
+
+#ifdef CAN_USE_GOTOL
+SEC("socket")
+__log_level(2)
+__msg("2: .123...... (25) if r1 > 0x7 goto pc+2")
+__msg("3: ..2....... (bf) r0 = r2")
+__msg("4: 0......... (06) gotol pc+1")
+__msg("5: ...3...... (bf) r0 = r3")
+__msg("6: 0......... (95) exit")
+__naked void gotol(void)
+{
+	asm volatile (
+		"r2 = 42;"
+		"r3 = 24;"
+		"if r1 > 0x7 goto +2;"
+		"r0 = r2;"
+		"gotol +1;"
+		"r0 = r3;"
+		"exit;"
+		:
+		: __imm(bpf_trace_printk)
+		: __clobber_all);
+}
+#endif
+
+SEC("socket")
+__log_level(2)
+__msg("0: .......... (b7) r1 = 1")
+__msg("1: .1........ (e5) may_goto pc+1")
+__msg("2: .......... (05) goto pc-3")
+__msg("3: .1........ (bf) r0 = r1")
+__msg("4: 0......... (95) exit")
+__naked void may_goto(void)
+{
+	asm volatile (
+	"1: r1 = 1;"
+	".8byte %[may_goto];"
+	"goto 1b;"
+	"r0 = r1;"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id),
+	  __imm_insn(may_goto, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, +1 /* offset */, 0))
+	: __clobber_all);
+}
+
+SEC("socket")
+__log_level(2)
+__msg("1: 0......... (18) r2 = 0x7")
+__msg("3: 0.2....... (0f) r0 += r2")
+__naked void ldimm64(void)
+{
+	asm volatile (
+		"r0 = 0;"
+		"r2 = 0x7 ll;"
+		"r0 += r2;"
+		"exit;"
+		:
+		:: __clobber_all);
+}
+
+/* No rules specific for LD_ABS/LD_IND, default behaviour kicks in */
+SEC("socket")
+__log_level(2)
+__msg("2: 0123456789 (30) r0 = *(u8 *)skb[42]")
+__msg("3: 012.456789 (0f) r7 += r0")
+__msg("4: 012.456789 (b7) r3 = 42")
+__msg("5: 0123456789 (50) r0 = *(u8 *)skb[r3 + 0]")
+__msg("6: 0......7.. (0f) r7 += r0")
+__naked void ldabs(void)
+{
+	asm volatile (
+		"r6 = r1;"
+		"r7 = 0;"
+		"r0 = *(u8 *)skb[42];"
+		"r7 += r0;"
+		"r3 = 42;"
+		".8byte %[ld_ind];" /* same as "r0 = *(u8 *)skb[r3];" */
+		"r7 += r0;"
+		"r0 = r7;"
+		"exit;"
+		:
+		: __imm_insn(ld_ind, BPF_LD_IND(BPF_B, BPF_REG_3, 0))
+		: __clobber_all);
+}
+
+
+#ifdef __BPF_FEATURE_ADDR_SPACE_CAST
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+__log_level(2)
+__msg(" 6: .12345.... (85) call bpf_arena_alloc_pages")
+__msg(" 7: 0......... (bf) r1 = addr_space_cast(r0, 0, 1)")
+__msg(" 8: .1........ (b7) r2 = 42")
+__naked void addr_space_cast(void)
+{
+	asm volatile (
+		"r1 = %[arena] ll;"
+		"r2 = 0;"
+		"r3 = 1;"
+		"r4 = 0;"
+		"r5 = 0;"
+		"call %[bpf_arena_alloc_pages];"
+		"r1 = addr_space_cast(r0, 0, 1);"
+		"r2 = 42;"
+		"*(u64 *)(r1 +0) = r2;"
+		"r0 = 0;"
+		"exit;"
+		:
+		: __imm(bpf_arena_alloc_pages),
+		  __imm_addr(arena)
+		: __clobber_all);
+}
+#endif
+
+static __used __naked int aux1(void)
+{
+	asm volatile (
+		"r0 = r1;"
+		"r0 += r2;"
+		"exit;"
+		::: __clobber_all);
+}
+
+SEC("socket")
+__log_level(2)
+__msg("0: ....45.... (b7) r1 = 1")
+__msg("1: .1..45.... (b7) r2 = 2")
+__msg("2: .12.45.... (b7) r3 = 3")
+/* Conservative liveness for subprog parameters. */
+__msg("3: .12345.... (85) call pc+2")
+__msg("4: .......... (b7) r0 = 0")
+__msg("5: 0......... (95) exit")
+__msg("6: .12....... (bf) r0 = r1")
+__msg("7: 0.2....... (0f) r0 += r2")
+/* Conservative liveness for subprog return value. */
+__msg("8: 0......... (95) exit")
+__naked void subprog1(void)
+{
+	asm volatile (
+		"r1 = 1;"
+		"r2 = 2;"
+		"r3 = 3;"
+		"call aux1;"
+		"r0 = 0;"
+		"exit;"
+		::: __clobber_all);
+}
+
+/* to retain debug info for BTF generation */
+void kfunc_root(void)
+{
+	bpf_arena_alloc_pages(0, 0, 0, 0, 0);
+}
+
+char _license[] SEC("license") = "GPL";

tools/testing/selftests/bpf/progs/connect4_dropper.c

@@ -13,12 +13,14 @@
 #define VERDICT_REJECT	0
 #define VERDICT_PROCEED	1
 
+int port;
+
 SEC("cgroup/connect4")
 int connect_v4_dropper(struct bpf_sock_addr *ctx)
 {
 	if (ctx->type != SOCK_STREAM)
 		return VERDICT_PROCEED;
-	if (ctx->user_port == bpf_htons(60120))
+	if (ctx->user_port == bpf_htons(port))
 		return VERDICT_REJECT;
 	return VERDICT_PROCEED;
 }

tools/testing/selftests/bpf/progs/core_reloc_types.h

@@ -347,6 +347,7 @@ struct core_reloc_nesting___err_too_deep {
  */
 struct core_reloc_arrays_output {
 	int a2;
+	int a3;
 	char b123;
 	int c1c;
 	int d00d;
@@ -455,6 +456,15 @@ struct core_reloc_arrays___err_bad_zero_sz_arr {
 	struct core_reloc_arrays_substruct d[1][2];
 };
 
+struct core_reloc_arrays___err_bad_signed_arr_elem_sz {
+	/* int -> short (signed!): not supported case */
+	short a[5];
+	char b[2][3][4];
+	struct core_reloc_arrays_substruct c[3];
+	struct core_reloc_arrays_substruct d[1][2];
+	struct core_reloc_arrays_substruct f[][2];
+};
+
 /*
  * PRIMITIVES
  */

tools/testing/selftests/bpf/progs/cpumask_common.h

@@ -61,6 +61,7 @@ u32 bpf_cpumask_any_distribute(const struct cpumask *src) __ksym __weak;
 u32 bpf_cpumask_any_and_distribute(const struct cpumask *src1,
 				   const struct cpumask *src2) __ksym __weak;
 u32 bpf_cpumask_weight(const struct cpumask *cpumask) __ksym __weak;
+int bpf_cpumask_populate(struct cpumask *cpumask, void *src, size_t src__sz) __ksym __weak;
 
 void bpf_rcu_read_lock(void) __ksym __weak;
 void bpf_rcu_read_unlock(void) __ksym __weak;

tools/testing/selftests/bpf/progs/cpumask_failure.c

@@ -222,3 +222,41 @@ int BPF_PROG(test_invalid_nested_array, struct task_struct *task, u64 clone_flag
 
 	return 0;
 }
+
+SEC("tp_btf/task_newtask")
+__failure __msg("type=scalar expected=fp")
+int BPF_PROG(test_populate_invalid_destination, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *invalid = (struct bpf_cpumask *)0x123456;
+	u64 bits;
+	int ret;
+
+	ret = bpf_cpumask_populate((struct cpumask *)invalid, &bits, sizeof(bits));
+	if (!ret)
+		err = 2;
+
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+__failure __msg("leads to invalid memory access")
+int BPF_PROG(test_populate_invalid_source, struct task_struct *task, u64 clone_flags)
+{
+	void *garbage = (void *)0x123456;
+	struct bpf_cpumask *local;
+	int ret;
+
+	local = create_cpumask();
+	if (!local) {
+		err = 1;
+		return 0;
+	}
+
+	ret = bpf_cpumask_populate((struct cpumask *)local, garbage, 8);
+	if (!ret)
+		err = 2;
+
+	bpf_cpumask_release(local);
+
+	return 0;
+}

tools/testing/selftests/bpf/progs/cpumask_success.c

@@ -749,7 +749,6 @@ out:
 }
 
 SEC("tp_btf/task_newtask")
-__success
 int BPF_PROG(test_refcount_null_tracking, struct task_struct *task, u64 clone_flags)
 {
 	struct bpf_cpumask *mask1, *mask2;
@@ -770,3 +769,122 @@ free_masks_return:
 		bpf_cpumask_release(mask2);
 	return 0;
 }
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_populate_reject_small_mask, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *local;
+	u8 toofewbits;
+	int ret;
+
+	if (!is_test_task())
+		return 0;
+
+	local = create_cpumask();
+	if (!local)
+		return 0;
+
+	/* The kfunc should prevent this operation */
+	ret = bpf_cpumask_populate((struct cpumask *)local, &toofewbits, sizeof(toofewbits));
+	if (ret != -EACCES)
+		err = 2;
+
+	bpf_cpumask_release(local);
+
+	return 0;
+}
+
+/* Mask is guaranteed to be large enough for bpf_cpumask_t. */
+#define CPUMASK_TEST_MASKLEN (sizeof(cpumask_t))
+
+/* Add an extra word for the test_populate_reject_unaligned test. */
+u64 bits[CPUMASK_TEST_MASKLEN / 8 + 1];
+extern bool CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS __kconfig __weak;
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_populate_reject_unaligned, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *mask;
+	char *src;
+	int ret;
+
+	if (!is_test_task())
+		return 0;
+
+	/* Skip if unaligned accesses are fine for this arch.  */
+	if (CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
+		return 0;
+
+	mask = bpf_cpumask_create();
+	if (!mask) {
+		err = 1;
+		return 0;
+	}
+
+	/* Misalign the source array by a byte. */
+	src = &((char *)bits)[1];
+
+	ret = bpf_cpumask_populate((struct cpumask *)mask, src, CPUMASK_TEST_MASKLEN);
+	if (ret != -EINVAL)
+		err = 2;
+
+	bpf_cpumask_release(mask);
+
+	return 0;
+}
+
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_populate, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *mask;
+	bool bit;
+	int ret;
+	int i;
+
+	if (!is_test_task())
+		return 0;
+
+	/* Set only odd bits. */
+	__builtin_memset(bits, 0xaa, CPUMASK_TEST_MASKLEN);
+
+	mask = bpf_cpumask_create();
+	if (!mask) {
+		err = 1;
+		return 0;
+	}
+
+	/* Pass the entire bits array, the kfunc will only copy the valid bits. */
+	ret = bpf_cpumask_populate((struct cpumask *)mask, bits, CPUMASK_TEST_MASKLEN);
+	if (ret) {
+		err = 2;
+		goto out;
+	}
+
+	/*
+	 * Test is there to appease the verifier. We cannot directly
+	 * access NR_CPUS, the upper bound for nr_cpus, so we infer
+	 * it from the size of cpumask_t.
+	 */
+	if (nr_cpus < 0 || nr_cpus >= CPUMASK_TEST_MASKLEN * 8) {
+		err = 3;
+		goto out;
+	}
+
+	bpf_for(i, 0, nr_cpus) {
+		/* Odd-numbered bits should be set, even ones unset. */
+		bit = bpf_cpumask_test_cpu(i, (const struct cpumask *)mask);
+		if (bit == (i % 2 != 0))
+			continue;
+
+		err = 4;
+		break;
+	}
+
+out:
+	bpf_cpumask_release(mask);
+
+	return 0;
+}
+
+#undef CPUMASK_TEST_MASKLEN

tools/testing/selftests/bpf/progs/dynptr_success.c

@@ -1,20 +1,19 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2022 Facebook */
 
+#include <vmlinux.h>
 #include <string.h>
 #include <stdbool.h>
-#include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 #include "bpf_misc.h"
-#include "bpf_kfuncs.h"
 #include "errno.h"
 
 char _license[] SEC("license") = "GPL";
 
 int pid, err, val;
 
-struct sample {
+struct ringbuf_sample {
 	int pid;
 	int seq;
 	long value;
@@ -121,7 +120,7 @@ int test_dynptr_data(void *ctx)
 
 static int ringbuf_callback(__u32 index, void *data)
 {
-	struct sample *sample;
+	struct ringbuf_sample *sample;
 
 	struct bpf_dynptr *ptr = (struct bpf_dynptr *)data;
 
@@ -138,7 +137,7 @@ SEC("?tp/syscalls/sys_enter_nanosleep")
 int test_ringbuf(void *ctx)
 {
 	struct bpf_dynptr ptr;
-	struct sample *sample;
+	struct ringbuf_sample *sample;
 
 	if (bpf_get_current_pid_tgid() >> 32 != pid)
 		return 0;
@@ -567,3 +566,117 @@ int BPF_PROG(test_dynptr_skb_tp_btf, void *skb, void *location)
 
 	return 1;
 }
+
+static inline int bpf_memcmp(const char *a, const char *b, u32 size)
+{
+	int i;
+
+	bpf_for(i, 0, size) {
+		if (a[i] != b[i])
+			return a[i] < b[i] ? -1 : 1;
+	}
+	return 0;
+}
+
+SEC("?tp/syscalls/sys_enter_nanosleep")
+int test_dynptr_copy(void *ctx)
+{
+	char data[] = "hello there, world!!";
+	char buf[32] = {'\0'};
+	__u32 sz = sizeof(data);
+	struct bpf_dynptr src, dst;
+
+	bpf_ringbuf_reserve_dynptr(&ringbuf, sz, 0, &src);
+	bpf_ringbuf_reserve_dynptr(&ringbuf, sz, 0, &dst);
+
+	/* Test basic case of copying contiguous memory backed dynptrs */
+	err = bpf_dynptr_write(&src, 0, data, sz, 0);
+	err = err ?: bpf_dynptr_copy(&dst, 0, &src, 0, sz);
+	err = err ?: bpf_dynptr_read(buf, sz, &dst, 0, 0);
+	err = err ?: bpf_memcmp(data, buf, sz);
+
+	/* Test that offsets are handled correctly */
+	err = err ?: bpf_dynptr_copy(&dst, 3, &src, 5, sz - 5);
+	err = err ?: bpf_dynptr_read(buf, sz - 5, &dst, 3, 0);
+	err = err ?: bpf_memcmp(data + 5, buf, sz - 5);
+
+	bpf_ringbuf_discard_dynptr(&src, 0);
+	bpf_ringbuf_discard_dynptr(&dst, 0);
+	return 0;
+}
+
+SEC("xdp")
+int test_dynptr_copy_xdp(struct xdp_md *xdp)
+{
+	struct bpf_dynptr ptr_buf, ptr_xdp;
+	char data[] = "qwertyuiopasdfghjkl";
+	char buf[32] = {'\0'};
+	__u32 len = sizeof(data);
+	int i, chunks = 200;
+
+	/* ptr_xdp is backed by non-contiguous memory */
+	bpf_dynptr_from_xdp(xdp, 0, &ptr_xdp);
+	bpf_ringbuf_reserve_dynptr(&ringbuf, len * chunks, 0, &ptr_buf);
+
+	/* Destination dynptr is backed by non-contiguous memory */
+	bpf_for(i, 0, chunks) {
+		err = bpf_dynptr_write(&ptr_buf, i * len, data, len, 0);
+		if (err)
+			goto out;
+	}
+
+	err = bpf_dynptr_copy(&ptr_xdp, 0, &ptr_buf, 0, len * chunks);
+	if (err)
+		goto out;
+
+	bpf_for(i, 0, chunks) {
+		__builtin_memset(buf, 0, sizeof(buf));
+		err = bpf_dynptr_read(&buf, len, &ptr_xdp, i * len, 0);
+		if (err)
+			goto out;
+		if (bpf_memcmp(data, buf, len) != 0)
+			goto out;
+	}
+
+	/* Source dynptr is backed by non-contiguous memory */
+	__builtin_memset(buf, 0, sizeof(buf));
+	bpf_for(i, 0, chunks) {
+		err = bpf_dynptr_write(&ptr_buf, i * len, buf, len, 0);
+		if (err)
+			goto out;
+	}
+
+	err = bpf_dynptr_copy(&ptr_buf, 0, &ptr_xdp, 0, len * chunks);
+	if (err)
+		goto out;
+
+	bpf_for(i, 0, chunks) {
+		__builtin_memset(buf, 0, sizeof(buf));
+		err = bpf_dynptr_read(&buf, len, &ptr_buf, i * len, 0);
+		if (err)
+			goto out;
+		if (bpf_memcmp(data, buf, len) != 0)
+			goto out;
+	}
+
+	/* Both source and destination dynptrs are backed by non-contiguous memory */
+	err = bpf_dynptr_copy(&ptr_xdp, 2, &ptr_xdp, len, len * (chunks - 1));
+	if (err)
+		goto out;
+
+	bpf_for(i, 0, chunks - 1) {
+		__builtin_memset(buf, 0, sizeof(buf));
+		err = bpf_dynptr_read(&buf, len, &ptr_xdp, 2 + i * len, 0);
+		if (err)
+			goto out;
+		if (bpf_memcmp(data, buf, len) != 0)
+			goto out;
+	}
+
+	if (bpf_dynptr_copy(&ptr_xdp, 2000, &ptr_xdp, 0, len * chunks) != -E2BIG)
+		err = 1;
+
+out:
+	bpf_ringbuf_discard_dynptr(&ptr_buf, 0);
+	return XDP_DROP;
+}

tools/testing/selftests/bpf/progs/fexit_noreturns.c

@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+SEC("fexit/do_exit")
+__failure __msg("Attaching fexit/fmod_ret to __noreturn functions is rejected.")
+int BPF_PROG(noreturns)
+{
+	return 0;
+}

tools/testing/selftests/bpf/progs/irq.c

@@ -222,7 +222,7 @@ int __noinline global_local_irq_balance(void)
 }
 
 SEC("?tc")
-__failure __msg("global function calls are not allowed with IRQs disabled")
+__success
 int irq_global_subprog(struct __sk_buff *ctx)
 {
 	unsigned long flags;
@@ -441,4 +441,73 @@ int irq_ooo_refs_array(struct __sk_buff *ctx)
 	return 0;
 }
 
+int __noinline
+global_subprog(int i)
+{
+	if (i)
+		bpf_printk("%p", &i);
+	return i;
+}
+
+int __noinline
+global_sleepable_helper_subprog(int i)
+{
+	if (i)
+		bpf_copy_from_user(&i, sizeof(i), NULL);
+	return i;
+}
+
+int __noinline
+global_sleepable_kfunc_subprog(int i)
+{
+	if (i)
+		bpf_copy_from_user_str(&i, sizeof(i), NULL, 0);
+	global_subprog(i);
+	return i;
+}
+
+int __noinline
+global_subprog_calling_sleepable_global(int i)
+{
+	if (!i)
+		global_sleepable_kfunc_subprog(i);
+	return i;
+}
+
+SEC("?syscall")
+__success
+int irq_non_sleepable_global_subprog(void *ctx)
+{
+	unsigned long flags;
+
+	bpf_local_irq_save(&flags);
+	global_subprog(0);
+	bpf_local_irq_restore(&flags);
+	return 0;
+}
+
+SEC("?syscall")
+__failure __msg("global functions that may sleep are not allowed in non-sleepable context")
+int irq_sleepable_helper_global_subprog(void *ctx)
+{
+	unsigned long flags;
+
+	bpf_local_irq_save(&flags);
+	global_sleepable_helper_subprog(0);
+	bpf_local_irq_restore(&flags);
+	return 0;
+}
+
+SEC("?syscall")
+__failure __msg("global functions that may sleep are not allowed in non-sleepable context")
+int irq_sleepable_global_subprog_indirect(void *ctx)
+{
+	unsigned long flags;
+
+	bpf_local_irq_save(&flags);
+	global_subprog_calling_sleepable_global(0);
+	bpf_local_irq_restore(&flags);
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";

tools/testing/selftests/bpf/progs/iters.c

@@ -7,6 +7,8 @@
 #include "bpf_misc.h"
 #include "bpf_compiler.h"
 
+#define unlikely(x)	__builtin_expect(!!(x), 0)
+
 static volatile int zero = 0;
 
 int my_pid;
@@ -1174,6 +1176,122 @@ __naked int loop_state_deps2(void)
 	);
 }
 
+SEC("?raw_tp")
+__failure
+__msg("math between fp pointer and register with unbounded")
+__flag(BPF_F_TEST_STATE_FREQ)
+__naked int loop_state_deps3(void)
+{
+	/* This is equivalent to a C program below.
+	 *
+	 *   if (random() != 24) {       // assume false branch is placed first
+	 *     i = iter_new();           // fp[-8]
+	 *     while (iter_next(i));
+	 *     iter_destroy(i);
+	 *     return;
+	 *   }
+	 *
+	 *   for (i = 10; i > 0; i--);   // increase dfs_depth for child states
+	 *
+	 *   i = iter_new();             // fp[-8]
+	 *   b = -24;                    // r8
+	 *   for (;;) {                  // checkpoint (L)
+	 *     if (iter_next(i))         // checkpoint (N)
+	 *       break;
+	 *     if (random() == 77) {     // assume false branch is placed first
+	 *       *(u64 *)(r10 + b) = 7;  // this is not safe when b == -25
+	 *       iter_destroy(i);
+	 *       return;
+	 *     }
+	 *     if (random() == 42) {     // assume false branch is placed first
+	 *       b = -25;
+	 *     }
+	 *   }
+	 *   iter_destroy(i);
+	 *
+	 * In case of a buggy verifier first loop might poison
+	 * env->cur_state->loop_entry with a state having 0 branches
+	 * and small dfs_depth. This would trigger NOT_EXACT states
+	 * comparison for some states within second loop.
+	 * Specifically, checkpoint (L) might be problematic if:
+	 * - branch with '*(u64 *)(r10 + b) = 7' is not explored yet;
+	 * - checkpoint (L) is first reached in state {b=-24};
+	 * - traversal is pruned at checkpoint (N) setting checkpoint's (L)
+	 *   branch count to 0, thus making it eligible for use in pruning;
+	 * - checkpoint (L) is next reached in state {b=-25},
+	 *   this would cause NOT_EXACT comparison with a state {b=-24}
+	 *   while 'b' is not marked precise yet.
+	 */
+	asm volatile (
+		"call %[bpf_get_prandom_u32];"
+		"if r0 == 24 goto 2f;"
+		"r1 = r10;"
+		"r1 += -8;"
+		"r2 = 0;"
+		"r3 = 5;"
+		"call %[bpf_iter_num_new];"
+	"1:"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_next];"
+		"if r0 != 0 goto 1b;"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_destroy];"
+		"r0 = 0;"
+		"exit;"
+	"2:"
+		/* loop to increase dfs_depth */
+		"r0 = 10;"
+	"3:"
+		"r0 -= 1;"
+		"if r0 != 0 goto 3b;"
+		/* end of loop */
+		"r1 = r10;"
+		"r1 += -8;"
+		"r2 = 0;"
+		"r3 = 10;"
+		"call %[bpf_iter_num_new];"
+		"r8 = -24;"
+	"main_loop_%=:"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_next];"
+		"if r0 == 0 goto main_loop_end_%=;"
+		/* first if */
+		"call %[bpf_get_prandom_u32];"
+		"if r0 == 77 goto unsafe_write_%=;"
+		/* second if */
+		"call %[bpf_get_prandom_u32];"
+		"if r0 == 42 goto poison_r8_%=;"
+		/* iterate */
+		"goto main_loop_%=;"
+	"main_loop_end_%=:"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_destroy];"
+		"r0 = 0;"
+		"exit;"
+
+	"unsafe_write_%=:"
+		"r0 = r10;"
+		"r0 += r8;"
+		"r1 = 7;"
+		"*(u64 *)(r0 + 0) = r1;"
+		"goto main_loop_end_%=;"
+
+	"poison_r8_%=:"
+		"r8 = -25;"
+		"goto main_loop_%=;"
+		:
+		: __imm(bpf_get_prandom_u32),
+		  __imm(bpf_iter_num_new),
+		  __imm(bpf_iter_num_next),
+		  __imm(bpf_iter_num_destroy)
+		: __clobber_all
+	);
+}
+
 SEC("?raw_tp")
 __success
 __naked int triple_continue(void)
@@ -1512,4 +1630,25 @@ int iter_destroy_bad_arg(const void *ctx)
 	return 0;
 }
 
+SEC("raw_tp")
+__success
+int clean_live_states(const void *ctx)
+{
+	char buf[1];
+	int i, j, k, l, m, n, o;
+
+	bpf_for(i, 0, 10)
+	bpf_for(j, 0, 10)
+	bpf_for(k, 0, 10)
+	bpf_for(l, 0, 10)
+	bpf_for(m, 0, 10)
+	bpf_for(n, 0, 10)
+	bpf_for(o, 0, 10) {
+		if (unlikely(bpf_get_prandom_u32()))
+			buf[0] = 42;
+		bpf_printk("%s", buf);
+	}
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";

tools/testing/selftests/bpf/progs/netns_cookie_prog.c

@@ -28,6 +28,7 @@ struct {
 } sock_map SEC(".maps");
 
 int tcx_init_netns_cookie, tcx_netns_cookie;
+int cgroup_skb_init_netns_cookie, cgroup_skb_netns_cookie;
 
 SEC("sockops")
 int get_netns_cookie_sockops(struct bpf_sock_ops *ctx)
@@ -91,4 +92,12 @@ int get_netns_cookie_tcx(struct __sk_buff *skb)
 	return TCX_PASS;
 }
 
+SEC("cgroup_skb/ingress")
+int get_netns_cookie_cgroup_skb(struct __sk_buff *skb)
+{
+	cgroup_skb_init_netns_cookie = bpf_get_netns_cookie(NULL);
+	cgroup_skb_netns_cookie = bpf_get_netns_cookie(skb);
+	return SK_PASS;
+}
+
 char _license[] SEC("license") = "GPL";

tools/testing/selftests/bpf/progs/preempt_lock.c

@@ -134,7 +134,7 @@ int __noinline preempt_global_subprog(void)
 }
 
 SEC("?tc")
-__failure __msg("global function calls are not allowed with preemption disabled")
+__success
 int preempt_global_subprog_test(struct __sk_buff *ctx)
 {
 	preempt_disable();
@@ -143,4 +143,70 @@ int preempt_global_subprog_test(struct __sk_buff *ctx)
 	return 0;
 }
 
+int __noinline
+global_subprog(int i)
+{
+	if (i)
+		bpf_printk("%p", &i);
+	return i;
+}
+
+int __noinline
+global_sleepable_helper_subprog(int i)
+{
+	if (i)
+		bpf_copy_from_user(&i, sizeof(i), NULL);
+	return i;
+}
+
+int __noinline
+global_sleepable_kfunc_subprog(int i)
+{
+	if (i)
+		bpf_copy_from_user_str(&i, sizeof(i), NULL, 0);
+	global_subprog(i);
+	return i;
+}
+
+int __noinline
+global_subprog_calling_sleepable_global(int i)
+{
+	if (!i)
+		global_sleepable_kfunc_subprog(i);
+	return i;
+}
+
+SEC("?syscall")
+__failure __msg("global functions that may sleep are not allowed in non-sleepable context")
+int preempt_global_sleepable_helper_subprog(struct __sk_buff *ctx)
+{
+	preempt_disable();
+	if (ctx->mark)
+		global_sleepable_helper_subprog(ctx->mark);
+	preempt_enable();
+	return 0;
+}
+
+SEC("?syscall")
+__failure __msg("global functions that may sleep are not allowed in non-sleepable context")
+int preempt_global_sleepable_kfunc_subprog(struct __sk_buff *ctx)
+{
+	preempt_disable();
+	if (ctx->mark)
+		global_sleepable_kfunc_subprog(ctx->mark);
+	preempt_enable();
+	return 0;
+}
+
+SEC("?syscall")
+__failure __msg("global functions that may sleep are not allowed in non-sleepable context")
+int preempt_global_sleepable_subprog_indirect(struct __sk_buff *ctx)
+{
+	preempt_disable();
+	if (ctx->mark)
+		global_subprog_calling_sleepable_global(ctx->mark);
+	preempt_enable();
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";

tools/testing/selftests/bpf/progs/prepare.c

@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta */
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+//#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+int err;
+
+struct {
+	__uint(type, BPF_MAP_TYPE_RINGBUF);
+	__uint(max_entries, 4096);
+} ringbuf SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, __u32);
+} array_map SEC(".maps");
+
+SEC("cgroup_skb/egress")
+int program(struct __sk_buff *skb)
+{
+	err = 0;
+	return 0;
+}

tools/testing/selftests/bpf/progs/priv_freplace_prog.c

@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+SEC("freplace/xdp_prog1")
+int new_xdp_prog2(struct xdp_md *xd)
+{
+	return XDP_DROP;
+}

tools/testing/selftests/bpf/progs/priv_prog.c

@@ -6,8 +6,8 @@
 
 char _license[] SEC("license") = "GPL";
 
-SEC("kprobe")
-int kprobe_prog(void *ctx)
+SEC("xdp")
+int xdp_prog1(struct xdp_md *xdp)
 {
-	return 1;
+	return XDP_DROP;
 }

tools/testing/selftests/bpf/progs/pro_epilogue_with_kfunc.c

@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "../test_kmods/bpf_testmod.h"
+#include "../test_kmods/bpf_testmod_kfunc.h"
+
+char _license[] SEC("license") = "GPL";
+
+void __kfunc_btf_root(void)
+{
+	bpf_kfunc_st_ops_inc10(NULL);
+}
+
+static __noinline __used int subprog(struct st_ops_args *args)
+{
+	args->a += 1;
+	return args->a;
+}
+
+__success
+/* prologue */
+__xlated("0: r8 = r1")
+__xlated("1: r1 = 0")
+__xlated("2: call kernel-function")
+__xlated("3: if r0 != 0x0 goto pc+5")
+__xlated("4: r6 = *(u64 *)(r8 +0)")
+__xlated("5: r7 = *(u64 *)(r6 +0)")
+__xlated("6: r7 += 1000")
+__xlated("7: *(u64 *)(r6 +0) = r7")
+__xlated("8: goto pc+2")
+__xlated("9: r1 = r0")
+__xlated("10: call kernel-function")
+__xlated("11: r1 = r8")
+/* save __u64 *ctx to stack */
+__xlated("12: *(u64 *)(r10 -8) = r1")
+/* main prog */
+__xlated("13: r1 = *(u64 *)(r1 +0)")
+__xlated("14: r6 = r1")
+__xlated("15: call kernel-function")
+__xlated("16: r1 = r6")
+__xlated("17: call pc+")
+/* epilogue */
+__xlated("18: r1 = 0")
+__xlated("19: r6 = 0")
+__xlated("20: call kernel-function")
+__xlated("21: if r0 != 0x0 goto pc+6")
+__xlated("22: r1 = *(u64 *)(r10 -8)")
+__xlated("23: r1 = *(u64 *)(r1 +0)")
+__xlated("24: r6 = *(u64 *)(r1 +0)")
+__xlated("25: r6 += 10000")
+__xlated("26: *(u64 *)(r1 +0) = r6")
+__xlated("27: goto pc+2")
+__xlated("28: r1 = r0")
+__xlated("29: call kernel-function")
+__xlated("30: r0 = r6")
+__xlated("31: r0 *= 2")
+__xlated("32: exit")
+SEC("struct_ops/test_pro_epilogue")
+__naked int test_kfunc_pro_epilogue(void)
+{
+	asm volatile (
+	"r1 = *(u64 *)(r1 +0);"
+	"r6 = r1;"
+	"call %[bpf_kfunc_st_ops_inc10];"
+	"r1 = r6;"
+	"call subprog;"
+	"exit;"
+	:
+	: __imm(bpf_kfunc_st_ops_inc10)
+	: __clobber_all);
+}
+
+SEC("syscall")
+__retval(22022) /* (PROLOGUE_A [1000] + KFUNC_INC10 + SUBPROG_A [1] + EPILOGUE_A [10000]) * 2 */
+int syscall_pro_epilogue(void *ctx)
+{
+	struct st_ops_args args = {};
+
+	return bpf_kfunc_st_ops_test_pro_epilogue(&args);
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_st_ops pro_epilogue_with_kfunc = {
+	.test_pro_epilogue = (void *)test_kfunc_pro_epilogue,
+};

tools/testing/selftests/bpf/progs/rcu_read_lock.c

@@ -242,7 +242,8 @@ out:
 }
 
 SEC("?lsm.s/bpf")
-int BPF_PROG(inproper_sleepable_kfunc, int cmd, union bpf_attr *attr, unsigned int size)
+int BPF_PROG(inproper_sleepable_kfunc, int cmd, union bpf_attr *attr, unsigned int size,
+	     bool kernel)
 {
 	struct bpf_key *bkey;
 
@@ -439,3 +440,61 @@ int rcu_read_lock_global_subprog_unlock(void *ctx)
 	ret += global_subprog_unlock(ret);
 	return 0;
 }
+
+int __noinline
+global_sleepable_helper_subprog(int i)
+{
+	if (i)
+		bpf_copy_from_user(&i, sizeof(i), NULL);
+	return i;
+}
+
+int __noinline
+global_sleepable_kfunc_subprog(int i)
+{
+	if (i)
+		bpf_copy_from_user_str(&i, sizeof(i), NULL, 0);
+	global_subprog(i);
+	return i;
+}
+
+int __noinline
+global_subprog_calling_sleepable_global(int i)
+{
+	if (!i)
+		global_sleepable_kfunc_subprog(i);
+	return i;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int rcu_read_lock_sleepable_helper_global_subprog(void *ctx)
+{
+	volatile int ret = 0;
+
+	bpf_rcu_read_lock();
+	ret += global_sleepable_helper_subprog(ret);
+	bpf_rcu_read_unlock();
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int rcu_read_lock_sleepable_kfunc_global_subprog(void *ctx)
+{
+	volatile int ret = 0;
+
+	bpf_rcu_read_lock();
+	ret += global_sleepable_kfunc_subprog(ret);
+	bpf_rcu_read_unlock();
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int rcu_read_lock_sleepable_global_subprog_indirect(void *ctx)
+{
+	volatile int ret = 0;
+
+	bpf_rcu_read_lock();
+	ret += global_subprog_calling_sleepable_global(ret);
+	bpf_rcu_read_unlock();
+	return 0;
+}

tools/testing/selftests/bpf/progs/read_vsyscall.c

@@ -8,14 +8,16 @@
 
 int target_pid = 0;
 void *user_ptr = 0;
-int read_ret[9];
+int read_ret[10];
 
 char _license[] SEC("license") = "GPL";
 
 /*
- * This is the only kfunc, the others are helpers
+ * These are the kfuncs, the others are helpers
  */
 int bpf_copy_from_user_str(void *dst, u32, const void *, u64) __weak __ksym;
+int bpf_copy_from_user_task_str(void *dst, u32, const void *,
+				struct task_struct *, u64) __weak __ksym;
 
 SEC("fentry/" SYS_PREFIX "sys_nanosleep")
 int do_probe_read(void *ctx)
@@ -47,6 +49,11 @@ int do_copy_from_user(void *ctx)
 	read_ret[7] = bpf_copy_from_user_task(buf, sizeof(buf), user_ptr,
 					      bpf_get_current_task_btf(), 0);
 	read_ret[8] = bpf_copy_from_user_str((char *)buf, sizeof(buf), user_ptr, 0);
+	read_ret[9] = bpf_copy_from_user_task_str((char *)buf,
+						  sizeof(buf),
+						  user_ptr,
+						  bpf_get_current_task_btf(),
+						  0);
 
 	return 0;
 }

tools/testing/selftests/bpf/progs/set_global_vars.c

@@ -0,0 +1,47 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include "bpf_experimental.h"
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+#include <stdbool.h>
+
+char _license[] SEC("license") = "GPL";
+
+enum Enum { EA1 = 0, EA2 = 11 };
+enum Enumu64 {EB1 = 0llu, EB2 = 12llu };
+enum Enums64 { EC1 = 0ll, EC2 = 13ll };
+
+const volatile __s64 var_s64 = -1;
+const volatile __u64 var_u64 = 0;
+const volatile __s32 var_s32 = -1;
+const volatile __u32 var_u32 = 0;
+const volatile __s16 var_s16 = -1;
+const volatile __u16 var_u16 = 0;
+const volatile __s8 var_s8 = -1;
+const volatile __u8 var_u8 = 0;
+const volatile enum Enum var_ea = EA1;
+const volatile enum Enumu64 var_eb = EB1;
+const volatile enum Enums64 var_ec = EC1;
+const volatile bool var_b = false;
+
+char arr[4] = {0};
+
+SEC("socket")
+int test_set_globals(void *ctx)
+{
+	volatile __s8 a;
+
+	a = var_s64;
+	a = var_u64;
+	a = var_s32;
+	a = var_u32;
+	a = var_s16;
+	a = var_u16;
+	a = var_s8;
+	a = var_u8;
+	a = var_ea;
+	a = var_eb;
+	a = var_ec;
+	a = var_b;
+	return a;
+}

tools/testing/selftests/bpf/progs/strncmp_bench.c

@@ -35,7 +35,10 @@ static __always_inline int local_strncmp(const char *s1, unsigned int sz,
 SEC("tp/syscalls/sys_enter_getpgid")
 int strncmp_no_helper(void *ctx)
 {
-	if (local_strncmp(str, cmp_str_len + 1, target) < 0)
+	const char *target_str = target;
+
+	barrier_var(target_str);
+	if (local_strncmp(str, cmp_str_len + 1, target_str) < 0)
 		__sync_add_and_fetch(&hits, 1);
 	return 0;
 }

tools/testing/selftests/bpf/progs/struct_ops_kptr_return.c

@@ -0,0 +1,30 @@
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "../test_kmods/bpf_testmod.h"
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+void bpf_task_release(struct task_struct *p) __ksym;
+
+/* This test struct_ops BPF programs returning referenced kptr. The verifier should
+ * allow a referenced kptr or a NULL pointer to be returned. A referenced kptr to task
+ * here is acquried automatically as the task argument is tagged with "__ref".
+ */
+SEC("struct_ops/test_return_ref_kptr")
+struct task_struct *BPF_PROG(kptr_return, int dummy,
+			     struct task_struct *task, struct cgroup *cgrp)
+{
+	if (dummy % 2) {
+		bpf_task_release(task);
+		return NULL;
+	}
+	return task;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops testmod_kptr_return = {
+	.test_return_ref_kptr = (void *)kptr_return,
+};
+
+

tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__invalid_scalar.c

@@ -0,0 +1,26 @@
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "../test_kmods/bpf_testmod.h"
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct cgroup *bpf_cgroup_acquire(struct cgroup *p) __ksym;
+void bpf_task_release(struct task_struct *p) __ksym;
+
+/* This test struct_ops BPF programs returning referenced kptr. The verifier should
+ * reject programs returning a non-zero scalar value.
+ */
+SEC("struct_ops/test_return_ref_kptr")
+__failure __msg("At program exit the register R0 has smin=1 smax=1 should have been in [0, 0]")
+struct task_struct *BPF_PROG(kptr_return_fail__invalid_scalar, int dummy,
+			     struct task_struct *task, struct cgroup *cgrp)
+{
+	bpf_task_release(task);
+	return (struct task_struct *)1;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops testmod_kptr_return = {
+	.test_return_ref_kptr = (void *)kptr_return_fail__invalid_scalar,
+};

tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__local_kptr.c

@@ -0,0 +1,34 @@
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "../test_kmods/bpf_testmod.h"
+#include "bpf_experimental.h"
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct cgroup *bpf_cgroup_acquire(struct cgroup *p) __ksym;
+void bpf_task_release(struct task_struct *p) __ksym;
+
+/* This test struct_ops BPF programs returning referenced kptr. The verifier should
+ * reject programs returning a local kptr.
+ */
+SEC("struct_ops/test_return_ref_kptr")
+__failure __msg("At program exit the register R0 is not a known value (ptr_or_null_)")
+struct task_struct *BPF_PROG(kptr_return_fail__local_kptr, int dummy,
+			     struct task_struct *task, struct cgroup *cgrp)
+{
+	struct task_struct *t;
+
+	bpf_task_release(task);
+
+	t = bpf_obj_new(typeof(*task));
+	if (!t)
+		return NULL;
+
+	return t;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops testmod_kptr_return = {
+	.test_return_ref_kptr = (void *)kptr_return_fail__local_kptr,
+};

tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__nonzero_offset.c

@@ -0,0 +1,25 @@
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "../test_kmods/bpf_testmod.h"
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct cgroup *bpf_cgroup_acquire(struct cgroup *p) __ksym;
+void bpf_task_release(struct task_struct *p) __ksym;
+
+/* This test struct_ops BPF programs returning referenced kptr. The verifier should
+ * reject programs returning a modified referenced kptr.
+ */
+SEC("struct_ops/test_return_ref_kptr")
+__failure __msg("dereference of modified trusted_ptr_ ptr R0 off={{[0-9]+}} disallowed")
+struct task_struct *BPF_PROG(kptr_return_fail__nonzero_offset, int dummy,
+			     struct task_struct *task, struct cgroup *cgrp)
+{
+	return (struct task_struct *)&task->jobctl;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops testmod_kptr_return = {
+	.test_return_ref_kptr = (void *)kptr_return_fail__nonzero_offset,
+};

tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__wrong_type.c

@@ -0,0 +1,30 @@
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "../test_kmods/bpf_testmod.h"
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct cgroup *bpf_cgroup_acquire(struct cgroup *p) __ksym;
+void bpf_task_release(struct task_struct *p) __ksym;
+
+/* This test struct_ops BPF programs returning referenced kptr. The verifier should
+ * reject programs returning a referenced kptr of the wrong type.
+ */
+SEC("struct_ops/test_return_ref_kptr")
+__failure __msg("At program exit the register R0 is not a known value (ptr_or_null_)")
+struct task_struct *BPF_PROG(kptr_return_fail__wrong_type, int dummy,
+			     struct task_struct *task, struct cgroup *cgrp)
+{
+	struct task_struct *ret;
+
+	ret = (struct task_struct *)bpf_cgroup_acquire(cgrp);
+	bpf_task_release(task);
+
+	return ret;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops testmod_kptr_return = {
+	.test_return_ref_kptr = (void *)kptr_return_fail__wrong_type,
+};

tools/testing/selftests/bpf/progs/struct_ops_refcounted.c

@@ -0,0 +1,31 @@
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "../test_kmods/bpf_testmod.h"
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+__attribute__((nomerge)) extern void bpf_task_release(struct task_struct *p) __ksym;
+
+/* This is a test BPF program that uses struct_ops to access a referenced
+ * kptr argument. This is a test for the verifier to ensure that it
+ * 1) recongnizes the task as a referenced object (i.e., ref_obj_id > 0), and
+ * 2) the same reference can be acquired from multiple paths as long as it
+ *    has not been released.
+ */
+SEC("struct_ops/test_refcounted")
+int BPF_PROG(refcounted, int dummy, struct task_struct *task)
+{
+	if (dummy == 1)
+		bpf_task_release(task);
+	else
+		bpf_task_release(task);
+	return 0;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops testmod_refcounted = {
+	.test_refcounted = (void *)refcounted,
+};
+
+

tools/testing/selftests/bpf/progs/struct_ops_refcounted_fail__global_subprog.c

@@ -0,0 +1,39 @@
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "../test_kmods/bpf_testmod.h"
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+extern void bpf_task_release(struct task_struct *p) __ksym;
+
+__noinline int subprog_release(__u64 *ctx __arg_ctx)
+{
+	struct task_struct *task = (struct task_struct *)ctx[1];
+	int dummy = (int)ctx[0];
+
+	bpf_task_release(task);
+
+	return dummy + 1;
+}
+
+/* Test that the verifier rejects a program that contains a global
+ * subprogram with referenced kptr arguments
+ */
+SEC("struct_ops/test_refcounted")
+__failure __log_level(2)
+__msg("Validating subprog_release() func#1...")
+__msg("invalid bpf_context access off=8. Reference may already be released")
+int refcounted_fail__global_subprog(unsigned long long *ctx)
+{
+	struct task_struct *task = (struct task_struct *)ctx[1];
+
+	bpf_task_release(task);
+
+	return subprog_release(ctx);
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops testmod_ref_acquire = {
+	.test_refcounted = (void *)refcounted_fail__global_subprog,
+};

tools/testing/selftests/bpf/progs/struct_ops_refcounted_fail__ref_leak.c

@@ -0,0 +1,22 @@
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "../test_kmods/bpf_testmod.h"
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+/* Test that the verifier rejects a program that acquires a referenced
+ * kptr through context without releasing the reference
+ */
+SEC("struct_ops/test_refcounted")
+__failure __msg("Unreleased reference id=1 alloc_insn=0")
+int BPF_PROG(refcounted_fail__ref_leak, int dummy,
+	     struct task_struct *task)
+{
+	return 0;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops testmod_ref_acquire = {
+	.test_refcounted = (void *)refcounted_fail__ref_leak,
+};

tools/testing/selftests/bpf/progs/struct_ops_refcounted_fail__tail_call.c

@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "../test_kmods/bpf_testmod.h"
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 1);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u32));
+} prog_array SEC(".maps");
+
+/* Test that the verifier rejects a program with referenced kptr arguments
+ * that tail call
+ */
+SEC("struct_ops/test_refcounted")
+__failure __msg("program with __ref argument cannot tail call")
+int refcounted_fail__tail_call(unsigned long long *ctx)
+{
+	struct task_struct *task = (struct task_struct *)ctx[1];
+
+	bpf_task_release(task);
+	bpf_tail_call(ctx, &prog_array, 0);
+
+	return 0;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops testmod_ref_acquire = {
+	.test_refcounted = (void *)refcounted_fail__tail_call,
+};
+

tools/testing/selftests/bpf/progs/summarization.c

@@ -0,0 +1,78 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+__noinline
+long changes_pkt_data(struct __sk_buff *sk)
+{
+	return bpf_skb_pull_data(sk, 0);
+}
+
+__noinline __weak
+long does_not_change_pkt_data(struct __sk_buff *sk)
+{
+	return 0;
+}
+
+SEC("?tc")
+int main_changes_with_subprogs(struct __sk_buff *sk)
+{
+	changes_pkt_data(sk);
+	does_not_change_pkt_data(sk);
+	return 0;
+}
+
+SEC("?tc")
+int main_changes(struct __sk_buff *sk)
+{
+	bpf_skb_pull_data(sk, 0);
+	return 0;
+}
+
+SEC("?tc")
+int main_does_not_change(struct __sk_buff *sk)
+{
+	return 0;
+}
+
+__noinline
+long might_sleep(struct pt_regs *ctx __arg_ctx)
+{
+	int i;
+
+	bpf_copy_from_user(&i, sizeof(i), NULL);
+	return i;
+}
+
+__noinline __weak
+long does_not_sleep(struct pt_regs *ctx __arg_ctx)
+{
+	return 0;
+}
+
+SEC("?uprobe.s")
+int main_might_sleep_with_subprogs(struct pt_regs *ctx)
+{
+	might_sleep(ctx);
+	does_not_sleep(ctx);
+	return 0;
+}
+
+SEC("?uprobe.s")
+int main_might_sleep(struct pt_regs *ctx)
+{
+	int i;
+
+	bpf_copy_from_user(&i, sizeof(i), NULL);
+	return i;
+}
+
+SEC("?uprobe.s")
+int main_does_not_sleep(struct pt_regs *ctx)
+{
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";

tools/testing/selftests/bpf/progs/summarization_freplace.c

@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 
-#include <linux/bpf.h>
+#include <vmlinux.h>
 #include <bpf/bpf_helpers.h>
 
 SEC("?freplace")
@@ -15,4 +15,19 @@ long does_not_change_pkt_data(struct __sk_buff *sk)
 	return 0;
 }
 
+SEC("?freplace")
+long might_sleep(struct pt_regs *ctx)
+{
+	int i;
+
+	bpf_copy_from_user(&i, sizeof(i), NULL);
+	return i;
+}
+
+SEC("?freplace")
+long does_not_sleep(struct pt_regs *ctx)
+{
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";

tools/testing/selftests/bpf/progs/test_cgroup1_hierarchy.c

@@ -51,13 +51,13 @@ out:
 }
 
 SEC("lsm/bpf")
-int BPF_PROG(lsm_run, int cmd, union bpf_attr *attr, unsigned int size)
+int BPF_PROG(lsm_run, int cmd, union bpf_attr *attr, unsigned int size, bool kernel)
 {
 	return bpf_link_create_verify(cmd);
 }
 
 SEC("lsm.s/bpf")
-int BPF_PROG(lsm_s_run, int cmd, union bpf_attr *attr, unsigned int size)
+int BPF_PROG(lsm_s_run, int cmd, union bpf_attr *attr, unsigned int size, bool kernel)
 {
 	return bpf_link_create_verify(cmd);
 }

tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c

@@ -15,6 +15,7 @@ struct {
 
 struct core_reloc_arrays_output {
 	int a2;
+	int a3;
 	char b123;
 	int c1c;
 	int d00d;
@@ -41,6 +42,7 @@ int test_core_arrays(void *ctx)
 {
 	struct core_reloc_arrays *in = (void *)&data.in;
 	struct core_reloc_arrays_output *out = (void *)&data.out;
+	int *a;
 
 	if (CORE_READ(&out->a2, &in->a[2]))
 		return 1;
@@ -53,6 +55,9 @@ int test_core_arrays(void *ctx)
 	if (CORE_READ(&out->f01c, &in->f[0][1].c))
 		return 1;
 
+	a = __builtin_preserve_access_index(({ in->a; }));
+	out->a3 = a[0] + a[1] + a[2] + a[3];
+
 	return 0;
 }
 

tools/testing/selftests/bpf/progs/test_get_xattr.c

@@ -6,6 +6,7 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 #include "bpf_kfuncs.h"
+#include "bpf_misc.h"
 
 char _license[] SEC("license") = "GPL";
 
@@ -17,12 +18,23 @@ static const char expected_value[] = "hello";
 char value1[32];
 char value2[32];
 
+/* Matches caller of test_get_xattr() in prog_tests/fs_kfuncs.c */
+static const char xattr_names[][64] = {
+	/* The following work. */
+	"user.kfuncs",
+	"security.bpf.xxx",
+
+	/* The following do not work. */
+	"security.bpf",
+	"security.selinux"
+};
+
 SEC("lsm.s/file_open")
 int BPF_PROG(test_file_open, struct file *f)
 {
 	struct bpf_dynptr value_ptr;
 	__u32 pid;
-	int ret;
+	int ret, i;
 
 	pid = bpf_get_current_pid_tgid() >> 32;
 	if (pid != monitored_pid)
@@ -30,7 +42,11 @@ int BPF_PROG(test_file_open, struct file *f)
 
 	bpf_dynptr_from_mem(value1, sizeof(value1), 0, &value_ptr);
 
-	ret = bpf_get_file_xattr(f, "user.kfuncs", &value_ptr);
+	for (i = 0; i < ARRAY_SIZE(xattr_names); i++) {
+		ret = bpf_get_file_xattr(f, xattr_names[i], &value_ptr);
+		if (ret == sizeof(expected_value))
+			break;
+	}
 	if (ret != sizeof(expected_value))
 		return 0;
 	if (bpf_strncmp(value1, ret, expected_value))
@@ -44,7 +60,7 @@ int BPF_PROG(test_inode_getxattr, struct dentry *dentry, char *name)
 {
 	struct bpf_dynptr value_ptr;
 	__u32 pid;
-	int ret;
+	int ret, i;
 
 	pid = bpf_get_current_pid_tgid() >> 32;
 	if (pid != monitored_pid)
@@ -52,7 +68,11 @@ int BPF_PROG(test_inode_getxattr, struct dentry *dentry, char *name)
 
 	bpf_dynptr_from_mem(value2, sizeof(value2), 0, &value_ptr);
 
-	ret = bpf_get_dentry_xattr(dentry, "user.kfuncs", &value_ptr);
+	for (i = 0; i < ARRAY_SIZE(xattr_names); i++) {
+		ret = bpf_get_dentry_xattr(dentry, xattr_names[i], &value_ptr);
+		if (ret == sizeof(expected_value))
+			break;
+	}
 	if (ret != sizeof(expected_value))
 		return 0;
 	if (bpf_strncmp(value2, ret, expected_value))

tools/testing/selftests/bpf/progs/test_kernel_flag.c

@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright (C) 2025 Microsoft Corporation
+ *
+ * Author: Blaise Boscaccy <bboscaccy@linux.microsoft.com>
+ */
+
+#include "vmlinux.h"
+#include <errno.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+__u32 monitored_tid;
+
+SEC("lsm.s/bpf")
+int BPF_PROG(bpf, int cmd, union bpf_attr *attr, unsigned int size, bool kernel)
+{
+	__u32 tid;
+
+	tid = bpf_get_current_pid_tgid() & 0xFFFFFFFF;
+	if (!kernel || tid != monitored_tid)
+		return 0;
+	else
+		return -EINVAL;
+}

tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c

@@ -36,7 +36,7 @@ char _license[] SEC("license") = "GPL";
 
 SEC("?lsm.s/bpf")
 __failure __msg("cannot pass in dynptr at an offset=-8")
-int BPF_PROG(not_valid_dynptr, int cmd, union bpf_attr *attr, unsigned int size)
+int BPF_PROG(not_valid_dynptr, int cmd, union bpf_attr *attr, unsigned int size, bool kernel)
 {
 	unsigned long val;
 
@@ -46,7 +46,7 @@ int BPF_PROG(not_valid_dynptr, int cmd, union bpf_attr *attr, unsigned int size)
 
 SEC("?lsm.s/bpf")
 __failure __msg("arg#0 expected pointer to stack or const struct bpf_dynptr")
-int BPF_PROG(not_ptr_to_stack, int cmd, union bpf_attr *attr, unsigned int size)
+int BPF_PROG(not_ptr_to_stack, int cmd, union bpf_attr *attr, unsigned int size, bool kernel)
 {
 	unsigned long val = 0;
 
@@ -55,7 +55,7 @@ int BPF_PROG(not_ptr_to_stack, int cmd, union bpf_attr *attr, unsigned int size)
 }
 
 SEC("lsm.s/bpf")
-int BPF_PROG(dynptr_data_null, int cmd, union bpf_attr *attr, unsigned int size)
+int BPF_PROG(dynptr_data_null, int cmd, union bpf_attr *attr, unsigned int size, bool kernel)
 {
 	struct bpf_key *trusted_keyring;
 	struct bpf_dynptr ptr;

tools/testing/selftests/bpf/progs/test_lookup_key.c

@@ -23,7 +23,7 @@ extern struct bpf_key *bpf_lookup_system_key(__u64 id) __ksym;
 extern void bpf_key_put(struct bpf_key *key) __ksym;
 
 SEC("lsm.s/bpf")
-int BPF_PROG(bpf, int cmd, union bpf_attr *attr, unsigned int size)
+int BPF_PROG(bpf, int cmd, union bpf_attr *attr, unsigned int size, bool kernel)
 {
 	struct bpf_key *bkey;
 	__u32 pid;

tools/testing/selftests/bpf/progs/test_ptr_untrusted.c

@@ -7,7 +7,7 @@
 char tp_name[128];
 
 SEC("lsm.s/bpf")
-int BPF_PROG(lsm_run, int cmd, union bpf_attr *attr, unsigned int size)
+int BPF_PROG(lsm_run, int cmd, union bpf_attr *attr, unsigned int size, bool kernel)
 {
 	switch (cmd) {
 	case BPF_RAW_TRACEPOINT_OPEN:

tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c

@@ -1,7 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2018 Facebook */
 
-#include <stdlib.h>
 #include <linux/in.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>

tools/testing/selftests/bpf/progs/test_set_remove_xattr.c

@@ -0,0 +1,133 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <errno.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_kfuncs.h"
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+__u32 monitored_pid;
+
+const char xattr_foo[] = "security.bpf.foo";
+const char xattr_bar[] = "security.bpf.bar";
+static const char xattr_selinux[] = "security.selinux";
+char value_bar[] = "world";
+char read_value[32];
+
+bool set_security_bpf_bar_success;
+bool remove_security_bpf_bar_success;
+bool set_security_selinux_fail;
+bool remove_security_selinux_fail;
+
+char name_buf[32];
+
+static inline bool name_match_foo(const char *name)
+{
+	bpf_probe_read_kernel(name_buf, sizeof(name_buf), name);
+
+	return !bpf_strncmp(name_buf, sizeof(xattr_foo), xattr_foo);
+}
+
+/* Test bpf_set_dentry_xattr and bpf_remove_dentry_xattr */
+SEC("lsm.s/inode_getxattr")
+int BPF_PROG(test_inode_getxattr, struct dentry *dentry, char *name)
+{
+	struct bpf_dynptr value_ptr;
+	__u32 pid;
+	int ret;
+
+	pid = bpf_get_current_pid_tgid() >> 32;
+	if (pid != monitored_pid)
+		return 0;
+
+	/* Only do the following for security.bpf.foo */
+	if (!name_match_foo(name))
+		return 0;
+
+	bpf_dynptr_from_mem(read_value, sizeof(read_value), 0, &value_ptr);
+
+	/* read security.bpf.bar */
+	ret = bpf_get_dentry_xattr(dentry, xattr_bar, &value_ptr);
+
+	if (ret < 0) {
+		/* If security.bpf.bar doesn't exist, set it */
+		bpf_dynptr_from_mem(value_bar, sizeof(value_bar), 0, &value_ptr);
+
+		ret = bpf_set_dentry_xattr(dentry, xattr_bar, &value_ptr, 0);
+		if (!ret)
+			set_security_bpf_bar_success = true;
+		ret = bpf_set_dentry_xattr(dentry, xattr_selinux, &value_ptr, 0);
+		if (ret)
+			set_security_selinux_fail = true;
+	} else {
+		/* If security.bpf.bar exists, remove it */
+		ret = bpf_remove_dentry_xattr(dentry, xattr_bar);
+		if (!ret)
+			remove_security_bpf_bar_success = true;
+
+		ret = bpf_remove_dentry_xattr(dentry, xattr_selinux);
+		if (ret)
+			remove_security_selinux_fail = true;
+	}
+
+	return 0;
+}
+
+bool locked_set_security_bpf_bar_success;
+bool locked_remove_security_bpf_bar_success;
+bool locked_set_security_selinux_fail;
+bool locked_remove_security_selinux_fail;
+
+/* Test bpf_set_dentry_xattr_locked and bpf_remove_dentry_xattr_locked.
+ * It not necessary to differentiate the _locked version and the
+ * not-_locked version in the BPF program. The verifier will fix them up
+ * properly.
+ */
+SEC("lsm.s/inode_setxattr")
+int BPF_PROG(test_inode_setxattr, struct mnt_idmap *idmap,
+	     struct dentry *dentry, const char *name,
+	     const void *value, size_t size, int flags)
+{
+	struct bpf_dynptr value_ptr;
+	__u32 pid;
+	int ret;
+
+	pid = bpf_get_current_pid_tgid() >> 32;
+	if (pid != monitored_pid)
+		return 0;
+
+	/* Only do the following for security.bpf.foo */
+	if (!name_match_foo(name))
+		return 0;
+
+	bpf_dynptr_from_mem(read_value, sizeof(read_value), 0, &value_ptr);
+
+	/* read security.bpf.bar */
+	ret = bpf_get_dentry_xattr(dentry, xattr_bar, &value_ptr);
+
+	if (ret < 0) {
+		/* If security.bpf.bar doesn't exist, set it */
+		bpf_dynptr_from_mem(value_bar, sizeof(value_bar), 0, &value_ptr);
+
+		ret = bpf_set_dentry_xattr(dentry, xattr_bar, &value_ptr, 0);
+		if (!ret)
+			locked_set_security_bpf_bar_success = true;
+		ret = bpf_set_dentry_xattr(dentry, xattr_selinux, &value_ptr, 0);
+		if (ret)
+			locked_set_security_selinux_fail = true;
+	} else {
+		/* If security.bpf.bar exists, remove it */
+		ret = bpf_remove_dentry_xattr(dentry, xattr_bar);
+		if (!ret)
+			locked_remove_security_bpf_bar_success = true;
+
+		ret = bpf_remove_dentry_xattr(dentry, xattr_selinux);
+		if (ret)
+			locked_remove_security_selinux_fail = true;
+	}
+
+	return 0;
+}