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()
  ...

63 files changed, 3078 insertions, 116 deletions

diff --git a/tools/testing/selftests/bpf/progs/arena_atomics.c b/tools/testing/selftests/bpf/progs/arena_atomics.c
index 40dd57fca5cc..a52feff98112 100644
--- a/tools/testing/selftests/bpf/progs/arena_atomics.c
+++ b/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";
diff --git a/tools/testing/selftests/bpf/progs/arena_spin_lock.c b/tools/testing/selftests/bpf/progs/arena_spin_lock.c
new file mode 100644
index 000000000000..c4500c37f85e
--- /dev/null
+++ b/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";
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_tasks.c b/tools/testing/selftests/bpf/progs/bpf_iter_tasks.c
index bc10c4e4b4fa..966ee5a7b066 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_tasks.c
+++ b/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");
 
diff --git a/tools/testing/selftests/bpf/progs/bpf_misc.h b/tools/testing/selftests/bpf/progs/bpf_misc.h
index f45f4352feeb..13a2e22f5465 100644
--- a/tools/testing/selftests/bpf/progs/bpf_misc.h
+++ b/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
diff --git a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
index eb6ed1b7b2ef..659694162739 100644
--- a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
+++ b/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
diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_bad_signed_arr_elem_sz.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_bad_signed_arr_elem_sz.c
new file mode 100644
index 000000000000..21a560427b10
--- /dev/null
+++ b/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) {}
diff --git a/tools/testing/selftests/bpf/progs/cgroup_preorder.c b/tools/testing/selftests/bpf/progs/cgroup_preorder.c
new file mode 100644
index 000000000000..4ef6202baa0a
--- /dev/null
+++ b/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;
+}
diff --git a/tools/testing/selftests/bpf/progs/changes_pkt_data.c b/tools/testing/selftests/bpf/progs/changes_pkt_data.c
deleted file mode 100644
index 43cada48b28a..000000000000
--- a/tools/testing/selftests/bpf/progs/changes_pkt_data.c
+++ /dev/null
@@ -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";
diff --git a/tools/testing/selftests/bpf/progs/compute_live_registers.c b/tools/testing/selftests/bpf/progs/compute_live_registers.c
new file mode 100644
index 000000000000..f3d79aecbf93
--- /dev/null
+++ b/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";
diff --git a/tools/testing/selftests/bpf/progs/connect4_dropper.c b/tools/testing/selftests/bpf/progs/connect4_dropper.c
index d3f4c5e4fb69..a3819a5d09c8 100644
--- a/tools/testing/selftests/bpf/progs/connect4_dropper.c
+++ b/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;
 }
diff --git a/tools/testing/selftests/bpf/progs/core_reloc_types.h b/tools/testing/selftests/bpf/progs/core_reloc_types.h
index fd8e1b4c6762..5760ae015e09 100644
--- a/tools/testing/selftests/bpf/progs/core_reloc_types.h
+++ b/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
  */
diff --git a/tools/testing/selftests/bpf/progs/cpumask_common.h b/tools/testing/selftests/bpf/progs/cpumask_common.h
index 4ece7873ba60..86085b79f5ca 100644
--- a/tools/testing/selftests/bpf/progs/cpumask_common.h
+++ b/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;
diff --git a/tools/testing/selftests/bpf/progs/cpumask_failure.c b/tools/testing/selftests/bpf/progs/cpumask_failure.c
index b40b52548ffb..8a2fd596c8a3 100644
--- a/tools/testing/selftests/bpf/progs/cpumask_failure.c
+++ b/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;
+}
diff --git a/tools/testing/selftests/bpf/progs/cpumask_success.c b/tools/testing/selftests/bpf/progs/cpumask_success.c
index 80ee469b0b60..0e04c31b91c0 100644
--- a/tools/testing/selftests/bpf/progs/cpumask_success.c
+++ b/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
diff --git a/tools/testing/selftests/bpf/progs/dynptr_success.c b/tools/testing/selftests/bpf/progs/dynptr_success.c
index bfcc85686cf0..e1fba28e4a86 100644
--- a/tools/testing/selftests/bpf/progs/dynptr_success.c
+++ b/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;
+}
diff --git a/tools/testing/selftests/bpf/progs/fexit_noreturns.c b/tools/testing/selftests/bpf/progs/fexit_noreturns.c
new file mode 100644
index 000000000000..54654539f550
--- /dev/null
+++ b/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;
+}
diff --git a/tools/testing/selftests/bpf/progs/irq.c b/tools/testing/selftests/bpf/progs/irq.c
index b0b53d980964..298d48d7886d 100644
--- a/tools/testing/selftests/bpf/progs/irq.c
+++ b/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";
diff --git a/tools/testing/selftests/bpf/progs/iters.c b/tools/testing/selftests/bpf/progs/iters.c
index 190822b2f08b..427b72954b87 100644
--- a/tools/testing/selftests/bpf/progs/iters.c
+++ b/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;
@@ -1175,6 +1177,122 @@ __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";
diff --git a/tools/testing/selftests/bpf/progs/netns_cookie_prog.c b/tools/testing/selftests/bpf/progs/netns_cookie_prog.c
index c6edf8dbefeb..94040714af18 100644
--- a/tools/testing/selftests/bpf/progs/netns_cookie_prog.c
+++ b/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";
diff --git a/tools/testing/selftests/bpf/progs/preempt_lock.c b/tools/testing/selftests/bpf/progs/preempt_lock.c
index 6c5797bf0ead..7d04254e61f1 100644
--- a/tools/testing/selftests/bpf/progs/preempt_lock.c
+++ b/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";
diff --git a/tools/testing/selftests/bpf/progs/prepare.c b/tools/testing/selftests/bpf/progs/prepare.c
new file mode 100644
index 000000000000..1f1dd547e4ee
--- /dev/null
+++ b/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;
+}
diff --git a/tools/testing/selftests/bpf/progs/priv_freplace_prog.c b/tools/testing/selftests/bpf/progs/priv_freplace_prog.c
new file mode 100644
index 000000000000..ccf1b04010ba
--- /dev/null
+++ b/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;
+}
diff --git a/tools/testing/selftests/bpf/progs/priv_prog.c b/tools/testing/selftests/bpf/progs/priv_prog.c
index 3c7b2b618c8a..725e29595079 100644
--- a/tools/testing/selftests/bpf/progs/priv_prog.c
+++ b/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;
 }
diff --git a/tools/testing/selftests/bpf/progs/pro_epilogue_with_kfunc.c b/tools/testing/selftests/bpf/progs/pro_epilogue_with_kfunc.c
new file mode 100644
index 000000000000..a5a8f08ac8fb
--- /dev/null
+++ b/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,
+};
diff --git a/tools/testing/selftests/bpf/progs/rcu_read_lock.c b/tools/testing/selftests/bpf/progs/rcu_read_lock.c
index ab3a532b7dd6..43637ee2cdcd 100644
--- a/tools/testing/selftests/bpf/progs/rcu_read_lock.c
+++ b/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;
+}
diff --git a/tools/testing/selftests/bpf/progs/read_vsyscall.c b/tools/testing/selftests/bpf/progs/read_vsyscall.c
index 39ebef430059..395591374d4f 100644
--- a/tools/testing/selftests/bpf/progs/read_vsyscall.c
+++ b/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;
 }
diff --git a/tools/testing/selftests/bpf/progs/set_global_vars.c b/tools/testing/selftests/bpf/progs/set_global_vars.c
new file mode 100644
index 000000000000..9adb5ba4cd4d
--- /dev/null
+++ b/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;
+}
diff --git a/tools/testing/selftests/bpf/progs/strncmp_bench.c b/tools/testing/selftests/bpf/progs/strncmp_bench.c
index 18373a7df76e..f47bf88f8d2a 100644
--- a/tools/testing/selftests/bpf/progs/strncmp_bench.c
+++ b/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;
 }
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_kptr_return.c b/tools/testing/selftests/bpf/progs/struct_ops_kptr_return.c
new file mode 100644
index 000000000000..36386b3c23a1
--- /dev/null
+++ b/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,
+};
+
+
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__invalid_scalar.c b/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__invalid_scalar.c
new file mode 100644
index 000000000000..caeea158ef69
--- /dev/null
+++ b/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,
+};
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__local_kptr.c b/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__local_kptr.c
new file mode 100644
index 000000000000..b8b4f05c3d7f
--- /dev/null
+++ b/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,
+};
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__nonzero_offset.c b/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__nonzero_offset.c
new file mode 100644
index 000000000000..7ddeb28c2329
--- /dev/null
+++ b/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,
+};
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__wrong_type.c b/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__wrong_type.c
new file mode 100644
index 000000000000..6a2dd5367802
--- /dev/null
+++ b/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,
+};
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_refcounted.c b/tools/testing/selftests/bpf/progs/struct_ops_refcounted.c
new file mode 100644
index 000000000000..76dcb6089d7f
--- /dev/null
+++ b/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,
+};
+
+
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_refcounted_fail__global_subprog.c b/tools/testing/selftests/bpf/progs/struct_ops_refcounted_fail__global_subprog.c
new file mode 100644
index 000000000000..ae074aa62852
--- /dev/null
+++ b/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,
+};
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_refcounted_fail__ref_leak.c b/tools/testing/selftests/bpf/progs/struct_ops_refcounted_fail__ref_leak.c
new file mode 100644
index 000000000000..e945b1a04294
--- /dev/null
+++ b/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,
+};
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_refcounted_fail__tail_call.c b/tools/testing/selftests/bpf/progs/struct_ops_refcounted_fail__tail_call.c
new file mode 100644
index 000000000000..3b125025a1f2
--- /dev/null
+++ b/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,
+};
+
diff --git a/tools/testing/selftests/bpf/progs/summarization.c b/tools/testing/selftests/bpf/progs/summarization.c
new file mode 100644
index 000000000000..f89effe82c9e
--- /dev/null
+++ b/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";
diff --git a/tools/testing/selftests/bpf/progs/changes_pkt_data_freplace.c b/tools/testing/selftests/bpf/progs/summarization_freplace.c
index f9a622705f1b..935f00e0e9ea 100644
--- a/tools/testing/selftests/bpf/progs/changes_pkt_data_freplace.c
+++ b/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";
diff --git a/tools/testing/selftests/bpf/progs/test_cgroup1_hierarchy.c b/tools/testing/selftests/bpf/progs/test_cgroup1_hierarchy.c
index 44628865fe1d..4fee0fdc7607 100644
--- a/tools/testing/selftests/bpf/progs/test_cgroup1_hierarchy.c
+++ b/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);
 }
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c b/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c
index 51b3f79df523..448403634eea 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c
+++ b/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;
 }
 
diff --git a/tools/testing/selftests/bpf/progs/test_get_xattr.c b/tools/testing/selftests/bpf/progs/test_get_xattr.c
index 66e737720f7c..54305f4c9f2d 100644
--- a/tools/testing/selftests/bpf/progs/test_get_xattr.c
+++ b/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))
diff --git a/tools/testing/selftests/bpf/progs/test_kernel_flag.c b/tools/testing/selftests/bpf/progs/test_kernel_flag.c
new file mode 100644
index 000000000000..b45fab3be352
--- /dev/null
+++ b/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;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c b/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c
index cd4d752bd089..061befb004c2 100644
--- a/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c
+++ b/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;
diff --git a/tools/testing/selftests/bpf/progs/test_lookup_key.c b/tools/testing/selftests/bpf/progs/test_lookup_key.c
index c73776990ae3..cdbbb12f1491 100644
--- a/tools/testing/selftests/bpf/progs/test_lookup_key.c
+++ b/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;
diff --git a/tools/testing/selftests/bpf/progs/test_ptr_untrusted.c b/tools/testing/selftests/bpf/progs/test_ptr_untrusted.c
index 2fdc44e76624..89b0cd5a3e06 100644
--- a/tools/testing/selftests/bpf/progs/test_ptr_untrusted.c
+++ b/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:
diff --git a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c
index 5eb25c6ad75b..a5be3267dbb0 100644
--- a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c
+++ b/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>
diff --git a/tools/testing/selftests/bpf/progs/test_set_remove_xattr.c b/tools/testing/selftests/bpf/progs/test_set_remove_xattr.c
new file mode 100644
index 000000000000..6a612cf168d3
--- /dev/null
+++ b/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;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_spin_lock_fail.c b/tools/testing/selftests/bpf/progs/test_spin_lock_fail.c
index 1c8b678e2e9a..f678ee6bd7ea 100644
--- a/tools/testing/selftests/bpf/progs/test_spin_lock_fail.c
+++ b/tools/testing/selftests/bpf/progs/test_spin_lock_fail.c
@@ -245,4 +245,73 @@ int lock_global_subprog_call2(struct __sk_buff *ctx)
 	return ret;
 }
 
+int __noinline
+global_subprog_int(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_int(i);
+	return i;
+}
+
+int __noinline
+global_subprog_calling_sleepable_global(int i)
+{
+	if (!i)
+		global_sleepable_kfunc_subprog(i);
+	return i;
+}
+
+SEC("?syscall")
+int lock_global_sleepable_helper_subprog(struct __sk_buff *ctx)
+{
+	int ret = 0;
+
+	bpf_spin_lock(&lockA);
+	if (ctx->mark == 42)
+		ret = global_sleepable_helper_subprog(ctx->mark);
+	bpf_spin_unlock(&lockA);
+	return ret;
+}
+
+SEC("?syscall")
+int lock_global_sleepable_kfunc_subprog(struct __sk_buff *ctx)
+{
+	int ret = 0;
+
+	bpf_spin_lock(&lockA);
+	if (ctx->mark == 42)
+		ret = global_sleepable_kfunc_subprog(ctx->mark);
+	bpf_spin_unlock(&lockA);
+	return ret;
+}
+
+SEC("?syscall")
+int lock_global_sleepable_subprog_indirect(struct __sk_buff *ctx)
+{
+	int ret = 0;
+
+	bpf_spin_lock(&lockA);
+	if (ctx->mark == 42)
+		ret = global_subprog_calling_sleepable_global(ctx->mark);
+	bpf_spin_unlock(&lockA);
+	return ret;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_task_under_cgroup.c b/tools/testing/selftests/bpf/progs/test_task_under_cgroup.c
index 7e750309ce27..0b74b8bd22e8 100644
--- a/tools/testing/selftests/bpf/progs/test_task_under_cgroup.c
+++ b/tools/testing/selftests/bpf/progs/test_task_under_cgroup.c
@@ -49,7 +49,7 @@ out:
 }
 
 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)
 {
 	struct cgroup *cgrp = NULL;
 	struct task_struct *task;
diff --git a/tools/testing/selftests/bpf/progs/test_usdt.c b/tools/testing/selftests/bpf/progs/test_usdt.c
index 505aab9a5234..096488f47fbc 100644
--- a/tools/testing/selftests/bpf/progs/test_usdt.c
+++ b/tools/testing/selftests/bpf/progs/test_usdt.c
@@ -11,6 +11,7 @@ int usdt0_called;
 u64 usdt0_cookie;
 int usdt0_arg_cnt;
 int usdt0_arg_ret;
+int usdt0_arg_size;
 
 SEC("usdt")
 int usdt0(struct pt_regs *ctx)
@@ -26,6 +27,7 @@ int usdt0(struct pt_regs *ctx)
 	usdt0_arg_cnt = bpf_usdt_arg_cnt(ctx);
 	/* should return -ENOENT for any arg_num */
 	usdt0_arg_ret = bpf_usdt_arg(ctx, bpf_get_prandom_u32(), &tmp);
+	usdt0_arg_size = bpf_usdt_arg_size(ctx, bpf_get_prandom_u32());
 	return 0;
 }
 
@@ -34,6 +36,7 @@ u64 usdt3_cookie;
 int usdt3_arg_cnt;
 int usdt3_arg_rets[3];
 u64 usdt3_args[3];
+int usdt3_arg_sizes[3];
 
 SEC("usdt//proc/self/exe:test:usdt3")
 int usdt3(struct pt_regs *ctx)
@@ -50,12 +53,15 @@ int usdt3(struct pt_regs *ctx)
 
 	usdt3_arg_rets[0] = bpf_usdt_arg(ctx, 0, &tmp);
 	usdt3_args[0] = (int)tmp;
+	usdt3_arg_sizes[0] = bpf_usdt_arg_size(ctx, 0);
 
 	usdt3_arg_rets[1] = bpf_usdt_arg(ctx, 1, &tmp);
 	usdt3_args[1] = (long)tmp;
+	usdt3_arg_sizes[1] = bpf_usdt_arg_size(ctx, 1);
 
 	usdt3_arg_rets[2] = bpf_usdt_arg(ctx, 2, &tmp);
 	usdt3_args[2] = (uintptr_t)tmp;
+	usdt3_arg_sizes[2] = bpf_usdt_arg_size(ctx, 2);
 
 	return 0;
 }
@@ -64,12 +70,15 @@ int usdt12_called;
 u64 usdt12_cookie;
 int usdt12_arg_cnt;
 u64 usdt12_args[12];
+int usdt12_arg_sizes[12];
 
 SEC("usdt//proc/self/exe:test:usdt12")
 int BPF_USDT(usdt12, int a1, int a2, long a3, long a4, unsigned a5,
 		     long a6, __u64 a7, uintptr_t a8, int a9, short a10,
 		     short a11, signed char a12)
 {
+	int i;
+
 	if (my_pid != (bpf_get_current_pid_tgid() >> 32))
 		return 0;
 
@@ -90,6 +99,11 @@ int BPF_USDT(usdt12, int a1, int a2, long a3, long a4, unsigned a5,
 	usdt12_args[9] = a10;
 	usdt12_args[10] = a11;
 	usdt12_args[11] = a12;
+
+	bpf_for(i, 0, 12) {
+		usdt12_arg_sizes[i] = bpf_usdt_arg_size(ctx, i);
+	}
+
 	return 0;
 }
 
diff --git a/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c b/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c
index 12034a73ee2d..e96d09e11115 100644
--- a/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c
+++ b/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c
@@ -37,7 +37,7 @@ struct {
 char _license[] SEC("license") = "GPL";
 
 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_dynptr data_ptr, sig_ptr;
 	struct data *data_val;
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_vlan.c b/tools/testing/selftests/bpf/progs/test_xdp_vlan.c
index a7588302268d..a80cc5f2f4f2 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_vlan.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_vlan.c
@@ -102,8 +102,8 @@ bool parse_eth_frame(struct ethhdr *eth, void *data_end, struct parse_pkt *pkt)
 #define TESTVLAN 4011 /* 0xFAB */
 // #define TO_VLAN  4000 /* 0xFA0 (hint 0xOA0 = 160) */
 
-SEC("xdp_drop_vlan_4011")
-int  xdp_prognum0(struct xdp_md *ctx)
+SEC("xdp")
+int xdp_drop_vlan_4011(struct xdp_md *ctx)
 {
 	void *data_end = (void *)(long)ctx->data_end;
 	void *data     = (void *)(long)ctx->data;
@@ -144,8 +144,8 @@ Load prog with ip tool:
 /* Changing VLAN to zero, have same practical effect as removing the VLAN. */
 #define TO_VLAN	0
 
-SEC("xdp_vlan_change")
-int  xdp_prognum1(struct xdp_md *ctx)
+SEC("xdp")
+int xdp_vlan_change(struct xdp_md *ctx)
 {
 	void *data_end = (void *)(long)ctx->data_end;
 	void *data     = (void *)(long)ctx->data;
@@ -178,8 +178,8 @@ int  xdp_prognum1(struct xdp_md *ctx)
 #endif
 #define VLAN_HDR_SZ	4	/* bytes */
 
-SEC("xdp_vlan_remove_outer")
-int  xdp_prognum2(struct xdp_md *ctx)
+SEC("xdp")
+int xdp_vlan_remove_outer(struct xdp_md *ctx)
 {
 	void *data_end = (void *)(long)ctx->data_end;
 	void *data     = (void *)(long)ctx->data;
@@ -224,8 +224,8 @@ void shift_mac_4bytes_32bit(void *data)
 	p[1] = p[0];
 }
 
-SEC("xdp_vlan_remove_outer2")
-int  xdp_prognum3(struct xdp_md *ctx)
+SEC("xdp")
+int xdp_vlan_remove_outer2(struct xdp_md *ctx)
 {
 	void *data_end = (void *)(long)ctx->data_end;
 	void *data     = (void *)(long)ctx->data;
@@ -254,8 +254,8 @@ int  xdp_prognum3(struct xdp_md *ctx)
  * The TC-clsact eBPF programs (currently) need to be attach via TC commands
  */
 
-SEC("tc_vlan_push")
-int _tc_progA(struct __sk_buff *ctx)
+SEC("tc")
+int tc_vlan_push(struct __sk_buff *ctx)
 {
 	bpf_skb_vlan_push(ctx, bpf_htons(ETH_P_8021Q), TESTVLAN);
 
diff --git a/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c b/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c
index 5094c288cfd7..a9be6ae49454 100644
--- a/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c
+++ b/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c
@@ -620,23 +620,61 @@ __naked void helper_call_does_not_prevent_bpf_fastcall(void)
 
 SEC("raw_tp")
 __arch_x86_64
+__log_level(4) __msg("stack depth 24")
+/* may_goto counter at -24 */
+__xlated("0: *(u64 *)(r10 -24) =")
+/* may_goto timestamp at -16 */
+__xlated("1: *(u64 *)(r10 -16) =")
+__xlated("2: r1 = 1")
+__xlated("...")
+__xlated("4: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+/* may_goto expansion starts */
+__xlated("6: r11 = *(u64 *)(r10 -24)")
+__xlated("7: if r11 == 0x0 goto pc+6")
+__xlated("8: r11 -= 1")
+__xlated("9: if r11 != 0x0 goto pc+2")
+__xlated("10: r11 = -24")
+__xlated("11: call unknown")
+__xlated("12: *(u64 *)(r10 -24) = r11")
+/* may_goto expansion ends */
+__xlated("13: *(u64 *)(r10 -8) = r1")
+__xlated("14: exit")
+__success
+__naked void may_goto_interaction_x86_64(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u64 *)(r10 - 16) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 16);"
+	".8byte %[may_goto];"
+	/* just touch some stack at -8 */
+	"*(u64 *)(r10 - 8) = 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("raw_tp")
+__arch_arm64
 __log_level(4) __msg("stack depth 16")
 /* may_goto counter at -16 */
 __xlated("0: *(u64 *)(r10 -16) =")
 __xlated("1: r1 = 1")
-__xlated("...")
-__xlated("3: r0 = &(void __percpu *)(r0)")
-__xlated("...")
+__xlated("2: call bpf_get_smp_processor_id")
 /* may_goto expansion starts */
-__xlated("5: r11 = *(u64 *)(r10 -16)")
-__xlated("6: if r11 == 0x0 goto pc+3")
-__xlated("7: r11 -= 1")
-__xlated("8: *(u64 *)(r10 -16) = r11")
+__xlated("3: r11 = *(u64 *)(r10 -16)")
+__xlated("4: if r11 == 0x0 goto pc+3")
+__xlated("5: r11 -= 1")
+__xlated("6: *(u64 *)(r10 -16) = r11")
 /* may_goto expansion ends */
-__xlated("9: *(u64 *)(r10 -8) = r1")
-__xlated("10: exit")
+__xlated("7: *(u64 *)(r10 -8) = r1")
+__xlated("8: exit")
 __success
-__naked void may_goto_interaction(void)
+__naked void may_goto_interaction_arm64(void)
 {
 	asm volatile (
 	"r1 = 1;"
diff --git a/tools/testing/selftests/bpf/progs/verifier_gotol.c b/tools/testing/selftests/bpf/progs/verifier_gotol.c
index 05a329ee45ee..d5d8f24df394 100644
--- a/tools/testing/selftests/bpf/progs/verifier_gotol.c
+++ b/tools/testing/selftests/bpf/progs/verifier_gotol.c
@@ -4,11 +4,7 @@
 #include <bpf/bpf_helpers.h>
 #include "bpf_misc.h"
 
-#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
+#ifdef CAN_USE_GOTOL
 
 SEC("socket")
 __description("gotol, small_imm")
diff --git a/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c
index e54bb5385bc1..75dd922e4e9f 100644
--- a/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c
+++ b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c
@@ -407,11 +407,7 @@ l0_%=:	call %[bpf_jiffies64];		\
 	: __clobber_all);
 }
 
-#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
+#ifdef CAN_USE_GOTOL
 SEC("socket")
 __success __retval(0)
 __naked void gotol_and_may_goto(void)
diff --git a/tools/testing/selftests/bpf/progs/verifier_load_acquire.c b/tools/testing/selftests/bpf/progs/verifier_load_acquire.c
new file mode 100644
index 000000000000..77698d5a19e4
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_load_acquire.c
@@ -0,0 +1,218 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Google LLC. */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "../../../include/linux/filter.h"
+#include "bpf_misc.h"
+
+#ifdef CAN_USE_LOAD_ACQ_STORE_REL
+
+SEC("socket")
+__description("load-acquire, 8-bit")
+__success __success_unpriv __retval(0x12)
+__naked void load_acquire_8(void)
+{
+	asm volatile (
+	"w1 = 0x12;"
+	"*(u8 *)(r10 - 1) = w1;"
+	".8byte %[load_acquire_insn];" // w0 = load_acquire((u8 *)(r10 - 1));
+	"exit;"
+	:
+	: __imm_insn(load_acquire_insn,
+		     BPF_ATOMIC_OP(BPF_B, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_10, -1))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("load-acquire, 16-bit")
+__success __success_unpriv __retval(0x1234)
+__naked void load_acquire_16(void)
+{
+	asm volatile (
+	"w1 = 0x1234;"
+	"*(u16 *)(r10 - 2) = w1;"
+	".8byte %[load_acquire_insn];" // w0 = load_acquire((u16 *)(r10 - 2));
+	"exit;"
+	:
+	: __imm_insn(load_acquire_insn,
+		     BPF_ATOMIC_OP(BPF_H, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_10, -2))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("load-acquire, 32-bit")
+__success __success_unpriv __retval(0x12345678)
+__naked void load_acquire_32(void)
+{
+	asm volatile (
+	"w1 = 0x12345678;"
+	"*(u32 *)(r10 - 4) = w1;"
+	".8byte %[load_acquire_insn];" // w0 = load_acquire((u32 *)(r10 - 4));
+	"exit;"
+	:
+	: __imm_insn(load_acquire_insn,
+		     BPF_ATOMIC_OP(BPF_W, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_10, -4))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("load-acquire, 64-bit")
+__success __success_unpriv __retval(0x1234567890abcdef)
+__naked void load_acquire_64(void)
+{
+	asm volatile (
+	"r1 = 0x1234567890abcdef ll;"
+	"*(u64 *)(r10 - 8) = r1;"
+	".8byte %[load_acquire_insn];" // r0 = load_acquire((u64 *)(r10 - 8));
+	"exit;"
+	:
+	: __imm_insn(load_acquire_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_10, -8))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("load-acquire with uninitialized src_reg")
+__failure __failure_unpriv __msg("R2 !read_ok")
+__naked void load_acquire_with_uninitialized_src_reg(void)
+{
+	asm volatile (
+	".8byte %[load_acquire_insn];" // r0 = load_acquire((u64 *)(r2 + 0));
+	"exit;"
+	:
+	: __imm_insn(load_acquire_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_2, 0))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("load-acquire with non-pointer src_reg")
+__failure __failure_unpriv __msg("R1 invalid mem access 'scalar'")
+__naked void load_acquire_with_non_pointer_src_reg(void)
+{
+	asm volatile (
+	"r1 = 0;"
+	".8byte %[load_acquire_insn];" // r0 = load_acquire((u64 *)(r1 + 0));
+	"exit;"
+	:
+	: __imm_insn(load_acquire_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_1, 0))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("misaligned load-acquire")
+__failure __failure_unpriv __msg("misaligned stack access off")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void load_acquire_misaligned(void)
+{
+	asm volatile (
+	"r1 = 0;"
+	"*(u64 *)(r10 - 8) = r1;"
+	".8byte %[load_acquire_insn];" // w0 = load_acquire((u32 *)(r10 - 5));
+	"exit;"
+	:
+	: __imm_insn(load_acquire_insn,
+		     BPF_ATOMIC_OP(BPF_W, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_10, -5))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("load-acquire from ctx pointer")
+__failure __failure_unpriv __msg("BPF_ATOMIC loads from R1 ctx is not allowed")
+__naked void load_acquire_from_ctx_pointer(void)
+{
+	asm volatile (
+	".8byte %[load_acquire_insn];" // w0 = load_acquire((u8 *)(r1 + 0));
+	"exit;"
+	:
+	: __imm_insn(load_acquire_insn,
+		     BPF_ATOMIC_OP(BPF_B, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_1, 0))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("load-acquire from pkt pointer")
+__failure __msg("BPF_ATOMIC loads from R2 pkt is not allowed")
+__naked void load_acquire_from_pkt_pointer(void)
+{
+	asm volatile (
+	"r2 = *(u32 *)(r1 + %[xdp_md_data]);"
+	"r3 = *(u32 *)(r1 + %[xdp_md_data_end]);"
+	"r1 = r2;"
+	"r1 += 8;"
+	"if r1 >= r3 goto l0_%=;"
+	".8byte %[load_acquire_insn];" // w0 = load_acquire((u8 *)(r2 + 0));
+"l0_%=:  r0 = 0;"
+	"exit;"
+	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)),
+	  __imm_insn(load_acquire_insn,
+		     BPF_ATOMIC_OP(BPF_B, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_2, 0))
+	: __clobber_all);
+}
+
+SEC("flow_dissector")
+__description("load-acquire from flow_keys pointer")
+__failure __msg("BPF_ATOMIC loads from R2 flow_keys is not allowed")
+__naked void load_acquire_from_flow_keys_pointer(void)
+{
+	asm volatile (
+	"r2 = *(u64 *)(r1 + %[__sk_buff_flow_keys]);"
+	".8byte %[load_acquire_insn];" // w0 = load_acquire((u8 *)(r2 + 0));
+	"exit;"
+	:
+	: __imm_const(__sk_buff_flow_keys,
+		      offsetof(struct __sk_buff, flow_keys)),
+	  __imm_insn(load_acquire_insn,
+		     BPF_ATOMIC_OP(BPF_B, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_2, 0))
+	: __clobber_all);
+}
+
+SEC("sk_reuseport")
+__description("load-acquire from sock pointer")
+__failure __msg("BPF_ATOMIC loads from R2 sock is not allowed")
+__naked void load_acquire_from_sock_pointer(void)
+{
+	asm volatile (
+	"r2 = *(u64 *)(r1 + %[sk_reuseport_md_sk]);"
+	// w0 = load_acquire((u8 *)(r2 + offsetof(struct bpf_sock, family)));
+	".8byte %[load_acquire_insn];"
+	"exit;"
+	:
+	: __imm_const(sk_reuseport_md_sk, offsetof(struct sk_reuseport_md, sk)),
+	  __imm_insn(load_acquire_insn,
+		     BPF_ATOMIC_OP(BPF_B, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_2,
+				   offsetof(struct bpf_sock, family)))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("load-acquire with invalid register R15")
+__failure __failure_unpriv __msg("R15 is invalid")
+__naked void load_acquire_with_invalid_reg(void)
+{
+	asm volatile (
+	".8byte %[load_acquire_insn];" // r0 = load_acquire((u64 *)(r15 + 0));
+	"exit;"
+	:
+	: __imm_insn(load_acquire_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_LOAD_ACQ, BPF_REG_0, 15 /* invalid reg */, 0))
+	: __clobber_all);
+}
+
+#else /* CAN_USE_LOAD_ACQ_STORE_REL */
+
+SEC("socket")
+__description("Clang version < 18, ENABLE_ATOMICS_TESTS not defined, and/or JIT doesn't support load-acquire, use a dummy test")
+__success
+int dummy_test(void)
+{
+	return 0;
+}
+
+#endif /* CAN_USE_LOAD_ACQ_STORE_REL */
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_may_goto_1.c b/tools/testing/selftests/bpf/progs/verifier_may_goto_1.c
index e81097c96fe2..3966d827f288 100644
--- a/tools/testing/selftests/bpf/progs/verifier_may_goto_1.c
+++ b/tools/testing/selftests/bpf/progs/verifier_may_goto_1.c
@@ -69,8 +69,38 @@ __naked void may_goto_batch_1(void)
 }
 
 SEC("raw_tp")
-__description("may_goto batch with offsets 2/0")
+__description("may_goto batch with offsets 2/0 - x86_64")
 __arch_x86_64
+__xlated("0: *(u64 *)(r10 -16) = 65535")
+__xlated("1: *(u64 *)(r10 -8) = 0")
+__xlated("2: r11 = *(u64 *)(r10 -16)")
+__xlated("3: if r11 == 0x0 goto pc+6")
+__xlated("4: r11 -= 1")
+__xlated("5: if r11 != 0x0 goto pc+2")
+__xlated("6: r11 = -16")
+__xlated("7: call unknown")
+__xlated("8: *(u64 *)(r10 -16) = r11")
+__xlated("9: r0 = 1")
+__xlated("10: r0 = 2")
+__xlated("11: exit")
+__success
+__naked void may_goto_batch_2_x86_64(void)
+{
+	asm volatile (
+	".8byte %[may_goto1];"
+	".8byte %[may_goto3];"
+	"r0 = 1;"
+	"r0 = 2;"
+	"exit;"
+	:
+	: __imm_insn(may_goto1, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, 2 /* offset */, 0)),
+	  __imm_insn(may_goto3, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, 0 /* offset */, 0))
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__description("may_goto batch with offsets 2/0 - arm64")
+__arch_arm64
 __xlated("0: *(u64 *)(r10 -8) = 8388608")
 __xlated("1: r11 = *(u64 *)(r10 -8)")
 __xlated("2: if r11 == 0x0 goto pc+3")
@@ -80,7 +110,7 @@ __xlated("5: r0 = 1")
 __xlated("6: r0 = 2")
 __xlated("7: exit")
 __success
-__naked void may_goto_batch_2(void)
+__naked void may_goto_batch_2_arm64(void)
 {
 	asm volatile (
 	".8byte %[may_goto1];"
diff --git a/tools/testing/selftests/bpf/progs/verifier_precision.c b/tools/testing/selftests/bpf/progs/verifier_precision.c
index 6b564d4c0986..6662d4b39969 100644
--- a/tools/testing/selftests/bpf/progs/verifier_precision.c
+++ b/tools/testing/selftests/bpf/progs/verifier_precision.c
@@ -2,6 +2,7 @@
 /* Copyright (C) 2023 SUSE LLC */
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
+#include "../../../include/linux/filter.h"
 #include "bpf_misc.h"
 
 SEC("?raw_tp")
@@ -90,6 +91,54 @@ __naked int bpf_end_bswap(void)
 		::: __clobber_all);
 }
 
+#if defined(ENABLE_ATOMICS_TESTS) && \
+	(defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86))
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r2 stack= before 3: (bf) r3 = r10")
+__msg("mark_precise: frame0: regs=r2 stack= before 2: (db) r2 = load_acquire((u64 *)(r10 -8))")
+__msg("mark_precise: frame0: regs= stack=-8 before 1: (7b) *(u64 *)(r10 -8) = r1")
+__msg("mark_precise: frame0: regs=r1 stack= before 0: (b7) r1 = 8")
+__naked int bpf_load_acquire(void)
+{
+	asm volatile (
+	"r1 = 8;"
+	"*(u64 *)(r10 - 8) = r1;"
+	".8byte %[load_acquire_insn];" /* r2 = load_acquire((u64 *)(r10 - 8)); */
+	"r3 = r10;"
+	"r3 += r2;" /* mark_precise */
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_insn(load_acquire_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_LOAD_ACQ, BPF_REG_2, BPF_REG_10, -8))
+	: __clobber_all);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r1 stack= before 3: (bf) r2 = r10")
+__msg("mark_precise: frame0: regs=r1 stack= before 2: (79) r1 = *(u64 *)(r10 -8)")
+__msg("mark_precise: frame0: regs= stack=-8 before 1: (db) store_release((u64 *)(r10 -8), r1)")
+__msg("mark_precise: frame0: regs=r1 stack= before 0: (b7) r1 = 8")
+__naked int bpf_store_release(void)
+{
+	asm volatile (
+	"r1 = 8;"
+	".8byte %[store_release_insn];" /* store_release((u64 *)(r10 - 8), r1); */
+	"r1 = *(u64 *)(r10 - 8);"
+	"r2 = r10;"
+	"r2 += r1;" /* mark_precise */
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_insn(store_release_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_STORE_REL, BPF_REG_10, BPF_REG_1, -8))
+	: __clobber_all);
+}
+
+#endif /* load-acquire, store-release */
 #endif /* v4 instruction */
 
 SEC("?raw_tp")
diff --git a/tools/testing/selftests/bpf/progs/verifier_stack_ptr.c b/tools/testing/selftests/bpf/progs/verifier_stack_ptr.c
index 417c61cd4b19..24aabc6083fd 100644
--- a/tools/testing/selftests/bpf/progs/verifier_stack_ptr.c
+++ b/tools/testing/selftests/bpf/progs/verifier_stack_ptr.c
@@ -481,4 +481,56 @@ l1_%=:	r0 = 42;					\
 	: __clobber_all);
 }
 
+SEC("socket")
+__description("PTR_TO_STACK stack size > 512")
+__failure __msg("invalid write to stack R1 off=-520 size=8")
+__naked void stack_check_size_gt_512(void)
+{
+	asm volatile ("					\
+	r1 = r10;					\
+	r1 += -520;					\
+	r0 = 42;					\
+	*(u64*)(r1 + 0) = r0;				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+#ifdef __BPF_FEATURE_MAY_GOTO
+SEC("socket")
+__description("PTR_TO_STACK stack size 512 with may_goto with jit")
+__load_if_JITed()
+__success __retval(42)
+__naked void stack_check_size_512_with_may_goto_jit(void)
+{
+	asm volatile ("					\
+	r1 = r10;					\
+	r1 += -512;					\
+	r0 = 42;					\
+	*(u32*)(r1 + 0) = r0;				\
+	may_goto l0_%=;					\
+	r2 = 100;					\
+	l0_%=:						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("PTR_TO_STACK stack size 512 with may_goto without jit")
+__load_if_no_JITed()
+__failure __msg("stack size 520(extra 8) is too large")
+__naked void stack_check_size_512_with_may_goto(void)
+{
+	asm volatile ("					\
+	r1 = r10;					\
+	r1 += -512;					\
+	r0 = 42;					\
+	*(u32*)(r1 + 0) = r0;				\
+	may_goto l0_%=;					\
+	r2 = 100;					\
+	l0_%=:						\
+	exit;						\
+"	::: __clobber_all);
+}
+#endif
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_store_release.c b/tools/testing/selftests/bpf/progs/verifier_store_release.c
new file mode 100644
index 000000000000..c0442d5bb049
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_store_release.c
@@ -0,0 +1,286 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Google LLC. */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "../../../include/linux/filter.h"
+#include "bpf_misc.h"
+
+#if __clang_major__ >= 18 && defined(ENABLE_ATOMICS_TESTS) && \
+	(defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86))
+
+SEC("socket")
+__description("store-release, 8-bit")
+__success __success_unpriv __retval(0x12)
+__naked void store_release_8(void)
+{
+	asm volatile (
+	"w1 = 0x12;"
+	".8byte %[store_release_insn];" // store_release((u8 *)(r10 - 1), w1);
+	"w0 = *(u8 *)(r10 - 1);"
+	"exit;"
+	:
+	: __imm_insn(store_release_insn,
+		     BPF_ATOMIC_OP(BPF_B, BPF_STORE_REL, BPF_REG_10, BPF_REG_1, -1))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("store-release, 16-bit")
+__success __success_unpriv __retval(0x1234)
+__naked void store_release_16(void)
+{
+	asm volatile (
+	"w1 = 0x1234;"
+	".8byte %[store_release_insn];" // store_release((u16 *)(r10 - 2), w1);
+	"w0 = *(u16 *)(r10 - 2);"
+	"exit;"
+	:
+	: __imm_insn(store_release_insn,
+		     BPF_ATOMIC_OP(BPF_H, BPF_STORE_REL, BPF_REG_10, BPF_REG_1, -2))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("store-release, 32-bit")
+__success __success_unpriv __retval(0x12345678)
+__naked void store_release_32(void)
+{
+	asm volatile (
+	"w1 = 0x12345678;"
+	".8byte %[store_release_insn];" // store_release((u32 *)(r10 - 4), w1);
+	"w0 = *(u32 *)(r10 - 4);"
+	"exit;"
+	:
+	: __imm_insn(store_release_insn,
+		     BPF_ATOMIC_OP(BPF_W, BPF_STORE_REL, BPF_REG_10, BPF_REG_1, -4))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("store-release, 64-bit")
+__success __success_unpriv __retval(0x1234567890abcdef)
+__naked void store_release_64(void)
+{
+	asm volatile (
+	"r1 = 0x1234567890abcdef ll;"
+	".8byte %[store_release_insn];" // store_release((u64 *)(r10 - 8), r1);
+	"r0 = *(u64 *)(r10 - 8);"
+	"exit;"
+	:
+	: __imm_insn(store_release_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_STORE_REL, BPF_REG_10, BPF_REG_1, -8))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("store-release with uninitialized src_reg")
+__failure __failure_unpriv __msg("R2 !read_ok")
+__naked void store_release_with_uninitialized_src_reg(void)
+{
+	asm volatile (
+	".8byte %[store_release_insn];" // store_release((u64 *)(r10 - 8), r2);
+	"exit;"
+	:
+	: __imm_insn(store_release_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_STORE_REL, BPF_REG_10, BPF_REG_2, -8))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("store-release with uninitialized dst_reg")
+__failure __failure_unpriv __msg("R2 !read_ok")
+__naked void store_release_with_uninitialized_dst_reg(void)
+{
+	asm volatile (
+	"r1 = 0;"
+	".8byte %[store_release_insn];" // store_release((u64 *)(r2 - 8), r1);
+	"exit;"
+	:
+	: __imm_insn(store_release_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_STORE_REL, BPF_REG_2, BPF_REG_1, -8))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("store-release with non-pointer dst_reg")
+__failure __failure_unpriv __msg("R1 invalid mem access 'scalar'")
+__naked void store_release_with_non_pointer_dst_reg(void)
+{
+	asm volatile (
+	"r1 = 0;"
+	".8byte %[store_release_insn];" // store_release((u64 *)(r1 + 0), r1);
+	"exit;"
+	:
+	: __imm_insn(store_release_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_STORE_REL, BPF_REG_1, BPF_REG_1, 0))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("misaligned store-release")
+__failure __failure_unpriv __msg("misaligned stack access off")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void store_release_misaligned(void)
+{
+	asm volatile (
+	"w0 = 0;"
+	".8byte %[store_release_insn];" // store_release((u32 *)(r10 - 5), w0);
+	"exit;"
+	:
+	: __imm_insn(store_release_insn,
+		     BPF_ATOMIC_OP(BPF_W, BPF_STORE_REL, BPF_REG_10, BPF_REG_0, -5))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("store-release to ctx pointer")
+__failure __failure_unpriv __msg("BPF_ATOMIC stores into R1 ctx is not allowed")
+__naked void store_release_to_ctx_pointer(void)
+{
+	asm volatile (
+	"w0 = 0;"
+	// store_release((u8 *)(r1 + offsetof(struct __sk_buff, cb[0])), w0);
+	".8byte %[store_release_insn];"
+	"exit;"
+	:
+	: __imm_insn(store_release_insn,
+		     BPF_ATOMIC_OP(BPF_B, BPF_STORE_REL, BPF_REG_1, BPF_REG_0,
+				   offsetof(struct __sk_buff, cb[0])))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("store-release to pkt pointer")
+__failure __msg("BPF_ATOMIC stores into R2 pkt is not allowed")
+__naked void store_release_to_pkt_pointer(void)
+{
+	asm volatile (
+	"w0 = 0;"
+	"r2 = *(u32 *)(r1 + %[xdp_md_data]);"
+	"r3 = *(u32 *)(r1 + %[xdp_md_data_end]);"
+	"r1 = r2;"
+	"r1 += 8;"
+	"if r1 >= r3 goto l0_%=;"
+	".8byte %[store_release_insn];" // store_release((u8 *)(r2 + 0), w0);
+"l0_%=:  r0 = 0;"
+	"exit;"
+	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)),
+	  __imm_insn(store_release_insn,
+		     BPF_ATOMIC_OP(BPF_B, BPF_STORE_REL, BPF_REG_2, BPF_REG_0, 0))
+	: __clobber_all);
+}
+
+SEC("flow_dissector")
+__description("store-release to flow_keys pointer")
+__failure __msg("BPF_ATOMIC stores into R2 flow_keys is not allowed")
+__naked void store_release_to_flow_keys_pointer(void)
+{
+	asm volatile (
+	"w0 = 0;"
+	"r2 = *(u64 *)(r1 + %[__sk_buff_flow_keys]);"
+	".8byte %[store_release_insn];" // store_release((u8 *)(r2 + 0), w0);
+	"exit;"
+	:
+	: __imm_const(__sk_buff_flow_keys,
+		      offsetof(struct __sk_buff, flow_keys)),
+	  __imm_insn(store_release_insn,
+		     BPF_ATOMIC_OP(BPF_B, BPF_STORE_REL, BPF_REG_2, BPF_REG_0, 0))
+	: __clobber_all);
+}
+
+SEC("sk_reuseport")
+__description("store-release to sock pointer")
+__failure __msg("R2 cannot write into sock")
+__naked void store_release_to_sock_pointer(void)
+{
+	asm volatile (
+	"w0 = 0;"
+	"r2 = *(u64 *)(r1 + %[sk_reuseport_md_sk]);"
+	".8byte %[store_release_insn];" // store_release((u8 *)(r2 + 0), w0);
+	"exit;"
+	:
+	: __imm_const(sk_reuseport_md_sk, offsetof(struct sk_reuseport_md, sk)),
+	  __imm_insn(store_release_insn,
+		     BPF_ATOMIC_OP(BPF_B, BPF_STORE_REL, BPF_REG_2, BPF_REG_0, 0))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("store-release, leak pointer to stack")
+__success __success_unpriv __retval(0)
+__naked void store_release_leak_pointer_to_stack(void)
+{
+	asm volatile (
+	".8byte %[store_release_insn];" // store_release((u64 *)(r10 - 8), r1);
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_insn(store_release_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_STORE_REL, BPF_REG_10, BPF_REG_1, -8))
+	: __clobber_all);
+}
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, long long);
+	__type(value, long long);
+} map_hash_8b SEC(".maps");
+
+SEC("socket")
+__description("store-release, leak pointer to map")
+__success __retval(0)
+__failure_unpriv __msg_unpriv("R6 leaks addr into map")
+__naked void store_release_leak_pointer_to_map(void)
+{
+	asm volatile (
+	"r6 = r1;"
+	"r1 = %[map_hash_8b] ll;"
+	"r2 = 0;"
+	"*(u64 *)(r10 - 8) = r2;"
+	"r2 = r10;"
+	"r2 += -8;"
+	"call %[bpf_map_lookup_elem];"
+	"if r0 == 0 goto l0_%=;"
+	".8byte %[store_release_insn];" // store_release((u64 *)(r0 + 0), r6);
+"l0_%=:"
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_addr(map_hash_8b),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_insn(store_release_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_STORE_REL, BPF_REG_0, BPF_REG_6, 0))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("store-release with invalid register R15")
+__failure __failure_unpriv __msg("R15 is invalid")
+__naked void store_release_with_invalid_reg(void)
+{
+	asm volatile (
+	".8byte %[store_release_insn];" // store_release((u64 *)(r15 + 0), r1);
+	"exit;"
+	:
+	: __imm_insn(store_release_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_STORE_REL, 15 /* invalid reg */, BPF_REG_1, 0))
+	: __clobber_all);
+}
+
+#else
+
+SEC("socket")
+__description("Clang version < 18, ENABLE_ATOMICS_TESTS not defined, and/or JIT doesn't support store-release, use a dummy test")
+__success
+int dummy_test(void)
+{
+	return 0;
+}
+
+#endif
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/xdp_redirect_map.c b/tools/testing/selftests/bpf/progs/xdp_redirect_map.c
index 682dda8dabbc..50c8958f94e5 100644
--- a/tools/testing/selftests/bpf/progs/xdp_redirect_map.c
+++ b/tools/testing/selftests/bpf/progs/xdp_redirect_map.c
@@ -1,7 +1,10 @@
 // SPDX-License-Identifier: GPL-2.0
 
+#include <linux/if_ether.h>
+
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
 
 struct {
 	__uint(type, BPF_MAP_TYPE_DEVMAP);
@@ -28,4 +31,89 @@ int xdp_redirect_map_2(struct xdp_md *xdp)
 	return bpf_redirect_map(&tx_port, 2, 0);
 }
 
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 3);
+	__type(key, __u32);
+	__type(value, __u64);
+} rxcnt SEC(".maps");
+
+static int xdp_count(struct xdp_md *xdp, __u32 key)
+{
+	void *data_end = (void *)(long)xdp->data_end;
+	void *data = (void *)(long)xdp->data;
+	struct ethhdr *eth = data;
+	__u64 *count;
+
+	if (data + sizeof(*eth) > data_end)
+		return XDP_DROP;
+
+	if (bpf_htons(eth->h_proto) == ETH_P_IP) {
+		/* We only count IPv4 packets */
+		count = bpf_map_lookup_elem(&rxcnt, &key);
+		if (count)
+			*count += 1;
+	}
+
+	return XDP_PASS;
+}
+
+SEC("xdp")
+int xdp_count_0(struct xdp_md *xdp)
+{
+	return xdp_count(xdp, 0);
+}
+
+SEC("xdp")
+int xdp_count_1(struct xdp_md *xdp)
+{
+	return xdp_count(xdp, 1);
+}
+
+SEC("xdp")
+int xdp_count_2(struct xdp_md *xdp)
+{
+	return xdp_count(xdp, 2);
+}
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 2);
+	__type(key, __u32);
+	__type(value, __be64);
+} rx_mac SEC(".maps");
+
+static int store_mac(struct xdp_md *xdp, __u32 id)
+{
+	void *data_end = (void *)(long)xdp->data_end;
+	void *data = (void *)(long)xdp->data;
+	struct ethhdr *eth = data;
+	__u32 key = id;
+	__be64 mac = 0;
+
+	if (data + sizeof(*eth) > data_end)
+		return XDP_DROP;
+
+	/* Only store IPv4 MAC to avoid being polluted by IPv6 packets */
+	if (eth->h_proto == bpf_htons(ETH_P_IP)) {
+		__builtin_memcpy(&mac, eth->h_source, ETH_ALEN);
+		bpf_map_update_elem(&rx_mac, &key, &mac, 0);
+		bpf_printk("%s - %x", __func__, mac);
+	}
+
+	return XDP_PASS;
+}
+
+SEC("xdp")
+int store_mac_1(struct xdp_md *xdp)
+{
+	return store_mac(xdp, 0);
+}
+
+SEC("xdp")
+int store_mac_2(struct xdp_md *xdp)
+{
+	return store_mac(xdp, 1);
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c b/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c
index 97b26a30b59a..bc2945ed8a80 100644
--- a/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c
+++ b/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c
@@ -34,6 +34,14 @@ struct {
 	__uint(max_entries, 128);
 } mac_map SEC(".maps");
 
+/* map to store redirect flags for each protocol*/
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, __u16);
+	__type(value, __u64);
+	__uint(max_entries, 16);
+} redirect_flags SEC(".maps");
+
 SEC("xdp")
 int xdp_redirect_map_multi_prog(struct xdp_md *ctx)
 {
@@ -41,25 +49,34 @@ int xdp_redirect_map_multi_prog(struct xdp_md *ctx)
 	void *data = (void *)(long)ctx->data;
 	int if_index = ctx->ingress_ifindex;
 	struct ethhdr *eth = data;
+	__u64 *flags_from_map;
 	__u16 h_proto;
 	__u64 nh_off;
+	__u64 flags;
 
 	nh_off = sizeof(*eth);
 	if (data + nh_off > data_end)
 		return XDP_DROP;
 
-	h_proto = eth->h_proto;
-
-	/* Using IPv4 for (BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS) testing */
-	if (h_proto == bpf_htons(ETH_P_IP))
-		return bpf_redirect_map(&map_all, 0,
-					BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS);
-	/* Using IPv6 for none flag testing */
-	else if (h_proto == bpf_htons(ETH_P_IPV6))
-		return bpf_redirect_map(&map_all, if_index, 0);
-	/* All others for BPF_F_BROADCAST testing */
-	else
-		return bpf_redirect_map(&map_all, 0, BPF_F_BROADCAST);
+	h_proto = bpf_htons(eth->h_proto);
+
+	flags_from_map = bpf_map_lookup_elem(&redirect_flags, &h_proto);
+
+	/* Default flags for IPv4 : (BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS) */
+	if (h_proto == ETH_P_IP) {
+		flags = flags_from_map ? *flags_from_map : BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS;
+		return bpf_redirect_map(&map_all, 0, flags);
+	}
+	/* Default flags for IPv6 : 0 */
+	if (h_proto == ETH_P_IPV6) {
+		flags = flags_from_map ? *flags_from_map : 0;
+		return bpf_redirect_map(&map_all, if_index, flags);
+	}
+	/* Default flags for others BPF_F_BROADCAST : 0 */
+	else {
+		flags = flags_from_map ? *flags_from_map : BPF_F_BROADCAST;
+		return bpf_redirect_map(&map_all, 0, flags);
+	}
 }
 
 /* The following 2 progs are for 2nd devmap prog testing */